|
--- |
|
license: cc-by-sa-4.0 |
|
base_model: EMBEDDIA/sloberta |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: 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. --> |
|
|
|
# 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: 0.6898 |
|
- Accuracy: 0.6897 |
|
- F1: 0.6912 |
|
|
|
## 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 | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:| |
|
| 0.7035 | 1.7241 | 50 | 0.7322 | 0.4138 | 0.2422 | |
|
| 0.7032 | 3.4483 | 100 | 0.6935 | 0.4138 | 0.2422 | |
|
| 0.6998 | 5.1724 | 150 | 0.7021 | 0.4138 | 0.2422 | |
|
| 0.697 | 6.8966 | 200 | 0.6828 | 0.5862 | 0.4333 | |
|
| 0.6968 | 8.6207 | 250 | 0.6837 | 0.5862 | 0.4333 | |
|
| 0.6965 | 10.3448 | 300 | 0.6897 | 0.5862 | 0.4333 | |
|
| 0.6934 | 12.0690 | 350 | 0.6869 | 0.5862 | 0.4333 | |
|
| 0.6878 | 13.7931 | 400 | 0.6898 | 0.6897 | 0.6912 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
