Downloads · 30 days
9
36% of all-time downloads
xlm-roberta-self-supervision
JamesLemo/xlm-roberta-self-supervision
xlm-roberta-self-supervision is a fill-mask model from JamesLemo. 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
25
Public
Parameters
560M
6.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Dec 23, 2025
- Updated
- Dec 23, 2025
- SHA
- 03935e82
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. -->
xlm-roberta-self-supervision
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0899
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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 |
|---|---|---|---|
| 0.5941 | 0.4132 | 100 | 0.5656 |
| 0.2904 | 0.8264 | 200 | 0.3468 |
| 0.3479 | 1.2397 | 300 | 0.2029 |
| 0.5638 | 1.6529 | 400 | 0.2151 |
| 0.3173 | 2.0661 | 500 | 0.2894 |
| 0.5959 | 2.4793 | 600 | 0.2483 |
| 0.1404 | 2.8926 | 700 | 0.2484 |
| 0.2309 | 3.3058 | 800 | 0.1808 |
| 0.0921 | 3.7190 | 900 | 0.1847 |
| 0.1374 | 4.1322 | 1000 | 0.1084 |
| 0.1611 | 4.5455 | 1100 | 0.1429 |
| 0.1057 | 4.9587 | 1200 | 0.0899 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Dec 23, 2025
- Updated
- Dec 23, 2025