Upload 2 files
Browse files- eval_results.log +96 -0
- mcse.pt +3 -0
eval_results.log
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2021-10-07 16:25:08,199 : ***** Transfer task : STS12 *****
|
2 |
+
|
3 |
+
|
4 |
+
2021-10-07 16:25:11,524 : MSRpar : pearson = 0.6385, spearman = 0.6277, align_loss = 0.1472, uniform_loss = -1.9531
|
5 |
+
2021-10-07 16:25:12,835 : MSRvid : pearson = 0.8927, spearman = 0.8893, align_loss = 0.1807, uniform_loss = -1.9198
|
6 |
+
2021-10-07 16:25:13,964 : SMTeuroparl : pearson = 0.5341, spearman = 0.5812, align_loss = 0.1966, uniform_loss = -1.3802
|
7 |
+
2021-10-07 16:25:15,951 : surprise.OnWN : pearson = 0.7567, spearman = 0.7188, align_loss = 0.2179, uniform_loss = -1.9324
|
8 |
+
2021-10-07 16:25:17,066 : surprise.SMTnews : pearson = 0.7105, spearman = 0.6142, align_loss = 0.1903, uniform_loss = -1.4507
|
9 |
+
2021-10-07 16:25:17,071 : ALL : Pearson = 0.8081, Spearman = 0.7174, align_loss = 0.1855, uniform_loss = -1.7752
|
10 |
+
2021-10-07 16:25:17,071 : ALL (weighted average) : Pearson = 0.7222, Spearman = 0.7042, align_loss = 0.1852, uniform_loss = -1.7910
|
11 |
+
2021-10-07 16:25:17,072 : ALL (average) : Pearson = 0.7065, Spearman = 0.6862, align_loss = 0.1865, uniform_loss = -1.7272
|
12 |
+
|
13 |
+
2021-10-07 16:25:17,077 : ***** Transfer task : STS13 (-SMT) *****
|
14 |
+
|
15 |
+
|
16 |
+
2021-10-07 16:25:18,125 : FNWN : pearson = 0.6377, spearman = 0.6645, align_loss = 0.2690, uniform_loss = -1.7120
|
17 |
+
2021-10-07 16:25:19,856 : headlines : pearson = 0.7919, spearman = 0.7916, align_loss = 0.1893, uniform_loss = -1.9193
|
18 |
+
2021-10-07 16:25:20,985 : OnWN : pearson = 0.8636, spearman = 0.8378, align_loss = 0.2356, uniform_loss = -1.8226
|
19 |
+
2021-10-07 16:25:20,988 : ALL : Pearson = 0.8223, Spearman = 0.8260, align_loss = 0.2194, uniform_loss = -1.8502
|
20 |
+
2021-10-07 16:25:20,988 : ALL (weighted average) : Pearson = 0.7993, Spearman = 0.7928, align_loss = 0.2167, uniform_loss = -1.8570
|
21 |
+
2021-10-07 16:25:20,988 : ALL (average) : Pearson = 0.7644, Spearman = 0.7646, align_loss = 0.2313, uniform_loss = -1.8180
|
22 |
+
|
23 |
+
2021-10-07 16:25:20,989 : ***** Transfer task : STS14 *****
|
24 |
+
|
25 |
+
|
26 |
+
2021-10-07 16:25:22,216 : deft-forum : pearson = 0.5599, spearman = 0.5425, align_loss = 0.2140, uniform_loss = -1.7958
|
27 |
+
2021-10-07 16:25:23,530 : deft-news : pearson = 0.7945, spearman = 0.7483, align_loss = 0.1556, uniform_loss = -1.8096
|
28 |
+
2021-10-07 16:25:25,363 : headlines : pearson = 0.7907, spearman = 0.7687, align_loss = 0.1759, uniform_loss = -1.9653
|
29 |
+
2021-10-07 16:25:26,984 : images : pearson = 0.8765, spearman = 0.8525, align_loss = 0.1784, uniform_loss = -2.0066
|
30 |
+
2021-10-07 16:25:28,642 : OnWN : pearson = 0.8735, spearman = 0.8602, align_loss = 0.2378, uniform_loss = -1.8534
|
31 |
+
2021-10-07 16:25:30,908 : tweet-news : pearson = 0.7726, spearman = 0.7054, align_loss = 0.2983, uniform_loss = -1.8457
|
32 |
+
2021-10-07 16:25:30,913 : ALL : Pearson = 0.7965, Spearman = 0.7567, align_loss = 0.2150, uniform_loss = -1.8916
|
33 |
+
2021-10-07 16:25:30,913 : ALL (weighted average) : Pearson = 0.7934, Spearman = 0.7623, align_loss = 0.2162, uniform_loss = -1.8945
|
34 |
+
2021-10-07 16:25:30,913 : ALL (average) : Pearson = 0.7779, Spearman = 0.7463, align_loss = 0.2100, uniform_loss = -1.8794
|
35 |
+
|
36 |
+
2021-10-07 16:25:30,918 : ***** Transfer task : STS15 *****
|
37 |
+
|
38 |
+
|
39 |
+
2021-10-07 16:25:32,577 : answers-forums : pearson = 0.7341, spearman = 0.7387, align_loss = 0.3866, uniform_loss = -1.9430
|
40 |
+
2021-10-07 16:25:34,257 : answers-students : pearson = 0.7654, spearman = 0.7759, align_loss = 0.2215, uniform_loss = -1.2486
|
41 |
+
2021-10-07 16:25:36,065 : belief : pearson = 0.8094, spearman = 0.8136, align_loss = 0.2693, uniform_loss = -1.7862
|
42 |
+
2021-10-07 16:25:38,331 : headlines : pearson = 0.8290, spearman = 0.8334, align_loss = 0.1846, uniform_loss = -1.9589
|
43 |
+
2021-10-07 16:25:40,201 : images : pearson = 0.9071, spearman = 0.9132, align_loss = 0.1945, uniform_loss = -2.0353
|
44 |
+
2021-10-07 16:25:40,206 : ALL : Pearson = 0.8362, Spearman = 0.8449, align_loss = 0.2321, uniform_loss = -1.7768
|
45 |
+
2021-10-07 16:25:40,206 : ALL (weighted average) : Pearson = 0.8183, Spearman = 0.8247, align_loss = 0.2321, uniform_loss = -1.7768
|
46 |
+
2021-10-07 16:25:40,206 : ALL (average) : Pearson = 0.8090, Spearman = 0.8150, align_loss = 0.2513, uniform_loss = -1.7944
|
47 |
+
|
48 |
+
2021-10-07 16:25:40,211 : ***** Transfer task : STS16 *****
|
49 |
+
|
50 |
+
|
51 |
+
2021-10-07 16:25:41,053 : answer-answer : pearson = 0.7412, spearman = 0.7434, align_loss = 0.2435, uniform_loss = -1.4824
|
52 |
+
2021-10-07 16:25:41,737 : headlines : pearson = 0.8196, spearman = 0.8381, align_loss = 0.1571, uniform_loss = -1.9802
|
53 |
+
2021-10-07 16:25:42,487 : plagiarism : pearson = 0.8495, spearman = 0.8620, align_loss = 0.1564, uniform_loss = -1.6272
|
54 |
+
2021-10-07 16:25:43,891 : postediting : pearson = 0.8548, spearman = 0.8739, align_loss = 0.1171, uniform_loss = -1.7985
|
55 |
+
2021-10-07 16:25:44,530 : question-question : pearson = 0.7249, spearman = 0.7206, align_loss = 0.1987, uniform_loss = -1.7836
|
56 |
+
2021-10-07 16:25:44,533 : ALL : Pearson = 0.7944, Spearman = 0.8074, align_loss = 0.1746, uniform_loss = -1.7344
|
57 |
+
2021-10-07 16:25:44,534 : ALL (weighted average) : Pearson = 0.7992, Spearman = 0.8091, align_loss = 0.1746, uniform_loss = -1.7331
|
58 |
+
2021-10-07 16:25:44,534 : ALL (average) : Pearson = 0.7980, Spearman = 0.8076, align_loss = 0.1746, uniform_loss = -1.7344
|
59 |
+
|
60 |
+
2021-10-07 16:25:44,536 :
|
61 |
+
|
62 |
+
***** Transfer task : STSBenchmark*****
|
63 |
+
|
64 |
+
|
65 |
+
2021-10-07 16:26:05,137 : train : pearson = 0.8198, spearman = 0.7975, align_loss = 0.1852, uniform_loss = -1.9620
|
66 |
+
2021-10-07 16:26:11,036 : dev : pearson = 0.8570, spearman = 0.8597, align_loss = 0.2060, uniform_loss = -1.9924
|
67 |
+
2021-10-07 16:26:16,108 : test : pearson = 0.8090, spearman = 0.8152, align_loss = 0.1776, uniform_loss = -1.9208
|
68 |
+
2021-10-07 16:26:16,137 : ALL : Pearson = 0.8258, Spearman = 0.8145, align_loss = 0.1876, uniform_loss = -1.9607
|
69 |
+
2021-10-07 16:26:16,137 : ALL (weighted average) : Pearson = 0.8246, Spearman = 0.8112, align_loss = 0.1876, uniform_loss = -1.9607
|
70 |
+
2021-10-07 16:26:16,137 : ALL (average) : Pearson = 0.8286, Spearman = 0.8241, align_loss = 0.1896, uniform_loss = -1.9584
|
71 |
+
|
72 |
+
2021-10-07 16:26:16,147 :
|
73 |
+
|
74 |
+
***** Transfer task : SICKRelatedness*****
|
75 |
+
|
76 |
+
|
77 |
+
2021-10-07 16:26:28,880 : train : pearson = 0.8053, spearman = 0.7307, align_loss = 0.1797, uniform_loss = -1.9860
|
78 |
+
2021-10-07 16:26:30,456 : dev : pearson = 0.8165, spearman = 0.7514, align_loss = 0.1858, uniform_loss = -2.1245
|
79 |
+
2021-10-07 16:26:44,329 : test : pearson = 0.7953, spearman = 0.7230, align_loss = 0.1798, uniform_loss = -1.9833
|
80 |
+
2021-10-07 16:26:44,336 : ALL : Pearson = 0.8009, Spearman = 0.7280, align_loss = 0.1800, uniform_loss = -1.9917
|
81 |
+
2021-10-07 16:26:44,336 : ALL (weighted average) : Pearson = 0.8009, Spearman = 0.7279, align_loss = 0.1800, uniform_loss = -1.9916
|
82 |
+
2021-10-07 16:26:44,336 : ALL (average) : Pearson = 0.8057, Spearman = 0.7350, align_loss = 0.1817, uniform_loss = -2.0313
|
83 |
+
|
84 |
+
2021-10-07 16:26:44,336 : ------ test ------
|
85 |
+
2021-10-07 16:26:44,337 : +--------+--------+--------+--------+--------+--------------+-----------------+--------+
|
86 |
+
| STS12 | STS13 | STS14 | STS15 | STS16 | STSBenchmark | SICKRelatedness | Avg. |
|
87 |
+
+--------+--------+--------+--------+--------+--------------+-----------------+--------+
|
88 |
+
| 71.74 | 82.60 | 75.67 | 84.49 | 80.74 | 81.52 | 72.30 | 78.44 |
|
89 |
+
| 0.185 | 0.219 | 0.215 | 0.232 | 0.175 | 0.178 | 0.180 | 0.198 |
|
90 |
+
| -1.775 | -1.850 | -1.892 | -1.777 | -1.734 | -1.921 | -1.983 | -1.847 |
|
91 |
+
+--------+--------+--------+--------+--------+--------------+-----------------+--------+
|
92 |
+
2021-10-07 16:26:44,338 : +------+------+------+------+------+------+------+------+
|
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:b9eb92d445111835d5ba49f06f172d7baa453b8b1d26284578e1bead690d2034
|
3 |
+
size 2887571
|