Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
test_ci.sh 6.1 KB
Newer Older
Fazzie-Maqianli's avatar
[Coati] first commit (#3283)  
Fazzie-Maqianli committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42 
#!/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
Camille Zhong's avatar
[chatgpt] add pre-trained model RoBERTa for RLHF stage 2 & 3 (#3223)  
Camille Zhong committed
43
44
45
46
47
48
49 
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
Fazzie-Maqianli's avatar
[Coati] first commit (#3283)  
Fazzie-Maqianli committed
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77 
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
Camille Zhong's avatar
[chatgpt] add pre-trained model RoBERTa for RLHF stage 2 & 3 (#3223)  
Camille Zhong committed
78
79
80
81
82
83
84 
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
Fazzie-Maqianli's avatar
[Coati] first commit (#3283)  
Fazzie-Maqianli committed
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110 
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
Camille Zhong's avatar
[chatgpt] add pre-trained model RoBERTa for RLHF stage 2 & 3 (#3223)  
Camille Zhong committed
111
112
113
114
115
116 
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
Fazzie-Maqianli's avatar
[Coati] first commit (#3283)  
Fazzie-Maqianli committed
117 
rm -rf ${BASE}/rm_ckpt.pt