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: 42.6907
• Rouge2: 18.3626
• Rougel: 35.2723
• Rougelsum: 38.9062
• 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	42.4935	18.3634	35.0823	38.8358	16.6532
1.8578	0.7	200	1.6878	42.0329	18.2685	34.9421	38.4636	16.7216
1.835	1.06	300	1.6823	42.7493	18.6379	35.4001	38.9845	16.9048
1.8144	1.41	400	1.6786	42.6157	18.4093	35.3149	38.8787	16.6618
1.8094	1.76	500	1.6754	42.6907	18.3626	35.2723	38.9062	16.8474

Framework versions

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