Downloads · 30 days
14
24% of all-time downloads
intfloat-multilingual-e5-small-arabic-fp16
abdulrahman-nuzha/intfloat-multilingual-e5-small-arabic-fp16
intfloat-multilingual-e5-small-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
59
Public
Parameters
118M
493 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors471 MB · 95%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025
- SHA
- 823ac238
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-multilingual-e5-small-arabic-fp16
This model is a fine-tuned version of intfloat/multilingual-e5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5545
- Accuracy: 0.7845
- Precision: 0.7877
- Recall: 0.7845
- F1: 0.7855
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 |
|---|---|---|---|---|---|---|---|
| 1.1004 | 0.3636 | 50 | 1.0937 | 0.4409 | 0.5501 | 0.4409 | 0.2840 |
| 1.0836 | 0.7273 | 100 | 1.0569 | 0.4923 | 0.7472 | 0.4923 | 0.3721 |
| 1.0058 | 1.0873 | 150 | 0.9185 | 0.6682 | 0.7418 | 0.6682 | 0.5839 |
| 0.8875 | 1.4509 | 200 | 0.8000 | 0.7191 | 0.7297 | 0.7191 | 0.6883 |
| 0.7929 | 1.8145 | 250 | 0.7344 | 0.7436 | 0.7441 | 0.7436 | 0.7432 |
| 0.7229 | 2.1745 | 300 | 0.6749 | 0.7573 | 0.7585 | 0.7573 | 0.7575 |
| 0.6733 | 2.5382 | 350 | 0.6474 | 0.7677 | 0.7692 | 0.7677 | 0.7613 |
| 0.6496 | 2.9018 | 400 | 0.6064 | 0.7805 | 0.7852 | 0.7805 | 0.7803 |
| 0.5981 | 3.2618 | 450 | 0.5917 | 0.7782 | 0.7835 | 0.7782 | 0.7779 |
| 0.5646 | 3.6255 | 500 | 0.5961 | 0.7755 | 0.7812 | 0.7755 | 0.7773 |
| 0.5663 | 3.9891 | 550 | 0.5629 | 0.7891 | 0.7880 | 0.7891 | 0.7884 |
| 0.5179 | 4.3491 | 600 | 0.5673 | 0.7905 | 0.7900 | 0.7905 | 0.7880 |
| 0.5167 | 4.7127 | 650 | 0.5993 | 0.7618 | 0.7787 | 0.7618 | 0.7657 |
| 0.4984 | 5.0727 | 700 | 0.5545 | 0.7845 | 0.7877 | 0.7845 | 0.7855 |
| 0.4905 | 5.4364 | 750 | 0.5496 | 0.7936 | 0.7926 | 0.7936 | 0.7926 |
| 0.474 | 5.8 | 800 | 0.5585 | 0.7832 | 0.7842 | 0.7832 | 0.7836 |
| 0.457 | 6.16 | 850 | 0.5726 | 0.785 | 0.7876 | 0.785 | 0.7860 |
| 0.4471 | 6.5236 | 900 | 0.5530 | 0.7886 | 0.7873 | 0.7886 | 0.7877 |
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