ValidationError: 1 validation error for PyTorchPredictorModel

[cooling-0]

scheduler = DEISMultistepScheduler( num_train_timesteps=150, beta_end=0.1, )

estimator = TimeGradEstimator(
    input_size=int(dataset.metadata.feat_static_cat[0].cardinality),
    hidden_size=64,
    num_layers=2,
    dropout_rate=0.1,
    lags_seq=[1],
    scheduler=scheduler,
    num_inference_steps=10,
    prediction_length=dataset.metadata.prediction_length,
    context_length=dataset.metadata.prediction_length,
    freq=dataset.metadata.freq,
    scaling="mean",
    trainer_kwargs=dict(max_epochs=3, accelerator="gpu", devices="-1"),
)
predictor = estimator.train(dataset_train)

Hi, I am running the code and got the following error. Can you tell me how to solve this?
I installed pytorch-ts by git clone and branched to ver-0.7.0.
the code is Time-Grad-Electricity.ipynb

GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
HPU available: False, using: 0 HPUs
[c:\Users\chanyoung\anaconda3\envs\coolingts\lib\site-packages\lightning\pytorch\trainer\configuration_validator.py:74](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/lightning/pytorch/trainer/configuration_validator.py:74): You defined a `validation_step` but have no `val_dataloader`. Skipping val loop.
You are using a CUDA device ('NVIDIA GeForce RTX 3090') that has Tensor Cores. To properly utilize them, you should set `torch.set_float32_matmul_precision('medium' | 'high')` which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]

  | Name  | Type          | Params | In sizes | Out sizes        
-----------------------------------------------------------------------
0 | model | TimeGradModel | 432 K  | ?        | [1, 100, 24, 370]
-----------------------------------------------------------------------
432 K     Trainable params
0         Non-trainable params
432 K     Total params
1.729     Total estimated model params size (MB)
Epoch 0: |          | 50/? [00:26<00:00,  1.86it/s, v_num=11, train_loss=0.414]
Epoch 0, global step 50: 'train_loss' reached 0.41410 (best 0.41410), saving model to 'c:\\Users\\chanyoung\\Desktop\\새 폴더 (2)\\lightning_logs\\version_11\\checkpoints\\epoch=0-step=50.ckpt' as top 1
Epoch 1: |          | 50/? [00:25<00:00,  1.93it/s, v_num=11, train_loss=0.265]
Epoch 1, global step 100: 'train_loss' reached 0.26505 (best 0.26505), saving model to 'c:\\Users\\chanyoung\\Desktop\\새 폴더 (2)\\lightning_logs\\version_11\\checkpoints\\epoch=1-step=100.ckpt' as top 1
Epoch 2: |          | 50/? [00:27<00:00,  1.79it/s, v_num=11, train_loss=0.189]
Epoch 2, global step 150: 'train_loss' reached 0.18864 (best 0.18864), saving model to 'c:\\Users\\chanyoung\\Desktop\\새 폴더 (2)\\lightning_logs\\version_11\\checkpoints\\epoch=2-step=150.ckpt' as top 1
`Trainer.fit` stopped: `max_epochs=3` reached.
Epoch 2: |          | 50/? [00:27<00:00,  1.79it/s, v_num=11, train_loss=0.189]

---

---

ValidationError                           Traceback (most recent call last)
Cell In[13], [line 1](vscode-notebook-cell:?execution_count=13&line=1)
----> [1](vscode-notebook-cell:?execution_count=13&line=1) predictor = estimator.train(dataset_train)

File [c:\Users\chanyoung\anaconda3\envs\coolingts\lib\site-packages\gluonts\torch\model\estimator.py:246](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:246), in PyTorchLightningEstimator.train(self, training_data, validation_data, shuffle_buffer_length, cache_data, ckpt_path, **kwargs)
    [237](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:237) def train(
    [238](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:238)     self,
    [239](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:239)     training_data: Dataset,
   (...)
    [244](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:244)     **kwargs,
    [245](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:245) ) -> PyTorchPredictor:
--> [246](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:246)     return self.train_model(
    [247](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:247)         training_data,
    [248](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:248)         validation_data,
    [249](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:249)         shuffle_buffer_length=shuffle_buffer_length,
    [250](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:250)         cache_data=cache_data,
    [251](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:251)         ckpt_path=ckpt_path,
    [252](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:252)     ).predictor

File [c:\Users\chanyoung\anaconda3\envs\coolingts\lib\site-packages\gluonts\torch\model\estimator.py:230](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:230), in PyTorchLightningEstimator.train_model(self, training_data, validation_data, from_predictor, shuffle_buffer_length, cache_data, ckpt_path, **kwargs)
    [223](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:223) else:
    [224](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:224)     best_model = training_network
    [226](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:226) return TrainOutput(
    [227](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/gluonts/torch/model/estimator.py:227)     transformation=transformation,
...
File [c:\Users\chanyoung\anaconda3\envs\coolingts\lib\site-packages\pydantic\main.py:341](file:https:///C:/Users/chanyoung/anaconda3/envs/coolingts/lib/site-packages/pydantic/main.py:341), in pydantic.main.BaseModel.__init__()

ValidationError: 1 validation error for PyTorchPredictorModel
device
  str type expected (type=type_error.str)