README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - big_patent
metrics:
  - rouge
model-index:
  - name: nd_pegasus_bigpatent_cnn_xsum_model
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: big_patent
          type: big_patent
          config: d
          split: train[:200]
          args: d
        metrics:
          - name: Rouge1
            type: rouge
            value: 0.3465

nd_pegasus_bigpatent_cnn_xsum_model

This model is a fine-tuned version of google/pegasus-cnn_dailymail on the big_patent dataset. It achieves the following results on the evaluation set:

• Loss: 3.1037
• Rouge1: 0.3465
• Rouge2: 0.1181
• Rougel: 0.2258
• Rougelsum: 0.227
• Gen Len: 85.75

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.5734	1.0	80	3.1804	0.3468	0.1231	0.2262	0.2268	89.95
3.3146	2.0	160	3.1037	0.3465	0.1181	0.2258	0.227	85.75

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.1+cu116
• Datasets 2.11.0
• Tokenizers 0.13.2