NLP-Paper-to-QA-Generation

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

• Loss: 2.9593

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 184
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.99	46	4.8204
5.3975	1.99	92	4.4450
5.3975	2.98	138	3.9634
4.494	3.97	184	3.4658
4.494	4.97	230	3.1863
3.5664	5.96	276	3.0828
3.5664	6.95	322	3.0403
3.2954	7.95	368	3.0155
3.2954	8.94	414	2.9989
3.1918	9.93	460	2.9826
3.1918	10.93	506	2.9742
3.1547	11.92	552	2.9670
3.1547	12.91	598	2.9620
3.1233	13.91	644	2.9601
3.1233	14.9	690	2.9593

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0