Edit model card

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: 0.1002
  • Accuracy: 0.9406

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: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.9039 1.0 318 0.5777 0.7335
0.4486 2.0 636 0.2860 0.8768
0.2528 3.0 954 0.1792 0.9210
0.176 4.0 1272 0.1398 0.9274
0.1417 5.0 1590 0.1209 0.9329
0.1245 6.0 1908 0.1110 0.94
0.1135 7.0 2226 0.1061 0.9390
0.1074 8.0 2544 0.1026 0.94
0.1032 9.0 2862 0.1006 0.9410
0.1017 10.0 3180 0.1002 0.9406

Framework versions

  • Transformers 4.11.3
  • Pytorch 1.10.0+cu111
  • Datasets 1.16.1
  • Tokenizers 0.10.3
Downloads last month
26

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

Evaluation results