| step,training_loss,grad_norm | |
| 10,22.4391,10.000000953674316 | |
| 20,18.5398,9.999999046325684 | |
| 30,18.8696,10.0 | |
| 40,17.9832,9.999999046325684 | |
| 50,15.0181,10.0 | |
| 60,14.2746,9.999999046325684 | |
| 70,11.9335,10.0 | |
| 80,9.6611,10.0 | |
| 90,8.2423,10.0 | |
| 100,7.0975,9.999999046325684 | |
| 110,5.2427,10.0 | |
| 120,5.0576,9.999999046325684 | |
| 130,4.3215,9.999999046325684 | |
| 140,3.7479,9.999999046325684 | |
| 150,3.5213,9.422039985656738 | |
| 160,3.2425,9.999998092651367 | |
| 170,2.8891,9.351380348205566 | |
| 180,2.783,8.307005882263184 | |
| 190,2.7527,8.963129997253418 | |
| 200,2.4355,8.570749282836914 | |
| 210,2.4091,8.063360214233398 | |
| 220,2.1608,8.824004173278809 | |
| 230,2.2534,7.373661994934082 | |
| 240,2.1537,8.307866096496582 | |
| 250,1.9916,5.856404781341553 | |
| 260,1.9904,8.64548397064209 | |
| 270,2.0503,7.271899223327637 | |
| 280,1.9192,6.368246555328369 | |
| 290,1.6597,6.038721561431885 | |
| 300,1.9203,6.260958194732666 | |
| 310,1.8547,7.62371301651001 | |
| 320,1.7249,7.491437911987305 | |
| 330,1.5601,7.197510719299316 | |
| 340,1.6026,6.928409099578857 | |
| 350,1.5981,6.700569152832031 | |
| 360,1.4863,6.20810604095459 | |
| 370,1.5054,6.265394687652588 | |
| 380,1.4892,7.249783039093018 | |
| 390,1.3346,6.698989391326904 | |
| 400,1.269,6.408270359039307 | |
| 410,1.2479,6.221065521240234 | |
| 420,1.1823,6.697783470153809 | |
| 430,1.2215,6.298666000366211 | |
| 440,1.2094,5.8949875831604 | |
| 450,1.1668,4.865890026092529 | |
| 460,1.0941,4.905447006225586 | |
| 470,1.081,5.108652591705322 | |
| 480,1.0708,4.898155212402344 | |
| 490,0.9574,4.2186455726623535 | |
| 500,1.1016,4.5638957023620605 | |
| 510,0.9938,5.078132152557373 | |
| 520,1.0042,6.263752460479736 | |
| 530,0.8717,4.613877773284912 | |
| 540,0.9252,5.016404151916504 | |
| 550,0.9297,4.927691459655762 | |
| 560,0.8883,4.506190299987793 | |
| 570,0.8302,5.3836350440979 | |
| 580,0.8401,4.673761367797852 | |
| 590,0.888,3.7030556201934814 | |
| 600,0.8483,4.952301025390625 | |
| 610,0.7925,4.4545769691467285 | |
| 620,0.7347,4.0674896240234375 | |
| 630,0.7413,6.8568034172058105 | |
| 640,0.7714,6.715765476226807 | |
| 650,0.7337,4.419723033905029 | |
| 660,0.6854,4.291261672973633 | |
| 670,0.7224,5.974247932434082 | |
| 680,0.6737,4.334232807159424 | |
| 690,0.6505,4.699735164642334 | |
| 700,0.6696,4.12949275970459 | |
| 710,0.6587,3.9896364212036133 | |
| 720,0.6189,4.438923358917236 | |
| 730,0.6249,3.4031989574432373 | |
| 740,0.6462,5.202292442321777 | |
| 750,0.5842,5.27857780456543 | |
| 760,0.5659,4.678514003753662 | |
| 770,0.5833,4.691657543182373 | |
| 780,0.5958,7.131917476654053 | |
| 790,0.6307,5.070577144622803 | |
| 800,0.6064,4.827574253082275 | |
| 810,0.5218,3.8818304538726807 | |
| 820,0.5342,6.581722736358643 | |
| 830,0.5167,9.561187744140625 | |
| 840,0.5674,6.698048114776611 | |
| 850,0.5432,5.142230987548828 | |
| 860,0.557,5.226676940917969 | |
| 870,0.4969,5.462721824645996 | |
| 880,0.5004,4.489198207855225 | |
| 890,0.4465,4.706643104553223 | |
| 900,0.4989,7.614391803741455 | |
| 910,0.4978,3.3230834007263184 | |
| 920,0.4477,4.60692834854126 | |
| 930,0.4573,4.93078088760376 | |
| 940,0.4262,3.973932981491089 | |
| 950,0.4804,3.4613964557647705 | |
| 960,0.4037,3.4361777305603027 | |
| 970,0.4436,3.738327980041504 | |
| 980,0.4489,5.539529323577881 | |
| 990,0.4346,3.828397512435913 | |
| 1000,0.4615,4.032661437988281 | |
| 1010,0.4137,3.523750066757202 | |
| 1020,0.4397,5.352044582366943 | |
| 1030,0.4411,3.491257667541504 | |
| 1040,0.3997,2.7892098426818848 | |
| 1050,0.4118,3.231407880783081 | |
| 1060,0.3631,4.61359977722168 | |
| 1070,0.399,7.804078578948975 | |
| 1080,0.4628,5.450227737426758 | |
| 1090,0.4149,4.55374002456665 | |
| 1100,0.3892,2.5150911808013916 | |
| 1110,0.3874,3.4889912605285645 | |
| 1120,0.4126,4.045688629150391 | |
| 1130,0.3564,5.061463356018066 | |
| 1140,0.4036,3.681854248046875 | |
| 1150,0.4049,4.347032070159912 | |
| 1160,0.3708,7.9803314208984375 | |
| 1170,0.376,5.374613285064697 | |
| 1180,0.371,3.0691614151000977 | |
| 1190,0.3681,4.836121082305908 | |
| 1200,0.3379,3.778252124786377 | |
| 1210,0.3627,3.3291821479797363 | |
| 1220,0.3423,3.522620916366577 | |
| 1230,0.3301,3.283186912536621 | |
| 1240,0.3468,4.433807849884033 | |
| 1250,0.3376,3.97624135017395 | |
| 1260,0.3032,3.079582929611206 | |
| 1270,0.3452,4.162789821624756 | |
| 1280,0.3351,4.1800665855407715 | |
| 1290,0.3579,4.206212520599365 | |
| 1300,0.3328,3.900646924972534 | |
| 1310,0.345,5.285961627960205 | |
| 1320,0.321,2.616771697998047 | |
| 1330,0.3188,3.762444496154785 | |
| 1340,0.3299,3.244722366333008 | |
| 1350,0.3063,3.7463319301605225 | |
| 1360,0.3218,2.2992026805877686 | |
| 1370,0.3295,3.3672423362731934 | |
| 1380,0.282,3.5933585166931152 | |
| 1390,0.3113,5.269179821014404 | |
| 1400,0.2977,2.99794340133667 | |
| 1410,0.2954,3.103388547897339 | |
| 1420,0.2779,2.7087464332580566 | |
| 1430,0.3277,4.316291809082031 | |
| 1440,0.2738,3.2305455207824707 | |
| 1450,0.2764,2.637054443359375 | |
| 1460,0.2624,2.727341890335083 | |
| 1470,0.2889,3.334686756134033 | |
| 1480,0.3006,2.98366641998291 | |
| 1490,0.2628,3.3115627765655518 | |
| 1500,0.2607,4.2003583908081055 | |
| 1510,0.2869,6.368921756744385 | |
| 1520,0.2757,6.977168083190918 | |
| 1530,0.2545,2.90818452835083 | |
| 1540,0.2632,3.735295534133911 | |
| 1550,0.2347,3.361546039581299 | |
| 1560,0.2601,4.228140830993652 | |
| 1570,0.2604,4.071884632110596 | |
| 1580,0.2353,2.7090647220611572 | |
| 1590,0.2311,5.145593166351318 | |
| 1600,0.2466,3.904247522354126 | |
| 1610,0.267,1.8991984128952026 | |
| 1620,0.2648,3.3171005249023438 | |
| 1630,0.2293,2.8795769214630127 | |
| 1640,0.2243,3.4193594455718994 | |
| 1650,0.2339,3.470912218093872 | |
| 1660,0.2346,4.2241926193237305 | |
| 1670,0.2162,2.4578678607940674 | |
| 1680,0.2254,2.8263041973114014 | |
| 1690,0.2099,2.4483835697174072 | |
| 1700,0.2054,3.059027671813965 | |
| 1710,0.1919,2.2340033054351807 | |
| 1720,0.202,3.059826374053955 | |
| 1730,0.2025,2.4581353664398193 | |
| 1740,0.2119,3.7301676273345947 | |
| 1750,0.2102,2.9101502895355225 | |
| 1760,0.1975,1.4716150760650635 | |
| 1770,0.1818,1.810396432876587 | |
| 1780,0.205,2.5587878227233887 | |
| 1790,0.2066,2.6180355548858643 | |
| 1800,0.1986,3.3715500831604004 | |
| 1810,0.18,1.9417994022369385 | |
| 1820,0.1848,2.6988582611083984 | |
| 1830,0.2074,2.6839194297790527 | |
| 1840,0.1929,2.4248201847076416 | |
| 1850,0.1761,2.474905252456665 | |
| 1860,0.1693,1.7574677467346191 | |
| 1870,0.1683,2.314537286758423 | |
| 1880,0.2025,2.127652406692505 | |
| 1890,0.1697,3.3728537559509277 | |
| 1900,0.1669,1.9143751859664917 | |
| 1910,0.1695,2.564091205596924 | |
| 1920,0.1836,3.54518985748291 | |
| 1930,0.1701,1.8193870782852173 | |
| 1940,0.1572,3.027362585067749 | |
| 1950,0.164,2.244178295135498 | |
| 1960,0.1667,3.8362321853637695 | |
| 1970,0.1642,3.5789124965667725 | |
| 1980,0.1615,3.8518402576446533 | |
| 1990,0.1591,2.248826265335083 | |
| 2000,0.1679,2.504639148712158 | |
| 2010,0.1887,2.4511938095092773 | |
| 2020,0.1584,2.2310004234313965 | |
| 2030,0.1493,2.4412670135498047 | |
| 2040,0.1636,2.1844723224639893 | |
| 2050,0.1602,2.738367795944214 | |
| 2060,0.159,2.138552188873291 | |
| 2070,0.1428,1.3966834545135498 | |
| 2080,0.1542,2.3553030490875244 | |
| 2090,0.1433,2.553690195083618 | |
| 2100,0.139,2.555643081665039 | |
| 2110,0.1688,2.7808148860931396 | |
| 2120,0.1508,3.2580206394195557 | |
| 2130,0.1613,4.284587860107422 | |
| 2140,0.1562,1.9140340089797974 | |
| 2150,0.1465,2.13785719871521 | |
| 2160,0.1254,2.165259599685669 | |
| 2170,0.1436,2.14497971534729 | |
| 2180,0.154,2.4378933906555176 | |
| 2190,0.1485,2.225801467895508 | |
| 2200,0.1312,1.9187358617782593 | |
| 2210,0.1574,2.536228895187378 | |
| 2220,0.133,1.6395888328552246 | |
| 2230,0.139,1.9579951763153076 | |
| 2240,0.1312,2.6751959323883057 | |
| 2250,0.1324,2.2726802825927734 | |
| 2260,0.1271,1.9153738021850586 | |
| 2270,0.1268,1.5008968114852905 | |
| 2280,0.1108,1.671263575553894 | |
| 2290,0.1251,2.4821507930755615 | |
| 2300,0.1224,1.8863062858581543 | |
| 2310,0.1206,2.204700469970703 | |
| 2320,0.1379,3.5700721740722656 | |
| 2330,0.1289,1.4034169912338257 | |
| 2340,0.1374,2.7189619541168213 | |
| 2350,0.1306,1.9794065952301025 | |
| 2360,0.1279,1.698568344116211 | |
| 2370,0.1354,1.7154345512390137 | |
| 2380,0.1308,1.5892575979232788 | |
| 2390,0.1239,1.742138147354126 | |
| 2400,0.1235,2.4784200191497803 | |
| 2410,0.1193,1.3302199840545654 | |
| 2420,0.1252,2.079979658126831 | |
| 2430,0.118,2.201711893081665 | |
| 2440,0.1116,1.476678729057312 | |
| 2450,0.1116,1.3897534608840942 | |
| 2460,0.121,2.085052728652954 | |
| 2470,0.1242,1.4823940992355347 | |
| 2480,0.1182,1.9251364469528198 | |
| 2490,0.1127,1.792622447013855 | |
| 2500,0.1137,2.0481772422790527 | |
| 2510,0.1162,2.2373077869415283 | |
| 2520,0.1102,1.4368358850479126 | |
| 2530,0.119,1.7859045267105103 | |
| 2540,0.1168,2.55025315284729 | |
| 2550,0.1203,1.7251120805740356 | |
| 2560,0.1091,1.499519944190979 | |
| 2570,0.1238,2.4695260524749756 | |
| 2580,0.1113,1.6461279392242432 | |
| 2590,0.1153,2.1009840965270996 | |
| 2600,0.1248,1.6194204092025757 | |
| 2610,0.1126,1.8107424974441528 | |
| 2620,0.1119,1.6274248361587524 | |
| 2630,0.1121,1.5619142055511475 | |
| 2640,0.1246,2.297623634338379 | |
| 2650,0.103,1.5185441970825195 | |
| 2660,0.1173,1.9803398847579956 | |
| 2670,0.1166,2.065286874771118 | |
| 2680,0.1036,1.6951541900634766 | |
| 2690,0.1086,1.2760865688323975 | |
| 2700,0.1063,2.6494252681732178 | |
| 2710,0.1159,1.4181417226791382 | |
| 2720,0.1098,1.8402090072631836 | |
| 2730,0.1126,2.2500264644622803 | |
| 2740,0.106,1.485680103302002 | |
| 2750,0.1099,1.3506594896316528 | |
| 2760,0.2101,1.615838885307312 | |
| 2770,0.1022,1.8304481506347656 | |
| 2780,0.102,1.7675200700759888 | |
| 2790,0.1078,1.363110899925232 | |
| 2800,0.1099,3.771144151687622 | |
| 2810,0.1128,1.606154203414917 | |
| 2820,0.0987,1.24965238571167 | |
| 2830,0.1114,1.2326825857162476 | |
| 2840,0.1114,1.5760172605514526 | |
| 2850,0.1108,2.7495434284210205 | |
| 2860,0.1015,1.2853425741195679 | |
| 2870,0.0976,1.6944804191589355 | |
| 2880,0.1088,1.2788165807724 | |
| 2890,0.1057,1.9614472389221191 | |
| 2900,0.116,1.3156172037124634 | |
| 2910,0.1127,2.4010279178619385 | |
| 2920,0.1061,2.3485734462738037 | |
| 2930,0.1048,2.0748932361602783 | |
| 2940,0.1039,1.0390431880950928 | |
| 2950,0.1021,1.1470861434936523 | |
| 2960,0.1025,1.8556820154190063 | |
| 2970,0.1126,1.5888488292694092 | |
| 2980,0.1084,1.8423320055007935 | |
| 2990,0.1029,1.38668954372406 | |
| 3000,0.1082,2.0503017902374268 | |
| 3010,0.0986,1.526978850364685 | |
| 3020,0.1093,2.662074089050293 | |
| 3030,0.0976,1.9316941499710083 | |
| 3040,0.1076,2.845834732055664 | |
| 3050,0.1015,2.393538475036621 | |
| 3060,0.1197,2.8218283653259277 | |
| 3070,0.0988,1.0874052047729492 | |
| 3080,0.1024,1.1840276718139648 | |
| 3090,0.106,1.8606740236282349 | |
| 3100,0.1041,1.9203367233276367 | |
| 3110,0.114,1.15613853931427 | |
| 3120,0.1012,2.514665365219116 | |
| 3125,nan,nan | |