Edit model card

distilbert-base-uncased-finetuned-emotion

This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1703
  • Accuracy: 0.9315
  • F1: 0.9316

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: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.8038 1.0 250 0.2937 0.9095 0.9087
0.223 2.0 500 0.1875 0.927 0.9277
0.1549 3.0 750 0.1703 0.9315 0.9316

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.1.0
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
5

Finetuned from

Dataset used to train florianehmann/distilbert-base-uncased-finetuned-emotion

Evaluation results