fnet-large-finetuned-cola

This model is a fine-tuned version of google/fnet-large on the GLUE COLA dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6243
  • Matthews Correlation: 0.0

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: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss Matthews Correlation
0.6195 1.0 2138 0.6527 0.0
0.6168 2.0 4276 0.6259 0.0
0.616 3.0 6414 0.6243 0.0

Framework versions

  • Transformers 4.11.0.dev0
  • Pytorch 1.9.0
  • Datasets 1.12.1
  • Tokenizers 0.10.3