flan-t5-small-samsum

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

• Loss: 1.6754
• Rouge1: 42.6698
• Rouge2: 18.3442
• Rougel: 35.2697
• Rougelsum: 38.9457
• Gen Len: 16.8474

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: 52
• eval_batch_size: 52
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.8824	0.35	100	1.7015	42.477	18.2999	35.0949	38.8554	16.6532
1.8578	0.7	200	1.6878	42.0138	18.2348	34.9449	38.4907	16.7216
1.835	1.06	300	1.6823	42.7733	18.5982	35.3899	39.0215	16.9048
1.8144	1.41	400	1.6786	42.6285	18.384	35.3233	38.9203	16.6618
1.8094	1.76	500	1.6754	42.6698	18.3442	35.2697	38.9457	16.8474

Framework versions

• Transformers 4.36.0
• Pytorch 2.0.0
• Datasets 2.15.0
• Tokenizers 0.15.0