jeqcho's picture
Upload folder using huggingface_hub
1fbed15 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": 1.1175572872161865,
"learning_rate": 0.0,
"loss": 3.0744,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 1.2595356702804565,
"learning_rate": 4e-05,
"loss": 3.3519,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 1.1831451654434204,
"learning_rate": 8e-05,
"loss": 3.4142,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.1135042905807495,
"learning_rate": 0.00012,
"loss": 2.8473,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 1.6986281871795654,
"learning_rate": 0.00016,
"loss": 3.1145,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 1.8996844291687012,
"learning_rate": 0.0002,
"loss": 2.7206,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 1.654848337173462,
"learning_rate": 0.00019955654101995565,
"loss": 1.6435,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 1.9960455894470215,
"learning_rate": 0.00019911308203991133,
"loss": 1.6488,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 1.1452784538269043,
"learning_rate": 0.00019866962305986697,
"loss": 1.2791,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.9133374094963074,
"learning_rate": 0.00019822616407982261,
"loss": 1.0621,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.7128933668136597,
"learning_rate": 0.00019778270509977829,
"loss": 0.8729,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.9738520383834839,
"learning_rate": 0.00019733924611973393,
"loss": 0.945,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 1.0968796014785767,
"learning_rate": 0.0001968957871396896,
"loss": 0.9219,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.8448852300643921,
"learning_rate": 0.00019645232815964525,
"loss": 0.7323,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.6533470153808594,
"learning_rate": 0.00019600886917960092,
"loss": 0.7965,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.5058298707008362,
"learning_rate": 0.00019556541019955653,
"loss": 0.7675,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.5244030952453613,
"learning_rate": 0.0001951219512195122,
"loss": 0.6938,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.5534260869026184,
"learning_rate": 0.00019467849223946785,
"loss": 0.7475,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.49227115511894226,
"learning_rate": 0.00019423503325942352,
"loss": 0.7782,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.6014466881752014,
"learning_rate": 0.00019379157427937917,
"loss": 0.6281,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.46302980184555054,
"learning_rate": 0.00019334811529933484,
"loss": 0.6085,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.3817231357097626,
"learning_rate": 0.00019290465631929045,
"loss": 0.4978,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.41959288716316223,
"learning_rate": 0.00019246119733924613,
"loss": 0.7479,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.37861549854278564,
"learning_rate": 0.00019201773835920177,
"loss": 0.5145,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.41947174072265625,
"learning_rate": 0.00019157427937915744,
"loss": 0.6564,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.43568453192710876,
"learning_rate": 0.00019113082039911309,
"loss": 0.7639,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.35360434651374817,
"learning_rate": 0.00019068736141906876,
"loss": 0.7617,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.43759599328041077,
"learning_rate": 0.0001902439024390244,
"loss": 0.6815,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.3009309470653534,
"learning_rate": 0.00018980044345898005,
"loss": 0.5048,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.37697890400886536,
"learning_rate": 0.00018935698447893572,
"loss": 0.5197,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.36582183837890625,
"learning_rate": 0.00018891352549889136,
"loss": 0.4953,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.4371263384819031,
"learning_rate": 0.00018847006651884703,
"loss": 0.6357,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.35323941707611084,
"learning_rate": 0.00018802660753880268,
"loss": 0.6407,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.4218985438346863,
"learning_rate": 0.00018758314855875832,
"loss": 0.6067,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.4576883614063263,
"learning_rate": 0.00018713968957871397,
"loss": 0.7649,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.3939562737941742,
"learning_rate": 0.00018669623059866964,
"loss": 0.7539,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.3907439112663269,
"learning_rate": 0.00018625277161862528,
"loss": 0.6574,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.34653839468955994,
"learning_rate": 0.00018580931263858095,
"loss": 0.4845,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.30807438492774963,
"learning_rate": 0.0001853658536585366,
"loss": 0.5046,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.3422587811946869,
"learning_rate": 0.00018492239467849224,
"loss": 0.642,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.4083802103996277,
"learning_rate": 0.0001844789356984479,
"loss": 0.6177,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.3902239203453064,
"learning_rate": 0.00018403547671840356,
"loss": 0.6883,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.413637638092041,
"learning_rate": 0.0001835920177383592,
"loss": 0.5178,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.3305671513080597,
"learning_rate": 0.00018314855875831487,
"loss": 0.4925,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.3556175231933594,
"learning_rate": 0.00018270509977827052,
"loss": 0.4991,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.3833027482032776,
"learning_rate": 0.00018226164079822616,
"loss": 0.5837,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.34828928112983704,
"learning_rate": 0.00018181818181818183,
"loss": 0.4893,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.4020296335220337,
"learning_rate": 0.00018137472283813748,
"loss": 0.4792,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.47377222776412964,
"learning_rate": 0.00018093126385809312,
"loss": 0.5776,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.47716471552848816,
"learning_rate": 0.0001804878048780488,
"loss": 0.6295,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.4160218834877014,
"learning_rate": 0.00018004434589800444,
"loss": 0.5249,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.3925120234489441,
"learning_rate": 0.00017960088691796008,
"loss": 0.5979,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.451288104057312,
"learning_rate": 0.00017915742793791575,
"loss": 0.7045,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.44237250089645386,
"learning_rate": 0.0001787139689578714,
"loss": 0.6288,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.37273454666137695,
"learning_rate": 0.00017827050997782707,
"loss": 0.5214,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.4249885380268097,
"learning_rate": 0.00017782705099778271,
"loss": 0.6523,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.4397568702697754,
"learning_rate": 0.00017738359201773839,
"loss": 0.7857,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.37436991930007935,
"learning_rate": 0.000176940133037694,
"loss": 0.5266,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.3295058310031891,
"learning_rate": 0.00017649667405764967,
"loss": 0.5685,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.3959578275680542,
"learning_rate": 0.00017605321507760532,
"loss": 0.4584,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.37387439608573914,
"learning_rate": 0.000175609756097561,
"loss": 0.5703,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.28911006450653076,
"learning_rate": 0.00017516629711751663,
"loss": 0.4591,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.6077892184257507,
"learning_rate": 0.0001747228381374723,
"loss": 0.7229,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.44933897256851196,
"learning_rate": 0.00017427937915742792,
"loss": 0.4895,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.4583057463169098,
"learning_rate": 0.0001738359201773836,
"loss": 0.5422,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.441131055355072,
"learning_rate": 0.00017339246119733924,
"loss": 0.5039,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.37214893102645874,
"learning_rate": 0.0001729490022172949,
"loss": 0.4451,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.37915486097335815,
"learning_rate": 0.00017250554323725056,
"loss": 0.5498,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.43058085441589355,
"learning_rate": 0.00017206208425720623,
"loss": 0.6258,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.4087371528148651,
"learning_rate": 0.00017161862527716187,
"loss": 0.4304,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.3702792525291443,
"learning_rate": 0.00017117516629711752,
"loss": 0.5061,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.40271690487861633,
"learning_rate": 0.0001707317073170732,
"loss": 0.5221,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.4654999077320099,
"learning_rate": 0.00017028824833702883,
"loss": 0.5427,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.422850638628006,
"learning_rate": 0.0001698447893569845,
"loss": 0.5003,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.35233739018440247,
"learning_rate": 0.00016940133037694015,
"loss": 0.5353,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.3508605659008026,
"learning_rate": 0.00016895787139689582,
"loss": 0.5011,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.35129278898239136,
"learning_rate": 0.00016851441241685144,
"loss": 0.5396,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.4907684922218323,
"learning_rate": 0.0001680709534368071,
"loss": 0.5464,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.3281923234462738,
"learning_rate": 0.00016762749445676275,
"loss": 0.5209,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.444183349609375,
"learning_rate": 0.00016718403547671842,
"loss": 0.7176,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.5929686427116394,
"learning_rate": 0.00016674057649667407,
"loss": 0.6389,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.40402573347091675,
"learning_rate": 0.00016629711751662974,
"loss": 0.4612,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.4387584626674652,
"learning_rate": 0.00016585365853658536,
"loss": 0.4967,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.3580304682254791,
"learning_rate": 0.00016541019955654103,
"loss": 0.5834,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.5472170114517212,
"learning_rate": 0.00016496674057649667,
"loss": 0.5454,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.4298936426639557,
"learning_rate": 0.00016452328159645234,
"loss": 0.4903,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.428013414144516,
"learning_rate": 0.000164079822616408,
"loss": 0.5407,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.4182053506374359,
"learning_rate": 0.00016363636363636366,
"loss": 0.5558,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.3617396652698517,
"learning_rate": 0.0001631929046563193,
"loss": 0.4448,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.35693031549453735,
"learning_rate": 0.00016274944567627495,
"loss": 0.5425,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.3613317012786865,
"learning_rate": 0.0001623059866962306,
"loss": 0.4412,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.417049765586853,
"learning_rate": 0.00016186252771618626,
"loss": 0.5735,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.43856459856033325,
"learning_rate": 0.0001614190687361419,
"loss": 0.4225,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.47907739877700806,
"learning_rate": 0.00016097560975609758,
"loss": 0.502,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.36149153113365173,
"learning_rate": 0.00016053215077605322,
"loss": 0.4725,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.4654827117919922,
"learning_rate": 0.00016008869179600887,
"loss": 0.5749,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.4263451397418976,
"learning_rate": 0.00015964523281596454,
"loss": 0.5116,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.44888293743133545,
"learning_rate": 0.00015920177383592018,
"loss": 0.5232,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.5640338659286499,
"learning_rate": 0.00015875831485587586,
"loss": 0.7007,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.4415484070777893,
"learning_rate": 0.0001583148558758315,
"loss": 0.3907,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.473460853099823,
"learning_rate": 0.00015787139689578714,
"loss": 0.55,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.5150168538093567,
"learning_rate": 0.0001574279379157428,
"loss": 0.5257,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.3559170365333557,
"learning_rate": 0.00015698447893569846,
"loss": 0.4953,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.3546290099620819,
"learning_rate": 0.0001565410199556541,
"loss": 0.5694,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.4086984395980835,
"learning_rate": 0.00015609756097560978,
"loss": 0.4952,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.4047616422176361,
"learning_rate": 0.00015565410199556542,
"loss": 0.4458,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.35968494415283203,
"learning_rate": 0.00015521064301552106,
"loss": 0.4463,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.42160969972610474,
"learning_rate": 0.0001547671840354767,
"loss": 0.5333,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.49412330985069275,
"learning_rate": 0.00015432372505543238,
"loss": 0.6404,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.4050638675689697,
"learning_rate": 0.00015388026607538802,
"loss": 0.5419,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.3907662034034729,
"learning_rate": 0.0001534368070953437,
"loss": 0.5049,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.36140918731689453,
"learning_rate": 0.00015299334811529934,
"loss": 0.4011,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.38780495524406433,
"learning_rate": 0.00015254988913525498,
"loss": 0.5795,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 1.2969988584518433,
"learning_rate": 0.00015210643015521066,
"loss": 0.5652,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.41087356209754944,
"learning_rate": 0.0001516629711751663,
"loss": 0.5451,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.351934015750885,
"learning_rate": 0.00015121951219512197,
"loss": 0.5072,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.3761547803878784,
"learning_rate": 0.00015077605321507762,
"loss": 0.4851,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.38351503014564514,
"learning_rate": 0.0001503325942350333,
"loss": 0.479,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.3756462037563324,
"learning_rate": 0.0001498891352549889,
"loss": 0.4348,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.42825978994369507,
"learning_rate": 0.00014944567627494458,
"loss": 0.6265,
"step": 120
},
{
"epoch": 0.7978021978021979,
"grad_norm": 0.40038374066352844,
"learning_rate": 0.00014900221729490022,
"loss": 0.4257,
"step": 121
},
{
"epoch": 0.8043956043956044,
"grad_norm": 0.40185239911079407,
"learning_rate": 0.0001485587583148559,
"loss": 0.4819,
"step": 122
},
{
"epoch": 0.810989010989011,
"grad_norm": 0.3839464485645294,
"learning_rate": 0.00014811529933481154,
"loss": 0.4153,
"step": 123
},
{
"epoch": 0.8175824175824176,
"grad_norm": 0.4148792624473572,
"learning_rate": 0.0001476718403547672,
"loss": 0.5652,
"step": 124
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.37263253331184387,
"learning_rate": 0.00014722838137472282,
"loss": 0.619,
"step": 125
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.4481087327003479,
"learning_rate": 0.0001467849223946785,
"loss": 0.5542,
"step": 126
},
{
"epoch": 0.8373626373626374,
"grad_norm": 0.39149171113967896,
"learning_rate": 0.00014634146341463414,
"loss": 0.5478,
"step": 127
},
{
"epoch": 0.843956043956044,
"grad_norm": 0.3571181297302246,
"learning_rate": 0.0001458980044345898,
"loss": 0.5864,
"step": 128
},
{
"epoch": 0.8505494505494505,
"grad_norm": 0.3801731765270233,
"learning_rate": 0.00014545454545454546,
"loss": 0.5381,
"step": 129
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.3862723708152771,
"learning_rate": 0.00014501108647450113,
"loss": 0.4461,
"step": 130
},
{
"epoch": 0.8637362637362638,
"grad_norm": 0.36548087000846863,
"learning_rate": 0.00014456762749445675,
"loss": 0.5404,
"step": 131
},
{
"epoch": 0.8703296703296703,
"grad_norm": 0.3452293276786804,
"learning_rate": 0.00014412416851441242,
"loss": 0.4019,
"step": 132
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.3497912287712097,
"learning_rate": 0.00014368070953436806,
"loss": 0.5098,
"step": 133
},
{
"epoch": 0.8835164835164835,
"grad_norm": 0.35823172330856323,
"learning_rate": 0.00014323725055432373,
"loss": 0.5005,
"step": 134
},
{
"epoch": 0.8901098901098901,
"grad_norm": 0.4362906217575073,
"learning_rate": 0.00014279379157427938,
"loss": 0.4726,
"step": 135
},
{
"epoch": 0.8967032967032967,
"grad_norm": 0.38212844729423523,
"learning_rate": 0.00014235033259423505,
"loss": 0.5083,
"step": 136
},
{
"epoch": 0.9032967032967033,
"grad_norm": 0.40376564860343933,
"learning_rate": 0.0001419068736141907,
"loss": 0.4904,
"step": 137
},
{
"epoch": 0.9098901098901099,
"grad_norm": 0.38468191027641296,
"learning_rate": 0.00014146341463414634,
"loss": 0.5085,
"step": 138
},
{
"epoch": 0.9164835164835164,
"grad_norm": 0.4096522629261017,
"learning_rate": 0.000141019955654102,
"loss": 0.4871,
"step": 139
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.4750652313232422,
"learning_rate": 0.00014057649667405765,
"loss": 0.4523,
"step": 140
},
{
"epoch": 0.9296703296703297,
"grad_norm": 0.3995967507362366,
"learning_rate": 0.00014013303769401332,
"loss": 0.5426,
"step": 141
},
{
"epoch": 0.9362637362637363,
"grad_norm": 0.3848707675933838,
"learning_rate": 0.00013968957871396897,
"loss": 0.4811,
"step": 142
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.36099928617477417,
"learning_rate": 0.00013924611973392464,
"loss": 0.4182,
"step": 143
},
{
"epoch": 0.9494505494505494,
"grad_norm": 0.47264882922172546,
"learning_rate": 0.00013880266075388026,
"loss": 0.3971,
"step": 144
},
{
"epoch": 0.9560439560439561,
"grad_norm": 0.41076722741127014,
"learning_rate": 0.00013835920177383593,
"loss": 0.5617,
"step": 145
},
{
"epoch": 0.9626373626373627,
"grad_norm": 0.2651715874671936,
"learning_rate": 0.00013791574279379157,
"loss": 0.4181,
"step": 146
},
{
"epoch": 0.9692307692307692,
"grad_norm": 0.3821229338645935,
"learning_rate": 0.00013747228381374724,
"loss": 0.3827,
"step": 147
},
{
"epoch": 0.9758241758241758,
"grad_norm": 0.3557185232639313,
"learning_rate": 0.0001370288248337029,
"loss": 0.3979,
"step": 148
},
{
"epoch": 0.9824175824175824,
"grad_norm": 0.37807080149650574,
"learning_rate": 0.00013658536585365856,
"loss": 0.5276,
"step": 149
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.3489227294921875,
"learning_rate": 0.00013614190687361418,
"loss": 0.4667,
"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": 6.141098778419405e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}