---
license: cc-by-sa-4.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: SloBertAA_Top5_WithoutOOC_082023
  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. -->

# SloBertAA_Top5_WithoutOOC_082023

This model is a fine-tuned version of [EMBEDDIA/sloberta](https://huggingface.co/EMBEDDIA/sloberta) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4398
- Accuracy: 0.9478
- F1: 0.9478
- Precision: 0.9481
- Recall: 0.9478

## Other related models

Models fine-tuned on the RTV datasets:

| Base model          | Includes the OOC class? | 5 classes | 10 classes | 20 classes | 50 classes | 100 classes |
| ------------------- | ----------------------- |:---------:|:----------:|:----------:|:----------:|:-----------:|
| SloBERTa            | Yes                     | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top5_WithOOC_082023) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top10_WithOOC_082023) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top20_WithOOC_082023) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top50_WithOOC_082023) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top100_WithOOC_082023) |
| SloBERTa            | No                      | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top5_WithoutOOC_082023) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top10_WithoutOOC_082023) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top20_WithoutOOC_082023) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top50_WithoutOOC_082023) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top100_WithoutOOC_082023) | 
| BERT Multilingual   | Yes                     | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top5_WithOOC_082023_MultilingualBertBase) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top10_WithOOC_082023_MultilingualBertBase) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top20_WithOOC_082023_MultilingualBertBase) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top50_WithOOC_082023_MultilingualBertBase) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top100_WithOOC_082023_MultilingualBertBase) |
| BERT Multilingual   | No                      | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top5_WithoutOOC_082023_MultilingualBertBase) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top10_WithoutOOC_082023_MultilingualBertBase) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top20_WithoutOOC_082023_MultilingualBertBase) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top50_WithoutOOC_082023_MultilingualBertBase) | [link](https://huggingface.co/gregorgabrovsek/SloBertAA_Top100_WithoutOOC_082023_MultilingualBertBase) |

Models fine-tuned on the IMDb datasets:

| Base model          | Includes the OOC class? | 5 classes | 10 classes | 25 classes | 50 classes | 100 classes |
| ------------------- | ----------------------- |:---------:|:----------:|:----------:|:----------:|:-----------:|
| BERT Multilingual   | No                      | [link](https://huggingface.co/gregorgabrovsek/BERT_AA_IMDB_Top5_WithoutOOC_082023_MultilingualBertBase) |[link](https://huggingface.co/gregorgabrovsek/BERT_AA_IMDB_Top10_WithoutOOC_082023_MultilingualBertBase) |[link](https://huggingface.co/gregorgabrovsek/BERT_AA_IMDB_Top25_WithoutOOC_082023_MultilingualBertBase) |[link](https://huggingface.co/gregorgabrovsek/BERT_AA_IMDB_Top50_WithoutOOC_082023_MultilingualBertBase) |[link](https://huggingface.co/gregorgabrovsek/BERT_AA_IMDB_Top100_WithoutOOC_082023_MultilingualBertBase) |

## 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: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.2468        | 1.0   | 8757  | 0.2629          | 0.9194   | 0.9199 | 0.9226    | 0.9194 |
| 0.1864        | 2.0   | 17514 | 0.2340          | 0.9375   | 0.9377 | 0.9386    | 0.9375 |
| 0.1419        | 3.0   | 26271 | 0.2821          | 0.9371   | 0.9374 | 0.9389    | 0.9371 |
| 0.1001        | 4.0   | 35028 | 0.3135          | 0.9408   | 0.9409 | 0.9412    | 0.9408 |
| 0.0727        | 5.0   | 43785 | 0.3584          | 0.9415   | 0.9416 | 0.9423    | 0.9415 |
| 0.057         | 6.0   | 52542 | 0.3552          | 0.9440   | 0.9442 | 0.9450    | 0.9440 |
| 0.0332        | 7.0   | 61299 | 0.4318          | 0.9394   | 0.9396 | 0.9407    | 0.9394 |
| 0.0268        | 8.0   | 70056 | 0.4376          | 0.9442   | 0.9444 | 0.9455    | 0.9442 |
| 0.019         | 9.0   | 78813 | 0.4377          | 0.9444   | 0.9445 | 0.9451    | 0.9444 |
| 0.0181        | 10.0  | 87570 | 0.4398          | 0.9478   | 0.9478 | 0.9481    | 0.9478 |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.8.0
- Datasets 2.10.1
- Tokenizers 0.13.2