|
---
|
|
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_cb_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_cb_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: 1.4606 |
|
- Accuracy: 0.3182 |
|
- F1: 0.1536 |
|
|
|
## 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 | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:| |
|
| 0.932 | 3.5714 | 50 | 1.2096 | 0.3182 | 0.1536 | |
|
| 0.745 | 7.1429 | 100 | 1.3888 | 0.3182 | 0.1536 | |
|
| 0.743 | 10.7143 | 150 | 1.4293 | 0.3182 | 0.1536 | |
|
| 0.6881 | 14.2857 | 200 | 1.4559 | 0.3182 | 0.1536 | |
|
| 0.7204 | 17.8571 | 250 | 1.4635 | 0.3182 | 0.1536 | |
|
| 0.7244 | 21.4286 | 300 | 1.4588 | 0.3182 | 0.1536 | |
|
| 0.6949 | 25.0 | 350 | 1.4588 | 0.3182 | 0.1536 | |
|
| 0.7195 | 28.5714 | 400 | 1.4606 | 0.3182 | 0.1536 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.40.1 |
|
- Pytorch 2.1.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
