Commit
路
ffa80c4
1
Parent(s):
a88b0be
Upload README.md
Browse files- NaTu/README.md +21 -0
NaTu/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- squad
|
| 4 |
+
library_name: transformers
|
| 5 |
+
pipeline_tag: question-answering
|
| 6 |
+
---
|
| 7 |
+
This model is a fine-tuned version of huawei-noah/TinyBERT_General_4L_312D on SQuAD dataset.
|
| 8 |
+
|
| 9 |
+
### Training parameters
|
| 10 |
+
- learning_rate: 1e-05
|
| 11 |
+
- train_batch_size: 20
|
| 12 |
+
- eval_batch_size: 32
|
| 13 |
+
- optimizer:paged_adamw_32bit
|
| 14 |
+
- num_epochs: 1
|
| 15 |
+
|
| 16 |
+
### Framework versions
|
| 17 |
+
|
| 18 |
+
- Transformers 4.35.2
|
| 19 |
+
- Pytorch 2.1.0+cu118
|
| 20 |
+
- Datasets 2.15.0
|
| 21 |
+
- Tokenizers 0.15.0
|