t5-large_readme_summarization

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

• Loss: 1.7393
• Rouge1: 0.4806
• Rouge2: 0.3307
• Rougel: 0.4559
• Rougelsum: 0.4552
• Gen Len: 13.8969

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

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.968	1.0	2916	1.8066	0.4624	0.3113	0.4349	0.4342	14.0995
1.8681	2.0	5832	1.7578	0.4791	0.327	0.453	0.4526	13.8046
1.875	3.0	8748	1.7441	0.479	0.3291	0.4536	0.4536	13.8909
1.8169	4.0	11664	1.7393	0.4806	0.3307	0.4559	0.4552	13.8969

Framework versions

• Transformers 4.35.1
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1