bart-abs-2409-0144-lr-3e-05-bs-4-maxep-6

This model is a fine-tuned version of sshleifer/distilbart-xsum-12-6 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.3498
• Rouge/rouge1: 0.4687
• Rouge/rouge2: 0.2167
• Rouge/rougel: 0.3984
• Rouge/rougelsum: 0.3997
• Bertscore/bertscore-precision: 0.8968
• Bertscore/bertscore-recall: 0.8932
• Bertscore/bertscore-f1: 0.8948
• Meteor: 0.4183
• Gen Len: 37.6273

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: 3e-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: 6
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge/rouge1	Rouge/rouge2	Rouge/rougel	Rouge/rougelsum	Bertscore/bertscore-precision	Bertscore/bertscore-recall	Bertscore/bertscore-f1	Meteor	Gen Len
2.3602	1.0	217	2.0806	0.4443	0.2067	0.3739	0.3745	0.8966	0.8891	0.8927	0.3937	38.2364
1.6559	2.0	434	1.9951	0.4581	0.22	0.3968	0.3973	0.8994	0.8919	0.8955	0.4032	35.1273
1.2943	3.0	651	2.0581	0.4592	0.2156	0.3932	0.3942	0.8995	0.8924	0.8958	0.4071	35.2364
1.0197	4.0	868	2.1312	0.478	0.2304	0.409	0.4111	0.9003	0.8935	0.8967	0.4209	36.1091
0.8117	5.0	1085	2.2532	0.4878	0.2376	0.4181	0.4194	0.9009	0.8945	0.8976	0.4293	35.2636
0.6733	6.0	1302	2.3498	0.4687	0.2167	0.3984	0.3997	0.8968	0.8932	0.8948	0.4183	37.6273

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1