ColossalAI/applications/Chat/examples/train_prompts.sh
Wenhao Chen b03d64d010
[chat] refactor trainer class (#4080)
* to: add SLTrainer

* refactor: refactor RMTrainer and SFTTrainer

* fix: fix init file

* feat: remove on_learn_epoch fn as not used

* fix: align with modified gemini arguments

* to: add OnPolicyTrainer

* revert: add _on_learn_epoch fn

* refactor: refactor PPOTrainer

* style: rename PPOTrainer argument

* fix: align with modified PPO arguments

* test: align with modified train_prompts arguments

* chore: modify train_prompts

* docs: align with modified arguments

* fix: remove unnecessary output

* fix: move dataloader to fit fn of SLTrainer

* fix: move dataloader to fit fn of OnPolicyTrainer

* fix: modify usage of prompt and pretrain dataloader
2023-06-29 10:48:09 +08:00

26 lines
896 B
Bash
Executable File

set_n_least_used_CUDA_VISIBLE_DEVICES() {
local n=${1:-"9999"}
echo "GPU Memory Usage:"
local FIRST_N_GPU_IDS=$(nvidia-smi --query-gpu=memory.used --format=csv |
tail -n +2 |
nl -v 0 |
tee /dev/tty |
sort -g -k 2 |
awk '{print $1}' |
head -n $n)
export CUDA_VISIBLE_DEVICES=$(echo $FIRST_N_GPU_IDS | sed 's/ /,/g')
echo "Now CUDA_VISIBLE_DEVICES is set to:"
echo "CUDA_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES"
}
set_n_least_used_CUDA_VISIBLE_DEVICES 2
# torchrun --standalone --nproc_per_node=2 train_prompts.py prompts.csv --strategy colossalai_zero2
torchrun --standalone --nproc_per_node=2 train_prompts.py \
--pretrain_dataset /path/to/data.json \
--prompt_dataset /path/to/data.json \
--strategy colossalai_zero2 \
--num_episodes 1 --num_collect_steps 2 --num_update_steps 1 \
--train_batch_size 2