{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9952, "eval_steps": 500, "global_step": 1638, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.0000000000000003e-07, "loss": 0.8079, "step": 1 }, { "epoch": 0.0, "learning_rate": 8.000000000000001e-07, "loss": 0.7828, "step": 2 }, { "epoch": 0.01, "learning_rate": 1.2000000000000002e-06, "loss": 0.7845, "step": 3 }, { "epoch": 0.01, "learning_rate": 1.6000000000000001e-06, "loss": 0.7802, "step": 4 }, { "epoch": 0.01, "learning_rate": 2.0000000000000003e-06, "loss": 0.7728, "step": 5 }, { "epoch": 0.01, "learning_rate": 2.4000000000000003e-06, "loss": 0.7783, "step": 6 }, { "epoch": 0.01, "learning_rate": 2.8000000000000003e-06, "loss": 0.7707, "step": 7 }, { "epoch": 0.01, "learning_rate": 3.2000000000000003e-06, "loss": 0.7661, "step": 8 }, { "epoch": 0.02, "learning_rate": 3.6000000000000003e-06, "loss": 0.7169, "step": 9 }, { "epoch": 0.02, "learning_rate": 4.000000000000001e-06, "loss": 0.7298, "step": 10 }, { "epoch": 0.02, "learning_rate": 4.4e-06, "loss": 0.7293, "step": 11 }, { "epoch": 0.02, "learning_rate": 4.800000000000001e-06, "loss": 0.6884, "step": 12 }, { "epoch": 0.02, "learning_rate": 5.2e-06, "loss": 0.7098, "step": 13 }, { "epoch": 0.03, "learning_rate": 5.600000000000001e-06, "loss": 0.694, "step": 14 }, { "epoch": 0.03, "learning_rate": 6e-06, "loss": 0.6775, "step": 15 }, { "epoch": 0.03, "learning_rate": 6.4000000000000006e-06, "loss": 0.7008, "step": 16 }, { "epoch": 0.03, "learning_rate": 6.800000000000001e-06, "loss": 0.6801, "step": 17 }, { "epoch": 0.03, "learning_rate": 7.2000000000000005e-06, "loss": 0.706, "step": 18 }, { "epoch": 0.03, "learning_rate": 7.600000000000001e-06, "loss": 0.6867, "step": 19 }, { "epoch": 0.04, "learning_rate": 8.000000000000001e-06, "loss": 0.67, "step": 20 }, { "epoch": 0.04, "learning_rate": 8.400000000000001e-06, "loss": 0.6414, "step": 21 }, { "epoch": 0.04, "learning_rate": 8.8e-06, "loss": 0.6347, "step": 22 }, { "epoch": 0.04, "learning_rate": 9.200000000000002e-06, "loss": 0.681, "step": 23 }, { "epoch": 0.04, "learning_rate": 9.600000000000001e-06, "loss": 0.6419, "step": 24 }, { "epoch": 0.05, "learning_rate": 1e-05, "loss": 0.6479, "step": 25 }, { "epoch": 0.05, "learning_rate": 1.04e-05, "loss": 0.677, "step": 26 }, { "epoch": 0.05, "learning_rate": 1.0800000000000002e-05, "loss": 0.6524, "step": 27 }, { "epoch": 0.05, "learning_rate": 1.1200000000000001e-05, "loss": 0.6438, "step": 28 }, { "epoch": 0.05, "learning_rate": 1.16e-05, "loss": 0.6681, "step": 29 }, { "epoch": 0.05, "learning_rate": 1.2e-05, "loss": 0.6418, "step": 30 }, { "epoch": 0.06, "learning_rate": 1.2400000000000002e-05, "loss": 0.6767, "step": 31 }, { "epoch": 0.06, "learning_rate": 1.2800000000000001e-05, "loss": 0.6286, "step": 32 }, { "epoch": 0.06, "learning_rate": 1.3200000000000002e-05, "loss": 0.6145, "step": 33 }, { "epoch": 0.06, "learning_rate": 1.3600000000000002e-05, "loss": 0.6542, "step": 34 }, { "epoch": 0.06, "learning_rate": 1.4e-05, "loss": 0.6431, "step": 35 }, { "epoch": 0.07, "learning_rate": 1.4400000000000001e-05, "loss": 0.6634, "step": 36 }, { "epoch": 0.07, "learning_rate": 1.48e-05, "loss": 0.6329, "step": 37 }, { "epoch": 0.07, "learning_rate": 1.5200000000000002e-05, "loss": 0.6286, "step": 38 }, { "epoch": 0.07, "learning_rate": 1.5600000000000003e-05, "loss": 0.6587, "step": 39 }, { "epoch": 0.07, "learning_rate": 1.6000000000000003e-05, "loss": 0.6214, "step": 40 }, { "epoch": 0.07, "learning_rate": 1.64e-05, "loss": 0.6435, "step": 41 }, { "epoch": 0.08, "learning_rate": 1.6800000000000002e-05, "loss": 0.6204, "step": 42 }, { "epoch": 0.08, "learning_rate": 1.72e-05, "loss": 0.6182, "step": 43 }, { "epoch": 0.08, "learning_rate": 1.76e-05, "loss": 0.6466, "step": 44 }, { "epoch": 0.08, "learning_rate": 1.8e-05, "loss": 0.6283, "step": 45 }, { "epoch": 0.08, "learning_rate": 1.8400000000000003e-05, "loss": 0.6419, "step": 46 }, { "epoch": 0.09, "learning_rate": 1.88e-05, "loss": 0.5917, "step": 47 }, { "epoch": 0.09, "learning_rate": 1.9200000000000003e-05, "loss": 0.6473, "step": 48 }, { "epoch": 0.09, "learning_rate": 1.9600000000000002e-05, "loss": 0.5984, "step": 49 }, { "epoch": 0.09, "learning_rate": 2e-05, "loss": 0.6266, "step": 50 }, { "epoch": 0.09, "learning_rate": 1.9999980431000962e-05, "loss": 0.592, "step": 51 }, { "epoch": 0.1, "learning_rate": 1.999992172408044e-05, "loss": 0.6053, "step": 52 }, { "epoch": 0.1, "learning_rate": 1.999982387946819e-05, "loss": 0.6411, "step": 53 }, { "epoch": 0.1, "learning_rate": 1.999968689754717e-05, "loss": 0.6284, "step": 54 }, { "epoch": 0.1, "learning_rate": 1.999951077885349e-05, "loss": 0.6482, "step": 55 }, { "epoch": 0.1, "learning_rate": 1.9999295524076455e-05, "loss": 0.6372, "step": 56 }, { "epoch": 0.1, "learning_rate": 1.9999041134058514e-05, "loss": 0.6351, "step": 57 }, { "epoch": 0.11, "learning_rate": 1.999874760979531e-05, "loss": 0.634, "step": 58 }, { "epoch": 0.11, "learning_rate": 1.999841495243563e-05, "loss": 0.6034, "step": 59 }, { "epoch": 0.11, "learning_rate": 1.9998043163281435e-05, "loss": 0.6062, "step": 60 }, { "epoch": 0.11, "learning_rate": 1.999763224378783e-05, "loss": 0.6315, "step": 61 }, { "epoch": 0.11, "learning_rate": 1.999718219556307e-05, "loss": 0.6283, "step": 62 }, { "epoch": 0.12, "learning_rate": 1.999669302036856e-05, "loss": 0.626, "step": 63 }, { "epoch": 0.12, "learning_rate": 1.999616472011883e-05, "loss": 0.6246, "step": 64 }, { "epoch": 0.12, "learning_rate": 1.9995597296881542e-05, "loss": 0.6058, "step": 65 }, { "epoch": 0.12, "learning_rate": 1.9994990752877473e-05, "loss": 0.5862, "step": 66 }, { "epoch": 0.12, "learning_rate": 1.999434509048052e-05, "loss": 0.6235, "step": 67 }, { "epoch": 0.12, "learning_rate": 1.9993660312217674e-05, "loss": 0.5882, "step": 68 }, { "epoch": 0.13, "learning_rate": 1.999293642076902e-05, "loss": 0.633, "step": 69 }, { "epoch": 0.13, "learning_rate": 1.999217341896772e-05, "loss": 0.5946, "step": 70 }, { "epoch": 0.13, "learning_rate": 1.9991371309800024e-05, "loss": 0.6311, "step": 71 }, { "epoch": 0.13, "learning_rate": 1.999053009640521e-05, "loss": 0.6261, "step": 72 }, { "epoch": 0.13, "learning_rate": 1.998964978207563e-05, "loss": 0.6138, "step": 73 }, { "epoch": 0.14, "learning_rate": 1.9988730370256654e-05, "loss": 0.6095, "step": 74 }, { "epoch": 0.14, "learning_rate": 1.9987771864546677e-05, "loss": 0.6492, "step": 75 }, { "epoch": 0.14, "learning_rate": 1.9986774268697098e-05, "loss": 0.586, "step": 76 }, { "epoch": 0.14, "learning_rate": 1.9985737586612307e-05, "loss": 0.5801, "step": 77 }, { "epoch": 0.14, "learning_rate": 1.998466182234967e-05, "loss": 0.6112, "step": 78 }, { "epoch": 0.14, "learning_rate": 1.998354698011951e-05, "loss": 0.6219, "step": 79 }, { "epoch": 0.15, "learning_rate": 1.9982393064285106e-05, "loss": 0.6038, "step": 80 }, { "epoch": 0.15, "learning_rate": 1.9981200079362645e-05, "loss": 0.6138, "step": 81 }, { "epoch": 0.15, "learning_rate": 1.997996803002123e-05, "loss": 0.6318, "step": 82 }, { "epoch": 0.15, "learning_rate": 1.997869692108286e-05, "loss": 0.6058, "step": 83 }, { "epoch": 0.15, "learning_rate": 1.99773867575224e-05, "loss": 0.6175, "step": 84 }, { "epoch": 0.16, "learning_rate": 1.997603754446757e-05, "loss": 0.5948, "step": 85 }, { "epoch": 0.16, "learning_rate": 1.997464928719892e-05, "loss": 0.5982, "step": 86 }, { "epoch": 0.16, "learning_rate": 1.9973221991149804e-05, "loss": 0.6268, "step": 87 }, { "epoch": 0.16, "learning_rate": 1.9971755661906376e-05, "loss": 0.5966, "step": 88 }, { "epoch": 0.16, "learning_rate": 1.9970250305207557e-05, "loss": 0.5967, "step": 89 }, { "epoch": 0.16, "learning_rate": 1.9968705926945015e-05, "loss": 0.6143, "step": 90 }, { "epoch": 0.17, "learning_rate": 1.996712253316313e-05, "loss": 0.6139, "step": 91 }, { "epoch": 0.17, "learning_rate": 1.9965500130058996e-05, "loss": 0.5995, "step": 92 }, { "epoch": 0.17, "learning_rate": 1.9963838723982368e-05, "loss": 0.5798, "step": 93 }, { "epoch": 0.17, "learning_rate": 1.9962138321435658e-05, "loss": 0.607, "step": 94 }, { "epoch": 0.17, "learning_rate": 1.99603989290739e-05, "loss": 0.6157, "step": 95 }, { "epoch": 0.18, "learning_rate": 1.9958620553704737e-05, "loss": 0.643, "step": 96 }, { "epoch": 0.18, "learning_rate": 1.9956803202288358e-05, "loss": 0.6246, "step": 97 }, { "epoch": 0.18, "learning_rate": 1.9954946881937525e-05, "loss": 0.6213, "step": 98 }, { "epoch": 0.18, "learning_rate": 1.99530515999175e-05, "loss": 0.5969, "step": 99 }, { "epoch": 0.18, "learning_rate": 1.9951117363646036e-05, "loss": 0.6109, "step": 100 }, { "epoch": 0.18, "learning_rate": 1.994914418069335e-05, "loss": 0.6268, "step": 101 }, { "epoch": 0.19, "learning_rate": 1.9947132058782082e-05, "loss": 0.5923, "step": 102 }, { "epoch": 0.19, "learning_rate": 1.994508100578728e-05, "loss": 0.6107, "step": 103 }, { "epoch": 0.19, "learning_rate": 1.9942991029736346e-05, "loss": 0.6048, "step": 104 }, { "epoch": 0.19, "learning_rate": 1.9940862138809036e-05, "loss": 0.6215, "step": 105 }, { "epoch": 0.19, "learning_rate": 1.9938694341337398e-05, "loss": 0.614, "step": 106 }, { "epoch": 0.2, "learning_rate": 1.993648764580576e-05, "loss": 0.5971, "step": 107 }, { "epoch": 0.2, "learning_rate": 1.993424206085068e-05, "loss": 0.6248, "step": 108 }, { "epoch": 0.2, "learning_rate": 1.993195759526094e-05, "loss": 0.612, "step": 109 }, { "epoch": 0.2, "learning_rate": 1.9929634257977467e-05, "loss": 0.6018, "step": 110 }, { "epoch": 0.2, "learning_rate": 1.992727205809335e-05, "loss": 0.5908, "step": 111 }, { "epoch": 0.2, "learning_rate": 1.992487100485376e-05, "loss": 0.6068, "step": 112 }, { "epoch": 0.21, "learning_rate": 1.9922431107655942e-05, "loss": 0.6192, "step": 113 }, { "epoch": 0.21, "learning_rate": 1.991995237604916e-05, "loss": 0.5977, "step": 114 }, { "epoch": 0.21, "learning_rate": 1.991743481973468e-05, "loss": 0.6301, "step": 115 }, { "epoch": 0.21, "learning_rate": 1.9914878448565712e-05, "loss": 0.604, "step": 116 }, { "epoch": 0.21, "learning_rate": 1.991228327254738e-05, "loss": 0.5903, "step": 117 }, { "epoch": 0.22, "learning_rate": 1.9909649301836675e-05, "loss": 0.5724, "step": 118 }, { "epoch": 0.22, "learning_rate": 1.9906976546742443e-05, "loss": 0.5983, "step": 119 }, { "epoch": 0.22, "learning_rate": 1.990426501772531e-05, "loss": 0.6081, "step": 120 }, { "epoch": 0.22, "learning_rate": 1.990151472539765e-05, "loss": 0.6154, "step": 121 }, { "epoch": 0.22, "learning_rate": 1.989872568052357e-05, "loss": 0.6173, "step": 122 }, { "epoch": 0.22, "learning_rate": 1.9895897894018822e-05, "loss": 0.6004, "step": 123 }, { "epoch": 0.23, "learning_rate": 1.98930313769508e-05, "loss": 0.6188, "step": 124 }, { "epoch": 0.23, "learning_rate": 1.9890126140538476e-05, "loss": 0.5958, "step": 125 }, { "epoch": 0.23, "learning_rate": 1.988718219615237e-05, "loss": 0.6109, "step": 126 }, { "epoch": 0.23, "learning_rate": 1.9884199555314484e-05, "loss": 0.6114, "step": 127 }, { "epoch": 0.23, "learning_rate": 1.9881178229698278e-05, "loss": 0.5804, "step": 128 }, { "epoch": 0.24, "learning_rate": 1.987811823112862e-05, "loss": 0.6244, "step": 129 }, { "epoch": 0.24, "learning_rate": 1.987501957158173e-05, "loss": 0.5762, "step": 130 }, { "epoch": 0.24, "learning_rate": 1.9871882263185137e-05, "loss": 0.5868, "step": 131 }, { "epoch": 0.24, "learning_rate": 1.9868706318217645e-05, "loss": 0.6118, "step": 132 }, { "epoch": 0.24, "learning_rate": 1.986549174910926e-05, "loss": 0.6156, "step": 133 }, { "epoch": 0.25, "learning_rate": 1.9862238568441166e-05, "loss": 0.6046, "step": 134 }, { "epoch": 0.25, "learning_rate": 1.985894678894566e-05, "loss": 0.6137, "step": 135 }, { "epoch": 0.25, "learning_rate": 1.9855616423506106e-05, "loss": 0.5729, "step": 136 }, { "epoch": 0.25, "learning_rate": 1.9852247485156892e-05, "loss": 0.5827, "step": 137 }, { "epoch": 0.25, "learning_rate": 1.9848839987083366e-05, "loss": 0.6024, "step": 138 }, { "epoch": 0.25, "learning_rate": 1.9845393942621793e-05, "loss": 0.6106, "step": 139 }, { "epoch": 0.26, "learning_rate": 1.98419093652593e-05, "loss": 0.5903, "step": 140 }, { "epoch": 0.26, "learning_rate": 1.983838626863383e-05, "loss": 0.5913, "step": 141 }, { "epoch": 0.26, "learning_rate": 1.9834824666534073e-05, "loss": 0.5789, "step": 142 }, { "epoch": 0.26, "learning_rate": 1.9831224572899424e-05, "loss": 0.5984, "step": 143 }, { "epoch": 0.26, "learning_rate": 1.9827586001819933e-05, "loss": 0.6024, "step": 144 }, { "epoch": 0.27, "learning_rate": 1.9823908967536242e-05, "loss": 0.6001, "step": 145 }, { "epoch": 0.27, "learning_rate": 1.9820193484439523e-05, "loss": 0.5916, "step": 146 }, { "epoch": 0.27, "learning_rate": 1.981643956707143e-05, "loss": 0.5942, "step": 147 }, { "epoch": 0.27, "learning_rate": 1.981264723012405e-05, "loss": 0.5926, "step": 148 }, { "epoch": 0.27, "learning_rate": 1.9808816488439834e-05, "loss": 0.5747, "step": 149 }, { "epoch": 0.27, "learning_rate": 1.9804947357011525e-05, "loss": 0.5834, "step": 150 }, { "epoch": 0.28, "learning_rate": 1.980103985098214e-05, "loss": 0.6075, "step": 151 }, { "epoch": 0.28, "learning_rate": 1.9797093985644866e-05, "loss": 0.6352, "step": 152 }, { "epoch": 0.28, "learning_rate": 1.979310977644304e-05, "loss": 0.5982, "step": 153 }, { "epoch": 0.28, "learning_rate": 1.9789087238970056e-05, "loss": 0.6055, "step": 154 }, { "epoch": 0.28, "learning_rate": 1.9785026388969316e-05, "loss": 0.5945, "step": 155 }, { "epoch": 0.29, "learning_rate": 1.978092724233418e-05, "loss": 0.6098, "step": 156 }, { "epoch": 0.29, "learning_rate": 1.9776789815107882e-05, "loss": 0.6038, "step": 157 }, { "epoch": 0.29, "learning_rate": 1.9772614123483488e-05, "loss": 0.6047, "step": 158 }, { "epoch": 0.29, "learning_rate": 1.9768400183803814e-05, "loss": 0.5774, "step": 159 }, { "epoch": 0.29, "learning_rate": 1.9764148012561384e-05, "loss": 0.6083, "step": 160 }, { "epoch": 0.29, "learning_rate": 1.9759857626398336e-05, "loss": 0.6183, "step": 161 }, { "epoch": 0.3, "learning_rate": 1.9755529042106394e-05, "loss": 0.5771, "step": 162 }, { "epoch": 0.3, "learning_rate": 1.975116227662676e-05, "loss": 0.6356, "step": 163 }, { "epoch": 0.3, "learning_rate": 1.974675734705008e-05, "loss": 0.5723, "step": 164 }, { "epoch": 0.3, "learning_rate": 1.9742314270616375e-05, "loss": 0.584, "step": 165 }, { "epoch": 0.3, "learning_rate": 1.973783306471495e-05, "loss": 0.5755, "step": 166 }, { "epoch": 0.31, "learning_rate": 1.973331374688435e-05, "loss": 0.6151, "step": 167 }, { "epoch": 0.31, "learning_rate": 1.972875633481228e-05, "loss": 0.5881, "step": 168 }, { "epoch": 0.31, "learning_rate": 1.9724160846335535e-05, "loss": 0.5915, "step": 169 }, { "epoch": 0.31, "learning_rate": 1.9719527299439944e-05, "loss": 0.6112, "step": 170 }, { "epoch": 0.31, "learning_rate": 1.9714855712260275e-05, "loss": 0.5792, "step": 171 }, { "epoch": 0.31, "learning_rate": 1.971014610308019e-05, "loss": 0.5869, "step": 172 }, { "epoch": 0.32, "learning_rate": 1.9705398490332154e-05, "loss": 0.5925, "step": 173 }, { "epoch": 0.32, "learning_rate": 1.9700612892597376e-05, "loss": 0.5889, "step": 174 }, { "epoch": 0.32, "learning_rate": 1.9695789328605722e-05, "loss": 0.5877, "step": 175 }, { "epoch": 0.32, "learning_rate": 1.969092781723566e-05, "loss": 0.5891, "step": 176 }, { "epoch": 0.32, "learning_rate": 1.968602837751417e-05, "loss": 0.6091, "step": 177 }, { "epoch": 0.33, "learning_rate": 1.968109102861668e-05, "loss": 0.6106, "step": 178 }, { "epoch": 0.33, "learning_rate": 1.9676115789866982e-05, "loss": 0.616, "step": 179 }, { "epoch": 0.33, "learning_rate": 1.9671102680737172e-05, "loss": 0.6002, "step": 180 }, { "epoch": 0.33, "learning_rate": 1.9666051720847546e-05, "loss": 0.6018, "step": 181 }, { "epoch": 0.33, "learning_rate": 1.9660962929966553e-05, "loss": 0.5887, "step": 182 }, { "epoch": 0.33, "learning_rate": 1.9655836328010708e-05, "loss": 0.6081, "step": 183 }, { "epoch": 0.34, "learning_rate": 1.9650671935044497e-05, "loss": 0.5922, "step": 184 }, { "epoch": 0.34, "learning_rate": 1.9645469771280326e-05, "loss": 0.6012, "step": 185 }, { "epoch": 0.34, "learning_rate": 1.9640229857078417e-05, "loss": 0.6147, "step": 186 }, { "epoch": 0.34, "learning_rate": 1.963495221294675e-05, "loss": 0.5961, "step": 187 }, { "epoch": 0.34, "learning_rate": 1.9629636859540962e-05, "loss": 0.6114, "step": 188 }, { "epoch": 0.35, "learning_rate": 1.9624283817664287e-05, "loss": 0.558, "step": 189 }, { "epoch": 0.35, "learning_rate": 1.9618893108267457e-05, "loss": 0.5626, "step": 190 }, { "epoch": 0.35, "learning_rate": 1.961346475244863e-05, "loss": 0.5684, "step": 191 }, { "epoch": 0.35, "learning_rate": 1.9607998771453306e-05, "loss": 0.5819, "step": 192 }, { "epoch": 0.35, "learning_rate": 1.9602495186674237e-05, "loss": 0.5933, "step": 193 }, { "epoch": 0.35, "learning_rate": 1.9596954019651354e-05, "loss": 0.5997, "step": 194 }, { "epoch": 0.36, "learning_rate": 1.9591375292071677e-05, "loss": 0.5898, "step": 195 }, { "epoch": 0.36, "learning_rate": 1.9585759025769225e-05, "loss": 0.6317, "step": 196 }, { "epoch": 0.36, "learning_rate": 1.958010524272494e-05, "loss": 0.5999, "step": 197 }, { "epoch": 0.36, "learning_rate": 1.95744139650666e-05, "loss": 0.5931, "step": 198 }, { "epoch": 0.36, "learning_rate": 1.9568685215068726e-05, "loss": 0.5992, "step": 199 }, { "epoch": 0.37, "learning_rate": 1.95629190151525e-05, "loss": 0.6168, "step": 200 }, { "epoch": 0.37, "learning_rate": 1.9557115387885667e-05, "loss": 0.5959, "step": 201 }, { "epoch": 0.37, "learning_rate": 1.955127435598247e-05, "loss": 0.5897, "step": 202 }, { "epoch": 0.37, "learning_rate": 1.9545395942303538e-05, "loss": 0.5889, "step": 203 }, { "epoch": 0.37, "learning_rate": 1.95394801698558e-05, "loss": 0.5823, "step": 204 }, { "epoch": 0.37, "learning_rate": 1.953352706179241e-05, "loss": 0.6082, "step": 205 }, { "epoch": 0.38, "learning_rate": 1.9527536641412637e-05, "loss": 0.5797, "step": 206 }, { "epoch": 0.38, "learning_rate": 1.9521508932161796e-05, "loss": 0.5849, "step": 207 }, { "epoch": 0.38, "learning_rate": 1.951544395763112e-05, "loss": 0.5984, "step": 208 }, { "epoch": 0.38, "learning_rate": 1.9509341741557716e-05, "loss": 0.5976, "step": 209 }, { "epoch": 0.38, "learning_rate": 1.9503202307824433e-05, "loss": 0.5769, "step": 210 }, { "epoch": 0.39, "learning_rate": 1.9497025680459786e-05, "loss": 0.5792, "step": 211 }, { "epoch": 0.39, "learning_rate": 1.949081188363786e-05, "loss": 0.5952, "step": 212 }, { "epoch": 0.39, "learning_rate": 1.9484560941678207e-05, "loss": 0.5986, "step": 213 }, { "epoch": 0.39, "learning_rate": 1.9478272879045764e-05, "loss": 0.5843, "step": 214 }, { "epoch": 0.39, "learning_rate": 1.947194772035075e-05, "loss": 0.5933, "step": 215 }, { "epoch": 0.39, "learning_rate": 1.9465585490348574e-05, "loss": 0.5783, "step": 216 }, { "epoch": 0.4, "learning_rate": 1.9459186213939723e-05, "loss": 0.5939, "step": 217 }, { "epoch": 0.4, "learning_rate": 1.945274991616969e-05, "loss": 0.597, "step": 218 }, { "epoch": 0.4, "learning_rate": 1.944627662222885e-05, "loss": 0.5597, "step": 219 }, { "epoch": 0.4, "learning_rate": 1.9439766357452386e-05, "loss": 0.5595, "step": 220 }, { "epoch": 0.4, "learning_rate": 1.9433219147320166e-05, "loss": 0.608, "step": 221 }, { "epoch": 0.41, "learning_rate": 1.942663501745666e-05, "loss": 0.6106, "step": 222 }, { "epoch": 0.41, "learning_rate": 1.9420013993630843e-05, "loss": 0.5993, "step": 223 }, { "epoch": 0.41, "learning_rate": 1.9413356101756063e-05, "loss": 0.5813, "step": 224 }, { "epoch": 0.41, "learning_rate": 1.940666136788999e-05, "loss": 0.5912, "step": 225 }, { "epoch": 0.41, "learning_rate": 1.9399929818234457e-05, "loss": 0.581, "step": 226 }, { "epoch": 0.42, "learning_rate": 1.939316147913541e-05, "loss": 0.5803, "step": 227 }, { "epoch": 0.42, "learning_rate": 1.9386356377082776e-05, "loss": 0.5895, "step": 228 }, { "epoch": 0.42, "learning_rate": 1.937951453871036e-05, "loss": 0.5689, "step": 229 }, { "epoch": 0.42, "learning_rate": 1.9372635990795744e-05, "loss": 0.6018, "step": 230 }, { "epoch": 0.42, "learning_rate": 1.9365720760260193e-05, "loss": 0.6061, "step": 231 }, { "epoch": 0.42, "learning_rate": 1.935876887416853e-05, "loss": 0.5929, "step": 232 }, { "epoch": 0.43, "learning_rate": 1.9351780359729047e-05, "loss": 0.5928, "step": 233 }, { "epoch": 0.43, "learning_rate": 1.934475524429339e-05, "loss": 0.587, "step": 234 }, { "epoch": 0.43, "learning_rate": 1.9337693555356458e-05, "loss": 0.6007, "step": 235 }, { "epoch": 0.43, "learning_rate": 1.9330595320556286e-05, "loss": 0.5837, "step": 236 }, { "epoch": 0.43, "learning_rate": 1.932346056767394e-05, "loss": 0.5752, "step": 237 }, { "epoch": 0.44, "learning_rate": 1.931628932463342e-05, "loss": 0.6123, "step": 238 }, { "epoch": 0.44, "learning_rate": 1.9309081619501533e-05, "loss": 0.5801, "step": 239 }, { "epoch": 0.44, "learning_rate": 1.9301837480487794e-05, "loss": 0.596, "step": 240 }, { "epoch": 0.44, "learning_rate": 1.929455693594431e-05, "loss": 0.6054, "step": 241 }, { "epoch": 0.44, "learning_rate": 1.9287240014365682e-05, "loss": 0.5945, "step": 242 }, { "epoch": 0.44, "learning_rate": 1.9279886744388875e-05, "loss": 0.5767, "step": 243 }, { "epoch": 0.45, "learning_rate": 1.9272497154793107e-05, "loss": 0.5914, "step": 244 }, { "epoch": 0.45, "learning_rate": 1.926507127449976e-05, "loss": 0.6313, "step": 245 }, { "epoch": 0.45, "learning_rate": 1.925760913257224e-05, "loss": 0.5949, "step": 246 }, { "epoch": 0.45, "learning_rate": 1.9250110758215882e-05, "loss": 0.5606, "step": 247 }, { "epoch": 0.45, "learning_rate": 1.9242576180777816e-05, "loss": 0.5818, "step": 248 }, { "epoch": 0.46, "learning_rate": 1.923500542974687e-05, "loss": 0.5786, "step": 249 }, { "epoch": 0.46, "learning_rate": 1.922739853475345e-05, "loss": 0.5931, "step": 250 }, { "epoch": 0.46, "learning_rate": 1.9219755525569418e-05, "loss": 0.5688, "step": 251 }, { "epoch": 0.46, "learning_rate": 1.921207643210799e-05, "loss": 0.6043, "step": 252 }, { "epoch": 0.46, "learning_rate": 1.9204361284423586e-05, "loss": 0.6096, "step": 253 }, { "epoch": 0.46, "learning_rate": 1.9196610112711763e-05, "loss": 0.5528, "step": 254 }, { "epoch": 0.47, "learning_rate": 1.9188822947309046e-05, "loss": 0.5853, "step": 255 }, { "epoch": 0.47, "learning_rate": 1.918099981869285e-05, "loss": 0.5707, "step": 256 }, { "epoch": 0.47, "learning_rate": 1.9173140757481325e-05, "loss": 0.5716, "step": 257 }, { "epoch": 0.47, "learning_rate": 1.9165245794433272e-05, "loss": 0.6002, "step": 258 }, { "epoch": 0.47, "learning_rate": 1.9157314960447988e-05, "loss": 0.5648, "step": 259 }, { "epoch": 0.48, "learning_rate": 1.9149348286565176e-05, "loss": 0.5971, "step": 260 }, { "epoch": 0.48, "learning_rate": 1.91413458039648e-05, "loss": 0.5905, "step": 261 }, { "epoch": 0.48, "learning_rate": 1.9133307543966976e-05, "loss": 0.5786, "step": 262 }, { "epoch": 0.48, "learning_rate": 1.9125233538031836e-05, "loss": 0.5853, "step": 263 }, { "epoch": 0.48, "learning_rate": 1.9117123817759438e-05, "loss": 0.6005, "step": 264 }, { "epoch": 0.48, "learning_rate": 1.9108978414889595e-05, "loss": 0.569, "step": 265 }, { "epoch": 0.49, "learning_rate": 1.910079736130178e-05, "loss": 0.6134, "step": 266 }, { "epoch": 0.49, "learning_rate": 1.9092580689015007e-05, "loss": 0.5816, "step": 267 }, { "epoch": 0.49, "learning_rate": 1.9084328430187677e-05, "loss": 0.5978, "step": 268 }, { "epoch": 0.49, "learning_rate": 1.907604061711749e-05, "loss": 0.5856, "step": 269 }, { "epoch": 0.49, "learning_rate": 1.906771728224128e-05, "loss": 0.5805, "step": 270 }, { "epoch": 0.5, "learning_rate": 1.9059358458134914e-05, "loss": 0.5881, "step": 271 }, { "epoch": 0.5, "learning_rate": 1.9050964177513158e-05, "loss": 0.5941, "step": 272 }, { "epoch": 0.5, "learning_rate": 1.9042534473229544e-05, "loss": 0.5932, "step": 273 }, { "epoch": 0.5, "learning_rate": 1.903406937827625e-05, "loss": 0.5798, "step": 274 }, { "epoch": 0.5, "learning_rate": 1.902556892578396e-05, "loss": 0.5978, "step": 275 }, { "epoch": 0.5, "learning_rate": 1.9017033149021747e-05, "loss": 0.5805, "step": 276 }, { "epoch": 0.51, "learning_rate": 1.9008462081396924e-05, "loss": 0.5915, "step": 277 }, { "epoch": 0.51, "learning_rate": 1.8999855756454945e-05, "loss": 0.5872, "step": 278 }, { "epoch": 0.51, "learning_rate": 1.8991214207879233e-05, "loss": 0.564, "step": 279 }, { "epoch": 0.51, "learning_rate": 1.898253746949109e-05, "loss": 0.571, "step": 280 }, { "epoch": 0.51, "learning_rate": 1.897382557524952e-05, "loss": 0.5675, "step": 281 }, { "epoch": 0.52, "learning_rate": 1.8965078559251144e-05, "loss": 0.5753, "step": 282 }, { "epoch": 0.52, "learning_rate": 1.8956296455730027e-05, "loss": 0.5819, "step": 283 }, { "epoch": 0.52, "learning_rate": 1.8947479299057562e-05, "loss": 0.5728, "step": 284 }, { "epoch": 0.52, "learning_rate": 1.893862712374234e-05, "loss": 0.5565, "step": 285 }, { "epoch": 0.52, "learning_rate": 1.8929739964430002e-05, "loss": 0.5988, "step": 286 }, { "epoch": 0.52, "learning_rate": 1.8920817855903103e-05, "loss": 0.5909, "step": 287 }, { "epoch": 0.53, "learning_rate": 1.8911860833081e-05, "loss": 0.5718, "step": 288 }, { "epoch": 0.53, "learning_rate": 1.8902868931019683e-05, "loss": 0.5807, "step": 289 }, { "epoch": 0.53, "learning_rate": 1.8893842184911656e-05, "loss": 0.5766, "step": 290 }, { "epoch": 0.53, "learning_rate": 1.8884780630085795e-05, "loss": 0.5602, "step": 291 }, { "epoch": 0.53, "learning_rate": 1.8875684302007215e-05, "loss": 0.5749, "step": 292 }, { "epoch": 0.54, "learning_rate": 1.886655323627712e-05, "loss": 0.5826, "step": 293 }, { "epoch": 0.54, "learning_rate": 1.8857387468632675e-05, "loss": 0.5909, "step": 294 }, { "epoch": 0.54, "learning_rate": 1.884818703494686e-05, "loss": 0.5728, "step": 295 }, { "epoch": 0.54, "learning_rate": 1.8838951971228326e-05, "loss": 0.5622, "step": 296 }, { "epoch": 0.54, "learning_rate": 1.8829682313621268e-05, "loss": 0.5836, "step": 297 }, { "epoch": 0.54, "learning_rate": 1.8820378098405272e-05, "loss": 0.5974, "step": 298 }, { "epoch": 0.55, "learning_rate": 1.8811039361995173e-05, "loss": 0.5754, "step": 299 }, { "epoch": 0.55, "learning_rate": 1.880166614094091e-05, "loss": 0.5675, "step": 300 }, { "epoch": 0.55, "learning_rate": 1.87922584719274e-05, "loss": 0.5901, "step": 301 }, { "epoch": 0.55, "learning_rate": 1.878281639177437e-05, "loss": 0.582, "step": 302 }, { "epoch": 0.55, "learning_rate": 1.8773339937436237e-05, "loss": 0.5656, "step": 303 }, { "epoch": 0.56, "learning_rate": 1.876382914600195e-05, "loss": 0.5803, "step": 304 }, { "epoch": 0.56, "learning_rate": 1.875428405469483e-05, "loss": 0.5909, "step": 305 }, { "epoch": 0.56, "learning_rate": 1.8744704700872463e-05, "loss": 0.5609, "step": 306 }, { "epoch": 0.56, "learning_rate": 1.8735091122026522e-05, "loss": 0.5477, "step": 307 }, { "epoch": 0.56, "learning_rate": 1.8725443355782623e-05, "loss": 0.5823, "step": 308 }, { "epoch": 0.57, "learning_rate": 1.8715761439900203e-05, "loss": 0.5714, "step": 309 }, { "epoch": 0.57, "learning_rate": 1.870604541227233e-05, "loss": 0.5884, "step": 310 }, { "epoch": 0.57, "learning_rate": 1.86962953109256e-05, "loss": 0.5589, "step": 311 }, { "epoch": 0.57, "learning_rate": 1.8686511174019956e-05, "loss": 0.5694, "step": 312 }, { "epoch": 0.57, "learning_rate": 1.8676693039848548e-05, "loss": 0.5743, "step": 313 }, { "epoch": 0.57, "learning_rate": 1.866684094683759e-05, "loss": 0.5731, "step": 314 }, { "epoch": 0.58, "learning_rate": 1.86569549335462e-05, "loss": 0.5609, "step": 315 }, { "epoch": 0.58, "learning_rate": 1.864703503866626e-05, "loss": 0.5631, "step": 316 }, { "epoch": 0.58, "learning_rate": 1.8637081301022248e-05, "loss": 0.5614, "step": 317 }, { "epoch": 0.58, "learning_rate": 1.86270937595711e-05, "loss": 0.593, "step": 318 }, { "epoch": 0.58, "learning_rate": 1.8617072453402058e-05, "loss": 0.6037, "step": 319 }, { "epoch": 0.59, "learning_rate": 1.86070174217365e-05, "loss": 0.6023, "step": 320 }, { "epoch": 0.59, "learning_rate": 1.8596928703927816e-05, "loss": 0.5916, "step": 321 }, { "epoch": 0.59, "learning_rate": 1.8586806339461226e-05, "loss": 0.5926, "step": 322 }, { "epoch": 0.59, "learning_rate": 1.8576650367953634e-05, "loss": 0.5685, "step": 323 }, { "epoch": 0.59, "learning_rate": 1.8566460829153484e-05, "loss": 0.5785, "step": 324 }, { "epoch": 0.59, "learning_rate": 1.8556237762940585e-05, "loss": 0.5775, "step": 325 }, { "epoch": 0.6, "learning_rate": 1.8545981209325975e-05, "loss": 0.5783, "step": 326 }, { "epoch": 0.6, "learning_rate": 1.8535691208451757e-05, "loss": 0.5943, "step": 327 }, { "epoch": 0.6, "learning_rate": 1.8525367800590927e-05, "loss": 0.597, "step": 328 }, { "epoch": 0.6, "learning_rate": 1.8515011026147238e-05, "loss": 0.5838, "step": 329 }, { "epoch": 0.6, "learning_rate": 1.8504620925655034e-05, "loss": 0.5721, "step": 330 }, { "epoch": 0.61, "learning_rate": 1.8494197539779083e-05, "loss": 0.5873, "step": 331 }, { "epoch": 0.61, "learning_rate": 1.848374090931444e-05, "loss": 0.5705, "step": 332 }, { "epoch": 0.61, "learning_rate": 1.8473251075186257e-05, "loss": 0.5626, "step": 333 }, { "epoch": 0.61, "learning_rate": 1.8462728078449642e-05, "loss": 0.5775, "step": 334 }, { "epoch": 0.61, "learning_rate": 1.8452171960289506e-05, "loss": 0.5936, "step": 335 }, { "epoch": 0.61, "learning_rate": 1.8441582762020374e-05, "loss": 0.5872, "step": 336 }, { "epoch": 0.62, "learning_rate": 1.8430960525086255e-05, "loss": 0.5848, "step": 337 }, { "epoch": 0.62, "learning_rate": 1.8420305291060457e-05, "loss": 0.5815, "step": 338 }, { "epoch": 0.62, "learning_rate": 1.8409617101645425e-05, "loss": 0.6121, "step": 339 }, { "epoch": 0.62, "learning_rate": 1.83988959986726e-05, "loss": 0.5709, "step": 340 }, { "epoch": 0.62, "learning_rate": 1.8388142024102234e-05, "loss": 0.5965, "step": 341 }, { "epoch": 0.63, "learning_rate": 1.8377355220023223e-05, "loss": 0.5989, "step": 342 }, { "epoch": 0.63, "learning_rate": 1.8366535628652966e-05, "loss": 0.6011, "step": 343 }, { "epoch": 0.63, "learning_rate": 1.8355683292337174e-05, "loss": 0.5804, "step": 344 }, { "epoch": 0.63, "learning_rate": 1.834479825354972e-05, "loss": 0.5699, "step": 345 }, { "epoch": 0.63, "learning_rate": 1.8333880554892466e-05, "loss": 0.5538, "step": 346 }, { "epoch": 0.63, "learning_rate": 1.83229302390951e-05, "loss": 0.5755, "step": 347 }, { "epoch": 0.64, "learning_rate": 1.8311947349014968e-05, "loss": 0.5812, "step": 348 }, { "epoch": 0.64, "learning_rate": 1.8300931927636895e-05, "loss": 0.5754, "step": 349 }, { "epoch": 0.64, "learning_rate": 1.8289884018073042e-05, "loss": 0.5936, "step": 350 }, { "epoch": 0.64, "learning_rate": 1.8278803663562718e-05, "loss": 0.6044, "step": 351 }, { "epoch": 0.64, "learning_rate": 1.82676909074722e-05, "loss": 0.5521, "step": 352 }, { "epoch": 0.65, "learning_rate": 1.8256545793294606e-05, "loss": 0.5978, "step": 353 }, { "epoch": 0.65, "learning_rate": 1.8245368364649675e-05, "loss": 0.5588, "step": 354 }, { "epoch": 0.65, "learning_rate": 1.8234158665283618e-05, "loss": 0.583, "step": 355 }, { "epoch": 0.65, "learning_rate": 1.8222916739068964e-05, "loss": 0.5646, "step": 356 }, { "epoch": 0.65, "learning_rate": 1.8211642630004358e-05, "loss": 0.5844, "step": 357 }, { "epoch": 0.65, "learning_rate": 1.8200336382214406e-05, "loss": 0.5684, "step": 358 }, { "epoch": 0.66, "learning_rate": 1.8188998039949502e-05, "loss": 0.5786, "step": 359 }, { "epoch": 0.66, "learning_rate": 1.8177627647585644e-05, "loss": 0.5932, "step": 360 }, { "epoch": 0.66, "learning_rate": 1.8166225249624266e-05, "loss": 0.5567, "step": 361 }, { "epoch": 0.66, "learning_rate": 1.8154790890692082e-05, "loss": 0.5618, "step": 362 }, { "epoch": 0.66, "learning_rate": 1.8143324615540878e-05, "loss": 0.5652, "step": 363 }, { "epoch": 0.67, "learning_rate": 1.813182646904736e-05, "loss": 0.5642, "step": 364 }, { "epoch": 0.67, "learning_rate": 1.812029649621297e-05, "loss": 0.5469, "step": 365 }, { "epoch": 0.67, "learning_rate": 1.8108734742163717e-05, "loss": 0.5477, "step": 366 }, { "epoch": 0.67, "learning_rate": 1.809714125214999e-05, "loss": 0.5935, "step": 367 }, { "epoch": 0.67, "learning_rate": 1.8085516071546385e-05, "loss": 0.5882, "step": 368 }, { "epoch": 0.67, "learning_rate": 1.807385924585154e-05, "loss": 0.5835, "step": 369 }, { "epoch": 0.68, "learning_rate": 1.8062170820687925e-05, "loss": 0.5568, "step": 370 }, { "epoch": 0.68, "learning_rate": 1.805045084180171e-05, "loss": 0.561, "step": 371 }, { "epoch": 0.68, "learning_rate": 1.803869935506253e-05, "loss": 0.5967, "step": 372 }, { "epoch": 0.68, "learning_rate": 1.8026916406463368e-05, "loss": 0.5683, "step": 373 }, { "epoch": 0.68, "learning_rate": 1.8015102042120314e-05, "loss": 0.567, "step": 374 }, { "epoch": 0.69, "learning_rate": 1.8003256308272434e-05, "loss": 0.5758, "step": 375 }, { "epoch": 0.69, "learning_rate": 1.799137925128155e-05, "loss": 0.5801, "step": 376 }, { "epoch": 0.69, "learning_rate": 1.797947091763209e-05, "loss": 0.5398, "step": 377 }, { "epoch": 0.69, "learning_rate": 1.7967531353930893e-05, "loss": 0.5696, "step": 378 }, { "epoch": 0.69, "learning_rate": 1.795556060690701e-05, "loss": 0.5672, "step": 379 }, { "epoch": 0.69, "learning_rate": 1.7943558723411555e-05, "loss": 0.5797, "step": 380 }, { "epoch": 0.7, "learning_rate": 1.7931525750417497e-05, "loss": 0.5604, "step": 381 }, { "epoch": 0.7, "learning_rate": 1.791946173501948e-05, "loss": 0.5656, "step": 382 }, { "epoch": 0.7, "learning_rate": 1.790736672443365e-05, "loss": 0.579, "step": 383 }, { "epoch": 0.7, "learning_rate": 1.7895240765997455e-05, "loss": 0.551, "step": 384 }, { "epoch": 0.7, "learning_rate": 1.788308390716947e-05, "loss": 0.559, "step": 385 }, { "epoch": 0.71, "learning_rate": 1.7870896195529205e-05, "loss": 0.5617, "step": 386 }, { "epoch": 0.71, "learning_rate": 1.7858677678776923e-05, "loss": 0.5522, "step": 387 }, { "epoch": 0.71, "learning_rate": 1.7846428404733456e-05, "loss": 0.5895, "step": 388 }, { "epoch": 0.71, "learning_rate": 1.7834148421340006e-05, "loss": 0.5826, "step": 389 }, { "epoch": 0.71, "learning_rate": 1.7821837776657968e-05, "loss": 0.5902, "step": 390 }, { "epoch": 0.71, "learning_rate": 1.780949651886875e-05, "loss": 0.5567, "step": 391 }, { "epoch": 0.72, "learning_rate": 1.7797124696273553e-05, "loss": 0.5509, "step": 392 }, { "epoch": 0.72, "learning_rate": 1.7784722357293225e-05, "loss": 0.5516, "step": 393 }, { "epoch": 0.72, "learning_rate": 1.7772289550468033e-05, "loss": 0.5642, "step": 394 }, { "epoch": 0.72, "learning_rate": 1.775982632445749e-05, "loss": 0.5823, "step": 395 }, { "epoch": 0.72, "learning_rate": 1.774733272804017e-05, "loss": 0.5602, "step": 396 }, { "epoch": 0.73, "learning_rate": 1.7734808810113512e-05, "loss": 0.5983, "step": 397 }, { "epoch": 0.73, "learning_rate": 1.772225461969362e-05, "loss": 0.5519, "step": 398 }, { "epoch": 0.73, "learning_rate": 1.7709670205915084e-05, "loss": 0.5914, "step": 399 }, { "epoch": 0.73, "learning_rate": 1.7697055618030777e-05, "loss": 0.5604, "step": 400 }, { "epoch": 0.73, "learning_rate": 1.7684410905411675e-05, "loss": 0.5462, "step": 401 }, { "epoch": 0.74, "learning_rate": 1.7671736117546646e-05, "loss": 0.534, "step": 402 }, { "epoch": 0.74, "learning_rate": 1.765903130404228e-05, "loss": 0.5752, "step": 403 }, { "epoch": 0.74, "learning_rate": 1.7646296514622666e-05, "loss": 0.5551, "step": 404 }, { "epoch": 0.74, "learning_rate": 1.7633531799129227e-05, "loss": 0.5619, "step": 405 }, { "epoch": 0.74, "learning_rate": 1.76207372075205e-05, "loss": 0.5663, "step": 406 }, { "epoch": 0.74, "learning_rate": 1.7607912789871956e-05, "loss": 0.562, "step": 407 }, { "epoch": 0.75, "learning_rate": 1.75950585963758e-05, "loss": 0.5543, "step": 408 }, { "epoch": 0.75, "learning_rate": 1.7582174677340767e-05, "loss": 0.5614, "step": 409 }, { "epoch": 0.75, "learning_rate": 1.7569261083191942e-05, "loss": 0.5856, "step": 410 }, { "epoch": 0.75, "learning_rate": 1.7556317864470543e-05, "loss": 0.6035, "step": 411 }, { "epoch": 0.75, "learning_rate": 1.7543345071833745e-05, "loss": 0.5694, "step": 412 }, { "epoch": 0.76, "learning_rate": 1.7530342756054452e-05, "loss": 0.5486, "step": 413 }, { "epoch": 0.76, "learning_rate": 1.751731096802113e-05, "loss": 0.567, "step": 414 }, { "epoch": 0.76, "learning_rate": 1.7504249758737587e-05, "loss": 0.5631, "step": 415 }, { "epoch": 0.76, "learning_rate": 1.7491159179322785e-05, "loss": 0.5486, "step": 416 }, { "epoch": 0.76, "learning_rate": 1.747803928101062e-05, "loss": 0.5754, "step": 417 }, { "epoch": 0.76, "learning_rate": 1.746489011514976e-05, "loss": 0.5776, "step": 418 }, { "epoch": 0.77, "learning_rate": 1.7451711733203406e-05, "loss": 0.5888, "step": 419 }, { "epoch": 0.77, "learning_rate": 1.7438504186749105e-05, "loss": 0.5417, "step": 420 }, { "epoch": 0.77, "learning_rate": 1.7425267527478543e-05, "loss": 0.5689, "step": 421 }, { "epoch": 0.77, "learning_rate": 1.7412001807197362e-05, "loss": 0.5896, "step": 422 }, { "epoch": 0.77, "learning_rate": 1.7398707077824936e-05, "loss": 0.5549, "step": 423 }, { "epoch": 0.78, "learning_rate": 1.7385383391394174e-05, "loss": 0.5503, "step": 424 }, { "epoch": 0.78, "learning_rate": 1.737203080005131e-05, "loss": 0.5957, "step": 425 }, { "epoch": 0.78, "learning_rate": 1.735864935605572e-05, "loss": 0.5354, "step": 426 }, { "epoch": 0.78, "learning_rate": 1.7345239111779697e-05, "loss": 0.558, "step": 427 }, { "epoch": 0.78, "learning_rate": 1.733180011970825e-05, "loss": 0.5548, "step": 428 }, { "epoch": 0.78, "learning_rate": 1.7318332432438906e-05, "loss": 0.5616, "step": 429 }, { "epoch": 0.79, "learning_rate": 1.7304836102681494e-05, "loss": 0.5659, "step": 430 }, { "epoch": 0.79, "learning_rate": 1.729131118325795e-05, "loss": 0.594, "step": 431 }, { "epoch": 0.79, "learning_rate": 1.72777577271021e-05, "loss": 0.5509, "step": 432 }, { "epoch": 0.79, "learning_rate": 1.726417578725946e-05, "loss": 0.5784, "step": 433 }, { "epoch": 0.79, "learning_rate": 1.7250565416887016e-05, "loss": 0.575, "step": 434 }, { "epoch": 0.8, "learning_rate": 1.7236926669253043e-05, "loss": 0.5795, "step": 435 }, { "epoch": 0.8, "learning_rate": 1.7223259597736863e-05, "loss": 0.5651, "step": 436 }, { "epoch": 0.8, "learning_rate": 1.7209564255828653e-05, "loss": 0.549, "step": 437 }, { "epoch": 0.8, "learning_rate": 1.7195840697129252e-05, "loss": 0.5601, "step": 438 }, { "epoch": 0.8, "learning_rate": 1.718208897534991e-05, "loss": 0.5688, "step": 439 }, { "epoch": 0.8, "learning_rate": 1.716830914431212e-05, "loss": 0.5515, "step": 440 }, { "epoch": 0.81, "learning_rate": 1.715450125794738e-05, "loss": 0.5623, "step": 441 }, { "epoch": 0.81, "learning_rate": 1.7140665370296995e-05, "loss": 0.5534, "step": 442 }, { "epoch": 0.81, "learning_rate": 1.7126801535511854e-05, "loss": 0.5982, "step": 443 }, { "epoch": 0.81, "learning_rate": 1.7112909807852237e-05, "loss": 0.5784, "step": 444 }, { "epoch": 0.81, "learning_rate": 1.709899024168758e-05, "loss": 0.5545, "step": 445 }, { "epoch": 0.82, "learning_rate": 1.7085042891496283e-05, "loss": 0.5658, "step": 446 }, { "epoch": 0.82, "learning_rate": 1.7071067811865477e-05, "loss": 0.5827, "step": 447 }, { "epoch": 0.82, "learning_rate": 1.705706505749083e-05, "loss": 0.5529, "step": 448 }, { "epoch": 0.82, "learning_rate": 1.704303468317632e-05, "loss": 0.5623, "step": 449 }, { "epoch": 0.82, "learning_rate": 1.702897674383402e-05, "loss": 0.5638, "step": 450 }, { "epoch": 0.82, "learning_rate": 1.7014891294483893e-05, "loss": 0.5845, "step": 451 }, { "epoch": 0.83, "learning_rate": 1.7000778390253566e-05, "loss": 0.5605, "step": 452 }, { "epoch": 0.83, "learning_rate": 1.6986638086378124e-05, "loss": 0.5594, "step": 453 }, { "epoch": 0.83, "learning_rate": 1.6972470438199883e-05, "loss": 0.5823, "step": 454 }, { "epoch": 0.83, "learning_rate": 1.6958275501168183e-05, "loss": 0.5924, "step": 455 }, { "epoch": 0.83, "learning_rate": 1.6944053330839164e-05, "loss": 0.5598, "step": 456 }, { "epoch": 0.84, "learning_rate": 1.692980398287555e-05, "loss": 0.5459, "step": 457 }, { "epoch": 0.84, "learning_rate": 1.6915527513046445e-05, "loss": 0.5401, "step": 458 }, { "epoch": 0.84, "learning_rate": 1.690122397722709e-05, "loss": 0.5689, "step": 459 }, { "epoch": 0.84, "learning_rate": 1.6886893431398664e-05, "loss": 0.586, "step": 460 }, { "epoch": 0.84, "learning_rate": 1.6872535931648046e-05, "loss": 0.5453, "step": 461 }, { "epoch": 0.84, "learning_rate": 1.685815153416762e-05, "loss": 0.549, "step": 462 }, { "epoch": 0.85, "learning_rate": 1.6843740295255044e-05, "loss": 0.5612, "step": 463 }, { "epoch": 0.85, "learning_rate": 1.6829302271313012e-05, "loss": 0.5649, "step": 464 }, { "epoch": 0.85, "learning_rate": 1.6814837518849064e-05, "loss": 0.5521, "step": 465 }, { "epoch": 0.85, "learning_rate": 1.680034609447535e-05, "loss": 0.5812, "step": 466 }, { "epoch": 0.85, "learning_rate": 1.6785828054908393e-05, "loss": 0.5477, "step": 467 }, { "epoch": 0.86, "learning_rate": 1.6771283456968905e-05, "loss": 0.5471, "step": 468 }, { "epoch": 0.86, "learning_rate": 1.6756712357581526e-05, "loss": 0.5506, "step": 469 }, { "epoch": 0.86, "learning_rate": 1.674211481377462e-05, "loss": 0.5484, "step": 470 }, { "epoch": 0.86, "learning_rate": 1.6727490882680052e-05, "loss": 0.5591, "step": 471 }, { "epoch": 0.86, "learning_rate": 1.6712840621532963e-05, "loss": 0.5707, "step": 472 }, { "epoch": 0.86, "learning_rate": 1.669816408767154e-05, "loss": 0.5579, "step": 473 }, { "epoch": 0.87, "learning_rate": 1.66834613385368e-05, "loss": 0.5469, "step": 474 }, { "epoch": 0.87, "learning_rate": 1.6668732431672357e-05, "loss": 0.5561, "step": 475 }, { "epoch": 0.87, "learning_rate": 1.6653977424724208e-05, "loss": 0.5755, "step": 476 }, { "epoch": 0.87, "learning_rate": 1.663919637544049e-05, "loss": 0.5522, "step": 477 }, { "epoch": 0.87, "learning_rate": 1.662438934167128e-05, "loss": 0.5507, "step": 478 }, { "epoch": 0.88, "learning_rate": 1.660955638136834e-05, "loss": 0.5565, "step": 479 }, { "epoch": 0.88, "learning_rate": 1.65946975525849e-05, "loss": 0.5865, "step": 480 }, { "epoch": 0.88, "learning_rate": 1.657981291347545e-05, "loss": 0.5546, "step": 481 }, { "epoch": 0.88, "learning_rate": 1.6564902522295484e-05, "loss": 0.5583, "step": 482 }, { "epoch": 0.88, "learning_rate": 1.654996643740129e-05, "loss": 0.5629, "step": 483 }, { "epoch": 0.89, "learning_rate": 1.6535004717249713e-05, "loss": 0.5689, "step": 484 }, { "epoch": 0.89, "learning_rate": 1.6520017420397933e-05, "loss": 0.5913, "step": 485 }, { "epoch": 0.89, "learning_rate": 1.6505004605503227e-05, "loss": 0.556, "step": 486 }, { "epoch": 0.89, "learning_rate": 1.648996633132274e-05, "loss": 0.5533, "step": 487 }, { "epoch": 0.89, "learning_rate": 1.647490265671328e-05, "loss": 0.5738, "step": 488 }, { "epoch": 0.89, "learning_rate": 1.645981364063105e-05, "loss": 0.5692, "step": 489 }, { "epoch": 0.9, "learning_rate": 1.644469934213143e-05, "loss": 0.572, "step": 490 }, { "epoch": 0.9, "learning_rate": 1.642955982036877e-05, "loss": 0.5626, "step": 491 }, { "epoch": 0.9, "learning_rate": 1.641439513459612e-05, "loss": 0.5657, "step": 492 }, { "epoch": 0.9, "learning_rate": 1.6399205344165022e-05, "loss": 0.566, "step": 493 }, { "epoch": 0.9, "learning_rate": 1.6383990508525283e-05, "loss": 0.5658, "step": 494 }, { "epoch": 0.91, "learning_rate": 1.636875068722472e-05, "loss": 0.5354, "step": 495 }, { "epoch": 0.91, "learning_rate": 1.635348593990894e-05, "loss": 0.5572, "step": 496 }, { "epoch": 0.91, "learning_rate": 1.633819632632111e-05, "loss": 0.5348, "step": 497 }, { "epoch": 0.91, "learning_rate": 1.6322881906301724e-05, "loss": 0.5562, "step": 498 }, { "epoch": 0.91, "learning_rate": 1.630754273978834e-05, "loss": 0.5529, "step": 499 }, { "epoch": 0.91, "learning_rate": 1.62921788868154e-05, "loss": 0.5645, "step": 500 }, { "epoch": 0.92, "learning_rate": 1.6276790407513943e-05, "loss": 0.5347, "step": 501 }, { "epoch": 0.92, "learning_rate": 1.6261377362111396e-05, "loss": 0.5566, "step": 502 }, { "epoch": 0.92, "learning_rate": 1.6245939810931336e-05, "loss": 0.5584, "step": 503 }, { "epoch": 0.92, "learning_rate": 1.623047781439324e-05, "loss": 0.5484, "step": 504 }, { "epoch": 0.92, "learning_rate": 1.6214991433012274e-05, "loss": 0.584, "step": 505 }, { "epoch": 0.93, "learning_rate": 1.6199480727399035e-05, "loss": 0.5531, "step": 506 }, { "epoch": 0.93, "learning_rate": 1.6183945758259316e-05, "loss": 0.5728, "step": 507 }, { "epoch": 0.93, "learning_rate": 1.616838658639388e-05, "loss": 0.5342, "step": 508 }, { "epoch": 0.93, "learning_rate": 1.615280327269821e-05, "loss": 0.566, "step": 509 }, { "epoch": 0.93, "learning_rate": 1.6137195878162267e-05, "loss": 0.5672, "step": 510 }, { "epoch": 0.93, "learning_rate": 1.6121564463870285e-05, "loss": 0.6008, "step": 511 }, { "epoch": 0.94, "learning_rate": 1.610590909100048e-05, "loss": 0.5723, "step": 512 }, { "epoch": 0.94, "learning_rate": 1.6090229820824846e-05, "loss": 0.5521, "step": 513 }, { "epoch": 0.94, "learning_rate": 1.6074526714708913e-05, "loss": 0.5584, "step": 514 }, { "epoch": 0.94, "learning_rate": 1.605879983411149e-05, "loss": 0.5813, "step": 515 }, { "epoch": 0.94, "learning_rate": 1.6043049240584445e-05, "loss": 0.5368, "step": 516 }, { "epoch": 0.95, "learning_rate": 1.6027274995772445e-05, "loss": 0.5588, "step": 517 }, { "epoch": 0.95, "learning_rate": 1.6011477161412724e-05, "loss": 0.5642, "step": 518 }, { "epoch": 0.95, "learning_rate": 1.5995655799334845e-05, "loss": 0.5855, "step": 519 }, { "epoch": 0.95, "learning_rate": 1.597981097146045e-05, "loss": 0.5612, "step": 520 }, { "epoch": 0.95, "learning_rate": 1.5963942739803028e-05, "loss": 0.5509, "step": 521 }, { "epoch": 0.95, "learning_rate": 1.594805116646766e-05, "loss": 0.568, "step": 522 }, { "epoch": 0.96, "learning_rate": 1.5932136313650776e-05, "loss": 0.567, "step": 523 }, { "epoch": 0.96, "learning_rate": 1.5916198243639933e-05, "loss": 0.5717, "step": 524 }, { "epoch": 0.96, "learning_rate": 1.590023701881354e-05, "loss": 0.5676, "step": 525 }, { "epoch": 0.96, "learning_rate": 1.5884252701640638e-05, "loss": 0.5679, "step": 526 }, { "epoch": 0.96, "learning_rate": 1.5868245354680642e-05, "loss": 0.5579, "step": 527 }, { "epoch": 0.97, "learning_rate": 1.585221504058311e-05, "loss": 0.5628, "step": 528 }, { "epoch": 0.97, "learning_rate": 1.5836161822087474e-05, "loss": 0.5745, "step": 529 }, { "epoch": 0.97, "learning_rate": 1.5820085762022827e-05, "loss": 0.5609, "step": 530 }, { "epoch": 0.97, "learning_rate": 1.580398692330764e-05, "loss": 0.5385, "step": 531 }, { "epoch": 0.97, "learning_rate": 1.578786536894955e-05, "loss": 0.5622, "step": 532 }, { "epoch": 0.97, "learning_rate": 1.577172116204509e-05, "loss": 0.5523, "step": 533 }, { "epoch": 0.98, "learning_rate": 1.5755554365779458e-05, "loss": 0.5268, "step": 534 }, { "epoch": 0.98, "learning_rate": 1.5739365043426256e-05, "loss": 0.5557, "step": 535 }, { "epoch": 0.98, "learning_rate": 1.572315325834725e-05, "loss": 0.557, "step": 536 }, { "epoch": 0.98, "learning_rate": 1.5706919073992125e-05, "loss": 0.5497, "step": 537 }, { "epoch": 0.98, "learning_rate": 1.5690662553898224e-05, "loss": 0.5465, "step": 538 }, { "epoch": 0.99, "learning_rate": 1.5674383761690316e-05, "loss": 0.5601, "step": 539 }, { "epoch": 0.99, "learning_rate": 1.5658082761080332e-05, "loss": 0.5325, "step": 540 }, { "epoch": 0.99, "learning_rate": 1.5641759615867127e-05, "loss": 0.5747, "step": 541 }, { "epoch": 0.99, "learning_rate": 1.562541438993622e-05, "loss": 0.5634, "step": 542 }, { "epoch": 0.99, "learning_rate": 1.560904714725956e-05, "loss": 0.5313, "step": 543 }, { "epoch": 0.99, "learning_rate": 1.559265795189525e-05, "loss": 0.5649, "step": 544 }, { "epoch": 1.0, "learning_rate": 1.5576246867987324e-05, "loss": 0.5602, "step": 545 }, { "epoch": 1.0, "learning_rate": 1.5559813959765482e-05, "loss": 0.5628, "step": 546 }, { "epoch": 1.0, "learning_rate": 1.554335929154483e-05, "loss": 0.5351, "step": 547 }, { "epoch": 1.0, "learning_rate": 1.5526882927725652e-05, "loss": 0.4116, "step": 548 }, { "epoch": 1.0, "learning_rate": 1.5510384932793132e-05, "loss": 0.3934, "step": 549 }, { "epoch": 1.01, "learning_rate": 1.5493865371317125e-05, "loss": 0.3794, "step": 550 }, { "epoch": 1.01, "learning_rate": 1.5477324307951883e-05, "loss": 0.4035, "step": 551 }, { "epoch": 1.01, "learning_rate": 1.5460761807435817e-05, "loss": 0.3856, "step": 552 }, { "epoch": 1.01, "learning_rate": 1.5444177934591242e-05, "loss": 0.3793, "step": 553 }, { "epoch": 1.01, "learning_rate": 1.542757275432411e-05, "loss": 0.3793, "step": 554 }, { "epoch": 1.01, "learning_rate": 1.541094633162378e-05, "loss": 0.4176, "step": 555 }, { "epoch": 1.02, "learning_rate": 1.5394298731562736e-05, "loss": 0.3934, "step": 556 }, { "epoch": 1.02, "learning_rate": 1.5377630019296358e-05, "loss": 0.3836, "step": 557 }, { "epoch": 1.02, "learning_rate": 1.536094026006264e-05, "loss": 0.3855, "step": 558 }, { "epoch": 1.02, "learning_rate": 1.5344229519181964e-05, "loss": 0.3732, "step": 559 }, { "epoch": 1.02, "learning_rate": 1.5327497862056825e-05, "loss": 0.384, "step": 560 }, { "epoch": 1.03, "learning_rate": 1.5310745354171576e-05, "loss": 0.3938, "step": 561 }, { "epoch": 1.03, "learning_rate": 1.5293972061092187e-05, "loss": 0.3776, "step": 562 }, { "epoch": 1.03, "learning_rate": 1.5277178048465958e-05, "loss": 0.3957, "step": 563 }, { "epoch": 1.03, "learning_rate": 1.52603633820213e-05, "loss": 0.36, "step": 564 }, { "epoch": 1.03, "learning_rate": 1.524352812756745e-05, "loss": 0.3807, "step": 565 }, { "epoch": 1.03, "learning_rate": 1.5226672350994222e-05, "loss": 0.3937, "step": 566 }, { "epoch": 1.04, "learning_rate": 1.5209796118271753e-05, "loss": 0.3751, "step": 567 }, { "epoch": 1.04, "learning_rate": 1.5192899495450237e-05, "loss": 0.3935, "step": 568 }, { "epoch": 1.04, "learning_rate": 1.5175982548659675e-05, "loss": 0.3704, "step": 569 }, { "epoch": 1.04, "learning_rate": 1.5159045344109613e-05, "loss": 0.3622, "step": 570 }, { "epoch": 1.04, "learning_rate": 1.5142087948088873e-05, "loss": 0.3732, "step": 571 }, { "epoch": 1.05, "learning_rate": 1.512511042696531e-05, "loss": 0.3859, "step": 572 }, { "epoch": 1.05, "learning_rate": 1.5108112847185545e-05, "loss": 0.3515, "step": 573 }, { "epoch": 1.05, "learning_rate": 1.5091095275274701e-05, "loss": 0.3677, "step": 574 }, { "epoch": 1.05, "learning_rate": 1.5074057777836148e-05, "loss": 0.3912, "step": 575 }, { "epoch": 1.05, "learning_rate": 1.505700042155124e-05, "loss": 0.3717, "step": 576 }, { "epoch": 1.06, "learning_rate": 1.5039923273179055e-05, "loss": 0.3761, "step": 577 }, { "epoch": 1.06, "learning_rate": 1.5022826399556135e-05, "loss": 0.3749, "step": 578 }, { "epoch": 1.06, "learning_rate": 1.5005709867596216e-05, "loss": 0.3833, "step": 579 }, { "epoch": 1.06, "learning_rate": 1.498857374428998e-05, "loss": 0.3908, "step": 580 }, { "epoch": 1.06, "learning_rate": 1.4971418096704784e-05, "loss": 0.3764, "step": 581 }, { "epoch": 1.06, "learning_rate": 1.4954242991984398e-05, "loss": 0.3663, "step": 582 }, { "epoch": 1.07, "learning_rate": 1.4937048497348743e-05, "loss": 0.3787, "step": 583 }, { "epoch": 1.07, "learning_rate": 1.4919834680093628e-05, "loss": 0.3826, "step": 584 }, { "epoch": 1.07, "learning_rate": 1.4902601607590489e-05, "loss": 0.3784, "step": 585 }, { "epoch": 1.07, "learning_rate": 1.4885349347286118e-05, "loss": 0.386, "step": 586 }, { "epoch": 1.07, "learning_rate": 1.4868077966702414e-05, "loss": 0.3729, "step": 587 }, { "epoch": 1.08, "learning_rate": 1.4850787533436101e-05, "loss": 0.377, "step": 588 }, { "epoch": 1.08, "learning_rate": 1.4833478115158472e-05, "loss": 0.4029, "step": 589 }, { "epoch": 1.08, "learning_rate": 1.4816149779615128e-05, "loss": 0.376, "step": 590 }, { "epoch": 1.08, "learning_rate": 1.47988025946257e-05, "loss": 0.3731, "step": 591 }, { "epoch": 1.08, "learning_rate": 1.4781436628083601e-05, "loss": 0.3813, "step": 592 }, { "epoch": 1.08, "learning_rate": 1.4764051947955746e-05, "loss": 0.3864, "step": 593 }, { "epoch": 1.09, "learning_rate": 1.4746648622282294e-05, "loss": 0.3943, "step": 594 }, { "epoch": 1.09, "learning_rate": 1.4729226719176377e-05, "loss": 0.3903, "step": 595 }, { "epoch": 1.09, "learning_rate": 1.4711786306823838e-05, "loss": 0.3799, "step": 596 }, { "epoch": 1.09, "learning_rate": 1.4694327453482956e-05, "loss": 0.385, "step": 597 }, { "epoch": 1.09, "learning_rate": 1.4676850227484191e-05, "loss": 0.3902, "step": 598 }, { "epoch": 1.1, "learning_rate": 1.4659354697229903e-05, "loss": 0.3802, "step": 599 }, { "epoch": 1.1, "learning_rate": 1.46418409311941e-05, "loss": 0.3914, "step": 600 }, { "epoch": 1.1, "learning_rate": 1.4624308997922151e-05, "loss": 0.3899, "step": 601 }, { "epoch": 1.1, "learning_rate": 1.4606758966030536e-05, "loss": 0.4017, "step": 602 }, { "epoch": 1.1, "learning_rate": 1.4589190904206565e-05, "loss": 0.38, "step": 603 }, { "epoch": 1.1, "learning_rate": 1.4571604881208118e-05, "loss": 0.3905, "step": 604 }, { "epoch": 1.11, "learning_rate": 1.4554000965863367e-05, "loss": 0.3738, "step": 605 }, { "epoch": 1.11, "learning_rate": 1.453637922707051e-05, "loss": 0.3874, "step": 606 }, { "epoch": 1.11, "learning_rate": 1.4518739733797507e-05, "loss": 0.3871, "step": 607 }, { "epoch": 1.11, "learning_rate": 1.4501082555081802e-05, "loss": 0.3947, "step": 608 }, { "epoch": 1.11, "learning_rate": 1.448340776003006e-05, "loss": 0.3709, "step": 609 }, { "epoch": 1.12, "learning_rate": 1.4465715417817889e-05, "loss": 0.3882, "step": 610 }, { "epoch": 1.12, "learning_rate": 1.4448005597689573e-05, "loss": 0.3874, "step": 611 }, { "epoch": 1.12, "learning_rate": 1.4430278368957809e-05, "loss": 0.3688, "step": 612 }, { "epoch": 1.12, "learning_rate": 1.4412533801003412e-05, "loss": 0.3661, "step": 613 }, { "epoch": 1.12, "learning_rate": 1.4394771963275079e-05, "loss": 0.3673, "step": 614 }, { "epoch": 1.12, "learning_rate": 1.4376992925289077e-05, "loss": 0.3727, "step": 615 }, { "epoch": 1.13, "learning_rate": 1.4359196756629006e-05, "loss": 0.4, "step": 616 }, { "epoch": 1.13, "learning_rate": 1.4341383526945507e-05, "loss": 0.3828, "step": 617 }, { "epoch": 1.13, "learning_rate": 1.4323553305956e-05, "loss": 0.3674, "step": 618 }, { "epoch": 1.13, "learning_rate": 1.4305706163444391e-05, "loss": 0.3801, "step": 619 }, { "epoch": 1.13, "learning_rate": 1.4287842169260827e-05, "loss": 0.3809, "step": 620 }, { "epoch": 1.14, "learning_rate": 1.426996139332141e-05, "loss": 0.3966, "step": 621 }, { "epoch": 1.14, "learning_rate": 1.425206390560791e-05, "loss": 0.3815, "step": 622 }, { "epoch": 1.14, "learning_rate": 1.4234149776167518e-05, "loss": 0.3607, "step": 623 }, { "epoch": 1.14, "learning_rate": 1.4216219075112542e-05, "loss": 0.3858, "step": 624 }, { "epoch": 1.14, "learning_rate": 1.4198271872620162e-05, "loss": 0.3859, "step": 625 }, { "epoch": 1.14, "learning_rate": 1.4180308238932137e-05, "loss": 0.3776, "step": 626 }, { "epoch": 1.15, "learning_rate": 1.4162328244354528e-05, "loss": 0.3681, "step": 627 }, { "epoch": 1.15, "learning_rate": 1.4144331959257438e-05, "loss": 0.381, "step": 628 }, { "epoch": 1.15, "learning_rate": 1.4126319454074725e-05, "loss": 0.3737, "step": 629 }, { "epoch": 1.15, "learning_rate": 1.4108290799303721e-05, "loss": 0.3595, "step": 630 }, { "epoch": 1.15, "learning_rate": 1.4090246065504981e-05, "loss": 0.3937, "step": 631 }, { "epoch": 1.16, "learning_rate": 1.4072185323301977e-05, "loss": 0.3699, "step": 632 }, { "epoch": 1.16, "learning_rate": 1.4054108643380838e-05, "loss": 0.3801, "step": 633 }, { "epoch": 1.16, "learning_rate": 1.4036016096490066e-05, "loss": 0.3492, "step": 634 }, { "epoch": 1.16, "learning_rate": 1.4017907753440278e-05, "loss": 0.3773, "step": 635 }, { "epoch": 1.16, "learning_rate": 1.3999783685103893e-05, "loss": 0.3756, "step": 636 }, { "epoch": 1.16, "learning_rate": 1.398164396241489e-05, "loss": 0.384, "step": 637 }, { "epoch": 1.17, "learning_rate": 1.3963488656368518e-05, "loss": 0.4027, "step": 638 }, { "epoch": 1.17, "learning_rate": 1.3945317838021001e-05, "loss": 0.3945, "step": 639 }, { "epoch": 1.17, "learning_rate": 1.3927131578489292e-05, "loss": 0.3563, "step": 640 }, { "epoch": 1.17, "learning_rate": 1.3908929948950763e-05, "loss": 0.384, "step": 641 }, { "epoch": 1.17, "learning_rate": 1.3890713020642951e-05, "loss": 0.385, "step": 642 }, { "epoch": 1.18, "learning_rate": 1.3872480864863272e-05, "loss": 0.402, "step": 643 }, { "epoch": 1.18, "learning_rate": 1.3854233552968726e-05, "loss": 0.3818, "step": 644 }, { "epoch": 1.18, "learning_rate": 1.383597115637564e-05, "loss": 0.3692, "step": 645 }, { "epoch": 1.18, "learning_rate": 1.3817693746559382e-05, "loss": 0.3782, "step": 646 }, { "epoch": 1.18, "learning_rate": 1.3799401395054073e-05, "loss": 0.3891, "step": 647 }, { "epoch": 1.18, "learning_rate": 1.3781094173452316e-05, "loss": 0.3803, "step": 648 }, { "epoch": 1.19, "learning_rate": 1.3762772153404909e-05, "loss": 0.3734, "step": 649 }, { "epoch": 1.19, "learning_rate": 1.3744435406620571e-05, "loss": 0.3802, "step": 650 }, { "epoch": 1.19, "learning_rate": 1.3726084004865659e-05, "loss": 0.383, "step": 651 }, { "epoch": 1.19, "learning_rate": 1.3707718019963887e-05, "loss": 0.3854, "step": 652 }, { "epoch": 1.19, "learning_rate": 1.3689337523796043e-05, "loss": 0.3889, "step": 653 }, { "epoch": 1.2, "learning_rate": 1.3670942588299708e-05, "loss": 0.3806, "step": 654 }, { "epoch": 1.2, "learning_rate": 1.3652533285468972e-05, "loss": 0.3754, "step": 655 }, { "epoch": 1.2, "learning_rate": 1.3634109687354169e-05, "loss": 0.3696, "step": 656 }, { "epoch": 1.2, "learning_rate": 1.3615671866061573e-05, "loss": 0.3823, "step": 657 }, { "epoch": 1.2, "learning_rate": 1.3597219893753119e-05, "loss": 0.3897, "step": 658 }, { "epoch": 1.21, "learning_rate": 1.3578753842646137e-05, "loss": 0.3893, "step": 659 }, { "epoch": 1.21, "learning_rate": 1.3560273785013057e-05, "loss": 0.3894, "step": 660 }, { "epoch": 1.21, "learning_rate": 1.3541779793181122e-05, "loss": 0.3959, "step": 661 }, { "epoch": 1.21, "learning_rate": 1.3523271939532112e-05, "loss": 0.3988, "step": 662 }, { "epoch": 1.21, "learning_rate": 1.3504750296502064e-05, "loss": 0.3687, "step": 663 }, { "epoch": 1.21, "learning_rate": 1.3486214936580977e-05, "loss": 0.3587, "step": 664 }, { "epoch": 1.22, "learning_rate": 1.3467665932312545e-05, "loss": 0.3789, "step": 665 }, { "epoch": 1.22, "learning_rate": 1.3449103356293853e-05, "loss": 0.3779, "step": 666 }, { "epoch": 1.22, "learning_rate": 1.343052728117511e-05, "loss": 0.3618, "step": 667 }, { "epoch": 1.22, "learning_rate": 1.341193777965935e-05, "loss": 0.3809, "step": 668 }, { "epoch": 1.22, "learning_rate": 1.3393334924502168e-05, "loss": 0.3936, "step": 669 }, { "epoch": 1.23, "learning_rate": 1.3374718788511412e-05, "loss": 0.403, "step": 670 }, { "epoch": 1.23, "learning_rate": 1.3356089444546906e-05, "loss": 0.3877, "step": 671 }, { "epoch": 1.23, "learning_rate": 1.3337446965520183e-05, "loss": 0.3733, "step": 672 }, { "epoch": 1.23, "learning_rate": 1.3318791424394161e-05, "loss": 0.3867, "step": 673 }, { "epoch": 1.23, "learning_rate": 1.330012289418291e-05, "loss": 0.3893, "step": 674 }, { "epoch": 1.23, "learning_rate": 1.3281441447951304e-05, "loss": 0.3911, "step": 675 }, { "epoch": 1.24, "learning_rate": 1.3262747158814791e-05, "loss": 0.3739, "step": 676 }, { "epoch": 1.24, "learning_rate": 1.3244040099939078e-05, "loss": 0.3748, "step": 677 }, { "epoch": 1.24, "learning_rate": 1.3225320344539845e-05, "loss": 0.3797, "step": 678 }, { "epoch": 1.24, "learning_rate": 1.3206587965882465e-05, "loss": 0.3707, "step": 679 }, { "epoch": 1.24, "learning_rate": 1.3187843037281725e-05, "loss": 0.38, "step": 680 }, { "epoch": 1.25, "learning_rate": 1.3169085632101515e-05, "loss": 0.3798, "step": 681 }, { "epoch": 1.25, "learning_rate": 1.3150315823754572e-05, "loss": 0.3683, "step": 682 }, { "epoch": 1.25, "learning_rate": 1.313153368570216e-05, "loss": 0.3678, "step": 683 }, { "epoch": 1.25, "learning_rate": 1.3112739291453812e-05, "loss": 0.3823, "step": 684 }, { "epoch": 1.25, "learning_rate": 1.3093932714567026e-05, "loss": 0.3803, "step": 685 }, { "epoch": 1.25, "learning_rate": 1.3075114028646976e-05, "loss": 0.4052, "step": 686 }, { "epoch": 1.26, "learning_rate": 1.3056283307346234e-05, "loss": 0.3622, "step": 687 }, { "epoch": 1.26, "learning_rate": 1.3037440624364468e-05, "loss": 0.3754, "step": 688 }, { "epoch": 1.26, "learning_rate": 1.3018586053448173e-05, "loss": 0.3776, "step": 689 }, { "epoch": 1.26, "learning_rate": 1.299971966839036e-05, "loss": 0.3856, "step": 690 }, { "epoch": 1.26, "learning_rate": 1.298084154303029e-05, "loss": 0.3818, "step": 691 }, { "epoch": 1.27, "learning_rate": 1.2961951751253158e-05, "loss": 0.3781, "step": 692 }, { "epoch": 1.27, "learning_rate": 1.2943050366989833e-05, "loss": 0.3672, "step": 693 }, { "epoch": 1.27, "learning_rate": 1.292413746421655e-05, "loss": 0.3942, "step": 694 }, { "epoch": 1.27, "learning_rate": 1.290521311695462e-05, "loss": 0.3921, "step": 695 }, { "epoch": 1.27, "learning_rate": 1.2886277399270153e-05, "loss": 0.3753, "step": 696 }, { "epoch": 1.27, "learning_rate": 1.2867330385273756e-05, "loss": 0.3896, "step": 697 }, { "epoch": 1.28, "learning_rate": 1.2848372149120248e-05, "loss": 0.3903, "step": 698 }, { "epoch": 1.28, "learning_rate": 1.282940276500837e-05, "loss": 0.3835, "step": 699 }, { "epoch": 1.28, "learning_rate": 1.2810422307180497e-05, "loss": 0.3968, "step": 700 }, { "epoch": 1.28, "learning_rate": 1.2791430849922335e-05, "loss": 0.3778, "step": 701 }, { "epoch": 1.28, "learning_rate": 1.2772428467562653e-05, "loss": 0.3746, "step": 702 }, { "epoch": 1.29, "learning_rate": 1.2753415234472965e-05, "loss": 0.4004, "step": 703 }, { "epoch": 1.29, "learning_rate": 1.2734391225067264e-05, "loss": 0.3841, "step": 704 }, { "epoch": 1.29, "learning_rate": 1.2715356513801714e-05, "loss": 0.3868, "step": 705 }, { "epoch": 1.29, "learning_rate": 1.2696311175174358e-05, "loss": 0.3962, "step": 706 }, { "epoch": 1.29, "learning_rate": 1.2677255283724844e-05, "loss": 0.3979, "step": 707 }, { "epoch": 1.29, "learning_rate": 1.265818891403412e-05, "loss": 0.3917, "step": 708 }, { "epoch": 1.3, "learning_rate": 1.2639112140724133e-05, "loss": 0.3858, "step": 709 }, { "epoch": 1.3, "learning_rate": 1.2620025038457555e-05, "loss": 0.3887, "step": 710 }, { "epoch": 1.3, "learning_rate": 1.260092768193749e-05, "loss": 0.4006, "step": 711 }, { "epoch": 1.3, "learning_rate": 1.258182014590716e-05, "loss": 0.3572, "step": 712 }, { "epoch": 1.3, "learning_rate": 1.256270250514964e-05, "loss": 0.3722, "step": 713 }, { "epoch": 1.31, "learning_rate": 1.2543574834487551e-05, "loss": 0.3939, "step": 714 }, { "epoch": 1.31, "learning_rate": 1.252443720878276e-05, "loss": 0.3948, "step": 715 }, { "epoch": 1.31, "learning_rate": 1.2505289702936109e-05, "loss": 0.3963, "step": 716 }, { "epoch": 1.31, "learning_rate": 1.2486132391887103e-05, "loss": 0.3698, "step": 717 }, { "epoch": 1.31, "learning_rate": 1.2466965350613615e-05, "loss": 0.3875, "step": 718 }, { "epoch": 1.31, "learning_rate": 1.2447788654131616e-05, "loss": 0.3684, "step": 719 }, { "epoch": 1.32, "learning_rate": 1.2428602377494851e-05, "loss": 0.3773, "step": 720 }, { "epoch": 1.32, "learning_rate": 1.240940659579457e-05, "loss": 0.3706, "step": 721 }, { "epoch": 1.32, "learning_rate": 1.239020138415922e-05, "loss": 0.3714, "step": 722 }, { "epoch": 1.32, "learning_rate": 1.2370986817754146e-05, "loss": 0.39, "step": 723 }, { "epoch": 1.32, "learning_rate": 1.2351762971781324e-05, "loss": 0.396, "step": 724 }, { "epoch": 1.33, "learning_rate": 1.2332529921479037e-05, "loss": 0.398, "step": 725 }, { "epoch": 1.33, "learning_rate": 1.2313287742121592e-05, "loss": 0.3778, "step": 726 }, { "epoch": 1.33, "learning_rate": 1.2294036509019025e-05, "loss": 0.3743, "step": 727 }, { "epoch": 1.33, "learning_rate": 1.227477629751681e-05, "loss": 0.3706, "step": 728 }, { "epoch": 1.33, "learning_rate": 1.225550718299556e-05, "loss": 0.3777, "step": 729 }, { "epoch": 1.33, "learning_rate": 1.2236229240870731e-05, "loss": 0.3891, "step": 730 }, { "epoch": 1.34, "learning_rate": 1.2216942546592333e-05, "loss": 0.3915, "step": 731 }, { "epoch": 1.34, "learning_rate": 1.2197647175644618e-05, "loss": 0.3677, "step": 732 }, { "epoch": 1.34, "learning_rate": 1.2178343203545811e-05, "loss": 0.38, "step": 733 }, { "epoch": 1.34, "learning_rate": 1.2159030705847792e-05, "loss": 0.367, "step": 734 }, { "epoch": 1.34, "learning_rate": 1.2139709758135814e-05, "loss": 0.3878, "step": 735 }, { "epoch": 1.35, "learning_rate": 1.2120380436028194e-05, "loss": 0.3845, "step": 736 }, { "epoch": 1.35, "learning_rate": 1.2101042815176031e-05, "loss": 0.3796, "step": 737 }, { "epoch": 1.35, "learning_rate": 1.2081696971262905e-05, "loss": 0.3773, "step": 738 }, { "epoch": 1.35, "learning_rate": 1.2062342980004573e-05, "loss": 0.3682, "step": 739 }, { "epoch": 1.35, "learning_rate": 1.204298091714868e-05, "loss": 0.3771, "step": 740 }, { "epoch": 1.35, "learning_rate": 1.2023610858474465e-05, "loss": 0.3758, "step": 741 }, { "epoch": 1.36, "learning_rate": 1.2004232879792465e-05, "loss": 0.3739, "step": 742 }, { "epoch": 1.36, "learning_rate": 1.1984847056944207e-05, "loss": 0.3826, "step": 743 }, { "epoch": 1.36, "learning_rate": 1.1965453465801916e-05, "loss": 0.3796, "step": 744 }, { "epoch": 1.36, "learning_rate": 1.1946052182268228e-05, "loss": 0.3728, "step": 745 }, { "epoch": 1.36, "learning_rate": 1.1926643282275884e-05, "loss": 0.3811, "step": 746 }, { "epoch": 1.37, "learning_rate": 1.1907226841787436e-05, "loss": 0.3794, "step": 747 }, { "epoch": 1.37, "learning_rate": 1.1887802936794938e-05, "loss": 0.3681, "step": 748 }, { "epoch": 1.37, "learning_rate": 1.1868371643319669e-05, "loss": 0.3765, "step": 749 }, { "epoch": 1.37, "learning_rate": 1.1848933037411825e-05, "loss": 0.3898, "step": 750 }, { "epoch": 1.37, "learning_rate": 1.1829487195150211e-05, "loss": 0.4043, "step": 751 }, { "epoch": 1.38, "learning_rate": 1.1810034192641969e-05, "loss": 0.3779, "step": 752 }, { "epoch": 1.38, "learning_rate": 1.1790574106022247e-05, "loss": 0.3954, "step": 753 }, { "epoch": 1.38, "learning_rate": 1.1771107011453934e-05, "loss": 0.3675, "step": 754 }, { "epoch": 1.38, "learning_rate": 1.1751632985127341e-05, "loss": 0.3658, "step": 755 }, { "epoch": 1.38, "learning_rate": 1.1732152103259913e-05, "loss": 0.3647, "step": 756 }, { "epoch": 1.38, "learning_rate": 1.171266444209591e-05, "loss": 0.3907, "step": 757 }, { "epoch": 1.39, "learning_rate": 1.1693170077906145e-05, "loss": 0.393, "step": 758 }, { "epoch": 1.39, "learning_rate": 1.1673669086987653e-05, "loss": 0.3661, "step": 759 }, { "epoch": 1.39, "learning_rate": 1.1654161545663413e-05, "loss": 0.3805, "step": 760 }, { "epoch": 1.39, "learning_rate": 1.1634647530282035e-05, "loss": 0.3897, "step": 761 }, { "epoch": 1.39, "learning_rate": 1.1615127117217465e-05, "loss": 0.379, "step": 762 }, { "epoch": 1.4, "learning_rate": 1.1595600382868692e-05, "loss": 0.3773, "step": 763 }, { "epoch": 1.4, "learning_rate": 1.157606740365945e-05, "loss": 0.3856, "step": 764 }, { "epoch": 1.4, "learning_rate": 1.155652825603791e-05, "loss": 0.4042, "step": 765 }, { "epoch": 1.4, "learning_rate": 1.1536983016476375e-05, "loss": 0.3684, "step": 766 }, { "epoch": 1.4, "learning_rate": 1.1517431761471009e-05, "loss": 0.3628, "step": 767 }, { "epoch": 1.4, "learning_rate": 1.1497874567541505e-05, "loss": 0.3742, "step": 768 }, { "epoch": 1.41, "learning_rate": 1.1478311511230808e-05, "loss": 0.3806, "step": 769 }, { "epoch": 1.41, "learning_rate": 1.1458742669104806e-05, "loss": 0.38, "step": 770 }, { "epoch": 1.41, "learning_rate": 1.143916811775202e-05, "loss": 0.3914, "step": 771 }, { "epoch": 1.41, "learning_rate": 1.1419587933783334e-05, "loss": 0.3888, "step": 772 }, { "epoch": 1.41, "learning_rate": 1.140000219383167e-05, "loss": 0.378, "step": 773 }, { "epoch": 1.42, "learning_rate": 1.1380410974551683e-05, "loss": 0.4107, "step": 774 }, { "epoch": 1.42, "learning_rate": 1.1360814352619489e-05, "loss": 0.3612, "step": 775 }, { "epoch": 1.42, "learning_rate": 1.1341212404732348e-05, "loss": 0.3933, "step": 776 }, { "epoch": 1.42, "learning_rate": 1.1321605207608355e-05, "loss": 0.3796, "step": 777 }, { "epoch": 1.42, "learning_rate": 1.1301992837986154e-05, "loss": 0.3918, "step": 778 }, { "epoch": 1.42, "learning_rate": 1.1282375372624632e-05, "loss": 0.3687, "step": 779 }, { "epoch": 1.43, "learning_rate": 1.1262752888302624e-05, "loss": 0.3687, "step": 780 }, { "epoch": 1.43, "learning_rate": 1.1243125461818605e-05, "loss": 0.3629, "step": 781 }, { "epoch": 1.43, "learning_rate": 1.1223493169990394e-05, "loss": 0.3728, "step": 782 }, { "epoch": 1.43, "learning_rate": 1.1203856089654847e-05, "loss": 0.3909, "step": 783 }, { "epoch": 1.43, "learning_rate": 1.1184214297667571e-05, "loss": 0.3912, "step": 784 }, { "epoch": 1.44, "learning_rate": 1.1164567870902603e-05, "loss": 0.3864, "step": 785 }, { "epoch": 1.44, "learning_rate": 1.1144916886252126e-05, "loss": 0.3741, "step": 786 }, { "epoch": 1.44, "learning_rate": 1.1125261420626162e-05, "loss": 0.3811, "step": 787 }, { "epoch": 1.44, "learning_rate": 1.110560155095226e-05, "loss": 0.3891, "step": 788 }, { "epoch": 1.44, "learning_rate": 1.1085937354175225e-05, "loss": 0.3873, "step": 789 }, { "epoch": 1.44, "learning_rate": 1.1066268907256783e-05, "loss": 0.3624, "step": 790 }, { "epoch": 1.45, "learning_rate": 1.1046596287175297e-05, "loss": 0.3776, "step": 791 }, { "epoch": 1.45, "learning_rate": 1.1026919570925463e-05, "loss": 0.4078, "step": 792 }, { "epoch": 1.45, "learning_rate": 1.1007238835518008e-05, "loss": 0.379, "step": 793 }, { "epoch": 1.45, "learning_rate": 1.0987554157979392e-05, "loss": 0.3804, "step": 794 }, { "epoch": 1.45, "learning_rate": 1.0967865615351508e-05, "loss": 0.383, "step": 795 }, { "epoch": 1.46, "learning_rate": 1.0948173284691359e-05, "loss": 0.3762, "step": 796 }, { "epoch": 1.46, "learning_rate": 1.0928477243070793e-05, "loss": 0.3947, "step": 797 }, { "epoch": 1.46, "learning_rate": 1.090877756757617e-05, "loss": 0.3487, "step": 798 }, { "epoch": 1.46, "learning_rate": 1.0889074335308081e-05, "loss": 0.3884, "step": 799 }, { "epoch": 1.46, "learning_rate": 1.0869367623381026e-05, "loss": 0.3777, "step": 800 }, { "epoch": 1.46, "learning_rate": 1.0849657508923137e-05, "loss": 0.403, "step": 801 }, { "epoch": 1.47, "learning_rate": 1.0829944069075848e-05, "loss": 0.3675, "step": 802 }, { "epoch": 1.47, "learning_rate": 1.0810227380993628e-05, "loss": 0.3893, "step": 803 }, { "epoch": 1.47, "learning_rate": 1.0790507521843636e-05, "loss": 0.3923, "step": 804 }, { "epoch": 1.47, "learning_rate": 1.0770784568805457e-05, "loss": 0.4103, "step": 805 }, { "epoch": 1.47, "learning_rate": 1.0751058599070782e-05, "loss": 0.4027, "step": 806 }, { "epoch": 1.48, "learning_rate": 1.0731329689843105e-05, "loss": 0.4037, "step": 807 }, { "epoch": 1.48, "learning_rate": 1.071159791833743e-05, "loss": 0.3827, "step": 808 }, { "epoch": 1.48, "learning_rate": 1.069186336177996e-05, "loss": 0.3761, "step": 809 }, { "epoch": 1.48, "learning_rate": 1.0672126097407796e-05, "loss": 0.376, "step": 810 }, { "epoch": 1.48, "learning_rate": 1.0652386202468638e-05, "loss": 0.4017, "step": 811 }, { "epoch": 1.48, "learning_rate": 1.0632643754220496e-05, "loss": 0.3802, "step": 812 }, { "epoch": 1.49, "learning_rate": 1.0612898829931341e-05, "loss": 0.3995, "step": 813 }, { "epoch": 1.49, "learning_rate": 1.0593151506878868e-05, "loss": 0.39, "step": 814 }, { "epoch": 1.49, "learning_rate": 1.057340186235014e-05, "loss": 0.3782, "step": 815 }, { "epoch": 1.49, "learning_rate": 1.0553649973641314e-05, "loss": 0.3838, "step": 816 }, { "epoch": 1.49, "learning_rate": 1.0533895918057326e-05, "loss": 0.3689, "step": 817 }, { "epoch": 1.5, "learning_rate": 1.0514139772911598e-05, "loss": 0.3748, "step": 818 }, { "epoch": 1.5, "learning_rate": 1.0494381615525726e-05, "loss": 0.3812, "step": 819 }, { "epoch": 1.5, "learning_rate": 1.0474621523229182e-05, "loss": 0.3822, "step": 820 }, { "epoch": 1.5, "learning_rate": 1.0454859573359013e-05, "loss": 0.3758, "step": 821 }, { "epoch": 1.5, "learning_rate": 1.0435095843259531e-05, "loss": 0.3901, "step": 822 }, { "epoch": 1.5, "learning_rate": 1.0415330410282021e-05, "loss": 0.3999, "step": 823 }, { "epoch": 1.51, "learning_rate": 1.0395563351784433e-05, "loss": 0.3697, "step": 824 }, { "epoch": 1.51, "learning_rate": 1.0375794745131074e-05, "loss": 0.3819, "step": 825 }, { "epoch": 1.51, "learning_rate": 1.0356024667692314e-05, "loss": 0.359, "step": 826 }, { "epoch": 1.51, "learning_rate": 1.0336253196844276e-05, "loss": 0.3813, "step": 827 }, { "epoch": 1.51, "learning_rate": 1.0316480409968543e-05, "loss": 0.3665, "step": 828 }, { "epoch": 1.52, "learning_rate": 1.0296706384451842e-05, "loss": 0.3875, "step": 829 }, { "epoch": 1.52, "learning_rate": 1.0276931197685753e-05, "loss": 0.3858, "step": 830 }, { "epoch": 1.52, "learning_rate": 1.0257154927066393e-05, "loss": 0.3853, "step": 831 }, { "epoch": 1.52, "learning_rate": 1.0237377649994129e-05, "loss": 0.3802, "step": 832 }, { "epoch": 1.52, "learning_rate": 1.0217599443873265e-05, "loss": 0.3795, "step": 833 }, { "epoch": 1.53, "learning_rate": 1.0197820386111738e-05, "loss": 0.3867, "step": 834 }, { "epoch": 1.53, "learning_rate": 1.0178040554120825e-05, "loss": 0.384, "step": 835 }, { "epoch": 1.53, "learning_rate": 1.0158260025314821e-05, "loss": 0.3789, "step": 836 }, { "epoch": 1.53, "learning_rate": 1.0138478877110765e-05, "loss": 0.3767, "step": 837 }, { "epoch": 1.53, "learning_rate": 1.0118697186928107e-05, "loss": 0.3634, "step": 838 }, { "epoch": 1.53, "learning_rate": 1.0098915032188416e-05, "loss": 0.3804, "step": 839 }, { "epoch": 1.54, "learning_rate": 1.0079132490315095e-05, "loss": 0.3881, "step": 840 }, { "epoch": 1.54, "learning_rate": 1.0059349638733045e-05, "loss": 0.3893, "step": 841 }, { "epoch": 1.54, "learning_rate": 1.0039566554868393e-05, "loss": 0.3855, "step": 842 }, { "epoch": 1.54, "learning_rate": 1.0019783316148168e-05, "loss": 0.3824, "step": 843 }, { "epoch": 1.54, "learning_rate": 1e-05, "loss": 0.3813, "step": 844 }, { "epoch": 1.55, "learning_rate": 9.980216683851837e-06, "loss": 0.392, "step": 845 }, { "epoch": 1.55, "learning_rate": 9.960433445131608e-06, "loss": 0.381, "step": 846 }, { "epoch": 1.55, "learning_rate": 9.940650361266956e-06, "loss": 0.3543, "step": 847 }, { "epoch": 1.55, "learning_rate": 9.92086750968491e-06, "loss": 0.3672, "step": 848 }, { "epoch": 1.55, "learning_rate": 9.901084967811586e-06, "loss": 0.386, "step": 849 }, { "epoch": 1.55, "learning_rate": 9.881302813071898e-06, "loss": 0.3724, "step": 850 }, { "epoch": 1.56, "learning_rate": 9.86152112288924e-06, "loss": 0.3985, "step": 851 }, { "epoch": 1.56, "learning_rate": 9.841739974685179e-06, "loss": 0.3916, "step": 852 }, { "epoch": 1.56, "learning_rate": 9.821959445879178e-06, "loss": 0.3681, "step": 853 }, { "epoch": 1.56, "learning_rate": 9.802179613888264e-06, "loss": 0.3812, "step": 854 }, { "epoch": 1.56, "learning_rate": 9.782400556126737e-06, "loss": 0.3759, "step": 855 }, { "epoch": 1.57, "learning_rate": 9.762622350005873e-06, "loss": 0.3888, "step": 856 }, { "epoch": 1.57, "learning_rate": 9.742845072933612e-06, "loss": 0.3792, "step": 857 }, { "epoch": 1.57, "learning_rate": 9.723068802314247e-06, "loss": 0.3717, "step": 858 }, { "epoch": 1.57, "learning_rate": 9.70329361554816e-06, "loss": 0.3732, "step": 859 }, { "epoch": 1.57, "learning_rate": 9.683519590031459e-06, "loss": 0.3937, "step": 860 }, { "epoch": 1.57, "learning_rate": 9.663746803155729e-06, "loss": 0.3776, "step": 861 }, { "epoch": 1.58, "learning_rate": 9.643975332307687e-06, "loss": 0.3752, "step": 862 }, { "epoch": 1.58, "learning_rate": 9.62420525486893e-06, "loss": 0.3611, "step": 863 }, { "epoch": 1.58, "learning_rate": 9.604436648215572e-06, "loss": 0.3819, "step": 864 }, { "epoch": 1.58, "learning_rate": 9.58466958971798e-06, "loss": 0.3577, "step": 865 }, { "epoch": 1.58, "learning_rate": 9.564904156740474e-06, "loss": 0.3588, "step": 866 }, { "epoch": 1.59, "learning_rate": 9.545140426640992e-06, "loss": 0.4042, "step": 867 }, { "epoch": 1.59, "learning_rate": 9.525378476770821e-06, "loss": 0.3754, "step": 868 }, { "epoch": 1.59, "learning_rate": 9.505618384474277e-06, "loss": 0.3836, "step": 869 }, { "epoch": 1.59, "learning_rate": 9.485860227088406e-06, "loss": 0.3757, "step": 870 }, { "epoch": 1.59, "learning_rate": 9.466104081942674e-06, "loss": 0.3551, "step": 871 }, { "epoch": 1.59, "learning_rate": 9.44635002635869e-06, "loss": 0.3712, "step": 872 }, { "epoch": 1.6, "learning_rate": 9.426598137649866e-06, "loss": 0.3697, "step": 873 }, { "epoch": 1.6, "learning_rate": 9.406848493121134e-06, "loss": 0.3597, "step": 874 }, { "epoch": 1.6, "learning_rate": 9.38710117006866e-06, "loss": 0.3892, "step": 875 }, { "epoch": 1.6, "learning_rate": 9.36735624577951e-06, "loss": 0.3965, "step": 876 }, { "epoch": 1.6, "learning_rate": 9.347613797531362e-06, "loss": 0.4039, "step": 877 }, { "epoch": 1.61, "learning_rate": 9.327873902592207e-06, "loss": 0.362, "step": 878 }, { "epoch": 1.61, "learning_rate": 9.308136638220044e-06, "loss": 0.3831, "step": 879 }, { "epoch": 1.61, "learning_rate": 9.288402081662571e-06, "loss": 0.3894, "step": 880 }, { "epoch": 1.61, "learning_rate": 9.268670310156897e-06, "loss": 0.3932, "step": 881 }, { "epoch": 1.61, "learning_rate": 9.248941400929223e-06, "loss": 0.3789, "step": 882 }, { "epoch": 1.61, "learning_rate": 9.229215431194543e-06, "loss": 0.3819, "step": 883 }, { "epoch": 1.62, "learning_rate": 9.209492478156367e-06, "loss": 0.3734, "step": 884 }, { "epoch": 1.62, "learning_rate": 9.189772619006377e-06, "loss": 0.4128, "step": 885 }, { "epoch": 1.62, "learning_rate": 9.170055930924152e-06, "loss": 0.3861, "step": 886 }, { "epoch": 1.62, "learning_rate": 9.150342491076866e-06, "loss": 0.391, "step": 887 }, { "epoch": 1.62, "learning_rate": 9.130632376618978e-06, "loss": 0.3616, "step": 888 }, { "epoch": 1.63, "learning_rate": 9.110925664691922e-06, "loss": 0.3611, "step": 889 }, { "epoch": 1.63, "learning_rate": 9.091222432423832e-06, "loss": 0.371, "step": 890 }, { "epoch": 1.63, "learning_rate": 9.071522756929212e-06, "loss": 0.3951, "step": 891 }, { "epoch": 1.63, "learning_rate": 9.051826715308646e-06, "loss": 0.3876, "step": 892 }, { "epoch": 1.63, "learning_rate": 9.032134384648496e-06, "loss": 0.3813, "step": 893 }, { "epoch": 1.63, "learning_rate": 9.012445842020611e-06, "loss": 0.3745, "step": 894 }, { "epoch": 1.64, "learning_rate": 8.992761164481997e-06, "loss": 0.4143, "step": 895 }, { "epoch": 1.64, "learning_rate": 8.97308042907454e-06, "loss": 0.3763, "step": 896 }, { "epoch": 1.64, "learning_rate": 8.953403712824706e-06, "loss": 0.3852, "step": 897 }, { "epoch": 1.64, "learning_rate": 8.93373109274322e-06, "loss": 0.3908, "step": 898 }, { "epoch": 1.64, "learning_rate": 8.914062645824774e-06, "loss": 0.3802, "step": 899 }, { "epoch": 1.65, "learning_rate": 8.894398449047741e-06, "loss": 0.374, "step": 900 }, { "epoch": 1.65, "learning_rate": 8.874738579373843e-06, "loss": 0.3823, "step": 901 }, { "epoch": 1.65, "learning_rate": 8.855083113747876e-06, "loss": 0.3841, "step": 902 }, { "epoch": 1.65, "learning_rate": 8.8354321290974e-06, "loss": 0.3846, "step": 903 }, { "epoch": 1.65, "learning_rate": 8.815785702332434e-06, "loss": 0.396, "step": 904 }, { "epoch": 1.65, "learning_rate": 8.796143910345153e-06, "loss": 0.3734, "step": 905 }, { "epoch": 1.66, "learning_rate": 8.776506830009607e-06, "loss": 0.3672, "step": 906 }, { "epoch": 1.66, "learning_rate": 8.756874538181397e-06, "loss": 0.3665, "step": 907 }, { "epoch": 1.66, "learning_rate": 8.737247111697378e-06, "loss": 0.379, "step": 908 }, { "epoch": 1.66, "learning_rate": 8.717624627375371e-06, "loss": 0.3837, "step": 909 }, { "epoch": 1.66, "learning_rate": 8.698007162013851e-06, "loss": 0.3702, "step": 910 }, { "epoch": 1.67, "learning_rate": 8.67839479239165e-06, "loss": 0.3712, "step": 911 }, { "epoch": 1.67, "learning_rate": 8.658787595267654e-06, "loss": 0.3573, "step": 912 }, { "epoch": 1.67, "learning_rate": 8.639185647380513e-06, "loss": 0.3914, "step": 913 }, { "epoch": 1.67, "learning_rate": 8.619589025448318e-06, "loss": 0.3673, "step": 914 }, { "epoch": 1.67, "learning_rate": 8.599997806168335e-06, "loss": 0.3679, "step": 915 }, { "epoch": 1.67, "learning_rate": 8.58041206621667e-06, "loss": 0.3771, "step": 916 }, { "epoch": 1.68, "learning_rate": 8.56083188224798e-06, "loss": 0.3701, "step": 917 }, { "epoch": 1.68, "learning_rate": 8.541257330895198e-06, "loss": 0.3792, "step": 918 }, { "epoch": 1.68, "learning_rate": 8.521688488769194e-06, "loss": 0.3777, "step": 919 }, { "epoch": 1.68, "learning_rate": 8.502125432458495e-06, "loss": 0.366, "step": 920 }, { "epoch": 1.68, "learning_rate": 8.482568238528994e-06, "loss": 0.3835, "step": 921 }, { "epoch": 1.69, "learning_rate": 8.463016983523629e-06, "loss": 0.3991, "step": 922 }, { "epoch": 1.69, "learning_rate": 8.443471743962098e-06, "loss": 0.3829, "step": 923 }, { "epoch": 1.69, "learning_rate": 8.423932596340551e-06, "loss": 0.38, "step": 924 }, { "epoch": 1.69, "learning_rate": 8.404399617131311e-06, "loss": 0.363, "step": 925 }, { "epoch": 1.69, "learning_rate": 8.384872882782542e-06, "loss": 0.393, "step": 926 }, { "epoch": 1.7, "learning_rate": 8.365352469717969e-06, "loss": 0.3717, "step": 927 }, { "epoch": 1.7, "learning_rate": 8.345838454336589e-06, "loss": 0.3624, "step": 928 }, { "epoch": 1.7, "learning_rate": 8.32633091301235e-06, "loss": 0.3872, "step": 929 }, { "epoch": 1.7, "learning_rate": 8.306829922093857e-06, "loss": 0.3662, "step": 930 }, { "epoch": 1.7, "learning_rate": 8.287335557904092e-06, "loss": 0.3882, "step": 931 }, { "epoch": 1.7, "learning_rate": 8.267847896740092e-06, "loss": 0.3654, "step": 932 }, { "epoch": 1.71, "learning_rate": 8.248367014872659e-06, "loss": 0.3864, "step": 933 }, { "epoch": 1.71, "learning_rate": 8.228892988546067e-06, "loss": 0.3648, "step": 934 }, { "epoch": 1.71, "learning_rate": 8.209425893977758e-06, "loss": 0.3853, "step": 935 }, { "epoch": 1.71, "learning_rate": 8.189965807358033e-06, "loss": 0.3634, "step": 936 }, { "epoch": 1.71, "learning_rate": 8.170512804849792e-06, "loss": 0.3776, "step": 937 }, { "epoch": 1.72, "learning_rate": 8.151066962588181e-06, "loss": 0.377, "step": 938 }, { "epoch": 1.72, "learning_rate": 8.131628356680331e-06, "loss": 0.375, "step": 939 }, { "epoch": 1.72, "learning_rate": 8.112197063205063e-06, "loss": 0.369, "step": 940 }, { "epoch": 1.72, "learning_rate": 8.092773158212567e-06, "loss": 0.3819, "step": 941 }, { "epoch": 1.72, "learning_rate": 8.073356717724116e-06, "loss": 0.372, "step": 942 }, { "epoch": 1.72, "learning_rate": 8.053947817731773e-06, "loss": 0.3779, "step": 943 }, { "epoch": 1.73, "learning_rate": 8.034546534198087e-06, "loss": 0.3772, "step": 944 }, { "epoch": 1.73, "learning_rate": 8.015152943055797e-06, "loss": 0.3895, "step": 945 }, { "epoch": 1.73, "learning_rate": 7.995767120207537e-06, "loss": 0.3579, "step": 946 }, { "epoch": 1.73, "learning_rate": 7.976389141525536e-06, "loss": 0.3775, "step": 947 }, { "epoch": 1.73, "learning_rate": 7.957019082851322e-06, "loss": 0.3559, "step": 948 }, { "epoch": 1.74, "learning_rate": 7.93765701999543e-06, "loss": 0.3775, "step": 949 }, { "epoch": 1.74, "learning_rate": 7.918303028737097e-06, "loss": 0.3761, "step": 950 }, { "epoch": 1.74, "learning_rate": 7.898957184823974e-06, "loss": 0.3846, "step": 951 }, { "epoch": 1.74, "learning_rate": 7.879619563971808e-06, "loss": 0.3969, "step": 952 }, { "epoch": 1.74, "learning_rate": 7.860290241864191e-06, "loss": 0.3808, "step": 953 }, { "epoch": 1.74, "learning_rate": 7.840969294152212e-06, "loss": 0.4052, "step": 954 }, { "epoch": 1.75, "learning_rate": 7.821656796454192e-06, "loss": 0.366, "step": 955 }, { "epoch": 1.75, "learning_rate": 7.802352824355385e-06, "loss": 0.3763, "step": 956 }, { "epoch": 1.75, "learning_rate": 7.783057453407673e-06, "loss": 0.3634, "step": 957 }, { "epoch": 1.75, "learning_rate": 7.76377075912927e-06, "loss": 0.3709, "step": 958 }, { "epoch": 1.75, "learning_rate": 7.744492817004443e-06, "loss": 0.4129, "step": 959 }, { "epoch": 1.76, "learning_rate": 7.725223702483193e-06, "loss": 0.3709, "step": 960 }, { "epoch": 1.76, "learning_rate": 7.705963490980977e-06, "loss": 0.3795, "step": 961 }, { "epoch": 1.76, "learning_rate": 7.68671225787841e-06, "loss": 0.3902, "step": 962 }, { "epoch": 1.76, "learning_rate": 7.667470078520966e-06, "loss": 0.3665, "step": 963 }, { "epoch": 1.76, "learning_rate": 7.648237028218676e-06, "loss": 0.3944, "step": 964 }, { "epoch": 1.76, "learning_rate": 7.6290131822458554e-06, "loss": 0.3958, "step": 965 }, { "epoch": 1.77, "learning_rate": 7.609798615840785e-06, "loss": 0.3705, "step": 966 }, { "epoch": 1.77, "learning_rate": 7.590593404205432e-06, "loss": 0.3614, "step": 967 }, { "epoch": 1.77, "learning_rate": 7.571397622505151e-06, "loss": 0.3722, "step": 968 }, { "epoch": 1.77, "learning_rate": 7.552211345868388e-06, "loss": 0.3805, "step": 969 }, { "epoch": 1.77, "learning_rate": 7.533034649386385e-06, "loss": 0.3705, "step": 970 }, { "epoch": 1.78, "learning_rate": 7.513867608112901e-06, "loss": 0.3765, "step": 971 }, { "epoch": 1.78, "learning_rate": 7.494710297063894e-06, "loss": 0.3618, "step": 972 }, { "epoch": 1.78, "learning_rate": 7.4755627912172405e-06, "loss": 0.3753, "step": 973 }, { "epoch": 1.78, "learning_rate": 7.456425165512453e-06, "loss": 0.3808, "step": 974 }, { "epoch": 1.78, "learning_rate": 7.437297494850362e-06, "loss": 0.3847, "step": 975 }, { "epoch": 1.78, "learning_rate": 7.418179854092842e-06, "loss": 0.3931, "step": 976 }, { "epoch": 1.79, "learning_rate": 7.399072318062514e-06, "loss": 0.3744, "step": 977 }, { "epoch": 1.79, "learning_rate": 7.379974961542447e-06, "loss": 0.3786, "step": 978 }, { "epoch": 1.79, "learning_rate": 7.3608878592758695e-06, "loss": 0.383, "step": 979 }, { "epoch": 1.79, "learning_rate": 7.341811085965884e-06, "loss": 0.3758, "step": 980 }, { "epoch": 1.79, "learning_rate": 7.322744716275159e-06, "loss": 0.3809, "step": 981 }, { "epoch": 1.8, "learning_rate": 7.303688824825648e-06, "loss": 0.3748, "step": 982 }, { "epoch": 1.8, "learning_rate": 7.2846434861982905e-06, "loss": 0.3634, "step": 983 }, { "epoch": 1.8, "learning_rate": 7.2656087749327385e-06, "loss": 0.3976, "step": 984 }, { "epoch": 1.8, "learning_rate": 7.246584765527038e-06, "loss": 0.3683, "step": 985 }, { "epoch": 1.8, "learning_rate": 7.22757153243735e-06, "loss": 0.3628, "step": 986 }, { "epoch": 1.8, "learning_rate": 7.208569150077668e-06, "loss": 0.3715, "step": 987 }, { "epoch": 1.81, "learning_rate": 7.189577692819508e-06, "loss": 0.3725, "step": 988 }, { "epoch": 1.81, "learning_rate": 7.170597234991632e-06, "loss": 0.3686, "step": 989 }, { "epoch": 1.81, "learning_rate": 7.151627850879757e-06, "loss": 0.3601, "step": 990 }, { "epoch": 1.81, "learning_rate": 7.132669614726249e-06, "loss": 0.3532, "step": 991 }, { "epoch": 1.81, "learning_rate": 7.113722600729848e-06, "loss": 0.3715, "step": 992 }, { "epoch": 1.82, "learning_rate": 7.094786883045383e-06, "loss": 0.3907, "step": 993 }, { "epoch": 1.82, "learning_rate": 7.075862535783454e-06, "loss": 0.359, "step": 994 }, { "epoch": 1.82, "learning_rate": 7.056949633010166e-06, "loss": 0.3632, "step": 995 }, { "epoch": 1.82, "learning_rate": 7.038048248746842e-06, "loss": 0.3876, "step": 996 }, { "epoch": 1.82, "learning_rate": 7.019158456969714e-06, "loss": 0.3827, "step": 997 }, { "epoch": 1.82, "learning_rate": 7.000280331609641e-06, "loss": 0.3578, "step": 998 }, { "epoch": 1.83, "learning_rate": 6.981413946551832e-06, "loss": 0.3849, "step": 999 }, { "epoch": 1.83, "learning_rate": 6.962559375635536e-06, "loss": 0.3857, "step": 1000 }, { "epoch": 1.83, "learning_rate": 6.943716692653771e-06, "loss": 0.3659, "step": 1001 }, { "epoch": 1.83, "learning_rate": 6.924885971353027e-06, "loss": 0.3739, "step": 1002 }, { "epoch": 1.83, "learning_rate": 6.906067285432978e-06, "loss": 0.3648, "step": 1003 }, { "epoch": 1.84, "learning_rate": 6.8872607085461875e-06, "loss": 0.3642, "step": 1004 }, { "epoch": 1.84, "learning_rate": 6.868466314297841e-06, "loss": 0.3777, "step": 1005 }, { "epoch": 1.84, "learning_rate": 6.849684176245432e-06, "loss": 0.367, "step": 1006 }, { "epoch": 1.84, "learning_rate": 6.830914367898485e-06, "loss": 0.3904, "step": 1007 }, { "epoch": 1.84, "learning_rate": 6.812156962718279e-06, "loss": 0.3662, "step": 1008 }, { "epoch": 1.85, "learning_rate": 6.793412034117537e-06, "loss": 0.3596, "step": 1009 }, { "epoch": 1.85, "learning_rate": 6.774679655460159e-06, "loss": 0.3785, "step": 1010 }, { "epoch": 1.85, "learning_rate": 6.755959900060925e-06, "loss": 0.3715, "step": 1011 }, { "epoch": 1.85, "learning_rate": 6.737252841185212e-06, "loss": 0.3673, "step": 1012 }, { "epoch": 1.85, "learning_rate": 6.718558552048701e-06, "loss": 0.3782, "step": 1013 }, { "epoch": 1.85, "learning_rate": 6.699877105817093e-06, "loss": 0.3803, "step": 1014 }, { "epoch": 1.86, "learning_rate": 6.6812085756058394e-06, "loss": 0.3609, "step": 1015 }, { "epoch": 1.86, "learning_rate": 6.662553034479824e-06, "loss": 0.3797, "step": 1016 }, { "epoch": 1.86, "learning_rate": 6.643910555453094e-06, "loss": 0.3638, "step": 1017 }, { "epoch": 1.86, "learning_rate": 6.625281211488592e-06, "loss": 0.364, "step": 1018 }, { "epoch": 1.86, "learning_rate": 6.606665075497835e-06, "loss": 0.3955, "step": 1019 }, { "epoch": 1.87, "learning_rate": 6.588062220340651e-06, "loss": 0.373, "step": 1020 }, { "epoch": 1.87, "learning_rate": 6.569472718824894e-06, "loss": 0.3893, "step": 1021 }, { "epoch": 1.87, "learning_rate": 6.55089664370615e-06, "loss": 0.3562, "step": 1022 }, { "epoch": 1.87, "learning_rate": 6.532334067687458e-06, "loss": 0.3911, "step": 1023 }, { "epoch": 1.87, "learning_rate": 6.513785063419025e-06, "loss": 0.3592, "step": 1024 }, { "epoch": 1.87, "learning_rate": 6.4952497034979415e-06, "loss": 0.3709, "step": 1025 }, { "epoch": 1.88, "learning_rate": 6.47672806046789e-06, "loss": 0.3692, "step": 1026 }, { "epoch": 1.88, "learning_rate": 6.45822020681888e-06, "loss": 0.3548, "step": 1027 }, { "epoch": 1.88, "learning_rate": 6.4397262149869475e-06, "loss": 0.3748, "step": 1028 }, { "epoch": 1.88, "learning_rate": 6.421246157353863e-06, "loss": 0.404, "step": 1029 }, { "epoch": 1.88, "learning_rate": 6.402780106246884e-06, "loss": 0.3677, "step": 1030 }, { "epoch": 1.89, "learning_rate": 6.384328133938432e-06, "loss": 0.3834, "step": 1031 }, { "epoch": 1.89, "learning_rate": 6.365890312645833e-06, "loss": 0.3599, "step": 1032 }, { "epoch": 1.89, "learning_rate": 6.347466714531031e-06, "loss": 0.3856, "step": 1033 }, { "epoch": 1.89, "learning_rate": 6.329057411700299e-06, "loss": 0.3641, "step": 1034 }, { "epoch": 1.89, "learning_rate": 6.310662476203959e-06, "loss": 0.3804, "step": 1035 }, { "epoch": 1.89, "learning_rate": 6.292281980036116e-06, "loss": 0.3792, "step": 1036 }, { "epoch": 1.9, "learning_rate": 6.2739159951343435e-06, "loss": 0.3855, "step": 1037 }, { "epoch": 1.9, "learning_rate": 6.25556459337943e-06, "loss": 0.3672, "step": 1038 }, { "epoch": 1.9, "learning_rate": 6.237227846595093e-06, "loss": 0.3656, "step": 1039 }, { "epoch": 1.9, "learning_rate": 6.218905826547688e-06, "loss": 0.3711, "step": 1040 }, { "epoch": 1.9, "learning_rate": 6.200598604945929e-06, "loss": 0.3792, "step": 1041 }, { "epoch": 1.91, "learning_rate": 6.1823062534406196e-06, "loss": 0.3718, "step": 1042 }, { "epoch": 1.91, "learning_rate": 6.1640288436243635e-06, "loss": 0.3758, "step": 1043 }, { "epoch": 1.91, "learning_rate": 6.14576644703128e-06, "loss": 0.3754, "step": 1044 }, { "epoch": 1.91, "learning_rate": 6.127519135136732e-06, "loss": 0.3731, "step": 1045 }, { "epoch": 1.91, "learning_rate": 6.109286979357052e-06, "loss": 0.3542, "step": 1046 }, { "epoch": 1.91, "learning_rate": 6.091070051049241e-06, "loss": 0.3595, "step": 1047 }, { "epoch": 1.92, "learning_rate": 6.072868421510711e-06, "loss": 0.397, "step": 1048 }, { "epoch": 1.92, "learning_rate": 6.0546821619790005e-06, "loss": 0.3925, "step": 1049 }, { "epoch": 1.92, "learning_rate": 6.036511343631488e-06, "loss": 0.3714, "step": 1050 }, { "epoch": 1.92, "learning_rate": 6.0183560375851095e-06, "loss": 0.371, "step": 1051 }, { "epoch": 1.92, "learning_rate": 6.00021631489611e-06, "loss": 0.3731, "step": 1052 }, { "epoch": 1.93, "learning_rate": 5.982092246559728e-06, "loss": 0.386, "step": 1053 }, { "epoch": 1.93, "learning_rate": 5.963983903509936e-06, "loss": 0.3633, "step": 1054 }, { "epoch": 1.93, "learning_rate": 5.945891356619166e-06, "loss": 0.3781, "step": 1055 }, { "epoch": 1.93, "learning_rate": 5.927814676698027e-06, "loss": 0.3689, "step": 1056 }, { "epoch": 1.93, "learning_rate": 5.909753934495019e-06, "loss": 0.3588, "step": 1057 }, { "epoch": 1.93, "learning_rate": 5.891709200696281e-06, "loss": 0.3772, "step": 1058 }, { "epoch": 1.94, "learning_rate": 5.873680545925281e-06, "loss": 0.3636, "step": 1059 }, { "epoch": 1.94, "learning_rate": 5.855668040742564e-06, "loss": 0.3679, "step": 1060 }, { "epoch": 1.94, "learning_rate": 5.837671755645473e-06, "loss": 0.3825, "step": 1061 }, { "epoch": 1.94, "learning_rate": 5.819691761067866e-06, "loss": 0.3932, "step": 1062 }, { "epoch": 1.94, "learning_rate": 5.801728127379837e-06, "loss": 0.3792, "step": 1063 }, { "epoch": 1.95, "learning_rate": 5.783780924887462e-06, "loss": 0.3635, "step": 1064 }, { "epoch": 1.95, "learning_rate": 5.765850223832489e-06, "loss": 0.3677, "step": 1065 }, { "epoch": 1.95, "learning_rate": 5.74793609439209e-06, "loss": 0.3854, "step": 1066 }, { "epoch": 1.95, "learning_rate": 5.730038606678593e-06, "loss": 0.3634, "step": 1067 }, { "epoch": 1.95, "learning_rate": 5.712157830739176e-06, "loss": 0.381, "step": 1068 }, { "epoch": 1.95, "learning_rate": 5.69429383655561e-06, "loss": 0.3723, "step": 1069 }, { "epoch": 1.96, "learning_rate": 5.676446694044003e-06, "loss": 0.3711, "step": 1070 }, { "epoch": 1.96, "learning_rate": 5.658616473054495e-06, "loss": 0.3741, "step": 1071 }, { "epoch": 1.96, "learning_rate": 5.640803243370997e-06, "loss": 0.3747, "step": 1072 }, { "epoch": 1.96, "learning_rate": 5.623007074710928e-06, "loss": 0.3629, "step": 1073 }, { "epoch": 1.96, "learning_rate": 5.605228036724928e-06, "loss": 0.3681, "step": 1074 }, { "epoch": 1.97, "learning_rate": 5.587466198996592e-06, "loss": 0.3885, "step": 1075 }, { "epoch": 1.97, "learning_rate": 5.569721631042193e-06, "loss": 0.3743, "step": 1076 }, { "epoch": 1.97, "learning_rate": 5.551994402310428e-06, "loss": 0.3781, "step": 1077 }, { "epoch": 1.97, "learning_rate": 5.5342845821821145e-06, "loss": 0.3666, "step": 1078 }, { "epoch": 1.97, "learning_rate": 5.51659223996994e-06, "loss": 0.3805, "step": 1079 }, { "epoch": 1.97, "learning_rate": 5.498917444918199e-06, "loss": 0.3554, "step": 1080 }, { "epoch": 1.98, "learning_rate": 5.481260266202496e-06, "loss": 0.3702, "step": 1081 }, { "epoch": 1.98, "learning_rate": 5.463620772929494e-06, "loss": 0.3821, "step": 1082 }, { "epoch": 1.98, "learning_rate": 5.445999034136637e-06, "loss": 0.3757, "step": 1083 }, { "epoch": 1.98, "learning_rate": 5.428395118791887e-06, "loss": 0.3588, "step": 1084 }, { "epoch": 1.98, "learning_rate": 5.410809095793436e-06, "loss": 0.3819, "step": 1085 }, { "epoch": 1.99, "learning_rate": 5.393241033969466e-06, "loss": 0.3716, "step": 1086 }, { "epoch": 1.99, "learning_rate": 5.375691002077853e-06, "loss": 0.3851, "step": 1087 }, { "epoch": 1.99, "learning_rate": 5.358159068805902e-06, "loss": 0.3566, "step": 1088 }, { "epoch": 1.99, "learning_rate": 5.340645302770097e-06, "loss": 0.3563, "step": 1089 }, { "epoch": 1.99, "learning_rate": 5.323149772515812e-06, "loss": 0.3708, "step": 1090 }, { "epoch": 1.99, "learning_rate": 5.305672546517047e-06, "loss": 0.3732, "step": 1091 }, { "epoch": 2.0, "learning_rate": 5.288213693176165e-06, "loss": 0.3659, "step": 1092 }, { "epoch": 2.0, "learning_rate": 5.270773280823627e-06, "loss": 0.3716, "step": 1093 }, { "epoch": 2.0, "learning_rate": 5.253351377717707e-06, "loss": 0.3442, "step": 1094 }, { "epoch": 2.0, "learning_rate": 5.235948052044255e-06, "loss": 0.238, "step": 1095 }, { "epoch": 2.0, "learning_rate": 5.218563371916403e-06, "loss": 0.2582, "step": 1096 }, { "epoch": 2.01, "learning_rate": 5.2011974053743005e-06, "loss": 0.2428, "step": 1097 }, { "epoch": 2.01, "learning_rate": 5.183850220384874e-06, "loss": 0.23, "step": 1098 }, { "epoch": 2.01, "learning_rate": 5.166521884841533e-06, "loss": 0.2213, "step": 1099 }, { "epoch": 2.01, "learning_rate": 5.149212466563901e-06, "loss": 0.241, "step": 1100 }, { "epoch": 2.01, "learning_rate": 5.131922033297587e-06, "loss": 0.2402, "step": 1101 }, { "epoch": 2.02, "learning_rate": 5.114650652713885e-06, "loss": 0.2182, "step": 1102 }, { "epoch": 2.02, "learning_rate": 5.097398392409514e-06, "loss": 0.2325, "step": 1103 }, { "epoch": 2.02, "learning_rate": 5.0801653199063745e-06, "loss": 0.2307, "step": 1104 }, { "epoch": 2.02, "learning_rate": 5.062951502651261e-06, "loss": 0.2159, "step": 1105 }, { "epoch": 2.02, "learning_rate": 5.045757008015606e-06, "loss": 0.2085, "step": 1106 }, { "epoch": 2.02, "learning_rate": 5.0285819032952195e-06, "loss": 0.2257, "step": 1107 }, { "epoch": 2.03, "learning_rate": 5.0114262557100246e-06, "loss": 0.227, "step": 1108 }, { "epoch": 2.03, "learning_rate": 4.99429013240379e-06, "loss": 0.2344, "step": 1109 }, { "epoch": 2.03, "learning_rate": 4.9771736004438685e-06, "loss": 0.2166, "step": 1110 }, { "epoch": 2.03, "learning_rate": 4.960076726820947e-06, "loss": 0.2376, "step": 1111 }, { "epoch": 2.03, "learning_rate": 4.942999578448763e-06, "loss": 0.2309, "step": 1112 }, { "epoch": 2.04, "learning_rate": 4.925942222163852e-06, "loss": 0.2286, "step": 1113 }, { "epoch": 2.04, "learning_rate": 4.908904724725299e-06, "loss": 0.2108, "step": 1114 }, { "epoch": 2.04, "learning_rate": 4.8918871528144574e-06, "loss": 0.229, "step": 1115 }, { "epoch": 2.04, "learning_rate": 4.874889573034693e-06, "loss": 0.2102, "step": 1116 }, { "epoch": 2.04, "learning_rate": 4.857912051911131e-06, "loss": 0.2198, "step": 1117 }, { "epoch": 2.04, "learning_rate": 4.840954655890392e-06, "loss": 0.239, "step": 1118 }, { "epoch": 2.05, "learning_rate": 4.824017451340325e-06, "loss": 0.226, "step": 1119 }, { "epoch": 2.05, "learning_rate": 4.8071005045497644e-06, "loss": 0.2263, "step": 1120 }, { "epoch": 2.05, "learning_rate": 4.7902038817282504e-06, "loss": 0.2212, "step": 1121 }, { "epoch": 2.05, "learning_rate": 4.773327649005778e-06, "loss": 0.2362, "step": 1122 }, { "epoch": 2.05, "learning_rate": 4.756471872432551e-06, "loss": 0.2148, "step": 1123 }, { "epoch": 2.06, "learning_rate": 4.739636617978701e-06, "loss": 0.2317, "step": 1124 }, { "epoch": 2.06, "learning_rate": 4.7228219515340446e-06, "loss": 0.243, "step": 1125 }, { "epoch": 2.06, "learning_rate": 4.706027938907819e-06, "loss": 0.2238, "step": 1126 }, { "epoch": 2.06, "learning_rate": 4.689254645828427e-06, "loss": 0.2252, "step": 1127 }, { "epoch": 2.06, "learning_rate": 4.6725021379431764e-06, "loss": 0.2343, "step": 1128 }, { "epoch": 2.06, "learning_rate": 4.655770480818039e-06, "loss": 0.2297, "step": 1129 }, { "epoch": 2.07, "learning_rate": 4.639059739937365e-06, "loss": 0.233, "step": 1130 }, { "epoch": 2.07, "learning_rate": 4.622369980703645e-06, "loss": 0.2335, "step": 1131 }, { "epoch": 2.07, "learning_rate": 4.605701268437265e-06, "loss": 0.2341, "step": 1132 }, { "epoch": 2.07, "learning_rate": 4.589053668376222e-06, "loss": 0.2298, "step": 1133 }, { "epoch": 2.07, "learning_rate": 4.572427245675891e-06, "loss": 0.2288, "step": 1134 }, { "epoch": 2.08, "learning_rate": 4.555822065408762e-06, "loss": 0.2173, "step": 1135 }, { "epoch": 2.08, "learning_rate": 4.539238192564187e-06, "loss": 0.2377, "step": 1136 }, { "epoch": 2.08, "learning_rate": 4.522675692048123e-06, "loss": 0.2165, "step": 1137 }, { "epoch": 2.08, "learning_rate": 4.506134628682878e-06, "loss": 0.219, "step": 1138 }, { "epoch": 2.08, "learning_rate": 4.489615067206869e-06, "loss": 0.2225, "step": 1139 }, { "epoch": 2.08, "learning_rate": 4.473117072274352e-06, "loss": 0.2371, "step": 1140 }, { "epoch": 2.09, "learning_rate": 4.45664070845517e-06, "loss": 0.2341, "step": 1141 }, { "epoch": 2.09, "learning_rate": 4.440186040234524e-06, "loss": 0.2222, "step": 1142 }, { "epoch": 2.09, "learning_rate": 4.423753132012681e-06, "loss": 0.2418, "step": 1143 }, { "epoch": 2.09, "learning_rate": 4.407342048104753e-06, "loss": 0.255, "step": 1144 }, { "epoch": 2.09, "learning_rate": 4.390952852740445e-06, "loss": 0.2225, "step": 1145 }, { "epoch": 2.1, "learning_rate": 4.374585610063784e-06, "loss": 0.2304, "step": 1146 }, { "epoch": 2.1, "learning_rate": 4.358240384132876e-06, "loss": 0.2242, "step": 1147 }, { "epoch": 2.1, "learning_rate": 4.341917238919671e-06, "loss": 0.2019, "step": 1148 }, { "epoch": 2.1, "learning_rate": 4.325616238309687e-06, "loss": 0.228, "step": 1149 }, { "epoch": 2.1, "learning_rate": 4.309337446101779e-06, "loss": 0.236, "step": 1150 }, { "epoch": 2.1, "learning_rate": 4.293080926007878e-06, "loss": 0.2225, "step": 1151 }, { "epoch": 2.11, "learning_rate": 4.2768467416527536e-06, "loss": 0.2296, "step": 1152 }, { "epoch": 2.11, "learning_rate": 4.260634956573746e-06, "loss": 0.2249, "step": 1153 }, { "epoch": 2.11, "learning_rate": 4.244445634220545e-06, "loss": 0.2215, "step": 1154 }, { "epoch": 2.11, "learning_rate": 4.228278837954914e-06, "loss": 0.2291, "step": 1155 }, { "epoch": 2.11, "learning_rate": 4.212134631050453e-06, "loss": 0.2361, "step": 1156 }, { "epoch": 2.12, "learning_rate": 4.196013076692363e-06, "loss": 0.2341, "step": 1157 }, { "epoch": 2.12, "learning_rate": 4.179914237977177e-06, "loss": 0.2222, "step": 1158 }, { "epoch": 2.12, "learning_rate": 4.163838177912527e-06, "loss": 0.2285, "step": 1159 }, { "epoch": 2.12, "learning_rate": 4.147784959416894e-06, "loss": 0.2218, "step": 1160 }, { "epoch": 2.12, "learning_rate": 4.13175464531936e-06, "loss": 0.2199, "step": 1161 }, { "epoch": 2.12, "learning_rate": 4.1157472983593636e-06, "loss": 0.2321, "step": 1162 }, { "epoch": 2.13, "learning_rate": 4.099762981186463e-06, "loss": 0.2171, "step": 1163 }, { "epoch": 2.13, "learning_rate": 4.083801756360071e-06, "loss": 0.2307, "step": 1164 }, { "epoch": 2.13, "learning_rate": 4.067863686349226e-06, "loss": 0.22, "step": 1165 }, { "epoch": 2.13, "learning_rate": 4.051948833532342e-06, "loss": 0.219, "step": 1166 }, { "epoch": 2.13, "learning_rate": 4.036057260196973e-06, "loss": 0.2258, "step": 1167 }, { "epoch": 2.14, "learning_rate": 4.02018902853955e-06, "loss": 0.2309, "step": 1168 }, { "epoch": 2.14, "learning_rate": 4.004344200665159e-06, "loss": 0.2321, "step": 1169 }, { "epoch": 2.14, "learning_rate": 3.988522838587281e-06, "loss": 0.217, "step": 1170 }, { "epoch": 2.14, "learning_rate": 3.972725004227561e-06, "loss": 0.2199, "step": 1171 }, { "epoch": 2.14, "learning_rate": 3.956950759415556e-06, "loss": 0.2276, "step": 1172 }, { "epoch": 2.14, "learning_rate": 3.9412001658885114e-06, "loss": 0.2356, "step": 1173 }, { "epoch": 2.15, "learning_rate": 3.925473285291092e-06, "loss": 0.2261, "step": 1174 }, { "epoch": 2.15, "learning_rate": 3.909770179175155e-06, "loss": 0.2175, "step": 1175 }, { "epoch": 2.15, "learning_rate": 3.894090908999524e-06, "loss": 0.2233, "step": 1176 }, { "epoch": 2.15, "learning_rate": 3.878435536129721e-06, "loss": 0.2272, "step": 1177 }, { "epoch": 2.15, "learning_rate": 3.862804121837733e-06, "loss": 0.2215, "step": 1178 }, { "epoch": 2.16, "learning_rate": 3.847196727301796e-06, "loss": 0.2259, "step": 1179 }, { "epoch": 2.16, "learning_rate": 3.831613413606124e-06, "loss": 0.2329, "step": 1180 }, { "epoch": 2.16, "learning_rate": 3.816054241740685e-06, "loss": 0.2217, "step": 1181 }, { "epoch": 2.16, "learning_rate": 3.8005192726009664e-06, "loss": 0.2215, "step": 1182 }, { "epoch": 2.16, "learning_rate": 3.785008566987728e-06, "loss": 0.2322, "step": 1183 }, { "epoch": 2.17, "learning_rate": 3.7695221856067597e-06, "loss": 0.2227, "step": 1184 }, { "epoch": 2.17, "learning_rate": 3.754060189068671e-06, "loss": 0.2436, "step": 1185 }, { "epoch": 2.17, "learning_rate": 3.7386226378886082e-06, "loss": 0.2193, "step": 1186 }, { "epoch": 2.17, "learning_rate": 3.723209592486059e-06, "loss": 0.2235, "step": 1187 }, { "epoch": 2.17, "learning_rate": 3.707821113184601e-06, "loss": 0.2304, "step": 1188 }, { "epoch": 2.17, "learning_rate": 3.6924572602116606e-06, "loss": 0.2248, "step": 1189 }, { "epoch": 2.18, "learning_rate": 3.6771180936982785e-06, "loss": 0.2369, "step": 1190 }, { "epoch": 2.18, "learning_rate": 3.6618036736788888e-06, "loss": 0.2376, "step": 1191 }, { "epoch": 2.18, "learning_rate": 3.646514060091061e-06, "loss": 0.2486, "step": 1192 }, { "epoch": 2.18, "learning_rate": 3.6312493127752835e-06, "loss": 0.2493, "step": 1193 }, { "epoch": 2.18, "learning_rate": 3.61600949147472e-06, "loss": 0.2367, "step": 1194 }, { "epoch": 2.19, "learning_rate": 3.6007946558349815e-06, "loss": 0.24, "step": 1195 }, { "epoch": 2.19, "learning_rate": 3.5856048654038867e-06, "loss": 0.2247, "step": 1196 }, { "epoch": 2.19, "learning_rate": 3.570440179631234e-06, "loss": 0.225, "step": 1197 }, { "epoch": 2.19, "learning_rate": 3.555300657868571e-06, "loss": 0.2321, "step": 1198 }, { "epoch": 2.19, "learning_rate": 3.5401863593689554e-06, "loss": 0.2221, "step": 1199 }, { "epoch": 2.19, "learning_rate": 3.5250973432867195e-06, "loss": 0.2307, "step": 1200 }, { "epoch": 2.2, "learning_rate": 3.5100336686772596e-06, "loss": 0.2337, "step": 1201 }, { "epoch": 2.2, "learning_rate": 3.4949953944967785e-06, "loss": 0.2388, "step": 1202 }, { "epoch": 2.2, "learning_rate": 3.4799825796020716e-06, "loss": 0.22, "step": 1203 }, { "epoch": 2.2, "learning_rate": 3.46499528275029e-06, "loss": 0.2314, "step": 1204 }, { "epoch": 2.2, "learning_rate": 3.450033562598714e-06, "loss": 0.2283, "step": 1205 }, { "epoch": 2.21, "learning_rate": 3.4350974777045175e-06, "loss": 0.2371, "step": 1206 }, { "epoch": 2.21, "learning_rate": 3.4201870865245525e-06, "loss": 0.2307, "step": 1207 }, { "epoch": 2.21, "learning_rate": 3.4053024474151032e-06, "loss": 0.2241, "step": 1208 }, { "epoch": 2.21, "learning_rate": 3.3904436186316636e-06, "loss": 0.2346, "step": 1209 }, { "epoch": 2.21, "learning_rate": 3.3756106583287206e-06, "loss": 0.2175, "step": 1210 }, { "epoch": 2.21, "learning_rate": 3.360803624559509e-06, "loss": 0.2314, "step": 1211 }, { "epoch": 2.22, "learning_rate": 3.346022575275795e-06, "loss": 0.2318, "step": 1212 }, { "epoch": 2.22, "learning_rate": 3.3312675683276453e-06, "loss": 0.2212, "step": 1213 }, { "epoch": 2.22, "learning_rate": 3.3165386614632045e-06, "loss": 0.2371, "step": 1214 }, { "epoch": 2.22, "learning_rate": 3.3018359123284604e-06, "loss": 0.2321, "step": 1215 }, { "epoch": 2.22, "learning_rate": 3.2871593784670386e-06, "loss": 0.2155, "step": 1216 }, { "epoch": 2.23, "learning_rate": 3.2725091173199497e-06, "loss": 0.2462, "step": 1217 }, { "epoch": 2.23, "learning_rate": 3.2578851862253802e-06, "loss": 0.2124, "step": 1218 }, { "epoch": 2.23, "learning_rate": 3.2432876424184756e-06, "loss": 0.2309, "step": 1219 }, { "epoch": 2.23, "learning_rate": 3.2287165430310985e-06, "loss": 0.2306, "step": 1220 }, { "epoch": 2.23, "learning_rate": 3.2141719450916065e-06, "loss": 0.228, "step": 1221 }, { "epoch": 2.23, "learning_rate": 3.1996539055246543e-06, "loss": 0.223, "step": 1222 }, { "epoch": 2.24, "learning_rate": 3.1851624811509385e-06, "loss": 0.2313, "step": 1223 }, { "epoch": 2.24, "learning_rate": 3.17069772868699e-06, "loss": 0.2217, "step": 1224 }, { "epoch": 2.24, "learning_rate": 3.1562597047449597e-06, "loss": 0.2358, "step": 1225 }, { "epoch": 2.24, "learning_rate": 3.141848465832381e-06, "loss": 0.2052, "step": 1226 }, { "epoch": 2.24, "learning_rate": 3.1274640683519577e-06, "loss": 0.2137, "step": 1227 }, { "epoch": 2.25, "learning_rate": 3.1131065686013417e-06, "loss": 0.22, "step": 1228 }, { "epoch": 2.25, "learning_rate": 3.0987760227729124e-06, "loss": 0.2189, "step": 1229 }, { "epoch": 2.25, "learning_rate": 3.084472486953558e-06, "loss": 0.2226, "step": 1230 }, { "epoch": 2.25, "learning_rate": 3.0701960171244504e-06, "loss": 0.2232, "step": 1231 }, { "epoch": 2.25, "learning_rate": 3.055946669160841e-06, "loss": 0.2341, "step": 1232 }, { "epoch": 2.25, "learning_rate": 3.0417244988318217e-06, "loss": 0.2355, "step": 1233 }, { "epoch": 2.26, "learning_rate": 3.0275295618001177e-06, "loss": 0.2165, "step": 1234 }, { "epoch": 2.26, "learning_rate": 3.0133619136218772e-06, "loss": 0.2178, "step": 1235 }, { "epoch": 2.26, "learning_rate": 2.9992216097464346e-06, "loss": 0.2284, "step": 1236 }, { "epoch": 2.26, "learning_rate": 2.98510870551611e-06, "loss": 0.2317, "step": 1237 }, { "epoch": 2.26, "learning_rate": 2.9710232561659834e-06, "loss": 0.2226, "step": 1238 }, { "epoch": 2.27, "learning_rate": 2.9569653168236847e-06, "loss": 0.2357, "step": 1239 }, { "epoch": 2.27, "learning_rate": 2.942934942509171e-06, "loss": 0.2228, "step": 1240 }, { "epoch": 2.27, "learning_rate": 2.9289321881345257e-06, "loss": 0.2308, "step": 1241 }, { "epoch": 2.27, "learning_rate": 2.914957108503722e-06, "loss": 0.2207, "step": 1242 }, { "epoch": 2.27, "learning_rate": 2.9010097583124208e-06, "loss": 0.2319, "step": 1243 }, { "epoch": 2.27, "learning_rate": 2.8870901921477656e-06, "loss": 0.2325, "step": 1244 }, { "epoch": 2.28, "learning_rate": 2.873198464488147e-06, "loss": 0.2352, "step": 1245 }, { "epoch": 2.28, "learning_rate": 2.8593346297030077e-06, "loss": 0.2267, "step": 1246 }, { "epoch": 2.28, "learning_rate": 2.8454987420526215e-06, "loss": 0.2375, "step": 1247 }, { "epoch": 2.28, "learning_rate": 2.831690855687882e-06, "loss": 0.2489, "step": 1248 }, { "epoch": 2.28, "learning_rate": 2.8179110246500905e-06, "loss": 0.2138, "step": 1249 }, { "epoch": 2.29, "learning_rate": 2.8041593028707513e-06, "loss": 0.2278, "step": 1250 }, { "epoch": 2.29, "learning_rate": 2.790435744171348e-06, "loss": 0.2378, "step": 1251 }, { "epoch": 2.29, "learning_rate": 2.7767404022631404e-06, "loss": 0.2267, "step": 1252 }, { "epoch": 2.29, "learning_rate": 2.7630733307469593e-06, "loss": 0.2359, "step": 1253 }, { "epoch": 2.29, "learning_rate": 2.749434583112984e-06, "loss": 0.2303, "step": 1254 }, { "epoch": 2.29, "learning_rate": 2.7358242127405434e-06, "loss": 0.2433, "step": 1255 }, { "epoch": 2.3, "learning_rate": 2.7222422728979015e-06, "loss": 0.2192, "step": 1256 }, { "epoch": 2.3, "learning_rate": 2.708688816742051e-06, "loss": 0.2309, "step": 1257 }, { "epoch": 2.3, "learning_rate": 2.695163897318508e-06, "loss": 0.2202, "step": 1258 }, { "epoch": 2.3, "learning_rate": 2.681667567561095e-06, "loss": 0.2278, "step": 1259 }, { "epoch": 2.3, "learning_rate": 2.668199880291751e-06, "loss": 0.2145, "step": 1260 }, { "epoch": 2.31, "learning_rate": 2.6547608882203056e-06, "loss": 0.223, "step": 1261 }, { "epoch": 2.31, "learning_rate": 2.6413506439442804e-06, "loss": 0.2479, "step": 1262 }, { "epoch": 2.31, "learning_rate": 2.6279691999486945e-06, "loss": 0.2328, "step": 1263 }, { "epoch": 2.31, "learning_rate": 2.614616608605833e-06, "loss": 0.2407, "step": 1264 }, { "epoch": 2.31, "learning_rate": 2.601292922175066e-06, "loss": 0.2036, "step": 1265 }, { "epoch": 2.31, "learning_rate": 2.587998192802639e-06, "loss": 0.2284, "step": 1266 }, { "epoch": 2.32, "learning_rate": 2.5747324725214595e-06, "loss": 0.2138, "step": 1267 }, { "epoch": 2.32, "learning_rate": 2.5614958132508983e-06, "loss": 0.2319, "step": 1268 }, { "epoch": 2.32, "learning_rate": 2.5482882667965945e-06, "loss": 0.2272, "step": 1269 }, { "epoch": 2.32, "learning_rate": 2.5351098848502385e-06, "loss": 0.2344, "step": 1270 }, { "epoch": 2.32, "learning_rate": 2.5219607189893804e-06, "loss": 0.234, "step": 1271 }, { "epoch": 2.33, "learning_rate": 2.508840820677221e-06, "loss": 0.2281, "step": 1272 }, { "epoch": 2.33, "learning_rate": 2.495750241262417e-06, "loss": 0.2278, "step": 1273 }, { "epoch": 2.33, "learning_rate": 2.482689031978872e-06, "loss": 0.2355, "step": 1274 }, { "epoch": 2.33, "learning_rate": 2.4696572439455503e-06, "loss": 0.2283, "step": 1275 }, { "epoch": 2.33, "learning_rate": 2.4566549281662587e-06, "loss": 0.2226, "step": 1276 }, { "epoch": 2.34, "learning_rate": 2.443682135529456e-06, "loss": 0.2282, "step": 1277 }, { "epoch": 2.34, "learning_rate": 2.430738916808061e-06, "loss": 0.2181, "step": 1278 }, { "epoch": 2.34, "learning_rate": 2.417825322659236e-06, "loss": 0.2316, "step": 1279 }, { "epoch": 2.34, "learning_rate": 2.4049414036242057e-06, "loss": 0.2322, "step": 1280 }, { "epoch": 2.34, "learning_rate": 2.392087210128048e-06, "loss": 0.2192, "step": 1281 }, { "epoch": 2.34, "learning_rate": 2.379262792479504e-06, "loss": 0.2271, "step": 1282 }, { "epoch": 2.35, "learning_rate": 2.3664682008707753e-06, "loss": 0.2293, "step": 1283 }, { "epoch": 2.35, "learning_rate": 2.3537034853773357e-06, "loss": 0.2374, "step": 1284 }, { "epoch": 2.35, "learning_rate": 2.340968695957724e-06, "loss": 0.2176, "step": 1285 }, { "epoch": 2.35, "learning_rate": 2.328263882453353e-06, "loss": 0.2213, "step": 1286 }, { "epoch": 2.35, "learning_rate": 2.3155890945883274e-06, "loss": 0.2323, "step": 1287 }, { "epoch": 2.36, "learning_rate": 2.3029443819692255e-06, "loss": 0.229, "step": 1288 }, { "epoch": 2.36, "learning_rate": 2.29032979408492e-06, "loss": 0.2237, "step": 1289 }, { "epoch": 2.36, "learning_rate": 2.2777453803063834e-06, "loss": 0.2139, "step": 1290 }, { "epoch": 2.36, "learning_rate": 2.265191189886492e-06, "loss": 0.2132, "step": 1291 }, { "epoch": 2.36, "learning_rate": 2.252667271959834e-06, "loss": 0.2254, "step": 1292 }, { "epoch": 2.36, "learning_rate": 2.240173675542513e-06, "loss": 0.2262, "step": 1293 }, { "epoch": 2.37, "learning_rate": 2.2277104495319714e-06, "loss": 0.2137, "step": 1294 }, { "epoch": 2.37, "learning_rate": 2.215277642706778e-06, "loss": 0.2216, "step": 1295 }, { "epoch": 2.37, "learning_rate": 2.202875303726445e-06, "loss": 0.2329, "step": 1296 }, { "epoch": 2.37, "learning_rate": 2.190503481131252e-06, "loss": 0.2147, "step": 1297 }, { "epoch": 2.37, "learning_rate": 2.1781622233420353e-06, "loss": 0.2178, "step": 1298 }, { "epoch": 2.38, "learning_rate": 2.1658515786599985e-06, "loss": 0.2366, "step": 1299 }, { "epoch": 2.38, "learning_rate": 2.1535715952665494e-06, "loss": 0.2285, "step": 1300 }, { "epoch": 2.38, "learning_rate": 2.1413223212230806e-06, "loss": 0.2186, "step": 1301 }, { "epoch": 2.38, "learning_rate": 2.129103804470797e-06, "loss": 0.2248, "step": 1302 }, { "epoch": 2.38, "learning_rate": 2.1169160928305323e-06, "loss": 0.2256, "step": 1303 }, { "epoch": 2.38, "learning_rate": 2.1047592340025456e-06, "loss": 0.231, "step": 1304 }, { "epoch": 2.39, "learning_rate": 2.0926332755663493e-06, "loss": 0.2316, "step": 1305 }, { "epoch": 2.39, "learning_rate": 2.080538264980523e-06, "loss": 0.2235, "step": 1306 }, { "epoch": 2.39, "learning_rate": 2.068474249582508e-06, "loss": 0.2222, "step": 1307 }, { "epoch": 2.39, "learning_rate": 2.056441276588448e-06, "loss": 0.2166, "step": 1308 }, { "epoch": 2.39, "learning_rate": 2.044439393092994e-06, "loss": 0.2282, "step": 1309 }, { "epoch": 2.4, "learning_rate": 2.0324686460691124e-06, "loss": 0.2286, "step": 1310 }, { "epoch": 2.4, "learning_rate": 2.020529082367909e-06, "loss": 0.2274, "step": 1311 }, { "epoch": 2.4, "learning_rate": 2.0086207487184504e-06, "loss": 0.23, "step": 1312 }, { "epoch": 2.4, "learning_rate": 1.9967436917275683e-06, "loss": 0.2103, "step": 1313 }, { "epoch": 2.4, "learning_rate": 1.984897957879687e-06, "loss": 0.2535, "step": 1314 }, { "epoch": 2.4, "learning_rate": 1.9730835935366355e-06, "loss": 0.2315, "step": 1315 }, { "epoch": 2.41, "learning_rate": 1.9613006449374715e-06, "loss": 0.2072, "step": 1316 }, { "epoch": 2.41, "learning_rate": 1.949549158198295e-06, "loss": 0.2247, "step": 1317 }, { "epoch": 2.41, "learning_rate": 1.937829179312076e-06, "loss": 0.2368, "step": 1318 }, { "epoch": 2.41, "learning_rate": 1.9261407541484657e-06, "loss": 0.2217, "step": 1319 }, { "epoch": 2.41, "learning_rate": 1.9144839284536177e-06, "loss": 0.2369, "step": 1320 }, { "epoch": 2.42, "learning_rate": 1.9028587478500126e-06, "loss": 0.2233, "step": 1321 }, { "epoch": 2.42, "learning_rate": 1.8912652578362857e-06, "loss": 0.2573, "step": 1322 }, { "epoch": 2.42, "learning_rate": 1.8797035037870326e-06, "loss": 0.2232, "step": 1323 }, { "epoch": 2.42, "learning_rate": 1.8681735309526438e-06, "loss": 0.2237, "step": 1324 }, { "epoch": 2.42, "learning_rate": 1.8566753844591257e-06, "loss": 0.2256, "step": 1325 }, { "epoch": 2.42, "learning_rate": 1.8452091093079217e-06, "loss": 0.2164, "step": 1326 }, { "epoch": 2.43, "learning_rate": 1.833774750375734e-06, "loss": 0.2266, "step": 1327 }, { "epoch": 2.43, "learning_rate": 1.822372352414361e-06, "loss": 0.2283, "step": 1328 }, { "epoch": 2.43, "learning_rate": 1.8110019600505014e-06, "loss": 0.2344, "step": 1329 }, { "epoch": 2.43, "learning_rate": 1.7996636177855931e-06, "loss": 0.2167, "step": 1330 }, { "epoch": 2.43, "learning_rate": 1.7883573699956425e-06, "loss": 0.2197, "step": 1331 }, { "epoch": 2.44, "learning_rate": 1.7770832609310374e-06, "loss": 0.2177, "step": 1332 }, { "epoch": 2.44, "learning_rate": 1.765841334716384e-06, "loss": 0.2287, "step": 1333 }, { "epoch": 2.44, "learning_rate": 1.75463163535033e-06, "loss": 0.2278, "step": 1334 }, { "epoch": 2.44, "learning_rate": 1.7434542067053972e-06, "loss": 0.2334, "step": 1335 }, { "epoch": 2.44, "learning_rate": 1.7323090925277986e-06, "loss": 0.2454, "step": 1336 }, { "epoch": 2.44, "learning_rate": 1.7211963364372852e-06, "loss": 0.2329, "step": 1337 }, { "epoch": 2.45, "learning_rate": 1.7101159819269585e-06, "loss": 0.2198, "step": 1338 }, { "epoch": 2.45, "learning_rate": 1.6990680723631048e-06, "loss": 0.2246, "step": 1339 }, { "epoch": 2.45, "learning_rate": 1.6880526509850347e-06, "loss": 0.2284, "step": 1340 }, { "epoch": 2.45, "learning_rate": 1.6770697609049024e-06, "loss": 0.2225, "step": 1341 }, { "epoch": 2.45, "learning_rate": 1.6661194451075346e-06, "loss": 0.2256, "step": 1342 }, { "epoch": 2.46, "learning_rate": 1.6552017464502813e-06, "loss": 0.238, "step": 1343 }, { "epoch": 2.46, "learning_rate": 1.6443167076628285e-06, "loss": 0.2221, "step": 1344 }, { "epoch": 2.46, "learning_rate": 1.6334643713470344e-06, "loss": 0.2208, "step": 1345 }, { "epoch": 2.46, "learning_rate": 1.6226447799767775e-06, "loss": 0.2333, "step": 1346 }, { "epoch": 2.46, "learning_rate": 1.6118579758977693e-06, "loss": 0.2256, "step": 1347 }, { "epoch": 2.46, "learning_rate": 1.6011040013274015e-06, "loss": 0.2213, "step": 1348 }, { "epoch": 2.47, "learning_rate": 1.5903828983545778e-06, "loss": 0.2201, "step": 1349 }, { "epoch": 2.47, "learning_rate": 1.5796947089395475e-06, "loss": 0.2105, "step": 1350 }, { "epoch": 2.47, "learning_rate": 1.5690394749137471e-06, "loss": 0.234, "step": 1351 }, { "epoch": 2.47, "learning_rate": 1.5584172379796247e-06, "loss": 0.2156, "step": 1352 }, { "epoch": 2.47, "learning_rate": 1.547828039710496e-06, "loss": 0.2157, "step": 1353 }, { "epoch": 2.48, "learning_rate": 1.5372719215503584e-06, "loss": 0.2254, "step": 1354 }, { "epoch": 2.48, "learning_rate": 1.5267489248137445e-06, "loss": 0.2256, "step": 1355 }, { "epoch": 2.48, "learning_rate": 1.5162590906855612e-06, "loss": 0.2369, "step": 1356 }, { "epoch": 2.48, "learning_rate": 1.5058024602209164e-06, "loss": 0.2076, "step": 1357 }, { "epoch": 2.48, "learning_rate": 1.4953790743449703e-06, "loss": 0.2173, "step": 1358 }, { "epoch": 2.49, "learning_rate": 1.4849889738527656e-06, "loss": 0.2138, "step": 1359 }, { "epoch": 2.49, "learning_rate": 1.4746321994090774e-06, "loss": 0.2123, "step": 1360 }, { "epoch": 2.49, "learning_rate": 1.4643087915482445e-06, "loss": 0.2198, "step": 1361 }, { "epoch": 2.49, "learning_rate": 1.4540187906740245e-06, "loss": 0.2285, "step": 1362 }, { "epoch": 2.49, "learning_rate": 1.4437622370594172e-06, "loss": 0.2239, "step": 1363 }, { "epoch": 2.49, "learning_rate": 1.4335391708465185e-06, "loss": 0.2292, "step": 1364 }, { "epoch": 2.5, "learning_rate": 1.4233496320463668e-06, "loss": 0.2247, "step": 1365 }, { "epoch": 2.5, "learning_rate": 1.4131936605387764e-06, "loss": 0.2128, "step": 1366 }, { "epoch": 2.5, "learning_rate": 1.4030712960721848e-06, "loss": 0.2246, "step": 1367 }, { "epoch": 2.5, "learning_rate": 1.3929825782635009e-06, "loss": 0.2223, "step": 1368 }, { "epoch": 2.5, "learning_rate": 1.3829275465979476e-06, "loss": 0.2205, "step": 1369 }, { "epoch": 2.51, "learning_rate": 1.3729062404289017e-06, "loss": 0.2226, "step": 1370 }, { "epoch": 2.51, "learning_rate": 1.3629186989777542e-06, "loss": 0.236, "step": 1371 }, { "epoch": 2.51, "learning_rate": 1.3529649613337425e-06, "loss": 0.2163, "step": 1372 }, { "epoch": 2.51, "learning_rate": 1.3430450664537986e-06, "loss": 0.2407, "step": 1373 }, { "epoch": 2.51, "learning_rate": 1.3331590531624116e-06, "loss": 0.2281, "step": 1374 }, { "epoch": 2.51, "learning_rate": 1.3233069601514537e-06, "loss": 0.2149, "step": 1375 }, { "epoch": 2.52, "learning_rate": 1.3134888259800472e-06, "loss": 0.2262, "step": 1376 }, { "epoch": 2.52, "learning_rate": 1.303704689074402e-06, "loss": 0.2205, "step": 1377 }, { "epoch": 2.52, "learning_rate": 1.2939545877276726e-06, "loss": 0.2056, "step": 1378 }, { "epoch": 2.52, "learning_rate": 1.2842385600998032e-06, "loss": 0.2155, "step": 1379 }, { "epoch": 2.52, "learning_rate": 1.2745566442173773e-06, "loss": 0.23, "step": 1380 }, { "epoch": 2.53, "learning_rate": 1.264908877973482e-06, "loss": 0.2223, "step": 1381 }, { "epoch": 2.53, "learning_rate": 1.2552952991275402e-06, "loss": 0.2245, "step": 1382 }, { "epoch": 2.53, "learning_rate": 1.2457159453051715e-06, "loss": 0.2398, "step": 1383 }, { "epoch": 2.53, "learning_rate": 1.2361708539980565e-06, "loss": 0.2337, "step": 1384 }, { "epoch": 2.53, "learning_rate": 1.2266600625637659e-06, "loss": 0.2271, "step": 1385 }, { "epoch": 2.53, "learning_rate": 1.2171836082256316e-06, "loss": 0.2274, "step": 1386 }, { "epoch": 2.54, "learning_rate": 1.2077415280726047e-06, "loss": 0.2086, "step": 1387 }, { "epoch": 2.54, "learning_rate": 1.1983338590590932e-06, "loss": 0.2182, "step": 1388 }, { "epoch": 2.54, "learning_rate": 1.1889606380048301e-06, "loss": 0.2216, "step": 1389 }, { "epoch": 2.54, "learning_rate": 1.1796219015947286e-06, "loss": 0.2282, "step": 1390 }, { "epoch": 2.54, "learning_rate": 1.1703176863787313e-06, "loss": 0.2226, "step": 1391 }, { "epoch": 2.55, "learning_rate": 1.1610480287716764e-06, "loss": 0.2225, "step": 1392 }, { "epoch": 2.55, "learning_rate": 1.151812965053144e-06, "loss": 0.2129, "step": 1393 }, { "epoch": 2.55, "learning_rate": 1.1426125313673287e-06, "loss": 0.2307, "step": 1394 }, { "epoch": 2.55, "learning_rate": 1.1334467637228818e-06, "loss": 0.2319, "step": 1395 }, { "epoch": 2.55, "learning_rate": 1.1243156979927873e-06, "loss": 0.2159, "step": 1396 }, { "epoch": 2.55, "learning_rate": 1.1152193699142067e-06, "loss": 0.2068, "step": 1397 }, { "epoch": 2.56, "learning_rate": 1.1061578150883445e-06, "loss": 0.2347, "step": 1398 }, { "epoch": 2.56, "learning_rate": 1.0971310689803173e-06, "loss": 0.221, "step": 1399 }, { "epoch": 2.56, "learning_rate": 1.088139166919e-06, "loss": 0.2269, "step": 1400 }, { "epoch": 2.56, "learning_rate": 1.0791821440968963e-06, "loss": 0.2128, "step": 1401 }, { "epoch": 2.56, "learning_rate": 1.070260035570002e-06, "loss": 0.2271, "step": 1402 }, { "epoch": 2.57, "learning_rate": 1.0613728762576625e-06, "loss": 0.2259, "step": 1403 }, { "epoch": 2.57, "learning_rate": 1.0525207009424377e-06, "loss": 0.2132, "step": 1404 }, { "epoch": 2.57, "learning_rate": 1.043703544269975e-06, "loss": 0.2284, "step": 1405 }, { "epoch": 2.57, "learning_rate": 1.0349214407488573e-06, "loss": 0.229, "step": 1406 }, { "epoch": 2.57, "learning_rate": 1.026174424750479e-06, "loss": 0.2467, "step": 1407 }, { "epoch": 2.57, "learning_rate": 1.0174625305089125e-06, "loss": 0.2324, "step": 1408 }, { "epoch": 2.58, "learning_rate": 1.0087857921207667e-06, "loss": 0.2332, "step": 1409 }, { "epoch": 2.58, "learning_rate": 1.0001442435450581e-06, "loss": 0.2395, "step": 1410 }, { "epoch": 2.58, "learning_rate": 9.915379186030771e-07, "loss": 0.2356, "step": 1411 }, { "epoch": 2.58, "learning_rate": 9.829668509782576e-07, "loss": 0.2155, "step": 1412 }, { "epoch": 2.58, "learning_rate": 9.744310742160434e-07, "loss": 0.2289, "step": 1413 }, { "epoch": 2.59, "learning_rate": 9.65930621723752e-07, "loss": 0.2332, "step": 1414 }, { "epoch": 2.59, "learning_rate": 9.57465526770457e-07, "loss": 0.2308, "step": 1415 }, { "epoch": 2.59, "learning_rate": 9.490358224868445e-07, "loss": 0.2226, "step": 1416 }, { "epoch": 2.59, "learning_rate": 9.406415418650872e-07, "loss": 0.2356, "step": 1417 }, { "epoch": 2.59, "learning_rate": 9.322827177587212e-07, "loss": 0.2406, "step": 1418 }, { "epoch": 2.59, "learning_rate": 9.239593828825133e-07, "loss": 0.2185, "step": 1419 }, { "epoch": 2.6, "learning_rate": 9.156715698123231e-07, "loss": 0.2246, "step": 1420 }, { "epoch": 2.6, "learning_rate": 9.074193109849971e-07, "loss": 0.2206, "step": 1421 }, { "epoch": 2.6, "learning_rate": 8.992026386982222e-07, "loss": 0.2167, "step": 1422 }, { "epoch": 2.6, "learning_rate": 8.910215851104087e-07, "loss": 0.2406, "step": 1423 }, { "epoch": 2.6, "learning_rate": 8.828761822405641e-07, "loss": 0.2078, "step": 1424 }, { "epoch": 2.61, "learning_rate": 8.747664619681639e-07, "loss": 0.219, "step": 1425 }, { "epoch": 2.61, "learning_rate": 8.666924560330293e-07, "loss": 0.2145, "step": 1426 }, { "epoch": 2.61, "learning_rate": 8.586541960352035e-07, "loss": 0.2229, "step": 1427 }, { "epoch": 2.61, "learning_rate": 8.506517134348269e-07, "loss": 0.2193, "step": 1428 }, { "epoch": 2.61, "learning_rate": 8.426850395520126e-07, "loss": 0.2321, "step": 1429 }, { "epoch": 2.61, "learning_rate": 8.347542055667313e-07, "loss": 0.2325, "step": 1430 }, { "epoch": 2.62, "learning_rate": 8.268592425186761e-07, "loss": 0.2269, "step": 1431 }, { "epoch": 2.62, "learning_rate": 8.190001813071524e-07, "loss": 0.2141, "step": 1432 }, { "epoch": 2.62, "learning_rate": 8.111770526909535e-07, "loss": 0.2299, "step": 1433 }, { "epoch": 2.62, "learning_rate": 8.033898872882396e-07, "loss": 0.2205, "step": 1434 }, { "epoch": 2.62, "learning_rate": 7.956387155764145e-07, "loss": 0.2404, "step": 1435 }, { "epoch": 2.63, "learning_rate": 7.87923567892015e-07, "loss": 0.2244, "step": 1436 }, { "epoch": 2.63, "learning_rate": 7.802444744305826e-07, "loss": 0.2343, "step": 1437 }, { "epoch": 2.63, "learning_rate": 7.726014652465508e-07, "loss": 0.2221, "step": 1438 }, { "epoch": 2.63, "learning_rate": 7.649945702531314e-07, "loss": 0.2429, "step": 1439 }, { "epoch": 2.63, "learning_rate": 7.574238192221872e-07, "loss": 0.2117, "step": 1440 }, { "epoch": 2.63, "learning_rate": 7.498892417841208e-07, "loss": 0.2254, "step": 1441 }, { "epoch": 2.64, "learning_rate": 7.42390867427758e-07, "loss": 0.2282, "step": 1442 }, { "epoch": 2.64, "learning_rate": 7.349287255002401e-07, "loss": 0.2273, "step": 1443 }, { "epoch": 2.64, "learning_rate": 7.275028452068944e-07, "loss": 0.2244, "step": 1444 }, { "epoch": 2.64, "learning_rate": 7.20113255611129e-07, "loss": 0.2246, "step": 1445 }, { "epoch": 2.64, "learning_rate": 7.127599856343192e-07, "loss": 0.224, "step": 1446 }, { "epoch": 2.65, "learning_rate": 7.054430640556898e-07, "loss": 0.2178, "step": 1447 }, { "epoch": 2.65, "learning_rate": 6.981625195122077e-07, "loss": 0.2191, "step": 1448 }, { "epoch": 2.65, "learning_rate": 6.909183804984698e-07, "loss": 0.2344, "step": 1449 }, { "epoch": 2.65, "learning_rate": 6.837106753665823e-07, "loss": 0.2256, "step": 1450 }, { "epoch": 2.65, "learning_rate": 6.76539432326061e-07, "loss": 0.2204, "step": 1451 }, { "epoch": 2.66, "learning_rate": 6.69404679443717e-07, "loss": 0.2277, "step": 1452 }, { "epoch": 2.66, "learning_rate": 6.623064446435434e-07, "loss": 0.2196, "step": 1453 }, { "epoch": 2.66, "learning_rate": 6.55244755706611e-07, "loss": 0.2256, "step": 1454 }, { "epoch": 2.66, "learning_rate": 6.482196402709562e-07, "loss": 0.2312, "step": 1455 }, { "epoch": 2.66, "learning_rate": 6.41231125831474e-07, "loss": 0.2293, "step": 1456 }, { "epoch": 2.66, "learning_rate": 6.342792397398101e-07, "loss": 0.2246, "step": 1457 }, { "epoch": 2.67, "learning_rate": 6.273640092042577e-07, "loss": 0.2194, "step": 1458 }, { "epoch": 2.67, "learning_rate": 6.204854612896427e-07, "loss": 0.2295, "step": 1459 }, { "epoch": 2.67, "learning_rate": 6.136436229172238e-07, "loss": 0.2144, "step": 1460 }, { "epoch": 2.67, "learning_rate": 6.06838520864591e-07, "loss": 0.2115, "step": 1461 }, { "epoch": 2.67, "learning_rate": 6.000701817655474e-07, "loss": 0.238, "step": 1462 }, { "epoch": 2.68, "learning_rate": 5.933386321100155e-07, "loss": 0.2273, "step": 1463 }, { "epoch": 2.68, "learning_rate": 5.866438982439382e-07, "loss": 0.2274, "step": 1464 }, { "epoch": 2.68, "learning_rate": 5.799860063691609e-07, "loss": 0.2175, "step": 1465 }, { "epoch": 2.68, "learning_rate": 5.733649825433385e-07, "loss": 0.2202, "step": 1466 }, { "epoch": 2.68, "learning_rate": 5.667808526798358e-07, "loss": 0.2238, "step": 1467 }, { "epoch": 2.68, "learning_rate": 5.602336425476174e-07, "loss": 0.2211, "step": 1468 }, { "epoch": 2.69, "learning_rate": 5.537233777711526e-07, "loss": 0.203, "step": 1469 }, { "epoch": 2.69, "learning_rate": 5.472500838303141e-07, "loss": 0.2197, "step": 1470 }, { "epoch": 2.69, "learning_rate": 5.408137860602803e-07, "loss": 0.2118, "step": 1471 }, { "epoch": 2.69, "learning_rate": 5.344145096514308e-07, "loss": 0.2388, "step": 1472 }, { "epoch": 2.69, "learning_rate": 5.280522796492504e-07, "loss": 0.2448, "step": 1473 }, { "epoch": 2.7, "learning_rate": 5.217271209542384e-07, "loss": 0.2383, "step": 1474 }, { "epoch": 2.7, "learning_rate": 5.154390583217961e-07, "loss": 0.2271, "step": 1475 }, { "epoch": 2.7, "learning_rate": 5.091881163621426e-07, "loss": 0.2254, "step": 1476 }, { "epoch": 2.7, "learning_rate": 5.029743195402149e-07, "loss": 0.2384, "step": 1477 }, { "epoch": 2.7, "learning_rate": 4.96797692175568e-07, "loss": 0.2375, "step": 1478 }, { "epoch": 2.7, "learning_rate": 4.906582584422859e-07, "loss": 0.21, "step": 1479 }, { "epoch": 2.71, "learning_rate": 4.845560423688822e-07, "loss": 0.2286, "step": 1480 }, { "epoch": 2.71, "learning_rate": 4.784910678382093e-07, "loss": 0.2467, "step": 1481 }, { "epoch": 2.71, "learning_rate": 4.724633585873628e-07, "loss": 0.2318, "step": 1482 }, { "epoch": 2.71, "learning_rate": 4.6647293820759167e-07, "loss": 0.2179, "step": 1483 }, { "epoch": 2.71, "learning_rate": 4.6051983014420155e-07, "loss": 0.2177, "step": 1484 }, { "epoch": 2.72, "learning_rate": 4.546040576964628e-07, "loss": 0.2291, "step": 1485 }, { "epoch": 2.72, "learning_rate": 4.487256440175292e-07, "loss": 0.2166, "step": 1486 }, { "epoch": 2.72, "learning_rate": 4.428846121143326e-07, "loss": 0.2256, "step": 1487 }, { "epoch": 2.72, "learning_rate": 4.370809848475033e-07, "loss": 0.2134, "step": 1488 }, { "epoch": 2.72, "learning_rate": 4.313147849312749e-07, "loss": 0.2329, "step": 1489 }, { "epoch": 2.72, "learning_rate": 4.2558603493340066e-07, "loss": 0.2207, "step": 1490 }, { "epoch": 2.73, "learning_rate": 4.198947572750611e-07, "loss": 0.2215, "step": 1491 }, { "epoch": 2.73, "learning_rate": 4.142409742307774e-07, "loss": 0.2353, "step": 1492 }, { "epoch": 2.73, "learning_rate": 4.0862470792832565e-07, "loss": 0.2102, "step": 1493 }, { "epoch": 2.73, "learning_rate": 4.030459803486464e-07, "loss": 0.2189, "step": 1494 }, { "epoch": 2.73, "learning_rate": 3.975048133257631e-07, "loss": 0.2178, "step": 1495 }, { "epoch": 2.74, "learning_rate": 3.9200122854669674e-07, "loss": 0.2272, "step": 1496 }, { "epoch": 2.74, "learning_rate": 3.8653524755137063e-07, "loss": 0.2198, "step": 1497 }, { "epoch": 2.74, "learning_rate": 3.8110689173254443e-07, "loss": 0.2215, "step": 1498 }, { "epoch": 2.74, "learning_rate": 3.7571618233571584e-07, "loss": 0.2324, "step": 1499 }, { "epoch": 2.74, "learning_rate": 3.703631404590402e-07, "loss": 0.2319, "step": 1500 }, { "epoch": 2.74, "learning_rate": 3.6504778705325314e-07, "loss": 0.2204, "step": 1501 }, { "epoch": 2.75, "learning_rate": 3.5977014292158496e-07, "loss": 0.2236, "step": 1502 }, { "epoch": 2.75, "learning_rate": 3.545302287196772e-07, "loss": 0.2181, "step": 1503 }, { "epoch": 2.75, "learning_rate": 3.493280649555042e-07, "loss": 0.2298, "step": 1504 }, { "epoch": 2.75, "learning_rate": 3.441636719892938e-07, "loss": 0.2221, "step": 1505 }, { "epoch": 2.75, "learning_rate": 3.3903707003344775e-07, "loss": 0.221, "step": 1506 }, { "epoch": 2.76, "learning_rate": 3.339482791524562e-07, "loss": 0.2164, "step": 1507 }, { "epoch": 2.76, "learning_rate": 3.28897319262832e-07, "loss": 0.2261, "step": 1508 }, { "epoch": 2.76, "learning_rate": 3.2388421013301973e-07, "loss": 0.2268, "step": 1509 }, { "epoch": 2.76, "learning_rate": 3.1890897138332266e-07, "loss": 0.2278, "step": 1510 }, { "epoch": 2.76, "learning_rate": 3.139716224858336e-07, "loss": 0.2172, "step": 1511 }, { "epoch": 2.76, "learning_rate": 3.090721827643439e-07, "loss": 0.2258, "step": 1512 }, { "epoch": 2.77, "learning_rate": 3.042106713942816e-07, "loss": 0.2308, "step": 1513 }, { "epoch": 2.77, "learning_rate": 2.993871074026289e-07, "loss": 0.231, "step": 1514 }, { "epoch": 2.77, "learning_rate": 2.9460150966784786e-07, "loss": 0.2189, "step": 1515 }, { "epoch": 2.77, "learning_rate": 2.898538969198117e-07, "loss": 0.2305, "step": 1516 }, { "epoch": 2.77, "learning_rate": 2.85144287739727e-07, "loss": 0.2188, "step": 1517 }, { "epoch": 2.78, "learning_rate": 2.8047270056005937e-07, "loss": 0.2247, "step": 1518 }, { "epoch": 2.78, "learning_rate": 2.7583915366446554e-07, "loss": 0.2252, "step": 1519 }, { "epoch": 2.78, "learning_rate": 2.712436651877237e-07, "loss": 0.2302, "step": 1520 }, { "epoch": 2.78, "learning_rate": 2.666862531156533e-07, "loss": 0.2167, "step": 1521 }, { "epoch": 2.78, "learning_rate": 2.6216693528505197e-07, "loss": 0.229, "step": 1522 }, { "epoch": 2.78, "learning_rate": 2.5768572938362767e-07, "loss": 0.2085, "step": 1523 }, { "epoch": 2.79, "learning_rate": 2.5324265294992103e-07, "loss": 0.2208, "step": 1524 }, { "epoch": 2.79, "learning_rate": 2.488377233732431e-07, "loss": 0.219, "step": 1525 }, { "epoch": 2.79, "learning_rate": 2.4447095789360885e-07, "loss": 0.2299, "step": 1526 }, { "epoch": 2.79, "learning_rate": 2.401423736016628e-07, "loss": 0.2214, "step": 1527 }, { "epoch": 2.79, "learning_rate": 2.3585198743861782e-07, "loss": 0.2281, "step": 1528 }, { "epoch": 2.8, "learning_rate": 2.3159981619618633e-07, "loss": 0.2118, "step": 1529 }, { "epoch": 2.8, "learning_rate": 2.273858765165149e-07, "loss": 0.2244, "step": 1530 }, { "epoch": 2.8, "learning_rate": 2.2321018489211977e-07, "loss": 0.2415, "step": 1531 }, { "epoch": 2.8, "learning_rate": 2.190727576658225e-07, "loss": 0.2179, "step": 1532 }, { "epoch": 2.8, "learning_rate": 2.1497361103068548e-07, "loss": 0.2175, "step": 1533 }, { "epoch": 2.81, "learning_rate": 2.1091276102994662e-07, "loss": 0.2237, "step": 1534 }, { "epoch": 2.81, "learning_rate": 2.068902235569603e-07, "loss": 0.2146, "step": 1535 }, { "epoch": 2.81, "learning_rate": 2.0290601435513423e-07, "loss": 0.2036, "step": 1536 }, { "epoch": 2.81, "learning_rate": 1.9896014901786386e-07, "loss": 0.2328, "step": 1537 }, { "epoch": 2.81, "learning_rate": 1.9505264298847693e-07, "loss": 0.2265, "step": 1538 }, { "epoch": 2.81, "learning_rate": 1.9118351156017124e-07, "loss": 0.2165, "step": 1539 }, { "epoch": 2.82, "learning_rate": 1.8735276987595031e-07, "loss": 0.2332, "step": 1540 }, { "epoch": 2.82, "learning_rate": 1.8356043292857008e-07, "loss": 0.2325, "step": 1541 }, { "epoch": 2.82, "learning_rate": 1.7980651556048e-07, "loss": 0.24, "step": 1542 }, { "epoch": 2.82, "learning_rate": 1.760910324637599e-07, "loss": 0.2246, "step": 1543 }, { "epoch": 2.82, "learning_rate": 1.7241399818006765e-07, "loss": 0.2169, "step": 1544 }, { "epoch": 2.83, "learning_rate": 1.6877542710057814e-07, "loss": 0.2167, "step": 1545 }, { "epoch": 2.83, "learning_rate": 1.651753334659323e-07, "loss": 0.2103, "step": 1546 }, { "epoch": 2.83, "learning_rate": 1.6161373136617365e-07, "loss": 0.224, "step": 1547 }, { "epoch": 2.83, "learning_rate": 1.5809063474070075e-07, "loss": 0.2212, "step": 1548 }, { "epoch": 2.83, "learning_rate": 1.5460605737820823e-07, "loss": 0.2103, "step": 1549 }, { "epoch": 2.83, "learning_rate": 1.5116001291663463e-07, "loss": 0.2193, "step": 1550 }, { "epoch": 2.84, "learning_rate": 1.4775251484310803e-07, "loss": 0.2057, "step": 1551 }, { "epoch": 2.84, "learning_rate": 1.443835764938939e-07, "loss": 0.202, "step": 1552 }, { "epoch": 2.84, "learning_rate": 1.4105321105434056e-07, "loss": 0.2245, "step": 1553 }, { "epoch": 2.84, "learning_rate": 1.3776143155883492e-07, "loss": 0.2147, "step": 1554 }, { "epoch": 2.84, "learning_rate": 1.3450825089074137e-07, "loss": 0.2134, "step": 1555 }, { "epoch": 2.85, "learning_rate": 1.3129368178235845e-07, "loss": 0.2199, "step": 1556 }, { "epoch": 2.85, "learning_rate": 1.281177368148645e-07, "loss": 0.2249, "step": 1557 }, { "epoch": 2.85, "learning_rate": 1.2498042841827317e-07, "loss": 0.2215, "step": 1558 }, { "epoch": 2.85, "learning_rate": 1.2188176887138137e-07, "loss": 0.2268, "step": 1559 }, { "epoch": 2.85, "learning_rate": 1.1882177030172248e-07, "loss": 0.225, "step": 1560 }, { "epoch": 2.85, "learning_rate": 1.1580044468551876e-07, "loss": 0.231, "step": 1561 }, { "epoch": 2.86, "learning_rate": 1.128178038476324e-07, "loss": 0.2231, "step": 1562 }, { "epoch": 2.86, "learning_rate": 1.0987385946152451e-07, "loss": 0.2284, "step": 1563 }, { "epoch": 2.86, "learning_rate": 1.0696862304920175e-07, "loss": 0.229, "step": 1564 }, { "epoch": 2.86, "learning_rate": 1.0410210598118086e-07, "loss": 0.2214, "step": 1565 }, { "epoch": 2.86, "learning_rate": 1.0127431947643318e-07, "loss": 0.2261, "step": 1566 }, { "epoch": 2.87, "learning_rate": 9.848527460234902e-08, "loss": 0.2347, "step": 1567 }, { "epoch": 2.87, "learning_rate": 9.573498227469336e-08, "loss": 0.2339, "step": 1568 }, { "epoch": 2.87, "learning_rate": 9.302345325755801e-08, "loss": 0.2262, "step": 1569 }, { "epoch": 2.87, "learning_rate": 9.03506981633262e-08, "loss": 0.2076, "step": 1570 }, { "epoch": 2.87, "learning_rate": 8.771672745262583e-08, "loss": 0.2345, "step": 1571 }, { "epoch": 2.87, "learning_rate": 8.512155143429068e-08, "loss": 0.2214, "step": 1572 }, { "epoch": 2.88, "learning_rate": 8.256518026532046e-08, "loss": 0.218, "step": 1573 }, { "epoch": 2.88, "learning_rate": 8.004762395083965e-08, "loss": 0.2267, "step": 1574 }, { "epoch": 2.88, "learning_rate": 7.756889234405984e-08, "loss": 0.2094, "step": 1575 }, { "epoch": 2.88, "learning_rate": 7.512899514624084e-08, "loss": 0.2129, "step": 1576 }, { "epoch": 2.88, "learning_rate": 7.272794190665178e-08, "loss": 0.2206, "step": 1577 }, { "epoch": 2.89, "learning_rate": 7.036574202253343e-08, "loss": 0.2357, "step": 1578 }, { "epoch": 2.89, "learning_rate": 6.804240473906486e-08, "loss": 0.2163, "step": 1579 }, { "epoch": 2.89, "learning_rate": 6.575793914932127e-08, "loss": 0.2225, "step": 1580 }, { "epoch": 2.89, "learning_rate": 6.351235419424506e-08, "loss": 0.2033, "step": 1581 }, { "epoch": 2.89, "learning_rate": 6.130565866260485e-08, "loss": 0.2257, "step": 1582 }, { "epoch": 2.89, "learning_rate": 5.913786119096654e-08, "loss": 0.2178, "step": 1583 }, { "epoch": 2.9, "learning_rate": 5.7008970263654485e-08, "loss": 0.2265, "step": 1584 }, { "epoch": 2.9, "learning_rate": 5.491899421272262e-08, "loss": 0.2275, "step": 1585 }, { "epoch": 2.9, "learning_rate": 5.2867941217917826e-08, "loss": 0.2143, "step": 1586 }, { "epoch": 2.9, "learning_rate": 5.085581930665107e-08, "loss": 0.2268, "step": 1587 }, { "epoch": 2.9, "learning_rate": 4.8882636353965174e-08, "loss": 0.2317, "step": 1588 }, { "epoch": 2.91, "learning_rate": 4.6948400082502676e-08, "loss": 0.223, "step": 1589 }, { "epoch": 2.91, "learning_rate": 4.505311806247803e-08, "loss": 0.2234, "step": 1590 }, { "epoch": 2.91, "learning_rate": 4.319679771164431e-08, "loss": 0.2162, "step": 1591 }, { "epoch": 2.91, "learning_rate": 4.1379446295268796e-08, "loss": 0.2307, "step": 1592 }, { "epoch": 2.91, "learning_rate": 3.960107092609966e-08, "loss": 0.2119, "step": 1593 }, { "epoch": 2.91, "learning_rate": 3.786167856434375e-08, "loss": 0.2124, "step": 1594 }, { "epoch": 2.92, "learning_rate": 3.6161276017634416e-08, "loss": 0.2148, "step": 1595 }, { "epoch": 2.92, "learning_rate": 3.449986994100596e-08, "loss": 0.2364, "step": 1596 }, { "epoch": 2.92, "learning_rate": 3.287746683687032e-08, "loss": 0.2057, "step": 1597 }, { "epoch": 2.92, "learning_rate": 3.1294073054987105e-08, "loss": 0.2212, "step": 1598 }, { "epoch": 2.92, "learning_rate": 2.9749694792442498e-08, "loss": 0.2166, "step": 1599 }, { "epoch": 2.93, "learning_rate": 2.8244338093625923e-08, "loss": 0.2194, "step": 1600 }, { "epoch": 2.93, "learning_rate": 2.67780088502001e-08, "loss": 0.2327, "step": 1601 }, { "epoch": 2.93, "learning_rate": 2.5350712801084365e-08, "loss": 0.2194, "step": 1602 }, { "epoch": 2.93, "learning_rate": 2.3962455532430262e-08, "loss": 0.2273, "step": 1603 }, { "epoch": 2.93, "learning_rate": 2.261324247759933e-08, "loss": 0.2118, "step": 1604 }, { "epoch": 2.93, "learning_rate": 2.1303078917139787e-08, "loss": 0.2252, "step": 1605 }, { "epoch": 2.94, "learning_rate": 2.0031969978770993e-08, "loss": 0.2274, "step": 1606 }, { "epoch": 2.94, "learning_rate": 1.8799920637359027e-08, "loss": 0.2256, "step": 1607 }, { "epoch": 2.94, "learning_rate": 1.760693571489669e-08, "loss": 0.2135, "step": 1608 }, { "epoch": 2.94, "learning_rate": 1.6453019880490194e-08, "loss": 0.2098, "step": 1609 }, { "epoch": 2.94, "learning_rate": 1.533817765033252e-08, "loss": 0.2179, "step": 1610 }, { "epoch": 2.95, "learning_rate": 1.4262413387695629e-08, "loss": 0.2273, "step": 1611 }, { "epoch": 2.95, "learning_rate": 1.3225731302903833e-08, "loss": 0.2448, "step": 1612 }, { "epoch": 2.95, "learning_rate": 1.2228135453324907e-08, "loss": 0.2242, "step": 1613 }, { "epoch": 2.95, "learning_rate": 1.1269629743346777e-08, "loss": 0.2096, "step": 1614 }, { "epoch": 2.95, "learning_rate": 1.0350217924370853e-08, "loss": 0.2198, "step": 1615 }, { "epoch": 2.95, "learning_rate": 9.469903594790941e-09, "loss": 0.2105, "step": 1616 }, { "epoch": 2.96, "learning_rate": 8.628690199979917e-09, "loss": 0.2255, "step": 1617 }, { "epoch": 2.96, "learning_rate": 7.826581032279734e-09, "loss": 0.2211, "step": 1618 }, { "epoch": 2.96, "learning_rate": 7.063579230983664e-09, "loss": 0.2208, "step": 1619 }, { "epoch": 2.96, "learning_rate": 6.3396877823296286e-09, "loss": 0.2099, "step": 1620 }, { "epoch": 2.96, "learning_rate": 5.654909519483554e-09, "loss": 0.2167, "step": 1621 }, { "epoch": 2.97, "learning_rate": 5.0092471225293705e-09, "loss": 0.2323, "step": 1622 }, { "epoch": 2.97, "learning_rate": 4.402703118461249e-09, "loss": 0.225, "step": 1623 }, { "epoch": 2.97, "learning_rate": 3.835279881171383e-09, "loss": 0.2259, "step": 1624 }, { "epoch": 2.97, "learning_rate": 3.3069796314399993e-09, "loss": 0.2149, "step": 1625 }, { "epoch": 2.97, "learning_rate": 2.8178044369286948e-09, "loss": 0.2228, "step": 1626 }, { "epoch": 2.98, "learning_rate": 2.367756212171557e-09, "loss": 0.2286, "step": 1627 }, { "epoch": 2.98, "learning_rate": 1.9568367185673897e-09, "loss": 0.2264, "step": 1628 }, { "epoch": 2.98, "learning_rate": 1.5850475643719443e-09, "loss": 0.2208, "step": 1629 }, { "epoch": 2.98, "learning_rate": 1.2523902046934767e-09, "loss": 0.2182, "step": 1630 }, { "epoch": 2.98, "learning_rate": 9.58865941487197e-10, "loss": 0.2207, "step": 1631 }, { "epoch": 2.98, "learning_rate": 7.044759235486087e-10, "loss": 0.2339, "step": 1632 }, { "epoch": 2.99, "learning_rate": 4.892211465079566e-10, "loss": 0.2241, "step": 1633 }, { "epoch": 2.99, "learning_rate": 3.1310245283022735e-10, "loss": 0.2129, "step": 1634 }, { "epoch": 2.99, "learning_rate": 1.761205318095982e-10, "loss": 0.1959, "step": 1635 }, { "epoch": 2.99, "learning_rate": 7.827591956388603e-11, "loss": 0.2139, "step": 1636 }, { "epoch": 2.99, "learning_rate": 1.956899903787779e-11, "loss": 0.2199, "step": 1637 }, { "epoch": 3.0, "learning_rate": 0.0, "loss": 0.22, "step": 1638 }, { "epoch": 3.0, "step": 1638, "total_flos": 4.3401313435024097e+18, "train_loss": 0.3987319528856411, "train_runtime": 82484.0165, "train_samples_per_second": 2.546, "train_steps_per_second": 0.02 } ], "logging_steps": 1.0, "max_steps": 1638, "num_train_epochs": 3, "save_steps": 2000, "total_flos": 4.3401313435024097e+18, "trial_name": null, "trial_params": null }