Downloads · 30 days
36
19% of all-time downloads
mmbert-multilingual-20250916-155528
MikeDoes/mmbert-multilingual-20250916-155528
mmbert-multilingual-20250916-155528 is a fill-mask model from MikeDoes. Use it when you need the model to fill a missing word. 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
186
Public
Parameters
141M
12.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt7.9 GB · 62%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- mit
- Model type
- modernbert
- Access
- Public
- Created
- Sep 16, 2025
- Updated
- Sep 16, 2025
- SHA
- 98621eb7
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. -->
mmbert-multilingual-20250916-155528
This model is a fine-tuned version of jhu-clsp/mmBERT-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8368
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use 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: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.365 | 0.4444 | 20 | nan |
| 0.7782 | 0.8889 | 40 | 0.0002 |
| 0.0072 | 1.3333 | 60 | 0.0407 |
| 0.5034 | 1.7778 | 80 | 0.5761 |
| 0.815 | 2.2222 | 100 | 1.7751 |
| 0.3767 | 2.6667 | 120 | 0.0539 |
| 0.0 | 3.1111 | 140 | 1.4726 |
| 0.1596 | 3.5556 | 160 | 0.0963 |
| 0.1221 | 4.0 | 180 | 0.0002 |
| 0.0001 | 4.4444 | 200 | 0.8061 |
| 0.253 | 4.8889 | 220 | 0.0000 |
| 0.0859 | 5.3333 | 240 | 0.0000 |
| 0.0 | 5.7778 | 260 | 0.7759 |
| 0.0001 | 6.2222 | 280 | 0.0000 |
| 0.0622 | 6.6667 | 300 | 0.0000 |
| 0.1486 | 7.1111 | 320 | 0.1663 |
| 0.1506 | 7.5556 | 340 | nan |
| 0.0003 | 8.0 | 360 | 0.0001 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.1.0
- Tokenizers 0.22.0
- Task
- Fill-Mask
- Library
- transformers
- Type
- modernbert
- License
- mit
- Created
- Sep 16, 2025
- Updated
- Sep 16, 2025