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: 1.3707
• Rouge1: 47.39
• Rouge2: 23.8837
• Rougel: 40.08
• Rougelsum: 43.7241
• Gen Len: 17.2137

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
1.4525	1.0	1842	1.3837	46.4021	22.8734	39.1025	42.8284	17.2149
1.3436	2.0	3684	1.3725	47.0983	23.5269	39.8757	43.4526	17.1954
1.2821	3.0	5526	1.3708	47.2332	23.6343	39.7749	43.4436	17.2271
1.2307	4.0	7368	1.3707	47.39	23.8837	40.08	43.7241	17.2137
1.1986	5.0	9210	1.3762	47.4841	23.9306	40.0741	43.7225	17.2821

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.1+cu117
• Datasets 2.15.0
• Tokenizers 0.15.0