Update README.md
Browse files
README.md
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
thumbnail:
|
4 |
+
tags:
|
5 |
+
- pytorch
|
6 |
+
- text-classification
|
7 |
+
license:
|
8 |
+
datasets:
|
9 |
+
- MNLI
|
10 |
+
---
|
11 |
+
|
12 |
+
# distilbert-base-uncased finetuned on MNLI
|
13 |
+
|
14 |
+
## Model Details and Training Data
|
15 |
+
|
16 |
+
We used the pretrained model from [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) and finetuned it on [MultiNLI](https://cims.nyu.edu/~sbowman/multinli/) dataset.
|
17 |
+
|
18 |
+
The training parameters were kept the same as [Devlin et al., 2019](https://arxiv.org/abs/1810.04805) (learning rate = 2e-5, training epochs = 3, max_sequence_len = 128 and batch_size = 32).
|
19 |
+
|
20 |
+
## Evaluation Results
|
21 |
+
|
22 |
+
The evaluation results are mentioned in the table below.
|
23 |
+
|
24 |
+
| Test Corpus | Accuracy |
|
25 |
+
|:---:|:---------:|
|
26 |
+
| Matched | 0.8223 |
|
27 |
+
| Mismatched | 0.8216 |
|
28 |
+
|