README.md

metadata

license: apache-2.0
base_model: facebook/bart-base
tags:
  - generated_from_trainer
datasets:
  - samsum
metrics:
  - rouge
model-index:
  - name: samsum_139_bart-base
    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: 0.4834

samsum_139_bart-base

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

• Loss: 0.5331
• Rouge1: 0.4834
• Rouge2: 0.2527
• Rougel: 0.4093
• Rougelsum: 0.4092
• Gen Len: 18.3215

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.5323	4.34	500	0.5449	0.4788	0.2457	0.4002	0.4004	18.7653
0.4101	8.69	1000	0.5331	0.4834	0.2527	0.4093	0.4092	18.3215

Framework versions

• Transformers 4.36.2
• Pytorch 2.0.1+cu117
• Datasets 2.15.0
• Tokenizers 0.15.0