Add evaluation results on the default config of xsum
Browse filesBeep boop, I am a bot from Hugging Face's automatic model evaluator 👋!\
Your model has been evaluated on the default config of the [xsum](https://huggingface.co/datasets/xsum) dataset by
@lewtun
, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-xsum-c7d88063-10885461).\
Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=xsum).\
Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=xsum).
README.md
CHANGED
@@ -209,6 +209,39 @@ model-index:
|
|
209 |
type: gen_len
|
210 |
value: 34.464
|
211 |
verified: true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
212 |
---
|
213 |
|
214 |
# long-t5-tglobal-base-16384 + BookSum
|
|
|
209 |
type: gen_len
|
210 |
value: 34.464
|
211 |
verified: true
|
212 |
+
- task:
|
213 |
+
type: summarization
|
214 |
+
name: Summarization
|
215 |
+
dataset:
|
216 |
+
name: xsum
|
217 |
+
type: xsum
|
218 |
+
config: default
|
219 |
+
split: test
|
220 |
+
metrics:
|
221 |
+
- name: ROUGE-1
|
222 |
+
type: rouge
|
223 |
+
value: 20.5398
|
224 |
+
verified: true
|
225 |
+
- name: ROUGE-2
|
226 |
+
type: rouge
|
227 |
+
value: 3.4827
|
228 |
+
verified: true
|
229 |
+
- name: ROUGE-L
|
230 |
+
type: rouge
|
231 |
+
value: 13.647
|
232 |
+
verified: true
|
233 |
+
- name: ROUGE-LSUM
|
234 |
+
type: rouge
|
235 |
+
value: 15.8818
|
236 |
+
verified: true
|
237 |
+
- name: loss
|
238 |
+
type: loss
|
239 |
+
value: .nan
|
240 |
+
verified: true
|
241 |
+
- name: gen_len
|
242 |
+
type: gen_len
|
243 |
+
value: 81.4964
|
244 |
+
verified: true
|
245 |
---
|
246 |
|
247 |
# long-t5-tglobal-base-16384 + BookSum
|