jeqcho's picture
Upload folder using huggingface_hub
073f1dc verified
Raw
History Blame Contribute Delete
18.9 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6923076923076923,
"eval_steps": 500,
"global_step": 105,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 1.1258277893066406,
"learning_rate": 0.0,
"loss": 3.0295,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 1.0469061136245728,
"learning_rate": 4e-05,
"loss": 2.8199,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 0.9328632354736328,
"learning_rate": 8e-05,
"loss": 2.6328,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.3742667436599731,
"learning_rate": 0.00012,
"loss": 2.9986,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 1.3568042516708374,
"learning_rate": 0.00016,
"loss": 2.5623,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 1.9343546628952026,
"learning_rate": 0.0002,
"loss": 2.5039,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 1.6630727052688599,
"learning_rate": 0.00019955654101995565,
"loss": 1.7366,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 1.5585440397262573,
"learning_rate": 0.00019911308203991133,
"loss": 1.8155,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 0.9433563351631165,
"learning_rate": 0.00019866962305986697,
"loss": 1.1226,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.9606233835220337,
"learning_rate": 0.00019822616407982261,
"loss": 1.0042,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.7951949238777161,
"learning_rate": 0.00019778270509977829,
"loss": 0.9564,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.7159879207611084,
"learning_rate": 0.00019733924611973393,
"loss": 0.7373,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.805880069732666,
"learning_rate": 0.0001968957871396896,
"loss": 0.792,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.6829606294631958,
"learning_rate": 0.00019645232815964525,
"loss": 0.6215,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.5796816945075989,
"learning_rate": 0.00019600886917960092,
"loss": 0.8198,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.5503753423690796,
"learning_rate": 0.00019556541019955653,
"loss": 0.7578,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.5514731407165527,
"learning_rate": 0.0001951219512195122,
"loss": 0.7522,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.4225347340106964,
"learning_rate": 0.00019467849223946785,
"loss": 0.6527,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.4526655375957489,
"learning_rate": 0.00019423503325942352,
"loss": 0.607,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.481832891702652,
"learning_rate": 0.00019379157427937917,
"loss": 0.6847,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.4877224862575531,
"learning_rate": 0.00019334811529933484,
"loss": 0.7136,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.3743646740913391,
"learning_rate": 0.00019290465631929045,
"loss": 0.5966,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.4489605128765106,
"learning_rate": 0.00019246119733924613,
"loss": 0.6452,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.45275574922561646,
"learning_rate": 0.00019201773835920177,
"loss": 0.5869,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.4297250807285309,
"learning_rate": 0.00019157427937915744,
"loss": 0.61,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.3726891875267029,
"learning_rate": 0.00019113082039911309,
"loss": 0.6145,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.38317251205444336,
"learning_rate": 0.00019068736141906876,
"loss": 0.6995,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.39017173647880554,
"learning_rate": 0.0001902439024390244,
"loss": 0.5878,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.3254614472389221,
"learning_rate": 0.00018980044345898005,
"loss": 0.501,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.47432705760002136,
"learning_rate": 0.00018935698447893572,
"loss": 0.62,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.4453403055667877,
"learning_rate": 0.00018891352549889136,
"loss": 0.6706,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.35256972908973694,
"learning_rate": 0.00018847006651884703,
"loss": 0.5292,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.36604660749435425,
"learning_rate": 0.00018802660753880268,
"loss": 0.537,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.36700016260147095,
"learning_rate": 0.00018758314855875832,
"loss": 0.5214,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.29663094878196716,
"learning_rate": 0.00018713968957871397,
"loss": 0.5031,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.28732767701148987,
"learning_rate": 0.00018669623059866964,
"loss": 0.4768,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.3642386794090271,
"learning_rate": 0.00018625277161862528,
"loss": 0.574,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.40244248509407043,
"learning_rate": 0.00018580931263858095,
"loss": 0.4877,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.3658510744571686,
"learning_rate": 0.0001853658536585366,
"loss": 0.5191,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.4025786817073822,
"learning_rate": 0.00018492239467849224,
"loss": 0.5328,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.41957223415374756,
"learning_rate": 0.0001844789356984479,
"loss": 0.5718,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.3137666881084442,
"learning_rate": 0.00018403547671840356,
"loss": 0.4743,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.4241214692592621,
"learning_rate": 0.0001835920177383592,
"loss": 0.5761,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.35041534900665283,
"learning_rate": 0.00018314855875831487,
"loss": 0.5104,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.44434788823127747,
"learning_rate": 0.00018270509977827052,
"loss": 0.539,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.30492666363716125,
"learning_rate": 0.00018226164079822616,
"loss": 0.6963,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.38742250204086304,
"learning_rate": 0.00018181818181818183,
"loss": 0.5314,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.3342526853084564,
"learning_rate": 0.00018137472283813748,
"loss": 0.5585,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.3805127739906311,
"learning_rate": 0.00018093126385809312,
"loss": 0.5723,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.3670502007007599,
"learning_rate": 0.0001804878048780488,
"loss": 0.5283,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.3458058834075928,
"learning_rate": 0.00018004434589800444,
"loss": 0.4398,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.4033033549785614,
"learning_rate": 0.00017960088691796008,
"loss": 0.5544,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.3558763563632965,
"learning_rate": 0.00017915742793791575,
"loss": 0.4877,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.3886813521385193,
"learning_rate": 0.0001787139689578714,
"loss": 0.6995,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.38272568583488464,
"learning_rate": 0.00017827050997782707,
"loss": 0.4899,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.48774710297584534,
"learning_rate": 0.00017782705099778271,
"loss": 0.5643,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.42786574363708496,
"learning_rate": 0.00017738359201773839,
"loss": 0.5489,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.3868570923805237,
"learning_rate": 0.000176940133037694,
"loss": 0.5215,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.3829129934310913,
"learning_rate": 0.00017649667405764967,
"loss": 0.5186,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.329976886510849,
"learning_rate": 0.00017605321507760532,
"loss": 0.5287,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.3485603332519531,
"learning_rate": 0.000175609756097561,
"loss": 0.5313,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.3575219511985779,
"learning_rate": 0.00017516629711751663,
"loss": 0.5349,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.3275308310985565,
"learning_rate": 0.0001747228381374723,
"loss": 0.4863,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.42464715242385864,
"learning_rate": 0.00017427937915742792,
"loss": 0.5776,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.3628101646900177,
"learning_rate": 0.0001738359201773836,
"loss": 0.5751,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.3428574502468109,
"learning_rate": 0.00017339246119733924,
"loss": 0.4941,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.2916024923324585,
"learning_rate": 0.0001729490022172949,
"loss": 0.4345,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.33352556824684143,
"learning_rate": 0.00017250554323725056,
"loss": 0.4253,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.3252923786640167,
"learning_rate": 0.00017206208425720623,
"loss": 0.4447,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.3962821364402771,
"learning_rate": 0.00017161862527716187,
"loss": 0.4752,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.49113529920578003,
"learning_rate": 0.00017117516629711752,
"loss": 0.5114,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.35567113757133484,
"learning_rate": 0.0001707317073170732,
"loss": 0.4933,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.3056921660900116,
"learning_rate": 0.00017028824833702883,
"loss": 0.4618,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.42156627774238586,
"learning_rate": 0.0001698447893569845,
"loss": 0.5053,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.4406984746456146,
"learning_rate": 0.00016940133037694015,
"loss": 0.5012,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.42425596714019775,
"learning_rate": 0.00016895787139689582,
"loss": 0.5621,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.35644426941871643,
"learning_rate": 0.00016851441241685144,
"loss": 0.5384,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.28911274671554565,
"learning_rate": 0.0001680709534368071,
"loss": 0.508,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.32456129789352417,
"learning_rate": 0.00016762749445676275,
"loss": 0.6684,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.4201291501522064,
"learning_rate": 0.00016718403547671842,
"loss": 0.4951,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.4306047558784485,
"learning_rate": 0.00016674057649667407,
"loss": 0.4994,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.3155696988105774,
"learning_rate": 0.00016629711751662974,
"loss": 0.4537,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.33225157856941223,
"learning_rate": 0.00016585365853658536,
"loss": 0.4942,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.4080914556980133,
"learning_rate": 0.00016541019955654103,
"loss": 0.6126,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.3456087112426758,
"learning_rate": 0.00016496674057649667,
"loss": 0.3832,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.34410449862480164,
"learning_rate": 0.00016452328159645234,
"loss": 0.4581,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.3481915295124054,
"learning_rate": 0.000164079822616408,
"loss": 0.5581,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.4316079318523407,
"learning_rate": 0.00016363636363636366,
"loss": 0.5078,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.4453663229942322,
"learning_rate": 0.0001631929046563193,
"loss": 0.5025,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.3725511133670807,
"learning_rate": 0.00016274944567627495,
"loss": 0.5028,
"step": 90
},
{
"epoch": 0.6,
"grad_norm": 0.41532671451568604,
"learning_rate": 0.0001623059866962306,
"loss": 0.5095,
"step": 91
},
{
"epoch": 0.6065934065934065,
"grad_norm": 0.2991493344306946,
"learning_rate": 0.00016186252771618626,
"loss": 0.3922,
"step": 92
},
{
"epoch": 0.6131868131868132,
"grad_norm": 0.422572523355484,
"learning_rate": 0.0001614190687361419,
"loss": 0.4997,
"step": 93
},
{
"epoch": 0.6197802197802198,
"grad_norm": 0.3846403658390045,
"learning_rate": 0.00016097560975609758,
"loss": 0.4912,
"step": 94
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.3804264962673187,
"learning_rate": 0.00016053215077605322,
"loss": 0.4565,
"step": 95
},
{
"epoch": 0.6329670329670329,
"grad_norm": 0.34783074259757996,
"learning_rate": 0.00016008869179600887,
"loss": 0.53,
"step": 96
},
{
"epoch": 0.6395604395604395,
"grad_norm": 0.3216366171836853,
"learning_rate": 0.00015964523281596454,
"loss": 0.4462,
"step": 97
},
{
"epoch": 0.6461538461538462,
"grad_norm": 0.41518279910087585,
"learning_rate": 0.00015920177383592018,
"loss": 0.5432,
"step": 98
},
{
"epoch": 0.6527472527472528,
"grad_norm": 0.38873574137687683,
"learning_rate": 0.00015875831485587586,
"loss": 0.468,
"step": 99
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.415010541677475,
"learning_rate": 0.0001583148558758315,
"loss": 0.5427,
"step": 100
},
{
"epoch": 0.6659340659340659,
"grad_norm": 0.48093146085739136,
"learning_rate": 0.00015787139689578714,
"loss": 0.4513,
"step": 101
},
{
"epoch": 0.6725274725274726,
"grad_norm": 0.2963591516017914,
"learning_rate": 0.0001574279379157428,
"loss": 0.4207,
"step": 102
},
{
"epoch": 0.6791208791208792,
"grad_norm": 0.3437178134918213,
"learning_rate": 0.00015698447893569846,
"loss": 0.4672,
"step": 103
},
{
"epoch": 0.6857142857142857,
"grad_norm": 0.4175635874271393,
"learning_rate": 0.0001565410199556541,
"loss": 0.4549,
"step": 104
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.5979942679405212,
"learning_rate": 0.00015609756097560978,
"loss": 0.5752,
"step": 105
}
],
"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": 4.225041515261952e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}