File size: 2,481 Bytes
05744dc |
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 |
export WANDB_MODE=disabled
export CUDA_LAUNCH_BLOCKING=1
DATASET=Games
BASE_MODEL=huggyllama/llama-7b
DATA_PATH=./data
OUTPUT_DIR=./ckpt/$DATASET/
torchrun --nproc_per_node=8 --master_port=3324 finetune.py \
--base_model $BASE_MODEL \
--output_dir $OUTPUT_DIR \
--dataset $DATASET \
--data_path $DATA_PATH \
--per_device_batch_size 8 \
--gradient_accumulation_steps 2 \
--learning_rate 5e-5 \
--epochs 4 \
--weight_decay 0.01 \
--save_and_eval_strategy epoch \
--deepspeed ./config/ds_z3_bf16.json \
--bf16 \
--only_train_response \
--tasks seqrec,item2index,index2item,fusionseqrec,itemsearch,preferenceobtain \
--train_prompt_sample_num 1,1,1,1,1,1 \
--train_data_sample_num 0,0,0,100000,0,0 \
--index_file .index.json
cd convert
nohup ./convert.sh $OUTPUT_DIR >convert.log 2>&1 &
cd ..
DATASET=Arts
BASE_MODEL=huggyllama/llama-7b
DATA_PATH=./data
OUTPUT_DIR=./ckpt/$DATASET/
torchrun --nproc_per_node=8 --master_port=3324 finetune.py \
--base_model $BASE_MODEL \
--output_dir $OUTPUT_DIR \
--dataset $DATASET \
--data_path $DATA_PATH \
--per_device_batch_size 8 \
--gradient_accumulation_steps 2 \
--learning_rate 5e-5 \
--epochs 4 \
--weight_decay 0.01 \
--save_and_eval_strategy epoch \
--deepspeed ./config/ds_z3_bf16.json \
--bf16 \
--only_train_response \
--tasks seqrec,item2index,index2item,fusionseqrec,itemsearch,preferenceobtain \
--train_prompt_sample_num 1,1,1,1,1,1 \
--train_data_sample_num 0,0,0,30000,0,0 \
--index_file .index.json
cd convert
nohup ./convert.sh $OUTPUT_DIR >convert.log 2>&1 &
cd ..
DATASET=Instruments
BASE_MODEL=huggyllama/llama-7b
DATA_PATH=./data
OUTPUT_DIR=./ckpt/$DATASET/
torchrun --nproc_per_node=8 --master_port=3324 finetune.py \
--base_model $BASE_MODEL \
--output_dir $OUTPUT_DIR \
--dataset $DATASET \
--data_path $DATA_PATH \
--per_device_batch_size 8 \
--gradient_accumulation_steps 2 \
--learning_rate 5e-5 \
--epochs 4 \
--weight_decay 0.01 \
--save_and_eval_strategy epoch \
--deepspeed ./config/ds_z3_bf16.json \
--bf16 \
--only_train_response \
--tasks seqrec,item2index,index2item,fusionseqrec,itemsearch,preferenceobtain \
--train_prompt_sample_num 1,1,1,1,1,1 \
--train_data_sample_num 0,0,0,20000,0,0 \
--index_file .index.json
cd convert
nohup ./convert.sh $OUTPUT_DIR >convert.log 2>&1 &
cd ..
|