{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9994372537985369, "eval_steps": 500, "global_step": 888, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0011254924029262803, "grad_norm": 0.8479363918304443, "learning_rate": 2.247191011235955e-06, "loss": 1.0084, "step": 1 }, { "epoch": 0.005627462014631401, "grad_norm": 1.0625563859939575, "learning_rate": 1.1235955056179776e-05, "loss": 1.1513, "step": 5 }, { "epoch": 0.011254924029262802, "grad_norm": 1.9530349969863892, "learning_rate": 2.2471910112359552e-05, "loss": 1.3647, "step": 10 }, { "epoch": 0.016882386043894203, "grad_norm": 1.0856108665466309, "learning_rate": 3.370786516853933e-05, "loss": 1.1026, "step": 15 }, { "epoch": 0.022509848058525603, "grad_norm": 1.3664439916610718, "learning_rate": 4.4943820224719104e-05, "loss": 0.836, "step": 20 }, { "epoch": 0.028137310073157007, "grad_norm": 0.8295888304710388, "learning_rate": 5.6179775280898885e-05, "loss": 0.6505, "step": 25 }, { "epoch": 0.03376477208778841, "grad_norm": 0.8303141593933105, "learning_rate": 6.741573033707866e-05, "loss": 0.6232, "step": 30 }, { "epoch": 0.03939223410241981, "grad_norm": 0.6008478999137878, "learning_rate": 7.865168539325843e-05, "loss": 0.428, "step": 35 }, { "epoch": 0.04501969611705121, "grad_norm": 0.731120228767395, "learning_rate": 8.988764044943821e-05, "loss": 0.4453, "step": 40 }, { "epoch": 0.050647158131682614, "grad_norm": 0.503491997718811, "learning_rate": 0.00010112359550561799, "loss": 0.3312, "step": 45 }, { "epoch": 0.056274620146314014, "grad_norm": 0.736613392829895, "learning_rate": 0.00011235955056179777, "loss": 0.3825, "step": 50 }, { "epoch": 0.061902082160945414, "grad_norm": 1.1015475988388062, "learning_rate": 0.00012359550561797752, "loss": 0.2907, "step": 55 }, { "epoch": 0.06752954417557681, "grad_norm": 0.7216058373451233, "learning_rate": 0.00013483146067415732, "loss": 0.3717, "step": 60 }, { "epoch": 0.07315700619020822, "grad_norm": 1.0304406881332397, "learning_rate": 0.0001460674157303371, "loss": 0.4053, "step": 65 }, { "epoch": 0.07878446820483961, "grad_norm": 0.717244029045105, "learning_rate": 0.00015730337078651685, "loss": 0.3471, "step": 70 }, { "epoch": 0.08441193021947102, "grad_norm": 0.8437204360961914, "learning_rate": 0.00016853932584269662, "loss": 0.3412, "step": 75 }, { "epoch": 0.09003939223410241, "grad_norm": 0.5658055543899536, "learning_rate": 0.00017977528089887642, "loss": 0.4183, "step": 80 }, { "epoch": 0.09566685424873382, "grad_norm": 0.6256535053253174, "learning_rate": 0.00019101123595505618, "loss": 0.3304, "step": 85 }, { "epoch": 0.10129431626336523, "grad_norm": 0.41338804364204407, "learning_rate": 0.00019999922700687455, "loss": 0.324, "step": 90 }, { "epoch": 0.10692177827799662, "grad_norm": 1.2900114059448242, "learning_rate": 0.000199972173502251, "loss": 0.3403, "step": 95 }, { "epoch": 0.11254924029262803, "grad_norm": 0.5315810441970825, "learning_rate": 0.00019990648229089103, "loss": 0.3061, "step": 100 }, { "epoch": 0.11817670230725942, "grad_norm": 0.6736317276954651, "learning_rate": 0.00019980217876143698, "loss": 0.307, "step": 105 }, { "epoch": 0.12380416432189083, "grad_norm": 0.5415677428245544, "learning_rate": 0.000199659303225598, "loss": 0.3489, "step": 110 }, { "epoch": 0.12943162633652222, "grad_norm": 0.6013039946556091, "learning_rate": 0.0001994779109025702, "loss": 0.3426, "step": 115 }, { "epoch": 0.13505908835115363, "grad_norm": 0.6924653053283691, "learning_rate": 0.00019925807189769533, "loss": 0.3847, "step": 120 }, { "epoch": 0.14068655036578503, "grad_norm": 2.3059215545654297, "learning_rate": 0.00019899987117536587, "loss": 0.3521, "step": 125 }, { "epoch": 0.14631401238041644, "grad_norm": 0.7815282940864563, "learning_rate": 0.00019870340852618803, "loss": 0.2937, "step": 130 }, { "epoch": 0.15194147439504782, "grad_norm": 0.7751880288124084, "learning_rate": 0.00019836879852841387, "loss": 0.3299, "step": 135 }, { "epoch": 0.15756893640967923, "grad_norm": 0.6737527251243591, "learning_rate": 0.0001979961705036587, "loss": 0.307, "step": 140 }, { "epoch": 0.16319639842431063, "grad_norm": 0.4875199794769287, "learning_rate": 0.00019758566846692029, "loss": 0.3564, "step": 145 }, { "epoch": 0.16882386043894204, "grad_norm": 0.48927029967308044, "learning_rate": 0.00019713745107091923, "loss": 0.3709, "step": 150 }, { "epoch": 0.17445132245357345, "grad_norm": 0.8061405420303345, "learning_rate": 0.00019665169154478213, "loss": 0.2479, "step": 155 }, { "epoch": 0.18007878446820483, "grad_norm": 0.5379148721694946, "learning_rate": 0.00019612857762709124, "loss": 0.2649, "step": 160 }, { "epoch": 0.18570624648283623, "grad_norm": 0.659520149230957, "learning_rate": 0.0001955683114933263, "loss": 0.3598, "step": 165 }, { "epoch": 0.19133370849746764, "grad_norm": 0.6669427752494812, "learning_rate": 0.00019497110967772692, "loss": 0.2604, "step": 170 }, { "epoch": 0.19696117051209905, "grad_norm": 0.48957839608192444, "learning_rate": 0.00019433720298960537, "loss": 0.2664, "step": 175 }, { "epoch": 0.20258863252673046, "grad_norm": 0.4717267155647278, "learning_rate": 0.0001936668364241424, "loss": 0.2949, "step": 180 }, { "epoch": 0.20821609454136183, "grad_norm": 0.5135904550552368, "learning_rate": 0.00019296026906770027, "loss": 0.3402, "step": 185 }, { "epoch": 0.21384355655599324, "grad_norm": 0.36506161093711853, "learning_rate": 0.00019221777399768998, "loss": 0.2935, "step": 190 }, { "epoch": 0.21947101857062465, "grad_norm": 0.6421459317207336, "learning_rate": 0.00019143963817703087, "loss": 0.2803, "step": 195 }, { "epoch": 0.22509848058525606, "grad_norm": 0.6440847516059875, "learning_rate": 0.0001906261623432441, "loss": 0.2791, "step": 200 }, { "epoch": 0.23072594259988746, "grad_norm": 0.4226614832878113, "learning_rate": 0.00018977766089222208, "loss": 0.2942, "step": 205 }, { "epoch": 0.23635340461451884, "grad_norm": 0.3801310360431671, "learning_rate": 0.00018889446175671926, "loss": 0.3874, "step": 210 }, { "epoch": 0.24198086662915025, "grad_norm": 0.626059353351593, "learning_rate": 0.00018797690627961132, "loss": 0.4083, "step": 215 }, { "epoch": 0.24760832864378166, "grad_norm": 0.35303783416748047, "learning_rate": 0.0001870253490819713, "loss": 0.2474, "step": 220 }, { "epoch": 0.25323579065841306, "grad_norm": 0.5032233595848083, "learning_rate": 0.00018604015792601396, "loss": 0.236, "step": 225 }, { "epoch": 0.25886325267304444, "grad_norm": 0.7859108448028564, "learning_rate": 0.00018502171357296144, "loss": 0.2065, "step": 230 }, { "epoch": 0.2644907146876759, "grad_norm": 0.47997885942459106, "learning_rate": 0.00018397040963588488, "loss": 0.2757, "step": 235 }, { "epoch": 0.27011817670230726, "grad_norm": 0.3313188850879669, "learning_rate": 0.00018288665242757903, "loss": 0.2234, "step": 240 }, { "epoch": 0.27574563871693863, "grad_norm": 0.42563286423683167, "learning_rate": 0.0001817708608035286, "loss": 0.2735, "step": 245 }, { "epoch": 0.28137310073157007, "grad_norm": 0.7245692610740662, "learning_rate": 0.00018062346600002699, "loss": 0.247, "step": 250 }, { "epoch": 0.28700056274620145, "grad_norm": 0.41776588559150696, "learning_rate": 0.00017944491146751026, "loss": 0.3202, "step": 255 }, { "epoch": 0.2926280247608329, "grad_norm": 0.46748408675193787, "learning_rate": 0.0001782356526991702, "loss": 0.2366, "step": 260 }, { "epoch": 0.29825548677546426, "grad_norm": 0.3817427456378937, "learning_rate": 0.00017699615705491325, "loss": 0.2053, "step": 265 }, { "epoch": 0.30388294879009564, "grad_norm": 0.3615594208240509, "learning_rate": 0.00017572690358073326, "loss": 0.1965, "step": 270 }, { "epoch": 0.3095104108047271, "grad_norm": 0.48413321375846863, "learning_rate": 0.00017442838282356727, "loss": 0.2121, "step": 275 }, { "epoch": 0.31513787281935846, "grad_norm": 0.7311267256736755, "learning_rate": 0.00017310109664170703, "loss": 0.3424, "step": 280 }, { "epoch": 0.3207653348339899, "grad_norm": 0.4602237641811371, "learning_rate": 0.00017174555801083814, "loss": 0.2099, "step": 285 }, { "epoch": 0.32639279684862127, "grad_norm": 0.5406469702720642, "learning_rate": 0.00017036229082578307, "loss": 0.3583, "step": 290 }, { "epoch": 0.33202025886325265, "grad_norm": 0.26748359203338623, "learning_rate": 0.00016895182969802386, "loss": 0.2119, "step": 295 }, { "epoch": 0.3376477208778841, "grad_norm": 0.40785279870033264, "learning_rate": 0.00016751471974908288, "loss": 0.2793, "step": 300 }, { "epoch": 0.34327518289251546, "grad_norm": 0.5709397196769714, "learning_rate": 0.00016605151639984187, "loss": 0.2525, "step": 305 }, { "epoch": 0.3489026449071469, "grad_norm": 0.857624351978302, "learning_rate": 0.00016456278515588024, "loss": 0.3339, "step": 310 }, { "epoch": 0.3545301069217783, "grad_norm": 0.33093103766441345, "learning_rate": 0.00016304910138891597, "loss": 0.3434, "step": 315 }, { "epoch": 0.36015756893640966, "grad_norm": 0.44036629796028137, "learning_rate": 0.00016151105011443314, "loss": 0.229, "step": 320 }, { "epoch": 0.3657850309510411, "grad_norm": 0.3742360770702362, "learning_rate": 0.00015994922576558263, "loss": 0.3026, "step": 325 }, { "epoch": 0.37141249296567247, "grad_norm": 0.3356841802597046, "learning_rate": 0.0001583642319634426, "loss": 0.2458, "step": 330 }, { "epoch": 0.3770399549803039, "grad_norm": 0.48720481991767883, "learning_rate": 0.00015675668128372854, "loss": 0.2653, "step": 335 }, { "epoch": 0.3826674169949353, "grad_norm": 0.6053282022476196, "learning_rate": 0.00015512719502004197, "loss": 0.3231, "step": 340 }, { "epoch": 0.38829487900956666, "grad_norm": 0.41004592180252075, "learning_rate": 0.00015347640294375005, "loss": 0.3181, "step": 345 }, { "epoch": 0.3939223410241981, "grad_norm": 0.6467001438140869, "learning_rate": 0.0001518049430605887, "loss": 0.5039, "step": 350 }, { "epoch": 0.3995498030388295, "grad_norm": 0.4072398543357849, "learning_rate": 0.0001501134613640832, "loss": 0.22, "step": 355 }, { "epoch": 0.4051772650534609, "grad_norm": 0.7158648371696472, "learning_rate": 0.0001484026115858815, "loss": 0.2842, "step": 360 }, { "epoch": 0.4108047270680923, "grad_norm": 0.5195010304450989, "learning_rate": 0.00014667305494309727, "loss": 0.2622, "step": 365 }, { "epoch": 0.41643218908272367, "grad_norm": 0.5050496459007263, "learning_rate": 0.00014492545988275933, "loss": 0.3665, "step": 370 }, { "epoch": 0.4220596510973551, "grad_norm": 0.27042141556739807, "learning_rate": 0.00014316050182346733, "loss": 0.3115, "step": 375 }, { "epoch": 0.4276871131119865, "grad_norm": 0.35634538531303406, "learning_rate": 0.00014137886289435295, "loss": 0.2217, "step": 380 }, { "epoch": 0.4333145751266179, "grad_norm": 0.336165189743042, "learning_rate": 0.00013958123167144733, "loss": 0.2716, "step": 385 }, { "epoch": 0.4389420371412493, "grad_norm": 0.5529112219810486, "learning_rate": 0.00013776830291155703, "loss": 0.3433, "step": 390 }, { "epoch": 0.4445694991558807, "grad_norm": 0.3461211025714874, "learning_rate": 0.00013594077728375128, "loss": 0.2916, "step": 395 }, { "epoch": 0.4501969611705121, "grad_norm": 0.6085760593414307, "learning_rate": 0.00013409936109856424, "loss": 0.2442, "step": 400 }, { "epoch": 0.4558244231851435, "grad_norm": 0.601696252822876, "learning_rate": 0.00013224476603501662, "loss": 0.2316, "step": 405 }, { "epoch": 0.4614518851997749, "grad_norm": 0.44390204548835754, "learning_rate": 0.00013037770886556294, "loss": 0.3902, "step": 410 }, { "epoch": 0.4670793472144063, "grad_norm": 0.3032180368900299, "learning_rate": 0.00012849891117906978, "loss": 0.2376, "step": 415 }, { "epoch": 0.4727068092290377, "grad_norm": 1.0338925123214722, "learning_rate": 0.00012660909910193303, "loss": 0.2524, "step": 420 }, { "epoch": 0.4783342712436691, "grad_norm": 0.29725944995880127, "learning_rate": 0.000124709003017441, "loss": 0.2789, "step": 425 }, { "epoch": 0.4839617332583005, "grad_norm": 0.5633781552314758, "learning_rate": 0.0001227993572834926, "loss": 0.2129, "step": 430 }, { "epoch": 0.48958919527293193, "grad_norm": 0.4558543562889099, "learning_rate": 0.0001208808999487793, "loss": 0.2721, "step": 435 }, { "epoch": 0.4952166572875633, "grad_norm": 0.41546952724456787, "learning_rate": 0.00011895437246754074, "loss": 0.2707, "step": 440 }, { "epoch": 0.5008441193021947, "grad_norm": 0.5292194485664368, "learning_rate": 0.00011702051941300396, "loss": 0.2852, "step": 445 }, { "epoch": 0.5064715813168261, "grad_norm": 0.44494009017944336, "learning_rate": 0.00011508008818961731, "loss": 0.1887, "step": 450 }, { "epoch": 0.5120990433314575, "grad_norm": 2.672574043273926, "learning_rate": 0.00011313382874419031, "loss": 0.2296, "step": 455 }, { "epoch": 0.5177265053460889, "grad_norm": 0.4071643054485321, "learning_rate": 0.00011118249327605055, "loss": 0.2921, "step": 460 }, { "epoch": 0.5233539673607203, "grad_norm": 0.41754430532455444, "learning_rate": 0.00010922683594633021, "loss": 0.2266, "step": 465 }, { "epoch": 0.5289814293753518, "grad_norm": 0.27264049649238586, "learning_rate": 0.00010726761258649461, "loss": 0.239, "step": 470 }, { "epoch": 0.5346088913899831, "grad_norm": 0.5015512704849243, "learning_rate": 0.00010530558040622472, "loss": 0.3052, "step": 475 }, { "epoch": 0.5402363534046145, "grad_norm": 0.3031107187271118, "learning_rate": 0.00010334149770076747, "loss": 0.3044, "step": 480 }, { "epoch": 0.5458638154192459, "grad_norm": 0.75295090675354, "learning_rate": 0.00010137612355786618, "loss": 0.2545, "step": 485 }, { "epoch": 0.5514912774338773, "grad_norm": 0.5242462754249573, "learning_rate": 9.941021756438488e-05, "loss": 0.2483, "step": 490 }, { "epoch": 0.5571187394485088, "grad_norm": 0.30885180830955505, "learning_rate": 9.744453951273968e-05, "loss": 0.279, "step": 495 }, { "epoch": 0.5627462014631401, "grad_norm": 0.39063045382499695, "learning_rate": 9.547984910725064e-05, "loss": 0.211, "step": 500 }, { "epoch": 0.5683736634777715, "grad_norm": 0.3500135838985443, "learning_rate": 9.35169056705278e-05, "loss": 0.2148, "step": 505 }, { "epoch": 0.5740011254924029, "grad_norm": 0.34409910440444946, "learning_rate": 9.155646785000467e-05, "loss": 0.2509, "step": 510 }, { "epoch": 0.5796285875070343, "grad_norm": 0.3541821539402008, "learning_rate": 8.959929332473262e-05, "loss": 0.3381, "step": 515 }, { "epoch": 0.5852560495216658, "grad_norm": 0.8181503415107727, "learning_rate": 8.764613851254968e-05, "loss": 0.2808, "step": 520 }, { "epoch": 0.5908835115362971, "grad_norm": 0.36616384983062744, "learning_rate": 8.569775827773656e-05, "loss": 0.1762, "step": 525 }, { "epoch": 0.5965109735509285, "grad_norm": 0.5440443754196167, "learning_rate": 8.375490563927328e-05, "loss": 0.2909, "step": 530 }, { "epoch": 0.6021384355655599, "grad_norm": 0.4618743360042572, "learning_rate": 8.181833147980894e-05, "loss": 0.3326, "step": 535 }, { "epoch": 0.6077658975801913, "grad_norm": 0.604923665523529, "learning_rate": 7.98887842554572e-05, "loss": 0.2639, "step": 540 }, { "epoch": 0.6133933595948228, "grad_norm": 0.46064886450767517, "learning_rate": 7.796700970652932e-05, "loss": 0.2933, "step": 545 }, { "epoch": 0.6190208216094542, "grad_norm": 0.4644724428653717, "learning_rate": 7.605375056931712e-05, "loss": 0.2487, "step": 550 }, { "epoch": 0.6246482836240855, "grad_norm": 0.5088258981704712, "learning_rate": 7.41497462890369e-05, "loss": 0.2957, "step": 555 }, { "epoch": 0.6302757456387169, "grad_norm": 0.6130680441856384, "learning_rate": 7.225573273404513e-05, "loss": 0.2588, "step": 560 }, { "epoch": 0.6359032076533483, "grad_norm": 0.45168906450271606, "learning_rate": 7.037244191143661e-05, "loss": 0.2477, "step": 565 }, { "epoch": 0.6415306696679798, "grad_norm": 0.2619435787200928, "learning_rate": 6.850060168413518e-05, "loss": 0.1566, "step": 570 }, { "epoch": 0.6471581316826112, "grad_norm": 0.36049678921699524, "learning_rate": 6.66409354895857e-05, "loss": 0.3076, "step": 575 }, { "epoch": 0.6527855936972425, "grad_norm": 0.20779716968536377, "learning_rate": 6.479416206015679e-05, "loss": 0.1849, "step": 580 }, { "epoch": 0.6584130557118739, "grad_norm": 0.5497414469718933, "learning_rate": 6.296099514536167e-05, "loss": 0.2734, "step": 585 }, { "epoch": 0.6640405177265053, "grad_norm": 0.3398374319076538, "learning_rate": 6.114214323600504e-05, "loss": 0.2271, "step": 590 }, { "epoch": 0.6696679797411368, "grad_norm": 0.2531116306781769, "learning_rate": 5.9338309290362324e-05, "loss": 0.1864, "step": 595 }, { "epoch": 0.6752954417557682, "grad_norm": 0.38855037093162537, "learning_rate": 5.7550190462496946e-05, "loss": 0.2591, "step": 600 }, { "epoch": 0.6809229037703995, "grad_norm": 0.4525040090084076, "learning_rate": 5.577847783282122e-05, "loss": 0.3319, "step": 605 }, { "epoch": 0.6865503657850309, "grad_norm": 0.5147562623023987, "learning_rate": 5.4023856141004236e-05, "loss": 0.2328, "step": 610 }, { "epoch": 0.6921778277996623, "grad_norm": 0.48170509934425354, "learning_rate": 5.228700352133071e-05, "loss": 0.3459, "step": 615 }, { "epoch": 0.6978052898142938, "grad_norm": 0.3423648178577423, "learning_rate": 5.05685912406123e-05, "loss": 0.2372, "step": 620 }, { "epoch": 0.7034327518289252, "grad_norm": 0.34861063957214355, "learning_rate": 4.886928343875341e-05, "loss": 0.2686, "step": 625 }, { "epoch": 0.7090602138435566, "grad_norm": 0.5629642009735107, "learning_rate": 4.71897368720714e-05, "loss": 0.1908, "step": 630 }, { "epoch": 0.7146876758581879, "grad_norm": 0.47687891125679016, "learning_rate": 4.553060065947013e-05, "loss": 0.3051, "step": 635 }, { "epoch": 0.7203151378728193, "grad_norm": 0.3600665032863617, "learning_rate": 4.3892516031565954e-05, "loss": 0.216, "step": 640 }, { "epoch": 0.7259425998874508, "grad_norm": 0.3238658905029297, "learning_rate": 4.227611608286147e-05, "loss": 0.2727, "step": 645 }, { "epoch": 0.7315700619020822, "grad_norm": 0.5159012675285339, "learning_rate": 4.0682025527064486e-05, "loss": 0.2408, "step": 650 }, { "epoch": 0.7371975239167136, "grad_norm": 0.5588057041168213, "learning_rate": 3.911086045564575e-05, "loss": 0.2084, "step": 655 }, { "epoch": 0.7428249859313449, "grad_norm": 0.33754897117614746, "learning_rate": 3.756322809972905e-05, "loss": 0.2405, "step": 660 }, { "epoch": 0.7484524479459763, "grad_norm": 0.3047542870044708, "learning_rate": 3.6039726595405755e-05, "loss": 0.2054, "step": 665 }, { "epoch": 0.7540799099606078, "grad_norm": 0.5348085761070251, "learning_rate": 3.4540944752564406e-05, "loss": 0.215, "step": 670 }, { "epoch": 0.7597073719752392, "grad_norm": 0.6096937656402588, "learning_rate": 3.3067461827324755e-05, "loss": 0.3615, "step": 675 }, { "epoch": 0.7653348339898706, "grad_norm": 0.29212549328804016, "learning_rate": 3.161984729816415e-05, "loss": 0.2056, "step": 680 }, { "epoch": 0.770962296004502, "grad_norm": 0.40820997953414917, "learning_rate": 3.0198660645822985e-05, "loss": 0.2244, "step": 685 }, { "epoch": 0.7765897580191333, "grad_norm": 0.35913002490997314, "learning_rate": 2.880445113707384e-05, "loss": 0.2536, "step": 690 }, { "epoch": 0.7822172200337648, "grad_norm": 0.36664295196533203, "learning_rate": 2.743775761243843e-05, "loss": 0.266, "step": 695 }, { "epoch": 0.7878446820483962, "grad_norm": 0.3958778381347656, "learning_rate": 2.6099108277934103e-05, "loss": 0.2483, "step": 700 }, { "epoch": 0.7934721440630276, "grad_norm": 0.4310711920261383, "learning_rate": 2.4789020500930095e-05, "loss": 0.179, "step": 705 }, { "epoch": 0.799099606077659, "grad_norm": 1.0834096670150757, "learning_rate": 2.3508000610193258e-05, "loss": 0.3142, "step": 710 }, { "epoch": 0.8047270680922903, "grad_norm": 1.0267940759658813, "learning_rate": 2.2256543700199685e-05, "loss": 0.2546, "step": 715 }, { "epoch": 0.8103545301069218, "grad_norm": 0.2950025498867035, "learning_rate": 2.1035133439788236e-05, "loss": 0.151, "step": 720 }, { "epoch": 0.8159819921215532, "grad_norm": 0.3759666085243225, "learning_rate": 1.9844241885230163e-05, "loss": 0.2239, "step": 725 }, { "epoch": 0.8216094541361846, "grad_norm": 0.34732529520988464, "learning_rate": 1.8684329297786453e-05, "loss": 0.2362, "step": 730 }, { "epoch": 0.827236916150816, "grad_norm": 0.2747817635536194, "learning_rate": 1.7555843965823992e-05, "loss": 0.2227, "step": 735 }, { "epoch": 0.8328643781654473, "grad_norm": 0.5855769515037537, "learning_rate": 1.6459222031558974e-05, "loss": 0.2677, "step": 740 }, { "epoch": 0.8384918401800788, "grad_norm": 0.49194827675819397, "learning_rate": 1.5394887322494732e-05, "loss": 0.2306, "step": 745 }, { "epoch": 0.8441193021947102, "grad_norm": 0.475304514169693, "learning_rate": 1.4363251187618854e-05, "loss": 0.3053, "step": 750 }, { "epoch": 0.8497467642093416, "grad_norm": 0.37457942962646484, "learning_rate": 1.3364712338423214e-05, "loss": 0.1884, "step": 755 }, { "epoch": 0.855374226223973, "grad_norm": 0.4119722247123718, "learning_rate": 1.2399656694807971e-05, "loss": 0.3746, "step": 760 }, { "epoch": 0.8610016882386043, "grad_norm": 0.5167866945266724, "learning_rate": 1.1468457235929597e-05, "loss": 0.2426, "step": 765 }, { "epoch": 0.8666291502532358, "grad_norm": 0.41178828477859497, "learning_rate": 1.0571473856050107e-05, "loss": 0.2886, "step": 770 }, { "epoch": 0.8722566122678672, "grad_norm": 0.43694284558296204, "learning_rate": 9.709053225443487e-06, "loss": 0.2708, "step": 775 }, { "epoch": 0.8778840742824986, "grad_norm": 0.22772341966629028, "learning_rate": 8.881528656412963e-06, "loss": 0.1469, "step": 780 }, { "epoch": 0.88351153629713, "grad_norm": 0.38090091943740845, "learning_rate": 8.08921997447094e-06, "loss": 0.3346, "step": 785 }, { "epoch": 0.8891389983117614, "grad_norm": 0.3263999819755554, "learning_rate": 7.332433394731331e-06, "loss": 0.2386, "step": 790 }, { "epoch": 0.8947664603263928, "grad_norm": 0.30097389221191406, "learning_rate": 6.611461403562147e-06, "loss": 0.1905, "step": 795 }, { "epoch": 0.9003939223410242, "grad_norm": 0.41428399085998535, "learning_rate": 5.92658264554401e-06, "loss": 0.2399, "step": 800 }, { "epoch": 0.9060213843556556, "grad_norm": 0.4272648096084595, "learning_rate": 5.278061815778313e-06, "loss": 0.195, "step": 805 }, { "epoch": 0.911648846370287, "grad_norm": 0.44488322734832764, "learning_rate": 4.666149557586697e-06, "loss": 0.2342, "step": 810 }, { "epoch": 0.9172763083849184, "grad_norm": 0.3607059717178345, "learning_rate": 4.091082365641085e-06, "loss": 0.2702, "step": 815 }, { "epoch": 0.9229037703995498, "grad_norm": 0.30268949270248413, "learning_rate": 3.5530824945623542e-06, "loss": 0.2509, "step": 820 }, { "epoch": 0.9285312324141812, "grad_norm": 0.478462815284729, "learning_rate": 3.0523578730221713e-06, "loss": 0.2529, "step": 825 }, { "epoch": 0.9341586944288126, "grad_norm": 0.36823543906211853, "learning_rate": 2.589102023381895e-06, "loss": 0.2497, "step": 830 }, { "epoch": 0.939786156443444, "grad_norm": 0.6508424878120422, "learning_rate": 2.1634939868990235e-06, "loss": 0.4272, "step": 835 }, { "epoch": 0.9454136184580754, "grad_norm": 0.4297642409801483, "learning_rate": 1.7756982545306443e-06, "loss": 0.2261, "step": 840 }, { "epoch": 0.9510410804727069, "grad_norm": 0.2725857198238373, "learning_rate": 1.4258647033601024e-06, "loss": 0.1526, "step": 845 }, { "epoch": 0.9566685424873382, "grad_norm": 0.366515189409256, "learning_rate": 1.1141285386718437e-06, "loss": 0.2365, "step": 850 }, { "epoch": 0.9622960045019696, "grad_norm": 0.4519096910953522, "learning_rate": 8.406102416967043e-07, "loss": 0.2357, "step": 855 }, { "epoch": 0.967923466516601, "grad_norm": 0.36480775475502014, "learning_rate": 6.054155230476699e-07, "loss": 0.2632, "step": 860 }, { "epoch": 0.9735509285312324, "grad_norm": 0.29836106300354004, "learning_rate": 4.0863528186445564e-07, "loss": 0.2645, "step": 865 }, { "epoch": 0.9791783905458639, "grad_norm": 0.33390042185783386, "learning_rate": 2.50345570682331e-07, "loss": 0.2836, "step": 870 }, { "epoch": 0.9848058525604952, "grad_norm": 0.5138782262802124, "learning_rate": 1.3060756603897605e-07, "loss": 0.2035, "step": 875 }, { "epoch": 0.9904333145751266, "grad_norm": 0.47627323865890503, "learning_rate": 4.946754483071692e-08, "loss": 0.2365, "step": 880 }, { "epoch": 0.996060776589758, "grad_norm": 0.2622200548648834, "learning_rate": 6.95686642719906e-09, "loss": 0.1815, "step": 885 }, { "epoch": 0.9994372537985369, "step": 888, "total_flos": 8.639715708407644e+17, "train_loss": 0.2980908542066007, "train_runtime": 5659.1413, "train_samples_per_second": 2.512, "train_steps_per_second": 0.157 } ], "logging_steps": 5, "max_steps": 888, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 8.639715708407644e+17, "train_batch_size": 4, "trial_name": null, "trial_params": null }