Downloads · 30 days
21
54% of all-time downloads
distilbert-base-uncased-distilled-clinc
Shinrajim/distilbert-base-uncased-distilled-clinc
distilbert-base-uncased-distilled-clinc is a machine learning model from Shinrajim. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
39
Public
Repo size
805 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin268 MB · 100%
At a glance
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Nov 9, 2024
- Updated
- Nov 17, 2024
- SHA
- bf078b90
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. -->
distilbert-base-uncased-distilled-clinc
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: 0.0439
- Accuracy: 0.9310
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: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8393 | 1.0 | 318 | 0.4398 | 0.6748 |
| 0.3332 | 2.0 | 636 | 0.1605 | 0.8519 |
| 0.157 | 3.0 | 954 | 0.0855 | 0.9016 |
| 0.1025 | 4.0 | 1272 | 0.0628 | 0.9171 |
| 0.0809 | 5.0 | 1590 | 0.0537 | 0.9239 |
| 0.0709 | 6.0 | 1908 | 0.0487 | 0.9294 |
| 0.0647 | 7.0 | 2226 | 0.0461 | 0.9287 |
| 0.0614 | 8.0 | 2544 | 0.0445 | 0.9306 |
| 0.0596 | 9.0 | 2862 | 0.0439 | 0.9310 |
Framework versions
- Transformers 4.16.2
- Pytorch 2.5.1+cu121
- Datasets 1.16.1
- Tokenizers 0.20.3
- Type
- distilbert
- License
- apache-2.0
- Created
- Nov 9, 2024
- Updated
- Nov 17, 2024