Upload 2 files
Browse files- eval_results.log +96 -0
- mcse.pt +3 -0
eval_results.log
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2021-10-09 12:51:14,515 : ***** Transfer task : STS12 *****
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
2021-10-09 12:51:17,767 : MSRpar : pearson = 0.6532, spearman = 0.6454, align_loss = 0.1535, uniform_loss = -2.0307
|
| 5 |
+
2021-10-09 12:51:18,984 : MSRvid : pearson = 0.8689, spearman = 0.8689, align_loss = 0.2007, uniform_loss = -1.8306
|
| 6 |
+
2021-10-09 12:51:20,049 : SMTeuroparl : pearson = 0.5416, spearman = 0.5946, align_loss = 0.2092, uniform_loss = -1.4600
|
| 7 |
+
2021-10-09 12:51:21,965 : surprise.OnWN : pearson = 0.7591, spearman = 0.7194, align_loss = 0.2337, uniform_loss = -2.0349
|
| 8 |
+
2021-10-09 12:51:22,994 : surprise.SMTnews : pearson = 0.7206, spearman = 0.6276, align_loss = 0.1864, uniform_loss = -1.4955
|
| 9 |
+
2021-10-09 12:51:22,997 : ALL : Pearson = 0.7804, Spearman = 0.7079, align_loss = 0.1965, uniform_loss = -1.8154
|
| 10 |
+
2021-10-09 12:51:22,997 : ALL (weighted average) : Pearson = 0.7230, Spearman = 0.7074, align_loss = 0.1967, uniform_loss = -1.8304
|
| 11 |
+
2021-10-09 12:51:22,997 : ALL (average) : Pearson = 0.7087, Spearman = 0.6912, align_loss = 0.1967, uniform_loss = -1.7703
|
| 12 |
+
|
| 13 |
+
2021-10-09 12:51:23,000 : ***** Transfer task : STS13 (-SMT) *****
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
2021-10-09 12:51:23,971 : FNWN : pearson = 0.6360, spearman = 0.6639, align_loss = 0.3311, uniform_loss = -1.8316
|
| 17 |
+
2021-10-09 12:51:25,584 : headlines : pearson = 0.8088, spearman = 0.8115, align_loss = 0.1909, uniform_loss = -1.9906
|
| 18 |
+
2021-10-09 12:51:26,659 : OnWN : pearson = 0.8599, spearman = 0.8422, align_loss = 0.2473, uniform_loss = -1.8941
|
| 19 |
+
2021-10-09 12:51:26,661 : ALL : Pearson = 0.8231, Spearman = 0.8281, align_loss = 0.2342, uniform_loss = -1.9290
|
| 20 |
+
2021-10-09 12:51:26,661 : ALL (weighted average) : Pearson = 0.8062, Spearman = 0.8044, align_loss = 0.2297, uniform_loss = -1.9344
|
| 21 |
+
2021-10-09 12:51:26,661 : ALL (average) : Pearson = 0.7683, Spearman = 0.7726, align_loss = 0.2564, uniform_loss = -1.9054
|
| 22 |
+
|
| 23 |
+
2021-10-09 12:51:26,662 : ***** Transfer task : STS14 *****
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
2021-10-09 12:51:27,841 : deft-forum : pearson = 0.5746, spearman = 0.5652, align_loss = 0.2150, uniform_loss = -1.9485
|
| 27 |
+
2021-10-09 12:51:29,101 : deft-news : pearson = 0.8208, spearman = 0.7740, align_loss = 0.1514, uniform_loss = -1.8488
|
| 28 |
+
2021-10-09 12:51:30,803 : headlines : pearson = 0.7927, spearman = 0.7746, align_loss = 0.1893, uniform_loss = -2.0195
|
| 29 |
+
2021-10-09 12:51:32,323 : images : pearson = 0.8899, spearman = 0.8514, align_loss = 0.2120, uniform_loss = -2.0607
|
| 30 |
+
2021-10-09 12:51:33,885 : OnWN : pearson = 0.8645, spearman = 0.8547, align_loss = 0.2589, uniform_loss = -1.9353
|
| 31 |
+
2021-10-09 12:51:36,001 : tweet-news : pearson = 0.7930, spearman = 0.7280, align_loss = 0.2927, uniform_loss = -1.9504
|
| 32 |
+
2021-10-09 12:51:36,005 : ALL : Pearson = 0.8028, Spearman = 0.7616, align_loss = 0.2268, uniform_loss = -1.9721
|
| 33 |
+
2021-10-09 12:51:36,005 : ALL (weighted average) : Pearson = 0.8026, Spearman = 0.7715, align_loss = 0.2285, uniform_loss = -1.9749
|
| 34 |
+
2021-10-09 12:51:36,005 : ALL (average) : Pearson = 0.7893, Spearman = 0.7580, align_loss = 0.2199, uniform_loss = -1.9605
|
| 35 |
+
|
| 36 |
+
2021-10-09 12:51:36,008 : ***** Transfer task : STS15 *****
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
2021-10-09 12:51:37,508 : answers-forums : pearson = 0.7354, spearman = 0.7407, align_loss = 0.4058, uniform_loss = -2.0225
|
| 40 |
+
2021-10-09 12:51:39,060 : answers-students : pearson = 0.7466, spearman = 0.7530, align_loss = 0.2678, uniform_loss = -1.4429
|
| 41 |
+
2021-10-09 12:51:40,625 : belief : pearson = 0.8251, spearman = 0.8323, align_loss = 0.2794, uniform_loss = -1.9058
|
| 42 |
+
2021-10-09 12:51:42,490 : headlines : pearson = 0.8350, spearman = 0.8412, align_loss = 0.1893, uniform_loss = -2.0135
|
| 43 |
+
2021-10-09 12:51:44,133 : images : pearson = 0.8972, spearman = 0.9090, align_loss = 0.1812, uniform_loss = -1.8359
|
| 44 |
+
2021-10-09 12:51:44,137 : ALL : Pearson = 0.8239, Spearman = 0.8313, align_loss = 0.2452, uniform_loss = -1.8141
|
| 45 |
+
2021-10-09 12:51:44,138 : ALL (weighted average) : Pearson = 0.8147, Spearman = 0.8224, align_loss = 0.2452, uniform_loss = -1.8141
|
| 46 |
+
2021-10-09 12:51:44,138 : ALL (average) : Pearson = 0.8078, Spearman = 0.8152, align_loss = 0.2647, uniform_loss = -1.8441
|
| 47 |
+
|
| 48 |
+
2021-10-09 12:51:44,141 : ***** Transfer task : STS16 *****
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
2021-10-09 12:51:44,870 : answer-answer : pearson = 0.7683, spearman = 0.7647, align_loss = 0.2618, uniform_loss = -1.6292
|
| 52 |
+
2021-10-09 12:51:45,422 : headlines : pearson = 0.8241, spearman = 0.8471, align_loss = 0.1570, uniform_loss = -2.0297
|
| 53 |
+
2021-10-09 12:51:46,104 : plagiarism : pearson = 0.8587, spearman = 0.8670, align_loss = 0.1583, uniform_loss = -1.6840
|
| 54 |
+
2021-10-09 12:51:47,451 : postediting : pearson = 0.8617, spearman = 0.8771, align_loss = 0.1205, uniform_loss = -1.8880
|
| 55 |
+
2021-10-09 12:51:48,001 : question-question : pearson = 0.7415, spearman = 0.7430, align_loss = 0.2224, uniform_loss = -1.9116
|
| 56 |
+
2021-10-09 12:51:48,003 : ALL : Pearson = 0.8069, Spearman = 0.8176, align_loss = 0.1840, uniform_loss = -1.8285
|
| 57 |
+
2021-10-09 12:51:48,003 : ALL (weighted average) : Pearson = 0.8120, Spearman = 0.8211, align_loss = 0.1837, uniform_loss = -1.8269
|
| 58 |
+
2021-10-09 12:51:48,003 : ALL (average) : Pearson = 0.8108, Spearman = 0.8198, align_loss = 0.1840, uniform_loss = -1.8285
|
| 59 |
+
|
| 60 |
+
2021-10-09 12:51:48,004 :
|
| 61 |
+
|
| 62 |
+
***** Transfer task : STSBenchmark*****
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
2021-10-09 12:52:07,123 : train : pearson = 0.8266, spearman = 0.8037, align_loss = 0.1921, uniform_loss = -1.9833
|
| 66 |
+
2021-10-09 12:52:12,465 : dev : pearson = 0.8510, spearman = 0.8524, align_loss = 0.2155, uniform_loss = -1.9961
|
| 67 |
+
2021-10-09 12:52:17,090 : test : pearson = 0.8202, spearman = 0.8172, align_loss = 0.1894, uniform_loss = -1.9345
|
| 68 |
+
2021-10-09 12:52:17,096 : ALL : Pearson = 0.8307, Spearman = 0.8176, align_loss = 0.1958, uniform_loss = -1.9776
|
| 69 |
+
2021-10-09 12:52:17,096 : ALL (weighted average) : Pearson = 0.8298, Spearman = 0.8143, align_loss = 0.1957, uniform_loss = -1.9777
|
| 70 |
+
2021-10-09 12:52:17,096 : ALL (average) : Pearson = 0.8326, Spearman = 0.8244, align_loss = 0.1990, uniform_loss = -1.9713
|
| 71 |
+
|
| 72 |
+
2021-10-09 12:52:17,105 :
|
| 73 |
+
|
| 74 |
+
***** Transfer task : SICKRelatedness*****
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
2021-10-09 12:52:28,392 : train : pearson = 0.8009, spearman = 0.7122, align_loss = 0.1779, uniform_loss = -1.9437
|
| 78 |
+
2021-10-09 12:52:29,814 : dev : pearson = 0.8048, spearman = 0.7328, align_loss = 0.1817, uniform_loss = -2.0617
|
| 79 |
+
2021-10-09 12:52:42,160 : test : pearson = 0.7955, spearman = 0.7081, align_loss = 0.1763, uniform_loss = -1.9393
|
| 80 |
+
2021-10-09 12:52:42,167 : ALL : Pearson = 0.7984, Spearman = 0.7113, align_loss = 0.1773, uniform_loss = -1.9475
|
| 81 |
+
2021-10-09 12:52:42,167 : ALL (weighted average) : Pearson = 0.7984, Spearman = 0.7112, align_loss = 0.1773, uniform_loss = -1.9475
|
| 82 |
+
2021-10-09 12:52:42,167 : ALL (average) : Pearson = 0.8004, Spearman = 0.7177, align_loss = 0.1787, uniform_loss = -1.9816
|
| 83 |
+
|
| 84 |
+
2021-10-09 12:52:42,167 : ------ test ------
|
| 85 |
+
2021-10-09 12:52:42,168 : +--------+--------+--------+--------+--------+--------------+-----------------+--------+
|
| 86 |
+
| STS12 | STS13 | STS14 | STS15 | STS16 | STSBenchmark | SICKRelatedness | Avg. |
|
| 87 |
+
+--------+--------+--------+--------+--------+--------------+-----------------+--------+
|
| 88 |
+
| 70.79 | 82.81 | 76.16 | 83.13 | 81.76 | 81.72 | 70.81 | 78.17 |
|
| 89 |
+
| 0.197 | 0.234 | 0.227 | 0.245 | 0.184 | 0.189 | 0.176 | 0.207 |
|
| 90 |
+
| -1.815 | -1.929 | -1.972 | -1.814 | -1.828 | -1.935 | -1.939 | -1.890 |
|
| 91 |
+
+--------+--------+--------+--------+--------+--------------+-----------------+--------+
|
| 92 |
+
2021-10-09 12:52:42,170 : +------+------+------+------+------+------+------+------+
|
| 93 |
+
| MR | CR | SUBJ | MPQA | SST2 | TREC | MRPC | Avg. |
|
| 94 |
+
+------+------+------+------+------+------+------+------+
|
| 95 |
+
| 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
|
| 96 |
+
+------+------+------+------+------+------+------+------+
|
mcse.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38ea9b1e390623c0567e7abe6c763f6e6f1280ef55d4bac4f9f0bb2b203c7f0f
|
| 3 |
+
size 2887571
|