prompt_fine_tuned_boolq_bert

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

• Loss: 0.6444
• Accuracy: 0.8333
• F1: 0.7914

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	12	0.6844	0.5	0.5333
No log	2.0	24	0.6700	0.6111	0.6408
No log	3.0	36	0.6572	0.7778	0.7778
No log	4.0	48	0.6492	0.8333	0.7914
No log	5.0	60	0.6454	0.8333	0.7914
No log	6.0	72	0.6444	0.8333	0.7914

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1