| step,training_loss,grad_norm | |
| 10,24.9631,10.000000953674316 | |
| 20,20.8406,10.0 | |
| 30,18.8175,10.0 | |
| 40,20.6395,10.000000953674316 | |
| 50,17.492,9.999998092651367 | |
| 60,15.7832,10.0 | |
| 70,14.5836,10.0 | |
| 80,12.4576,9.999999046325684 | |
| 90,10.0393,10.0 | |
| 100,7.721,9.999999046325684 | |
| 110,7.7382,10.000000953674316 | |
| 120,5.6715,9.999999046325684 | |
| 130,5.0697,9.999999046325684 | |
| 140,4.6669,9.999999046325684 | |
| 150,4.5226,10.0 | |
| 160,3.7166,9.999999046325684 | |
| 170,3.6585,9.999999046325684 | |
| 180,3.0612,9.999999046325684 | |
| 190,3.1613,10.0 | |
| 200,3.059,9.628771781921387 | |
| 210,2.7733,9.586786270141602 | |
| 220,2.6752,9.884883880615234 | |
| 230,2.7686,8.088533401489258 | |
| 240,2.463,7.879763603210449 | |
| 250,2.2555,10.0 | |
| 260,2.4123,8.265613555908203 | |
| 270,2.1918,8.316008567810059 | |
| 280,2.2272,9.114105224609375 | |
| 290,1.9593,9.300642013549805 | |
| 300,2.0377,9.566454887390137 | |
| 310,1.9443,8.621969223022461 | |
| 320,1.8093,7.225710391998291 | |
| 330,1.9922,9.70196533203125 | |
| 340,1.8382,7.131272792816162 | |
| 350,1.7659,7.785069465637207 | |
| 360,1.6541,8.18884563446045 | |
| 370,1.6964,8.7020263671875 | |
| 380,1.7058,9.419608116149902 | |
| 390,1.5773,4.900589942932129 | |
| 400,1.7163,9.17340087890625 | |
| 410,1.6505,7.4362616539001465 | |
| 420,1.5706,6.498612880706787 | |
| 430,1.5137,7.84408712387085 | |
| 440,1.5546,9.464787483215332 | |
| 450,1.4404,8.63725757598877 | |
| 460,1.3584,9.00522232055664 | |
| 470,1.2826,6.751660346984863 | |
| 480,1.2767,9.651211738586426 | |
| 490,1.3371,7.526703357696533 | |
| 500,1.2118,5.82845401763916 | |
| 510,1.0983,6.827119827270508 | |
| 520,1.1228,7.042975425720215 | |
| 530,0.9704,6.176724910736084 | |
| 540,1.183,9.999999046325684 | |
| 550,1.0296,5.635732650756836 | |
| 560,0.9987,9.842893600463867 | |
| 570,0.9455,8.999287605285645 | |
| 580,1.0243,9.999999046325684 | |
| 590,0.9884,6.9205827713012695 | |
| 600,0.977,9.999999046325684 | |
| 610,0.9394,9.999998092651367 | |
| 620,0.8862,9.98512077331543 | |
| 630,0.9152,6.723015785217285 | |
| 640,0.7909,5.47459602355957 | |
| 650,0.8646,5.321897029876709 | |
| 660,0.8641,7.815572738647461 | |
| 670,0.7373,4.958643436431885 | |
| 680,0.698,6.5276875495910645 | |
| 690,0.784,6.228632926940918 | |
| 700,0.6606,7.006032943725586 | |
| 710,0.7276,6.825442790985107 | |
| 720,0.6912,6.571051120758057 | |
| 730,0.7122,4.326778411865234 | |
| 740,0.6474,4.319221019744873 | |
| 750,0.6999,5.887426853179932 | |
| 760,0.6467,4.543856620788574 | |
| 770,0.6638,4.395698070526123 | |
| 780,0.5995,6.596084117889404 | |
| 790,0.5944,8.952577590942383 | |
| 800,0.6457,8.518202781677246 | |
| 810,0.6516,8.593810081481934 | |
| 820,0.6265,4.971993923187256 | |
| 830,0.5941,7.201608657836914 | |
| 840,0.5637,5.481573104858398 | |
| 850,0.5177,5.261704444885254 | |
| 860,0.5685,6.122642993927002 | |
| 870,0.5585,4.627248764038086 | |
| 880,0.5825,4.712826728820801 | |
| 890,0.5572,7.80577278137207 | |
| 900,0.5302,5.428683280944824 | |
| 910,0.5665,6.566429615020752 | |
| 920,0.5625,7.354272365570068 | |
| 930,0.5421,5.946643352508545 | |
| 940,0.4312,6.19100284576416 | |
| 950,0.474,4.216638565063477 | |
| 960,0.465,4.427928447723389 | |
| 970,0.4665,4.779841423034668 | |
| 980,0.48,5.669528484344482 | |
| 990,0.51,7.017117500305176 | |
| 1000,0.5019,7.059611797332764 | |
| 1010,0.4544,4.046283721923828 | |
| 1020,0.4836,4.116858005523682 | |
| 1030,0.4327,4.138635635375977 | |
| 1040,0.4197,5.3947577476501465 | |
| 1050,0.4455,4.98423957824707 | |
| 1060,0.4911,4.391843318939209 | |
| 1070,0.4314,3.1840767860412598 | |
| 1080,0.4114,4.046396732330322 | |
| 1090,0.4386,5.266067981719971 | |
| 1100,0.4145,5.4654951095581055 | |
| 1110,0.4039,3.72259521484375 | |
| 1120,0.3989,4.96457052230835 | |
| 1130,0.3456,3.831160068511963 | |
| 1140,0.3827,4.052297115325928 | |
| 1150,0.3745,5.16130256652832 | |
| 1160,0.36,4.293144226074219 | |
| 1170,0.3906,2.9887006282806396 | |
| 1180,0.3718,5.04908561706543 | |
| 1190,0.3667,4.748033046722412 | |
| 1200,0.3187,6.720622539520264 | |
| 1210,0.3489,5.302358150482178 | |
| 1220,0.3638,3.59417462348938 | |
| 1230,0.3533,6.106253147125244 | |
| 1240,0.3413,3.0482683181762695 | |
| 1250,0.3503,4.1857500076293945 | |
| 1260,0.3224,3.9182565212249756 | |
| 1270,0.3237,3.7868616580963135 | |
| 1280,0.3375,3.272305965423584 | |
| 1290,0.3339,3.8790831565856934 | |
| 1300,0.3089,4.695404052734375 | |
| 1310,0.3289,3.2050020694732666 | |
| 1320,0.3361,3.027517557144165 | |
| 1330,0.3012,3.260744571685791 | |
| 1340,0.2947,2.5760984420776367 | |
| 1350,0.2798,3.7423956394195557 | |
| 1360,0.2573,2.8880527019500732 | |
| 1370,0.2884,3.848341464996338 | |
| 1380,0.26,2.9584686756134033 | |
| 1390,0.2591,3.3850250244140625 | |
| 1400,0.275,4.0127387046813965 | |
| 1410,0.2892,3.7733118534088135 | |
| 1420,0.2691,2.6666953563690186 | |
| 1430,0.2745,3.1808416843414307 | |
| 1440,0.2663,4.617330074310303 | |
| 1450,0.2528,3.740236520767212 | |
| 1460,0.2554,3.2529256343841553 | |
| 1470,0.2588,3.2568247318267822 | |
| 1480,0.262,5.33850622177124 | |
| 1490,0.2468,5.042779922485352 | |
| 1500,0.2623,2.649498224258423 | |
| 1510,0.2409,3.46178936958313 | |
| 1520,0.2404,4.172382831573486 | |
| 1530,0.2308,2.367910385131836 | |
| 1540,0.2362,2.469956398010254 | |
| 1550,0.2457,2.4397411346435547 | |
| 1560,0.214,2.6383445262908936 | |
| 1570,0.2055,2.170884609222412 | |
| 1580,0.2212,2.846895217895508 | |
| 1590,0.204,2.712366819381714 | |
| 1600,0.2047,2.447471857070923 | |
| 1610,0.2323,2.5376291275024414 | |
| 1620,0.2043,3.2458057403564453 | |
| 1630,0.2185,2.34938645362854 | |
| 1640,0.1977,3.2154054641723633 | |
| 1650,0.1998,2.5128464698791504 | |
| 1660,0.1978,3.6363720893859863 | |
| 1670,0.1849,1.650388479232788 | |
| 1680,0.1973,2.6597306728363037 | |
| 1690,0.2012,2.410196304321289 | |
| 1700,0.1887,2.417191743850708 | |
| 1710,0.1812,1.77193021774292 | |
| 1720,0.1729,2.4603259563446045 | |
| 1730,0.1799,2.3087384700775146 | |
| 1740,0.1971,3.3030126094818115 | |
| 1750,0.1855,2.3733720779418945 | |
| 1760,0.1619,1.909800410270691 | |
| 1770,0.1987,3.0450034141540527 | |
| 1780,0.1902,7.974597454071045 | |
| 1790,0.1881,3.595928907394409 | |
| 1800,0.1781,1.6789438724517822 | |
| 1810,0.1682,2.4755332469940186 | |
| 1820,0.1677,2.7560534477233887 | |
| 1830,0.1755,2.2446439266204834 | |
| 1840,0.1704,2.204357624053955 | |
| 1850,0.1628,2.05080509185791 | |
| 1860,0.1726,1.5275906324386597 | |
| 1870,0.1674,2.030513048171997 | |
| 1880,0.1648,2.6978938579559326 | |
| 1890,0.1557,1.7440263032913208 | |
| 1900,0.1636,2.075267791748047 | |
| 1910,0.1657,2.1358184814453125 | |
| 1920,0.1564,1.5332633256912231 | |
| 1930,0.1505,1.9167696237564087 | |
| 1940,0.15,3.0243899822235107 | |
| 1950,0.1503,2.9686858654022217 | |
| 1960,0.1537,2.0411455631256104 | |
| 1970,0.1447,2.8846511840820312 | |
| 1980,0.1507,2.098325490951538 | |
| 1990,0.1505,2.713503360748291 | |
| 2000,0.1551,2.709930658340454 | |
| 2010,0.1526,3.630295991897583 | |
| 2020,0.1369,1.6541911363601685 | |
| 2030,0.1445,2.212904214859009 | |
| 2040,0.1463,2.0813424587249756 | |
| 2050,0.1441,3.0553150177001953 | |
| 2060,0.1386,2.165588140487671 | |
| 2070,0.1401,1.6694422960281372 | |
| 2080,0.1426,1.8330750465393066 | |
| 2090,0.1325,1.9006876945495605 | |
| 2100,0.1477,2.488478660583496 | |
| 2110,0.1551,1.8582606315612793 | |
| 2120,0.1527,1.7370256185531616 | |
| 2130,0.1459,1.926459550857544 | |
| 2140,0.1399,1.9653120040893555 | |
| 2150,0.1409,2.491975784301758 | |
| 2160,0.1386,2.253796339035034 | |
| 2170,0.1254,2.142688512802124 | |
| 2180,0.1182,2.1504247188568115 | |
| 2190,0.1517,2.1450459957122803 | |
| 2200,0.1485,2.323805570602417 | |
| 2210,0.1369,2.709195613861084 | |
| 2220,0.1317,1.8090829849243164 | |
| 2230,0.1217,2.5093414783477783 | |
| 2240,0.1335,1.427565336227417 | |
| 2250,0.1264,2.4537243843078613 | |
| 2260,0.1357,1.7222257852554321 | |
| 2270,0.1282,1.5699914693832397 | |
| 2280,0.1346,1.597873330116272 | |
| 2290,0.1236,1.831920862197876 | |
| 2300,0.1307,1.5934253931045532 | |
| 2310,0.1345,1.5124200582504272 | |
| 2320,0.1336,2.2041866779327393 | |
| 2330,0.1355,1.9419604539871216 | |
| 2340,0.128,2.395643949508667 | |
| 2350,0.1278,1.6096221208572388 | |
| 2360,0.1153,1.5739423036575317 | |
| 2370,0.1172,2.158097982406616 | |
| 2380,0.1262,1.5097861289978027 | |
| 2390,0.1316,1.9915529489517212 | |
| 2400,0.1271,1.4936026334762573 | |
| 2410,0.1237,1.2583588361740112 | |
| 2420,0.1276,1.693161964416504 | |
| 2430,0.1126,1.8149479627609253 | |
| 2440,0.1128,1.5526076555252075 | |
| 2450,0.3024,8.050654411315918 | |
| 2460,0.1187,1.6099882125854492 | |
| 2470,0.1098,1.8025749921798706 | |
| 2480,0.1292,1.7324920892715454 | |
| 2490,0.114,2.0919933319091797 | |
| 2500,0.1258,1.464938998222351 | |
| 2510,0.118,1.8821276426315308 | |
| 2520,0.1147,1.4615644216537476 | |
| 2530,0.1143,1.6426907777786255 | |
| 2540,0.1135,2.4523229598999023 | |
| 2550,0.1245,1.6785757541656494 | |
| 2560,0.1156,1.503734827041626 | |
| 2570,0.1136,1.5107955932617188 | |
| 2580,0.1151,2.7832164764404297 | |
| 2590,0.1147,1.5118536949157715 | |
| 2600,0.1062,1.9129774570465088 | |
| 2610,0.1119,1.3641362190246582 | |
| 2620,0.1047,1.5150868892669678 | |
| 2630,0.1165,1.4528048038482666 | |
| 2640,0.1238,1.6915483474731445 | |
| 2650,0.1022,2.2077555656433105 | |
| 2660,0.1087,3.6118428707122803 | |
| 2670,0.1102,2.0867350101470947 | |
| 2680,0.1058,2.128396511077881 | |
| 2690,0.1063,1.7146245241165161 | |
| 2700,0.118,2.5430219173431396 | |
| 2710,0.1072,1.9589694738388062 | |
| 2720,0.1298,2.741550922393799 | |
| 2730,0.1033,2.003413677215576 | |
| 2740,0.1115,1.9745001792907715 | |
| 2750,0.1042,2.7120094299316406 | |
| 2760,0.1105,2.5961086750030518 | |
| 2770,0.1019,1.581310510635376 | |
| 2780,0.0936,1.422912836074829 | |
| 2790,0.1019,1.8189693689346313 | |
| 2800,0.1014,1.2943332195281982 | |
| 2810,0.1075,1.7528398036956787 | |
| 2820,0.1206,2.2377705574035645 | |
| 2830,0.1096,1.8247408866882324 | |
| 2840,0.1104,1.8777835369110107 | |
| 2850,0.1041,1.9983779191970825 | |
| 2860,0.1067,1.6120233535766602 | |
| 2870,0.1083,1.5283420085906982 | |
| 2880,0.1004,1.3929494619369507 | |
| 2890,0.101,1.3750373125076294 | |
| 2900,0.1053,1.5251433849334717 | |
| 2910,0.0976,1.520762324333191 | |
| 2920,0.0997,1.3639968633651733 | |
| 2930,0.0947,1.41064453125 | |
| 2940,0.1059,1.3565398454666138 | |
| 2950,0.1064,3.0992274284362793 | |
| 2960,0.0936,2.12271785736084 | |
| 2970,0.1025,2.1983823776245117 | |
| 2980,0.1032,2.5740675926208496 | |
| 2990,0.0982,2.195711851119995 | |
| 3000,0.0955,1.1637061834335327 | |
| 3010,0.1055,2.551534414291382 | |
| 3020,0.1045,1.514855980873108 | |
| 3030,0.098,1.692115068435669 | |
| 3040,0.104,2.3038151264190674 | |
| 3050,0.0956,2.007957935333252 | |
| 3060,0.1019,1.778769612312317 | |
| 3070,0.1024,1.8261606693267822 | |
| 3080,0.0995,1.3561267852783203 | |
| 3090,0.0984,1.6872135400772095 | |
| 3100,0.098,1.2371549606323242 | |
| 3110,0.1094,2.050222635269165 | |
| 3120,0.0958,1.5597504377365112 | |
| 3125,nan,nan | |