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: 1.3716
• Rouge1: 47.2663
• Rouge2: 23.5327
• Rougel: 39.6491
• Rougelsum: 43.3169
• Gen Len: 17.3907

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
1.4379	1.0	1842	1.3805	47.1438	23.6153	39.6699	43.5505	17.1197
1.3559	2.0	3684	1.3716	47.2663	23.5327	39.6491	43.3169	17.3907
1.2783	3.0	5526	1.3721	47.4896	23.7684	39.7733	43.4494	17.1832
1.2378	4.0	7368	1.3757	47.9122	24.0531	40.2225	43.996	17.3053
1.1983	5.0	9210	1.3751	47.8507	24.0061	40.231	43.8698	17.3040

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2