jeqcho's picture
Upload seed2/checkpoint-180
6ef31f3 verified
Raw
History Blame Contribute Delete
31.9 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.1846153846153846,
"eval_steps": 500,
"global_step": 180,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 1.0638142824172974,
"learning_rate": 0.0,
"loss": 1.0777,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 0.9542151689529419,
"learning_rate": 9.56e-05,
"loss": 1.1025,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 1.0668847560882568,
"learning_rate": 0.0001912,
"loss": 1.0405,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.0646922588348389,
"learning_rate": 0.0002868,
"loss": 0.9056,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 0.6475369334220886,
"learning_rate": 0.0003824,
"loss": 0.8513,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 0.653504490852356,
"learning_rate": 0.000478,
"loss": 0.9432,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 0.5652804374694824,
"learning_rate": 0.00047694013303769406,
"loss": 0.8951,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 0.38114824891090393,
"learning_rate": 0.00047588026607538804,
"loss": 0.8546,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 0.3202402591705322,
"learning_rate": 0.0004748203991130821,
"loss": 0.9013,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.3632391095161438,
"learning_rate": 0.00047376053215077607,
"loss": 0.7981,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.38180795311927795,
"learning_rate": 0.00047270066518847006,
"loss": 0.8034,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.44034814834594727,
"learning_rate": 0.0004716407982261641,
"loss": 0.8194,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.5649089217185974,
"learning_rate": 0.00047058093126385814,
"loss": 0.7964,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.4905894994735718,
"learning_rate": 0.0004695210643015521,
"loss": 0.7767,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.5945530533790588,
"learning_rate": 0.00046846119733924617,
"loss": 0.7485,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.47223448753356934,
"learning_rate": 0.00046740133037694015,
"loss": 0.7412,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.4855833053588867,
"learning_rate": 0.00046634146341463414,
"loss": 0.7992,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.420284628868103,
"learning_rate": 0.0004652815964523282,
"loss": 0.7427,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.517633855342865,
"learning_rate": 0.0004642217294900222,
"loss": 0.7918,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.434706449508667,
"learning_rate": 0.0004631618625277162,
"loss": 0.7891,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.3698730766773224,
"learning_rate": 0.00046210199556541025,
"loss": 0.7076,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.3561922609806061,
"learning_rate": 0.00046104212860310423,
"loss": 0.7893,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.3815233111381531,
"learning_rate": 0.0004599822616407982,
"loss": 0.7999,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.38611900806427,
"learning_rate": 0.00045892239467849226,
"loss": 0.7928,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.29186370968818665,
"learning_rate": 0.0004578625277161863,
"loss": 0.724,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.3245350420475006,
"learning_rate": 0.0004568026607538803,
"loss": 0.7503,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.3803184926509857,
"learning_rate": 0.00045574279379157433,
"loss": 0.7455,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.3178353011608124,
"learning_rate": 0.00045468292682926826,
"loss": 0.7207,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.4353942573070526,
"learning_rate": 0.0004536230598669623,
"loss": 0.8268,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.3097940981388092,
"learning_rate": 0.00045256319290465634,
"loss": 0.6621,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.3318345546722412,
"learning_rate": 0.00045150332594235033,
"loss": 0.7092,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.31531524658203125,
"learning_rate": 0.00045044345898004437,
"loss": 0.7668,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.3566637933254242,
"learning_rate": 0.0004493835920177384,
"loss": 0.7545,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.36444291472435,
"learning_rate": 0.00044832372505543234,
"loss": 0.8064,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.3560720980167389,
"learning_rate": 0.0004472638580931264,
"loss": 0.7774,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.3715183734893799,
"learning_rate": 0.0004462039911308204,
"loss": 0.7131,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.2921788692474365,
"learning_rate": 0.0004451441241685144,
"loss": 0.8009,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.29083380103111267,
"learning_rate": 0.00044408425720620845,
"loss": 0.7223,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.3140243887901306,
"learning_rate": 0.0004430243902439025,
"loss": 0.7196,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.3676493465900421,
"learning_rate": 0.0004419645232815964,
"loss": 0.7143,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.3598462641239166,
"learning_rate": 0.00044090465631929047,
"loss": 0.7474,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.3195889890193939,
"learning_rate": 0.0004398447893569845,
"loss": 0.7229,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.30827897787094116,
"learning_rate": 0.0004387849223946785,
"loss": 0.7428,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.38703453540802,
"learning_rate": 0.00043772505543237253,
"loss": 0.7169,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.28942254185676575,
"learning_rate": 0.0004366651884700666,
"loss": 0.7456,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.35373979806900024,
"learning_rate": 0.0004356053215077605,
"loss": 0.7703,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.3619854748249054,
"learning_rate": 0.00043454545454545455,
"loss": 0.6991,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.3936954438686371,
"learning_rate": 0.0004334855875831486,
"loss": 0.7505,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.31419533491134644,
"learning_rate": 0.0004324257206208426,
"loss": 0.7218,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.31622064113616943,
"learning_rate": 0.0004313658536585366,
"loss": 0.7133,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.31881847977638245,
"learning_rate": 0.00043030598669623066,
"loss": 0.7015,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.29825660586357117,
"learning_rate": 0.0004292461197339246,
"loss": 0.7513,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.28996437788009644,
"learning_rate": 0.00042818625277161863,
"loss": 0.7417,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.317898690700531,
"learning_rate": 0.00042712638580931267,
"loss": 0.7547,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.35207676887512207,
"learning_rate": 0.00042606651884700666,
"loss": 0.8215,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.2996538579463959,
"learning_rate": 0.0004250066518847007,
"loss": 0.7897,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.35331282019615173,
"learning_rate": 0.00042394678492239474,
"loss": 0.7466,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.30339422821998596,
"learning_rate": 0.00042288691796008867,
"loss": 0.7079,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.35229793190956116,
"learning_rate": 0.0004218270509977827,
"loss": 0.7322,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.3471188545227051,
"learning_rate": 0.00042076718403547675,
"loss": 0.6908,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.384351521730423,
"learning_rate": 0.00041970731707317074,
"loss": 0.6937,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.34261906147003174,
"learning_rate": 0.0004186474501108648,
"loss": 0.694,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.36659127473831177,
"learning_rate": 0.0004175875831485588,
"loss": 0.7186,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.3876580595970154,
"learning_rate": 0.00041652771618625275,
"loss": 0.7474,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.3435872495174408,
"learning_rate": 0.0004154678492239468,
"loss": 0.7313,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.2954373061656952,
"learning_rate": 0.00041440798226164083,
"loss": 0.6693,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.2931239604949951,
"learning_rate": 0.0004133481152993348,
"loss": 0.7175,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.37997666001319885,
"learning_rate": 0.00041228824833702886,
"loss": 0.704,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.3305527865886688,
"learning_rate": 0.00041122838137472285,
"loss": 0.7234,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.33284375071525574,
"learning_rate": 0.00041016851441241683,
"loss": 0.6931,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.32701659202575684,
"learning_rate": 0.00040910864745011087,
"loss": 0.7191,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.32257601618766785,
"learning_rate": 0.00040804878048780486,
"loss": 0.6495,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.34117209911346436,
"learning_rate": 0.0004069889135254989,
"loss": 0.7386,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.41902703046798706,
"learning_rate": 0.00040592904656319294,
"loss": 0.7807,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.3014705181121826,
"learning_rate": 0.0004048691796008869,
"loss": 0.6529,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.34272533655166626,
"learning_rate": 0.00040380931263858097,
"loss": 0.7318,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.3316797614097595,
"learning_rate": 0.00040274944567627495,
"loss": 0.6452,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.290902704000473,
"learning_rate": 0.00040168957871396894,
"loss": 0.742,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.34589096903800964,
"learning_rate": 0.000400629711751663,
"loss": 0.7207,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.35719630122184753,
"learning_rate": 0.000399569844789357,
"loss": 0.7156,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.36912935972213745,
"learning_rate": 0.000398509977827051,
"loss": 0.7168,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.3709248900413513,
"learning_rate": 0.00039745011086474505,
"loss": 0.7413,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.3554258942604065,
"learning_rate": 0.00039639024390243904,
"loss": 0.7422,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.2682874798774719,
"learning_rate": 0.000395330376940133,
"loss": 0.6487,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.275944322347641,
"learning_rate": 0.00039427050997782706,
"loss": 0.7031,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.3202199935913086,
"learning_rate": 0.0003932106430155211,
"loss": 0.6992,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.3686879575252533,
"learning_rate": 0.0003921507760532151,
"loss": 0.7499,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.303440660238266,
"learning_rate": 0.00039109090909090913,
"loss": 0.7126,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.3335700035095215,
"learning_rate": 0.0003900310421286031,
"loss": 0.782,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.33381161093711853,
"learning_rate": 0.0003889711751662971,
"loss": 0.6969,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.30890610814094543,
"learning_rate": 0.00038791130820399114,
"loss": 0.7082,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.3305893540382385,
"learning_rate": 0.0003868514412416852,
"loss": 0.7532,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.29973316192626953,
"learning_rate": 0.00038579157427937917,
"loss": 0.6992,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.2805730402469635,
"learning_rate": 0.0003847317073170732,
"loss": 0.7513,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.29244521260261536,
"learning_rate": 0.0003836718403547672,
"loss": 0.7227,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.2936287224292755,
"learning_rate": 0.0003826119733924612,
"loss": 0.7598,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.30633246898651123,
"learning_rate": 0.0003815521064301552,
"loss": 0.6596,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.3642038404941559,
"learning_rate": 0.00038049223946784927,
"loss": 0.7832,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.3244490921497345,
"learning_rate": 0.00037943237250554325,
"loss": 0.6916,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.3080962896347046,
"learning_rate": 0.0003783725055432373,
"loss": 0.6874,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.340778648853302,
"learning_rate": 0.0003773126385809313,
"loss": 0.8066,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.3969302177429199,
"learning_rate": 0.00037625277161862527,
"loss": 0.726,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.30715158581733704,
"learning_rate": 0.0003751929046563193,
"loss": 0.7383,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.38129615783691406,
"learning_rate": 0.00037413303769401335,
"loss": 0.7091,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.33120641112327576,
"learning_rate": 0.00037307317073170733,
"loss": 0.7248,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.3293302059173584,
"learning_rate": 0.0003720133037694014,
"loss": 0.5786,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.32738253474235535,
"learning_rate": 0.00037095343680709536,
"loss": 0.7797,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.31135183572769165,
"learning_rate": 0.00036989356984478935,
"loss": 0.6484,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.40488898754119873,
"learning_rate": 0.0003688337028824834,
"loss": 0.7333,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.33448660373687744,
"learning_rate": 0.0003677738359201774,
"loss": 0.7262,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.38866227865219116,
"learning_rate": 0.0003667139689578714,
"loss": 0.6933,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.3379201591014862,
"learning_rate": 0.00036565410199556546,
"loss": 0.6609,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.33066609501838684,
"learning_rate": 0.0003645942350332594,
"loss": 0.725,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.2952742278575897,
"learning_rate": 0.00036353436807095343,
"loss": 0.6916,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.3941051661968231,
"learning_rate": 0.00036247450110864747,
"loss": 0.7429,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.3148791491985321,
"learning_rate": 0.00036141463414634146,
"loss": 0.7121,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.3531208336353302,
"learning_rate": 0.0003603547671840355,
"loss": 0.7297,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.3178044855594635,
"learning_rate": 0.00035929490022172954,
"loss": 0.7168,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.30421027541160583,
"learning_rate": 0.00035823503325942347,
"loss": 0.7223,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.3736768364906311,
"learning_rate": 0.0003571751662971175,
"loss": 0.6606,
"step": 120
},
{
"epoch": 0.7978021978021979,
"grad_norm": 0.3562946617603302,
"learning_rate": 0.00035611529933481155,
"loss": 0.7329,
"step": 121
},
{
"epoch": 0.8043956043956044,
"grad_norm": 0.3355368375778198,
"learning_rate": 0.00035505543237250554,
"loss": 0.6589,
"step": 122
},
{
"epoch": 0.810989010989011,
"grad_norm": 0.3533897399902344,
"learning_rate": 0.0003539955654101996,
"loss": 0.6781,
"step": 123
},
{
"epoch": 0.8175824175824176,
"grad_norm": 0.31134122610092163,
"learning_rate": 0.0003529356984478936,
"loss": 0.6875,
"step": 124
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.3257146179676056,
"learning_rate": 0.00035187583148558755,
"loss": 0.693,
"step": 125
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.355998694896698,
"learning_rate": 0.0003508159645232816,
"loss": 0.7246,
"step": 126
},
{
"epoch": 0.8373626373626374,
"grad_norm": 0.30442821979522705,
"learning_rate": 0.00034975609756097563,
"loss": 0.7177,
"step": 127
},
{
"epoch": 0.843956043956044,
"grad_norm": 0.2803910970687866,
"learning_rate": 0.0003486962305986696,
"loss": 0.7422,
"step": 128
},
{
"epoch": 0.8505494505494505,
"grad_norm": 0.3258972465991974,
"learning_rate": 0.00034763636363636366,
"loss": 0.7031,
"step": 129
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.382231205701828,
"learning_rate": 0.0003465764966740577,
"loss": 0.7223,
"step": 130
},
{
"epoch": 0.8637362637362638,
"grad_norm": 0.3049597144126892,
"learning_rate": 0.00034551662971175163,
"loss": 0.7557,
"step": 131
},
{
"epoch": 0.8703296703296703,
"grad_norm": 0.34174099564552307,
"learning_rate": 0.00034445676274944567,
"loss": 0.729,
"step": 132
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.348481684923172,
"learning_rate": 0.0003433968957871397,
"loss": 0.7002,
"step": 133
},
{
"epoch": 0.8835164835164835,
"grad_norm": 0.28441721200942993,
"learning_rate": 0.0003423370288248337,
"loss": 0.7053,
"step": 134
},
{
"epoch": 0.8901098901098901,
"grad_norm": 0.3341362178325653,
"learning_rate": 0.00034127716186252774,
"loss": 0.7317,
"step": 135
},
{
"epoch": 0.8967032967032967,
"grad_norm": 0.3288741409778595,
"learning_rate": 0.0003402172949002218,
"loss": 0.7089,
"step": 136
},
{
"epoch": 0.9032967032967033,
"grad_norm": 0.3161088526248932,
"learning_rate": 0.00033915742793791577,
"loss": 0.6842,
"step": 137
},
{
"epoch": 0.9098901098901099,
"grad_norm": 0.3017628788948059,
"learning_rate": 0.00033809756097560975,
"loss": 0.6552,
"step": 138
},
{
"epoch": 0.9164835164835164,
"grad_norm": 0.2661060690879822,
"learning_rate": 0.0003370376940133038,
"loss": 0.7478,
"step": 139
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.31222012639045715,
"learning_rate": 0.0003359778270509978,
"loss": 0.7552,
"step": 140
},
{
"epoch": 0.9296703296703297,
"grad_norm": 0.43476974964141846,
"learning_rate": 0.0003349179600886918,
"loss": 0.758,
"step": 141
},
{
"epoch": 0.9362637362637363,
"grad_norm": 0.3367742598056793,
"learning_rate": 0.00033385809312638586,
"loss": 0.7794,
"step": 142
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.3539772927761078,
"learning_rate": 0.00033279822616407985,
"loss": 0.7972,
"step": 143
},
{
"epoch": 0.9494505494505494,
"grad_norm": 0.28672459721565247,
"learning_rate": 0.00033173835920177384,
"loss": 0.7016,
"step": 144
},
{
"epoch": 0.9560439560439561,
"grad_norm": 0.28496575355529785,
"learning_rate": 0.0003306784922394679,
"loss": 0.7164,
"step": 145
},
{
"epoch": 0.9626373626373627,
"grad_norm": 0.2734069228172302,
"learning_rate": 0.00032961862527716186,
"loss": 0.8092,
"step": 146
},
{
"epoch": 0.9692307692307692,
"grad_norm": 0.26828694343566895,
"learning_rate": 0.0003285587583148559,
"loss": 0.7474,
"step": 147
},
{
"epoch": 0.9758241758241758,
"grad_norm": 0.32626521587371826,
"learning_rate": 0.00032749889135254994,
"loss": 0.7146,
"step": 148
},
{
"epoch": 0.9824175824175824,
"grad_norm": 0.3634294271469116,
"learning_rate": 0.00032643902439024393,
"loss": 0.7179,
"step": 149
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.30671507120132446,
"learning_rate": 0.0003253791574279379,
"loss": 0.7103,
"step": 150
},
{
"epoch": 0.9956043956043956,
"grad_norm": 0.3247479498386383,
"learning_rate": 0.0003243192904656319,
"loss": 0.7221,
"step": 151
},
{
"epoch": 1.0,
"grad_norm": 0.42680439352989197,
"learning_rate": 0.00032325942350332594,
"loss": 0.7161,
"step": 152
},
{
"epoch": 1.0065934065934066,
"grad_norm": 0.36276939511299133,
"learning_rate": 0.00032219955654102,
"loss": 0.7322,
"step": 153
},
{
"epoch": 1.0131868131868131,
"grad_norm": 0.3108954131603241,
"learning_rate": 0.00032113968957871397,
"loss": 0.673,
"step": 154
},
{
"epoch": 1.0197802197802197,
"grad_norm": 0.3481237292289734,
"learning_rate": 0.000320079822616408,
"loss": 0.6863,
"step": 155
},
{
"epoch": 1.0263736263736263,
"grad_norm": 0.4196075201034546,
"learning_rate": 0.000319019955654102,
"loss": 0.6962,
"step": 156
},
{
"epoch": 1.032967032967033,
"grad_norm": 0.3725369870662689,
"learning_rate": 0.000317960088691796,
"loss": 0.6477,
"step": 157
},
{
"epoch": 1.0395604395604396,
"grad_norm": 0.3431801497936249,
"learning_rate": 0.00031690022172949,
"loss": 0.7138,
"step": 158
},
{
"epoch": 1.0461538461538462,
"grad_norm": 0.352556973695755,
"learning_rate": 0.00031584035476718407,
"loss": 0.696,
"step": 159
},
{
"epoch": 1.0527472527472528,
"grad_norm": 0.3816937208175659,
"learning_rate": 0.00031478048780487805,
"loss": 0.6795,
"step": 160
},
{
"epoch": 1.0593406593406594,
"grad_norm": 0.3353464901447296,
"learning_rate": 0.0003137206208425721,
"loss": 0.6945,
"step": 161
},
{
"epoch": 1.065934065934066,
"grad_norm": 0.3413096070289612,
"learning_rate": 0.0003126607538802661,
"loss": 0.6986,
"step": 162
},
{
"epoch": 1.0725274725274725,
"grad_norm": 0.39247822761535645,
"learning_rate": 0.00031160088691796007,
"loss": 0.6975,
"step": 163
},
{
"epoch": 1.079120879120879,
"grad_norm": 0.37605905532836914,
"learning_rate": 0.0003105410199556541,
"loss": 0.6648,
"step": 164
},
{
"epoch": 1.0857142857142856,
"grad_norm": 0.3390028476715088,
"learning_rate": 0.00030948115299334815,
"loss": 0.6513,
"step": 165
},
{
"epoch": 1.0923076923076924,
"grad_norm": 0.3718453049659729,
"learning_rate": 0.00030842128603104213,
"loss": 0.6919,
"step": 166
},
{
"epoch": 1.098901098901099,
"grad_norm": 0.2975955307483673,
"learning_rate": 0.0003073614190687362,
"loss": 0.6299,
"step": 167
},
{
"epoch": 1.1054945054945056,
"grad_norm": 0.34555625915527344,
"learning_rate": 0.00030630155210643016,
"loss": 0.7005,
"step": 168
},
{
"epoch": 1.1120879120879121,
"grad_norm": 0.32412344217300415,
"learning_rate": 0.00030524168514412415,
"loss": 0.6203,
"step": 169
},
{
"epoch": 1.1186813186813187,
"grad_norm": 0.3432216942310333,
"learning_rate": 0.0003041818181818182,
"loss": 0.606,
"step": 170
},
{
"epoch": 1.1252747252747253,
"grad_norm": 0.3454482853412628,
"learning_rate": 0.00030312195121951223,
"loss": 0.6129,
"step": 171
},
{
"epoch": 1.1318681318681318,
"grad_norm": 0.44866660237312317,
"learning_rate": 0.0003020620842572062,
"loss": 0.6854,
"step": 172
},
{
"epoch": 1.1384615384615384,
"grad_norm": 0.4065716564655304,
"learning_rate": 0.00030100221729490026,
"loss": 0.7183,
"step": 173
},
{
"epoch": 1.145054945054945,
"grad_norm": 0.35473760962486267,
"learning_rate": 0.00029994235033259424,
"loss": 0.5937,
"step": 174
},
{
"epoch": 1.1516483516483516,
"grad_norm": 0.4422287940979004,
"learning_rate": 0.00029888248337028823,
"loss": 0.6083,
"step": 175
},
{
"epoch": 1.1582417582417581,
"grad_norm": 0.3578943908214569,
"learning_rate": 0.00029782261640798227,
"loss": 0.6769,
"step": 176
},
{
"epoch": 1.164835164835165,
"grad_norm": 0.3340145945549011,
"learning_rate": 0.0002967627494456763,
"loss": 0.644,
"step": 177
},
{
"epoch": 1.1714285714285715,
"grad_norm": 0.33603644371032715,
"learning_rate": 0.0002957028824833703,
"loss": 0.645,
"step": 178
},
{
"epoch": 1.178021978021978,
"grad_norm": 0.3559483289718628,
"learning_rate": 0.00029464301552106434,
"loss": 0.6179,
"step": 179
},
{
"epoch": 1.1846153846153846,
"grad_norm": 0.38981226086616516,
"learning_rate": 0.0002935831485587583,
"loss": 0.6229,
"step": 180
}
],
"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": 8.20362936627118e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}