|
--- |
|
license: cc-by-4.0 |
|
base_model: vesteinn/DanskBERT |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: MeMo_BERT-SA_DanskBERT |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# MeMo_BERT-SA_DanskBERT |
|
|
|
This model is a fine-tuned version of [vesteinn/DanskBERT](https://huggingface.co./vesteinn/DanskBERT) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8561 |
|
- F1-score: 0.8037 |
|
|
|
## 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: 5e-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 |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1-score | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 265 | 0.7133 | 0.7595 | |
|
| 0.7319 | 2.0 | 530 | 0.7466 | 0.7937 | |
|
| 0.7319 | 3.0 | 795 | 0.7983 | 0.7609 | |
|
| 0.3709 | 4.0 | 1060 | 1.0861 | 0.7859 | |
|
| 0.3709 | 5.0 | 1325 | 1.3603 | 0.7637 | |
|
| 0.1632 | 6.0 | 1590 | 1.3124 | 0.7835 | |
|
| 0.1632 | 7.0 | 1855 | 1.6351 | 0.7432 | |
|
| 0.0846 | 8.0 | 2120 | 1.4934 | 0.7842 | |
|
| 0.0846 | 9.0 | 2385 | 1.5827 | 0.7891 | |
|
| 0.0438 | 10.0 | 2650 | 1.8168 | 0.7695 | |
|
| 0.0438 | 11.0 | 2915 | 1.7212 | 0.7837 | |
|
| 0.0149 | 12.0 | 3180 | 1.7602 | 0.7906 | |
|
| 0.0149 | 13.0 | 3445 | 1.8375 | 0.7869 | |
|
| 0.0152 | 14.0 | 3710 | 1.9152 | 0.7768 | |
|
| 0.0152 | 15.0 | 3975 | 1.9085 | 0.7918 | |
|
| 0.0049 | 16.0 | 4240 | 1.9808 | 0.7835 | |
|
| 0.0094 | 17.0 | 4505 | 1.8629 | 0.8016 | |
|
| 0.0094 | 18.0 | 4770 | 1.8561 | 0.8037 | |
|
| 0.0027 | 19.0 | 5035 | 1.9061 | 0.7939 | |
|
| 0.0027 | 20.0 | 5300 | 1.9370 | 0.7898 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|