metadata
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_copa_sloberta
results: []
loha_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: 0.6929
- Accuracy: 0.51
- F1: 0.5104
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 |
|---|---|---|---|---|---|
| 0.7001 | 1.0 | 50 | 0.6935 | 0.47 | 0.4711 |
| 0.6932 | 2.0 | 100 | 0.6931 | 0.48 | 0.48 |
| 0.6913 | 3.0 | 150 | 0.6928 | 0.51 | 0.5112 |
| 0.7055 | 4.0 | 200 | 0.6927 | 0.48 | 0.48 |
| 0.6902 | 5.0 | 250 | 0.6926 | 0.5 | 0.4988 |
| 0.6981 | 6.0 | 300 | 0.6930 | 0.47 | 0.4694 |
| 0.7011 | 7.0 | 350 | 0.6930 | 0.5 | 0.4988 |
| 0.6894 | 8.0 | 400 | 0.6929 | 0.51 | 0.5104 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1