{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1863, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005367686527106817, "grad_norm": 24.305655426812773, "learning_rate": 5.3475935828877005e-08, "loss": 1.3555, "step": 1 }, { "epoch": 0.0026838432635534087, "grad_norm": 23.22138878044751, "learning_rate": 2.6737967914438503e-07, "loss": 1.3448, "step": 5 }, { "epoch": 0.005367686527106817, "grad_norm": 15.39412500867573, "learning_rate": 5.347593582887701e-07, "loss": 1.3152, "step": 10 }, { "epoch": 0.008051529790660225, "grad_norm": 11.814690159057262, "learning_rate": 8.021390374331551e-07, "loss": 1.1495, "step": 15 }, { "epoch": 0.010735373054213635, "grad_norm": 9.400955813538365, "learning_rate": 1.0695187165775401e-06, "loss": 1.0489, "step": 20 }, { "epoch": 0.013419216317767043, "grad_norm": 3.612620121520767, "learning_rate": 1.3368983957219254e-06, "loss": 0.962, "step": 25 }, { "epoch": 0.01610305958132045, "grad_norm": 3.507034366901718, "learning_rate": 1.6042780748663103e-06, "loss": 0.9095, "step": 30 }, { "epoch": 0.01878690284487386, "grad_norm": 2.9769449976377174, "learning_rate": 1.8716577540106954e-06, "loss": 0.8651, "step": 35 }, { "epoch": 0.02147074610842727, "grad_norm": 2.963828184373544, "learning_rate": 2.1390374331550802e-06, "loss": 0.8482, "step": 40 }, { "epoch": 0.024154589371980676, "grad_norm": 3.1133147768329232, "learning_rate": 2.4064171122994653e-06, "loss": 0.85, "step": 45 }, { "epoch": 0.026838432635534086, "grad_norm": 2.931545369425598, "learning_rate": 2.673796791443851e-06, "loss": 0.8309, "step": 50 }, { "epoch": 0.029522275899087493, "grad_norm": 3.0256227773094384, "learning_rate": 2.9411764705882355e-06, "loss": 0.8186, "step": 55 }, { "epoch": 0.0322061191626409, "grad_norm": 3.0925781868322955, "learning_rate": 3.2085561497326205e-06, "loss": 0.8041, "step": 60 }, { "epoch": 0.03488996242619431, "grad_norm": 3.063930015490271, "learning_rate": 3.4759358288770056e-06, "loss": 0.806, "step": 65 }, { "epoch": 0.03757380568974772, "grad_norm": 3.2043146977534662, "learning_rate": 3.7433155080213907e-06, "loss": 0.8075, "step": 70 }, { "epoch": 0.040257648953301126, "grad_norm": 2.92763825791418, "learning_rate": 4.010695187165775e-06, "loss": 0.7952, "step": 75 }, { "epoch": 0.04294149221685454, "grad_norm": 3.0927861281954665, "learning_rate": 4.2780748663101604e-06, "loss": 0.7924, "step": 80 }, { "epoch": 0.045625335480407946, "grad_norm": 3.0187031080233817, "learning_rate": 4.5454545454545455e-06, "loss": 0.7472, "step": 85 }, { "epoch": 0.04830917874396135, "grad_norm": 2.974576768839193, "learning_rate": 4.812834224598931e-06, "loss": 0.7615, "step": 90 }, { "epoch": 0.05099302200751476, "grad_norm": 2.986145546612386, "learning_rate": 5.0802139037433165e-06, "loss": 0.7619, "step": 95 }, { "epoch": 0.05367686527106817, "grad_norm": 3.0743318362981755, "learning_rate": 5.347593582887702e-06, "loss": 0.7617, "step": 100 }, { "epoch": 0.05636070853462158, "grad_norm": 3.2918058213261094, "learning_rate": 5.614973262032086e-06, "loss": 0.7675, "step": 105 }, { "epoch": 0.059044551798174985, "grad_norm": 3.2237072710532493, "learning_rate": 5.882352941176471e-06, "loss": 0.7331, "step": 110 }, { "epoch": 0.06172839506172839, "grad_norm": 3.1899890654845606, "learning_rate": 6.149732620320856e-06, "loss": 0.7459, "step": 115 }, { "epoch": 0.0644122383252818, "grad_norm": 3.043596246389249, "learning_rate": 6.417112299465241e-06, "loss": 0.744, "step": 120 }, { "epoch": 0.06709608158883522, "grad_norm": 2.9018863887175743, "learning_rate": 6.684491978609626e-06, "loss": 0.7377, "step": 125 }, { "epoch": 0.06977992485238863, "grad_norm": 2.907463722040111, "learning_rate": 6.951871657754011e-06, "loss": 0.7427, "step": 130 }, { "epoch": 0.07246376811594203, "grad_norm": 2.84315815544186, "learning_rate": 7.219251336898396e-06, "loss": 0.7319, "step": 135 }, { "epoch": 0.07514761137949544, "grad_norm": 2.973654603626244, "learning_rate": 7.486631016042781e-06, "loss": 0.7328, "step": 140 }, { "epoch": 0.07783145464304884, "grad_norm": 3.141459628944732, "learning_rate": 7.754010695187166e-06, "loss": 0.7338, "step": 145 }, { "epoch": 0.08051529790660225, "grad_norm": 2.842095254666257, "learning_rate": 8.02139037433155e-06, "loss": 0.7343, "step": 150 }, { "epoch": 0.08319914117015566, "grad_norm": 2.868583490076937, "learning_rate": 8.288770053475937e-06, "loss": 0.7287, "step": 155 }, { "epoch": 0.08588298443370908, "grad_norm": 2.8470718739082255, "learning_rate": 8.556149732620321e-06, "loss": 0.7195, "step": 160 }, { "epoch": 0.08856682769726248, "grad_norm": 2.9010358259004065, "learning_rate": 8.823529411764707e-06, "loss": 0.7036, "step": 165 }, { "epoch": 0.09125067096081589, "grad_norm": 3.305646484034517, "learning_rate": 9.090909090909091e-06, "loss": 0.7215, "step": 170 }, { "epoch": 0.0939345142243693, "grad_norm": 2.969331866099511, "learning_rate": 9.358288770053477e-06, "loss": 0.721, "step": 175 }, { "epoch": 0.0966183574879227, "grad_norm": 2.93754880819952, "learning_rate": 9.625668449197861e-06, "loss": 0.7038, "step": 180 }, { "epoch": 0.09930220075147611, "grad_norm": 2.7050202580005065, "learning_rate": 9.893048128342247e-06, "loss": 0.7206, "step": 185 }, { "epoch": 0.10198604401502952, "grad_norm": 3.047634989404141, "learning_rate": 9.999920944317846e-06, "loss": 0.6872, "step": 190 }, { "epoch": 0.10466988727858294, "grad_norm": 2.795885504909657, "learning_rate": 9.99943783531341e-06, "loss": 0.7127, "step": 195 }, { "epoch": 0.10735373054213634, "grad_norm": 2.744750472731151, "learning_rate": 9.998515579512446e-06, "loss": 0.7165, "step": 200 }, { "epoch": 0.11003757380568975, "grad_norm": 2.7651055012729104, "learning_rate": 9.997154257925199e-06, "loss": 0.7171, "step": 205 }, { "epoch": 0.11272141706924316, "grad_norm": 3.206532585503099, "learning_rate": 9.995353990129115e-06, "loss": 0.695, "step": 210 }, { "epoch": 0.11540526033279656, "grad_norm": 3.024589614754047, "learning_rate": 9.99311493425834e-06, "loss": 0.7037, "step": 215 }, { "epoch": 0.11808910359634997, "grad_norm": 2.551935026870453, "learning_rate": 9.99043728698983e-06, "loss": 0.6877, "step": 220 }, { "epoch": 0.12077294685990338, "grad_norm": 2.539435880635434, "learning_rate": 9.987321283526072e-06, "loss": 0.7087, "step": 225 }, { "epoch": 0.12345679012345678, "grad_norm": 2.676637809439421, "learning_rate": 9.983767197574432e-06, "loss": 0.6936, "step": 230 }, { "epoch": 0.1261406333870102, "grad_norm": 2.7492296664847045, "learning_rate": 9.979775341323097e-06, "loss": 0.6915, "step": 235 }, { "epoch": 0.1288244766505636, "grad_norm": 2.6934789882553742, "learning_rate": 9.975346065413673e-06, "loss": 0.7031, "step": 240 }, { "epoch": 0.13150831991411702, "grad_norm": 2.640702210698053, "learning_rate": 9.970479758910365e-06, "loss": 0.7108, "step": 245 }, { "epoch": 0.13419216317767044, "grad_norm": 2.748234011053248, "learning_rate": 9.965176849265814e-06, "loss": 0.7027, "step": 250 }, { "epoch": 0.13687600644122383, "grad_norm": 2.5844501833121294, "learning_rate": 9.959437802283552e-06, "loss": 0.6878, "step": 255 }, { "epoch": 0.13955984970477725, "grad_norm": 2.66470810089039, "learning_rate": 9.953263122077077e-06, "loss": 0.6805, "step": 260 }, { "epoch": 0.14224369296833064, "grad_norm": 2.4613007519929866, "learning_rate": 9.946653351025575e-06, "loss": 0.6808, "step": 265 }, { "epoch": 0.14492753623188406, "grad_norm": 2.7303364431033583, "learning_rate": 9.939609069726279e-06, "loss": 0.6872, "step": 270 }, { "epoch": 0.14761137949543746, "grad_norm": 2.4095297951330865, "learning_rate": 9.932130896943477e-06, "loss": 0.6788, "step": 275 }, { "epoch": 0.15029522275899088, "grad_norm": 2.5247027802281847, "learning_rate": 9.924219489554145e-06, "loss": 0.6903, "step": 280 }, { "epoch": 0.1529790660225443, "grad_norm": 2.48852250288296, "learning_rate": 9.915875542490257e-06, "loss": 0.6873, "step": 285 }, { "epoch": 0.1556629092860977, "grad_norm": 2.5324167659849333, "learning_rate": 9.907099788677745e-06, "loss": 0.6576, "step": 290 }, { "epoch": 0.1583467525496511, "grad_norm": 2.564293700320395, "learning_rate": 9.897892998972113e-06, "loss": 0.6685, "step": 295 }, { "epoch": 0.1610305958132045, "grad_norm": 2.7292649090364183, "learning_rate": 9.888255982090728e-06, "loss": 0.6812, "step": 300 }, { "epoch": 0.16371443907675792, "grad_norm": 2.43813150224106, "learning_rate": 9.878189584541783e-06, "loss": 0.6707, "step": 305 }, { "epoch": 0.16639828234031132, "grad_norm": 4.145173454039506, "learning_rate": 9.867694690549943e-06, "loss": 0.6579, "step": 310 }, { "epoch": 0.16908212560386474, "grad_norm": 2.5276238351648552, "learning_rate": 9.85677222197867e-06, "loss": 0.6707, "step": 315 }, { "epoch": 0.17176596886741816, "grad_norm": 2.482449160388171, "learning_rate": 9.845423138249254e-06, "loss": 0.6629, "step": 320 }, { "epoch": 0.17444981213097155, "grad_norm": 2.426718943488087, "learning_rate": 9.833648436256525e-06, "loss": 0.6677, "step": 325 }, { "epoch": 0.17713365539452497, "grad_norm": 2.453880759981358, "learning_rate": 9.821449150281308e-06, "loss": 0.6725, "step": 330 }, { "epoch": 0.17981749865807836, "grad_norm": 2.539784755342757, "learning_rate": 9.808826351899551e-06, "loss": 0.6626, "step": 335 }, { "epoch": 0.18250134192163178, "grad_norm": 2.519434594701762, "learning_rate": 9.795781149888216e-06, "loss": 0.666, "step": 340 }, { "epoch": 0.18518518518518517, "grad_norm": 2.7383878655688814, "learning_rate": 9.782314690127867e-06, "loss": 0.6448, "step": 345 }, { "epoch": 0.1878690284487386, "grad_norm": 2.64399762195394, "learning_rate": 9.768428155502038e-06, "loss": 0.654, "step": 350 }, { "epoch": 0.19055287171229202, "grad_norm": 2.4804265805545134, "learning_rate": 9.754122765793306e-06, "loss": 0.629, "step": 355 }, { "epoch": 0.1932367149758454, "grad_norm": 2.543201466486224, "learning_rate": 9.739399777576169e-06, "loss": 0.6409, "step": 360 }, { "epoch": 0.19592055823939883, "grad_norm": 2.5609743466777397, "learning_rate": 9.72426048410665e-06, "loss": 0.6568, "step": 365 }, { "epoch": 0.19860440150295222, "grad_norm": 2.403379282200782, "learning_rate": 9.70870621520871e-06, "loss": 0.645, "step": 370 }, { "epoch": 0.20128824476650564, "grad_norm": 2.3259878238624014, "learning_rate": 9.692738337157441e-06, "loss": 0.6507, "step": 375 }, { "epoch": 0.20397208803005903, "grad_norm": 2.5652621488474936, "learning_rate": 9.676358252559034e-06, "loss": 0.6441, "step": 380 }, { "epoch": 0.20665593129361245, "grad_norm": 2.7173664219726934, "learning_rate": 9.6595674002276e-06, "loss": 0.6407, "step": 385 }, { "epoch": 0.20933977455716588, "grad_norm": 2.6039911875109563, "learning_rate": 9.642367255058767e-06, "loss": 0.6218, "step": 390 }, { "epoch": 0.21202361782071927, "grad_norm": 2.344579879458719, "learning_rate": 9.624759327900131e-06, "loss": 0.6536, "step": 395 }, { "epoch": 0.2147074610842727, "grad_norm": 2.6297589664652947, "learning_rate": 9.606745165418554e-06, "loss": 0.6363, "step": 400 }, { "epoch": 0.21739130434782608, "grad_norm": 2.39785560505727, "learning_rate": 9.58832634996429e-06, "loss": 0.6436, "step": 405 }, { "epoch": 0.2200751476113795, "grad_norm": 2.585642851240206, "learning_rate": 9.569504499432005e-06, "loss": 0.6258, "step": 410 }, { "epoch": 0.2227589908749329, "grad_norm": 2.8691418365076053, "learning_rate": 9.550281267118659e-06, "loss": 0.6275, "step": 415 }, { "epoch": 0.22544283413848631, "grad_norm": 2.476684695004809, "learning_rate": 9.530658341578276e-06, "loss": 0.6417, "step": 420 }, { "epoch": 0.2281266774020397, "grad_norm": 2.363278675306579, "learning_rate": 9.510637446473633e-06, "loss": 0.6242, "step": 425 }, { "epoch": 0.23081052066559313, "grad_norm": 2.4597379363178624, "learning_rate": 9.490220340424844e-06, "loss": 0.6375, "step": 430 }, { "epoch": 0.23349436392914655, "grad_norm": 2.383668683197536, "learning_rate": 9.469408816854898e-06, "loss": 0.6058, "step": 435 }, { "epoch": 0.23617820719269994, "grad_norm": 2.355853732674972, "learning_rate": 9.448204703832102e-06, "loss": 0.6156, "step": 440 }, { "epoch": 0.23886205045625336, "grad_norm": 2.3375352653671646, "learning_rate": 9.426609863909537e-06, "loss": 0.6238, "step": 445 }, { "epoch": 0.24154589371980675, "grad_norm": 2.547634943087699, "learning_rate": 9.404626193961427e-06, "loss": 0.6186, "step": 450 }, { "epoch": 0.24422973698336017, "grad_norm": 2.719745903154331, "learning_rate": 9.382255625016527e-06, "loss": 0.6312, "step": 455 }, { "epoch": 0.24691358024691357, "grad_norm": 2.8633960737686164, "learning_rate": 9.359500122088511e-06, "loss": 0.6158, "step": 460 }, { "epoch": 0.249597423510467, "grad_norm": 2.4972600338410573, "learning_rate": 9.336361684003353e-06, "loss": 0.629, "step": 465 }, { "epoch": 0.2522812667740204, "grad_norm": 2.2735215195501697, "learning_rate": 9.312842343223764e-06, "loss": 0.6106, "step": 470 }, { "epoch": 0.2549651100375738, "grad_norm": 2.365141838824348, "learning_rate": 9.288944165670651e-06, "loss": 0.6059, "step": 475 }, { "epoch": 0.2576489533011272, "grad_norm": 2.5760090652843046, "learning_rate": 9.264669250541658e-06, "loss": 0.6246, "step": 480 }, { "epoch": 0.2603327965646806, "grad_norm": 2.5329655943720226, "learning_rate": 9.240019730126764e-06, "loss": 0.606, "step": 485 }, { "epoch": 0.26301663982823403, "grad_norm": 2.5738935216730003, "learning_rate": 9.214997769620998e-06, "loss": 0.6143, "step": 490 }, { "epoch": 0.26570048309178745, "grad_norm": 2.63987142371882, "learning_rate": 9.189605566934235e-06, "loss": 0.602, "step": 495 }, { "epoch": 0.2683843263553409, "grad_norm": 2.322948855489504, "learning_rate": 9.163845352498141e-06, "loss": 0.5985, "step": 500 }, { "epoch": 0.27106816961889424, "grad_norm": 2.402976520275366, "learning_rate": 9.137719389070259e-06, "loss": 0.608, "step": 505 }, { "epoch": 0.27375201288244766, "grad_norm": 2.456701559661602, "learning_rate": 9.111229971535231e-06, "loss": 0.6084, "step": 510 }, { "epoch": 0.2764358561460011, "grad_norm": 2.396999722003953, "learning_rate": 9.084379426703245e-06, "loss": 0.6078, "step": 515 }, { "epoch": 0.2791196994095545, "grad_norm": 2.2944656877855123, "learning_rate": 9.057170113105622e-06, "loss": 0.5982, "step": 520 }, { "epoch": 0.28180354267310787, "grad_norm": 2.5488002762479773, "learning_rate": 9.029604420787666e-06, "loss": 0.595, "step": 525 }, { "epoch": 0.2844873859366613, "grad_norm": 2.5621814193544656, "learning_rate": 9.001684771098709e-06, "loss": 0.5849, "step": 530 }, { "epoch": 0.2871712292002147, "grad_norm": 2.4681234501326927, "learning_rate": 8.973413616479429e-06, "loss": 0.5943, "step": 535 }, { "epoch": 0.2898550724637681, "grad_norm": 2.722213219660786, "learning_rate": 8.944793440246435e-06, "loss": 0.6, "step": 540 }, { "epoch": 0.29253891572732155, "grad_norm": 2.482994818215236, "learning_rate": 8.915826756374118e-06, "loss": 0.6043, "step": 545 }, { "epoch": 0.2952227589908749, "grad_norm": 2.3130329135558867, "learning_rate": 8.88651610927384e-06, "loss": 0.585, "step": 550 }, { "epoch": 0.29790660225442833, "grad_norm": 2.608504562134939, "learning_rate": 8.856864073570429e-06, "loss": 0.5769, "step": 555 }, { "epoch": 0.30059044551798175, "grad_norm": 2.518035685353769, "learning_rate": 8.82687325387603e-06, "loss": 0.5684, "step": 560 }, { "epoch": 0.3032742887815352, "grad_norm": 2.3907513070004662, "learning_rate": 8.796546284561307e-06, "loss": 0.5925, "step": 565 }, { "epoch": 0.3059581320450886, "grad_norm": 2.3102125436889347, "learning_rate": 8.765885829524059e-06, "loss": 0.5875, "step": 570 }, { "epoch": 0.30864197530864196, "grad_norm": 2.3679548171728224, "learning_rate": 8.734894581955208e-06, "loss": 0.5935, "step": 575 }, { "epoch": 0.3113258185721954, "grad_norm": 2.384663332405018, "learning_rate": 8.703575264102245e-06, "loss": 0.587, "step": 580 }, { "epoch": 0.3140096618357488, "grad_norm": 2.4842753819177177, "learning_rate": 8.6719306270301e-06, "loss": 0.5877, "step": 585 }, { "epoch": 0.3166935050993022, "grad_norm": 2.4604537301515355, "learning_rate": 8.639963450379494e-06, "loss": 0.5937, "step": 590 }, { "epoch": 0.3193773483628556, "grad_norm": 2.3929768937522464, "learning_rate": 8.607676542122782e-06, "loss": 0.5873, "step": 595 }, { "epoch": 0.322061191626409, "grad_norm": 2.2712444923217303, "learning_rate": 8.575072738317297e-06, "loss": 0.5867, "step": 600 }, { "epoch": 0.3247450348899624, "grad_norm": 2.4285841734633054, "learning_rate": 8.542154902856232e-06, "loss": 0.5798, "step": 605 }, { "epoch": 0.32742887815351585, "grad_norm": 2.5643185358166165, "learning_rate": 8.508925927217083e-06, "loss": 0.5696, "step": 610 }, { "epoch": 0.33011272141706927, "grad_norm": 2.480969569279566, "learning_rate": 8.475388730207662e-06, "loss": 0.5531, "step": 615 }, { "epoch": 0.33279656468062263, "grad_norm": 2.4832540196963455, "learning_rate": 8.441546257709708e-06, "loss": 0.5653, "step": 620 }, { "epoch": 0.33548040794417605, "grad_norm": 2.3354177059858623, "learning_rate": 8.407401482420129e-06, "loss": 0.5788, "step": 625 }, { "epoch": 0.33816425120772947, "grad_norm": 2.542916086554623, "learning_rate": 8.372957403589873e-06, "loss": 0.5626, "step": 630 }, { "epoch": 0.3408480944712829, "grad_norm": 2.469264768397056, "learning_rate": 8.33821704676049e-06, "loss": 0.5641, "step": 635 }, { "epoch": 0.3435319377348363, "grad_norm": 2.335932114462721, "learning_rate": 8.303183463498357e-06, "loss": 0.5588, "step": 640 }, { "epoch": 0.3462157809983897, "grad_norm": 2.3426121287532506, "learning_rate": 8.26785973112664e-06, "loss": 0.5665, "step": 645 }, { "epoch": 0.3488996242619431, "grad_norm": 2.5085502164744407, "learning_rate": 8.232248952454978e-06, "loss": 0.5551, "step": 650 }, { "epoch": 0.3515834675254965, "grad_norm": 2.367908978354936, "learning_rate": 8.196354255506937e-06, "loss": 0.5841, "step": 655 }, { "epoch": 0.35426731078904994, "grad_norm": 2.368147432676988, "learning_rate": 8.160178793245254e-06, "loss": 0.5543, "step": 660 }, { "epoch": 0.3569511540526033, "grad_norm": 2.4274434068510464, "learning_rate": 8.12372574329487e-06, "loss": 0.553, "step": 665 }, { "epoch": 0.3596349973161567, "grad_norm": 2.42778146542873, "learning_rate": 8.086998307663815e-06, "loss": 0.5613, "step": 670 }, { "epoch": 0.36231884057971014, "grad_norm": 2.38111212352637, "learning_rate": 8.049999712461956e-06, "loss": 0.5437, "step": 675 }, { "epoch": 0.36500268384326356, "grad_norm": 2.33473536282302, "learning_rate": 8.012733207617602e-06, "loss": 0.5519, "step": 680 }, { "epoch": 0.367686527106817, "grad_norm": 2.260812226426273, "learning_rate": 7.975202066592038e-06, "loss": 0.5453, "step": 685 }, { "epoch": 0.37037037037037035, "grad_norm": 2.463629677104882, "learning_rate": 7.937409586091996e-06, "loss": 0.552, "step": 690 }, { "epoch": 0.37305421363392377, "grad_norm": 2.507311462473454, "learning_rate": 7.899359085780062e-06, "loss": 0.5482, "step": 695 }, { "epoch": 0.3757380568974772, "grad_norm": 2.4632736487546905, "learning_rate": 7.86105390798309e-06, "loss": 0.5416, "step": 700 }, { "epoch": 0.3784219001610306, "grad_norm": 2.4592304831976333, "learning_rate": 7.822497417398607e-06, "loss": 0.5461, "step": 705 }, { "epoch": 0.38110574342458403, "grad_norm": 2.3972861209417484, "learning_rate": 7.783693000799263e-06, "loss": 0.5415, "step": 710 }, { "epoch": 0.3837895866881374, "grad_norm": 2.385175750668056, "learning_rate": 7.744644066735335e-06, "loss": 0.529, "step": 715 }, { "epoch": 0.3864734299516908, "grad_norm": 2.2941982595733634, "learning_rate": 7.705354045235335e-06, "loss": 0.5263, "step": 720 }, { "epoch": 0.38915727321524424, "grad_norm": 2.4098039236931217, "learning_rate": 7.665826387504708e-06, "loss": 0.5367, "step": 725 }, { "epoch": 0.39184111647879766, "grad_norm": 2.369548787017956, "learning_rate": 7.626064565622684e-06, "loss": 0.5492, "step": 730 }, { "epoch": 0.394524959742351, "grad_norm": 2.485485577179457, "learning_rate": 7.586072072237291e-06, "loss": 0.549, "step": 735 }, { "epoch": 0.39720880300590444, "grad_norm": 2.3413134338829678, "learning_rate": 7.545852420258566e-06, "loss": 0.5416, "step": 740 }, { "epoch": 0.39989264626945786, "grad_norm": 2.4643129883436163, "learning_rate": 7.505409142549987e-06, "loss": 0.5317, "step": 745 }, { "epoch": 0.4025764895330113, "grad_norm": 2.4296220280963796, "learning_rate": 7.464745791618138e-06, "loss": 0.517, "step": 750 }, { "epoch": 0.4052603327965647, "grad_norm": 2.2974621401486988, "learning_rate": 7.423865939300674e-06, "loss": 0.5291, "step": 755 }, { "epoch": 0.40794417606011807, "grad_norm": 2.3986283475814685, "learning_rate": 7.382773176452561e-06, "loss": 0.5143, "step": 760 }, { "epoch": 0.4106280193236715, "grad_norm": 2.4550380944787893, "learning_rate": 7.341471112630667e-06, "loss": 0.5303, "step": 765 }, { "epoch": 0.4133118625872249, "grad_norm": 2.439286617193026, "learning_rate": 7.2999633757766956e-06, "loss": 0.5209, "step": 770 }, { "epoch": 0.41599570585077833, "grad_norm": 2.579280240608442, "learning_rate": 7.258253611898509e-06, "loss": 0.5181, "step": 775 }, { "epoch": 0.41867954911433175, "grad_norm": 2.4459646375459707, "learning_rate": 7.216345484749876e-06, "loss": 0.5285, "step": 780 }, { "epoch": 0.4213633923778851, "grad_norm": 2.31347148751011, "learning_rate": 7.174242675508636e-06, "loss": 0.5209, "step": 785 }, { "epoch": 0.42404723564143854, "grad_norm": 2.2544720712727306, "learning_rate": 7.131948882453361e-06, "loss": 0.5189, "step": 790 }, { "epoch": 0.42673107890499196, "grad_norm": 2.4273603418815353, "learning_rate": 7.089467820638491e-06, "loss": 0.5185, "step": 795 }, { "epoch": 0.4294149221685454, "grad_norm": 2.474461554762193, "learning_rate": 7.0468032215680116e-06, "loss": 0.5005, "step": 800 }, { "epoch": 0.43209876543209874, "grad_norm": 2.3040840560842515, "learning_rate": 7.003958832867681e-06, "loss": 0.5089, "step": 805 }, { "epoch": 0.43478260869565216, "grad_norm": 2.3521717336924923, "learning_rate": 6.960938417955841e-06, "loss": 0.4912, "step": 810 }, { "epoch": 0.4374664519592056, "grad_norm": 2.645750501936123, "learning_rate": 6.917745755712839e-06, "loss": 0.5103, "step": 815 }, { "epoch": 0.440150295222759, "grad_norm": 2.3864966496000775, "learning_rate": 6.874384640149101e-06, "loss": 0.5173, "step": 820 }, { "epoch": 0.4428341384863124, "grad_norm": 2.4243382348421023, "learning_rate": 6.830858880071859e-06, "loss": 0.5008, "step": 825 }, { "epoch": 0.4455179817498658, "grad_norm": 2.3826616991498994, "learning_rate": 6.7871722987505975e-06, "loss": 0.4975, "step": 830 }, { "epoch": 0.4482018250134192, "grad_norm": 2.350730267510358, "learning_rate": 6.743328733581211e-06, "loss": 0.4974, "step": 835 }, { "epoch": 0.45088566827697263, "grad_norm": 2.4759950761731533, "learning_rate": 6.6993320357489396e-06, "loss": 0.5109, "step": 840 }, { "epoch": 0.45356951154052605, "grad_norm": 2.435108148176811, "learning_rate": 6.6551860698900804e-06, "loss": 0.5109, "step": 845 }, { "epoch": 0.4562533548040794, "grad_norm": 2.328924887512505, "learning_rate": 6.610894713752513e-06, "loss": 0.511, "step": 850 }, { "epoch": 0.45893719806763283, "grad_norm": 2.7752731374751853, "learning_rate": 6.566461857855096e-06, "loss": 0.482, "step": 855 }, { "epoch": 0.46162104133118625, "grad_norm": 2.7298504650341933, "learning_rate": 6.52189140514591e-06, "loss": 0.4899, "step": 860 }, { "epoch": 0.4643048845947397, "grad_norm": 2.3730194932640716, "learning_rate": 6.477187270659444e-06, "loss": 0.4933, "step": 865 }, { "epoch": 0.4669887278582931, "grad_norm": 2.5257680480017943, "learning_rate": 6.432353381172686e-06, "loss": 0.5118, "step": 870 }, { "epoch": 0.46967257112184646, "grad_norm": 2.3277533281506684, "learning_rate": 6.387393674860205e-06, "loss": 0.4726, "step": 875 }, { "epoch": 0.4723564143853999, "grad_norm": 2.360810322256424, "learning_rate": 6.3423121009482226e-06, "loss": 0.4923, "step": 880 }, { "epoch": 0.4750402576489533, "grad_norm": 2.3485189902814594, "learning_rate": 6.297112619367721e-06, "loss": 0.4812, "step": 885 }, { "epoch": 0.4777241009125067, "grad_norm": 2.4376276616820047, "learning_rate": 6.2517992004066e-06, "loss": 0.486, "step": 890 }, { "epoch": 0.48040794417606014, "grad_norm": 2.3269791738701753, "learning_rate": 6.2063758243609275e-06, "loss": 0.5026, "step": 895 }, { "epoch": 0.4830917874396135, "grad_norm": 2.305172802716132, "learning_rate": 6.160846481185326e-06, "loss": 0.492, "step": 900 }, { "epoch": 0.4857756307031669, "grad_norm": 2.355738561421812, "learning_rate": 6.115215170142481e-06, "loss": 0.4864, "step": 905 }, { "epoch": 0.48845947396672035, "grad_norm": 2.2772567999964894, "learning_rate": 6.069485899451863e-06, "loss": 0.4957, "step": 910 }, { "epoch": 0.49114331723027377, "grad_norm": 2.293960156110535, "learning_rate": 6.023662685937643e-06, "loss": 0.4785, "step": 915 }, { "epoch": 0.49382716049382713, "grad_norm": 2.452682027740044, "learning_rate": 5.9777495546758556e-06, "loss": 0.4706, "step": 920 }, { "epoch": 0.49651100375738055, "grad_norm": 2.3356554581318307, "learning_rate": 5.9317505386408436e-06, "loss": 0.4879, "step": 925 }, { "epoch": 0.499194847020934, "grad_norm": 2.413325314490582, "learning_rate": 5.885669678350997e-06, "loss": 0.4836, "step": 930 }, { "epoch": 0.5018786902844874, "grad_norm": 2.34645866757674, "learning_rate": 5.839511021513853e-06, "loss": 0.4732, "step": 935 }, { "epoch": 0.5045625335480408, "grad_norm": 2.2963428361302904, "learning_rate": 5.793278622670527e-06, "loss": 0.4768, "step": 940 }, { "epoch": 0.5072463768115942, "grad_norm": 2.365796624292683, "learning_rate": 5.746976542839583e-06, "loss": 0.4723, "step": 945 }, { "epoch": 0.5099302200751477, "grad_norm": 2.2909468487010347, "learning_rate": 5.700608849160307e-06, "loss": 0.4632, "step": 950 }, { "epoch": 0.512614063338701, "grad_norm": 2.400437273534213, "learning_rate": 5.654179614535457e-06, "loss": 0.4558, "step": 955 }, { "epoch": 0.5152979066022544, "grad_norm": 2.366575335205731, "learning_rate": 5.607692917273499e-06, "loss": 0.4651, "step": 960 }, { "epoch": 0.5179817498658078, "grad_norm": 2.2766517969507554, "learning_rate": 5.561152840730371e-06, "loss": 0.4559, "step": 965 }, { "epoch": 0.5206655931293612, "grad_norm": 2.2683862531318733, "learning_rate": 5.514563472950812e-06, "loss": 0.4501, "step": 970 }, { "epoch": 0.5233494363929146, "grad_norm": 2.307175024358814, "learning_rate": 5.46792890630926e-06, "loss": 0.451, "step": 975 }, { "epoch": 0.5260332796564681, "grad_norm": 2.3931220819772174, "learning_rate": 5.421253237150389e-06, "loss": 0.4562, "step": 980 }, { "epoch": 0.5287171229200215, "grad_norm": 2.230895258923371, "learning_rate": 5.374540565429288e-06, "loss": 0.4703, "step": 985 }, { "epoch": 0.5314009661835749, "grad_norm": 2.3419568661003147, "learning_rate": 5.327794994351321e-06, "loss": 0.4641, "step": 990 }, { "epoch": 0.5340848094471283, "grad_norm": 2.304734852864055, "learning_rate": 5.281020630011703e-06, "loss": 0.463, "step": 995 }, { "epoch": 0.5367686527106817, "grad_norm": 2.2318721628819413, "learning_rate": 5.234221581034834e-06, "loss": 0.4541, "step": 1000 }, { "epoch": 0.5394524959742351, "grad_norm": 2.3906459933439077, "learning_rate": 5.187401958213391e-06, "loss": 0.4525, "step": 1005 }, { "epoch": 0.5421363392377885, "grad_norm": 2.467365672509074, "learning_rate": 5.140565874147236e-06, "loss": 0.4501, "step": 1010 }, { "epoch": 0.5448201825013419, "grad_norm": 2.277483626055024, "learning_rate": 5.093717442882185e-06, "loss": 0.4545, "step": 1015 }, { "epoch": 0.5475040257648953, "grad_norm": 2.3593150665128393, "learning_rate": 5.046860779548613e-06, "loss": 0.4483, "step": 1020 }, { "epoch": 0.5501878690284487, "grad_norm": 2.258246761530304, "learning_rate": 5e-06, "loss": 0.4546, "step": 1025 }, { "epoch": 0.5528717122920022, "grad_norm": 2.370134681916226, "learning_rate": 4.953139220451386e-06, "loss": 0.4515, "step": 1030 }, { "epoch": 0.5555555555555556, "grad_norm": 2.2408497142914263, "learning_rate": 4.906282557117817e-06, "loss": 0.4341, "step": 1035 }, { "epoch": 0.558239398819109, "grad_norm": 2.3069571005115286, "learning_rate": 4.859434125852764e-06, "loss": 0.443, "step": 1040 }, { "epoch": 0.5609232420826624, "grad_norm": 2.3320315085107963, "learning_rate": 4.812598041786611e-06, "loss": 0.4394, "step": 1045 }, { "epoch": 0.5636070853462157, "grad_norm": 2.3442024150109355, "learning_rate": 4.765778418965168e-06, "loss": 0.4457, "step": 1050 }, { "epoch": 0.5662909286097692, "grad_norm": 2.3358028069710355, "learning_rate": 4.718979369988299e-06, "loss": 0.4391, "step": 1055 }, { "epoch": 0.5689747718733226, "grad_norm": 2.5507352210470993, "learning_rate": 4.672205005648681e-06, "loss": 0.437, "step": 1060 }, { "epoch": 0.571658615136876, "grad_norm": 2.309839111983691, "learning_rate": 4.625459434570712e-06, "loss": 0.4412, "step": 1065 }, { "epoch": 0.5743424584004294, "grad_norm": 2.3271635616011768, "learning_rate": 4.578746762849612e-06, "loss": 0.4494, "step": 1070 }, { "epoch": 0.5770263016639828, "grad_norm": 2.3546579002361514, "learning_rate": 4.532071093690741e-06, "loss": 0.4379, "step": 1075 }, { "epoch": 0.5797101449275363, "grad_norm": 2.2413776268605665, "learning_rate": 4.485436527049189e-06, "loss": 0.432, "step": 1080 }, { "epoch": 0.5823939881910897, "grad_norm": 2.1798039451185613, "learning_rate": 4.438847159269631e-06, "loss": 0.4258, "step": 1085 }, { "epoch": 0.5850778314546431, "grad_norm": 2.3359688865498662, "learning_rate": 4.392307082726503e-06, "loss": 0.4359, "step": 1090 }, { "epoch": 0.5877616747181964, "grad_norm": 2.3364533232377998, "learning_rate": 4.345820385464543e-06, "loss": 0.4281, "step": 1095 }, { "epoch": 0.5904455179817498, "grad_norm": 2.3860711291519356, "learning_rate": 4.299391150839694e-06, "loss": 0.4364, "step": 1100 }, { "epoch": 0.5931293612453032, "grad_norm": 2.276752067399093, "learning_rate": 4.253023457160418e-06, "loss": 0.4186, "step": 1105 }, { "epoch": 0.5958132045088567, "grad_norm": 2.467553896688473, "learning_rate": 4.2067213773294745e-06, "loss": 0.4387, "step": 1110 }, { "epoch": 0.5984970477724101, "grad_norm": 2.3540003775384046, "learning_rate": 4.16048897848615e-06, "loss": 0.43, "step": 1115 }, { "epoch": 0.6011808910359635, "grad_norm": 2.505862126720908, "learning_rate": 4.114330321649004e-06, "loss": 0.4321, "step": 1120 }, { "epoch": 0.6038647342995169, "grad_norm": 2.4630371968354656, "learning_rate": 4.068249461359158e-06, "loss": 0.4297, "step": 1125 }, { "epoch": 0.6065485775630703, "grad_norm": 2.272836354134841, "learning_rate": 4.022250445324145e-06, "loss": 0.4268, "step": 1130 }, { "epoch": 0.6092324208266238, "grad_norm": 2.2886295946366975, "learning_rate": 3.976337314062358e-06, "loss": 0.4167, "step": 1135 }, { "epoch": 0.6119162640901772, "grad_norm": 2.2103585092808617, "learning_rate": 3.9305141005481385e-06, "loss": 0.4199, "step": 1140 }, { "epoch": 0.6146001073537305, "grad_norm": 2.2740765745796123, "learning_rate": 3.8847848298575205e-06, "loss": 0.4189, "step": 1145 }, { "epoch": 0.6172839506172839, "grad_norm": 2.258557673733666, "learning_rate": 3.839153518814677e-06, "loss": 0.4306, "step": 1150 }, { "epoch": 0.6199677938808373, "grad_norm": 2.2068268474418358, "learning_rate": 3.7936241756390746e-06, "loss": 0.4247, "step": 1155 }, { "epoch": 0.6226516371443908, "grad_norm": 2.194022472389834, "learning_rate": 3.748200799593402e-06, "loss": 0.4231, "step": 1160 }, { "epoch": 0.6253354804079442, "grad_norm": 2.326988084434494, "learning_rate": 3.7028873806322797e-06, "loss": 0.4238, "step": 1165 }, { "epoch": 0.6280193236714976, "grad_norm": 2.2517958835294296, "learning_rate": 3.6576878990517783e-06, "loss": 0.416, "step": 1170 }, { "epoch": 0.630703166935051, "grad_norm": 2.1808207196710883, "learning_rate": 3.6126063251397968e-06, "loss": 0.4287, "step": 1175 }, { "epoch": 0.6333870101986044, "grad_norm": 2.3042249504814047, "learning_rate": 3.567646618827315e-06, "loss": 0.4125, "step": 1180 }, { "epoch": 0.6360708534621579, "grad_norm": 2.3472786605740343, "learning_rate": 3.522812729340557e-06, "loss": 0.4206, "step": 1185 }, { "epoch": 0.6387546967257112, "grad_norm": 2.2475547544387866, "learning_rate": 3.4781085948540907e-06, "loss": 0.398, "step": 1190 }, { "epoch": 0.6414385399892646, "grad_norm": 2.287893454196299, "learning_rate": 3.4335381421449056e-06, "loss": 0.4078, "step": 1195 }, { "epoch": 0.644122383252818, "grad_norm": 2.3938598824979236, "learning_rate": 3.3891052862474884e-06, "loss": 0.4184, "step": 1200 }, { "epoch": 0.6468062265163714, "grad_norm": 2.284784413306213, "learning_rate": 3.3448139301099212e-06, "loss": 0.413, "step": 1205 }, { "epoch": 0.6494900697799249, "grad_norm": 2.313513606221783, "learning_rate": 3.3006679642510596e-06, "loss": 0.4222, "step": 1210 }, { "epoch": 0.6521739130434783, "grad_norm": 2.2811158566992407, "learning_rate": 3.2566712664187907e-06, "loss": 0.4103, "step": 1215 }, { "epoch": 0.6548577563070317, "grad_norm": 2.231261781303834, "learning_rate": 3.2128277012494046e-06, "loss": 0.4073, "step": 1220 }, { "epoch": 0.6575415995705851, "grad_norm": 2.377033426744753, "learning_rate": 3.169141119928142e-06, "loss": 0.4083, "step": 1225 }, { "epoch": 0.6602254428341385, "grad_norm": 2.2511272231711787, "learning_rate": 3.125615359850902e-06, "loss": 0.3908, "step": 1230 }, { "epoch": 0.6629092860976918, "grad_norm": 2.1422423919919233, "learning_rate": 3.082254244287163e-06, "loss": 0.3956, "step": 1235 }, { "epoch": 0.6655931293612453, "grad_norm": 2.1833809439258007, "learning_rate": 3.0390615820441605e-06, "loss": 0.4078, "step": 1240 }, { "epoch": 0.6682769726247987, "grad_norm": 2.0915894234273305, "learning_rate": 2.9960411671323215e-06, "loss": 0.415, "step": 1245 }, { "epoch": 0.6709608158883521, "grad_norm": 2.3267272756698767, "learning_rate": 2.9531967784319897e-06, "loss": 0.3998, "step": 1250 }, { "epoch": 0.6736446591519055, "grad_norm": 2.2454024145911147, "learning_rate": 2.9105321793615106e-06, "loss": 0.4139, "step": 1255 }, { "epoch": 0.6763285024154589, "grad_norm": 2.1672873136892337, "learning_rate": 2.8680511175466384e-06, "loss": 0.4012, "step": 1260 }, { "epoch": 0.6790123456790124, "grad_norm": 2.36164728633219, "learning_rate": 2.8257573244913637e-06, "loss": 0.4053, "step": 1265 }, { "epoch": 0.6816961889425658, "grad_norm": 2.198633451961816, "learning_rate": 2.783654515250126e-06, "loss": 0.3895, "step": 1270 }, { "epoch": 0.6843800322061192, "grad_norm": 2.1741967245818454, "learning_rate": 2.741746388101493e-06, "loss": 0.4037, "step": 1275 }, { "epoch": 0.6870638754696726, "grad_norm": 2.4661760766296754, "learning_rate": 2.700036624223308e-06, "loss": 0.4011, "step": 1280 }, { "epoch": 0.6897477187332259, "grad_norm": 2.283551766561198, "learning_rate": 2.6585288873693355e-06, "loss": 0.398, "step": 1285 }, { "epoch": 0.6924315619967794, "grad_norm": 2.2282092986087796, "learning_rate": 2.6172268235474396e-06, "loss": 0.3896, "step": 1290 }, { "epoch": 0.6951154052603328, "grad_norm": 2.190285384279946, "learning_rate": 2.576134060699328e-06, "loss": 0.4081, "step": 1295 }, { "epoch": 0.6977992485238862, "grad_norm": 2.1692244547778405, "learning_rate": 2.5352542083818636e-06, "loss": 0.3887, "step": 1300 }, { "epoch": 0.7004830917874396, "grad_norm": 2.2586754461746126, "learning_rate": 2.494590857450016e-06, "loss": 0.3957, "step": 1305 }, { "epoch": 0.703166935050993, "grad_norm": 2.374656982408945, "learning_rate": 2.454147579741436e-06, "loss": 0.3874, "step": 1310 }, { "epoch": 0.7058507783145465, "grad_norm": 2.2261704008153536, "learning_rate": 2.4139279277627113e-06, "loss": 0.388, "step": 1315 }, { "epoch": 0.7085346215780999, "grad_norm": 2.2437976230745384, "learning_rate": 2.373935434377316e-06, "loss": 0.3905, "step": 1320 }, { "epoch": 0.7112184648416533, "grad_norm": 2.1589184736112075, "learning_rate": 2.3341736124952924e-06, "loss": 0.3928, "step": 1325 }, { "epoch": 0.7139023081052066, "grad_norm": 2.1883376186173638, "learning_rate": 2.294645954764666e-06, "loss": 0.3937, "step": 1330 }, { "epoch": 0.71658615136876, "grad_norm": 2.115522768168307, "learning_rate": 2.2553559332646675e-06, "loss": 0.3738, "step": 1335 }, { "epoch": 0.7192699946323134, "grad_norm": 2.2554699265788014, "learning_rate": 2.216306999200739e-06, "loss": 0.3756, "step": 1340 }, { "epoch": 0.7219538378958669, "grad_norm": 2.1331294949741513, "learning_rate": 2.1775025826013953e-06, "loss": 0.3794, "step": 1345 }, { "epoch": 0.7246376811594203, "grad_norm": 2.2181208326555892, "learning_rate": 2.1389460920169105e-06, "loss": 0.3739, "step": 1350 }, { "epoch": 0.7273215244229737, "grad_norm": 2.3464498796911317, "learning_rate": 2.100640914219939e-06, "loss": 0.4009, "step": 1355 }, { "epoch": 0.7300053676865271, "grad_norm": 2.205656545431609, "learning_rate": 2.062590413908007e-06, "loss": 0.3926, "step": 1360 }, { "epoch": 0.7326892109500805, "grad_norm": 2.1357870746338414, "learning_rate": 2.0247979334079646e-06, "loss": 0.3877, "step": 1365 }, { "epoch": 0.735373054213634, "grad_norm": 2.1907334794002744, "learning_rate": 1.9872667923823996e-06, "loss": 0.38, "step": 1370 }, { "epoch": 0.7380568974771873, "grad_norm": 2.1251695806868596, "learning_rate": 1.9500002875380458e-06, "loss": 0.3933, "step": 1375 }, { "epoch": 0.7407407407407407, "grad_norm": 2.1564914485662734, "learning_rate": 1.9130016923361843e-06, "loss": 0.3933, "step": 1380 }, { "epoch": 0.7434245840042941, "grad_norm": 2.036260794536821, "learning_rate": 1.8762742567051318e-06, "loss": 0.3765, "step": 1385 }, { "epoch": 0.7461084272678475, "grad_norm": 2.116566265103448, "learning_rate": 1.8398212067547455e-06, "loss": 0.3709, "step": 1390 }, { "epoch": 0.748792270531401, "grad_norm": 2.22514017476847, "learning_rate": 1.8036457444930643e-06, "loss": 0.3789, "step": 1395 }, { "epoch": 0.7514761137949544, "grad_norm": 2.213733855156735, "learning_rate": 1.7677510475450244e-06, "loss": 0.3842, "step": 1400 }, { "epoch": 0.7541599570585078, "grad_norm": 2.181820066227329, "learning_rate": 1.7321402688733618e-06, "loss": 0.3806, "step": 1405 }, { "epoch": 0.7568438003220612, "grad_norm": 2.2050398353530203, "learning_rate": 1.6968165365016443e-06, "loss": 0.3823, "step": 1410 }, { "epoch": 0.7595276435856146, "grad_norm": 2.19530752654402, "learning_rate": 1.661782953239512e-06, "loss": 0.3793, "step": 1415 }, { "epoch": 0.7622114868491681, "grad_norm": 2.1495195721953024, "learning_rate": 1.6270425964101272e-06, "loss": 0.3741, "step": 1420 }, { "epoch": 0.7648953301127214, "grad_norm": 2.103554729221664, "learning_rate": 1.5925985175798741e-06, "loss": 0.3729, "step": 1425 }, { "epoch": 0.7675791733762748, "grad_norm": 2.076683083573831, "learning_rate": 1.5584537422902923e-06, "loss": 0.3801, "step": 1430 }, { "epoch": 0.7702630166398282, "grad_norm": 2.058902410005422, "learning_rate": 1.5246112697923389e-06, "loss": 0.3716, "step": 1435 }, { "epoch": 0.7729468599033816, "grad_norm": 2.12166477747948, "learning_rate": 1.4910740727829176e-06, "loss": 0.3736, "step": 1440 }, { "epoch": 0.775630703166935, "grad_norm": 2.0736640828083344, "learning_rate": 1.457845097143769e-06, "loss": 0.3656, "step": 1445 }, { "epoch": 0.7783145464304885, "grad_norm": 2.162464954805237, "learning_rate": 1.424927261682703e-06, "loss": 0.3645, "step": 1450 }, { "epoch": 0.7809983896940419, "grad_norm": 2.322539410509905, "learning_rate": 1.3923234578772177e-06, "loss": 0.3737, "step": 1455 }, { "epoch": 0.7836822329575953, "grad_norm": 2.0847406596927334, "learning_rate": 1.3600365496205059e-06, "loss": 0.367, "step": 1460 }, { "epoch": 0.7863660762211487, "grad_norm": 2.175126277242884, "learning_rate": 1.3280693729699018e-06, "loss": 0.3719, "step": 1465 }, { "epoch": 0.789049919484702, "grad_norm": 2.0902393466668983, "learning_rate": 1.2964247358977567e-06, "loss": 0.3657, "step": 1470 }, { "epoch": 0.7917337627482555, "grad_norm": 1.9974175235545193, "learning_rate": 1.265105418044793e-06, "loss": 0.3567, "step": 1475 }, { "epoch": 0.7944176060118089, "grad_norm": 2.3125749433062746, "learning_rate": 1.2341141704759418e-06, "loss": 0.3638, "step": 1480 }, { "epoch": 0.7971014492753623, "grad_norm": 2.08290293868451, "learning_rate": 1.2034537154386933e-06, "loss": 0.3785, "step": 1485 }, { "epoch": 0.7997852925389157, "grad_norm": 2.0481414392713626, "learning_rate": 1.173126746123972e-06, "loss": 0.3665, "step": 1490 }, { "epoch": 0.8024691358024691, "grad_norm": 1.9820157935875906, "learning_rate": 1.1431359264295717e-06, "loss": 0.3613, "step": 1495 }, { "epoch": 0.8051529790660226, "grad_norm": 2.2394169396929793, "learning_rate": 1.113483890726162e-06, "loss": 0.3679, "step": 1500 }, { "epoch": 0.807836822329576, "grad_norm": 2.2229175878011516, "learning_rate": 1.084173243625884e-06, "loss": 0.3515, "step": 1505 }, { "epoch": 0.8105206655931294, "grad_norm": 2.1249532345306976, "learning_rate": 1.0552065597535671e-06, "loss": 0.3541, "step": 1510 }, { "epoch": 0.8132045088566827, "grad_norm": 2.151379889387235, "learning_rate": 1.0265863835205709e-06, "loss": 0.3565, "step": 1515 }, { "epoch": 0.8158883521202361, "grad_norm": 2.247568453760684, "learning_rate": 9.983152289012926e-07, "loss": 0.3767, "step": 1520 }, { "epoch": 0.8185721953837896, "grad_norm": 2.030213334768943, "learning_rate": 9.70395579212336e-07, "loss": 0.3626, "step": 1525 }, { "epoch": 0.821256038647343, "grad_norm": 2.16307272105344, "learning_rate": 9.428298868943791e-07, "loss": 0.3661, "step": 1530 }, { "epoch": 0.8239398819108964, "grad_norm": 1.9353846707087516, "learning_rate": 9.15620573296756e-07, "loss": 0.3559, "step": 1535 }, { "epoch": 0.8266237251744498, "grad_norm": 2.4706388638021948, "learning_rate": 8.887700284647699e-07, "loss": 0.3502, "step": 1540 }, { "epoch": 0.8293075684380032, "grad_norm": 2.0964124856887505, "learning_rate": 8.622806109297432e-07, "loss": 0.3635, "step": 1545 }, { "epoch": 0.8319914117015567, "grad_norm": 2.1655642607273213, "learning_rate": 8.361546475018589e-07, "loss": 0.3524, "step": 1550 }, { "epoch": 0.8346752549651101, "grad_norm": 2.151020178624645, "learning_rate": 8.103944330657665e-07, "loss": 0.3631, "step": 1555 }, { "epoch": 0.8373590982286635, "grad_norm": 2.2274203854683643, "learning_rate": 7.850022303790033e-07, "loss": 0.3536, "step": 1560 }, { "epoch": 0.8400429414922168, "grad_norm": 2.0005675417169084, "learning_rate": 7.599802698732356e-07, "loss": 0.3504, "step": 1565 }, { "epoch": 0.8427267847557702, "grad_norm": 2.048544707751455, "learning_rate": 7.353307494583445e-07, "loss": 0.3688, "step": 1570 }, { "epoch": 0.8454106280193237, "grad_norm": 2.286454488879537, "learning_rate": 7.1105583432935e-07, "loss": 0.3563, "step": 1575 }, { "epoch": 0.8480944712828771, "grad_norm": 2.1209732067930878, "learning_rate": 6.871576567762373e-07, "loss": 0.3481, "step": 1580 }, { "epoch": 0.8507783145464305, "grad_norm": 2.0479042834863113, "learning_rate": 6.63638315996647e-07, "loss": 0.3746, "step": 1585 }, { "epoch": 0.8534621578099839, "grad_norm": 2.0564571087729733, "learning_rate": 6.404998779114912e-07, "loss": 0.3599, "step": 1590 }, { "epoch": 0.8561460010735373, "grad_norm": 2.110264353818972, "learning_rate": 6.177443749834743e-07, "loss": 0.3498, "step": 1595 }, { "epoch": 0.8588298443370908, "grad_norm": 1.958321769357571, "learning_rate": 5.953738060385761e-07, "loss": 0.3497, "step": 1600 }, { "epoch": 0.8615136876006442, "grad_norm": 2.1502748066197843, "learning_rate": 5.733901360904648e-07, "loss": 0.3571, "step": 1605 }, { "epoch": 0.8641975308641975, "grad_norm": 2.3497614671533262, "learning_rate": 5.517952961678997e-07, "loss": 0.348, "step": 1610 }, { "epoch": 0.8668813741277509, "grad_norm": 2.035748778996207, "learning_rate": 5.305911831451044e-07, "loss": 0.3471, "step": 1615 }, { "epoch": 0.8695652173913043, "grad_norm": 2.056520258073967, "learning_rate": 5.097796595751564e-07, "loss": 0.3645, "step": 1620 }, { "epoch": 0.8722490606548577, "grad_norm": 1.9264861733728513, "learning_rate": 4.89362553526368e-07, "loss": 0.3416, "step": 1625 }, { "epoch": 0.8749329039184112, "grad_norm": 1.983591179837642, "learning_rate": 4.6934165842172476e-07, "loss": 0.3526, "step": 1630 }, { "epoch": 0.8776167471819646, "grad_norm": 2.3439353018231053, "learning_rate": 4.4971873288134237e-07, "loss": 0.3545, "step": 1635 }, { "epoch": 0.880300590445518, "grad_norm": 2.0168435139254774, "learning_rate": 4.304955005679962e-07, "loss": 0.3585, "step": 1640 }, { "epoch": 0.8829844337090714, "grad_norm": 2.0767665979805945, "learning_rate": 4.1167365003571047e-07, "loss": 0.362, "step": 1645 }, { "epoch": 0.8856682769726248, "grad_norm": 2.2587982125889914, "learning_rate": 3.9325483458144684e-07, "loss": 0.3588, "step": 1650 }, { "epoch": 0.8883521202361782, "grad_norm": 2.0212128576246022, "learning_rate": 3.752406720998691e-07, "loss": 0.3501, "step": 1655 }, { "epoch": 0.8910359634997316, "grad_norm": 2.174607134671128, "learning_rate": 3.5763274494123424e-07, "loss": 0.3504, "step": 1660 }, { "epoch": 0.893719806763285, "grad_norm": 1.8892853467813568, "learning_rate": 3.404325997723995e-07, "loss": 0.348, "step": 1665 }, { "epoch": 0.8964036500268384, "grad_norm": 2.202688784379415, "learning_rate": 3.2364174744096587e-07, "loss": 0.3474, "step": 1670 }, { "epoch": 0.8990874932903918, "grad_norm": 1.9882966199629937, "learning_rate": 3.072616628425601e-07, "loss": 0.3488, "step": 1675 }, { "epoch": 0.9017713365539453, "grad_norm": 2.042351450731294, "learning_rate": 2.9129378479129e-07, "loss": 0.3521, "step": 1680 }, { "epoch": 0.9044551798174987, "grad_norm": 1.9810136810117025, "learning_rate": 2.7573951589335177e-07, "loss": 0.3576, "step": 1685 }, { "epoch": 0.9071390230810521, "grad_norm": 2.039125294256416, "learning_rate": 2.60600222423833e-07, "loss": 0.3595, "step": 1690 }, { "epoch": 0.9098228663446055, "grad_norm": 2.1305767673918568, "learning_rate": 2.45877234206694e-07, "loss": 0.3506, "step": 1695 }, { "epoch": 0.9125067096081588, "grad_norm": 1.999762682379838, "learning_rate": 2.3157184449796365e-07, "loss": 0.3451, "step": 1700 }, { "epoch": 0.9151905528717122, "grad_norm": 2.4121285473633343, "learning_rate": 2.1768530987213267e-07, "loss": 0.3561, "step": 1705 }, { "epoch": 0.9178743961352657, "grad_norm": 2.1045057194711383, "learning_rate": 2.0421885011178532e-07, "loss": 0.3633, "step": 1710 }, { "epoch": 0.9205582393988191, "grad_norm": 2.036353438280661, "learning_rate": 1.911736481004489e-07, "loss": 0.3439, "step": 1715 }, { "epoch": 0.9232420826623725, "grad_norm": 2.0085164573021834, "learning_rate": 1.7855084971869385e-07, "loss": 0.3522, "step": 1720 }, { "epoch": 0.9259259259259259, "grad_norm": 1.9703347585874995, "learning_rate": 1.663515637434765e-07, "loss": 0.3491, "step": 1725 }, { "epoch": 0.9286097691894794, "grad_norm": 1.9548157965432644, "learning_rate": 1.5457686175074816e-07, "loss": 0.3485, "step": 1730 }, { "epoch": 0.9312936124530328, "grad_norm": 2.0143091147389574, "learning_rate": 1.432277780213298e-07, "loss": 0.3438, "step": 1735 }, { "epoch": 0.9339774557165862, "grad_norm": 1.9390821452634188, "learning_rate": 1.3230530945005704e-07, "loss": 0.3482, "step": 1740 }, { "epoch": 0.9366612989801396, "grad_norm": 1.9503085883819737, "learning_rate": 1.2181041545821727e-07, "loss": 0.3584, "step": 1745 }, { "epoch": 0.9393451422436929, "grad_norm": 2.1428772506615372, "learning_rate": 1.1174401790927325e-07, "loss": 0.3509, "step": 1750 }, { "epoch": 0.9420289855072463, "grad_norm": 2.058814075788709, "learning_rate": 1.0210700102788796e-07, "loss": 0.3483, "step": 1755 }, { "epoch": 0.9447128287707998, "grad_norm": 2.0643232309660924, "learning_rate": 9.290021132225546e-08, "loss": 0.3514, "step": 1760 }, { "epoch": 0.9473966720343532, "grad_norm": 1.957473416803994, "learning_rate": 8.412445750974385e-08, "loss": 0.3461, "step": 1765 }, { "epoch": 0.9500805152979066, "grad_norm": 2.1168590825637343, "learning_rate": 7.578051044585644e-08, "loss": 0.3501, "step": 1770 }, { "epoch": 0.95276435856146, "grad_norm": 2.052308145807329, "learning_rate": 6.786910305652373e-08, "loss": 0.3485, "step": 1775 }, { "epoch": 0.9554482018250134, "grad_norm": 2.255753145623415, "learning_rate": 6.0390930273721e-08, "loss": 0.3476, "step": 1780 }, { "epoch": 0.9581320450885669, "grad_norm": 2.062015912171957, "learning_rate": 5.334664897442721e-08, "loss": 0.3478, "step": 1785 }, { "epoch": 0.9608158883521203, "grad_norm": 2.08850888814244, "learning_rate": 4.673687792292436e-08, "loss": 0.331, "step": 1790 }, { "epoch": 0.9634997316156736, "grad_norm": 1.958352874050667, "learning_rate": 4.0562197716448316e-08, "loss": 0.346, "step": 1795 }, { "epoch": 0.966183574879227, "grad_norm": 2.199826624458542, "learning_rate": 3.4823150734186184e-08, "loss": 0.3513, "step": 1800 }, { "epoch": 0.9688674181427804, "grad_norm": 1.9676144059006588, "learning_rate": 2.9520241089636692e-08, "loss": 0.3408, "step": 1805 }, { "epoch": 0.9715512614063339, "grad_norm": 2.0588816398308203, "learning_rate": 2.4653934586328365e-08, "loss": 0.3476, "step": 1810 }, { "epoch": 0.9742351046698873, "grad_norm": 2.0271208836113956, "learning_rate": 2.022465867690282e-08, "loss": 0.342, "step": 1815 }, { "epoch": 0.9769189479334407, "grad_norm": 2.069016814300102, "learning_rate": 1.6232802425568683e-08, "loss": 0.3486, "step": 1820 }, { "epoch": 0.9796027911969941, "grad_norm": 2.094116862857401, "learning_rate": 1.2678716473927821e-08, "loss": 0.3502, "step": 1825 }, { "epoch": 0.9822866344605475, "grad_norm": 2.11652859366789, "learning_rate": 9.562713010171088e-09, "loss": 0.3559, "step": 1830 }, { "epoch": 0.984970477724101, "grad_norm": 1.9636086634173566, "learning_rate": 6.885065741661367e-09, "loss": 0.3462, "step": 1835 }, { "epoch": 0.9876543209876543, "grad_norm": 2.0953962053297115, "learning_rate": 4.646009870885593e-09, "loss": 0.3658, "step": 1840 }, { "epoch": 0.9903381642512077, "grad_norm": 1.980946754920061, "learning_rate": 2.845742074801261e-09, "loss": 0.3472, "step": 1845 }, { "epoch": 0.9930220075147611, "grad_norm": 2.081291822609216, "learning_rate": 1.484420487553595e-09, "loss": 0.3509, "step": 1850 }, { "epoch": 0.9957058507783145, "grad_norm": 1.962894597303225, "learning_rate": 5.621646865899832e-10, "loss": 0.339, "step": 1855 }, { "epoch": 0.998389694041868, "grad_norm": 2.014333652313711, "learning_rate": 7.905568215504921e-11, "loss": 0.3415, "step": 1860 }, { "epoch": 1.0, "eval_runtime": 3.3909, "eval_samples_per_second": 2.949, "eval_steps_per_second": 0.885, "step": 1863 }, { "epoch": 1.0, "step": 1863, "total_flos": 195037149265920.0, "train_loss": 0.5120102114659513, "train_runtime": 16685.4185, "train_samples_per_second": 1.786, "train_steps_per_second": 0.112 } ], "logging_steps": 5, "max_steps": 1863, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 195037149265920.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }