maanasharma5's picture
Upload folder using huggingface_hub
b997456 verified
step,training_loss,grad_norm
10,22.4391,9.999999046325684
20,18.5401,10.0
30,18.8722,10.0
40,17.9956,10.0
50,15.0615,10.000000953674316
60,14.3948,9.999998092651367
70,12.1943,9.999999046325684
80,10.114,9.999999046325684
90,8.9744,9.999999046325684
100,8.1171,10.0
110,6.1562,10.0
120,6.1523,9.999999046325684
130,5.1105,10.0
140,4.6447,10.0
150,4.441,9.999999046325684
160,3.9956,9.999999046325684
170,3.6844,9.999999046325684
180,3.6594,9.74394702911377
190,3.5963,9.999999046325684
200,3.0941,9.999999046325684
210,3.0641,10.0
220,2.8093,10.0
230,2.9413,9.999998092651367
240,2.7816,9.999999046325684
250,2.6371,7.968898773193359
260,2.5965,9.999999046325684
270,2.7478,9.171067237854004
280,2.4879,9.04393196105957
290,2.2215,8.444461822509766
300,2.6473,8.200078964233398
310,2.3853,9.681734085083008
320,2.2498,9.111586570739746
330,2.0398,9.999998092651367
340,1.9816,9.552145957946777
350,2.0454,8.0576171875
360,1.8505,6.90339994430542
370,1.8279,8.755167007446289
380,1.8657,8.947823524475098
390,1.6115,9.317538261413574
400,1.6446,9.361852645874023
410,1.5443,7.044137001037598
420,1.4368,6.381120681762695
430,1.4774,7.995136260986328
440,1.3529,6.258317470550537
450,1.3406,5.482784748077393
460,1.3311,5.9611921310424805
470,1.2302,5.832077503204346
480,1.1862,5.394923686981201
490,1.1394,4.73380708694458
500,1.2688,5.2955427169799805
510,1.1342,6.693230628967285
520,1.1557,6.776840686798096
530,1.0529,5.950035572052002
540,1.1195,6.108712673187256
550,1.1074,7.9674787521362305
560,1.0794,5.42255163192749
570,1.0796,8.32884693145752
580,1.0595,5.415431022644043
590,1.0503,5.638887405395508
600,1.037,6.9637908935546875
610,0.915,4.847858905792236
620,0.9626,4.449883460998535
630,0.9122,6.299098968505859
640,0.9696,9.391380310058594
650,0.8972,7.544974327087402
660,0.9055,5.396461009979248
670,0.9223,6.584786891937256
680,0.8602,5.7641072273254395
690,0.8629,5.566444396972656
700,0.8402,5.248049736022949
710,0.8218,4.847179889678955
720,0.8042,5.082803726196289
730,0.8003,3.536363124847412
740,0.8405,7.2759857177734375
750,0.7769,5.047908306121826
760,0.7445,4.044074535369873
770,0.7424,4.787796497344971
780,0.7705,5.314538955688477
790,0.8262,7.510671138763428
800,0.8339,6.341707706451416
810,0.6955,5.165682792663574
820,0.7221,6.235734939575195
830,0.6867,6.6283488273620605
840,0.733,8.073585510253906
850,0.7132,8.499881744384766
860,0.7183,6.54105806350708
870,0.6529,5.989783763885498
880,0.6531,4.016666412353516
890,0.6357,6.746622085571289
900,0.6638,5.905118942260742
910,0.6784,5.090343952178955
920,0.635,6.740263938903809
930,0.6421,6.317070484161377
940,0.5963,6.079349994659424
950,0.6379,4.388522624969482
960,0.5692,3.835901975631714
970,0.6069,3.3163001537323
980,0.5933,5.156872749328613
990,0.544,3.8711464405059814
1000,0.6124,6.842670917510986
1010,0.5312,5.548664569854736
1020,0.6036,6.509451389312744
1030,0.5867,3.848813533782959
1040,0.5403,4.100753307342529
1050,0.5903,4.498255252838135
1060,0.5171,5.71539831161499
1070,0.5315,6.740539073944092
1080,0.6017,5.979411602020264
1090,0.5629,5.852504253387451
1100,0.5144,3.0850918292999268
1110,0.4906,4.634555339813232
1120,0.5649,6.15895414352417
1130,0.4627,4.997654914855957
1140,0.4985,4.061686038970947
1150,0.4774,4.477031707763672
1160,0.4635,5.712886810302734
1170,0.4568,7.275344371795654
1180,0.4543,4.3618364334106445
1190,0.4615,6.843659400939941
1200,0.4053,4.021126747131348
1210,0.4241,4.5041069984436035
1220,0.4412,4.459962844848633
1230,0.4122,3.881894588470459
1240,0.4358,4.284637451171875
1250,0.407,4.454357624053955
1260,0.3787,3.3918070793151855
1270,0.4132,4.96063756942749
1280,0.409,5.919780254364014
1290,0.4547,5.709549427032471
1300,0.4131,4.5489349365234375
1310,0.4027,3.3304429054260254
1320,0.3894,2.7704129219055176
1330,0.3766,6.625534534454346
1340,0.4129,4.533291339874268
1350,0.366,6.264132976531982
1360,0.3728,4.117740631103516
1370,0.3514,3.296051025390625
1380,0.3392,4.544425964355469
1390,0.3427,6.508903980255127
1400,0.3154,3.8851804733276367
1410,0.3421,4.247873783111572
1420,0.3086,5.067176818847656
1430,0.3494,3.9404332637786865
1440,0.3144,4.0142822265625
1450,0.3061,2.31613826751709
1460,0.2921,3.2096686363220215
1470,0.3227,5.634882926940918
1480,0.3521,4.442248344421387
1490,0.3034,3.5769202709198
1500,0.2806,4.759718894958496
1510,0.2903,5.413734436035156
1520,0.3088,5.242001533508301
1530,0.292,3.810133218765259
1540,0.2982,5.0193023681640625
1550,0.2494,3.1278297901153564
1560,0.2765,3.620786190032959
1570,0.273,3.282259464263916
1580,0.2675,2.5962984561920166
1590,0.2561,5.7002787590026855
1600,0.2642,3.456076145172119
1610,0.289,3.859783411026001
1620,0.2722,2.2919702529907227
1630,0.2393,2.624751567840576
1640,0.2401,3.1490752696990967
1650,0.2362,3.9848804473876953
1660,0.2363,5.311415672302246
1670,0.244,2.246136426925659
1680,0.2428,2.677457571029663
1690,0.2147,3.197678327560425
1700,0.225,4.309765815734863
1710,0.2173,3.1181559562683105
1720,0.2174,2.730708360671997
1730,0.2065,2.331942081451416
1740,0.2154,4.71842622756958
1750,0.225,2.290827989578247
1760,0.2234,1.7604676485061646
1770,0.2069,2.8914430141448975
1780,0.2137,2.695112466812134
1790,0.2265,3.153864860534668
1800,0.2184,2.9276316165924072
1810,0.2047,2.0935676097869873
1820,0.196,2.0270116329193115
1830,0.2023,3.581533670425415
1840,0.1947,2.189016342163086
1850,0.1968,2.613018274307251
1860,0.1795,1.6381279230117798
1870,0.185,2.9138712882995605
1880,0.2061,3.8309102058410645
1890,0.1847,2.3997795581817627
1900,0.1898,2.6803364753723145
1910,0.1935,2.676018238067627
1920,0.194,4.005608558654785
1930,0.178,2.0579423904418945
1940,0.1769,3.387993574142456
1950,0.172,2.394421339035034
1960,0.1776,3.314922571182251
1970,0.1765,3.107218027114868
1980,0.1879,4.710299015045166
1990,0.1689,2.651448965072632
2000,0.1854,2.7613463401794434
2010,0.201,2.5603368282318115
2020,0.1606,2.4434683322906494
2030,0.1695,3.0501456260681152
2040,0.177,1.5982695817947388
2050,0.1763,2.7528181076049805
2060,0.1702,2.7957491874694824
2070,0.164,1.6270503997802734
2080,0.1748,2.3618762493133545
2090,0.1541,3.2674052715301514
2100,0.1517,1.9046889543533325
2110,0.1861,1.8505709171295166
2120,0.1548,3.82865047454834
2130,0.1797,3.949946641921997
2140,0.1639,2.983675956726074
2150,0.1588,1.9660401344299316
2160,0.1553,2.7449395656585693
2170,0.1603,1.9276952743530273
2180,0.1598,2.2562904357910156
2190,0.1601,2.2897818088531494
2200,0.1417,1.7737034559249878
2210,0.1794,2.640472173690796
2220,0.1445,2.8277909755706787
2230,0.1528,2.287991523742676
2240,0.1393,2.436365842819214
2250,0.1391,2.4227402210235596
2260,0.1423,1.8195456266403198
2270,0.1465,1.9462803602218628
2280,0.1217,1.5456150770187378
2290,0.1316,3.13179612159729
2300,0.1432,2.0412580966949463
2310,0.1325,2.3401479721069336
2320,0.1503,1.8098496198654175
2330,0.1452,1.7403185367584229
2340,0.1484,2.0069713592529297
2350,0.138,2.249183416366577
2360,0.1389,1.7765642404556274
2370,0.1552,1.5941318273544312
2380,0.1375,1.5062505006790161
2390,0.1368,2.394498586654663
2400,0.1367,2.680593967437744
2410,0.1297,1.6163920164108276
2420,0.131,2.071157455444336
2430,0.1304,3.0522313117980957
2440,0.127,2.017282009124756
2450,0.1244,1.9524980783462524
2460,0.1409,2.556171417236328
2470,0.1274,1.6622446775436401
2480,0.1323,1.9248820543289185
2490,0.1301,2.1036221981048584
2500,0.1216,1.6761208772659302
2510,0.1338,2.89397931098938
2520,0.1264,2.2912402153015137
2530,0.1321,2.0714144706726074
2540,0.1277,3.272960901260376
2550,0.1301,1.8504010438919067
2560,0.1225,2.447061061859131
2570,0.1377,2.020902395248413
2580,0.1238,1.4962462186813354
2590,0.1254,2.4895267486572266
2600,0.1391,1.4031554460525513
2610,0.1228,1.472172498703003
2620,0.1216,1.7857037782669067
2630,0.1271,2.2501163482666016
2640,0.1394,2.6882874965667725
2650,0.1163,1.6687155961990356
2660,0.1257,2.6670000553131104
2670,0.1333,1.77886164188385
2680,0.1151,1.5165330171585083
2690,0.1213,1.5670900344848633
2700,0.1232,1.878943920135498
2710,0.1244,1.5453932285308838
2720,0.1189,1.8712074756622314
2730,0.1202,1.4645411968231201
2740,0.1162,1.605932354927063
2750,0.1287,1.7104394435882568
2760,0.2169,1.9555670022964478
2770,0.1144,2.0241458415985107
2780,0.1134,1.8091477155685425
2790,0.122,2.328983783721924
2800,0.1177,2.8249378204345703
2810,0.128,1.338085651397705
2820,0.1057,1.635053038597107
2830,0.1097,1.7977182865142822
2840,0.1237,1.781990647315979
2850,0.1171,2.48148775100708
2860,0.1077,1.3490359783172607
2870,0.1066,1.5256094932556152
2880,0.125,1.5943819284439087
2890,0.1112,1.8614747524261475
2900,0.1246,1.2486650943756104
2910,0.1231,2.3569819927215576
2920,0.114,2.198814868927002
2930,0.1127,1.7546306848526
2940,0.1128,1.148824691772461
2950,0.1126,1.61479914188385
2960,0.1133,2.365548849105835
2970,0.1285,1.6197785139083862
2980,0.1108,1.727784276008606
2990,0.1145,1.6709702014923096
3000,0.1135,2.0024709701538086
3010,0.1063,1.8355417251586914
3020,0.1203,1.5643547773361206
3030,0.1158,2.120378255844116
3040,0.12,2.3552708625793457
3050,0.1143,1.9691171646118164
3060,0.1239,2.707933187484741
3070,0.1111,1.4246569871902466
3080,0.1151,1.4995771646499634
3090,0.1178,2.139070749282837
3100,0.109,1.5565009117126465
3110,0.1226,1.771331787109375
3120,0.1086,2.2940099239349365
3125,nan,nan