Downloads · 30 days
6
14% of all-time downloads
bert-base-uncased-mean-pooling-finetuned-cola
ilkekas/bert-base-uncased-mean-pooling-finetuned-cola
bert-base-uncased-mean-pooling-finetuned-cola is a text classification model from ilkekas. Use it when you need a label for a piece of text. 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
42
Public
Repo size
14 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin438 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- May 6, 2023
- Updated
- May 6, 2023
- SHA
- 9b328093
Try a prompt
Datasets
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-mean-pooling-finetuned-cola
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4983
- Matthews Correlation: 0.5628
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: 3.3487316926587096e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.5613 | 1.0 | 535 | 0.4981 | 0.4273 |
| 0.43 | 2.0 | 1070 | 0.4379 | 0.5367 |
| 0.3647 | 3.0 | 1605 | 0.5213 | 0.5030 |
| 0.312 | 4.0 | 2140 | 0.5085 | 0.5391 |
| 0.2832 | 5.0 | 2675 | 0.4983 | 0.5628 |
| 0.245 | 6.0 | 3210 | 0.6061 | 0.5339 |
| 0.2291 | 7.0 | 3745 | 0.5835 | 0.5443 |
| 0.2065 | 8.0 | 4280 | 0.5907 | 0.5443 |
| 0.2032 | 9.0 | 4815 | 0.6072 | 0.5469 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- May 6, 2023
- Updated
- May 6, 2023