|
--- |
|
base_model: airesearch/wangchanberta-base-att-spm-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: lst20-baseline-new |
|
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. --> |
|
|
|
# lst20-baseline-new |
|
|
|
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 None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1359 |
|
- Precision: 0.8427 |
|
- Recall: 0.6944 |
|
- F1: 0.7614 |
|
- Accuracy: 0.9474 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1354 | 1.0 | 1274 | 0.1384 | 0.8232 | 0.6967 | 0.7547 | 0.9453 | |
|
| 0.1392 | 2.0 | 2548 | 0.1396 | 0.8570 | 0.6681 | 0.7508 | 0.9464 | |
|
| 0.1325 | 3.0 | 3822 | 0.1352 | 0.8148 | 0.7212 | 0.7651 | 0.9465 | |
|
| 0.1266 | 4.0 | 5096 | 0.1366 | 0.8536 | 0.6746 | 0.7536 | 0.9467 | |
|
| 0.1195 | 5.0 | 6370 | 0.1359 | 0.8427 | 0.6944 | 0.7614 | 0.9474 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|
