{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.5018190942165349, "eval_steps": 500, "global_step": 1000, "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 } ], "logging_steps": 5, "max_steps": 9960, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "total_flos": 5.320804662283469e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }