terry69's picture
Model save
74d111b verified
raw
history blame contribute delete
No virus
65.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1863,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005367686527106817,
"grad_norm": 24.532250817459463,
"learning_rate": 5.3475935828877005e-08,
"loss": 1.3138,
"step": 1
},
{
"epoch": 0.0026838432635534087,
"grad_norm": 22.479300081612294,
"learning_rate": 2.6737967914438503e-07,
"loss": 1.3002,
"step": 5
},
{
"epoch": 0.005367686527106817,
"grad_norm": 15.54111760887706,
"learning_rate": 5.347593582887701e-07,
"loss": 1.2704,
"step": 10
},
{
"epoch": 0.008051529790660225,
"grad_norm": 12.534742860225304,
"learning_rate": 8.021390374331551e-07,
"loss": 1.1283,
"step": 15
},
{
"epoch": 0.010735373054213635,
"grad_norm": 9.147671503937955,
"learning_rate": 1.0695187165775401e-06,
"loss": 1.0341,
"step": 20
},
{
"epoch": 0.013419216317767043,
"grad_norm": 3.433701365796985,
"learning_rate": 1.3368983957219254e-06,
"loss": 0.9283,
"step": 25
},
{
"epoch": 0.01610305958132045,
"grad_norm": 3.4271738875345377,
"learning_rate": 1.6042780748663103e-06,
"loss": 0.8924,
"step": 30
},
{
"epoch": 0.01878690284487386,
"grad_norm": 2.8975789735077973,
"learning_rate": 1.8716577540106954e-06,
"loss": 0.8584,
"step": 35
},
{
"epoch": 0.02147074610842727,
"grad_norm": 2.8729414451167226,
"learning_rate": 2.1390374331550802e-06,
"loss": 0.8417,
"step": 40
},
{
"epoch": 0.024154589371980676,
"grad_norm": 2.827429910087497,
"learning_rate": 2.4064171122994653e-06,
"loss": 0.8229,
"step": 45
},
{
"epoch": 0.026838432635534086,
"grad_norm": 2.8959001486827574,
"learning_rate": 2.673796791443851e-06,
"loss": 0.8203,
"step": 50
},
{
"epoch": 0.029522275899087493,
"grad_norm": 3.0595595781040337,
"learning_rate": 2.9411764705882355e-06,
"loss": 0.8131,
"step": 55
},
{
"epoch": 0.0322061191626409,
"grad_norm": 3.0267540777499375,
"learning_rate": 3.2085561497326205e-06,
"loss": 0.8006,
"step": 60
},
{
"epoch": 0.03488996242619431,
"grad_norm": 3.0813472677719207,
"learning_rate": 3.4759358288770056e-06,
"loss": 0.7948,
"step": 65
},
{
"epoch": 0.03757380568974772,
"grad_norm": 3.0313107960276615,
"learning_rate": 3.7433155080213907e-06,
"loss": 0.7748,
"step": 70
},
{
"epoch": 0.040257648953301126,
"grad_norm": 3.0434680433124246,
"learning_rate": 4.010695187165775e-06,
"loss": 0.7711,
"step": 75
},
{
"epoch": 0.04294149221685454,
"grad_norm": 2.9437229789589527,
"learning_rate": 4.2780748663101604e-06,
"loss": 0.7757,
"step": 80
},
{
"epoch": 0.045625335480407946,
"grad_norm": 3.186097917871563,
"learning_rate": 4.5454545454545455e-06,
"loss": 0.7595,
"step": 85
},
{
"epoch": 0.04830917874396135,
"grad_norm": 3.001408491927411,
"learning_rate": 4.812834224598931e-06,
"loss": 0.7398,
"step": 90
},
{
"epoch": 0.05099302200751476,
"grad_norm": 3.255982858352429,
"learning_rate": 5.0802139037433165e-06,
"loss": 0.7472,
"step": 95
},
{
"epoch": 0.05367686527106817,
"grad_norm": 3.02587969572454,
"learning_rate": 5.347593582887702e-06,
"loss": 0.7477,
"step": 100
},
{
"epoch": 0.05636070853462158,
"grad_norm": 2.9034466316514718,
"learning_rate": 5.614973262032086e-06,
"loss": 0.7328,
"step": 105
},
{
"epoch": 0.059044551798174985,
"grad_norm": 2.963969783004761,
"learning_rate": 5.882352941176471e-06,
"loss": 0.7306,
"step": 110
},
{
"epoch": 0.06172839506172839,
"grad_norm": 3.011826081077009,
"learning_rate": 6.149732620320856e-06,
"loss": 0.7386,
"step": 115
},
{
"epoch": 0.0644122383252818,
"grad_norm": 3.0450295583090754,
"learning_rate": 6.417112299465241e-06,
"loss": 0.7278,
"step": 120
},
{
"epoch": 0.06709608158883522,
"grad_norm": 2.8442223467397247,
"learning_rate": 6.684491978609626e-06,
"loss": 0.7188,
"step": 125
},
{
"epoch": 0.06977992485238863,
"grad_norm": 2.896755919332201,
"learning_rate": 6.951871657754011e-06,
"loss": 0.7112,
"step": 130
},
{
"epoch": 0.07246376811594203,
"grad_norm": 2.9785923822216636,
"learning_rate": 7.219251336898396e-06,
"loss": 0.7006,
"step": 135
},
{
"epoch": 0.07514761137949544,
"grad_norm": 2.8639433452496337,
"learning_rate": 7.486631016042781e-06,
"loss": 0.7012,
"step": 140
},
{
"epoch": 0.07783145464304884,
"grad_norm": 2.9748426164928032,
"learning_rate": 7.754010695187166e-06,
"loss": 0.6996,
"step": 145
},
{
"epoch": 0.08051529790660225,
"grad_norm": 2.8259720368976606,
"learning_rate": 8.02139037433155e-06,
"loss": 0.7063,
"step": 150
},
{
"epoch": 0.08319914117015566,
"grad_norm": 2.988719545239136,
"learning_rate": 8.288770053475937e-06,
"loss": 0.7006,
"step": 155
},
{
"epoch": 0.08588298443370908,
"grad_norm": 2.920246855352462,
"learning_rate": 8.556149732620321e-06,
"loss": 0.7103,
"step": 160
},
{
"epoch": 0.08856682769726248,
"grad_norm": 3.0463191656329185,
"learning_rate": 8.823529411764707e-06,
"loss": 0.6985,
"step": 165
},
{
"epoch": 0.09125067096081589,
"grad_norm": 2.6865694036401706,
"learning_rate": 9.090909090909091e-06,
"loss": 0.6975,
"step": 170
},
{
"epoch": 0.0939345142243693,
"grad_norm": 2.626512525739788,
"learning_rate": 9.358288770053477e-06,
"loss": 0.7027,
"step": 175
},
{
"epoch": 0.0966183574879227,
"grad_norm": 2.8908193689229704,
"learning_rate": 9.625668449197861e-06,
"loss": 0.7071,
"step": 180
},
{
"epoch": 0.09930220075147611,
"grad_norm": 3.005600658965135,
"learning_rate": 9.893048128342247e-06,
"loss": 0.6974,
"step": 185
},
{
"epoch": 0.10198604401502952,
"grad_norm": 2.6820135855233427,
"learning_rate": 9.999920944317846e-06,
"loss": 0.7078,
"step": 190
},
{
"epoch": 0.10466988727858294,
"grad_norm": 2.8217337120554595,
"learning_rate": 9.99943783531341e-06,
"loss": 0.6827,
"step": 195
},
{
"epoch": 0.10735373054213634,
"grad_norm": 2.6986357719933087,
"learning_rate": 9.998515579512446e-06,
"loss": 0.7012,
"step": 200
},
{
"epoch": 0.11003757380568975,
"grad_norm": 2.5840789947652096,
"learning_rate": 9.997154257925199e-06,
"loss": 0.6933,
"step": 205
},
{
"epoch": 0.11272141706924316,
"grad_norm": 2.6923419523116348,
"learning_rate": 9.995353990129115e-06,
"loss": 0.6877,
"step": 210
},
{
"epoch": 0.11540526033279656,
"grad_norm": 2.6327095351046244,
"learning_rate": 9.99311493425834e-06,
"loss": 0.6913,
"step": 215
},
{
"epoch": 0.11808910359634997,
"grad_norm": 2.7716420958204337,
"learning_rate": 9.99043728698983e-06,
"loss": 0.6777,
"step": 220
},
{
"epoch": 0.12077294685990338,
"grad_norm": 2.5671683281410216,
"learning_rate": 9.987321283526072e-06,
"loss": 0.678,
"step": 225
},
{
"epoch": 0.12345679012345678,
"grad_norm": 2.6849722010316626,
"learning_rate": 9.983767197574432e-06,
"loss": 0.6908,
"step": 230
},
{
"epoch": 0.1261406333870102,
"grad_norm": 2.5611382815074015,
"learning_rate": 9.979775341323097e-06,
"loss": 0.6792,
"step": 235
},
{
"epoch": 0.1288244766505636,
"grad_norm": 2.5649832974368474,
"learning_rate": 9.975346065413673e-06,
"loss": 0.6856,
"step": 240
},
{
"epoch": 0.13150831991411702,
"grad_norm": 2.408926177053808,
"learning_rate": 9.970479758910365e-06,
"loss": 0.6904,
"step": 245
},
{
"epoch": 0.13419216317767044,
"grad_norm": 2.6082645630171726,
"learning_rate": 9.965176849265814e-06,
"loss": 0.6873,
"step": 250
},
{
"epoch": 0.13687600644122383,
"grad_norm": 2.5439914668381114,
"learning_rate": 9.959437802283552e-06,
"loss": 0.6773,
"step": 255
},
{
"epoch": 0.13955984970477725,
"grad_norm": 2.490950435247341,
"learning_rate": 9.953263122077077e-06,
"loss": 0.6755,
"step": 260
},
{
"epoch": 0.14224369296833064,
"grad_norm": 2.5615157225803595,
"learning_rate": 9.946653351025575e-06,
"loss": 0.6675,
"step": 265
},
{
"epoch": 0.14492753623188406,
"grad_norm": 2.5970332229833426,
"learning_rate": 9.939609069726279e-06,
"loss": 0.6727,
"step": 270
},
{
"epoch": 0.14761137949543746,
"grad_norm": 2.698178435782262,
"learning_rate": 9.932130896943477e-06,
"loss": 0.6651,
"step": 275
},
{
"epoch": 0.15029522275899088,
"grad_norm": 2.6376811569878114,
"learning_rate": 9.924219489554145e-06,
"loss": 0.6627,
"step": 280
},
{
"epoch": 0.1529790660225443,
"grad_norm": 2.597622100810795,
"learning_rate": 9.915875542490257e-06,
"loss": 0.6853,
"step": 285
},
{
"epoch": 0.1556629092860977,
"grad_norm": 2.6511726087211174,
"learning_rate": 9.907099788677745e-06,
"loss": 0.6701,
"step": 290
},
{
"epoch": 0.1583467525496511,
"grad_norm": 2.6406315274257337,
"learning_rate": 9.897892998972113e-06,
"loss": 0.6693,
"step": 295
},
{
"epoch": 0.1610305958132045,
"grad_norm": 2.4213035415558966,
"learning_rate": 9.888255982090728e-06,
"loss": 0.6602,
"step": 300
},
{
"epoch": 0.16371443907675792,
"grad_norm": 3.4846721277150046,
"learning_rate": 9.878189584541783e-06,
"loss": 0.6608,
"step": 305
},
{
"epoch": 0.16639828234031132,
"grad_norm": 7.014634191079299,
"learning_rate": 9.867694690549943e-06,
"loss": 0.6653,
"step": 310
},
{
"epoch": 0.16908212560386474,
"grad_norm": 2.932139360044067,
"learning_rate": 9.85677222197867e-06,
"loss": 0.6657,
"step": 315
},
{
"epoch": 0.17176596886741816,
"grad_norm": 2.3975958892517566,
"learning_rate": 9.845423138249254e-06,
"loss": 0.6529,
"step": 320
},
{
"epoch": 0.17444981213097155,
"grad_norm": 2.5923171187304477,
"learning_rate": 9.833648436256525e-06,
"loss": 0.6618,
"step": 325
},
{
"epoch": 0.17713365539452497,
"grad_norm": 2.4438855676344433,
"learning_rate": 9.821449150281308e-06,
"loss": 0.6483,
"step": 330
},
{
"epoch": 0.17981749865807836,
"grad_norm": 2.519109888602999,
"learning_rate": 9.808826351899551e-06,
"loss": 0.6515,
"step": 335
},
{
"epoch": 0.18250134192163178,
"grad_norm": 2.540504649667965,
"learning_rate": 9.795781149888216e-06,
"loss": 0.6629,
"step": 340
},
{
"epoch": 0.18518518518518517,
"grad_norm": 2.4014123234116,
"learning_rate": 9.782314690127867e-06,
"loss": 0.6631,
"step": 345
},
{
"epoch": 0.1878690284487386,
"grad_norm": 2.4262806054618484,
"learning_rate": 9.768428155502038e-06,
"loss": 0.6583,
"step": 350
},
{
"epoch": 0.19055287171229202,
"grad_norm": 2.401370354238805,
"learning_rate": 9.754122765793306e-06,
"loss": 0.6443,
"step": 355
},
{
"epoch": 0.1932367149758454,
"grad_norm": 2.569449085939293,
"learning_rate": 9.739399777576169e-06,
"loss": 0.6375,
"step": 360
},
{
"epoch": 0.19592055823939883,
"grad_norm": 2.631241782716603,
"learning_rate": 9.72426048410665e-06,
"loss": 0.6233,
"step": 365
},
{
"epoch": 0.19860440150295222,
"grad_norm": 2.426731921614948,
"learning_rate": 9.70870621520871e-06,
"loss": 0.622,
"step": 370
},
{
"epoch": 0.20128824476650564,
"grad_norm": 2.672676505801346,
"learning_rate": 9.692738337157441e-06,
"loss": 0.6304,
"step": 375
},
{
"epoch": 0.20397208803005903,
"grad_norm": 2.3546077000692054,
"learning_rate": 9.676358252559034e-06,
"loss": 0.6471,
"step": 380
},
{
"epoch": 0.20665593129361245,
"grad_norm": 2.603636786602239,
"learning_rate": 9.6595674002276e-06,
"loss": 0.6518,
"step": 385
},
{
"epoch": 0.20933977455716588,
"grad_norm": 2.6654147172003766,
"learning_rate": 9.642367255058767e-06,
"loss": 0.6432,
"step": 390
},
{
"epoch": 0.21202361782071927,
"grad_norm": 2.7927745223130342,
"learning_rate": 9.624759327900131e-06,
"loss": 0.6221,
"step": 395
},
{
"epoch": 0.2147074610842727,
"grad_norm": 2.322677945570656,
"learning_rate": 9.606745165418554e-06,
"loss": 0.6236,
"step": 400
},
{
"epoch": 0.21739130434782608,
"grad_norm": 2.606115769256056,
"learning_rate": 9.58832634996429e-06,
"loss": 0.6288,
"step": 405
},
{
"epoch": 0.2200751476113795,
"grad_norm": 2.4723541437661414,
"learning_rate": 9.569504499432005e-06,
"loss": 0.608,
"step": 410
},
{
"epoch": 0.2227589908749329,
"grad_norm": 2.290568268708195,
"learning_rate": 9.550281267118659e-06,
"loss": 0.6087,
"step": 415
},
{
"epoch": 0.22544283413848631,
"grad_norm": 2.351420152069522,
"learning_rate": 9.530658341578276e-06,
"loss": 0.6138,
"step": 420
},
{
"epoch": 0.2281266774020397,
"grad_norm": 2.4088354796246016,
"learning_rate": 9.510637446473633e-06,
"loss": 0.6163,
"step": 425
},
{
"epoch": 0.23081052066559313,
"grad_norm": 2.439124497002319,
"learning_rate": 9.490220340424844e-06,
"loss": 0.6149,
"step": 430
},
{
"epoch": 0.23349436392914655,
"grad_norm": 2.3651788352560428,
"learning_rate": 9.469408816854898e-06,
"loss": 0.6185,
"step": 435
},
{
"epoch": 0.23617820719269994,
"grad_norm": 2.618918214991491,
"learning_rate": 9.448204703832102e-06,
"loss": 0.611,
"step": 440
},
{
"epoch": 0.23886205045625336,
"grad_norm": 2.48742969484966,
"learning_rate": 9.426609863909537e-06,
"loss": 0.6219,
"step": 445
},
{
"epoch": 0.24154589371980675,
"grad_norm": 2.5469891537442613,
"learning_rate": 9.404626193961427e-06,
"loss": 0.6179,
"step": 450
},
{
"epoch": 0.24422973698336017,
"grad_norm": 2.3741171814621853,
"learning_rate": 9.382255625016527e-06,
"loss": 0.6106,
"step": 455
},
{
"epoch": 0.24691358024691357,
"grad_norm": 2.3804430378530115,
"learning_rate": 9.359500122088511e-06,
"loss": 0.6153,
"step": 460
},
{
"epoch": 0.249597423510467,
"grad_norm": 2.3284131550985396,
"learning_rate": 9.336361684003353e-06,
"loss": 0.6093,
"step": 465
},
{
"epoch": 0.2522812667740204,
"grad_norm": 2.456024811325016,
"learning_rate": 9.312842343223764e-06,
"loss": 0.6169,
"step": 470
},
{
"epoch": 0.2549651100375738,
"grad_norm": 2.4687514469686693,
"learning_rate": 9.288944165670651e-06,
"loss": 0.6143,
"step": 475
},
{
"epoch": 0.2576489533011272,
"grad_norm": 2.390708189479994,
"learning_rate": 9.264669250541658e-06,
"loss": 0.5868,
"step": 480
},
{
"epoch": 0.2603327965646806,
"grad_norm": 2.3542679707474217,
"learning_rate": 9.240019730126764e-06,
"loss": 0.6135,
"step": 485
},
{
"epoch": 0.26301663982823403,
"grad_norm": 2.3093208133811634,
"learning_rate": 9.214997769620998e-06,
"loss": 0.5951,
"step": 490
},
{
"epoch": 0.26570048309178745,
"grad_norm": 2.3453177239592233,
"learning_rate": 9.189605566934235e-06,
"loss": 0.6055,
"step": 495
},
{
"epoch": 0.2683843263553409,
"grad_norm": 2.68049017575752,
"learning_rate": 9.163845352498141e-06,
"loss": 0.6012,
"step": 500
},
{
"epoch": 0.27106816961889424,
"grad_norm": 2.410046138698886,
"learning_rate": 9.137719389070259e-06,
"loss": 0.6054,
"step": 505
},
{
"epoch": 0.27375201288244766,
"grad_norm": 2.681286439839222,
"learning_rate": 9.111229971535231e-06,
"loss": 0.603,
"step": 510
},
{
"epoch": 0.2764358561460011,
"grad_norm": 2.558308980840885,
"learning_rate": 9.084379426703245e-06,
"loss": 0.602,
"step": 515
},
{
"epoch": 0.2791196994095545,
"grad_norm": 2.4105884527460573,
"learning_rate": 9.057170113105622e-06,
"loss": 0.5946,
"step": 520
},
{
"epoch": 0.28180354267310787,
"grad_norm": 2.2742333866866855,
"learning_rate": 9.029604420787666e-06,
"loss": 0.5811,
"step": 525
},
{
"epoch": 0.2844873859366613,
"grad_norm": 2.519471188975317,
"learning_rate": 9.001684771098709e-06,
"loss": 0.5868,
"step": 530
},
{
"epoch": 0.2871712292002147,
"grad_norm": 2.6490393180845015,
"learning_rate": 8.973413616479429e-06,
"loss": 0.5917,
"step": 535
},
{
"epoch": 0.2898550724637681,
"grad_norm": 2.383951019415346,
"learning_rate": 8.944793440246435e-06,
"loss": 0.5888,
"step": 540
},
{
"epoch": 0.29253891572732155,
"grad_norm": 2.4461042507556803,
"learning_rate": 8.915826756374118e-06,
"loss": 0.5782,
"step": 545
},
{
"epoch": 0.2952227589908749,
"grad_norm": 2.4291911892877622,
"learning_rate": 8.88651610927384e-06,
"loss": 0.5678,
"step": 550
},
{
"epoch": 0.29790660225442833,
"grad_norm": 2.4530217266247663,
"learning_rate": 8.856864073570429e-06,
"loss": 0.5659,
"step": 555
},
{
"epoch": 0.30059044551798175,
"grad_norm": 2.4328222140868827,
"learning_rate": 8.82687325387603e-06,
"loss": 0.578,
"step": 560
},
{
"epoch": 0.3032742887815352,
"grad_norm": 2.4319552814059437,
"learning_rate": 8.796546284561307e-06,
"loss": 0.5804,
"step": 565
},
{
"epoch": 0.3059581320450886,
"grad_norm": 2.657187133317878,
"learning_rate": 8.765885829524059e-06,
"loss": 0.5789,
"step": 570
},
{
"epoch": 0.30864197530864196,
"grad_norm": 2.2697836625371663,
"learning_rate": 8.734894581955208e-06,
"loss": 0.573,
"step": 575
},
{
"epoch": 0.3113258185721954,
"grad_norm": 2.401887770020238,
"learning_rate": 8.703575264102245e-06,
"loss": 0.5776,
"step": 580
},
{
"epoch": 0.3140096618357488,
"grad_norm": 2.2792894044568586,
"learning_rate": 8.6719306270301e-06,
"loss": 0.5589,
"step": 585
},
{
"epoch": 0.3166935050993022,
"grad_norm": 2.5255443105698134,
"learning_rate": 8.639963450379494e-06,
"loss": 0.566,
"step": 590
},
{
"epoch": 0.3193773483628556,
"grad_norm": 2.8143947788616295,
"learning_rate": 8.607676542122782e-06,
"loss": 0.5662,
"step": 595
},
{
"epoch": 0.322061191626409,
"grad_norm": 2.3227435317108434,
"learning_rate": 8.575072738317297e-06,
"loss": 0.5813,
"step": 600
},
{
"epoch": 0.3247450348899624,
"grad_norm": 2.5213044273313896,
"learning_rate": 8.542154902856232e-06,
"loss": 0.586,
"step": 605
},
{
"epoch": 0.32742887815351585,
"grad_norm": 2.3633935742818912,
"learning_rate": 8.508925927217083e-06,
"loss": 0.5557,
"step": 610
},
{
"epoch": 0.33011272141706927,
"grad_norm": 2.336769550705686,
"learning_rate": 8.475388730207662e-06,
"loss": 0.5596,
"step": 615
},
{
"epoch": 0.33279656468062263,
"grad_norm": 2.4227646867382235,
"learning_rate": 8.441546257709708e-06,
"loss": 0.5709,
"step": 620
},
{
"epoch": 0.33548040794417605,
"grad_norm": 2.53539797666282,
"learning_rate": 8.407401482420129e-06,
"loss": 0.5546,
"step": 625
},
{
"epoch": 0.33816425120772947,
"grad_norm": 2.6247283116786355,
"learning_rate": 8.372957403589873e-06,
"loss": 0.5689,
"step": 630
},
{
"epoch": 0.3408480944712829,
"grad_norm": 2.5918886646394323,
"learning_rate": 8.33821704676049e-06,
"loss": 0.555,
"step": 635
},
{
"epoch": 0.3435319377348363,
"grad_norm": 2.341174391808383,
"learning_rate": 8.303183463498357e-06,
"loss": 0.5622,
"step": 640
},
{
"epoch": 0.3462157809983897,
"grad_norm": 2.3492859021408936,
"learning_rate": 8.26785973112664e-06,
"loss": 0.5422,
"step": 645
},
{
"epoch": 0.3488996242619431,
"grad_norm": 2.4364746430045767,
"learning_rate": 8.232248952454978e-06,
"loss": 0.5444,
"step": 650
},
{
"epoch": 0.3515834675254965,
"grad_norm": 2.3799694997859584,
"learning_rate": 8.196354255506937e-06,
"loss": 0.559,
"step": 655
},
{
"epoch": 0.35426731078904994,
"grad_norm": 2.3548609807079317,
"learning_rate": 8.160178793245254e-06,
"loss": 0.5636,
"step": 660
},
{
"epoch": 0.3569511540526033,
"grad_norm": 2.351750584868109,
"learning_rate": 8.12372574329487e-06,
"loss": 0.5429,
"step": 665
},
{
"epoch": 0.3596349973161567,
"grad_norm": 2.3597264710105854,
"learning_rate": 8.086998307663815e-06,
"loss": 0.5379,
"step": 670
},
{
"epoch": 0.36231884057971014,
"grad_norm": 2.3278172683561005,
"learning_rate": 8.049999712461956e-06,
"loss": 0.5458,
"step": 675
},
{
"epoch": 0.36500268384326356,
"grad_norm": 2.4331488317138863,
"learning_rate": 8.012733207617602e-06,
"loss": 0.5513,
"step": 680
},
{
"epoch": 0.367686527106817,
"grad_norm": 2.399924321390654,
"learning_rate": 7.975202066592038e-06,
"loss": 0.5236,
"step": 685
},
{
"epoch": 0.37037037037037035,
"grad_norm": 2.492472394720929,
"learning_rate": 7.937409586091996e-06,
"loss": 0.5315,
"step": 690
},
{
"epoch": 0.37305421363392377,
"grad_norm": 2.335660439190083,
"learning_rate": 7.899359085780062e-06,
"loss": 0.5419,
"step": 695
},
{
"epoch": 0.3757380568974772,
"grad_norm": 2.365824065630226,
"learning_rate": 7.86105390798309e-06,
"loss": 0.5326,
"step": 700
},
{
"epoch": 0.3784219001610306,
"grad_norm": 2.5349179902891463,
"learning_rate": 7.822497417398607e-06,
"loss": 0.5299,
"step": 705
},
{
"epoch": 0.38110574342458403,
"grad_norm": 2.2732071597123866,
"learning_rate": 7.783693000799263e-06,
"loss": 0.5395,
"step": 710
},
{
"epoch": 0.3837895866881374,
"grad_norm": 2.5477511751272677,
"learning_rate": 7.744644066735335e-06,
"loss": 0.5264,
"step": 715
},
{
"epoch": 0.3864734299516908,
"grad_norm": 2.3110188045053803,
"learning_rate": 7.705354045235335e-06,
"loss": 0.515,
"step": 720
},
{
"epoch": 0.38915727321524424,
"grad_norm": 2.357694411169259,
"learning_rate": 7.665826387504708e-06,
"loss": 0.5228,
"step": 725
},
{
"epoch": 0.39184111647879766,
"grad_norm": 2.333837584901147,
"learning_rate": 7.626064565622684e-06,
"loss": 0.5354,
"step": 730
},
{
"epoch": 0.394524959742351,
"grad_norm": 2.3812550691442205,
"learning_rate": 7.586072072237291e-06,
"loss": 0.5262,
"step": 735
},
{
"epoch": 0.39720880300590444,
"grad_norm": 2.414868601462948,
"learning_rate": 7.545852420258566e-06,
"loss": 0.5267,
"step": 740
},
{
"epoch": 0.39989264626945786,
"grad_norm": 2.9293269013478493,
"learning_rate": 7.505409142549987e-06,
"loss": 0.5141,
"step": 745
},
{
"epoch": 0.4025764895330113,
"grad_norm": 2.330251706558549,
"learning_rate": 7.464745791618138e-06,
"loss": 0.5071,
"step": 750
},
{
"epoch": 0.4052603327965647,
"grad_norm": 2.3362656238807937,
"learning_rate": 7.423865939300674e-06,
"loss": 0.5017,
"step": 755
},
{
"epoch": 0.40794417606011807,
"grad_norm": 2.4001763619738523,
"learning_rate": 7.382773176452561e-06,
"loss": 0.5349,
"step": 760
},
{
"epoch": 0.4106280193236715,
"grad_norm": 2.3709879728169185,
"learning_rate": 7.341471112630667e-06,
"loss": 0.5326,
"step": 765
},
{
"epoch": 0.4133118625872249,
"grad_norm": 5.503655512197041,
"learning_rate": 7.2999633757766956e-06,
"loss": 0.5163,
"step": 770
},
{
"epoch": 0.41599570585077833,
"grad_norm": 2.3922360788223846,
"learning_rate": 7.258253611898509e-06,
"loss": 0.5186,
"step": 775
},
{
"epoch": 0.41867954911433175,
"grad_norm": 2.3251447839049275,
"learning_rate": 7.216345484749876e-06,
"loss": 0.5079,
"step": 780
},
{
"epoch": 0.4213633923778851,
"grad_norm": 2.2951407025338013,
"learning_rate": 7.174242675508636e-06,
"loss": 0.5068,
"step": 785
},
{
"epoch": 0.42404723564143854,
"grad_norm": 2.6480277827202694,
"learning_rate": 7.131948882453361e-06,
"loss": 0.4885,
"step": 790
},
{
"epoch": 0.42673107890499196,
"grad_norm": 2.2951285614754737,
"learning_rate": 7.089467820638491e-06,
"loss": 0.4987,
"step": 795
},
{
"epoch": 0.4294149221685454,
"grad_norm": 2.3181424069661545,
"learning_rate": 7.0468032215680116e-06,
"loss": 0.5221,
"step": 800
},
{
"epoch": 0.43209876543209874,
"grad_norm": 2.2684038771454045,
"learning_rate": 7.003958832867681e-06,
"loss": 0.5242,
"step": 805
},
{
"epoch": 0.43478260869565216,
"grad_norm": 2.676404966090793,
"learning_rate": 6.960938417955841e-06,
"loss": 0.5069,
"step": 810
},
{
"epoch": 0.4374664519592056,
"grad_norm": 2.349894917490143,
"learning_rate": 6.917745755712839e-06,
"loss": 0.5004,
"step": 815
},
{
"epoch": 0.440150295222759,
"grad_norm": 2.3871699426635598,
"learning_rate": 6.874384640149101e-06,
"loss": 0.5077,
"step": 820
},
{
"epoch": 0.4428341384863124,
"grad_norm": 2.3369644314777593,
"learning_rate": 6.830858880071859e-06,
"loss": 0.4891,
"step": 825
},
{
"epoch": 0.4455179817498658,
"grad_norm": 2.336086582871217,
"learning_rate": 6.7871722987505975e-06,
"loss": 0.5015,
"step": 830
},
{
"epoch": 0.4482018250134192,
"grad_norm": 2.4367965667465836,
"learning_rate": 6.743328733581211e-06,
"loss": 0.4997,
"step": 835
},
{
"epoch": 0.45088566827697263,
"grad_norm": 2.531976248724946,
"learning_rate": 6.6993320357489396e-06,
"loss": 0.4955,
"step": 840
},
{
"epoch": 0.45356951154052605,
"grad_norm": 2.2364342225876688,
"learning_rate": 6.6551860698900804e-06,
"loss": 0.487,
"step": 845
},
{
"epoch": 0.4562533548040794,
"grad_norm": 2.3568280656289313,
"learning_rate": 6.610894713752513e-06,
"loss": 0.4979,
"step": 850
},
{
"epoch": 0.45893719806763283,
"grad_norm": 2.3652469723056293,
"learning_rate": 6.566461857855096e-06,
"loss": 0.4814,
"step": 855
},
{
"epoch": 0.46162104133118625,
"grad_norm": 2.472649298194179,
"learning_rate": 6.52189140514591e-06,
"loss": 0.4911,
"step": 860
},
{
"epoch": 0.4643048845947397,
"grad_norm": 2.29208612124955,
"learning_rate": 6.477187270659444e-06,
"loss": 0.4857,
"step": 865
},
{
"epoch": 0.4669887278582931,
"grad_norm": 2.3253472470844354,
"learning_rate": 6.432353381172686e-06,
"loss": 0.4846,
"step": 870
},
{
"epoch": 0.46967257112184646,
"grad_norm": 2.5172836620382135,
"learning_rate": 6.387393674860205e-06,
"loss": 0.4818,
"step": 875
},
{
"epoch": 0.4723564143853999,
"grad_norm": 2.351389915294756,
"learning_rate": 6.3423121009482226e-06,
"loss": 0.5004,
"step": 880
},
{
"epoch": 0.4750402576489533,
"grad_norm": 2.563901057893881,
"learning_rate": 6.297112619367721e-06,
"loss": 0.4893,
"step": 885
},
{
"epoch": 0.4777241009125067,
"grad_norm": 2.1864865097415604,
"learning_rate": 6.2517992004066e-06,
"loss": 0.4927,
"step": 890
},
{
"epoch": 0.48040794417606014,
"grad_norm": 2.280701532767888,
"learning_rate": 6.2063758243609275e-06,
"loss": 0.4662,
"step": 895
},
{
"epoch": 0.4830917874396135,
"grad_norm": 2.921678160976539,
"learning_rate": 6.160846481185326e-06,
"loss": 0.4706,
"step": 900
},
{
"epoch": 0.4857756307031669,
"grad_norm": 2.283768315182298,
"learning_rate": 6.115215170142481e-06,
"loss": 0.4788,
"step": 905
},
{
"epoch": 0.48845947396672035,
"grad_norm": 2.333889889432955,
"learning_rate": 6.069485899451863e-06,
"loss": 0.4664,
"step": 910
},
{
"epoch": 0.49114331723027377,
"grad_norm": 2.599686462975885,
"learning_rate": 6.023662685937643e-06,
"loss": 0.4497,
"step": 915
},
{
"epoch": 0.49382716049382713,
"grad_norm": 2.5492827283831216,
"learning_rate": 5.9777495546758556e-06,
"loss": 0.4857,
"step": 920
},
{
"epoch": 0.49651100375738055,
"grad_norm": 2.4175643213741553,
"learning_rate": 5.9317505386408436e-06,
"loss": 0.4608,
"step": 925
},
{
"epoch": 0.499194847020934,
"grad_norm": 2.377055030538647,
"learning_rate": 5.885669678350997e-06,
"loss": 0.4803,
"step": 930
},
{
"epoch": 0.5018786902844874,
"grad_norm": 2.2334506971052965,
"learning_rate": 5.839511021513853e-06,
"loss": 0.4493,
"step": 935
},
{
"epoch": 0.5045625335480408,
"grad_norm": 2.32425118765916,
"learning_rate": 5.793278622670527e-06,
"loss": 0.4589,
"step": 940
},
{
"epoch": 0.5072463768115942,
"grad_norm": 2.410888326463012,
"learning_rate": 5.746976542839583e-06,
"loss": 0.4831,
"step": 945
},
{
"epoch": 0.5099302200751477,
"grad_norm": 2.2260467185492057,
"learning_rate": 5.700608849160307e-06,
"loss": 0.4613,
"step": 950
},
{
"epoch": 0.512614063338701,
"grad_norm": 2.345626470642079,
"learning_rate": 5.654179614535457e-06,
"loss": 0.4611,
"step": 955
},
{
"epoch": 0.5152979066022544,
"grad_norm": 2.4115998693660496,
"learning_rate": 5.607692917273499e-06,
"loss": 0.4816,
"step": 960
},
{
"epoch": 0.5179817498658078,
"grad_norm": 2.2111047514137927,
"learning_rate": 5.561152840730371e-06,
"loss": 0.465,
"step": 965
},
{
"epoch": 0.5206655931293612,
"grad_norm": 2.5262140714719212,
"learning_rate": 5.514563472950812e-06,
"loss": 0.4622,
"step": 970
},
{
"epoch": 0.5233494363929146,
"grad_norm": 2.2195436050046817,
"learning_rate": 5.46792890630926e-06,
"loss": 0.4558,
"step": 975
},
{
"epoch": 0.5260332796564681,
"grad_norm": 2.2799485984178944,
"learning_rate": 5.421253237150389e-06,
"loss": 0.4648,
"step": 980
},
{
"epoch": 0.5287171229200215,
"grad_norm": 2.6301434385590885,
"learning_rate": 5.374540565429288e-06,
"loss": 0.4631,
"step": 985
},
{
"epoch": 0.5314009661835749,
"grad_norm": 2.471540341708861,
"learning_rate": 5.327794994351321e-06,
"loss": 0.4524,
"step": 990
},
{
"epoch": 0.5340848094471283,
"grad_norm": 2.337507326917371,
"learning_rate": 5.281020630011703e-06,
"loss": 0.4684,
"step": 995
},
{
"epoch": 0.5367686527106817,
"grad_norm": 2.3216726905360288,
"learning_rate": 5.234221581034834e-06,
"loss": 0.445,
"step": 1000
},
{
"epoch": 0.5394524959742351,
"grad_norm": 2.644572388685312,
"learning_rate": 5.187401958213391e-06,
"loss": 0.4493,
"step": 1005
},
{
"epoch": 0.5421363392377885,
"grad_norm": 2.560926397352056,
"learning_rate": 5.140565874147236e-06,
"loss": 0.4279,
"step": 1010
},
{
"epoch": 0.5448201825013419,
"grad_norm": 2.2873708099653247,
"learning_rate": 5.093717442882185e-06,
"loss": 0.4512,
"step": 1015
},
{
"epoch": 0.5475040257648953,
"grad_norm": 2.260442565307831,
"learning_rate": 5.046860779548613e-06,
"loss": 0.4401,
"step": 1020
},
{
"epoch": 0.5501878690284487,
"grad_norm": 2.3869038782477543,
"learning_rate": 5e-06,
"loss": 0.4382,
"step": 1025
},
{
"epoch": 0.5528717122920022,
"grad_norm": 2.468747863225457,
"learning_rate": 4.953139220451386e-06,
"loss": 0.4722,
"step": 1030
},
{
"epoch": 0.5555555555555556,
"grad_norm": 2.2473611442378507,
"learning_rate": 4.906282557117817e-06,
"loss": 0.4495,
"step": 1035
},
{
"epoch": 0.558239398819109,
"grad_norm": 2.3833544443902532,
"learning_rate": 4.859434125852764e-06,
"loss": 0.4525,
"step": 1040
},
{
"epoch": 0.5609232420826624,
"grad_norm": 2.2632676724347367,
"learning_rate": 4.812598041786611e-06,
"loss": 0.4425,
"step": 1045
},
{
"epoch": 0.5636070853462157,
"grad_norm": 2.3341675236603447,
"learning_rate": 4.765778418965168e-06,
"loss": 0.4496,
"step": 1050
},
{
"epoch": 0.5662909286097692,
"grad_norm": 2.3837166818982816,
"learning_rate": 4.718979369988299e-06,
"loss": 0.4421,
"step": 1055
},
{
"epoch": 0.5689747718733226,
"grad_norm": 2.2164362902062744,
"learning_rate": 4.672205005648681e-06,
"loss": 0.4311,
"step": 1060
},
{
"epoch": 0.571658615136876,
"grad_norm": 2.1717995325593806,
"learning_rate": 4.625459434570712e-06,
"loss": 0.4231,
"step": 1065
},
{
"epoch": 0.5743424584004294,
"grad_norm": 2.365900130956694,
"learning_rate": 4.578746762849612e-06,
"loss": 0.4188,
"step": 1070
},
{
"epoch": 0.5770263016639828,
"grad_norm": 2.270809807847061,
"learning_rate": 4.532071093690741e-06,
"loss": 0.432,
"step": 1075
},
{
"epoch": 0.5797101449275363,
"grad_norm": 2.3336831813622014,
"learning_rate": 4.485436527049189e-06,
"loss": 0.4364,
"step": 1080
},
{
"epoch": 0.5823939881910897,
"grad_norm": 2.2310929205351657,
"learning_rate": 4.438847159269631e-06,
"loss": 0.4237,
"step": 1085
},
{
"epoch": 0.5850778314546431,
"grad_norm": 2.2709185614877057,
"learning_rate": 4.392307082726503e-06,
"loss": 0.4117,
"step": 1090
},
{
"epoch": 0.5877616747181964,
"grad_norm": 2.376948990363339,
"learning_rate": 4.345820385464543e-06,
"loss": 0.4184,
"step": 1095
},
{
"epoch": 0.5904455179817498,
"grad_norm": 2.4527120854156954,
"learning_rate": 4.299391150839694e-06,
"loss": 0.4124,
"step": 1100
},
{
"epoch": 0.5931293612453032,
"grad_norm": 2.405380755864835,
"learning_rate": 4.253023457160418e-06,
"loss": 0.4235,
"step": 1105
},
{
"epoch": 0.5958132045088567,
"grad_norm": 2.2780181294314965,
"learning_rate": 4.2067213773294745e-06,
"loss": 0.4311,
"step": 1110
},
{
"epoch": 0.5984970477724101,
"grad_norm": 2.352910332550843,
"learning_rate": 4.16048897848615e-06,
"loss": 0.4258,
"step": 1115
},
{
"epoch": 0.6011808910359635,
"grad_norm": 2.305493324748258,
"learning_rate": 4.114330321649004e-06,
"loss": 0.4293,
"step": 1120
},
{
"epoch": 0.6038647342995169,
"grad_norm": 2.426031927463211,
"learning_rate": 4.068249461359158e-06,
"loss": 0.4164,
"step": 1125
},
{
"epoch": 0.6065485775630703,
"grad_norm": 2.1758999179831053,
"learning_rate": 4.022250445324145e-06,
"loss": 0.4275,
"step": 1130
},
{
"epoch": 0.6092324208266238,
"grad_norm": 2.2904273454936783,
"learning_rate": 3.976337314062358e-06,
"loss": 0.4086,
"step": 1135
},
{
"epoch": 0.6119162640901772,
"grad_norm": 2.201522523908664,
"learning_rate": 3.9305141005481385e-06,
"loss": 0.4138,
"step": 1140
},
{
"epoch": 0.6146001073537305,
"grad_norm": 2.218773679624799,
"learning_rate": 3.8847848298575205e-06,
"loss": 0.4208,
"step": 1145
},
{
"epoch": 0.6172839506172839,
"grad_norm": 2.338212794329488,
"learning_rate": 3.839153518814677e-06,
"loss": 0.4072,
"step": 1150
},
{
"epoch": 0.6199677938808373,
"grad_norm": 2.3310971417294275,
"learning_rate": 3.7936241756390746e-06,
"loss": 0.4214,
"step": 1155
},
{
"epoch": 0.6226516371443908,
"grad_norm": 2.268125759049343,
"learning_rate": 3.748200799593402e-06,
"loss": 0.4037,
"step": 1160
},
{
"epoch": 0.6253354804079442,
"grad_norm": 2.3815930670980903,
"learning_rate": 3.7028873806322797e-06,
"loss": 0.4053,
"step": 1165
},
{
"epoch": 0.6280193236714976,
"grad_norm": 2.4002503785531535,
"learning_rate": 3.6576878990517783e-06,
"loss": 0.427,
"step": 1170
},
{
"epoch": 0.630703166935051,
"grad_norm": 2.2287683393400157,
"learning_rate": 3.6126063251397968e-06,
"loss": 0.4047,
"step": 1175
},
{
"epoch": 0.6333870101986044,
"grad_norm": 2.24030612251451,
"learning_rate": 3.567646618827315e-06,
"loss": 0.4072,
"step": 1180
},
{
"epoch": 0.6360708534621579,
"grad_norm": 2.2476861153746173,
"learning_rate": 3.522812729340557e-06,
"loss": 0.4057,
"step": 1185
},
{
"epoch": 0.6387546967257112,
"grad_norm": 2.250620066869653,
"learning_rate": 3.4781085948540907e-06,
"loss": 0.4135,
"step": 1190
},
{
"epoch": 0.6414385399892646,
"grad_norm": 2.426377994243079,
"learning_rate": 3.4335381421449056e-06,
"loss": 0.3927,
"step": 1195
},
{
"epoch": 0.644122383252818,
"grad_norm": 2.232109850238908,
"learning_rate": 3.3891052862474884e-06,
"loss": 0.399,
"step": 1200
},
{
"epoch": 0.6468062265163714,
"grad_norm": 2.241392662695428,
"learning_rate": 3.3448139301099212e-06,
"loss": 0.3984,
"step": 1205
},
{
"epoch": 0.6494900697799249,
"grad_norm": 2.1992057878349844,
"learning_rate": 3.3006679642510596e-06,
"loss": 0.399,
"step": 1210
},
{
"epoch": 0.6521739130434783,
"grad_norm": 2.3288135117678,
"learning_rate": 3.2566712664187907e-06,
"loss": 0.4058,
"step": 1215
},
{
"epoch": 0.6548577563070317,
"grad_norm": 2.1656603730720914,
"learning_rate": 3.2128277012494046e-06,
"loss": 0.4043,
"step": 1220
},
{
"epoch": 0.6575415995705851,
"grad_norm": 2.2233875096004385,
"learning_rate": 3.169141119928142e-06,
"loss": 0.3953,
"step": 1225
},
{
"epoch": 0.6602254428341385,
"grad_norm": 2.1164011887056136,
"learning_rate": 3.125615359850902e-06,
"loss": 0.3927,
"step": 1230
},
{
"epoch": 0.6629092860976918,
"grad_norm": 2.40060936517856,
"learning_rate": 3.082254244287163e-06,
"loss": 0.3999,
"step": 1235
},
{
"epoch": 0.6655931293612453,
"grad_norm": 2.1792932052704166,
"learning_rate": 3.0390615820441605e-06,
"loss": 0.3869,
"step": 1240
},
{
"epoch": 0.6682769726247987,
"grad_norm": 2.282109833051735,
"learning_rate": 2.9960411671323215e-06,
"loss": 0.3901,
"step": 1245
},
{
"epoch": 0.6709608158883521,
"grad_norm": 2.2959829437776276,
"learning_rate": 2.9531967784319897e-06,
"loss": 0.3847,
"step": 1250
},
{
"epoch": 0.6736446591519055,
"grad_norm": 2.1816584624767494,
"learning_rate": 2.9105321793615106e-06,
"loss": 0.3889,
"step": 1255
},
{
"epoch": 0.6763285024154589,
"grad_norm": 2.1709836152453676,
"learning_rate": 2.8680511175466384e-06,
"loss": 0.3921,
"step": 1260
},
{
"epoch": 0.6790123456790124,
"grad_norm": 2.0728452674033644,
"learning_rate": 2.8257573244913637e-06,
"loss": 0.393,
"step": 1265
},
{
"epoch": 0.6816961889425658,
"grad_norm": 2.292875337921466,
"learning_rate": 2.783654515250126e-06,
"loss": 0.3903,
"step": 1270
},
{
"epoch": 0.6843800322061192,
"grad_norm": 2.2405815280316843,
"learning_rate": 2.741746388101493e-06,
"loss": 0.3837,
"step": 1275
},
{
"epoch": 0.6870638754696726,
"grad_norm": 2.084014176066845,
"learning_rate": 2.700036624223308e-06,
"loss": 0.383,
"step": 1280
},
{
"epoch": 0.6897477187332259,
"grad_norm": 2.4092559373163254,
"learning_rate": 2.6585288873693355e-06,
"loss": 0.3798,
"step": 1285
},
{
"epoch": 0.6924315619967794,
"grad_norm": 2.0250661432577393,
"learning_rate": 2.6172268235474396e-06,
"loss": 0.3841,
"step": 1290
},
{
"epoch": 0.6951154052603328,
"grad_norm": 2.1763028564231295,
"learning_rate": 2.576134060699328e-06,
"loss": 0.3831,
"step": 1295
},
{
"epoch": 0.6977992485238862,
"grad_norm": 2.373398864029605,
"learning_rate": 2.5352542083818636e-06,
"loss": 0.3823,
"step": 1300
},
{
"epoch": 0.7004830917874396,
"grad_norm": 2.1727773171979643,
"learning_rate": 2.494590857450016e-06,
"loss": 0.3768,
"step": 1305
},
{
"epoch": 0.703166935050993,
"grad_norm": 2.149371676612498,
"learning_rate": 2.454147579741436e-06,
"loss": 0.3822,
"step": 1310
},
{
"epoch": 0.7058507783145465,
"grad_norm": 2.2872835046116777,
"learning_rate": 2.4139279277627113e-06,
"loss": 0.3871,
"step": 1315
},
{
"epoch": 0.7085346215780999,
"grad_norm": 2.153287257767556,
"learning_rate": 2.373935434377316e-06,
"loss": 0.3755,
"step": 1320
},
{
"epoch": 0.7112184648416533,
"grad_norm": 2.081735295703771,
"learning_rate": 2.3341736124952924e-06,
"loss": 0.3774,
"step": 1325
},
{
"epoch": 0.7139023081052066,
"grad_norm": 2.3934001061899544,
"learning_rate": 2.294645954764666e-06,
"loss": 0.3819,
"step": 1330
},
{
"epoch": 0.71658615136876,
"grad_norm": 2.189084634687172,
"learning_rate": 2.2553559332646675e-06,
"loss": 0.3833,
"step": 1335
},
{
"epoch": 0.7192699946323134,
"grad_norm": 2.2004454536339018,
"learning_rate": 2.216306999200739e-06,
"loss": 0.3662,
"step": 1340
},
{
"epoch": 0.7219538378958669,
"grad_norm": 2.164856903929889,
"learning_rate": 2.1775025826013953e-06,
"loss": 0.3717,
"step": 1345
},
{
"epoch": 0.7246376811594203,
"grad_norm": 2.2223965015758167,
"learning_rate": 2.1389460920169105e-06,
"loss": 0.3677,
"step": 1350
},
{
"epoch": 0.7273215244229737,
"grad_norm": 2.1657596827057977,
"learning_rate": 2.100640914219939e-06,
"loss": 0.3694,
"step": 1355
},
{
"epoch": 0.7300053676865271,
"grad_norm": 2.2173155958372806,
"learning_rate": 2.062590413908007e-06,
"loss": 0.37,
"step": 1360
},
{
"epoch": 0.7326892109500805,
"grad_norm": 2.0909707865425027,
"learning_rate": 2.0247979334079646e-06,
"loss": 0.3632,
"step": 1365
},
{
"epoch": 0.735373054213634,
"grad_norm": 2.2709941625135555,
"learning_rate": 1.9872667923823996e-06,
"loss": 0.3767,
"step": 1370
},
{
"epoch": 0.7380568974771873,
"grad_norm": 2.025865786970852,
"learning_rate": 1.9500002875380458e-06,
"loss": 0.3799,
"step": 1375
},
{
"epoch": 0.7407407407407407,
"grad_norm": 2.1733581353054454,
"learning_rate": 1.9130016923361843e-06,
"loss": 0.3774,
"step": 1380
},
{
"epoch": 0.7434245840042941,
"grad_norm": 2.25182494556845,
"learning_rate": 1.8762742567051318e-06,
"loss": 0.3733,
"step": 1385
},
{
"epoch": 0.7461084272678475,
"grad_norm": 2.124622472715877,
"learning_rate": 1.8398212067547455e-06,
"loss": 0.38,
"step": 1390
},
{
"epoch": 0.748792270531401,
"grad_norm": 2.1174183808257716,
"learning_rate": 1.8036457444930643e-06,
"loss": 0.364,
"step": 1395
},
{
"epoch": 0.7514761137949544,
"grad_norm": 2.095221806332882,
"learning_rate": 1.7677510475450244e-06,
"loss": 0.3644,
"step": 1400
},
{
"epoch": 0.7541599570585078,
"grad_norm": 2.191592696456213,
"learning_rate": 1.7321402688733618e-06,
"loss": 0.3655,
"step": 1405
},
{
"epoch": 0.7568438003220612,
"grad_norm": 2.1010897455276734,
"learning_rate": 1.6968165365016443e-06,
"loss": 0.356,
"step": 1410
},
{
"epoch": 0.7595276435856146,
"grad_norm": 2.2759244034217883,
"learning_rate": 1.661782953239512e-06,
"loss": 0.354,
"step": 1415
},
{
"epoch": 0.7622114868491681,
"grad_norm": 2.250779850948082,
"learning_rate": 1.6270425964101272e-06,
"loss": 0.3723,
"step": 1420
},
{
"epoch": 0.7648953301127214,
"grad_norm": 2.205374517042519,
"learning_rate": 1.5925985175798741e-06,
"loss": 0.3603,
"step": 1425
},
{
"epoch": 0.7675791733762748,
"grad_norm": 2.3498037872131685,
"learning_rate": 1.5584537422902923e-06,
"loss": 0.3688,
"step": 1430
},
{
"epoch": 0.7702630166398282,
"grad_norm": 2.198726674592499,
"learning_rate": 1.5246112697923389e-06,
"loss": 0.3677,
"step": 1435
},
{
"epoch": 0.7729468599033816,
"grad_norm": 2.1347598985352705,
"learning_rate": 1.4910740727829176e-06,
"loss": 0.3577,
"step": 1440
},
{
"epoch": 0.775630703166935,
"grad_norm": 1.9265646159076812,
"learning_rate": 1.457845097143769e-06,
"loss": 0.3629,
"step": 1445
},
{
"epoch": 0.7783145464304885,
"grad_norm": 2.104097817328808,
"learning_rate": 1.424927261682703e-06,
"loss": 0.3742,
"step": 1450
},
{
"epoch": 0.7809983896940419,
"grad_norm": 2.2536366979029703,
"learning_rate": 1.3923234578772177e-06,
"loss": 0.356,
"step": 1455
},
{
"epoch": 0.7836822329575953,
"grad_norm": 2.028767198712377,
"learning_rate": 1.3600365496205059e-06,
"loss": 0.3656,
"step": 1460
},
{
"epoch": 0.7863660762211487,
"grad_norm": 2.1494026106033894,
"learning_rate": 1.3280693729699018e-06,
"loss": 0.3633,
"step": 1465
},
{
"epoch": 0.789049919484702,
"grad_norm": 2.144837474228769,
"learning_rate": 1.2964247358977567e-06,
"loss": 0.3687,
"step": 1470
},
{
"epoch": 0.7917337627482555,
"grad_norm": 1.9179097398769962,
"learning_rate": 1.265105418044793e-06,
"loss": 0.3604,
"step": 1475
},
{
"epoch": 0.7944176060118089,
"grad_norm": 2.205613654909181,
"learning_rate": 1.2341141704759418e-06,
"loss": 0.3618,
"step": 1480
},
{
"epoch": 0.7971014492753623,
"grad_norm": 2.1038507710445473,
"learning_rate": 1.2034537154386933e-06,
"loss": 0.3662,
"step": 1485
},
{
"epoch": 0.7997852925389157,
"grad_norm": 2.1118262886014256,
"learning_rate": 1.173126746123972e-06,
"loss": 0.3425,
"step": 1490
},
{
"epoch": 0.8024691358024691,
"grad_norm": 2.069286005090326,
"learning_rate": 1.1431359264295717e-06,
"loss": 0.3635,
"step": 1495
},
{
"epoch": 0.8051529790660226,
"grad_norm": 2.0457106069970177,
"learning_rate": 1.113483890726162e-06,
"loss": 0.3515,
"step": 1500
},
{
"epoch": 0.807836822329576,
"grad_norm": 2.2183430868311804,
"learning_rate": 1.084173243625884e-06,
"loss": 0.3569,
"step": 1505
},
{
"epoch": 0.8105206655931294,
"grad_norm": 2.0344709131176484,
"learning_rate": 1.0552065597535671e-06,
"loss": 0.3657,
"step": 1510
},
{
"epoch": 0.8132045088566827,
"grad_norm": 1.9907375662103048,
"learning_rate": 1.0265863835205709e-06,
"loss": 0.354,
"step": 1515
},
{
"epoch": 0.8158883521202361,
"grad_norm": 2.1485376873924507,
"learning_rate": 9.983152289012926e-07,
"loss": 0.349,
"step": 1520
},
{
"epoch": 0.8185721953837896,
"grad_norm": 2.237249281661755,
"learning_rate": 9.70395579212336e-07,
"loss": 0.3597,
"step": 1525
},
{
"epoch": 0.821256038647343,
"grad_norm": 2.147026323371532,
"learning_rate": 9.428298868943791e-07,
"loss": 0.3543,
"step": 1530
},
{
"epoch": 0.8239398819108964,
"grad_norm": 2.0799388572163533,
"learning_rate": 9.15620573296756e-07,
"loss": 0.3467,
"step": 1535
},
{
"epoch": 0.8266237251744498,
"grad_norm": 2.2341120733387494,
"learning_rate": 8.887700284647699e-07,
"loss": 0.3523,
"step": 1540
},
{
"epoch": 0.8293075684380032,
"grad_norm": 2.160195897291193,
"learning_rate": 8.622806109297432e-07,
"loss": 0.3521,
"step": 1545
},
{
"epoch": 0.8319914117015567,
"grad_norm": 2.1704772185740664,
"learning_rate": 8.361546475018589e-07,
"loss": 0.3478,
"step": 1550
},
{
"epoch": 0.8346752549651101,
"grad_norm": 2.1013253656723494,
"learning_rate": 8.103944330657665e-07,
"loss": 0.3484,
"step": 1555
},
{
"epoch": 0.8373590982286635,
"grad_norm": 1.9819529400537306,
"learning_rate": 7.850022303790033e-07,
"loss": 0.3487,
"step": 1560
},
{
"epoch": 0.8400429414922168,
"grad_norm": 2.13766447402272,
"learning_rate": 7.599802698732356e-07,
"loss": 0.3565,
"step": 1565
},
{
"epoch": 0.8427267847557702,
"grad_norm": 2.038419435075784,
"learning_rate": 7.353307494583445e-07,
"loss": 0.3423,
"step": 1570
},
{
"epoch": 0.8454106280193237,
"grad_norm": 2.1486967728137554,
"learning_rate": 7.1105583432935e-07,
"loss": 0.3459,
"step": 1575
},
{
"epoch": 0.8480944712828771,
"grad_norm": 2.009446726024661,
"learning_rate": 6.871576567762373e-07,
"loss": 0.3576,
"step": 1580
},
{
"epoch": 0.8507783145464305,
"grad_norm": 2.1352354185011286,
"learning_rate": 6.63638315996647e-07,
"loss": 0.3495,
"step": 1585
},
{
"epoch": 0.8534621578099839,
"grad_norm": 2.1148156049768305,
"learning_rate": 6.404998779114912e-07,
"loss": 0.3479,
"step": 1590
},
{
"epoch": 0.8561460010735373,
"grad_norm": 2.1166468876773794,
"learning_rate": 6.177443749834743e-07,
"loss": 0.3417,
"step": 1595
},
{
"epoch": 0.8588298443370908,
"grad_norm": 2.0787291132598122,
"learning_rate": 5.953738060385761e-07,
"loss": 0.346,
"step": 1600
},
{
"epoch": 0.8615136876006442,
"grad_norm": 2.217292596926989,
"learning_rate": 5.733901360904648e-07,
"loss": 0.3411,
"step": 1605
},
{
"epoch": 0.8641975308641975,
"grad_norm": 2.1642916240096355,
"learning_rate": 5.517952961678997e-07,
"loss": 0.3349,
"step": 1610
},
{
"epoch": 0.8668813741277509,
"grad_norm": 2.0909486003584887,
"learning_rate": 5.305911831451044e-07,
"loss": 0.3491,
"step": 1615
},
{
"epoch": 0.8695652173913043,
"grad_norm": 2.049728625753877,
"learning_rate": 5.097796595751564e-07,
"loss": 0.332,
"step": 1620
},
{
"epoch": 0.8722490606548577,
"grad_norm": 2.0464556041654443,
"learning_rate": 4.89362553526368e-07,
"loss": 0.3509,
"step": 1625
},
{
"epoch": 0.8749329039184112,
"grad_norm": 2.008080188893636,
"learning_rate": 4.6934165842172476e-07,
"loss": 0.3327,
"step": 1630
},
{
"epoch": 0.8776167471819646,
"grad_norm": 2.0461563237864206,
"learning_rate": 4.4971873288134237e-07,
"loss": 0.3477,
"step": 1635
},
{
"epoch": 0.880300590445518,
"grad_norm": 1.9259918611757012,
"learning_rate": 4.304955005679962e-07,
"loss": 0.3501,
"step": 1640
},
{
"epoch": 0.8829844337090714,
"grad_norm": 2.1512221676085135,
"learning_rate": 4.1167365003571047e-07,
"loss": 0.3474,
"step": 1645
},
{
"epoch": 0.8856682769726248,
"grad_norm": 2.068297381192029,
"learning_rate": 3.9325483458144684e-07,
"loss": 0.3416,
"step": 1650
},
{
"epoch": 0.8883521202361782,
"grad_norm": 2.0719476007696644,
"learning_rate": 3.752406720998691e-07,
"loss": 0.3494,
"step": 1655
},
{
"epoch": 0.8910359634997316,
"grad_norm": 2.187345102618568,
"learning_rate": 3.5763274494123424e-07,
"loss": 0.3435,
"step": 1660
},
{
"epoch": 0.893719806763285,
"grad_norm": 2.0083898672947695,
"learning_rate": 3.404325997723995e-07,
"loss": 0.3359,
"step": 1665
},
{
"epoch": 0.8964036500268384,
"grad_norm": 1.9668453339791825,
"learning_rate": 3.2364174744096587e-07,
"loss": 0.3433,
"step": 1670
},
{
"epoch": 0.8990874932903918,
"grad_norm": 1.958103712575425,
"learning_rate": 3.072616628425601e-07,
"loss": 0.3416,
"step": 1675
},
{
"epoch": 0.9017713365539453,
"grad_norm": 2.031949910949981,
"learning_rate": 2.9129378479129e-07,
"loss": 0.3565,
"step": 1680
},
{
"epoch": 0.9044551798174987,
"grad_norm": 1.9869345393432467,
"learning_rate": 2.7573951589335177e-07,
"loss": 0.3405,
"step": 1685
},
{
"epoch": 0.9071390230810521,
"grad_norm": 2.0792432646936994,
"learning_rate": 2.60600222423833e-07,
"loss": 0.3495,
"step": 1690
},
{
"epoch": 0.9098228663446055,
"grad_norm": 2.0883501214443916,
"learning_rate": 2.45877234206694e-07,
"loss": 0.3329,
"step": 1695
},
{
"epoch": 0.9125067096081588,
"grad_norm": 2.1613119200340742,
"learning_rate": 2.3157184449796365e-07,
"loss": 0.3395,
"step": 1700
},
{
"epoch": 0.9151905528717122,
"grad_norm": 1.9941904808234305,
"learning_rate": 2.1768530987213267e-07,
"loss": 0.3443,
"step": 1705
},
{
"epoch": 0.9178743961352657,
"grad_norm": 2.0396795637412417,
"learning_rate": 2.0421885011178532e-07,
"loss": 0.349,
"step": 1710
},
{
"epoch": 0.9205582393988191,
"grad_norm": 2.0580171530995743,
"learning_rate": 1.911736481004489e-07,
"loss": 0.3501,
"step": 1715
},
{
"epoch": 0.9232420826623725,
"grad_norm": 2.0365505244300177,
"learning_rate": 1.7855084971869385e-07,
"loss": 0.3389,
"step": 1720
},
{
"epoch": 0.9259259259259259,
"grad_norm": 1.9808336724602207,
"learning_rate": 1.663515637434765e-07,
"loss": 0.3273,
"step": 1725
},
{
"epoch": 0.9286097691894794,
"grad_norm": 2.071334998406864,
"learning_rate": 1.5457686175074816e-07,
"loss": 0.3378,
"step": 1730
},
{
"epoch": 0.9312936124530328,
"grad_norm": 2.032001004284079,
"learning_rate": 1.432277780213298e-07,
"loss": 0.3387,
"step": 1735
},
{
"epoch": 0.9339774557165862,
"grad_norm": 2.3423646041282193,
"learning_rate": 1.3230530945005704e-07,
"loss": 0.3493,
"step": 1740
},
{
"epoch": 0.9366612989801396,
"grad_norm": 2.237272627315429,
"learning_rate": 1.2181041545821727e-07,
"loss": 0.3399,
"step": 1745
},
{
"epoch": 0.9393451422436929,
"grad_norm": 1.910922922082721,
"learning_rate": 1.1174401790927325e-07,
"loss": 0.3324,
"step": 1750
},
{
"epoch": 0.9420289855072463,
"grad_norm": 2.0289396869646543,
"learning_rate": 1.0210700102788796e-07,
"loss": 0.3353,
"step": 1755
},
{
"epoch": 0.9447128287707998,
"grad_norm": 1.9930688135886,
"learning_rate": 9.290021132225546e-08,
"loss": 0.343,
"step": 1760
},
{
"epoch": 0.9473966720343532,
"grad_norm": 1.9869439455930584,
"learning_rate": 8.412445750974385e-08,
"loss": 0.3433,
"step": 1765
},
{
"epoch": 0.9500805152979066,
"grad_norm": 1.9706742656413212,
"learning_rate": 7.578051044585644e-08,
"loss": 0.3276,
"step": 1770
},
{
"epoch": 0.95276435856146,
"grad_norm": 2.0487015305286196,
"learning_rate": 6.786910305652373e-08,
"loss": 0.3424,
"step": 1775
},
{
"epoch": 0.9554482018250134,
"grad_norm": 1.8807707801511768,
"learning_rate": 6.0390930273721e-08,
"loss": 0.3253,
"step": 1780
},
{
"epoch": 0.9581320450885669,
"grad_norm": 2.1651075487867972,
"learning_rate": 5.334664897442721e-08,
"loss": 0.3427,
"step": 1785
},
{
"epoch": 0.9608158883521203,
"grad_norm": 1.9918327197264334,
"learning_rate": 4.673687792292436e-08,
"loss": 0.3468,
"step": 1790
},
{
"epoch": 0.9634997316156736,
"grad_norm": 2.0832421947647908,
"learning_rate": 4.0562197716448316e-08,
"loss": 0.3413,
"step": 1795
},
{
"epoch": 0.966183574879227,
"grad_norm": 1.8518143782906564,
"learning_rate": 3.4823150734186184e-08,
"loss": 0.3314,
"step": 1800
},
{
"epoch": 0.9688674181427804,
"grad_norm": 1.8591662070449098,
"learning_rate": 2.9520241089636692e-08,
"loss": 0.3402,
"step": 1805
},
{
"epoch": 0.9715512614063339,
"grad_norm": 2.004188829558215,
"learning_rate": 2.4653934586328365e-08,
"loss": 0.3382,
"step": 1810
},
{
"epoch": 0.9742351046698873,
"grad_norm": 1.8626147867674074,
"learning_rate": 2.022465867690282e-08,
"loss": 0.3398,
"step": 1815
},
{
"epoch": 0.9769189479334407,
"grad_norm": 1.9428514502995295,
"learning_rate": 1.6232802425568683e-08,
"loss": 0.3438,
"step": 1820
},
{
"epoch": 0.9796027911969941,
"grad_norm": 2.023262028137228,
"learning_rate": 1.2678716473927821e-08,
"loss": 0.3261,
"step": 1825
},
{
"epoch": 0.9822866344605475,
"grad_norm": 1.9375157251991955,
"learning_rate": 9.562713010171088e-09,
"loss": 0.3411,
"step": 1830
},
{
"epoch": 0.984970477724101,
"grad_norm": 1.9840670565628429,
"learning_rate": 6.885065741661367e-09,
"loss": 0.3448,
"step": 1835
},
{
"epoch": 0.9876543209876543,
"grad_norm": 2.1326177570275067,
"learning_rate": 4.646009870885593e-09,
"loss": 0.3509,
"step": 1840
},
{
"epoch": 0.9903381642512077,
"grad_norm": 2.2161553703672867,
"learning_rate": 2.845742074801261e-09,
"loss": 0.336,
"step": 1845
},
{
"epoch": 0.9930220075147611,
"grad_norm": 1.962610075480555,
"learning_rate": 1.484420487553595e-09,
"loss": 0.348,
"step": 1850
},
{
"epoch": 0.9957058507783145,
"grad_norm": 1.9169206999486972,
"learning_rate": 5.621646865899832e-10,
"loss": 0.3394,
"step": 1855
},
{
"epoch": 0.998389694041868,
"grad_norm": 1.9220724874106698,
"learning_rate": 7.905568215504921e-11,
"loss": 0.347,
"step": 1860
},
{
"epoch": 1.0,
"eval_runtime": 3.3936,
"eval_samples_per_second": 2.947,
"eval_steps_per_second": 0.884,
"step": 1863
},
{
"epoch": 1.0,
"step": 1863,
"total_flos": 195037149265920.0,
"train_loss": 0.5024847409063555,
"train_runtime": 16621.9401,
"train_samples_per_second": 1.793,
"train_steps_per_second": 0.112
}
],
"logging_steps": 5,
"max_steps": 1863,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 195037149265920.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}