Downloads · 30 days
7
4% of all-time downloads
bert-base-uncased-finetune
avikumar/bert-base-uncased-finetune
bert-base-uncased-finetune is a multiple choice model from avikumar. Use it for the multiple choice task on the model card, and read the license before you ship it in a product. 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
176
Public
Parameters
109M
32 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors438 MB · 100%
At a glance
- Task
- multiple choice
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Apr 30, 2024
- Updated
- Apr 30, 2024
- SHA
- c26036e0
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-finetune
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7793
- Accuracy: 0.7993
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7582 | 1.0 | 2299 | 0.5703 | 0.7783 |
| 0.381 | 2.0 | 4598 | 0.5787 | 0.7950 |
| 0.1529 | 3.0 | 6897 | 0.7793 | 0.7993 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- multiple choice
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Apr 30, 2024
- Updated
- Apr 30, 2024