Downloads · 30 days
5
14% of all-time downloads
intfloat-e5-small-v2-arabic-fp16
abdulrahman-nuzha/intfloat-e5-small-v2-arabic-fp16
intfloat-e5-small-v2-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
37
Public
Parameters
33.4M
133 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors133 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025
- SHA
- 5ff9ec9d
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-small-v2-arabic-fp16
This model is a fine-tuned version of intfloat/e5-small-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7284
- Accuracy: 0.7109
- Precision: 0.7059
- Recall: 0.7109
- F1: 0.6922
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 |
|---|---|---|---|---|---|---|---|
| 1.0988 | 0.3636 | 50 | 1.0884 | 0.4373 | 0.7539 | 0.4373 | 0.2661 |
| 1.0735 | 0.7273 | 100 | 1.0306 | 0.5786 | 0.6758 | 0.5786 | 0.5022 |
| 0.986 | 1.0873 | 150 | 0.9164 | 0.6264 | 0.7095 | 0.6264 | 0.5473 |
| 0.9137 | 1.4509 | 200 | 0.8738 | 0.635 | 0.7249 | 0.635 | 0.5536 |
| 0.8973 | 1.8145 | 250 | 0.8504 | 0.6459 | 0.5992 | 0.6459 | 0.5891 |
| 0.8622 | 2.1745 | 300 | 0.8124 | 0.6732 | 0.6575 | 0.6732 | 0.6336 |
| 0.8328 | 2.5382 | 350 | 0.7966 | 0.6782 | 0.6775 | 0.6782 | 0.6744 |
| 0.8225 | 2.9018 | 400 | 0.7772 | 0.6909 | 0.6851 | 0.6909 | 0.6826 |
| 0.7789 | 3.2618 | 450 | 0.7731 | 0.6836 | 0.6951 | 0.6836 | 0.6808 |
| 0.7832 | 3.6255 | 500 | 0.7850 | 0.6645 | 0.6903 | 0.6645 | 0.6727 |
| 0.7715 | 3.9891 | 550 | 0.7558 | 0.6936 | 0.6945 | 0.6936 | 0.6936 |
| 0.7354 | 4.3491 | 600 | 0.7284 | 0.7109 | 0.7059 | 0.7109 | 0.6922 |
| 0.7288 | 4.7127 | 650 | 0.7168 | 0.7095 | 0.7073 | 0.7095 | 0.7069 |
| 0.7149 | 5.0727 | 700 | 0.7276 | 0.7023 | 0.7072 | 0.7023 | 0.7023 |
| 0.7073 | 5.4364 | 750 | 0.7043 | 0.715 | 0.7110 | 0.715 | 0.7100 |
| 0.698 | 5.8 | 800 | 0.7291 | 0.7118 | 0.7028 | 0.7118 | 0.7039 |
| 0.6863 | 6.16 | 850 | 0.7169 | 0.7073 | 0.7077 | 0.7073 | 0.7075 |
| 0.6754 | 6.5236 | 900 | 0.7287 | 0.6977 | 0.7042 | 0.6977 | 0.7004 |
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