{ "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": 8.7039, "step": 2 }, { "epoch": 0.01, "learning_rate": 0.0, "loss": 8.8091, "step": 4 }, { "epoch": 0.01, "learning_rate": 2.9850746268656714e-08, "loss": 9.0106, "step": 6 }, { "epoch": 0.02, "learning_rate": 8.955223880597014e-08, "loss": 9.072, "step": 8 }, { "epoch": 0.02, "learning_rate": 1.4925373134328355e-07, "loss": 8.6012, "step": 10 }, { "epoch": 0.03, "learning_rate": 2.08955223880597e-07, "loss": 8.9917, "step": 12 }, { "epoch": 0.03, "learning_rate": 2.686567164179104e-07, "loss": 8.7255, "step": 14 }, { "epoch": 0.04, "learning_rate": 3.2835820895522385e-07, "loss": 9.289, "step": 16 }, { "epoch": 0.04, "learning_rate": 3.880597014925373e-07, "loss": 8.6583, "step": 18 }, { "epoch": 0.05, "learning_rate": 4.4776119402985074e-07, "loss": 8.4296, "step": 20 }, { "epoch": 0.05, "learning_rate": 5.074626865671642e-07, "loss": 8.5667, "step": 22 }, { "epoch": 0.05, "learning_rate": 5.671641791044775e-07, "loss": 7.747, "step": 24 }, { "epoch": 0.06, "learning_rate": 6.26865671641791e-07, "loss": 7.9642, "step": 26 }, { "epoch": 0.06, "learning_rate": 6.865671641791044e-07, "loss": 8.1156, "step": 28 }, { "epoch": 0.07, "learning_rate": 7.462686567164179e-07, "loss": 7.4846, "step": 30 }, { "epoch": 0.07, "learning_rate": 8.059701492537313e-07, "loss": 7.1547, "step": 32 }, { "epoch": 0.08, "learning_rate": 8.35820895522388e-07, "loss": 6.7033, "step": 34 }, { "epoch": 0.08, "learning_rate": 8.955223880597015e-07, "loss": 6.5868, "step": 36 }, { "epoch": 0.09, "learning_rate": 9.552238805970149e-07, "loss": 6.0138, "step": 38 }, { "epoch": 0.09, "learning_rate": 1.0149253731343285e-06, "loss": 5.8993, "step": 40 }, { "epoch": 0.09, "learning_rate": 1.0746268656716416e-06, "loss": 5.5833, "step": 42 }, { "epoch": 0.1, "learning_rate": 1.134328358208955e-06, "loss": 5.2659, "step": 44 }, { "epoch": 0.1, "learning_rate": 1.1940298507462684e-06, "loss": 5.0501, "step": 46 }, { "epoch": 0.11, "learning_rate": 1.253731343283582e-06, "loss": 5.441, "step": 48 }, { "epoch": 0.11, "learning_rate": 1.3134328358208954e-06, "loss": 5.2393, "step": 50 }, { "epoch": 0.12, "learning_rate": 1.3731343283582088e-06, "loss": 4.6421, "step": 52 }, { "epoch": 0.12, "learning_rate": 1.4328358208955222e-06, "loss": 4.6876, "step": 54 }, { "epoch": 0.13, "learning_rate": 1.4925373134328358e-06, "loss": 4.602, "step": 56 }, { "epoch": 0.13, "learning_rate": 1.5522388059701492e-06, "loss": 4.306, "step": 58 }, { "epoch": 0.14, "learning_rate": 1.6119402985074626e-06, "loss": 4.857, "step": 60 }, { "epoch": 0.14, "learning_rate": 1.671641791044776e-06, "loss": 4.8468, "step": 62 }, { "epoch": 0.14, "learning_rate": 1.7313432835820893e-06, "loss": 4.5246, "step": 64 }, { "epoch": 0.15, "learning_rate": 1.791044776119403e-06, "loss": 4.0832, "step": 66 }, { "epoch": 0.15, "learning_rate": 1.8507462686567163e-06, "loss": 4.2813, "step": 68 }, { "epoch": 0.16, "learning_rate": 1.9104477611940297e-06, "loss": 4.4003, "step": 70 }, { "epoch": 0.16, "learning_rate": 1.970149253731343e-06, "loss": 4.1632, "step": 72 }, { "epoch": 0.17, "learning_rate": 1.999998925453213e-06, "loss": 4.6656, "step": 74 }, { "epoch": 0.17, "learning_rate": 1.999990329092774e-06, "loss": 4.2304, "step": 76 }, { "epoch": 0.18, "learning_rate": 1.9999731364457933e-06, "loss": 3.7582, "step": 78 }, { "epoch": 0.18, "learning_rate": 1.9999473476600653e-06, "loss": 4.6062, "step": 80 }, { "epoch": 0.19, "learning_rate": 1.99991296295728e-06, "loss": 3.7619, "step": 82 }, { "epoch": 0.19, "learning_rate": 1.9998699826330215e-06, "loss": 3.7262, "step": 84 }, { "epoch": 0.19, "learning_rate": 1.9998184070567638e-06, "loss": 4.2597, "step": 86 }, { "epoch": 0.2, "learning_rate": 1.9997582366718695e-06, "loss": 4.0068, "step": 88 }, { "epoch": 0.2, "learning_rate": 1.9996894719955866e-06, "loss": 3.7567, "step": 90 }, { "epoch": 0.21, "learning_rate": 1.99961211361904e-06, "loss": 4.3052, "step": 92 }, { "epoch": 0.21, "learning_rate": 1.999526162207233e-06, "loss": 4.4518, "step": 94 }, { "epoch": 0.22, "learning_rate": 1.9994316184990337e-06, "loss": 4.4373, "step": 96 }, { "epoch": 0.22, "learning_rate": 1.999328483307176e-06, "loss": 4.1842, "step": 98 }, { "epoch": 0.23, "learning_rate": 1.9992167575182478e-06, "loss": 4.2331, "step": 100 }, { "epoch": 0.23, "learning_rate": 1.999096442092685e-06, "loss": 3.9966, "step": 102 }, { "epoch": 0.24, "learning_rate": 1.9989675380647637e-06, "loss": 3.5594, "step": 104 }, { "epoch": 0.24, "learning_rate": 1.998830046542591e-06, "loss": 4.0698, "step": 106 }, { "epoch": 0.24, "learning_rate": 1.998683968708094e-06, "loss": 4.0807, "step": 108 }, { "epoch": 0.25, "learning_rate": 1.9985293058170123e-06, "loss": 4.1596, "step": 110 }, { "epoch": 0.25, "learning_rate": 1.9983660591988855e-06, "loss": 4.134, "step": 112 }, { "epoch": 0.26, "learning_rate": 1.9981942302570413e-06, "loss": 4.0118, "step": 114 }, { "epoch": 0.26, "learning_rate": 1.9980138204685853e-06, "loss": 4.1501, "step": 116 }, { "epoch": 0.27, "learning_rate": 1.9978248313843862e-06, "loss": 3.5906, "step": 118 }, { "epoch": 0.27, "learning_rate": 1.9976272646290646e-06, "loss": 3.9156, "step": 120 }, { "epoch": 0.28, "learning_rate": 1.997421121900977e-06, "loss": 3.5392, "step": 122 }, { "epoch": 0.28, "learning_rate": 1.997206404972203e-06, "loss": 4.3503, "step": 124 }, { "epoch": 0.28, "learning_rate": 1.9969831156885276e-06, "loss": 4.4325, "step": 126 }, { "epoch": 0.29, "learning_rate": 1.996751255969429e-06, "loss": 4.3012, "step": 128 }, { "epoch": 0.29, "learning_rate": 1.9965108278080595e-06, "loss": 4.2846, "step": 130 }, { "epoch": 0.3, "learning_rate": 1.996261833271227e-06, "loss": 4.0294, "step": 132 }, { "epoch": 0.3, "learning_rate": 1.9960042744993815e-06, "loss": 3.488, "step": 134 }, { "epoch": 0.31, "learning_rate": 1.9957381537065932e-06, "loss": 4.6518, "step": 136 }, { "epoch": 0.31, "learning_rate": 1.995463473180535e-06, "loss": 4.4723, "step": 138 }, { "epoch": 0.32, "learning_rate": 1.995180235282462e-06, "loss": 4.509, "step": 140 }, { "epoch": 0.32, "learning_rate": 1.9948884424471923e-06, "loss": 3.3275, "step": 142 }, { "epoch": 0.33, "learning_rate": 1.9945880971830843e-06, "loss": 3.6704, "step": 144 }, { "epoch": 0.33, "learning_rate": 1.994279202072018e-06, "loss": 4.1992, "step": 146 }, { "epoch": 0.33, "learning_rate": 1.9939617597693683e-06, "loss": 3.7296, "step": 148 }, { "epoch": 0.34, "learning_rate": 1.993635773003988e-06, "loss": 3.5335, "step": 150 }, { "epoch": 0.34, "learning_rate": 1.9933012445781795e-06, "loss": 4.0511, "step": 152 }, { "epoch": 0.35, "learning_rate": 1.9929581773676725e-06, "loss": 3.9205, "step": 154 }, { "epoch": 0.35, "learning_rate": 1.9926065743216e-06, "loss": 3.8872, "step": 156 }, { "epoch": 0.36, "learning_rate": 1.9922464384624714e-06, "loss": 4.0427, "step": 158 }, { "epoch": 0.36, "learning_rate": 1.9918777728861474e-06, "loss": 3.9574, "step": 160 }, { "epoch": 0.37, "learning_rate": 1.9915005807618145e-06, "loss": 4.4929, "step": 162 }, { "epoch": 0.37, "learning_rate": 1.991114865331955e-06, "loss": 3.6872, "step": 164 }, { "epoch": 0.38, "learning_rate": 1.9907206299123214e-06, "loss": 4.1757, "step": 166 }, { "epoch": 0.38, "learning_rate": 1.9903178778919072e-06, "loss": 4.0117, "step": 168 }, { "epoch": 0.38, "learning_rate": 1.9899066127329178e-06, "loss": 4.4938, "step": 170 }, { "epoch": 0.39, "learning_rate": 1.98948683797074e-06, "loss": 3.98, "step": 172 }, { "epoch": 0.39, "learning_rate": 1.9890585572139136e-06, "loss": 3.9085, "step": 174 }, { "epoch": 0.4, "learning_rate": 1.988621774144098e-06, "loss": 4.0111, "step": 176 }, { "epoch": 0.4, "learning_rate": 1.9881764925160414e-06, "loss": 3.6935, "step": 178 }, { "epoch": 0.41, "learning_rate": 1.9877227161575497e-06, "loss": 3.623, "step": 180 }, { "epoch": 0.41, "learning_rate": 1.9872604489694526e-06, "loss": 4.3184, "step": 182 }, { "epoch": 0.42, "learning_rate": 1.9867896949255693e-06, "loss": 3.3212, "step": 184 }, { "epoch": 0.42, "learning_rate": 1.9863104580726754e-06, "loss": 3.7107, "step": 186 }, { "epoch": 0.43, "learning_rate": 1.9858227425304686e-06, "loss": 3.5705, "step": 188 }, { "epoch": 0.43, "learning_rate": 1.9853265524915316e-06, "loss": 4.1051, "step": 190 }, { "epoch": 0.43, "learning_rate": 1.9848218922212978e-06, "loss": 3.6446, "step": 192 }, { "epoch": 0.44, "learning_rate": 1.9843087660580133e-06, "loss": 3.4356, "step": 194 }, { "epoch": 0.44, "learning_rate": 1.9837871784126997e-06, "loss": 3.515, "step": 196 }, { "epoch": 0.45, "learning_rate": 1.983257133769118e-06, "loss": 3.6508, "step": 198 }, { "epoch": 0.45, "learning_rate": 1.982718636683727e-06, "loss": 3.5755, "step": 200 }, { "epoch": 0.46, "learning_rate": 1.9821716917856482e-06, "loss": 3.2402, "step": 202 }, { "epoch": 0.46, "learning_rate": 1.9816163037766205e-06, "loss": 3.2438, "step": 204 }, { "epoch": 0.47, "learning_rate": 1.981052477430966e-06, "loss": 3.4967, "step": 206 }, { "epoch": 0.47, "learning_rate": 1.980480217595543e-06, "loss": 4.2713, "step": 208 }, { "epoch": 0.47, "learning_rate": 1.9798995291897097e-06, "loss": 3.811, "step": 210 }, { "epoch": 0.48, "learning_rate": 1.979310417205278e-06, "loss": 3.2827, "step": 212 }, { "epoch": 0.48, "learning_rate": 1.9787128867064714e-06, "loss": 3.4953, "step": 214 }, { "epoch": 0.49, "learning_rate": 1.9781069428298845e-06, "loss": 3.322, "step": 216 }, { "epoch": 0.49, "learning_rate": 1.977492590784434e-06, "loss": 3.3156, "step": 218 }, { "epoch": 0.5, "learning_rate": 1.9768698358513173e-06, "loss": 3.8641, "step": 220 }, { "epoch": 0.5, "learning_rate": 1.9762386833839656e-06, "loss": 3.6241, "step": 222 }, { "epoch": 0.51, "learning_rate": 1.9755991388079994e-06, "loss": 3.6677, "step": 224 }, { "epoch": 0.51, "learning_rate": 1.9749512076211804e-06, "loss": 3.6243, "step": 226 }, { "epoch": 0.52, "learning_rate": 1.9742948953933643e-06, "loss": 3.8242, "step": 228 }, { "epoch": 0.52, "learning_rate": 1.973630207766454e-06, "loss": 3.5467, "step": 230 }, { "epoch": 0.52, "learning_rate": 1.972957150454349e-06, "loss": 4.0652, "step": 232 }, { "epoch": 0.53, "learning_rate": 1.9722757292429e-06, "loss": 3.5798, "step": 234 }, { "epoch": 0.53, "learning_rate": 1.9715859499898555e-06, "loss": 4.3079, "step": 236 }, { "epoch": 0.54, "learning_rate": 1.970887818624812e-06, "loss": 4.1985, "step": 238 }, { "epoch": 0.54, "learning_rate": 1.9701813411491656e-06, "loss": 3.7113, "step": 240 }, { "epoch": 0.55, "learning_rate": 1.9694665236360575e-06, "loss": 3.4273, "step": 242 }, { "epoch": 0.55, "learning_rate": 1.9687433722303236e-06, "loss": 3.5031, "step": 244 }, { "epoch": 0.56, "learning_rate": 1.9680118931484407e-06, "loss": 3.6452, "step": 246 }, { "epoch": 0.56, "learning_rate": 1.967272092678473e-06, "loss": 3.2726, "step": 248 }, { "epoch": 0.57, "learning_rate": 1.9665239771800197e-06, "loss": 3.2449, "step": 250 }, { "epoch": 0.57, "learning_rate": 1.9657675530841568e-06, "loss": 4.126, "step": 252 }, { "epoch": 0.57, "learning_rate": 1.9650028268933865e-06, "loss": 3.7822, "step": 254 }, { "epoch": 0.58, "learning_rate": 1.964229805181578e-06, "loss": 3.6748, "step": 256 }, { "epoch": 0.58, "learning_rate": 1.9634484945939108e-06, "loss": 3.4094, "step": 258 }, { "epoch": 0.59, "learning_rate": 1.96265890184682e-06, "loss": 3.5794, "step": 260 }, { "epoch": 0.59, "learning_rate": 1.961861033727937e-06, "loss": 4.0293, "step": 262 }, { "epoch": 0.6, "learning_rate": 1.961054897096031e-06, "loss": 3.0789, "step": 264 }, { "epoch": 0.6, "learning_rate": 1.96024049888095e-06, "loss": 3.8775, "step": 266 }, { "epoch": 0.61, "learning_rate": 1.9594178460835627e-06, "loss": 2.8333, "step": 268 }, { "epoch": 0.61, "learning_rate": 1.958586945775697e-06, "loss": 3.3959, "step": 270 }, { "epoch": 0.62, "learning_rate": 1.9577478051000774e-06, "loss": 3.827, "step": 272 }, { "epoch": 0.62, "learning_rate": 1.9569004312702694e-06, "loss": 3.6752, "step": 274 }, { "epoch": 0.62, "learning_rate": 1.95604483157061e-06, "loss": 3.5585, "step": 276 }, { "epoch": 0.63, "learning_rate": 1.9551810133561524e-06, "loss": 3.4696, "step": 278 }, { "epoch": 0.63, "learning_rate": 1.9543089840525953e-06, "loss": 4.0242, "step": 280 }, { "epoch": 0.64, "learning_rate": 1.9534287511562268e-06, "loss": 3.2607, "step": 282 }, { "epoch": 0.64, "learning_rate": 1.952540322233853e-06, "loss": 4.0142, "step": 284 }, { "epoch": 0.65, "learning_rate": 1.951643704922737e-06, "loss": 3.7433, "step": 286 }, { "epoch": 0.65, "learning_rate": 1.9507389069305344e-06, "loss": 3.7004, "step": 288 }, { "epoch": 0.66, "learning_rate": 1.9498259360352218e-06, "loss": 3.5172, "step": 290 }, { "epoch": 0.66, "learning_rate": 1.9489048000850346e-06, "loss": 3.1189, "step": 292 }, { "epoch": 0.66, "learning_rate": 1.9479755069983987e-06, "loss": 3.9421, "step": 294 }, { "epoch": 0.67, "learning_rate": 1.947038064763861e-06, "loss": 3.3838, "step": 296 }, { "epoch": 0.67, "learning_rate": 1.9460924814400205e-06, "loss": 3.9235, "step": 298 }, { "epoch": 0.68, "learning_rate": 1.9451387651554616e-06, "loss": 3.6673, "step": 300 }, { "epoch": 0.68, "learning_rate": 1.944176924108682e-06, "loss": 3.1712, "step": 302 }, { "epoch": 0.69, "learning_rate": 1.943206966568023e-06, "loss": 3.4347, "step": 304 }, { "epoch": 0.69, "learning_rate": 1.942228900871598e-06, "loss": 3.329, "step": 306 }, { "epoch": 0.7, "learning_rate": 1.941242735427222e-06, "loss": 3.6442, "step": 308 }, { "epoch": 0.7, "learning_rate": 1.940248478712337e-06, "loss": 3.1651, "step": 310 }, { "epoch": 0.71, "learning_rate": 1.9392461392739412e-06, "loss": 3.3006, "step": 312 }, { "epoch": 0.71, "learning_rate": 1.938235725728515e-06, "loss": 3.6091, "step": 314 }, { "epoch": 0.71, "learning_rate": 1.9372172467619476e-06, "loss": 3.4012, "step": 316 }, { "epoch": 0.72, "learning_rate": 1.9361907111294597e-06, "loss": 3.623, "step": 318 }, { "epoch": 0.72, "learning_rate": 1.9351561276555314e-06, "loss": 3.4288, "step": 320 }, { "epoch": 0.73, "learning_rate": 1.9341135052338247e-06, "loss": 3.4907, "step": 322 }, { "epoch": 0.73, "learning_rate": 1.9330628528271074e-06, "loss": 3.7643, "step": 324 }, { "epoch": 0.74, "learning_rate": 1.9320041794671763e-06, "loss": 3.3143, "step": 326 }, { "epoch": 0.74, "learning_rate": 1.9309374942547785e-06, "loss": 3.4362, "step": 328 }, { "epoch": 0.75, "learning_rate": 1.9298628063595345e-06, "loss": 3.1767, "step": 330 }, { "epoch": 0.75, "learning_rate": 1.928780125019859e-06, "loss": 3.7644, "step": 332 }, { "epoch": 0.76, "learning_rate": 1.9276894595428805e-06, "loss": 3.1695, "step": 334 }, { "epoch": 0.76, "learning_rate": 1.9265908193043632e-06, "loss": 3.5266, "step": 336 }, { "epoch": 0.76, "learning_rate": 1.9254842137486245e-06, "loss": 3.614, "step": 338 }, { "epoch": 0.77, "learning_rate": 1.9243696523884546e-06, "loss": 3.559, "step": 340 }, { "epoch": 0.77, "learning_rate": 1.9232471448050358e-06, "loss": 3.368, "step": 342 }, { "epoch": 0.78, "learning_rate": 1.922116700647857e-06, "loss": 3.7383, "step": 344 }, { "epoch": 0.78, "learning_rate": 1.9209783296346356e-06, "loss": 3.141, "step": 346 }, { "epoch": 0.79, "learning_rate": 1.9198320415512286e-06, "loss": 3.2768, "step": 348 }, { "epoch": 0.79, "learning_rate": 1.918677846251552e-06, "loss": 3.7393, "step": 350 }, { "epoch": 0.8, "learning_rate": 1.917515753657496e-06, "loss": 2.8872, "step": 352 }, { "epoch": 0.8, "learning_rate": 1.9163457737588374e-06, "loss": 3.49, "step": 354 }, { "epoch": 0.8, "learning_rate": 1.915167916613156e-06, "loss": 3.8771, "step": 356 }, { "epoch": 0.81, "learning_rate": 1.9139821923457483e-06, "loss": 2.8274, "step": 358 }, { "epoch": 0.81, "learning_rate": 1.9127886111495373e-06, "loss": 2.858, "step": 360 }, { "epoch": 0.82, "learning_rate": 1.9115871832849887e-06, "loss": 3.1705, "step": 362 }, { "epoch": 0.82, "learning_rate": 1.91037791908002e-06, "loss": 3.4805, "step": 364 }, { "epoch": 0.83, "learning_rate": 1.9091608289299143e-06, "loss": 3.3386, "step": 366 }, { "epoch": 0.83, "learning_rate": 1.9079359232972276e-06, "loss": 3.273, "step": 368 }, { "epoch": 0.84, "learning_rate": 1.9067032127117022e-06, "loss": 3.5189, "step": 370 }, { "epoch": 0.84, "learning_rate": 1.9054627077701735e-06, "loss": 3.2572, "step": 372 }, { "epoch": 0.85, "learning_rate": 1.9042144191364805e-06, "loss": 3.1284, "step": 374 }, { "epoch": 0.85, "learning_rate": 1.9029583575413744e-06, "loss": 3.4332, "step": 376 }, { "epoch": 0.85, "learning_rate": 1.9016945337824244e-06, "loss": 3.2338, "step": 378 }, { "epoch": 0.86, "learning_rate": 1.9004229587239266e-06, "loss": 3.3696, "step": 380 }, { "epoch": 0.86, "learning_rate": 1.8991436432968111e-06, "loss": 3.2127, "step": 382 }, { "epoch": 0.87, "learning_rate": 1.8978565984985458e-06, "loss": 3.3047, "step": 384 }, { "epoch": 0.87, "learning_rate": 1.8965618353930431e-06, "loss": 3.4949, "step": 386 }, { "epoch": 0.88, "learning_rate": 1.895259365110566e-06, "loss": 2.9415, "step": 388 }, { "epoch": 0.88, "learning_rate": 1.8939491988476298e-06, "loss": 3.0993, "step": 390 }, { "epoch": 0.89, "learning_rate": 1.8926313478669092e-06, "loss": 3.1004, "step": 392 }, { "epoch": 0.89, "learning_rate": 1.8913058234971375e-06, "loss": 3.2096, "step": 394 }, { "epoch": 0.9, "learning_rate": 1.8899726371330122e-06, "loss": 3.1733, "step": 396 }, { "epoch": 0.9, "learning_rate": 1.8886318002350965e-06, "loss": 3.6095, "step": 398 }, { "epoch": 0.9, "learning_rate": 1.8872833243297196e-06, "loss": 2.803, "step": 400 }, { "epoch": 0.91, "learning_rate": 1.8859272210088796e-06, "loss": 3.9185, "step": 402 }, { "epoch": 0.91, "learning_rate": 1.8845635019301413e-06, "loss": 3.0202, "step": 404 }, { "epoch": 0.92, "learning_rate": 1.883192178816538e-06, "loss": 3.2104, "step": 406 }, { "epoch": 0.92, "learning_rate": 1.881813263456471e-06, "loss": 3.2693, "step": 408 }, { "epoch": 0.93, "learning_rate": 1.8804267677036053e-06, "loss": 2.9124, "step": 410 }, { "epoch": 0.93, "learning_rate": 1.8790327034767718e-06, "loss": 3.4246, "step": 412 }, { "epoch": 0.94, "learning_rate": 1.877631082759862e-06, "loss": 3.4019, "step": 414 }, { "epoch": 0.94, "learning_rate": 1.8762219176017251e-06, "loss": 3.4459, "step": 416 }, { "epoch": 0.95, "learning_rate": 1.874805220116066e-06, "loss": 3.414, "step": 418 }, { "epoch": 0.95, "learning_rate": 1.87338100248134e-06, "loss": 3.4045, "step": 420 }, { "epoch": 0.95, "learning_rate": 1.8719492769406488e-06, "loss": 2.9695, "step": 422 }, { "epoch": 0.96, "learning_rate": 1.8705100558016338e-06, "loss": 2.9683, "step": 424 }, { "epoch": 0.96, "learning_rate": 1.869063351436372e-06, "loss": 3.3641, "step": 426 }, { "epoch": 0.97, "learning_rate": 1.8676091762812695e-06, "loss": 3.1818, "step": 428 }, { "epoch": 0.97, "learning_rate": 1.8661475428369531e-06, "loss": 3.3037, "step": 430 }, { "epoch": 0.98, "learning_rate": 1.8646784636681642e-06, "loss": 3.2608, "step": 432 }, { "epoch": 0.98, "learning_rate": 1.8632019514036506e-06, "loss": 3.3332, "step": 434 }, { "epoch": 0.99, "learning_rate": 1.8617180187360573e-06, "loss": 3.564, "step": 436 }, { "epoch": 0.99, "learning_rate": 1.8602266784218184e-06, "loss": 3.2229, "step": 438 }, { "epoch": 0.99, "learning_rate": 1.858727943281046e-06, "loss": 2.9376, "step": 440 }, { "epoch": 1.0, "learning_rate": 1.8572218261974224e-06, "loss": 3.34, "step": 442 }, { "epoch": 1.0, "learning_rate": 1.855708340118086e-06, "loss": 2.8005, "step": 444 }, { "epoch": 1.01, "learning_rate": 1.8541874980535229e-06, "loss": 3.5975, "step": 446 }, { "epoch": 1.01, "learning_rate": 1.8526593130774535e-06, "loss": 3.6855, "step": 448 }, { "epoch": 1.02, "learning_rate": 1.8511237983267212e-06, "loss": 3.3772, "step": 450 }, { "epoch": 1.02, "learning_rate": 1.8495809670011782e-06, "loss": 3.1185, "step": 452 }, { "epoch": 1.03, "learning_rate": 1.8480308323635728e-06, "loss": 3.2001, "step": 454 }, { "epoch": 1.03, "learning_rate": 1.8464734077394354e-06, "loss": 3.2238, "step": 456 }, { "epoch": 1.04, "learning_rate": 1.8449087065169643e-06, "loss": 3.2378, "step": 458 }, { "epoch": 1.04, "learning_rate": 1.843336742146909e-06, "loss": 3.3176, "step": 460 }, { "epoch": 1.04, "learning_rate": 1.8417575281424567e-06, "loss": 3.0237, "step": 462 }, { "epoch": 1.05, "learning_rate": 1.8401710780791147e-06, "loss": 3.4636, "step": 464 }, { "epoch": 1.05, "learning_rate": 1.8385774055945942e-06, "loss": 3.3706, "step": 466 }, { "epoch": 1.06, "learning_rate": 1.8369765243886932e-06, "loss": 3.1429, "step": 468 }, { "epoch": 1.06, "learning_rate": 1.8353684482231779e-06, "loss": 3.4949, "step": 470 }, { "epoch": 1.07, "learning_rate": 1.8337531909216662e-06, "loss": 3.2904, "step": 472 }, { "epoch": 1.07, "learning_rate": 1.8321307663695063e-06, "loss": 3.0508, "step": 474 }, { "epoch": 1.08, "learning_rate": 1.8305011885136594e-06, "loss": 3.158, "step": 476 }, { "epoch": 1.08, "learning_rate": 1.8288644713625798e-06, "loss": 3.3871, "step": 478 }, { "epoch": 1.09, "learning_rate": 1.827220628986093e-06, "loss": 2.991, "step": 480 }, { "epoch": 1.09, "learning_rate": 1.8255696755152753e-06, "loss": 2.9043, "step": 482 }, { "epoch": 1.09, "learning_rate": 1.8239116251423335e-06, "loss": 3.1425, "step": 484 }, { "epoch": 1.1, "learning_rate": 1.822246492120481e-06, "loss": 3.299, "step": 486 }, { "epoch": 1.1, "learning_rate": 1.8205742907638178e-06, "loss": 3.1543, "step": 488 }, { "epoch": 1.11, "learning_rate": 1.8188950354472041e-06, "loss": 3.0269, "step": 490 }, { "epoch": 1.11, "learning_rate": 1.8172087406061396e-06, "loss": 3.2797, "step": 492 }, { "epoch": 1.12, "learning_rate": 1.8155154207366384e-06, "loss": 3.4322, "step": 494 }, { "epoch": 1.12, "learning_rate": 1.8138150903951036e-06, "loss": 2.785, "step": 496 }, { "epoch": 1.13, "learning_rate": 1.8121077641982034e-06, "loss": 3.1905, "step": 498 }, { "epoch": 1.13, "learning_rate": 1.8103934568227456e-06, "loss": 3.4125, "step": 500 }, { "epoch": 1.14, "learning_rate": 1.80867218300555e-06, "loss": 3.7323, "step": 502 }, { "epoch": 1.14, "learning_rate": 1.8069439575433216e-06, "loss": 3.3511, "step": 504 }, { "epoch": 1.14, "learning_rate": 1.8052087952925266e-06, "loss": 3.1786, "step": 506 }, { "epoch": 1.15, "learning_rate": 1.8034667111692605e-06, "loss": 2.8096, "step": 508 }, { "epoch": 1.15, "learning_rate": 1.8017177201491224e-06, "loss": 3.5119, "step": 510 }, { "epoch": 1.16, "learning_rate": 1.7999618372670863e-06, "loss": 2.6925, "step": 512 }, { "epoch": 1.16, "learning_rate": 1.79819907761737e-06, "loss": 2.8054, "step": 514 }, { "epoch": 1.17, "learning_rate": 1.7964294563533074e-06, "loss": 3.4254, "step": 516 }, { "epoch": 1.17, "learning_rate": 1.7946529886872166e-06, "loss": 3.2991, "step": 518 }, { "epoch": 1.18, "learning_rate": 1.792869689890271e-06, "loss": 3.0612, "step": 520 }, { "epoch": 1.18, "learning_rate": 1.791079575292366e-06, "loss": 3.6067, "step": 522 }, { "epoch": 1.18, "learning_rate": 1.7892826602819882e-06, "loss": 2.9019, "step": 524 }, { "epoch": 1.19, "learning_rate": 1.7874789603060836e-06, "loss": 3.4247, "step": 526 }, { "epoch": 1.19, "learning_rate": 1.785668490869924e-06, "loss": 3.207, "step": 528 }, { "epoch": 1.2, "learning_rate": 1.7838512675369737e-06, "loss": 2.9828, "step": 530 }, { "epoch": 1.2, "learning_rate": 1.7820273059287567e-06, "loss": 3.3176, "step": 532 }, { "epoch": 1.21, "learning_rate": 1.7801966217247206e-06, "loss": 2.8266, "step": 534 }, { "epoch": 1.21, "learning_rate": 1.7783592306621044e-06, "loss": 2.919, "step": 536 }, { "epoch": 1.22, "learning_rate": 1.7765151485358004e-06, "loss": 3.3196, "step": 538 }, { "epoch": 1.22, "learning_rate": 1.7746643911982204e-06, "loss": 3.0448, "step": 540 }, { "epoch": 1.23, "learning_rate": 1.7728069745591583e-06, "loss": 3.0457, "step": 542 }, { "epoch": 1.23, "learning_rate": 1.770942914585655e-06, "loss": 3.576, "step": 544 }, { "epoch": 1.23, "learning_rate": 1.769072227301858e-06, "loss": 2.9104, "step": 546 }, { "epoch": 1.24, "learning_rate": 1.767194928788888e-06, "loss": 3.2746, "step": 548 }, { "epoch": 1.24, "learning_rate": 1.765311035184696e-06, "loss": 3.5344, "step": 550 }, { "epoch": 1.25, "learning_rate": 1.763420562683928e-06, "loss": 3.3503, "step": 552 }, { "epoch": 1.25, "learning_rate": 1.7615235275377851e-06, "loss": 3.1624, "step": 554 }, { "epoch": 1.26, "learning_rate": 1.759619946053882e-06, "loss": 3.0503, "step": 556 }, { "epoch": 1.26, "learning_rate": 1.7577098345961094e-06, "loss": 3.137, "step": 558 }, { "epoch": 1.27, "learning_rate": 1.755793209584491e-06, "loss": 3.1191, "step": 560 }, { "epoch": 1.27, "learning_rate": 1.7538700874950447e-06, "loss": 3.1422, "step": 562 }, { "epoch": 1.28, "learning_rate": 1.7519404848596379e-06, "loss": 3.2557, "step": 564 }, { "epoch": 1.28, "learning_rate": 1.750004418265849e-06, "loss": 2.9908, "step": 566 }, { "epoch": 1.28, "learning_rate": 1.7480619043568217e-06, "loss": 3.674, "step": 568 }, { "epoch": 1.29, "learning_rate": 1.746112959831124e-06, "loss": 3.1564, "step": 570 }, { "epoch": 1.29, "learning_rate": 1.744157601442603e-06, "loss": 3.4259, "step": 572 }, { "epoch": 1.3, "learning_rate": 1.742195846000243e-06, "loss": 3.1509, "step": 574 }, { "epoch": 1.3, "learning_rate": 1.7402277103680185e-06, "loss": 2.959, "step": 576 }, { "epoch": 1.31, "learning_rate": 1.7382532114647508e-06, "loss": 3.0531, "step": 578 }, { "epoch": 1.31, "learning_rate": 1.7362723662639627e-06, "loss": 2.9379, "step": 580 }, { "epoch": 1.32, "learning_rate": 1.734285191793732e-06, "loss": 3.1013, "step": 582 }, { "epoch": 1.32, "learning_rate": 1.7322917051365447e-06, "loss": 3.2695, "step": 584 }, { "epoch": 1.33, "learning_rate": 1.730291923429149e-06, "loss": 3.2645, "step": 586 }, { "epoch": 1.33, "learning_rate": 1.7282858638624082e-06, "loss": 3.549, "step": 588 }, { "epoch": 1.33, "learning_rate": 1.7262735436811514e-06, "loss": 3.1911, "step": 590 }, { "epoch": 1.34, "learning_rate": 1.7242549801840273e-06, "loss": 3.1877, "step": 592 }, { "epoch": 1.34, "learning_rate": 1.7222301907233537e-06, "loss": 2.8169, "step": 594 }, { "epoch": 1.35, "learning_rate": 1.7201991927049689e-06, "loss": 2.8251, "step": 596 }, { "epoch": 1.35, "learning_rate": 1.7181620035880832e-06, "loss": 3.7822, "step": 598 }, { "epoch": 1.36, "learning_rate": 1.7161186408851274e-06, "loss": 2.8952, "step": 600 }, { "epoch": 1.36, "learning_rate": 1.714069122161602e-06, "loss": 2.9431, "step": 602 }, { "epoch": 1.37, "learning_rate": 1.7120134650359285e-06, "loss": 2.9651, "step": 604 }, { "epoch": 1.37, "learning_rate": 1.709951687179295e-06, "loss": 3.0515, "step": 606 }, { "epoch": 1.37, "learning_rate": 1.7078838063155061e-06, "loss": 2.989, "step": 608 }, { "epoch": 1.38, "learning_rate": 1.7058098402208305e-06, "loss": 3.1881, "step": 610 }, { "epoch": 1.38, "learning_rate": 1.703729806723847e-06, "loss": 3.1811, "step": 612 }, { "epoch": 1.39, "learning_rate": 1.7016437237052928e-06, "loss": 3.0997, "step": 614 }, { "epoch": 1.39, "learning_rate": 1.6995516090979084e-06, "loss": 3.0892, "step": 616 }, { "epoch": 1.4, "learning_rate": 1.6974534808862847e-06, "loss": 2.7145, "step": 618 }, { "epoch": 1.4, "learning_rate": 1.6953493571067074e-06, "loss": 3.1671, "step": 620 }, { "epoch": 1.41, "learning_rate": 1.6932392558470022e-06, "loss": 3.1385, "step": 622 }, { "epoch": 1.41, "learning_rate": 1.6911231952463796e-06, "loss": 3.4414, "step": 624 }, { "epoch": 1.42, "learning_rate": 1.6890011934952788e-06, "loss": 3.1059, "step": 626 }, { "epoch": 1.42, "learning_rate": 1.6868732688352112e-06, "loss": 3.0871, "step": 628 }, { "epoch": 1.42, "learning_rate": 1.684739439558604e-06, "loss": 3.5906, "step": 630 }, { "epoch": 1.43, "learning_rate": 1.682599724008643e-06, "loss": 3.2214, "step": 632 }, { "epoch": 1.43, "learning_rate": 1.6804541405791127e-06, "loss": 2.861, "step": 634 }, { "epoch": 1.44, "learning_rate": 1.6783027077142426e-06, "loss": 2.6858, "step": 636 }, { "epoch": 1.44, "learning_rate": 1.6761454439085446e-06, "loss": 3.124, "step": 638 }, { "epoch": 1.45, "learning_rate": 1.6739823677066557e-06, "loss": 3.023, "step": 640 }, { "epoch": 1.45, "learning_rate": 1.6718134977031788e-06, "loss": 2.8426, "step": 642 }, { "epoch": 1.46, "learning_rate": 1.669638852542522e-06, "loss": 2.9067, "step": 644 }, { "epoch": 1.46, "learning_rate": 1.6674584509187393e-06, "loss": 2.7238, "step": 646 }, { "epoch": 1.47, "learning_rate": 1.665272311575369e-06, "loss": 3.4309, "step": 648 }, { "epoch": 1.47, "learning_rate": 1.6630804533052727e-06, "loss": 2.925, "step": 650 }, { "epoch": 1.47, "learning_rate": 1.660882894950475e-06, "loss": 3.4704, "step": 652 }, { "epoch": 1.48, "learning_rate": 1.6586796554019994e-06, "loss": 2.8797, "step": 654 }, { "epoch": 1.48, "learning_rate": 1.6564707535997078e-06, "loss": 2.8973, "step": 656 }, { "epoch": 1.49, "learning_rate": 1.6542562085321365e-06, "loss": 3.5394, "step": 658 }, { "epoch": 1.49, "learning_rate": 1.652036039236334e-06, "loss": 2.6825, "step": 660 }, { "epoch": 1.5, "learning_rate": 1.6498102647976956e-06, "loss": 2.9722, "step": 662 }, { "epoch": 1.5, "learning_rate": 1.6475789043498018e-06, "loss": 3.265, "step": 664 }, { "epoch": 1.51, "learning_rate": 1.6453419770742514e-06, "loss": 2.7527, "step": 666 }, { "epoch": 1.51, "learning_rate": 1.6430995022004987e-06, "loss": 2.9699, "step": 668 }, { "epoch": 1.51, "learning_rate": 1.6408514990056863e-06, "loss": 3.2719, "step": 670 }, { "epoch": 1.52, "learning_rate": 1.638597986814481e-06, "loss": 2.88, "step": 672 }, { "epoch": 1.52, "learning_rate": 1.6363389849989062e-06, "loss": 2.6988, "step": 674 }, { "epoch": 1.53, "learning_rate": 1.6340745129781772e-06, "loss": 2.7853, "step": 676 }, { "epoch": 1.53, "learning_rate": 1.6318045902185325e-06, "loss": 3.0281, "step": 678 }, { "epoch": 1.54, "learning_rate": 1.6295292362330666e-06, "loss": 3.2167, "step": 680 }, { "epoch": 1.54, "learning_rate": 1.6272484705815645e-06, "loss": 2.9943, "step": 682 }, { "epoch": 1.55, "learning_rate": 1.6249623128703304e-06, "loss": 3.1188, "step": 684 }, { "epoch": 1.55, "learning_rate": 1.6226707827520207e-06, "loss": 3.0372, "step": 686 }, { "epoch": 1.56, "learning_rate": 1.620373899925476e-06, "loss": 3.3827, "step": 688 }, { "epoch": 1.56, "learning_rate": 1.6180716841355505e-06, "loss": 3.0925, "step": 690 }, { "epoch": 1.56, "learning_rate": 1.615764155172941e-06, "loss": 2.9955, "step": 692 }, { "epoch": 1.57, "learning_rate": 1.6134513328740206e-06, "loss": 3.1093, "step": 694 }, { "epoch": 1.57, "learning_rate": 1.6111332371206646e-06, "loss": 3.2061, "step": 696 }, { "epoch": 1.58, "learning_rate": 1.6088098878400808e-06, "loss": 2.86, "step": 698 }, { "epoch": 1.58, "learning_rate": 1.6064813050046384e-06, "loss": 3.1753, "step": 700 }, { "epoch": 1.59, "learning_rate": 1.6041475086316964e-06, "loss": 3.0915, "step": 702 }, { "epoch": 1.59, "learning_rate": 1.6018085187834314e-06, "loss": 3.1951, "step": 704 }, { "epoch": 1.6, "learning_rate": 1.5994643555666645e-06, "loss": 2.6908, "step": 706 }, { "epoch": 1.6, "learning_rate": 1.5971150391326894e-06, "loss": 3.5141, "step": 708 }, { "epoch": 1.61, "learning_rate": 1.5947605896770985e-06, "loss": 3.3434, "step": 710 }, { "epoch": 1.61, "learning_rate": 1.5924010274396101e-06, "loss": 2.974, "step": 712 }, { "epoch": 1.61, "learning_rate": 1.590036372703893e-06, "loss": 3.0547, "step": 714 }, { "epoch": 1.62, "learning_rate": 1.5876666457973937e-06, "loss": 2.8732, "step": 716 }, { "epoch": 1.62, "learning_rate": 1.585291867091161e-06, "loss": 2.9996, "step": 718 }, { "epoch": 1.63, "learning_rate": 1.5829120569996702e-06, "loss": 2.5978, "step": 720 }, { "epoch": 1.63, "learning_rate": 1.5805272359806485e-06, "loss": 3.2971, "step": 722 }, { "epoch": 1.64, "learning_rate": 1.5781374245348992e-06, "loss": 3.0118, "step": 724 }, { "epoch": 1.64, "learning_rate": 1.575742643206125e-06, "loss": 2.9805, "step": 726 }, { "epoch": 1.65, "learning_rate": 1.573342912580751e-06, "loss": 2.7381, "step": 728 }, { "epoch": 1.65, "learning_rate": 1.5709382532877498e-06, "loss": 2.9873, "step": 730 }, { "epoch": 1.66, "learning_rate": 1.5685286859984607e-06, "loss": 3.1344, "step": 732 }, { "epoch": 1.66, "learning_rate": 1.5661142314264154e-06, "loss": 2.9644, "step": 734 }, { "epoch": 1.66, "learning_rate": 1.5636949103271575e-06, "loss": 2.8556, "step": 736 }, { "epoch": 1.67, "learning_rate": 1.561270743498066e-06, "loss": 3.1983, "step": 738 }, { "epoch": 1.67, "learning_rate": 1.5588417517781748e-06, "loss": 2.9379, "step": 740 }, { "epoch": 1.68, "learning_rate": 1.5564079560479949e-06, "loss": 3.0293, "step": 742 }, { "epoch": 1.68, "learning_rate": 1.5539693772293336e-06, "loss": 2.9691, "step": 744 }, { "epoch": 1.69, "learning_rate": 1.5515260362851167e-06, "loss": 2.9998, "step": 746 }, { "epoch": 1.69, "learning_rate": 1.5490779542192056e-06, "loss": 2.8059, "step": 748 }, { "epoch": 1.7, "learning_rate": 1.5466251520762193e-06, "loss": 2.7757, "step": 750 }, { "epoch": 1.7, "learning_rate": 1.5441676509413508e-06, "loss": 3.1546, "step": 752 }, { "epoch": 1.7, "learning_rate": 1.5417054719401895e-06, "loss": 2.7844, "step": 754 }, { "epoch": 1.71, "learning_rate": 1.5392386362385355e-06, "loss": 3.0033, "step": 756 }, { "epoch": 1.71, "learning_rate": 1.5367671650422206e-06, "loss": 2.9029, "step": 758 }, { "epoch": 1.72, "learning_rate": 1.534291079596925e-06, "loss": 3.1112, "step": 760 }, { "epoch": 1.72, "learning_rate": 1.5318104011879943e-06, "loss": 3.1761, "step": 762 }, { "epoch": 1.73, "learning_rate": 1.5293251511402576e-06, "loss": 3.182, "step": 764 }, { "epoch": 1.73, "learning_rate": 1.5268353508178423e-06, "loss": 3.4263, "step": 766 }, { "epoch": 1.74, "learning_rate": 1.5243410216239935e-06, "loss": 3.1214, "step": 768 }, { "epoch": 1.74, "learning_rate": 1.521842185000886e-06, "loss": 2.982, "step": 770 }, { "epoch": 1.75, "learning_rate": 1.5193388624294437e-06, "loss": 2.6247, "step": 772 }, { "epoch": 1.75, "learning_rate": 1.5168310754291524e-06, "loss": 2.7246, "step": 774 }, { "epoch": 1.75, "learning_rate": 1.5143188455578768e-06, "loss": 2.7487, "step": 776 }, { "epoch": 1.76, "learning_rate": 1.5118021944116732e-06, "loss": 2.7274, "step": 778 }, { "epoch": 1.76, "learning_rate": 1.5092811436246053e-06, "loss": 3.0194, "step": 780 }, { "epoch": 1.77, "learning_rate": 1.5067557148685577e-06, "loss": 3.18, "step": 782 }, { "epoch": 1.77, "learning_rate": 1.5042259298530495e-06, "loss": 2.7721, "step": 784 }, { "epoch": 1.78, "learning_rate": 1.501691810325048e-06, "loss": 3.1104, "step": 786 }, { "epoch": 1.78, "learning_rate": 1.4991533780687812e-06, "loss": 3.0119, "step": 788 }, { "epoch": 1.79, "learning_rate": 1.4966106549055518e-06, "loss": 2.7858, "step": 790 }, { "epoch": 1.79, "learning_rate": 1.4940636626935473e-06, "loss": 2.9825, "step": 792 }, { "epoch": 1.8, "learning_rate": 1.4915124233276549e-06, "loss": 2.8126, "step": 794 }, { "epoch": 1.8, "learning_rate": 1.4889569587392707e-06, "loss": 2.634, "step": 796 }, { "epoch": 1.8, "learning_rate": 1.4863972908961136e-06, "loss": 2.9189, "step": 798 }, { "epoch": 1.81, "learning_rate": 1.4838334418020345e-06, "loss": 3.2004, "step": 800 }, { "epoch": 1.81, "learning_rate": 1.4812654334968278e-06, "loss": 3.1504, "step": 802 }, { "epoch": 1.82, "learning_rate": 1.4786932880560424e-06, "loss": 3.1554, "step": 804 }, { "epoch": 1.82, "learning_rate": 1.4761170275907913e-06, "loss": 2.8328, "step": 806 }, { "epoch": 1.83, "learning_rate": 1.473536674247562e-06, "loss": 3.0234, "step": 808 }, { "epoch": 1.83, "learning_rate": 1.4709522502080253e-06, "loss": 2.8962, "step": 810 }, { "epoch": 1.84, "learning_rate": 1.4683637776888461e-06, "loss": 2.9613, "step": 812 }, { "epoch": 1.84, "learning_rate": 1.465771278941491e-06, "loss": 3.1268, "step": 814 }, { "epoch": 1.85, "learning_rate": 1.4631747762520374e-06, "loss": 3.1406, "step": 816 }, { "epoch": 1.85, "learning_rate": 1.4605742919409827e-06, "loss": 3.1191, "step": 818 }, { "epoch": 1.85, "learning_rate": 1.4579698483630508e-06, "loss": 2.9212, "step": 820 }, { "epoch": 1.86, "learning_rate": 1.4553614679070018e-06, "loss": 2.8084, "step": 822 }, { "epoch": 1.86, "learning_rate": 1.4527491729954384e-06, "loss": 2.7168, "step": 824 }, { "epoch": 1.87, "learning_rate": 1.4501329860846134e-06, "loss": 3.2382, "step": 826 }, { "epoch": 1.87, "learning_rate": 1.4475129296642364e-06, "loss": 3.2147, "step": 828 }, { "epoch": 1.88, "learning_rate": 1.444889026257281e-06, "loss": 3.1521, "step": 830 }, { "epoch": 1.88, "learning_rate": 1.4422612984197914e-06, "loss": 3.2244, "step": 832 }, { "epoch": 1.89, "learning_rate": 1.4396297687406864e-06, "loss": 3.104, "step": 834 }, { "epoch": 1.89, "learning_rate": 1.436994459841569e-06, "loss": 2.8863, "step": 836 }, { "epoch": 1.89, "learning_rate": 1.4343553943765283e-06, "loss": 2.8873, "step": 838 }, { "epoch": 1.9, "learning_rate": 1.431712595031947e-06, "loss": 2.8483, "step": 840 }, { "epoch": 1.9, "learning_rate": 1.4290660845263044e-06, "loss": 2.991, "step": 842 }, { "epoch": 1.91, "learning_rate": 1.426415885609984e-06, "loss": 3.0173, "step": 844 }, { "epoch": 1.91, "learning_rate": 1.4237620210650748e-06, "loss": 2.9983, "step": 846 }, { "epoch": 1.92, "learning_rate": 1.4211045137051778e-06, "loss": 3.4527, "step": 848 }, { "epoch": 1.92, "learning_rate": 1.4184433863752086e-06, "loss": 2.9962, "step": 850 }, { "epoch": 1.93, "learning_rate": 1.4157786619512015e-06, "loss": 2.8991, "step": 852 }, { "epoch": 1.93, "learning_rate": 1.413110363340113e-06, "loss": 3.0066, "step": 854 }, { "epoch": 1.94, "learning_rate": 1.4104385134796239e-06, "loss": 3.1625, "step": 856 }, { "epoch": 1.94, "learning_rate": 1.407763135337944e-06, "loss": 3.1423, "step": 858 }, { "epoch": 1.94, "learning_rate": 1.405084251913612e-06, "loss": 3.1875, "step": 860 }, { "epoch": 1.95, "learning_rate": 1.4024018862353004e-06, "loss": 3.1666, "step": 862 }, { "epoch": 1.95, "learning_rate": 1.3997160613616166e-06, "loss": 2.7344, "step": 864 }, { "epoch": 1.96, "learning_rate": 1.3970268003809037e-06, "loss": 3.0386, "step": 866 }, { "epoch": 1.96, "learning_rate": 1.3943341264110431e-06, "loss": 3.0802, "step": 868 }, { "epoch": 1.97, "learning_rate": 1.391638062599256e-06, "loss": 2.8641, "step": 870 }, { "epoch": 1.97, "learning_rate": 1.3889386321219036e-06, "loss": 2.6548, "step": 872 }, { "epoch": 1.98, "learning_rate": 1.3862358581842881e-06, "loss": 2.7543, "step": 874 }, { "epoch": 1.98, "learning_rate": 1.3835297640204535e-06, "loss": 2.8009, "step": 876 }, { "epoch": 1.99, "learning_rate": 1.3808203728929853e-06, "loss": 2.7519, "step": 878 }, { "epoch": 1.99, "learning_rate": 1.378107708092812e-06, "loss": 2.8885, "step": 880 }, { "epoch": 1.99, "learning_rate": 1.3753917929390017e-06, "loss": 3.0521, "step": 882 }, { "epoch": 2.0, "learning_rate": 1.3726726507785663e-06, "loss": 3.3975, "step": 884 }, { "epoch": 2.0, "learning_rate": 1.3699503049862563e-06, "loss": 2.7805, "step": 886 }, { "epoch": 2.01, "learning_rate": 1.3672247789643632e-06, "loss": 2.9564, "step": 888 }, { "epoch": 2.01, "learning_rate": 1.3644960961425157e-06, "loss": 2.7772, "step": 890 }, { "epoch": 2.02, "learning_rate": 1.36176427997748e-06, "loss": 3.1836, "step": 892 }, { "epoch": 2.02, "learning_rate": 1.3590293539529581e-06, "loss": 3.0701, "step": 894 }, { "epoch": 2.03, "learning_rate": 1.3562913415793848e-06, "loss": 2.9681, "step": 896 }, { "epoch": 2.03, "learning_rate": 1.3535502663937272e-06, "loss": 2.9341, "step": 898 }, { "epoch": 2.04, "learning_rate": 1.35080615195928e-06, "loss": 3.2534, "step": 900 }, { "epoch": 2.04, "learning_rate": 1.3480590218654665e-06, "loss": 2.7241, "step": 902 }, { "epoch": 2.04, "learning_rate": 1.3453088997276314e-06, "loss": 2.6314, "step": 904 }, { "epoch": 2.05, "learning_rate": 1.3425558091868419e-06, "loss": 3.1443, "step": 906 }, { "epoch": 2.05, "learning_rate": 1.3397997739096818e-06, "loss": 3.0952, "step": 908 }, { "epoch": 2.06, "learning_rate": 1.3370408175880492e-06, "loss": 2.7361, "step": 910 }, { "epoch": 2.06, "learning_rate": 1.3342789639389529e-06, "loss": 2.9146, "step": 912 }, { "epoch": 2.07, "learning_rate": 1.3315142367043075e-06, "loss": 2.9966, "step": 914 }, { "epoch": 2.07, "learning_rate": 1.3287466596507303e-06, "loss": 3.0012, "step": 916 }, { "epoch": 2.08, "learning_rate": 1.3259762565693372e-06, "loss": 2.7587, "step": 918 }, { "epoch": 2.08, "learning_rate": 1.3232030512755363e-06, "loss": 3.2964, "step": 920 }, { "epoch": 2.08, "learning_rate": 1.3204270676088267e-06, "loss": 2.5617, "step": 922 }, { "epoch": 2.09, "learning_rate": 1.3176483294325892e-06, "loss": 2.9865, "step": 924 }, { "epoch": 2.09, "learning_rate": 1.3148668606338855e-06, "loss": 3.1165, "step": 926 }, { "epoch": 2.1, "learning_rate": 1.3120826851232485e-06, "loss": 2.9653, "step": 928 }, { "epoch": 2.1, "learning_rate": 1.309295826834481e-06, "loss": 3.2534, "step": 930 }, { "epoch": 2.11, "learning_rate": 1.3065063097244461e-06, "loss": 2.7433, "step": 932 }, { "epoch": 2.11, "learning_rate": 1.3037141577728652e-06, "loss": 3.1489, "step": 934 }, { "epoch": 2.12, "learning_rate": 1.300919394982108e-06, "loss": 2.7699, "step": 936 }, { "epoch": 2.12, "learning_rate": 1.2981220453769887e-06, "loss": 3.0569, "step": 938 }, { "epoch": 2.13, "learning_rate": 1.295322133004559e-06, "loss": 3.0079, "step": 940 }, { "epoch": 2.13, "learning_rate": 1.2925196819339e-06, "loss": 2.951, "step": 942 }, { "epoch": 2.13, "learning_rate": 1.2897147162559178e-06, "loss": 2.4466, "step": 944 }, { "epoch": 2.14, "learning_rate": 1.286907260083134e-06, "loss": 2.9399, "step": 946 }, { "epoch": 2.14, "learning_rate": 1.2840973375494795e-06, "loss": 3.011, "step": 948 }, { "epoch": 2.15, "learning_rate": 1.2812849728100873e-06, "loss": 3.3986, "step": 950 }, { "epoch": 2.15, "learning_rate": 1.2784701900410851e-06, "loss": 2.5518, "step": 952 }, { "epoch": 2.16, "learning_rate": 1.2756530134393848e-06, "loss": 3.1175, "step": 954 }, { "epoch": 2.16, "learning_rate": 1.2728334672224788e-06, "loss": 3.2315, "step": 956 }, { "epoch": 2.17, "learning_rate": 1.2700115756282285e-06, "loss": 2.8895, "step": 958 }, { "epoch": 2.17, "learning_rate": 1.2671873629146573e-06, "loss": 3.0108, "step": 960 }, { "epoch": 2.18, "learning_rate": 1.2643608533597416e-06, "loss": 2.9859, "step": 962 }, { "epoch": 2.18, "learning_rate": 1.2615320712612026e-06, "loss": 2.5764, "step": 964 }, { "epoch": 2.18, "learning_rate": 1.2587010409362967e-06, "loss": 2.6289, "step": 966 }, { "epoch": 2.19, "learning_rate": 1.2558677867216072e-06, "loss": 2.4742, "step": 968 }, { "epoch": 2.19, "learning_rate": 1.2530323329728352e-06, "loss": 2.9857, "step": 970 }, { "epoch": 2.2, "learning_rate": 1.2501947040645883e-06, "loss": 2.7427, "step": 972 }, { "epoch": 2.2, "learning_rate": 1.2473549243901744e-06, "loss": 3.3442, "step": 974 }, { "epoch": 2.21, "learning_rate": 1.2445130183613897e-06, "loss": 3.2576, "step": 976 }, { "epoch": 2.21, "learning_rate": 1.241669010408308e-06, "loss": 3.4891, "step": 978 }, { "epoch": 2.22, "learning_rate": 1.2388229249790736e-06, "loss": 2.5758, "step": 980 }, { "epoch": 2.22, "learning_rate": 1.235974786539689e-06, "loss": 2.9928, "step": 982 }, { "epoch": 2.22, "learning_rate": 1.2331246195738053e-06, "loss": 3.2582, "step": 984 }, { "epoch": 2.23, "learning_rate": 1.2302724485825104e-06, "loss": 2.8876, "step": 986 }, { "epoch": 2.23, "learning_rate": 1.227418298084122e-06, "loss": 2.8763, "step": 988 }, { "epoch": 2.24, "learning_rate": 1.2245621926139716e-06, "loss": 2.6262, "step": 990 }, { "epoch": 2.24, "learning_rate": 1.221704156724198e-06, "loss": 3.024, "step": 992 }, { "epoch": 2.25, "learning_rate": 1.218844214983535e-06, "loss": 3.1893, "step": 994 }, { "epoch": 2.25, "learning_rate": 1.215982391977098e-06, "loss": 2.5119, "step": 996 }, { "epoch": 2.26, "learning_rate": 1.2131187123061766e-06, "loss": 2.9757, "step": 998 }, { "epoch": 2.26, "learning_rate": 1.2102532005880189e-06, "loss": 2.8571, "step": 1000 }, { "epoch": 2.27, "learning_rate": 1.2073858814556235e-06, "loss": 3.1847, "step": 1002 }, { "epoch": 2.27, "learning_rate": 1.204516779557525e-06, "loss": 2.8061, "step": 1004 }, { "epoch": 2.27, "learning_rate": 1.201645919557585e-06, "loss": 2.9262, "step": 1006 }, { "epoch": 2.28, "learning_rate": 1.1987733261347764e-06, "loss": 2.7418, "step": 1008 }, { "epoch": 2.28, "learning_rate": 1.1958990239829745e-06, "loss": 3.0034, "step": 1010 }, { "epoch": 2.29, "learning_rate": 1.1930230378107434e-06, "loss": 2.5847, "step": 1012 }, { "epoch": 2.29, "learning_rate": 1.1901453923411234e-06, "loss": 2.9149, "step": 1014 }, { "epoch": 2.3, "learning_rate": 1.1872661123114182e-06, "loss": 2.7005, "step": 1016 }, { "epoch": 2.3, "learning_rate": 1.184385222472984e-06, "loss": 2.8502, "step": 1018 }, { "epoch": 2.31, "learning_rate": 1.1815027475910146e-06, "loss": 3.0551, "step": 1020 }, { "epoch": 2.31, "learning_rate": 1.1786187124443297e-06, "loss": 3.2617, "step": 1022 }, { "epoch": 2.32, "learning_rate": 1.1757331418251616e-06, "loss": 2.826, "step": 1024 }, { "epoch": 2.32, "learning_rate": 1.1728460605389417e-06, "loss": 3.0789, "step": 1026 }, { "epoch": 2.32, "learning_rate": 1.1699574934040884e-06, "loss": 2.7854, "step": 1028 }, { "epoch": 2.33, "learning_rate": 1.1670674652517925e-06, "loss": 3.1996, "step": 1030 }, { "epoch": 2.33, "learning_rate": 1.1641760009258047e-06, "loss": 2.8062, "step": 1032 }, { "epoch": 2.34, "learning_rate": 1.1612831252822207e-06, "loss": 3.1246, "step": 1034 }, { "epoch": 2.34, "learning_rate": 1.1583888631892692e-06, "loss": 3.0461, "step": 1036 }, { "epoch": 2.35, "learning_rate": 1.1554932395270973e-06, "loss": 3.2731, "step": 1038 }, { "epoch": 2.35, "learning_rate": 1.1525962791875561e-06, "loss": 2.8905, "step": 1040 }, { "epoch": 2.36, "learning_rate": 1.1496980070739882e-06, "loss": 2.8582, "step": 1042 }, { "epoch": 2.36, "learning_rate": 1.146798448101011e-06, "loss": 2.8488, "step": 1044 }, { "epoch": 2.37, "learning_rate": 1.1438976271943065e-06, "loss": 3.0372, "step": 1046 }, { "epoch": 2.37, "learning_rate": 1.140995569290403e-06, "loss": 2.7814, "step": 1048 }, { "epoch": 2.37, "learning_rate": 1.1380922993364634e-06, "loss": 2.767, "step": 1050 }, { "epoch": 2.38, "learning_rate": 1.1351878422900689e-06, "loss": 2.6881, "step": 1052 }, { "epoch": 2.38, "learning_rate": 1.1322822231190064e-06, "loss": 3.0476, "step": 1054 }, { "epoch": 2.39, "learning_rate": 1.1293754668010525e-06, "loss": 3.0044, "step": 1056 }, { "epoch": 2.39, "learning_rate": 1.1264675983237588e-06, "loss": 2.9124, "step": 1058 }, { "epoch": 2.4, "learning_rate": 1.1235586426842381e-06, "loss": 2.7616, "step": 1060 }, { "epoch": 2.4, "learning_rate": 1.1206486248889476e-06, "loss": 3.0564, "step": 1062 }, { "epoch": 2.41, "learning_rate": 1.1177375699534772e-06, "loss": 2.749, "step": 1064 }, { "epoch": 2.41, "learning_rate": 1.1148255029023305e-06, "loss": 2.7536, "step": 1066 }, { "epoch": 2.41, "learning_rate": 1.1119124487687126e-06, "loss": 2.9939, "step": 1068 }, { "epoch": 2.42, "learning_rate": 1.1089984325943138e-06, "loss": 2.461, "step": 1070 }, { "epoch": 2.42, "learning_rate": 1.1060834794290942e-06, "loss": 2.9466, "step": 1072 }, { "epoch": 2.43, "learning_rate": 1.1031676143310689e-06, "loss": 2.7418, "step": 1074 }, { "epoch": 2.43, "learning_rate": 1.100250862366092e-06, "loss": 2.5268, "step": 1076 }, { "epoch": 2.44, "learning_rate": 1.0973332486076421e-06, "loss": 2.8977, "step": 1078 }, { "epoch": 2.44, "learning_rate": 1.0944147981366052e-06, "loss": 3.162, "step": 1080 }, { "epoch": 2.45, "learning_rate": 1.0914955360410607e-06, "loss": 3.0853, "step": 1082 }, { "epoch": 2.45, "learning_rate": 1.0885754874160647e-06, "loss": 2.723, "step": 1084 }, { "epoch": 2.46, "learning_rate": 1.0856546773634346e-06, "loss": 2.9771, "step": 1086 }, { "epoch": 2.46, "learning_rate": 1.082733130991533e-06, "loss": 2.6165, "step": 1088 }, { "epoch": 2.46, "learning_rate": 1.0798108734150533e-06, "loss": 2.7038, "step": 1090 }, { "epoch": 2.47, "learning_rate": 1.0768879297548016e-06, "loss": 2.7173, "step": 1092 }, { "epoch": 2.47, "learning_rate": 1.073964325137482e-06, "loss": 2.5754, "step": 1094 }, { "epoch": 2.48, "learning_rate": 1.0710400846954809e-06, "loss": 2.9935, "step": 1096 }, { "epoch": 2.48, "learning_rate": 1.0681152335666492e-06, "loss": 3.0974, "step": 1098 }, { "epoch": 2.49, "learning_rate": 1.0651897968940899e-06, "loss": 2.988, "step": 1100 }, { "epoch": 2.49, "learning_rate": 1.062263799825937e-06, "loss": 3.1065, "step": 1102 }, { "epoch": 2.5, "learning_rate": 1.0593372675151436e-06, "loss": 3.1001, "step": 1104 }, { "epoch": 2.5, "learning_rate": 1.0564102251192628e-06, "loss": 2.9429, "step": 1106 }, { "epoch": 2.51, "learning_rate": 1.0534826978002333e-06, "loss": 3.0176, "step": 1108 }, { "epoch": 2.51, "learning_rate": 1.0505547107241625e-06, "loss": 2.95, "step": 1110 }, { "epoch": 2.51, "learning_rate": 1.0476262890611093e-06, "loss": 2.6614, "step": 1112 }, { "epoch": 2.52, "learning_rate": 1.0446974579848693e-06, "loss": 3.1559, "step": 1114 }, { "epoch": 2.52, "learning_rate": 1.0417682426727565e-06, "loss": 2.8184, "step": 1116 }, { "epoch": 2.53, "learning_rate": 1.0388386683053895e-06, "loss": 2.7238, "step": 1118 }, { "epoch": 2.53, "learning_rate": 1.0359087600664712e-06, "loss": 2.7008, "step": 1120 }, { "epoch": 2.54, "learning_rate": 1.0329785431425773e-06, "loss": 2.895, "step": 1122 }, { "epoch": 2.54, "learning_rate": 1.030048042722935e-06, "loss": 2.7421, "step": 1124 }, { "epoch": 2.55, "learning_rate": 1.0271172839992092e-06, "loss": 2.6903, "step": 1126 }, { "epoch": 2.55, "learning_rate": 1.0241862921652859e-06, "loss": 2.9545, "step": 1128 }, { "epoch": 2.56, "learning_rate": 1.0212550924170538e-06, "loss": 3.4199, "step": 1130 }, { "epoch": 2.56, "learning_rate": 1.01832370995219e-06, "loss": 2.7924, "step": 1132 }, { "epoch": 2.56, "learning_rate": 1.0153921699699416e-06, "loss": 2.6713, "step": 1134 }, { "epoch": 2.57, "learning_rate": 1.0124604976709098e-06, "loss": 3.0744, "step": 1136 }, { "epoch": 2.57, "learning_rate": 1.0095287182568338e-06, "loss": 2.9019, "step": 1138 }, { "epoch": 2.58, "learning_rate": 1.0065968569303732e-06, "loss": 3.0902, "step": 1140 }, { "epoch": 2.58, "learning_rate": 1.0036649388948915e-06, "loss": 3.0283, "step": 1142 }, { "epoch": 2.59, "learning_rate": 1.0007329893542401e-06, "loss": 2.6646, "step": 1144 }, { "epoch": 2.59, "learning_rate": 9.978010335125418e-07, "loss": 2.8361, "step": 1146 }, { "epoch": 2.6, "learning_rate": 9.948690965739719e-07, "loss": 3.0105, "step": 1148 }, { "epoch": 2.6, "learning_rate": 9.919372037425448e-07, "loss": 3.2998, "step": 1150 }, { "epoch": 2.6, "learning_rate": 9.89005380221895e-07, "loss": 2.6464, "step": 1152 }, { "epoch": 2.61, "learning_rate": 9.860736512150612e-07, "loss": 2.997, "step": 1154 }, { "epoch": 2.61, "learning_rate": 9.831420419242695e-07, "loss": 2.42, "step": 1156 }, { "epoch": 2.62, "learning_rate": 9.802105775507176e-07, "loss": 2.682, "step": 1158 }, { "epoch": 2.62, "learning_rate": 9.772792832943572e-07, "loss": 3.0499, "step": 1160 }, { "epoch": 2.63, "learning_rate": 9.743481843536763e-07, "loss": 2.7949, "step": 1162 }, { "epoch": 2.63, "learning_rate": 9.71417305925486e-07, "loss": 2.8605, "step": 1164 }, { "epoch": 2.64, "learning_rate": 9.684866732046999e-07, "loss": 2.6879, "step": 1166 }, { "epoch": 2.64, "learning_rate": 9.65556311384121e-07, "loss": 3.1393, "step": 1168 }, { "epoch": 2.65, "learning_rate": 9.626262456542221e-07, "loss": 3.2325, "step": 1170 }, { "epoch": 2.65, "learning_rate": 9.596965012029322e-07, "loss": 2.9502, "step": 1172 }, { "epoch": 2.65, "learning_rate": 9.567671032154167e-07, "loss": 2.6999, "step": 1174 }, { "epoch": 2.66, "learning_rate": 9.538380768738643e-07, "loss": 2.7066, "step": 1176 }, { "epoch": 2.66, "learning_rate": 9.509094473572684e-07, "loss": 3.2916, "step": 1178 }, { "epoch": 2.67, "learning_rate": 9.479812398412102e-07, "loss": 3.0087, "step": 1180 }, { "epoch": 2.67, "learning_rate": 9.450534794976447e-07, "loss": 3.0141, "step": 1182 }, { "epoch": 2.68, "learning_rate": 9.421261914946818e-07, "loss": 2.9588, "step": 1184 }, { "epoch": 2.68, "learning_rate": 9.391994009963715e-07, "loss": 2.6658, "step": 1186 }, { "epoch": 2.69, "learning_rate": 9.362731331624865e-07, "loss": 3.3134, "step": 1188 }, { "epoch": 2.69, "learning_rate": 9.333474131483075e-07, "loss": 3.1166, "step": 1190 }, { "epoch": 2.7, "learning_rate": 9.304222661044046e-07, "loss": 2.9513, "step": 1192 }, { "epoch": 2.7, "learning_rate": 9.274977171764235e-07, "loss": 2.7799, "step": 1194 }, { "epoch": 2.7, "learning_rate": 9.245737915048683e-07, "loss": 2.6805, "step": 1196 }, { "epoch": 2.71, "learning_rate": 9.216505142248842e-07, "loss": 3.2019, "step": 1198 }, { "epoch": 2.71, "learning_rate": 9.187279104660441e-07, "loss": 3.1596, "step": 1200 }, { "epoch": 2.72, "learning_rate": 9.158060053521299e-07, "loss": 3.0177, "step": 1202 }, { "epoch": 2.72, "learning_rate": 9.128848240009182e-07, "loss": 2.9292, "step": 1204 }, { "epoch": 2.73, "learning_rate": 9.099643915239636e-07, "loss": 3.2616, "step": 1206 }, { "epoch": 2.73, "learning_rate": 9.070447330263837e-07, "loss": 3.1557, "step": 1208 }, { "epoch": 2.74, "learning_rate": 9.041258736066419e-07, "loss": 3.0772, "step": 1210 }, { "epoch": 2.74, "learning_rate": 9.012078383563331e-07, "loss": 2.9273, "step": 1212 }, { "epoch": 2.75, "learning_rate": 8.98290652359967e-07, "loss": 3.0041, "step": 1214 }, { "epoch": 2.75, "learning_rate": 8.953743406947524e-07, "loss": 2.8386, "step": 1216 }, { "epoch": 2.75, "learning_rate": 8.924589284303833e-07, "loss": 2.7779, "step": 1218 }, { "epoch": 2.76, "learning_rate": 8.895444406288204e-07, "loss": 3.1077, "step": 1220 }, { "epoch": 2.76, "learning_rate": 8.86630902344079e-07, "loss": 2.7719, "step": 1222 }, { "epoch": 2.77, "learning_rate": 8.837183386220105e-07, "loss": 2.9666, "step": 1224 }, { "epoch": 2.77, "learning_rate": 8.808067745000901e-07, "loss": 3.1377, "step": 1226 }, { "epoch": 2.78, "learning_rate": 8.778962350071989e-07, "loss": 2.6671, "step": 1228 }, { "epoch": 2.78, "learning_rate": 8.749867451634103e-07, "loss": 3.3089, "step": 1230 }, { "epoch": 2.79, "learning_rate": 8.720783299797749e-07, "loss": 2.7018, "step": 1232 }, { "epoch": 2.79, "learning_rate": 8.691710144581045e-07, "loss": 3.1339, "step": 1234 }, { "epoch": 2.79, "learning_rate": 8.662648235907583e-07, "loss": 2.9497, "step": 1236 }, { "epoch": 2.8, "learning_rate": 8.633597823604271e-07, "loss": 3.0274, "step": 1238 }, { "epoch": 2.8, "learning_rate": 8.604559157399196e-07, "loss": 3.2419, "step": 1240 }, { "epoch": 2.81, "learning_rate": 8.575532486919463e-07, "loss": 2.959, "step": 1242 }, { "epoch": 2.81, "learning_rate": 8.546518061689066e-07, "loss": 3.0502, "step": 1244 }, { "epoch": 2.82, "learning_rate": 8.517516131126726e-07, "loss": 2.9865, "step": 1246 }, { "epoch": 2.82, "learning_rate": 8.488526944543763e-07, "loss": 3.1317, "step": 1248 }, { "epoch": 2.83, "learning_rate": 8.459550751141941e-07, "loss": 3.058, "step": 1250 }, { "epoch": 2.83, "learning_rate": 8.430587800011329e-07, "loss": 3.0949, "step": 1252 }, { "epoch": 2.84, "learning_rate": 8.401638340128166e-07, "loss": 2.4696, "step": 1254 }, { "epoch": 2.84, "learning_rate": 8.372702620352703e-07, "loss": 2.5343, "step": 1256 }, { "epoch": 2.84, "learning_rate": 8.343780889427091e-07, "loss": 2.4664, "step": 1258 }, { "epoch": 2.85, "learning_rate": 8.314873395973217e-07, "loss": 3.148, "step": 1260 }, { "epoch": 2.85, "learning_rate": 8.285980388490585e-07, "loss": 2.8745, "step": 1262 }, { "epoch": 2.86, "learning_rate": 8.257102115354163e-07, "loss": 3.0458, "step": 1264 }, { "epoch": 2.86, "learning_rate": 8.228238824812266e-07, "loss": 2.8101, "step": 1266 }, { "epoch": 2.87, "learning_rate": 8.19939076498441e-07, "loss": 2.8935, "step": 1268 }, { "epoch": 2.87, "learning_rate": 8.170558183859181e-07, "loss": 2.6005, "step": 1270 }, { "epoch": 2.88, "learning_rate": 8.141741329292104e-07, "loss": 2.9618, "step": 1272 }, { "epoch": 2.88, "learning_rate": 8.112940449003515e-07, "loss": 2.8762, "step": 1274 }, { "epoch": 2.89, "learning_rate": 8.084155790576427e-07, "loss": 3.0862, "step": 1276 }, { "epoch": 2.89, "learning_rate": 8.055387601454407e-07, "loss": 3.0238, "step": 1278 }, { "epoch": 2.89, "learning_rate": 8.026636128939442e-07, "loss": 2.9851, "step": 1280 }, { "epoch": 2.9, "learning_rate": 7.997901620189815e-07, "loss": 2.6715, "step": 1282 }, { "epoch": 2.9, "learning_rate": 7.96918432221799e-07, "loss": 2.7081, "step": 1284 }, { "epoch": 2.91, "learning_rate": 7.940484481888477e-07, "loss": 2.7954, "step": 1286 }, { "epoch": 2.91, "learning_rate": 7.911802345915711e-07, "loss": 3.0421, "step": 1288 }, { "epoch": 2.92, "learning_rate": 7.883138160861938e-07, "loss": 2.7387, "step": 1290 }, { "epoch": 2.92, "learning_rate": 7.854492173135087e-07, "loss": 2.9555, "step": 1292 }, { "epoch": 2.93, "learning_rate": 7.825864628986659e-07, "loss": 2.66, "step": 1294 }, { "epoch": 2.93, "learning_rate": 7.797255774509606e-07, "loss": 3.3273, "step": 1296 }, { "epoch": 2.93, "learning_rate": 7.768665855636218e-07, "loss": 2.3258, "step": 1298 }, { "epoch": 2.94, "learning_rate": 7.740095118136007e-07, "loss": 2.7619, "step": 1300 }, { "epoch": 2.94, "learning_rate": 7.711543807613591e-07, "loss": 2.8864, "step": 1302 }, { "epoch": 2.95, "learning_rate": 7.683012169506597e-07, "loss": 2.7459, "step": 1304 }, { "epoch": 2.95, "learning_rate": 7.654500449083525e-07, "loss": 2.7373, "step": 1306 }, { "epoch": 2.96, "learning_rate": 7.626008891441671e-07, "loss": 2.9385, "step": 1308 }, { "epoch": 2.96, "learning_rate": 7.597537741504994e-07, "loss": 2.9396, "step": 1310 }, { "epoch": 2.97, "learning_rate": 7.569087244022025e-07, "loss": 2.7592, "step": 1312 }, { "epoch": 2.97, "learning_rate": 7.540657643563755e-07, "loss": 2.8496, "step": 1314 }, { "epoch": 2.98, "learning_rate": 7.512249184521543e-07, "loss": 2.5767, "step": 1316 }, { "epoch": 2.98, "learning_rate": 7.483862111105002e-07, "loss": 3.4805, "step": 1318 }, { "epoch": 2.98, "learning_rate": 7.45549666733991e-07, "loss": 3.045, "step": 1320 }, { "epoch": 2.99, "learning_rate": 7.42715309706611e-07, "loss": 2.9565, "step": 1322 }, { "epoch": 2.99, "learning_rate": 7.398831643935406e-07, "loss": 2.7017, "step": 1324 }, { "epoch": 3.0, "learning_rate": 7.370532551409485e-07, "loss": 2.8842, "step": 1326 }, { "epoch": 3.0, "learning_rate": 7.342256062757799e-07, "loss": 3.4756, "step": 1328 }, { "epoch": 3.01, "learning_rate": 7.314002421055505e-07, "loss": 2.774, "step": 1330 }, { "epoch": 3.01, "learning_rate": 7.285771869181347e-07, "loss": 2.7775, "step": 1332 }, { "epoch": 3.02, "learning_rate": 7.257564649815591e-07, "loss": 2.8437, "step": 1334 }, { "epoch": 3.02, "learning_rate": 7.229381005437916e-07, "loss": 2.8976, "step": 1336 }, { "epoch": 3.03, "learning_rate": 7.20122117832535e-07, "loss": 2.8491, "step": 1338 }, { "epoch": 3.03, "learning_rate": 7.173085410550179e-07, "loss": 2.9297, "step": 1340 }, { "epoch": 3.03, "learning_rate": 7.144973943977859e-07, "loss": 2.5881, "step": 1342 }, { "epoch": 3.04, "learning_rate": 7.116887020264956e-07, "loss": 3.0427, "step": 1344 }, { "epoch": 3.04, "learning_rate": 7.088824880857043e-07, "loss": 3.2461, "step": 1346 }, { "epoch": 3.05, "learning_rate": 7.060787766986646e-07, "loss": 3.1212, "step": 1348 }, { "epoch": 3.05, "learning_rate": 7.032775919671161e-07, "loss": 3.1453, "step": 1350 }, { "epoch": 3.06, "learning_rate": 7.004789579710786e-07, "loss": 2.7477, "step": 1352 }, { "epoch": 3.06, "learning_rate": 6.976828987686439e-07, "loss": 3.359, "step": 1354 }, { "epoch": 3.07, "learning_rate": 6.948894383957708e-07, "loss": 2.9923, "step": 1356 }, { "epoch": 3.07, "learning_rate": 6.920986008660776e-07, "loss": 2.964, "step": 1358 }, { "epoch": 3.08, "learning_rate": 6.89310410170635e-07, "loss": 2.7211, "step": 1360 }, { "epoch": 3.08, "learning_rate": 6.865248902777614e-07, "loss": 2.9151, "step": 1362 }, { "epoch": 3.08, "learning_rate": 6.83742065132815e-07, "loss": 3.0861, "step": 1364 }, { "epoch": 3.09, "learning_rate": 6.8096195865799e-07, "loss": 2.9508, "step": 1366 }, { "epoch": 3.09, "learning_rate": 6.78184594752109e-07, "loss": 2.9543, "step": 1368 }, { "epoch": 3.1, "learning_rate": 6.75409997290419e-07, "loss": 3.2212, "step": 1370 }, { "epoch": 3.1, "learning_rate": 6.726381901243856e-07, "loss": 3.0979, "step": 1372 }, { "epoch": 3.11, "learning_rate": 6.698691970814877e-07, "loss": 2.584, "step": 1374 }, { "epoch": 3.11, "learning_rate": 6.671030419650135e-07, "loss": 2.9239, "step": 1376 }, { "epoch": 3.12, "learning_rate": 6.643397485538542e-07, "loss": 2.7375, "step": 1378 }, { "epoch": 3.12, "learning_rate": 6.615793406023024e-07, "loss": 2.7545, "step": 1380 }, { "epoch": 3.12, "learning_rate": 6.588218418398447e-07, "loss": 2.8863, "step": 1382 }, { "epoch": 3.13, "learning_rate": 6.5606727597096e-07, "loss": 2.9359, "step": 1384 }, { "epoch": 3.13, "learning_rate": 6.533156666749149e-07, "loss": 2.8601, "step": 1386 }, { "epoch": 3.14, "learning_rate": 6.505670376055601e-07, "loss": 2.9439, "step": 1388 }, { "epoch": 3.14, "learning_rate": 6.478214123911267e-07, "loss": 2.4303, "step": 1390 }, { "epoch": 3.15, "learning_rate": 6.450788146340247e-07, "loss": 3.0653, "step": 1392 }, { "epoch": 3.15, "learning_rate": 6.423392679106384e-07, "loss": 2.8843, "step": 1394 }, { "epoch": 3.16, "learning_rate": 6.396027957711233e-07, "loss": 2.8514, "step": 1396 }, { "epoch": 3.16, "learning_rate": 6.368694217392063e-07, "loss": 2.9471, "step": 1398 }, { "epoch": 3.17, "learning_rate": 6.341391693119806e-07, "loss": 2.9424, "step": 1400 }, { "epoch": 3.17, "learning_rate": 6.314120619597058e-07, "loss": 2.6701, "step": 1402 }, { "epoch": 3.17, "learning_rate": 6.286881231256046e-07, "loss": 2.8001, "step": 1404 }, { "epoch": 3.18, "learning_rate": 6.25967376225662e-07, "loss": 3.3145, "step": 1406 }, { "epoch": 3.18, "learning_rate": 6.232498446484246e-07, "loss": 2.6981, "step": 1408 }, { "epoch": 3.19, "learning_rate": 6.205355517547979e-07, "loss": 2.8041, "step": 1410 }, { "epoch": 3.19, "learning_rate": 6.178245208778476e-07, "loss": 3.2282, "step": 1412 }, { "epoch": 3.2, "learning_rate": 6.151167753225968e-07, "loss": 2.525, "step": 1414 }, { "epoch": 3.2, "learning_rate": 6.124123383658275e-07, "loss": 2.7799, "step": 1416 }, { "epoch": 3.21, "learning_rate": 6.097112332558798e-07, "loss": 3.002, "step": 1418 }, { "epoch": 3.21, "learning_rate": 6.070134832124514e-07, "loss": 2.9979, "step": 1420 }, { "epoch": 3.22, "learning_rate": 6.04319111426399e-07, "loss": 2.7198, "step": 1422 }, { "epoch": 3.22, "learning_rate": 6.016281410595389e-07, "loss": 2.9849, "step": 1424 }, { "epoch": 3.22, "learning_rate": 5.989405952444466e-07, "loss": 2.8014, "step": 1426 }, { "epoch": 3.23, "learning_rate": 5.962564970842599e-07, "loss": 2.4289, "step": 1428 }, { "epoch": 3.23, "learning_rate": 5.935758696524786e-07, "loss": 2.8162, "step": 1430 }, { "epoch": 3.24, "learning_rate": 5.908987359927673e-07, "loss": 2.6256, "step": 1432 }, { "epoch": 3.24, "learning_rate": 5.882251191187561e-07, "loss": 2.505, "step": 1434 }, { "epoch": 3.25, "learning_rate": 5.855550420138447e-07, "loss": 2.6142, "step": 1436 }, { "epoch": 3.25, "learning_rate": 5.828885276310024e-07, "loss": 2.6745, "step": 1438 }, { "epoch": 3.26, "learning_rate": 5.802255988925728e-07, "loss": 2.7963, "step": 1440 }, { "epoch": 3.26, "learning_rate": 5.775662786900757e-07, "loss": 3.0402, "step": 1442 }, { "epoch": 3.27, "learning_rate": 5.749105898840108e-07, "loss": 3.078, "step": 1444 }, { "epoch": 3.27, "learning_rate": 5.722585553036605e-07, "loss": 2.9393, "step": 1446 }, { "epoch": 3.27, "learning_rate": 5.696101977468952e-07, "loss": 2.5433, "step": 1448 }, { "epoch": 3.28, "learning_rate": 5.669655399799746e-07, "loss": 2.7848, "step": 1450 }, { "epoch": 3.28, "learning_rate": 5.643246047373549e-07, "loss": 3.005, "step": 1452 }, { "epoch": 3.29, "learning_rate": 5.616874147214918e-07, "loss": 2.642, "step": 1454 }, { "epoch": 3.29, "learning_rate": 5.590539926026459e-07, "loss": 3.1637, "step": 1456 }, { "epoch": 3.3, "learning_rate": 5.564243610186863e-07, "loss": 2.498, "step": 1458 }, { "epoch": 3.3, "learning_rate": 5.537985425748987e-07, "loss": 2.8173, "step": 1460 }, { "epoch": 3.31, "learning_rate": 5.511765598437894e-07, "loss": 2.9329, "step": 1462 }, { "epoch": 3.31, "learning_rate": 5.485584353648911e-07, "loss": 2.7406, "step": 1464 }, { "epoch": 3.31, "learning_rate": 5.4594419164457e-07, "loss": 3.0264, "step": 1466 }, { "epoch": 3.32, "learning_rate": 5.433338511558308e-07, "loss": 2.7586, "step": 1468 }, { "epoch": 3.32, "learning_rate": 5.407274363381256e-07, "loss": 2.8112, "step": 1470 }, { "epoch": 3.33, "learning_rate": 5.3812496959716e-07, "loss": 2.7818, "step": 1472 }, { "epoch": 3.33, "learning_rate": 5.355264733047e-07, "loss": 2.7619, "step": 1474 }, { "epoch": 3.34, "learning_rate": 5.329319697983803e-07, "loss": 2.9242, "step": 1476 }, { "epoch": 3.34, "learning_rate": 5.303414813815119e-07, "loss": 2.7811, "step": 1478 }, { "epoch": 3.35, "learning_rate": 5.277550303228914e-07, "loss": 3.0296, "step": 1480 }, { "epoch": 3.35, "learning_rate": 5.251726388566079e-07, "loss": 3.0903, "step": 1482 }, { "epoch": 3.36, "learning_rate": 5.225943291818536e-07, "loss": 3.1375, "step": 1484 }, { "epoch": 3.36, "learning_rate": 5.200201234627309e-07, "loss": 3.1292, "step": 1486 }, { "epoch": 3.36, "learning_rate": 5.174500438280638e-07, "loss": 2.9122, "step": 1488 }, { "epoch": 3.37, "learning_rate": 5.148841123712074e-07, "loss": 2.9945, "step": 1490 }, { "epoch": 3.37, "learning_rate": 5.123223511498569e-07, "loss": 3.0855, "step": 1492 }, { "epoch": 3.38, "learning_rate": 5.097647821858592e-07, "loss": 2.6993, "step": 1494 }, { "epoch": 3.38, "learning_rate": 5.072114274650217e-07, "loss": 2.9345, "step": 1496 }, { "epoch": 3.39, "learning_rate": 5.04662308936926e-07, "loss": 3.1058, "step": 1498 }, { "epoch": 3.39, "learning_rate": 5.021174485147373e-07, "loss": 3.3233, "step": 1500 }, { "epoch": 3.4, "learning_rate": 4.995768680750167e-07, "loss": 2.7399, "step": 1502 }, { "epoch": 3.4, "learning_rate": 4.970405894575326e-07, "loss": 3.0433, "step": 1504 }, { "epoch": 3.41, "learning_rate": 4.945086344650735e-07, "loss": 2.9797, "step": 1506 }, { "epoch": 3.41, "learning_rate": 4.919810248632607e-07, "loss": 3.134, "step": 1508 }, { "epoch": 3.41, "learning_rate": 4.894577823803609e-07, "loss": 2.6385, "step": 1510 }, { "epoch": 3.42, "learning_rate": 4.869389287070993e-07, "loss": 2.4828, "step": 1512 }, { "epoch": 3.42, "learning_rate": 4.844244854964728e-07, "loss": 2.5808, "step": 1514 }, { "epoch": 3.43, "learning_rate": 4.819144743635648e-07, "loss": 2.83, "step": 1516 }, { "epoch": 3.43, "learning_rate": 4.794089168853592e-07, "loss": 3.2125, "step": 1518 }, { "epoch": 3.44, "learning_rate": 4.769078346005547e-07, "loss": 2.496, "step": 1520 }, { "epoch": 3.44, "learning_rate": 4.7441124900937825e-07, "loss": 3.0066, "step": 1522 }, { "epoch": 3.45, "learning_rate": 4.7191918157340303e-07, "loss": 2.7898, "step": 1524 }, { "epoch": 3.45, "learning_rate": 4.69431653715362e-07, "loss": 2.8295, "step": 1526 }, { "epoch": 3.46, "learning_rate": 4.6694868681896416e-07, "loss": 2.5544, "step": 1528 }, { "epoch": 3.46, "learning_rate": 4.644703022287111e-07, "loss": 2.7788, "step": 1530 }, { "epoch": 3.46, "learning_rate": 4.619965212497124e-07, "loss": 2.652, "step": 1532 }, { "epoch": 3.47, "learning_rate": 4.5952736514750423e-07, "loss": 2.8017, "step": 1534 }, { "epoch": 3.47, "learning_rate": 4.5706285514786514e-07, "loss": 2.742, "step": 1536 }, { "epoch": 3.48, "learning_rate": 4.5460301243663445e-07, "loss": 3.0324, "step": 1538 }, { "epoch": 3.48, "learning_rate": 4.521478581595288e-07, "loss": 3.0012, "step": 1540 }, { "epoch": 3.49, "learning_rate": 4.4969741342196253e-07, "loss": 3.2382, "step": 1542 }, { "epoch": 3.49, "learning_rate": 4.472516992888642e-07, "loss": 2.8675, "step": 1544 }, { "epoch": 3.5, "learning_rate": 4.4481073678449666e-07, "loss": 2.4355, "step": 1546 }, { "epoch": 3.5, "learning_rate": 4.423745468922764e-07, "loss": 2.803, "step": 1548 }, { "epoch": 3.5, "learning_rate": 4.3994315055459164e-07, "loss": 2.806, "step": 1550 }, { "epoch": 3.51, "learning_rate": 4.375165686726243e-07, "loss": 2.8804, "step": 1552 }, { "epoch": 3.51, "learning_rate": 4.3509482210616963e-07, "loss": 2.7872, "step": 1554 }, { "epoch": 3.52, "learning_rate": 4.3267793167345646e-07, "loss": 3.0428, "step": 1556 }, { "epoch": 3.52, "learning_rate": 4.302659181509677e-07, "loss": 2.935, "step": 1558 }, { "epoch": 3.53, "learning_rate": 4.2785880227326375e-07, "loss": 2.7639, "step": 1560 }, { "epoch": 3.53, "learning_rate": 4.254566047328024e-07, "loss": 3.0243, "step": 1562 }, { "epoch": 3.54, "learning_rate": 4.230593461797619e-07, "loss": 3.0211, "step": 1564 }, { "epoch": 3.54, "learning_rate": 4.206670472218633e-07, "loss": 3.0111, "step": 1566 }, { "epoch": 3.55, "learning_rate": 4.18279728424192e-07, "loss": 2.893, "step": 1568 }, { "epoch": 3.55, "learning_rate": 4.158974103090235e-07, "loss": 2.9818, "step": 1570 }, { "epoch": 3.55, "learning_rate": 4.135201133556446e-07, "loss": 3.0244, "step": 1572 }, { "epoch": 3.56, "learning_rate": 4.111478580001796e-07, "loss": 2.8845, "step": 1574 }, { "epoch": 3.56, "learning_rate": 4.087806646354114e-07, "loss": 2.8003, "step": 1576 }, { "epoch": 3.57, "learning_rate": 4.0641855361060975e-07, "loss": 2.6908, "step": 1578 }, { "epoch": 3.57, "learning_rate": 4.0406154523135426e-07, "loss": 2.9427, "step": 1580 }, { "epoch": 3.58, "learning_rate": 4.017096597593602e-07, "loss": 2.605, "step": 1582 }, { "epoch": 3.58, "learning_rate": 3.993629174123051e-07, "loss": 2.8646, "step": 1584 }, { "epoch": 3.59, "learning_rate": 3.970213383636527e-07, "loss": 2.9782, "step": 1586 }, { "epoch": 3.59, "learning_rate": 3.946849427424828e-07, "loss": 2.748, "step": 1588 }, { "epoch": 3.6, "learning_rate": 3.9235375063331556e-07, "loss": 3.0263, "step": 1590 }, { "epoch": 3.6, "learning_rate": 3.9002778207594053e-07, "loss": 2.6372, "step": 1592 }, { "epoch": 3.6, "learning_rate": 3.8770705706524286e-07, "loss": 2.7644, "step": 1594 }, { "epoch": 3.61, "learning_rate": 3.8539159555103273e-07, "loss": 2.8305, "step": 1596 }, { "epoch": 3.61, "learning_rate": 3.830814174378735e-07, "loss": 2.7768, "step": 1598 }, { "epoch": 3.62, "learning_rate": 3.807765425849101e-07, "loss": 3.1515, "step": 1600 }, { "epoch": 3.62, "learning_rate": 3.784769908056992e-07, "loss": 2.6024, "step": 1602 }, { "epoch": 3.63, "learning_rate": 3.761827818680372e-07, "loss": 3.0388, "step": 1604 }, { "epoch": 3.63, "learning_rate": 3.738939354937928e-07, "loss": 3.0923, "step": 1606 }, { "epoch": 3.64, "learning_rate": 3.7161047135873533e-07, "loss": 2.7462, "step": 1608 }, { "epoch": 3.64, "learning_rate": 3.693324090923672e-07, "loss": 2.6594, "step": 1610 }, { "epoch": 3.64, "learning_rate": 3.6705976827775297e-07, "loss": 2.6957, "step": 1612 }, { "epoch": 3.65, "learning_rate": 3.6479256845135365e-07, "loss": 2.9971, "step": 1614 }, { "epoch": 3.65, "learning_rate": 3.6253082910285706e-07, "loss": 2.6025, "step": 1616 }, { "epoch": 3.66, "learning_rate": 3.602745696750107e-07, "loss": 2.7404, "step": 1618 }, { "epoch": 3.66, "learning_rate": 3.58023809563455e-07, "loss": 2.9475, "step": 1620 }, { "epoch": 3.67, "learning_rate": 3.5577856811655535e-07, "loss": 3.0561, "step": 1622 }, { "epoch": 3.67, "learning_rate": 3.5353886463523753e-07, "loss": 2.5821, "step": 1624 }, { "epoch": 3.68, "learning_rate": 3.513047183728207e-07, "loss": 3.193, "step": 1626 }, { "epoch": 3.68, "learning_rate": 3.4907614853485234e-07, "loss": 2.7803, "step": 1628 }, { "epoch": 3.69, "learning_rate": 3.468531742789419e-07, "loss": 2.6514, "step": 1630 }, { "epoch": 3.69, "learning_rate": 3.4463581471459824e-07, "loss": 2.7064, "step": 1632 }, { "epoch": 3.69, "learning_rate": 3.4242408890306383e-07, "loss": 2.7941, "step": 1634 }, { "epoch": 3.7, "learning_rate": 3.402180158571516e-07, "loss": 2.9509, "step": 1636 }, { "epoch": 3.7, "learning_rate": 3.38017614541081e-07, "loss": 3.0859, "step": 1638 }, { "epoch": 3.71, "learning_rate": 3.3582290387031465e-07, "loss": 2.8725, "step": 1640 }, { "epoch": 3.71, "learning_rate": 3.336339027113971e-07, "loss": 2.9056, "step": 1642 }, { "epoch": 3.72, "learning_rate": 3.314506298817917e-07, "loss": 2.7756, "step": 1644 }, { "epoch": 3.72, "learning_rate": 3.2927310414971897e-07, "loss": 2.8349, "step": 1646 }, { "epoch": 3.73, "learning_rate": 3.271013442339944e-07, "loss": 2.5402, "step": 1648 }, { "epoch": 3.73, "learning_rate": 3.249353688038695e-07, "loss": 2.973, "step": 1650 }, { "epoch": 3.74, "learning_rate": 3.2277519647886973e-07, "loss": 3.0307, "step": 1652 }, { "epoch": 3.74, "learning_rate": 3.2062084582863504e-07, "loss": 2.5357, "step": 1654 }, { "epoch": 3.74, "learning_rate": 3.184723353727602e-07, "loss": 3.1462, "step": 1656 }, { "epoch": 3.75, "learning_rate": 3.163296835806347e-07, "loss": 2.6682, "step": 1658 }, { "epoch": 3.75, "learning_rate": 3.1419290887128604e-07, "loss": 3.1249, "step": 1660 }, { "epoch": 3.76, "learning_rate": 3.1206202961321914e-07, "loss": 2.9504, "step": 1662 }, { "epoch": 3.76, "learning_rate": 3.0993706412426045e-07, "loss": 2.8624, "step": 1664 }, { "epoch": 3.77, "learning_rate": 3.078180306713981e-07, "loss": 2.7059, "step": 1666 }, { "epoch": 3.77, "learning_rate": 3.057049474706274e-07, "loss": 2.6241, "step": 1668 }, { "epoch": 3.78, "learning_rate": 3.035978326867925e-07, "loss": 2.9037, "step": 1670 }, { "epoch": 3.78, "learning_rate": 3.014967044334313e-07, "loss": 3.0965, "step": 1672 }, { "epoch": 3.79, "learning_rate": 2.9940158077261926e-07, "loss": 2.9823, "step": 1674 }, { "epoch": 3.79, "learning_rate": 2.973124797148131e-07, "loss": 2.8902, "step": 1676 }, { "epoch": 3.79, "learning_rate": 2.952294192186981e-07, "loss": 2.9734, "step": 1678 }, { "epoch": 3.8, "learning_rate": 2.931524171910327e-07, "loss": 3.3766, "step": 1680 }, { "epoch": 3.8, "learning_rate": 2.9108149148649405e-07, "loss": 2.9264, "step": 1682 }, { "epoch": 3.81, "learning_rate": 2.890166599075247e-07, "loss": 2.6805, "step": 1684 }, { "epoch": 3.81, "learning_rate": 2.8695794020418043e-07, "loss": 2.8779, "step": 1686 }, { "epoch": 3.82, "learning_rate": 2.849053500739769e-07, "loss": 2.767, "step": 1688 }, { "epoch": 3.82, "learning_rate": 2.8285890716173764e-07, "loss": 2.7864, "step": 1690 }, { "epoch": 3.83, "learning_rate": 2.8081862905944276e-07, "loss": 2.9544, "step": 1692 }, { "epoch": 3.83, "learning_rate": 2.7878453330607656e-07, "loss": 2.8805, "step": 1694 }, { "epoch": 3.83, "learning_rate": 2.767566373874781e-07, "loss": 2.8375, "step": 1696 }, { "epoch": 3.84, "learning_rate": 2.747349587361908e-07, "loss": 2.9756, "step": 1698 }, { "epoch": 3.84, "learning_rate": 2.7271951473131163e-07, "loss": 2.9132, "step": 1700 }, { "epoch": 3.85, "learning_rate": 2.7071032269834195e-07, "loss": 2.883, "step": 1702 }, { "epoch": 3.85, "learning_rate": 2.687073999090395e-07, "loss": 2.8958, "step": 1704 }, { "epoch": 3.86, "learning_rate": 2.6671076358126874e-07, "loss": 2.6718, "step": 1706 }, { "epoch": 3.86, "learning_rate": 2.64720430878854e-07, "loss": 2.8714, "step": 1708 }, { "epoch": 3.87, "learning_rate": 2.627364189114312e-07, "loss": 2.8066, "step": 1710 }, { "epoch": 3.87, "learning_rate": 2.607587447342998e-07, "loss": 2.9195, "step": 1712 }, { "epoch": 3.88, "learning_rate": 2.587874253482788e-07, "loss": 2.6239, "step": 1714 }, { "epoch": 3.88, "learning_rate": 2.5682247769955814e-07, "loss": 2.8051, "step": 1716 }, { "epoch": 3.88, "learning_rate": 2.548639186795546e-07, "loss": 2.9248, "step": 1718 }, { "epoch": 3.89, "learning_rate": 2.529117651247649e-07, "loss": 2.74, "step": 1720 }, { "epoch": 3.89, "learning_rate": 2.5096603381662286e-07, "loss": 3.0104, "step": 1722 }, { "epoch": 3.9, "learning_rate": 2.490267414813544e-07, "loss": 2.9472, "step": 1724 }, { "epoch": 3.9, "learning_rate": 2.470939047898331e-07, "loss": 2.6576, "step": 1726 }, { "epoch": 3.91, "learning_rate": 2.4516754035743794e-07, "loss": 2.9355, "step": 1728 }, { "epoch": 3.91, "learning_rate": 2.4324766474390934e-07, "loss": 2.7161, "step": 1730 }, { "epoch": 3.92, "learning_rate": 2.4133429445320796e-07, "loss": 2.9894, "step": 1732 }, { "epoch": 3.92, "learning_rate": 2.3942744593337214e-07, "loss": 2.6632, "step": 1734 }, { "epoch": 3.93, "learning_rate": 2.3752713557637704e-07, "loss": 2.8151, "step": 1736 }, { "epoch": 3.93, "learning_rate": 2.3563337971799224e-07, "loss": 2.6808, "step": 1738 }, { "epoch": 3.93, "learning_rate": 2.3374619463764378e-07, "loss": 3.118, "step": 1740 }, { "epoch": 3.94, "learning_rate": 2.3186559655827188e-07, "loss": 3.0497, "step": 1742 }, { "epoch": 3.94, "learning_rate": 2.2999160164619314e-07, "loss": 2.8969, "step": 1744 }, { "epoch": 3.95, "learning_rate": 2.281242260109607e-07, "loss": 2.9299, "step": 1746 }, { "epoch": 3.95, "learning_rate": 2.2626348570522548e-07, "loss": 2.8887, "step": 1748 }, { "epoch": 3.96, "learning_rate": 2.24409396724599e-07, "loss": 2.9444, "step": 1750 }, { "epoch": 3.96, "learning_rate": 2.2256197500751582e-07, "loss": 2.8401, "step": 1752 }, { "epoch": 3.97, "learning_rate": 2.207212364350961e-07, "loss": 2.9745, "step": 1754 }, { "epoch": 3.97, "learning_rate": 2.1888719683100853e-07, "loss": 2.9167, "step": 1756 }, { "epoch": 3.98, "learning_rate": 2.1705987196133601e-07, "loss": 3.0139, "step": 1758 }, { "epoch": 3.98, "learning_rate": 2.152392775344384e-07, "loss": 2.8689, "step": 1760 }, { "epoch": 3.98, "learning_rate": 2.1342542920081853e-07, "loss": 2.71, "step": 1762 }, { "epoch": 3.99, "learning_rate": 2.116183425529875e-07, "loss": 2.7611, "step": 1764 }, { "epoch": 3.99, "learning_rate": 2.0981803312532953e-07, "loss": 2.4722, "step": 1766 }, { "epoch": 4.0, "learning_rate": 2.0802451639397046e-07, "loss": 2.7075, "step": 1768 }, { "epoch": 4.0, "learning_rate": 2.062378077766429e-07, "loss": 2.9215, "step": 1770 }, { "epoch": 4.01, "learning_rate": 2.0445792263255502e-07, "loss": 2.8989, "step": 1772 }, { "epoch": 4.01, "learning_rate": 2.0268487626225706e-07, "loss": 3.339, "step": 1774 }, { "epoch": 4.02, "learning_rate": 2.009186839075111e-07, "loss": 2.5366, "step": 1776 }, { "epoch": 4.02, "learning_rate": 1.991593607511597e-07, "loss": 2.9139, "step": 1778 }, { "epoch": 4.02, "learning_rate": 1.9740692191699516e-07, "loss": 3.1604, "step": 1780 }, { "epoch": 4.03, "learning_rate": 1.9566138246962959e-07, "loss": 2.7238, "step": 1782 }, { "epoch": 4.03, "learning_rate": 1.9392275741436502e-07, "loss": 3.0002, "step": 1784 }, { "epoch": 4.04, "learning_rate": 1.9219106169706533e-07, "loss": 2.4732, "step": 1786 }, { "epoch": 4.04, "learning_rate": 1.9046631020402704e-07, "loss": 2.8181, "step": 1788 }, { "epoch": 4.05, "learning_rate": 1.8874851776185197e-07, "loss": 2.8632, "step": 1790 }, { "epoch": 4.05, "learning_rate": 1.8703769913731826e-07, "loss": 2.7334, "step": 1792 }, { "epoch": 4.06, "learning_rate": 1.8533386903725578e-07, "loss": 2.9473, "step": 1794 }, { "epoch": 4.06, "learning_rate": 1.836370421084177e-07, "loss": 3.2462, "step": 1796 }, { "epoch": 4.07, "learning_rate": 1.819472329373557e-07, "loss": 2.7017, "step": 1798 }, { "epoch": 4.07, "learning_rate": 1.802644560502944e-07, "loss": 2.8516, "step": 1800 }, { "epoch": 4.07, "learning_rate": 1.7858872591300535e-07, "loss": 2.4993, "step": 1802 }, { "epoch": 4.08, "learning_rate": 1.7692005693068456e-07, "loss": 2.7791, "step": 1804 }, { "epoch": 4.08, "learning_rate": 1.7525846344782757e-07, "loss": 2.8628, "step": 1806 }, { "epoch": 4.09, "learning_rate": 1.736039597481064e-07, "loss": 2.6484, "step": 1808 }, { "epoch": 4.09, "learning_rate": 1.7195656005424598e-07, "loss": 3.2381, "step": 1810 }, { "epoch": 4.1, "learning_rate": 1.703162785279033e-07, "loss": 3.0048, "step": 1812 }, { "epoch": 4.1, "learning_rate": 1.6868312926954486e-07, "loss": 2.6365, "step": 1814 }, { "epoch": 4.11, "learning_rate": 1.6705712631832535e-07, "loss": 2.7068, "step": 1816 }, { "epoch": 4.11, "learning_rate": 1.6543828365196742e-07, "loss": 3.1421, "step": 1818 }, { "epoch": 4.12, "learning_rate": 1.6382661518664065e-07, "loss": 2.9912, "step": 1820 }, { "epoch": 4.12, "learning_rate": 1.622221347768432e-07, "loss": 2.9992, "step": 1822 }, { "epoch": 4.12, "learning_rate": 1.6062485621528177e-07, "loss": 3.0134, "step": 1824 }, { "epoch": 4.13, "learning_rate": 1.590347932327537e-07, "loss": 2.5122, "step": 1826 }, { "epoch": 4.13, "learning_rate": 1.574519594980276e-07, "loss": 3.0067, "step": 1828 }, { "epoch": 4.14, "learning_rate": 1.5587636861772768e-07, "loss": 2.6505, "step": 1830 }, { "epoch": 4.14, "learning_rate": 1.5430803413621563e-07, "loss": 2.7393, "step": 1832 }, { "epoch": 4.15, "learning_rate": 1.5274696953547428e-07, "loss": 3.2975, "step": 1834 }, { "epoch": 4.15, "learning_rate": 1.511931882349925e-07, "loss": 2.7859, "step": 1836 }, { "epoch": 4.16, "learning_rate": 1.4964670359164812e-07, "loss": 2.9659, "step": 1838 }, { "epoch": 4.16, "learning_rate": 1.481075288995951e-07, "loss": 3.0608, "step": 1840 }, { "epoch": 4.17, "learning_rate": 1.4657567739014808e-07, "loss": 2.8377, "step": 1842 }, { "epoch": 4.17, "learning_rate": 1.4505116223166925e-07, "loss": 2.7088, "step": 1844 }, { "epoch": 4.17, "learning_rate": 1.4353399652945386e-07, "loss": 2.8332, "step": 1846 }, { "epoch": 4.18, "learning_rate": 1.4202419332561944e-07, "loss": 2.7625, "step": 1848 }, { "epoch": 4.18, "learning_rate": 1.4052176559899254e-07, "loss": 2.7921, "step": 1850 }, { "epoch": 4.19, "learning_rate": 1.3902672626499723e-07, "loss": 2.8269, "step": 1852 }, { "epoch": 4.19, "learning_rate": 1.3753908817554461e-07, "loss": 3.3591, "step": 1854 }, { "epoch": 4.2, "learning_rate": 1.360588641189211e-07, "loss": 2.8286, "step": 1856 }, { "epoch": 4.2, "learning_rate": 1.345860668196801e-07, "loss": 2.9208, "step": 1858 }, { "epoch": 4.21, "learning_rate": 1.3312070893853177e-07, "loss": 2.8625, "step": 1860 }, { "epoch": 4.21, "learning_rate": 1.3166280307223442e-07, "loss": 2.7791, "step": 1862 }, { "epoch": 4.21, "learning_rate": 1.3021236175348516e-07, "loss": 2.9848, "step": 1864 }, { "epoch": 4.22, "learning_rate": 1.2876939745081417e-07, "loss": 2.9931, "step": 1866 }, { "epoch": 4.22, "learning_rate": 1.2733392256847597e-07, "loss": 2.9145, "step": 1868 }, { "epoch": 4.23, "learning_rate": 1.2590594944634337e-07, "loss": 2.6273, "step": 1870 }, { "epoch": 4.23, "learning_rate": 1.2448549035980138e-07, "loss": 3.2187, "step": 1872 }, { "epoch": 4.24, "learning_rate": 1.2307255751964086e-07, "loss": 2.9382, "step": 1874 }, { "epoch": 4.24, "learning_rate": 1.2166716307195525e-07, "loss": 3.0494, "step": 1876 }, { "epoch": 4.25, "learning_rate": 1.2026931909803472e-07, "loss": 2.8885, "step": 1878 }, { "epoch": 4.25, "learning_rate": 1.1887903761426288e-07, "loss": 2.6072, "step": 1880 }, { "epoch": 4.26, "learning_rate": 1.1749633057201313e-07, "loss": 2.9803, "step": 1882 }, { "epoch": 4.26, "learning_rate": 1.1612120985754636e-07, "loss": 2.6744, "step": 1884 }, { "epoch": 4.26, "learning_rate": 1.147536872919087e-07, "loss": 2.6035, "step": 1886 }, { "epoch": 4.27, "learning_rate": 1.1339377463082967e-07, "loss": 2.8646, "step": 1888 }, { "epoch": 4.27, "learning_rate": 1.120414835646214e-07, "loss": 2.7573, "step": 1890 }, { "epoch": 4.28, "learning_rate": 1.1069682571807737e-07, "loss": 2.6551, "step": 1892 }, { "epoch": 4.28, "learning_rate": 1.0935981265037375e-07, "loss": 2.7625, "step": 1894 }, { "epoch": 4.29, "learning_rate": 1.0803045585496906e-07, "loss": 2.732, "step": 1896 }, { "epoch": 4.29, "learning_rate": 1.0670876675950613e-07, "loss": 3.1257, "step": 1898 }, { "epoch": 4.3, "learning_rate": 1.053947567257124e-07, "loss": 2.7498, "step": 1900 }, { "epoch": 4.3, "learning_rate": 1.0408843704930426e-07, "loss": 2.8032, "step": 1902 }, { "epoch": 4.31, "learning_rate": 1.0278981895988848e-07, "loss": 2.96, "step": 1904 }, { "epoch": 4.31, "learning_rate": 1.0149891362086627e-07, "loss": 2.5762, "step": 1906 }, { "epoch": 4.31, "learning_rate": 1.002157321293372e-07, "loss": 2.8509, "step": 1908 }, { "epoch": 4.32, "learning_rate": 9.894028551600352e-08, "loss": 3.0293, "step": 1910 }, { "epoch": 4.32, "learning_rate": 9.7672584745076e-08, "loss": 2.7798, "step": 1912 }, { "epoch": 4.33, "learning_rate": 9.641264071417899e-08, "loss": 2.9707, "step": 1914 }, { "epoch": 4.33, "learning_rate": 9.516046425425739e-08, "loss": 2.6264, "step": 1916 }, { "epoch": 4.34, "learning_rate": 9.391606612948256e-08, "loss": 2.6834, "step": 1918 }, { "epoch": 4.34, "learning_rate": 9.267945703716096e-08, "loss": 3.1564, "step": 1920 }, { "epoch": 4.35, "learning_rate": 9.145064760764166e-08, "loss": 2.9236, "step": 1922 }, { "epoch": 4.35, "learning_rate": 9.022964840422453e-08, "loss": 2.6168, "step": 1924 }, { "epoch": 4.36, "learning_rate": 8.901646992307054e-08, "loss": 3.1438, "step": 1926 }, { "epoch": 4.36, "learning_rate": 8.781112259310986e-08, "loss": 2.4969, "step": 1928 }, { "epoch": 4.36, "learning_rate": 8.661361677595391e-08, "loss": 3.1392, "step": 1930 }, { "epoch": 4.37, "learning_rate": 8.542396276580543e-08, "loss": 2.9307, "step": 1932 }, { "epoch": 4.37, "learning_rate": 8.424217078937035e-08, "loss": 2.7094, "step": 1934 }, { "epoch": 4.38, "learning_rate": 8.306825100576886e-08, "loss": 2.7887, "step": 1936 }, { "epoch": 4.38, "learning_rate": 8.190221350644966e-08, "loss": 2.973, "step": 1938 }, { "epoch": 4.39, "learning_rate": 8.074406831510206e-08, "loss": 2.6853, "step": 1940 }, { "epoch": 4.39, "learning_rate": 7.959382538757043e-08, "loss": 3.1157, "step": 1942 }, { "epoch": 4.4, "learning_rate": 7.845149461176814e-08, "loss": 2.7685, "step": 1944 }, { "epoch": 4.4, "learning_rate": 7.731708580759267e-08, "loss": 3.2796, "step": 1946 }, { "epoch": 4.4, "learning_rate": 7.619060872684157e-08, "loss": 2.9947, "step": 1948 }, { "epoch": 4.41, "learning_rate": 7.507207305312835e-08, "loss": 3.0201, "step": 1950 }, { "epoch": 4.41, "learning_rate": 7.396148840179894e-08, "loss": 2.6056, "step": 1952 }, { "epoch": 4.42, "learning_rate": 7.285886431984978e-08, "loss": 3.1953, "step": 1954 }, { "epoch": 4.42, "learning_rate": 7.1764210285845e-08, "loss": 3.0045, "step": 1956 }, { "epoch": 4.43, "learning_rate": 7.067753570983526e-08, "loss": 2.7863, "step": 1958 }, { "epoch": 4.43, "learning_rate": 6.959884993327725e-08, "loss": 3.0581, "step": 1960 }, { "epoch": 4.44, "learning_rate": 6.85281622289523e-08, "loss": 2.9746, "step": 1962 }, { "epoch": 4.44, "learning_rate": 6.746548180088785e-08, "loss": 2.6516, "step": 1964 }, { "epoch": 4.45, "learning_rate": 6.64108177842777e-08, "loss": 2.5994, "step": 1966 }, { "epoch": 4.45, "learning_rate": 6.536417924540371e-08, "loss": 2.9475, "step": 1968 }, { "epoch": 4.45, "learning_rate": 6.432557518155768e-08, "loss": 2.7227, "step": 1970 }, { "epoch": 4.46, "learning_rate": 6.329501452096397e-08, "loss": 2.9451, "step": 1972 }, { "epoch": 4.46, "learning_rate": 6.227250612270297e-08, "loss": 2.839, "step": 1974 }, { "epoch": 4.47, "learning_rate": 6.125805877663493e-08, "loss": 2.7328, "step": 1976 }, { "epoch": 4.47, "learning_rate": 6.025168120332447e-08, "loss": 2.6994, "step": 1978 }, { "epoch": 4.48, "learning_rate": 5.925338205396491e-08, "loss": 2.8006, "step": 1980 }, { "epoch": 4.48, "learning_rate": 5.8263169910304774e-08, "loss": 2.7229, "step": 1982 }, { "epoch": 4.49, "learning_rate": 5.7281053284574e-08, "loss": 2.8487, "step": 1984 }, { "epoch": 4.49, "learning_rate": 5.630704061940994e-08, "loss": 2.861, "step": 1986 }, { "epoch": 4.5, "learning_rate": 5.53411402877858e-08, "loss": 2.8665, "step": 1988 }, { "epoch": 4.5, "learning_rate": 5.4383360592937575e-08, "loss": 2.7878, "step": 1990 }, { "epoch": 4.5, "learning_rate": 5.343370976829364e-08, "loss": 2.5705, "step": 1992 }, { "epoch": 4.51, "learning_rate": 5.249219597740373e-08, "loss": 3.2162, "step": 1994 }, { "epoch": 4.51, "learning_rate": 5.15588273138684e-08, "loss": 2.6569, "step": 1996 }, { "epoch": 4.52, "learning_rate": 5.063361180126968e-08, "loss": 2.9358, "step": 1998 }, { "epoch": 4.52, "learning_rate": 4.971655739310199e-08, "loss": 2.9044, "step": 2000 }, { "epoch": 4.53, "learning_rate": 4.88076719727043e-08, "loss": 2.9087, "step": 2002 }, { "epoch": 4.53, "learning_rate": 4.790696335319144e-08, "loss": 2.822, "step": 2004 }, { "epoch": 4.54, "learning_rate": 4.701443927738802e-08, "loss": 3.0138, "step": 2006 }, { "epoch": 4.54, "learning_rate": 4.6130107417760575e-08, "loss": 2.9747, "step": 2008 }, { "epoch": 4.54, "learning_rate": 4.5253975376352896e-08, "loss": 3.0653, "step": 2010 }, { "epoch": 4.55, "learning_rate": 4.438605068471979e-08, "loss": 3.0542, "step": 2012 }, { "epoch": 4.55, "learning_rate": 4.352634080386286e-08, "loss": 2.6002, "step": 2014 }, { "epoch": 4.56, "learning_rate": 4.2674853124165964e-08, "loss": 2.8976, "step": 2016 }, { "epoch": 4.56, "learning_rate": 4.1831594965331954e-08, "loss": 2.7584, "step": 2018 }, { "epoch": 4.57, "learning_rate": 4.0996573576319695e-08, "loss": 2.5147, "step": 2020 }, { "epoch": 4.57, "learning_rate": 4.016979613528182e-08, "loss": 3.0233, "step": 2022 }, { "epoch": 4.58, "learning_rate": 3.935126974950298e-08, "loss": 2.8162, "step": 2024 }, { "epoch": 4.58, "learning_rate": 3.854100145533823e-08, "loss": 2.75, "step": 2026 }, { "epoch": 4.59, "learning_rate": 3.773899821815363e-08, "loss": 2.9344, "step": 2028 }, { "epoch": 4.59, "learning_rate": 3.694526693226541e-08, "loss": 2.711, "step": 2030 }, { "epoch": 4.59, "learning_rate": 3.615981442088112e-08, "loss": 2.4516, "step": 2032 }, { "epoch": 4.6, "learning_rate": 3.538264743604091e-08, "loss": 3.2293, "step": 2034 }, { "epoch": 4.6, "learning_rate": 3.461377265855947e-08, "loss": 2.6974, "step": 2036 }, { "epoch": 4.61, "learning_rate": 3.38531966979686e-08, "loss": 3.2955, "step": 2038 }, { "epoch": 4.61, "learning_rate": 3.310092609246051e-08, "loss": 2.5985, "step": 2040 }, { "epoch": 4.62, "learning_rate": 3.235696730883142e-08, "loss": 2.7748, "step": 2042 }, { "epoch": 4.62, "learning_rate": 3.16213267424259e-08, "loss": 2.8904, "step": 2044 }, { "epoch": 4.63, "learning_rate": 3.089401071708242e-08, "loss": 2.9976, "step": 2046 }, { "epoch": 4.63, "learning_rate": 3.017502548507822e-08, "loss": 2.8383, "step": 2048 }, { "epoch": 4.64, "learning_rate": 2.9464377227076288e-08, "loss": 2.9383, "step": 2050 }, { "epoch": 4.64, "learning_rate": 2.8762072052071707e-08, "loss": 2.914, "step": 2052 }, { "epoch": 4.64, "learning_rate": 2.806811599733938e-08, "loss": 2.8149, "step": 2054 }, { "epoch": 4.65, "learning_rate": 2.738251502838207e-08, "loss": 2.9969, "step": 2056 }, { "epoch": 4.65, "learning_rate": 2.6705275038879095e-08, "loss": 2.9372, "step": 2058 }, { "epoch": 4.66, "learning_rate": 2.6036401850636048e-08, "loss": 2.87, "step": 2060 }, { "epoch": 4.66, "learning_rate": 2.5375901213533836e-08, "loss": 2.6653, "step": 2062 }, { "epoch": 4.67, "learning_rate": 2.4723778805480157e-08, "loss": 2.7326, "step": 2064 }, { "epoch": 4.67, "learning_rate": 2.4080040232360322e-08, "loss": 2.8675, "step": 2066 }, { "epoch": 4.68, "learning_rate": 2.3444691027989185e-08, "loss": 2.8471, "step": 2068 }, { "epoch": 4.68, "learning_rate": 2.281773665406328e-08, "loss": 3.063, "step": 2070 }, { "epoch": 4.69, "learning_rate": 2.21991825001141e-08, "loss": 3.2441, "step": 2072 }, { "epoch": 4.69, "learning_rate": 2.1589033883462004e-08, "loss": 2.6652, "step": 2074 }, { "epoch": 4.69, "learning_rate": 2.0987296049169935e-08, "loss": 2.6458, "step": 2076 }, { "epoch": 4.7, "learning_rate": 2.0393974169998774e-08, "loss": 2.8888, "step": 2078 }, { "epoch": 4.7, "learning_rate": 1.9809073346362836e-08, "loss": 3.1569, "step": 2080 }, { "epoch": 4.71, "learning_rate": 1.9232598606285565e-08, "loss": 2.5679, "step": 2082 }, { "epoch": 4.71, "learning_rate": 1.8664554905357233e-08, "loss": 2.891, "step": 2084 }, { "epoch": 4.72, "learning_rate": 1.8104947126691418e-08, "loss": 2.937, "step": 2086 }, { "epoch": 4.72, "learning_rate": 1.7553780080883374e-08, "loss": 2.7998, "step": 2088 }, { "epoch": 4.73, "learning_rate": 1.7011058505968733e-08, "loss": 2.7805, "step": 2090 }, { "epoch": 4.73, "learning_rate": 1.6476787067382868e-08, "loss": 2.8235, "step": 2092 }, { "epoch": 4.73, "learning_rate": 1.595097035792059e-08, "loss": 2.9455, "step": 2094 }, { "epoch": 4.74, "learning_rate": 1.5433612897696734e-08, "loss": 2.8152, "step": 2096 }, { "epoch": 4.74, "learning_rate": 1.49247191341072e-08, "loss": 2.4293, "step": 2098 }, { "epoch": 4.75, "learning_rate": 1.442429344179097e-08, "loss": 2.9213, "step": 2100 }, { "epoch": 4.75, "learning_rate": 1.3932340122592256e-08, "loss": 2.66, "step": 2102 }, { "epoch": 4.76, "learning_rate": 1.3448863405523647e-08, "loss": 2.8613, "step": 2104 }, { "epoch": 4.76, "learning_rate": 1.2973867446729792e-08, "loss": 2.9877, "step": 2106 }, { "epoch": 4.77, "learning_rate": 1.2507356329451435e-08, "loss": 2.9628, "step": 2108 }, { "epoch": 4.77, "learning_rate": 1.2049334063990669e-08, "loss": 2.8398, "step": 2110 }, { "epoch": 4.78, "learning_rate": 1.1599804587676288e-08, "loss": 2.8501, "step": 2112 }, { "epoch": 4.78, "learning_rate": 1.115877176482971e-08, "loss": 2.7105, "step": 2114 }, { "epoch": 4.78, "learning_rate": 1.0726239386732228e-08, "loss": 2.8352, "step": 2116 }, { "epoch": 4.79, "learning_rate": 1.0302211171592023e-08, "loss": 3.3139, "step": 2118 }, { "epoch": 4.79, "learning_rate": 9.886690764512317e-09, "loss": 2.639, "step": 2120 }, { "epoch": 4.8, "learning_rate": 9.479681737460165e-09, "loss": 2.9957, "step": 2122 }, { "epoch": 4.8, "learning_rate": 9.081187589235706e-09, "loss": 2.936, "step": 2124 }, { "epoch": 4.81, "learning_rate": 8.691211745441962e-09, "loss": 2.9505, "step": 2126 }, { "epoch": 4.81, "learning_rate": 8.30975755845531e-09, "loss": 2.9567, "step": 2128 }, { "epoch": 4.82, "learning_rate": 7.93682830739706e-09, "loss": 2.5002, "step": 2130 }, { "epoch": 4.82, "learning_rate": 7.572427198104913e-09, "loss": 2.8445, "step": 2132 }, { "epoch": 4.83, "learning_rate": 7.2165573631054465e-09, "loss": 3.3974, "step": 2134 }, { "epoch": 4.83, "learning_rate": 6.869221861587338e-09, "loss": 2.5848, "step": 2136 }, { "epoch": 4.83, "learning_rate": 6.5304236793750635e-09, "loss": 2.5381, "step": 2138 }, { "epoch": 4.84, "learning_rate": 6.200165728903028e-09, "loss": 2.9897, "step": 2140 }, { "epoch": 4.84, "learning_rate": 5.878450849190475e-09, "loss": 2.7295, "step": 2142 }, { "epoch": 4.85, "learning_rate": 5.565281805817612e-09, "loss": 2.9766, "step": 2144 }, { "epoch": 4.85, "learning_rate": 5.260661290901302e-09, "loss": 2.9119, "step": 2146 }, { "epoch": 4.86, "learning_rate": 4.9645919230719705e-09, "loss": 2.7419, "step": 2148 }, { "epoch": 4.86, "learning_rate": 4.677076247451617e-09, "loss": 2.6276, "step": 2150 }, { "epoch": 4.87, "learning_rate": 4.398116735630952e-09, "loss": 2.7752, "step": 2152 }, { "epoch": 4.87, "learning_rate": 4.127715785649299e-09, "loss": 2.9302, "step": 2154 }, { "epoch": 4.88, "learning_rate": 3.865875721973055e-09, "loss": 2.8168, "step": 2156 }, { "epoch": 4.88, "learning_rate": 3.6125987954762627e-09, "loss": 2.697, "step": 2158 }, { "epoch": 4.88, "learning_rate": 3.36788718342107e-09, "loss": 2.5574, "step": 2160 }, { "epoch": 4.89, "learning_rate": 3.131742989438857e-09, "loss": 2.6584, "step": 2162 }, { "epoch": 4.89, "learning_rate": 2.9041682435123614e-09, "loss": 2.8213, "step": 2164 }, { "epoch": 4.9, "learning_rate": 2.685164901958359e-09, "loss": 3.5479, "step": 2166 }, { "epoch": 4.9, "learning_rate": 2.4747348474105645e-09, "loss": 2.8797, "step": 2168 }, { "epoch": 4.91, "learning_rate": 2.272879888803425e-09, "loss": 3.0118, "step": 2170 }, { "epoch": 4.91, "learning_rate": 2.079601761356797e-09, "loss": 2.7637, "step": 2172 }, { "epoch": 4.92, "learning_rate": 1.894902126560849e-09, "loss": 2.7964, "step": 2174 }, { "epoch": 4.92, "learning_rate": 1.7187825721620696e-09, "loss": 3.0763, "step": 2176 }, { "epoch": 4.92, "learning_rate": 1.5512446121490607e-09, "loss": 2.9606, "step": 2178 }, { "epoch": 4.93, "learning_rate": 1.3922896867403221e-09, "loss": 2.5363, "step": 2180 }, { "epoch": 4.93, "learning_rate": 1.2419191623709302e-09, "loss": 2.8541, "step": 2182 }, { "epoch": 4.94, "learning_rate": 1.100134331681657e-09, "loss": 2.6917, "step": 2184 }, { "epoch": 4.94, "learning_rate": 9.669364135072023e-10, "loss": 2.9523, "step": 2186 }, { "epoch": 4.95, "learning_rate": 8.423265528660905e-10, "loss": 2.6671, "step": 2188 }, { "epoch": 4.95, "learning_rate": 7.26305820950901e-10, "loss": 2.7536, "step": 2190 }, { "epoch": 4.96, "learning_rate": 6.188752151186083e-10, "loss": 2.8874, "step": 2192 }, { "epoch": 4.96, "learning_rate": 5.200356588824784e-10, "loss": 2.9403, "step": 2194 }, { "epoch": 4.97, "learning_rate": 4.2978800190385245e-10, "loss": 2.6072, "step": 2196 }, { "epoch": 4.97, "learning_rate": 3.481330199849308e-10, "loss": 2.7767, "step": 2198 }, { "epoch": 4.97, "learning_rate": 2.750714150621114e-10, "loss": 2.5985, "step": 2200 }, { "epoch": 4.98, "learning_rate": 2.1060381519999448e-10, "loss": 3.2195, "step": 2202 }, { "epoch": 4.98, "learning_rate": 1.5473077458594276e-10, "loss": 2.6724, "step": 2204 }, { "epoch": 4.99, "learning_rate": 1.0745277352519622e-10, "loss": 2.8641, "step": 2206 }, { "epoch": 4.99, "learning_rate": 6.87702184369865e-11, "loss": 2.9528, "step": 2208 }, { "epoch": 5.0, "learning_rate": 3.868344185087302e-11, "loss": 2.9681, "step": 2210 }, { "epoch": 5.0, "step": 2210, "total_flos": 4.772726620500787e+16, "train_loss": 3.1684074565835667, "train_runtime": 15917.9897, "train_samples_per_second": 8.889, "train_steps_per_second": 0.139 } ], "logging_steps": 2, "max_steps": 2210, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 8000, "total_flos": 4.772726620500787e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }