We finetuned huggyllama/llama-7b on tatsu-lab/alpaca Dataset for 5 epochs or ~ 25,000 steps using MonsterAPI no-code LLM finetuner.
This dataset is HuggingFaceH4/tatsu-lab/alpaca unfiltered, removing 36 instances of blatant alignment.
The finetuning session got completed in 4 hours and costed us only $16 for the entire finetuning run!
Hyperparameters & Run details:
- Model Path: huggyllama/llama-7b
- Dataset: tatsu-lab/alpaca
- Learning rate: 0.0003
- Number of epochs: 5
- Data split: Training: 90% / Validation: 10%
- Gradient accumulation steps: 1
