Downloads · 30 days
33
38% of all-time downloads
distilbert-base-multilingual-cased-Confusion_mlm-20230608
soBeauty/distilbert-base-multilingual-cased-Confusion_mlm-20230608
distilbert-base-multilingual-cased-Confusion_mlm-20230608 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
88
Public
Repo size
9.2 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
- c657194a
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-20230608
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: 0.6882
- Loss: 1.2871
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 | 0.6533 | 1.4298 |
| No log | 2.0 | 260 | 0.6733 | 1.2080 |
| No log | 3.0 | 390 | 0.6554 | 1.3312 |
| 1.4795 | 4.0 | 520 | 0.6495 | 1.4023 |
| 1.4795 | 5.0 | 650 | 0.6105 | 1.4489 |
| 1.4795 | 6.0 | 780 | 0.7175 | 1.1518 |
| 1.4795 | 7.0 | 910 | 0.7214 | 1.0541 |
| 1.3934 | 8.0 | 1040 | 0.7336 | 1.2016 |
| 1.3934 | 9.0 | 1170 | 0.7107 | 1.1739 |
| 1.3934 | 10.0 | 1300 | 0.6882 | 1.2871 |
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