Downloads · 30 days
72
5% of all-time downloads
genome-bert
nestorgonzalovich/genome-bert
genome-bert is a fill-mask model from nestorgonzalovich. 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
1.5K
Public
Repo size
70.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin498 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 23, 2023
- Updated
- Apr 5, 2023
- SHA
- 796ca693
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. -->
genome-bert
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4267
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 400
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5187 | 0.65 | 1000 | 0.6013 |
| 0.4429 | 1.31 | 2000 | 0.5585 |
| 0.3791 | 1.96 | 3000 | 0.5298 |
| 0.3316 | 2.62 | 4000 | 0.5153 |
| 0.2991 | 3.27 | 5000 | 0.5025 |
| 0.3066 | 3.93 | 6000 | 0.4808 |
| 0.2795 | 4.58 | 7000 | 0.4675 |
| 0.2599 | 5.24 | 8000 | 0.4594 |
| 0.2432 | 5.89 | 9000 | 0.4460 |
| 0.2282 | 6.54 | 10000 | 0.4431 |
| 0.2167 | 7.2 | 11000 | 0.4381 |
| 0.2075 | 7.85 | 12000 | 0.4291 |
| 0.2013 | 8.51 | 13000 | 0.4307 |
| 0.1977 | 9.16 | 14000 | 0.4266 |
| 0.1951 | 9.82 | 15000 | 0.4267 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- Created
- Jan 23, 2023
- Updated
- Apr 5, 2023