Initial commit

2025-04-13 09:30:46 +08:00
commit 4f8972e88a
248 changed files with 34689 additions and 0 deletions
@@ -0,0 +1,64 @@
+export OMP_NUM_THREADS=8
+export NCCL_IB_DISABLE=0
+export NCCL_IB_GID_INDEX=3
+# export NCCL_IB_HCA=${ARNOLD_RDMA_DEVICE}
+export NCCL_SOCKET_IFNAME=eth0
+export NCCL_DEBUG=INFO
+
+VISION_MODEL_VERSION="openai/clip-vit-large-patch14-336"
+VISION_MODEL_VERSION_CLEAN="${VISION_MODEL_VERSION//\//_}"
+
+############### Pretrain ################
+
+# Stage 2
+PROMPT_VERSION="qwen_1_5"
+
+#torchrun --nproc_per_node="${ARNOLD_WORKER_GPU}" --nnodes="${ARNOLD_WORKER_NUM}" --node_rank="${ARNOLD_ID}" --master_addr="${METIS_WORKER_0_HOST}" --master_port="${port_in_cmd}" \
+ACCELERATE_CPU_AFFINITY=1 torchrun --nproc_per_node="${ARNOLD_WORKER_GPU}" --nnodes="${ARNOLD_WORKER_NUM}" --node_rank="${ARNOLD_ID}" --master_addr="${METIS_WORKER_0_HOST}" --master_port="${port_in_cmd}" \
+    llava/train/train_dpo.py \
+    --deepspeed scripts/zero3.json \
+    --model_name_or_path lmms-lab/LongVA-7B \
+    --version $PROMPT_VERSION \
+    --dpo_alpha 1.0 --beta 0.1 --gamma 0 \
+    --data_path="/data/llava_video/shareVideoGPTV/dpo/sft_dpo_17k.jsonl" \
+    --image_folder /data/llava_data \
+    --video_folder /llava_video/shareVideoGPTV/frames/all_frames/ \
+    --mm_tunable_parts="mm_vision_tower,mm_mlp_adapter,mm_language_model" \
+    --vision_tower ${VISION_MODEL_VERSION} \
+    --mm_projector_type mlp2x_gelu \
+    --mm_vision_select_layer -2 \
+    --mm_use_im_start_end False \
+    --mm_use_im_patch_token False \
+    --mm_spatial_pool_stride 2 \
+    --mm_resampler_type "spatial_pool" \
+    --mm_spatial_pool_out_channels 1024 \
+    --group_by_modality_length True \
+    --image_aspect_ratio anyres \
+    --image_grid_pinpoints "[(336, 672), (672, 336), (672, 672), (1008, 336), (336, 1008)]" \
+    --mm_patch_merge_type unires \
+    --bf16 True \
+    --run_name $MID_RUN_NAME \
+    --output_dir "/checkpoints/${MID_RUN_NAME}" \
+    --num_train_epochs 3 \
+    --per_device_train_batch_size 1 \
+    --per_device_eval_batch_size 4 \
+    --gradient_accumulation_steps 16 \
+    --evaluation_strategy "no" \
+    --save_strategy "steps" \
+    --save_steps 3000 \
+    --save_total_limit 1 \
+    --learning_rate 5e-7 \
+    --weight_decay 0. \
+    --warmup_ratio 0.1 \
+    --lr_scheduler_type "linear" \
+    --logging_steps 1 \
+    --tf32 True \
+    --model_max_length 32768 \
+    --gradient_checkpointing True \
+    --dataloader_num_workers 16 \
+    --lazy_preprocess True \
+    --report_to wandb \
+    --torch_compile True \
+    --torch_compile_backend "inductor" \
+    --dataloader_drop_last True \
+    --attn_implementation sdpa