---
library_name: transformers
license: mit
base_model: simpliTax/bert-automap-pbt-fine-tuned
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: category-v6-strict
  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. -->

# category-v6-strict

This model is a fine-tuned version of [simpliTax/bert-automap-pbt-fine-tuned](https://huggingface.co/simpliTax/bert-automap-pbt-fine-tuned) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.9421
- Accuracy: 0.5960
- Macro F1: 0.1895
- Weighted F1: 0.5291

## 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: 13
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|
| 3.8728        | 1.0   | 727  | 2.5961          | 0.4930   | 0.1212   | 0.4187      |
| 2.6532        | 2.0   | 1454 | 2.0727          | 0.5728   | 0.1676   | 0.5043      |
| 1.8412        | 3.0   | 2181 | 1.9421          | 0.5960   | 0.1895   | 0.5291      |


### Framework versions

- Transformers 5.0.0.dev0
- Pytorch 2.9.0+cu126
- Datasets 4.3.0
- Tokenizers 0.22.1