|
--- |
|
license: mit |
|
base_model: FacebookAI/xlm-roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: xlm_70k_co_vn |
|
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_70k_co_vn |
|
|
|
This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1934 |
|
- Accuracy: 0.9679 |
|
- F1: 0.9680 |
|
|
|
## 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: cosine_with_restarts |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:| |
|
| 0.2054 | 1.0 | 1719 | 0.1449 | 0.9595 | 0.9599 | |
|
| 0.1226 | 2.0 | 3438 | 0.1261 | 0.9638 | 0.9641 | |
|
| 0.1038 | 3.0 | 5157 | 0.1055 | 0.9682 | 0.9684 | |
|
| 0.0856 | 4.0 | 6876 | 0.1107 | 0.9676 | 0.9678 | |
|
| 0.0732 | 5.0 | 8595 | 0.1240 | 0.9680 | 0.9680 | |
|
| 0.0595 | 6.0 | 10314 | 0.1457 | 0.9679 | 0.9679 | |
|
| 0.0494 | 7.0 | 12033 | 0.1931 | 0.9667 | 0.9668 | |
|
| 0.0425 | 8.0 | 13752 | 0.1772 | 0.9672 | 0.9674 | |
|
| 0.0375 | 9.0 | 15471 | 0.1867 | 0.9683 | 0.9684 | |
|
| 0.034 | 10.0 | 17190 | 0.1934 | 0.9679 | 0.9680 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
