Add evaluation results on the default config of multi_nli
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 [multi_nli](https://huggingface.co/datasets/multi_nli) dataset by
@MoritzLaurer
, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-multi_nli-default-4a02ee-14425976).\
Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=multi_nli).\
Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=multi_nli).
README.md
CHANGED
@@ -121,6 +121,59 @@ model-index:
|
|
121 |
type: loss
|
122 |
value: 1.0105403661727905
|
123 |
verified: true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
124 |
---
|
125 |
# DeBERTa-v3-base-mnli-fever-anli
|
126 |
## Model description
|
|
|
121 |
type: loss
|
122 |
value: 1.0105403661727905
|
123 |
verified: true
|
124 |
+
- task:
|
125 |
+
type: natural-language-inference
|
126 |
+
name: Natural Language Inference
|
127 |
+
dataset:
|
128 |
+
name: multi_nli
|
129 |
+
type: multi_nli
|
130 |
+
config: default
|
131 |
+
split: validation_mismatched
|
132 |
+
metrics:
|
133 |
+
- name: Accuracy
|
134 |
+
type: accuracy
|
135 |
+
value: 0.902766476810415
|
136 |
+
verified: true
|
137 |
+
- name: Precision Macro
|
138 |
+
type: precision
|
139 |
+
value: 0.9023816542652491
|
140 |
+
verified: true
|
141 |
+
- name: Precision Micro
|
142 |
+
type: precision
|
143 |
+
value: 0.902766476810415
|
144 |
+
verified: true
|
145 |
+
- name: Precision Weighted
|
146 |
+
type: precision
|
147 |
+
value: 0.9034597464719761
|
148 |
+
verified: true
|
149 |
+
- name: Recall Macro
|
150 |
+
type: recall
|
151 |
+
value: 0.9024304801555488
|
152 |
+
verified: true
|
153 |
+
- name: Recall Micro
|
154 |
+
type: recall
|
155 |
+
value: 0.902766476810415
|
156 |
+
verified: true
|
157 |
+
- name: Recall Weighted
|
158 |
+
type: recall
|
159 |
+
value: 0.902766476810415
|
160 |
+
verified: true
|
161 |
+
- name: F1 Macro
|
162 |
+
type: f1
|
163 |
+
value: 0.9023086094638595
|
164 |
+
verified: true
|
165 |
+
- name: F1 Micro
|
166 |
+
type: f1
|
167 |
+
value: 0.902766476810415
|
168 |
+
verified: true
|
169 |
+
- name: F1 Weighted
|
170 |
+
type: f1
|
171 |
+
value: 0.9030161011457231
|
172 |
+
verified: true
|
173 |
+
- name: loss
|
174 |
+
type: loss
|
175 |
+
value: 0.3283354640007019
|
176 |
+
verified: true
|
177 |
---
|
178 |
# DeBERTa-v3-base-mnli-fever-anli
|
179 |
## Model description
|