Downloads · 30 days
13
3% of all-time downloads
finetuned_ckpt
susnato/finetuned_ckpt
finetuned_ckpt is a text classification model from susnato. 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
376
Public
Repo size
1.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin268 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Dec 12, 2022
- Updated
- Dec 12, 2022
- SHA
- 4be0156f
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. -->
finetuned_ckpt
This model is a fine-tuned version of distilbert-base-uncased on the clinc_oos dataset. It achieves the following results on the evaluation set:
- Loss: 0.7767
- Accuracy: 0.9161
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: 48
- eval_batch_size: 48
- 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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 318 | 3.2814 | 0.7410 |
| 3.783 | 2.0 | 636 | 1.8740 | 0.8335 |
| 3.783 | 3.0 | 954 | 1.1590 | 0.8916 |
| 1.6892 | 4.0 | 1272 | 0.8595 | 0.9103 |
| 0.9052 | 5.0 | 1590 | 0.7767 | 0.9161 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.12.1
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Dec 12, 2022
- Updated
- Dec 12, 2022