fine_tuned_boolq_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: 1.8633
- Accuracy: 0.6111
- F1: 0.6255
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 |
---|---|---|---|---|---|
0.6442 | 4.1667 | 50 | 0.5523 | 0.7778 | 0.6806 |
0.3817 | 8.3333 | 100 | 1.0475 | 0.5556 | 0.5902 |
0.0355 | 12.5 | 150 | 1.4581 | 0.6111 | 0.6255 |
0.0098 | 16.6667 | 200 | 1.6364 | 0.6111 | 0.6255 |
0.0065 | 20.8333 | 250 | 1.8167 | 0.6111 | 0.6255 |
0.005 | 25.0 | 300 | 1.8363 | 0.6111 | 0.6255 |
0.0043 | 29.1667 | 350 | 1.8635 | 0.6111 | 0.6255 |
0.004 | 33.3333 | 400 | 1.8633 | 0.6111 | 0.6255 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 18
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for tjasad/fine_tuned_boolq_sloberta
Base model
EMBEDDIA/sloberta
Finetuned
this model