Downloads · 30 days
26
4% of all-time downloads
reformer-big_patent-16384
robingeibel/reformer-big_patent-16384
reformer-big_patent-16384 is a fill-mask model from robingeibel. 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
646
Public
Repo size
3.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin712 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- reformer
- Access
- Public
- Created
- Jul 26, 2022
- Updated
- Jul 27, 2022
- SHA
- 72123eaf
Try a prompt
Datasets
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. -->
reformer-big_patent-16384
This model was trained from scratch on the big_patent dataset. It achieves the following results on the evaluation set:
- Loss: 6.0565
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: 2.5e-06
- 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: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.0379 | 1.0 | 17732 | 6.0935 |
| 5.9941 | 2.0 | 35464 | 6.0363 |
| 5.9831 | 3.0 | 53196 | 6.0565 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- reformer
- Created
- Jul 26, 2022
- Updated
- Jul 27, 2022