<!-- 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. -->
finetuned-ner-hadith-fistsubisa1
This model is a fine-tuned version of hatmimoha/arabic-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4707
- Precision: 0.3641
- Recall: 0.7
- F1: 0.4790
- Accuracy: 0.8111
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: 2
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 312 | 0.4445 | 0.3683 | 0.6555 | 0.4716 | 0.8105 |
0.5169 | 2.0 | 624 | 0.4690 | 0.3528 | 0.6956 | 0.4682 | 0.8076 |
0.5169 | 3.0 | 936 | 0.4314 | 0.3405 | 0.6781 | 0.4534 | 0.8099 |
0.3852 | 4.0 | 1248 | 0.4360 | 0.3509 | 0.6774 | 0.4623 | 0.8132 |
0.3269 | 5.0 | 1560 | 0.4707 | 0.3641 | 0.7 | 0.4790 | 0.8111 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0
- Datasets 2.1.0
- Tokenizers 0.12.1