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: 1.5736
• Accuracy: 0.7222
• F1: 0.7325

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
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6443	4.1667	50	0.5606	0.7778	0.6806
0.3932	8.3333	100	0.6016	0.6111	0.6255
0.126	12.5	150	1.0887	0.5	0.5418
0.0166	16.6667	200	1.5543	0.5556	0.5829
0.0041	20.8333	250	1.5032	0.7222	0.7325
0.0022	25.0	300	1.7354	0.6667	0.6872
0.0018	29.1667	350	1.5756	0.6667	0.6667
0.0016	33.3333	400	1.5736	0.7222	0.7325

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0
• Datasets 2.19.0
• Tokenizers 0.19.1