my_awesome_health_qa_model

This model is a fine-tuned version of deepset/roberta-base-squad2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1521

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: 1e-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: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	124	0.3119
No log	2.0	248	0.2871
No log	3.0	372	0.2269
No log	4.0	496	0.1773
0.3107	5.0	620	0.1965
0.3107	6.0	744	0.2013
0.3107	7.0	868	0.1753
0.3107	8.0	992	0.1575
0.1229	9.0	1116	0.1749
0.1229	10.0	1240	0.1600
0.1229	11.0	1364	0.1480
0.1229	12.0	1488	0.1539
0.0902	13.0	1612	0.1448
0.0902	14.0	1736	0.1513
0.0902	15.0	1860	0.1521

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1