eli5

This model is a fine-tuned version of t5-base on the eli5 dataset. It achieves the following results on the evaluation set:

• Loss: 2.2569
• Rouge1: 14.6325
• Rouge2: 2.3714
• Rougel: 11.2941
• Rougelsum: 13.2006
• Gen Len: 18.9911

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.4057	1.0	34080	2.2708	14.6356	2.3501	11.3428	13.213	18.9946
2.3943	2.0	68160	2.2569	14.6325	2.3714	11.2941	13.2006	18.9911

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0
• Datasets 2.14.5
• Tokenizers 0.14.1