distilbert-finetuned-squadv2

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

• Loss: 1.5319

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.3945	0.4998	2741	1.3654
1.2187	0.9996	5482	1.2518
0.9937	1.4995	8223	1.2515
0.8966	1.9993	10964	1.2321
0.7284	2.4991	13705	1.3200
0.7586	2.9989	16446	1.2978
0.5655	3.4987	19187	1.4298
0.567	3.9985	21928	1.4508
0.479	4.4984	24669	1.4952
0.4874	4.9982	27410	1.5319

Framework versions

• Transformers 4.57.6
• Pytorch 2.9.0+cu126
• Datasets 2.16.1
• Tokenizers 0.22.2