---
library_name: transformers
license: cc-by-4.0
base_model: vesteinn/DanskBERT
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: danskbert_indirect_speech
  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. -->

# danskbert_indirect_speech

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:
- Accuracy: 0.6577
- Precision: 0.6982
- Recall: 0.6577
- F1: 0.6486
- Loss: 0.8890

## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Accuracy | Precision | Recall | F1     | Validation Loss |
|:-------------:|:-----:|:----:|:--------:|:---------:|:------:|:------:|:---------------:|
| No log        | 1.0   | 13   | 0.5310   | 0.2819    | 0.5310 | 0.3683 | 1.1024          |
| No log        | 2.0   | 26   | 0.5329   | 0.5102    | 0.5329 | 0.3785 | 0.9938          |
| No log        | 3.0   | 39   | 0.4206   | 0.5351    | 0.4206 | 0.2658 | 1.1366          |
| No log        | 4.0   | 52   | 0.6118   | 0.6521    | 0.6118 | 0.5410 | 0.8100          |
| No log        | 5.0   | 65   | 0.6691   | 0.6700    | 0.6691 | 0.6430 | 0.7886          |
| No log        | 6.0   | 78   | 0.6214   | 0.6756    | 0.6214 | 0.5529 | 0.8290          |
| No log        | 7.0   | 91   | 0.6182   | 0.7008    | 0.6182 | 0.5988 | 0.9558          |
| No log        | 8.0   | 104  | 0.4476   | 0.7400    | 0.4476 | 0.3122 | 1.3500          |
| No log        | 9.0   | 117  | 0.5997   | 0.7008    | 0.5997 | 0.5757 | 1.0460          |
| No log        | 10.0  | 130  | 0.5717   | 0.7244    | 0.5717 | 0.5303 | 1.0733          |
| No log        | 11.0  | 143  | 0.6566   | 0.7000    | 0.6566 | 0.6473 | 0.8322          |
| No log        | 12.0  | 156  | 0.6562   | 0.7050    | 0.6562 | 0.6488 | 0.8855          |
| No log        | 13.0  | 169  | 0.6711   | 0.6900    | 0.6711 | 0.6647 | 0.8431          |
| No log        | 14.0  | 182  | 0.6208   | 0.7001    | 0.6208 | 0.6025 | 0.9622          |
| No log        | 15.0  | 195  | 0.6823   | 0.7000    | 0.6823 | 0.6758 | 0.7811          |
| No log        | 16.0  | 208  | 0.6611   | 0.6971    | 0.6611 | 0.6533 | 0.8808          |
| No log        | 17.0  | 221  | 0.6677   | 0.6960    | 0.6677 | 0.6604 | 0.8277          |
| No log        | 18.0  | 234  | 0.6579   | 0.6991    | 0.6579 | 0.6488 | 0.8897          |
| No log        | 18.48 | 240  | 0.6577   | 0.6982    | 0.6577 | 0.6486 | 0.8890          |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Tokenizers 0.21.0