bert-large-cased-finetuned-cola

This model is a fine-tuned version of bert-large-cased on the GLUE COLA dataset. It achieves the following results on the evaluation set:

• Loss: 0.8385
• Matthews Correlation: 0.5957

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.5533	1.0	2138	0.7943	0.4439
0.5004	2.0	4276	0.7272	0.5678
0.2865	3.0	6414	0.8385	0.5957

Framework versions

• Transformers 4.11.0.dev0
• Pytorch 1.9.0
• Datasets 1.12.1
• Tokenizers 0.10.3