summary-tragedy-Bart-Large-CNN

This model is a fine-tuned version of facebook/bart-large-cnn on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4758
• Rouge1: 0.3972
• Rouge2: 0.1525
• Rougel: 0.2279
• Rougelsum: 0.2297
• Gen Len: 142.0

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.8064	1.0	10	2.5907	0.3676	0.08	0.1808	0.1804	136.0
2.4065	2.0	20	2.5102	0.3116	0.0669	0.1732	0.1732	142.0
2.2329	3.0	30	2.4821	0.3931	0.108	0.2077	0.2074	142.0
2.1376	4.0	40	2.4786	0.3972	0.1525	0.2279	0.2297	142.0
2.0733	5.0	50	2.4758	0.3972	0.1525	0.2279	0.2297	142.0

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3