jeqcho's picture
Upload folder using huggingface_hub
3f77cf5 verified
Raw
History Blame Contribute Delete
16.3 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5934065934065934,
"eval_steps": 500,
"global_step": 90,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006593406593406593,
"grad_norm": 0.8822625875473022,
"learning_rate": 0.0,
"loss": 2.9966,
"step": 1
},
{
"epoch": 0.013186813186813187,
"grad_norm": 1.1069581508636475,
"learning_rate": 4e-05,
"loss": 2.9598,
"step": 2
},
{
"epoch": 0.01978021978021978,
"grad_norm": 0.8758227229118347,
"learning_rate": 8e-05,
"loss": 2.5775,
"step": 3
},
{
"epoch": 0.026373626373626374,
"grad_norm": 1.0401133298873901,
"learning_rate": 0.00012,
"loss": 2.6196,
"step": 4
},
{
"epoch": 0.03296703296703297,
"grad_norm": 1.4041666984558105,
"learning_rate": 0.00016,
"loss": 3.1798,
"step": 5
},
{
"epoch": 0.03956043956043956,
"grad_norm": 1.4210084676742554,
"learning_rate": 0.0002,
"loss": 2.0834,
"step": 6
},
{
"epoch": 0.046153846153846156,
"grad_norm": 2.1845953464508057,
"learning_rate": 0.00019955654101995565,
"loss": 2.3524,
"step": 7
},
{
"epoch": 0.05274725274725275,
"grad_norm": 1.3485188484191895,
"learning_rate": 0.00019911308203991133,
"loss": 1.616,
"step": 8
},
{
"epoch": 0.05934065934065934,
"grad_norm": 1.0533819198608398,
"learning_rate": 0.00019866962305986697,
"loss": 1.2391,
"step": 9
},
{
"epoch": 0.06593406593406594,
"grad_norm": 1.1041414737701416,
"learning_rate": 0.00019822616407982261,
"loss": 1.0831,
"step": 10
},
{
"epoch": 0.07252747252747253,
"grad_norm": 0.7204957604408264,
"learning_rate": 0.00019778270509977829,
"loss": 0.8896,
"step": 11
},
{
"epoch": 0.07912087912087912,
"grad_norm": 0.7176511287689209,
"learning_rate": 0.00019733924611973393,
"loss": 0.8995,
"step": 12
},
{
"epoch": 0.08571428571428572,
"grad_norm": 0.7679543495178223,
"learning_rate": 0.0001968957871396896,
"loss": 0.7737,
"step": 13
},
{
"epoch": 0.09230769230769231,
"grad_norm": 0.8583915829658508,
"learning_rate": 0.00019645232815964525,
"loss": 0.8345,
"step": 14
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.5992399454116821,
"learning_rate": 0.00019600886917960092,
"loss": 0.7105,
"step": 15
},
{
"epoch": 0.1054945054945055,
"grad_norm": 0.5483726859092712,
"learning_rate": 0.00019556541019955653,
"loss": 0.7893,
"step": 16
},
{
"epoch": 0.11208791208791209,
"grad_norm": 0.47341662645339966,
"learning_rate": 0.0001951219512195122,
"loss": 0.8783,
"step": 17
},
{
"epoch": 0.11868131868131868,
"grad_norm": 0.4923449456691742,
"learning_rate": 0.00019467849223946785,
"loss": 0.5529,
"step": 18
},
{
"epoch": 0.12527472527472527,
"grad_norm": 0.382350355386734,
"learning_rate": 0.00019423503325942352,
"loss": 0.6698,
"step": 19
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.43962135910987854,
"learning_rate": 0.00019379157427937917,
"loss": 0.6906,
"step": 20
},
{
"epoch": 0.13846153846153847,
"grad_norm": 0.6100013256072998,
"learning_rate": 0.00019334811529933484,
"loss": 0.7102,
"step": 21
},
{
"epoch": 0.14505494505494507,
"grad_norm": 0.4505807161331177,
"learning_rate": 0.00019290465631929045,
"loss": 0.5965,
"step": 22
},
{
"epoch": 0.15164835164835164,
"grad_norm": 0.420966774225235,
"learning_rate": 0.00019246119733924613,
"loss": 0.8076,
"step": 23
},
{
"epoch": 0.15824175824175823,
"grad_norm": 0.37792259454727173,
"learning_rate": 0.00019201773835920177,
"loss": 0.4851,
"step": 24
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.39667177200317383,
"learning_rate": 0.00019157427937915744,
"loss": 0.7452,
"step": 25
},
{
"epoch": 0.17142857142857143,
"grad_norm": 0.35318464040756226,
"learning_rate": 0.00019113082039911309,
"loss": 0.7378,
"step": 26
},
{
"epoch": 0.17802197802197803,
"grad_norm": 0.34349656105041504,
"learning_rate": 0.00019068736141906876,
"loss": 0.6639,
"step": 27
},
{
"epoch": 0.18461538461538463,
"grad_norm": 0.37496012449264526,
"learning_rate": 0.0001902439024390244,
"loss": 0.5393,
"step": 28
},
{
"epoch": 0.1912087912087912,
"grad_norm": 0.42517000436782837,
"learning_rate": 0.00018980044345898005,
"loss": 0.6226,
"step": 29
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.365597128868103,
"learning_rate": 0.00018935698447893572,
"loss": 0.5503,
"step": 30
},
{
"epoch": 0.2043956043956044,
"grad_norm": 0.4194570481777191,
"learning_rate": 0.00018891352549889136,
"loss": 0.6564,
"step": 31
},
{
"epoch": 0.210989010989011,
"grad_norm": 0.400821328163147,
"learning_rate": 0.00018847006651884703,
"loss": 0.7257,
"step": 32
},
{
"epoch": 0.2175824175824176,
"grad_norm": 0.4243015646934509,
"learning_rate": 0.00018802660753880268,
"loss": 0.5831,
"step": 33
},
{
"epoch": 0.22417582417582418,
"grad_norm": 0.4274579584598541,
"learning_rate": 0.00018758314855875832,
"loss": 0.6801,
"step": 34
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.30914393067359924,
"learning_rate": 0.00018713968957871397,
"loss": 0.4985,
"step": 35
},
{
"epoch": 0.23736263736263735,
"grad_norm": 0.36418190598487854,
"learning_rate": 0.00018669623059866964,
"loss": 0.506,
"step": 36
},
{
"epoch": 0.24395604395604395,
"grad_norm": 0.5366491079330444,
"learning_rate": 0.00018625277161862528,
"loss": 0.6998,
"step": 37
},
{
"epoch": 0.25054945054945055,
"grad_norm": 0.40732792019844055,
"learning_rate": 0.00018580931263858095,
"loss": 0.6035,
"step": 38
},
{
"epoch": 0.2571428571428571,
"grad_norm": 0.41157761216163635,
"learning_rate": 0.0001853658536585366,
"loss": 0.5741,
"step": 39
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.49116623401641846,
"learning_rate": 0.00018492239467849224,
"loss": 0.5644,
"step": 40
},
{
"epoch": 0.2703296703296703,
"grad_norm": 0.43378788232803345,
"learning_rate": 0.0001844789356984479,
"loss": 0.5459,
"step": 41
},
{
"epoch": 0.27692307692307694,
"grad_norm": 0.43929198384284973,
"learning_rate": 0.00018403547671840356,
"loss": 0.4644,
"step": 42
},
{
"epoch": 0.2835164835164835,
"grad_norm": 0.40316739678382874,
"learning_rate": 0.0001835920177383592,
"loss": 0.6401,
"step": 43
},
{
"epoch": 0.29010989010989013,
"grad_norm": 0.41275328397750854,
"learning_rate": 0.00018314855875831487,
"loss": 0.601,
"step": 44
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.2872825264930725,
"learning_rate": 0.00018270509977827052,
"loss": 0.4375,
"step": 45
},
{
"epoch": 0.3032967032967033,
"grad_norm": 0.4530083239078522,
"learning_rate": 0.00018226164079822616,
"loss": 0.7684,
"step": 46
},
{
"epoch": 0.3098901098901099,
"grad_norm": 0.31746530532836914,
"learning_rate": 0.00018181818181818183,
"loss": 0.5948,
"step": 47
},
{
"epoch": 0.31648351648351647,
"grad_norm": 0.35115814208984375,
"learning_rate": 0.00018137472283813748,
"loss": 0.6928,
"step": 48
},
{
"epoch": 0.3230769230769231,
"grad_norm": 0.29176679253578186,
"learning_rate": 0.00018093126385809312,
"loss": 0.5716,
"step": 49
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.356320858001709,
"learning_rate": 0.0001804878048780488,
"loss": 0.5595,
"step": 50
},
{
"epoch": 0.3362637362637363,
"grad_norm": 0.33391836285591125,
"learning_rate": 0.00018004434589800444,
"loss": 0.5823,
"step": 51
},
{
"epoch": 0.34285714285714286,
"grad_norm": 0.35161083936691284,
"learning_rate": 0.00017960088691796008,
"loss": 0.5482,
"step": 52
},
{
"epoch": 0.34945054945054943,
"grad_norm": 0.31787368655204773,
"learning_rate": 0.00017915742793791575,
"loss": 0.5471,
"step": 53
},
{
"epoch": 0.35604395604395606,
"grad_norm": 0.2908938527107239,
"learning_rate": 0.0001787139689578714,
"loss": 0.5348,
"step": 54
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.34024009108543396,
"learning_rate": 0.00017827050997782707,
"loss": 0.4426,
"step": 55
},
{
"epoch": 0.36923076923076925,
"grad_norm": 0.40695953369140625,
"learning_rate": 0.00017782705099778271,
"loss": 0.5771,
"step": 56
},
{
"epoch": 0.3758241758241758,
"grad_norm": 0.49275121092796326,
"learning_rate": 0.00017738359201773839,
"loss": 0.544,
"step": 57
},
{
"epoch": 0.3824175824175824,
"grad_norm": 0.4099092483520508,
"learning_rate": 0.000176940133037694,
"loss": 0.5028,
"step": 58
},
{
"epoch": 0.389010989010989,
"grad_norm": 0.31285232305526733,
"learning_rate": 0.00017649667405764967,
"loss": 0.5137,
"step": 59
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.414304256439209,
"learning_rate": 0.00017605321507760532,
"loss": 0.4803,
"step": 60
},
{
"epoch": 0.4021978021978022,
"grad_norm": 0.4016311466693878,
"learning_rate": 0.000175609756097561,
"loss": 0.5934,
"step": 61
},
{
"epoch": 0.4087912087912088,
"grad_norm": 0.30074217915534973,
"learning_rate": 0.00017516629711751663,
"loss": 0.461,
"step": 62
},
{
"epoch": 0.4153846153846154,
"grad_norm": 0.3320770859718323,
"learning_rate": 0.0001747228381374723,
"loss": 0.5756,
"step": 63
},
{
"epoch": 0.421978021978022,
"grad_norm": 0.37848159670829773,
"learning_rate": 0.00017427937915742792,
"loss": 0.6247,
"step": 64
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.3719041347503662,
"learning_rate": 0.0001738359201773836,
"loss": 0.5425,
"step": 65
},
{
"epoch": 0.4351648351648352,
"grad_norm": 0.3609648644924164,
"learning_rate": 0.00017339246119733924,
"loss": 0.484,
"step": 66
},
{
"epoch": 0.44175824175824174,
"grad_norm": 0.32436180114746094,
"learning_rate": 0.0001729490022172949,
"loss": 0.5081,
"step": 67
},
{
"epoch": 0.44835164835164837,
"grad_norm": 0.33831897377967834,
"learning_rate": 0.00017250554323725056,
"loss": 0.5861,
"step": 68
},
{
"epoch": 0.45494505494505494,
"grad_norm": 0.26558148860931396,
"learning_rate": 0.00017206208425720623,
"loss": 0.6159,
"step": 69
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.32884278893470764,
"learning_rate": 0.00017161862527716187,
"loss": 0.5497,
"step": 70
},
{
"epoch": 0.46813186813186813,
"grad_norm": 0.34436213970184326,
"learning_rate": 0.00017117516629711752,
"loss": 0.4994,
"step": 71
},
{
"epoch": 0.4747252747252747,
"grad_norm": 0.3457243740558624,
"learning_rate": 0.0001707317073170732,
"loss": 0.6952,
"step": 72
},
{
"epoch": 0.48131868131868133,
"grad_norm": 0.310139536857605,
"learning_rate": 0.00017028824833702883,
"loss": 0.5439,
"step": 73
},
{
"epoch": 0.4879120879120879,
"grad_norm": 0.417996346950531,
"learning_rate": 0.0001698447893569845,
"loss": 0.5534,
"step": 74
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.35336464643478394,
"learning_rate": 0.00016940133037694015,
"loss": 0.4557,
"step": 75
},
{
"epoch": 0.5010989010989011,
"grad_norm": 0.3493141233921051,
"learning_rate": 0.00016895787139689582,
"loss": 0.5587,
"step": 76
},
{
"epoch": 0.5076923076923077,
"grad_norm": 0.38658949732780457,
"learning_rate": 0.00016851441241685144,
"loss": 0.64,
"step": 77
},
{
"epoch": 0.5142857142857142,
"grad_norm": 0.4228934049606323,
"learning_rate": 0.0001680709534368071,
"loss": 0.7367,
"step": 78
},
{
"epoch": 0.5208791208791209,
"grad_norm": 0.38229817152023315,
"learning_rate": 0.00016762749445676275,
"loss": 0.5983,
"step": 79
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.3111512362957001,
"learning_rate": 0.00016718403547671842,
"loss": 0.601,
"step": 80
},
{
"epoch": 0.5340659340659341,
"grad_norm": 0.3454195261001587,
"learning_rate": 0.00016674057649667407,
"loss": 0.4988,
"step": 81
},
{
"epoch": 0.5406593406593406,
"grad_norm": 0.3082880675792694,
"learning_rate": 0.00016629711751662974,
"loss": 0.3354,
"step": 82
},
{
"epoch": 0.5472527472527473,
"grad_norm": 0.3996518552303314,
"learning_rate": 0.00016585365853658536,
"loss": 0.5782,
"step": 83
},
{
"epoch": 0.5538461538461539,
"grad_norm": 0.3453790843486786,
"learning_rate": 0.00016541019955654103,
"loss": 0.604,
"step": 84
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.3558626174926758,
"learning_rate": 0.00016496674057649667,
"loss": 0.4868,
"step": 85
},
{
"epoch": 0.567032967032967,
"grad_norm": 0.3380248248577118,
"learning_rate": 0.00016452328159645234,
"loss": 0.6232,
"step": 86
},
{
"epoch": 0.5736263736263736,
"grad_norm": 0.3425062298774719,
"learning_rate": 0.000164079822616408,
"loss": 0.6562,
"step": 87
},
{
"epoch": 0.5802197802197803,
"grad_norm": 0.31318148970603943,
"learning_rate": 0.00016363636363636366,
"loss": 0.4692,
"step": 88
},
{
"epoch": 0.5868131868131868,
"grad_norm": 0.3718196153640747,
"learning_rate": 0.0001631929046563193,
"loss": 0.7078,
"step": 89
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.34966057538986206,
"learning_rate": 0.00016274944567627495,
"loss": 0.5526,
"step": 90
}
],
"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": 3.992823349569331e+16,
"train_batch_size": 22,
"trial_name": null,
"trial_params": null
}