SashaSheykina's picture
Training complete
583e6f6 verified
metadata
base_model: microsoft/CodeGPT-small-py
tags:
  - Code Generation
  - generated_from_trainer
metrics:
  - rouge
  - bleu
model-index:
  - name: codeGpt2-finetuned-cXg-nl-to-code
    results: []

codeGpt2-finetuned-cXg-nl-to-code

This model is a fine-tuned version of microsoft/CodeGPT-small-py on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 3.2141
  • Rouge1: 0.0873
  • Rouge2: 0.0056
  • Rougel: 0.0626
  • Bleu: 1.1469
  • Meteor: 0.1189
  • Codebleu: 0.2350

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: 5e-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: 3
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1