flan-t5-small-samsum-summary

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: 1.6317
• Rouge1: 43.8792
• Rouge2: 19.5266
• Rougel: 36.2843
• Rougelsum: 39.8895
• Gen Len: 16.8803

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
1.8261	1.0	1842	1.6670	42.9616	18.7768	35.5551	39.3237	17.1136
1.7348	2.0	3684	1.6477	43.1943	19.0967	35.9006	39.446	16.9414
1.6883	3.0	5526	1.6371	43.5598	19.4071	36.0767	39.8372	16.8694
1.6559	4.0	7368	1.6359	43.4343	19.2178	36.0452	39.6163	17.1477
1.6413	5.0	9210	1.6317	43.8792	19.5266	36.2843	39.8895	16.8803

Framework versions

• Transformers 4.39.0
• Pytorch 2.2.1+cu121
• Datasets 2.14.7
• Tokenizers 0.15.2