deberta-hydrangea-leafspot / trainer_state.json
Balajip30's picture
Upload DeBERTa v3 hydrangea leaf spot classifier
ced51de verified
{
"best_global_step": 13206,
"best_metric": 0.9868791709426586,
"best_model_checkpoint": "/home/myid/bp67339/plant_disease/models/deberta_v3_base_textclf_phase3/checkpoint-13206",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 13206,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.011358473421172195,
"grad_norm": 2.552668809890747,
"learning_rate": 1.9925791306981678e-05,
"loss": 0.1196,
"step": 50
},
{
"epoch": 0.02271694684234439,
"grad_norm": 0.47541937232017517,
"learning_rate": 1.985006815084053e-05,
"loss": 0.0812,
"step": 100
},
{
"epoch": 0.034075420263516586,
"grad_norm": 7.045262813568115,
"learning_rate": 1.977434499469938e-05,
"loss": 0.0859,
"step": 150
},
{
"epoch": 0.04543389368468878,
"grad_norm": 0.03415582329034805,
"learning_rate": 1.9698621838558232e-05,
"loss": 0.0847,
"step": 200
},
{
"epoch": 0.05679236710586097,
"grad_norm": 0.05752035602927208,
"learning_rate": 1.9622898682417084e-05,
"loss": 0.0988,
"step": 250
},
{
"epoch": 0.06815084052703317,
"grad_norm": 3.0614030361175537,
"learning_rate": 1.9547175526275936e-05,
"loss": 0.1058,
"step": 300
},
{
"epoch": 0.07950931394820536,
"grad_norm": 1.2528300285339355,
"learning_rate": 1.947145237013479e-05,
"loss": 0.0842,
"step": 350
},
{
"epoch": 0.09086778736937756,
"grad_norm": 8.556694984436035,
"learning_rate": 1.9395729213993642e-05,
"loss": 0.0777,
"step": 400
},
{
"epoch": 0.10222626079054975,
"grad_norm": 20.690099716186523,
"learning_rate": 1.9320006057852494e-05,
"loss": 0.0764,
"step": 450
},
{
"epoch": 0.11358473421172194,
"grad_norm": 4.0012030601501465,
"learning_rate": 1.9244282901711345e-05,
"loss": 0.0814,
"step": 500
},
{
"epoch": 0.12494320763289414,
"grad_norm": 0.06608668714761734,
"learning_rate": 1.9168559745570197e-05,
"loss": 0.0637,
"step": 550
},
{
"epoch": 0.13630168105406634,
"grad_norm": 5.306321620941162,
"learning_rate": 1.909283658942905e-05,
"loss": 0.0479,
"step": 600
},
{
"epoch": 0.14766015447523853,
"grad_norm": 5.900157451629639,
"learning_rate": 1.90171134332879e-05,
"loss": 0.0892,
"step": 650
},
{
"epoch": 0.15901862789641072,
"grad_norm": 2.73388934135437,
"learning_rate": 1.8941390277146755e-05,
"loss": 0.0721,
"step": 700
},
{
"epoch": 0.1703771013175829,
"grad_norm": 6.770120143890381,
"learning_rate": 1.8865667121005603e-05,
"loss": 0.082,
"step": 750
},
{
"epoch": 0.18173557473875512,
"grad_norm": 0.010230629704892635,
"learning_rate": 1.8789943964864458e-05,
"loss": 0.0604,
"step": 800
},
{
"epoch": 0.1930940481599273,
"grad_norm": 11.530449867248535,
"learning_rate": 1.871422080872331e-05,
"loss": 0.0578,
"step": 850
},
{
"epoch": 0.2044525215810995,
"grad_norm": 0.014014088548719883,
"learning_rate": 1.863849765258216e-05,
"loss": 0.0574,
"step": 900
},
{
"epoch": 0.2158109950022717,
"grad_norm": 0.016662120819091797,
"learning_rate": 1.8562774496441013e-05,
"loss": 0.0654,
"step": 950
},
{
"epoch": 0.22716946842344388,
"grad_norm": 1.2837393283843994,
"learning_rate": 1.8487051340299865e-05,
"loss": 0.0638,
"step": 1000
},
{
"epoch": 0.2385279418446161,
"grad_norm": 0.45574066042900085,
"learning_rate": 1.8411328184158716e-05,
"loss": 0.0448,
"step": 1050
},
{
"epoch": 0.24988641526578828,
"grad_norm": 2.423413038253784,
"learning_rate": 1.8335605028017568e-05,
"loss": 0.0535,
"step": 1100
},
{
"epoch": 0.2612448886869605,
"grad_norm": 4.537928104400635,
"learning_rate": 1.8259881871876423e-05,
"loss": 0.0833,
"step": 1150
},
{
"epoch": 0.2726033621081327,
"grad_norm": 6.994387626647949,
"learning_rate": 1.8184158715735274e-05,
"loss": 0.06,
"step": 1200
},
{
"epoch": 0.2839618355293049,
"grad_norm": 0.01928258314728737,
"learning_rate": 1.8108435559594126e-05,
"loss": 0.0498,
"step": 1250
},
{
"epoch": 0.29532030895047706,
"grad_norm": 0.4064951241016388,
"learning_rate": 1.8032712403452977e-05,
"loss": 0.0491,
"step": 1300
},
{
"epoch": 0.30667878237164925,
"grad_norm": 2.6388704776763916,
"learning_rate": 1.795698924731183e-05,
"loss": 0.0327,
"step": 1350
},
{
"epoch": 0.31803725579282144,
"grad_norm": 2.0852885246276855,
"learning_rate": 1.788126609117068e-05,
"loss": 0.0978,
"step": 1400
},
{
"epoch": 0.3293957292139936,
"grad_norm": 2.8278560638427734,
"learning_rate": 1.7805542935029532e-05,
"loss": 0.0521,
"step": 1450
},
{
"epoch": 0.3407542026351658,
"grad_norm": 4.4425177574157715,
"learning_rate": 1.7729819778888387e-05,
"loss": 0.0532,
"step": 1500
},
{
"epoch": 0.352112676056338,
"grad_norm": 0.0768510028719902,
"learning_rate": 1.7654096622747235e-05,
"loss": 0.0486,
"step": 1550
},
{
"epoch": 0.36347114947751025,
"grad_norm": 0.4614756405353546,
"learning_rate": 1.757837346660609e-05,
"loss": 0.0419,
"step": 1600
},
{
"epoch": 0.37482962289868244,
"grad_norm": 0.5945758819580078,
"learning_rate": 1.7502650310464942e-05,
"loss": 0.055,
"step": 1650
},
{
"epoch": 0.3861880963198546,
"grad_norm": 0.5370413661003113,
"learning_rate": 1.7426927154323794e-05,
"loss": 0.0434,
"step": 1700
},
{
"epoch": 0.3975465697410268,
"grad_norm": 13.6658296585083,
"learning_rate": 1.7351203998182645e-05,
"loss": 0.0329,
"step": 1750
},
{
"epoch": 0.408905043162199,
"grad_norm": 0.9185870885848999,
"learning_rate": 1.72754808420415e-05,
"loss": 0.0584,
"step": 1800
},
{
"epoch": 0.4202635165833712,
"grad_norm": 0.3048367500305176,
"learning_rate": 1.719975768590035e-05,
"loss": 0.0561,
"step": 1850
},
{
"epoch": 0.4316219900045434,
"grad_norm": 3.6233348846435547,
"learning_rate": 1.71240345297592e-05,
"loss": 0.0568,
"step": 1900
},
{
"epoch": 0.44298046342571556,
"grad_norm": 7.301445007324219,
"learning_rate": 1.7048311373618055e-05,
"loss": 0.0545,
"step": 1950
},
{
"epoch": 0.45433893684688775,
"grad_norm": 12.261190414428711,
"learning_rate": 1.6972588217476907e-05,
"loss": 0.0347,
"step": 2000
},
{
"epoch": 0.46569741026806,
"grad_norm": 0.004870145116001368,
"learning_rate": 1.6896865061335758e-05,
"loss": 0.0297,
"step": 2050
},
{
"epoch": 0.4770558836892322,
"grad_norm": 0.08898526430130005,
"learning_rate": 1.682114190519461e-05,
"loss": 0.0368,
"step": 2100
},
{
"epoch": 0.4884143571104044,
"grad_norm": 0.007771740201860666,
"learning_rate": 1.674541874905346e-05,
"loss": 0.037,
"step": 2150
},
{
"epoch": 0.49977283053157656,
"grad_norm": 0.06338020414113998,
"learning_rate": 1.6669695592912313e-05,
"loss": 0.0351,
"step": 2200
},
{
"epoch": 0.5111313039527488,
"grad_norm": 0.2080918550491333,
"learning_rate": 1.6593972436771168e-05,
"loss": 0.0424,
"step": 2250
},
{
"epoch": 0.522489777373921,
"grad_norm": 0.005484211724251509,
"learning_rate": 1.651824928063002e-05,
"loss": 0.0498,
"step": 2300
},
{
"epoch": 0.5338482507950931,
"grad_norm": 1.5300865173339844,
"learning_rate": 1.6442526124488868e-05,
"loss": 0.0309,
"step": 2350
},
{
"epoch": 0.5452067242162654,
"grad_norm": 1.4512425661087036,
"learning_rate": 1.6366802968347723e-05,
"loss": 0.0397,
"step": 2400
},
{
"epoch": 0.5565651976374375,
"grad_norm": 0.07551686465740204,
"learning_rate": 1.6291079812206574e-05,
"loss": 0.0368,
"step": 2450
},
{
"epoch": 0.5679236710586097,
"grad_norm": 5.5924272537231445,
"learning_rate": 1.6215356656065426e-05,
"loss": 0.0169,
"step": 2500
},
{
"epoch": 0.5792821444797819,
"grad_norm": 0.03456870838999748,
"learning_rate": 1.6139633499924277e-05,
"loss": 0.0397,
"step": 2550
},
{
"epoch": 0.5906406179009541,
"grad_norm": 1.605539321899414,
"learning_rate": 1.6063910343783132e-05,
"loss": 0.0353,
"step": 2600
},
{
"epoch": 0.6019990913221263,
"grad_norm": 2.287083864212036,
"learning_rate": 1.598818718764198e-05,
"loss": 0.0233,
"step": 2650
},
{
"epoch": 0.6133575647432985,
"grad_norm": 0.02498025633394718,
"learning_rate": 1.5912464031500836e-05,
"loss": 0.0389,
"step": 2700
},
{
"epoch": 0.6247160381644707,
"grad_norm": 0.009853340685367584,
"learning_rate": 1.5836740875359687e-05,
"loss": 0.0343,
"step": 2750
},
{
"epoch": 0.6360745115856429,
"grad_norm": 0.006630271207541227,
"learning_rate": 1.576101771921854e-05,
"loss": 0.0211,
"step": 2800
},
{
"epoch": 0.6474329850068151,
"grad_norm": 9.345346450805664,
"learning_rate": 1.568529456307739e-05,
"loss": 0.0374,
"step": 2850
},
{
"epoch": 0.6587914584279873,
"grad_norm": 6.142024040222168,
"learning_rate": 1.5609571406936242e-05,
"loss": 0.0551,
"step": 2900
},
{
"epoch": 0.6701499318491595,
"grad_norm": 0.0021689136046916246,
"learning_rate": 1.5533848250795093e-05,
"loss": 0.0223,
"step": 2950
},
{
"epoch": 0.6815084052703316,
"grad_norm": 0.12782888114452362,
"learning_rate": 1.5458125094653945e-05,
"loss": 0.0397,
"step": 3000
},
{
"epoch": 0.6928668786915039,
"grad_norm": 0.021150466054677963,
"learning_rate": 1.53824019385128e-05,
"loss": 0.0465,
"step": 3050
},
{
"epoch": 0.704225352112676,
"grad_norm": 0.03622226044535637,
"learning_rate": 1.530667878237165e-05,
"loss": 0.0245,
"step": 3100
},
{
"epoch": 0.7155838255338483,
"grad_norm": 0.01021323911845684,
"learning_rate": 1.5230955626230503e-05,
"loss": 0.04,
"step": 3150
},
{
"epoch": 0.7269422989550205,
"grad_norm": 0.3106459677219391,
"learning_rate": 1.5155232470089353e-05,
"loss": 0.0257,
"step": 3200
},
{
"epoch": 0.7383007723761926,
"grad_norm": 0.00275537115521729,
"learning_rate": 1.5079509313948206e-05,
"loss": 0.0263,
"step": 3250
},
{
"epoch": 0.7496592457973649,
"grad_norm": 2.062044143676758,
"learning_rate": 1.5003786157807058e-05,
"loss": 0.0309,
"step": 3300
},
{
"epoch": 0.761017719218537,
"grad_norm": 9.71252155303955,
"learning_rate": 1.4928063001665911e-05,
"loss": 0.0398,
"step": 3350
},
{
"epoch": 0.7723761926397092,
"grad_norm": 0.1981002688407898,
"learning_rate": 1.4852339845524763e-05,
"loss": 0.0361,
"step": 3400
},
{
"epoch": 0.7837346660608814,
"grad_norm": 5.37298059463501,
"learning_rate": 1.4776616689383614e-05,
"loss": 0.028,
"step": 3450
},
{
"epoch": 0.7950931394820536,
"grad_norm": 0.01882290095090866,
"learning_rate": 1.4700893533242466e-05,
"loss": 0.0326,
"step": 3500
},
{
"epoch": 0.8064516129032258,
"grad_norm": 0.035887233912944794,
"learning_rate": 1.462517037710132e-05,
"loss": 0.0416,
"step": 3550
},
{
"epoch": 0.817810086324398,
"grad_norm": 13.781176567077637,
"learning_rate": 1.4549447220960171e-05,
"loss": 0.023,
"step": 3600
},
{
"epoch": 0.8291685597455702,
"grad_norm": 0.06990953534841537,
"learning_rate": 1.4473724064819024e-05,
"loss": 0.0213,
"step": 3650
},
{
"epoch": 0.8405270331667424,
"grad_norm": 0.6063719987869263,
"learning_rate": 1.4398000908677874e-05,
"loss": 0.0228,
"step": 3700
},
{
"epoch": 0.8518855065879146,
"grad_norm": 4.930353164672852,
"learning_rate": 1.4322277752536726e-05,
"loss": 0.0335,
"step": 3750
},
{
"epoch": 0.8632439800090868,
"grad_norm": 0.004565690644085407,
"learning_rate": 1.4246554596395579e-05,
"loss": 0.0214,
"step": 3800
},
{
"epoch": 0.874602453430259,
"grad_norm": 0.17241248488426208,
"learning_rate": 1.417083144025443e-05,
"loss": 0.0401,
"step": 3850
},
{
"epoch": 0.8859609268514311,
"grad_norm": 5.231073379516602,
"learning_rate": 1.4095108284113284e-05,
"loss": 0.0168,
"step": 3900
},
{
"epoch": 0.8973194002726034,
"grad_norm": 0.25602054595947266,
"learning_rate": 1.4019385127972135e-05,
"loss": 0.0399,
"step": 3950
},
{
"epoch": 0.9086778736937755,
"grad_norm": 0.04758666455745697,
"learning_rate": 1.3943661971830987e-05,
"loss": 0.0232,
"step": 4000
},
{
"epoch": 0.9200363471149478,
"grad_norm": 0.007415900472551584,
"learning_rate": 1.3867938815689839e-05,
"loss": 0.0254,
"step": 4050
},
{
"epoch": 0.93139482053612,
"grad_norm": 0.05941289663314819,
"learning_rate": 1.3792215659548692e-05,
"loss": 0.0182,
"step": 4100
},
{
"epoch": 0.9427532939572921,
"grad_norm": 0.2857076823711395,
"learning_rate": 1.3716492503407543e-05,
"loss": 0.015,
"step": 4150
},
{
"epoch": 0.9541117673784644,
"grad_norm": 6.7106852531433105,
"learning_rate": 1.3640769347266397e-05,
"loss": 0.0218,
"step": 4200
},
{
"epoch": 0.9654702407996365,
"grad_norm": 2.165870189666748,
"learning_rate": 1.3565046191125247e-05,
"loss": 0.0477,
"step": 4250
},
{
"epoch": 0.9768287142208087,
"grad_norm": 1.2232965230941772,
"learning_rate": 1.3489323034984098e-05,
"loss": 0.0227,
"step": 4300
},
{
"epoch": 0.9881871876419809,
"grad_norm": 6.756147384643555,
"learning_rate": 1.3413599878842951e-05,
"loss": 0.0273,
"step": 4350
},
{
"epoch": 0.9995456610631531,
"grad_norm": 0.07053057104349136,
"learning_rate": 1.3337876722701803e-05,
"loss": 0.0217,
"step": 4400
},
{
"epoch": 1.0,
"eval_accuracy": 0.9839739413680781,
"eval_f1_macro": 0.982934850082554,
"eval_loss": 0.08169186860322952,
"eval_runtime": 25.3611,
"eval_samples_per_second": 302.629,
"eval_steps_per_second": 4.732,
"step": 4402
},
{
"epoch": 1.0109041344843253,
"grad_norm": 0.005929551087319851,
"learning_rate": 1.3262153566560656e-05,
"loss": 0.0101,
"step": 4450
},
{
"epoch": 1.0222626079054975,
"grad_norm": 0.011584239080548286,
"learning_rate": 1.3186430410419508e-05,
"loss": 0.012,
"step": 4500
},
{
"epoch": 1.0336210813266697,
"grad_norm": 0.06345133483409882,
"learning_rate": 1.3110707254278358e-05,
"loss": 0.0295,
"step": 4550
},
{
"epoch": 1.044979554747842,
"grad_norm": 0.003701810259371996,
"learning_rate": 1.3034984098137211e-05,
"loss": 0.0096,
"step": 4600
},
{
"epoch": 1.056338028169014,
"grad_norm": 0.0013922312064096332,
"learning_rate": 1.2959260941996063e-05,
"loss": 0.0267,
"step": 4650
},
{
"epoch": 1.0676965015901863,
"grad_norm": 0.0026676456909626722,
"learning_rate": 1.2883537785854916e-05,
"loss": 0.0145,
"step": 4700
},
{
"epoch": 1.0790549750113585,
"grad_norm": 0.0031162630766630173,
"learning_rate": 1.2807814629713768e-05,
"loss": 0.0124,
"step": 4750
},
{
"epoch": 1.0904134484325307,
"grad_norm": 3.748222589492798,
"learning_rate": 1.273209147357262e-05,
"loss": 0.0074,
"step": 4800
},
{
"epoch": 1.1017719218537028,
"grad_norm": 0.0014477827353402972,
"learning_rate": 1.265636831743147e-05,
"loss": 0.0179,
"step": 4850
},
{
"epoch": 1.113130395274875,
"grad_norm": 4.411365985870361,
"learning_rate": 1.2580645161290324e-05,
"loss": 0.0181,
"step": 4900
},
{
"epoch": 1.1244888686960473,
"grad_norm": 0.05877981334924698,
"learning_rate": 1.2504922005149176e-05,
"loss": 0.013,
"step": 4950
},
{
"epoch": 1.1358473421172195,
"grad_norm": 0.999143123626709,
"learning_rate": 1.2429198849008029e-05,
"loss": 0.0114,
"step": 5000
},
{
"epoch": 1.1472058155383915,
"grad_norm": 0.0030792481265962124,
"learning_rate": 1.2353475692866879e-05,
"loss": 0.0114,
"step": 5050
},
{
"epoch": 1.1585642889595638,
"grad_norm": 0.0014463861007243395,
"learning_rate": 1.227775253672573e-05,
"loss": 0.0188,
"step": 5100
},
{
"epoch": 1.169922762380736,
"grad_norm": 0.0017361458158120513,
"learning_rate": 1.2202029380584584e-05,
"loss": 0.0234,
"step": 5150
},
{
"epoch": 1.1812812358019082,
"grad_norm": 13.90465259552002,
"learning_rate": 1.2126306224443435e-05,
"loss": 0.0078,
"step": 5200
},
{
"epoch": 1.1926397092230805,
"grad_norm": 5.497283935546875,
"learning_rate": 1.2050583068302289e-05,
"loss": 0.0124,
"step": 5250
},
{
"epoch": 1.2039981826442525,
"grad_norm": 3.7859766483306885,
"learning_rate": 1.197485991216114e-05,
"loss": 0.0319,
"step": 5300
},
{
"epoch": 1.2153566560654248,
"grad_norm": 0.0024443278089165688,
"learning_rate": 1.1899136756019992e-05,
"loss": 0.0177,
"step": 5350
},
{
"epoch": 1.226715129486597,
"grad_norm": 0.20258040726184845,
"learning_rate": 1.1823413599878843e-05,
"loss": 0.009,
"step": 5400
},
{
"epoch": 1.2380736029077692,
"grad_norm": 0.0014519239775836468,
"learning_rate": 1.1747690443737697e-05,
"loss": 0.0069,
"step": 5450
},
{
"epoch": 1.2494320763289415,
"grad_norm": 0.02450985088944435,
"learning_rate": 1.1671967287596548e-05,
"loss": 0.017,
"step": 5500
},
{
"epoch": 1.2607905497501135,
"grad_norm": 0.004507457371801138,
"learning_rate": 1.1596244131455401e-05,
"loss": 0.01,
"step": 5550
},
{
"epoch": 1.2721490231712858,
"grad_norm": 9.089266777038574,
"learning_rate": 1.1520520975314251e-05,
"loss": 0.0382,
"step": 5600
},
{
"epoch": 1.283507496592458,
"grad_norm": 5.648477077484131,
"learning_rate": 1.1444797819173103e-05,
"loss": 0.0165,
"step": 5650
},
{
"epoch": 1.2948659700136302,
"grad_norm": 1.2645410299301147,
"learning_rate": 1.1369074663031956e-05,
"loss": 0.0163,
"step": 5700
},
{
"epoch": 1.3062244434348025,
"grad_norm": 0.0017288923263549805,
"learning_rate": 1.1293351506890808e-05,
"loss": 0.0202,
"step": 5750
},
{
"epoch": 1.3175829168559745,
"grad_norm": 0.00359937222674489,
"learning_rate": 1.1217628350749661e-05,
"loss": 0.0135,
"step": 5800
},
{
"epoch": 1.3289413902771468,
"grad_norm": 4.165374279022217,
"learning_rate": 1.1141905194608513e-05,
"loss": 0.0132,
"step": 5850
},
{
"epoch": 1.340299863698319,
"grad_norm": 0.0018008551560342312,
"learning_rate": 1.1066182038467364e-05,
"loss": 0.0112,
"step": 5900
},
{
"epoch": 1.351658337119491,
"grad_norm": 0.5573896765708923,
"learning_rate": 1.0990458882326216e-05,
"loss": 0.0221,
"step": 5950
},
{
"epoch": 1.3630168105406633,
"grad_norm": 1.456154704093933,
"learning_rate": 1.091473572618507e-05,
"loss": 0.011,
"step": 6000
},
{
"epoch": 1.3743752839618355,
"grad_norm": 3.8196120262145996,
"learning_rate": 1.083901257004392e-05,
"loss": 0.0158,
"step": 6050
},
{
"epoch": 1.3857337573830077,
"grad_norm": 0.0017874937038868666,
"learning_rate": 1.0763289413902774e-05,
"loss": 0.0107,
"step": 6100
},
{
"epoch": 1.39709223080418,
"grad_norm": 0.0008583781309425831,
"learning_rate": 1.0687566257761624e-05,
"loss": 0.0031,
"step": 6150
},
{
"epoch": 1.408450704225352,
"grad_norm": 0.44672343134880066,
"learning_rate": 1.0611843101620476e-05,
"loss": 0.0223,
"step": 6200
},
{
"epoch": 1.4198091776465243,
"grad_norm": 0.009662467055022717,
"learning_rate": 1.0536119945479329e-05,
"loss": 0.0157,
"step": 6250
},
{
"epoch": 1.4311676510676965,
"grad_norm": 0.0007439041510224342,
"learning_rate": 1.046039678933818e-05,
"loss": 0.0165,
"step": 6300
},
{
"epoch": 1.4425261244888687,
"grad_norm": 0.001364586642012,
"learning_rate": 1.0384673633197034e-05,
"loss": 0.0054,
"step": 6350
},
{
"epoch": 1.453884597910041,
"grad_norm": 0.001398891326971352,
"learning_rate": 1.0308950477055884e-05,
"loss": 0.0087,
"step": 6400
},
{
"epoch": 1.465243071331213,
"grad_norm": 0.002500066999346018,
"learning_rate": 1.0233227320914735e-05,
"loss": 0.0117,
"step": 6450
},
{
"epoch": 1.4766015447523853,
"grad_norm": 0.0015706096310168505,
"learning_rate": 1.0157504164773588e-05,
"loss": 0.0173,
"step": 6500
},
{
"epoch": 1.4879600181735575,
"grad_norm": 0.0015295586781576276,
"learning_rate": 1.008178100863244e-05,
"loss": 0.0284,
"step": 6550
},
{
"epoch": 1.4993184915947297,
"grad_norm": 2.286747932434082,
"learning_rate": 1.0006057852491293e-05,
"loss": 0.011,
"step": 6600
},
{
"epoch": 1.510676965015902,
"grad_norm": 0.002311094431206584,
"learning_rate": 9.930334696350145e-06,
"loss": 0.0166,
"step": 6650
},
{
"epoch": 1.522035438437074,
"grad_norm": 0.0014053047634661198,
"learning_rate": 9.854611540208996e-06,
"loss": 0.0174,
"step": 6700
},
{
"epoch": 1.5333939118582463,
"grad_norm": 0.012581984512507915,
"learning_rate": 9.778888384067848e-06,
"loss": 0.0099,
"step": 6750
},
{
"epoch": 1.5447523852794185,
"grad_norm": 0.023738177493214607,
"learning_rate": 9.703165227926701e-06,
"loss": 0.0098,
"step": 6800
},
{
"epoch": 1.5561108587005905,
"grad_norm": 0.014806082472205162,
"learning_rate": 9.627442071785553e-06,
"loss": 0.017,
"step": 6850
},
{
"epoch": 1.567469332121763,
"grad_norm": 0.11848437041044235,
"learning_rate": 9.551718915644405e-06,
"loss": 0.0051,
"step": 6900
},
{
"epoch": 1.578827805542935,
"grad_norm": 2.107661485671997,
"learning_rate": 9.475995759503258e-06,
"loss": 0.0066,
"step": 6950
},
{
"epoch": 1.5901862789641072,
"grad_norm": 0.08532427251338959,
"learning_rate": 9.40027260336211e-06,
"loss": 0.0162,
"step": 7000
},
{
"epoch": 1.6015447523852795,
"grad_norm": 0.0039615873247385025,
"learning_rate": 9.324549447220961e-06,
"loss": 0.0043,
"step": 7050
},
{
"epoch": 1.6129032258064515,
"grad_norm": 0.0013789839576929808,
"learning_rate": 9.248826291079813e-06,
"loss": 0.0127,
"step": 7100
},
{
"epoch": 1.6242616992276238,
"grad_norm": 9.550993919372559,
"learning_rate": 9.173103134938664e-06,
"loss": 0.0106,
"step": 7150
},
{
"epoch": 1.635620172648796,
"grad_norm": 0.0011268022935837507,
"learning_rate": 9.097379978797517e-06,
"loss": 0.009,
"step": 7200
},
{
"epoch": 1.6469786460699682,
"grad_norm": 0.0006976621225476265,
"learning_rate": 9.021656822656369e-06,
"loss": 0.015,
"step": 7250
},
{
"epoch": 1.6583371194911405,
"grad_norm": 0.0014887871220707893,
"learning_rate": 8.94593366651522e-06,
"loss": 0.015,
"step": 7300
},
{
"epoch": 1.6696955929123125,
"grad_norm": 0.0009298041695728898,
"learning_rate": 8.870210510374074e-06,
"loss": 0.0155,
"step": 7350
},
{
"epoch": 1.6810540663334848,
"grad_norm": 0.287706583738327,
"learning_rate": 8.794487354232925e-06,
"loss": 0.0116,
"step": 7400
},
{
"epoch": 1.692412539754657,
"grad_norm": 0.051804594695568085,
"learning_rate": 8.718764198091777e-06,
"loss": 0.0086,
"step": 7450
},
{
"epoch": 1.703771013175829,
"grad_norm": 1.3675575256347656,
"learning_rate": 8.643041041950629e-06,
"loss": 0.023,
"step": 7500
},
{
"epoch": 1.7151294865970015,
"grad_norm": 0.0012162342900410295,
"learning_rate": 8.56731788580948e-06,
"loss": 0.0081,
"step": 7550
},
{
"epoch": 1.7264879600181735,
"grad_norm": 0.0013599529629573226,
"learning_rate": 8.491594729668334e-06,
"loss": 0.0075,
"step": 7600
},
{
"epoch": 1.7378464334393458,
"grad_norm": 0.0011247453512623906,
"learning_rate": 8.415871573527185e-06,
"loss": 0.0079,
"step": 7650
},
{
"epoch": 1.749204906860518,
"grad_norm": 0.003529078559949994,
"learning_rate": 8.340148417386037e-06,
"loss": 0.0053,
"step": 7700
},
{
"epoch": 1.76056338028169,
"grad_norm": 13.674657821655273,
"learning_rate": 8.26442526124489e-06,
"loss": 0.0058,
"step": 7750
},
{
"epoch": 1.7719218537028625,
"grad_norm": 0.0018937140703201294,
"learning_rate": 8.188702105103742e-06,
"loss": 0.0073,
"step": 7800
},
{
"epoch": 1.7832803271240345,
"grad_norm": 0.0012737379875034094,
"learning_rate": 8.112978948962593e-06,
"loss": 0.0067,
"step": 7850
},
{
"epoch": 1.7946388005452067,
"grad_norm": 0.0010197096271440387,
"learning_rate": 8.037255792821446e-06,
"loss": 0.0057,
"step": 7900
},
{
"epoch": 1.805997273966379,
"grad_norm": 0.009366828948259354,
"learning_rate": 7.961532636680296e-06,
"loss": 0.026,
"step": 7950
},
{
"epoch": 1.817355747387551,
"grad_norm": 0.012473216280341148,
"learning_rate": 7.88580948053915e-06,
"loss": 0.024,
"step": 8000
},
{
"epoch": 1.8287142208087233,
"grad_norm": 0.26876014471054077,
"learning_rate": 7.810086324398001e-06,
"loss": 0.0079,
"step": 8050
},
{
"epoch": 1.8400726942298955,
"grad_norm": 0.0026707984507083893,
"learning_rate": 7.734363168256853e-06,
"loss": 0.0149,
"step": 8100
},
{
"epoch": 1.8514311676510677,
"grad_norm": 0.036166541278362274,
"learning_rate": 7.658640012115706e-06,
"loss": 0.0062,
"step": 8150
},
{
"epoch": 1.86278964107224,
"grad_norm": 0.013438834808766842,
"learning_rate": 7.582916855974558e-06,
"loss": 0.0047,
"step": 8200
},
{
"epoch": 1.874148114493412,
"grad_norm": 0.0015038993442431092,
"learning_rate": 7.507193699833409e-06,
"loss": 0.0155,
"step": 8250
},
{
"epoch": 1.8855065879145843,
"grad_norm": 0.0006626308313570917,
"learning_rate": 7.431470543692262e-06,
"loss": 0.0014,
"step": 8300
},
{
"epoch": 1.8968650613357565,
"grad_norm": 0.0032690023072063923,
"learning_rate": 7.355747387551114e-06,
"loss": 0.0103,
"step": 8350
},
{
"epoch": 1.9082235347569285,
"grad_norm": 0.0008181309676729143,
"learning_rate": 7.280024231409966e-06,
"loss": 0.0184,
"step": 8400
},
{
"epoch": 1.919582008178101,
"grad_norm": 0.0026349183171987534,
"learning_rate": 7.204301075268818e-06,
"loss": 0.0074,
"step": 8450
},
{
"epoch": 1.930940481599273,
"grad_norm": 0.0025627773720771074,
"learning_rate": 7.12857791912767e-06,
"loss": 0.0061,
"step": 8500
},
{
"epoch": 1.9422989550204453,
"grad_norm": 0.000963448139373213,
"learning_rate": 7.052854762986522e-06,
"loss": 0.0049,
"step": 8550
},
{
"epoch": 1.9536574284416175,
"grad_norm": 0.0005609341314993799,
"learning_rate": 6.977131606845375e-06,
"loss": 0.0007,
"step": 8600
},
{
"epoch": 1.9650159018627895,
"grad_norm": 0.0011694286949932575,
"learning_rate": 6.901408450704225e-06,
"loss": 0.0017,
"step": 8650
},
{
"epoch": 1.976374375283962,
"grad_norm": 0.0010692242067307234,
"learning_rate": 6.825685294563078e-06,
"loss": 0.0115,
"step": 8700
},
{
"epoch": 1.987732848705134,
"grad_norm": 0.05440627783536911,
"learning_rate": 6.74996213842193e-06,
"loss": 0.0068,
"step": 8750
},
{
"epoch": 1.9990913221263062,
"grad_norm": 0.004324722569435835,
"learning_rate": 6.674238982280782e-06,
"loss": 0.0147,
"step": 8800
},
{
"epoch": 2.0,
"eval_accuracy": 0.9846254071661238,
"eval_f1_macro": 0.9835472402504412,
"eval_loss": 0.1140478253364563,
"eval_runtime": 24.9,
"eval_samples_per_second": 308.233,
"eval_steps_per_second": 4.819,
"step": 8804
},
{
"epoch": 2.0104497955474785,
"grad_norm": 0.000489537778776139,
"learning_rate": 6.598515826139634e-06,
"loss": 0.0007,
"step": 8850
},
{
"epoch": 2.0218082689686505,
"grad_norm": 0.0013550950679928064,
"learning_rate": 6.522792669998486e-06,
"loss": 0.0027,
"step": 8900
},
{
"epoch": 2.033166742389823,
"grad_norm": 0.0009673606837168336,
"learning_rate": 6.447069513857338e-06,
"loss": 0.0091,
"step": 8950
},
{
"epoch": 2.044525215810995,
"grad_norm": 0.0004022994253318757,
"learning_rate": 6.371346357716191e-06,
"loss": 0.0003,
"step": 9000
},
{
"epoch": 2.055883689232167,
"grad_norm": 0.0007892374997027218,
"learning_rate": 6.2956232015750415e-06,
"loss": 0.0024,
"step": 9050
},
{
"epoch": 2.0672421626533395,
"grad_norm": 0.012260637246072292,
"learning_rate": 6.219900045433894e-06,
"loss": 0.0016,
"step": 9100
},
{
"epoch": 2.0786006360745115,
"grad_norm": 0.002542909001931548,
"learning_rate": 6.144176889292746e-06,
"loss": 0.0001,
"step": 9150
},
{
"epoch": 2.089959109495684,
"grad_norm": 0.002916930941864848,
"learning_rate": 6.068453733151598e-06,
"loss": 0.0073,
"step": 9200
},
{
"epoch": 2.101317582916856,
"grad_norm": 0.0003816105308942497,
"learning_rate": 5.99273057701045e-06,
"loss": 0.0089,
"step": 9250
},
{
"epoch": 2.112676056338028,
"grad_norm": 0.0005522597930394113,
"learning_rate": 5.917007420869302e-06,
"loss": 0.0049,
"step": 9300
},
{
"epoch": 2.1240345297592005,
"grad_norm": 0.0011015296913683414,
"learning_rate": 5.841284264728154e-06,
"loss": 0.0066,
"step": 9350
},
{
"epoch": 2.1353930031803725,
"grad_norm": 0.00041281242738477886,
"learning_rate": 5.765561108587007e-06,
"loss": 0.0019,
"step": 9400
},
{
"epoch": 2.146751476601545,
"grad_norm": 0.0007952914456836879,
"learning_rate": 5.689837952445858e-06,
"loss": 0.0036,
"step": 9450
},
{
"epoch": 2.158109950022717,
"grad_norm": 0.0004673805378843099,
"learning_rate": 5.614114796304711e-06,
"loss": 0.0042,
"step": 9500
},
{
"epoch": 2.169468423443889,
"grad_norm": 0.00038412591675296426,
"learning_rate": 5.538391640163563e-06,
"loss": 0.0001,
"step": 9550
},
{
"epoch": 2.1808268968650615,
"grad_norm": 0.00038422050420194864,
"learning_rate": 5.462668484022414e-06,
"loss": 0.0093,
"step": 9600
},
{
"epoch": 2.1921853702862335,
"grad_norm": 0.0006754286587238312,
"learning_rate": 5.3869453278812665e-06,
"loss": 0.0028,
"step": 9650
},
{
"epoch": 2.2035438437074055,
"grad_norm": 0.0004887759569101036,
"learning_rate": 5.311222171740119e-06,
"loss": 0.0051,
"step": 9700
},
{
"epoch": 2.214902317128578,
"grad_norm": 0.05471280589699745,
"learning_rate": 5.2354990155989705e-06,
"loss": 0.0059,
"step": 9750
},
{
"epoch": 2.22626079054975,
"grad_norm": 0.0008195925038307905,
"learning_rate": 5.159775859457823e-06,
"loss": 0.0036,
"step": 9800
},
{
"epoch": 2.2376192639709225,
"grad_norm": 0.000433308829087764,
"learning_rate": 5.0840527033166745e-06,
"loss": 0.0022,
"step": 9850
},
{
"epoch": 2.2489777373920945,
"grad_norm": 0.012868039309978485,
"learning_rate": 5.008329547175527e-06,
"loss": 0.0051,
"step": 9900
},
{
"epoch": 2.2603362108132665,
"grad_norm": 0.5331919193267822,
"learning_rate": 4.9326063910343785e-06,
"loss": 0.0115,
"step": 9950
},
{
"epoch": 2.271694684234439,
"grad_norm": 0.0005174391553737223,
"learning_rate": 4.856883234893231e-06,
"loss": 0.0007,
"step": 10000
},
{
"epoch": 2.283053157655611,
"grad_norm": 0.00032180239213630557,
"learning_rate": 4.7811600787520825e-06,
"loss": 0.0095,
"step": 10050
},
{
"epoch": 2.294411631076783,
"grad_norm": 0.07410291582345963,
"learning_rate": 4.705436922610935e-06,
"loss": 0.008,
"step": 10100
},
{
"epoch": 2.3057701044979555,
"grad_norm": 0.024364503100514412,
"learning_rate": 4.6297137664697866e-06,
"loss": 0.0026,
"step": 10150
},
{
"epoch": 2.3171285779191275,
"grad_norm": 0.00038883680826984346,
"learning_rate": 4.553990610328639e-06,
"loss": 0.0026,
"step": 10200
},
{
"epoch": 2.3284870513403,
"grad_norm": 0.0038193499203771353,
"learning_rate": 4.478267454187491e-06,
"loss": 0.0001,
"step": 10250
},
{
"epoch": 2.339845524761472,
"grad_norm": 0.0023336990270763636,
"learning_rate": 4.402544298046343e-06,
"loss": 0.0084,
"step": 10300
},
{
"epoch": 2.351203998182644,
"grad_norm": 0.04238196834921837,
"learning_rate": 4.326821141905195e-06,
"loss": 0.0033,
"step": 10350
},
{
"epoch": 2.3625624716038165,
"grad_norm": 0.000569637690205127,
"learning_rate": 4.251097985764047e-06,
"loss": 0.0012,
"step": 10400
},
{
"epoch": 2.3739209450249885,
"grad_norm": 0.00034202905953861773,
"learning_rate": 4.1753748296228995e-06,
"loss": 0.0036,
"step": 10450
},
{
"epoch": 2.385279418446161,
"grad_norm": 0.00034673314075917006,
"learning_rate": 4.099651673481751e-06,
"loss": 0.0013,
"step": 10500
},
{
"epoch": 2.396637891867333,
"grad_norm": 0.0012820770498365164,
"learning_rate": 4.023928517340603e-06,
"loss": 0.0006,
"step": 10550
},
{
"epoch": 2.407996365288505,
"grad_norm": 0.0017663290491327643,
"learning_rate": 3.948205361199455e-06,
"loss": 0.0002,
"step": 10600
},
{
"epoch": 2.4193548387096775,
"grad_norm": 13.78622817993164,
"learning_rate": 3.8724822050583075e-06,
"loss": 0.0029,
"step": 10650
},
{
"epoch": 2.4307133121308495,
"grad_norm": 0.00041380742914043367,
"learning_rate": 3.796759048917159e-06,
"loss": 0.0051,
"step": 10700
},
{
"epoch": 2.442071785552022,
"grad_norm": 0.0015727384015917778,
"learning_rate": 3.721035892776011e-06,
"loss": 0.0002,
"step": 10750
},
{
"epoch": 2.453430258973194,
"grad_norm": 0.00039928112528286874,
"learning_rate": 3.6453127366348636e-06,
"loss": 0.0041,
"step": 10800
},
{
"epoch": 2.464788732394366,
"grad_norm": 0.0007231036433950067,
"learning_rate": 3.569589580493715e-06,
"loss": 0.0013,
"step": 10850
},
{
"epoch": 2.4761472058155385,
"grad_norm": 0.0004043302033096552,
"learning_rate": 3.493866424352567e-06,
"loss": 0.0038,
"step": 10900
},
{
"epoch": 2.4875056792367105,
"grad_norm": 0.00035005921381525695,
"learning_rate": 3.418143268211419e-06,
"loss": 0.0042,
"step": 10950
},
{
"epoch": 2.498864152657883,
"grad_norm": 13.098333358764648,
"learning_rate": 3.3424201120702716e-06,
"loss": 0.0039,
"step": 11000
},
{
"epoch": 2.510222626079055,
"grad_norm": 0.0030333756003528833,
"learning_rate": 3.2666969559291232e-06,
"loss": 0.0002,
"step": 11050
},
{
"epoch": 2.521581099500227,
"grad_norm": 0.0002801103692036122,
"learning_rate": 3.1909737997879752e-06,
"loss": 0.0003,
"step": 11100
},
{
"epoch": 2.5329395729213995,
"grad_norm": 0.5628141164779663,
"learning_rate": 3.1152506436468277e-06,
"loss": 0.0064,
"step": 11150
},
{
"epoch": 2.5442980463425715,
"grad_norm": 0.002491287887096405,
"learning_rate": 3.0395274875056797e-06,
"loss": 0.0037,
"step": 11200
},
{
"epoch": 2.555656519763744,
"grad_norm": 0.002808187622576952,
"learning_rate": 2.9638043313645317e-06,
"loss": 0.0028,
"step": 11250
},
{
"epoch": 2.567014993184916,
"grad_norm": 0.043582722544670105,
"learning_rate": 2.8880811752233833e-06,
"loss": 0.002,
"step": 11300
},
{
"epoch": 2.578373466606088,
"grad_norm": 0.00028100161580368876,
"learning_rate": 2.8123580190822357e-06,
"loss": 0.0072,
"step": 11350
},
{
"epoch": 2.5897319400272605,
"grad_norm": 0.0003854044189210981,
"learning_rate": 2.7366348629410877e-06,
"loss": 0.0085,
"step": 11400
},
{
"epoch": 2.6010904134484325,
"grad_norm": 41.185237884521484,
"learning_rate": 2.6609117067999397e-06,
"loss": 0.0031,
"step": 11450
},
{
"epoch": 2.612448886869605,
"grad_norm": 0.0006349310860969126,
"learning_rate": 2.5851885506587913e-06,
"loss": 0.0001,
"step": 11500
},
{
"epoch": 2.623807360290777,
"grad_norm": 0.0002767475671134889,
"learning_rate": 2.5094653945176438e-06,
"loss": 0.0065,
"step": 11550
},
{
"epoch": 2.635165833711949,
"grad_norm": 0.002331246854737401,
"learning_rate": 2.4337422383764958e-06,
"loss": 0.006,
"step": 11600
},
{
"epoch": 2.646524307133121,
"grad_norm": 0.0015208119293674827,
"learning_rate": 2.3580190822353478e-06,
"loss": 0.0037,
"step": 11650
},
{
"epoch": 2.6578827805542935,
"grad_norm": 0.026821589097380638,
"learning_rate": 2.2822959260942e-06,
"loss": 0.0093,
"step": 11700
},
{
"epoch": 2.669241253975466,
"grad_norm": 5.861845016479492,
"learning_rate": 2.206572769953052e-06,
"loss": 0.0003,
"step": 11750
},
{
"epoch": 2.680599727396638,
"grad_norm": 0.00030583186889998615,
"learning_rate": 2.130849613811904e-06,
"loss": 0.0015,
"step": 11800
},
{
"epoch": 2.69195820081781,
"grad_norm": 0.004688043612986803,
"learning_rate": 2.055126457670756e-06,
"loss": 0.0069,
"step": 11850
},
{
"epoch": 2.703316674238982,
"grad_norm": 0.0014823823003098369,
"learning_rate": 1.979403301529608e-06,
"loss": 0.0011,
"step": 11900
},
{
"epoch": 2.7146751476601545,
"grad_norm": 0.0003014960384462029,
"learning_rate": 1.9036801453884599e-06,
"loss": 0.0001,
"step": 11950
},
{
"epoch": 2.7260336210813265,
"grad_norm": 0.0012561273761093616,
"learning_rate": 1.827956989247312e-06,
"loss": 0.0029,
"step": 12000
},
{
"epoch": 2.737392094502499,
"grad_norm": 0.08546403795480728,
"learning_rate": 1.7522338331061639e-06,
"loss": 0.0027,
"step": 12050
},
{
"epoch": 2.748750567923671,
"grad_norm": 0.0004358178994152695,
"learning_rate": 1.676510676965016e-06,
"loss": 0.0002,
"step": 12100
},
{
"epoch": 2.760109041344843,
"grad_norm": 0.0006170666310936213,
"learning_rate": 1.600787520823868e-06,
"loss": 0.0035,
"step": 12150
},
{
"epoch": 2.7714675147660155,
"grad_norm": 0.00022272793285083026,
"learning_rate": 1.5250643646827201e-06,
"loss": 0.0005,
"step": 12200
},
{
"epoch": 2.7828259881871875,
"grad_norm": 0.0002821196976583451,
"learning_rate": 1.449341208541572e-06,
"loss": 0.0003,
"step": 12250
},
{
"epoch": 2.79418446160836,
"grad_norm": 0.0002386348060099408,
"learning_rate": 1.3736180524004241e-06,
"loss": 0.0009,
"step": 12300
},
{
"epoch": 2.805542935029532,
"grad_norm": 0.05056820809841156,
"learning_rate": 1.2978948962592762e-06,
"loss": 0.0016,
"step": 12350
},
{
"epoch": 2.816901408450704,
"grad_norm": 0.0051028188318014145,
"learning_rate": 1.2221717401181282e-06,
"loss": 0.0005,
"step": 12400
},
{
"epoch": 2.8282598818718765,
"grad_norm": 0.00031195359770208597,
"learning_rate": 1.1464485839769802e-06,
"loss": 0.0047,
"step": 12450
},
{
"epoch": 2.8396183552930485,
"grad_norm": 0.0005304196383804083,
"learning_rate": 1.0707254278358322e-06,
"loss": 0.0005,
"step": 12500
},
{
"epoch": 2.850976828714221,
"grad_norm": 0.004895700607448816,
"learning_rate": 9.950022716946842e-07,
"loss": 0.0023,
"step": 12550
},
{
"epoch": 2.862335302135393,
"grad_norm": 0.00021093177201692015,
"learning_rate": 9.192791155535363e-07,
"loss": 0.0002,
"step": 12600
},
{
"epoch": 2.873693775556565,
"grad_norm": 0.00027342038811184466,
"learning_rate": 8.435559594123883e-07,
"loss": 0.0002,
"step": 12650
},
{
"epoch": 2.8850522489777375,
"grad_norm": 0.0002328462287550792,
"learning_rate": 7.678328032712403e-07,
"loss": 0.0001,
"step": 12700
},
{
"epoch": 2.8964107223989095,
"grad_norm": 0.00026081790565513074,
"learning_rate": 6.921096471300924e-07,
"loss": 0.0008,
"step": 12750
},
{
"epoch": 2.907769195820082,
"grad_norm": 0.07156021147966385,
"learning_rate": 6.163864909889445e-07,
"loss": 0.0015,
"step": 12800
},
{
"epoch": 2.919127669241254,
"grad_norm": 0.002825228963047266,
"learning_rate": 5.406633348477965e-07,
"loss": 0.0001,
"step": 12850
},
{
"epoch": 2.930486142662426,
"grad_norm": 0.0006366794114001095,
"learning_rate": 4.6494017870664856e-07,
"loss": 0.0049,
"step": 12900
},
{
"epoch": 2.9418446160835985,
"grad_norm": 3.086198329925537,
"learning_rate": 3.8921702256550057e-07,
"loss": 0.0009,
"step": 12950
},
{
"epoch": 2.9532030895047705,
"grad_norm": 0.000288445531623438,
"learning_rate": 3.134938664243526e-07,
"loss": 0.0003,
"step": 13000
},
{
"epoch": 2.964561562925943,
"grad_norm": 0.00021304447727743536,
"learning_rate": 2.3777071028320462e-07,
"loss": 0.0006,
"step": 13050
},
{
"epoch": 2.975920036347115,
"grad_norm": 0.0010498821502551436,
"learning_rate": 1.6204755414205666e-07,
"loss": 0.0001,
"step": 13100
},
{
"epoch": 2.987278509768287,
"grad_norm": 0.00040187168633565307,
"learning_rate": 8.632439800090868e-08,
"loss": 0.0005,
"step": 13150
},
{
"epoch": 2.9986369831894595,
"grad_norm": 0.0003258317010477185,
"learning_rate": 1.0601241859760717e-08,
"loss": 0.0092,
"step": 13200
},
{
"epoch": 3.0,
"eval_accuracy": 0.9877524429967427,
"eval_f1_macro": 0.9868791709426586,
"eval_loss": 0.09756067395210266,
"eval_runtime": 25.8171,
"eval_samples_per_second": 297.284,
"eval_steps_per_second": 4.648,
"step": 13206
}
],
"logging_steps": 50,
"max_steps": 13206,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.341359158497128e+16,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}