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: 47.2599
• Rouge2: 23.4743
• Rougel: 39.7653
• Rougelsum: 43.3969
• 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	46.6845	22.7619	39.0062	42.8447	17.3993
1.3385	2.0	3684	1.3751	46.9176	23.2372	39.1453	43.0158	17.3431
1.2711	3.0	5526	1.3745	47.2849	23.4742	39.6359	43.4259	17.4493
1.2284	4.0	7368	1.3743	47.2599	23.4743	39.7653	43.3969	17.2466
1.2085	5.0	9210	1.3759	47.4194	23.7268	39.8035	43.6216	17.2967

Framework versions

• Transformers 4.36.0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0