Issue on ray library

[Milardkh]

Path: /neuralforecast/docs/tutorials/forecasting_tft.html
Consider the following my system environment and code snippet

Python version: 3.12.11 | packaged by conda-forge | (main, Jun 4 2025, 14:29:09) [MSC v.1943 64 bit (AMD64)]
PyTorch version: 2.5.1
CUDA available: True
CUDA device: NVIDIA GeForce RTX 4070 Ti SUPER
Pandas version: 2.3.0
Matplotlib version: 3.10.3
NeuralForecast version: 3.0.0

import os
os.environ["RAY_DASHBOARD_HOST"] = "disable"
os.environ["RAY_DISABLE_DASHBOARD"] = "1"

import ray
ray.init(ignore_reinit_error=True, include_dashboard=False)

from ray import tune
from ray.tune import RunConfig

from neuralforecast.auto import AutoTFT
from neuralforecast.core import NeuralForecast
from neuralforecast.losses.pytorch import MAE

import logging
logging.getLogger(name="pytorch_lightning").setLevel(level=logging.WARNING)

horizon = 24
models = [
    AutoTFT(
        h=horizon,
        loss=MAE(),
        config=None,
        num_samples=3,
        backend="ray"
    )
]

nf = NeuralForecast(models=models, freq='h', local_scaler_type=None)
nf.fit(df=Y_df)

The following error appears
2025-06-26 17:28:01,679 ERROR services.py:1362 -- Failed to start the dashboard , return code 3221226505
2025-06-26 17:28:01,679 ERROR services.py:1387 -- Error should be written to 'dashboard.log' or 'dashboard.err'. We are printing the last 20 lines for you. See 'https://docs.ray.io/en/master/ray-observability/user-guides/configure-logging.html#logging-directory-structure' to find where the log file is.
2025-06-26 17:28:01,684 ERROR services.py:1431 --
The last 20 lines of C:\Users\ROG\AppData\Local\Temp\ray\session_2025-06-26_17-28-00_312903_3324\logs\dashboard.log (it contains the error message from the dashboard):
Traceback (most recent call last):
File "c:\Users\ROG\anaconda3\envs\neuralforecast\Lib\site-packages\ray\dashboard\dashboard.py", line 247, in
logging_utils.redirect_stdout_stderr_if_needed(
File "c:\Users\ROG\anaconda3\envs\neuralforecast\Lib\site-packages\ray_private\logging_utils.py", line 48, in redirect_stdout_stderr_if_needed
sys.stderr = open_log(stderr_fileno, unbuffered=True, closefd=False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\Users\ROG\anaconda3\envs\neuralforecast\Lib\site-packages\ray_private\utils.py", line 446, in open_log
stream = open(path, **kwargs)
^^^^^^^^^^^^^^^^^^^^
OSError: [WinError 6] The handle is invalid

2025-06-26 17:28:01,836 INFO worker.py:1888 -- Started a local Ray instance.