| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9990766389658357, | |
| "eval_steps": 500, | |
| "global_step": 541, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018467220683287165, | |
| "grad_norm": 0.18254348635673523, | |
| "learning_rate": 3.636363636363636e-06, | |
| "loss": 0.8244, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009233610341643583, | |
| "grad_norm": 0.1816311925649643, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.7911, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018467220683287166, | |
| "grad_norm": 0.16621439158916473, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.7968, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027700831024930747, | |
| "grad_norm": 0.1893552839756012, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.7942, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03693444136657433, | |
| "grad_norm": 0.12671160697937012, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.7531, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.046168051708217916, | |
| "grad_norm": 0.12510479986667633, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.7688, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.055401662049861494, | |
| "grad_norm": 0.1175699383020401, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 0.7694, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06463527239150507, | |
| "grad_norm": 0.11805781722068787, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 0.7348, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07386888273314866, | |
| "grad_norm": 0.11772854626178741, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 0.7407, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08310249307479224, | |
| "grad_norm": 0.2634792625904083, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 0.7324, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09233610341643583, | |
| "grad_norm": 0.1200411394238472, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.7535, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10156971375807941, | |
| "grad_norm": 0.12060506641864777, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7487, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.11080332409972299, | |
| "grad_norm": 0.12120962888002396, | |
| "learning_rate": 0.00019994777247895855, | |
| "loss": 0.745, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.12003693444136658, | |
| "grad_norm": 0.14212490618228912, | |
| "learning_rate": 0.00019979114447011323, | |
| "loss": 0.7294, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.12927054478301014, | |
| "grad_norm": 0.1235802099108696, | |
| "learning_rate": 0.00019953027957931658, | |
| "loss": 0.7391, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13850415512465375, | |
| "grad_norm": 0.11884737759828568, | |
| "learning_rate": 0.00019916545029310012, | |
| "loss": 0.7324, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.14773776546629733, | |
| "grad_norm": 0.1151009351015091, | |
| "learning_rate": 0.00019869703769404828, | |
| "loss": 0.7266, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1569713758079409, | |
| "grad_norm": 0.11894387751817703, | |
| "learning_rate": 0.00019812553106273847, | |
| "loss": 0.7467, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.16620498614958448, | |
| "grad_norm": 0.1144394502043724, | |
| "learning_rate": 0.00019745152736666302, | |
| "loss": 0.7376, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 0.11750061810016632, | |
| "learning_rate": 0.0001966757306366662, | |
| "loss": 0.7383, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.18467220683287167, | |
| "grad_norm": 0.13155049085617065, | |
| "learning_rate": 0.0001957989512315489, | |
| "loss": 0.7451, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.19390581717451524, | |
| "grad_norm": 0.11150489002466202, | |
| "learning_rate": 0.00019482210499160765, | |
| "loss": 0.7412, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.20313942751615882, | |
| "grad_norm": 0.10819390416145325, | |
| "learning_rate": 0.0001937462122819935, | |
| "loss": 0.7422, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2123730378578024, | |
| "grad_norm": 0.11923832446336746, | |
| "learning_rate": 0.00019257239692688907, | |
| "loss": 0.7377, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.22160664819944598, | |
| "grad_norm": 0.11017678678035736, | |
| "learning_rate": 0.00019130188503561741, | |
| "loss": 0.7351, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.23084025854108955, | |
| "grad_norm": 0.11701685935258865, | |
| "learning_rate": 0.00018993600372190932, | |
| "loss": 0.7282, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.24007386888273316, | |
| "grad_norm": 0.11328760534524918, | |
| "learning_rate": 0.00018847617971766577, | |
| "loss": 0.7269, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.24930747922437674, | |
| "grad_norm": 0.11526869982481003, | |
| "learning_rate": 0.00018692393788266479, | |
| "loss": 0.7083, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.2585410895660203, | |
| "grad_norm": 0.1022554561495781, | |
| "learning_rate": 0.0001852808996117683, | |
| "loss": 0.7118, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2677746999076639, | |
| "grad_norm": 0.12440157681703568, | |
| "learning_rate": 0.00018354878114129367, | |
| "loss": 0.7294, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.2770083102493075, | |
| "grad_norm": 0.11588307470083237, | |
| "learning_rate": 0.00018172939175631808, | |
| "loss": 0.743, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.28624192059095105, | |
| "grad_norm": 0.12347640097141266, | |
| "learning_rate": 0.0001798246319007893, | |
| "loss": 0.7449, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.29547553093259465, | |
| "grad_norm": 0.12588274478912354, | |
| "learning_rate": 0.00017783649119241602, | |
| "loss": 0.761, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3047091412742382, | |
| "grad_norm": 0.11528731882572174, | |
| "learning_rate": 0.0001757670463444118, | |
| "loss": 0.7353, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.3139427516158818, | |
| "grad_norm": 0.11055415123701096, | |
| "learning_rate": 0.00017361845899626355, | |
| "loss": 0.7331, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3231763619575254, | |
| "grad_norm": 0.10451104491949081, | |
| "learning_rate": 0.00017139297345578994, | |
| "loss": 0.7594, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.33240997229916897, | |
| "grad_norm": 0.11109859496355057, | |
| "learning_rate": 0.0001690929143548488, | |
| "loss": 0.7291, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.34164358264081257, | |
| "grad_norm": 0.11210189759731293, | |
| "learning_rate": 0.00016672068422114196, | |
| "loss": 0.7372, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 0.11521945893764496, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 0.7404, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3601108033240997, | |
| "grad_norm": 0.11584653705358505, | |
| "learning_rate": 0.00016176969530934572, | |
| "loss": 0.7465, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.36934441366574333, | |
| "grad_norm": 0.11106808483600616, | |
| "learning_rate": 0.0001591961080888076, | |
| "loss": 0.7235, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3785780240073869, | |
| "grad_norm": 0.09438136965036392, | |
| "learning_rate": 0.00015656068754865387, | |
| "loss": 0.7104, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.3878116343490305, | |
| "grad_norm": 0.10474290698766708, | |
| "learning_rate": 0.0001538661865185188, | |
| "loss": 0.7567, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.39704524469067404, | |
| "grad_norm": 0.11921609193086624, | |
| "learning_rate": 0.00015111541954058734, | |
| "loss": 0.739, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.40627885503231764, | |
| "grad_norm": 0.11335526406764984, | |
| "learning_rate": 0.00014831125992966385, | |
| "loss": 0.734, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4155124653739612, | |
| "grad_norm": 0.11289556324481964, | |
| "learning_rate": 0.00014545663677185006, | |
| "loss": 0.7448, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.4247460757156048, | |
| "grad_norm": 0.10999900847673416, | |
| "learning_rate": 0.00014255453186496673, | |
| "loss": 0.7316, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4339796860572484, | |
| "grad_norm": 0.1110299751162529, | |
| "learning_rate": 0.0001396079766039157, | |
| "loss": 0.7247, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.44321329639889195, | |
| "grad_norm": 0.11613520234823227, | |
| "learning_rate": 0.0001366200488142348, | |
| "loss": 0.7364, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.45244690674053556, | |
| "grad_norm": 0.11091934144496918, | |
| "learning_rate": 0.00013359386953715421, | |
| "loss": 0.7497, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.4616805170821791, | |
| "grad_norm": 0.1117897480726242, | |
| "learning_rate": 0.00013053259976951133, | |
| "loss": 0.7318, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4709141274238227, | |
| "grad_norm": 0.10972230136394501, | |
| "learning_rate": 0.00012743943716193016, | |
| "loss": 0.7362, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.4801477377654663, | |
| "grad_norm": 0.1100962832570076, | |
| "learning_rate": 0.00012431761267871417, | |
| "loss": 0.7246, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.48938134810710987, | |
| "grad_norm": 0.11420110613107681, | |
| "learning_rate": 0.0001211703872229411, | |
| "loss": 0.6997, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.4986149584487535, | |
| "grad_norm": 0.11659246683120728, | |
| "learning_rate": 0.00011800104823028515, | |
| "loss": 0.7216, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5078485687903971, | |
| "grad_norm": 0.10777433216571808, | |
| "learning_rate": 0.0001148129062351249, | |
| "loss": 0.7386, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5170821791320406, | |
| "grad_norm": 0.1175241768360138, | |
| "learning_rate": 0.00011160929141252303, | |
| "loss": 0.7354, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.11116177588701248, | |
| "learning_rate": 0.00010839355009969068, | |
| "loss": 0.74, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.5355493998153278, | |
| "grad_norm": 0.11569847166538239, | |
| "learning_rate": 0.00010516904130056946, | |
| "loss": 0.7488, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5447830101569714, | |
| "grad_norm": 0.12016792595386505, | |
| "learning_rate": 0.00010193913317718244, | |
| "loss": 0.7238, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.554016620498615, | |
| "grad_norm": 0.11518382281064987, | |
| "learning_rate": 9.870719953141917e-05, | |
| "loss": 0.7223, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5632502308402585, | |
| "grad_norm": 0.1142842248082161, | |
| "learning_rate": 9.547661628092937e-05, | |
| "loss": 0.7409, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.5724838411819021, | |
| "grad_norm": 0.10657477378845215, | |
| "learning_rate": 9.225075793280692e-05, | |
| "loss": 0.7228, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5817174515235457, | |
| "grad_norm": 0.10703656822443008, | |
| "learning_rate": 8.903299405874684e-05, | |
| "loss": 0.7367, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.5909510618651893, | |
| "grad_norm": 0.10378415137529373, | |
| "learning_rate": 8.582668577535797e-05, | |
| "loss": 0.7368, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6001846722068329, | |
| "grad_norm": 0.1063636764883995, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.7504, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.6094182825484764, | |
| "grad_norm": 0.1067524254322052, | |
| "learning_rate": 7.94618171189618e-05, | |
| "loss": 0.7114, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.61865189289012, | |
| "grad_norm": 0.11942796409130096, | |
| "learning_rate": 7.630990517218808e-05, | |
| "loss": 0.7372, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.6278855032317636, | |
| "grad_norm": 0.11493529379367828, | |
| "learning_rate": 7.318273872393625e-05, | |
| "loss": 0.7194, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6371191135734072, | |
| "grad_norm": 0.10850054770708084, | |
| "learning_rate": 7.008358425723585e-05, | |
| "loss": 0.7423, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.6463527239150508, | |
| "grad_norm": 0.11228082329034805, | |
| "learning_rate": 6.701567899518924e-05, | |
| "loss": 0.7064, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6555863342566943, | |
| "grad_norm": 0.10916541516780853, | |
| "learning_rate": 6.398222751952899e-05, | |
| "loss": 0.7026, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.6648199445983379, | |
| "grad_norm": 0.11889058351516724, | |
| "learning_rate": 6.098639842327052e-05, | |
| "loss": 0.7273, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6740535549399815, | |
| "grad_norm": 0.11622773110866547, | |
| "learning_rate": 5.80313210009571e-05, | |
| "loss": 0.7251, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.6832871652816251, | |
| "grad_norm": 0.11390994489192963, | |
| "learning_rate": 5.5120081979953785e-05, | |
| "loss": 0.7425, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6925207756232687, | |
| "grad_norm": 0.10942788422107697, | |
| "learning_rate": 5.22557222962051e-05, | |
| "loss": 0.7278, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.11150877922773361, | |
| "learning_rate": 4.9441233917824106e-05, | |
| "loss": 0.7199, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7109879963065558, | |
| "grad_norm": 0.11406592279672623, | |
| "learning_rate": 4.66795567198309e-05, | |
| "loss": 0.7635, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.7202216066481995, | |
| "grad_norm": 0.10552997142076492, | |
| "learning_rate": 4.397357541330476e-05, | |
| "loss": 0.74, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7294552169898431, | |
| "grad_norm": 0.11307038366794586, | |
| "learning_rate": 4.132611653215822e-05, | |
| "loss": 0.7155, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.7386888273314867, | |
| "grad_norm": 0.11548582464456558, | |
| "learning_rate": 3.873994548067972e-05, | |
| "loss": 0.735, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7479224376731302, | |
| "grad_norm": 0.11258837580680847, | |
| "learning_rate": 3.621776364492939e-05, | |
| "loss": 0.7438, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.7571560480147738, | |
| "grad_norm": 0.11234745383262634, | |
| "learning_rate": 3.376220557100523e-05, | |
| "loss": 0.7289, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.7663896583564174, | |
| "grad_norm": 0.11089134961366653, | |
| "learning_rate": 3.137583621312665e-05, | |
| "loss": 0.7185, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.775623268698061, | |
| "grad_norm": 0.1163964495062828, | |
| "learning_rate": 2.906114825441072e-05, | |
| "loss": 0.7194, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7848568790397045, | |
| "grad_norm": 0.12141181528568268, | |
| "learning_rate": 2.6820559503138797e-05, | |
| "loss": 0.7271, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.7940904893813481, | |
| "grad_norm": 0.11405418813228607, | |
| "learning_rate": 2.465641036723393e-05, | |
| "loss": 0.7176, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.8033240997229917, | |
| "grad_norm": 0.1123843789100647, | |
| "learning_rate": 2.2570961409586754e-05, | |
| "loss": 0.7218, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.8125577100646353, | |
| "grad_norm": 0.1090715080499649, | |
| "learning_rate": 2.0566390986783646e-05, | |
| "loss": 0.7348, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8217913204062789, | |
| "grad_norm": 0.1076655238866806, | |
| "learning_rate": 1.864479297370325e-05, | |
| "loss": 0.7508, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.8310249307479224, | |
| "grad_norm": 0.1181124672293663, | |
| "learning_rate": 1.6808174576358848e-05, | |
| "loss": 0.7248, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.840258541089566, | |
| "grad_norm": 0.11672370880842209, | |
| "learning_rate": 1.505845423527027e-05, | |
| "loss": 0.7357, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.8494921514312096, | |
| "grad_norm": 0.10791666060686111, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.7117, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.8587257617728532, | |
| "grad_norm": 0.10970946401357651, | |
| "learning_rate": 1.18269257278392e-05, | |
| "loss": 0.724, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.8679593721144968, | |
| "grad_norm": 0.10867480933666229, | |
| "learning_rate": 1.0348493055959062e-05, | |
| "loss": 0.7184, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 0.10204034298658371, | |
| "learning_rate": 8.963705903385345e-06, | |
| "loss": 0.7395, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.8864265927977839, | |
| "grad_norm": 0.10882284492254257, | |
| "learning_rate": 7.674010750120964e-06, | |
| "loss": 0.727, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8956602031394275, | |
| "grad_norm": 0.11304344236850739, | |
| "learning_rate": 6.480754747781037e-06, | |
| "loss": 0.7039, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.9048938134810711, | |
| "grad_norm": 0.11570131033658981, | |
| "learning_rate": 5.385184312424974e-06, | |
| "loss": 0.7444, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9141274238227147, | |
| "grad_norm": 0.10709495097398758, | |
| "learning_rate": 4.3884438226120424e-06, | |
| "loss": 0.7134, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.9233610341643582, | |
| "grad_norm": 0.11614098399877548, | |
| "learning_rate": 3.4915744240403558e-06, | |
| "loss": 0.707, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9325946445060018, | |
| "grad_norm": 0.11611202359199524, | |
| "learning_rate": 2.6955129420176196e-06, | |
| "loss": 0.737, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.9418282548476454, | |
| "grad_norm": 0.11080285161733627, | |
| "learning_rate": 2.0010909028998827e-06, | |
| "loss": 0.7359, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.951061865189289, | |
| "grad_norm": 0.1167815551161766, | |
| "learning_rate": 1.409033665520354e-06, | |
| "loss": 0.7131, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.9602954755309326, | |
| "grad_norm": 0.11581467092037201, | |
| "learning_rate": 9.199596635154683e-07, | |
| "loss": 0.7062, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9695290858725761, | |
| "grad_norm": 0.1139911562204361, | |
| "learning_rate": 5.343797593398536e-07, | |
| "loss": 0.7382, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.9787626962142197, | |
| "grad_norm": 0.10670532286167145, | |
| "learning_rate": 2.5269671064467313e-07, | |
| "loss": 0.6965, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.9879963065558633, | |
| "grad_norm": 0.10769211500883102, | |
| "learning_rate": 7.520474957699586e-08, | |
| "loss": 0.7086, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.997229916897507, | |
| "grad_norm": 0.10409457236528397, | |
| "learning_rate": 2.0892754394208346e-09, | |
| "loss": 0.702, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.9990766389658357, | |
| "eval_loss": 0.9494999051094055, | |
| "eval_runtime": 131.5083, | |
| "eval_samples_per_second": 8.783, | |
| "eval_steps_per_second": 0.555, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.9990766389658357, | |
| "step": 541, | |
| "total_flos": 2.2228397020277637e+18, | |
| "train_loss": 0.7336494325489742, | |
| "train_runtime": 26329.8311, | |
| "train_samples_per_second": 3.947, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 541, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2228397020277637e+18, | |
| "train_batch_size": 24, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |