jssky's picture
Training in progress, step 198, checkpoint
f6f154f verified
raw
history blame
35.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 50,
"global_step": 198,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005050505050505051,
"grad_norm": 23.029043197631836,
"learning_rate": 2e-05,
"loss": 2.6769,
"step": 1
},
{
"epoch": 0.010101010101010102,
"grad_norm": 634.5021362304688,
"learning_rate": 4e-05,
"loss": 3.2691,
"step": 2
},
{
"epoch": 0.015151515151515152,
"grad_norm": 87.77198028564453,
"learning_rate": 6e-05,
"loss": 2.2667,
"step": 3
},
{
"epoch": 0.020202020202020204,
"grad_norm": 27.21422576904297,
"learning_rate": 8e-05,
"loss": 3.2698,
"step": 4
},
{
"epoch": 0.025252525252525252,
"grad_norm": 17.437393188476562,
"learning_rate": 0.0001,
"loss": 2.2537,
"step": 5
},
{
"epoch": 0.030303030303030304,
"grad_norm": 21.726999282836914,
"learning_rate": 0.00012,
"loss": 2.7696,
"step": 6
},
{
"epoch": 0.03535353535353535,
"grad_norm": 14.650723457336426,
"learning_rate": 0.00014,
"loss": 1.979,
"step": 7
},
{
"epoch": 0.04040404040404041,
"grad_norm": 15.102992057800293,
"learning_rate": 0.00016,
"loss": 1.5791,
"step": 8
},
{
"epoch": 0.045454545454545456,
"grad_norm": 17.626737594604492,
"learning_rate": 0.00018,
"loss": 1.4636,
"step": 9
},
{
"epoch": 0.050505050505050504,
"grad_norm": 25.798032760620117,
"learning_rate": 0.0002,
"loss": 1.5067,
"step": 10
},
{
"epoch": 0.05555555555555555,
"grad_norm": 27.792566299438477,
"learning_rate": 0.00019998603811858571,
"loss": 1.4289,
"step": 11
},
{
"epoch": 0.06060606060606061,
"grad_norm": 46.56501770019531,
"learning_rate": 0.00019994415637302547,
"loss": 1.7922,
"step": 12
},
{
"epoch": 0.06565656565656566,
"grad_norm": 26.839624404907227,
"learning_rate": 0.0001998743664582786,
"loss": 1.1899,
"step": 13
},
{
"epoch": 0.0707070707070707,
"grad_norm": 25.198179244995117,
"learning_rate": 0.00019977668786231534,
"loss": 1.0497,
"step": 14
},
{
"epoch": 0.07575757575757576,
"grad_norm": 51.9806022644043,
"learning_rate": 0.00019965114786067516,
"loss": 1.3165,
"step": 15
},
{
"epoch": 0.08080808080808081,
"grad_norm": 28.80169677734375,
"learning_rate": 0.00019949778150885042,
"loss": 1.111,
"step": 16
},
{
"epoch": 0.08585858585858586,
"grad_norm": 25.198205947875977,
"learning_rate": 0.00019931663163249742,
"loss": 1.0153,
"step": 17
},
{
"epoch": 0.09090909090909091,
"grad_norm": 25.36805534362793,
"learning_rate": 0.000199107748815478,
"loss": 0.8575,
"step": 18
},
{
"epoch": 0.09595959595959595,
"grad_norm": 28.688661575317383,
"learning_rate": 0.0001988711913857346,
"loss": 0.7617,
"step": 19
},
{
"epoch": 0.10101010101010101,
"grad_norm": 22.180784225463867,
"learning_rate": 0.00019860702539900287,
"loss": 1.0212,
"step": 20
},
{
"epoch": 0.10606060606060606,
"grad_norm": 20.960046768188477,
"learning_rate": 0.00019831532462036636,
"loss": 0.892,
"step": 21
},
{
"epoch": 0.1111111111111111,
"grad_norm": 20.003198623657227,
"learning_rate": 0.0001979961705036587,
"loss": 0.8259,
"step": 22
},
{
"epoch": 0.11616161616161616,
"grad_norm": 20.527767181396484,
"learning_rate": 0.00019764965216871846,
"loss": 0.7981,
"step": 23
},
{
"epoch": 0.12121212121212122,
"grad_norm": 24.499876022338867,
"learning_rate": 0.00019727586637650373,
"loss": 0.7407,
"step": 24
},
{
"epoch": 0.12626262626262627,
"grad_norm": 27.962913513183594,
"learning_rate": 0.00019687491750207254,
"loss": 0.8106,
"step": 25
},
{
"epoch": 0.13131313131313133,
"grad_norm": 20.95252227783203,
"learning_rate": 0.00019644691750543767,
"loss": 0.8093,
"step": 26
},
{
"epoch": 0.13636363636363635,
"grad_norm": 24.588537216186523,
"learning_rate": 0.0001959919859003031,
"loss": 0.9619,
"step": 27
},
{
"epoch": 0.1414141414141414,
"grad_norm": 25.922687530517578,
"learning_rate": 0.00019551024972069126,
"loss": 1.0955,
"step": 28
},
{
"epoch": 0.14646464646464646,
"grad_norm": 18.61737823486328,
"learning_rate": 0.00019500184348547042,
"loss": 0.7048,
"step": 29
},
{
"epoch": 0.15151515151515152,
"grad_norm": 17.320585250854492,
"learning_rate": 0.0001944669091607919,
"loss": 0.5604,
"step": 30
},
{
"epoch": 0.15656565656565657,
"grad_norm": 16.542715072631836,
"learning_rate": 0.0001939055961204478,
"loss": 0.7072,
"step": 31
},
{
"epoch": 0.16161616161616163,
"grad_norm": 22.6462459564209,
"learning_rate": 0.00019331806110416027,
"loss": 0.7732,
"step": 32
},
{
"epoch": 0.16666666666666666,
"grad_norm": 33.40491485595703,
"learning_rate": 0.00019270446817381377,
"loss": 0.6016,
"step": 33
},
{
"epoch": 0.1717171717171717,
"grad_norm": 21.087663650512695,
"learning_rate": 0.00019206498866764288,
"loss": 0.61,
"step": 34
},
{
"epoch": 0.17676767676767677,
"grad_norm": 17.59093475341797,
"learning_rate": 0.00019139980115238827,
"loss": 0.6075,
"step": 35
},
{
"epoch": 0.18181818181818182,
"grad_norm": 19.23078155517578,
"learning_rate": 0.00019070909137343408,
"loss": 0.694,
"step": 36
},
{
"epoch": 0.18686868686868688,
"grad_norm": 26.05833625793457,
"learning_rate": 0.0001899930522029408,
"loss": 0.7611,
"step": 37
},
{
"epoch": 0.1919191919191919,
"grad_norm": 27.84595489501953,
"learning_rate": 0.00018925188358598813,
"loss": 0.6542,
"step": 38
},
{
"epoch": 0.19696969696969696,
"grad_norm": 26.004344940185547,
"learning_rate": 0.00018848579248474288,
"loss": 0.6681,
"step": 39
},
{
"epoch": 0.20202020202020202,
"grad_norm": 20.24230194091797,
"learning_rate": 0.00018769499282066717,
"loss": 0.5088,
"step": 40
},
{
"epoch": 0.20707070707070707,
"grad_norm": 21.711565017700195,
"learning_rate": 0.00018687970541478364,
"loss": 0.74,
"step": 41
},
{
"epoch": 0.21212121212121213,
"grad_norm": 17.97589111328125,
"learning_rate": 0.00018604015792601396,
"loss": 0.4864,
"step": 42
},
{
"epoch": 0.21717171717171718,
"grad_norm": 34.957908630371094,
"learning_rate": 0.0001851765847876076,
"loss": 0.6905,
"step": 43
},
{
"epoch": 0.2222222222222222,
"grad_norm": 26.597530364990234,
"learning_rate": 0.0001842892271416797,
"loss": 0.7611,
"step": 44
},
{
"epoch": 0.22727272727272727,
"grad_norm": 16.2249755859375,
"learning_rate": 0.00018337833277187472,
"loss": 0.4251,
"step": 45
},
{
"epoch": 0.23232323232323232,
"grad_norm": 24.652427673339844,
"learning_rate": 0.00018244415603417603,
"loss": 0.9778,
"step": 46
},
{
"epoch": 0.23737373737373738,
"grad_norm": 17.19180679321289,
"learning_rate": 0.00018148695778588033,
"loss": 0.6035,
"step": 47
},
{
"epoch": 0.24242424242424243,
"grad_norm": 21.772842407226562,
"learning_rate": 0.0001805070053127563,
"loss": 0.9396,
"step": 48
},
{
"epoch": 0.2474747474747475,
"grad_norm": 30.497249603271484,
"learning_rate": 0.0001795045722544083,
"loss": 1.0868,
"step": 49
},
{
"epoch": 0.25252525252525254,
"grad_norm": 20.648635864257812,
"learning_rate": 0.0001784799385278661,
"loss": 0.6751,
"step": 50
},
{
"epoch": 0.25252525252525254,
"eval_loss": 0.4286772310733795,
"eval_runtime": 12.8415,
"eval_samples_per_second": 6.541,
"eval_steps_per_second": 3.271,
"step": 50
},
{
"epoch": 0.25757575757575757,
"grad_norm": 15.56528091430664,
"learning_rate": 0.00017743339024942135,
"loss": 0.5069,
"step": 51
},
{
"epoch": 0.26262626262626265,
"grad_norm": 13.587965965270996,
"learning_rate": 0.00017636521965473323,
"loss": 0.5898,
"step": 52
},
{
"epoch": 0.2676767676767677,
"grad_norm": 11.232004165649414,
"learning_rate": 0.00017527572501722512,
"loss": 0.5344,
"step": 53
},
{
"epoch": 0.2727272727272727,
"grad_norm": 48.71158981323242,
"learning_rate": 0.00017416521056479577,
"loss": 0.5318,
"step": 54
},
{
"epoch": 0.2777777777777778,
"grad_norm": 13.308910369873047,
"learning_rate": 0.00017303398639486695,
"loss": 0.456,
"step": 55
},
{
"epoch": 0.2828282828282828,
"grad_norm": 17.141597747802734,
"learning_rate": 0.00017188236838779295,
"loss": 0.4883,
"step": 56
},
{
"epoch": 0.2878787878787879,
"grad_norm": 11.742911338806152,
"learning_rate": 0.00017071067811865476,
"loss": 0.4722,
"step": 57
},
{
"epoch": 0.29292929292929293,
"grad_norm": 12.313322067260742,
"learning_rate": 0.00016951924276746425,
"loss": 0.4694,
"step": 58
},
{
"epoch": 0.29797979797979796,
"grad_norm": 15.240520477294922,
"learning_rate": 0.0001683083950278031,
"loss": 0.6767,
"step": 59
},
{
"epoch": 0.30303030303030304,
"grad_norm": 18.384809494018555,
"learning_rate": 0.00016707847301392236,
"loss": 0.5452,
"step": 60
},
{
"epoch": 0.30808080808080807,
"grad_norm": 24.02840805053711,
"learning_rate": 0.00016582982016632818,
"loss": 0.4739,
"step": 61
},
{
"epoch": 0.31313131313131315,
"grad_norm": 25.153413772583008,
"learning_rate": 0.00016456278515588024,
"loss": 0.5608,
"step": 62
},
{
"epoch": 0.3181818181818182,
"grad_norm": 16.113597869873047,
"learning_rate": 0.00016327772178642986,
"loss": 0.5061,
"step": 63
},
{
"epoch": 0.32323232323232326,
"grad_norm": 14.654685020446777,
"learning_rate": 0.00016197498889602448,
"loss": 0.5645,
"step": 64
},
{
"epoch": 0.3282828282828283,
"grad_norm": 13.464080810546875,
"learning_rate": 0.00016065495025670675,
"loss": 0.46,
"step": 65
},
{
"epoch": 0.3333333333333333,
"grad_norm": 16.236915588378906,
"learning_rate": 0.00015931797447293552,
"loss": 0.4963,
"step": 66
},
{
"epoch": 0.3383838383838384,
"grad_norm": 15.136520385742188,
"learning_rate": 0.00015796443487865776,
"loss": 0.3889,
"step": 67
},
{
"epoch": 0.3434343434343434,
"grad_norm": 17.57411766052246,
"learning_rate": 0.00015659470943305955,
"loss": 0.6627,
"step": 68
},
{
"epoch": 0.3484848484848485,
"grad_norm": 26.13228988647461,
"learning_rate": 0.00015520918061502569,
"loss": 0.5681,
"step": 69
},
{
"epoch": 0.35353535353535354,
"grad_norm": 19.557939529418945,
"learning_rate": 0.00015380823531633729,
"loss": 0.4217,
"step": 70
},
{
"epoch": 0.35858585858585856,
"grad_norm": 20.687942504882812,
"learning_rate": 0.00015239226473363687,
"loss": 0.4085,
"step": 71
},
{
"epoch": 0.36363636363636365,
"grad_norm": 18.704753875732422,
"learning_rate": 0.00015096166425919175,
"loss": 0.5309,
"step": 72
},
{
"epoch": 0.3686868686868687,
"grad_norm": 14.950682640075684,
"learning_rate": 0.00014951683337048537,
"loss": 0.5447,
"step": 73
},
{
"epoch": 0.37373737373737376,
"grad_norm": 15.215104103088379,
"learning_rate": 0.00014805817551866838,
"loss": 0.4135,
"step": 74
},
{
"epoch": 0.3787878787878788,
"grad_norm": 20.362154006958008,
"learning_rate": 0.00014658609801589982,
"loss": 0.5322,
"step": 75
},
{
"epoch": 0.3838383838383838,
"grad_norm": 17.189462661743164,
"learning_rate": 0.00014510101192161018,
"loss": 0.6402,
"step": 76
},
{
"epoch": 0.3888888888888889,
"grad_norm": 14.426923751831055,
"learning_rate": 0.0001436033319277183,
"loss": 0.4401,
"step": 77
},
{
"epoch": 0.3939393939393939,
"grad_norm": 16.389694213867188,
"learning_rate": 0.0001420934762428335,
"loss": 0.3578,
"step": 78
},
{
"epoch": 0.398989898989899,
"grad_norm": 13.852417945861816,
"learning_rate": 0.0001405718664754764,
"loss": 0.4186,
"step": 79
},
{
"epoch": 0.40404040404040403,
"grad_norm": 14.556455612182617,
"learning_rate": 0.00013903892751634947,
"loss": 0.5181,
"step": 80
},
{
"epoch": 0.4090909090909091,
"grad_norm": 11.96506404876709,
"learning_rate": 0.00013749508741969213,
"loss": 0.5548,
"step": 81
},
{
"epoch": 0.41414141414141414,
"grad_norm": 20.171615600585938,
"learning_rate": 0.00013594077728375128,
"loss": 0.5334,
"step": 82
},
{
"epoch": 0.41919191919191917,
"grad_norm": 14.336783409118652,
"learning_rate": 0.00013437643113040301,
"loss": 0.543,
"step": 83
},
{
"epoch": 0.42424242424242425,
"grad_norm": 31.304283142089844,
"learning_rate": 0.0001328024857839569,
"loss": 0.5402,
"step": 84
},
{
"epoch": 0.4292929292929293,
"grad_norm": 16.0805721282959,
"learning_rate": 0.00013121938074917865,
"loss": 0.4462,
"step": 85
},
{
"epoch": 0.43434343434343436,
"grad_norm": 20.255895614624023,
"learning_rate": 0.00012962755808856342,
"loss": 0.3971,
"step": 86
},
{
"epoch": 0.4393939393939394,
"grad_norm": 14.014909744262695,
"learning_rate": 0.00012802746229889563,
"loss": 0.4082,
"step": 87
},
{
"epoch": 0.4444444444444444,
"grad_norm": 16.093183517456055,
"learning_rate": 0.00012641954018712863,
"loss": 0.5894,
"step": 88
},
{
"epoch": 0.4494949494949495,
"grad_norm": 19.122770309448242,
"learning_rate": 0.00012480424074561933,
"loss": 0.6092,
"step": 89
},
{
"epoch": 0.45454545454545453,
"grad_norm": 22.975881576538086,
"learning_rate": 0.00012318201502675285,
"loss": 0.6141,
"step": 90
},
{
"epoch": 0.4595959595959596,
"grad_norm": 12.433504104614258,
"learning_rate": 0.00012155331601699136,
"loss": 0.4174,
"step": 91
},
{
"epoch": 0.46464646464646464,
"grad_norm": 18.699106216430664,
"learning_rate": 0.0001199185985103836,
"loss": 0.5296,
"step": 92
},
{
"epoch": 0.4696969696969697,
"grad_norm": 17.323938369750977,
"learning_rate": 0.00011827831898156905,
"loss": 0.6469,
"step": 93
},
{
"epoch": 0.47474747474747475,
"grad_norm": 11.476202964782715,
"learning_rate": 0.00011663293545831302,
"loss": 0.4282,
"step": 94
},
{
"epoch": 0.4797979797979798,
"grad_norm": 15.700027465820312,
"learning_rate": 0.00011498290739360815,
"loss": 0.5744,
"step": 95
},
{
"epoch": 0.48484848484848486,
"grad_norm": 30.623720169067383,
"learning_rate": 0.0001133286955373779,
"loss": 0.7131,
"step": 96
},
{
"epoch": 0.4898989898989899,
"grad_norm": 17.045047760009766,
"learning_rate": 0.00011167076180781764,
"loss": 0.5727,
"step": 97
},
{
"epoch": 0.494949494949495,
"grad_norm": 15.74181842803955,
"learning_rate": 0.00011000956916240985,
"loss": 0.5673,
"step": 98
},
{
"epoch": 0.5,
"grad_norm": 16.612184524536133,
"learning_rate": 0.000108345581468649,
"loss": 0.5101,
"step": 99
},
{
"epoch": 0.5050505050505051,
"grad_norm": 18.710609436035156,
"learning_rate": 0.00010667926337451217,
"loss": 0.5985,
"step": 100
},
{
"epoch": 0.5050505050505051,
"eval_loss": 0.3532155752182007,
"eval_runtime": 12.0059,
"eval_samples_per_second": 6.997,
"eval_steps_per_second": 3.498,
"step": 100
},
{
"epoch": 0.51010101010101,
"grad_norm": 11.24027156829834,
"learning_rate": 0.00010501108017871192,
"loss": 0.4537,
"step": 101
},
{
"epoch": 0.5151515151515151,
"grad_norm": 14.357158660888672,
"learning_rate": 0.00010334149770076747,
"loss": 0.4567,
"step": 102
},
{
"epoch": 0.5202020202020202,
"grad_norm": 12.492400169372559,
"learning_rate": 0.00010167098215093009,
"loss": 0.4684,
"step": 103
},
{
"epoch": 0.5252525252525253,
"grad_norm": 11.547194480895996,
"learning_rate": 0.0001,
"loss": 0.4345,
"step": 104
},
{
"epoch": 0.5303030303030303,
"grad_norm": 13.756988525390625,
"learning_rate": 9.83290178490699e-05,
"loss": 0.4538,
"step": 105
},
{
"epoch": 0.5353535353535354,
"grad_norm": 13.91006088256836,
"learning_rate": 9.665850229923258e-05,
"loss": 0.3966,
"step": 106
},
{
"epoch": 0.5404040404040404,
"grad_norm": 13.23215103149414,
"learning_rate": 9.498891982128809e-05,
"loss": 0.3571,
"step": 107
},
{
"epoch": 0.5454545454545454,
"grad_norm": 13.87959098815918,
"learning_rate": 9.332073662548784e-05,
"loss": 0.4389,
"step": 108
},
{
"epoch": 0.5505050505050505,
"grad_norm": 12.538737297058105,
"learning_rate": 9.165441853135104e-05,
"loss": 0.4184,
"step": 109
},
{
"epoch": 0.5555555555555556,
"grad_norm": 23.718013763427734,
"learning_rate": 8.999043083759017e-05,
"loss": 0.3822,
"step": 110
},
{
"epoch": 0.5606060606060606,
"grad_norm": 70.29689025878906,
"learning_rate": 8.832923819218238e-05,
"loss": 0.3815,
"step": 111
},
{
"epoch": 0.5656565656565656,
"grad_norm": 11.808393478393555,
"learning_rate": 8.667130446262214e-05,
"loss": 0.362,
"step": 112
},
{
"epoch": 0.5707070707070707,
"grad_norm": 13.301114082336426,
"learning_rate": 8.501709260639186e-05,
"loss": 0.5234,
"step": 113
},
{
"epoch": 0.5757575757575758,
"grad_norm": 11.385530471801758,
"learning_rate": 8.336706454168701e-05,
"loss": 0.546,
"step": 114
},
{
"epoch": 0.5808080808080808,
"grad_norm": 17.040523529052734,
"learning_rate": 8.172168101843099e-05,
"loss": 0.4199,
"step": 115
},
{
"epoch": 0.5858585858585859,
"grad_norm": 18.70421028137207,
"learning_rate": 8.008140148961641e-05,
"loss": 0.5603,
"step": 116
},
{
"epoch": 0.5909090909090909,
"grad_norm": 13.10011100769043,
"learning_rate": 7.844668398300865e-05,
"loss": 0.6309,
"step": 117
},
{
"epoch": 0.5959595959595959,
"grad_norm": 13.03792953491211,
"learning_rate": 7.681798497324716e-05,
"loss": 0.4718,
"step": 118
},
{
"epoch": 0.601010101010101,
"grad_norm": 14.050755500793457,
"learning_rate": 7.519575925438067e-05,
"loss": 0.372,
"step": 119
},
{
"epoch": 0.6060606060606061,
"grad_norm": 13.505302429199219,
"learning_rate": 7.358045981287141e-05,
"loss": 0.5525,
"step": 120
},
{
"epoch": 0.6111111111111112,
"grad_norm": 13.572732925415039,
"learning_rate": 7.197253770110438e-05,
"loss": 0.4607,
"step": 121
},
{
"epoch": 0.6161616161616161,
"grad_norm": 22.72136878967285,
"learning_rate": 7.037244191143661e-05,
"loss": 0.632,
"step": 122
},
{
"epoch": 0.6212121212121212,
"grad_norm": 12.22665786743164,
"learning_rate": 6.878061925082137e-05,
"loss": 0.429,
"step": 123
},
{
"epoch": 0.6262626262626263,
"grad_norm": 10.075366973876953,
"learning_rate": 6.719751421604309e-05,
"loss": 0.4592,
"step": 124
},
{
"epoch": 0.6313131313131313,
"grad_norm": 16.798250198364258,
"learning_rate": 6.562356886959704e-05,
"loss": 0.368,
"step": 125
},
{
"epoch": 0.6363636363636364,
"grad_norm": 10.359375953674316,
"learning_rate": 6.405922271624874e-05,
"loss": 0.2825,
"step": 126
},
{
"epoch": 0.6414141414141414,
"grad_norm": 12.54139232635498,
"learning_rate": 6.250491258030791e-05,
"loss": 0.479,
"step": 127
},
{
"epoch": 0.6464646464646465,
"grad_norm": 15.544010162353516,
"learning_rate": 6.0961072483650526e-05,
"loss": 0.4355,
"step": 128
},
{
"epoch": 0.6515151515151515,
"grad_norm": 13.150715827941895,
"learning_rate": 5.9428133524523646e-05,
"loss": 0.3998,
"step": 129
},
{
"epoch": 0.6565656565656566,
"grad_norm": 11.6818265914917,
"learning_rate": 5.790652375716652e-05,
"loss": 0.4009,
"step": 130
},
{
"epoch": 0.6616161616161617,
"grad_norm": 16.20279884338379,
"learning_rate": 5.639666807228175e-05,
"loss": 0.5703,
"step": 131
},
{
"epoch": 0.6666666666666666,
"grad_norm": 15.14217758178711,
"learning_rate": 5.48989880783898e-05,
"loss": 0.4918,
"step": 132
},
{
"epoch": 0.6717171717171717,
"grad_norm": 17.63346290588379,
"learning_rate": 5.341390198410019e-05,
"loss": 0.4146,
"step": 133
},
{
"epoch": 0.6767676767676768,
"grad_norm": 17.88300323486328,
"learning_rate": 5.1941824481331626e-05,
"loss": 0.4518,
"step": 134
},
{
"epoch": 0.6818181818181818,
"grad_norm": 19.94394302368164,
"learning_rate": 5.0483166629514654e-05,
"loss": 0.6016,
"step": 135
},
{
"epoch": 0.6868686868686869,
"grad_norm": 14.756821632385254,
"learning_rate": 4.903833574080825e-05,
"loss": 0.3996,
"step": 136
},
{
"epoch": 0.6919191919191919,
"grad_norm": 19.392858505249023,
"learning_rate": 4.760773526636315e-05,
"loss": 0.6053,
"step": 137
},
{
"epoch": 0.696969696969697,
"grad_norm": 7.531655788421631,
"learning_rate": 4.6191764683662744e-05,
"loss": 0.2299,
"step": 138
},
{
"epoch": 0.702020202020202,
"grad_norm": 23.472288131713867,
"learning_rate": 4.479081938497435e-05,
"loss": 0.5437,
"step": 139
},
{
"epoch": 0.7070707070707071,
"grad_norm": 17.57956314086914,
"learning_rate": 4.340529056694047e-05,
"loss": 0.5943,
"step": 140
},
{
"epoch": 0.7121212121212122,
"grad_norm": 11.99634075164795,
"learning_rate": 4.2035565121342246e-05,
"loss": 0.2477,
"step": 141
},
{
"epoch": 0.7171717171717171,
"grad_norm": 34.67549133300781,
"learning_rate": 4.0682025527064486e-05,
"loss": 0.4986,
"step": 142
},
{
"epoch": 0.7222222222222222,
"grad_norm": 12.304537773132324,
"learning_rate": 3.934504974329326e-05,
"loss": 0.5063,
"step": 143
},
{
"epoch": 0.7272727272727273,
"grad_norm": 14.232462882995605,
"learning_rate": 3.802501110397553e-05,
"loss": 0.5271,
"step": 144
},
{
"epoch": 0.7323232323232324,
"grad_norm": 23.888545989990234,
"learning_rate": 3.672227821357014e-05,
"loss": 0.6568,
"step": 145
},
{
"epoch": 0.7373737373737373,
"grad_norm": 16.624494552612305,
"learning_rate": 3.543721484411976e-05,
"loss": 0.4932,
"step": 146
},
{
"epoch": 0.7424242424242424,
"grad_norm": 15.917621612548828,
"learning_rate": 3.4170179833671846e-05,
"loss": 0.6934,
"step": 147
},
{
"epoch": 0.7474747474747475,
"grad_norm": 9.06427001953125,
"learning_rate": 3.292152698607768e-05,
"loss": 0.3849,
"step": 148
},
{
"epoch": 0.7525252525252525,
"grad_norm": 17.903718948364258,
"learning_rate": 3.169160497219692e-05,
"loss": 0.3646,
"step": 149
},
{
"epoch": 0.7575757575757576,
"grad_norm": 11.98536205291748,
"learning_rate": 3.0480757232535772e-05,
"loss": 0.46,
"step": 150
},
{
"epoch": 0.7575757575757576,
"eval_loss": 0.3067511022090912,
"eval_runtime": 12.2523,
"eval_samples_per_second": 6.856,
"eval_steps_per_second": 3.428,
"step": 150
},
{
"epoch": 0.7626262626262627,
"grad_norm": 9.82388687133789,
"learning_rate": 2.9289321881345254e-05,
"loss": 0.302,
"step": 151
},
{
"epoch": 0.7676767676767676,
"grad_norm": 12.946221351623535,
"learning_rate": 2.8117631612207084e-05,
"loss": 0.4361,
"step": 152
},
{
"epoch": 0.7727272727272727,
"grad_norm": 9.764445304870605,
"learning_rate": 2.6966013605133088e-05,
"loss": 0.3317,
"step": 153
},
{
"epoch": 0.7777777777777778,
"grad_norm": 14.5607271194458,
"learning_rate": 2.5834789435204243e-05,
"loss": 0.3403,
"step": 154
},
{
"epoch": 0.7828282828282829,
"grad_norm": 11.619050979614258,
"learning_rate": 2.4724274982774865e-05,
"loss": 0.4053,
"step": 155
},
{
"epoch": 0.7878787878787878,
"grad_norm": 14.43159008026123,
"learning_rate": 2.3634780345266806e-05,
"loss": 0.3843,
"step": 156
},
{
"epoch": 0.7929292929292929,
"grad_norm": 15.145977020263672,
"learning_rate": 2.2566609750578673e-05,
"loss": 0.4364,
"step": 157
},
{
"epoch": 0.797979797979798,
"grad_norm": 11.833556175231934,
"learning_rate": 2.1520061472133902e-05,
"loss": 0.3154,
"step": 158
},
{
"epoch": 0.803030303030303,
"grad_norm": 12.835911750793457,
"learning_rate": 2.04954277455917e-05,
"loss": 0.3429,
"step": 159
},
{
"epoch": 0.8080808080808081,
"grad_norm": 11.492507934570312,
"learning_rate": 1.9492994687243714e-05,
"loss": 0.3757,
"step": 160
},
{
"epoch": 0.8131313131313131,
"grad_norm": 13.120503425598145,
"learning_rate": 1.851304221411967e-05,
"loss": 0.4127,
"step": 161
},
{
"epoch": 0.8181818181818182,
"grad_norm": 20.865995407104492,
"learning_rate": 1.7555843965823992e-05,
"loss": 0.4,
"step": 162
},
{
"epoch": 0.8232323232323232,
"grad_norm": 11.817997932434082,
"learning_rate": 1.6621667228125302e-05,
"loss": 0.4647,
"step": 163
},
{
"epoch": 0.8282828282828283,
"grad_norm": 10.320054054260254,
"learning_rate": 1.57107728583203e-05,
"loss": 0.3413,
"step": 164
},
{
"epoch": 0.8333333333333334,
"grad_norm": 11.233556747436523,
"learning_rate": 1.4823415212392377e-05,
"loss": 0.2859,
"step": 165
},
{
"epoch": 0.8383838383838383,
"grad_norm": 10.825108528137207,
"learning_rate": 1.3959842073986085e-05,
"loss": 0.2771,
"step": 166
},
{
"epoch": 0.8434343434343434,
"grad_norm": 11.109395027160645,
"learning_rate": 1.3120294585216353e-05,
"loss": 0.3611,
"step": 167
},
{
"epoch": 0.8484848484848485,
"grad_norm": 10.571539878845215,
"learning_rate": 1.230500717933285e-05,
"loss": 0.3888,
"step": 168
},
{
"epoch": 0.8535353535353535,
"grad_norm": 11.521129608154297,
"learning_rate": 1.1514207515257147e-05,
"loss": 0.3247,
"step": 169
},
{
"epoch": 0.8585858585858586,
"grad_norm": 11.530449867248535,
"learning_rate": 1.0748116414011888e-05,
"loss": 0.2623,
"step": 170
},
{
"epoch": 0.8636363636363636,
"grad_norm": 10.529777526855469,
"learning_rate": 1.0006947797059219e-05,
"loss": 0.3313,
"step": 171
},
{
"epoch": 0.8686868686868687,
"grad_norm": 9.755709648132324,
"learning_rate": 9.29090862656593e-06,
"loss": 0.3945,
"step": 172
},
{
"epoch": 0.8737373737373737,
"grad_norm": 10.26276969909668,
"learning_rate": 8.600198847611729e-06,
"loss": 0.2629,
"step": 173
},
{
"epoch": 0.8787878787878788,
"grad_norm": 18.38811492919922,
"learning_rate": 7.935011332357112e-06,
"loss": 0.408,
"step": 174
},
{
"epoch": 0.8838383838383839,
"grad_norm": 11.992220878601074,
"learning_rate": 7.295531826186264e-06,
"loss": 0.4615,
"step": 175
},
{
"epoch": 0.8888888888888888,
"grad_norm": 14.000274658203125,
"learning_rate": 6.681938895839746e-06,
"loss": 0.3583,
"step": 176
},
{
"epoch": 0.8939393939393939,
"grad_norm": 11.123028755187988,
"learning_rate": 6.094403879552213e-06,
"loss": 0.2686,
"step": 177
},
{
"epoch": 0.898989898989899,
"grad_norm": 11.463796615600586,
"learning_rate": 5.533090839208133e-06,
"loss": 0.3694,
"step": 178
},
{
"epoch": 0.9040404040404041,
"grad_norm": 14.426941871643066,
"learning_rate": 4.998156514529595e-06,
"loss": 0.4453,
"step": 179
},
{
"epoch": 0.9090909090909091,
"grad_norm": 11.056812286376953,
"learning_rate": 4.489750279308757e-06,
"loss": 0.3627,
"step": 180
},
{
"epoch": 0.9141414141414141,
"grad_norm": 15.307928085327148,
"learning_rate": 4.008014099696922e-06,
"loss": 0.5187,
"step": 181
},
{
"epoch": 0.9191919191919192,
"grad_norm": 16.49620246887207,
"learning_rate": 3.5530824945623542e-06,
"loss": 0.4363,
"step": 182
},
{
"epoch": 0.9242424242424242,
"grad_norm": 14.4350004196167,
"learning_rate": 3.1250824979274675e-06,
"loss": 0.422,
"step": 183
},
{
"epoch": 0.9292929292929293,
"grad_norm": 8.324783325195312,
"learning_rate": 2.7241336234962944e-06,
"loss": 0.3985,
"step": 184
},
{
"epoch": 0.9343434343434344,
"grad_norm": 11.766496658325195,
"learning_rate": 2.3503478312815298e-06,
"loss": 0.3377,
"step": 185
},
{
"epoch": 0.9393939393939394,
"grad_norm": 15.193984031677246,
"learning_rate": 2.003829496341325e-06,
"loss": 0.3802,
"step": 186
},
{
"epoch": 0.9444444444444444,
"grad_norm": 20.59272003173828,
"learning_rate": 1.684675379633649e-06,
"loss": 0.4727,
"step": 187
},
{
"epoch": 0.9494949494949495,
"grad_norm": 10.777263641357422,
"learning_rate": 1.3929746009971433e-06,
"loss": 0.3044,
"step": 188
},
{
"epoch": 0.9545454545454546,
"grad_norm": 20.804996490478516,
"learning_rate": 1.1288086142653864e-06,
"loss": 0.3692,
"step": 189
},
{
"epoch": 0.9595959595959596,
"grad_norm": 19.473365783691406,
"learning_rate": 8.922511845219971e-07,
"loss": 0.321,
"step": 190
},
{
"epoch": 0.9646464646464646,
"grad_norm": 10.078756332397461,
"learning_rate": 6.833683675025904e-07,
"loss": 0.3689,
"step": 191
},
{
"epoch": 0.9696969696969697,
"grad_norm": 10.66713809967041,
"learning_rate": 5.022184911495864e-07,
"loss": 0.2831,
"step": 192
},
{
"epoch": 0.9747474747474747,
"grad_norm": 13.519158363342285,
"learning_rate": 3.488521393248401e-07,
"loss": 0.3693,
"step": 193
},
{
"epoch": 0.9797979797979798,
"grad_norm": 18.351518630981445,
"learning_rate": 2.2331213768468363e-07,
"loss": 0.5692,
"step": 194
},
{
"epoch": 0.9848484848484849,
"grad_norm": 20.144264221191406,
"learning_rate": 1.2563354172142606e-07,
"loss": 0.4896,
"step": 195
},
{
"epoch": 0.98989898989899,
"grad_norm": 21.47068977355957,
"learning_rate": 5.584362697453882e-08,
"loss": 0.4884,
"step": 196
},
{
"epoch": 0.9949494949494949,
"grad_norm": 14.894364356994629,
"learning_rate": 1.3961881414292778e-08,
"loss": 0.4101,
"step": 197
},
{
"epoch": 1.0,
"grad_norm": 20.294527053833008,
"learning_rate": 0.0,
"loss": 0.5037,
"step": 198
}
],
"logging_steps": 1,
"max_steps": 198,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.812060362394829e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}