|
--- |
|
base_model: airesearch/wangchanberta-base-att-spm-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: lst20-orchid-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-orchid-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: 0.1383 |
|
- Precision: 0.8460 |
|
- Recall: 0.6761 |
|
- F1: 0.7516 |
|
- Accuracy: 0.9460 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.1753 | 1.0 | 1425 | 0.1463 | 0.8332 | 0.6466 | 0.7281 | 0.9417 | |
|
| 0.1513 | 2.0 | 2850 | 0.1457 | 0.8829 | 0.6099 | 0.7214 | 0.9431 | |
|
| 0.1393 | 3.0 | 4275 | 0.1388 | 0.8607 | 0.6495 | 0.7403 | 0.9450 | |
|
| 0.129 | 4.0 | 5700 | 0.1394 | 0.8561 | 0.6596 | 0.7451 | 0.9455 | |
|
| 0.1266 | 5.0 | 7125 | 0.1383 | 0.8460 | 0.6761 | 0.7516 | 0.9460 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|