{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.997173544375354, "eval_steps": 500, "global_step": 2210, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 0.0, "loss": 10.5991, "step": 2 }, { "epoch": 0.01, "learning_rate": 0.0, "loss": 10.4827, "step": 4 }, { "epoch": 0.01, "learning_rate": 5.970149253731343e-08, "loss": 10.3175, "step": 6 }, { "epoch": 0.02, "learning_rate": 1.1940298507462686e-07, "loss": 10.4247, "step": 8 }, { "epoch": 0.02, "learning_rate": 1.4925373134328355e-07, "loss": 10.7072, "step": 10 }, { "epoch": 0.03, "learning_rate": 2.08955223880597e-07, "loss": 10.2469, "step": 12 }, { "epoch": 0.03, "learning_rate": 2.686567164179104e-07, "loss": 10.7392, "step": 14 }, { "epoch": 0.04, "learning_rate": 3.2835820895522385e-07, "loss": 10.4914, "step": 16 }, { "epoch": 0.04, "learning_rate": 3.880597014925373e-07, "loss": 10.3911, "step": 18 }, { "epoch": 0.05, "learning_rate": 4.4776119402985074e-07, "loss": 10.3605, "step": 20 }, { "epoch": 0.05, "learning_rate": 5.074626865671642e-07, "loss": 10.1571, "step": 22 }, { "epoch": 0.05, "learning_rate": 5.671641791044775e-07, "loss": 9.9087, "step": 24 }, { "epoch": 0.06, "learning_rate": 6.26865671641791e-07, "loss": 10.0494, "step": 26 }, { "epoch": 0.06, "learning_rate": 6.865671641791044e-07, "loss": 9.9599, "step": 28 }, { "epoch": 0.07, "learning_rate": 7.462686567164179e-07, "loss": 9.343, "step": 30 }, { "epoch": 0.07, "learning_rate": 8.059701492537313e-07, "loss": 9.3516, "step": 32 }, { "epoch": 0.08, "learning_rate": 8.656716417910447e-07, "loss": 8.9835, "step": 34 }, { "epoch": 0.08, "learning_rate": 9.253731343283582e-07, "loss": 9.0495, "step": 36 }, { "epoch": 0.09, "learning_rate": 9.850746268656714e-07, "loss": 8.4679, "step": 38 }, { "epoch": 0.09, "learning_rate": 1.0447761194029848e-06, "loss": 8.4778, "step": 40 }, { "epoch": 0.09, "learning_rate": 1.1044776119402984e-06, "loss": 8.5988, "step": 42 }, { "epoch": 0.1, "learning_rate": 1.1641791044776118e-06, "loss": 8.025, "step": 44 }, { "epoch": 0.1, "learning_rate": 1.2238805970149252e-06, "loss": 7.83, "step": 46 }, { "epoch": 0.11, "learning_rate": 1.2835820895522386e-06, "loss": 8.0105, "step": 48 }, { "epoch": 0.11, "learning_rate": 1.3432835820895522e-06, "loss": 8.0879, "step": 50 }, { "epoch": 0.12, "learning_rate": 1.4029850746268656e-06, "loss": 7.4775, "step": 52 }, { "epoch": 0.12, "learning_rate": 1.462686567164179e-06, "loss": 7.4841, "step": 54 }, { "epoch": 0.13, "learning_rate": 1.5223880597014924e-06, "loss": 6.8994, "step": 56 }, { "epoch": 0.13, "learning_rate": 1.5820895522388058e-06, "loss": 6.7791, "step": 58 }, { "epoch": 0.14, "learning_rate": 1.6417910447761194e-06, "loss": 6.784, "step": 60 }, { "epoch": 0.14, "learning_rate": 1.7014925373134328e-06, "loss": 6.7576, "step": 62 }, { "epoch": 0.14, "learning_rate": 1.7611940298507461e-06, "loss": 6.4316, "step": 64 }, { "epoch": 0.15, "learning_rate": 1.8208955223880595e-06, "loss": 5.6876, "step": 66 }, { "epoch": 0.15, "learning_rate": 1.8805970149253731e-06, "loss": 5.738, "step": 68 }, { "epoch": 0.16, "learning_rate": 1.9402985074626867e-06, "loss": 5.2889, "step": 70 }, { "epoch": 0.16, "learning_rate": 2e-06, "loss": 4.9295, "step": 72 }, { "epoch": 0.17, "learning_rate": 1.9999957018151615e-06, "loss": 5.684, "step": 74 }, { "epoch": 0.17, "learning_rate": 1.999982807297596e-06, "loss": 4.8791, "step": 76 }, { "epoch": 0.18, "learning_rate": 1.999961316558149e-06, "loss": 4.4769, "step": 78 }, { "epoch": 0.18, "learning_rate": 1.999931229781563e-06, "loss": 4.8514, "step": 80 }, { "epoch": 0.19, "learning_rate": 1.999892547226475e-06, "loss": 4.2112, "step": 82 }, { "epoch": 0.19, "learning_rate": 1.9998452692254138e-06, "loss": 4.2773, "step": 84 }, { "epoch": 0.19, "learning_rate": 1.9997893961847997e-06, "loss": 4.5068, "step": 86 }, { "epoch": 0.2, "learning_rate": 1.999724928584938e-06, "loss": 4.2763, "step": 88 }, { "epoch": 0.2, "learning_rate": 1.9996518669800148e-06, "loss": 4.2041, "step": 90 }, { "epoch": 0.21, "learning_rate": 1.999570211998096e-06, "loss": 4.4396, "step": 92 }, { "epoch": 0.21, "learning_rate": 1.9994799643411174e-06, "loss": 5.0899, "step": 94 }, { "epoch": 0.22, "learning_rate": 1.9993811247848815e-06, "loss": 4.655, "step": 96 }, { "epoch": 0.22, "learning_rate": 1.999273694179049e-06, "loss": 4.3956, "step": 98 }, { "epoch": 0.23, "learning_rate": 1.999157673447134e-06, "loss": 4.3652, "step": 100 }, { "epoch": 0.23, "learning_rate": 1.999033063586493e-06, "loss": 4.2803, "step": 102 }, { "epoch": 0.24, "learning_rate": 1.998899865668318e-06, "loss": 3.7498, "step": 104 }, { "epoch": 0.24, "learning_rate": 1.998758080837629e-06, "loss": 4.3783, "step": 106 }, { "epoch": 0.24, "learning_rate": 1.9986077103132595e-06, "loss": 4.1143, "step": 108 }, { "epoch": 0.25, "learning_rate": 1.998448755387851e-06, "loss": 4.5194, "step": 110 }, { "epoch": 0.25, "learning_rate": 1.998281217427838e-06, "loss": 4.1893, "step": 112 }, { "epoch": 0.26, "learning_rate": 1.998105097873439e-06, "loss": 4.043, "step": 114 }, { "epoch": 0.26, "learning_rate": 1.997920398238643e-06, "loss": 4.3604, "step": 116 }, { "epoch": 0.27, "learning_rate": 1.9977271201111964e-06, "loss": 3.7151, "step": 118 }, { "epoch": 0.27, "learning_rate": 1.997525265152589e-06, "loss": 4.1618, "step": 120 }, { "epoch": 0.28, "learning_rate": 1.9973148350980416e-06, "loss": 3.8081, "step": 122 }, { "epoch": 0.28, "learning_rate": 1.9970958317564874e-06, "loss": 4.3248, "step": 124 }, { "epoch": 0.28, "learning_rate": 1.996868257010561e-06, "loss": 4.4134, "step": 126 }, { "epoch": 0.29, "learning_rate": 1.996632112816579e-06, "loss": 4.4383, "step": 128 }, { "epoch": 0.29, "learning_rate": 1.9963874012045237e-06, "loss": 4.1804, "step": 130 }, { "epoch": 0.3, "learning_rate": 1.996134124278027e-06, "loss": 3.9685, "step": 132 }, { "epoch": 0.3, "learning_rate": 1.9958722842143507e-06, "loss": 3.5527, "step": 134 }, { "epoch": 0.31, "learning_rate": 1.995601883264369e-06, "loss": 4.7716, "step": 136 }, { "epoch": 0.31, "learning_rate": 1.9953229237525486e-06, "loss": 4.3694, "step": 138 }, { "epoch": 0.32, "learning_rate": 1.995035408076928e-06, "loss": 4.4472, "step": 140 }, { "epoch": 0.32, "learning_rate": 1.9947393387090986e-06, "loss": 3.4981, "step": 142 }, { "epoch": 0.33, "learning_rate": 1.994434718194182e-06, "loss": 3.7344, "step": 144 }, { "epoch": 0.33, "learning_rate": 1.9941215491508094e-06, "loss": 4.2549, "step": 146 }, { "epoch": 0.33, "learning_rate": 1.993799834271097e-06, "loss": 3.8295, "step": 148 }, { "epoch": 0.34, "learning_rate": 1.9934695763206246e-06, "loss": 3.7353, "step": 150 }, { "epoch": 0.34, "learning_rate": 1.9931307781384125e-06, "loss": 4.1323, "step": 152 }, { "epoch": 0.35, "learning_rate": 1.9927834426368943e-06, "loss": 3.8522, "step": 154 }, { "epoch": 0.35, "learning_rate": 1.992427572801895e-06, "loss": 3.8591, "step": 156 }, { "epoch": 0.36, "learning_rate": 1.992063171692603e-06, "loss": 4.1224, "step": 158 }, { "epoch": 0.36, "learning_rate": 1.9916902424415446e-06, "loss": 3.9431, "step": 160 }, { "epoch": 0.37, "learning_rate": 1.991308788254558e-06, "loss": 4.5052, "step": 162 }, { "epoch": 0.37, "learning_rate": 1.990918812410764e-06, "loss": 3.5612, "step": 164 }, { "epoch": 0.38, "learning_rate": 1.99052031826254e-06, "loss": 4.1358, "step": 166 }, { "epoch": 0.38, "learning_rate": 1.9901133092354876e-06, "loss": 4.0081, "step": 168 }, { "epoch": 0.38, "learning_rate": 1.9896977888284078e-06, "loss": 4.3439, "step": 170 }, { "epoch": 0.39, "learning_rate": 1.989273760613268e-06, "loss": 4.0603, "step": 172 }, { "epoch": 0.39, "learning_rate": 1.98884122823517e-06, "loss": 3.939, "step": 174 }, { "epoch": 0.4, "learning_rate": 1.9884001954123236e-06, "loss": 4.0202, "step": 176 }, { "epoch": 0.4, "learning_rate": 1.987950665936009e-06, "loss": 3.5036, "step": 178 }, { "epoch": 0.41, "learning_rate": 1.9874926436705483e-06, "loss": 3.71, "step": 180 }, { "epoch": 0.41, "learning_rate": 1.98702613255327e-06, "loss": 4.2036, "step": 182 }, { "epoch": 0.42, "learning_rate": 1.9865511365944765e-06, "loss": 3.3415, "step": 184 }, { "epoch": 0.42, "learning_rate": 1.9860676598774076e-06, "loss": 3.6936, "step": 186 }, { "epoch": 0.43, "learning_rate": 1.985575706558209e-06, "loss": 3.7071, "step": 188 }, { "epoch": 0.43, "learning_rate": 1.985075280865893e-06, "loss": 4.0125, "step": 190 }, { "epoch": 0.43, "learning_rate": 1.984566387102303e-06, "loss": 3.6338, "step": 192 }, { "epoch": 0.44, "learning_rate": 1.984049029642079e-06, "loss": 3.3184, "step": 194 }, { "epoch": 0.44, "learning_rate": 1.9835232129326172e-06, "loss": 3.39, "step": 196 }, { "epoch": 0.45, "learning_rate": 1.9829889414940315e-06, "loss": 3.7733, "step": 198 }, { "epoch": 0.45, "learning_rate": 1.9824462199191166e-06, "loss": 3.6512, "step": 200 }, { "epoch": 0.46, "learning_rate": 1.9818950528733086e-06, "loss": 3.2357, "step": 202 }, { "epoch": 0.46, "learning_rate": 1.9813354450946425e-06, "loss": 3.2044, "step": 204 }, { "epoch": 0.47, "learning_rate": 1.9807674013937144e-06, "loss": 3.2554, "step": 206 }, { "epoch": 0.47, "learning_rate": 1.980190926653637e-06, "loss": 4.2192, "step": 208 }, { "epoch": 0.47, "learning_rate": 1.979606025830001e-06, "loss": 3.7451, "step": 210 }, { "epoch": 0.48, "learning_rate": 1.97901270395083e-06, "loss": 3.3525, "step": 212 }, { "epoch": 0.48, "learning_rate": 1.978410966116538e-06, "loss": 3.4178, "step": 214 }, { "epoch": 0.49, "learning_rate": 1.9778008174998856e-06, "loss": 3.2279, "step": 216 }, { "epoch": 0.49, "learning_rate": 1.9771822633459368e-06, "loss": 3.2696, "step": 218 }, { "epoch": 0.5, "learning_rate": 1.976555308972011e-06, "loss": 3.6581, "step": 220 }, { "epoch": 0.5, "learning_rate": 1.97591995976764e-06, "loss": 3.4102, "step": 222 }, { "epoch": 0.51, "learning_rate": 1.97527622119452e-06, "loss": 3.5503, "step": 224 }, { "epoch": 0.51, "learning_rate": 1.9746240987864664e-06, "loss": 3.6236, "step": 226 }, { "epoch": 0.52, "learning_rate": 1.973963598149364e-06, "loss": 3.9091, "step": 228 }, { "epoch": 0.52, "learning_rate": 1.973294724961121e-06, "loss": 3.384, "step": 230 }, { "epoch": 0.52, "learning_rate": 1.972617484971618e-06, "loss": 4.0156, "step": 232 }, { "epoch": 0.53, "learning_rate": 1.9719318840026603e-06, "loss": 3.5326, "step": 234 }, { "epoch": 0.53, "learning_rate": 1.971237927947928e-06, "loss": 4.3285, "step": 236 }, { "epoch": 0.54, "learning_rate": 1.9705356227729238e-06, "loss": 3.8971, "step": 238 }, { "epoch": 0.54, "learning_rate": 1.9698249745149214e-06, "loss": 3.4896, "step": 240 }, { "epoch": 0.55, "learning_rate": 1.9691059892829174e-06, "loss": 3.3414, "step": 242 }, { "epoch": 0.55, "learning_rate": 1.968378673257574e-06, "loss": 3.4332, "step": 244 }, { "epoch": 0.56, "learning_rate": 1.9676430326911686e-06, "loss": 3.364, "step": 246 }, { "epoch": 0.56, "learning_rate": 1.966899073907539e-06, "loss": 3.2128, "step": 248 }, { "epoch": 0.57, "learning_rate": 1.9661468033020314e-06, "loss": 3.0516, "step": 250 }, { "epoch": 0.57, "learning_rate": 1.9653862273414402e-06, "loss": 3.7286, "step": 252 }, { "epoch": 0.57, "learning_rate": 1.964617352563959e-06, "loss": 3.7722, "step": 254 }, { "epoch": 0.58, "learning_rate": 1.963840185579119e-06, "loss": 3.3726, "step": 256 }, { "epoch": 0.58, "learning_rate": 1.9630547330677346e-06, "loss": 3.2923, "step": 258 }, { "epoch": 0.59, "learning_rate": 1.9622610017818463e-06, "loss": 3.4995, "step": 260 }, { "epoch": 0.59, "learning_rate": 1.9614589985446616e-06, "loss": 3.9451, "step": 262 }, { "epoch": 0.6, "learning_rate": 1.9606487302504967e-06, "loss": 3.1992, "step": 264 }, { "epoch": 0.6, "learning_rate": 1.959830203864718e-06, "loss": 3.3219, "step": 266 }, { "epoch": 0.61, "learning_rate": 1.9590034264236805e-06, "loss": 2.801, "step": 268 }, { "epoch": 0.61, "learning_rate": 1.958168405034668e-06, "loss": 3.3391, "step": 270 }, { "epoch": 0.62, "learning_rate": 1.957325146875834e-06, "loss": 3.636, "step": 272 }, { "epoch": 0.62, "learning_rate": 1.956473659196137e-06, "loss": 3.5637, "step": 274 }, { "epoch": 0.62, "learning_rate": 1.95561394931528e-06, "loss": 3.3122, "step": 276 }, { "epoch": 0.63, "learning_rate": 1.9547460246236473e-06, "loss": 3.1412, "step": 278 }, { "epoch": 0.63, "learning_rate": 1.953869892582239e-06, "loss": 3.7121, "step": 280 }, { "epoch": 0.64, "learning_rate": 1.9529855607226118e-06, "loss": 3.2284, "step": 282 }, { "epoch": 0.64, "learning_rate": 1.9520930366468084e-06, "loss": 3.782, "step": 284 }, { "epoch": 0.65, "learning_rate": 1.951192328027296e-06, "loss": 3.617, "step": 286 }, { "epoch": 0.65, "learning_rate": 1.950283442606898e-06, "loss": 3.6816, "step": 288 }, { "epoch": 0.66, "learning_rate": 1.9493663881987304e-06, "loss": 3.3045, "step": 290 }, { "epoch": 0.66, "learning_rate": 1.9484411726861315e-06, "loss": 3.2486, "step": 292 }, { "epoch": 0.66, "learning_rate": 1.9475078040225962e-06, "loss": 4.0499, "step": 294 }, { "epoch": 0.67, "learning_rate": 1.9465662902317063e-06, "loss": 3.2418, "step": 296 }, { "epoch": 0.67, "learning_rate": 1.9456166394070624e-06, "loss": 3.7954, "step": 298 }, { "epoch": 0.68, "learning_rate": 1.9446588597122142e-06, "loss": 3.3849, "step": 300 }, { "epoch": 0.68, "learning_rate": 1.94369295938059e-06, "loss": 3.1413, "step": 302 }, { "epoch": 0.69, "learning_rate": 1.942718946715426e-06, "loss": 3.2812, "step": 304 }, { "epoch": 0.69, "learning_rate": 1.941736830089695e-06, "loss": 3.1166, "step": 306 }, { "epoch": 0.7, "learning_rate": 1.940746617946035e-06, "loss": 3.3677, "step": 308 }, { "epoch": 0.7, "learning_rate": 1.9397483187966755e-06, "loss": 3.0289, "step": 310 }, { "epoch": 0.71, "learning_rate": 1.938741941223365e-06, "loss": 3.1387, "step": 312 }, { "epoch": 0.71, "learning_rate": 1.9377274938772968e-06, "loss": 3.6475, "step": 314 }, { "epoch": 0.71, "learning_rate": 1.936704985479036e-06, "loss": 3.2878, "step": 316 }, { "epoch": 0.72, "learning_rate": 1.935674424818442e-06, "loss": 3.4601, "step": 318 }, { "epoch": 0.72, "learning_rate": 1.9346358207545962e-06, "loss": 3.4044, "step": 320 }, { "epoch": 0.73, "learning_rate": 1.933589182215722e-06, "loss": 3.1634, "step": 322 }, { "epoch": 0.73, "learning_rate": 1.932534518199112e-06, "loss": 3.7184, "step": 324 }, { "epoch": 0.74, "learning_rate": 1.9314718377710476e-06, "loss": 3.1998, "step": 326 }, { "epoch": 0.74, "learning_rate": 1.930401150066723e-06, "loss": 3.4314, "step": 328 }, { "epoch": 0.75, "learning_rate": 1.9293224642901643e-06, "loss": 3.0628, "step": 330 }, { "epoch": 0.75, "learning_rate": 1.928235789714155e-06, "loss": 3.5893, "step": 332 }, { "epoch": 0.76, "learning_rate": 1.92714113568015e-06, "loss": 3.1285, "step": 334 }, { "epoch": 0.76, "learning_rate": 1.926038511598201e-06, "loss": 3.3582, "step": 336 }, { "epoch": 0.76, "learning_rate": 1.9249279269468717e-06, "loss": 3.4167, "step": 338 }, { "epoch": 0.77, "learning_rate": 1.9238093912731584e-06, "loss": 3.4235, "step": 340 }, { "epoch": 0.77, "learning_rate": 1.9226829141924077e-06, "loss": 3.2468, "step": 342 }, { "epoch": 0.78, "learning_rate": 1.921548505388232e-06, "loss": 3.5108, "step": 344 }, { "epoch": 0.78, "learning_rate": 1.9204061746124294e-06, "loss": 2.8882, "step": 346 }, { "epoch": 0.79, "learning_rate": 1.919255931684898e-06, "loss": 2.9842, "step": 348 }, { "epoch": 0.79, "learning_rate": 1.9180977864935506e-06, "loss": 3.6712, "step": 350 }, { "epoch": 0.8, "learning_rate": 1.916931748994231e-06, "loss": 2.7371, "step": 352 }, { "epoch": 0.8, "learning_rate": 1.9157578292106297e-06, "loss": 3.2926, "step": 354 }, { "epoch": 0.8, "learning_rate": 1.9145760372341945e-06, "loss": 3.7796, "step": 356 }, { "epoch": 0.81, "learning_rate": 1.913386383224046e-06, "loss": 2.6051, "step": 358 }, { "epoch": 0.81, "learning_rate": 1.9121888774068904e-06, "loss": 2.7009, "step": 360 }, { "epoch": 0.82, "learning_rate": 1.91098353007693e-06, "loss": 2.9167, "step": 362 }, { "epoch": 0.82, "learning_rate": 1.9097703515957755e-06, "loss": 3.4324, "step": 364 }, { "epoch": 0.83, "learning_rate": 1.9085493523923583e-06, "loss": 3.2668, "step": 366 }, { "epoch": 0.83, "learning_rate": 1.907320542962839e-06, "loss": 3.1366, "step": 368 }, { "epoch": 0.84, "learning_rate": 1.9060839338705175e-06, "loss": 3.2571, "step": 370 }, { "epoch": 0.84, "learning_rate": 1.9048395357457427e-06, "loss": 3.0712, "step": 372 }, { "epoch": 0.85, "learning_rate": 1.903587359285821e-06, "loss": 2.9556, "step": 374 }, { "epoch": 0.85, "learning_rate": 1.902327415254924e-06, "loss": 3.2769, "step": 376 }, { "epoch": 0.85, "learning_rate": 1.9010597144839964e-06, "loss": 3.0196, "step": 378 }, { "epoch": 0.86, "learning_rate": 1.8997842678706628e-06, "loss": 3.3813, "step": 380 }, { "epoch": 0.86, "learning_rate": 1.8985010863791337e-06, "loss": 3.1364, "step": 382 }, { "epoch": 0.87, "learning_rate": 1.8972101810401115e-06, "loss": 3.1097, "step": 384 }, { "epoch": 0.87, "learning_rate": 1.8959115629506957e-06, "loss": 3.4303, "step": 386 }, { "epoch": 0.88, "learning_rate": 1.8946052432742876e-06, "loss": 2.8442, "step": 388 }, { "epoch": 0.88, "learning_rate": 1.893291233240494e-06, "loss": 2.9757, "step": 390 }, { "epoch": 0.89, "learning_rate": 1.891969544145031e-06, "loss": 3.0015, "step": 392 }, { "epoch": 0.89, "learning_rate": 1.8906401873496263e-06, "loss": 3.175, "step": 394 }, { "epoch": 0.9, "learning_rate": 1.8893031742819228e-06, "loss": 3.0683, "step": 396 }, { "epoch": 0.9, "learning_rate": 1.8879585164353786e-06, "loss": 3.4469, "step": 398 }, { "epoch": 0.9, "learning_rate": 1.8866062253691703e-06, "loss": 2.7505, "step": 400 }, { "epoch": 0.91, "learning_rate": 1.8852463127080914e-06, "loss": 3.9957, "step": 402 }, { "epoch": 0.91, "learning_rate": 1.8838787901424538e-06, "loss": 2.9123, "step": 404 }, { "epoch": 0.92, "learning_rate": 1.882503669427987e-06, "loss": 3.1732, "step": 406 }, { "epoch": 0.92, "learning_rate": 1.8811209623857372e-06, "loss": 2.9553, "step": 408 }, { "epoch": 0.93, "learning_rate": 1.8797306809019652e-06, "loss": 2.877, "step": 410 }, { "epoch": 0.93, "learning_rate": 1.8783328369280446e-06, "loss": 3.3683, "step": 412 }, { "epoch": 0.94, "learning_rate": 1.8769274424803592e-06, "loss": 3.3829, "step": 414 }, { "epoch": 0.94, "learning_rate": 1.8755145096401988e-06, "loss": 3.1289, "step": 416 }, { "epoch": 0.95, "learning_rate": 1.8740940505536567e-06, "loss": 3.1022, "step": 418 }, { "epoch": 0.95, "learning_rate": 1.8726660774315239e-06, "loss": 3.3707, "step": 420 }, { "epoch": 0.95, "learning_rate": 1.8712306025491857e-06, "loss": 2.8037, "step": 422 }, { "epoch": 0.96, "learning_rate": 1.8697876382465147e-06, "loss": 2.8546, "step": 424 }, { "epoch": 0.96, "learning_rate": 1.8683371969277658e-06, "loss": 3.3804, "step": 426 }, { "epoch": 0.97, "learning_rate": 1.8668792910614681e-06, "loss": 3.0239, "step": 428 }, { "epoch": 0.97, "learning_rate": 1.8654139331803198e-06, "loss": 3.0974, "step": 430 }, { "epoch": 0.98, "learning_rate": 1.863941135881079e-06, "loss": 3.0269, "step": 432 }, { "epoch": 0.98, "learning_rate": 1.8624609118244554e-06, "loss": 3.0716, "step": 434 }, { "epoch": 0.99, "learning_rate": 1.8609732737350027e-06, "loss": 3.4675, "step": 436 }, { "epoch": 0.99, "learning_rate": 1.8594782344010076e-06, "loss": 3.048, "step": 438 }, { "epoch": 0.99, "learning_rate": 1.8579758066743807e-06, "loss": 2.787, "step": 440 }, { "epoch": 1.0, "learning_rate": 1.8564660034705462e-06, "loss": 3.342, "step": 442 }, { "epoch": 1.0, "learning_rate": 1.854948837768331e-06, "loss": 2.682, "step": 444 }, { "epoch": 1.01, "learning_rate": 1.8534243226098521e-06, "loss": 3.4592, "step": 446 }, { "epoch": 1.01, "learning_rate": 1.8518924711004049e-06, "loss": 3.4522, "step": 448 }, { "epoch": 1.02, "learning_rate": 1.850353296408352e-06, "loss": 2.9862, "step": 450 }, { "epoch": 1.02, "learning_rate": 1.8488068117650078e-06, "loss": 2.948, "step": 452 }, { "epoch": 1.03, "learning_rate": 1.8472530304645257e-06, "loss": 2.9827, "step": 454 }, { "epoch": 1.03, "learning_rate": 1.8456919658637844e-06, "loss": 3.2129, "step": 456 }, { "epoch": 1.04, "learning_rate": 1.8441236313822724e-06, "loss": 2.9592, "step": 458 }, { "epoch": 1.04, "learning_rate": 1.8425480405019726e-06, "loss": 3.2023, "step": 460 }, { "epoch": 1.04, "learning_rate": 1.8409652067672465e-06, "loss": 3.0004, "step": 462 }, { "epoch": 1.05, "learning_rate": 1.8393751437847183e-06, "loss": 3.1313, "step": 464 }, { "epoch": 1.05, "learning_rate": 1.8377778652231568e-06, "loss": 3.3725, "step": 466 }, { "epoch": 1.06, "learning_rate": 1.8361733848133595e-06, "loss": 3.0454, "step": 468 }, { "epoch": 1.06, "learning_rate": 1.8345617163480327e-06, "loss": 3.1489, "step": 470 }, { "epoch": 1.07, "learning_rate": 1.8329428736816746e-06, "loss": 3.4101, "step": 472 }, { "epoch": 1.07, "learning_rate": 1.8313168707304549e-06, "loss": 3.0215, "step": 474 }, { "epoch": 1.08, "learning_rate": 1.8296837214720967e-06, "loss": 3.1681, "step": 476 }, { "epoch": 1.08, "learning_rate": 1.828043439945754e-06, "loss": 2.9717, "step": 478 }, { "epoch": 1.09, "learning_rate": 1.8263960402518937e-06, "loss": 2.9814, "step": 480 }, { "epoch": 1.09, "learning_rate": 1.8247415365521723e-06, "loss": 2.752, "step": 482 }, { "epoch": 1.09, "learning_rate": 1.8230799430693154e-06, "loss": 3.3524, "step": 484 }, { "epoch": 1.1, "learning_rate": 1.8214112740869946e-06, "loss": 2.9591, "step": 486 }, { "epoch": 1.1, "learning_rate": 1.8197355439497058e-06, "loss": 3.0024, "step": 488 }, { "epoch": 1.11, "learning_rate": 1.8180527670626443e-06, "loss": 3.0181, "step": 490 }, { "epoch": 1.11, "learning_rate": 1.8163629578915823e-06, "loss": 3.016, "step": 492 }, { "epoch": 1.12, "learning_rate": 1.8146661309627441e-06, "loss": 3.2005, "step": 494 }, { "epoch": 1.12, "learning_rate": 1.8129623008626818e-06, "loss": 3.0706, "step": 496 }, { "epoch": 1.13, "learning_rate": 1.8112514822381483e-06, "loss": 2.8435, "step": 498 }, { "epoch": 1.13, "learning_rate": 1.8095336897959729e-06, "loss": 3.0324, "step": 500 }, { "epoch": 1.14, "learning_rate": 1.8078089383029347e-06, "loss": 3.4639, "step": 502 }, { "epoch": 1.14, "learning_rate": 1.8060772425856352e-06, "loss": 3.2607, "step": 504 }, { "epoch": 1.14, "learning_rate": 1.8043386175303706e-06, "loss": 3.1481, "step": 506 }, { "epoch": 1.15, "learning_rate": 1.8025930780830048e-06, "loss": 2.9177, "step": 508 }, { "epoch": 1.15, "learning_rate": 1.8008406392488402e-06, "loss": 3.5127, "step": 510 }, { "epoch": 1.16, "learning_rate": 1.7990813160924888e-06, "loss": 2.4117, "step": 512 }, { "epoch": 1.16, "learning_rate": 1.797315123737743e-06, "loss": 2.7837, "step": 514 }, { "epoch": 1.17, "learning_rate": 1.795542077367445e-06, "loss": 3.0138, "step": 516 }, { "epoch": 1.17, "learning_rate": 1.793762192223357e-06, "loss": 3.0584, "step": 518 }, { "epoch": 1.18, "learning_rate": 1.7919754836060297e-06, "loss": 3.0763, "step": 520 }, { "epoch": 1.18, "learning_rate": 1.7901819668746704e-06, "loss": 3.5087, "step": 522 }, { "epoch": 1.18, "learning_rate": 1.7883816574470125e-06, "loss": 2.7614, "step": 524 }, { "epoch": 1.19, "learning_rate": 1.7865745707991816e-06, "loss": 3.097, "step": 526 }, { "epoch": 1.19, "learning_rate": 1.7847607224655616e-06, "loss": 3.2038, "step": 528 }, { "epoch": 1.2, "learning_rate": 1.782940128038664e-06, "loss": 3.0407, "step": 530 }, { "epoch": 1.2, "learning_rate": 1.7811128031689915e-06, "loss": 3.0128, "step": 532 }, { "epoch": 1.21, "learning_rate": 1.7792787635649043e-06, "loss": 2.8996, "step": 534 }, { "epoch": 1.21, "learning_rate": 1.7774380249924842e-06, "loss": 2.8381, "step": 536 }, { "epoch": 1.22, "learning_rate": 1.7755906032754008e-06, "loss": 3.0, "step": 538 }, { "epoch": 1.22, "learning_rate": 1.7737365142947746e-06, "loss": 3.134, "step": 540 }, { "epoch": 1.23, "learning_rate": 1.7718757739890393e-06, "loss": 2.8977, "step": 542 }, { "epoch": 1.23, "learning_rate": 1.7700083983538065e-06, "loss": 3.2885, "step": 544 }, { "epoch": 1.23, "learning_rate": 1.7681344034417281e-06, "loss": 2.9073, "step": 546 }, { "epoch": 1.24, "learning_rate": 1.7662538053623562e-06, "loss": 2.9674, "step": 548 }, { "epoch": 1.24, "learning_rate": 1.7643666202820078e-06, "loss": 3.5389, "step": 550 }, { "epoch": 1.25, "learning_rate": 1.762472864423623e-06, "loss": 2.9166, "step": 552 }, { "epoch": 1.25, "learning_rate": 1.760572554066628e-06, "loss": 3.3294, "step": 554 }, { "epoch": 1.26, "learning_rate": 1.7586657055467922e-06, "loss": 2.8968, "step": 556 }, { "epoch": 1.26, "learning_rate": 1.7567523352560907e-06, "loss": 3.0126, "step": 558 }, { "epoch": 1.27, "learning_rate": 1.7548324596425622e-06, "loss": 2.9592, "step": 560 }, { "epoch": 1.27, "learning_rate": 1.7529060952101666e-06, "loss": 2.9064, "step": 562 }, { "epoch": 1.28, "learning_rate": 1.7509732585186457e-06, "loss": 3.0465, "step": 564 }, { "epoch": 1.28, "learning_rate": 1.749033966183377e-06, "loss": 2.8386, "step": 566 }, { "epoch": 1.28, "learning_rate": 1.7470882348752354e-06, "loss": 3.4267, "step": 568 }, { "epoch": 1.29, "learning_rate": 1.7451360813204454e-06, "loss": 3.2419, "step": 570 }, { "epoch": 1.29, "learning_rate": 1.7431775223004416e-06, "loss": 3.0164, "step": 572 }, { "epoch": 1.3, "learning_rate": 1.7412125746517212e-06, "loss": 3.4307, "step": 574 }, { "epoch": 1.3, "learning_rate": 1.7392412552657e-06, "loss": 2.9396, "step": 576 }, { "epoch": 1.31, "learning_rate": 1.737263581088569e-06, "loss": 2.7438, "step": 578 }, { "epoch": 1.31, "learning_rate": 1.7352795691211459e-06, "loss": 2.7535, "step": 580 }, { "epoch": 1.32, "learning_rate": 1.7332892364187313e-06, "loss": 3.0422, "step": 582 }, { "epoch": 1.32, "learning_rate": 1.7312926000909606e-06, "loss": 2.7916, "step": 584 }, { "epoch": 1.33, "learning_rate": 1.7292896773016581e-06, "loss": 3.5253, "step": 586 }, { "epoch": 1.33, "learning_rate": 1.7272804852686886e-06, "loss": 3.4058, "step": 588 }, { "epoch": 1.33, "learning_rate": 1.725265041263809e-06, "loss": 3.1248, "step": 590 }, { "epoch": 1.34, "learning_rate": 1.7232433626125217e-06, "loss": 3.1154, "step": 592 }, { "epoch": 1.34, "learning_rate": 1.7212154666939234e-06, "loss": 2.646, "step": 594 }, { "epoch": 1.35, "learning_rate": 1.7191813709405572e-06, "loss": 2.7494, "step": 596 }, { "epoch": 1.35, "learning_rate": 1.7171410928382622e-06, "loss": 3.5374, "step": 598 }, { "epoch": 1.36, "learning_rate": 1.715094649926023e-06, "loss": 2.79, "step": 600 }, { "epoch": 1.36, "learning_rate": 1.7130420597958196e-06, "loss": 2.9815, "step": 602 }, { "epoch": 1.37, "learning_rate": 1.7109833400924754e-06, "loss": 2.7357, "step": 604 }, { "epoch": 1.37, "learning_rate": 1.708918508513506e-06, "loss": 2.9524, "step": 606 }, { "epoch": 1.37, "learning_rate": 1.7068475828089672e-06, "loss": 2.9479, "step": 608 }, { "epoch": 1.38, "learning_rate": 1.7047705807813017e-06, "loss": 3.043, "step": 610 }, { "epoch": 1.38, "learning_rate": 1.702687520285187e-06, "loss": 2.9926, "step": 612 }, { "epoch": 1.39, "learning_rate": 1.700598419227381e-06, "loss": 2.9575, "step": 614 }, { "epoch": 1.39, "learning_rate": 1.6985032955665686e-06, "loss": 3.155, "step": 616 }, { "epoch": 1.4, "learning_rate": 1.6964021673132075e-06, "loss": 2.6612, "step": 618 }, { "epoch": 1.4, "learning_rate": 1.6942950525293726e-06, "loss": 2.9378, "step": 620 }, { "epoch": 1.41, "learning_rate": 1.692181969328602e-06, "loss": 3.1512, "step": 622 }, { "epoch": 1.41, "learning_rate": 1.6900629358757396e-06, "loss": 3.2628, "step": 624 }, { "epoch": 1.42, "learning_rate": 1.687937970386781e-06, "loss": 2.9707, "step": 626 }, { "epoch": 1.42, "learning_rate": 1.6858070911287139e-06, "loss": 3.1349, "step": 628 }, { "epoch": 1.42, "learning_rate": 1.6836703164193651e-06, "loss": 3.1754, "step": 630 }, { "epoch": 1.43, "learning_rate": 1.6815276646272399e-06, "loss": 3.3287, "step": 632 }, { "epoch": 1.43, "learning_rate": 1.6793791541713649e-06, "loss": 2.9116, "step": 634 }, { "epoch": 1.44, "learning_rate": 1.6772248035211303e-06, "loss": 2.6243, "step": 636 }, { "epoch": 1.44, "learning_rate": 1.6750646311961305e-06, "loss": 3.0353, "step": 638 }, { "epoch": 1.45, "learning_rate": 1.6728986557660056e-06, "loss": 3.0738, "step": 640 }, { "epoch": 1.45, "learning_rate": 1.670726895850281e-06, "loss": 2.6913, "step": 642 }, { "epoch": 1.46, "learning_rate": 1.668549370118208e-06, "loss": 2.8307, "step": 644 }, { "epoch": 1.46, "learning_rate": 1.666366097288603e-06, "loss": 2.9507, "step": 646 }, { "epoch": 1.47, "learning_rate": 1.6641770961296854e-06, "loss": 3.0626, "step": 648 }, { "epoch": 1.47, "learning_rate": 1.661982385458919e-06, "loss": 2.7811, "step": 650 }, { "epoch": 1.47, "learning_rate": 1.6597819841428481e-06, "loss": 3.4271, "step": 652 }, { "epoch": 1.48, "learning_rate": 1.6575759110969361e-06, "loss": 2.98, "step": 654 }, { "epoch": 1.48, "learning_rate": 1.6553641852854017e-06, "loss": 2.7632, "step": 656 }, { "epoch": 1.49, "learning_rate": 1.6531468257210582e-06, "loss": 3.2849, "step": 658 }, { "epoch": 1.49, "learning_rate": 1.6509238514651479e-06, "loss": 2.726, "step": 660 }, { "epoch": 1.5, "learning_rate": 1.6486952816271793e-06, "loss": 2.8952, "step": 662 }, { "epoch": 1.5, "learning_rate": 1.6464611353647624e-06, "loss": 3.0349, "step": 664 }, { "epoch": 1.51, "learning_rate": 1.6442214318834446e-06, "loss": 2.8746, "step": 666 }, { "epoch": 1.51, "learning_rate": 1.6419761904365453e-06, "loss": 2.8227, "step": 668 }, { "epoch": 1.51, "learning_rate": 1.6397254303249893e-06, "loss": 3.1655, "step": 670 }, { "epoch": 1.52, "learning_rate": 1.637469170897143e-06, "loss": 2.7579, "step": 672 }, { "epoch": 1.52, "learning_rate": 1.6352074315486463e-06, "loss": 2.6705, "step": 674 }, { "epoch": 1.53, "learning_rate": 1.6329402317222472e-06, "loss": 2.9705, "step": 676 }, { "epoch": 1.53, "learning_rate": 1.630667590907633e-06, "loss": 2.906, "step": 678 }, { "epoch": 1.54, "learning_rate": 1.6283895286412646e-06, "loss": 3.1805, "step": 680 }, { "epoch": 1.54, "learning_rate": 1.626106064506207e-06, "loss": 2.8826, "step": 682 }, { "epoch": 1.55, "learning_rate": 1.6238172181319629e-06, "loss": 3.0817, "step": 684 }, { "epoch": 1.55, "learning_rate": 1.621523009194301e-06, "loss": 3.0208, "step": 686 }, { "epoch": 1.56, "learning_rate": 1.6192234574150897e-06, "loss": 3.182, "step": 688 }, { "epoch": 1.56, "learning_rate": 1.6169185825621266e-06, "loss": 3.1146, "step": 690 }, { "epoch": 1.56, "learning_rate": 1.6146084044489672e-06, "loss": 2.9739, "step": 692 }, { "epoch": 1.57, "learning_rate": 1.6122929429347574e-06, "loss": 2.8537, "step": 694 }, { "epoch": 1.57, "learning_rate": 1.6099722179240595e-06, "loss": 3.1857, "step": 696 }, { "epoch": 1.58, "learning_rate": 1.6076462493666844e-06, "loss": 2.9034, "step": 698 }, { "epoch": 1.58, "learning_rate": 1.6053150572575173e-06, "loss": 2.8878, "step": 700 }, { "epoch": 1.59, "learning_rate": 1.6029786616363472e-06, "loss": 2.8523, "step": 702 }, { "epoch": 1.59, "learning_rate": 1.6006370825876952e-06, "loss": 3.2026, "step": 704 }, { "epoch": 1.6, "learning_rate": 1.5982903402406396e-06, "loss": 2.5883, "step": 706 }, { "epoch": 1.6, "learning_rate": 1.5959384547686455e-06, "loss": 3.3862, "step": 708 }, { "epoch": 1.61, "learning_rate": 1.5935814463893903e-06, "loss": 3.1856, "step": 710 }, { "epoch": 1.61, "learning_rate": 1.5912193353645887e-06, "loss": 2.8158, "step": 712 }, { "epoch": 1.61, "learning_rate": 1.5888521419998206e-06, "loss": 3.0144, "step": 714 }, { "epoch": 1.62, "learning_rate": 1.5864798866443554e-06, "loss": 2.7278, "step": 716 }, { "epoch": 1.62, "learning_rate": 1.5841025896909766e-06, "loss": 3.1902, "step": 718 }, { "epoch": 1.63, "learning_rate": 1.5817202715758081e-06, "loss": 2.6701, "step": 720 }, { "epoch": 1.63, "learning_rate": 1.5793329527781367e-06, "loss": 2.9999, "step": 722 }, { "epoch": 1.64, "learning_rate": 1.576940653820238e-06, "loss": 2.9395, "step": 724 }, { "epoch": 1.64, "learning_rate": 1.5745433952671973e-06, "loss": 2.8951, "step": 726 }, { "epoch": 1.65, "learning_rate": 1.5721411977267363e-06, "loss": 2.6139, "step": 728 }, { "epoch": 1.65, "learning_rate": 1.5697340818490324e-06, "loss": 3.2042, "step": 730 }, { "epoch": 1.66, "learning_rate": 1.5673220683265437e-06, "loss": 2.813, "step": 732 }, { "epoch": 1.66, "learning_rate": 1.5649051778938303e-06, "loss": 2.8708, "step": 734 }, { "epoch": 1.66, "learning_rate": 1.5624834313273755e-06, "loss": 2.668, "step": 736 }, { "epoch": 1.67, "learning_rate": 1.5600568494454084e-06, "loss": 3.3815, "step": 738 }, { "epoch": 1.67, "learning_rate": 1.5576254531077238e-06, "loss": 2.7051, "step": 740 }, { "epoch": 1.68, "learning_rate": 1.555189263215503e-06, "loss": 3.0297, "step": 742 }, { "epoch": 1.68, "learning_rate": 1.5527483007111357e-06, "loss": 2.8407, "step": 744 }, { "epoch": 1.69, "learning_rate": 1.5503025865780374e-06, "loss": 2.7572, "step": 746 }, { "epoch": 1.69, "learning_rate": 1.5478521418404712e-06, "loss": 2.7898, "step": 748 }, { "epoch": 1.7, "learning_rate": 1.5453969875633655e-06, "loss": 2.7977, "step": 750 }, { "epoch": 1.7, "learning_rate": 1.5429371448521346e-06, "loss": 2.8936, "step": 752 }, { "epoch": 1.7, "learning_rate": 1.5404726348524956e-06, "loss": 2.8459, "step": 754 }, { "epoch": 1.71, "learning_rate": 1.5380034787502874e-06, "loss": 2.8091, "step": 756 }, { "epoch": 1.71, "learning_rate": 1.5355296977712887e-06, "loss": 3.0049, "step": 758 }, { "epoch": 1.72, "learning_rate": 1.5330513131810356e-06, "loss": 3.1344, "step": 760 }, { "epoch": 1.72, "learning_rate": 1.530568346284638e-06, "loss": 3.065, "step": 762 }, { "epoch": 1.73, "learning_rate": 1.5280808184265968e-06, "loss": 3.0737, "step": 764 }, { "epoch": 1.73, "learning_rate": 1.5255887509906219e-06, "loss": 3.4171, "step": 766 }, { "epoch": 1.74, "learning_rate": 1.5230921653994452e-06, "loss": 3.1458, "step": 768 }, { "epoch": 1.74, "learning_rate": 1.5205910831146405e-06, "loss": 2.7437, "step": 770 }, { "epoch": 1.75, "learning_rate": 1.518085525636435e-06, "loss": 2.6169, "step": 772 }, { "epoch": 1.75, "learning_rate": 1.5155755145035273e-06, "loss": 2.5982, "step": 774 }, { "epoch": 1.75, "learning_rate": 1.513061071292901e-06, "loss": 2.7623, "step": 776 }, { "epoch": 1.76, "learning_rate": 1.5105422176196388e-06, "loss": 2.7865, "step": 778 }, { "epoch": 1.76, "learning_rate": 1.5080189751367392e-06, "loss": 2.7576, "step": 780 }, { "epoch": 1.77, "learning_rate": 1.5054913655349264e-06, "loss": 3.1102, "step": 782 }, { "epoch": 1.77, "learning_rate": 1.5029594105424674e-06, "loss": 2.5107, "step": 784 }, { "epoch": 1.78, "learning_rate": 1.5004231319249833e-06, "loss": 3.3043, "step": 786 }, { "epoch": 1.78, "learning_rate": 1.4978825514852624e-06, "loss": 3.1024, "step": 788 }, { "epoch": 1.79, "learning_rate": 1.495337691063074e-06, "loss": 2.9356, "step": 790 }, { "epoch": 1.79, "learning_rate": 1.492788572534978e-06, "loss": 2.8193, "step": 792 }, { "epoch": 1.8, "learning_rate": 1.4902352178141409e-06, "loss": 2.8079, "step": 794 }, { "epoch": 1.8, "learning_rate": 1.4876776488501426e-06, "loss": 2.6642, "step": 796 }, { "epoch": 1.8, "learning_rate": 1.4851158876287923e-06, "loss": 2.8662, "step": 798 }, { "epoch": 1.81, "learning_rate": 1.482549956171936e-06, "loss": 3.0592, "step": 800 }, { "epoch": 1.81, "learning_rate": 1.4799798765372693e-06, "loss": 3.129, "step": 802 }, { "epoch": 1.82, "learning_rate": 1.4774056708181464e-06, "loss": 2.9623, "step": 804 }, { "epoch": 1.82, "learning_rate": 1.4748273611433918e-06, "loss": 2.6141, "step": 806 }, { "epoch": 1.83, "learning_rate": 1.4722449696771084e-06, "loss": 2.9788, "step": 808 }, { "epoch": 1.83, "learning_rate": 1.4696585186184878e-06, "loss": 2.8914, "step": 810 }, { "epoch": 1.84, "learning_rate": 1.4670680302016199e-06, "loss": 2.8962, "step": 812 }, { "epoch": 1.84, "learning_rate": 1.4644735266953e-06, "loss": 2.7766, "step": 814 }, { "epoch": 1.85, "learning_rate": 1.46187503040284e-06, "loss": 3.4853, "step": 816 }, { "epoch": 1.85, "learning_rate": 1.4592725636618743e-06, "loss": 2.6859, "step": 818 }, { "epoch": 1.85, "learning_rate": 1.4566661488441691e-06, "loss": 2.9598, "step": 820 }, { "epoch": 1.86, "learning_rate": 1.45405580835543e-06, "loss": 2.8372, "step": 822 }, { "epoch": 1.86, "learning_rate": 1.4514415646351087e-06, "loss": 2.5959, "step": 824 }, { "epoch": 1.87, "learning_rate": 1.4488234401562104e-06, "loss": 3.1798, "step": 826 }, { "epoch": 1.87, "learning_rate": 1.4462014574251012e-06, "loss": 2.8983, "step": 828 }, { "epoch": 1.88, "learning_rate": 1.4435756389813137e-06, "loss": 3.2622, "step": 830 }, { "epoch": 1.88, "learning_rate": 1.4409460073973543e-06, "loss": 3.1218, "step": 832 }, { "epoch": 1.89, "learning_rate": 1.4383125852785081e-06, "loss": 3.0423, "step": 834 }, { "epoch": 1.89, "learning_rate": 1.4356753952626449e-06, "loss": 2.719, "step": 836 }, { "epoch": 1.89, "learning_rate": 1.4330344600200253e-06, "loss": 2.7674, "step": 838 }, { "epoch": 1.9, "learning_rate": 1.4303898022531046e-06, "loss": 2.8647, "step": 840 }, { "epoch": 1.9, "learning_rate": 1.427741444696339e-06, "loss": 2.7449, "step": 842 }, { "epoch": 1.91, "learning_rate": 1.425089410115989e-06, "loss": 2.9066, "step": 844 }, { "epoch": 1.91, "learning_rate": 1.422433721309924e-06, "loss": 2.7818, "step": 846 }, { "epoch": 1.92, "learning_rate": 1.419774401107427e-06, "loss": 3.2886, "step": 848 }, { "epoch": 1.92, "learning_rate": 1.4171114723689975e-06, "loss": 3.0819, "step": 850 }, { "epoch": 1.93, "learning_rate": 1.4144449579861552e-06, "loss": 2.8043, "step": 852 }, { "epoch": 1.93, "learning_rate": 1.4117748808812437e-06, "loss": 2.9312, "step": 854 }, { "epoch": 1.94, "learning_rate": 1.409101264007233e-06, "loss": 3.0167, "step": 856 }, { "epoch": 1.94, "learning_rate": 1.4064241303475212e-06, "loss": 3.3519, "step": 858 }, { "epoch": 1.94, "learning_rate": 1.4037435029157399e-06, "loss": 2.8223, "step": 860 }, { "epoch": 1.95, "learning_rate": 1.4010594047555533e-06, "loss": 2.9047, "step": 862 }, { "epoch": 1.95, "learning_rate": 1.398371858940461e-06, "loss": 2.687, "step": 864 }, { "epoch": 1.96, "learning_rate": 1.395680888573601e-06, "loss": 3.0266, "step": 866 }, { "epoch": 1.96, "learning_rate": 1.3929865167875486e-06, "loss": 2.9913, "step": 868 }, { "epoch": 1.97, "learning_rate": 1.3902887667441203e-06, "loss": 2.7403, "step": 870 }, { "epoch": 1.97, "learning_rate": 1.3875876616341724e-06, "loss": 2.5568, "step": 872 }, { "epoch": 1.98, "learning_rate": 1.3848832246774034e-06, "loss": 2.6422, "step": 874 }, { "epoch": 1.98, "learning_rate": 1.3821754791221525e-06, "loss": 2.8895, "step": 876 }, { "epoch": 1.99, "learning_rate": 1.379464448245202e-06, "loss": 2.7376, "step": 878 }, { "epoch": 1.99, "learning_rate": 1.3767501553515757e-06, "loss": 2.8462, "step": 880 }, { "epoch": 1.99, "learning_rate": 1.374032623774338e-06, "loss": 2.9053, "step": 882 }, { "epoch": 2.0, "learning_rate": 1.3713118768743957e-06, "loss": 3.2814, "step": 884 }, { "epoch": 2.0, "learning_rate": 1.3685879380402942e-06, "loss": 2.7977, "step": 886 }, { "epoch": 2.01, "learning_rate": 1.3658608306880196e-06, "loss": 2.7935, "step": 888 }, { "epoch": 2.01, "learning_rate": 1.363130578260794e-06, "loss": 2.7293, "step": 890 }, { "epoch": 2.02, "learning_rate": 1.360397204228877e-06, "loss": 3.2322, "step": 892 }, { "epoch": 2.02, "learning_rate": 1.357660732089362e-06, "loss": 2.8346, "step": 894 }, { "epoch": 2.03, "learning_rate": 1.3549211853659752e-06, "loss": 3.0882, "step": 896 }, { "epoch": 2.03, "learning_rate": 1.3521785876088734e-06, "loss": 2.6518, "step": 898 }, { "epoch": 2.04, "learning_rate": 1.3494329623944402e-06, "loss": 3.3182, "step": 900 }, { "epoch": 2.04, "learning_rate": 1.3466843333250855e-06, "loss": 2.8439, "step": 902 }, { "epoch": 2.04, "learning_rate": 1.3439327240290402e-06, "loss": 2.5887, "step": 904 }, { "epoch": 2.05, "learning_rate": 1.3411781581601557e-06, "loss": 2.8299, "step": 906 }, { "epoch": 2.05, "learning_rate": 1.338420659397698e-06, "loss": 3.1664, "step": 908 }, { "epoch": 2.06, "learning_rate": 1.3356602514461457e-06, "loss": 2.7001, "step": 910 }, { "epoch": 2.06, "learning_rate": 1.3328969580349867e-06, "loss": 2.772, "step": 912 }, { "epoch": 2.07, "learning_rate": 1.3301308029185123e-06, "loss": 3.1132, "step": 914 }, { "epoch": 2.07, "learning_rate": 1.3273618098756148e-06, "loss": 2.8351, "step": 916 }, { "epoch": 2.08, "learning_rate": 1.324590002709581e-06, "loss": 2.7281, "step": 918 }, { "epoch": 2.08, "learning_rate": 1.3218154052478915e-06, "loss": 3.2806, "step": 920 }, { "epoch": 2.08, "learning_rate": 1.3190380413420103e-06, "loss": 2.5147, "step": 922 }, { "epoch": 2.09, "learning_rate": 1.3162579348671852e-06, "loss": 2.8666, "step": 924 }, { "epoch": 2.09, "learning_rate": 1.313475109722239e-06, "loss": 2.9747, "step": 926 }, { "epoch": 2.1, "learning_rate": 1.3106895898293651e-06, "loss": 2.8454, "step": 928 }, { "epoch": 2.1, "learning_rate": 1.3079013991339228e-06, "loss": 3.3243, "step": 930 }, { "epoch": 2.11, "learning_rate": 1.3051105616042294e-06, "loss": 2.6016, "step": 932 }, { "epoch": 2.11, "learning_rate": 1.3023171012313566e-06, "loss": 2.9384, "step": 934 }, { "epoch": 2.12, "learning_rate": 1.2995210420289216e-06, "loss": 2.7868, "step": 936 }, { "epoch": 2.12, "learning_rate": 1.296722408032884e-06, "loss": 3.0151, "step": 938 }, { "epoch": 2.13, "learning_rate": 1.2939212233013354e-06, "loss": 2.9898, "step": 940 }, { "epoch": 2.13, "learning_rate": 1.2911175119142962e-06, "loss": 2.8768, "step": 942 }, { "epoch": 2.13, "learning_rate": 1.2883112979735047e-06, "loss": 2.4141, "step": 944 }, { "epoch": 2.14, "learning_rate": 1.285502605602214e-06, "loss": 2.723, "step": 946 }, { "epoch": 2.14, "learning_rate": 1.2826914589449825e-06, "loss": 3.1389, "step": 948 }, { "epoch": 2.15, "learning_rate": 1.2798778821674652e-06, "loss": 3.1153, "step": 950 }, { "epoch": 2.15, "learning_rate": 1.2770618994562088e-06, "loss": 2.6294, "step": 952 }, { "epoch": 2.16, "learning_rate": 1.274243535018441e-06, "loss": 3.0102, "step": 954 }, { "epoch": 2.16, "learning_rate": 1.2714228130818654e-06, "loss": 3.0944, "step": 956 }, { "epoch": 2.17, "learning_rate": 1.2685997578944495e-06, "loss": 3.0764, "step": 958 }, { "epoch": 2.17, "learning_rate": 1.2657743937242201e-06, "loss": 2.5106, "step": 960 }, { "epoch": 2.18, "learning_rate": 1.2629467448590519e-06, "loss": 2.8248, "step": 962 }, { "epoch": 2.18, "learning_rate": 1.2601168356064593e-06, "loss": 2.5243, "step": 964 }, { "epoch": 2.18, "learning_rate": 1.2572846902933893e-06, "loss": 2.5107, "step": 966 }, { "epoch": 2.19, "learning_rate": 1.254450333266009e-06, "loss": 2.6401, "step": 968 }, { "epoch": 2.19, "learning_rate": 1.2516137888895003e-06, "loss": 2.9231, "step": 970 }, { "epoch": 2.2, "learning_rate": 1.248775081547846e-06, "loss": 2.6478, "step": 972 }, { "epoch": 2.2, "learning_rate": 1.245934235643625e-06, "loss": 3.1858, "step": 974 }, { "epoch": 2.21, "learning_rate": 1.2430912755977978e-06, "loss": 2.9196, "step": 976 }, { "epoch": 2.21, "learning_rate": 1.240246225849501e-06, "loss": 3.4172, "step": 978 }, { "epoch": 2.22, "learning_rate": 1.237399110855833e-06, "loss": 2.8239, "step": 980 }, { "epoch": 2.22, "learning_rate": 1.2345499550916475e-06, "loss": 2.9645, "step": 982 }, { "epoch": 2.22, "learning_rate": 1.2316987830493407e-06, "loss": 3.0415, "step": 984 }, { "epoch": 2.23, "learning_rate": 1.228845619238641e-06, "loss": 2.9531, "step": 986 }, { "epoch": 2.23, "learning_rate": 1.2259904881863996e-06, "loss": 2.7871, "step": 988 }, { "epoch": 2.24, "learning_rate": 1.2231334144363783e-06, "loss": 2.7016, "step": 990 }, { "epoch": 2.24, "learning_rate": 1.2202744225490395e-06, "loss": 3.3212, "step": 992 }, { "epoch": 2.25, "learning_rate": 1.2174135371013342e-06, "loss": 2.9828, "step": 994 }, { "epoch": 2.25, "learning_rate": 1.2145507826864916e-06, "loss": 2.4862, "step": 996 }, { "epoch": 2.26, "learning_rate": 1.2116861839138064e-06, "loss": 2.9166, "step": 998 }, { "epoch": 2.26, "learning_rate": 1.208819765408429e-06, "loss": 3.1725, "step": 1000 }, { "epoch": 2.27, "learning_rate": 1.2059515518111525e-06, "loss": 2.8519, "step": 1002 }, { "epoch": 2.27, "learning_rate": 1.203081567778201e-06, "loss": 2.7825, "step": 1004 }, { "epoch": 2.27, "learning_rate": 1.200209837981019e-06, "loss": 2.7329, "step": 1006 }, { "epoch": 2.28, "learning_rate": 1.1973363871060563e-06, "loss": 2.812, "step": 1008 }, { "epoch": 2.28, "learning_rate": 1.1944612398545595e-06, "loss": 3.0708, "step": 1010 }, { "epoch": 2.29, "learning_rate": 1.1915844209423572e-06, "loss": 2.4646, "step": 1012 }, { "epoch": 2.29, "learning_rate": 1.1887059550996486e-06, "loss": 2.9059, "step": 1014 }, { "epoch": 2.3, "learning_rate": 1.1858258670707894e-06, "loss": 2.7188, "step": 1016 }, { "epoch": 2.3, "learning_rate": 1.182944181614082e-06, "loss": 2.8745, "step": 1018 }, { "epoch": 2.31, "learning_rate": 1.1800609235015589e-06, "loss": 2.8054, "step": 1020 }, { "epoch": 2.31, "learning_rate": 1.1771761175187734e-06, "loss": 3.4573, "step": 1022 }, { "epoch": 2.32, "learning_rate": 1.1742897884645837e-06, "loss": 2.6994, "step": 1024 }, { "epoch": 2.32, "learning_rate": 1.1714019611509416e-06, "loss": 2.8901, "step": 1026 }, { "epoch": 2.32, "learning_rate": 1.1685126604026783e-06, "loss": 2.8239, "step": 1028 }, { "epoch": 2.33, "learning_rate": 1.1656219110572908e-06, "loss": 3.1191, "step": 1030 }, { "epoch": 2.33, "learning_rate": 1.1627297379647297e-06, "loss": 2.6534, "step": 1032 }, { "epoch": 2.34, "learning_rate": 1.1598361659871835e-06, "loss": 3.364, "step": 1034 }, { "epoch": 2.34, "learning_rate": 1.156941219998867e-06, "loss": 2.9694, "step": 1036 }, { "epoch": 2.35, "learning_rate": 1.1540449248858059e-06, "loss": 3.0236, "step": 1038 }, { "epoch": 2.35, "learning_rate": 1.1511473055456237e-06, "loss": 2.8845, "step": 1040 }, { "epoch": 2.36, "learning_rate": 1.1482483868873274e-06, "loss": 2.7542, "step": 1042 }, { "epoch": 2.36, "learning_rate": 1.1453481938310934e-06, "loss": 2.8498, "step": 1044 }, { "epoch": 2.37, "learning_rate": 1.1424467513080537e-06, "loss": 2.8957, "step": 1046 }, { "epoch": 2.37, "learning_rate": 1.1395440842600805e-06, "loss": 2.5015, "step": 1048 }, { "epoch": 2.37, "learning_rate": 1.136640217639573e-06, "loss": 2.7661, "step": 1050 }, { "epoch": 2.38, "learning_rate": 1.1337351764092418e-06, "loss": 2.7323, "step": 1052 }, { "epoch": 2.38, "learning_rate": 1.1308289855418955e-06, "loss": 2.8539, "step": 1054 }, { "epoch": 2.39, "learning_rate": 1.1279216700202251e-06, "loss": 2.8593, "step": 1056 }, { "epoch": 2.39, "learning_rate": 1.12501325483659e-06, "loss": 2.9112, "step": 1058 }, { "epoch": 2.4, "learning_rate": 1.122103764992801e-06, "loss": 2.6268, "step": 1060 }, { "epoch": 2.4, "learning_rate": 1.1191932254999098e-06, "loss": 3.1306, "step": 1062 }, { "epoch": 2.41, "learning_rate": 1.1162816613779896e-06, "loss": 2.8467, "step": 1064 }, { "epoch": 2.41, "learning_rate": 1.1133690976559212e-06, "loss": 2.6382, "step": 1066 }, { "epoch": 2.41, "learning_rate": 1.1104555593711796e-06, "loss": 2.7961, "step": 1068 }, { "epoch": 2.42, "learning_rate": 1.1075410715696167e-06, "loss": 2.6495, "step": 1070 }, { "epoch": 2.42, "learning_rate": 1.1046256593052474e-06, "loss": 2.88, "step": 1072 }, { "epoch": 2.43, "learning_rate": 1.101709347640033e-06, "loss": 2.5019, "step": 1074 }, { "epoch": 2.43, "learning_rate": 1.098792161643667e-06, "loss": 2.4956, "step": 1076 }, { "epoch": 2.44, "learning_rate": 1.095874126393358e-06, "loss": 2.7829, "step": 1078 }, { "epoch": 2.44, "learning_rate": 1.0929552669736162e-06, "loss": 3.1953, "step": 1080 }, { "epoch": 2.45, "learning_rate": 1.0900356084760365e-06, "loss": 2.8705, "step": 1082 }, { "epoch": 2.45, "learning_rate": 1.087115175999082e-06, "loss": 2.6656, "step": 1084 }, { "epoch": 2.46, "learning_rate": 1.0841939946478703e-06, "loss": 2.8489, "step": 1086 }, { "epoch": 2.46, "learning_rate": 1.081272089533956e-06, "loss": 2.5249, "step": 1088 }, { "epoch": 2.46, "learning_rate": 1.0783494857751158e-06, "loss": 2.8785, "step": 1090 }, { "epoch": 2.47, "learning_rate": 1.0754262084951317e-06, "loss": 2.4657, "step": 1092 }, { "epoch": 2.47, "learning_rate": 1.0725022828235764e-06, "loss": 2.469, "step": 1094 }, { "epoch": 2.48, "learning_rate": 1.0695777338955954e-06, "loss": 3.0364, "step": 1096 }, { "epoch": 2.48, "learning_rate": 1.0666525868516925e-06, "loss": 3.0765, "step": 1098 }, { "epoch": 2.49, "learning_rate": 1.0637268668375135e-06, "loss": 2.7057, "step": 1100 }, { "epoch": 2.49, "learning_rate": 1.0608005990036287e-06, "loss": 3.059, "step": 1102 }, { "epoch": 2.5, "learning_rate": 1.0578738085053182e-06, "loss": 3.1274, "step": 1104 }, { "epoch": 2.5, "learning_rate": 1.0549465205023552e-06, "loss": 2.9918, "step": 1106 }, { "epoch": 2.51, "learning_rate": 1.0520187601587898e-06, "loss": 3.0493, "step": 1108 }, { "epoch": 2.51, "learning_rate": 1.0490905526427316e-06, "loss": 2.7862, "step": 1110 }, { "epoch": 2.51, "learning_rate": 1.0461619231261356e-06, "loss": 2.5813, "step": 1112 }, { "epoch": 2.52, "learning_rate": 1.0432328967845832e-06, "loss": 3.2164, "step": 1114 }, { "epoch": 2.52, "learning_rate": 1.0403034987970677e-06, "loss": 2.622, "step": 1116 }, { "epoch": 2.53, "learning_rate": 1.0373737543457778e-06, "loss": 2.7361, "step": 1118 }, { "epoch": 2.53, "learning_rate": 1.0344436886158792e-06, "loss": 2.6086, "step": 1120 }, { "epoch": 2.54, "learning_rate": 1.0315133267953002e-06, "loss": 2.7857, "step": 1122 }, { "epoch": 2.54, "learning_rate": 1.0285826940745142e-06, "loss": 2.6796, "step": 1124 }, { "epoch": 2.55, "learning_rate": 1.0256518156463238e-06, "loss": 2.7021, "step": 1126 }, { "epoch": 2.55, "learning_rate": 1.0227207167056432e-06, "loss": 2.7122, "step": 1128 }, { "epoch": 2.56, "learning_rate": 1.0197894224492825e-06, "loss": 3.2042, "step": 1130 }, { "epoch": 2.56, "learning_rate": 1.0168579580757304e-06, "loss": 2.7248, "step": 1132 }, { "epoch": 2.56, "learning_rate": 1.013926348784939e-06, "loss": 2.5811, "step": 1134 }, { "epoch": 2.57, "learning_rate": 1.0109946197781052e-06, "loss": 3.098, "step": 1136 }, { "epoch": 2.57, "learning_rate": 1.0080627962574553e-06, "loss": 2.7278, "step": 1138 }, { "epoch": 2.58, "learning_rate": 1.0051309034260282e-06, "loss": 3.1614, "step": 1140 }, { "epoch": 2.58, "learning_rate": 1.0021989664874581e-06, "loss": 2.656, "step": 1142 }, { "epoch": 2.59, "learning_rate": 9.992670106457598e-07, "loss": 2.7654, "step": 1144 }, { "epoch": 2.59, "learning_rate": 9.963350611051087e-07, "loss": 2.9324, "step": 1146 }, { "epoch": 2.6, "learning_rate": 9.934031430696267e-07, "loss": 2.7284, "step": 1148 }, { "epoch": 2.6, "learning_rate": 9.904712817431664e-07, "loss": 3.0669, "step": 1150 }, { "epoch": 2.6, "learning_rate": 9.8753950232909e-07, "loss": 2.7457, "step": 1152 }, { "epoch": 2.61, "learning_rate": 9.846078300300585e-07, "loss": 2.7766, "step": 1154 }, { "epoch": 2.61, "learning_rate": 9.8167629004781e-07, "loss": 2.5405, "step": 1156 }, { "epoch": 2.62, "learning_rate": 9.78744907582946e-07, "loss": 2.5982, "step": 1158 }, { "epoch": 2.62, "learning_rate": 9.75813707834714e-07, "loss": 3.0882, "step": 1160 }, { "epoch": 2.63, "learning_rate": 9.728827160007907e-07, "loss": 2.5018, "step": 1162 }, { "epoch": 2.63, "learning_rate": 9.69951957277065e-07, "loss": 2.7916, "step": 1164 }, { "epoch": 2.64, "learning_rate": 9.670214568574226e-07, "loss": 2.6006, "step": 1166 }, { "epoch": 2.64, "learning_rate": 9.640912399335289e-07, "loss": 3.1336, "step": 1168 }, { "epoch": 2.65, "learning_rate": 9.611613316946109e-07, "loss": 3.1566, "step": 1170 }, { "epoch": 2.65, "learning_rate": 9.582317573272434e-07, "loss": 3.0712, "step": 1172 }, { "epoch": 2.65, "learning_rate": 9.553025420151306e-07, "loss": 2.6743, "step": 1174 }, { "epoch": 2.66, "learning_rate": 9.523737109388906e-07, "loss": 2.4703, "step": 1176 }, { "epoch": 2.66, "learning_rate": 9.494452892758374e-07, "loss": 3.336, "step": 1178 }, { "epoch": 2.67, "learning_rate": 9.465173021997665e-07, "loss": 3.0323, "step": 1180 }, { "epoch": 2.67, "learning_rate": 9.435897748807373e-07, "loss": 2.8528, "step": 1182 }, { "epoch": 2.68, "learning_rate": 9.406627324848563e-07, "loss": 2.7218, "step": 1184 }, { "epoch": 2.68, "learning_rate": 9.37736200174063e-07, "loss": 2.7988, "step": 1186 }, { "epoch": 2.69, "learning_rate": 9.348102031059101e-07, "loss": 3.2579, "step": 1188 }, { "epoch": 2.69, "learning_rate": 9.318847664333507e-07, "loss": 2.6088, "step": 1190 }, { "epoch": 2.7, "learning_rate": 9.289599153045193e-07, "loss": 2.8507, "step": 1192 }, { "epoch": 2.7, "learning_rate": 9.260356748625181e-07, "loss": 2.7802, "step": 1194 }, { "epoch": 2.7, "learning_rate": 9.231120702451984e-07, "loss": 2.7047, "step": 1196 }, { "epoch": 2.71, "learning_rate": 9.201891265849467e-07, "loss": 3.073, "step": 1198 }, { "epoch": 2.71, "learning_rate": 9.172668690084668e-07, "loss": 2.9916, "step": 1200 }, { "epoch": 2.72, "learning_rate": 9.143453226365655e-07, "loss": 2.8411, "step": 1202 }, { "epoch": 2.72, "learning_rate": 9.114245125839355e-07, "loss": 3.1306, "step": 1204 }, { "epoch": 2.73, "learning_rate": 9.085044639589393e-07, "loss": 3.1617, "step": 1206 }, { "epoch": 2.73, "learning_rate": 9.055852018633949e-07, "loss": 3.1174, "step": 1208 }, { "epoch": 2.74, "learning_rate": 9.026667513923581e-07, "loss": 2.7785, "step": 1210 }, { "epoch": 2.74, "learning_rate": 8.997491376339081e-07, "loss": 3.1294, "step": 1212 }, { "epoch": 2.75, "learning_rate": 8.968323856689312e-07, "loss": 2.9793, "step": 1214 }, { "epoch": 2.75, "learning_rate": 8.939165205709061e-07, "loss": 2.7154, "step": 1216 }, { "epoch": 2.75, "learning_rate": 8.910015674056863e-07, "loss": 2.8357, "step": 1218 }, { "epoch": 2.76, "learning_rate": 8.880875512312873e-07, "loss": 3.0594, "step": 1220 }, { "epoch": 2.76, "learning_rate": 8.851744970976696e-07, "loss": 2.7825, "step": 1222 }, { "epoch": 2.77, "learning_rate": 8.822624300465227e-07, "loss": 2.7974, "step": 1224 }, { "epoch": 2.77, "learning_rate": 8.793513751110523e-07, "loss": 3.0372, "step": 1226 }, { "epoch": 2.78, "learning_rate": 8.764413573157621e-07, "loss": 2.834, "step": 1228 }, { "epoch": 2.78, "learning_rate": 8.735324016762413e-07, "loss": 3.1707, "step": 1230 }, { "epoch": 2.79, "learning_rate": 8.706245331989475e-07, "loss": 2.6728, "step": 1232 }, { "epoch": 2.79, "learning_rate": 8.677177768809936e-07, "loss": 2.8578, "step": 1234 }, { "epoch": 2.79, "learning_rate": 8.648121577099313e-07, "loss": 3.0628, "step": 1236 }, { "epoch": 2.8, "learning_rate": 8.619077006635366e-07, "loss": 2.9427, "step": 1238 }, { "epoch": 2.8, "learning_rate": 8.590044307095969e-07, "loss": 3.085, "step": 1240 }, { "epoch": 2.81, "learning_rate": 8.561023728056933e-07, "loss": 2.8008, "step": 1242 }, { "epoch": 2.81, "learning_rate": 8.53201551898989e-07, "loss": 3.142, "step": 1244 }, { "epoch": 2.82, "learning_rate": 8.503019929260121e-07, "loss": 2.9355, "step": 1246 }, { "epoch": 2.82, "learning_rate": 8.474037208124438e-07, "loss": 2.9118, "step": 1248 }, { "epoch": 2.83, "learning_rate": 8.445067604729027e-07, "loss": 3.047, "step": 1250 }, { "epoch": 2.83, "learning_rate": 8.416111368107308e-07, "loss": 3.1393, "step": 1252 }, { "epoch": 2.84, "learning_rate": 8.387168747177793e-07, "loss": 2.3831, "step": 1254 }, { "epoch": 2.84, "learning_rate": 8.358239990741954e-07, "loss": 2.4256, "step": 1256 }, { "epoch": 2.84, "learning_rate": 8.329325347482075e-07, "loss": 2.5293, "step": 1258 }, { "epoch": 2.85, "learning_rate": 8.300425065959115e-07, "loss": 2.976, "step": 1260 }, { "epoch": 2.85, "learning_rate": 8.271539394610584e-07, "loss": 2.818, "step": 1262 }, { "epoch": 2.86, "learning_rate": 8.242668581748387e-07, "loss": 2.9666, "step": 1264 }, { "epoch": 2.86, "learning_rate": 8.213812875556705e-07, "loss": 2.8793, "step": 1266 }, { "epoch": 2.87, "learning_rate": 8.184972524089854e-07, "loss": 2.8458, "step": 1268 }, { "epoch": 2.87, "learning_rate": 8.156147775270161e-07, "loss": 2.797, "step": 1270 }, { "epoch": 2.88, "learning_rate": 8.127338876885817e-07, "loss": 2.7497, "step": 1272 }, { "epoch": 2.88, "learning_rate": 8.098546076588767e-07, "loss": 2.8402, "step": 1274 }, { "epoch": 2.89, "learning_rate": 8.069769621892566e-07, "loss": 2.9016, "step": 1276 }, { "epoch": 2.89, "learning_rate": 8.041009760170255e-07, "loss": 2.8648, "step": 1278 }, { "epoch": 2.89, "learning_rate": 8.012266738652238e-07, "loss": 2.9125, "step": 1280 }, { "epoch": 2.9, "learning_rate": 7.983540804424153e-07, "loss": 2.507, "step": 1282 }, { "epoch": 2.9, "learning_rate": 7.954832204424751e-07, "loss": 2.6752, "step": 1284 }, { "epoch": 2.91, "learning_rate": 7.926141185443769e-07, "loss": 2.6717, "step": 1286 }, { "epoch": 2.91, "learning_rate": 7.897467994119815e-07, "loss": 3.0396, "step": 1288 }, { "epoch": 2.92, "learning_rate": 7.868812876938237e-07, "loss": 2.8133, "step": 1290 }, { "epoch": 2.92, "learning_rate": 7.840176080229018e-07, "loss": 2.6828, "step": 1292 }, { "epoch": 2.93, "learning_rate": 7.811557850164652e-07, "loss": 2.7036, "step": 1294 }, { "epoch": 2.93, "learning_rate": 7.782958432758019e-07, "loss": 3.1691, "step": 1296 }, { "epoch": 2.93, "learning_rate": 7.754378073860288e-07, "loss": 2.3585, "step": 1298 }, { "epoch": 2.94, "learning_rate": 7.725817019158784e-07, "loss": 2.777, "step": 1300 }, { "epoch": 2.94, "learning_rate": 7.697275514174897e-07, "loss": 2.7481, "step": 1302 }, { "epoch": 2.95, "learning_rate": 7.668753804261952e-07, "loss": 2.7663, "step": 1304 }, { "epoch": 2.95, "learning_rate": 7.640252134603114e-07, "loss": 2.7147, "step": 1306 }, { "epoch": 2.96, "learning_rate": 7.611770750209266e-07, "loss": 2.5766, "step": 1308 }, { "epoch": 2.96, "learning_rate": 7.583309895916922e-07, "loss": 3.0408, "step": 1310 }, { "epoch": 2.97, "learning_rate": 7.554869816386106e-07, "loss": 2.5816, "step": 1312 }, { "epoch": 2.97, "learning_rate": 7.526450756098255e-07, "loss": 2.8271, "step": 1314 }, { "epoch": 2.98, "learning_rate": 7.498052959354119e-07, "loss": 2.6384, "step": 1316 }, { "epoch": 2.98, "learning_rate": 7.469676670271652e-07, "loss": 3.4966, "step": 1318 }, { "epoch": 2.98, "learning_rate": 7.44132213278393e-07, "loss": 2.7207, "step": 1320 }, { "epoch": 2.99, "learning_rate": 7.412989590637036e-07, "loss": 2.9802, "step": 1322 }, { "epoch": 2.99, "learning_rate": 7.384679287387978e-07, "loss": 2.5428, "step": 1324 }, { "epoch": 3.0, "learning_rate": 7.356391466402586e-07, "loss": 2.9594, "step": 1326 }, { "epoch": 3.0, "learning_rate": 7.328126370853428e-07, "loss": 3.1476, "step": 1328 }, { "epoch": 3.01, "learning_rate": 7.299884243717717e-07, "loss": 2.6429, "step": 1330 }, { "epoch": 3.01, "learning_rate": 7.271665327775213e-07, "loss": 2.862, "step": 1332 }, { "epoch": 3.02, "learning_rate": 7.243469865606155e-07, "loss": 2.7028, "step": 1334 }, { "epoch": 3.02, "learning_rate": 7.215298099589153e-07, "loss": 2.7126, "step": 1336 }, { "epoch": 3.03, "learning_rate": 7.187150271899127e-07, "loss": 2.8973, "step": 1338 }, { "epoch": 3.03, "learning_rate": 7.159026624505206e-07, "loss": 2.995, "step": 1340 }, { "epoch": 3.03, "learning_rate": 7.130927399168665e-07, "loss": 2.5874, "step": 1342 }, { "epoch": 3.04, "learning_rate": 7.102852837440824e-07, "loss": 3.0309, "step": 1344 }, { "epoch": 3.04, "learning_rate": 7.074803180661e-07, "loss": 3.0624, "step": 1346 }, { "epoch": 3.05, "learning_rate": 7.046778669954415e-07, "loss": 2.9275, "step": 1348 }, { "epoch": 3.05, "learning_rate": 7.018779546230113e-07, "loss": 3.1457, "step": 1350 }, { "epoch": 3.06, "learning_rate": 6.990806050178923e-07, "loss": 2.9151, "step": 1352 }, { "epoch": 3.06, "learning_rate": 6.96285842227135e-07, "loss": 3.1813, "step": 1354 }, { "epoch": 3.07, "learning_rate": 6.934936902755539e-07, "loss": 3.1868, "step": 1356 }, { "epoch": 3.07, "learning_rate": 6.907041731655195e-07, "loss": 2.655, "step": 1358 }, { "epoch": 3.08, "learning_rate": 6.879173148767517e-07, "loss": 2.8534, "step": 1360 }, { "epoch": 3.08, "learning_rate": 6.851331393661147e-07, "loss": 2.775, "step": 1362 }, { "epoch": 3.08, "learning_rate": 6.823516705674106e-07, "loss": 3.2059, "step": 1364 }, { "epoch": 3.09, "learning_rate": 6.795729323911736e-07, "loss": 2.8204, "step": 1366 }, { "epoch": 3.09, "learning_rate": 6.767969487244635e-07, "loss": 2.8428, "step": 1368 }, { "epoch": 3.1, "learning_rate": 6.740237434306633e-07, "loss": 2.9497, "step": 1370 }, { "epoch": 3.1, "learning_rate": 6.712533403492699e-07, "loss": 3.1668, "step": 1372 }, { "epoch": 3.11, "learning_rate": 6.684857632956928e-07, "loss": 2.5495, "step": 1374 }, { "epoch": 3.11, "learning_rate": 6.657210360610473e-07, "loss": 2.8043, "step": 1376 }, { "epoch": 3.12, "learning_rate": 6.629591824119509e-07, "loss": 2.6969, "step": 1378 }, { "epoch": 3.12, "learning_rate": 6.602002260903183e-07, "loss": 2.678, "step": 1380 }, { "epoch": 3.12, "learning_rate": 6.574441908131581e-07, "loss": 2.8735, "step": 1382 }, { "epoch": 3.13, "learning_rate": 6.546911002723687e-07, "loss": 2.744, "step": 1384 }, { "epoch": 3.13, "learning_rate": 6.519409781345338e-07, "loss": 2.9366, "step": 1386 }, { "epoch": 3.14, "learning_rate": 6.491938480407199e-07, "loss": 2.7117, "step": 1388 }, { "epoch": 3.14, "learning_rate": 6.464497336062731e-07, "loss": 2.4606, "step": 1390 }, { "epoch": 3.15, "learning_rate": 6.437086584206153e-07, "loss": 2.788, "step": 1392 }, { "epoch": 3.15, "learning_rate": 6.409706460470421e-07, "loss": 2.9095, "step": 1394 }, { "epoch": 3.16, "learning_rate": 6.382357200225203e-07, "loss": 2.9612, "step": 1396 }, { "epoch": 3.16, "learning_rate": 6.355039038574846e-07, "loss": 2.6613, "step": 1398 }, { "epoch": 3.17, "learning_rate": 6.32775221035637e-07, "loss": 2.8352, "step": 1400 }, { "epoch": 3.17, "learning_rate": 6.300496950137437e-07, "loss": 2.6352, "step": 1402 }, { "epoch": 3.17, "learning_rate": 6.273273492214338e-07, "loss": 2.78, "step": 1404 }, { "epoch": 3.18, "learning_rate": 6.246082070609985e-07, "loss": 3.015, "step": 1406 }, { "epoch": 3.18, "learning_rate": 6.218922919071885e-07, "loss": 2.6095, "step": 1408 }, { "epoch": 3.19, "learning_rate": 6.191796271070149e-07, "loss": 2.7799, "step": 1410 }, { "epoch": 3.19, "learning_rate": 6.164702359795462e-07, "loss": 3.1965, "step": 1412 }, { "epoch": 3.2, "learning_rate": 6.137641418157117e-07, "loss": 2.5616, "step": 1414 }, { "epoch": 3.2, "learning_rate": 6.110613678780961e-07, "loss": 2.6017, "step": 1416 }, { "epoch": 3.21, "learning_rate": 6.083619374007438e-07, "loss": 2.969, "step": 1418 }, { "epoch": 3.21, "learning_rate": 6.056658735889566e-07, "loss": 2.8425, "step": 1420 }, { "epoch": 3.22, "learning_rate": 6.029731996190963e-07, "loss": 2.7602, "step": 1422 }, { "epoch": 3.22, "learning_rate": 6.002839386383833e-07, "loss": 2.8186, "step": 1424 }, { "epoch": 3.22, "learning_rate": 5.975981137646995e-07, "loss": 2.8212, "step": 1426 }, { "epoch": 3.23, "learning_rate": 5.94915748086388e-07, "loss": 2.3831, "step": 1428 }, { "epoch": 3.23, "learning_rate": 5.922368646620559e-07, "loss": 2.8483, "step": 1430 }, { "epoch": 3.24, "learning_rate": 5.895614865203757e-07, "loss": 2.7061, "step": 1432 }, { "epoch": 3.24, "learning_rate": 5.868896366598868e-07, "loss": 2.4338, "step": 1434 }, { "epoch": 3.25, "learning_rate": 5.842213380487982e-07, "loss": 2.6146, "step": 1436 }, { "epoch": 3.25, "learning_rate": 5.815566136247911e-07, "loss": 2.5909, "step": 1438 }, { "epoch": 3.26, "learning_rate": 5.78895486294822e-07, "loss": 2.7424, "step": 1440 }, { "epoch": 3.26, "learning_rate": 5.762379789349253e-07, "loss": 2.8332, "step": 1442 }, { "epoch": 3.27, "learning_rate": 5.735841143900162e-07, "loss": 3.0104, "step": 1444 }, { "epoch": 3.27, "learning_rate": 5.709339154736955e-07, "loss": 2.8087, "step": 1446 }, { "epoch": 3.27, "learning_rate": 5.68287404968053e-07, "loss": 2.3975, "step": 1448 }, { "epoch": 3.28, "learning_rate": 5.656446056234712e-07, "loss": 2.6708, "step": 1450 }, { "epoch": 3.28, "learning_rate": 5.630055401584309e-07, "loss": 3.0557, "step": 1452 }, { "epoch": 3.29, "learning_rate": 5.603702312593134e-07, "loss": 2.7384, "step": 1454 }, { "epoch": 3.29, "learning_rate": 5.577387015802086e-07, "loss": 2.8848, "step": 1456 }, { "epoch": 3.3, "learning_rate": 5.551109737427186e-07, "loss": 2.4909, "step": 1458 }, { "epoch": 3.3, "learning_rate": 5.524870703357637e-07, "loss": 2.788, "step": 1460 }, { "epoch": 3.31, "learning_rate": 5.498670139153867e-07, "loss": 2.8365, "step": 1462 }, { "epoch": 3.31, "learning_rate": 5.472508270045614e-07, "loss": 2.7904, "step": 1464 }, { "epoch": 3.31, "learning_rate": 5.44638532092998e-07, "loss": 2.7949, "step": 1466 }, { "epoch": 3.32, "learning_rate": 5.420301516369489e-07, "loss": 2.6716, "step": 1468 }, { "epoch": 3.32, "learning_rate": 5.394257080590174e-07, "loss": 2.8075, "step": 1470 }, { "epoch": 3.33, "learning_rate": 5.368252237479625e-07, "loss": 2.9066, "step": 1472 }, { "epoch": 3.33, "learning_rate": 5.342287210585088e-07, "loss": 2.632, "step": 1474 }, { "epoch": 3.34, "learning_rate": 5.316362223111534e-07, "loss": 2.9816, "step": 1476 }, { "epoch": 3.34, "learning_rate": 5.290477497919747e-07, "loss": 2.5143, "step": 1478 }, { "epoch": 3.35, "learning_rate": 5.26463325752438e-07, "loss": 2.8944, "step": 1480 }, { "epoch": 3.35, "learning_rate": 5.238829724092085e-07, "loss": 3.1665, "step": 1482 }, { "epoch": 3.36, "learning_rate": 5.213067119439573e-07, "loss": 3.0553, "step": 1484 }, { "epoch": 3.36, "learning_rate": 5.187345665031719e-07, "loss": 2.9319, "step": 1486 }, { "epoch": 3.36, "learning_rate": 5.161665581979655e-07, "loss": 2.7709, "step": 1488 }, { "epoch": 3.37, "learning_rate": 5.136027091038864e-07, "loss": 2.9586, "step": 1490 }, { "epoch": 3.37, "learning_rate": 5.110430412607292e-07, "loss": 3.112, "step": 1492 }, { "epoch": 3.38, "learning_rate": 5.084875766723451e-07, "loss": 2.7321, "step": 1494 }, { "epoch": 3.38, "learning_rate": 5.059363373064528e-07, "loss": 2.7936, "step": 1496 }, { "epoch": 3.39, "learning_rate": 5.033893450944482e-07, "loss": 3.076, "step": 1498 }, { "epoch": 3.39, "learning_rate": 5.008466219312185e-07, "loss": 3.0745, "step": 1500 }, { "epoch": 3.4, "learning_rate": 4.983081896749517e-07, "loss": 2.7958, "step": 1502 }, { "epoch": 3.4, "learning_rate": 4.957740701469501e-07, "loss": 2.7821, "step": 1504 }, { "epoch": 3.41, "learning_rate": 4.932442851314422e-07, "loss": 2.9441, "step": 1506 }, { "epoch": 3.41, "learning_rate": 4.907188563753944e-07, "loss": 2.9545, "step": 1508 }, { "epoch": 3.41, "learning_rate": 4.881978055883266e-07, "loss": 2.7054, "step": 1510 }, { "epoch": 3.42, "learning_rate": 4.856811544421229e-07, "loss": 2.405, "step": 1512 }, { "epoch": 3.42, "learning_rate": 4.831689245708475e-07, "loss": 2.6209, "step": 1514 }, { "epoch": 3.43, "learning_rate": 4.806611375705564e-07, "loss": 2.9136, "step": 1516 }, { "epoch": 3.43, "learning_rate": 4.781578149991138e-07, "loss": 3.0014, "step": 1518 }, { "epoch": 3.44, "learning_rate": 4.756589783760063e-07, "loss": 2.5568, "step": 1520 }, { "epoch": 3.44, "learning_rate": 4.7316464918215704e-07, "loss": 2.8057, "step": 1522 }, { "epoch": 3.45, "learning_rate": 4.706748488597424e-07, "loss": 2.771, "step": 1524 }, { "epoch": 3.45, "learning_rate": 4.6818959881200537e-07, "loss": 2.8506, "step": 1526 }, { "epoch": 3.46, "learning_rate": 4.6570892040307477e-07, "loss": 2.4494, "step": 1528 }, { "epoch": 3.46, "learning_rate": 4.632328349577791e-07, "loss": 2.6936, "step": 1530 }, { "epoch": 3.46, "learning_rate": 4.607613637614646e-07, "loss": 2.4716, "step": 1532 }, { "epoch": 3.47, "learning_rate": 4.582945280598105e-07, "loss": 2.7458, "step": 1534 }, { "epoch": 3.47, "learning_rate": 4.5583234905864896e-07, "loss": 2.7454, "step": 1536 }, { "epoch": 3.48, "learning_rate": 4.533748479237807e-07, "loss": 2.8297, "step": 1538 }, { "epoch": 3.48, "learning_rate": 4.509220457807941e-07, "loss": 3.0781, "step": 1540 }, { "epoch": 3.49, "learning_rate": 4.4847396371488333e-07, "loss": 2.9005, "step": 1542 }, { "epoch": 3.49, "learning_rate": 4.4603062277066627e-07, "loss": 2.8911, "step": 1544 }, { "epoch": 3.5, "learning_rate": 4.4359204395200523e-07, "loss": 2.5086, "step": 1546 }, { "epoch": 3.5, "learning_rate": 4.4115824822182513e-07, "loss": 2.5064, "step": 1548 }, { "epoch": 3.5, "learning_rate": 4.3872925650193416e-07, "loss": 2.7979, "step": 1550 }, { "epoch": 3.51, "learning_rate": 4.363050896728425e-07, "loss": 2.5966, "step": 1552 }, { "epoch": 3.51, "learning_rate": 4.338857685735846e-07, "loss": 2.8215, "step": 1554 }, { "epoch": 3.52, "learning_rate": 4.3147131400153915e-07, "loss": 2.943, "step": 1556 }, { "epoch": 3.52, "learning_rate": 4.2906174671224993e-07, "loss": 3.0082, "step": 1558 }, { "epoch": 3.53, "learning_rate": 4.2665708741924876e-07, "loss": 2.6888, "step": 1560 }, { "epoch": 3.53, "learning_rate": 4.2425735679387507e-07, "loss": 2.7884, "step": 1562 }, { "epoch": 3.54, "learning_rate": 4.218625754651007e-07, "loss": 2.8401, "step": 1564 }, { "epoch": 3.54, "learning_rate": 4.1947276401935137e-07, "loss": 2.7452, "step": 1566 }, { "epoch": 3.55, "learning_rate": 4.1708794300033e-07, "loss": 2.8595, "step": 1568 }, { "epoch": 3.55, "learning_rate": 4.1470813290883913e-07, "loss": 3.0268, "step": 1570 }, { "epoch": 3.55, "learning_rate": 4.123333542026061e-07, "loss": 2.9248, "step": 1572 }, { "epoch": 3.56, "learning_rate": 4.099636272961069e-07, "loss": 2.8476, "step": 1574 }, { "epoch": 3.56, "learning_rate": 4.075989725603898e-07, "loss": 2.7816, "step": 1576 }, { "epoch": 3.57, "learning_rate": 4.0523941032290153e-07, "loss": 2.9042, "step": 1578 }, { "epoch": 3.57, "learning_rate": 4.028849608673107e-07, "loss": 2.7047, "step": 1580 }, { "epoch": 3.58, "learning_rate": 4.0053564443333553e-07, "loss": 2.5792, "step": 1582 }, { "epoch": 3.58, "learning_rate": 3.9819148121656856e-07, "loss": 2.9062, "step": 1584 }, { "epoch": 3.59, "learning_rate": 3.9585249136830366e-07, "loss": 2.8347, "step": 1586 }, { "epoch": 3.59, "learning_rate": 3.935186949953617e-07, "loss": 2.7122, "step": 1588 }, { "epoch": 3.6, "learning_rate": 3.9119011215991927e-07, "loss": 3.1072, "step": 1590 }, { "epoch": 3.6, "learning_rate": 3.888667628793353e-07, "loss": 2.5003, "step": 1592 }, { "epoch": 3.6, "learning_rate": 3.86548667125979e-07, "loss": 2.7578, "step": 1594 }, { "epoch": 3.61, "learning_rate": 3.84235844827059e-07, "loss": 2.7218, "step": 1596 }, { "epoch": 3.61, "learning_rate": 3.8192831586444975e-07, "loss": 2.766, "step": 1598 }, { "epoch": 3.62, "learning_rate": 3.7962610007452376e-07, "loss": 2.8965, "step": 1600 }, { "epoch": 3.62, "learning_rate": 3.773292172479791e-07, "loss": 2.7869, "step": 1602 }, { "epoch": 3.63, "learning_rate": 3.7503768712966997e-07, "loss": 2.9772, "step": 1604 }, { "epoch": 3.63, "learning_rate": 3.727515294184356e-07, "loss": 2.7947, "step": 1606 }, { "epoch": 3.64, "learning_rate": 3.704707637669332e-07, "loss": 2.698, "step": 1608 }, { "epoch": 3.64, "learning_rate": 3.6819540978146757e-07, "loss": 2.5499, "step": 1610 }, { "epoch": 3.64, "learning_rate": 3.6592548702182257e-07, "loss": 2.6437, "step": 1612 }, { "epoch": 3.65, "learning_rate": 3.6366101500109383e-07, "loss": 2.7488, "step": 1614 }, { "epoch": 3.65, "learning_rate": 3.614020131855192e-07, "loss": 2.453, "step": 1616 }, { "epoch": 3.66, "learning_rate": 3.591485009943137e-07, "loss": 2.9844, "step": 1618 }, { "epoch": 3.66, "learning_rate": 3.5690049779950125e-07, "loss": 2.6074, "step": 1620 }, { "epoch": 3.67, "learning_rate": 3.546580229257488e-07, "loss": 2.8769, "step": 1622 }, { "epoch": 3.67, "learning_rate": 3.524210956501984e-07, "loss": 2.9232, "step": 1624 }, { "epoch": 3.68, "learning_rate": 3.5018973520230443e-07, "loss": 2.6338, "step": 1626 }, { "epoch": 3.68, "learning_rate": 3.479639607636661e-07, "loss": 2.59, "step": 1628 }, { "epoch": 3.69, "learning_rate": 3.4574379146786327e-07, "loss": 2.3974, "step": 1630 }, { "epoch": 3.69, "learning_rate": 3.4352924640029234e-07, "loss": 2.8362, "step": 1632 }, { "epoch": 3.69, "learning_rate": 3.413203445980006e-07, "loss": 2.8762, "step": 1634 }, { "epoch": 3.7, "learning_rate": 3.3911710504952497e-07, "loss": 2.9781, "step": 1636 }, { "epoch": 3.7, "learning_rate": 3.3691954669472713e-07, "loss": 2.994, "step": 1638 }, { "epoch": 3.71, "learning_rate": 3.347276884246313e-07, "loss": 2.7129, "step": 1640 }, { "epoch": 3.71, "learning_rate": 3.3254154908126073e-07, "loss": 2.9263, "step": 1642 }, { "epoch": 3.72, "learning_rate": 3.3036114745747803e-07, "loss": 2.6921, "step": 1644 }, { "epoch": 3.72, "learning_rate": 3.281865022968212e-07, "loss": 2.7026, "step": 1646 }, { "epoch": 3.73, "learning_rate": 3.2601763229334423e-07, "loss": 2.6587, "step": 1648 }, { "epoch": 3.73, "learning_rate": 3.238545560914556e-07, "loss": 2.7986, "step": 1650 }, { "epoch": 3.74, "learning_rate": 3.2169729228575747e-07, "loss": 2.8521, "step": 1652 }, { "epoch": 3.74, "learning_rate": 3.1954585942088716e-07, "loss": 2.4757, "step": 1654 }, { "epoch": 3.74, "learning_rate": 3.174002759913572e-07, "loss": 2.8834, "step": 1656 }, { "epoch": 3.75, "learning_rate": 3.152605604413959e-07, "loss": 2.6921, "step": 1658 }, { "epoch": 3.75, "learning_rate": 3.131267311647887e-07, "loss": 2.9068, "step": 1660 }, { "epoch": 3.76, "learning_rate": 3.1099880650472123e-07, "loss": 2.913, "step": 1662 }, { "epoch": 3.76, "learning_rate": 3.088768047536203e-07, "loss": 2.7947, "step": 1664 }, { "epoch": 3.77, "learning_rate": 3.067607441529977e-07, "loss": 2.6862, "step": 1666 }, { "epoch": 3.77, "learning_rate": 3.0465064289329266e-07, "loss": 2.7645, "step": 1668 }, { "epoch": 3.78, "learning_rate": 3.025465191137152e-07, "loss": 2.861, "step": 1670 }, { "epoch": 3.78, "learning_rate": 3.004483909020915e-07, "loss": 3.0162, "step": 1672 }, { "epoch": 3.79, "learning_rate": 2.983562762947072e-07, "loss": 2.8758, "step": 1674 }, { "epoch": 3.79, "learning_rate": 2.9627019327615313e-07, "loss": 2.8295, "step": 1676 }, { "epoch": 3.79, "learning_rate": 2.9419015977916963e-07, "loss": 2.7618, "step": 1678 }, { "epoch": 3.8, "learning_rate": 2.921161936844938e-07, "loss": 3.2872, "step": 1680 }, { "epoch": 3.8, "learning_rate": 2.90048312820705e-07, "loss": 3.0227, "step": 1682 }, { "epoch": 3.81, "learning_rate": 2.879865349640713e-07, "loss": 2.5878, "step": 1684 }, { "epoch": 3.81, "learning_rate": 2.85930877838398e-07, "loss": 2.847, "step": 1686 }, { "epoch": 3.82, "learning_rate": 2.838813591148729e-07, "loss": 2.7505, "step": 1688 }, { "epoch": 3.82, "learning_rate": 2.8183799641191686e-07, "loss": 2.5317, "step": 1690 }, { "epoch": 3.83, "learning_rate": 2.7980080729503107e-07, "loss": 2.9387, "step": 1692 }, { "epoch": 3.83, "learning_rate": 2.777698092766467e-07, "loss": 2.7368, "step": 1694 }, { "epoch": 3.83, "learning_rate": 2.757450198159728e-07, "loss": 2.7084, "step": 1696 }, { "epoch": 3.84, "learning_rate": 2.737264563188485e-07, "loss": 2.8752, "step": 1698 }, { "epoch": 3.84, "learning_rate": 2.717141361375918e-07, "loss": 2.917, "step": 1700 }, { "epoch": 3.85, "learning_rate": 2.697080765708507e-07, "loss": 2.7381, "step": 1702 }, { "epoch": 3.85, "learning_rate": 2.677082948634555e-07, "loss": 2.734, "step": 1704 }, { "epoch": 3.86, "learning_rate": 2.65714808206268e-07, "loss": 2.8567, "step": 1706 }, { "epoch": 3.86, "learning_rate": 2.6372763373603715e-07, "loss": 2.8301, "step": 1708 }, { "epoch": 3.87, "learning_rate": 2.6174678853524914e-07, "loss": 2.7349, "step": 1710 }, { "epoch": 3.87, "learning_rate": 2.597722896319817e-07, "loss": 2.9651, "step": 1712 }, { "epoch": 3.88, "learning_rate": 2.578041539997571e-07, "loss": 2.4586, "step": 1714 }, { "epoch": 3.88, "learning_rate": 2.5584239855739676e-07, "loss": 2.9208, "step": 1716 }, { "epoch": 3.88, "learning_rate": 2.53887040168876e-07, "loss": 2.7206, "step": 1718 }, { "epoch": 3.89, "learning_rate": 2.5193809564317805e-07, "loss": 2.7308, "step": 1720 }, { "epoch": 3.89, "learning_rate": 2.4999558173415104e-07, "loss": 3.0907, "step": 1722 }, { "epoch": 3.9, "learning_rate": 2.4805951514036194e-07, "loss": 2.891, "step": 1724 }, { "epoch": 3.9, "learning_rate": 2.461299125049553e-07, "loss": 2.5363, "step": 1726 }, { "epoch": 3.91, "learning_rate": 2.442067904155086e-07, "loss": 2.8429, "step": 1728 }, { "epoch": 3.91, "learning_rate": 2.4229016540389066e-07, "loss": 2.7666, "step": 1730 }, { "epoch": 3.92, "learning_rate": 2.4038005394611793e-07, "loss": 2.8593, "step": 1732 }, { "epoch": 3.92, "learning_rate": 2.3847647246221494e-07, "loss": 2.5029, "step": 1734 }, { "epoch": 3.93, "learning_rate": 2.365794373160719e-07, "loss": 2.6644, "step": 1736 }, { "epoch": 3.93, "learning_rate": 2.346889648153041e-07, "loss": 2.6089, "step": 1738 }, { "epoch": 3.93, "learning_rate": 2.3280507121111237e-07, "loss": 2.9541, "step": 1740 }, { "epoch": 3.94, "learning_rate": 2.30927772698142e-07, "loss": 2.9293, "step": 1742 }, { "epoch": 3.94, "learning_rate": 2.290570854143452e-07, "loss": 2.9763, "step": 1744 }, { "epoch": 3.95, "learning_rate": 2.271930254408415e-07, "loss": 2.849, "step": 1746 }, { "epoch": 3.95, "learning_rate": 2.2533560880177958e-07, "loss": 2.9161, "step": 1748 }, { "epoch": 3.96, "learning_rate": 2.234848514641997e-07, "loss": 2.6359, "step": 1750 }, { "epoch": 3.96, "learning_rate": 2.2164076933789566e-07, "loss": 2.9435, "step": 1752 }, { "epoch": 3.97, "learning_rate": 2.1980337827527916e-07, "loss": 2.7513, "step": 1754 }, { "epoch": 3.97, "learning_rate": 2.179726940712433e-07, "loss": 2.9036, "step": 1756 }, { "epoch": 3.98, "learning_rate": 2.1614873246302645e-07, "loss": 2.8476, "step": 1758 }, { "epoch": 3.98, "learning_rate": 2.1433150913007613e-07, "loss": 2.9069, "step": 1760 }, { "epoch": 3.98, "learning_rate": 2.1252103969391643e-07, "loss": 2.7289, "step": 1762 }, { "epoch": 3.99, "learning_rate": 2.1071733971801186e-07, "loss": 2.7152, "step": 1764 }, { "epoch": 3.99, "learning_rate": 2.0892042470763406e-07, "loss": 2.374, "step": 1766 }, { "epoch": 4.0, "learning_rate": 2.0713031010972914e-07, "loss": 2.4215, "step": 1768 }, { "epoch": 4.0, "learning_rate": 2.053470113127833e-07, "loss": 2.8458, "step": 1770 }, { "epoch": 4.01, "learning_rate": 2.0357054364669258e-07, "loss": 2.8896, "step": 1772 }, { "epoch": 4.01, "learning_rate": 2.018009223826298e-07, "loss": 3.2975, "step": 1774 }, { "epoch": 4.02, "learning_rate": 2.0003816273291375e-07, "loss": 2.4431, "step": 1776 }, { "epoch": 4.02, "learning_rate": 1.9828227985087743e-07, "loss": 2.8371, "step": 1778 }, { "epoch": 4.02, "learning_rate": 1.965332888307395e-07, "loss": 2.9554, "step": 1780 }, { "epoch": 4.03, "learning_rate": 1.9479120470747346e-07, "loss": 2.8779, "step": 1782 }, { "epoch": 4.03, "learning_rate": 1.930560424566783e-07, "loss": 2.8531, "step": 1784 }, { "epoch": 4.04, "learning_rate": 1.9132781699445045e-07, "loss": 2.3459, "step": 1786 }, { "epoch": 4.04, "learning_rate": 1.8960654317725432e-07, "loss": 2.713, "step": 1788 }, { "epoch": 4.05, "learning_rate": 1.8789223580179636e-07, "loss": 2.8662, "step": 1790 }, { "epoch": 4.05, "learning_rate": 1.861849096048964e-07, "loss": 2.5315, "step": 1792 }, { "epoch": 4.06, "learning_rate": 1.8448457926336193e-07, "loss": 2.9132, "step": 1794 }, { "epoch": 4.06, "learning_rate": 1.8279125939386042e-07, "loss": 3.0467, "step": 1796 }, { "epoch": 4.07, "learning_rate": 1.811049645527959e-07, "loss": 2.5794, "step": 1798 }, { "epoch": 4.07, "learning_rate": 1.7942570923618218e-07, "loss": 2.7728, "step": 1800 }, { "epoch": 4.07, "learning_rate": 1.777535078795187e-07, "loss": 2.3633, "step": 1802 }, { "epoch": 4.08, "learning_rate": 1.760883748576667e-07, "loss": 2.7745, "step": 1804 }, { "epoch": 4.08, "learning_rate": 1.7443032448472484e-07, "loss": 2.8177, "step": 1806 }, { "epoch": 4.09, "learning_rate": 1.7277937101390715e-07, "loss": 2.5525, "step": 1808 }, { "epoch": 4.09, "learning_rate": 1.711355286374201e-07, "loss": 3.2756, "step": 1810 }, { "epoch": 4.1, "learning_rate": 1.694988114863406e-07, "loss": 2.9206, "step": 1812 }, { "epoch": 4.1, "learning_rate": 1.6786923363049398e-07, "loss": 2.5144, "step": 1814 }, { "epoch": 4.11, "learning_rate": 1.66246809078334e-07, "loss": 2.6694, "step": 1816 }, { "epoch": 4.11, "learning_rate": 1.646315517768221e-07, "loss": 3.1745, "step": 1818 }, { "epoch": 4.12, "learning_rate": 1.630234756113068e-07, "loss": 2.9225, "step": 1820 }, { "epoch": 4.12, "learning_rate": 1.6142259440540594e-07, "loss": 3.0162, "step": 1822 }, { "epoch": 4.12, "learning_rate": 1.5982892192088538e-07, "loss": 2.8536, "step": 1824 }, { "epoch": 4.13, "learning_rate": 1.5824247185754337e-07, "loss": 2.4751, "step": 1826 }, { "epoch": 4.13, "learning_rate": 1.56663257853091e-07, "loss": 2.7807, "step": 1828 }, { "epoch": 4.14, "learning_rate": 1.5509129348303597e-07, "loss": 2.599, "step": 1830 }, { "epoch": 4.14, "learning_rate": 1.5352659226056464e-07, "loss": 2.7341, "step": 1832 }, { "epoch": 4.15, "learning_rate": 1.519691676364273e-07, "loss": 3.2655, "step": 1834 }, { "epoch": 4.15, "learning_rate": 1.5041903299882197e-07, "loss": 2.5942, "step": 1836 }, { "epoch": 4.16, "learning_rate": 1.4887620167327875e-07, "loss": 2.7099, "step": 1838 }, { "epoch": 4.16, "learning_rate": 1.4734068692254654e-07, "loss": 3.0175, "step": 1840 }, { "epoch": 4.17, "learning_rate": 1.458125019464772e-07, "loss": 2.7466, "step": 1842 }, { "epoch": 4.17, "learning_rate": 1.4429165988191404e-07, "loss": 2.6732, "step": 1844 }, { "epoch": 4.17, "learning_rate": 1.427781738025775e-07, "loss": 2.6375, "step": 1846 }, { "epoch": 4.18, "learning_rate": 1.4127205671895382e-07, "loss": 2.7321, "step": 1848 }, { "epoch": 4.18, "learning_rate": 1.3977332157818166e-07, "loss": 2.7113, "step": 1850 }, { "epoch": 4.19, "learning_rate": 1.3828198126394264e-07, "loss": 2.9913, "step": 1852 }, { "epoch": 4.19, "learning_rate": 1.3679804859634936e-07, "loss": 3.2291, "step": 1854 }, { "epoch": 4.2, "learning_rate": 1.3532153633183573e-07, "loss": 2.7025, "step": 1856 }, { "epoch": 4.2, "learning_rate": 1.3385245716304695e-07, "loss": 2.8242, "step": 1858 }, { "epoch": 4.21, "learning_rate": 1.3239082371873046e-07, "loss": 2.714, "step": 1860 }, { "epoch": 4.21, "learning_rate": 1.3093664856362784e-07, "loss": 2.6625, "step": 1862 }, { "epoch": 4.21, "learning_rate": 1.2948994419836623e-07, "loss": 2.8933, "step": 1864 }, { "epoch": 4.22, "learning_rate": 1.2805072305935137e-07, "loss": 2.7814, "step": 1866 }, { "epoch": 4.22, "learning_rate": 1.266189975186599e-07, "loss": 2.8734, "step": 1868 }, { "epoch": 4.23, "learning_rate": 1.25194779883934e-07, "loss": 2.5842, "step": 1870 }, { "epoch": 4.23, "learning_rate": 1.237780823982749e-07, "loss": 3.2454, "step": 1872 }, { "epoch": 4.24, "learning_rate": 1.22368917240138e-07, "loss": 2.915, "step": 1874 }, { "epoch": 4.24, "learning_rate": 1.2096729652322802e-07, "loss": 2.9905, "step": 1876 }, { "epoch": 4.25, "learning_rate": 1.1957323229639449e-07, "loss": 2.8364, "step": 1878 }, { "epoch": 4.25, "learning_rate": 1.1818673654352906e-07, "loss": 2.4591, "step": 1880 }, { "epoch": 4.26, "learning_rate": 1.1680782118346167e-07, "loss": 2.7887, "step": 1882 }, { "epoch": 4.26, "learning_rate": 1.1543649806985889e-07, "loss": 2.6807, "step": 1884 }, { "epoch": 4.26, "learning_rate": 1.1407277899112055e-07, "loss": 2.4981, "step": 1886 }, { "epoch": 4.27, "learning_rate": 1.1271667567028032e-07, "loss": 2.9639, "step": 1888 }, { "epoch": 4.27, "learning_rate": 1.1136819976490364e-07, "loss": 2.5958, "step": 1890 }, { "epoch": 4.28, "learning_rate": 1.1002736286698777e-07, "loss": 2.5903, "step": 1892 }, { "epoch": 4.28, "learning_rate": 1.0869417650286272e-07, "loss": 2.7834, "step": 1894 }, { "epoch": 4.29, "learning_rate": 1.0736865213309088e-07, "loss": 2.7334, "step": 1896 }, { "epoch": 4.29, "learning_rate": 1.0605080115236997e-07, "loss": 2.9776, "step": 1898 }, { "epoch": 4.3, "learning_rate": 1.0474063488943407e-07, "loss": 2.6577, "step": 1900 }, { "epoch": 4.3, "learning_rate": 1.0343816460695709e-07, "loss": 2.7938, "step": 1902 }, { "epoch": 4.31, "learning_rate": 1.021434015014545e-07, "loss": 2.8686, "step": 1904 }, { "epoch": 4.31, "learning_rate": 1.0085635670318893e-07, "loss": 2.6591, "step": 1906 }, { "epoch": 4.31, "learning_rate": 9.957704127607325e-08, "loss": 2.7277, "step": 1908 }, { "epoch": 4.32, "learning_rate": 9.830546621757562e-08, "loss": 2.9303, "step": 1910 }, { "epoch": 4.32, "learning_rate": 9.704164245862578e-08, "loss": 2.8451, "step": 1912 }, { "epoch": 4.33, "learning_rate": 9.57855808635194e-08, "loss": 2.9587, "step": 1914 }, { "epoch": 4.33, "learning_rate": 9.453729222982654e-08, "loss": 2.6009, "step": 1916 }, { "epoch": 4.34, "learning_rate": 9.329678728829781e-08, "loss": 2.6641, "step": 1918 }, { "epoch": 4.34, "learning_rate": 9.206407670277239e-08, "loss": 3.0336, "step": 1920 }, { "epoch": 4.35, "learning_rate": 9.083917107008576e-08, "loss": 2.8155, "step": 1922 }, { "epoch": 4.35, "learning_rate": 8.96220809199798e-08, "loss": 2.4796, "step": 1924 }, { "epoch": 4.36, "learning_rate": 8.841281671501133e-08, "loss": 3.1721, "step": 1926 }, { "epoch": 4.36, "learning_rate": 8.721138885046264e-08, "loss": 2.4867, "step": 1928 }, { "epoch": 4.36, "learning_rate": 8.601780765425182e-08, "loss": 3.0135, "step": 1930 }, { "epoch": 4.37, "learning_rate": 8.483208338684366e-08, "loss": 2.6856, "step": 1932 }, { "epoch": 4.37, "learning_rate": 8.36542262411627e-08, "loss": 2.6301, "step": 1934 }, { "epoch": 4.38, "learning_rate": 8.248424634250417e-08, "loss": 2.7208, "step": 1936 }, { "epoch": 4.38, "learning_rate": 8.132215374844808e-08, "loss": 2.9551, "step": 1938 }, { "epoch": 4.39, "learning_rate": 8.016795844877166e-08, "loss": 2.712, "step": 1940 }, { "epoch": 4.39, "learning_rate": 7.902167036536444e-08, "loss": 3.1717, "step": 1942 }, { "epoch": 4.4, "learning_rate": 7.788329935214255e-08, "loss": 2.6908, "step": 1944 }, { "epoch": 4.4, "learning_rate": 7.67528551949641e-08, "loss": 3.1038, "step": 1946 }, { "epoch": 4.4, "learning_rate": 7.563034761154508e-08, "loss": 2.8941, "step": 1948 }, { "epoch": 4.41, "learning_rate": 7.451578625137534e-08, "loss": 2.85, "step": 1950 }, { "epoch": 4.41, "learning_rate": 7.340918069563662e-08, "loss": 2.5891, "step": 1952 }, { "epoch": 4.42, "learning_rate": 7.231054045711948e-08, "loss": 3.1967, "step": 1954 }, { "epoch": 4.42, "learning_rate": 7.121987498014115e-08, "loss": 2.9553, "step": 1956 }, { "epoch": 4.43, "learning_rate": 7.013719364046555e-08, "loss": 2.6721, "step": 1958 }, { "epoch": 4.43, "learning_rate": 6.906250574522154e-08, "loss": 2.9495, "step": 1960 }, { "epoch": 4.44, "learning_rate": 6.79958205328236e-08, "loss": 2.9901, "step": 1962 }, { "epoch": 4.44, "learning_rate": 6.693714717289245e-08, "loss": 2.4818, "step": 1964 }, { "epoch": 4.45, "learning_rate": 6.588649476617525e-08, "loss": 2.5111, "step": 1966 }, { "epoch": 4.45, "learning_rate": 6.484387234446853e-08, "loss": 2.9521, "step": 1968 }, { "epoch": 4.45, "learning_rate": 6.380928887054027e-08, "loss": 2.734, "step": 1970 }, { "epoch": 4.46, "learning_rate": 6.278275323805249e-08, "loss": 2.8852, "step": 1972 }, { "epoch": 4.46, "learning_rate": 6.176427427148467e-08, "loss": 2.7127, "step": 1974 }, { "epoch": 4.47, "learning_rate": 6.075386072605871e-08, "loss": 2.6874, "step": 1976 }, { "epoch": 4.47, "learning_rate": 5.975152128766292e-08, "loss": 2.5825, "step": 1978 }, { "epoch": 4.48, "learning_rate": 5.875726457277774e-08, "loss": 2.7224, "step": 1980 }, { "epoch": 4.48, "learning_rate": 5.7771099128401615e-08, "loss": 2.7397, "step": 1982 }, { "epoch": 4.49, "learning_rate": 5.6793033431976836e-08, "loss": 2.7022, "step": 1984 }, { "epoch": 4.49, "learning_rate": 5.582307589131785e-08, "loss": 2.8325, "step": 1986 }, { "epoch": 4.5, "learning_rate": 5.4861234844538415e-08, "loss": 2.9048, "step": 1988 }, { "epoch": 4.5, "learning_rate": 5.3907518559979656e-08, "loss": 2.8014, "step": 1990 }, { "epoch": 4.5, "learning_rate": 5.296193523613923e-08, "loss": 2.4705, "step": 1992 }, { "epoch": 4.51, "learning_rate": 5.2024493001601056e-08, "loss": 3.3352, "step": 1994 }, { "epoch": 4.51, "learning_rate": 5.1095199914965025e-08, "loss": 2.6105, "step": 1996 }, { "epoch": 4.52, "learning_rate": 5.017406396477808e-08, "loss": 2.8586, "step": 1998 }, { "epoch": 4.52, "learning_rate": 4.9261093069465576e-08, "loss": 2.8067, "step": 2000 }, { "epoch": 4.53, "learning_rate": 4.835629507726258e-08, "loss": 2.8375, "step": 2002 }, { "epoch": 4.53, "learning_rate": 4.745967776614712e-08, "loss": 2.7522, "step": 2004 }, { "epoch": 4.54, "learning_rate": 4.657124884377317e-08, "loss": 2.9548, "step": 2006 }, { "epoch": 4.54, "learning_rate": 4.5691015947404323e-08, "loss": 3.0078, "step": 2008 }, { "epoch": 4.54, "learning_rate": 4.4818986643847645e-08, "loss": 3.0684, "step": 2010 }, { "epoch": 4.55, "learning_rate": 4.39551684293894e-08, "loss": 3.015, "step": 2012 }, { "epoch": 4.55, "learning_rate": 4.309956872973053e-08, "loss": 2.5523, "step": 2014 }, { "epoch": 4.56, "learning_rate": 4.225219489992227e-08, "loss": 2.6985, "step": 2016 }, { "epoch": 4.56, "learning_rate": 4.141305422430341e-08, "loss": 2.6523, "step": 2018 }, { "epoch": 4.57, "learning_rate": 4.0582153916437045e-08, "loss": 2.4092, "step": 2020 }, { "epoch": 4.57, "learning_rate": 3.975950111904969e-08, "loss": 2.9381, "step": 2022 }, { "epoch": 4.58, "learning_rate": 3.894510290396891e-08, "loss": 2.7444, "step": 2024 }, { "epoch": 4.58, "learning_rate": 3.813896627206281e-08, "loss": 2.7797, "step": 2026 }, { "epoch": 4.59, "learning_rate": 3.734109815317976e-08, "loss": 2.7712, "step": 2028 }, { "epoch": 4.59, "learning_rate": 3.655150540608909e-08, "loss": 2.5961, "step": 2030 }, { "epoch": 4.59, "learning_rate": 3.5770194818422025e-08, "loss": 2.3656, "step": 2032 }, { "epoch": 4.6, "learning_rate": 3.499717310661321e-08, "loss": 3.1496, "step": 2034 }, { "epoch": 4.6, "learning_rate": 3.423244691584304e-08, "loss": 2.7277, "step": 2036 }, { "epoch": 4.61, "learning_rate": 3.3476022819980523e-08, "loss": 3.1633, "step": 2038 }, { "epoch": 4.61, "learning_rate": 3.2727907321526746e-08, "loss": 2.4825, "step": 2040 }, { "epoch": 4.62, "learning_rate": 3.198810685155917e-08, "loss": 2.7128, "step": 2042 }, { "epoch": 4.62, "learning_rate": 3.1256627769676304e-08, "loss": 2.7887, "step": 2044 }, { "epoch": 4.63, "learning_rate": 3.0533476363942435e-08, "loss": 2.8487, "step": 2046 }, { "epoch": 4.63, "learning_rate": 2.981865885083446e-08, "loss": 2.7965, "step": 2048 }, { "epoch": 4.64, "learning_rate": 2.9112181375188116e-08, "loss": 2.9398, "step": 2050 }, { "epoch": 4.64, "learning_rate": 2.841405001014474e-08, "loss": 2.8398, "step": 2052 }, { "epoch": 4.64, "learning_rate": 2.7724270757099933e-08, "loss": 2.7288, "step": 2054 }, { "epoch": 4.65, "learning_rate": 2.7042849545650837e-08, "loss": 3.021, "step": 2056 }, { "epoch": 4.65, "learning_rate": 2.6369792233546184e-08, "loss": 2.8611, "step": 2058 }, { "epoch": 4.66, "learning_rate": 2.570510460663555e-08, "loss": 2.842, "step": 2060 }, { "epoch": 4.66, "learning_rate": 2.5048792378819516e-08, "loss": 2.578, "step": 2062 }, { "epoch": 4.67, "learning_rate": 2.4400861192000356e-08, "loss": 2.5474, "step": 2064 }, { "epoch": 4.67, "learning_rate": 2.376131661603431e-08, "loss": 2.7978, "step": 2066 }, { "epoch": 4.68, "learning_rate": 2.3130164148682852e-08, "loss": 2.7627, "step": 2068 }, { "epoch": 4.68, "learning_rate": 2.2507409215566043e-08, "loss": 2.9917, "step": 2070 }, { "epoch": 4.69, "learning_rate": 2.189305717011547e-08, "loss": 3.1182, "step": 2072 }, { "epoch": 4.69, "learning_rate": 2.128711329352828e-08, "loss": 2.6249, "step": 2074 }, { "epoch": 4.69, "learning_rate": 2.0689582794722215e-08, "loss": 2.5374, "step": 2076 }, { "epoch": 4.7, "learning_rate": 2.0100470810290205e-08, "loss": 2.8641, "step": 2078 }, { "epoch": 4.7, "learning_rate": 1.951978240445684e-08, "loss": 3.0506, "step": 2080 }, { "epoch": 4.71, "learning_rate": 1.8947522569034092e-08, "loss": 2.4831, "step": 2082 }, { "epoch": 4.71, "learning_rate": 1.8664554905357233e-08, "loss": 2.8003, "step": 2084 }, { "epoch": 4.72, "learning_rate": 1.8104947126691418e-08, "loss": 2.8693, "step": 2086 }, { "epoch": 4.72, "learning_rate": 1.7553780080883374e-08, "loss": 2.641, "step": 2088 }, { "epoch": 4.73, "learning_rate": 1.7011058505968733e-08, "loss": 2.6897, "step": 2090 }, { "epoch": 4.73, "learning_rate": 1.6476787067382868e-08, "loss": 2.6884, "step": 2092 }, { "epoch": 4.73, "learning_rate": 1.595097035792059e-08, "loss": 2.9753, "step": 2094 }, { "epoch": 4.74, "learning_rate": 1.5433612897696734e-08, "loss": 2.7691, "step": 2096 }, { "epoch": 4.74, "learning_rate": 1.49247191341072e-08, "loss": 2.366, "step": 2098 }, { "epoch": 4.75, "learning_rate": 1.442429344179097e-08, "loss": 2.872, "step": 2100 }, { "epoch": 4.75, "learning_rate": 1.3932340122592256e-08, "loss": 2.6101, "step": 2102 }, { "epoch": 4.76, "learning_rate": 1.3448863405523647e-08, "loss": 2.8054, "step": 2104 }, { "epoch": 4.76, "learning_rate": 1.3210305074430661e-08, "loss": 2.9566, "step": 2106 }, { "epoch": 4.77, "learning_rate": 1.2739551030547358e-08, "loss": 2.9017, "step": 2108 }, { "epoch": 4.77, "learning_rate": 1.2277283842450192e-08, "loss": 2.893, "step": 2110 }, { "epoch": 4.78, "learning_rate": 1.182350748395866e-08, "loss": 2.6741, "step": 2112 }, { "epoch": 4.78, "learning_rate": 1.1378225855902201e-08, "loss": 2.673, "step": 2114 }, { "epoch": 4.78, "learning_rate": 1.094144278608633e-08, "loss": 2.8725, "step": 2116 }, { "epoch": 4.79, "learning_rate": 1.051316202925978e-08, "loss": 3.2024, "step": 2118 }, { "epoch": 4.79, "learning_rate": 1.0093387267082198e-08, "loss": 2.5178, "step": 2120 }, { "epoch": 4.8, "learning_rate": 9.682122108092605e-09, "loss": 2.9502, "step": 2122 }, { "epoch": 4.8, "learning_rate": 9.279370087678429e-09, "loss": 2.7508, "step": 2124 }, { "epoch": 4.81, "learning_rate": 8.885134668044858e-09, "loss": 2.811, "step": 2126 }, { "epoch": 4.81, "learning_rate": 8.499419238185423e-09, "loss": 2.8079, "step": 2128 }, { "epoch": 4.82, "learning_rate": 8.122227113852353e-09, "loss": 2.3613, "step": 2130 }, { "epoch": 4.82, "learning_rate": 7.753561537528708e-09, "loss": 2.6701, "step": 2132 }, { "epoch": 4.83, "learning_rate": 7.393425678400067e-09, "loss": 3.1051, "step": 2134 }, { "epoch": 4.83, "learning_rate": 7.041822632327443e-09, "loss": 2.4941, "step": 2136 }, { "epoch": 4.83, "learning_rate": 6.698755421820523e-09, "loss": 2.4881, "step": 2138 }, { "epoch": 4.84, "learning_rate": 6.364226996011801e-09, "loss": 2.9043, "step": 2140 }, { "epoch": 4.84, "learning_rate": 6.038240230631486e-09, "loss": 2.7145, "step": 2142 }, { "epoch": 4.85, "learning_rate": 5.7207979279821905e-09, "loss": 2.9102, "step": 2144 }, { "epoch": 4.85, "learning_rate": 5.411902816915392e-09, "loss": 2.9073, "step": 2146 }, { "epoch": 4.86, "learning_rate": 5.111557552807566e-09, "loss": 2.6111, "step": 2148 }, { "epoch": 4.86, "learning_rate": 4.819764717537644e-09, "loss": 2.5371, "step": 2150 }, { "epoch": 4.87, "learning_rate": 4.536526819464703e-09, "loss": 2.7557, "step": 2152 }, { "epoch": 4.87, "learning_rate": 4.2618462934065344e-09, "loss": 2.7289, "step": 2154 }, { "epoch": 4.88, "learning_rate": 3.99572550061833e-09, "loss": 2.7556, "step": 2156 }, { "epoch": 4.88, "learning_rate": 3.738166728772918e-09, "loss": 2.6094, "step": 2158 }, { "epoch": 4.88, "learning_rate": 3.4891721919405594e-09, "loss": 2.5753, "step": 2160 }, { "epoch": 4.89, "learning_rate": 3.248744030570516e-09, "loss": 2.5225, "step": 2162 }, { "epoch": 4.89, "learning_rate": 3.0168843114720676e-09, "loss": 2.8242, "step": 2164 }, { "epoch": 4.9, "learning_rate": 2.79359502779708e-09, "loss": 3.3142, "step": 2166 }, { "epoch": 4.9, "learning_rate": 2.5788780990227964e-09, "loss": 2.6283, "step": 2168 }, { "epoch": 4.91, "learning_rate": 2.372735370935297e-09, "loss": 2.8375, "step": 2170 }, { "epoch": 4.91, "learning_rate": 2.1751686156136205e-09, "loss": 2.667, "step": 2172 }, { "epoch": 4.92, "learning_rate": 1.986179531414778e-09, "loss": 2.6787, "step": 2174 }, { "epoch": 4.92, "learning_rate": 1.8057697429586515e-09, "loss": 2.8926, "step": 2176 }, { "epoch": 4.92, "learning_rate": 1.633940801114564e-09, "loss": 2.9471, "step": 2178 }, { "epoch": 4.93, "learning_rate": 1.4706941829875086e-09, "loss": 2.4699, "step": 2180 }, { "epoch": 4.93, "learning_rate": 1.3160312919059391e-09, "loss": 2.8239, "step": 2182 }, { "epoch": 4.94, "learning_rate": 1.169953457409112e-09, "loss": 2.5784, "step": 2184 }, { "epoch": 4.94, "learning_rate": 1.0324619352362062e-09, "loss": 2.857, "step": 2186 }, { "epoch": 4.95, "learning_rate": 9.035579073150002e-10, "loss": 2.5956, "step": 2188 }, { "epoch": 4.95, "learning_rate": 7.83242481752322e-10, "loss": 2.5993, "step": 2190 }, { "epoch": 4.96, "learning_rate": 6.71516692823948e-10, "loss": 2.7151, "step": 2192 }, { "epoch": 4.96, "learning_rate": 5.683815009661641e-10, "loss": 2.843, "step": 2194 }, { "epoch": 4.97, "learning_rate": 4.738377927671067e-10, "loss": 2.5233, "step": 2196 }, { "epoch": 4.97, "learning_rate": 3.8788638095954564e-10, "loss": 2.7304, "step": 2198 }, { "epoch": 4.97, "learning_rate": 3.105280044135572e-10, "loss": 2.4621, "step": 2200 }, { "epoch": 4.98, "learning_rate": 2.417633281301956e-10, "loss": 3.0428, "step": 2202 }, { "epoch": 4.98, "learning_rate": 1.8159294323627506e-10, "loss": 2.6062, "step": 2204 }, { "epoch": 4.99, "learning_rate": 1.300173669784854e-10, "loss": 2.9352, "step": 2206 }, { "epoch": 4.99, "learning_rate": 8.703704271961765e-11, "loss": 2.895, "step": 2208 }, { "epoch": 5.0, "learning_rate": 5.265233993445584e-11, "loss": 2.8186, "step": 2210 }, { "epoch": 5.0, "step": 2210, "total_flos": 4.854091284584858e+16, "train_loss": 3.165947407511025, "train_runtime": 16257.9617, "train_samples_per_second": 8.703, "train_steps_per_second": 0.136 } ], "logging_steps": 2, "max_steps": 2210, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 8000, "total_flos": 4.854091284584858e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }