---
library_name: transformers
license: apache-2.0
base_model: PKOBP/polish-roberta-8k
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: mwik-classifier-xd
  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. -->

# mwik-classifier-xd

This model is a fine-tuned version of [PKOBP/polish-roberta-8k](https://huggingface.co/PKOBP/polish-roberta-8k) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1723
- Accuracy: 0.7561
- Precision: 0.7279
- Recall: 0.7561
- F1: 0.7335

## 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: 1e-05
- train_batch_size: 24
- eval_batch_size: 48
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- 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: polynomial
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 8
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| No log        | 1.0   | 40   | 2.6964          | 0.4366   | 0.3391    | 0.4366 | 0.3326 |
| 3.1054        | 2.0   | 80   | 1.8682          | 0.6393   | 0.5160    | 0.6393 | 0.5555 |
| 2.1011        | 3.0   | 120  | 1.4782          | 0.7114   | 0.6120    | 0.7114 | 0.6473 |
| 1.5616        | 4.0   | 160  | 1.2761          | 0.7537   | 0.7102    | 0.7537 | 0.7116 |
| 1.2881        | 5.0   | 200  | 1.1802          | 0.7674   | 0.7394    | 0.7674 | 0.7318 |
| 1.2881        | 6.0   | 240  | 1.1084          | 0.7786   | 0.7529    | 0.7786 | 0.7527 |
| 1.112         | 7.0   | 280  | 1.0741          | 0.7836   | 0.7578    | 0.7836 | 0.7613 |
| 1.0374        | 8.0   | 320  | 1.0621          | 0.7848   | 0.7596    | 0.7848 | 0.7643 |


### Framework versions

- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1