distilbert-base-uncased-finetuned-cola

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

• Loss: 0.9469
• Matthews Correlation: 0.5245

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: 2.01437918768118e-05
• train_batch_size: 4
• eval_batch_size: 16
• seed: 9
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.5529	1.0	2138	0.4856	0.4792
0.4354	2.0	4276	0.7809	0.4759
0.281	3.0	6414	0.9469	0.5245

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2