---
library_name: transformers
base_model: UBC-NLP/MARBERT
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: MARBERT-fold5
  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. -->

# MARBERT-fold5

This model is a fine-tuned version of [UBC-NLP/MARBERT](https://huggingface.co/UBC-NLP/MARBERT) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1994
- Accuracy: 0.7917
- Macro F1: 0.7921
- Weighted F1: 0.7917
- F1 Pro: 0.7850
- F1 Against: 0.7874
- F1 Neutral: 0.8039

## 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: 42
- optimizer: Use OptimizerNames.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: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 | F1 Pro | F1 Against | F1 Neutral |
|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|:------:|:----------:|:----------:|
| 0.9663        | 1.1628 | 50   | 0.7450          | 0.7143   | 0.7149   | 0.7149      | 0.7216 | 0.7101     | 0.7129     |
| 0.5286        | 2.3256 | 100  | 0.6924          | 0.7381   | 0.7381   | 0.7379      | 0.7586 | 0.7179     | 0.7379     |
| 0.2872        | 3.4884 | 150  | 0.7109          | 0.7619   | 0.7620   | 0.7628      | 0.7677 | 0.7769     | 0.7414     |
| 0.1544        | 4.6512 | 200  | 0.9794          | 0.7679   | 0.7676   | 0.7677      | 0.7611 | 0.7742     | 0.7677     |
| 0.1275        | 5.8140 | 250  | 1.1354          | 0.7619   | 0.7626   | 0.7622      | 0.7748 | 0.7438     | 0.7692     |
| 0.0587        | 6.9767 | 300  | 1.1990          | 0.7917   | 0.7921   | 0.7917      | 0.7850 | 0.7874     | 0.8039     |
| 0.0195        | 8.1395 | 350  | 1.3248          | 0.7738   | 0.7744   | 0.7738      | 0.7719 | 0.7627     | 0.7885     |
| 0.0241        | 9.3023 | 400  | 1.3347          | 0.7798   | 0.7803   | 0.7799      | 0.7719 | 0.7769     | 0.7921     |


### Framework versions

- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2