Downloads · 30 days
9
1% of all-time downloads
intfloat-multilingual-e5-large-arabic-fp16
abdulrahman-nuzha/intfloat-multilingual-e5-large-arabic-fp16
intfloat-multilingual-e5-large-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
732
Public
Parameters
560M
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025
- SHA
- 33104619
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-large-arabic-fp16
This model is a fine-tuned version of intfloat/multilingual-e5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4707
- Accuracy: 0.8177
- Precision: 0.8189
- Recall: 0.8177
- F1: 0.8176
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 |
|---|---|---|---|---|---|---|---|
| 1.0811 | 0.3636 | 50 | 0.9500 | 0.57 | 0.7318 | 0.57 | 0.4829 |
| 0.8355 | 0.7273 | 100 | 0.6392 | 0.7605 | 0.7622 | 0.7605 | 0.7510 |
| 0.5786 | 1.0873 | 150 | 0.5154 | 0.7986 | 0.7983 | 0.7986 | 0.7981 |
| 0.508 | 1.4509 | 200 | 0.4863 | 0.8155 | 0.8144 | 0.8155 | 0.8139 |
| 0.4931 | 1.8145 | 250 | 0.4732 | 0.8114 | 0.8102 | 0.8114 | 0.8103 |
| 0.4708 | 2.1745 | 300 | 0.4988 | 0.8164 | 0.8184 | 0.8164 | 0.8163 |
| 0.4146 | 2.5382 | 350 | 0.5011 | 0.8073 | 0.8110 | 0.8073 | 0.8079 |
| 0.4436 | 2.9018 | 400 | 0.4707 | 0.8177 | 0.8189 | 0.8177 | 0.8176 |
| 0.3741 | 3.2618 | 450 | 0.5440 | 0.8 | 0.8042 | 0.8 | 0.8013 |
| 0.3358 | 3.6255 | 500 | 0.5422 | 0.7982 | 0.8063 | 0.7982 | 0.7994 |
| 0.3497 | 3.9891 | 550 | 0.5210 | 0.8105 | 0.8147 | 0.8105 | 0.8102 |
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
- xlm-roberta
- License
- mit
- Created
- Apr 16, 2025
- Updated
- Apr 16, 2025