Prashanth-1998's picture
Model save
3f27e67
metadata
license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
datasets:
  - wikihow
metrics:
  - rouge
model-index:
  - name: wikihow_t5small_model
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: wikihow
          type: wikihow
          config: all
          split: test
          args: all
        metrics:
          - name: Rouge1
            type: rouge
            value: 0.2067

wikihow_t5small_model

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

  • Loss: 2.9412
  • Rouge1: 0.2067
  • Rouge2: 0.0618
  • Rougel: 0.17
  • Rougelsum: 0.1698
  • Gen Len: 18.864

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
3.4224 1.0 1250 3.0417 0.2045 0.0591 0.1659 0.1657 18.873
3.2253 2.0 2500 2.9721 0.2052 0.0603 0.168 0.1678 18.858
3.1943 3.0 3750 2.9477 0.2075 0.0621 0.1704 0.1701 18.876
3.1793 4.0 5000 2.9412 0.2067 0.0618 0.17 0.1698 18.864

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.0+cu118
  • Datasets 2.15.0
  • Tokenizers 0.15.0