mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-09-13 05:01:44 +00:00
27061426f7
* [gemini] remove distributed-related part from colotensor (#4379) * [gemini] remove process group dependency * [gemini] remove tp part from colo tensor * [gemini] patch inplace op * [gemini] fix param op hook and update tests * [test] remove useless tests * [test] remove useless tests * [misc] fix requirements * [test] fix model zoo * [test] fix model zoo * [test] fix model zoo * [test] fix model zoo * [test] fix model zoo * [misc] update requirements * [gemini] refactor gemini optimizer and gemini ddp (#4398) * [gemini] update optimizer interface * [gemini] renaming gemini optimizer * [gemini] refactor gemini ddp class * [example] update gemini related example * [example] update gemini related example * [plugin] fix gemini plugin args * [test] update gemini ckpt tests * [gemini] fix checkpoint io * [example] fix opt example requirements * [example] fix opt example * [example] fix opt example * [example] fix opt example * [gemini] add static placement policy (#4443) * [gemini] add static placement policy * [gemini] fix param offload * [test] update gemini tests * [plugin] update gemini plugin * [plugin] update gemini plugin docstr * [misc] fix flash attn requirement * [test] fix gemini checkpoint io test * [example] update resnet example result (#4457) * [example] update bert example result (#4458) * [doc] update gemini doc (#4468) * [example] update gemini related examples (#4473) * [example] update gpt example * [example] update dreambooth example * [example] update vit * [example] update opt * [example] update palm * [example] update vit and opt benchmark * [hotfix] fix bert in model zoo (#4480) * [hotfix] fix bert in model zoo * [test] remove chatglm gemini test * [test] remove sam gemini test * [test] remove vit gemini test * [hotfix] fix opt tutorial example (#4497) * [hotfix] fix opt tutorial example * [hotfix] fix opt tutorial example
25 lines
687 B
Bash
25 lines
687 B
Bash
#!/bin/bash
|
|
set -xe
|
|
pip install -r requirements.txt
|
|
|
|
HF_DATASETS_OFFLINE=1
|
|
TRANSFORMERS_OFFLINE=1
|
|
DIFFUSERS_OFFLINE=1
|
|
|
|
# "torch_ddp" "torch_ddp_fp16" "low_level_zero"
|
|
for plugin in "gemini"; do
|
|
torchrun --nproc_per_node 4 --standalone train_dreambooth_colossalai.py \
|
|
--pretrained_model_name_or_path="/data/dreambooth/diffuser/stable-diffusion-v1-4" \
|
|
--instance_data_dir="/data/dreambooth/Teyvat/data" \
|
|
--output_dir="./weight_output" \
|
|
--instance_prompt="a picture of a dog" \
|
|
--resolution=512 \
|
|
--plugin=$plugin \
|
|
--train_batch_size=1 \
|
|
--learning_rate=5e-6 \
|
|
--lr_scheduler="constant" \
|
|
--lr_warmup_steps=0 \
|
|
--test_run=True \
|
|
--num_class_images=200
|
|
done
|