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: 1.3743
• Rouge1: 47.2702
• Rouge2: 23.5181
• Rougel: 39.8232
• Rougelsum: 43.3645
• Gen Len: 17.2466

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
1.4528	1.0	1842	1.3867	46.7028	22.7798	39.0236	42.7977	17.3993
1.3385	2.0	3684	1.3751	46.9306	23.2467	39.1768	42.9745	17.3431
1.2711	3.0	5526	1.3745	47.2857	23.5195	39.6304	43.3844	17.4493
1.2284	4.0	7368	1.3743	47.2702	23.5181	39.8232	43.3645	17.2466
1.2085	5.0	9210	1.3759	47.4235	23.7621	39.8577	43.5762	17.2967

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0