Add evaluation results on the default config and test split of xsum
#12
by
autoevaluator
HF staff
- opened
README.md
CHANGED
@@ -14,29 +14,29 @@ model-index:
|
|
14 |
config: samsum
|
15 |
split: train
|
16 |
metrics:
|
17 |
-
-
|
18 |
-
type: rouge
|
19 |
value: 21.8096
|
|
|
20 |
verified: true
|
21 |
-
-
|
22 |
-
type: rouge
|
23 |
value: 4.2525
|
|
|
24 |
verified: true
|
25 |
-
-
|
26 |
-
type: rouge
|
27 |
value: 17.4469
|
|
|
28 |
verified: true
|
29 |
-
-
|
30 |
-
type: rouge
|
31 |
value: 18.8907
|
|
|
32 |
verified: true
|
33 |
-
-
|
34 |
-
type: loss
|
35 |
value: 3.0317161083221436
|
|
|
36 |
verified: true
|
37 |
-
-
|
38 |
-
type: gen_len
|
39 |
value: 20.3122
|
|
|
40 |
verified: true
|
41 |
- task:
|
42 |
type: summarization
|
@@ -47,30 +47,36 @@ model-index:
|
|
47 |
config: default
|
48 |
split: test
|
49 |
metrics:
|
50 |
-
-
|
51 |
-
|
52 |
-
|
53 |
-
verified: true
|
54 |
-
|
55 |
-
|
56 |
-
value: 24.
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
-
|
71 |
-
|
72 |
-
|
73 |
-
verified: true
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
- task:
|
75 |
type: summarization
|
76 |
name: Summarization
|
@@ -80,29 +86,29 @@ model-index:
|
|
80 |
config: 3.0.0
|
81 |
split: test
|
82 |
metrics:
|
83 |
-
-
|
84 |
-
type: rouge
|
85 |
value: 22.2062
|
|
|
86 |
verified: true
|
87 |
-
-
|
88 |
-
type: rouge
|
89 |
value: 7.6701
|
|
|
90 |
verified: true
|
91 |
-
-
|
92 |
-
type: rouge
|
93 |
value: 15.4046
|
|
|
94 |
verified: true
|
95 |
-
-
|
96 |
-
type: rouge
|
97 |
value: 19.2182
|
|
|
98 |
verified: true
|
99 |
-
-
|
100 |
-
type: loss
|
101 |
value: 2.681241273880005
|
|
|
102 |
verified: true
|
103 |
-
-
|
104 |
-
type: gen_len
|
105 |
value: 25.0234
|
|
|
106 |
verified: true
|
107 |
---
|
108 |
|
|
|
14 |
config: samsum
|
15 |
split: train
|
16 |
metrics:
|
17 |
+
- type: rouge
|
|
|
18 |
value: 21.8096
|
19 |
+
name: ROUGE-1
|
20 |
verified: true
|
21 |
+
- type: rouge
|
|
|
22 |
value: 4.2525
|
23 |
+
name: ROUGE-2
|
24 |
verified: true
|
25 |
+
- type: rouge
|
|
|
26 |
value: 17.4469
|
27 |
+
name: ROUGE-L
|
28 |
verified: true
|
29 |
+
- type: rouge
|
|
|
30 |
value: 18.8907
|
31 |
+
name: ROUGE-LSUM
|
32 |
verified: true
|
33 |
+
- type: loss
|
|
|
34 |
value: 3.0317161083221436
|
35 |
+
name: loss
|
36 |
verified: true
|
37 |
+
- type: gen_len
|
|
|
38 |
value: 20.3122
|
39 |
+
name: gen_len
|
40 |
verified: true
|
41 |
- task:
|
42 |
type: summarization
|
|
|
47 |
config: default
|
48 |
split: test
|
49 |
metrics:
|
50 |
+
- type: rouge
|
51 |
+
value: 46.7908
|
52 |
+
name: ROUGE-1
|
53 |
+
verified: true
|
54 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjNiY2RlNDhlN2Y2ZjNlNzJlZmQ4YjBhMWMwMjY0NmMxNDU0ODY5Y2MwYjE2ZTc2ZWZlOGUyZjA5Y2ZjNzk5MyIsInZlcnNpb24iOjF9.C5KrRkK2fTkD8WGcgQ1ma1yLtjXPWk5A6nz6EHm6kixYsqu4zCbRZAFj9VzpTqvZEZu2J2KPVrLYIEHxKUusDA
|
55 |
+
- type: rouge
|
56 |
+
value: 24.4119
|
57 |
+
name: ROUGE-2
|
58 |
+
verified: true
|
59 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzU4YzlhMzY2YmEwNzliYmViOTBkYTdmYTM2MmRiNzI4ZTZiYzQ2MmQ2NGFjNDA2Y2E1MzYzYTQ5YmZjZmJmZCIsInZlcnNpb24iOjF9.VrnKQalNaFRyhp-PFXUlzXZf1zuyCLXuTKsbF0gUd4I-4px-ZiHobGt9MboPascJWHnxnzQITYy2EPzQgqZHCg
|
60 |
+
- type: rouge
|
61 |
+
value: 38.9822
|
62 |
+
name: ROUGE-L
|
63 |
+
verified: true
|
64 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDkzNjAzMjI1MzUxN2U2MTI0MWEwYzk4MmViZDc2ZTcwZmRiMTdiMWMxYzU2YWE1N2FhODBkZGU2NDk3NDc2MSIsInZlcnNpb24iOjF9.CcAWEhczzW30o8IM-n-rxGI-jRiisnFo7Fg7WtRyXKRuLnxzD5jrsbKFt9xO0Wx4nHromI5_Br7TVuVdnp-RAw
|
65 |
+
- type: rouge
|
66 |
+
value: 39.0437
|
67 |
+
name: ROUGE-LSUM
|
68 |
+
verified: true
|
69 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTk5MTc1ZWYwNDZlZjEyNjFkYzM5OWI5OGQ1MjQ2NDYwNzc3NGFhZmQ2ZTI4ODU3NzQ4NGU4ZjMwMWNhOTU4OSIsInZlcnNpb24iOjF9.acbOskynDDoZ4BO592J-8wcuV_JXWuTH_kcbxPJnSpdv1ih_0l99RvLyrQO_M5Ngfr6dTSnYi1e4Pry_fQH-AA
|
70 |
+
- type: loss
|
71 |
+
value: 1.5713257789611816
|
72 |
+
name: loss
|
73 |
+
verified: true
|
74 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODhhNDFkMjdhNmI0MDc4NWFkYjkzZTc2OGM5MTY4NGMwZDE0NWZhMTBmZmY5ZGMyMWU5NTY3MjFjZWZkZTdmYiIsInZlcnNpb24iOjF9.PJcC1UpQpfSz44f8mQN5gp5ZFbEbDtRPLzK5RoPjTirRJ4cDPxX88yLI3rDiUMZRdXitEaWqQpLkFqu-5g75Bw
|
75 |
+
- type: gen_len
|
76 |
+
value: 23.089
|
77 |
+
name: gen_len
|
78 |
+
verified: true
|
79 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGNlMDZmNjRjNWM1YTg0M2FmNDg4ZGE2OGMzYjc4MmE3MTk3YTQzNzM3ZmJmZmJhNDVlMGZlYWNiOGJmYmFlMSIsInZlcnNpb24iOjF9.w-ce3jWHW2dzLFaJe2R9hAiCvIdX-SIcrCe5ADTCDyBQwLrHOJf8-xFYLt9oE9EAlXJsbrhjlCMJbzFChNQTBg
|
80 |
- task:
|
81 |
type: summarization
|
82 |
name: Summarization
|
|
|
86 |
config: 3.0.0
|
87 |
split: test
|
88 |
metrics:
|
89 |
+
- type: rouge
|
|
|
90 |
value: 22.2062
|
91 |
+
name: ROUGE-1
|
92 |
verified: true
|
93 |
+
- type: rouge
|
|
|
94 |
value: 7.6701
|
95 |
+
name: ROUGE-2
|
96 |
verified: true
|
97 |
+
- type: rouge
|
|
|
98 |
value: 15.4046
|
99 |
+
name: ROUGE-L
|
100 |
verified: true
|
101 |
+
- type: rouge
|
|
|
102 |
value: 19.2182
|
103 |
+
name: ROUGE-LSUM
|
104 |
verified: true
|
105 |
+
- type: loss
|
|
|
106 |
value: 2.681241273880005
|
107 |
+
name: loss
|
108 |
verified: true
|
109 |
+
- type: gen_len
|
|
|
110 |
value: 25.0234
|
111 |
+
name: gen_len
|
112 |
verified: true
|
113 |
---
|
114 |
|