Downloads · 30 days
5
14% of all-time downloads
mlm
emohammadi97/mlm
mlm is a fill-mask model from emohammadi97. 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
35
Public
Parameters
68.2M
273 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors273 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Dec 27, 2023
- Updated
- Dec 27, 2023
- SHA
- d9d87dab
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: 4.5407
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.9586 | 10.87 | 500 | 5.6039 |
| 4.9096 | 21.74 | 1000 | 5.0384 |
| 4.2463 | 32.61 | 1500 | 4.7924 |
| 3.6977 | 43.48 | 2000 | 4.6626 |
| 3.258 | 54.35 | 2500 | 4.4548 |
| 2.8435 | 65.22 | 3000 | 4.4381 |
| 2.5083 | 76.09 | 3500 | 4.2610 |
| 2.1856 | 86.96 | 4000 | 4.1977 |
| 1.9237 | 97.83 | 4500 | 4.4848 |
| 1.6827 | 108.7 | 5000 | 4.5539 |
| 1.4808 | 119.57 | 5500 | 4.5407 |
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 27, 2023
- Updated
- Dec 27, 2023