Downloads · 30 days
60
16% of all-time downloads
tiny-mlm-glue-qqp-custom-tokenizer
muhtasham/tiny-mlm-glue-qqp-custom-tokenizer
tiny-mlm-glue-qqp-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. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
369
Public
Repo size
442 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin17.7 MB · 97%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jan 6, 2023
- Updated
- Jan 6, 2023
- SHA
- 6d9556d7
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-qqp-custom-tokenizer
This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.7811
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
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.4263 | 0.4 | 500 | 6.7180 |
| 6.4992 | 0.8 | 1000 | 6.6456 |
| 6.2737 | 1.2 | 1500 | 6.4546 |
| 5.9994 | 1.6 | 2000 | 6.2448 |
| 5.875 | 2.0 | 2500 | 6.2319 |
| 5.7667 | 2.4 | 3000 | 6.1561 |
| 5.7425 | 2.8 | 3500 | 6.2058 |
| 5.753 | 3.2 | 4000 | 6.0921 |
| 5.5982 | 3.6 | 4500 | 6.1794 |
| 5.6196 | 4.0 | 5000 | 6.1381 |
| 5.512 | 4.4 | 5500 | 6.0225 |
| 5.5096 | 4.8 | 6000 | 6.0408 |
| 5.4474 | 5.2 | 6500 | 5.8967 |
| 5.3589 | 5.6 | 7000 | 5.9714 |
| 5.329 | 6.0 | 7500 | 5.9004 |
| 5.2965 | 6.4 | 8000 | 5.8087 |
| 5.2853 | 6.8 | 8500 | 5.8612 |
| 5.2446 | 7.2 | 9000 | 5.8007 |
| 5.0895 | 7.6 | 9500 | 5.7173 |
| 5.1699 | 8.0 | 10000 | 5.8139 |
| 5.0603 | 8.4 | 10500 | 5.6959 |
| 5.0748 | 8.8 | 11000 | 5.7078 |
| 5.0742 | 9.2 | 11500 | 5.7509 |
| 4.955 | 9.6 | 12000 | 5.7811 |
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
- License
- apache-2.0
- Created
- Jan 6, 2023
- Updated
- Jan 6, 2023