bart_memsum

This model is a fine-tuned version of facebook/bart-base on the learn3r/gov_report_memsum_oracle dataset. It achieves the following results on the evaluation set:

• Loss: 1.7431

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: 0.0002
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 32
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
• lr_scheduler_type: linear
• num_epochs: 10.0

Training results

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.14.4
• Tokenizers 0.13.3