| step,training_loss,grad_norm | |
| 10,22.4391,0.9999999403953552 | |
| 20,18.5403,0.9999999403953552 | |
| 30,18.8727,0.9999999403953552 | |
| 40,17.9965,1.0 | |
| 50,15.0628,1.0 | |
| 60,14.3966,0.9999998807907104 | |
| 70,12.1963,1.0 | |
| 80,10.1156,0.9999998807907104 | |
| 90,8.9759,0.9999998211860657 | |
| 100,8.1186,0.9999998807907104 | |
| 110,6.1573,0.9999998211860657 | |
| 120,6.1534,0.9999998807907104 | |
| 130,5.1112,0.9999998807907104 | |
| 140,4.6452,0.9999999403953552 | |
| 150,4.4413,0.9999999403953552 | |
| 160,3.9959,0.9999999403953552 | |
| 170,3.6835,0.9999998211860657 | |
| 180,3.6577,0.9999998807907104 | |
| 190,3.5963,1.0 | |
| 200,3.0896,0.9999998807907104 | |
| 210,3.0582,0.9999998807907104 | |
| 220,2.8008,1.0 | |
| 230,2.9291,0.9999998211860657 | |
| 240,2.77,0.9999998211860657 | |
| 250,2.6318,0.9999999403953552 | |
| 260,2.5917,0.9999998807907104 | |
| 270,2.7395,0.9999998807907104 | |
| 280,2.4794,0.9999998807907104 | |
| 290,2.2085,0.9999999403953552 | |
| 300,2.6265,0.9999998807907104 | |
| 310,2.3575,0.9999998211860657 | |
| 320,2.2324,0.9999999403953552 | |
| 330,2.016,0.9999998807907104 | |
| 340,1.9396,0.9999998807907104 | |
| 350,2.0169,0.9999997615814209 | |
| 360,1.8053,0.9999998211860657 | |
| 370,1.78,0.9999999403953552 | |
| 380,1.8029,0.9999998211860657 | |
| 390,1.5602,0.9999999403953552 | |
| 400,1.5888,0.9999999403953552 | |
| 410,1.4702,0.9999997615814209 | |
| 420,1.3691,0.9999998211860657 | |
| 430,1.428,0.9999998211860657 | |
| 440,1.2926,0.9999998807907104 | |
| 450,1.2644,0.9999997615814209 | |
| 460,1.2895,0.9999998211860657 | |
| 470,1.1582,0.9999997019767761 | |
| 480,1.1133,0.9999997615814209 | |
| 490,1.0649,0.9999998211860657 | |
| 500,1.2008,0.9999998211860657 | |
| 510,1.0492,0.9999998211860657 | |
| 520,1.0742,0.9999998211860657 | |
| 530,0.9886,0.9999998211860657 | |
| 540,1.0551,0.9999998211860657 | |
| 550,1.0441,0.9999999403953552 | |
| 560,1.0036,0.9999998807907104 | |
| 570,1.0253,0.9999999403953552 | |
| 580,0.9892,0.9999998807907104 | |
| 590,0.9759,0.9999998211860657 | |
| 600,0.9612,0.9999998211860657 | |
| 610,0.8466,0.9999997019767761 | |
| 620,0.8808,0.9999997615814209 | |
| 630,0.8237,0.9999998211860657 | |
| 640,0.8928,0.9999998211860657 | |
| 650,0.8201,0.9999997615814209 | |
| 660,0.8201,0.9999998211860657 | |
| 670,0.8449,0.9999998211860657 | |
| 680,0.7961,0.9999998211860657 | |
| 690,0.7885,0.9999998807907104 | |
| 700,0.7426,0.9999997615814209 | |
| 710,0.7338,0.9999998807907104 | |
| 720,0.7224,0.9999997019767761 | |
| 730,0.7136,0.9999999403953552 | |
| 740,0.7625,0.9999997615814209 | |
| 750,0.6866,0.9999998807907104 | |
| 760,0.6498,0.9999998807907104 | |
| 770,0.6607,0.9999998211860657 | |
| 780,0.6734,0.9999997615814209 | |
| 790,0.7109,0.9999998211860657 | |
| 800,0.7259,0.9999998807907104 | |
| 810,0.632,0.9999998211860657 | |
| 820,0.6206,0.9999999403953552 | |
| 830,0.6071,0.9999997615814209 | |
| 840,0.6507,0.9999998807907104 | |
| 850,0.6243,0.9999998807907104 | |
| 860,0.6064,0.9999999403953552 | |
| 870,0.5709,0.9999998807907104 | |
| 880,0.5443,0.9999997615814209 | |
| 890,0.5449,0.9999999403953552 | |
| 900,0.5745,0.9999998211860657 | |
| 910,0.5592,0.9999998211860657 | |
| 920,0.5191,0.9999999403953552 | |
| 930,0.522,0.9999998807907104 | |
| 940,0.471,0.9999998211860657 | |
| 950,0.5226,0.9999997615814209 | |
| 960,0.4361,0.9999997615814209 | |
| 970,0.4848,0.9999997615814209 | |
| 980,0.4722,0.9999998807907104 | |
| 990,0.4307,0.9999998807907104 | |
| 1000,0.4638,0.9999997615814209 | |
| 1010,0.3979,0.9999998211860657 | |
| 1020,0.45,0.9999998211860657 | |
| 1030,0.4491,0.9999997019767761 | |
| 1040,0.3971,0.9999997019767761 | |
| 1050,0.4599,0.9999997019767761 | |
| 1060,0.4001,0.9999998211860657 | |
| 1070,0.4001,0.9999998211860657 | |
| 1080,0.444,0.9999998211860657 | |
| 1090,0.3911,0.9999997019767761 | |
| 1100,0.3774,0.9999995827674866 | |
| 1110,0.3516,0.9999997615814209 | |
| 1120,0.3805,0.9999997019767761 | |
| 1130,0.3262,0.9999996423721313 | |
| 1140,0.3327,0.9999997615814209 | |
| 1150,0.318,0.9999996423721313 | |
| 1160,0.3137,0.9999997615814209 | |
| 1170,0.3147,0.9999997615814209 | |
| 1180,0.2952,0.9999997615814209 | |
| 1190,0.3148,0.9999997615814209 | |
| 1200,0.256,0.9999996423721313 | |
| 1210,0.2966,0.9999997615814209 | |
| 1220,0.2835,0.9999996423721313 | |
| 1230,0.2818,0.9999997019767761 | |
| 1240,0.2967,0.9999996423721313 | |
| 1250,0.2521,0.9999998211860657 | |
| 1260,0.2363,0.9999995231628418 | |
| 1270,0.2581,0.9999997615814209 | |
| 1280,0.2437,0.9999997019767761 | |
| 1290,0.2641,0.9999997615814209 | |
| 1300,0.2355,0.9999995231628418 | |
| 1310,0.2339,0.999999463558197 | |
| 1320,0.2322,0.9999994039535522 | |
| 1330,0.2263,0.9999996423721313 | |
| 1340,0.2467,0.9999996423721313 | |
| 1350,0.2095,0.9999998211860657 | |
| 1360,0.2196,0.999999463558197 | |
| 1370,0.1847,0.9999996423721313 | |
| 1380,0.1807,0.9999995231628418 | |
| 1390,0.1792,0.9999995827674866 | |
| 1400,0.1762,0.9999996423721313 | |
| 1410,0.1929,0.9999996423721313 | |
| 1420,0.177,0.9999996423721313 | |
| 1430,0.1919,0.9999995231628418 | |
| 1440,0.1648,0.999999463558197 | |
| 1450,0.1644,0.9999993443489075 | |
| 1460,0.1454,0.999999463558197 | |
| 1470,0.1625,0.9999997019767761 | |
| 1480,0.175,0.9999994039535522 | |
| 1490,0.1486,0.999999463558197 | |
| 1500,0.1386,0.9999994039535522 | |
| 1510,0.1508,0.9999994039535522 | |
| 1520,0.1566,0.9999995827674866 | |
| 1530,0.1586,0.9999995827674866 | |
| 1540,0.1434,0.9999994039535522 | |
| 1550,0.1321,0.9999996423721313 | |
| 1560,0.1466,0.9999995827674866 | |
| 1570,0.1376,0.9999995231628418 | |
| 1580,0.1318,0.9999993443489075 | |
| 1590,0.135,0.9999995827674866 | |
| 1600,0.145,0.999999463558197 | |
| 1610,0.1536,0.9999995827674866 | |
| 1620,0.1459,0.9999995231628418 | |
| 1630,0.1162,0.9999992251396179 | |
| 1640,0.1148,0.999999463558197 | |
| 1650,0.1139,0.999999463558197 | |
| 1660,0.1074,0.9999997019767761 | |
| 1670,0.1301,0.9999991059303284 | |
| 1680,0.1177,0.9999991655349731 | |
| 1690,0.101,0.9999993443489075 | |
| 1700,0.1123,0.9999995827674866 | |
| 1710,0.1042,0.9999997615814209 | |
| 1720,0.1038,0.9999993443489075 | |
| 1730,0.1012,0.9999992251396179 | |
| 1740,0.11,0.9999995231628418 | |
| 1750,0.1091,0.9999992847442627 | |
| 1760,0.1026,0.9999992847442627 | |
| 1770,0.0942,0.9473298788070679 | |
| 1780,0.0907,0.9999991655349731 | |
| 1790,0.1042,0.999999463558197 | |
| 1800,0.1079,0.999999463558197 | |
| 1810,0.0929,0.9999993443489075 | |
| 1820,0.0969,0.9999991655349731 | |
| 1830,0.0983,0.9999992847442627 | |
| 1840,0.0948,0.9999992251396179 | |
| 1850,0.0902,0.9999992251396179 | |
| 1860,0.0817,0.999999463558197 | |
| 1870,0.0847,0.9999991655349731 | |
| 1880,0.0941,0.999999463558197 | |
| 1890,0.0831,0.9999993443489075 | |
| 1900,0.0841,0.9999992847442627 | |
| 1910,0.0901,0.9999994039535522 | |
| 1920,0.0853,0.9999997615814209 | |
| 1930,0.0829,0.9999991655349731 | |
| 1940,0.0759,0.9999993443489075 | |
| 1950,0.0768,0.9999991059303284 | |
| 1960,0.0789,0.9999992847442627 | |
| 1970,0.0807,0.9999993443489075 | |
| 1980,0.0829,0.999999463558197 | |
| 1990,0.0765,0.9999993443489075 | |
| 2000,0.0853,0.9999992251396179 | |
| 2010,0.0825,0.9999990463256836 | |
| 2020,0.0691,0.9999991059303284 | |
| 2030,0.0759,0.9999993443489075 | |
| 2040,0.0792,0.9881004095077515 | |
| 2050,0.0773,0.9999992251396179 | |
| 2060,0.0766,0.9999994039535522 | |
| 2070,0.0664,0.9999991655349731 | |
| 2080,0.0779,0.9999992251396179 | |
| 2090,0.0664,0.9999993443489075 | |
| 2100,0.0653,0.9999994039535522 | |
| 2110,0.0788,0.9999992251396179 | |
| 2120,0.0626,0.9999992847442627 | |
| 2130,0.0776,0.9999996423721313 | |
| 2140,0.068,0.9999991059303284 | |
| 2150,0.0638,0.9999992251396179 | |
| 2160,0.0636,0.999999463558197 | |
| 2170,0.0714,0.9999994039535522 | |
| 2180,0.0645,0.9999993443489075 | |
| 2190,0.0695,0.8402087688446045 | |
| 2200,0.0593,0.8664417862892151 | |
| 2210,0.0819,0.9999995827674866 | |
| 2220,0.0659,0.999999463558197 | |
| 2230,0.0649,0.9079611301422119 | |
| 2240,0.0678,0.9999992251396179 | |
| 2250,0.0588,0.9999992251396179 | |
| 2260,0.0577,0.9309330582618713 | |
| 2270,0.0613,0.7242733836174011 | |
| 2280,0.0501,0.8994721174240112 | |
| 2290,0.0563,0.999999463558197 | |
| 2300,0.062,0.9999991655349731 | |
| 2310,0.0547,0.9815754294395447 | |
| 2320,0.0609,0.9999991059303284 | |
| 2330,0.0558,0.633185088634491 | |
| 2340,0.0602,0.8977016806602478 | |
| 2350,0.0567,0.8778071999549866 | |
| 2360,0.0575,0.9999991655349731 | |
| 2370,0.0663,0.950730562210083 | |
| 2380,0.0615,0.9357079267501831 | |
| 2390,0.0561,0.8874356746673584 | |
| 2400,0.0553,0.9999992847442627 | |
| 2410,0.0561,0.8361284732818604 | |
| 2420,0.0513,0.9999991655349731 | |
| 2430,0.0556,0.9999992251396179 | |
| 2440,0.0535,0.9999992251396179 | |
| 2450,0.0503,0.9999990463256836 | |
| 2460,0.0574,0.9999991655349731 | |
| 2470,0.051,0.9563975930213928 | |
| 2480,0.0499,0.9999993443489075 | |
| 2490,0.0511,0.944343090057373 | |
| 2500,0.0511,0.9999991655349731 | |
| 2510,0.0539,0.9999994039535522 | |
| 2520,0.0526,0.9999991059303284 | |
| 2530,0.0525,0.9999991059303284 | |
| 2540,0.0491,0.9999990463256836 | |
| 2550,0.0544,0.9999993443489075 | |
| 2560,0.0497,0.9999992251396179 | |
| 2570,0.057,0.9999993443489075 | |
| 2580,0.0472,0.937023401260376 | |
| 2590,0.0528,0.8308994174003601 | |
| 2600,0.0551,0.9655416011810303 | |
| 2610,0.0475,0.8491576910018921 | |
| 2620,0.0467,0.7142296433448792 | |
| 2630,0.047,0.9999991655349731 | |
| 2640,0.0526,0.9999991655349731 | |
| 2650,0.0477,0.9757289886474609 | |
| 2660,0.0504,0.9999992847442627 | |
| 2670,0.0503,0.9999991655349731 | |
| 2680,0.0434,0.6634371280670166 | |
| 2690,0.0463,0.8291290402412415 | |
| 2700,0.0491,0.9999989867210388 | |
| 2710,0.0497,0.8437713980674744 | |
| 2720,0.046,0.9999992847442627 | |
| 2730,0.0473,0.9464171528816223 | |
| 2740,0.047,0.9209029078483582 | |
| 2750,0.0469,0.8307206034660339 | |
| 2760,0.0803,0.9999991655349731 | |
| 2770,0.0474,0.999999463558197 | |
| 2780,0.0448,0.9999992847442627 | |
| 2790,0.049,0.9999991059303284 | |
| 2800,0.0453,0.9999992251396179 | |
| 2810,0.0453,0.5893862843513489 | |
| 2820,0.0433,0.9848343729972839 | |
| 2830,0.0447,0.9999989867210388 | |
| 2840,0.0479,0.9301748275756836 | |
| 2850,0.0504,0.9999991059303284 | |
| 2860,0.0427,0.7579120993614197 | |
| 2870,0.0415,0.7811035513877869 | |
| 2880,0.0482,0.6998886466026306 | |
| 2890,0.0459,0.8271780014038086 | |
| 2900,0.0496,0.7415490746498108 | |
| 2910,0.0478,0.9999991655349731 | |
| 2920,0.0464,0.9999994039535522 | |
| 2930,0.0438,0.9900453686714172 | |
| 2940,0.0442,0.5051868557929993 | |
| 2950,0.0457,0.8847522735595703 | |
| 2960,0.0465,0.8838505744934082 | |
| 2970,0.0523,0.7302128672599792 | |
| 2980,0.0458,0.8874303698539734 | |
| 2990,0.0455,0.9999990463256836 | |
| 3000,0.0457,0.9999991655349731 | |
| 3010,0.0443,0.7528011798858643 | |
| 3020,0.0467,0.7724560499191284 | |
| 3030,0.0461,0.9128491282463074 | |
| 3040,0.0455,0.9999991655349731 | |
| 3050,0.0458,0.9999992847442627 | |
| 3060,0.0468,0.9999993443489075 | |
| 3070,0.0421,0.5832995772361755 | |
| 3080,0.0433,0.6920338273048401 | |
| 3090,0.0442,0.9999991059303284 | |
| 3100,0.0433,0.6920685172080994 | |
| 3110,0.0488,0.9999991059303284 | |
| 3120,0.0399,0.7507163286209106 | |
| 3125,nan,nan | |