Downloads · 30 days
11
41% of all-time downloads
pre-train_mBERT
morten-j/pre-train_mBERT
pre-train_mBERT is a fill-mask model from morten-j. 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
27
Public
Parameters
178M
712 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors712 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- May 3, 2024
- Updated
- May 3, 2024
- SHA
- e9f6eba1
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. -->
pre-train_mBERT
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1971
- Perplexity 3.31
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4994 | 1.0 | 368814 | 1.3694 |
| 1.3718 | 2.0 | 737628 | 1.2540 |
| 1.2979 | 3.0 | 1106442 | 1.1986 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.3.0a0+ebedce2
- Datasets 2.17.1
- Tokenizers 0.15.2
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- May 3, 2024
- Updated
- May 3, 2024