SpanBERT-qa

This model is a fine-tuned version of SpanBERT/spanbert-base-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4649

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.476	1.0	3854	1.5405
1.1605	2.0	7708	1.4162
0.9986	3.0	11562	1.4649

Framework versions

• Transformers 4.25.1
• Pytorch 1.11.0+cu102
• Datasets 2.8.0
• Tokenizers 0.13.2