Downloads · 30 days
21
3% of all-time downloads
tiny-mlm-glue-mrpc
muhtasham/tiny-mlm-glue-mrpc
tiny-mlm-glue-mrpc 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
613
Public
Parameters
4.4M
195 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin17.7 MB · 49%
Parameter types
How the weights are stored.
F324.4M · 100%
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. -->
tiny-mlm-glue-mrpc
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: 4.0034
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 |
|---|---|---|---|
| 4.4206 | 1.09 | 500 | 3.9467 |
| 4.3088 | 2.18 | 1000 | 3.8183 |
| 4.1805 | 3.27 | 1500 | 3.9761 |
| 4.1129 | 4.36 | 2000 | 4.0324 |
| 4.032 | 5.45 | 2500 | 3.7326 |
| 4.0162 | 6.54 | 3000 | 3.7890 |
| 3.9261 | 7.63 | 3500 | 3.7041 |
| 3.943 | 8.71 | 4000 | 3.9622 |
| 3.8852 | 9.8 | 4500 | 3.8910 |
| 3.8712 | 10.89 | 5000 | 4.0034 |
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 5, 2023
- Updated
- Sep 15, 2023