This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# This is a modified version of TRL's `SFTTrainer` example (https://github.com/huggingface/trl/blob/main/examples/scripts/sft_trainer.py), | |
# adapted to run with DeepSpeed ZeRO-3 and Mistral-7B-V1.0. The settings below were run on 1 node of 8 x A100 (80GB) GPUs. | |
# | |
# Usage: | |
# - Install the latest transformers & accelerate versions: `pip install -U transformers accelerate` | |
# - Install deepspeed: `pip install deepspeed==0.9.5` | |
# - Install TRL from main: pip install git+https://github.com/huggingface/trl.git | |
# - Clone the repo: git clone github.com/huggingface/trl.git | |
# - Copy this Gist into trl/examples/scripts | |
# - Run from root of trl repo with: accelerate launch --config_file=examples/accelerate_configs/deepspeed_zero3.yaml --gradient_accumulation_steps 8 examples/scripts/sft_trainer.py |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# UPDATED: 5-MAY-2023 | |
from multiprocessing import Pool, freeze_support | |
from time import sleep | |
import streamlit as st | |
# https://discuss.streamlit.io/t/stqdm-a-tqdm-like-progress-bar-for-streamlit/10097 | |
# pip install stqdm | |
from stqdm import stqdm |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
license: gpl-3.0 | |
height: 950 | |
border: no |