metadata
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: []
lora_fine_tuned_copa_sloberta
This model is a fine-tuned version of EMBEDDIA/sloberta on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6931
- Accuracy: 0.55
- F1: 0.5509
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 |
|---|---|---|---|---|---|
| 0.7011 | 1.0 | 50 | 0.6931 | 0.52 | 0.5188 |
| 0.6953 | 2.0 | 100 | 0.6931 | 0.59 | 0.5895 |
| 0.6981 | 3.0 | 150 | 0.6931 | 0.57 | 0.5704 |
| 0.6978 | 4.0 | 200 | 0.6931 | 0.55 | 0.5495 |
| 0.692 | 5.0 | 250 | 0.6931 | 0.54 | 0.5411 |
| 0.7014 | 6.0 | 300 | 0.6931 | 0.48 | 0.48 |
| 0.6928 | 7.0 | 350 | 0.6931 | 0.5 | 0.5012 |
| 0.6953 | 8.0 | 400 | 0.6931 | 0.55 | 0.5509 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1