distilbert-base-cased-distilled-squad-finetuned-lr1e-06-epochs15

This model is a fine-tuned version of distilbert-base-cased-distilled-squad on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0730

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: 1e-06
• 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	8	1.0971
No log	2.0	16	1.0827
No log	3.0	24	1.0815
No log	4.0	32	1.0722
No log	5.0	40	1.0708
No log	6.0	48	1.0693
No log	7.0	56	1.0708
No log	8.0	64	1.0715
No log	9.0	72	1.0721
No log	10.0	80	1.0765
No log	11.0	88	1.0793
No log	12.0	96	1.0782
No log	13.0	104	1.0755
No log	14.0	112	1.0734
No log	15.0	120	1.0730

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3