IsRoBERTa / log_history.json
system's picture
system HF staff
Update log_history.json
a51b180
[
{
"loss": 8.221125,
"learning_rate": 4.977302440441604e-05,
"epoch": 0.004539511911679256,
"total_flos": 1534078999360512,
"step": 500
},
{
"loss": 7.613228515625,
"learning_rate": 4.9546048808832074e-05,
"epoch": 0.009079023823358512,
"total_flos": 3066979584402432,
"step": 1000
},
{
"loss": 7.3869140625,
"learning_rate": 4.931907321324811e-05,
"epoch": 0.01361853573503777,
"total_flos": 4595094364354560,
"step": 1500
},
{
"loss": 7.200509765625,
"learning_rate": 4.909209761766415e-05,
"epoch": 0.018158047646717024,
"total_flos": 6127634210319360,
"step": 2000
},
{
"loss": 7.10742578125,
"learning_rate": 4.886512202208019e-05,
"epoch": 0.02269755955839628,
"total_flos": 7662338490746880,
"step": 2500
},
{
"loss": 6.98366796875,
"learning_rate": 4.8638146426496224e-05,
"epoch": 0.02723707147007554,
"total_flos": 9193050592054272,
"step": 3000
},
{
"loss": 6.89792578125,
"learning_rate": 4.841117083091226e-05,
"epoch": 0.03177658338175479,
"total_flos": 10724748713505792,
"step": 3500
},
{
"loss": 6.84346875,
"learning_rate": 4.81841952353283e-05,
"epoch": 0.03631609529343405,
"total_flos": 12256855672578048,
"step": 4000
},
{
"loss": 6.70800390625,
"learning_rate": 4.795721963974434e-05,
"epoch": 0.0408556072051133,
"total_flos": 13787471576798208,
"step": 4500
},
{
"loss": 6.61594140625,
"learning_rate": 4.7730244044160374e-05,
"epoch": 0.04539511911679256,
"total_flos": 15318303924464640,
"step": 5000
},
{
"loss": 6.4896953125,
"learning_rate": 4.750326844857641e-05,
"epoch": 0.049934631028471815,
"total_flos": 16850747573342208,
"step": 5500
},
{
"loss": 6.3819609375,
"learning_rate": 4.7276292852992446e-05,
"epoch": 0.05447414294015108,
"total_flos": 18381291329746944,
"step": 6000
},
{
"loss": 6.242921875,
"learning_rate": 4.7049317257408485e-05,
"epoch": 0.059013654851830334,
"total_flos": 19910728819648512,
"step": 6500
},
{
"loss": 6.1153828125,
"learning_rate": 4.682234166182452e-05,
"epoch": 0.06355316676350958,
"total_flos": 21443990143767552,
"step": 7000
},
{
"loss": 6.03621875,
"learning_rate": 4.6595366066240556e-05,
"epoch": 0.06809267867518884,
"total_flos": 22974990836336640,
"step": 7500
},
{
"loss": 5.920453125,
"learning_rate": 4.6368390470656596e-05,
"epoch": 0.0726321905868681,
"total_flos": 24509574870405120,
"step": 8000
},
{
"loss": 5.7900625,
"learning_rate": 4.6141414875072635e-05,
"epoch": 0.07717170249854735,
"total_flos": 26041994470010880,
"step": 8500
},
{
"loss": 5.6957890625,
"learning_rate": 4.591443927948867e-05,
"epoch": 0.0817112144102266,
"total_flos": 27574606463791104,
"step": 9000
},
{
"loss": 5.611875,
"learning_rate": 4.5687463683904706e-05,
"epoch": 0.08625072632190586,
"total_flos": 29103514869712896,
"step": 9500
},
{
"loss": 5.5246484375,
"learning_rate": 4.5460488088320745e-05,
"epoch": 0.09079023823358512,
"total_flos": 30636247109852160,
"step": 10000
},
{
"loss": 5.417921875,
"learning_rate": 4.5233512492736785e-05,
"epoch": 0.09532975014526437,
"total_flos": 32167800935672832,
"step": 10500
},
{
"loss": 5.356875,
"learning_rate": 4.500653689715282e-05,
"epoch": 0.09986926205694363,
"total_flos": 33702120427751424,
"step": 11000
},
{
"loss": 5.248140625,
"learning_rate": 4.4779561301568856e-05,
"epoch": 0.1044087739686229,
"total_flos": 35233578056484864,
"step": 11500
},
{
"loss": 5.219984375,
"learning_rate": 4.4552585705984895e-05,
"epoch": 0.10894828588030216,
"total_flos": 36765228079392768,
"step": 12000
},
{
"loss": 5.129609375,
"learning_rate": 4.4325610110400935e-05,
"epoch": 0.11348779779198141,
"total_flos": 38297816023901184,
"step": 12500
},
{
"loss": 5.08884375,
"learning_rate": 4.409863451481697e-05,
"epoch": 0.11802730970366067,
"total_flos": 39827782597782528,
"step": 13000
},
{
"loss": 5.06709375,
"learning_rate": 4.3871658919233006e-05,
"epoch": 0.12256682161533992,
"total_flos": 41360995823357952,
"step": 13500
},
{
"loss": 4.992921875,
"learning_rate": 4.3644683323649045e-05,
"epoch": 0.12710633352701917,
"total_flos": 42891299087044608,
"step": 14000
},
{
"loss": 4.955390625,
"learning_rate": 4.3417707728065085e-05,
"epoch": 0.13164584543869842,
"total_flos": 44422756715778048,
"step": 14500
},
{
"loss": 4.915578125,
"learning_rate": 4.319073213248112e-05,
"epoch": 0.13618535735037768,
"total_flos": 45955392758830080,
"step": 15000
},
{
"loss": 4.83159375,
"learning_rate": 4.2963756536897156e-05,
"epoch": 0.14072486926205693,
"total_flos": 47487668062804992,
"step": 15500
},
{
"loss": 4.842171875,
"learning_rate": 4.2736780941313195e-05,
"epoch": 0.1452643811737362,
"total_flos": 49018356114840576,
"step": 16000
},
{
"loss": 4.789875,
"learning_rate": 4.250980534572923e-05,
"epoch": 0.14980389308541545,
"total_flos": 50547168323675136,
"step": 16500
},
{
"loss": 4.773703125,
"learning_rate": 4.228282975014527e-05,
"epoch": 0.1543434049970947,
"total_flos": 52076846306294784,
"step": 17000
},
{
"loss": 4.713765625,
"learning_rate": 4.20558541545613e-05,
"epoch": 0.15888291690877396,
"total_flos": 53608448230659072,
"step": 17500
},
{
"loss": 4.704203125,
"learning_rate": 4.182887855897734e-05,
"epoch": 0.1634224288204532,
"total_flos": 55139160331966464,
"step": 18000
},
{
"loss": 4.666015625,
"learning_rate": 4.160190296339338e-05,
"epoch": 0.16796194073213247,
"total_flos": 56672445705357312,
"step": 18500
},
{
"loss": 4.6343125,
"learning_rate": 4.137492736780941e-05,
"epoch": 0.17250145264381173,
"total_flos": 58205875374379008,
"step": 19000
},
{
"loss": 4.595625,
"learning_rate": 4.114795177222545e-05,
"epoch": 0.17704096455549098,
"total_flos": 59740627753350144,
"step": 19500
},
{
"loss": 4.544984375,
"learning_rate": 4.092097617664149e-05,
"epoch": 0.18158047646717024,
"total_flos": 61268598237671424,
"step": 20000
},
{
"loss": 4.53390625,
"learning_rate": 4.069400058105753e-05,
"epoch": 0.1861199883788495,
"total_flos": 62799502733153280,
"step": 20500
},
{
"loss": 4.511140625,
"learning_rate": 4.046702498547356e-05,
"epoch": 0.19065950029052875,
"total_flos": 64333870323775488,
"step": 21000
},
{
"loss": 4.49559375,
"learning_rate": 4.02400493898896e-05,
"epoch": 0.195199012202208,
"total_flos": 65865183656878080,
"step": 21500
},
{
"loss": 4.464828125,
"learning_rate": 4.001307379430564e-05,
"epoch": 0.19973852411388726,
"total_flos": 67398517128812544,
"step": 22000
},
{
"loss": 4.4189375,
"learning_rate": 3.978609819872168e-05,
"epoch": 0.20427803602556652,
"total_flos": 68930359545894912,
"step": 22500
},
{
"loss": 4.41446875,
"learning_rate": 3.955912260313771e-05,
"epoch": 0.2088175479372458,
"total_flos": 70460855203756032,
"step": 23000
},
{
"loss": 4.362109375,
"learning_rate": 3.933214700755375e-05,
"epoch": 0.21335705984892506,
"total_flos": 71991879945596928,
"step": 23500
},
{
"loss": 4.349375,
"learning_rate": 3.910517141196979e-05,
"epoch": 0.2178965717606043,
"total_flos": 73525550107336704,
"step": 24000
},
{
"loss": 4.3429375,
"learning_rate": 3.887819581638583e-05,
"epoch": 0.22243608367228357,
"total_flos": 75056911538982912,
"step": 24500
},
{
"loss": 4.29459375,
"learning_rate": 3.865122022080186e-05,
"epoch": 0.22697559558396282,
"total_flos": 76589595680578560,
"step": 25000
},
{
"loss": 4.31003125,
"learning_rate": 3.84242446252179e-05,
"epoch": 0.23151510749564208,
"total_flos": 78121606442563584,
"step": 25500
},
{
"loss": 4.278125,
"learning_rate": 3.819726902963394e-05,
"epoch": 0.23605461940732134,
"total_flos": 79651645164260352,
"step": 26000
},
{
"loss": 4.2620625,
"learning_rate": 3.797029343404998e-05,
"epoch": 0.2405941313190006,
"total_flos": 81182621807557632,
"step": 26500
},
{
"loss": 4.2123125,
"learning_rate": 3.774331783846601e-05,
"epoch": 0.24513364323067985,
"total_flos": 82714921160804352,
"step": 27000
},
{
"loss": 4.2054375,
"learning_rate": 3.751634224288205e-05,
"epoch": 0.2496731551423591,
"total_flos": 84246883824245760,
"step": 27500
},
{
"loss": 4.176625,
"learning_rate": 3.728936664729809e-05,
"epoch": 0.25421266705403833,
"total_flos": 85777163038660608,
"step": 28000
},
{
"loss": 4.17928125,
"learning_rate": 3.706239105171412e-05,
"epoch": 0.2587521789657176,
"total_flos": 87308476371763200,
"step": 28500
},
{
"loss": 4.144,
"learning_rate": 3.683541545613016e-05,
"epoch": 0.26329169087739684,
"total_flos": 88841857942241280,
"step": 29000
},
{
"loss": 4.12915625,
"learning_rate": 3.660843986054619e-05,
"epoch": 0.26783120278907613,
"total_flos": 90372185255199744,
"step": 29500
},
{
"loss": 4.1188125,
"learning_rate": 3.638146426496223e-05,
"epoch": 0.27237071470075536,
"total_flos": 91901069611849728,
"step": 30000
},
{
"loss": 4.1068125,
"learning_rate": 3.615448866937827e-05,
"epoch": 0.27691022661243464,
"total_flos": 93430819742284800,
"step": 30500
},
{
"loss": 4.08590625,
"learning_rate": 3.59275130737943e-05,
"epoch": 0.28144973852411387,
"total_flos": 94959535754032128,
"step": 31000
},
{
"loss": 4.0940625,
"learning_rate": 3.570053747821034e-05,
"epoch": 0.28598925043579315,
"total_flos": 96491859156550656,
"step": 31500
},
{
"loss": 4.04140625,
"learning_rate": 3.547356188262638e-05,
"epoch": 0.2905287623474724,
"total_flos": 98024879987951616,
"step": 32000
},
{
"loss": 4.045,
"learning_rate": 3.524658628704242e-05,
"epoch": 0.29506827425915166,
"total_flos": 99554076985135104,
"step": 32500
},
{
"loss": 4.0135,
"learning_rate": 3.501961069145845e-05,
"epoch": 0.2996077861708309,
"total_flos": 101083803066298368,
"step": 33000
},
{
"loss": 4.00115625,
"learning_rate": 3.479263509587449e-05,
"epoch": 0.3041472980825102,
"total_flos": 102618507346725888,
"step": 33500
},
{
"loss": 3.9580625,
"learning_rate": 3.456565950029053e-05,
"epoch": 0.3086868099941894,
"total_flos": 104149532088566784,
"step": 34000
},
{
"loss": 3.9779375,
"learning_rate": 3.433868390470657e-05,
"epoch": 0.3132263219058687,
"total_flos": 105683202250306560,
"step": 34500
},
{
"loss": 3.9616875,
"learning_rate": 3.41117083091226e-05,
"epoch": 0.3177658338175479,
"total_flos": 107214082696516608,
"step": 35000
},
{
"loss": 3.93290625,
"learning_rate": 3.388473271353864e-05,
"epoch": 0.3223053457292272,
"total_flos": 108744746699280384,
"step": 35500
},
{
"loss": 3.93778125,
"learning_rate": 3.365775711795468e-05,
"epoch": 0.3268448576409064,
"total_flos": 110276949855439872,
"step": 36000
},
{
"loss": 3.9205625,
"learning_rate": 3.343078152237072e-05,
"epoch": 0.3313843695525857,
"total_flos": 111804607699227648,
"step": 36500
},
{
"loss": 3.88321875,
"learning_rate": 3.320380592678675e-05,
"epoch": 0.33592388146426494,
"total_flos": 113335848884514816,
"step": 37000
},
{
"loss": 3.888125,
"learning_rate": 3.297683033120279e-05,
"epoch": 0.3404633933759442,
"total_flos": 114868653272469504,
"step": 37500
},
{
"loss": 3.89365625,
"learning_rate": 3.274985473561883e-05,
"epoch": 0.34500290528762345,
"total_flos": 116403814489061376,
"step": 38000
},
{
"loss": 3.86290625,
"learning_rate": 3.252287914003487e-05,
"epoch": 0.34954241719930274,
"total_flos": 117934117752748032,
"step": 38500
},
{
"loss": 3.84853125,
"learning_rate": 3.22959035444509e-05,
"epoch": 0.35408192911098196,
"total_flos": 119463771686095872,
"step": 39000
},
{
"loss": 3.8525,
"learning_rate": 3.206892794886694e-05,
"epoch": 0.35862144102266125,
"total_flos": 120998981001231360,
"step": 39500
},
{
"loss": 3.8159375,
"learning_rate": 3.1841952353282975e-05,
"epoch": 0.3631609529343405,
"total_flos": 122533011902048256,
"step": 40000
},
{
"loss": 3.81184375,
"learning_rate": 3.1614976757699014e-05,
"epoch": 0.36770046484601976,
"total_flos": 124066008684177408,
"step": 40500
},
{
"loss": 3.80665625,
"learning_rate": 3.1388001162115046e-05,
"epoch": 0.372239976757699,
"total_flos": 125597610608541696,
"step": 41000
},
{
"loss": 3.78921875,
"learning_rate": 3.1161025566531086e-05,
"epoch": 0.37677948866937827,
"total_flos": 127130006158875648,
"step": 41500
},
{
"loss": 3.7755,
"learning_rate": 3.0934049970947125e-05,
"epoch": 0.3813190005810575,
"total_flos": 128661632132511744,
"step": 42000
},
{
"loss": 3.76021875,
"learning_rate": 3.0707074375363164e-05,
"epoch": 0.3858585124927368,
"total_flos": 130193210007604224,
"step": 42500
},
{
"loss": 3.75678125,
"learning_rate": 3.04800987797792e-05,
"epoch": 0.390398024404416,
"total_flos": 131723801862552576,
"step": 43000
},
{
"loss": 3.74840625,
"learning_rate": 3.0253123184195235e-05,
"epoch": 0.3949375363160953,
"total_flos": 133253768436433920,
"step": 43500
},
{
"loss": 3.7486875,
"learning_rate": 3.0026147588611275e-05,
"epoch": 0.3994770482277745,
"total_flos": 134787727189435392,
"step": 44000
},
{
"loss": 3.7429375,
"learning_rate": 2.9799171993027314e-05,
"epoch": 0.4040165601394538,
"total_flos": 136321589745349632,
"step": 44500
},
{
"loss": 3.70103125,
"learning_rate": 2.9572196397443346e-05,
"epoch": 0.40855607205113303,
"total_flos": 137853696704421888,
"step": 45000
},
{
"loss": 3.7165625,
"learning_rate": 2.9345220801859385e-05,
"epoch": 0.4130955839628123,
"total_flos": 139387583309607936,
"step": 45500
},
{
"loss": 3.6774375,
"learning_rate": 2.9118245206275425e-05,
"epoch": 0.4176350958744916,
"total_flos": 140920796535183360,
"step": 46000
},
{
"loss": 3.6928125,
"learning_rate": 2.8891269610691457e-05,
"epoch": 0.42217460778617083,
"total_flos": 142455452717067264,
"step": 46500
},
{
"loss": 3.6948125,
"learning_rate": 2.8664294015107496e-05,
"epoch": 0.4267141196978501,
"total_flos": 143988545696283648,
"step": 47000
},
{
"loss": 3.65459375,
"learning_rate": 2.8437318419523535e-05,
"epoch": 0.43125363160952934,
"total_flos": 145519618536668160,
"step": 47500
},
{
"loss": 3.66340625,
"learning_rate": 2.821034282393957e-05,
"epoch": 0.4357931435212086,
"total_flos": 147054851901075456,
"step": 48000
},
{
"loss": 3.65359375,
"learning_rate": 2.7983367228355607e-05,
"epoch": 0.44033265543288785,
"total_flos": 148586742416701440,
"step": 48500
},
{
"loss": 3.64646875,
"learning_rate": 2.7756391632771643e-05,
"epoch": 0.44487216734456714,
"total_flos": 150117430468737024,
"step": 49000
},
{
"loss": 3.63471875,
"learning_rate": 2.7529416037187682e-05,
"epoch": 0.44941167925624637,
"total_flos": 151648912146742272,
"step": 49500
},
{
"loss": 3.60778125,
"learning_rate": 2.730244044160372e-05,
"epoch": 0.45395119116792565,
"total_flos": 153182077273774080,
"step": 50000
},
{
"loss": 3.5908125,
"learning_rate": 2.7075464846019754e-05,
"epoch": 0.4584907030796049,
"total_flos": 154711081876783104,
"step": 50500
},
{
"loss": 3.6209375,
"learning_rate": 2.6848489250435793e-05,
"epoch": 0.46303021499128416,
"total_flos": 156241240844838912,
"step": 51000
},
{
"loss": 3.596,
"learning_rate": 2.6621513654851832e-05,
"epoch": 0.4675697269029634,
"total_flos": 157773083261921280,
"step": 51500
},
{
"loss": 3.57665625,
"learning_rate": 2.639453805926787e-05,
"epoch": 0.4721092388146427,
"total_flos": 159301246140417024,
"step": 52000
},
{
"loss": 3.5551875,
"learning_rate": 2.6167562463683904e-05,
"epoch": 0.4766487507263219,
"total_flos": 160831573453375488,
"step": 52500
},
{
"loss": 3.57975,
"learning_rate": 2.5940586868099943e-05,
"epoch": 0.4811882626380012,
"total_flos": 162364834777494528,
"step": 53000
},
{
"loss": 3.55321875,
"learning_rate": 2.5713611272515982e-05,
"epoch": 0.4857277745496804,
"total_flos": 163897711313264640,
"step": 53500
},
{
"loss": 3.5406875,
"learning_rate": 2.5486635676932018e-05,
"epoch": 0.4902672864613597,
"total_flos": 165430708095393792,
"step": 54000
},
{
"loss": 3.5404375,
"learning_rate": 2.5259660081348054e-05,
"epoch": 0.4948067983730389,
"total_flos": 166962550512476160,
"step": 54500
},
{
"loss": 3.5504375,
"learning_rate": 2.503268448576409e-05,
"epoch": 0.4993463102847182,
"total_flos": 168496485216205824,
"step": 55000
},
{
"loss": 3.541,
"learning_rate": 2.480570889018013e-05,
"epoch": 0.5038858221963974,
"total_flos": 170029049111442432,
"step": 55500
},
{
"loss": 3.5195625,
"learning_rate": 2.4578733294596164e-05,
"epoch": 0.5084253341080767,
"total_flos": 171563681244054528,
"step": 56000
},
{
"loss": 3.51209375,
"learning_rate": 2.4351757699012204e-05,
"epoch": 0.512964846019756,
"total_flos": 173096076794388480,
"step": 56500
},
{
"loss": 3.509,
"learning_rate": 2.412478210342824e-05,
"epoch": 0.5175043579314352,
"total_flos": 174627462275306496,
"step": 57000
},
{
"loss": 3.51578125,
"learning_rate": 2.389780650784428e-05,
"epoch": 0.5220438698431145,
"total_flos": 176158102228798464,
"step": 57500
},
{
"loss": 3.48325,
"learning_rate": 2.3670830912260314e-05,
"epoch": 0.5265833817547937,
"total_flos": 177692157178887168,
"step": 58000
},
{
"loss": 3.474625,
"learning_rate": 2.3443855316676354e-05,
"epoch": 0.531122893666473,
"total_flos": 179225418503006208,
"step": 58500
},
{
"loss": 3.4898125,
"learning_rate": 2.321687972109239e-05,
"epoch": 0.5356624055781523,
"total_flos": 180754567401646080,
"step": 59000
},
{
"loss": 3.4839375,
"learning_rate": 2.298990412550843e-05,
"epoch": 0.5402019174898315,
"total_flos": 182287227493969920,
"step": 59500
},
{
"loss": 3.4523125,
"learning_rate": 2.2762928529924464e-05,
"epoch": 0.5447414294015107,
"total_flos": 183817578856200192,
"step": 60000
},
{
"loss": 3.467875,
"learning_rate": 2.25359529343405e-05,
"epoch": 0.54928094131319,
"total_flos": 185350335145611264,
"step": 60500
},
{
"loss": 3.4614375,
"learning_rate": 2.2308977338756536e-05,
"epoch": 0.5538204532248693,
"total_flos": 186880734606385152,
"step": 61000
},
{
"loss": 3.4434375,
"learning_rate": 2.2082001743172575e-05,
"epoch": 0.5583599651365485,
"total_flos": 188413827585601536,
"step": 61500
},
{
"loss": 3.440875,
"learning_rate": 2.185502614758861e-05,
"epoch": 0.5628994770482277,
"total_flos": 189945429509965824,
"step": 62000
},
{
"loss": 3.4280625,
"learning_rate": 2.162805055200465e-05,
"epoch": 0.5674389889599071,
"total_flos": 191479243967336448,
"step": 62500
},
{
"loss": 3.41775,
"learning_rate": 2.1401074956420686e-05,
"epoch": 0.5719785008715863,
"total_flos": 193010629448254464,
"step": 63000
},
{
"loss": 3.4230625,
"learning_rate": 2.1174099360836725e-05,
"epoch": 0.5765180127832655,
"total_flos": 194545213482322944,
"step": 63500
},
{
"loss": 3.3981875,
"learning_rate": 2.094712376525276e-05,
"epoch": 0.5810575246949448,
"total_flos": 196078571003529216,
"step": 64000
},
{
"loss": 3.41275,
"learning_rate": 2.07201481696688e-05,
"epoch": 0.5855970366066241,
"total_flos": 197608970464303104,
"step": 64500
},
{
"loss": 3.398,
"learning_rate": 2.0493172574084836e-05,
"epoch": 0.5901365485183033,
"total_flos": 199141414113180672,
"step": 65000
},
{
"loss": 3.399375,
"learning_rate": 2.026619697850087e-05,
"epoch": 0.5946760604299826,
"total_flos": 200673304628806656,
"step": 65500
},
{
"loss": 3.4090625,
"learning_rate": 2.0039221382916907e-05,
"epoch": 0.5992155723416618,
"total_flos": 202205628031325184,
"step": 66000
},
{
"loss": 3.3909375,
"learning_rate": 1.9812245787332947e-05,
"epoch": 0.6037550842533411,
"total_flos": 203738961503259648,
"step": 66500
},
{
"loss": 3.3735625,
"learning_rate": 1.9585270191748982e-05,
"epoch": 0.6082945961650204,
"total_flos": 205271789940486144,
"step": 67000
},
{
"loss": 3.36775,
"learning_rate": 1.935829459616502e-05,
"epoch": 0.6128341080766996,
"total_flos": 206805123412420608,
"step": 67500
},
{
"loss": 3.3604375,
"learning_rate": 1.9131319000581057e-05,
"epoch": 0.6173736199883788,
"total_flos": 208335643119553536,
"step": 68000
},
{
"loss": 3.36825,
"learning_rate": 1.8904343404997097e-05,
"epoch": 0.6219131319000581,
"total_flos": 209869096837847040,
"step": 68500
},
{
"loss": 3.340125,
"learning_rate": 1.8677367809413132e-05,
"epoch": 0.6264526438117374,
"total_flos": 211403344182110208,
"step": 69000
},
{
"loss": 3.33675,
"learning_rate": 1.845039221382917e-05,
"epoch": 0.6309921557234166,
"total_flos": 212935787830987776,
"step": 69500
},
{
"loss": 3.344125,
"learning_rate": 1.8223416618245207e-05,
"epoch": 0.6355316676350958,
"total_flos": 214466932819187712,
"step": 70000
},
{
"loss": 3.336,
"learning_rate": 1.7996441022661247e-05,
"epoch": 0.6400711795467752,
"total_flos": 215998222103018496,
"step": 70500
},
{
"loss": 3.349375,
"learning_rate": 1.7769465427077282e-05,
"epoch": 0.6446106914584544,
"total_flos": 217531844166214656,
"step": 71000
},
{
"loss": 3.3093125,
"learning_rate": 1.7542489831493318e-05,
"epoch": 0.6491502033701336,
"total_flos": 219061257606844416,
"step": 71500
},
{
"loss": 3.314375,
"learning_rate": 1.7315514235909354e-05,
"epoch": 0.6536897152818129,
"total_flos": 220591969708151808,
"step": 72000
},
{
"loss": 3.3166875,
"learning_rate": 1.7088538640325393e-05,
"epoch": 0.6582292271934922,
"total_flos": 222126144904599552,
"step": 72500
},
{
"loss": 3.32175,
"learning_rate": 1.686156304474143e-05,
"epoch": 0.6627687391051714,
"total_flos": 223658997391097856,
"step": 73000
},
{
"loss": 3.2955625,
"learning_rate": 1.6634587449157468e-05,
"epoch": 0.6673082510168507,
"total_flos": 225189493048958976,
"step": 73500
},
{
"loss": 3.35425,
"learning_rate": 1.6407611853573504e-05,
"epoch": 0.6718477629285299,
"total_flos": 226722032894923776,
"step": 74000
},
{
"loss": 3.2941875,
"learning_rate": 1.6180636257989543e-05,
"epoch": 0.6763872748402092,
"total_flos": 228254404395985920,
"step": 74500
},
{
"loss": 3.2930625,
"learning_rate": 1.595366066240558e-05,
"epoch": 0.6809267867518884,
"total_flos": 229787834065007616,
"step": 75000
},
{
"loss": 3.3018125,
"learning_rate": 1.5726685066821618e-05,
"epoch": 0.6854662986635677,
"total_flos": 231321937113639936,
"step": 75500
},
{
"loss": 3.2865,
"learning_rate": 1.5499709471237654e-05,
"epoch": 0.6900058105752469,
"total_flos": 232855607275379712,
"step": 76000
},
{
"loss": 3.2755,
"learning_rate": 1.5272733875653693e-05,
"epoch": 0.6945453224869262,
"total_flos": 234390022964545536,
"step": 76500
},
{
"loss": 3.2875625,
"learning_rate": 1.5045758280069727e-05,
"epoch": 0.6990848343986055,
"total_flos": 235921119854201856,
"step": 77000
},
{
"loss": 3.254,
"learning_rate": 1.4818782684485766e-05,
"epoch": 0.7036243463102847,
"total_flos": 237454693818854400,
"step": 77500
},
{
"loss": 3.25675,
"learning_rate": 1.4591807088901802e-05,
"epoch": 0.7081638582219639,
"total_flos": 238986728630111232,
"step": 78000
},
{
"loss": 3.2600625,
"learning_rate": 1.436483149331784e-05,
"epoch": 0.7127033701336433,
"total_flos": 240520519038210048,
"step": 78500
},
{
"loss": 3.26825,
"learning_rate": 1.4137855897733875e-05,
"epoch": 0.7172428820453225,
"total_flos": 242053515820339200,
"step": 79000
},
{
"loss": 3.2588125,
"learning_rate": 1.3910880302149915e-05,
"epoch": 0.7217823939570017,
"total_flos": 243586416405381120,
"step": 79500
},
{
"loss": 3.249,
"learning_rate": 1.368390470656595e-05,
"epoch": 0.726321905868681,
"total_flos": 245117368999406592,
"step": 80000
},
{
"loss": 3.24175,
"learning_rate": 1.345692911098199e-05,
"epoch": 0.7308614177803603,
"total_flos": 246648778529596416,
"step": 80500
},
{
"loss": 3.2466875,
"learning_rate": 1.3229953515398025e-05,
"epoch": 0.7354009296920395,
"total_flos": 248182496789879808,
"step": 81000
},
{
"loss": 3.2416875,
"learning_rate": 1.3002977919814063e-05,
"epoch": 0.7399404416037187,
"total_flos": 249716022655988736,
"step": 81500
},
{
"loss": 3.2241875,
"learning_rate": 1.2776002324230099e-05,
"epoch": 0.744479953515398,
"total_flos": 251249211832292352,
"step": 82000
},
{
"loss": 3.2393125,
"learning_rate": 1.2549026728646138e-05,
"epoch": 0.7490194654270773,
"total_flos": 252781751678257152,
"step": 82500
},
{
"loss": 3.2358125,
"learning_rate": 1.2322051133062174e-05,
"epoch": 0.7535589773387565,
"total_flos": 254314387721309184,
"step": 83000
},
{
"loss": 3.205125,
"learning_rate": 1.2095075537478211e-05,
"epoch": 0.7580984892504358,
"total_flos": 255847456651253760,
"step": 83500
},
{
"loss": 3.2190625,
"learning_rate": 1.1868099941894249e-05,
"epoch": 0.762638001162115,
"total_flos": 257379034526346240,
"step": 84000
},
{
"loss": 3.2224375,
"learning_rate": 1.1641124346310285e-05,
"epoch": 0.7671775130737943,
"total_flos": 258912247751921664,
"step": 84500
},
{
"loss": 3.225,
"learning_rate": 1.1414148750726322e-05,
"epoch": 0.7717170249854736,
"total_flos": 260445460977497088,
"step": 85000
},
{
"loss": 3.2075625,
"learning_rate": 1.118717315514236e-05,
"epoch": 0.7762565368971528,
"total_flos": 261975668044096512,
"step": 85500
},
{
"loss": 3.19675,
"learning_rate": 1.0960197559558397e-05,
"epoch": 0.780796048808832,
"total_flos": 263509434402923520,
"step": 86000
},
{
"loss": 3.2095,
"learning_rate": 1.0733221963974434e-05,
"epoch": 0.7853355607205114,
"total_flos": 265042815973401600,
"step": 86500
},
{
"loss": 3.2146875,
"learning_rate": 1.050624636839047e-05,
"epoch": 0.7898750726321906,
"total_flos": 266577448106013696,
"step": 87000
},
{
"loss": 3.1964375,
"learning_rate": 1.0279270772806508e-05,
"epoch": 0.7944145845438698,
"total_flos": 268109699360716800,
"step": 87500
},
{
"loss": 3.1685625,
"learning_rate": 1.0052295177222545e-05,
"epoch": 0.798954096455549,
"total_flos": 269643032832651264,
"step": 88000
},
{
"loss": 3.1924375,
"learning_rate": 9.825319581638583e-06,
"epoch": 0.8034936083672284,
"total_flos": 271174490461384704,
"step": 88500
},
{
"loss": 3.198875,
"learning_rate": 9.59834398605462e-06,
"epoch": 0.8080331202789076,
"total_flos": 272707270800067584,
"step": 89000
},
{
"loss": 3.2030625,
"learning_rate": 9.371368390470658e-06,
"epoch": 0.8125726321905868,
"total_flos": 274237501915938816,
"step": 89500
},
{
"loss": 3.183125,
"learning_rate": 9.144392794886694e-06,
"epoch": 0.8171121441022661,
"total_flos": 275768502608507904,
"step": 90000
},
{
"loss": 3.1576875,
"learning_rate": 8.917417199302731e-06,
"epoch": 0.8216516560139454,
"total_flos": 277300705764667392,
"step": 90500
},
{
"loss": 3.1826875,
"learning_rate": 8.690441603718769e-06,
"epoch": 0.8261911679256246,
"total_flos": 278832163393400832,
"step": 91000
},
{
"loss": 3.1574375,
"learning_rate": 8.463466008134806e-06,
"epoch": 0.8307306798373039,
"total_flos": 280364631091550208,
"step": 91500
},
{
"loss": 3.160125,
"learning_rate": 8.236490412550844e-06,
"epoch": 0.8352701917489832,
"total_flos": 281895944424652800,
"step": 92000
},
{
"loss": 3.163875,
"learning_rate": 8.009514816966881e-06,
"epoch": 0.8398097036606624,
"total_flos": 283429542438577152,
"step": 92500
},
{
"loss": 3.177625,
"learning_rate": 7.782539221382917e-06,
"epoch": 0.8443492155723417,
"total_flos": 284961793693280256,
"step": 93000
},
{
"loss": 3.161875,
"learning_rate": 7.555563625798954e-06,
"epoch": 0.8488887274840209,
"total_flos": 286495920791184384,
"step": 93500
},
{
"loss": 3.16925,
"learning_rate": 7.328588030214992e-06,
"epoch": 0.8534282393957002,
"total_flos": 288029470706565120,
"step": 94000
},
{
"loss": 3.1579375,
"learning_rate": 7.101612434631029e-06,
"epoch": 0.8579677513073795,
"total_flos": 289561505517821952,
"step": 94500
},
{
"loss": 3.1499375,
"learning_rate": 6.874636839047066e-06,
"epoch": 0.8625072632190587,
"total_flos": 291092097372770304,
"step": 95000
},
{
"loss": 3.1406875,
"learning_rate": 6.6476612434631034e-06,
"epoch": 0.8670467751307379,
"total_flos": 292625791583781888,
"step": 95500
},
{
"loss": 3.1599375,
"learning_rate": 6.420685647879141e-06,
"epoch": 0.8715862870424173,
"total_flos": 294158114986300416,
"step": 96000
},
{
"loss": 3.1481875,
"learning_rate": 6.1937100522951776e-06,
"epoch": 0.8761257989540965,
"total_flos": 295691833246583808,
"step": 96500
},
{
"loss": 3.13575,
"learning_rate": 5.966734456711215e-06,
"epoch": 0.8806653108657757,
"total_flos": 297225791999585280,
"step": 97000
},
{
"loss": 3.1423125,
"learning_rate": 5.739758861127252e-06,
"epoch": 0.8852048227774549,
"total_flos": 298758620436811776,
"step": 97500
},
{
"loss": 3.157625,
"learning_rate": 5.512783265543289e-06,
"epoch": 0.8897443346891343,
"total_flos": 300291689366756352,
"step": 98000
},
{
"loss": 3.126125,
"learning_rate": 5.285807669959327e-06,
"epoch": 0.8942838466008135,
"total_flos": 301824734247429120,
"step": 98500
},
{
"loss": 3.1455625,
"learning_rate": 5.058832074375363e-06,
"epoch": 0.8988233585124927,
"total_flos": 303358115817907200,
"step": 99000
},
{
"loss": 3.1365625,
"learning_rate": 4.831856478791401e-06,
"epoch": 0.903362870424172,
"total_flos": 304890920205861888,
"step": 99500
},
{
"loss": 3.131625,
"learning_rate": 4.604880883207438e-06,
"epoch": 0.9079023823358513,
"total_flos": 306422858820031488,
"step": 100000
},
{
"loss": 3.15225,
"learning_rate": 4.377905287623475e-06,
"epoch": 0.9124418942475305,
"total_flos": 307953498773523456,
"step": 100500
},
{
"loss": 3.145,
"learning_rate": 4.1509296920395125e-06,
"epoch": 0.9169814061592098,
"total_flos": 309485365239877632,
"step": 101000
},
{
"loss": 3.1263125,
"learning_rate": 3.92395409645555e-06,
"epoch": 0.921520918070889,
"total_flos": 311017039312057344,
"step": 101500
},
{
"loss": 3.12225,
"learning_rate": 3.696978500871586e-06,
"epoch": 0.9260604299825683,
"total_flos": 312548977926226944,
"step": 102000
},
{
"loss": 3.1128125,
"learning_rate": 3.4700029052876232e-06,
"epoch": 0.9305999418942476,
"total_flos": 314081493722919936,
"step": 102500
},
{
"loss": 3.1099375,
"learning_rate": 3.2430273097036603e-06,
"epoch": 0.9351394538059268,
"total_flos": 315613744977623040,
"step": 103000
},
{
"loss": 3.114,
"learning_rate": 3.0160517141196982e-06,
"epoch": 0.939678965717606,
"total_flos": 317144096339853312,
"step": 103500
},
{
"loss": 3.1200625,
"learning_rate": 2.7890761185357353e-06,
"epoch": 0.9442184776292853,
"total_flos": 318675169180237824,
"step": 104000
},
{
"loss": 3.104625,
"learning_rate": 2.5621005229517724e-06,
"epoch": 0.9487579895409646,
"total_flos": 320208959588336640,
"step": 104500
},
{
"loss": 3.1181875,
"learning_rate": 2.3351249273678094e-06,
"epoch": 0.9532975014526438,
"total_flos": 321739960280905728,
"step": 105000
},
{
"loss": 3.1073125,
"learning_rate": 2.108149331783847e-06,
"epoch": 0.957837013364323,
"total_flos": 323273894984635392,
"step": 105500
},
{
"loss": 3.141375,
"learning_rate": 1.881173736199884e-06,
"epoch": 0.9623765252760024,
"total_flos": 324804607085942784,
"step": 106000
},
{
"loss": 3.1269375,
"learning_rate": 1.6541981406159213e-06,
"epoch": 0.9669160371876816,
"total_flos": 326337627917343744,
"step": 106500
},
{
"loss": 3.118,
"learning_rate": 1.4272225450319581e-06,
"epoch": 0.9714555490993608,
"total_flos": 327871298079083520,
"step": 107000
},
{
"loss": 3.1175,
"learning_rate": 1.2002469494479954e-06,
"epoch": 0.97599506101104,
"total_flos": 329401745638401024,
"step": 107500
},
{
"loss": 3.120375,
"learning_rate": 9.732713538640327e-07,
"epoch": 0.9805345729227194,
"total_flos": 330934525977083904,
"step": 108000
},
{
"loss": 3.0920625,
"learning_rate": 7.462957582800698e-07,
"epoch": 0.9850740848343986,
"total_flos": 332464155861159936,
"step": 108500
},
{
"loss": 3.0940625,
"learning_rate": 5.19320162696107e-07,
"epoch": 0.9896135967460779,
"total_flos": 333995685637708800,
"step": 109000
},
{
"loss": 3.10975,
"learning_rate": 2.923445671121441e-07,
"epoch": 0.9941531086577571,
"total_flos": 335529836784884736,
"step": 109500
},
{
"loss": 3.115375,
"learning_rate": 6.536897152818129e-08,
"epoch": 0.9986926205694364,
"total_flos": 337063434798809088,
"step": 110000
}
]