Edit model card
YAML Metadata Error: "model-index" must be an array

bert-base-uncased-finetuned-semeval2020-task4a

This model is a fine-tuned version of bert-base-uncased on the ComVE dataset which was part of SemEval 2020 Task 4. It achieves the following results on the test set:

  • Loss: 0.2782
  • Accuracy: 0.9040

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • 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
No log 1.0 344 0.2700 0.8940
0.349 2.0 688 0.2782 0.9040

Framework versions

  • Transformers 4.12.3
  • Pytorch 1.9.1
  • Datasets 1.12.1
  • Tokenizers 0.10.3
Downloads last month
3

Evaluation results

Model card error

This model's model-index metadata is invalid: Schema validation error. "value" must be an array