bart-base-finetuned-xsum

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

• Loss: 1.7558
• Rouge1: 38.6459
• Rouge2: 17.3528
• Rougel: 31.9807
• Rougelsum: 31.9765

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: 5.6e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	12753	1.8305	37.5583	16.2117	30.8468	30.842
No log	2.0	25506	1.7558	38.6459	17.3528	31.9807	31.9765

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1