|
--- |
|
license: mit |
|
base_model: xlm-roberta-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: xlmr-large-nli-indoindo |
|
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. --> |
|
|
|
# xlmr-large-nli-indoindo |
|
|
|
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3131 |
|
- Accuracy: 0.8584 |
|
- Precision: 0.8584 |
|
- Recall: 0.8584 |
|
- F1 Score: 0.8585 |
|
|
|
## 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: 3e-06 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:| |
|
| 1.449 | 1.0 | 10330 | 1.2228 | 0.7838 | 0.7838 | 0.7838 | 0.7810 | |
|
| 1.2575 | 2.0 | 20660 | 1.1182 | 0.8257 | 0.8257 | 0.8257 | 0.8273 | |
|
| 0.8123 | 3.0 | 30990 | 1.1538 | 0.8489 | 0.8489 | 0.8489 | 0.8488 | |
|
| 0.6541 | 4.0 | 41320 | 1.1288 | 0.8562 | 0.8562 | 0.8562 | 0.8558 | |
|
| 0.3653 | 5.0 | 51650 | 1.2424 | 0.8543 | 0.8543 | 0.8543 | 0.8544 | |
|
| 0.3436 | 6.0 | 61980 | 1.3131 | 0.8584 | 0.8584 | 0.8584 | 0.8585 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.3 |
|
|
