maanasharma5's picture
Upload folder using huggingface_hub
ddc9e60 verified
step,training_loss,grad_norm
25,31.4578,1.0
50,13.9596,1.0
75,2.9235,0.9999999403953552
100,0.8709,0.9999998807907104
125,0.3412,0.9999999403953552
150,0.1776,0.9999997019767761
175,0.0869,0.9999992847442627
200,0.0427,0.9999993443489075
225,0.0334,0.9999994039535522
250,0.0245,0.9999991059303284
275,0.0194,0.5040819644927979
300,0.0162,0.28836962580680847
325,0.0119,0.36946022510528564
350,0.0101,0.18219341337680817
375,0.0102,0.346537709236145
400,0.0063,0.1566116064786911
425,0.0073,0.3900704085826874
450,0.006,0.2905888855457306
475,0.0063,0.21024370193481445
500,0.0051,0.16816172003746033
525,0.0067,0.18459093570709229
550,0.0082,0.2551088333129883
575,0.0062,0.10228601098060608
600,0.0089,0.13139168918132782
625,0.0111,0.2454502433538437
650,0.0115,0.23336242139339447
675,0.0111,0.1291302740573883
700,0.0117,0.09489353746175766
725,0.0101,0.10764757543802261
750,0.0108,0.05678122863173485
775,0.0092,0.020527774468064308
800,0.008,0.173589825630188
825,0.0095,0.11555282026529312
850,0.0076,0.10608159005641937
875,0.0088,0.06152668967843056
900,0.0087,0.05914616957306862
925,0.0053,0.08186350762844086
950,0.0096,0.05925089120864868
975,0.0095,0.06511278450489044
1000,0.0078,0.0931800976395607
1025,0.0114,0.11269059777259827
1050,0.0081,0.11722524464130402
1075,0.0062,0.02581837587058544
1100,0.0086,0.03710322082042694
1125,0.0087,0.0785575807094574
1150,0.0094,0.03801395744085312
1175,0.0055,0.02926984615623951
1200,0.0074,0.06864086538553238
1225,0.0166,0.24592509865760803
1250,0.0044,0.009355338290333748
1275,0.013,0.028833230957388878
1300,0.0093,0.03938307613134384
1325,0.006,0.11239250749349594
1350,0.0086,0.04799900949001312
1375,0.0073,0.04325583949685097
1400,0.0079,0.12982821464538574
1425,0.0066,0.039880137890577316
1450,0.0088,0.09205818176269531
1475,0.012,0.025647256523370743
1500,0.0049,0.00850376021116972
1525,0.0062,0.053814683109521866
1550,0.0056,0.017620235681533813
1575,0.0094,0.06328332424163818
1600,0.0073,0.01586659997701645
1625,0.0073,0.06639364361763
1650,0.0092,0.025078224018216133
1675,0.0155,0.030920514836907387
1700,0.0254,0.019702352583408356
1725,0.0209,0.058125484734773636
1750,0.0075,0.08721068501472473
1775,0.0092,0.06881119310855865
1800,0.0048,0.042318228632211685
1825,0.1704,0.03332323953509331
1850,0.0078,0.017344973981380463
1875,0.0066,0.0921916738152504
1900,0.0058,0.047606635838747025
1925,0.0097,0.012247292324900627
1950,0.0093,0.03050140291452408
1975,0.0092,0.05324883013963699
2000,0.0066,0.005056755617260933
2025,0.0093,0.04616018757224083
2050,0.0074,0.054854802787303925
2075,0.0087,0.14178453385829926
2100,0.0064,0.03896906226873398
2125,0.006,0.05203302949666977
2150,0.0092,0.030274970456957817
2175,0.0079,0.025429146364331245
2200,0.0053,0.03921952471137047
2225,0.0048,0.0275532566010952
2250,0.0061,0.08406868577003479
2275,0.0081,0.020618749782443047
2300,0.0055,0.10382752120494843
2325,0.0044,0.022244878113269806
2350,0.0094,0.034629061818122864
2375,0.0055,0.036780521273612976
2400,0.0059,0.039211541414260864
2425,0.0087,0.06942432373762131
2450,0.0068,0.041311245411634445
2475,0.0069,0.03627919405698776
2500,0.0087,0.024002324789762497
2525,0.0051,0.05027247965335846
2550,0.0103,0.06653782725334167
2575,0.0068,0.00849505327641964
2600,0.0065,0.04040840268135071
2625,0.0067,0.045712754130363464
2650,0.0065,0.025737490504980087
2675,0.0078,0.07164289057254791
2700,0.0066,0.09239096939563751
2725,0.0062,0.07628490775823593
2750,0.0051,0.0411304235458374
2775,0.007,0.06397545337677002
2800,0.008,0.030154844745993614
2825,0.0084,0.040724631398916245
2850,0.0068,0.025906840339303017
2875,0.0059,0.027138639241456985
2900,0.007,0.021879535168409348
2925,0.0061,0.013186395168304443
2950,0.003,0.008580982685089111
2975,0.0052,0.044154196977615356
3000,0.0063,0.004964599385857582
3025,0.0078,0.010907050222158432
3050,0.0063,0.007799224928021431
3075,0.0054,0.02618151344358921
3100,0.0058,0.0310830045491457
3125,0.0072,0.05583451688289642
3150,0.0075,0.04992624372243881
3175,0.0059,0.007094631437212229
3200,0.0056,0.01994423381984234
3225,0.0078,0.06047689542174339
3250,0.0093,0.13539674878120422
3275,0.0061,0.04615447297692299
3300,0.0071,0.04085761681199074
3325,0.0059,0.03766684606671333
3350,0.0076,0.02195749245584011
3375,0.0063,0.02973691187798977
3400,0.0076,0.05148019269108772
3425,0.0052,0.011282436549663544
3450,0.0065,0.05086426064372063
3475,0.006,0.02926880493760109
3500,0.0052,0.034639764577150345
3525,0.0072,0.029749711975455284
3550,0.0084,0.0718211904168129
3575,0.0075,0.017676351591944695
3600,0.0072,0.03638003021478653
3625,0.0072,0.10200083255767822
3650,0.0081,0.09819641709327698
3675,0.0092,0.04367353022098541
3700,0.0049,0.03470621630549431
3725,0.0058,0.03568466752767563
3750,0.0066,0.023045117035508156
3775,0.0076,0.031446292996406555
3800,0.0075,0.021200425922870636
3825,0.0058,0.010020218789577484
3850,0.005,0.042888298630714417
3875,0.0036,0.029418272897601128
3900,0.0067,0.0629127025604248
3925,0.0049,0.016996443271636963
3950,0.0075,0.047823332250118256
3975,0.0079,0.05331983417272568
4000,0.0055,0.05240904167294502
4025,0.005,0.0431116446852684
4050,0.0073,0.04298826679587364
4075,0.0067,0.0108329514041543
4100,0.0063,0.03371378779411316
4125,0.0079,0.05766622722148895
4150,0.0078,0.044588733464479446
4175,0.0068,0.008596602827310562
4200,0.0063,0.03333525359630585
4225,0.0052,0.039462611079216
4250,0.0056,0.030581792816519737
4275,0.0099,0.04156120866537094
4300,0.0051,0.005466620437800884
4325,0.0052,0.052788831293582916
4350,0.0069,0.01870301552116871
4375,0.0053,0.037073876708745956
4400,0.0039,0.010114496573805809
4425,0.0071,0.020075639709830284
4450,0.0061,0.010710636153817177
4475,0.0035,0.020632978528738022
4500,0.0041,0.003840275574475527
4525,0.0063,0.021195722743868828
4550,0.0064,0.020218640565872192
4575,0.0056,0.02108372375369072
4600,0.0085,0.020056743174791336
4625,0.0073,0.01583085209131241
4650,0.0032,0.12288468331098557
4675,0.0064,0.046227652579545975
4700,0.0059,0.04086026921868324
4725,0.0071,0.06276891380548477
4750,0.0066,0.042417172342538834
4775,0.0052,0.02600391022861004
4800,0.0053,0.056686464697122574
4825,0.0078,0.0984799712896347
4850,0.0064,0.02541746012866497
4875,0.0041,0.0031209930311888456
4900,0.0072,0.02284972183406353
4925,0.005,0.008291699923574924
4950,0.0063,0.053799472749233246
4975,0.0057,0.027841107919812202
5000,0.0077,0.022198401391506195
5025,0.0065,0.0833696499466896
5050,0.005,0.05972975492477417
5075,0.0081,0.009321928024291992
5100,0.0039,0.019817939028143883
5125,0.0075,0.11429083347320557
5150,0.0069,0.03985302522778511
5175,0.0072,0.051477305591106415
5200,0.0274,0.0623275525867939
5225,0.0054,0.029703307896852493
5250,0.0061,0.01976659893989563
5275,0.0062,0.007804244756698608
5300,0.0086,0.022708997130393982
5325,0.004,0.009148282930254936
5350,0.0068,0.025990599766373634
5375,0.0052,0.02007969468832016
5400,0.0071,0.011696074157953262
5425,0.0062,0.009660330601036549
5450,0.005,0.11059202998876572
5475,0.0064,0.003688623895868659
5500,0.0064,0.0029289782978594303
5525,0.0061,0.05751211196184158
5550,0.0058,0.027019964531064034
5575,0.0083,0.012189670465886593
5600,0.0044,0.018571799620985985
5625,0.0052,0.01716735027730465
5650,0.0024,0.012174936942756176
5675,0.0055,0.005989996716380119
5700,0.0052,0.025115180760622025
5725,0.01,0.14719215035438538
5750,0.0049,0.07037623971700668
5775,0.0079,0.032678067684173584
5800,0.0063,0.033811017870903015
5825,0.0049,0.025420691817998886
5850,0.0039,0.017590470612049103
5875,0.0036,0.011016396805644035
5900,0.0032,0.033053021878004074
5925,0.0065,0.0220868568867445
5950,0.0061,0.023077713325619698
5975,0.008,0.013037641532719135
6000,0.0074,0.022959226742386818
6025,0.0052,0.042981818318367004
6050,0.0056,0.00365566648542881
6075,0.0088,0.04007144644856453
6100,0.0052,0.01665695570409298
6125,0.0063,0.01618644781410694
6150,0.0057,0.01607874594628811
6175,0.0067,0.014631692320108414
6200,0.0053,0.014799010008573532
6225,0.0036,0.013224060647189617
6250,0.0052,0.01719365455210209
6275,0.0039,0.00670283567160368
6300,0.0055,0.012490464374423027
6325,0.0053,0.053342562168836594
6350,0.0066,0.012790626846253872
6375,0.0072,0.020184172317385674
6400,0.0069,0.008641798980534077
6425,0.0051,0.008252914063632488
6450,0.0041,0.012832541950047016
6475,0.0028,0.01688714697957039
6500,0.0056,0.010820427909493446
6525,0.0033,0.04037313908338547
6550,0.0059,0.03897557780146599
6575,0.006,0.10380974411964417
6600,0.0088,0.04861383140087128
6625,0.0044,0.06502659618854523
6650,0.0055,0.009777329862117767
6675,0.0051,0.011738971807062626
6700,0.0072,0.020410852506756783
6725,0.0034,0.06134270131587982
6750,0.0062,0.035853419452905655
6775,0.0049,0.009298743680119514
6800,0.0011,0.005139731802046299
6825,0.0045,0.027789639309048653
6850,0.0072,0.0045198374427855015
6875,0.0046,0.02971138246357441
6900,0.0066,0.04742075875401497
6925,0.0088,0.06857524812221527
6950,0.007,0.0034381544683128595
6975,0.0039,0.016937021166086197
7000,0.0067,0.009283335879445076
7025,0.0053,0.019029904156923294
7050,0.0072,0.0509205125272274
7075,0.0054,0.010384796187281609
7100,0.0045,0.041787177324295044
7125,0.0064,0.024587826803326607
7150,0.0087,0.026031114161014557
7175,0.0042,0.02266843244433403
7200,0.0071,0.03987506404519081
7225,0.0074,0.014604664407670498
7250,0.0061,0.07387812435626984
7275,0.0055,0.03857952356338501
7300,0.0078,0.023385362699627876
7325,0.0064,0.017102278769016266
7350,0.0084,0.09217793494462967
7375,0.0036,0.010486803017556667
7400,0.0061,0.03860871121287346
7425,0.0055,0.027882162481546402
7450,0.0066,0.006253429688513279
7475,0.0089,0.04895792528986931
7500,0.0042,0.03398202359676361
7525,0.0077,0.11929480731487274
7550,0.0042,0.020099198445677757
7575,0.0044,0.01212060172110796
7600,0.0059,0.05100569128990173
7625,0.0029,0.006222897209227085
7650,0.0034,0.005934122949838638
7675,0.0053,0.027948638424277306
7700,0.0062,0.056068260222673416
7725,0.0075,0.016006290912628174
7750,0.0044,0.00754152238368988
7775,0.0067,0.054222043603658676
7800,0.0052,0.023336593061685562
7825,0.0062,0.09903142601251602
7850,0.0061,0.02077372930943966
7875,0.0059,0.010855688713490963
7900,0.0034,0.0030878460966050625
7925,0.0055,0.01702873967587948
7950,0.0061,0.0037723006680607796
7975,0.0042,0.010709065943956375
8000,0.0066,0.05091671645641327
8025,0.0033,0.00932751689106226
8050,0.0075,0.019212756305933
8075,0.0045,0.01869232952594757
8100,0.005,0.042577359825372696
8125,0.0078,0.07118666917085648
8150,0.0082,0.07169465720653534
8175,0.0069,0.005254754330962896
8200,0.005,0.01942657306790352
8225,0.0047,0.025129327550530434
8250,0.0054,0.04207939654588699
8275,0.005,0.08291144669055939
8300,0.0068,0.021148962900042534
8325,0.0086,0.04724569618701935
8350,0.0078,0.03966548666357994
8375,0.0053,0.06350229680538177
8400,0.0054,0.04373415559530258
8425,0.0053,0.01120704971253872
8450,0.0041,0.004217603709548712
8475,0.0045,0.0087474649772048
8500,0.0061,0.03382999077439308
8525,0.0035,0.02600662223994732
8550,0.0066,0.04476379230618477
8575,0.0059,0.01614108681678772
8600,0.0075,0.06252333521842957
8625,0.0028,0.016921255737543106
8650,0.0032,0.017712265253067017
8675,0.006,0.017742784693837166
8700,0.0082,0.04793838784098625
8725,0.0105,0.01527359988540411
8750,0.0064,0.039721813052892685
8775,0.0051,0.020311519503593445
8800,0.0036,0.01527799665927887
8825,0.0029,0.004488667938858271
8850,0.0041,0.011761274188756943
8875,0.0061,0.00490645132958889
8900,0.0064,0.02786768414080143
8925,0.0063,0.05509403347969055
8950,0.0065,0.03129858523607254
8975,0.0027,0.007339318748563528
9000,0.0073,0.04159502685070038
9025,0.0052,0.037648797035217285
9050,0.0063,0.03475749492645264
9075,0.0061,0.018472403287887573
9100,0.0071,0.10050947219133377
9125,0.0035,0.0367448516190052
9150,0.0068,0.03752695024013519
9175,0.0038,0.020593639463186264
9200,0.0053,0.018106378614902496
9225,0.0057,0.010866868309676647
9250,0.0066,0.0380171462893486
9275,0.0069,0.007030328270047903
9300,0.0047,0.06721625477075577
9325,0.0036,0.037225693464279175
9350,0.0029,0.027388542890548706
9375,0.005,0.005372846033424139
9400,0.0065,0.017429152503609657
9425,0.0037,0.007131170015782118
9450,0.0046,0.0026561806444078684
9475,0.0039,0.005191391799598932
9500,0.0047,0.013838549144566059
9525,0.0075,0.018644478172063828
9550,0.0042,0.05698929727077484
9575,0.0067,0.08505070209503174
9600,0.0049,0.05149736627936363
9625,0.0085,0.07415908575057983
9650,0.0059,0.007522387430071831
9675,0.0046,0.12882766127586365
9700,0.0103,0.09133855253458023
9725,0.0035,0.015390663407742977
9750,0.0072,0.03923804312944412
9775,0.0051,0.026569504290819168
9800,0.0036,0.003571274923160672
9825,0.0046,0.05760616064071655
9850,0.0087,0.015277689322829247
9875,0.0068,0.005475339479744434
9900,0.0039,0.014056065119802952
9925,0.0035,0.024020763114094734
9950,0.0015,0.003872293047606945
9975,0.003,0.02095160260796547
10000,0.0058,0.019500363618135452
10025,0.0034,0.03557732701301575
10050,0.0034,0.008075891062617302
10075,0.0057,0.056688856333494186
10100,0.0028,0.006594487465918064
10125,0.0065,0.029085172340273857
10150,0.0051,0.04668280854821205
10175,0.0051,0.021017123013734818
10200,0.0049,0.019834507256746292
10225,0.0057,0.04481719806790352
10250,0.0077,0.02224249392747879
10275,0.0024,0.013529354706406593
10300,0.0076,0.014378903433680534
10325,0.0039,0.004396422766149044
10350,0.0034,0.005224245600402355
10375,0.0021,0.006193783134222031
10400,0.007,0.019727183505892754
10425,0.0017,0.005371595732867718
10450,0.0001,0.002164234174415469
10475,0.0036,0.014232157729566097
10500,0.0054,0.017161883413791656
10525,0.0046,0.0462929867208004
10550,0.0033,0.011271982453763485
10575,0.004,0.04190723970532417
10600,0.0056,0.0060460567474365234
10625,0.007,0.015975279733538628
10650,0.0043,0.013375417329370975
10675,0.0066,0.040882647037506104
10700,0.0046,0.058305710554122925
10725,0.0019,0.04821503534913063
10750,0.0072,0.07600951939821243
10775,0.0044,0.007441168650984764
10800,0.0055,0.018674997612833977
10825,0.0078,0.0318719744682312
10850,0.0089,0.02394421584904194
10875,0.0041,0.011769738048315048
10900,0.0077,0.03388582170009613
10925,0.0042,0.02844126522541046
10950,0.0076,0.041917093098163605
10975,0.0058,0.02569505199790001
11000,0.0074,0.014149842783808708
11025,0.0033,0.03967441990971565
11050,0.0034,0.019350789487361908
11075,0.0018,0.04618023708462715
11100,0.0071,0.03902919963002205
11125,0.0029,0.025987375527620316
11150,0.0067,0.010576830245554447
11175,0.0022,0.009293319657444954
11200,0.0005,0.023490658029913902
11225,0.004,0.014267063699662685
11250,0.0047,0.05665036290884018
11275,0.0083,0.04620165005326271
11300,0.004,0.016191937029361725
11325,0.0069,0.019027508795261383
11350,0.0036,0.05005323886871338
11375,0.0066,0.017813177779316902
11400,0.0065,0.017873097211122513
11425,0.0068,0.09523989260196686
11450,0.0072,0.07632995396852493
11475,0.0067,0.028961945325136185
11500,0.0045,0.016702063381671906
11525,0.0031,0.040976133197546005
11550,0.0073,0.057852085679769516
11575,0.007,0.025202294811606407
11600,0.0027,0.022307831794023514
11625,0.0041,0.048785142600536346
11650,0.0038,0.010863160714507103
11675,0.0041,0.0028403247706592083
11700,0.0037,0.0060117836110293865
11725,0.0033,0.02536999247968197
11750,0.0062,0.033626943826675415
11775,0.0073,0.010561923496425152
11800,0.0045,0.016587452962994576
11825,0.0062,0.019106652587652206
11850,0.0068,0.01756969839334488
11875,0.0078,0.029949558898806572
11900,0.0065,0.027250220999121666
11925,0.0063,0.018932731822133064
11950,0.0104,0.017978109419345856
11975,0.0017,0.017068522050976753
12000,0.0041,0.04096332564949989
12025,0.0045,0.023155082017183304
12050,0.0037,0.014300097711384296
12075,0.0051,0.045832931995391846
12100,0.0099,0.02715732716023922
12125,0.0074,0.03522827848792076
12150,0.0014,0.023234747350215912
12175,0.0025,0.01505227666348219
12200,0.0019,0.014911390841007233
12225,0.0024,0.022456694394350052
12250,0.0039,0.02334211766719818
12275,0.0043,0.039633139967918396
12300,0.0078,0.03481031954288483
12325,0.0029,0.027688203379511833
12350,0.0042,0.02317345142364502
12375,0.0051,0.022227274253964424
12400,0.0023,0.015826454386115074
12425,0.0015,0.017629349604249
12450,0.0012,0.011832443065941334
12475,0.001,0.012542919255793095
12500,0.001,0.012756671756505966
12500,nan,nan