|
--- |
|
library_name: transformers |
|
base_model: monsoon-nlp/bert-base-thai |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: bert-base-thai-intent-booking |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# bert-base-thai-intent-booking |
|
|
|
This model is a fine-tuned version of [monsoon-nlp/bert-base-thai](https://huggingface.co/monsoon-nlp/bert-base-thai) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.1536 |
|
- Accuracy: 0.1982 |
|
- F1: 0.1700 |
|
- Precision: 0.2287 |
|
- Recall: 0.1982 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 64 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 2.3662 | 1.0 | 65 | 2.3486 | 0.0901 | 0.0149 | 0.0081 | 0.0901 | |
|
| 2.3449 | 2.0 | 130 | 2.2698 | 0.1982 | 0.1149 | 0.0942 | 0.1982 | |
|
| 2.2956 | 3.0 | 195 | 2.2133 | 0.1396 | 0.0764 | 0.0628 | 0.1396 | |
|
| 2.2669 | 4.0 | 260 | 2.1724 | 0.1712 | 0.1367 | 0.1656 | 0.1712 | |
|
| 2.2199 | 5.0 | 325 | 2.2163 | 0.1577 | 0.1191 | 0.1388 | 0.1577 | |
|
| 2.2279 | 6.0 | 390 | 2.1963 | 0.1396 | 0.1008 | 0.1460 | 0.1396 | |
|
| 2.1828 | 7.0 | 455 | 2.1606 | 0.1892 | 0.1644 | 0.2060 | 0.1892 | |
|
| 2.1635 | 8.0 | 520 | 2.1509 | 0.1982 | 0.1701 | 0.2170 | 0.1982 | |
|
| 2.1588 | 9.0 | 585 | 2.1404 | 0.1937 | 0.1677 | 0.2157 | 0.1937 | |
|
| 2.1415 | 10.0 | 650 | 2.1212 | 0.2027 | 0.1743 | 0.2244 | 0.2027 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|
