summarisation_arxiv_model

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

• Loss: 2.6373
• Rouge1: 0.1729
• Rouge2: 0.0617
• Rougel: 0.1378
• Rougelsum: 0.1377
• 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	403	2.7717	0.1646	0.0557	0.1319	0.1319	19.0
3.0546	2.0	806	2.7195	0.1684	0.0585	0.1347	0.1346	19.0
2.8771	3.0	1209	2.6899	0.1695	0.0597	0.1356	0.1356	19.0
2.8364	4.0	1612	2.6719	0.1716	0.0606	0.137	0.1369	19.0
2.8058	5.0	2015	2.6585	0.1718	0.061	0.1371	0.137	19.0
2.8058	6.0	2418	2.6504	0.1721	0.0616	0.1374	0.1373	19.0
2.7852	7.0	2821	2.6453	0.1726	0.0618	0.1378	0.1377	19.0
2.778	8.0	3224	2.6404	0.1728	0.0618	0.1378	0.1377	19.0
2.7612	9.0	3627	2.6386	0.1725	0.0615	0.1375	0.1374	19.0
2.7644	10.0	4030	2.6373	0.1729	0.0617	0.1378	0.1377	19.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0
• Datasets 3.0.0
• Tokenizers 0.19.1