TokenizerTestingMTSUFall2024SoftwareEngineering

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

• Loss: 1.5198
• Rouge1: 0.2778
• Rouge2: 0.2234
• Rougel: 0.2686
• Rougelsum: 0.2686
• Gen Len: 18.9697

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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.8333	1.0	12429	1.6354	0.2717	0.2139	0.262	0.262	18.9751
1.7368	2.0	24858	1.5610	0.2763	0.2208	0.267	0.267	18.9735
1.6978	3.0	37287	1.5291	0.2777	0.2227	0.2683	0.2682	18.9699
1.7008	4.0	49716	1.5198	0.2778	0.2234	0.2686	0.2686	18.9697

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1