step,training_loss,grad_norm
10,24.9631,10.0
20,20.8404,9.999998092651367
30,18.8159,10.0
40,20.6325,10.0
50,17.4707,10.0
60,15.7267,9.999999046325684
70,14.4446,10.000000953674316
80,12.1937,9.999998092651367
90,9.5339,9.999999046325684
100,6.8862,9.999999046325684
110,6.4802,9.999999046325684
120,4.1698,9.999998092651367
130,3.6582,9.999999046325684
140,3.0036,8.310874938964844
150,2.5991,8.249914169311523
160,2.0956,6.633706092834473
170,1.8054,4.844052791595459
180,1.5541,5.696422100067139
190,1.5431,5.249777793884277
200,1.5084,4.493651866912842
210,1.3255,3.875426769256592
220,1.368,3.985583782196045
230,1.2237,3.1382219791412354
240,1.1944,3.6973352432250977
250,1.1278,4.306434154510498
260,1.1202,4.24944543838501
270,1.0113,4.12693977355957
280,1.0587,3.7358357906341553
290,0.9658,4.148690223693848
300,1.0358,4.104267120361328
310,0.9948,3.458801746368408
320,0.8794,2.915538787841797
330,0.9644,3.209948778152466
340,0.9274,3.135376214981079
350,0.9099,3.4967312812805176
360,0.8661,3.2876088619232178
370,0.8903,3.465593099594116
380,0.8406,3.491227388381958
390,0.8485,3.153066396713257
400,0.8795,4.715076446533203
410,0.8124,3.2449190616607666
420,0.7733,3.496378183364868
430,0.7438,3.975687265396118
440,0.7557,4.541060447692871
450,0.7744,3.7180514335632324
460,0.7894,4.477784156799316
470,0.664,6.005988121032715
480,0.6678,3.6489133834838867
490,0.6436,4.066476821899414
500,0.6698,2.9249703884124756
510,0.6342,3.470515489578247
520,0.6154,3.9201626777648926
530,0.5471,3.164458990097046
540,0.6391,8.615708351135254
550,0.5768,2.548628330230713
560,0.5361,5.320557594299316
570,0.542,5.885339736938477
580,0.572,3.641576051712036
590,0.5329,4.401009559631348
600,0.5004,3.0472371578216553
610,0.4432,4.5183491706848145
620,0.438,4.483486175537109
630,0.4345,3.5213429927825928
640,0.391,2.9145050048828125
650,0.3555,2.7155418395996094
660,0.3709,2.8801558017730713
670,0.3194,3.217880964279175
680,0.3249,3.9972708225250244
690,0.2929,2.758613109588623
700,0.2982,3.3077003955841064
710,0.2758,3.283940315246582
720,0.2943,2.544793128967285
730,0.2791,2.6508431434631348
740,0.2808,3.0049996376037598
750,0.2658,3.1359918117523193
760,0.2412,2.4908928871154785
770,0.2347,3.4816462993621826
780,0.1969,2.2120361328125
790,0.1985,2.589252471923828
800,0.2202,3.6688730716705322
810,0.1926,1.6741994619369507
820,0.1819,1.583107352256775
830,0.1932,3.296635389328003
840,0.1878,2.3639001846313477
850,0.1477,1.4914251565933228
860,0.1528,2.3486623764038086
870,0.1699,1.2986149787902832
880,0.1868,3.43965482711792
890,0.1491,1.4145461320877075
900,0.1712,1.6416748762130737
910,0.257,2.666991949081421
920,0.1845,9.999999046325684
930,0.1405,1.8368594646453857
940,0.1718,2.364957571029663
950,0.1523,1.2922320365905762
960,0.1563,2.202463150024414
970,0.1351,3.0725717544555664
980,0.1392,1.8276102542877197
990,0.1276,2.689838409423828
1000,0.1284,1.680222511291504
1010,0.1239,1.0360759496688843
1020,0.1361,1.915683388710022
1030,0.1408,1.8662254810333252
1040,0.1047,1.5222748517990112
1050,0.1252,1.9447592496871948
1060,0.1198,1.8480818271636963
1070,0.1147,1.8532341718673706
1080,0.1041,1.458263874053955
1090,0.0934,0.8418246507644653
1100,0.1029,1.1937845945358276
1110,0.1057,1.4058141708374023
1120,0.1136,2.04742169380188
1130,0.098,1.3528432846069336
1140,0.0982,1.3083478212356567
1150,0.1011,1.3803431987762451
1160,0.0976,1.8763604164123535
1170,0.1021,1.459699273109436
1180,0.094,2.516188621520996
1190,0.0951,2.072133779525757
1200,0.085,1.3856562376022339
1210,0.0894,1.524794101715088
1220,0.0813,0.8352987170219421
1230,0.0941,1.99660062789917
1240,0.0943,1.9948227405548096
1250,0.0903,2.417297601699829
1260,0.0934,1.255522608757019
1270,0.0823,3.0397634506225586
1280,0.0937,2.1224780082702637
1290,0.0952,2.0656044483184814
1300,0.0882,1.334979772567749
1310,0.0889,1.4411072731018066
1320,0.0817,1.8725781440734863
1330,0.0857,1.0607643127441406
1340,0.0813,1.0576326847076416
1350,0.0724,0.8751885294914246
1360,0.0801,1.0008176565170288
1370,0.0827,1.0499143600463867
1380,0.0764,1.6805224418640137
1390,0.0799,1.0352784395217896
1400,0.0758,1.2008415460586548
1410,0.0878,1.247338891029358
1420,0.072,0.975530207157135
1430,0.0722,1.0029404163360596
1440,0.0701,0.8437648415565491
1450,0.0695,1.1050156354904175
1460,0.0675,0.9750869870185852
1470,0.0721,0.8726626038551331
1480,0.0687,3.020092725753784
1490,0.0721,1.3524830341339111
1500,0.0727,1.7134172916412354
1510,0.0702,1.3195223808288574
1520,0.0754,1.1717275381088257
1530,0.0596,0.9258642792701721
1540,0.0631,1.4086549282073975
1550,0.0748,1.211665153503418
1560,0.0696,1.8159215450286865
1570,0.0629,1.5430232286453247
1580,0.0647,0.971611499786377
1590,0.0689,2.795301675796509
1600,0.0649,1.0469309091567993
1610,0.0619,1.5577256679534912
1620,0.0622,1.732717752456665
1630,0.0672,1.4120196104049683
1640,0.064,1.2306411266326904
1650,0.0664,2.0534772872924805
1660,0.0665,1.562451720237732
1670,0.0561,1.1336791515350342
1680,0.0579,0.9556323885917664
1690,0.0591,1.3072831630706787
1700,0.0615,0.9365288019180298
1710,0.0613,0.8340426683425903
1720,0.0569,1.1264219284057617
1730,0.0593,1.1999742984771729
1740,0.0613,1.1102709770202637
1750,0.056,1.0732330083847046
1760,0.0546,1.3392184972763062
1770,0.0589,1.005621314048767
1780,0.0597,1.4382975101470947
1790,0.0566,1.4868929386138916
1800,0.0497,0.7314358353614807
1810,0.0517,0.8784840106964111
1820,0.0628,2.5038092136383057
1830,0.0532,0.8334175944328308
1840,0.0508,0.9410456418991089
1850,0.0581,0.974979817867279
1860,0.0541,0.8645688891410828
1870,0.05,0.647721529006958
1880,0.0504,0.8814899325370789
1890,0.06,0.835896372795105
1900,0.0514,1.4004669189453125
1910,0.0554,1.7096471786499023
1920,0.0531,0.7163381576538086
1930,0.0535,0.8033366799354553
1940,0.0537,1.36751389503479
1950,0.0508,0.6608594655990601
1960,0.054,1.4556374549865723
1970,0.0557,1.026332139968872
1980,0.0511,1.2365747690200806
1990,0.0426,1.0087261199951172
2000,0.0452,0.8160260915756226
2010,0.0489,1.6539990901947021
2020,0.0447,0.5857284069061279
2030,0.0481,0.8850499987602234
2040,0.0502,0.9914937019348145
2050,0.0471,0.9070343971252441
2060,0.0436,0.9179836511611938
2070,0.0486,0.7364044785499573
2080,0.046,0.6488219499588013
2090,0.0494,1.5407613515853882
2100,0.0457,2.3234798908233643
2110,0.0461,1.3606553077697754
2120,0.0412,1.338086724281311
2130,0.0487,0.8436578512191772
2140,0.0477,0.9895771145820618
2150,0.0381,1.4392690658569336
2160,0.0513,0.8517897129058838
2170,0.0471,0.765490710735321
2180,0.0435,0.95233154296875
2190,0.0443,0.9749875068664551
2200,0.0419,1.3162479400634766
2210,0.0443,0.9644461870193481
2220,0.0462,1.3393887281417847
2230,0.0443,0.9995754361152649
2240,0.0462,1.211478590965271
2250,0.0426,0.6780794858932495
2260,0.0423,0.8342995047569275
2270,0.0449,1.2715864181518555
2280,0.0465,0.8093573451042175
2290,0.0488,1.1649224758148193
2300,0.0475,1.2314190864562988
2310,0.047,0.9177021980285645
2320,0.0417,1.1093103885650635
2330,0.0416,0.7009869813919067
2340,0.0471,1.0457608699798584
2350,0.0479,0.8647756576538086
2360,0.0388,0.8496474027633667
2370,0.0428,0.8979694843292236
2380,0.04,1.0336112976074219
2390,0.0412,0.8268937468528748
2400,0.0415,0.759469747543335
2410,0.0392,0.9482242465019226
2420,0.0472,0.8537123799324036
2430,0.0449,0.6745234727859497
2440,0.0419,0.9895679950714111
2450,0.0851,4.300079822540283
2460,0.0445,0.8699926137924194
2470,0.0404,0.7995278239250183
2480,0.0399,1.3382374048233032
2490,0.0412,0.7148540616035461
2500,0.0372,1.0621765851974487
2510,0.0395,1.328330636024475
2520,0.0423,0.7691792249679565
2530,0.0402,0.8384915590286255
2540,0.0395,1.1409624814987183
2550,0.0457,0.9339775443077087
2560,0.042,1.1918686628341675
2570,0.0365,0.655660092830658
2580,0.0468,1.1334338188171387
2590,0.0392,1.0458253622055054
2600,0.0381,0.9219187498092651
2610,0.0406,0.7008917927742004
2620,0.038,0.8411391973495483
2630,0.0388,1.0414551496505737
2640,0.044,0.8157031536102295
2650,0.0396,1.8497180938720703
2660,0.0388,1.7988622188568115
2670,0.0401,1.505881667137146
2680,0.039,1.3370205163955688
2690,0.0368,0.7456148862838745
2700,0.0402,0.8330332040786743
2710,0.0403,0.8216585516929626
2720,0.0369,0.9162799715995789
2730,0.0396,0.9739064574241638
2740,0.0368,0.8707442283630371
2750,0.0351,0.678347110748291
2760,0.041,1.152178168296814
2770,0.0378,0.7693957090377808
2780,0.0403,1.3139463663101196
2790,0.0344,0.9965353012084961
2800,0.0396,1.0216691493988037
2810,0.035,0.5650272965431213
2820,0.038,1.3575382232666016
2830,0.0374,0.7426192164421082
2840,0.0385,1.6532901525497437
2850,0.0381,1.0569813251495361
2860,0.0381,0.6354155540466309
2870,0.04,0.6795879602432251
2880,0.0385,1.0496159791946411
2890,0.0392,0.6077241897583008
2900,0.0359,0.7129323482513428
2910,0.0385,0.6670847535133362
2920,0.0318,1.0024406909942627
2930,0.0336,0.7983542680740356
2940,0.0398,0.9120166301727295
2950,0.0391,0.7662246227264404
2960,0.0358,1.092923641204834
2970,0.0388,0.9875261187553406
2980,0.0327,0.6102545857429504
2990,0.0378,1.5828185081481934
3000,0.0396,1.5497301816940308
3010,0.036,0.9273558259010315
3020,0.0336,0.8762300610542297
3030,0.035,1.1286474466323853
3040,0.0339,0.9490174651145935
3050,0.0332,0.6286265850067139
3060,0.0384,0.9210827350616455
3070,0.0425,0.7867606282234192
3080,0.0329,1.2552579641342163
3090,0.0348,0.4516272246837616
3100,0.039,0.9391326904296875
3110,0.0374,1.3417290449142456
3120,0.0321,0.6872617602348328
3125,nan,nan