summarization_model

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

• Loss: 0.1359
• Rouge1: 0.1813
• Rouge2: 0.1114
• Rougel: 0.1616
• Rougelsum: 0.1617
• 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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.2358	1.0	1635	0.1719	0.1758	0.1033	0.1554	0.1554	19.0
0.2043	2.0	3270	0.1574	0.1764	0.1046	0.1561	0.1561	19.0
0.191	3.0	4905	0.1505	0.1778	0.1069	0.1577	0.1578	19.0
0.178	4.0	6540	0.1448	0.1797	0.1093	0.1597	0.1597	19.0
0.1734	5.0	8175	0.1406	0.1804	0.1102	0.1605	0.1604	19.0
0.1681	6.0	9810	0.1376	0.1811	0.111	0.1613	0.1613	19.0
0.1665	7.0	11445	0.1365	0.1815	0.1114	0.1618	0.1618	19.0
0.1643	8.0	13080	0.1359	0.1813	0.1114	0.1616	0.1617	19.0

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3