bart-large-xsum-samsum

This model is a fine-tuned version of facebook/bart-large-xsum on the samsum dataset. It achieves the following results on the evaluation set:

• Loss: 0.4330
• Rouge1: 54.3742
• Rouge2: 29.1289
• Rougel: 44.1238
• Gen Len: 29.8973

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
No log	0.9989	460	0.4542	53.4662	28.4545	43.6636	29.6174
0.7083	2.0	921	0.4415	53.6674	28.8109	44.0343	29.2665
0.3748	2.9967	1380	0.4330	54.3742	29.1289	44.1238	29.8973

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1