openllama-3b-cooking / training_logs.json
joshuaclymer's picture
Upload folder using huggingface_hub
5fcae90
[
{
"loss": 0.6916,
"learning_rate": 7.2e-05,
"epoch": 0.02,
"step": 1
},
{
"loss": 0.6981,
"learning_rate": 7.2e-05,
"epoch": 0.04,
"step": 2
},
{
"loss": 0.6824,
"learning_rate": 7.2e-05,
"epoch": 0.05,
"step": 3
},
{
"loss": 0.6878,
"learning_rate": 7.2e-05,
"epoch": 0.07,
"step": 4
},
{
"loss": 0.6848,
"learning_rate": 7.2e-05,
"epoch": 0.09,
"step": 5
},
{
"loss": 0.6842,
"learning_rate": 7.2e-05,
"epoch": 0.11,
"step": 6
},
{
"loss": 0.6826,
"learning_rate": 7.2e-05,
"epoch": 0.12,
"step": 7
},
{
"loss": 0.6571,
"learning_rate": 7.2e-05,
"epoch": 0.14,
"step": 8
},
{
"loss": 0.6723,
"learning_rate": 7.2e-05,
"epoch": 0.16,
"step": 9
},
{
"loss": 0.6706,
"learning_rate": 7.2e-05,
"epoch": 0.18,
"step": 10
},
{
"loss": 0.669,
"learning_rate": 7.2e-05,
"epoch": 0.19,
"step": 11
},
{
"loss": 0.6648,
"learning_rate": 7.2e-05,
"epoch": 0.21,
"step": 12
},
{
"loss": 0.6491,
"learning_rate": 7.2e-05,
"epoch": 0.23,
"step": 13
},
{
"loss": 0.6483,
"learning_rate": 7.2e-05,
"epoch": 0.25,
"step": 14
},
{
"loss": 0.6688,
"learning_rate": 7.2e-05,
"epoch": 0.26,
"step": 15
},
{
"loss": 0.6457,
"learning_rate": 7.2e-05,
"epoch": 0.28,
"step": 16
},
{
"loss": 0.6418,
"learning_rate": 7.2e-05,
"epoch": 0.3,
"step": 17
},
{
"loss": 0.642,
"learning_rate": 7.2e-05,
"epoch": 0.32,
"step": 18
},
{
"loss": 0.6052,
"learning_rate": 7.2e-05,
"epoch": 0.33,
"step": 19
},
{
"loss": 0.6353,
"learning_rate": 7.2e-05,
"epoch": 0.35,
"step": 20
},
{
"loss": 0.6342,
"learning_rate": 7.2e-05,
"epoch": 0.37,
"step": 21
},
{
"loss": 0.5882,
"learning_rate": 7.2e-05,
"epoch": 0.39,
"step": 22
},
{
"loss": 0.6016,
"learning_rate": 7.2e-05,
"epoch": 0.4,
"step": 23
},
{
"loss": 0.5912,
"learning_rate": 7.2e-05,
"epoch": 0.42,
"step": 24
},
{
"loss": 0.5357,
"learning_rate": 7.2e-05,
"epoch": 0.44,
"step": 25
},
{
"eval_cooking_loss": 0.5587261915206909,
"eval_cooking_score": -0.18656283617019653,
"eval_cooking_brier_score": 0.18656283617019653,
"eval_cooking_average_probability": 0.5775389671325684,
"eval_cooking_accuracy": 0.86,
"eval_cooking_probabilities": [
0.6535859107971191,
0.7789987921714783,
0.7278355956077576,
0.5034284591674805,
0.5114082098007202,
0.5213085412979126,
0.4919251799583435,
0.5028612613677979,
0.5094664692878723,
0.5756015777587891,
0.649503231048584,
0.596377432346344,
0.5078422427177429,
0.5245868563652039,
0.49776366353034973,
0.6764980554580688,
0.6633638739585876,
0.7384623885154724,
0.7947311401367188,
0.782829761505127,
0.8216938972473145,
0.7805530428886414,
0.763758659362793,
0.7716487050056458,
0.5573330521583557,
0.4893724322319031,
0.618384838104248,
0.5045730471611023,
0.493682861328125,
0.4950566589832306,
0.5033178329467773,
0.5005538463592529,
0.5081912279129028,
0.619926929473877,
0.693365216255188,
0.5872482061386108,
0.5683161616325378,
0.5579834580421448,
0.5524486303329468,
0.5865271687507629,
0.596405029296875,
0.5350281000137329,
0.6161436438560486,
0.6798644661903381,
0.6344469785690308,
0.5292232632637024,
0.5086079239845276,
0.5822234749794006,
0.5117786526679993,
0.519439160823822,
0.507979154586792,
0.4805572032928467,
0.5027401447296143,
0.496711790561676,
0.5047993659973145,
0.50522780418396,
0.5031599998474121,
0.5163615345954895,
0.5120277404785156,
0.5277899503707886,
0.7266655564308167,
0.7472778558731079,
0.6976069808006287,
0.5717738270759583,
0.6468728184700012,
0.6206830143928528,
0.49703091382980347,
0.5049151182174683,
0.48914843797683716,
0.5019007325172424,
0.5251224637031555,
0.5308592319488525,
0.5176806449890137,
0.5524135231971741,
0.5026034116744995,
0.5673679113388062,
0.4874042868614197,
0.5103644728660583,
0.49143484234809875,
0.4760080873966217,
0.5319715738296509,
0.6992161273956299,
0.5555852055549622,
0.5927191376686096,
0.4964844882488251,
0.5331833362579346,
0.5580875873565674,
0.5332431197166443,
0.5607354044914246,
0.5862356424331665,
0.5830809473991394,
0.6106278300285339,
0.6358562707901001,
0.5881476402282715,
0.5585660934448242,
0.7618038654327393,
0.5552946329116821,
0.5067716836929321,
0.491814523935318,
0.6965087652206421
],
"eval_cooking_runtime": 16.9456,
"eval_cooking_samples_per_second": 5.901,
"eval_cooking_steps_per_second": 0.118,
"epoch": 0.44,
"step": 25
},
{
"loss": 0.6283,
"learning_rate": 7.2e-05,
"epoch": 0.46,
"step": 26
},
{
"loss": 0.5924,
"learning_rate": 7.2e-05,
"epoch": 0.47,
"step": 27
},
{
"loss": 0.5645,
"learning_rate": 7.2e-05,
"epoch": 0.49,
"step": 28
},
{
"loss": 0.5242,
"learning_rate": 7.2e-05,
"epoch": 0.51,
"step": 29
},
{
"loss": 0.5376,
"learning_rate": 7.2e-05,
"epoch": 0.53,
"step": 30
},
{
"loss": 0.535,
"learning_rate": 7.2e-05,
"epoch": 0.54,
"step": 31
},
{
"loss": 0.5309,
"learning_rate": 7.2e-05,
"epoch": 0.56,
"step": 32
},
{
"loss": 0.531,
"learning_rate": 7.2e-05,
"epoch": 0.58,
"step": 33
},
{
"loss": 0.4605,
"learning_rate": 7.2e-05,
"epoch": 0.6,
"step": 34
},
{
"loss": 0.4715,
"learning_rate": 7.2e-05,
"epoch": 0.61,
"step": 35
},
{
"loss": 0.4234,
"learning_rate": 7.2e-05,
"epoch": 0.63,
"step": 36
},
{
"loss": 0.4365,
"learning_rate": 7.2e-05,
"epoch": 0.65,
"step": 37
},
{
"loss": 0.4103,
"learning_rate": 7.2e-05,
"epoch": 0.67,
"step": 38
},
{
"loss": 0.3823,
"learning_rate": 7.2e-05,
"epoch": 0.68,
"step": 39
},
{
"loss": 0.4441,
"learning_rate": 7.2e-05,
"epoch": 0.7,
"step": 40
},
{
"loss": 0.3933,
"learning_rate": 7.2e-05,
"epoch": 0.72,
"step": 41
},
{
"loss": 0.2843,
"learning_rate": 7.2e-05,
"epoch": 0.74,
"step": 42
},
{
"loss": 0.369,
"learning_rate": 7.2e-05,
"epoch": 0.75,
"step": 43
},
{
"loss": 0.2645,
"learning_rate": 7.2e-05,
"epoch": 0.77,
"step": 44
},
{
"loss": 0.2849,
"learning_rate": 7.2e-05,
"epoch": 0.79,
"step": 45
},
{
"loss": 0.4064,
"learning_rate": 7.2e-05,
"epoch": 0.81,
"step": 46
},
{
"loss": 0.2997,
"learning_rate": 7.2e-05,
"epoch": 0.82,
"step": 47
},
{
"loss": 0.2671,
"learning_rate": 7.2e-05,
"epoch": 0.84,
"step": 48
},
{
"loss": 0.3314,
"learning_rate": 7.2e-05,
"epoch": 0.86,
"step": 49
},
{
"loss": 0.4259,
"learning_rate": 7.2e-05,
"epoch": 0.88,
"step": 50
},
{
"eval_cooking_loss": 0.24271316826343536,
"eval_cooking_score": -0.07499240338802338,
"eval_cooking_brier_score": 0.07499240338802338,
"eval_cooking_average_probability": 0.8277876973152161,
"eval_cooking_accuracy": 0.9,
"eval_cooking_probabilities": [
0.999724805355072,
0.9999879598617554,
0.9999728202819824,
0.7033181190490723,
0.7430822253227234,
0.881674587726593,
0.41176167130470276,
0.708188533782959,
0.6328032612800598,
0.9212954640388489,
0.9990290403366089,
0.9299277067184448,
0.7640402317047119,
0.3545408844947815,
0.5027904510498047,
0.9999113082885742,
0.9996991157531738,
0.9999837875366211,
0.9999978542327881,
0.9999983310699463,
0.9999994039535522,
0.9645881056785583,
0.9580472707748413,
0.8383041024208069,
0.9042266011238098,
0.34083274006843567,
0.9612021446228027,
0.6464914083480835,
0.5505920648574829,
0.5640060901641846,
0.4715419113636017,
0.5866241455078125,
0.5923582315444946,
0.9999804496765137,
0.9999958276748657,
0.9999480247497559,
0.9675708413124084,
0.9627715349197388,
0.9368075728416443,
0.9998013377189636,
0.9998076558113098,
0.9965103268623352,
0.9999927282333374,
0.9999969005584717,
0.9999947547912598,
0.6305108070373535,
0.9222402572631836,
0.9166140556335449,
0.9501265287399292,
0.8001410961151123,
0.5643638968467712,
0.28959962725639343,
0.46665191650390625,
0.4726523160934448,
0.5652157664299011,
0.6580631136894226,
0.5187925696372986,
0.7297425270080566,
0.6905303001403809,
0.7946078181266785,
0.9999961853027344,
0.9999949932098389,
0.9999889135360718,
0.9987756609916687,
0.9995506405830383,
0.9991851449012756,
0.48971259593963623,
0.5437894463539124,
0.5442638993263245,
0.6886961460113525,
0.8295254707336426,
0.7418484091758728,
0.9925927519798279,
0.9959911704063416,
0.5952439904212952,
0.9897077083587646,
0.621001660823822,
0.6627683043479919,
0.42167624831199646,
0.25209811329841614,
0.833419680595398,
0.999998927116394,
0.9988007545471191,
0.9999165534973145,
0.9955934882164001,
0.9992002844810486,
0.9901018142700195,
0.9907991290092468,
0.9996410608291626,
0.9999163150787354,
0.9285746812820435,
0.9999537467956543,
0.9999878406524658,
0.9995831847190857,
0.999691367149353,
0.9999963045120239,
0.9960076808929443,
0.9942654967308044,
0.9234359860420227,
0.9999021291732788
],
"eval_cooking_runtime": 16.9232,
"eval_cooking_samples_per_second": 5.909,
"eval_cooking_steps_per_second": 0.118,
"epoch": 0.88,
"step": 50
},
{
"loss": 0.179,
"learning_rate": 7.2e-05,
"epoch": 0.89,
"step": 51
},
{
"loss": 0.2263,
"learning_rate": 7.2e-05,
"epoch": 0.91,
"step": 52
},
{
"loss": 0.254,
"learning_rate": 7.2e-05,
"epoch": 0.93,
"step": 53
},
{
"loss": 0.2283,
"learning_rate": 7.2e-05,
"epoch": 0.95,
"step": 54
},
{
"loss": 0.1749,
"learning_rate": 7.2e-05,
"epoch": 0.96,
"step": 55
},
{
"loss": 0.2974,
"learning_rate": 7.2e-05,
"epoch": 0.98,
"step": 56
},
{
"loss": 0.2037,
"learning_rate": 7.2e-05,
"epoch": 1.0,
"step": 57
},
{
"loss": 0.2979,
"learning_rate": 7.2e-05,
"epoch": 1.02,
"step": 58
},
{
"loss": 0.1342,
"learning_rate": 7.2e-05,
"epoch": 1.04,
"step": 59
},
{
"loss": 0.1416,
"learning_rate": 7.2e-05,
"epoch": 1.05,
"step": 60
},
{
"loss": 0.1714,
"learning_rate": 7.2e-05,
"epoch": 1.07,
"step": 61
},
{
"loss": 0.1309,
"learning_rate": 7.2e-05,
"epoch": 1.09,
"step": 62
},
{
"loss": 0.21,
"learning_rate": 7.2e-05,
"epoch": 1.11,
"step": 63
},
{
"loss": 0.1542,
"learning_rate": 7.2e-05,
"epoch": 1.12,
"step": 64
},
{
"loss": 0.2992,
"learning_rate": 7.2e-05,
"epoch": 1.14,
"step": 65
},
{
"loss": 0.1631,
"learning_rate": 7.2e-05,
"epoch": 1.16,
"step": 66
},
{
"loss": 0.5016,
"learning_rate": 7.2e-05,
"epoch": 1.18,
"step": 67
},
{
"loss": 0.1565,
"learning_rate": 7.2e-05,
"epoch": 1.19,
"step": 68
},
{
"loss": 0.1252,
"learning_rate": 7.2e-05,
"epoch": 1.21,
"step": 69
},
{
"loss": 0.1232,
"learning_rate": 7.2e-05,
"epoch": 1.23,
"step": 70
},
{
"loss": 0.1189,
"learning_rate": 7.2e-05,
"epoch": 1.25,
"step": 71
},
{
"loss": 0.1427,
"learning_rate": 7.2e-05,
"epoch": 1.26,
"step": 72
},
{
"loss": 0.1295,
"learning_rate": 7.2e-05,
"epoch": 1.28,
"step": 73
},
{
"loss": 0.0967,
"learning_rate": 7.2e-05,
"epoch": 1.3,
"step": 74
},
{
"loss": 0.13,
"learning_rate": 7.2e-05,
"epoch": 1.32,
"step": 75
},
{
"eval_cooking_loss": 0.1628786027431488,
"eval_cooking_score": -0.05112582817673683,
"eval_cooking_brier_score": 0.05112582817673683,
"eval_cooking_average_probability": 0.8956797122955322,
"eval_cooking_accuracy": 0.93,
"eval_cooking_probabilities": [
0.9999997615814209,
1.0,
1.0,
0.9542316198348999,
0.9880340695381165,
0.9988256096839905,
0.5675406455993652,
0.9845830202102661,
0.9547784328460693,
0.9989789724349976,
0.9999997615814209,
0.9986110925674438,
0.9338040351867676,
0.17299044132232666,
0.45846590399742126,
0.999994158744812,
0.9999963045120239,
0.9999996423721313,
1.0,
1.0,
1.0,
0.9999418258666992,
0.99986732006073,
0.8973928093910217,
0.9987490177154541,
0.9780608415603638,
0.999396562576294,
0.9193954467773438,
0.7913320660591125,
0.723684549331665,
0.4277496635913849,
0.7048351168632507,
0.7073538303375244,
1.0,
1.0,
0.9999998807907104,
0.9997616410255432,
0.9998383522033691,
0.9980823993682861,
0.9999997615814209,
0.9999997615814209,
0.9999886751174927,
1.0,
1.0,
1.0,
0.7106478214263916,
0.9978567957878113,
0.9251576662063599,
0.9943885207176208,
0.9633152484893799,
0.7126079201698303,
0.15048664808273315,
0.8353597521781921,
0.5454015731811523,
0.8950506448745728,
0.7718052268028259,
0.5149663090705872,
0.9856672883033752,
0.998984158039093,
0.9991474151611328,
1.0,
1.0,
1.0,
0.9999971389770508,
0.9999994039535522,
0.9999972581863403,
0.7013386487960815,
0.2816448211669922,
0.728237509727478,
0.7397965788841248,
0.9191795587539673,
0.886256754398346,
0.9999814033508301,
0.9999879598617554,
0.8164882659912109,
0.999995231628418,
0.962520182132721,
0.9958972930908203,
0.4359956681728363,
0.15542198717594147,
0.7957375049591064,
1.0,
1.0,
1.0,
0.9998841285705566,
0.9999792575836182,
0.9998303651809692,
0.9999983310699463,
0.9999995231628418,
0.9999998807907104,
0.9967737793922424,
0.9999997615814209,
0.9999998807907104,
0.9999998807907104,
1.0,
1.0,
0.999854564666748,
0.9992210865020752,
0.9968494772911072,
1.0
],
"eval_cooking_runtime": 16.9537,
"eval_cooking_samples_per_second": 5.898,
"eval_cooking_steps_per_second": 0.118,
"epoch": 1.32,
"step": 75
},
{
"loss": 0.1269,
"learning_rate": 7.2e-05,
"epoch": 1.33,
"step": 76
},
{
"loss": 0.1392,
"learning_rate": 7.2e-05,
"epoch": 1.35,
"step": 77
},
{
"loss": 0.1445,
"learning_rate": 7.2e-05,
"epoch": 1.37,
"step": 78
},
{
"loss": 0.1587,
"learning_rate": 7.2e-05,
"epoch": 1.39,
"step": 79
},
{
"loss": 0.1955,
"learning_rate": 7.2e-05,
"epoch": 1.4,
"step": 80
},
{
"loss": 0.1407,
"learning_rate": 7.2e-05,
"epoch": 1.42,
"step": 81
},
{
"loss": 0.1618,
"learning_rate": 7.2e-05,
"epoch": 1.44,
"step": 82
},
{
"loss": 0.1103,
"learning_rate": 7.2e-05,
"epoch": 1.46,
"step": 83
},
{
"loss": 0.1269,
"learning_rate": 7.2e-05,
"epoch": 1.47,
"step": 84
},
{
"loss": 0.1417,
"learning_rate": 7.2e-05,
"epoch": 1.49,
"step": 85
},
{
"loss": 0.1295,
"learning_rate": 7.2e-05,
"epoch": 1.51,
"step": 86
},
{
"loss": 0.1235,
"learning_rate": 7.2e-05,
"epoch": 1.53,
"step": 87
},
{
"loss": 0.128,
"learning_rate": 7.2e-05,
"epoch": 1.54,
"step": 88
},
{
"loss": 0.3058,
"learning_rate": 7.2e-05,
"epoch": 1.56,
"step": 89
},
{
"loss": 0.1572,
"learning_rate": 7.2e-05,
"epoch": 1.58,
"step": 90
},
{
"loss": 0.1179,
"learning_rate": 7.2e-05,
"epoch": 1.6,
"step": 91
},
{
"loss": 0.1117,
"learning_rate": 7.2e-05,
"epoch": 1.61,
"step": 92
},
{
"loss": 0.1062,
"learning_rate": 7.2e-05,
"epoch": 1.63,
"step": 93
},
{
"loss": 0.0737,
"learning_rate": 7.2e-05,
"epoch": 1.65,
"step": 94
},
{
"loss": 0.1918,
"learning_rate": 7.2e-05,
"epoch": 1.67,
"step": 95
},
{
"loss": 0.1854,
"learning_rate": 7.2e-05,
"epoch": 1.68,
"step": 96
},
{
"loss": 0.0775,
"learning_rate": 7.2e-05,
"epoch": 1.7,
"step": 97
},
{
"loss": 0.0842,
"learning_rate": 7.2e-05,
"epoch": 1.72,
"step": 98
},
{
"loss": 0.0614,
"learning_rate": 7.2e-05,
"epoch": 1.74,
"step": 99
},
{
"loss": 0.0925,
"learning_rate": 7.2e-05,
"epoch": 1.75,
"step": 100
},
{
"eval_cooking_loss": 0.16701044142246246,
"eval_cooking_score": -0.049089040607213974,
"eval_cooking_brier_score": 0.049089040607213974,
"eval_cooking_average_probability": 0.9079131484031677,
"eval_cooking_accuracy": 0.93,
"eval_cooking_probabilities": [
1.0,
1.0,
1.0,
0.9960379600524902,
0.9952751398086548,
0.9999885559082031,
0.8473833799362183,
0.9993119239807129,
0.9969514608383179,
0.999823272228241,
1.0,
0.9998192191123962,
0.9292259812355042,
0.37933260202407837,
0.36354097723960876,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9999985694885254,
0.9999842643737793,
0.8276720643043518,
0.999998927116394,
0.9999539852142334,
0.9999990463256836,
0.9115281105041504,
0.7917703986167908,
0.7387007474899292,
0.37488386034965515,
0.8065743446350098,
0.6968543529510498,
1.0,
1.0,
1.0,
0.9999852180480957,
0.9999778270721436,
0.9997331500053406,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.631415605545044,
0.9998106360435486,
0.9700195789337158,
0.9995588660240173,
0.9897929430007935,
0.7991155385971069,
0.016083385795354843,
0.7816288471221924,
0.505143940448761,
0.9806777834892273,
0.926846444606781,
0.6193849444389343,
0.9996283054351807,
0.999963641166687,
0.9999926090240479,
1.0,
1.0,
1.0,
1.0,
1.0,
1.0,
0.8756850957870483,
0.20660391449928284,
0.8607563972473145,
0.7930099368095398,
0.9620106816291809,
0.9651699066162109,
1.0,
1.0,
0.7446385622024536,
1.0,
0.9957782030105591,
0.9999175071716309,
0.42324966192245483,
0.15068158507347107,
0.9407676458358765,
1.0,
1.0,
1.0,
0.9999991655349731,
0.9999998807907104,
0.9999990463256836,
1.0,
1.0,
1.0,
0.9996916055679321,
1.0,
1.0,
1.0,
1.0,
1.0,
0.9999998807907104,
0.9999940395355225,
0.9999938011169434,
1.0
],
"eval_cooking_runtime": 16.9203,
"eval_cooking_samples_per_second": 5.91,
"eval_cooking_steps_per_second": 0.118,
"epoch": 1.75,
"step": 100
},
{
"train_runtime": 1392.5305,
"train_samples_per_second": 2.298,
"train_steps_per_second": 0.072,
"total_flos": 0.0,
"train_loss": 0.3521362992748618,
"epoch": 1.75,
"step": 100
}
]