gpt2-finetuned-cola-finetuned-cola

This model is a fine-tuned version of PavanNeerudu/gpt2-finetuned-cola on the glue dataset. It achieves the following results on the evaluation set:

• Loss: 0.5620
• Matthews Correlation: 0.3886

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: 1.2972292434767088e-06
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.3926	1.0	535	0.5620	0.3886

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0
• Datasets 2.12.0
• Tokenizers 0.13.3