distilbert-base-uncased-distilled-squad-BiLSTM-finetuned-squad-pure2

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

• Loss: 1.0750

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
0.6764	1.0	5483	1.0746
0.6618	2.0	10966	1.0799
0.6434	3.0	16449	1.0750

Framework versions

• Transformers 4.40.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1