smollm-135M-instruct-v2 / trainer_state.json
loubnabnl's picture
loubnabnl HF staff
Model save
d7feb6c verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 819,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001221001221001221,
"grad_norm": 1.0205980343161538,
"learning_rate": 1.2195121951219513e-05,
"loss": 1.6063,
"step": 1
},
{
"epoch": 0.006105006105006105,
"grad_norm": 0.89369227471272,
"learning_rate": 6.097560975609756e-05,
"loss": 1.6127,
"step": 5
},
{
"epoch": 0.01221001221001221,
"grad_norm": 0.773993509246519,
"learning_rate": 0.00012195121951219512,
"loss": 1.5596,
"step": 10
},
{
"epoch": 0.018315018315018316,
"grad_norm": 0.6209997076659476,
"learning_rate": 0.00018292682926829268,
"loss": 1.4619,
"step": 15
},
{
"epoch": 0.02442002442002442,
"grad_norm": 0.4770932033448127,
"learning_rate": 0.00024390243902439024,
"loss": 1.4028,
"step": 20
},
{
"epoch": 0.030525030525030524,
"grad_norm": 0.3320501554134054,
"learning_rate": 0.0003048780487804878,
"loss": 1.347,
"step": 25
},
{
"epoch": 0.03663003663003663,
"grad_norm": 0.2002596607926003,
"learning_rate": 0.00036585365853658537,
"loss": 1.3103,
"step": 30
},
{
"epoch": 0.042735042735042736,
"grad_norm": 0.20128176628182073,
"learning_rate": 0.0004268292682926829,
"loss": 1.3026,
"step": 35
},
{
"epoch": 0.04884004884004884,
"grad_norm": 0.17594648344906566,
"learning_rate": 0.0004878048780487805,
"loss": 1.2854,
"step": 40
},
{
"epoch": 0.054945054945054944,
"grad_norm": 0.17236683696702648,
"learning_rate": 0.0005487804878048781,
"loss": 1.271,
"step": 45
},
{
"epoch": 0.06105006105006105,
"grad_norm": 0.17916116023910555,
"learning_rate": 0.0006097560975609756,
"loss": 1.2661,
"step": 50
},
{
"epoch": 0.06715506715506715,
"grad_norm": 0.15617178601932155,
"learning_rate": 0.0006707317073170732,
"loss": 1.2528,
"step": 55
},
{
"epoch": 0.07326007326007326,
"grad_norm": 0.1927465066785224,
"learning_rate": 0.0007317073170731707,
"loss": 1.252,
"step": 60
},
{
"epoch": 0.07936507936507936,
"grad_norm": 0.20776151355108807,
"learning_rate": 0.0007926829268292683,
"loss": 1.2463,
"step": 65
},
{
"epoch": 0.08547008547008547,
"grad_norm": 0.1655472216601126,
"learning_rate": 0.0008536585365853659,
"loss": 1.239,
"step": 70
},
{
"epoch": 0.09157509157509157,
"grad_norm": 0.20874533177899088,
"learning_rate": 0.0009146341463414635,
"loss": 1.2417,
"step": 75
},
{
"epoch": 0.09768009768009768,
"grad_norm": 0.21100479425784993,
"learning_rate": 0.000975609756097561,
"loss": 1.2328,
"step": 80
},
{
"epoch": 0.10378510378510379,
"grad_norm": 0.20904541266897642,
"learning_rate": 0.000999959117130623,
"loss": 1.2336,
"step": 85
},
{
"epoch": 0.10989010989010989,
"grad_norm": 0.20019701905382167,
"learning_rate": 0.000999709301584265,
"loss": 1.2252,
"step": 90
},
{
"epoch": 0.115995115995116,
"grad_norm": 0.21413001652476213,
"learning_rate": 0.0009992324965361792,
"loss": 1.2243,
"step": 95
},
{
"epoch": 0.1221001221001221,
"grad_norm": 0.16522854367968515,
"learning_rate": 0.0009985289185717684,
"loss": 1.2121,
"step": 100
},
{
"epoch": 0.1282051282051282,
"grad_norm": 0.25042890936419604,
"learning_rate": 0.000997598887286467,
"loss": 1.2153,
"step": 105
},
{
"epoch": 0.1343101343101343,
"grad_norm": 0.2092348207313529,
"learning_rate": 0.000996442825140569,
"loss": 1.2067,
"step": 110
},
{
"epoch": 0.14041514041514042,
"grad_norm": 0.1987412303455424,
"learning_rate": 0.0009950612572673255,
"loss": 1.211,
"step": 115
},
{
"epoch": 0.14652014652014653,
"grad_norm": 0.19695075669196946,
"learning_rate": 0.0009934548112344088,
"loss": 1.2139,
"step": 120
},
{
"epoch": 0.15262515262515264,
"grad_norm": 0.1432709740921402,
"learning_rate": 0.0009916242167588433,
"loss": 1.2147,
"step": 125
},
{
"epoch": 0.15873015873015872,
"grad_norm": 0.16002380073043662,
"learning_rate": 0.0009895703053755364,
"loss": 1.2028,
"step": 130
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.15340967683760462,
"learning_rate": 0.0009872940100595598,
"loss": 1.1995,
"step": 135
},
{
"epoch": 0.17094017094017094,
"grad_norm": 0.18565794761972862,
"learning_rate": 0.0009847963648023522,
"loss": 1.1992,
"step": 140
},
{
"epoch": 0.17704517704517705,
"grad_norm": 0.20113198830929513,
"learning_rate": 0.000982078504142035,
"loss": 1.1846,
"step": 145
},
{
"epoch": 0.18315018315018314,
"grad_norm": 0.239052195300538,
"learning_rate": 0.000979141662648057,
"loss": 1.1917,
"step": 150
},
{
"epoch": 0.18925518925518925,
"grad_norm": 0.18541851296547388,
"learning_rate": 0.0009759871743604004,
"loss": 1.1883,
"step": 155
},
{
"epoch": 0.19536019536019536,
"grad_norm": 0.1976795721725536,
"learning_rate": 0.0009726164721835996,
"loss": 1.1844,
"step": 160
},
{
"epoch": 0.20146520146520147,
"grad_norm": 0.17463002143028833,
"learning_rate": 0.0009690310872358572,
"loss": 1.1969,
"step": 165
},
{
"epoch": 0.20757020757020758,
"grad_norm": 0.21323309987103073,
"learning_rate": 0.0009652326481535434,
"loss": 1.188,
"step": 170
},
{
"epoch": 0.21367521367521367,
"grad_norm": 0.23172909898163094,
"learning_rate": 0.0009612228803513976,
"loss": 1.186,
"step": 175
},
{
"epoch": 0.21978021978021978,
"grad_norm": 0.22579230538853118,
"learning_rate": 0.0009570036052387725,
"loss": 1.1798,
"step": 180
},
{
"epoch": 0.2258852258852259,
"grad_norm": 0.1619341093580773,
"learning_rate": 0.0009525767393922706,
"loss": 1.1662,
"step": 185
},
{
"epoch": 0.231990231990232,
"grad_norm": 0.183207674619275,
"learning_rate": 0.0009479442936851526,
"loss": 1.1723,
"step": 190
},
{
"epoch": 0.23809523809523808,
"grad_norm": 0.21188703922152927,
"learning_rate": 0.0009431083723739124,
"loss": 1.1576,
"step": 195
},
{
"epoch": 0.2442002442002442,
"grad_norm": 0.2089350434131967,
"learning_rate": 0.0009380711721424326,
"loss": 1.1619,
"step": 200
},
{
"epoch": 0.2503052503052503,
"grad_norm": 0.15157070914539794,
"learning_rate": 0.0009328349811041565,
"loss": 1.1631,
"step": 205
},
{
"epoch": 0.2564102564102564,
"grad_norm": 0.16351230424545868,
"learning_rate": 0.0009274021777627277,
"loss": 1.1709,
"step": 210
},
{
"epoch": 0.2625152625152625,
"grad_norm": 0.17564187179508275,
"learning_rate": 0.0009217752299315725,
"loss": 1.1462,
"step": 215
},
{
"epoch": 0.2686202686202686,
"grad_norm": 0.2131938226227643,
"learning_rate": 0.0009159566936129111,
"loss": 1.1723,
"step": 220
},
{
"epoch": 0.27472527472527475,
"grad_norm": 0.20887852013049316,
"learning_rate": 0.0009099492118367123,
"loss": 1.1689,
"step": 225
},
{
"epoch": 0.28083028083028083,
"grad_norm": 0.17857721915396702,
"learning_rate": 0.0009037555134601149,
"loss": 1.1466,
"step": 230
},
{
"epoch": 0.2869352869352869,
"grad_norm": 0.1620613655817899,
"learning_rate": 0.000897378411927864,
"loss": 1.1592,
"step": 235
},
{
"epoch": 0.29304029304029305,
"grad_norm": 0.2125809185558365,
"learning_rate": 0.0008908208039943213,
"loss": 1.1485,
"step": 240
},
{
"epoch": 0.29914529914529914,
"grad_norm": 0.1748347227235315,
"learning_rate": 0.0008840856684076366,
"loss": 1.1332,
"step": 245
},
{
"epoch": 0.3052503052503053,
"grad_norm": 0.22239189840818827,
"learning_rate": 0.0008771760645566706,
"loss": 1.141,
"step": 250
},
{
"epoch": 0.31135531135531136,
"grad_norm": 3.2813461087169853,
"learning_rate": 0.000870095131081289,
"loss": 1.1641,
"step": 255
},
{
"epoch": 0.31746031746031744,
"grad_norm": 0.2268012798675002,
"learning_rate": 0.0008628460844466573,
"loss": 1.1401,
"step": 260
},
{
"epoch": 0.3235653235653236,
"grad_norm": 0.19745728202118107,
"learning_rate": 0.0008554322174821833,
"loss": 1.1401,
"step": 265
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.1818589584492454,
"learning_rate": 0.0008478568978857722,
"loss": 1.1412,
"step": 270
},
{
"epoch": 0.33577533577533575,
"grad_norm": 0.17803807739093683,
"learning_rate": 0.0008401235666940728,
"loss": 1.1427,
"step": 275
},
{
"epoch": 0.3418803418803419,
"grad_norm": 0.1635966967881225,
"learning_rate": 0.0008322357367194109,
"loss": 1.1348,
"step": 280
},
{
"epoch": 0.34798534798534797,
"grad_norm": 0.16634307483679497,
"learning_rate": 0.0008241969909541184,
"loss": 1.1291,
"step": 285
},
{
"epoch": 0.3540903540903541,
"grad_norm": 0.22380463687576627,
"learning_rate": 0.0008160109809429835,
"loss": 1.1375,
"step": 290
},
{
"epoch": 0.3601953601953602,
"grad_norm": 0.17014516986944303,
"learning_rate": 0.0008076814251245613,
"loss": 1.1315,
"step": 295
},
{
"epoch": 0.3663003663003663,
"grad_norm": 0.19479534952981664,
"learning_rate": 0.0007992121071421001,
"loss": 1.1478,
"step": 300
},
{
"epoch": 0.3724053724053724,
"grad_norm": 0.1880458408856176,
"learning_rate": 0.0007906068741248461,
"loss": 1.1281,
"step": 305
},
{
"epoch": 0.3785103785103785,
"grad_norm": 0.15460815741303807,
"learning_rate": 0.0007818696349405123,
"loss": 1.1362,
"step": 310
},
{
"epoch": 0.38461538461538464,
"grad_norm": 0.15045386348296025,
"learning_rate": 0.0007730043584197021,
"loss": 1.1259,
"step": 315
},
{
"epoch": 0.3907203907203907,
"grad_norm": 0.20122942405887176,
"learning_rate": 0.0007640150715530953,
"loss": 1.1181,
"step": 320
},
{
"epoch": 0.3968253968253968,
"grad_norm": 0.20533248267550017,
"learning_rate": 0.0007549058576622157,
"loss": 1.1293,
"step": 325
},
{
"epoch": 0.40293040293040294,
"grad_norm": 0.13677076752035072,
"learning_rate": 0.0007456808545446102,
"loss": 1.1221,
"step": 330
},
{
"epoch": 0.409035409035409,
"grad_norm": 0.1734062852611153,
"learning_rate": 0.0007363442525942826,
"loss": 1.118,
"step": 335
},
{
"epoch": 0.41514041514041516,
"grad_norm": 0.16356872758418958,
"learning_rate": 0.0007269002928982366,
"loss": 1.1231,
"step": 340
},
{
"epoch": 0.42124542124542125,
"grad_norm": 0.17309361004903426,
"learning_rate": 0.0007173532653099911,
"loss": 1.1146,
"step": 345
},
{
"epoch": 0.42735042735042733,
"grad_norm": 0.1326003328898491,
"learning_rate": 0.0007077075065009433,
"loss": 1.136,
"step": 350
},
{
"epoch": 0.43345543345543347,
"grad_norm": 0.1811730240238145,
"learning_rate": 0.0006979673979904665,
"loss": 1.1276,
"step": 355
},
{
"epoch": 0.43956043956043955,
"grad_norm": 0.13629851189524775,
"learning_rate": 0.0006881373641556346,
"loss": 1.1113,
"step": 360
},
{
"epoch": 0.4456654456654457,
"grad_norm": 0.21374115697770382,
"learning_rate": 0.0006782218702214797,
"loss": 1.1078,
"step": 365
},
{
"epoch": 0.4517704517704518,
"grad_norm": 0.16886558971737456,
"learning_rate": 0.000668225420232694,
"loss": 1.1108,
"step": 370
},
{
"epoch": 0.45787545787545786,
"grad_norm": 0.16694922624121042,
"learning_rate": 0.0006581525550076989,
"loss": 1.1068,
"step": 375
},
{
"epoch": 0.463980463980464,
"grad_norm": 0.16014858561217288,
"learning_rate": 0.0006480078500760096,
"loss": 1.1185,
"step": 380
},
{
"epoch": 0.4700854700854701,
"grad_norm": 0.18799411654589882,
"learning_rate": 0.0006377959135998322,
"loss": 1.1143,
"step": 385
},
{
"epoch": 0.47619047619047616,
"grad_norm": 0.1270424719263773,
"learning_rate": 0.0006275213842808383,
"loss": 1.1055,
"step": 390
},
{
"epoch": 0.4822954822954823,
"grad_norm": 0.17394420991284418,
"learning_rate": 0.0006171889292530655,
"loss": 1.105,
"step": 395
},
{
"epoch": 0.4884004884004884,
"grad_norm": 0.15074553592858597,
"learning_rate": 0.0006068032419629059,
"loss": 1.1167,
"step": 400
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.1575327685510419,
"learning_rate": 0.0005963690400371386,
"loss": 1.105,
"step": 405
},
{
"epoch": 0.5006105006105006,
"grad_norm": 0.15495173159548875,
"learning_rate": 0.0005858910631399817,
"loss": 1.1079,
"step": 410
},
{
"epoch": 0.5067155067155067,
"grad_norm": 0.12495502826181124,
"learning_rate": 0.0005753740708201315,
"loss": 1.0961,
"step": 415
},
{
"epoch": 0.5128205128205128,
"grad_norm": 0.17798304801391704,
"learning_rate": 0.0005648228403487712,
"loss": 1.103,
"step": 420
},
{
"epoch": 0.518925518925519,
"grad_norm": 0.15145475180954737,
"learning_rate": 0.0005542421645495279,
"loss": 1.1082,
"step": 425
},
{
"epoch": 0.525030525030525,
"grad_norm": 0.1674135601603621,
"learning_rate": 0.0005436368496213656,
"loss": 1.0922,
"step": 430
},
{
"epoch": 0.5311355311355311,
"grad_norm": 0.1322258266693411,
"learning_rate": 0.0005330117129554028,
"loss": 1.0969,
"step": 435
},
{
"epoch": 0.5372405372405372,
"grad_norm": 0.16392404937146968,
"learning_rate": 0.0005223715809466454,
"loss": 1.1023,
"step": 440
},
{
"epoch": 0.5433455433455433,
"grad_norm": 0.15868256924573232,
"learning_rate": 0.0005117212868016303,
"loss": 1.0961,
"step": 445
},
{
"epoch": 0.5494505494505495,
"grad_norm": 0.1493324553731281,
"learning_rate": 0.0005010656683429746,
"loss": 1.0992,
"step": 450
},
{
"epoch": 0.5555555555555556,
"grad_norm": 0.13303968473914282,
"learning_rate": 0.0004904095658118283,
"loss": 1.0869,
"step": 455
},
{
"epoch": 0.5616605616605617,
"grad_norm": 0.13445179172013122,
"learning_rate": 0.0004797578196692281,
"loss": 1.0979,
"step": 460
},
{
"epoch": 0.5677655677655677,
"grad_norm": 0.1353400408710943,
"learning_rate": 0.00046911526839735093,
"loss": 1.1058,
"step": 465
},
{
"epoch": 0.5738705738705738,
"grad_norm": 0.15268434606287648,
"learning_rate": 0.0004584867463016671,
"loss": 1.0955,
"step": 470
},
{
"epoch": 0.57997557997558,
"grad_norm": 0.14945079736642003,
"learning_rate": 0.00044787708131499104,
"loss": 1.0829,
"step": 475
},
{
"epoch": 0.5860805860805861,
"grad_norm": 0.1308874678872484,
"learning_rate": 0.0004372910928044249,
"loss": 1.0899,
"step": 480
},
{
"epoch": 0.5921855921855922,
"grad_norm": 0.1315948608079688,
"learning_rate": 0.00042673358938219544,
"loss": 1.0864,
"step": 485
},
{
"epoch": 0.5982905982905983,
"grad_norm": 0.19438574034423878,
"learning_rate": 0.00041620936672137393,
"loss": 1.093,
"step": 490
},
{
"epoch": 0.6043956043956044,
"grad_norm": 0.12572375675032343,
"learning_rate": 0.00040572320537747656,
"loss": 1.0875,
"step": 495
},
{
"epoch": 0.6105006105006106,
"grad_norm": 0.12787583668085029,
"learning_rate": 0.0003952798686169279,
"loss": 1.1024,
"step": 500
},
{
"epoch": 0.6166056166056166,
"grad_norm": 0.14209081780825783,
"learning_rate": 0.00038488410025338133,
"loss": 1.0938,
"step": 505
},
{
"epoch": 0.6227106227106227,
"grad_norm": 0.13751458022764315,
"learning_rate": 0.00037454062249287477,
"loss": 1.0878,
"step": 510
},
{
"epoch": 0.6288156288156288,
"grad_norm": 0.13954841564889886,
"learning_rate": 0.0003642541337887999,
"loss": 1.0912,
"step": 515
},
{
"epoch": 0.6349206349206349,
"grad_norm": 0.14997321061776903,
"learning_rate": 0.00035402930670766296,
"loss": 1.0747,
"step": 520
},
{
"epoch": 0.6410256410256411,
"grad_norm": 0.1701293287916612,
"learning_rate": 0.00034387078580660346,
"loss": 1.0783,
"step": 525
},
{
"epoch": 0.6471306471306472,
"grad_norm": 0.12199767794093884,
"learning_rate": 0.00033378318552363664,
"loss": 1.0776,
"step": 530
},
{
"epoch": 0.6532356532356532,
"grad_norm": 0.16919824019980462,
"learning_rate": 0.0003237710880815756,
"loss": 1.0889,
"step": 535
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.13811611845852387,
"learning_rate": 0.00031383904140658986,
"loss": 1.0762,
"step": 540
},
{
"epoch": 0.6654456654456654,
"grad_norm": 0.15905169364412688,
"learning_rate": 0.0003039915570623396,
"loss": 1.082,
"step": 545
},
{
"epoch": 0.6715506715506715,
"grad_norm": 0.1296226609467321,
"learning_rate": 0.0002942331082006308,
"loss": 1.0724,
"step": 550
},
{
"epoch": 0.6776556776556777,
"grad_norm": 0.1330698219795046,
"learning_rate": 0.00028456812752951485,
"loss": 1.0723,
"step": 555
},
{
"epoch": 0.6837606837606838,
"grad_norm": 0.13173063625642664,
"learning_rate": 0.0002750010052997635,
"loss": 1.0783,
"step": 560
},
{
"epoch": 0.6898656898656899,
"grad_norm": 0.11827576804873147,
"learning_rate": 0.00026553608731062604,
"loss": 1.0734,
"step": 565
},
{
"epoch": 0.6959706959706959,
"grad_norm": 0.12044643950959122,
"learning_rate": 0.00025617767293578176,
"loss": 1.0695,
"step": 570
},
{
"epoch": 0.702075702075702,
"grad_norm": 0.12921730309691146,
"learning_rate": 0.0002469300131703773,
"loss": 1.0721,
"step": 575
},
{
"epoch": 0.7081807081807082,
"grad_norm": 0.12533218466426468,
"learning_rate": 0.00023779730870004235,
"loss": 1.0608,
"step": 580
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.12817655243582374,
"learning_rate": 0.00022878370799275777,
"loss": 1.0789,
"step": 585
},
{
"epoch": 0.7203907203907204,
"grad_norm": 0.1293778348063508,
"learning_rate": 0.0002198933054144414,
"loss": 1.0602,
"step": 590
},
{
"epoch": 0.7264957264957265,
"grad_norm": 0.1263148140338118,
"learning_rate": 0.00021113013936911113,
"loss": 1.0679,
"step": 595
},
{
"epoch": 0.7326007326007326,
"grad_norm": 0.13594429624621016,
"learning_rate": 0.00020249819046446837,
"loss": 1.0683,
"step": 600
},
{
"epoch": 0.7387057387057387,
"grad_norm": 0.11897323140031583,
"learning_rate": 0.00019400137970373356,
"loss": 1.0715,
"step": 605
},
{
"epoch": 0.7448107448107448,
"grad_norm": 0.12134111257996806,
"learning_rate": 0.00018564356670455767,
"loss": 1.0737,
"step": 610
},
{
"epoch": 0.7509157509157509,
"grad_norm": 0.12412837845655514,
"learning_rate": 0.00017742854794581785,
"loss": 1.077,
"step": 615
},
{
"epoch": 0.757020757020757,
"grad_norm": 0.10995117277188224,
"learning_rate": 0.00016936005504309342,
"loss": 1.0725,
"step": 620
},
{
"epoch": 0.7631257631257631,
"grad_norm": 0.12324463281674919,
"learning_rate": 0.0001614417530536042,
"loss": 1.0714,
"step": 625
},
{
"epoch": 0.7692307692307693,
"grad_norm": 0.12422719561341983,
"learning_rate": 0.00015367723881138434,
"loss": 1.0764,
"step": 630
},
{
"epoch": 0.7753357753357754,
"grad_norm": 0.15097612554081813,
"learning_rate": 0.00014607003929344492,
"loss": 1.0735,
"step": 635
},
{
"epoch": 0.7814407814407814,
"grad_norm": 0.10792336331652043,
"learning_rate": 0.00013862361001766972,
"loss": 1.0656,
"step": 640
},
{
"epoch": 0.7875457875457875,
"grad_norm": 0.10878726224284914,
"learning_rate": 0.00013134133347316885,
"loss": 1.054,
"step": 645
},
{
"epoch": 0.7936507936507936,
"grad_norm": 0.10538532292466002,
"learning_rate": 0.0001242265175838072,
"loss": 1.0565,
"step": 650
},
{
"epoch": 0.7997557997557998,
"grad_norm": 0.132655865253661,
"learning_rate": 0.00011728239420560316,
"loss": 1.0623,
"step": 655
},
{
"epoch": 0.8058608058608059,
"grad_norm": 0.13898152967373176,
"learning_rate": 0.0001105121176586793,
"loss": 1.062,
"step": 660
},
{
"epoch": 0.811965811965812,
"grad_norm": 0.1284900261818914,
"learning_rate": 0.00010391876329443534,
"loss": 1.0573,
"step": 665
},
{
"epoch": 0.818070818070818,
"grad_norm": 0.12601548049011016,
"learning_rate": 9.750532609858991e-05,
"loss": 1.0627,
"step": 670
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.10148390380785619,
"learning_rate": 9.127471933073007e-05,
"loss": 1.0689,
"step": 675
},
{
"epoch": 0.8302808302808303,
"grad_norm": 0.11101937832472626,
"learning_rate": 8.522977320098224e-05,
"loss": 1.0592,
"step": 680
},
{
"epoch": 0.8363858363858364,
"grad_norm": 0.11000851597542352,
"learning_rate": 7.937323358440934e-05,
"loss": 1.0613,
"step": 685
},
{
"epoch": 0.8424908424908425,
"grad_norm": 0.13212021122536566,
"learning_rate": 7.370776077371622e-05,
"loss": 1.055,
"step": 690
},
{
"epoch": 0.8485958485958486,
"grad_norm": 0.12501157813798788,
"learning_rate": 6.82359282708292e-05,
"loss": 1.0644,
"step": 695
},
{
"epoch": 0.8547008547008547,
"grad_norm": 0.12182549104138736,
"learning_rate": 6.296022161790149e-05,
"loss": 1.0686,
"step": 700
},
{
"epoch": 0.8608058608058609,
"grad_norm": 0.10898863882704415,
"learning_rate": 5.78830372682721e-05,
"loss": 1.0595,
"step": 705
},
{
"epoch": 0.8669108669108669,
"grad_norm": 0.1292362091327554,
"learning_rate": 5.300668149789417e-05,
"loss": 1.0628,
"step": 710
},
{
"epoch": 0.873015873015873,
"grad_norm": 0.11135921961101819,
"learning_rate": 4.833336935772442e-05,
"loss": 1.0532,
"step": 715
},
{
"epoch": 0.8791208791208791,
"grad_norm": 0.1040842333058969,
"learning_rate": 4.386522366755169e-05,
"loss": 1.0548,
"step": 720
},
{
"epoch": 0.8852258852258852,
"grad_norm": 0.11114144762934852,
"learning_rate": 3.960427405172079e-05,
"loss": 1.0602,
"step": 725
},
{
"epoch": 0.8913308913308914,
"grad_norm": 0.10851073660711448,
"learning_rate": 3.5552456017189926e-05,
"loss": 1.0615,
"step": 730
},
{
"epoch": 0.8974358974358975,
"grad_norm": 0.1046722141969564,
"learning_rate": 3.171161007433937e-05,
"loss": 1.0542,
"step": 735
},
{
"epoch": 0.9035409035409036,
"grad_norm": 0.11710428457476799,
"learning_rate": 2.808348090093277e-05,
"loss": 1.0671,
"step": 740
},
{
"epoch": 0.9096459096459096,
"grad_norm": 0.11332319869107195,
"learning_rate": 2.466971654960931e-05,
"loss": 1.0611,
"step": 745
},
{
"epoch": 0.9157509157509157,
"grad_norm": 0.10374082585506901,
"learning_rate": 2.147186769926712e-05,
"loss": 1.0498,
"step": 750
},
{
"epoch": 0.9218559218559218,
"grad_norm": 0.11492942958557875,
"learning_rate": 1.8491386950677812e-05,
"loss": 1.0571,
"step": 755
},
{
"epoch": 0.927960927960928,
"grad_norm": 0.11080015958091284,
"learning_rate": 1.572962816665302e-05,
"loss": 1.0558,
"step": 760
},
{
"epoch": 0.9340659340659341,
"grad_norm": 0.117953492017612,
"learning_rate": 1.3187845857061508e-05,
"loss": 1.0462,
"step": 765
},
{
"epoch": 0.9401709401709402,
"grad_norm": 0.11023247026103157,
"learning_rate": 1.0867194608976228e-05,
"loss": 1.0731,
"step": 770
},
{
"epoch": 0.9462759462759462,
"grad_norm": 0.11752064314919194,
"learning_rate": 8.768728562211947e-06,
"loss": 1.058,
"step": 775
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.10584711974817956,
"learning_rate": 6.893400930488569e-06,
"loss": 1.0638,
"step": 780
},
{
"epoch": 0.9584859584859585,
"grad_norm": 0.12776920092469246,
"learning_rate": 5.242063568441313e-06,
"loss": 1.0633,
"step": 785
},
{
"epoch": 0.9645909645909646,
"grad_norm": 0.10955827972683771,
"learning_rate": 3.815466584670746e-06,
"loss": 1.0533,
"step": 790
},
{
"epoch": 0.9706959706959707,
"grad_norm": 0.11036039903845696,
"learning_rate": 2.6142580010117823e-06,
"loss": 1.0576,
"step": 795
},
{
"epoch": 0.9768009768009768,
"grad_norm": 0.10123727837311189,
"learning_rate": 1.6389834581739814e-06,
"loss": 1.0609,
"step": 800
},
{
"epoch": 0.9829059829059829,
"grad_norm": 0.11176827609005396,
"learning_rate": 8.900859678879769e-07,
"loss": 1.0575,
"step": 805
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.10493373702681778,
"learning_rate": 3.6790571167061305e-07,
"loss": 1.0604,
"step": 810
},
{
"epoch": 0.9951159951159951,
"grad_norm": 0.11496441250413074,
"learning_rate": 7.26798862996092e-08,
"loss": 1.0534,
"step": 815
},
{
"epoch": 1.0,
"eval_loss": 1.4183021783828735,
"eval_runtime": 107.3754,
"eval_samples_per_second": 195.501,
"eval_steps_per_second": 6.109,
"step": 819
},
{
"epoch": 1.0,
"step": 819,
"total_flos": 45247522406400.0,
"train_loss": 1.1312509008088536,
"train_runtime": 1838.4003,
"train_samples_per_second": 57.016,
"train_steps_per_second": 0.445
}
],
"logging_steps": 5,
"max_steps": 819,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 45247522406400.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}