RuntimeError: Parent directory ./Video-ChatGPT_7B-1.1_Checkpoints/checkpoint-3000 does not exist.

[tianguang2525]

When the steps run tosave_steps, the above error will be reported

[tianguang2525]

I see mm_mlp_adapter is saved in /home/develop/fyy/Video-ChatGPT-main/Video-ChatGPT_7B-1.1_Checkpoints/mm_projector, is there anything need to save? or I download the wrong package

[HaotianLiu123]

I also have the same problem.

[mmaaz60]

Hi @tianguang2525 @HaotianLiu123,

Thank you for your interest in our work and apologies for the late reply. Were you able to solve the issue?

If not, please provide some more information regarding the issue, such as, what command you are running and where exactly the error is coming. This information would be helpful to reproduce the error on my side and provide further help. Thanks.

[rjccv]

I had the same error.

27%|██▋       | 3000/11214 [4:55:11<13:22:58,  5.87s/it]Traceback (most recent call last):

  File "/home/usr/Video-ChatGPT/video_chatgpt/train/train_mem.py", line 9, in <module>
    train()
  File "/home/usr/Video-ChatGPT/video_chatgpt/train/train.py", line 828, in train
    trainer.train()
  File "/home/usr/my-envs/vid-chatgpt/lib/python3.10/site-packages/transformers/trainer.py", line 1932, in train
    return inner_training_loop(
  File "/home/usr/my-envs/vid-chatgpt/lib/python3.10/site-packages/transformers/trainer.py", line 2345, in _inner_training_loop
    self._maybe_log_save_evaluate(tr_loss, grad_norm, model, trial, epoch, ignore_keys_for_eval)
  File "/home/usr/my-envs/vid-chatgpt/lib/python3.10/site-packages/transformers/trainer.py", line 2796, in _maybe_log_save_evaluate
    self._save_checkpoint(model, trial, metrics=metrics)
  File "/home/usr/my-envs/vid-chatgpt/lib/python3.10/site-packages/transformers/trainer.py", line 2879, in _save_checkpoint
    self._save_optimizer_and_scheduler(output_dir)
  File "/home/usr/my-envs/vid-chatgpt/lib/python3.10/site-packages/transformers/trainer.py", line 2995, in _save_optimizer_and_scheduler
    torch.save(self.optimizer.state_dict(), os.path.join(output_dir, OPTIMIZER_NAME))
  File "/home/usr/my-envs/vid-chatgpt/lib/python3.10/site-packages/torch/serialization.py", line 627, in save
    with _open_zipfile_writer(f) as opened_zipfile:
  File "/home/usr/my-envs/vid-chatgpt/lib/python3.10/site-packages/torch/serialization.py", line 501, in _open_zipfile_writer
    return container(name_or_buffer)
  File "/home/usr/my-envs/vid-chatgpt/lib/python3.10/site-packages/torch/serialization.py", line 472, in __init__
    super().__init__(torch._C.PyTorchFileWriter(self.name))
RuntimeError: Parent directory ./Video-ChatGPT_7B-1.1_Checkpoints_Vids/checkpoint-3000 does not exist.
 27%|██▋       | 3000/11214 [4:55:15<13:28:24,  5.91s/it]

I am not using the transformers version which is suggested, but rather transformers==4.42.3. I wonder if that could be causing this issue.

[rjccv]

I have started a fresh environment with the original package versions from requirements.txt and still experience the same issue. This is the script I use for training.

export PYTHONPATH="./:$PYTHONPATH"
python video_chatgpt/train/train_mem.py \
--model_name_or_path /home/usr/Video-ChatGPT/LLaVA-7B-Lightening-v1-1 \
--version v1 \
--data_path /home/usr/Video-ChatGPT/qa_video.json \
--video_folder /home/usr/pkls \
--tune_mm_mlp_adapter True \
--mm_use_img_start_end \
--lazy_preprocess True \
--bf16 True \
--output_dir /home/usr/Video-ChatGPT/Video-ChatGPT_7B-1.1_Checkpoints_Vids_Start_End \
--num_train_epochs 3 \
--per_device_train_batch_size 8 \
--per_device_eval_batch_size 2 \
--gradient_accumulation_steps 2 \
--evaluation_strategy "no" \
--save_strategy "steps" \
--save_steps 3000 \
--save_total_limit 3 \
--learning_rate 2e-5 \
--weight_decay 0. \
--warmup_ratio 0.03 \
--lr_scheduler_type "cosine" \
--logging_steps 100 \
--tf32 True \
--model_max_length 2048 \
--gradient_checkpointing True \