Downloads · 30 days
16
5% of all-time downloads
bert_base_48
gokuls/bert_base_48
bert_base_48 is a fill-mask model from gokuls. 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
348
Public
Repo size
3.1 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
- Jun 11, 2023
- Updated
- Jun 12, 2023
- SHA
- 494d9a22
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. -->
bert_base_48
This model is a fine-tuned version of gokuls/bert_base_24 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.6418
- Accuracy: 0.1663
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: 1e-05
- train_batch_size: 48
- eval_batch_size: 48
- seed: 10
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 6.005 | 0.08 | 10000 | 5.9999 | 0.1513 |
| 5.9845 | 0.16 | 20000 | 5.9811 | 0.1511 |
| 5.9695 | 0.25 | 30000 | 5.9673 | 0.1518 |
| 5.9599 | 0.33 | 40000 | 5.9513 | 0.1515 |
| 5.9402 | 0.41 | 50000 | 5.9411 | 0.1517 |
| 5.9291 | 0.49 | 60000 | 5.9217 | 0.1518 |
| 5.6816 | 0.57 | 70000 | 5.6418 | 0.1663 |
Framework versions
- Transformers 4.30.1
- Pytorch 1.14.0a0+410ce96
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Jun 11, 2023
- Updated
- Jun 12, 2023