fnet-large-finetuned-cola-copy4

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: 0.6500
• 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: 4e-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: polynomial
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.6345	1.0	2138	0.6611	0.0
0.6359	2.0	4276	0.6840	0.0
0.6331	3.0	6414	0.6500	0.0

Framework versions

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