Add evaluation results on the 3.0.0 config of cnn_dailymail
#4
by
autoevaluator
HF staff
- opened
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
- en
|
4 |
- fr
|
5 |
- ro
|
@@ -9,8 +9,43 @@ datasets:
|
|
9 |
tags:
|
10 |
- summarization
|
11 |
- translation
|
12 |
-
|
13 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
---
|
15 |
|
16 |
[Google's T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html)
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
- en
|
4 |
- fr
|
5 |
- ro
|
|
|
9 |
tags:
|
10 |
- summarization
|
11 |
- translation
|
|
|
12 |
license: apache-2.0
|
13 |
+
model-index:
|
14 |
+
- name: t5-large
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
type: summarization
|
18 |
+
name: Summarization
|
19 |
+
dataset:
|
20 |
+
name: cnn_dailymail
|
21 |
+
type: cnn_dailymail
|
22 |
+
config: 3.0.0
|
23 |
+
split: train
|
24 |
+
metrics:
|
25 |
+
- name: ROUGE-1
|
26 |
+
type: rouge
|
27 |
+
value: 24.2402
|
28 |
+
verified: true
|
29 |
+
- name: ROUGE-2
|
30 |
+
type: rouge
|
31 |
+
value: 11.2483
|
32 |
+
verified: true
|
33 |
+
- name: ROUGE-L
|
34 |
+
type: rouge
|
35 |
+
value: 20.0572
|
36 |
+
verified: true
|
37 |
+
- name: ROUGE-LSUM
|
38 |
+
type: rouge
|
39 |
+
value: 22.6894
|
40 |
+
verified: true
|
41 |
+
- name: loss
|
42 |
+
type: loss
|
43 |
+
value: 1.8751693964004517
|
44 |
+
verified: true
|
45 |
+
- name: gen_len
|
46 |
+
type: gen_len
|
47 |
+
value: 18.9862
|
48 |
+
verified: true
|
49 |
---
|
50 |
|
51 |
[Google's T5](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html)
|