autoevaluator HF staff commited on
Commit
84ee1a6
1 Parent(s): e5350ef

Add evaluation results on the plain_text config and dev_r1 split of anli

Browse files

Beep boop, I am a bot from Hugging Face's automatic model evaluator 👋!\
Your model has been evaluated on the plain_text config and dev_r1 split of the [anli](https://huggingface.co/datasets/anli) dataset by

@ctkang
, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-eval-anli-plain_text-f2dca1-2066067125).\
Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=anli).\
Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=anli).

Files changed (1) hide show
  1. README.md +53 -0
README.md CHANGED
@@ -174,6 +174,59 @@ model-index:
174
  type: loss
175
  value: 0.3283354640007019
176
  verified: true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
177
  ---
178
  # DeBERTa-v3-base-mnli-fever-anli
179
  ## Model description
 
174
  type: loss
175
  value: 0.3283354640007019
176
  verified: true
177
+ - task:
178
+ type: natural-language-inference
179
+ name: Natural Language Inference
180
+ dataset:
181
+ name: anli
182
+ type: anli
183
+ config: plain_text
184
+ split: dev_r1
185
+ metrics:
186
+ - name: Accuracy
187
+ type: accuracy
188
+ value: 0.737
189
+ verified: true
190
+ - name: Precision Macro
191
+ type: precision
192
+ value: 0.737681071614645
193
+ verified: true
194
+ - name: Precision Micro
195
+ type: precision
196
+ value: 0.737
197
+ verified: true
198
+ - name: Precision Weighted
199
+ type: precision
200
+ value: 0.7376755842752241
201
+ verified: true
202
+ - name: Recall Macro
203
+ type: recall
204
+ value: 0.7369675064285843
205
+ verified: true
206
+ - name: Recall Micro
207
+ type: recall
208
+ value: 0.737
209
+ verified: true
210
+ - name: Recall Weighted
211
+ type: recall
212
+ value: 0.737
213
+ verified: true
214
+ - name: F1 Macro
215
+ type: f1
216
+ value: 0.7366853496239583
217
+ verified: true
218
+ - name: F1 Micro
219
+ type: f1
220
+ value: 0.737
221
+ verified: true
222
+ - name: F1 Weighted
223
+ type: f1
224
+ value: 0.7366990292378379
225
+ verified: true
226
+ - name: loss
227
+ type: loss
228
+ value: 0.9349392056465149
229
+ verified: true
230
  ---
231
  # DeBERTa-v3-base-mnli-fever-anli
232
  ## Model description