results

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: 0.0000
• Rouge1: 0.8708
• Rouge2: 0.8636
• Rougel: 0.8708
• Rougelsum: 0.8708

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: 0.001
• train_batch_size: 24
• eval_batch_size: 4
• 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	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	1	1.1463	0.2430	0.1714	0.2430	0.2430
No log	2.0	2	0.4544	0.7028	0.6432	0.7028	0.7028
No log	3.0	3	0.1078	0.8708	0.8413	0.8708	0.8708
No log	4.0	4	0.0477	0.8708	0.8636	0.8708	0.8708
No log	5.0	5	0.0856	0.8708	0.8636	0.8708	0.8708
No log	6.0	6	0.0128	0.8708	0.8636	0.8708	0.8708
No log	7.0	7	0.0088	0.8708	0.8636	0.8708	0.8708
No log	8.0	8	0.0082	0.8708	0.8636	0.8708	0.8708
No log	9.0	9	0.0019	0.8708	0.8636	0.8708	0.8708
No log	10.0	10	0.0008	0.8708	0.8636	0.8708	0.8708
No log	11.0	11	0.0005	0.8708	0.8636	0.8708	0.8708
No log	12.0	12	0.0003	0.8708	0.8636	0.8708	0.8708
No log	13.0	13	0.0002	0.8708	0.8636	0.8708	0.8708
No log	14.0	14	0.0001	0.8708	0.8636	0.8708	0.8708
No log	15.0	15	0.0001	0.8708	0.8636	0.8708	0.8708
No log	16.0	16	0.0001	0.8708	0.8636	0.8708	0.8708
No log	17.0	17	0.0000	0.8708	0.8636	0.8708	0.8708
No log	18.0	18	0.0001	0.8708	0.8636	0.8708	0.8708
No log	19.0	19	0.0001	0.8708	0.8636	0.8708	0.8708
No log	20.0	20	0.0000	0.8708	0.8636	0.8708	0.8708

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1