sjlee311bart-large-cnn-finetuned

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

• Loss: 2.1557
• Rouge1: 49.9356
• Rouge2: 14.8574
• Rougel: 22.2849
• Precision: 86.7404
• Recall: 86.4333
• F1: 86.584
• Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.35.2)
• Fkgl: 10.01
• Cloze Score: 17.05
• Reading Level 13-15: 110
• Reading Level 11-12: 39
• Reading Level 16+: 85
• Reading Level 9-10: 7
• Reading Level Mode: 13-15
• Summac Val: 0.57
• Gen Len: 434.7842

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Framework versions

• Transformers 4.35.2
• Pytorch 2.2.2+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2