Add evaluation results on the default config and test split of xsum
#11
by
autoevaluator
HF staff
- opened
README.md
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
---
|
2 |
-
tags:
|
3 |
-
- summarization
|
4 |
language:
|
5 |
- en
|
6 |
license: mit
|
|
|
|
|
7 |
model-index:
|
8 |
- name: facebook/bart-large-xsum
|
9 |
results:
|
@@ -16,29 +16,29 @@ model-index:
|
|
16 |
config: 3.0.0
|
17 |
split: test
|
18 |
metrics:
|
19 |
-
-
|
20 |
-
type: rouge
|
21 |
value: 25.2697
|
|
|
22 |
verified: true
|
23 |
-
-
|
24 |
-
type: rouge
|
25 |
value: 7.6638
|
|
|
26 |
verified: true
|
27 |
-
-
|
28 |
-
type: rouge
|
29 |
value: 17.1808
|
|
|
30 |
verified: true
|
31 |
-
-
|
32 |
-
type: rouge
|
33 |
value: 21.7933
|
|
|
34 |
verified: true
|
35 |
-
-
|
36 |
-
type: loss
|
37 |
value: 3.5042972564697266
|
|
|
38 |
verified: true
|
39 |
-
-
|
40 |
-
type: gen_len
|
41 |
value: 27.4462
|
|
|
42 |
verified: true
|
43 |
- task:
|
44 |
type: summarization
|
@@ -49,30 +49,36 @@ model-index:
|
|
49 |
config: default
|
50 |
split: test
|
51 |
metrics:
|
52 |
-
-
|
53 |
-
|
54 |
-
|
55 |
-
verified: true
|
56 |
-
|
57 |
-
|
58 |
-
value: 22.
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
-
|
73 |
-
|
|
|
|
|
|
|
|
|
74 |
value: 25.5435
|
|
|
75 |
verified: true
|
|
|
76 |
- task:
|
77 |
type: summarization
|
78 |
name: Summarization
|
@@ -82,29 +88,29 @@ model-index:
|
|
82 |
config: samsum
|
83 |
split: train
|
84 |
metrics:
|
85 |
-
-
|
86 |
-
type: rouge
|
87 |
value: 24.7852
|
|
|
88 |
verified: true
|
89 |
-
-
|
90 |
-
type: rouge
|
91 |
value: 5.2533
|
|
|
92 |
verified: true
|
93 |
-
-
|
94 |
-
type: rouge
|
95 |
value: 18.6792
|
|
|
96 |
verified: true
|
97 |
-
-
|
98 |
-
type: rouge
|
99 |
value: 20.629
|
|
|
100 |
verified: true
|
101 |
-
-
|
102 |
-
type: loss
|
103 |
value: 3.746837854385376
|
|
|
104 |
verified: true
|
105 |
-
-
|
106 |
-
type: gen_len
|
107 |
value: 23.1206
|
|
|
108 |
verified: true
|
109 |
- task:
|
110 |
type: summarization
|
@@ -115,29 +121,29 @@ model-index:
|
|
115 |
config: samsum
|
116 |
split: test
|
117 |
metrics:
|
118 |
-
-
|
119 |
-
type: rouge
|
120 |
value: 24.9158
|
|
|
121 |
verified: true
|
122 |
-
-
|
123 |
-
type: rouge
|
124 |
value: 5.5837
|
|
|
125 |
verified: true
|
126 |
-
-
|
127 |
-
type: rouge
|
128 |
value: 18.8935
|
|
|
129 |
verified: true
|
130 |
-
-
|
131 |
-
type: rouge
|
132 |
value: 20.76
|
|
|
133 |
verified: true
|
134 |
-
-
|
135 |
-
type: loss
|
136 |
value: 3.775235891342163
|
|
|
137 |
verified: true
|
138 |
-
-
|
139 |
-
type: gen_len
|
140 |
value: 23.0928
|
|
|
141 |
verified: true
|
142 |
---
|
143 |
### Bart model finetuned on xsum
|
|
|
1 |
---
|
|
|
|
|
2 |
language:
|
3 |
- en
|
4 |
license: mit
|
5 |
+
tags:
|
6 |
+
- summarization
|
7 |
model-index:
|
8 |
- name: facebook/bart-large-xsum
|
9 |
results:
|
|
|
16 |
config: 3.0.0
|
17 |
split: test
|
18 |
metrics:
|
19 |
+
- type: rouge
|
|
|
20 |
value: 25.2697
|
21 |
+
name: ROUGE-1
|
22 |
verified: true
|
23 |
+
- type: rouge
|
|
|
24 |
value: 7.6638
|
25 |
+
name: ROUGE-2
|
26 |
verified: true
|
27 |
+
- type: rouge
|
|
|
28 |
value: 17.1808
|
29 |
+
name: ROUGE-L
|
30 |
verified: true
|
31 |
+
- type: rouge
|
|
|
32 |
value: 21.7933
|
33 |
+
name: ROUGE-LSUM
|
34 |
verified: true
|
35 |
+
- type: loss
|
|
|
36 |
value: 3.5042972564697266
|
37 |
+
name: loss
|
38 |
verified: true
|
39 |
+
- type: gen_len
|
|
|
40 |
value: 27.4462
|
41 |
+
name: gen_len
|
42 |
verified: true
|
43 |
- task:
|
44 |
type: summarization
|
|
|
49 |
config: default
|
50 |
split: test
|
51 |
metrics:
|
52 |
+
- type: rouge
|
53 |
+
value: 45.4419
|
54 |
+
name: ROUGE-1
|
55 |
+
verified: true
|
56 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzkzZTM0ZTQ3OTJhODgxOGJhNWE0Y2QxMjcwMjBiODdlMzY3Yjk1MjQ1MDJlODQwZjNlZWUyMTEwNmYyYjUzYiIsInZlcnNpb24iOjF9.3_JITjNVx36poltYC02qpeuMiAyYu2AOrfMpCACYdX2_FTtSxxWeYkUJHEbBnuJQKgERHmJncLcQxbh4IlvXBA
|
57 |
+
- type: rouge
|
58 |
+
value: 22.3723
|
59 |
+
name: ROUGE-2
|
60 |
+
verified: true
|
61 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDQzZTkxMWM4ZDgyOTcyYmI1MDgyNTk1YmExNTJmNDAxYjViNjlmZjUzNjQ3ZDQwNzQ5ZWQ0ZDU1YTFjYTdlYiIsInZlcnNpb24iOjF9.sDIZfKrHyHDcuYxKNYcvrl-1eMrnwMtm8cA-xDxNP4hX7eEhNoQSAo_CLiPibibcHNMOjZX9fPCMULiGb0qnBw
|
62 |
+
- type: rouge
|
63 |
+
value: 37.2229
|
64 |
+
name: ROUGE-L
|
65 |
+
verified: true
|
66 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOWM2MThmY2Y1YmY4OTEwYTZjZjRiNTYxMTY4NDVmMzBhOGM3YTlkZmExMDZmOGU0ZmM1MjMwM2RjOWU1YWQxNyIsInZlcnNpb24iOjF9.TNMvdtMB-5DHUth3HeMc9IilhlciZgPI8AW8RLWl5fWTDko8X0JRk-gTMW6b6cNcRUe2lmfZ9I_ZSd-ZvnjEBA
|
67 |
+
- type: rouge
|
68 |
+
value: 37.2239
|
69 |
+
name: ROUGE-LSUM
|
70 |
+
verified: true
|
71 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzZlMGI2NmRmMTEwMWFhNzAxOTRlMWQyNzA0YjI1ODE3ZjVjYmE1ODMzZTE1M2Y3MTk2YTcxZDYwN2U2NGI4NiIsInZlcnNpb24iOjF9.tcsUnGTDhbrOi1ZNusrI8Do4kt8BuNLD91fhbJwOsr9EvP6NlAAWnfoG1iBSNYKByMcC9Y31lwZlUOUBvnUdDQ
|
72 |
+
- type: loss
|
73 |
+
value: 2.3128323554992676
|
74 |
+
name: loss
|
75 |
+
verified: true
|
76 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzQ3ODBjNWY2ODdhZTAwODUxY2ViMjBmNDY3N2EwMTUzYzdjOGJlZjZlMTI0ZjhkM2I0MGRjNjM5OWNhZDU3NSIsInZlcnNpb24iOjF9.IleOf5Dq60z64kqp6w5dyc6azb1egIARnnKch-x-hpKdQUdTMyPmUO34SpWzuhMt9bJQXRG5qNxb0mpr2-ZMCg
|
77 |
+
- type: gen_len
|
78 |
value: 25.5435
|
79 |
+
name: gen_len
|
80 |
verified: true
|
81 |
+
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTE3ODlkZDhhMTEwNTlhNzVjMWMxMGQyZDc0OTc0NWY0MDBlMzUzNGI3MGQwNmJmNzQ3NTQ5MjhhNDhiYTM5YSIsInZlcnNpb24iOjF9.e7nHzg3OH3zkWiCj3iZVAAQG6Zy0E16_MJzBEEyGTlSVuPGMziNfcjRvLD6WeY_6lXUonEwc9lur0X-qUvB7Aw
|
82 |
- task:
|
83 |
type: summarization
|
84 |
name: Summarization
|
|
|
88 |
config: samsum
|
89 |
split: train
|
90 |
metrics:
|
91 |
+
- type: rouge
|
|
|
92 |
value: 24.7852
|
93 |
+
name: ROUGE-1
|
94 |
verified: true
|
95 |
+
- type: rouge
|
|
|
96 |
value: 5.2533
|
97 |
+
name: ROUGE-2
|
98 |
verified: true
|
99 |
+
- type: rouge
|
|
|
100 |
value: 18.6792
|
101 |
+
name: ROUGE-L
|
102 |
verified: true
|
103 |
+
- type: rouge
|
|
|
104 |
value: 20.629
|
105 |
+
name: ROUGE-LSUM
|
106 |
verified: true
|
107 |
+
- type: loss
|
|
|
108 |
value: 3.746837854385376
|
109 |
+
name: loss
|
110 |
verified: true
|
111 |
+
- type: gen_len
|
|
|
112 |
value: 23.1206
|
113 |
+
name: gen_len
|
114 |
verified: true
|
115 |
- task:
|
116 |
type: summarization
|
|
|
121 |
config: samsum
|
122 |
split: test
|
123 |
metrics:
|
124 |
+
- type: rouge
|
|
|
125 |
value: 24.9158
|
126 |
+
name: ROUGE-1
|
127 |
verified: true
|
128 |
+
- type: rouge
|
|
|
129 |
value: 5.5837
|
130 |
+
name: ROUGE-2
|
131 |
verified: true
|
132 |
+
- type: rouge
|
|
|
133 |
value: 18.8935
|
134 |
+
name: ROUGE-L
|
135 |
verified: true
|
136 |
+
- type: rouge
|
|
|
137 |
value: 20.76
|
138 |
+
name: ROUGE-LSUM
|
139 |
verified: true
|
140 |
+
- type: loss
|
|
|
141 |
value: 3.775235891342163
|
142 |
+
name: loss
|
143 |
verified: true
|
144 |
+
- type: gen_len
|
|
|
145 |
value: 23.0928
|
146 |
+
name: gen_len
|
147 |
verified: true
|
148 |
---
|
149 |
### Bart model finetuned on xsum
|