distilbert-base-uncased-finetuned-cola

This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:

• Loss: 1.0426
• Matthews Correlation: 0.3558

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: 4.0180563319684876e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 36
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
No log	1.0	54	0.5807	0.0
No log	2.0	108	0.6416	0.2717
No log	3.0	162	0.7327	0.3380
No log	4.0	216	0.9711	0.3521
No log	5.0	270	1.0426	0.3558

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3