bigbird-QA-squad_v2.3

This model is a fine-tuned version of google/bigbird-roberta-base on the squad_v2 dataset. It achieves the following results on the evaluation set:

• Loss: 1.3324

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: 8
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 121
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.7892	1.0	203	1.6201
1.4879	2.0	407	1.3778
1.3885	2.99	609	1.3324

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1