jeqcho's picture
Upload folder using huggingface_hub
b9de780 verified
Raw
History Blame
21.5 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7912087912087912,
"eval_steps": 500,
"global_step": 120,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 0.9058706164360046,
"learning_rate": 0.0,
"loss": 2.6592,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 1.219626784324646,
"learning_rate": 4e-05,
"loss": 3.1435,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 1.0091753005981445,
"learning_rate": 8e-05,
"loss": 2.7687,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.2226085662841797,
"learning_rate": 0.00012,
"loss": 2.7522,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 1.5870455503463745,
"learning_rate": 0.00016,
"loss": 2.9693,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 1.2248976230621338,
"learning_rate": 0.0002,
"loss": 1.9829,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 1.9660221338272095,
"learning_rate": 0.00019955654101995565,
"loss": 2.1591,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 1.6100647449493408,
"learning_rate": 0.00019911308203991133,
"loss": 1.6047,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 2.6327474117279053,
"learning_rate": 0.00019866962305986697,
"loss": 1.2919,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 1.0000981092453003,
"learning_rate": 0.00019822616407982261,
"loss": 1.2185,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 1.1878960132598877,
"learning_rate": 0.00019778270509977829,
"loss": 1.1615,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 1.0137351751327515,
"learning_rate": 0.00019733924611973393,
"loss": 1.0325,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.7761878967285156,
"learning_rate": 0.0001968957871396896,
"loss": 1.1103,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.6137439012527466,
"learning_rate": 0.00019645232815964525,
"loss": 0.8803,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.529127836227417,
"learning_rate": 0.00019600886917960092,
"loss": 0.7937,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.44533517956733704,
"learning_rate": 0.00019556541019955653,
"loss": 0.7276,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.5100841522216797,
"learning_rate": 0.0001951219512195122,
"loss": 0.8415,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.4358687996864319,
"learning_rate": 0.00019467849223946785,
"loss": 0.6406,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.4740825295448303,
"learning_rate": 0.00019423503325942352,
"loss": 0.7853,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.4259636104106903,
"learning_rate": 0.00019379157427937917,
"loss": 0.8089,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.42271819710731506,
"learning_rate": 0.00019334811529933484,
"loss": 0.7404,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.37292444705963135,
"learning_rate": 0.00019290465631929045,
"loss": 0.6191,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.39097458124160767,
"learning_rate": 0.00019246119733924613,
"loss": 0.8551,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.44129955768585205,
"learning_rate": 0.00019201773835920177,
"loss": 0.794,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.33836016058921814,
"learning_rate": 0.00019157427937915744,
"loss": 0.7167,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.3723263442516327,
"learning_rate": 0.00019113082039911309,
"loss": 0.6662,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.38374266028404236,
"learning_rate": 0.00019068736141906876,
"loss": 0.7065,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.280962198972702,
"learning_rate": 0.0001902439024390244,
"loss": 0.613,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.2813490033149719,
"learning_rate": 0.00018980044345898005,
"loss": 0.5334,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.3661186099052429,
"learning_rate": 0.00018935698447893572,
"loss": 0.6754,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.39945557713508606,
"learning_rate": 0.00018891352549889136,
"loss": 0.6044,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.37376123666763306,
"learning_rate": 0.00018847006651884703,
"loss": 0.6617,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.419382244348526,
"learning_rate": 0.00018802660753880268,
"loss": 0.6897,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.4468085765838623,
"learning_rate": 0.00018758314855875832,
"loss": 0.6385,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.34990063309669495,
"learning_rate": 0.00018713968957871397,
"loss": 0.6188,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.33336585760116577,
"learning_rate": 0.00018669623059866964,
"loss": 0.5363,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.44632357358932495,
"learning_rate": 0.00018625277161862528,
"loss": 0.7779,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.40058109164237976,
"learning_rate": 0.00018580931263858095,
"loss": 0.655,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.6219450831413269,
"learning_rate": 0.0001853658536585366,
"loss": 0.6118,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.3633034825325012,
"learning_rate": 0.00018492239467849224,
"loss": 0.5482,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.4150526225566864,
"learning_rate": 0.0001844789356984479,
"loss": 0.7125,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.3828578591346741,
"learning_rate": 0.00018403547671840356,
"loss": 0.5939,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.3500871956348419,
"learning_rate": 0.0001835920177383592,
"loss": 0.7746,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.3674778640270233,
"learning_rate": 0.00018314855875831487,
"loss": 0.6894,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.362627774477005,
"learning_rate": 0.00018270509977827052,
"loss": 0.6434,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.37107113003730774,
"learning_rate": 0.00018226164079822616,
"loss": 0.4993,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.3172447681427002,
"learning_rate": 0.00018181818181818183,
"loss": 0.555,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.3316763639450073,
"learning_rate": 0.00018137472283813748,
"loss": 0.5874,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.35375964641571045,
"learning_rate": 0.00018093126385809312,
"loss": 0.6978,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.4692983031272888,
"learning_rate": 0.0001804878048780488,
"loss": 0.6987,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.363521009683609,
"learning_rate": 0.00018004434589800444,
"loss": 0.5867,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.4793933928012848,
"learning_rate": 0.00017960088691796008,
"loss": 0.6129,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.3823592960834503,
"learning_rate": 0.00017915742793791575,
"loss": 0.6144,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.4127606749534607,
"learning_rate": 0.0001787139689578714,
"loss": 0.6742,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.37317946553230286,
"learning_rate": 0.00017827050997782707,
"loss": 0.508,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.4024200439453125,
"learning_rate": 0.00017782705099778271,
"loss": 0.6188,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.3430168628692627,
"learning_rate": 0.00017738359201773839,
"loss": 0.5028,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.34839069843292236,
"learning_rate": 0.000176940133037694,
"loss": 0.5424,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.42866602540016174,
"learning_rate": 0.00017649667405764967,
"loss": 0.6811,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.3768810033798218,
"learning_rate": 0.00017605321507760532,
"loss": 0.5579,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.3702148497104645,
"learning_rate": 0.000175609756097561,
"loss": 0.7605,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.3371511697769165,
"learning_rate": 0.00017516629711751663,
"loss": 0.5193,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.47222787141799927,
"learning_rate": 0.0001747228381374723,
"loss": 0.6252,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.5072468519210815,
"learning_rate": 0.00017427937915742792,
"loss": 0.8734,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.3626039922237396,
"learning_rate": 0.0001738359201773836,
"loss": 0.5178,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.4846837818622589,
"learning_rate": 0.00017339246119733924,
"loss": 0.4895,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.4155651330947876,
"learning_rate": 0.0001729490022172949,
"loss": 0.763,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.4719211757183075,
"learning_rate": 0.00017250554323725056,
"loss": 0.5307,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.42008718848228455,
"learning_rate": 0.00017206208425720623,
"loss": 0.5896,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.46930480003356934,
"learning_rate": 0.00017161862527716187,
"loss": 0.7034,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.38539618253707886,
"learning_rate": 0.00017117516629711752,
"loss": 0.5653,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.3295809328556061,
"learning_rate": 0.0001707317073170732,
"loss": 0.4109,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.35690838098526,
"learning_rate": 0.00017028824833702883,
"loss": 0.5478,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.3013554513454437,
"learning_rate": 0.0001698447893569845,
"loss": 0.44,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.4589758813381195,
"learning_rate": 0.00016940133037694015,
"loss": 0.6521,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.3709176778793335,
"learning_rate": 0.00016895787139689582,
"loss": 0.5086,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.418459415435791,
"learning_rate": 0.00016851441241685144,
"loss": 0.6077,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.3665759563446045,
"learning_rate": 0.0001680709534368071,
"loss": 0.4976,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.42736196517944336,
"learning_rate": 0.00016762749445676275,
"loss": 0.567,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.40261924266815186,
"learning_rate": 0.00016718403547671842,
"loss": 0.5513,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.3527747094631195,
"learning_rate": 0.00016674057649667407,
"loss": 0.5328,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.34639862179756165,
"learning_rate": 0.00016629711751662974,
"loss": 0.5172,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.36874815821647644,
"learning_rate": 0.00016585365853658536,
"loss": 0.3959,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.43388038873672485,
"learning_rate": 0.00016541019955654103,
"loss": 0.5426,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.3631628453731537,
"learning_rate": 0.00016496674057649667,
"loss": 0.5244,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.37413424253463745,
"learning_rate": 0.00016452328159645234,
"loss": 0.5704,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.41879546642303467,
"learning_rate": 0.000164079822616408,
"loss": 0.5793,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.3621118664741516,
"learning_rate": 0.00016363636363636366,
"loss": 0.5442,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.45643946528434753,
"learning_rate": 0.0001631929046563193,
"loss": 0.8116,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.3559912443161011,
"learning_rate": 0.00016274944567627495,
"loss": 0.5546,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.5008060336112976,
"learning_rate": 0.0001623059866962306,
"loss": 0.581,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.37355196475982666,
"learning_rate": 0.00016186252771618626,
"loss": 0.4637,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.3737070858478546,
"learning_rate": 0.0001614190687361419,
"loss": 0.5034,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.394748330116272,
"learning_rate": 0.00016097560975609758,
"loss": 0.5049,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.38985559344291687,
"learning_rate": 0.00016053215077605322,
"loss": 0.5347,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.3751285970211029,
"learning_rate": 0.00016008869179600887,
"loss": 0.4733,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.5150198936462402,
"learning_rate": 0.00015964523281596454,
"loss": 0.619,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.3533032238483429,
"learning_rate": 0.00015920177383592018,
"loss": 0.5024,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.4514521062374115,
"learning_rate": 0.00015875831485587586,
"loss": 0.5868,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.37845054268836975,
"learning_rate": 0.0001583148558758315,
"loss": 0.4635,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.49906760454177856,
"learning_rate": 0.00015787139689578714,
"loss": 0.545,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.42360034584999084,
"learning_rate": 0.0001574279379157428,
"loss": 0.5881,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.3848630487918854,
"learning_rate": 0.00015698447893569846,
"loss": 0.4289,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.43491026759147644,
"learning_rate": 0.0001565410199556541,
"loss": 0.5486,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.4626753032207489,
"learning_rate": 0.00015609756097560978,
"loss": 0.5634,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.40432143211364746,
"learning_rate": 0.00015565410199556542,
"loss": 0.5414,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.3656046688556671,
"learning_rate": 0.00015521064301552106,
"loss": 0.5293,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.38330209255218506,
"learning_rate": 0.0001547671840354767,
"loss": 0.6344,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.5870491862297058,
"learning_rate": 0.00015432372505543238,
"loss": 0.7264,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.4007914960384369,
"learning_rate": 0.00015388026607538802,
"loss": 0.3698,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.4824475347995758,
"learning_rate": 0.0001534368070953437,
"loss": 0.651,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.4099094569683075,
"learning_rate": 0.00015299334811529934,
"loss": 0.5062,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.3784629702568054,
"learning_rate": 0.00015254988913525498,
"loss": 0.5569,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.5365519523620605,
"learning_rate": 0.00015210643015521066,
"loss": 0.6492,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.3854978084564209,
"learning_rate": 0.0001516629711751663,
"loss": 0.5107,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.3853599429130554,
"learning_rate": 0.00015121951219512197,
"loss": 0.683,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.3824496865272522,
"learning_rate": 0.00015077605321507762,
"loss": 0.5041,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.4500579833984375,
"learning_rate": 0.0001503325942350333,
"loss": 0.4954,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.43113070726394653,
"learning_rate": 0.0001498891352549889,
"loss": 0.5647,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.4825321435928345,
"learning_rate": 0.00014944567627494458,
"loss": 0.5008,
"step": 120
}
],
"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": 5.050300510389658e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}