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: 1.3808
• Rouge1: 48.3584
• Rouge2: 25.2355
• Rougel: 41.0959
• Rougelsum: 44.8827
• Gen Len: 17.3496

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
1.4515	1.0	1842	1.3930	47.8577	24.5602	40.427	44.374	17.4487
1.346	2.0	3684	1.3809	48.1527	24.809	40.8549	44.5684	17.4633
1.2806	3.0	5526	1.3817	48.2629	25.0493	40.952	44.6847	17.3704
1.2414	4.0	7368	1.3799	48.2785	25.1137	41.1032	44.7977	17.3778
1.2081	5.0	9210	1.3808	48.3584	25.2355	41.0959	44.8827	17.3496

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3