flan-t5-large-finetuned-samsum

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

• Loss: 1.2099
• Rouge1: 48.8719
• Rouge2: 25.5658
• Rougel: 41.6686
• Rougelsum: 45.2419
• Gen Len: 17.1880

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
1.1871	1.0	1842	1.2099	48.8719	25.5658	41.6686	45.2419	17.1880
1.0344	2.0	3684	1.2168	48.9633	25.5702	41.449	45.2238	17.3810
0.9457	3.0	5526	1.2322	49.2708	25.8481	41.9485	45.3808	17.1392
0.8706	4.0	7368	1.2459	49.4742	26.3099	42.0051	45.4181	17.2369
0.8173	5.0	9210	1.2660	49.5398	26.1602	41.9861	45.4851	17.3040

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2