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: 0.1580
  • Accuracy: 0.9487

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: 13

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.7033 1.0 318 1.2016 0.7610
0.9281 2.0 636 0.6128 0.8855
0.4901 3.0 954 0.3447 0.9252
0.289 4.0 1272 0.2389 0.9403
0.2016 5.0 1590 0.2000 0.9455
0.1647 6.0 1908 0.1826 0.9484
0.1446 7.0 2226 0.1723 0.9487
0.1329 8.0 2544 0.1672 0.9477
0.1255 9.0 2862 0.1639 0.9494
0.1211 10.0 3180 0.1621 0.9497
0.1171 11.0 3498 0.1591 0.95
0.1149 12.0 3816 0.1585 0.9494
0.1136 13.0 4134 0.1580 0.9487

Framework versions

  • Transformers 4.16.2
  • Pytorch 2.4.1+cu121
  • Datasets 1.16.1
  • Tokenizers 0.19.1
Downloads last month
6
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train heid5356/distilbert-base-uncased-distilled-clinc

Evaluation results