metadata
library_name: peft
tags:
- code
- instruct
- llama2
datasets:
- HuggingFaceH4/no_robots
base_model: meta-llama/Llama-2-7b-hf
license: apache-2.0
Finetuning Overview:
Model Used: meta-llama/Llama-2-7b-hf
Dataset: HuggingFaceH4/no_robots
Dataset Insights:
No Robots is a high-quality dataset of 10,000 instructions and demonstrations created by skilled human annotators. This data can be used for supervised fine-tuning (SFT) to make language models follow instructions better.
Finetuning Details:
With the utilization of MonsterAPI's LLM finetuner, this finetuning:
- Was achieved with great cost-effectiveness.
- Completed in a total duration of 39mins 4secs for 1 epoch using an A6000 48GB GPU.
- Costed
$1.313
for the entire epoch.
Hyperparameters & Additional Details:
- Epochs: 1
- Cost Per Epoch: $1.313
- Total Finetuning Cost: $1.313
- Model Path: meta-llama/Llama-2-7b-hf
- Learning Rate: 0.0002
- Data Split: 99% train 1% validation
- Gradient Accumulation Steps: 4
- lora r: 32
- lora alpha: 64
Prompt Structure
### INSTRUCTION:
[instruction]
### RESPONSE:
[text]
Train loss :
license: apache-2.0