simpletransformers: simpletransformers model trained on Colab doesn't work locally

Hello! First of all, thank you for this library! It is awesome! I encountered the following problem while trying to work with simpletransformers: I’ve followed the instructions in this link and trained a BERT model on Google Colab. I then downloaded it and tried to use it locally on my computer. But something went wrong.

Here is my code for training the model (on Google Colab):

from simpletransformers.classification import ClassificationModel
train_args ={"reprocess_input_data": True,
             "fp16":False,
             "num_train_epochs": 1,
             "save_steps": 100_000,
             "logging_steps": 100}

model = ClassificationModel(
    "bert", "bert-base-german-cased",
    num_labels=21,
    args=train_args
)
model.train_model(train_df)

It worked completely fine on Colab but I need it locally, so I downloaded the archive that was created using the following code:

import os
import tarfile

def pack_model(model_path='',file_name=''):
  files = [files for root, dirs, files in os.walk(model_path)][0]
  with tarfile.open(file_name+ '.tar.gz', 'w:gz') as f:
    for file in files:
      f.add(f'{model_path}/{file}')

pack_model('outputs', 'model')

I then unpacked it and placed in the directory with the file with the following code for testing the model:

from simpletransformers.classification import ClassificationModel

train_args ={"reprocess_input_data": True,
             "fp16":False,
             "num_train_epochs": 1,
             "save_steps": 100_000,
             "logging_steps": 100}

model = ClassificationModel(
    "bert", "outputs/",
    num_labels=21,
    args=train_args,
    use_cuda=False
)

test = "Boris Johnson hält eine Pressekonferenz zum Coronavirus-Aktionsplan der Regierung"

predictions, raw_outputs = model.predict([test])
print([predictions[0])

So the only difference in how I create models is use_cuda=False (because I don’t have a GPU locally).

When I executed the code the following output appeared:

I0526 17:16:12.761774 14508 file_utils.py:39] PyTorch version 1.5.0+cpu available.
I0526 17:16:32.703790 14508 configuration_utils.py:283] loading configuration file outputs/config.json
I0526 17:16:32.706786 14508 configuration_utils.py:321] Model config BertConfig {
  "architectures": [
    "BertForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4",
    "5": "LABEL_5",
    "6": "LABEL_6",
    "7": "LABEL_7",
    "8": "LABEL_8",
    "9": "LABEL_9",
    "10": "LABEL_10",
    "11": "LABEL_11",
    "12": "LABEL_12",
    "13": "LABEL_13",
    "14": "LABEL_14",
    "15": "LABEL_15",
    "16": "LABEL_16",
    "17": "LABEL_17",
    "18": "LABEL_18",
    "19": "LABEL_19",
    "20": "LABEL_20"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_10": 10,
    "LABEL_11": 11,
    "LABEL_12": 12,
    "LABEL_13": 13,
    "LABEL_14": 14,
    "LABEL_15": 15,
    "LABEL_16": 16,
    "LABEL_17": 17,
    "LABEL_18": 18,
    "LABEL_19": 19,
    "LABEL_2": 2,
    "LABEL_20": 20,
    "LABEL_3": 3,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6,
    "LABEL_7": 7,
    "LABEL_8": 8,
    "LABEL_9": 9
  },
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "bert",
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 0,
  "type_vocab_size": 2,
  "vocab_size": 30000
}

I0526 17:16:32.723798 14508 modeling_utils.py:648] loading weights file outputs/pytorch_model.bin
I0526 17:16:41.755029 14508 tokenization_utils.py:929] Model name 'outputs/' not found in model shortcut name list (bert-base-uncased, bert-large-uncased, bert-base-cased, bert-large-cased, bert-base-multilingual-uncased, bert-base-multilingual-cased, bert-base-chinese, bert-base-german-cased, bert-large-uncased-whole-word-masking, bert-large-cased-whole-word-masking, bert-large-uncased-whole-word-masking-finetuned-squad, bert-large-cased-whole-word-masking-finetuned-squad, bert-base-cased-finetuned-mrpc, bert-base-german-dbmdz-cased, bert-base-german-dbmdz-uncased, bert-base-finnish-cased-v1, bert-base-finnish-uncased-v1, bert-base-dutch-cased). Assuming 'outputs/' is a path, a model identifier, or url to a directory containing tokenizer files.
I0526 17:16:41.770021 14508 tokenization_utils.py:958] Didn't find file outputs/added_tokens.json. We won't load it.
I0526 17:16:41.779017 14508 tokenization_utils.py:1013] loading file outputs/vocab.txt
I0526 17:16:41.788011 14508 tokenization_utils.py:1013] loading file None
I0526 17:16:41.794008 14508 tokenization_utils.py:1013] loading file outputs/special_tokens_map.json
I0526 17:16:41.806000 14508 tokenization_utils.py:1013] loading file outputs/tokenizer_config.json
I0526 17:16:41.986897 14508 classification_model.py:801]  Converting to features started. Cache is not used.

  0%|          | 0/1 [00:00<?, ?it/s]

And it freezes on this moment. Nothing happens despite this progress bar. What should I do to make it work locally? Maybe there is another way?

My system:

• Windows 10 Home
• Python: 3.7.2
• simpletransformers: 0.29.1

Thanks in advance for any help!