mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-05-21 06:40:08 +00:00
7b9b86441f
* feat: modify forward fn of critic and reward model * feat: modify calc_action_log_probs * to: add wandb in sft and rm trainer * feat: update train_sft * feat: update train_rm * style: modify type annotation and add warning * feat: pass tokenizer to ppo trainer * to: modify trainer base and maker base * feat: add wandb in ppo trainer * feat: pass tokenizer to generate * test: update generate fn tests * test: update train tests * fix: remove action_mask * feat: remove unused code * fix: fix wrong ignore_index * fix: fix mock tokenizer * chore: update requirements * revert: modify make_experience * fix: fix inference * fix: add padding side * style: modify _on_learn_batch_end * test: use mock tokenizer * fix: use bf16 to avoid overflow * fix: fix workflow * [chat] fix gemini strategy * [chat] fix * sync: update colossalai strategy * fix: fix args and model dtype * fix: fix checkpoint test * fix: fix requirements * fix: fix missing import and wrong arg * fix: temporarily skip gemini test in stage 3 * style: apply pre-commit * fix: temporarily skip gemini test in stage 1&2 --------- Co-authored-by: Mingyan Jiang <1829166702@qq.com>
26 lines
772 B
Bash
Executable File
26 lines
772 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_reward_model.py \
|
|
--pretrain 'gpt2' \
|
|
--model 'gpt2' \
|
|
--strategy colossalai_zero2 \
|
|
--loss_fn 'log_exp' \
|
|
--dataset 'Anthropic/hh-rlhf' \
|
|
--batch_size 16 \
|
|
--max_epochs 10
|