Downloads · 30 days
8
2% of all-time downloads
mlm
Mahdi-Salahshour/mlm
mlm is a fill-mask model from Mahdi-Salahshour. 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
352
Public
Parameters
125M
998 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors499 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Dec 22, 2023
- Updated
- Dec 24, 2023
- SHA
- 7742b2f5
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. -->
mlm
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.4066
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.1287 | 2.17 | 100 | 6.4156 |
| 6.2349 | 4.35 | 200 | 6.2942 |
| 6.1294 | 6.52 | 300 | 6.2401 |
| 6.0832 | 8.7 | 400 | 6.2258 |
| 6.3872 | 10.87 | 500 | 6.2017 |
| 6.0572 | 13.04 | 600 | 6.2860 |
| 6.0423 | 15.22 | 700 | 6.1084 |
| 6.0311 | 17.39 | 800 | 6.2598 |
| 6.009 | 19.57 | 900 | 6.3806 |
| 6.0152 | 21.74 | 1000 | 6.2286 |
| 6.0004 | 23.91 | 1100 | 6.2187 |
| 5.9887 | 26.09 | 1200 | 6.4066 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- Created
- Dec 22, 2023
- Updated
- Dec 24, 2023