github
/
ColossalAI
mirror of https://github.com/hpcaitech/ColossalAI
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
ColossalAI/applications/Chat/examples/test_ci.sh

118 lines
6.1 KiB
Bash
Raw Normal View History

[Coati] first commit (#3283)
2023-03-28 12:25:36 +00:00
#!/usr/bin/env bash
set -xue
if [ -z "$PROMPT_PATH" ]; then
echo "Please set \$PROMPT_PATH to the path to prompts csv."
exit 1
fi
BASE=$(realpath $(dirname $0))
export OMP_NUM_THREADS=8
# install requirements
pip install -r ${BASE}/requirements.txt
# train dummy
python ${BASE}/train_dummy.py --strategy naive --num_episodes 1 \
--max_timesteps 2 --update_timesteps 2 \
--max_epochs 1 --train_batch_size 2 --lora_rank 4
torchrun --standalone --nproc_per_node=2 ${BASE}/train_dummy.py \
--strategy colossalai_gemini --num_episodes 1 --max_timesteps 2 \
--update_timesteps 2 --max_epochs 1 --train_batch_size 2\
--pretrain 'facebook/opt-350m' --model opt --lora_rank 4\
--save_path ${BASE}/actor_checkpoint_dummy.pt
python ${BASE}/inference.py --model_path ${BASE}/actor_checkpoint_dummy.pt --pretrain 'facebook/opt-350m' --model opt
torchrun --standalone --nproc_per_node=2 ${BASE}/train_dummy.py \
--strategy ddp --num_episodes 1 --max_timesteps 2 \
--update_timesteps 2 --max_epochs 1 --train_batch_size 2\
--pretrain 'facebook/opt-350m' --model opt --lora_rank 4\
--save_path ${BASE}/actor_checkpoint_dummy.pt
python ${BASE}/inference.py --model_path ${BASE}/actor_checkpoint_dummy.pt --pretrain 'facebook/opt-350m' --model opt
torchrun --standalone --nproc_per_node=2 ${BASE}/train_dummy.py \
--strategy colossalai_zero2 --num_episodes 1 --max_timesteps 2 \
--update_timesteps 2 --max_epochs 1 --train_batch_size 2\
--pretrain 'gpt2' --model gpt2 --lora_rank 4\
--save_path ${BASE}/actor_checkpoint_dummy.pt
python ${BASE}/inference.py --model_path ${BASE}/actor_checkpoint_dummy.pt --pretrain 'gpt2' --model gpt2
[chatgpt] add pre-trained model RoBERTa for RLHF stage 2 & 3 (#3223) * 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 commit 06741d894dcbe958acd4e10d771f22275e20e368. * 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 * add test for reward model training * 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 commit 06741d894dcbe958acd4e10d771f22275e20e368. * 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
2023-04-03 02:11:03 +00:00
torchrun --standalone --nproc_per_node=2 ${BASE}/train_dummy.py \
--strategy colossalai_zero2 --num_episodes 1 --max_timesteps 2 \
--update_timesteps 2 --max_epochs 1 --train_batch_size 2\
--pretrain 'roberta-base' --model roberta --lora_rank 4\
--save_path ${BASE}/actor_checkpoint_dummy.pt
python ${BASE}/inference.py --model_path ${BASE}/actor_checkpoint_dummy.pt --pretrain 'roberta-base' --model roberta
[Coati] first commit (#3283)
2023-03-28 12:25:36 +00:00
rm -rf ${BASE}/actor_checkpoint_dummy.pt
# train prompts
python ${BASE}/train_prompts.py $PROMPT_PATH --strategy naive --num_episodes 1 \
--max_timesteps 2 --update_timesteps 2 \
--max_epochs 1 --train_batch_size 2 --lora_rank 4
torchrun --standalone --nproc_per_node=2 ${BASE}/train_prompts.py $PROMPT_PATH \
--strategy colossalai_zero2 --num_episodes 1 --max_timesteps 2 \
--update_timesteps 2 --max_epochs 1 --train_batch_size 2\
--pretrain 'facebook/opt-350m' --model opt --lora_rank 4\
--save_path ${BASE}/actor_checkpoint_prompts.pt
python ${BASE}/inference.py --model_path ${BASE}/actor_checkpoint_prompts.pt --pretrain 'facebook/opt-350m' --model opt
torchrun --standalone --nproc_per_node=2 ${BASE}/train_prompts.py $PROMPT_PATH \
--strategy ddp --num_episodes 1 --max_timesteps 2 \
--update_timesteps 2 --max_epochs 1 --train_batch_size 2\
--pretrain 'gpt2' --model gpt2 --lora_rank 4\
--save_path ${BASE}/actor_checkpoint_prompts.pt
python ${BASE}/inference.py --model_path ${BASE}/actor_checkpoint_prompts.pt --pretrain 'gpt2' --model gpt2
torchrun --standalone --nproc_per_node=2 ${BASE}/train_prompts.py $PROMPT_PATH \
--strategy colossalai_gemini --num_episodes 1 --max_timesteps 2 \
--update_timesteps 2 --max_epochs 1 --train_batch_size 2\
--pretrain 'gpt2' --model gpt2 --lora_rank 4\
--save_path ${BASE}/actor_checkpoint_prompts.pt
python ${BASE}/inference.py --model_path ${BASE}/actor_checkpoint_prompts.pt --pretrain 'gpt2' --model gpt2
[chatgpt] add pre-trained model RoBERTa for RLHF stage 2 & 3 (#3223) * 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 commit 06741d894dcbe958acd4e10d771f22275e20e368. * 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 * add test for reward model training * 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 commit 06741d894dcbe958acd4e10d771f22275e20e368. * 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
2023-04-03 02:11:03 +00:00
torchrun --standalone --nproc_per_node=2 ${BASE}/train_prompts.py $PROMPT_PATH \
--strategy colossalai_zero2 --num_episodes 1 --max_timesteps 2 \
--update_timesteps 2 --max_epochs 1 --train_batch_size 2\
--pretrain 'roberta-base' --model roberta --lora_rank 4\
--save_path ${BASE}/actor_checkpoint_prompts.pt
python ${BASE}/inference.py --model_path ${BASE}/actor_checkpoint_prompts.pt --pretrain 'roberta-base' --model roberta
[Coati] first commit (#3283)
2023-03-28 12:25:36 +00:00
rm -rf ${BASE}/actor_checkpoint_prompts.pt
# train rm
torchrun --standalone --nproc_per_node=2 ${BASE}/train_reward_model.py \
--pretrain 'facebook/opt-350m' --model 'opt' \
--strategy colossalai_zero2 --loss_fn 'log_sig'\
--dataset 'Anthropic/hh-rlhf' --subset 'harmless-base'\
--test True --lora_rank 4
torchrun --standalone --nproc_per_node=2 ${BASE}/train_reward_model.py \
--pretrain 'gpt2' --model 'gpt2' \
--strategy colossalai_gemini --loss_fn 'log_exp'\
--dataset 'Dahoas/rm-static' --test True --lora_rank 4
torchrun --standalone --nproc_per_node=2 ${BASE}/train_reward_model.py \
--pretrain 'bigscience/bloom-560m' --model 'bloom' \
--strategy colossalai_zero2 --loss_fn 'log_sig'\
--dataset 'Anthropic/hh-rlhf' --subset 'harmless-base'\
--test True --lora_rank 4
torchrun --standalone --nproc_per_node=2 ${BASE}/train_reward_model.py \
--pretrain 'microsoft/deberta-v3-large' --model 'deberta' \
--strategy colossalai_zero2 --loss_fn 'log_sig'\
--dataset 'Anthropic/hh-rlhf' --subset 'harmless-base'\
--test True --lora_rank 4
[chatgpt] add pre-trained model RoBERTa for RLHF stage 2 & 3 (#3223) * 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 commit 06741d894dcbe958acd4e10d771f22275e20e368. * 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 * add test for reward model training * 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 commit 06741d894dcbe958acd4e10d771f22275e20e368. * 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
2023-04-03 02:11:03 +00:00
torchrun --standalone --nproc_per_node=2 ${BASE}/train_reward_model.py \
--pretrain 'roberta-base' --model 'roberta' \
--strategy colossalai_zero2 --loss_fn 'log_exp'\
--dataset 'Anthropic/hh-rlhf' --subset 'harmless-base'\
--test True --lora_rank 4
[Coati] first commit (#3283)
2023-03-28 12:25:36 +00:00
rm -rf ${BASE}/rm_ckpt.pt