distilbert_squad_newsqa

This model is a fine-tuned version of distilbert-base-cased-distilled-squad on the NewsQA dataset. It achieves the following results on the evaluation set:

• Loss: 1.6247

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
• distributed_type: tpu
• 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
1.7181	1.0	6730	1.6477
1.4932	2.0	13460	1.6274
1.4426	3.0	20190	1.6247

Framework versions

• Transformers 4.26.0
• Pytorch 1.12.1+cu102
• Datasets 2.9.0
• Tokenizers 0.13.2