Spaces:
Sleeping
Sleeping
File size: 4,198 Bytes
6376749 |
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 43 44 45 46 47 48 49 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 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 |
export MODEL_PATH='google/gemma-2b'
export MASTER_ADDR="localhost"
export MASTER_PORT="1231"
export GLOO_SOCKET_IFNAME="lo"
export NCCL_SOCKET_IFNAME="lo"
#SVFT_PLAIN
export SAVE_PATH='./Gemma_2B_metamath40k_svft_plain'
CUDA_VISIBLE_DEVICES=0 python3 -m torch.distributed.launch --master_addr ${MASTER_ADDR} --master_port ${MASTER_PORT} --nproc_per_node=1 --use_env train_math.py \
--model_name_or_path $MODEL_PATH \
--data_path "./data/train/MetaMathQA-40K.json" \
--data_length 10000000 \
--bf16 True \
--output_dir $SAVE_PATH \
--per_device_train_batch_size 4 \
--per_device_eval_batch_size 4 \
--gradient_accumulation_steps 16 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 1000 \
--save_total_limit 2 \
--learning_rate 5e-2\
--weight_decay 0. \
--warmup_ratio 0.1 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--num_train_epochs 2 \
--pattern "banded" \
--off_diag 0 \
--target_modules q_proj k_proj v_proj up_proj down_proj o_proj gate_proj \
--adapter_name "svft"
#SVFT_Random_d=16
export SAVE_PATH='./Gemma_2B_metamath40k_svft_16diag_random'
CUDA_VISIBLE_DEVICES=0 python3 -m torch.distributed.launch --master_addr ${MASTER_ADDR} --master_port ${MASTER_PORT} --nproc_per_node=1 --use_env train_math.py \
--model_name_or_path $MODEL_PATH \
--data_path "./data/train/MetaMathQA-40K.json" \
--data_length 10000000 \
--bf16 True \
--output_dir $SAVE_PATH \
--per_device_train_batch_size 4 \
--per_device_eval_batch_size 4 \
--gradient_accumulation_steps 16 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 1000 \
--save_total_limit 2 \
--learning_rate 5e-2\
--weight_decay 0. \
--warmup_ratio 0.1 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--num_train_epochs 2 \
--pattern "random" \
--off_diag 16 \
--target_modules q_proj k_proj v_proj up_proj down_proj o_proj gate_proj \
--adapter_name "svft"
#SVFT_Random_d=16
export SAVE_PATH='./Gemma_2B_metamath40k_svft_16diag_banded'
CUDA_VISIBLE_DEVICES=0 python3 -m torch.distributed.launch --master_addr ${MASTER_ADDR} --master_port ${MASTER_PORT} --nproc_per_node=1 --use_env train_math.py \
--model_name_or_path $MODEL_PATH \
--data_path "./data/train/MetaMathQA-40K.json" \
--data_length 10000000 \
--bf16 True \
--output_dir $SAVE_PATH \
--per_device_train_batch_size 4 \
--per_device_eval_batch_size 4 \
--gradient_accumulation_steps 16 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 1000 \
--save_total_limit 2 \
--learning_rate 5e-3\
--weight_decay 0. \
--warmup_ratio 0.1 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--num_train_epochs 2 \
--pattern "banded" \
--off_diag 16 \
--target_modules q_proj k_proj v_proj up_proj down_proj o_proj gate_proj \
--adapter_name "svft"
#SVFT_Random_d=16
export SAVE_PATH='./Gemma_2B_metamath40k_svft_16diag_topk'
CUDA_VISIBLE_DEVICES=0 python3 -m torch.distributed.launch --master_addr ${MASTER_ADDR} --master_port ${MASTER_PORT} --nproc_per_node=1 --use_env train_math.py \
--model_name_or_path $MODEL_PATH \
--data_path "./data/train/MetaMathQA-40K.json" \
--data_length 10000000 \
--bf16 True \
--output_dir $SAVE_PATH \
--per_device_train_batch_size 4 \
--per_device_eval_batch_size 4 \
--gradient_accumulation_steps 16 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 1000 \
--save_total_limit 2 \
--learning_rate 5e-3\
--weight_decay 0. \
--warmup_ratio 0.1 \
--lr_scheduler_type "cosine" \
--logging_steps 1 \
--num_train_epochs 2 \
--pattern "top_k" \
--off_diag 16 \
--target_modules q_proj k_proj v_proj up_proj down_proj o_proj gate_proj \
--adapter_name "svft"
#EVAL
#python eval_gsm8k.py --model './Gemma_2B_metamath40k_svft_16diag_random' --data_file ../MetaMath/data/test/GSM8K_test.jsonl
#python eval_math.py --model './Gemma_2B_metamath40k_svft_16diag_random' --data_file ../MetaMath/data/test/MATH_test.jsonl
|