metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 19levels_52521
results: []
19levels_52521
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9054
- Macro F1: 0.3798
- Macro Precision: 0.3840
- Macro Recall: 0.3883
- Accuracy: 0.5238
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Macro Precision | Macro Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.7168 | 1.0 | 821 | 1.3900 | 0.3710 | 0.3964 | 0.3909 | 0.5166 |
| 1.2221 | 2.0 | 1642 | 1.3667 | 0.3603 | 0.3970 | 0.3625 | 0.5335 |
| 1.02 | 3.0 | 2463 | 1.4292 | 0.3891 | 0.3945 | 0.4063 | 0.5370 |
| 0.7054 | 4.0 | 3284 | 1.5853 | 0.3706 | 0.3779 | 0.3837 | 0.5271 |
| 0.5116 | 5.0 | 4105 | 1.7836 | 0.3813 | 0.3804 | 0.3939 | 0.5240 |
| 0.4122 | 6.0 | 4926 | 1.9054 | 0.3798 | 0.3840 | 0.3883 | 0.5238 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.19.1