README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - mbpp
metrics:
  - bleu
model-index:
  - name: t5-mbpp
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: mbpp
          type: mbpp
          config: full
          split: train
          args: full
        metrics:
          - name: Bleu
            type: bleu
            value: 0.0177

t5-mbpp

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

• Loss: 4.6617
• Bleu: 0.0177
• Gen Len: 17.88

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	19	4.7777	0.0207	17.88
No log	2.0	38	4.6617	0.0177	17.88

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.1+cu117
• Datasets 2.11.0
• Tokenizers 0.13.3