|
---
|
|
license: cc-by-sa-4.0
|
|
library_name: peft
|
|
tags:
|
|
- generated_from_trainer
|
|
base_model: EMBEDDIA/sloberta
|
|
metrics:
|
|
- accuracy
|
|
- f1
|
|
model-index:
|
|
- name: lora_fine_tuned_copa_sloberta
|
|
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. --> |
|
|
|
# lora_fine_tuned_copa_sloberta |
|
|
|
This model is a fine-tuned version of [EMBEDDIA/sloberta](https://huggingface.co./EMBEDDIA/sloberta) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6931 |
|
- Accuracy: 0.47 |
|
- F1: 0.4533 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| 0.698 | 1.0 | 50 | 0.6931 | 0.47 | 0.4606 | |
|
| 0.6955 | 2.0 | 100 | 0.6931 | 0.5 | 0.4861 | |
|
| 0.7099 | 3.0 | 150 | 0.6931 | 0.49 | 0.4838 | |
|
| 0.6962 | 4.0 | 200 | 0.6931 | 0.58 | 0.5713 | |
|
| 0.702 | 5.0 | 250 | 0.6931 | 0.44 | 0.4409 | |
|
| 0.6869 | 6.0 | 300 | 0.6931 | 0.54 | 0.5332 | |
|
| 0.7083 | 7.0 | 350 | 0.6931 | 0.57 | 0.5564 | |
|
| 0.6959 | 8.0 | 400 | 0.6931 | 0.47 | 0.4533 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
