veronica-girolimetti/t5-summarization-headers-zero-shot

test-dialogue-summarization-headers

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

• Loss: 2.4536
• Rouge: {'rouge1': 44.8698, 'rouge2': 19.92, 'rougeL': 20.7147, 'rougeLsum': 20.7147}
• Bert Score: 0.8733
• Bleurt 20: -0.8548
• Gen Len: 15.305

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: 7
• eval_batch_size: 7
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge	Bert Score	Bleurt 20	Gen Len
2.6545	1.0	186	2.5321	{'rouge1': 45.8489, 'rouge2': 19.7993, 'rougeL': 20.5196, 'rougeLsum': 20.5196}	0.8737	-0.8571	15.16
2.6779	2.0	372	2.4884	{'rouge1': 44.2284, 'rouge2': 19.6646, 'rougeL': 20.6804, 'rougeLsum': 20.6804}	0.8737	-0.8594	15.13
2.6701	3.0	558	2.4682	{'rouge1': 44.6249, 'rouge2': 19.9539, 'rougeL': 20.6036, 'rougeLsum': 20.6036}	0.8737	-0.8576	15.25
2.597	4.0	744	2.4582	{'rouge1': 45.0018, 'rouge2': 19.7794, 'rougeL': 20.647, 'rougeLsum': 20.647}	0.8739	-0.8582	15.295
2.5861	5.0	930	2.4536	{'rouge1': 44.8698, 'rouge2': 19.92, 'rougeL': 20.7147, 'rougeLsum': 20.7147}	0.8733	-0.8548	15.305

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0