jeqcho's picture
Upload folder using huggingface_hub
1cbb7ba 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": 1.6434824466705322,
"learning_rate": 0.0,
"loss": 2.5324,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 1.5169517993927002,
"learning_rate": 4e-05,
"loss": 2.4298,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 2.1552116870880127,
"learning_rate": 8e-05,
"loss": 3.6751,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.7675827741622925,
"learning_rate": 0.00012,
"loss": 2.6287,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 1.9941221475601196,
"learning_rate": 0.00016,
"loss": 2.4341,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 2.577136516571045,
"learning_rate": 0.0002,
"loss": 2.3798,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 2.411424398422241,
"learning_rate": 0.00019955654101995565,
"loss": 1.8769,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 1.9915826320648193,
"learning_rate": 0.00019911308203991133,
"loss": 1.671,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 0.7537499070167542,
"learning_rate": 0.00019866962305986697,
"loss": 1.2368,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 1.5307854413986206,
"learning_rate": 0.00019822616407982261,
"loss": 1.2651,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 1.0386676788330078,
"learning_rate": 0.00019778270509977829,
"loss": 1.3088,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.5621629953384399,
"learning_rate": 0.00019733924611973393,
"loss": 1.1189,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.6583429574966431,
"learning_rate": 0.0001968957871396896,
"loss": 1.1157,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.45013824105262756,
"learning_rate": 0.00019645232815964525,
"loss": 0.9839,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.44181209802627563,
"learning_rate": 0.00019600886917960092,
"loss": 1.4493,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.3815290033817291,
"learning_rate": 0.00019556541019955653,
"loss": 0.9192,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.3356572985649109,
"learning_rate": 0.0001951219512195122,
"loss": 1.1357,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.31392374634742737,
"learning_rate": 0.00019467849223946785,
"loss": 1.0106,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.5165255069732666,
"learning_rate": 0.00019423503325942352,
"loss": 1.0717,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.32307010889053345,
"learning_rate": 0.00019379157427937917,
"loss": 1.0066,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.38696736097335815,
"learning_rate": 0.00019334811529933484,
"loss": 1.0178,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.45919156074523926,
"learning_rate": 0.00019290465631929045,
"loss": 1.3634,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.3402266800403595,
"learning_rate": 0.00019246119733924613,
"loss": 1.0087,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.2613711655139923,
"learning_rate": 0.00019201773835920177,
"loss": 0.8385,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.35281801223754883,
"learning_rate": 0.00019157427937915744,
"loss": 0.9981,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.347657710313797,
"learning_rate": 0.00019113082039911309,
"loss": 1.097,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.2869630455970764,
"learning_rate": 0.00019068736141906876,
"loss": 0.8232,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.33703890442848206,
"learning_rate": 0.0001902439024390244,
"loss": 1.0008,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.32335910201072693,
"learning_rate": 0.00018980044345898005,
"loss": 1.0167,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.26683419942855835,
"learning_rate": 0.00018935698447893572,
"loss": 0.788,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.32632026076316833,
"learning_rate": 0.00018891352549889136,
"loss": 0.9766,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.4012938439846039,
"learning_rate": 0.00018847006651884703,
"loss": 1.1352,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.2666340470314026,
"learning_rate": 0.00018802660753880268,
"loss": 0.7854,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.31724995374679565,
"learning_rate": 0.00018758314855875832,
"loss": 1.131,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.35468608140945435,
"learning_rate": 0.00018713968957871397,
"loss": 0.824,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.29676058888435364,
"learning_rate": 0.00018669623059866964,
"loss": 0.9068,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.3603779077529907,
"learning_rate": 0.00018625277161862528,
"loss": 1.0625,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.28585994243621826,
"learning_rate": 0.00018580931263858095,
"loss": 0.96,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.3147846758365631,
"learning_rate": 0.0001853658536585366,
"loss": 1.0241,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.365302175283432,
"learning_rate": 0.00018492239467849224,
"loss": 1.2389,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.29522451758384705,
"learning_rate": 0.0001844789356984479,
"loss": 0.7442,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.2930554449558258,
"learning_rate": 0.00018403547671840356,
"loss": 1.115,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.31714215874671936,
"learning_rate": 0.0001835920177383592,
"loss": 0.9953,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.3149819076061249,
"learning_rate": 0.00018314855875831487,
"loss": 1.0285,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.2990363836288452,
"learning_rate": 0.00018270509977827052,
"loss": 1.0126,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.2756856083869934,
"learning_rate": 0.00018226164079822616,
"loss": 0.9699,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.3523540794849396,
"learning_rate": 0.00018181818181818183,
"loss": 1.1403,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.28931504487991333,
"learning_rate": 0.00018137472283813748,
"loss": 0.9127,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.25859928131103516,
"learning_rate": 0.00018093126385809312,
"loss": 0.827,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.30126574635505676,
"learning_rate": 0.0001804878048780488,
"loss": 0.975,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.31548774242401123,
"learning_rate": 0.00018004434589800444,
"loss": 0.9585,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.353438138961792,
"learning_rate": 0.00017960088691796008,
"loss": 0.9411,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.30521494150161743,
"learning_rate": 0.00017915742793791575,
"loss": 0.8952,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.3431454598903656,
"learning_rate": 0.0001787139689578714,
"loss": 0.7917,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.2956169545650482,
"learning_rate": 0.00017827050997782707,
"loss": 1.0781,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.3299672603607178,
"learning_rate": 0.00017782705099778271,
"loss": 1.0668,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.2662365734577179,
"learning_rate": 0.00017738359201773839,
"loss": 0.9365,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.34422916173934937,
"learning_rate": 0.000176940133037694,
"loss": 0.9569,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.3445512354373932,
"learning_rate": 0.00017649667405764967,
"loss": 0.9401,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.2959913909435272,
"learning_rate": 0.00017605321507760532,
"loss": 0.9567,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.38244959712028503,
"learning_rate": 0.000175609756097561,
"loss": 1.0616,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.262168824672699,
"learning_rate": 0.00017516629711751663,
"loss": 0.8975,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.3406493067741394,
"learning_rate": 0.0001747228381374723,
"loss": 1.0175,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.31124845147132874,
"learning_rate": 0.00017427937915742792,
"loss": 1.0236,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.2719510793685913,
"learning_rate": 0.0001738359201773836,
"loss": 0.9587,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.3550527095794678,
"learning_rate": 0.00017339246119733924,
"loss": 0.947,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.30880212783813477,
"learning_rate": 0.0001729490022172949,
"loss": 0.7273,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.293490469455719,
"learning_rate": 0.00017250554323725056,
"loss": 0.8787,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.3188346028327942,
"learning_rate": 0.00017206208425720623,
"loss": 0.9462,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.30488207936286926,
"learning_rate": 0.00017161862527716187,
"loss": 0.8909,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.3669050931930542,
"learning_rate": 0.00017117516629711752,
"loss": 0.7724,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.34658676385879517,
"learning_rate": 0.0001707317073170732,
"loss": 1.0216,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.34964701533317566,
"learning_rate": 0.00017028824833702883,
"loss": 0.8537,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.27874794602394104,
"learning_rate": 0.0001698447893569845,
"loss": 0.9198,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.3259141147136688,
"learning_rate": 0.00016940133037694015,
"loss": 1.0472,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.30889272689819336,
"learning_rate": 0.00016895787139689582,
"loss": 0.9495,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.26667729020118713,
"learning_rate": 0.00016851441241685144,
"loss": 0.9594,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.43131670355796814,
"learning_rate": 0.0001680709534368071,
"loss": 0.9616,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.37081974744796753,
"learning_rate": 0.00016762749445676275,
"loss": 0.949,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.3411784768104553,
"learning_rate": 0.00016718403547671842,
"loss": 0.9533,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.35899344086647034,
"learning_rate": 0.00016674057649667407,
"loss": 0.7617,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.32060304284095764,
"learning_rate": 0.00016629711751662974,
"loss": 1.1515,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.3621525764465332,
"learning_rate": 0.00016585365853658536,
"loss": 1.1095,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.3007383346557617,
"learning_rate": 0.00016541019955654103,
"loss": 0.8155,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.4037930965423584,
"learning_rate": 0.00016496674057649667,
"loss": 1.1333,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.31922397017478943,
"learning_rate": 0.00016452328159645234,
"loss": 0.911,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.317917138338089,
"learning_rate": 0.000164079822616408,
"loss": 0.8599,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.4045136570930481,
"learning_rate": 0.00016363636363636366,
"loss": 0.9552,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.37755998969078064,
"learning_rate": 0.0001631929046563193,
"loss": 0.9467,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.3034217953681946,
"learning_rate": 0.00016274944567627495,
"loss": 0.8334,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.2951507866382599,
"learning_rate": 0.0001623059866962306,
"loss": 0.9948,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.3009272515773773,
"learning_rate": 0.00016186252771618626,
"loss": 0.9841,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.3593916594982147,
"learning_rate": 0.0001614190687361419,
"loss": 1.0054,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.37854069471359253,
"learning_rate": 0.00016097560975609758,
"loss": 0.9836,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.33264443278312683,
"learning_rate": 0.00016053215077605322,
"loss": 0.8622,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.23670782148838043,
"learning_rate": 0.00016008869179600887,
"loss": 0.8994,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.3387210965156555,
"learning_rate": 0.00015964523281596454,
"loss": 1.0462,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.2806674838066101,
"learning_rate": 0.00015920177383592018,
"loss": 0.864,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.3407931923866272,
"learning_rate": 0.00015875831485587586,
"loss": 1.0029,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.31352943181991577,
"learning_rate": 0.0001583148558758315,
"loss": 0.9595,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.24135953187942505,
"learning_rate": 0.00015787139689578714,
"loss": 0.8837,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.324372798204422,
"learning_rate": 0.0001574279379157428,
"loss": 0.8163,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.3886672258377075,
"learning_rate": 0.00015698447893569846,
"loss": 1.0885,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.41554713249206543,
"learning_rate": 0.0001565410199556541,
"loss": 1.0039,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.30493584275245667,
"learning_rate": 0.00015609756097560978,
"loss": 0.9387,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.28995105624198914,
"learning_rate": 0.00015565410199556542,
"loss": 0.9279,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.41606131196022034,
"learning_rate": 0.00015521064301552106,
"loss": 1.0043,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.3501121699810028,
"learning_rate": 0.0001547671840354767,
"loss": 1.227,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.31511804461479187,
"learning_rate": 0.00015432372505543238,
"loss": 0.9559,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.26200565695762634,
"learning_rate": 0.00015388026607538802,
"loss": 0.8849,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.34899747371673584,
"learning_rate": 0.0001534368070953437,
"loss": 0.9281,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.43095970153808594,
"learning_rate": 0.00015299334811529934,
"loss": 1.0609,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.3562941551208496,
"learning_rate": 0.00015254988913525498,
"loss": 1.183,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.3362618386745453,
"learning_rate": 0.00015210643015521066,
"loss": 1.0343,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.30683737993240356,
"learning_rate": 0.0001516629711751663,
"loss": 0.9362,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.29971304535865784,
"learning_rate": 0.00015121951219512197,
"loss": 0.8391,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.4042914807796478,
"learning_rate": 0.00015077605321507762,
"loss": 0.9498,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.27822911739349365,
"learning_rate": 0.0001503325942350333,
"loss": 0.9683,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.32644709944725037,
"learning_rate": 0.0001498891352549889,
"loss": 0.9593,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.33641940355300903,
"learning_rate": 0.00014944567627494458,
"loss": 0.9588,
"step": 120
},
{
"epoch": 0.7978021978021979,
"grad_norm": 0.3272525370121002,
"learning_rate": 0.00014900221729490022,
"loss": 0.9687,
"step": 121
},
{
"epoch": 0.8043956043956044,
"grad_norm": 0.3204166293144226,
"learning_rate": 0.0001485587583148559,
"loss": 0.9355,
"step": 122
},
{
"epoch": 0.810989010989011,
"grad_norm": 0.3043823838233948,
"learning_rate": 0.00014811529933481154,
"loss": 1.0508,
"step": 123
},
{
"epoch": 0.8175824175824176,
"grad_norm": 0.33311590552330017,
"learning_rate": 0.0001476718403547672,
"loss": 1.027,
"step": 124
},
{
"epoch": 0.8241758241758241,
"grad_norm": 0.3851073682308197,
"learning_rate": 0.00014722838137472282,
"loss": 1.036,
"step": 125
},
{
"epoch": 0.8307692307692308,
"grad_norm": 0.30533120036125183,
"learning_rate": 0.0001467849223946785,
"loss": 0.8389,
"step": 126
},
{
"epoch": 0.8373626373626374,
"grad_norm": 0.40461820363998413,
"learning_rate": 0.00014634146341463414,
"loss": 0.8547,
"step": 127
},
{
"epoch": 0.843956043956044,
"grad_norm": 0.32906022667884827,
"learning_rate": 0.0001458980044345898,
"loss": 0.8823,
"step": 128
},
{
"epoch": 0.8505494505494505,
"grad_norm": 0.33507299423217773,
"learning_rate": 0.00014545454545454546,
"loss": 0.7823,
"step": 129
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.3369043171405792,
"learning_rate": 0.00014501108647450113,
"loss": 0.8948,
"step": 130
},
{
"epoch": 0.8637362637362638,
"grad_norm": 0.3621140122413635,
"learning_rate": 0.00014456762749445675,
"loss": 0.9148,
"step": 131
},
{
"epoch": 0.8703296703296703,
"grad_norm": 0.275978684425354,
"learning_rate": 0.00014412416851441242,
"loss": 0.653,
"step": 132
},
{
"epoch": 0.8769230769230769,
"grad_norm": 0.34134697914123535,
"learning_rate": 0.00014368070953436806,
"loss": 1.067,
"step": 133
},
{
"epoch": 0.8835164835164835,
"grad_norm": 0.3106148838996887,
"learning_rate": 0.00014323725055432373,
"loss": 0.9086,
"step": 134
},
{
"epoch": 0.8901098901098901,
"grad_norm": 0.28977343440055847,
"learning_rate": 0.00014279379157427938,
"loss": 0.9585,
"step": 135
},
{
"epoch": 0.8967032967032967,
"grad_norm": 0.34807276725769043,
"learning_rate": 0.00014235033259423505,
"loss": 0.8746,
"step": 136
},
{
"epoch": 0.9032967032967033,
"grad_norm": 0.308969110250473,
"learning_rate": 0.0001419068736141907,
"loss": 1.0125,
"step": 137
},
{
"epoch": 0.9098901098901099,
"grad_norm": 0.4206806719303131,
"learning_rate": 0.00014146341463414634,
"loss": 0.8913,
"step": 138
},
{
"epoch": 0.9164835164835164,
"grad_norm": 0.28508925437927246,
"learning_rate": 0.000141019955654102,
"loss": 0.7584,
"step": 139
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.32829904556274414,
"learning_rate": 0.00014057649667405765,
"loss": 1.1856,
"step": 140
},
{
"epoch": 0.9296703296703297,
"grad_norm": 0.3049874007701874,
"learning_rate": 0.00014013303769401332,
"loss": 0.8474,
"step": 141
},
{
"epoch": 0.9362637362637363,
"grad_norm": 0.31897589564323425,
"learning_rate": 0.00013968957871396897,
"loss": 0.8829,
"step": 142
},
{
"epoch": 0.9428571428571428,
"grad_norm": 0.35534486174583435,
"learning_rate": 0.00013924611973392464,
"loss": 0.9745,
"step": 143
},
{
"epoch": 0.9494505494505494,
"grad_norm": 0.35839682817459106,
"learning_rate": 0.00013880266075388026,
"loss": 1.0084,
"step": 144
},
{
"epoch": 0.9560439560439561,
"grad_norm": 0.3480103313922882,
"learning_rate": 0.00013835920177383593,
"loss": 0.9347,
"step": 145
},
{
"epoch": 0.9626373626373627,
"grad_norm": 0.31824761629104614,
"learning_rate": 0.00013791574279379157,
"loss": 0.9989,
"step": 146
},
{
"epoch": 0.9692307692307692,
"grad_norm": 0.3492334485054016,
"learning_rate": 0.00013747228381374724,
"loss": 1.0016,
"step": 147
},
{
"epoch": 0.9758241758241758,
"grad_norm": 0.4156409502029419,
"learning_rate": 0.0001370288248337029,
"loss": 0.8574,
"step": 148
},
{
"epoch": 0.9824175824175824,
"grad_norm": 0.2570762634277344,
"learning_rate": 0.00013658536585365856,
"loss": 0.674,
"step": 149
},
{
"epoch": 0.989010989010989,
"grad_norm": 0.35878464579582214,
"learning_rate": 0.00013614190687361418,
"loss": 0.9205,
"step": 150
},
{
"epoch": 0.9956043956043956,
"grad_norm": 0.3057461380958557,
"learning_rate": 0.00013569844789356985,
"loss": 0.7442,
"step": 151
},
{
"epoch": 1.0,
"grad_norm": 0.8474589586257935,
"learning_rate": 0.0001352549889135255,
"loss": 1.133,
"step": 152
},
{
"epoch": 1.0065934065934066,
"grad_norm": 0.3437095880508423,
"learning_rate": 0.00013481152993348116,
"loss": 0.8786,
"step": 153
},
{
"epoch": 1.0131868131868131,
"grad_norm": 0.27395349740982056,
"learning_rate": 0.0001343680709534368,
"loss": 0.9305,
"step": 154
},
{
"epoch": 1.0197802197802197,
"grad_norm": 0.3620387613773346,
"learning_rate": 0.00013392461197339248,
"loss": 0.889,
"step": 155
},
{
"epoch": 1.0263736263736263,
"grad_norm": 0.2791484296321869,
"learning_rate": 0.00013348115299334812,
"loss": 0.9797,
"step": 156
},
{
"epoch": 1.032967032967033,
"grad_norm": 0.30360496044158936,
"learning_rate": 0.00013303769401330377,
"loss": 0.8066,
"step": 157
},
{
"epoch": 1.0395604395604396,
"grad_norm": 0.30937135219573975,
"learning_rate": 0.00013259423503325944,
"loss": 0.8638,
"step": 158
},
{
"epoch": 1.0461538461538462,
"grad_norm": 0.3081912100315094,
"learning_rate": 0.00013215077605321509,
"loss": 0.8113,
"step": 159
},
{
"epoch": 1.0527472527472528,
"grad_norm": 0.3650044798851013,
"learning_rate": 0.00013170731707317076,
"loss": 0.8438,
"step": 160
},
{
"epoch": 1.0593406593406594,
"grad_norm": 0.34040015935897827,
"learning_rate": 0.0001312638580931264,
"loss": 0.9233,
"step": 161
},
{
"epoch": 1.065934065934066,
"grad_norm": 0.30776068568229675,
"learning_rate": 0.00013082039911308205,
"loss": 0.8206,
"step": 162
},
{
"epoch": 1.0725274725274725,
"grad_norm": 0.3026445209980011,
"learning_rate": 0.0001303769401330377,
"loss": 0.9224,
"step": 163
},
{
"epoch": 1.079120879120879,
"grad_norm": 0.42985305190086365,
"learning_rate": 0.00012993348115299336,
"loss": 0.8493,
"step": 164
},
{
"epoch": 1.0857142857142856,
"grad_norm": 0.3884040117263794,
"learning_rate": 0.000129490022172949,
"loss": 0.9732,
"step": 165
},
{
"epoch": 1.0923076923076924,
"grad_norm": 0.30262163281440735,
"learning_rate": 0.00012904656319290468,
"loss": 0.7478,
"step": 166
},
{
"epoch": 1.098901098901099,
"grad_norm": 0.2942698895931244,
"learning_rate": 0.00012860310421286032,
"loss": 0.7617,
"step": 167
},
{
"epoch": 1.1054945054945056,
"grad_norm": 0.44344866275787354,
"learning_rate": 0.00012815964523281597,
"loss": 0.9006,
"step": 168
},
{
"epoch": 1.1120879120879121,
"grad_norm": 0.3734571039676666,
"learning_rate": 0.0001277161862527716,
"loss": 0.9352,
"step": 169
},
{
"epoch": 1.1186813186813187,
"grad_norm": 0.34700432419776917,
"learning_rate": 0.00012727272727272728,
"loss": 0.87,
"step": 170
},
{
"epoch": 1.1252747252747253,
"grad_norm": 0.39114832878112793,
"learning_rate": 0.00012682926829268293,
"loss": 0.7903,
"step": 171
},
{
"epoch": 1.1318681318681318,
"grad_norm": 0.32196515798568726,
"learning_rate": 0.0001263858093126386,
"loss": 0.8809,
"step": 172
},
{
"epoch": 1.1384615384615384,
"grad_norm": 0.30956554412841797,
"learning_rate": 0.00012594235033259424,
"loss": 0.7394,
"step": 173
},
{
"epoch": 1.145054945054945,
"grad_norm": 0.2833406627178192,
"learning_rate": 0.00012549889135254989,
"loss": 0.6533,
"step": 174
},
{
"epoch": 1.1516483516483516,
"grad_norm": 0.34335243701934814,
"learning_rate": 0.00012505543237250553,
"loss": 0.9679,
"step": 175
},
{
"epoch": 1.1582417582417581,
"grad_norm": 0.36387017369270325,
"learning_rate": 0.0001246119733924612,
"loss": 0.9091,
"step": 176
},
{
"epoch": 1.164835164835165,
"grad_norm": 0.4111376106739044,
"learning_rate": 0.00012416851441241685,
"loss": 0.7327,
"step": 177
},
{
"epoch": 1.1714285714285715,
"grad_norm": 0.3737115263938904,
"learning_rate": 0.00012372505543237252,
"loss": 0.7335,
"step": 178
},
{
"epoch": 1.178021978021978,
"grad_norm": 0.43880000710487366,
"learning_rate": 0.00012328159645232816,
"loss": 0.8456,
"step": 179
},
{
"epoch": 1.1846153846153846,
"grad_norm": 0.32169827818870544,
"learning_rate": 0.0001228381374722838,
"loss": 0.6974,
"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": 2.9870689357430784e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}