codezakh's picture
Improve metadata, link to project page (#1)
faee48d verified
metadata
base_model: meta-llama/Llama-3.1-8B-Instruct
datasets:
  - codezakh/EFAGen-Llama-3.1-8B-Instruct-Training-Data
library_name: transformers
license: other
pipeline_tag: text-generation
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: llama_factory_output_dir
    results: []

📃 Paper

Project Page: https://zaidkhan.me/EFAGen

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct trained to generate Executable Functional Abstractions (EFAs) for math problems. The training data for this model can be found here. The model was trained using Llama-Factory and the data is already in Alpaca instruction-tuning format. The "Instruction" field contains a prompt with instructions defining the EFA protocol and a set of static in-context examples (they're the same for all rows). The "Response" field contains the code of the EFA.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 8
  • total_eval_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1