step,training_loss,grad_norm
25,19.3644,9.999999046325684
50,21.635,10.0
75,23.0075,9.999999046325684
100,21.8425,9.999999046325684
125,19.6638,9.999999046325684
150,17.0712,9.999999046325684
175,14.515,10.0
200,12.8981,10.0
225,8.8631,10.0
250,7.1437,9.999999046325684
275,5.8559,10.0
300,4.9659,9.999999046325684
325,4.0294,9.999999046325684
350,3.6666,9.999999046325684
375,3.6069,9.999999046325684
400,2.7969,9.999998092651367
425,2.5284,10.0
450,2.0644,10.0
475,2.0409,9.999999046325684
500,1.7772,8.733105659484863
525,1.6891,9.849020004272461
550,1.5814,9.999998092651367
575,1.6084,10.0
600,1.485,9.999998092651367
625,1.3298,8.400633811950684
650,1.3288,10.0
675,1.3405,6.071508884429932
700,1.3984,5.087871074676514
725,1.4909,8.115151405334473
750,1.2788,9.999999046325684
775,1.1642,9.999998092651367
800,1.2852,8.533564567565918
825,1.4995,6.425107002258301
850,1.4728,7.173632621765137
875,1.2195,9.999999046325684
900,1.0725,10.0
925,1.407,9.999998092651367
950,1.3089,9.999999046325684
975,1.2133,6.951350688934326
1000,0.9161,6.956536769866943
1025,0.8923,6.5048980712890625
1050,0.7664,5.490457057952881
1075,0.6669,8.969732284545898
1100,0.57,6.964494705200195
1125,0.5673,6.175039768218994
1150,0.5612,4.365687847137451
1175,0.4641,6.405065059661865
1200,0.4512,7.912027359008789
1225,0.4274,7.463885307312012
1250,0.4027,4.986520290374756
1275,0.3658,5.006614685058594
1300,0.4006,4.416974067687988
1325,0.3343,3.033876895904541
1350,0.3303,3.0094447135925293
1375,0.368,4.074039459228516
1400,0.2551,2.561288595199585
1425,0.2854,4.860777854919434
1450,0.2728,4.60885763168335
1475,0.2743,4.4157819747924805
1500,0.2663,4.541990280151367
1525,0.293,3.2872719764709473
1550,0.2733,3.2525782585144043
1575,0.3007,2.4279098510742188
1600,0.2244,2.6792752742767334
1625,0.3133,5.864560127258301
1650,0.3527,9.413264274597168
1675,0.2966,4.826953887939453
1700,0.2604,4.045746803283691
1725,0.2359,4.011420249938965
1750,0.2346,3.0883126258850098
1775,0.239,3.6184933185577393
1800,0.2159,3.680492639541626
1825,0.2074,2.80781888961792
1850,0.2135,1.8006107807159424
1875,0.1984,1.975327968597412
1900,0.2359,4.4519829750061035
1925,0.3254,5.481602668762207
1950,0.215,3.976586103439331
1975,0.2389,3.3455350399017334
2000,0.2567,2.9957892894744873
2025,0.2984,7.376578330993652
2050,0.2943,3.9867990016937256
2075,0.2098,2.9383342266082764
2100,0.2376,3.178882598876953
2125,0.2174,4.625823020935059
2150,0.2556,3.780802011489868
2175,0.2425,3.4531807899475098
2200,0.2159,2.2498137950897217
2225,0.1964,3.480879545211792
2250,0.2222,3.478935718536377
2275,0.2524,2.5691466331481934
2300,0.2666,4.4807634353637695
2325,0.2777,8.857295989990234
2350,0.3463,6.194652080535889
2375,0.2807,3.8633298873901367
2400,0.2235,3.748914957046509
2425,0.2706,3.7181026935577393
2450,0.4206,5.784154415130615
2475,0.4293,4.211385250091553
2500,0.3247,2.5507090091705322
2525,0.2979,5.2416605949401855
2550,0.2541,3.939008951187134
2575,0.2734,4.834407329559326
2600,0.2106,2.6947684288024902
2625,0.2367,3.3849809169769287
2650,0.2641,3.6567835807800293
2675,0.2862,1.7707035541534424
2700,0.2334,3.6603424549102783
2725,0.2461,4.508834362030029
2750,0.3099,5.292873859405518
2775,0.299,2.941026210784912
2800,0.3441,3.3865294456481934
2825,0.2827,2.9909675121307373
2850,0.4028,4.660192489624023
2875,0.2922,3.6457438468933105
2900,0.3052,4.334083557128906
2925,0.2695,1.6578612327575684
2950,0.2473,3.9105734825134277
2975,0.2289,3.7363741397857666
3000,0.2265,5.946505546569824
3025,0.2439,3.1521129608154297
3050,0.2934,6.297743797302246
3075,0.2047,3.7168004512786865
3100,0.1968,2.5231215953826904
3125,0.2402,1.5523802042007446
3150,0.2026,3.95577335357666
3175,0.2114,2.6147470474243164
3200,0.2051,1.9665610790252686
3225,0.2236,3.4738948345184326
3250,0.2246,4.726480960845947
3275,0.2425,6.082703113555908
3300,0.2622,3.778524875640869
3325,0.3312,2.57025146484375
3350,0.308,2.0766170024871826
3375,0.2157,1.8118575811386108
3400,0.197,2.521602153778076
3425,0.18,2.3297104835510254
3450,2.0385,1.8249939680099487
3475,0.2003,4.042101860046387
3500,0.2248,2.5911829471588135
3525,0.2145,4.426886081695557
3550,0.2414,2.5873820781707764
3575,0.2265,3.574604034423828
3600,0.2162,2.1246144771575928
3625,0.2119,2.4623210430145264
3650,0.2666,1.939052939414978
3675,0.2917,4.871487617492676
3700,0.2766,3.3946070671081543
3725,0.223,3.1354947090148926
3750,0.2182,2.2619903087615967
3775,0.2194,2.680527687072754
3800,0.1948,2.257735252380371
3825,0.2236,1.8460540771484375
3850,0.1927,3.9407341480255127
3875,0.2386,2.1662144660949707
3900,0.2215,4.368568420410156
3925,0.2263,2.4291648864746094
3950,0.2556,1.9631394147872925
3975,0.2137,2.8494460582733154
4000,0.2219,3.429109811782837
4025,0.2052,2.8964619636535645
4050,0.2166,4.051430702209473
4075,0.252,4.998623371124268
4100,0.3473,4.567267417907715
4125,0.3993,4.64363431930542
4150,0.4055,1.962385892868042
4175,0.2564,3.884730339050293
4200,0.2813,3.614605665206909
4225,0.2429,5.032766342163086
4250,0.2083,3.4835762977600098
4275,0.224,3.03711199760437
4300,0.2118,2.2498130798339844
4325,0.2248,2.638035535812378
4350,0.2423,3.831488609313965
4375,0.2705,3.109325408935547
4400,0.397,7.651581287384033
4425,0.5287,6.074461460113525
4450,0.6548,10.0
4475,0.5806,4.721529006958008
4500,0.3468,3.7539854049682617
4525,0.3645,5.81071138381958
4550,0.5205,8.466436386108398
4575,0.4793,6.861752986907959
4600,0.489,3.1359570026397705
4625,0.2985,3.413712501525879
4650,0.2619,3.5613062381744385
4675,0.8445,5.510183334350586
4700,0.2694,2.35094952583313
4725,0.3175,3.022472381591797
4750,0.3737,4.120944499969482
4775,0.29,2.8101983070373535
4800,0.2365,2.885542154312134
4825,0.3186,5.574375152587891
4850,0.2699,1.6198357343673706
4875,0.2939,3.4339687824249268
4900,0.243,2.536407947540283
4925,0.248,2.5938756465911865
4950,0.2042,3.654160261154175
4975,0.2837,2.9111123085021973
5000,0.2336,2.0088400840759277
5025,0.2027,2.629927158355713
5050,0.2154,2.0652315616607666
5075,0.1898,2.2361974716186523
5100,0.3048,9.999998092651367
5125,0.3449,3.2120394706726074
5150,0.2263,4.242217540740967
5175,0.2307,3.623842239379883
5200,0.2684,7.33601188659668
5225,0.3751,3.1884450912475586
5250,0.3096,3.7340331077575684
5275,0.2725,2.2840030193328857
5300,0.2638,3.211394786834717
5325,0.3037,2.5673115253448486
5350,0.2863,3.181957960128784
5375,0.2699,3.7148170471191406
5400,0.2763,5.346311092376709
5425,0.3173,3.7558517456054688
5450,0.2859,2.272958517074585
5475,0.2568,3.792710542678833
5500,0.2886,2.5337955951690674
5525,0.2855,3.8816304206848145
5550,0.4484,6.751675605773926
5575,0.6011,4.532516956329346
5600,0.6591,6.416435241699219
5625,0.6223,6.285699844360352
5650,0.628,3.7751307487487793
5675,0.4836,3.9472553730010986
5700,0.3209,2.05910062789917
5725,0.3001,3.1533219814300537
5750,0.2771,1.726547360420227
5775,0.3288,2.7609128952026367
5800,0.3313,3.0350358486175537
5825,0.329,2.0775253772735596
5850,0.2945,2.3551688194274902
5875,0.2795,2.8756253719329834
5900,0.2915,2.1013882160186768
5925,0.3235,1.9603461027145386
5950,0.3756,4.011349201202393
5975,0.3085,3.3174166679382324
6000,0.4271,3.70078706741333
6025,0.525,4.48657751083374
6050,0.5792,3.7473058700561523
6075,0.4738,3.4352762699127197
6100,0.4601,4.7443318367004395
6125,0.4362,5.010796070098877
6150,0.3733,3.3928487300872803
6175,0.4489,3.691997528076172
6200,0.4268,4.077215671539307
6225,0.4332,2.4025914669036865
6250,0.3139,1.1958376169204712
6275,0.2819,3.412989377975464
6300,0.3314,2.409029006958008
6325,0.2879,4.068899631500244
6350,0.3133,3.1250805854797363
6375,0.4361,6.479849815368652
6400,0.5266,9.999999046325684
6425,0.3655,2.052577257156372
6450,0.4078,2.718487501144409
6475,0.5708,2.5393545627593994
6500,0.5908,4.421356201171875
6525,0.5333,3.2929673194885254
6550,0.4549,5.323559761047363
6575,0.4637,4.3406829833984375
6600,0.9096,2.5741612911224365
6625,0.4315,4.236935615539551
6650,0.4595,3.2091827392578125
6675,0.4909,5.050178527832031
6700,0.5366,4.042117595672607
6725,0.5275,5.56032133102417
6750,0.5438,4.945067882537842
6775,0.5959,3.912391185760498
6800,0.6052,5.062077045440674
6825,0.5759,4.203139305114746
6850,0.6,3.9204838275909424
6875,0.5292,3.937417507171631
6900,0.5863,3.4809153079986572
6925,0.5576,3.2194325923919678
6950,0.5895,5.168957233428955
6975,0.5684,3.555751085281372
7000,0.5387,3.1332764625549316
7025,0.5062,6.89694881439209
7050,0.6241,5.807682037353516
7075,0.6962,5.834748268127441
7100,0.7207,5.457459449768066
7125,0.7399,5.64279317855835
7150,0.6447,5.270878791809082
7175,0.6111,5.904502868652344
7200,0.7905,8.198131561279297
7225,1.1965,9.766966819763184
7250,0.8963,6.869325637817383
7275,1.0628,8.57149600982666
7300,0.9464,6.814278602600098
7325,0.8141,7.547422409057617
7350,0.7995,10.0
7375,0.7358,6.016157627105713
7400,1.1397,10.0
7425,1.2956,7.940433979034424
7450,1.2686,4.957721710205078
7475,0.929,7.410361289978027
7500,0.7621,5.946856498718262
7525,0.6776,5.345898151397705
7550,0.8398,6.915894985198975
7575,0.7527,4.215994834899902
7600,0.8056,10.0
7625,0.989,8.950183868408203
7650,1.2019,9.999998092651367
7675,1.0529,7.125528812408447
7700,1.023,6.8198137283325195
7725,1.0716,7.366546154022217
7750,0.9624,7.515008449554443
7775,0.8452,4.907805919647217
7800,0.6327,3.3749523162841797
7825,0.5621,7.235078811645508
7850,0.5825,5.887763500213623
7875,0.5249,6.869328498840332
7900,0.6365,4.994117736816406
7925,0.5982,5.468984603881836
7950,0.6029,3.0212745666503906
7975,0.6189,4.107227802276611
8000,0.5558,6.86392879486084
8025,0.6577,4.903964519500732
8050,0.5784,5.611396789550781
8075,0.5781,5.847573280334473
8100,0.5665,7.835755348205566
8125,0.6038,3.60332989692688
8150,0.5998,3.3499767780303955
8175,0.5485,5.414116382598877
8200,0.5193,4.981704235076904
8225,0.5672,4.212274551391602
8250,0.5654,2.9717214107513428
8275,0.5837,5.550238609313965
8300,0.5305,6.510632038116455
8325,0.5726,2.8211727142333984
8350,0.5923,7.3533525466918945
8375,0.5798,4.2050628662109375
8400,0.5457,5.426537990570068
8425,0.6445,8.916367530822754
8450,0.5335,3.435342788696289
8475,0.6645,5.325408935546875
8500,0.6178,4.976362228393555
8525,0.7073,5.221662998199463
8550,0.6584,5.579411029815674
8575,0.5841,4.318902969360352
8600,0.5885,7.043297290802002
8625,0.4923,6.708474636077881
8650,0.6191,4.643575191497803
8675,0.5722,6.608451843261719
8700,0.7361,6.543538570404053
8725,0.7505,10.0
8750,0.7809,7.388099193572998
8775,0.8591,5.904901504516602
8800,1.1517,8.434646606445312
8825,1.2703,8.504474639892578
8850,1.3692,7.467097759246826
8875,1.4739,10.0
8900,1.6351,9.131770133972168
8925,1.4685,8.618627548217773
8950,1.1797,9.49679183959961
8975,1.0362,10.0
9000,0.7908,6.54273796081543
9025,1.003,5.984649181365967
9050,1.0115,6.730302333831787
9075,2.3353,8.481163024902344
9100,8.8228,10.000000953674316
9125,0.822,8.870530128479004
9150,0.8056,5.662878036499023
9175,0.7811,7.857844829559326
9200,1.1736,4.50975227355957
9225,1.3848,10.0
9250,1.1964,8.632330894470215
9275,1.2202,9.999998092651367
9300,1.0701,6.165679454803467
9325,0.8573,9.662639617919922
9350,0.9595,7.709205150604248
9375,0.998,5.787785053253174
9400,0.8761,5.231419086456299
9425,0.7324,3.4517014026641846
9450,0.7777,6.099903583526611
9475,0.9167,7.82935094833374
9500,0.8305,4.524116516113281
9525,0.8576,6.013489723205566
9550,0.7513,6.795015335083008
9575,0.9275,7.952845573425293
9600,0.9914,5.938045024871826
9625,0.8977,4.757489204406738
9650,1.0302,6.430868148803711
9675,0.9498,8.093586921691895
9700,0.8273,7.50097131729126
9725,0.8959,9.999999046325684
9750,0.8605,9.999998092651367
9775,0.897,9.04084300994873
9800,1.0569,9.40126895904541
9825,1.0,8.271095275878906
9850,1.0199,5.211069583892822
9875,0.7682,4.611247539520264
9900,0.7037,6.649309158325195
9925,0.7575,7.5593743324279785
9950,0.6609,7.5696797370910645
9975,0.652,5.30731201171875
10000,0.55,6.973793029785156
10025,0.678,4.325422763824463
10050,0.6145,5.384605884552002
10075,0.6122,3.1212027072906494
10100,0.5207,4.432228088378906
10125,0.5429,5.909042835235596
10150,0.5825,3.840482711791992
10175,0.497,6.464734077453613
10200,0.561,3.831021308898926
10225,0.5942,4.269604206085205
10250,0.6365,6.719264507293701
10275,0.786,4.552702903747559
10300,0.6795,7.5663557052612305
10325,0.7036,5.126781940460205
10350,0.6486,6.3577961921691895
10375,0.6343,4.263833522796631
10400,0.7256,6.06663179397583
10425,0.5955,6.957421779632568
10450,0.7493,6.274393081665039
10475,0.6709,5.577758312225342
10500,0.7337,9.869497299194336
10525,0.7602,10.0
10550,0.7623,3.3764655590057373
10575,0.8676,9.74258041381836
10600,0.8063,7.281429767608643
10625,1.303,7.7411298751831055
10650,1.1091,7.891229629516602
10675,1.0167,6.40557336807251
10700,0.9532,8.542132377624512
10725,1.0725,10.0
10750,0.8681,7.855854511260986
10775,0.6245,5.295994281768799
10800,0.798,6.245997905731201
10825,0.7465,3.56915545463562
10850,1.1146,7.232759475708008
10875,1.01,7.144115447998047
10900,0.8175,9.283742904663086
10925,0.7724,4.0777907371521
10950,0.6845,3.9145376682281494
10975,0.6973,8.036284446716309
11000,0.6929,6.701058387756348
11025,0.8137,4.834790229797363
11050,0.6284,9.999998092651367
11075,0.9124,7.314215183258057
11100,1.1084,4.6845479011535645
11125,1.0298,4.529223442077637
11150,0.9695,8.942623138427734
11175,0.8152,9.99999713897705
11200,0.8431,7.805789470672607
11225,0.8153,7.58958101272583
11250,0.8167,6.402045249938965
11275,0.8171,5.116407871246338
11300,0.6991,4.415517807006836
11325,0.8407,5.388542652130127
11350,0.8488,9.928600311279297
11375,0.7895,9.984822273254395
11400,0.6633,8.3101167678833
11425,0.7409,8.01140022277832
11450,0.7331,3.3790359497070312
11475,0.7246,5.916175842285156
11500,0.6462,4.511324882507324
11525,0.6295,9.999999046325684
11550,0.833,5.360689640045166
11575,0.8448,7.188095569610596
11600,0.7705,8.284466743469238
11625,0.6943,8.768387794494629
11650,0.8195,6.779496192932129
11675,0.8227,6.228411674499512
11700,0.822,4.794731140136719
11725,0.8145,4.857844829559326
11750,0.7351,4.976624011993408
11775,0.7285,4.682915210723877
11800,0.6428,5.454544544219971
11825,0.7488,5.217667102813721
11850,0.8093,9.999999046325684
11875,0.7029,6.276889324188232
11900,0.7525,4.114125728607178
11925,0.7461,5.132946014404297
11950,0.7805,5.300218105316162
11975,0.7079,5.23477840423584
12000,0.8147,6.446083068847656
12025,0.8166,6.6287455558776855
12050,0.8299,9.658268928527832
12075,0.7512,5.166134834289551
12100,0.6657,6.4543280601501465
12125,0.9304,7.561258316040039
12150,0.7973,6.71431827545166
12175,0.7572,7.901317119598389
12200,0.8029,8.718077659606934
12225,0.7772,4.240918159484863
12250,0.8545,7.042811393737793
12275,0.843,6.165143966674805
12300,0.8973,5.622447490692139
12325,0.8744,6.034954071044922
12350,0.8141,7.312039852142334
12375,0.7893,9.858924865722656
12400,0.7833,5.383648872375488
12425,0.8043,4.915627956390381
12450,0.7433,6.988242149353027
12475,0.7643,8.0437593460083
12500,0.941,7.186142444610596
12500,nan,nan