model-cnn-dailymail

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.0614
• Rouge: {'rouge1': 0.244712987386149, 'rouge2': 0.09089741156156833, 'rougeL': 0.20130780704255938, 'rougeLsum': 0.2014458092407283}
• Bleu: 0.1054
• Perplexity: 7.8927
• Gen Len: 19.0

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

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge	Bleu	Perplexity	Gen Len
No log	1.0	75	2.1554	{'rouge1': 0.24004289659476444, 'rouge2': 0.08899351952220792, 'rougeL': 0.19620544968984488, 'rougeLsum': 0.19620948547030603}	0.1014	None	19.0
No log	2.0	150	2.0823	{'rouge1': 0.2395197299581741, 'rouge2': 0.08874595402755553, 'rougeL': 0.19692733055468523, 'rougeLsum': 0.19727630390573275}	0.1010	8.6314	19.0
No log	3.0	225	2.0659	{'rouge1': 0.24346041598310222, 'rouge2': 0.09042566103154628, 'rougeL': 0.20046289165406544, 'rougeLsum': 0.2007357619831489}	0.1041	8.0232	19.0
No log	4.0	300	2.0614	{'rouge1': 0.244712987386149, 'rouge2': 0.09089741156156833, 'rougeL': 0.20130780704255938, 'rougeLsum': 0.2014458092407283}	0.1054	7.8927	19.0

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cpu
• Datasets 2.18.0
• Tokenizers 0.15.2