jeqcho's picture
Upload folder using huggingface_hub
fe3cd0a verified
Raw
History Blame Contribute Delete
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": 0.9548422694206238,
"learning_rate": 0.0,
"loss": 2.456,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 0.9033191800117493,
"learning_rate": 4e-05,
"loss": 2.7771,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 0.9564813375473022,
"learning_rate": 8e-05,
"loss": 2.7839,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.4111387729644775,
"learning_rate": 0.00012,
"loss": 3.2357,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 1.9880008697509766,
"learning_rate": 0.00016,
"loss": 3.5809,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 2.1871581077575684,
"learning_rate": 0.0002,
"loss": 2.9169,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 2.0554776191711426,
"learning_rate": 0.00019955654101995565,
"loss": 2.1632,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 1.8138749599456787,
"learning_rate": 0.00019911308203991133,
"loss": 1.6378,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 1.0925194025039673,
"learning_rate": 0.00019866962305986697,
"loss": 1.157,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.8452661633491516,
"learning_rate": 0.00019822616407982261,
"loss": 1.11,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.9047808051109314,
"learning_rate": 0.00019778270509977829,
"loss": 0.903,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.8229642510414124,
"learning_rate": 0.00019733924611973393,
"loss": 0.923,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.6836701035499573,
"learning_rate": 0.0001968957871396896,
"loss": 0.7578,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.7976304292678833,
"learning_rate": 0.00019645232815964525,
"loss": 0.7888,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.5903546214103699,
"learning_rate": 0.00019600886917960092,
"loss": 0.7382,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.5188648104667664,
"learning_rate": 0.00019556541019955653,
"loss": 0.7559,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.43109938502311707,
"learning_rate": 0.0001951219512195122,
"loss": 0.6449,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.5063297748565674,
"learning_rate": 0.00019467849223946785,
"loss": 0.7978,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.48597580194473267,
"learning_rate": 0.00019423503325942352,
"loss": 0.7311,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.4553968906402588,
"learning_rate": 0.00019379157427937917,
"loss": 0.7349,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.4415663778781891,
"learning_rate": 0.00019334811529933484,
"loss": 0.5978,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.44407373666763306,
"learning_rate": 0.00019290465631929045,
"loss": 0.6434,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.4405691623687744,
"learning_rate": 0.00019246119733924613,
"loss": 0.6702,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.45118415355682373,
"learning_rate": 0.00019201773835920177,
"loss": 0.6987,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.4140220582485199,
"learning_rate": 0.00019157427937915744,
"loss": 0.739,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.3368533253669739,
"learning_rate": 0.00019113082039911309,
"loss": 0.6759,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.32022058963775635,
"learning_rate": 0.00019068736141906876,
"loss": 0.5563,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.30251631140708923,
"learning_rate": 0.0001902439024390244,
"loss": 0.5916,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.33803412318229675,
"learning_rate": 0.00018980044345898005,
"loss": 0.5178,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.3477880656719208,
"learning_rate": 0.00018935698447893572,
"loss": 0.7149,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.4316825568675995,
"learning_rate": 0.00018891352549889136,
"loss": 0.6876,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.3937191665172577,
"learning_rate": 0.00018847006651884703,
"loss": 0.6659,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.36258432269096375,
"learning_rate": 0.00018802660753880268,
"loss": 0.5481,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.4232417643070221,
"learning_rate": 0.00018758314855875832,
"loss": 0.6761,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.3215615749359131,
"learning_rate": 0.00018713968957871397,
"loss": 0.6068,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.3615092933177948,
"learning_rate": 0.00018669623059866964,
"loss": 0.5814,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.33303868770599365,
"learning_rate": 0.00018625277161862528,
"loss": 0.5659,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.34852537512779236,
"learning_rate": 0.00018580931263858095,
"loss": 0.5848,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.333442360162735,
"learning_rate": 0.0001853658536585366,
"loss": 0.5249,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.3381938636302948,
"learning_rate": 0.00018492239467849224,
"loss": 0.6407,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.3696731626987457,
"learning_rate": 0.0001844789356984479,
"loss": 0.6736,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.4098624587059021,
"learning_rate": 0.00018403547671840356,
"loss": 0.6643,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.3498683273792267,
"learning_rate": 0.0001835920177383592,
"loss": 0.5443,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.3131304383277893,
"learning_rate": 0.00018314855875831487,
"loss": 0.5232,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.39961516857147217,
"learning_rate": 0.00018270509977827052,
"loss": 0.7046,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.4616391360759735,
"learning_rate": 0.00018226164079822616,
"loss": 0.6706,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.38573798537254333,
"learning_rate": 0.00018181818181818183,
"loss": 0.6662,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.336185097694397,
"learning_rate": 0.00018137472283813748,
"loss": 0.5845,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.3926178216934204,
"learning_rate": 0.00018093126385809312,
"loss": 0.495,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.36642107367515564,
"learning_rate": 0.0001804878048780488,
"loss": 0.5075,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.4265896677970886,
"learning_rate": 0.00018004434589800444,
"loss": 0.6636,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.4908406436443329,
"learning_rate": 0.00017960088691796008,
"loss": 0.6943,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.3566623032093048,
"learning_rate": 0.00017915742793791575,
"loss": 0.5919,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.3888160288333893,
"learning_rate": 0.0001787139689578714,
"loss": 0.7048,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.3611518144607544,
"learning_rate": 0.00017827050997782707,
"loss": 0.505,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.3949228823184967,
"learning_rate": 0.00017782705099778271,
"loss": 0.6138,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.4875071942806244,
"learning_rate": 0.00017738359201773839,
"loss": 0.7643,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.44993212819099426,
"learning_rate": 0.000176940133037694,
"loss": 0.702,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.34542116522789,
"learning_rate": 0.00017649667405764967,
"loss": 0.5463,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.42165201902389526,
"learning_rate": 0.00017605321507760532,
"loss": 0.5946,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.3682475984096527,
"learning_rate": 0.000175609756097561,
"loss": 0.5548,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.36798593401908875,
"learning_rate": 0.00017516629711751663,
"loss": 0.3957,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.4413401186466217,
"learning_rate": 0.0001747228381374723,
"loss": 0.6863,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.4089689552783966,
"learning_rate": 0.00017427937915742792,
"loss": 0.5794,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.357327938079834,
"learning_rate": 0.0001738359201773836,
"loss": 0.5446,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.3936524987220764,
"learning_rate": 0.00017339246119733924,
"loss": 0.569,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.4308718144893646,
"learning_rate": 0.0001729490022172949,
"loss": 0.608,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.4803222417831421,
"learning_rate": 0.00017250554323725056,
"loss": 0.6635,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.4282255470752716,
"learning_rate": 0.00017206208425720623,
"loss": 0.5607,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.44135338068008423,
"learning_rate": 0.00017161862527716187,
"loss": 0.5048,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.5171645879745483,
"learning_rate": 0.00017117516629711752,
"loss": 0.6101,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.4031164348125458,
"learning_rate": 0.0001707317073170732,
"loss": 0.5566,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.35505273938179016,
"learning_rate": 0.00017028824833702883,
"loss": 0.6453,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.3494785726070404,
"learning_rate": 0.0001698447893569845,
"loss": 0.6731,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.4739617109298706,
"learning_rate": 0.00016940133037694015,
"loss": 0.5278,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.3757701814174652,
"learning_rate": 0.00016895787139689582,
"loss": 0.4467,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.4467487633228302,
"learning_rate": 0.00016851441241685144,
"loss": 0.6486,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.4626796543598175,
"learning_rate": 0.0001680709534368071,
"loss": 0.4425,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.4805651307106018,
"learning_rate": 0.00016762749445676275,
"loss": 0.532,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.6599902510643005,
"learning_rate": 0.00016718403547671842,
"loss": 0.6162,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.45104750990867615,
"learning_rate": 0.00016674057649667407,
"loss": 0.5708,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.4385611414909363,
"learning_rate": 0.00016629711751662974,
"loss": 0.5711,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.4250934422016144,
"learning_rate": 0.00016585365853658536,
"loss": 0.6049,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.4899722635746002,
"learning_rate": 0.00016541019955654103,
"loss": 0.6084,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.33061057329177856,
"learning_rate": 0.00016496674057649667,
"loss": 0.4669,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.4679504632949829,
"learning_rate": 0.00016452328159645234,
"loss": 0.643,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.32151514291763306,
"learning_rate": 0.000164079822616408,
"loss": 0.3998,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.3151485323905945,
"learning_rate": 0.00016363636363636366,
"loss": 0.468,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.3355564773082733,
"learning_rate": 0.0001631929046563193,
"loss": 0.4659,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.4314066469669342,
"learning_rate": 0.00016274944567627495,
"loss": 0.5191,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.37781575322151184,
"learning_rate": 0.0001623059866962306,
"loss": 0.5223,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.3945695757865906,
"learning_rate": 0.00016186252771618626,
"loss": 0.6548,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.39695677161216736,
"learning_rate": 0.0001614190687361419,
"loss": 0.5879,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.37342777848243713,
"learning_rate": 0.00016097560975609758,
"loss": 0.5142,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.4140840470790863,
"learning_rate": 0.00016053215077605322,
"loss": 0.5664,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.408898264169693,
"learning_rate": 0.00016008869179600887,
"loss": 0.4901,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.536078155040741,
"learning_rate": 0.00015964523281596454,
"loss": 0.6765,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.4385940134525299,
"learning_rate": 0.00015920177383592018,
"loss": 0.4839,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.40652719140052795,
"learning_rate": 0.00015875831485587586,
"loss": 0.5111,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.3607117533683777,
"learning_rate": 0.0001583148558758315,
"loss": 0.4711,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.4337385594844818,
"learning_rate": 0.00015787139689578714,
"loss": 0.5256,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.44065672159194946,
"learning_rate": 0.0001574279379157428,
"loss": 0.537,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.41281890869140625,
"learning_rate": 0.00015698447893569846,
"loss": 0.6817,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.43731898069381714,
"learning_rate": 0.0001565410199556541,
"loss": 0.5918,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.37266799807548523,
"learning_rate": 0.00015609756097560978,
"loss": 0.4624,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.5089952945709229,
"learning_rate": 0.00015565410199556542,
"loss": 0.5598,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.3849126398563385,
"learning_rate": 0.00015521064301552106,
"loss": 0.5541,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.38067758083343506,
"learning_rate": 0.0001547671840354767,
"loss": 0.3536,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.48663806915283203,
"learning_rate": 0.00015432372505543238,
"loss": 0.5676,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.4446583390235901,
"learning_rate": 0.00015388026607538802,
"loss": 0.5869,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.3267216384410858,
"learning_rate": 0.0001534368070953437,
"loss": 0.5256,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.51227867603302,
"learning_rate": 0.00015299334811529934,
"loss": 0.5383,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.41122210025787354,
"learning_rate": 0.00015254988913525498,
"loss": 0.5064,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.4868994653224945,
"learning_rate": 0.00015210643015521066,
"loss": 0.6346,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.46564382314682007,
"learning_rate": 0.0001516629711751663,
"loss": 0.5746,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.5163165330886841,
"learning_rate": 0.00015121951219512197,
"loss": 0.5524,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.3719719648361206,
"learning_rate": 0.00015077605321507762,
"loss": 0.6073,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.4514992833137512,
"learning_rate": 0.0001503325942350333,
"loss": 0.5236,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.4167504906654358,
"learning_rate": 0.0001498891352549889,
"loss": 0.5555,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.4539602994918823,
"learning_rate": 0.00014944567627494458,
"loss": 0.4845,
"step": 120
},
{
"epoch": 0.7978021978021979,
"grad_norm": 0.4488826096057892,
"learning_rate": 0.00014900221729490022,
"loss": 0.4869,
"step": 121
},
{
"epoch": 0.8043956043956044,
"grad_norm": 0.4719310402870178,
"learning_rate": 0.0001485587583148559,
"loss": 0.5128,
"step": 122
},
{
"epoch": 0.810989010989011,
"grad_norm": 0.4561479389667511,
"learning_rate": 0.00014811529933481154,
"loss": 0.6461,
"step": 123
},
{
"epoch": 0.8175824175824176,
"grad_norm": 0.386296808719635,
"learning_rate": 0.0001476718403547672,
"loss": 0.5113,
"step": 124
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.3054978847503662,
"learning_rate": 0.00014722838137472282,
"loss": 0.5141,
"step": 125
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.4869299829006195,
"learning_rate": 0.0001467849223946785,
"loss": 0.5434,
"step": 126
},
{
"epoch": 0.8373626373626374,
"grad_norm": 0.43943488597869873,
"learning_rate": 0.00014634146341463414,
"loss": 0.5831,
"step": 127
},
{
"epoch": 0.843956043956044,
"grad_norm": 0.4663369953632355,
"learning_rate": 0.0001458980044345898,
"loss": 0.5491,
"step": 128
},
{
"epoch": 0.8505494505494505,
"grad_norm": 0.4164719879627228,
"learning_rate": 0.00014545454545454546,
"loss": 0.5615,
"step": 129
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.4484899044036865,
"learning_rate": 0.00014501108647450113,
"loss": 0.4977,
"step": 130
},
{
"epoch": 0.8637362637362638,
"grad_norm": 0.4520849883556366,
"learning_rate": 0.00014456762749445675,
"loss": 0.5019,
"step": 131
},
{
"epoch": 0.8703296703296703,
"grad_norm": 0.5417237281799316,
"learning_rate": 0.00014412416851441242,
"loss": 0.6027,
"step": 132
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.4517190754413605,
"learning_rate": 0.00014368070953436806,
"loss": 0.3898,
"step": 133
},
{
"epoch": 0.8835164835164835,
"grad_norm": 0.46595922112464905,
"learning_rate": 0.00014323725055432373,
"loss": 0.5217,
"step": 134
},
{
"epoch": 0.8901098901098901,
"grad_norm": 0.42509788274765015,
"learning_rate": 0.00014279379157427938,
"loss": 0.5972,
"step": 135
},
{
"epoch": 0.8967032967032967,
"grad_norm": 0.4257327616214752,
"learning_rate": 0.00014235033259423505,
"loss": 0.4282,
"step": 136
},
{
"epoch": 0.9032967032967033,
"grad_norm": 0.5871689915657043,
"learning_rate": 0.0001419068736141907,
"loss": 0.6593,
"step": 137
},
{
"epoch": 0.9098901098901099,
"grad_norm": 0.29505041241645813,
"learning_rate": 0.00014146341463414634,
"loss": 0.4918,
"step": 138
},
{
"epoch": 0.9164835164835164,
"grad_norm": 0.3970448672771454,
"learning_rate": 0.000141019955654102,
"loss": 0.5234,
"step": 139
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.4519578218460083,
"learning_rate": 0.00014057649667405765,
"loss": 0.5396,
"step": 140
},
{
"epoch": 0.9296703296703297,
"grad_norm": 0.31789276003837585,
"learning_rate": 0.00014013303769401332,
"loss": 0.4215,
"step": 141
},
{
"epoch": 0.9362637362637363,
"grad_norm": 0.4112825393676758,
"learning_rate": 0.00013968957871396897,
"loss": 0.6616,
"step": 142
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.3623558580875397,
"learning_rate": 0.00013924611973392464,
"loss": 0.4341,
"step": 143
},
{
"epoch": 0.9494505494505494,
"grad_norm": 0.4286142587661743,
"learning_rate": 0.00013880266075388026,
"loss": 0.3684,
"step": 144
},
{
"epoch": 0.9560439560439561,
"grad_norm": 0.5302484631538391,
"learning_rate": 0.00013835920177383593,
"loss": 0.5972,
"step": 145
},
{
"epoch": 0.9626373626373627,
"grad_norm": 0.42222657799720764,
"learning_rate": 0.00013791574279379157,
"loss": 0.5068,
"step": 146
},
{
"epoch": 0.9692307692307692,
"grad_norm": 0.3991227149963379,
"learning_rate": 0.00013747228381374724,
"loss": 0.4817,
"step": 147
},
{
"epoch": 0.9758241758241758,
"grad_norm": 0.45304563641548157,
"learning_rate": 0.0001370288248337029,
"loss": 0.4327,
"step": 148
},
{
"epoch": 0.9824175824175824,
"grad_norm": 0.4595620036125183,
"learning_rate": 0.00013658536585365856,
"loss": 0.5759,
"step": 149
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.48510870337486267,
"learning_rate": 0.00013614190687361418,
"loss": 0.6115,
"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": 6.340651027212902e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}