Upload results/results_rteb_fast.csv with huggingface_hub
Browse files
results/results_rteb_fast.csv
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
run,checkpoint,AILACasedocs,AILAStatutes,LegalSummarization,FinanceBench,HC3Finance,FinQA,APPS,DS1000,HumanEval,MBPP,WikiSQL,ChatDoctor_HealthCareMagic,CUREv1_en,MEAN
|
| 2 |
+
moe_e8k2_untrained,ckpts/moe_e8k2_alt (untrained),0.0856,0.0581,0.1524,0.0530,0.0341,0.0392,0.0004,0.0540,0.1430,0.0253,0.0014,0.0300,0.0192,0.0535
|
| 3 |
+
anchor_nomic_mbe,nomic-ai/modernbert-embed-base,0.1408,0.1393,0.6198,0.6525,0.4483,0.4347,0.0396,0.3369,0.6999,0.7738,0.7705,0.5443,0.5652,0.4743
|
| 4 |
+
e8k2_s0,runs/e8k2_s0/final,0.0694,0.0508,0.1827,0.1402,0.0886,0.0378,0.0013,0.1257,0.1597,0.1205,0.0157,0.0361,0.1426,0.0901
|
| 5 |
+
e8k2_s1,runs/e8k2_s1/final,0.0872,0.0784,0.1514,0.1488,0.0712,0.0279,0.0020,0.1489,0.1422,0.0624,0.0102,0.0419,0.1901,0.0894
|
| 6 |
+
e8k2_s2,runs/e8k2_s2/final,0.0742,0.0628,0.2025,0.1345,0.0882,0.0311,0.0017,0.1259,0.1216,0.0613,0.0103,0.0378,0.1386,0.0839
|
| 7 |
+
e8k2_s3,runs/e8k2_s3/final,0.0591,0.0783,0.1459,0.1374,0.0795,0.0356,0.0014,0.1148,0.1431,0.0778,0.0316,0.0177,0.1480,0.0823
|
| 8 |
+
e8k2_lb0_s0,runs/e8k2_lb0_s0/final,0.0981,0.0605,0.1702,0.1757,0.0951,0.0549,0.0030,0.1639,0.2408,0.1926,0.0234,0.0601,0.2155,0.1195
|
| 9 |
+
e8k2_lb0_s1,runs/e8k2_lb0_s1/final,0.0726,0.0735,0.0785,0.1041,0.0542,0.0180,0.0033,0.0855,0.1604,0.0557,0.0163,0.0163,0.1774,0.0704
|
| 10 |
+
e8k2_lb0_s2,runs/e8k2_lb0_s2/final,0.0730,0.0373,0.1794,0.1461,0.0747,0.0151,0.0028,0.0939,0.1733,0.0632,0.0294,0.0271,0.2324,0.0883
|
| 11 |
+
e8k2_lb0_s3,runs/e8k2_lb0_s3/final,0.1092,0.0677,0.1783,0.1722,0.1051,0.0353,0.0015,0.1308,0.1383,0.1258,0.0128,0.0396,0.1609,0.0983
|
| 12 |
+
e8k2_lb1e-3_s0,runs/e8k2_lb1e-3_s0/final,0.0519,0.0667,0.1234,0.1098,0.0448,0.0340,0.0015,0.1142,0.1218,0.0561,0.0114,0.0163,0.1749,0.0713
|
| 13 |
+
e8k2_lb1e-3_s1,runs/e8k2_lb1e-3_s1/final,0.0697,0.0464,0.1476,0.1374,0.0710,0.0324,0.0012,0.1080,0.1408,0.0516,0.0207,0.0197,0.1569,0.0772
|
| 14 |
+
e8k2_lb1e-3_s2,runs/e8k2_lb1e-3_s2/final,0.1119,0.0577,0.1201,0.1055,0.0689,0.0362,0.0017,0.1042,0.0966,0.0272,0.0174,0.0238,0.1393,0.0700
|
| 15 |
+
e8k2_lb1e-3_s3,runs/e8k2_lb1e-3_s3/final,0.0997,0.0690,0.1485,0.1001,0.0418,0.0279,0.0025,0.1389,0.2459,0.2265,0.0538,0.0258,0.1951,0.1058
|
| 16 |
+
e8k2_lb1e-1_s0,runs/e8k2_lb1e-1_s0/final,0.0625,0.0614,0.2234,0.1462,0.0834,0.0452,0.0027,0.1129,0.1770,0.0736,0.0179,0.0310,0.1566,0.0918
|
| 17 |
+
e8k2_lb1e-1_s1,runs/e8k2_lb1e-1_s1/final,0.0539,0.0588,0.1965,0.1369,0.0586,0.0320,0.0011,0.1189,0.1057,0.0732,0.0105,0.0256,0.1565,0.0791
|
| 18 |
+
e8k2_lb1e-1_s2,runs/e8k2_lb1e-1_s2/final,0.0692,0.0430,0.1333,0.1008,0.0764,0.0198,0.0015,0.1338,0.1581,0.0796,0.0143,0.0434,0.1946,0.0821
|
| 19 |
+
e8k2_lb1e-1_s3,runs/e8k2_lb1e-1_s3/final,0.0755,0.0349,0.1500,0.1519,0.0917,0.0240,0.0020,0.1382,0.2101,0.0968,0.0077,0.0323,0.1467,0.0894
|
| 20 |
+
e8k2_lb1_s0,runs/e8k2_lb1_s0/final,0.0697,0.0586,0.2540,0.1516,0.0971,0.0536,0.0012,0.1380,0.1394,0.1004,0.0239,0.0457,0.2069,0.1031
|
| 21 |
+
e8k2_lb1_s1,runs/e8k2_lb1_s1/final,0.0910,0.0736,0.1865,0.1633,0.0854,0.0268,0.0019,0.1289,0.1721,0.0903,0.0106,0.0267,0.1657,0.0941
|
| 22 |
+
e8k2_lb1_s2,runs/e8k2_lb1_s2/final,0.0496,0.0795,0.0752,0.1259,0.0623,0.0163,0.0036,0.1339,0.1429,0.0914,0.0230,0.0303,0.2021,0.0797
|
| 23 |
+
e8k2_lb1_s3,runs/e8k2_lb1_s3/final,0.0668,0.0626,0.1335,0.1285,0.0816,0.0264,0.0031,0.1489,0.1754,0.1275,0.0212,0.0297,0.1442,0.0884
|
| 24 |
+
dense_s0,runs/dense_s0/final,0.0330,0.0769,0.1468,0.1211,0.0508,0.0449,0.0017,0.1418,0.1643,0.1355,0.0258,0.0238,0.1913,0.0891
|
| 25 |
+
dense_s1,runs/dense_s1/final,0.0388,0.0578,0.2686,0.1626,0.0922,0.0326,0.0030,0.1394,0.1938,0.0844,0.0074,0.0441,0.1519,0.0982
|
| 26 |
+
dense_s2,runs/dense_s2/final,0.0490,0.0711,0.1362,0.1141,0.0717,0.0157,0.0010,0.0616,0.1350,0.0721,0.0116,0.0227,0.1919,0.0734
|
| 27 |
+
dense_s3,runs/dense_s3/final,0.0880,0.0817,0.1827,0.1275,0.0587,0.0173,0.0031,0.1486,0.1686,0.0931,0.0113,0.0264,0.1287,0.0874
|
| 28 |
+
e8k2_rrand_s0,runs/e8k2_rrand_s0/final,0.0588,0.0894,0.1973,0.1731,0.1057,0.0572,0.0017,0.1065,0.1581,0.0684,0.0153,0.0307,0.1772,0.0953
|
| 29 |
+
e8k2_rrand_s1,runs/e8k2_rrand_s1/final,0.0501,0.0830,0.1765,0.1570,0.0940,0.0706,0.0012,0.0828,0.1694,0.0869,0.0092,0.0195,0.1428,0.0879
|
| 30 |
+
e8k2_rrand_s2,runs/e8k2_rrand_s2/final,0.0775,0.0802,0.1809,0.1582,0.0878,0.0250,0.0016,0.1508,0.1599,0.1343,0.0119,0.0237,0.1653,0.0967
|
| 31 |
+
e8k2_rrand_s3,runs/e8k2_rrand_s3/final,0.0510,0.0623,0.1914,0.1713,0.0956,0.0436,0.0027,0.1587,0.1541,0.0574,0.0118,0.0318,0.1640,0.0920
|
| 32 |
+
e8k2_shuf_s0,runs/e8k2_shuf_s0/final,0.1056,0.0829,0.1482,0.1485,0.0966,0.0387,0.0033,0.1176,0.1698,0.0746,0.0123,0.0303,0.1835,0.0932
|
| 33 |
+
e8k2_shuf_s1,runs/e8k2_shuf_s1/final,0.1064,0.0762,0.1118,0.1080,0.0422,0.0171,0.0011,0.1113,0.1599,0.1154,0.0091,0.0147,0.1331,0.0774
|
| 34 |
+
e8k2_shuf_s2,runs/e8k2_shuf_s2/final,0.0303,0.0579,0.1791,0.1477,0.0678,0.0258,0.0029,0.1388,0.1529,0.0820,0.0157,0.0275,0.1754,0.0849
|
| 35 |
+
e8k2_shuf_s3,runs/e8k2_shuf_s3/final,0.0878,0.0811,0.1761,0.1581,0.0814,0.0376,0.0020,0.1432,0.1348,0.1039,0.0142,0.0288,0.2014,0.0962
|
| 36 |
+
e8k2_drop5_s0,runs/e8k2_drop5_s0/final,0.0946,0.0368,0.0793,0.1378,0.0707,0.0392,0.0012,0.0861,0.1125,0.0693,0.0257,0.0298,0.1968,0.0754
|
| 37 |
+
e8k2_drop5_s1,runs/e8k2_drop5_s1/final,0.0518,0.0623,0.0873,0.1286,0.0568,0.0258,0.0017,0.0989,0.0960,0.0273,0.0344,0.0294,0.1976,0.0691
|
| 38 |
+
e8k2_drop5_s2,runs/e8k2_drop5_s2/final,0.0548,0.0633,0.0841,0.1397,0.0604,0.0552,0.0023,0.0818,0.1151,0.0661,0.0135,0.0272,0.1415,0.0696
|
| 39 |
+
e8k2_drop5_s3,runs/e8k2_drop5_s3/final,0.0836,0.0823,0.1306,0.1525,0.0749,0.0553,0.0028,0.1187,0.1014,0.0505,0.0413,0.0684,0.2011,0.0895
|
| 40 |
+
dense_untrained_flagship,answerdotai/ModernBERT-base (untrained dense),0.0797,0.0573,0.1535,0.0527,0.0360,0.0387,0.0004,0.0528,0.1498,0.0257,0.0014,0.0296,0.0191,0.0536
|
| 41 |
+
flagship_moe_step2000,runs/pretrain_flagship_h100_4x8/step2000,0.0887,0.2619,0.4868,0.4174,0.4692,0.2721,0.0237,0.2920,0.5250,0.6299,0.6101,0.4316,0.3699,0.3753
|
| 42 |
+
flagship_moe_final_step40589,runs/pretrain_flagship_h100_4x8/final,0.1507,0.1493,0.4092,0.5556,0.6046,0.2410,0.0345,0.2708,0.7247,0.7704,0.4769,0.5371,0.4062,0.4101
|