Add evaluation results on the plain_text config and test split of launch/gov_report
#2
by
autoevaluator
HF staff
- opened
README.md
CHANGED
@@ -219,6 +219,39 @@ model-index:
|
|
219 |
type: gen_len
|
220 |
value: 45.2173
|
221 |
verified: true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
222 |
---
|
223 |
|
224 |
# pszemraj/pegasus-x-large-book-summary
|
|
|
219 |
type: gen_len
|
220 |
value: 45.2173
|
221 |
verified: true
|
222 |
+
- task:
|
223 |
+
type: summarization
|
224 |
+
name: Summarization
|
225 |
+
dataset:
|
226 |
+
name: launch/gov_report
|
227 |
+
type: launch/gov_report
|
228 |
+
config: plain_text
|
229 |
+
split: test
|
230 |
+
metrics:
|
231 |
+
- name: ROUGE-1
|
232 |
+
type: rouge
|
233 |
+
value: 39.7279
|
234 |
+
verified: true
|
235 |
+
- name: ROUGE-2
|
236 |
+
type: rouge
|
237 |
+
value: 10.8944
|
238 |
+
verified: true
|
239 |
+
- name: ROUGE-L
|
240 |
+
type: rouge
|
241 |
+
value: 19.7018
|
242 |
+
verified: true
|
243 |
+
- name: ROUGE-LSUM
|
244 |
+
type: rouge
|
245 |
+
value: 36.5634
|
246 |
+
verified: true
|
247 |
+
- name: loss
|
248 |
+
type: loss
|
249 |
+
value: 2.473011016845703
|
250 |
+
verified: true
|
251 |
+
- name: gen_len
|
252 |
+
type: gen_len
|
253 |
+
value: 212.8243
|
254 |
+
verified: true
|
255 |
---
|
256 |
|
257 |
# pszemraj/pegasus-x-large-book-summary
|