.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "auto_examples/training_and_testing/plot_one_model_regression_traintest.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_auto_examples_training_and_testing_plot_one_model_regression_traintest.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_auto_examples_training_and_testing_plot_one_model_regression_traintest.py:


Train/Test split: Regression
======================================================

🚀 In this tutorial, we'll explore regression using a train/test split.
Specifically, we're using the :class:`~.TabularCrossmodalMultiheadAttention` model.

Data:

The data we are using is 500 rows of the MNIST dataset, split into top and bottom halves as our two tabular modalities.
The bottom half's values have been inverted to make the task more difficult.
The prediction labels (the number shown in the image) has been changed into a continuous variable (1.0, 2.0, 3.0, etc.) and had some noise added to it.
So the labels look more like 1.05, 2.02, 3.01, etc.

Key Features:

- 📥 Importing a model based on its path.
- 🧪 Training and testing a model with train/test split.
- 📈 Plotting the loss curves of each fold.
- 📊 Visualising the results of a single train/test model using the :class:`~.RealsVsPreds` class.

.. GENERATED FROM PYTHON SOURCE LINES 22-33

.. code-block:: Python


    import matplotlib.pyplot as plt
    from tqdm.auto import tqdm
    import os

    from fusilli.data import prepare_fusion_data
    from fusilli.eval import RealsVsPreds
    from fusilli.train import train_and_save_models

    # sphinx_gallery_thumbnail_number = -1








.. GENERATED FROM PYTHON SOURCE LINES 34-38

1. Import the fusion model 🔍
--------------------------------
We're importing only one model for this example, the :class:`~.TabularCrossmodalMultiheadAttention` model.
Instead of using the :func:`~fusilli.utils.model_chooser.import_chosen_fusion_models` function, we're importing the model directly like with any other library method.

.. GENERATED FROM PYTHON SOURCE LINES 38-44

.. code-block:: Python



    from fusilli.fusionmodels.tabularfusion.crossmodal_att import (
        TabularCrossmodalMultiheadAttention,
    )








.. GENERATED FROM PYTHON SOURCE LINES 45-63

2. Set the training parameters 🎯
-----------------------------------
Now we're configuring our training parameters.

For training and testing, the necessary parameters are:
- Paths to the input data files.
- Paths to the output directories.
- ``prediction_task``: the type of prediction to be performed. This is either ``regression``, ``binary``, or ``classification``.

Some optional parameters are:

- ``kfold``: a boolean of whether to use k-fold cross-validation (True) or not (False). By default, this is set to False.
- ``num_folds``: the number of folds to use. It can't be ``k=1``.
- ``wandb_logging``: a boolean of whether to log the results using Weights and Biases (True) or not (False). Default is False.
- ``test_size``: the proportion of the dataset to include in the test split. Default is 0.2.
- ``batch_size``: the batch size to use for training. Default is 8.
- ``multiclass_dimensions``: the number of classes to use for multiclass classification. Default is None unless ``prediction_task`` is ``multiclass``.
- ``max_epochs``: the maximum number of epochs to train for. Default is 1000.

.. GENERATED FROM PYTHON SOURCE LINES 63-89

.. code-block:: Python


    # Regression task
    prediction_task = "regression"

    # Set the batch size
    batch_size = 32

    # Setting output directories
    output_paths = {
        "losses": "loss_logs/one_model_regression_traintest",
        "checkpoints": "checkpoints/one_model_regression_traintest",
        "figures": "figures/one_model_regression_traintest",
    }

    # Create the output directories if they don't exist
    for path in output_paths.values():
        os.makedirs(path, exist_ok=True)

    # Clearing the loss logs directory (only for the example notebooks)
    for dir in os.listdir(output_paths["losses"]):
        # remove files
        for file in os.listdir(os.path.join(output_paths["losses"], dir)):
            os.remove(os.path.join(output_paths["losses"], dir, file))
        # remove dir
        os.rmdir(os.path.join(output_paths["losses"], dir))








.. GENERATED FROM PYTHON SOURCE LINES 90-93

3. Specifying input file paths 🔮
--------------------------------
We're using the MNIST dataset for this example, and the CSV files are stored in the ``_static/mnist_data`` directory with the documentation files.

.. GENERATED FROM PYTHON SOURCE LINES 93-101

.. code-block:: Python



    data_paths = {
        "tabular1": "../../_static/mnist_data/mnist1_regression.csv",
        "tabular2": "../../_static/mnist_data/mnist2_regression.csv",
        "image": "",
    }








.. GENERATED FROM PYTHON SOURCE LINES 102-116

4. Training the fusion model 🏁
--------------------------------------
Now we're ready to train our model. We're using the :func:`~fusilli.train.train_and_save_models` function to train our model.

First we need to create a data module using the :func:`~fusilli.data.prepare_fusion_data` function.
This function takes the following parameters:

- ``prediction_task``: the type of prediction to be performed.
- ``fusion_model``: the fusion model to be trained.
- ``data_paths``: the paths to the input data files.
- ``output_paths``: the paths to the output directories.

Then we pass the data module and the fusion model to the :func:`~fusilli.train.train_and_save_models` function.
We're not using checkpointing for this example, so we set ``enable_checkpointing=False``. We're also setting ``show_loss_plot=True`` to plot the loss curve.

.. GENERATED FROM PYTHON SOURCE LINES 116-139

.. code-block:: Python



    fusion_model = TabularCrossmodalMultiheadAttention

    print("method_name:", fusion_model.method_name)
    print("modality_type:", fusion_model.modality_type)
    print("fusion_type:", fusion_model.fusion_type)

    dm = prepare_fusion_data(prediction_task=prediction_task,
                             fusion_model=fusion_model,
                             data_paths=data_paths,
                             output_paths=output_paths,
                             batch_size=batch_size)

    # train and test
    single_model_list = train_and_save_models(
        data_module=dm,
        fusion_model=fusion_model,
        enable_checkpointing=False,  # False for the example notebooks
        show_loss_plot=True,
        metrics_list=["r2", "mae", "mse"]
    )




.. image-sg:: /auto_examples/training_and_testing/images/sphx_glr_plot_one_model_regression_traintest_001.png
   :alt: Loss Curves for TabularCrossmodalMultiheadAttention
   :srcset: /auto_examples/training_and_testing/images/sphx_glr_plot_one_model_regression_traintest_001.png
   :class: sphx-glr-single-img


.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    method_name: Tabular Crossmodal multi-head attention
    modality_type: tabular_tabular
    fusion_type: attention

    Training: |          | 0/? [00:00<?, ?it/s]
    Training:   0%|          | 0/13 [00:00<?, ?it/s]
    Epoch 0:   0%|          | 0/13 [00:00<?, ?it/s] 
    Epoch 0:   8%|▊         | 1/13 [00:00<00:00, 65.96it/s]
    Epoch 0:   8%|▊         | 1/13 [00:00<00:00, 64.83it/s, v_num=tion]
    Epoch 0:  15%|█▌        | 2/13 [00:00<00:00, 70.37it/s, v_num=tion]
    Epoch 0:  15%|█▌        | 2/13 [00:00<00:00, 69.87it/s, v_num=tion]
    Epoch 0:  23%|██▎       | 3/13 [00:00<00:00, 72.71it/s, v_num=tion]
    Epoch 0:  23%|██▎       | 3/13 [00:00<00:00, 72.38it/s, v_num=tion]
    Epoch 0:  31%|███       | 4/13 [00:00<00:00, 73.72it/s, v_num=tion]
    Epoch 0:  31%|███       | 4/13 [00:00<00:00, 73.46it/s, v_num=tion]
    Epoch 0:  38%|███▊      | 5/13 [00:00<00:00, 74.98it/s, v_num=tion]
    Epoch 0:  38%|███▊      | 5/13 [00:00<00:00, 74.77it/s, v_num=tion]
    Epoch 0:  46%|████▌     | 6/13 [00:00<00:00, 75.71it/s, v_num=tion]
    Epoch 0:  46%|████▌     | 6/13 [00:00<00:00, 75.52it/s, v_num=tion]
    Epoch 0:  54%|█████▍    | 7/13 [00:00<00:00, 76.32it/s, v_num=tion]
    Epoch 0:  54%|█████▍    | 7/13 [00:00<00:00, 76.14it/s, v_num=tion]
    Epoch 0:  62%|██████▏   | 8/13 [00:00<00:00, 76.18it/s, v_num=tion]
    Epoch 0:  62%|██████▏   | 8/13 [00:00<00:00, 76.03it/s, v_num=tion]
    Epoch 0:  69%|██████▉   | 9/13 [00:00<00:00, 76.52it/s, v_num=tion]
    Epoch 0:  69%|██████▉   | 9/13 [00:00<00:00, 76.39it/s, v_num=tion]
    Epoch 0:  77%|███████▋  | 10/13 [00:00<00:00, 76.95it/s, v_num=tion]
    Epoch 0:  77%|███████▋  | 10/13 [00:00<00:00, 76.83it/s, v_num=tion]
    Epoch 0:  85%|████████▍ | 11/13 [00:00<00:00, 77.11it/s, v_num=tion]
    Epoch 0:  85%|████████▍ | 11/13 [00:00<00:00, 77.01it/s, v_num=tion]
    Epoch 0:  92%|█████████▏| 12/13 [00:00<00:00, 77.00it/s, v_num=tion]
    Epoch 0:  92%|█████████▏| 12/13 [00:00<00:00, 76.91it/s, v_num=tion]
    Epoch 0: 100%|██████████| 13/13 [00:00<00:00, 77.51it/s, v_num=tion]
    Epoch 0: 100%|██████████| 13/13 [00:00<00:00, 77.42it/s, v_num=tion]
    Epoch 0: 100%|██████████| 13/13 [00:00<00:00, 70.50it/s, v_num=tion, val_loss=5.610]
    Epoch 0: 100%|██████████| 13/13 [00:00<00:00, 70.27it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 0:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=5.610, train_loss=9.650]         
    Epoch 1:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:   8%|▊         | 1/13 [00:00<00:00, 79.68it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:   8%|▊         | 1/13 [00:00<00:00, 78.41it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  15%|█▌        | 2/13 [00:00<00:00, 80.67it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  15%|█▌        | 2/13 [00:00<00:00, 80.01it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  23%|██▎       | 3/13 [00:00<00:00, 81.07it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  23%|██▎       | 3/13 [00:00<00:00, 80.55it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  31%|███       | 4/13 [00:00<00:00, 81.32it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  31%|███       | 4/13 [00:00<00:00, 80.95it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  38%|███▊      | 5/13 [00:00<00:00, 80.60it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  38%|███▊      | 5/13 [00:00<00:00, 80.31it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  46%|████▌     | 6/13 [00:00<00:00, 80.70it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  46%|████▌     | 6/13 [00:00<00:00, 80.48it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  54%|█████▍    | 7/13 [00:00<00:00, 80.98it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  54%|█████▍    | 7/13 [00:00<00:00, 80.79it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  62%|██████▏   | 8/13 [00:00<00:00, 80.97it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  62%|██████▏   | 8/13 [00:00<00:00, 80.80it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  69%|██████▉   | 9/13 [00:00<00:00, 80.68it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  69%|██████▉   | 9/13 [00:00<00:00, 80.53it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  77%|███████▋  | 10/13 [00:00<00:00, 80.75it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  77%|███████▋  | 10/13 [00:00<00:00, 80.62it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  85%|████████▍ | 11/13 [00:00<00:00, 80.87it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  85%|████████▍ | 11/13 [00:00<00:00, 80.74it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  92%|█████████▏| 12/13 [00:00<00:00, 80.89it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1:  92%|█████████▏| 12/13 [00:00<00:00, 80.78it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1: 100%|██████████| 13/13 [00:00<00:00, 81.00it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1: 100%|██████████| 13/13 [00:00<00:00, 80.90it/s, v_num=tion, val_loss=5.610, train_loss=9.650]
    Epoch 1: 100%|██████████| 13/13 [00:00<00:00, 73.67it/s, v_num=tion, val_loss=3.720, train_loss=9.650]
    Epoch 1: 100%|██████████| 13/13 [00:00<00:00, 73.41it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 1:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=3.720, train_loss=5.470]         
    Epoch 2:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:   8%|▊         | 1/13 [00:00<00:00, 79.64it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:   8%|▊         | 1/13 [00:00<00:00, 78.37it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  15%|█▌        | 2/13 [00:00<00:00, 81.32it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  15%|█▌        | 2/13 [00:00<00:00, 80.64it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  23%|██▎       | 3/13 [00:00<00:00, 79.21it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  23%|██▎       | 3/13 [00:00<00:00, 78.76it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  31%|███       | 4/13 [00:00<00:00, 79.71it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  31%|███       | 4/13 [00:00<00:00, 79.38it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  38%|███▊      | 5/13 [00:00<00:00, 80.05it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  38%|███▊      | 5/13 [00:00<00:00, 79.76it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  46%|████▌     | 6/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  46%|████▌     | 6/13 [00:00<00:00, 79.97it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  54%|█████▍    | 7/13 [00:00<00:00, 79.93it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  54%|█████▍    | 7/13 [00:00<00:00, 79.74it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  62%|██████▏   | 8/13 [00:00<00:00, 80.09it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  62%|██████▏   | 8/13 [00:00<00:00, 79.93it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  69%|██████▉   | 9/13 [00:00<00:00, 80.22it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  69%|██████▉   | 9/13 [00:00<00:00, 80.07it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  77%|███████▋  | 10/13 [00:00<00:00, 80.36it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  77%|███████▋  | 10/13 [00:00<00:00, 80.21it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  85%|████████▍ | 11/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  85%|████████▍ | 11/13 [00:00<00:00, 80.07it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  92%|█████████▏| 12/13 [00:00<00:00, 80.31it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2:  92%|█████████▏| 12/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2: 100%|██████████| 13/13 [00:00<00:00, 80.62it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2: 100%|██████████| 13/13 [00:00<00:00, 80.52it/s, v_num=tion, val_loss=3.720, train_loss=5.470]
    Epoch 2: 100%|██████████| 13/13 [00:00<00:00, 73.39it/s, v_num=tion, val_loss=3.130, train_loss=5.470]
    Epoch 2: 100%|██████████| 13/13 [00:00<00:00, 73.13it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 2:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=3.130, train_loss=3.460]         
    Epoch 3:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:   8%|▊         | 1/13 [00:00<00:00, 79.25it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:   8%|▊         | 1/13 [00:00<00:00, 78.01it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  15%|█▌        | 2/13 [00:00<00:00, 80.38it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  15%|█▌        | 2/13 [00:00<00:00, 79.61it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  23%|██▎       | 3/13 [00:00<00:00, 80.75it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  23%|██▎       | 3/13 [00:00<00:00, 80.31it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  31%|███       | 4/13 [00:00<00:00, 80.92it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  31%|███       | 4/13 [00:00<00:00, 80.57it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  38%|███▊      | 5/13 [00:00<00:00, 80.44it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  38%|███▊      | 5/13 [00:00<00:00, 80.17it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  46%|████▌     | 6/13 [00:00<00:00, 80.55it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  46%|████▌     | 6/13 [00:00<00:00, 80.33it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  54%|█████▍    | 7/13 [00:00<00:00, 80.70it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  54%|█████▍    | 7/13 [00:00<00:00, 80.51it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  62%|██████▏   | 8/13 [00:00<00:00, 80.81it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  62%|██████▏   | 8/13 [00:00<00:00, 80.63it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  69%|██████▉   | 9/13 [00:00<00:00, 80.57it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  69%|██████▉   | 9/13 [00:00<00:00, 80.42it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  77%|███████▋  | 10/13 [00:00<00:00, 80.73it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  77%|███████▋  | 10/13 [00:00<00:00, 80.58it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  85%|████████▍ | 11/13 [00:00<00:00, 80.51it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  85%|████████▍ | 11/13 [00:00<00:00, 80.39it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  92%|█████████▏| 12/13 [00:00<00:00, 80.40it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3:  92%|█████████▏| 12/13 [00:00<00:00, 80.29it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3: 100%|██████████| 13/13 [00:00<00:00, 80.45it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3: 100%|██████████| 13/13 [00:00<00:00, 80.35it/s, v_num=tion, val_loss=3.130, train_loss=3.460]
    Epoch 3: 100%|██████████| 13/13 [00:00<00:00, 73.21it/s, v_num=tion, val_loss=2.530, train_loss=3.460]
    Epoch 3: 100%|██████████| 13/13 [00:00<00:00, 72.95it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 3:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.530, train_loss=2.770]         
    Epoch 4:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:   8%|▊         | 1/13 [00:00<00:00, 79.63it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:   8%|▊         | 1/13 [00:00<00:00, 78.36it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  15%|█▌        | 2/13 [00:00<00:00, 80.36it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  15%|█▌        | 2/13 [00:00<00:00, 79.70it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  23%|██▎       | 3/13 [00:00<00:00, 79.75it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  23%|██▎       | 3/13 [00:00<00:00, 79.32it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  31%|███       | 4/13 [00:00<00:00, 80.55it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  31%|███       | 4/13 [00:00<00:00, 80.21it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  38%|███▊      | 5/13 [00:00<00:00, 80.02it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  38%|███▊      | 5/13 [00:00<00:00, 79.76it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  46%|████▌     | 6/13 [00:00<00:00, 79.90it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  46%|████▌     | 6/13 [00:00<00:00, 79.66it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  54%|█████▍    | 7/13 [00:00<00:00, 79.63it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  54%|█████▍    | 7/13 [00:00<00:00, 79.45it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  62%|██████▏   | 8/13 [00:00<00:00, 79.91it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  62%|██████▏   | 8/13 [00:00<00:00, 79.73it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  69%|██████▉   | 9/13 [00:00<00:00, 80.03it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  69%|██████▉   | 9/13 [00:00<00:00, 79.88it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  77%|███████▋  | 10/13 [00:00<00:00, 80.18it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  77%|███████▋  | 10/13 [00:00<00:00, 80.05it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  85%|████████▍ | 11/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  85%|████████▍ | 11/13 [00:00<00:00, 80.06it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  92%|█████████▏| 12/13 [00:00<00:00, 80.21it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4:  92%|█████████▏| 12/13 [00:00<00:00, 80.07it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4: 100%|██████████| 13/13 [00:00<00:00, 80.21it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4: 100%|██████████| 13/13 [00:00<00:00, 80.09it/s, v_num=tion, val_loss=2.530, train_loss=2.770]
    Epoch 4: 100%|██████████| 13/13 [00:00<00:00, 72.91it/s, v_num=tion, val_loss=2.330, train_loss=2.770]
    Epoch 4: 100%|██████████| 13/13 [00:00<00:00, 72.65it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 4:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.330, train_loss=2.160]         
    Epoch 5:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:   8%|▊         | 1/13 [00:00<00:00, 77.36it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:   8%|▊         | 1/13 [00:00<00:00, 76.17it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  15%|█▌        | 2/13 [00:00<00:00, 79.16it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  15%|█▌        | 2/13 [00:00<00:00, 78.52it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  23%|██▎       | 3/13 [00:00<00:00, 79.91it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  23%|██▎       | 3/13 [00:00<00:00, 79.44it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  31%|███       | 4/13 [00:00<00:00, 80.29it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  31%|███       | 4/13 [00:00<00:00, 79.96it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  38%|███▊      | 5/13 [00:00<00:00, 79.96it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  38%|███▊      | 5/13 [00:00<00:00, 79.67it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  46%|████▌     | 6/13 [00:00<00:00, 80.21it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  46%|████▌     | 6/13 [00:00<00:00, 79.99it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  54%|█████▍    | 7/13 [00:00<00:00, 80.48it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  54%|█████▍    | 7/13 [00:00<00:00, 80.30it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  62%|██████▏   | 8/13 [00:00<00:00, 80.61it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  62%|██████▏   | 8/13 [00:00<00:00, 80.44it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  69%|██████▉   | 9/13 [00:00<00:00, 79.66it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  69%|██████▉   | 9/13 [00:00<00:00, 79.52it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  77%|███████▋  | 10/13 [00:00<00:00, 79.80it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  77%|███████▋  | 10/13 [00:00<00:00, 79.67it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  85%|████████▍ | 11/13 [00:00<00:00, 79.94it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  85%|████████▍ | 11/13 [00:00<00:00, 79.82it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  92%|█████████▏| 12/13 [00:00<00:00, 80.03it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5:  92%|█████████▏| 12/13 [00:00<00:00, 79.92it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5: 100%|██████████| 13/13 [00:00<00:00, 80.13it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5: 100%|██████████| 13/13 [00:00<00:00, 80.03it/s, v_num=tion, val_loss=2.330, train_loss=2.160]
    Epoch 5: 100%|██████████| 13/13 [00:00<00:00, 72.84it/s, v_num=tion, val_loss=2.480, train_loss=2.160]
    Epoch 5: 100%|██████████| 13/13 [00:00<00:00, 72.58it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 5:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.480, train_loss=1.990]         
    Epoch 6:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:   8%|▊         | 1/13 [00:00<00:00, 81.52it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:   8%|▊         | 1/13 [00:00<00:00, 80.20it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  15%|█▌        | 2/13 [00:00<00:00, 81.78it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  15%|█▌        | 2/13 [00:00<00:00, 81.10it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  23%|██▎       | 3/13 [00:00<00:00, 80.86it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  23%|██▎       | 3/13 [00:00<00:00, 80.42it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  31%|███       | 4/13 [00:00<00:00, 81.09it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  31%|███       | 4/13 [00:00<00:00, 80.75it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  38%|███▊      | 5/13 [00:00<00:00, 81.12it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  38%|███▊      | 5/13 [00:00<00:00, 80.83it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  46%|████▌     | 6/13 [00:00<00:00, 81.25it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  46%|████▌     | 6/13 [00:00<00:00, 81.02it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  54%|█████▍    | 7/13 [00:00<00:00, 80.98it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  54%|█████▍    | 7/13 [00:00<00:00, 80.79it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  62%|██████▏   | 8/13 [00:00<00:00, 81.06it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  62%|██████▏   | 8/13 [00:00<00:00, 80.87it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  69%|██████▉   | 9/13 [00:00<00:00, 81.19it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  69%|██████▉   | 9/13 [00:00<00:00, 81.04it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  77%|███████▋  | 10/13 [00:00<00:00, 81.28it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  77%|███████▋  | 10/13 [00:00<00:00, 81.15it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  85%|████████▍ | 11/13 [00:00<00:00, 81.07it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  85%|████████▍ | 11/13 [00:00<00:00, 80.94it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  92%|█████████▏| 12/13 [00:00<00:00, 81.10it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6:  92%|█████████▏| 12/13 [00:00<00:00, 80.99it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6: 100%|██████████| 13/13 [00:00<00:00, 81.36it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6: 100%|██████████| 13/13 [00:00<00:00, 81.25it/s, v_num=tion, val_loss=2.480, train_loss=1.990]
    Epoch 6: 100%|██████████| 13/13 [00:00<00:00, 73.98it/s, v_num=tion, val_loss=1.970, train_loss=1.990]
    Epoch 6: 100%|██████████| 13/13 [00:00<00:00, 73.72it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 6:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.970, train_loss=1.150]         
    Epoch 7:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:   8%|▊         | 1/13 [00:00<00:00, 79.71it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:   8%|▊         | 1/13 [00:00<00:00, 78.44it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  15%|█▌        | 2/13 [00:00<00:00, 80.97it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  15%|█▌        | 2/13 [00:00<00:00, 80.23it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  23%|██▎       | 3/13 [00:00<00:00, 81.18it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  23%|██▎       | 3/13 [00:00<00:00, 80.74it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  31%|███       | 4/13 [00:00<00:00, 80.94it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  31%|███       | 4/13 [00:00<00:00, 80.61it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  38%|███▊      | 5/13 [00:00<00:00, 80.24it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  38%|███▊      | 5/13 [00:00<00:00, 79.97it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  46%|████▌     | 6/13 [00:00<00:00, 80.42it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  46%|████▌     | 6/13 [00:00<00:00, 80.20it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  54%|█████▍    | 7/13 [00:00<00:00, 80.52it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  54%|█████▍    | 7/13 [00:00<00:00, 80.33it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  62%|██████▏   | 8/13 [00:00<00:00, 80.70it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  62%|██████▏   | 8/13 [00:00<00:00, 80.53it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  69%|██████▉   | 9/13 [00:00<00:00, 80.49it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  69%|██████▉   | 9/13 [00:00<00:00, 80.32it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  77%|███████▋  | 10/13 [00:00<00:00, 80.51it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  77%|███████▋  | 10/13 [00:00<00:00, 80.37it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  85%|████████▍ | 11/13 [00:00<00:00, 80.60it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  85%|████████▍ | 11/13 [00:00<00:00, 80.47it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  92%|█████████▏| 12/13 [00:00<00:00, 80.64it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7:  92%|█████████▏| 12/13 [00:00<00:00, 80.52it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7: 100%|██████████| 13/13 [00:00<00:00, 80.66it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7: 100%|██████████| 13/13 [00:00<00:00, 80.56it/s, v_num=tion, val_loss=1.970, train_loss=1.150]
    Epoch 7: 100%|██████████| 13/13 [00:00<00:00, 73.36it/s, v_num=tion, val_loss=2.070, train_loss=1.150]
    Epoch 7: 100%|██████████| 13/13 [00:00<00:00, 73.11it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 7:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.070, train_loss=0.944]         
    Epoch 8:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:   8%|▊         | 1/13 [00:00<00:00, 79.24it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:   8%|▊         | 1/13 [00:00<00:00, 77.98it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  15%|█▌        | 2/13 [00:00<00:00, 80.46it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  15%|█▌        | 2/13 [00:00<00:00, 79.80it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  23%|██▎       | 3/13 [00:00<00:00, 79.90it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  23%|██▎       | 3/13 [00:00<00:00, 79.46it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  31%|███       | 4/13 [00:00<00:00, 80.22it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  31%|███       | 4/13 [00:00<00:00, 79.89it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  38%|███▊      | 5/13 [00:00<00:00, 80.63it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  38%|███▊      | 5/13 [00:00<00:00, 80.36it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  46%|████▌     | 6/13 [00:00<00:00, 81.04it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  46%|████▌     | 6/13 [00:00<00:00, 80.82it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  54%|█████▍    | 7/13 [00:00<00:00, 80.68it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  54%|█████▍    | 7/13 [00:00<00:00, 80.49it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  62%|██████▏   | 8/13 [00:00<00:00, 80.80it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  62%|██████▏   | 8/13 [00:00<00:00, 80.62it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  69%|██████▉   | 9/13 [00:00<00:00, 80.49it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  69%|██████▉   | 9/13 [00:00<00:00, 80.34it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  77%|███████▋  | 10/13 [00:00<00:00, 80.61it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  77%|███████▋  | 10/13 [00:00<00:00, 80.48it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  85%|████████▍ | 11/13 [00:00<00:00, 80.51it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  85%|████████▍ | 11/13 [00:00<00:00, 80.39it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  92%|█████████▏| 12/13 [00:00<00:00, 80.68it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8:  92%|█████████▏| 12/13 [00:00<00:00, 80.57it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8: 100%|██████████| 13/13 [00:00<00:00, 80.74it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8: 100%|██████████| 13/13 [00:00<00:00, 80.64it/s, v_num=tion, val_loss=2.070, train_loss=0.944]
    Epoch 8: 100%|██████████| 13/13 [00:00<00:00, 73.02it/s, v_num=tion, val_loss=1.930, train_loss=0.944]
    Epoch 8: 100%|██████████| 13/13 [00:00<00:00, 72.76it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 8:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.930, train_loss=0.723]         
    Epoch 9:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:   8%|▊         | 1/13 [00:00<00:00, 72.33it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:   8%|▊         | 1/13 [00:00<00:00, 71.16it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  15%|█▌        | 2/13 [00:00<00:00, 76.14it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  15%|█▌        | 2/13 [00:00<00:00, 75.55it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  23%|██▎       | 3/13 [00:00<00:00, 77.43it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  23%|██▎       | 3/13 [00:00<00:00, 77.02it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  31%|███       | 4/13 [00:00<00:00, 78.20it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  31%|███       | 4/13 [00:00<00:00, 77.89it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  38%|███▊      | 5/13 [00:00<00:00, 78.05it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  38%|███▊      | 5/13 [00:00<00:00, 77.68it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  46%|████▌     | 6/13 [00:00<00:00, 78.44it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  46%|████▌     | 6/13 [00:00<00:00, 78.21it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  54%|█████▍    | 7/13 [00:00<00:00, 78.87it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  54%|█████▍    | 7/13 [00:00<00:00, 78.69it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  62%|██████▏   | 8/13 [00:00<00:00, 79.05it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  62%|██████▏   | 8/13 [00:00<00:00, 78.89it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  69%|██████▉   | 9/13 [00:00<00:00, 78.88it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  69%|██████▉   | 9/13 [00:00<00:00, 78.71it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  77%|███████▋  | 10/13 [00:00<00:00, 78.96it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  77%|███████▋  | 10/13 [00:00<00:00, 78.83it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  85%|████████▍ | 11/13 [00:00<00:00, 79.05it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  85%|████████▍ | 11/13 [00:00<00:00, 78.93it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  92%|█████████▏| 12/13 [00:00<00:00, 79.12it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9:  92%|█████████▏| 12/13 [00:00<00:00, 79.01it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9: 100%|██████████| 13/13 [00:00<00:00, 79.20it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9: 100%|██████████| 13/13 [00:00<00:00, 79.10it/s, v_num=tion, val_loss=1.930, train_loss=0.723]
    Epoch 9: 100%|██████████| 13/13 [00:00<00:00, 72.15it/s, v_num=tion, val_loss=2.020, train_loss=0.723]
    Epoch 9: 100%|██████████| 13/13 [00:00<00:00, 71.91it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 9:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.020, train_loss=0.448]         
    Epoch 10:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:   8%|▊         | 1/13 [00:00<00:00, 81.58it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:   8%|▊         | 1/13 [00:00<00:00, 80.24it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  15%|█▌        | 2/13 [00:00<00:00, 81.63it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  15%|█▌        | 2/13 [00:00<00:00, 80.88it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  23%|██▎       | 3/13 [00:00<00:00, 81.07it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  23%|██▎       | 3/13 [00:00<00:00, 80.62it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  31%|███       | 4/13 [00:00<00:00, 81.35it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  31%|███       | 4/13 [00:00<00:00, 81.02it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  38%|███▊      | 5/13 [00:00<00:00, 81.46it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  38%|███▊      | 5/13 [00:00<00:00, 81.19it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  46%|████▌     | 6/13 [00:00<00:00, 81.55it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  46%|████▌     | 6/13 [00:00<00:00, 81.30it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  54%|█████▍    | 7/13 [00:00<00:00, 81.27it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  54%|█████▍    | 7/13 [00:00<00:00, 81.08it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  62%|██████▏   | 8/13 [00:00<00:00, 81.40it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  62%|██████▏   | 8/13 [00:00<00:00, 81.22it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  69%|██████▉   | 9/13 [00:00<00:00, 81.42it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  69%|██████▉   | 9/13 [00:00<00:00, 81.26it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  77%|███████▋  | 10/13 [00:00<00:00, 81.50it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  77%|███████▋  | 10/13 [00:00<00:00, 81.36it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  85%|████████▍ | 11/13 [00:00<00:00, 81.28it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  85%|████████▍ | 11/13 [00:00<00:00, 81.16it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  92%|█████████▏| 12/13 [00:00<00:00, 81.08it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10:  92%|█████████▏| 12/13 [00:00<00:00, 80.97it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10: 100%|██████████| 13/13 [00:00<00:00, 81.23it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10: 100%|██████████| 13/13 [00:00<00:00, 81.12it/s, v_num=tion, val_loss=2.020, train_loss=0.448]
    Epoch 10: 100%|██████████| 13/13 [00:00<00:00, 73.59it/s, v_num=tion, val_loss=1.720, train_loss=0.448]
    Epoch 10: 100%|██████████| 13/13 [00:00<00:00, 73.34it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 10:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.720, train_loss=0.393]         
    Epoch 11:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:   8%|▊         | 1/13 [00:00<00:00, 77.13it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:   8%|▊         | 1/13 [00:00<00:00, 75.76it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  15%|█▌        | 2/13 [00:00<00:00, 78.16it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  15%|█▌        | 2/13 [00:00<00:00, 77.37it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  23%|██▎       | 3/13 [00:00<00:00, 78.65it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  23%|██▎       | 3/13 [00:00<00:00, 78.23it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  31%|███       | 4/13 [00:00<00:00, 79.05it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  31%|███       | 4/13 [00:00<00:00, 78.53it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  38%|███▊      | 5/13 [00:00<00:00, 78.27it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  38%|███▊      | 5/13 [00:00<00:00, 78.01it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  46%|████▌     | 6/13 [00:00<00:00, 78.34it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  46%|████▌     | 6/13 [00:00<00:00, 78.11it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  54%|█████▍    | 7/13 [00:00<00:00, 78.33it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  54%|█████▍    | 7/13 [00:00<00:00, 78.14it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  62%|██████▏   | 8/13 [00:00<00:00, 78.84it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  62%|██████▏   | 8/13 [00:00<00:00, 78.66it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  69%|██████▉   | 9/13 [00:00<00:00, 78.68it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  69%|██████▉   | 9/13 [00:00<00:00, 78.54it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  77%|███████▋  | 10/13 [00:00<00:00, 78.90it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  77%|███████▋  | 10/13 [00:00<00:00, 78.77it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  85%|████████▍ | 11/13 [00:00<00:00, 78.97it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  85%|████████▍ | 11/13 [00:00<00:00, 78.84it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  92%|█████████▏| 12/13 [00:00<00:00, 79.16it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11:  92%|█████████▏| 12/13 [00:00<00:00, 79.03it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11: 100%|██████████| 13/13 [00:00<00:00, 79.08it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11: 100%|██████████| 13/13 [00:00<00:00, 78.97it/s, v_num=tion, val_loss=1.720, train_loss=0.393]
    Epoch 11: 100%|██████████| 13/13 [00:00<00:00, 71.92it/s, v_num=tion, val_loss=2.070, train_loss=0.393]
    Epoch 11: 100%|██████████| 13/13 [00:00<00:00, 71.61it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 11:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.070, train_loss=0.349]         
    Epoch 12:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:   8%|▊         | 1/13 [00:00<00:00, 80.68it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:   8%|▊         | 1/13 [00:00<00:00, 79.38it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  15%|█▌        | 2/13 [00:00<00:00, 81.23it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  15%|█▌        | 2/13 [00:00<00:00, 80.56it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  23%|██▎       | 3/13 [00:00<00:00, 80.11it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  23%|██▎       | 3/13 [00:00<00:00, 79.67it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  31%|███       | 4/13 [00:00<00:00, 80.42it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  31%|███       | 4/13 [00:00<00:00, 80.08it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  38%|███▊      | 5/13 [00:00<00:00, 80.69it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  38%|███▊      | 5/13 [00:00<00:00, 80.42it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  46%|████▌     | 6/13 [00:00<00:00, 80.85it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  46%|████▌     | 6/13 [00:00<00:00, 80.63it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  54%|█████▍    | 7/13 [00:00<00:00, 79.94it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  54%|█████▍    | 7/13 [00:00<00:00, 79.75it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  62%|██████▏   | 8/13 [00:00<00:00, 80.12it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  62%|██████▏   | 8/13 [00:00<00:00, 79.95it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  69%|██████▉   | 9/13 [00:00<00:00, 80.26it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  69%|██████▉   | 9/13 [00:00<00:00, 80.10it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  77%|███████▋  | 10/13 [00:00<00:00, 80.36it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  77%|███████▋  | 10/13 [00:00<00:00, 80.23it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  85%|████████▍ | 11/13 [00:00<00:00, 80.13it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  85%|████████▍ | 11/13 [00:00<00:00, 80.01it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  92%|█████████▏| 12/13 [00:00<00:00, 80.25it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12:  92%|█████████▏| 12/13 [00:00<00:00, 80.14it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12: 100%|██████████| 13/13 [00:00<00:00, 80.57it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12: 100%|██████████| 13/13 [00:00<00:00, 80.47it/s, v_num=tion, val_loss=2.070, train_loss=0.349]
    Epoch 12: 100%|██████████| 13/13 [00:00<00:00, 73.32it/s, v_num=tion, val_loss=2.090, train_loss=0.349]
    Epoch 12: 100%|██████████| 13/13 [00:00<00:00, 73.07it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 12:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.090, train_loss=0.330]         
    Epoch 13:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:   8%|▊         | 1/13 [00:00<00:00, 78.65it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:   8%|▊         | 1/13 [00:00<00:00, 77.40it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  15%|█▌        | 2/13 [00:00<00:00, 80.43it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  15%|█▌        | 2/13 [00:00<00:00, 79.77it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  23%|██▎       | 3/13 [00:00<00:00, 80.86it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  23%|██▎       | 3/13 [00:00<00:00, 80.41it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  31%|███       | 4/13 [00:00<00:00, 80.73it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  31%|███       | 4/13 [00:00<00:00, 80.37it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  38%|███▊      | 5/13 [00:00<00:00, 80.35it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  38%|███▊      | 5/13 [00:00<00:00, 80.09it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  46%|████▌     | 6/13 [00:00<00:00, 80.60it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  46%|████▌     | 6/13 [00:00<00:00, 80.34it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  54%|█████▍    | 7/13 [00:00<00:00, 80.66it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  54%|█████▍    | 7/13 [00:00<00:00, 80.47it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  62%|██████▏   | 8/13 [00:00<00:00, 80.79it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  62%|██████▏   | 8/13 [00:00<00:00, 80.63it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  69%|██████▉   | 9/13 [00:00<00:00, 80.54it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  69%|██████▉   | 9/13 [00:00<00:00, 80.38it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  77%|███████▋  | 10/13 [00:00<00:00, 80.64it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  77%|███████▋  | 10/13 [00:00<00:00, 80.51it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  85%|████████▍ | 11/13 [00:00<00:00, 80.78it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  85%|████████▍ | 11/13 [00:00<00:00, 80.66it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  92%|█████████▏| 12/13 [00:00<00:00, 80.87it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13:  92%|█████████▏| 12/13 [00:00<00:00, 80.76it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13: 100%|██████████| 13/13 [00:00<00:00, 80.89it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13: 100%|██████████| 13/13 [00:00<00:00, 80.79it/s, v_num=tion, val_loss=2.090, train_loss=0.330]
    Epoch 13: 100%|██████████| 13/13 [00:00<00:00, 73.63it/s, v_num=tion, val_loss=2.150, train_loss=0.330]
    Epoch 13: 100%|██████████| 13/13 [00:00<00:00, 73.37it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 13:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.150, train_loss=0.333]         
    Epoch 14:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:   8%|▊         | 1/13 [00:00<00:00, 81.20it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:   8%|▊         | 1/13 [00:00<00:00, 79.87it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  15%|█▌        | 2/13 [00:00<00:00, 81.64it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  15%|█▌        | 2/13 [00:00<00:00, 80.91it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  23%|██▎       | 3/13 [00:00<00:00, 80.72it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  23%|██▎       | 3/13 [00:00<00:00, 80.25it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  31%|███       | 4/13 [00:00<00:00, 81.06it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  31%|███       | 4/13 [00:00<00:00, 80.72it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  38%|███▊      | 5/13 [00:00<00:00, 81.23it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  38%|███▊      | 5/13 [00:00<00:00, 80.96it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  46%|████▌     | 6/13 [00:00<00:00, 81.35it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  46%|████▌     | 6/13 [00:00<00:00, 81.10it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  54%|█████▍    | 7/13 [00:00<00:00, 81.03it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  54%|█████▍    | 7/13 [00:00<00:00, 80.84it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  62%|██████▏   | 8/13 [00:00<00:00, 81.13it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  62%|██████▏   | 8/13 [00:00<00:00, 80.94it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  69%|██████▉   | 9/13 [00:00<00:00, 81.17it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  69%|██████▉   | 9/13 [00:00<00:00, 81.02it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  77%|███████▋  | 10/13 [00:00<00:00, 81.17it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  77%|███████▋  | 10/13 [00:00<00:00, 81.03it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  85%|████████▍ | 11/13 [00:00<00:00, 80.90it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  85%|████████▍ | 11/13 [00:00<00:00, 80.78it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  92%|█████████▏| 12/13 [00:00<00:00, 80.99it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14:  92%|█████████▏| 12/13 [00:00<00:00, 80.87it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14: 100%|██████████| 13/13 [00:00<00:00, 80.94it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14: 100%|██████████| 13/13 [00:00<00:00, 80.81it/s, v_num=tion, val_loss=2.150, train_loss=0.333]
    Epoch 14: 100%|██████████| 13/13 [00:00<00:00, 73.41it/s, v_num=tion, val_loss=2.380, train_loss=0.333]
    Epoch 14: 100%|██████████| 13/13 [00:00<00:00, 73.14it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 14:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.380, train_loss=0.281]         
    Epoch 15:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:   8%|▊         | 1/13 [00:00<00:00, 78.10it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:   8%|▊         | 1/13 [00:00<00:00, 76.87it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  15%|█▌        | 2/13 [00:00<00:00, 80.14it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  15%|█▌        | 2/13 [00:00<00:00, 79.48it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  23%|██▎       | 3/13 [00:00<00:00, 80.66it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  23%|██▎       | 3/13 [00:00<00:00, 80.18it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  31%|███       | 4/13 [00:00<00:00, 80.83it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  31%|███       | 4/13 [00:00<00:00, 80.49it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  38%|███▊      | 5/13 [00:00<00:00, 80.50it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  38%|███▊      | 5/13 [00:00<00:00, 80.22it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  46%|████▌     | 6/13 [00:00<00:00, 80.68it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  46%|████▌     | 6/13 [00:00<00:00, 80.44it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  54%|█████▍    | 7/13 [00:00<00:00, 80.69it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  54%|█████▍    | 7/13 [00:00<00:00, 80.50it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  62%|██████▏   | 8/13 [00:00<00:00, 80.64it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  62%|██████▏   | 8/13 [00:00<00:00, 80.40it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  69%|██████▉   | 9/13 [00:00<00:00, 80.13it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  69%|██████▉   | 9/13 [00:00<00:00, 79.96it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  77%|███████▋  | 10/13 [00:00<00:00, 80.26it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  77%|███████▋  | 10/13 [00:00<00:00, 80.13it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  85%|████████▍ | 11/13 [00:00<00:00, 80.35it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  85%|████████▍ | 11/13 [00:00<00:00, 80.23it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  92%|█████████▏| 12/13 [00:00<00:00, 80.38it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15:  92%|█████████▏| 12/13 [00:00<00:00, 80.26it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15: 100%|██████████| 13/13 [00:00<00:00, 80.22it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15: 100%|██████████| 13/13 [00:00<00:00, 80.11it/s, v_num=tion, val_loss=2.380, train_loss=0.281]
    Epoch 15: 100%|██████████| 13/13 [00:00<00:00, 73.00it/s, v_num=tion, val_loss=2.200, train_loss=0.281]
    Epoch 15: 100%|██████████| 13/13 [00:00<00:00, 72.73it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 15:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.200, train_loss=0.335]         
    Epoch 16:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:   8%|▊         | 1/13 [00:00<00:00, 81.52it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:   8%|▊         | 1/13 [00:00<00:00, 80.18it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  15%|█▌        | 2/13 [00:00<00:00, 81.55it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  15%|█▌        | 2/13 [00:00<00:00, 80.88it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  23%|██▎       | 3/13 [00:00<00:00, 80.45it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  23%|██▎       | 3/13 [00:00<00:00, 80.01it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  31%|███       | 4/13 [00:00<00:00, 80.72it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  31%|███       | 4/13 [00:00<00:00, 80.39it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  38%|███▊      | 5/13 [00:00<00:00, 80.89it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  38%|███▊      | 5/13 [00:00<00:00, 80.60it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  46%|████▌     | 6/13 [00:00<00:00, 80.92it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  46%|████▌     | 6/13 [00:00<00:00, 80.70it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  54%|█████▍    | 7/13 [00:00<00:00, 80.57it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  54%|█████▍    | 7/13 [00:00<00:00, 80.36it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  62%|██████▏   | 8/13 [00:00<00:00, 80.70it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  62%|██████▏   | 8/13 [00:00<00:00, 80.53it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  69%|██████▉   | 9/13 [00:00<00:00, 80.87it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  69%|██████▉   | 9/13 [00:00<00:00, 80.72it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  77%|███████▋  | 10/13 [00:00<00:00, 81.00it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  77%|███████▋  | 10/13 [00:00<00:00, 80.86it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  85%|████████▍ | 11/13 [00:00<00:00, 80.76it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  85%|████████▍ | 11/13 [00:00<00:00, 80.64it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  92%|█████████▏| 12/13 [00:00<00:00, 80.86it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16:  92%|█████████▏| 12/13 [00:00<00:00, 80.74it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16: 100%|██████████| 13/13 [00:00<00:00, 81.09it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16: 100%|██████████| 13/13 [00:00<00:00, 80.99it/s, v_num=tion, val_loss=2.200, train_loss=0.335]
    Epoch 16: 100%|██████████| 13/13 [00:00<00:00, 73.70it/s, v_num=tion, val_loss=1.890, train_loss=0.335]
    Epoch 16: 100%|██████████| 13/13 [00:00<00:00, 73.44it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 16:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.890, train_loss=0.205]         
    Epoch 17:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:   8%|▊         | 1/13 [00:00<00:00, 78.17it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:   8%|▊         | 1/13 [00:00<00:00, 76.93it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  15%|█▌        | 2/13 [00:00<00:00, 79.94it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  15%|█▌        | 2/13 [00:00<00:00, 79.24it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  23%|██▎       | 3/13 [00:00<00:00, 80.12it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  23%|██▎       | 3/13 [00:00<00:00, 79.68it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  31%|███       | 4/13 [00:00<00:00, 80.32it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  31%|███       | 4/13 [00:00<00:00, 79.99it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  38%|███▊      | 5/13 [00:00<00:00, 80.02it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  38%|███▊      | 5/13 [00:00<00:00, 79.76it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  46%|████▌     | 6/13 [00:00<00:00, 80.22it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  46%|████▌     | 6/13 [00:00<00:00, 80.00it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  54%|█████▍    | 7/13 [00:00<00:00, 80.42it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  54%|█████▍    | 7/13 [00:00<00:00, 80.23it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  62%|██████▏   | 8/13 [00:00<00:00, 80.62it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  62%|██████▏   | 8/13 [00:00<00:00, 80.44it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  69%|██████▉   | 9/13 [00:00<00:00, 80.33it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  69%|██████▉   | 9/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  77%|███████▋  | 10/13 [00:00<00:00, 80.51it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  77%|███████▋  | 10/13 [00:00<00:00, 80.36it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  85%|████████▍ | 11/13 [00:00<00:00, 80.55it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  85%|████████▍ | 11/13 [00:00<00:00, 80.43it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  92%|█████████▏| 12/13 [00:00<00:00, 80.65it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17:  92%|█████████▏| 12/13 [00:00<00:00, 80.54it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17: 100%|██████████| 13/13 [00:00<00:00, 80.69it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17: 100%|██████████| 13/13 [00:00<00:00, 80.57it/s, v_num=tion, val_loss=1.890, train_loss=0.205]
    Epoch 17: 100%|██████████| 13/13 [00:00<00:00, 73.45it/s, v_num=tion, val_loss=2.080, train_loss=0.205]
    Epoch 17: 100%|██████████| 13/13 [00:00<00:00, 73.18it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 17:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.080, train_loss=0.135]         
    Epoch 18:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:   8%|▊         | 1/13 [00:00<00:00, 81.66it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:   8%|▊         | 1/13 [00:00<00:00, 80.32it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  15%|█▌        | 2/13 [00:00<00:00, 81.73it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  15%|█▌        | 2/13 [00:00<00:00, 81.05it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  23%|██▎       | 3/13 [00:00<00:00, 80.79it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  23%|██▎       | 3/13 [00:00<00:00, 80.35it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  31%|███       | 4/13 [00:00<00:00, 81.01it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  31%|███       | 4/13 [00:00<00:00, 80.67it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  38%|███▊      | 5/13 [00:00<00:00, 81.30it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  38%|███▊      | 5/13 [00:00<00:00, 81.03it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  46%|████▌     | 6/13 [00:00<00:00, 81.36it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  46%|████▌     | 6/13 [00:00<00:00, 81.13it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  54%|█████▍    | 7/13 [00:00<00:00, 81.03it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  54%|█████▍    | 7/13 [00:00<00:00, 80.84it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  62%|██████▏   | 8/13 [00:00<00:00, 81.17it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  62%|██████▏   | 8/13 [00:00<00:00, 81.00it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  69%|██████▉   | 9/13 [00:00<00:00, 81.25it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  69%|██████▉   | 9/13 [00:00<00:00, 81.09it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  77%|███████▋  | 10/13 [00:00<00:00, 81.41it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  77%|███████▋  | 10/13 [00:00<00:00, 81.27it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  85%|████████▍ | 11/13 [00:00<00:00, 81.20it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  85%|████████▍ | 11/13 [00:00<00:00, 81.07it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  92%|█████████▏| 12/13 [00:00<00:00, 81.26it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18:  92%|█████████▏| 12/13 [00:00<00:00, 81.15it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18: 100%|██████████| 13/13 [00:00<00:00, 81.49it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18: 100%|██████████| 13/13 [00:00<00:00, 81.39it/s, v_num=tion, val_loss=2.080, train_loss=0.135]
    Epoch 18: 100%|██████████| 13/13 [00:00<00:00, 74.10it/s, v_num=tion, val_loss=1.900, train_loss=0.135]
    Epoch 18: 100%|██████████| 13/13 [00:00<00:00, 73.85it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 18:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.900, train_loss=0.121]         
    Epoch 19:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:   8%|▊         | 1/13 [00:00<00:00, 79.18it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:   8%|▊         | 1/13 [00:00<00:00, 77.92it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  15%|█▌        | 2/13 [00:00<00:00, 80.55it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  15%|█▌        | 2/13 [00:00<00:00, 79.89it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  23%|██▎       | 3/13 [00:00<00:00, 80.82it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  23%|██▎       | 3/13 [00:00<00:00, 80.37it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  31%|███       | 4/13 [00:00<00:00, 80.68it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  31%|███       | 4/13 [00:00<00:00, 80.35it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  38%|███▊      | 5/13 [00:00<00:00, 80.07it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  38%|███▊      | 5/13 [00:00<00:00, 79.81it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  46%|████▌     | 6/13 [00:00<00:00, 80.30it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  46%|████▌     | 6/13 [00:00<00:00, 80.08it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  54%|█████▍    | 7/13 [00:00<00:00, 80.34it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  54%|█████▍    | 7/13 [00:00<00:00, 80.15it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  62%|██████▏   | 8/13 [00:00<00:00, 80.35it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  62%|██████▏   | 8/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  69%|██████▉   | 9/13 [00:00<00:00, 80.03it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  69%|██████▉   | 9/13 [00:00<00:00, 79.88it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  77%|███████▋  | 10/13 [00:00<00:00, 80.18it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  77%|███████▋  | 10/13 [00:00<00:00, 80.05it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  85%|████████▍ | 11/13 [00:00<00:00, 80.17it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  85%|████████▍ | 11/13 [00:00<00:00, 80.05it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  92%|█████████▏| 12/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19:  92%|█████████▏| 12/13 [00:00<00:00, 80.08it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19: 100%|██████████| 13/13 [00:00<00:00, 80.26it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19: 100%|██████████| 13/13 [00:00<00:00, 80.16it/s, v_num=tion, val_loss=1.900, train_loss=0.121]
    Epoch 19: 100%|██████████| 13/13 [00:00<00:00, 73.08it/s, v_num=tion, val_loss=2.000, train_loss=0.121]
    Epoch 19: 100%|██████████| 13/13 [00:00<00:00, 72.82it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 19:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.000, train_loss=0.092]         
    Epoch 20:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:   8%|▊         | 1/13 [00:00<00:00, 78.60it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:   8%|▊         | 1/13 [00:00<00:00, 77.35it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  15%|█▌        | 2/13 [00:00<00:00, 78.02it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  15%|█▌        | 2/13 [00:00<00:00, 77.40it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  23%|██▎       | 3/13 [00:00<00:00, 77.81it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  23%|██▎       | 3/13 [00:00<00:00, 77.38it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  31%|███       | 4/13 [00:00<00:00, 78.51it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  31%|███       | 4/13 [00:00<00:00, 78.17it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  38%|███▊      | 5/13 [00:00<00:00, 78.72it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  38%|███▊      | 5/13 [00:00<00:00, 78.46it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  46%|████▌     | 6/13 [00:00<00:00, 78.94it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  46%|████▌     | 6/13 [00:00<00:00, 78.73it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  54%|█████▍    | 7/13 [00:00<00:00, 78.86it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  54%|█████▍    | 7/13 [00:00<00:00, 78.67it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  62%|██████▏   | 8/13 [00:00<00:00, 78.97it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  62%|██████▏   | 8/13 [00:00<00:00, 78.81it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  69%|██████▉   | 9/13 [00:00<00:00, 79.28it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  69%|██████▉   | 9/13 [00:00<00:00, 79.13it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  77%|███████▋  | 10/13 [00:00<00:00, 79.38it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  77%|███████▋  | 10/13 [00:00<00:00, 79.25it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  85%|████████▍ | 11/13 [00:00<00:00, 79.31it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  85%|████████▍ | 11/13 [00:00<00:00, 79.20it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  92%|█████████▏| 12/13 [00:00<00:00, 79.40it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20:  92%|█████████▏| 12/13 [00:00<00:00, 79.27it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20: 100%|██████████| 13/13 [00:00<00:00, 79.66it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20: 100%|██████████| 13/13 [00:00<00:00, 79.55it/s, v_num=tion, val_loss=2.000, train_loss=0.092]
    Epoch 20: 100%|██████████| 13/13 [00:00<00:00, 72.41it/s, v_num=tion, val_loss=2.050, train_loss=0.092]
    Epoch 20: 100%|██████████| 13/13 [00:00<00:00, 72.15it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 20:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]         
    Epoch 21:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:   8%|▊         | 1/13 [00:00<00:00, 77.26it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:   8%|▊         | 1/13 [00:00<00:00, 76.06it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  15%|█▌        | 2/13 [00:00<00:00, 79.39it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  15%|█▌        | 2/13 [00:00<00:00, 78.75it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  23%|██▎       | 3/13 [00:00<00:00, 80.00it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  23%|██▎       | 3/13 [00:00<00:00, 79.56it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  31%|███       | 4/13 [00:00<00:00, 80.43it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  31%|███       | 4/13 [00:00<00:00, 80.10it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  38%|███▊      | 5/13 [00:00<00:00, 80.34it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  38%|███▊      | 5/13 [00:00<00:00, 80.03it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  46%|████▌     | 6/13 [00:00<00:00, 80.67it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  46%|████▌     | 6/13 [00:00<00:00, 80.43it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  54%|█████▍    | 7/13 [00:00<00:00, 80.84it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  54%|█████▍    | 7/13 [00:00<00:00, 80.65it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  62%|██████▏   | 8/13 [00:00<00:00, 80.99it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  62%|██████▏   | 8/13 [00:00<00:00, 80.82it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  69%|██████▉   | 9/13 [00:00<00:00, 80.76it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  69%|██████▉   | 9/13 [00:00<00:00, 80.60it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  77%|███████▋  | 10/13 [00:00<00:00, 80.92it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  77%|███████▋  | 10/13 [00:00<00:00, 80.79it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  85%|████████▍ | 11/13 [00:00<00:00, 81.02it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  85%|████████▍ | 11/13 [00:00<00:00, 80.89it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  92%|█████████▏| 12/13 [00:00<00:00, 81.10it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21:  92%|█████████▏| 12/13 [00:00<00:00, 80.99it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21: 100%|██████████| 13/13 [00:00<00:00, 81.10it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21: 100%|██████████| 13/13 [00:00<00:00, 80.99it/s, v_num=tion, val_loss=2.050, train_loss=0.0845]
    Epoch 21: 100%|██████████| 13/13 [00:00<00:00, 73.56it/s, v_num=tion, val_loss=1.730, train_loss=0.0845]
    Epoch 21: 100%|██████████| 13/13 [00:00<00:00, 73.30it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 21:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]         
    Epoch 22:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:   8%|▊         | 1/13 [00:00<00:00, 79.76it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:   8%|▊         | 1/13 [00:00<00:00, 78.49it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  15%|█▌        | 2/13 [00:00<00:00, 79.88it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  15%|█▌        | 2/13 [00:00<00:00, 79.23it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  23%|██▎       | 3/13 [00:00<00:00, 78.54it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  23%|██▎       | 3/13 [00:00<00:00, 78.11it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  31%|███       | 4/13 [00:00<00:00, 79.03it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  31%|███       | 4/13 [00:00<00:00, 78.71it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  38%|███▊      | 5/13 [00:00<00:00, 79.13it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  38%|███▊      | 5/13 [00:00<00:00, 78.87it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  46%|████▌     | 6/13 [00:00<00:00, 79.37it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  46%|████▌     | 6/13 [00:00<00:00, 79.16it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  54%|█████▍    | 7/13 [00:00<00:00, 78.99it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  54%|█████▍    | 7/13 [00:00<00:00, 78.80it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  62%|██████▏   | 8/13 [00:00<00:00, 79.20it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  62%|██████▏   | 8/13 [00:00<00:00, 79.03it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  69%|██████▉   | 9/13 [00:00<00:00, 79.09it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  69%|██████▉   | 9/13 [00:00<00:00, 78.95it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  77%|███████▋  | 10/13 [00:00<00:00, 79.19it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  77%|███████▋  | 10/13 [00:00<00:00, 79.05it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  85%|████████▍ | 11/13 [00:00<00:00, 78.86it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  85%|████████▍ | 11/13 [00:00<00:00, 78.74it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  92%|█████████▏| 12/13 [00:00<00:00, 79.07it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22:  92%|█████████▏| 12/13 [00:00<00:00, 78.97it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22: 100%|██████████| 13/13 [00:00<00:00, 79.37it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22: 100%|██████████| 13/13 [00:00<00:00, 79.27it/s, v_num=tion, val_loss=1.730, train_loss=0.0588]
    Epoch 22: 100%|██████████| 13/13 [00:00<00:00, 72.14it/s, v_num=tion, val_loss=1.910, train_loss=0.0588]
    Epoch 22: 100%|██████████| 13/13 [00:00<00:00, 71.89it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 22:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]         
    Epoch 23:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:   8%|▊         | 1/13 [00:00<00:00, 78.27it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:   8%|▊         | 1/13 [00:00<00:00, 76.91it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  15%|█▌        | 2/13 [00:00<00:00, 78.71it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  15%|█▌        | 2/13 [00:00<00:00, 78.08it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  23%|██▎       | 3/13 [00:00<00:00, 79.17it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  23%|██▎       | 3/13 [00:00<00:00, 78.69it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  31%|███       | 4/13 [00:00<00:00, 79.59it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  31%|███       | 4/13 [00:00<00:00, 79.26it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  38%|███▊      | 5/13 [00:00<00:00, 79.65it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  38%|███▊      | 5/13 [00:00<00:00, 79.34it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  46%|████▌     | 6/13 [00:00<00:00, 79.92it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  46%|████▌     | 6/13 [00:00<00:00, 79.70it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  54%|█████▍    | 7/13 [00:00<00:00, 80.18it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  54%|█████▍    | 7/13 [00:00<00:00, 80.00it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  62%|██████▏   | 8/13 [00:00<00:00, 80.36it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  62%|██████▏   | 8/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  69%|██████▉   | 9/13 [00:00<00:00, 80.05it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  69%|██████▉   | 9/13 [00:00<00:00, 79.90it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  77%|███████▋  | 10/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  77%|███████▋  | 10/13 [00:00<00:00, 80.06it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  85%|████████▍ | 11/13 [00:00<00:00, 80.29it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  85%|████████▍ | 11/13 [00:00<00:00, 80.17it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  92%|█████████▏| 12/13 [00:00<00:00, 80.42it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23:  92%|█████████▏| 12/13 [00:00<00:00, 80.31it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23: 100%|██████████| 13/13 [00:00<00:00, 80.52it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23: 100%|██████████| 13/13 [00:00<00:00, 80.42it/s, v_num=tion, val_loss=1.910, train_loss=0.0419]
    Epoch 23: 100%|██████████| 13/13 [00:00<00:00, 73.28it/s, v_num=tion, val_loss=1.870, train_loss=0.0419]
    Epoch 23: 100%|██████████| 13/13 [00:00<00:00, 73.01it/s, v_num=tion, val_loss=1.870, train_loss=0.053] 
    Epoch 23:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.870, train_loss=0.053]         
    Epoch 24:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:   8%|▊         | 1/13 [00:00<00:00, 81.99it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:   8%|▊         | 1/13 [00:00<00:00, 80.50it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  15%|█▌        | 2/13 [00:00<00:00, 81.22it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  15%|█▌        | 2/13 [00:00<00:00, 80.53it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  23%|██▎       | 3/13 [00:00<00:00, 80.19it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  23%|██▎       | 3/13 [00:00<00:00, 79.75it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  31%|███       | 4/13 [00:00<00:00, 80.60it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  31%|███       | 4/13 [00:00<00:00, 80.27it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  38%|███▊      | 5/13 [00:00<00:00, 80.75it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  38%|███▊      | 5/13 [00:00<00:00, 80.49it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  46%|████▌     | 6/13 [00:00<00:00, 80.92it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  46%|████▌     | 6/13 [00:00<00:00, 80.67it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  54%|█████▍    | 7/13 [00:00<00:00, 80.36it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  54%|█████▍    | 7/13 [00:00<00:00, 80.15it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  62%|██████▏   | 8/13 [00:00<00:00, 80.62it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  62%|██████▏   | 8/13 [00:00<00:00, 80.43it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  69%|██████▉   | 9/13 [00:00<00:00, 80.75it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  69%|██████▉   | 9/13 [00:00<00:00, 80.60it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  77%|███████▋  | 10/13 [00:00<00:00, 80.90it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  77%|███████▋  | 10/13 [00:00<00:00, 80.77it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  85%|████████▍ | 11/13 [00:00<00:00, 80.65it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  85%|████████▍ | 11/13 [00:00<00:00, 80.53it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  92%|█████████▏| 12/13 [00:00<00:00, 80.77it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24:  92%|█████████▏| 12/13 [00:00<00:00, 80.66it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24: 100%|██████████| 13/13 [00:00<00:00, 81.05it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24: 100%|██████████| 13/13 [00:00<00:00, 80.94it/s, v_num=tion, val_loss=1.870, train_loss=0.053]
    Epoch 24: 100%|██████████| 13/13 [00:00<00:00, 73.69it/s, v_num=tion, val_loss=1.800, train_loss=0.053]
    Epoch 24: 100%|██████████| 13/13 [00:00<00:00, 73.44it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 24:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]         
    Epoch 25:   0%|          | 0/13 [00:00<?, ?it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:   8%|▊         | 1/13 [00:00<00:00, 79.42it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:   8%|▊         | 1/13 [00:00<00:00, 78.02it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  15%|█▌        | 2/13 [00:00<00:00, 80.43it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  15%|█▌        | 2/13 [00:00<00:00, 79.77it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  23%|██▎       | 3/13 [00:00<00:00, 81.14it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  23%|██▎       | 3/13 [00:00<00:00, 80.69it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  31%|███       | 4/13 [00:00<00:00, 81.26it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  31%|███       | 4/13 [00:00<00:00, 80.93it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  38%|███▊      | 5/13 [00:00<00:00, 80.81it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  38%|███▊      | 5/13 [00:00<00:00, 80.54it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  46%|████▌     | 6/13 [00:00<00:00, 80.96it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  46%|████▌     | 6/13 [00:00<00:00, 80.73it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  54%|█████▍    | 7/13 [00:00<00:00, 81.09it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  54%|█████▍    | 7/13 [00:00<00:00, 80.89it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  62%|██████▏   | 8/13 [00:00<00:00, 81.16it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  62%|██████▏   | 8/13 [00:00<00:00, 80.98it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  69%|██████▉   | 9/13 [00:00<00:00, 80.85it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  69%|██████▉   | 9/13 [00:00<00:00, 80.70it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  77%|███████▋  | 10/13 [00:00<00:00, 80.98it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  77%|███████▋  | 10/13 [00:00<00:00, 80.83it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  85%|████████▍ | 11/13 [00:00<00:00, 81.06it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  85%|████████▍ | 11/13 [00:00<00:00, 80.94it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  92%|█████████▏| 12/13 [00:00<00:00, 81.09it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25:  92%|█████████▏| 12/13 [00:00<00:00, 80.98it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25: 100%|██████████| 13/13 [00:00<00:00, 81.01it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25: 100%|██████████| 13/13 [00:00<00:00, 80.89it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25: 100%|██████████| 13/13 [00:00<00:00, 73.52it/s, v_num=tion, val_loss=1.800, train_loss=0.0877]
    Epoch 25: 100%|██████████| 13/13 [00:00<00:00, 73.27it/s, v_num=tion, val_loss=1.800, train_loss=0.104] 
    Epoch 25: 100%|██████████| 13/13 [00:00<00:00, 72.98it/s, v_num=tion, val_loss=1.800, train_loss=0.104]
    ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
         Validate metric           DataLoader 0
    ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
             mae_val             0.924605131149292
             mse_val            1.8015339374542236
             r2_val             0.7826212048530579
            val_loss             1.801533818244934
    ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────




.. GENERATED FROM PYTHON SOURCE LINES 140-144

6. Plotting the results 📊
----------------------------
Now we're ready to plot the results of our model.
We're using the :class:`~.RealsVsPreds` class to plot the confusion matrix.

.. GENERATED FROM PYTHON SOURCE LINES 144-149

.. code-block:: Python


    reals_preds_fig = RealsVsPreds.from_final_val_data(
        single_model_list
    )
    plt.show()



.. image-sg:: /auto_examples/training_and_testing/images/sphx_glr_plot_one_model_regression_traintest_002.png
   :alt: Evaluation: Validation Data, Tabular Crossmodal multi-head attention - Validation r2: 0.783
   :srcset: /auto_examples/training_and_testing/images/sphx_glr_plot_one_model_regression_traintest_002.png
   :class: sphx-glr-single-img






.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 5.094 seconds)


.. _sphx_glr_download_auto_examples_training_and_testing_plot_one_model_regression_traintest.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: plot_one_model_regression_traintest.ipynb <plot_one_model_regression_traintest.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: plot_one_model_regression_traintest.py <plot_one_model_regression_traintest.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: plot_one_model_regression_traintest.zip <plot_one_model_regression_traintest.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_