jeqcho's picture
Upload folder using huggingface_hub
726fc63 verified
Raw
History Blame Contribute Delete
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": 1.2240082025527954,
"learning_rate": 0.0,
"loss": 3.2004,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 1.1817413568496704,
"learning_rate": 4e-05,
"loss": 2.9195,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 1.089200496673584,
"learning_rate": 8e-05,
"loss": 2.9322,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.23591947555542,
"learning_rate": 0.00012,
"loss": 2.493,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 1.2914438247680664,
"learning_rate": 0.00016,
"loss": 2.6719,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 1.425159215927124,
"learning_rate": 0.0002,
"loss": 2.0729,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 1.8763092756271362,
"learning_rate": 0.00019955654101995565,
"loss": 2.063,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 1.2933986186981201,
"learning_rate": 0.00019911308203991133,
"loss": 1.4339,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 1.5251818895339966,
"learning_rate": 0.00019866962305986697,
"loss": 1.5351,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.9210705161094666,
"learning_rate": 0.00019822616407982261,
"loss": 1.1847,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.8823724389076233,
"learning_rate": 0.00019778270509977829,
"loss": 0.9696,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.8065115809440613,
"learning_rate": 0.00019733924611973393,
"loss": 1.0103,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.8599637150764465,
"learning_rate": 0.0001968957871396896,
"loss": 0.7631,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.7091007232666016,
"learning_rate": 0.00019645232815964525,
"loss": 0.774,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.5932487845420837,
"learning_rate": 0.00019600886917960092,
"loss": 0.7102,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.5805957317352295,
"learning_rate": 0.00019556541019955653,
"loss": 0.8034,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.5351698398590088,
"learning_rate": 0.0001951219512195122,
"loss": 0.7074,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.5085647106170654,
"learning_rate": 0.00019467849223946785,
"loss": 0.7856,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.4852818250656128,
"learning_rate": 0.00019423503325942352,
"loss": 0.6869,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.4774964451789856,
"learning_rate": 0.00019379157427937917,
"loss": 0.5578,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.4320865273475647,
"learning_rate": 0.00019334811529933484,
"loss": 0.6558,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.5121509432792664,
"learning_rate": 0.00019290465631929045,
"loss": 0.7886,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.43891361355781555,
"learning_rate": 0.00019246119733924613,
"loss": 0.6733,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.4488874077796936,
"learning_rate": 0.00019201773835920177,
"loss": 0.6966,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.42902886867523193,
"learning_rate": 0.00019157427937915744,
"loss": 0.75,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.42811888456344604,
"learning_rate": 0.00019113082039911309,
"loss": 0.5749,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.38084888458251953,
"learning_rate": 0.00019068736141906876,
"loss": 0.6558,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.39865079522132874,
"learning_rate": 0.0001902439024390244,
"loss": 0.6655,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.29908454418182373,
"learning_rate": 0.00018980044345898005,
"loss": 0.5844,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.38320380449295044,
"learning_rate": 0.00018935698447893572,
"loss": 0.6285,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.44202783703804016,
"learning_rate": 0.00018891352549889136,
"loss": 0.7849,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.34681448340415955,
"learning_rate": 0.00018847006651884703,
"loss": 0.5957,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.3555922210216522,
"learning_rate": 0.00018802660753880268,
"loss": 0.6433,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.7906959056854248,
"learning_rate": 0.00018758314855875832,
"loss": 0.7658,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.4097070097923279,
"learning_rate": 0.00018713968957871397,
"loss": 0.7638,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.36098968982696533,
"learning_rate": 0.00018669623059866964,
"loss": 0.5424,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.3689538836479187,
"learning_rate": 0.00018625277161862528,
"loss": 0.6799,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.3969242572784424,
"learning_rate": 0.00018580931263858095,
"loss": 0.5619,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.41041359305381775,
"learning_rate": 0.0001853658536585366,
"loss": 0.7333,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.33059433102607727,
"learning_rate": 0.00018492239467849224,
"loss": 0.5086,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.428994745016098,
"learning_rate": 0.0001844789356984479,
"loss": 0.526,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.3604447841644287,
"learning_rate": 0.00018403547671840356,
"loss": 0.575,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.3401334881782532,
"learning_rate": 0.0001835920177383592,
"loss": 0.5467,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.41614830493927,
"learning_rate": 0.00018314855875831487,
"loss": 0.5289,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.4010107219219208,
"learning_rate": 0.00018270509977827052,
"loss": 0.5476,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.31574419140815735,
"learning_rate": 0.00018226164079822616,
"loss": 0.4687,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.42631375789642334,
"learning_rate": 0.00018181818181818183,
"loss": 0.7165,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.45691990852355957,
"learning_rate": 0.00018137472283813748,
"loss": 0.6254,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.34974104166030884,
"learning_rate": 0.00018093126385809312,
"loss": 0.7309,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.4650188684463501,
"learning_rate": 0.0001804878048780488,
"loss": 0.679,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.3808349668979645,
"learning_rate": 0.00018004434589800444,
"loss": 0.7072,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.39578449726104736,
"learning_rate": 0.00017960088691796008,
"loss": 0.6168,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.4203926920890808,
"learning_rate": 0.00017915742793791575,
"loss": 0.5618,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.3733426332473755,
"learning_rate": 0.0001787139689578714,
"loss": 0.5847,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.3396105468273163,
"learning_rate": 0.00017827050997782707,
"loss": 0.4976,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.3268498182296753,
"learning_rate": 0.00017782705099778271,
"loss": 0.4698,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.34606558084487915,
"learning_rate": 0.00017738359201773839,
"loss": 0.5485,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.3481427729129791,
"learning_rate": 0.000176940133037694,
"loss": 0.537,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.4629095792770386,
"learning_rate": 0.00017649667405764967,
"loss": 0.5555,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.462342768907547,
"learning_rate": 0.00017605321507760532,
"loss": 0.6044,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.43930208683013916,
"learning_rate": 0.000175609756097561,
"loss": 0.6379,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.4079689383506775,
"learning_rate": 0.00017516629711751663,
"loss": 0.495,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.5146216154098511,
"learning_rate": 0.0001747228381374723,
"loss": 0.645,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.3735997676849365,
"learning_rate": 0.00017427937915742792,
"loss": 0.6333,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.462772011756897,
"learning_rate": 0.0001738359201773836,
"loss": 0.5522,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.46557778120040894,
"learning_rate": 0.00017339246119733924,
"loss": 0.4982,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.422385036945343,
"learning_rate": 0.0001729490022172949,
"loss": 0.498,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.3375857174396515,
"learning_rate": 0.00017250554323725056,
"loss": 0.6013,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.29001280665397644,
"learning_rate": 0.00017206208425720623,
"loss": 0.5406,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.4896228015422821,
"learning_rate": 0.00017161862527716187,
"loss": 0.5926,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.3039141297340393,
"learning_rate": 0.00017117516629711752,
"loss": 0.5804,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.3966655731201172,
"learning_rate": 0.0001707317073170732,
"loss": 0.6625,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.4385382831096649,
"learning_rate": 0.00017028824833702883,
"loss": 0.5815,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.40156519412994385,
"learning_rate": 0.0001698447893569845,
"loss": 0.6006,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.37846580147743225,
"learning_rate": 0.00016940133037694015,
"loss": 0.5044,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.3760215938091278,
"learning_rate": 0.00016895787139689582,
"loss": 0.501,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.4516732394695282,
"learning_rate": 0.00016851441241685144,
"loss": 0.4967,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.3656870126724243,
"learning_rate": 0.0001680709534368071,
"loss": 0.5011,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.31711170077323914,
"learning_rate": 0.00016762749445676275,
"loss": 0.4302,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.40144112706184387,
"learning_rate": 0.00016718403547671842,
"loss": 0.5364,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.37173205614089966,
"learning_rate": 0.00016674057649667407,
"loss": 0.4019,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.352626234292984,
"learning_rate": 0.00016629711751662974,
"loss": 0.592,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.3332176208496094,
"learning_rate": 0.00016585365853658536,
"loss": 0.4131,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.3604816198348999,
"learning_rate": 0.00016541019955654103,
"loss": 0.5192,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.3146759271621704,
"learning_rate": 0.00016496674057649667,
"loss": 0.4339,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.35468390583992004,
"learning_rate": 0.00016452328159645234,
"loss": 0.4299,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.4313686788082123,
"learning_rate": 0.000164079822616408,
"loss": 0.5436,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.3751888871192932,
"learning_rate": 0.00016363636363636366,
"loss": 0.493,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.39044705033302307,
"learning_rate": 0.0001631929046563193,
"loss": 0.6177,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.3849164843559265,
"learning_rate": 0.00016274944567627495,
"loss": 0.4894,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.40703052282333374,
"learning_rate": 0.0001623059866962306,
"loss": 0.545,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.367977112531662,
"learning_rate": 0.00016186252771618626,
"loss": 0.452,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.5252164006233215,
"learning_rate": 0.0001614190687361419,
"loss": 0.4366,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.4373919665813446,
"learning_rate": 0.00016097560975609758,
"loss": 0.5665,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.3770761489868164,
"learning_rate": 0.00016053215077605322,
"loss": 0.4594,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.6411177515983582,
"learning_rate": 0.00016008869179600887,
"loss": 0.5672,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.5393151640892029,
"learning_rate": 0.00015964523281596454,
"loss": 0.5241,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.3491095006465912,
"learning_rate": 0.00015920177383592018,
"loss": 0.6669,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.4589627981185913,
"learning_rate": 0.00015875831485587586,
"loss": 0.5866,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.41086679697036743,
"learning_rate": 0.0001583148558758315,
"loss": 0.5123,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.5647931098937988,
"learning_rate": 0.00015787139689578714,
"loss": 0.6576,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.36647412180900574,
"learning_rate": 0.0001574279379157428,
"loss": 0.5656,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.3683735728263855,
"learning_rate": 0.00015698447893569846,
"loss": 0.5391,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.4131142497062683,
"learning_rate": 0.0001565410199556541,
"loss": 0.5337,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.3431665599346161,
"learning_rate": 0.00015609756097560978,
"loss": 0.4085,
"step": 105
},
{
"epoch": 0.6989010989010989,
"grad_norm": 0.4302043914794922,
"learning_rate": 0.00015565410199556542,
"loss": 0.5011,
"step": 106
},
{
"epoch": 0.7054945054945055,
"grad_norm": 0.3393073081970215,
"learning_rate": 0.00015521064301552106,
"loss": 0.3961,
"step": 107
},
{
"epoch": 0.7120879120879121,
"grad_norm": 0.45697256922721863,
"learning_rate": 0.0001547671840354767,
"loss": 0.4796,
"step": 108
},
{
"epoch": 0.7186813186813187,
"grad_norm": 0.4157907962799072,
"learning_rate": 0.00015432372505543238,
"loss": 0.5821,
"step": 109
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.507879912853241,
"learning_rate": 0.00015388026607538802,
"loss": 0.6692,
"step": 110
},
{
"epoch": 0.7318681318681318,
"grad_norm": 0.3931836485862732,
"learning_rate": 0.0001534368070953437,
"loss": 0.4588,
"step": 111
},
{
"epoch": 0.7384615384615385,
"grad_norm": 0.427739679813385,
"learning_rate": 0.00015299334811529934,
"loss": 0.4788,
"step": 112
},
{
"epoch": 0.7450549450549451,
"grad_norm": 0.37858736515045166,
"learning_rate": 0.00015254988913525498,
"loss": 0.5924,
"step": 113
},
{
"epoch": 0.7516483516483516,
"grad_norm": 0.4577133059501648,
"learning_rate": 0.00015210643015521066,
"loss": 0.5587,
"step": 114
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.40195730328559875,
"learning_rate": 0.0001516629711751663,
"loss": 0.6127,
"step": 115
},
{
"epoch": 0.7648351648351648,
"grad_norm": 0.4415499269962311,
"learning_rate": 0.00015121951219512197,
"loss": 0.6255,
"step": 116
},
{
"epoch": 0.7714285714285715,
"grad_norm": 0.5513373017311096,
"learning_rate": 0.00015077605321507762,
"loss": 0.653,
"step": 117
},
{
"epoch": 0.778021978021978,
"grad_norm": 0.6036509871482849,
"learning_rate": 0.0001503325942350333,
"loss": 0.6635,
"step": 118
},
{
"epoch": 0.7846153846153846,
"grad_norm": 0.3825967311859131,
"learning_rate": 0.0001498891352549889,
"loss": 0.4513,
"step": 119
},
{
"epoch": 0.7912087912087912,
"grad_norm": 0.48890331387519836,
"learning_rate": 0.00014944567627494458,
"loss": 0.5639,
"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": 5.042719022513357e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}