bert-base-uncased-cola

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

• Loss: 0.5406
• Matthews Correlation: 0.5880

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: 32
• 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
No log	1.0	268	0.4598	0.5135
0.393	2.0	536	0.4875	0.5573
0.393	3.0	804	0.5406	0.5880

Framework versions

• Transformers 4.20.0.dev0
• Pytorch 1.11.0+cu113
• Datasets 2.1.0
• Tokenizers 0.12.1