SSahas/codegen_python

1---2license: bsd-3-clause3library_name: peft4tags:5- trl6- sft7- generated_from_trainer8base_model: Salesforce/codegen-350M-mono9model-index:10- name: codegen11  results: []12metrics:13- rougeL - 0.4114pipeline_tag: text-generation15---16 17<!-- This model card has been generated automatically according to the information the Trainer had access to. You18should probably proofread and complete it, then remove this comment. -->19 20# codegen21 22This model is a fine-tuned version of [Salesforce/codegen-350M-mono](https://huggingface.co/Salesforce/codegen-350M-mono) on the python dataset.23 24## Model description25 26More information needed27 28## Intended uses & limitations29 30More information needed31 32## Training and evaluation data33 34More information needed35 36## Training procedure37 38### Training hyperparameters39 40The following hyperparameters were used during training:41- learning_rate: 0.000542- train_batch_size: 143- eval_batch_size: 844- seed: 4245- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0846- lr_scheduler_type: cosine47- num_epochs: 648- mixed_precision_training: Native AMP49 50### Training results51 52 53 54### Framework versions55 56- PEFT 0.10.1.dev057- Transformers 4.38.258- Pytorch 2.0.059- Datasets 2.18.060- Tokenizers 0.15.2