| --- |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - accuracy |
| model-index: |
| - name: train |
| 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. --> |
|
|
| # train |
|
|
| This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.9948 |
| - Macro F1: 0.7856 |
| - Precision: 0.7820 |
| - Recall: 0.7956 |
| - Kappa: 0.6940 |
| - Accuracy: 0.7956 |
|
|
| ## 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: 128 |
| - seed: 25 |
| - gradient_accumulation_steps: 2 |
| - total_train_batch_size: 32 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 15 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Macro F1 | Precision | Recall | Kappa | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:--------:| |
| | No log | 1.0 | 101 | 1.1562 | 0.6031 | 0.5561 | 0.7044 | 0.4967 | 0.7044 | |
| | No log | 2.0 | 203 | 0.9119 | 0.7151 | 0.7107 | 0.7672 | 0.6236 | 0.7672 | |
| | No log | 3.0 | 304 | 0.8493 | 0.7280 | 0.7139 | 0.7734 | 0.6381 | 0.7734 | |
| | No log | 4.0 | 406 | 0.8087 | 0.7455 | 0.7632 | 0.7648 | 0.6421 | 0.7648 | |
| | 0.9431 | 5.0 | 507 | 0.7735 | 0.7779 | 0.7741 | 0.7931 | 0.6858 | 0.7931 | |
| | 0.9431 | 6.0 | 609 | 0.8201 | 0.7753 | 0.7735 | 0.7869 | 0.6797 | 0.7869 | |
| | 0.9431 | 7.0 | 710 | 0.8564 | 0.7886 | 0.7883 | 0.8017 | 0.7004 | 0.8017 | |
| | 0.9431 | 8.0 | 812 | 0.8712 | 0.7799 | 0.7754 | 0.7894 | 0.6854 | 0.7894 | |
| | 0.9431 | 9.0 | 913 | 0.9142 | 0.7775 | 0.7751 | 0.7869 | 0.6811 | 0.7869 | |
| | 0.2851 | 10.0 | 1015 | 0.9007 | 0.7820 | 0.7764 | 0.7943 | 0.6913 | 0.7943 | |
| | 0.2851 | 11.0 | 1116 | 0.9425 | 0.7859 | 0.7825 | 0.7956 | 0.6940 | 0.7956 | |
| | 0.2851 | 12.0 | 1218 | 0.9798 | 0.7815 | 0.7797 | 0.7906 | 0.6869 | 0.7906 | |
| | 0.2851 | 13.0 | 1319 | 0.9895 | 0.7895 | 0.7860 | 0.7993 | 0.7003 | 0.7993 | |
| | 0.2851 | 14.0 | 1421 | 0.9872 | 0.7854 | 0.7813 | 0.7943 | 0.6935 | 0.7943 | |
| | 0.1273 | 14.93 | 1515 | 0.9948 | 0.7856 | 0.7820 | 0.7956 | 0.6940 | 0.7956 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.30.2 |
| - Pytorch 2.0.1+cu118 |
| - Tokenizers 0.13.3 |
| |
