Edit model card

distilbert-base-uncased-finetuned-go_emotions_20220608_1

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

  • Loss: 0.0857
  • F1: 0.5575
  • Roc Auc: 0.7242
  • Accuracy: 0.4364

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: 5

Training results

Training Loss Epoch Step Validation Loss F1 Roc Auc Accuracy
0.173 1.0 679 0.1074 0.4245 0.6455 0.2976
0.0989 2.0 1358 0.0903 0.5199 0.6974 0.3972
0.0865 3.0 2037 0.0868 0.5504 0.7180 0.4263
0.0806 4.0 2716 0.0860 0.5472 0.7160 0.4233
0.0771 5.0 3395 0.0857 0.5575 0.7242 0.4364

Framework versions

  • Transformers 4.19.2
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.2
  • Tokenizers 0.12.1
Downloads last month
7

Dataset used to train jungealexander/distilbert-base-uncased-finetuned-go_emotions_20220608_1

Evaluation results