README.md

metadata

base_model: TinyPixel/Llama-2-7B-bf16-sharded
tags:
  - generated_from_trainer
model-index:
  - name: Llama-2-7B-codeGPT
    results: []
license: openrail
datasets:
  - red1xe/code_instructions
language:
  - en
metrics:
  - rouge

Llama-2-7B-codeGPT

This model is a fine-tuned version of TinyPixel/Llama-2-7B-bf16-sharded on an red1xe/red1xe/code_instructions dataset.

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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 150

Training results

Framework versions

• Transformers 4.32.0.dev0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3