Downloads · 30 days
4
11% of all-time downloads
distilbert-base-uncased
juan-mathew/distilbert-base-uncased
distilbert-base-uncased is a text classification model from juan-mathew. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
35
Public
Parameters
67M
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors268 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- distilbert
- Access
- Public
- Created
- May 23, 2024
- Updated
- May 24, 2024
- SHA
- 032c9741
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. -->
distilbert-base-uncased
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8081
- Matthews Correlation: 0.5533
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.5224 | 1.0 | 535 | 0.4595 | 0.4332 |
| 0.3513 | 2.0 | 1070 | 0.4861 | 0.5317 |
| 0.224 | 3.0 | 1605 | 0.6453 | 0.5187 |
| 0.1721 | 4.0 | 2140 | 0.7943 | 0.5286 |
| 0.1254 | 5.0 | 2675 | 0.8081 | 0.5533 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- Created
- May 23, 2024
- Updated
- May 24, 2024