MODEL_NAME_OR_PATH="/data/models/llava/llava-1.5-13b-hf" # model path

TRAIN_DATASETS="/data/align-anything/jiayi/ti2t/refine_gen_wo_res/1021_13b_2000" # dataset path
TRAIN_TEMPLATE="AA_TI2T_Critique" # dataset template
TRAIN_SPLIT="train" # split the dataset

PTX_DATASETS="/data/align-anything/jiayi/ti2t/ti-to-t-instruction-following"
PTX_TEMPLATE="AA_TI2T"
PTX_SPLIT="train"

OUTPUT_DIR="/data/align-anything/jiayi/ti2t/rm_10_22_ours_13b_2000/slice_2392" # output dir
export CUDA_HOME='/data/align-anything/miniconda3/envs/jy-s'
# For wandb online logging
export WANDB_API_KEY="c072b41ab5beb29a43942f29660da87354fd3612"
export NCCL_SOCKET_IFNAME="bond0.212"

# Source the setup script
source ./setup.sh

# Execute deepspeed command
deepspeed \
    --hostfile ./hostfile \
    --master_port ${MASTER_PORT} \
    --module align_anything.trainers.text_image_to_text.dpo \
    --model_name_or_path ${MODEL_NAME_OR_PATH} \
    --train_datasets ${TRAIN_DATASETS} \
    --train_template ${TRAIN_TEMPLATE} \
    --train_split ${TRAIN_SPLIT} \
    --ptx_datasets ${PTX_DATASETS} \
    --ptx_template ${PTX_TEMPLATE} \
    --ptx_split ${PTX_SPLIT} \
    --output_dir ${OUTPUT_DIR} \
    --save_interval 1200 \
    --epochs 5