jeqcho's picture
Upload folder using huggingface_hub
03192d7 verified
Raw
History Blame Contribute Delete
68.2 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.567032967032967,
"eval_steps": 500,
"global_step": 390,
"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
},
{
"epoch": 1.1912087912087912,
"grad_norm": 0.36517950892448425,
"learning_rate": 0.00012239467849223948,
"loss": 0.8414,
"step": 181
},
{
"epoch": 1.1978021978021978,
"grad_norm": 0.44836437702178955,
"learning_rate": 0.00012195121951219512,
"loss": 0.9481,
"step": 182
},
{
"epoch": 1.2043956043956043,
"grad_norm": 0.4397249221801758,
"learning_rate": 0.00012150776053215078,
"loss": 0.838,
"step": 183
},
{
"epoch": 1.210989010989011,
"grad_norm": 0.4569542706012726,
"learning_rate": 0.00012106430155210644,
"loss": 0.9055,
"step": 184
},
{
"epoch": 1.2175824175824177,
"grad_norm": 0.3338332176208496,
"learning_rate": 0.0001206208425720621,
"loss": 0.7758,
"step": 185
},
{
"epoch": 1.2241758241758243,
"grad_norm": 0.374711811542511,
"learning_rate": 0.00012017738359201774,
"loss": 0.8104,
"step": 186
},
{
"epoch": 1.2307692307692308,
"grad_norm": 0.4020582437515259,
"learning_rate": 0.0001197339246119734,
"loss": 0.886,
"step": 187
},
{
"epoch": 1.2373626373626374,
"grad_norm": 0.3730420470237732,
"learning_rate": 0.00011929046563192906,
"loss": 0.8025,
"step": 188
},
{
"epoch": 1.243956043956044,
"grad_norm": 0.44028961658477783,
"learning_rate": 0.00011884700665188471,
"loss": 0.894,
"step": 189
},
{
"epoch": 1.2505494505494505,
"grad_norm": 0.3578510582447052,
"learning_rate": 0.00011840354767184036,
"loss": 0.8352,
"step": 190
},
{
"epoch": 1.2571428571428571,
"grad_norm": 0.3951568007469177,
"learning_rate": 0.00011796008869179602,
"loss": 0.9741,
"step": 191
},
{
"epoch": 1.2637362637362637,
"grad_norm": 0.44361162185668945,
"learning_rate": 0.00011751662971175166,
"loss": 0.8778,
"step": 192
},
{
"epoch": 1.2703296703296703,
"grad_norm": 0.4443974494934082,
"learning_rate": 0.00011707317073170732,
"loss": 0.8936,
"step": 193
},
{
"epoch": 1.2769230769230768,
"grad_norm": 0.38907331228256226,
"learning_rate": 0.00011662971175166298,
"loss": 1.0263,
"step": 194
},
{
"epoch": 1.2835164835164834,
"grad_norm": 0.3887748718261719,
"learning_rate": 0.00011618625277161863,
"loss": 0.8719,
"step": 195
},
{
"epoch": 1.2901098901098902,
"grad_norm": 0.41394010186195374,
"learning_rate": 0.00011574279379157429,
"loss": 0.8421,
"step": 196
},
{
"epoch": 1.2967032967032968,
"grad_norm": 0.4270264804363251,
"learning_rate": 0.00011529933481152995,
"loss": 0.8422,
"step": 197
},
{
"epoch": 1.3032967032967033,
"grad_norm": 0.3818177580833435,
"learning_rate": 0.00011485587583148558,
"loss": 0.9402,
"step": 198
},
{
"epoch": 1.30989010989011,
"grad_norm": 0.41748562455177307,
"learning_rate": 0.00011441241685144124,
"loss": 0.8877,
"step": 199
},
{
"epoch": 1.3164835164835165,
"grad_norm": 0.42905327677726746,
"learning_rate": 0.0001139689578713969,
"loss": 0.8915,
"step": 200
},
{
"epoch": 1.323076923076923,
"grad_norm": 0.5538219809532166,
"learning_rate": 0.00011352549889135255,
"loss": 0.9188,
"step": 201
},
{
"epoch": 1.3296703296703296,
"grad_norm": 0.5572859644889832,
"learning_rate": 0.00011308203991130821,
"loss": 0.921,
"step": 202
},
{
"epoch": 1.3362637362637364,
"grad_norm": 0.3806891441345215,
"learning_rate": 0.00011263858093126387,
"loss": 0.6525,
"step": 203
},
{
"epoch": 1.342857142857143,
"grad_norm": 0.44809314608573914,
"learning_rate": 0.00011219512195121953,
"loss": 0.8546,
"step": 204
},
{
"epoch": 1.3494505494505495,
"grad_norm": 0.44073691964149475,
"learning_rate": 0.00011175166297117516,
"loss": 1.0716,
"step": 205
},
{
"epoch": 1.3560439560439561,
"grad_norm": 0.4129194915294647,
"learning_rate": 0.00011130820399113082,
"loss": 0.9638,
"step": 206
},
{
"epoch": 1.3626373626373627,
"grad_norm": 0.47953000664711,
"learning_rate": 0.00011086474501108647,
"loss": 0.8628,
"step": 207
},
{
"epoch": 1.3692307692307693,
"grad_norm": 0.5595114231109619,
"learning_rate": 0.00011042128603104213,
"loss": 0.7176,
"step": 208
},
{
"epoch": 1.3758241758241758,
"grad_norm": 0.3820893466472626,
"learning_rate": 0.00010997782705099779,
"loss": 0.8491,
"step": 209
},
{
"epoch": 1.3824175824175824,
"grad_norm": 0.4465320408344269,
"learning_rate": 0.00010953436807095345,
"loss": 0.832,
"step": 210
},
{
"epoch": 1.389010989010989,
"grad_norm": 0.40102419257164,
"learning_rate": 0.00010909090909090909,
"loss": 0.8367,
"step": 211
},
{
"epoch": 1.3956043956043955,
"grad_norm": 0.4284117817878723,
"learning_rate": 0.00010864745011086475,
"loss": 0.8423,
"step": 212
},
{
"epoch": 1.402197802197802,
"grad_norm": 0.47202739119529724,
"learning_rate": 0.00010820399113082041,
"loss": 0.9148,
"step": 213
},
{
"epoch": 1.4087912087912087,
"grad_norm": 0.5076578259468079,
"learning_rate": 0.00010776053215077607,
"loss": 0.8134,
"step": 214
},
{
"epoch": 1.4153846153846155,
"grad_norm": 0.5029810070991516,
"learning_rate": 0.00010731707317073172,
"loss": 0.8268,
"step": 215
},
{
"epoch": 1.421978021978022,
"grad_norm": 0.48758772015571594,
"learning_rate": 0.00010687361419068738,
"loss": 0.8738,
"step": 216
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.47710666060447693,
"learning_rate": 0.00010643015521064301,
"loss": 0.8784,
"step": 217
},
{
"epoch": 1.4351648351648352,
"grad_norm": 0.3943558633327484,
"learning_rate": 0.00010598669623059867,
"loss": 0.9256,
"step": 218
},
{
"epoch": 1.4417582417582417,
"grad_norm": 0.5376501083374023,
"learning_rate": 0.00010554323725055433,
"loss": 0.9089,
"step": 219
},
{
"epoch": 1.4483516483516483,
"grad_norm": 0.5635764002799988,
"learning_rate": 0.00010509977827050999,
"loss": 0.9254,
"step": 220
},
{
"epoch": 1.4549450549450549,
"grad_norm": 0.4008137285709381,
"learning_rate": 0.00010465631929046564,
"loss": 0.6356,
"step": 221
},
{
"epoch": 1.4615384615384617,
"grad_norm": 0.48087647557258606,
"learning_rate": 0.0001042128603104213,
"loss": 0.762,
"step": 222
},
{
"epoch": 1.4681318681318682,
"grad_norm": 0.5253714323043823,
"learning_rate": 0.00010376940133037693,
"loss": 1.0206,
"step": 223
},
{
"epoch": 1.4747252747252748,
"grad_norm": 0.5255848169326782,
"learning_rate": 0.00010332594235033259,
"loss": 0.9327,
"step": 224
},
{
"epoch": 1.4813186813186814,
"grad_norm": 0.37826597690582275,
"learning_rate": 0.00010288248337028825,
"loss": 0.7133,
"step": 225
},
{
"epoch": 1.487912087912088,
"grad_norm": 0.5715931057929993,
"learning_rate": 0.0001024390243902439,
"loss": 0.9258,
"step": 226
},
{
"epoch": 1.4945054945054945,
"grad_norm": 0.4119124412536621,
"learning_rate": 0.00010199556541019956,
"loss": 0.7946,
"step": 227
},
{
"epoch": 1.501098901098901,
"grad_norm": 0.505630612373352,
"learning_rate": 0.00010155210643015522,
"loss": 0.7857,
"step": 228
},
{
"epoch": 1.5076923076923077,
"grad_norm": 0.4280208945274353,
"learning_rate": 0.00010110864745011087,
"loss": 0.9038,
"step": 229
},
{
"epoch": 1.5142857142857142,
"grad_norm": 0.532058835029602,
"learning_rate": 0.00010066518847006652,
"loss": 0.8312,
"step": 230
},
{
"epoch": 1.5208791208791208,
"grad_norm": 0.4033065438270569,
"learning_rate": 0.00010022172949002218,
"loss": 0.7958,
"step": 231
},
{
"epoch": 1.5274725274725274,
"grad_norm": 0.46123024821281433,
"learning_rate": 9.977827050997783e-05,
"loss": 0.9297,
"step": 232
},
{
"epoch": 1.534065934065934,
"grad_norm": 0.45616596937179565,
"learning_rate": 9.933481152993348e-05,
"loss": 0.7593,
"step": 233
},
{
"epoch": 1.5406593406593405,
"grad_norm": 0.5083249807357788,
"learning_rate": 9.889135254988914e-05,
"loss": 0.8581,
"step": 234
},
{
"epoch": 1.5472527472527473,
"grad_norm": 0.510529637336731,
"learning_rate": 9.84478935698448e-05,
"loss": 0.8267,
"step": 235
},
{
"epoch": 1.5538461538461539,
"grad_norm": 0.5444358587265015,
"learning_rate": 9.800443458980046e-05,
"loss": 0.8602,
"step": 236
},
{
"epoch": 1.5604395604395604,
"grad_norm": 0.8113863468170166,
"learning_rate": 9.75609756097561e-05,
"loss": 0.9275,
"step": 237
},
{
"epoch": 1.567032967032967,
"grad_norm": 0.45696744322776794,
"learning_rate": 9.711751662971176e-05,
"loss": 0.7688,
"step": 238
},
{
"epoch": 1.5736263736263736,
"grad_norm": 0.542674720287323,
"learning_rate": 9.667405764966742e-05,
"loss": 0.8524,
"step": 239
},
{
"epoch": 1.5802197802197804,
"grad_norm": 0.5304957628250122,
"learning_rate": 9.623059866962306e-05,
"loss": 0.8642,
"step": 240
},
{
"epoch": 1.586813186813187,
"grad_norm": 0.491951584815979,
"learning_rate": 9.578713968957872e-05,
"loss": 0.8286,
"step": 241
},
{
"epoch": 1.5934065934065935,
"grad_norm": 0.48613667488098145,
"learning_rate": 9.534368070953438e-05,
"loss": 0.8712,
"step": 242
},
{
"epoch": 1.6,
"grad_norm": 0.49706676602363586,
"learning_rate": 9.490022172949002e-05,
"loss": 0.6718,
"step": 243
},
{
"epoch": 1.6065934065934067,
"grad_norm": 0.49495822191238403,
"learning_rate": 9.445676274944568e-05,
"loss": 0.8206,
"step": 244
},
{
"epoch": 1.6131868131868132,
"grad_norm": 0.6443434357643127,
"learning_rate": 9.401330376940134e-05,
"loss": 1.0183,
"step": 245
},
{
"epoch": 1.6197802197802198,
"grad_norm": 0.43216127157211304,
"learning_rate": 9.356984478935698e-05,
"loss": 0.7506,
"step": 246
},
{
"epoch": 1.6263736263736264,
"grad_norm": 0.5162910223007202,
"learning_rate": 9.312638580931264e-05,
"loss": 0.8798,
"step": 247
},
{
"epoch": 1.632967032967033,
"grad_norm": 0.4986926019191742,
"learning_rate": 9.26829268292683e-05,
"loss": 0.7542,
"step": 248
},
{
"epoch": 1.6395604395604395,
"grad_norm": 0.5325050950050354,
"learning_rate": 9.223946784922394e-05,
"loss": 0.7125,
"step": 249
},
{
"epoch": 1.646153846153846,
"grad_norm": 0.5778030753135681,
"learning_rate": 9.17960088691796e-05,
"loss": 0.8233,
"step": 250
},
{
"epoch": 1.6527472527472526,
"grad_norm": 0.44990086555480957,
"learning_rate": 9.135254988913526e-05,
"loss": 0.8734,
"step": 251
},
{
"epoch": 1.6593406593406592,
"grad_norm": 0.44442686438560486,
"learning_rate": 9.090909090909092e-05,
"loss": 0.7772,
"step": 252
},
{
"epoch": 1.6659340659340658,
"grad_norm": 0.42507997155189514,
"learning_rate": 9.046563192904656e-05,
"loss": 0.8029,
"step": 253
},
{
"epoch": 1.6725274725274726,
"grad_norm": 0.47296181321144104,
"learning_rate": 9.002217294900222e-05,
"loss": 0.7162,
"step": 254
},
{
"epoch": 1.6791208791208792,
"grad_norm": 0.48159700632095337,
"learning_rate": 8.957871396895788e-05,
"loss": 0.6961,
"step": 255
},
{
"epoch": 1.6857142857142857,
"grad_norm": 0.536461591720581,
"learning_rate": 8.913525498891354e-05,
"loss": 0.9668,
"step": 256
},
{
"epoch": 1.6923076923076923,
"grad_norm": 0.5366361141204834,
"learning_rate": 8.869179600886919e-05,
"loss": 0.7046,
"step": 257
},
{
"epoch": 1.6989010989010989,
"grad_norm": 0.4559578597545624,
"learning_rate": 8.824833702882484e-05,
"loss": 0.9402,
"step": 258
},
{
"epoch": 1.7054945054945057,
"grad_norm": 0.5212759971618652,
"learning_rate": 8.78048780487805e-05,
"loss": 0.8066,
"step": 259
},
{
"epoch": 1.7120879120879122,
"grad_norm": 0.4856880009174347,
"learning_rate": 8.736141906873615e-05,
"loss": 0.861,
"step": 260
},
{
"epoch": 1.7186813186813188,
"grad_norm": 0.5332313776016235,
"learning_rate": 8.69179600886918e-05,
"loss": 0.8588,
"step": 261
},
{
"epoch": 1.7252747252747254,
"grad_norm": 0.38355979323387146,
"learning_rate": 8.647450110864746e-05,
"loss": 0.688,
"step": 262
},
{
"epoch": 1.731868131868132,
"grad_norm": 0.4994678497314453,
"learning_rate": 8.603104212860311e-05,
"loss": 0.7778,
"step": 263
},
{
"epoch": 1.7384615384615385,
"grad_norm": 0.5529941916465759,
"learning_rate": 8.558758314855876e-05,
"loss": 0.8509,
"step": 264
},
{
"epoch": 1.745054945054945,
"grad_norm": 0.5791758894920349,
"learning_rate": 8.514412416851442e-05,
"loss": 0.9519,
"step": 265
},
{
"epoch": 1.7516483516483516,
"grad_norm": 0.6058807969093323,
"learning_rate": 8.470066518847007e-05,
"loss": 0.9526,
"step": 266
},
{
"epoch": 1.7582417582417582,
"grad_norm": 0.4993143677711487,
"learning_rate": 8.425720620842572e-05,
"loss": 0.9413,
"step": 267
},
{
"epoch": 1.7648351648351648,
"grad_norm": 0.5066776275634766,
"learning_rate": 8.381374722838138e-05,
"loss": 1.065,
"step": 268
},
{
"epoch": 1.7714285714285714,
"grad_norm": 0.5073964595794678,
"learning_rate": 8.337028824833703e-05,
"loss": 0.9184,
"step": 269
},
{
"epoch": 1.778021978021978,
"grad_norm": 0.5927123427391052,
"learning_rate": 8.292682926829268e-05,
"loss": 0.8154,
"step": 270
},
{
"epoch": 1.7846153846153845,
"grad_norm": 0.5897004008293152,
"learning_rate": 8.248337028824834e-05,
"loss": 0.917,
"step": 271
},
{
"epoch": 1.791208791208791,
"grad_norm": 0.5182631611824036,
"learning_rate": 8.2039911308204e-05,
"loss": 0.8783,
"step": 272
},
{
"epoch": 1.7978021978021979,
"grad_norm": 0.5345656275749207,
"learning_rate": 8.159645232815965e-05,
"loss": 0.8112,
"step": 273
},
{
"epoch": 1.8043956043956044,
"grad_norm": 0.546957790851593,
"learning_rate": 8.11529933481153e-05,
"loss": 0.8206,
"step": 274
},
{
"epoch": 1.810989010989011,
"grad_norm": 0.47993218898773193,
"learning_rate": 8.070953436807095e-05,
"loss": 0.7343,
"step": 275
},
{
"epoch": 1.8175824175824176,
"grad_norm": 0.46397554874420166,
"learning_rate": 8.026607538802661e-05,
"loss": 0.7177,
"step": 276
},
{
"epoch": 1.8241758241758241,
"grad_norm": 0.5194482207298279,
"learning_rate": 7.982261640798227e-05,
"loss": 0.9204,
"step": 277
},
{
"epoch": 1.830769230769231,
"grad_norm": 0.45893725752830505,
"learning_rate": 7.937915742793793e-05,
"loss": 0.7786,
"step": 278
},
{
"epoch": 1.8373626373626375,
"grad_norm": 0.5668184161186218,
"learning_rate": 7.893569844789357e-05,
"loss": 1.0424,
"step": 279
},
{
"epoch": 1.843956043956044,
"grad_norm": 0.408590167760849,
"learning_rate": 7.849223946784923e-05,
"loss": 0.6733,
"step": 280
},
{
"epoch": 1.8505494505494506,
"grad_norm": 0.5162156820297241,
"learning_rate": 7.804878048780489e-05,
"loss": 0.8978,
"step": 281
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.5077143311500549,
"learning_rate": 7.760532150776053e-05,
"loss": 0.8475,
"step": 282
},
{
"epoch": 1.8637362637362638,
"grad_norm": 0.45225420594215393,
"learning_rate": 7.716186252771619e-05,
"loss": 0.8797,
"step": 283
},
{
"epoch": 1.8703296703296703,
"grad_norm": 0.5481660962104797,
"learning_rate": 7.671840354767185e-05,
"loss": 0.9036,
"step": 284
},
{
"epoch": 1.876923076923077,
"grad_norm": 0.5467819571495056,
"learning_rate": 7.627494456762749e-05,
"loss": 0.9198,
"step": 285
},
{
"epoch": 1.8835164835164835,
"grad_norm": 0.5100396871566772,
"learning_rate": 7.583148558758315e-05,
"loss": 0.8325,
"step": 286
},
{
"epoch": 1.89010989010989,
"grad_norm": 0.4944553077220917,
"learning_rate": 7.538802660753881e-05,
"loss": 0.8878,
"step": 287
},
{
"epoch": 1.8967032967032966,
"grad_norm": 0.5813539028167725,
"learning_rate": 7.494456762749445e-05,
"loss": 0.8573,
"step": 288
},
{
"epoch": 1.9032967032967032,
"grad_norm": 0.5417572855949402,
"learning_rate": 7.450110864745011e-05,
"loss": 0.8873,
"step": 289
},
{
"epoch": 1.9098901098901098,
"grad_norm": 0.49736300110816956,
"learning_rate": 7.405764966740577e-05,
"loss": 0.6223,
"step": 290
},
{
"epoch": 1.9164835164835163,
"grad_norm": 0.48220983147621155,
"learning_rate": 7.361419068736141e-05,
"loss": 0.7772,
"step": 291
},
{
"epoch": 1.9230769230769231,
"grad_norm": 0.5532078146934509,
"learning_rate": 7.317073170731707e-05,
"loss": 0.7545,
"step": 292
},
{
"epoch": 1.9296703296703297,
"grad_norm": 0.6092115044593811,
"learning_rate": 7.272727272727273e-05,
"loss": 0.9056,
"step": 293
},
{
"epoch": 1.9362637362637363,
"grad_norm": 0.5845623016357422,
"learning_rate": 7.228381374722837e-05,
"loss": 0.8775,
"step": 294
},
{
"epoch": 1.9428571428571428,
"grad_norm": 0.5559525489807129,
"learning_rate": 7.184035476718403e-05,
"loss": 0.8232,
"step": 295
},
{
"epoch": 1.9494505494505494,
"grad_norm": 0.5213296413421631,
"learning_rate": 7.139689578713969e-05,
"loss": 0.7606,
"step": 296
},
{
"epoch": 1.9560439560439562,
"grad_norm": 0.5458694696426392,
"learning_rate": 7.095343680709535e-05,
"loss": 0.868,
"step": 297
},
{
"epoch": 1.9626373626373628,
"grad_norm": 0.5273828506469727,
"learning_rate": 7.0509977827051e-05,
"loss": 0.6023,
"step": 298
},
{
"epoch": 1.9692307692307693,
"grad_norm": 0.4832824170589447,
"learning_rate": 7.006651884700666e-05,
"loss": 0.8605,
"step": 299
},
{
"epoch": 1.975824175824176,
"grad_norm": 0.5657328963279724,
"learning_rate": 6.962305986696232e-05,
"loss": 0.7707,
"step": 300
},
{
"epoch": 1.9824175824175825,
"grad_norm": 0.5884835124015808,
"learning_rate": 6.917960088691796e-05,
"loss": 0.9925,
"step": 301
},
{
"epoch": 1.989010989010989,
"grad_norm": 0.5887730121612549,
"learning_rate": 6.873614190687362e-05,
"loss": 1.0348,
"step": 302
},
{
"epoch": 1.9956043956043956,
"grad_norm": 0.5426163673400879,
"learning_rate": 6.829268292682928e-05,
"loss": 0.8134,
"step": 303
},
{
"epoch": 2.0,
"grad_norm": 0.8350123763084412,
"learning_rate": 6.784922394678492e-05,
"loss": 0.8766,
"step": 304
},
{
"epoch": 2.0065934065934066,
"grad_norm": 0.49237483739852905,
"learning_rate": 6.740576496674058e-05,
"loss": 0.6589,
"step": 305
},
{
"epoch": 2.013186813186813,
"grad_norm": 0.5131711959838867,
"learning_rate": 6.696230598669624e-05,
"loss": 0.8187,
"step": 306
},
{
"epoch": 2.0197802197802197,
"grad_norm": 0.48230329155921936,
"learning_rate": 6.651884700665188e-05,
"loss": 0.81,
"step": 307
},
{
"epoch": 2.0263736263736263,
"grad_norm": 0.593840479850769,
"learning_rate": 6.607538802660754e-05,
"loss": 0.7184,
"step": 308
},
{
"epoch": 2.032967032967033,
"grad_norm": 0.461073100566864,
"learning_rate": 6.56319290465632e-05,
"loss": 0.6939,
"step": 309
},
{
"epoch": 2.0395604395604394,
"grad_norm": 0.523365318775177,
"learning_rate": 6.518847006651884e-05,
"loss": 0.7522,
"step": 310
},
{
"epoch": 2.046153846153846,
"grad_norm": 0.5663949251174927,
"learning_rate": 6.47450110864745e-05,
"loss": 0.6287,
"step": 311
},
{
"epoch": 2.0527472527472526,
"grad_norm": 0.5744668841362,
"learning_rate": 6.430155210643016e-05,
"loss": 0.7664,
"step": 312
},
{
"epoch": 2.059340659340659,
"grad_norm": 0.5253913402557373,
"learning_rate": 6.38580931263858e-05,
"loss": 0.6664,
"step": 313
},
{
"epoch": 2.065934065934066,
"grad_norm": 0.44012558460235596,
"learning_rate": 6.341463414634146e-05,
"loss": 0.5797,
"step": 314
},
{
"epoch": 2.0725274725274727,
"grad_norm": 0.5389400720596313,
"learning_rate": 6.297117516629712e-05,
"loss": 0.8768,
"step": 315
},
{
"epoch": 2.0791208791208793,
"grad_norm": 0.5396459102630615,
"learning_rate": 6.252771618625277e-05,
"loss": 0.5846,
"step": 316
},
{
"epoch": 2.085714285714286,
"grad_norm": 0.5646059513092041,
"learning_rate": 6.208425720620842e-05,
"loss": 0.5756,
"step": 317
},
{
"epoch": 2.0923076923076924,
"grad_norm": 0.5128243565559387,
"learning_rate": 6.164079822616408e-05,
"loss": 0.6835,
"step": 318
},
{
"epoch": 2.098901098901099,
"grad_norm": 0.5853198170661926,
"learning_rate": 6.119733924611974e-05,
"loss": 0.7042,
"step": 319
},
{
"epoch": 2.1054945054945056,
"grad_norm": 0.6777295470237732,
"learning_rate": 6.075388026607539e-05,
"loss": 0.6979,
"step": 320
},
{
"epoch": 2.112087912087912,
"grad_norm": 0.5376538634300232,
"learning_rate": 6.031042128603105e-05,
"loss": 0.5373,
"step": 321
},
{
"epoch": 2.1186813186813187,
"grad_norm": 0.47314679622650146,
"learning_rate": 5.98669623059867e-05,
"loss": 0.5836,
"step": 322
},
{
"epoch": 2.1252747252747253,
"grad_norm": 0.7186151742935181,
"learning_rate": 5.942350332594236e-05,
"loss": 0.8785,
"step": 323
},
{
"epoch": 2.131868131868132,
"grad_norm": 0.5601128339767456,
"learning_rate": 5.898004434589801e-05,
"loss": 0.7062,
"step": 324
},
{
"epoch": 2.1384615384615384,
"grad_norm": 0.5976690649986267,
"learning_rate": 5.853658536585366e-05,
"loss": 0.7378,
"step": 325
},
{
"epoch": 2.145054945054945,
"grad_norm": 0.5961958765983582,
"learning_rate": 5.809312638580932e-05,
"loss": 0.6391,
"step": 326
},
{
"epoch": 2.1516483516483516,
"grad_norm": 0.5582660436630249,
"learning_rate": 5.7649667405764975e-05,
"loss": 0.718,
"step": 327
},
{
"epoch": 2.158241758241758,
"grad_norm": 0.603960394859314,
"learning_rate": 5.720620842572062e-05,
"loss": 0.6247,
"step": 328
},
{
"epoch": 2.1648351648351647,
"grad_norm": 0.724873960018158,
"learning_rate": 5.676274944567628e-05,
"loss": 0.6949,
"step": 329
},
{
"epoch": 2.1714285714285713,
"grad_norm": 0.6676297783851624,
"learning_rate": 5.6319290465631935e-05,
"loss": 0.637,
"step": 330
},
{
"epoch": 2.178021978021978,
"grad_norm": 0.6630086898803711,
"learning_rate": 5.587583148558758e-05,
"loss": 0.679,
"step": 331
},
{
"epoch": 2.184615384615385,
"grad_norm": 0.6064302921295166,
"learning_rate": 5.543237250554324e-05,
"loss": 0.8782,
"step": 332
},
{
"epoch": 2.1912087912087914,
"grad_norm": 0.6407224535942078,
"learning_rate": 5.4988913525498895e-05,
"loss": 0.6025,
"step": 333
},
{
"epoch": 2.197802197802198,
"grad_norm": 0.512618899345398,
"learning_rate": 5.4545454545454546e-05,
"loss": 0.5802,
"step": 334
},
{
"epoch": 2.2043956043956046,
"grad_norm": 0.5423387289047241,
"learning_rate": 5.4101995565410204e-05,
"loss": 0.6301,
"step": 335
},
{
"epoch": 2.210989010989011,
"grad_norm": 0.6641631126403809,
"learning_rate": 5.365853658536586e-05,
"loss": 0.8007,
"step": 336
},
{
"epoch": 2.2175824175824177,
"grad_norm": 0.6003826856613159,
"learning_rate": 5.3215077605321506e-05,
"loss": 0.6912,
"step": 337
},
{
"epoch": 2.2241758241758243,
"grad_norm": 0.624869167804718,
"learning_rate": 5.2771618625277164e-05,
"loss": 0.6601,
"step": 338
},
{
"epoch": 2.230769230769231,
"grad_norm": 0.6477227210998535,
"learning_rate": 5.232815964523282e-05,
"loss": 0.7885,
"step": 339
},
{
"epoch": 2.2373626373626374,
"grad_norm": 0.5255128145217896,
"learning_rate": 5.1884700665188466e-05,
"loss": 0.7617,
"step": 340
},
{
"epoch": 2.243956043956044,
"grad_norm": 0.6669898629188538,
"learning_rate": 5.1441241685144124e-05,
"loss": 0.7807,
"step": 341
},
{
"epoch": 2.2505494505494505,
"grad_norm": 0.7278643846511841,
"learning_rate": 5.099778270509978e-05,
"loss": 0.7766,
"step": 342
},
{
"epoch": 2.257142857142857,
"grad_norm": 0.5562098026275635,
"learning_rate": 5.0554323725055433e-05,
"loss": 0.6341,
"step": 343
},
{
"epoch": 2.2637362637362637,
"grad_norm": 0.5082377195358276,
"learning_rate": 5.011086474501109e-05,
"loss": 0.5488,
"step": 344
},
{
"epoch": 2.2703296703296703,
"grad_norm": 0.6659572124481201,
"learning_rate": 4.966740576496674e-05,
"loss": 0.7689,
"step": 345
},
{
"epoch": 2.276923076923077,
"grad_norm": 0.5882406830787659,
"learning_rate": 4.92239467849224e-05,
"loss": 0.6797,
"step": 346
},
{
"epoch": 2.2835164835164834,
"grad_norm": 0.567855715751648,
"learning_rate": 4.878048780487805e-05,
"loss": 0.7245,
"step": 347
},
{
"epoch": 2.29010989010989,
"grad_norm": 0.6571938395500183,
"learning_rate": 4.833702882483371e-05,
"loss": 0.6824,
"step": 348
},
{
"epoch": 2.2967032967032965,
"grad_norm": 0.5148727297782898,
"learning_rate": 4.789356984478936e-05,
"loss": 0.668,
"step": 349
},
{
"epoch": 2.303296703296703,
"grad_norm": 0.686972439289093,
"learning_rate": 4.745011086474501e-05,
"loss": 0.8285,
"step": 350
},
{
"epoch": 2.3098901098901097,
"grad_norm": 0.6508296728134155,
"learning_rate": 4.700665188470067e-05,
"loss": 0.7141,
"step": 351
},
{
"epoch": 2.3164835164835162,
"grad_norm": 0.5596418976783752,
"learning_rate": 4.656319290465632e-05,
"loss": 0.7682,
"step": 352
},
{
"epoch": 2.3230769230769233,
"grad_norm": 0.5760199427604675,
"learning_rate": 4.611973392461197e-05,
"loss": 0.8937,
"step": 353
},
{
"epoch": 2.32967032967033,
"grad_norm": 0.6793621182441711,
"learning_rate": 4.567627494456763e-05,
"loss": 0.7657,
"step": 354
},
{
"epoch": 2.3362637362637364,
"grad_norm": 0.5601732730865479,
"learning_rate": 4.523281596452328e-05,
"loss": 0.755,
"step": 355
},
{
"epoch": 2.342857142857143,
"grad_norm": 0.6809371113777161,
"learning_rate": 4.478935698447894e-05,
"loss": 0.806,
"step": 356
},
{
"epoch": 2.3494505494505495,
"grad_norm": 0.6329469084739685,
"learning_rate": 4.4345898004434597e-05,
"loss": 0.6438,
"step": 357
},
{
"epoch": 2.356043956043956,
"grad_norm": 0.7516498565673828,
"learning_rate": 4.390243902439025e-05,
"loss": 0.7626,
"step": 358
},
{
"epoch": 2.3626373626373627,
"grad_norm": 0.6632409691810608,
"learning_rate": 4.34589800443459e-05,
"loss": 0.5659,
"step": 359
},
{
"epoch": 2.3692307692307693,
"grad_norm": 0.7438989281654358,
"learning_rate": 4.301552106430156e-05,
"loss": 0.7361,
"step": 360
},
{
"epoch": 2.375824175824176,
"grad_norm": 0.5665183663368225,
"learning_rate": 4.257206208425721e-05,
"loss": 0.6118,
"step": 361
},
{
"epoch": 2.3824175824175824,
"grad_norm": 0.7712103128433228,
"learning_rate": 4.212860310421286e-05,
"loss": 0.6796,
"step": 362
},
{
"epoch": 2.389010989010989,
"grad_norm": 0.7268961668014526,
"learning_rate": 4.168514412416852e-05,
"loss": 0.8604,
"step": 363
},
{
"epoch": 2.3956043956043955,
"grad_norm": 0.6694988012313843,
"learning_rate": 4.124168514412417e-05,
"loss": 0.7683,
"step": 364
},
{
"epoch": 2.402197802197802,
"grad_norm": 0.675880491733551,
"learning_rate": 4.0798226164079826e-05,
"loss": 0.6688,
"step": 365
},
{
"epoch": 2.4087912087912087,
"grad_norm": 0.7321246862411499,
"learning_rate": 4.035476718403548e-05,
"loss": 0.6213,
"step": 366
},
{
"epoch": 2.4153846153846152,
"grad_norm": 0.687709391117096,
"learning_rate": 3.9911308203991135e-05,
"loss": 0.7414,
"step": 367
},
{
"epoch": 2.421978021978022,
"grad_norm": 0.7096782326698303,
"learning_rate": 3.9467849223946786e-05,
"loss": 0.793,
"step": 368
},
{
"epoch": 2.4285714285714284,
"grad_norm": 0.7100688815116882,
"learning_rate": 3.9024390243902444e-05,
"loss": 0.8244,
"step": 369
},
{
"epoch": 2.4351648351648354,
"grad_norm": 0.6187054514884949,
"learning_rate": 3.8580931263858095e-05,
"loss": 0.6447,
"step": 370
},
{
"epoch": 2.441758241758242,
"grad_norm": 0.7524551153182983,
"learning_rate": 3.8137472283813746e-05,
"loss": 0.7546,
"step": 371
},
{
"epoch": 2.4483516483516485,
"grad_norm": 0.6049002408981323,
"learning_rate": 3.7694013303769404e-05,
"loss": 0.4725,
"step": 372
},
{
"epoch": 2.454945054945055,
"grad_norm": 0.6673345565795898,
"learning_rate": 3.7250554323725055e-05,
"loss": 0.7983,
"step": 373
},
{
"epoch": 2.4615384615384617,
"grad_norm": 0.7936543822288513,
"learning_rate": 3.6807095343680706e-05,
"loss": 0.712,
"step": 374
},
{
"epoch": 2.4681318681318682,
"grad_norm": 0.8414682149887085,
"learning_rate": 3.6363636363636364e-05,
"loss": 0.6765,
"step": 375
},
{
"epoch": 2.474725274725275,
"grad_norm": 0.6636696457862854,
"learning_rate": 3.5920177383592015e-05,
"loss": 0.7681,
"step": 376
},
{
"epoch": 2.4813186813186814,
"grad_norm": 0.7594190835952759,
"learning_rate": 3.547671840354767e-05,
"loss": 0.7104,
"step": 377
},
{
"epoch": 2.487912087912088,
"grad_norm": 0.8486660718917847,
"learning_rate": 3.503325942350333e-05,
"loss": 0.6983,
"step": 378
},
{
"epoch": 2.4945054945054945,
"grad_norm": 0.7499498724937439,
"learning_rate": 3.458980044345898e-05,
"loss": 0.8157,
"step": 379
},
{
"epoch": 2.501098901098901,
"grad_norm": 0.7208576202392578,
"learning_rate": 3.414634146341464e-05,
"loss": 0.8638,
"step": 380
},
{
"epoch": 2.5076923076923077,
"grad_norm": 0.770270586013794,
"learning_rate": 3.370288248337029e-05,
"loss": 0.7273,
"step": 381
},
{
"epoch": 2.5142857142857142,
"grad_norm": 0.5958781242370605,
"learning_rate": 3.325942350332594e-05,
"loss": 0.6764,
"step": 382
},
{
"epoch": 2.520879120879121,
"grad_norm": 0.8103930354118347,
"learning_rate": 3.28159645232816e-05,
"loss": 0.8306,
"step": 383
},
{
"epoch": 2.5274725274725274,
"grad_norm": 0.6277719736099243,
"learning_rate": 3.237250554323725e-05,
"loss": 0.7026,
"step": 384
},
{
"epoch": 2.534065934065934,
"grad_norm": 0.7029876708984375,
"learning_rate": 3.19290465631929e-05,
"loss": 0.8211,
"step": 385
},
{
"epoch": 2.5406593406593405,
"grad_norm": 0.6387957334518433,
"learning_rate": 3.148558758314856e-05,
"loss": 0.6529,
"step": 386
},
{
"epoch": 2.547252747252747,
"grad_norm": 0.7103434801101685,
"learning_rate": 3.104212860310421e-05,
"loss": 0.6525,
"step": 387
},
{
"epoch": 2.5538461538461537,
"grad_norm": 0.6053327322006226,
"learning_rate": 3.059866962305987e-05,
"loss": 0.592,
"step": 388
},
{
"epoch": 2.5604395604395602,
"grad_norm": 0.6235735416412354,
"learning_rate": 3.0155210643015524e-05,
"loss": 0.7646,
"step": 389
},
{
"epoch": 2.567032967032967,
"grad_norm": 0.6998478770256042,
"learning_rate": 2.971175166297118e-05,
"loss": 0.6495,
"step": 390
}
],
"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": 6.436155730147738e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}