joey234's picture
Update README.md
f25ee9d
metadata
license: mit
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: roberta2-base-mnli-negnli
    results: []

roberta2-base-mnli-negnli

This model is a fine-tuned version of sileod/roberta-base-mnli on the GLUE MNLI dataset and the MNLI subset in NegNLI. It achieves the following results on the evaluation set:

  • Loss: 0.8397
  • Accuracy: 0.8400

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5.0

Training results

Framework versions

  • Transformers 4.21.0.dev0
  • Pytorch 1.8.0
  • Datasets 1.18.3
  • Tokenizers 0.12.1