bart-large-cnn

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 2.8506
• eval_rouge1: 0.3613
• eval_rouge2: 0.0744
• eval_rougeL: 0.1665
• eval_rougeLsum: 0.3401
• eval_gen_len: 385.8086
• eval_runtime: 8322.7751
• eval_samples_per_second: 0.151
• eval_steps_per_second: 0.076
• epoch: 0.99
• step: 63

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0