jeqcho's picture
Upload seed0/checkpoint-135
4559243 verified
Raw History Blame
24.1 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8901098901098901,
"eval_steps": 500,
"global_step": 135,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 1.0287306308746338,
"learning_rate": 0.0,
"loss": 1.084,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 0.948112428188324,
"learning_rate": 9.56e-05,
"loss": 1.0638,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 1.0350998640060425,
"learning_rate": 0.0001912,
"loss": 1.143,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.1360750198364258,
"learning_rate": 0.0002868,
"loss": 1.0394,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 0.7310333251953125,
"learning_rate": 0.0003824,
"loss": 0.8949,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 0.6246419548988342,
"learning_rate": 0.000478,
"loss": 0.9157,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 0.5591331720352173,
"learning_rate": 0.00047694013303769406,
"loss": 0.9064,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 0.411284863948822,
"learning_rate": 0.00047588026607538804,
"loss": 0.8349,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 0.30876654386520386,
"learning_rate": 0.0004748203991130821,
"loss": 0.8626,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.39697328209877014,
"learning_rate": 0.00047376053215077607,
"loss": 0.8347,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.3990109860897064,
"learning_rate": 0.00047270066518847006,
"loss": 0.8383,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.3827734589576721,
"learning_rate": 0.0004716407982261641,
"loss": 0.7593,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.5764995217323303,
"learning_rate": 0.00047058093126385814,
"loss": 0.7725,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.5014582276344299,
"learning_rate": 0.0004695210643015521,
"loss": 0.7577,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.4466342628002167,
"learning_rate": 0.00046846119733924617,
"loss": 0.7279,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.3709656894207001,
"learning_rate": 0.00046740133037694015,
"loss": 0.7577,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.5953618288040161,
"learning_rate": 0.00046634146341463414,
"loss": 0.8038,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.43582218885421753,
"learning_rate": 0.0004652815964523282,
"loss": 0.7836,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.35281723737716675,
"learning_rate": 0.0004642217294900222,
"loss": 0.7541,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.4125503897666931,
"learning_rate": 0.0004631618625277162,
"loss": 0.7476,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.3566338121891022,
"learning_rate": 0.00046210199556541025,
"loss": 0.6958,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.3785325884819031,
"learning_rate": 0.00046104212860310423,
"loss": 0.7827,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.3147861659526825,
"learning_rate": 0.0004599822616407982,
"loss": 0.7631,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.4547198712825775,
"learning_rate": 0.00045892239467849226,
"loss": 0.7453,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.3506404459476471,
"learning_rate": 0.0004578625277161863,
"loss": 0.7397,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.35579541325569153,
"learning_rate": 0.0004568026607538803,
"loss": 0.8032,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.35984915494918823,
"learning_rate": 0.00045574279379157433,
"loss": 0.6869,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.3912736177444458,
"learning_rate": 0.00045468292682926826,
"loss": 0.7423,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.3313451111316681,
"learning_rate": 0.0004536230598669623,
"loss": 0.826,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.3460421860218048,
"learning_rate": 0.00045256319290465634,
"loss": 0.7155,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.42073190212249756,
"learning_rate": 0.00045150332594235033,
"loss": 0.7308,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.3369511067867279,
"learning_rate": 0.00045044345898004437,
"loss": 0.7529,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.3326997756958008,
"learning_rate": 0.0004493835920177384,
"loss": 0.7098,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.3323321044445038,
"learning_rate": 0.00044832372505543234,
"loss": 0.7104,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.365688294172287,
"learning_rate": 0.0004472638580931264,
"loss": 0.6777,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.4034178853034973,
"learning_rate": 0.0004462039911308204,
"loss": 0.7655,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.4079640209674835,
"learning_rate": 0.0004451441241685144,
"loss": 0.6348,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.35669246315956116,
"learning_rate": 0.00044408425720620845,
"loss": 0.7146,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.4017118513584137,
"learning_rate": 0.0004430243902439025,
"loss": 0.8002,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.37425458431243896,
"learning_rate": 0.0004419645232815964,
"loss": 0.6953,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.3201092779636383,
"learning_rate": 0.00044090465631929047,
"loss": 0.6991,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.3773852288722992,
"learning_rate": 0.0004398447893569845,
"loss": 0.7467,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.2974673807621002,
"learning_rate": 0.0004387849223946785,
"loss": 0.7288,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.30199432373046875,
"learning_rate": 0.00043772505543237253,
"loss": 0.7304,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.3696371018886566,
"learning_rate": 0.0004366651884700666,
"loss": 0.7752,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.3928535282611847,
"learning_rate": 0.0004356053215077605,
"loss": 0.6959,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.3518235683441162,
"learning_rate": 0.00043454545454545455,
"loss": 0.7344,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.3202143907546997,
"learning_rate": 0.0004334855875831486,
"loss": 0.7144,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.39293670654296875,
"learning_rate": 0.0004324257206208426,
"loss": 0.7044,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.42684948444366455,
"learning_rate": 0.0004313658536585366,
"loss": 0.7236,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.4143947958946228,
"learning_rate": 0.00043030598669623066,
"loss": 0.687,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.46073058247566223,
"learning_rate": 0.0004292461197339246,
"loss": 0.7201,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.38219717144966125,
"learning_rate": 0.00042818625277161863,
"loss": 0.7589,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.27848541736602783,
"learning_rate": 0.00042712638580931267,
"loss": 0.7208,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.2882401943206787,
"learning_rate": 0.00042606651884700666,
"loss": 0.7121,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.3918374180793762,
"learning_rate": 0.0004250066518847007,
"loss": 0.6783,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.3108501732349396,
"learning_rate": 0.00042394678492239474,
"loss": 0.7249,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.31900638341903687,
"learning_rate": 0.00042288691796008867,
"loss": 0.725,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.4268058240413666,
"learning_rate": 0.0004218270509977827,
"loss": 0.7717,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.3654431700706482,
"learning_rate": 0.00042076718403547675,
"loss": 0.7369,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.3035155236721039,
"learning_rate": 0.00041970731707317074,
"loss": 0.6962,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.3147648870944977,
"learning_rate": 0.0004186474501108648,
"loss": 0.7239,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.30889788269996643,
"learning_rate": 0.0004175875831485588,
"loss": 0.7697,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.29330822825431824,
"learning_rate": 0.00041652771618625275,
"loss": 0.7438,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.3334480822086334,
"learning_rate": 0.0004154678492239468,
"loss": 0.6889,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.29151853919029236,
"learning_rate": 0.00041440798226164083,
"loss": 0.6632,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.38440635800361633,
"learning_rate": 0.0004133481152993348,
"loss": 0.7305,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.32712990045547485,
"learning_rate": 0.00041228824833702886,
"loss": 0.8122,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.37737423181533813,
"learning_rate": 0.00041122838137472285,
"loss": 0.6368,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.3335571885108948,
"learning_rate": 0.00041016851441241683,
"loss": 0.6586,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.3446078598499298,
"learning_rate": 0.00040910864745011087,
"loss": 0.7299,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.30252110958099365,
"learning_rate": 0.00040804878048780486,
"loss": 0.7084,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.23997364938259125,
"learning_rate": 0.0004069889135254989,
"loss": 0.7479,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.3268393576145172,
"learning_rate": 0.00040592904656319294,
"loss": 0.7417,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.2819831371307373,
"learning_rate": 0.0004048691796008869,
"loss": 0.7691,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.3438951075077057,
"learning_rate": 0.00040380931263858097,
"loss": 0.7447,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.34539034962654114,
"learning_rate": 0.00040274944567627495,
"loss": 0.7299,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.39309996366500854,
"learning_rate": 0.00040168957871396894,
"loss": 0.7103,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.4111672341823578,
"learning_rate": 0.000400629711751663,
"loss": 0.7175,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.35200831294059753,
"learning_rate": 0.000399569844789357,
"loss": 0.7914,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.3106718063354492,
"learning_rate": 0.000398509977827051,
"loss": 0.7064,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.40410006046295166,
"learning_rate": 0.00039745011086474505,
"loss": 0.7015,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.3284229338169098,
"learning_rate": 0.00039639024390243904,
"loss": 0.7696,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.2930781841278076,
"learning_rate": 0.000395330376940133,
"loss": 0.6839,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.4067613184452057,
"learning_rate": 0.00039427050997782706,
"loss": 0.7693,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.39632725715637207,
"learning_rate": 0.0003932106430155211,
"loss": 0.776,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.3314855992794037,
"learning_rate": 0.0003921507760532151,
"loss": 0.7207,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.3370056748390198,
"learning_rate": 0.00039109090909090913,
"loss": 0.7828,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.3866356313228607,
"learning_rate": 0.0003900310421286031,
"loss": 0.7538,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.3172929883003235,
"learning_rate": 0.0003889711751662971,
"loss": 0.7807,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.32534992694854736,
"learning_rate": 0.00038791130820399114,
"loss": 0.7072,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.26510292291641235,
"learning_rate": 0.0003868514412416852,
"loss": 0.6967,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.29210713505744934,
"learning_rate": 0.00038579157427937917,
"loss": 0.6601,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.3541831374168396,
"learning_rate": 0.0003847317073170732,
"loss": 0.7131,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.3541385531425476,
"learning_rate": 0.0003836718403547672,
"loss": 0.7248,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.3337606191635132,
"learning_rate": 0.0003826119733924612,
"loss": 0.7652,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.33775588870048523,
"learning_rate": 0.0003815521064301552,
"loss": 0.7818,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.3222000300884247,
"learning_rate": 0.00038049223946784927,
"loss": 0.733,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.3088921904563904,
"learning_rate": 0.00037943237250554325,
"loss": 0.6638,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.2936277687549591,
"learning_rate": 0.0003783725055432373,
"loss": 0.7121,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.26708656549453735,
"learning_rate": 0.0003773126385809313,
"loss": 0.7353,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.29909640550613403,
"learning_rate": 0.00037625277161862527,
"loss": 0.7214,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.30008482933044434,
"learning_rate": 0.0003751929046563193,
"loss": 0.7365,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.38386833667755127,
"learning_rate": 0.00037413303769401335,
"loss": 0.7514,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.3135545253753662,
"learning_rate": 0.00037307317073170733,
"loss": 0.6882,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.31808924674987793,
"learning_rate": 0.0003720133037694014,
"loss": 0.744,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.30010560154914856,
"learning_rate": 0.00037095343680709536,
"loss": 0.6816,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.31569167971611023,
"learning_rate": 0.00036989356984478935,
"loss": 0.7064,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.30984246730804443,
"learning_rate": 0.0003688337028824834,
"loss": 0.7154,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.286091685295105,
"learning_rate": 0.0003677738359201774,
"loss": 0.701,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.3322799503803253,
"learning_rate": 0.0003667139689578714,
"loss": 0.6629,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.32251879572868347,
"learning_rate": 0.00036565410199556546,
"loss": 0.7101,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.3163260221481323,
"learning_rate": 0.0003645942350332594,
"loss": 0.7318,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.35563021898269653,
"learning_rate": 0.00036353436807095343,
"loss": 0.6708,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.3295123875141144,
"learning_rate": 0.00036247450110864747,
"loss": 0.7531,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.3174284100532532,
"learning_rate": 0.00036141463414634146,
"loss": 0.6435,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.3112541139125824,
"learning_rate": 0.0003603547671840355,
"loss": 0.7079,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.2765205204486847,
"learning_rate": 0.00035929490022172954,
"loss": 0.7399,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.4011540412902832,
"learning_rate": 0.00035823503325942347,
"loss": 0.7471,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.3467070758342743,
"learning_rate": 0.0003571751662971175,
"loss": 0.749,
"step": 120
},
{
"epoch": 0.7978021978021979,
"grad_norm": 0.322721391916275,
"learning_rate": 0.00035611529933481155,
"loss": 0.6992,
"step": 121
},
{
"epoch": 0.8043956043956044,
"grad_norm": 0.3257431089878082,
"learning_rate": 0.00035505543237250554,
"loss": 0.7448,
"step": 122
},
{
"epoch": 0.810989010989011,
"grad_norm": 0.3538271188735962,
"learning_rate": 0.0003539955654101996,
"loss": 0.7202,
"step": 123
},
{
"epoch": 0.8175824175824176,
"grad_norm": 0.33168667554855347,
"learning_rate": 0.0003529356984478936,
"loss": 0.7521,
"step": 124
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.3086656630039215,
"learning_rate": 0.00035187583148558755,
"loss": 0.6933,
"step": 125
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.29101550579071045,
"learning_rate": 0.0003508159645232816,
"loss": 0.6807,
"step": 126
},
{
"epoch": 0.8373626373626374,
"grad_norm": 0.31047967076301575,
"learning_rate": 0.00034975609756097563,
"loss": 0.7028,
"step": 127
},
{
"epoch": 0.843956043956044,
"grad_norm": 0.4100898206233978,
"learning_rate": 0.0003486962305986696,
"loss": 0.7063,
"step": 128
},
{
"epoch": 0.8505494505494505,
"grad_norm": 0.3553723096847534,
"learning_rate": 0.00034763636363636366,
"loss": 0.6585,
"step": 129
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.34842953085899353,
"learning_rate": 0.0003465764966740577,
"loss": 0.6551,
"step": 130
},
{
"epoch": 0.8637362637362638,
"grad_norm": 0.29668596386909485,
"learning_rate": 0.00034551662971175163,
"loss": 0.7625,
"step": 131
},
{
"epoch": 0.8703296703296703,
"grad_norm": 0.32529106736183167,
"learning_rate": 0.00034445676274944567,
"loss": 0.6823,
"step": 132
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.3435796797275543,
"learning_rate": 0.0003433968957871397,
"loss": 0.7695,
"step": 133
},
{
"epoch": 0.8835164835164835,
"grad_norm": 0.360817015171051,
"learning_rate": 0.0003423370288248337,
"loss": 0.718,
"step": 134
},
{
"epoch": 0.8901098901098901,
"grad_norm": 0.37331467866897583,
"learning_rate": 0.00034127716186252774,
"loss": 0.7678,
"step": 135
}
],
"logging_steps": 1,
"max_steps": 456,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 15,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.171986321619149e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}