t5-small-finetuned-QuestionGen

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

• Loss: 1.9736
• Rouge1: 28.8472
• Rouge2: 9.1148
• Rougel: 26.1148
• Rougelsum: 26.1005
• Gen Len: 13.8242

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.2236	1.0	5475	2.0208	28.8909	9.1623	26.2536	26.248	13.3811
2.1541	2.0	10950	1.9838	28.9823	9.2269	26.2339	26.2225	13.8656
2.1237	3.0	16425	1.9736	28.8472	9.1148	26.1148	26.1005	13.8242

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1