distilbert-base-cased-distilled-squad-finetuned-lr1e-05-epochs20

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: 1.0635

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-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	8	3.7689
No log	2.0	16	2.9065
No log	3.0	24	2.3956
No log	4.0	32	2.0317
No log	5.0	40	1.7636
No log	6.0	48	1.4953
No log	7.0	56	1.3982
No log	8.0	64	1.3121
No log	9.0	72	1.1879
No log	10.0	80	1.1360
No log	11.0	88	1.1250
No log	12.0	96	1.0959
No log	13.0	104	1.0450
No log	14.0	112	1.0294
No log	15.0	120	1.0386
No log	16.0	128	1.0541
No log	17.0	136	1.0922
No log	18.0	144	1.0970
No log	19.0	152	1.0686
No log	20.0	160	1.0635

Framework versions

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