flan-t5-base-eLife

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

• Loss: 2.0533
• Rouge1: 16.8601
• Rouge2: 3.5043
• Rougel: 13.0262
• Rougelsum: 15.2504
• Gen Len: 19.0

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: 5e-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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.6071	1.0	544	2.2323	16.7606	3.2667	12.9074	15.1681	19.0
2.438	2.0	1088	2.1395	16.9106	3.3542	13.0126	15.3345	19.0
2.3649	3.0	1632	2.0900	16.9637	3.5315	13.0919	15.3446	19.0
2.3264	4.0	2176	2.0624	16.8183	3.4983	13.0296	15.226	19.0
2.292	5.0	2720	2.0533	16.8601	3.5043	13.0262	15.2504	19.0

Framework versions

• Transformers 4.40.1
• Pytorch 2.1.2
• Datasets 2.19.0
• Tokenizers 0.19.1