Update README.md
Browse files
README.md
CHANGED
|
@@ -14,22 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# wangchanberta-base-att-spm-uncased-finetuned-th-squad
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on the thaiqa_squad dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 1.0395
|
| 19 |
|
| 20 |
-
## Model description
|
| 21 |
-
|
| 22 |
-
More information needed
|
| 23 |
-
|
| 24 |
-
## Intended uses & limitations
|
| 25 |
-
|
| 26 |
-
More information needed
|
| 27 |
-
|
| 28 |
-
## Training and evaluation data
|
| 29 |
-
|
| 30 |
-
More information needed
|
| 31 |
-
|
| 32 |
-
## Training procedure
|
| 33 |
|
| 34 |
### Training hyperparameters
|
| 35 |
|
|
@@ -42,14 +27,6 @@ The following hyperparameters were used during training:
|
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- num_epochs: 3
|
| 44 |
|
| 45 |
-
### Training results
|
| 46 |
-
|
| 47 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
-
| 1.2114 | 1.0 | 1258 | 1.1932 |
|
| 50 |
-
| 0.9658 | 2.0 | 2516 | 1.0572 |
|
| 51 |
-
| 0.8971 | 3.0 | 3774 | 1.0395 |
|
| 52 |
-
|
| 53 |
|
| 54 |
### Framework versions
|
| 55 |
|
|
|
|
| 14 |
# wangchanberta-base-att-spm-uncased-finetuned-th-squad
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [airesearch/wangchanberta-base-att-spm-uncased](https://huggingface.co/airesearch/wangchanberta-base-att-spm-uncased) on the thaiqa_squad dataset.
|
|
|
|
|
|
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
### Training hyperparameters
|
| 20 |
|
|
|
|
| 27 |
- lr_scheduler_type: linear
|
| 28 |
- num_epochs: 3
|
| 29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
### Framework versions
|
| 32 |
|