Downloads · 30 days
18
24% of all-time downloads
distilbert-base-multilingual-cased-Confusion_mlm-20230610
soBeauty/distilbert-base-multilingual-cased-Confusion_mlm-20230610
distilbert-base-multilingual-cased-Confusion_mlm-20230610 is a fill-mask model from soBeauty. Use it when you need the model to fill a missing word. 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
74
Public
Repo size
4.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin542 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Jun 10, 2023
- Updated
- Jun 10, 2023
- SHA
- 8099a761
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. -->
distilbert-base-multilingual-cased-Confusion_mlm-20230610
This model is a fine-tuned version of distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Accuracy: 0.5125
- Loss: 2.0564
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| No log | 1.0 | 130 | 0.5301 | 1.9624 |
| No log | 2.0 | 260 | 0.4876 | 2.0142 |
| No log | 3.0 | 390 | 0.5203 | 2.0986 |
| 2.0509 | 4.0 | 520 | 0.5692 | 1.9098 |
| 2.0509 | 5.0 | 650 | 0.5460 | 1.9322 |
| 2.0509 | 6.0 | 780 | 0.5371 | 2.0830 |
| 2.0509 | 7.0 | 910 | 0.5343 | 2.0515 |
| 1.856 | 8.0 | 1040 | 0.5339 | 1.8678 |
| 1.856 | 9.0 | 1170 | 0.5823 | 1.7815 |
| 1.856 | 10.0 | 1300 | 0.5125 | 2.0564 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Fill-Mask
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Jun 10, 2023
- Updated
- Jun 10, 2023