Downloads · 30 days
6
10% of all-time downloads
ModernBERT-base-dreaddit-mlm
andreagasparini/ModernBERT-base-dreaddit-mlm
ModernBERT-base-dreaddit-mlm is a fill-mask model from andreagasparini. 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
61
Public
Parameters
150M
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors599 MB · 99%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- modernbert
- Access
- Public
- Created
- Jan 23, 2025
- Updated
- Jan 23, 2025
- SHA
- 7f051463
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. -->
ModernBERT-base-dreaddit-mlm
This model is a fine-tuned version of answerdotai/ModernBERT-base on the Dreaddit dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5279
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.559 | 1.0 | 178 | 1.4901 |
| 1.4621 | 2.0 | 356 | 1.4861 |
| 1.4719 | 3.0 | 534 | 1.5321 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.0+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0
- Task
- Fill-Mask
- Library
- transformers
- Type
- modernbert
- License
- apache-2.0
- Created
- Jan 23, 2025
- Updated
- Jan 23, 2025