flan-t5-large-xsum / README.md
spacemanidol's picture
Upload 12 files
5f1a0cc
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - xsum
metrics:
  - rouge
model-index:
  - name: large
    results:
      - task:
          name: Summarization
          type: summarization
        dataset:
          name: xsum
          type: xsum
          config: default
          split: validation
          args: default
        metrics:
          - name: Rouge1
            type: rouge
            value: 39.7125

large

This model is a fine-tuned version of google/flan-t5-large on the xsum dataset. It achieves the following results on the evaluation set:

  • Loss: nan
  • Rouge1: 39.7125
  • Rouge2: 16.3418
  • Rougel: 31.7246
  • Rougelsum: 31.7214
  • Gen Len: 26.7397

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: 0.0001
  • train_batch_size: 8
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.27.0.dev0
  • Pytorch 1.9.0+cu111
  • Datasets 2.5.1
  • Tokenizers 0.12.1