finetuned-bert-mrpc

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

• Loss: 0.4148
• Accuracy: 0.8603
• F1: 0.9036

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: 16
• eval_batch_size: 16
• 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	Accuracy	F1
0.5315	1.0	230	0.3698	0.8382	0.8862
0.3	2.0	460	0.3677	0.8431	0.8919
0.1575	3.0	690	0.4148	0.8603	0.9036

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.1+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2