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: 1.3701
• Rouge1: 47.1222
• Rouge2: 23.3908
• Rougel: 39.7231
• Rougelsum: 43.3842
• Gen Len: 17.1465

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: 16
• eval_batch_size: 16
• 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
1.4683	1.0	921	1.3897	46.737	23.2046	39.4441	43.2001	17.1526
1.3586	2.0	1842	1.3726	47.2757	23.701	39.7059	43.502	17.2222
1.3138	3.0	2763	1.3701	47.1222	23.3908	39.7231	43.3842	17.1465
1.2828	4.0	3684	1.3737	47.3039	23.5383	39.8402	43.5561	17.3309
1.2492	5.0	4605	1.3738	47.557	23.7814	40.1904	43.89	17.2332

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.0
• Datasets 2.12.0
• Tokenizers 0.13.3