README.md

metadata

license: mit
base_model: facebook/bart-large-xsum
tags:
  - generated_from_trainer
datasets:
  - samsum
metrics:
  - rouge
model-index:
  - name: conversation-summ
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: samsum
          type: samsum
          config: samsum
          split: validation
          args: samsum
        metrics:
          - name: Rouge1
            type: rouge
            value: 54.5208

conversation-summ

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

• Loss: 0.3072
• Rouge1: 54.5208
• Rouge2: 29.613
• Rougel: 44.529
• Rougelsum: 49.9578
• Gen Len: 30.1968

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
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.2898	1.0	3683	0.3072	54.5208	29.613	44.529	49.9578	30.1968

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3