Downloads · 30 days
7
1% of all-time downloads
distilbert-base-uncased-finetuned-truthful
agi-css/distilbert-base-uncased-finetuned-truthful
distilbert-base-uncased-finetuned-truthful is a text classification model from agi-css. 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
482
Public
Repo size
804 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin268 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Apr 5, 2022
- Updated
- Apr 5, 2022
- SHA
- 3991bb8e
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-finetuned-truthful
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4660
- Accuracy: 0.87
- F1: 0.8697
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: 9.910294163459086e-05
- train_batch_size: 400
- eval_batch_size: 400
- 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 5 | 0.6509 | 0.59 | 0.5780 |
| No log | 2.0 | 10 | 0.4950 | 0.77 | 0.7701 |
| No log | 3.0 | 15 | 0.4787 | 0.81 | 0.8099 |
| No log | 4.0 | 20 | 0.4936 | 0.81 | 0.8096 |
| No log | 5.0 | 25 | 0.4443 | 0.82 | 0.82 |
| No log | 6.0 | 30 | 0.4547 | 0.85 | 0.8497 |
| No log | 7.0 | 35 | 0.4268 | 0.85 | 0.8500 |
| No log | 8.0 | 40 | 0.4790 | 0.87 | 0.8697 |
| No log | 9.0 | 45 | 0.4660 | 0.87 | 0.8697 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.1
- Datasets 2.0.0
- Tokenizers 0.11.0
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Apr 5, 2022
- Updated
- Apr 5, 2022