Edit model card

distilbert-base-uncased-finetuned-switchboard

This model is a fine-tuned version of distilbert-base-uncased on switchboard phone conversation transcripts. It achieves the following results on the evaluation set:

  • Loss: 0.5255
  • Accuracy: 0.7421
  • F1: 0.7383

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: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.5645 1.0 370 0.5308 0.7316 0.7290
0.5121 2.0 740 0.5255 0.7421 0.7383

Framework versions

  • Transformers 4.13.0
  • Pytorch 1.13.0+cu116
  • Datasets 1.16.1
  • Tokenizers 0.10.3
Downloads last month
12