mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-05-30 02:45:18 +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
24 lines
600 B
Bash
24 lines
600 B
Bash
set -x
|
|
$(cd `dirname $0`;pwd)
|
|
export TRAIN_STEP=4
|
|
|
|
for MODEL_TYPE in "gpt2_medium"; do
|
|
for DISTPLAN in "CAI_Gemini"; do
|
|
for BATCH_SIZE in 2; do
|
|
for GPUNUM in 1 4; do
|
|
MODEL_TYPE=${MODEL_TYPE} DISTPLAN=${DISTPLAN} BATCH_SIZE=${BATCH_SIZE} GPUNUM=${GPUNUM} \
|
|
bash ./run_gemini.sh
|
|
done
|
|
done
|
|
done
|
|
|
|
for DISTPLAN in "CAI_ZeRO2" "CAI_ZeRO1"; do
|
|
for BATCH_SIZE in 2; do
|
|
for GPUNUM in 1 4; do
|
|
MODEL_TYPE=${MODEL_TYPE} DISTPLAN=${DISTPLAN} BATCH_SIZE=${BATCH_SIZE} GPUNUM=${GPUNUM} \
|
|
bash ./run_gemini.sh
|
|
done
|
|
done
|
|
done
|
|
done
|