|
--- |
|
library_name: peft |
|
tags: |
|
- meta-llama |
|
- code |
|
- instruct |
|
- databricks-dolly-15k |
|
- Llama-2-70b-hf |
|
datasets: |
|
- databricks/databricks-dolly-15k |
|
base_model: meta-llama/Llama-2-70b-hf |
|
license: apache-2.0 |
|
--- |
|
|
|
Note: This repo contains the base weights already merged with lora, pls check qblocks/llama2_70B_dolly15k repo for LORA adapters only |
|
|
|
|
|
### Finetuning Overview: |
|
|
|
**Model Used:** meta-llama/Llama-2-70b-hf |
|
**Dataset:** Databricks-dolly-15k |
|
|
|
#### Dataset Insights: |
|
|
|
The Databricks-dolly-15k dataset is an impressive compilation of over 15,000 records, made possible by the hard work and dedication of a multitude of Databricks professionals. It has been tailored to: |
|
|
|
- Elevate the interactive capabilities of ChatGPT-like systems. |
|
- Provide prompt/response pairs spanning eight distinct instruction categories, inclusive of the seven categories from the InstructGPT paper and an exploratory open-ended category. |
|
- Ensure genuine and original content, largely offline-sourced with exceptions for Wikipedia in particular categories, and free from generative AI influences. |
|
|
|
The contributors had the opportunity to rephrase and answer queries from their peers, highlighting a focus on accuracy and clarity. Additionally, some data subsets feature Wikipedia-sourced reference texts, marked by bracketed citation numbers like [42]. |
|
|
|
#### Finetuning Details: |
|
|
|
Using [MonsterAPI](https://monsterapi.ai)'s user-friendly [LLM finetuner](https://docs.monsterapi.ai/fine-tune-a-large-language-model-llm), the finetuning: |
|
|
|
- Stands out for its cost-effectiveness. |
|
- Was executed in a total of 17.5 hours for 3 epochs with an A100 80GB GPU. |
|
- Broke down to just 5.8 hours and `$19.25` per epoch, culminating in a combined cost of `$57.75` for all epochs. |
|
|
|
#### Hyperparameters & Additional Details: |
|
|
|
- **Epochs:** 3 |
|
- **Cost Per Epoch:** $19.25 |
|
- **Total Finetuning Cost:** $57.75 |
|
- **Model Path:** meta-llama/Llama-2-70b-hf |
|
- **Learning Rate:** 0.0002 |
|
- **Data Split:** Training 90% / Validation 10% |
|
- **Gradient Accumulation Steps:** 4 |
|
|
|
--- |
|
|
|
### Prompt Structure: |
|
|
|
|
|
``` |
|
### INSTRUCTION: |
|
[instruction] |
|
|
|
[context] |
|
|
|
### RESPONSE: |
|
[response] |
|
``` |
|
|
|
Loss metrics |
|
|
|
Training loss (Blue) Validation Loss (orange): |
|
 |
|
|
|
--- |
|
|
|
license: apache-2.0 |
