metadata
license: apache-2.0
base_model: Mohamedd123321/Arabizi_Checkpoints-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: Arabizi_Checkpoints_vlast
results: []
Arabizi_Checkpoints_vlast
This model is a fine-tuned version of Mohamedd123321/Arabizi_Checkpoints-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8227
- Accuracy: 0.8735
- F1: 0.8735
- Precision: 0.8738
- Recall: 0.8735
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.4446 | 1.7247 | 5000 | 0.8677 | 0.8691 | 0.4791 | 0.8724 | 0.8677 |
| 0.3038 | 3.4495 | 10000 | 0.8694 | 0.8720 | 0.6029 | 0.8771 | 0.8694 |
| 0.2221 | 5.1742 | 15000 | 0.8227 | 0.8735 | 0.8735 | 0.8738 | 0.8735 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.8.0+cu128
- Datasets 5.0.0
- Tokenizers 0.19.1