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: 1.3721
• Rouge1: 47.5
• Rouge2: 23.9237
• Rougel: 40.0646
• Rougelsum: 43.6387
• Gen Len: 17.2405

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
1.4398	1.0	1842	1.3823	47.2415	23.7419	39.5142	43.4177	17.0354
1.3564	2.0	3684	1.3747	46.833	23.308	39.2838	42.9821	17.3077
1.2776	3.0	5526	1.3721	47.5	23.9237	40.0646	43.6387	17.2405
1.2345	4.0	7368	1.3744	47.5599	23.9714	40.06	43.8107	17.2454
1.194	5.0	9210	1.3760	47.7868	24.0949	40.2021	43.789	17.2466

Framework versions

• Transformers 4.27.4
• Pytorch 2.0.0+cu117
• Datasets 2.11.0
• Tokenizers 0.13.3