flan-t5-small-qa-91

This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0727

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: 8
• eval_batch_size: 8
• 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
0.1207	1.0	500	0.0685
0.1176	2.0	1000	0.0693
0.116	3.0	1500	0.0696
0.1152	4.0	2000	0.0709
0.1138	5.0	2500	0.0703
0.1134	6.0	3000	0.0717
0.1125	7.0	3500	0.0707
0.1119	8.0	4000	0.0710
0.1115	9.0	4500	0.0717
0.1113	10.0	5000	0.0713
0.111	11.0	5500	0.0721
0.1107	12.0	6000	0.0726
0.1106	13.0	6500	0.0721
0.111	14.0	7000	0.0720
0.1108	15.0	7500	0.0721
0.1106	16.0	8000	0.0722
0.1104	17.0	8500	0.0729
0.1102	18.0	9000	0.0727
0.1101	19.0	9500	0.0727
0.11	20.0	10000	0.0727

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu118
• Tokenizers 0.13.3