lora_fine_tuned_rte_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: 0.6917
- Accuracy: 0.5517
- F1: 0.5539
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 |
---|---|---|---|---|---|
0.6987 | 1.7241 | 50 | 0.6974 | 0.4483 | 0.3134 |
0.6918 | 3.4483 | 100 | 0.6891 | 0.5862 | 0.4333 |
0.694 | 5.1724 | 150 | 0.6964 | 0.3793 | 0.2764 |
0.6919 | 6.8966 | 200 | 0.6971 | 0.3793 | 0.2764 |
0.6904 | 8.6207 | 250 | 0.6930 | 0.4483 | 0.4443 |
0.6936 | 10.3448 | 300 | 0.6923 | 0.4828 | 0.4828 |
0.6901 | 12.0690 | 350 | 0.6913 | 0.6552 | 0.6491 |
0.6874 | 13.7931 | 400 | 0.6917 | 0.5517 | 0.5539 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for lenatr99/lora_fine_tuned_rte_sloberta
Base model
EMBEDDIA/sloberta
Adapter
this model