README.md

metadata

license: apache-2.0
tags:
  - simplification
  - generated_from_trainer
datasets:
  - inglish
metrics:
  - bleu
model-index:
  - name: t5-small-inglish
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: inglish
          type: inglish
          config: default
          split: validation
          args: default
        metrics:
          - name: Bleu
            type: bleu
            value: 6.6396

t5-small-inglish

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

• Loss: 2.4875
• Bleu: 6.6396
• Gen Len: 18.706

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: 5.6e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.9396	1.0	1088	2.5632	6.0855	18.7222
2.7585	2.0	2176	2.4875	6.6396	18.706

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2