Downloads · 30 days
12
26% of all-time downloads
medium-mlm-imdb
muhtasham/medium-mlm-imdb
medium-mlm-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
47
Public
Repo size
5.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin166 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Dec 10, 2022
- Updated
- Sep 13, 2023
- SHA
- b73dc1e9
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. -->
medium-mlm-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: 2.1889
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 |
|---|---|---|---|
| 2.5116 | 0.16 | 500 | 2.3298 |
| 2.4448 | 0.32 | 1000 | 2.3157 |
| 2.4362 | 0.48 | 1500 | 2.2987 |
| 2.4287 | 0.64 | 2000 | 2.2878 |
| 2.4125 | 0.8 | 2500 | 2.2693 |
| 2.4066 | 0.96 | 3000 | 2.2666 |
| 2.352 | 1.12 | 3500 | 2.2590 |
| 2.3406 | 1.28 | 4000 | 2.2501 |
| 2.3443 | 1.44 | 4500 | 2.2433 |
| 2.3331 | 1.6 | 5000 | 2.2373 |
| 2.3247 | 1.76 | 5500 | 2.2357 |
| 2.3343 | 1.92 | 6000 | 2.2332 |
| 2.3092 | 2.08 | 6500 | 2.2334 |
| 2.3034 | 2.24 | 7000 | 2.2319 |
| 2.2984 | 2.4 | 7500 | 2.2254 |
| 2.2794 | 2.56 | 8000 | 2.2186 |
| 2.3028 | 2.72 | 8500 | 2.2130 |
| 2.3047 | 2.88 | 9000 | 2.2156 |
| 2.2785 | 3.04 | 9500 | 2.2084 |
| 2.2562 | 3.2 | 10000 | 2.2105 |
| 2.2553 | 3.36 | 10500 | 2.2034 |
| 2.2626 | 3.52 | 11000 | 2.2024 |
| 2.2313 | 3.68 | 11500 | 2.2056 |
| 2.2514 | 3.84 | 12000 | 2.1980 |
| 2.2462 | 4.0 | 12500 | 2.2052 |
| 2.2143 | 4.16 | 13000 | 2.1928 |
| 2.2199 | 4.32 | 13500 | 2.1972 |
| 2.2045 | 4.48 | 14000 | 2.2014 |
| 2.2246 | 4.64 | 14500 | 2.1885 |
| 2.2272 | 4.8 | 15000 | 2.1895 |
| 2.2213 | 4.96 | 15500 | 2.1976 |
| 2.2074 | 5.12 | 16000 | 2.1889 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Dec 10, 2022
- Updated
- Sep 13, 2023