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: 0.9259
• Matthews Correlation: 0.5280

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: 1.6431647433677446e-05
• train_batch_size: 4
• eval_batch_size: 16
• seed: 29
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.5652	1.0	2138	0.5803	0.3891
0.4508	2.0	4276	0.8841	0.4727
0.2869	3.0	6414	0.9259	0.5280

Framework versions

• Transformers 4.54.0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.2