|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
base_model: xlm-roberta-large |
|
model-index: |
|
- name: fine-tuned-NLI-indonesian-with-xlm-roberta-large |
|
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. --> |
|
|
|
# fine-tuned-NLI-indonesian-with-xlm-roberta-large |
|
|
|
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2112 |
|
- Accuracy: 0.9463 |
|
- F1: 0.9463 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 128 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.7348 | 0.49 | 72 | 0.6119 | 0.6584 | 0.6544 | |
|
| 0.5955 | 0.99 | 144 | 0.2496 | 0.8959 | 0.8959 | |
|
| 0.2352 | 1.49 | 216 | 0.1968 | 0.9169 | 0.9169 | |
|
| 0.1987 | 1.98 | 288 | 0.1773 | 0.9267 | 0.9265 | |
|
| 0.1315 | 2.48 | 360 | 0.1585 | 0.9437 | 0.9437 | |
|
| 0.1206 | 2.97 | 432 | 0.1540 | 0.9411 | 0.9411 | |
|
| 0.0821 | 3.47 | 504 | 0.1861 | 0.9470 | 0.9470 | |
|
| 0.0782 | 3.97 | 576 | 0.1791 | 0.9503 | 0.9503 | |
|
| 0.0743 | 4.47 | 648 | 0.1801 | 0.9476 | 0.9476 | |
|
| 0.0691 | 4.96 | 720 | 0.1902 | 0.9463 | 0.9463 | |
|
| 0.0569 | 5.46 | 792 | 0.2112 | 0.9463 | 0.9463 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.2.0 |
|
- Tokenizers 0.13.2 |
|
|
