Downloads · 30 days
15
3% of all-time downloads
bert-medium-mlm-finetuned-imdb
muhtasham/bert-medium-mlm-finetuned-imdb
bert-medium-mlm-finetuned-imdb 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
438
Public
Repo size
6.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin166 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Dec 5, 2022
- Updated
- Dec 5, 2022
- SHA
- a777cc6d
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. -->
bert-medium-mlm-finetuned-imdb
This model is a fine-tuned version of google/bert_uncased_L-8_H-512_A-8 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.1565
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: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|
| 2.4752 | 0.32 | 500 | 2.2958 |
| 2.4164 | 0.64 | 1000 | 2.2739 |
| 2.3904 | 0.96 | 1500 | 2.2490 |
| 2.3531 | 1.28 | 2000 | 2.2429 |
| 2.3497 | 1.6 | 2500 | 2.2277 |
| 2.3208 | 1.92 | 3000 | 2.2253 |
| 2.3035 | 2.24 | 3500 | 2.2126 |
| 2.2941 | 2.56 | 4000 | 2.2129 |
| 2.2953 | 2.88 | 4500 | 2.2009 |
| 2.2682 | 3.2 | 5000 | 2.1931 |
| 2.2608 | 3.52 | 5500 | 2.1944 |
| 2.2475 | 3.84 | 6000 | 2.1844 |
| 2.2347 | 4.16 | 6500 | 2.1790 |
| 2.2176 | 4.48 | 7000 | 2.1799 |
| 2.2263 | 4.8 | 7500 | 2.1722 |
| 2.2187 | 5.12 | 8000 | 2.1809 |
| 2.1981 | 5.44 | 8500 | 2.1838 |
| 2.2157 | 5.76 | 9000 | 2.1646 |
| 2.1879 | 6.08 | 9500 | 2.1666 |
| 2.194 | 6.4 | 10000 | 2.1639 |
| 2.1758 | 6.72 | 10500 | 2.1622 |
| 2.1811 | 7.04 | 11000 | 2.1605 |
| 2.1662 | 7.36 | 11500 | 2.1543 |
| 2.1744 | 7.68 | 12000 | 2.1530 |
| 2.1712 | 8.0 | 12500 | 2.1577 |
| 2.1528 | 8.32 | 13000 | 2.1597 |
| 2.1374 | 8.64 | 13500 | 2.1565 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Dec 5, 2022
- Updated
- Dec 5, 2022