bart-cnndm

This model is a fine-tuned version of facebook/bart-base on an 20，000 pieces of news from abisee/cnn_dailymail dataset. It achieves the following results on the evaluation set:

• Loss: 1.9615
• Rouge1: 35.04
• Rouge2: 14.58
• Rougel: 24.22
• Rougelsum: 32.09
• Gen Len: 70.5145

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.3.0
• Tokenizers 0.22.1