Update README.md
Browse files
README.md
CHANGED
@@ -1,34 +1,35 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
-
license: apache-2.0
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- glue
|
9 |
model-index:
|
10 |
-
- name:
|
11 |
results: []
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
-
#
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
|
21 |
-
|
22 |
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
|
|
|
|
32 |
|
33 |
## Training procedure
|
34 |
|
@@ -52,4 +53,4 @@ The following hyperparameters were used during training:
|
|
52 |
- Transformers 4.22.2
|
53 |
- Pytorch 1.12.1+cu113
|
54 |
- Datasets 2.4.0
|
55 |
-
- Tokenizers 0.12.1
|
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- glue
|
8 |
model-index:
|
9 |
+
- name: debug
|
10 |
results: []
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
+
# BioLinkBERT-large-mnli
|
17 |
|
18 |
+
This model is a fine-tuned version of [BioLinkBERT-large](https://huggingface.co/michiyasunaga/BioLinkBERT-large) on the GLUE [MNLI](https://huggingface.co/datasets/multi_nli) dataset.
|
19 |
|
20 |
+
The results are
|
21 |
|
22 |
+
| **Model** | **Dataset** | **Acc** |
|
23 |
+
|------------------------|-------------|---------|
|
24 |
+
| Roberta-large-mnli | MNLI dev mm | 90.12 |
|
25 |
+
| | MNLI dev m | 90.59 |
|
26 |
+
| | SNLI test | 88.25 |
|
27 |
+
| BioLinkBERT-large | MNLI dev mm | 33.56 |
|
28 |
+
| | MNLI dev m | 33.18 |
|
29 |
+
| | SNLI test | 32.66 |
|
30 |
+
| BioLinkBERT-large-mnli | MNLI dev mm | 85.19 |
|
31 |
+
| | MNLI dev m | 84.96 |
|
32 |
+
| | SNLI test | 78.959 |
|
33 |
|
34 |
## Training procedure
|
35 |
|
|
|
53 |
- Transformers 4.22.2
|
54 |
- Pytorch 1.12.1+cu113
|
55 |
- Datasets 2.4.0
|
56 |
+
- Tokenizers 0.12.1
|