Cuda failure 'invalid argument'

[FSet89]

I'm running finetune_onevision.sh to finetune on my dataset and I get this error:

Traceback (most recent call last): File "/home/ubuntu/LLaVA-NeXT/llava/train/train_mem.py", line 4, in train() File "/home/ubuntu/LLaVA-NeXT/llava/train/train.py", line 1672, in train trainer.train() File "/opt/conda/envs/llava/lib/python3.10/site-packages/transformers/trainer.py", line 1806, in train return inner_training_loop( File "/opt/conda/envs/llava/lib/python3.10/site-packages/transformers/trainer.py", line 2150, in _inner_training_loop tr_loss_step = self.training_step(model, inputs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/transformers/trainer.py", line 3077, in training_step self.accelerator.backward(loss) File "/opt/conda/envs/llava/lib/python3.10/site-packages/accelerate/accelerator.py", line 2151, in backward self.deepspeed_engine_wrapped.backward(loss, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/accelerate/utils/deepspeed.py", line 166, in backward self.engine.backward(loss, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/utils/nvtx.py", line 15, in wrapped_fn ret_val = func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/engine.py", line 1976, in backward self.optimizer.backward(loss, retain_graph=retain_graph) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/utils/nvtx.py", line 15, in wrapped_fn ret_val = func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/zero/stage3.py", line 2213, in backward self.loss_scaler.backward(loss.float(), retain_graph=retain_graph) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/fp16/loss_scaler.py", line 63, in backward scaled_loss.backward(retain_graph=retain_graph) File "/opt/conda/envs/llava/lib/python3.10/site-packages/torch/_tensor.py", line 492, in backward torch.autograd.backward( File "/opt/conda/envs/llava/lib/python3.10/site-packages/torch/autograd/init.py", line 251, in backward Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/utils/nvtx.py", line 15, in wrapped_fn ret_val = func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/zero/stage3.py", line 1132, in reduce_partition_and_remove_grads self.reduce_ready_partitions_and_remove_grads(param) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/zero/stage3.py", line 1483, in reduce_ready_partitions_and_remove_grads self.reduce_independent_p_g_buckets_and_remove_grads(param) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/zero/stage3.py", line 1224, in reduce_independent_p_g_buckets_and_remove_grads self.__reduce_and_partition_ipg_grads() File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/utils/nvtx.py", line 15, in wrapped_fn ret_val = func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/zero/stage3.py", line 1274, in __reduce_and_partition_ipg_grads grad_partitions = self.__avg_scatter_grads(self.params_in_ipg_bucket) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/utils/nvtx.py", line 15, in wrapped_fn ret_val = func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/zero/stage3.py", line 1343, in __avg_scatter_grads grad_partitions_for_rank = reduce_scatter_coalesced(full_grads_for_rank, self.dp_process_group) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/utils/nvtx.py", line 15, in wrapped_fn ret_val = func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/comm/coalesced_collectives.py", line 128, in reduce_scatter_coalesced _torch_reduce_scatter_fn(tensor_partition_flat_buffer, File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/runtime/comm/coalesced_collectives.py", line 23, in _torch_reduce_scatter_fn return instrument_w_nvtx(dist.reduce_scatter_fn)(output_tensor, input_tensor, group=group, async_op=False) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/utils/nvtx.py", line 15, in wrapped_fn ret_val = func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/comm/comm.py", line 257, in reduce_scatter_fn return reduce_scatter_tensor(output_tensor, File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/comm/comm.py", line 117, in log_wrapper return func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/comm/comm.py", line 289, in reduce_scatter_tensor return cdb.reduce_scatter_tensor(output_tensor=output_tensor, File "/opt/conda/envs/llava/lib/python3.10/site-packages/torch/_dynamo/eval_frame.py", line 328, in _fn return fn(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/deepspeed/comm/torch.py", line 263, in reduce_scatter_tensor return self.reduce_scatter_function(output_tensor, File "/opt/conda/envs/llava/lib/python3.10/site-packages/torch/distributed/c10d_logger.py", line 47, in wrapper return func(*args, **kwargs) File "/opt/conda/envs/llava/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py", line 3375, in reduce_scatter_tensor work = group._reduce_scatter_base(output, input, opts) torch.distributed.DistBackendError: NCCL error in: ../torch/csrc/distributed/c10d/ProcessGroupNCCL.cpp:1333, unhandled cuda error (run with NCCL_DEBUG=INFO for details), NCCL version 2.18.1 ncclUnhandledCudaError: Call to CUDA function failed. Last error: Cuda failure 'invalid argument'

This is the modified script:

export OMP_NUM_THREADS=8
export NCCL_IB_DISABLE=0
export NCCL_IB_GID_INDEX=3
export NCCL_SOCKET_IFNAME=ens5
export NCCL_DEBUG=INFO
# TEST
export RANK=0
export PORT=29401
export NNODES=1
export NUM_GPUS=8
export ADDR=0.0.0.0

LLM_VERSION="Qwen/Qwen2-7B-Instruct" 

# for 7b model we recommend bs=1, accum=2, 16 nodes, 128 gpus, lr=1e-5, warmup=0.03
# for 72b model we recommend bs=1, accum=1, 32 nodes, 256 gpus, lr=1e-5, warmup=0.03
LLM_VERSION_CLEAN="${LLM_VERSION//\//_}"
VISION_MODEL_VERSION="google/siglip-so400m-patch14-384"
VISION_MODEL_VERSION_CLEAN="${VISION_MODEL_VERSION//\//_}"

############### Pretrain ################

PROMPT_VERSION="qwen_1_5"

BASE_RUN_NAME="llavanext-${VISION_MODEL_VERSION_CLEAN}-${LLM_VERSION_CLEAN}-mlp2x_gelu-pretrain_blip558k_plain"
echo "BASE_RUN_NAME: ${BASE_RUN_NAME}"

# TEST
MID_RUN_NAME="llavanext-${VISION_MODEL_VERSION_CLEAN}-${LLM_VERSION_CLEAN}-mlp2x_gelu-pretrain_blip558k_plain_MID"


CKPT_PATH=$LLM_VERSION # this could also be the previous stage checkpoint

ACCELERATE_CPU_AFFINITY=1 torchrun --nproc_per_node="${NUM_GPUS}" --nnodes="${NNODES}" --node_rank="${RANK}" --master_addr="${ADDR}" --master_port="${PORT}" \
    llava/train/train_mem.py \
    --deepspeed scripts/zero3.json \
    --model_name_or_path ${CKPT_PATH} \
    --version ${PROMPT_VERSION} \
    --data_path /home/ubuntu/llava_finetuning/finetuning.yaml \
    --image_folder /home/ubuntu/llava_finetuning \
    --video_folder /home/ubuntu/llava_finetuning \
    --pretrain_mm_mlp_adapter="/home/ubuntu/LLaVA-NeXT/llava/checkpoints/projectors/${BASE_RUN_NAME}/mm_projector.bin" \
    --mm_tunable_parts="mm_vision_tower,mm_mlp_adapter,mm_language_model" \
    --mm_vision_tower_lr=2e-6 \
    --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 \
    --group_by_modality_length True \
    --image_aspect_ratio anyres_max_9 \
    --image_grid_pinpoints  "(1x1),...,(6x6)" \
    --mm_patch_merge_type spatial_unpad \
    --bf16 True \
    --run_name $MID_RUN_NAME \
    --output_dir "checkpoints/${MID_RUN_NAME}" \
    --num_train_epochs 1 \
    --per_device_train_batch_size 1 \
    --per_device_eval_batch_size 4 \
    --gradient_accumulation_steps 2 \
    --evaluation_strategy "no" \
    --save_strategy "steps" \
    --save_steps 1000 \
    --save_total_limit 1 \
    --learning_rate 1e-5 \
    --weight_decay 0. \
    --warmup_ratio 0.03 \
    --lr_scheduler_type "cosine" \
    --logging_steps 1 \
    --tf32 True \
    --model_max_length 32768 \
    --gradient_checkpointing True \
    --dataloader_num_workers 4 \
    --lazy_preprocess True \
    --torch_compile True \
    --torch_compile_backend "inductor" \
    --dataloader_drop_last True \
    --frames_upbound 32