adhisetiawan's picture
End of training
f10985f verified
{
"best_metric": 0.834983498349835,
"best_model_checkpoint": "vit-base-patch16-224-finetuned-food101/checkpoint-1596",
"epoch": 2.995776630689817,
"eval_steps": 500,
"global_step": 1596,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.018770530267480056,
"grad_norm": 2.9933698177337646,
"learning_rate": 3.125e-06,
"loss": 4.739,
"step": 10
},
{
"epoch": 0.03754106053496011,
"grad_norm": 3.0962929725646973,
"learning_rate": 6.25e-06,
"loss": 4.7159,
"step": 20
},
{
"epoch": 0.05631159080244017,
"grad_norm": 3.2671728134155273,
"learning_rate": 9.375000000000001e-06,
"loss": 4.6674,
"step": 30
},
{
"epoch": 0.07508212106992022,
"grad_norm": 3.073523759841919,
"learning_rate": 1.25e-05,
"loss": 4.6293,
"step": 40
},
{
"epoch": 0.09385265133740028,
"grad_norm": 3.1302390098571777,
"learning_rate": 1.5625e-05,
"loss": 4.5709,
"step": 50
},
{
"epoch": 0.11262318160488034,
"grad_norm": 2.9043614864349365,
"learning_rate": 1.8750000000000002e-05,
"loss": 4.4634,
"step": 60
},
{
"epoch": 0.1313937118723604,
"grad_norm": 3.4175333976745605,
"learning_rate": 2.1875e-05,
"loss": 4.3879,
"step": 70
},
{
"epoch": 0.15016424213984045,
"grad_norm": 3.323888063430786,
"learning_rate": 2.5e-05,
"loss": 4.2587,
"step": 80
},
{
"epoch": 0.1689347724073205,
"grad_norm": 3.0213475227355957,
"learning_rate": 2.8125000000000003e-05,
"loss": 4.0885,
"step": 90
},
{
"epoch": 0.18770530267480057,
"grad_norm": 3.02178955078125,
"learning_rate": 3.125e-05,
"loss": 3.9028,
"step": 100
},
{
"epoch": 0.2064758329422806,
"grad_norm": 3.3495538234710693,
"learning_rate": 3.4375e-05,
"loss": 3.7353,
"step": 110
},
{
"epoch": 0.22524636320976069,
"grad_norm": 3.1515848636627197,
"learning_rate": 3.7500000000000003e-05,
"loss": 3.4697,
"step": 120
},
{
"epoch": 0.24401689347724073,
"grad_norm": 3.284679889678955,
"learning_rate": 4.0625000000000005e-05,
"loss": 3.2815,
"step": 130
},
{
"epoch": 0.2627874237447208,
"grad_norm": 3.226576805114746,
"learning_rate": 4.375e-05,
"loss": 2.9895,
"step": 140
},
{
"epoch": 0.28155795401220085,
"grad_norm": 3.181521415710449,
"learning_rate": 4.6875e-05,
"loss": 2.7421,
"step": 150
},
{
"epoch": 0.3003284842796809,
"grad_norm": 3.1563026905059814,
"learning_rate": 5e-05,
"loss": 2.587,
"step": 160
},
{
"epoch": 0.31909901454716094,
"grad_norm": 3.2322466373443604,
"learning_rate": 4.965181058495822e-05,
"loss": 2.3671,
"step": 170
},
{
"epoch": 0.337869544814641,
"grad_norm": 3.2258055210113525,
"learning_rate": 4.930362116991643e-05,
"loss": 2.1425,
"step": 180
},
{
"epoch": 0.3566400750821211,
"grad_norm": 3.141265392303467,
"learning_rate": 4.895543175487465e-05,
"loss": 2.0185,
"step": 190
},
{
"epoch": 0.37541060534960113,
"grad_norm": 3.157705307006836,
"learning_rate": 4.860724233983287e-05,
"loss": 1.9035,
"step": 200
},
{
"epoch": 0.3941811356170812,
"grad_norm": 3.300532102584839,
"learning_rate": 4.825905292479109e-05,
"loss": 1.8364,
"step": 210
},
{
"epoch": 0.4129516658845612,
"grad_norm": 3.4612457752227783,
"learning_rate": 4.79108635097493e-05,
"loss": 1.693,
"step": 220
},
{
"epoch": 0.43172219615204127,
"grad_norm": 3.306436777114868,
"learning_rate": 4.756267409470752e-05,
"loss": 1.5683,
"step": 230
},
{
"epoch": 0.45049272641952137,
"grad_norm": 3.522141695022583,
"learning_rate": 4.721448467966574e-05,
"loss": 1.5139,
"step": 240
},
{
"epoch": 0.4692632566870014,
"grad_norm": 3.511997938156128,
"learning_rate": 4.686629526462396e-05,
"loss": 1.4348,
"step": 250
},
{
"epoch": 0.48803378695448146,
"grad_norm": 3.343367576599121,
"learning_rate": 4.6518105849582176e-05,
"loss": 1.3879,
"step": 260
},
{
"epoch": 0.5068043172219615,
"grad_norm": 3.2004270553588867,
"learning_rate": 4.6169916434540394e-05,
"loss": 1.3787,
"step": 270
},
{
"epoch": 0.5255748474894416,
"grad_norm": 3.113529682159424,
"learning_rate": 4.582172701949861e-05,
"loss": 1.3503,
"step": 280
},
{
"epoch": 0.5443453777569216,
"grad_norm": 3.2955970764160156,
"learning_rate": 4.547353760445683e-05,
"loss": 1.3139,
"step": 290
},
{
"epoch": 0.5631159080244017,
"grad_norm": 3.1911182403564453,
"learning_rate": 4.5125348189415044e-05,
"loss": 1.2995,
"step": 300
},
{
"epoch": 0.5818864382918817,
"grad_norm": 3.416416645050049,
"learning_rate": 4.477715877437326e-05,
"loss": 1.2014,
"step": 310
},
{
"epoch": 0.6006569685593618,
"grad_norm": 4.6215410232543945,
"learning_rate": 4.442896935933148e-05,
"loss": 1.1872,
"step": 320
},
{
"epoch": 0.6194274988268419,
"grad_norm": 3.202340841293335,
"learning_rate": 4.40807799442897e-05,
"loss": 1.1448,
"step": 330
},
{
"epoch": 0.6381980290943219,
"grad_norm": 3.1017255783081055,
"learning_rate": 4.373259052924791e-05,
"loss": 1.2542,
"step": 340
},
{
"epoch": 0.656968559361802,
"grad_norm": 3.4146809577941895,
"learning_rate": 4.338440111420613e-05,
"loss": 1.143,
"step": 350
},
{
"epoch": 0.675739089629282,
"grad_norm": 3.4860126972198486,
"learning_rate": 4.303621169916435e-05,
"loss": 1.1936,
"step": 360
},
{
"epoch": 0.6945096198967621,
"grad_norm": 3.000502109527588,
"learning_rate": 4.268802228412256e-05,
"loss": 1.0896,
"step": 370
},
{
"epoch": 0.7132801501642422,
"grad_norm": 3.3682737350463867,
"learning_rate": 4.233983286908078e-05,
"loss": 0.9863,
"step": 380
},
{
"epoch": 0.7320506804317222,
"grad_norm": 2.903545379638672,
"learning_rate": 4.1991643454039e-05,
"loss": 1.0206,
"step": 390
},
{
"epoch": 0.7508212106992023,
"grad_norm": 3.5237250328063965,
"learning_rate": 4.164345403899722e-05,
"loss": 1.0655,
"step": 400
},
{
"epoch": 0.7695917409666823,
"grad_norm": 3.5761749744415283,
"learning_rate": 4.129526462395543e-05,
"loss": 1.0016,
"step": 410
},
{
"epoch": 0.7883622712341624,
"grad_norm": 3.3111650943756104,
"learning_rate": 4.094707520891365e-05,
"loss": 1.0225,
"step": 420
},
{
"epoch": 0.8071328015016425,
"grad_norm": 2.9664759635925293,
"learning_rate": 4.0598885793871866e-05,
"loss": 1.0624,
"step": 430
},
{
"epoch": 0.8259033317691225,
"grad_norm": 3.750908136367798,
"learning_rate": 4.0250696378830085e-05,
"loss": 1.0223,
"step": 440
},
{
"epoch": 0.8446738620366026,
"grad_norm": 3.176248788833618,
"learning_rate": 3.9902506963788303e-05,
"loss": 0.9834,
"step": 450
},
{
"epoch": 0.8634443923040825,
"grad_norm": 3.428868293762207,
"learning_rate": 3.955431754874652e-05,
"loss": 1.0338,
"step": 460
},
{
"epoch": 0.8822149225715626,
"grad_norm": 3.6257553100585938,
"learning_rate": 3.920612813370474e-05,
"loss": 1.0156,
"step": 470
},
{
"epoch": 0.9009854528390427,
"grad_norm": 3.195758104324341,
"learning_rate": 3.885793871866296e-05,
"loss": 1.0171,
"step": 480
},
{
"epoch": 0.9197559831065227,
"grad_norm": 2.6419994831085205,
"learning_rate": 3.850974930362117e-05,
"loss": 0.9735,
"step": 490
},
{
"epoch": 0.9385265133740028,
"grad_norm": 3.462597608566284,
"learning_rate": 3.816155988857939e-05,
"loss": 1.0049,
"step": 500
},
{
"epoch": 0.9572970436414828,
"grad_norm": 2.8139870166778564,
"learning_rate": 3.781337047353761e-05,
"loss": 0.9696,
"step": 510
},
{
"epoch": 0.9760675739089629,
"grad_norm": 3.027811288833618,
"learning_rate": 3.746518105849583e-05,
"loss": 0.9242,
"step": 520
},
{
"epoch": 0.994838104176443,
"grad_norm": 3.6760294437408447,
"learning_rate": 3.711699164345404e-05,
"loss": 0.912,
"step": 530
},
{
"epoch": 0.998592210229939,
"eval_accuracy": 0.7968316831683169,
"eval_loss": 0.8397366404533386,
"eval_runtime": 120.4032,
"eval_samples_per_second": 62.914,
"eval_steps_per_second": 1.968,
"step": 532
},
{
"epoch": 1.013608634443923,
"grad_norm": 2.9862356185913086,
"learning_rate": 3.676880222841226e-05,
"loss": 0.8398,
"step": 540
},
{
"epoch": 1.0323791647114031,
"grad_norm": 3.0735647678375244,
"learning_rate": 3.642061281337048e-05,
"loss": 0.8379,
"step": 550
},
{
"epoch": 1.0511496949788832,
"grad_norm": 3.5392494201660156,
"learning_rate": 3.607242339832869e-05,
"loss": 0.8264,
"step": 560
},
{
"epoch": 1.069920225246363,
"grad_norm": 3.511627435684204,
"learning_rate": 3.572423398328691e-05,
"loss": 0.8204,
"step": 570
},
{
"epoch": 1.0886907555138432,
"grad_norm": 3.393699884414673,
"learning_rate": 3.5376044568245126e-05,
"loss": 0.8963,
"step": 580
},
{
"epoch": 1.1074612857813233,
"grad_norm": 4.332097053527832,
"learning_rate": 3.5027855153203345e-05,
"loss": 0.8623,
"step": 590
},
{
"epoch": 1.1262318160488034,
"grad_norm": 3.1262927055358887,
"learning_rate": 3.4679665738161556e-05,
"loss": 0.8025,
"step": 600
},
{
"epoch": 1.1450023463162835,
"grad_norm": 3.1130638122558594,
"learning_rate": 3.4331476323119775e-05,
"loss": 0.8388,
"step": 610
},
{
"epoch": 1.1637728765837636,
"grad_norm": 3.509665012359619,
"learning_rate": 3.3983286908077994e-05,
"loss": 0.8306,
"step": 620
},
{
"epoch": 1.1825434068512435,
"grad_norm": 3.595564842224121,
"learning_rate": 3.363509749303621e-05,
"loss": 0.8241,
"step": 630
},
{
"epoch": 1.2013139371187236,
"grad_norm": 2.9736037254333496,
"learning_rate": 3.328690807799443e-05,
"loss": 0.8333,
"step": 640
},
{
"epoch": 1.2200844673862037,
"grad_norm": 3.5477538108825684,
"learning_rate": 3.293871866295265e-05,
"loss": 0.84,
"step": 650
},
{
"epoch": 1.2388549976536838,
"grad_norm": 3.617574453353882,
"learning_rate": 3.259052924791087e-05,
"loss": 0.7652,
"step": 660
},
{
"epoch": 1.2576255279211637,
"grad_norm": 3.621431589126587,
"learning_rate": 3.224233983286909e-05,
"loss": 0.7634,
"step": 670
},
{
"epoch": 1.2763960581886438,
"grad_norm": 3.5540874004364014,
"learning_rate": 3.18941504178273e-05,
"loss": 0.7951,
"step": 680
},
{
"epoch": 1.2951665884561239,
"grad_norm": 3.1876299381256104,
"learning_rate": 3.154596100278552e-05,
"loss": 0.787,
"step": 690
},
{
"epoch": 1.313937118723604,
"grad_norm": 3.8441293239593506,
"learning_rate": 3.1197771587743737e-05,
"loss": 0.7799,
"step": 700
},
{
"epoch": 1.332707648991084,
"grad_norm": 3.2278223037719727,
"learning_rate": 3.0849582172701955e-05,
"loss": 0.845,
"step": 710
},
{
"epoch": 1.3514781792585642,
"grad_norm": 3.1881773471832275,
"learning_rate": 3.050139275766017e-05,
"loss": 0.7415,
"step": 720
},
{
"epoch": 1.370248709526044,
"grad_norm": 3.34291672706604,
"learning_rate": 3.0153203342618386e-05,
"loss": 0.7424,
"step": 730
},
{
"epoch": 1.3890192397935242,
"grad_norm": 5.416168689727783,
"learning_rate": 2.98050139275766e-05,
"loss": 0.8025,
"step": 740
},
{
"epoch": 1.4077897700610043,
"grad_norm": 3.111943244934082,
"learning_rate": 2.945682451253482e-05,
"loss": 0.8537,
"step": 750
},
{
"epoch": 1.4265603003284844,
"grad_norm": 3.118394374847412,
"learning_rate": 2.9108635097493035e-05,
"loss": 0.7796,
"step": 760
},
{
"epoch": 1.4453308305959642,
"grad_norm": 3.8577425479888916,
"learning_rate": 2.8760445682451254e-05,
"loss": 0.7926,
"step": 770
},
{
"epoch": 1.4641013608634443,
"grad_norm": 4.177425384521484,
"learning_rate": 2.841225626740947e-05,
"loss": 0.7863,
"step": 780
},
{
"epoch": 1.4828718911309244,
"grad_norm": 3.465301275253296,
"learning_rate": 2.8064066852367688e-05,
"loss": 0.7687,
"step": 790
},
{
"epoch": 1.5016424213984045,
"grad_norm": 3.2810630798339844,
"learning_rate": 2.7715877437325903e-05,
"loss": 0.8167,
"step": 800
},
{
"epoch": 1.5204129516658846,
"grad_norm": 3.05501127243042,
"learning_rate": 2.736768802228412e-05,
"loss": 0.7299,
"step": 810
},
{
"epoch": 1.5391834819333647,
"grad_norm": 2.9829261302948,
"learning_rate": 2.7019498607242337e-05,
"loss": 0.7677,
"step": 820
},
{
"epoch": 1.5579540122008448,
"grad_norm": 3.561396360397339,
"learning_rate": 2.6671309192200562e-05,
"loss": 0.7813,
"step": 830
},
{
"epoch": 1.5767245424683247,
"grad_norm": 2.8982436656951904,
"learning_rate": 2.6323119777158778e-05,
"loss": 0.731,
"step": 840
},
{
"epoch": 1.5954950727358048,
"grad_norm": 3.406423330307007,
"learning_rate": 2.5974930362116996e-05,
"loss": 0.73,
"step": 850
},
{
"epoch": 1.6142656030032847,
"grad_norm": 3.0049679279327393,
"learning_rate": 2.562674094707521e-05,
"loss": 0.7826,
"step": 860
},
{
"epoch": 1.6330361332707648,
"grad_norm": 3.500458002090454,
"learning_rate": 2.527855153203343e-05,
"loss": 0.7499,
"step": 870
},
{
"epoch": 1.651806663538245,
"grad_norm": 3.0891637802124023,
"learning_rate": 2.4930362116991646e-05,
"loss": 0.7587,
"step": 880
},
{
"epoch": 1.670577193805725,
"grad_norm": 3.149742841720581,
"learning_rate": 2.4582172701949864e-05,
"loss": 0.7374,
"step": 890
},
{
"epoch": 1.689347724073205,
"grad_norm": 3.1518661975860596,
"learning_rate": 2.423398328690808e-05,
"loss": 0.7893,
"step": 900
},
{
"epoch": 1.7081182543406852,
"grad_norm": 3.08024525642395,
"learning_rate": 2.3885793871866298e-05,
"loss": 0.7853,
"step": 910
},
{
"epoch": 1.7268887846081653,
"grad_norm": 3.158390522003174,
"learning_rate": 2.3537604456824514e-05,
"loss": 0.7694,
"step": 920
},
{
"epoch": 1.7456593148756452,
"grad_norm": 3.0718069076538086,
"learning_rate": 2.318941504178273e-05,
"loss": 0.7843,
"step": 930
},
{
"epoch": 1.7644298451431253,
"grad_norm": 3.4767684936523438,
"learning_rate": 2.2841225626740948e-05,
"loss": 0.7483,
"step": 940
},
{
"epoch": 1.7832003754106054,
"grad_norm": 3.350541353225708,
"learning_rate": 2.2493036211699163e-05,
"loss": 0.7457,
"step": 950
},
{
"epoch": 1.8019709056780853,
"grad_norm": 3.4785940647125244,
"learning_rate": 2.214484679665738e-05,
"loss": 0.7586,
"step": 960
},
{
"epoch": 1.8207414359455654,
"grad_norm": 3.245809316635132,
"learning_rate": 2.17966573816156e-05,
"loss": 0.7035,
"step": 970
},
{
"epoch": 1.8395119662130455,
"grad_norm": 3.292048692703247,
"learning_rate": 2.144846796657382e-05,
"loss": 0.7366,
"step": 980
},
{
"epoch": 1.8582824964805256,
"grad_norm": 4.539200305938721,
"learning_rate": 2.1100278551532034e-05,
"loss": 0.7377,
"step": 990
},
{
"epoch": 1.8770530267480057,
"grad_norm": 2.6051247119903564,
"learning_rate": 2.0752089136490253e-05,
"loss": 0.8442,
"step": 1000
},
{
"epoch": 1.8958235570154858,
"grad_norm": 3.7407584190368652,
"learning_rate": 2.0403899721448468e-05,
"loss": 0.732,
"step": 1010
},
{
"epoch": 1.9145940872829659,
"grad_norm": 3.855624198913574,
"learning_rate": 2.0055710306406687e-05,
"loss": 0.8147,
"step": 1020
},
{
"epoch": 1.9333646175504458,
"grad_norm": 3.7936253547668457,
"learning_rate": 1.9707520891364902e-05,
"loss": 0.6852,
"step": 1030
},
{
"epoch": 1.9521351478179259,
"grad_norm": 3.4030821323394775,
"learning_rate": 1.935933147632312e-05,
"loss": 0.7311,
"step": 1040
},
{
"epoch": 1.970905678085406,
"grad_norm": 3.5526273250579834,
"learning_rate": 1.9011142061281336e-05,
"loss": 0.7846,
"step": 1050
},
{
"epoch": 1.9896762083528858,
"grad_norm": 3.1862409114837646,
"learning_rate": 1.8662952646239558e-05,
"loss": 0.7233,
"step": 1060
},
{
"epoch": 1.999061473486626,
"eval_accuracy": 0.8294389438943894,
"eval_loss": 0.6780887842178345,
"eval_runtime": 125.2435,
"eval_samples_per_second": 60.482,
"eval_steps_per_second": 1.892,
"step": 1065
},
{
"epoch": 2.008446738620366,
"grad_norm": 3.521763563156128,
"learning_rate": 1.8314763231197773e-05,
"loss": 0.6907,
"step": 1070
},
{
"epoch": 2.027217268887846,
"grad_norm": 3.0328750610351562,
"learning_rate": 1.7966573816155992e-05,
"loss": 0.6829,
"step": 1080
},
{
"epoch": 2.045987799155326,
"grad_norm": 4.274998188018799,
"learning_rate": 1.7618384401114207e-05,
"loss": 0.635,
"step": 1090
},
{
"epoch": 2.0647583294228062,
"grad_norm": 3.0744423866271973,
"learning_rate": 1.7270194986072426e-05,
"loss": 0.7163,
"step": 1100
},
{
"epoch": 2.0835288596902863,
"grad_norm": 3.0927815437316895,
"learning_rate": 1.692200557103064e-05,
"loss": 0.6817,
"step": 1110
},
{
"epoch": 2.1022993899577664,
"grad_norm": 2.5418238639831543,
"learning_rate": 1.6573816155988857e-05,
"loss": 0.6235,
"step": 1120
},
{
"epoch": 2.1210699202252465,
"grad_norm": 3.1327621936798096,
"learning_rate": 1.6225626740947075e-05,
"loss": 0.6351,
"step": 1130
},
{
"epoch": 2.139840450492726,
"grad_norm": 4.186623573303223,
"learning_rate": 1.587743732590529e-05,
"loss": 0.6383,
"step": 1140
},
{
"epoch": 2.1586109807602063,
"grad_norm": 3.007977247238159,
"learning_rate": 1.552924791086351e-05,
"loss": 0.6994,
"step": 1150
},
{
"epoch": 2.1773815110276864,
"grad_norm": 3.232109308242798,
"learning_rate": 1.518105849582173e-05,
"loss": 0.6615,
"step": 1160
},
{
"epoch": 2.1961520412951665,
"grad_norm": 2.8354580402374268,
"learning_rate": 1.4832869080779947e-05,
"loss": 0.6686,
"step": 1170
},
{
"epoch": 2.2149225715626466,
"grad_norm": 3.6194567680358887,
"learning_rate": 1.4484679665738164e-05,
"loss": 0.6649,
"step": 1180
},
{
"epoch": 2.2336931018301267,
"grad_norm": 4.279024600982666,
"learning_rate": 1.413649025069638e-05,
"loss": 0.6529,
"step": 1190
},
{
"epoch": 2.252463632097607,
"grad_norm": 3.035931348800659,
"learning_rate": 1.3788300835654596e-05,
"loss": 0.6796,
"step": 1200
},
{
"epoch": 2.271234162365087,
"grad_norm": 3.2257440090179443,
"learning_rate": 1.3440111420612813e-05,
"loss": 0.6501,
"step": 1210
},
{
"epoch": 2.290004692632567,
"grad_norm": 3.176237106323242,
"learning_rate": 1.309192200557103e-05,
"loss": 0.7252,
"step": 1220
},
{
"epoch": 2.308775222900047,
"grad_norm": 3.575956344604492,
"learning_rate": 1.2743732590529247e-05,
"loss": 0.6798,
"step": 1230
},
{
"epoch": 2.327545753167527,
"grad_norm": 3.1033012866973877,
"learning_rate": 1.2395543175487466e-05,
"loss": 0.6291,
"step": 1240
},
{
"epoch": 2.346316283435007,
"grad_norm": 3.797513961791992,
"learning_rate": 1.2047353760445683e-05,
"loss": 0.6908,
"step": 1250
},
{
"epoch": 2.365086813702487,
"grad_norm": 3.399435043334961,
"learning_rate": 1.16991643454039e-05,
"loss": 0.5915,
"step": 1260
},
{
"epoch": 2.383857343969967,
"grad_norm": 2.9869837760925293,
"learning_rate": 1.1350974930362116e-05,
"loss": 0.6665,
"step": 1270
},
{
"epoch": 2.402627874237447,
"grad_norm": 3.171600580215454,
"learning_rate": 1.1002785515320335e-05,
"loss": 0.6202,
"step": 1280
},
{
"epoch": 2.4213984045049273,
"grad_norm": 2.0792176723480225,
"learning_rate": 1.0654596100278552e-05,
"loss": 0.5773,
"step": 1290
},
{
"epoch": 2.4401689347724074,
"grad_norm": 3.339883804321289,
"learning_rate": 1.0306406685236769e-05,
"loss": 0.6435,
"step": 1300
},
{
"epoch": 2.4589394650398875,
"grad_norm": 3.2008817195892334,
"learning_rate": 9.958217270194986e-06,
"loss": 0.6448,
"step": 1310
},
{
"epoch": 2.4777099953073676,
"grad_norm": 2.828279733657837,
"learning_rate": 9.610027855153205e-06,
"loss": 0.6121,
"step": 1320
},
{
"epoch": 2.4964805255748477,
"grad_norm": 2.920414924621582,
"learning_rate": 9.261838440111422e-06,
"loss": 0.6569,
"step": 1330
},
{
"epoch": 2.5152510558423273,
"grad_norm": 3.4083826541900635,
"learning_rate": 8.913649025069639e-06,
"loss": 0.6819,
"step": 1340
},
{
"epoch": 2.534021586109808,
"grad_norm": 2.8921279907226562,
"learning_rate": 8.565459610027856e-06,
"loss": 0.6257,
"step": 1350
},
{
"epoch": 2.5527921163772875,
"grad_norm": 3.33734130859375,
"learning_rate": 8.217270194986073e-06,
"loss": 0.6439,
"step": 1360
},
{
"epoch": 2.5715626466447676,
"grad_norm": 4.184520244598389,
"learning_rate": 7.869080779944291e-06,
"loss": 0.6742,
"step": 1370
},
{
"epoch": 2.5903331769122477,
"grad_norm": 3.5494306087493896,
"learning_rate": 7.5208913649025075e-06,
"loss": 0.6485,
"step": 1380
},
{
"epoch": 2.609103707179728,
"grad_norm": 2.791755437850952,
"learning_rate": 7.1727019498607245e-06,
"loss": 0.6061,
"step": 1390
},
{
"epoch": 2.627874237447208,
"grad_norm": 3.616508960723877,
"learning_rate": 6.8245125348189415e-06,
"loss": 0.7124,
"step": 1400
},
{
"epoch": 2.646644767714688,
"grad_norm": 3.5052719116210938,
"learning_rate": 6.4763231197771585e-06,
"loss": 0.6545,
"step": 1410
},
{
"epoch": 2.665415297982168,
"grad_norm": 3.463571786880493,
"learning_rate": 6.128133704735376e-06,
"loss": 0.5905,
"step": 1420
},
{
"epoch": 2.684185828249648,
"grad_norm": 3.2912559509277344,
"learning_rate": 5.779944289693594e-06,
"loss": 0.5468,
"step": 1430
},
{
"epoch": 2.7029563585171283,
"grad_norm": 3.0410854816436768,
"learning_rate": 5.43175487465181e-06,
"loss": 0.6286,
"step": 1440
},
{
"epoch": 2.721726888784608,
"grad_norm": 3.565953016281128,
"learning_rate": 5.083565459610028e-06,
"loss": 0.6567,
"step": 1450
},
{
"epoch": 2.740497419052088,
"grad_norm": 3.0948688983917236,
"learning_rate": 4.735376044568245e-06,
"loss": 0.644,
"step": 1460
},
{
"epoch": 2.759267949319568,
"grad_norm": 3.734225034713745,
"learning_rate": 4.387186629526462e-06,
"loss": 0.65,
"step": 1470
},
{
"epoch": 2.7780384795870483,
"grad_norm": 3.245823860168457,
"learning_rate": 4.03899721448468e-06,
"loss": 0.613,
"step": 1480
},
{
"epoch": 2.7968090098545284,
"grad_norm": 2.6476266384124756,
"learning_rate": 3.690807799442897e-06,
"loss": 0.6562,
"step": 1490
},
{
"epoch": 2.8155795401220085,
"grad_norm": 3.1951568126678467,
"learning_rate": 3.3426183844011147e-06,
"loss": 0.5897,
"step": 1500
},
{
"epoch": 2.8343500703894886,
"grad_norm": 3.754561424255371,
"learning_rate": 2.9944289693593313e-06,
"loss": 0.5686,
"step": 1510
},
{
"epoch": 2.8531206006569687,
"grad_norm": 2.6758432388305664,
"learning_rate": 2.6462395543175487e-06,
"loss": 0.6791,
"step": 1520
},
{
"epoch": 2.871891130924449,
"grad_norm": 2.6981005668640137,
"learning_rate": 2.298050139275766e-06,
"loss": 0.5544,
"step": 1530
},
{
"epoch": 2.8906616611919285,
"grad_norm": 3.503272294998169,
"learning_rate": 1.9498607242339835e-06,
"loss": 0.6921,
"step": 1540
},
{
"epoch": 2.9094321914594086,
"grad_norm": 3.2283263206481934,
"learning_rate": 1.6016713091922007e-06,
"loss": 0.6307,
"step": 1550
},
{
"epoch": 2.9282027217268887,
"grad_norm": 3.2601311206817627,
"learning_rate": 1.253481894150418e-06,
"loss": 0.653,
"step": 1560
},
{
"epoch": 2.9469732519943688,
"grad_norm": 3.5451338291168213,
"learning_rate": 9.052924791086352e-07,
"loss": 0.5953,
"step": 1570
},
{
"epoch": 2.965743782261849,
"grad_norm": 3.605889081954956,
"learning_rate": 5.571030640668524e-07,
"loss": 0.6338,
"step": 1580
},
{
"epoch": 2.984514312529329,
"grad_norm": 4.055668830871582,
"learning_rate": 2.0891364902506967e-07,
"loss": 0.6047,
"step": 1590
},
{
"epoch": 2.995776630689817,
"eval_accuracy": 0.834983498349835,
"eval_loss": 0.6400949358940125,
"eval_runtime": 126.916,
"eval_samples_per_second": 59.685,
"eval_steps_per_second": 1.867,
"step": 1596
},
{
"epoch": 2.995776630689817,
"step": 1596,
"total_flos": 1.584209316447959e+19,
"train_loss": 1.1699181137825911,
"train_runtime": 8274.5103,
"train_samples_per_second": 24.717,
"train_steps_per_second": 0.193
}
],
"logging_steps": 10,
"max_steps": 1596,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.584209316447959e+19,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}