uda_qa_deberta

This model is a fine-tuned version of timpal0l/mdeberta-v3-base-squad2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9272

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: 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: 12
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.7868	1.0	24	1.3981
0.7556	2.0	48	1.0414
0.508	3.0	72	0.9954
0.3307	4.0	96	0.9373
0.3098	5.0	120	0.9613
0.2105	6.0	144	0.9799
0.1567	7.0	168	0.8763
0.105	8.0	192	0.9742
0.0942	9.0	216	0.9634
0.0733	10.0	240	0.9067
0.0493	11.0	264	0.9081
0.0348	12.0	288	0.9272

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0