metadata
library_name: transformers
license: mit
base_model: gerulata/slovakbert
tags:
- generated_from_trainer
model-index:
- name: lease_sk_ner_emph_bi
results: []
lease_sk_ner_emph_bi
This model is a fine-tuned version of gerulata/slovakbert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0441
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 1334 | 0.0253 |
| 0.0506 | 2.0 | 2668 | 0.0222 |
| 0.0102 | 3.0 | 4002 | 0.0250 |
| 0.0102 | 4.0 | 5336 | 0.0271 |
| 0.0062 | 5.0 | 6670 | 0.0276 |
| 0.0047 | 6.0 | 8004 | 0.0287 |
| 0.0047 | 7.0 | 9338 | 0.0333 |
| 0.0033 | 8.0 | 10672 | 0.0333 |
| 0.0027 | 9.0 | 12006 | 0.0345 |
| 0.0027 | 10.0 | 13340 | 0.0387 |
| 0.0019 | 11.0 | 14674 | 0.0374 |
| 0.0016 | 12.0 | 16008 | 0.0405 |
| 0.0016 | 13.0 | 17342 | 0.0418 |
| 0.0012 | 14.0 | 18676 | 0.0440 |
| 0.001 | 15.0 | 20010 | 0.0441 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1