gchhablani's picture
update model card README.md
c032b80
metadata
language:
  - en
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - glue
metrics:
  - matthews_correlation
model-index:
  - name: fnet-large-finetuned-cola-copy2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: GLUE COLA
          type: glue
          args: cola
        metrics:
          - name: Matthews Correlation
            type: matthews_correlation
            value: 0

fnet-large-finetuned-cola-copy2

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: 0.6173
  • 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: 2e-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
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss Matthews Correlation
0.6192 1.0 2138 0.6443 0.0
0.6177 2.0 4276 0.6296 0.0
0.6128 3.0 6414 0.6173 0.0

Framework versions

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