Downloads · 30 days
6
15% of all-time downloads
de_wiki_mlm_42_new
fpadovani/de_wiki_mlm_42_new
de_wiki_mlm_42_new is a fill-mask model from fpadovani. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
41
Public
Parameters
14.9M
2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2 GB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Jun 10, 2025
- Updated
- Sep 11, 2026
- SHA
- 4fffba4c
Try a prompt
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. -->
de_wiki_mlm_42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.0027
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40000
- training_steps: 100000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0796 | 2000 | 8.1248 |
| 8.1604 | 2.1592 | 4000 | 7.4613 |
| 8.1604 | 3.2389 | 6000 | 7.3457 |
| 7.3684 | 4.3185 | 8000 | 7.2823 |
| 7.3684 | 5.3981 | 10000 | 7.1806 |
| 7.2121 | 6.4777 | 12000 | 7.1159 |
| 7.2121 | 7.5574 | 14000 | 7.0322 |
| 7.0695 | 8.6370 | 16000 | 7.0128 |
| 7.0695 | 9.7166 | 18000 | 6.9382 |
| 6.9563 | 10.7962 | 20000 | 6.9027 |
| 6.9563 | 11.8758 | 22000 | 6.8521 |
| 6.8584 | 12.9555 | 24000 | 6.7639 |
| 6.8584 | 14.0351 | 26000 | 6.6782 |
| 6.6954 | 15.1147 | 28000 | 6.5272 |
| 6.6954 | 16.1943 | 30000 | 6.3891 |
| 6.4335 | 17.2740 | 32000 | 6.1050 |
| 6.4335 | 18.3536 | 34000 | 5.6402 |
| 5.7799 | 19.4332 | 36000 | 5.1583 |
| 5.7799 | 20.5128 | 38000 | 4.8938 |
| 5.0133 | 21.5924 | 40000 | 4.6340 |
| 5.0133 | 22.6721 | 42000 | 4.4619 |
| 4.5804 | 23.7517 | 44000 | 4.2638 |
| 4.5804 | 24.8313 | 46000 | 4.1289 |
| 4.2594 | 25.9109 | 48000 | 4.0013 |
| 4.2594 | 26.9906 | 50000 | 3.8840 |
| 4.0135 | 28.0702 | 52000 | 3.8026 |
| 4.0135 | 29.1498 | 54000 | 3.7119 |
| 3.8273 | 30.2294 | 56000 | 3.6407 |
| 3.8273 | 31.3090 | 58000 | 3.5547 |
| 3.6814 | 32.3887 | 60000 | 3.5167 |
| 3.6814 | 33.4683 | 62000 | 3.4455 |
| 3.56 | 34.5479 | 64000 | 3.4070 |
| 3.56 | 35.6275 | 66000 | 3.3657 |
| 3.4651 | 36.7072 | 68000 | 3.3225 |
| 3.4651 | 37.7868 | 70000 | 3.3028 |
| 3.3776 | 38.8664 | 72000 | 3.2467 |
| 3.3776 | 39.9460 | 74000 | 3.2158 |
| 3.3098 | 41.0256 | 76000 | 3.2050 |
| 3.3098 | 42.1053 | 78000 | 3.1554 |
| 3.2499 | 43.1849 | 80000 | 3.1305 |
| 3.2499 | 44.2645 | 82000 | 3.1254 |
| 3.2031 | 45.3441 | 84000 | 3.0903 |
| 3.2031 | 46.4238 | 86000 | 3.0811 |
| 3.1596 | 47.5034 | 88000 | 3.0615 |
| 3.1596 | 48.5830 | 90000 | 3.0489 |
| 3.1274 | 49.6626 | 92000 | 3.0343 |
| 3.1274 | 50.7422 | 94000 | 3.0256 |
| 3.1001 | 51.8219 | 96000 | 3.0236 |
| 3.1001 | 52.9015 | 98000 | 3.0081 |
| 3.0805 | 53.9811 | 100000 | 3.0027 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- Created
- Jun 10, 2025
- Updated
- Sep 11, 2026