distilbert-base-uncased-qa

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: 3.4871

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: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	66	3.2096
No log	2.0	132	2.8592
No log	3.0	198	2.8928
No log	4.0	264	2.6908
No log	5.0	330	2.5923
No log	6.0	396	2.7418
No log	7.0	462	2.9204
2.1971	8.0	528	3.0142
2.1971	9.0	594	3.1064
2.1971	10.0	660	3.2017
2.1971	11.0	726	3.4628
2.1971	12.0	792	3.3789
2.1971	13.0	858	3.3585
2.1971	14.0	924	3.4515
2.1971	15.0	990	3.4871

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3