bert-gpqa

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

• Loss: 0.2227
• Accuracy: 0.9174

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: 0.0005
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	28	1.3863	0.2723
No log	2.0	56	1.3860	0.3036
No log	3.0	84	1.3855	0.3125
No log	4.0	112	1.3841	0.3951
No log	5.0	140	1.3562	0.5781
No log	6.0	168	0.9820	0.6674
No log	7.0	196	0.6106	0.7812
No log	8.0	224	0.4142	0.8527
No log	9.0	252	0.2647	0.9241
No log	10.0	280	0.2227	0.9174

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2