GIST-small-topic / trainer_state.json
agentlans's picture
Upload 11 files
323ffee verified
Raw History Blame Contribute Delete
81.4 kB
{
"best_global_step": 211530,
"best_metric": 0.9179618788534967,
"best_model_checkpoint": "./GIST-small-topic/checkpoint-211530",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 211530,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0070911927386186355,
"grad_norm": 2.0094034671783447,
"learning_rate": 4.988204982744765e-05,
"loss": 2.21929736328125,
"step": 500
},
{
"epoch": 0.014182385477237271,
"grad_norm": 19.219717025756836,
"learning_rate": 4.9763863281804004e-05,
"loss": 1.0627626953125,
"step": 1000
},
{
"epoch": 0.021273578215855907,
"grad_norm": 12.463168144226074,
"learning_rate": 4.964567673616036e-05,
"loss": 0.7230818481445312,
"step": 1500
},
{
"epoch": 0.028364770954474542,
"grad_norm": 30.950218200683594,
"learning_rate": 4.952749019051671e-05,
"loss": 0.56197265625,
"step": 2000
},
{
"epoch": 0.03545596369309318,
"grad_norm": 2.983157157897949,
"learning_rate": 4.940930364487307e-05,
"loss": 0.542384033203125,
"step": 2500
},
{
"epoch": 0.042547156431711815,
"grad_norm": 5.0553436279296875,
"learning_rate": 4.929111709922943e-05,
"loss": 0.4953382568359375,
"step": 3000
},
{
"epoch": 0.04963834917033045,
"grad_norm": 12.18031120300293,
"learning_rate": 4.917293055358578e-05,
"loss": 0.4707428283691406,
"step": 3500
},
{
"epoch": 0.056729541908949084,
"grad_norm": 13.765538215637207,
"learning_rate": 4.905474400794214e-05,
"loss": 0.46302090454101563,
"step": 4000
},
{
"epoch": 0.06382073464756773,
"grad_norm": 27.128658294677734,
"learning_rate": 4.893655746229849e-05,
"loss": 0.4627261962890625,
"step": 4500
},
{
"epoch": 0.07091192738618636,
"grad_norm": 22.089130401611328,
"learning_rate": 4.8818370916654845e-05,
"loss": 0.48565313720703124,
"step": 5000
},
{
"epoch": 0.078003120124805,
"grad_norm": 19.198444366455078,
"learning_rate": 4.8700184371011206e-05,
"loss": 0.4377886962890625,
"step": 5500
},
{
"epoch": 0.08509431286342363,
"grad_norm": 26.68898582458496,
"learning_rate": 4.858199782536757e-05,
"loss": 0.45854840087890625,
"step": 6000
},
{
"epoch": 0.09218550560204226,
"grad_norm": 1.396219253540039,
"learning_rate": 4.846381127972392e-05,
"loss": 0.42720388793945313,
"step": 6500
},
{
"epoch": 0.0992766983406609,
"grad_norm": 17.45922088623047,
"learning_rate": 4.8345624734080276e-05,
"loss": 0.4388797912597656,
"step": 7000
},
{
"epoch": 0.10636789107927953,
"grad_norm": 13.813079833984375,
"learning_rate": 4.822743818843663e-05,
"loss": 0.43045758056640626,
"step": 7500
},
{
"epoch": 0.11345908381789817,
"grad_norm": 19.49132537841797,
"learning_rate": 4.8109251642792985e-05,
"loss": 0.4109803771972656,
"step": 8000
},
{
"epoch": 0.1205502765565168,
"grad_norm": 15.026893615722656,
"learning_rate": 4.799106509714934e-05,
"loss": 0.43473480224609373,
"step": 8500
},
{
"epoch": 0.12764146929513545,
"grad_norm": 0.4883650541305542,
"learning_rate": 4.78728785515057e-05,
"loss": 0.4177641296386719,
"step": 9000
},
{
"epoch": 0.13473266203375409,
"grad_norm": 18.900754928588867,
"learning_rate": 4.7754692005862054e-05,
"loss": 0.38533172607421873,
"step": 9500
},
{
"epoch": 0.14182385477237272,
"grad_norm": 1.1473286151885986,
"learning_rate": 4.763650546021841e-05,
"loss": 0.4119681396484375,
"step": 10000
},
{
"epoch": 0.14891504751099136,
"grad_norm": 11.821301460266113,
"learning_rate": 4.751831891457477e-05,
"loss": 0.40965200805664065,
"step": 10500
},
{
"epoch": 0.15600624024961,
"grad_norm": 23.506179809570312,
"learning_rate": 4.7400132368931124e-05,
"loss": 0.3976383972167969,
"step": 11000
},
{
"epoch": 0.16309743298822862,
"grad_norm": 5.233912944793701,
"learning_rate": 4.728194582328748e-05,
"loss": 0.42674627685546873,
"step": 11500
},
{
"epoch": 0.17018862572684726,
"grad_norm": 0.5937948226928711,
"learning_rate": 4.716375927764384e-05,
"loss": 0.40512103271484373,
"step": 12000
},
{
"epoch": 0.1772798184654659,
"grad_norm": 17.91236686706543,
"learning_rate": 4.7045572732000194e-05,
"loss": 0.4136376953125,
"step": 12500
},
{
"epoch": 0.18437101120408453,
"grad_norm": 22.474529266357422,
"learning_rate": 4.692738618635655e-05,
"loss": 0.4313943176269531,
"step": 13000
},
{
"epoch": 0.19146220394270316,
"grad_norm": 8.908188819885254,
"learning_rate": 4.68091996407129e-05,
"loss": 0.407843017578125,
"step": 13500
},
{
"epoch": 0.1985533966813218,
"grad_norm": 18.582136154174805,
"learning_rate": 4.6691013095069256e-05,
"loss": 0.4009266357421875,
"step": 14000
},
{
"epoch": 0.20564458941994043,
"grad_norm": 10.631417274475098,
"learning_rate": 4.657282654942561e-05,
"loss": 0.3847767333984375,
"step": 14500
},
{
"epoch": 0.21273578215855907,
"grad_norm": 0.06845115125179291,
"learning_rate": 4.645464000378197e-05,
"loss": 0.404919189453125,
"step": 15000
},
{
"epoch": 0.2198269748971777,
"grad_norm": 10.31063175201416,
"learning_rate": 4.6336453458138326e-05,
"loss": 0.41001177978515624,
"step": 15500
},
{
"epoch": 0.22691816763579634,
"grad_norm": 22.720964431762695,
"learning_rate": 4.621826691249469e-05,
"loss": 0.4126224365234375,
"step": 16000
},
{
"epoch": 0.23400936037441497,
"grad_norm": 15.995619773864746,
"learning_rate": 4.610008036685104e-05,
"loss": 0.39923910522460937,
"step": 16500
},
{
"epoch": 0.2411005531130336,
"grad_norm": 45.834747314453125,
"learning_rate": 4.5981893821207396e-05,
"loss": 0.3683683166503906,
"step": 17000
},
{
"epoch": 0.24819174585165224,
"grad_norm": 10.192611694335938,
"learning_rate": 4.586370727556375e-05,
"loss": 0.38183563232421874,
"step": 17500
},
{
"epoch": 0.2552829385902709,
"grad_norm": 17.221702575683594,
"learning_rate": 4.574552072992011e-05,
"loss": 0.3848875427246094,
"step": 18000
},
{
"epoch": 0.26237413132888954,
"grad_norm": 11.800912857055664,
"learning_rate": 4.5627334184276465e-05,
"loss": 0.3841501159667969,
"step": 18500
},
{
"epoch": 0.26946532406750817,
"grad_norm": 10.162900924682617,
"learning_rate": 4.550914763863282e-05,
"loss": 0.3888123779296875,
"step": 19000
},
{
"epoch": 0.2765565168061268,
"grad_norm": 4.604160785675049,
"learning_rate": 4.5390961092989174e-05,
"loss": 0.3991587219238281,
"step": 19500
},
{
"epoch": 0.28364770954474544,
"grad_norm": 20.095441818237305,
"learning_rate": 4.527277454734553e-05,
"loss": 0.3958879089355469,
"step": 20000
},
{
"epoch": 0.2907389022833641,
"grad_norm": 12.304089546203613,
"learning_rate": 4.515458800170189e-05,
"loss": 0.3968980712890625,
"step": 20500
},
{
"epoch": 0.2978300950219827,
"grad_norm": 0.5610142350196838,
"learning_rate": 4.503640145605825e-05,
"loss": 0.4232771301269531,
"step": 21000
},
{
"epoch": 0.30492128776060134,
"grad_norm": 2.9310262203216553,
"learning_rate": 4.4918214910414605e-05,
"loss": 0.39260968017578124,
"step": 21500
},
{
"epoch": 0.31201248049922,
"grad_norm": 0.5716455578804016,
"learning_rate": 4.480002836477096e-05,
"loss": 0.38827359008789064,
"step": 22000
},
{
"epoch": 0.3191036732378386,
"grad_norm": 1.3526256084442139,
"learning_rate": 4.468184181912731e-05,
"loss": 0.37964959716796876,
"step": 22500
},
{
"epoch": 0.32619486597645725,
"grad_norm": 15.395561218261719,
"learning_rate": 4.456365527348367e-05,
"loss": 0.3920819091796875,
"step": 23000
},
{
"epoch": 0.3332860587150759,
"grad_norm": 10.289068222045898,
"learning_rate": 4.444546872784002e-05,
"loss": 0.38668710327148437,
"step": 23500
},
{
"epoch": 0.3403772514536945,
"grad_norm": 1.6159920692443848,
"learning_rate": 4.432728218219638e-05,
"loss": 0.3819559326171875,
"step": 24000
},
{
"epoch": 0.34746844419231315,
"grad_norm": 7.291048526763916,
"learning_rate": 4.420909563655274e-05,
"loss": 0.34942718505859377,
"step": 24500
},
{
"epoch": 0.3545596369309318,
"grad_norm": 21.11905288696289,
"learning_rate": 4.409090909090909e-05,
"loss": 0.4017558898925781,
"step": 25000
},
{
"epoch": 0.3616508296695504,
"grad_norm": 11.451282501220703,
"learning_rate": 4.3972722545265446e-05,
"loss": 0.37077435302734374,
"step": 25500
},
{
"epoch": 0.36874202240816906,
"grad_norm": 16.3957462310791,
"learning_rate": 4.385453599962181e-05,
"loss": 0.3965981140136719,
"step": 26000
},
{
"epoch": 0.3758332151467877,
"grad_norm": 26.137174606323242,
"learning_rate": 4.373634945397816e-05,
"loss": 0.40133779907226563,
"step": 26500
},
{
"epoch": 0.3829244078854063,
"grad_norm": 21.809417724609375,
"learning_rate": 4.361816290833452e-05,
"loss": 0.3455391845703125,
"step": 27000
},
{
"epoch": 0.39001560062402496,
"grad_norm": 9.511174201965332,
"learning_rate": 4.3499976362690876e-05,
"loss": 0.39233285522460937,
"step": 27500
},
{
"epoch": 0.3971067933626436,
"grad_norm": 31.224679946899414,
"learning_rate": 4.338178981704723e-05,
"loss": 0.37783285522460935,
"step": 28000
},
{
"epoch": 0.40419798610126223,
"grad_norm": 3.0387356281280518,
"learning_rate": 4.3263603271403585e-05,
"loss": 0.36522085571289065,
"step": 28500
},
{
"epoch": 0.41128917883988086,
"grad_norm": 9.661357879638672,
"learning_rate": 4.314541672575994e-05,
"loss": 0.3850714721679688,
"step": 29000
},
{
"epoch": 0.4183803715784995,
"grad_norm": 20.81166648864746,
"learning_rate": 4.3027230180116293e-05,
"loss": 0.3951400146484375,
"step": 29500
},
{
"epoch": 0.42547156431711813,
"grad_norm": 11.138774871826172,
"learning_rate": 4.290904363447265e-05,
"loss": 0.3763404541015625,
"step": 30000
},
{
"epoch": 0.43256275705573677,
"grad_norm": 0.7437636852264404,
"learning_rate": 4.279085708882901e-05,
"loss": 0.36979705810546876,
"step": 30500
},
{
"epoch": 0.4396539497943554,
"grad_norm": 23.123035430908203,
"learning_rate": 4.267267054318537e-05,
"loss": 0.3605682373046875,
"step": 31000
},
{
"epoch": 0.44674514253297404,
"grad_norm": 11.462782859802246,
"learning_rate": 4.2554483997541724e-05,
"loss": 0.3390813293457031,
"step": 31500
},
{
"epoch": 0.4538363352715927,
"grad_norm": 12.093498229980469,
"learning_rate": 4.243629745189808e-05,
"loss": 0.37293450927734373,
"step": 32000
},
{
"epoch": 0.4609275280102113,
"grad_norm": 0.0507306233048439,
"learning_rate": 4.231811090625443e-05,
"loss": 0.39073757934570313,
"step": 32500
},
{
"epoch": 0.46801872074882994,
"grad_norm": 15.834416389465332,
"learning_rate": 4.219992436061079e-05,
"loss": 0.3769065856933594,
"step": 33000
},
{
"epoch": 0.4751099134874486,
"grad_norm": 38.923831939697266,
"learning_rate": 4.208173781496715e-05,
"loss": 0.34681292724609375,
"step": 33500
},
{
"epoch": 0.4822011062260672,
"grad_norm": 3.2983150482177734,
"learning_rate": 4.19635512693235e-05,
"loss": 0.3393735961914062,
"step": 34000
},
{
"epoch": 0.48929229896468585,
"grad_norm": 13.693626403808594,
"learning_rate": 4.184536472367986e-05,
"loss": 0.3842292175292969,
"step": 34500
},
{
"epoch": 0.4963834917033045,
"grad_norm": 17.57269287109375,
"learning_rate": 4.172717817803621e-05,
"loss": 0.3563892517089844,
"step": 35000
},
{
"epoch": 0.5034746844419231,
"grad_norm": 4.0084710121154785,
"learning_rate": 4.160899163239257e-05,
"loss": 0.39765109252929687,
"step": 35500
},
{
"epoch": 0.5105658771805418,
"grad_norm": 20.67154884338379,
"learning_rate": 4.1490805086748926e-05,
"loss": 0.35460427856445315,
"step": 36000
},
{
"epoch": 0.5176570699191604,
"grad_norm": 0.30911800265312195,
"learning_rate": 4.137261854110529e-05,
"loss": 0.36283389282226564,
"step": 36500
},
{
"epoch": 0.5247482626577791,
"grad_norm": 3.699970245361328,
"learning_rate": 4.125443199546164e-05,
"loss": 0.3951703491210937,
"step": 37000
},
{
"epoch": 0.5318394553963977,
"grad_norm": 35.91598129272461,
"learning_rate": 4.1136245449817996e-05,
"loss": 0.3673123779296875,
"step": 37500
},
{
"epoch": 0.5389306481350163,
"grad_norm": 15.166389465332031,
"learning_rate": 4.101805890417435e-05,
"loss": 0.3646431579589844,
"step": 38000
},
{
"epoch": 0.5460218408736349,
"grad_norm": 4.839053630828857,
"learning_rate": 4.0899872358530705e-05,
"loss": 0.37225506591796875,
"step": 38500
},
{
"epoch": 0.5531130336122536,
"grad_norm": 16.341421127319336,
"learning_rate": 4.078168581288706e-05,
"loss": 0.3248492431640625,
"step": 39000
},
{
"epoch": 0.5602042263508722,
"grad_norm": 12.289342880249023,
"learning_rate": 4.066349926724342e-05,
"loss": 0.35200335693359375,
"step": 39500
},
{
"epoch": 0.5672954190894909,
"grad_norm": 0.07165870815515518,
"learning_rate": 4.0545312721599774e-05,
"loss": 0.3465135192871094,
"step": 40000
},
{
"epoch": 0.5743866118281095,
"grad_norm": 19.236539840698242,
"learning_rate": 4.042712617595613e-05,
"loss": 0.36539205932617186,
"step": 40500
},
{
"epoch": 0.5814778045667282,
"grad_norm": 1.1958494186401367,
"learning_rate": 4.030893963031249e-05,
"loss": 0.3689007873535156,
"step": 41000
},
{
"epoch": 0.5885689973053467,
"grad_norm": 22.092870712280273,
"learning_rate": 4.0190753084668844e-05,
"loss": 0.37182241821289064,
"step": 41500
},
{
"epoch": 0.5956601900439654,
"grad_norm": 0.08594904839992523,
"learning_rate": 4.00725665390252e-05,
"loss": 0.36475091552734373,
"step": 42000
},
{
"epoch": 0.602751382782584,
"grad_norm": 29.551023483276367,
"learning_rate": 3.995437999338156e-05,
"loss": 0.331034423828125,
"step": 42500
},
{
"epoch": 0.6098425755212027,
"grad_norm": 0.04614920914173126,
"learning_rate": 3.9836193447737913e-05,
"loss": 0.33374911499023435,
"step": 43000
},
{
"epoch": 0.6169337682598213,
"grad_norm": 15.710551261901855,
"learning_rate": 3.971800690209427e-05,
"loss": 0.37484417724609376,
"step": 43500
},
{
"epoch": 0.62402496099844,
"grad_norm": 37.30379104614258,
"learning_rate": 3.959982035645062e-05,
"loss": 0.32213079833984376,
"step": 44000
},
{
"epoch": 0.6311161537370585,
"grad_norm": 6.224698543548584,
"learning_rate": 3.9481633810806976e-05,
"loss": 0.3595847473144531,
"step": 44500
},
{
"epoch": 0.6382073464756772,
"grad_norm": 6.233162879943848,
"learning_rate": 3.936344726516333e-05,
"loss": 0.34365115356445314,
"step": 45000
},
{
"epoch": 0.6452985392142958,
"grad_norm": 14.356497764587402,
"learning_rate": 3.924526071951969e-05,
"loss": 0.3619053955078125,
"step": 45500
},
{
"epoch": 0.6523897319529145,
"grad_norm": 9.267119407653809,
"learning_rate": 3.912707417387605e-05,
"loss": 0.35733905029296875,
"step": 46000
},
{
"epoch": 0.6594809246915331,
"grad_norm": 4.029196739196777,
"learning_rate": 3.900888762823241e-05,
"loss": 0.3212258605957031,
"step": 46500
},
{
"epoch": 0.6665721174301518,
"grad_norm": 34.695552825927734,
"learning_rate": 3.889070108258876e-05,
"loss": 0.3341042785644531,
"step": 47000
},
{
"epoch": 0.6736633101687703,
"grad_norm": 0.026256900280714035,
"learning_rate": 3.8772514536945116e-05,
"loss": 0.336823486328125,
"step": 47500
},
{
"epoch": 0.680754502907389,
"grad_norm": 17.9473819732666,
"learning_rate": 3.865432799130147e-05,
"loss": 0.3473232727050781,
"step": 48000
},
{
"epoch": 0.6878456956460076,
"grad_norm": 10.06433391571045,
"learning_rate": 3.853614144565783e-05,
"loss": 0.3433890075683594,
"step": 48500
},
{
"epoch": 0.6949368883846263,
"grad_norm": 9.97581672668457,
"learning_rate": 3.8417954900014185e-05,
"loss": 0.3339334716796875,
"step": 49000
},
{
"epoch": 0.7020280811232449,
"grad_norm": 2.1598761081695557,
"learning_rate": 3.829976835437054e-05,
"loss": 0.34377346801757813,
"step": 49500
},
{
"epoch": 0.7091192738618636,
"grad_norm": 0.6067615747451782,
"learning_rate": 3.8181581808726894e-05,
"loss": 0.3535705261230469,
"step": 50000
},
{
"epoch": 0.7162104666004822,
"grad_norm": 4.127110958099365,
"learning_rate": 3.806339526308325e-05,
"loss": 0.3544539794921875,
"step": 50500
},
{
"epoch": 0.7233016593391008,
"grad_norm": 0.1849542111158371,
"learning_rate": 3.794520871743961e-05,
"loss": 0.3537879943847656,
"step": 51000
},
{
"epoch": 0.7303928520777194,
"grad_norm": 3.8822484016418457,
"learning_rate": 3.782702217179597e-05,
"loss": 0.3630632629394531,
"step": 51500
},
{
"epoch": 0.7374840448163381,
"grad_norm": 7.645042419433594,
"learning_rate": 3.7708835626152324e-05,
"loss": 0.3490135498046875,
"step": 52000
},
{
"epoch": 0.7445752375549567,
"grad_norm": 8.459843635559082,
"learning_rate": 3.759064908050868e-05,
"loss": 0.31747186279296874,
"step": 52500
},
{
"epoch": 0.7516664302935754,
"grad_norm": 1.0256061553955078,
"learning_rate": 3.747246253486503e-05,
"loss": 0.37400778198242185,
"step": 53000
},
{
"epoch": 0.758757623032194,
"grad_norm": 15.987700462341309,
"learning_rate": 3.735427598922139e-05,
"loss": 0.32377114868164064,
"step": 53500
},
{
"epoch": 0.7658488157708127,
"grad_norm": 0.1935882717370987,
"learning_rate": 3.723608944357774e-05,
"loss": 0.3376795654296875,
"step": 54000
},
{
"epoch": 0.7729400085094312,
"grad_norm": 1.3788025379180908,
"learning_rate": 3.71179028979341e-05,
"loss": 0.3611544189453125,
"step": 54500
},
{
"epoch": 0.7800312012480499,
"grad_norm": 26.272855758666992,
"learning_rate": 3.699971635229046e-05,
"loss": 0.32168243408203123,
"step": 55000
},
{
"epoch": 0.7871223939866686,
"grad_norm": 0.6588231921195984,
"learning_rate": 3.688152980664681e-05,
"loss": 0.33372409057617186,
"step": 55500
},
{
"epoch": 0.7942135867252872,
"grad_norm": 11.952702522277832,
"learning_rate": 3.676334326100317e-05,
"loss": 0.35271978759765626,
"step": 56000
},
{
"epoch": 0.8013047794639059,
"grad_norm": 7.862829685211182,
"learning_rate": 3.6645156715359527e-05,
"loss": 0.37077886962890627,
"step": 56500
},
{
"epoch": 0.8083959722025245,
"grad_norm": 0.029279431328177452,
"learning_rate": 3.652697016971588e-05,
"loss": 0.330326171875,
"step": 57000
},
{
"epoch": 0.8154871649411432,
"grad_norm": 34.08498001098633,
"learning_rate": 3.6408783624072235e-05,
"loss": 0.34447216796875,
"step": 57500
},
{
"epoch": 0.8225783576797617,
"grad_norm": 0.06102259084582329,
"learning_rate": 3.6290597078428596e-05,
"loss": 0.33774069213867186,
"step": 58000
},
{
"epoch": 0.8296695504183804,
"grad_norm": 11.09460163116455,
"learning_rate": 3.617241053278495e-05,
"loss": 0.33897756958007813,
"step": 58500
},
{
"epoch": 0.836760743156999,
"grad_norm": 0.3205820322036743,
"learning_rate": 3.6054223987141305e-05,
"loss": 0.3516035461425781,
"step": 59000
},
{
"epoch": 0.8438519358956177,
"grad_norm": 6.811905860900879,
"learning_rate": 3.593603744149766e-05,
"loss": 0.3145771179199219,
"step": 59500
},
{
"epoch": 0.8509431286342363,
"grad_norm": 0.2537534832954407,
"learning_rate": 3.581785089585401e-05,
"loss": 0.3381671447753906,
"step": 60000
},
{
"epoch": 0.858034321372855,
"grad_norm": 32.04276657104492,
"learning_rate": 3.5699664350210374e-05,
"loss": 0.3617617797851562,
"step": 60500
},
{
"epoch": 0.8651255141114735,
"grad_norm": 23.124114990234375,
"learning_rate": 3.558147780456673e-05,
"loss": 0.29876913452148435,
"step": 61000
},
{
"epoch": 0.8722167068500922,
"grad_norm": 18.933256149291992,
"learning_rate": 3.546329125892309e-05,
"loss": 0.3718148803710937,
"step": 61500
},
{
"epoch": 0.8793078995887108,
"grad_norm": 0.27876582741737366,
"learning_rate": 3.5345104713279444e-05,
"loss": 0.3371610717773437,
"step": 62000
},
{
"epoch": 0.8863990923273295,
"grad_norm": 0.8196110129356384,
"learning_rate": 3.52269181676358e-05,
"loss": 0.35435800170898435,
"step": 62500
},
{
"epoch": 0.8934902850659481,
"grad_norm": 1.0336010456085205,
"learning_rate": 3.510873162199215e-05,
"loss": 0.34713302612304686,
"step": 63000
},
{
"epoch": 0.9005814778045668,
"grad_norm": 7.554769515991211,
"learning_rate": 3.499054507634851e-05,
"loss": 0.30580343627929685,
"step": 63500
},
{
"epoch": 0.9076726705431853,
"grad_norm": 13.311524391174316,
"learning_rate": 3.487235853070487e-05,
"loss": 0.3226221618652344,
"step": 64000
},
{
"epoch": 0.914763863281804,
"grad_norm": 8.582770347595215,
"learning_rate": 3.475417198506122e-05,
"loss": 0.3254347229003906,
"step": 64500
},
{
"epoch": 0.9218550560204226,
"grad_norm": 13.36210823059082,
"learning_rate": 3.4635985439417577e-05,
"loss": 0.32660067749023436,
"step": 65000
},
{
"epoch": 0.9289462487590413,
"grad_norm": 9.560787200927734,
"learning_rate": 3.451779889377393e-05,
"loss": 0.33592776489257814,
"step": 65500
},
{
"epoch": 0.9360374414976599,
"grad_norm": 2.2018673419952393,
"learning_rate": 3.439961234813029e-05,
"loss": 0.34028265380859374,
"step": 66000
},
{
"epoch": 0.9431286342362786,
"grad_norm": 0.298260897397995,
"learning_rate": 3.4281425802486646e-05,
"loss": 0.3319949951171875,
"step": 66500
},
{
"epoch": 0.9502198269748972,
"grad_norm": 25.438379287719727,
"learning_rate": 3.416323925684301e-05,
"loss": 0.33092230224609376,
"step": 67000
},
{
"epoch": 0.9573110197135158,
"grad_norm": 20.164203643798828,
"learning_rate": 3.404505271119936e-05,
"loss": 0.3341027526855469,
"step": 67500
},
{
"epoch": 0.9644022124521344,
"grad_norm": 1.966504454612732,
"learning_rate": 3.3926866165555716e-05,
"loss": 0.3280333557128906,
"step": 68000
},
{
"epoch": 0.9714934051907531,
"grad_norm": 0.7266027331352234,
"learning_rate": 3.380867961991207e-05,
"loss": 0.30428872680664065,
"step": 68500
},
{
"epoch": 0.9785845979293717,
"grad_norm": 10.37846565246582,
"learning_rate": 3.3690493074268424e-05,
"loss": 0.3406554870605469,
"step": 69000
},
{
"epoch": 0.9856757906679904,
"grad_norm": 10.847968101501465,
"learning_rate": 3.357230652862478e-05,
"loss": 0.3461930847167969,
"step": 69500
},
{
"epoch": 0.992766983406609,
"grad_norm": 4.485472679138184,
"learning_rate": 3.345411998298114e-05,
"loss": 0.32495584106445313,
"step": 70000
},
{
"epoch": 0.9998581761452277,
"grad_norm": 7.784725189208984,
"learning_rate": 3.3335933437337494e-05,
"loss": 0.32551593017578123,
"step": 70500
},
{
"epoch": 1.0,
"eval_f1": 0.9001437024994532,
"eval_loss": 0.3130093514919281,
"eval_runtime": 35.0631,
"eval_samples_per_second": 1787.518,
"eval_steps_per_second": 223.454,
"step": 70510
},
{
"epoch": 1.0069493688838462,
"grad_norm": 18.948123931884766,
"learning_rate": 3.321774689169385e-05,
"loss": 0.2339570770263672,
"step": 71000
},
{
"epoch": 1.0140405616224648,
"grad_norm": 29.96381187438965,
"learning_rate": 3.309956034605021e-05,
"loss": 0.24531968688964845,
"step": 71500
},
{
"epoch": 1.0211317543610836,
"grad_norm": 9.150673866271973,
"learning_rate": 3.2981373800406564e-05,
"loss": 0.23301620483398439,
"step": 72000
},
{
"epoch": 1.0282229470997022,
"grad_norm": 3.4844117164611816,
"learning_rate": 3.286318725476292e-05,
"loss": 0.24279484558105469,
"step": 72500
},
{
"epoch": 1.0353141398383208,
"grad_norm": 16.226896286010742,
"learning_rate": 3.274500070911928e-05,
"loss": 0.26405026245117186,
"step": 73000
},
{
"epoch": 1.0424053325769393,
"grad_norm": 16.192201614379883,
"learning_rate": 3.262681416347563e-05,
"loss": 0.26442111206054686,
"step": 73500
},
{
"epoch": 1.0494965253155581,
"grad_norm": 4.49188756942749,
"learning_rate": 3.250862761783199e-05,
"loss": 0.24738125610351563,
"step": 74000
},
{
"epoch": 1.0565877180541767,
"grad_norm": 7.046379566192627,
"learning_rate": 3.239044107218834e-05,
"loss": 0.24555711364746094,
"step": 74500
},
{
"epoch": 1.0636789107927953,
"grad_norm": 6.727515697479248,
"learning_rate": 3.2272254526544696e-05,
"loss": 0.24705020141601564,
"step": 75000
},
{
"epoch": 1.0707701035314139,
"grad_norm": 0.3115968406200409,
"learning_rate": 3.215406798090105e-05,
"loss": 0.2594069213867187,
"step": 75500
},
{
"epoch": 1.0778612962700327,
"grad_norm": 0.05208302289247513,
"learning_rate": 3.203588143525741e-05,
"loss": 0.25708364868164063,
"step": 76000
},
{
"epoch": 1.0849524890086513,
"grad_norm": 37.00107955932617,
"learning_rate": 3.191769488961377e-05,
"loss": 0.2607995300292969,
"step": 76500
},
{
"epoch": 1.0920436817472698,
"grad_norm": 0.03668564558029175,
"learning_rate": 3.179950834397013e-05,
"loss": 0.24529719543457032,
"step": 77000
},
{
"epoch": 1.0991348744858884,
"grad_norm": 12.771923065185547,
"learning_rate": 3.168132179832648e-05,
"loss": 0.26328732299804686,
"step": 77500
},
{
"epoch": 1.1062260672245072,
"grad_norm": 14.881919860839844,
"learning_rate": 3.1563135252682835e-05,
"loss": 0.23408724975585937,
"step": 78000
},
{
"epoch": 1.1133172599631258,
"grad_norm": 0.04091072082519531,
"learning_rate": 3.144494870703919e-05,
"loss": 0.2638915710449219,
"step": 78500
},
{
"epoch": 1.1204084527017444,
"grad_norm": 0.10562195628881454,
"learning_rate": 3.132676216139555e-05,
"loss": 0.2641329040527344,
"step": 79000
},
{
"epoch": 1.1274996454403632,
"grad_norm": 21.768539428710938,
"learning_rate": 3.1208575615751905e-05,
"loss": 0.2338363494873047,
"step": 79500
},
{
"epoch": 1.1345908381789818,
"grad_norm": 17.84772300720215,
"learning_rate": 3.109038907010826e-05,
"loss": 0.27257015991210937,
"step": 80000
},
{
"epoch": 1.1416820309176003,
"grad_norm": 30.124338150024414,
"learning_rate": 3.0972202524464614e-05,
"loss": 0.24515379333496093,
"step": 80500
},
{
"epoch": 1.148773223656219,
"grad_norm": 11.695418357849121,
"learning_rate": 3.0854015978820975e-05,
"loss": 0.2721016845703125,
"step": 81000
},
{
"epoch": 1.1558644163948375,
"grad_norm": 26.140457153320312,
"learning_rate": 3.073582943317733e-05,
"loss": 0.24677125549316406,
"step": 81500
},
{
"epoch": 1.1629556091334563,
"grad_norm": 29.512819290161133,
"learning_rate": 3.061764288753369e-05,
"loss": 0.23260931396484374,
"step": 82000
},
{
"epoch": 1.1700468018720749,
"grad_norm": 18.654695510864258,
"learning_rate": 3.049945634189004e-05,
"loss": 0.2659488525390625,
"step": 82500
},
{
"epoch": 1.1771379946106935,
"grad_norm": 0.5423130393028259,
"learning_rate": 3.03812697962464e-05,
"loss": 0.28602008056640627,
"step": 83000
},
{
"epoch": 1.1842291873493123,
"grad_norm": 2.1269562244415283,
"learning_rate": 3.0263083250602753e-05,
"loss": 0.25295765686035154,
"step": 83500
},
{
"epoch": 1.1913203800879308,
"grad_norm": 0.2145138829946518,
"learning_rate": 3.0144896704959107e-05,
"loss": 0.270892822265625,
"step": 84000
},
{
"epoch": 1.1984115728265494,
"grad_norm": 14.912803649902344,
"learning_rate": 3.0026710159315465e-05,
"loss": 0.2607357177734375,
"step": 84500
},
{
"epoch": 1.205502765565168,
"grad_norm": 22.76487922668457,
"learning_rate": 2.990852361367182e-05,
"loss": 0.2576714782714844,
"step": 85000
},
{
"epoch": 1.2125939583037866,
"grad_norm": 41.264957427978516,
"learning_rate": 2.979033706802818e-05,
"loss": 0.25466714477539065,
"step": 85500
},
{
"epoch": 1.2196851510424054,
"grad_norm": 0.6082525253295898,
"learning_rate": 2.9672150522384534e-05,
"loss": 0.24727694702148437,
"step": 86000
},
{
"epoch": 1.226776343781024,
"grad_norm": 29.448619842529297,
"learning_rate": 2.955396397674089e-05,
"loss": 0.2584855041503906,
"step": 86500
},
{
"epoch": 1.2338675365196425,
"grad_norm": 26.285261154174805,
"learning_rate": 2.9435777431097243e-05,
"loss": 0.24061129760742186,
"step": 87000
},
{
"epoch": 1.2409587292582613,
"grad_norm": 0.16065184772014618,
"learning_rate": 2.93175908854536e-05,
"loss": 0.2392629089355469,
"step": 87500
},
{
"epoch": 1.24804992199688,
"grad_norm": 21.22818374633789,
"learning_rate": 2.9199404339809955e-05,
"loss": 0.2565277404785156,
"step": 88000
},
{
"epoch": 1.2551411147354985,
"grad_norm": 1.9699393510818481,
"learning_rate": 2.9081217794166316e-05,
"loss": 0.2656244201660156,
"step": 88500
},
{
"epoch": 1.262232307474117,
"grad_norm": 0.008314297534525394,
"learning_rate": 2.896303124852267e-05,
"loss": 0.2834685974121094,
"step": 89000
},
{
"epoch": 1.2693235002127357,
"grad_norm": 29.66657066345215,
"learning_rate": 2.8844844702879025e-05,
"loss": 0.22878916931152343,
"step": 89500
},
{
"epoch": 1.2764146929513545,
"grad_norm": 5.645302772521973,
"learning_rate": 2.8726658157235382e-05,
"loss": 0.2764334716796875,
"step": 90000
},
{
"epoch": 1.283505885689973,
"grad_norm": 40.7809944152832,
"learning_rate": 2.8608471611591737e-05,
"loss": 0.26810882568359373,
"step": 90500
},
{
"epoch": 1.2905970784285916,
"grad_norm": 0.20153196156024933,
"learning_rate": 2.849028506594809e-05,
"loss": 0.2662352294921875,
"step": 91000
},
{
"epoch": 1.2976882711672104,
"grad_norm": 15.62852668762207,
"learning_rate": 2.8372098520304452e-05,
"loss": 0.24166206359863282,
"step": 91500
},
{
"epoch": 1.304779463905829,
"grad_norm": 9.84329891204834,
"learning_rate": 2.8253911974660806e-05,
"loss": 0.25200973510742186,
"step": 92000
},
{
"epoch": 1.3118706566444476,
"grad_norm": 11.219542503356934,
"learning_rate": 2.8135725429017164e-05,
"loss": 0.2455371856689453,
"step": 92500
},
{
"epoch": 1.3189618493830662,
"grad_norm": 6.952165603637695,
"learning_rate": 2.8017538883373518e-05,
"loss": 0.23567097473144533,
"step": 93000
},
{
"epoch": 1.3260530421216847,
"grad_norm": 0.18090137839317322,
"learning_rate": 2.7899352337729872e-05,
"loss": 0.25478639221191407,
"step": 93500
},
{
"epoch": 1.3331442348603035,
"grad_norm": 6.70249605178833,
"learning_rate": 2.7781165792086227e-05,
"loss": 0.2323372344970703,
"step": 94000
},
{
"epoch": 1.3402354275989221,
"grad_norm": 15.918278694152832,
"learning_rate": 2.7662979246442588e-05,
"loss": 0.24013563537597657,
"step": 94500
},
{
"epoch": 1.3473266203375407,
"grad_norm": 15.899653434753418,
"learning_rate": 2.7544792700798942e-05,
"loss": 0.289270263671875,
"step": 95000
},
{
"epoch": 1.3544178130761595,
"grad_norm": 0.18003711104393005,
"learning_rate": 2.74266061551553e-05,
"loss": 0.2555249786376953,
"step": 95500
},
{
"epoch": 1.361509005814778,
"grad_norm": 13.276187896728516,
"learning_rate": 2.7308419609511654e-05,
"loss": 0.23787432861328126,
"step": 96000
},
{
"epoch": 1.3686001985533967,
"grad_norm": 8.532690048217773,
"learning_rate": 2.719023306386801e-05,
"loss": 0.25991943359375,
"step": 96500
},
{
"epoch": 1.3756913912920155,
"grad_norm": 4.646186828613281,
"learning_rate": 2.7072046518224363e-05,
"loss": 0.21854473876953126,
"step": 97000
},
{
"epoch": 1.382782584030634,
"grad_norm": 21.81673240661621,
"learning_rate": 2.6953859972580724e-05,
"loss": 0.2662290954589844,
"step": 97500
},
{
"epoch": 1.3898737767692526,
"grad_norm": 28.627748489379883,
"learning_rate": 2.683567342693708e-05,
"loss": 0.24742735290527343,
"step": 98000
},
{
"epoch": 1.3969649695078712,
"grad_norm": 33.29374313354492,
"learning_rate": 2.6717486881293436e-05,
"loss": 0.24210856628417968,
"step": 98500
},
{
"epoch": 1.4040561622464898,
"grad_norm": 0.2819039225578308,
"learning_rate": 2.659930033564979e-05,
"loss": 0.24692779541015625,
"step": 99000
},
{
"epoch": 1.4111473549851086,
"grad_norm": 17.91493797302246,
"learning_rate": 2.6481113790006144e-05,
"loss": 0.2515403747558594,
"step": 99500
},
{
"epoch": 1.4182385477237271,
"grad_norm": 13.0459566116333,
"learning_rate": 2.6362927244362502e-05,
"loss": 0.26895028686523437,
"step": 100000
},
{
"epoch": 1.4253297404623457,
"grad_norm": 0.16175471246242523,
"learning_rate": 2.6244740698718863e-05,
"loss": 0.2610643005371094,
"step": 100500
},
{
"epoch": 1.4324209332009645,
"grad_norm": 27.48076057434082,
"learning_rate": 2.6126554153075217e-05,
"loss": 0.24979777526855468,
"step": 101000
},
{
"epoch": 1.439512125939583,
"grad_norm": 19.9309139251709,
"learning_rate": 2.600836760743157e-05,
"loss": 0.23954156494140624,
"step": 101500
},
{
"epoch": 1.4466033186782017,
"grad_norm": 0.9473751187324524,
"learning_rate": 2.5890181061787926e-05,
"loss": 0.2484783935546875,
"step": 102000
},
{
"epoch": 1.4536945114168203,
"grad_norm": 0.019480137154459953,
"learning_rate": 2.5771994516144284e-05,
"loss": 0.2650618591308594,
"step": 102500
},
{
"epoch": 1.4607857041554388,
"grad_norm": 5.095986366271973,
"learning_rate": 2.5653807970500638e-05,
"loss": 0.24525790405273437,
"step": 103000
},
{
"epoch": 1.4678768968940576,
"grad_norm": 1.9547197818756104,
"learning_rate": 2.5535621424857e-05,
"loss": 0.2501990814208984,
"step": 103500
},
{
"epoch": 1.4749680896326762,
"grad_norm": 16.961444854736328,
"learning_rate": 2.5417434879213353e-05,
"loss": 0.26945120239257814,
"step": 104000
},
{
"epoch": 1.4820592823712948,
"grad_norm": 3.286417007446289,
"learning_rate": 2.5299248333569707e-05,
"loss": 0.20170649719238282,
"step": 104500
},
{
"epoch": 1.4891504751099136,
"grad_norm": 4.446686267852783,
"learning_rate": 2.5181061787926065e-05,
"loss": 0.2484140167236328,
"step": 105000
},
{
"epoch": 1.4962416678485322,
"grad_norm": 13.637587547302246,
"learning_rate": 2.506287524228242e-05,
"loss": 0.25150202941894534,
"step": 105500
},
{
"epoch": 1.5033328605871508,
"grad_norm": 13.85167121887207,
"learning_rate": 2.4944688696638777e-05,
"loss": 0.24099073791503905,
"step": 106000
},
{
"epoch": 1.5104240533257693,
"grad_norm": 3.044691801071167,
"learning_rate": 2.482650215099513e-05,
"loss": 0.22556625366210936,
"step": 106500
},
{
"epoch": 1.517515246064388,
"grad_norm": 12.65417194366455,
"learning_rate": 2.4708315605351486e-05,
"loss": 0.23180502319335938,
"step": 107000
},
{
"epoch": 1.5246064388030067,
"grad_norm": 0.14622563123703003,
"learning_rate": 2.4590129059707843e-05,
"loss": 0.23009732055664062,
"step": 107500
},
{
"epoch": 1.5316976315416253,
"grad_norm": 0.06789112836122513,
"learning_rate": 2.44719425140642e-05,
"loss": 0.22312631225585938,
"step": 108000
},
{
"epoch": 1.5387888242802439,
"grad_norm": 11.768181800842285,
"learning_rate": 2.4353755968420555e-05,
"loss": 0.25088430786132815,
"step": 108500
},
{
"epoch": 1.5458800170188627,
"grad_norm": 2.2163679599761963,
"learning_rate": 2.4235569422776913e-05,
"loss": 0.2586100769042969,
"step": 109000
},
{
"epoch": 1.5529712097574813,
"grad_norm": 28.564294815063477,
"learning_rate": 2.4117382877133267e-05,
"loss": 0.23646495056152345,
"step": 109500
},
{
"epoch": 1.5600624024960998,
"grad_norm": 9.31340503692627,
"learning_rate": 2.3999196331489625e-05,
"loss": 0.24966954040527345,
"step": 110000
},
{
"epoch": 1.5671535952347186,
"grad_norm": 0.030354458838701248,
"learning_rate": 2.3881009785845983e-05,
"loss": 0.21572161865234374,
"step": 110500
},
{
"epoch": 1.574244787973337,
"grad_norm": 0.21176375448703766,
"learning_rate": 2.3762823240202337e-05,
"loss": 0.2511417388916016,
"step": 111000
},
{
"epoch": 1.5813359807119558,
"grad_norm": 21.672609329223633,
"learning_rate": 2.364463669455869e-05,
"loss": 0.2573843078613281,
"step": 111500
},
{
"epoch": 1.5884271734505744,
"grad_norm": 24.937227249145508,
"learning_rate": 2.352645014891505e-05,
"loss": 0.2552000427246094,
"step": 112000
},
{
"epoch": 1.595518366189193,
"grad_norm": 5.9547929763793945,
"learning_rate": 2.3408263603271403e-05,
"loss": 0.22973036193847657,
"step": 112500
},
{
"epoch": 1.6026095589278118,
"grad_norm": 18.1229248046875,
"learning_rate": 2.329007705762776e-05,
"loss": 0.25020263671875,
"step": 113000
},
{
"epoch": 1.6097007516664303,
"grad_norm": 2.4165852069854736,
"learning_rate": 2.317189051198412e-05,
"loss": 0.22359278869628907,
"step": 113500
},
{
"epoch": 1.616791944405049,
"grad_norm": 16.324846267700195,
"learning_rate": 2.3053703966340473e-05,
"loss": 0.22524745178222655,
"step": 114000
},
{
"epoch": 1.6238831371436677,
"grad_norm": 25.62078285217285,
"learning_rate": 2.2935517420696827e-05,
"loss": 0.22996726989746094,
"step": 114500
},
{
"epoch": 1.630974329882286,
"grad_norm": 2.2023043632507324,
"learning_rate": 2.2817330875053185e-05,
"loss": 0.2342103576660156,
"step": 115000
},
{
"epoch": 1.6380655226209049,
"grad_norm": 15.966785430908203,
"learning_rate": 2.2699144329409542e-05,
"loss": 0.22872525024414062,
"step": 115500
},
{
"epoch": 1.6451567153595235,
"grad_norm": 30.15620994567871,
"learning_rate": 2.2580957783765897e-05,
"loss": 0.2582462463378906,
"step": 116000
},
{
"epoch": 1.652247908098142,
"grad_norm": 24.71402931213379,
"learning_rate": 2.2462771238122254e-05,
"loss": 0.24020169067382813,
"step": 116500
},
{
"epoch": 1.6593391008367608,
"grad_norm": 3.300433397293091,
"learning_rate": 2.234458469247861e-05,
"loss": 0.2408741455078125,
"step": 117000
},
{
"epoch": 1.6664302935753794,
"grad_norm": 12.283791542053223,
"learning_rate": 2.2226398146834966e-05,
"loss": 0.26206723022460937,
"step": 117500
},
{
"epoch": 1.673521486313998,
"grad_norm": 0.08979803323745728,
"learning_rate": 2.2108211601191324e-05,
"loss": 0.23730998229980468,
"step": 118000
},
{
"epoch": 1.6806126790526168,
"grad_norm": 0.06282109022140503,
"learning_rate": 2.1990025055547678e-05,
"loss": 0.23903207397460938,
"step": 118500
},
{
"epoch": 1.6877038717912352,
"grad_norm": 0.016728730872273445,
"learning_rate": 2.1871838509904033e-05,
"loss": 0.2454003601074219,
"step": 119000
},
{
"epoch": 1.694795064529854,
"grad_norm": 2.2816197872161865,
"learning_rate": 2.175365196426039e-05,
"loss": 0.24397659301757812,
"step": 119500
},
{
"epoch": 1.7018862572684725,
"grad_norm": 26.379451751708984,
"learning_rate": 2.1635465418616745e-05,
"loss": 0.24761070251464845,
"step": 120000
},
{
"epoch": 1.7089774500070911,
"grad_norm": 47.5869026184082,
"learning_rate": 2.1517278872973102e-05,
"loss": 0.2261453857421875,
"step": 120500
},
{
"epoch": 1.71606864274571,
"grad_norm": 2.1440539360046387,
"learning_rate": 2.139909232732946e-05,
"loss": 0.20931365966796875,
"step": 121000
},
{
"epoch": 1.7231598354843285,
"grad_norm": 30.778135299682617,
"learning_rate": 2.1280905781685814e-05,
"loss": 0.2319616241455078,
"step": 121500
},
{
"epoch": 1.730251028222947,
"grad_norm": 21.168132781982422,
"learning_rate": 2.116271923604217e-05,
"loss": 0.21780960083007814,
"step": 122000
},
{
"epoch": 1.7373422209615659,
"grad_norm": 9.625178337097168,
"learning_rate": 2.1044532690398526e-05,
"loss": 0.2460269317626953,
"step": 122500
},
{
"epoch": 1.7444334137001842,
"grad_norm": 26.388690948486328,
"learning_rate": 2.0926346144754884e-05,
"loss": 0.23820440673828125,
"step": 123000
},
{
"epoch": 1.751524606438803,
"grad_norm": 14.67889404296875,
"learning_rate": 2.0808159599111238e-05,
"loss": 0.20397705078125,
"step": 123500
},
{
"epoch": 1.7586157991774216,
"grad_norm": 1.371814250946045,
"learning_rate": 2.0689973053467596e-05,
"loss": 0.25807009887695315,
"step": 124000
},
{
"epoch": 1.7657069919160402,
"grad_norm": 20.472400665283203,
"learning_rate": 2.057178650782395e-05,
"loss": 0.252404052734375,
"step": 124500
},
{
"epoch": 1.772798184654659,
"grad_norm": 17.071815490722656,
"learning_rate": 2.0453599962180304e-05,
"loss": 0.25610809326171874,
"step": 125000
},
{
"epoch": 1.7798893773932776,
"grad_norm": 3.6083006858825684,
"learning_rate": 2.0335413416536662e-05,
"loss": 0.24112467956542968,
"step": 125500
},
{
"epoch": 1.7869805701318962,
"grad_norm": 21.218019485473633,
"learning_rate": 2.021722687089302e-05,
"loss": 0.22636663818359376,
"step": 126000
},
{
"epoch": 1.794071762870515,
"grad_norm": 0.1448567509651184,
"learning_rate": 2.0099040325249374e-05,
"loss": 0.2508505249023438,
"step": 126500
},
{
"epoch": 1.8011629556091333,
"grad_norm": 0.1806713044643402,
"learning_rate": 1.9980853779605728e-05,
"loss": 0.24530409240722656,
"step": 127000
},
{
"epoch": 1.808254148347752,
"grad_norm": 20.15835952758789,
"learning_rate": 1.9862667233962086e-05,
"loss": 0.2393865966796875,
"step": 127500
},
{
"epoch": 1.8153453410863707,
"grad_norm": 33.55228805541992,
"learning_rate": 1.9744480688318444e-05,
"loss": 0.21739024353027345,
"step": 128000
},
{
"epoch": 1.8224365338249893,
"grad_norm": 0.005695621017366648,
"learning_rate": 1.9626294142674798e-05,
"loss": 0.22674476623535156,
"step": 128500
},
{
"epoch": 1.829527726563608,
"grad_norm": 0.22916552424430847,
"learning_rate": 1.9508107597031156e-05,
"loss": 0.2238863983154297,
"step": 129000
},
{
"epoch": 1.8366189193022266,
"grad_norm": 23.052061080932617,
"learning_rate": 1.938992105138751e-05,
"loss": 0.23063746643066407,
"step": 129500
},
{
"epoch": 1.8437101120408452,
"grad_norm": 44.00524139404297,
"learning_rate": 1.9271734505743867e-05,
"loss": 0.28974740600585935,
"step": 130000
},
{
"epoch": 1.850801304779464,
"grad_norm": 22.83168601989746,
"learning_rate": 1.9153547960100225e-05,
"loss": 0.26516534423828125,
"step": 130500
},
{
"epoch": 1.8578924975180824,
"grad_norm": 6.64744234085083,
"learning_rate": 1.903536141445658e-05,
"loss": 0.23341806030273438,
"step": 131000
},
{
"epoch": 1.8649836902567012,
"grad_norm": 0.2639598548412323,
"learning_rate": 1.8917174868812934e-05,
"loss": 0.2186959228515625,
"step": 131500
},
{
"epoch": 1.8720748829953198,
"grad_norm": 0.0198422372341156,
"learning_rate": 1.879898832316929e-05,
"loss": 0.2466629180908203,
"step": 132000
},
{
"epoch": 1.8791660757339383,
"grad_norm": 8.830817222595215,
"learning_rate": 1.8680801777525646e-05,
"loss": 0.22397691345214843,
"step": 132500
},
{
"epoch": 1.8862572684725571,
"grad_norm": 1.0056872367858887,
"learning_rate": 1.8562615231882003e-05,
"loss": 0.2407335205078125,
"step": 133000
},
{
"epoch": 1.8933484612111757,
"grad_norm": 48.30131149291992,
"learning_rate": 1.844442868623836e-05,
"loss": 0.2587491455078125,
"step": 133500
},
{
"epoch": 1.9004396539497943,
"grad_norm": 23.683746337890625,
"learning_rate": 1.8326242140594715e-05,
"loss": 0.2463997802734375,
"step": 134000
},
{
"epoch": 1.907530846688413,
"grad_norm": 24.923192977905273,
"learning_rate": 1.820805559495107e-05,
"loss": 0.2411627197265625,
"step": 134500
},
{
"epoch": 1.9146220394270315,
"grad_norm": 0.06352449953556061,
"learning_rate": 1.8089869049307427e-05,
"loss": 0.22823338317871095,
"step": 135000
},
{
"epoch": 1.9217132321656503,
"grad_norm": 32.77594757080078,
"learning_rate": 1.7971682503663785e-05,
"loss": 0.21709400939941406,
"step": 135500
},
{
"epoch": 1.9288044249042688,
"grad_norm": 0.017425935715436935,
"learning_rate": 1.785349595802014e-05,
"loss": 0.23348135375976561,
"step": 136000
},
{
"epoch": 1.9358956176428874,
"grad_norm": 0.06207435205578804,
"learning_rate": 1.7735309412376497e-05,
"loss": 0.24263145446777343,
"step": 136500
},
{
"epoch": 1.9429868103815062,
"grad_norm": 27.20115852355957,
"learning_rate": 1.761712286673285e-05,
"loss": 0.21952764892578125,
"step": 137000
},
{
"epoch": 1.9500780031201248,
"grad_norm": 16.1690673828125,
"learning_rate": 1.7498936321089205e-05,
"loss": 0.24376431274414062,
"step": 137500
},
{
"epoch": 1.9571691958587434,
"grad_norm": 9.383126258850098,
"learning_rate": 1.7380749775445567e-05,
"loss": 0.22622024536132812,
"step": 138000
},
{
"epoch": 1.9642603885973622,
"grad_norm": 2.753221035003662,
"learning_rate": 1.726256322980192e-05,
"loss": 0.22754640197753906,
"step": 138500
},
{
"epoch": 1.9713515813359808,
"grad_norm": 3.7281320095062256,
"learning_rate": 1.7144376684158275e-05,
"loss": 0.24726861572265624,
"step": 139000
},
{
"epoch": 1.9784427740745993,
"grad_norm": 15.740147590637207,
"learning_rate": 1.7026190138514633e-05,
"loss": 0.22890939331054688,
"step": 139500
},
{
"epoch": 1.9855339668132181,
"grad_norm": 0.003955185413360596,
"learning_rate": 1.6908003592870987e-05,
"loss": 0.2409364471435547,
"step": 140000
},
{
"epoch": 1.9926251595518365,
"grad_norm": 5.179277420043945,
"learning_rate": 1.6789817047227345e-05,
"loss": 0.23150363159179688,
"step": 140500
},
{
"epoch": 1.9997163522904553,
"grad_norm": 1.189130187034607,
"learning_rate": 1.6671630501583702e-05,
"loss": 0.2506495666503906,
"step": 141000
},
{
"epoch": 2.0,
"eval_f1": 0.9113587652715626,
"eval_loss": 0.30701881647109985,
"eval_runtime": 34.7472,
"eval_samples_per_second": 1803.773,
"eval_steps_per_second": 225.486,
"step": 141020
},
{
"epoch": 2.006807545029074,
"grad_norm": 8.762104034423828,
"learning_rate": 1.6553443955940057e-05,
"loss": 0.13735191345214845,
"step": 141500
},
{
"epoch": 2.0138987377676925,
"grad_norm": 16.843982696533203,
"learning_rate": 1.643525741029641e-05,
"loss": 0.13929669189453125,
"step": 142000
},
{
"epoch": 2.0209899305063113,
"grad_norm": 0.14556214213371277,
"learning_rate": 1.631707086465277e-05,
"loss": 0.165760986328125,
"step": 142500
},
{
"epoch": 2.0280811232449296,
"grad_norm": 14.105688095092773,
"learning_rate": 1.6198884319009126e-05,
"loss": 0.14633389282226564,
"step": 143000
},
{
"epoch": 2.0351723159835484,
"grad_norm": 11.033661842346191,
"learning_rate": 1.608069777336548e-05,
"loss": 0.1571947784423828,
"step": 143500
},
{
"epoch": 2.042263508722167,
"grad_norm": 0.4138220250606537,
"learning_rate": 1.596251122772184e-05,
"loss": 0.1553509979248047,
"step": 144000
},
{
"epoch": 2.0493547014607856,
"grad_norm": 0.18340089917182922,
"learning_rate": 1.5844324682078193e-05,
"loss": 0.14218241882324217,
"step": 144500
},
{
"epoch": 2.0564458941994044,
"grad_norm": 26.402450561523438,
"learning_rate": 1.5726138136434547e-05,
"loss": 0.1493837127685547,
"step": 145000
},
{
"epoch": 2.063537086938023,
"grad_norm": 0.017796684056520462,
"learning_rate": 1.5607951590790908e-05,
"loss": 0.13917120361328125,
"step": 145500
},
{
"epoch": 2.0706282796766415,
"grad_norm": 4.48541784286499,
"learning_rate": 1.5489765045147262e-05,
"loss": 0.166038330078125,
"step": 146000
},
{
"epoch": 2.0777194724152603,
"grad_norm": 0.04194904491305351,
"learning_rate": 1.5371578499503617e-05,
"loss": 0.17019865417480468,
"step": 146500
},
{
"epoch": 2.0848106651538787,
"grad_norm": 0.08959656208753586,
"learning_rate": 1.5253391953859974e-05,
"loss": 0.17017556762695313,
"step": 147000
},
{
"epoch": 2.0919018578924975,
"grad_norm": 0.024056239053606987,
"learning_rate": 1.513520540821633e-05,
"loss": 0.1524031982421875,
"step": 147500
},
{
"epoch": 2.0989930506311163,
"grad_norm": 3.757331132888794,
"learning_rate": 1.5017018862572684e-05,
"loss": 0.16371908569335938,
"step": 148000
},
{
"epoch": 2.1060842433697347,
"grad_norm": 0.005578572396188974,
"learning_rate": 1.4898832316929042e-05,
"loss": 0.14432456970214844,
"step": 148500
},
{
"epoch": 2.1131754361083535,
"grad_norm": 0.20444293320178986,
"learning_rate": 1.4780645771285398e-05,
"loss": 0.15017152404785156,
"step": 149000
},
{
"epoch": 2.1202666288469723,
"grad_norm": 31.46082305908203,
"learning_rate": 1.4662459225641752e-05,
"loss": 0.1499925079345703,
"step": 149500
},
{
"epoch": 2.1273578215855906,
"grad_norm": 0.04699752479791641,
"learning_rate": 1.4544272679998112e-05,
"loss": 0.14757901000976562,
"step": 150000
},
{
"epoch": 2.1344490143242094,
"grad_norm": 0.09684433788061142,
"learning_rate": 1.4426086134354466e-05,
"loss": 0.1339453125,
"step": 150500
},
{
"epoch": 2.1415402070628278,
"grad_norm": 4.374368190765381,
"learning_rate": 1.4307899588710822e-05,
"loss": 0.18209759521484375,
"step": 151000
},
{
"epoch": 2.1486313998014466,
"grad_norm": 3.098288059234619,
"learning_rate": 1.4189713043067176e-05,
"loss": 0.15519505310058593,
"step": 151500
},
{
"epoch": 2.1557225925400654,
"grad_norm": 36.79690933227539,
"learning_rate": 1.4071526497423534e-05,
"loss": 0.16159878540039063,
"step": 152000
},
{
"epoch": 2.1628137852786837,
"grad_norm": 12.765725135803223,
"learning_rate": 1.395333995177989e-05,
"loss": 0.14087939453125,
"step": 152500
},
{
"epoch": 2.1699049780173025,
"grad_norm": 39.51382827758789,
"learning_rate": 1.3835153406136244e-05,
"loss": 0.17208224487304688,
"step": 153000
},
{
"epoch": 2.1769961707559213,
"grad_norm": 0.0060351816937327385,
"learning_rate": 1.3716966860492602e-05,
"loss": 0.14393453979492188,
"step": 153500
},
{
"epoch": 2.1840873634945397,
"grad_norm": 10.022261619567871,
"learning_rate": 1.3598780314848958e-05,
"loss": 0.14195445251464844,
"step": 154000
},
{
"epoch": 2.1911785562331585,
"grad_norm": 13.055335998535156,
"learning_rate": 1.3480593769205312e-05,
"loss": 0.16839701843261717,
"step": 154500
},
{
"epoch": 2.198269748971777,
"grad_norm": 0.005155665799975395,
"learning_rate": 1.3362407223561672e-05,
"loss": 0.13682273864746095,
"step": 155000
},
{
"epoch": 2.2053609417103957,
"grad_norm": 0.03768813982605934,
"learning_rate": 1.3244220677918026e-05,
"loss": 0.147459716796875,
"step": 155500
},
{
"epoch": 2.2124521344490145,
"grad_norm": 0.0052944389171898365,
"learning_rate": 1.3126034132274382e-05,
"loss": 0.15078125,
"step": 156000
},
{
"epoch": 2.219543327187633,
"grad_norm": 0.05137820541858673,
"learning_rate": 1.300784758663074e-05,
"loss": 0.1661295928955078,
"step": 156500
},
{
"epoch": 2.2266345199262516,
"grad_norm": 1.7747735977172852,
"learning_rate": 1.2889661040987094e-05,
"loss": 0.1691404266357422,
"step": 157000
},
{
"epoch": 2.2337257126648704,
"grad_norm": 0.5062932968139648,
"learning_rate": 1.277147449534345e-05,
"loss": 0.13608209228515625,
"step": 157500
},
{
"epoch": 2.2408169054034888,
"grad_norm": 0.00868254341185093,
"learning_rate": 1.2653287949699807e-05,
"loss": 0.1646303253173828,
"step": 158000
},
{
"epoch": 2.2479080981421076,
"grad_norm": 37.39674758911133,
"learning_rate": 1.2535101404056163e-05,
"loss": 0.14406378173828124,
"step": 158500
},
{
"epoch": 2.2549992908807264,
"grad_norm": 0.05140453577041626,
"learning_rate": 1.241691485841252e-05,
"loss": 0.1655428924560547,
"step": 159000
},
{
"epoch": 2.2620904836193447,
"grad_norm": 0.6167375445365906,
"learning_rate": 1.2298728312768874e-05,
"loss": 0.15687255859375,
"step": 159500
},
{
"epoch": 2.2691816763579635,
"grad_norm": 0.25186359882354736,
"learning_rate": 1.2180541767125231e-05,
"loss": 0.15488937377929687,
"step": 160000
},
{
"epoch": 2.276272869096582,
"grad_norm": 0.7437479496002197,
"learning_rate": 1.2062355221481587e-05,
"loss": 0.17920101928710938,
"step": 160500
},
{
"epoch": 2.2833640618352007,
"grad_norm": 2.2038159370422363,
"learning_rate": 1.1944168675837943e-05,
"loss": 0.14488670349121094,
"step": 161000
},
{
"epoch": 2.2904552545738195,
"grad_norm": 0.09207261353731155,
"learning_rate": 1.18259821301943e-05,
"loss": 0.1460616455078125,
"step": 161500
},
{
"epoch": 2.297546447312438,
"grad_norm": 8.36626148223877,
"learning_rate": 1.1707795584550655e-05,
"loss": 0.1439178466796875,
"step": 162000
},
{
"epoch": 2.3046376400510566,
"grad_norm": 24.07008934020996,
"learning_rate": 1.1589609038907011e-05,
"loss": 0.1375425567626953,
"step": 162500
},
{
"epoch": 2.311728832789675,
"grad_norm": 0.006591141689568758,
"learning_rate": 1.1471422493263367e-05,
"loss": 0.14682974243164063,
"step": 163000
},
{
"epoch": 2.318820025528294,
"grad_norm": 0.003745208028703928,
"learning_rate": 1.1353235947619723e-05,
"loss": 0.17611679077148437,
"step": 163500
},
{
"epoch": 2.3259112182669126,
"grad_norm": 0.055207427591085434,
"learning_rate": 1.123504940197608e-05,
"loss": 0.13750846862792968,
"step": 164000
},
{
"epoch": 2.333002411005531,
"grad_norm": 24.4141902923584,
"learning_rate": 1.1116862856332435e-05,
"loss": 0.15058929443359376,
"step": 164500
},
{
"epoch": 2.3400936037441498,
"grad_norm": 0.039343949407339096,
"learning_rate": 1.0998676310688793e-05,
"loss": 0.1544068908691406,
"step": 165000
},
{
"epoch": 2.3471847964827686,
"grad_norm": 0.5133422613143921,
"learning_rate": 1.0880489765045147e-05,
"loss": 0.156828857421875,
"step": 165500
},
{
"epoch": 2.354275989221387,
"grad_norm": 0.019299687817692757,
"learning_rate": 1.0762303219401503e-05,
"loss": 0.14771522521972658,
"step": 166000
},
{
"epoch": 2.3613671819600057,
"grad_norm": 0.08121506869792938,
"learning_rate": 1.064411667375786e-05,
"loss": 0.15364268493652344,
"step": 166500
},
{
"epoch": 2.3684583746986245,
"grad_norm": 0.0018154352437704802,
"learning_rate": 1.0525930128114215e-05,
"loss": 0.14453233337402344,
"step": 167000
},
{
"epoch": 2.375549567437243,
"grad_norm": 21.995845794677734,
"learning_rate": 1.0407743582470573e-05,
"loss": 0.1485889434814453,
"step": 167500
},
{
"epoch": 2.3826407601758617,
"grad_norm": 0.7876914739608765,
"learning_rate": 1.0289557036826929e-05,
"loss": 0.14667256164550782,
"step": 168000
},
{
"epoch": 2.38973195291448,
"grad_norm": 0.005331524182111025,
"learning_rate": 1.0171370491183283e-05,
"loss": 0.1651925048828125,
"step": 168500
},
{
"epoch": 2.396823145653099,
"grad_norm": 1.219325304031372,
"learning_rate": 1.005318394553964e-05,
"loss": 0.1457272491455078,
"step": 169000
},
{
"epoch": 2.4039143383917176,
"grad_norm": 0.31564515829086304,
"learning_rate": 9.934997399895997e-06,
"loss": 0.15064247131347655,
"step": 169500
},
{
"epoch": 2.411005531130336,
"grad_norm": 0.013693287968635559,
"learning_rate": 9.816810854252353e-06,
"loss": 0.14803697204589844,
"step": 170000
},
{
"epoch": 2.418096723868955,
"grad_norm": 0.09091508388519287,
"learning_rate": 9.698624308608709e-06,
"loss": 0.15610772705078124,
"step": 170500
},
{
"epoch": 2.425187916607573,
"grad_norm": 37.69474411010742,
"learning_rate": 9.580437762965065e-06,
"loss": 0.16669456481933595,
"step": 171000
},
{
"epoch": 2.432279109346192,
"grad_norm": 0.05470133572816849,
"learning_rate": 9.46225121732142e-06,
"loss": 0.13893193054199218,
"step": 171500
},
{
"epoch": 2.4393703020848108,
"grad_norm": 1.0212795734405518,
"learning_rate": 9.344064671677777e-06,
"loss": 0.16194654846191406,
"step": 172000
},
{
"epoch": 2.446461494823429,
"grad_norm": 18.309724807739258,
"learning_rate": 9.225878126034133e-06,
"loss": 0.16784349060058593,
"step": 172500
},
{
"epoch": 2.453552687562048,
"grad_norm": 3.127192735671997,
"learning_rate": 9.107691580390489e-06,
"loss": 0.16073973083496093,
"step": 173000
},
{
"epoch": 2.4606438803006667,
"grad_norm": 10.823789596557617,
"learning_rate": 8.989505034746845e-06,
"loss": 0.14176687622070314,
"step": 173500
},
{
"epoch": 2.467735073039285,
"grad_norm": 0.016493933275341988,
"learning_rate": 8.8713184891032e-06,
"loss": 0.15874830627441405,
"step": 174000
},
{
"epoch": 2.474826265777904,
"grad_norm": 0.06581011414527893,
"learning_rate": 8.753131943459556e-06,
"loss": 0.1369631805419922,
"step": 174500
},
{
"epoch": 2.4819174585165227,
"grad_norm": 0.15490815043449402,
"learning_rate": 8.634945397815914e-06,
"loss": 0.16546914672851562,
"step": 175000
},
{
"epoch": 2.489008651255141,
"grad_norm": 3.7111988067626953,
"learning_rate": 8.516758852172268e-06,
"loss": 0.14232369995117186,
"step": 175500
},
{
"epoch": 2.49609984399376,
"grad_norm": 0.005735097918659449,
"learning_rate": 8.398572306528624e-06,
"loss": 0.15004513549804688,
"step": 176000
},
{
"epoch": 2.503191036732378,
"grad_norm": 0.1627586930990219,
"learning_rate": 8.280385760884982e-06,
"loss": 0.17055393981933595,
"step": 176500
},
{
"epoch": 2.510282229470997,
"grad_norm": 0.016294831410050392,
"learning_rate": 8.162199215241336e-06,
"loss": 0.14088502502441405,
"step": 177000
},
{
"epoch": 2.517373422209616,
"grad_norm": 0.20740552246570587,
"learning_rate": 8.044012669597694e-06,
"loss": 0.14491709899902344,
"step": 177500
},
{
"epoch": 2.524464614948234,
"grad_norm": 80.30838012695312,
"learning_rate": 7.92582612395405e-06,
"loss": 0.14266546630859375,
"step": 178000
},
{
"epoch": 2.531555807686853,
"grad_norm": 6.494327545166016,
"learning_rate": 7.807639578310404e-06,
"loss": 0.1425498504638672,
"step": 178500
},
{
"epoch": 2.5386470004254713,
"grad_norm": 10.817715644836426,
"learning_rate": 7.689453032666762e-06,
"loss": 0.13685794067382812,
"step": 179000
},
{
"epoch": 2.54573819316409,
"grad_norm": 0.05190029367804527,
"learning_rate": 7.571266487023118e-06,
"loss": 0.15212284851074218,
"step": 179500
},
{
"epoch": 2.552829385902709,
"grad_norm": 0.023630203679203987,
"learning_rate": 7.453079941379473e-06,
"loss": 0.13549761962890625,
"step": 180000
},
{
"epoch": 2.5599205786413277,
"grad_norm": 0.022259913384914398,
"learning_rate": 7.33489339573583e-06,
"loss": 0.13580258178710938,
"step": 180500
},
{
"epoch": 2.567011771379946,
"grad_norm": 0.05255912244319916,
"learning_rate": 7.216706850092187e-06,
"loss": 0.1679718780517578,
"step": 181000
},
{
"epoch": 2.574102964118565,
"grad_norm": 0.03855106234550476,
"learning_rate": 7.098520304448542e-06,
"loss": 0.16043946838378906,
"step": 181500
},
{
"epoch": 2.5811941568571832,
"grad_norm": 0.1921262890100479,
"learning_rate": 6.980333758804898e-06,
"loss": 0.15679566955566407,
"step": 182000
},
{
"epoch": 2.588285349595802,
"grad_norm": 0.03098134882748127,
"learning_rate": 6.862147213161255e-06,
"loss": 0.1534794921875,
"step": 182500
},
{
"epoch": 2.595376542334421,
"grad_norm": 22.469654083251953,
"learning_rate": 6.74396066751761e-06,
"loss": 0.13415251159667968,
"step": 183000
},
{
"epoch": 2.602467735073039,
"grad_norm": 0.003964544739574194,
"learning_rate": 6.625774121873967e-06,
"loss": 0.15105152893066406,
"step": 183500
},
{
"epoch": 2.609558927811658,
"grad_norm": 1.3596986532211304,
"learning_rate": 6.507587576230323e-06,
"loss": 0.17991926574707032,
"step": 184000
},
{
"epoch": 2.6166501205502763,
"grad_norm": 0.155672088265419,
"learning_rate": 6.389401030586678e-06,
"loss": 0.13662466430664064,
"step": 184500
},
{
"epoch": 2.623741313288895,
"grad_norm": 0.022043386474251747,
"learning_rate": 6.271214484943035e-06,
"loss": 0.15543783569335937,
"step": 185000
},
{
"epoch": 2.630832506027514,
"grad_norm": 0.004181036725640297,
"learning_rate": 6.153027939299391e-06,
"loss": 0.16623443603515625,
"step": 185500
},
{
"epoch": 2.6379236987661323,
"grad_norm": 0.015014543198049068,
"learning_rate": 6.0348413936557466e-06,
"loss": 0.13246311950683592,
"step": 186000
},
{
"epoch": 2.645014891504751,
"grad_norm": 0.02488175965845585,
"learning_rate": 5.9166548480121026e-06,
"loss": 0.14923362731933593,
"step": 186500
},
{
"epoch": 2.6521060842433695,
"grad_norm": 10.722357749938965,
"learning_rate": 5.7984683023684585e-06,
"loss": 0.14898843383789062,
"step": 187000
},
{
"epoch": 2.6591972769819883,
"grad_norm": 5.965242862701416,
"learning_rate": 5.6802817567248145e-06,
"loss": 0.13296836853027344,
"step": 187500
},
{
"epoch": 2.666288469720607,
"grad_norm": 0.0026237820275127888,
"learning_rate": 5.562095211081171e-06,
"loss": 0.13209194946289063,
"step": 188000
},
{
"epoch": 2.673379662459226,
"grad_norm": 0.46034377813339233,
"learning_rate": 5.443908665437527e-06,
"loss": 0.15388623046875,
"step": 188500
},
{
"epoch": 2.6804708551978442,
"grad_norm": 17.380584716796875,
"learning_rate": 5.3257221197938825e-06,
"loss": 0.12723853302001953,
"step": 189000
},
{
"epoch": 2.687562047936463,
"grad_norm": 2.5008175373077393,
"learning_rate": 5.2075355741502384e-06,
"loss": 0.1331744079589844,
"step": 189500
},
{
"epoch": 2.6946532406750814,
"grad_norm": 0.004737582989037037,
"learning_rate": 5.089349028506595e-06,
"loss": 0.15081929016113282,
"step": 190000
},
{
"epoch": 2.7017444334137,
"grad_norm": 0.08174813538789749,
"learning_rate": 4.971162482862951e-06,
"loss": 0.15177557373046874,
"step": 190500
},
{
"epoch": 2.708835626152319,
"grad_norm": 24.13783073425293,
"learning_rate": 4.852975937219307e-06,
"loss": 0.1373896484375,
"step": 191000
},
{
"epoch": 2.7159268188909373,
"grad_norm": 0.028941305354237556,
"learning_rate": 4.734789391575663e-06,
"loss": 0.16214389038085938,
"step": 191500
},
{
"epoch": 2.723018011629556,
"grad_norm": 13.542202949523926,
"learning_rate": 4.616602845932019e-06,
"loss": 0.161189208984375,
"step": 192000
},
{
"epoch": 2.7301092043681745,
"grad_norm": 0.18116530776023865,
"learning_rate": 4.498416300288375e-06,
"loss": 0.13959812927246093,
"step": 192500
},
{
"epoch": 2.7372003971067933,
"grad_norm": 60.92932891845703,
"learning_rate": 4.380229754644732e-06,
"loss": 0.13540277099609374,
"step": 193000
},
{
"epoch": 2.744291589845412,
"grad_norm": 0.014164292253553867,
"learning_rate": 4.262043209001088e-06,
"loss": 0.1398023223876953,
"step": 193500
},
{
"epoch": 2.751382782584031,
"grad_norm": 5.37201452255249,
"learning_rate": 4.143856663357443e-06,
"loss": 0.1264494171142578,
"step": 194000
},
{
"epoch": 2.7584739753226493,
"grad_norm": 0.0796019434928894,
"learning_rate": 4.0256701177138e-06,
"loss": 0.1359503173828125,
"step": 194500
},
{
"epoch": 2.765565168061268,
"grad_norm": 0.13115420937538147,
"learning_rate": 3.907483572070156e-06,
"loss": 0.15993971252441405,
"step": 195000
},
{
"epoch": 2.7726563607998864,
"grad_norm": 10.917163848876953,
"learning_rate": 3.7892970264265115e-06,
"loss": 0.16762310791015625,
"step": 195500
},
{
"epoch": 2.7797475535385052,
"grad_norm": 21.855243682861328,
"learning_rate": 3.6711104807828674e-06,
"loss": 0.12708675384521484,
"step": 196000
},
{
"epoch": 2.786838746277124,
"grad_norm": 20.499042510986328,
"learning_rate": 3.552923935139224e-06,
"loss": 0.12649768829345703,
"step": 196500
},
{
"epoch": 2.7939299390157424,
"grad_norm": 1.0606557130813599,
"learning_rate": 3.43473738949558e-06,
"loss": 0.1379012451171875,
"step": 197000
},
{
"epoch": 2.801021131754361,
"grad_norm": 0.117930106818676,
"learning_rate": 3.316550843851936e-06,
"loss": 0.16560685729980468,
"step": 197500
},
{
"epoch": 2.8081123244929795,
"grad_norm": 0.007242361083626747,
"learning_rate": 3.1983642982082922e-06,
"loss": 0.1315562744140625,
"step": 198000
},
{
"epoch": 2.8152035172315983,
"grad_norm": 0.005843205843120813,
"learning_rate": 3.080177752564648e-06,
"loss": 0.14702142333984375,
"step": 198500
},
{
"epoch": 2.822294709970217,
"grad_norm": 0.008035923354327679,
"learning_rate": 2.961991206921004e-06,
"loss": 0.14689279174804687,
"step": 199000
},
{
"epoch": 2.8293859027088355,
"grad_norm": 23.067476272583008,
"learning_rate": 2.84380466127736e-06,
"loss": 0.15188876342773439,
"step": 199500
},
{
"epoch": 2.8364770954474543,
"grad_norm": 0.43422043323516846,
"learning_rate": 2.7256181156337166e-06,
"loss": 0.12116779327392578,
"step": 200000
},
{
"epoch": 2.8435682881860727,
"grad_norm": 2.646021604537964,
"learning_rate": 2.6074315699900725e-06,
"loss": 0.13729490661621094,
"step": 200500
},
{
"epoch": 2.8506594809246915,
"grad_norm": 0.0913633182644844,
"learning_rate": 2.4892450243464285e-06,
"loss": 0.1404597625732422,
"step": 201000
},
{
"epoch": 2.8577506736633103,
"grad_norm": 0.09719549864530563,
"learning_rate": 2.3710584787027845e-06,
"loss": 0.1671805419921875,
"step": 201500
},
{
"epoch": 2.864841866401929,
"grad_norm": 0.0015564130153506994,
"learning_rate": 2.2528719330591405e-06,
"loss": 0.12479610443115234,
"step": 202000
},
{
"epoch": 2.8719330591405474,
"grad_norm": 0.10027438402175903,
"learning_rate": 2.134685387415497e-06,
"loss": 0.13885786437988282,
"step": 202500
},
{
"epoch": 2.879024251879166,
"grad_norm": 0.7187597155570984,
"learning_rate": 2.016498841771853e-06,
"loss": 0.12357424926757812,
"step": 203000
},
{
"epoch": 2.8861154446177846,
"grad_norm": 0.17996720969676971,
"learning_rate": 1.8983122961282088e-06,
"loss": 0.13657070922851564,
"step": 203500
},
{
"epoch": 2.8932066373564034,
"grad_norm": 7.7822771072387695,
"learning_rate": 1.780125750484565e-06,
"loss": 0.12291963958740235,
"step": 204000
},
{
"epoch": 2.900297830095022,
"grad_norm": 12.129283905029297,
"learning_rate": 1.6619392048409208e-06,
"loss": 0.14823594665527343,
"step": 204500
},
{
"epoch": 2.9073890228336405,
"grad_norm": 0.013198443688452244,
"learning_rate": 1.543752659197277e-06,
"loss": 0.14506388854980468,
"step": 205000
},
{
"epoch": 2.9144802155722593,
"grad_norm": 11.327927589416504,
"learning_rate": 1.425566113553633e-06,
"loss": 0.13541313171386718,
"step": 205500
},
{
"epoch": 2.9215714083108777,
"grad_norm": 5.3539652824401855,
"learning_rate": 1.3073795679099892e-06,
"loss": 0.1454547119140625,
"step": 206000
},
{
"epoch": 2.9286626010494965,
"grad_norm": 0.08805113285779953,
"learning_rate": 1.1891930222663454e-06,
"loss": 0.12136942291259765,
"step": 206500
},
{
"epoch": 2.9357537937881153,
"grad_norm": 0.001831616973504424,
"learning_rate": 1.0710064766227013e-06,
"loss": 0.152857177734375,
"step": 207000
},
{
"epoch": 2.9428449865267337,
"grad_norm": 0.1370995193719864,
"learning_rate": 9.528199309790573e-07,
"loss": 0.16752561950683595,
"step": 207500
},
{
"epoch": 2.9499361792653525,
"grad_norm": 19.748567581176758,
"learning_rate": 8.346333853354135e-07,
"loss": 0.13742178344726563,
"step": 208000
},
{
"epoch": 2.957027372003971,
"grad_norm": 0.002913739997893572,
"learning_rate": 7.164468396917696e-07,
"loss": 0.1452206268310547,
"step": 208500
},
{
"epoch": 2.9641185647425896,
"grad_norm": 35.350101470947266,
"learning_rate": 5.982602940481256e-07,
"loss": 0.1341029510498047,
"step": 209000
},
{
"epoch": 2.9712097574812084,
"grad_norm": 0.07304254174232483,
"learning_rate": 4.800737484044817e-07,
"loss": 0.1393485107421875,
"step": 209500
},
{
"epoch": 2.978300950219827,
"grad_norm": 29.43463897705078,
"learning_rate": 3.618872027608377e-07,
"loss": 0.14128144836425782,
"step": 210000
},
{
"epoch": 2.9853921429584456,
"grad_norm": 0.309042364358902,
"learning_rate": 2.437006571171938e-07,
"loss": 0.13661312866210937,
"step": 210500
},
{
"epoch": 2.9924833356970644,
"grad_norm": 0.006605884060263634,
"learning_rate": 1.2551411147354984e-07,
"loss": 0.1400542297363281,
"step": 211000
},
{
"epoch": 2.9995745284356827,
"grad_norm": 0.05949639901518822,
"learning_rate": 7.3275658299059235e-09,
"loss": 0.15822608947753905,
"step": 211500
},
{
"epoch": 3.0,
"eval_f1": 0.9179618788534967,
"eval_loss": 0.339036762714386,
"eval_runtime": 34.5239,
"eval_samples_per_second": 1815.439,
"eval_steps_per_second": 226.944,
"step": 211530
},
{
"epoch": 3.0,
"step": 211530,
"total_flos": 2.7880428532368384e+16,
"train_loss": 0.26259335841951326,
"train_runtime": 3658.4093,
"train_samples_per_second": 462.558,
"train_steps_per_second": 57.82
}
],
"logging_steps": 500,
"max_steps": 211530,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.7880428532368384e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}