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: 42.6976
• Rouge2: 18.3401
• Rougel: 35.2388
• Rougelsum: 38.9044
• 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	42.4907	18.3171	35.0684	38.8292	16.6532
1.8578	0.7	200	1.6878	42.0288	18.2503	34.9411	38.4881	16.7216
1.835	1.06	300	1.6823	42.742	18.6174	35.3759	38.992	16.9048
1.8144	1.41	400	1.6786	42.6286	18.3873	35.3084	38.8797	16.6618
1.8094	1.76	500	1.6754	42.6976	18.3401	35.2388	38.9044	16.8474

Framework versions

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