Downloads · 30 days
5
19% of all-time downloads
intfloat-e5-base-arabic-fp16
abdulrahman-nuzha/intfloat-e5-base-arabic-fp16
intfloat-e5-base-arabic-fp16 is a text classification model from abdulrahman-nuzha. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
27
Public
Parameters
109M
438 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025
- SHA
- a9fce895
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
intfloat-e5-base-arabic-fp16
This model is a fine-tuned version of intfloat/e5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7482
- Accuracy: 0.6909
- Precision: 0.6879
- Recall: 0.6909
- F1: 0.6881
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.3
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.0832 | 0.3636 | 50 | 1.0122 | 0.49 | 0.6672 | 0.49 | 0.3741 |
| 0.9697 | 0.7273 | 100 | 0.8935 | 0.6073 | 0.5817 | 0.6073 | 0.5493 |
| 0.8744 | 1.0873 | 150 | 0.8016 | 0.6636 | 0.6552 | 0.6636 | 0.6272 |
| 0.8115 | 1.4509 | 200 | 0.7482 | 0.6909 | 0.6879 | 0.6909 | 0.6881 |
| 0.7757 | 1.8145 | 250 | 0.8217 | 0.6482 | 0.6747 | 0.6482 | 0.6500 |
| 0.7566 | 2.1745 | 300 | 0.7877 | 0.6518 | 0.6874 | 0.6518 | 0.6610 |
| 0.7325 | 2.5382 | 350 | 0.8127 | 0.6436 | 0.6968 | 0.6436 | 0.6553 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025