bert-base-uncased-finetuned-cola

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

• Loss: 0.4500
• Matthews Correlation: 0.555170

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: 3.5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• dropout: 0.18
• max_length: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
No log	1.0	268	0.4692	0.4912
0.4636	2.0	536	0.4500	0.5313
0.4636	3.0	804	0.4809	0.5233
0.01977	10.0	-	-	0.5552
Average Training Accuracy: 99.553%
Average Validation Accuracy: 82.69%

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3