codegen_python / README.md
SSahas's picture
Update README.md
3559d6b verified
|
raw
history blame
1.21 kB
metadata
license: bsd-3-clause
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: Salesforce/codegen-350M-mono
model-index:
  - name: codegen
    results: []
metrics:
  - rougeL - 0.41
pipeline_tag: text-generation

codegen

This model is a fine-tuned version of Salesforce/codegen-350M-mono on the pythondataset.

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: 0.0005
  • train_batch_size: 1
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 6
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.10.1.dev0
  • Transformers 4.38.2
  • Pytorch 2.0.0
  • Datasets 2.18.0
  • Tokenizers 0.15.2