Dilated RNN

The Dilated Recurrent Neural Network (DilatedRNN) addresses common challenges of modeling long sequences like vanishing gradients, computational efficiency, and improved model flexibility to model complex relationships while maintaining its parsimony. The DilatedRNN builds a deep stack of RNN layers using skip conditions on the temporal and the network’s depth dimensions. The temporal dilated recurrent skip connections offer the capability to focus on multi-resolution inputs.

References
-Shiyu Chang, et al. “Dilated Recurrent Neural Networks”.
-Yao Qin, et al. “A Dual-Stage Attention-Based recurrent neural network for time series prediction”.
-Kashif Rasul, et al. “Zalando Research: PyTorch Dilated Recurrent Neural Networks”.

Figure 1. Three layer DilatedRNN with dilation 1, 2, 4.

---

source

DilatedRNN

 DilatedRNN (input_size:int, h:int, cell_type:str='LSTM',
             state_hsize:int=200, step_size:int=1,
             dilations:List[List[int]]=[[1, 2], [4, 8]],
             add_nl_layer:bool=False, learning_rate:float=0.001,
             normalize:bool=True, loss=<neuralforecast.losses.pytorch.MAE
             object at 0x7fd0f3885810>, random_seed:int=1)

Hooks to be used in LightningModule.

import matplotlib.pyplot as plt
import pandas as pd
from neuralforecast.utils import AirPassengersDF as Y_df
from neuralforecast.tsdataset import TimeSeriesDataset, TimeSeriesLoader

# Add second series
Y_df_2 = Y_df.tail(100).copy()
Y_df_2['unique_id'] = 2.0
Y_df_2['y'] = 0.5*Y_df_2['y']
Y_df = Y_df.append(Y_df_2).reset_index(drop=True)

# Train/Test split
Y_train_df = Y_df[Y_df.ds<='1959-12-31'] # 132 train
Y_test_df = Y_df[Y_df.ds>'1959-12-31']   # 12 test

dataset, *_ = TimeSeriesDataset.from_df(df = Y_train_df)
model = DilatedRNN(24, 12, learning_rate=1e-3)
trainer = pl.Trainer(max_epochs=200)
model.fit(dataset=dataset, trainer=trainer)
y_hat = model.predict(dataset=dataset, trainer=trainer)

Y_test_df['DilatedRNN'] = y_hat

Training: 0it [00:00, ?it/s]Training:   0%|          | 0/1 [00:00<?, ?it/s]Epoch 0:   0%|          | 0/1 [00:00<?, ?it/s] Epoch 0: 100%|##########| 1/1 [00:00<00:00, 12.18it/s]Epoch 0: 100%|##########| 1/1 [00:00<00:00, 12.07it/s, loss=0.75, v_num=5, train_loss_step=0.750]Epoch 0: 100%|##########| 1/1 [00:00<00:00, 11.95it/s, loss=0.75, v_num=5, train_loss_step=0.750, train_loss_epoch=0.750]Epoch 0:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.75, v_num=5, train_loss_step=0.750, train_loss_epoch=0.750]        Epoch 1:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.75, v_num=5, train_loss_step=0.750, train_loss_epoch=0.750]Epoch 1: 100%|##########| 1/1 [00:00<00:00, 16.00it/s, loss=0.75, v_num=5, train_loss_step=0.750, train_loss_epoch=0.750]Epoch 1: 100%|##########| 1/1 [00:00<00:00, 15.89it/s, loss=0.738, v_num=5, train_loss_step=0.725, train_loss_epoch=0.750]Epoch 1: 100%|##########| 1/1 [00:00<00:00, 15.73it/s, loss=0.738, v_num=5, train_loss_step=0.725, train_loss_epoch=0.725]Epoch 1:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.738, v_num=5, train_loss_step=0.725, train_loss_epoch=0.725]        Epoch 2:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.738, v_num=5, train_loss_step=0.725, train_loss_epoch=0.725]Epoch 2: 100%|##########| 1/1 [00:00<00:00,  4.09it/s, loss=0.738, v_num=5, train_loss_step=0.725, train_loss_epoch=0.725]Epoch 2: 100%|##########| 1/1 [00:00<00:00,  4.09it/s, loss=0.725, v_num=5, train_loss_step=0.698, train_loss_epoch=0.725]Epoch 2: 100%|##########| 1/1 [00:00<00:00,  4.08it/s, loss=0.725, v_num=5, train_loss_step=0.698, train_loss_epoch=0.698]Epoch 2:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.725, v_num=5, train_loss_step=0.698, train_loss_epoch=0.698]        Epoch 3:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.725, v_num=5, train_loss_step=0.698, train_loss_epoch=0.698]Epoch 3: 100%|##########| 1/1 [00:00<00:00, 14.65it/s, loss=0.725, v_num=5, train_loss_step=0.698, train_loss_epoch=0.698]Epoch 3: 100%|##########| 1/1 [00:00<00:00, 14.50it/s, loss=0.709, v_num=5, train_loss_step=0.663, train_loss_epoch=0.698]Epoch 3: 100%|##########| 1/1 [00:00<00:00, 14.37it/s, loss=0.709, v_num=5, train_loss_step=0.663, train_loss_epoch=0.663]Epoch 3:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.709, v_num=5, train_loss_step=0.663, train_loss_epoch=0.663]        Epoch 4:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.709, v_num=5, train_loss_step=0.663, train_loss_epoch=0.663]Epoch 4: 100%|##########| 1/1 [00:00<00:00, 16.06it/s, loss=0.709, v_num=5, train_loss_step=0.663, train_loss_epoch=0.663]Epoch 4: 100%|##########| 1/1 [00:00<00:00, 15.93it/s, loss=0.69, v_num=5, train_loss_step=0.613, train_loss_epoch=0.663] Epoch 4: 100%|##########| 1/1 [00:00<00:00, 15.75it/s, loss=0.69, v_num=5, train_loss_step=0.613, train_loss_epoch=0.613]Epoch 4:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.69, v_num=5, train_loss_step=0.613, train_loss_epoch=0.613]        Epoch 5:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.69, v_num=5, train_loss_step=0.613, train_loss_epoch=0.613]Epoch 5: 100%|##########| 1/1 [00:00<00:00, 14.83it/s, loss=0.69, v_num=5, train_loss_step=0.613, train_loss_epoch=0.613]Epoch 5: 100%|##########| 1/1 [00:00<00:00, 14.73it/s, loss=0.665, v_num=5, train_loss_step=0.539, train_loss_epoch=0.613]Epoch 5: 100%|##########| 1/1 [00:00<00:00, 14.58it/s, loss=0.665, v_num=5, train_loss_step=0.539, train_loss_epoch=0.539]Epoch 5:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.665, v_num=5, train_loss_step=0.539, train_loss_epoch=0.539]        Epoch 6:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.665, v_num=5, train_loss_step=0.539, train_loss_epoch=0.539]Epoch 6: 100%|##########| 1/1 [00:00<00:00, 13.25it/s, loss=0.665, v_num=5, train_loss_step=0.539, train_loss_epoch=0.539]Epoch 6: 100%|##########| 1/1 [00:00<00:00, 13.17it/s, loss=0.635, v_num=5, train_loss_step=0.455, train_loss_epoch=0.539]Epoch 6: 100%|##########| 1/1 [00:00<00:00, 13.05it/s, loss=0.635, v_num=5, train_loss_step=0.455, train_loss_epoch=0.455]Epoch 6:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.635, v_num=5, train_loss_step=0.455, train_loss_epoch=0.455]        Epoch 7:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.635, v_num=5, train_loss_step=0.455, train_loss_epoch=0.455]Epoch 7: 100%|##########| 1/1 [00:00<00:00, 14.27it/s, loss=0.635, v_num=5, train_loss_step=0.455, train_loss_epoch=0.455]Epoch 7: 100%|##########| 1/1 [00:00<00:00, 14.18it/s, loss=0.614, v_num=5, train_loss_step=0.468, train_loss_epoch=0.455]Epoch 7: 100%|##########| 1/1 [00:00<00:00, 14.05it/s, loss=0.614, v_num=5, train_loss_step=0.468, train_loss_epoch=0.468]Epoch 7:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.614, v_num=5, train_loss_step=0.468, train_loss_epoch=0.468]        Epoch 8:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.614, v_num=5, train_loss_step=0.468, train_loss_epoch=0.468]Epoch 8: 100%|##########| 1/1 [00:00<00:00, 16.39it/s, loss=0.614, v_num=5, train_loss_step=0.468, train_loss_epoch=0.468]Epoch 8: 100%|##########| 1/1 [00:00<00:00, 16.27it/s, loss=0.6, v_num=5, train_loss_step=0.489, train_loss_epoch=0.468]  Epoch 8: 100%|##########| 1/1 [00:00<00:00, 16.13it/s, loss=0.6, v_num=5, train_loss_step=0.489, train_loss_epoch=0.489]Epoch 8:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.6, v_num=5, train_loss_step=0.489, train_loss_epoch=0.489]        Epoch 9:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.6, v_num=5, train_loss_step=0.489, train_loss_epoch=0.489]Epoch 9: 100%|##########| 1/1 [00:00<00:00, 17.53it/s, loss=0.6, v_num=5, train_loss_step=0.489, train_loss_epoch=0.489]Epoch 9: 100%|##########| 1/1 [00:00<00:00, 17.41it/s, loss=0.586, v_num=5, train_loss_step=0.464, train_loss_epoch=0.489]Epoch 9: 100%|##########| 1/1 [00:00<00:00, 17.25it/s, loss=0.586, v_num=5, train_loss_step=0.464, train_loss_epoch=0.464]Epoch 9:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.586, v_num=5, train_loss_step=0.464, train_loss_epoch=0.464]        Epoch 10:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.586, v_num=5, train_loss_step=0.464, train_loss_epoch=0.464]Epoch 10: 100%|##########| 1/1 [00:00<00:00, 14.38it/s, loss=0.586, v_num=5, train_loss_step=0.464, train_loss_epoch=0.464]Epoch 10: 100%|##########| 1/1 [00:00<00:00, 14.29it/s, loss=0.572, v_num=5, train_loss_step=0.432, train_loss_epoch=0.464]Epoch 10: 100%|##########| 1/1 [00:00<00:00, 14.16it/s, loss=0.572, v_num=5, train_loss_step=0.432, train_loss_epoch=0.432]Epoch 10:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.572, v_num=5, train_loss_step=0.432, train_loss_epoch=0.432]        Epoch 11:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.572, v_num=5, train_loss_step=0.432, train_loss_epoch=0.432]Epoch 11: 100%|##########| 1/1 [00:00<00:00, 17.69it/s, loss=0.572, v_num=5, train_loss_step=0.432, train_loss_epoch=0.432]Epoch 11: 100%|##########| 1/1 [00:00<00:00, 17.56it/s, loss=0.559, v_num=5, train_loss_step=0.416, train_loss_epoch=0.432]Epoch 11: 100%|##########| 1/1 [00:00<00:00, 17.39it/s, loss=0.559, v_num=5, train_loss_step=0.416, train_loss_epoch=0.416]Epoch 11:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.559, v_num=5, train_loss_step=0.416, train_loss_epoch=0.416]        Epoch 12:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.559, v_num=5, train_loss_step=0.416, train_loss_epoch=0.416]Epoch 12: 100%|##########| 1/1 [00:00<00:00, 17.79it/s, loss=0.559, v_num=5, train_loss_step=0.416, train_loss_epoch=0.416]Epoch 12: 100%|##########| 1/1 [00:00<00:00, 17.66it/s, loss=0.549, v_num=5, train_loss_step=0.422, train_loss_epoch=0.416]Epoch 12: 100%|##########| 1/1 [00:00<00:00, 17.46it/s, loss=0.549, v_num=5, train_loss_step=0.422, train_loss_epoch=0.422]Epoch 12:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.549, v_num=5, train_loss_step=0.422, train_loss_epoch=0.422]        Epoch 13:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.549, v_num=5, train_loss_step=0.422, train_loss_epoch=0.422]Epoch 13: 100%|##########| 1/1 [00:00<00:00, 16.36it/s, loss=0.549, v_num=5, train_loss_step=0.422, train_loss_epoch=0.422]Epoch 13: 100%|##########| 1/1 [00:00<00:00, 16.24it/s, loss=0.54, v_num=5, train_loss_step=0.432, train_loss_epoch=0.422] Epoch 13: 100%|##########| 1/1 [00:00<00:00, 16.04it/s, loss=0.54, v_num=5, train_loss_step=0.432, train_loss_epoch=0.432]Epoch 13:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.54, v_num=5, train_loss_step=0.432, train_loss_epoch=0.432]        Epoch 14:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.54, v_num=5, train_loss_step=0.432, train_loss_epoch=0.432]Epoch 14: 100%|##########| 1/1 [00:00<00:00, 14.78it/s, loss=0.54, v_num=5, train_loss_step=0.432, train_loss_epoch=0.432]Epoch 14: 100%|##########| 1/1 [00:00<00:00, 14.68it/s, loss=0.533, v_num=5, train_loss_step=0.435, train_loss_epoch=0.432]Epoch 14: 100%|##########| 1/1 [00:00<00:00, 14.55it/s, loss=0.533, v_num=5, train_loss_step=0.435, train_loss_epoch=0.435]Epoch 14:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.533, v_num=5, train_loss_step=0.435, train_loss_epoch=0.435]        Epoch 15:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.533, v_num=5, train_loss_step=0.435, train_loss_epoch=0.435]Epoch 15: 100%|##########| 1/1 [00:00<00:00, 15.51it/s, loss=0.533, v_num=5, train_loss_step=0.435, train_loss_epoch=0.435]Epoch 15: 100%|##########| 1/1 [00:00<00:00, 15.40it/s, loss=0.527, v_num=5, train_loss_step=0.430, train_loss_epoch=0.435]Epoch 15: 100%|##########| 1/1 [00:00<00:00, 15.24it/s, loss=0.527, v_num=5, train_loss_step=0.430, train_loss_epoch=0.430]Epoch 15:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.527, v_num=5, train_loss_step=0.430, train_loss_epoch=0.430]        Epoch 16:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.527, v_num=5, train_loss_step=0.430, train_loss_epoch=0.430]Epoch 16: 100%|##########| 1/1 [00:00<00:00, 15.87it/s, loss=0.527, v_num=5, train_loss_step=0.430, train_loss_epoch=0.430]Epoch 16: 100%|##########| 1/1 [00:00<00:00, 15.76it/s, loss=0.521, v_num=5, train_loss_step=0.422, train_loss_epoch=0.430]Epoch 16: 100%|##########| 1/1 [00:00<00:00, 15.61it/s, loss=0.521, v_num=5, train_loss_step=0.422, train_loss_epoch=0.422]Epoch 16:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.521, v_num=5, train_loss_step=0.422, train_loss_epoch=0.422]        Epoch 17:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.521, v_num=5, train_loss_step=0.422, train_loss_epoch=0.422]Epoch 17: 100%|##########| 1/1 [00:00<00:00, 14.67it/s, loss=0.521, v_num=5, train_loss_step=0.422, train_loss_epoch=0.422]Epoch 17: 100%|##########| 1/1 [00:00<00:00, 14.57it/s, loss=0.515, v_num=5, train_loss_step=0.415, train_loss_epoch=0.422]Epoch 17: 100%|##########| 1/1 [00:00<00:00, 14.43it/s, loss=0.515, v_num=5, train_loss_step=0.415, train_loss_epoch=0.415]Epoch 17:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.515, v_num=5, train_loss_step=0.415, train_loss_epoch=0.415]        Epoch 18:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.515, v_num=5, train_loss_step=0.415, train_loss_epoch=0.415]Epoch 18: 100%|##########| 1/1 [00:00<00:00, 15.84it/s, loss=0.515, v_num=5, train_loss_step=0.415, train_loss_epoch=0.415]Epoch 18: 100%|##########| 1/1 [00:00<00:00, 15.74it/s, loss=0.509, v_num=5, train_loss_step=0.411, train_loss_epoch=0.415]Epoch 18: 100%|##########| 1/1 [00:00<00:00, 15.61it/s, loss=0.509, v_num=5, train_loss_step=0.411, train_loss_epoch=0.411]Epoch 18:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.509, v_num=5, train_loss_step=0.411, train_loss_epoch=0.411]        Epoch 19:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.509, v_num=5, train_loss_step=0.411, train_loss_epoch=0.411]Epoch 19: 100%|##########| 1/1 [00:00<00:00, 16.51it/s, loss=0.509, v_num=5, train_loss_step=0.411, train_loss_epoch=0.411]Epoch 19: 100%|##########| 1/1 [00:00<00:00, 16.39it/s, loss=0.504, v_num=5, train_loss_step=0.410, train_loss_epoch=0.411]Epoch 19: 100%|##########| 1/1 [00:00<00:00, 16.23it/s, loss=0.504, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 19:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.504, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]        Epoch 20:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.504, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 20: 100%|##########| 1/1 [00:00<00:00, 16.23it/s, loss=0.504, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 20: 100%|##########| 1/1 [00:00<00:00, 16.12it/s, loss=0.487, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 20: 100%|##########| 1/1 [00:00<00:00, 15.95it/s, loss=0.487, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 20:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.487, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]        Epoch 21:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.487, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 21: 100%|##########| 1/1 [00:00<00:00, 14.63it/s, loss=0.487, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 21: 100%|##########| 1/1 [00:00<00:00, 14.53it/s, loss=0.472, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 21: 100%|##########| 1/1 [00:00<00:00, 14.40it/s, loss=0.472, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 21:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.472, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]        Epoch 22:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.472, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 22: 100%|##########| 1/1 [00:00<00:00, 15.73it/s, loss=0.472, v_num=5, train_loss_step=0.410, train_loss_epoch=0.410]Epoch 22: 100%|##########| 1/1 [00:00<00:00, 15.62it/s, loss=0.457, v_num=5, train_loss_step=0.408, train_loss_epoch=0.410]Epoch 22: 100%|##########| 1/1 [00:00<00:00, 15.46it/s, loss=0.457, v_num=5, train_loss_step=0.408, train_loss_epoch=0.408]Epoch 22:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.457, v_num=5, train_loss_step=0.408, train_loss_epoch=0.408]        Epoch 23:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.457, v_num=5, train_loss_step=0.408, train_loss_epoch=0.408]Epoch 23: 100%|##########| 1/1 [00:00<00:00, 17.42it/s, loss=0.457, v_num=5, train_loss_step=0.408, train_loss_epoch=0.408]Epoch 23: 100%|##########| 1/1 [00:00<00:00, 17.29it/s, loss=0.444, v_num=5, train_loss_step=0.404, train_loss_epoch=0.408]Epoch 23: 100%|##########| 1/1 [00:00<00:00, 17.12it/s, loss=0.444, v_num=5, train_loss_step=0.404, train_loss_epoch=0.404]Epoch 23:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.444, v_num=5, train_loss_step=0.404, train_loss_epoch=0.404]        Epoch 24:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.444, v_num=5, train_loss_step=0.404, train_loss_epoch=0.404]Epoch 24: 100%|##########| 1/1 [00:00<00:00, 17.70it/s, loss=0.444, v_num=5, train_loss_step=0.404, train_loss_epoch=0.404]Epoch 24: 100%|##########| 1/1 [00:00<00:00, 17.58it/s, loss=0.434, v_num=5, train_loss_step=0.401, train_loss_epoch=0.404]Epoch 24: 100%|##########| 1/1 [00:00<00:00, 17.40it/s, loss=0.434, v_num=5, train_loss_step=0.401, train_loss_epoch=0.401]Epoch 24:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.434, v_num=5, train_loss_step=0.401, train_loss_epoch=0.401]        Epoch 25:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.434, v_num=5, train_loss_step=0.401, train_loss_epoch=0.401]Epoch 25: 100%|##########| 1/1 [00:00<00:00, 16.92it/s, loss=0.434, v_num=5, train_loss_step=0.401, train_loss_epoch=0.401]Epoch 25: 100%|##########| 1/1 [00:00<00:00, 16.79it/s, loss=0.426, v_num=5, train_loss_step=0.398, train_loss_epoch=0.401]Epoch 25: 100%|##########| 1/1 [00:00<00:00, 16.61it/s, loss=0.426, v_num=5, train_loss_step=0.398, train_loss_epoch=0.398]Epoch 25:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.426, v_num=5, train_loss_step=0.398, train_loss_epoch=0.398]        Epoch 26:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.426, v_num=5, train_loss_step=0.398, train_loss_epoch=0.398]Epoch 26: 100%|##########| 1/1 [00:00<00:00, 16.66it/s, loss=0.426, v_num=5, train_loss_step=0.398, train_loss_epoch=0.398]Epoch 26: 100%|##########| 1/1 [00:00<00:00, 16.54it/s, loss=0.423, v_num=5, train_loss_step=0.395, train_loss_epoch=0.398]Epoch 26: 100%|##########| 1/1 [00:00<00:00, 16.39it/s, loss=0.423, v_num=5, train_loss_step=0.395, train_loss_epoch=0.395]Epoch 26:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.423, v_num=5, train_loss_step=0.395, train_loss_epoch=0.395]        Epoch 27:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.423, v_num=5, train_loss_step=0.395, train_loss_epoch=0.395]Epoch 27: 100%|##########| 1/1 [00:00<00:00, 14.51it/s, loss=0.423, v_num=5, train_loss_step=0.395, train_loss_epoch=0.395]Epoch 27: 100%|##########| 1/1 [00:00<00:00, 14.42it/s, loss=0.42, v_num=5, train_loss_step=0.393, train_loss_epoch=0.395] Epoch 27: 100%|##########| 1/1 [00:00<00:00, 14.28it/s, loss=0.42, v_num=5, train_loss_step=0.393, train_loss_epoch=0.393]Epoch 27:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.42, v_num=5, train_loss_step=0.393, train_loss_epoch=0.393]        Epoch 28:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.42, v_num=5, train_loss_step=0.393, train_loss_epoch=0.393]Epoch 28: 100%|##########| 1/1 [00:00<00:00, 15.94it/s, loss=0.42, v_num=5, train_loss_step=0.393, train_loss_epoch=0.393]Epoch 28: 100%|##########| 1/1 [00:00<00:00, 15.75it/s, loss=0.415, v_num=5, train_loss_step=0.389, train_loss_epoch=0.393]Epoch 28: 100%|##########| 1/1 [00:00<00:00, 15.59it/s, loss=0.415, v_num=5, train_loss_step=0.389, train_loss_epoch=0.389]Epoch 28:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.415, v_num=5, train_loss_step=0.389, train_loss_epoch=0.389]        Epoch 29:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.415, v_num=5, train_loss_step=0.389, train_loss_epoch=0.389]Epoch 29: 100%|##########| 1/1 [00:00<00:00, 15.76it/s, loss=0.415, v_num=5, train_loss_step=0.389, train_loss_epoch=0.389]Epoch 29: 100%|##########| 1/1 [00:00<00:00, 15.65it/s, loss=0.411, v_num=5, train_loss_step=0.385, train_loss_epoch=0.389]Epoch 29: 100%|##########| 1/1 [00:00<00:00, 15.50it/s, loss=0.411, v_num=5, train_loss_step=0.385, train_loss_epoch=0.385]Epoch 29:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.411, v_num=5, train_loss_step=0.385, train_loss_epoch=0.385]        Epoch 30:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.411, v_num=5, train_loss_step=0.385, train_loss_epoch=0.385]Epoch 30: 100%|##########| 1/1 [00:00<00:00, 16.38it/s, loss=0.411, v_num=5, train_loss_step=0.385, train_loss_epoch=0.385]Epoch 30: 100%|##########| 1/1 [00:00<00:00, 16.20it/s, loss=0.408, v_num=5, train_loss_step=0.380, train_loss_epoch=0.385]Epoch 30: 100%|##########| 1/1 [00:00<00:00, 16.02it/s, loss=0.408, v_num=5, train_loss_step=0.380, train_loss_epoch=0.380]Epoch 30:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.408, v_num=5, train_loss_step=0.380, train_loss_epoch=0.380]        Epoch 31:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.408, v_num=5, train_loss_step=0.380, train_loss_epoch=0.380]Epoch 31: 100%|##########| 1/1 [00:00<00:00, 15.16it/s, loss=0.408, v_num=5, train_loss_step=0.380, train_loss_epoch=0.380]Epoch 31: 100%|##########| 1/1 [00:00<00:00, 15.06it/s, loss=0.406, v_num=5, train_loss_step=0.373, train_loss_epoch=0.380]Epoch 31: 100%|##########| 1/1 [00:00<00:00, 14.93it/s, loss=0.406, v_num=5, train_loss_step=0.373, train_loss_epoch=0.373]Epoch 31:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.406, v_num=5, train_loss_step=0.373, train_loss_epoch=0.373]        Epoch 32:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.406, v_num=5, train_loss_step=0.373, train_loss_epoch=0.373]Epoch 32: 100%|##########| 1/1 [00:00<00:00, 16.04it/s, loss=0.406, v_num=5, train_loss_step=0.373, train_loss_epoch=0.373]Epoch 32: 100%|##########| 1/1 [00:00<00:00, 15.93it/s, loss=0.403, v_num=5, train_loss_step=0.364, train_loss_epoch=0.373]Epoch 32: 100%|##########| 1/1 [00:00<00:00, 15.78it/s, loss=0.403, v_num=5, train_loss_step=0.364, train_loss_epoch=0.364]Epoch 32:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.403, v_num=5, train_loss_step=0.364, train_loss_epoch=0.364]        Epoch 33:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.403, v_num=5, train_loss_step=0.364, train_loss_epoch=0.364]Epoch 33: 100%|##########| 1/1 [00:00<00:00, 15.75it/s, loss=0.403, v_num=5, train_loss_step=0.364, train_loss_epoch=0.364]Epoch 33: 100%|##########| 1/1 [00:00<00:00, 15.64it/s, loss=0.399, v_num=5, train_loss_step=0.354, train_loss_epoch=0.364]Epoch 33: 100%|##########| 1/1 [00:00<00:00, 15.48it/s, loss=0.399, v_num=5, train_loss_step=0.354, train_loss_epoch=0.354]Epoch 33:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.399, v_num=5, train_loss_step=0.354, train_loss_epoch=0.354]        Epoch 34:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.399, v_num=5, train_loss_step=0.354, train_loss_epoch=0.354]Epoch 34: 100%|##########| 1/1 [00:00<00:00, 17.48it/s, loss=0.399, v_num=5, train_loss_step=0.354, train_loss_epoch=0.354]Epoch 34: 100%|##########| 1/1 [00:00<00:00, 17.36it/s, loss=0.395, v_num=5, train_loss_step=0.343, train_loss_epoch=0.354]Epoch 34: 100%|##########| 1/1 [00:00<00:00, 17.19it/s, loss=0.395, v_num=5, train_loss_step=0.343, train_loss_epoch=0.343]Epoch 34:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.395, v_num=5, train_loss_step=0.343, train_loss_epoch=0.343]        Epoch 35:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.395, v_num=5, train_loss_step=0.343, train_loss_epoch=0.343]Epoch 35: 100%|##########| 1/1 [00:00<00:00, 17.47it/s, loss=0.395, v_num=5, train_loss_step=0.343, train_loss_epoch=0.343]Epoch 35: 100%|##########| 1/1 [00:00<00:00, 17.36it/s, loss=0.39, v_num=5, train_loss_step=0.331, train_loss_epoch=0.343] Epoch 35: 100%|##########| 1/1 [00:00<00:00, 17.18it/s, loss=0.39, v_num=5, train_loss_step=0.331, train_loss_epoch=0.331]Epoch 35:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.39, v_num=5, train_loss_step=0.331, train_loss_epoch=0.331]        Epoch 36:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.39, v_num=5, train_loss_step=0.331, train_loss_epoch=0.331]Epoch 36: 100%|##########| 1/1 [00:00<00:00, 16.67it/s, loss=0.39, v_num=5, train_loss_step=0.331, train_loss_epoch=0.331]Epoch 36: 100%|##########| 1/1 [00:00<00:00, 16.55it/s, loss=0.385, v_num=5, train_loss_step=0.318, train_loss_epoch=0.331]Epoch 36: 100%|##########| 1/1 [00:00<00:00, 16.38it/s, loss=0.385, v_num=5, train_loss_step=0.318, train_loss_epoch=0.318]Epoch 36:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.385, v_num=5, train_loss_step=0.318, train_loss_epoch=0.318]        Epoch 37:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.385, v_num=5, train_loss_step=0.318, train_loss_epoch=0.318]Epoch 37: 100%|##########| 1/1 [00:00<00:00, 17.61it/s, loss=0.385, v_num=5, train_loss_step=0.318, train_loss_epoch=0.318]Epoch 37: 100%|##########| 1/1 [00:00<00:00, 17.49it/s, loss=0.379, v_num=5, train_loss_step=0.303, train_loss_epoch=0.318]Epoch 37: 100%|##########| 1/1 [00:00<00:00, 17.32it/s, loss=0.379, v_num=5, train_loss_step=0.303, train_loss_epoch=0.303]Epoch 37:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.379, v_num=5, train_loss_step=0.303, train_loss_epoch=0.303]        Epoch 38:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.379, v_num=5, train_loss_step=0.303, train_loss_epoch=0.303]Epoch 38: 100%|##########| 1/1 [00:00<00:00, 15.91it/s, loss=0.379, v_num=5, train_loss_step=0.303, train_loss_epoch=0.303]Epoch 38: 100%|##########| 1/1 [00:00<00:00, 15.79it/s, loss=0.373, v_num=5, train_loss_step=0.288, train_loss_epoch=0.303]Epoch 38: 100%|##########| 1/1 [00:00<00:00, 15.63it/s, loss=0.373, v_num=5, train_loss_step=0.288, train_loss_epoch=0.288]Epoch 38:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.373, v_num=5, train_loss_step=0.288, train_loss_epoch=0.288]        Epoch 39:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.373, v_num=5, train_loss_step=0.288, train_loss_epoch=0.288]Epoch 39: 100%|##########| 1/1 [00:00<00:00, 14.45it/s, loss=0.373, v_num=5, train_loss_step=0.288, train_loss_epoch=0.288]Epoch 39: 100%|##########| 1/1 [00:00<00:00, 14.35it/s, loss=0.366, v_num=5, train_loss_step=0.273, train_loss_epoch=0.288]Epoch 39: 100%|##########| 1/1 [00:00<00:00, 14.22it/s, loss=0.366, v_num=5, train_loss_step=0.273, train_loss_epoch=0.273]Epoch 39:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.366, v_num=5, train_loss_step=0.273, train_loss_epoch=0.273]        Epoch 40:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.366, v_num=5, train_loss_step=0.273, train_loss_epoch=0.273]Epoch 40: 100%|##########| 1/1 [00:00<00:00, 15.12it/s, loss=0.366, v_num=5, train_loss_step=0.273, train_loss_epoch=0.273]Epoch 40: 100%|##########| 1/1 [00:00<00:00, 15.02it/s, loss=0.359, v_num=5, train_loss_step=0.261, train_loss_epoch=0.273]Epoch 40: 100%|##########| 1/1 [00:00<00:00, 14.87it/s, loss=0.359, v_num=5, train_loss_step=0.261, train_loss_epoch=0.261]Epoch 40:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.359, v_num=5, train_loss_step=0.261, train_loss_epoch=0.261]        Epoch 41:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.359, v_num=5, train_loss_step=0.261, train_loss_epoch=0.261]Epoch 41: 100%|##########| 1/1 [00:00<00:00, 16.30it/s, loss=0.359, v_num=5, train_loss_step=0.261, train_loss_epoch=0.261]Epoch 41: 100%|##########| 1/1 [00:00<00:00, 16.20it/s, loss=0.351, v_num=5, train_loss_step=0.253, train_loss_epoch=0.261]Epoch 41: 100%|##########| 1/1 [00:00<00:00, 16.05it/s, loss=0.351, v_num=5, train_loss_step=0.253, train_loss_epoch=0.253]Epoch 41:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.351, v_num=5, train_loss_step=0.253, train_loss_epoch=0.253]        Epoch 42:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.351, v_num=5, train_loss_step=0.253, train_loss_epoch=0.253]Epoch 42: 100%|##########| 1/1 [00:00<00:00, 15.82it/s, loss=0.351, v_num=5, train_loss_step=0.253, train_loss_epoch=0.253]Epoch 42: 100%|##########| 1/1 [00:00<00:00, 15.71it/s, loss=0.343, v_num=5, train_loss_step=0.251, train_loss_epoch=0.253]Epoch 42: 100%|##########| 1/1 [00:00<00:00, 15.58it/s, loss=0.343, v_num=5, train_loss_step=0.251, train_loss_epoch=0.251]Epoch 42:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.343, v_num=5, train_loss_step=0.251, train_loss_epoch=0.251]        Epoch 43:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.343, v_num=5, train_loss_step=0.251, train_loss_epoch=0.251]Epoch 43: 100%|##########| 1/1 [00:00<00:00, 15.13it/s, loss=0.343, v_num=5, train_loss_step=0.251, train_loss_epoch=0.251]Epoch 43: 100%|##########| 1/1 [00:00<00:00, 15.03it/s, loss=0.335, v_num=5, train_loss_step=0.247, train_loss_epoch=0.251]Epoch 43: 100%|##########| 1/1 [00:00<00:00, 14.89it/s, loss=0.335, v_num=5, train_loss_step=0.247, train_loss_epoch=0.247]Epoch 43:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.335, v_num=5, train_loss_step=0.247, train_loss_epoch=0.247]        Epoch 44:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.335, v_num=5, train_loss_step=0.247, train_loss_epoch=0.247]Epoch 44: 100%|##########| 1/1 [00:00<00:00, 15.94it/s, loss=0.335, v_num=5, train_loss_step=0.247, train_loss_epoch=0.247]Epoch 44: 100%|##########| 1/1 [00:00<00:00, 15.83it/s, loss=0.327, v_num=5, train_loss_step=0.244, train_loss_epoch=0.247]Epoch 44: 100%|##########| 1/1 [00:00<00:00, 15.66it/s, loss=0.327, v_num=5, train_loss_step=0.244, train_loss_epoch=0.244]Epoch 44:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.327, v_num=5, train_loss_step=0.244, train_loss_epoch=0.244]        Epoch 45:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.327, v_num=5, train_loss_step=0.244, train_loss_epoch=0.244]Epoch 45: 100%|##########| 1/1 [00:00<00:00, 15.80it/s, loss=0.327, v_num=5, train_loss_step=0.244, train_loss_epoch=0.244]Epoch 45: 100%|##########| 1/1 [00:00<00:00, 15.70it/s, loss=0.32, v_num=5, train_loss_step=0.244, train_loss_epoch=0.244] Epoch 45: 100%|##########| 1/1 [00:00<00:00, 15.56it/s, loss=0.32, v_num=5, train_loss_step=0.244, train_loss_epoch=0.244]Epoch 45:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.32, v_num=5, train_loss_step=0.244, train_loss_epoch=0.244]        Epoch 46:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.32, v_num=5, train_loss_step=0.244, train_loss_epoch=0.244]Epoch 46: 100%|##########| 1/1 [00:00<00:00, 15.58it/s, loss=0.32, v_num=5, train_loss_step=0.244, train_loss_epoch=0.244]Epoch 46: 100%|##########| 1/1 [00:00<00:00, 15.48it/s, loss=0.312, v_num=5, train_loss_step=0.238, train_loss_epoch=0.244]Epoch 46: 100%|##########| 1/1 [00:00<00:00, 15.34it/s, loss=0.312, v_num=5, train_loss_step=0.238, train_loss_epoch=0.238]Epoch 46:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.312, v_num=5, train_loss_step=0.238, train_loss_epoch=0.238]        Epoch 47:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.312, v_num=5, train_loss_step=0.238, train_loss_epoch=0.238]Epoch 47: 100%|##########| 1/1 [00:00<00:00, 16.84it/s, loss=0.312, v_num=5, train_loss_step=0.238, train_loss_epoch=0.238]Epoch 47: 100%|##########| 1/1 [00:00<00:00, 16.71it/s, loss=0.304, v_num=5, train_loss_step=0.234, train_loss_epoch=0.238]Epoch 47: 100%|##########| 1/1 [00:00<00:00, 16.53it/s, loss=0.304, v_num=5, train_loss_step=0.234, train_loss_epoch=0.234]Epoch 47:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.304, v_num=5, train_loss_step=0.234, train_loss_epoch=0.234]        Epoch 48:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.304, v_num=5, train_loss_step=0.234, train_loss_epoch=0.234]Epoch 48: 100%|##########| 1/1 [00:00<00:00, 17.21it/s, loss=0.304, v_num=5, train_loss_step=0.234, train_loss_epoch=0.234]Epoch 48: 100%|##########| 1/1 [00:00<00:00, 17.09it/s, loss=0.296, v_num=5, train_loss_step=0.229, train_loss_epoch=0.234]Epoch 48: 100%|##########| 1/1 [00:00<00:00, 16.91it/s, loss=0.296, v_num=5, train_loss_step=0.229, train_loss_epoch=0.229]Epoch 48:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.296, v_num=5, train_loss_step=0.229, train_loss_epoch=0.229]        Epoch 49:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.296, v_num=5, train_loss_step=0.229, train_loss_epoch=0.229]Epoch 49: 100%|##########| 1/1 [00:00<00:00, 17.72it/s, loss=0.296, v_num=5, train_loss_step=0.229, train_loss_epoch=0.229]Epoch 49: 100%|##########| 1/1 [00:00<00:00, 17.60it/s, loss=0.288, v_num=5, train_loss_step=0.222, train_loss_epoch=0.229]Epoch 49: 100%|##########| 1/1 [00:00<00:00, 17.22it/s, loss=0.288, v_num=5, train_loss_step=0.222, train_loss_epoch=0.222]Epoch 49:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.288, v_num=5, train_loss_step=0.222, train_loss_epoch=0.222]        Epoch 50:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.288, v_num=5, train_loss_step=0.222, train_loss_epoch=0.222]Epoch 50: 100%|##########| 1/1 [00:00<00:00, 18.18it/s, loss=0.288, v_num=5, train_loss_step=0.222, train_loss_epoch=0.222]Epoch 50: 100%|##########| 1/1 [00:00<00:00, 18.05it/s, loss=0.279, v_num=5, train_loss_step=0.215, train_loss_epoch=0.222]Epoch 50: 100%|##########| 1/1 [00:00<00:00, 17.85it/s, loss=0.279, v_num=5, train_loss_step=0.215, train_loss_epoch=0.215]Epoch 50:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.279, v_num=5, train_loss_step=0.215, train_loss_epoch=0.215]        Epoch 51:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.279, v_num=5, train_loss_step=0.215, train_loss_epoch=0.215]Epoch 51: 100%|##########| 1/1 [00:00<00:00, 14.74it/s, loss=0.279, v_num=5, train_loss_step=0.215, train_loss_epoch=0.215]Epoch 51: 100%|##########| 1/1 [00:00<00:00, 14.65it/s, loss=0.271, v_num=5, train_loss_step=0.208, train_loss_epoch=0.215]Epoch 51: 100%|##########| 1/1 [00:00<00:00, 14.54it/s, loss=0.271, v_num=5, train_loss_step=0.208, train_loss_epoch=0.208]Epoch 51:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.271, v_num=5, train_loss_step=0.208, train_loss_epoch=0.208]        Epoch 52:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.271, v_num=5, train_loss_step=0.208, train_loss_epoch=0.208]Epoch 52: 100%|##########| 1/1 [00:00<00:00, 16.51it/s, loss=0.271, v_num=5, train_loss_step=0.208, train_loss_epoch=0.208]Epoch 52: 100%|##########| 1/1 [00:00<00:00, 16.40it/s, loss=0.263, v_num=5, train_loss_step=0.202, train_loss_epoch=0.208]Epoch 52: 100%|##########| 1/1 [00:00<00:00, 16.22it/s, loss=0.263, v_num=5, train_loss_step=0.202, train_loss_epoch=0.202]Epoch 52:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.263, v_num=5, train_loss_step=0.202, train_loss_epoch=0.202]        Epoch 53:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.263, v_num=5, train_loss_step=0.202, train_loss_epoch=0.202]Epoch 53: 100%|##########| 1/1 [00:00<00:00, 16.25it/s, loss=0.263, v_num=5, train_loss_step=0.202, train_loss_epoch=0.202]Epoch 53: 100%|##########| 1/1 [00:00<00:00, 16.14it/s, loss=0.255, v_num=5, train_loss_step=0.198, train_loss_epoch=0.202]Epoch 53: 100%|##########| 1/1 [00:00<00:00, 15.98it/s, loss=0.255, v_num=5, train_loss_step=0.198, train_loss_epoch=0.198]Epoch 53:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.255, v_num=5, train_loss_step=0.198, train_loss_epoch=0.198]        Epoch 54:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.255, v_num=5, train_loss_step=0.198, train_loss_epoch=0.198]Epoch 54: 100%|##########| 1/1 [00:00<00:00, 15.61it/s, loss=0.255, v_num=5, train_loss_step=0.198, train_loss_epoch=0.198]Epoch 54: 100%|##########| 1/1 [00:00<00:00, 15.49it/s, loss=0.248, v_num=5, train_loss_step=0.192, train_loss_epoch=0.198]Epoch 54: 100%|##########| 1/1 [00:00<00:00, 15.33it/s, loss=0.248, v_num=5, train_loss_step=0.192, train_loss_epoch=0.192]Epoch 54:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.248, v_num=5, train_loss_step=0.192, train_loss_epoch=0.192]        Epoch 55:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.248, v_num=5, train_loss_step=0.192, train_loss_epoch=0.192]Epoch 55: 100%|##########| 1/1 [00:00<00:00, 15.86it/s, loss=0.248, v_num=5, train_loss_step=0.192, train_loss_epoch=0.192]Epoch 55: 100%|##########| 1/1 [00:00<00:00, 15.76it/s, loss=0.24, v_num=5, train_loss_step=0.187, train_loss_epoch=0.192] Epoch 55: 100%|##########| 1/1 [00:00<00:00, 15.62it/s, loss=0.24, v_num=5, train_loss_step=0.187, train_loss_epoch=0.187]Epoch 55:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.24, v_num=5, train_loss_step=0.187, train_loss_epoch=0.187]        Epoch 56:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.24, v_num=5, train_loss_step=0.187, train_loss_epoch=0.187]Epoch 56: 100%|##########| 1/1 [00:00<00:00, 15.10it/s, loss=0.24, v_num=5, train_loss_step=0.187, train_loss_epoch=0.187]Epoch 56: 100%|##########| 1/1 [00:00<00:00, 14.99it/s, loss=0.234, v_num=5, train_loss_step=0.181, train_loss_epoch=0.187]Epoch 56: 100%|##########| 1/1 [00:00<00:00, 14.83it/s, loss=0.234, v_num=5, train_loss_step=0.181, train_loss_epoch=0.181]Epoch 56:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.234, v_num=5, train_loss_step=0.181, train_loss_epoch=0.181]        Epoch 57:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.234, v_num=5, train_loss_step=0.181, train_loss_epoch=0.181]Epoch 57: 100%|##########| 1/1 [00:00<00:00, 16.21it/s, loss=0.234, v_num=5, train_loss_step=0.181, train_loss_epoch=0.181]Epoch 57: 100%|##########| 1/1 [00:00<00:00, 16.11it/s, loss=0.227, v_num=5, train_loss_step=0.175, train_loss_epoch=0.181]Epoch 57: 100%|##########| 1/1 [00:00<00:00, 15.95it/s, loss=0.227, v_num=5, train_loss_step=0.175, train_loss_epoch=0.175]Epoch 57:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.227, v_num=5, train_loss_step=0.175, train_loss_epoch=0.175]        Epoch 58:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.227, v_num=5, train_loss_step=0.175, train_loss_epoch=0.175]Epoch 58: 100%|##########| 1/1 [00:00<00:00, 17.20it/s, loss=0.227, v_num=5, train_loss_step=0.175, train_loss_epoch=0.175]Epoch 58: 100%|##########| 1/1 [00:00<00:00, 17.07it/s, loss=0.221, v_num=5, train_loss_step=0.170, train_loss_epoch=0.175]Epoch 58: 100%|##########| 1/1 [00:00<00:00, 16.89it/s, loss=0.221, v_num=5, train_loss_step=0.170, train_loss_epoch=0.170]Epoch 58:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.221, v_num=5, train_loss_step=0.170, train_loss_epoch=0.170]        Epoch 59:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.221, v_num=5, train_loss_step=0.170, train_loss_epoch=0.170]Epoch 59: 100%|##########| 1/1 [00:00<00:00, 17.53it/s, loss=0.221, v_num=5, train_loss_step=0.170, train_loss_epoch=0.170]Epoch 59: 100%|##########| 1/1 [00:00<00:00, 17.40it/s, loss=0.216, v_num=5, train_loss_step=0.163, train_loss_epoch=0.170]Epoch 59: 100%|##########| 1/1 [00:00<00:00, 17.23it/s, loss=0.216, v_num=5, train_loss_step=0.163, train_loss_epoch=0.163]Epoch 59:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.216, v_num=5, train_loss_step=0.163, train_loss_epoch=0.163]        Epoch 60:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.216, v_num=5, train_loss_step=0.163, train_loss_epoch=0.163]Epoch 60: 100%|##########| 1/1 [00:00<00:00, 16.86it/s, loss=0.216, v_num=5, train_loss_step=0.163, train_loss_epoch=0.163]Epoch 60: 100%|##########| 1/1 [00:00<00:00, 16.73it/s, loss=0.211, v_num=5, train_loss_step=0.159, train_loss_epoch=0.163]Epoch 60: 100%|##########| 1/1 [00:00<00:00, 16.55it/s, loss=0.211, v_num=5, train_loss_step=0.159, train_loss_epoch=0.159]Epoch 60:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.211, v_num=5, train_loss_step=0.159, train_loss_epoch=0.159]        Epoch 61:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.211, v_num=5, train_loss_step=0.159, train_loss_epoch=0.159]Epoch 61: 100%|##########| 1/1 [00:00<00:00, 17.62it/s, loss=0.211, v_num=5, train_loss_step=0.159, train_loss_epoch=0.159]Epoch 61: 100%|##########| 1/1 [00:00<00:00, 17.49it/s, loss=0.206, v_num=5, train_loss_step=0.154, train_loss_epoch=0.159]Epoch 61: 100%|##########| 1/1 [00:00<00:00, 17.31it/s, loss=0.206, v_num=5, train_loss_step=0.154, train_loss_epoch=0.154]Epoch 61:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.206, v_num=5, train_loss_step=0.154, train_loss_epoch=0.154]        Epoch 62:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.206, v_num=5, train_loss_step=0.154, train_loss_epoch=0.154]Epoch 62: 100%|##########| 1/1 [00:00<00:00, 14.50it/s, loss=0.206, v_num=5, train_loss_step=0.154, train_loss_epoch=0.154]Epoch 62: 100%|##########| 1/1 [00:00<00:00, 14.41it/s, loss=0.201, v_num=5, train_loss_step=0.150, train_loss_epoch=0.154]Epoch 62: 100%|##########| 1/1 [00:00<00:00, 14.27it/s, loss=0.201, v_num=5, train_loss_step=0.150, train_loss_epoch=0.150]Epoch 62:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.201, v_num=5, train_loss_step=0.150, train_loss_epoch=0.150]        Epoch 63:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.201, v_num=5, train_loss_step=0.150, train_loss_epoch=0.150]Epoch 63: 100%|##########| 1/1 [00:00<00:00, 16.38it/s, loss=0.201, v_num=5, train_loss_step=0.150, train_loss_epoch=0.150]Epoch 63: 100%|##########| 1/1 [00:00<00:00, 16.26it/s, loss=0.196, v_num=5, train_loss_step=0.147, train_loss_epoch=0.150]Epoch 63: 100%|##########| 1/1 [00:00<00:00, 16.09it/s, loss=0.196, v_num=5, train_loss_step=0.147, train_loss_epoch=0.147]Epoch 63:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.196, v_num=5, train_loss_step=0.147, train_loss_epoch=0.147]        Epoch 64:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.196, v_num=5, train_loss_step=0.147, train_loss_epoch=0.147]Epoch 64: 100%|##########| 1/1 [00:00<00:00, 15.72it/s, loss=0.196, v_num=5, train_loss_step=0.147, train_loss_epoch=0.147]Epoch 64: 100%|##########| 1/1 [00:00<00:00, 15.62it/s, loss=0.191, v_num=5, train_loss_step=0.144, train_loss_epoch=0.147]Epoch 64: 100%|##########| 1/1 [00:00<00:00, 15.48it/s, loss=0.191, v_num=5, train_loss_step=0.144, train_loss_epoch=0.144]Epoch 64:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.191, v_num=5, train_loss_step=0.144, train_loss_epoch=0.144]        Epoch 65:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.191, v_num=5, train_loss_step=0.144, train_loss_epoch=0.144]Epoch 65: 100%|##########| 1/1 [00:00<00:00, 16.10it/s, loss=0.191, v_num=5, train_loss_step=0.144, train_loss_epoch=0.144]Epoch 65: 100%|##########| 1/1 [00:00<00:00, 15.99it/s, loss=0.185, v_num=5, train_loss_step=0.142, train_loss_epoch=0.144]Epoch 65: 100%|##########| 1/1 [00:00<00:00, 15.83it/s, loss=0.185, v_num=5, train_loss_step=0.142, train_loss_epoch=0.142]Epoch 65:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.185, v_num=5, train_loss_step=0.142, train_loss_epoch=0.142]        Epoch 66:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.185, v_num=5, train_loss_step=0.142, train_loss_epoch=0.142]Epoch 66: 100%|##########| 1/1 [00:00<00:00, 15.50it/s, loss=0.185, v_num=5, train_loss_step=0.142, train_loss_epoch=0.142]Epoch 66: 100%|##########| 1/1 [00:00<00:00, 15.39it/s, loss=0.181, v_num=5, train_loss_step=0.140, train_loss_epoch=0.142]Epoch 66: 100%|##########| 1/1 [00:00<00:00, 15.24it/s, loss=0.181, v_num=5, train_loss_step=0.140, train_loss_epoch=0.140]Epoch 66:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.181, v_num=5, train_loss_step=0.140, train_loss_epoch=0.140]        Epoch 67:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.181, v_num=5, train_loss_step=0.140, train_loss_epoch=0.140]Epoch 67: 100%|##########| 1/1 [00:00<00:00, 14.61it/s, loss=0.181, v_num=5, train_loss_step=0.140, train_loss_epoch=0.140]Epoch 67: 100%|##########| 1/1 [00:00<00:00, 14.52it/s, loss=0.176, v_num=5, train_loss_step=0.137, train_loss_epoch=0.140]Epoch 67: 100%|##########| 1/1 [00:00<00:00, 14.40it/s, loss=0.176, v_num=5, train_loss_step=0.137, train_loss_epoch=0.137]Epoch 67:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.176, v_num=5, train_loss_step=0.137, train_loss_epoch=0.137]        Epoch 68:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.176, v_num=5, train_loss_step=0.137, train_loss_epoch=0.137]Epoch 68: 100%|##########| 1/1 [00:00<00:00, 16.27it/s, loss=0.176, v_num=5, train_loss_step=0.137, train_loss_epoch=0.137]Epoch 68: 100%|##########| 1/1 [00:00<00:00, 16.15it/s, loss=0.171, v_num=5, train_loss_step=0.136, train_loss_epoch=0.137]Epoch 68: 100%|##########| 1/1 [00:00<00:00, 15.99it/s, loss=0.171, v_num=5, train_loss_step=0.136, train_loss_epoch=0.136]Epoch 68:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.171, v_num=5, train_loss_step=0.136, train_loss_epoch=0.136]        Epoch 69:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.171, v_num=5, train_loss_step=0.136, train_loss_epoch=0.136]Epoch 69: 100%|##########| 1/1 [00:00<00:00, 16.39it/s, loss=0.171, v_num=5, train_loss_step=0.136, train_loss_epoch=0.136]Epoch 69: 100%|##########| 1/1 [00:00<00:00, 16.27it/s, loss=0.167, v_num=5, train_loss_step=0.134, train_loss_epoch=0.136]Epoch 69: 100%|##########| 1/1 [00:00<00:00, 16.10it/s, loss=0.167, v_num=5, train_loss_step=0.134, train_loss_epoch=0.134]Epoch 69:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.167, v_num=5, train_loss_step=0.134, train_loss_epoch=0.134]        Epoch 70:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.167, v_num=5, train_loss_step=0.134, train_loss_epoch=0.134]Epoch 70: 100%|##########| 1/1 [00:00<00:00, 16.56it/s, loss=0.167, v_num=5, train_loss_step=0.134, train_loss_epoch=0.134]Epoch 70: 100%|##########| 1/1 [00:00<00:00, 16.38it/s, loss=0.163, v_num=5, train_loss_step=0.133, train_loss_epoch=0.134]Epoch 70: 100%|##########| 1/1 [00:00<00:00, 16.22it/s, loss=0.163, v_num=5, train_loss_step=0.133, train_loss_epoch=0.133]Epoch 70:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.163, v_num=5, train_loss_step=0.133, train_loss_epoch=0.133]        Epoch 71:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.163, v_num=5, train_loss_step=0.133, train_loss_epoch=0.133]Epoch 71: 100%|##########| 1/1 [00:00<00:00, 16.77it/s, loss=0.163, v_num=5, train_loss_step=0.133, train_loss_epoch=0.133]Epoch 71: 100%|##########| 1/1 [00:00<00:00, 16.64it/s, loss=0.159, v_num=5, train_loss_step=0.131, train_loss_epoch=0.133]Epoch 71: 100%|##########| 1/1 [00:00<00:00, 16.45it/s, loss=0.159, v_num=5, train_loss_step=0.131, train_loss_epoch=0.131]Epoch 71:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.159, v_num=5, train_loss_step=0.131, train_loss_epoch=0.131]        Epoch 72:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.159, v_num=5, train_loss_step=0.131, train_loss_epoch=0.131]Epoch 72: 100%|##########| 1/1 [00:00<00:00, 17.22it/s, loss=0.159, v_num=5, train_loss_step=0.131, train_loss_epoch=0.131]Epoch 72: 100%|##########| 1/1 [00:00<00:00, 17.10it/s, loss=0.155, v_num=5, train_loss_step=0.130, train_loss_epoch=0.131]Epoch 72: 100%|##########| 1/1 [00:00<00:00, 16.92it/s, loss=0.155, v_num=5, train_loss_step=0.130, train_loss_epoch=0.130]Epoch 72:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.155, v_num=5, train_loss_step=0.130, train_loss_epoch=0.130]        Epoch 73:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.155, v_num=5, train_loss_step=0.130, train_loss_epoch=0.130]Epoch 73: 100%|##########| 1/1 [00:00<00:00, 17.25it/s, loss=0.155, v_num=5, train_loss_step=0.130, train_loss_epoch=0.130]Epoch 73: 100%|##########| 1/1 [00:00<00:00, 17.11it/s, loss=0.152, v_num=5, train_loss_step=0.128, train_loss_epoch=0.130]Epoch 73: 100%|##########| 1/1 [00:00<00:00, 16.92it/s, loss=0.152, v_num=5, train_loss_step=0.128, train_loss_epoch=0.128]Epoch 73:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.152, v_num=5, train_loss_step=0.128, train_loss_epoch=0.128]        Epoch 74:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.152, v_num=5, train_loss_step=0.128, train_loss_epoch=0.128]Epoch 74: 100%|##########| 1/1 [00:00<00:00, 16.83it/s, loss=0.152, v_num=5, train_loss_step=0.128, train_loss_epoch=0.128]Epoch 74: 100%|##########| 1/1 [00:00<00:00, 16.71it/s, loss=0.148, v_num=5, train_loss_step=0.126, train_loss_epoch=0.128]Epoch 74: 100%|##########| 1/1 [00:00<00:00, 16.53it/s, loss=0.148, v_num=5, train_loss_step=0.126, train_loss_epoch=0.126]Epoch 74:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.148, v_num=5, train_loss_step=0.126, train_loss_epoch=0.126]        Epoch 75:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.148, v_num=5, train_loss_step=0.126, train_loss_epoch=0.126]Epoch 75: 100%|##########| 1/1 [00:00<00:00, 16.58it/s, loss=0.148, v_num=5, train_loss_step=0.126, train_loss_epoch=0.126]Epoch 75: 100%|##########| 1/1 [00:00<00:00, 16.45it/s, loss=0.145, v_num=5, train_loss_step=0.124, train_loss_epoch=0.126]Epoch 75: 100%|##########| 1/1 [00:00<00:00, 16.29it/s, loss=0.145, v_num=5, train_loss_step=0.124, train_loss_epoch=0.124]Epoch 75:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.145, v_num=5, train_loss_step=0.124, train_loss_epoch=0.124]        Epoch 76:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.145, v_num=5, train_loss_step=0.124, train_loss_epoch=0.124]Epoch 76: 100%|##########| 1/1 [00:00<00:00, 16.45it/s, loss=0.145, v_num=5, train_loss_step=0.124, train_loss_epoch=0.124]Epoch 76: 100%|##########| 1/1 [00:00<00:00, 16.33it/s, loss=0.142, v_num=5, train_loss_step=0.123, train_loss_epoch=0.124]Epoch 76: 100%|##########| 1/1 [00:00<00:00, 16.15it/s, loss=0.142, v_num=5, train_loss_step=0.123, train_loss_epoch=0.123]Epoch 76:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.142, v_num=5, train_loss_step=0.123, train_loss_epoch=0.123]        Epoch 77:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.142, v_num=5, train_loss_step=0.123, train_loss_epoch=0.123]Epoch 77: 100%|##########| 1/1 [00:00<00:00, 16.40it/s, loss=0.142, v_num=5, train_loss_step=0.123, train_loss_epoch=0.123]Epoch 77: 100%|##########| 1/1 [00:00<00:00, 16.28it/s, loss=0.14, v_num=5, train_loss_step=0.124, train_loss_epoch=0.123] Epoch 77: 100%|##########| 1/1 [00:00<00:00, 16.10it/s, loss=0.14, v_num=5, train_loss_step=0.124, train_loss_epoch=0.124]Epoch 77:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.14, v_num=5, train_loss_step=0.124, train_loss_epoch=0.124]        Epoch 78:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.14, v_num=5, train_loss_step=0.124, train_loss_epoch=0.124]Epoch 78: 100%|##########| 1/1 [00:00<00:00, 16.74it/s, loss=0.14, v_num=5, train_loss_step=0.124, train_loss_epoch=0.124]Epoch 78: 100%|##########| 1/1 [00:00<00:00, 16.63it/s, loss=0.137, v_num=5, train_loss_step=0.121, train_loss_epoch=0.124]Epoch 78: 100%|##########| 1/1 [00:00<00:00, 16.47it/s, loss=0.137, v_num=5, train_loss_step=0.121, train_loss_epoch=0.121]Epoch 78:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.137, v_num=5, train_loss_step=0.121, train_loss_epoch=0.121]        Epoch 79:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.137, v_num=5, train_loss_step=0.121, train_loss_epoch=0.121]Epoch 79: 100%|##########| 1/1 [00:00<00:00, 15.76it/s, loss=0.137, v_num=5, train_loss_step=0.121, train_loss_epoch=0.121]Epoch 79: 100%|##########| 1/1 [00:00<00:00, 15.65it/s, loss=0.135, v_num=5, train_loss_step=0.117, train_loss_epoch=0.121]Epoch 79: 100%|##########| 1/1 [00:00<00:00, 15.49it/s, loss=0.135, v_num=5, train_loss_step=0.117, train_loss_epoch=0.117]Epoch 79:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.135, v_num=5, train_loss_step=0.117, train_loss_epoch=0.117]        Epoch 80:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.135, v_num=5, train_loss_step=0.117, train_loss_epoch=0.117]Epoch 80: 100%|##########| 1/1 [00:00<00:00, 16.53it/s, loss=0.135, v_num=5, train_loss_step=0.117, train_loss_epoch=0.117]Epoch 80: 100%|##########| 1/1 [00:00<00:00, 16.40it/s, loss=0.133, v_num=5, train_loss_step=0.116, train_loss_epoch=0.117]Epoch 80: 100%|##########| 1/1 [00:00<00:00, 16.23it/s, loss=0.133, v_num=5, train_loss_step=0.116, train_loss_epoch=0.116]Epoch 80:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.133, v_num=5, train_loss_step=0.116, train_loss_epoch=0.116]        Epoch 81:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.133, v_num=5, train_loss_step=0.116, train_loss_epoch=0.116]Epoch 81: 100%|##########| 1/1 [00:00<00:00, 16.71it/s, loss=0.133, v_num=5, train_loss_step=0.116, train_loss_epoch=0.116]Epoch 81: 100%|##########| 1/1 [00:00<00:00, 16.58it/s, loss=0.131, v_num=5, train_loss_step=0.118, train_loss_epoch=0.116]Epoch 81: 100%|##########| 1/1 [00:00<00:00, 16.41it/s, loss=0.131, v_num=5, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 81:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.131, v_num=5, train_loss_step=0.118, train_loss_epoch=0.118]        Epoch 82:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.131, v_num=5, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 82: 100%|##########| 1/1 [00:00<00:00, 16.78it/s, loss=0.131, v_num=5, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 82: 100%|##########| 1/1 [00:00<00:00, 16.59it/s, loss=0.129, v_num=5, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 82: 100%|##########| 1/1 [00:00<00:00, 16.42it/s, loss=0.129, v_num=5, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 82:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.129, v_num=5, train_loss_step=0.118, train_loss_epoch=0.118]        Epoch 83:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.129, v_num=5, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 83: 100%|##########| 1/1 [00:00<00:00, 17.24it/s, loss=0.129, v_num=5, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 83: 100%|##########| 1/1 [00:00<00:00, 17.11it/s, loss=0.128, v_num=5, train_loss_step=0.113, train_loss_epoch=0.118]Epoch 83: 100%|##########| 1/1 [00:00<00:00, 16.94it/s, loss=0.128, v_num=5, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 83:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.128, v_num=5, train_loss_step=0.113, train_loss_epoch=0.113]        Epoch 84:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.128, v_num=5, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 84: 100%|##########| 1/1 [00:00<00:00, 17.31it/s, loss=0.128, v_num=5, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 84: 100%|##########| 1/1 [00:00<00:00, 17.19it/s, loss=0.126, v_num=5, train_loss_step=0.112, train_loss_epoch=0.113]Epoch 84: 100%|##########| 1/1 [00:00<00:00, 17.03it/s, loss=0.126, v_num=5, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 84:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.126, v_num=5, train_loss_step=0.112, train_loss_epoch=0.112]        Epoch 85:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.126, v_num=5, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 85: 100%|##########| 1/1 [00:00<00:00, 17.67it/s, loss=0.126, v_num=5, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 85: 100%|##########| 1/1 [00:00<00:00, 17.55it/s, loss=0.125, v_num=5, train_loss_step=0.113, train_loss_epoch=0.112]Epoch 85: 100%|##########| 1/1 [00:00<00:00, 17.38it/s, loss=0.125, v_num=5, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 85:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.125, v_num=5, train_loss_step=0.113, train_loss_epoch=0.113]        Epoch 86:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.125, v_num=5, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 86: 100%|##########| 1/1 [00:00<00:00, 17.06it/s, loss=0.125, v_num=5, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 86: 100%|##########| 1/1 [00:00<00:00, 16.95it/s, loss=0.123, v_num=5, train_loss_step=0.112, train_loss_epoch=0.113]Epoch 86: 100%|##########| 1/1 [00:00<00:00, 16.80it/s, loss=0.123, v_num=5, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 86:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.123, v_num=5, train_loss_step=0.112, train_loss_epoch=0.112]        Epoch 87:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.123, v_num=5, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 87: 100%|##########| 1/1 [00:00<00:00, 17.57it/s, loss=0.123, v_num=5, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 87: 100%|##########| 1/1 [00:00<00:00, 17.43it/s, loss=0.122, v_num=5, train_loss_step=0.108, train_loss_epoch=0.112]Epoch 87: 100%|##########| 1/1 [00:00<00:00, 17.24it/s, loss=0.122, v_num=5, train_loss_step=0.108, train_loss_epoch=0.108]Epoch 87:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.122, v_num=5, train_loss_step=0.108, train_loss_epoch=0.108]        Epoch 88:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.122, v_num=5, train_loss_step=0.108, train_loss_epoch=0.108]Epoch 88: 100%|##########| 1/1 [00:00<00:00, 17.28it/s, loss=0.122, v_num=5, train_loss_step=0.108, train_loss_epoch=0.108]Epoch 88: 100%|##########| 1/1 [00:00<00:00, 17.15it/s, loss=0.12, v_num=5, train_loss_step=0.109, train_loss_epoch=0.108] Epoch 88: 100%|##########| 1/1 [00:00<00:00, 16.98it/s, loss=0.12, v_num=5, train_loss_step=0.109, train_loss_epoch=0.109]Epoch 88:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.12, v_num=5, train_loss_step=0.109, train_loss_epoch=0.109]        Epoch 89:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.12, v_num=5, train_loss_step=0.109, train_loss_epoch=0.109]Epoch 89: 100%|##########| 1/1 [00:00<00:00, 17.24it/s, loss=0.12, v_num=5, train_loss_step=0.109, train_loss_epoch=0.109]Epoch 89: 100%|##########| 1/1 [00:00<00:00, 17.10it/s, loss=0.119, v_num=5, train_loss_step=0.110, train_loss_epoch=0.109]Epoch 89: 100%|##########| 1/1 [00:00<00:00, 16.91it/s, loss=0.119, v_num=5, train_loss_step=0.110, train_loss_epoch=0.110]Epoch 89:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.119, v_num=5, train_loss_step=0.110, train_loss_epoch=0.110]        Epoch 90:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.119, v_num=5, train_loss_step=0.110, train_loss_epoch=0.110]Epoch 90: 100%|##########| 1/1 [00:00<00:00, 17.88it/s, loss=0.119, v_num=5, train_loss_step=0.110, train_loss_epoch=0.110]Epoch 90: 100%|##########| 1/1 [00:00<00:00, 17.75it/s, loss=0.118, v_num=5, train_loss_step=0.105, train_loss_epoch=0.110]Epoch 90: 100%|##########| 1/1 [00:00<00:00, 17.56it/s, loss=0.118, v_num=5, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 90:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.118, v_num=5, train_loss_step=0.105, train_loss_epoch=0.105]        Epoch 91:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.118, v_num=5, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 91: 100%|##########| 1/1 [00:00<00:00, 16.71it/s, loss=0.118, v_num=5, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 91: 100%|##########| 1/1 [00:00<00:00, 16.59it/s, loss=0.117, v_num=5, train_loss_step=0.106, train_loss_epoch=0.105]Epoch 91: 100%|##########| 1/1 [00:00<00:00, 16.42it/s, loss=0.117, v_num=5, train_loss_step=0.106, train_loss_epoch=0.106]Epoch 91:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.117, v_num=5, train_loss_step=0.106, train_loss_epoch=0.106]        Epoch 92:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.117, v_num=5, train_loss_step=0.106, train_loss_epoch=0.106]Epoch 92: 100%|##########| 1/1 [00:00<00:00, 17.17it/s, loss=0.117, v_num=5, train_loss_step=0.106, train_loss_epoch=0.106]Epoch 92: 100%|##########| 1/1 [00:00<00:00, 17.06it/s, loss=0.115, v_num=5, train_loss_step=0.106, train_loss_epoch=0.106]Epoch 92: 100%|##########| 1/1 [00:00<00:00, 16.88it/s, loss=0.115, v_num=5, train_loss_step=0.106, train_loss_epoch=0.106]Epoch 92:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.115, v_num=5, train_loss_step=0.106, train_loss_epoch=0.106]        Epoch 93:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.115, v_num=5, train_loss_step=0.106, train_loss_epoch=0.106]Epoch 93: 100%|##########| 1/1 [00:00<00:00, 16.80it/s, loss=0.115, v_num=5, train_loss_step=0.106, train_loss_epoch=0.106]Epoch 93: 100%|##########| 1/1 [00:00<00:00, 16.68it/s, loss=0.114, v_num=5, train_loss_step=0.103, train_loss_epoch=0.106]Epoch 93: 100%|##########| 1/1 [00:00<00:00, 16.51it/s, loss=0.114, v_num=5, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 93:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.114, v_num=5, train_loss_step=0.103, train_loss_epoch=0.103]        Epoch 94:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.114, v_num=5, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 94: 100%|##########| 1/1 [00:00<00:00, 17.57it/s, loss=0.114, v_num=5, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 94: 100%|##########| 1/1 [00:00<00:00, 17.45it/s, loss=0.113, v_num=5, train_loss_step=0.102, train_loss_epoch=0.103]Epoch 94: 100%|##########| 1/1 [00:00<00:00, 17.28it/s, loss=0.113, v_num=5, train_loss_step=0.102, train_loss_epoch=0.102]Epoch 94:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.113, v_num=5, train_loss_step=0.102, train_loss_epoch=0.102]        Epoch 95:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.113, v_num=5, train_loss_step=0.102, train_loss_epoch=0.102]Epoch 95: 100%|##########| 1/1 [00:00<00:00, 17.35it/s, loss=0.113, v_num=5, train_loss_step=0.102, train_loss_epoch=0.102]Epoch 95: 100%|##########| 1/1 [00:00<00:00, 17.23it/s, loss=0.112, v_num=5, train_loss_step=0.103, train_loss_epoch=0.102]Epoch 95: 100%|##########| 1/1 [00:00<00:00, 17.06it/s, loss=0.112, v_num=5, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 95:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.112, v_num=5, train_loss_step=0.103, train_loss_epoch=0.103]        Epoch 96:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.112, v_num=5, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 96: 100%|##########| 1/1 [00:00<00:00, 17.43it/s, loss=0.112, v_num=5, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 96: 100%|##########| 1/1 [00:00<00:00, 17.32it/s, loss=0.111, v_num=5, train_loss_step=0.0993, train_loss_epoch=0.103]Epoch 96: 100%|##########| 1/1 [00:00<00:00, 17.14it/s, loss=0.111, v_num=5, train_loss_step=0.0993, train_loss_epoch=0.0993]Epoch 96:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.111, v_num=5, train_loss_step=0.0993, train_loss_epoch=0.0993]        Epoch 97:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.111, v_num=5, train_loss_step=0.0993, train_loss_epoch=0.0993]Epoch 97: 100%|##########| 1/1 [00:00<00:00, 17.62it/s, loss=0.111, v_num=5, train_loss_step=0.0993, train_loss_epoch=0.0993]Epoch 97: 100%|##########| 1/1 [00:00<00:00, 17.48it/s, loss=0.109, v_num=5, train_loss_step=0.100, train_loss_epoch=0.0993] Epoch 97: 100%|##########| 1/1 [00:00<00:00, 17.30it/s, loss=0.109, v_num=5, train_loss_step=0.100, train_loss_epoch=0.100] Epoch 97:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.109, v_num=5, train_loss_step=0.100, train_loss_epoch=0.100]        Epoch 98:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.109, v_num=5, train_loss_step=0.100, train_loss_epoch=0.100]Epoch 98: 100%|##########| 1/1 [00:00<00:00, 17.39it/s, loss=0.109, v_num=5, train_loss_step=0.100, train_loss_epoch=0.100]Epoch 98: 100%|##########| 1/1 [00:00<00:00, 17.27it/s, loss=0.108, v_num=5, train_loss_step=0.0979, train_loss_epoch=0.100]Epoch 98: 100%|##########| 1/1 [00:00<00:00, 17.10it/s, loss=0.108, v_num=5, train_loss_step=0.0979, train_loss_epoch=0.0979]Epoch 98:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.108, v_num=5, train_loss_step=0.0979, train_loss_epoch=0.0979]        Epoch 99:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.108, v_num=5, train_loss_step=0.0979, train_loss_epoch=0.0979]Epoch 99: 100%|##########| 1/1 [00:00<00:00, 16.74it/s, loss=0.108, v_num=5, train_loss_step=0.0979, train_loss_epoch=0.0979]Epoch 99: 100%|##########| 1/1 [00:00<00:00, 16.62it/s, loss=0.107, v_num=5, train_loss_step=0.0975, train_loss_epoch=0.0979]Epoch 99: 100%|##########| 1/1 [00:00<00:00, 16.28it/s, loss=0.107, v_num=5, train_loss_step=0.0975, train_loss_epoch=0.0975]Epoch 99:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.107, v_num=5, train_loss_step=0.0975, train_loss_epoch=0.0975]        Epoch 100:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.107, v_num=5, train_loss_step=0.0975, train_loss_epoch=0.0975]Epoch 100: 100%|##########| 1/1 [00:00<00:00, 17.12it/s, loss=0.107, v_num=5, train_loss_step=0.0975, train_loss_epoch=0.0975]Epoch 100: 100%|##########| 1/1 [00:00<00:00, 17.00it/s, loss=0.106, v_num=5, train_loss_step=0.0955, train_loss_epoch=0.0975]Epoch 100: 100%|##########| 1/1 [00:00<00:00, 16.84it/s, loss=0.106, v_num=5, train_loss_step=0.0955, train_loss_epoch=0.0955]Epoch 100:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.106, v_num=5, train_loss_step=0.0955, train_loss_epoch=0.0955]        Epoch 101:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.106, v_num=5, train_loss_step=0.0955, train_loss_epoch=0.0955]Epoch 101: 100%|##########| 1/1 [00:00<00:00, 16.90it/s, loss=0.106, v_num=5, train_loss_step=0.0955, train_loss_epoch=0.0955]Epoch 101: 100%|##########| 1/1 [00:00<00:00, 16.78it/s, loss=0.105, v_num=5, train_loss_step=0.0951, train_loss_epoch=0.0955]Epoch 101: 100%|##########| 1/1 [00:00<00:00, 16.60it/s, loss=0.105, v_num=5, train_loss_step=0.0951, train_loss_epoch=0.0951]Epoch 101:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.105, v_num=5, train_loss_step=0.0951, train_loss_epoch=0.0951]        Epoch 102:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.105, v_num=5, train_loss_step=0.0951, train_loss_epoch=0.0951]Epoch 102: 100%|##########| 1/1 [00:00<00:00, 17.45it/s, loss=0.105, v_num=5, train_loss_step=0.0951, train_loss_epoch=0.0951]Epoch 102: 100%|##########| 1/1 [00:00<00:00, 17.32it/s, loss=0.104, v_num=5, train_loss_step=0.0936, train_loss_epoch=0.0951]Epoch 102: 100%|##########| 1/1 [00:00<00:00, 17.14it/s, loss=0.104, v_num=5, train_loss_step=0.0936, train_loss_epoch=0.0936]Epoch 102:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.104, v_num=5, train_loss_step=0.0936, train_loss_epoch=0.0936]        Epoch 103:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.104, v_num=5, train_loss_step=0.0936, train_loss_epoch=0.0936]Epoch 103: 100%|##########| 1/1 [00:00<00:00, 15.12it/s, loss=0.104, v_num=5, train_loss_step=0.0936, train_loss_epoch=0.0936]Epoch 103: 100%|##########| 1/1 [00:00<00:00, 15.00it/s, loss=0.103, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0936]Epoch 103: 100%|##########| 1/1 [00:00<00:00, 14.85it/s, loss=0.103, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0929]Epoch 103:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.103, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0929]        Epoch 104:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.103, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0929]Epoch 104: 100%|##########| 1/1 [00:00<00:00, 16.76it/s, loss=0.103, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0929]Epoch 104: 100%|##########| 1/1 [00:00<00:00, 16.64it/s, loss=0.102, v_num=5, train_loss_step=0.0914, train_loss_epoch=0.0929]Epoch 104: 100%|##########| 1/1 [00:00<00:00, 16.46it/s, loss=0.102, v_num=5, train_loss_step=0.0914, train_loss_epoch=0.0914]Epoch 104:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.102, v_num=5, train_loss_step=0.0914, train_loss_epoch=0.0914]        Epoch 105:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.102, v_num=5, train_loss_step=0.0914, train_loss_epoch=0.0914]Epoch 105: 100%|##########| 1/1 [00:00<00:00, 16.44it/s, loss=0.102, v_num=5, train_loss_step=0.0914, train_loss_epoch=0.0914]Epoch 105: 100%|##########| 1/1 [00:00<00:00, 16.32it/s, loss=0.101, v_num=5, train_loss_step=0.091, train_loss_epoch=0.0914] Epoch 105: 100%|##########| 1/1 [00:00<00:00, 16.14it/s, loss=0.101, v_num=5, train_loss_step=0.091, train_loss_epoch=0.091] Epoch 105:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.101, v_num=5, train_loss_step=0.091, train_loss_epoch=0.091]        Epoch 106:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.101, v_num=5, train_loss_step=0.091, train_loss_epoch=0.091]Epoch 106: 100%|##########| 1/1 [00:00<00:00, 17.09it/s, loss=0.101, v_num=5, train_loss_step=0.091, train_loss_epoch=0.091]Epoch 106: 100%|##########| 1/1 [00:00<00:00, 16.91it/s, loss=0.0998, v_num=5, train_loss_step=0.0905, train_loss_epoch=0.091]Epoch 106: 100%|##########| 1/1 [00:00<00:00, 16.74it/s, loss=0.0998, v_num=5, train_loss_step=0.0905, train_loss_epoch=0.0905]Epoch 106:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0998, v_num=5, train_loss_step=0.0905, train_loss_epoch=0.0905]        Epoch 107:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0998, v_num=5, train_loss_step=0.0905, train_loss_epoch=0.0905]Epoch 107: 100%|##########| 1/1 [00:00<00:00, 16.43it/s, loss=0.0998, v_num=5, train_loss_step=0.0905, train_loss_epoch=0.0905]Epoch 107: 100%|##########| 1/1 [00:00<00:00, 16.32it/s, loss=0.0991, v_num=5, train_loss_step=0.0931, train_loss_epoch=0.0905]Epoch 107: 100%|##########| 1/1 [00:00<00:00, 16.17it/s, loss=0.0991, v_num=5, train_loss_step=0.0931, train_loss_epoch=0.0931]Epoch 107:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0991, v_num=5, train_loss_step=0.0931, train_loss_epoch=0.0931]        Epoch 108:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0991, v_num=5, train_loss_step=0.0931, train_loss_epoch=0.0931]Epoch 108: 100%|##########| 1/1 [00:00<00:00, 17.40it/s, loss=0.0991, v_num=5, train_loss_step=0.0931, train_loss_epoch=0.0931]Epoch 108: 100%|##########| 1/1 [00:00<00:00, 17.28it/s, loss=0.0984, v_num=5, train_loss_step=0.096, train_loss_epoch=0.0931] Epoch 108: 100%|##########| 1/1 [00:00<00:00, 17.12it/s, loss=0.0984, v_num=5, train_loss_step=0.096, train_loss_epoch=0.096] Epoch 108:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0984, v_num=5, train_loss_step=0.096, train_loss_epoch=0.096]        Epoch 109:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0984, v_num=5, train_loss_step=0.096, train_loss_epoch=0.096]Epoch 109: 100%|##########| 1/1 [00:00<00:00, 17.17it/s, loss=0.0984, v_num=5, train_loss_step=0.096, train_loss_epoch=0.096]Epoch 109: 100%|##########| 1/1 [00:00<00:00, 17.04it/s, loss=0.0976, v_num=5, train_loss_step=0.0926, train_loss_epoch=0.096]Epoch 109: 100%|##########| 1/1 [00:00<00:00, 16.85it/s, loss=0.0976, v_num=5, train_loss_step=0.0926, train_loss_epoch=0.0926]Epoch 109:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0976, v_num=5, train_loss_step=0.0926, train_loss_epoch=0.0926]        Epoch 110:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0976, v_num=5, train_loss_step=0.0926, train_loss_epoch=0.0926]Epoch 110: 100%|##########| 1/1 [00:00<00:00, 17.33it/s, loss=0.0976, v_num=5, train_loss_step=0.0926, train_loss_epoch=0.0926]Epoch 110: 100%|##########| 1/1 [00:00<00:00, 17.20it/s, loss=0.0966, v_num=5, train_loss_step=0.0861, train_loss_epoch=0.0926]Epoch 110: 100%|##########| 1/1 [00:00<00:00, 17.01it/s, loss=0.0966, v_num=5, train_loss_step=0.0861, train_loss_epoch=0.0861]Epoch 110:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0966, v_num=5, train_loss_step=0.0861, train_loss_epoch=0.0861]        Epoch 111:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0966, v_num=5, train_loss_step=0.0861, train_loss_epoch=0.0861]Epoch 111: 100%|##########| 1/1 [00:00<00:00, 18.00it/s, loss=0.0966, v_num=5, train_loss_step=0.0861, train_loss_epoch=0.0861]Epoch 111: 100%|##########| 1/1 [00:00<00:00, 17.87it/s, loss=0.096, v_num=5, train_loss_step=0.0932, train_loss_epoch=0.0861] Epoch 111: 100%|##########| 1/1 [00:00<00:00, 17.69it/s, loss=0.096, v_num=5, train_loss_step=0.0932, train_loss_epoch=0.0932]Epoch 111:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.096, v_num=5, train_loss_step=0.0932, train_loss_epoch=0.0932]        Epoch 112:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.096, v_num=5, train_loss_step=0.0932, train_loss_epoch=0.0932]Epoch 112: 100%|##########| 1/1 [00:00<00:00, 17.28it/s, loss=0.096, v_num=5, train_loss_step=0.0932, train_loss_epoch=0.0932]Epoch 112: 100%|##########| 1/1 [00:00<00:00, 17.16it/s, loss=0.0953, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0932]Epoch 112: 100%|##########| 1/1 [00:00<00:00, 16.98it/s, loss=0.0953, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0929]Epoch 112:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0953, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0929]        Epoch 113:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0953, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0929]Epoch 113: 100%|##########| 1/1 [00:00<00:00, 17.03it/s, loss=0.0953, v_num=5, train_loss_step=0.0929, train_loss_epoch=0.0929]Epoch 113: 100%|##########| 1/1 [00:00<00:00, 16.91it/s, loss=0.0944, v_num=5, train_loss_step=0.085, train_loss_epoch=0.0929] Epoch 113: 100%|##########| 1/1 [00:00<00:00, 16.72it/s, loss=0.0944, v_num=5, train_loss_step=0.085, train_loss_epoch=0.085] Epoch 113:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0944, v_num=5, train_loss_step=0.085, train_loss_epoch=0.085]        Epoch 114:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0944, v_num=5, train_loss_step=0.085, train_loss_epoch=0.085]Epoch 114: 100%|##########| 1/1 [00:00<00:00, 16.77it/s, loss=0.0944, v_num=5, train_loss_step=0.085, train_loss_epoch=0.085]Epoch 114: 100%|##########| 1/1 [00:00<00:00, 16.64it/s, loss=0.0936, v_num=5, train_loss_step=0.0857, train_loss_epoch=0.085]Epoch 114: 100%|##########| 1/1 [00:00<00:00, 16.47it/s, loss=0.0936, v_num=5, train_loss_step=0.0857, train_loss_epoch=0.0857]Epoch 114:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0936, v_num=5, train_loss_step=0.0857, train_loss_epoch=0.0857]        Epoch 115:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0936, v_num=5, train_loss_step=0.0857, train_loss_epoch=0.0857]Epoch 115: 100%|##########| 1/1 [00:00<00:00, 16.38it/s, loss=0.0936, v_num=5, train_loss_step=0.0857, train_loss_epoch=0.0857]Epoch 115: 100%|##########| 1/1 [00:00<00:00, 16.26it/s, loss=0.0929, v_num=5, train_loss_step=0.0884, train_loss_epoch=0.0857]Epoch 115: 100%|##########| 1/1 [00:00<00:00, 16.09it/s, loss=0.0929, v_num=5, train_loss_step=0.0884, train_loss_epoch=0.0884]Epoch 115:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0929, v_num=5, train_loss_step=0.0884, train_loss_epoch=0.0884]        Epoch 116:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0929, v_num=5, train_loss_step=0.0884, train_loss_epoch=0.0884]Epoch 116: 100%|##########| 1/1 [00:00<00:00, 16.42it/s, loss=0.0929, v_num=5, train_loss_step=0.0884, train_loss_epoch=0.0884]Epoch 116: 100%|##########| 1/1 [00:00<00:00, 16.30it/s, loss=0.0921, v_num=5, train_loss_step=0.0826, train_loss_epoch=0.0884]Epoch 116: 100%|##########| 1/1 [00:00<00:00, 16.13it/s, loss=0.0921, v_num=5, train_loss_step=0.0826, train_loss_epoch=0.0826]Epoch 116:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0921, v_num=5, train_loss_step=0.0826, train_loss_epoch=0.0826]        Epoch 117:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0921, v_num=5, train_loss_step=0.0826, train_loss_epoch=0.0826]Epoch 117: 100%|##########| 1/1 [00:00<00:00, 17.22it/s, loss=0.0921, v_num=5, train_loss_step=0.0826, train_loss_epoch=0.0826]Epoch 117: 100%|##########| 1/1 [00:00<00:00, 17.10it/s, loss=0.0911, v_num=5, train_loss_step=0.0814, train_loss_epoch=0.0826]Epoch 117: 100%|##########| 1/1 [00:00<00:00, 16.91it/s, loss=0.0911, v_num=5, train_loss_step=0.0814, train_loss_epoch=0.0814]Epoch 117:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0911, v_num=5, train_loss_step=0.0814, train_loss_epoch=0.0814]        Epoch 118:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0911, v_num=5, train_loss_step=0.0814, train_loss_epoch=0.0814]Epoch 118: 100%|##########| 1/1 [00:00<00:00, 17.51it/s, loss=0.0911, v_num=5, train_loss_step=0.0814, train_loss_epoch=0.0814]Epoch 118: 100%|##########| 1/1 [00:00<00:00, 17.37it/s, loss=0.0905, v_num=5, train_loss_step=0.0847, train_loss_epoch=0.0814]Epoch 118: 100%|##########| 1/1 [00:00<00:00, 17.16it/s, loss=0.0905, v_num=5, train_loss_step=0.0847, train_loss_epoch=0.0847]Epoch 118:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0905, v_num=5, train_loss_step=0.0847, train_loss_epoch=0.0847]        Epoch 119:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0905, v_num=5, train_loss_step=0.0847, train_loss_epoch=0.0847]Epoch 119: 100%|##########| 1/1 [00:00<00:00, 16.56it/s, loss=0.0905, v_num=5, train_loss_step=0.0847, train_loss_epoch=0.0847]Epoch 119: 100%|##########| 1/1 [00:00<00:00, 16.43it/s, loss=0.0895, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0847]Epoch 119: 100%|##########| 1/1 [00:00<00:00, 16.27it/s, loss=0.0895, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0784]Epoch 119:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0895, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0784]        Epoch 120:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0895, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0784]Epoch 120: 100%|##########| 1/1 [00:00<00:00, 16.79it/s, loss=0.0895, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0784]Epoch 120: 100%|##########| 1/1 [00:00<00:00, 16.66it/s, loss=0.0886, v_num=5, train_loss_step=0.0783, train_loss_epoch=0.0784]Epoch 120: 100%|##########| 1/1 [00:00<00:00, 16.48it/s, loss=0.0886, v_num=5, train_loss_step=0.0783, train_loss_epoch=0.0783]Epoch 120:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0886, v_num=5, train_loss_step=0.0783, train_loss_epoch=0.0783]        Epoch 121:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0886, v_num=5, train_loss_step=0.0783, train_loss_epoch=0.0783]Epoch 121: 100%|##########| 1/1 [00:00<00:00, 15.91it/s, loss=0.0886, v_num=5, train_loss_step=0.0783, train_loss_epoch=0.0783]Epoch 121: 100%|##########| 1/1 [00:00<00:00, 15.80it/s, loss=0.0878, v_num=5, train_loss_step=0.0789, train_loss_epoch=0.0783]Epoch 121: 100%|##########| 1/1 [00:00<00:00, 15.66it/s, loss=0.0878, v_num=5, train_loss_step=0.0789, train_loss_epoch=0.0789]Epoch 121:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0878, v_num=5, train_loss_step=0.0789, train_loss_epoch=0.0789]        Epoch 122:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0878, v_num=5, train_loss_step=0.0789, train_loss_epoch=0.0789]Epoch 122: 100%|##########| 1/1 [00:00<00:00, 16.60it/s, loss=0.0878, v_num=5, train_loss_step=0.0789, train_loss_epoch=0.0789]Epoch 122: 100%|##########| 1/1 [00:00<00:00, 16.48it/s, loss=0.0871, v_num=5, train_loss_step=0.079, train_loss_epoch=0.0789] Epoch 122: 100%|##########| 1/1 [00:00<00:00, 16.33it/s, loss=0.0871, v_num=5, train_loss_step=0.079, train_loss_epoch=0.079] Epoch 122:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0871, v_num=5, train_loss_step=0.079, train_loss_epoch=0.079]        Epoch 123:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0871, v_num=5, train_loss_step=0.079, train_loss_epoch=0.079]Epoch 123: 100%|##########| 1/1 [00:00<00:00, 17.68it/s, loss=0.0871, v_num=5, train_loss_step=0.079, train_loss_epoch=0.079]Epoch 123: 100%|##########| 1/1 [00:00<00:00, 17.55it/s, loss=0.0862, v_num=5, train_loss_step=0.0741, train_loss_epoch=0.079]Epoch 123: 100%|##########| 1/1 [00:00<00:00, 17.37it/s, loss=0.0862, v_num=5, train_loss_step=0.0741, train_loss_epoch=0.0741]Epoch 123:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0862, v_num=5, train_loss_step=0.0741, train_loss_epoch=0.0741]        Epoch 124:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0862, v_num=5, train_loss_step=0.0741, train_loss_epoch=0.0741]Epoch 124: 100%|##########| 1/1 [00:00<00:00, 17.26it/s, loss=0.0862, v_num=5, train_loss_step=0.0741, train_loss_epoch=0.0741]Epoch 124: 100%|##########| 1/1 [00:00<00:00, 17.13it/s, loss=0.0854, v_num=5, train_loss_step=0.0754, train_loss_epoch=0.0741]Epoch 124: 100%|##########| 1/1 [00:00<00:00, 16.94it/s, loss=0.0854, v_num=5, train_loss_step=0.0754, train_loss_epoch=0.0754]Epoch 124:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0854, v_num=5, train_loss_step=0.0754, train_loss_epoch=0.0754]        Epoch 125:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0854, v_num=5, train_loss_step=0.0754, train_loss_epoch=0.0754]Epoch 125: 100%|##########| 1/1 [00:00<00:00, 16.84it/s, loss=0.0854, v_num=5, train_loss_step=0.0754, train_loss_epoch=0.0754]Epoch 125: 100%|##########| 1/1 [00:00<00:00, 16.72it/s, loss=0.0847, v_num=5, train_loss_step=0.0772, train_loss_epoch=0.0754]Epoch 125: 100%|##########| 1/1 [00:00<00:00, 16.54it/s, loss=0.0847, v_num=5, train_loss_step=0.0772, train_loss_epoch=0.0772]Epoch 125:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0847, v_num=5, train_loss_step=0.0772, train_loss_epoch=0.0772]        Epoch 126:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0847, v_num=5, train_loss_step=0.0772, train_loss_epoch=0.0772]Epoch 126: 100%|##########| 1/1 [00:00<00:00, 16.80it/s, loss=0.0847, v_num=5, train_loss_step=0.0772, train_loss_epoch=0.0772]Epoch 126: 100%|##########| 1/1 [00:00<00:00, 16.67it/s, loss=0.0839, v_num=5, train_loss_step=0.0755, train_loss_epoch=0.0772]Epoch 126: 100%|##########| 1/1 [00:00<00:00, 16.49it/s, loss=0.0839, v_num=5, train_loss_step=0.0755, train_loss_epoch=0.0755]Epoch 126:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0839, v_num=5, train_loss_step=0.0755, train_loss_epoch=0.0755]        Epoch 127:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0839, v_num=5, train_loss_step=0.0755, train_loss_epoch=0.0755]Epoch 127: 100%|##########| 1/1 [00:00<00:00, 17.28it/s, loss=0.0839, v_num=5, train_loss_step=0.0755, train_loss_epoch=0.0755]Epoch 127: 100%|##########| 1/1 [00:00<00:00, 17.15it/s, loss=0.0828, v_num=5, train_loss_step=0.0705, train_loss_epoch=0.0755]Epoch 127: 100%|##########| 1/1 [00:00<00:00, 16.96it/s, loss=0.0828, v_num=5, train_loss_step=0.0705, train_loss_epoch=0.0705]Epoch 127:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0828, v_num=5, train_loss_step=0.0705, train_loss_epoch=0.0705]        Epoch 128:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0828, v_num=5, train_loss_step=0.0705, train_loss_epoch=0.0705]Epoch 128: 100%|##########| 1/1 [00:00<00:00, 16.67it/s, loss=0.0828, v_num=5, train_loss_step=0.0705, train_loss_epoch=0.0705]Epoch 128: 100%|##########| 1/1 [00:00<00:00, 16.54it/s, loss=0.0818, v_num=5, train_loss_step=0.0761, train_loss_epoch=0.0705]Epoch 128: 100%|##########| 1/1 [00:00<00:00, 16.37it/s, loss=0.0818, v_num=5, train_loss_step=0.0761, train_loss_epoch=0.0761]Epoch 128:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0818, v_num=5, train_loss_step=0.0761, train_loss_epoch=0.0761]        Epoch 129:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0818, v_num=5, train_loss_step=0.0761, train_loss_epoch=0.0761]Epoch 129: 100%|##########| 1/1 [00:00<00:00, 17.57it/s, loss=0.0818, v_num=5, train_loss_step=0.0761, train_loss_epoch=0.0761]Epoch 129: 100%|##########| 1/1 [00:00<00:00, 17.44it/s, loss=0.0811, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0761]Epoch 129: 100%|##########| 1/1 [00:00<00:00, 17.26it/s, loss=0.0811, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0784]Epoch 129:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0811, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0784]        Epoch 130:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0811, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0784]Epoch 130: 100%|##########| 1/1 [00:00<00:00, 16.66it/s, loss=0.0811, v_num=5, train_loss_step=0.0784, train_loss_epoch=0.0784]Epoch 130: 100%|##########| 1/1 [00:00<00:00, 16.54it/s, loss=0.0804, v_num=5, train_loss_step=0.0714, train_loss_epoch=0.0784]Epoch 130: 100%|##########| 1/1 [00:00<00:00, 16.39it/s, loss=0.0804, v_num=5, train_loss_step=0.0714, train_loss_epoch=0.0714]Epoch 130:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0804, v_num=5, train_loss_step=0.0714, train_loss_epoch=0.0714]        Epoch 131:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0804, v_num=5, train_loss_step=0.0714, train_loss_epoch=0.0714]Epoch 131: 100%|##########| 1/1 [00:00<00:00, 17.01it/s, loss=0.0804, v_num=5, train_loss_step=0.0714, train_loss_epoch=0.0714]Epoch 131: 100%|##########| 1/1 [00:00<00:00, 16.88it/s, loss=0.0792, v_num=5, train_loss_step=0.0701, train_loss_epoch=0.0714]Epoch 131: 100%|##########| 1/1 [00:00<00:00, 16.70it/s, loss=0.0792, v_num=5, train_loss_step=0.0701, train_loss_epoch=0.0701]Epoch 131:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0792, v_num=5, train_loss_step=0.0701, train_loss_epoch=0.0701]        Epoch 132:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0792, v_num=5, train_loss_step=0.0701, train_loss_epoch=0.0701]Epoch 132: 100%|##########| 1/1 [00:00<00:00, 16.41it/s, loss=0.0792, v_num=5, train_loss_step=0.0701, train_loss_epoch=0.0701]Epoch 132: 100%|##########| 1/1 [00:00<00:00, 16.22it/s, loss=0.0782, v_num=5, train_loss_step=0.0729, train_loss_epoch=0.0701]Epoch 132: 100%|##########| 1/1 [00:00<00:00, 16.06it/s, loss=0.0782, v_num=5, train_loss_step=0.0729, train_loss_epoch=0.0729]Epoch 132:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0782, v_num=5, train_loss_step=0.0729, train_loss_epoch=0.0729]        Epoch 133:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0782, v_num=5, train_loss_step=0.0729, train_loss_epoch=0.0729]Epoch 133: 100%|##########| 1/1 [00:00<00:00, 16.43it/s, loss=0.0782, v_num=5, train_loss_step=0.0729, train_loss_epoch=0.0729]Epoch 133: 100%|##########| 1/1 [00:00<00:00, 16.31it/s, loss=0.0776, v_num=5, train_loss_step=0.0737, train_loss_epoch=0.0729]Epoch 133: 100%|##########| 1/1 [00:00<00:00, 16.14it/s, loss=0.0776, v_num=5, train_loss_step=0.0737, train_loss_epoch=0.0737]Epoch 133:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0776, v_num=5, train_loss_step=0.0737, train_loss_epoch=0.0737]        Epoch 134:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0776, v_num=5, train_loss_step=0.0737, train_loss_epoch=0.0737]Epoch 134: 100%|##########| 1/1 [00:00<00:00, 17.41it/s, loss=0.0776, v_num=5, train_loss_step=0.0737, train_loss_epoch=0.0737]Epoch 134: 100%|##########| 1/1 [00:00<00:00, 17.28it/s, loss=0.0766, v_num=5, train_loss_step=0.0652, train_loss_epoch=0.0737]Epoch 134: 100%|##########| 1/1 [00:00<00:00, 17.10it/s, loss=0.0766, v_num=5, train_loss_step=0.0652, train_loss_epoch=0.0652]Epoch 134:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0766, v_num=5, train_loss_step=0.0652, train_loss_epoch=0.0652]        Epoch 135:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0766, v_num=5, train_loss_step=0.0652, train_loss_epoch=0.0652]Epoch 135: 100%|##########| 1/1 [00:00<00:00, 16.88it/s, loss=0.0766, v_num=5, train_loss_step=0.0652, train_loss_epoch=0.0652]Epoch 135: 100%|##########| 1/1 [00:00<00:00, 16.74it/s, loss=0.0757, v_num=5, train_loss_step=0.0706, train_loss_epoch=0.0652]Epoch 135: 100%|##########| 1/1 [00:00<00:00, 16.56it/s, loss=0.0757, v_num=5, train_loss_step=0.0706, train_loss_epoch=0.0706]Epoch 135:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0757, v_num=5, train_loss_step=0.0706, train_loss_epoch=0.0706]        Epoch 136:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0757, v_num=5, train_loss_step=0.0706, train_loss_epoch=0.0706]Epoch 136: 100%|##########| 1/1 [00:00<00:00, 16.25it/s, loss=0.0757, v_num=5, train_loss_step=0.0706, train_loss_epoch=0.0706]Epoch 136: 100%|##########| 1/1 [00:00<00:00, 16.13it/s, loss=0.0751, v_num=5, train_loss_step=0.0704, train_loss_epoch=0.0706]Epoch 136: 100%|##########| 1/1 [00:00<00:00, 15.96it/s, loss=0.0751, v_num=5, train_loss_step=0.0704, train_loss_epoch=0.0704]Epoch 136:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0751, v_num=5, train_loss_step=0.0704, train_loss_epoch=0.0704]        Epoch 137:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0751, v_num=5, train_loss_step=0.0704, train_loss_epoch=0.0704]Epoch 137: 100%|##########| 1/1 [00:00<00:00, 16.31it/s, loss=0.0751, v_num=5, train_loss_step=0.0704, train_loss_epoch=0.0704]Epoch 137: 100%|##########| 1/1 [00:00<00:00, 16.19it/s, loss=0.0743, v_num=5, train_loss_step=0.0648, train_loss_epoch=0.0704]Epoch 137: 100%|##########| 1/1 [00:00<00:00, 16.02it/s, loss=0.0743, v_num=5, train_loss_step=0.0648, train_loss_epoch=0.0648]Epoch 137:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0743, v_num=5, train_loss_step=0.0648, train_loss_epoch=0.0648]        Epoch 138:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0743, v_num=5, train_loss_step=0.0648, train_loss_epoch=0.0648]Epoch 138: 100%|##########| 1/1 [00:00<00:00, 16.76it/s, loss=0.0743, v_num=5, train_loss_step=0.0648, train_loss_epoch=0.0648]Epoch 138: 100%|##########| 1/1 [00:00<00:00, 16.63it/s, loss=0.0732, v_num=5, train_loss_step=0.0627, train_loss_epoch=0.0648]Epoch 138: 100%|##########| 1/1 [00:00<00:00, 16.44it/s, loss=0.0732, v_num=5, train_loss_step=0.0627, train_loss_epoch=0.0627]Epoch 138:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0732, v_num=5, train_loss_step=0.0627, train_loss_epoch=0.0627]        Epoch 139:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0732, v_num=5, train_loss_step=0.0627, train_loss_epoch=0.0627]Epoch 139: 100%|##########| 1/1 [00:00<00:00, 16.55it/s, loss=0.0732, v_num=5, train_loss_step=0.0627, train_loss_epoch=0.0627]Epoch 139: 100%|##########| 1/1 [00:00<00:00, 16.43it/s, loss=0.0729, v_num=5, train_loss_step=0.0722, train_loss_epoch=0.0627]Epoch 139: 100%|##########| 1/1 [00:00<00:00, 16.25it/s, loss=0.0729, v_num=5, train_loss_step=0.0722, train_loss_epoch=0.0722]Epoch 139:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0729, v_num=5, train_loss_step=0.0722, train_loss_epoch=0.0722]        Epoch 140:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0729, v_num=5, train_loss_step=0.0722, train_loss_epoch=0.0722]Epoch 140: 100%|##########| 1/1 [00:00<00:00, 16.94it/s, loss=0.0729, v_num=5, train_loss_step=0.0722, train_loss_epoch=0.0722]Epoch 140: 100%|##########| 1/1 [00:00<00:00, 16.82it/s, loss=0.0721, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0722]Epoch 140: 100%|##########| 1/1 [00:00<00:00, 16.64it/s, loss=0.0721, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 140:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0721, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0633]        Epoch 141:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0721, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 141: 100%|##########| 1/1 [00:00<00:00, 17.09it/s, loss=0.0721, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 141: 100%|##########| 1/1 [00:00<00:00, 16.95it/s, loss=0.0712, v_num=5, train_loss_step=0.0602, train_loss_epoch=0.0633]Epoch 141: 100%|##########| 1/1 [00:00<00:00, 16.76it/s, loss=0.0712, v_num=5, train_loss_step=0.0602, train_loss_epoch=0.0602]Epoch 141:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0712, v_num=5, train_loss_step=0.0602, train_loss_epoch=0.0602]        Epoch 142:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0712, v_num=5, train_loss_step=0.0602, train_loss_epoch=0.0602]Epoch 142: 100%|##########| 1/1 [00:00<00:00, 16.94it/s, loss=0.0712, v_num=5, train_loss_step=0.0602, train_loss_epoch=0.0602]Epoch 142: 100%|##########| 1/1 [00:00<00:00, 16.80it/s, loss=0.0703, v_num=5, train_loss_step=0.062, train_loss_epoch=0.0602] Epoch 142: 100%|##########| 1/1 [00:00<00:00, 16.62it/s, loss=0.0703, v_num=5, train_loss_step=0.062, train_loss_epoch=0.062] Epoch 142:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0703, v_num=5, train_loss_step=0.062, train_loss_epoch=0.062]        Epoch 143:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0703, v_num=5, train_loss_step=0.062, train_loss_epoch=0.062]Epoch 143: 100%|##########| 1/1 [00:00<00:00, 16.61it/s, loss=0.0703, v_num=5, train_loss_step=0.062, train_loss_epoch=0.062]Epoch 143: 100%|##########| 1/1 [00:00<00:00, 16.50it/s, loss=0.0698, v_num=5, train_loss_step=0.0639, train_loss_epoch=0.062]Epoch 143: 100%|##########| 1/1 [00:00<00:00, 16.35it/s, loss=0.0698, v_num=5, train_loss_step=0.0639, train_loss_epoch=0.0639]Epoch 143:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0698, v_num=5, train_loss_step=0.0639, train_loss_epoch=0.0639]        Epoch 144:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0698, v_num=5, train_loss_step=0.0639, train_loss_epoch=0.0639]Epoch 144: 100%|##########| 1/1 [00:00<00:00, 16.03it/s, loss=0.0698, v_num=5, train_loss_step=0.0639, train_loss_epoch=0.0639]Epoch 144: 100%|##########| 1/1 [00:00<00:00, 15.92it/s, loss=0.0691, v_num=5, train_loss_step=0.0615, train_loss_epoch=0.0639]Epoch 144: 100%|##########| 1/1 [00:00<00:00, 15.78it/s, loss=0.0691, v_num=5, train_loss_step=0.0615, train_loss_epoch=0.0615]Epoch 144:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0691, v_num=5, train_loss_step=0.0615, train_loss_epoch=0.0615]        Epoch 145:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0691, v_num=5, train_loss_step=0.0615, train_loss_epoch=0.0615]Epoch 145: 100%|##########| 1/1 [00:00<00:00, 17.00it/s, loss=0.0691, v_num=5, train_loss_step=0.0615, train_loss_epoch=0.0615]Epoch 145: 100%|##########| 1/1 [00:00<00:00, 16.87it/s, loss=0.068, v_num=5, train_loss_step=0.0555, train_loss_epoch=0.0615] Epoch 145: 100%|##########| 1/1 [00:00<00:00, 16.67it/s, loss=0.068, v_num=5, train_loss_step=0.0555, train_loss_epoch=0.0555]Epoch 145:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.068, v_num=5, train_loss_step=0.0555, train_loss_epoch=0.0555]        Epoch 146:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.068, v_num=5, train_loss_step=0.0555, train_loss_epoch=0.0555]Epoch 146: 100%|##########| 1/1 [00:00<00:00, 17.25it/s, loss=0.068, v_num=5, train_loss_step=0.0555, train_loss_epoch=0.0555]Epoch 146: 100%|##########| 1/1 [00:00<00:00, 17.12it/s, loss=0.0675, v_num=5, train_loss_step=0.0654, train_loss_epoch=0.0555]Epoch 146: 100%|##########| 1/1 [00:00<00:00, 16.92it/s, loss=0.0675, v_num=5, train_loss_step=0.0654, train_loss_epoch=0.0654]Epoch 146:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0675, v_num=5, train_loss_step=0.0654, train_loss_epoch=0.0654]        Epoch 147:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0675, v_num=5, train_loss_step=0.0654, train_loss_epoch=0.0654]Epoch 147: 100%|##########| 1/1 [00:00<00:00, 14.67it/s, loss=0.0675, v_num=5, train_loss_step=0.0654, train_loss_epoch=0.0654]Epoch 147: 100%|##########| 1/1 [00:00<00:00, 14.57it/s, loss=0.067, v_num=5, train_loss_step=0.0603, train_loss_epoch=0.0654] Epoch 147: 100%|##########| 1/1 [00:00<00:00, 14.43it/s, loss=0.067, v_num=5, train_loss_step=0.0603, train_loss_epoch=0.0603]Epoch 147:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.067, v_num=5, train_loss_step=0.0603, train_loss_epoch=0.0603]        Epoch 148:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.067, v_num=5, train_loss_step=0.0603, train_loss_epoch=0.0603]Epoch 148: 100%|##########| 1/1 [00:00<00:00, 16.36it/s, loss=0.067, v_num=5, train_loss_step=0.0603, train_loss_epoch=0.0603]Epoch 148: 100%|##########| 1/1 [00:00<00:00, 16.25it/s, loss=0.0661, v_num=5, train_loss_step=0.0568, train_loss_epoch=0.0603]Epoch 148: 100%|##########| 1/1 [00:00<00:00, 16.07it/s, loss=0.0661, v_num=5, train_loss_step=0.0568, train_loss_epoch=0.0568]Epoch 148:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0661, v_num=5, train_loss_step=0.0568, train_loss_epoch=0.0568]        Epoch 149:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0661, v_num=5, train_loss_step=0.0568, train_loss_epoch=0.0568]Epoch 149: 100%|##########| 1/1 [00:00<00:00, 17.36it/s, loss=0.0661, v_num=5, train_loss_step=0.0568, train_loss_epoch=0.0568]Epoch 149: 100%|##########| 1/1 [00:00<00:00, 17.22it/s, loss=0.065, v_num=5, train_loss_step=0.057, train_loss_epoch=0.0568]  Epoch 149: 100%|##########| 1/1 [00:00<00:00, 16.86it/s, loss=0.065, v_num=5, train_loss_step=0.057, train_loss_epoch=0.057] Epoch 149:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.065, v_num=5, train_loss_step=0.057, train_loss_epoch=0.057]        Epoch 150:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.065, v_num=5, train_loss_step=0.057, train_loss_epoch=0.057]Epoch 150: 100%|##########| 1/1 [00:00<00:00, 17.02it/s, loss=0.065, v_num=5, train_loss_step=0.057, train_loss_epoch=0.057]Epoch 150: 100%|##########| 1/1 [00:00<00:00, 16.89it/s, loss=0.065, v_num=5, train_loss_step=0.0715, train_loss_epoch=0.057]Epoch 150: 100%|##########| 1/1 [00:00<00:00, 16.72it/s, loss=0.065, v_num=5, train_loss_step=0.0715, train_loss_epoch=0.0715]Epoch 150:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.065, v_num=5, train_loss_step=0.0715, train_loss_epoch=0.0715]        Epoch 151:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.065, v_num=5, train_loss_step=0.0715, train_loss_epoch=0.0715]Epoch 151: 100%|##########| 1/1 [00:00<00:00, 16.94it/s, loss=0.065, v_num=5, train_loss_step=0.0715, train_loss_epoch=0.0715]Epoch 151: 100%|##########| 1/1 [00:00<00:00, 16.82it/s, loss=0.0642, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0715]Epoch 151: 100%|##########| 1/1 [00:00<00:00, 16.64it/s, loss=0.0642, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0534]Epoch 151:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0642, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0534]        Epoch 152:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0642, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0534]Epoch 152: 100%|##########| 1/1 [00:00<00:00, 16.61it/s, loss=0.0642, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0534]Epoch 152: 100%|##########| 1/1 [00:00<00:00, 16.49it/s, loss=0.0638, v_num=5, train_loss_step=0.0649, train_loss_epoch=0.0534]Epoch 152: 100%|##########| 1/1 [00:00<00:00, 16.32it/s, loss=0.0638, v_num=5, train_loss_step=0.0649, train_loss_epoch=0.0649]Epoch 152:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0638, v_num=5, train_loss_step=0.0649, train_loss_epoch=0.0649]        Epoch 153:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0638, v_num=5, train_loss_step=0.0649, train_loss_epoch=0.0649]Epoch 153: 100%|##########| 1/1 [00:00<00:00, 16.75it/s, loss=0.0638, v_num=5, train_loss_step=0.0649, train_loss_epoch=0.0649]Epoch 153: 100%|##########| 1/1 [00:00<00:00, 16.64it/s, loss=0.0633, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0649]Epoch 153: 100%|##########| 1/1 [00:00<00:00, 16.47it/s, loss=0.0633, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 153:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0633, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0633]        Epoch 154:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0633, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 154: 100%|##########| 1/1 [00:00<00:00, 17.25it/s, loss=0.0633, v_num=5, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 154: 100%|##########| 1/1 [00:00<00:00, 17.13it/s, loss=0.063, v_num=5, train_loss_step=0.060, train_loss_epoch=0.0633]  Epoch 154: 100%|##########| 1/1 [00:00<00:00, 16.95it/s, loss=0.063, v_num=5, train_loss_step=0.060, train_loss_epoch=0.060] Epoch 154:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.063, v_num=5, train_loss_step=0.060, train_loss_epoch=0.060]        Epoch 155:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.063, v_num=5, train_loss_step=0.060, train_loss_epoch=0.060]Epoch 155: 100%|##########| 1/1 [00:00<00:00, 16.76it/s, loss=0.063, v_num=5, train_loss_step=0.060, train_loss_epoch=0.060]Epoch 155: 100%|##########| 1/1 [00:00<00:00, 16.63it/s, loss=0.0631, v_num=5, train_loss_step=0.072, train_loss_epoch=0.060]Epoch 155: 100%|##########| 1/1 [00:00<00:00, 16.45it/s, loss=0.0631, v_num=5, train_loss_step=0.072, train_loss_epoch=0.072]Epoch 155:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0631, v_num=5, train_loss_step=0.072, train_loss_epoch=0.072]        Epoch 156:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0631, v_num=5, train_loss_step=0.072, train_loss_epoch=0.072]Epoch 156: 100%|##########| 1/1 [00:00<00:00, 16.55it/s, loss=0.0631, v_num=5, train_loss_step=0.072, train_loss_epoch=0.072]Epoch 156: 100%|##########| 1/1 [00:00<00:00, 16.43it/s, loss=0.0622, v_num=5, train_loss_step=0.0525, train_loss_epoch=0.072]Epoch 156: 100%|##########| 1/1 [00:00<00:00, 16.26it/s, loss=0.0622, v_num=5, train_loss_step=0.0525, train_loss_epoch=0.0525]Epoch 156:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0622, v_num=5, train_loss_step=0.0525, train_loss_epoch=0.0525]        Epoch 157:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0622, v_num=5, train_loss_step=0.0525, train_loss_epoch=0.0525]Epoch 157: 100%|##########| 1/1 [00:00<00:00, 17.09it/s, loss=0.0622, v_num=5, train_loss_step=0.0525, train_loss_epoch=0.0525]Epoch 157: 100%|##########| 1/1 [00:00<00:00, 16.96it/s, loss=0.0622, v_num=5, train_loss_step=0.0647, train_loss_epoch=0.0525]Epoch 157: 100%|##########| 1/1 [00:00<00:00, 16.77it/s, loss=0.0622, v_num=5, train_loss_step=0.0647, train_loss_epoch=0.0647]Epoch 157:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0622, v_num=5, train_loss_step=0.0647, train_loss_epoch=0.0647]        Epoch 158:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0622, v_num=5, train_loss_step=0.0647, train_loss_epoch=0.0647]Epoch 158: 100%|##########| 1/1 [00:00<00:00, 16.64it/s, loss=0.0622, v_num=5, train_loss_step=0.0647, train_loss_epoch=0.0647]Epoch 158: 100%|##########| 1/1 [00:00<00:00, 16.53it/s, loss=0.0618, v_num=5, train_loss_step=0.0546, train_loss_epoch=0.0647]Epoch 158: 100%|##########| 1/1 [00:00<00:00, 16.37it/s, loss=0.0618, v_num=5, train_loss_step=0.0546, train_loss_epoch=0.0546]Epoch 158:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0618, v_num=5, train_loss_step=0.0546, train_loss_epoch=0.0546]        Epoch 159:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0618, v_num=5, train_loss_step=0.0546, train_loss_epoch=0.0546]Epoch 159: 100%|##########| 1/1 [00:00<00:00, 17.14it/s, loss=0.0618, v_num=5, train_loss_step=0.0546, train_loss_epoch=0.0546]Epoch 159: 100%|##########| 1/1 [00:00<00:00, 17.01it/s, loss=0.0617, v_num=5, train_loss_step=0.0716, train_loss_epoch=0.0546]Epoch 159: 100%|##########| 1/1 [00:00<00:00, 16.82it/s, loss=0.0617, v_num=5, train_loss_step=0.0716, train_loss_epoch=0.0716]Epoch 159:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0617, v_num=5, train_loss_step=0.0716, train_loss_epoch=0.0716]        Epoch 160:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0617, v_num=5, train_loss_step=0.0716, train_loss_epoch=0.0716]Epoch 160: 100%|##########| 1/1 [00:00<00:00, 17.09it/s, loss=0.0617, v_num=5, train_loss_step=0.0716, train_loss_epoch=0.0716]Epoch 160: 100%|##########| 1/1 [00:00<00:00, 16.96it/s, loss=0.0613, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0716]Epoch 160: 100%|##########| 1/1 [00:00<00:00, 16.78it/s, loss=0.0613, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0549]Epoch 160:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0613, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0549]        Epoch 161:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0613, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0549]Epoch 161: 100%|##########| 1/1 [00:00<00:00, 17.52it/s, loss=0.0613, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0549]Epoch 161: 100%|##########| 1/1 [00:00<00:00, 17.39it/s, loss=0.0615, v_num=5, train_loss_step=0.0644, train_loss_epoch=0.0549]Epoch 161: 100%|##########| 1/1 [00:00<00:00, 17.21it/s, loss=0.0615, v_num=5, train_loss_step=0.0644, train_loss_epoch=0.0644]Epoch 161:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0615, v_num=5, train_loss_step=0.0644, train_loss_epoch=0.0644]        Epoch 162:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0615, v_num=5, train_loss_step=0.0644, train_loss_epoch=0.0644]Epoch 162: 100%|##########| 1/1 [00:00<00:00, 17.40it/s, loss=0.0615, v_num=5, train_loss_step=0.0644, train_loss_epoch=0.0644]Epoch 162: 100%|##########| 1/1 [00:00<00:00, 17.27it/s, loss=0.0615, v_num=5, train_loss_step=0.061, train_loss_epoch=0.0644] Epoch 162: 100%|##########| 1/1 [00:00<00:00, 17.09it/s, loss=0.0615, v_num=5, train_loss_step=0.061, train_loss_epoch=0.061] Epoch 162:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0615, v_num=5, train_loss_step=0.061, train_loss_epoch=0.061]        Epoch 163:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0615, v_num=5, train_loss_step=0.061, train_loss_epoch=0.061]Epoch 163: 100%|##########| 1/1 [00:00<00:00, 17.39it/s, loss=0.0615, v_num=5, train_loss_step=0.061, train_loss_epoch=0.061]Epoch 163: 100%|##########| 1/1 [00:00<00:00, 17.26it/s, loss=0.0614, v_num=5, train_loss_step=0.0632, train_loss_epoch=0.061]Epoch 163: 100%|##########| 1/1 [00:00<00:00, 17.08it/s, loss=0.0614, v_num=5, train_loss_step=0.0632, train_loss_epoch=0.0632]Epoch 163:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0614, v_num=5, train_loss_step=0.0632, train_loss_epoch=0.0632]        Epoch 164:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0614, v_num=5, train_loss_step=0.0632, train_loss_epoch=0.0632]Epoch 164: 100%|##########| 1/1 [00:00<00:00, 17.24it/s, loss=0.0614, v_num=5, train_loss_step=0.0632, train_loss_epoch=0.0632]Epoch 164: 100%|##########| 1/1 [00:00<00:00, 17.10it/s, loss=0.0611, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0632]Epoch 164: 100%|##########| 1/1 [00:00<00:00, 16.92it/s, loss=0.0611, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0549]Epoch 164:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0611, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0549]        Epoch 165:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0611, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0549]Epoch 165: 100%|##########| 1/1 [00:00<00:00, 16.64it/s, loss=0.0611, v_num=5, train_loss_step=0.0549, train_loss_epoch=0.0549]Epoch 165: 100%|##########| 1/1 [00:00<00:00, 16.52it/s, loss=0.0613, v_num=5, train_loss_step=0.0598, train_loss_epoch=0.0549]Epoch 165: 100%|##########| 1/1 [00:00<00:00, 16.33it/s, loss=0.0613, v_num=5, train_loss_step=0.0598, train_loss_epoch=0.0598]Epoch 165:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0613, v_num=5, train_loss_step=0.0598, train_loss_epoch=0.0598]        Epoch 166:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0613, v_num=5, train_loss_step=0.0598, train_loss_epoch=0.0598]Epoch 166: 100%|##########| 1/1 [00:00<00:00, 16.40it/s, loss=0.0613, v_num=5, train_loss_step=0.0598, train_loss_epoch=0.0598]Epoch 166: 100%|##########| 1/1 [00:00<00:00, 16.28it/s, loss=0.0605, v_num=5, train_loss_step=0.0488, train_loss_epoch=0.0598]Epoch 166: 100%|##########| 1/1 [00:00<00:00, 16.10it/s, loss=0.0605, v_num=5, train_loss_step=0.0488, train_loss_epoch=0.0488]Epoch 166:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0605, v_num=5, train_loss_step=0.0488, train_loss_epoch=0.0488]        Epoch 167:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0605, v_num=5, train_loss_step=0.0488, train_loss_epoch=0.0488]Epoch 167: 100%|##########| 1/1 [00:00<00:00, 17.26it/s, loss=0.0605, v_num=5, train_loss_step=0.0488, train_loss_epoch=0.0488]Epoch 167: 100%|##########| 1/1 [00:00<00:00, 17.13it/s, loss=0.0605, v_num=5, train_loss_step=0.0605, train_loss_epoch=0.0488]Epoch 167: 100%|##########| 1/1 [00:00<00:00, 16.95it/s, loss=0.0605, v_num=5, train_loss_step=0.0605, train_loss_epoch=0.0605]Epoch 167:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0605, v_num=5, train_loss_step=0.0605, train_loss_epoch=0.0605]        Epoch 168:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0605, v_num=5, train_loss_step=0.0605, train_loss_epoch=0.0605]Epoch 168: 100%|##########| 1/1 [00:00<00:00, 16.27it/s, loss=0.0605, v_num=5, train_loss_step=0.0605, train_loss_epoch=0.0605]Epoch 168: 100%|##########| 1/1 [00:00<00:00, 16.15it/s, loss=0.0603, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0605]Epoch 168: 100%|##########| 1/1 [00:00<00:00, 15.98it/s, loss=0.0603, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0534]Epoch 168:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0603, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0534]        Epoch 169:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0603, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0534]Epoch 169: 100%|##########| 1/1 [00:00<00:00, 16.34it/s, loss=0.0603, v_num=5, train_loss_step=0.0534, train_loss_epoch=0.0534]Epoch 169: 100%|##########| 1/1 [00:00<00:00, 16.22it/s, loss=0.0599, v_num=5, train_loss_step=0.0485, train_loss_epoch=0.0534]Epoch 169: 100%|##########| 1/1 [00:00<00:00, 16.05it/s, loss=0.0599, v_num=5, train_loss_step=0.0485, train_loss_epoch=0.0485]Epoch 169:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0599, v_num=5, train_loss_step=0.0485, train_loss_epoch=0.0485]        Epoch 170:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0599, v_num=5, train_loss_step=0.0485, train_loss_epoch=0.0485]Epoch 170: 100%|##########| 1/1 [00:00<00:00, 15.93it/s, loss=0.0599, v_num=5, train_loss_step=0.0485, train_loss_epoch=0.0485]Epoch 170: 100%|##########| 1/1 [00:00<00:00, 15.80it/s, loss=0.0592, v_num=5, train_loss_step=0.0578, train_loss_epoch=0.0485]Epoch 170: 100%|##########| 1/1 [00:00<00:00, 15.63it/s, loss=0.0592, v_num=5, train_loss_step=0.0578, train_loss_epoch=0.0578]Epoch 170:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0592, v_num=5, train_loss_step=0.0578, train_loss_epoch=0.0578]        Epoch 171:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0592, v_num=5, train_loss_step=0.0578, train_loss_epoch=0.0578]Epoch 171: 100%|##########| 1/1 [00:00<00:00, 16.43it/s, loss=0.0592, v_num=5, train_loss_step=0.0578, train_loss_epoch=0.0578]Epoch 171: 100%|##########| 1/1 [00:00<00:00, 16.31it/s, loss=0.0588, v_num=5, train_loss_step=0.0461, train_loss_epoch=0.0578]Epoch 171: 100%|##########| 1/1 [00:00<00:00, 16.13it/s, loss=0.0588, v_num=5, train_loss_step=0.0461, train_loss_epoch=0.0461]Epoch 171:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0588, v_num=5, train_loss_step=0.0461, train_loss_epoch=0.0461]        Epoch 172:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0588, v_num=5, train_loss_step=0.0461, train_loss_epoch=0.0461]Epoch 172: 100%|##########| 1/1 [00:00<00:00, 16.59it/s, loss=0.0588, v_num=5, train_loss_step=0.0461, train_loss_epoch=0.0461]Epoch 172: 100%|##########| 1/1 [00:00<00:00, 16.47it/s, loss=0.0584, v_num=5, train_loss_step=0.0558, train_loss_epoch=0.0461]Epoch 172: 100%|##########| 1/1 [00:00<00:00, 16.30it/s, loss=0.0584, v_num=5, train_loss_step=0.0558, train_loss_epoch=0.0558]Epoch 172:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0584, v_num=5, train_loss_step=0.0558, train_loss_epoch=0.0558]        Epoch 173:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0584, v_num=5, train_loss_step=0.0558, train_loss_epoch=0.0558]Epoch 173: 100%|##########| 1/1 [00:00<00:00, 16.79it/s, loss=0.0584, v_num=5, train_loss_step=0.0558, train_loss_epoch=0.0558]Epoch 173: 100%|##########| 1/1 [00:00<00:00, 16.67it/s, loss=0.0578, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0558]Epoch 173: 100%|##########| 1/1 [00:00<00:00, 16.50it/s, loss=0.0578, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0516]Epoch 173:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0578, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0516]        Epoch 174:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0578, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0516]Epoch 174: 100%|##########| 1/1 [00:00<00:00, 17.40it/s, loss=0.0578, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0516]Epoch 174: 100%|##########| 1/1 [00:00<00:00, 17.26it/s, loss=0.0574, v_num=5, train_loss_step=0.0514, train_loss_epoch=0.0516]Epoch 174: 100%|##########| 1/1 [00:00<00:00, 17.07it/s, loss=0.0574, v_num=5, train_loss_step=0.0514, train_loss_epoch=0.0514]Epoch 174:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0574, v_num=5, train_loss_step=0.0514, train_loss_epoch=0.0514]        Epoch 175:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0574, v_num=5, train_loss_step=0.0514, train_loss_epoch=0.0514]Epoch 175: 100%|##########| 1/1 [00:00<00:00, 17.28it/s, loss=0.0574, v_num=5, train_loss_step=0.0514, train_loss_epoch=0.0514]Epoch 175: 100%|##########| 1/1 [00:00<00:00, 17.14it/s, loss=0.0562, v_num=5, train_loss_step=0.0494, train_loss_epoch=0.0514]Epoch 175: 100%|##########| 1/1 [00:00<00:00, 16.95it/s, loss=0.0562, v_num=5, train_loss_step=0.0494, train_loss_epoch=0.0494]Epoch 175:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0562, v_num=5, train_loss_step=0.0494, train_loss_epoch=0.0494]        Epoch 176:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0562, v_num=5, train_loss_step=0.0494, train_loss_epoch=0.0494]Epoch 176: 100%|##########| 1/1 [00:00<00:00, 16.61it/s, loss=0.0562, v_num=5, train_loss_step=0.0494, train_loss_epoch=0.0494]Epoch 176: 100%|##########| 1/1 [00:00<00:00, 16.49it/s, loss=0.056, v_num=5, train_loss_step=0.0478, train_loss_epoch=0.0494] Epoch 176: 100%|##########| 1/1 [00:00<00:00, 16.31it/s, loss=0.056, v_num=5, train_loss_step=0.0478, train_loss_epoch=0.0478]Epoch 176:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.056, v_num=5, train_loss_step=0.0478, train_loss_epoch=0.0478]        Epoch 177:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.056, v_num=5, train_loss_step=0.0478, train_loss_epoch=0.0478]Epoch 177: 100%|##########| 1/1 [00:00<00:00, 16.91it/s, loss=0.056, v_num=5, train_loss_step=0.0478, train_loss_epoch=0.0478]Epoch 177: 100%|##########| 1/1 [00:00<00:00, 16.79it/s, loss=0.0553, v_num=5, train_loss_step=0.0515, train_loss_epoch=0.0478]Epoch 177: 100%|##########| 1/1 [00:00<00:00, 16.62it/s, loss=0.0553, v_num=5, train_loss_step=0.0515, train_loss_epoch=0.0515]Epoch 177:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0553, v_num=5, train_loss_step=0.0515, train_loss_epoch=0.0515]        Epoch 178:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0553, v_num=5, train_loss_step=0.0515, train_loss_epoch=0.0515]Epoch 178: 100%|##########| 1/1 [00:00<00:00, 16.42it/s, loss=0.0553, v_num=5, train_loss_step=0.0515, train_loss_epoch=0.0515]Epoch 178: 100%|##########| 1/1 [00:00<00:00, 16.31it/s, loss=0.0549, v_num=5, train_loss_step=0.0464, train_loss_epoch=0.0515]Epoch 178: 100%|##########| 1/1 [00:00<00:00, 16.14it/s, loss=0.0549, v_num=5, train_loss_step=0.0464, train_loss_epoch=0.0464]Epoch 178:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0549, v_num=5, train_loss_step=0.0464, train_loss_epoch=0.0464]        Epoch 179:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0549, v_num=5, train_loss_step=0.0464, train_loss_epoch=0.0464]Epoch 179: 100%|##########| 1/1 [00:00<00:00, 17.02it/s, loss=0.0549, v_num=5, train_loss_step=0.0464, train_loss_epoch=0.0464]Epoch 179: 100%|##########| 1/1 [00:00<00:00, 16.90it/s, loss=0.0537, v_num=5, train_loss_step=0.046, train_loss_epoch=0.0464] Epoch 179: 100%|##########| 1/1 [00:00<00:00, 16.73it/s, loss=0.0537, v_num=5, train_loss_step=0.046, train_loss_epoch=0.046] Epoch 179:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0537, v_num=5, train_loss_step=0.046, train_loss_epoch=0.046]        Epoch 180:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0537, v_num=5, train_loss_step=0.046, train_loss_epoch=0.046]Epoch 180: 100%|##########| 1/1 [00:00<00:00, 16.38it/s, loss=0.0537, v_num=5, train_loss_step=0.046, train_loss_epoch=0.046]Epoch 180: 100%|##########| 1/1 [00:00<00:00, 16.25it/s, loss=0.0533, v_num=5, train_loss_step=0.0469, train_loss_epoch=0.046]Epoch 180: 100%|##########| 1/1 [00:00<00:00, 16.08it/s, loss=0.0533, v_num=5, train_loss_step=0.0469, train_loss_epoch=0.0469]Epoch 180:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0533, v_num=5, train_loss_step=0.0469, train_loss_epoch=0.0469]        Epoch 181:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0533, v_num=5, train_loss_step=0.0469, train_loss_epoch=0.0469]Epoch 181: 100%|##########| 1/1 [00:00<00:00, 16.42it/s, loss=0.0533, v_num=5, train_loss_step=0.0469, train_loss_epoch=0.0469]Epoch 181: 100%|##########| 1/1 [00:00<00:00, 16.30it/s, loss=0.0521, v_num=5, train_loss_step=0.0407, train_loss_epoch=0.0469]Epoch 181: 100%|##########| 1/1 [00:00<00:00, 16.13it/s, loss=0.0521, v_num=5, train_loss_step=0.0407, train_loss_epoch=0.0407]Epoch 181:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0521, v_num=5, train_loss_step=0.0407, train_loss_epoch=0.0407]        Epoch 182:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0521, v_num=5, train_loss_step=0.0407, train_loss_epoch=0.0407]Epoch 182: 100%|##########| 1/1 [00:00<00:00, 16.31it/s, loss=0.0521, v_num=5, train_loss_step=0.0407, train_loss_epoch=0.0407]Epoch 182: 100%|##########| 1/1 [00:00<00:00, 16.19it/s, loss=0.0513, v_num=5, train_loss_step=0.0456, train_loss_epoch=0.0407]Epoch 182: 100%|##########| 1/1 [00:00<00:00, 16.01it/s, loss=0.0513, v_num=5, train_loss_step=0.0456, train_loss_epoch=0.0456]Epoch 182:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0513, v_num=5, train_loss_step=0.0456, train_loss_epoch=0.0456]        Epoch 183:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0513, v_num=5, train_loss_step=0.0456, train_loss_epoch=0.0456]Epoch 183: 100%|##########| 1/1 [00:00<00:00, 16.74it/s, loss=0.0513, v_num=5, train_loss_step=0.0456, train_loss_epoch=0.0456]Epoch 183: 100%|##########| 1/1 [00:00<00:00, 16.61it/s, loss=0.0503, v_num=5, train_loss_step=0.0424, train_loss_epoch=0.0456]Epoch 183: 100%|##########| 1/1 [00:00<00:00, 16.44it/s, loss=0.0503, v_num=5, train_loss_step=0.0424, train_loss_epoch=0.0424]Epoch 183:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0503, v_num=5, train_loss_step=0.0424, train_loss_epoch=0.0424]        Epoch 184:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0503, v_num=5, train_loss_step=0.0424, train_loss_epoch=0.0424]Epoch 184: 100%|##########| 1/1 [00:00<00:00, 17.55it/s, loss=0.0503, v_num=5, train_loss_step=0.0424, train_loss_epoch=0.0424]Epoch 184: 100%|##########| 1/1 [00:00<00:00, 17.43it/s, loss=0.0495, v_num=5, train_loss_step=0.0395, train_loss_epoch=0.0424]Epoch 184: 100%|##########| 1/1 [00:00<00:00, 17.27it/s, loss=0.0495, v_num=5, train_loss_step=0.0395, train_loss_epoch=0.0395]Epoch 184:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0495, v_num=5, train_loss_step=0.0395, train_loss_epoch=0.0395]        Epoch 185:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0495, v_num=5, train_loss_step=0.0395, train_loss_epoch=0.0395]Epoch 185: 100%|##########| 1/1 [00:00<00:00, 17.15it/s, loss=0.0495, v_num=5, train_loss_step=0.0395, train_loss_epoch=0.0395]Epoch 185: 100%|##########| 1/1 [00:00<00:00, 17.03it/s, loss=0.0489, v_num=5, train_loss_step=0.047, train_loss_epoch=0.0395] Epoch 185: 100%|##########| 1/1 [00:00<00:00, 16.85it/s, loss=0.0489, v_num=5, train_loss_step=0.047, train_loss_epoch=0.047] Epoch 185:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0489, v_num=5, train_loss_step=0.047, train_loss_epoch=0.047]        Epoch 186:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0489, v_num=5, train_loss_step=0.047, train_loss_epoch=0.047]Epoch 186: 100%|##########| 1/1 [00:00<00:00, 17.23it/s, loss=0.0489, v_num=5, train_loss_step=0.047, train_loss_epoch=0.047]Epoch 186: 100%|##########| 1/1 [00:00<00:00, 17.11it/s, loss=0.0484, v_num=5, train_loss_step=0.0391, train_loss_epoch=0.047]Epoch 186: 100%|##########| 1/1 [00:00<00:00, 16.94it/s, loss=0.0484, v_num=5, train_loss_step=0.0391, train_loss_epoch=0.0391]Epoch 186:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0484, v_num=5, train_loss_step=0.0391, train_loss_epoch=0.0391]        Epoch 187:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0484, v_num=5, train_loss_step=0.0391, train_loss_epoch=0.0391]Epoch 187: 100%|##########| 1/1 [00:00<00:00, 16.96it/s, loss=0.0484, v_num=5, train_loss_step=0.0391, train_loss_epoch=0.0391]Epoch 187: 100%|##########| 1/1 [00:00<00:00, 16.83it/s, loss=0.0473, v_num=5, train_loss_step=0.040, train_loss_epoch=0.0391] Epoch 187: 100%|##########| 1/1 [00:00<00:00, 16.65it/s, loss=0.0473, v_num=5, train_loss_step=0.040, train_loss_epoch=0.040] Epoch 187:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0473, v_num=5, train_loss_step=0.040, train_loss_epoch=0.040]        Epoch 188:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0473, v_num=5, train_loss_step=0.040, train_loss_epoch=0.040]Epoch 188: 100%|##########| 1/1 [00:00<00:00, 16.74it/s, loss=0.0473, v_num=5, train_loss_step=0.040, train_loss_epoch=0.040]Epoch 188: 100%|##########| 1/1 [00:00<00:00, 16.62it/s, loss=0.0469, v_num=5, train_loss_step=0.0449, train_loss_epoch=0.040]Epoch 188: 100%|##########| 1/1 [00:00<00:00, 16.46it/s, loss=0.0469, v_num=5, train_loss_step=0.0449, train_loss_epoch=0.0449]Epoch 188:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0469, v_num=5, train_loss_step=0.0449, train_loss_epoch=0.0449]        Epoch 189:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0469, v_num=5, train_loss_step=0.0449, train_loss_epoch=0.0449]Epoch 189: 100%|##########| 1/1 [00:00<00:00, 17.21it/s, loss=0.0469, v_num=5, train_loss_step=0.0449, train_loss_epoch=0.0449]Epoch 189: 100%|##########| 1/1 [00:00<00:00, 17.08it/s, loss=0.0464, v_num=5, train_loss_step=0.0379, train_loss_epoch=0.0449]Epoch 189: 100%|##########| 1/1 [00:00<00:00, 16.89it/s, loss=0.0464, v_num=5, train_loss_step=0.0379, train_loss_epoch=0.0379]Epoch 189:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0464, v_num=5, train_loss_step=0.0379, train_loss_epoch=0.0379]        Epoch 190:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0464, v_num=5, train_loss_step=0.0379, train_loss_epoch=0.0379]Epoch 190: 100%|##########| 1/1 [00:00<00:00, 17.18it/s, loss=0.0464, v_num=5, train_loss_step=0.0379, train_loss_epoch=0.0379]Epoch 190: 100%|##########| 1/1 [00:00<00:00, 17.05it/s, loss=0.0456, v_num=5, train_loss_step=0.0415, train_loss_epoch=0.0379]Epoch 190: 100%|##########| 1/1 [00:00<00:00, 16.88it/s, loss=0.0456, v_num=5, train_loss_step=0.0415, train_loss_epoch=0.0415]Epoch 190:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0456, v_num=5, train_loss_step=0.0415, train_loss_epoch=0.0415]        Epoch 191:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0456, v_num=5, train_loss_step=0.0415, train_loss_epoch=0.0415]Epoch 191: 100%|##########| 1/1 [00:00<00:00, 17.41it/s, loss=0.0456, v_num=5, train_loss_step=0.0415, train_loss_epoch=0.0415]Epoch 191: 100%|##########| 1/1 [00:00<00:00, 17.25it/s, loss=0.0455, v_num=5, train_loss_step=0.0454, train_loss_epoch=0.0415]Epoch 191: 100%|##########| 1/1 [00:00<00:00, 17.07it/s, loss=0.0455, v_num=5, train_loss_step=0.0454, train_loss_epoch=0.0454]Epoch 191:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0455, v_num=5, train_loss_step=0.0454, train_loss_epoch=0.0454]        Epoch 192:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0455, v_num=5, train_loss_step=0.0454, train_loss_epoch=0.0454]Epoch 192: 100%|##########| 1/1 [00:00<00:00, 16.88it/s, loss=0.0455, v_num=5, train_loss_step=0.0454, train_loss_epoch=0.0454]Epoch 192: 100%|##########| 1/1 [00:00<00:00, 16.76it/s, loss=0.0447, v_num=5, train_loss_step=0.0398, train_loss_epoch=0.0454]Epoch 192: 100%|##########| 1/1 [00:00<00:00, 16.59it/s, loss=0.0447, v_num=5, train_loss_step=0.0398, train_loss_epoch=0.0398]Epoch 192:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0447, v_num=5, train_loss_step=0.0398, train_loss_epoch=0.0398]        Epoch 193:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0447, v_num=5, train_loss_step=0.0398, train_loss_epoch=0.0398]Epoch 193: 100%|##########| 1/1 [00:00<00:00, 16.27it/s, loss=0.0447, v_num=5, train_loss_step=0.0398, train_loss_epoch=0.0398]Epoch 193: 100%|##########| 1/1 [00:00<00:00, 16.16it/s, loss=0.0447, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0398]Epoch 193: 100%|##########| 1/1 [00:00<00:00, 16.01it/s, loss=0.0447, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0516]Epoch 193:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0447, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0516]        Epoch 194:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0447, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0516]Epoch 194: 100%|##########| 1/1 [00:00<00:00, 16.43it/s, loss=0.0447, v_num=5, train_loss_step=0.0516, train_loss_epoch=0.0516]Epoch 194: 100%|##########| 1/1 [00:00<00:00, 16.31it/s, loss=0.0441, v_num=5, train_loss_step=0.0389, train_loss_epoch=0.0516]Epoch 194: 100%|##########| 1/1 [00:00<00:00, 16.15it/s, loss=0.0441, v_num=5, train_loss_step=0.0389, train_loss_epoch=0.0389]Epoch 194:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0441, v_num=5, train_loss_step=0.0389, train_loss_epoch=0.0389]        Epoch 195:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0441, v_num=5, train_loss_step=0.0389, train_loss_epoch=0.0389]Epoch 195: 100%|##########| 1/1 [00:00<00:00, 17.21it/s, loss=0.0441, v_num=5, train_loss_step=0.0389, train_loss_epoch=0.0389]Epoch 195: 100%|##########| 1/1 [00:00<00:00, 17.09it/s, loss=0.0439, v_num=5, train_loss_step=0.0458, train_loss_epoch=0.0389]Epoch 195: 100%|##########| 1/1 [00:00<00:00, 16.93it/s, loss=0.0439, v_num=5, train_loss_step=0.0458, train_loss_epoch=0.0458]Epoch 195:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0439, v_num=5, train_loss_step=0.0458, train_loss_epoch=0.0458]        Epoch 196:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0439, v_num=5, train_loss_step=0.0458, train_loss_epoch=0.0458]Epoch 196: 100%|##########| 1/1 [00:00<00:00, 16.20it/s, loss=0.0439, v_num=5, train_loss_step=0.0458, train_loss_epoch=0.0458]Epoch 196: 100%|##########| 1/1 [00:00<00:00, 16.08it/s, loss=0.0434, v_num=5, train_loss_step=0.0378, train_loss_epoch=0.0458]Epoch 196: 100%|##########| 1/1 [00:00<00:00, 15.91it/s, loss=0.0434, v_num=5, train_loss_step=0.0378, train_loss_epoch=0.0378]Epoch 196:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0434, v_num=5, train_loss_step=0.0378, train_loss_epoch=0.0378]        Epoch 197:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0434, v_num=5, train_loss_step=0.0378, train_loss_epoch=0.0378]Epoch 197: 100%|##########| 1/1 [00:00<00:00, 16.69it/s, loss=0.0434, v_num=5, train_loss_step=0.0378, train_loss_epoch=0.0378]Epoch 197: 100%|##########| 1/1 [00:00<00:00, 16.53it/s, loss=0.0431, v_num=5, train_loss_step=0.0451, train_loss_epoch=0.0378]Epoch 197: 100%|##########| 1/1 [00:00<00:00, 16.35it/s, loss=0.0431, v_num=5, train_loss_step=0.0451, train_loss_epoch=0.0451]Epoch 197:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0431, v_num=5, train_loss_step=0.0451, train_loss_epoch=0.0451]        Epoch 198:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0431, v_num=5, train_loss_step=0.0451, train_loss_epoch=0.0451]Epoch 198: 100%|##########| 1/1 [00:00<00:00, 16.81it/s, loss=0.0431, v_num=5, train_loss_step=0.0451, train_loss_epoch=0.0451]Epoch 198: 100%|##########| 1/1 [00:00<00:00, 16.69it/s, loss=0.0429, v_num=5, train_loss_step=0.0422, train_loss_epoch=0.0451]Epoch 198: 100%|##########| 1/1 [00:00<00:00, 16.51it/s, loss=0.0429, v_num=5, train_loss_step=0.0422, train_loss_epoch=0.0422]Epoch 198:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0429, v_num=5, train_loss_step=0.0422, train_loss_epoch=0.0422]        Epoch 199:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0429, v_num=5, train_loss_step=0.0422, train_loss_epoch=0.0422]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 17.06it/s, loss=0.0429, v_num=5, train_loss_step=0.0422, train_loss_epoch=0.0422]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 16.94it/s, loss=0.0425, v_num=5, train_loss_step=0.0384, train_loss_epoch=0.0422]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 16.56it/s, loss=0.0425, v_num=5, train_loss_step=0.0384, train_loss_epoch=0.0384]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 11.25it/s, loss=0.0425, v_num=5, train_loss_step=0.0384, train_loss_epoch=0.0384]
Predicting: 1it [00:00, ?it/s]Predicting:   0%|          | 0/1 [00:00<00:00, -28926.23it/s]Predicting DataLoader 0:   0%|          | 0/1 [00:00<?, ?it/s]Predicting DataLoader 0: 100%|##########| 1/1 [00:00<00:00, 100.87it/s]Predicting DataLoader 0: 100%|##########| 1/1 [00:00<00:00, 97.36it/s] 

pd.concat([Y_train_df[Y_train_df['unique_id']==1.0], Y_test_df[Y_test_df['unique_id']==1.0]]).drop('unique_id', axis=1).set_index('ds').plot()
pd.concat([Y_train_df[Y_train_df['unique_id']==2.0], Y_test_df[Y_test_df['unique_id']==2.0]]).drop('unique_id', axis=1).set_index('ds').plot()