Downloads · 30 days
6
12% of all-time downloads
bert-base-uncased-finetuned-dob
MattiaParavisi/bert-base-uncased-finetuned-dob
bert-base-uncased-finetuned-dob is a fill-mask model from MattiaParavisi. 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
52
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Oct 5, 2023
- Updated
- Oct 9, 2023
- SHA
- 665415f1
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. -->
bert-base-uncased-finetuned-dob
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0005
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: 2e-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: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.218 | 1.0 | 20 | 0.9998 |
| 0.5247 | 2.0 | 40 | 0.1072 |
| 0.0813 | 3.0 | 60 | 0.0406 |
| 0.0421 | 4.0 | 80 | 0.0351 |
| 0.0339 | 5.0 | 100 | 0.0286 |
| 0.0249 | 6.0 | 120 | 0.0064 |
| 0.0109 | 7.0 | 140 | 0.0022 |
| 0.0039 | 8.0 | 160 | 0.0016 |
| 0.0026 | 9.0 | 180 | 0.0013 |
| 0.0022 | 10.0 | 200 | 0.0011 |
| 0.002 | 11.0 | 220 | 0.0010 |
| 0.0017 | 12.0 | 240 | 0.0009 |
| 0.0015 | 13.0 | 260 | 0.0009 |
| 0.0014 | 14.0 | 280 | 0.0008 |
| 0.0013 | 15.0 | 300 | 0.0007 |
| 0.0013 | 16.0 | 320 | 0.0007 |
| 0.0012 | 17.0 | 340 | 0.0007 |
| 0.0011 | 18.0 | 360 | 0.0006 |
| 0.001 | 19.0 | 380 | 0.0006 |
| 0.001 | 20.0 | 400 | 0.0006 |
| 0.0009 | 21.0 | 420 | 0.0006 |
| 0.0009 | 22.0 | 440 | 0.0006 |
| 0.0009 | 23.0 | 460 | 0.0006 |
| 0.0009 | 24.0 | 480 | 0.0005 |
| 0.0008 | 25.0 | 500 | 0.0005 |
| 0.0008 | 26.0 | 520 | 0.0005 |
| 0.0008 | 27.0 | 540 | 0.0005 |
| 0.0008 | 28.0 | 560 | 0.0005 |
| 0.0008 | 29.0 | 580 | 0.0005 |
| 0.0008 | 30.0 | 600 | 0.0005 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Oct 5, 2023
- Updated
- Oct 9, 2023