TypeError: get_logger() got an unexpected keyword argument 'log_level' about text-to-video-finetuning

[ExponentialML]

Hi, I am trying to run your script but it always shows me this error. Another thing is that it's not possible for me to install triton. It's like the repo doesn't exist anymore.

Error caught was: No module named 'triton'
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ C:\Users\Life\Text-To-Video-Finetuning\train.py:43 in <module>                                   │
│                                                                                                  │
│    40 # Will error if the minimal version of diffusers is not installed. Remove at your own ri   │
│    41 check_min_version("0.10.0.dev0")                                                           │
│    42                                                                                            │
│ ❱  43 logger = get_logger(__name__, log_level="INFO")                                            │
│    44                                                                                            │
│    45 def create_logging(logging, logger, accelerator):                                          │
│    46 │   logging.basicConfig(                                                                   │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
TypeError: get_logger() got an unexpected keyword argument 'log_level'

Can you try pip install accelerate -U and see if that solves the issue?
Also on your issue about Triton, pip install triton seems to work for me. Which version of Python are you running?

[Devalinor]

It seems like pip install accelerate -U has worked
I am using python 3.10.7
Now I am getting this error

│   377 │   │   │   │   │   f" {pretrained_model_name_or_path}:\n{err}"                            │
│   378 │   │   │   │   )                                                                          │
│   379 │   │   │   except ValueError:                                                             │
│ ❱ 380 │   │   │   │   raise EnvironmentError(                                                    │
│   381 │   │   │   │   │   f"We couldn't connect to '{HUGGINGFACE_CO_RESOLVE_ENDPOINT}' to load   │
│   382 │   │   │   │   │   f" in the cached files and it looks like {pretrained_model_name_or_p   │
│   383 │   │   │   │   │   f" directory containing a {cls.config_name} file.\nCheckout your int   │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it
looks like ./models/model_scope_diffusers/ is not the path to a directory containing a scheduler_config.json file.
Checkout your internet connection or see how to run the library in offline mode at
'https://huggingface.co/docs/diffusers/installation#offline-mode'.

[ExponentialML]

@Devalinor You need to go here and download the files.

https://huggingface.co/damo-vilab/text-to-video-ms-1.7b/tree/main.

1. Place them in a folder ./some_directory/modelscope
2. The folder structure must be the same as above.

You can also try this in the command line, but you may get all of the mode files. Then you can point to the directory it was downloaded to in your config.

git lfs install
git clone https://huggingface.co/damo-vilab/text-to-video-ms-1.7b

[JPW0080]

Also, Triton on Win:
pip install https://huggingface.co/r4ziel/xformers_pre_built/resolve/main/triton-2.0.0-cp310-cp310-win_amd64.whl