|
--- |
|
license: cc-by-sa-4.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: EMBEDDIA/sloberta |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: loha_fine_tuned_rte_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. --> |
|
|
|
# loha_fine_tuned_rte_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: 0.6925 |
|
- Accuracy: 0.5172 |
|
- F1: 0.5207 |
|
|
|
## 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 |
|
- 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 | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:| |
|
| 0.6991 | 1.7241 | 50 | 0.6870 | 0.5862 | 0.4333 | |
|
| 0.6913 | 3.4483 | 100 | 0.6865 | 0.5862 | 0.4333 | |
|
| 0.6957 | 5.1724 | 150 | 0.6913 | 0.6897 | 0.6687 | |
|
| 0.6913 | 6.8966 | 200 | 0.6937 | 0.4483 | 0.4145 | |
|
| 0.6909 | 8.6207 | 250 | 0.6931 | 0.4483 | 0.4443 | |
|
| 0.6946 | 10.3448 | 300 | 0.6929 | 0.4138 | 0.4138 | |
|
| 0.6925 | 12.0690 | 350 | 0.6924 | 0.5517 | 0.5539 | |
|
| 0.6891 | 13.7931 | 400 | 0.6925 | 0.5172 | 0.5207 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |