Downloads · 30 days
6
9% of all-time downloads
marbert-arabic-tweet-sentiment-cosine
3liel/marbert-arabic-tweet-sentiment-cosine
marbert-arabic-tweet-sentiment-cosine is a text classification model from 3liel. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
69
Public
Parameters
163M
3.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors651 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Aug 28, 2026
- Updated
- Aug 28, 2026
- SHA
- f3c0cea4
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. -->
marbert-arabic-tweet-sentiment-cosine
This model is a fine-tuned version of UBC-NLP/MARBERTv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8414
- Accuracy: 0.7284
- F1: 0.7297
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 115 | 1.2740 | 0.75 | 0.7548 |
| No log | 2.0 | 230 | 1.5809 | 0.7253 | 0.7299 |
| No log | 3.0 | 345 | 1.6912 | 0.7407 | 0.7347 |
| No log | 4.0 | 460 | 1.7265 | 0.7377 | 0.7435 |
| 0.0341 | 5.0 | 575 | 1.8414 | 0.7284 | 0.7297 |
Framework versions
- Transformers 5.15.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Created
- Aug 28, 2026
- Updated
- Aug 28, 2026