|
---
|
|
license: mit
|
|
library_name: peft
|
|
tags:
|
|
- generated_from_trainer
|
|
base_model: xlm-roberta-base
|
|
metrics:
|
|
- accuracy
|
|
- f1
|
|
model-index:
|
|
- name: loha_fine_tuned_copa_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_copa_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: 0.6929 |
|
- Accuracy: 0.57 |
|
- F1: 0.5695 |
|
|
|
## 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: 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.6981 | 1.0 | 50 | 0.6929 | 0.56 | 0.5589 | |
|
| 0.701 | 2.0 | 100 | 0.6929 | 0.56 | 0.5589 | |
|
| 0.6932 | 3.0 | 150 | 0.6929 | 0.57 | 0.5695 | |
|
| 0.6896 | 4.0 | 200 | 0.6929 | 0.57 | 0.5695 | |
|
| 0.6968 | 5.0 | 250 | 0.6929 | 0.57 | 0.5695 | |
|
| 0.6979 | 6.0 | 300 | 0.6929 | 0.57 | 0.5695 | |
|
| 0.6984 | 7.0 | 350 | 0.6929 | 0.57 | 0.5695 | |
|
| 0.6999 | 8.0 | 400 | 0.6929 | 0.57 | 0.5695 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
