bert-fine-tuned-cola

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

• Loss: 0.8694
• Matthews Correlation: 0.5705

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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
0.46	1.0	1069	0.4515	0.5050
0.3138	2.0	2138	0.6163	0.5737
0.1809	3.0	3207	0.8694	0.5705

Framework versions

• Transformers 4.47.1
• Pytorch 2.6.0
• Datasets 3.2.0
• Tokenizers 0.21.0