|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: xlm-roberta-base |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: loha_fine_tuned_rte_XLMroberta |
|
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. --> |
|
|
|
# loha_fine_tuned_rte_XLMroberta |
|
|
|
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.4748 |
|
- Accuracy: 0.6897 |
|
- F1: 0.6873 |
|
|
|
## 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: 0.003 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- training_steps: 400 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:| |
|
| 0.8438 | 1.7241 | 50 | 0.7276 | 0.4138 | 0.2422 | |
|
| 0.7427 | 3.4483 | 100 | 0.6836 | 0.5862 | 0.4333 | |
|
| 0.6788 | 5.1724 | 150 | 0.9009 | 0.4828 | 0.3781 | |
|
| 0.5085 | 6.8966 | 200 | 1.6699 | 0.5172 | 0.4944 | |
|
| 0.2264 | 8.6207 | 250 | 2.0941 | 0.6207 | 0.6179 | |
|
| 0.094 | 10.3448 | 300 | 2.0207 | 0.6897 | 0.6687 | |
|
| 0.0286 | 12.0690 | 350 | 2.3929 | 0.6552 | 0.6491 | |
|
| 0.004 | 13.7931 | 400 | 2.4748 | 0.6897 | 0.6873 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
