flan-t5-base-samsum

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

• Loss: 1.3649
• Rouge1: 47.6412
• Rouge2: 24.051
• Rougel: 40.0954
• Rougelsum: 43.6636
• Gen Len: 17.1844

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.4548	1.0	1842	1.3789	46.7801	23.374	39.5739	43.1465	17.4164
1.3452	2.0	3684	1.3678	47.1262	23.3912	39.8206	43.4192	17.2601
1.2821	3.0	5526	1.3649	47.6412	24.051	40.0954	43.6636	17.1844
1.2347	4.0	7368	1.3712	47.5837	24.0545	40.2391	43.7923	17.2808
1.1983	5.0	9210	1.3732	47.33	23.983	39.957	43.6156	17.2808

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1