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: 42.6857
• Rouge2: 18.3487
• Rougel: 35.3275
• Rougelsum: 38.8882
• 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	42.4897	18.3435	35.1269	38.7613	16.6532
1.8578	0.7	200	1.6878	42.0049	18.2725	34.9941	38.4372	16.7216
1.835	1.06	300	1.6823	42.7659	18.64	35.4591	38.9559	16.9048
1.8144	1.41	400	1.6786	42.61	18.3931	35.3777	38.8516	16.6618
1.8094	1.76	500	1.6754	42.6857	18.3487	35.3275	38.8882	16.8474

Framework versions

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