metadata

base_model: microsoft/codebert-base
tags:
  - generated_from_trainer
model-index:
  - name: CodeBertForCodeTrans
    results: []

CodeBertForCodeTrans

This model is a fine-tuned version of microsoft/codebert-base on an unknown dataset.

Model description

This model is fine-tuned on CodeXGLUE codetrans dataset. It can only translate java code to c-sharp code. Prompt: '''Python "#translate this java code to c-sharp code:\njava:" '''

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: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 12354.0
num_epochs: 20

Training results

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu117
Datasets 2.16.1
Tokenizers 0.13.3