Downloads · 30 days
7
22% of all-time downloads
muril-focal-loss
Uni-Joseph/muril-focal-loss
muril-focal-loss is a text classification model from Uni-Joseph. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
32
Public
Parameters
238M
950 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors950 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026
- SHA
- 00e14a6e
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. -->
muril-focal-loss
This model is a fine-tuned version of google/muril-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0465
- Accuracy: 0.8592
- Macro F1: 0.7624
- Weighted F1: 0.8608
- Negative Recall: 0.6296
- Positive Recall: 0.9081
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: 32
- 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: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 | Negative Recall | Positive Recall |
|---|---|---|---|---|---|---|---|---|
| 0.0436 | 1.0 | 1506 | 0.0443 | 0.8467 | 0.7055 | 0.8378 | 0.4395 | 0.9334 |
| 0.0395 | 2.0 | 3012 | 0.0415 | 0.7840 | 0.7101 | 0.8051 | 0.7946 | 0.7818 |
| 0.0346 | 3.0 | 4518 | 0.0388 | 0.8464 | 0.7601 | 0.8534 | 0.7025 | 0.8770 |
| 0.0298 | 4.0 | 6024 | 0.0448 | 0.8504 | 0.7593 | 0.8554 | 0.6699 | 0.8888 |
| 0.0231 | 5.0 | 7530 | 0.0465 | 0.8592 | 0.7624 | 0.8608 | 0.6296 | 0.9081 |
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.23.1
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Sep 16, 2026
- Updated
- Sep 16, 2026