Update README.md
Browse files
README.md
CHANGED
@@ -6,6 +6,14 @@ tags:
|
|
6 |
model-index:
|
7 |
- name: FYP_qa_final
|
8 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -13,13 +21,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# FYP_qa_final
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
- Loss: 2.7493
|
19 |
|
20 |
## Model description
|
21 |
|
22 |
-
|
23 |
|
24 |
## Intended uses & limitations
|
25 |
|
@@ -27,7 +35,11 @@ More information needed
|
|
27 |
|
28 |
## Training and evaluation data
|
29 |
|
30 |
-
|
|
|
|
|
|
|
|
|
31 |
|
32 |
## Training procedure
|
33 |
|
@@ -60,4 +72,4 @@ The following hyperparameters were used during training:
|
|
60 |
- Transformers 4.39.3
|
61 |
- Pytorch 2.2.1+cu121
|
62 |
- Datasets 2.18.0
|
63 |
-
- Tokenizers 0.15.2
|
|
|
6 |
model-index:
|
7 |
- name: FYP_qa_final
|
8 |
results: []
|
9 |
+
datasets:
|
10 |
+
- rajpurkar/squad_v2
|
11 |
+
- mrqa
|
12 |
+
- UCLNLP/adversarial_qa
|
13 |
+
- mbartolo/synQA
|
14 |
+
language:
|
15 |
+
- en
|
16 |
+
pipeline_tag: question-answering
|
17 |
---
|
18 |
|
19 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
21 |
|
22 |
# FYP_qa_final
|
23 |
|
24 |
+
This model is a fine-tuned version of [deepset/deberta-v3-base-squad2](https://huggingface.co/deepset/deberta-v3-base-squad2) on an [MRQA](https://huggingface.co/datasets/mrqa) dataset.
|
25 |
It achieves the following results on the evaluation set:
|
26 |
- Loss: 2.7493
|
27 |
|
28 |
## Model description
|
29 |
|
30 |
+
This model is trained for performing extractive question-answering tasks for academic essays.
|
31 |
|
32 |
## Intended uses & limitations
|
33 |
|
|
|
35 |
|
36 |
## Training and evaluation data
|
37 |
|
38 |
+
The dataset used for training is listed below according to training sequences:
|
39 |
+
1. [MRQA(train split)](https://huggingface.co/datasets/mrqa)
|
40 |
+
2. [UCLNLP/adversarial_qa](https://huggingface.co/datasets/UCLNLP/adversarial_qa)
|
41 |
+
3. [mbartolo/synQA](https://huggingface.co/datasets/mbartolo/synQA)
|
42 |
+
4. [MRQA(test split)](https://huggingface.co/datasets/mrqa)
|
43 |
|
44 |
## Training procedure
|
45 |
|
|
|
72 |
- Transformers 4.39.3
|
73 |
- Pytorch 2.2.1+cu121
|
74 |
- Datasets 2.18.0
|
75 |
+
- Tokenizers 0.15.2
|