finetuned-bert-mrpc

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

• Loss: 0.4725
• Accuracy: 0.8382
• F1: 0.8881

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5236	0.4348	50	0.4882	0.7647	0.8452
0.4277	0.8696	100	0.3845	0.8431	0.8940
0.2727	1.3043	150	0.3824	0.8529	0.8980
0.2285	1.7391	200	0.3646	0.8358	0.8831
0.1305	2.1739	250	0.3605	0.8652	0.9002
0.1193	2.6087	300	0.4725	0.8382	0.8881

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2