Regression: Comparing Two Tabular Models Trained on Simulated Data๏ƒ

๐Ÿš€ Welcome to this tutorial on training and comparing two fusion models on a regression task using simulated multimodal tabular data! ๐ŸŽ‰

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 halfโ€™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.

๐ŸŒŸ Key Features:

  • ๐Ÿ“ฅ Importing models based on name.

  • ๐Ÿงช Training and testing models with train/test protocol.

  • ๐Ÿ’พ Saving trained models to a dictionary for later analysis.

  • ๐Ÿ“Š Plotting the results of a single model.

  • ๐Ÿ“ˆ Plotting the results of multiple models as a bar chart.

  • ๐Ÿ’พ Saving the results of multiple models as a CSV file.

import importlib

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

from fusilli.data import prepare_fusion_data
from fusilli.eval import RealsVsPreds, ModelComparison
from fusilli.train import train_and_save_models
from fusilli.utils.model_chooser import import_chosen_fusion_models

# sphinx_gallery_thumbnail_number = -1

1. Import fusion models ๐Ÿ”๏ƒ

Letโ€™s kick things off by importing our fusion models. The models are imported using the import_chosen_fusion_models() function, which takes a dictionary of conditions as an input. The conditions are the attributes of the models, e.g. the class name, the modality type, etc.

The function returns list of class objects that match the conditions. If no conditions are specified, then all the models are returned.

Weโ€™re importing Tabular1Unimodal and ConcatTabularFeatureMaps `models for this example, so we have one unimodal benchmark and one multimodal model.

model_conditions = {
    "class_name": ["Tabular1Unimodal", "ConcatTabularFeatureMaps"],
}

fusion_models = import_chosen_fusion_models(model_conditions)
Imported methods:
['Tabular1 uni-modal' 'Concatenating tabular feature maps']

2. Set the training parameters ๐ŸŽฏ๏ƒ

Now, letโ€™s configure our training parameters. The parameters are stored in a dictionary and passed to most of the methods in this library.

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 canโ€™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.

# Regression task (predicting a binary variable - 0 or 1)
prediction_task = "regression"

# Set the batch size
batch_size = 48

# Set the test_size
test_size = 0.3

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

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))

3. Specifying input file paths ๐Ÿ”ฎ๏ƒ

Weโ€™re using MNIST data for this example, and the CSV files are stored in the _static/mnist_data directory with the documentation files.

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

4. Training the first fusion model ๐Ÿ๏ƒ

Here we train the first fusion model. Weโ€™re using the train_and_save_models function to train and test the models. This function takes the following inputs:

  • 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.

First weโ€™ll create a dictionary to store both the trained models so we can compare them later.

all_trained_models = {}  # create dictionary to store trained models

To train the first model we need to:

  1. Choose the model: Weโ€™re using the first model in the fusion_models list we made earlier.

  2. Print the attributes of the model: To check itโ€™s been initialised correctly.

  3. Create the datamodule: This is done with the prepare_fusion_data() function. This function takes the initialised model and some parameters as inputs. It returns the datamodule.

  4. Train and test the model: This is done with the train_and_save_models() function. This function takes the datamodule and the fusion model as inputs, as well as optional training modifications. It returns the trained model.

  5. Add the trained model to the ``all_trained_models`` dictionary: This is so we can compare the results of the two models later.

fusion_model = fusion_models[0]

print("Method name:", fusion_model.method_name)
print("Modality type:", fusion_model.modality_type)
print("Fusion type:", fusion_model.fusion_type)

# Create the data module
dm = prepare_fusion_data(prediction_task=prediction_task,
                         fusion_model=fusion_model,
                         data_paths=data_paths,
                         output_paths=output_paths,
                         batch_size=batch_size,
                         test_size=test_size)

# train and test
model_1_list = train_and_save_models(
    data_module=dm,
    fusion_model=fusion_model,
    enable_checkpointing=False,  # False for the example notebooks
    show_loss_plot=True,
)

# Add trained model to dictionary
all_trained_models[fusion_model.__name__] = model_1_list
Loss Curves for Tabular1Unimodal
Method name: Tabular1 uni-modal
Modality type: tabular1
Fusion type: unimodal

Training: |          | 0/? [00:00<?, ?it/s]
Training:   0%|          | 0/8 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/8 [00:00<?, ?it/s]
Epoch 0:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 78.91it/s]
Epoch 0:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 76.85it/s, v_num=odal]
Epoch 0:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 92.70it/s, v_num=odal]
Epoch 0:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 91.54it/s, v_num=odal]
Epoch 0:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 99.35it/s, v_num=odal]
Epoch 0:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 98.49it/s, v_num=odal]
Epoch 0:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 102.80it/s, v_num=odal]
Epoch 0:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 102.11it/s, v_num=odal]
Epoch 0:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 104.37it/s, v_num=odal]
Epoch 0:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 103.74it/s, v_num=odal]
Epoch 0:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 105.79it/s, v_num=odal]
Epoch 0:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 105.26it/s, v_num=odal]
Epoch 0:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 105.45it/s, v_num=odal]
Epoch 0:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 104.93it/s, v_num=odal]
Epoch 0: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 106.98it/s, v_num=odal]
Epoch 0: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 106.55it/s, v_num=odal]
Epoch 0: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 89.83it/s, v_num=odal, val_loss=10.10]
Epoch 0: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 89.06it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 0:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.90it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 109.35it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 112.77it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 111.01it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.62it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 113.39it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.56it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.62it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.32it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 114.47it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 114.44it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 113.68it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 114.21it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 113.64it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 114.47it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 113.99it/s, v_num=odal, val_loss=10.10, train_loss=15.40]
Epoch 1: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 97.90it/s, v_num=odal, val_loss=7.280, train_loss=15.40]
Epoch 1: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 97.02it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 1:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.57it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.85it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.11it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.21it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.32it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.04it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.50it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.54it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.77it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.00it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.98it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.34it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.30it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.75it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.54it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.04it/s, v_num=odal, val_loss=7.280, train_loss=8.730]
Epoch 2: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.09it/s, v_num=odal, val_loss=5.780, train_loss=8.730]
Epoch 2: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.17it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 2:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 117.23it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 113.41it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.58it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.67it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.24it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 113.06it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.27it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.34it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.94it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.20it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.51it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.88it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.90it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.36it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.31it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.77it/s, v_num=odal, val_loss=5.780, train_loss=6.230]
Epoch 3: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.65it/s, v_num=odal, val_loss=5.210, train_loss=6.230]
Epoch 3: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.69it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 3:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 117.63it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 113.81it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.70it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 113.81it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.06it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 113.81it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.96it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.02it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.63it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.88it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.30it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.67it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.81it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.22it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.09it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.60it/s, v_num=odal, val_loss=5.210, train_loss=4.710]
Epoch 4: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.74it/s, v_num=odal, val_loss=5.310, train_loss=4.710]
Epoch 4: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.81it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 4:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 114.71it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 110.90it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.11it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.25it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.35it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 113.14it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.94it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.03it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.32it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 114.59it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.10it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.48it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.63it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.09it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.07it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.58it/s, v_num=odal, val_loss=5.310, train_loss=4.640]
Epoch 5: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.06it/s, v_num=odal, val_loss=4.720, train_loss=4.640]
Epoch 5: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.15it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 5:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 117.57it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 113.76it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 118.46it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.52it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 118.24it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.94it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.37it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.39it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.51it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.72it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.80it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.15it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.09it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.53it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.35it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.82it/s, v_num=odal, val_loss=4.720, train_loss=4.040]
Epoch 6: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.48it/s, v_num=odal, val_loss=4.290, train_loss=4.040]
Epoch 6: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.49it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 6:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 118.93it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.05it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 119.42it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.48it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.74it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.45it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.28it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.30it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.48it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.64it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 118.62it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.93it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.37it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.75it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.88it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.34it/s, v_num=odal, val_loss=4.290, train_loss=3.900]
Epoch 7: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.38it/s, v_num=odal, val_loss=3.870, train_loss=3.900]
Epoch 7: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.45it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 7:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.21it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.00it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.43it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.54it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.97it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.68it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.41it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.45it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.72it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.85it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.31it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 114.64it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 115.51it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 114.90it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.84it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.33it/s, v_num=odal, val_loss=3.870, train_loss=2.800]
Epoch 8: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.65it/s, v_num=odal, val_loss=3.600, train_loss=2.800]
Epoch 8: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.67it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 8:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.35it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 111.46it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 109.11it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 107.23it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 108.73it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 106.95it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 110.07it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 109.18it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 110.83it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 110.09it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 111.38it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 110.76it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 111.81it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 111.25it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 113.10it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 112.64it/s, v_num=odal, val_loss=3.600, train_loss=2.240]
Epoch 9: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 96.40it/s, v_num=odal, val_loss=3.290, train_loss=2.240]
Epoch 9: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 95.53it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 9:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.66it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.93it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.40it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.32it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.50it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.08it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.76it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.77it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.39it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 114.62it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 114.43it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 113.77it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 114.57it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 113.97it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 115.67it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 115.15it/s, v_num=odal, val_loss=3.290, train_loss=2.270]
Epoch 10: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.69it/s, v_num=odal, val_loss=3.700, train_loss=2.270]
Epoch 10: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 97.72it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 10:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.30it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.56it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.31it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.42it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.04it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.78it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.05it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.06it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.63it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.84it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.63it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.98it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.66it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.11it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.58it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.09it/s, v_num=odal, val_loss=3.700, train_loss=1.880]
Epoch 11: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.46it/s, v_num=odal, val_loss=3.540, train_loss=1.880]
Epoch 11: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.53it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 11:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 111.01it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 107.57it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.43it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 112.62it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.91it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.65it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.83it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.87it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.85it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.03it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.37it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 114.65it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 115.33it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 114.76it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.56it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.06it/s, v_num=odal, val_loss=3.540, train_loss=1.890]
Epoch 12: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.80it/s, v_num=odal, val_loss=3.440, train_loss=1.890]
Epoch 12: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 97.87it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 12:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 113.90it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 110.03it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.73it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 112.83it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 113.55it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 112.33it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.51it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 113.57it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.20it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 114.43it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.68it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.03it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.16it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 115.61it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.56it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.06it/s, v_num=odal, val_loss=3.440, train_loss=1.820]
Epoch 13: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.78it/s, v_num=odal, val_loss=3.750, train_loss=1.820]
Epoch 13: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.88it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 13:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.75it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 113.03it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.66it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.74it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 118.15it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.83it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.38it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.38it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.48it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.69it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.71it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.05it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.05it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.45it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.39it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.89it/s, v_num=odal, val_loss=3.750, train_loss=1.410]
Epoch 14: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.86it/s, v_num=odal, val_loss=3.440, train_loss=1.410]
Epoch 14: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.89it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 14:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 119.25it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.36it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 119.32it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.37it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.48it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.18it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.21it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.24it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.57it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.78it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 118.90it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 118.08it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.43it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.87it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.78it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.23it/s, v_num=odal, val_loss=3.440, train_loss=1.510]
Epoch 15: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.57it/s, v_num=odal, val_loss=3.480, train_loss=1.510]
Epoch 15: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.63it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 15:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.18it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 111.50it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.64it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 113.77it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.70it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.37it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.59it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.61it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.59it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 114.80it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 114.84it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 114.20it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 115.52it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 114.98it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.72it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.24it/s, v_num=odal, val_loss=3.480, train_loss=1.500]
Epoch 16: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.24it/s, v_num=odal, val_loss=3.040, train_loss=1.500]
Epoch 16: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.34it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 16:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.64it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.91it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 118.31it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.36it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.12it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.84it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.70it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.72it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.24it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.46it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.94it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.28it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.41it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.82it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.73it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.23it/s, v_num=odal, val_loss=3.040, train_loss=1.390]
Epoch 17: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.23it/s, v_num=odal, val_loss=2.950, train_loss=1.390]
Epoch 17: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.21it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 17:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.23it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.51it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.69it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.76it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.21it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.90it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.97it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.87it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.95it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.17it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.28it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 114.63it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 115.45it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 114.87it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.60it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.09it/s, v_num=odal, val_loss=2.950, train_loss=1.150]
Epoch 18: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.34it/s, v_num=odal, val_loss=2.870, train_loss=1.150]
Epoch 18: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.40it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 18:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 113.53it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 109.95it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.17it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 113.29it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.00it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 112.78it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.42it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.49it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.30it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.54it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.88it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.23it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.30it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.71it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.73it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.23it/s, v_num=odal, val_loss=2.870, train_loss=0.973]
Epoch 19: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.75it/s, v_num=odal, val_loss=2.900, train_loss=0.973]
Epoch 19: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.76it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 19:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 119.76it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.84it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 120.12it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 118.13it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 120.22it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 118.87it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 120.40it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 119.39it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 120.36it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 119.55it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 119.40it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 118.69it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 119.51it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.86it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 120.68it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 120.12it/s, v_num=odal, val_loss=2.900, train_loss=0.691]
Epoch 20: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 102.51it/s, v_num=odal, val_loss=2.770, train_loss=0.691]
Epoch 20: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.47it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 20:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.77it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.01it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.12it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.20it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.57it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.27it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.13it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.05it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.24it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.43it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.57it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.90it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.64it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.05it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.83it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.33it/s, v_num=odal, val_loss=2.770, train_loss=0.663]
Epoch 21: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.58it/s, v_num=odal, val_loss=2.760, train_loss=0.663]
Epoch 21: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.65it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 21:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.16it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.42it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.13it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.21it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.85it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.53it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.39it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.42it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.88it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.09it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 118.17it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.51it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.32it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.75it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.61it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.11it/s, v_num=odal, val_loss=2.760, train_loss=0.714]
Epoch 22: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.49it/s, v_num=odal, val_loss=2.940, train_loss=0.714]
Epoch 22: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.49it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 22:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 117.98it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 114.16it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 118.70it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.77it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.26it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.96it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.07it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.08it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.60it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.80it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 119.08it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 118.41it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 119.41it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.83it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 120.71it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 120.19it/s, v_num=odal, val_loss=2.940, train_loss=0.883]
Epoch 23: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 102.01it/s, v_num=odal, val_loss=2.860, train_loss=0.883]
Epoch 23: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.06it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 23:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 117.63it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 113.84it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 118.10it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.17it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 118.47it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.17it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.97it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.98it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.13it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.33it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.26it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.55it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.60it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.04it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.34it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.84it/s, v_num=odal, val_loss=2.860, train_loss=0.679]
Epoch 24: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.18it/s, v_num=odal, val_loss=2.910, train_loss=0.679]
Epoch 24: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.28it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 24:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 120.19it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.03it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 120.29it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.99it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 118.26it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.95it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.86it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.86it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 119.29it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.49it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 119.00it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 118.34it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 119.37it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.80it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 120.66it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 120.15it/s, v_num=odal, val_loss=2.910, train_loss=0.648]
Epoch 25: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 102.34it/s, v_num=odal, val_loss=2.890, train_loss=0.648]
Epoch 25: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.38it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 25:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 119.63it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.56it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 118.40it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.47it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 119.05it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.73it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.66it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.67it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.89it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.08it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 118.14it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.47it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.41it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.84it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.40it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.90it/s, v_num=odal, val_loss=2.890, train_loss=0.597]
Epoch 26: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.70it/s, v_num=odal, val_loss=2.830, train_loss=0.597]
Epoch 26: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.76it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 26:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 117.39it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 113.61it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.96it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.02it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.88it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.61it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.80it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.82it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.17it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.39it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 118.55it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.89it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.90it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 118.34it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 120.25it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.74it/s, v_num=odal, val_loss=2.830, train_loss=0.445]
Epoch 27: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.51it/s, v_num=odal, val_loss=3.010, train_loss=0.445]
Epoch 27: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.55it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 27:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 114.48it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 110.85it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.25it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.36it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 117.04it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.75it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.26it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.23it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.15it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.31it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.44it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 114.76it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 114.93it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 114.10it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 115.94it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 115.47it/s, v_num=odal, val_loss=3.010, train_loss=0.485]
Epoch 28: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.93it/s, v_num=odal, val_loss=2.970, train_loss=0.485]
Epoch 28: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.03it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 28:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 116.68it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.42it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.43it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.50it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.00it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.75it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.96it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.99it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.81it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.03it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.73it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.08it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.77it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.22it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.49it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.99it/s, v_num=odal, val_loss=2.970, train_loss=0.583]
Epoch 29: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.80it/s, v_num=odal, val_loss=3.010, train_loss=0.583]
Epoch 29: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.81it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 29:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.82it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.08it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.14it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 115.21it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 118.01it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.69it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 118.10it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.10it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 118.19it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.40it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 117.43it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.78it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.76it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.21it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 119.01it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.45it/s, v_num=odal, val_loss=3.010, train_loss=0.388]
Epoch 30: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 101.39it/s, v_num=odal, val_loss=3.030, train_loss=0.388]
Epoch 30: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.51it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 30:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 118.97it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.10it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 119.65it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 117.68it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 118.27it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 116.35it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 108.81it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 107.97it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 109.89it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 109.16it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 109.53it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 108.95it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 110.84it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 110.34it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 112.27it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 111.82it/s, v_num=odal, val_loss=3.030, train_loss=0.519]
Epoch 31: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 95.80it/s, v_num=odal, val_loss=2.860, train_loss=0.519]
Epoch 31: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 94.95it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 31:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 114.68it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 110.91it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.75it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 112.85it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.35it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.02it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.84it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.85it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.33it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.55it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.87it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.23it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.32it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 115.75it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.60it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.09it/s, v_num=odal, val_loss=2.860, train_loss=0.559]
Epoch 32: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.17it/s, v_num=odal, val_loss=3.100, train_loss=0.559]
Epoch 32: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.16it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 32:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.41it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 111.73it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.89it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.99it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.87it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.62it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 117.14it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.13it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 117.76it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.91it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.71it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.15it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 115.59it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 115.07it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.89it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 116.40it/s, v_num=odal, val_loss=3.100, train_loss=0.457]
Epoch 33: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.06it/s, v_num=odal, val_loss=2.770, train_loss=0.457]
Epoch 33: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.13it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 33:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 111.49it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 107.95it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 112.17it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 110.26it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 112.30it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 110.99it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 113.00it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 111.96it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 113.63it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 112.86it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 113.20it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 112.56it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 113.87it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 113.32it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 115.51it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 115.02it/s, v_num=odal, val_loss=2.770, train_loss=0.516]
Epoch 34: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 98.02it/s, v_num=odal, val_loss=3.060, train_loss=0.516]
Epoch 34: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 97.12it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 34:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 115.82it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 112.11it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 116.72it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.79it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.75it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 113.47it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.78it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 114.82it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 116.43it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.66it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.99it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 116.34it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 117.44it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.88it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.86it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 118.37it/s, v_num=odal, val_loss=3.060, train_loss=0.434]
Epoch 35: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.74it/s, v_num=odal, val_loss=2.970, train_loss=0.434]
Epoch 35: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.77it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 35:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:   0%|          | 0/8 [00:00<?, ?it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 113.42it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 109.87it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 114.86it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 113.00it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 115.39it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 114.14it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 116.43it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 115.42it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 115.68it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 114.83it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 115.25it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 114.62it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 116.03it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 115.48it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.57it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 117.08it/s, v_num=odal, val_loss=2.970, train_loss=0.429]
Epoch 36: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 100.00it/s, v_num=odal, val_loss=2.940, train_loss=0.429]
Epoch 36: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 99.03it/s, v_num=odal, val_loss=2.940, train_loss=0.536]
Epoch 36: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 97.53it/s, v_num=odal, val_loss=2.940, train_loss=0.536]
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
     Validate metric           DataLoader 0
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
         MAE_val            1.3372687101364136
         R2_val             0.5574553608894348
        val_loss            2.9392478466033936
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€

5. Plotting the results of the first model ๐Ÿ“Š๏ƒ

Letโ€™s unveil the results of our first modelโ€™s hard work. Weโ€™re using the RealsVsPreds class to plot the results of the first model. This class takes the trained model as an input and returns a plot of the real values vs the predicted values from the final validation data (when using from_final_val_data). If you want to plot the results from the test data, you can use from_new_data instead. See the example notebook on plotting with new data for more detail.

reals_preds_model_1 = RealsVsPreds.from_final_val_data(model_1_list)

plt.show()
Evaluation: Validation Data, Tabular1 uni-modal - Validation R2: 0.557

6. Training the second fusion model ๐Ÿ๏ƒ

Itโ€™s time for our second fusion model to shine! Here we train the second fusion model: ConcatTabularFeatureMaps. Weโ€™re using the same steps as before, but this time weโ€™re using the second model in the fusion_models list.

Choose the model

fusion_model = fusion_models[1]

print("Method name:", fusion_model.method_name)
print("Modality type:", fusion_model.modality_type)
print("Fusion type:", fusion_model.fusion_type)

# Create the data module
dm = prepare_fusion_data(prediction_task=prediction_task,
                         fusion_model=fusion_model,
                         data_paths=data_paths,
                         output_paths=output_paths,
                         batch_size=batch_size,
                         test_size=test_size)

# train and test
model_2_list = train_and_save_models(
    data_module=dm,
    fusion_model=fusion_model,
    enable_checkpointing=False,  # False for the example notebooks
    show_loss_plot=True,
)

# Add trained model to dictionary
all_trained_models[fusion_model.__name__] = model_2_list
Loss Curves for ConcatTabularFeatureMaps
Method name: Concatenating tabular feature maps
Modality type: tabular_tabular
Fusion type: operation

Training: |          | 0/? [00:00<?, ?it/s]
Training:   0%|          | 0/8 [00:00<?, ?it/s]
Epoch 0:   0%|          | 0/8 [00:00<?, ?it/s]
Epoch 0:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 61.55it/s]
Epoch 0:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 60.27it/s, v_num=Maps]
Epoch 0:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 68.64it/s, v_num=Maps]
Epoch 0:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 67.90it/s, v_num=Maps]
Epoch 0:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 72.46it/s, v_num=Maps]
Epoch 0:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 71.91it/s, v_num=Maps]
Epoch 0:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 74.67it/s, v_num=Maps]
Epoch 0:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 74.23it/s, v_num=Maps]
Epoch 0:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 76.24it/s, v_num=Maps]
Epoch 0:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 75.88it/s, v_num=Maps]
Epoch 0:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 77.46it/s, v_num=Maps]
Epoch 0:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 77.17it/s, v_num=Maps]
Epoch 0:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 77.86it/s, v_num=Maps]
Epoch 0:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 77.60it/s, v_num=Maps]
Epoch 0: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 79.40it/s, v_num=Maps]
Epoch 0: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 79.17it/s, v_num=Maps]
Epoch 0: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 68.20it/s, v_num=Maps, val_loss=8.070]
Epoch 0: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 67.71it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 0:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 82.86it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 80.90it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 82.60it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 81.63it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.46it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 82.78it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.05it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 83.54it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.45it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.03it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.34it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 83.99it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 83.67it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 83.37it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 84.87it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 84.60it/s, v_num=Maps, val_loss=8.070, train_loss=12.60]
Epoch 1: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.71it/s, v_num=Maps, val_loss=6.060, train_loss=12.60]
Epoch 1: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.15it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 1:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 84.33it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 82.16it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.69it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.60it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.85it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.14it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 83.99it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 83.45it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.43it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.01it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.36it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 83.99it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.31it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.00it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.05it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 84.77it/s, v_num=Maps, val_loss=6.060, train_loss=7.870]
Epoch 2: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.80it/s, v_num=Maps, val_loss=9.620, train_loss=7.870]
Epoch 2: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.25it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 2:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 78.24it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 76.52it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 81.93it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 80.98it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.51it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 82.86it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.43it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 83.93it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.60it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.17it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 83.79it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 83.45it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.24it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 83.95it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.55it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.27it/s, v_num=Maps, val_loss=9.620, train_loss=6.220]
Epoch 3: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.51it/s, v_num=Maps, val_loss=5.120, train_loss=6.220]
Epoch 3: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.96it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 3:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 87.30it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 85.20it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 87.00it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 85.92it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.45it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.72it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.24it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.70it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.29it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.86it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.39it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.03it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.50it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.19it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.58it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.31it/s, v_num=Maps, val_loss=5.120, train_loss=6.910]
Epoch 4: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.76it/s, v_num=Maps, val_loss=4.450, train_loss=6.910]
Epoch 4: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.19it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 4:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 73.61it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 71.60it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 75.17it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 74.15it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 75.98it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 75.29it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 75.55it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 74.96it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 74.55it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 74.15it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 75.71it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 75.40it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 76.81it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 76.54it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 77.34it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 77.05it/s, v_num=Maps, val_loss=4.450, train_loss=4.610]
Epoch 5: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 67.00it/s, v_num=Maps, val_loss=3.950, train_loss=4.610]
Epoch 5: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 66.47it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 5:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 75.94it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 73.89it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 76.21it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 75.28it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 78.11it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 77.50it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 79.07it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 78.60it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 80.18it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 79.80it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 80.55it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 80.09it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 80.57it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 80.30it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 82.13it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 81.89it/s, v_num=Maps, val_loss=3.950, train_loss=3.850]
Epoch 6: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 71.84it/s, v_num=Maps, val_loss=3.270, train_loss=3.850]
Epoch 6: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 71.31it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 6:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 84.48it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 82.23it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.88it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.85it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.55it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.86it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.82it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.30it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.14it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.72it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.46it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.11it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.49it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.20it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.21it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.94it/s, v_num=Maps, val_loss=3.270, train_loss=3.620]
Epoch 7: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.94it/s, v_num=Maps, val_loss=3.180, train_loss=3.620]
Epoch 7: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.36it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 7:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 81.34it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 79.46it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.89it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 82.90it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.63it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.03it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.45it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.89it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.73it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.28it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.60it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.20it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.49it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.14it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.41it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.13it/s, v_num=Maps, val_loss=3.180, train_loss=2.790]
Epoch 8: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.11it/s, v_num=Maps, val_loss=3.580, train_loss=2.790]
Epoch 8: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.54it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 8:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.49it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 81.53it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.63it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.62it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.79it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.09it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.11it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 83.59it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 83.05it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 82.45it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 83.26it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 82.92it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 83.53it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 83.19it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 84.21it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 83.92it/s, v_num=Maps, val_loss=3.580, train_loss=2.540]
Epoch 9: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 72.55it/s, v_num=Maps, val_loss=2.690, train_loss=2.540]
Epoch 9: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 72.01it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 9:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.86it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 81.90it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.97it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.95it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.68it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.99it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.62it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.94it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.22it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.80it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.85it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.51it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.04it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.74it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.26it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.97it/s, v_num=Maps, val_loss=2.690, train_loss=2.310]
Epoch 10: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.98it/s, v_num=Maps, val_loss=2.570, train_loss=2.310]
Epoch 10: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.41it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 10:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 87.19it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 85.06it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 87.56it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 86.48it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.63it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.90it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 80.97it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 80.36it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 80.46it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 80.02it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 80.48it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 80.11it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 80.17it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 79.82it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 80.78it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 80.50it/s, v_num=Maps, val_loss=2.570, train_loss=1.730]
Epoch 11: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 69.59it/s, v_num=Maps, val_loss=2.500, train_loss=1.730]
Epoch 11: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 69.03it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 11:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 81.12it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 79.26it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 81.61it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 80.67it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.08it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 82.43it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 83.80it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 83.29it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 83.71it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 83.30it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.21it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 83.87it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.76it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.45it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.02it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.76it/s, v_num=Maps, val_loss=2.500, train_loss=1.470]
Epoch 12: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.70it/s, v_num=Maps, val_loss=2.420, train_loss=1.470]
Epoch 12: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.13it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 12:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 85.78it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.74it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.32it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.32it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.41it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.72it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.98it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.47it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 86.50it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 86.04it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.90it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.54it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.63it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.32it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.72it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.45it/s, v_num=Maps, val_loss=2.420, train_loss=1.020]
Epoch 13: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 76.16it/s, v_num=Maps, val_loss=2.280, train_loss=1.020]
Epoch 13: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.57it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 13:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 86.31it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 84.16it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 86.06it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.98it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.46it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.76it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.93it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.41it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.42it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.95it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.02it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.63it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.34it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.03it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.07it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 84.80it/s, v_num=Maps, val_loss=2.280, train_loss=0.986]
Epoch 14: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.56it/s, v_num=Maps, val_loss=2.380, train_loss=0.986]
Epoch 14: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.01it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 14:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 82.15it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 80.25it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 82.49it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 81.50it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.31it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 82.57it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.35it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 83.84it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.04it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.62it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.94it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.60it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.78it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.48it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.08it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.81it/s, v_num=Maps, val_loss=2.380, train_loss=0.936]
Epoch 15: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.65it/s, v_num=Maps, val_loss=2.270, train_loss=0.936]
Epoch 15: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.08it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 15:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 85.63it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.52it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 85.36it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.32it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.50it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.82it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.53it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.02it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.11it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.66it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.49it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.14it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.77it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.47it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.99it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.72it/s, v_num=Maps, val_loss=2.270, train_loss=0.701]
Epoch 16: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.14it/s, v_num=Maps, val_loss=2.190, train_loss=0.701]
Epoch 16: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.53it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 16:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 85.63it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.60it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 85.93it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.90it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 86.37it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.67it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 86.65it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 86.06it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 86.29it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.83it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.58it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.22it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.64it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.31it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.37it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.04it/s, v_num=Maps, val_loss=2.190, train_loss=0.748]
Epoch 17: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.39it/s, v_num=Maps, val_loss=2.420, train_loss=0.748]
Epoch 17: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.79it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 17:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 81.22it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 78.94it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 76.94it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 75.67it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 77.09it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 76.42it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 78.11it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 77.63it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 79.45it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 79.06it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 80.56it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 80.24it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 80.29it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 79.97it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 81.21it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 80.92it/s, v_num=Maps, val_loss=2.420, train_loss=0.869]
Epoch 18: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 70.39it/s, v_num=Maps, val_loss=2.580, train_loss=0.869]
Epoch 18: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 69.84it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 18:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 82.50it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 80.59it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.79it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 82.79it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.79it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.11it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.53it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.02it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.17it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.76it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.39it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.92it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.47it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.17it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.67it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.40it/s, v_num=Maps, val_loss=2.580, train_loss=0.760]
Epoch 19: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.19it/s, v_num=Maps, val_loss=2.630, train_loss=0.760]
Epoch 19: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.62it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 19:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 82.47it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 80.45it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.94it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.93it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.60it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.85it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.68it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.13it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.89it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.45it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.89it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.53it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.03it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.71it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.75it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.47it/s, v_num=Maps, val_loss=2.630, train_loss=0.770]
Epoch 20: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.42it/s, v_num=Maps, val_loss=2.500, train_loss=0.770]
Epoch 20: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.85it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 20:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.16it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 81.17it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.07it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.01it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 82.47it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 81.75it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 82.96it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 82.43it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 83.33it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 82.91it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 83.70it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 83.36it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.17it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 83.85it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.49it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.22it/s, v_num=Maps, val_loss=2.500, train_loss=0.669]
Epoch 21: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.82it/s, v_num=Maps, val_loss=2.840, train_loss=0.669]
Epoch 21: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.27it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 21:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 85.52it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.44it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 85.76it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.70it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.93it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.22it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 86.32it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.80it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 86.00it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.58it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.37it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.01it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.42it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.10it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.49it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.22it/s, v_num=Maps, val_loss=2.840, train_loss=0.781]
Epoch 22: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.87it/s, v_num=Maps, val_loss=2.790, train_loss=0.781]
Epoch 22: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.29it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 22:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 86.98it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 84.88it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 85.24it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.22it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.23it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.62it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.94it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.41it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 86.35it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.93it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.81it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.45it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.60it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.27it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.63it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.35it/s, v_num=Maps, val_loss=2.790, train_loss=0.869]
Epoch 23: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.71it/s, v_num=Maps, val_loss=2.540, train_loss=0.869]
Epoch 23: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.11it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 23:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 86.14it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 84.08it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 86.50it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 85.45it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 86.84it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 86.11it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 86.01it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.47it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 86.18it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.73it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.24it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.86it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.31it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.00it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.98it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.69it/s, v_num=Maps, val_loss=2.540, train_loss=0.754]
Epoch 24: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.90it/s, v_num=Maps, val_loss=2.430, train_loss=0.754]
Epoch 24: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.35it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 24:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.04it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 81.11it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.81it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.79it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.66it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.96it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 86.14it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.56it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 86.42it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.99it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.03it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.65it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.20it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.90it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.41it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.13it/s, v_num=Maps, val_loss=2.430, train_loss=0.511]
Epoch 25: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.88it/s, v_num=Maps, val_loss=2.620, train_loss=0.511]
Epoch 25: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.31it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 25:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.89it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 81.90it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 85.09it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 84.06it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.19it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.59it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.39it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.85it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.80it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.37it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.09it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.72it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.17it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.80it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.72it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.42it/s, v_num=Maps, val_loss=2.620, train_loss=0.536]
Epoch 26: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.67it/s, v_num=Maps, val_loss=2.760, train_loss=0.536]
Epoch 26: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 73.08it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 26:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 78.00it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 75.78it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 75.15it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 74.10it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 75.35it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 74.69it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 77.00it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 76.49it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 77.36it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 76.92it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 75.99it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 75.62it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 75.78it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 75.48it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 77.38it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 77.13it/s, v_num=Maps, val_loss=2.760, train_loss=0.515]
Epoch 27: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 67.88it/s, v_num=Maps, val_loss=2.620, train_loss=0.515]
Epoch 27: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 67.39it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 27:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 84.07it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 82.07it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.20it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 82.22it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.55it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 83.88it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.38it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.86it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.64it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.22it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.07it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.72it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.88it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.57it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.07it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.80it/s, v_num=Maps, val_loss=2.620, train_loss=0.464]
Epoch 28: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.68it/s, v_num=Maps, val_loss=2.920, train_loss=0.464]
Epoch 28: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.11it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 28:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 85.86it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 83.81it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 86.48it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 85.37it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 86.89it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 86.18it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.63it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.09it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.34it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 84.92it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.43it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 85.07it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.64it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 85.34it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.64it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 86.36it/s, v_num=Maps, val_loss=2.920, train_loss=0.502]
Epoch 29: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.16it/s, v_num=Maps, val_loss=2.410, train_loss=0.502]
Epoch 29: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.57it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 29:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 81.06it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 79.23it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 83.32it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 82.33it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.77it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.09it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.05it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 84.50it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.77it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.34it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.45it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 84.04it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.76it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 84.44it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.98it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 85.71it/s, v_num=Maps, val_loss=2.410, train_loss=0.540]
Epoch 30: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.78it/s, v_num=Maps, val_loss=2.480, train_loss=0.540]
Epoch 30: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.19it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 30:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:   0%|          | 0/8 [00:00<?, ?it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 86.79it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  12%|โ–ˆโ–Ž        | 1/8 [00:00<00:00, 84.63it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 86.87it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  25%|โ–ˆโ–ˆโ–Œ       | 2/8 [00:00<00:00, 85.79it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 85.46it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  38%|โ–ˆโ–ˆโ–ˆโ–Š      | 3/8 [00:00<00:00, 84.76it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.93it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ     | 4/8 [00:00<00:00, 85.40it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 86.19it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž   | 5/8 [00:00<00:00, 85.71it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.47it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ  | 6/8 [00:00<00:00, 86.10it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.73it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31:  88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 7/8 [00:00<00:00, 86.41it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.83it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 87.56it/s, v_num=Maps, val_loss=2.480, train_loss=0.666]
Epoch 31: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.72it/s, v_num=Maps, val_loss=2.690, train_loss=0.666]
Epoch 31: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 75.11it/s, v_num=Maps, val_loss=2.690, train_loss=0.532]
Epoch 31: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 8/8 [00:00<00:00, 74.27it/s, v_num=Maps, val_loss=2.690, train_loss=0.532]
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
     Validate metric           DataLoader 0
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
         MAE_val             1.178006887435913
         R2_val             0.6820151209831238
        val_loss            2.6859920024871826
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€

7. Plotting the results of the second model ๐Ÿ“Š๏ƒ

reals_preds_model_2 = RealsVsPreds.from_final_val_data(model_2_list)

plt.show()
Evaluation: Validation Data, Concatenating tabular feature maps - Validation R2: 0.682

8. Comparing the results of the two models ๐Ÿ“ˆ๏ƒ

Let the ultimate showdown begin! Weโ€™re comparing the results of our two models. Weโ€™re using the ModelComparison class to compare the results of the two models. This class takes the trained models as an input and returns a plot of the results of the two models and a Pandas DataFrame of the metrics of the two models.

comparison_plot, metrics_dataframe = ModelComparison.from_final_val_data(
    all_trained_models
)

plt.show()
Model Performance Comparison, R2, MAE

9. Saving the metrics of the two models ๐Ÿ’พ๏ƒ

Time to archive our modelsโ€™ achievements. Weโ€™re using the ModelComparison class to save the metrics of the two models.

metrics_dataframe
R2 MAE
Method
Tabular1 uni-modal 0.557455 1.337269
Concatenating tabular feature maps 0.682015 1.178007


Total running time of the script: (0 minutes 8.075 seconds)

Gallery generated by Sphinx-Gallery