README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - fairytale_qa
metrics:
  - rouge
model-index:
  - name: t5-base-QG-finetuned-FairytaleQA
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: fairytale_qa
          type: fairytale_qa
          config: default
          split: validation
          args: default
        metrics:
          - name: Rouge1
            type: rouge
            value: 45.1292

t5-base-QG-finetuned-FairytaleQA

This model is a fine-tuned version of t5-base on the fairytale_qa dataset. It achieves the following results on the evaluation set:

• Loss: 1.0876
• Rouge1: 45.1292
• Rouge2: 26.5987
• Rougel: 43.2701
• Rougelsum: 43.2744
• Gen Len: 15.1024

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.1882	1.0	2137	1.0876	45.1292	26.5987	43.2701	43.2744	15.1024

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3