Downloads · 30 days
59
14% of all-time downloads
tiny-mlm-glue-wnli-from-scratch-custom-tokenizer
muhtasham/tiny-mlm-glue-wnli-from-scratch-custom-tokenizer
tiny-mlm-glue-wnli-from-scratch-custom-tokenizer is a fill-mask model from muhtasham. 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
415
Public
Repo size
36.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin3.3 MB · 98%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 12, 2023
- Updated
- Jan 12, 2023
- SHA
- 39c5e363
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. -->
tiny-mlm-glue-wnli-from-scratch-custom-tokenizer
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.4279
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.1494 | 6.25 | 500 | 6.6863 |
| 6.2515 | 12.5 | 1000 | 6.2279 |
| 5.9308 | 18.75 | 1500 | 6.0591 |
| 5.836 | 25.0 | 2000 | 5.7884 |
| 5.7371 | 31.25 | 2500 | 5.6423 |
| 5.6668 | 37.5 | 3000 | 5.8836 |
| 5.595 | 43.75 | 3500 | 5.4954 |
| 5.5433 | 50.0 | 4000 | 5.7668 |
| 5.4809 | 56.25 | 4500 | 5.4280 |
| 5.4256 | 62.5 | 5000 | 5.4279 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- Created
- Jan 12, 2023
- Updated
- Jan 12, 2023