t5-base_readme_summarization

This model is a fine-tuned version of t5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7573
• Rouge1: 0.4859
• Rouge2: 0.3402
• Rougel: 0.4581
• Rougelsum: 0.4581
• Gen Len: 14.1882

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.1761	1.0	1458	1.8974	0.4769	0.3281	0.4486	0.4484	14.265
1.9982	2.0	2916	1.8329	0.4819	0.3349	0.4553	0.4552	14.0492
1.8626	3.0	4374	1.7946	0.4793	0.3343	0.4528	0.4529	14.5971
1.8013	4.0	5832	1.7695	0.4873	0.3418	0.4609	0.4614	14.1691
1.7478	5.0	7290	1.7573	0.4859	0.3402	0.4581	0.4581	14.1882

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1