ArghaKamalSamanta
commited on
Commit
•
91884de
1
Parent(s):
600f478
Update README.md
Browse files
README.md
CHANGED
@@ -1,7 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
# Entailment Detection by Fine-tuning BERT
|
2 |
----------------------------------------------
|
3 |
<li>The model in this repository is fine-tuned on Google's encoder-decoder transformer-based model BERT.</li>
|
4 |
<li>New York University's Multi-NLI dataset is used for fine-tuning.</li>
|
5 |
<li>Accuracy achieved: ~73%</li>
|
6 |
<p></p><p></p>
|
7 |
-
<i><b>N.B.:</b> Due to computational resource constraints, only 11K samples are used for fine-tuning. There is room for accuracy improvement if a model is trained on all the 390K samples in the dataset.</i>
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- nyu-mll/multi_nli
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
library_name: adapter-transformers
|
10 |
+
pipeline_tag: text-classification
|
11 |
+
tags:
|
12 |
+
- code
|
13 |
+
base_model: bert
|
14 |
+
---
|
15 |
# Entailment Detection by Fine-tuning BERT
|
16 |
----------------------------------------------
|
17 |
<li>The model in this repository is fine-tuned on Google's encoder-decoder transformer-based model BERT.</li>
|
18 |
<li>New York University's Multi-NLI dataset is used for fine-tuning.</li>
|
19 |
<li>Accuracy achieved: ~73%</li>
|
20 |
<p></p><p></p>
|
21 |
+
<i><b>N.B.:</b> Due to computational resource constraints, only 11K samples are used for fine-tuning. There is room for accuracy improvement if a model is trained on all the 390K samples in the dataset.</i>
|