NF-bigbird-squad

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

• Loss: 1.0218

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: 2
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 160
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
1.0526	1.0	1095	1.1762
0.8623	2.0	2190	1.0830
0.8911	3.0	3285	1.0327
0.9511	4.0	4380	1.0218

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3