|
--- |
|
license: mit |
|
base_model: xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: xlm-roberta-base-New_VietNam-aug_insert_synonym |
|
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. --> |
|
|
|
# xlm-roberta-base-New_VietNam-aug_insert_synonym |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0069 |
|
- Accuracy: 0.69 |
|
- F1: 0.7005 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 1.0846 | 1.0 | 43 | 0.9691 | 0.59 | 0.4903 | |
|
| 0.8237 | 2.0 | 86 | 0.7961 | 0.64 | 0.6370 | |
|
| 0.6422 | 3.0 | 129 | 0.7569 | 0.71 | 0.7145 | |
|
| 0.515 | 4.0 | 172 | 0.7775 | 0.71 | 0.7151 | |
|
| 0.4099 | 5.0 | 215 | 0.8224 | 0.69 | 0.6970 | |
|
| 0.3239 | 6.0 | 258 | 0.8941 | 0.69 | 0.7013 | |
|
| 0.2709 | 7.0 | 301 | 0.8975 | 0.68 | 0.6907 | |
|
| 0.2011 | 8.0 | 344 | 0.9745 | 0.7 | 0.7120 | |
|
| 0.1795 | 9.0 | 387 | 1.0128 | 0.7 | 0.7120 | |
|
| 0.158 | 10.0 | 430 | 1.0069 | 0.69 | 0.7005 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|