distilbert-base-uncased-model-4

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

• Loss: 3.1544

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: 0.0003
• 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss
2.7789	1.0	554	2.0564
1.4826	2.0	1108	2.0916
0.7706	3.0	1662	2.4116
0.3379	4.0	2216	3.1544

Framework versions

• Transformers 4.24.0
• Pytorch 1.12.1+cu113
• Datasets 2.6.1
• Tokenizers 0.13.2