---
tags:
- generated_from_trainer
metrics:
- accuracy
- recall
- precision
model-index:
- name: MARBERT-QADI
  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-QADI

This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0342
- Macro F1: 0.5099
- Accuracy: 0.5138
- Recall: 0.5136
- Precision: 0.6223

## 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: 4e-06
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Macro F1 | Accuracy | Recall | Precision |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:------:|:---------:|
| 0.8588        | 1.0   | 1125  | 0.7883          | 0.7550   | 0.7554   | 0.7552 | 0.7609    |
| 0.7475        | 2.0   | 2250  | 0.7718          | 0.7632   | 0.7634   | 0.7631 | 0.7653    |
| 0.6527        | 3.0   | 3375  | 0.7758          | 0.7668   | 0.7673   | 0.7671 | 0.7679    |
| 0.5654        | 4.0   | 4500  | 0.7845          | 0.7665   | 0.7673   | 0.7671 | 0.7682    |
| 0.5001        | 5.0   | 5625  | 0.8068          | 0.7650   | 0.7663   | 0.7660 | 0.7657    |
| 0.4641        | 6.0   | 6750  | 0.8216          | 0.7647   | 0.7658   | 0.7655 | 0.7650    |
| 0.4049        | 7.0   | 7875  | 0.8393          | 0.7645   | 0.7654   | 0.7649 | 0.7657    |
| 0.3773        | 8.0   | 9000  | 0.8477          | 0.7651   | 0.7657   | 0.7654 | 0.7659    |
| 0.3393        | 9.0   | 10125 | 0.8569          | 0.7663   | 0.7669   | 0.7665 | 0.7670    |
| 0.3383        | 10.0  | 11250 | 0.8589          | 0.7663   | 0.7669   | 0.7666 | 0.7667    |


### Framework versions

- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1