Invalid JSON: Unexpected token 'N', ..."ad_norm": NaN,
"... is not valid JSON
| { | |
| "best_global_step": 79000, | |
| "best_metric": 3.530731439590454, | |
| "best_model_checkpoint": "/scratch/cl5625/exceptions/models/swap_take_to_drop_1032/checkpoint-40000", | |
| "epoch": 28.812761993479274, | |
| "eval_steps": 1000, | |
| "global_step": 99000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014555193292966931, | |
| "grad_norm": 1.1135019063949585, | |
| "learning_rate": 0.000294, | |
| "loss": 8.4764, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.029110386585933862, | |
| "grad_norm": 0.6933409571647644, | |
| "learning_rate": 0.0005939999999999999, | |
| "loss": 6.7367, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04366557987890079, | |
| "grad_norm": 0.4633563756942749, | |
| "learning_rate": 0.0005998287711124053, | |
| "loss": 6.349, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.058220773171867725, | |
| "grad_norm": 0.647269606590271, | |
| "learning_rate": 0.000599654047757717, | |
| "loss": 6.14, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07277596646483465, | |
| "grad_norm": 0.5047195553779602, | |
| "learning_rate": 0.0005994793244030285, | |
| "loss": 6.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08733115975780158, | |
| "grad_norm": 0.4613751173019409, | |
| "learning_rate": 0.00059930460104834, | |
| "loss": 5.8753, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10188635305076851, | |
| "grad_norm": 0.518086850643158, | |
| "learning_rate": 0.0005991298776936517, | |
| "loss": 5.7543, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.11644154634373545, | |
| "grad_norm": 0.4745529890060425, | |
| "learning_rate": 0.0005989551543389632, | |
| "loss": 5.6361, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1309967396367024, | |
| "grad_norm": 0.4274802505970001, | |
| "learning_rate": 0.0005987804309842748, | |
| "loss": 5.5354, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1455519329296693, | |
| "grad_norm": 0.5071395039558411, | |
| "learning_rate": 0.0005986057076295864, | |
| "loss": 5.4332, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.16010712622263623, | |
| "grad_norm": 0.6902869939804077, | |
| "learning_rate": 0.0005984309842748981, | |
| "loss": 5.3484, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.17466231951560315, | |
| "grad_norm": 0.41560250520706177, | |
| "learning_rate": 0.0005982562609202096, | |
| "loss": 5.282, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1892175128085701, | |
| "grad_norm": 0.39118432998657227, | |
| "learning_rate": 0.0005980815375655212, | |
| "loss": 5.2064, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.20377270610153703, | |
| "grad_norm": 0.41390764713287354, | |
| "learning_rate": 0.0005979068142108328, | |
| "loss": 5.1458, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.21832789939450395, | |
| "grad_norm": 0.49317467212677, | |
| "learning_rate": 0.0005977320908561445, | |
| "loss": 5.0822, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2328830926874709, | |
| "grad_norm": 0.43355047702789307, | |
| "learning_rate": 0.000597557367501456, | |
| "loss": 5.0452, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24743828598043782, | |
| "grad_norm": 0.3977106511592865, | |
| "learning_rate": 0.0005973826441467675, | |
| "loss": 4.9823, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.2619934792734048, | |
| "grad_norm": 0.42605483531951904, | |
| "learning_rate": 0.0005972079207920792, | |
| "loss": 4.922, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.27654867256637167, | |
| "grad_norm": 0.4037967026233673, | |
| "learning_rate": 0.0005970331974373907, | |
| "loss": 4.9038, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.2911038658593386, | |
| "grad_norm": 0.5289016962051392, | |
| "learning_rate": 0.0005968584740827023, | |
| "loss": 4.8398, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2911038658593386, | |
| "eval_accuracy": 0.2531515828401202, | |
| "eval_loss": 4.767043113708496, | |
| "eval_runtime": 53.2198, | |
| "eval_samples_per_second": 312.872, | |
| "eval_steps_per_second": 19.56, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.30565905915230557, | |
| "grad_norm": 0.4042770266532898, | |
| "learning_rate": 0.0005966837507280139, | |
| "loss": 4.7938, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.32021425244527246, | |
| "grad_norm": 0.7539849281311035, | |
| "learning_rate": 0.0005965090273733256, | |
| "loss": 4.7414, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3347694457382394, | |
| "grad_norm": 0.4608651399612427, | |
| "learning_rate": 0.0005963343040186371, | |
| "loss": 4.7108, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.3493246390312063, | |
| "grad_norm": 0.5037618279457092, | |
| "learning_rate": 0.0005961595806639486, | |
| "loss": 4.6742, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.36387983232417326, | |
| "grad_norm": 0.4513559937477112, | |
| "learning_rate": 0.0005959848573092603, | |
| "loss": 4.6444, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.3784350256171402, | |
| "grad_norm": 0.43533873558044434, | |
| "learning_rate": 0.0005958101339545718, | |
| "loss": 4.6017, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.3929902189101071, | |
| "grad_norm": 0.41644278168678284, | |
| "learning_rate": 0.0005956354105998835, | |
| "loss": 4.5795, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.40754541220307405, | |
| "grad_norm": 0.4235057532787323, | |
| "learning_rate": 0.000595460687245195, | |
| "loss": 4.5547, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.422100605496041, | |
| "grad_norm": 0.45937755703926086, | |
| "learning_rate": 0.0005952859638905067, | |
| "loss": 4.5365, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.4366557987890079, | |
| "grad_norm": 0.4133026599884033, | |
| "learning_rate": 0.0005951112405358182, | |
| "loss": 4.5183, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.45121099208197485, | |
| "grad_norm": 0.39966627955436707, | |
| "learning_rate": 0.0005949365171811299, | |
| "loss": 4.4827, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.4657661853749418, | |
| "grad_norm": 0.44825735688209534, | |
| "learning_rate": 0.0005947617938264414, | |
| "loss": 4.4729, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4803213786679087, | |
| "grad_norm": 0.3955637514591217, | |
| "learning_rate": 0.000594587070471753, | |
| "loss": 4.4521, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.49487657196087564, | |
| "grad_norm": 0.4014606773853302, | |
| "learning_rate": 0.0005944123471170646, | |
| "loss": 4.4229, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.5094317652538426, | |
| "grad_norm": 0.3664035499095917, | |
| "learning_rate": 0.0005942376237623762, | |
| "loss": 4.4283, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.5239869585468095, | |
| "grad_norm": 0.3934309184551239, | |
| "learning_rate": 0.0005940629004076878, | |
| "loss": 4.3938, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5385421518397764, | |
| "grad_norm": 0.3886612355709076, | |
| "learning_rate": 0.0005938881770529993, | |
| "loss": 4.3828, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5530973451327433, | |
| "grad_norm": 0.37885406613349915, | |
| "learning_rate": 0.000593713453698311, | |
| "loss": 4.3619, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5676525384257103, | |
| "grad_norm": 0.4075015187263489, | |
| "learning_rate": 0.0005935387303436226, | |
| "loss": 4.3443, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.5822077317186772, | |
| "grad_norm": 0.3959999978542328, | |
| "learning_rate": 0.0005933640069889342, | |
| "loss": 4.347, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5822077317186772, | |
| "eval_accuracy": 0.2993617914734175, | |
| "eval_loss": 4.282224178314209, | |
| "eval_runtime": 53.4073, | |
| "eval_samples_per_second": 311.774, | |
| "eval_steps_per_second": 19.492, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5967629250116442, | |
| "grad_norm": 0.373216450214386, | |
| "learning_rate": 0.0005931892836342457, | |
| "loss": 4.33, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.6113181183046111, | |
| "grad_norm": 0.4129070043563843, | |
| "learning_rate": 0.0005930145602795573, | |
| "loss": 4.3078, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.625873311597578, | |
| "grad_norm": 0.41189518570899963, | |
| "learning_rate": 0.000592839836924869, | |
| "loss": 4.2989, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.6404285048905449, | |
| "grad_norm": 0.40223053097724915, | |
| "learning_rate": 0.0005926651135701805, | |
| "loss": 4.2943, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6549836981835119, | |
| "grad_norm": 0.36179110407829285, | |
| "learning_rate": 0.0005924903902154921, | |
| "loss": 4.2864, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.6695388914764788, | |
| "grad_norm": 0.36739879846572876, | |
| "learning_rate": 0.0005923156668608037, | |
| "loss": 4.2701, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6840940847694458, | |
| "grad_norm": 0.416104793548584, | |
| "learning_rate": 0.0005921409435061153, | |
| "loss": 4.2687, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6986492780624126, | |
| "grad_norm": 0.3904774487018585, | |
| "learning_rate": 0.0005919662201514268, | |
| "loss": 4.242, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7132044713553796, | |
| "grad_norm": 0.3793289363384247, | |
| "learning_rate": 0.0005917914967967384, | |
| "loss": 4.2393, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.7277596646483465, | |
| "grad_norm": 0.3648878037929535, | |
| "learning_rate": 0.0005916167734420501, | |
| "loss": 4.2325, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.7423148579413135, | |
| "grad_norm": 0.3943111002445221, | |
| "learning_rate": 0.0005914420500873616, | |
| "loss": 4.2085, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.7568700512342804, | |
| "grad_norm": 0.4353366494178772, | |
| "learning_rate": 0.0005912673267326732, | |
| "loss": 4.208, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7714252445272474, | |
| "grad_norm": 0.3554055392742157, | |
| "learning_rate": 0.0005910926033779848, | |
| "loss": 4.2018, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.7859804378202142, | |
| "grad_norm": 0.3675667941570282, | |
| "learning_rate": 0.0005909178800232964, | |
| "loss": 4.1968, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.8005356311131812, | |
| "grad_norm": 0.3496781587600708, | |
| "learning_rate": 0.000590743156668608, | |
| "loss": 4.1826, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.8150908244061481, | |
| "grad_norm": 0.41734233498573303, | |
| "learning_rate": 0.0005905684333139196, | |
| "loss": 4.175, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.8296460176991151, | |
| "grad_norm": 0.3665666878223419, | |
| "learning_rate": 0.0005903937099592312, | |
| "loss": 4.1687, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.844201210992082, | |
| "grad_norm": 0.37103888392448425, | |
| "learning_rate": 0.0005902189866045427, | |
| "loss": 4.1732, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.858756404285049, | |
| "grad_norm": 0.35831448435783386, | |
| "learning_rate": 0.0005900442632498543, | |
| "loss": 4.155, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.8733115975780158, | |
| "grad_norm": 0.344338595867157, | |
| "learning_rate": 0.0005898695398951659, | |
| "loss": 4.1504, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8733115975780158, | |
| "eval_accuracy": 0.3155376621538924, | |
| "eval_loss": 4.096097946166992, | |
| "eval_runtime": 53.5495, | |
| "eval_samples_per_second": 310.946, | |
| "eval_steps_per_second": 19.44, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8878667908709827, | |
| "grad_norm": 0.3826272785663605, | |
| "learning_rate": 0.0005896948165404776, | |
| "loss": 4.1384, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.9024219841639497, | |
| "grad_norm": 0.3648945391178131, | |
| "learning_rate": 0.0005895200931857891, | |
| "loss": 4.154, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.9169771774569166, | |
| "grad_norm": 0.38487711548805237, | |
| "learning_rate": 0.0005893453698311007, | |
| "loss": 4.1285, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.9315323707498836, | |
| "grad_norm": 0.4140414893627167, | |
| "learning_rate": 0.0005891706464764123, | |
| "loss": 4.1234, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.9460875640428504, | |
| "grad_norm": 0.3520990014076233, | |
| "learning_rate": 0.0005889959231217238, | |
| "loss": 4.11, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.9606427573358174, | |
| "grad_norm": 0.3490293622016907, | |
| "learning_rate": 0.0005888211997670355, | |
| "loss": 4.0953, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9751979506287843, | |
| "grad_norm": 0.33983540534973145, | |
| "learning_rate": 0.000588646476412347, | |
| "loss": 4.0917, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.9897531439217513, | |
| "grad_norm": 0.34323808550834656, | |
| "learning_rate": 0.0005884717530576587, | |
| "loss": 4.0894, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.0040754541220307, | |
| "grad_norm": 0.3433239459991455, | |
| "learning_rate": 0.0005882970297029702, | |
| "loss": 4.08, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.0186306474149978, | |
| "grad_norm": 0.33468693494796753, | |
| "learning_rate": 0.0005881223063482818, | |
| "loss": 4.0124, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.0331858407079646, | |
| "grad_norm": 0.3436813950538635, | |
| "learning_rate": 0.0005879475829935934, | |
| "loss": 4.0179, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.0477410340009314, | |
| "grad_norm": 0.3461218774318695, | |
| "learning_rate": 0.0005877728596389051, | |
| "loss": 4.0222, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.0622962272938985, | |
| "grad_norm": 0.37807410955429077, | |
| "learning_rate": 0.0005875981362842166, | |
| "loss": 4.0145, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.0768514205868653, | |
| "grad_norm": 0.349275141954422, | |
| "learning_rate": 0.0005874234129295281, | |
| "loss": 4.0082, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.0914066138798324, | |
| "grad_norm": 0.35138973593711853, | |
| "learning_rate": 0.0005872486895748398, | |
| "loss": 3.9918, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.1059618071727992, | |
| "grad_norm": 0.3480738401412964, | |
| "learning_rate": 0.0005870739662201513, | |
| "loss": 4.0096, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.120517000465766, | |
| "grad_norm": 0.33315569162368774, | |
| "learning_rate": 0.000586899242865463, | |
| "loss": 4.0107, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.1350721937587331, | |
| "grad_norm": 0.36737823486328125, | |
| "learning_rate": 0.0005867245195107746, | |
| "loss": 3.9925, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.1496273870517, | |
| "grad_norm": 0.32605332136154175, | |
| "learning_rate": 0.0005865497961560862, | |
| "loss": 3.9921, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.164182580344667, | |
| "grad_norm": 0.3551664650440216, | |
| "learning_rate": 0.0005863750728013977, | |
| "loss": 3.9818, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.164182580344667, | |
| "eval_accuracy": 0.32474804202447366, | |
| "eval_loss": 3.9911961555480957, | |
| "eval_runtime": 53.3912, | |
| "eval_samples_per_second": 311.868, | |
| "eval_steps_per_second": 19.498, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.1787377736376339, | |
| "grad_norm": 0.3581082224845886, | |
| "learning_rate": 0.0005862003494467094, | |
| "loss": 3.9909, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.193292966930601, | |
| "grad_norm": 0.31523895263671875, | |
| "learning_rate": 0.0005860256260920209, | |
| "loss": 3.9883, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.2078481602235678, | |
| "grad_norm": 0.35966089367866516, | |
| "learning_rate": 0.0005858509027373325, | |
| "loss": 3.9796, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.2224033535165346, | |
| "grad_norm": 0.36373308300971985, | |
| "learning_rate": 0.0005856761793826441, | |
| "loss": 3.9772, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.2369585468095017, | |
| "grad_norm": 0.33591705560684204, | |
| "learning_rate": 0.0005855014560279557, | |
| "loss": 3.9928, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.2515137401024685, | |
| "grad_norm": 0.3368073105812073, | |
| "learning_rate": 0.0005853267326732673, | |
| "loss": 3.9775, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.2660689333954354, | |
| "grad_norm": 0.3425745666027069, | |
| "learning_rate": 0.0005851520093185788, | |
| "loss": 3.9661, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.2806241266884024, | |
| "grad_norm": 0.34713825583457947, | |
| "learning_rate": 0.0005849772859638905, | |
| "loss": 3.9658, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.2951793199813695, | |
| "grad_norm": 0.3460465967655182, | |
| "learning_rate": 0.0005848025626092021, | |
| "loss": 3.9631, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.3097345132743363, | |
| "grad_norm": 0.35283970832824707, | |
| "learning_rate": 0.0005846278392545136, | |
| "loss": 3.9524, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.3242897065673032, | |
| "grad_norm": 0.32421359419822693, | |
| "learning_rate": 0.0005844531158998252, | |
| "loss": 3.9656, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.3388448998602702, | |
| "grad_norm": 0.33419591188430786, | |
| "learning_rate": 0.0005842783925451368, | |
| "loss": 3.9502, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.353400093153237, | |
| "grad_norm": 0.36504805088043213, | |
| "learning_rate": 0.0005841036691904484, | |
| "loss": 3.9616, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.367955286446204, | |
| "grad_norm": 0.32445722818374634, | |
| "learning_rate": 0.00058392894583576, | |
| "loss": 3.9467, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.382510479739171, | |
| "grad_norm": 0.3311734199523926, | |
| "learning_rate": 0.0005837542224810716, | |
| "loss": 3.9581, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.3970656730321378, | |
| "grad_norm": 0.3372970223426819, | |
| "learning_rate": 0.0005835794991263832, | |
| "loss": 3.9302, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.4116208663251049, | |
| "grad_norm": 0.3580183982849121, | |
| "learning_rate": 0.0005834047757716948, | |
| "loss": 3.938, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.4261760596180717, | |
| "grad_norm": 0.3132576048374176, | |
| "learning_rate": 0.0005832300524170063, | |
| "loss": 3.9369, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.4407312529110388, | |
| "grad_norm": 0.31795844435691833, | |
| "learning_rate": 0.0005830553290623179, | |
| "loss": 3.9343, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.4552864462040056, | |
| "grad_norm": 0.3307916820049286, | |
| "learning_rate": 0.0005828806057076296, | |
| "loss": 3.9237, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.4552864462040056, | |
| "eval_accuracy": 0.33100284521853673, | |
| "eval_loss": 3.916764974594116, | |
| "eval_runtime": 53.4277, | |
| "eval_samples_per_second": 311.655, | |
| "eval_steps_per_second": 19.484, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.4698416394969724, | |
| "grad_norm": 0.35131537914276123, | |
| "learning_rate": 0.0005827058823529411, | |
| "loss": 3.9271, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.4843968327899395, | |
| "grad_norm": 0.3273395895957947, | |
| "learning_rate": 0.0005825311589982527, | |
| "loss": 3.9251, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.4989520260829063, | |
| "grad_norm": 0.33433112502098083, | |
| "learning_rate": 0.0005823564356435643, | |
| "loss": 3.9229, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.5135072193758732, | |
| "grad_norm": 0.32034412026405334, | |
| "learning_rate": 0.0005821817122888759, | |
| "loss": 3.9149, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.5280624126688402, | |
| "grad_norm": 0.3438781499862671, | |
| "learning_rate": 0.0005820069889341875, | |
| "loss": 3.9214, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.5426176059618073, | |
| "grad_norm": 0.35249361395835876, | |
| "learning_rate": 0.000581832265579499, | |
| "loss": 3.9108, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.5571727992547741, | |
| "grad_norm": 0.3303695023059845, | |
| "learning_rate": 0.0005816575422248107, | |
| "loss": 3.9238, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 1.571727992547741, | |
| "grad_norm": 0.35583415627479553, | |
| "learning_rate": 0.0005814828188701222, | |
| "loss": 3.9096, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.586283185840708, | |
| "grad_norm": 0.3421223759651184, | |
| "learning_rate": 0.0005813080955154338, | |
| "loss": 3.9178, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 1.6008383791336749, | |
| "grad_norm": 0.3205304741859436, | |
| "learning_rate": 0.0005811333721607454, | |
| "loss": 3.9066, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.6153935724266417, | |
| "grad_norm": 0.35243138670921326, | |
| "learning_rate": 0.0005809586488060571, | |
| "loss": 3.9071, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 1.6299487657196088, | |
| "grad_norm": 0.3527873754501343, | |
| "learning_rate": 0.0005807839254513686, | |
| "loss": 3.9092, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.6445039590125758, | |
| "grad_norm": 0.31976228952407837, | |
| "learning_rate": 0.0005806092020966802, | |
| "loss": 3.893, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 1.6590591523055425, | |
| "grad_norm": 0.3309817314147949, | |
| "learning_rate": 0.0005804344787419918, | |
| "loss": 3.8945, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.6736143455985095, | |
| "grad_norm": 0.30710405111312866, | |
| "learning_rate": 0.0005802597553873033, | |
| "loss": 3.8917, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 1.6881695388914766, | |
| "grad_norm": 0.32099786400794983, | |
| "learning_rate": 0.000580085032032615, | |
| "loss": 3.8907, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.7027247321844434, | |
| "grad_norm": 0.3333797752857208, | |
| "learning_rate": 0.0005799103086779265, | |
| "loss": 3.8932, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 1.7172799254774103, | |
| "grad_norm": 0.3453357219696045, | |
| "learning_rate": 0.0005797355853232382, | |
| "loss": 3.8748, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.7318351187703773, | |
| "grad_norm": 0.3047594726085663, | |
| "learning_rate": 0.0005795608619685497, | |
| "loss": 3.8837, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 1.7463903120633442, | |
| "grad_norm": 0.3399483859539032, | |
| "learning_rate": 0.0005793861386138614, | |
| "loss": 3.8777, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.7463903120633442, | |
| "eval_accuracy": 0.33710321753328754, | |
| "eval_loss": 3.856112480163574, | |
| "eval_runtime": 53.2061, | |
| "eval_samples_per_second": 312.953, | |
| "eval_steps_per_second": 19.565, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.760945505356311, | |
| "grad_norm": 0.3243379592895508, | |
| "learning_rate": 0.0005792114152591729, | |
| "loss": 3.8901, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 1.775500698649278, | |
| "grad_norm": 0.3042827844619751, | |
| "learning_rate": 0.0005790366919044846, | |
| "loss": 3.8765, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.7900558919422451, | |
| "grad_norm": 0.3178008198738098, | |
| "learning_rate": 0.0005788619685497961, | |
| "loss": 3.8778, | |
| "step": 6150 | |
| }, | |
| { | |
| "epoch": 1.804611085235212, | |
| "grad_norm": 0.31493183970451355, | |
| "learning_rate": 0.0005786872451951077, | |
| "loss": 3.8646, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.8191662785281788, | |
| "grad_norm": 0.34667932987213135, | |
| "learning_rate": 0.0005785125218404193, | |
| "loss": 3.8665, | |
| "step": 6250 | |
| }, | |
| { | |
| "epoch": 1.8337214718211459, | |
| "grad_norm": 0.3208017647266388, | |
| "learning_rate": 0.0005783377984857308, | |
| "loss": 3.8685, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.8482766651141127, | |
| "grad_norm": 0.3304716944694519, | |
| "learning_rate": 0.0005781630751310425, | |
| "loss": 3.8705, | |
| "step": 6350 | |
| }, | |
| { | |
| "epoch": 1.8628318584070795, | |
| "grad_norm": 0.3251796066761017, | |
| "learning_rate": 0.0005779883517763541, | |
| "loss": 3.8577, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.8773870517000466, | |
| "grad_norm": 0.30464258790016174, | |
| "learning_rate": 0.0005778136284216657, | |
| "loss": 3.8567, | |
| "step": 6450 | |
| }, | |
| { | |
| "epoch": 1.8919422449930137, | |
| "grad_norm": 0.3136630952358246, | |
| "learning_rate": 0.0005776389050669772, | |
| "loss": 3.8521, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.9064974382859803, | |
| "grad_norm": 0.37593430280685425, | |
| "learning_rate": 0.0005774641817122889, | |
| "loss": 3.8602, | |
| "step": 6550 | |
| }, | |
| { | |
| "epoch": 1.9210526315789473, | |
| "grad_norm": 0.30204054713249207, | |
| "learning_rate": 0.0005772894583576004, | |
| "loss": 3.8508, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.9356078248719144, | |
| "grad_norm": 0.3180621564388275, | |
| "learning_rate": 0.000577114735002912, | |
| "loss": 3.8565, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 1.9501630181648812, | |
| "grad_norm": 0.3116956353187561, | |
| "learning_rate": 0.0005769400116482236, | |
| "loss": 3.8614, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.964718211457848, | |
| "grad_norm": 0.3198639154434204, | |
| "learning_rate": 0.0005767652882935352, | |
| "loss": 3.8428, | |
| "step": 6750 | |
| }, | |
| { | |
| "epoch": 1.9792734047508151, | |
| "grad_norm": 0.33717164397239685, | |
| "learning_rate": 0.0005765905649388468, | |
| "loss": 3.8632, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 1.993828598043782, | |
| "grad_norm": 0.3187156617641449, | |
| "learning_rate": 0.0005764158415841583, | |
| "loss": 3.844, | |
| "step": 6850 | |
| }, | |
| { | |
| "epoch": 2.0081509082440614, | |
| "grad_norm": 0.29923951625823975, | |
| "learning_rate": 0.00057624111822947, | |
| "loss": 3.8059, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.0227061015370285, | |
| "grad_norm": 0.307099312543869, | |
| "learning_rate": 0.0005760663948747816, | |
| "loss": 3.7508, | |
| "step": 6950 | |
| }, | |
| { | |
| "epoch": 2.0372612948299955, | |
| "grad_norm": 0.32064998149871826, | |
| "learning_rate": 0.0005758916715200931, | |
| "loss": 3.7473, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.0372612948299955, | |
| "eval_accuracy": 0.3410239284418547, | |
| "eval_loss": 3.816014289855957, | |
| "eval_runtime": 53.3981, | |
| "eval_samples_per_second": 311.828, | |
| "eval_steps_per_second": 19.495, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.051816488122962, | |
| "grad_norm": 0.319642573595047, | |
| "learning_rate": 0.0005757169481654047, | |
| "loss": 3.7386, | |
| "step": 7050 | |
| }, | |
| { | |
| "epoch": 2.066371681415929, | |
| "grad_norm": 0.29956769943237305, | |
| "learning_rate": 0.0005755422248107163, | |
| "loss": 3.7584, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.0809268747088963, | |
| "grad_norm": 0.308060884475708, | |
| "learning_rate": 0.0005753675014560279, | |
| "loss": 3.7516, | |
| "step": 7150 | |
| }, | |
| { | |
| "epoch": 2.095482068001863, | |
| "grad_norm": 0.3130384087562561, | |
| "learning_rate": 0.0005751927781013395, | |
| "loss": 3.7697, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.11003726129483, | |
| "grad_norm": 0.32310935854911804, | |
| "learning_rate": 0.0005750180547466511, | |
| "loss": 3.7534, | |
| "step": 7250 | |
| }, | |
| { | |
| "epoch": 2.124592454587797, | |
| "grad_norm": 0.32767730951309204, | |
| "learning_rate": 0.0005748433313919627, | |
| "loss": 3.7626, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.139147647880764, | |
| "grad_norm": 0.3242262899875641, | |
| "learning_rate": 0.0005746686080372743, | |
| "loss": 3.7529, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 2.1537028411737307, | |
| "grad_norm": 0.3297455608844757, | |
| "learning_rate": 0.0005744938846825858, | |
| "loss": 3.7501, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.1682580344666977, | |
| "grad_norm": 0.31598904728889465, | |
| "learning_rate": 0.0005743191613278974, | |
| "loss": 3.7454, | |
| "step": 7450 | |
| }, | |
| { | |
| "epoch": 2.182813227759665, | |
| "grad_norm": 0.301129013299942, | |
| "learning_rate": 0.0005741444379732091, | |
| "loss": 3.7606, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.1973684210526314, | |
| "grad_norm": 0.30926215648651123, | |
| "learning_rate": 0.0005739697146185206, | |
| "loss": 3.7597, | |
| "step": 7550 | |
| }, | |
| { | |
| "epoch": 2.2119236143455985, | |
| "grad_norm": 0.31310802698135376, | |
| "learning_rate": 0.0005737949912638322, | |
| "loss": 3.7517, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.2264788076385655, | |
| "grad_norm": 0.32444682717323303, | |
| "learning_rate": 0.0005736202679091438, | |
| "loss": 3.7452, | |
| "step": 7650 | |
| }, | |
| { | |
| "epoch": 2.241034000931532, | |
| "grad_norm": 0.3288429081439972, | |
| "learning_rate": 0.0005734455445544554, | |
| "loss": 3.7406, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 2.255589194224499, | |
| "grad_norm": 0.3042623996734619, | |
| "learning_rate": 0.000573270821199767, | |
| "loss": 3.7574, | |
| "step": 7750 | |
| }, | |
| { | |
| "epoch": 2.2701443875174663, | |
| "grad_norm": 0.3354697525501251, | |
| "learning_rate": 0.0005730960978450785, | |
| "loss": 3.7503, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 2.2846995808104333, | |
| "grad_norm": 0.31058791279792786, | |
| "learning_rate": 0.0005729213744903902, | |
| "loss": 3.7512, | |
| "step": 7850 | |
| }, | |
| { | |
| "epoch": 2.2992547741034, | |
| "grad_norm": 0.3280554413795471, | |
| "learning_rate": 0.0005727466511357017, | |
| "loss": 3.7531, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 2.313809967396367, | |
| "grad_norm": 0.3011781871318817, | |
| "learning_rate": 0.0005725719277810134, | |
| "loss": 3.7561, | |
| "step": 7950 | |
| }, | |
| { | |
| "epoch": 2.328365160689334, | |
| "grad_norm": 0.32062652707099915, | |
| "learning_rate": 0.0005723972044263249, | |
| "loss": 3.7551, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.328365160689334, | |
| "eval_accuracy": 0.34429306796921394, | |
| "eval_loss": 3.7835283279418945, | |
| "eval_runtime": 53.2746, | |
| "eval_samples_per_second": 312.551, | |
| "eval_steps_per_second": 19.54, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.3429203539823007, | |
| "grad_norm": 0.3354705572128296, | |
| "learning_rate": 0.0005722224810716366, | |
| "loss": 3.7464, | |
| "step": 8050 | |
| }, | |
| { | |
| "epoch": 2.3574755472752678, | |
| "grad_norm": 0.31234511733055115, | |
| "learning_rate": 0.0005720477577169481, | |
| "loss": 3.757, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 2.372030740568235, | |
| "grad_norm": 0.3153094947338104, | |
| "learning_rate": 0.0005718730343622598, | |
| "loss": 3.7537, | |
| "step": 8150 | |
| }, | |
| { | |
| "epoch": 2.386585933861202, | |
| "grad_norm": 0.31794092059135437, | |
| "learning_rate": 0.0005716983110075713, | |
| "loss": 3.7562, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.4011411271541685, | |
| "grad_norm": 0.3287888467311859, | |
| "learning_rate": 0.0005715235876528828, | |
| "loss": 3.7457, | |
| "step": 8250 | |
| }, | |
| { | |
| "epoch": 2.4156963204471356, | |
| "grad_norm": 0.32458144426345825, | |
| "learning_rate": 0.0005713488642981945, | |
| "loss": 3.761, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 2.4302515137401026, | |
| "grad_norm": 0.32528385519981384, | |
| "learning_rate": 0.0005711741409435061, | |
| "loss": 3.7643, | |
| "step": 8350 | |
| }, | |
| { | |
| "epoch": 2.4448067070330692, | |
| "grad_norm": 0.31060904264450073, | |
| "learning_rate": 0.0005709994175888177, | |
| "loss": 3.7441, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.4593619003260363, | |
| "grad_norm": 0.3071330189704895, | |
| "learning_rate": 0.0005708246942341292, | |
| "loss": 3.7408, | |
| "step": 8450 | |
| }, | |
| { | |
| "epoch": 2.4739170936190034, | |
| "grad_norm": 0.32358062267303467, | |
| "learning_rate": 0.0005706499708794409, | |
| "loss": 3.7444, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.4884722869119704, | |
| "grad_norm": 0.3185156285762787, | |
| "learning_rate": 0.0005704752475247524, | |
| "loss": 3.7316, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 2.503027480204937, | |
| "grad_norm": 0.3113254904747009, | |
| "learning_rate": 0.0005703005241700641, | |
| "loss": 3.7485, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.517582673497904, | |
| "grad_norm": 0.29909488558769226, | |
| "learning_rate": 0.0005701258008153756, | |
| "loss": 3.7457, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 2.5321378667908707, | |
| "grad_norm": 0.31834450364112854, | |
| "learning_rate": 0.0005699510774606872, | |
| "loss": 3.741, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 2.546693060083838, | |
| "grad_norm": 0.30466559529304504, | |
| "learning_rate": 0.0005697763541059988, | |
| "loss": 3.7541, | |
| "step": 8750 | |
| }, | |
| { | |
| "epoch": 2.561248253376805, | |
| "grad_norm": 0.3079618811607361, | |
| "learning_rate": 0.0005696016307513103, | |
| "loss": 3.738, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.575803446669772, | |
| "grad_norm": 0.3128642439842224, | |
| "learning_rate": 0.000569426907396622, | |
| "loss": 3.7446, | |
| "step": 8850 | |
| }, | |
| { | |
| "epoch": 2.590358639962739, | |
| "grad_norm": 0.2976256012916565, | |
| "learning_rate": 0.0005692521840419336, | |
| "loss": 3.7364, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 2.6049138332557056, | |
| "grad_norm": 0.296798974275589, | |
| "learning_rate": 0.0005690774606872452, | |
| "loss": 3.7438, | |
| "step": 8950 | |
| }, | |
| { | |
| "epoch": 2.6194690265486726, | |
| "grad_norm": 0.3170147240161896, | |
| "learning_rate": 0.0005689027373325567, | |
| "loss": 3.7385, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.6194690265486726, | |
| "eval_accuracy": 0.34704214917012205, | |
| "eval_loss": 3.7561147212982178, | |
| "eval_runtime": 53.3737, | |
| "eval_samples_per_second": 311.97, | |
| "eval_steps_per_second": 19.504, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.6340242198416393, | |
| "grad_norm": 0.32044902443885803, | |
| "learning_rate": 0.0005687280139778683, | |
| "loss": 3.7394, | |
| "step": 9050 | |
| }, | |
| { | |
| "epoch": 2.6485794131346063, | |
| "grad_norm": 0.3042409121990204, | |
| "learning_rate": 0.0005685532906231799, | |
| "loss": 3.7462, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 2.6631346064275734, | |
| "grad_norm": 0.2910836637020111, | |
| "learning_rate": 0.0005683785672684915, | |
| "loss": 3.727, | |
| "step": 9150 | |
| }, | |
| { | |
| "epoch": 2.6776897997205404, | |
| "grad_norm": 0.3197953701019287, | |
| "learning_rate": 0.0005682038439138031, | |
| "loss": 3.736, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.692244993013507, | |
| "grad_norm": 0.3052990138530731, | |
| "learning_rate": 0.0005680291205591147, | |
| "loss": 3.7582, | |
| "step": 9250 | |
| }, | |
| { | |
| "epoch": 2.706800186306474, | |
| "grad_norm": 0.3056725561618805, | |
| "learning_rate": 0.0005678543972044263, | |
| "loss": 3.742, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 2.721355379599441, | |
| "grad_norm": 0.3238438665866852, | |
| "learning_rate": 0.0005676796738497378, | |
| "loss": 3.7324, | |
| "step": 9350 | |
| }, | |
| { | |
| "epoch": 2.735910572892408, | |
| "grad_norm": 0.3079993426799774, | |
| "learning_rate": 0.0005675049504950495, | |
| "loss": 3.742, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.750465766185375, | |
| "grad_norm": 0.306488573551178, | |
| "learning_rate": 0.0005673302271403611, | |
| "loss": 3.7251, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 2.765020959478342, | |
| "grad_norm": 0.3277283012866974, | |
| "learning_rate": 0.0005671555037856726, | |
| "loss": 3.7261, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.779576152771309, | |
| "grad_norm": 0.29886722564697266, | |
| "learning_rate": 0.0005669807804309842, | |
| "loss": 3.7281, | |
| "step": 9550 | |
| }, | |
| { | |
| "epoch": 2.7941313460642756, | |
| "grad_norm": 0.3110831081867218, | |
| "learning_rate": 0.0005668060570762958, | |
| "loss": 3.7361, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.8086865393572427, | |
| "grad_norm": 0.3029453456401825, | |
| "learning_rate": 0.0005666313337216074, | |
| "loss": 3.7276, | |
| "step": 9650 | |
| }, | |
| { | |
| "epoch": 2.8232417326502097, | |
| "grad_norm": 0.3316793739795685, | |
| "learning_rate": 0.000566456610366919, | |
| "loss": 3.7202, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 2.8377969259431763, | |
| "grad_norm": 0.3127792179584503, | |
| "learning_rate": 0.0005662818870122306, | |
| "loss": 3.7303, | |
| "step": 9750 | |
| }, | |
| { | |
| "epoch": 2.8523521192361434, | |
| "grad_norm": 0.3021428883075714, | |
| "learning_rate": 0.0005661071636575422, | |
| "loss": 3.7277, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.8669073125291105, | |
| "grad_norm": 0.3044377267360687, | |
| "learning_rate": 0.0005659324403028537, | |
| "loss": 3.7166, | |
| "step": 9850 | |
| }, | |
| { | |
| "epoch": 2.8814625058220775, | |
| "grad_norm": 0.2994714081287384, | |
| "learning_rate": 0.0005657577169481653, | |
| "loss": 3.722, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 2.896017699115044, | |
| "grad_norm": 0.2987304627895355, | |
| "learning_rate": 0.0005655829935934769, | |
| "loss": 3.7173, | |
| "step": 9950 | |
| }, | |
| { | |
| "epoch": 2.910572892408011, | |
| "grad_norm": 0.2998504936695099, | |
| "learning_rate": 0.0005654082702387886, | |
| "loss": 3.7358, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.910572892408011, | |
| "eval_accuracy": 0.34975773508898755, | |
| "eval_loss": 3.727468967437744, | |
| "eval_runtime": 53.4831, | |
| "eval_samples_per_second": 311.332, | |
| "eval_steps_per_second": 19.464, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.9251280857009783, | |
| "grad_norm": 0.3378303050994873, | |
| "learning_rate": 0.0005652335468841001, | |
| "loss": 3.7182, | |
| "step": 10050 | |
| }, | |
| { | |
| "epoch": 2.939683278993945, | |
| "grad_norm": 0.3029598891735077, | |
| "learning_rate": 0.0005650588235294117, | |
| "loss": 3.7244, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 2.954238472286912, | |
| "grad_norm": 0.279568076133728, | |
| "learning_rate": 0.0005648841001747233, | |
| "loss": 3.7215, | |
| "step": 10150 | |
| }, | |
| { | |
| "epoch": 2.968793665579879, | |
| "grad_norm": 0.2990720272064209, | |
| "learning_rate": 0.0005647093768200349, | |
| "loss": 3.7297, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 2.983348858872846, | |
| "grad_norm": 0.3209785223007202, | |
| "learning_rate": 0.0005645346534653465, | |
| "loss": 3.7181, | |
| "step": 10250 | |
| }, | |
| { | |
| "epoch": 2.9979040521658127, | |
| "grad_norm": 0.32323557138442993, | |
| "learning_rate": 0.0005643599301106582, | |
| "loss": 3.7159, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 3.0122263623660923, | |
| "grad_norm": 0.31043893098831177, | |
| "learning_rate": 0.0005641852067559697, | |
| "loss": 3.6487, | |
| "step": 10350 | |
| }, | |
| { | |
| "epoch": 3.026781555659059, | |
| "grad_norm": 0.32079580426216125, | |
| "learning_rate": 0.0005640104834012812, | |
| "loss": 3.6169, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 3.041336748952026, | |
| "grad_norm": 0.30255889892578125, | |
| "learning_rate": 0.0005638357600465929, | |
| "loss": 3.609, | |
| "step": 10450 | |
| }, | |
| { | |
| "epoch": 3.055891942244993, | |
| "grad_norm": 0.3344894051551819, | |
| "learning_rate": 0.0005636610366919044, | |
| "loss": 3.6117, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.07044713553796, | |
| "grad_norm": 0.3106098771095276, | |
| "learning_rate": 0.0005634863133372161, | |
| "loss": 3.6251, | |
| "step": 10550 | |
| }, | |
| { | |
| "epoch": 3.0850023288309267, | |
| "grad_norm": 0.3262277841567993, | |
| "learning_rate": 0.0005633115899825276, | |
| "loss": 3.6299, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 3.099557522123894, | |
| "grad_norm": 0.3101554811000824, | |
| "learning_rate": 0.0005631368666278393, | |
| "loss": 3.6304, | |
| "step": 10650 | |
| }, | |
| { | |
| "epoch": 3.114112715416861, | |
| "grad_norm": 0.3250229060649872, | |
| "learning_rate": 0.0005629621432731508, | |
| "loss": 3.6474, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 3.1286679087098275, | |
| "grad_norm": 0.3248714506626129, | |
| "learning_rate": 0.0005627874199184623, | |
| "loss": 3.6348, | |
| "step": 10750 | |
| }, | |
| { | |
| "epoch": 3.1432231020027945, | |
| "grad_norm": 0.30085551738739014, | |
| "learning_rate": 0.000562612696563774, | |
| "loss": 3.6374, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 3.1577782952957616, | |
| "grad_norm": 0.3127143681049347, | |
| "learning_rate": 0.0005624379732090856, | |
| "loss": 3.6311, | |
| "step": 10850 | |
| }, | |
| { | |
| "epoch": 3.1723334885887287, | |
| "grad_norm": 0.3028300702571869, | |
| "learning_rate": 0.0005622632498543972, | |
| "loss": 3.63, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 3.1868886818816953, | |
| "grad_norm": 0.30366742610931396, | |
| "learning_rate": 0.0005620885264997087, | |
| "loss": 3.638, | |
| "step": 10950 | |
| }, | |
| { | |
| "epoch": 3.2014438751746623, | |
| "grad_norm": 0.3122618496417999, | |
| "learning_rate": 0.0005619138031450204, | |
| "loss": 3.6371, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.2014438751746623, | |
| "eval_accuracy": 0.3515147683049072, | |
| "eval_loss": 3.714933156967163, | |
| "eval_runtime": 53.2947, | |
| "eval_samples_per_second": 312.433, | |
| "eval_steps_per_second": 19.533, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.2159990684676294, | |
| "grad_norm": 0.31365302205085754, | |
| "learning_rate": 0.0005617390797903319, | |
| "loss": 3.6291, | |
| "step": 11050 | |
| }, | |
| { | |
| "epoch": 3.230554261760596, | |
| "grad_norm": 0.32741230726242065, | |
| "learning_rate": 0.0005615643564356436, | |
| "loss": 3.639, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 3.245109455053563, | |
| "grad_norm": 0.31929394602775574, | |
| "learning_rate": 0.0005613896330809551, | |
| "loss": 3.6379, | |
| "step": 11150 | |
| }, | |
| { | |
| "epoch": 3.25966464834653, | |
| "grad_norm": 0.3116866946220398, | |
| "learning_rate": 0.0005612149097262667, | |
| "loss": 3.6359, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 3.274219841639497, | |
| "grad_norm": 0.3216688632965088, | |
| "learning_rate": 0.0005610401863715783, | |
| "loss": 3.6408, | |
| "step": 11250 | |
| }, | |
| { | |
| "epoch": 3.288775034932464, | |
| "grad_norm": 0.30940675735473633, | |
| "learning_rate": 0.0005608654630168898, | |
| "loss": 3.6406, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 3.303330228225431, | |
| "grad_norm": 0.3255838453769684, | |
| "learning_rate": 0.0005606907396622015, | |
| "loss": 3.6475, | |
| "step": 11350 | |
| }, | |
| { | |
| "epoch": 3.317885421518398, | |
| "grad_norm": 0.31127750873565674, | |
| "learning_rate": 0.0005605160163075131, | |
| "loss": 3.6506, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 3.3324406148113646, | |
| "grad_norm": 0.31689971685409546, | |
| "learning_rate": 0.0005603412929528247, | |
| "loss": 3.6396, | |
| "step": 11450 | |
| }, | |
| { | |
| "epoch": 3.3469958081043316, | |
| "grad_norm": 0.3424036204814911, | |
| "learning_rate": 0.0005601665695981362, | |
| "loss": 3.6454, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.3615510013972987, | |
| "grad_norm": 0.3130670189857483, | |
| "learning_rate": 0.0005599918462434478, | |
| "loss": 3.6413, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 3.3761061946902653, | |
| "grad_norm": 0.31962189078330994, | |
| "learning_rate": 0.0005598171228887594, | |
| "loss": 3.6468, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 3.3906613879832324, | |
| "grad_norm": 0.3296726942062378, | |
| "learning_rate": 0.0005596423995340709, | |
| "loss": 3.6364, | |
| "step": 11650 | |
| }, | |
| { | |
| "epoch": 3.4052165812761994, | |
| "grad_norm": 0.3237113058567047, | |
| "learning_rate": 0.0005594676761793826, | |
| "loss": 3.6418, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 3.419771774569166, | |
| "grad_norm": 0.31087416410446167, | |
| "learning_rate": 0.0005592929528246942, | |
| "loss": 3.635, | |
| "step": 11750 | |
| }, | |
| { | |
| "epoch": 3.434326967862133, | |
| "grad_norm": 0.3091017007827759, | |
| "learning_rate": 0.0005591182294700058, | |
| "loss": 3.6453, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 3.4488821611551, | |
| "grad_norm": 0.34498894214630127, | |
| "learning_rate": 0.0005589435061153173, | |
| "loss": 3.6502, | |
| "step": 11850 | |
| }, | |
| { | |
| "epoch": 3.463437354448067, | |
| "grad_norm": 0.31695738434791565, | |
| "learning_rate": 0.000558768782760629, | |
| "loss": 3.6504, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 3.477992547741034, | |
| "grad_norm": 0.3105430006980896, | |
| "learning_rate": 0.0005585940594059406, | |
| "loss": 3.6395, | |
| "step": 11950 | |
| }, | |
| { | |
| "epoch": 3.492547741034001, | |
| "grad_norm": 0.32732608914375305, | |
| "learning_rate": 0.0005584193360512521, | |
| "loss": 3.6539, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.492547741034001, | |
| "eval_accuracy": 0.3528896027236248, | |
| "eval_loss": 3.6969735622406006, | |
| "eval_runtime": 53.5413, | |
| "eval_samples_per_second": 310.994, | |
| "eval_steps_per_second": 19.443, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.507102934326968, | |
| "grad_norm": 0.3077699840068817, | |
| "learning_rate": 0.0005582446126965637, | |
| "loss": 3.6437, | |
| "step": 12050 | |
| }, | |
| { | |
| "epoch": 3.5216581276199346, | |
| "grad_norm": 0.314300537109375, | |
| "learning_rate": 0.0005580698893418753, | |
| "loss": 3.636, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 3.5362133209129016, | |
| "grad_norm": 0.3131679892539978, | |
| "learning_rate": 0.0005578951659871869, | |
| "loss": 3.641, | |
| "step": 12150 | |
| }, | |
| { | |
| "epoch": 3.5507685142058687, | |
| "grad_norm": 0.3469048738479614, | |
| "learning_rate": 0.0005577204426324985, | |
| "loss": 3.6499, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 3.5653237074988358, | |
| "grad_norm": 0.2866024672985077, | |
| "learning_rate": 0.0005575457192778101, | |
| "loss": 3.6483, | |
| "step": 12250 | |
| }, | |
| { | |
| "epoch": 3.5798789007918024, | |
| "grad_norm": 0.33073994517326355, | |
| "learning_rate": 0.0005573709959231217, | |
| "loss": 3.6491, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 3.5944340940847694, | |
| "grad_norm": 0.30543893575668335, | |
| "learning_rate": 0.0005571962725684332, | |
| "loss": 3.6568, | |
| "step": 12350 | |
| }, | |
| { | |
| "epoch": 3.6089892873777365, | |
| "grad_norm": 0.3051474988460541, | |
| "learning_rate": 0.0005570215492137449, | |
| "loss": 3.6251, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 3.623544480670703, | |
| "grad_norm": 0.32578974962234497, | |
| "learning_rate": 0.0005568468258590564, | |
| "loss": 3.6349, | |
| "step": 12450 | |
| }, | |
| { | |
| "epoch": 3.63809967396367, | |
| "grad_norm": 0.31897076964378357, | |
| "learning_rate": 0.0005566721025043681, | |
| "loss": 3.6376, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.6526548672566372, | |
| "grad_norm": 0.3143940567970276, | |
| "learning_rate": 0.0005564973791496796, | |
| "loss": 3.6272, | |
| "step": 12550 | |
| }, | |
| { | |
| "epoch": 3.6672100605496043, | |
| "grad_norm": 0.2999384105205536, | |
| "learning_rate": 0.0005563226557949913, | |
| "loss": 3.6462, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 3.681765253842571, | |
| "grad_norm": 0.2864264249801636, | |
| "learning_rate": 0.0005561479324403028, | |
| "loss": 3.6486, | |
| "step": 12650 | |
| }, | |
| { | |
| "epoch": 3.696320447135538, | |
| "grad_norm": 0.296589195728302, | |
| "learning_rate": 0.0005559732090856144, | |
| "loss": 3.6312, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 3.710875640428505, | |
| "grad_norm": 0.3220252990722656, | |
| "learning_rate": 0.000555798485730926, | |
| "loss": 3.6362, | |
| "step": 12750 | |
| }, | |
| { | |
| "epoch": 3.7254308337214717, | |
| "grad_norm": 0.31383004784584045, | |
| "learning_rate": 0.0005556237623762376, | |
| "loss": 3.6497, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 3.7399860270144387, | |
| "grad_norm": 0.31332045793533325, | |
| "learning_rate": 0.0005554490390215492, | |
| "loss": 3.6366, | |
| "step": 12850 | |
| }, | |
| { | |
| "epoch": 3.754541220307406, | |
| "grad_norm": 0.32753342390060425, | |
| "learning_rate": 0.0005552743156668607, | |
| "loss": 3.6366, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 3.769096413600373, | |
| "grad_norm": 0.3163292407989502, | |
| "learning_rate": 0.0005550995923121724, | |
| "loss": 3.6439, | |
| "step": 12950 | |
| }, | |
| { | |
| "epoch": 3.7836516068933395, | |
| "grad_norm": 0.3240298926830292, | |
| "learning_rate": 0.0005549248689574839, | |
| "loss": 3.6469, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.7836516068933395, | |
| "eval_accuracy": 0.3549230601618751, | |
| "eval_loss": 3.6789798736572266, | |
| "eval_runtime": 53.5602, | |
| "eval_samples_per_second": 310.884, | |
| "eval_steps_per_second": 19.436, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.7982068001863065, | |
| "grad_norm": 0.3121490478515625, | |
| "learning_rate": 0.0005547501456027955, | |
| "loss": 3.6489, | |
| "step": 13050 | |
| }, | |
| { | |
| "epoch": 3.812761993479273, | |
| "grad_norm": 0.3035634160041809, | |
| "learning_rate": 0.0005545754222481071, | |
| "loss": 3.632, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 3.82731718677224, | |
| "grad_norm": 0.3016563653945923, | |
| "learning_rate": 0.0005544006988934188, | |
| "loss": 3.6422, | |
| "step": 13150 | |
| }, | |
| { | |
| "epoch": 3.8418723800652073, | |
| "grad_norm": 0.31660547852516174, | |
| "learning_rate": 0.0005542259755387303, | |
| "loss": 3.6368, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 3.8564275733581743, | |
| "grad_norm": 0.3109196126461029, | |
| "learning_rate": 0.0005540512521840418, | |
| "loss": 3.6298, | |
| "step": 13250 | |
| }, | |
| { | |
| "epoch": 3.8709827666511414, | |
| "grad_norm": 0.3088270425796509, | |
| "learning_rate": 0.0005538765288293535, | |
| "loss": 3.6297, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 3.885537959944108, | |
| "grad_norm": 0.3025343716144562, | |
| "learning_rate": 0.0005537018054746651, | |
| "loss": 3.6346, | |
| "step": 13350 | |
| }, | |
| { | |
| "epoch": 3.900093153237075, | |
| "grad_norm": 0.30994585156440735, | |
| "learning_rate": 0.0005535270821199767, | |
| "loss": 3.6345, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 3.9146483465300417, | |
| "grad_norm": 0.3035052716732025, | |
| "learning_rate": 0.0005533523587652882, | |
| "loss": 3.6279, | |
| "step": 13450 | |
| }, | |
| { | |
| "epoch": 3.9292035398230087, | |
| "grad_norm": 0.3128682076931, | |
| "learning_rate": 0.0005531776354105999, | |
| "loss": 3.6527, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.943758733115976, | |
| "grad_norm": 0.31095144152641296, | |
| "learning_rate": 0.0005530029120559114, | |
| "loss": 3.6465, | |
| "step": 13550 | |
| }, | |
| { | |
| "epoch": 3.958313926408943, | |
| "grad_norm": 0.3066427409648895, | |
| "learning_rate": 0.0005528281887012229, | |
| "loss": 3.6413, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 3.9728691197019095, | |
| "grad_norm": 0.304396390914917, | |
| "learning_rate": 0.0005526534653465346, | |
| "loss": 3.6304, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 3.9874243129948765, | |
| "grad_norm": 0.31533896923065186, | |
| "learning_rate": 0.0005524787419918462, | |
| "loss": 3.6374, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 4.001746623195156, | |
| "grad_norm": 0.3675478994846344, | |
| "learning_rate": 0.0005523040186371578, | |
| "loss": 3.6242, | |
| "step": 13750 | |
| }, | |
| { | |
| "epoch": 4.016301816488123, | |
| "grad_norm": 0.29201996326446533, | |
| "learning_rate": 0.0005521292952824693, | |
| "loss": 3.5318, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 4.03085700978109, | |
| "grad_norm": 0.30893081426620483, | |
| "learning_rate": 0.000551954571927781, | |
| "loss": 3.5254, | |
| "step": 13850 | |
| }, | |
| { | |
| "epoch": 4.045412203074057, | |
| "grad_norm": 0.3096214830875397, | |
| "learning_rate": 0.0005517798485730926, | |
| "loss": 3.5233, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 4.059967396367024, | |
| "grad_norm": 0.31587645411491394, | |
| "learning_rate": 0.0005516051252184042, | |
| "loss": 3.5255, | |
| "step": 13950 | |
| }, | |
| { | |
| "epoch": 4.074522589659991, | |
| "grad_norm": 0.3416009247303009, | |
| "learning_rate": 0.0005514304018637157, | |
| "loss": 3.536, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.074522589659991, | |
| "eval_accuracy": 0.3564118960668429, | |
| "eval_loss": 3.6700236797332764, | |
| "eval_runtime": 53.4334, | |
| "eval_samples_per_second": 311.621, | |
| "eval_steps_per_second": 19.482, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.089077782952957, | |
| "grad_norm": 0.33188971877098083, | |
| "learning_rate": 0.0005512556785090273, | |
| "loss": 3.5451, | |
| "step": 14050 | |
| }, | |
| { | |
| "epoch": 4.103632976245924, | |
| "grad_norm": 0.3042742908000946, | |
| "learning_rate": 0.0005510809551543389, | |
| "loss": 3.5366, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 4.118188169538891, | |
| "grad_norm": 0.3066245913505554, | |
| "learning_rate": 0.0005509062317996504, | |
| "loss": 3.5394, | |
| "step": 14150 | |
| }, | |
| { | |
| "epoch": 4.132743362831858, | |
| "grad_norm": 0.31989961862564087, | |
| "learning_rate": 0.0005507315084449621, | |
| "loss": 3.5518, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 4.1472985561248255, | |
| "grad_norm": 0.2979581654071808, | |
| "learning_rate": 0.0005505567850902737, | |
| "loss": 3.5544, | |
| "step": 14250 | |
| }, | |
| { | |
| "epoch": 4.1618537494177925, | |
| "grad_norm": 0.3020860552787781, | |
| "learning_rate": 0.0005503820617355853, | |
| "loss": 3.5501, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 4.17640894271076, | |
| "grad_norm": 0.30943456292152405, | |
| "learning_rate": 0.0005502073383808969, | |
| "loss": 3.5578, | |
| "step": 14350 | |
| }, | |
| { | |
| "epoch": 4.190964136003726, | |
| "grad_norm": 0.33941027522087097, | |
| "learning_rate": 0.0005500326150262085, | |
| "loss": 3.5601, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 4.205519329296693, | |
| "grad_norm": 0.30638518929481506, | |
| "learning_rate": 0.00054985789167152, | |
| "loss": 3.5642, | |
| "step": 14450 | |
| }, | |
| { | |
| "epoch": 4.22007452258966, | |
| "grad_norm": 0.3232273757457733, | |
| "learning_rate": 0.0005496831683168316, | |
| "loss": 3.5546, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.234629715882627, | |
| "grad_norm": 0.3078799247741699, | |
| "learning_rate": 0.0005495084449621433, | |
| "loss": 3.5686, | |
| "step": 14550 | |
| }, | |
| { | |
| "epoch": 4.249184909175594, | |
| "grad_norm": 0.3173246383666992, | |
| "learning_rate": 0.0005493337216074548, | |
| "loss": 3.5553, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 4.263740102468561, | |
| "grad_norm": 0.30258744955062866, | |
| "learning_rate": 0.0005491589982527664, | |
| "loss": 3.5563, | |
| "step": 14650 | |
| }, | |
| { | |
| "epoch": 4.278295295761528, | |
| "grad_norm": 0.32782596349716187, | |
| "learning_rate": 0.000548984274898078, | |
| "loss": 3.5592, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 4.292850489054494, | |
| "grad_norm": 0.29621395468711853, | |
| "learning_rate": 0.0005488095515433897, | |
| "loss": 3.5716, | |
| "step": 14750 | |
| }, | |
| { | |
| "epoch": 4.307405682347461, | |
| "grad_norm": 0.31056085228919983, | |
| "learning_rate": 0.0005486348281887012, | |
| "loss": 3.5578, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 4.321960875640428, | |
| "grad_norm": 0.3205181062221527, | |
| "learning_rate": 0.0005484601048340127, | |
| "loss": 3.5648, | |
| "step": 14850 | |
| }, | |
| { | |
| "epoch": 4.3365160689333955, | |
| "grad_norm": 0.31166449189186096, | |
| "learning_rate": 0.0005482853814793244, | |
| "loss": 3.5709, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 4.3510712622263625, | |
| "grad_norm": 0.30264922976493835, | |
| "learning_rate": 0.0005481106581246359, | |
| "loss": 3.5661, | |
| "step": 14950 | |
| }, | |
| { | |
| "epoch": 4.36562645551933, | |
| "grad_norm": 0.32774078845977783, | |
| "learning_rate": 0.0005479359347699475, | |
| "loss": 3.5777, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.36562645551933, | |
| "eval_accuracy": 0.35688435583460193, | |
| "eval_loss": 3.6629531383514404, | |
| "eval_runtime": 53.643, | |
| "eval_samples_per_second": 310.404, | |
| "eval_steps_per_second": 19.406, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.380181648812297, | |
| "grad_norm": 0.3218841552734375, | |
| "learning_rate": 0.0005477612114152591, | |
| "loss": 3.5697, | |
| "step": 15050 | |
| }, | |
| { | |
| "epoch": 4.394736842105263, | |
| "grad_norm": 0.32773557305336, | |
| "learning_rate": 0.0005475864880605708, | |
| "loss": 3.5738, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 4.40929203539823, | |
| "grad_norm": 0.3104153275489807, | |
| "learning_rate": 0.0005474117647058823, | |
| "loss": 3.5632, | |
| "step": 15150 | |
| }, | |
| { | |
| "epoch": 4.423847228691197, | |
| "grad_norm": 0.31165000796318054, | |
| "learning_rate": 0.0005472370413511939, | |
| "loss": 3.5798, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 4.438402421984164, | |
| "grad_norm": 0.3084467053413391, | |
| "learning_rate": 0.0005470623179965055, | |
| "loss": 3.5725, | |
| "step": 15250 | |
| }, | |
| { | |
| "epoch": 4.452957615277131, | |
| "grad_norm": 0.3122389316558838, | |
| "learning_rate": 0.0005468875946418171, | |
| "loss": 3.5758, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 4.467512808570098, | |
| "grad_norm": 0.30723056197166443, | |
| "learning_rate": 0.0005467128712871287, | |
| "loss": 3.5743, | |
| "step": 15350 | |
| }, | |
| { | |
| "epoch": 4.482068001863064, | |
| "grad_norm": 0.3274446427822113, | |
| "learning_rate": 0.0005465381479324402, | |
| "loss": 3.5711, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 4.496623195156031, | |
| "grad_norm": 0.32006531953811646, | |
| "learning_rate": 0.0005463634245777519, | |
| "loss": 3.5834, | |
| "step": 15450 | |
| }, | |
| { | |
| "epoch": 4.511178388448998, | |
| "grad_norm": 0.29839152097702026, | |
| "learning_rate": 0.0005461887012230634, | |
| "loss": 3.5843, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.5257335817419655, | |
| "grad_norm": 0.31520766019821167, | |
| "learning_rate": 0.000546013977868375, | |
| "loss": 3.5658, | |
| "step": 15550 | |
| }, | |
| { | |
| "epoch": 4.5402887750349326, | |
| "grad_norm": 0.31398266553878784, | |
| "learning_rate": 0.0005458392545136866, | |
| "loss": 3.5779, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 4.5548439683279, | |
| "grad_norm": 0.3142099976539612, | |
| "learning_rate": 0.0005456645311589983, | |
| "loss": 3.574, | |
| "step": 15650 | |
| }, | |
| { | |
| "epoch": 4.569399161620867, | |
| "grad_norm": 0.3211691975593567, | |
| "learning_rate": 0.0005454898078043098, | |
| "loss": 3.5777, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 4.583954354913834, | |
| "grad_norm": 0.30189618468284607, | |
| "learning_rate": 0.0005453150844496213, | |
| "loss": 3.5665, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 4.5985095482068, | |
| "grad_norm": 0.30451640486717224, | |
| "learning_rate": 0.000545140361094933, | |
| "loss": 3.5752, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 4.613064741499767, | |
| "grad_norm": 0.29846951365470886, | |
| "learning_rate": 0.0005449656377402445, | |
| "loss": 3.5717, | |
| "step": 15850 | |
| }, | |
| { | |
| "epoch": 4.627619934792734, | |
| "grad_norm": 0.3026646375656128, | |
| "learning_rate": 0.0005447909143855562, | |
| "loss": 3.5862, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 4.642175128085701, | |
| "grad_norm": 0.3179943859577179, | |
| "learning_rate": 0.0005446161910308677, | |
| "loss": 3.5825, | |
| "step": 15950 | |
| }, | |
| { | |
| "epoch": 4.656730321378668, | |
| "grad_norm": 0.3168904185295105, | |
| "learning_rate": 0.0005444414676761794, | |
| "loss": 3.5722, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.656730321378668, | |
| "eval_accuracy": 0.3580772579845407, | |
| "eval_loss": 3.649070978164673, | |
| "eval_runtime": 53.495, | |
| "eval_samples_per_second": 311.262, | |
| "eval_steps_per_second": 19.46, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.671285514671635, | |
| "grad_norm": 0.3200220465660095, | |
| "learning_rate": 0.0005442667443214909, | |
| "loss": 3.5796, | |
| "step": 16050 | |
| }, | |
| { | |
| "epoch": 4.685840707964601, | |
| "grad_norm": 0.29701098799705505, | |
| "learning_rate": 0.0005440920209668024, | |
| "loss": 3.568, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 4.7003959012575685, | |
| "grad_norm": 0.3012307286262512, | |
| "learning_rate": 0.0005439172976121141, | |
| "loss": 3.5734, | |
| "step": 16150 | |
| }, | |
| { | |
| "epoch": 4.7149510945505355, | |
| "grad_norm": 0.31523796916007996, | |
| "learning_rate": 0.0005437425742574257, | |
| "loss": 3.5638, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 4.729506287843503, | |
| "grad_norm": 0.31565117835998535, | |
| "learning_rate": 0.0005435678509027373, | |
| "loss": 3.5784, | |
| "step": 16250 | |
| }, | |
| { | |
| "epoch": 4.74406148113647, | |
| "grad_norm": 0.3497096300125122, | |
| "learning_rate": 0.0005433931275480488, | |
| "loss": 3.5731, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 4.758616674429437, | |
| "grad_norm": 0.31138789653778076, | |
| "learning_rate": 0.0005432184041933605, | |
| "loss": 3.5909, | |
| "step": 16350 | |
| }, | |
| { | |
| "epoch": 4.773171867722404, | |
| "grad_norm": 0.3071785569190979, | |
| "learning_rate": 0.000543043680838672, | |
| "loss": 3.5814, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 4.78772706101537, | |
| "grad_norm": 0.31594768166542053, | |
| "learning_rate": 0.0005428689574839837, | |
| "loss": 3.5962, | |
| "step": 16450 | |
| }, | |
| { | |
| "epoch": 4.802282254308337, | |
| "grad_norm": 0.30671027302742004, | |
| "learning_rate": 0.0005426942341292952, | |
| "loss": 3.5767, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 4.816837447601304, | |
| "grad_norm": 0.30355602502822876, | |
| "learning_rate": 0.0005425195107746068, | |
| "loss": 3.5962, | |
| "step": 16550 | |
| }, | |
| { | |
| "epoch": 4.831392640894271, | |
| "grad_norm": 0.29484668374061584, | |
| "learning_rate": 0.0005423447874199184, | |
| "loss": 3.5794, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 4.845947834187238, | |
| "grad_norm": 0.318393349647522, | |
| "learning_rate": 0.00054217006406523, | |
| "loss": 3.5774, | |
| "step": 16650 | |
| }, | |
| { | |
| "epoch": 4.860503027480205, | |
| "grad_norm": 0.3051914870738983, | |
| "learning_rate": 0.0005419953407105417, | |
| "loss": 3.5757, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 4.875058220773171, | |
| "grad_norm": 0.32631877064704895, | |
| "learning_rate": 0.0005418206173558532, | |
| "loss": 3.568, | |
| "step": 16750 | |
| }, | |
| { | |
| "epoch": 4.8896134140661385, | |
| "grad_norm": 0.311920166015625, | |
| "learning_rate": 0.0005416458940011648, | |
| "loss": 3.5653, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 4.9041686073591055, | |
| "grad_norm": 0.30825456976890564, | |
| "learning_rate": 0.0005414711706464764, | |
| "loss": 3.5832, | |
| "step": 16850 | |
| }, | |
| { | |
| "epoch": 4.918723800652073, | |
| "grad_norm": 0.32179245352745056, | |
| "learning_rate": 0.000541296447291788, | |
| "loss": 3.5862, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 4.93327899394504, | |
| "grad_norm": 0.31406310200691223, | |
| "learning_rate": 0.0005411217239370995, | |
| "loss": 3.5787, | |
| "step": 16950 | |
| }, | |
| { | |
| "epoch": 4.947834187238007, | |
| "grad_norm": 0.3118932247161865, | |
| "learning_rate": 0.0005409470005824111, | |
| "loss": 3.5798, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.947834187238007, | |
| "eval_accuracy": 0.35958595600412335, | |
| "eval_loss": 3.6351637840270996, | |
| "eval_runtime": 53.7218, | |
| "eval_samples_per_second": 309.948, | |
| "eval_steps_per_second": 19.378, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.962389380530974, | |
| "grad_norm": 0.28993093967437744, | |
| "learning_rate": 0.0005407722772277228, | |
| "loss": 3.5827, | |
| "step": 17050 | |
| }, | |
| { | |
| "epoch": 4.976944573823941, | |
| "grad_norm": 0.3043540418148041, | |
| "learning_rate": 0.0005405975538730343, | |
| "loss": 3.5817, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 4.991499767116907, | |
| "grad_norm": 0.3084542155265808, | |
| "learning_rate": 0.0005404228305183459, | |
| "loss": 3.592, | |
| "step": 17150 | |
| }, | |
| { | |
| "epoch": 5.005822077317187, | |
| "grad_norm": 0.3285490870475769, | |
| "learning_rate": 0.0005402481071636575, | |
| "loss": 3.5405, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 5.020377270610154, | |
| "grad_norm": 0.3274278938770294, | |
| "learning_rate": 0.0005400733838089692, | |
| "loss": 3.4773, | |
| "step": 17250 | |
| }, | |
| { | |
| "epoch": 5.034932463903121, | |
| "grad_norm": 0.31990793347358704, | |
| "learning_rate": 0.0005398986604542807, | |
| "loss": 3.4764, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 5.049487657196088, | |
| "grad_norm": 0.311761736869812, | |
| "learning_rate": 0.0005397239370995922, | |
| "loss": 3.4754, | |
| "step": 17350 | |
| }, | |
| { | |
| "epoch": 5.064042850489055, | |
| "grad_norm": 0.306323379278183, | |
| "learning_rate": 0.0005395492137449039, | |
| "loss": 3.4642, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 5.078598043782021, | |
| "grad_norm": 0.31643232703208923, | |
| "learning_rate": 0.0005393744903902154, | |
| "loss": 3.4892, | |
| "step": 17450 | |
| }, | |
| { | |
| "epoch": 5.093153237074988, | |
| "grad_norm": 0.3218034505844116, | |
| "learning_rate": 0.000539199767035527, | |
| "loss": 3.4822, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 5.107708430367955, | |
| "grad_norm": 0.300322562456131, | |
| "learning_rate": 0.0005390250436808386, | |
| "loss": 3.4781, | |
| "step": 17550 | |
| }, | |
| { | |
| "epoch": 5.122263623660922, | |
| "grad_norm": 0.30128493905067444, | |
| "learning_rate": 0.0005388503203261503, | |
| "loss": 3.487, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 5.136818816953889, | |
| "grad_norm": 0.3042433261871338, | |
| "learning_rate": 0.0005386755969714618, | |
| "loss": 3.4874, | |
| "step": 17650 | |
| }, | |
| { | |
| "epoch": 5.151374010246856, | |
| "grad_norm": 0.33344727754592896, | |
| "learning_rate": 0.0005385008736167733, | |
| "loss": 3.4976, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 5.165929203539823, | |
| "grad_norm": 0.31497395038604736, | |
| "learning_rate": 0.000538326150262085, | |
| "loss": 3.4842, | |
| "step": 17750 | |
| }, | |
| { | |
| "epoch": 5.18048439683279, | |
| "grad_norm": 0.3139030933380127, | |
| "learning_rate": 0.0005381514269073965, | |
| "loss": 3.4886, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 5.195039590125757, | |
| "grad_norm": 0.3225633203983307, | |
| "learning_rate": 0.0005379767035527082, | |
| "loss": 3.497, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 5.209594783418724, | |
| "grad_norm": 0.34571751952171326, | |
| "learning_rate": 0.0005378019801980197, | |
| "loss": 3.4911, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 5.224149976711691, | |
| "grad_norm": 0.31457775831222534, | |
| "learning_rate": 0.0005376272568433314, | |
| "loss": 3.5029, | |
| "step": 17950 | |
| }, | |
| { | |
| "epoch": 5.238705170004658, | |
| "grad_norm": 0.3238813281059265, | |
| "learning_rate": 0.0005374525334886429, | |
| "loss": 3.4922, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.238705170004658, | |
| "eval_accuracy": 0.36014844168782845, | |
| "eval_loss": 3.6354222297668457, | |
| "eval_runtime": 53.6531, | |
| "eval_samples_per_second": 310.345, | |
| "eval_steps_per_second": 19.402, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 5.253260363297625, | |
| "grad_norm": 0.3407672345638275, | |
| "learning_rate": 0.0005372778101339545, | |
| "loss": 3.5179, | |
| "step": 18050 | |
| }, | |
| { | |
| "epoch": 5.267815556590591, | |
| "grad_norm": 0.30539172887802124, | |
| "learning_rate": 0.0005371030867792661, | |
| "loss": 3.5043, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 5.282370749883558, | |
| "grad_norm": 0.30435362458229065, | |
| "learning_rate": 0.0005369283634245778, | |
| "loss": 3.5082, | |
| "step": 18150 | |
| }, | |
| { | |
| "epoch": 5.296925943176525, | |
| "grad_norm": 0.3186531066894531, | |
| "learning_rate": 0.0005367536400698893, | |
| "loss": 3.506, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 5.311481136469492, | |
| "grad_norm": 0.31211575865745544, | |
| "learning_rate": 0.0005365789167152008, | |
| "loss": 3.4945, | |
| "step": 18250 | |
| }, | |
| { | |
| "epoch": 5.326036329762459, | |
| "grad_norm": 0.3212841749191284, | |
| "learning_rate": 0.0005364041933605125, | |
| "loss": 3.5152, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 5.340591523055426, | |
| "grad_norm": 0.30847251415252686, | |
| "learning_rate": 0.000536229470005824, | |
| "loss": 3.5219, | |
| "step": 18350 | |
| }, | |
| { | |
| "epoch": 5.3551467163483935, | |
| "grad_norm": 0.30765900015830994, | |
| "learning_rate": 0.0005360547466511357, | |
| "loss": 3.5253, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 5.36970190964136, | |
| "grad_norm": 0.33044424653053284, | |
| "learning_rate": 0.0005358800232964472, | |
| "loss": 3.5115, | |
| "step": 18450 | |
| }, | |
| { | |
| "epoch": 5.384257102934327, | |
| "grad_norm": 0.3065807521343231, | |
| "learning_rate": 0.0005357052999417589, | |
| "loss": 3.5211, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 5.398812296227294, | |
| "grad_norm": 0.3146962523460388, | |
| "learning_rate": 0.0005355305765870704, | |
| "loss": 3.5142, | |
| "step": 18550 | |
| }, | |
| { | |
| "epoch": 5.413367489520261, | |
| "grad_norm": 0.31133386492729187, | |
| "learning_rate": 0.000535355853232382, | |
| "loss": 3.4998, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 5.427922682813228, | |
| "grad_norm": 0.3130752444267273, | |
| "learning_rate": 0.0005351811298776936, | |
| "loss": 3.5272, | |
| "step": 18650 | |
| }, | |
| { | |
| "epoch": 5.442477876106195, | |
| "grad_norm": 0.30729568004608154, | |
| "learning_rate": 0.0005350064065230052, | |
| "loss": 3.5177, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 5.457033069399162, | |
| "grad_norm": 0.3040784001350403, | |
| "learning_rate": 0.0005348316831683168, | |
| "loss": 3.523, | |
| "step": 18750 | |
| }, | |
| { | |
| "epoch": 5.471588262692128, | |
| "grad_norm": 0.3313382863998413, | |
| "learning_rate": 0.0005346569598136284, | |
| "loss": 3.5224, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 5.486143455985095, | |
| "grad_norm": 0.3166414797306061, | |
| "learning_rate": 0.00053448223645894, | |
| "loss": 3.5175, | |
| "step": 18850 | |
| }, | |
| { | |
| "epoch": 5.500698649278062, | |
| "grad_norm": 0.32025575637817383, | |
| "learning_rate": 0.0005343075131042515, | |
| "loss": 3.5272, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 5.515253842571029, | |
| "grad_norm": 0.3252187967300415, | |
| "learning_rate": 0.0005341327897495632, | |
| "loss": 3.5306, | |
| "step": 18950 | |
| }, | |
| { | |
| "epoch": 5.529809035863996, | |
| "grad_norm": 0.3123398721218109, | |
| "learning_rate": 0.0005339580663948748, | |
| "loss": 3.5186, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 5.529809035863996, | |
| "eval_accuracy": 0.3612145318752269, | |
| "eval_loss": 3.6263232231140137, | |
| "eval_runtime": 53.4593, | |
| "eval_samples_per_second": 311.471, | |
| "eval_steps_per_second": 19.473, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 5.5443642291569635, | |
| "grad_norm": 0.30294138193130493, | |
| "learning_rate": 0.0005337833430401863, | |
| "loss": 3.537, | |
| "step": 19050 | |
| }, | |
| { | |
| "epoch": 5.5589194224499305, | |
| "grad_norm": 0.32932162284851074, | |
| "learning_rate": 0.0005336086196854979, | |
| "loss": 3.5284, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 5.573474615742897, | |
| "grad_norm": 0.34517279267311096, | |
| "learning_rate": 0.0005334338963308095, | |
| "loss": 3.517, | |
| "step": 19150 | |
| }, | |
| { | |
| "epoch": 5.588029809035864, | |
| "grad_norm": 0.3153057396411896, | |
| "learning_rate": 0.0005332591729761211, | |
| "loss": 3.5227, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 5.602585002328831, | |
| "grad_norm": 0.3112879991531372, | |
| "learning_rate": 0.0005330844496214327, | |
| "loss": 3.5176, | |
| "step": 19250 | |
| }, | |
| { | |
| "epoch": 5.617140195621798, | |
| "grad_norm": 0.33127614855766296, | |
| "learning_rate": 0.0005329097262667443, | |
| "loss": 3.5219, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 5.631695388914765, | |
| "grad_norm": 0.3078460097312927, | |
| "learning_rate": 0.0005327350029120559, | |
| "loss": 3.5341, | |
| "step": 19350 | |
| }, | |
| { | |
| "epoch": 5.646250582207732, | |
| "grad_norm": 0.3025256395339966, | |
| "learning_rate": 0.0005325602795573674, | |
| "loss": 3.5245, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 5.660805775500698, | |
| "grad_norm": 0.3317052125930786, | |
| "learning_rate": 0.000532385556202679, | |
| "loss": 3.528, | |
| "step": 19450 | |
| }, | |
| { | |
| "epoch": 5.675360968793665, | |
| "grad_norm": 0.31399670243263245, | |
| "learning_rate": 0.0005322108328479906, | |
| "loss": 3.5405, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 5.689916162086632, | |
| "grad_norm": 0.3107835650444031, | |
| "learning_rate": 0.0005320361094933023, | |
| "loss": 3.5254, | |
| "step": 19550 | |
| }, | |
| { | |
| "epoch": 5.704471355379599, | |
| "grad_norm": 0.31921184062957764, | |
| "learning_rate": 0.0005318613861386138, | |
| "loss": 3.5265, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 5.719026548672566, | |
| "grad_norm": 0.30891355872154236, | |
| "learning_rate": 0.0005316866627839254, | |
| "loss": 3.5297, | |
| "step": 19650 | |
| }, | |
| { | |
| "epoch": 5.7335817419655335, | |
| "grad_norm": 0.3252127766609192, | |
| "learning_rate": 0.000531511939429237, | |
| "loss": 3.5303, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 5.748136935258501, | |
| "grad_norm": 0.3049852252006531, | |
| "learning_rate": 0.0005313372160745486, | |
| "loss": 3.5236, | |
| "step": 19750 | |
| }, | |
| { | |
| "epoch": 5.762692128551468, | |
| "grad_norm": 0.3159811198711395, | |
| "learning_rate": 0.0005311624927198602, | |
| "loss": 3.5296, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 5.777247321844434, | |
| "grad_norm": 0.3251304030418396, | |
| "learning_rate": 0.0005309877693651717, | |
| "loss": 3.5252, | |
| "step": 19850 | |
| }, | |
| { | |
| "epoch": 5.791802515137401, | |
| "grad_norm": 0.30788806080818176, | |
| "learning_rate": 0.0005308130460104834, | |
| "loss": 3.5323, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 5.806357708430368, | |
| "grad_norm": 0.31760692596435547, | |
| "learning_rate": 0.0005306383226557949, | |
| "loss": 3.535, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 5.820912901723335, | |
| "grad_norm": 0.3128082752227783, | |
| "learning_rate": 0.0005304635993011065, | |
| "loss": 3.5291, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 5.820912901723335, | |
| "eval_accuracy": 0.3617880651256408, | |
| "eval_loss": 3.6157889366149902, | |
| "eval_runtime": 53.6061, | |
| "eval_samples_per_second": 310.618, | |
| "eval_steps_per_second": 19.419, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 5.835468095016302, | |
| "grad_norm": 0.29781579971313477, | |
| "learning_rate": 0.0005302888759464181, | |
| "loss": 3.5312, | |
| "step": 20050 | |
| }, | |
| { | |
| "epoch": 5.850023288309269, | |
| "grad_norm": 0.3068316578865051, | |
| "learning_rate": 0.0005301141525917298, | |
| "loss": 3.5282, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 5.864578481602235, | |
| "grad_norm": 0.31263458728790283, | |
| "learning_rate": 0.0005299394292370413, | |
| "loss": 3.5447, | |
| "step": 20150 | |
| }, | |
| { | |
| "epoch": 5.879133674895202, | |
| "grad_norm": 0.2962178587913513, | |
| "learning_rate": 0.0005297647058823528, | |
| "loss": 3.5259, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 5.893688868188169, | |
| "grad_norm": 0.3038765788078308, | |
| "learning_rate": 0.0005295899825276645, | |
| "loss": 3.5315, | |
| "step": 20250 | |
| }, | |
| { | |
| "epoch": 5.9082440614811365, | |
| "grad_norm": 0.32189029455184937, | |
| "learning_rate": 0.000529415259172976, | |
| "loss": 3.5406, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 5.9227992547741035, | |
| "grad_norm": 0.3118089735507965, | |
| "learning_rate": 0.0005292405358182877, | |
| "loss": 3.537, | |
| "step": 20350 | |
| }, | |
| { | |
| "epoch": 5.937354448067071, | |
| "grad_norm": 0.30968233942985535, | |
| "learning_rate": 0.0005290658124635992, | |
| "loss": 3.5417, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 5.951909641360038, | |
| "grad_norm": 0.3084794580936432, | |
| "learning_rate": 0.0005288910891089109, | |
| "loss": 3.5398, | |
| "step": 20450 | |
| }, | |
| { | |
| "epoch": 5.966464834653004, | |
| "grad_norm": 0.31465908885002136, | |
| "learning_rate": 0.0005287163657542224, | |
| "loss": 3.5291, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 5.981020027945971, | |
| "grad_norm": 0.3140786290168762, | |
| "learning_rate": 0.000528541642399534, | |
| "loss": 3.5343, | |
| "step": 20550 | |
| }, | |
| { | |
| "epoch": 5.995575221238938, | |
| "grad_norm": 0.2930114269256592, | |
| "learning_rate": 0.0005283669190448456, | |
| "loss": 3.5233, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 6.009897531439218, | |
| "grad_norm": 0.3094162046909332, | |
| "learning_rate": 0.0005281921956901572, | |
| "loss": 3.4567, | |
| "step": 20650 | |
| }, | |
| { | |
| "epoch": 6.024452724732185, | |
| "grad_norm": 0.3112754225730896, | |
| "learning_rate": 0.0005280174723354688, | |
| "loss": 3.4106, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 6.039007918025152, | |
| "grad_norm": 0.30582156777381897, | |
| "learning_rate": 0.0005278427489807804, | |
| "loss": 3.4274, | |
| "step": 20750 | |
| }, | |
| { | |
| "epoch": 6.053563111318118, | |
| "grad_norm": 0.31653255224227905, | |
| "learning_rate": 0.000527668025626092, | |
| "loss": 3.4263, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 6.068118304611085, | |
| "grad_norm": 0.3210879862308502, | |
| "learning_rate": 0.0005274933022714035, | |
| "loss": 3.4292, | |
| "step": 20850 | |
| }, | |
| { | |
| "epoch": 6.082673497904052, | |
| "grad_norm": 0.3249121904373169, | |
| "learning_rate": 0.0005273185789167152, | |
| "loss": 3.4442, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 6.097228691197019, | |
| "grad_norm": 0.3032764494419098, | |
| "learning_rate": 0.0005271438555620268, | |
| "loss": 3.4349, | |
| "step": 20950 | |
| }, | |
| { | |
| "epoch": 6.111783884489986, | |
| "grad_norm": 0.35914888978004456, | |
| "learning_rate": 0.0005269691322073384, | |
| "loss": 3.4527, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 6.111783884489986, | |
| "eval_accuracy": 0.3623956812946244, | |
| "eval_loss": 3.618173360824585, | |
| "eval_runtime": 53.9899, | |
| "eval_samples_per_second": 308.409, | |
| "eval_steps_per_second": 19.281, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 6.126339077782953, | |
| "grad_norm": 0.33278241753578186, | |
| "learning_rate": 0.0005267944088526499, | |
| "loss": 3.446, | |
| "step": 21050 | |
| }, | |
| { | |
| "epoch": 6.14089427107592, | |
| "grad_norm": 0.31333133578300476, | |
| "learning_rate": 0.0005266196854979615, | |
| "loss": 3.4412, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 6.155449464368886, | |
| "grad_norm": 0.3065875172615051, | |
| "learning_rate": 0.0005264449621432731, | |
| "loss": 3.4523, | |
| "step": 21150 | |
| }, | |
| { | |
| "epoch": 6.1700046576618535, | |
| "grad_norm": 0.32322120666503906, | |
| "learning_rate": 0.0005262702387885847, | |
| "loss": 3.4413, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 6.1845598509548205, | |
| "grad_norm": 0.32490748167037964, | |
| "learning_rate": 0.0005260955154338963, | |
| "loss": 3.461, | |
| "step": 21250 | |
| }, | |
| { | |
| "epoch": 6.199115044247788, | |
| "grad_norm": 0.3132990598678589, | |
| "learning_rate": 0.0005259207920792079, | |
| "loss": 3.4587, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 6.213670237540755, | |
| "grad_norm": 0.32926660776138306, | |
| "learning_rate": 0.0005257460687245195, | |
| "loss": 3.4522, | |
| "step": 21350 | |
| }, | |
| { | |
| "epoch": 6.228225430833722, | |
| "grad_norm": 0.3084983229637146, | |
| "learning_rate": 0.000525571345369831, | |
| "loss": 3.4546, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 6.242780624126689, | |
| "grad_norm": 0.3506135642528534, | |
| "learning_rate": 0.0005253966220151426, | |
| "loss": 3.4693, | |
| "step": 21450 | |
| }, | |
| { | |
| "epoch": 6.257335817419655, | |
| "grad_norm": 0.32451874017715454, | |
| "learning_rate": 0.0005252218986604543, | |
| "loss": 3.4747, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 6.271891010712622, | |
| "grad_norm": 0.3317224383354187, | |
| "learning_rate": 0.0005250471753057658, | |
| "loss": 3.4666, | |
| "step": 21550 | |
| }, | |
| { | |
| "epoch": 6.286446204005589, | |
| "grad_norm": 0.33130785822868347, | |
| "learning_rate": 0.0005248724519510774, | |
| "loss": 3.4683, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 6.301001397298556, | |
| "grad_norm": 0.3203778564929962, | |
| "learning_rate": 0.000524697728596389, | |
| "loss": 3.4639, | |
| "step": 21650 | |
| }, | |
| { | |
| "epoch": 6.315556590591523, | |
| "grad_norm": 0.3058604300022125, | |
| "learning_rate": 0.0005245230052417006, | |
| "loss": 3.4635, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 6.33011178388449, | |
| "grad_norm": 0.3277004659175873, | |
| "learning_rate": 0.0005243482818870122, | |
| "loss": 3.4654, | |
| "step": 21750 | |
| }, | |
| { | |
| "epoch": 6.344666977177457, | |
| "grad_norm": 0.31842777132987976, | |
| "learning_rate": 0.0005241735585323238, | |
| "loss": 3.4715, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 6.3592221704704235, | |
| "grad_norm": 0.30943790078163147, | |
| "learning_rate": 0.0005239988351776354, | |
| "loss": 3.4671, | |
| "step": 21850 | |
| }, | |
| { | |
| "epoch": 6.3737773637633905, | |
| "grad_norm": 0.3115125298500061, | |
| "learning_rate": 0.0005238241118229469, | |
| "loss": 3.4732, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 6.388332557056358, | |
| "grad_norm": 0.31756898760795593, | |
| "learning_rate": 0.0005236493884682585, | |
| "loss": 3.4651, | |
| "step": 21950 | |
| }, | |
| { | |
| "epoch": 6.402887750349325, | |
| "grad_norm": 0.3247394561767578, | |
| "learning_rate": 0.0005234746651135701, | |
| "loss": 3.4793, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.402887750349325, | |
| "eval_accuracy": 0.3631419796839949, | |
| "eval_loss": 3.6109635829925537, | |
| "eval_runtime": 53.4636, | |
| "eval_samples_per_second": 311.445, | |
| "eval_steps_per_second": 19.471, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 6.417442943642292, | |
| "grad_norm": 0.3089781701564789, | |
| "learning_rate": 0.0005232999417588818, | |
| "loss": 3.4666, | |
| "step": 22050 | |
| }, | |
| { | |
| "epoch": 6.431998136935259, | |
| "grad_norm": 0.31042516231536865, | |
| "learning_rate": 0.0005231252184041933, | |
| "loss": 3.4744, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 6.446553330228225, | |
| "grad_norm": 0.3057999014854431, | |
| "learning_rate": 0.0005229504950495049, | |
| "loss": 3.4702, | |
| "step": 22150 | |
| }, | |
| { | |
| "epoch": 6.461108523521192, | |
| "grad_norm": 0.30431073904037476, | |
| "learning_rate": 0.0005227757716948165, | |
| "loss": 3.4779, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 6.475663716814159, | |
| "grad_norm": 0.30396607518196106, | |
| "learning_rate": 0.000522601048340128, | |
| "loss": 3.4672, | |
| "step": 22250 | |
| }, | |
| { | |
| "epoch": 6.490218910107126, | |
| "grad_norm": 0.31502944231033325, | |
| "learning_rate": 0.0005224263249854397, | |
| "loss": 3.4799, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 6.504774103400093, | |
| "grad_norm": 0.3416776657104492, | |
| "learning_rate": 0.0005222516016307512, | |
| "loss": 3.4984, | |
| "step": 22350 | |
| }, | |
| { | |
| "epoch": 6.51932929669306, | |
| "grad_norm": 0.34649500250816345, | |
| "learning_rate": 0.0005220768782760629, | |
| "loss": 3.4869, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 6.533884489986027, | |
| "grad_norm": 0.3153761029243469, | |
| "learning_rate": 0.0005219021549213744, | |
| "loss": 3.4728, | |
| "step": 22450 | |
| }, | |
| { | |
| "epoch": 6.548439683278994, | |
| "grad_norm": 0.3142518997192383, | |
| "learning_rate": 0.000521727431566686, | |
| "loss": 3.4902, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 6.562994876571961, | |
| "grad_norm": 0.3267630934715271, | |
| "learning_rate": 0.0005215527082119976, | |
| "loss": 3.4784, | |
| "step": 22550 | |
| }, | |
| { | |
| "epoch": 6.577550069864928, | |
| "grad_norm": 0.30600109696388245, | |
| "learning_rate": 0.0005213779848573093, | |
| "loss": 3.4834, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 6.592105263157895, | |
| "grad_norm": 0.3079717755317688, | |
| "learning_rate": 0.0005212032615026208, | |
| "loss": 3.4899, | |
| "step": 22650 | |
| }, | |
| { | |
| "epoch": 6.606660456450862, | |
| "grad_norm": 0.32500362396240234, | |
| "learning_rate": 0.0005210285381479323, | |
| "loss": 3.4772, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 6.621215649743829, | |
| "grad_norm": 0.3158945143222809, | |
| "learning_rate": 0.000520853814793244, | |
| "loss": 3.4839, | |
| "step": 22750 | |
| }, | |
| { | |
| "epoch": 6.635770843036796, | |
| "grad_norm": 0.32037046551704407, | |
| "learning_rate": 0.0005206790914385555, | |
| "loss": 3.4834, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 6.650326036329762, | |
| "grad_norm": 0.30490437150001526, | |
| "learning_rate": 0.0005205043680838672, | |
| "loss": 3.4913, | |
| "step": 22850 | |
| }, | |
| { | |
| "epoch": 6.664881229622729, | |
| "grad_norm": 0.30731284618377686, | |
| "learning_rate": 0.0005203296447291787, | |
| "loss": 3.4731, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 6.679436422915696, | |
| "grad_norm": 0.30813777446746826, | |
| "learning_rate": 0.0005201549213744904, | |
| "loss": 3.4966, | |
| "step": 22950 | |
| }, | |
| { | |
| "epoch": 6.693991616208663, | |
| "grad_norm": 0.32473137974739075, | |
| "learning_rate": 0.0005199801980198019, | |
| "loss": 3.4844, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 6.693991616208663, | |
| "eval_accuracy": 0.3636337139298416, | |
| "eval_loss": 3.604031801223755, | |
| "eval_runtime": 53.646, | |
| "eval_samples_per_second": 310.386, | |
| "eval_steps_per_second": 19.405, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 6.70854680950163, | |
| "grad_norm": 0.31980106234550476, | |
| "learning_rate": 0.0005198054746651136, | |
| "loss": 3.4825, | |
| "step": 23050 | |
| }, | |
| { | |
| "epoch": 6.723102002794597, | |
| "grad_norm": 0.2905482053756714, | |
| "learning_rate": 0.0005196307513104251, | |
| "loss": 3.4965, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 6.737657196087564, | |
| "grad_norm": 0.3153842091560364, | |
| "learning_rate": 0.0005194560279557367, | |
| "loss": 3.4976, | |
| "step": 23150 | |
| }, | |
| { | |
| "epoch": 6.752212389380531, | |
| "grad_norm": 0.3169231116771698, | |
| "learning_rate": 0.0005192813046010483, | |
| "loss": 3.4793, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 6.766767582673498, | |
| "grad_norm": 0.3269803822040558, | |
| "learning_rate": 0.0005191065812463599, | |
| "loss": 3.5008, | |
| "step": 23250 | |
| }, | |
| { | |
| "epoch": 6.781322775966465, | |
| "grad_norm": 0.3197972774505615, | |
| "learning_rate": 0.0005189318578916715, | |
| "loss": 3.4907, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 6.795877969259432, | |
| "grad_norm": 0.2970565855503082, | |
| "learning_rate": 0.000518757134536983, | |
| "loss": 3.4893, | |
| "step": 23350 | |
| }, | |
| { | |
| "epoch": 6.810433162552399, | |
| "grad_norm": 0.2955489754676819, | |
| "learning_rate": 0.0005185824111822947, | |
| "loss": 3.4904, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 6.824988355845366, | |
| "grad_norm": 0.30435895919799805, | |
| "learning_rate": 0.0005184076878276063, | |
| "loss": 3.5053, | |
| "step": 23450 | |
| }, | |
| { | |
| "epoch": 6.839543549138332, | |
| "grad_norm": 0.31593433022499084, | |
| "learning_rate": 0.0005182329644729179, | |
| "loss": 3.4939, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 6.854098742431299, | |
| "grad_norm": 0.3007795512676239, | |
| "learning_rate": 0.0005180582411182294, | |
| "loss": 3.4875, | |
| "step": 23550 | |
| }, | |
| { | |
| "epoch": 6.868653935724266, | |
| "grad_norm": 0.29918912053108215, | |
| "learning_rate": 0.000517883517763541, | |
| "loss": 3.4991, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 6.883209129017233, | |
| "grad_norm": 0.335203617811203, | |
| "learning_rate": 0.0005177087944088526, | |
| "loss": 3.4863, | |
| "step": 23650 | |
| }, | |
| { | |
| "epoch": 6.8977643223102, | |
| "grad_norm": 0.3322928845882416, | |
| "learning_rate": 0.0005175340710541642, | |
| "loss": 3.498, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 6.912319515603167, | |
| "grad_norm": 0.31045687198638916, | |
| "learning_rate": 0.0005173593476994758, | |
| "loss": 3.4955, | |
| "step": 23750 | |
| }, | |
| { | |
| "epoch": 6.926874708896134, | |
| "grad_norm": 0.34360310435295105, | |
| "learning_rate": 0.0005171846243447874, | |
| "loss": 3.4912, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 6.9414299021891015, | |
| "grad_norm": 0.30857187509536743, | |
| "learning_rate": 0.000517009900990099, | |
| "loss": 3.4815, | |
| "step": 23850 | |
| }, | |
| { | |
| "epoch": 6.955985095482068, | |
| "grad_norm": 0.3461898863315582, | |
| "learning_rate": 0.0005168351776354105, | |
| "loss": 3.4992, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 6.970540288775035, | |
| "grad_norm": 0.30683234333992004, | |
| "learning_rate": 0.0005166604542807221, | |
| "loss": 3.4976, | |
| "step": 23950 | |
| }, | |
| { | |
| "epoch": 6.985095482068002, | |
| "grad_norm": 0.34013286232948303, | |
| "learning_rate": 0.0005164857309260338, | |
| "loss": 3.499, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 6.985095482068002, | |
| "eval_accuracy": 0.3646574942872915, | |
| "eval_loss": 3.592878580093384, | |
| "eval_runtime": 53.4717, | |
| "eval_samples_per_second": 311.398, | |
| "eval_steps_per_second": 19.468, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 6.999650675360969, | |
| "grad_norm": 0.3229374885559082, | |
| "learning_rate": 0.0005163110075713453, | |
| "loss": 3.4981, | |
| "step": 24050 | |
| }, | |
| { | |
| "epoch": 7.0139729855612485, | |
| "grad_norm": 0.3400660455226898, | |
| "learning_rate": 0.0005161362842166569, | |
| "loss": 3.3897, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 7.0285281788542155, | |
| "grad_norm": 0.3460919260978699, | |
| "learning_rate": 0.0005159615608619685, | |
| "loss": 3.3941, | |
| "step": 24150 | |
| }, | |
| { | |
| "epoch": 7.043083372147182, | |
| "grad_norm": 0.30968958139419556, | |
| "learning_rate": 0.0005157868375072801, | |
| "loss": 3.3861, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 7.057638565440149, | |
| "grad_norm": 0.3293498158454895, | |
| "learning_rate": 0.0005156121141525917, | |
| "loss": 3.3853, | |
| "step": 24250 | |
| }, | |
| { | |
| "epoch": 7.072193758733116, | |
| "grad_norm": 0.344931036233902, | |
| "learning_rate": 0.0005154373907979033, | |
| "loss": 3.3909, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 7.086748952026083, | |
| "grad_norm": 0.3015292286872864, | |
| "learning_rate": 0.0005152626674432149, | |
| "loss": 3.3954, | |
| "step": 24350 | |
| }, | |
| { | |
| "epoch": 7.10130414531905, | |
| "grad_norm": 0.3357579708099365, | |
| "learning_rate": 0.0005150879440885264, | |
| "loss": 3.3955, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 7.115859338612017, | |
| "grad_norm": 0.34056004881858826, | |
| "learning_rate": 0.000514913220733838, | |
| "loss": 3.4115, | |
| "step": 24450 | |
| }, | |
| { | |
| "epoch": 7.130414531904984, | |
| "grad_norm": 0.35026246309280396, | |
| "learning_rate": 0.0005147384973791496, | |
| "loss": 3.4147, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 7.14496972519795, | |
| "grad_norm": 0.3078658878803253, | |
| "learning_rate": 0.0005145637740244613, | |
| "loss": 3.4131, | |
| "step": 24550 | |
| }, | |
| { | |
| "epoch": 7.159524918490917, | |
| "grad_norm": 0.3245953917503357, | |
| "learning_rate": 0.0005143890506697728, | |
| "loss": 3.4116, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 7.174080111783884, | |
| "grad_norm": 0.31279706954956055, | |
| "learning_rate": 0.0005142143273150844, | |
| "loss": 3.4178, | |
| "step": 24650 | |
| }, | |
| { | |
| "epoch": 7.1886353050768514, | |
| "grad_norm": 0.32999566197395325, | |
| "learning_rate": 0.000514039603960396, | |
| "loss": 3.4103, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 7.2031904983698185, | |
| "grad_norm": 0.3385637402534485, | |
| "learning_rate": 0.0005138648806057075, | |
| "loss": 3.4181, | |
| "step": 24750 | |
| }, | |
| { | |
| "epoch": 7.217745691662786, | |
| "grad_norm": 0.32742172479629517, | |
| "learning_rate": 0.0005136901572510192, | |
| "loss": 3.4213, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 7.232300884955753, | |
| "grad_norm": 0.34171661734580994, | |
| "learning_rate": 0.0005135154338963307, | |
| "loss": 3.4221, | |
| "step": 24850 | |
| }, | |
| { | |
| "epoch": 7.246856078248719, | |
| "grad_norm": 0.32661959528923035, | |
| "learning_rate": 0.0005133407105416424, | |
| "loss": 3.4365, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 7.261411271541686, | |
| "grad_norm": 0.33498385548591614, | |
| "learning_rate": 0.0005131659871869539, | |
| "loss": 3.4272, | |
| "step": 24950 | |
| }, | |
| { | |
| "epoch": 7.275966464834653, | |
| "grad_norm": 0.32916367053985596, | |
| "learning_rate": 0.0005129912638322656, | |
| "loss": 3.4161, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 7.275966464834653, | |
| "eval_accuracy": 0.36435509653046466, | |
| "eval_loss": 3.5989937782287598, | |
| "eval_runtime": 53.4679, | |
| "eval_samples_per_second": 311.421, | |
| "eval_steps_per_second": 19.47, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 7.29052165812762, | |
| "grad_norm": 0.3240163326263428, | |
| "learning_rate": 0.0005128165404775771, | |
| "loss": 3.4296, | |
| "step": 25050 | |
| }, | |
| { | |
| "epoch": 7.305076851420587, | |
| "grad_norm": 0.35457611083984375, | |
| "learning_rate": 0.0005126418171228888, | |
| "loss": 3.4249, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 7.319632044713554, | |
| "grad_norm": 0.3302605450153351, | |
| "learning_rate": 0.0005124670937682003, | |
| "loss": 3.4259, | |
| "step": 25150 | |
| }, | |
| { | |
| "epoch": 7.334187238006521, | |
| "grad_norm": 0.3313428461551666, | |
| "learning_rate": 0.000512292370413512, | |
| "loss": 3.4399, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 7.348742431299487, | |
| "grad_norm": 0.31213662028312683, | |
| "learning_rate": 0.0005121176470588235, | |
| "loss": 3.4378, | |
| "step": 25250 | |
| }, | |
| { | |
| "epoch": 7.363297624592454, | |
| "grad_norm": 0.30027875304222107, | |
| "learning_rate": 0.000511942923704135, | |
| "loss": 3.4527, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 7.3778528178854215, | |
| "grad_norm": 0.30463436245918274, | |
| "learning_rate": 0.0005117682003494467, | |
| "loss": 3.4396, | |
| "step": 25350 | |
| }, | |
| { | |
| "epoch": 7.3924080111783885, | |
| "grad_norm": 0.31254589557647705, | |
| "learning_rate": 0.0005115934769947583, | |
| "loss": 3.4356, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 7.406963204471356, | |
| "grad_norm": 0.3229205310344696, | |
| "learning_rate": 0.0005114187536400699, | |
| "loss": 3.4315, | |
| "step": 25450 | |
| }, | |
| { | |
| "epoch": 7.421518397764323, | |
| "grad_norm": 0.33431607484817505, | |
| "learning_rate": 0.0005112440302853814, | |
| "loss": 3.4381, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 7.436073591057289, | |
| "grad_norm": 0.3249758780002594, | |
| "learning_rate": 0.0005110693069306931, | |
| "loss": 3.429, | |
| "step": 25550 | |
| }, | |
| { | |
| "epoch": 7.450628784350256, | |
| "grad_norm": 0.33510854840278625, | |
| "learning_rate": 0.0005108945835760046, | |
| "loss": 3.4515, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 7.465183977643223, | |
| "grad_norm": 0.32908889651298523, | |
| "learning_rate": 0.0005107198602213162, | |
| "loss": 3.4504, | |
| "step": 25650 | |
| }, | |
| { | |
| "epoch": 7.47973917093619, | |
| "grad_norm": 0.32020148634910583, | |
| "learning_rate": 0.0005105451368666278, | |
| "loss": 3.4553, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 7.494294364229157, | |
| "grad_norm": 0.30864962935447693, | |
| "learning_rate": 0.0005103704135119394, | |
| "loss": 3.4491, | |
| "step": 25750 | |
| }, | |
| { | |
| "epoch": 7.508849557522124, | |
| "grad_norm": 0.3200761377811432, | |
| "learning_rate": 0.000510195690157251, | |
| "loss": 3.4494, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 7.523404750815091, | |
| "grad_norm": 0.338183730840683, | |
| "learning_rate": 0.0005100209668025625, | |
| "loss": 3.4418, | |
| "step": 25850 | |
| }, | |
| { | |
| "epoch": 7.537959944108058, | |
| "grad_norm": 0.33356398344039917, | |
| "learning_rate": 0.0005098462434478742, | |
| "loss": 3.4379, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 7.552515137401024, | |
| "grad_norm": 0.345225989818573, | |
| "learning_rate": 0.0005096715200931858, | |
| "loss": 3.4491, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 7.5670703306939915, | |
| "grad_norm": 0.31163063645362854, | |
| "learning_rate": 0.0005094967967384974, | |
| "loss": 3.4466, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 7.5670703306939915, | |
| "eval_accuracy": 0.3652886159173576, | |
| "eval_loss": 3.590536594390869, | |
| "eval_runtime": 53.5061, | |
| "eval_samples_per_second": 311.198, | |
| "eval_steps_per_second": 19.456, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 7.5816255239869585, | |
| "grad_norm": 0.31356167793273926, | |
| "learning_rate": 0.0005093220733838089, | |
| "loss": 3.4472, | |
| "step": 26050 | |
| }, | |
| { | |
| "epoch": 7.596180717279926, | |
| "grad_norm": 0.3393348455429077, | |
| "learning_rate": 0.0005091473500291205, | |
| "loss": 3.4443, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 7.610735910572893, | |
| "grad_norm": 0.3119184076786041, | |
| "learning_rate": 0.0005089726266744321, | |
| "loss": 3.4468, | |
| "step": 26150 | |
| }, | |
| { | |
| "epoch": 7.625291103865859, | |
| "grad_norm": 0.3315845727920532, | |
| "learning_rate": 0.0005087979033197437, | |
| "loss": 3.4539, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 7.639846297158826, | |
| "grad_norm": 0.320338636636734, | |
| "learning_rate": 0.0005086231799650553, | |
| "loss": 3.4474, | |
| "step": 26250 | |
| }, | |
| { | |
| "epoch": 7.654401490451793, | |
| "grad_norm": 0.32066449522972107, | |
| "learning_rate": 0.0005084484566103669, | |
| "loss": 3.4558, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 7.66895668374476, | |
| "grad_norm": 0.3109360337257385, | |
| "learning_rate": 0.0005082737332556785, | |
| "loss": 3.4583, | |
| "step": 26350 | |
| }, | |
| { | |
| "epoch": 7.683511877037727, | |
| "grad_norm": 0.3201594352722168, | |
| "learning_rate": 0.00050809900990099, | |
| "loss": 3.4475, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 7.698067070330694, | |
| "grad_norm": 0.3280045986175537, | |
| "learning_rate": 0.0005079242865463016, | |
| "loss": 3.4577, | |
| "step": 26450 | |
| }, | |
| { | |
| "epoch": 7.712622263623661, | |
| "grad_norm": 0.31701672077178955, | |
| "learning_rate": 0.0005077495631916133, | |
| "loss": 3.4675, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 7.727177456916628, | |
| "grad_norm": 0.2981622815132141, | |
| "learning_rate": 0.0005075748398369248, | |
| "loss": 3.4597, | |
| "step": 26550 | |
| }, | |
| { | |
| "epoch": 7.7417326502095944, | |
| "grad_norm": 0.3085087239742279, | |
| "learning_rate": 0.0005074001164822364, | |
| "loss": 3.4549, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 7.7562878435025615, | |
| "grad_norm": 0.3165584206581116, | |
| "learning_rate": 0.000507225393127548, | |
| "loss": 3.4614, | |
| "step": 26650 | |
| }, | |
| { | |
| "epoch": 7.770843036795529, | |
| "grad_norm": 0.3389250636100769, | |
| "learning_rate": 0.0005070506697728596, | |
| "loss": 3.4621, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 7.785398230088496, | |
| "grad_norm": 0.3131444752216339, | |
| "learning_rate": 0.0005068759464181711, | |
| "loss": 3.4643, | |
| "step": 26750 | |
| }, | |
| { | |
| "epoch": 7.799953423381463, | |
| "grad_norm": 0.335517019033432, | |
| "learning_rate": 0.0005067012230634828, | |
| "loss": 3.4609, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 7.81450861667443, | |
| "grad_norm": 0.34369874000549316, | |
| "learning_rate": 0.0005065264997087944, | |
| "loss": 3.4608, | |
| "step": 26850 | |
| }, | |
| { | |
| "epoch": 7.829063809967396, | |
| "grad_norm": 0.3121283948421478, | |
| "learning_rate": 0.0005063517763541059, | |
| "loss": 3.4573, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 7.843619003260363, | |
| "grad_norm": 0.31813764572143555, | |
| "learning_rate": 0.0005061770529994175, | |
| "loss": 3.4573, | |
| "step": 26950 | |
| }, | |
| { | |
| "epoch": 7.85817419655333, | |
| "grad_norm": 0.30594533681869507, | |
| "learning_rate": 0.0005060023296447291, | |
| "loss": 3.4735, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 7.85817419655333, | |
| "eval_accuracy": 0.3660463144553532, | |
| "eval_loss": 3.5821263790130615, | |
| "eval_runtime": 53.6189, | |
| "eval_samples_per_second": 310.543, | |
| "eval_steps_per_second": 19.415, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 7.872729389846297, | |
| "grad_norm": 0.309291809797287, | |
| "learning_rate": 0.0005058276062900408, | |
| "loss": 3.4539, | |
| "step": 27050 | |
| }, | |
| { | |
| "epoch": 7.887284583139264, | |
| "grad_norm": 0.3263564705848694, | |
| "learning_rate": 0.0005056528829353523, | |
| "loss": 3.462, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 7.901839776432231, | |
| "grad_norm": 0.3128431737422943, | |
| "learning_rate": 0.000505478159580664, | |
| "loss": 3.4666, | |
| "step": 27150 | |
| }, | |
| { | |
| "epoch": 7.916394969725198, | |
| "grad_norm": 0.31295517086982727, | |
| "learning_rate": 0.0005053034362259755, | |
| "loss": 3.4704, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 7.930950163018165, | |
| "grad_norm": 0.3190186023712158, | |
| "learning_rate": 0.000505128712871287, | |
| "loss": 3.4628, | |
| "step": 27250 | |
| }, | |
| { | |
| "epoch": 7.9455053563111315, | |
| "grad_norm": 0.3315710723400116, | |
| "learning_rate": 0.0005049539895165987, | |
| "loss": 3.4639, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 7.960060549604099, | |
| "grad_norm": 0.33073070645332336, | |
| "learning_rate": 0.0005047792661619103, | |
| "loss": 3.4571, | |
| "step": 27350 | |
| }, | |
| { | |
| "epoch": 7.974615742897066, | |
| "grad_norm": 0.3234557509422302, | |
| "learning_rate": 0.0005046045428072219, | |
| "loss": 3.4678, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 7.989170936190033, | |
| "grad_norm": 0.3079441487789154, | |
| "learning_rate": 0.0005044298194525334, | |
| "loss": 3.448, | |
| "step": 27450 | |
| }, | |
| { | |
| "epoch": 8.003493246390311, | |
| "grad_norm": 0.3294244408607483, | |
| "learning_rate": 0.0005042550960978451, | |
| "loss": 3.4457, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 8.018048439683279, | |
| "grad_norm": 0.3271176517009735, | |
| "learning_rate": 0.0005040803727431566, | |
| "loss": 3.3592, | |
| "step": 27550 | |
| }, | |
| { | |
| "epoch": 8.032603632976246, | |
| "grad_norm": 0.36440953612327576, | |
| "learning_rate": 0.0005039056493884683, | |
| "loss": 3.3512, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 8.047158826269213, | |
| "grad_norm": 0.33122166991233826, | |
| "learning_rate": 0.0005037309260337798, | |
| "loss": 3.3586, | |
| "step": 27650 | |
| }, | |
| { | |
| "epoch": 8.06171401956218, | |
| "grad_norm": 0.3192889988422394, | |
| "learning_rate": 0.0005035562026790914, | |
| "loss": 3.3678, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 8.076269212855147, | |
| "grad_norm": 0.3358326554298401, | |
| "learning_rate": 0.000503381479324403, | |
| "loss": 3.3635, | |
| "step": 27750 | |
| }, | |
| { | |
| "epoch": 8.090824406148114, | |
| "grad_norm": 0.3561082184314728, | |
| "learning_rate": 0.0005032067559697145, | |
| "loss": 3.367, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 8.10537959944108, | |
| "grad_norm": 0.32903578877449036, | |
| "learning_rate": 0.0005030320326150262, | |
| "loss": 3.3573, | |
| "step": 27850 | |
| }, | |
| { | |
| "epoch": 8.119934792734048, | |
| "grad_norm": 0.32894840836524963, | |
| "learning_rate": 0.0005028573092603378, | |
| "loss": 3.3777, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 8.134489986027015, | |
| "grad_norm": 0.3106652796268463, | |
| "learning_rate": 0.0005026825859056494, | |
| "loss": 3.3871, | |
| "step": 27950 | |
| }, | |
| { | |
| "epoch": 8.149045179319982, | |
| "grad_norm": 0.3522495925426483, | |
| "learning_rate": 0.0005025078625509609, | |
| "loss": 3.3832, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 8.149045179319982, | |
| "eval_accuracy": 0.36594289042659006, | |
| "eval_loss": 3.5890581607818604, | |
| "eval_runtime": 53.5088, | |
| "eval_samples_per_second": 311.182, | |
| "eval_steps_per_second": 19.455, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 8.16360037261295, | |
| "grad_norm": 0.325960248708725, | |
| "learning_rate": 0.0005023331391962726, | |
| "loss": 3.3837, | |
| "step": 28050 | |
| }, | |
| { | |
| "epoch": 8.178155565905914, | |
| "grad_norm": 0.3273632526397705, | |
| "learning_rate": 0.0005021584158415841, | |
| "loss": 3.3826, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 8.192710759198881, | |
| "grad_norm": 0.3462362289428711, | |
| "learning_rate": 0.0005019836924868956, | |
| "loss": 3.3913, | |
| "step": 28150 | |
| }, | |
| { | |
| "epoch": 8.207265952491849, | |
| "grad_norm": 0.3270246684551239, | |
| "learning_rate": 0.0005018089691322073, | |
| "loss": 3.3921, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 8.221821145784816, | |
| "grad_norm": 0.3435835838317871, | |
| "learning_rate": 0.0005016342457775189, | |
| "loss": 3.3929, | |
| "step": 28250 | |
| }, | |
| { | |
| "epoch": 8.236376339077783, | |
| "grad_norm": 0.3535560965538025, | |
| "learning_rate": 0.0005014595224228305, | |
| "loss": 3.3816, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 8.25093153237075, | |
| "grad_norm": 0.3386369049549103, | |
| "learning_rate": 0.000501284799068142, | |
| "loss": 3.3919, | |
| "step": 28350 | |
| }, | |
| { | |
| "epoch": 8.265486725663717, | |
| "grad_norm": 0.3253107964992523, | |
| "learning_rate": 0.0005011100757134537, | |
| "loss": 3.3888, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 8.280041918956684, | |
| "grad_norm": 0.3146268129348755, | |
| "learning_rate": 0.0005009353523587653, | |
| "loss": 3.4049, | |
| "step": 28450 | |
| }, | |
| { | |
| "epoch": 8.294597112249651, | |
| "grad_norm": 0.35696449875831604, | |
| "learning_rate": 0.0005007606290040768, | |
| "loss": 3.3973, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 8.309152305542618, | |
| "grad_norm": 0.33402693271636963, | |
| "learning_rate": 0.0005005859056493884, | |
| "loss": 3.3875, | |
| "step": 28550 | |
| }, | |
| { | |
| "epoch": 8.323707498835585, | |
| "grad_norm": 0.3531701862812042, | |
| "learning_rate": 0.0005004111822947, | |
| "loss": 3.3834, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 8.338262692128552, | |
| "grad_norm": 0.34805771708488464, | |
| "learning_rate": 0.0005002364589400116, | |
| "loss": 3.4097, | |
| "step": 28650 | |
| }, | |
| { | |
| "epoch": 8.35281788542152, | |
| "grad_norm": 0.3358565866947174, | |
| "learning_rate": 0.0005000617355853231, | |
| "loss": 3.4048, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 8.367373078714486, | |
| "grad_norm": 0.33866482973098755, | |
| "learning_rate": 0.0004998870122306348, | |
| "loss": 3.4187, | |
| "step": 28750 | |
| }, | |
| { | |
| "epoch": 8.381928272007451, | |
| "grad_norm": 0.3327217102050781, | |
| "learning_rate": 0.0004997122888759464, | |
| "loss": 3.4142, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 8.396483465300419, | |
| "grad_norm": 0.33813586831092834, | |
| "learning_rate": 0.000499537565521258, | |
| "loss": 3.418, | |
| "step": 28850 | |
| }, | |
| { | |
| "epoch": 8.411038658593386, | |
| "grad_norm": 0.36705687642097473, | |
| "learning_rate": 0.0004993628421665695, | |
| "loss": 3.4168, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 8.425593851886353, | |
| "grad_norm": 0.32936182618141174, | |
| "learning_rate": 0.0004991881188118811, | |
| "loss": 3.4037, | |
| "step": 28950 | |
| }, | |
| { | |
| "epoch": 8.44014904517932, | |
| "grad_norm": 0.3183658719062805, | |
| "learning_rate": 0.0004990133954571928, | |
| "loss": 3.4061, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 8.44014904517932, | |
| "eval_accuracy": 0.366401952081532, | |
| "eval_loss": 3.5882623195648193, | |
| "eval_runtime": 53.5627, | |
| "eval_samples_per_second": 310.87, | |
| "eval_steps_per_second": 19.435, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 8.454704238472287, | |
| "grad_norm": 0.3316691219806671, | |
| "learning_rate": 0.0004988386721025043, | |
| "loss": 3.4064, | |
| "step": 29050 | |
| }, | |
| { | |
| "epoch": 8.469259431765254, | |
| "grad_norm": 0.3135945796966553, | |
| "learning_rate": 0.0004986639487478159, | |
| "loss": 3.4144, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 8.483814625058221, | |
| "grad_norm": 0.32762661576271057, | |
| "learning_rate": 0.0004984892253931275, | |
| "loss": 3.4138, | |
| "step": 29150 | |
| }, | |
| { | |
| "epoch": 8.498369818351188, | |
| "grad_norm": 0.3320242762565613, | |
| "learning_rate": 0.0004983145020384391, | |
| "loss": 3.4011, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 8.512925011644155, | |
| "grad_norm": 0.3420940935611725, | |
| "learning_rate": 0.0004981397786837507, | |
| "loss": 3.4034, | |
| "step": 29250 | |
| }, | |
| { | |
| "epoch": 8.527480204937122, | |
| "grad_norm": 0.33658385276794434, | |
| "learning_rate": 0.0004979650553290622, | |
| "loss": 3.4354, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 8.54203539823009, | |
| "grad_norm": 0.32970625162124634, | |
| "learning_rate": 0.0004977903319743739, | |
| "loss": 3.4415, | |
| "step": 29350 | |
| }, | |
| { | |
| "epoch": 8.556590591523056, | |
| "grad_norm": 0.34258556365966797, | |
| "learning_rate": 0.0004976156086196854, | |
| "loss": 3.4226, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 8.571145784816022, | |
| "grad_norm": 0.31930723786354065, | |
| "learning_rate": 0.0004974408852649971, | |
| "loss": 3.4215, | |
| "step": 29450 | |
| }, | |
| { | |
| "epoch": 8.585700978108989, | |
| "grad_norm": 0.34728145599365234, | |
| "learning_rate": 0.0004972661619103086, | |
| "loss": 3.4191, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 8.600256171401956, | |
| "grad_norm": 0.3359016478061676, | |
| "learning_rate": 0.0004970914385556202, | |
| "loss": 3.4252, | |
| "step": 29550 | |
| }, | |
| { | |
| "epoch": 8.614811364694923, | |
| "grad_norm": 0.30271053314208984, | |
| "learning_rate": 0.0004969167152009318, | |
| "loss": 3.4247, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 8.62936655798789, | |
| "grad_norm": 0.309200644493103, | |
| "learning_rate": 0.0004967419918462435, | |
| "loss": 3.4306, | |
| "step": 29650 | |
| }, | |
| { | |
| "epoch": 8.643921751280857, | |
| "grad_norm": 0.334758460521698, | |
| "learning_rate": 0.000496567268491555, | |
| "loss": 3.4198, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 8.658476944573824, | |
| "grad_norm": 0.3610553741455078, | |
| "learning_rate": 0.0004963925451368665, | |
| "loss": 3.4329, | |
| "step": 29750 | |
| }, | |
| { | |
| "epoch": 8.673032137866791, | |
| "grad_norm": 0.3275277316570282, | |
| "learning_rate": 0.0004962178217821782, | |
| "loss": 3.4342, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 8.687587331159758, | |
| "grad_norm": 0.32418811321258545, | |
| "learning_rate": 0.0004960430984274898, | |
| "loss": 3.4298, | |
| "step": 29850 | |
| }, | |
| { | |
| "epoch": 8.702142524452725, | |
| "grad_norm": 0.33169177174568176, | |
| "learning_rate": 0.0004958683750728014, | |
| "loss": 3.4236, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 8.716697717745692, | |
| "grad_norm": 0.31390687823295593, | |
| "learning_rate": 0.0004956936517181129, | |
| "loss": 3.4272, | |
| "step": 29950 | |
| }, | |
| { | |
| "epoch": 8.73125291103866, | |
| "grad_norm": 0.33808067440986633, | |
| "learning_rate": 0.0004955189283634246, | |
| "loss": 3.4397, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 8.73125291103866, | |
| "eval_accuracy": 0.3670959508199939, | |
| "eval_loss": 3.575246810913086, | |
| "eval_runtime": 53.6626, | |
| "eval_samples_per_second": 310.291, | |
| "eval_steps_per_second": 19.399, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 8.745808104331626, | |
| "grad_norm": 0.3337753117084503, | |
| "learning_rate": 0.0004953442050087361, | |
| "loss": 3.4366, | |
| "step": 30050 | |
| }, | |
| { | |
| "epoch": 8.760363297624593, | |
| "grad_norm": 0.32397356629371643, | |
| "learning_rate": 0.0004951694816540476, | |
| "loss": 3.4108, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 8.774918490917559, | |
| "grad_norm": 0.3341643512248993, | |
| "learning_rate": 0.0004949947582993593, | |
| "loss": 3.4279, | |
| "step": 30150 | |
| }, | |
| { | |
| "epoch": 8.789473684210526, | |
| "grad_norm": 0.3121252954006195, | |
| "learning_rate": 0.0004948200349446709, | |
| "loss": 3.4261, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 8.804028877503493, | |
| "grad_norm": 0.32449105381965637, | |
| "learning_rate": 0.0004946453115899825, | |
| "loss": 3.4314, | |
| "step": 30250 | |
| }, | |
| { | |
| "epoch": 8.81858407079646, | |
| "grad_norm": 0.33881548047065735, | |
| "learning_rate": 0.000494470588235294, | |
| "loss": 3.4257, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 8.833139264089427, | |
| "grad_norm": 0.3309210538864136, | |
| "learning_rate": 0.0004942958648806057, | |
| "loss": 3.4298, | |
| "step": 30350 | |
| }, | |
| { | |
| "epoch": 8.847694457382394, | |
| "grad_norm": 0.3625873923301697, | |
| "learning_rate": 0.0004941211415259173, | |
| "loss": 3.431, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 8.862249650675361, | |
| "grad_norm": 0.34724485874176025, | |
| "learning_rate": 0.0004939464181712289, | |
| "loss": 3.4347, | |
| "step": 30450 | |
| }, | |
| { | |
| "epoch": 8.876804843968328, | |
| "grad_norm": 0.3242975175380707, | |
| "learning_rate": 0.0004937716948165404, | |
| "loss": 3.4422, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 8.891360037261295, | |
| "grad_norm": 0.37616708874702454, | |
| "learning_rate": 0.000493596971461852, | |
| "loss": 3.442, | |
| "step": 30550 | |
| }, | |
| { | |
| "epoch": 8.905915230554262, | |
| "grad_norm": 0.347936749458313, | |
| "learning_rate": 0.0004934222481071636, | |
| "loss": 3.4328, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 8.92047042384723, | |
| "grad_norm": 0.3136371970176697, | |
| "learning_rate": 0.0004932475247524751, | |
| "loss": 3.4431, | |
| "step": 30650 | |
| }, | |
| { | |
| "epoch": 8.935025617140196, | |
| "grad_norm": 0.3110552430152893, | |
| "learning_rate": 0.0004930728013977868, | |
| "loss": 3.4431, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 8.949580810433163, | |
| "grad_norm": 0.31664732098579407, | |
| "learning_rate": 0.0004928980780430984, | |
| "loss": 3.4381, | |
| "step": 30750 | |
| }, | |
| { | |
| "epoch": 8.964136003726129, | |
| "grad_norm": 0.32102662324905396, | |
| "learning_rate": 0.00049272335468841, | |
| "loss": 3.4354, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 8.978691197019096, | |
| "grad_norm": 0.3171549439430237, | |
| "learning_rate": 0.0004925486313337215, | |
| "loss": 3.4459, | |
| "step": 30850 | |
| }, | |
| { | |
| "epoch": 8.993246390312063, | |
| "grad_norm": 0.29721736907958984, | |
| "learning_rate": 0.0004923739079790332, | |
| "loss": 3.4271, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 9.007568700512342, | |
| "grad_norm": 0.31595897674560547, | |
| "learning_rate": 0.0004921991846243447, | |
| "loss": 3.3793, | |
| "step": 30950 | |
| }, | |
| { | |
| "epoch": 9.02212389380531, | |
| "grad_norm": 0.3319658637046814, | |
| "learning_rate": 0.0004920244612696563, | |
| "loss": 3.3148, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 9.02212389380531, | |
| "eval_accuracy": 0.3673293600485435, | |
| "eval_loss": 3.584437847137451, | |
| "eval_runtime": 53.4398, | |
| "eval_samples_per_second": 311.585, | |
| "eval_steps_per_second": 19.48, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 9.036679087098276, | |
| "grad_norm": 0.33615490794181824, | |
| "learning_rate": 0.0004918497379149679, | |
| "loss": 3.3357, | |
| "step": 31050 | |
| }, | |
| { | |
| "epoch": 9.051234280391244, | |
| "grad_norm": 0.3399544060230255, | |
| "learning_rate": 0.0004916750145602795, | |
| "loss": 3.3366, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 9.06578947368421, | |
| "grad_norm": 0.34134435653686523, | |
| "learning_rate": 0.0004915002912055911, | |
| "loss": 3.3354, | |
| "step": 31150 | |
| }, | |
| { | |
| "epoch": 9.080344666977178, | |
| "grad_norm": 0.33406949043273926, | |
| "learning_rate": 0.0004913255678509026, | |
| "loss": 3.3474, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 9.094899860270145, | |
| "grad_norm": 0.3663691282272339, | |
| "learning_rate": 0.0004911508444962143, | |
| "loss": 3.3471, | |
| "step": 31250 | |
| }, | |
| { | |
| "epoch": 9.109455053563112, | |
| "grad_norm": 0.3201402723789215, | |
| "learning_rate": 0.0004909761211415259, | |
| "loss": 3.3545, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 9.124010246856079, | |
| "grad_norm": 0.33595725893974304, | |
| "learning_rate": 0.0004908013977868375, | |
| "loss": 3.3566, | |
| "step": 31350 | |
| }, | |
| { | |
| "epoch": 9.138565440149046, | |
| "grad_norm": 0.31587278842926025, | |
| "learning_rate": 0.0004906266744321491, | |
| "loss": 3.3434, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 9.153120633442011, | |
| "grad_norm": 0.3046572208404541, | |
| "learning_rate": 0.0004904519510774606, | |
| "loss": 3.3444, | |
| "step": 31450 | |
| }, | |
| { | |
| "epoch": 9.167675826734978, | |
| "grad_norm": 0.29908108711242676, | |
| "learning_rate": 0.0004902772277227722, | |
| "loss": 3.3674, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 9.182231020027945, | |
| "grad_norm": 0.3269266188144684, | |
| "learning_rate": 0.0004901025043680838, | |
| "loss": 3.36, | |
| "step": 31550 | |
| }, | |
| { | |
| "epoch": 9.196786213320912, | |
| "grad_norm": 0.35173773765563965, | |
| "learning_rate": 0.0004899277810133955, | |
| "loss": 3.3578, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 9.21134140661388, | |
| "grad_norm": 0.33379629254341125, | |
| "learning_rate": 0.000489753057658707, | |
| "loss": 3.3639, | |
| "step": 31650 | |
| }, | |
| { | |
| "epoch": 9.225896599906847, | |
| "grad_norm": 0.3437906503677368, | |
| "learning_rate": 0.0004895783343040186, | |
| "loss": 3.3716, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 9.240451793199814, | |
| "grad_norm": 0.3263828456401825, | |
| "learning_rate": 0.0004894036109493302, | |
| "loss": 3.3673, | |
| "step": 31750 | |
| }, | |
| { | |
| "epoch": 9.25500698649278, | |
| "grad_norm": 0.31504547595977783, | |
| "learning_rate": 0.0004892288875946419, | |
| "loss": 3.3613, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 9.269562179785748, | |
| "grad_norm": 0.3566463887691498, | |
| "learning_rate": 0.0004890541642399534, | |
| "loss": 3.3731, | |
| "step": 31850 | |
| }, | |
| { | |
| "epoch": 9.284117373078715, | |
| "grad_norm": 0.3411761224269867, | |
| "learning_rate": 0.0004888794408852649, | |
| "loss": 3.3771, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 9.298672566371682, | |
| "grad_norm": 0.3087772727012634, | |
| "learning_rate": 0.0004887047175305766, | |
| "loss": 3.3791, | |
| "step": 31950 | |
| }, | |
| { | |
| "epoch": 9.313227759664649, | |
| "grad_norm": 0.3811226487159729, | |
| "learning_rate": 0.0004885299941758881, | |
| "loss": 3.3641, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 9.313227759664649, | |
| "eval_accuracy": 0.3673082051335692, | |
| "eval_loss": 3.5798377990722656, | |
| "eval_runtime": 53.5284, | |
| "eval_samples_per_second": 311.068, | |
| "eval_steps_per_second": 19.448, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 9.327782952957616, | |
| "grad_norm": 0.3283770978450775, | |
| "learning_rate": 0.0004883552708211997, | |
| "loss": 3.3783, | |
| "step": 32050 | |
| }, | |
| { | |
| "epoch": 9.342338146250583, | |
| "grad_norm": 0.3225921392440796, | |
| "learning_rate": 0.00048818054746651137, | |
| "loss": 3.3715, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 9.356893339543548, | |
| "grad_norm": 0.3263804018497467, | |
| "learning_rate": 0.0004880058241118229, | |
| "loss": 3.3794, | |
| "step": 32150 | |
| }, | |
| { | |
| "epoch": 9.371448532836515, | |
| "grad_norm": 0.3523861765861511, | |
| "learning_rate": 0.0004878311007571345, | |
| "loss": 3.3802, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 9.386003726129482, | |
| "grad_norm": 0.3211838901042938, | |
| "learning_rate": 0.0004876563774024461, | |
| "loss": 3.3856, | |
| "step": 32250 | |
| }, | |
| { | |
| "epoch": 9.40055891942245, | |
| "grad_norm": 0.3431154489517212, | |
| "learning_rate": 0.00048748165404775763, | |
| "loss": 3.3882, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 9.415114112715417, | |
| "grad_norm": 0.3309096395969391, | |
| "learning_rate": 0.0004873069306930693, | |
| "loss": 3.3809, | |
| "step": 32350 | |
| }, | |
| { | |
| "epoch": 9.429669306008384, | |
| "grad_norm": 0.3327443599700928, | |
| "learning_rate": 0.0004871322073383809, | |
| "loss": 3.3886, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 9.44422449930135, | |
| "grad_norm": 0.35989439487457275, | |
| "learning_rate": 0.00048695748398369247, | |
| "loss": 3.3915, | |
| "step": 32450 | |
| }, | |
| { | |
| "epoch": 9.458779692594318, | |
| "grad_norm": 0.3196500539779663, | |
| "learning_rate": 0.000486782760629004, | |
| "loss": 3.3882, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 9.473334885887285, | |
| "grad_norm": 0.33183974027633667, | |
| "learning_rate": 0.0004866080372743156, | |
| "loss": 3.383, | |
| "step": 32550 | |
| }, | |
| { | |
| "epoch": 9.487890079180252, | |
| "grad_norm": 0.34491536021232605, | |
| "learning_rate": 0.0004864333139196272, | |
| "loss": 3.3949, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 9.502445272473219, | |
| "grad_norm": 0.3412875831127167, | |
| "learning_rate": 0.00048625859056493885, | |
| "loss": 3.392, | |
| "step": 32650 | |
| }, | |
| { | |
| "epoch": 9.517000465766186, | |
| "grad_norm": 0.3379037082195282, | |
| "learning_rate": 0.0004860838672102504, | |
| "loss": 3.3952, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 9.531555659059153, | |
| "grad_norm": 0.324245810508728, | |
| "learning_rate": 0.000485909143855562, | |
| "loss": 3.3996, | |
| "step": 32750 | |
| }, | |
| { | |
| "epoch": 9.546110852352118, | |
| "grad_norm": 0.31969350576400757, | |
| "learning_rate": 0.0004857344205008736, | |
| "loss": 3.3922, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 9.560666045645085, | |
| "grad_norm": 0.3300749957561493, | |
| "learning_rate": 0.00048555969714618517, | |
| "loss": 3.3892, | |
| "step": 32850 | |
| }, | |
| { | |
| "epoch": 9.575221238938052, | |
| "grad_norm": 0.32830169796943665, | |
| "learning_rate": 0.0004853849737914967, | |
| "loss": 3.3947, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 9.58977643223102, | |
| "grad_norm": 0.32420819997787476, | |
| "learning_rate": 0.00048521025043680836, | |
| "loss": 3.3991, | |
| "step": 32950 | |
| }, | |
| { | |
| "epoch": 9.604331625523987, | |
| "grad_norm": 0.30296534299850464, | |
| "learning_rate": 0.00048503552708211995, | |
| "loss": 3.3934, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 9.604331625523987, | |
| "eval_accuracy": 0.36784906579307836, | |
| "eval_loss": 3.5705058574676514, | |
| "eval_runtime": 53.7708, | |
| "eval_samples_per_second": 309.666, | |
| "eval_steps_per_second": 19.36, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 9.618886818816954, | |
| "grad_norm": 0.31142690777778625, | |
| "learning_rate": 0.00048486080372743155, | |
| "loss": 3.3946, | |
| "step": 33050 | |
| }, | |
| { | |
| "epoch": 9.63344201210992, | |
| "grad_norm": 0.31225040555000305, | |
| "learning_rate": 0.0004846860803727431, | |
| "loss": 3.4046, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 9.647997205402888, | |
| "grad_norm": 0.32433298230171204, | |
| "learning_rate": 0.0004845113570180547, | |
| "loss": 3.3981, | |
| "step": 33150 | |
| }, | |
| { | |
| "epoch": 9.662552398695855, | |
| "grad_norm": 0.32316821813583374, | |
| "learning_rate": 0.00048433663366336633, | |
| "loss": 3.402, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 9.677107591988822, | |
| "grad_norm": 0.3351520597934723, | |
| "learning_rate": 0.0004841619103086779, | |
| "loss": 3.4016, | |
| "step": 33250 | |
| }, | |
| { | |
| "epoch": 9.691662785281789, | |
| "grad_norm": 0.3141856789588928, | |
| "learning_rate": 0.00048398718695398947, | |
| "loss": 3.405, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 9.706217978574756, | |
| "grad_norm": 0.3592616319656372, | |
| "learning_rate": 0.00048381246359930106, | |
| "loss": 3.4049, | |
| "step": 33350 | |
| }, | |
| { | |
| "epoch": 9.720773171867723, | |
| "grad_norm": 0.32081735134124756, | |
| "learning_rate": 0.00048363774024461265, | |
| "loss": 3.4115, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 9.73532836516069, | |
| "grad_norm": 0.3009851574897766, | |
| "learning_rate": 0.0004834630168899242, | |
| "loss": 3.3909, | |
| "step": 33450 | |
| }, | |
| { | |
| "epoch": 9.749883558453657, | |
| "grad_norm": 0.33387187123298645, | |
| "learning_rate": 0.00048328829353523584, | |
| "loss": 3.4081, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 9.764438751746622, | |
| "grad_norm": 0.3098052144050598, | |
| "learning_rate": 0.00048311357018054744, | |
| "loss": 3.3973, | |
| "step": 33550 | |
| }, | |
| { | |
| "epoch": 9.77899394503959, | |
| "grad_norm": 0.3021669387817383, | |
| "learning_rate": 0.00048293884682585903, | |
| "loss": 3.4132, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 9.793549138332557, | |
| "grad_norm": 0.32370424270629883, | |
| "learning_rate": 0.00048276412347117057, | |
| "loss": 3.416, | |
| "step": 33650 | |
| }, | |
| { | |
| "epoch": 9.808104331625524, | |
| "grad_norm": 0.33125245571136475, | |
| "learning_rate": 0.00048258940011648217, | |
| "loss": 3.4056, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 9.82265952491849, | |
| "grad_norm": 0.34791597723960876, | |
| "learning_rate": 0.0004824146767617938, | |
| "loss": 3.4083, | |
| "step": 33750 | |
| }, | |
| { | |
| "epoch": 9.837214718211458, | |
| "grad_norm": 0.33894163370132446, | |
| "learning_rate": 0.0004822399534071054, | |
| "loss": 3.4095, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 9.851769911504425, | |
| "grad_norm": 0.34089744091033936, | |
| "learning_rate": 0.00048206523005241695, | |
| "loss": 3.4052, | |
| "step": 33850 | |
| }, | |
| { | |
| "epoch": 9.866325104797392, | |
| "grad_norm": 0.32176560163497925, | |
| "learning_rate": 0.00048189050669772854, | |
| "loss": 3.4052, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 9.880880298090359, | |
| "grad_norm": 0.30843693017959595, | |
| "learning_rate": 0.00048171578334304014, | |
| "loss": 3.408, | |
| "step": 33950 | |
| }, | |
| { | |
| "epoch": 9.895435491383326, | |
| "grad_norm": 0.3197186589241028, | |
| "learning_rate": 0.00048154105998835173, | |
| "loss": 3.4221, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 9.895435491383326, | |
| "eval_accuracy": 0.3684403456666096, | |
| "eval_loss": 3.5624873638153076, | |
| "eval_runtime": 53.5688, | |
| "eval_samples_per_second": 310.834, | |
| "eval_steps_per_second": 19.433, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 9.909990684676293, | |
| "grad_norm": 0.32542476058006287, | |
| "learning_rate": 0.0004813663366336633, | |
| "loss": 3.4105, | |
| "step": 34050 | |
| }, | |
| { | |
| "epoch": 9.92454587796926, | |
| "grad_norm": 0.29410064220428467, | |
| "learning_rate": 0.0004811916132789749, | |
| "loss": 3.4167, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 9.939101071262227, | |
| "grad_norm": 0.339298278093338, | |
| "learning_rate": 0.0004810168899242865, | |
| "loss": 3.3989, | |
| "step": 34150 | |
| }, | |
| { | |
| "epoch": 9.953656264555192, | |
| "grad_norm": 0.3445450961589813, | |
| "learning_rate": 0.0004808421665695981, | |
| "loss": 3.4142, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 9.96821145784816, | |
| "grad_norm": 0.3291611671447754, | |
| "learning_rate": 0.00048066744321490965, | |
| "loss": 3.4111, | |
| "step": 34250 | |
| }, | |
| { | |
| "epoch": 9.982766651141127, | |
| "grad_norm": 0.3134865462779999, | |
| "learning_rate": 0.00048049271986022124, | |
| "loss": 3.4177, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 9.997321844434094, | |
| "grad_norm": 0.3462051451206207, | |
| "learning_rate": 0.0004803179965055329, | |
| "loss": 3.4163, | |
| "step": 34350 | |
| }, | |
| { | |
| "epoch": 10.011644154634373, | |
| "grad_norm": 0.31786805391311646, | |
| "learning_rate": 0.0004801432731508445, | |
| "loss": 3.3261, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 10.02619934792734, | |
| "grad_norm": 0.309844434261322, | |
| "learning_rate": 0.000479968549796156, | |
| "loss": 3.2984, | |
| "step": 34450 | |
| }, | |
| { | |
| "epoch": 10.040754541220307, | |
| "grad_norm": 0.3425449728965759, | |
| "learning_rate": 0.0004797938264414676, | |
| "loss": 3.3042, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 10.055309734513274, | |
| "grad_norm": 0.32120344042778015, | |
| "learning_rate": 0.0004796191030867792, | |
| "loss": 3.3027, | |
| "step": 34550 | |
| }, | |
| { | |
| "epoch": 10.069864927806242, | |
| "grad_norm": 0.327881395816803, | |
| "learning_rate": 0.00047944437973209086, | |
| "loss": 3.312, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 10.084420121099209, | |
| "grad_norm": 0.3291587233543396, | |
| "learning_rate": 0.0004792696563774024, | |
| "loss": 3.3266, | |
| "step": 34650 | |
| }, | |
| { | |
| "epoch": 10.098975314392176, | |
| "grad_norm": 0.3266242742538452, | |
| "learning_rate": 0.000479094933022714, | |
| "loss": 3.3322, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 10.113530507685143, | |
| "grad_norm": 0.3427068293094635, | |
| "learning_rate": 0.0004789202096680256, | |
| "loss": 3.3216, | |
| "step": 34750 | |
| }, | |
| { | |
| "epoch": 10.12808570097811, | |
| "grad_norm": 0.3500446379184723, | |
| "learning_rate": 0.00047874548631333713, | |
| "loss": 3.3286, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 10.142640894271075, | |
| "grad_norm": 0.3395751416683197, | |
| "learning_rate": 0.0004785707629586487, | |
| "loss": 3.3327, | |
| "step": 34850 | |
| }, | |
| { | |
| "epoch": 10.157196087564042, | |
| "grad_norm": 0.34043699502944946, | |
| "learning_rate": 0.0004783960396039604, | |
| "loss": 3.3392, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 10.17175128085701, | |
| "grad_norm": 0.31045597791671753, | |
| "learning_rate": 0.00047822131624927197, | |
| "loss": 3.3325, | |
| "step": 34950 | |
| }, | |
| { | |
| "epoch": 10.186306474149976, | |
| "grad_norm": 0.3298252522945404, | |
| "learning_rate": 0.0004780465928945835, | |
| "loss": 3.3354, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 10.186306474149976, | |
| "eval_accuracy": 0.3681179682678626, | |
| "eval_loss": 3.5757086277008057, | |
| "eval_runtime": 53.4879, | |
| "eval_samples_per_second": 311.304, | |
| "eval_steps_per_second": 19.462, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 10.200861667442943, | |
| "grad_norm": 0.32574766874313354, | |
| "learning_rate": 0.0004778718695398951, | |
| "loss": 3.3398, | |
| "step": 35050 | |
| }, | |
| { | |
| "epoch": 10.21541686073591, | |
| "grad_norm": 0.33106088638305664, | |
| "learning_rate": 0.0004776971461852067, | |
| "loss": 3.332, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 10.229972054028877, | |
| "grad_norm": 0.32367774844169617, | |
| "learning_rate": 0.00047752242283051835, | |
| "loss": 3.3453, | |
| "step": 35150 | |
| }, | |
| { | |
| "epoch": 10.244527247321844, | |
| "grad_norm": 0.3259326219558716, | |
| "learning_rate": 0.00047734769947582994, | |
| "loss": 3.347, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 10.259082440614812, | |
| "grad_norm": 0.3162131905555725, | |
| "learning_rate": 0.0004771729761211415, | |
| "loss": 3.358, | |
| "step": 35250 | |
| }, | |
| { | |
| "epoch": 10.273637633907779, | |
| "grad_norm": 0.3248613178730011, | |
| "learning_rate": 0.0004769982527664531, | |
| "loss": 3.3467, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 10.288192827200746, | |
| "grad_norm": 0.34323063492774963, | |
| "learning_rate": 0.00047682352941176467, | |
| "loss": 3.3505, | |
| "step": 35350 | |
| }, | |
| { | |
| "epoch": 10.302748020493713, | |
| "grad_norm": 0.33190083503723145, | |
| "learning_rate": 0.0004766488060570762, | |
| "loss": 3.3551, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 10.31730321378668, | |
| "grad_norm": 0.33588477969169617, | |
| "learning_rate": 0.00047647408270238786, | |
| "loss": 3.3551, | |
| "step": 35450 | |
| }, | |
| { | |
| "epoch": 10.331858407079647, | |
| "grad_norm": 0.3292767107486725, | |
| "learning_rate": 0.00047629935934769945, | |
| "loss": 3.3662, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 10.346413600372612, | |
| "grad_norm": 0.33773326873779297, | |
| "learning_rate": 0.00047612463599301105, | |
| "loss": 3.3396, | |
| "step": 35550 | |
| }, | |
| { | |
| "epoch": 10.36096879366558, | |
| "grad_norm": 0.34879618883132935, | |
| "learning_rate": 0.0004759499126383226, | |
| "loss": 3.341, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 10.375523986958546, | |
| "grad_norm": 0.32844480872154236, | |
| "learning_rate": 0.0004757751892836342, | |
| "loss": 3.3544, | |
| "step": 35650 | |
| }, | |
| { | |
| "epoch": 10.390079180251513, | |
| "grad_norm": 0.33543866872787476, | |
| "learning_rate": 0.0004756004659289458, | |
| "loss": 3.3683, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 10.40463437354448, | |
| "grad_norm": 0.3378603756427765, | |
| "learning_rate": 0.0004754257425742574, | |
| "loss": 3.3553, | |
| "step": 35750 | |
| }, | |
| { | |
| "epoch": 10.419189566837447, | |
| "grad_norm": 0.337503582239151, | |
| "learning_rate": 0.00047525101921956896, | |
| "loss": 3.3682, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 10.433744760130415, | |
| "grad_norm": 0.32410839200019836, | |
| "learning_rate": 0.00047507629586488056, | |
| "loss": 3.3744, | |
| "step": 35850 | |
| }, | |
| { | |
| "epoch": 10.448299953423382, | |
| "grad_norm": 0.35159045457839966, | |
| "learning_rate": 0.00047490157251019215, | |
| "loss": 3.3561, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 10.462855146716349, | |
| "grad_norm": 0.3706214427947998, | |
| "learning_rate": 0.0004747268491555037, | |
| "loss": 3.375, | |
| "step": 35950 | |
| }, | |
| { | |
| "epoch": 10.477410340009316, | |
| "grad_norm": 0.34833791851997375, | |
| "learning_rate": 0.00047455212580081534, | |
| "loss": 3.3658, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 10.477410340009316, | |
| "eval_accuracy": 0.36844492923152067, | |
| "eval_loss": 3.568455457687378, | |
| "eval_runtime": 53.6229, | |
| "eval_samples_per_second": 310.52, | |
| "eval_steps_per_second": 19.413, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 10.491965533302283, | |
| "grad_norm": 0.348140686750412, | |
| "learning_rate": 0.00047437740244612694, | |
| "loss": 3.3706, | |
| "step": 36050 | |
| }, | |
| { | |
| "epoch": 10.50652072659525, | |
| "grad_norm": 0.34616634249687195, | |
| "learning_rate": 0.00047420267909143853, | |
| "loss": 3.3736, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 10.521075919888217, | |
| "grad_norm": 0.3239026367664337, | |
| "learning_rate": 0.0004740279557367501, | |
| "loss": 3.3807, | |
| "step": 36150 | |
| }, | |
| { | |
| "epoch": 10.535631113181182, | |
| "grad_norm": 0.32138124108314514, | |
| "learning_rate": 0.00047385323238206166, | |
| "loss": 3.3735, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 10.55018630647415, | |
| "grad_norm": 0.3209070861339569, | |
| "learning_rate": 0.00047367850902737326, | |
| "loss": 3.3716, | |
| "step": 36250 | |
| }, | |
| { | |
| "epoch": 10.564741499767116, | |
| "grad_norm": 0.33491426706314087, | |
| "learning_rate": 0.0004735037856726849, | |
| "loss": 3.3668, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 10.579296693060083, | |
| "grad_norm": 0.32375043630599976, | |
| "learning_rate": 0.0004733290623179965, | |
| "loss": 3.3762, | |
| "step": 36350 | |
| }, | |
| { | |
| "epoch": 10.59385188635305, | |
| "grad_norm": 0.3468237817287445, | |
| "learning_rate": 0.00047315433896330804, | |
| "loss": 3.3773, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 10.608407079646017, | |
| "grad_norm": 0.3716345727443695, | |
| "learning_rate": 0.00047297961560861964, | |
| "loss": 3.3786, | |
| "step": 36450 | |
| }, | |
| { | |
| "epoch": 10.622962272938985, | |
| "grad_norm": 0.348968505859375, | |
| "learning_rate": 0.00047280489225393123, | |
| "loss": 3.38, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 10.637517466231952, | |
| "grad_norm": 0.3269039988517761, | |
| "learning_rate": 0.0004726301688992429, | |
| "loss": 3.3683, | |
| "step": 36550 | |
| }, | |
| { | |
| "epoch": 10.652072659524919, | |
| "grad_norm": 0.3497937023639679, | |
| "learning_rate": 0.0004724554455445544, | |
| "loss": 3.3862, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 10.666627852817886, | |
| "grad_norm": 0.3173670172691345, | |
| "learning_rate": 0.000472280722189866, | |
| "loss": 3.3779, | |
| "step": 36650 | |
| }, | |
| { | |
| "epoch": 10.681183046110853, | |
| "grad_norm": 0.3418918251991272, | |
| "learning_rate": 0.0004721059988351776, | |
| "loss": 3.3814, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 10.69573823940382, | |
| "grad_norm": 0.3383764326572418, | |
| "learning_rate": 0.00047193127548048915, | |
| "loss": 3.3823, | |
| "step": 36750 | |
| }, | |
| { | |
| "epoch": 10.710293432696787, | |
| "grad_norm": 0.3304063081741333, | |
| "learning_rate": 0.00047175655212580074, | |
| "loss": 3.3765, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 10.724848625989754, | |
| "grad_norm": 0.3561539351940155, | |
| "learning_rate": 0.0004715818287711124, | |
| "loss": 3.3829, | |
| "step": 36850 | |
| }, | |
| { | |
| "epoch": 10.73940381928272, | |
| "grad_norm": 0.3793018162250519, | |
| "learning_rate": 0.000471407105416424, | |
| "loss": 3.3694, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 10.753959012575686, | |
| "grad_norm": 0.3463248610496521, | |
| "learning_rate": 0.0004712323820617355, | |
| "loss": 3.381, | |
| "step": 36950 | |
| }, | |
| { | |
| "epoch": 10.768514205868653, | |
| "grad_norm": 0.3424185514450073, | |
| "learning_rate": 0.0004710576587070471, | |
| "loss": 3.3732, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 10.768514205868653, | |
| "eval_accuracy": 0.36895346988204136, | |
| "eval_loss": 3.56215500831604, | |
| "eval_runtime": 53.4409, | |
| "eval_samples_per_second": 311.578, | |
| "eval_steps_per_second": 19.479, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 10.78306939916162, | |
| "grad_norm": 0.3367776870727539, | |
| "learning_rate": 0.0004708829353523587, | |
| "loss": 3.3869, | |
| "step": 37050 | |
| }, | |
| { | |
| "epoch": 10.797624592454587, | |
| "grad_norm": 0.336036741733551, | |
| "learning_rate": 0.0004707082119976703, | |
| "loss": 3.3825, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 10.812179785747555, | |
| "grad_norm": 0.326006680727005, | |
| "learning_rate": 0.0004705334886429819, | |
| "loss": 3.3806, | |
| "step": 37150 | |
| }, | |
| { | |
| "epoch": 10.826734979040522, | |
| "grad_norm": 0.3242209851741791, | |
| "learning_rate": 0.0004703587652882935, | |
| "loss": 3.3827, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 10.841290172333489, | |
| "grad_norm": 0.33953434228897095, | |
| "learning_rate": 0.0004701840419336051, | |
| "loss": 3.3933, | |
| "step": 37250 | |
| }, | |
| { | |
| "epoch": 10.855845365626456, | |
| "grad_norm": 0.33651044964790344, | |
| "learning_rate": 0.0004700093185789167, | |
| "loss": 3.3806, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 10.870400558919423, | |
| "grad_norm": 0.3412701189517975, | |
| "learning_rate": 0.0004698345952242282, | |
| "loss": 3.3959, | |
| "step": 37350 | |
| }, | |
| { | |
| "epoch": 10.88495575221239, | |
| "grad_norm": 0.32320114970207214, | |
| "learning_rate": 0.00046965987186953987, | |
| "loss": 3.3973, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 10.899510945505357, | |
| "grad_norm": 0.3424411714076996, | |
| "learning_rate": 0.00046948514851485147, | |
| "loss": 3.4029, | |
| "step": 37450 | |
| }, | |
| { | |
| "epoch": 10.914066138798324, | |
| "grad_norm": 0.341287225484848, | |
| "learning_rate": 0.00046931042516016306, | |
| "loss": 3.3832, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 10.92862133209129, | |
| "grad_norm": 0.3227987587451935, | |
| "learning_rate": 0.0004691357018054746, | |
| "loss": 3.3911, | |
| "step": 37550 | |
| }, | |
| { | |
| "epoch": 10.943176525384256, | |
| "grad_norm": 0.32630455493927, | |
| "learning_rate": 0.0004689609784507862, | |
| "loss": 3.3869, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 10.957731718677223, | |
| "grad_norm": 0.35883912444114685, | |
| "learning_rate": 0.0004687862550960978, | |
| "loss": 3.3981, | |
| "step": 37650 | |
| }, | |
| { | |
| "epoch": 10.97228691197019, | |
| "grad_norm": 0.31135573983192444, | |
| "learning_rate": 0.00046861153174140944, | |
| "loss": 3.3964, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 10.986842105263158, | |
| "grad_norm": 0.33533161878585815, | |
| "learning_rate": 0.000468436808386721, | |
| "loss": 3.4002, | |
| "step": 37750 | |
| }, | |
| { | |
| "epoch": 11.001164415463437, | |
| "grad_norm": 0.41261494159698486, | |
| "learning_rate": 0.0004682620850320326, | |
| "loss": 3.3873, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 11.015719608756404, | |
| "grad_norm": 0.32985225319862366, | |
| "learning_rate": 0.00046808736167734417, | |
| "loss": 3.2858, | |
| "step": 37850 | |
| }, | |
| { | |
| "epoch": 11.030274802049371, | |
| "grad_norm": 0.3471239507198334, | |
| "learning_rate": 0.0004679126383226557, | |
| "loss": 3.2893, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 11.044829995342338, | |
| "grad_norm": 0.33663108944892883, | |
| "learning_rate": 0.00046773791496796736, | |
| "loss": 3.2921, | |
| "step": 37950 | |
| }, | |
| { | |
| "epoch": 11.059385188635305, | |
| "grad_norm": 0.3395008146762848, | |
| "learning_rate": 0.00046756319161327895, | |
| "loss": 3.2937, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 11.059385188635305, | |
| "eval_accuracy": 0.36891045488826035, | |
| "eval_loss": 3.5691335201263428, | |
| "eval_runtime": 53.6637, | |
| "eval_samples_per_second": 310.284, | |
| "eval_steps_per_second": 19.399, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 11.073940381928272, | |
| "grad_norm": 0.3486023247241974, | |
| "learning_rate": 0.00046738846825859054, | |
| "loss": 3.3024, | |
| "step": 38050 | |
| }, | |
| { | |
| "epoch": 11.08849557522124, | |
| "grad_norm": 0.3424938917160034, | |
| "learning_rate": 0.0004672137449039021, | |
| "loss": 3.2947, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 11.103050768514207, | |
| "grad_norm": 0.3458380103111267, | |
| "learning_rate": 0.0004670390215492137, | |
| "loss": 3.3002, | |
| "step": 38150 | |
| }, | |
| { | |
| "epoch": 11.117605961807174, | |
| "grad_norm": 0.3442081809043884, | |
| "learning_rate": 0.0004668642981945253, | |
| "loss": 3.3061, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 11.132161155100139, | |
| "grad_norm": 0.32460713386535645, | |
| "learning_rate": 0.0004666895748398369, | |
| "loss": 3.2993, | |
| "step": 38250 | |
| }, | |
| { | |
| "epoch": 11.146716348393106, | |
| "grad_norm": 0.32236334681510925, | |
| "learning_rate": 0.00046651485148514846, | |
| "loss": 3.3226, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 11.161271541686073, | |
| "grad_norm": 0.3452746868133545, | |
| "learning_rate": 0.00046634012813046006, | |
| "loss": 3.316, | |
| "step": 38350 | |
| }, | |
| { | |
| "epoch": 11.17582673497904, | |
| "grad_norm": 0.3708697259426117, | |
| "learning_rate": 0.00046616540477577165, | |
| "loss": 3.325, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 11.190381928272007, | |
| "grad_norm": 0.35320329666137695, | |
| "learning_rate": 0.00046599068142108324, | |
| "loss": 3.3248, | |
| "step": 38450 | |
| }, | |
| { | |
| "epoch": 11.204937121564974, | |
| "grad_norm": 0.3435826897621155, | |
| "learning_rate": 0.0004658159580663948, | |
| "loss": 3.3144, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 11.219492314857941, | |
| "grad_norm": 0.36525121331214905, | |
| "learning_rate": 0.00046564123471170643, | |
| "loss": 3.3112, | |
| "step": 38550 | |
| }, | |
| { | |
| "epoch": 11.234047508150908, | |
| "grad_norm": 0.3306402862071991, | |
| "learning_rate": 0.00046546651135701803, | |
| "loss": 3.3181, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 11.248602701443875, | |
| "grad_norm": 0.33780917525291443, | |
| "learning_rate": 0.0004652917880023296, | |
| "loss": 3.3193, | |
| "step": 38650 | |
| }, | |
| { | |
| "epoch": 11.263157894736842, | |
| "grad_norm": 0.3386842608451843, | |
| "learning_rate": 0.00046511706464764116, | |
| "loss": 3.332, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 11.27771308802981, | |
| "grad_norm": 0.3490748703479767, | |
| "learning_rate": 0.00046494234129295276, | |
| "loss": 3.3336, | |
| "step": 38750 | |
| }, | |
| { | |
| "epoch": 11.292268281322777, | |
| "grad_norm": 0.35561442375183105, | |
| "learning_rate": 0.0004647676179382644, | |
| "loss": 3.3222, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 11.306823474615744, | |
| "grad_norm": 0.3507767915725708, | |
| "learning_rate": 0.000464592894583576, | |
| "loss": 3.3275, | |
| "step": 38850 | |
| }, | |
| { | |
| "epoch": 11.32137866790871, | |
| "grad_norm": 0.36345380544662476, | |
| "learning_rate": 0.00046441817122888754, | |
| "loss": 3.3286, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 11.335933861201676, | |
| "grad_norm": 0.35796356201171875, | |
| "learning_rate": 0.00046424344787419913, | |
| "loss": 3.339, | |
| "step": 38950 | |
| }, | |
| { | |
| "epoch": 11.350489054494643, | |
| "grad_norm": 0.34664463996887207, | |
| "learning_rate": 0.00046406872451951073, | |
| "loss": 3.333, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 11.350489054494643, | |
| "eval_accuracy": 0.36912470716602763, | |
| "eval_loss": 3.5678765773773193, | |
| "eval_runtime": 53.6239, | |
| "eval_samples_per_second": 310.514, | |
| "eval_steps_per_second": 19.413, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 11.36504424778761, | |
| "grad_norm": 0.3241993188858032, | |
| "learning_rate": 0.00046389400116482227, | |
| "loss": 3.3379, | |
| "step": 39050 | |
| }, | |
| { | |
| "epoch": 11.379599441080577, | |
| "grad_norm": 0.3430246114730835, | |
| "learning_rate": 0.0004637192778101339, | |
| "loss": 3.3427, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 11.394154634373544, | |
| "grad_norm": 0.36466196179389954, | |
| "learning_rate": 0.0004635445544554455, | |
| "loss": 3.3388, | |
| "step": 39150 | |
| }, | |
| { | |
| "epoch": 11.408709827666511, | |
| "grad_norm": 0.3346891701221466, | |
| "learning_rate": 0.0004633698311007571, | |
| "loss": 3.3454, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 11.423265020959478, | |
| "grad_norm": 0.3322499394416809, | |
| "learning_rate": 0.0004631951077460687, | |
| "loss": 3.3396, | |
| "step": 39250 | |
| }, | |
| { | |
| "epoch": 11.437820214252445, | |
| "grad_norm": 0.3287809491157532, | |
| "learning_rate": 0.00046302038439138024, | |
| "loss": 3.3433, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 11.452375407545413, | |
| "grad_norm": 0.37795814871788025, | |
| "learning_rate": 0.0004628456610366919, | |
| "loss": 3.3448, | |
| "step": 39350 | |
| }, | |
| { | |
| "epoch": 11.46693060083838, | |
| "grad_norm": 0.32181516289711, | |
| "learning_rate": 0.0004626709376820035, | |
| "loss": 3.337, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 11.481485794131347, | |
| "grad_norm": 0.33979737758636475, | |
| "learning_rate": 0.0004624962143273151, | |
| "loss": 3.3496, | |
| "step": 39450 | |
| }, | |
| { | |
| "epoch": 11.496040987424314, | |
| "grad_norm": 0.3518194258213043, | |
| "learning_rate": 0.0004623214909726266, | |
| "loss": 3.3555, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 11.51059618071728, | |
| "grad_norm": 0.34144338965415955, | |
| "learning_rate": 0.0004621467676179382, | |
| "loss": 3.355, | |
| "step": 39550 | |
| }, | |
| { | |
| "epoch": 11.525151374010246, | |
| "grad_norm": 0.32892072200775146, | |
| "learning_rate": 0.0004619720442632498, | |
| "loss": 3.3573, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 11.539706567303213, | |
| "grad_norm": 0.33298641443252563, | |
| "learning_rate": 0.00046179732090856145, | |
| "loss": 3.3612, | |
| "step": 39650 | |
| }, | |
| { | |
| "epoch": 11.55426176059618, | |
| "grad_norm": 0.31800341606140137, | |
| "learning_rate": 0.000461622597553873, | |
| "loss": 3.3588, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 11.568816953889147, | |
| "grad_norm": 0.31456729769706726, | |
| "learning_rate": 0.0004614478741991846, | |
| "loss": 3.3549, | |
| "step": 39750 | |
| }, | |
| { | |
| "epoch": 11.583372147182114, | |
| "grad_norm": 0.32660186290740967, | |
| "learning_rate": 0.0004612731508444962, | |
| "loss": 3.3585, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 11.597927340475081, | |
| "grad_norm": 0.3345406651496887, | |
| "learning_rate": 0.0004610984274898077, | |
| "loss": 3.3575, | |
| "step": 39850 | |
| }, | |
| { | |
| "epoch": 11.612482533768048, | |
| "grad_norm": 0.3572464883327484, | |
| "learning_rate": 0.00046092370413511937, | |
| "loss": 3.3578, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 11.627037727061015, | |
| "grad_norm": 0.33732089400291443, | |
| "learning_rate": 0.00046074898078043096, | |
| "loss": 3.3604, | |
| "step": 39950 | |
| }, | |
| { | |
| "epoch": 11.641592920353983, | |
| "grad_norm": 0.33168599009513855, | |
| "learning_rate": 0.00046057425742574256, | |
| "loss": 3.3593, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 11.641592920353983, | |
| "eval_accuracy": 0.3695037327259836, | |
| "eval_loss": 3.558704137802124, | |
| "eval_runtime": 53.4419, | |
| "eval_samples_per_second": 311.572, | |
| "eval_steps_per_second": 19.479, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 11.65614811364695, | |
| "grad_norm": 0.33097389340400696, | |
| "learning_rate": 0.0004603995340710541, | |
| "loss": 3.3595, | |
| "step": 40050 | |
| }, | |
| { | |
| "epoch": 11.670703306939917, | |
| "grad_norm": 0.32910600304603577, | |
| "learning_rate": 0.0004602248107163657, | |
| "loss": 3.3648, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 11.685258500232884, | |
| "grad_norm": 0.34012946486473083, | |
| "learning_rate": 0.0004600500873616773, | |
| "loss": 3.3683, | |
| "step": 40150 | |
| }, | |
| { | |
| "epoch": 11.69981369352585, | |
| "grad_norm": 0.36239832639694214, | |
| "learning_rate": 0.00045987536400698894, | |
| "loss": 3.3601, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 11.714368886818818, | |
| "grad_norm": 0.32226231694221497, | |
| "learning_rate": 0.0004597006406523005, | |
| "loss": 3.3569, | |
| "step": 40250 | |
| }, | |
| { | |
| "epoch": 11.728924080111783, | |
| "grad_norm": 0.3962358236312866, | |
| "learning_rate": 0.00045952591729761207, | |
| "loss": 3.3646, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 11.74347927340475, | |
| "grad_norm": 0.3227379322052002, | |
| "learning_rate": 0.00045935119394292367, | |
| "loss": 3.3607, | |
| "step": 40350 | |
| }, | |
| { | |
| "epoch": 11.758034466697717, | |
| "grad_norm": 0.34338995814323425, | |
| "learning_rate": 0.00045917647058823526, | |
| "loss": 3.3715, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 11.772589659990684, | |
| "grad_norm": 0.3215791583061218, | |
| "learning_rate": 0.0004590017472335468, | |
| "loss": 3.3743, | |
| "step": 40450 | |
| }, | |
| { | |
| "epoch": 11.787144853283651, | |
| "grad_norm": 0.3537582457065582, | |
| "learning_rate": 0.00045882702387885845, | |
| "loss": 3.3661, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 11.801700046576618, | |
| "grad_norm": 0.35051867365837097, | |
| "learning_rate": 0.00045865230052417004, | |
| "loss": 3.3551, | |
| "step": 40550 | |
| }, | |
| { | |
| "epoch": 11.816255239869585, | |
| "grad_norm": 0.34315794706344604, | |
| "learning_rate": 0.00045847757716948164, | |
| "loss": 3.3576, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 11.830810433162553, | |
| "grad_norm": 0.3305503726005554, | |
| "learning_rate": 0.0004583028538147932, | |
| "loss": 3.3675, | |
| "step": 40650 | |
| }, | |
| { | |
| "epoch": 11.84536562645552, | |
| "grad_norm": 0.3582182228565216, | |
| "learning_rate": 0.00045812813046010477, | |
| "loss": 3.3744, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 11.859920819748487, | |
| "grad_norm": 0.3373137414455414, | |
| "learning_rate": 0.0004579534071054164, | |
| "loss": 3.3682, | |
| "step": 40750 | |
| }, | |
| { | |
| "epoch": 11.874476013041454, | |
| "grad_norm": 0.32282936573028564, | |
| "learning_rate": 0.000457778683750728, | |
| "loss": 3.3615, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 11.88903120633442, | |
| "grad_norm": 0.33595630526542664, | |
| "learning_rate": 0.00045760396039603955, | |
| "loss": 3.3717, | |
| "step": 40850 | |
| }, | |
| { | |
| "epoch": 11.903586399627388, | |
| "grad_norm": 0.3551540970802307, | |
| "learning_rate": 0.00045742923704135115, | |
| "loss": 3.3717, | |
| "step": 40900 | |
| }, | |
| { | |
| "epoch": 11.918141592920353, | |
| "grad_norm": 0.34719353914260864, | |
| "learning_rate": 0.00045725451368666274, | |
| "loss": 3.3735, | |
| "step": 40950 | |
| }, | |
| { | |
| "epoch": 11.93269678621332, | |
| "grad_norm": 0.3262156546115875, | |
| "learning_rate": 0.0004570797903319743, | |
| "loss": 3.356, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 11.93269678621332, | |
| "eval_accuracy": 0.37028070574206684, | |
| "eval_loss": 3.5505871772766113, | |
| "eval_runtime": 53.3997, | |
| "eval_samples_per_second": 311.818, | |
| "eval_steps_per_second": 19.495, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 11.947251979506287, | |
| "grad_norm": 0.337962806224823, | |
| "learning_rate": 0.00045690506697728593, | |
| "loss": 3.3765, | |
| "step": 41050 | |
| }, | |
| { | |
| "epoch": 11.961807172799254, | |
| "grad_norm": 0.3479160666465759, | |
| "learning_rate": 0.0004567303436225975, | |
| "loss": 3.3675, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 11.976362366092221, | |
| "grad_norm": 0.3300924003124237, | |
| "learning_rate": 0.0004565556202679091, | |
| "loss": 3.3768, | |
| "step": 41150 | |
| }, | |
| { | |
| "epoch": 11.990917559385188, | |
| "grad_norm": 0.3442911207675934, | |
| "learning_rate": 0.00045638089691322066, | |
| "loss": 3.3644, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 12.005239869585468, | |
| "grad_norm": 0.39569589495658875, | |
| "learning_rate": 0.00045620617355853225, | |
| "loss": 3.3383, | |
| "step": 41250 | |
| }, | |
| { | |
| "epoch": 12.019795062878435, | |
| "grad_norm": 0.32977378368377686, | |
| "learning_rate": 0.0004560314502038439, | |
| "loss": 3.2589, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 12.034350256171402, | |
| "grad_norm": 0.35999372601509094, | |
| "learning_rate": 0.0004558567268491555, | |
| "loss": 3.2612, | |
| "step": 41350 | |
| }, | |
| { | |
| "epoch": 12.04890544946437, | |
| "grad_norm": 0.3495120108127594, | |
| "learning_rate": 0.00045568200349446704, | |
| "loss": 3.2638, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 12.063460642757336, | |
| "grad_norm": 0.3549163043498993, | |
| "learning_rate": 0.00045550728013977863, | |
| "loss": 3.2641, | |
| "step": 41450 | |
| }, | |
| { | |
| "epoch": 12.078015836050303, | |
| "grad_norm": 0.34798282384872437, | |
| "learning_rate": 0.0004553325567850902, | |
| "loss": 3.285, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 12.09257102934327, | |
| "grad_norm": 0.3600448966026306, | |
| "learning_rate": 0.0004551578334304018, | |
| "loss": 3.2748, | |
| "step": 41550 | |
| }, | |
| { | |
| "epoch": 12.107126222636236, | |
| "grad_norm": 0.322065532207489, | |
| "learning_rate": 0.00045498311007571347, | |
| "loss": 3.2894, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 12.121681415929203, | |
| "grad_norm": 0.3378659188747406, | |
| "learning_rate": 0.000454808386721025, | |
| "loss": 3.2923, | |
| "step": 41650 | |
| }, | |
| { | |
| "epoch": 12.13623660922217, | |
| "grad_norm": 0.3429020047187805, | |
| "learning_rate": 0.0004546336633663366, | |
| "loss": 3.2817, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 12.150791802515137, | |
| "grad_norm": 0.34111934900283813, | |
| "learning_rate": 0.0004544589400116482, | |
| "loss": 3.2788, | |
| "step": 41750 | |
| }, | |
| { | |
| "epoch": 12.165346995808104, | |
| "grad_norm": 0.3828873634338379, | |
| "learning_rate": 0.00045428421665695974, | |
| "loss": 3.298, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 12.179902189101071, | |
| "grad_norm": 0.34416258335113525, | |
| "learning_rate": 0.00045410949330227133, | |
| "loss": 3.2936, | |
| "step": 41850 | |
| }, | |
| { | |
| "epoch": 12.194457382394038, | |
| "grad_norm": 0.3474802076816559, | |
| "learning_rate": 0.000453934769947583, | |
| "loss": 3.2905, | |
| "step": 41900 | |
| }, | |
| { | |
| "epoch": 12.209012575687005, | |
| "grad_norm": 0.3587965965270996, | |
| "learning_rate": 0.0004537600465928946, | |
| "loss": 3.3073, | |
| "step": 41950 | |
| }, | |
| { | |
| "epoch": 12.223567768979972, | |
| "grad_norm": 0.3573007881641388, | |
| "learning_rate": 0.0004535853232382061, | |
| "loss": 3.3001, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 12.223567768979972, | |
| "eval_accuracy": 0.36961315064732275, | |
| "eval_loss": 3.5672249794006348, | |
| "eval_runtime": 53.5268, | |
| "eval_samples_per_second": 311.078, | |
| "eval_steps_per_second": 19.448, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 12.23812296227294, | |
| "grad_norm": 0.34919896721839905, | |
| "learning_rate": 0.0004534105998835177, | |
| "loss": 3.3091, | |
| "step": 42050 | |
| }, | |
| { | |
| "epoch": 12.252678155565906, | |
| "grad_norm": 0.3955753743648529, | |
| "learning_rate": 0.0004532358765288293, | |
| "loss": 3.3115, | |
| "step": 42100 | |
| }, | |
| { | |
| "epoch": 12.267233348858873, | |
| "grad_norm": 0.3572271168231964, | |
| "learning_rate": 0.00045306115317414095, | |
| "loss": 3.3013, | |
| "step": 42150 | |
| }, | |
| { | |
| "epoch": 12.28178854215184, | |
| "grad_norm": 0.34758853912353516, | |
| "learning_rate": 0.0004528864298194525, | |
| "loss": 3.3089, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 12.296343735444808, | |
| "grad_norm": 0.34926536679267883, | |
| "learning_rate": 0.0004527117064647641, | |
| "loss": 3.3297, | |
| "step": 42250 | |
| }, | |
| { | |
| "epoch": 12.310898928737773, | |
| "grad_norm": 0.3313453197479248, | |
| "learning_rate": 0.0004525369831100757, | |
| "loss": 3.313, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 12.32545412203074, | |
| "grad_norm": 0.32843706011772156, | |
| "learning_rate": 0.0004523622597553872, | |
| "loss": 3.3172, | |
| "step": 42350 | |
| }, | |
| { | |
| "epoch": 12.340009315323707, | |
| "grad_norm": 0.3525911569595337, | |
| "learning_rate": 0.0004521875364006988, | |
| "loss": 3.3252, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 12.354564508616674, | |
| "grad_norm": 0.3977005183696747, | |
| "learning_rate": 0.00045201281304601046, | |
| "loss": 3.3354, | |
| "step": 42450 | |
| }, | |
| { | |
| "epoch": 12.369119701909641, | |
| "grad_norm": 0.39300209283828735, | |
| "learning_rate": 0.00045183808969132206, | |
| "loss": 3.3309, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 12.383674895202608, | |
| "grad_norm": 0.33920717239379883, | |
| "learning_rate": 0.00045166336633663365, | |
| "loss": 3.3171, | |
| "step": 42550 | |
| }, | |
| { | |
| "epoch": 12.398230088495575, | |
| "grad_norm": 0.33965712785720825, | |
| "learning_rate": 0.0004514886429819452, | |
| "loss": 3.3235, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 12.412785281788542, | |
| "grad_norm": 0.35367551445961, | |
| "learning_rate": 0.0004513139196272568, | |
| "loss": 3.3296, | |
| "step": 42650 | |
| }, | |
| { | |
| "epoch": 12.42734047508151, | |
| "grad_norm": 0.34313255548477173, | |
| "learning_rate": 0.00045113919627256843, | |
| "loss": 3.3255, | |
| "step": 42700 | |
| }, | |
| { | |
| "epoch": 12.441895668374476, | |
| "grad_norm": 0.36909183859825134, | |
| "learning_rate": 0.00045096447291788003, | |
| "loss": 3.3208, | |
| "step": 42750 | |
| }, | |
| { | |
| "epoch": 12.456450861667443, | |
| "grad_norm": 0.3304850459098816, | |
| "learning_rate": 0.00045078974956319157, | |
| "loss": 3.3272, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 12.47100605496041, | |
| "grad_norm": 0.3269474506378174, | |
| "learning_rate": 0.00045061502620850316, | |
| "loss": 3.328, | |
| "step": 42850 | |
| }, | |
| { | |
| "epoch": 12.485561248253378, | |
| "grad_norm": 0.33981937170028687, | |
| "learning_rate": 0.00045044030285381476, | |
| "loss": 3.3302, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 12.500116441546343, | |
| "grad_norm": 0.3652309775352478, | |
| "learning_rate": 0.0004502655794991263, | |
| "loss": 3.3466, | |
| "step": 42950 | |
| }, | |
| { | |
| "epoch": 12.51467163483931, | |
| "grad_norm": 0.34370893239974976, | |
| "learning_rate": 0.00045009085614443795, | |
| "loss": 3.328, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 12.51467163483931, | |
| "eval_accuracy": 0.37014966279653166, | |
| "eval_loss": 3.5593037605285645, | |
| "eval_runtime": 53.4547, | |
| "eval_samples_per_second": 311.498, | |
| "eval_steps_per_second": 19.474, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 12.529226828132277, | |
| "grad_norm": 0.337211549282074, | |
| "learning_rate": 0.00044991613278974954, | |
| "loss": 3.3194, | |
| "step": 43050 | |
| }, | |
| { | |
| "epoch": 12.543782021425244, | |
| "grad_norm": 0.3669276833534241, | |
| "learning_rate": 0.00044974140943506113, | |
| "loss": 3.3313, | |
| "step": 43100 | |
| }, | |
| { | |
| "epoch": 12.558337214718211, | |
| "grad_norm": 0.3396778702735901, | |
| "learning_rate": 0.0004495666860803727, | |
| "loss": 3.3329, | |
| "step": 43150 | |
| }, | |
| { | |
| "epoch": 12.572892408011178, | |
| "grad_norm": 0.3290897011756897, | |
| "learning_rate": 0.00044939196272568427, | |
| "loss": 3.3412, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 12.587447601304145, | |
| "grad_norm": 0.34258797764778137, | |
| "learning_rate": 0.00044921723937099586, | |
| "loss": 3.3368, | |
| "step": 43250 | |
| }, | |
| { | |
| "epoch": 12.602002794597112, | |
| "grad_norm": 0.351852148771286, | |
| "learning_rate": 0.0004490425160163075, | |
| "loss": 3.3349, | |
| "step": 43300 | |
| }, | |
| { | |
| "epoch": 12.61655798789008, | |
| "grad_norm": 0.3397352695465088, | |
| "learning_rate": 0.00044886779266161905, | |
| "loss": 3.3417, | |
| "step": 43350 | |
| }, | |
| { | |
| "epoch": 12.631113181183046, | |
| "grad_norm": 0.3380641043186188, | |
| "learning_rate": 0.00044869306930693065, | |
| "loss": 3.3352, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 12.645668374476013, | |
| "grad_norm": 0.3385723829269409, | |
| "learning_rate": 0.00044851834595224224, | |
| "loss": 3.3431, | |
| "step": 43450 | |
| }, | |
| { | |
| "epoch": 12.66022356776898, | |
| "grad_norm": 0.32181715965270996, | |
| "learning_rate": 0.00044834362259755383, | |
| "loss": 3.3458, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 12.674778761061948, | |
| "grad_norm": 0.3412785232067108, | |
| "learning_rate": 0.00044816889924286543, | |
| "loss": 3.3435, | |
| "step": 43550 | |
| }, | |
| { | |
| "epoch": 12.689333954354915, | |
| "grad_norm": 0.33516597747802734, | |
| "learning_rate": 0.000447994175888177, | |
| "loss": 3.3546, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 12.703889147647882, | |
| "grad_norm": 0.3438853323459625, | |
| "learning_rate": 0.0004478194525334886, | |
| "loss": 3.3464, | |
| "step": 43650 | |
| }, | |
| { | |
| "epoch": 12.718444340940847, | |
| "grad_norm": 0.35373008251190186, | |
| "learning_rate": 0.0004476447291788002, | |
| "loss": 3.3483, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 12.732999534233814, | |
| "grad_norm": 0.3750246465206146, | |
| "learning_rate": 0.00044747000582411175, | |
| "loss": 3.3365, | |
| "step": 43750 | |
| }, | |
| { | |
| "epoch": 12.747554727526781, | |
| "grad_norm": 0.36178842186927795, | |
| "learning_rate": 0.00044729528246942335, | |
| "loss": 3.3572, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 12.762109920819748, | |
| "grad_norm": 0.3501986563205719, | |
| "learning_rate": 0.000447120559114735, | |
| "loss": 3.3572, | |
| "step": 43850 | |
| }, | |
| { | |
| "epoch": 12.776665114112715, | |
| "grad_norm": 0.3591527044773102, | |
| "learning_rate": 0.0004469458357600466, | |
| "loss": 3.351, | |
| "step": 43900 | |
| }, | |
| { | |
| "epoch": 12.791220307405682, | |
| "grad_norm": 0.37945297360420227, | |
| "learning_rate": 0.00044677111240535813, | |
| "loss": 3.3507, | |
| "step": 43950 | |
| }, | |
| { | |
| "epoch": 12.80577550069865, | |
| "grad_norm": 0.3560406267642975, | |
| "learning_rate": 0.0004465963890506697, | |
| "loss": 3.3444, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 12.80577550069865, | |
| "eval_accuracy": 0.37068394192693777, | |
| "eval_loss": 3.5476632118225098, | |
| "eval_runtime": 53.4435, | |
| "eval_samples_per_second": 311.563, | |
| "eval_steps_per_second": 19.479, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 12.820330693991616, | |
| "grad_norm": 0.3484605848789215, | |
| "learning_rate": 0.0004464216656959813, | |
| "loss": 3.3565, | |
| "step": 44050 | |
| }, | |
| { | |
| "epoch": 12.834885887284583, | |
| "grad_norm": 0.36749279499053955, | |
| "learning_rate": 0.00044624694234129297, | |
| "loss": 3.3493, | |
| "step": 44100 | |
| }, | |
| { | |
| "epoch": 12.84944108057755, | |
| "grad_norm": 0.3457622230052948, | |
| "learning_rate": 0.0004460722189866045, | |
| "loss": 3.3489, | |
| "step": 44150 | |
| }, | |
| { | |
| "epoch": 12.863996273870518, | |
| "grad_norm": 0.34354254603385925, | |
| "learning_rate": 0.0004458974956319161, | |
| "loss": 3.3575, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 12.878551467163485, | |
| "grad_norm": 0.34315767884254456, | |
| "learning_rate": 0.0004457227722772277, | |
| "loss": 3.3489, | |
| "step": 44250 | |
| }, | |
| { | |
| "epoch": 12.89310666045645, | |
| "grad_norm": 0.3415457606315613, | |
| "learning_rate": 0.00044554804892253923, | |
| "loss": 3.3567, | |
| "step": 44300 | |
| }, | |
| { | |
| "epoch": 12.907661853749417, | |
| "grad_norm": 0.3554341197013855, | |
| "learning_rate": 0.00044537332556785083, | |
| "loss": 3.3584, | |
| "step": 44350 | |
| }, | |
| { | |
| "epoch": 12.922217047042384, | |
| "grad_norm": 0.3443357050418854, | |
| "learning_rate": 0.0004451986022131625, | |
| "loss": 3.3577, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 12.936772240335351, | |
| "grad_norm": 0.3420358896255493, | |
| "learning_rate": 0.00044502387885847407, | |
| "loss": 3.3576, | |
| "step": 44450 | |
| }, | |
| { | |
| "epoch": 12.951327433628318, | |
| "grad_norm": 0.35203999280929565, | |
| "learning_rate": 0.0004448491555037856, | |
| "loss": 3.3555, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 12.965882626921285, | |
| "grad_norm": 0.3377878665924072, | |
| "learning_rate": 0.0004446744321490972, | |
| "loss": 3.3526, | |
| "step": 44550 | |
| }, | |
| { | |
| "epoch": 12.980437820214252, | |
| "grad_norm": 0.32598111033439636, | |
| "learning_rate": 0.0004444997087944088, | |
| "loss": 3.3484, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 12.99499301350722, | |
| "grad_norm": 0.35291609168052673, | |
| "learning_rate": 0.0004443249854397204, | |
| "loss": 3.3577, | |
| "step": 44650 | |
| }, | |
| { | |
| "epoch": 13.009315323707499, | |
| "grad_norm": 0.3497789800167084, | |
| "learning_rate": 0.000444150262085032, | |
| "loss": 3.2814, | |
| "step": 44700 | |
| }, | |
| { | |
| "epoch": 13.023870517000466, | |
| "grad_norm": 0.3519071340560913, | |
| "learning_rate": 0.0004439755387303436, | |
| "loss": 3.2509, | |
| "step": 44750 | |
| }, | |
| { | |
| "epoch": 13.038425710293433, | |
| "grad_norm": 0.3339556157588959, | |
| "learning_rate": 0.0004438008153756552, | |
| "loss": 3.2499, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 13.0529809035864, | |
| "grad_norm": 0.3638785481452942, | |
| "learning_rate": 0.00044362609202096677, | |
| "loss": 3.2537, | |
| "step": 44850 | |
| }, | |
| { | |
| "epoch": 13.067536096879367, | |
| "grad_norm": 0.34658241271972656, | |
| "learning_rate": 0.0004434513686662783, | |
| "loss": 3.2609, | |
| "step": 44900 | |
| }, | |
| { | |
| "epoch": 13.082091290172334, | |
| "grad_norm": 0.3546088933944702, | |
| "learning_rate": 0.00044327664531158996, | |
| "loss": 3.266, | |
| "step": 44950 | |
| }, | |
| { | |
| "epoch": 13.0966464834653, | |
| "grad_norm": 0.3482044041156769, | |
| "learning_rate": 0.00044310192195690155, | |
| "loss": 3.2682, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 13.0966464834653, | |
| "eval_accuracy": 0.3701778693498307, | |
| "eval_loss": 3.5653634071350098, | |
| "eval_runtime": 53.5063, | |
| "eval_samples_per_second": 311.197, | |
| "eval_steps_per_second": 19.456, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 13.111201676758267, | |
| "grad_norm": 0.3539417088031769, | |
| "learning_rate": 0.00044292719860221315, | |
| "loss": 3.279, | |
| "step": 45050 | |
| }, | |
| { | |
| "epoch": 13.125756870051234, | |
| "grad_norm": 0.37408214807510376, | |
| "learning_rate": 0.0004427524752475247, | |
| "loss": 3.2526, | |
| "step": 45100 | |
| }, | |
| { | |
| "epoch": 13.1403120633442, | |
| "grad_norm": 0.3644108474254608, | |
| "learning_rate": 0.0004425777518928363, | |
| "loss": 3.2816, | |
| "step": 45150 | |
| }, | |
| { | |
| "epoch": 13.154867256637168, | |
| "grad_norm": 0.34004518389701843, | |
| "learning_rate": 0.0004424030285381479, | |
| "loss": 3.2753, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 13.169422449930135, | |
| "grad_norm": 0.3613758087158203, | |
| "learning_rate": 0.0004422283051834595, | |
| "loss": 3.2776, | |
| "step": 45250 | |
| }, | |
| { | |
| "epoch": 13.183977643223102, | |
| "grad_norm": 0.35715919733047485, | |
| "learning_rate": 0.00044205358182877107, | |
| "loss": 3.2933, | |
| "step": 45300 | |
| }, | |
| { | |
| "epoch": 13.198532836516069, | |
| "grad_norm": 0.3454996645450592, | |
| "learning_rate": 0.00044187885847408266, | |
| "loss": 3.2878, | |
| "step": 45350 | |
| }, | |
| { | |
| "epoch": 13.213088029809036, | |
| "grad_norm": 0.3411758542060852, | |
| "learning_rate": 0.00044170413511939425, | |
| "loss": 3.281, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 13.227643223102003, | |
| "grad_norm": 0.3984512388706207, | |
| "learning_rate": 0.0004415294117647058, | |
| "loss": 3.2894, | |
| "step": 45450 | |
| }, | |
| { | |
| "epoch": 13.24219841639497, | |
| "grad_norm": 0.33969762921333313, | |
| "learning_rate": 0.00044135468841001744, | |
| "loss": 3.3079, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 13.256753609687937, | |
| "grad_norm": 0.342362642288208, | |
| "learning_rate": 0.00044117996505532904, | |
| "loss": 3.2934, | |
| "step": 45550 | |
| }, | |
| { | |
| "epoch": 13.271308802980904, | |
| "grad_norm": 0.3571806848049164, | |
| "learning_rate": 0.00044100524170064063, | |
| "loss": 3.2871, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 13.285863996273871, | |
| "grad_norm": 0.380403071641922, | |
| "learning_rate": 0.0004408305183459522, | |
| "loss": 3.2837, | |
| "step": 45650 | |
| }, | |
| { | |
| "epoch": 13.300419189566837, | |
| "grad_norm": 0.35478895902633667, | |
| "learning_rate": 0.00044065579499126377, | |
| "loss": 3.2931, | |
| "step": 45700 | |
| }, | |
| { | |
| "epoch": 13.314974382859804, | |
| "grad_norm": 0.32505473494529724, | |
| "learning_rate": 0.00044048107163657536, | |
| "loss": 3.3033, | |
| "step": 45750 | |
| }, | |
| { | |
| "epoch": 13.32952957615277, | |
| "grad_norm": 0.3654066324234009, | |
| "learning_rate": 0.000440306348281887, | |
| "loss": 3.2957, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 13.344084769445738, | |
| "grad_norm": 0.3213895261287689, | |
| "learning_rate": 0.0004401316249271986, | |
| "loss": 3.2947, | |
| "step": 45850 | |
| }, | |
| { | |
| "epoch": 13.358639962738705, | |
| "grad_norm": 0.34680667519569397, | |
| "learning_rate": 0.00043995690157251014, | |
| "loss": 3.2979, | |
| "step": 45900 | |
| }, | |
| { | |
| "epoch": 13.373195156031672, | |
| "grad_norm": 0.3588424324989319, | |
| "learning_rate": 0.00043978217821782174, | |
| "loss": 3.2963, | |
| "step": 45950 | |
| }, | |
| { | |
| "epoch": 13.387750349324639, | |
| "grad_norm": 0.3544321358203888, | |
| "learning_rate": 0.00043960745486313333, | |
| "loss": 3.3046, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 13.387750349324639, | |
| "eval_accuracy": 0.3703951773375388, | |
| "eval_loss": 3.561577558517456, | |
| "eval_runtime": 53.6878, | |
| "eval_samples_per_second": 310.145, | |
| "eval_steps_per_second": 19.39, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 13.402305542617606, | |
| "grad_norm": 0.32685863971710205, | |
| "learning_rate": 0.00043943273150844487, | |
| "loss": 3.3101, | |
| "step": 46050 | |
| }, | |
| { | |
| "epoch": 13.416860735910573, | |
| "grad_norm": 0.36263135075569153, | |
| "learning_rate": 0.0004392580081537565, | |
| "loss": 3.3125, | |
| "step": 46100 | |
| }, | |
| { | |
| "epoch": 13.43141592920354, | |
| "grad_norm": 0.3455837666988373, | |
| "learning_rate": 0.0004390832847990681, | |
| "loss": 3.3183, | |
| "step": 46150 | |
| }, | |
| { | |
| "epoch": 13.445971122496507, | |
| "grad_norm": 0.3492259383201599, | |
| "learning_rate": 0.0004389085614443797, | |
| "loss": 3.3132, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 13.460526315789474, | |
| "grad_norm": 0.35746267437934875, | |
| "learning_rate": 0.00043873383808969125, | |
| "loss": 3.3085, | |
| "step": 46250 | |
| }, | |
| { | |
| "epoch": 13.475081509082441, | |
| "grad_norm": 0.3470415472984314, | |
| "learning_rate": 0.00043855911473500284, | |
| "loss": 3.3188, | |
| "step": 46300 | |
| }, | |
| { | |
| "epoch": 13.489636702375407, | |
| "grad_norm": 0.3576386272907257, | |
| "learning_rate": 0.0004383843913803145, | |
| "loss": 3.309, | |
| "step": 46350 | |
| }, | |
| { | |
| "epoch": 13.504191895668374, | |
| "grad_norm": 0.3418940007686615, | |
| "learning_rate": 0.0004382096680256261, | |
| "loss": 3.3124, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 13.51874708896134, | |
| "grad_norm": 0.3416048586368561, | |
| "learning_rate": 0.0004380349446709376, | |
| "loss": 3.3191, | |
| "step": 46450 | |
| }, | |
| { | |
| "epoch": 13.533302282254308, | |
| "grad_norm": 0.33699357509613037, | |
| "learning_rate": 0.0004378602213162492, | |
| "loss": 3.3275, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 13.547857475547275, | |
| "grad_norm": 0.34516245126724243, | |
| "learning_rate": 0.0004376854979615608, | |
| "loss": 3.3204, | |
| "step": 46550 | |
| }, | |
| { | |
| "epoch": 13.562412668840242, | |
| "grad_norm": 0.33703818917274475, | |
| "learning_rate": 0.0004375107746068724, | |
| "loss": 3.3175, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 13.576967862133209, | |
| "grad_norm": 0.36189010739326477, | |
| "learning_rate": 0.000437336051252184, | |
| "loss": 3.3277, | |
| "step": 46650 | |
| }, | |
| { | |
| "epoch": 13.591523055426176, | |
| "grad_norm": 0.39786970615386963, | |
| "learning_rate": 0.0004371613278974956, | |
| "loss": 3.3223, | |
| "step": 46700 | |
| }, | |
| { | |
| "epoch": 13.606078248719143, | |
| "grad_norm": 0.34631863236427307, | |
| "learning_rate": 0.0004369866045428072, | |
| "loss": 3.3175, | |
| "step": 46750 | |
| }, | |
| { | |
| "epoch": 13.62063344201211, | |
| "grad_norm": 0.34966984391212463, | |
| "learning_rate": 0.0004368118811881188, | |
| "loss": 3.3185, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 13.635188635305077, | |
| "grad_norm": 0.3509593605995178, | |
| "learning_rate": 0.0004366371578334303, | |
| "loss": 3.3283, | |
| "step": 46850 | |
| }, | |
| { | |
| "epoch": 13.649743828598044, | |
| "grad_norm": 0.3456225097179413, | |
| "learning_rate": 0.000436462434478742, | |
| "loss": 3.3241, | |
| "step": 46900 | |
| }, | |
| { | |
| "epoch": 13.664299021891011, | |
| "grad_norm": 0.3707951307296753, | |
| "learning_rate": 0.00043628771112405357, | |
| "loss": 3.3131, | |
| "step": 46950 | |
| }, | |
| { | |
| "epoch": 13.678854215183978, | |
| "grad_norm": 0.3647649586200714, | |
| "learning_rate": 0.00043611298776936516, | |
| "loss": 3.3182, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 13.678854215183978, | |
| "eval_accuracy": 0.3708447192807423, | |
| "eval_loss": 3.5504887104034424, | |
| "eval_runtime": 53.3831, | |
| "eval_samples_per_second": 311.915, | |
| "eval_steps_per_second": 19.501, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 13.693409408476944, | |
| "grad_norm": 0.380444198846817, | |
| "learning_rate": 0.0004359382644146767, | |
| "loss": 3.3287, | |
| "step": 47050 | |
| }, | |
| { | |
| "epoch": 13.70796460176991, | |
| "grad_norm": 0.3570321500301361, | |
| "learning_rate": 0.0004357635410599883, | |
| "loss": 3.3284, | |
| "step": 47100 | |
| }, | |
| { | |
| "epoch": 13.722519795062878, | |
| "grad_norm": 0.3356628715991974, | |
| "learning_rate": 0.0004355888177052999, | |
| "loss": 3.328, | |
| "step": 47150 | |
| }, | |
| { | |
| "epoch": 13.737074988355845, | |
| "grad_norm": 0.3439415395259857, | |
| "learning_rate": 0.00043541409435061154, | |
| "loss": 3.3339, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 13.751630181648812, | |
| "grad_norm": 0.36410510540008545, | |
| "learning_rate": 0.0004352393709959231, | |
| "loss": 3.3441, | |
| "step": 47250 | |
| }, | |
| { | |
| "epoch": 13.766185374941779, | |
| "grad_norm": 0.3484279215335846, | |
| "learning_rate": 0.0004350646476412347, | |
| "loss": 3.3304, | |
| "step": 47300 | |
| }, | |
| { | |
| "epoch": 13.780740568234746, | |
| "grad_norm": 0.3761006295681, | |
| "learning_rate": 0.00043488992428654627, | |
| "loss": 3.3341, | |
| "step": 47350 | |
| }, | |
| { | |
| "epoch": 13.795295761527713, | |
| "grad_norm": 0.35704439878463745, | |
| "learning_rate": 0.0004347152009318578, | |
| "loss": 3.3399, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 13.80985095482068, | |
| "grad_norm": 0.3605094850063324, | |
| "learning_rate": 0.00043454047757716946, | |
| "loss": 3.3347, | |
| "step": 47450 | |
| }, | |
| { | |
| "epoch": 13.824406148113647, | |
| "grad_norm": 0.3660779297351837, | |
| "learning_rate": 0.00043436575422248105, | |
| "loss": 3.3389, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 13.838961341406614, | |
| "grad_norm": 0.3642270565032959, | |
| "learning_rate": 0.00043419103086779265, | |
| "loss": 3.3257, | |
| "step": 47550 | |
| }, | |
| { | |
| "epoch": 13.853516534699581, | |
| "grad_norm": 0.3574860095977783, | |
| "learning_rate": 0.0004340163075131042, | |
| "loss": 3.338, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 13.868071727992549, | |
| "grad_norm": 0.3333912789821625, | |
| "learning_rate": 0.0004338415841584158, | |
| "loss": 3.3339, | |
| "step": 47650 | |
| }, | |
| { | |
| "epoch": 13.882626921285514, | |
| "grad_norm": 0.33468636870384216, | |
| "learning_rate": 0.0004336668608037274, | |
| "loss": 3.3439, | |
| "step": 47700 | |
| }, | |
| { | |
| "epoch": 13.89718211457848, | |
| "grad_norm": 0.33719417452812195, | |
| "learning_rate": 0.000433492137449039, | |
| "loss": 3.3415, | |
| "step": 47750 | |
| }, | |
| { | |
| "epoch": 13.911737307871448, | |
| "grad_norm": 0.38772904872894287, | |
| "learning_rate": 0.00043331741409435056, | |
| "loss": 3.3399, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 13.926292501164415, | |
| "grad_norm": 0.35599151253700256, | |
| "learning_rate": 0.00043314269073966216, | |
| "loss": 3.3394, | |
| "step": 47850 | |
| }, | |
| { | |
| "epoch": 13.940847694457382, | |
| "grad_norm": 0.37248626351356506, | |
| "learning_rate": 0.00043296796738497375, | |
| "loss": 3.3351, | |
| "step": 47900 | |
| }, | |
| { | |
| "epoch": 13.955402887750349, | |
| "grad_norm": 0.3534635603427887, | |
| "learning_rate": 0.00043279324403028535, | |
| "loss": 3.3427, | |
| "step": 47950 | |
| }, | |
| { | |
| "epoch": 13.969958081043316, | |
| "grad_norm": 0.3702537715435028, | |
| "learning_rate": 0.0004326185206755969, | |
| "loss": 3.3466, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 13.969958081043316, | |
| "eval_accuracy": 0.37139944816229015, | |
| "eval_loss": 3.543956995010376, | |
| "eval_runtime": 53.7007, | |
| "eval_samples_per_second": 310.07, | |
| "eval_steps_per_second": 19.385, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 13.984513274336283, | |
| "grad_norm": 0.33839738368988037, | |
| "learning_rate": 0.00043244379732090854, | |
| "loss": 3.3466, | |
| "step": 48050 | |
| }, | |
| { | |
| "epoch": 13.99906846762925, | |
| "grad_norm": 0.36890435218811035, | |
| "learning_rate": 0.00043226907396622013, | |
| "loss": 3.3279, | |
| "step": 48100 | |
| }, | |
| { | |
| "epoch": 14.01339077782953, | |
| "grad_norm": 0.3310120701789856, | |
| "learning_rate": 0.0004320943506115317, | |
| "loss": 3.2359, | |
| "step": 48150 | |
| }, | |
| { | |
| "epoch": 14.027945971122497, | |
| "grad_norm": 0.35537096858024597, | |
| "learning_rate": 0.00043191962725684326, | |
| "loss": 3.2381, | |
| "step": 48200 | |
| }, | |
| { | |
| "epoch": 14.042501164415464, | |
| "grad_norm": 0.3801775574684143, | |
| "learning_rate": 0.00043174490390215486, | |
| "loss": 3.2477, | |
| "step": 48250 | |
| }, | |
| { | |
| "epoch": 14.057056357708431, | |
| "grad_norm": 0.3717610836029053, | |
| "learning_rate": 0.0004315701805474665, | |
| "loss": 3.2439, | |
| "step": 48300 | |
| }, | |
| { | |
| "epoch": 14.071611551001398, | |
| "grad_norm": 0.3570388853549957, | |
| "learning_rate": 0.0004313954571927781, | |
| "loss": 3.2448, | |
| "step": 48350 | |
| }, | |
| { | |
| "epoch": 14.086166744294363, | |
| "grad_norm": 0.35514572262763977, | |
| "learning_rate": 0.00043122073383808964, | |
| "loss": 3.2431, | |
| "step": 48400 | |
| }, | |
| { | |
| "epoch": 14.10072193758733, | |
| "grad_norm": 0.35711315274238586, | |
| "learning_rate": 0.00043104601048340124, | |
| "loss": 3.2595, | |
| "step": 48450 | |
| }, | |
| { | |
| "epoch": 14.115277130880298, | |
| "grad_norm": 0.3618149757385254, | |
| "learning_rate": 0.00043087128712871283, | |
| "loss": 3.2636, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 14.129832324173265, | |
| "grad_norm": 0.3800710141658783, | |
| "learning_rate": 0.00043069656377402437, | |
| "loss": 3.2528, | |
| "step": 48550 | |
| }, | |
| { | |
| "epoch": 14.144387517466232, | |
| "grad_norm": 0.35226449370384216, | |
| "learning_rate": 0.000430521840419336, | |
| "loss": 3.2568, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 14.158942710759199, | |
| "grad_norm": 0.3613344430923462, | |
| "learning_rate": 0.0004303471170646476, | |
| "loss": 3.2735, | |
| "step": 48650 | |
| }, | |
| { | |
| "epoch": 14.173497904052166, | |
| "grad_norm": 0.3699142038822174, | |
| "learning_rate": 0.0004301723937099592, | |
| "loss": 3.2626, | |
| "step": 48700 | |
| }, | |
| { | |
| "epoch": 14.188053097345133, | |
| "grad_norm": 0.36518362164497375, | |
| "learning_rate": 0.00042999767035527075, | |
| "loss": 3.2688, | |
| "step": 48750 | |
| }, | |
| { | |
| "epoch": 14.2026082906381, | |
| "grad_norm": 0.3447186052799225, | |
| "learning_rate": 0.00042982294700058234, | |
| "loss": 3.2669, | |
| "step": 48800 | |
| }, | |
| { | |
| "epoch": 14.217163483931067, | |
| "grad_norm": 0.3536320626735687, | |
| "learning_rate": 0.000429648223645894, | |
| "loss": 3.2635, | |
| "step": 48850 | |
| }, | |
| { | |
| "epoch": 14.231718677224034, | |
| "grad_norm": 0.34352579712867737, | |
| "learning_rate": 0.0004294735002912056, | |
| "loss": 3.2598, | |
| "step": 48900 | |
| }, | |
| { | |
| "epoch": 14.246273870517001, | |
| "grad_norm": 0.3466048538684845, | |
| "learning_rate": 0.0004292987769365172, | |
| "loss": 3.285, | |
| "step": 48950 | |
| }, | |
| { | |
| "epoch": 14.260829063809968, | |
| "grad_norm": 0.3724770247936249, | |
| "learning_rate": 0.0004291240535818287, | |
| "loss": 3.2754, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 14.260829063809968, | |
| "eval_accuracy": 0.3707863082099522, | |
| "eval_loss": 3.5598011016845703, | |
| "eval_runtime": 53.7099, | |
| "eval_samples_per_second": 310.017, | |
| "eval_steps_per_second": 19.382, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 14.275384257102935, | |
| "grad_norm": 0.39638257026672363, | |
| "learning_rate": 0.0004289493302271403, | |
| "loss": 3.2867, | |
| "step": 49050 | |
| }, | |
| { | |
| "epoch": 14.2899394503959, | |
| "grad_norm": 0.37979763746261597, | |
| "learning_rate": 0.0004287746068724519, | |
| "loss": 3.2701, | |
| "step": 49100 | |
| }, | |
| { | |
| "epoch": 14.304494643688868, | |
| "grad_norm": 0.34955981373786926, | |
| "learning_rate": 0.00042859988351776356, | |
| "loss": 3.2797, | |
| "step": 49150 | |
| }, | |
| { | |
| "epoch": 14.319049836981835, | |
| "grad_norm": 0.35419076681137085, | |
| "learning_rate": 0.0004284251601630751, | |
| "loss": 3.2675, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 14.333605030274802, | |
| "grad_norm": 0.38131004571914673, | |
| "learning_rate": 0.0004282504368083867, | |
| "loss": 3.2834, | |
| "step": 49250 | |
| }, | |
| { | |
| "epoch": 14.348160223567769, | |
| "grad_norm": 0.3478652834892273, | |
| "learning_rate": 0.0004280757134536983, | |
| "loss": 3.2895, | |
| "step": 49300 | |
| }, | |
| { | |
| "epoch": 14.362715416860736, | |
| "grad_norm": 0.3468261957168579, | |
| "learning_rate": 0.0004279009900990098, | |
| "loss": 3.2856, | |
| "step": 49350 | |
| }, | |
| { | |
| "epoch": 14.377270610153703, | |
| "grad_norm": 0.3900758624076843, | |
| "learning_rate": 0.0004277262667443214, | |
| "loss": 3.2871, | |
| "step": 49400 | |
| }, | |
| { | |
| "epoch": 14.39182580344667, | |
| "grad_norm": 0.3457072377204895, | |
| "learning_rate": 0.00042755154338963307, | |
| "loss": 3.2911, | |
| "step": 49450 | |
| }, | |
| { | |
| "epoch": 14.406380996739637, | |
| "grad_norm": 0.34359681606292725, | |
| "learning_rate": 0.00042737682003494466, | |
| "loss": 3.2885, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 14.420936190032604, | |
| "grad_norm": 0.3711550533771515, | |
| "learning_rate": 0.0004272020966802562, | |
| "loss": 3.3009, | |
| "step": 49550 | |
| }, | |
| { | |
| "epoch": 14.435491383325571, | |
| "grad_norm": 0.35895073413848877, | |
| "learning_rate": 0.0004270273733255678, | |
| "loss": 3.288, | |
| "step": 49600 | |
| }, | |
| { | |
| "epoch": 14.450046576618538, | |
| "grad_norm": 0.3567804992198944, | |
| "learning_rate": 0.0004268526499708794, | |
| "loss": 3.2945, | |
| "step": 49650 | |
| }, | |
| { | |
| "epoch": 14.464601769911505, | |
| "grad_norm": 0.35441455245018005, | |
| "learning_rate": 0.00042667792661619104, | |
| "loss": 3.2903, | |
| "step": 49700 | |
| }, | |
| { | |
| "epoch": 14.47915696320447, | |
| "grad_norm": 0.342666894197464, | |
| "learning_rate": 0.0004265032032615026, | |
| "loss": 3.2919, | |
| "step": 49750 | |
| }, | |
| { | |
| "epoch": 14.493712156497438, | |
| "grad_norm": 0.3864854872226715, | |
| "learning_rate": 0.0004263284799068142, | |
| "loss": 3.3099, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 14.508267349790405, | |
| "grad_norm": 0.3591754734516144, | |
| "learning_rate": 0.00042615375655212577, | |
| "loss": 3.3023, | |
| "step": 49850 | |
| }, | |
| { | |
| "epoch": 14.522822543083372, | |
| "grad_norm": 0.3885883390903473, | |
| "learning_rate": 0.00042597903319743736, | |
| "loss": 3.3035, | |
| "step": 49900 | |
| }, | |
| { | |
| "epoch": 14.537377736376339, | |
| "grad_norm": 0.35845860838890076, | |
| "learning_rate": 0.0004258043098427489, | |
| "loss": 3.3, | |
| "step": 49950 | |
| }, | |
| { | |
| "epoch": 14.551932929669306, | |
| "grad_norm": 0.39179670810699463, | |
| "learning_rate": 0.00042562958648806055, | |
| "loss": 3.3009, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 14.551932929669306, | |
| "eval_accuracy": 0.37129919737077316, | |
| "eval_loss": 3.55165696144104, | |
| "eval_runtime": 53.5291, | |
| "eval_samples_per_second": 311.064, | |
| "eval_steps_per_second": 19.447, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 14.566488122962273, | |
| "grad_norm": 0.335472971200943, | |
| "learning_rate": 0.00042545486313337214, | |
| "loss": 3.2954, | |
| "step": 50050 | |
| }, | |
| { | |
| "epoch": 14.58104331625524, | |
| "grad_norm": 0.35575392842292786, | |
| "learning_rate": 0.00042528013977868374, | |
| "loss": 3.3092, | |
| "step": 50100 | |
| }, | |
| { | |
| "epoch": 14.595598509548207, | |
| "grad_norm": 0.3596695065498352, | |
| "learning_rate": 0.0004251054164239953, | |
| "loss": 3.3049, | |
| "step": 50150 | |
| }, | |
| { | |
| "epoch": 14.610153702841174, | |
| "grad_norm": 0.35837888717651367, | |
| "learning_rate": 0.0004249306930693069, | |
| "loss": 3.3014, | |
| "step": 50200 | |
| }, | |
| { | |
| "epoch": 14.624708896134141, | |
| "grad_norm": 0.3785068094730377, | |
| "learning_rate": 0.0004247559697146185, | |
| "loss": 3.3117, | |
| "step": 50250 | |
| }, | |
| { | |
| "epoch": 14.639264089427108, | |
| "grad_norm": 0.3381900191307068, | |
| "learning_rate": 0.0004245812463599301, | |
| "loss": 3.3012, | |
| "step": 50300 | |
| }, | |
| { | |
| "epoch": 14.653819282720075, | |
| "grad_norm": 0.3588135838508606, | |
| "learning_rate": 0.00042440652300524166, | |
| "loss": 3.3103, | |
| "step": 50350 | |
| }, | |
| { | |
| "epoch": 14.668374476013042, | |
| "grad_norm": 0.3700288236141205, | |
| "learning_rate": 0.00042423179965055325, | |
| "loss": 3.3124, | |
| "step": 50400 | |
| }, | |
| { | |
| "epoch": 14.682929669306008, | |
| "grad_norm": 0.3798788785934448, | |
| "learning_rate": 0.00042405707629586484, | |
| "loss": 3.325, | |
| "step": 50450 | |
| }, | |
| { | |
| "epoch": 14.697484862598975, | |
| "grad_norm": 0.3425830006599426, | |
| "learning_rate": 0.0004238823529411764, | |
| "loss": 3.3139, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 14.712040055891942, | |
| "grad_norm": 0.35475632548332214, | |
| "learning_rate": 0.00042370762958648803, | |
| "loss": 3.3241, | |
| "step": 50550 | |
| }, | |
| { | |
| "epoch": 14.726595249184909, | |
| "grad_norm": 0.3482853174209595, | |
| "learning_rate": 0.00042353290623179963, | |
| "loss": 3.3075, | |
| "step": 50600 | |
| }, | |
| { | |
| "epoch": 14.741150442477876, | |
| "grad_norm": 0.3831191062927246, | |
| "learning_rate": 0.0004233581828771112, | |
| "loss": 3.307, | |
| "step": 50650 | |
| }, | |
| { | |
| "epoch": 14.755705635770843, | |
| "grad_norm": 0.35044384002685547, | |
| "learning_rate": 0.00042318345952242276, | |
| "loss": 3.3126, | |
| "step": 50700 | |
| }, | |
| { | |
| "epoch": 14.77026082906381, | |
| "grad_norm": 0.3586428463459015, | |
| "learning_rate": 0.00042300873616773436, | |
| "loss": 3.3218, | |
| "step": 50750 | |
| }, | |
| { | |
| "epoch": 14.784816022356777, | |
| "grad_norm": 0.3539646565914154, | |
| "learning_rate": 0.00042283401281304595, | |
| "loss": 3.3229, | |
| "step": 50800 | |
| }, | |
| { | |
| "epoch": 14.799371215649744, | |
| "grad_norm": 0.3365599811077118, | |
| "learning_rate": 0.0004226592894583576, | |
| "loss": 3.3177, | |
| "step": 50850 | |
| }, | |
| { | |
| "epoch": 14.813926408942711, | |
| "grad_norm": 0.36707398295402527, | |
| "learning_rate": 0.00042248456610366914, | |
| "loss": 3.332, | |
| "step": 50900 | |
| }, | |
| { | |
| "epoch": 14.828481602235678, | |
| "grad_norm": 0.36320602893829346, | |
| "learning_rate": 0.00042230984274898073, | |
| "loss": 3.3149, | |
| "step": 50950 | |
| }, | |
| { | |
| "epoch": 14.843036795528645, | |
| "grad_norm": 0.39062368869781494, | |
| "learning_rate": 0.00042213511939429233, | |
| "loss": 3.3316, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 14.843036795528645, | |
| "eval_accuracy": 0.3716635320175525, | |
| "eval_loss": 3.5434978008270264, | |
| "eval_runtime": 53.4702, | |
| "eval_samples_per_second": 311.407, | |
| "eval_steps_per_second": 19.469, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 14.857591988821612, | |
| "grad_norm": 0.3442405164241791, | |
| "learning_rate": 0.0004219603960396039, | |
| "loss": 3.3279, | |
| "step": 51050 | |
| }, | |
| { | |
| "epoch": 14.872147182114578, | |
| "grad_norm": 0.34880682826042175, | |
| "learning_rate": 0.0004217856726849155, | |
| "loss": 3.3227, | |
| "step": 51100 | |
| }, | |
| { | |
| "epoch": 14.886702375407545, | |
| "grad_norm": 0.3467597961425781, | |
| "learning_rate": 0.0004216109493302271, | |
| "loss": 3.3283, | |
| "step": 51150 | |
| }, | |
| { | |
| "epoch": 14.901257568700512, | |
| "grad_norm": 0.3343196511268616, | |
| "learning_rate": 0.0004214362259755387, | |
| "loss": 3.3283, | |
| "step": 51200 | |
| }, | |
| { | |
| "epoch": 14.915812761993479, | |
| "grad_norm": 0.37307101488113403, | |
| "learning_rate": 0.0004212615026208503, | |
| "loss": 3.3338, | |
| "step": 51250 | |
| }, | |
| { | |
| "epoch": 14.930367955286446, | |
| "grad_norm": 0.35305893421173096, | |
| "learning_rate": 0.00042108677926616184, | |
| "loss": 3.3273, | |
| "step": 51300 | |
| }, | |
| { | |
| "epoch": 14.944923148579413, | |
| "grad_norm": 0.34509143233299255, | |
| "learning_rate": 0.00042091205591147343, | |
| "loss": 3.315, | |
| "step": 51350 | |
| }, | |
| { | |
| "epoch": 14.95947834187238, | |
| "grad_norm": 0.37403181195259094, | |
| "learning_rate": 0.0004207373325567851, | |
| "loss": 3.3354, | |
| "step": 51400 | |
| }, | |
| { | |
| "epoch": 14.974033535165347, | |
| "grad_norm": 0.37314242124557495, | |
| "learning_rate": 0.0004205626092020967, | |
| "loss": 3.3309, | |
| "step": 51450 | |
| }, | |
| { | |
| "epoch": 14.988588728458314, | |
| "grad_norm": 0.3672788441181183, | |
| "learning_rate": 0.0004203878858474082, | |
| "loss": 3.3218, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 15.002911038658594, | |
| "grad_norm": 0.37780436873435974, | |
| "learning_rate": 0.0004202131624927198, | |
| "loss": 3.3028, | |
| "step": 51550 | |
| }, | |
| { | |
| "epoch": 15.01746623195156, | |
| "grad_norm": 0.35759609937667847, | |
| "learning_rate": 0.0004200384391380314, | |
| "loss": 3.2245, | |
| "step": 51600 | |
| }, | |
| { | |
| "epoch": 15.032021425244528, | |
| "grad_norm": 0.3455546796321869, | |
| "learning_rate": 0.00041986371578334305, | |
| "loss": 3.2228, | |
| "step": 51650 | |
| }, | |
| { | |
| "epoch": 15.046576618537495, | |
| "grad_norm": 0.3793853223323822, | |
| "learning_rate": 0.0004196889924286546, | |
| "loss": 3.2243, | |
| "step": 51700 | |
| }, | |
| { | |
| "epoch": 15.06113181183046, | |
| "grad_norm": 0.3504517376422882, | |
| "learning_rate": 0.0004195142690739662, | |
| "loss": 3.2402, | |
| "step": 51750 | |
| }, | |
| { | |
| "epoch": 15.075687005123427, | |
| "grad_norm": 0.3474739193916321, | |
| "learning_rate": 0.0004193395457192778, | |
| "loss": 3.2391, | |
| "step": 51800 | |
| }, | |
| { | |
| "epoch": 15.090242198416394, | |
| "grad_norm": 0.3809396028518677, | |
| "learning_rate": 0.0004191648223645893, | |
| "loss": 3.226, | |
| "step": 51850 | |
| }, | |
| { | |
| "epoch": 15.104797391709361, | |
| "grad_norm": 0.35305795073509216, | |
| "learning_rate": 0.0004189900990099009, | |
| "loss": 3.2467, | |
| "step": 51900 | |
| }, | |
| { | |
| "epoch": 15.119352585002328, | |
| "grad_norm": 0.3982357382774353, | |
| "learning_rate": 0.00041881537565521256, | |
| "loss": 3.237, | |
| "step": 51950 | |
| }, | |
| { | |
| "epoch": 15.133907778295296, | |
| "grad_norm": 0.3972439169883728, | |
| "learning_rate": 0.00041864065230052416, | |
| "loss": 3.2446, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 15.133907778295296, | |
| "eval_accuracy": 0.37101384107323115, | |
| "eval_loss": 3.559807300567627, | |
| "eval_runtime": 53.5523, | |
| "eval_samples_per_second": 310.93, | |
| "eval_steps_per_second": 19.439, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 15.148462971588263, | |
| "grad_norm": 0.3491523861885071, | |
| "learning_rate": 0.00041846592894583575, | |
| "loss": 3.2516, | |
| "step": 52050 | |
| }, | |
| { | |
| "epoch": 15.16301816488123, | |
| "grad_norm": 0.37828558683395386, | |
| "learning_rate": 0.0004182912055911473, | |
| "loss": 3.2508, | |
| "step": 52100 | |
| }, | |
| { | |
| "epoch": 15.177573358174197, | |
| "grad_norm": 0.3806478679180145, | |
| "learning_rate": 0.0004181164822364589, | |
| "loss": 3.2547, | |
| "step": 52150 | |
| }, | |
| { | |
| "epoch": 15.192128551467164, | |
| "grad_norm": 0.3949051797389984, | |
| "learning_rate": 0.0004179417588817705, | |
| "loss": 3.253, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 15.20668374476013, | |
| "grad_norm": 0.3910926878452301, | |
| "learning_rate": 0.00041776703552708213, | |
| "loss": 3.2567, | |
| "step": 52250 | |
| }, | |
| { | |
| "epoch": 15.221238938053098, | |
| "grad_norm": 0.36082324385643005, | |
| "learning_rate": 0.00041759231217239367, | |
| "loss": 3.2622, | |
| "step": 52300 | |
| }, | |
| { | |
| "epoch": 15.235794131346065, | |
| "grad_norm": 0.3850710391998291, | |
| "learning_rate": 0.00041741758881770527, | |
| "loss": 3.2537, | |
| "step": 52350 | |
| }, | |
| { | |
| "epoch": 15.250349324639032, | |
| "grad_norm": 0.36984217166900635, | |
| "learning_rate": 0.00041724286546301686, | |
| "loss": 3.2669, | |
| "step": 52400 | |
| }, | |
| { | |
| "epoch": 15.264904517931997, | |
| "grad_norm": 0.3359367251396179, | |
| "learning_rate": 0.0004170681421083284, | |
| "loss": 3.2659, | |
| "step": 52450 | |
| }, | |
| { | |
| "epoch": 15.279459711224964, | |
| "grad_norm": 0.3868344724178314, | |
| "learning_rate": 0.00041689341875364005, | |
| "loss": 3.2678, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 15.294014904517931, | |
| "grad_norm": 0.37767064571380615, | |
| "learning_rate": 0.00041671869539895164, | |
| "loss": 3.2625, | |
| "step": 52550 | |
| }, | |
| { | |
| "epoch": 15.308570097810899, | |
| "grad_norm": 0.35256677865982056, | |
| "learning_rate": 0.00041654397204426324, | |
| "loss": 3.2647, | |
| "step": 52600 | |
| }, | |
| { | |
| "epoch": 15.323125291103866, | |
| "grad_norm": 0.37042659521102905, | |
| "learning_rate": 0.0004163692486895748, | |
| "loss": 3.2741, | |
| "step": 52650 | |
| }, | |
| { | |
| "epoch": 15.337680484396833, | |
| "grad_norm": 0.38683468103408813, | |
| "learning_rate": 0.00041619452533488637, | |
| "loss": 3.2765, | |
| "step": 52700 | |
| }, | |
| { | |
| "epoch": 15.3522356776898, | |
| "grad_norm": 0.35517606139183044, | |
| "learning_rate": 0.00041601980198019797, | |
| "loss": 3.2728, | |
| "step": 52750 | |
| }, | |
| { | |
| "epoch": 15.366790870982767, | |
| "grad_norm": 0.3960016965866089, | |
| "learning_rate": 0.0004158450786255096, | |
| "loss": 3.2758, | |
| "step": 52800 | |
| }, | |
| { | |
| "epoch": 15.381346064275734, | |
| "grad_norm": 0.36555227637290955, | |
| "learning_rate": 0.00041567035527082115, | |
| "loss": 3.2821, | |
| "step": 52850 | |
| }, | |
| { | |
| "epoch": 15.3959012575687, | |
| "grad_norm": 0.383771687746048, | |
| "learning_rate": 0.00041549563191613275, | |
| "loss": 3.2802, | |
| "step": 52900 | |
| }, | |
| { | |
| "epoch": 15.410456450861668, | |
| "grad_norm": 0.380877286195755, | |
| "learning_rate": 0.00041532090856144434, | |
| "loss": 3.2717, | |
| "step": 52950 | |
| }, | |
| { | |
| "epoch": 15.425011644154635, | |
| "grad_norm": 0.3386833071708679, | |
| "learning_rate": 0.00041514618520675594, | |
| "loss": 3.2729, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 15.425011644154635, | |
| "eval_accuracy": 0.3715556419511836, | |
| "eval_loss": 3.5508904457092285, | |
| "eval_runtime": 53.6289, | |
| "eval_samples_per_second": 310.486, | |
| "eval_steps_per_second": 19.411, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 15.439566837447602, | |
| "grad_norm": 0.34450849890708923, | |
| "learning_rate": 0.00041497146185206753, | |
| "loss": 3.2809, | |
| "step": 53050 | |
| }, | |
| { | |
| "epoch": 15.454122030740567, | |
| "grad_norm": 0.3628314435482025, | |
| "learning_rate": 0.0004147967384973791, | |
| "loss": 3.2715, | |
| "step": 53100 | |
| }, | |
| { | |
| "epoch": 15.468677224033534, | |
| "grad_norm": 0.3600606322288513, | |
| "learning_rate": 0.0004146220151426907, | |
| "loss": 3.287, | |
| "step": 53150 | |
| }, | |
| { | |
| "epoch": 15.483232417326501, | |
| "grad_norm": 0.3714844286441803, | |
| "learning_rate": 0.0004144472917880023, | |
| "loss": 3.2967, | |
| "step": 53200 | |
| }, | |
| { | |
| "epoch": 15.497787610619469, | |
| "grad_norm": 0.39868026971817017, | |
| "learning_rate": 0.00041427256843331385, | |
| "loss": 3.2891, | |
| "step": 53250 | |
| }, | |
| { | |
| "epoch": 15.512342803912436, | |
| "grad_norm": 0.36960697174072266, | |
| "learning_rate": 0.00041409784507862545, | |
| "loss": 3.2821, | |
| "step": 53300 | |
| }, | |
| { | |
| "epoch": 15.526897997205403, | |
| "grad_norm": 0.3895995616912842, | |
| "learning_rate": 0.0004139231217239371, | |
| "loss": 3.2926, | |
| "step": 53350 | |
| }, | |
| { | |
| "epoch": 15.54145319049837, | |
| "grad_norm": 0.3854353129863739, | |
| "learning_rate": 0.0004137483983692487, | |
| "loss": 3.3022, | |
| "step": 53400 | |
| }, | |
| { | |
| "epoch": 15.556008383791337, | |
| "grad_norm": 0.335685670375824, | |
| "learning_rate": 0.00041357367501456023, | |
| "loss": 3.2991, | |
| "step": 53450 | |
| }, | |
| { | |
| "epoch": 15.570563577084304, | |
| "grad_norm": 0.3376021683216095, | |
| "learning_rate": 0.0004133989516598718, | |
| "loss": 3.2779, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 15.585118770377271, | |
| "grad_norm": 0.36275818943977356, | |
| "learning_rate": 0.0004132242283051834, | |
| "loss": 3.2821, | |
| "step": 53550 | |
| }, | |
| { | |
| "epoch": 15.599673963670238, | |
| "grad_norm": 0.3548260033130646, | |
| "learning_rate": 0.00041304950495049496, | |
| "loss": 3.3007, | |
| "step": 53600 | |
| }, | |
| { | |
| "epoch": 15.614229156963205, | |
| "grad_norm": 0.3370545506477356, | |
| "learning_rate": 0.0004128747815958066, | |
| "loss": 3.2962, | |
| "step": 53650 | |
| }, | |
| { | |
| "epoch": 15.628784350256172, | |
| "grad_norm": 0.3507649302482605, | |
| "learning_rate": 0.0004127000582411182, | |
| "loss": 3.2979, | |
| "step": 53700 | |
| }, | |
| { | |
| "epoch": 15.64333954354914, | |
| "grad_norm": 0.3768140971660614, | |
| "learning_rate": 0.0004125253348864298, | |
| "loss": 3.2945, | |
| "step": 53750 | |
| }, | |
| { | |
| "epoch": 15.657894736842106, | |
| "grad_norm": 0.35890328884124756, | |
| "learning_rate": 0.00041235061153174134, | |
| "loss": 3.29, | |
| "step": 53800 | |
| }, | |
| { | |
| "epoch": 15.672449930135071, | |
| "grad_norm": 0.3548602759838104, | |
| "learning_rate": 0.00041217588817705293, | |
| "loss": 3.2946, | |
| "step": 53850 | |
| }, | |
| { | |
| "epoch": 15.687005123428039, | |
| "grad_norm": 0.42979973554611206, | |
| "learning_rate": 0.0004120011648223646, | |
| "loss": 3.3017, | |
| "step": 53900 | |
| }, | |
| { | |
| "epoch": 15.701560316721006, | |
| "grad_norm": 0.3521318733692169, | |
| "learning_rate": 0.0004118264414676762, | |
| "loss": 3.3113, | |
| "step": 53950 | |
| }, | |
| { | |
| "epoch": 15.716115510013973, | |
| "grad_norm": 0.3744296133518219, | |
| "learning_rate": 0.0004116517181129877, | |
| "loss": 3.2847, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 15.716115510013973, | |
| "eval_accuracy": 0.372109078032372, | |
| "eval_loss": 3.5425467491149902, | |
| "eval_runtime": 53.7032, | |
| "eval_samples_per_second": 310.056, | |
| "eval_steps_per_second": 19.384, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 15.73067070330694, | |
| "grad_norm": 0.3841068744659424, | |
| "learning_rate": 0.0004114769947582993, | |
| "loss": 3.3037, | |
| "step": 54050 | |
| }, | |
| { | |
| "epoch": 15.745225896599907, | |
| "grad_norm": 0.3629019558429718, | |
| "learning_rate": 0.0004113022714036109, | |
| "loss": 3.3055, | |
| "step": 54100 | |
| }, | |
| { | |
| "epoch": 15.759781089892874, | |
| "grad_norm": 0.3605128526687622, | |
| "learning_rate": 0.0004111275480489225, | |
| "loss": 3.2894, | |
| "step": 54150 | |
| }, | |
| { | |
| "epoch": 15.774336283185841, | |
| "grad_norm": 0.3636111319065094, | |
| "learning_rate": 0.0004109528246942341, | |
| "loss": 3.3006, | |
| "step": 54200 | |
| }, | |
| { | |
| "epoch": 15.788891476478808, | |
| "grad_norm": 0.3551846742630005, | |
| "learning_rate": 0.0004107781013395457, | |
| "loss": 3.2915, | |
| "step": 54250 | |
| }, | |
| { | |
| "epoch": 15.803446669771775, | |
| "grad_norm": 0.359421044588089, | |
| "learning_rate": 0.0004106033779848573, | |
| "loss": 3.3176, | |
| "step": 54300 | |
| }, | |
| { | |
| "epoch": 15.818001863064742, | |
| "grad_norm": 0.3486231863498688, | |
| "learning_rate": 0.0004104286546301689, | |
| "loss": 3.3099, | |
| "step": 54350 | |
| }, | |
| { | |
| "epoch": 15.83255705635771, | |
| "grad_norm": 0.3626258373260498, | |
| "learning_rate": 0.0004102539312754804, | |
| "loss": 3.3047, | |
| "step": 54400 | |
| }, | |
| { | |
| "epoch": 15.847112249650674, | |
| "grad_norm": 0.3498855531215668, | |
| "learning_rate": 0.00041007920792079206, | |
| "loss": 3.3088, | |
| "step": 54450 | |
| }, | |
| { | |
| "epoch": 15.861667442943642, | |
| "grad_norm": 0.376212477684021, | |
| "learning_rate": 0.00040990448456610366, | |
| "loss": 3.303, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 15.876222636236609, | |
| "grad_norm": 0.35721027851104736, | |
| "learning_rate": 0.00040972976121141525, | |
| "loss": 3.2962, | |
| "step": 54550 | |
| }, | |
| { | |
| "epoch": 15.890777829529576, | |
| "grad_norm": 0.3870522081851959, | |
| "learning_rate": 0.0004095550378567268, | |
| "loss": 3.3251, | |
| "step": 54600 | |
| }, | |
| { | |
| "epoch": 15.905333022822543, | |
| "grad_norm": 0.3778719902038574, | |
| "learning_rate": 0.0004093803145020384, | |
| "loss": 3.3047, | |
| "step": 54650 | |
| }, | |
| { | |
| "epoch": 15.91988821611551, | |
| "grad_norm": 0.35420340299606323, | |
| "learning_rate": 0.00040920559114735, | |
| "loss": 3.3135, | |
| "step": 54700 | |
| }, | |
| { | |
| "epoch": 15.934443409408477, | |
| "grad_norm": 0.3482398986816406, | |
| "learning_rate": 0.00040903086779266163, | |
| "loss": 3.3131, | |
| "step": 54750 | |
| }, | |
| { | |
| "epoch": 15.948998602701444, | |
| "grad_norm": 0.3295566141605377, | |
| "learning_rate": 0.00040885614443797317, | |
| "loss": 3.3072, | |
| "step": 54800 | |
| }, | |
| { | |
| "epoch": 15.963553795994411, | |
| "grad_norm": 0.35038697719573975, | |
| "learning_rate": 0.00040868142108328476, | |
| "loss": 3.3127, | |
| "step": 54850 | |
| }, | |
| { | |
| "epoch": 15.978108989287378, | |
| "grad_norm": 0.36747032403945923, | |
| "learning_rate": 0.00040850669772859636, | |
| "loss": 3.3065, | |
| "step": 54900 | |
| }, | |
| { | |
| "epoch": 15.992664182580345, | |
| "grad_norm": 0.36744454503059387, | |
| "learning_rate": 0.0004083319743739079, | |
| "loss": 3.3068, | |
| "step": 54950 | |
| }, | |
| { | |
| "epoch": 16.006986492780623, | |
| "grad_norm": 0.3768289089202881, | |
| "learning_rate": 0.0004081572510192195, | |
| "loss": 3.2596, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 16.006986492780623, | |
| "eval_accuracy": 0.37148277502182775, | |
| "eval_loss": 3.5511021614074707, | |
| "eval_runtime": 53.6425, | |
| "eval_samples_per_second": 310.407, | |
| "eval_steps_per_second": 19.406, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 16.02154168607359, | |
| "grad_norm": 0.35373979806900024, | |
| "learning_rate": 0.00040798252766453114, | |
| "loss": 3.1979, | |
| "step": 55050 | |
| }, | |
| { | |
| "epoch": 16.036096879366557, | |
| "grad_norm": 0.3785567283630371, | |
| "learning_rate": 0.00040780780430984273, | |
| "loss": 3.2003, | |
| "step": 55100 | |
| }, | |
| { | |
| "epoch": 16.050652072659524, | |
| "grad_norm": 0.3592332601547241, | |
| "learning_rate": 0.0004076330809551543, | |
| "loss": 3.2191, | |
| "step": 55150 | |
| }, | |
| { | |
| "epoch": 16.06520726595249, | |
| "grad_norm": 0.3695092499256134, | |
| "learning_rate": 0.00040745835760046587, | |
| "loss": 3.2141, | |
| "step": 55200 | |
| }, | |
| { | |
| "epoch": 16.079762459245458, | |
| "grad_norm": 0.3837168216705322, | |
| "learning_rate": 0.00040728363424577746, | |
| "loss": 3.234, | |
| "step": 55250 | |
| }, | |
| { | |
| "epoch": 16.094317652538425, | |
| "grad_norm": 0.3706362545490265, | |
| "learning_rate": 0.0004071089108910891, | |
| "loss": 3.2119, | |
| "step": 55300 | |
| }, | |
| { | |
| "epoch": 16.108872845831392, | |
| "grad_norm": 0.3601118326187134, | |
| "learning_rate": 0.0004069341875364007, | |
| "loss": 3.2253, | |
| "step": 55350 | |
| }, | |
| { | |
| "epoch": 16.12342803912436, | |
| "grad_norm": 0.3782362937927246, | |
| "learning_rate": 0.00040675946418171225, | |
| "loss": 3.2185, | |
| "step": 55400 | |
| }, | |
| { | |
| "epoch": 16.137983232417326, | |
| "grad_norm": 0.37162870168685913, | |
| "learning_rate": 0.00040658474082702384, | |
| "loss": 3.229, | |
| "step": 55450 | |
| }, | |
| { | |
| "epoch": 16.152538425710294, | |
| "grad_norm": 0.37750357389450073, | |
| "learning_rate": 0.00040641001747233543, | |
| "loss": 3.2323, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 16.16709361900326, | |
| "grad_norm": 0.3554252088069916, | |
| "learning_rate": 0.000406235294117647, | |
| "loss": 3.2445, | |
| "step": 55550 | |
| }, | |
| { | |
| "epoch": 16.181648812296228, | |
| "grad_norm": 0.37780436873435974, | |
| "learning_rate": 0.0004060605707629586, | |
| "loss": 3.2459, | |
| "step": 55600 | |
| }, | |
| { | |
| "epoch": 16.196204005589195, | |
| "grad_norm": 0.41690900921821594, | |
| "learning_rate": 0.0004058858474082702, | |
| "loss": 3.2424, | |
| "step": 55650 | |
| }, | |
| { | |
| "epoch": 16.21075919888216, | |
| "grad_norm": 0.378083199262619, | |
| "learning_rate": 0.0004057111240535818, | |
| "loss": 3.2333, | |
| "step": 55700 | |
| }, | |
| { | |
| "epoch": 16.22531439217513, | |
| "grad_norm": 0.3967720568180084, | |
| "learning_rate": 0.00040553640069889335, | |
| "loss": 3.2598, | |
| "step": 55750 | |
| }, | |
| { | |
| "epoch": 16.239869585468096, | |
| "grad_norm": 0.39050132036209106, | |
| "learning_rate": 0.00040536167734420495, | |
| "loss": 3.2465, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 16.254424778761063, | |
| "grad_norm": 0.36171504855155945, | |
| "learning_rate": 0.0004051869539895166, | |
| "loss": 3.2495, | |
| "step": 55850 | |
| }, | |
| { | |
| "epoch": 16.26897997205403, | |
| "grad_norm": 0.3742135763168335, | |
| "learning_rate": 0.0004050122306348282, | |
| "loss": 3.2674, | |
| "step": 55900 | |
| }, | |
| { | |
| "epoch": 16.283535165346997, | |
| "grad_norm": 0.3664557635784149, | |
| "learning_rate": 0.00040483750728013973, | |
| "loss": 3.2487, | |
| "step": 55950 | |
| }, | |
| { | |
| "epoch": 16.298090358639964, | |
| "grad_norm": 0.37625637650489807, | |
| "learning_rate": 0.0004046627839254513, | |
| "loss": 3.2495, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 16.298090358639964, | |
| "eval_accuracy": 0.371524144633333, | |
| "eval_loss": 3.5544068813323975, | |
| "eval_runtime": 53.428, | |
| "eval_samples_per_second": 311.653, | |
| "eval_steps_per_second": 19.484, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 16.31264555193293, | |
| "grad_norm": 0.38411176204681396, | |
| "learning_rate": 0.0004044880605707629, | |
| "loss": 3.2583, | |
| "step": 56050 | |
| }, | |
| { | |
| "epoch": 16.3272007452259, | |
| "grad_norm": 0.35315781831741333, | |
| "learning_rate": 0.00040431333721607446, | |
| "loss": 3.2602, | |
| "step": 56100 | |
| }, | |
| { | |
| "epoch": 16.341755938518865, | |
| "grad_norm": 0.38930264115333557, | |
| "learning_rate": 0.0004041386138613861, | |
| "loss": 3.2415, | |
| "step": 56150 | |
| }, | |
| { | |
| "epoch": 16.35631113181183, | |
| "grad_norm": 0.37382471561431885, | |
| "learning_rate": 0.0004039638905066977, | |
| "loss": 3.2608, | |
| "step": 56200 | |
| }, | |
| { | |
| "epoch": 16.370866325104796, | |
| "grad_norm": 0.3800281882286072, | |
| "learning_rate": 0.0004037891671520093, | |
| "loss": 3.2704, | |
| "step": 56250 | |
| }, | |
| { | |
| "epoch": 16.385421518397763, | |
| "grad_norm": 0.3717670738697052, | |
| "learning_rate": 0.0004036144437973209, | |
| "loss": 3.2675, | |
| "step": 56300 | |
| }, | |
| { | |
| "epoch": 16.39997671169073, | |
| "grad_norm": 0.35903260111808777, | |
| "learning_rate": 0.00040343972044263243, | |
| "loss": 3.2664, | |
| "step": 56350 | |
| }, | |
| { | |
| "epoch": 16.414531904983697, | |
| "grad_norm": 0.37332117557525635, | |
| "learning_rate": 0.0004032649970879441, | |
| "loss": 3.2669, | |
| "step": 56400 | |
| }, | |
| { | |
| "epoch": 16.429087098276664, | |
| "grad_norm": 0.3922117352485657, | |
| "learning_rate": 0.00040309027373325567, | |
| "loss": 3.2805, | |
| "step": 56450 | |
| }, | |
| { | |
| "epoch": 16.44364229156963, | |
| "grad_norm": 0.34870415925979614, | |
| "learning_rate": 0.00040291555037856727, | |
| "loss": 3.2783, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 16.4581974848626, | |
| "grad_norm": 0.371022492647171, | |
| "learning_rate": 0.0004027408270238788, | |
| "loss": 3.2691, | |
| "step": 56550 | |
| }, | |
| { | |
| "epoch": 16.472752678155565, | |
| "grad_norm": 0.36151501536369324, | |
| "learning_rate": 0.0004025661036691904, | |
| "loss": 3.2852, | |
| "step": 56600 | |
| }, | |
| { | |
| "epoch": 16.487307871448532, | |
| "grad_norm": 0.36976906657218933, | |
| "learning_rate": 0.000402391380314502, | |
| "loss": 3.2781, | |
| "step": 56650 | |
| }, | |
| { | |
| "epoch": 16.5018630647415, | |
| "grad_norm": 0.39228200912475586, | |
| "learning_rate": 0.00040221665695981364, | |
| "loss": 3.2772, | |
| "step": 56700 | |
| }, | |
| { | |
| "epoch": 16.516418258034467, | |
| "grad_norm": 0.37740734219551086, | |
| "learning_rate": 0.0004020419336051252, | |
| "loss": 3.2682, | |
| "step": 56750 | |
| }, | |
| { | |
| "epoch": 16.530973451327434, | |
| "grad_norm": 0.3785878121852875, | |
| "learning_rate": 0.0004018672102504368, | |
| "loss": 3.267, | |
| "step": 56800 | |
| }, | |
| { | |
| "epoch": 16.5455286446204, | |
| "grad_norm": 0.3659798800945282, | |
| "learning_rate": 0.00040169248689574837, | |
| "loss": 3.2717, | |
| "step": 56850 | |
| }, | |
| { | |
| "epoch": 16.560083837913368, | |
| "grad_norm": 0.3837704062461853, | |
| "learning_rate": 0.0004015177635410599, | |
| "loss": 3.2815, | |
| "step": 56900 | |
| }, | |
| { | |
| "epoch": 16.574639031206335, | |
| "grad_norm": 0.3840257525444031, | |
| "learning_rate": 0.0004013430401863715, | |
| "loss": 3.2653, | |
| "step": 56950 | |
| }, | |
| { | |
| "epoch": 16.589194224499302, | |
| "grad_norm": 0.3545569181442261, | |
| "learning_rate": 0.00040116831683168315, | |
| "loss": 3.2826, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 16.589194224499302, | |
| "eval_accuracy": 0.37220098438520466, | |
| "eval_loss": 3.5467562675476074, | |
| "eval_runtime": 53.4526, | |
| "eval_samples_per_second": 311.51, | |
| "eval_steps_per_second": 19.475, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 16.60374941779227, | |
| "grad_norm": 0.35367175936698914, | |
| "learning_rate": 0.00040099359347699475, | |
| "loss": 3.2872, | |
| "step": 57050 | |
| }, | |
| { | |
| "epoch": 16.618304611085236, | |
| "grad_norm": 0.39484596252441406, | |
| "learning_rate": 0.0004008188701223063, | |
| "loss": 3.2735, | |
| "step": 57100 | |
| }, | |
| { | |
| "epoch": 16.632859804378203, | |
| "grad_norm": 0.4046483635902405, | |
| "learning_rate": 0.0004006441467676179, | |
| "loss": 3.2875, | |
| "step": 57150 | |
| }, | |
| { | |
| "epoch": 16.64741499767117, | |
| "grad_norm": 0.34602469205856323, | |
| "learning_rate": 0.0004004694234129295, | |
| "loss": 3.2799, | |
| "step": 57200 | |
| }, | |
| { | |
| "epoch": 16.661970190964137, | |
| "grad_norm": 0.4004819989204407, | |
| "learning_rate": 0.0004002947000582411, | |
| "loss": 3.2895, | |
| "step": 57250 | |
| }, | |
| { | |
| "epoch": 16.676525384257104, | |
| "grad_norm": 0.3903782367706299, | |
| "learning_rate": 0.00040011997670355267, | |
| "loss": 3.2912, | |
| "step": 57300 | |
| }, | |
| { | |
| "epoch": 16.69108057755007, | |
| "grad_norm": 0.35985222458839417, | |
| "learning_rate": 0.00039994525334886426, | |
| "loss": 3.2941, | |
| "step": 57350 | |
| }, | |
| { | |
| "epoch": 16.70563577084304, | |
| "grad_norm": 0.3627176284790039, | |
| "learning_rate": 0.00039977052999417585, | |
| "loss": 3.2877, | |
| "step": 57400 | |
| }, | |
| { | |
| "epoch": 16.720190964136005, | |
| "grad_norm": 0.37140709161758423, | |
| "learning_rate": 0.00039959580663948745, | |
| "loss": 3.2771, | |
| "step": 57450 | |
| }, | |
| { | |
| "epoch": 16.734746157428972, | |
| "grad_norm": 0.34368351101875305, | |
| "learning_rate": 0.000399421083284799, | |
| "loss": 3.29, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 16.749301350721936, | |
| "grad_norm": 0.3953946530818939, | |
| "learning_rate": 0.00039924635993011064, | |
| "loss": 3.2954, | |
| "step": 57550 | |
| }, | |
| { | |
| "epoch": 16.763856544014903, | |
| "grad_norm": 0.35603564977645874, | |
| "learning_rate": 0.00039907163657542223, | |
| "loss": 3.2911, | |
| "step": 57600 | |
| }, | |
| { | |
| "epoch": 16.77841173730787, | |
| "grad_norm": 0.39332327246665955, | |
| "learning_rate": 0.0003988969132207338, | |
| "loss": 3.292, | |
| "step": 57650 | |
| }, | |
| { | |
| "epoch": 16.792966930600837, | |
| "grad_norm": 0.36506056785583496, | |
| "learning_rate": 0.00039872218986604537, | |
| "loss": 3.2964, | |
| "step": 57700 | |
| }, | |
| { | |
| "epoch": 16.807522123893804, | |
| "grad_norm": 0.3711180090904236, | |
| "learning_rate": 0.00039854746651135696, | |
| "loss": 3.2775, | |
| "step": 57750 | |
| }, | |
| { | |
| "epoch": 16.82207731718677, | |
| "grad_norm": 0.379778116941452, | |
| "learning_rate": 0.0003983727431566686, | |
| "loss": 3.2917, | |
| "step": 57800 | |
| }, | |
| { | |
| "epoch": 16.83663251047974, | |
| "grad_norm": 0.36001497507095337, | |
| "learning_rate": 0.0003981980198019802, | |
| "loss": 3.295, | |
| "step": 57850 | |
| }, | |
| { | |
| "epoch": 16.851187703772705, | |
| "grad_norm": 0.3631613850593567, | |
| "learning_rate": 0.00039802329644729174, | |
| "loss": 3.2903, | |
| "step": 57900 | |
| }, | |
| { | |
| "epoch": 16.865742897065672, | |
| "grad_norm": 0.37399163842201233, | |
| "learning_rate": 0.00039784857309260334, | |
| "loss": 3.301, | |
| "step": 57950 | |
| }, | |
| { | |
| "epoch": 16.88029809035864, | |
| "grad_norm": 0.3752025067806244, | |
| "learning_rate": 0.00039767384973791493, | |
| "loss": 3.2957, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 16.88029809035864, | |
| "eval_accuracy": 0.3724651857677724, | |
| "eval_loss": 3.5390286445617676, | |
| "eval_runtime": 53.4952, | |
| "eval_samples_per_second": 311.262, | |
| "eval_steps_per_second": 19.46, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 16.894853283651607, | |
| "grad_norm": 0.37060099840164185, | |
| "learning_rate": 0.00039749912638322647, | |
| "loss": 3.2993, | |
| "step": 58050 | |
| }, | |
| { | |
| "epoch": 16.909408476944574, | |
| "grad_norm": 0.34579336643218994, | |
| "learning_rate": 0.0003973244030285381, | |
| "loss": 3.3007, | |
| "step": 58100 | |
| }, | |
| { | |
| "epoch": 16.92396367023754, | |
| "grad_norm": 0.37663620710372925, | |
| "learning_rate": 0.0003971496796738497, | |
| "loss": 3.2995, | |
| "step": 58150 | |
| }, | |
| { | |
| "epoch": 16.938518863530508, | |
| "grad_norm": 0.3452092409133911, | |
| "learning_rate": 0.0003969749563191613, | |
| "loss": 3.3004, | |
| "step": 58200 | |
| }, | |
| { | |
| "epoch": 16.953074056823475, | |
| "grad_norm": 0.36774107813835144, | |
| "learning_rate": 0.00039680023296447285, | |
| "loss": 3.285, | |
| "step": 58250 | |
| }, | |
| { | |
| "epoch": 16.967629250116442, | |
| "grad_norm": 0.3845987021923065, | |
| "learning_rate": 0.00039662550960978444, | |
| "loss": 3.302, | |
| "step": 58300 | |
| }, | |
| { | |
| "epoch": 16.98218444340941, | |
| "grad_norm": 0.3576522171497345, | |
| "learning_rate": 0.00039645078625509604, | |
| "loss": 3.307, | |
| "step": 58350 | |
| }, | |
| { | |
| "epoch": 16.996739636702376, | |
| "grad_norm": 0.35200732946395874, | |
| "learning_rate": 0.0003962760629004077, | |
| "loss": 3.2851, | |
| "step": 58400 | |
| }, | |
| { | |
| "epoch": 17.011061946902654, | |
| "grad_norm": 0.3575538694858551, | |
| "learning_rate": 0.0003961013395457193, | |
| "loss": 3.2058, | |
| "step": 58450 | |
| }, | |
| { | |
| "epoch": 17.02561714019562, | |
| "grad_norm": 0.3989085555076599, | |
| "learning_rate": 0.0003959266161910308, | |
| "loss": 3.1824, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 17.040172333488588, | |
| "grad_norm": 0.35313835740089417, | |
| "learning_rate": 0.0003957518928363424, | |
| "loss": 3.1878, | |
| "step": 58550 | |
| }, | |
| { | |
| "epoch": 17.054727526781555, | |
| "grad_norm": 0.36877205967903137, | |
| "learning_rate": 0.000395577169481654, | |
| "loss": 3.1958, | |
| "step": 58600 | |
| }, | |
| { | |
| "epoch": 17.069282720074522, | |
| "grad_norm": 0.3629121780395508, | |
| "learning_rate": 0.00039540244612696566, | |
| "loss": 3.1973, | |
| "step": 58650 | |
| }, | |
| { | |
| "epoch": 17.08383791336749, | |
| "grad_norm": 0.4019306004047394, | |
| "learning_rate": 0.0003952277227722772, | |
| "loss": 3.2077, | |
| "step": 58700 | |
| }, | |
| { | |
| "epoch": 17.098393106660456, | |
| "grad_norm": 0.36973902583122253, | |
| "learning_rate": 0.0003950529994175888, | |
| "loss": 3.2098, | |
| "step": 58750 | |
| }, | |
| { | |
| "epoch": 17.112948299953423, | |
| "grad_norm": 0.3842083215713501, | |
| "learning_rate": 0.0003948782760629004, | |
| "loss": 3.2247, | |
| "step": 58800 | |
| }, | |
| { | |
| "epoch": 17.12750349324639, | |
| "grad_norm": 0.37391912937164307, | |
| "learning_rate": 0.0003947035527082119, | |
| "loss": 3.2297, | |
| "step": 58850 | |
| }, | |
| { | |
| "epoch": 17.142058686539357, | |
| "grad_norm": 0.3761378228664398, | |
| "learning_rate": 0.0003945288293535235, | |
| "loss": 3.2174, | |
| "step": 58900 | |
| }, | |
| { | |
| "epoch": 17.156613879832324, | |
| "grad_norm": 0.3829362094402313, | |
| "learning_rate": 0.00039435410599883517, | |
| "loss": 3.2224, | |
| "step": 58950 | |
| }, | |
| { | |
| "epoch": 17.17116907312529, | |
| "grad_norm": 0.3926464319229126, | |
| "learning_rate": 0.00039417938264414676, | |
| "loss": 3.2293, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 17.17116907312529, | |
| "eval_accuracy": 0.3721046119947663, | |
| "eval_loss": 3.5530450344085693, | |
| "eval_runtime": 53.6932, | |
| "eval_samples_per_second": 310.114, | |
| "eval_steps_per_second": 19.388, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 17.18572426641826, | |
| "grad_norm": 0.345100998878479, | |
| "learning_rate": 0.0003940046592894583, | |
| "loss": 3.2253, | |
| "step": 59050 | |
| }, | |
| { | |
| "epoch": 17.200279459711226, | |
| "grad_norm": 0.36901769042015076, | |
| "learning_rate": 0.0003938299359347699, | |
| "loss": 3.233, | |
| "step": 59100 | |
| }, | |
| { | |
| "epoch": 17.214834653004193, | |
| "grad_norm": 0.3561706244945526, | |
| "learning_rate": 0.0003936552125800815, | |
| "loss": 3.2267, | |
| "step": 59150 | |
| }, | |
| { | |
| "epoch": 17.22938984629716, | |
| "grad_norm": 0.4001246690750122, | |
| "learning_rate": 0.00039348048922539314, | |
| "loss": 3.2339, | |
| "step": 59200 | |
| }, | |
| { | |
| "epoch": 17.243945039590127, | |
| "grad_norm": 0.38598838448524475, | |
| "learning_rate": 0.0003933057658707047, | |
| "loss": 3.2412, | |
| "step": 59250 | |
| }, | |
| { | |
| "epoch": 17.258500232883094, | |
| "grad_norm": 0.3747839331626892, | |
| "learning_rate": 0.0003931310425160163, | |
| "loss": 3.2508, | |
| "step": 59300 | |
| }, | |
| { | |
| "epoch": 17.27305542617606, | |
| "grad_norm": 0.39467811584472656, | |
| "learning_rate": 0.00039295631916132787, | |
| "loss": 3.2455, | |
| "step": 59350 | |
| }, | |
| { | |
| "epoch": 17.287610619469028, | |
| "grad_norm": 0.4095667004585266, | |
| "learning_rate": 0.00039278159580663946, | |
| "loss": 3.2386, | |
| "step": 59400 | |
| }, | |
| { | |
| "epoch": 17.302165812761995, | |
| "grad_norm": 0.38847097754478455, | |
| "learning_rate": 0.000392606872451951, | |
| "loss": 3.241, | |
| "step": 59450 | |
| }, | |
| { | |
| "epoch": 17.316721006054962, | |
| "grad_norm": 0.36311227083206177, | |
| "learning_rate": 0.00039243214909726265, | |
| "loss": 3.2419, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 17.331276199347926, | |
| "grad_norm": 0.3604174256324768, | |
| "learning_rate": 0.00039225742574257425, | |
| "loss": 3.2394, | |
| "step": 59550 | |
| }, | |
| { | |
| "epoch": 17.345831392640893, | |
| "grad_norm": 0.36166009306907654, | |
| "learning_rate": 0.00039208270238788584, | |
| "loss": 3.2402, | |
| "step": 59600 | |
| }, | |
| { | |
| "epoch": 17.36038658593386, | |
| "grad_norm": 0.3587791621685028, | |
| "learning_rate": 0.0003919079790331974, | |
| "loss": 3.2461, | |
| "step": 59650 | |
| }, | |
| { | |
| "epoch": 17.374941779226827, | |
| "grad_norm": 0.354829877614975, | |
| "learning_rate": 0.000391733255678509, | |
| "loss": 3.2574, | |
| "step": 59700 | |
| }, | |
| { | |
| "epoch": 17.389496972519794, | |
| "grad_norm": 0.3491046726703644, | |
| "learning_rate": 0.00039155853232382057, | |
| "loss": 3.2616, | |
| "step": 59750 | |
| }, | |
| { | |
| "epoch": 17.40405216581276, | |
| "grad_norm": 0.38688045740127563, | |
| "learning_rate": 0.0003913838089691322, | |
| "loss": 3.2529, | |
| "step": 59800 | |
| }, | |
| { | |
| "epoch": 17.418607359105728, | |
| "grad_norm": 0.36603111028671265, | |
| "learning_rate": 0.00039120908561444376, | |
| "loss": 3.2592, | |
| "step": 59850 | |
| }, | |
| { | |
| "epoch": 17.433162552398695, | |
| "grad_norm": 0.41972315311431885, | |
| "learning_rate": 0.00039103436225975535, | |
| "loss": 3.242, | |
| "step": 59900 | |
| }, | |
| { | |
| "epoch": 17.447717745691662, | |
| "grad_norm": 0.35975244641304016, | |
| "learning_rate": 0.00039085963890506695, | |
| "loss": 3.2612, | |
| "step": 59950 | |
| }, | |
| { | |
| "epoch": 17.46227293898463, | |
| "grad_norm": 0.4002673625946045, | |
| "learning_rate": 0.0003906849155503785, | |
| "loss": 3.2615, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 17.46227293898463, | |
| "eval_accuracy": 0.3723208622367256, | |
| "eval_loss": 3.5476441383361816, | |
| "eval_runtime": 53.5923, | |
| "eval_samples_per_second": 310.698, | |
| "eval_steps_per_second": 19.424, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 17.476828132277596, | |
| "grad_norm": 0.35748979449272156, | |
| "learning_rate": 0.00039051019219569014, | |
| "loss": 3.2669, | |
| "step": 60050 | |
| }, | |
| { | |
| "epoch": 17.491383325570563, | |
| "grad_norm": 0.3614111542701721, | |
| "learning_rate": 0.00039033546884100173, | |
| "loss": 3.2547, | |
| "step": 60100 | |
| }, | |
| { | |
| "epoch": 17.50593851886353, | |
| "grad_norm": 0.36013323068618774, | |
| "learning_rate": 0.0003901607454863133, | |
| "loss": 3.2607, | |
| "step": 60150 | |
| }, | |
| { | |
| "epoch": 17.520493712156497, | |
| "grad_norm": 0.35987821221351624, | |
| "learning_rate": 0.00038998602213162486, | |
| "loss": 3.2638, | |
| "step": 60200 | |
| }, | |
| { | |
| "epoch": 17.535048905449464, | |
| "grad_norm": 0.3712620139122009, | |
| "learning_rate": 0.00038981129877693646, | |
| "loss": 3.2626, | |
| "step": 60250 | |
| }, | |
| { | |
| "epoch": 17.54960409874243, | |
| "grad_norm": 0.38060471415519714, | |
| "learning_rate": 0.00038963657542224805, | |
| "loss": 3.2656, | |
| "step": 60300 | |
| }, | |
| { | |
| "epoch": 17.5641592920354, | |
| "grad_norm": 0.35977795720100403, | |
| "learning_rate": 0.0003894618520675597, | |
| "loss": 3.2669, | |
| "step": 60350 | |
| }, | |
| { | |
| "epoch": 17.578714485328366, | |
| "grad_norm": 0.4130357503890991, | |
| "learning_rate": 0.00038928712871287124, | |
| "loss": 3.2696, | |
| "step": 60400 | |
| }, | |
| { | |
| "epoch": 17.593269678621333, | |
| "grad_norm": 0.39794033765792847, | |
| "learning_rate": 0.00038911240535818284, | |
| "loss": 3.271, | |
| "step": 60450 | |
| }, | |
| { | |
| "epoch": 17.6078248719143, | |
| "grad_norm": 0.36843588948249817, | |
| "learning_rate": 0.00038893768200349443, | |
| "loss": 3.2789, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 17.622380065207267, | |
| "grad_norm": 0.40033963322639465, | |
| "learning_rate": 0.000388762958648806, | |
| "loss": 3.2795, | |
| "step": 60550 | |
| }, | |
| { | |
| "epoch": 17.636935258500234, | |
| "grad_norm": 0.35067299008369446, | |
| "learning_rate": 0.0003885882352941176, | |
| "loss": 3.2652, | |
| "step": 60600 | |
| }, | |
| { | |
| "epoch": 17.6514904517932, | |
| "grad_norm": 0.36796697974205017, | |
| "learning_rate": 0.0003884135119394292, | |
| "loss": 3.2792, | |
| "step": 60650 | |
| }, | |
| { | |
| "epoch": 17.666045645086168, | |
| "grad_norm": 0.36432501673698425, | |
| "learning_rate": 0.0003882387885847408, | |
| "loss": 3.2657, | |
| "step": 60700 | |
| }, | |
| { | |
| "epoch": 17.680600838379135, | |
| "grad_norm": 0.3727700114250183, | |
| "learning_rate": 0.0003880640652300524, | |
| "loss": 3.2709, | |
| "step": 60750 | |
| }, | |
| { | |
| "epoch": 17.695156031672102, | |
| "grad_norm": 0.367959588766098, | |
| "learning_rate": 0.00038788934187536394, | |
| "loss": 3.273, | |
| "step": 60800 | |
| }, | |
| { | |
| "epoch": 17.70971122496507, | |
| "grad_norm": 0.3949326276779175, | |
| "learning_rate": 0.00038771461852067554, | |
| "loss": 3.2868, | |
| "step": 60850 | |
| }, | |
| { | |
| "epoch": 17.724266418258033, | |
| "grad_norm": 0.3685151934623718, | |
| "learning_rate": 0.0003875398951659872, | |
| "loss": 3.271, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 17.738821611551, | |
| "grad_norm": 0.3561553359031677, | |
| "learning_rate": 0.0003873651718112988, | |
| "loss": 3.2837, | |
| "step": 60950 | |
| }, | |
| { | |
| "epoch": 17.753376804843967, | |
| "grad_norm": 0.36604318022727966, | |
| "learning_rate": 0.0003871904484566103, | |
| "loss": 3.2782, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 17.753376804843967, | |
| "eval_accuracy": 0.3725977565682779, | |
| "eval_loss": 3.539083242416382, | |
| "eval_runtime": 53.5998, | |
| "eval_samples_per_second": 310.654, | |
| "eval_steps_per_second": 19.422, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 17.767931998136934, | |
| "grad_norm": 0.37786874175071716, | |
| "learning_rate": 0.0003870157251019219, | |
| "loss": 3.2749, | |
| "step": 61050 | |
| }, | |
| { | |
| "epoch": 17.7824871914299, | |
| "grad_norm": 0.3626755475997925, | |
| "learning_rate": 0.0003868410017472335, | |
| "loss": 3.263, | |
| "step": 61100 | |
| }, | |
| { | |
| "epoch": 17.797042384722868, | |
| "grad_norm": 0.3866601288318634, | |
| "learning_rate": 0.00038666627839254505, | |
| "loss": 3.2811, | |
| "step": 61150 | |
| }, | |
| { | |
| "epoch": 17.811597578015835, | |
| "grad_norm": 0.38018879294395447, | |
| "learning_rate": 0.0003864915550378567, | |
| "loss": 3.2796, | |
| "step": 61200 | |
| }, | |
| { | |
| "epoch": 17.826152771308802, | |
| "grad_norm": 0.3671089708805084, | |
| "learning_rate": 0.0003863168316831683, | |
| "loss": 3.2877, | |
| "step": 61250 | |
| }, | |
| { | |
| "epoch": 17.84070796460177, | |
| "grad_norm": 0.3674529492855072, | |
| "learning_rate": 0.0003861421083284799, | |
| "loss": 3.2805, | |
| "step": 61300 | |
| }, | |
| { | |
| "epoch": 17.855263157894736, | |
| "grad_norm": 0.3691335618495941, | |
| "learning_rate": 0.0003859673849737914, | |
| "loss": 3.2755, | |
| "step": 61350 | |
| }, | |
| { | |
| "epoch": 17.869818351187703, | |
| "grad_norm": 0.3887404501438141, | |
| "learning_rate": 0.000385792661619103, | |
| "loss": 3.2774, | |
| "step": 61400 | |
| }, | |
| { | |
| "epoch": 17.88437354448067, | |
| "grad_norm": 0.3935135304927826, | |
| "learning_rate": 0.00038561793826441467, | |
| "loss": 3.2773, | |
| "step": 61450 | |
| }, | |
| { | |
| "epoch": 17.898928737773637, | |
| "grad_norm": 0.3719732165336609, | |
| "learning_rate": 0.00038544321490972626, | |
| "loss": 3.2971, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 17.913483931066605, | |
| "grad_norm": 0.37385624647140503, | |
| "learning_rate": 0.0003852684915550378, | |
| "loss": 3.2888, | |
| "step": 61550 | |
| }, | |
| { | |
| "epoch": 17.92803912435957, | |
| "grad_norm": 0.3705180287361145, | |
| "learning_rate": 0.0003850937682003494, | |
| "loss": 3.2722, | |
| "step": 61600 | |
| }, | |
| { | |
| "epoch": 17.94259431765254, | |
| "grad_norm": 0.367830753326416, | |
| "learning_rate": 0.000384919044845661, | |
| "loss": 3.2944, | |
| "step": 61650 | |
| }, | |
| { | |
| "epoch": 17.957149510945506, | |
| "grad_norm": 0.3608112335205078, | |
| "learning_rate": 0.0003847443214909726, | |
| "loss": 3.2823, | |
| "step": 61700 | |
| }, | |
| { | |
| "epoch": 17.971704704238473, | |
| "grad_norm": 0.3659210205078125, | |
| "learning_rate": 0.00038456959813628423, | |
| "loss": 3.2866, | |
| "step": 61750 | |
| }, | |
| { | |
| "epoch": 17.98625989753144, | |
| "grad_norm": 0.376975417137146, | |
| "learning_rate": 0.0003843948747815958, | |
| "loss": 3.2931, | |
| "step": 61800 | |
| }, | |
| { | |
| "epoch": 18.000582207731718, | |
| "grad_norm": 0.39236682653427124, | |
| "learning_rate": 0.00038422015142690737, | |
| "loss": 3.2734, | |
| "step": 61850 | |
| }, | |
| { | |
| "epoch": 18.015137401024685, | |
| "grad_norm": 0.38358330726623535, | |
| "learning_rate": 0.00038404542807221896, | |
| "loss": 3.1734, | |
| "step": 61900 | |
| }, | |
| { | |
| "epoch": 18.029692594317652, | |
| "grad_norm": 0.3715524673461914, | |
| "learning_rate": 0.0003838707047175305, | |
| "loss": 3.1818, | |
| "step": 61950 | |
| }, | |
| { | |
| "epoch": 18.04424778761062, | |
| "grad_norm": 0.36147281527519226, | |
| "learning_rate": 0.00038369598136284215, | |
| "loss": 3.1838, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 18.04424778761062, | |
| "eval_accuracy": 0.3726124474814545, | |
| "eval_loss": 3.5498955249786377, | |
| "eval_runtime": 53.5929, | |
| "eval_samples_per_second": 310.694, | |
| "eval_steps_per_second": 19.424, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 18.058802980903586, | |
| "grad_norm": 0.4079315662384033, | |
| "learning_rate": 0.00038352125800815374, | |
| "loss": 3.1945, | |
| "step": 62050 | |
| }, | |
| { | |
| "epoch": 18.073358174196553, | |
| "grad_norm": 0.37014585733413696, | |
| "learning_rate": 0.00038334653465346534, | |
| "loss": 3.196, | |
| "step": 62100 | |
| }, | |
| { | |
| "epoch": 18.08791336748952, | |
| "grad_norm": 0.3907884955406189, | |
| "learning_rate": 0.0003831718112987769, | |
| "loss": 3.2032, | |
| "step": 62150 | |
| }, | |
| { | |
| "epoch": 18.102468560782487, | |
| "grad_norm": 0.366449236869812, | |
| "learning_rate": 0.0003829970879440885, | |
| "loss": 3.2047, | |
| "step": 62200 | |
| }, | |
| { | |
| "epoch": 18.117023754075454, | |
| "grad_norm": 0.38395488262176514, | |
| "learning_rate": 0.00038282236458940007, | |
| "loss": 3.2097, | |
| "step": 62250 | |
| }, | |
| { | |
| "epoch": 18.13157894736842, | |
| "grad_norm": 0.38716116547584534, | |
| "learning_rate": 0.0003826476412347117, | |
| "loss": 3.1993, | |
| "step": 62300 | |
| }, | |
| { | |
| "epoch": 18.14613414066139, | |
| "grad_norm": 0.37983572483062744, | |
| "learning_rate": 0.00038247291788002326, | |
| "loss": 3.2009, | |
| "step": 62350 | |
| }, | |
| { | |
| "epoch": 18.160689333954355, | |
| "grad_norm": 0.42031049728393555, | |
| "learning_rate": 0.00038229819452533485, | |
| "loss": 3.2195, | |
| "step": 62400 | |
| }, | |
| { | |
| "epoch": 18.175244527247322, | |
| "grad_norm": 0.3917589485645294, | |
| "learning_rate": 0.00038212347117064644, | |
| "loss": 3.2175, | |
| "step": 62450 | |
| }, | |
| { | |
| "epoch": 18.18979972054029, | |
| "grad_norm": 0.3656430244445801, | |
| "learning_rate": 0.000381948747815958, | |
| "loss": 3.2185, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 18.204354913833257, | |
| "grad_norm": 0.372780442237854, | |
| "learning_rate": 0.0003817740244612696, | |
| "loss": 3.2161, | |
| "step": 62550 | |
| }, | |
| { | |
| "epoch": 18.218910107126224, | |
| "grad_norm": 0.38483792543411255, | |
| "learning_rate": 0.00038159930110658123, | |
| "loss": 3.2233, | |
| "step": 62600 | |
| }, | |
| { | |
| "epoch": 18.23346530041919, | |
| "grad_norm": 0.38355594873428345, | |
| "learning_rate": 0.0003814245777518928, | |
| "loss": 3.2184, | |
| "step": 62650 | |
| }, | |
| { | |
| "epoch": 18.248020493712158, | |
| "grad_norm": 0.36043310165405273, | |
| "learning_rate": 0.0003812498543972044, | |
| "loss": 3.2299, | |
| "step": 62700 | |
| }, | |
| { | |
| "epoch": 18.262575687005125, | |
| "grad_norm": 0.389116495847702, | |
| "learning_rate": 0.00038107513104251596, | |
| "loss": 3.2272, | |
| "step": 62750 | |
| }, | |
| { | |
| "epoch": 18.277130880298092, | |
| "grad_norm": 0.41563278436660767, | |
| "learning_rate": 0.00038090040768782755, | |
| "loss": 3.238, | |
| "step": 62800 | |
| }, | |
| { | |
| "epoch": 18.29168607359106, | |
| "grad_norm": 0.3994002640247345, | |
| "learning_rate": 0.0003807256843331392, | |
| "loss": 3.2348, | |
| "step": 62850 | |
| }, | |
| { | |
| "epoch": 18.306241266884022, | |
| "grad_norm": 0.3968697488307953, | |
| "learning_rate": 0.0003805509609784508, | |
| "loss": 3.2344, | |
| "step": 62900 | |
| }, | |
| { | |
| "epoch": 18.32079646017699, | |
| "grad_norm": 0.37374231219291687, | |
| "learning_rate": 0.00038037623762376233, | |
| "loss": 3.2271, | |
| "step": 62950 | |
| }, | |
| { | |
| "epoch": 18.335351653469957, | |
| "grad_norm": 0.39741528034210205, | |
| "learning_rate": 0.00038020151426907393, | |
| "loss": 3.2424, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 18.335351653469957, | |
| "eval_accuracy": 0.37257049023342215, | |
| "eval_loss": 3.5464248657226562, | |
| "eval_runtime": 53.726, | |
| "eval_samples_per_second": 309.925, | |
| "eval_steps_per_second": 19.376, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 18.349906846762924, | |
| "grad_norm": 0.3624269962310791, | |
| "learning_rate": 0.0003800267909143855, | |
| "loss": 3.2372, | |
| "step": 63050 | |
| }, | |
| { | |
| "epoch": 18.36446204005589, | |
| "grad_norm": 0.4036090075969696, | |
| "learning_rate": 0.00037985206755969706, | |
| "loss": 3.2297, | |
| "step": 63100 | |
| }, | |
| { | |
| "epoch": 18.379017233348858, | |
| "grad_norm": 0.3788849413394928, | |
| "learning_rate": 0.0003796773442050087, | |
| "loss": 3.2478, | |
| "step": 63150 | |
| }, | |
| { | |
| "epoch": 18.393572426641825, | |
| "grad_norm": 0.38333234190940857, | |
| "learning_rate": 0.0003795026208503203, | |
| "loss": 3.2393, | |
| "step": 63200 | |
| }, | |
| { | |
| "epoch": 18.408127619934792, | |
| "grad_norm": 0.405160129070282, | |
| "learning_rate": 0.0003793278974956319, | |
| "loss": 3.2353, | |
| "step": 63250 | |
| }, | |
| { | |
| "epoch": 18.42268281322776, | |
| "grad_norm": 0.36609381437301636, | |
| "learning_rate": 0.00037915317414094344, | |
| "loss": 3.2432, | |
| "step": 63300 | |
| }, | |
| { | |
| "epoch": 18.437238006520726, | |
| "grad_norm": 0.37396228313446045, | |
| "learning_rate": 0.00037897845078625503, | |
| "loss": 3.2488, | |
| "step": 63350 | |
| }, | |
| { | |
| "epoch": 18.451793199813693, | |
| "grad_norm": 0.3682529330253601, | |
| "learning_rate": 0.0003788037274315667, | |
| "loss": 3.241, | |
| "step": 63400 | |
| }, | |
| { | |
| "epoch": 18.46634839310666, | |
| "grad_norm": 0.3765323758125305, | |
| "learning_rate": 0.0003786290040768783, | |
| "loss": 3.2475, | |
| "step": 63450 | |
| }, | |
| { | |
| "epoch": 18.480903586399627, | |
| "grad_norm": 0.3813301920890808, | |
| "learning_rate": 0.0003784542807221898, | |
| "loss": 3.2494, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 18.495458779692594, | |
| "grad_norm": 0.3934621512889862, | |
| "learning_rate": 0.0003782795573675014, | |
| "loss": 3.2319, | |
| "step": 63550 | |
| }, | |
| { | |
| "epoch": 18.51001397298556, | |
| "grad_norm": 0.4102288782596588, | |
| "learning_rate": 0.000378104834012813, | |
| "loss": 3.2546, | |
| "step": 63600 | |
| }, | |
| { | |
| "epoch": 18.52456916627853, | |
| "grad_norm": 0.3712156116962433, | |
| "learning_rate": 0.0003779301106581246, | |
| "loss": 3.2443, | |
| "step": 63650 | |
| }, | |
| { | |
| "epoch": 18.539124359571495, | |
| "grad_norm": 0.3902559280395508, | |
| "learning_rate": 0.0003777553873034362, | |
| "loss": 3.2646, | |
| "step": 63700 | |
| }, | |
| { | |
| "epoch": 18.553679552864462, | |
| "grad_norm": 0.3871338963508606, | |
| "learning_rate": 0.0003775806639487478, | |
| "loss": 3.2486, | |
| "step": 63750 | |
| }, | |
| { | |
| "epoch": 18.56823474615743, | |
| "grad_norm": 0.4119662046432495, | |
| "learning_rate": 0.0003774059405940594, | |
| "loss": 3.2756, | |
| "step": 63800 | |
| }, | |
| { | |
| "epoch": 18.582789939450397, | |
| "grad_norm": 0.3914063274860382, | |
| "learning_rate": 0.000377231217239371, | |
| "loss": 3.2502, | |
| "step": 63850 | |
| }, | |
| { | |
| "epoch": 18.597345132743364, | |
| "grad_norm": 0.3795580565929413, | |
| "learning_rate": 0.0003770564938846825, | |
| "loss": 3.248, | |
| "step": 63900 | |
| }, | |
| { | |
| "epoch": 18.61190032603633, | |
| "grad_norm": 0.37923169136047363, | |
| "learning_rate": 0.00037688177052999416, | |
| "loss": 3.2585, | |
| "step": 63950 | |
| }, | |
| { | |
| "epoch": 18.626455519329298, | |
| "grad_norm": 0.36322852969169617, | |
| "learning_rate": 0.00037670704717530576, | |
| "loss": 3.266, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 18.626455519329298, | |
| "eval_accuracy": 0.37296361907002756, | |
| "eval_loss": 3.5405192375183105, | |
| "eval_runtime": 53.6658, | |
| "eval_samples_per_second": 310.272, | |
| "eval_steps_per_second": 19.398, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 18.641010712622265, | |
| "grad_norm": 0.3916160464286804, | |
| "learning_rate": 0.00037653232382061735, | |
| "loss": 3.2566, | |
| "step": 64050 | |
| }, | |
| { | |
| "epoch": 18.655565905915232, | |
| "grad_norm": 0.4122990667819977, | |
| "learning_rate": 0.0003763576004659289, | |
| "loss": 3.2461, | |
| "step": 64100 | |
| }, | |
| { | |
| "epoch": 18.6701210992082, | |
| "grad_norm": 0.39140254259109497, | |
| "learning_rate": 0.0003761828771112405, | |
| "loss": 3.2709, | |
| "step": 64150 | |
| }, | |
| { | |
| "epoch": 18.684676292501166, | |
| "grad_norm": 0.41236773133277893, | |
| "learning_rate": 0.0003760081537565521, | |
| "loss": 3.273, | |
| "step": 64200 | |
| }, | |
| { | |
| "epoch": 18.69923148579413, | |
| "grad_norm": 0.3984505236148834, | |
| "learning_rate": 0.00037583343040186373, | |
| "loss": 3.2664, | |
| "step": 64250 | |
| }, | |
| { | |
| "epoch": 18.713786679087097, | |
| "grad_norm": 0.3800402581691742, | |
| "learning_rate": 0.00037565870704717527, | |
| "loss": 3.268, | |
| "step": 64300 | |
| }, | |
| { | |
| "epoch": 18.728341872380064, | |
| "grad_norm": 0.4139155447483063, | |
| "learning_rate": 0.00037548398369248687, | |
| "loss": 3.2592, | |
| "step": 64350 | |
| }, | |
| { | |
| "epoch": 18.74289706567303, | |
| "grad_norm": 0.3867560029029846, | |
| "learning_rate": 0.00037530926033779846, | |
| "loss": 3.2509, | |
| "step": 64400 | |
| }, | |
| { | |
| "epoch": 18.757452258965998, | |
| "grad_norm": 0.3921962380409241, | |
| "learning_rate": 0.00037513453698311, | |
| "loss": 3.2826, | |
| "step": 64450 | |
| }, | |
| { | |
| "epoch": 18.772007452258965, | |
| "grad_norm": 0.3699600100517273, | |
| "learning_rate": 0.0003749598136284216, | |
| "loss": 3.2733, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 18.786562645551932, | |
| "grad_norm": 0.40228018164634705, | |
| "learning_rate": 0.00037478509027373324, | |
| "loss": 3.274, | |
| "step": 64550 | |
| }, | |
| { | |
| "epoch": 18.8011178388449, | |
| "grad_norm": 0.43841156363487244, | |
| "learning_rate": 0.00037461036691904484, | |
| "loss": 3.2655, | |
| "step": 64600 | |
| }, | |
| { | |
| "epoch": 18.815673032137866, | |
| "grad_norm": 0.3852190673351288, | |
| "learning_rate": 0.0003744356435643564, | |
| "loss": 3.2665, | |
| "step": 64650 | |
| }, | |
| { | |
| "epoch": 18.830228225430833, | |
| "grad_norm": 0.40769702196121216, | |
| "learning_rate": 0.00037426092020966797, | |
| "loss": 3.2678, | |
| "step": 64700 | |
| }, | |
| { | |
| "epoch": 18.8447834187238, | |
| "grad_norm": 0.4070548117160797, | |
| "learning_rate": 0.00037408619685497957, | |
| "loss": 3.263, | |
| "step": 64750 | |
| }, | |
| { | |
| "epoch": 18.859338612016767, | |
| "grad_norm": 0.4176812767982483, | |
| "learning_rate": 0.0003739114735002912, | |
| "loss": 3.2854, | |
| "step": 64800 | |
| }, | |
| { | |
| "epoch": 18.873893805309734, | |
| "grad_norm": 0.39820629358291626, | |
| "learning_rate": 0.0003737367501456028, | |
| "loss": 3.2676, | |
| "step": 64850 | |
| }, | |
| { | |
| "epoch": 18.8884489986027, | |
| "grad_norm": 0.3981149196624756, | |
| "learning_rate": 0.00037356202679091435, | |
| "loss": 3.2674, | |
| "step": 64900 | |
| }, | |
| { | |
| "epoch": 18.90300419189567, | |
| "grad_norm": 0.38341373205184937, | |
| "learning_rate": 0.00037338730343622594, | |
| "loss": 3.2656, | |
| "step": 64950 | |
| }, | |
| { | |
| "epoch": 18.917559385188635, | |
| "grad_norm": 0.37144750356674194, | |
| "learning_rate": 0.00037321258008153754, | |
| "loss": 3.2648, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 18.917559385188635, | |
| "eval_accuracy": 0.3731450812295848, | |
| "eval_loss": 3.536303758621216, | |
| "eval_runtime": 53.4955, | |
| "eval_samples_per_second": 311.26, | |
| "eval_steps_per_second": 19.46, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 18.932114578481603, | |
| "grad_norm": 0.40450090169906616, | |
| "learning_rate": 0.0003730378567268491, | |
| "loss": 3.2789, | |
| "step": 65050 | |
| }, | |
| { | |
| "epoch": 18.94666977177457, | |
| "grad_norm": 0.35897237062454224, | |
| "learning_rate": 0.0003728631333721607, | |
| "loss": 3.2718, | |
| "step": 65100 | |
| }, | |
| { | |
| "epoch": 18.961224965067537, | |
| "grad_norm": 0.37104153633117676, | |
| "learning_rate": 0.0003726884100174723, | |
| "loss": 3.2723, | |
| "step": 65150 | |
| }, | |
| { | |
| "epoch": 18.975780158360504, | |
| "grad_norm": 0.397222638130188, | |
| "learning_rate": 0.0003725136866627839, | |
| "loss": 3.275, | |
| "step": 65200 | |
| }, | |
| { | |
| "epoch": 18.99033535165347, | |
| "grad_norm": 0.3736797869205475, | |
| "learning_rate": 0.00037233896330809545, | |
| "loss": 3.2684, | |
| "step": 65250 | |
| }, | |
| { | |
| "epoch": 19.00465766185375, | |
| "grad_norm": 0.3938813805580139, | |
| "learning_rate": 0.00037216423995340705, | |
| "loss": 3.2459, | |
| "step": 65300 | |
| }, | |
| { | |
| "epoch": 19.019212855146716, | |
| "grad_norm": 0.40468358993530273, | |
| "learning_rate": 0.0003719895165987187, | |
| "loss": 3.1667, | |
| "step": 65350 | |
| }, | |
| { | |
| "epoch": 19.033768048439683, | |
| "grad_norm": 0.3898302912712097, | |
| "learning_rate": 0.0003718147932440303, | |
| "loss": 3.1746, | |
| "step": 65400 | |
| }, | |
| { | |
| "epoch": 19.04832324173265, | |
| "grad_norm": 0.40629255771636963, | |
| "learning_rate": 0.00037164006988934183, | |
| "loss": 3.1859, | |
| "step": 65450 | |
| }, | |
| { | |
| "epoch": 19.062878435025617, | |
| "grad_norm": 0.39562860131263733, | |
| "learning_rate": 0.0003714653465346534, | |
| "loss": 3.1899, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 19.077433628318584, | |
| "grad_norm": 0.4299829304218292, | |
| "learning_rate": 0.000371290623179965, | |
| "loss": 3.1773, | |
| "step": 65550 | |
| }, | |
| { | |
| "epoch": 19.09198882161155, | |
| "grad_norm": 0.4210468530654907, | |
| "learning_rate": 0.00037111589982527656, | |
| "loss": 3.1931, | |
| "step": 65600 | |
| }, | |
| { | |
| "epoch": 19.106544014904518, | |
| "grad_norm": 0.3752780556678772, | |
| "learning_rate": 0.0003709411764705882, | |
| "loss": 3.1969, | |
| "step": 65650 | |
| }, | |
| { | |
| "epoch": 19.121099208197485, | |
| "grad_norm": 0.35718461871147156, | |
| "learning_rate": 0.0003707664531158998, | |
| "loss": 3.1948, | |
| "step": 65700 | |
| }, | |
| { | |
| "epoch": 19.135654401490452, | |
| "grad_norm": 0.3707563877105713, | |
| "learning_rate": 0.0003705917297612114, | |
| "loss": 3.2045, | |
| "step": 65750 | |
| }, | |
| { | |
| "epoch": 19.15020959478342, | |
| "grad_norm": 0.38740453124046326, | |
| "learning_rate": 0.000370417006406523, | |
| "loss": 3.1995, | |
| "step": 65800 | |
| }, | |
| { | |
| "epoch": 19.164764788076386, | |
| "grad_norm": 0.401472270488739, | |
| "learning_rate": 0.00037024228305183453, | |
| "loss": 3.194, | |
| "step": 65850 | |
| }, | |
| { | |
| "epoch": 19.179319981369353, | |
| "grad_norm": 0.3963239789009094, | |
| "learning_rate": 0.0003700675596971461, | |
| "loss": 3.2014, | |
| "step": 65900 | |
| }, | |
| { | |
| "epoch": 19.19387517466232, | |
| "grad_norm": 0.40201330184936523, | |
| "learning_rate": 0.0003698928363424578, | |
| "loss": 3.1995, | |
| "step": 65950 | |
| }, | |
| { | |
| "epoch": 19.208430367955287, | |
| "grad_norm": 0.3954628109931946, | |
| "learning_rate": 0.00036971811298776937, | |
| "loss": 3.2083, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 19.208430367955287, | |
| "eval_accuracy": 0.3727680536338209, | |
| "eval_loss": 3.550874948501587, | |
| "eval_runtime": 53.6771, | |
| "eval_samples_per_second": 310.207, | |
| "eval_steps_per_second": 19.394, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 19.222985561248255, | |
| "grad_norm": 0.44608214497566223, | |
| "learning_rate": 0.0003695433896330809, | |
| "loss": 3.2026, | |
| "step": 66050 | |
| }, | |
| { | |
| "epoch": 19.23754075454122, | |
| "grad_norm": 0.4086514711380005, | |
| "learning_rate": 0.0003693686662783925, | |
| "loss": 3.1996, | |
| "step": 66100 | |
| }, | |
| { | |
| "epoch": 19.25209594783419, | |
| "grad_norm": 0.40679827332496643, | |
| "learning_rate": 0.0003691939429237041, | |
| "loss": 3.2182, | |
| "step": 66150 | |
| }, | |
| { | |
| "epoch": 19.266651141127156, | |
| "grad_norm": 0.3798060715198517, | |
| "learning_rate": 0.00036901921956901575, | |
| "loss": 3.2168, | |
| "step": 66200 | |
| }, | |
| { | |
| "epoch": 19.281206334420123, | |
| "grad_norm": 0.3875897526741028, | |
| "learning_rate": 0.0003688444962143273, | |
| "loss": 3.2192, | |
| "step": 66250 | |
| }, | |
| { | |
| "epoch": 19.29576152771309, | |
| "grad_norm": 0.40857604146003723, | |
| "learning_rate": 0.0003686697728596389, | |
| "loss": 3.2161, | |
| "step": 66300 | |
| }, | |
| { | |
| "epoch": 19.310316721006053, | |
| "grad_norm": 0.4081888496875763, | |
| "learning_rate": 0.0003684950495049505, | |
| "loss": 3.2199, | |
| "step": 66350 | |
| }, | |
| { | |
| "epoch": 19.32487191429902, | |
| "grad_norm": 0.36998409032821655, | |
| "learning_rate": 0.000368320326150262, | |
| "loss": 3.2259, | |
| "step": 66400 | |
| }, | |
| { | |
| "epoch": 19.339427107591987, | |
| "grad_norm": 0.4138041138648987, | |
| "learning_rate": 0.0003681456027955736, | |
| "loss": 3.2134, | |
| "step": 66450 | |
| }, | |
| { | |
| "epoch": 19.353982300884955, | |
| "grad_norm": 0.3892041742801666, | |
| "learning_rate": 0.00036797087944088526, | |
| "loss": 3.2215, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 19.36853749417792, | |
| "grad_norm": 0.40904441475868225, | |
| "learning_rate": 0.00036779615608619685, | |
| "loss": 3.2294, | |
| "step": 66550 | |
| }, | |
| { | |
| "epoch": 19.38309268747089, | |
| "grad_norm": 0.4268759787082672, | |
| "learning_rate": 0.0003676214327315084, | |
| "loss": 3.2376, | |
| "step": 66600 | |
| }, | |
| { | |
| "epoch": 19.397647880763856, | |
| "grad_norm": 0.39579281210899353, | |
| "learning_rate": 0.00036744670937682, | |
| "loss": 3.2403, | |
| "step": 66650 | |
| }, | |
| { | |
| "epoch": 19.412203074056823, | |
| "grad_norm": 0.401540070772171, | |
| "learning_rate": 0.0003672719860221316, | |
| "loss": 3.2308, | |
| "step": 66700 | |
| }, | |
| { | |
| "epoch": 19.42675826734979, | |
| "grad_norm": 0.36677086353302, | |
| "learning_rate": 0.00036709726266744323, | |
| "loss": 3.2218, | |
| "step": 66750 | |
| }, | |
| { | |
| "epoch": 19.441313460642757, | |
| "grad_norm": 0.3626297414302826, | |
| "learning_rate": 0.00036692253931275477, | |
| "loss": 3.2353, | |
| "step": 66800 | |
| }, | |
| { | |
| "epoch": 19.455868653935724, | |
| "grad_norm": 0.372329980134964, | |
| "learning_rate": 0.00036674781595806636, | |
| "loss": 3.2343, | |
| "step": 66850 | |
| }, | |
| { | |
| "epoch": 19.47042384722869, | |
| "grad_norm": 0.43542206287384033, | |
| "learning_rate": 0.00036657309260337796, | |
| "loss": 3.2433, | |
| "step": 66900 | |
| }, | |
| { | |
| "epoch": 19.484979040521658, | |
| "grad_norm": 0.37357252836227417, | |
| "learning_rate": 0.00036639836924868955, | |
| "loss": 3.2347, | |
| "step": 66950 | |
| }, | |
| { | |
| "epoch": 19.499534233814625, | |
| "grad_norm": 0.4016791582107544, | |
| "learning_rate": 0.0003662236458940011, | |
| "loss": 3.2486, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 19.499534233814625, | |
| "eval_accuracy": 0.373105004418439, | |
| "eval_loss": 3.546595335006714, | |
| "eval_runtime": 53.5919, | |
| "eval_samples_per_second": 310.7, | |
| "eval_steps_per_second": 19.425, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 19.514089427107592, | |
| "grad_norm": 0.3830515444278717, | |
| "learning_rate": 0.00036604892253931274, | |
| "loss": 3.2258, | |
| "step": 67050 | |
| }, | |
| { | |
| "epoch": 19.52864462040056, | |
| "grad_norm": 0.38446927070617676, | |
| "learning_rate": 0.00036587419918462433, | |
| "loss": 3.2452, | |
| "step": 67100 | |
| }, | |
| { | |
| "epoch": 19.543199813693526, | |
| "grad_norm": 0.43966013193130493, | |
| "learning_rate": 0.00036569947582993593, | |
| "loss": 3.2502, | |
| "step": 67150 | |
| }, | |
| { | |
| "epoch": 19.557755006986493, | |
| "grad_norm": 0.3503745198249817, | |
| "learning_rate": 0.00036552475247524747, | |
| "loss": 3.2377, | |
| "step": 67200 | |
| }, | |
| { | |
| "epoch": 19.57231020027946, | |
| "grad_norm": 0.39735761284828186, | |
| "learning_rate": 0.00036535002912055906, | |
| "loss": 3.2484, | |
| "step": 67250 | |
| }, | |
| { | |
| "epoch": 19.586865393572428, | |
| "grad_norm": 0.39670273661613464, | |
| "learning_rate": 0.00036517530576587066, | |
| "loss": 3.2432, | |
| "step": 67300 | |
| }, | |
| { | |
| "epoch": 19.601420586865395, | |
| "grad_norm": 0.38470038771629333, | |
| "learning_rate": 0.0003650005824111823, | |
| "loss": 3.2553, | |
| "step": 67350 | |
| }, | |
| { | |
| "epoch": 19.61597578015836, | |
| "grad_norm": 0.41007962822914124, | |
| "learning_rate": 0.00036482585905649385, | |
| "loss": 3.2521, | |
| "step": 67400 | |
| }, | |
| { | |
| "epoch": 19.63053097345133, | |
| "grad_norm": 0.4008373022079468, | |
| "learning_rate": 0.00036465113570180544, | |
| "loss": 3.258, | |
| "step": 67450 | |
| }, | |
| { | |
| "epoch": 19.645086166744296, | |
| "grad_norm": 0.3944298028945923, | |
| "learning_rate": 0.00036447641234711703, | |
| "loss": 3.2346, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 19.659641360037263, | |
| "grad_norm": 0.37867727875709534, | |
| "learning_rate": 0.0003643016889924286, | |
| "loss": 3.2514, | |
| "step": 67550 | |
| }, | |
| { | |
| "epoch": 19.67419655333023, | |
| "grad_norm": 0.4205871522426605, | |
| "learning_rate": 0.0003641269656377402, | |
| "loss": 3.2563, | |
| "step": 67600 | |
| }, | |
| { | |
| "epoch": 19.688751746623197, | |
| "grad_norm": 0.37643682956695557, | |
| "learning_rate": 0.0003639522422830518, | |
| "loss": 3.2482, | |
| "step": 67650 | |
| }, | |
| { | |
| "epoch": 19.70330693991616, | |
| "grad_norm": 0.4236048758029938, | |
| "learning_rate": 0.0003637775189283634, | |
| "loss": 3.2534, | |
| "step": 67700 | |
| }, | |
| { | |
| "epoch": 19.717862133209128, | |
| "grad_norm": 0.4319748282432556, | |
| "learning_rate": 0.00036360279557367495, | |
| "loss": 3.2533, | |
| "step": 67750 | |
| }, | |
| { | |
| "epoch": 19.732417326502095, | |
| "grad_norm": 0.3937004804611206, | |
| "learning_rate": 0.00036342807221898655, | |
| "loss": 3.2529, | |
| "step": 67800 | |
| }, | |
| { | |
| "epoch": 19.74697251979506, | |
| "grad_norm": 0.4067949950695038, | |
| "learning_rate": 0.00036325334886429814, | |
| "loss": 3.2502, | |
| "step": 67850 | |
| }, | |
| { | |
| "epoch": 19.76152771308803, | |
| "grad_norm": 0.38245004415512085, | |
| "learning_rate": 0.0003630786255096098, | |
| "loss": 3.2491, | |
| "step": 67900 | |
| }, | |
| { | |
| "epoch": 19.776082906380996, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00036290390215492133, | |
| "loss": 3.2663, | |
| "step": 67950 | |
| }, | |
| { | |
| "epoch": 19.790638099673963, | |
| "grad_norm": 0.3720107674598694, | |
| "learning_rate": 0.0003627291788002329, | |
| "loss": 3.2671, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 19.790638099673963, | |
| "eval_accuracy": 0.37347721339468104, | |
| "eval_loss": 3.536025047302246, | |
| "eval_runtime": 53.5094, | |
| "eval_samples_per_second": 311.179, | |
| "eval_steps_per_second": 19.455, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 19.80519329296693, | |
| "grad_norm": 0.3850249648094177, | |
| "learning_rate": 0.0003625544554455445, | |
| "loss": 3.2593, | |
| "step": 68050 | |
| }, | |
| { | |
| "epoch": 19.819748486259897, | |
| "grad_norm": 0.38478919863700867, | |
| "learning_rate": 0.0003623797320908561, | |
| "loss": 3.248, | |
| "step": 68100 | |
| }, | |
| { | |
| "epoch": 19.834303679552864, | |
| "grad_norm": 0.3765984773635864, | |
| "learning_rate": 0.00036220500873616776, | |
| "loss": 3.2578, | |
| "step": 68150 | |
| }, | |
| { | |
| "epoch": 19.84885887284583, | |
| "grad_norm": 0.3772033452987671, | |
| "learning_rate": 0.0003620302853814793, | |
| "loss": 3.2596, | |
| "step": 68200 | |
| }, | |
| { | |
| "epoch": 19.863414066138798, | |
| "grad_norm": 0.4011659622192383, | |
| "learning_rate": 0.0003618555620267909, | |
| "loss": 3.2487, | |
| "step": 68250 | |
| }, | |
| { | |
| "epoch": 19.877969259431765, | |
| "grad_norm": 0.39415985345840454, | |
| "learning_rate": 0.0003616808386721025, | |
| "loss": 3.2488, | |
| "step": 68300 | |
| }, | |
| { | |
| "epoch": 19.892524452724732, | |
| "grad_norm": 0.3650701344013214, | |
| "learning_rate": 0.00036150611531741403, | |
| "loss": 3.2557, | |
| "step": 68350 | |
| }, | |
| { | |
| "epoch": 19.9070796460177, | |
| "grad_norm": 0.37706032395362854, | |
| "learning_rate": 0.0003613313919627256, | |
| "loss": 3.2683, | |
| "step": 68400 | |
| }, | |
| { | |
| "epoch": 19.921634839310666, | |
| "grad_norm": 0.3774428367614746, | |
| "learning_rate": 0.00036115666860803727, | |
| "loss": 3.2672, | |
| "step": 68450 | |
| }, | |
| { | |
| "epoch": 19.936190032603633, | |
| "grad_norm": 0.3930302560329437, | |
| "learning_rate": 0.00036098194525334887, | |
| "loss": 3.2646, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 19.9507452258966, | |
| "grad_norm": 0.3946230709552765, | |
| "learning_rate": 0.0003608072218986604, | |
| "loss": 3.2631, | |
| "step": 68550 | |
| }, | |
| { | |
| "epoch": 19.965300419189568, | |
| "grad_norm": 0.3675050735473633, | |
| "learning_rate": 0.000360632498543972, | |
| "loss": 3.2636, | |
| "step": 68600 | |
| }, | |
| { | |
| "epoch": 19.979855612482535, | |
| "grad_norm": 0.3700838088989258, | |
| "learning_rate": 0.0003604577751892836, | |
| "loss": 3.2726, | |
| "step": 68650 | |
| }, | |
| { | |
| "epoch": 19.9944108057755, | |
| "grad_norm": 0.37471088767051697, | |
| "learning_rate": 0.00036028305183459513, | |
| "loss": 3.2695, | |
| "step": 68700 | |
| }, | |
| { | |
| "epoch": 20.00873311597578, | |
| "grad_norm": 0.4039229452610016, | |
| "learning_rate": 0.0003601083284799068, | |
| "loss": 3.2089, | |
| "step": 68750 | |
| }, | |
| { | |
| "epoch": 20.023288309268747, | |
| "grad_norm": 0.3923375606536865, | |
| "learning_rate": 0.0003599336051252184, | |
| "loss": 3.1607, | |
| "step": 68800 | |
| }, | |
| { | |
| "epoch": 20.037843502561714, | |
| "grad_norm": 0.39867857098579407, | |
| "learning_rate": 0.00035975888177052997, | |
| "loss": 3.1631, | |
| "step": 68850 | |
| }, | |
| { | |
| "epoch": 20.05239869585468, | |
| "grad_norm": 0.37938812375068665, | |
| "learning_rate": 0.0003595841584158415, | |
| "loss": 3.1611, | |
| "step": 68900 | |
| }, | |
| { | |
| "epoch": 20.066953889147648, | |
| "grad_norm": 0.3965538442134857, | |
| "learning_rate": 0.0003594094350611531, | |
| "loss": 3.171, | |
| "step": 68950 | |
| }, | |
| { | |
| "epoch": 20.081509082440615, | |
| "grad_norm": 0.4133109450340271, | |
| "learning_rate": 0.00035923471170646475, | |
| "loss": 3.1702, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 20.081509082440615, | |
| "eval_accuracy": 0.37253911044287696, | |
| "eval_loss": 3.5551199913024902, | |
| "eval_runtime": 53.5527, | |
| "eval_samples_per_second": 310.927, | |
| "eval_steps_per_second": 19.439, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 20.096064275733582, | |
| "grad_norm": 0.39560985565185547, | |
| "learning_rate": 0.00035905998835177635, | |
| "loss": 3.1709, | |
| "step": 69050 | |
| }, | |
| { | |
| "epoch": 20.11061946902655, | |
| "grad_norm": 0.3734511435031891, | |
| "learning_rate": 0.00035888526499708794, | |
| "loss": 3.1812, | |
| "step": 69100 | |
| }, | |
| { | |
| "epoch": 20.125174662319516, | |
| "grad_norm": 0.4139745533466339, | |
| "learning_rate": 0.0003587105416423995, | |
| "loss": 3.1906, | |
| "step": 69150 | |
| }, | |
| { | |
| "epoch": 20.139729855612483, | |
| "grad_norm": 0.3967720568180084, | |
| "learning_rate": 0.0003585358182877111, | |
| "loss": 3.1711, | |
| "step": 69200 | |
| }, | |
| { | |
| "epoch": 20.15428504890545, | |
| "grad_norm": 0.4036801755428314, | |
| "learning_rate": 0.00035836109493302267, | |
| "loss": 3.1834, | |
| "step": 69250 | |
| }, | |
| { | |
| "epoch": 20.168840242198417, | |
| "grad_norm": 0.36493250727653503, | |
| "learning_rate": 0.0003581863715783343, | |
| "loss": 3.1897, | |
| "step": 69300 | |
| }, | |
| { | |
| "epoch": 20.183395435491384, | |
| "grad_norm": 0.43222376704216003, | |
| "learning_rate": 0.00035801164822364586, | |
| "loss": 3.1975, | |
| "step": 69350 | |
| }, | |
| { | |
| "epoch": 20.19795062878435, | |
| "grad_norm": 0.3593828082084656, | |
| "learning_rate": 0.00035783692486895745, | |
| "loss": 3.195, | |
| "step": 69400 | |
| }, | |
| { | |
| "epoch": 20.21250582207732, | |
| "grad_norm": 0.44340449571609497, | |
| "learning_rate": 0.00035766220151426905, | |
| "loss": 3.2098, | |
| "step": 69450 | |
| }, | |
| { | |
| "epoch": 20.227061015370285, | |
| "grad_norm": 0.391792356967926, | |
| "learning_rate": 0.0003574874781595806, | |
| "loss": 3.1968, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 20.241616208663253, | |
| "grad_norm": 0.3826884627342224, | |
| "learning_rate": 0.00035731275480489224, | |
| "loss": 3.2141, | |
| "step": 69550 | |
| }, | |
| { | |
| "epoch": 20.25617140195622, | |
| "grad_norm": 0.41876623034477234, | |
| "learning_rate": 0.00035713803145020383, | |
| "loss": 3.2041, | |
| "step": 69600 | |
| }, | |
| { | |
| "epoch": 20.270726595249187, | |
| "grad_norm": 0.39623573422431946, | |
| "learning_rate": 0.0003569633080955154, | |
| "loss": 3.2148, | |
| "step": 69650 | |
| }, | |
| { | |
| "epoch": 20.28528178854215, | |
| "grad_norm": 0.40162044763565063, | |
| "learning_rate": 0.00035678858474082697, | |
| "loss": 3.2178, | |
| "step": 69700 | |
| }, | |
| { | |
| "epoch": 20.299836981835117, | |
| "grad_norm": 0.39154306054115295, | |
| "learning_rate": 0.00035661386138613856, | |
| "loss": 3.2079, | |
| "step": 69750 | |
| }, | |
| { | |
| "epoch": 20.314392175128084, | |
| "grad_norm": 0.4348454475402832, | |
| "learning_rate": 0.00035643913803145015, | |
| "loss": 3.2099, | |
| "step": 69800 | |
| }, | |
| { | |
| "epoch": 20.32894736842105, | |
| "grad_norm": 0.381529301404953, | |
| "learning_rate": 0.0003562644146767618, | |
| "loss": 3.2093, | |
| "step": 69850 | |
| }, | |
| { | |
| "epoch": 20.34350256171402, | |
| "grad_norm": 0.4265825152397156, | |
| "learning_rate": 0.00035608969132207334, | |
| "loss": 3.2081, | |
| "step": 69900 | |
| }, | |
| { | |
| "epoch": 20.358057755006985, | |
| "grad_norm": 0.388090044260025, | |
| "learning_rate": 0.00035591496796738494, | |
| "loss": 3.21, | |
| "step": 69950 | |
| }, | |
| { | |
| "epoch": 20.372612948299953, | |
| "grad_norm": 0.4144580662250519, | |
| "learning_rate": 0.00035574024461269653, | |
| "loss": 3.2111, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 20.372612948299953, | |
| "eval_accuracy": 0.3731256892241917, | |
| "eval_loss": 3.54860782623291, | |
| "eval_runtime": 53.6659, | |
| "eval_samples_per_second": 310.271, | |
| "eval_steps_per_second": 19.398, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 20.38716814159292, | |
| "grad_norm": 0.38947436213493347, | |
| "learning_rate": 0.0003555655212580081, | |
| "loss": 3.2292, | |
| "step": 70050 | |
| }, | |
| { | |
| "epoch": 20.401723334885887, | |
| "grad_norm": 0.37594932317733765, | |
| "learning_rate": 0.00035539079790331967, | |
| "loss": 3.2239, | |
| "step": 70100 | |
| }, | |
| { | |
| "epoch": 20.416278528178854, | |
| "grad_norm": 0.3541885316371918, | |
| "learning_rate": 0.0003552160745486313, | |
| "loss": 3.2196, | |
| "step": 70150 | |
| }, | |
| { | |
| "epoch": 20.43083372147182, | |
| "grad_norm": 0.385652095079422, | |
| "learning_rate": 0.0003550413511939429, | |
| "loss": 3.2294, | |
| "step": 70200 | |
| }, | |
| { | |
| "epoch": 20.445388914764788, | |
| "grad_norm": 0.42252057790756226, | |
| "learning_rate": 0.0003548666278392545, | |
| "loss": 3.2193, | |
| "step": 70250 | |
| }, | |
| { | |
| "epoch": 20.459944108057755, | |
| "grad_norm": 0.44054681062698364, | |
| "learning_rate": 0.00035469190448456604, | |
| "loss": 3.2212, | |
| "step": 70300 | |
| }, | |
| { | |
| "epoch": 20.474499301350722, | |
| "grad_norm": 0.3901931345462799, | |
| "learning_rate": 0.00035451718112987764, | |
| "loss": 3.234, | |
| "step": 70350 | |
| }, | |
| { | |
| "epoch": 20.48905449464369, | |
| "grad_norm": 0.38539695739746094, | |
| "learning_rate": 0.0003543424577751893, | |
| "loss": 3.2316, | |
| "step": 70400 | |
| }, | |
| { | |
| "epoch": 20.503609687936656, | |
| "grad_norm": 0.38549506664276123, | |
| "learning_rate": 0.0003541677344205009, | |
| "loss": 3.2121, | |
| "step": 70450 | |
| }, | |
| { | |
| "epoch": 20.518164881229623, | |
| "grad_norm": 0.3903706967830658, | |
| "learning_rate": 0.0003539930110658124, | |
| "loss": 3.2276, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 20.53272007452259, | |
| "grad_norm": 0.4072808027267456, | |
| "learning_rate": 0.000353818287711124, | |
| "loss": 3.2374, | |
| "step": 70550 | |
| }, | |
| { | |
| "epoch": 20.547275267815557, | |
| "grad_norm": 0.406862735748291, | |
| "learning_rate": 0.0003536435643564356, | |
| "loss": 3.2306, | |
| "step": 70600 | |
| }, | |
| { | |
| "epoch": 20.561830461108524, | |
| "grad_norm": 0.3827691078186035, | |
| "learning_rate": 0.00035346884100174715, | |
| "loss": 3.2265, | |
| "step": 70650 | |
| }, | |
| { | |
| "epoch": 20.57638565440149, | |
| "grad_norm": 0.37625613808631897, | |
| "learning_rate": 0.0003532941176470588, | |
| "loss": 3.2277, | |
| "step": 70700 | |
| }, | |
| { | |
| "epoch": 20.59094084769446, | |
| "grad_norm": 0.382710337638855, | |
| "learning_rate": 0.0003531193942923704, | |
| "loss": 3.2299, | |
| "step": 70750 | |
| }, | |
| { | |
| "epoch": 20.605496040987425, | |
| "grad_norm": 0.39314213395118713, | |
| "learning_rate": 0.000352944670937682, | |
| "loss": 3.2397, | |
| "step": 70800 | |
| }, | |
| { | |
| "epoch": 20.620051234280393, | |
| "grad_norm": 0.42123886942863464, | |
| "learning_rate": 0.0003527699475829935, | |
| "loss": 3.2445, | |
| "step": 70850 | |
| }, | |
| { | |
| "epoch": 20.63460642757336, | |
| "grad_norm": 0.40710893273353577, | |
| "learning_rate": 0.0003525952242283051, | |
| "loss": 3.2345, | |
| "step": 70900 | |
| }, | |
| { | |
| "epoch": 20.649161620866327, | |
| "grad_norm": 0.40057483315467834, | |
| "learning_rate": 0.00035242050087361677, | |
| "loss": 3.2215, | |
| "step": 70950 | |
| }, | |
| { | |
| "epoch": 20.663716814159294, | |
| "grad_norm": 0.3915923237800598, | |
| "learning_rate": 0.00035224577751892836, | |
| "loss": 3.2429, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 20.663716814159294, | |
| "eval_accuracy": 0.37321794815894066, | |
| "eval_loss": 3.542126417160034, | |
| "eval_runtime": 53.778, | |
| "eval_samples_per_second": 309.625, | |
| "eval_steps_per_second": 19.357, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 20.678272007452257, | |
| "grad_norm": 0.389903724193573, | |
| "learning_rate": 0.0003520710541642399, | |
| "loss": 3.2368, | |
| "step": 71050 | |
| }, | |
| { | |
| "epoch": 20.692827200745224, | |
| "grad_norm": 0.39273956418037415, | |
| "learning_rate": 0.0003518963308095515, | |
| "loss": 3.2457, | |
| "step": 71100 | |
| }, | |
| { | |
| "epoch": 20.70738239403819, | |
| "grad_norm": 0.4000990390777588, | |
| "learning_rate": 0.0003517216074548631, | |
| "loss": 3.2411, | |
| "step": 71150 | |
| }, | |
| { | |
| "epoch": 20.72193758733116, | |
| "grad_norm": 0.39781516790390015, | |
| "learning_rate": 0.0003515468841001747, | |
| "loss": 3.2445, | |
| "step": 71200 | |
| }, | |
| { | |
| "epoch": 20.736492780624125, | |
| "grad_norm": 0.4258250594139099, | |
| "learning_rate": 0.00035137216074548634, | |
| "loss": 3.2387, | |
| "step": 71250 | |
| }, | |
| { | |
| "epoch": 20.751047973917093, | |
| "grad_norm": 0.389139324426651, | |
| "learning_rate": 0.0003511974373907979, | |
| "loss": 3.251, | |
| "step": 71300 | |
| }, | |
| { | |
| "epoch": 20.76560316721006, | |
| "grad_norm": 0.37145423889160156, | |
| "learning_rate": 0.00035102271403610947, | |
| "loss": 3.2524, | |
| "step": 71350 | |
| }, | |
| { | |
| "epoch": 20.780158360503027, | |
| "grad_norm": 0.37975454330444336, | |
| "learning_rate": 0.00035084799068142106, | |
| "loss": 3.2353, | |
| "step": 71400 | |
| }, | |
| { | |
| "epoch": 20.794713553795994, | |
| "grad_norm": 0.40606576204299927, | |
| "learning_rate": 0.0003506732673267326, | |
| "loss": 3.2543, | |
| "step": 71450 | |
| }, | |
| { | |
| "epoch": 20.80926874708896, | |
| "grad_norm": 0.418183296918869, | |
| "learning_rate": 0.00035049854397204425, | |
| "loss": 3.2513, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 20.823823940381928, | |
| "grad_norm": 0.37952330708503723, | |
| "learning_rate": 0.00035032382061735585, | |
| "loss": 3.2493, | |
| "step": 71550 | |
| }, | |
| { | |
| "epoch": 20.838379133674895, | |
| "grad_norm": 0.4166284501552582, | |
| "learning_rate": 0.00035014909726266744, | |
| "loss": 3.2427, | |
| "step": 71600 | |
| }, | |
| { | |
| "epoch": 20.852934326967862, | |
| "grad_norm": 0.37393802404403687, | |
| "learning_rate": 0.000349974373907979, | |
| "loss": 3.2488, | |
| "step": 71650 | |
| }, | |
| { | |
| "epoch": 20.86748952026083, | |
| "grad_norm": 0.3974415957927704, | |
| "learning_rate": 0.0003497996505532906, | |
| "loss": 3.2436, | |
| "step": 71700 | |
| }, | |
| { | |
| "epoch": 20.882044713553796, | |
| "grad_norm": 0.384443074464798, | |
| "learning_rate": 0.00034962492719860217, | |
| "loss": 3.2546, | |
| "step": 71750 | |
| }, | |
| { | |
| "epoch": 20.896599906846763, | |
| "grad_norm": 0.39211505651474, | |
| "learning_rate": 0.0003494502038439138, | |
| "loss": 3.2433, | |
| "step": 71800 | |
| }, | |
| { | |
| "epoch": 20.91115510013973, | |
| "grad_norm": 0.4075499176979065, | |
| "learning_rate": 0.00034927548048922536, | |
| "loss": 3.2551, | |
| "step": 71850 | |
| }, | |
| { | |
| "epoch": 20.925710293432697, | |
| "grad_norm": 0.3966205418109894, | |
| "learning_rate": 0.00034910075713453695, | |
| "loss": 3.2598, | |
| "step": 71900 | |
| }, | |
| { | |
| "epoch": 20.940265486725664, | |
| "grad_norm": 0.3855561316013336, | |
| "learning_rate": 0.00034892603377984855, | |
| "loss": 3.2603, | |
| "step": 71950 | |
| }, | |
| { | |
| "epoch": 20.95482068001863, | |
| "grad_norm": 0.3942447900772095, | |
| "learning_rate": 0.0003487513104251601, | |
| "loss": 3.247, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 20.95482068001863, | |
| "eval_accuracy": 0.3734833248145625, | |
| "eval_loss": 3.5370914936065674, | |
| "eval_runtime": 53.6051, | |
| "eval_samples_per_second": 310.623, | |
| "eval_steps_per_second": 19.42, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 20.9693758733116, | |
| "grad_norm": 0.3857755959033966, | |
| "learning_rate": 0.0003485765870704717, | |
| "loss": 3.2535, | |
| "step": 72050 | |
| }, | |
| { | |
| "epoch": 20.983931066604566, | |
| "grad_norm": 0.41546157002449036, | |
| "learning_rate": 0.00034840186371578333, | |
| "loss": 3.2639, | |
| "step": 72100 | |
| }, | |
| { | |
| "epoch": 20.998486259897533, | |
| "grad_norm": 0.4054526388645172, | |
| "learning_rate": 0.0003482271403610949, | |
| "loss": 3.2596, | |
| "step": 72150 | |
| }, | |
| { | |
| "epoch": 21.01280857009781, | |
| "grad_norm": 0.39788350462913513, | |
| "learning_rate": 0.0003480524170064065, | |
| "loss": 3.1636, | |
| "step": 72200 | |
| }, | |
| { | |
| "epoch": 21.027363763390778, | |
| "grad_norm": 0.4038892388343811, | |
| "learning_rate": 0.00034787769365171806, | |
| "loss": 3.15, | |
| "step": 72250 | |
| }, | |
| { | |
| "epoch": 21.041918956683745, | |
| "grad_norm": 0.37624332308769226, | |
| "learning_rate": 0.00034770297029702965, | |
| "loss": 3.1489, | |
| "step": 72300 | |
| }, | |
| { | |
| "epoch": 21.05647414997671, | |
| "grad_norm": 0.41994425654411316, | |
| "learning_rate": 0.0003475282469423413, | |
| "loss": 3.1566, | |
| "step": 72350 | |
| }, | |
| { | |
| "epoch": 21.07102934326968, | |
| "grad_norm": 0.3953875005245209, | |
| "learning_rate": 0.0003473535235876529, | |
| "loss": 3.1688, | |
| "step": 72400 | |
| }, | |
| { | |
| "epoch": 21.085584536562646, | |
| "grad_norm": 0.39127373695373535, | |
| "learning_rate": 0.00034717880023296444, | |
| "loss": 3.1766, | |
| "step": 72450 | |
| }, | |
| { | |
| "epoch": 21.100139729855613, | |
| "grad_norm": 0.44027698040008545, | |
| "learning_rate": 0.00034700407687827603, | |
| "loss": 3.177, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 21.11469492314858, | |
| "grad_norm": 0.3971305191516876, | |
| "learning_rate": 0.0003468293535235876, | |
| "loss": 3.175, | |
| "step": 72550 | |
| }, | |
| { | |
| "epoch": 21.129250116441547, | |
| "grad_norm": 0.4126444458961487, | |
| "learning_rate": 0.00034665463016889916, | |
| "loss": 3.169, | |
| "step": 72600 | |
| }, | |
| { | |
| "epoch": 21.143805309734514, | |
| "grad_norm": 0.40494275093078613, | |
| "learning_rate": 0.0003464799068142108, | |
| "loss": 3.1733, | |
| "step": 72650 | |
| }, | |
| { | |
| "epoch": 21.15836050302748, | |
| "grad_norm": 0.38026145100593567, | |
| "learning_rate": 0.0003463051834595224, | |
| "loss": 3.1843, | |
| "step": 72700 | |
| }, | |
| { | |
| "epoch": 21.172915696320448, | |
| "grad_norm": 0.3856162428855896, | |
| "learning_rate": 0.000346130460104834, | |
| "loss": 3.1872, | |
| "step": 72750 | |
| }, | |
| { | |
| "epoch": 21.187470889613415, | |
| "grad_norm": 0.41442832350730896, | |
| "learning_rate": 0.00034595573675014554, | |
| "loss": 3.1889, | |
| "step": 72800 | |
| }, | |
| { | |
| "epoch": 21.202026082906382, | |
| "grad_norm": 0.39891165494918823, | |
| "learning_rate": 0.00034578101339545714, | |
| "loss": 3.1837, | |
| "step": 72850 | |
| }, | |
| { | |
| "epoch": 21.21658127619935, | |
| "grad_norm": 0.3947881758213043, | |
| "learning_rate": 0.0003456062900407688, | |
| "loss": 3.1836, | |
| "step": 72900 | |
| }, | |
| { | |
| "epoch": 21.231136469492316, | |
| "grad_norm": 0.5147214531898499, | |
| "learning_rate": 0.0003454315666860804, | |
| "loss": 3.1918, | |
| "step": 72950 | |
| }, | |
| { | |
| "epoch": 21.245691662785283, | |
| "grad_norm": 0.4068438708782196, | |
| "learning_rate": 0.0003452568433313919, | |
| "loss": 3.2008, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 21.245691662785283, | |
| "eval_accuracy": 0.3730759751740021, | |
| "eval_loss": 3.5525319576263428, | |
| "eval_runtime": 53.523, | |
| "eval_samples_per_second": 311.1, | |
| "eval_steps_per_second": 19.45, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 21.260246856078247, | |
| "grad_norm": 0.4086904525756836, | |
| "learning_rate": 0.0003450821199767035, | |
| "loss": 3.2071, | |
| "step": 73050 | |
| }, | |
| { | |
| "epoch": 21.274802049371214, | |
| "grad_norm": 0.42851176857948303, | |
| "learning_rate": 0.0003449073966220151, | |
| "loss": 3.1962, | |
| "step": 73100 | |
| }, | |
| { | |
| "epoch": 21.28935724266418, | |
| "grad_norm": 0.3665110170841217, | |
| "learning_rate": 0.0003447326732673267, | |
| "loss": 3.1918, | |
| "step": 73150 | |
| }, | |
| { | |
| "epoch": 21.303912435957148, | |
| "grad_norm": 0.4234129786491394, | |
| "learning_rate": 0.0003445579499126383, | |
| "loss": 3.1928, | |
| "step": 73200 | |
| }, | |
| { | |
| "epoch": 21.318467629250115, | |
| "grad_norm": 0.3884499967098236, | |
| "learning_rate": 0.0003443832265579499, | |
| "loss": 3.2012, | |
| "step": 73250 | |
| }, | |
| { | |
| "epoch": 21.333022822543082, | |
| "grad_norm": 0.4245227873325348, | |
| "learning_rate": 0.0003442085032032615, | |
| "loss": 3.2065, | |
| "step": 73300 | |
| }, | |
| { | |
| "epoch": 21.34757801583605, | |
| "grad_norm": 0.41382065415382385, | |
| "learning_rate": 0.0003440337798485731, | |
| "loss": 3.1936, | |
| "step": 73350 | |
| }, | |
| { | |
| "epoch": 21.362133209129016, | |
| "grad_norm": 0.3936980962753296, | |
| "learning_rate": 0.0003438590564938846, | |
| "loss": 3.2074, | |
| "step": 73400 | |
| }, | |
| { | |
| "epoch": 21.376688402421983, | |
| "grad_norm": 0.3830319046974182, | |
| "learning_rate": 0.0003436843331391962, | |
| "loss": 3.1991, | |
| "step": 73450 | |
| }, | |
| { | |
| "epoch": 21.39124359571495, | |
| "grad_norm": 0.3864900767803192, | |
| "learning_rate": 0.00034350960978450786, | |
| "loss": 3.2109, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 21.405798789007918, | |
| "grad_norm": 0.42121434211730957, | |
| "learning_rate": 0.00034333488642981946, | |
| "loss": 3.1999, | |
| "step": 73550 | |
| }, | |
| { | |
| "epoch": 21.420353982300885, | |
| "grad_norm": 0.41293206810951233, | |
| "learning_rate": 0.000343160163075131, | |
| "loss": 3.2064, | |
| "step": 73600 | |
| }, | |
| { | |
| "epoch": 21.43490917559385, | |
| "grad_norm": 0.3990970551967621, | |
| "learning_rate": 0.0003429854397204426, | |
| "loss": 3.2207, | |
| "step": 73650 | |
| }, | |
| { | |
| "epoch": 21.44946436888682, | |
| "grad_norm": 0.4230194389820099, | |
| "learning_rate": 0.0003428107163657542, | |
| "loss": 3.2082, | |
| "step": 73700 | |
| }, | |
| { | |
| "epoch": 21.464019562179786, | |
| "grad_norm": 0.4012469947338104, | |
| "learning_rate": 0.00034263599301106583, | |
| "loss": 3.2118, | |
| "step": 73750 | |
| }, | |
| { | |
| "epoch": 21.478574755472753, | |
| "grad_norm": 0.3971391022205353, | |
| "learning_rate": 0.0003424612696563774, | |
| "loss": 3.2164, | |
| "step": 73800 | |
| }, | |
| { | |
| "epoch": 21.49312994876572, | |
| "grad_norm": 0.40549421310424805, | |
| "learning_rate": 0.00034228654630168897, | |
| "loss": 3.215, | |
| "step": 73850 | |
| }, | |
| { | |
| "epoch": 21.507685142058687, | |
| "grad_norm": 0.3863505423069, | |
| "learning_rate": 0.00034211182294700056, | |
| "loss": 3.2143, | |
| "step": 73900 | |
| }, | |
| { | |
| "epoch": 21.522240335351654, | |
| "grad_norm": 0.3804347515106201, | |
| "learning_rate": 0.0003419370995923121, | |
| "loss": 3.2107, | |
| "step": 73950 | |
| }, | |
| { | |
| "epoch": 21.53679552864462, | |
| "grad_norm": 0.3824029266834259, | |
| "learning_rate": 0.0003417623762376237, | |
| "loss": 3.2202, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 21.53679552864462, | |
| "eval_accuracy": 0.3733442900122593, | |
| "eval_loss": 3.544466018676758, | |
| "eval_runtime": 53.7643, | |
| "eval_samples_per_second": 309.704, | |
| "eval_steps_per_second": 19.362, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 21.551350721937588, | |
| "grad_norm": 0.3935275375843048, | |
| "learning_rate": 0.00034158765288293534, | |
| "loss": 3.2331, | |
| "step": 74050 | |
| }, | |
| { | |
| "epoch": 21.565905915230555, | |
| "grad_norm": 0.38986170291900635, | |
| "learning_rate": 0.00034141292952824694, | |
| "loss": 3.2056, | |
| "step": 74100 | |
| }, | |
| { | |
| "epoch": 21.580461108523522, | |
| "grad_norm": 0.4273694157600403, | |
| "learning_rate": 0.0003412382061735585, | |
| "loss": 3.2215, | |
| "step": 74150 | |
| }, | |
| { | |
| "epoch": 21.59501630181649, | |
| "grad_norm": 0.37656649947166443, | |
| "learning_rate": 0.0003410634828188701, | |
| "loss": 3.227, | |
| "step": 74200 | |
| }, | |
| { | |
| "epoch": 21.609571495109456, | |
| "grad_norm": 0.3970280587673187, | |
| "learning_rate": 0.00034088875946418167, | |
| "loss": 3.2319, | |
| "step": 74250 | |
| }, | |
| { | |
| "epoch": 21.624126688402423, | |
| "grad_norm": 0.3648797273635864, | |
| "learning_rate": 0.0003407140361094933, | |
| "loss": 3.2246, | |
| "step": 74300 | |
| }, | |
| { | |
| "epoch": 21.63868188169539, | |
| "grad_norm": 0.40369299054145813, | |
| "learning_rate": 0.00034053931275480486, | |
| "loss": 3.2334, | |
| "step": 74350 | |
| }, | |
| { | |
| "epoch": 21.653237074988354, | |
| "grad_norm": 0.4132925570011139, | |
| "learning_rate": 0.00034036458940011645, | |
| "loss": 3.2381, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 21.66779226828132, | |
| "grad_norm": 0.3882160782814026, | |
| "learning_rate": 0.00034018986604542804, | |
| "loss": 3.2351, | |
| "step": 74450 | |
| }, | |
| { | |
| "epoch": 21.682347461574288, | |
| "grad_norm": 0.3801272213459015, | |
| "learning_rate": 0.00034001514269073964, | |
| "loss": 3.2267, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 21.696902654867255, | |
| "grad_norm": 0.3924247622489929, | |
| "learning_rate": 0.0003398404193360512, | |
| "loss": 3.238, | |
| "step": 74550 | |
| }, | |
| { | |
| "epoch": 21.711457848160222, | |
| "grad_norm": 0.39399275183677673, | |
| "learning_rate": 0.00033966569598136283, | |
| "loss": 3.2356, | |
| "step": 74600 | |
| }, | |
| { | |
| "epoch": 21.72601304145319, | |
| "grad_norm": 0.4084586501121521, | |
| "learning_rate": 0.0003394909726266744, | |
| "loss": 3.2443, | |
| "step": 74650 | |
| }, | |
| { | |
| "epoch": 21.740568234746156, | |
| "grad_norm": 0.4100543260574341, | |
| "learning_rate": 0.000339316249271986, | |
| "loss": 3.2322, | |
| "step": 74700 | |
| }, | |
| { | |
| "epoch": 21.755123428039123, | |
| "grad_norm": 0.3836959898471832, | |
| "learning_rate": 0.00033914152591729756, | |
| "loss": 3.2282, | |
| "step": 74750 | |
| }, | |
| { | |
| "epoch": 21.76967862133209, | |
| "grad_norm": 0.3974890410900116, | |
| "learning_rate": 0.00033896680256260915, | |
| "loss": 3.246, | |
| "step": 74800 | |
| }, | |
| { | |
| "epoch": 21.784233814625058, | |
| "grad_norm": 0.3729366064071655, | |
| "learning_rate": 0.00033879207920792074, | |
| "loss": 3.2401, | |
| "step": 74850 | |
| }, | |
| { | |
| "epoch": 21.798789007918025, | |
| "grad_norm": 0.3986077308654785, | |
| "learning_rate": 0.0003386173558532324, | |
| "loss": 3.2386, | |
| "step": 74900 | |
| }, | |
| { | |
| "epoch": 21.81334420121099, | |
| "grad_norm": 0.374778687953949, | |
| "learning_rate": 0.00033844263249854393, | |
| "loss": 3.2278, | |
| "step": 74950 | |
| }, | |
| { | |
| "epoch": 21.82789939450396, | |
| "grad_norm": 0.4308692216873169, | |
| "learning_rate": 0.00033826790914385553, | |
| "loss": 3.2269, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 21.82789939450396, | |
| "eval_accuracy": 0.3740117275796979, | |
| "eval_loss": 3.5365889072418213, | |
| "eval_runtime": 53.7533, | |
| "eval_samples_per_second": 309.767, | |
| "eval_steps_per_second": 19.366, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 21.842454587796926, | |
| "grad_norm": 0.3903064429759979, | |
| "learning_rate": 0.0003380931857891671, | |
| "loss": 3.2389, | |
| "step": 75050 | |
| }, | |
| { | |
| "epoch": 21.857009781089893, | |
| "grad_norm": 0.37731435894966125, | |
| "learning_rate": 0.00033791846243447866, | |
| "loss": 3.2236, | |
| "step": 75100 | |
| }, | |
| { | |
| "epoch": 21.87156497438286, | |
| "grad_norm": 0.40697067975997925, | |
| "learning_rate": 0.0003377437390797903, | |
| "loss": 3.2329, | |
| "step": 75150 | |
| }, | |
| { | |
| "epoch": 21.886120167675827, | |
| "grad_norm": 0.4108999967575073, | |
| "learning_rate": 0.0003375690157251019, | |
| "loss": 3.2371, | |
| "step": 75200 | |
| }, | |
| { | |
| "epoch": 21.900675360968794, | |
| "grad_norm": 0.35968855023384094, | |
| "learning_rate": 0.0003373942923704135, | |
| "loss": 3.2322, | |
| "step": 75250 | |
| }, | |
| { | |
| "epoch": 21.91523055426176, | |
| "grad_norm": 0.40624168515205383, | |
| "learning_rate": 0.00033721956901572504, | |
| "loss": 3.2356, | |
| "step": 75300 | |
| }, | |
| { | |
| "epoch": 21.929785747554728, | |
| "grad_norm": 0.3868545591831207, | |
| "learning_rate": 0.00033704484566103663, | |
| "loss": 3.2434, | |
| "step": 75350 | |
| }, | |
| { | |
| "epoch": 21.944340940847695, | |
| "grad_norm": 0.4109153747558594, | |
| "learning_rate": 0.00033687012230634823, | |
| "loss": 3.2526, | |
| "step": 75400 | |
| }, | |
| { | |
| "epoch": 21.958896134140662, | |
| "grad_norm": 0.41709011793136597, | |
| "learning_rate": 0.0003366953989516599, | |
| "loss": 3.2473, | |
| "step": 75450 | |
| }, | |
| { | |
| "epoch": 21.97345132743363, | |
| "grad_norm": 0.4181461036205292, | |
| "learning_rate": 0.00033652067559697147, | |
| "loss": 3.2546, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 21.988006520726596, | |
| "grad_norm": 0.402383953332901, | |
| "learning_rate": 0.000336345952242283, | |
| "loss": 3.2444, | |
| "step": 75550 | |
| }, | |
| { | |
| "epoch": 22.002328830926874, | |
| "grad_norm": 0.39139848947525024, | |
| "learning_rate": 0.0003361712288875946, | |
| "loss": 3.2368, | |
| "step": 75600 | |
| }, | |
| { | |
| "epoch": 22.01688402421984, | |
| "grad_norm": 0.40119317173957825, | |
| "learning_rate": 0.0003359965055329062, | |
| "loss": 3.1337, | |
| "step": 75650 | |
| }, | |
| { | |
| "epoch": 22.03143921751281, | |
| "grad_norm": 0.39970213174819946, | |
| "learning_rate": 0.00033582178217821785, | |
| "loss": 3.1467, | |
| "step": 75700 | |
| }, | |
| { | |
| "epoch": 22.045994410805775, | |
| "grad_norm": 0.38196083903312683, | |
| "learning_rate": 0.0003356470588235294, | |
| "loss": 3.14, | |
| "step": 75750 | |
| }, | |
| { | |
| "epoch": 22.060549604098743, | |
| "grad_norm": 0.4303697943687439, | |
| "learning_rate": 0.000335472335468841, | |
| "loss": 3.14, | |
| "step": 75800 | |
| }, | |
| { | |
| "epoch": 22.07510479739171, | |
| "grad_norm": 0.4171637296676636, | |
| "learning_rate": 0.0003352976121141526, | |
| "loss": 3.1699, | |
| "step": 75850 | |
| }, | |
| { | |
| "epoch": 22.089659990684677, | |
| "grad_norm": 0.3931276202201843, | |
| "learning_rate": 0.0003351228887594641, | |
| "loss": 3.1501, | |
| "step": 75900 | |
| }, | |
| { | |
| "epoch": 22.104215183977644, | |
| "grad_norm": 0.4390031099319458, | |
| "learning_rate": 0.0003349481654047757, | |
| "loss": 3.1497, | |
| "step": 75950 | |
| }, | |
| { | |
| "epoch": 22.11877037727061, | |
| "grad_norm": 0.42660608887672424, | |
| "learning_rate": 0.00033477344205008736, | |
| "loss": 3.1636, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 22.11877037727061, | |
| "eval_accuracy": 0.37321689041319195, | |
| "eval_loss": 3.552351951599121, | |
| "eval_runtime": 53.5346, | |
| "eval_samples_per_second": 311.033, | |
| "eval_steps_per_second": 19.445, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 22.133325570563578, | |
| "grad_norm": 0.4021102488040924, | |
| "learning_rate": 0.00033459871869539895, | |
| "loss": 3.1641, | |
| "step": 76050 | |
| }, | |
| { | |
| "epoch": 22.147880763856545, | |
| "grad_norm": 0.39087268710136414, | |
| "learning_rate": 0.0003344239953407105, | |
| "loss": 3.1666, | |
| "step": 76100 | |
| }, | |
| { | |
| "epoch": 22.162435957149512, | |
| "grad_norm": 0.42036816477775574, | |
| "learning_rate": 0.0003342492719860221, | |
| "loss": 3.1754, | |
| "step": 76150 | |
| }, | |
| { | |
| "epoch": 22.17699115044248, | |
| "grad_norm": 0.4071367681026459, | |
| "learning_rate": 0.0003340745486313337, | |
| "loss": 3.1689, | |
| "step": 76200 | |
| }, | |
| { | |
| "epoch": 22.191546343735446, | |
| "grad_norm": 0.39826059341430664, | |
| "learning_rate": 0.0003338998252766453, | |
| "loss": 3.1746, | |
| "step": 76250 | |
| }, | |
| { | |
| "epoch": 22.206101537028413, | |
| "grad_norm": 0.42533090710639954, | |
| "learning_rate": 0.00033372510192195687, | |
| "loss": 3.1857, | |
| "step": 76300 | |
| }, | |
| { | |
| "epoch": 22.22065673032138, | |
| "grad_norm": 0.4097287356853485, | |
| "learning_rate": 0.00033355037856726847, | |
| "loss": 3.1813, | |
| "step": 76350 | |
| }, | |
| { | |
| "epoch": 22.235211923614347, | |
| "grad_norm": 0.4521082043647766, | |
| "learning_rate": 0.00033337565521258006, | |
| "loss": 3.171, | |
| "step": 76400 | |
| }, | |
| { | |
| "epoch": 22.24976711690731, | |
| "grad_norm": 0.41257935762405396, | |
| "learning_rate": 0.00033320093185789165, | |
| "loss": 3.1859, | |
| "step": 76450 | |
| }, | |
| { | |
| "epoch": 22.264322310200278, | |
| "grad_norm": 0.43520471453666687, | |
| "learning_rate": 0.0003330262085032032, | |
| "loss": 3.1841, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 22.278877503493245, | |
| "grad_norm": 0.377008318901062, | |
| "learning_rate": 0.00033285148514851484, | |
| "loss": 3.1895, | |
| "step": 76550 | |
| }, | |
| { | |
| "epoch": 22.293432696786212, | |
| "grad_norm": 0.42324692010879517, | |
| "learning_rate": 0.00033267676179382644, | |
| "loss": 3.1876, | |
| "step": 76600 | |
| }, | |
| { | |
| "epoch": 22.30798789007918, | |
| "grad_norm": 0.40403997898101807, | |
| "learning_rate": 0.00033250203843913803, | |
| "loss": 3.1907, | |
| "step": 76650 | |
| }, | |
| { | |
| "epoch": 22.322543083372146, | |
| "grad_norm": 0.41679444909095764, | |
| "learning_rate": 0.00033232731508444957, | |
| "loss": 3.1876, | |
| "step": 76700 | |
| }, | |
| { | |
| "epoch": 22.337098276665113, | |
| "grad_norm": 0.3939540982246399, | |
| "learning_rate": 0.00033215259172976117, | |
| "loss": 3.1996, | |
| "step": 76750 | |
| }, | |
| { | |
| "epoch": 22.35165346995808, | |
| "grad_norm": 0.41562560200691223, | |
| "learning_rate": 0.00033197786837507276, | |
| "loss": 3.2112, | |
| "step": 76800 | |
| }, | |
| { | |
| "epoch": 22.366208663251047, | |
| "grad_norm": 0.39191558957099915, | |
| "learning_rate": 0.0003318031450203844, | |
| "loss": 3.1919, | |
| "step": 76850 | |
| }, | |
| { | |
| "epoch": 22.380763856544014, | |
| "grad_norm": 0.43300649523735046, | |
| "learning_rate": 0.00033162842166569595, | |
| "loss": 3.1942, | |
| "step": 76900 | |
| }, | |
| { | |
| "epoch": 22.39531904983698, | |
| "grad_norm": 0.42634981870651245, | |
| "learning_rate": 0.00033145369831100754, | |
| "loss": 3.2001, | |
| "step": 76950 | |
| }, | |
| { | |
| "epoch": 22.40987424312995, | |
| "grad_norm": 0.41050592064857483, | |
| "learning_rate": 0.00033127897495631914, | |
| "loss": 3.2047, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 22.40987424312995, | |
| "eval_accuracy": 0.3735130592228319, | |
| "eval_loss": 3.5465681552886963, | |
| "eval_runtime": 53.6918, | |
| "eval_samples_per_second": 310.122, | |
| "eval_steps_per_second": 19.388, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 22.424429436422916, | |
| "grad_norm": 0.39140987396240234, | |
| "learning_rate": 0.0003311042516016307, | |
| "loss": 3.214, | |
| "step": 77050 | |
| }, | |
| { | |
| "epoch": 22.438984629715883, | |
| "grad_norm": 0.43603771924972534, | |
| "learning_rate": 0.0003309295282469423, | |
| "loss": 3.2045, | |
| "step": 77100 | |
| }, | |
| { | |
| "epoch": 22.45353982300885, | |
| "grad_norm": 0.4079514443874359, | |
| "learning_rate": 0.0003307548048922539, | |
| "loss": 3.1992, | |
| "step": 77150 | |
| }, | |
| { | |
| "epoch": 22.468095016301817, | |
| "grad_norm": 0.4129694700241089, | |
| "learning_rate": 0.0003305800815375655, | |
| "loss": 3.2035, | |
| "step": 77200 | |
| }, | |
| { | |
| "epoch": 22.482650209594784, | |
| "grad_norm": 0.3873485028743744, | |
| "learning_rate": 0.00033040535818287705, | |
| "loss": 3.208, | |
| "step": 77250 | |
| }, | |
| { | |
| "epoch": 22.49720540288775, | |
| "grad_norm": 0.38549983501434326, | |
| "learning_rate": 0.00033023063482818865, | |
| "loss": 3.217, | |
| "step": 77300 | |
| }, | |
| { | |
| "epoch": 22.511760596180718, | |
| "grad_norm": 0.4100998342037201, | |
| "learning_rate": 0.00033005591147350024, | |
| "loss": 3.2267, | |
| "step": 77350 | |
| }, | |
| { | |
| "epoch": 22.526315789473685, | |
| "grad_norm": 0.4430851936340332, | |
| "learning_rate": 0.0003298811881188119, | |
| "loss": 3.209, | |
| "step": 77400 | |
| }, | |
| { | |
| "epoch": 22.540870982766652, | |
| "grad_norm": 0.37862566113471985, | |
| "learning_rate": 0.00032970646476412343, | |
| "loss": 3.2243, | |
| "step": 77450 | |
| }, | |
| { | |
| "epoch": 22.55542617605962, | |
| "grad_norm": 0.39100944995880127, | |
| "learning_rate": 0.000329531741409435, | |
| "loss": 3.2049, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 22.569981369352586, | |
| "grad_norm": 0.4275621175765991, | |
| "learning_rate": 0.0003293570180547466, | |
| "loss": 3.2099, | |
| "step": 77550 | |
| }, | |
| { | |
| "epoch": 22.584536562645553, | |
| "grad_norm": 0.39355242252349854, | |
| "learning_rate": 0.0003291822947000582, | |
| "loss": 3.2046, | |
| "step": 77600 | |
| }, | |
| { | |
| "epoch": 22.59909175593852, | |
| "grad_norm": 0.41366833448410034, | |
| "learning_rate": 0.00032900757134536975, | |
| "loss": 3.2153, | |
| "step": 77650 | |
| }, | |
| { | |
| "epoch": 22.613646949231487, | |
| "grad_norm": 0.38805335760116577, | |
| "learning_rate": 0.0003288328479906814, | |
| "loss": 3.211, | |
| "step": 77700 | |
| }, | |
| { | |
| "epoch": 22.628202142524454, | |
| "grad_norm": 0.40671414136886597, | |
| "learning_rate": 0.000328658124635993, | |
| "loss": 3.2242, | |
| "step": 77750 | |
| }, | |
| { | |
| "epoch": 22.64275733581742, | |
| "grad_norm": 0.4100366234779358, | |
| "learning_rate": 0.0003284834012813046, | |
| "loss": 3.2153, | |
| "step": 77800 | |
| }, | |
| { | |
| "epoch": 22.657312529110385, | |
| "grad_norm": 0.39938589930534363, | |
| "learning_rate": 0.00032830867792661613, | |
| "loss": 3.2158, | |
| "step": 77850 | |
| }, | |
| { | |
| "epoch": 22.671867722403352, | |
| "grad_norm": 0.3923737704753876, | |
| "learning_rate": 0.0003281339545719277, | |
| "loss": 3.2288, | |
| "step": 77900 | |
| }, | |
| { | |
| "epoch": 22.68642291569632, | |
| "grad_norm": 0.38785865902900696, | |
| "learning_rate": 0.0003279592312172394, | |
| "loss": 3.2214, | |
| "step": 77950 | |
| }, | |
| { | |
| "epoch": 22.700978108989286, | |
| "grad_norm": 0.4302196800708771, | |
| "learning_rate": 0.00032778450786255097, | |
| "loss": 3.2191, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 22.700978108989286, | |
| "eval_accuracy": 0.37395989803801094, | |
| "eval_loss": 3.537210464477539, | |
| "eval_runtime": 53.6756, | |
| "eval_samples_per_second": 310.215, | |
| "eval_steps_per_second": 19.394, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 22.715533302282253, | |
| "grad_norm": 0.45699915289878845, | |
| "learning_rate": 0.0003276097845078625, | |
| "loss": 3.2158, | |
| "step": 78050 | |
| }, | |
| { | |
| "epoch": 22.73008849557522, | |
| "grad_norm": 0.39410489797592163, | |
| "learning_rate": 0.0003274350611531741, | |
| "loss": 3.2247, | |
| "step": 78100 | |
| }, | |
| { | |
| "epoch": 22.744643688868187, | |
| "grad_norm": 0.42130592465400696, | |
| "learning_rate": 0.0003272603377984857, | |
| "loss": 3.2194, | |
| "step": 78150 | |
| }, | |
| { | |
| "epoch": 22.759198882161154, | |
| "grad_norm": 0.4036268889904022, | |
| "learning_rate": 0.00032708561444379724, | |
| "loss": 3.2275, | |
| "step": 78200 | |
| }, | |
| { | |
| "epoch": 22.77375407545412, | |
| "grad_norm": 0.4043295383453369, | |
| "learning_rate": 0.0003269108910891089, | |
| "loss": 3.2264, | |
| "step": 78250 | |
| }, | |
| { | |
| "epoch": 22.78830926874709, | |
| "grad_norm": 0.4120892584323883, | |
| "learning_rate": 0.0003267361677344205, | |
| "loss": 3.23, | |
| "step": 78300 | |
| }, | |
| { | |
| "epoch": 22.802864462040056, | |
| "grad_norm": 0.3961464464664459, | |
| "learning_rate": 0.0003265614443797321, | |
| "loss": 3.2232, | |
| "step": 78350 | |
| }, | |
| { | |
| "epoch": 22.817419655333023, | |
| "grad_norm": 0.4187760651111603, | |
| "learning_rate": 0.0003263867210250436, | |
| "loss": 3.2233, | |
| "step": 78400 | |
| }, | |
| { | |
| "epoch": 22.83197484862599, | |
| "grad_norm": 0.4022747576236725, | |
| "learning_rate": 0.0003262119976703552, | |
| "loss": 3.2321, | |
| "step": 78450 | |
| }, | |
| { | |
| "epoch": 22.846530041918957, | |
| "grad_norm": 0.3976438641548157, | |
| "learning_rate": 0.00032603727431566686, | |
| "loss": 3.2214, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 22.861085235211924, | |
| "grad_norm": 0.3985541760921478, | |
| "learning_rate": 0.00032586255096097845, | |
| "loss": 3.229, | |
| "step": 78550 | |
| }, | |
| { | |
| "epoch": 22.87564042850489, | |
| "grad_norm": 0.3990572690963745, | |
| "learning_rate": 0.00032568782760629005, | |
| "loss": 3.2286, | |
| "step": 78600 | |
| }, | |
| { | |
| "epoch": 22.890195621797858, | |
| "grad_norm": 0.4425085484981537, | |
| "learning_rate": 0.0003255131042516016, | |
| "loss": 3.2328, | |
| "step": 78650 | |
| }, | |
| { | |
| "epoch": 22.904750815090825, | |
| "grad_norm": 0.43304139375686646, | |
| "learning_rate": 0.0003253383808969132, | |
| "loss": 3.2269, | |
| "step": 78700 | |
| }, | |
| { | |
| "epoch": 22.919306008383792, | |
| "grad_norm": 0.4098978042602539, | |
| "learning_rate": 0.0003251636575422248, | |
| "loss": 3.2368, | |
| "step": 78750 | |
| }, | |
| { | |
| "epoch": 22.93386120167676, | |
| "grad_norm": 0.3754848539829254, | |
| "learning_rate": 0.0003249889341875364, | |
| "loss": 3.2278, | |
| "step": 78800 | |
| }, | |
| { | |
| "epoch": 22.948416394969726, | |
| "grad_norm": 0.3976745307445526, | |
| "learning_rate": 0.00032481421083284796, | |
| "loss": 3.2481, | |
| "step": 78850 | |
| }, | |
| { | |
| "epoch": 22.962971588262693, | |
| "grad_norm": 0.41294196248054504, | |
| "learning_rate": 0.00032463948747815956, | |
| "loss": 3.2335, | |
| "step": 78900 | |
| }, | |
| { | |
| "epoch": 22.97752678155566, | |
| "grad_norm": 0.42459627985954285, | |
| "learning_rate": 0.00032446476412347115, | |
| "loss": 3.233, | |
| "step": 78950 | |
| }, | |
| { | |
| "epoch": 22.992081974848627, | |
| "grad_norm": 0.4157381057739258, | |
| "learning_rate": 0.0003242900407687827, | |
| "loss": 3.227, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 22.992081974848627, | |
| "eval_accuracy": 0.3743393937071885, | |
| "eval_loss": 3.530731439590454, | |
| "eval_runtime": 53.6205, | |
| "eval_samples_per_second": 310.534, | |
| "eval_steps_per_second": 19.414, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 23.006404285048905, | |
| "grad_norm": 0.44045504927635193, | |
| "learning_rate": 0.00032411531741409434, | |
| "loss": 3.1849, | |
| "step": 79050 | |
| }, | |
| { | |
| "epoch": 23.020959478341872, | |
| "grad_norm": 0.39091747999191284, | |
| "learning_rate": 0.00032394059405940593, | |
| "loss": 3.1281, | |
| "step": 79100 | |
| }, | |
| { | |
| "epoch": 23.03551467163484, | |
| "grad_norm": 0.45454585552215576, | |
| "learning_rate": 0.00032376587070471753, | |
| "loss": 3.1221, | |
| "step": 79150 | |
| }, | |
| { | |
| "epoch": 23.050069864927806, | |
| "grad_norm": 0.3957388401031494, | |
| "learning_rate": 0.00032359114735002907, | |
| "loss": 3.1434, | |
| "step": 79200 | |
| }, | |
| { | |
| "epoch": 23.064625058220773, | |
| "grad_norm": 0.4071851670742035, | |
| "learning_rate": 0.00032341642399534066, | |
| "loss": 3.1516, | |
| "step": 79250 | |
| }, | |
| { | |
| "epoch": 23.07918025151374, | |
| "grad_norm": 0.4184959828853607, | |
| "learning_rate": 0.00032324170064065226, | |
| "loss": 3.1425, | |
| "step": 79300 | |
| }, | |
| { | |
| "epoch": 23.093735444806708, | |
| "grad_norm": 0.44066667556762695, | |
| "learning_rate": 0.0003230669772859639, | |
| "loss": 3.1584, | |
| "step": 79350 | |
| }, | |
| { | |
| "epoch": 23.108290638099675, | |
| "grad_norm": 0.4152480959892273, | |
| "learning_rate": 0.00032289225393127545, | |
| "loss": 3.1668, | |
| "step": 79400 | |
| }, | |
| { | |
| "epoch": 23.12284583139264, | |
| "grad_norm": 0.38862237334251404, | |
| "learning_rate": 0.00032271753057658704, | |
| "loss": 3.144, | |
| "step": 79450 | |
| }, | |
| { | |
| "epoch": 23.13740102468561, | |
| "grad_norm": 0.422527015209198, | |
| "learning_rate": 0.00032254280722189863, | |
| "loss": 3.164, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 23.151956217978576, | |
| "grad_norm": 0.39298492670059204, | |
| "learning_rate": 0.00032236808386721023, | |
| "loss": 3.1691, | |
| "step": 79550 | |
| }, | |
| { | |
| "epoch": 23.166511411271543, | |
| "grad_norm": 0.40448200702667236, | |
| "learning_rate": 0.00032219336051252177, | |
| "loss": 3.1649, | |
| "step": 79600 | |
| }, | |
| { | |
| "epoch": 23.18106660456451, | |
| "grad_norm": 0.42754289507865906, | |
| "learning_rate": 0.0003220186371578334, | |
| "loss": 3.1543, | |
| "step": 79650 | |
| }, | |
| { | |
| "epoch": 23.195621797857477, | |
| "grad_norm": 0.4162788689136505, | |
| "learning_rate": 0.000321843913803145, | |
| "loss": 3.1613, | |
| "step": 79700 | |
| }, | |
| { | |
| "epoch": 23.210176991150444, | |
| "grad_norm": 0.40713420510292053, | |
| "learning_rate": 0.0003216691904484566, | |
| "loss": 3.1608, | |
| "step": 79750 | |
| }, | |
| { | |
| "epoch": 23.22473218444341, | |
| "grad_norm": 0.41067633032798767, | |
| "learning_rate": 0.00032149446709376815, | |
| "loss": 3.1773, | |
| "step": 79800 | |
| }, | |
| { | |
| "epoch": 23.239287377736375, | |
| "grad_norm": 0.4268764853477478, | |
| "learning_rate": 0.00032131974373907974, | |
| "loss": 3.1651, | |
| "step": 79850 | |
| }, | |
| { | |
| "epoch": 23.25384257102934, | |
| "grad_norm": 0.41571900248527527, | |
| "learning_rate": 0.0003211450203843914, | |
| "loss": 3.1818, | |
| "step": 79900 | |
| }, | |
| { | |
| "epoch": 23.26839776432231, | |
| "grad_norm": 0.3887295424938202, | |
| "learning_rate": 0.000320970297029703, | |
| "loss": 3.1716, | |
| "step": 79950 | |
| }, | |
| { | |
| "epoch": 23.282952957615276, | |
| "grad_norm": 0.401355504989624, | |
| "learning_rate": 0.0003207955736750145, | |
| "loss": 3.1934, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 23.282952957615276, | |
| "eval_accuracy": 0.3734726298297699, | |
| "eval_loss": 3.549725294113159, | |
| "eval_runtime": 53.5353, | |
| "eval_samples_per_second": 311.029, | |
| "eval_steps_per_second": 19.445, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 23.297508150908243, | |
| "grad_norm": 0.4480530619621277, | |
| "learning_rate": 0.0003206208503203261, | |
| "loss": 3.1756, | |
| "step": 80050 | |
| }, | |
| { | |
| "epoch": 23.31206334420121, | |
| "grad_norm": 0.43842053413391113, | |
| "learning_rate": 0.0003204461269656377, | |
| "loss": 3.1808, | |
| "step": 80100 | |
| }, | |
| { | |
| "epoch": 23.326618537494177, | |
| "grad_norm": 0.4229533076286316, | |
| "learning_rate": 0.00032027140361094925, | |
| "loss": 3.1864, | |
| "step": 80150 | |
| }, | |
| { | |
| "epoch": 23.341173730787144, | |
| "grad_norm": 0.4049815237522125, | |
| "learning_rate": 0.0003200966802562609, | |
| "loss": 3.1865, | |
| "step": 80200 | |
| }, | |
| { | |
| "epoch": 23.35572892408011, | |
| "grad_norm": 0.4030032455921173, | |
| "learning_rate": 0.0003199219569015725, | |
| "loss": 3.1842, | |
| "step": 80250 | |
| }, | |
| { | |
| "epoch": 23.370284117373078, | |
| "grad_norm": 0.40929511189460754, | |
| "learning_rate": 0.0003197472335468841, | |
| "loss": 3.18, | |
| "step": 80300 | |
| }, | |
| { | |
| "epoch": 23.384839310666045, | |
| "grad_norm": 0.405794620513916, | |
| "learning_rate": 0.00031957251019219563, | |
| "loss": 3.1878, | |
| "step": 80350 | |
| }, | |
| { | |
| "epoch": 23.399394503959012, | |
| "grad_norm": 0.4158174693584442, | |
| "learning_rate": 0.0003193977868375072, | |
| "loss": 3.1903, | |
| "step": 80400 | |
| }, | |
| { | |
| "epoch": 23.41394969725198, | |
| "grad_norm": 0.4300137460231781, | |
| "learning_rate": 0.00031922306348281887, | |
| "loss": 3.1823, | |
| "step": 80450 | |
| }, | |
| { | |
| "epoch": 23.428504890544946, | |
| "grad_norm": 0.4187268912792206, | |
| "learning_rate": 0.00031904834012813047, | |
| "loss": 3.1959, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 23.443060083837914, | |
| "grad_norm": 0.41276413202285767, | |
| "learning_rate": 0.000318873616773442, | |
| "loss": 3.1934, | |
| "step": 80550 | |
| }, | |
| { | |
| "epoch": 23.45761527713088, | |
| "grad_norm": 0.46322381496429443, | |
| "learning_rate": 0.0003186988934187536, | |
| "loss": 3.2036, | |
| "step": 80600 | |
| }, | |
| { | |
| "epoch": 23.472170470423848, | |
| "grad_norm": 0.4055153727531433, | |
| "learning_rate": 0.0003185241700640652, | |
| "loss": 3.1941, | |
| "step": 80650 | |
| }, | |
| { | |
| "epoch": 23.486725663716815, | |
| "grad_norm": 0.39710983633995056, | |
| "learning_rate": 0.0003183494467093768, | |
| "loss": 3.2015, | |
| "step": 80700 | |
| }, | |
| { | |
| "epoch": 23.50128085700978, | |
| "grad_norm": 0.40547940135002136, | |
| "learning_rate": 0.0003181747233546884, | |
| "loss": 3.1871, | |
| "step": 80750 | |
| }, | |
| { | |
| "epoch": 23.51583605030275, | |
| "grad_norm": 0.4789862632751465, | |
| "learning_rate": 0.000318, | |
| "loss": 3.1932, | |
| "step": 80800 | |
| }, | |
| { | |
| "epoch": 23.530391243595716, | |
| "grad_norm": 0.4000310003757477, | |
| "learning_rate": 0.00031782527664531157, | |
| "loss": 3.2111, | |
| "step": 80850 | |
| }, | |
| { | |
| "epoch": 23.544946436888683, | |
| "grad_norm": 0.4375278353691101, | |
| "learning_rate": 0.00031765055329062317, | |
| "loss": 3.2029, | |
| "step": 80900 | |
| }, | |
| { | |
| "epoch": 23.55950163018165, | |
| "grad_norm": 0.41888943314552307, | |
| "learning_rate": 0.0003174758299359347, | |
| "loss": 3.2058, | |
| "step": 80950 | |
| }, | |
| { | |
| "epoch": 23.574056823474617, | |
| "grad_norm": 0.4245913326740265, | |
| "learning_rate": 0.0003173011065812463, | |
| "loss": 3.2029, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 23.574056823474617, | |
| "eval_accuracy": 0.3741068071697768, | |
| "eval_loss": 3.5433812141418457, | |
| "eval_runtime": 53.5919, | |
| "eval_samples_per_second": 310.7, | |
| "eval_steps_per_second": 19.425, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 23.588612016767584, | |
| "grad_norm": 0.4149046242237091, | |
| "learning_rate": 0.00031712638322655795, | |
| "loss": 3.2086, | |
| "step": 81050 | |
| }, | |
| { | |
| "epoch": 23.60316721006055, | |
| "grad_norm": 0.38923636078834534, | |
| "learning_rate": 0.00031695165987186954, | |
| "loss": 3.2011, | |
| "step": 81100 | |
| }, | |
| { | |
| "epoch": 23.61772240335352, | |
| "grad_norm": 0.40325772762298584, | |
| "learning_rate": 0.0003167769365171811, | |
| "loss": 3.2058, | |
| "step": 81150 | |
| }, | |
| { | |
| "epoch": 23.63227759664648, | |
| "grad_norm": 0.38651034235954285, | |
| "learning_rate": 0.0003166022131624927, | |
| "loss": 3.2148, | |
| "step": 81200 | |
| }, | |
| { | |
| "epoch": 23.64683278993945, | |
| "grad_norm": 0.420185387134552, | |
| "learning_rate": 0.00031642748980780427, | |
| "loss": 3.2022, | |
| "step": 81250 | |
| }, | |
| { | |
| "epoch": 23.661387983232416, | |
| "grad_norm": 0.4073801040649414, | |
| "learning_rate": 0.0003162527664531159, | |
| "loss": 3.2174, | |
| "step": 81300 | |
| }, | |
| { | |
| "epoch": 23.675943176525383, | |
| "grad_norm": 0.4201747179031372, | |
| "learning_rate": 0.00031607804309842746, | |
| "loss": 3.2136, | |
| "step": 81350 | |
| }, | |
| { | |
| "epoch": 23.69049836981835, | |
| "grad_norm": 0.42752504348754883, | |
| "learning_rate": 0.00031590331974373905, | |
| "loss": 3.22, | |
| "step": 81400 | |
| }, | |
| { | |
| "epoch": 23.705053563111317, | |
| "grad_norm": 0.4017604887485504, | |
| "learning_rate": 0.00031572859638905065, | |
| "loss": 3.2173, | |
| "step": 81450 | |
| }, | |
| { | |
| "epoch": 23.719608756404284, | |
| "grad_norm": 0.44222578406333923, | |
| "learning_rate": 0.0003155538730343622, | |
| "loss": 3.2222, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 23.73416394969725, | |
| "grad_norm": 0.4165010154247284, | |
| "learning_rate": 0.0003153791496796738, | |
| "loss": 3.2254, | |
| "step": 81550 | |
| }, | |
| { | |
| "epoch": 23.74871914299022, | |
| "grad_norm": 0.4030214548110962, | |
| "learning_rate": 0.00031520442632498543, | |
| "loss": 3.2115, | |
| "step": 81600 | |
| }, | |
| { | |
| "epoch": 23.763274336283185, | |
| "grad_norm": 0.4092274010181427, | |
| "learning_rate": 0.000315029702970297, | |
| "loss": 3.2139, | |
| "step": 81650 | |
| }, | |
| { | |
| "epoch": 23.777829529576152, | |
| "grad_norm": 0.4125419855117798, | |
| "learning_rate": 0.0003148549796156086, | |
| "loss": 3.2164, | |
| "step": 81700 | |
| }, | |
| { | |
| "epoch": 23.79238472286912, | |
| "grad_norm": 0.4165419638156891, | |
| "learning_rate": 0.00031468025626092016, | |
| "loss": 3.2129, | |
| "step": 81750 | |
| }, | |
| { | |
| "epoch": 23.806939916162086, | |
| "grad_norm": 0.4171595573425293, | |
| "learning_rate": 0.00031450553290623175, | |
| "loss": 3.2151, | |
| "step": 81800 | |
| }, | |
| { | |
| "epoch": 23.821495109455054, | |
| "grad_norm": 0.4400198757648468, | |
| "learning_rate": 0.0003143308095515434, | |
| "loss": 3.2211, | |
| "step": 81850 | |
| }, | |
| { | |
| "epoch": 23.83605030274802, | |
| "grad_norm": 0.40293431282043457, | |
| "learning_rate": 0.000314156086196855, | |
| "loss": 3.2123, | |
| "step": 81900 | |
| }, | |
| { | |
| "epoch": 23.850605496040988, | |
| "grad_norm": 0.394392192363739, | |
| "learning_rate": 0.00031398136284216654, | |
| "loss": 3.2258, | |
| "step": 81950 | |
| }, | |
| { | |
| "epoch": 23.865160689333955, | |
| "grad_norm": 0.3993387520313263, | |
| "learning_rate": 0.00031380663948747813, | |
| "loss": 3.2033, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 23.865160689333955, | |
| "eval_accuracy": 0.374409322453909, | |
| "eval_loss": 3.5348408222198486, | |
| "eval_runtime": 53.6409, | |
| "eval_samples_per_second": 310.416, | |
| "eval_steps_per_second": 19.407, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 23.879715882626922, | |
| "grad_norm": 0.3985002040863037, | |
| "learning_rate": 0.0003136319161327897, | |
| "loss": 3.2323, | |
| "step": 82050 | |
| }, | |
| { | |
| "epoch": 23.89427107591989, | |
| "grad_norm": 0.42125335335731506, | |
| "learning_rate": 0.00031345719277810127, | |
| "loss": 3.2257, | |
| "step": 82100 | |
| }, | |
| { | |
| "epoch": 23.908826269212856, | |
| "grad_norm": 0.4015097916126251, | |
| "learning_rate": 0.0003132824694234129, | |
| "loss": 3.2229, | |
| "step": 82150 | |
| }, | |
| { | |
| "epoch": 23.923381462505823, | |
| "grad_norm": 0.4217109680175781, | |
| "learning_rate": 0.0003131077460687245, | |
| "loss": 3.2242, | |
| "step": 82200 | |
| }, | |
| { | |
| "epoch": 23.93793665579879, | |
| "grad_norm": 0.4096372723579407, | |
| "learning_rate": 0.0003129330227140361, | |
| "loss": 3.2096, | |
| "step": 82250 | |
| }, | |
| { | |
| "epoch": 23.952491849091757, | |
| "grad_norm": 0.4082714319229126, | |
| "learning_rate": 0.00031275829935934764, | |
| "loss": 3.2209, | |
| "step": 82300 | |
| }, | |
| { | |
| "epoch": 23.967047042384724, | |
| "grad_norm": 0.40649911761283875, | |
| "learning_rate": 0.00031258357600465924, | |
| "loss": 3.2103, | |
| "step": 82350 | |
| }, | |
| { | |
| "epoch": 23.98160223567769, | |
| "grad_norm": 0.4140775501728058, | |
| "learning_rate": 0.00031240885264997083, | |
| "loss": 3.2283, | |
| "step": 82400 | |
| }, | |
| { | |
| "epoch": 23.99615742897066, | |
| "grad_norm": 0.40586623549461365, | |
| "learning_rate": 0.0003122341292952825, | |
| "loss": 3.2239, | |
| "step": 82450 | |
| }, | |
| { | |
| "epoch": 24.010479739170936, | |
| "grad_norm": 0.40577232837677, | |
| "learning_rate": 0.000312059405940594, | |
| "loss": 3.1561, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 24.025034932463903, | |
| "grad_norm": 0.39109107851982117, | |
| "learning_rate": 0.0003118846825859056, | |
| "loss": 3.1107, | |
| "step": 82550 | |
| }, | |
| { | |
| "epoch": 24.03959012575687, | |
| "grad_norm": 0.41762179136276245, | |
| "learning_rate": 0.0003117099592312172, | |
| "loss": 3.1319, | |
| "step": 82600 | |
| }, | |
| { | |
| "epoch": 24.054145319049837, | |
| "grad_norm": 0.40706348419189453, | |
| "learning_rate": 0.0003115352358765288, | |
| "loss": 3.1319, | |
| "step": 82650 | |
| }, | |
| { | |
| "epoch": 24.068700512342804, | |
| "grad_norm": 0.4439554214477539, | |
| "learning_rate": 0.0003113605125218404, | |
| "loss": 3.1435, | |
| "step": 82700 | |
| }, | |
| { | |
| "epoch": 24.08325570563577, | |
| "grad_norm": 0.4341192841529846, | |
| "learning_rate": 0.000311185789167152, | |
| "loss": 3.1352, | |
| "step": 82750 | |
| }, | |
| { | |
| "epoch": 24.09781089892874, | |
| "grad_norm": 0.42265355587005615, | |
| "learning_rate": 0.0003110110658124636, | |
| "loss": 3.1298, | |
| "step": 82800 | |
| }, | |
| { | |
| "epoch": 24.112366092221706, | |
| "grad_norm": 0.42810073494911194, | |
| "learning_rate": 0.0003108363424577752, | |
| "loss": 3.1398, | |
| "step": 82850 | |
| }, | |
| { | |
| "epoch": 24.126921285514673, | |
| "grad_norm": 0.4416172504425049, | |
| "learning_rate": 0.0003106616191030867, | |
| "loss": 3.1443, | |
| "step": 82900 | |
| }, | |
| { | |
| "epoch": 24.14147647880764, | |
| "grad_norm": 0.40943464636802673, | |
| "learning_rate": 0.0003104868957483983, | |
| "loss": 3.141, | |
| "step": 82950 | |
| }, | |
| { | |
| "epoch": 24.156031672100607, | |
| "grad_norm": 0.4297058880329132, | |
| "learning_rate": 0.00031031217239370996, | |
| "loss": 3.1478, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 24.156031672100607, | |
| "eval_accuracy": 0.3734232683614966, | |
| "eval_loss": 3.5530121326446533, | |
| "eval_runtime": 53.6513, | |
| "eval_samples_per_second": 310.356, | |
| "eval_steps_per_second": 19.403, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 24.170586865393574, | |
| "grad_norm": 0.4135890305042267, | |
| "learning_rate": 0.00031013744903902156, | |
| "loss": 3.1559, | |
| "step": 83050 | |
| }, | |
| { | |
| "epoch": 24.18514205868654, | |
| "grad_norm": 0.40565574169158936, | |
| "learning_rate": 0.0003099627256843331, | |
| "loss": 3.1542, | |
| "step": 83100 | |
| }, | |
| { | |
| "epoch": 24.199697251979508, | |
| "grad_norm": 0.4236745536327362, | |
| "learning_rate": 0.0003097880023296447, | |
| "loss": 3.1591, | |
| "step": 83150 | |
| }, | |
| { | |
| "epoch": 24.21425244527247, | |
| "grad_norm": 0.41588324308395386, | |
| "learning_rate": 0.0003096132789749563, | |
| "loss": 3.1589, | |
| "step": 83200 | |
| }, | |
| { | |
| "epoch": 24.22880763856544, | |
| "grad_norm": 0.40717968344688416, | |
| "learning_rate": 0.00030943855562026794, | |
| "loss": 3.1579, | |
| "step": 83250 | |
| }, | |
| { | |
| "epoch": 24.243362831858406, | |
| "grad_norm": 0.43625056743621826, | |
| "learning_rate": 0.0003092638322655795, | |
| "loss": 3.1593, | |
| "step": 83300 | |
| }, | |
| { | |
| "epoch": 24.257918025151373, | |
| "grad_norm": 0.4185596704483032, | |
| "learning_rate": 0.00030908910891089107, | |
| "loss": 3.1564, | |
| "step": 83350 | |
| }, | |
| { | |
| "epoch": 24.27247321844434, | |
| "grad_norm": 0.4140440821647644, | |
| "learning_rate": 0.00030891438555620266, | |
| "loss": 3.1641, | |
| "step": 83400 | |
| }, | |
| { | |
| "epoch": 24.287028411737307, | |
| "grad_norm": 0.43900999426841736, | |
| "learning_rate": 0.0003087396622015142, | |
| "loss": 3.174, | |
| "step": 83450 | |
| }, | |
| { | |
| "epoch": 24.301583605030274, | |
| "grad_norm": 0.46006324887275696, | |
| "learning_rate": 0.0003085649388468258, | |
| "loss": 3.1816, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 24.31613879832324, | |
| "grad_norm": 0.42923614382743835, | |
| "learning_rate": 0.00030839021549213745, | |
| "loss": 3.1824, | |
| "step": 83550 | |
| }, | |
| { | |
| "epoch": 24.330693991616208, | |
| "grad_norm": 0.44603514671325684, | |
| "learning_rate": 0.00030821549213744904, | |
| "loss": 3.1759, | |
| "step": 83600 | |
| }, | |
| { | |
| "epoch": 24.345249184909175, | |
| "grad_norm": 0.41222506761550903, | |
| "learning_rate": 0.0003080407687827606, | |
| "loss": 3.1784, | |
| "step": 83650 | |
| }, | |
| { | |
| "epoch": 24.359804378202142, | |
| "grad_norm": 0.4150962829589844, | |
| "learning_rate": 0.0003078660454280722, | |
| "loss": 3.1862, | |
| "step": 83700 | |
| }, | |
| { | |
| "epoch": 24.37435957149511, | |
| "grad_norm": 0.4268902540206909, | |
| "learning_rate": 0.00030769132207338377, | |
| "loss": 3.1732, | |
| "step": 83750 | |
| }, | |
| { | |
| "epoch": 24.388914764788076, | |
| "grad_norm": 0.4248001277446747, | |
| "learning_rate": 0.00030751659871869536, | |
| "loss": 3.1811, | |
| "step": 83800 | |
| }, | |
| { | |
| "epoch": 24.403469958081043, | |
| "grad_norm": 0.40944573283195496, | |
| "learning_rate": 0.00030734187536400696, | |
| "loss": 3.1761, | |
| "step": 83850 | |
| }, | |
| { | |
| "epoch": 24.41802515137401, | |
| "grad_norm": 0.40448611974716187, | |
| "learning_rate": 0.00030716715200931855, | |
| "loss": 3.1828, | |
| "step": 83900 | |
| }, | |
| { | |
| "epoch": 24.432580344666977, | |
| "grad_norm": 0.42356812953948975, | |
| "learning_rate": 0.00030699242865463015, | |
| "loss": 3.1825, | |
| "step": 83950 | |
| }, | |
| { | |
| "epoch": 24.447135537959944, | |
| "grad_norm": 0.43056565523147583, | |
| "learning_rate": 0.00030681770529994174, | |
| "loss": 3.1918, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 24.447135537959944, | |
| "eval_accuracy": 0.37363070405555, | |
| "eval_loss": 3.5493335723876953, | |
| "eval_runtime": 53.7227, | |
| "eval_samples_per_second": 309.944, | |
| "eval_steps_per_second": 19.377, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 24.46169073125291, | |
| "grad_norm": 0.41118696331977844, | |
| "learning_rate": 0.0003066429819452533, | |
| "loss": 3.1834, | |
| "step": 84050 | |
| }, | |
| { | |
| "epoch": 24.47624592454588, | |
| "grad_norm": 0.41080746054649353, | |
| "learning_rate": 0.00030646825859056493, | |
| "loss": 3.1879, | |
| "step": 84100 | |
| }, | |
| { | |
| "epoch": 24.490801117838846, | |
| "grad_norm": 0.44307202100753784, | |
| "learning_rate": 0.0003062935352358765, | |
| "loss": 3.1864, | |
| "step": 84150 | |
| }, | |
| { | |
| "epoch": 24.505356311131813, | |
| "grad_norm": 0.42828136682510376, | |
| "learning_rate": 0.0003061188118811881, | |
| "loss": 3.1976, | |
| "step": 84200 | |
| }, | |
| { | |
| "epoch": 24.51991150442478, | |
| "grad_norm": 0.4173254072666168, | |
| "learning_rate": 0.00030594408852649966, | |
| "loss": 3.187, | |
| "step": 84250 | |
| }, | |
| { | |
| "epoch": 24.534466697717747, | |
| "grad_norm": 0.45081448554992676, | |
| "learning_rate": 0.00030576936517181125, | |
| "loss": 3.2001, | |
| "step": 84300 | |
| }, | |
| { | |
| "epoch": 24.549021891010714, | |
| "grad_norm": 0.4157457649707794, | |
| "learning_rate": 0.00030559464181712285, | |
| "loss": 3.1856, | |
| "step": 84350 | |
| }, | |
| { | |
| "epoch": 24.56357708430368, | |
| "grad_norm": 0.4390169084072113, | |
| "learning_rate": 0.0003054199184624345, | |
| "loss": 3.2021, | |
| "step": 84400 | |
| }, | |
| { | |
| "epoch": 24.578132277596648, | |
| "grad_norm": 0.430556982755661, | |
| "learning_rate": 0.00030524519510774604, | |
| "loss": 3.1944, | |
| "step": 84450 | |
| }, | |
| { | |
| "epoch": 24.592687470889615, | |
| "grad_norm": 0.40199485421180725, | |
| "learning_rate": 0.00030507047175305763, | |
| "loss": 3.1884, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 24.60724266418258, | |
| "grad_norm": 0.42402201890945435, | |
| "learning_rate": 0.0003048957483983692, | |
| "loss": 3.1956, | |
| "step": 84550 | |
| }, | |
| { | |
| "epoch": 24.621797857475546, | |
| "grad_norm": 0.4377957880496979, | |
| "learning_rate": 0.00030472102504368076, | |
| "loss": 3.2031, | |
| "step": 84600 | |
| }, | |
| { | |
| "epoch": 24.636353050768513, | |
| "grad_norm": 0.43524065613746643, | |
| "learning_rate": 0.0003045463016889924, | |
| "loss": 3.1886, | |
| "step": 84650 | |
| }, | |
| { | |
| "epoch": 24.65090824406148, | |
| "grad_norm": 0.41947442293167114, | |
| "learning_rate": 0.000304371578334304, | |
| "loss": 3.1922, | |
| "step": 84700 | |
| }, | |
| { | |
| "epoch": 24.665463437354447, | |
| "grad_norm": 0.44606029987335205, | |
| "learning_rate": 0.0003041968549796156, | |
| "loss": 3.1979, | |
| "step": 84750 | |
| }, | |
| { | |
| "epoch": 24.680018630647414, | |
| "grad_norm": 0.42091575264930725, | |
| "learning_rate": 0.00030402213162492714, | |
| "loss": 3.1954, | |
| "step": 84800 | |
| }, | |
| { | |
| "epoch": 24.69457382394038, | |
| "grad_norm": 0.4004652798175812, | |
| "learning_rate": 0.00030384740827023874, | |
| "loss": 3.2131, | |
| "step": 84850 | |
| }, | |
| { | |
| "epoch": 24.709129017233348, | |
| "grad_norm": 0.3945496678352356, | |
| "learning_rate": 0.00030367268491555033, | |
| "loss": 3.2099, | |
| "step": 84900 | |
| }, | |
| { | |
| "epoch": 24.723684210526315, | |
| "grad_norm": 0.4158707559108734, | |
| "learning_rate": 0.000303497961560862, | |
| "loss": 3.1966, | |
| "step": 84950 | |
| }, | |
| { | |
| "epoch": 24.738239403819282, | |
| "grad_norm": 0.40710821747779846, | |
| "learning_rate": 0.00030332323820617357, | |
| "loss": 3.2035, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 24.738239403819282, | |
| "eval_accuracy": 0.37436795284240376, | |
| "eval_loss": 3.5408477783203125, | |
| "eval_runtime": 53.6153, | |
| "eval_samples_per_second": 310.564, | |
| "eval_steps_per_second": 19.416, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 24.75279459711225, | |
| "grad_norm": 0.4553806185722351, | |
| "learning_rate": 0.0003031485148514851, | |
| "loss": 3.2139, | |
| "step": 85050 | |
| }, | |
| { | |
| "epoch": 24.767349790405216, | |
| "grad_norm": 0.41034647822380066, | |
| "learning_rate": 0.0003029737914967967, | |
| "loss": 3.2087, | |
| "step": 85100 | |
| }, | |
| { | |
| "epoch": 24.781904983698183, | |
| "grad_norm": 0.4238823652267456, | |
| "learning_rate": 0.0003027990681421083, | |
| "loss": 3.2062, | |
| "step": 85150 | |
| }, | |
| { | |
| "epoch": 24.79646017699115, | |
| "grad_norm": 0.41979241371154785, | |
| "learning_rate": 0.00030262434478741984, | |
| "loss": 3.2045, | |
| "step": 85200 | |
| }, | |
| { | |
| "epoch": 24.811015370284117, | |
| "grad_norm": 0.4077977240085602, | |
| "learning_rate": 0.0003024496214327315, | |
| "loss": 3.2173, | |
| "step": 85250 | |
| }, | |
| { | |
| "epoch": 24.825570563577084, | |
| "grad_norm": 0.42751821875572205, | |
| "learning_rate": 0.0003022748980780431, | |
| "loss": 3.2075, | |
| "step": 85300 | |
| }, | |
| { | |
| "epoch": 24.84012575687005, | |
| "grad_norm": 0.41486644744873047, | |
| "learning_rate": 0.0003021001747233547, | |
| "loss": 3.2103, | |
| "step": 85350 | |
| }, | |
| { | |
| "epoch": 24.85468095016302, | |
| "grad_norm": 0.3816075026988983, | |
| "learning_rate": 0.0003019254513686662, | |
| "loss": 3.2168, | |
| "step": 85400 | |
| }, | |
| { | |
| "epoch": 24.869236143455986, | |
| "grad_norm": 0.4077073037624359, | |
| "learning_rate": 0.0003017507280139778, | |
| "loss": 3.2155, | |
| "step": 85450 | |
| }, | |
| { | |
| "epoch": 24.883791336748953, | |
| "grad_norm": 0.3986726701259613, | |
| "learning_rate": 0.00030157600465928946, | |
| "loss": 3.2109, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 24.89834653004192, | |
| "grad_norm": 0.43230748176574707, | |
| "learning_rate": 0.00030140128130460106, | |
| "loss": 3.2107, | |
| "step": 85550 | |
| }, | |
| { | |
| "epoch": 24.912901723334887, | |
| "grad_norm": 0.4341176152229309, | |
| "learning_rate": 0.0003012265579499126, | |
| "loss": 3.2183, | |
| "step": 85600 | |
| }, | |
| { | |
| "epoch": 24.927456916627854, | |
| "grad_norm": 0.4475161135196686, | |
| "learning_rate": 0.0003010518345952242, | |
| "loss": 3.2033, | |
| "step": 85650 | |
| }, | |
| { | |
| "epoch": 24.94201210992082, | |
| "grad_norm": 0.42576834559440613, | |
| "learning_rate": 0.0003008771112405358, | |
| "loss": 3.2142, | |
| "step": 85700 | |
| }, | |
| { | |
| "epoch": 24.956567303213788, | |
| "grad_norm": 0.4245013892650604, | |
| "learning_rate": 0.0003007023878858473, | |
| "loss": 3.2217, | |
| "step": 85750 | |
| }, | |
| { | |
| "epoch": 24.971122496506755, | |
| "grad_norm": 0.4295082688331604, | |
| "learning_rate": 0.000300527664531159, | |
| "loss": 3.2119, | |
| "step": 85800 | |
| }, | |
| { | |
| "epoch": 24.985677689799722, | |
| "grad_norm": 0.39927026629447937, | |
| "learning_rate": 0.00030035294117647057, | |
| "loss": 3.2212, | |
| "step": 85850 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 1.2407130002975464, | |
| "learning_rate": 0.00030017821782178216, | |
| "loss": 3.2168, | |
| "step": 85900 | |
| }, | |
| { | |
| "epoch": 25.014555193292967, | |
| "grad_norm": 0.422044038772583, | |
| "learning_rate": 0.00030000349446709376, | |
| "loss": 3.122, | |
| "step": 85950 | |
| }, | |
| { | |
| "epoch": 25.029110386585934, | |
| "grad_norm": 0.41474974155426025, | |
| "learning_rate": 0.00029982877111240535, | |
| "loss": 3.1208, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 25.029110386585934, | |
| "eval_accuracy": 0.37388855896362544, | |
| "eval_loss": 3.5477046966552734, | |
| "eval_runtime": 53.8221, | |
| "eval_samples_per_second": 309.371, | |
| "eval_steps_per_second": 19.341, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 25.0436655798789, | |
| "grad_norm": 0.41038137674331665, | |
| "learning_rate": 0.00029965404775771694, | |
| "loss": 3.1116, | |
| "step": 86050 | |
| }, | |
| { | |
| "epoch": 25.05822077317187, | |
| "grad_norm": 0.44865256547927856, | |
| "learning_rate": 0.0002994793244030285, | |
| "loss": 3.1297, | |
| "step": 86100 | |
| }, | |
| { | |
| "epoch": 25.072775966464835, | |
| "grad_norm": 0.4151347279548645, | |
| "learning_rate": 0.00029930460104834013, | |
| "loss": 3.1241, | |
| "step": 86150 | |
| }, | |
| { | |
| "epoch": 25.087331159757802, | |
| "grad_norm": 0.4309297502040863, | |
| "learning_rate": 0.0002991298776936517, | |
| "loss": 3.1223, | |
| "step": 86200 | |
| }, | |
| { | |
| "epoch": 25.10188635305077, | |
| "grad_norm": 0.4231893718242645, | |
| "learning_rate": 0.00029895515433896327, | |
| "loss": 3.1343, | |
| "step": 86250 | |
| }, | |
| { | |
| "epoch": 25.116441546343736, | |
| "grad_norm": 0.43143463134765625, | |
| "learning_rate": 0.00029878043098427486, | |
| "loss": 3.1312, | |
| "step": 86300 | |
| }, | |
| { | |
| "epoch": 25.130996739636704, | |
| "grad_norm": 0.42287325859069824, | |
| "learning_rate": 0.00029860570762958646, | |
| "loss": 3.1351, | |
| "step": 86350 | |
| }, | |
| { | |
| "epoch": 25.14555193292967, | |
| "grad_norm": 0.4508977234363556, | |
| "learning_rate": 0.00029843098427489805, | |
| "loss": 3.1459, | |
| "step": 86400 | |
| }, | |
| { | |
| "epoch": 25.160107126222638, | |
| "grad_norm": 0.4358970522880554, | |
| "learning_rate": 0.00029825626092020964, | |
| "loss": 3.1424, | |
| "step": 86450 | |
| }, | |
| { | |
| "epoch": 25.174662319515605, | |
| "grad_norm": 0.4380928874015808, | |
| "learning_rate": 0.00029808153756552124, | |
| "loss": 3.1358, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 25.189217512808572, | |
| "grad_norm": 0.4195115268230438, | |
| "learning_rate": 0.00029790681421083283, | |
| "loss": 3.1591, | |
| "step": 86550 | |
| }, | |
| { | |
| "epoch": 25.203772706101535, | |
| "grad_norm": 0.4579044282436371, | |
| "learning_rate": 0.00029773209085614443, | |
| "loss": 3.1493, | |
| "step": 86600 | |
| }, | |
| { | |
| "epoch": 25.218327899394502, | |
| "grad_norm": 0.42738059163093567, | |
| "learning_rate": 0.00029755736750145597, | |
| "loss": 3.1451, | |
| "step": 86650 | |
| }, | |
| { | |
| "epoch": 25.23288309268747, | |
| "grad_norm": 0.43628382682800293, | |
| "learning_rate": 0.0002973826441467676, | |
| "loss": 3.1405, | |
| "step": 86700 | |
| }, | |
| { | |
| "epoch": 25.247438285980436, | |
| "grad_norm": 0.4103586971759796, | |
| "learning_rate": 0.00029720792079207916, | |
| "loss": 3.1503, | |
| "step": 86750 | |
| }, | |
| { | |
| "epoch": 25.261993479273404, | |
| "grad_norm": 0.4390321373939514, | |
| "learning_rate": 0.00029703319743739075, | |
| "loss": 3.1571, | |
| "step": 86800 | |
| }, | |
| { | |
| "epoch": 25.27654867256637, | |
| "grad_norm": 0.4085807800292969, | |
| "learning_rate": 0.00029685847408270234, | |
| "loss": 3.1548, | |
| "step": 86850 | |
| }, | |
| { | |
| "epoch": 25.291103865859338, | |
| "grad_norm": 0.43049386143684387, | |
| "learning_rate": 0.00029668375072801394, | |
| "loss": 3.1687, | |
| "step": 86900 | |
| }, | |
| { | |
| "epoch": 25.305659059152305, | |
| "grad_norm": 0.41924601793289185, | |
| "learning_rate": 0.00029650902737332553, | |
| "loss": 3.1679, | |
| "step": 86950 | |
| }, | |
| { | |
| "epoch": 25.320214252445272, | |
| "grad_norm": 0.4083698093891144, | |
| "learning_rate": 0.00029633430401863713, | |
| "loss": 3.1662, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 25.320214252445272, | |
| "eval_accuracy": 0.3739913953558615, | |
| "eval_loss": 3.548922300338745, | |
| "eval_runtime": 53.706, | |
| "eval_samples_per_second": 310.04, | |
| "eval_steps_per_second": 19.383, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 25.33476944573824, | |
| "grad_norm": 0.4281640648841858, | |
| "learning_rate": 0.0002961595806639487, | |
| "loss": 3.1607, | |
| "step": 87050 | |
| }, | |
| { | |
| "epoch": 25.349324639031206, | |
| "grad_norm": 0.47053027153015137, | |
| "learning_rate": 0.0002959848573092603, | |
| "loss": 3.1644, | |
| "step": 87100 | |
| }, | |
| { | |
| "epoch": 25.363879832324173, | |
| "grad_norm": 0.4266578257083893, | |
| "learning_rate": 0.0002958101339545719, | |
| "loss": 3.1733, | |
| "step": 87150 | |
| }, | |
| { | |
| "epoch": 25.37843502561714, | |
| "grad_norm": 0.45390111207962036, | |
| "learning_rate": 0.0002956354105998835, | |
| "loss": 3.1663, | |
| "step": 87200 | |
| }, | |
| { | |
| "epoch": 25.392990218910107, | |
| "grad_norm": 0.4339146912097931, | |
| "learning_rate": 0.0002954606872451951, | |
| "loss": 3.1642, | |
| "step": 87250 | |
| }, | |
| { | |
| "epoch": 25.407545412203074, | |
| "grad_norm": 0.4300542175769806, | |
| "learning_rate": 0.0002952859638905067, | |
| "loss": 3.1738, | |
| "step": 87300 | |
| }, | |
| { | |
| "epoch": 25.42210060549604, | |
| "grad_norm": 0.4232361614704132, | |
| "learning_rate": 0.00029511124053581823, | |
| "loss": 3.1857, | |
| "step": 87350 | |
| }, | |
| { | |
| "epoch": 25.43665579878901, | |
| "grad_norm": 0.4554564654827118, | |
| "learning_rate": 0.0002949365171811299, | |
| "loss": 3.1735, | |
| "step": 87400 | |
| }, | |
| { | |
| "epoch": 25.451210992081975, | |
| "grad_norm": 0.41143476963043213, | |
| "learning_rate": 0.0002947617938264414, | |
| "loss": 3.1776, | |
| "step": 87450 | |
| }, | |
| { | |
| "epoch": 25.465766185374942, | |
| "grad_norm": 0.42447465658187866, | |
| "learning_rate": 0.000294587070471753, | |
| "loss": 3.1799, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 25.48032137866791, | |
| "grad_norm": 0.429790198802948, | |
| "learning_rate": 0.0002944123471170646, | |
| "loss": 3.1811, | |
| "step": 87550 | |
| }, | |
| { | |
| "epoch": 25.494876571960877, | |
| "grad_norm": 0.43548452854156494, | |
| "learning_rate": 0.0002942376237623762, | |
| "loss": 3.1811, | |
| "step": 87600 | |
| }, | |
| { | |
| "epoch": 25.509431765253844, | |
| "grad_norm": 0.44125983119010925, | |
| "learning_rate": 0.0002940629004076878, | |
| "loss": 3.181, | |
| "step": 87650 | |
| }, | |
| { | |
| "epoch": 25.52398695854681, | |
| "grad_norm": 0.4534256160259247, | |
| "learning_rate": 0.0002938881770529994, | |
| "loss": 3.172, | |
| "step": 87700 | |
| }, | |
| { | |
| "epoch": 25.538542151839778, | |
| "grad_norm": 0.44063693284988403, | |
| "learning_rate": 0.000293713453698311, | |
| "loss": 3.184, | |
| "step": 87750 | |
| }, | |
| { | |
| "epoch": 25.553097345132745, | |
| "grad_norm": 0.4750470519065857, | |
| "learning_rate": 0.0002935387303436226, | |
| "loss": 3.185, | |
| "step": 87800 | |
| }, | |
| { | |
| "epoch": 25.567652538425712, | |
| "grad_norm": 0.4128108322620392, | |
| "learning_rate": 0.0002933640069889342, | |
| "loss": 3.1878, | |
| "step": 87850 | |
| }, | |
| { | |
| "epoch": 25.58220773171868, | |
| "grad_norm": 0.44352927803993225, | |
| "learning_rate": 0.0002931892836342457, | |
| "loss": 3.1862, | |
| "step": 87900 | |
| }, | |
| { | |
| "epoch": 25.596762925011646, | |
| "grad_norm": 0.4503888487815857, | |
| "learning_rate": 0.00029301456027955736, | |
| "loss": 3.1811, | |
| "step": 87950 | |
| }, | |
| { | |
| "epoch": 25.61131811830461, | |
| "grad_norm": 0.4366030991077423, | |
| "learning_rate": 0.0002928398369248689, | |
| "loss": 3.1899, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 25.61131811830461, | |
| "eval_accuracy": 0.3741774410803298, | |
| "eval_loss": 3.5432403087615967, | |
| "eval_runtime": 53.6173, | |
| "eval_samples_per_second": 310.553, | |
| "eval_steps_per_second": 19.415, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 25.625873311597577, | |
| "grad_norm": 0.4520089030265808, | |
| "learning_rate": 0.0002926651135701805, | |
| "loss": 3.1875, | |
| "step": 88050 | |
| }, | |
| { | |
| "epoch": 25.640428504890544, | |
| "grad_norm": 0.4355313777923584, | |
| "learning_rate": 0.00029249039021549215, | |
| "loss": 3.188, | |
| "step": 88100 | |
| }, | |
| { | |
| "epoch": 25.65498369818351, | |
| "grad_norm": 0.43428879976272583, | |
| "learning_rate": 0.0002923156668608037, | |
| "loss": 3.1906, | |
| "step": 88150 | |
| }, | |
| { | |
| "epoch": 25.669538891476478, | |
| "grad_norm": 0.42153266072273254, | |
| "learning_rate": 0.0002921409435061153, | |
| "loss": 3.1852, | |
| "step": 88200 | |
| }, | |
| { | |
| "epoch": 25.684094084769445, | |
| "grad_norm": 0.4120045602321625, | |
| "learning_rate": 0.0002919662201514269, | |
| "loss": 3.2086, | |
| "step": 88250 | |
| }, | |
| { | |
| "epoch": 25.698649278062412, | |
| "grad_norm": 0.42300277948379517, | |
| "learning_rate": 0.00029179149679673847, | |
| "loss": 3.2045, | |
| "step": 88300 | |
| }, | |
| { | |
| "epoch": 25.71320447135538, | |
| "grad_norm": 0.45498040318489075, | |
| "learning_rate": 0.00029161677344205007, | |
| "loss": 3.193, | |
| "step": 88350 | |
| }, | |
| { | |
| "epoch": 25.727759664648346, | |
| "grad_norm": 0.4161326587200165, | |
| "learning_rate": 0.00029144205008736166, | |
| "loss": 3.1974, | |
| "step": 88400 | |
| }, | |
| { | |
| "epoch": 25.742314857941313, | |
| "grad_norm": 0.432766318321228, | |
| "learning_rate": 0.00029126732673267325, | |
| "loss": 3.1929, | |
| "step": 88450 | |
| }, | |
| { | |
| "epoch": 25.75687005123428, | |
| "grad_norm": 0.4074766933917999, | |
| "learning_rate": 0.00029109260337798485, | |
| "loss": 3.1864, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 25.771425244527247, | |
| "grad_norm": 0.44380316138267517, | |
| "learning_rate": 0.00029091788002329644, | |
| "loss": 3.1923, | |
| "step": 88550 | |
| }, | |
| { | |
| "epoch": 25.785980437820214, | |
| "grad_norm": 0.4449799060821533, | |
| "learning_rate": 0.000290743156668608, | |
| "loss": 3.1955, | |
| "step": 88600 | |
| }, | |
| { | |
| "epoch": 25.80053563111318, | |
| "grad_norm": 0.4222467541694641, | |
| "learning_rate": 0.00029056843331391963, | |
| "loss": 3.2097, | |
| "step": 88650 | |
| }, | |
| { | |
| "epoch": 25.81509082440615, | |
| "grad_norm": 0.3985813558101654, | |
| "learning_rate": 0.00029039370995923117, | |
| "loss": 3.2012, | |
| "step": 88700 | |
| }, | |
| { | |
| "epoch": 25.829646017699115, | |
| "grad_norm": 0.42477717995643616, | |
| "learning_rate": 0.00029021898660454277, | |
| "loss": 3.1924, | |
| "step": 88750 | |
| }, | |
| { | |
| "epoch": 25.844201210992082, | |
| "grad_norm": 0.42123109102249146, | |
| "learning_rate": 0.00029004426324985436, | |
| "loss": 3.2033, | |
| "step": 88800 | |
| }, | |
| { | |
| "epoch": 25.85875640428505, | |
| "grad_norm": 0.43403467535972595, | |
| "learning_rate": 0.00028986953989516595, | |
| "loss": 3.1927, | |
| "step": 88850 | |
| }, | |
| { | |
| "epoch": 25.873311597578017, | |
| "grad_norm": 0.4367496073246002, | |
| "learning_rate": 0.00028969481654047755, | |
| "loss": 3.2034, | |
| "step": 88900 | |
| }, | |
| { | |
| "epoch": 25.887866790870984, | |
| "grad_norm": 0.4122547209262848, | |
| "learning_rate": 0.00028952009318578914, | |
| "loss": 3.2044, | |
| "step": 88950 | |
| }, | |
| { | |
| "epoch": 25.90242198416395, | |
| "grad_norm": 0.41581931710243225, | |
| "learning_rate": 0.00028934536983110074, | |
| "loss": 3.2043, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 25.90242198416395, | |
| "eval_accuracy": 0.37459195988652033, | |
| "eval_loss": 3.535562038421631, | |
| "eval_runtime": 53.6231, | |
| "eval_samples_per_second": 310.519, | |
| "eval_steps_per_second": 19.413, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 25.916977177456918, | |
| "grad_norm": 0.4250512421131134, | |
| "learning_rate": 0.00028917064647641233, | |
| "loss": 3.2125, | |
| "step": 89050 | |
| }, | |
| { | |
| "epoch": 25.931532370749885, | |
| "grad_norm": 0.41754457354545593, | |
| "learning_rate": 0.0002889959231217239, | |
| "loss": 3.2002, | |
| "step": 89100 | |
| }, | |
| { | |
| "epoch": 25.946087564042852, | |
| "grad_norm": 0.4195300340652466, | |
| "learning_rate": 0.0002888211997670355, | |
| "loss": 3.2145, | |
| "step": 89150 | |
| }, | |
| { | |
| "epoch": 25.96064275733582, | |
| "grad_norm": 0.4224066436290741, | |
| "learning_rate": 0.0002886464764123471, | |
| "loss": 3.2078, | |
| "step": 89200 | |
| }, | |
| { | |
| "epoch": 25.975197950628786, | |
| "grad_norm": 0.4162447154521942, | |
| "learning_rate": 0.0002884717530576587, | |
| "loss": 3.2191, | |
| "step": 89250 | |
| }, | |
| { | |
| "epoch": 25.989753143921753, | |
| "grad_norm": 0.44151467084884644, | |
| "learning_rate": 0.00028829702970297025, | |
| "loss": 3.2181, | |
| "step": 89300 | |
| }, | |
| { | |
| "epoch": 26.00407545412203, | |
| "grad_norm": 0.4168373942375183, | |
| "learning_rate": 0.0002881223063482819, | |
| "loss": 3.1621, | |
| "step": 89350 | |
| }, | |
| { | |
| "epoch": 26.018630647414998, | |
| "grad_norm": 0.43965691328048706, | |
| "learning_rate": 0.00028794758299359344, | |
| "loss": 3.1053, | |
| "step": 89400 | |
| }, | |
| { | |
| "epoch": 26.033185840707965, | |
| "grad_norm": 0.42053425312042236, | |
| "learning_rate": 0.00028777285963890503, | |
| "loss": 3.1095, | |
| "step": 89450 | |
| }, | |
| { | |
| "epoch": 26.047741034000932, | |
| "grad_norm": 0.4846605062484741, | |
| "learning_rate": 0.0002875981362842166, | |
| "loss": 3.1321, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 26.0622962272939, | |
| "grad_norm": 0.44881072640419006, | |
| "learning_rate": 0.0002874234129295282, | |
| "loss": 3.116, | |
| "step": 89550 | |
| }, | |
| { | |
| "epoch": 26.076851420586866, | |
| "grad_norm": 0.4315189719200134, | |
| "learning_rate": 0.0002872486895748398, | |
| "loss": 3.1167, | |
| "step": 89600 | |
| }, | |
| { | |
| "epoch": 26.091406613879833, | |
| "grad_norm": 0.4244035482406616, | |
| "learning_rate": 0.0002870739662201514, | |
| "loss": 3.1337, | |
| "step": 89650 | |
| }, | |
| { | |
| "epoch": 26.1059618071728, | |
| "grad_norm": 0.43683502078056335, | |
| "learning_rate": 0.000286899242865463, | |
| "loss": 3.1279, | |
| "step": 89700 | |
| }, | |
| { | |
| "epoch": 26.120517000465767, | |
| "grad_norm": 0.5049900412559509, | |
| "learning_rate": 0.0002867245195107746, | |
| "loss": 3.1357, | |
| "step": 89750 | |
| }, | |
| { | |
| "epoch": 26.135072193758734, | |
| "grad_norm": 0.41325217485427856, | |
| "learning_rate": 0.0002865497961560862, | |
| "loss": 3.1268, | |
| "step": 89800 | |
| }, | |
| { | |
| "epoch": 26.1496273870517, | |
| "grad_norm": 0.4585389494895935, | |
| "learning_rate": 0.00028637507280139773, | |
| "loss": 3.1342, | |
| "step": 89850 | |
| }, | |
| { | |
| "epoch": 26.16418258034467, | |
| "grad_norm": 0.42807942628860474, | |
| "learning_rate": 0.0002862003494467094, | |
| "loss": 3.1492, | |
| "step": 89900 | |
| }, | |
| { | |
| "epoch": 26.178737773637636, | |
| "grad_norm": 0.4196861684322357, | |
| "learning_rate": 0.0002860256260920209, | |
| "loss": 3.1376, | |
| "step": 89950 | |
| }, | |
| { | |
| "epoch": 26.1932929669306, | |
| "grad_norm": 0.45424550771713257, | |
| "learning_rate": 0.0002858509027373325, | |
| "loss": 3.1422, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 26.1932929669306, | |
| "eval_accuracy": 0.3737140309150876, | |
| "eval_loss": 3.552821636199951, | |
| "eval_runtime": 53.6612, | |
| "eval_samples_per_second": 310.299, | |
| "eval_steps_per_second": 19.399, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 26.207848160223566, | |
| "grad_norm": 0.4326604902744293, | |
| "learning_rate": 0.0002856761793826441, | |
| "loss": 3.1462, | |
| "step": 90050 | |
| }, | |
| { | |
| "epoch": 26.222403353516533, | |
| "grad_norm": 0.42881691455841064, | |
| "learning_rate": 0.0002855014560279557, | |
| "loss": 3.1398, | |
| "step": 90100 | |
| }, | |
| { | |
| "epoch": 26.2369585468095, | |
| "grad_norm": 0.45310184359550476, | |
| "learning_rate": 0.0002853267326732673, | |
| "loss": 3.1469, | |
| "step": 90150 | |
| }, | |
| { | |
| "epoch": 26.251513740102467, | |
| "grad_norm": 0.4321194291114807, | |
| "learning_rate": 0.0002851520093185789, | |
| "loss": 3.1533, | |
| "step": 90200 | |
| }, | |
| { | |
| "epoch": 26.266068933395434, | |
| "grad_norm": 0.42668119072914124, | |
| "learning_rate": 0.0002849772859638905, | |
| "loss": 3.1458, | |
| "step": 90250 | |
| }, | |
| { | |
| "epoch": 26.2806241266884, | |
| "grad_norm": 0.4372236430644989, | |
| "learning_rate": 0.0002848025626092021, | |
| "loss": 3.1534, | |
| "step": 90300 | |
| }, | |
| { | |
| "epoch": 26.29517931998137, | |
| "grad_norm": 0.4351506531238556, | |
| "learning_rate": 0.0002846278392545137, | |
| "loss": 3.1335, | |
| "step": 90350 | |
| }, | |
| { | |
| "epoch": 26.309734513274336, | |
| "grad_norm": 0.42932531237602234, | |
| "learning_rate": 0.00028445311589982527, | |
| "loss": 3.1511, | |
| "step": 90400 | |
| }, | |
| { | |
| "epoch": 26.324289706567303, | |
| "grad_norm": 0.4168093204498291, | |
| "learning_rate": 0.00028427839254513686, | |
| "loss": 3.1598, | |
| "step": 90450 | |
| }, | |
| { | |
| "epoch": 26.33884489986027, | |
| "grad_norm": 0.4465610682964325, | |
| "learning_rate": 0.00028410366919044846, | |
| "loss": 3.1572, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 26.353400093153237, | |
| "grad_norm": 0.39175668358802795, | |
| "learning_rate": 0.00028392894583576, | |
| "loss": 3.1501, | |
| "step": 90550 | |
| }, | |
| { | |
| "epoch": 26.367955286446204, | |
| "grad_norm": 0.4551820456981659, | |
| "learning_rate": 0.00028375422248107165, | |
| "loss": 3.1649, | |
| "step": 90600 | |
| }, | |
| { | |
| "epoch": 26.38251047973917, | |
| "grad_norm": 0.4309490919113159, | |
| "learning_rate": 0.0002835794991263832, | |
| "loss": 3.157, | |
| "step": 90650 | |
| }, | |
| { | |
| "epoch": 26.397065673032138, | |
| "grad_norm": 0.43560129404067993, | |
| "learning_rate": 0.0002834047757716948, | |
| "loss": 3.165, | |
| "step": 90700 | |
| }, | |
| { | |
| "epoch": 26.411620866325105, | |
| "grad_norm": 0.42708632349967957, | |
| "learning_rate": 0.0002832300524170064, | |
| "loss": 3.1684, | |
| "step": 90750 | |
| }, | |
| { | |
| "epoch": 26.426176059618072, | |
| "grad_norm": 0.44753795862197876, | |
| "learning_rate": 0.00028305532906231797, | |
| "loss": 3.1744, | |
| "step": 90800 | |
| }, | |
| { | |
| "epoch": 26.44073125291104, | |
| "grad_norm": 0.4203333854675293, | |
| "learning_rate": 0.00028288060570762956, | |
| "loss": 3.1605, | |
| "step": 90850 | |
| }, | |
| { | |
| "epoch": 26.455286446204006, | |
| "grad_norm": 0.44073015451431274, | |
| "learning_rate": 0.00028270588235294116, | |
| "loss": 3.1704, | |
| "step": 90900 | |
| }, | |
| { | |
| "epoch": 26.469841639496973, | |
| "grad_norm": 0.4535035192966461, | |
| "learning_rate": 0.00028253115899825275, | |
| "loss": 3.173, | |
| "step": 90950 | |
| }, | |
| { | |
| "epoch": 26.48439683278994, | |
| "grad_norm": 0.42050549387931824, | |
| "learning_rate": 0.0002823564356435643, | |
| "loss": 3.1717, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 26.48439683278994, | |
| "eval_accuracy": 0.37426394117711353, | |
| "eval_loss": 3.543433904647827, | |
| "eval_runtime": 53.7695, | |
| "eval_samples_per_second": 309.674, | |
| "eval_steps_per_second": 19.36, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 26.498952026082907, | |
| "grad_norm": 0.4306468069553375, | |
| "learning_rate": 0.00028218171228887594, | |
| "loss": 3.1803, | |
| "step": 91050 | |
| }, | |
| { | |
| "epoch": 26.513507219375875, | |
| "grad_norm": 0.4638393223285675, | |
| "learning_rate": 0.0002820069889341875, | |
| "loss": 3.1705, | |
| "step": 91100 | |
| }, | |
| { | |
| "epoch": 26.52806241266884, | |
| "grad_norm": 0.4407005310058594, | |
| "learning_rate": 0.00028183226557949913, | |
| "loss": 3.1608, | |
| "step": 91150 | |
| }, | |
| { | |
| "epoch": 26.54261760596181, | |
| "grad_norm": 0.45036381483078003, | |
| "learning_rate": 0.00028165754222481067, | |
| "loss": 3.1651, | |
| "step": 91200 | |
| }, | |
| { | |
| "epoch": 26.557172799254776, | |
| "grad_norm": 0.4661485254764557, | |
| "learning_rate": 0.00028148281887012226, | |
| "loss": 3.1758, | |
| "step": 91250 | |
| }, | |
| { | |
| "epoch": 26.571727992547743, | |
| "grad_norm": 0.43861135840415955, | |
| "learning_rate": 0.0002813080955154339, | |
| "loss": 3.1729, | |
| "step": 91300 | |
| }, | |
| { | |
| "epoch": 26.586283185840706, | |
| "grad_norm": 0.46360695362091064, | |
| "learning_rate": 0.00028113337216074545, | |
| "loss": 3.1679, | |
| "step": 91350 | |
| }, | |
| { | |
| "epoch": 26.600838379133673, | |
| "grad_norm": 0.4070718288421631, | |
| "learning_rate": 0.00028095864880605705, | |
| "loss": 3.1795, | |
| "step": 91400 | |
| }, | |
| { | |
| "epoch": 26.61539357242664, | |
| "grad_norm": 0.43112340569496155, | |
| "learning_rate": 0.00028078392545136864, | |
| "loss": 3.1757, | |
| "step": 91450 | |
| }, | |
| { | |
| "epoch": 26.629948765719607, | |
| "grad_norm": 0.4501616060733795, | |
| "learning_rate": 0.00028060920209668023, | |
| "loss": 3.1866, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 26.644503959012575, | |
| "grad_norm": 0.46513840556144714, | |
| "learning_rate": 0.00028043447874199183, | |
| "loss": 3.1803, | |
| "step": 91550 | |
| }, | |
| { | |
| "epoch": 26.65905915230554, | |
| "grad_norm": 0.44853127002716064, | |
| "learning_rate": 0.0002802597553873034, | |
| "loss": 3.1758, | |
| "step": 91600 | |
| }, | |
| { | |
| "epoch": 26.67361434559851, | |
| "grad_norm": 0.4104275405406952, | |
| "learning_rate": 0.000280085032032615, | |
| "loss": 3.1868, | |
| "step": 91650 | |
| }, | |
| { | |
| "epoch": 26.688169538891476, | |
| "grad_norm": 0.457682341337204, | |
| "learning_rate": 0.00027991030867792656, | |
| "loss": 3.1786, | |
| "step": 91700 | |
| }, | |
| { | |
| "epoch": 26.702724732184443, | |
| "grad_norm": 0.4594995677471161, | |
| "learning_rate": 0.0002797355853232382, | |
| "loss": 3.1812, | |
| "step": 91750 | |
| }, | |
| { | |
| "epoch": 26.71727992547741, | |
| "grad_norm": 0.4579601287841797, | |
| "learning_rate": 0.00027956086196854975, | |
| "loss": 3.1828, | |
| "step": 91800 | |
| }, | |
| { | |
| "epoch": 26.731835118770377, | |
| "grad_norm": 0.4153093099594116, | |
| "learning_rate": 0.0002793861386138614, | |
| "loss": 3.1804, | |
| "step": 91850 | |
| }, | |
| { | |
| "epoch": 26.746390312063344, | |
| "grad_norm": 0.449344277381897, | |
| "learning_rate": 0.00027921141525917293, | |
| "loss": 3.1917, | |
| "step": 91900 | |
| }, | |
| { | |
| "epoch": 26.76094550535631, | |
| "grad_norm": 0.44225794076919556, | |
| "learning_rate": 0.00027903669190448453, | |
| "loss": 3.1858, | |
| "step": 91950 | |
| }, | |
| { | |
| "epoch": 26.775500698649278, | |
| "grad_norm": 0.42417779564857483, | |
| "learning_rate": 0.0002788619685497961, | |
| "loss": 3.1882, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 26.775500698649278, | |
| "eval_accuracy": 0.3747240605778042, | |
| "eval_loss": 3.5393319129943848, | |
| "eval_runtime": 53.6987, | |
| "eval_samples_per_second": 310.082, | |
| "eval_steps_per_second": 19.386, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 26.790055891942245, | |
| "grad_norm": 0.4308387339115143, | |
| "learning_rate": 0.0002786872451951077, | |
| "loss": 3.2008, | |
| "step": 92050 | |
| }, | |
| { | |
| "epoch": 26.804611085235212, | |
| "grad_norm": 0.4665704667568207, | |
| "learning_rate": 0.0002785125218404193, | |
| "loss": 3.2025, | |
| "step": 92100 | |
| }, | |
| { | |
| "epoch": 26.81916627852818, | |
| "grad_norm": 0.42753684520721436, | |
| "learning_rate": 0.0002783377984857309, | |
| "loss": 3.1852, | |
| "step": 92150 | |
| }, | |
| { | |
| "epoch": 26.833721471821146, | |
| "grad_norm": 0.4062555134296417, | |
| "learning_rate": 0.0002781630751310425, | |
| "loss": 3.1923, | |
| "step": 92200 | |
| }, | |
| { | |
| "epoch": 26.848276665114113, | |
| "grad_norm": 0.48631173372268677, | |
| "learning_rate": 0.0002779883517763541, | |
| "loss": 3.1896, | |
| "step": 92250 | |
| }, | |
| { | |
| "epoch": 26.86283185840708, | |
| "grad_norm": 0.41390180587768555, | |
| "learning_rate": 0.0002778136284216657, | |
| "loss": 3.2031, | |
| "step": 92300 | |
| }, | |
| { | |
| "epoch": 26.877387051700047, | |
| "grad_norm": 0.4423968493938446, | |
| "learning_rate": 0.0002776389050669773, | |
| "loss": 3.187, | |
| "step": 92350 | |
| }, | |
| { | |
| "epoch": 26.891942244993015, | |
| "grad_norm": 0.43332940340042114, | |
| "learning_rate": 0.0002774641817122888, | |
| "loss": 3.187, | |
| "step": 92400 | |
| }, | |
| { | |
| "epoch": 26.90649743828598, | |
| "grad_norm": 0.4035518169403076, | |
| "learning_rate": 0.00027728945835760047, | |
| "loss": 3.1756, | |
| "step": 92450 | |
| }, | |
| { | |
| "epoch": 26.92105263157895, | |
| "grad_norm": 0.4539894759654999, | |
| "learning_rate": 0.000277114735002912, | |
| "loss": 3.1955, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 26.935607824871916, | |
| "grad_norm": 0.44463565945625305, | |
| "learning_rate": 0.00027694001164822366, | |
| "loss": 3.186, | |
| "step": 92550 | |
| }, | |
| { | |
| "epoch": 26.950163018164883, | |
| "grad_norm": 0.4479128122329712, | |
| "learning_rate": 0.0002767652882935352, | |
| "loss": 3.1924, | |
| "step": 92600 | |
| }, | |
| { | |
| "epoch": 26.96471821145785, | |
| "grad_norm": 0.4516030251979828, | |
| "learning_rate": 0.0002765905649388468, | |
| "loss": 3.2034, | |
| "step": 92650 | |
| }, | |
| { | |
| "epoch": 26.979273404750813, | |
| "grad_norm": 0.4199993908405304, | |
| "learning_rate": 0.0002764158415841584, | |
| "loss": 3.1925, | |
| "step": 92700 | |
| }, | |
| { | |
| "epoch": 26.99382859804378, | |
| "grad_norm": 0.437560498714447, | |
| "learning_rate": 0.00027624111822947, | |
| "loss": 3.2089, | |
| "step": 92750 | |
| }, | |
| { | |
| "epoch": 27.008150908244062, | |
| "grad_norm": 0.4369962513446808, | |
| "learning_rate": 0.0002760663948747816, | |
| "loss": 3.1441, | |
| "step": 92800 | |
| }, | |
| { | |
| "epoch": 27.02270610153703, | |
| "grad_norm": 0.4700404405593872, | |
| "learning_rate": 0.00027589167152009317, | |
| "loss": 3.1001, | |
| "step": 92850 | |
| }, | |
| { | |
| "epoch": 27.037261294829996, | |
| "grad_norm": 0.43609800934791565, | |
| "learning_rate": 0.00027571694816540477, | |
| "loss": 3.1069, | |
| "step": 92900 | |
| }, | |
| { | |
| "epoch": 27.051816488122963, | |
| "grad_norm": 0.40873023867607117, | |
| "learning_rate": 0.0002755422248107163, | |
| "loss": 3.0994, | |
| "step": 92950 | |
| }, | |
| { | |
| "epoch": 27.06637168141593, | |
| "grad_norm": 0.43277284502983093, | |
| "learning_rate": 0.00027536750145602795, | |
| "loss": 3.1051, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 27.06637168141593, | |
| "eval_accuracy": 0.37393698021345545, | |
| "eval_loss": 3.5548183917999268, | |
| "eval_runtime": 53.4964, | |
| "eval_samples_per_second": 311.254, | |
| "eval_steps_per_second": 19.459, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 27.080926874708897, | |
| "grad_norm": 0.43973806500434875, | |
| "learning_rate": 0.0002751927781013395, | |
| "loss": 3.1143, | |
| "step": 93050 | |
| }, | |
| { | |
| "epoch": 27.095482068001864, | |
| "grad_norm": 0.4374482333660126, | |
| "learning_rate": 0.0002750180547466511, | |
| "loss": 3.1115, | |
| "step": 93100 | |
| }, | |
| { | |
| "epoch": 27.11003726129483, | |
| "grad_norm": 0.43325090408325195, | |
| "learning_rate": 0.0002748433313919627, | |
| "loss": 3.1219, | |
| "step": 93150 | |
| }, | |
| { | |
| "epoch": 27.1245924545878, | |
| "grad_norm": 0.4514847993850708, | |
| "learning_rate": 0.0002746686080372743, | |
| "loss": 3.1166, | |
| "step": 93200 | |
| }, | |
| { | |
| "epoch": 27.139147647880765, | |
| "grad_norm": 0.45671555399894714, | |
| "learning_rate": 0.00027449388468258587, | |
| "loss": 3.1224, | |
| "step": 93250 | |
| }, | |
| { | |
| "epoch": 27.153702841173732, | |
| "grad_norm": 0.4461299777030945, | |
| "learning_rate": 0.00027431916132789747, | |
| "loss": 3.1108, | |
| "step": 93300 | |
| }, | |
| { | |
| "epoch": 27.168258034466696, | |
| "grad_norm": 0.4486783444881439, | |
| "learning_rate": 0.00027414443797320906, | |
| "loss": 3.142, | |
| "step": 93350 | |
| }, | |
| { | |
| "epoch": 27.182813227759663, | |
| "grad_norm": 0.48491784930229187, | |
| "learning_rate": 0.00027396971461852065, | |
| "loss": 3.1281, | |
| "step": 93400 | |
| }, | |
| { | |
| "epoch": 27.19736842105263, | |
| "grad_norm": 0.4203689694404602, | |
| "learning_rate": 0.00027379499126383225, | |
| "loss": 3.1402, | |
| "step": 93450 | |
| }, | |
| { | |
| "epoch": 27.211923614345597, | |
| "grad_norm": 0.4057740271091461, | |
| "learning_rate": 0.00027362026790914384, | |
| "loss": 3.1343, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 27.226478807638564, | |
| "grad_norm": 0.46938467025756836, | |
| "learning_rate": 0.00027344554455445544, | |
| "loss": 3.1498, | |
| "step": 93550 | |
| }, | |
| { | |
| "epoch": 27.24103400093153, | |
| "grad_norm": 0.44543612003326416, | |
| "learning_rate": 0.00027327082119976703, | |
| "loss": 3.1347, | |
| "step": 93600 | |
| }, | |
| { | |
| "epoch": 27.2555891942245, | |
| "grad_norm": 0.44882431626319885, | |
| "learning_rate": 0.00027309609784507857, | |
| "loss": 3.1386, | |
| "step": 93650 | |
| }, | |
| { | |
| "epoch": 27.270144387517465, | |
| "grad_norm": 0.4503701329231262, | |
| "learning_rate": 0.0002729213744903902, | |
| "loss": 3.1347, | |
| "step": 93700 | |
| }, | |
| { | |
| "epoch": 27.284699580810432, | |
| "grad_norm": 0.4397549033164978, | |
| "learning_rate": 0.00027274665113570176, | |
| "loss": 3.1393, | |
| "step": 93750 | |
| }, | |
| { | |
| "epoch": 27.2992547741034, | |
| "grad_norm": 0.43866729736328125, | |
| "learning_rate": 0.00027257192778101335, | |
| "loss": 3.1316, | |
| "step": 93800 | |
| }, | |
| { | |
| "epoch": 27.313809967396367, | |
| "grad_norm": 0.4700663387775421, | |
| "learning_rate": 0.00027239720442632495, | |
| "loss": 3.1607, | |
| "step": 93850 | |
| }, | |
| { | |
| "epoch": 27.328365160689334, | |
| "grad_norm": 0.43782612681388855, | |
| "learning_rate": 0.00027222248107163654, | |
| "loss": 3.1429, | |
| "step": 93900 | |
| }, | |
| { | |
| "epoch": 27.3429203539823, | |
| "grad_norm": 0.42867985367774963, | |
| "learning_rate": 0.00027204775771694814, | |
| "loss": 3.1405, | |
| "step": 93950 | |
| }, | |
| { | |
| "epoch": 27.357475547275268, | |
| "grad_norm": 0.4537684917449951, | |
| "learning_rate": 0.00027187303436225973, | |
| "loss": 3.1594, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 27.357475547275268, | |
| "eval_accuracy": 0.3744202524933124, | |
| "eval_loss": 3.5456807613372803, | |
| "eval_runtime": 53.5354, | |
| "eval_samples_per_second": 311.028, | |
| "eval_steps_per_second": 19.445, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 27.372030740568235, | |
| "grad_norm": 0.43250444531440735, | |
| "learning_rate": 0.0002716983110075713, | |
| "loss": 3.1573, | |
| "step": 94050 | |
| }, | |
| { | |
| "epoch": 27.386585933861202, | |
| "grad_norm": 0.4533463418483734, | |
| "learning_rate": 0.0002715235876528829, | |
| "loss": 3.1583, | |
| "step": 94100 | |
| }, | |
| { | |
| "epoch": 27.40114112715417, | |
| "grad_norm": 0.4333341419696808, | |
| "learning_rate": 0.0002713488642981945, | |
| "loss": 3.1601, | |
| "step": 94150 | |
| }, | |
| { | |
| "epoch": 27.415696320447136, | |
| "grad_norm": 0.4784789979457855, | |
| "learning_rate": 0.00027117414094350606, | |
| "loss": 3.1557, | |
| "step": 94200 | |
| }, | |
| { | |
| "epoch": 27.430251513740103, | |
| "grad_norm": 0.46767035126686096, | |
| "learning_rate": 0.0002709994175888177, | |
| "loss": 3.1603, | |
| "step": 94250 | |
| }, | |
| { | |
| "epoch": 27.44480670703307, | |
| "grad_norm": 0.4538698196411133, | |
| "learning_rate": 0.00027082469423412924, | |
| "loss": 3.1622, | |
| "step": 94300 | |
| }, | |
| { | |
| "epoch": 27.459361900326037, | |
| "grad_norm": 0.4671664535999298, | |
| "learning_rate": 0.00027064997087944084, | |
| "loss": 3.1461, | |
| "step": 94350 | |
| }, | |
| { | |
| "epoch": 27.473917093619004, | |
| "grad_norm": 0.44458189606666565, | |
| "learning_rate": 0.00027047524752475243, | |
| "loss": 3.1615, | |
| "step": 94400 | |
| }, | |
| { | |
| "epoch": 27.48847228691197, | |
| "grad_norm": 0.43016189336776733, | |
| "learning_rate": 0.000270300524170064, | |
| "loss": 3.1542, | |
| "step": 94450 | |
| }, | |
| { | |
| "epoch": 27.50302748020494, | |
| "grad_norm": 0.45877593755722046, | |
| "learning_rate": 0.0002701258008153757, | |
| "loss": 3.1684, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 27.517582673497905, | |
| "grad_norm": 0.43803977966308594, | |
| "learning_rate": 0.0002699510774606872, | |
| "loss": 3.1711, | |
| "step": 94550 | |
| }, | |
| { | |
| "epoch": 27.532137866790872, | |
| "grad_norm": 0.419470876455307, | |
| "learning_rate": 0.0002697763541059988, | |
| "loss": 3.1622, | |
| "step": 94600 | |
| }, | |
| { | |
| "epoch": 27.54669306008384, | |
| "grad_norm": 0.4280085265636444, | |
| "learning_rate": 0.0002696016307513104, | |
| "loss": 3.1558, | |
| "step": 94650 | |
| }, | |
| { | |
| "epoch": 27.561248253376803, | |
| "grad_norm": 0.4552350640296936, | |
| "learning_rate": 0.000269426907396622, | |
| "loss": 3.1543, | |
| "step": 94700 | |
| }, | |
| { | |
| "epoch": 27.57580344666977, | |
| "grad_norm": 0.44216257333755493, | |
| "learning_rate": 0.0002692521840419336, | |
| "loss": 3.1724, | |
| "step": 94750 | |
| }, | |
| { | |
| "epoch": 27.590358639962737, | |
| "grad_norm": 0.4339045286178589, | |
| "learning_rate": 0.0002690774606872452, | |
| "loss": 3.1669, | |
| "step": 94800 | |
| }, | |
| { | |
| "epoch": 27.604913833255704, | |
| "grad_norm": 0.44733309745788574, | |
| "learning_rate": 0.0002689027373325568, | |
| "loss": 3.1664, | |
| "step": 94850 | |
| }, | |
| { | |
| "epoch": 27.61946902654867, | |
| "grad_norm": 0.4487958252429962, | |
| "learning_rate": 0.0002687280139778683, | |
| "loss": 3.1747, | |
| "step": 94900 | |
| }, | |
| { | |
| "epoch": 27.63402421984164, | |
| "grad_norm": 0.43804869055747986, | |
| "learning_rate": 0.00026855329062317997, | |
| "loss": 3.1666, | |
| "step": 94950 | |
| }, | |
| { | |
| "epoch": 27.648579413134605, | |
| "grad_norm": 0.4367426931858063, | |
| "learning_rate": 0.0002683785672684915, | |
| "loss": 3.168, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 27.648579413134605, | |
| "eval_accuracy": 0.37467822492869324, | |
| "eval_loss": 3.544126033782959, | |
| "eval_runtime": 53.5555, | |
| "eval_samples_per_second": 310.911, | |
| "eval_steps_per_second": 19.438, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 27.663134606427572, | |
| "grad_norm": 0.47739312052726746, | |
| "learning_rate": 0.0002682038439138031, | |
| "loss": 3.182, | |
| "step": 95050 | |
| }, | |
| { | |
| "epoch": 27.67768979972054, | |
| "grad_norm": 0.45261552929878235, | |
| "learning_rate": 0.0002680291205591147, | |
| "loss": 3.1821, | |
| "step": 95100 | |
| }, | |
| { | |
| "epoch": 27.692244993013507, | |
| "grad_norm": 0.4462185502052307, | |
| "learning_rate": 0.0002678543972044263, | |
| "loss": 3.1661, | |
| "step": 95150 | |
| }, | |
| { | |
| "epoch": 27.706800186306474, | |
| "grad_norm": 0.43977272510528564, | |
| "learning_rate": 0.0002676796738497379, | |
| "loss": 3.1788, | |
| "step": 95200 | |
| }, | |
| { | |
| "epoch": 27.72135537959944, | |
| "grad_norm": 0.44454291462898254, | |
| "learning_rate": 0.0002675049504950495, | |
| "loss": 3.1668, | |
| "step": 95250 | |
| }, | |
| { | |
| "epoch": 27.735910572892408, | |
| "grad_norm": 0.43140122294425964, | |
| "learning_rate": 0.0002673302271403611, | |
| "loss": 3.1874, | |
| "step": 95300 | |
| }, | |
| { | |
| "epoch": 27.750465766185375, | |
| "grad_norm": 0.4258497357368469, | |
| "learning_rate": 0.00026715550378567267, | |
| "loss": 3.1779, | |
| "step": 95350 | |
| }, | |
| { | |
| "epoch": 27.765020959478342, | |
| "grad_norm": 0.46175652742385864, | |
| "learning_rate": 0.00026698078043098426, | |
| "loss": 3.1765, | |
| "step": 95400 | |
| }, | |
| { | |
| "epoch": 27.77957615277131, | |
| "grad_norm": 0.43039289116859436, | |
| "learning_rate": 0.00026680605707629586, | |
| "loss": 3.1772, | |
| "step": 95450 | |
| }, | |
| { | |
| "epoch": 27.794131346064276, | |
| "grad_norm": 0.41723737120628357, | |
| "learning_rate": 0.00026663133372160745, | |
| "loss": 3.1793, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 27.808686539357243, | |
| "grad_norm": 0.46801409125328064, | |
| "learning_rate": 0.00026645661036691905, | |
| "loss": 3.1702, | |
| "step": 95550 | |
| }, | |
| { | |
| "epoch": 27.82324173265021, | |
| "grad_norm": 0.4733223617076874, | |
| "learning_rate": 0.0002662818870122306, | |
| "loss": 3.1828, | |
| "step": 95600 | |
| }, | |
| { | |
| "epoch": 27.837796925943177, | |
| "grad_norm": 0.43480008840560913, | |
| "learning_rate": 0.00026610716365754224, | |
| "loss": 3.1862, | |
| "step": 95650 | |
| }, | |
| { | |
| "epoch": 27.852352119236144, | |
| "grad_norm": 0.4450317919254303, | |
| "learning_rate": 0.0002659324403028538, | |
| "loss": 3.1737, | |
| "step": 95700 | |
| }, | |
| { | |
| "epoch": 27.86690731252911, | |
| "grad_norm": 0.43006742000579834, | |
| "learning_rate": 0.00026575771694816537, | |
| "loss": 3.1909, | |
| "step": 95750 | |
| }, | |
| { | |
| "epoch": 27.88146250582208, | |
| "grad_norm": 0.4653988182544708, | |
| "learning_rate": 0.00026558299359347696, | |
| "loss": 3.196, | |
| "step": 95800 | |
| }, | |
| { | |
| "epoch": 27.896017699115045, | |
| "grad_norm": 0.41280511021614075, | |
| "learning_rate": 0.00026540827023878856, | |
| "loss": 3.1951, | |
| "step": 95850 | |
| }, | |
| { | |
| "epoch": 27.910572892408013, | |
| "grad_norm": 0.43786656856536865, | |
| "learning_rate": 0.00026523354688410015, | |
| "loss": 3.1828, | |
| "step": 95900 | |
| }, | |
| { | |
| "epoch": 27.92512808570098, | |
| "grad_norm": 0.45567384362220764, | |
| "learning_rate": 0.00026505882352941175, | |
| "loss": 3.1773, | |
| "step": 95950 | |
| }, | |
| { | |
| "epoch": 27.939683278993947, | |
| "grad_norm": 0.45088210701942444, | |
| "learning_rate": 0.00026488410017472334, | |
| "loss": 3.1803, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 27.939683278993947, | |
| "eval_accuracy": 0.37466870521695483, | |
| "eval_loss": 3.5346882343292236, | |
| "eval_runtime": 53.6516, | |
| "eval_samples_per_second": 310.354, | |
| "eval_steps_per_second": 19.403, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 27.95423847228691, | |
| "grad_norm": 0.4410727024078369, | |
| "learning_rate": 0.00026470937682003494, | |
| "loss": 3.1821, | |
| "step": 96050 | |
| }, | |
| { | |
| "epoch": 27.968793665579877, | |
| "grad_norm": 0.43434426188468933, | |
| "learning_rate": 0.00026453465346534653, | |
| "loss": 3.1932, | |
| "step": 96100 | |
| }, | |
| { | |
| "epoch": 27.983348858872844, | |
| "grad_norm": 0.4693484902381897, | |
| "learning_rate": 0.00026435993011065807, | |
| "loss": 3.1892, | |
| "step": 96150 | |
| }, | |
| { | |
| "epoch": 27.99790405216581, | |
| "grad_norm": 0.4658077359199524, | |
| "learning_rate": 0.0002641852067559697, | |
| "loss": 3.2025, | |
| "step": 96200 | |
| }, | |
| { | |
| "epoch": 28.012226362366093, | |
| "grad_norm": 0.4529211223125458, | |
| "learning_rate": 0.00026401048340128126, | |
| "loss": 3.1034, | |
| "step": 96250 | |
| }, | |
| { | |
| "epoch": 28.02678155565906, | |
| "grad_norm": 0.45847851037979126, | |
| "learning_rate": 0.00026383576004659285, | |
| "loss": 3.0865, | |
| "step": 96300 | |
| }, | |
| { | |
| "epoch": 28.041336748952027, | |
| "grad_norm": 0.4646276831626892, | |
| "learning_rate": 0.00026366103669190445, | |
| "loss": 3.0928, | |
| "step": 96350 | |
| }, | |
| { | |
| "epoch": 28.055891942244994, | |
| "grad_norm": 0.4562079906463623, | |
| "learning_rate": 0.00026348631333721604, | |
| "loss": 3.1026, | |
| "step": 96400 | |
| }, | |
| { | |
| "epoch": 28.07044713553796, | |
| "grad_norm": 0.4497821629047394, | |
| "learning_rate": 0.00026331158998252764, | |
| "loss": 3.1054, | |
| "step": 96450 | |
| }, | |
| { | |
| "epoch": 28.085002328830928, | |
| "grad_norm": 0.4543379247188568, | |
| "learning_rate": 0.00026313686662783923, | |
| "loss": 3.1083, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 28.099557522123895, | |
| "grad_norm": 0.434215784072876, | |
| "learning_rate": 0.0002629621432731508, | |
| "loss": 3.1095, | |
| "step": 96550 | |
| }, | |
| { | |
| "epoch": 28.114112715416862, | |
| "grad_norm": 0.4451253414154053, | |
| "learning_rate": 0.0002627874199184624, | |
| "loss": 3.1078, | |
| "step": 96600 | |
| }, | |
| { | |
| "epoch": 28.12866790870983, | |
| "grad_norm": 0.44648224115371704, | |
| "learning_rate": 0.000262612696563774, | |
| "loss": 3.1237, | |
| "step": 96650 | |
| }, | |
| { | |
| "epoch": 28.143223102002796, | |
| "grad_norm": 0.42843908071517944, | |
| "learning_rate": 0.0002624379732090856, | |
| "loss": 3.1049, | |
| "step": 96700 | |
| }, | |
| { | |
| "epoch": 28.15777829529576, | |
| "grad_norm": 0.4594564139842987, | |
| "learning_rate": 0.0002622632498543972, | |
| "loss": 3.1266, | |
| "step": 96750 | |
| }, | |
| { | |
| "epoch": 28.172333488588727, | |
| "grad_norm": 0.46885013580322266, | |
| "learning_rate": 0.0002620885264997088, | |
| "loss": 3.1247, | |
| "step": 96800 | |
| }, | |
| { | |
| "epoch": 28.186888681881694, | |
| "grad_norm": 0.4439263343811035, | |
| "learning_rate": 0.00026191380314502034, | |
| "loss": 3.1399, | |
| "step": 96850 | |
| }, | |
| { | |
| "epoch": 28.20144387517466, | |
| "grad_norm": 0.44049715995788574, | |
| "learning_rate": 0.000261739079790332, | |
| "loss": 3.1181, | |
| "step": 96900 | |
| }, | |
| { | |
| "epoch": 28.215999068467628, | |
| "grad_norm": 0.4559531807899475, | |
| "learning_rate": 0.0002615643564356435, | |
| "loss": 3.1221, | |
| "step": 96950 | |
| }, | |
| { | |
| "epoch": 28.230554261760595, | |
| "grad_norm": 0.4322149455547333, | |
| "learning_rate": 0.0002613896330809551, | |
| "loss": 3.1195, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 28.230554261760595, | |
| "eval_accuracy": 0.3744060316893575, | |
| "eval_loss": 3.5524556636810303, | |
| "eval_runtime": 53.5295, | |
| "eval_samples_per_second": 311.062, | |
| "eval_steps_per_second": 19.447, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 28.245109455053562, | |
| "grad_norm": 0.4650440812110901, | |
| "learning_rate": 0.0002612149097262667, | |
| "loss": 3.1229, | |
| "step": 97050 | |
| }, | |
| { | |
| "epoch": 28.25966464834653, | |
| "grad_norm": 0.48387694358825684, | |
| "learning_rate": 0.0002610401863715783, | |
| "loss": 3.1259, | |
| "step": 97100 | |
| }, | |
| { | |
| "epoch": 28.274219841639496, | |
| "grad_norm": 0.4855106472969055, | |
| "learning_rate": 0.0002608654630168899, | |
| "loss": 3.1342, | |
| "step": 97150 | |
| }, | |
| { | |
| "epoch": 28.288775034932463, | |
| "grad_norm": 0.4329018294811249, | |
| "learning_rate": 0.0002606907396622015, | |
| "loss": 3.1279, | |
| "step": 97200 | |
| }, | |
| { | |
| "epoch": 28.30333022822543, | |
| "grad_norm": 0.4279111623764038, | |
| "learning_rate": 0.0002605160163075131, | |
| "loss": 3.1463, | |
| "step": 97250 | |
| }, | |
| { | |
| "epoch": 28.317885421518397, | |
| "grad_norm": 0.4886746406555176, | |
| "learning_rate": 0.0002603412929528247, | |
| "loss": 3.1277, | |
| "step": 97300 | |
| }, | |
| { | |
| "epoch": 28.332440614811365, | |
| "grad_norm": 0.44445788860321045, | |
| "learning_rate": 0.0002601665695981363, | |
| "loss": 3.1382, | |
| "step": 97350 | |
| }, | |
| { | |
| "epoch": 28.34699580810433, | |
| "grad_norm": 0.4592202305793762, | |
| "learning_rate": 0.0002599918462434478, | |
| "loss": 3.1411, | |
| "step": 97400 | |
| }, | |
| { | |
| "epoch": 28.3615510013973, | |
| "grad_norm": 0.4419022798538208, | |
| "learning_rate": 0.00025981712288875947, | |
| "loss": 3.1488, | |
| "step": 97450 | |
| }, | |
| { | |
| "epoch": 28.376106194690266, | |
| "grad_norm": 0.4636155664920807, | |
| "learning_rate": 0.000259642399534071, | |
| "loss": 3.1472, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 28.390661387983233, | |
| "grad_norm": 0.43500280380249023, | |
| "learning_rate": 0.0002594676761793826, | |
| "loss": 3.144, | |
| "step": 97550 | |
| }, | |
| { | |
| "epoch": 28.4052165812762, | |
| "grad_norm": 0.47602471709251404, | |
| "learning_rate": 0.0002592929528246942, | |
| "loss": 3.1556, | |
| "step": 97600 | |
| }, | |
| { | |
| "epoch": 28.419771774569167, | |
| "grad_norm": 0.44774195551872253, | |
| "learning_rate": 0.0002591182294700058, | |
| "loss": 3.1535, | |
| "step": 97650 | |
| }, | |
| { | |
| "epoch": 28.434326967862134, | |
| "grad_norm": 0.45153942704200745, | |
| "learning_rate": 0.0002589435061153174, | |
| "loss": 3.1506, | |
| "step": 97700 | |
| }, | |
| { | |
| "epoch": 28.4488821611551, | |
| "grad_norm": 0.46956953406333923, | |
| "learning_rate": 0.000258768782760629, | |
| "loss": 3.1444, | |
| "step": 97750 | |
| }, | |
| { | |
| "epoch": 28.463437354448068, | |
| "grad_norm": 0.469913512468338, | |
| "learning_rate": 0.0002585940594059406, | |
| "loss": 3.1482, | |
| "step": 97800 | |
| }, | |
| { | |
| "epoch": 28.477992547741035, | |
| "grad_norm": 0.4754005968570709, | |
| "learning_rate": 0.00025841933605125217, | |
| "loss": 3.1563, | |
| "step": 97850 | |
| }, | |
| { | |
| "epoch": 28.492547741034002, | |
| "grad_norm": 0.4373231530189514, | |
| "learning_rate": 0.00025824461269656376, | |
| "loss": 3.1569, | |
| "step": 97900 | |
| }, | |
| { | |
| "epoch": 28.50710293432697, | |
| "grad_norm": 0.44589629769325256, | |
| "learning_rate": 0.00025806988934187536, | |
| "loss": 3.1433, | |
| "step": 97950 | |
| }, | |
| { | |
| "epoch": 28.521658127619936, | |
| "grad_norm": 0.4373462200164795, | |
| "learning_rate": 0.00025789516598718695, | |
| "loss": 3.1487, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 28.521658127619936, | |
| "eval_accuracy": 0.3745458891827986, | |
| "eval_loss": 3.542678117752075, | |
| "eval_runtime": 53.5166, | |
| "eval_samples_per_second": 311.137, | |
| "eval_steps_per_second": 19.452, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 28.536213320912903, | |
| "grad_norm": 0.4420069456100464, | |
| "learning_rate": 0.00025772044263249854, | |
| "loss": 3.1466, | |
| "step": 98050 | |
| }, | |
| { | |
| "epoch": 28.55076851420587, | |
| "grad_norm": 0.49999868869781494, | |
| "learning_rate": 0.0002575457192778101, | |
| "loss": 3.1607, | |
| "step": 98100 | |
| }, | |
| { | |
| "epoch": 28.565323707498834, | |
| "grad_norm": 0.45186087489128113, | |
| "learning_rate": 0.00025737099592312173, | |
| "loss": 3.1536, | |
| "step": 98150 | |
| }, | |
| { | |
| "epoch": 28.5798789007918, | |
| "grad_norm": 0.4375789761543274, | |
| "learning_rate": 0.0002571962725684333, | |
| "loss": 3.1451, | |
| "step": 98200 | |
| }, | |
| { | |
| "epoch": 28.594434094084768, | |
| "grad_norm": 0.4431735873222351, | |
| "learning_rate": 0.00025702154921374487, | |
| "loss": 3.1616, | |
| "step": 98250 | |
| }, | |
| { | |
| "epoch": 28.608989287377735, | |
| "grad_norm": 0.43172794580459595, | |
| "learning_rate": 0.00025684682585905646, | |
| "loss": 3.1524, | |
| "step": 98300 | |
| }, | |
| { | |
| "epoch": 28.623544480670702, | |
| "grad_norm": 0.48056942224502563, | |
| "learning_rate": 0.00025667210250436806, | |
| "loss": 3.1584, | |
| "step": 98350 | |
| }, | |
| { | |
| "epoch": 28.63809967396367, | |
| "grad_norm": 0.44568321108818054, | |
| "learning_rate": 0.00025649737914967965, | |
| "loss": 3.1681, | |
| "step": 98400 | |
| }, | |
| { | |
| "epoch": 28.652654867256636, | |
| "grad_norm": 0.4867875277996063, | |
| "learning_rate": 0.00025632265579499124, | |
| "loss": 3.1603, | |
| "step": 98450 | |
| }, | |
| { | |
| "epoch": 28.667210060549603, | |
| "grad_norm": 0.4730188250541687, | |
| "learning_rate": 0.00025614793244030284, | |
| "loss": 3.1713, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 28.68176525384257, | |
| "grad_norm": 0.44978052377700806, | |
| "learning_rate": 0.0002559732090856144, | |
| "loss": 3.1576, | |
| "step": 98550 | |
| }, | |
| { | |
| "epoch": 28.696320447135538, | |
| "grad_norm": 0.4637473225593567, | |
| "learning_rate": 0.00025579848573092603, | |
| "loss": 3.1738, | |
| "step": 98600 | |
| }, | |
| { | |
| "epoch": 28.710875640428505, | |
| "grad_norm": 0.4374428689479828, | |
| "learning_rate": 0.0002556237623762376, | |
| "loss": 3.1602, | |
| "step": 98650 | |
| }, | |
| { | |
| "epoch": 28.72543083372147, | |
| "grad_norm": 0.47962844371795654, | |
| "learning_rate": 0.0002554490390215492, | |
| "loss": 3.1735, | |
| "step": 98700 | |
| }, | |
| { | |
| "epoch": 28.73998602701444, | |
| "grad_norm": 0.48206692934036255, | |
| "learning_rate": 0.0002552743156668608, | |
| "loss": 3.1676, | |
| "step": 98750 | |
| }, | |
| { | |
| "epoch": 28.754541220307406, | |
| "grad_norm": 0.44927337765693665, | |
| "learning_rate": 0.00025509959231217235, | |
| "loss": 3.1618, | |
| "step": 98800 | |
| }, | |
| { | |
| "epoch": 28.769096413600373, | |
| "grad_norm": 0.5087392926216125, | |
| "learning_rate": 0.000254924868957484, | |
| "loss": 3.1736, | |
| "step": 98850 | |
| }, | |
| { | |
| "epoch": 28.78365160689334, | |
| "grad_norm": 0.4800972640514374, | |
| "learning_rate": 0.00025475014560279554, | |
| "loss": 3.1702, | |
| "step": 98900 | |
| }, | |
| { | |
| "epoch": 28.798206800186307, | |
| "grad_norm": 0.4333168566226959, | |
| "learning_rate": 0.00025457542224810713, | |
| "loss": 3.1868, | |
| "step": 98950 | |
| }, | |
| { | |
| "epoch": 28.812761993479274, | |
| "grad_norm": 0.45487380027770996, | |
| "learning_rate": 0.00025440069889341873, | |
| "loss": 3.1746, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 28.812761993479274, | |
| "eval_accuracy": 0.3751652580823234, | |
| "eval_loss": 3.5361626148223877, | |
| "eval_runtime": 53.729, | |
| "eval_samples_per_second": 309.907, | |
| "eval_steps_per_second": 19.375, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 28.812761993479274, | |
| "step": 99000, | |
| "total_flos": 2.068898812526592e+18, | |
| "train_loss": 3.3939504055447047, | |
| "train_runtime": 44109.3766, | |
| "train_samples_per_second": 311.506, | |
| "train_steps_per_second": 3.895 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 171800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 20, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 11 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.068898812526592e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |