model_output

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: 1.8702
• Rouge-1: {'r': 0.1449206060602415, 'p': 0.612228865799888, 'f': 0.2314199657444668}
• Rouge-2: {'r': 0.06217585891598185, 'p': 0.3306214679875187, 'f': 0.10338896078492887}
• Rouge-l: {'r': 0.12714023830372423, 'p': 0.539238202328148, 'f': 0.20314789762608454}

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	Rouge-1	Rouge-2	Rouge-l
2.2905	1.0	774	1.9726	{'r': 0.14027789446494138, 'p': 0.6013831620449274, 'f': 0.22452882138970473}	{'r': 0.05888226359145526, 'p': 0.31779608267296355, 'f': 0.09805637819321582}	{'r': 0.1224534604628376, 'p': 0.5254403024438363, 'f': 0.19599547417477767}
2.0699	2.0	1548	1.9046	{'r': 0.1443383469259305, 'p': 0.6126968055462134, 'f': 0.23058379100363557}	{'r': 0.061031058218561175, 'p': 0.3258341532224339, 'f': 0.10151469929542385}	{'r': 0.12661559647672582, 'p': 0.5387896667222934, 'f': 0.20232290318208698}
2.0266	3.0	2322	1.8790	{'r': 0.14521947151897238, 'p': 0.6137526775465678, 'f': 0.23191975811273857}	{'r': 0.062005041526819744, 'p': 0.3292476462164101, 'f': 0.10309342638663624}	{'r': 0.12726161117386992, 'p': 0.5393284920986702, 'f': 0.20331473785771298}
2.0042	4.0	3096	1.8702	{'r': 0.1449206060602415, 'p': 0.612228865799888, 'f': 0.2314199657444668}	{'r': 0.06217585891598185, 'p': 0.3306214679875187, 'f': 0.10338896078492887}	{'r': 0.12714023830372423, 'p': 0.539238202328148, 'f': 0.20314789762608454}

Framework versions

• Transformers 4.42.4
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1