codezakh/EFAGen-Llama-3.1-Instruct-8B

📃 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