jeqcho's picture
Upload seed1/checkpoint-150
a30ac1e verified
Raw
History Blame
26.7 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.989010989010989,
"eval_steps": 500,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 0.9970224499702454,
"learning_rate": 0.0,
"loss": 1.0991,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 1.144827127456665,
"learning_rate": 9.56e-05,
"loss": 1.1545,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 1.1169440746307373,
"learning_rate": 0.0001912,
"loss": 1.123,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.0855385065078735,
"learning_rate": 0.0002868,
"loss": 0.9259,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 0.8469429016113281,
"learning_rate": 0.0003824,
"loss": 0.8556,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 0.7604000568389893,
"learning_rate": 0.000478,
"loss": 0.9009,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 0.5317047834396362,
"learning_rate": 0.00047694013303769406,
"loss": 0.9281,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 0.47205209732055664,
"learning_rate": 0.00047588026607538804,
"loss": 0.8713,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 0.2961072027683258,
"learning_rate": 0.0004748203991130821,
"loss": 0.8788,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.38304176926612854,
"learning_rate": 0.00047376053215077607,
"loss": 0.816,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.5212758779525757,
"learning_rate": 0.00047270066518847006,
"loss": 0.8274,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.543552577495575,
"learning_rate": 0.0004716407982261641,
"loss": 0.8489,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.4572776257991791,
"learning_rate": 0.00047058093126385814,
"loss": 0.8166,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.44755756855010986,
"learning_rate": 0.0004695210643015521,
"loss": 0.7803,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.5597015023231506,
"learning_rate": 0.00046846119733924617,
"loss": 0.801,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.39118215441703796,
"learning_rate": 0.00046740133037694015,
"loss": 0.7196,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.4890790581703186,
"learning_rate": 0.00046634146341463414,
"loss": 0.7744,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.5199437737464905,
"learning_rate": 0.0004652815964523282,
"loss": 0.7521,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.4048418402671814,
"learning_rate": 0.0004642217294900222,
"loss": 0.7232,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.4759422242641449,
"learning_rate": 0.0004631618625277162,
"loss": 0.7887,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.373710572719574,
"learning_rate": 0.00046210199556541025,
"loss": 0.7673,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.3180016577243805,
"learning_rate": 0.00046104212860310423,
"loss": 0.7553,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.43041887879371643,
"learning_rate": 0.0004599822616407982,
"loss": 0.7573,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.4632937014102936,
"learning_rate": 0.00045892239467849226,
"loss": 0.7318,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.3658117651939392,
"learning_rate": 0.0004578625277161863,
"loss": 0.7129,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.39879968762397766,
"learning_rate": 0.0004568026607538803,
"loss": 0.7212,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.4226565659046173,
"learning_rate": 0.00045574279379157433,
"loss": 0.7441,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.3761254549026489,
"learning_rate": 0.00045468292682926826,
"loss": 0.7351,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.3735473155975342,
"learning_rate": 0.0004536230598669623,
"loss": 0.7274,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.3605045676231384,
"learning_rate": 0.00045256319290465634,
"loss": 0.7511,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.49938589334487915,
"learning_rate": 0.00045150332594235033,
"loss": 0.733,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.3388383090496063,
"learning_rate": 0.00045044345898004437,
"loss": 0.7086,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.6535608768463135,
"learning_rate": 0.0004493835920177384,
"loss": 0.7686,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.36676231026649475,
"learning_rate": 0.00044832372505543234,
"loss": 0.6831,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.3847268521785736,
"learning_rate": 0.0004472638580931264,
"loss": 0.7375,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.37475308775901794,
"learning_rate": 0.0004462039911308204,
"loss": 0.7084,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.3576759696006775,
"learning_rate": 0.0004451441241685144,
"loss": 0.7693,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.33207494020462036,
"learning_rate": 0.00044408425720620845,
"loss": 0.7844,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.4797557592391968,
"learning_rate": 0.0004430243902439025,
"loss": 0.6863,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.3291913866996765,
"learning_rate": 0.0004419645232815964,
"loss": 0.6941,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.3354625701904297,
"learning_rate": 0.00044090465631929047,
"loss": 0.7254,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.3200039267539978,
"learning_rate": 0.0004398447893569845,
"loss": 0.6928,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.377468079328537,
"learning_rate": 0.0004387849223946785,
"loss": 0.7907,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.35265693068504333,
"learning_rate": 0.00043772505543237253,
"loss": 0.6916,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.4030437171459198,
"learning_rate": 0.0004366651884700666,
"loss": 0.721,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.3848680853843689,
"learning_rate": 0.0004356053215077605,
"loss": 0.7261,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.3052960932254791,
"learning_rate": 0.00043454545454545455,
"loss": 0.7063,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.3832049071788788,
"learning_rate": 0.0004334855875831486,
"loss": 0.7652,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.3644565939903259,
"learning_rate": 0.0004324257206208426,
"loss": 0.8106,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.3032757639884949,
"learning_rate": 0.0004313658536585366,
"loss": 0.7162,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.3071494996547699,
"learning_rate": 0.00043030598669623066,
"loss": 0.7907,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.32176244258880615,
"learning_rate": 0.0004292461197339246,
"loss": 0.7865,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.3945949375629425,
"learning_rate": 0.00042818625277161863,
"loss": 0.8038,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.2989363968372345,
"learning_rate": 0.00042712638580931267,
"loss": 0.7172,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.317256361246109,
"learning_rate": 0.00042606651884700666,
"loss": 0.7325,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.27640077471733093,
"learning_rate": 0.0004250066518847007,
"loss": 0.765,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.3094281256198883,
"learning_rate": 0.00042394678492239474,
"loss": 0.7391,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.30334004759788513,
"learning_rate": 0.00042288691796008867,
"loss": 0.7486,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.3377019166946411,
"learning_rate": 0.0004218270509977827,
"loss": 0.7444,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.34436339139938354,
"learning_rate": 0.00042076718403547675,
"loss": 0.7041,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.27596402168273926,
"learning_rate": 0.00041970731707317074,
"loss": 0.6926,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.3022932708263397,
"learning_rate": 0.0004186474501108648,
"loss": 0.7138,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.2816564738750458,
"learning_rate": 0.0004175875831485588,
"loss": 0.7261,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.3032025992870331,
"learning_rate": 0.00041652771618625275,
"loss": 0.6791,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.26954764127731323,
"learning_rate": 0.0004154678492239468,
"loss": 0.7032,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.3011576235294342,
"learning_rate": 0.00041440798226164083,
"loss": 0.7512,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.33316031098365784,
"learning_rate": 0.0004133481152993348,
"loss": 0.7345,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.3042667508125305,
"learning_rate": 0.00041228824833702886,
"loss": 0.7834,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.28509846329689026,
"learning_rate": 0.00041122838137472285,
"loss": 0.7127,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.3400508761405945,
"learning_rate": 0.00041016851441241683,
"loss": 0.7382,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.3198228180408478,
"learning_rate": 0.00040910864745011087,
"loss": 0.7625,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.32544252276420593,
"learning_rate": 0.00040804878048780486,
"loss": 0.7485,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.345786988735199,
"learning_rate": 0.0004069889135254989,
"loss": 0.7448,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.2966018319129944,
"learning_rate": 0.00040592904656319294,
"loss": 0.6449,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.27237051725387573,
"learning_rate": 0.0004048691796008869,
"loss": 0.6467,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.332011342048645,
"learning_rate": 0.00040380931263858097,
"loss": 0.7323,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.32000380754470825,
"learning_rate": 0.00040274944567627495,
"loss": 0.7653,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.34098610281944275,
"learning_rate": 0.00040168957871396894,
"loss": 0.7202,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.2874126732349396,
"learning_rate": 0.000400629711751663,
"loss": 0.7367,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.322229266166687,
"learning_rate": 0.000399569844789357,
"loss": 0.6588,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.3342168927192688,
"learning_rate": 0.000398509977827051,
"loss": 0.7579,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.3295648396015167,
"learning_rate": 0.00039745011086474505,
"loss": 0.7388,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.2803487479686737,
"learning_rate": 0.00039639024390243904,
"loss": 0.7614,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.32823750376701355,
"learning_rate": 0.000395330376940133,
"loss": 0.7479,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.32557007670402527,
"learning_rate": 0.00039427050997782706,
"loss": 0.7527,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.33845341205596924,
"learning_rate": 0.0003932106430155211,
"loss": 0.7203,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.39683398604393005,
"learning_rate": 0.0003921507760532151,
"loss": 0.7576,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.3514403998851776,
"learning_rate": 0.00039109090909090913,
"loss": 0.7556,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.3493777811527252,
"learning_rate": 0.0003900310421286031,
"loss": 0.6633,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.28230881690979004,
"learning_rate": 0.0003889711751662971,
"loss": 0.7153,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.31960365176200867,
"learning_rate": 0.00038791130820399114,
"loss": 0.7101,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.3226240575313568,
"learning_rate": 0.0003868514412416852,
"loss": 0.6795,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.37568366527557373,
"learning_rate": 0.00038579157427937917,
"loss": 0.6586,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.3764398992061615,
"learning_rate": 0.0003847317073170732,
"loss": 0.8014,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.32533973455429077,
"learning_rate": 0.0003836718403547672,
"loss": 0.7237,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.28496646881103516,
"learning_rate": 0.0003826119733924612,
"loss": 0.7134,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.29689112305641174,
"learning_rate": 0.0003815521064301552,
"loss": 0.7035,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.31590795516967773,
"learning_rate": 0.00038049223946784927,
"loss": 0.7087,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.2947428822517395,
"learning_rate": 0.00037943237250554325,
"loss": 0.6697,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.27264344692230225,
"learning_rate": 0.0003783725055432373,
"loss": 0.6232,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.38913288712501526,
"learning_rate": 0.0003773126385809313,
"loss": 0.6705,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.3600233793258667,
"learning_rate": 0.00037625277161862527,
"loss": 0.69,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.36744818091392517,
"learning_rate": 0.0003751929046563193,
"loss": 0.7739,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.33523765206336975,
"learning_rate": 0.00037413303769401335,
"loss": 0.7414,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.33133506774902344,
"learning_rate": 0.00037307317073170733,
"loss": 0.7447,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.38341405987739563,
"learning_rate": 0.0003720133037694014,
"loss": 0.7693,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.3323330283164978,
"learning_rate": 0.00037095343680709536,
"loss": 0.7502,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.3311186730861664,
"learning_rate": 0.00036989356984478935,
"loss": 0.6478,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.32154369354248047,
"learning_rate": 0.0003688337028824834,
"loss": 0.689,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.33734986186027527,
"learning_rate": 0.0003677738359201774,
"loss": 0.7497,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.29922378063201904,
"learning_rate": 0.0003667139689578714,
"loss": 0.6458,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.35878702998161316,
"learning_rate": 0.00036565410199556546,
"loss": 0.6826,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.4202096462249756,
"learning_rate": 0.0003645942350332594,
"loss": 0.7508,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.34974202513694763,
"learning_rate": 0.00036353436807095343,
"loss": 0.6995,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.3248356878757477,
"learning_rate": 0.00036247450110864747,
"loss": 0.7133,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.3106825649738312,
"learning_rate": 0.00036141463414634146,
"loss": 0.7873,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.3386942148208618,
"learning_rate": 0.0003603547671840355,
"loss": 0.674,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.31210097670555115,
"learning_rate": 0.00035929490022172954,
"loss": 0.761,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.3049944043159485,
"learning_rate": 0.00035823503325942347,
"loss": 0.6974,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.2945634722709656,
"learning_rate": 0.0003571751662971175,
"loss": 0.7786,
"step": 120
},
{
"epoch": 0.7978021978021979,
"grad_norm": 0.334928423166275,
"learning_rate": 0.00035611529933481155,
"loss": 0.7759,
"step": 121
},
{
"epoch": 0.8043956043956044,
"grad_norm": 0.33794817328453064,
"learning_rate": 0.00035505543237250554,
"loss": 0.7268,
"step": 122
},
{
"epoch": 0.810989010989011,
"grad_norm": 0.34872716665267944,
"learning_rate": 0.0003539955654101996,
"loss": 0.6964,
"step": 123
},
{
"epoch": 0.8175824175824176,
"grad_norm": 0.27211689949035645,
"learning_rate": 0.0003529356984478936,
"loss": 0.7026,
"step": 124
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.303218811750412,
"learning_rate": 0.00035187583148558755,
"loss": 0.7113,
"step": 125
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.28027018904685974,
"learning_rate": 0.0003508159645232816,
"loss": 0.7727,
"step": 126
},
{
"epoch": 0.8373626373626374,
"grad_norm": 0.2782959043979645,
"learning_rate": 0.00034975609756097563,
"loss": 0.7235,
"step": 127
},
{
"epoch": 0.843956043956044,
"grad_norm": 0.27962350845336914,
"learning_rate": 0.0003486962305986696,
"loss": 0.7115,
"step": 128
},
{
"epoch": 0.8505494505494505,
"grad_norm": 0.28686633706092834,
"learning_rate": 0.00034763636363636366,
"loss": 0.7398,
"step": 129
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.3914222717285156,
"learning_rate": 0.0003465764966740577,
"loss": 0.7521,
"step": 130
},
{
"epoch": 0.8637362637362638,
"grad_norm": 0.30597811937332153,
"learning_rate": 0.00034551662971175163,
"loss": 0.718,
"step": 131
},
{
"epoch": 0.8703296703296703,
"grad_norm": 0.2956196069717407,
"learning_rate": 0.00034445676274944567,
"loss": 0.6925,
"step": 132
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.3160248398780823,
"learning_rate": 0.0003433968957871397,
"loss": 0.7046,
"step": 133
},
{
"epoch": 0.8835164835164835,
"grad_norm": 0.2987951338291168,
"learning_rate": 0.0003423370288248337,
"loss": 0.6252,
"step": 134
},
{
"epoch": 0.8901098901098901,
"grad_norm": 0.3024667501449585,
"learning_rate": 0.00034127716186252774,
"loss": 0.778,
"step": 135
},
{
"epoch": 0.8967032967032967,
"grad_norm": 0.2868024408817291,
"learning_rate": 0.0003402172949002218,
"loss": 0.6807,
"step": 136
},
{
"epoch": 0.9032967032967033,
"grad_norm": 0.29994046688079834,
"learning_rate": 0.00033915742793791577,
"loss": 0.711,
"step": 137
},
{
"epoch": 0.9098901098901099,
"grad_norm": 0.3246282935142517,
"learning_rate": 0.00033809756097560975,
"loss": 0.7606,
"step": 138
},
{
"epoch": 0.9164835164835164,
"grad_norm": 0.3361048698425293,
"learning_rate": 0.0003370376940133038,
"loss": 0.6995,
"step": 139
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.3376304507255554,
"learning_rate": 0.0003359778270509978,
"loss": 0.71,
"step": 140
},
{
"epoch": 0.9296703296703297,
"grad_norm": 0.29205799102783203,
"learning_rate": 0.0003349179600886918,
"loss": 0.6685,
"step": 141
},
{
"epoch": 0.9362637362637363,
"grad_norm": 0.30635398626327515,
"learning_rate": 0.00033385809312638586,
"loss": 0.7522,
"step": 142
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.3423284590244293,
"learning_rate": 0.00033279822616407985,
"loss": 0.6769,
"step": 143
},
{
"epoch": 0.9494505494505494,
"grad_norm": 0.30614131689071655,
"learning_rate": 0.00033173835920177384,
"loss": 0.6788,
"step": 144
},
{
"epoch": 0.9560439560439561,
"grad_norm": 0.3104928433895111,
"learning_rate": 0.0003306784922394679,
"loss": 0.6591,
"step": 145
},
{
"epoch": 0.9626373626373627,
"grad_norm": 0.33305084705352783,
"learning_rate": 0.00032961862527716186,
"loss": 0.6966,
"step": 146
},
{
"epoch": 0.9692307692307692,
"grad_norm": 0.3775268495082855,
"learning_rate": 0.0003285587583148559,
"loss": 0.7447,
"step": 147
},
{
"epoch": 0.9758241758241758,
"grad_norm": 0.3366539776325226,
"learning_rate": 0.00032749889135254994,
"loss": 0.7501,
"step": 148
},
{
"epoch": 0.9824175824175824,
"grad_norm": 0.38443613052368164,
"learning_rate": 0.00032643902439024393,
"loss": 0.645,
"step": 149
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.3002435863018036,
"learning_rate": 0.0003253791574279379,
"loss": 0.7398,
"step": 150
}
],
"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": 6.866488050534605e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}