Getting error while training model online

here is the error

 C:\Users\sanchit\PycharmProjects\chatbots\venv\Scripts\python.exe C:/Users/sanchit/PycharmProjects/chatbots/train_init.py
C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint8 = np.dtype([("qint8", np.int8, 1)])
C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint8 = np.dtype([("quint8", np.uint8, 1)])
C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:528: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint16 = np.dtype([("qint16", np.int16, 1)])
C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:529: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_quint16 = np.dtype([("quint16", np.uint16, 1)])
C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:530: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  _np_qint32 = np.dtype([("qint32", np.int32, 1)])
C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\tensorflow\python\framework\dtypes.py:535: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
Processed Story Blocks: 100%|██████████| 4/4 [00:00<00:00, 4006.98it/s, # trackers=1]
Processed Story Blocks: 100%|██████████| 4/4 [00:00<00:00, 1334.38it/s, # trackers=4]
Processed Story Blocks: 100%|██████████| 4/4 [00:00<00:00, 181.90it/s, # trackers=20]
Processed Story Blocks: 100%|██████████| 4/4 [00:00<00:00, 173.89it/s, # trackers=20]
Traceback (most recent call last):
  File "C:/Users/sanchit/PycharmProjects/chatbots/train_init.py", line 11, in <module>
    agent.persist('./models')
  File "C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\rasa_core\agent.py", line 609, in persist
    self.policy_ensemble.persist(model_path, dump_flattened_stories)
  File "C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\rasa_core\policies\ensemble.py", line 172, in persist
    self._persist_metadata(path, dump_flattened_stories)
  File "C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\rasa_core\policies\ensemble.py", line 146, in _persist_metadata
    self.training_trackers)
  File "C:\Users\sanchit\PycharmProjects\chatbots\venv\lib\site-packages\rasa_core\policies\ensemble.py", line 51, in _training_events_from_trackers
    for t in training_trackers:
TypeError: 'NoneType' object is not iterable

Process finished with exit code 1

& here is my code

from rasa_core.policies.memoization import MemoizationPolicy
from rasa_core.agent import Agent
from rasa_core.policies.keras_policy import KerasPolicy

agent = Agent('weather_domain.yml',  policies=[MemoizationPolicy(max_history=5),
                        KerasPolicy(  validation_split = 0.0 , epochs=500, batch_size=10 , augmentation_factor = 50 , max_history=2 ,)])

training_data = agent.load_data('./data/stories.md')


agent.persist('./models')

Please help

I think you forgot to call the train method. Can you try:

from rasa_core.policies.memoization import MemoizationPolicy
from rasa_core.agent import Agent
from rasa_core.policies.keras_policy import KerasPolicy

agent = Agent('weather_domain.yml',  policies=[MemoizationPolicy(max_history=5),
                        KerasPolicy(  validation_split = 0.0 , epochs=500, batch_size=10 , augmentation_factor = 50 , max_history=2 ,)])

training_data = agent.load_data('./data/stories.md')

agent.train(training_data)

agent.persist('./models')

Thanks for replying @Tanja it works now, but i have version compatibility issue with rasa_nlu & rasa_core so i am working on that now :confused: BTW Thanks If I need Help I’ll Surely let u know. Thanks Again @Tanja

Glad it works.

What version of Rasa are you using? If you are using a version > 1.0, you should use rasa.core and rasa.nlu instead of rasa_core and rasa_nlu.

Hey @Tanja will you please look at this issue once Error in train_online.py