stablelm-2-1_6b-sft-full / trainer_state.json
nnheui's picture
Model save
0d1677a verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9990846083431411,
"eval_steps": 500,
"global_step": 955,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0010461618935530272,
"grad_norm": 4.961991027903084,
"learning_rate": 2.0833333333333333e-07,
"loss": 1.5879,
"step": 1
},
{
"epoch": 0.005230809467765137,
"grad_norm": 4.618544468117898,
"learning_rate": 1.0416666666666667e-06,
"loss": 1.5933,
"step": 5
},
{
"epoch": 0.010461618935530274,
"grad_norm": 4.037023933749454,
"learning_rate": 2.0833333333333334e-06,
"loss": 1.5702,
"step": 10
},
{
"epoch": 0.01569242840329541,
"grad_norm": 1.8708269586813249,
"learning_rate": 3.125e-06,
"loss": 1.5369,
"step": 15
},
{
"epoch": 0.020923237871060547,
"grad_norm": 1.5902570000850822,
"learning_rate": 4.166666666666667e-06,
"loss": 1.4646,
"step": 20
},
{
"epoch": 0.026154047338825683,
"grad_norm": 1.23920395738266,
"learning_rate": 5.208333333333334e-06,
"loss": 1.4335,
"step": 25
},
{
"epoch": 0.03138485680659082,
"grad_norm": 1.1663956891784453,
"learning_rate": 6.25e-06,
"loss": 1.3982,
"step": 30
},
{
"epoch": 0.03661566627435596,
"grad_norm": 0.8974420486494152,
"learning_rate": 7.291666666666667e-06,
"loss": 1.3919,
"step": 35
},
{
"epoch": 0.041846475742121095,
"grad_norm": 0.8445948684549006,
"learning_rate": 8.333333333333334e-06,
"loss": 1.3576,
"step": 40
},
{
"epoch": 0.04707728520988623,
"grad_norm": 0.6980197067702758,
"learning_rate": 9.375000000000001e-06,
"loss": 1.3582,
"step": 45
},
{
"epoch": 0.052308094677651365,
"grad_norm": 0.8409122561540898,
"learning_rate": 1.0416666666666668e-05,
"loss": 1.3458,
"step": 50
},
{
"epoch": 0.0575389041454165,
"grad_norm": 0.6948599150905024,
"learning_rate": 1.1458333333333333e-05,
"loss": 1.335,
"step": 55
},
{
"epoch": 0.06276971361318164,
"grad_norm": 0.651340813779911,
"learning_rate": 1.25e-05,
"loss": 1.322,
"step": 60
},
{
"epoch": 0.06800052308094677,
"grad_norm": 0.684798803653097,
"learning_rate": 1.3541666666666668e-05,
"loss": 1.3456,
"step": 65
},
{
"epoch": 0.07323133254871192,
"grad_norm": 0.6258722254574212,
"learning_rate": 1.4583333333333333e-05,
"loss": 1.317,
"step": 70
},
{
"epoch": 0.07846214201647705,
"grad_norm": 0.661994715425898,
"learning_rate": 1.5625e-05,
"loss": 1.314,
"step": 75
},
{
"epoch": 0.08369295148424219,
"grad_norm": 0.6157440945511082,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.3174,
"step": 80
},
{
"epoch": 0.08892376095200732,
"grad_norm": 0.6136457513656507,
"learning_rate": 1.7708333333333335e-05,
"loss": 1.3208,
"step": 85
},
{
"epoch": 0.09415457041977246,
"grad_norm": 0.6609752901635255,
"learning_rate": 1.8750000000000002e-05,
"loss": 1.3217,
"step": 90
},
{
"epoch": 0.0993853798875376,
"grad_norm": 0.6433338679997594,
"learning_rate": 1.979166666666667e-05,
"loss": 1.3209,
"step": 95
},
{
"epoch": 0.10461618935530273,
"grad_norm": 0.748785028585811,
"learning_rate": 1.999892997072575e-05,
"loss": 1.3015,
"step": 100
},
{
"epoch": 0.10984699882306787,
"grad_norm": 0.7348845509310983,
"learning_rate": 1.99945833692589e-05,
"loss": 1.3043,
"step": 105
},
{
"epoch": 0.115077808290833,
"grad_norm": 0.7150167557908745,
"learning_rate": 1.9986894771071707e-05,
"loss": 1.3036,
"step": 110
},
{
"epoch": 0.12030861775859815,
"grad_norm": 0.6229579295007591,
"learning_rate": 1.9975866747083734e-05,
"loss": 1.3046,
"step": 115
},
{
"epoch": 0.12553942722636327,
"grad_norm": 0.626634171036282,
"learning_rate": 1.9961502984854394e-05,
"loss": 1.3011,
"step": 120
},
{
"epoch": 0.1307702366941284,
"grad_norm": 0.6732748047847544,
"learning_rate": 1.9943808287349902e-05,
"loss": 1.2922,
"step": 125
},
{
"epoch": 0.13600104616189354,
"grad_norm": 0.6336745846509011,
"learning_rate": 1.992278857133726e-05,
"loss": 1.3023,
"step": 130
},
{
"epoch": 0.1412318556296587,
"grad_norm": 0.63287698051173,
"learning_rate": 1.9898450865405786e-05,
"loss": 1.2912,
"step": 135
},
{
"epoch": 0.14646266509742384,
"grad_norm": 0.6243758841550209,
"learning_rate": 1.9870803307616916e-05,
"loss": 1.2953,
"step": 140
},
{
"epoch": 0.15169347456518897,
"grad_norm": 0.7127519633361736,
"learning_rate": 1.983985514278296e-05,
"loss": 1.2955,
"step": 145
},
{
"epoch": 0.1569242840329541,
"grad_norm": 0.6226333486523956,
"learning_rate": 1.9805616719375852e-05,
"loss": 1.2932,
"step": 150
},
{
"epoch": 0.16215509350071924,
"grad_norm": 0.6823517100118245,
"learning_rate": 1.9768099486066776e-05,
"loss": 1.2745,
"step": 155
},
{
"epoch": 0.16738590296848438,
"grad_norm": 0.6663881488848158,
"learning_rate": 1.9727315987897993e-05,
"loss": 1.3024,
"step": 160
},
{
"epoch": 0.17261671243624951,
"grad_norm": 0.6250204764928626,
"learning_rate": 1.9683279862087986e-05,
"loss": 1.2725,
"step": 165
},
{
"epoch": 0.17784752190401465,
"grad_norm": 0.6587024144174084,
"learning_rate": 1.963600583347147e-05,
"loss": 1.2883,
"step": 170
},
{
"epoch": 0.18307833137177978,
"grad_norm": 0.6553453461637575,
"learning_rate": 1.9585509709575646e-05,
"loss": 1.2934,
"step": 175
},
{
"epoch": 0.18830914083954492,
"grad_norm": 0.6612913681156035,
"learning_rate": 1.9531808375334512e-05,
"loss": 1.2663,
"step": 180
},
{
"epoch": 0.19353995030731005,
"grad_norm": 0.6536121257096528,
"learning_rate": 1.9474919787442835e-05,
"loss": 1.2588,
"step": 185
},
{
"epoch": 0.1987707597750752,
"grad_norm": 0.6498560967867221,
"learning_rate": 1.9414862968351788e-05,
"loss": 1.261,
"step": 190
},
{
"epoch": 0.20400156924284032,
"grad_norm": 0.6437028941150709,
"learning_rate": 1.935165799990821e-05,
"loss": 1.2764,
"step": 195
},
{
"epoch": 0.20923237871060546,
"grad_norm": 0.7042353774035648,
"learning_rate": 1.9285326016639624e-05,
"loss": 1.2715,
"step": 200
},
{
"epoch": 0.2144631881783706,
"grad_norm": 0.6615769962934966,
"learning_rate": 1.9215889198687245e-05,
"loss": 1.2515,
"step": 205
},
{
"epoch": 0.21969399764613573,
"grad_norm": 0.6674880822729611,
"learning_rate": 1.9143370764389374e-05,
"loss": 1.2828,
"step": 210
},
{
"epoch": 0.22492480711390087,
"grad_norm": 0.6423252942504364,
"learning_rate": 1.906779496251763e-05,
"loss": 1.2791,
"step": 215
},
{
"epoch": 0.230155616581666,
"grad_norm": 0.6391984125238104,
"learning_rate": 1.8989187064168643e-05,
"loss": 1.2519,
"step": 220
},
{
"epoch": 0.23538642604943116,
"grad_norm": 0.6477151176504692,
"learning_rate": 1.8907573354313853e-05,
"loss": 1.2777,
"step": 225
},
{
"epoch": 0.2406172355171963,
"grad_norm": 0.6269146787303694,
"learning_rate": 1.8822981123010343e-05,
"loss": 1.2736,
"step": 230
},
{
"epoch": 0.24584804498496143,
"grad_norm": 0.6477481280746402,
"learning_rate": 1.873543865627556e-05,
"loss": 1.2732,
"step": 235
},
{
"epoch": 0.25107885445272654,
"grad_norm": 0.6651047763900065,
"learning_rate": 1.8644975226629025e-05,
"loss": 1.2829,
"step": 240
},
{
"epoch": 0.2563096639204917,
"grad_norm": 0.6432975261843621,
"learning_rate": 1.8551621083304147e-05,
"loss": 1.2615,
"step": 245
},
{
"epoch": 0.2615404733882568,
"grad_norm": 0.6589800378988344,
"learning_rate": 1.8455407442133467e-05,
"loss": 1.2824,
"step": 250
},
{
"epoch": 0.266771282856022,
"grad_norm": 0.6374519780745838,
"learning_rate": 1.8356366475110697e-05,
"loss": 1.2809,
"step": 255
},
{
"epoch": 0.2720020923237871,
"grad_norm": 0.6474176000311428,
"learning_rate": 1.8254531299633007e-05,
"loss": 1.2765,
"step": 260
},
{
"epoch": 0.27723290179155224,
"grad_norm": 0.611205619408698,
"learning_rate": 1.81499359674272e-05,
"loss": 1.2723,
"step": 265
},
{
"epoch": 0.2824637112593174,
"grad_norm": 0.680714525048176,
"learning_rate": 1.8042615453163484e-05,
"loss": 1.2606,
"step": 270
},
{
"epoch": 0.2876945207270825,
"grad_norm": 0.6405723682781137,
"learning_rate": 1.7932605642760607e-05,
"loss": 1.2495,
"step": 275
},
{
"epoch": 0.2929253301948477,
"grad_norm": 0.6279226914713609,
"learning_rate": 1.7819943321386295e-05,
"loss": 1.2735,
"step": 280
},
{
"epoch": 0.2981561396626128,
"grad_norm": 0.6284127404605249,
"learning_rate": 1.7704666161156994e-05,
"loss": 1.241,
"step": 285
},
{
"epoch": 0.30338694913037795,
"grad_norm": 0.6499789986037162,
"learning_rate": 1.7586812708541046e-05,
"loss": 1.2607,
"step": 290
},
{
"epoch": 0.30861775859814305,
"grad_norm": 0.6557734964553777,
"learning_rate": 1.746642237146948e-05,
"loss": 1.2746,
"step": 295
},
{
"epoch": 0.3138485680659082,
"grad_norm": 0.6397583630089397,
"learning_rate": 1.7343535406158773e-05,
"loss": 1.2606,
"step": 300
},
{
"epoch": 0.3190793775336733,
"grad_norm": 0.6893845618635109,
"learning_rate": 1.7218192903649926e-05,
"loss": 1.261,
"step": 305
},
{
"epoch": 0.3243101870014385,
"grad_norm": 0.7201666359135361,
"learning_rate": 1.7090436776068422e-05,
"loss": 1.2713,
"step": 310
},
{
"epoch": 0.3295409964692036,
"grad_norm": 0.6687526125254434,
"learning_rate": 1.6960309742609603e-05,
"loss": 1.2721,
"step": 315
},
{
"epoch": 0.33477180593696876,
"grad_norm": 0.7677992466340372,
"learning_rate": 1.682785531525422e-05,
"loss": 1.2671,
"step": 320
},
{
"epoch": 0.34000261540473387,
"grad_norm": 0.7054430863360542,
"learning_rate": 1.6693117784218818e-05,
"loss": 1.2512,
"step": 325
},
{
"epoch": 0.34523342487249903,
"grad_norm": 0.7122244372275465,
"learning_rate": 1.655614220314598e-05,
"loss": 1.2625,
"step": 330
},
{
"epoch": 0.35046423434026414,
"grad_norm": 0.679853303463346,
"learning_rate": 1.6416974374039227e-05,
"loss": 1.2767,
"step": 335
},
{
"epoch": 0.3556950438080293,
"grad_norm": 0.6684546083293239,
"learning_rate": 1.6275660831947725e-05,
"loss": 1.253,
"step": 340
},
{
"epoch": 0.3609258532757944,
"grad_norm": 0.6148491341875125,
"learning_rate": 1.6132248829405845e-05,
"loss": 1.2664,
"step": 345
},
{
"epoch": 0.36615666274355957,
"grad_norm": 0.6287400163765243,
"learning_rate": 1.5986786320632842e-05,
"loss": 1.29,
"step": 350
},
{
"epoch": 0.3713874722113247,
"grad_norm": 0.6429840333148633,
"learning_rate": 1.5839321945497847e-05,
"loss": 1.259,
"step": 355
},
{
"epoch": 0.37661828167908984,
"grad_norm": 0.6213894267805022,
"learning_rate": 1.5689905013255683e-05,
"loss": 1.2721,
"step": 360
},
{
"epoch": 0.381849091146855,
"grad_norm": 0.6657140337203303,
"learning_rate": 1.5538585486058747e-05,
"loss": 1.2629,
"step": 365
},
{
"epoch": 0.3870799006146201,
"grad_norm": 0.6216486922374719,
"learning_rate": 1.5385413962250657e-05,
"loss": 1.2445,
"step": 370
},
{
"epoch": 0.39231071008238527,
"grad_norm": 0.640435105766003,
"learning_rate": 1.5230441659447128e-05,
"loss": 1.2672,
"step": 375
},
{
"epoch": 0.3975415195501504,
"grad_norm": 0.628008495827186,
"learning_rate": 1.507372039740978e-05,
"loss": 1.2782,
"step": 380
},
{
"epoch": 0.40277232901791554,
"grad_norm": 0.6525051028721182,
"learning_rate": 1.4915302580718614e-05,
"loss": 1.249,
"step": 385
},
{
"epoch": 0.40800313848568065,
"grad_norm": 0.6278258712485207,
"learning_rate": 1.4755241181248923e-05,
"loss": 1.2588,
"step": 390
},
{
"epoch": 0.4132339479534458,
"grad_norm": 0.6550288396521164,
"learning_rate": 1.4593589720458507e-05,
"loss": 1.255,
"step": 395
},
{
"epoch": 0.4184647574212109,
"grad_norm": 0.6820552488018682,
"learning_rate": 1.443040225149114e-05,
"loss": 1.2498,
"step": 400
},
{
"epoch": 0.4236955668889761,
"grad_norm": 0.6399254481819071,
"learning_rate": 1.4265733341102235e-05,
"loss": 1.2666,
"step": 405
},
{
"epoch": 0.4289263763567412,
"grad_norm": 0.6722624199607894,
"learning_rate": 1.4099638051412745e-05,
"loss": 1.245,
"step": 410
},
{
"epoch": 0.43415718582450635,
"grad_norm": 0.6302145600803009,
"learning_rate": 1.3932171921497483e-05,
"loss": 1.2611,
"step": 415
},
{
"epoch": 0.43938799529227146,
"grad_norm": 0.6031404765855133,
"learning_rate": 1.3763390948813897e-05,
"loss": 1.2372,
"step": 420
},
{
"epoch": 0.4446188047600366,
"grad_norm": 0.646493114663968,
"learning_rate": 1.3593351570477608e-05,
"loss": 1.2426,
"step": 425
},
{
"epoch": 0.44984961422780173,
"grad_norm": 0.6195059553793902,
"learning_rate": 1.3422110644390911e-05,
"loss": 1.2169,
"step": 430
},
{
"epoch": 0.4550804236955669,
"grad_norm": 0.6012958936997463,
"learning_rate": 1.3249725430230595e-05,
"loss": 1.2728,
"step": 435
},
{
"epoch": 0.460311233163332,
"grad_norm": 0.617177322353044,
"learning_rate": 1.3076253570301409e-05,
"loss": 1.2518,
"step": 440
},
{
"epoch": 0.46554204263109716,
"grad_norm": 0.6292828261202444,
"learning_rate": 1.2901753070261565e-05,
"loss": 1.2543,
"step": 445
},
{
"epoch": 0.4707728520988623,
"grad_norm": 0.597666355379697,
"learning_rate": 1.2726282279726788e-05,
"loss": 1.2427,
"step": 450
},
{
"epoch": 0.47600366156662743,
"grad_norm": 0.6234161905971162,
"learning_rate": 1.2549899872759288e-05,
"loss": 1.2602,
"step": 455
},
{
"epoch": 0.4812344710343926,
"grad_norm": 0.629762327137135,
"learning_rate": 1.237266482824832e-05,
"loss": 1.2428,
"step": 460
},
{
"epoch": 0.4864652805021577,
"grad_norm": 0.6210086267634197,
"learning_rate": 1.2194636410188748e-05,
"loss": 1.2281,
"step": 465
},
{
"epoch": 0.49169608996992287,
"grad_norm": 0.6456911580326817,
"learning_rate": 1.2015874147864314e-05,
"loss": 1.2342,
"step": 470
},
{
"epoch": 0.496926899437688,
"grad_norm": 0.6472528263693088,
"learning_rate": 1.183643781594219e-05,
"loss": 1.2427,
"step": 475
},
{
"epoch": 0.5021577089054531,
"grad_norm": 0.647823531177134,
"learning_rate": 1.165638741448548e-05,
"loss": 1.2522,
"step": 480
},
{
"epoch": 0.5073885183732183,
"grad_norm": 0.6693118299281153,
"learning_rate": 1.147578314889033e-05,
"loss": 1.2619,
"step": 485
},
{
"epoch": 0.5126193278409834,
"grad_norm": 0.667730694230485,
"learning_rate": 1.1294685409754434e-05,
"loss": 1.2429,
"step": 490
},
{
"epoch": 0.5178501373087485,
"grad_norm": 0.6046644310580812,
"learning_rate": 1.1113154752683548e-05,
"loss": 1.2588,
"step": 495
},
{
"epoch": 0.5230809467765136,
"grad_norm": 0.6785327532515957,
"learning_rate": 1.0931251878042882e-05,
"loss": 1.2673,
"step": 500
},
{
"epoch": 0.5283117562442788,
"grad_norm": 0.6252703595295017,
"learning_rate": 1.0749037610660041e-05,
"loss": 1.264,
"step": 505
},
{
"epoch": 0.533542565712044,
"grad_norm": 0.6079580441878377,
"learning_rate": 1.0566572879486388e-05,
"loss": 1.2619,
"step": 510
},
{
"epoch": 0.538773375179809,
"grad_norm": 0.6213036767388472,
"learning_rate": 1.0383918697223564e-05,
"loss": 1.2602,
"step": 515
},
{
"epoch": 0.5440041846475742,
"grad_norm": 0.5992653066437161,
"learning_rate": 1.020113613992203e-05,
"loss": 1.2636,
"step": 520
},
{
"epoch": 0.5492349941153394,
"grad_norm": 0.5983825011403769,
"learning_rate": 1.001828632655837e-05,
"loss": 1.254,
"step": 525
},
{
"epoch": 0.5544658035831045,
"grad_norm": 0.6237947953829833,
"learning_rate": 9.835430398598319e-06,
"loss": 1.2573,
"step": 530
},
{
"epoch": 0.5596966130508696,
"grad_norm": 0.6015544745764206,
"learning_rate": 9.652629499552216e-06,
"loss": 1.2332,
"step": 535
},
{
"epoch": 0.5649274225186348,
"grad_norm": 0.6724219499123357,
"learning_rate": 9.469944754529784e-06,
"loss": 1.2489,
"step": 540
},
{
"epoch": 0.5701582319863999,
"grad_norm": 0.5900962511293482,
"learning_rate": 9.28743724980107e-06,
"loss": 1.2486,
"step": 545
},
{
"epoch": 0.575389041454165,
"grad_norm": 0.5939356137294083,
"learning_rate": 9.105168012370372e-06,
"loss": 1.2464,
"step": 550
},
{
"epoch": 0.5806198509219301,
"grad_norm": 0.6072005219993765,
"learning_rate": 8.923197989569981e-06,
"loss": 1.2484,
"step": 555
},
{
"epoch": 0.5858506603896954,
"grad_norm": 0.6408535640602984,
"learning_rate": 8.741588028680566e-06,
"loss": 1.2577,
"step": 560
},
{
"epoch": 0.5910814698574605,
"grad_norm": 0.5820294502690248,
"learning_rate": 8.560398856585002e-06,
"loss": 1.2519,
"step": 565
},
{
"epoch": 0.5963122793252256,
"grad_norm": 0.5866823280811903,
"learning_rate": 8.379691059462478e-06,
"loss": 1.2373,
"step": 570
},
{
"epoch": 0.6015430887929907,
"grad_norm": 0.6268376105145648,
"learning_rate": 8.199525062529626e-06,
"loss": 1.261,
"step": 575
},
{
"epoch": 0.6067738982607559,
"grad_norm": 0.5899507751154045,
"learning_rate": 8.01996110983552e-06,
"loss": 1.2469,
"step": 580
},
{
"epoch": 0.612004707728521,
"grad_norm": 0.6110501827689294,
"learning_rate": 7.841059244117189e-06,
"loss": 1.24,
"step": 585
},
{
"epoch": 0.6172355171962861,
"grad_norm": 0.628795675438309,
"learning_rate": 7.662879286722496e-06,
"loss": 1.2678,
"step": 590
},
{
"epoch": 0.6224663266640512,
"grad_norm": 0.5817062103966367,
"learning_rate": 7.485480817607031e-06,
"loss": 1.2384,
"step": 595
},
{
"epoch": 0.6276971361318164,
"grad_norm": 0.5950726911519293,
"learning_rate": 7.30892315541171e-06,
"loss": 1.2356,
"step": 600
},
{
"epoch": 0.6329279455995815,
"grad_norm": 0.5727952261916434,
"learning_rate": 7.133265337627757e-06,
"loss": 1.2406,
"step": 605
},
{
"epoch": 0.6381587550673467,
"grad_norm": 0.575271616339552,
"learning_rate": 6.958566100855716e-06,
"loss": 1.2437,
"step": 610
},
{
"epoch": 0.6433895645351118,
"grad_norm": 0.5790390123089401,
"learning_rate": 6.78488386116505e-06,
"loss": 1.2583,
"step": 615
},
{
"epoch": 0.648620374002877,
"grad_norm": 0.5932077205106131,
"learning_rate": 6.612276694560927e-06,
"loss": 1.2413,
"step": 620
},
{
"epoch": 0.6538511834706421,
"grad_norm": 0.5947522152199447,
"learning_rate": 6.44080231756473e-06,
"loss": 1.2549,
"step": 625
},
{
"epoch": 0.6590819929384072,
"grad_norm": 1.3459652842247485,
"learning_rate": 6.2705180679147455e-06,
"loss": 1.2387,
"step": 630
},
{
"epoch": 0.6643128024061724,
"grad_norm": 0.7269750930986757,
"learning_rate": 6.101480885393537e-06,
"loss": 1.2315,
"step": 635
},
{
"epoch": 0.6695436118739375,
"grad_norm": 0.5957998707048122,
"learning_rate": 5.933747292788369e-06,
"loss": 1.2677,
"step": 640
},
{
"epoch": 0.6747744213417026,
"grad_norm": 0.5850290378596165,
"learning_rate": 5.767373376991082e-06,
"loss": 1.2291,
"step": 645
},
{
"epoch": 0.6800052308094677,
"grad_norm": 0.5844027863277863,
"learning_rate": 5.602414770243698e-06,
"loss": 1.2273,
"step": 650
},
{
"epoch": 0.685236040277233,
"grad_norm": 0.5868679965624024,
"learning_rate": 5.438926631536087e-06,
"loss": 1.2479,
"step": 655
},
{
"epoch": 0.6904668497449981,
"grad_norm": 0.5831449921364225,
"learning_rate": 5.276963628161833e-06,
"loss": 1.247,
"step": 660
},
{
"epoch": 0.6956976592127632,
"grad_norm": 0.5755759622405301,
"learning_rate": 5.116579917438564e-06,
"loss": 1.2447,
"step": 665
},
{
"epoch": 0.7009284686805283,
"grad_norm": 0.5768540427743302,
"learning_rate": 4.957829128598781e-06,
"loss": 1.2177,
"step": 670
},
{
"epoch": 0.7061592781482935,
"grad_norm": 0.598911774868325,
"learning_rate": 4.80076434485727e-06,
"loss": 1.2321,
"step": 675
},
{
"epoch": 0.7113900876160586,
"grad_norm": 0.5969706523304447,
"learning_rate": 4.645438085661085e-06,
"loss": 1.234,
"step": 680
},
{
"epoch": 0.7166208970838237,
"grad_norm": 0.5866245773773069,
"learning_rate": 4.4919022891280725e-06,
"loss": 1.2456,
"step": 685
},
{
"epoch": 0.7218517065515888,
"grad_norm": 0.5811720592986388,
"learning_rate": 4.340208294679745e-06,
"loss": 1.245,
"step": 690
},
{
"epoch": 0.727082516019354,
"grad_norm": 0.5849016337714122,
"learning_rate": 4.190406825874377e-06,
"loss": 1.2212,
"step": 695
},
{
"epoch": 0.7323133254871191,
"grad_norm": 0.6255138841124418,
"learning_rate": 4.042547973446017e-06,
"loss": 1.2318,
"step": 700
},
{
"epoch": 0.7375441349548842,
"grad_norm": 0.5808819882391798,
"learning_rate": 3.896681178555099e-06,
"loss": 1.2616,
"step": 705
},
{
"epoch": 0.7427749444226494,
"grad_norm": 0.5821049889121402,
"learning_rate": 3.7528552162562858e-06,
"loss": 1.2342,
"step": 710
},
{
"epoch": 0.7480057538904146,
"grad_norm": 0.6008223090596293,
"learning_rate": 3.6111181791890184e-06,
"loss": 1.2472,
"step": 715
},
{
"epoch": 0.7532365633581797,
"grad_norm": 0.5950331976607752,
"learning_rate": 3.471517461496253e-06,
"loss": 1.2211,
"step": 720
},
{
"epoch": 0.7584673728259448,
"grad_norm": 0.5695566788307966,
"learning_rate": 3.3340997429767786e-06,
"loss": 1.2397,
"step": 725
},
{
"epoch": 0.76369818229371,
"grad_norm": 0.5922108634556766,
"learning_rate": 3.1989109734763936e-06,
"loss": 1.2624,
"step": 730
},
{
"epoch": 0.7689289917614751,
"grad_norm": 0.573161649411567,
"learning_rate": 3.0659963575231544e-06,
"loss": 1.25,
"step": 735
},
{
"epoch": 0.7741598012292402,
"grad_norm": 0.5745082815289888,
"learning_rate": 2.935400339211841e-06,
"loss": 1.2564,
"step": 740
},
{
"epoch": 0.7793906106970053,
"grad_norm": 0.5599070185795609,
"learning_rate": 2.8071665873427244e-06,
"loss": 1.2341,
"step": 745
},
{
"epoch": 0.7846214201647705,
"grad_norm": 0.5798846902278265,
"learning_rate": 2.681337980819536e-06,
"loss": 1.2425,
"step": 750
},
{
"epoch": 0.7898522296325357,
"grad_norm": 0.5630366958265783,
"learning_rate": 2.5579565943116092e-06,
"loss": 1.2503,
"step": 755
},
{
"epoch": 0.7950830391003008,
"grad_norm": 0.5612114479196867,
"learning_rate": 2.437063684184893e-06,
"loss": 1.2372,
"step": 760
},
{
"epoch": 0.8003138485680659,
"grad_norm": 0.5786482688071404,
"learning_rate": 2.318699674706639e-06,
"loss": 1.2539,
"step": 765
},
{
"epoch": 0.8055446580358311,
"grad_norm": 0.5609594448423239,
"learning_rate": 2.202904144528295e-06,
"loss": 1.2359,
"step": 770
},
{
"epoch": 0.8107754675035962,
"grad_norm": 0.5761081087482597,
"learning_rate": 2.08971581345115e-06,
"loss": 1.2333,
"step": 775
},
{
"epoch": 0.8160062769713613,
"grad_norm": 0.5773902237533778,
"learning_rate": 1.979172529479193e-06,
"loss": 1.2405,
"step": 780
},
{
"epoch": 0.8212370864391264,
"grad_norm": 0.5692272061773305,
"learning_rate": 1.8713112561634671e-06,
"loss": 1.2531,
"step": 785
},
{
"epoch": 0.8264678959068916,
"grad_norm": 0.8502635478696626,
"learning_rate": 1.7661680602421594e-06,
"loss": 1.2357,
"step": 790
},
{
"epoch": 0.8316987053746567,
"grad_norm": 0.5725480612758482,
"learning_rate": 1.663778099580583e-06,
"loss": 1.231,
"step": 795
},
{
"epoch": 0.8369295148424218,
"grad_norm": 0.5528630417115946,
"learning_rate": 1.5641756114150552e-06,
"loss": 1.2412,
"step": 800
},
{
"epoch": 0.842160324310187,
"grad_norm": 0.5462565230167501,
"learning_rate": 1.4673939009046268e-06,
"loss": 1.2233,
"step": 805
},
{
"epoch": 0.8473911337779522,
"grad_norm": 0.5663269502388393,
"learning_rate": 1.3734653299944834e-06,
"loss": 1.2277,
"step": 810
},
{
"epoch": 0.8526219432457173,
"grad_norm": 0.5686962762287001,
"learning_rate": 1.2824213065947232e-06,
"loss": 1.2357,
"step": 815
},
{
"epoch": 0.8578527527134824,
"grad_norm": 0.5638758372127466,
"learning_rate": 1.194292274078156e-06,
"loss": 1.2377,
"step": 820
},
{
"epoch": 0.8630835621812476,
"grad_norm": 0.5586378869453262,
"learning_rate": 1.1091077011006302e-06,
"loss": 1.2223,
"step": 825
},
{
"epoch": 0.8683143716490127,
"grad_norm": 0.5517524656609795,
"learning_rate": 1.0268960717472742e-06,
"loss": 1.2574,
"step": 830
},
{
"epoch": 0.8735451811167778,
"grad_norm": 0.5569662486368889,
"learning_rate": 9.476848760079671e-07,
"loss": 1.2335,
"step": 835
},
{
"epoch": 0.8787759905845429,
"grad_norm": 0.5643447607687533,
"learning_rate": 8.715006005852144e-07,
"loss": 1.2304,
"step": 840
},
{
"epoch": 0.8840068000523081,
"grad_norm": 0.550747548292025,
"learning_rate": 7.983687200375046e-07,
"loss": 1.2281,
"step": 845
},
{
"epoch": 0.8892376095200732,
"grad_norm": 0.5574658998449357,
"learning_rate": 7.283136882611063e-07,
"loss": 1.2329,
"step": 850
},
{
"epoch": 0.8944684189878384,
"grad_norm": 0.5737161178123568,
"learning_rate": 6.613589303131506e-07,
"loss": 1.2465,
"step": 855
},
{
"epoch": 0.8996992284556035,
"grad_norm": 0.5738100002167115,
"learning_rate": 5.975268345787455e-07,
"loss": 1.2408,
"step": 860
},
{
"epoch": 0.9049300379233687,
"grad_norm": 0.5542103705854088,
"learning_rate": 5.368387452847312e-07,
"loss": 1.2369,
"step": 865
},
{
"epoch": 0.9101608473911338,
"grad_norm": 0.5509438118396119,
"learning_rate": 4.793149553625786e-07,
"loss": 1.2677,
"step": 870
},
{
"epoch": 0.9153916568588989,
"grad_norm": 0.5573824119903792,
"learning_rate": 4.2497469966282125e-07,
"loss": 1.2429,
"step": 875
},
{
"epoch": 0.920622466326664,
"grad_norm": 0.5438647452016272,
"learning_rate": 3.738361485232922e-07,
"loss": 1.2236,
"step": 880
},
{
"epoch": 0.9258532757944292,
"grad_norm": 0.5597553842668248,
"learning_rate": 3.2591640169331697e-07,
"loss": 1.2443,
"step": 885
},
{
"epoch": 0.9310840852621943,
"grad_norm": 0.5541351488188309,
"learning_rate": 2.8123148261587465e-07,
"loss": 1.2292,
"step": 890
},
{
"epoch": 0.9363148947299594,
"grad_norm": 0.5510390666909667,
"learning_rate": 2.397963330696751e-07,
"loss": 1.2371,
"step": 895
},
{
"epoch": 0.9415457041977247,
"grad_norm": 0.5662372990839701,
"learning_rate": 2.0162480817291442e-07,
"loss": 1.2385,
"step": 900
},
{
"epoch": 0.9467765136654898,
"grad_norm": 0.5633092432947229,
"learning_rate": 1.6672967175038634e-07,
"loss": 1.2357,
"step": 905
},
{
"epoch": 0.9520073231332549,
"grad_norm": 0.5485802540619047,
"learning_rate": 1.3512259206550748e-07,
"loss": 1.241,
"step": 910
},
{
"epoch": 0.95723813260102,
"grad_norm": 0.5451187400528298,
"learning_rate": 1.0681413791867157e-07,
"loss": 1.2331,
"step": 915
},
{
"epoch": 0.9624689420687852,
"grad_norm": 0.5544164676125732,
"learning_rate": 8.181377511324306e-08,
"loss": 1.2486,
"step": 920
},
{
"epoch": 0.9676997515365503,
"grad_norm": 0.5773845105032677,
"learning_rate": 6.012986329038462e-08,
"loss": 1.2386,
"step": 925
},
{
"epoch": 0.9729305610043154,
"grad_norm": 0.5478843295079262,
"learning_rate": 4.1769653133743036e-08,
"loss": 1.215,
"step": 930
},
{
"epoch": 0.9781613704720805,
"grad_norm": 0.5608458529460807,
"learning_rate": 2.673928394496206e-08,
"loss": 1.2301,
"step": 935
},
{
"epoch": 0.9833921799398457,
"grad_norm": 0.5519105435517161,
"learning_rate": 1.5043781590823313e-08,
"loss": 1.2173,
"step": 940
},
{
"epoch": 0.9886229894076108,
"grad_norm": 0.5536445777152418,
"learning_rate": 6.687056822688442e-09,
"loss": 1.2308,
"step": 945
},
{
"epoch": 0.993853798875376,
"grad_norm": 0.5686300705360647,
"learning_rate": 1.6719039688162242e-09,
"loss": 1.2192,
"step": 950
},
{
"epoch": 0.9990846083431411,
"grad_norm": 0.5671702033849003,
"learning_rate": 0.0,
"loss": 1.24,
"step": 955
},
{
"epoch": 0.9990846083431411,
"step": 955,
"total_flos": 522931729858560.0,
"train_loss": 1.2670168572071334,
"train_runtime": 18760.2941,
"train_samples_per_second": 6.522,
"train_steps_per_second": 0.051
}
],
"logging_steps": 5,
"max_steps": 955,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 522931729858560.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}