mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-05-01 21:26:42 +00:00
8bccb72c8d
* Add RoBERTa for RLHF Stage 2 & 3 (test) RoBERTa for RLHF Stage 2 & 3 (still in testing) Revert "Add RoBERTa for RLHF Stage 2 & 3 (test)" This reverts commit06741d894d. Add RoBERTa for RLHF stage 2 & 3 1. add roberta folder under model folder 2. add roberta option in train_reward_model.py 3. add some test in testci Update test_ci.sh Revert "Update test_ci.sh" This reverts commit 9c7352b81766f3177d31eeec0ec178a301df966a. Add RoBERTa for RLHF Stage 2 & 3 (test) RoBERTa for RLHF Stage 2 & 3 (still in testing) Revert "Add RoBERTa for RLHF Stage 2 & 3 (test)" This reverts commit06741d894d. Add RoBERTa for RLHF stage 2 & 3 1. add roberta folder under model folder 2. add roberta option in train_reward_model.py 3. add some test in testci Update test_ci.sh Revert "Update test_ci.sh" This reverts commit 9c7352b81766f3177d31eeec0ec178a301df966a. update roberta with coati chat ci update Revert "chat ci update" This reverts commit 17ae7ae01fa752bd3289fc39069868fde99cf846. * Update README.md Update README.md * update readme * Update test_ci.sh
21 lines
759 B
Bash
Executable File
21 lines
759 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 --prompt_dataset /path/to/data.json --strategy colossalai_zero2
|