rqadri's picture
Add files using upload-large-folder tool
b398e77 verified
Raw History Blame Contribute Delete
46 kB
{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.23328330832082708, "eval_steps": 500, "global_step": 2798, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0008337502084375521, "grad_norm": 13.566391944885254, "learning_rate": 1.1061797752808989e-06, "loss": 2.2566, "step": 10 }, { "epoch": 0.0016675004168751042, "grad_norm": 2.918423652648926, "learning_rate": 2.2241573033707866e-06, "loss": 2.04, "step": 20 }, { "epoch": 0.0025012506253126563, "grad_norm": 3.1750669479370117, "learning_rate": 3.342134831460675e-06, "loss": 1.8853, "step": 30 }, { "epoch": 0.0033350008337502085, "grad_norm": 1.5451328754425049, "learning_rate": 4.4601123595505624e-06, "loss": 1.482, "step": 40 }, { "epoch": 0.00416875104218776, "grad_norm": 0.9934996366500854, "learning_rate": 5.5780898876404495e-06, "loss": 1.232, "step": 50 }, { "epoch": 0.0050025012506253125, "grad_norm": 0.6822673082351685, "learning_rate": 6.6960674157303374e-06, "loss": 1.1003, "step": 60 }, { "epoch": 0.005836251459062865, "grad_norm": 0.8204601407051086, "learning_rate": 7.814044943820226e-06, "loss": 1.0664, "step": 70 }, { "epoch": 0.006670001667500417, "grad_norm": 0.5949751734733582, "learning_rate": 8.932022471910112e-06, "loss": 1.0583, "step": 80 }, { "epoch": 0.007503751875937969, "grad_norm": 0.6005659103393555, "learning_rate": 1.005e-05, "loss": 0.9972, "step": 90 }, { "epoch": 0.00833750208437552, "grad_norm": 0.5980632305145264, "learning_rate": 1.1167977528089888e-05, "loss": 0.9785, "step": 100 }, { "epoch": 0.009171252292813074, "grad_norm": 0.5540244579315186, "learning_rate": 1.2285955056179776e-05, "loss": 1.0015, "step": 110 }, { "epoch": 0.010005002501250625, "grad_norm": 0.593195378780365, "learning_rate": 1.3403932584269664e-05, "loss": 0.9758, "step": 120 }, { "epoch": 0.010838752709688178, "grad_norm": 0.583214282989502, "learning_rate": 1.4521910112359552e-05, "loss": 0.9762, "step": 130 }, { "epoch": 0.01167250291812573, "grad_norm": 1.0294115543365479, "learning_rate": 1.563988764044944e-05, "loss": 0.9824, "step": 140 }, { "epoch": 0.01250625312656328, "grad_norm": 0.6010154485702515, "learning_rate": 1.6757865168539328e-05, "loss": 0.9845, "step": 150 }, { "epoch": 0.013340003335000834, "grad_norm": 0.5743474960327148, "learning_rate": 1.7875842696629214e-05, "loss": 0.9589, "step": 160 }, { "epoch": 0.014173753543438385, "grad_norm": 0.6928213238716125, "learning_rate": 1.89938202247191e-05, "loss": 0.9375, "step": 170 }, { "epoch": 0.015007503751875938, "grad_norm": 0.5875935554504395, "learning_rate": 2e-05, "loss": 0.9497, "step": 180 }, { "epoch": 0.01584125396031349, "grad_norm": 0.6017818450927734, "learning_rate": 2e-05, "loss": 0.9398, "step": 190 }, { "epoch": 0.01667500416875104, "grad_norm": 0.6024709939956665, "learning_rate": 2e-05, "loss": 0.9518, "step": 200 }, { "epoch": 0.017508754377188594, "grad_norm": 0.5575109124183655, "learning_rate": 2e-05, "loss": 0.9559, "step": 210 }, { "epoch": 0.018342504585626147, "grad_norm": 0.5377241969108582, "learning_rate": 2e-05, "loss": 0.9173, "step": 220 }, { "epoch": 0.019176254794063697, "grad_norm": 0.6026791930198669, "learning_rate": 2e-05, "loss": 0.9429, "step": 230 }, { "epoch": 0.02001000500250125, "grad_norm": 0.5152384042739868, "learning_rate": 2e-05, "loss": 0.9307, "step": 240 }, { "epoch": 0.020843755210938803, "grad_norm": 0.5376507043838501, "learning_rate": 2e-05, "loss": 0.9141, "step": 250 }, { "epoch": 0.021677505419376356, "grad_norm": 0.5467250943183899, "learning_rate": 2e-05, "loss": 0.9635, "step": 260 }, { "epoch": 0.022511255627813906, "grad_norm": 0.48651859164237976, "learning_rate": 2e-05, "loss": 0.9256, "step": 270 }, { "epoch": 0.02334500583625146, "grad_norm": 0.5394302606582642, "learning_rate": 2e-05, "loss": 0.9682, "step": 280 }, { "epoch": 0.024178756044689012, "grad_norm": 0.557639479637146, "learning_rate": 2e-05, "loss": 0.8902, "step": 290 }, { "epoch": 0.02501250625312656, "grad_norm": 0.5069289207458496, "learning_rate": 2e-05, "loss": 0.8967, "step": 300 }, { "epoch": 0.025846256461564115, "grad_norm": 0.5206510424613953, "learning_rate": 2e-05, "loss": 0.9144, "step": 310 }, { "epoch": 0.026680006670001668, "grad_norm": 0.6359990835189819, "learning_rate": 2e-05, "loss": 0.9147, "step": 320 }, { "epoch": 0.02751375687843922, "grad_norm": 0.5385337471961975, "learning_rate": 2e-05, "loss": 0.9343, "step": 330 }, { "epoch": 0.02834750708687677, "grad_norm": 0.9713227152824402, "learning_rate": 2e-05, "loss": 0.922, "step": 340 }, { "epoch": 0.029181257295314324, "grad_norm": 0.541314959526062, "learning_rate": 2e-05, "loss": 0.8897, "step": 350 }, { "epoch": 0.030015007503751877, "grad_norm": 0.5001296401023865, "learning_rate": 2e-05, "loss": 0.935, "step": 360 }, { "epoch": 0.030848757712189426, "grad_norm": 0.5119391083717346, "learning_rate": 2e-05, "loss": 0.9041, "step": 370 }, { "epoch": 0.03168250792062698, "grad_norm": 0.4927831292152405, "learning_rate": 2e-05, "loss": 0.917, "step": 380 }, { "epoch": 0.03251625812906453, "grad_norm": 0.5068843364715576, "learning_rate": 2e-05, "loss": 0.8978, "step": 390 }, { "epoch": 0.03335000833750208, "grad_norm": 0.524895191192627, "learning_rate": 2e-05, "loss": 0.9182, "step": 400 }, { "epoch": 0.034183758545939635, "grad_norm": 0.5074824690818787, "learning_rate": 2e-05, "loss": 0.9265, "step": 410 }, { "epoch": 0.03501750875437719, "grad_norm": 0.4857582151889801, "learning_rate": 2e-05, "loss": 0.9585, "step": 420 }, { "epoch": 0.03585125896281474, "grad_norm": 0.5838627219200134, "learning_rate": 2e-05, "loss": 0.9099, "step": 430 }, { "epoch": 0.036685009171252295, "grad_norm": 0.4798157513141632, "learning_rate": 2e-05, "loss": 0.8595, "step": 440 }, { "epoch": 0.03751875937968985, "grad_norm": 0.4893852472305298, "learning_rate": 2e-05, "loss": 0.9249, "step": 450 }, { "epoch": 0.038352509588127394, "grad_norm": 0.4752409756183624, "learning_rate": 2e-05, "loss": 0.8971, "step": 460 }, { "epoch": 0.03918625979656495, "grad_norm": 0.5044603943824768, "learning_rate": 2e-05, "loss": 0.9007, "step": 470 }, { "epoch": 0.0400200100050025, "grad_norm": 0.4857725203037262, "learning_rate": 2e-05, "loss": 0.8884, "step": 480 }, { "epoch": 0.04085376021344005, "grad_norm": 0.5009463429450989, "learning_rate": 2e-05, "loss": 0.897, "step": 490 }, { "epoch": 0.041687510421877606, "grad_norm": 0.5030511617660522, "learning_rate": 2e-05, "loss": 0.8975, "step": 500 }, { "epoch": 0.04252126063031516, "grad_norm": 0.4980432689189911, "learning_rate": 2e-05, "loss": 0.8826, "step": 510 }, { "epoch": 0.04335501083875271, "grad_norm": 0.503282368183136, "learning_rate": 2e-05, "loss": 0.9187, "step": 520 }, { "epoch": 0.04418876104719026, "grad_norm": 0.4999975860118866, "learning_rate": 2e-05, "loss": 0.9012, "step": 530 }, { "epoch": 0.04502251125562781, "grad_norm": 0.5200240015983582, "learning_rate": 2e-05, "loss": 0.9279, "step": 540 }, { "epoch": 0.045856261464065365, "grad_norm": 0.4858852028846741, "learning_rate": 2e-05, "loss": 0.8755, "step": 550 }, { "epoch": 0.04669001167250292, "grad_norm": 0.4801354706287384, "learning_rate": 2e-05, "loss": 0.8966, "step": 560 }, { "epoch": 0.04752376188094047, "grad_norm": 0.4935963451862335, "learning_rate": 2e-05, "loss": 0.8972, "step": 570 }, { "epoch": 0.048357512089378024, "grad_norm": 0.474505752325058, "learning_rate": 2e-05, "loss": 0.9117, "step": 580 }, { "epoch": 0.04919126229781558, "grad_norm": 0.4899780750274658, "learning_rate": 2e-05, "loss": 0.9031, "step": 590 }, { "epoch": 0.05002501250625312, "grad_norm": 0.4700799286365509, "learning_rate": 2e-05, "loss": 0.8806, "step": 600 }, { "epoch": 0.050858762714690676, "grad_norm": 0.48884260654449463, "learning_rate": 2e-05, "loss": 0.9147, "step": 610 }, { "epoch": 0.05169251292312823, "grad_norm": 0.5095788836479187, "learning_rate": 2e-05, "loss": 0.913, "step": 620 }, { "epoch": 0.05252626313156578, "grad_norm": 0.4703826904296875, "learning_rate": 2e-05, "loss": 0.8676, "step": 630 }, { "epoch": 0.053360013340003336, "grad_norm": 0.47759559750556946, "learning_rate": 2e-05, "loss": 0.9071, "step": 640 }, { "epoch": 0.05419376354844089, "grad_norm": 0.4874522387981415, "learning_rate": 2e-05, "loss": 0.9025, "step": 650 }, { "epoch": 0.05502751375687844, "grad_norm": 0.5711647272109985, "learning_rate": 2e-05, "loss": 0.8959, "step": 660 }, { "epoch": 0.05586126396531599, "grad_norm": 0.467171311378479, "learning_rate": 2e-05, "loss": 0.8513, "step": 670 }, { "epoch": 0.05669501417375354, "grad_norm": 0.46761074662208557, "learning_rate": 2e-05, "loss": 0.9062, "step": 680 }, { "epoch": 0.057528764382191094, "grad_norm": 0.5580011010169983, "learning_rate": 2e-05, "loss": 0.8929, "step": 690 }, { "epoch": 0.05836251459062865, "grad_norm": 0.48909950256347656, "learning_rate": 2e-05, "loss": 0.8542, "step": 700 }, { "epoch": 0.0591962647990662, "grad_norm": 0.476967990398407, "learning_rate": 2e-05, "loss": 0.8883, "step": 710 }, { "epoch": 0.060030015007503754, "grad_norm": 0.465226948261261, "learning_rate": 2e-05, "loss": 0.8702, "step": 720 }, { "epoch": 0.06086376521594131, "grad_norm": 0.5059548616409302, "learning_rate": 2e-05, "loss": 0.9262, "step": 730 }, { "epoch": 0.06169751542437885, "grad_norm": 0.47689661383628845, "learning_rate": 2e-05, "loss": 0.8881, "step": 740 }, { "epoch": 0.06253126563281641, "grad_norm": 0.4785926043987274, "learning_rate": 2e-05, "loss": 0.8778, "step": 750 }, { "epoch": 0.06336501584125397, "grad_norm": 0.4779227375984192, "learning_rate": 2e-05, "loss": 0.8711, "step": 760 }, { "epoch": 0.06419876604969152, "grad_norm": 0.4782222509384155, "learning_rate": 2e-05, "loss": 0.8741, "step": 770 }, { "epoch": 0.06503251625812906, "grad_norm": 0.48066234588623047, "learning_rate": 2e-05, "loss": 0.8801, "step": 780 }, { "epoch": 0.06586626646656661, "grad_norm": 0.47301703691482544, "learning_rate": 2e-05, "loss": 0.883, "step": 790 }, { "epoch": 0.06670001667500416, "grad_norm": 0.5085282921791077, "learning_rate": 2e-05, "loss": 0.8742, "step": 800 }, { "epoch": 0.06753376688344172, "grad_norm": 0.45049068331718445, "learning_rate": 2e-05, "loss": 0.8756, "step": 810 }, { "epoch": 0.06836751709187927, "grad_norm": 0.49371621012687683, "learning_rate": 2e-05, "loss": 0.8805, "step": 820 }, { "epoch": 0.06920126730031682, "grad_norm": 0.4748493432998657, "learning_rate": 2e-05, "loss": 0.8604, "step": 830 }, { "epoch": 0.07003501750875438, "grad_norm": 0.4948427081108093, "learning_rate": 2e-05, "loss": 0.9014, "step": 840 }, { "epoch": 0.07086876771719193, "grad_norm": 0.4881714880466461, "learning_rate": 2e-05, "loss": 0.8926, "step": 850 }, { "epoch": 0.07170251792562948, "grad_norm": 0.48637422919273376, "learning_rate": 2e-05, "loss": 0.8852, "step": 860 }, { "epoch": 0.07253626813406704, "grad_norm": 0.47452136874198914, "learning_rate": 2e-05, "loss": 0.8837, "step": 870 }, { "epoch": 0.07337001834250459, "grad_norm": 0.5064214468002319, "learning_rate": 2e-05, "loss": 0.8451, "step": 880 }, { "epoch": 0.07420376855094214, "grad_norm": 0.5455189943313599, "learning_rate": 2e-05, "loss": 0.8783, "step": 890 }, { "epoch": 0.0750375187593797, "grad_norm": 0.4725022315979004, "learning_rate": 2e-05, "loss": 0.8772, "step": 900 }, { "epoch": 0.07587126896781725, "grad_norm": 0.49021732807159424, "learning_rate": 2e-05, "loss": 0.863, "step": 910 }, { "epoch": 0.07670501917625479, "grad_norm": 0.4547465145587921, "learning_rate": 2e-05, "loss": 0.8704, "step": 920 }, { "epoch": 0.07753876938469234, "grad_norm": 0.4670726954936981, "learning_rate": 2e-05, "loss": 0.8707, "step": 930 }, { "epoch": 0.0783725195931299, "grad_norm": 0.4348442852497101, "learning_rate": 2e-05, "loss": 0.8489, "step": 940 }, { "epoch": 0.07920626980156745, "grad_norm": 0.49067702889442444, "learning_rate": 2e-05, "loss": 0.8632, "step": 950 }, { "epoch": 0.080040020010005, "grad_norm": 0.46889927983283997, "learning_rate": 2e-05, "loss": 0.8597, "step": 960 }, { "epoch": 0.08087377021844255, "grad_norm": 0.4586699903011322, "learning_rate": 2e-05, "loss": 0.8419, "step": 970 }, { "epoch": 0.0817075204268801, "grad_norm": 0.49893268942832947, "learning_rate": 2e-05, "loss": 0.895, "step": 980 }, { "epoch": 0.08254127063531766, "grad_norm": 0.4792695939540863, "learning_rate": 2e-05, "loss": 0.8723, "step": 990 }, { "epoch": 0.08337502084375521, "grad_norm": 0.4571530818939209, "learning_rate": 2e-05, "loss": 0.8824, "step": 1000 }, { "epoch": 0.08420877105219277, "grad_norm": 0.46045640110969543, "learning_rate": 2e-05, "loss": 0.872, "step": 1010 }, { "epoch": 0.08504252126063032, "grad_norm": 0.45626309514045715, "learning_rate": 2e-05, "loss": 0.8686, "step": 1020 }, { "epoch": 0.08587627146906787, "grad_norm": 0.45131054520606995, "learning_rate": 2e-05, "loss": 0.8719, "step": 1030 }, { "epoch": 0.08671002167750542, "grad_norm": 0.48775601387023926, "learning_rate": 2e-05, "loss": 0.8844, "step": 1040 }, { "epoch": 0.08754377188594298, "grad_norm": 0.45046332478523254, "learning_rate": 2e-05, "loss": 0.8626, "step": 1050 }, { "epoch": 0.08837752209438052, "grad_norm": 0.47383394837379456, "learning_rate": 2e-05, "loss": 0.8636, "step": 1060 }, { "epoch": 0.08921127230281807, "grad_norm": 0.4502175450325012, "learning_rate": 2e-05, "loss": 0.8932, "step": 1070 }, { "epoch": 0.09004502251125562, "grad_norm": 0.4500514566898346, "learning_rate": 2e-05, "loss": 0.8616, "step": 1080 }, { "epoch": 0.09087877271969318, "grad_norm": 0.4716588854789734, "learning_rate": 2e-05, "loss": 0.889, "step": 1090 }, { "epoch": 0.09171252292813073, "grad_norm": 0.46128395199775696, "learning_rate": 2e-05, "loss": 0.8749, "step": 1100 }, { "epoch": 0.09254627313656828, "grad_norm": 0.45671573281288147, "learning_rate": 2e-05, "loss": 0.8675, "step": 1110 }, { "epoch": 0.09338002334500584, "grad_norm": 0.4433386027812958, "learning_rate": 2e-05, "loss": 0.8851, "step": 1120 }, { "epoch": 0.09421377355344339, "grad_norm": 0.47851717472076416, "learning_rate": 2e-05, "loss": 0.8543, "step": 1130 }, { "epoch": 0.09504752376188094, "grad_norm": 0.45275554060935974, "learning_rate": 2e-05, "loss": 0.8557, "step": 1140 }, { "epoch": 0.0958812739703185, "grad_norm": 0.4398982524871826, "learning_rate": 2e-05, "loss": 0.8765, "step": 1150 }, { "epoch": 0.09671502417875605, "grad_norm": 0.47268056869506836, "learning_rate": 2e-05, "loss": 0.8504, "step": 1160 }, { "epoch": 0.0975487743871936, "grad_norm": 0.5026320219039917, "learning_rate": 2e-05, "loss": 0.8582, "step": 1170 }, { "epoch": 0.09838252459563115, "grad_norm": 0.47815778851509094, "learning_rate": 2e-05, "loss": 0.8824, "step": 1180 }, { "epoch": 0.09921627480406871, "grad_norm": 0.4754660129547119, "learning_rate": 2e-05, "loss": 0.8418, "step": 1190 }, { "epoch": 0.10005002501250625, "grad_norm": 0.4670088589191437, "learning_rate": 2e-05, "loss": 0.8685, "step": 1200 }, { "epoch": 0.1008837752209438, "grad_norm": 0.445632666349411, "learning_rate": 2e-05, "loss": 0.9002, "step": 1210 }, { "epoch": 0.10171752542938135, "grad_norm": 0.4594423472881317, "learning_rate": 2e-05, "loss": 0.8335, "step": 1220 }, { "epoch": 0.1025512756378189, "grad_norm": 0.46774882078170776, "learning_rate": 2e-05, "loss": 0.8707, "step": 1230 }, { "epoch": 0.10338502584625646, "grad_norm": 0.4260616898536682, "learning_rate": 2e-05, "loss": 0.8438, "step": 1240 }, { "epoch": 0.10421877605469401, "grad_norm": 0.455828994512558, "learning_rate": 2e-05, "loss": 0.8826, "step": 1250 }, { "epoch": 0.10505252626313157, "grad_norm": 0.4610627293586731, "learning_rate": 2e-05, "loss": 0.8514, "step": 1260 }, { "epoch": 0.10588627647156912, "grad_norm": 0.44051027297973633, "learning_rate": 2e-05, "loss": 0.8328, "step": 1270 }, { "epoch": 0.10672002668000667, "grad_norm": 0.43709734082221985, "learning_rate": 2e-05, "loss": 0.8399, "step": 1280 }, { "epoch": 0.10755377688844422, "grad_norm": 0.4435420334339142, "learning_rate": 2e-05, "loss": 0.8651, "step": 1290 }, { "epoch": 0.10838752709688178, "grad_norm": 0.4506440758705139, "learning_rate": 2e-05, "loss": 0.8647, "step": 1300 }, { "epoch": 0.10922127730531933, "grad_norm": 0.4587005376815796, "learning_rate": 2e-05, "loss": 0.8565, "step": 1310 }, { "epoch": 0.11005502751375688, "grad_norm": 0.4504447281360626, "learning_rate": 2e-05, "loss": 0.8265, "step": 1320 }, { "epoch": 0.11088877772219444, "grad_norm": 0.4566003978252411, "learning_rate": 2e-05, "loss": 0.8727, "step": 1330 }, { "epoch": 0.11172252793063198, "grad_norm": 0.4230361580848694, "learning_rate": 2e-05, "loss": 0.8721, "step": 1340 }, { "epoch": 0.11255627813906953, "grad_norm": 0.43980881571769714, "learning_rate": 2e-05, "loss": 0.8323, "step": 1350 }, { "epoch": 0.11339002834750708, "grad_norm": 0.4772922396659851, "learning_rate": 2e-05, "loss": 0.8312, "step": 1360 }, { "epoch": 0.11422377855594464, "grad_norm": 0.44763606786727905, "learning_rate": 2e-05, "loss": 0.8666, "step": 1370 }, { "epoch": 0.11505752876438219, "grad_norm": 0.4610816538333893, "learning_rate": 2e-05, "loss": 0.824, "step": 1380 }, { "epoch": 0.11589127897281974, "grad_norm": 0.46850505471229553, "learning_rate": 2e-05, "loss": 0.8562, "step": 1390 }, { "epoch": 0.1167250291812573, "grad_norm": 0.44208332896232605, "learning_rate": 2e-05, "loss": 0.8283, "step": 1400 }, { "epoch": 0.11755877938969485, "grad_norm": 0.4290333390235901, "learning_rate": 2e-05, "loss": 0.8678, "step": 1410 }, { "epoch": 0.1183925295981324, "grad_norm": 0.4428878128528595, "learning_rate": 2e-05, "loss": 0.8617, "step": 1420 }, { "epoch": 0.11922627980656995, "grad_norm": 0.4282263219356537, "learning_rate": 2e-05, "loss": 0.8685, "step": 1430 }, { "epoch": 0.12006003001500751, "grad_norm": 0.45656654238700867, "learning_rate": 2e-05, "loss": 0.8432, "step": 1440 }, { "epoch": 0.12089378022344506, "grad_norm": 0.44715428352355957, "learning_rate": 2e-05, "loss": 0.8511, "step": 1450 }, { "epoch": 0.12172753043188261, "grad_norm": 0.4341605603694916, "learning_rate": 2e-05, "loss": 0.8541, "step": 1460 }, { "epoch": 0.12256128064032017, "grad_norm": 0.4401302933692932, "learning_rate": 2e-05, "loss": 0.8299, "step": 1470 }, { "epoch": 0.1233950308487577, "grad_norm": 0.4861335754394531, "learning_rate": 2e-05, "loss": 0.8838, "step": 1480 }, { "epoch": 0.12422878105719526, "grad_norm": 0.5418664813041687, "learning_rate": 2e-05, "loss": 0.8731, "step": 1490 }, { "epoch": 0.12506253126563283, "grad_norm": 0.43481454253196716, "learning_rate": 2e-05, "loss": 0.834, "step": 1500 }, { "epoch": 0.12589628147407037, "grad_norm": 0.4351367652416229, "learning_rate": 2e-05, "loss": 0.823, "step": 1510 }, { "epoch": 0.12673003168250793, "grad_norm": 0.42949992418289185, "learning_rate": 2e-05, "loss": 0.8313, "step": 1520 }, { "epoch": 0.12756378189094547, "grad_norm": 0.47757044434547424, "learning_rate": 2e-05, "loss": 0.8467, "step": 1530 }, { "epoch": 0.12839753209938304, "grad_norm": 0.44212520122528076, "learning_rate": 2e-05, "loss": 0.8179, "step": 1540 }, { "epoch": 0.12923128230782058, "grad_norm": 0.46180012822151184, "learning_rate": 2e-05, "loss": 0.8594, "step": 1550 }, { "epoch": 0.13006503251625812, "grad_norm": 0.4632825553417206, "learning_rate": 2e-05, "loss": 0.8523, "step": 1560 }, { "epoch": 0.13089878272469568, "grad_norm": 0.45442265272140503, "learning_rate": 2e-05, "loss": 0.8682, "step": 1570 }, { "epoch": 0.13173253293313322, "grad_norm": 0.42941489815711975, "learning_rate": 2e-05, "loss": 0.8648, "step": 1580 }, { "epoch": 0.1325662831415708, "grad_norm": 0.4399435520172119, "learning_rate": 2e-05, "loss": 0.8374, "step": 1590 }, { "epoch": 0.13340003335000833, "grad_norm": 0.4403332769870758, "learning_rate": 2e-05, "loss": 0.8397, "step": 1600 }, { "epoch": 0.1342337835584459, "grad_norm": 0.4336073100566864, "learning_rate": 2e-05, "loss": 0.8274, "step": 1610 }, { "epoch": 0.13506753376688344, "grad_norm": 0.4528632164001465, "learning_rate": 2e-05, "loss": 0.856, "step": 1620 }, { "epoch": 0.135901283975321, "grad_norm": 0.4432793855667114, "learning_rate": 2e-05, "loss": 0.8504, "step": 1630 }, { "epoch": 0.13673503418375854, "grad_norm": 0.41927823424339294, "learning_rate": 2e-05, "loss": 0.8275, "step": 1640 }, { "epoch": 0.1375687843921961, "grad_norm": 0.4702625274658203, "learning_rate": 2e-05, "loss": 0.8484, "step": 1650 }, { "epoch": 0.13840253460063365, "grad_norm": 0.44438639283180237, "learning_rate": 2e-05, "loss": 0.8615, "step": 1660 }, { "epoch": 0.13923628480907121, "grad_norm": 0.41862818598747253, "learning_rate": 2e-05, "loss": 0.7987, "step": 1670 }, { "epoch": 0.14007003501750875, "grad_norm": 0.4880077540874481, "learning_rate": 2e-05, "loss": 0.882, "step": 1680 }, { "epoch": 0.1409037852259463, "grad_norm": 0.4247034192085266, "learning_rate": 2e-05, "loss": 0.8713, "step": 1690 }, { "epoch": 0.14173753543438386, "grad_norm": 0.48232707381248474, "learning_rate": 2e-05, "loss": 0.8157, "step": 1700 }, { "epoch": 0.1425712856428214, "grad_norm": 0.4385620653629303, "learning_rate": 2e-05, "loss": 0.8653, "step": 1710 }, { "epoch": 0.14340503585125897, "grad_norm": 0.40841519832611084, "learning_rate": 2e-05, "loss": 0.8421, "step": 1720 }, { "epoch": 0.1442387860596965, "grad_norm": 0.4390290379524231, "learning_rate": 2e-05, "loss": 0.8325, "step": 1730 }, { "epoch": 0.14507253626813407, "grad_norm": 0.43640732765197754, "learning_rate": 2e-05, "loss": 0.8035, "step": 1740 }, { "epoch": 0.1459062864765716, "grad_norm": 0.4441671073436737, "learning_rate": 2e-05, "loss": 0.8573, "step": 1750 }, { "epoch": 0.14674003668500918, "grad_norm": 0.5069043040275574, "learning_rate": 2e-05, "loss": 0.8239, "step": 1760 }, { "epoch": 0.14757378689344672, "grad_norm": 0.4640333950519562, "learning_rate": 2e-05, "loss": 0.8502, "step": 1770 }, { "epoch": 0.14840753710188428, "grad_norm": 0.4455471634864807, "learning_rate": 2e-05, "loss": 0.8146, "step": 1780 }, { "epoch": 0.14924128731032182, "grad_norm": 0.4304905831813812, "learning_rate": 2e-05, "loss": 0.8315, "step": 1790 }, { "epoch": 0.1500750375187594, "grad_norm": 0.4412347376346588, "learning_rate": 2e-05, "loss": 0.848, "step": 1800 }, { "epoch": 0.15090878772719693, "grad_norm": 0.47276702523231506, "learning_rate": 2e-05, "loss": 0.8394, "step": 1810 }, { "epoch": 0.1517425379356345, "grad_norm": 0.4487875998020172, "learning_rate": 2e-05, "loss": 0.8238, "step": 1820 }, { "epoch": 0.15257628814407204, "grad_norm": 0.4340097904205322, "learning_rate": 2e-05, "loss": 0.8331, "step": 1830 }, { "epoch": 0.15341003835250958, "grad_norm": 0.47058507800102234, "learning_rate": 2e-05, "loss": 0.8841, "step": 1840 }, { "epoch": 0.15424378856094714, "grad_norm": 0.44329574704170227, "learning_rate": 2e-05, "loss": 0.8383, "step": 1850 }, { "epoch": 0.15507753876938468, "grad_norm": 0.4418177604675293, "learning_rate": 2e-05, "loss": 0.8502, "step": 1860 }, { "epoch": 0.15591128897782225, "grad_norm": 0.428423136472702, "learning_rate": 2e-05, "loss": 0.8119, "step": 1870 }, { "epoch": 0.1567450391862598, "grad_norm": 0.440356969833374, "learning_rate": 2e-05, "loss": 0.8329, "step": 1880 }, { "epoch": 0.15757878939469736, "grad_norm": 0.42486879229545593, "learning_rate": 2e-05, "loss": 0.8544, "step": 1890 }, { "epoch": 0.1584125396031349, "grad_norm": 0.4485068917274475, "learning_rate": 2e-05, "loss": 0.8636, "step": 1900 }, { "epoch": 0.15924628981157246, "grad_norm": 0.40998324751853943, "learning_rate": 2e-05, "loss": 0.8147, "step": 1910 }, { "epoch": 0.16008004002001, "grad_norm": 0.42555490136146545, "learning_rate": 2e-05, "loss": 0.8372, "step": 1920 }, { "epoch": 0.16091379022844757, "grad_norm": 0.4394669830799103, "learning_rate": 2e-05, "loss": 0.8044, "step": 1930 }, { "epoch": 0.1617475404368851, "grad_norm": 0.45242002606391907, "learning_rate": 2e-05, "loss": 0.846, "step": 1940 }, { "epoch": 0.16258129064532267, "grad_norm": 0.5341451168060303, "learning_rate": 2e-05, "loss": 0.819, "step": 1950 }, { "epoch": 0.1634150408537602, "grad_norm": 0.429604172706604, "learning_rate": 2e-05, "loss": 0.8567, "step": 1960 }, { "epoch": 0.16424879106219775, "grad_norm": 0.46033960580825806, "learning_rate": 2e-05, "loss": 0.8622, "step": 1970 }, { "epoch": 0.16508254127063532, "grad_norm": 0.461689293384552, "learning_rate": 2e-05, "loss": 0.8663, "step": 1980 }, { "epoch": 0.16591629147907286, "grad_norm": 0.42240920662879944, "learning_rate": 2e-05, "loss": 0.8422, "step": 1990 }, { "epoch": 0.16675004168751043, "grad_norm": 0.4205416440963745, "learning_rate": 2e-05, "loss": 0.8178, "step": 2000 }, { "epoch": 0.16758379189594796, "grad_norm": 0.46915921568870544, "learning_rate": 2e-05, "loss": 0.8677, "step": 2010 }, { "epoch": 0.16841754210438553, "grad_norm": 0.44211524724960327, "learning_rate": 2e-05, "loss": 0.8183, "step": 2020 }, { "epoch": 0.16925129231282307, "grad_norm": 0.4337581694126129, "learning_rate": 2e-05, "loss": 0.8405, "step": 2030 }, { "epoch": 0.17008504252126064, "grad_norm": 0.463716596364975, "learning_rate": 2e-05, "loss": 0.8798, "step": 2040 }, { "epoch": 0.17091879272969818, "grad_norm": 0.44323939085006714, "learning_rate": 2e-05, "loss": 0.8193, "step": 2050 }, { "epoch": 0.17175254293813574, "grad_norm": 0.46792158484458923, "learning_rate": 2e-05, "loss": 0.8516, "step": 2060 }, { "epoch": 0.17258629314657328, "grad_norm": 0.4367827773094177, "learning_rate": 2e-05, "loss": 0.8503, "step": 2070 }, { "epoch": 0.17342004335501085, "grad_norm": 0.45662805438041687, "learning_rate": 2e-05, "loss": 0.8479, "step": 2080 }, { "epoch": 0.1742537935634484, "grad_norm": 0.44357606768608093, "learning_rate": 2e-05, "loss": 0.8517, "step": 2090 }, { "epoch": 0.17508754377188596, "grad_norm": 0.4385230243206024, "learning_rate": 2e-05, "loss": 0.8418, "step": 2100 }, { "epoch": 0.1759212939803235, "grad_norm": 0.4620836079120636, "learning_rate": 2e-05, "loss": 0.8237, "step": 2110 }, { "epoch": 0.17675504418876103, "grad_norm": 0.41884246468544006, "learning_rate": 2e-05, "loss": 0.8155, "step": 2120 }, { "epoch": 0.1775887943971986, "grad_norm": 0.4452560842037201, "learning_rate": 2e-05, "loss": 0.85, "step": 2130 }, { "epoch": 0.17842254460563614, "grad_norm": 0.43115249276161194, "learning_rate": 2e-05, "loss": 0.8247, "step": 2140 }, { "epoch": 0.1792562948140737, "grad_norm": 0.41687360405921936, "learning_rate": 2e-05, "loss": 0.8233, "step": 2150 }, { "epoch": 0.18009004502251125, "grad_norm": 0.4290129542350769, "learning_rate": 2e-05, "loss": 0.8496, "step": 2160 }, { "epoch": 0.18092379523094881, "grad_norm": 0.4227672517299652, "learning_rate": 2e-05, "loss": 0.8286, "step": 2170 }, { "epoch": 0.18175754543938635, "grad_norm": 0.4615258574485779, "learning_rate": 2e-05, "loss": 0.8535, "step": 2180 }, { "epoch": 0.18259129564782392, "grad_norm": 0.40805891156196594, "learning_rate": 2e-05, "loss": 0.8636, "step": 2190 }, { "epoch": 0.18342504585626146, "grad_norm": 0.44394758343696594, "learning_rate": 2e-05, "loss": 0.8477, "step": 2200 }, { "epoch": 0.18425879606469903, "grad_norm": 0.446467787027359, "learning_rate": 2e-05, "loss": 0.868, "step": 2210 }, { "epoch": 0.18509254627313657, "grad_norm": 0.43390893936157227, "learning_rate": 2e-05, "loss": 0.8099, "step": 2220 }, { "epoch": 0.18592629648157413, "grad_norm": 0.4239795207977295, "learning_rate": 2e-05, "loss": 0.8365, "step": 2230 }, { "epoch": 0.18676004669001167, "grad_norm": 0.44403794407844543, "learning_rate": 2e-05, "loss": 0.8241, "step": 2240 }, { "epoch": 0.1875937968984492, "grad_norm": 0.44895854592323303, "learning_rate": 2e-05, "loss": 0.8658, "step": 2250 }, { "epoch": 0.18842754710688678, "grad_norm": 0.44715580344200134, "learning_rate": 2e-05, "loss": 0.8144, "step": 2260 }, { "epoch": 0.18926129731532432, "grad_norm": 0.43580275774002075, "learning_rate": 2e-05, "loss": 0.8347, "step": 2270 }, { "epoch": 0.19009504752376188, "grad_norm": 0.4666694700717926, "learning_rate": 2e-05, "loss": 0.8474, "step": 2280 }, { "epoch": 0.19092879773219942, "grad_norm": 0.4219069182872772, "learning_rate": 2e-05, "loss": 0.8425, "step": 2290 }, { "epoch": 0.191762547940637, "grad_norm": 0.43905431032180786, "learning_rate": 2e-05, "loss": 0.8549, "step": 2300 }, { "epoch": 0.19259629814907453, "grad_norm": 0.4393678307533264, "learning_rate": 2e-05, "loss": 0.8291, "step": 2310 }, { "epoch": 0.1934300483575121, "grad_norm": 0.4422663450241089, "learning_rate": 2e-05, "loss": 0.8187, "step": 2320 }, { "epoch": 0.19426379856594964, "grad_norm": 0.4156511723995209, "learning_rate": 2e-05, "loss": 0.8291, "step": 2330 }, { "epoch": 0.1950975487743872, "grad_norm": 0.4404476284980774, "learning_rate": 2e-05, "loss": 0.8287, "step": 2340 }, { "epoch": 0.19593129898282474, "grad_norm": 0.447643905878067, "learning_rate": 2e-05, "loss": 0.82, "step": 2350 }, { "epoch": 0.1967650491912623, "grad_norm": 0.4360268712043762, "learning_rate": 2e-05, "loss": 0.8253, "step": 2360 }, { "epoch": 0.19759879939969985, "grad_norm": 0.43036919832229614, "learning_rate": 2e-05, "loss": 0.7905, "step": 2370 }, { "epoch": 0.19843254960813742, "grad_norm": 0.4261600375175476, "learning_rate": 2e-05, "loss": 0.8079, "step": 2380 }, { "epoch": 0.19926629981657495, "grad_norm": 0.43624958395957947, "learning_rate": 2e-05, "loss": 0.8271, "step": 2390 }, { "epoch": 0.2001000500250125, "grad_norm": 0.44643980264663696, "learning_rate": 2e-05, "loss": 0.8472, "step": 2400 }, { "epoch": 0.20093380023345006, "grad_norm": 0.4306788146495819, "learning_rate": 2e-05, "loss": 0.8481, "step": 2410 }, { "epoch": 0.2017675504418876, "grad_norm": 0.4344717562198639, "learning_rate": 2e-05, "loss": 0.8361, "step": 2420 }, { "epoch": 0.20260130065032517, "grad_norm": 0.4240482747554779, "learning_rate": 2e-05, "loss": 0.8419, "step": 2430 }, { "epoch": 0.2034350508587627, "grad_norm": 0.43387749791145325, "learning_rate": 2e-05, "loss": 0.8388, "step": 2440 }, { "epoch": 0.20426880106720027, "grad_norm": 0.42623400688171387, "learning_rate": 2e-05, "loss": 0.8509, "step": 2450 }, { "epoch": 0.2051025512756378, "grad_norm": 0.42098426818847656, "learning_rate": 2e-05, "loss": 0.8254, "step": 2460 }, { "epoch": 0.20593630148407538, "grad_norm": 0.4316154420375824, "learning_rate": 2e-05, "loss": 0.836, "step": 2470 }, { "epoch": 0.20677005169251292, "grad_norm": 0.43836063146591187, "learning_rate": 2e-05, "loss": 0.8161, "step": 2480 }, { "epoch": 0.20760380190095049, "grad_norm": 0.4331987202167511, "learning_rate": 2e-05, "loss": 0.8358, "step": 2490 }, { "epoch": 0.20843755210938802, "grad_norm": 0.43718579411506653, "learning_rate": 2e-05, "loss": 0.8002, "step": 2500 }, { "epoch": 0.2092713023178256, "grad_norm": 0.42872241139411926, "learning_rate": 2e-05, "loss": 0.8273, "step": 2510 }, { "epoch": 0.21010505252626313, "grad_norm": 0.4349031448364258, "learning_rate": 2e-05, "loss": 0.8494, "step": 2520 }, { "epoch": 0.21093880273470067, "grad_norm": 0.4240064322948456, "learning_rate": 2e-05, "loss": 0.7908, "step": 2530 }, { "epoch": 0.21177255294313824, "grad_norm": 0.4284305274486542, "learning_rate": 2e-05, "loss": 0.838, "step": 2540 }, { "epoch": 0.21260630315157578, "grad_norm": 0.43543389439582825, "learning_rate": 1.9980979278401095e-05, "loss": 0.8221, "step": 2550 }, { "epoch": 0.21344005336001334, "grad_norm": 0.4159574806690216, "learning_rate": 1.982924955463327e-05, "loss": 0.7917, "step": 2560 }, { "epoch": 0.21427380356845088, "grad_norm": 0.41882404685020447, "learning_rate": 1.9528108298328235e-05, "loss": 0.8472, "step": 2570 }, { "epoch": 0.21510755377688845, "grad_norm": 0.5758752822875977, "learning_rate": 1.9082156473635994e-05, "loss": 0.7986, "step": 2580 }, { "epoch": 0.215941303985326, "grad_norm": 0.4210717976093292, "learning_rate": 1.8498207522139434e-05, "loss": 0.838, "step": 2590 }, { "epoch": 0.21677505419376356, "grad_norm": 0.42680999636650085, "learning_rate": 1.7785183264196977e-05, "loss": 0.8161, "step": 2600 }, { "epoch": 0.2176088044022011, "grad_norm": 0.4452272355556488, "learning_rate": 1.6953977587577846e-05, "loss": 0.8445, "step": 2610 }, { "epoch": 0.21844255461063866, "grad_norm": 0.41371989250183105, "learning_rate": 1.601729000601297e-05, "loss": 0.832, "step": 2620 }, { "epoch": 0.2192763048190762, "grad_norm": 0.44707146286964417, "learning_rate": 1.4989431630624763e-05, "loss": 0.8182, "step": 2630 }, { "epoch": 0.22011005502751377, "grad_norm": 0.40754055976867676, "learning_rate": 1.3886106518686746e-05, "loss": 0.7717, "step": 2640 }, { "epoch": 0.2209438052359513, "grad_norm": 0.4234548807144165, "learning_rate": 1.2724171740359612e-05, "loss": 0.8304, "step": 2650 }, { "epoch": 0.22177755544438887, "grad_norm": 0.43384844064712524, "learning_rate": 1.1521379829206218e-05, "loss": 0.8078, "step": 2660 }, { "epoch": 0.2226113056528264, "grad_norm": 0.42325618863105774, "learning_rate": 1.029610755143595e-05, "loss": 0.8463, "step": 2670 }, { "epoch": 0.22344505586126395, "grad_norm": 0.4216043949127197, "learning_rate": 9.067075137857348e-06, "loss": 0.8185, "step": 2680 }, { "epoch": 0.22427880606970152, "grad_norm": 0.40853047370910645, "learning_rate": 7.853060268232525e-06, "loss": 0.8129, "step": 2690 }, { "epoch": 0.22511255627813906, "grad_norm": 0.41691499948501587, "learning_rate": 6.672611177902054e-06, "loss": 0.7916, "step": 2700 }, { "epoch": 0.22594630648657663, "grad_norm": 0.41657066345214844, "learning_rate": 5.543763269959312e-06, "loss": 0.8058, "step": 2710 }, { "epoch": 0.22678005669501416, "grad_norm": 0.40979239344596863, "learning_rate": 4.483763562693867e-06, "loss": 0.8336, "step": 2720 }, { "epoch": 0.22761380690345173, "grad_norm": 0.4085537791252136, "learning_rate": 3.508807182313187e-06, "loss": 0.7919, "step": 2730 }, { "epoch": 0.22844755711188927, "grad_norm": 0.3874081075191498, "learning_rate": 2.6337899269187294e-06, "loss": 0.7977, "step": 2740 }, { "epoch": 0.22928130732032684, "grad_norm": 0.43159088492393494, "learning_rate": 1.8720806821693126e-06, "loss": 0.8041, "step": 2750 }, { "epoch": 0.23011505752876438, "grad_norm": 0.40444597601890564, "learning_rate": 1.2353171657619887e-06, "loss": 0.8059, "step": 2760 }, { "epoch": 0.23094880773720194, "grad_norm": 0.40747424960136414, "learning_rate": 7.332281214330356e-07, "loss": 0.8044, "step": 2770 }, { "epoch": 0.23178255794563948, "grad_norm": 0.4012775123119354, "learning_rate": 3.73484679074808e-07, "loss": 0.7843, "step": 2780 }, { "epoch": 0.23261630815407705, "grad_norm": 0.4051250219345093, "learning_rate": 1.61583151951702e-07, "loss": 0.8053, "step": 2790 }, { "epoch": 0.23328330832082708, "step": 2798, "total_flos": 1.1366756130249245e+19, "train_loss": 0.0737981237284706, "train_runtime": 2289.6412, "train_samples_per_second": 14.664, "train_steps_per_second": 1.222 } ], "logging_steps": 10, "max_steps": 2798, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 159, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.1366756130249245e+19, "train_batch_size": 1, "trial_name": null, "trial_params": null }
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.23328330832082708,
"eval_steps": 500,
"global_step": 2798,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008337502084375521,
"grad_norm": 13.566391944885254,
"learning_rate": 1.1061797752808989e-06,
"loss": 2.2566,
"step": 10
},
{
"epoch": 0.0016675004168751042,
"grad_norm": 2.918423652648926,
"learning_rate": 2.2241573033707866e-06,
"loss": 2.04,
"step": 20
},
{
"epoch": 0.0025012506253126563,
"grad_norm": 3.1750669479370117,
"learning_rate": 3.342134831460675e-06,
"loss": 1.8853,
"step": 30
},
{
"epoch": 0.0033350008337502085,
"grad_norm": 1.5451328754425049,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.482,
"step": 40
},
{
"epoch": 0.00416875104218776,
"grad_norm": 0.9934996366500854,
"learning_rate": 5.5780898876404495e-06,
"loss": 1.232,
"step": 50
},
{
"epoch": 0.0050025012506253125,
"grad_norm": 0.6822673082351685,
"learning_rate": 6.6960674157303374e-06,
"loss": 1.1003,
"step": 60
},
{
"epoch": 0.005836251459062865,
"grad_norm": 0.8204601407051086,
"learning_rate": 7.814044943820226e-06,
"loss": 1.0664,
"step": 70
},
{
"epoch": 0.006670001667500417,
"grad_norm": 0.5949751734733582,
"learning_rate": 8.932022471910112e-06,
"loss": 1.0583,
"step": 80
},
{
"epoch": 0.007503751875937969,
"grad_norm": 0.6005659103393555,
"learning_rate": 1.005e-05,
"loss": 0.9972,
"step": 90
},
{
"epoch": 0.00833750208437552,
"grad_norm": 0.5980632305145264,
"learning_rate": 1.1167977528089888e-05,
"loss": 0.9785,
"step": 100
},
{
"epoch": 0.009171252292813074,
"grad_norm": 0.5540244579315186,
"learning_rate": 1.2285955056179776e-05,
"loss": 1.0015,
"step": 110
},
{
"epoch": 0.010005002501250625,
"grad_norm": 0.593195378780365,
"learning_rate": 1.3403932584269664e-05,
"loss": 0.9758,
"step": 120
},
{
"epoch": 0.010838752709688178,
"grad_norm": 0.583214282989502,
"learning_rate": 1.4521910112359552e-05,
"loss": 0.9762,