metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: fine_tuned_mix400k_arabert
results: []
fine_tuned_mix400k_arabert
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1851
- Accuracy: 0.9674
- Precision: 0.9835
- Recall: 0.9723
- F1: 0.9778
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: 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 | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.113 | 1.0 | 42279 | 0.1089 | 0.9541 | 0.9962 | 0.9414 | 0.9680 |
| 0.0957 | 2.0 | 84558 | 0.1094 | 0.9639 | 0.9869 | 0.9638 | 0.9752 |
| 0.0833 | 3.0 | 126837 | 0.1061 | 0.9641 | 0.9900 | 0.9611 | 0.9753 |
| 0.0691 | 4.0 | 169116 | 0.1558 | 0.9677 | 0.9845 | 0.9716 | 0.9780 |
| 0.0552 | 5.0 | 211395 | 0.1193 | 0.9676 | 0.9843 | 0.9717 | 0.9780 |
| 0.0411 | 6.0 | 253674 | 0.1851 | 0.9674 | 0.9835 | 0.9723 | 0.9778 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1