{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0109145652992098, "eval_steps": 500, "global_step": 6000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.9999980101927616e-05, "loss": 3.2533, "step": 5 }, { "epoch": 0.01, "learning_rate": 4.99999204077421e-05, "loss": 3.2279, "step": 10 }, { "epoch": 0.01, "learning_rate": 4.999978982687695e-05, "loss": 3.193, "step": 15 }, { "epoch": 0.01, "learning_rate": 4.9999597065062966e-05, "loss": 3.2863, "step": 20 }, { "epoch": 0.01, "learning_rate": 4.999934212277958e-05, "loss": 3.1724, "step": 25 }, { "epoch": 0.02, "learning_rate": 4.999902500066093e-05, "loss": 3.1088, "step": 30 }, { "epoch": 0.02, "learning_rate": 4.999864569949576e-05, "loss": 3.3241, "step": 35 }, { "epoch": 0.02, "learning_rate": 4.99982042202275e-05, "loss": 3.1904, "step": 40 }, { "epoch": 0.02, "learning_rate": 4.999770056395421e-05, "loss": 2.9254, "step": 45 }, { "epoch": 0.03, "learning_rate": 4.999713473192863e-05, "loss": 3.1845, "step": 50 }, { "epoch": 0.03, "learning_rate": 4.999650672555812e-05, "loss": 2.8475, "step": 55 }, { "epoch": 0.03, "learning_rate": 4.9995816546404695e-05, "loss": 3.0486, "step": 60 }, { "epoch": 0.03, "learning_rate": 4.9995064196185014e-05, "loss": 2.6464, "step": 65 }, { "epoch": 0.04, "learning_rate": 4.9994249676770364e-05, "loss": 3.0446, "step": 70 }, { "epoch": 0.04, "learning_rate": 4.999337299018667e-05, "loss": 3.375, "step": 75 }, { "epoch": 0.04, "learning_rate": 4.999243413861447e-05, "loss": 2.8787, "step": 80 }, { "epoch": 0.04, "learning_rate": 4.999143312438893e-05, "loss": 3.014, "step": 85 }, { "epoch": 0.05, "learning_rate": 4.999036994999985e-05, "loss": 2.8288, "step": 90 }, { "epoch": 0.05, "learning_rate": 4.9989244618091596e-05, "loss": 3.1879, "step": 95 }, { "epoch": 0.05, "learning_rate": 4.998805713146317e-05, "loss": 2.9749, "step": 100 }, { "epoch": 0.05, "learning_rate": 4.9986807493068165e-05, "loss": 2.6304, "step": 105 }, { "epoch": 0.06, "learning_rate": 4.998549570601475e-05, "loss": 2.943, "step": 110 }, { "epoch": 0.06, "learning_rate": 4.998412177356568e-05, "loss": 2.7595, "step": 115 }, { "epoch": 0.06, "learning_rate": 4.9982685699138275e-05, "loss": 2.7377, "step": 120 }, { "epoch": 0.06, "learning_rate": 4.9981187486304423e-05, "loss": 2.9878, "step": 125 }, { "epoch": 0.07, "learning_rate": 4.997962713879058e-05, "loss": 2.7882, "step": 130 }, { "epoch": 0.07, "learning_rate": 4.997800466047772e-05, "loss": 2.7802, "step": 135 }, { "epoch": 0.07, "learning_rate": 4.997632005540138e-05, "loss": 3.0129, "step": 140 }, { "epoch": 0.07, "learning_rate": 4.997457332775159e-05, "loss": 2.9444, "step": 145 }, { "epoch": 0.08, "learning_rate": 4.997276448187294e-05, "loss": 2.9664, "step": 150 }, { "epoch": 0.08, "learning_rate": 4.9970893522264476e-05, "loss": 2.7367, "step": 155 }, { "epoch": 0.08, "learning_rate": 4.996896045357977e-05, "loss": 2.7012, "step": 160 }, { "epoch": 0.08, "learning_rate": 4.9966965280626856e-05, "loss": 2.8493, "step": 165 }, { "epoch": 0.09, "learning_rate": 4.996490800836825e-05, "loss": 2.9274, "step": 170 }, { "epoch": 0.09, "learning_rate": 4.996278864192092e-05, "loss": 2.8093, "step": 175 }, { "epoch": 0.09, "learning_rate": 4.9960607186556286e-05, "loss": 3.1782, "step": 180 }, { "epoch": 0.09, "learning_rate": 4.995836364770018e-05, "loss": 2.7507, "step": 185 }, { "epoch": 0.1, "learning_rate": 4.995605803093287e-05, "loss": 2.6724, "step": 190 }, { "epoch": 0.1, "learning_rate": 4.9953690341989026e-05, "loss": 3.0258, "step": 195 }, { "epoch": 0.1, "learning_rate": 4.9951260586757694e-05, "loss": 3.1134, "step": 200 }, { "epoch": 0.1, "learning_rate": 4.9948768771282314e-05, "loss": 2.9937, "step": 205 }, { "epoch": 0.11, "learning_rate": 4.9946214901760665e-05, "loss": 2.7394, "step": 210 }, { "epoch": 0.11, "learning_rate": 4.99435989845449e-05, "loss": 2.9696, "step": 215 }, { "epoch": 0.11, "learning_rate": 4.994092102614146e-05, "loss": 2.753, "step": 220 }, { "epoch": 0.11, "learning_rate": 4.993818103321113e-05, "loss": 3.0759, "step": 225 }, { "epoch": 0.12, "learning_rate": 4.9935379012568985e-05, "loss": 2.7512, "step": 230 }, { "epoch": 0.12, "learning_rate": 4.993251497118438e-05, "loss": 2.8656, "step": 235 }, { "epoch": 0.12, "learning_rate": 4.992958891618091e-05, "loss": 2.6628, "step": 240 }, { "epoch": 0.12, "learning_rate": 4.992660085483645e-05, "loss": 2.8012, "step": 245 }, { "epoch": 0.13, "learning_rate": 4.992355079458307e-05, "loss": 2.8141, "step": 250 }, { "epoch": 0.13, "learning_rate": 4.992043874300706e-05, "loss": 2.9083, "step": 255 }, { "epoch": 0.13, "learning_rate": 4.991726470784891e-05, "loss": 2.5846, "step": 260 }, { "epoch": 0.13, "learning_rate": 4.991402869700325e-05, "loss": 2.8088, "step": 265 }, { "epoch": 0.14, "learning_rate": 4.991073071851889e-05, "loss": 2.9979, "step": 270 }, { "epoch": 0.14, "learning_rate": 4.990737078059875e-05, "loss": 3.0171, "step": 275 }, { "epoch": 0.14, "learning_rate": 4.990394889159986e-05, "loss": 2.9278, "step": 280 }, { "epoch": 0.14, "learning_rate": 4.9900465060033364e-05, "loss": 2.7998, "step": 285 }, { "epoch": 0.15, "learning_rate": 4.989691929456443e-05, "loss": 2.721, "step": 290 }, { "epoch": 0.15, "learning_rate": 4.9893311604012306e-05, "loss": 3.0291, "step": 295 }, { "epoch": 0.15, "learning_rate": 4.988964199735024e-05, "loss": 2.9777, "step": 300 }, { "epoch": 0.15, "learning_rate": 4.988591048370552e-05, "loss": 2.318, "step": 305 }, { "epoch": 0.16, "learning_rate": 4.988211707235936e-05, "loss": 3.0332, "step": 310 }, { "epoch": 0.16, "learning_rate": 4.987826177274697e-05, "loss": 2.4888, "step": 315 }, { "epoch": 0.16, "learning_rate": 4.987434459445748e-05, "loss": 2.9259, "step": 320 }, { "epoch": 0.16, "learning_rate": 4.987036554723391e-05, "loss": 2.9568, "step": 325 }, { "epoch": 0.17, "learning_rate": 4.98663246409732e-05, "loss": 2.8708, "step": 330 }, { "epoch": 0.17, "learning_rate": 4.986222188572611e-05, "loss": 2.7848, "step": 335 }, { "epoch": 0.17, "learning_rate": 4.985805729169728e-05, "loss": 2.6178, "step": 340 }, { "epoch": 0.17, "learning_rate": 4.985383086924511e-05, "loss": 2.8326, "step": 345 }, { "epoch": 0.18, "learning_rate": 4.984954262888182e-05, "loss": 2.8845, "step": 350 }, { "epoch": 0.18, "learning_rate": 4.9845192581273365e-05, "loss": 2.6151, "step": 355 }, { "epoch": 0.18, "learning_rate": 4.984078073723944e-05, "loss": 2.8474, "step": 360 }, { "epoch": 0.18, "learning_rate": 4.9836307107753455e-05, "loss": 2.808, "step": 365 }, { "epoch": 0.19, "learning_rate": 4.983177170394248e-05, "loss": 2.8491, "step": 370 }, { "epoch": 0.19, "learning_rate": 4.9827174537087226e-05, "loss": 2.7764, "step": 375 }, { "epoch": 0.19, "learning_rate": 4.982251561862205e-05, "loss": 2.7582, "step": 380 }, { "epoch": 0.19, "learning_rate": 4.981779496013489e-05, "loss": 2.5379, "step": 385 }, { "epoch": 0.2, "learning_rate": 4.981301257336723e-05, "loss": 2.9937, "step": 390 }, { "epoch": 0.2, "learning_rate": 4.980816847021412e-05, "loss": 2.8574, "step": 395 }, { "epoch": 0.2, "learning_rate": 4.980326266272409e-05, "loss": 2.9369, "step": 400 }, { "epoch": 0.2, "learning_rate": 4.979829516309915e-05, "loss": 2.836, "step": 405 }, { "epoch": 0.21, "learning_rate": 4.979326598369477e-05, "loss": 2.9369, "step": 410 }, { "epoch": 0.21, "learning_rate": 4.9788175137019814e-05, "loss": 2.6667, "step": 415 }, { "epoch": 0.21, "learning_rate": 4.9783022635736534e-05, "loss": 2.999, "step": 420 }, { "epoch": 0.21, "learning_rate": 4.977780849266054e-05, "loss": 2.907, "step": 425 }, { "epoch": 0.22, "learning_rate": 4.9772532720760744e-05, "loss": 2.8028, "step": 430 }, { "epoch": 0.22, "learning_rate": 4.976719533315937e-05, "loss": 2.7999, "step": 435 }, { "epoch": 0.22, "learning_rate": 4.976179634313187e-05, "loss": 2.8918, "step": 440 }, { "epoch": 0.22, "learning_rate": 4.9756335764106944e-05, "loss": 2.7926, "step": 445 }, { "epoch": 0.23, "learning_rate": 4.975081360966646e-05, "loss": 2.6709, "step": 450 }, { "epoch": 0.23, "learning_rate": 4.9745229893545436e-05, "loss": 2.8248, "step": 455 }, { "epoch": 0.23, "learning_rate": 4.973958462963203e-05, "loss": 3.1146, "step": 460 }, { "epoch": 0.23, "learning_rate": 4.973387783196747e-05, "loss": 2.9991, "step": 465 }, { "epoch": 0.24, "learning_rate": 4.972810951474605e-05, "loss": 2.7726, "step": 470 }, { "epoch": 0.24, "learning_rate": 4.972227969231505e-05, "loss": 2.9025, "step": 475 }, { "epoch": 0.24, "learning_rate": 4.971638837917475e-05, "loss": 2.6521, "step": 480 }, { "epoch": 0.24, "learning_rate": 4.971043558997839e-05, "loss": 2.9511, "step": 485 }, { "epoch": 0.25, "learning_rate": 4.9704421339532075e-05, "loss": 2.6938, "step": 490 }, { "epoch": 0.25, "learning_rate": 4.969834564279482e-05, "loss": 2.8533, "step": 495 }, { "epoch": 0.25, "learning_rate": 4.9692208514878444e-05, "loss": 2.6411, "step": 500 }, { "epoch": 0.25, "learning_rate": 4.968600997104758e-05, "loss": 2.6486, "step": 505 }, { "epoch": 0.26, "learning_rate": 4.967975002671961e-05, "loss": 2.8561, "step": 510 }, { "epoch": 0.26, "learning_rate": 4.967342869746463e-05, "loss": 2.6984, "step": 515 }, { "epoch": 0.26, "learning_rate": 4.9667045999005424e-05, "loss": 2.91, "step": 520 }, { "epoch": 0.26, "learning_rate": 4.966060194721742e-05, "loss": 2.7205, "step": 525 }, { "epoch": 0.27, "learning_rate": 4.965409655812865e-05, "loss": 2.7634, "step": 530 }, { "epoch": 0.27, "learning_rate": 4.9647529847919684e-05, "loss": 2.9647, "step": 535 }, { "epoch": 0.27, "learning_rate": 4.964090183292364e-05, "loss": 2.6357, "step": 540 }, { "epoch": 0.27, "learning_rate": 4.963421252962609e-05, "loss": 3.0285, "step": 545 }, { "epoch": 0.28, "learning_rate": 4.96274619546651e-05, "loss": 2.9895, "step": 550 }, { "epoch": 0.28, "learning_rate": 4.962065012483106e-05, "loss": 2.7286, "step": 555 }, { "epoch": 0.28, "learning_rate": 4.961377705706677e-05, "loss": 3.1337, "step": 560 }, { "epoch": 0.28, "learning_rate": 4.960684276846733e-05, "loss": 2.8268, "step": 565 }, { "epoch": 0.29, "learning_rate": 4.959984727628011e-05, "loss": 2.5851, "step": 570 }, { "epoch": 0.29, "learning_rate": 4.959279059790471e-05, "loss": 2.9359, "step": 575 }, { "epoch": 0.29, "learning_rate": 4.958567275089291e-05, "loss": 2.8842, "step": 580 }, { "epoch": 0.29, "learning_rate": 4.957849375294864e-05, "loss": 2.6186, "step": 585 }, { "epoch": 0.3, "learning_rate": 4.957125362192794e-05, "loss": 3.0116, "step": 590 }, { "epoch": 0.3, "learning_rate": 4.956395237583887e-05, "loss": 2.7045, "step": 595 }, { "epoch": 0.3, "learning_rate": 4.9556590032841526e-05, "loss": 2.8766, "step": 600 }, { "epoch": 0.3, "learning_rate": 4.954916661124797e-05, "loss": 2.7858, "step": 605 }, { "epoch": 0.31, "learning_rate": 4.954168212952216e-05, "loss": 2.7379, "step": 610 }, { "epoch": 0.31, "learning_rate": 4.953413660627995e-05, "loss": 2.475, "step": 615 }, { "epoch": 0.31, "learning_rate": 4.9526530060289e-05, "loss": 2.8357, "step": 620 }, { "epoch": 0.31, "learning_rate": 4.951886251046876e-05, "loss": 2.9284, "step": 625 }, { "epoch": 0.32, "learning_rate": 4.951113397589042e-05, "loss": 2.8144, "step": 630 }, { "epoch": 0.32, "learning_rate": 4.9503344475776846e-05, "loss": 2.6845, "step": 635 }, { "epoch": 0.32, "learning_rate": 4.9495494029502535e-05, "loss": 2.8937, "step": 640 }, { "epoch": 0.32, "learning_rate": 4.9487582656593575e-05, "loss": 3.0325, "step": 645 }, { "epoch": 0.33, "learning_rate": 4.94796103767276e-05, "loss": 2.7058, "step": 650 }, { "epoch": 0.33, "learning_rate": 4.9471577209733746e-05, "loss": 2.6162, "step": 655 }, { "epoch": 0.33, "learning_rate": 4.946348317559257e-05, "loss": 3.0129, "step": 660 }, { "epoch": 0.33, "learning_rate": 4.945532829443603e-05, "loss": 2.7587, "step": 665 }, { "epoch": 0.34, "learning_rate": 4.944711258654742e-05, "loss": 2.8915, "step": 670 }, { "epoch": 0.34, "learning_rate": 4.943883607236135e-05, "loss": 2.7343, "step": 675 }, { "epoch": 0.34, "learning_rate": 4.943049877246364e-05, "loss": 2.881, "step": 680 }, { "epoch": 0.34, "learning_rate": 4.942210070759131e-05, "loss": 2.488, "step": 685 }, { "epoch": 0.35, "learning_rate": 4.941364189863253e-05, "loss": 2.896, "step": 690 }, { "epoch": 0.35, "learning_rate": 4.940512236662654e-05, "loss": 2.7757, "step": 695 }, { "epoch": 0.35, "learning_rate": 4.9396542132763634e-05, "loss": 2.6271, "step": 700 }, { "epoch": 0.35, "learning_rate": 4.938790121838506e-05, "loss": 2.6804, "step": 705 }, { "epoch": 0.36, "learning_rate": 4.937919964498302e-05, "loss": 2.7313, "step": 710 }, { "epoch": 0.36, "learning_rate": 4.937043743420058e-05, "loss": 2.9277, "step": 715 }, { "epoch": 0.36, "learning_rate": 4.9361614607831605e-05, "loss": 2.6366, "step": 720 }, { "epoch": 0.36, "learning_rate": 4.935273118782078e-05, "loss": 3.0556, "step": 725 }, { "epoch": 0.37, "learning_rate": 4.934378719626345e-05, "loss": 3.0182, "step": 730 }, { "epoch": 0.37, "learning_rate": 4.933478265540564e-05, "loss": 2.824, "step": 735 }, { "epoch": 0.37, "learning_rate": 4.932571758764398e-05, "loss": 2.636, "step": 740 }, { "epoch": 0.37, "learning_rate": 4.931659201552563e-05, "loss": 2.7025, "step": 745 }, { "epoch": 0.38, "learning_rate": 4.930740596174827e-05, "loss": 2.8919, "step": 750 }, { "epoch": 0.38, "learning_rate": 4.9298159449159965e-05, "loss": 2.8434, "step": 755 }, { "epoch": 0.38, "learning_rate": 4.928885250075921e-05, "loss": 2.9448, "step": 760 }, { "epoch": 0.38, "learning_rate": 4.927948513969478e-05, "loss": 2.7312, "step": 765 }, { "epoch": 0.39, "learning_rate": 4.927005738926573e-05, "loss": 2.8688, "step": 770 }, { "epoch": 0.39, "learning_rate": 4.926056927292132e-05, "loss": 2.8639, "step": 775 }, { "epoch": 0.39, "learning_rate": 4.925102081426095e-05, "loss": 2.7809, "step": 780 }, { "epoch": 0.39, "learning_rate": 4.9241412037034115e-05, "loss": 3.0111, "step": 785 }, { "epoch": 0.4, "learning_rate": 4.9231742965140314e-05, "loss": 2.7252, "step": 790 }, { "epoch": 0.4, "learning_rate": 4.922201362262905e-05, "loss": 2.9717, "step": 795 }, { "epoch": 0.4, "learning_rate": 4.92122240336997e-05, "loss": 2.7191, "step": 800 }, { "epoch": 0.4, "learning_rate": 4.920237422270153e-05, "loss": 2.9346, "step": 805 }, { "epoch": 0.41, "learning_rate": 4.9192464214133536e-05, "loss": 2.7967, "step": 810 }, { "epoch": 0.41, "learning_rate": 4.9182494032644496e-05, "loss": 2.7326, "step": 815 }, { "epoch": 0.41, "learning_rate": 4.917246370303284e-05, "loss": 2.8933, "step": 820 }, { "epoch": 0.41, "learning_rate": 4.9162373250246575e-05, "loss": 2.7939, "step": 825 }, { "epoch": 0.42, "learning_rate": 4.9152222699383273e-05, "loss": 2.7807, "step": 830 }, { "epoch": 0.42, "learning_rate": 4.9142012075689994e-05, "loss": 2.6996, "step": 835 }, { "epoch": 0.42, "learning_rate": 4.913174140456319e-05, "loss": 2.7569, "step": 840 }, { "epoch": 0.42, "learning_rate": 4.912141071154869e-05, "loss": 2.9347, "step": 845 }, { "epoch": 0.43, "learning_rate": 4.911102002234159e-05, "loss": 2.7251, "step": 850 }, { "epoch": 0.43, "learning_rate": 4.910056936278623e-05, "loss": 3.1228, "step": 855 }, { "epoch": 0.43, "learning_rate": 4.90900587588761e-05, "loss": 2.9902, "step": 860 }, { "epoch": 0.43, "learning_rate": 4.9079488236753803e-05, "loss": 2.5095, "step": 865 }, { "epoch": 0.44, "learning_rate": 4.906885782271095e-05, "loss": 2.7523, "step": 870 }, { "epoch": 0.44, "learning_rate": 4.905816754318814e-05, "loss": 2.6656, "step": 875 }, { "epoch": 0.44, "learning_rate": 4.9047417424774874e-05, "loss": 2.8454, "step": 880 }, { "epoch": 0.44, "learning_rate": 4.903660749420946e-05, "loss": 2.8194, "step": 885 }, { "epoch": 0.45, "learning_rate": 4.9025737778379025e-05, "loss": 2.8421, "step": 890 }, { "epoch": 0.45, "learning_rate": 4.9014808304319326e-05, "loss": 2.9656, "step": 895 }, { "epoch": 0.45, "learning_rate": 4.900381909921482e-05, "loss": 2.7484, "step": 900 }, { "epoch": 0.45, "learning_rate": 4.899277019039849e-05, "loss": 2.9044, "step": 905 }, { "epoch": 0.46, "learning_rate": 4.898166160535186e-05, "loss": 2.8016, "step": 910 }, { "epoch": 0.46, "learning_rate": 4.8970493371704826e-05, "loss": 2.6278, "step": 915 }, { "epoch": 0.46, "learning_rate": 4.895926551723569e-05, "loss": 2.7214, "step": 920 }, { "epoch": 0.46, "learning_rate": 4.8947978069871036e-05, "loss": 2.7679, "step": 925 }, { "epoch": 0.47, "learning_rate": 4.8936631057685654e-05, "loss": 2.7196, "step": 930 }, { "epoch": 0.47, "learning_rate": 4.8925224508902514e-05, "loss": 2.7866, "step": 935 }, { "epoch": 0.47, "learning_rate": 4.8913758451892644e-05, "loss": 2.72, "step": 940 }, { "epoch": 0.47, "learning_rate": 4.89022329151751e-05, "loss": 2.752, "step": 945 }, { "epoch": 0.48, "learning_rate": 4.8890647927416887e-05, "loss": 3.0487, "step": 950 }, { "epoch": 0.48, "learning_rate": 4.8879003517432857e-05, "loss": 2.8928, "step": 955 }, { "epoch": 0.48, "learning_rate": 4.886729971418568e-05, "loss": 2.7793, "step": 960 }, { "epoch": 0.48, "learning_rate": 4.8855536546785726e-05, "loss": 2.537, "step": 965 }, { "epoch": 0.49, "learning_rate": 4.884371404449105e-05, "loss": 2.8345, "step": 970 }, { "epoch": 0.49, "learning_rate": 4.8831832236707284e-05, "loss": 2.9673, "step": 975 }, { "epoch": 0.49, "learning_rate": 4.8819891152987546e-05, "loss": 2.8295, "step": 980 }, { "epoch": 0.49, "learning_rate": 4.880789082303241e-05, "loss": 3.0753, "step": 985 }, { "epoch": 0.5, "learning_rate": 4.879583127668979e-05, "loss": 2.6748, "step": 990 }, { "epoch": 0.5, "learning_rate": 4.878371254395492e-05, "loss": 2.8115, "step": 995 }, { "epoch": 0.5, "learning_rate": 4.877153465497022e-05, "loss": 2.7039, "step": 1000 }, { "epoch": 0.5, "learning_rate": 4.8759297640025235e-05, "loss": 2.9469, "step": 1005 }, { "epoch": 0.51, "learning_rate": 4.874700152955661e-05, "loss": 2.9745, "step": 1010 }, { "epoch": 0.51, "learning_rate": 4.8734646354147936e-05, "loss": 2.9341, "step": 1015 }, { "epoch": 0.51, "learning_rate": 4.8722232144529754e-05, "loss": 3.0511, "step": 1020 }, { "epoch": 0.51, "learning_rate": 4.870975893157941e-05, "loss": 2.5396, "step": 1025 }, { "epoch": 0.52, "learning_rate": 4.8697226746321004e-05, "loss": 2.6699, "step": 1030 }, { "epoch": 0.52, "learning_rate": 4.868463561992532e-05, "loss": 2.4887, "step": 1035 }, { "epoch": 0.52, "learning_rate": 4.867198558370977e-05, "loss": 2.4773, "step": 1040 }, { "epoch": 0.52, "learning_rate": 4.865927666913825e-05, "loss": 2.7612, "step": 1045 }, { "epoch": 0.53, "learning_rate": 4.864650890782113e-05, "loss": 2.9116, "step": 1050 }, { "epoch": 0.53, "learning_rate": 4.863368233151514e-05, "loss": 2.8205, "step": 1055 }, { "epoch": 0.53, "learning_rate": 4.862079697212329e-05, "loss": 2.6711, "step": 1060 }, { "epoch": 0.53, "learning_rate": 4.8607852861694804e-05, "loss": 3.1138, "step": 1065 }, { "epoch": 0.54, "learning_rate": 4.859485003242503e-05, "loss": 2.5603, "step": 1070 }, { "epoch": 0.54, "learning_rate": 4.858178851665539e-05, "loss": 2.7981, "step": 1075 }, { "epoch": 0.54, "learning_rate": 4.856866834687323e-05, "loss": 2.507, "step": 1080 }, { "epoch": 0.54, "learning_rate": 4.855548955571183e-05, "loss": 3.0315, "step": 1085 }, { "epoch": 0.55, "learning_rate": 4.8542252175950244e-05, "loss": 2.75, "step": 1090 }, { "epoch": 0.55, "learning_rate": 4.852895624051326e-05, "loss": 2.6794, "step": 1095 }, { "epoch": 0.55, "learning_rate": 4.851560178247132e-05, "loss": 2.8278, "step": 1100 }, { "epoch": 0.55, "learning_rate": 4.850218883504041e-05, "loss": 2.6993, "step": 1105 }, { "epoch": 0.56, "learning_rate": 4.8488717431582005e-05, "loss": 2.875, "step": 1110 }, { "epoch": 0.56, "learning_rate": 4.8475187605602974e-05, "loss": 2.6057, "step": 1115 }, { "epoch": 0.56, "learning_rate": 4.84615993907555e-05, "loss": 2.847, "step": 1120 }, { "epoch": 0.56, "learning_rate": 4.844795282083697e-05, "loss": 2.7652, "step": 1125 }, { "epoch": 0.57, "learning_rate": 4.843424792978997e-05, "loss": 2.8128, "step": 1130 }, { "epoch": 0.57, "learning_rate": 4.842048475170209e-05, "loss": 2.7077, "step": 1135 }, { "epoch": 0.57, "learning_rate": 4.840666332080592e-05, "loss": 2.7081, "step": 1140 }, { "epoch": 0.57, "learning_rate": 4.8392783671478934e-05, "loss": 2.6479, "step": 1145 }, { "epoch": 0.58, "learning_rate": 4.837884583824342e-05, "loss": 2.667, "step": 1150 }, { "epoch": 0.58, "learning_rate": 4.836484985576638e-05, "loss": 2.7514, "step": 1155 }, { "epoch": 0.58, "learning_rate": 4.835079575885944e-05, "loss": 2.5058, "step": 1160 }, { "epoch": 0.58, "learning_rate": 4.833668358247876e-05, "loss": 2.6183, "step": 1165 }, { "epoch": 0.59, "learning_rate": 4.8322513361725006e-05, "loss": 2.9959, "step": 1170 }, { "epoch": 0.59, "learning_rate": 4.830828513184317e-05, "loss": 2.5714, "step": 1175 }, { "epoch": 0.59, "learning_rate": 4.8293998928222536e-05, "loss": 2.965, "step": 1180 }, { "epoch": 0.59, "learning_rate": 4.827965478639661e-05, "loss": 2.2106, "step": 1185 }, { "epoch": 0.6, "learning_rate": 4.8265252742042965e-05, "loss": 2.7456, "step": 1190 }, { "epoch": 0.6, "learning_rate": 4.8250792830983225e-05, "loss": 2.5694, "step": 1195 }, { "epoch": 0.6, "learning_rate": 4.8236275089182936e-05, "loss": 2.6826, "step": 1200 }, { "epoch": 0.6, "learning_rate": 4.8221699552751465e-05, "loss": 2.878, "step": 1205 }, { "epoch": 0.61, "learning_rate": 4.820706625794196e-05, "loss": 2.8191, "step": 1210 }, { "epoch": 0.61, "learning_rate": 4.81923752411512e-05, "loss": 2.739, "step": 1215 }, { "epoch": 0.61, "learning_rate": 4.8177626538919565e-05, "loss": 3.0544, "step": 1220 }, { "epoch": 0.61, "learning_rate": 4.8162820187930875e-05, "loss": 2.8393, "step": 1225 }, { "epoch": 0.62, "learning_rate": 4.814795622501237e-05, "loss": 2.4457, "step": 1230 }, { "epoch": 0.62, "learning_rate": 4.813303468713456e-05, "loss": 2.8575, "step": 1235 }, { "epoch": 0.62, "learning_rate": 4.8118055611411197e-05, "loss": 2.8307, "step": 1240 }, { "epoch": 0.62, "learning_rate": 4.810301903509909e-05, "loss": 2.7951, "step": 1245 }, { "epoch": 0.63, "learning_rate": 4.8087924995598125e-05, "loss": 2.8456, "step": 1250 }, { "epoch": 0.63, "learning_rate": 4.807277353045106e-05, "loss": 2.3564, "step": 1255 }, { "epoch": 0.63, "learning_rate": 4.8057564677343524e-05, "loss": 2.5076, "step": 1260 }, { "epoch": 0.63, "learning_rate": 4.8042298474103884e-05, "loss": 2.605, "step": 1265 }, { "epoch": 0.64, "learning_rate": 4.8026974958703116e-05, "loss": 2.4782, "step": 1270 }, { "epoch": 0.64, "learning_rate": 4.8011594169254784e-05, "loss": 2.7193, "step": 1275 }, { "epoch": 0.64, "learning_rate": 4.799615614401488e-05, "loss": 2.8284, "step": 1280 }, { "epoch": 0.64, "learning_rate": 4.798066092138178e-05, "loss": 2.5378, "step": 1285 }, { "epoch": 0.65, "learning_rate": 4.796510853989612e-05, "loss": 2.7396, "step": 1290 }, { "epoch": 0.65, "learning_rate": 4.794949903824069e-05, "loss": 2.7948, "step": 1295 }, { "epoch": 0.65, "learning_rate": 4.793383245524035e-05, "loss": 2.7818, "step": 1300 }, { "epoch": 0.65, "learning_rate": 4.791810882986197e-05, "loss": 2.7334, "step": 1305 }, { "epoch": 0.66, "learning_rate": 4.7902328201214256e-05, "loss": 2.4824, "step": 1310 }, { "epoch": 0.66, "learning_rate": 4.7886490608547727e-05, "loss": 2.6131, "step": 1315 }, { "epoch": 0.66, "learning_rate": 4.7870596091254584e-05, "loss": 2.7778, "step": 1320 }, { "epoch": 0.66, "learning_rate": 4.7854644688868594e-05, "loss": 2.5263, "step": 1325 }, { "epoch": 0.67, "learning_rate": 4.783863644106502e-05, "loss": 2.7825, "step": 1330 }, { "epoch": 0.67, "learning_rate": 4.782257138766053e-05, "loss": 2.7902, "step": 1335 }, { "epoch": 0.67, "learning_rate": 4.7806449568613066e-05, "loss": 2.8333, "step": 1340 }, { "epoch": 0.67, "learning_rate": 4.779027102402177e-05, "loss": 2.856, "step": 1345 }, { "epoch": 0.68, "learning_rate": 4.777403579412686e-05, "loss": 2.8021, "step": 1350 }, { "epoch": 0.68, "learning_rate": 4.775774391930956e-05, "loss": 2.6639, "step": 1355 }, { "epoch": 0.68, "learning_rate": 4.7741395440091976e-05, "loss": 2.5226, "step": 1360 }, { "epoch": 0.68, "learning_rate": 4.772499039713702e-05, "loss": 2.6803, "step": 1365 }, { "epoch": 0.69, "learning_rate": 4.7708528831248274e-05, "loss": 2.4608, "step": 1370 }, { "epoch": 0.69, "learning_rate": 4.769201078336991e-05, "loss": 2.786, "step": 1375 }, { "epoch": 0.69, "learning_rate": 4.7675436294586586e-05, "loss": 2.8294, "step": 1380 }, { "epoch": 0.7, "learning_rate": 4.7658805406123356e-05, "loss": 2.6776, "step": 1385 }, { "epoch": 0.7, "learning_rate": 4.7642118159345544e-05, "loss": 2.8003, "step": 1390 }, { "epoch": 0.7, "learning_rate": 4.762537459575865e-05, "loss": 2.7796, "step": 1395 }, { "epoch": 0.7, "learning_rate": 4.7608574757008245e-05, "loss": 2.9156, "step": 1400 }, { "epoch": 0.71, "learning_rate": 4.7591718684879883e-05, "loss": 3.0521, "step": 1405 }, { "epoch": 0.71, "learning_rate": 4.7574806421298976e-05, "loss": 2.6469, "step": 1410 }, { "epoch": 0.71, "learning_rate": 4.755783800833071e-05, "loss": 2.8512, "step": 1415 }, { "epoch": 0.71, "learning_rate": 4.754081348817991e-05, "loss": 2.66, "step": 1420 }, { "epoch": 0.72, "learning_rate": 4.752373290319096e-05, "loss": 2.6625, "step": 1425 }, { "epoch": 0.72, "learning_rate": 4.7506596295847716e-05, "loss": 2.6711, "step": 1430 }, { "epoch": 0.72, "learning_rate": 4.7489403708773346e-05, "loss": 2.8951, "step": 1435 }, { "epoch": 0.72, "learning_rate": 4.747215518473026e-05, "loss": 2.7375, "step": 1440 }, { "epoch": 0.73, "learning_rate": 4.745485076662e-05, "loss": 2.8037, "step": 1445 }, { "epoch": 0.73, "learning_rate": 4.743749049748315e-05, "loss": 2.5375, "step": 1450 }, { "epoch": 0.73, "learning_rate": 4.742007442049918e-05, "loss": 2.7664, "step": 1455 }, { "epoch": 0.73, "learning_rate": 4.7402602578986374e-05, "loss": 2.9644, "step": 1460 }, { "epoch": 0.74, "learning_rate": 4.738507501640175e-05, "loss": 2.8212, "step": 1465 }, { "epoch": 0.74, "learning_rate": 4.736749177634087e-05, "loss": 2.7201, "step": 1470 }, { "epoch": 0.74, "learning_rate": 4.734985290253782e-05, "loss": 2.7087, "step": 1475 }, { "epoch": 0.74, "learning_rate": 4.7332158438865035e-05, "loss": 2.5502, "step": 1480 }, { "epoch": 0.75, "learning_rate": 4.731440842933322e-05, "loss": 2.7607, "step": 1485 }, { "epoch": 0.75, "learning_rate": 4.729660291809126e-05, "loss": 2.5601, "step": 1490 }, { "epoch": 0.75, "learning_rate": 4.727874194942606e-05, "loss": 2.5562, "step": 1495 }, { "epoch": 0.75, "learning_rate": 4.7260825567762486e-05, "loss": 2.5539, "step": 1500 }, { "epoch": 0.76, "learning_rate": 4.7242853817663204e-05, "loss": 2.6405, "step": 1505 }, { "epoch": 0.76, "learning_rate": 4.72248267438286e-05, "loss": 2.9237, "step": 1510 }, { "epoch": 0.76, "learning_rate": 4.72067443910967e-05, "loss": 3.0453, "step": 1515 }, { "epoch": 0.76, "learning_rate": 4.718860680444297e-05, "loss": 2.7176, "step": 1520 }, { "epoch": 0.77, "learning_rate": 4.71704140289803e-05, "loss": 2.6713, "step": 1525 }, { "epoch": 0.77, "learning_rate": 4.715216610995883e-05, "loss": 2.7284, "step": 1530 }, { "epoch": 0.77, "learning_rate": 4.713386309276585e-05, "loss": 2.5022, "step": 1535 }, { "epoch": 0.77, "learning_rate": 4.7115505022925706e-05, "loss": 2.8323, "step": 1540 }, { "epoch": 0.78, "learning_rate": 4.7097091946099666e-05, "loss": 2.7005, "step": 1545 }, { "epoch": 0.78, "learning_rate": 4.7078623908085825e-05, "loss": 2.8142, "step": 1550 }, { "epoch": 0.78, "learning_rate": 4.7060100954818974e-05, "loss": 2.8505, "step": 1555 }, { "epoch": 0.78, "learning_rate": 4.70415231323705e-05, "loss": 2.5892, "step": 1560 }, { "epoch": 0.79, "learning_rate": 4.7022890486948236e-05, "loss": 2.8951, "step": 1565 }, { "epoch": 0.79, "learning_rate": 4.700420306489641e-05, "loss": 2.7551, "step": 1570 }, { "epoch": 0.79, "learning_rate": 4.698546091269547e-05, "loss": 2.6814, "step": 1575 }, { "epoch": 0.79, "learning_rate": 4.696666407696201e-05, "loss": 2.8698, "step": 1580 }, { "epoch": 0.8, "learning_rate": 4.694781260444862e-05, "loss": 2.8389, "step": 1585 }, { "epoch": 0.8, "learning_rate": 4.6928906542043786e-05, "loss": 2.8353, "step": 1590 }, { "epoch": 0.8, "learning_rate": 4.690994593677179e-05, "loss": 2.6565, "step": 1595 }, { "epoch": 0.8, "learning_rate": 4.689093083579256e-05, "loss": 2.6958, "step": 1600 }, { "epoch": 0.81, "learning_rate": 4.687186128640157e-05, "loss": 2.6768, "step": 1605 }, { "epoch": 0.81, "learning_rate": 4.685273733602975e-05, "loss": 2.734, "step": 1610 }, { "epoch": 0.81, "learning_rate": 4.6833559032243284e-05, "loss": 2.5348, "step": 1615 }, { "epoch": 0.81, "learning_rate": 4.6814326422743594e-05, "loss": 2.7775, "step": 1620 }, { "epoch": 0.82, "learning_rate": 4.679503955536715e-05, "loss": 2.6578, "step": 1625 }, { "epoch": 0.82, "learning_rate": 4.6775698478085393e-05, "loss": 2.8792, "step": 1630 }, { "epoch": 0.82, "learning_rate": 4.675630323900458e-05, "loss": 2.7883, "step": 1635 }, { "epoch": 0.82, "learning_rate": 4.67368538863657e-05, "loss": 2.8824, "step": 1640 }, { "epoch": 0.83, "learning_rate": 4.671735046854433e-05, "loss": 2.6775, "step": 1645 }, { "epoch": 0.83, "learning_rate": 4.669779303405051e-05, "loss": 2.5658, "step": 1650 }, { "epoch": 0.83, "learning_rate": 4.667818163152864e-05, "loss": 2.5262, "step": 1655 }, { "epoch": 0.83, "learning_rate": 4.665851630975736e-05, "loss": 2.5749, "step": 1660 }, { "epoch": 0.84, "learning_rate": 4.6638797117649424e-05, "loss": 2.8718, "step": 1665 }, { "epoch": 0.84, "learning_rate": 4.661902410425155e-05, "loss": 2.8039, "step": 1670 }, { "epoch": 0.84, "learning_rate": 4.659919731874435e-05, "loss": 2.8089, "step": 1675 }, { "epoch": 0.84, "learning_rate": 4.6579316810442174e-05, "loss": 2.8144, "step": 1680 }, { "epoch": 0.85, "learning_rate": 4.6559382628792995e-05, "loss": 2.5963, "step": 1685 }, { "epoch": 0.85, "learning_rate": 4.653939482337828e-05, "loss": 2.5755, "step": 1690 }, { "epoch": 0.85, "learning_rate": 4.651935344391286e-05, "loss": 2.7631, "step": 1695 }, { "epoch": 0.85, "learning_rate": 4.649925854024486e-05, "loss": 2.8117, "step": 1700 }, { "epoch": 0.86, "learning_rate": 4.647911016235549e-05, "loss": 2.7352, "step": 1705 }, { "epoch": 0.86, "learning_rate": 4.6458908360358985e-05, "loss": 2.5572, "step": 1710 }, { "epoch": 0.86, "learning_rate": 4.643865318450246e-05, "loss": 2.8372, "step": 1715 }, { "epoch": 0.86, "learning_rate": 4.6418344685165774e-05, "loss": 2.7892, "step": 1720 }, { "epoch": 0.87, "learning_rate": 4.639798291286143e-05, "loss": 2.7832, "step": 1725 }, { "epoch": 0.87, "learning_rate": 4.637756791823442e-05, "loss": 2.5401, "step": 1730 }, { "epoch": 0.87, "learning_rate": 4.635709975206213e-05, "loss": 2.9286, "step": 1735 }, { "epoch": 0.87, "learning_rate": 4.633657846525417e-05, "loss": 2.6474, "step": 1740 }, { "epoch": 0.88, "learning_rate": 4.6316004108852305e-05, "loss": 2.5047, "step": 1745 }, { "epoch": 0.88, "learning_rate": 4.629537673403029e-05, "loss": 2.8374, "step": 1750 }, { "epoch": 0.88, "learning_rate": 4.627469639209373e-05, "loss": 2.634, "step": 1755 }, { "epoch": 0.88, "learning_rate": 4.6253963134480006e-05, "loss": 2.6884, "step": 1760 }, { "epoch": 0.89, "learning_rate": 4.623317701275809e-05, "loss": 2.6334, "step": 1765 }, { "epoch": 0.89, "learning_rate": 4.621233807862844e-05, "loss": 2.764, "step": 1770 }, { "epoch": 0.89, "learning_rate": 4.6191446383922886e-05, "loss": 3.0864, "step": 1775 }, { "epoch": 0.89, "learning_rate": 4.617050198060448e-05, "loss": 2.7964, "step": 1780 }, { "epoch": 0.9, "learning_rate": 4.6149504920767376e-05, "loss": 2.4538, "step": 1785 }, { "epoch": 0.9, "learning_rate": 4.6128455256636706e-05, "loss": 2.7352, "step": 1790 }, { "epoch": 0.9, "learning_rate": 4.6107353040568416e-05, "loss": 2.6893, "step": 1795 }, { "epoch": 0.9, "learning_rate": 4.6086198325049185e-05, "loss": 2.8609, "step": 1800 }, { "epoch": 0.91, "learning_rate": 4.6064991162696275e-05, "loss": 2.5285, "step": 1805 }, { "epoch": 0.91, "learning_rate": 4.604373160625739e-05, "loss": 2.5707, "step": 1810 }, { "epoch": 0.91, "learning_rate": 4.602241970861053e-05, "loss": 2.7198, "step": 1815 }, { "epoch": 0.91, "learning_rate": 4.6001055522763926e-05, "loss": 2.855, "step": 1820 }, { "epoch": 0.92, "learning_rate": 4.597963910185582e-05, "loss": 2.4175, "step": 1825 }, { "epoch": 0.92, "learning_rate": 4.595817049915441e-05, "loss": 2.5444, "step": 1830 }, { "epoch": 0.92, "learning_rate": 4.5936649768057646e-05, "loss": 2.6893, "step": 1835 }, { "epoch": 0.92, "learning_rate": 4.591507696209318e-05, "loss": 2.6725, "step": 1840 }, { "epoch": 0.93, "learning_rate": 4.589345213491817e-05, "loss": 2.834, "step": 1845 }, { "epoch": 0.93, "learning_rate": 4.587177534031914e-05, "loss": 2.8259, "step": 1850 }, { "epoch": 0.93, "learning_rate": 4.585004663221188e-05, "loss": 2.6146, "step": 1855 }, { "epoch": 0.93, "learning_rate": 4.582826606464134e-05, "loss": 2.4673, "step": 1860 }, { "epoch": 0.94, "learning_rate": 4.5806433691781416e-05, "loss": 2.9178, "step": 1865 }, { "epoch": 0.94, "learning_rate": 4.578454956793487e-05, "loss": 2.9224, "step": 1870 }, { "epoch": 0.94, "learning_rate": 4.576261374753318e-05, "loss": 2.7987, "step": 1875 }, { "epoch": 0.94, "learning_rate": 4.574062628513642e-05, "loss": 2.3848, "step": 1880 }, { "epoch": 0.95, "learning_rate": 4.57185872354331e-05, "loss": 2.6054, "step": 1885 }, { "epoch": 0.95, "learning_rate": 4.569649665324003e-05, "loss": 2.6743, "step": 1890 }, { "epoch": 0.95, "learning_rate": 4.567435459350222e-05, "loss": 2.9375, "step": 1895 }, { "epoch": 0.95, "learning_rate": 4.565216111129269e-05, "loss": 2.9372, "step": 1900 }, { "epoch": 0.96, "learning_rate": 4.562991626181239e-05, "loss": 2.669, "step": 1905 }, { "epoch": 0.96, "learning_rate": 4.560762010039001e-05, "loss": 2.7644, "step": 1910 }, { "epoch": 0.96, "learning_rate": 4.558527268248187e-05, "loss": 2.6886, "step": 1915 }, { "epoch": 0.96, "learning_rate": 4.55628740636718e-05, "loss": 2.8618, "step": 1920 }, { "epoch": 0.97, "learning_rate": 4.554042429967095e-05, "loss": 2.8411, "step": 1925 }, { "epoch": 0.97, "learning_rate": 4.55179234463177e-05, "loss": 2.6047, "step": 1930 }, { "epoch": 0.97, "learning_rate": 4.5495371559577496e-05, "loss": 2.8675, "step": 1935 }, { "epoch": 0.97, "learning_rate": 4.547276869554271e-05, "loss": 2.751, "step": 1940 }, { "epoch": 0.98, "learning_rate": 4.545011491043253e-05, "loss": 2.8638, "step": 1945 }, { "epoch": 0.98, "learning_rate": 4.5427410260592775e-05, "loss": 2.5092, "step": 1950 }, { "epoch": 0.98, "learning_rate": 4.540465480249579e-05, "loss": 2.5059, "step": 1955 }, { "epoch": 0.98, "learning_rate": 4.5381848592740285e-05, "loss": 2.9433, "step": 1960 }, { "epoch": 0.99, "learning_rate": 4.535899168805121e-05, "loss": 2.6959, "step": 1965 }, { "epoch": 0.99, "learning_rate": 4.533608414527961e-05, "loss": 2.552, "step": 1970 }, { "epoch": 0.99, "learning_rate": 4.5313126021402465e-05, "loss": 2.7169, "step": 1975 }, { "epoch": 0.99, "learning_rate": 4.529011737352258e-05, "loss": 2.5672, "step": 1980 }, { "epoch": 1.0, "learning_rate": 4.526705825886841e-05, "loss": 2.6434, "step": 1985 }, { "epoch": 1.0, "learning_rate": 4.5243948734793947e-05, "loss": 2.8062, "step": 1990 }, { "epoch": 1.0, "learning_rate": 4.5220788858778556e-05, "loss": 2.6929, "step": 1995 }, { "epoch": 1.0, "learning_rate": 4.519757868842684e-05, "loss": 2.5837, "step": 2000 }, { "epoch": 1.01, "learning_rate": 4.517431828146852e-05, "loss": 2.821, "step": 2005 }, { "epoch": 1.01, "learning_rate": 4.515100769575824e-05, "loss": 2.7913, "step": 2010 }, { "epoch": 1.01, "learning_rate": 4.512764698927545e-05, "loss": 2.699, "step": 2015 }, { "epoch": 1.01, "learning_rate": 4.5104236220124286e-05, "loss": 2.6574, "step": 2020 }, { "epoch": 1.02, "learning_rate": 4.508077544653338e-05, "loss": 2.5909, "step": 2025 }, { "epoch": 1.02, "learning_rate": 4.5057264726855765e-05, "loss": 2.5695, "step": 2030 }, { "epoch": 1.02, "learning_rate": 4.5033704119568675e-05, "loss": 2.4937, "step": 2035 }, { "epoch": 1.02, "learning_rate": 4.501009368327344e-05, "loss": 2.7253, "step": 2040 }, { "epoch": 1.03, "learning_rate": 4.4986433476695334e-05, "loss": 2.8681, "step": 2045 }, { "epoch": 1.03, "learning_rate": 4.496272355868341e-05, "loss": 2.74, "step": 2050 }, { "epoch": 1.03, "learning_rate": 4.4938963988210365e-05, "loss": 2.7439, "step": 2055 }, { "epoch": 1.03, "learning_rate": 4.491515482437242e-05, "loss": 2.9539, "step": 2060 }, { "epoch": 1.04, "learning_rate": 4.4891296126389104e-05, "loss": 2.8165, "step": 2065 }, { "epoch": 1.04, "learning_rate": 4.48673879536032e-05, "loss": 2.601, "step": 2070 }, { "epoch": 1.04, "learning_rate": 4.484343036548051e-05, "loss": 2.5189, "step": 2075 }, { "epoch": 1.04, "learning_rate": 4.481942342160976e-05, "loss": 2.6276, "step": 2080 }, { "epoch": 1.05, "learning_rate": 4.479536718170243e-05, "loss": 2.5027, "step": 2085 }, { "epoch": 1.05, "learning_rate": 4.477126170559262e-05, "loss": 2.8654, "step": 2090 }, { "epoch": 1.05, "learning_rate": 4.474710705323688e-05, "loss": 2.8511, "step": 2095 }, { "epoch": 1.05, "learning_rate": 4.47229032847141e-05, "loss": 2.6129, "step": 2100 }, { "epoch": 1.06, "learning_rate": 4.469865046022531e-05, "loss": 2.8964, "step": 2105 }, { "epoch": 1.06, "learning_rate": 4.4674348640093554e-05, "loss": 2.7502, "step": 2110 }, { "epoch": 1.06, "learning_rate": 4.4649997884763765e-05, "loss": 2.591, "step": 2115 }, { "epoch": 1.06, "learning_rate": 4.462559825480257e-05, "loss": 2.7982, "step": 2120 }, { "epoch": 1.07, "learning_rate": 4.460114981089815e-05, "loss": 2.576, "step": 2125 }, { "epoch": 1.07, "learning_rate": 4.457665261386014e-05, "loss": 2.692, "step": 2130 }, { "epoch": 1.07, "learning_rate": 4.455210672461938e-05, "loss": 2.5818, "step": 2135 }, { "epoch": 1.07, "learning_rate": 4.452751220422787e-05, "loss": 2.6792, "step": 2140 }, { "epoch": 1.08, "learning_rate": 4.450286911385856e-05, "loss": 2.8352, "step": 2145 }, { "epoch": 1.08, "learning_rate": 4.4478177514805166e-05, "loss": 2.5787, "step": 2150 }, { "epoch": 1.08, "learning_rate": 4.4453437468482103e-05, "loss": 2.655, "step": 2155 }, { "epoch": 1.08, "learning_rate": 4.442864903642428e-05, "loss": 2.7664, "step": 2160 }, { "epoch": 1.09, "learning_rate": 4.440381228028692e-05, "loss": 2.7231, "step": 2165 }, { "epoch": 1.09, "learning_rate": 4.437892726184548e-05, "loss": 2.416, "step": 2170 }, { "epoch": 1.09, "learning_rate": 4.4353994042995446e-05, "loss": 2.4619, "step": 2175 }, { "epoch": 1.09, "learning_rate": 4.4329012685752183e-05, "loss": 2.7816, "step": 2180 }, { "epoch": 1.1, "learning_rate": 4.430398325225078e-05, "loss": 2.8678, "step": 2185 }, { "epoch": 1.1, "learning_rate": 4.427890580474594e-05, "loss": 2.6007, "step": 2190 }, { "epoch": 1.1, "learning_rate": 4.4253780405611754e-05, "loss": 2.8195, "step": 2195 }, { "epoch": 1.1, "learning_rate": 4.42286071173416e-05, "loss": 2.5117, "step": 2200 }, { "epoch": 1.11, "learning_rate": 4.4203386002547956e-05, "loss": 2.5527, "step": 2205 }, { "epoch": 1.11, "learning_rate": 4.417811712396226e-05, "loss": 2.662, "step": 2210 }, { "epoch": 1.11, "learning_rate": 4.415280054443477e-05, "loss": 2.7563, "step": 2215 }, { "epoch": 1.11, "learning_rate": 4.4127436326934354e-05, "loss": 2.5118, "step": 2220 }, { "epoch": 1.12, "learning_rate": 4.41020245345484e-05, "loss": 2.7208, "step": 2225 }, { "epoch": 1.12, "learning_rate": 4.4076565230482607e-05, "loss": 2.649, "step": 2230 }, { "epoch": 1.12, "learning_rate": 4.4051058478060856e-05, "loss": 2.652, "step": 2235 }, { "epoch": 1.12, "learning_rate": 4.402550434072505e-05, "loss": 2.6885, "step": 2240 }, { "epoch": 1.13, "learning_rate": 4.3999902882034935e-05, "loss": 2.8545, "step": 2245 }, { "epoch": 1.13, "learning_rate": 4.397425416566797e-05, "loss": 2.9435, "step": 2250 }, { "epoch": 1.13, "learning_rate": 4.3948558255419146e-05, "loss": 2.6555, "step": 2255 }, { "epoch": 1.13, "learning_rate": 4.392281521520085e-05, "loss": 2.6108, "step": 2260 }, { "epoch": 1.14, "learning_rate": 4.389702510904269e-05, "loss": 2.6256, "step": 2265 }, { "epoch": 1.14, "learning_rate": 4.387118800109133e-05, "loss": 2.7996, "step": 2270 }, { "epoch": 1.14, "learning_rate": 4.384530395561035e-05, "loss": 2.6649, "step": 2275 }, { "epoch": 1.14, "learning_rate": 4.381937303698006e-05, "loss": 3.0073, "step": 2280 }, { "epoch": 1.15, "learning_rate": 4.379339530969738e-05, "loss": 2.8493, "step": 2285 }, { "epoch": 1.15, "learning_rate": 4.3767370838375635e-05, "loss": 2.5572, "step": 2290 }, { "epoch": 1.15, "learning_rate": 4.374129968774443e-05, "loss": 2.3837, "step": 2295 }, { "epoch": 1.15, "learning_rate": 4.371518192264946e-05, "loss": 2.4604, "step": 2300 }, { "epoch": 1.16, "learning_rate": 4.3689017608052374e-05, "loss": 2.8866, "step": 2305 }, { "epoch": 1.16, "learning_rate": 4.3662806809030585e-05, "loss": 2.8943, "step": 2310 }, { "epoch": 1.16, "learning_rate": 4.3636549590777144e-05, "loss": 2.7629, "step": 2315 }, { "epoch": 1.16, "learning_rate": 4.361024601860054e-05, "loss": 2.8629, "step": 2320 }, { "epoch": 1.17, "learning_rate": 4.3583896157924574e-05, "loss": 2.7952, "step": 2325 }, { "epoch": 1.17, "learning_rate": 4.355750007428817e-05, "loss": 2.2057, "step": 2330 }, { "epoch": 1.17, "learning_rate": 4.3531057833345216e-05, "loss": 2.9143, "step": 2335 }, { "epoch": 1.17, "learning_rate": 4.3504569500864424e-05, "loss": 2.5354, "step": 2340 }, { "epoch": 1.18, "learning_rate": 4.347803514272911e-05, "loss": 2.7451, "step": 2345 }, { "epoch": 1.18, "learning_rate": 4.3451454824937113e-05, "loss": 3.0827, "step": 2350 }, { "epoch": 1.18, "learning_rate": 4.3424828613600555e-05, "loss": 2.5842, "step": 2355 }, { "epoch": 1.18, "learning_rate": 4.339815657494572e-05, "loss": 2.4492, "step": 2360 }, { "epoch": 1.19, "learning_rate": 4.3371438775312865e-05, "loss": 2.5067, "step": 2365 }, { "epoch": 1.19, "learning_rate": 4.334467528115608e-05, "loss": 2.5902, "step": 2370 }, { "epoch": 1.19, "learning_rate": 4.33178661590431e-05, "loss": 2.8618, "step": 2375 }, { "epoch": 1.19, "learning_rate": 4.329101147565515e-05, "loss": 2.6831, "step": 2380 }, { "epoch": 1.2, "learning_rate": 4.3264111297786794e-05, "loss": 2.7531, "step": 2385 }, { "epoch": 1.2, "learning_rate": 4.323716569234572e-05, "loss": 2.819, "step": 2390 }, { "epoch": 1.2, "learning_rate": 4.321017472635263e-05, "loss": 2.6319, "step": 2395 }, { "epoch": 1.2, "learning_rate": 4.318313846694105e-05, "loss": 2.3078, "step": 2400 }, { "epoch": 1.21, "learning_rate": 4.315605698135714e-05, "loss": 2.7962, "step": 2405 }, { "epoch": 1.21, "learning_rate": 4.312893033695958e-05, "loss": 2.8479, "step": 2410 }, { "epoch": 1.21, "learning_rate": 4.310175860121936e-05, "loss": 2.6289, "step": 2415 }, { "epoch": 1.21, "learning_rate": 4.30745418417196e-05, "loss": 2.7003, "step": 2420 }, { "epoch": 1.22, "learning_rate": 4.304728012615543e-05, "loss": 2.4947, "step": 2425 }, { "epoch": 1.22, "learning_rate": 4.3019973522333815e-05, "loss": 2.6911, "step": 2430 }, { "epoch": 1.22, "learning_rate": 4.2992622098173334e-05, "loss": 2.6931, "step": 2435 }, { "epoch": 1.22, "learning_rate": 4.296522592170406e-05, "loss": 2.774, "step": 2440 }, { "epoch": 1.23, "learning_rate": 4.293778506106737e-05, "loss": 2.759, "step": 2445 }, { "epoch": 1.23, "learning_rate": 4.29102995845158e-05, "loss": 2.5543, "step": 2450 }, { "epoch": 1.23, "learning_rate": 4.288276956041284e-05, "loss": 2.7702, "step": 2455 }, { "epoch": 1.23, "learning_rate": 4.285519505723278e-05, "loss": 2.835, "step": 2460 }, { "epoch": 1.24, "learning_rate": 4.282757614356055e-05, "loss": 2.6516, "step": 2465 }, { "epoch": 1.24, "learning_rate": 4.2799912888091544e-05, "loss": 2.7392, "step": 2470 }, { "epoch": 1.24, "learning_rate": 4.277220535963143e-05, "loss": 2.6522, "step": 2475 }, { "epoch": 1.24, "learning_rate": 4.274445362709601e-05, "loss": 2.6514, "step": 2480 }, { "epoch": 1.25, "learning_rate": 4.271665775951104e-05, "loss": 2.7507, "step": 2485 }, { "epoch": 1.25, "learning_rate": 4.2688817826012005e-05, "loss": 3.0499, "step": 2490 }, { "epoch": 1.25, "learning_rate": 4.2660933895844055e-05, "loss": 2.6927, "step": 2495 }, { "epoch": 1.25, "learning_rate": 4.2633006038361736e-05, "loss": 2.8456, "step": 2500 }, { "epoch": 1.26, "learning_rate": 4.2605034323028844e-05, "loss": 2.671, "step": 2505 }, { "epoch": 1.26, "learning_rate": 4.2577018819418296e-05, "loss": 2.6543, "step": 2510 }, { "epoch": 1.26, "learning_rate": 4.254895959721189e-05, "loss": 2.566, "step": 2515 }, { "epoch": 1.26, "learning_rate": 4.252085672620019e-05, "loss": 2.4943, "step": 2520 }, { "epoch": 1.27, "learning_rate": 4.249271027628228e-05, "loss": 2.5115, "step": 2525 }, { "epoch": 1.27, "learning_rate": 4.24645203174657e-05, "loss": 2.3859, "step": 2530 }, { "epoch": 1.27, "learning_rate": 4.243628691986617e-05, "loss": 2.8148, "step": 2535 }, { "epoch": 1.27, "learning_rate": 4.240801015370743e-05, "loss": 2.5597, "step": 2540 }, { "epoch": 1.28, "learning_rate": 4.2379690089321145e-05, "loss": 2.805, "step": 2545 }, { "epoch": 1.28, "learning_rate": 4.235132679714664e-05, "loss": 2.7308, "step": 2550 }, { "epoch": 1.28, "learning_rate": 4.232292034773076e-05, "loss": 2.675, "step": 2555 }, { "epoch": 1.28, "learning_rate": 4.2294470811727704e-05, "loss": 2.6359, "step": 2560 }, { "epoch": 1.29, "learning_rate": 4.226597825989883e-05, "loss": 2.4288, "step": 2565 }, { "epoch": 1.29, "learning_rate": 4.223744276311249e-05, "loss": 2.642, "step": 2570 }, { "epoch": 1.29, "learning_rate": 4.220886439234385e-05, "loss": 2.7375, "step": 2575 }, { "epoch": 1.29, "learning_rate": 4.218024321867472e-05, "loss": 2.6114, "step": 2580 }, { "epoch": 1.3, "learning_rate": 4.2151579313293364e-05, "loss": 2.4941, "step": 2585 }, { "epoch": 1.3, "learning_rate": 4.212287274749434e-05, "loss": 2.6086, "step": 2590 }, { "epoch": 1.3, "learning_rate": 4.2094123592678295e-05, "loss": 2.7854, "step": 2595 }, { "epoch": 1.3, "learning_rate": 4.206533192035184e-05, "loss": 2.8291, "step": 2600 }, { "epoch": 1.31, "learning_rate": 4.2036497802127294e-05, "loss": 2.6846, "step": 2605 }, { "epoch": 1.31, "learning_rate": 4.200762130972259e-05, "loss": 2.6667, "step": 2610 }, { "epoch": 1.31, "learning_rate": 4.197870251496103e-05, "loss": 2.7895, "step": 2615 }, { "epoch": 1.31, "learning_rate": 4.1949741489771155e-05, "loss": 2.6958, "step": 2620 }, { "epoch": 1.32, "learning_rate": 4.192073830618652e-05, "loss": 2.8536, "step": 2625 }, { "epoch": 1.32, "learning_rate": 4.189169303634555e-05, "loss": 2.5218, "step": 2630 }, { "epoch": 1.32, "learning_rate": 4.186260575249136e-05, "loss": 2.6141, "step": 2635 }, { "epoch": 1.32, "learning_rate": 4.1833476526971546e-05, "loss": 2.6231, "step": 2640 }, { "epoch": 1.33, "learning_rate": 4.1804305432238036e-05, "loss": 2.8229, "step": 2645 }, { "epoch": 1.33, "learning_rate": 4.1775092540846885e-05, "loss": 2.4763, "step": 2650 }, { "epoch": 1.33, "learning_rate": 4.174583792545813e-05, "loss": 2.5162, "step": 2655 }, { "epoch": 1.33, "learning_rate": 4.1716541658835574e-05, "loss": 2.7301, "step": 2660 }, { "epoch": 1.34, "learning_rate": 4.16872038138466e-05, "loss": 2.6055, "step": 2665 }, { "epoch": 1.34, "learning_rate": 4.165782446346203e-05, "loss": 2.6529, "step": 2670 }, { "epoch": 1.34, "learning_rate": 4.162840368075591e-05, "loss": 2.7934, "step": 2675 }, { "epoch": 1.34, "learning_rate": 4.159894153890536e-05, "loss": 2.9108, "step": 2680 }, { "epoch": 1.35, "learning_rate": 4.1569438111190326e-05, "loss": 2.6543, "step": 2685 }, { "epoch": 1.35, "learning_rate": 4.1539893470993496e-05, "loss": 2.6038, "step": 2690 }, { "epoch": 1.35, "learning_rate": 4.151030769180002e-05, "loss": 2.5741, "step": 2695 }, { "epoch": 1.35, "learning_rate": 4.14806808471974e-05, "loss": 2.8525, "step": 2700 }, { "epoch": 1.36, "learning_rate": 4.1451013010875275e-05, "loss": 2.5151, "step": 2705 }, { "epoch": 1.36, "learning_rate": 4.1421304256625206e-05, "loss": 2.5666, "step": 2710 }, { "epoch": 1.36, "learning_rate": 4.139155465834058e-05, "loss": 2.7287, "step": 2715 }, { "epoch": 1.36, "learning_rate": 4.136176429001634e-05, "loss": 2.8867, "step": 2720 }, { "epoch": 1.37, "learning_rate": 4.133193322574885e-05, "loss": 2.6398, "step": 2725 }, { "epoch": 1.37, "learning_rate": 4.130206153973568e-05, "loss": 2.699, "step": 2730 }, { "epoch": 1.37, "learning_rate": 4.1272149306275447e-05, "loss": 2.5248, "step": 2735 }, { "epoch": 1.37, "learning_rate": 4.124219659976762e-05, "loss": 2.8947, "step": 2740 }, { "epoch": 1.38, "learning_rate": 4.1212203494712344e-05, "loss": 2.6473, "step": 2745 }, { "epoch": 1.38, "learning_rate": 4.1182170065710226e-05, "loss": 2.3734, "step": 2750 }, { "epoch": 1.38, "learning_rate": 4.115209638746218e-05, "loss": 2.685, "step": 2755 }, { "epoch": 1.39, "learning_rate": 4.1121982534769224e-05, "loss": 2.9712, "step": 2760 }, { "epoch": 1.39, "learning_rate": 4.109182858253231e-05, "loss": 2.6578, "step": 2765 }, { "epoch": 1.39, "learning_rate": 4.106163460575212e-05, "loss": 2.6842, "step": 2770 }, { "epoch": 1.39, "learning_rate": 4.10314006795289e-05, "loss": 2.511, "step": 2775 }, { "epoch": 1.4, "learning_rate": 4.100112687906224e-05, "loss": 2.8426, "step": 2780 }, { "epoch": 1.4, "learning_rate": 4.097081327965092e-05, "loss": 2.8462, "step": 2785 }, { "epoch": 1.4, "learning_rate": 4.094045995669271e-05, "loss": 2.7552, "step": 2790 }, { "epoch": 1.4, "learning_rate": 4.091006698568419e-05, "loss": 2.3802, "step": 2795 }, { "epoch": 1.41, "learning_rate": 4.087963444222054e-05, "loss": 2.3967, "step": 2800 }, { "epoch": 1.41, "learning_rate": 4.084916240199537e-05, "loss": 2.7945, "step": 2805 }, { "epoch": 1.41, "learning_rate": 4.0818650940800524e-05, "loss": 2.5304, "step": 2810 }, { "epoch": 1.41, "learning_rate": 4.0788100134525925e-05, "loss": 2.6779, "step": 2815 }, { "epoch": 1.42, "learning_rate": 4.075751005915932e-05, "loss": 2.6202, "step": 2820 }, { "epoch": 1.42, "learning_rate": 4.072688079078616e-05, "loss": 2.5915, "step": 2825 }, { "epoch": 1.42, "learning_rate": 4.069621240558935e-05, "loss": 2.5139, "step": 2830 }, { "epoch": 1.42, "learning_rate": 4.066550497984911e-05, "loss": 2.5506, "step": 2835 }, { "epoch": 1.43, "learning_rate": 4.063475858994276e-05, "loss": 2.7154, "step": 2840 }, { "epoch": 1.43, "learning_rate": 4.060397331234452e-05, "loss": 2.6309, "step": 2845 }, { "epoch": 1.43, "learning_rate": 4.0573149223625365e-05, "loss": 2.6922, "step": 2850 }, { "epoch": 1.43, "learning_rate": 4.054228640045276e-05, "loss": 2.703, "step": 2855 }, { "epoch": 1.44, "learning_rate": 4.051138491959053e-05, "loss": 2.3475, "step": 2860 }, { "epoch": 1.44, "learning_rate": 4.048044485789869e-05, "loss": 2.7186, "step": 2865 }, { "epoch": 1.44, "learning_rate": 4.044946629233316e-05, "loss": 2.4667, "step": 2870 }, { "epoch": 1.44, "learning_rate": 4.041844929994566e-05, "loss": 2.562, "step": 2875 }, { "epoch": 1.45, "learning_rate": 4.038739395788347e-05, "loss": 2.4116, "step": 2880 }, { "epoch": 1.45, "learning_rate": 4.0356300343389276e-05, "loss": 2.6133, "step": 2885 }, { "epoch": 1.45, "learning_rate": 4.032516853380094e-05, "loss": 2.6893, "step": 2890 }, { "epoch": 1.45, "learning_rate": 4.029399860655132e-05, "loss": 2.8196, "step": 2895 }, { "epoch": 1.46, "learning_rate": 4.026279063916811e-05, "loss": 2.8933, "step": 2900 }, { "epoch": 1.46, "learning_rate": 4.023154470927361e-05, "loss": 3.0289, "step": 2905 }, { "epoch": 1.46, "learning_rate": 4.0200260894584516e-05, "loss": 2.5586, "step": 2910 }, { "epoch": 1.46, "learning_rate": 4.016893927291179e-05, "loss": 2.785, "step": 2915 }, { "epoch": 1.47, "learning_rate": 4.0137579922160395e-05, "loss": 2.5293, "step": 2920 }, { "epoch": 1.47, "learning_rate": 4.010618292032917e-05, "loss": 2.6696, "step": 2925 }, { "epoch": 1.47, "learning_rate": 4.007474834551058e-05, "loss": 2.7003, "step": 2930 }, { "epoch": 1.47, "learning_rate": 4.004327627589056e-05, "loss": 2.6005, "step": 2935 }, { "epoch": 1.48, "learning_rate": 4.001176678974828e-05, "loss": 2.7198, "step": 2940 }, { "epoch": 1.48, "learning_rate": 3.998021996545599e-05, "loss": 2.5329, "step": 2945 }, { "epoch": 1.48, "learning_rate": 3.994863588147881e-05, "loss": 2.7051, "step": 2950 }, { "epoch": 1.48, "learning_rate": 3.9917014616374535e-05, "loss": 2.9277, "step": 2955 }, { "epoch": 1.49, "learning_rate": 3.988535624879344e-05, "loss": 2.3729, "step": 2960 }, { "epoch": 1.49, "learning_rate": 3.985366085747808e-05, "loss": 2.5122, "step": 2965 }, { "epoch": 1.49, "learning_rate": 3.982192852126309e-05, "loss": 2.4413, "step": 2970 }, { "epoch": 1.49, "learning_rate": 3.979015931907501e-05, "loss": 2.6104, "step": 2975 }, { "epoch": 1.5, "learning_rate": 3.975835332993207e-05, "loss": 2.8855, "step": 2980 }, { "epoch": 1.5, "learning_rate": 3.9726510632944e-05, "loss": 2.7487, "step": 2985 }, { "epoch": 1.5, "learning_rate": 3.969463130731183e-05, "loss": 2.7085, "step": 2990 }, { "epoch": 1.5, "learning_rate": 3.966271543232769e-05, "loss": 2.6464, "step": 2995 }, { "epoch": 1.51, "learning_rate": 3.9630763087374625e-05, "loss": 2.4105, "step": 3000 }, { "epoch": 1.51, "learning_rate": 3.9598774351926394e-05, "loss": 2.7296, "step": 3005 }, { "epoch": 1.51, "learning_rate": 3.956674930554725e-05, "loss": 2.5319, "step": 3010 }, { "epoch": 1.51, "learning_rate": 3.9534688027891785e-05, "loss": 2.5544, "step": 3015 }, { "epoch": 1.52, "learning_rate": 3.9502590598704696e-05, "loss": 2.7981, "step": 3020 }, { "epoch": 1.52, "learning_rate": 3.94704570978206e-05, "loss": 2.6186, "step": 3025 }, { "epoch": 1.52, "learning_rate": 3.943828760516382e-05, "loss": 2.6443, "step": 3030 }, { "epoch": 1.52, "learning_rate": 3.940608220074822e-05, "loss": 2.4564, "step": 3035 }, { "epoch": 1.53, "learning_rate": 3.9373840964676976e-05, "loss": 2.8394, "step": 3040 }, { "epoch": 1.53, "learning_rate": 3.934156397714238e-05, "loss": 2.3683, "step": 3045 }, { "epoch": 1.53, "learning_rate": 3.930925131842567e-05, "loss": 2.875, "step": 3050 }, { "epoch": 1.53, "learning_rate": 3.9276903068896784e-05, "loss": 2.6381, "step": 3055 }, { "epoch": 1.54, "learning_rate": 3.9244519309014206e-05, "loss": 2.8077, "step": 3060 }, { "epoch": 1.54, "learning_rate": 3.9212100119324706e-05, "loss": 2.6208, "step": 3065 }, { "epoch": 1.54, "learning_rate": 3.917964558046322e-05, "loss": 2.9, "step": 3070 }, { "epoch": 1.54, "learning_rate": 3.9147155773152586e-05, "loss": 2.5678, "step": 3075 }, { "epoch": 1.55, "learning_rate": 3.911463077820336e-05, "loss": 2.7059, "step": 3080 }, { "epoch": 1.55, "learning_rate": 3.90820706765136e-05, "loss": 2.7433, "step": 3085 }, { "epoch": 1.55, "learning_rate": 3.9049475549068757e-05, "loss": 2.5916, "step": 3090 }, { "epoch": 1.55, "learning_rate": 3.901684547694132e-05, "loss": 2.6978, "step": 3095 }, { "epoch": 1.56, "learning_rate": 3.8984180541290724e-05, "loss": 2.8709, "step": 3100 }, { "epoch": 1.56, "learning_rate": 3.895148082336313e-05, "loss": 2.8652, "step": 3105 }, { "epoch": 1.56, "learning_rate": 3.89187464044912e-05, "loss": 3.0331, "step": 3110 }, { "epoch": 1.56, "learning_rate": 3.8885977366093905e-05, "loss": 2.7334, "step": 3115 }, { "epoch": 1.57, "learning_rate": 3.885317378967633e-05, "loss": 2.6026, "step": 3120 }, { "epoch": 1.57, "learning_rate": 3.882033575682945e-05, "loss": 2.831, "step": 3125 }, { "epoch": 1.57, "learning_rate": 3.878746334922996e-05, "loss": 2.5585, "step": 3130 }, { "epoch": 1.57, "learning_rate": 3.875455664864005e-05, "loss": 2.762, "step": 3135 }, { "epoch": 1.58, "learning_rate": 3.8721615736907205e-05, "loss": 2.769, "step": 3140 }, { "epoch": 1.58, "learning_rate": 3.868864069596399e-05, "loss": 2.6496, "step": 3145 }, { "epoch": 1.58, "learning_rate": 3.8655631607827876e-05, "loss": 2.486, "step": 3150 }, { "epoch": 1.58, "learning_rate": 3.8622588554601e-05, "loss": 2.8387, "step": 3155 }, { "epoch": 1.59, "learning_rate": 3.858951161847001e-05, "loss": 2.816, "step": 3160 }, { "epoch": 1.59, "learning_rate": 3.855640088170579e-05, "loss": 2.8128, "step": 3165 }, { "epoch": 1.59, "learning_rate": 3.8523256426663313e-05, "loss": 2.5875, "step": 3170 }, { "epoch": 1.59, "learning_rate": 3.8490078335781423e-05, "loss": 2.5853, "step": 3175 }, { "epoch": 1.6, "learning_rate": 3.845686669158263e-05, "loss": 2.7638, "step": 3180 }, { "epoch": 1.6, "learning_rate": 3.842362157667287e-05, "loss": 2.8281, "step": 3185 }, { "epoch": 1.6, "learning_rate": 3.839700144139754e-05, "loss": 2.3574, "step": 3190 }, { "epoch": 1.6, "learning_rate": 3.836369628764067e-05, "loss": 2.5533, "step": 3195 }, { "epoch": 1.61, "learning_rate": 3.833035789491177e-05, "loss": 2.4513, "step": 3200 }, { "epoch": 1.61, "learning_rate": 3.8296986346132036e-05, "loss": 2.567, "step": 3205 }, { "epoch": 1.61, "learning_rate": 3.826358172430516e-05, "loss": 2.6501, "step": 3210 }, { "epoch": 1.61, "learning_rate": 3.823014411251708e-05, "loss": 2.6927, "step": 3215 }, { "epoch": 1.62, "learning_rate": 3.819667359393578e-05, "loss": 2.6094, "step": 3220 }, { "epoch": 1.62, "learning_rate": 3.816317025181111e-05, "loss": 2.6776, "step": 3225 }, { "epoch": 1.62, "learning_rate": 3.8129634169474563e-05, "loss": 2.5833, "step": 3230 }, { "epoch": 1.62, "learning_rate": 3.809606543033905e-05, "loss": 2.6483, "step": 3235 }, { "epoch": 1.63, "learning_rate": 3.8062464117898724e-05, "loss": 2.4814, "step": 3240 }, { "epoch": 1.63, "learning_rate": 3.802883031572874e-05, "loss": 2.5217, "step": 3245 }, { "epoch": 1.63, "learning_rate": 3.799516410748506e-05, "loss": 2.5127, "step": 3250 }, { "epoch": 1.63, "learning_rate": 3.796146557690428e-05, "loss": 2.9325, "step": 3255 }, { "epoch": 1.64, "learning_rate": 3.792773480780335e-05, "loss": 2.4567, "step": 3260 }, { "epoch": 1.64, "learning_rate": 3.789397188407944e-05, "loss": 2.6045, "step": 3265 }, { "epoch": 1.64, "learning_rate": 3.786017688970967e-05, "loss": 2.5031, "step": 3270 }, { "epoch": 1.64, "learning_rate": 3.782634990875094e-05, "loss": 2.7692, "step": 3275 }, { "epoch": 1.65, "learning_rate": 3.779249102533972e-05, "loss": 2.6893, "step": 3280 }, { "epoch": 1.65, "learning_rate": 3.7758600323691806e-05, "loss": 2.604, "step": 3285 }, { "epoch": 1.65, "learning_rate": 3.7724677888102145e-05, "loss": 2.6633, "step": 3290 }, { "epoch": 1.65, "learning_rate": 3.769072380294463e-05, "loss": 2.4804, "step": 3295 }, { "epoch": 1.66, "learning_rate": 3.765673815267184e-05, "loss": 2.5951, "step": 3300 }, { "epoch": 1.66, "learning_rate": 3.76227210218149e-05, "loss": 2.598, "step": 3305 }, { "epoch": 1.66, "learning_rate": 3.758867249498321e-05, "loss": 2.8652, "step": 3310 }, { "epoch": 1.66, "learning_rate": 3.7554592656864285e-05, "loss": 2.5312, "step": 3315 }, { "epoch": 1.67, "learning_rate": 3.752048159222349e-05, "loss": 2.7432, "step": 3320 }, { "epoch": 1.67, "learning_rate": 3.748633938590388e-05, "loss": 2.64, "step": 3325 }, { "epoch": 1.67, "learning_rate": 3.745216612282596e-05, "loss": 2.751, "step": 3330 }, { "epoch": 1.67, "learning_rate": 3.741796188798747e-05, "loss": 2.7636, "step": 3335 }, { "epoch": 1.68, "learning_rate": 3.738372676646321e-05, "loss": 2.8103, "step": 3340 }, { "epoch": 1.68, "learning_rate": 3.7349460843404796e-05, "loss": 2.6672, "step": 3345 }, { "epoch": 1.68, "learning_rate": 3.731516420404043e-05, "loss": 2.5272, "step": 3350 }, { "epoch": 1.68, "learning_rate": 3.728083693367474e-05, "loss": 2.6674, "step": 3355 }, { "epoch": 1.69, "learning_rate": 3.724647911768854e-05, "loss": 2.708, "step": 3360 }, { "epoch": 1.69, "learning_rate": 3.72120908415386e-05, "loss": 2.3902, "step": 3365 }, { "epoch": 1.69, "learning_rate": 3.7177672190757476e-05, "loss": 2.8144, "step": 3370 }, { "epoch": 1.69, "learning_rate": 3.714322325095325e-05, "loss": 2.8525, "step": 3375 }, { "epoch": 1.7, "learning_rate": 3.7108744107809364e-05, "loss": 2.4671, "step": 3380 }, { "epoch": 1.7, "learning_rate": 3.7074234847084363e-05, "loss": 2.3723, "step": 3385 }, { "epoch": 1.7, "learning_rate": 3.703969555461173e-05, "loss": 2.8825, "step": 3390 }, { "epoch": 1.7, "learning_rate": 3.700512631629961e-05, "loss": 2.768, "step": 3395 }, { "epoch": 1.71, "learning_rate": 3.6970527218130644e-05, "loss": 2.4601, "step": 3400 }, { "epoch": 1.71, "learning_rate": 3.693589834616176e-05, "loss": 2.7482, "step": 3405 }, { "epoch": 1.71, "learning_rate": 3.6901239786523914e-05, "loss": 2.4536, "step": 3410 }, { "epoch": 1.71, "learning_rate": 3.686655162542192e-05, "loss": 2.571, "step": 3415 }, { "epoch": 1.72, "learning_rate": 3.683183394913422e-05, "loss": 2.5796, "step": 3420 }, { "epoch": 1.72, "learning_rate": 3.6797086844012654e-05, "loss": 2.7312, "step": 3425 }, { "epoch": 1.72, "learning_rate": 3.676231039648227e-05, "loss": 2.5584, "step": 3430 }, { "epoch": 1.72, "learning_rate": 3.67275046930411e-05, "loss": 2.6298, "step": 3435 }, { "epoch": 1.73, "learning_rate": 3.669266982025993e-05, "loss": 2.628, "step": 3440 }, { "epoch": 1.73, "learning_rate": 3.6657805864782116e-05, "loss": 2.5943, "step": 3445 }, { "epoch": 1.73, "learning_rate": 3.662291291332333e-05, "loss": 2.6121, "step": 3450 }, { "epoch": 1.73, "learning_rate": 3.658799105267138e-05, "loss": 2.6501, "step": 3455 }, { "epoch": 1.74, "learning_rate": 3.655304036968597e-05, "loss": 2.5708, "step": 3460 }, { "epoch": 1.74, "learning_rate": 3.651806095129849e-05, "loss": 2.8039, "step": 3465 }, { "epoch": 1.74, "learning_rate": 3.648305288451183e-05, "loss": 2.8159, "step": 3470 }, { "epoch": 1.74, "learning_rate": 3.64480162564001e-05, "loss": 2.6506, "step": 3475 }, { "epoch": 1.75, "learning_rate": 3.641295115410847e-05, "loss": 2.8982, "step": 3480 }, { "epoch": 1.75, "learning_rate": 3.637785766485291e-05, "loss": 2.8018, "step": 3485 }, { "epoch": 1.75, "learning_rate": 3.634273587592003e-05, "loss": 2.5278, "step": 3490 }, { "epoch": 1.75, "learning_rate": 3.630758587466681e-05, "loss": 2.8937, "step": 3495 }, { "epoch": 1.76, "learning_rate": 3.6272407748520394e-05, "loss": 2.1922, "step": 3500 }, { "epoch": 1.76, "learning_rate": 3.623720158497789e-05, "loss": 2.4288, "step": 3505 }, { "epoch": 1.76, "learning_rate": 3.620196747160613e-05, "loss": 2.9423, "step": 3510 }, { "epoch": 1.76, "learning_rate": 3.61667054960415e-05, "loss": 2.5559, "step": 3515 }, { "epoch": 1.77, "learning_rate": 3.613141574598965e-05, "loss": 2.7228, "step": 3520 }, { "epoch": 1.77, "learning_rate": 3.6096098309225325e-05, "loss": 2.6933, "step": 3525 }, { "epoch": 1.77, "learning_rate": 3.606075327359212e-05, "loss": 2.5865, "step": 3530 }, { "epoch": 1.77, "learning_rate": 3.602538072700229e-05, "loss": 2.5846, "step": 3535 }, { "epoch": 1.78, "learning_rate": 3.598998075743653e-05, "loss": 2.8847, "step": 3540 }, { "epoch": 1.78, "learning_rate": 3.595455345294372e-05, "loss": 2.5386, "step": 3545 }, { "epoch": 1.78, "learning_rate": 3.5919098901640735e-05, "loss": 2.5932, "step": 3550 }, { "epoch": 1.78, "learning_rate": 3.588361719171223e-05, "loss": 2.4481, "step": 3555 }, { "epoch": 1.79, "learning_rate": 3.584810841141039e-05, "loss": 2.5773, "step": 3560 }, { "epoch": 1.79, "learning_rate": 3.581257264905476e-05, "loss": 2.6305, "step": 3565 }, { "epoch": 1.79, "learning_rate": 3.5777009993031955e-05, "loss": 2.7, "step": 3570 }, { "epoch": 1.79, "learning_rate": 3.574142053179553e-05, "loss": 2.4408, "step": 3575 }, { "epoch": 1.8, "learning_rate": 3.5705804353865677e-05, "loss": 2.7292, "step": 3580 }, { "epoch": 1.8, "learning_rate": 3.567016154782906e-05, "loss": 2.4371, "step": 3585 }, { "epoch": 1.8, "learning_rate": 3.563449220233855e-05, "loss": 2.7977, "step": 3590 }, { "epoch": 1.8, "learning_rate": 3.559879640611305e-05, "loss": 2.7357, "step": 3595 }, { "epoch": 1.81, "learning_rate": 3.5563074247937244e-05, "loss": 2.6255, "step": 3600 }, { "epoch": 1.81, "learning_rate": 3.552732581666139e-05, "loss": 2.8134, "step": 3605 }, { "epoch": 1.81, "learning_rate": 3.549155120120109e-05, "loss": 2.702, "step": 3610 }, { "epoch": 1.81, "learning_rate": 3.545575049053707e-05, "loss": 2.4854, "step": 3615 }, { "epoch": 1.82, "learning_rate": 3.541992377371497e-05, "loss": 2.7596, "step": 3620 }, { "epoch": 1.82, "learning_rate": 3.53840711398451e-05, "loss": 2.6891, "step": 3625 }, { "epoch": 1.82, "learning_rate": 3.5348192678102254e-05, "loss": 2.5619, "step": 3630 }, { "epoch": 1.82, "learning_rate": 3.531228847772544e-05, "loss": 2.5719, "step": 3635 }, { "epoch": 1.83, "learning_rate": 3.52763586280177e-05, "loss": 2.6297, "step": 3640 }, { "epoch": 1.83, "learning_rate": 3.524040321834589e-05, "loss": 2.5114, "step": 3645 }, { "epoch": 1.83, "learning_rate": 3.52044223381404e-05, "loss": 2.8536, "step": 3650 }, { "epoch": 1.83, "learning_rate": 3.516841607689501e-05, "loss": 2.5271, "step": 3655 }, { "epoch": 1.84, "learning_rate": 3.51323845241666e-05, "loss": 2.5654, "step": 3660 }, { "epoch": 1.84, "learning_rate": 3.509632776957497e-05, "loss": 2.6269, "step": 3665 }, { "epoch": 1.84, "learning_rate": 3.50602459028026e-05, "loss": 2.4401, "step": 3670 }, { "epoch": 1.84, "learning_rate": 3.502413901359445e-05, "loss": 2.4368, "step": 3675 }, { "epoch": 1.85, "learning_rate": 3.498800719175768e-05, "loss": 2.6087, "step": 3680 }, { "epoch": 1.85, "learning_rate": 3.4951850527161495e-05, "loss": 2.5927, "step": 3685 }, { "epoch": 1.85, "learning_rate": 3.4915669109736876e-05, "loss": 2.8352, "step": 3690 }, { "epoch": 1.85, "learning_rate": 3.487946302947637e-05, "loss": 2.8485, "step": 3695 }, { "epoch": 1.86, "learning_rate": 3.484323237643389e-05, "loss": 2.6611, "step": 3700 }, { "epoch": 1.86, "learning_rate": 3.4806977240724423e-05, "loss": 2.5251, "step": 3705 }, { "epoch": 1.86, "learning_rate": 3.47706977125239e-05, "loss": 2.6043, "step": 3710 }, { "epoch": 1.86, "learning_rate": 3.473439388206887e-05, "loss": 2.5911, "step": 3715 }, { "epoch": 1.87, "learning_rate": 3.469806583965639e-05, "loss": 2.7092, "step": 3720 }, { "epoch": 1.87, "learning_rate": 3.466171367564368e-05, "loss": 2.4572, "step": 3725 }, { "epoch": 1.87, "learning_rate": 3.462533748044801e-05, "loss": 2.464, "step": 3730 }, { "epoch": 1.87, "learning_rate": 3.458893734454636e-05, "loss": 2.8654, "step": 3735 }, { "epoch": 1.88, "learning_rate": 3.455251335847531e-05, "loss": 2.752, "step": 3740 }, { "epoch": 1.88, "learning_rate": 3.451606561283074e-05, "loss": 2.59, "step": 3745 }, { "epoch": 1.88, "learning_rate": 3.447959419826763e-05, "loss": 2.4732, "step": 3750 }, { "epoch": 1.88, "learning_rate": 3.444309920549983e-05, "loss": 2.7611, "step": 3755 }, { "epoch": 1.89, "learning_rate": 3.440658072529983e-05, "loss": 2.5923, "step": 3760 }, { "epoch": 1.89, "learning_rate": 3.437003884849854e-05, "loss": 2.5405, "step": 3765 }, { "epoch": 1.89, "learning_rate": 3.433347366598506e-05, "loss": 2.6368, "step": 3770 }, { "epoch": 1.89, "learning_rate": 3.429688526870649e-05, "loss": 2.5877, "step": 3775 }, { "epoch": 1.9, "learning_rate": 3.4260273747667635e-05, "loss": 2.5978, "step": 3780 }, { "epoch": 1.9, "learning_rate": 3.422363919393082e-05, "loss": 2.7375, "step": 3785 }, { "epoch": 1.9, "learning_rate": 3.418698169861567e-05, "loss": 2.4161, "step": 3790 }, { "epoch": 1.9, "learning_rate": 3.415030135289884e-05, "loss": 2.3959, "step": 3795 }, { "epoch": 1.91, "learning_rate": 3.4113598248013875e-05, "loss": 2.9642, "step": 3800 }, { "epoch": 1.91, "learning_rate": 3.40768724752509e-05, "loss": 2.7313, "step": 3805 }, { "epoch": 1.91, "learning_rate": 3.404012412595639e-05, "loss": 2.6311, "step": 3810 }, { "epoch": 1.91, "learning_rate": 3.400335329153304e-05, "loss": 2.6268, "step": 3815 }, { "epoch": 1.92, "learning_rate": 3.396656006343939e-05, "loss": 2.5252, "step": 3820 }, { "epoch": 1.92, "learning_rate": 3.392974453318975e-05, "loss": 2.5863, "step": 3825 }, { "epoch": 1.92, "learning_rate": 3.3892906792353886e-05, "loss": 2.4848, "step": 3830 }, { "epoch": 1.92, "learning_rate": 3.3856046932556775e-05, "loss": 2.5517, "step": 3835 }, { "epoch": 1.93, "learning_rate": 3.3819165045478426e-05, "loss": 2.6679, "step": 3840 }, { "epoch": 1.93, "learning_rate": 3.3782261222853654e-05, "loss": 2.4474, "step": 3845 }, { "epoch": 1.93, "learning_rate": 3.37453355564718e-05, "loss": 2.5378, "step": 3850 }, { "epoch": 1.93, "learning_rate": 3.3708388138176584e-05, "loss": 2.8168, "step": 3855 }, { "epoch": 1.94, "learning_rate": 3.367141905986578e-05, "loss": 2.6556, "step": 3860 }, { "epoch": 1.94, "learning_rate": 3.3634428413491054e-05, "loss": 2.5122, "step": 3865 }, { "epoch": 1.94, "learning_rate": 3.359741629105773e-05, "loss": 2.7044, "step": 3870 }, { "epoch": 1.94, "learning_rate": 3.3560382784624524e-05, "loss": 2.6193, "step": 3875 }, { "epoch": 1.95, "learning_rate": 3.352332798630336e-05, "loss": 3.0051, "step": 3880 }, { "epoch": 1.95, "learning_rate": 3.3486251988259134e-05, "loss": 2.5351, "step": 3885 }, { "epoch": 1.95, "learning_rate": 3.344915488270942e-05, "loss": 2.7273, "step": 3890 }, { "epoch": 1.95, "learning_rate": 3.341203676192433e-05, "loss": 2.3833, "step": 3895 }, { "epoch": 1.96, "learning_rate": 3.3374897718226236e-05, "loss": 2.5073, "step": 3900 }, { "epoch": 1.96, "learning_rate": 3.333773784398957e-05, "loss": 2.7216, "step": 3905 }, { "epoch": 1.96, "learning_rate": 3.330055723164055e-05, "loss": 2.6666, "step": 3910 }, { "epoch": 1.96, "learning_rate": 3.326335597365698e-05, "loss": 2.4959, "step": 3915 }, { "epoch": 1.97, "learning_rate": 3.322613416256802e-05, "loss": 2.8799, "step": 3920 }, { "epoch": 1.97, "learning_rate": 3.3188891890953956e-05, "loss": 2.6041, "step": 3925 }, { "epoch": 1.97, "learning_rate": 3.315162925144595e-05, "loss": 2.7423, "step": 3930 }, { "epoch": 1.97, "learning_rate": 3.3114346336725834e-05, "loss": 2.5765, "step": 3935 }, { "epoch": 1.98, "learning_rate": 3.3077043239525874e-05, "loss": 2.152, "step": 3940 }, { "epoch": 1.98, "learning_rate": 3.303972005262852e-05, "loss": 2.6474, "step": 3945 }, { "epoch": 1.98, "learning_rate": 3.3002376868866206e-05, "loss": 2.473, "step": 3950 }, { "epoch": 1.98, "learning_rate": 3.296501378112109e-05, "loss": 2.6779, "step": 3955 }, { "epoch": 1.99, "learning_rate": 3.292763088232485e-05, "loss": 2.7439, "step": 3960 }, { "epoch": 1.99, "learning_rate": 3.289022826545844e-05, "loss": 2.8874, "step": 3965 }, { "epoch": 1.99, "learning_rate": 3.2852806023551834e-05, "loss": 2.7191, "step": 3970 }, { "epoch": 1.99, "learning_rate": 3.281536424968383e-05, "loss": 2.563, "step": 3975 }, { "epoch": 2.0, "learning_rate": 3.2777903036981836e-05, "loss": 2.7884, "step": 3980 }, { "epoch": 2.0, "learning_rate": 3.274042247862158e-05, "loss": 2.5221, "step": 3985 }, { "epoch": 2.0, "learning_rate": 3.270292266782689e-05, "loss": 2.462, "step": 3990 }, { "epoch": 2.0, "learning_rate": 3.266540369786953e-05, "loss": 2.5059, "step": 3995 }, { "epoch": 2.01, "learning_rate": 3.262786566206888e-05, "loss": 2.688, "step": 4000 }, { "epoch": 2.01, "learning_rate": 3.259030865379174e-05, "loss": 2.7194, "step": 4005 }, { "epoch": 2.01, "learning_rate": 3.255273276645214e-05, "loss": 2.4145, "step": 4010 }, { "epoch": 2.01, "learning_rate": 3.251513809351101e-05, "loss": 2.5469, "step": 4015 }, { "epoch": 2.02, "learning_rate": 3.247752472847605e-05, "loss": 2.7916, "step": 4020 }, { "epoch": 2.02, "learning_rate": 3.243989276490143e-05, "loss": 2.5973, "step": 4025 }, { "epoch": 2.02, "learning_rate": 3.240224229638758e-05, "loss": 2.6732, "step": 4030 }, { "epoch": 2.02, "learning_rate": 3.236457341658097e-05, "loss": 2.2159, "step": 4035 }, { "epoch": 2.03, "learning_rate": 3.232688621917386e-05, "loss": 2.6783, "step": 4040 }, { "epoch": 2.03, "learning_rate": 3.2289180797904055e-05, "loss": 2.8193, "step": 4045 }, { "epoch": 2.03, "learning_rate": 3.22514572465547e-05, "loss": 2.3885, "step": 4050 }, { "epoch": 2.03, "learning_rate": 3.221371565895404e-05, "loss": 2.6288, "step": 4055 }, { "epoch": 2.04, "learning_rate": 3.217595612897516e-05, "loss": 2.5372, "step": 4060 }, { "epoch": 2.04, "learning_rate": 3.21381787505358e-05, "loss": 2.7257, "step": 4065 }, { "epoch": 2.04, "learning_rate": 3.210038361759807e-05, "loss": 2.6329, "step": 4070 }, { "epoch": 2.04, "learning_rate": 3.206257082416825e-05, "loss": 2.6518, "step": 4075 }, { "epoch": 2.05, "learning_rate": 3.2024740464296544e-05, "loss": 2.4218, "step": 4080 }, { "epoch": 2.05, "learning_rate": 3.198689263207686e-05, "loss": 2.7266, "step": 4085 }, { "epoch": 2.05, "learning_rate": 3.1949027421646546e-05, "loss": 2.4466, "step": 4090 }, { "epoch": 2.05, "learning_rate": 3.1911144927186185e-05, "loss": 2.6014, "step": 4095 }, { "epoch": 2.06, "learning_rate": 3.1873245242919354e-05, "loss": 2.7072, "step": 4100 }, { "epoch": 2.06, "learning_rate": 3.183532846311236e-05, "loss": 2.5211, "step": 4105 }, { "epoch": 2.06, "learning_rate": 3.179739468207406e-05, "loss": 2.5787, "step": 4110 }, { "epoch": 2.06, "learning_rate": 3.175944399415559e-05, "loss": 2.5141, "step": 4115 }, { "epoch": 2.07, "learning_rate": 3.1721476493750134e-05, "loss": 2.6807, "step": 4120 }, { "epoch": 2.07, "learning_rate": 3.1683492275292695e-05, "loss": 2.5611, "step": 4125 }, { "epoch": 2.07, "learning_rate": 3.164549143325985e-05, "loss": 2.5864, "step": 4130 }, { "epoch": 2.08, "learning_rate": 3.160747406216953e-05, "loss": 2.7378, "step": 4135 }, { "epoch": 2.08, "learning_rate": 3.156944025658079e-05, "loss": 2.7334, "step": 4140 }, { "epoch": 2.08, "learning_rate": 3.153139011109354e-05, "loss": 2.4465, "step": 4145 }, { "epoch": 2.08, "learning_rate": 3.149332372034834e-05, "loss": 2.5482, "step": 4150 }, { "epoch": 2.09, "learning_rate": 3.145524117902617e-05, "loss": 2.7633, "step": 4155 }, { "epoch": 2.09, "learning_rate": 3.141714258184816e-05, "loss": 2.6796, "step": 4160 }, { "epoch": 2.09, "learning_rate": 3.137902802357538e-05, "loss": 2.6622, "step": 4165 }, { "epoch": 2.09, "learning_rate": 3.134089759900861e-05, "loss": 2.9277, "step": 4170 }, { "epoch": 2.1, "learning_rate": 3.130275140298808e-05, "loss": 2.351, "step": 4175 }, { "epoch": 2.1, "learning_rate": 3.1264589530393263e-05, "loss": 2.654, "step": 4180 }, { "epoch": 2.1, "learning_rate": 3.12264120761426e-05, "loss": 2.6229, "step": 4185 }, { "epoch": 2.1, "learning_rate": 3.118821913519333e-05, "loss": 2.6415, "step": 4190 }, { "epoch": 2.11, "learning_rate": 3.115001080254115e-05, "loss": 2.6029, "step": 4195 }, { "epoch": 2.11, "learning_rate": 3.1111787173220095e-05, "loss": 2.6775, "step": 4200 }, { "epoch": 2.11, "learning_rate": 3.107354834230223e-05, "loss": 2.7393, "step": 4205 }, { "epoch": 2.11, "learning_rate": 3.1035294404897396e-05, "loss": 2.5886, "step": 4210 }, { "epoch": 2.12, "learning_rate": 3.099702545615307e-05, "loss": 2.3812, "step": 4215 }, { "epoch": 2.12, "learning_rate": 3.0958741591254026e-05, "loss": 3.1271, "step": 4220 }, { "epoch": 2.12, "learning_rate": 3.0920442905422145e-05, "loss": 2.7758, "step": 4225 }, { "epoch": 2.12, "learning_rate": 3.0882129493916167e-05, "loss": 2.7682, "step": 4230 }, { "epoch": 2.13, "learning_rate": 3.0843801452031466e-05, "loss": 2.2826, "step": 4235 }, { "epoch": 2.13, "learning_rate": 3.0805458875099804e-05, "loss": 2.5934, "step": 4240 }, { "epoch": 2.13, "learning_rate": 3.0767101858489103e-05, "loss": 2.7693, "step": 4245 }, { "epoch": 2.13, "learning_rate": 3.072873049760319e-05, "loss": 2.6955, "step": 4250 }, { "epoch": 2.14, "learning_rate": 3.0690344887881565e-05, "loss": 2.7344, "step": 4255 }, { "epoch": 2.14, "learning_rate": 3.0651945124799185e-05, "loss": 2.6215, "step": 4260 }, { "epoch": 2.14, "learning_rate": 3.061353130386619e-05, "loss": 2.5794, "step": 4265 }, { "epoch": 2.14, "learning_rate": 3.05751035206277e-05, "loss": 2.671, "step": 4270 }, { "epoch": 2.15, "learning_rate": 3.0536661870663576e-05, "loss": 2.7265, "step": 4275 }, { "epoch": 2.15, "learning_rate": 3.0498206449588136e-05, "loss": 2.9018, "step": 4280 }, { "epoch": 2.15, "learning_rate": 3.045973735304996e-05, "loss": 2.4823, "step": 4285 }, { "epoch": 2.15, "learning_rate": 3.0421254676731664e-05, "loss": 2.5454, "step": 4290 }, { "epoch": 2.16, "learning_rate": 3.0382758516349623e-05, "loss": 2.7888, "step": 4295 }, { "epoch": 2.16, "learning_rate": 3.0344248967653754e-05, "loss": 2.596, "step": 4300 }, { "epoch": 2.16, "learning_rate": 3.030572612642727e-05, "loss": 2.7905, "step": 4305 }, { "epoch": 2.16, "learning_rate": 3.0267190088486452e-05, "loss": 2.5676, "step": 4310 }, { "epoch": 2.17, "learning_rate": 3.0228640949680388e-05, "loss": 2.5836, "step": 4315 }, { "epoch": 2.17, "learning_rate": 3.0190078805890786e-05, "loss": 2.7138, "step": 4320 }, { "epoch": 2.17, "learning_rate": 3.015150375303168e-05, "loss": 2.4747, "step": 4325 }, { "epoch": 2.17, "learning_rate": 3.011291588704919e-05, "loss": 2.5188, "step": 4330 }, { "epoch": 2.18, "learning_rate": 3.0074315303921353e-05, "loss": 2.2952, "step": 4335 }, { "epoch": 2.18, "learning_rate": 3.0035702099657787e-05, "loss": 2.4875, "step": 4340 }, { "epoch": 2.18, "learning_rate": 2.9997076370299544e-05, "loss": 2.5085, "step": 4345 }, { "epoch": 2.18, "learning_rate": 2.9958438211918805e-05, "loss": 2.7452, "step": 4350 }, { "epoch": 2.19, "learning_rate": 2.9919787720618676e-05, "loss": 2.334, "step": 4355 }, { "epoch": 2.19, "learning_rate": 2.9881124992532933e-05, "loss": 2.6904, "step": 4360 }, { "epoch": 2.19, "learning_rate": 2.984245012382579e-05, "loss": 2.5706, "step": 4365 }, { "epoch": 2.19, "learning_rate": 2.980376321069165e-05, "loss": 2.6657, "step": 4370 }, { "epoch": 2.2, "learning_rate": 2.976506434935489e-05, "loss": 2.4117, "step": 4375 }, { "epoch": 2.2, "learning_rate": 2.9726353636069582e-05, "loss": 2.4446, "step": 4380 }, { "epoch": 2.2, "learning_rate": 2.968763116711931e-05, "loss": 2.5681, "step": 4385 }, { "epoch": 2.2, "learning_rate": 2.964889703881686e-05, "loss": 2.7244, "step": 4390 }, { "epoch": 2.21, "learning_rate": 2.9610151347504044e-05, "loss": 2.577, "step": 4395 }, { "epoch": 2.21, "learning_rate": 2.957139418955143e-05, "loss": 2.6176, "step": 4400 }, { "epoch": 2.21, "learning_rate": 2.9532625661358105e-05, "loss": 2.5708, "step": 4405 }, { "epoch": 2.21, "learning_rate": 2.949384585935143e-05, "loss": 2.4873, "step": 4410 }, { "epoch": 2.22, "learning_rate": 2.9455054879986797e-05, "loss": 2.5953, "step": 4415 }, { "epoch": 2.22, "learning_rate": 2.941625281974743e-05, "loss": 2.5578, "step": 4420 }, { "epoch": 2.22, "learning_rate": 2.93774397751441e-05, "loss": 2.5782, "step": 4425 }, { "epoch": 2.22, "learning_rate": 2.9338615842714883e-05, "loss": 2.8227, "step": 4430 }, { "epoch": 2.23, "learning_rate": 2.9299781119024956e-05, "loss": 2.4317, "step": 4435 }, { "epoch": 2.23, "learning_rate": 2.926093570066633e-05, "loss": 2.7054, "step": 4440 }, { "epoch": 2.23, "learning_rate": 2.9222079684257608e-05, "loss": 2.7207, "step": 4445 }, { "epoch": 2.23, "learning_rate": 2.9183213166443778e-05, "loss": 2.6732, "step": 4450 }, { "epoch": 2.24, "learning_rate": 2.9144336243895927e-05, "loss": 2.4768, "step": 4455 }, { "epoch": 2.24, "learning_rate": 2.910544901331101e-05, "loss": 2.5146, "step": 4460 }, { "epoch": 2.24, "learning_rate": 2.9066551571411645e-05, "loss": 2.4941, "step": 4465 }, { "epoch": 2.24, "learning_rate": 2.902764401494584e-05, "loss": 2.1425, "step": 4470 }, { "epoch": 2.25, "learning_rate": 2.898872644068676e-05, "loss": 2.6335, "step": 4475 }, { "epoch": 2.25, "learning_rate": 2.8949798945432483e-05, "loss": 2.4093, "step": 4480 }, { "epoch": 2.25, "learning_rate": 2.8910861626005776e-05, "loss": 2.4006, "step": 4485 }, { "epoch": 2.25, "learning_rate": 2.8871914579253824e-05, "loss": 2.4762, "step": 4490 }, { "epoch": 2.26, "learning_rate": 2.8832957902048014e-05, "loss": 2.6309, "step": 4495 }, { "epoch": 2.26, "learning_rate": 2.8793991691283684e-05, "loss": 2.7734, "step": 4500 }, { "epoch": 2.26, "learning_rate": 2.87550160438799e-05, "loss": 2.5444, "step": 4505 }, { "epoch": 2.26, "learning_rate": 2.871603105677917e-05, "loss": 2.5277, "step": 4510 }, { "epoch": 2.27, "learning_rate": 2.8677036826947264e-05, "loss": 2.5775, "step": 4515 }, { "epoch": 2.27, "learning_rate": 2.863803345137291e-05, "loss": 2.4524, "step": 4520 }, { "epoch": 2.27, "learning_rate": 2.8599021027067608e-05, "loss": 2.572, "step": 4525 }, { "epoch": 2.27, "learning_rate": 2.855999965106536e-05, "loss": 2.8112, "step": 4530 }, { "epoch": 2.28, "learning_rate": 2.8520969420422427e-05, "loss": 2.65, "step": 4535 }, { "epoch": 2.28, "learning_rate": 2.8481930432217096e-05, "loss": 2.4675, "step": 4540 }, { "epoch": 2.28, "learning_rate": 2.844288278354943e-05, "loss": 2.668, "step": 4545 }, { "epoch": 2.28, "learning_rate": 2.8403826571541046e-05, "loss": 2.7135, "step": 4550 }, { "epoch": 2.29, "learning_rate": 2.8364761893334858e-05, "loss": 2.5212, "step": 4555 }, { "epoch": 2.29, "learning_rate": 2.8325688846094817e-05, "loss": 2.698, "step": 4560 }, { "epoch": 2.29, "learning_rate": 2.828660752700572e-05, "loss": 2.6517, "step": 4565 }, { "epoch": 2.29, "learning_rate": 2.8247518033272924e-05, "loss": 2.6687, "step": 4570 }, { "epoch": 2.3, "learning_rate": 2.8208420462122105e-05, "loss": 2.4934, "step": 4575 }, { "epoch": 2.3, "learning_rate": 2.816931491079906e-05, "loss": 2.3762, "step": 4580 }, { "epoch": 2.3, "learning_rate": 2.8130201476569413e-05, "loss": 2.6873, "step": 4585 }, { "epoch": 2.3, "learning_rate": 2.8091080256718398e-05, "loss": 2.6981, "step": 4590 }, { "epoch": 2.31, "learning_rate": 2.805195134855061e-05, "loss": 2.6814, "step": 4595 }, { "epoch": 2.31, "learning_rate": 2.8012814849389785e-05, "loss": 2.6641, "step": 4600 }, { "epoch": 2.31, "learning_rate": 2.797367085657852e-05, "loss": 2.488, "step": 4605 }, { "epoch": 2.31, "learning_rate": 2.793451946747806e-05, "loss": 2.4358, "step": 4610 }, { "epoch": 2.32, "learning_rate": 2.7895360779468044e-05, "loss": 2.7458, "step": 4615 }, { "epoch": 2.32, "learning_rate": 2.785619488994627e-05, "loss": 2.7558, "step": 4620 }, { "epoch": 2.32, "learning_rate": 2.7817021896328427e-05, "loss": 2.6906, "step": 4625 }, { "epoch": 2.32, "learning_rate": 2.7777841896047914e-05, "loss": 2.5384, "step": 4630 }, { "epoch": 2.33, "learning_rate": 2.7738654986555523e-05, "loss": 2.8354, "step": 4635 }, { "epoch": 2.33, "learning_rate": 2.7699461265319242e-05, "loss": 2.6352, "step": 4640 }, { "epoch": 2.33, "learning_rate": 2.7660260829824003e-05, "loss": 2.5602, "step": 4645 }, { "epoch": 2.33, "learning_rate": 2.7621053777571425e-05, "loss": 2.7109, "step": 4650 }, { "epoch": 2.34, "learning_rate": 2.7581840206079616e-05, "loss": 2.7317, "step": 4655 }, { "epoch": 2.34, "learning_rate": 2.754262021288287e-05, "loss": 2.6874, "step": 4660 }, { "epoch": 2.34, "learning_rate": 2.750339389553146e-05, "loss": 2.5854, "step": 4665 }, { "epoch": 2.34, "learning_rate": 2.7464161351591393e-05, "loss": 2.4774, "step": 4670 }, { "epoch": 2.35, "learning_rate": 2.7424922678644172e-05, "loss": 2.3301, "step": 4675 }, { "epoch": 2.35, "learning_rate": 2.7385677974286517e-05, "loss": 2.8886, "step": 4680 }, { "epoch": 2.35, "learning_rate": 2.7346427336130175e-05, "loss": 2.4401, "step": 4685 }, { "epoch": 2.35, "learning_rate": 2.7307170861801644e-05, "loss": 2.4788, "step": 4690 }, { "epoch": 2.36, "learning_rate": 2.7267908648941938e-05, "loss": 2.4079, "step": 4695 }, { "epoch": 2.36, "learning_rate": 2.7228640795206344e-05, "loss": 2.3763, "step": 4700 }, { "epoch": 2.36, "learning_rate": 2.718936739826417e-05, "loss": 2.4751, "step": 4705 }, { "epoch": 2.36, "learning_rate": 2.7150088555798537e-05, "loss": 2.5827, "step": 4710 }, { "epoch": 2.37, "learning_rate": 2.7110804365506083e-05, "loss": 2.8181, "step": 4715 }, { "epoch": 2.37, "learning_rate": 2.7071514925096762e-05, "loss": 2.5951, "step": 4720 }, { "epoch": 2.37, "learning_rate": 2.703222033229359e-05, "loss": 2.8812, "step": 4725 }, { "epoch": 2.37, "learning_rate": 2.6992920684832374e-05, "loss": 2.8793, "step": 4730 }, { "epoch": 2.38, "learning_rate": 2.6953616080461526e-05, "loss": 2.7234, "step": 4735 }, { "epoch": 2.38, "learning_rate": 2.6914306616941764e-05, "loss": 2.566, "step": 4740 }, { "epoch": 2.38, "learning_rate": 2.68749923920459e-05, "loss": 2.7924, "step": 4745 }, { "epoch": 2.38, "learning_rate": 2.683567350355859e-05, "loss": 2.5467, "step": 4750 }, { "epoch": 2.39, "learning_rate": 2.679635004927608e-05, "loss": 2.8032, "step": 4755 }, { "epoch": 2.39, "learning_rate": 2.6757022127006e-05, "loss": 2.4976, "step": 4760 }, { "epoch": 2.39, "learning_rate": 2.6717689834567055e-05, "loss": 2.7968, "step": 4765 }, { "epoch": 2.39, "learning_rate": 2.6678353269788854e-05, "loss": 2.4099, "step": 4770 }, { "epoch": 2.4, "learning_rate": 2.66390125305116e-05, "loss": 2.4246, "step": 4775 }, { "epoch": 2.4, "learning_rate": 2.659966771458589e-05, "loss": 2.7296, "step": 4780 }, { "epoch": 2.4, "learning_rate": 2.656031891987249e-05, "loss": 2.5013, "step": 4785 }, { "epoch": 2.4, "learning_rate": 2.6520966244242024e-05, "loss": 2.4029, "step": 4790 }, { "epoch": 2.41, "learning_rate": 2.648160978557479e-05, "loss": 2.405, "step": 4795 }, { "epoch": 2.41, "learning_rate": 2.644224964176048e-05, "loss": 2.5121, "step": 4800 }, { "epoch": 2.41, "learning_rate": 2.6402885910697966e-05, "loss": 2.7865, "step": 4805 }, { "epoch": 2.41, "learning_rate": 2.6363518690295035e-05, "loss": 2.3725, "step": 4810 }, { "epoch": 2.42, "learning_rate": 2.632414807846816e-05, "loss": 2.612, "step": 4815 }, { "epoch": 2.42, "learning_rate": 2.6284774173142233e-05, "loss": 2.5412, "step": 4820 }, { "epoch": 2.42, "learning_rate": 2.624539707225036e-05, "loss": 2.4828, "step": 4825 }, { "epoch": 2.42, "learning_rate": 2.6206016873733574e-05, "loss": 2.6912, "step": 4830 }, { "epoch": 2.43, "learning_rate": 2.6166633675540635e-05, "loss": 2.9305, "step": 4835 }, { "epoch": 2.43, "learning_rate": 2.612724757562775e-05, "loss": 2.4224, "step": 4840 }, { "epoch": 2.43, "learning_rate": 2.608785867195834e-05, "loss": 2.448, "step": 4845 }, { "epoch": 2.43, "learning_rate": 2.60484670625028e-05, "loss": 2.356, "step": 4850 }, { "epoch": 2.44, "learning_rate": 2.600907284523827e-05, "loss": 2.3987, "step": 4855 }, { "epoch": 2.44, "learning_rate": 2.5969676118148358e-05, "loss": 1.9985, "step": 4860 }, { "epoch": 2.44, "learning_rate": 2.5930276979222927e-05, "loss": 2.7017, "step": 4865 }, { "epoch": 2.44, "learning_rate": 2.5890875526457836e-05, "loss": 2.5223, "step": 4870 }, { "epoch": 2.45, "learning_rate": 2.5851471857854697e-05, "loss": 2.5558, "step": 4875 }, { "epoch": 2.45, "learning_rate": 2.5812066071420632e-05, "loss": 2.3048, "step": 4880 }, { "epoch": 2.45, "learning_rate": 2.5772658265168025e-05, "loss": 2.6089, "step": 4885 }, { "epoch": 2.45, "learning_rate": 2.5733248537114306e-05, "loss": 2.6711, "step": 4890 }, { "epoch": 2.46, "learning_rate": 2.569383698528166e-05, "loss": 2.6202, "step": 4895 }, { "epoch": 2.46, "learning_rate": 2.5654423707696833e-05, "loss": 2.6619, "step": 4900 }, { "epoch": 2.46, "learning_rate": 2.5615008802390834e-05, "loss": 2.6442, "step": 4905 }, { "epoch": 2.46, "learning_rate": 2.5575592367398733e-05, "loss": 2.7031, "step": 4910 }, { "epoch": 2.47, "learning_rate": 2.5536174500759417e-05, "loss": 2.5043, "step": 4915 }, { "epoch": 2.47, "learning_rate": 2.5496755300515323e-05, "loss": 2.3442, "step": 4920 }, { "epoch": 2.47, "learning_rate": 2.5457334864712206e-05, "loss": 2.7005, "step": 4925 }, { "epoch": 2.47, "learning_rate": 2.5417913291398892e-05, "loss": 2.8544, "step": 4930 }, { "epoch": 2.48, "learning_rate": 2.5378490678627043e-05, "loss": 2.3004, "step": 4935 }, { "epoch": 2.48, "learning_rate": 2.5339067124450887e-05, "loss": 2.527, "step": 4940 }, { "epoch": 2.48, "learning_rate": 2.5299642726927035e-05, "loss": 2.689, "step": 4945 }, { "epoch": 2.48, "learning_rate": 2.526021758411415e-05, "loss": 2.7824, "step": 4950 }, { "epoch": 2.49, "learning_rate": 2.5220791794072774e-05, "loss": 2.5121, "step": 4955 }, { "epoch": 2.49, "learning_rate": 2.518136545486504e-05, "loss": 2.3836, "step": 4960 }, { "epoch": 2.49, "learning_rate": 2.5141938664554482e-05, "loss": 2.6548, "step": 4965 }, { "epoch": 2.49, "learning_rate": 2.5102511521205718e-05, "loss": 2.5556, "step": 4970 }, { "epoch": 2.5, "learning_rate": 2.5063084122884267e-05, "loss": 2.4746, "step": 4975 }, { "epoch": 2.5, "learning_rate": 2.5023656567656272e-05, "loss": 2.5669, "step": 4980 }, { "epoch": 2.5, "learning_rate": 2.498422895358827e-05, "loss": 2.4125, "step": 4985 }, { "epoch": 2.5, "learning_rate": 2.4944801378746935e-05, "loss": 2.6531, "step": 4990 }, { "epoch": 2.51, "learning_rate": 2.4905373941198864e-05, "loss": 2.7697, "step": 4995 }, { "epoch": 2.51, "learning_rate": 2.48659467390103e-05, "loss": 2.5167, "step": 5000 }, { "epoch": 2.51, "learning_rate": 2.4826519870246897e-05, "loss": 2.6029, "step": 5005 }, { "epoch": 2.51, "learning_rate": 2.478709343297349e-05, "loss": 2.3878, "step": 5010 }, { "epoch": 2.52, "learning_rate": 2.4747667525253825e-05, "loss": 2.6694, "step": 5015 }, { "epoch": 2.52, "learning_rate": 2.470824224515034e-05, "loss": 2.606, "step": 5020 }, { "epoch": 2.52, "learning_rate": 2.466881769072392e-05, "loss": 2.6548, "step": 5025 }, { "epoch": 2.52, "learning_rate": 2.4629393960033633e-05, "loss": 2.2612, "step": 5030 }, { "epoch": 2.53, "learning_rate": 2.4589971151136503e-05, "loss": 2.6507, "step": 5035 }, { "epoch": 2.53, "learning_rate": 2.4550549362087258e-05, "loss": 2.4926, "step": 5040 }, { "epoch": 2.53, "learning_rate": 2.45111286909381e-05, "loss": 2.4079, "step": 5045 }, { "epoch": 2.53, "learning_rate": 2.447170923573844e-05, "loss": 2.5999, "step": 5050 }, { "epoch": 2.54, "learning_rate": 2.443229109453467e-05, "loss": 2.4915, "step": 5055 }, { "epoch": 2.54, "learning_rate": 2.43928743653699e-05, "loss": 2.4626, "step": 5060 }, { "epoch": 2.54, "learning_rate": 2.4353459146283743e-05, "loss": 2.405, "step": 5065 }, { "epoch": 2.54, "learning_rate": 2.431404553531206e-05, "loss": 2.857, "step": 5070 }, { "epoch": 2.55, "learning_rate": 2.42746336304867e-05, "loss": 2.8089, "step": 5075 }, { "epoch": 2.55, "learning_rate": 2.423522352983527e-05, "loss": 2.5966, "step": 5080 }, { "epoch": 2.55, "learning_rate": 2.41958153313809e-05, "loss": 2.4951, "step": 5085 }, { "epoch": 2.55, "learning_rate": 2.4156409133141967e-05, "loss": 2.519, "step": 5090 }, { "epoch": 2.56, "learning_rate": 2.4117005033131894e-05, "loss": 2.4516, "step": 5095 }, { "epoch": 2.56, "learning_rate": 2.40776031293589e-05, "loss": 2.4225, "step": 5100 }, { "epoch": 2.56, "learning_rate": 2.4038203519825676e-05, "loss": 2.47, "step": 5105 }, { "epoch": 2.56, "learning_rate": 2.399880630252928e-05, "loss": 2.4996, "step": 5110 }, { "epoch": 2.57, "learning_rate": 2.3959411575460777e-05, "loss": 2.4737, "step": 5115 }, { "epoch": 2.57, "learning_rate": 2.392001943660506e-05, "loss": 2.636, "step": 5120 }, { "epoch": 2.57, "learning_rate": 2.3880629983940572e-05, "loss": 2.5773, "step": 5125 }, { "epoch": 2.57, "learning_rate": 2.3841243315439077e-05, "loss": 2.7459, "step": 5130 }, { "epoch": 2.58, "learning_rate": 2.3801859529065416e-05, "loss": 2.1073, "step": 5135 }, { "epoch": 2.58, "learning_rate": 2.3762478722777264e-05, "loss": 2.3601, "step": 5140 }, { "epoch": 2.58, "learning_rate": 2.3723100994524873e-05, "loss": 2.5435, "step": 5145 }, { "epoch": 2.58, "learning_rate": 2.3683726442250853e-05, "loss": 2.3054, "step": 5150 }, { "epoch": 2.59, "learning_rate": 2.3644355163889908e-05, "loss": 2.6588, "step": 5155 }, { "epoch": 2.59, "learning_rate": 2.3604987257368596e-05, "loss": 2.6469, "step": 5160 }, { "epoch": 2.59, "learning_rate": 2.3565622820605096e-05, "loss": 2.4276, "step": 5165 }, { "epoch": 2.59, "learning_rate": 2.3526261951508947e-05, "loss": 2.8147, "step": 5170 }, { "epoch": 2.6, "learning_rate": 2.3486904747980817e-05, "loss": 2.5942, "step": 5175 }, { "epoch": 2.6, "learning_rate": 2.344755130791227e-05, "loss": 2.7043, "step": 5180 }, { "epoch": 2.6, "learning_rate": 2.340820172918549e-05, "loss": 2.7551, "step": 5185 }, { "epoch": 2.6, "learning_rate": 2.336885610967308e-05, "loss": 2.4544, "step": 5190 }, { "epoch": 2.61, "learning_rate": 2.3329514547237757e-05, "loss": 2.5914, "step": 5195 }, { "epoch": 2.61, "learning_rate": 2.3290177139732186e-05, "loss": 2.5679, "step": 5200 }, { "epoch": 2.61, "learning_rate": 2.325084398499868e-05, "loss": 2.5207, "step": 5205 }, { "epoch": 2.61, "learning_rate": 2.3211515180868972e-05, "loss": 2.4572, "step": 5210 }, { "epoch": 2.62, "learning_rate": 2.3172190825163987e-05, "loss": 2.6281, "step": 5215 }, { "epoch": 2.62, "learning_rate": 2.3132871015693566e-05, "loss": 2.5488, "step": 5220 }, { "epoch": 2.62, "learning_rate": 2.309355585025627e-05, "loss": 2.74, "step": 5225 }, { "epoch": 2.62, "learning_rate": 2.3054245426639078e-05, "loss": 2.5737, "step": 5230 }, { "epoch": 2.63, "learning_rate": 2.3014939842617197e-05, "loss": 2.5987, "step": 5235 }, { "epoch": 2.63, "learning_rate": 2.297563919595379e-05, "loss": 2.5215, "step": 5240 }, { "epoch": 2.63, "learning_rate": 2.293634358439973e-05, "loss": 2.4514, "step": 5245 }, { "epoch": 2.63, "learning_rate": 2.289705310569338e-05, "loss": 2.8411, "step": 5250 }, { "epoch": 2.64, "learning_rate": 2.2857767857560337e-05, "loss": 2.9463, "step": 5255 }, { "epoch": 2.64, "learning_rate": 2.281848793771318e-05, "loss": 2.6361, "step": 5260 }, { "epoch": 2.64, "learning_rate": 2.2779213443851233e-05, "loss": 2.4919, "step": 5265 }, { "epoch": 2.64, "learning_rate": 2.2739944473660332e-05, "loss": 2.3893, "step": 5270 }, { "epoch": 2.65, "learning_rate": 2.2700681124812574e-05, "loss": 2.6469, "step": 5275 }, { "epoch": 2.65, "learning_rate": 2.2661423494966074e-05, "loss": 2.7062, "step": 5280 }, { "epoch": 2.65, "learning_rate": 2.2622171681764706e-05, "loss": 2.6681, "step": 5285 }, { "epoch": 2.65, "learning_rate": 2.2582925782837898e-05, "loss": 2.5944, "step": 5290 }, { "epoch": 2.66, "learning_rate": 2.254368589580036e-05, "loss": 2.6699, "step": 5295 }, { "epoch": 2.66, "learning_rate": 2.250445211825185e-05, "loss": 2.7243, "step": 5300 }, { "epoch": 2.66, "learning_rate": 2.2465224547776934e-05, "loss": 2.5652, "step": 5305 }, { "epoch": 2.66, "learning_rate": 2.2426003281944725e-05, "loss": 2.4402, "step": 5310 }, { "epoch": 2.67, "learning_rate": 2.238678841830867e-05, "loss": 2.5059, "step": 5315 }, { "epoch": 2.67, "learning_rate": 2.234758005440628e-05, "loss": 2.5083, "step": 5320 }, { "epoch": 2.67, "learning_rate": 2.2308378287758906e-05, "loss": 2.3585, "step": 5325 }, { "epoch": 2.67, "learning_rate": 2.22691832158715e-05, "loss": 2.8297, "step": 5330 }, { "epoch": 2.68, "learning_rate": 2.2229994936232346e-05, "loss": 2.4266, "step": 5335 }, { "epoch": 2.68, "learning_rate": 2.219081354631284e-05, "loss": 2.3729, "step": 5340 }, { "epoch": 2.68, "learning_rate": 2.2151639143567236e-05, "loss": 2.4558, "step": 5345 }, { "epoch": 2.68, "learning_rate": 2.211247182543242e-05, "loss": 2.5797, "step": 5350 }, { "epoch": 2.69, "learning_rate": 2.2073311689327648e-05, "loss": 2.4579, "step": 5355 }, { "epoch": 2.69, "learning_rate": 2.203415883265432e-05, "loss": 2.5511, "step": 5360 }, { "epoch": 2.69, "learning_rate": 2.1995013352795725e-05, "loss": 2.4825, "step": 5365 }, { "epoch": 2.69, "learning_rate": 2.1955875347116808e-05, "loss": 2.4933, "step": 5370 }, { "epoch": 2.7, "learning_rate": 2.191674491296391e-05, "loss": 2.434, "step": 5375 }, { "epoch": 2.7, "learning_rate": 2.187762214766456e-05, "loss": 2.5205, "step": 5380 }, { "epoch": 2.7, "learning_rate": 2.1838507148527197e-05, "loss": 2.5461, "step": 5385 }, { "epoch": 2.7, "learning_rate": 2.179940001284095e-05, "loss": 2.4265, "step": 5390 }, { "epoch": 2.71, "learning_rate": 2.176030083787539e-05, "loss": 2.6166, "step": 5395 }, { "epoch": 2.71, "learning_rate": 2.1721209720880277e-05, "loss": 2.5101, "step": 5400 }, { "epoch": 2.71, "learning_rate": 2.168212675908536e-05, "loss": 2.4824, "step": 5405 }, { "epoch": 2.71, "learning_rate": 2.1643052049700066e-05, "loss": 2.347, "step": 5410 }, { "epoch": 2.72, "learning_rate": 2.1603985689913317e-05, "loss": 2.5476, "step": 5415 }, { "epoch": 2.72, "learning_rate": 2.1564927776893264e-05, "loss": 2.456, "step": 5420 }, { "epoch": 2.72, "learning_rate": 2.152587840778704e-05, "loss": 2.4415, "step": 5425 }, { "epoch": 2.72, "learning_rate": 2.1486837679720535e-05, "loss": 2.7548, "step": 5430 }, { "epoch": 2.73, "learning_rate": 2.144780568979816e-05, "loss": 2.3779, "step": 5435 }, { "epoch": 2.73, "learning_rate": 2.1408782535102566e-05, "loss": 2.5284, "step": 5440 }, { "epoch": 2.73, "learning_rate": 2.136976831269444e-05, "loss": 2.6886, "step": 5445 }, { "epoch": 2.73, "learning_rate": 2.133076311961226e-05, "loss": 2.5138, "step": 5450 }, { "epoch": 2.74, "learning_rate": 2.1291767052872035e-05, "loss": 2.664, "step": 5455 }, { "epoch": 2.74, "learning_rate": 2.1252780209467073e-05, "loss": 2.4325, "step": 5460 }, { "epoch": 2.74, "learning_rate": 2.121380268636775e-05, "loss": 2.5471, "step": 5465 }, { "epoch": 2.74, "learning_rate": 2.1174834580521253e-05, "loss": 2.4363, "step": 5470 }, { "epoch": 2.75, "learning_rate": 2.113587598885135e-05, "loss": 2.6272, "step": 5475 }, { "epoch": 2.75, "learning_rate": 2.109692700825814e-05, "loss": 2.5261, "step": 5480 }, { "epoch": 2.75, "learning_rate": 2.105798773561783e-05, "loss": 2.9262, "step": 5485 }, { "epoch": 2.75, "learning_rate": 2.101905826778246e-05, "loss": 2.3964, "step": 5490 }, { "epoch": 2.76, "learning_rate": 2.0980138701579704e-05, "loss": 2.6239, "step": 5495 }, { "epoch": 2.76, "learning_rate": 2.0941229133812593e-05, "loss": 2.53, "step": 5500 }, { "epoch": 2.76, "learning_rate": 2.0902329661259293e-05, "loss": 2.7035, "step": 5505 }, { "epoch": 2.77, "learning_rate": 2.0863440380672856e-05, "loss": 2.5909, "step": 5510 }, { "epoch": 2.77, "learning_rate": 2.0824561388781005e-05, "loss": 2.1592, "step": 5515 }, { "epoch": 2.77, "learning_rate": 2.078569278228585e-05, "loss": 2.5515, "step": 5520 }, { "epoch": 2.77, "learning_rate": 2.0746834657863672e-05, "loss": 2.6217, "step": 5525 }, { "epoch": 2.78, "learning_rate": 2.0707987112164692e-05, "loss": 2.6302, "step": 5530 }, { "epoch": 2.78, "learning_rate": 2.0669150241812807e-05, "loss": 2.3984, "step": 5535 }, { "epoch": 2.78, "learning_rate": 2.0630324143405372e-05, "loss": 2.6425, "step": 5540 }, { "epoch": 2.78, "learning_rate": 2.0591508913512954e-05, "loss": 2.6817, "step": 5545 }, { "epoch": 2.79, "learning_rate": 2.055270464867906e-05, "loss": 2.3904, "step": 5550 }, { "epoch": 2.79, "learning_rate": 2.0513911445419936e-05, "loss": 2.6625, "step": 5555 }, { "epoch": 2.79, "learning_rate": 2.0475129400224337e-05, "loss": 2.6876, "step": 5560 }, { "epoch": 2.79, "learning_rate": 2.043635860955325e-05, "loss": 2.4981, "step": 5565 }, { "epoch": 2.8, "learning_rate": 2.039759916983966e-05, "loss": 2.3809, "step": 5570 }, { "epoch": 2.8, "learning_rate": 2.0358851177488326e-05, "loss": 2.4396, "step": 5575 }, { "epoch": 2.8, "learning_rate": 2.0320114728875538e-05, "loss": 2.526, "step": 5580 }, { "epoch": 2.8, "learning_rate": 2.028138992034887e-05, "loss": 2.6806, "step": 5585 }, { "epoch": 2.81, "learning_rate": 2.0242676848226948e-05, "loss": 2.5842, "step": 5590 }, { "epoch": 2.81, "learning_rate": 2.02039756087992e-05, "loss": 2.4016, "step": 5595 }, { "epoch": 2.81, "learning_rate": 2.0165286298325638e-05, "loss": 2.5254, "step": 5600 }, { "epoch": 2.81, "learning_rate": 2.0126609013036575e-05, "loss": 2.4995, "step": 5605 }, { "epoch": 2.82, "learning_rate": 2.0087943849132446e-05, "loss": 2.473, "step": 5610 }, { "epoch": 2.82, "learning_rate": 2.004929090278351e-05, "loss": 2.668, "step": 5615 }, { "epoch": 2.82, "learning_rate": 2.001065027012966e-05, "loss": 2.693, "step": 5620 }, { "epoch": 2.82, "learning_rate": 1.9972022047280154e-05, "loss": 2.5113, "step": 5625 }, { "epoch": 2.83, "learning_rate": 1.9933406330313374e-05, "loss": 2.7322, "step": 5630 }, { "epoch": 2.83, "learning_rate": 1.989480321527661e-05, "loss": 2.6501, "step": 5635 }, { "epoch": 2.83, "learning_rate": 1.9856212798185798e-05, "loss": 2.546, "step": 5640 }, { "epoch": 2.83, "learning_rate": 1.9817635175025295e-05, "loss": 2.8634, "step": 5645 }, { "epoch": 2.84, "learning_rate": 1.9779070441747638e-05, "loss": 2.2475, "step": 5650 }, { "epoch": 2.84, "learning_rate": 1.97405186942733e-05, "loss": 2.5021, "step": 5655 }, { "epoch": 2.84, "learning_rate": 1.9701980028490452e-05, "loss": 2.4607, "step": 5660 }, { "epoch": 2.84, "learning_rate": 1.9663454540254744e-05, "loss": 2.4587, "step": 5665 }, { "epoch": 2.85, "learning_rate": 1.9624942325389032e-05, "loss": 2.6975, "step": 5670 }, { "epoch": 2.85, "learning_rate": 1.9586443479683164e-05, "loss": 2.728, "step": 5675 }, { "epoch": 2.85, "learning_rate": 1.9547958098893734e-05, "loss": 2.6458, "step": 5680 }, { "epoch": 2.85, "learning_rate": 1.9509486278743847e-05, "loss": 2.7608, "step": 5685 }, { "epoch": 2.86, "learning_rate": 1.9471028114922873e-05, "loss": 2.7753, "step": 5690 }, { "epoch": 2.86, "learning_rate": 1.9432583703086235e-05, "loss": 2.3438, "step": 5695 }, { "epoch": 2.86, "learning_rate": 1.9394153138855127e-05, "loss": 2.5513, "step": 5700 }, { "epoch": 2.86, "learning_rate": 1.9355736517816313e-05, "loss": 2.6064, "step": 5705 }, { "epoch": 2.87, "learning_rate": 1.9317333935521872e-05, "loss": 2.6884, "step": 5710 }, { "epoch": 2.87, "learning_rate": 1.927894548748897e-05, "loss": 2.479, "step": 5715 }, { "epoch": 2.87, "learning_rate": 1.9240571269199607e-05, "loss": 2.741, "step": 5720 }, { "epoch": 2.87, "learning_rate": 1.9202211376100427e-05, "loss": 2.6736, "step": 5725 }, { "epoch": 2.88, "learning_rate": 1.9163865903602374e-05, "loss": 2.5357, "step": 5730 }, { "epoch": 2.88, "learning_rate": 1.9125534947080574e-05, "loss": 2.4667, "step": 5735 }, { "epoch": 2.88, "learning_rate": 1.908721860187406e-05, "loss": 2.3793, "step": 5740 }, { "epoch": 2.88, "learning_rate": 1.904891696328548e-05, "loss": 2.6379, "step": 5745 }, { "epoch": 2.89, "learning_rate": 1.901063012658093e-05, "loss": 2.5932, "step": 5750 }, { "epoch": 2.89, "learning_rate": 1.897235818698969e-05, "loss": 2.3479, "step": 5755 }, { "epoch": 2.89, "learning_rate": 1.8934101239703973e-05, "loss": 2.7664, "step": 5760 }, { "epoch": 2.89, "learning_rate": 1.889585937987871e-05, "loss": 2.6163, "step": 5765 }, { "epoch": 2.9, "learning_rate": 1.885763270263131e-05, "loss": 2.644, "step": 5770 }, { "epoch": 2.9, "learning_rate": 1.881942130304142e-05, "loss": 2.6584, "step": 5775 }, { "epoch": 2.9, "learning_rate": 1.8781225276150675e-05, "loss": 2.7552, "step": 5780 }, { "epoch": 2.9, "learning_rate": 1.874304471696248e-05, "loss": 2.3176, "step": 5785 }, { "epoch": 2.91, "learning_rate": 1.8704879720441773e-05, "loss": 2.9294, "step": 5790 }, { "epoch": 2.91, "learning_rate": 1.8666730381514774e-05, "loss": 2.5388, "step": 5795 }, { "epoch": 2.91, "learning_rate": 1.8628596795068776e-05, "loss": 2.5343, "step": 5800 }, { "epoch": 2.91, "learning_rate": 1.859047905595187e-05, "loss": 2.5239, "step": 5805 }, { "epoch": 2.92, "learning_rate": 1.8552377258972747e-05, "loss": 2.382, "step": 5810 }, { "epoch": 2.92, "learning_rate": 1.851429149890044e-05, "loss": 2.7965, "step": 5815 }, { "epoch": 2.92, "learning_rate": 1.8476221870464083e-05, "loss": 2.738, "step": 5820 }, { "epoch": 2.92, "learning_rate": 1.84381684683527e-05, "loss": 2.7431, "step": 5825 }, { "epoch": 2.93, "learning_rate": 1.8400131387214964e-05, "loss": 2.6551, "step": 5830 }, { "epoch": 2.93, "learning_rate": 1.8362110721658927e-05, "loss": 2.5836, "step": 5835 }, { "epoch": 2.93, "learning_rate": 1.832410656625183e-05, "loss": 2.3278, "step": 5840 }, { "epoch": 2.93, "learning_rate": 1.8286119015519852e-05, "loss": 2.5348, "step": 5845 }, { "epoch": 2.94, "learning_rate": 1.8248148163947866e-05, "loss": 2.388, "step": 5850 }, { "epoch": 2.94, "learning_rate": 1.8210194105979205e-05, "loss": 2.5839, "step": 5855 }, { "epoch": 2.94, "learning_rate": 1.817225693601543e-05, "loss": 2.7362, "step": 5860 }, { "epoch": 2.94, "learning_rate": 1.8134336748416115e-05, "loss": 2.2506, "step": 5865 }, { "epoch": 2.95, "learning_rate": 1.8096433637498574e-05, "loss": 2.6163, "step": 5870 }, { "epoch": 2.95, "learning_rate": 1.8058547697537655e-05, "loss": 2.6588, "step": 5875 }, { "epoch": 2.95, "learning_rate": 1.802067902276551e-05, "loss": 2.6955, "step": 5880 }, { "epoch": 2.95, "learning_rate": 1.7982827707371326e-05, "loss": 2.5438, "step": 5885 }, { "epoch": 2.96, "learning_rate": 1.7944993845501118e-05, "loss": 2.6858, "step": 5890 }, { "epoch": 2.96, "learning_rate": 1.7907177531257507e-05, "loss": 2.5499, "step": 5895 }, { "epoch": 2.96, "learning_rate": 1.7869378858699452e-05, "loss": 2.572, "step": 5900 }, { "epoch": 2.96, "learning_rate": 1.783159792184203e-05, "loss": 2.6499, "step": 5905 }, { "epoch": 2.97, "learning_rate": 1.779383481465622e-05, "loss": 2.6526, "step": 5910 }, { "epoch": 2.97, "learning_rate": 1.775608963106863e-05, "loss": 2.5916, "step": 5915 }, { "epoch": 2.97, "learning_rate": 1.7718362464961314e-05, "loss": 2.7463, "step": 5920 }, { "epoch": 2.97, "learning_rate": 1.76806534101715e-05, "loss": 2.6052, "step": 5925 }, { "epoch": 2.98, "learning_rate": 1.764296256049137e-05, "loss": 2.4542, "step": 5930 }, { "epoch": 2.98, "learning_rate": 1.760529000966782e-05, "loss": 2.5414, "step": 5935 }, { "epoch": 2.98, "learning_rate": 1.7567635851402238e-05, "loss": 2.6181, "step": 5940 }, { "epoch": 2.98, "learning_rate": 1.753000017935026e-05, "loss": 2.4822, "step": 5945 }, { "epoch": 2.99, "learning_rate": 1.7492383087121546e-05, "loss": 2.6495, "step": 5950 }, { "epoch": 2.99, "learning_rate": 1.7454784668279546e-05, "loss": 2.455, "step": 5955 }, { "epoch": 2.99, "learning_rate": 1.7417205016341258e-05, "loss": 2.3959, "step": 5960 }, { "epoch": 2.99, "learning_rate": 1.7379644224777004e-05, "loss": 2.5139, "step": 5965 }, { "epoch": 3.0, "learning_rate": 1.7342102387010194e-05, "loss": 2.6985, "step": 5970 }, { "epoch": 3.0, "learning_rate": 1.7304579596417104e-05, "loss": 2.6598, "step": 5975 }, { "epoch": 3.0, "learning_rate": 1.726707594632661e-05, "loss": 2.6638, "step": 5980 }, { "epoch": 3.0, "learning_rate": 1.7229591530020022e-05, "loss": 2.446, "step": 5985 }, { "epoch": 3.01, "learning_rate": 1.7192126440730784e-05, "loss": 2.5736, "step": 5990 }, { "epoch": 3.01, "learning_rate": 1.7154680771644242e-05, "loss": 2.4385, "step": 5995 }, { "epoch": 3.01, "learning_rate": 1.7117254615897497e-05, "loss": 2.5651, "step": 6000 } ], "logging_steps": 5, "max_steps": 9960, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "total_flos": 3.175526755909632e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }