{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1862, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005370569280343716, "grad_norm": 24.25113947879833, "learning_rate": 5.3475935828877005e-08, "loss": 1.3237, "step": 1 }, { "epoch": 0.0026852846401718583, "grad_norm": 23.161748165504072, "learning_rate": 2.6737967914438503e-07, "loss": 1.3357, "step": 5 }, { "epoch": 0.0053705692803437165, "grad_norm": 15.788644713919888, "learning_rate": 5.347593582887701e-07, "loss": 1.2928, "step": 10 }, { "epoch": 0.008055853920515575, "grad_norm": 12.065360956658548, "learning_rate": 8.021390374331551e-07, "loss": 1.1734, "step": 15 }, { "epoch": 0.010741138560687433, "grad_norm": 8.451481103732192, "learning_rate": 1.0695187165775401e-06, "loss": 1.053, "step": 20 }, { "epoch": 0.01342642320085929, "grad_norm": 3.607181792793628, "learning_rate": 1.3368983957219254e-06, "loss": 0.9479, "step": 25 }, { "epoch": 0.01611170784103115, "grad_norm": 3.4122039231622128, "learning_rate": 1.6042780748663103e-06, "loss": 0.9164, "step": 30 }, { "epoch": 0.018796992481203006, "grad_norm": 2.9894854055400732, "learning_rate": 1.8716577540106954e-06, "loss": 0.8869, "step": 35 }, { "epoch": 0.021482277121374866, "grad_norm": 3.052529317760186, "learning_rate": 2.1390374331550802e-06, "loss": 0.8571, "step": 40 }, { "epoch": 0.024167561761546726, "grad_norm": 2.9434989562495484, "learning_rate": 2.4064171122994653e-06, "loss": 0.857, "step": 45 }, { "epoch": 0.02685284640171858, "grad_norm": 3.0139599082135424, "learning_rate": 2.673796791443851e-06, "loss": 0.8329, "step": 50 }, { "epoch": 0.02953813104189044, "grad_norm": 2.8752390849195306, "learning_rate": 2.9411764705882355e-06, "loss": 0.8183, "step": 55 }, { "epoch": 0.0322234156820623, "grad_norm": 2.9815477478474164, "learning_rate": 3.2085561497326205e-06, "loss": 0.8154, "step": 60 }, { "epoch": 0.03490870032223416, "grad_norm": 3.1961157011348433, "learning_rate": 3.4759358288770056e-06, "loss": 0.8127, "step": 65 }, { "epoch": 0.03759398496240601, "grad_norm": 3.011408828479708, "learning_rate": 3.7433155080213907e-06, "loss": 0.7876, "step": 70 }, { "epoch": 0.040279269602577876, "grad_norm": 3.074730944639507, "learning_rate": 4.010695187165775e-06, "loss": 0.7812, "step": 75 }, { "epoch": 0.04296455424274973, "grad_norm": 3.0954880610087416, "learning_rate": 4.2780748663101604e-06, "loss": 0.7938, "step": 80 }, { "epoch": 0.04564983888292159, "grad_norm": 3.103351806444735, "learning_rate": 4.5454545454545455e-06, "loss": 0.7783, "step": 85 }, { "epoch": 0.04833512352309345, "grad_norm": 3.1872294877792693, "learning_rate": 4.812834224598931e-06, "loss": 0.7573, "step": 90 }, { "epoch": 0.05102040816326531, "grad_norm": 3.1638880990567455, "learning_rate": 5.0802139037433165e-06, "loss": 0.7558, "step": 95 }, { "epoch": 0.05370569280343716, "grad_norm": 3.0115638804221754, "learning_rate": 5.347593582887702e-06, "loss": 0.7537, "step": 100 }, { "epoch": 0.05639097744360902, "grad_norm": 3.2941594696139145, "learning_rate": 5.614973262032086e-06, "loss": 0.7515, "step": 105 }, { "epoch": 0.05907626208378088, "grad_norm": 3.3155309676050013, "learning_rate": 5.882352941176471e-06, "loss": 0.7397, "step": 110 }, { "epoch": 0.06176154672395274, "grad_norm": 3.162740571135442, "learning_rate": 6.149732620320856e-06, "loss": 0.7296, "step": 115 }, { "epoch": 0.0644468313641246, "grad_norm": 3.0840588519609016, "learning_rate": 6.417112299465241e-06, "loss": 0.7336, "step": 120 }, { "epoch": 0.06713211600429646, "grad_norm": 3.150117025536966, "learning_rate": 6.684491978609626e-06, "loss": 0.7382, "step": 125 }, { "epoch": 0.06981740064446831, "grad_norm": 2.9252296896598278, "learning_rate": 6.951871657754011e-06, "loss": 0.7211, "step": 130 }, { "epoch": 0.07250268528464017, "grad_norm": 3.0320480967430092, "learning_rate": 7.219251336898396e-06, "loss": 0.73, "step": 135 }, { "epoch": 0.07518796992481203, "grad_norm": 2.874198329021165, "learning_rate": 7.486631016042781e-06, "loss": 0.7434, "step": 140 }, { "epoch": 0.07787325456498388, "grad_norm": 2.9173140627663656, "learning_rate": 7.754010695187166e-06, "loss": 0.7353, "step": 145 }, { "epoch": 0.08055853920515575, "grad_norm": 2.9848439720434294, "learning_rate": 8.02139037433155e-06, "loss": 0.73, "step": 150 }, { "epoch": 0.08324382384532761, "grad_norm": 2.87264895278571, "learning_rate": 8.288770053475937e-06, "loss": 0.7264, "step": 155 }, { "epoch": 0.08592910848549946, "grad_norm": 2.864090437505294, "learning_rate": 8.556149732620321e-06, "loss": 0.716, "step": 160 }, { "epoch": 0.08861439312567132, "grad_norm": 2.9211346467401826, "learning_rate": 8.823529411764707e-06, "loss": 0.7213, "step": 165 }, { "epoch": 0.09129967776584318, "grad_norm": 2.812817629694785, "learning_rate": 9.090909090909091e-06, "loss": 0.7239, "step": 170 }, { "epoch": 0.09398496240601503, "grad_norm": 3.0966947636468323, "learning_rate": 9.358288770053477e-06, "loss": 0.7252, "step": 175 }, { "epoch": 0.0966702470461869, "grad_norm": 2.8482566526889066, "learning_rate": 9.625668449197861e-06, "loss": 0.7111, "step": 180 }, { "epoch": 0.09935553168635876, "grad_norm": 3.103402165074239, "learning_rate": 9.893048128342247e-06, "loss": 0.709, "step": 185 }, { "epoch": 0.10204081632653061, "grad_norm": 2.833371746409837, "learning_rate": 9.999920849895074e-06, "loss": 0.7141, "step": 190 }, { "epoch": 0.10472610096670247, "grad_norm": 2.7601482578055685, "learning_rate": 9.99943716388422e-06, "loss": 0.7091, "step": 195 }, { "epoch": 0.10741138560687433, "grad_norm": 2.7694618688472334, "learning_rate": 9.998513806628825e-06, "loss": 0.6892, "step": 200 }, { "epoch": 0.11009667024704618, "grad_norm": 2.7627170756712545, "learning_rate": 9.997150859332753e-06, "loss": 0.7057, "step": 205 }, { "epoch": 0.11278195488721804, "grad_norm": 2.641313671359486, "learning_rate": 9.995348441859243e-06, "loss": 0.6968, "step": 210 }, { "epoch": 0.11546723952738991, "grad_norm": 2.7210282435142163, "learning_rate": 9.993106712720367e-06, "loss": 0.7126, "step": 215 }, { "epoch": 0.11815252416756176, "grad_norm": 2.6468526042665563, "learning_rate": 9.990425869063085e-06, "loss": 0.7133, "step": 220 }, { "epoch": 0.12083780880773362, "grad_norm": 2.669248971535401, "learning_rate": 9.987306146651908e-06, "loss": 0.6862, "step": 225 }, { "epoch": 0.12352309344790548, "grad_norm": 2.614929201255673, "learning_rate": 9.983747819848168e-06, "loss": 0.6822, "step": 230 }, { "epoch": 0.12620837808807733, "grad_norm": 2.752612192498847, "learning_rate": 9.97975120158589e-06, "loss": 0.7086, "step": 235 }, { "epoch": 0.1288936627282492, "grad_norm": 2.779012267697376, "learning_rate": 9.975316643344257e-06, "loss": 0.7081, "step": 240 }, { "epoch": 0.13157894736842105, "grad_norm": 2.5890743255074278, "learning_rate": 9.970444535116721e-06, "loss": 0.6914, "step": 245 }, { "epoch": 0.13426423200859292, "grad_norm": 2.6285297060534334, "learning_rate": 9.965135305376694e-06, "loss": 0.681, "step": 250 }, { "epoch": 0.13694951664876476, "grad_norm": 2.5527710360428038, "learning_rate": 9.959389421039863e-06, "loss": 0.6912, "step": 255 }, { "epoch": 0.13963480128893663, "grad_norm": 2.665201173590149, "learning_rate": 9.95320738742313e-06, "loss": 0.6911, "step": 260 }, { "epoch": 0.1423200859291085, "grad_norm": 2.57466357634417, "learning_rate": 9.946589748200185e-06, "loss": 0.7051, "step": 265 }, { "epoch": 0.14500537056928034, "grad_norm": 2.512739592787712, "learning_rate": 9.939537085353668e-06, "loss": 0.6789, "step": 270 }, { "epoch": 0.1476906552094522, "grad_norm": 2.5488133338759544, "learning_rate": 9.932050019124011e-06, "loss": 0.6722, "step": 275 }, { "epoch": 0.15037593984962405, "grad_norm": 2.563447287239947, "learning_rate": 9.924129207954877e-06, "loss": 0.68, "step": 280 }, { "epoch": 0.15306122448979592, "grad_norm": 2.6455202812435066, "learning_rate": 9.915775348435266e-06, "loss": 0.6829, "step": 285 }, { "epoch": 0.15574650912996776, "grad_norm": 2.607428689084183, "learning_rate": 9.906989175238232e-06, "loss": 0.6734, "step": 290 }, { "epoch": 0.15843179377013963, "grad_norm": 2.632494678548499, "learning_rate": 9.8977714610563e-06, "loss": 0.6654, "step": 295 }, { "epoch": 0.1611170784103115, "grad_norm": 2.5679386221927163, "learning_rate": 9.888123016533496e-06, "loss": 0.6464, "step": 300 }, { "epoch": 0.16380236305048335, "grad_norm": 2.4455235169022123, "learning_rate": 9.878044690194055e-06, "loss": 0.6808, "step": 305 }, { "epoch": 0.16648764769065522, "grad_norm": 2.6134103392173254, "learning_rate": 9.86753736836781e-06, "loss": 0.6689, "step": 310 }, { "epoch": 0.16917293233082706, "grad_norm": 2.553706613546006, "learning_rate": 9.856601975112227e-06, "loss": 0.6588, "step": 315 }, { "epoch": 0.17185821697099893, "grad_norm": 2.5066521118011407, "learning_rate": 9.84523947213116e-06, "loss": 0.6663, "step": 320 }, { "epoch": 0.17454350161117077, "grad_norm": 2.337716810935506, "learning_rate": 9.833450858690257e-06, "loss": 0.6571, "step": 325 }, { "epoch": 0.17722878625134264, "grad_norm": 2.568589396910675, "learning_rate": 9.821237171529088e-06, "loss": 0.6569, "step": 330 }, { "epoch": 0.1799140708915145, "grad_norm": 2.385921872954393, "learning_rate": 9.808599484769971e-06, "loss": 0.656, "step": 335 }, { "epoch": 0.18259935553168635, "grad_norm": 2.4819007537288362, "learning_rate": 9.79553890982351e-06, "loss": 0.6609, "step": 340 }, { "epoch": 0.18528464017185822, "grad_norm": 2.437061379076581, "learning_rate": 9.782056595290848e-06, "loss": 0.6455, "step": 345 }, { "epoch": 0.18796992481203006, "grad_norm": 2.564231295853269, "learning_rate": 9.768153726862652e-06, "loss": 0.6612, "step": 350 }, { "epoch": 0.19065520945220193, "grad_norm": 2.4893325625782583, "learning_rate": 9.753831527214854e-06, "loss": 0.662, "step": 355 }, { "epoch": 0.1933404940923738, "grad_norm": 2.4552866529124757, "learning_rate": 9.739091255901105e-06, "loss": 0.6486, "step": 360 }, { "epoch": 0.19602577873254565, "grad_norm": 2.5401346090028154, "learning_rate": 9.723934209242015e-06, "loss": 0.6471, "step": 365 }, { "epoch": 0.19871106337271752, "grad_norm": 2.5620972387781253, "learning_rate": 9.708361720211146e-06, "loss": 0.6419, "step": 370 }, { "epoch": 0.20139634801288936, "grad_norm": 2.4951612644213554, "learning_rate": 9.692375158317787e-06, "loss": 0.6492, "step": 375 }, { "epoch": 0.20408163265306123, "grad_norm": 2.4669992078317917, "learning_rate": 9.675975929486512e-06, "loss": 0.6546, "step": 380 }, { "epoch": 0.20676691729323307, "grad_norm": 2.603925161419725, "learning_rate": 9.659165475933537e-06, "loss": 0.6433, "step": 385 }, { "epoch": 0.20945220193340494, "grad_norm": 2.358390538888436, "learning_rate": 9.641945276039885e-06, "loss": 0.6436, "step": 390 }, { "epoch": 0.2121374865735768, "grad_norm": 2.4363415566836184, "learning_rate": 9.624316844221376e-06, "loss": 0.626, "step": 395 }, { "epoch": 0.21482277121374865, "grad_norm": 2.282557445492374, "learning_rate": 9.606281730795435e-06, "loss": 0.6267, "step": 400 }, { "epoch": 0.21750805585392052, "grad_norm": 2.3912481386253654, "learning_rate": 9.587841521844755e-06, "loss": 0.6451, "step": 405 }, { "epoch": 0.22019334049409237, "grad_norm": 2.468086968145363, "learning_rate": 9.568997839077812e-06, "loss": 0.6275, "step": 410 }, { "epoch": 0.22287862513426424, "grad_norm": 2.777359054522718, "learning_rate": 9.549752339686243e-06, "loss": 0.6487, "step": 415 }, { "epoch": 0.22556390977443608, "grad_norm": 2.435355179570479, "learning_rate": 9.530106716199103e-06, "loss": 0.6467, "step": 420 }, { "epoch": 0.22824919441460795, "grad_norm": 2.383529479537672, "learning_rate": 9.510062696334024e-06, "loss": 0.6345, "step": 425 }, { "epoch": 0.23093447905477982, "grad_norm": 2.4092098189126734, "learning_rate": 9.489622042845266e-06, "loss": 0.6239, "step": 430 }, { "epoch": 0.23361976369495166, "grad_norm": 2.426365302575787, "learning_rate": 9.468786553368694e-06, "loss": 0.6238, "step": 435 }, { "epoch": 0.23630504833512353, "grad_norm": 2.5087002358611574, "learning_rate": 9.447558060263693e-06, "loss": 0.6237, "step": 440 }, { "epoch": 0.23899033297529537, "grad_norm": 2.387385697008228, "learning_rate": 9.42593843045201e-06, "loss": 0.622, "step": 445 }, { "epoch": 0.24167561761546724, "grad_norm": 2.326708486574728, "learning_rate": 9.403929565253582e-06, "loss": 0.6306, "step": 450 }, { "epoch": 0.24436090225563908, "grad_norm": 2.369288401258165, "learning_rate": 9.381533400219319e-06, "loss": 0.6073, "step": 455 }, { "epoch": 0.24704618689581095, "grad_norm": 2.383046130914992, "learning_rate": 9.358751904960885e-06, "loss": 0.6205, "step": 460 }, { "epoch": 0.24973147153598282, "grad_norm": 2.414995815331301, "learning_rate": 9.335587082977484e-06, "loss": 0.6106, "step": 465 }, { "epoch": 0.25241675617615467, "grad_norm": 2.768675173604855, "learning_rate": 9.312040971479663e-06, "loss": 0.6272, "step": 470 }, { "epoch": 0.25510204081632654, "grad_norm": 2.2921439710822185, "learning_rate": 9.288115641210144e-06, "loss": 0.6113, "step": 475 }, { "epoch": 0.2577873254564984, "grad_norm": 2.3081671484334807, "learning_rate": 9.26381319626173e-06, "loss": 0.6102, "step": 480 }, { "epoch": 0.2604726100966702, "grad_norm": 2.5833114870823355, "learning_rate": 9.239135773892249e-06, "loss": 0.6042, "step": 485 }, { "epoch": 0.2631578947368421, "grad_norm": 2.3993711180589425, "learning_rate": 9.214085544336597e-06, "loss": 0.6043, "step": 490 }, { "epoch": 0.26584317937701396, "grad_norm": 2.3928350581872073, "learning_rate": 9.188664710615886e-06, "loss": 0.6072, "step": 495 }, { "epoch": 0.26852846401718583, "grad_norm": 2.291178931562558, "learning_rate": 9.162875508343691e-06, "loss": 0.607, "step": 500 }, { "epoch": 0.2712137486573577, "grad_norm": 2.302429905502462, "learning_rate": 9.136720205529446e-06, "loss": 0.6212, "step": 505 }, { "epoch": 0.2738990332975295, "grad_norm": 2.4002220088345227, "learning_rate": 9.110201102378991e-06, "loss": 0.6022, "step": 510 }, { "epoch": 0.2765843179377014, "grad_norm": 2.345306335150251, "learning_rate": 9.083320531092268e-06, "loss": 0.5849, "step": 515 }, { "epoch": 0.27926960257787325, "grad_norm": 2.361854410468674, "learning_rate": 9.056080855658233e-06, "loss": 0.5941, "step": 520 }, { "epoch": 0.2819548872180451, "grad_norm": 2.329088369479831, "learning_rate": 9.02848447164695e-06, "loss": 0.592, "step": 525 }, { "epoch": 0.284640171858217, "grad_norm": 2.9145104665950834, "learning_rate": 9.00053380599891e-06, "loss": 0.6079, "step": 530 }, { "epoch": 0.2873254564983888, "grad_norm": 2.30854865495231, "learning_rate": 8.972231316811608e-06, "loss": 0.5902, "step": 535 }, { "epoch": 0.2900107411385607, "grad_norm": 2.710514687574968, "learning_rate": 8.943579493123354e-06, "loss": 0.6139, "step": 540 }, { "epoch": 0.29269602577873255, "grad_norm": 2.3749882685361907, "learning_rate": 8.914580854694389e-06, "loss": 0.5982, "step": 545 }, { "epoch": 0.2953813104189044, "grad_norm": 2.341531483158182, "learning_rate": 8.885237951785275e-06, "loss": 0.6009, "step": 550 }, { "epoch": 0.2980665950590763, "grad_norm": 2.31541797689058, "learning_rate": 8.855553364932628e-06, "loss": 0.5539, "step": 555 }, { "epoch": 0.3007518796992481, "grad_norm": 2.3459951500114773, "learning_rate": 8.82552970472216e-06, "loss": 0.5793, "step": 560 }, { "epoch": 0.30343716433942, "grad_norm": 2.305688250517311, "learning_rate": 8.795169611559108e-06, "loss": 0.6016, "step": 565 }, { "epoch": 0.30612244897959184, "grad_norm": 2.5187456404531936, "learning_rate": 8.764475755436011e-06, "loss": 0.5785, "step": 570 }, { "epoch": 0.3088077336197637, "grad_norm": 2.3186145964360336, "learning_rate": 8.733450835697914e-06, "loss": 0.5952, "step": 575 }, { "epoch": 0.31149301825993553, "grad_norm": 2.4852031283314675, "learning_rate": 8.702097580804962e-06, "loss": 0.5921, "step": 580 }, { "epoch": 0.3141783029001074, "grad_norm": 2.48247156500519, "learning_rate": 8.670418748092465e-06, "loss": 0.5824, "step": 585 }, { "epoch": 0.31686358754027927, "grad_norm": 2.4487511752763003, "learning_rate": 8.638417123528393e-06, "loss": 0.5766, "step": 590 }, { "epoch": 0.31954887218045114, "grad_norm": 2.5523301393566973, "learning_rate": 8.60609552146837e-06, "loss": 0.5778, "step": 595 }, { "epoch": 0.322234156820623, "grad_norm": 2.463880439656359, "learning_rate": 8.573456784408162e-06, "loss": 0.5876, "step": 600 }, { "epoch": 0.3249194414607948, "grad_norm": 2.279384394364597, "learning_rate": 8.540503782733718e-06, "loss": 0.5564, "step": 605 }, { "epoch": 0.3276047261009667, "grad_norm": 2.3581766823519703, "learning_rate": 8.507239414468707e-06, "loss": 0.5711, "step": 610 }, { "epoch": 0.33029001074113856, "grad_norm": 2.386244897526467, "learning_rate": 8.473666605019673e-06, "loss": 0.5606, "step": 615 }, { "epoch": 0.33297529538131043, "grad_norm": 2.6538204423039176, "learning_rate": 8.439788306918759e-06, "loss": 0.5679, "step": 620 }, { "epoch": 0.3356605800214823, "grad_norm": 2.3536598330429994, "learning_rate": 8.405607499564044e-06, "loss": 0.5686, "step": 625 }, { "epoch": 0.3383458646616541, "grad_norm": 2.5411210857238737, "learning_rate": 8.371127188957527e-06, "loss": 0.5568, "step": 630 }, { "epoch": 0.341031149301826, "grad_norm": 2.3248484069987447, "learning_rate": 8.336350407440766e-06, "loss": 0.5603, "step": 635 }, { "epoch": 0.34371643394199786, "grad_norm": 2.531937446280703, "learning_rate": 8.3012802134282e-06, "loss": 0.559, "step": 640 }, { "epoch": 0.3464017185821697, "grad_norm": 2.453303019061587, "learning_rate": 8.26591969113818e-06, "loss": 0.5515, "step": 645 }, { "epoch": 0.34908700322234154, "grad_norm": 2.69008655565826, "learning_rate": 8.230271950321733e-06, "loss": 0.5581, "step": 650 }, { "epoch": 0.3517722878625134, "grad_norm": 2.2858934099243546, "learning_rate": 8.194340125989068e-06, "loss": 0.5584, "step": 655 }, { "epoch": 0.3544575725026853, "grad_norm": 2.4227589614633307, "learning_rate": 8.158127378133886e-06, "loss": 0.5338, "step": 660 }, { "epoch": 0.35714285714285715, "grad_norm": 2.473273208390763, "learning_rate": 8.121636891455462e-06, "loss": 0.5488, "step": 665 }, { "epoch": 0.359828141783029, "grad_norm": 4.029648668242547, "learning_rate": 8.084871875078574e-06, "loss": 0.5558, "step": 670 }, { "epoch": 0.36251342642320084, "grad_norm": 2.3823297359151487, "learning_rate": 8.047835562271289e-06, "loss": 0.5347, "step": 675 }, { "epoch": 0.3651987110633727, "grad_norm": 2.3206951441879062, "learning_rate": 8.010531210160594e-06, "loss": 0.5474, "step": 680 }, { "epoch": 0.3678839957035446, "grad_norm": 2.401861048928935, "learning_rate": 7.972962099445979e-06, "loss": 0.5336, "step": 685 }, { "epoch": 0.37056928034371645, "grad_norm": 2.283419604263929, "learning_rate": 7.935131534110893e-06, "loss": 0.5423, "step": 690 }, { "epoch": 0.3732545649838883, "grad_norm": 2.4091957808848377, "learning_rate": 7.897042841132195e-06, "loss": 0.5512, "step": 695 }, { "epoch": 0.37593984962406013, "grad_norm": 2.360101346375749, "learning_rate": 7.858699370187558e-06, "loss": 0.5521, "step": 700 }, { "epoch": 0.378625134264232, "grad_norm": 2.578398145192331, "learning_rate": 7.820104493360883e-06, "loss": 0.5446, "step": 705 }, { "epoch": 0.38131041890440387, "grad_norm": 2.392308313238444, "learning_rate": 7.781261604845754e-06, "loss": 0.539, "step": 710 }, { "epoch": 0.38399570354457574, "grad_norm": 2.4396652511764434, "learning_rate": 7.742174120646929e-06, "loss": 0.5459, "step": 715 }, { "epoch": 0.3866809881847476, "grad_norm": 2.4045120660307138, "learning_rate": 7.70284547827992e-06, "loss": 0.5245, "step": 720 }, { "epoch": 0.3893662728249194, "grad_norm": 2.2765914991878358, "learning_rate": 7.663279136468696e-06, "loss": 0.5493, "step": 725 }, { "epoch": 0.3920515574650913, "grad_norm": 2.350607787315242, "learning_rate": 7.623478574841499e-06, "loss": 0.5274, "step": 730 }, { "epoch": 0.39473684210526316, "grad_norm": 2.4564288550698166, "learning_rate": 7.58344729362483e-06, "loss": 0.5272, "step": 735 }, { "epoch": 0.39742212674543503, "grad_norm": 2.308846635556029, "learning_rate": 7.5431888133356334e-06, "loss": 0.5256, "step": 740 }, { "epoch": 0.40010741138560685, "grad_norm": 2.3648049921250105, "learning_rate": 7.502706674471678e-06, "loss": 0.5374, "step": 745 }, { "epoch": 0.4027926960257787, "grad_norm": 2.372539412693635, "learning_rate": 7.462004437200195e-06, "loss": 0.5322, "step": 750 }, { "epoch": 0.4054779806659506, "grad_norm": 2.35495618473913, "learning_rate": 7.42108568104479e-06, "loss": 0.5278, "step": 755 }, { "epoch": 0.40816326530612246, "grad_norm": 2.432730442205152, "learning_rate": 7.379954004570628e-06, "loss": 0.543, "step": 760 }, { "epoch": 0.41084854994629433, "grad_norm": 2.383640686140904, "learning_rate": 7.338613025067977e-06, "loss": 0.5493, "step": 765 }, { "epoch": 0.41353383458646614, "grad_norm": 2.2937243918245307, "learning_rate": 7.2970663782340765e-06, "loss": 0.5159, "step": 770 }, { "epoch": 0.416219119226638, "grad_norm": 2.584638869408312, "learning_rate": 7.25531771785341e-06, "loss": 0.528, "step": 775 }, { "epoch": 0.4189044038668099, "grad_norm": 2.4008027863806363, "learning_rate": 7.2133707154763646e-06, "loss": 0.5264, "step": 780 }, { "epoch": 0.42158968850698175, "grad_norm": 2.388791471928522, "learning_rate": 7.17122906009635e-06, "loss": 0.5123, "step": 785 }, { "epoch": 0.4242749731471536, "grad_norm": 2.3442732809582774, "learning_rate": 7.128896457825364e-06, "loss": 0.5149, "step": 790 }, { "epoch": 0.42696025778732544, "grad_norm": 2.279111093706145, "learning_rate": 7.08637663156807e-06, "loss": 0.5168, "step": 795 }, { "epoch": 0.4296455424274973, "grad_norm": 2.4062295480857805, "learning_rate": 7.043673320694386e-06, "loss": 0.5015, "step": 800 }, { "epoch": 0.4323308270676692, "grad_norm": 2.5033445807132932, "learning_rate": 7.000790280710625e-06, "loss": 0.5221, "step": 805 }, { "epoch": 0.43501611170784105, "grad_norm": 2.3456722409693698, "learning_rate": 6.957731282929224e-06, "loss": 0.498, "step": 810 }, { "epoch": 0.4377013963480129, "grad_norm": 2.3434221234555936, "learning_rate": 6.914500114137082e-06, "loss": 0.4955, "step": 815 }, { "epoch": 0.44038668098818473, "grad_norm": 2.351670401180038, "learning_rate": 6.871100576262526e-06, "loss": 0.5041, "step": 820 }, { "epoch": 0.4430719656283566, "grad_norm": 2.357200356793434, "learning_rate": 6.827536486040964e-06, "loss": 0.5131, "step": 825 }, { "epoch": 0.44575725026852847, "grad_norm": 2.3716872327140948, "learning_rate": 6.783811674679216e-06, "loss": 0.5072, "step": 830 }, { "epoch": 0.44844253490870034, "grad_norm": 2.3837956868904753, "learning_rate": 6.7399299875185875e-06, "loss": 0.5072, "step": 835 }, { "epoch": 0.45112781954887216, "grad_norm": 2.468749709382942, "learning_rate": 6.695895283696691e-06, "loss": 0.4916, "step": 840 }, { "epoch": 0.453813104189044, "grad_norm": 2.2977664623966576, "learning_rate": 6.651711435808061e-06, "loss": 0.5073, "step": 845 }, { "epoch": 0.4564983888292159, "grad_norm": 2.3750347681190367, "learning_rate": 6.607382329563581e-06, "loss": 0.5042, "step": 850 }, { "epoch": 0.45918367346938777, "grad_norm": 2.3201817159617604, "learning_rate": 6.562911863448752e-06, "loss": 0.505, "step": 855 }, { "epoch": 0.46186895810955964, "grad_norm": 2.317046101118156, "learning_rate": 6.518303948380854e-06, "loss": 0.5027, "step": 860 }, { "epoch": 0.46455424274973145, "grad_norm": 2.4450948832382844, "learning_rate": 6.473562507364995e-06, "loss": 0.5057, "step": 865 }, { "epoch": 0.4672395273899033, "grad_norm": 2.342313602440348, "learning_rate": 6.428691475149107e-06, "loss": 0.4859, "step": 870 }, { "epoch": 0.4699248120300752, "grad_norm": 2.3462970754354084, "learning_rate": 6.383694797877915e-06, "loss": 0.4714, "step": 875 }, { "epoch": 0.47261009667024706, "grad_norm": 2.5885071330202627, "learning_rate": 6.338576432745891e-06, "loss": 0.4875, "step": 880 }, { "epoch": 0.47529538131041893, "grad_norm": 2.2979744167450358, "learning_rate": 6.293340347649234e-06, "loss": 0.4951, "step": 885 }, { "epoch": 0.47798066595059074, "grad_norm": 2.291237469268037, "learning_rate": 6.247990520836935e-06, "loss": 0.4883, "step": 890 }, { "epoch": 0.4806659505907626, "grad_norm": 2.3728016920526565, "learning_rate": 6.202530940560897e-06, "loss": 0.485, "step": 895 }, { "epoch": 0.4833512352309345, "grad_norm": 2.610281937328259, "learning_rate": 6.156965604725202e-06, "loss": 0.4882, "step": 900 }, { "epoch": 0.48603651987110635, "grad_norm": 2.3718642604920834, "learning_rate": 6.111298520534514e-06, "loss": 0.4866, "step": 905 }, { "epoch": 0.48872180451127817, "grad_norm": 2.3757882082854573, "learning_rate": 6.065533704141666e-06, "loss": 0.4798, "step": 910 }, { "epoch": 0.49140708915145004, "grad_norm": 2.3521649976871712, "learning_rate": 6.019675180294469e-06, "loss": 0.4876, "step": 915 }, { "epoch": 0.4940923737916219, "grad_norm": 2.263694366342218, "learning_rate": 5.973726981981756e-06, "loss": 0.4838, "step": 920 }, { "epoch": 0.4967776584317938, "grad_norm": 2.574827738131497, "learning_rate": 5.9276931500787045e-06, "loss": 0.4893, "step": 925 }, { "epoch": 0.49946294307196565, "grad_norm": 2.3280039732972355, "learning_rate": 5.8815777329914655e-06, "loss": 0.4748, "step": 930 }, { "epoch": 0.5021482277121375, "grad_norm": 2.472054452574987, "learning_rate": 5.83538478630113e-06, "loss": 0.4906, "step": 935 }, { "epoch": 0.5048335123523093, "grad_norm": 2.3804196285899186, "learning_rate": 5.789118372407061e-06, "loss": 0.4631, "step": 940 }, { "epoch": 0.5075187969924813, "grad_norm": 2.3558638927371742, "learning_rate": 5.7427825601696376e-06, "loss": 0.4691, "step": 945 }, { "epoch": 0.5102040816326531, "grad_norm": 2.359879850321753, "learning_rate": 5.696381424552411e-06, "loss": 0.4639, "step": 950 }, { "epoch": 0.5128893662728249, "grad_norm": 2.322787328071383, "learning_rate": 5.649919046263742e-06, "loss": 0.465, "step": 955 }, { "epoch": 0.5155746509129968, "grad_norm": 2.4521402907626646, "learning_rate": 5.6033995113979336e-06, "loss": 0.4623, "step": 960 }, { "epoch": 0.5182599355531686, "grad_norm": 2.2573376873830284, "learning_rate": 5.556826911075867e-06, "loss": 0.4642, "step": 965 }, { "epoch": 0.5209452201933404, "grad_norm": 2.398522707712972, "learning_rate": 5.510205341085224e-06, "loss": 0.4754, "step": 970 }, { "epoch": 0.5236305048335124, "grad_norm": 2.4170684561458757, "learning_rate": 5.463538901520278e-06, "loss": 0.4602, "step": 975 }, { "epoch": 0.5263157894736842, "grad_norm": 2.3207712466054096, "learning_rate": 5.416831696421325e-06, "loss": 0.464, "step": 980 }, { "epoch": 0.5290010741138561, "grad_norm": 2.4520936790108108, "learning_rate": 5.370087833413747e-06, "loss": 0.47, "step": 985 }, { "epoch": 0.5316863587540279, "grad_norm": 2.382760350655894, "learning_rate": 5.323311423346775e-06, "loss": 0.4744, "step": 990 }, { "epoch": 0.5343716433941997, "grad_norm": 2.392728462627693, "learning_rate": 5.2765065799319646e-06, "loss": 0.4539, "step": 995 }, { "epoch": 0.5370569280343717, "grad_norm": 2.317069450690583, "learning_rate": 5.229677419381417e-06, "loss": 0.4724, "step": 1000 }, { "epoch": 0.5397422126745435, "grad_norm": 2.181814505403613, "learning_rate": 5.182828060045783e-06, "loss": 0.4709, "step": 1005 }, { "epoch": 0.5424274973147154, "grad_norm": 2.2356286647456862, "learning_rate": 5.1359626220520804e-06, "loss": 0.4543, "step": 1010 }, { "epoch": 0.5451127819548872, "grad_norm": 2.309541338501052, "learning_rate": 5.08908522694135e-06, "loss": 0.4445, "step": 1015 }, { "epoch": 0.547798066595059, "grad_norm": 2.334557739373175, "learning_rate": 5.042199997306185e-06, "loss": 0.4579, "step": 1020 }, { "epoch": 0.550483351235231, "grad_norm": 2.3861434626116633, "learning_rate": 4.995311056428192e-06, "loss": 0.4487, "step": 1025 }, { "epoch": 0.5531686358754028, "grad_norm": 2.277598529970781, "learning_rate": 4.948422527915348e-06, "loss": 0.459, "step": 1030 }, { "epoch": 0.5558539205155747, "grad_norm": 2.5154062392897885, "learning_rate": 4.901538535339369e-06, "loss": 0.4471, "step": 1035 }, { "epoch": 0.5585392051557465, "grad_norm": 2.290644492599463, "learning_rate": 4.854663201873066e-06, "loss": 0.4534, "step": 1040 }, { "epoch": 0.5612244897959183, "grad_norm": 2.3507551432764715, "learning_rate": 4.807800649927723e-06, "loss": 0.4463, "step": 1045 }, { "epoch": 0.5639097744360902, "grad_norm": 2.1774339041234225, "learning_rate": 4.760955000790572e-06, "loss": 0.4365, "step": 1050 }, { "epoch": 0.5665950590762621, "grad_norm": 2.1529579750128454, "learning_rate": 4.714130374262339e-06, "loss": 0.4227, "step": 1055 }, { "epoch": 0.569280343716434, "grad_norm": 2.320093713572853, "learning_rate": 4.667330888294934e-06, "loss": 0.4212, "step": 1060 }, { "epoch": 0.5719656283566058, "grad_norm": 2.2930843074583427, "learning_rate": 4.620560658629303e-06, "loss": 0.4284, "step": 1065 }, { "epoch": 0.5746509129967776, "grad_norm": 2.2548004697834165, "learning_rate": 4.573823798433469e-06, "loss": 0.4446, "step": 1070 }, { "epoch": 0.5773361976369495, "grad_norm": 2.6223716299704347, "learning_rate": 4.527124417940812e-06, "loss": 0.4569, "step": 1075 }, { "epoch": 0.5800214822771214, "grad_norm": 2.2996066174355776, "learning_rate": 4.48046662408858e-06, "loss": 0.443, "step": 1080 }, { "epoch": 0.5827067669172933, "grad_norm": 2.331188250468318, "learning_rate": 4.43385452015673e-06, "loss": 0.4373, "step": 1085 }, { "epoch": 0.5853920515574651, "grad_norm": 2.2636646634515527, "learning_rate": 4.387292205407055e-06, "loss": 0.4359, "step": 1090 }, { "epoch": 0.5880773361976369, "grad_norm": 2.2831377194175033, "learning_rate": 4.3407837747226765e-06, "loss": 0.4364, "step": 1095 }, { "epoch": 0.5907626208378088, "grad_norm": 2.2946882078675146, "learning_rate": 4.29433331824793e-06, "loss": 0.4261, "step": 1100 }, { "epoch": 0.5934479054779807, "grad_norm": 2.2943723069744664, "learning_rate": 4.247944921028663e-06, "loss": 0.4358, "step": 1105 }, { "epoch": 0.5961331901181526, "grad_norm": 2.579316764381701, "learning_rate": 4.201622662652972e-06, "loss": 0.4204, "step": 1110 }, { "epoch": 0.5988184747583244, "grad_norm": 2.1742173999609737, "learning_rate": 4.155370616892422e-06, "loss": 0.4269, "step": 1115 }, { "epoch": 0.6015037593984962, "grad_norm": 2.6709708559911935, "learning_rate": 4.1091928513438005e-06, "loss": 0.4259, "step": 1120 }, { "epoch": 0.6041890440386681, "grad_norm": 2.1624211921715277, "learning_rate": 4.063093427071376e-06, "loss": 0.4311, "step": 1125 }, { "epoch": 0.60687432867884, "grad_norm": 2.3121026535251294, "learning_rate": 4.0170763982497716e-06, "loss": 0.4123, "step": 1130 }, { "epoch": 0.6095596133190118, "grad_norm": 2.291719266377087, "learning_rate": 3.971145811807397e-06, "loss": 0.4332, "step": 1135 }, { "epoch": 0.6122448979591837, "grad_norm": 2.151850103320739, "learning_rate": 3.925305707070572e-06, "loss": 0.4242, "step": 1140 }, { "epoch": 0.6149301825993555, "grad_norm": 2.199401051328622, "learning_rate": 3.879560115408279e-06, "loss": 0.4158, "step": 1145 }, { "epoch": 0.6176154672395274, "grad_norm": 2.229032836245145, "learning_rate": 3.833913059877622e-06, "loss": 0.4221, "step": 1150 }, { "epoch": 0.6203007518796992, "grad_norm": 2.29573891109709, "learning_rate": 3.788368554870034e-06, "loss": 0.4213, "step": 1155 }, { "epoch": 0.6229860365198711, "grad_norm": 2.1322887575075784, "learning_rate": 3.7429306057582306e-06, "loss": 0.4191, "step": 1160 }, { "epoch": 0.625671321160043, "grad_norm": 2.2395834148078198, "learning_rate": 3.6976032085439563e-06, "loss": 0.4203, "step": 1165 }, { "epoch": 0.6283566058002148, "grad_norm": 2.4717439033137625, "learning_rate": 3.6523903495065634e-06, "loss": 0.4186, "step": 1170 }, { "epoch": 0.6310418904403867, "grad_norm": 2.1334153639365976, "learning_rate": 3.6072960048524443e-06, "loss": 0.4142, "step": 1175 }, { "epoch": 0.6337271750805585, "grad_norm": 2.427052147510359, "learning_rate": 3.562324140365343e-06, "loss": 0.3999, "step": 1180 }, { "epoch": 0.6364124597207304, "grad_norm": 2.343168557743432, "learning_rate": 3.5174787110575904e-06, "loss": 0.4236, "step": 1185 }, { "epoch": 0.6390977443609023, "grad_norm": 2.1562840384388213, "learning_rate": 3.4727636608222813e-06, "loss": 0.4245, "step": 1190 }, { "epoch": 0.6417830290010741, "grad_norm": 2.36892688222517, "learning_rate": 3.428182922086437e-06, "loss": 0.4228, "step": 1195 }, { "epoch": 0.644468313641246, "grad_norm": 2.156449921799051, "learning_rate": 3.3837404154651677e-06, "loss": 0.415, "step": 1200 }, { "epoch": 0.6471535982814178, "grad_norm": 2.368201965573027, "learning_rate": 3.3394400494168745e-06, "loss": 0.4045, "step": 1205 }, { "epoch": 0.6498388829215896, "grad_norm": 2.272852040156483, "learning_rate": 3.2952857198995304e-06, "loss": 0.4206, "step": 1210 }, { "epoch": 0.6525241675617616, "grad_norm": 2.1923519803290206, "learning_rate": 3.2512813100280494e-06, "loss": 0.3881, "step": 1215 }, { "epoch": 0.6552094522019334, "grad_norm": 2.1711514227665556, "learning_rate": 3.2074306897327913e-06, "loss": 0.4089, "step": 1220 }, { "epoch": 0.6578947368421053, "grad_norm": 2.209964102937834, "learning_rate": 3.163737715419216e-06, "loss": 0.4131, "step": 1225 }, { "epoch": 0.6605800214822771, "grad_norm": 2.143618617488237, "learning_rate": 3.1202062296287507e-06, "loss": 0.4015, "step": 1230 }, { "epoch": 0.6632653061224489, "grad_norm": 2.1799040308872875, "learning_rate": 3.076840060700848e-06, "loss": 0.4186, "step": 1235 }, { "epoch": 0.6659505907626209, "grad_norm": 2.152210047047405, "learning_rate": 3.0336430224363067e-06, "loss": 0.4149, "step": 1240 }, { "epoch": 0.6686358754027927, "grad_norm": 2.2584562292798362, "learning_rate": 2.990618913761876e-06, "loss": 0.3926, "step": 1245 }, { "epoch": 0.6713211600429646, "grad_norm": 2.291181695240791, "learning_rate": 2.9477715183961634e-06, "loss": 0.3955, "step": 1250 }, { "epoch": 0.6740064446831364, "grad_norm": 2.1922026655553717, "learning_rate": 2.905104604516872e-06, "loss": 0.394, "step": 1255 }, { "epoch": 0.6766917293233082, "grad_norm": 2.3493386069538227, "learning_rate": 2.8626219244294074e-06, "loss": 0.3969, "step": 1260 }, { "epoch": 0.6793770139634802, "grad_norm": 2.2115983870340172, "learning_rate": 2.820327214236904e-06, "loss": 0.3937, "step": 1265 }, { "epoch": 0.682062298603652, "grad_norm": 2.1951996772318934, "learning_rate": 2.7782241935116337e-06, "loss": 0.4049, "step": 1270 }, { "epoch": 0.6847475832438239, "grad_norm": 2.425201994001083, "learning_rate": 2.7363165649679045e-06, "loss": 0.403, "step": 1275 }, { "epoch": 0.6874328678839957, "grad_norm": 2.2240784535487883, "learning_rate": 2.6946080141364295e-06, "loss": 0.3873, "step": 1280 }, { "epoch": 0.6901181525241675, "grad_norm": 2.2329860565273054, "learning_rate": 2.6531022090401946e-06, "loss": 0.3902, "step": 1285 }, { "epoch": 0.6928034371643395, "grad_norm": 2.327403916708101, "learning_rate": 2.611802799871893e-06, "loss": 0.3913, "step": 1290 }, { "epoch": 0.6954887218045113, "grad_norm": 2.1904991482392018, "learning_rate": 2.570713418672893e-06, "loss": 0.3919, "step": 1295 }, { "epoch": 0.6981740064446831, "grad_norm": 2.193162643266735, "learning_rate": 2.529837679013841e-06, "loss": 0.3878, "step": 1300 }, { "epoch": 0.700859291084855, "grad_norm": 2.37196563077284, "learning_rate": 2.4891791756768587e-06, "loss": 0.393, "step": 1305 }, { "epoch": 0.7035445757250268, "grad_norm": 2.165348884869985, "learning_rate": 2.4487414843394015e-06, "loss": 0.3931, "step": 1310 }, { "epoch": 0.7062298603651987, "grad_norm": 2.1614220141607277, "learning_rate": 2.4085281612598027e-06, "loss": 0.3912, "step": 1315 }, { "epoch": 0.7089151450053706, "grad_norm": 2.169220432212257, "learning_rate": 2.368542742964519e-06, "loss": 0.3869, "step": 1320 }, { "epoch": 0.7116004296455424, "grad_norm": 2.2172750452575154, "learning_rate": 2.3287887459371193e-06, "loss": 0.39, "step": 1325 }, { "epoch": 0.7142857142857143, "grad_norm": 2.386818932717909, "learning_rate": 2.2892696663090223e-06, "loss": 0.3852, "step": 1330 }, { "epoch": 0.7169709989258861, "grad_norm": 2.1061167664528395, "learning_rate": 2.2499889795520342e-06, "loss": 0.3759, "step": 1335 }, { "epoch": 0.719656283566058, "grad_norm": 2.3100938865418454, "learning_rate": 2.2109501401727097e-06, "loss": 0.385, "step": 1340 }, { "epoch": 0.7223415682062299, "grad_norm": 2.108999556383698, "learning_rate": 2.1721565814085355e-06, "loss": 0.3909, "step": 1345 }, { "epoch": 0.7250268528464017, "grad_norm": 2.2870436769769182, "learning_rate": 2.133611714926005e-06, "loss": 0.387, "step": 1350 }, { "epoch": 0.7277121374865736, "grad_norm": 2.0105731033958594, "learning_rate": 2.0953189305205847e-06, "loss": 0.3784, "step": 1355 }, { "epoch": 0.7303974221267454, "grad_norm": 2.0901917154894716, "learning_rate": 2.057281595818592e-06, "loss": 0.3859, "step": 1360 }, { "epoch": 0.7330827067669173, "grad_norm": 2.225721981804376, "learning_rate": 2.0195030559810387e-06, "loss": 0.3877, "step": 1365 }, { "epoch": 0.7357679914070892, "grad_norm": 2.1392668817849643, "learning_rate": 1.981986633409447e-06, "loss": 0.3846, "step": 1370 }, { "epoch": 0.738453276047261, "grad_norm": 2.255949862237254, "learning_rate": 1.944735627453654e-06, "loss": 0.3702, "step": 1375 }, { "epoch": 0.7411385606874329, "grad_norm": 2.223172130508635, "learning_rate": 1.907753314121662e-06, "loss": 0.3706, "step": 1380 }, { "epoch": 0.7438238453276047, "grad_norm": 2.120940618444079, "learning_rate": 1.8710429457915269e-06, "loss": 0.3723, "step": 1385 }, { "epoch": 0.7465091299677766, "grad_norm": 2.1971361335849506, "learning_rate": 1.834607750925333e-06, "loss": 0.3834, "step": 1390 }, { "epoch": 0.7491944146079484, "grad_norm": 2.0298699482093423, "learning_rate": 1.7984509337852724e-06, "loss": 0.3781, "step": 1395 }, { "epoch": 0.7518796992481203, "grad_norm": 1.9834275411391264, "learning_rate": 1.7625756741518407e-06, "loss": 0.3788, "step": 1400 }, { "epoch": 0.7545649838882922, "grad_norm": 2.0910842672856993, "learning_rate": 1.7269851270441978e-06, "loss": 0.3754, "step": 1405 }, { "epoch": 0.757250268528464, "grad_norm": 2.0335731739498093, "learning_rate": 1.6916824224427098e-06, "loss": 0.3725, "step": 1410 }, { "epoch": 0.7599355531686359, "grad_norm": 2.225103100697698, "learning_rate": 1.6566706650136704e-06, "loss": 0.3718, "step": 1415 }, { "epoch": 0.7626208378088077, "grad_norm": 2.240436179080048, "learning_rate": 1.6219529338362756e-06, "loss": 0.3749, "step": 1420 }, { "epoch": 0.7653061224489796, "grad_norm": 2.2290538372638045, "learning_rate": 1.587532282131835e-06, "loss": 0.3825, "step": 1425 }, { "epoch": 0.7679914070891515, "grad_norm": 2.0263712228907957, "learning_rate": 1.5534117369952523e-06, "loss": 0.371, "step": 1430 }, { "epoch": 0.7706766917293233, "grad_norm": 2.2797523248416005, "learning_rate": 1.5195942991288214e-06, "loss": 0.3638, "step": 1435 }, { "epoch": 0.7733619763694952, "grad_norm": 2.0115399295361733, "learning_rate": 1.4860829425783151e-06, "loss": 0.3733, "step": 1440 }, { "epoch": 0.776047261009667, "grad_norm": 2.2080947234810493, "learning_rate": 1.4528806144714546e-06, "loss": 0.3778, "step": 1445 }, { "epoch": 0.7787325456498388, "grad_norm": 2.290998397138441, "learning_rate": 1.4199902347587186e-06, "loss": 0.3656, "step": 1450 }, { "epoch": 0.7814178302900108, "grad_norm": 2.228838980742681, "learning_rate": 1.3874146959565387e-06, "loss": 0.3768, "step": 1455 }, { "epoch": 0.7841031149301826, "grad_norm": 2.257284588661445, "learning_rate": 1.3551568628929434e-06, "loss": 0.3702, "step": 1460 }, { "epoch": 0.7867883995703545, "grad_norm": 2.0867760648839884, "learning_rate": 1.3232195724555919e-06, "loss": 0.3613, "step": 1465 }, { "epoch": 0.7894736842105263, "grad_norm": 2.0536005270696687, "learning_rate": 1.291605633342301e-06, "loss": 0.3672, "step": 1470 }, { "epoch": 0.7921589688506981, "grad_norm": 2.1344491365761695, "learning_rate": 1.2603178258140264e-06, "loss": 0.363, "step": 1475 }, { "epoch": 0.7948442534908701, "grad_norm": 2.1698541824902953, "learning_rate": 1.22935890145036e-06, "loss": 0.3663, "step": 1480 }, { "epoch": 0.7975295381310419, "grad_norm": 2.1279360172580213, "learning_rate": 1.198731582907547e-06, "loss": 0.3645, "step": 1485 }, { "epoch": 0.8002148227712137, "grad_norm": 2.169055503223085, "learning_rate": 1.1684385636790368e-06, "loss": 0.3599, "step": 1490 }, { "epoch": 0.8029001074113856, "grad_norm": 1.9187045539119953, "learning_rate": 1.1384825078586114e-06, "loss": 0.3522, "step": 1495 }, { "epoch": 0.8055853920515574, "grad_norm": 2.2725376974932945, "learning_rate": 1.108866049906096e-06, "loss": 0.3627, "step": 1500 }, { "epoch": 0.8082706766917294, "grad_norm": 2.0445590327981824, "learning_rate": 1.079591794415667e-06, "loss": 0.3652, "step": 1505 }, { "epoch": 0.8109559613319012, "grad_norm": 2.160848009226544, "learning_rate": 1.0506623158867952e-06, "loss": 0.3692, "step": 1510 }, { "epoch": 0.813641245972073, "grad_norm": 2.073859022962504, "learning_rate": 1.0220801584978408e-06, "loss": 0.3639, "step": 1515 }, { "epoch": 0.8163265306122449, "grad_norm": 2.033806455267016, "learning_rate": 9.93847835882296e-07, "loss": 0.3517, "step": 1520 }, { "epoch": 0.8190118152524167, "grad_norm": 2.26746303873919, "learning_rate": 9.659678309077374e-07, "loss": 0.3516, "step": 1525 }, { "epoch": 0.8216970998925887, "grad_norm": 2.141101672161054, "learning_rate": 9.384425954574617e-07, "loss": 0.3607, "step": 1530 }, { "epoch": 0.8243823845327605, "grad_norm": 2.131127304156173, "learning_rate": 9.112745502148629e-07, "loss": 0.3618, "step": 1535 }, { "epoch": 0.8270676691729323, "grad_norm": 2.1498231144464026, "learning_rate": 8.844660844505498e-07, "loss": 0.3573, "step": 1540 }, { "epoch": 0.8297529538131042, "grad_norm": 1.9731227944157326, "learning_rate": 8.580195558122167e-07, "loss": 0.3691, "step": 1545 }, { "epoch": 0.832438238453276, "grad_norm": 2.068766813819825, "learning_rate": 8.319372901173045e-07, "loss": 0.3525, "step": 1550 }, { "epoch": 0.835123523093448, "grad_norm": 2.0577739725964075, "learning_rate": 8.062215811484652e-07, "loss": 0.3679, "step": 1555 }, { "epoch": 0.8378088077336198, "grad_norm": 2.0681341001622204, "learning_rate": 7.808746904518261e-07, "loss": 0.3589, "step": 1560 }, { "epoch": 0.8404940923737916, "grad_norm": 2.0118053393234216, "learning_rate": 7.558988471381063e-07, "loss": 0.3523, "step": 1565 }, { "epoch": 0.8431793770139635, "grad_norm": 2.0792733438147453, "learning_rate": 7.312962476865831e-07, "loss": 0.3485, "step": 1570 }, { "epoch": 0.8458646616541353, "grad_norm": 2.040693327935837, "learning_rate": 7.070690557519139e-07, "loss": 0.3605, "step": 1575 }, { "epoch": 0.8485499462943072, "grad_norm": 2.0885341784359195, "learning_rate": 6.832194019738686e-07, "loss": 0.3597, "step": 1580 }, { "epoch": 0.8512352309344791, "grad_norm": 2.0494324488359315, "learning_rate": 6.597493837899377e-07, "loss": 0.334, "step": 1585 }, { "epoch": 0.8539205155746509, "grad_norm": 2.370416793000066, "learning_rate": 6.366610652508875e-07, "loss": 0.3699, "step": 1590 }, { "epoch": 0.8566058002148228, "grad_norm": 2.013431987936131, "learning_rate": 6.13956476839237e-07, "loss": 0.3433, "step": 1595 }, { "epoch": 0.8592910848549946, "grad_norm": 2.248933148588524, "learning_rate": 5.916376152906761e-07, "loss": 0.3619, "step": 1600 }, { "epoch": 0.8619763694951665, "grad_norm": 2.199576156596231, "learning_rate": 5.697064434184835e-07, "loss": 0.3585, "step": 1605 }, { "epoch": 0.8646616541353384, "grad_norm": 2.0492788724705564, "learning_rate": 5.481648899408943e-07, "loss": 0.351, "step": 1610 }, { "epoch": 0.8673469387755102, "grad_norm": 2.1643262087841832, "learning_rate": 5.270148493114896e-07, "loss": 0.3613, "step": 1615 }, { "epoch": 0.8700322234156821, "grad_norm": 2.0363688955790775, "learning_rate": 5.062581815525819e-07, "loss": 0.3536, "step": 1620 }, { "epoch": 0.8727175080558539, "grad_norm": 2.2102662292719226, "learning_rate": 4.858967120916436e-07, "loss": 0.3691, "step": 1625 }, { "epoch": 0.8754027926960258, "grad_norm": 2.068954213267209, "learning_rate": 4.659322316007714e-07, "loss": 0.3579, "step": 1630 }, { "epoch": 0.8780880773361976, "grad_norm": 2.065009690643561, "learning_rate": 4.463664958392017e-07, "loss": 0.3476, "step": 1635 }, { "epoch": 0.8807733619763695, "grad_norm": 2.132923284888097, "learning_rate": 4.2720122549890607e-07, "loss": 0.3465, "step": 1640 }, { "epoch": 0.8834586466165414, "grad_norm": 2.0233890775516388, "learning_rate": 4.084381060532672e-07, "loss": 0.3436, "step": 1645 }, { "epoch": 0.8861439312567132, "grad_norm": 2.131767022151055, "learning_rate": 3.9007878760884856e-07, "loss": 0.3484, "step": 1650 }, { "epoch": 0.888829215896885, "grad_norm": 2.117063081591432, "learning_rate": 3.721248847602771e-07, "loss": 0.3557, "step": 1655 }, { "epoch": 0.8915145005370569, "grad_norm": 2.0080840103832025, "learning_rate": 3.5457797644825376e-07, "loss": 0.3575, "step": 1660 }, { "epoch": 0.8941997851772288, "grad_norm": 1.9992195938670811, "learning_rate": 3.3743960582068745e-07, "loss": 0.3563, "step": 1665 }, { "epoch": 0.8968850698174007, "grad_norm": 2.0730852522100585, "learning_rate": 3.207112800969925e-07, "loss": 0.3673, "step": 1670 }, { "epoch": 0.8995703544575725, "grad_norm": 2.124531809466262, "learning_rate": 3.0439447043553005e-07, "loss": 0.3495, "step": 1675 }, { "epoch": 0.9022556390977443, "grad_norm": 2.149507198420767, "learning_rate": 2.884906118042313e-07, "loss": 0.3464, "step": 1680 }, { "epoch": 0.9049409237379162, "grad_norm": 2.1429851911430773, "learning_rate": 2.730011028544044e-07, "loss": 0.3539, "step": 1685 }, { "epoch": 0.907626208378088, "grad_norm": 2.033562450055928, "learning_rate": 2.579273057977244e-07, "loss": 0.3683, "step": 1690 }, { "epoch": 0.91031149301826, "grad_norm": 2.099140956543066, "learning_rate": 2.4327054628643764e-07, "loss": 0.3524, "step": 1695 }, { "epoch": 0.9129967776584318, "grad_norm": 2.0654751576888324, "learning_rate": 2.29032113296781e-07, "loss": 0.3441, "step": 1700 }, { "epoch": 0.9156820622986036, "grad_norm": 2.065019806707046, "learning_rate": 2.1521325901561918e-07, "loss": 0.3489, "step": 1705 }, { "epoch": 0.9183673469387755, "grad_norm": 2.0595682015060177, "learning_rate": 2.018151987303263e-07, "loss": 0.3499, "step": 1710 }, { "epoch": 0.9210526315789473, "grad_norm": 2.1629799218903494, "learning_rate": 1.8883911072190619e-07, "loss": 0.354, "step": 1715 }, { "epoch": 0.9237379162191193, "grad_norm": 1.947786552992977, "learning_rate": 1.7628613616137048e-07, "loss": 0.3503, "step": 1720 }, { "epoch": 0.9264232008592911, "grad_norm": 2.087692154284924, "learning_rate": 1.6415737900937811e-07, "loss": 0.3501, "step": 1725 }, { "epoch": 0.9291084854994629, "grad_norm": 2.2226555122389406, "learning_rate": 1.5245390591914877e-07, "loss": 0.3426, "step": 1730 }, { "epoch": 0.9317937701396348, "grad_norm": 1.9281690244795662, "learning_rate": 1.4117674614265885e-07, "loss": 0.3598, "step": 1735 }, { "epoch": 0.9344790547798066, "grad_norm": 2.145136219649984, "learning_rate": 1.3032689144012457e-07, "loss": 0.3526, "step": 1740 }, { "epoch": 0.9371643394199786, "grad_norm": 2.0780704803664776, "learning_rate": 1.1990529599277656e-07, "loss": 0.3478, "step": 1745 }, { "epoch": 0.9398496240601504, "grad_norm": 2.1046408925852664, "learning_rate": 1.0991287631895498e-07, "loss": 0.3432, "step": 1750 }, { "epoch": 0.9425349087003222, "grad_norm": 1.8655403585442782, "learning_rate": 1.0035051119349881e-07, "loss": 0.3443, "step": 1755 }, { "epoch": 0.9452201933404941, "grad_norm": 1.9887511942254457, "learning_rate": 9.121904157046779e-08, "loss": 0.3483, "step": 1760 }, { "epoch": 0.9479054779806659, "grad_norm": 2.07044391687569, "learning_rate": 8.251927050918262e-08, "loss": 0.3487, "step": 1765 }, { "epoch": 0.9505907626208379, "grad_norm": 2.01578129872718, "learning_rate": 7.425196310360094e-08, "loss": 0.3576, "step": 1770 }, { "epoch": 0.9532760472610097, "grad_norm": 2.1282924163459325, "learning_rate": 6.64178464150339e-08, "loss": 0.3531, "step": 1775 }, { "epoch": 0.9559613319011815, "grad_norm": 2.0989453675717407, "learning_rate": 5.9017609408203445e-08, "loss": 0.3447, "step": 1780 }, { "epoch": 0.9586466165413534, "grad_norm": 2.0934033811862105, "learning_rate": 5.2051902890651316e-08, "loss": 0.3502, "step": 1785 }, { "epoch": 0.9613319011815252, "grad_norm": 2.1433944065391026, "learning_rate": 4.5521339455507075e-08, "loss": 0.3575, "step": 1790 }, { "epoch": 0.9640171858216972, "grad_norm": 2.0317297365975806, "learning_rate": 3.9426493427611177e-08, "loss": 0.3481, "step": 1795 }, { "epoch": 0.966702470461869, "grad_norm": 2.169192328216417, "learning_rate": 3.3767900813007623e-08, "loss": 0.3494, "step": 1800 }, { "epoch": 0.9693877551020408, "grad_norm": 2.0312846504114392, "learning_rate": 2.8546059251806092e-08, "loss": 0.3614, "step": 1805 }, { "epoch": 0.9720730397422127, "grad_norm": 2.280532113774367, "learning_rate": 2.3761427974416383e-08, "loss": 0.341, "step": 1810 }, { "epoch": 0.9747583243823845, "grad_norm": 2.0782148533974323, "learning_rate": 1.9414427761162423e-08, "loss": 0.3356, "step": 1815 }, { "epoch": 0.9774436090225563, "grad_norm": 2.0216470643000695, "learning_rate": 1.5505440905276835e-08, "loss": 0.3463, "step": 1820 }, { "epoch": 0.9801288936627283, "grad_norm": 2.005745009335829, "learning_rate": 1.203481117928007e-08, "loss": 0.3469, "step": 1825 }, { "epoch": 0.9828141783029001, "grad_norm": 2.091918639115214, "learning_rate": 9.002843804748473e-09, "loss": 0.3589, "step": 1830 }, { "epoch": 0.985499462943072, "grad_norm": 1.9926243886806494, "learning_rate": 6.409805425470761e-09, "loss": 0.3425, "step": 1835 }, { "epoch": 0.9881847475832438, "grad_norm": 1.9769758283227723, "learning_rate": 4.255924083999552e-09, "loss": 0.3621, "step": 1840 }, { "epoch": 0.9908700322234156, "grad_norm": 2.1185976376922038, "learning_rate": 2.5413892015951903e-09, "loss": 0.3617, "step": 1845 }, { "epoch": 0.9935553168635876, "grad_norm": 1.9588801206495003, "learning_rate": 1.266351561568513e-09, "loss": 0.3582, "step": 1850 }, { "epoch": 0.9962406015037594, "grad_norm": 2.0220772450114204, "learning_rate": 4.3092329601923664e-10, "loss": 0.3441, "step": 1855 }, { "epoch": 0.9989258861439313, "grad_norm": 2.0638722610945814, "learning_rate": 3.517787597440148e-11, "loss": 0.3507, "step": 1860 }, { "epoch": 1.0, "eval_runtime": 2.6591, "eval_samples_per_second": 3.761, "eval_steps_per_second": 1.128, "step": 1862 }, { "epoch": 1.0, "step": 1862, "total_flos": 194932459438080.0, "train_loss": 0.5118633475710831, "train_runtime": 20414.4633, "train_samples_per_second": 1.459, "train_steps_per_second": 0.091 } ], "logging_steps": 5, "max_steps": 1862, "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": 194932459438080.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }