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: 1.3724
• Rouge1: 47.1323
• Rouge2: 23.6343
• Rougel: 39.907
• Rougelsum: 43.4826
• Gen Len: 17.3260

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.4541	1.0	1842	1.3788	46.6486	23.2493	39.359	43.0174	17.4469
1.3467	2.0	3684	1.3682	47.1945	23.7803	40.0316	43.5134	17.2295
1.2945	3.0	5526	1.3724	47.1323	23.6343	39.907	43.4826	17.3260

Framework versions

• Transformers 4.33.3
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3