LSTM

The Long Short-Term Memory Recurrent Neural Network (LSTM), uses a multilayer LSTM encoder and an MLP decoder. It builds upon the LSTM-cell that improves the exploding and vanishing gradients of classic RNN’s. This network has been extensively used in sequential prediction tasks like language modeling, phonetic labeling, and forecasting.

References
-Jeffrey L. Elman (1990). “Finding Structure in Time”.
-Haşim Sak, Andrew Senior, Françoise Beaufays (2014). “Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition.”

source

LSTM

 LSTM (input_size:int, h:int, state_hsize:int=200, step_size:int=1,
       n_layers:int=2, bias:bool=True, dropout:float=0.0,
       learning_rate:float=0.001, normalize:bool=True,
       loss=<neuralforecast.losses.pytorch.MAE object at 0x7f8744bf6320>,
       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 = LSTM(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['LSTM'] = 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, 11.72it/s]Epoch 0: 100%|##########| 1/1 [00:00<00:00, 11.64it/s, loss=0.753, v_num=3, train_loss_step=0.753]Epoch 0: 100%|##########| 1/1 [00:00<00:00, 11.54it/s, loss=0.753, v_num=3, train_loss_step=0.753, train_loss_epoch=0.753]Epoch 0:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.753, v_num=3, train_loss_step=0.753, train_loss_epoch=0.753]        Epoch 1:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.753, v_num=3, train_loss_step=0.753, train_loss_epoch=0.753]Epoch 1: 100%|##########| 1/1 [00:00<00:00, 19.34it/s, loss=0.753, v_num=3, train_loss_step=0.753, train_loss_epoch=0.753]Epoch 1: 100%|##########| 1/1 [00:00<00:00, 19.15it/s, loss=0.743, v_num=3, train_loss_step=0.733, train_loss_epoch=0.753]Epoch 1: 100%|##########| 1/1 [00:00<00:00, 18.91it/s, loss=0.743, v_num=3, train_loss_step=0.733, train_loss_epoch=0.733]Epoch 1:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.743, v_num=3, train_loss_step=0.733, train_loss_epoch=0.733]        Epoch 2:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.743, v_num=3, train_loss_step=0.733, train_loss_epoch=0.733]Epoch 2: 100%|##########| 1/1 [00:00<00:00, 20.12it/s, loss=0.743, v_num=3, train_loss_step=0.733, train_loss_epoch=0.733]Epoch 2: 100%|##########| 1/1 [00:00<00:00, 19.97it/s, loss=0.732, v_num=3, train_loss_step=0.711, train_loss_epoch=0.733]Epoch 2: 100%|##########| 1/1 [00:00<00:00, 19.72it/s, loss=0.732, v_num=3, train_loss_step=0.711, train_loss_epoch=0.711]Epoch 2:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.732, v_num=3, train_loss_step=0.711, train_loss_epoch=0.711]        Epoch 3:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.732, v_num=3, train_loss_step=0.711, train_loss_epoch=0.711]Epoch 3: 100%|##########| 1/1 [00:00<00:00, 21.21it/s, loss=0.732, v_num=3, train_loss_step=0.711, train_loss_epoch=0.711]Epoch 3: 100%|##########| 1/1 [00:00<00:00, 21.00it/s, loss=0.72, v_num=3, train_loss_step=0.682, train_loss_epoch=0.711] Epoch 3: 100%|##########| 1/1 [00:00<00:00, 20.72it/s, loss=0.72, v_num=3, train_loss_step=0.682, train_loss_epoch=0.682]Epoch 3:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.72, v_num=3, train_loss_step=0.682, train_loss_epoch=0.682]        Epoch 4:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.72, v_num=3, train_loss_step=0.682, train_loss_epoch=0.682]Epoch 4: 100%|##########| 1/1 [00:00<00:00, 20.62it/s, loss=0.72, v_num=3, train_loss_step=0.682, train_loss_epoch=0.682]Epoch 4: 100%|##########| 1/1 [00:00<00:00, 20.44it/s, loss=0.704, v_num=3, train_loss_step=0.639, train_loss_epoch=0.682]Epoch 4: 100%|##########| 1/1 [00:00<00:00, 20.18it/s, loss=0.704, v_num=3, train_loss_step=0.639, train_loss_epoch=0.639]Epoch 4:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.704, v_num=3, train_loss_step=0.639, train_loss_epoch=0.639]        Epoch 5:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.704, v_num=3, train_loss_step=0.639, train_loss_epoch=0.639]Epoch 5: 100%|##########| 1/1 [00:00<00:00, 20.27it/s, loss=0.704, v_num=3, train_loss_step=0.639, train_loss_epoch=0.639]Epoch 5: 100%|##########| 1/1 [00:00<00:00, 20.03it/s, loss=0.682, v_num=3, train_loss_step=0.571, train_loss_epoch=0.639]Epoch 5: 100%|##########| 1/1 [00:00<00:00, 19.78it/s, loss=0.682, v_num=3, train_loss_step=0.571, train_loss_epoch=0.571]Epoch 5:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.682, v_num=3, train_loss_step=0.571, train_loss_epoch=0.571]        Epoch 6:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.682, v_num=3, train_loss_step=0.571, train_loss_epoch=0.571]Epoch 6: 100%|##########| 1/1 [00:00<00:00, 21.61it/s, loss=0.682, v_num=3, train_loss_step=0.571, train_loss_epoch=0.571]Epoch 6: 100%|##########| 1/1 [00:00<00:00, 21.43it/s, loss=0.653, v_num=3, train_loss_step=0.484, train_loss_epoch=0.571]Epoch 6: 100%|##########| 1/1 [00:00<00:00, 21.16it/s, loss=0.653, v_num=3, train_loss_step=0.484, train_loss_epoch=0.484]Epoch 6:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.653, v_num=3, train_loss_step=0.484, train_loss_epoch=0.484]        Epoch 7:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.653, v_num=3, train_loss_step=0.484, train_loss_epoch=0.484]Epoch 7: 100%|##########| 1/1 [00:00<00:00, 22.60it/s, loss=0.653, v_num=3, train_loss_step=0.484, train_loss_epoch=0.484]Epoch 7: 100%|##########| 1/1 [00:00<00:00, 22.36it/s, loss=0.627, v_num=3, train_loss_step=0.442, train_loss_epoch=0.484]Epoch 7: 100%|##########| 1/1 [00:00<00:00, 22.04it/s, loss=0.627, v_num=3, train_loss_step=0.442, train_loss_epoch=0.442]Epoch 7:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.627, v_num=3, train_loss_step=0.442, train_loss_epoch=0.442]        Epoch 8:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.627, v_num=3, train_loss_step=0.442, train_loss_epoch=0.442]Epoch 8: 100%|##########| 1/1 [00:00<00:00, 21.79it/s, loss=0.627, v_num=3, train_loss_step=0.442, train_loss_epoch=0.442]Epoch 8: 100%|##########| 1/1 [00:00<00:00, 21.62it/s, loss=0.609, v_num=3, train_loss_step=0.466, train_loss_epoch=0.442]Epoch 8: 100%|##########| 1/1 [00:00<00:00, 21.34it/s, loss=0.609, v_num=3, train_loss_step=0.466, train_loss_epoch=0.466]Epoch 8:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.609, v_num=3, train_loss_step=0.466, train_loss_epoch=0.466]        Epoch 9:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.609, v_num=3, train_loss_step=0.466, train_loss_epoch=0.466]Epoch 9: 100%|##########| 1/1 [00:00<00:00, 21.40it/s, loss=0.609, v_num=3, train_loss_step=0.466, train_loss_epoch=0.466]Epoch 9: 100%|##########| 1/1 [00:00<00:00, 21.15it/s, loss=0.596, v_num=3, train_loss_step=0.476, train_loss_epoch=0.466]Epoch 9: 100%|##########| 1/1 [00:00<00:00, 20.88it/s, loss=0.596, v_num=3, train_loss_step=0.476, train_loss_epoch=0.476]Epoch 9:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.596, v_num=3, train_loss_step=0.476, train_loss_epoch=0.476]        Epoch 10:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.596, v_num=3, train_loss_step=0.476, train_loss_epoch=0.476]Epoch 10: 100%|##########| 1/1 [00:00<00:00, 22.46it/s, loss=0.596, v_num=3, train_loss_step=0.476, train_loss_epoch=0.476]Epoch 10: 100%|##########| 1/1 [00:00<00:00, 22.29it/s, loss=0.584, v_num=3, train_loss_step=0.465, train_loss_epoch=0.476]Epoch 10: 100%|##########| 1/1 [00:00<00:00, 22.01it/s, loss=0.584, v_num=3, train_loss_step=0.465, train_loss_epoch=0.465]Epoch 10:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.584, v_num=3, train_loss_step=0.465, train_loss_epoch=0.465]        Epoch 11:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.584, v_num=3, train_loss_step=0.465, train_loss_epoch=0.465]Epoch 11: 100%|##########| 1/1 [00:00<00:00, 20.96it/s, loss=0.584, v_num=3, train_loss_step=0.465, train_loss_epoch=0.465]Epoch 11: 100%|##########| 1/1 [00:00<00:00, 20.69it/s, loss=0.572, v_num=3, train_loss_step=0.444, train_loss_epoch=0.465]Epoch 11: 100%|##########| 1/1 [00:00<00:00, 20.42it/s, loss=0.572, v_num=3, train_loss_step=0.444, train_loss_epoch=0.444]Epoch 11:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.572, v_num=3, train_loss_step=0.444, train_loss_epoch=0.444]        Epoch 12:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.572, v_num=3, train_loss_step=0.444, train_loss_epoch=0.444]Epoch 12: 100%|##########| 1/1 [00:00<00:00, 20.10it/s, loss=0.572, v_num=3, train_loss_step=0.444, train_loss_epoch=0.444]Epoch 12: 100%|##########| 1/1 [00:00<00:00, 19.93it/s, loss=0.561, v_num=3, train_loss_step=0.424, train_loss_epoch=0.444]Epoch 12: 100%|##########| 1/1 [00:00<00:00, 19.69it/s, loss=0.561, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]Epoch 12:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.561, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]        Epoch 13:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.561, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]Epoch 13: 100%|##########| 1/1 [00:00<00:00, 19.85it/s, loss=0.561, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]Epoch 13: 100%|##########| 1/1 [00:00<00:00, 19.61it/s, loss=0.55, v_num=3, train_loss_step=0.416, train_loss_epoch=0.424] Epoch 13: 100%|##########| 1/1 [00:00<00:00, 19.37it/s, loss=0.55, v_num=3, train_loss_step=0.416, train_loss_epoch=0.416]Epoch 13:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.55, v_num=3, train_loss_step=0.416, train_loss_epoch=0.416]        Epoch 14:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.55, v_num=3, train_loss_step=0.416, train_loss_epoch=0.416]Epoch 14: 100%|##########| 1/1 [00:00<00:00, 19.92it/s, loss=0.55, v_num=3, train_loss_step=0.416, train_loss_epoch=0.416]Epoch 14: 100%|##########| 1/1 [00:00<00:00, 19.75it/s, loss=0.542, v_num=3, train_loss_step=0.418, train_loss_epoch=0.416]Epoch 14: 100%|##########| 1/1 [00:00<00:00, 19.49it/s, loss=0.542, v_num=3, train_loss_step=0.418, train_loss_epoch=0.418]Epoch 14:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.542, v_num=3, train_loss_step=0.418, train_loss_epoch=0.418]        Epoch 15:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.542, v_num=3, train_loss_step=0.418, train_loss_epoch=0.418]Epoch 15: 100%|##########| 1/1 [00:00<00:00, 20.94it/s, loss=0.542, v_num=3, train_loss_step=0.418, train_loss_epoch=0.418]Epoch 15: 100%|##########| 1/1 [00:00<00:00, 20.68it/s, loss=0.534, v_num=3, train_loss_step=0.424, train_loss_epoch=0.418]Epoch 15: 100%|##########| 1/1 [00:00<00:00, 20.42it/s, loss=0.534, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]Epoch 15:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.534, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]        Epoch 16:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.534, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]Epoch 16: 100%|##########| 1/1 [00:00<00:00, 21.25it/s, loss=0.534, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]Epoch 16: 100%|##########| 1/1 [00:00<00:00, 21.09it/s, loss=0.528, v_num=3, train_loss_step=0.428, train_loss_epoch=0.424]Epoch 16: 100%|##########| 1/1 [00:00<00:00, 20.83it/s, loss=0.528, v_num=3, train_loss_step=0.428, train_loss_epoch=0.428]Epoch 16:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.528, v_num=3, train_loss_step=0.428, train_loss_epoch=0.428]        Epoch 17:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.528, v_num=3, train_loss_step=0.428, train_loss_epoch=0.428]Epoch 17: 100%|##########| 1/1 [00:00<00:00, 22.65it/s, loss=0.528, v_num=3, train_loss_step=0.428, train_loss_epoch=0.428]Epoch 17: 100%|##########| 1/1 [00:00<00:00, 22.42it/s, loss=0.522, v_num=3, train_loss_step=0.427, train_loss_epoch=0.428]Epoch 17: 100%|##########| 1/1 [00:00<00:00, 22.15it/s, loss=0.522, v_num=3, train_loss_step=0.427, train_loss_epoch=0.427]Epoch 17:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.522, v_num=3, train_loss_step=0.427, train_loss_epoch=0.427]        Epoch 18:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.522, v_num=3, train_loss_step=0.427, train_loss_epoch=0.427]Epoch 18: 100%|##########| 1/1 [00:00<00:00, 22.47it/s, loss=0.522, v_num=3, train_loss_step=0.427, train_loss_epoch=0.427]Epoch 18: 100%|##########| 1/1 [00:00<00:00, 22.31it/s, loss=0.517, v_num=3, train_loss_step=0.424, train_loss_epoch=0.427]Epoch 18: 100%|##########| 1/1 [00:00<00:00, 22.06it/s, loss=0.517, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]Epoch 18:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.517, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]        Epoch 19:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.517, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]Epoch 19: 100%|##########| 1/1 [00:00<00:00, 20.78it/s, loss=0.517, v_num=3, train_loss_step=0.424, train_loss_epoch=0.424]Epoch 19: 100%|##########| 1/1 [00:00<00:00, 20.59it/s, loss=0.512, v_num=3, train_loss_step=0.418, train_loss_epoch=0.424]Epoch 19: 100%|##########| 1/1 [00:00<00:00, 20.35it/s, loss=0.512, v_num=3, train_loss_step=0.418, train_loss_epoch=0.418]Epoch 19:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.512, v_num=3, train_loss_step=0.418, train_loss_epoch=0.418]        Epoch 20:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.512, v_num=3, train_loss_step=0.418, train_loss_epoch=0.418]Epoch 20: 100%|##########| 1/1 [00:00<00:00, 19.59it/s, loss=0.512, v_num=3, train_loss_step=0.418, train_loss_epoch=0.418]Epoch 20: 100%|##########| 1/1 [00:00<00:00, 19.34it/s, loss=0.495, v_num=3, train_loss_step=0.412, train_loss_epoch=0.418]Epoch 20: 100%|##########| 1/1 [00:00<00:00, 19.11it/s, loss=0.495, v_num=3, train_loss_step=0.412, train_loss_epoch=0.412]Epoch 20:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.495, v_num=3, train_loss_step=0.412, train_loss_epoch=0.412]        Epoch 21:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.495, v_num=3, train_loss_step=0.412, train_loss_epoch=0.412]Epoch 21: 100%|##########| 1/1 [00:00<00:00, 18.56it/s, loss=0.495, v_num=3, train_loss_step=0.412, train_loss_epoch=0.412]Epoch 21: 100%|##########| 1/1 [00:00<00:00, 18.40it/s, loss=0.479, v_num=3, train_loss_step=0.407, train_loss_epoch=0.412]Epoch 21: 100%|##########| 1/1 [00:00<00:00, 18.14it/s, loss=0.479, v_num=3, train_loss_step=0.407, train_loss_epoch=0.407]Epoch 21:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.479, v_num=3, train_loss_step=0.407, train_loss_epoch=0.407]        Epoch 22:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.479, v_num=3, train_loss_step=0.407, train_loss_epoch=0.407]Epoch 22: 100%|##########| 1/1 [00:00<00:00, 20.54it/s, loss=0.479, v_num=3, train_loss_step=0.407, train_loss_epoch=0.407]Epoch 22: 100%|##########| 1/1 [00:00<00:00, 20.33it/s, loss=0.463, v_num=3, train_loss_step=0.403, train_loss_epoch=0.407]Epoch 22: 100%|##########| 1/1 [00:00<00:00, 20.04it/s, loss=0.463, v_num=3, train_loss_step=0.403, train_loss_epoch=0.403]Epoch 22:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.463, v_num=3, train_loss_step=0.403, train_loss_epoch=0.403]        Epoch 23:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.463, v_num=3, train_loss_step=0.403, train_loss_epoch=0.403]Epoch 23: 100%|##########| 1/1 [00:00<00:00, 21.59it/s, loss=0.463, v_num=3, train_loss_step=0.403, train_loss_epoch=0.403]Epoch 23: 100%|##########| 1/1 [00:00<00:00, 21.38it/s, loss=0.449, v_num=3, train_loss_step=0.400, train_loss_epoch=0.403]Epoch 23: 100%|##########| 1/1 [00:00<00:00, 21.11it/s, loss=0.449, v_num=3, train_loss_step=0.400, train_loss_epoch=0.400]Epoch 23:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.449, v_num=3, train_loss_step=0.400, train_loss_epoch=0.400]        Epoch 24:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.449, v_num=3, train_loss_step=0.400, train_loss_epoch=0.400]Epoch 24: 100%|##########| 1/1 [00:00<00:00, 21.54it/s, loss=0.449, v_num=3, train_loss_step=0.400, train_loss_epoch=0.400]Epoch 24: 100%|##########| 1/1 [00:00<00:00, 21.30it/s, loss=0.437, v_num=3, train_loss_step=0.397, train_loss_epoch=0.400]Epoch 24: 100%|##########| 1/1 [00:00<00:00, 21.04it/s, loss=0.437, v_num=3, train_loss_step=0.397, train_loss_epoch=0.397]Epoch 24:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.437, v_num=3, train_loss_step=0.397, train_loss_epoch=0.397]        Epoch 25:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.437, v_num=3, train_loss_step=0.397, train_loss_epoch=0.397]Epoch 25: 100%|##########| 1/1 [00:00<00:00, 21.48it/s, loss=0.437, v_num=3, train_loss_step=0.397, train_loss_epoch=0.397]Epoch 25: 100%|##########| 1/1 [00:00<00:00, 21.29it/s, loss=0.428, v_num=3, train_loss_step=0.395, train_loss_epoch=0.397]Epoch 25: 100%|##########| 1/1 [00:00<00:00, 21.00it/s, loss=0.428, v_num=3, train_loss_step=0.395, train_loss_epoch=0.395]Epoch 25:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.428, v_num=3, train_loss_step=0.395, train_loss_epoch=0.395]        Epoch 26:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.428, v_num=3, train_loss_step=0.395, train_loss_epoch=0.395]Epoch 26: 100%|##########| 1/1 [00:00<00:00, 21.80it/s, loss=0.428, v_num=3, train_loss_step=0.395, train_loss_epoch=0.395]Epoch 26: 100%|##########| 1/1 [00:00<00:00, 21.53it/s, loss=0.424, v_num=3, train_loss_step=0.391, train_loss_epoch=0.395]Epoch 26: 100%|##########| 1/1 [00:00<00:00, 21.19it/s, loss=0.424, v_num=3, train_loss_step=0.391, train_loss_epoch=0.391]Epoch 26:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.424, v_num=3, train_loss_step=0.391, train_loss_epoch=0.391]        Epoch 27:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.424, v_num=3, train_loss_step=0.391, train_loss_epoch=0.391]Epoch 27: 100%|##########| 1/1 [00:00<00:00, 21.63it/s, loss=0.424, v_num=3, train_loss_step=0.391, train_loss_epoch=0.391]Epoch 27: 100%|##########| 1/1 [00:00<00:00, 21.48it/s, loss=0.421, v_num=3, train_loss_step=0.385, train_loss_epoch=0.391]Epoch 27: 100%|##########| 1/1 [00:00<00:00, 21.24it/s, loss=0.421, v_num=3, train_loss_step=0.385, train_loss_epoch=0.385]Epoch 27:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.421, v_num=3, train_loss_step=0.385, train_loss_epoch=0.385]        Epoch 28:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.421, v_num=3, train_loss_step=0.385, train_loss_epoch=0.385]Epoch 28: 100%|##########| 1/1 [00:00<00:00, 22.23it/s, loss=0.421, v_num=3, train_loss_step=0.385, train_loss_epoch=0.385]Epoch 28: 100%|##########| 1/1 [00:00<00:00, 22.04it/s, loss=0.416, v_num=3, train_loss_step=0.377, train_loss_epoch=0.385]Epoch 28: 100%|##########| 1/1 [00:00<00:00, 21.75it/s, loss=0.416, v_num=3, train_loss_step=0.377, train_loss_epoch=0.377]Epoch 28:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.416, v_num=3, train_loss_step=0.377, train_loss_epoch=0.377]        Epoch 29:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.416, v_num=3, train_loss_step=0.377, train_loss_epoch=0.377]Epoch 29: 100%|##########| 1/1 [00:00<00:00, 20.63it/s, loss=0.416, v_num=3, train_loss_step=0.377, train_loss_epoch=0.377]Epoch 29: 100%|##########| 1/1 [00:00<00:00, 20.40it/s, loss=0.411, v_num=3, train_loss_step=0.367, train_loss_epoch=0.377]Epoch 29: 100%|##########| 1/1 [00:00<00:00, 20.16it/s, loss=0.411, v_num=3, train_loss_step=0.367, train_loss_epoch=0.367]Epoch 29:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.411, v_num=3, train_loss_step=0.367, train_loss_epoch=0.367]        Epoch 30:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.411, v_num=3, train_loss_step=0.367, train_loss_epoch=0.367]Epoch 30: 100%|##########| 1/1 [00:00<00:00, 20.63it/s, loss=0.411, v_num=3, train_loss_step=0.367, train_loss_epoch=0.367]Epoch 30: 100%|##########| 1/1 [00:00<00:00, 20.46it/s, loss=0.406, v_num=3, train_loss_step=0.358, train_loss_epoch=0.367]Epoch 30: 100%|##########| 1/1 [00:00<00:00, 20.19it/s, loss=0.406, v_num=3, train_loss_step=0.358, train_loss_epoch=0.358]Epoch 30:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.406, v_num=3, train_loss_step=0.358, train_loss_epoch=0.358]        Epoch 31:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.406, v_num=3, train_loss_step=0.358, train_loss_epoch=0.358]Epoch 31: 100%|##########| 1/1 [00:00<00:00, 21.22it/s, loss=0.406, v_num=3, train_loss_step=0.358, train_loss_epoch=0.358]Epoch 31: 100%|##########| 1/1 [00:00<00:00, 21.05it/s, loss=0.401, v_num=3, train_loss_step=0.349, train_loss_epoch=0.358]Epoch 31: 100%|##########| 1/1 [00:00<00:00, 20.78it/s, loss=0.401, v_num=3, train_loss_step=0.349, train_loss_epoch=0.349]Epoch 31:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.401, v_num=3, train_loss_step=0.349, train_loss_epoch=0.349]        Epoch 32:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.401, v_num=3, train_loss_step=0.349, train_loss_epoch=0.349]Epoch 32: 100%|##########| 1/1 [00:00<00:00, 20.90it/s, loss=0.401, v_num=3, train_loss_step=0.349, train_loss_epoch=0.349]Epoch 32: 100%|##########| 1/1 [00:00<00:00, 20.73it/s, loss=0.397, v_num=3, train_loss_step=0.338, train_loss_epoch=0.349]Epoch 32: 100%|##########| 1/1 [00:00<00:00, 20.48it/s, loss=0.397, v_num=3, train_loss_step=0.338, train_loss_epoch=0.338]Epoch 32:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.397, v_num=3, train_loss_step=0.338, train_loss_epoch=0.338]        Epoch 33:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.397, v_num=3, train_loss_step=0.338, train_loss_epoch=0.338]Epoch 33: 100%|##########| 1/1 [00:00<00:00, 21.37it/s, loss=0.397, v_num=3, train_loss_step=0.338, train_loss_epoch=0.338]Epoch 33: 100%|##########| 1/1 [00:00<00:00, 21.18it/s, loss=0.392, v_num=3, train_loss_step=0.325, train_loss_epoch=0.338]Epoch 33: 100%|##########| 1/1 [00:00<00:00, 20.92it/s, loss=0.392, v_num=3, train_loss_step=0.325, train_loss_epoch=0.325]Epoch 33:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.392, v_num=3, train_loss_step=0.325, train_loss_epoch=0.325]        Epoch 34:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.392, v_num=3, train_loss_step=0.325, train_loss_epoch=0.325]Epoch 34: 100%|##########| 1/1 [00:00<00:00, 20.95it/s, loss=0.392, v_num=3, train_loss_step=0.325, train_loss_epoch=0.325]Epoch 34: 100%|##########| 1/1 [00:00<00:00, 20.71it/s, loss=0.387, v_num=3, train_loss_step=0.311, train_loss_epoch=0.325]Epoch 34: 100%|##########| 1/1 [00:00<00:00, 20.44it/s, loss=0.387, v_num=3, train_loss_step=0.311, train_loss_epoch=0.311]Epoch 34:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.387, v_num=3, train_loss_step=0.311, train_loss_epoch=0.311]        Epoch 35:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.387, v_num=3, train_loss_step=0.311, train_loss_epoch=0.311]Epoch 35: 100%|##########| 1/1 [00:00<00:00, 20.02it/s, loss=0.387, v_num=3, train_loss_step=0.311, train_loss_epoch=0.311]Epoch 35: 100%|##########| 1/1 [00:00<00:00, 19.76it/s, loss=0.38, v_num=3, train_loss_step=0.297, train_loss_epoch=0.311] Epoch 35: 100%|##########| 1/1 [00:00<00:00, 19.53it/s, loss=0.38, v_num=3, train_loss_step=0.297, train_loss_epoch=0.297]Epoch 35:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.38, v_num=3, train_loss_step=0.297, train_loss_epoch=0.297]        Epoch 36:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.38, v_num=3, train_loss_step=0.297, train_loss_epoch=0.297]Epoch 36: 100%|##########| 1/1 [00:00<00:00, 20.15it/s, loss=0.38, v_num=3, train_loss_step=0.297, train_loss_epoch=0.297]Epoch 36: 100%|##########| 1/1 [00:00<00:00, 19.99it/s, loss=0.373, v_num=3, train_loss_step=0.282, train_loss_epoch=0.297]Epoch 36: 100%|##########| 1/1 [00:00<00:00, 19.76it/s, loss=0.373, v_num=3, train_loss_step=0.282, train_loss_epoch=0.282]Epoch 36:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.373, v_num=3, train_loss_step=0.282, train_loss_epoch=0.282]        Epoch 37:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.373, v_num=3, train_loss_step=0.282, train_loss_epoch=0.282]Epoch 37: 100%|##########| 1/1 [00:00<00:00, 20.41it/s, loss=0.373, v_num=3, train_loss_step=0.282, train_loss_epoch=0.282]Epoch 37: 100%|##########| 1/1 [00:00<00:00, 20.16it/s, loss=0.365, v_num=3, train_loss_step=0.268, train_loss_epoch=0.282]Epoch 37: 100%|##########| 1/1 [00:00<00:00, 19.90it/s, loss=0.365, v_num=3, train_loss_step=0.268, train_loss_epoch=0.268]Epoch 37:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.365, v_num=3, train_loss_step=0.268, train_loss_epoch=0.268]        Epoch 38:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.365, v_num=3, train_loss_step=0.268, train_loss_epoch=0.268]Epoch 38: 100%|##########| 1/1 [00:00<00:00, 20.62it/s, loss=0.365, v_num=3, train_loss_step=0.268, train_loss_epoch=0.268]Epoch 38: 100%|##########| 1/1 [00:00<00:00, 20.45it/s, loss=0.357, v_num=3, train_loss_step=0.258, train_loss_epoch=0.268]Epoch 38: 100%|##########| 1/1 [00:00<00:00, 20.23it/s, loss=0.357, v_num=3, train_loss_step=0.258, train_loss_epoch=0.258]Epoch 38:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.357, v_num=3, train_loss_step=0.258, train_loss_epoch=0.258]        Epoch 39:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.357, v_num=3, train_loss_step=0.258, train_loss_epoch=0.258]Epoch 39: 100%|##########| 1/1 [00:00<00:00, 20.67it/s, loss=0.357, v_num=3, train_loss_step=0.258, train_loss_epoch=0.258]Epoch 39: 100%|##########| 1/1 [00:00<00:00, 20.44it/s, loss=0.349, v_num=3, train_loss_step=0.253, train_loss_epoch=0.258]Epoch 39: 100%|##########| 1/1 [00:00<00:00, 20.21it/s, loss=0.349, v_num=3, train_loss_step=0.253, train_loss_epoch=0.253]Epoch 39:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.349, v_num=3, train_loss_step=0.253, train_loss_epoch=0.253]        Epoch 40:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.349, v_num=3, train_loss_step=0.253, train_loss_epoch=0.253]Epoch 40: 100%|##########| 1/1 [00:00<00:00, 21.26it/s, loss=0.349, v_num=3, train_loss_step=0.253, train_loss_epoch=0.253]Epoch 40: 100%|##########| 1/1 [00:00<00:00, 21.11it/s, loss=0.341, v_num=3, train_loss_step=0.252, train_loss_epoch=0.253]Epoch 40: 100%|##########| 1/1 [00:00<00:00, 20.85it/s, loss=0.341, v_num=3, train_loss_step=0.252, train_loss_epoch=0.252]Epoch 40:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.341, v_num=3, train_loss_step=0.252, train_loss_epoch=0.252]        Epoch 41:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.341, v_num=3, train_loss_step=0.252, train_loss_epoch=0.252]Epoch 41: 100%|##########| 1/1 [00:00<00:00, 22.01it/s, loss=0.341, v_num=3, train_loss_step=0.252, train_loss_epoch=0.252]Epoch 41: 100%|##########| 1/1 [00:00<00:00, 21.76it/s, loss=0.333, v_num=3, train_loss_step=0.248, train_loss_epoch=0.252]Epoch 41: 100%|##########| 1/1 [00:00<00:00, 21.51it/s, loss=0.333, v_num=3, train_loss_step=0.248, train_loss_epoch=0.248]Epoch 41:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.333, v_num=3, train_loss_step=0.248, train_loss_epoch=0.248]        Epoch 42:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.333, v_num=3, train_loss_step=0.248, train_loss_epoch=0.248]Epoch 42: 100%|##########| 1/1 [00:00<00:00, 22.20it/s, loss=0.333, v_num=3, train_loss_step=0.248, train_loss_epoch=0.248]Epoch 42: 100%|##########| 1/1 [00:00<00:00, 22.01it/s, loss=0.325, v_num=3, train_loss_step=0.243, train_loss_epoch=0.248]Epoch 42: 100%|##########| 1/1 [00:00<00:00, 21.71it/s, loss=0.325, v_num=3, train_loss_step=0.243, train_loss_epoch=0.243]Epoch 42:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.325, v_num=3, train_loss_step=0.243, train_loss_epoch=0.243]        Epoch 43:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.325, v_num=3, train_loss_step=0.243, train_loss_epoch=0.243]Epoch 43: 100%|##########| 1/1 [00:00<00:00, 21.29it/s, loss=0.325, v_num=3, train_loss_step=0.243, train_loss_epoch=0.243]Epoch 43: 100%|##########| 1/1 [00:00<00:00, 21.06it/s, loss=0.317, v_num=3, train_loss_step=0.239, train_loss_epoch=0.243]Epoch 43: 100%|##########| 1/1 [00:00<00:00, 20.81it/s, loss=0.317, v_num=3, train_loss_step=0.239, train_loss_epoch=0.239]Epoch 43:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.317, v_num=3, train_loss_step=0.239, train_loss_epoch=0.239]        Epoch 44:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.317, v_num=3, train_loss_step=0.239, train_loss_epoch=0.239]Epoch 44: 100%|##########| 1/1 [00:00<00:00, 21.52it/s, loss=0.317, v_num=3, train_loss_step=0.239, train_loss_epoch=0.239]Epoch 44: 100%|##########| 1/1 [00:00<00:00, 21.38it/s, loss=0.309, v_num=3, train_loss_step=0.236, train_loss_epoch=0.239]Epoch 44: 100%|##########| 1/1 [00:00<00:00, 21.12it/s, loss=0.309, v_num=3, train_loss_step=0.236, train_loss_epoch=0.236]Epoch 44:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.309, v_num=3, train_loss_step=0.236, train_loss_epoch=0.236]        Epoch 45:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.309, v_num=3, train_loss_step=0.236, train_loss_epoch=0.236]Epoch 45: 100%|##########| 1/1 [00:00<00:00, 21.10it/s, loss=0.309, v_num=3, train_loss_step=0.236, train_loss_epoch=0.236]Epoch 45: 100%|##########| 1/1 [00:00<00:00, 20.91it/s, loss=0.3, v_num=3, train_loss_step=0.231, train_loss_epoch=0.236]  Epoch 45: 100%|##########| 1/1 [00:00<00:00, 20.68it/s, loss=0.3, v_num=3, train_loss_step=0.231, train_loss_epoch=0.231]Epoch 45:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.3, v_num=3, train_loss_step=0.231, train_loss_epoch=0.231]        Epoch 46:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.3, v_num=3, train_loss_step=0.231, train_loss_epoch=0.231]Epoch 46: 100%|##########| 1/1 [00:00<00:00, 21.54it/s, loss=0.3, v_num=3, train_loss_step=0.231, train_loss_epoch=0.231]Epoch 46: 100%|##########| 1/1 [00:00<00:00, 21.36it/s, loss=0.292, v_num=3, train_loss_step=0.225, train_loss_epoch=0.231]Epoch 46: 100%|##########| 1/1 [00:00<00:00, 21.12it/s, loss=0.292, v_num=3, train_loss_step=0.225, train_loss_epoch=0.225]Epoch 46:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.292, v_num=3, train_loss_step=0.225, train_loss_epoch=0.225]        Epoch 47:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.292, v_num=3, train_loss_step=0.225, train_loss_epoch=0.225]Epoch 47: 100%|##########| 1/1 [00:00<00:00, 21.59it/s, loss=0.292, v_num=3, train_loss_step=0.225, train_loss_epoch=0.225]Epoch 47: 100%|##########| 1/1 [00:00<00:00, 21.34it/s, loss=0.284, v_num=3, train_loss_step=0.220, train_loss_epoch=0.225]Epoch 47: 100%|##########| 1/1 [00:00<00:00, 21.08it/s, loss=0.284, v_num=3, train_loss_step=0.220, train_loss_epoch=0.220]Epoch 47:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.284, v_num=3, train_loss_step=0.220, train_loss_epoch=0.220]        Epoch 48:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.284, v_num=3, train_loss_step=0.220, train_loss_epoch=0.220]Epoch 48: 100%|##########| 1/1 [00:00<00:00, 20.36it/s, loss=0.284, v_num=3, train_loss_step=0.220, train_loss_epoch=0.220]Epoch 48: 100%|##########| 1/1 [00:00<00:00, 20.21it/s, loss=0.276, v_num=3, train_loss_step=0.216, train_loss_epoch=0.220]Epoch 48: 100%|##########| 1/1 [00:00<00:00, 19.97it/s, loss=0.276, v_num=3, train_loss_step=0.216, train_loss_epoch=0.216]Epoch 48:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.276, v_num=3, train_loss_step=0.216, train_loss_epoch=0.216]        Epoch 49:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.276, v_num=3, train_loss_step=0.216, train_loss_epoch=0.216]Epoch 49: 100%|##########| 1/1 [00:00<00:00, 21.47it/s, loss=0.276, v_num=3, train_loss_step=0.216, train_loss_epoch=0.216]Epoch 49: 100%|##########| 1/1 [00:00<00:00, 21.30it/s, loss=0.268, v_num=3, train_loss_step=0.211, train_loss_epoch=0.216]Epoch 49: 100%|##########| 1/1 [00:00<00:00, 20.79it/s, loss=0.268, v_num=3, train_loss_step=0.211, train_loss_epoch=0.211]Epoch 49:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.268, v_num=3, train_loss_step=0.211, train_loss_epoch=0.211]        Epoch 50:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.268, v_num=3, train_loss_step=0.211, train_loss_epoch=0.211]Epoch 50: 100%|##########| 1/1 [00:00<00:00, 18.62it/s, loss=0.268, v_num=3, train_loss_step=0.211, train_loss_epoch=0.211]Epoch 50: 100%|##########| 1/1 [00:00<00:00, 18.43it/s, loss=0.26, v_num=3, train_loss_step=0.206, train_loss_epoch=0.211] Epoch 50: 100%|##########| 1/1 [00:00<00:00, 18.21it/s, loss=0.26, v_num=3, train_loss_step=0.206, train_loss_epoch=0.206]Epoch 50:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.26, v_num=3, train_loss_step=0.206, train_loss_epoch=0.206]        Epoch 51:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.26, v_num=3, train_loss_step=0.206, train_loss_epoch=0.206]Epoch 51: 100%|##########| 1/1 [00:00<00:00, 20.48it/s, loss=0.26, v_num=3, train_loss_step=0.206, train_loss_epoch=0.206]Epoch 51: 100%|##########| 1/1 [00:00<00:00, 20.25it/s, loss=0.253, v_num=3, train_loss_step=0.200, train_loss_epoch=0.206]Epoch 51: 100%|##########| 1/1 [00:00<00:00, 20.00it/s, loss=0.253, v_num=3, train_loss_step=0.200, train_loss_epoch=0.200]Epoch 51:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.253, v_num=3, train_loss_step=0.200, train_loss_epoch=0.200]        Epoch 52:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.253, v_num=3, train_loss_step=0.200, train_loss_epoch=0.200]Epoch 52: 100%|##########| 1/1 [00:00<00:00, 20.87it/s, loss=0.253, v_num=3, train_loss_step=0.200, train_loss_epoch=0.200]Epoch 52: 100%|##########| 1/1 [00:00<00:00, 20.64it/s, loss=0.246, v_num=3, train_loss_step=0.194, train_loss_epoch=0.200]Epoch 52: 100%|##########| 1/1 [00:00<00:00, 20.38it/s, loss=0.246, v_num=3, train_loss_step=0.194, train_loss_epoch=0.194]Epoch 52:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.246, v_num=3, train_loss_step=0.194, train_loss_epoch=0.194]        Epoch 53:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.246, v_num=3, train_loss_step=0.194, train_loss_epoch=0.194]Epoch 53: 100%|##########| 1/1 [00:00<00:00, 20.28it/s, loss=0.246, v_num=3, train_loss_step=0.194, train_loss_epoch=0.194]Epoch 53: 100%|##########| 1/1 [00:00<00:00, 20.11it/s, loss=0.239, v_num=3, train_loss_step=0.189, train_loss_epoch=0.194]Epoch 53: 100%|##########| 1/1 [00:00<00:00, 19.84it/s, loss=0.239, v_num=3, train_loss_step=0.189, train_loss_epoch=0.189]Epoch 53:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.239, v_num=3, train_loss_step=0.189, train_loss_epoch=0.189]        Epoch 54:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.239, v_num=3, train_loss_step=0.189, train_loss_epoch=0.189]Epoch 54: 100%|##########| 1/1 [00:00<00:00, 21.31it/s, loss=0.239, v_num=3, train_loss_step=0.189, train_loss_epoch=0.189]Epoch 54: 100%|##########| 1/1 [00:00<00:00, 21.09it/s, loss=0.233, v_num=3, train_loss_step=0.184, train_loss_epoch=0.189]Epoch 54: 100%|##########| 1/1 [00:00<00:00, 20.86it/s, loss=0.233, v_num=3, train_loss_step=0.184, train_loss_epoch=0.184]Epoch 54:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.233, v_num=3, train_loss_step=0.184, train_loss_epoch=0.184]        Epoch 55:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.233, v_num=3, train_loss_step=0.184, train_loss_epoch=0.184]Epoch 55: 100%|##########| 1/1 [00:00<00:00, 21.72it/s, loss=0.233, v_num=3, train_loss_step=0.184, train_loss_epoch=0.184]Epoch 55: 100%|##########| 1/1 [00:00<00:00, 21.55it/s, loss=0.227, v_num=3, train_loss_step=0.177, train_loss_epoch=0.184]Epoch 55: 100%|##########| 1/1 [00:00<00:00, 21.27it/s, loss=0.227, v_num=3, train_loss_step=0.177, train_loss_epoch=0.177]Epoch 55:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.227, v_num=3, train_loss_step=0.177, train_loss_epoch=0.177]        Epoch 56:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.227, v_num=3, train_loss_step=0.177, train_loss_epoch=0.177]Epoch 56: 100%|##########| 1/1 [00:00<00:00, 21.56it/s, loss=0.227, v_num=3, train_loss_step=0.177, train_loss_epoch=0.177]Epoch 56: 100%|##########| 1/1 [00:00<00:00, 21.33it/s, loss=0.221, v_num=3, train_loss_step=0.172, train_loss_epoch=0.177]Epoch 56: 100%|##########| 1/1 [00:00<00:00, 21.09it/s, loss=0.221, v_num=3, train_loss_step=0.172, train_loss_epoch=0.172]Epoch 56:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.221, v_num=3, train_loss_step=0.172, train_loss_epoch=0.172]        Epoch 57:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.221, v_num=3, train_loss_step=0.172, train_loss_epoch=0.172]Epoch 57: 100%|##########| 1/1 [00:00<00:00, 21.45it/s, loss=0.221, v_num=3, train_loss_step=0.172, train_loss_epoch=0.172]Epoch 57: 100%|##########| 1/1 [00:00<00:00, 21.26it/s, loss=0.216, v_num=3, train_loss_step=0.166, train_loss_epoch=0.172]Epoch 57: 100%|##########| 1/1 [00:00<00:00, 21.00it/s, loss=0.216, v_num=3, train_loss_step=0.166, train_loss_epoch=0.166]Epoch 57:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.216, v_num=3, train_loss_step=0.166, train_loss_epoch=0.166]        Epoch 58:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.216, v_num=3, train_loss_step=0.166, train_loss_epoch=0.166]Epoch 58: 100%|##########| 1/1 [00:00<00:00, 21.45it/s, loss=0.216, v_num=3, train_loss_step=0.166, train_loss_epoch=0.166]Epoch 58: 100%|##########| 1/1 [00:00<00:00, 21.23it/s, loss=0.211, v_num=3, train_loss_step=0.162, train_loss_epoch=0.166]Epoch 58: 100%|##########| 1/1 [00:00<00:00, 20.98it/s, loss=0.211, v_num=3, train_loss_step=0.162, train_loss_epoch=0.162]Epoch 58:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.211, v_num=3, train_loss_step=0.162, train_loss_epoch=0.162]        Epoch 59:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.211, v_num=3, train_loss_step=0.162, train_loss_epoch=0.162]Epoch 59: 100%|##########| 1/1 [00:00<00:00, 21.31it/s, loss=0.211, v_num=3, train_loss_step=0.162, train_loss_epoch=0.162]Epoch 59: 100%|##########| 1/1 [00:00<00:00, 21.07it/s, loss=0.206, v_num=3, train_loss_step=0.157, train_loss_epoch=0.162]Epoch 59: 100%|##########| 1/1 [00:00<00:00, 20.81it/s, loss=0.206, v_num=3, train_loss_step=0.157, train_loss_epoch=0.157]Epoch 59:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.206, v_num=3, train_loss_step=0.157, train_loss_epoch=0.157]        Epoch 60:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.206, v_num=3, train_loss_step=0.157, train_loss_epoch=0.157]Epoch 60: 100%|##########| 1/1 [00:00<00:00, 21.26it/s, loss=0.206, v_num=3, train_loss_step=0.157, train_loss_epoch=0.157]Epoch 60: 100%|##########| 1/1 [00:00<00:00, 21.09it/s, loss=0.201, v_num=3, train_loss_step=0.154, train_loss_epoch=0.157]Epoch 60: 100%|##########| 1/1 [00:00<00:00, 20.83it/s, loss=0.201, v_num=3, train_loss_step=0.154, train_loss_epoch=0.154]Epoch 60:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.201, v_num=3, train_loss_step=0.154, train_loss_epoch=0.154]        Epoch 61:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.201, v_num=3, train_loss_step=0.154, train_loss_epoch=0.154]Epoch 61: 100%|##########| 1/1 [00:00<00:00, 20.44it/s, loss=0.201, v_num=3, train_loss_step=0.154, train_loss_epoch=0.154]Epoch 61: 100%|##########| 1/1 [00:00<00:00, 20.22it/s, loss=0.197, v_num=3, train_loss_step=0.150, train_loss_epoch=0.154]Epoch 61: 100%|##########| 1/1 [00:00<00:00, 19.97it/s, loss=0.197, v_num=3, train_loss_step=0.150, train_loss_epoch=0.150]Epoch 61:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.197, v_num=3, train_loss_step=0.150, train_loss_epoch=0.150]        Epoch 62:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.197, v_num=3, train_loss_step=0.150, train_loss_epoch=0.150]Epoch 62: 100%|##########| 1/1 [00:00<00:00, 21.14it/s, loss=0.197, v_num=3, train_loss_step=0.150, train_loss_epoch=0.150]Epoch 62: 100%|##########| 1/1 [00:00<00:00, 20.87it/s, loss=0.192, v_num=3, train_loss_step=0.146, train_loss_epoch=0.150]Epoch 62: 100%|##########| 1/1 [00:00<00:00, 20.58it/s, loss=0.192, v_num=3, train_loss_step=0.146, train_loss_epoch=0.146]Epoch 62:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.192, v_num=3, train_loss_step=0.146, train_loss_epoch=0.146]        Epoch 63:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.192, v_num=3, train_loss_step=0.146, train_loss_epoch=0.146]Epoch 63: 100%|##########| 1/1 [00:00<00:00, 21.06it/s, loss=0.192, v_num=3, train_loss_step=0.146, train_loss_epoch=0.146]Epoch 63: 100%|##########| 1/1 [00:00<00:00, 20.88it/s, loss=0.187, v_num=3, train_loss_step=0.143, train_loss_epoch=0.146]Epoch 63: 100%|##########| 1/1 [00:00<00:00, 20.60it/s, loss=0.187, v_num=3, train_loss_step=0.143, train_loss_epoch=0.143]Epoch 63:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.187, v_num=3, train_loss_step=0.143, train_loss_epoch=0.143]        Epoch 64:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.187, v_num=3, train_loss_step=0.143, train_loss_epoch=0.143]Epoch 64: 100%|##########| 1/1 [00:00<00:00, 20.57it/s, loss=0.187, v_num=3, train_loss_step=0.143, train_loss_epoch=0.143]Epoch 64: 100%|##########| 1/1 [00:00<00:00, 20.36it/s, loss=0.182, v_num=3, train_loss_step=0.142, train_loss_epoch=0.143]Epoch 64: 100%|##########| 1/1 [00:00<00:00, 20.10it/s, loss=0.182, v_num=3, train_loss_step=0.142, train_loss_epoch=0.142]Epoch 64:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.182, v_num=3, train_loss_step=0.142, train_loss_epoch=0.142]        Epoch 65:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.182, v_num=3, train_loss_step=0.142, train_loss_epoch=0.142]Epoch 65: 100%|##########| 1/1 [00:00<00:00, 21.47it/s, loss=0.182, v_num=3, train_loss_step=0.142, train_loss_epoch=0.142]Epoch 65: 100%|##########| 1/1 [00:00<00:00, 21.30it/s, loss=0.178, v_num=3, train_loss_step=0.140, train_loss_epoch=0.142]Epoch 65: 100%|##########| 1/1 [00:00<00:00, 21.03it/s, loss=0.178, v_num=3, train_loss_step=0.140, train_loss_epoch=0.140]Epoch 65:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.178, v_num=3, train_loss_step=0.140, train_loss_epoch=0.140]        Epoch 66:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.178, v_num=3, train_loss_step=0.140, train_loss_epoch=0.140]Epoch 66: 100%|##########| 1/1 [00:00<00:00, 21.54it/s, loss=0.178, v_num=3, train_loss_step=0.140, train_loss_epoch=0.140]Epoch 66: 100%|##########| 1/1 [00:00<00:00, 21.38it/s, loss=0.173, v_num=3, train_loss_step=0.138, train_loss_epoch=0.140]Epoch 66: 100%|##########| 1/1 [00:00<00:00, 21.11it/s, loss=0.173, v_num=3, train_loss_step=0.138, train_loss_epoch=0.138]Epoch 66:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.173, v_num=3, train_loss_step=0.138, train_loss_epoch=0.138]        Epoch 67:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.173, v_num=3, train_loss_step=0.138, train_loss_epoch=0.138]Epoch 67: 100%|##########| 1/1 [00:00<00:00, 21.17it/s, loss=0.173, v_num=3, train_loss_step=0.138, train_loss_epoch=0.138]Epoch 67: 100%|##########| 1/1 [00:00<00:00, 21.00it/s, loss=0.169, v_num=3, train_loss_step=0.136, train_loss_epoch=0.138]Epoch 67: 100%|##########| 1/1 [00:00<00:00, 20.76it/s, loss=0.169, v_num=3, train_loss_step=0.136, train_loss_epoch=0.136]Epoch 67:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.169, v_num=3, train_loss_step=0.136, train_loss_epoch=0.136]        Epoch 68:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.169, v_num=3, train_loss_step=0.136, train_loss_epoch=0.136]Epoch 68: 100%|##########| 1/1 [00:00<00:00, 21.59it/s, loss=0.169, v_num=3, train_loss_step=0.136, train_loss_epoch=0.136]Epoch 68: 100%|##########| 1/1 [00:00<00:00, 21.40it/s, loss=0.165, v_num=3, train_loss_step=0.135, train_loss_epoch=0.136]Epoch 68: 100%|##########| 1/1 [00:00<00:00, 21.13it/s, loss=0.165, v_num=3, train_loss_step=0.135, train_loss_epoch=0.135]Epoch 68:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.165, v_num=3, train_loss_step=0.135, train_loss_epoch=0.135]        Epoch 69:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.165, v_num=3, train_loss_step=0.135, train_loss_epoch=0.135]Epoch 69: 100%|##########| 1/1 [00:00<00:00, 20.24it/s, loss=0.165, v_num=3, train_loss_step=0.135, train_loss_epoch=0.135]Epoch 69: 100%|##########| 1/1 [00:00<00:00, 20.09it/s, loss=0.161, v_num=3, train_loss_step=0.133, train_loss_epoch=0.135]Epoch 69: 100%|##########| 1/1 [00:00<00:00, 19.87it/s, loss=0.161, v_num=3, train_loss_step=0.133, train_loss_epoch=0.133]Epoch 69:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.161, v_num=3, train_loss_step=0.133, train_loss_epoch=0.133]        Epoch 70:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.161, v_num=3, train_loss_step=0.133, train_loss_epoch=0.133]Epoch 70: 100%|##########| 1/1 [00:00<00:00, 19.71it/s, loss=0.161, v_num=3, train_loss_step=0.133, train_loss_epoch=0.133]Epoch 70: 100%|##########| 1/1 [00:00<00:00, 19.50it/s, loss=0.157, v_num=3, train_loss_step=0.131, train_loss_epoch=0.133]Epoch 70: 100%|##########| 1/1 [00:00<00:00, 19.26it/s, loss=0.157, v_num=3, train_loss_step=0.131, train_loss_epoch=0.131]Epoch 70:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.157, v_num=3, train_loss_step=0.131, train_loss_epoch=0.131]        Epoch 71:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.157, v_num=3, train_loss_step=0.131, train_loss_epoch=0.131]Epoch 71: 100%|##########| 1/1 [00:00<00:00, 16.95it/s, loss=0.157, v_num=3, train_loss_step=0.131, train_loss_epoch=0.131]Epoch 71: 100%|##########| 1/1 [00:00<00:00, 16.80it/s, loss=0.154, v_num=3, train_loss_step=0.129, train_loss_epoch=0.131]Epoch 71: 100%|##########| 1/1 [00:00<00:00, 16.61it/s, loss=0.154, v_num=3, train_loss_step=0.129, train_loss_epoch=0.129]Epoch 71:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.154, v_num=3, train_loss_step=0.129, train_loss_epoch=0.129]        Epoch 72:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.154, v_num=3, train_loss_step=0.129, train_loss_epoch=0.129]Epoch 72: 100%|##########| 1/1 [00:00<00:00, 19.72it/s, loss=0.154, v_num=3, train_loss_step=0.129, train_loss_epoch=0.129]Epoch 72: 100%|##########| 1/1 [00:00<00:00, 19.53it/s, loss=0.151, v_num=3, train_loss_step=0.127, train_loss_epoch=0.129]Epoch 72: 100%|##########| 1/1 [00:00<00:00, 19.30it/s, loss=0.151, v_num=3, train_loss_step=0.127, train_loss_epoch=0.127]Epoch 72:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.151, v_num=3, train_loss_step=0.127, train_loss_epoch=0.127]        Epoch 73:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.151, v_num=3, train_loss_step=0.127, train_loss_epoch=0.127]Epoch 73: 100%|##########| 1/1 [00:00<00:00, 20.98it/s, loss=0.151, v_num=3, train_loss_step=0.127, train_loss_epoch=0.127]Epoch 73: 100%|##########| 1/1 [00:00<00:00, 20.76it/s, loss=0.147, v_num=3, train_loss_step=0.125, train_loss_epoch=0.127]Epoch 73: 100%|##########| 1/1 [00:00<00:00, 20.50it/s, loss=0.147, v_num=3, train_loss_step=0.125, train_loss_epoch=0.125]Epoch 73:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.147, v_num=3, train_loss_step=0.125, train_loss_epoch=0.125]        Epoch 74:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.147, v_num=3, train_loss_step=0.125, train_loss_epoch=0.125]Epoch 74: 100%|##########| 1/1 [00:00<00:00, 21.37it/s, loss=0.147, v_num=3, train_loss_step=0.125, train_loss_epoch=0.125]Epoch 74: 100%|##########| 1/1 [00:00<00:00, 21.18it/s, loss=0.144, v_num=3, train_loss_step=0.123, train_loss_epoch=0.125]Epoch 74: 100%|##########| 1/1 [00:00<00:00, 20.90it/s, loss=0.144, v_num=3, train_loss_step=0.123, train_loss_epoch=0.123]Epoch 74:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.144, v_num=3, train_loss_step=0.123, train_loss_epoch=0.123]        Epoch 75:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.144, v_num=3, train_loss_step=0.123, train_loss_epoch=0.123]Epoch 75: 100%|##########| 1/1 [00:00<00:00, 21.30it/s, loss=0.144, v_num=3, train_loss_step=0.123, train_loss_epoch=0.123]Epoch 75: 100%|##########| 1/1 [00:00<00:00, 21.08it/s, loss=0.142, v_num=3, train_loss_step=0.121, train_loss_epoch=0.123]Epoch 75: 100%|##########| 1/1 [00:00<00:00, 20.81it/s, loss=0.142, v_num=3, train_loss_step=0.121, train_loss_epoch=0.121]Epoch 75:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.142, v_num=3, train_loss_step=0.121, train_loss_epoch=0.121]        Epoch 76:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.142, v_num=3, train_loss_step=0.121, train_loss_epoch=0.121]Epoch 76: 100%|##########| 1/1 [00:00<00:00, 21.77it/s, loss=0.142, v_num=3, train_loss_step=0.121, train_loss_epoch=0.121]Epoch 76: 100%|##########| 1/1 [00:00<00:00, 21.58it/s, loss=0.139, v_num=3, train_loss_step=0.120, train_loss_epoch=0.121]Epoch 76: 100%|##########| 1/1 [00:00<00:00, 21.28it/s, loss=0.139, v_num=3, train_loss_step=0.120, train_loss_epoch=0.120]Epoch 76:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.139, v_num=3, train_loss_step=0.120, train_loss_epoch=0.120]        Epoch 77:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.139, v_num=3, train_loss_step=0.120, train_loss_epoch=0.120]Epoch 77: 100%|##########| 1/1 [00:00<00:00, 20.18it/s, loss=0.139, v_num=3, train_loss_step=0.120, train_loss_epoch=0.120]Epoch 77: 100%|##########| 1/1 [00:00<00:00, 20.02it/s, loss=0.136, v_num=3, train_loss_step=0.118, train_loss_epoch=0.120]Epoch 77: 100%|##########| 1/1 [00:00<00:00, 19.80it/s, loss=0.136, v_num=3, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 77:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.136, v_num=3, train_loss_step=0.118, train_loss_epoch=0.118]        Epoch 78:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.136, v_num=3, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 78: 100%|##########| 1/1 [00:00<00:00, 21.51it/s, loss=0.136, v_num=3, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 78: 100%|##########| 1/1 [00:00<00:00, 21.34it/s, loss=0.134, v_num=3, train_loss_step=0.117, train_loss_epoch=0.118]Epoch 78: 100%|##########| 1/1 [00:00<00:00, 21.08it/s, loss=0.134, v_num=3, train_loss_step=0.117, train_loss_epoch=0.117]Epoch 78:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.134, v_num=3, train_loss_step=0.117, train_loss_epoch=0.117]        Epoch 79:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.134, v_num=3, train_loss_step=0.117, train_loss_epoch=0.117]Epoch 79: 100%|##########| 1/1 [00:00<00:00, 21.71it/s, loss=0.134, v_num=3, train_loss_step=0.117, train_loss_epoch=0.117]Epoch 79: 100%|##########| 1/1 [00:00<00:00, 21.51it/s, loss=0.132, v_num=3, train_loss_step=0.116, train_loss_epoch=0.117]Epoch 79: 100%|##########| 1/1 [00:00<00:00, 21.25it/s, loss=0.132, v_num=3, train_loss_step=0.116, train_loss_epoch=0.116]Epoch 79:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.132, v_num=3, train_loss_step=0.116, train_loss_epoch=0.116]        Epoch 80:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.132, v_num=3, train_loss_step=0.116, train_loss_epoch=0.116]Epoch 80: 100%|##########| 1/1 [00:00<00:00, 20.37it/s, loss=0.132, v_num=3, train_loss_step=0.116, train_loss_epoch=0.116]Epoch 80: 100%|##########| 1/1 [00:00<00:00, 20.19it/s, loss=0.13, v_num=3, train_loss_step=0.114, train_loss_epoch=0.116] Epoch 80: 100%|##########| 1/1 [00:00<00:00, 19.95it/s, loss=0.13, v_num=3, train_loss_step=0.114, train_loss_epoch=0.114]Epoch 80:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.13, v_num=3, train_loss_step=0.114, train_loss_epoch=0.114]        Epoch 81:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.13, v_num=3, train_loss_step=0.114, train_loss_epoch=0.114]Epoch 81: 100%|##########| 1/1 [00:00<00:00, 20.68it/s, loss=0.13, v_num=3, train_loss_step=0.114, train_loss_epoch=0.114]Epoch 81: 100%|##########| 1/1 [00:00<00:00, 20.48it/s, loss=0.128, v_num=3, train_loss_step=0.113, train_loss_epoch=0.114]Epoch 81: 100%|##########| 1/1 [00:00<00:00, 20.25it/s, loss=0.128, v_num=3, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 81:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.128, v_num=3, train_loss_step=0.113, train_loss_epoch=0.113]        Epoch 82:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.128, v_num=3, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 82: 100%|##########| 1/1 [00:00<00:00, 19.44it/s, loss=0.128, v_num=3, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 82: 100%|##########| 1/1 [00:00<00:00, 19.28it/s, loss=0.127, v_num=3, train_loss_step=0.112, train_loss_epoch=0.113]Epoch 82: 100%|##########| 1/1 [00:00<00:00, 19.04it/s, loss=0.127, v_num=3, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 82:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.127, v_num=3, train_loss_step=0.112, train_loss_epoch=0.112]        Epoch 83:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.127, v_num=3, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 83: 100%|##########| 1/1 [00:00<00:00, 20.39it/s, loss=0.127, v_num=3, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 83: 100%|##########| 1/1 [00:00<00:00, 20.18it/s, loss=0.125, v_num=3, train_loss_step=0.111, train_loss_epoch=0.112]Epoch 83: 100%|##########| 1/1 [00:00<00:00, 19.92it/s, loss=0.125, v_num=3, train_loss_step=0.111, train_loss_epoch=0.111]Epoch 83:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.125, v_num=3, train_loss_step=0.111, train_loss_epoch=0.111]        Epoch 84:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.125, v_num=3, train_loss_step=0.111, train_loss_epoch=0.111]Epoch 84: 100%|##########| 1/1 [00:00<00:00, 19.98it/s, loss=0.125, v_num=3, train_loss_step=0.111, train_loss_epoch=0.111]Epoch 84: 100%|##########| 1/1 [00:00<00:00, 19.81it/s, loss=0.123, v_num=3, train_loss_step=0.109, train_loss_epoch=0.111]Epoch 84: 100%|##########| 1/1 [00:00<00:00, 19.56it/s, loss=0.123, v_num=3, train_loss_step=0.109, train_loss_epoch=0.109]Epoch 84:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.123, v_num=3, train_loss_step=0.109, train_loss_epoch=0.109]        Epoch 85:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.123, v_num=3, train_loss_step=0.109, train_loss_epoch=0.109]Epoch 85: 100%|##########| 1/1 [00:00<00:00, 19.99it/s, loss=0.123, v_num=3, train_loss_step=0.109, train_loss_epoch=0.109]Epoch 85: 100%|##########| 1/1 [00:00<00:00, 19.77it/s, loss=0.122, v_num=3, train_loss_step=0.108, train_loss_epoch=0.109]Epoch 85: 100%|##########| 1/1 [00:00<00:00, 19.51it/s, loss=0.122, v_num=3, train_loss_step=0.108, train_loss_epoch=0.108]Epoch 85:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.122, v_num=3, train_loss_step=0.108, train_loss_epoch=0.108]        Epoch 86:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.122, v_num=3, train_loss_step=0.108, train_loss_epoch=0.108]Epoch 86: 100%|##########| 1/1 [00:00<00:00, 20.58it/s, loss=0.122, v_num=3, train_loss_step=0.108, train_loss_epoch=0.108]Epoch 86: 100%|##########| 1/1 [00:00<00:00, 20.36it/s, loss=0.12, v_num=3, train_loss_step=0.107, train_loss_epoch=0.108] Epoch 86: 100%|##########| 1/1 [00:00<00:00, 20.11it/s, loss=0.12, v_num=3, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 86:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.12, v_num=3, train_loss_step=0.107, train_loss_epoch=0.107]        Epoch 87:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.12, v_num=3, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 87: 100%|##########| 1/1 [00:00<00:00, 19.82it/s, loss=0.12, v_num=3, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 87: 100%|##########| 1/1 [00:00<00:00, 19.62it/s, loss=0.119, v_num=3, train_loss_step=0.105, train_loss_epoch=0.107]Epoch 87: 100%|##########| 1/1 [00:00<00:00, 19.38it/s, loss=0.119, v_num=3, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 87:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.119, v_num=3, train_loss_step=0.105, train_loss_epoch=0.105]        Epoch 88:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.119, v_num=3, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 88: 100%|##########| 1/1 [00:00<00:00, 20.10it/s, loss=0.119, v_num=3, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 88: 100%|##########| 1/1 [00:00<00:00, 19.86it/s, loss=0.117, v_num=3, train_loss_step=0.104, train_loss_epoch=0.105]Epoch 88: 100%|##########| 1/1 [00:00<00:00, 19.61it/s, loss=0.117, v_num=3, train_loss_step=0.104, train_loss_epoch=0.104]Epoch 88:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.117, v_num=3, train_loss_step=0.104, train_loss_epoch=0.104]        Epoch 89:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.117, v_num=3, train_loss_step=0.104, train_loss_epoch=0.104]Epoch 89: 100%|##########| 1/1 [00:00<00:00, 21.36it/s, loss=0.117, v_num=3, train_loss_step=0.104, train_loss_epoch=0.104]Epoch 89: 100%|##########| 1/1 [00:00<00:00, 21.15it/s, loss=0.116, v_num=3, train_loss_step=0.103, train_loss_epoch=0.104]Epoch 89: 100%|##########| 1/1 [00:00<00:00, 20.91it/s, loss=0.116, v_num=3, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 89:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.116, v_num=3, train_loss_step=0.103, train_loss_epoch=0.103]        Epoch 90:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.116, v_num=3, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 90: 100%|##########| 1/1 [00:00<00:00, 20.85it/s, loss=0.116, v_num=3, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 90: 100%|##########| 1/1 [00:00<00:00, 20.60it/s, loss=0.114, v_num=3, train_loss_step=0.102, train_loss_epoch=0.103]Epoch 90: 100%|##########| 1/1 [00:00<00:00, 20.34it/s, loss=0.114, v_num=3, train_loss_step=0.102, train_loss_epoch=0.102]Epoch 90:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.114, v_num=3, train_loss_step=0.102, train_loss_epoch=0.102]        Epoch 91:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.114, v_num=3, train_loss_step=0.102, train_loss_epoch=0.102]Epoch 91: 100%|##########| 1/1 [00:00<00:00, 21.49it/s, loss=0.114, v_num=3, train_loss_step=0.102, train_loss_epoch=0.102]Epoch 91: 100%|##########| 1/1 [00:00<00:00, 21.23it/s, loss=0.113, v_num=3, train_loss_step=0.101, train_loss_epoch=0.102]Epoch 91: 100%|##########| 1/1 [00:00<00:00, 20.95it/s, loss=0.113, v_num=3, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 91:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.113, v_num=3, train_loss_step=0.101, train_loss_epoch=0.101]        Epoch 92:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.113, v_num=3, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 92: 100%|##########| 1/1 [00:00<00:00, 21.48it/s, loss=0.113, v_num=3, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 92: 100%|##########| 1/1 [00:00<00:00, 21.26it/s, loss=0.111, v_num=3, train_loss_step=0.0994, train_loss_epoch=0.101]Epoch 92: 100%|##########| 1/1 [00:00<00:00, 20.99it/s, loss=0.111, v_num=3, train_loss_step=0.0994, train_loss_epoch=0.0994]Epoch 92:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.111, v_num=3, train_loss_step=0.0994, train_loss_epoch=0.0994]        Epoch 93:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.111, v_num=3, train_loss_step=0.0994, train_loss_epoch=0.0994]Epoch 93: 100%|##########| 1/1 [00:00<00:00, 20.52it/s, loss=0.111, v_num=3, train_loss_step=0.0994, train_loss_epoch=0.0994]Epoch 93: 100%|##########| 1/1 [00:00<00:00, 20.30it/s, loss=0.11, v_num=3, train_loss_step=0.0983, train_loss_epoch=0.0994] Epoch 93: 100%|##########| 1/1 [00:00<00:00, 20.09it/s, loss=0.11, v_num=3, train_loss_step=0.0983, train_loss_epoch=0.0983]Epoch 93:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.11, v_num=3, train_loss_step=0.0983, train_loss_epoch=0.0983]        Epoch 94:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.11, v_num=3, train_loss_step=0.0983, train_loss_epoch=0.0983]Epoch 94: 100%|##########| 1/1 [00:00<00:00, 20.85it/s, loss=0.11, v_num=3, train_loss_step=0.0983, train_loss_epoch=0.0983]Epoch 94: 100%|##########| 1/1 [00:00<00:00, 20.70it/s, loss=0.109, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0983]Epoch 94: 100%|##########| 1/1 [00:00<00:00, 20.45it/s, loss=0.109, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0973]Epoch 94:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.109, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0973]        Epoch 95:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.109, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0973]Epoch 95: 100%|##########| 1/1 [00:00<00:00, 20.07it/s, loss=0.109, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0973]Epoch 95: 100%|##########| 1/1 [00:00<00:00, 19.83it/s, loss=0.108, v_num=3, train_loss_step=0.0957, train_loss_epoch=0.0973]Epoch 95: 100%|##########| 1/1 [00:00<00:00, 19.58it/s, loss=0.108, v_num=3, train_loss_step=0.0957, train_loss_epoch=0.0957]Epoch 95:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.108, v_num=3, train_loss_step=0.0957, train_loss_epoch=0.0957]        Epoch 96:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.108, v_num=3, train_loss_step=0.0957, train_loss_epoch=0.0957]Epoch 96: 100%|##########| 1/1 [00:00<00:00, 20.45it/s, loss=0.108, v_num=3, train_loss_step=0.0957, train_loss_epoch=0.0957]Epoch 96: 100%|##########| 1/1 [00:00<00:00, 20.29it/s, loss=0.106, v_num=3, train_loss_step=0.0942, train_loss_epoch=0.0957]Epoch 96: 100%|##########| 1/1 [00:00<00:00, 20.05it/s, loss=0.106, v_num=3, train_loss_step=0.0942, train_loss_epoch=0.0942]Epoch 96:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.106, v_num=3, train_loss_step=0.0942, train_loss_epoch=0.0942]        Epoch 97:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.106, v_num=3, train_loss_step=0.0942, train_loss_epoch=0.0942]Epoch 97: 100%|##########| 1/1 [00:00<00:00, 21.71it/s, loss=0.106, v_num=3, train_loss_step=0.0942, train_loss_epoch=0.0942]Epoch 97: 100%|##########| 1/1 [00:00<00:00, 21.55it/s, loss=0.105, v_num=3, train_loss_step=0.0939, train_loss_epoch=0.0942]Epoch 97: 100%|##########| 1/1 [00:00<00:00, 21.29it/s, loss=0.105, v_num=3, train_loss_step=0.0939, train_loss_epoch=0.0939]Epoch 97:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.105, v_num=3, train_loss_step=0.0939, train_loss_epoch=0.0939]        Epoch 98:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.105, v_num=3, train_loss_step=0.0939, train_loss_epoch=0.0939]Epoch 98: 100%|##########| 1/1 [00:00<00:00, 20.40it/s, loss=0.105, v_num=3, train_loss_step=0.0939, train_loss_epoch=0.0939]Epoch 98: 100%|##########| 1/1 [00:00<00:00, 20.17it/s, loss=0.104, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0939]Epoch 98: 100%|##########| 1/1 [00:00<00:00, 19.92it/s, loss=0.104, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0973]Epoch 98:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.104, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0973]        Epoch 99:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.104, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0973]Epoch 99: 100%|##########| 1/1 [00:00<00:00, 20.69it/s, loss=0.104, v_num=3, train_loss_step=0.0973, train_loss_epoch=0.0973]Epoch 99: 100%|##########| 1/1 [00:00<00:00, 20.45it/s, loss=0.103, v_num=3, train_loss_step=0.0984, train_loss_epoch=0.0973]Epoch 99: 100%|##########| 1/1 [00:00<00:00, 19.91it/s, loss=0.103, v_num=3, train_loss_step=0.0984, train_loss_epoch=0.0984]Epoch 99:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.103, v_num=3, train_loss_step=0.0984, train_loss_epoch=0.0984]        Epoch 100:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.103, v_num=3, train_loss_step=0.0984, train_loss_epoch=0.0984]Epoch 100: 100%|##########| 1/1 [00:00<00:00, 20.17it/s, loss=0.103, v_num=3, train_loss_step=0.0984, train_loss_epoch=0.0984]Epoch 100: 100%|##########| 1/1 [00:00<00:00, 19.97it/s, loss=0.102, v_num=3, train_loss_step=0.0916, train_loss_epoch=0.0984]Epoch 100: 100%|##########| 1/1 [00:00<00:00, 19.71it/s, loss=0.102, v_num=3, train_loss_step=0.0916, train_loss_epoch=0.0916]Epoch 100:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.102, v_num=3, train_loss_step=0.0916, train_loss_epoch=0.0916]        Epoch 101:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.102, v_num=3, train_loss_step=0.0916, train_loss_epoch=0.0916]Epoch 101: 100%|##########| 1/1 [00:00<00:00, 19.91it/s, loss=0.102, v_num=3, train_loss_step=0.0916, train_loss_epoch=0.0916]Epoch 101: 100%|##########| 1/1 [00:00<00:00, 19.74it/s, loss=0.101, v_num=3, train_loss_step=0.0895, train_loss_epoch=0.0916]Epoch 101: 100%|##########| 1/1 [00:00<00:00, 19.51it/s, loss=0.101, v_num=3, train_loss_step=0.0895, train_loss_epoch=0.0895]Epoch 101:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.101, v_num=3, train_loss_step=0.0895, train_loss_epoch=0.0895]        Epoch 102:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.101, v_num=3, train_loss_step=0.0895, train_loss_epoch=0.0895]Epoch 102: 100%|##########| 1/1 [00:00<00:00, 20.88it/s, loss=0.101, v_num=3, train_loss_step=0.0895, train_loss_epoch=0.0895]Epoch 102: 100%|##########| 1/1 [00:00<00:00, 20.71it/s, loss=0.1, v_num=3, train_loss_step=0.093, train_loss_epoch=0.0895]   Epoch 102: 100%|##########| 1/1 [00:00<00:00, 20.44it/s, loss=0.1, v_num=3, train_loss_step=0.093, train_loss_epoch=0.093] Epoch 102:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.1, v_num=3, train_loss_step=0.093, train_loss_epoch=0.093]        Epoch 103:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.1, v_num=3, train_loss_step=0.093, train_loss_epoch=0.093]Epoch 103: 100%|##########| 1/1 [00:00<00:00, 20.83it/s, loss=0.1, v_num=3, train_loss_step=0.093, train_loss_epoch=0.093]Epoch 103: 100%|##########| 1/1 [00:00<00:00, 20.58it/s, loss=0.0989, v_num=3, train_loss_step=0.0887, train_loss_epoch=0.093]Epoch 103: 100%|##########| 1/1 [00:00<00:00, 20.34it/s, loss=0.0989, v_num=3, train_loss_step=0.0887, train_loss_epoch=0.0887]Epoch 103:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0989, v_num=3, train_loss_step=0.0887, train_loss_epoch=0.0887]        Epoch 104:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0989, v_num=3, train_loss_step=0.0887, train_loss_epoch=0.0887]Epoch 104: 100%|##########| 1/1 [00:00<00:00, 20.88it/s, loss=0.0989, v_num=3, train_loss_step=0.0887, train_loss_epoch=0.0887]Epoch 104: 100%|##########| 1/1 [00:00<00:00, 20.71it/s, loss=0.0977, v_num=3, train_loss_step=0.0852, train_loss_epoch=0.0887]Epoch 104: 100%|##########| 1/1 [00:00<00:00, 20.42it/s, loss=0.0977, v_num=3, train_loss_step=0.0852, train_loss_epoch=0.0852]Epoch 104:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0977, v_num=3, train_loss_step=0.0852, train_loss_epoch=0.0852]        Epoch 105:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0977, v_num=3, train_loss_step=0.0852, train_loss_epoch=0.0852]Epoch 105: 100%|##########| 1/1 [00:00<00:00, 20.88it/s, loss=0.0977, v_num=3, train_loss_step=0.0852, train_loss_epoch=0.0852]Epoch 105: 100%|##########| 1/1 [00:00<00:00, 20.72it/s, loss=0.0966, v_num=3, train_loss_step=0.0861, train_loss_epoch=0.0852]Epoch 105: 100%|##########| 1/1 [00:00<00:00, 20.48it/s, loss=0.0966, v_num=3, train_loss_step=0.0861, train_loss_epoch=0.0861]Epoch 105:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0966, v_num=3, train_loss_step=0.0861, train_loss_epoch=0.0861]        Epoch 106:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0966, v_num=3, train_loss_step=0.0861, train_loss_epoch=0.0861]Epoch 106: 100%|##########| 1/1 [00:00<00:00, 21.88it/s, loss=0.0966, v_num=3, train_loss_step=0.0861, train_loss_epoch=0.0861]Epoch 106: 100%|##########| 1/1 [00:00<00:00, 21.69it/s, loss=0.0954, v_num=3, train_loss_step=0.0842, train_loss_epoch=0.0861]Epoch 106: 100%|##########| 1/1 [00:00<00:00, 21.42it/s, loss=0.0954, v_num=3, train_loss_step=0.0842, train_loss_epoch=0.0842]Epoch 106:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0954, v_num=3, train_loss_step=0.0842, train_loss_epoch=0.0842]        Epoch 107:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0954, v_num=3, train_loss_step=0.0842, train_loss_epoch=0.0842]Epoch 107: 100%|##########| 1/1 [00:00<00:00, 20.95it/s, loss=0.0954, v_num=3, train_loss_step=0.0842, train_loss_epoch=0.0842]Epoch 107: 100%|##########| 1/1 [00:00<00:00, 20.79it/s, loss=0.0942, v_num=3, train_loss_step=0.0813, train_loss_epoch=0.0842]Epoch 107: 100%|##########| 1/1 [00:00<00:00, 20.54it/s, loss=0.0942, v_num=3, train_loss_step=0.0813, train_loss_epoch=0.0813]Epoch 107:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0942, v_num=3, train_loss_step=0.0813, train_loss_epoch=0.0813]        Epoch 108:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0942, v_num=3, train_loss_step=0.0813, train_loss_epoch=0.0813]Epoch 108: 100%|##########| 1/1 [00:00<00:00, 21.60it/s, loss=0.0942, v_num=3, train_loss_step=0.0813, train_loss_epoch=0.0813]Epoch 108: 100%|##########| 1/1 [00:00<00:00, 21.35it/s, loss=0.0931, v_num=3, train_loss_step=0.0822, train_loss_epoch=0.0813]Epoch 108: 100%|##########| 1/1 [00:00<00:00, 21.07it/s, loss=0.0931, v_num=3, train_loss_step=0.0822, train_loss_epoch=0.0822]Epoch 108:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0931, v_num=3, train_loss_step=0.0822, train_loss_epoch=0.0822]        Epoch 109:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0931, v_num=3, train_loss_step=0.0822, train_loss_epoch=0.0822]Epoch 109: 100%|##########| 1/1 [00:00<00:00, 20.41it/s, loss=0.0931, v_num=3, train_loss_step=0.0822, train_loss_epoch=0.0822]Epoch 109: 100%|##########| 1/1 [00:00<00:00, 20.25it/s, loss=0.0922, v_num=3, train_loss_step=0.0844, train_loss_epoch=0.0822]Epoch 109: 100%|##########| 1/1 [00:00<00:00, 20.02it/s, loss=0.0922, v_num=3, train_loss_step=0.0844, train_loss_epoch=0.0844]Epoch 109:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0922, v_num=3, train_loss_step=0.0844, train_loss_epoch=0.0844]        Epoch 110:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0922, v_num=3, train_loss_step=0.0844, train_loss_epoch=0.0844]Epoch 110: 100%|##########| 1/1 [00:00<00:00, 20.13it/s, loss=0.0922, v_num=3, train_loss_step=0.0844, train_loss_epoch=0.0844]Epoch 110: 100%|##########| 1/1 [00:00<00:00, 19.87it/s, loss=0.0911, v_num=3, train_loss_step=0.0798, train_loss_epoch=0.0844]Epoch 110: 100%|##########| 1/1 [00:00<00:00, 19.64it/s, loss=0.0911, v_num=3, train_loss_step=0.0798, train_loss_epoch=0.0798]Epoch 110:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0911, v_num=3, train_loss_step=0.0798, train_loss_epoch=0.0798]        Epoch 111:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0911, v_num=3, train_loss_step=0.0798, train_loss_epoch=0.0798]Epoch 111: 100%|##########| 1/1 [00:00<00:00, 19.17it/s, loss=0.0911, v_num=3, train_loss_step=0.0798, train_loss_epoch=0.0798]Epoch 111: 100%|##########| 1/1 [00:00<00:00, 19.00it/s, loss=0.0898, v_num=3, train_loss_step=0.0759, train_loss_epoch=0.0798]Epoch 111: 100%|##########| 1/1 [00:00<00:00, 18.78it/s, loss=0.0898, v_num=3, train_loss_step=0.0759, train_loss_epoch=0.0759]Epoch 111:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0898, v_num=3, train_loss_step=0.0759, train_loss_epoch=0.0759]        Epoch 112:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0898, v_num=3, train_loss_step=0.0759, train_loss_epoch=0.0759]Epoch 112: 100%|##########| 1/1 [00:00<00:00, 21.28it/s, loss=0.0898, v_num=3, train_loss_step=0.0759, train_loss_epoch=0.0759]Epoch 112: 100%|##########| 1/1 [00:00<00:00, 21.02it/s, loss=0.0887, v_num=3, train_loss_step=0.0783, train_loss_epoch=0.0759]Epoch 112: 100%|##########| 1/1 [00:00<00:00, 20.77it/s, loss=0.0887, v_num=3, train_loss_step=0.0783, train_loss_epoch=0.0783]Epoch 112:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0887, v_num=3, train_loss_step=0.0783, train_loss_epoch=0.0783]        Epoch 113:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0887, v_num=3, train_loss_step=0.0783, train_loss_epoch=0.0783]Epoch 113: 100%|##########| 1/1 [00:00<00:00, 21.26it/s, loss=0.0887, v_num=3, train_loss_step=0.0783, train_loss_epoch=0.0783]Epoch 113: 100%|##########| 1/1 [00:00<00:00, 21.05it/s, loss=0.0879, v_num=3, train_loss_step=0.0804, train_loss_epoch=0.0783]Epoch 113: 100%|##########| 1/1 [00:00<00:00, 20.75it/s, loss=0.0879, v_num=3, train_loss_step=0.0804, train_loss_epoch=0.0804]Epoch 113:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0879, v_num=3, train_loss_step=0.0804, train_loss_epoch=0.0804]        Epoch 114:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0879, v_num=3, train_loss_step=0.0804, train_loss_epoch=0.0804]Epoch 114: 100%|##########| 1/1 [00:00<00:00, 21.15it/s, loss=0.0879, v_num=3, train_loss_step=0.0804, train_loss_epoch=0.0804]Epoch 114: 100%|##########| 1/1 [00:00<00:00, 20.93it/s, loss=0.0867, v_num=3, train_loss_step=0.0751, train_loss_epoch=0.0804]Epoch 114: 100%|##########| 1/1 [00:00<00:00, 20.66it/s, loss=0.0867, v_num=3, train_loss_step=0.0751, train_loss_epoch=0.0751]Epoch 114:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0867, v_num=3, train_loss_step=0.0751, train_loss_epoch=0.0751]        Epoch 115:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0867, v_num=3, train_loss_step=0.0751, train_loss_epoch=0.0751]Epoch 115: 100%|##########| 1/1 [00:00<00:00, 20.80it/s, loss=0.0867, v_num=3, train_loss_step=0.0751, train_loss_epoch=0.0751]Epoch 115: 100%|##########| 1/1 [00:00<00:00, 20.58it/s, loss=0.0856, v_num=3, train_loss_step=0.0727, train_loss_epoch=0.0751]Epoch 115: 100%|##########| 1/1 [00:00<00:00, 20.33it/s, loss=0.0856, v_num=3, train_loss_step=0.0727, train_loss_epoch=0.0727]Epoch 115:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0856, v_num=3, train_loss_step=0.0727, train_loss_epoch=0.0727]        Epoch 116:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0856, v_num=3, train_loss_step=0.0727, train_loss_epoch=0.0727]Epoch 116: 100%|##########| 1/1 [00:00<00:00, 21.71it/s, loss=0.0856, v_num=3, train_loss_step=0.0727, train_loss_epoch=0.0727]Epoch 116: 100%|##########| 1/1 [00:00<00:00, 21.52it/s, loss=0.0845, v_num=3, train_loss_step=0.0721, train_loss_epoch=0.0727]Epoch 116: 100%|##########| 1/1 [00:00<00:00, 21.25it/s, loss=0.0845, v_num=3, train_loss_step=0.0721, train_loss_epoch=0.0721]Epoch 116:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0845, v_num=3, train_loss_step=0.0721, train_loss_epoch=0.0721]        Epoch 117:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0845, v_num=3, train_loss_step=0.0721, train_loss_epoch=0.0721]Epoch 117: 100%|##########| 1/1 [00:00<00:00, 20.35it/s, loss=0.0845, v_num=3, train_loss_step=0.0721, train_loss_epoch=0.0721]Epoch 117: 100%|##########| 1/1 [00:00<00:00, 20.19it/s, loss=0.0834, v_num=3, train_loss_step=0.0725, train_loss_epoch=0.0721]Epoch 117: 100%|##########| 1/1 [00:00<00:00, 19.93it/s, loss=0.0834, v_num=3, train_loss_step=0.0725, train_loss_epoch=0.0725]Epoch 117:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0834, v_num=3, train_loss_step=0.0725, train_loss_epoch=0.0725]        Epoch 118:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0834, v_num=3, train_loss_step=0.0725, train_loss_epoch=0.0725]Epoch 118: 100%|##########| 1/1 [00:00<00:00, 20.76it/s, loss=0.0834, v_num=3, train_loss_step=0.0725, train_loss_epoch=0.0725]Epoch 118: 100%|##########| 1/1 [00:00<00:00, 20.54it/s, loss=0.0822, v_num=3, train_loss_step=0.072, train_loss_epoch=0.0725] Epoch 118: 100%|##########| 1/1 [00:00<00:00, 20.28it/s, loss=0.0822, v_num=3, train_loss_step=0.072, train_loss_epoch=0.072] Epoch 118:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0822, v_num=3, train_loss_step=0.072, train_loss_epoch=0.072]        Epoch 119:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0822, v_num=3, train_loss_step=0.072, train_loss_epoch=0.072]Epoch 119: 100%|##########| 1/1 [00:00<00:00, 20.87it/s, loss=0.0822, v_num=3, train_loss_step=0.072, train_loss_epoch=0.072]Epoch 119: 100%|##########| 1/1 [00:00<00:00, 20.71it/s, loss=0.0806, v_num=3, train_loss_step=0.0678, train_loss_epoch=0.072]Epoch 119: 100%|##########| 1/1 [00:00<00:00, 20.48it/s, loss=0.0806, v_num=3, train_loss_step=0.0678, train_loss_epoch=0.0678]Epoch 119:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0806, v_num=3, train_loss_step=0.0678, train_loss_epoch=0.0678]        Epoch 120:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0806, v_num=3, train_loss_step=0.0678, train_loss_epoch=0.0678]Epoch 120: 100%|##########| 1/1 [00:00<00:00, 21.10it/s, loss=0.0806, v_num=3, train_loss_step=0.0678, train_loss_epoch=0.0678]Epoch 120: 100%|##########| 1/1 [00:00<00:00, 20.90it/s, loss=0.0794, v_num=3, train_loss_step=0.0674, train_loss_epoch=0.0678]Epoch 120: 100%|##########| 1/1 [00:00<00:00, 20.67it/s, loss=0.0794, v_num=3, train_loss_step=0.0674, train_loss_epoch=0.0674]Epoch 120:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0794, v_num=3, train_loss_step=0.0674, train_loss_epoch=0.0674]        Epoch 121:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0794, v_num=3, train_loss_step=0.0674, train_loss_epoch=0.0674]Epoch 121: 100%|##########| 1/1 [00:00<00:00, 20.63it/s, loss=0.0794, v_num=3, train_loss_step=0.0674, train_loss_epoch=0.0674]Epoch 121: 100%|##########| 1/1 [00:00<00:00, 20.46it/s, loss=0.0782, v_num=3, train_loss_step=0.0658, train_loss_epoch=0.0674]Epoch 121: 100%|##########| 1/1 [00:00<00:00, 20.17it/s, loss=0.0782, v_num=3, train_loss_step=0.0658, train_loss_epoch=0.0658]Epoch 121:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0782, v_num=3, train_loss_step=0.0658, train_loss_epoch=0.0658]        Epoch 122:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0782, v_num=3, train_loss_step=0.0658, train_loss_epoch=0.0658]Epoch 122: 100%|##########| 1/1 [00:00<00:00, 20.84it/s, loss=0.0782, v_num=3, train_loss_step=0.0658, train_loss_epoch=0.0658]Epoch 122: 100%|##########| 1/1 [00:00<00:00, 20.65it/s, loss=0.0769, v_num=3, train_loss_step=0.0655, train_loss_epoch=0.0658]Epoch 122: 100%|##########| 1/1 [00:00<00:00, 20.37it/s, loss=0.0769, v_num=3, train_loss_step=0.0655, train_loss_epoch=0.0655]Epoch 122:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0769, v_num=3, train_loss_step=0.0655, train_loss_epoch=0.0655]        Epoch 123:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0769, v_num=3, train_loss_step=0.0655, train_loss_epoch=0.0655]Epoch 123: 100%|##########| 1/1 [00:00<00:00, 20.96it/s, loss=0.0769, v_num=3, train_loss_step=0.0655, train_loss_epoch=0.0655]Epoch 123: 100%|##########| 1/1 [00:00<00:00, 20.79it/s, loss=0.0757, v_num=3, train_loss_step=0.0664, train_loss_epoch=0.0655]Epoch 123: 100%|##########| 1/1 [00:00<00:00, 20.55it/s, loss=0.0757, v_num=3, train_loss_step=0.0664, train_loss_epoch=0.0664]Epoch 123:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0757, v_num=3, train_loss_step=0.0664, train_loss_epoch=0.0664]        Epoch 124:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0757, v_num=3, train_loss_step=0.0664, train_loss_epoch=0.0664]Epoch 124: 100%|##########| 1/1 [00:00<00:00, 20.16it/s, loss=0.0757, v_num=3, train_loss_step=0.0664, train_loss_epoch=0.0664]Epoch 124: 100%|##########| 1/1 [00:00<00:00, 19.95it/s, loss=0.0746, v_num=3, train_loss_step=0.0629, train_loss_epoch=0.0664]Epoch 124: 100%|##########| 1/1 [00:00<00:00, 19.70it/s, loss=0.0746, v_num=3, train_loss_step=0.0629, train_loss_epoch=0.0629]Epoch 124:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0746, v_num=3, train_loss_step=0.0629, train_loss_epoch=0.0629]        Epoch 125:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0746, v_num=3, train_loss_step=0.0629, train_loss_epoch=0.0629]Epoch 125: 100%|##########| 1/1 [00:00<00:00, 19.82it/s, loss=0.0746, v_num=3, train_loss_step=0.0629, train_loss_epoch=0.0629]Epoch 125: 100%|##########| 1/1 [00:00<00:00, 19.66it/s, loss=0.0735, v_num=3, train_loss_step=0.0635, train_loss_epoch=0.0629]Epoch 125: 100%|##########| 1/1 [00:00<00:00, 19.41it/s, loss=0.0735, v_num=3, train_loss_step=0.0635, train_loss_epoch=0.0635]Epoch 125:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0735, v_num=3, train_loss_step=0.0635, train_loss_epoch=0.0635]        Epoch 126:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0735, v_num=3, train_loss_step=0.0635, train_loss_epoch=0.0635]Epoch 126: 100%|##########| 1/1 [00:00<00:00, 20.66it/s, loss=0.0735, v_num=3, train_loss_step=0.0635, train_loss_epoch=0.0635]Epoch 126: 100%|##########| 1/1 [00:00<00:00, 20.46it/s, loss=0.0725, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.0635]Epoch 126: 100%|##########| 1/1 [00:00<00:00, 20.20it/s, loss=0.0725, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 126:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0725, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.0633]        Epoch 127:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0725, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 127: 100%|##########| 1/1 [00:00<00:00, 20.61it/s, loss=0.0725, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 127: 100%|##########| 1/1 [00:00<00:00, 20.45it/s, loss=0.0714, v_num=3, train_loss_step=0.060, train_loss_epoch=0.0633] Epoch 127: 100%|##########| 1/1 [00:00<00:00, 20.21it/s, loss=0.0714, v_num=3, train_loss_step=0.060, train_loss_epoch=0.060] Epoch 127:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0714, v_num=3, train_loss_step=0.060, train_loss_epoch=0.060]        Epoch 128:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0714, v_num=3, train_loss_step=0.060, train_loss_epoch=0.060]Epoch 128: 100%|##########| 1/1 [00:00<00:00, 20.37it/s, loss=0.0714, v_num=3, train_loss_step=0.060, train_loss_epoch=0.060]Epoch 128: 100%|##########| 1/1 [00:00<00:00, 20.18it/s, loss=0.0705, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.060]Epoch 128: 100%|##########| 1/1 [00:00<00:00, 19.92it/s, loss=0.0705, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 128:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0705, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.0633]        Epoch 129:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0705, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 129: 100%|##########| 1/1 [00:00<00:00, 19.83it/s, loss=0.0705, v_num=3, train_loss_step=0.0633, train_loss_epoch=0.0633]Epoch 129: 100%|##########| 1/1 [00:00<00:00, 19.59it/s, loss=0.0693, v_num=3, train_loss_step=0.062, train_loss_epoch=0.0633] Epoch 129: 100%|##########| 1/1 [00:00<00:00, 19.36it/s, loss=0.0693, v_num=3, train_loss_step=0.062, train_loss_epoch=0.062] Epoch 129:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0693, v_num=3, train_loss_step=0.062, train_loss_epoch=0.062]        Epoch 130:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0693, v_num=3, train_loss_step=0.062, train_loss_epoch=0.062]Epoch 130: 100%|##########| 1/1 [00:00<00:00, 19.84it/s, loss=0.0693, v_num=3, train_loss_step=0.062, train_loss_epoch=0.062]Epoch 130: 100%|##########| 1/1 [00:00<00:00, 19.67it/s, loss=0.0683, v_num=3, train_loss_step=0.0584, train_loss_epoch=0.062]Epoch 130: 100%|##########| 1/1 [00:00<00:00, 19.42it/s, loss=0.0683, v_num=3, train_loss_step=0.0584, train_loss_epoch=0.0584]Epoch 130:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0683, v_num=3, train_loss_step=0.0584, train_loss_epoch=0.0584]        Epoch 131:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0683, v_num=3, train_loss_step=0.0584, train_loss_epoch=0.0584]Epoch 131: 100%|##########| 1/1 [00:00<00:00, 19.53it/s, loss=0.0683, v_num=3, train_loss_step=0.0584, train_loss_epoch=0.0584]Epoch 131: 100%|##########| 1/1 [00:00<00:00, 19.32it/s, loss=0.0675, v_num=3, train_loss_step=0.0613, train_loss_epoch=0.0584]Epoch 131: 100%|##########| 1/1 [00:00<00:00, 19.08it/s, loss=0.0675, v_num=3, train_loss_step=0.0613, train_loss_epoch=0.0613]Epoch 131:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0675, v_num=3, train_loss_step=0.0613, train_loss_epoch=0.0613]        Epoch 132:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0675, v_num=3, train_loss_step=0.0613, train_loss_epoch=0.0613]Epoch 132: 100%|##########| 1/1 [00:00<00:00, 19.67it/s, loss=0.0675, v_num=3, train_loss_step=0.0613, train_loss_epoch=0.0613]Epoch 132: 100%|##########| 1/1 [00:00<00:00, 19.46it/s, loss=0.0665, v_num=3, train_loss_step=0.0577, train_loss_epoch=0.0613]Epoch 132: 100%|##########| 1/1 [00:00<00:00, 19.21it/s, loss=0.0665, v_num=3, train_loss_step=0.0577, train_loss_epoch=0.0577]Epoch 132:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0665, v_num=3, train_loss_step=0.0577, train_loss_epoch=0.0577]        Epoch 133:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0665, v_num=3, train_loss_step=0.0577, train_loss_epoch=0.0577]Epoch 133: 100%|##########| 1/1 [00:00<00:00, 19.55it/s, loss=0.0665, v_num=3, train_loss_step=0.0577, train_loss_epoch=0.0577]Epoch 133: 100%|##########| 1/1 [00:00<00:00, 19.32it/s, loss=0.0653, v_num=3, train_loss_step=0.0573, train_loss_epoch=0.0577]Epoch 133: 100%|##########| 1/1 [00:00<00:00, 19.08it/s, loss=0.0653, v_num=3, train_loss_step=0.0573, train_loss_epoch=0.0573]Epoch 133:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0653, v_num=3, train_loss_step=0.0573, train_loss_epoch=0.0573]        Epoch 134:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0653, v_num=3, train_loss_step=0.0573, train_loss_epoch=0.0573]Epoch 134: 100%|##########| 1/1 [00:00<00:00, 19.64it/s, loss=0.0653, v_num=3, train_loss_step=0.0573, train_loss_epoch=0.0573]Epoch 134: 100%|##########| 1/1 [00:00<00:00, 19.46it/s, loss=0.0644, v_num=3, train_loss_step=0.0569, train_loss_epoch=0.0573]Epoch 134: 100%|##########| 1/1 [00:00<00:00, 19.21it/s, loss=0.0644, v_num=3, train_loss_step=0.0569, train_loss_epoch=0.0569]Epoch 134:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0644, v_num=3, train_loss_step=0.0569, train_loss_epoch=0.0569]        Epoch 135:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0644, v_num=3, train_loss_step=0.0569, train_loss_epoch=0.0569]Epoch 135: 100%|##########| 1/1 [00:00<00:00, 20.63it/s, loss=0.0644, v_num=3, train_loss_step=0.0569, train_loss_epoch=0.0569]Epoch 135: 100%|##########| 1/1 [00:00<00:00, 20.45it/s, loss=0.0636, v_num=3, train_loss_step=0.0557, train_loss_epoch=0.0569]Epoch 135: 100%|##########| 1/1 [00:00<00:00, 20.21it/s, loss=0.0636, v_num=3, train_loss_step=0.0557, train_loss_epoch=0.0557]Epoch 135:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0636, v_num=3, train_loss_step=0.0557, train_loss_epoch=0.0557]        Epoch 136:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0636, v_num=3, train_loss_step=0.0557, train_loss_epoch=0.0557]Epoch 136: 100%|##########| 1/1 [00:00<00:00, 20.65it/s, loss=0.0636, v_num=3, train_loss_step=0.0557, train_loss_epoch=0.0557]Epoch 136: 100%|##########| 1/1 [00:00<00:00, 20.49it/s, loss=0.0628, v_num=3, train_loss_step=0.0561, train_loss_epoch=0.0557]Epoch 136: 100%|##########| 1/1 [00:00<00:00, 20.26it/s, loss=0.0628, v_num=3, train_loss_step=0.0561, train_loss_epoch=0.0561]Epoch 136:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0628, v_num=3, train_loss_step=0.0561, train_loss_epoch=0.0561]        Epoch 137:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0628, v_num=3, train_loss_step=0.0561, train_loss_epoch=0.0561]Epoch 137: 100%|##########| 1/1 [00:00<00:00, 20.62it/s, loss=0.0628, v_num=3, train_loss_step=0.0561, train_loss_epoch=0.0561]Epoch 137: 100%|##########| 1/1 [00:00<00:00, 20.42it/s, loss=0.0619, v_num=3, train_loss_step=0.0543, train_loss_epoch=0.0561]Epoch 137: 100%|##########| 1/1 [00:00<00:00, 20.18it/s, loss=0.0619, v_num=3, train_loss_step=0.0543, train_loss_epoch=0.0543]Epoch 137:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0619, v_num=3, train_loss_step=0.0543, train_loss_epoch=0.0543]        Epoch 138:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0619, v_num=3, train_loss_step=0.0543, train_loss_epoch=0.0543]Epoch 138: 100%|##########| 1/1 [00:00<00:00, 21.05it/s, loss=0.0619, v_num=3, train_loss_step=0.0543, train_loss_epoch=0.0543]Epoch 138: 100%|##########| 1/1 [00:00<00:00, 20.87it/s, loss=0.061, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0543] Epoch 138: 100%|##########| 1/1 [00:00<00:00, 20.60it/s, loss=0.061, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 138:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.061, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0539]        Epoch 139:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.061, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 139: 100%|##########| 1/1 [00:00<00:00, 20.65it/s, loss=0.061, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 139: 100%|##########| 1/1 [00:00<00:00, 20.44it/s, loss=0.0603, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 139: 100%|##########| 1/1 [00:00<00:00, 20.18it/s, loss=0.0603, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 139:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0603, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0539]        Epoch 140:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0603, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 140: 100%|##########| 1/1 [00:00<00:00, 21.30it/s, loss=0.0603, v_num=3, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 140: 100%|##########| 1/1 [00:00<00:00, 21.14it/s, loss=0.0596, v_num=3, train_loss_step=0.0537, train_loss_epoch=0.0539]Epoch 140: 100%|##########| 1/1 [00:00<00:00, 20.91it/s, loss=0.0596, v_num=3, train_loss_step=0.0537, train_loss_epoch=0.0537]Epoch 140:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0596, v_num=3, train_loss_step=0.0537, train_loss_epoch=0.0537]        Epoch 141:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0596, v_num=3, train_loss_step=0.0537, train_loss_epoch=0.0537]Epoch 141: 100%|##########| 1/1 [00:00<00:00, 20.78it/s, loss=0.0596, v_num=3, train_loss_step=0.0537, train_loss_epoch=0.0537]Epoch 141: 100%|##########| 1/1 [00:00<00:00, 20.55it/s, loss=0.0589, v_num=3, train_loss_step=0.0515, train_loss_epoch=0.0537]Epoch 141: 100%|##########| 1/1 [00:00<00:00, 20.28it/s, loss=0.0589, v_num=3, train_loss_step=0.0515, train_loss_epoch=0.0515]Epoch 141:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0589, v_num=3, train_loss_step=0.0515, train_loss_epoch=0.0515]        Epoch 142:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0589, v_num=3, train_loss_step=0.0515, train_loss_epoch=0.0515]Epoch 142: 100%|##########| 1/1 [00:00<00:00, 20.99it/s, loss=0.0589, v_num=3, train_loss_step=0.0515, train_loss_epoch=0.0515]Epoch 142: 100%|##########| 1/1 [00:00<00:00, 20.78it/s, loss=0.0581, v_num=3, train_loss_step=0.0502, train_loss_epoch=0.0515]Epoch 142: 100%|##########| 1/1 [00:00<00:00, 20.48it/s, loss=0.0581, v_num=3, train_loss_step=0.0502, train_loss_epoch=0.0502]Epoch 142:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0581, v_num=3, train_loss_step=0.0502, train_loss_epoch=0.0502]        Epoch 143:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0581, v_num=3, train_loss_step=0.0502, train_loss_epoch=0.0502]Epoch 143: 100%|##########| 1/1 [00:00<00:00, 20.26it/s, loss=0.0581, v_num=3, train_loss_step=0.0502, train_loss_epoch=0.0502]Epoch 143: 100%|##########| 1/1 [00:00<00:00, 20.10it/s, loss=0.0572, v_num=3, train_loss_step=0.0484, train_loss_epoch=0.0502]Epoch 143: 100%|##########| 1/1 [00:00<00:00, 19.88it/s, loss=0.0572, v_num=3, train_loss_step=0.0484, train_loss_epoch=0.0484]Epoch 143:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0572, v_num=3, train_loss_step=0.0484, train_loss_epoch=0.0484]        Epoch 144:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0572, v_num=3, train_loss_step=0.0484, train_loss_epoch=0.0484]Epoch 144: 100%|##########| 1/1 [00:00<00:00, 20.99it/s, loss=0.0572, v_num=3, train_loss_step=0.0484, train_loss_epoch=0.0484]Epoch 144: 100%|##########| 1/1 [00:00<00:00, 20.81it/s, loss=0.0566, v_num=3, train_loss_step=0.050, train_loss_epoch=0.0484] Epoch 144: 100%|##########| 1/1 [00:00<00:00, 20.54it/s, loss=0.0566, v_num=3, train_loss_step=0.050, train_loss_epoch=0.050] Epoch 144:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0566, v_num=3, train_loss_step=0.050, train_loss_epoch=0.050]        Epoch 145:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0566, v_num=3, train_loss_step=0.050, train_loss_epoch=0.050]Epoch 145: 100%|##########| 1/1 [00:00<00:00, 19.94it/s, loss=0.0566, v_num=3, train_loss_step=0.050, train_loss_epoch=0.050]Epoch 145: 100%|##########| 1/1 [00:00<00:00, 19.72it/s, loss=0.0559, v_num=3, train_loss_step=0.0509, train_loss_epoch=0.050]Epoch 145: 100%|##########| 1/1 [00:00<00:00, 19.46it/s, loss=0.0559, v_num=3, train_loss_step=0.0509, train_loss_epoch=0.0509]Epoch 145:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0559, v_num=3, train_loss_step=0.0509, train_loss_epoch=0.0509]        Epoch 146:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0559, v_num=3, train_loss_step=0.0509, train_loss_epoch=0.0509]Epoch 146: 100%|##########| 1/1 [00:00<00:00, 19.59it/s, loss=0.0559, v_num=3, train_loss_step=0.0509, train_loss_epoch=0.0509]Epoch 146: 100%|##########| 1/1 [00:00<00:00, 19.34it/s, loss=0.0554, v_num=3, train_loss_step=0.0516, train_loss_epoch=0.0509]Epoch 146: 100%|##########| 1/1 [00:00<00:00, 19.12it/s, loss=0.0554, v_num=3, train_loss_step=0.0516, train_loss_epoch=0.0516]Epoch 146:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0554, v_num=3, train_loss_step=0.0516, train_loss_epoch=0.0516]        Epoch 147:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0554, v_num=3, train_loss_step=0.0516, train_loss_epoch=0.0516]Epoch 147: 100%|##########| 1/1 [00:00<00:00, 20.61it/s, loss=0.0554, v_num=3, train_loss_step=0.0516, train_loss_epoch=0.0516]Epoch 147: 100%|##########| 1/1 [00:00<00:00, 20.45it/s, loss=0.0548, v_num=3, train_loss_step=0.0488, train_loss_epoch=0.0516]Epoch 147: 100%|##########| 1/1 [00:00<00:00, 20.20it/s, loss=0.0548, v_num=3, train_loss_step=0.0488, train_loss_epoch=0.0488]Epoch 147:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0548, v_num=3, train_loss_step=0.0488, train_loss_epoch=0.0488]        Epoch 148:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0548, v_num=3, train_loss_step=0.0488, train_loss_epoch=0.0488]Epoch 148: 100%|##########| 1/1 [00:00<00:00, 20.48it/s, loss=0.0548, v_num=3, train_loss_step=0.0488, train_loss_epoch=0.0488]Epoch 148: 100%|##########| 1/1 [00:00<00:00, 20.32it/s, loss=0.054, v_num=3, train_loss_step=0.0478, train_loss_epoch=0.0488] Epoch 148: 100%|##########| 1/1 [00:00<00:00, 20.07it/s, loss=0.054, v_num=3, train_loss_step=0.0478, train_loss_epoch=0.0478]Epoch 148:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.054, v_num=3, train_loss_step=0.0478, train_loss_epoch=0.0478]        Epoch 149:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.054, v_num=3, train_loss_step=0.0478, train_loss_epoch=0.0478]Epoch 149: 100%|##########| 1/1 [00:00<00:00, 21.13it/s, loss=0.054, v_num=3, train_loss_step=0.0478, train_loss_epoch=0.0478]Epoch 149: 100%|##########| 1/1 [00:00<00:00, 20.95it/s, loss=0.0532, v_num=3, train_loss_step=0.0466, train_loss_epoch=0.0478]Epoch 149: 100%|##########| 1/1 [00:00<00:00, 20.42it/s, loss=0.0532, v_num=3, train_loss_step=0.0466, train_loss_epoch=0.0466]Epoch 149:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0532, v_num=3, train_loss_step=0.0466, train_loss_epoch=0.0466]        Epoch 150:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0532, v_num=3, train_loss_step=0.0466, train_loss_epoch=0.0466]Epoch 150: 100%|##########| 1/1 [00:00<00:00, 20.69it/s, loss=0.0532, v_num=3, train_loss_step=0.0466, train_loss_epoch=0.0466]Epoch 150: 100%|##########| 1/1 [00:00<00:00, 20.43it/s, loss=0.0526, v_num=3, train_loss_step=0.0452, train_loss_epoch=0.0466]Epoch 150: 100%|##########| 1/1 [00:00<00:00, 20.18it/s, loss=0.0526, v_num=3, train_loss_step=0.0452, train_loss_epoch=0.0452]Epoch 150:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0526, v_num=3, train_loss_step=0.0452, train_loss_epoch=0.0452]        Epoch 151:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0526, v_num=3, train_loss_step=0.0452, train_loss_epoch=0.0452]Epoch 151: 100%|##########| 1/1 [00:00<00:00, 21.09it/s, loss=0.0526, v_num=3, train_loss_step=0.0452, train_loss_epoch=0.0452]Epoch 151: 100%|##########| 1/1 [00:00<00:00, 20.91it/s, loss=0.0518, v_num=3, train_loss_step=0.0464, train_loss_epoch=0.0452]Epoch 151: 100%|##########| 1/1 [00:00<00:00, 20.64it/s, loss=0.0518, v_num=3, train_loss_step=0.0464, train_loss_epoch=0.0464]Epoch 151:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0518, v_num=3, train_loss_step=0.0464, train_loss_epoch=0.0464]        Epoch 152:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0518, v_num=3, train_loss_step=0.0464, train_loss_epoch=0.0464]Epoch 152: 100%|##########| 1/1 [00:00<00:00, 20.70it/s, loss=0.0518, v_num=3, train_loss_step=0.0464, train_loss_epoch=0.0464]Epoch 152: 100%|##########| 1/1 [00:00<00:00, 20.54it/s, loss=0.0512, v_num=3, train_loss_step=0.0457, train_loss_epoch=0.0464]Epoch 152: 100%|##########| 1/1 [00:00<00:00, 20.27it/s, loss=0.0512, v_num=3, train_loss_step=0.0457, train_loss_epoch=0.0457]Epoch 152:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0512, v_num=3, train_loss_step=0.0457, train_loss_epoch=0.0457]        Epoch 153:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0512, v_num=3, train_loss_step=0.0457, train_loss_epoch=0.0457]Epoch 153: 100%|##########| 1/1 [00:00<00:00, 21.87it/s, loss=0.0512, v_num=3, train_loss_step=0.0457, train_loss_epoch=0.0457]Epoch 153: 100%|##########| 1/1 [00:00<00:00, 21.67it/s, loss=0.0506, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0457]Epoch 153: 100%|##########| 1/1 [00:00<00:00, 21.43it/s, loss=0.0506, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0453]Epoch 153:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0506, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0453]        Epoch 154:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0506, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0453]Epoch 154: 100%|##########| 1/1 [00:00<00:00, 20.63it/s, loss=0.0506, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0453]Epoch 154: 100%|##########| 1/1 [00:00<00:00, 20.41it/s, loss=0.05, v_num=3, train_loss_step=0.0442, train_loss_epoch=0.0453]  Epoch 154: 100%|##########| 1/1 [00:00<00:00, 20.14it/s, loss=0.05, v_num=3, train_loss_step=0.0442, train_loss_epoch=0.0442]Epoch 154:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.05, v_num=3, train_loss_step=0.0442, train_loss_epoch=0.0442]        Epoch 155:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.05, v_num=3, train_loss_step=0.0442, train_loss_epoch=0.0442]Epoch 155: 100%|##########| 1/1 [00:00<00:00, 19.95it/s, loss=0.05, v_num=3, train_loss_step=0.0442, train_loss_epoch=0.0442]Epoch 155: 100%|##########| 1/1 [00:00<00:00, 19.75it/s, loss=0.0494, v_num=3, train_loss_step=0.0441, train_loss_epoch=0.0442]Epoch 155: 100%|##########| 1/1 [00:00<00:00, 19.52it/s, loss=0.0494, v_num=3, train_loss_step=0.0441, train_loss_epoch=0.0441]Epoch 155:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0494, v_num=3, train_loss_step=0.0441, train_loss_epoch=0.0441]        Epoch 156:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0494, v_num=3, train_loss_step=0.0441, train_loss_epoch=0.0441]Epoch 156: 100%|##########| 1/1 [00:00<00:00, 20.18it/s, loss=0.0494, v_num=3, train_loss_step=0.0441, train_loss_epoch=0.0441]Epoch 156: 100%|##########| 1/1 [00:00<00:00, 20.04it/s, loss=0.0487, v_num=3, train_loss_step=0.0412, train_loss_epoch=0.0441]Epoch 156: 100%|##########| 1/1 [00:00<00:00, 19.83it/s, loss=0.0487, v_num=3, train_loss_step=0.0412, train_loss_epoch=0.0412]Epoch 156:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0487, v_num=3, train_loss_step=0.0412, train_loss_epoch=0.0412]        Epoch 157:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0487, v_num=3, train_loss_step=0.0412, train_loss_epoch=0.0412]Epoch 157: 100%|##########| 1/1 [00:00<00:00, 20.79it/s, loss=0.0487, v_num=3, train_loss_step=0.0412, train_loss_epoch=0.0412]Epoch 157: 100%|##########| 1/1 [00:00<00:00, 20.58it/s, loss=0.048, v_num=3, train_loss_step=0.0415, train_loss_epoch=0.0412] Epoch 157: 100%|##########| 1/1 [00:00<00:00, 20.32it/s, loss=0.048, v_num=3, train_loss_step=0.0415, train_loss_epoch=0.0415]Epoch 157:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.048, v_num=3, train_loss_step=0.0415, train_loss_epoch=0.0415]        Epoch 158:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.048, v_num=3, train_loss_step=0.0415, train_loss_epoch=0.0415]Epoch 158: 100%|##########| 1/1 [00:00<00:00, 21.48it/s, loss=0.048, v_num=3, train_loss_step=0.0415, train_loss_epoch=0.0415]Epoch 158: 100%|##########| 1/1 [00:00<00:00, 21.30it/s, loss=0.0474, v_num=3, train_loss_step=0.0416, train_loss_epoch=0.0415]Epoch 158: 100%|##########| 1/1 [00:00<00:00, 21.01it/s, loss=0.0474, v_num=3, train_loss_step=0.0416, train_loss_epoch=0.0416]Epoch 158:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0474, v_num=3, train_loss_step=0.0416, train_loss_epoch=0.0416]        Epoch 159:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0474, v_num=3, train_loss_step=0.0416, train_loss_epoch=0.0416]Epoch 159: 100%|##########| 1/1 [00:00<00:00, 20.83it/s, loss=0.0474, v_num=3, train_loss_step=0.0416, train_loss_epoch=0.0416]Epoch 159: 100%|##########| 1/1 [00:00<00:00, 20.62it/s, loss=0.0468, v_num=3, train_loss_step=0.041, train_loss_epoch=0.0416] Epoch 159: 100%|##########| 1/1 [00:00<00:00, 20.35it/s, loss=0.0468, v_num=3, train_loss_step=0.041, train_loss_epoch=0.041] Epoch 159:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0468, v_num=3, train_loss_step=0.041, train_loss_epoch=0.041]        Epoch 160:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0468, v_num=3, train_loss_step=0.041, train_loss_epoch=0.041]Epoch 160: 100%|##########| 1/1 [00:00<00:00, 20.93it/s, loss=0.0468, v_num=3, train_loss_step=0.041, train_loss_epoch=0.041]Epoch 160: 100%|##########| 1/1 [00:00<00:00, 20.77it/s, loss=0.0465, v_num=3, train_loss_step=0.0474, train_loss_epoch=0.041]Epoch 160: 100%|##########| 1/1 [00:00<00:00, 20.51it/s, loss=0.0465, v_num=3, train_loss_step=0.0474, train_loss_epoch=0.0474]Epoch 160:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0465, v_num=3, train_loss_step=0.0474, train_loss_epoch=0.0474]        Epoch 161:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0465, v_num=3, train_loss_step=0.0474, train_loss_epoch=0.0474]Epoch 161: 100%|##########| 1/1 [00:00<00:00, 21.09it/s, loss=0.0465, v_num=3, train_loss_step=0.0474, train_loss_epoch=0.0474]Epoch 161: 100%|##########| 1/1 [00:00<00:00, 20.94it/s, loss=0.0465, v_num=3, train_loss_step=0.0518, train_loss_epoch=0.0474]Epoch 161: 100%|##########| 1/1 [00:00<00:00, 20.71it/s, loss=0.0465, v_num=3, train_loss_step=0.0518, train_loss_epoch=0.0518]Epoch 161:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0465, v_num=3, train_loss_step=0.0518, train_loss_epoch=0.0518]        Epoch 162:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0465, v_num=3, train_loss_step=0.0518, train_loss_epoch=0.0518]Epoch 162: 100%|##########| 1/1 [00:00<00:00, 20.95it/s, loss=0.0465, v_num=3, train_loss_step=0.0518, train_loss_epoch=0.0518]Epoch 162: 100%|##########| 1/1 [00:00<00:00, 20.78it/s, loss=0.0462, v_num=3, train_loss_step=0.045, train_loss_epoch=0.0518] Epoch 162: 100%|##########| 1/1 [00:00<00:00, 20.50it/s, loss=0.0462, v_num=3, train_loss_step=0.045, train_loss_epoch=0.045] Epoch 162:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0462, v_num=3, train_loss_step=0.045, train_loss_epoch=0.045]        Epoch 163:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0462, v_num=3, train_loss_step=0.045, train_loss_epoch=0.045]Epoch 163: 100%|##########| 1/1 [00:00<00:00, 21.78it/s, loss=0.0462, v_num=3, train_loss_step=0.045, train_loss_epoch=0.045]Epoch 163: 100%|##########| 1/1 [00:00<00:00, 21.56it/s, loss=0.0457, v_num=3, train_loss_step=0.0377, train_loss_epoch=0.045]Epoch 163: 100%|##########| 1/1 [00:00<00:00, 21.32it/s, loss=0.0457, v_num=3, train_loss_step=0.0377, train_loss_epoch=0.0377]Epoch 163:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0457, v_num=3, train_loss_step=0.0377, train_loss_epoch=0.0377]        Epoch 164:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0457, v_num=3, train_loss_step=0.0377, train_loss_epoch=0.0377]Epoch 164: 100%|##########| 1/1 [00:00<00:00, 21.85it/s, loss=0.0457, v_num=3, train_loss_step=0.0377, train_loss_epoch=0.0377]Epoch 164: 100%|##########| 1/1 [00:00<00:00, 21.69it/s, loss=0.0453, v_num=3, train_loss_step=0.0426, train_loss_epoch=0.0377]Epoch 164: 100%|##########| 1/1 [00:00<00:00, 21.45it/s, loss=0.0453, v_num=3, train_loss_step=0.0426, train_loss_epoch=0.0426]Epoch 164:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0453, v_num=3, train_loss_step=0.0426, train_loss_epoch=0.0426]        Epoch 165:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0453, v_num=3, train_loss_step=0.0426, train_loss_epoch=0.0426]Epoch 165: 100%|##########| 1/1 [00:00<00:00, 21.32it/s, loss=0.0453, v_num=3, train_loss_step=0.0426, train_loss_epoch=0.0426]Epoch 165: 100%|##########| 1/1 [00:00<00:00, 21.10it/s, loss=0.0451, v_num=3, train_loss_step=0.0465, train_loss_epoch=0.0426]Epoch 165: 100%|##########| 1/1 [00:00<00:00, 20.84it/s, loss=0.0451, v_num=3, train_loss_step=0.0465, train_loss_epoch=0.0465]Epoch 165:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0451, v_num=3, train_loss_step=0.0465, train_loss_epoch=0.0465]        Epoch 166:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0451, v_num=3, train_loss_step=0.0465, train_loss_epoch=0.0465]Epoch 166: 100%|##########| 1/1 [00:00<00:00, 21.65it/s, loss=0.0451, v_num=3, train_loss_step=0.0465, train_loss_epoch=0.0465]Epoch 166: 100%|##########| 1/1 [00:00<00:00, 21.42it/s, loss=0.0448, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0465]Epoch 166: 100%|##########| 1/1 [00:00<00:00, 21.16it/s, loss=0.0448, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0453]Epoch 166:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0448, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0453]        Epoch 167:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0448, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0453]Epoch 167: 100%|##########| 1/1 [00:00<00:00, 20.83it/s, loss=0.0448, v_num=3, train_loss_step=0.0453, train_loss_epoch=0.0453]Epoch 167: 100%|##########| 1/1 [00:00<00:00, 20.66it/s, loss=0.0442, v_num=3, train_loss_step=0.0376, train_loss_epoch=0.0453]Epoch 167: 100%|##########| 1/1 [00:00<00:00, 20.41it/s, loss=0.0442, v_num=3, train_loss_step=0.0376, train_loss_epoch=0.0376]Epoch 167:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0442, v_num=3, train_loss_step=0.0376, train_loss_epoch=0.0376]        Epoch 168:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0442, v_num=3, train_loss_step=0.0376, train_loss_epoch=0.0376]Epoch 168: 100%|##########| 1/1 [00:00<00:00, 22.20it/s, loss=0.0442, v_num=3, train_loss_step=0.0376, train_loss_epoch=0.0376]Epoch 168: 100%|##########| 1/1 [00:00<00:00, 21.98it/s, loss=0.044, v_num=3, train_loss_step=0.0434, train_loss_epoch=0.0376] Epoch 168: 100%|##########| 1/1 [00:00<00:00, 21.68it/s, loss=0.044, v_num=3, train_loss_step=0.0434, train_loss_epoch=0.0434]Epoch 168:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.044, v_num=3, train_loss_step=0.0434, train_loss_epoch=0.0434]        Epoch 169:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.044, v_num=3, train_loss_step=0.0434, train_loss_epoch=0.0434]Epoch 169: 100%|##########| 1/1 [00:00<00:00, 21.47it/s, loss=0.044, v_num=3, train_loss_step=0.0434, train_loss_epoch=0.0434]Epoch 169: 100%|##########| 1/1 [00:00<00:00, 21.26it/s, loss=0.0437, v_num=3, train_loss_step=0.0409, train_loss_epoch=0.0434]Epoch 169: 100%|##########| 1/1 [00:00<00:00, 21.01it/s, loss=0.0437, v_num=3, train_loss_step=0.0409, train_loss_epoch=0.0409]Epoch 169:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0437, v_num=3, train_loss_step=0.0409, train_loss_epoch=0.0409]        Epoch 170:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0437, v_num=3, train_loss_step=0.0409, train_loss_epoch=0.0409]Epoch 170: 100%|##########| 1/1 [00:00<00:00, 21.66it/s, loss=0.0437, v_num=3, train_loss_step=0.0409, train_loss_epoch=0.0409]Epoch 170: 100%|##########| 1/1 [00:00<00:00, 21.46it/s, loss=0.0436, v_num=3, train_loss_step=0.0429, train_loss_epoch=0.0409]Epoch 170: 100%|##########| 1/1 [00:00<00:00, 21.16it/s, loss=0.0436, v_num=3, train_loss_step=0.0429, train_loss_epoch=0.0429]Epoch 170:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0436, v_num=3, train_loss_step=0.0429, train_loss_epoch=0.0429]        Epoch 171:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0436, v_num=3, train_loss_step=0.0429, train_loss_epoch=0.0429]Epoch 171: 100%|##########| 1/1 [00:00<00:00, 20.87it/s, loss=0.0436, v_num=3, train_loss_step=0.0429, train_loss_epoch=0.0429]Epoch 171: 100%|##########| 1/1 [00:00<00:00, 20.67it/s, loss=0.0432, v_num=3, train_loss_step=0.0372, train_loss_epoch=0.0429]Epoch 171: 100%|##########| 1/1 [00:00<00:00, 20.41it/s, loss=0.0432, v_num=3, train_loss_step=0.0372, train_loss_epoch=0.0372]Epoch 171:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0432, v_num=3, train_loss_step=0.0372, train_loss_epoch=0.0372]        Epoch 172:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0432, v_num=3, train_loss_step=0.0372, train_loss_epoch=0.0372]Epoch 172: 100%|##########| 1/1 [00:00<00:00, 19.91it/s, loss=0.0432, v_num=3, train_loss_step=0.0372, train_loss_epoch=0.0372]Epoch 172: 100%|##########| 1/1 [00:00<00:00, 19.74it/s, loss=0.043, v_num=3, train_loss_step=0.0424, train_loss_epoch=0.0372] Epoch 172: 100%|##########| 1/1 [00:00<00:00, 19.49it/s, loss=0.043, v_num=3, train_loss_step=0.0424, train_loss_epoch=0.0424]Epoch 172:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.043, v_num=3, train_loss_step=0.0424, train_loss_epoch=0.0424]        Epoch 173:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.043, v_num=3, train_loss_step=0.0424, train_loss_epoch=0.0424]Epoch 173: 100%|##########| 1/1 [00:00<00:00, 20.45it/s, loss=0.043, v_num=3, train_loss_step=0.0424, train_loss_epoch=0.0424]Epoch 173: 100%|##########| 1/1 [00:00<00:00, 20.21it/s, loss=0.0427, v_num=3, train_loss_step=0.039, train_loss_epoch=0.0424]Epoch 173: 100%|##########| 1/1 [00:00<00:00, 19.95it/s, loss=0.0427, v_num=3, train_loss_step=0.039, train_loss_epoch=0.039] Epoch 173:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0427, v_num=3, train_loss_step=0.039, train_loss_epoch=0.039]        Epoch 174:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0427, v_num=3, train_loss_step=0.039, train_loss_epoch=0.039]Epoch 174: 100%|##########| 1/1 [00:00<00:00, 20.89it/s, loss=0.0427, v_num=3, train_loss_step=0.039, train_loss_epoch=0.039]Epoch 174: 100%|##########| 1/1 [00:00<00:00, 20.72it/s, loss=0.0424, v_num=3, train_loss_step=0.0386, train_loss_epoch=0.039]Epoch 174: 100%|##########| 1/1 [00:00<00:00, 20.46it/s, loss=0.0424, v_num=3, train_loss_step=0.0386, train_loss_epoch=0.0386]Epoch 174:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0424, v_num=3, train_loss_step=0.0386, train_loss_epoch=0.0386]        Epoch 175:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0424, v_num=3, train_loss_step=0.0386, train_loss_epoch=0.0386]Epoch 175: 100%|##########| 1/1 [00:00<00:00, 21.21it/s, loss=0.0424, v_num=3, train_loss_step=0.0386, train_loss_epoch=0.0386]Epoch 175: 100%|##########| 1/1 [00:00<00:00, 21.00it/s, loss=0.042, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0386] Epoch 175: 100%|##########| 1/1 [00:00<00:00, 20.74it/s, loss=0.042, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0363]Epoch 175:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.042, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0363]        Epoch 176:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.042, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0363]Epoch 176: 100%|##########| 1/1 [00:00<00:00, 20.10it/s, loss=0.042, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0363]Epoch 176: 100%|##########| 1/1 [00:00<00:00, 19.94it/s, loss=0.0419, v_num=3, train_loss_step=0.0396, train_loss_epoch=0.0363]Epoch 176: 100%|##########| 1/1 [00:00<00:00, 19.67it/s, loss=0.0419, v_num=3, train_loss_step=0.0396, train_loss_epoch=0.0396]Epoch 176:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0419, v_num=3, train_loss_step=0.0396, train_loss_epoch=0.0396]        Epoch 177:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0419, v_num=3, train_loss_step=0.0396, train_loss_epoch=0.0396]Epoch 177: 100%|##########| 1/1 [00:00<00:00, 20.59it/s, loss=0.0419, v_num=3, train_loss_step=0.0396, train_loss_epoch=0.0396]Epoch 177: 100%|##########| 1/1 [00:00<00:00, 20.34it/s, loss=0.0416, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0396]Epoch 177: 100%|##########| 1/1 [00:00<00:00, 20.10it/s, loss=0.0416, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0358]Epoch 177:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0416, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0358]        Epoch 178:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0416, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0358]Epoch 178: 100%|##########| 1/1 [00:00<00:00, 20.89it/s, loss=0.0416, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0358]Epoch 178: 100%|##########| 1/1 [00:00<00:00, 20.70it/s, loss=0.0414, v_num=3, train_loss_step=0.0369, train_loss_epoch=0.0358]Epoch 178: 100%|##########| 1/1 [00:00<00:00, 20.43it/s, loss=0.0414, v_num=3, train_loss_step=0.0369, train_loss_epoch=0.0369]Epoch 178:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0414, v_num=3, train_loss_step=0.0369, train_loss_epoch=0.0369]        Epoch 179:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0414, v_num=3, train_loss_step=0.0369, train_loss_epoch=0.0369]Epoch 179: 100%|##########| 1/1 [00:00<00:00, 21.37it/s, loss=0.0414, v_num=3, train_loss_step=0.0369, train_loss_epoch=0.0369]Epoch 179: 100%|##########| 1/1 [00:00<00:00, 21.15it/s, loss=0.0412, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0369]Epoch 179: 100%|##########| 1/1 [00:00<00:00, 20.89it/s, loss=0.0412, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0363]Epoch 179:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0412, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0363]        Epoch 180:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0412, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0363]Epoch 180: 100%|##########| 1/1 [00:00<00:00, 20.94it/s, loss=0.0412, v_num=3, train_loss_step=0.0363, train_loss_epoch=0.0363]Epoch 180: 100%|##########| 1/1 [00:00<00:00, 20.77it/s, loss=0.0406, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0363]Epoch 180: 100%|##########| 1/1 [00:00<00:00, 20.51it/s, loss=0.0406, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0358]Epoch 180:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0406, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0358]        Epoch 181:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0406, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0358]Epoch 181: 100%|##########| 1/1 [00:00<00:00, 22.06it/s, loss=0.0406, v_num=3, train_loss_step=0.0358, train_loss_epoch=0.0358]Epoch 181: 100%|##########| 1/1 [00:00<00:00, 21.85it/s, loss=0.0398, v_num=3, train_loss_step=0.0353, train_loss_epoch=0.0358]Epoch 181: 100%|##########| 1/1 [00:00<00:00, 21.57it/s, loss=0.0398, v_num=3, train_loss_step=0.0353, train_loss_epoch=0.0353]Epoch 181:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0398, v_num=3, train_loss_step=0.0353, train_loss_epoch=0.0353]        Epoch 182:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0398, v_num=3, train_loss_step=0.0353, train_loss_epoch=0.0353]Epoch 182: 100%|##########| 1/1 [00:00<00:00, 22.26it/s, loss=0.0398, v_num=3, train_loss_step=0.0353, train_loss_epoch=0.0353]Epoch 182: 100%|##########| 1/1 [00:00<00:00, 22.08it/s, loss=0.0392, v_num=3, train_loss_step=0.0344, train_loss_epoch=0.0353]Epoch 182: 100%|##########| 1/1 [00:00<00:00, 21.80it/s, loss=0.0392, v_num=3, train_loss_step=0.0344, train_loss_epoch=0.0344]Epoch 182:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0392, v_num=3, train_loss_step=0.0344, train_loss_epoch=0.0344]        Epoch 183:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0392, v_num=3, train_loss_step=0.0344, train_loss_epoch=0.0344]Epoch 183: 100%|##########| 1/1 [00:00<00:00, 20.22it/s, loss=0.0392, v_num=3, train_loss_step=0.0344, train_loss_epoch=0.0344]Epoch 183: 100%|##########| 1/1 [00:00<00:00, 20.02it/s, loss=0.039, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0344] Epoch 183: 100%|##########| 1/1 [00:00<00:00, 19.78it/s, loss=0.039, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0339]Epoch 183:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.039, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0339]        Epoch 184:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.039, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0339]Epoch 184: 100%|##########| 1/1 [00:00<00:00, 20.75it/s, loss=0.039, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0339]Epoch 184: 100%|##########| 1/1 [00:00<00:00, 20.57it/s, loss=0.0386, v_num=3, train_loss_step=0.0332, train_loss_epoch=0.0339]Epoch 184: 100%|##########| 1/1 [00:00<00:00, 20.30it/s, loss=0.0386, v_num=3, train_loss_step=0.0332, train_loss_epoch=0.0332]Epoch 184:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0386, v_num=3, train_loss_step=0.0332, train_loss_epoch=0.0332]        Epoch 185:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0386, v_num=3, train_loss_step=0.0332, train_loss_epoch=0.0332]Epoch 185: 100%|##########| 1/1 [00:00<00:00, 19.91it/s, loss=0.0386, v_num=3, train_loss_step=0.0332, train_loss_epoch=0.0332]Epoch 185: 100%|##########| 1/1 [00:00<00:00, 19.72it/s, loss=0.038, v_num=3, train_loss_step=0.0359, train_loss_epoch=0.0332] Epoch 185: 100%|##########| 1/1 [00:00<00:00, 19.48it/s, loss=0.038, v_num=3, train_loss_step=0.0359, train_loss_epoch=0.0359]Epoch 185:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.038, v_num=3, train_loss_step=0.0359, train_loss_epoch=0.0359]        Epoch 186:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.038, v_num=3, train_loss_step=0.0359, train_loss_epoch=0.0359]Epoch 186: 100%|##########| 1/1 [00:00<00:00, 20.84it/s, loss=0.038, v_num=3, train_loss_step=0.0359, train_loss_epoch=0.0359]Epoch 186: 100%|##########| 1/1 [00:00<00:00, 20.67it/s, loss=0.0375, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0359]Epoch 186: 100%|##########| 1/1 [00:00<00:00, 20.39it/s, loss=0.0375, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0339]Epoch 186:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0375, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0339]        Epoch 187:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0375, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0339]Epoch 187: 100%|##########| 1/1 [00:00<00:00, 20.72it/s, loss=0.0375, v_num=3, train_loss_step=0.0339, train_loss_epoch=0.0339]Epoch 187: 100%|##########| 1/1 [00:00<00:00, 20.51it/s, loss=0.0373, v_num=3, train_loss_step=0.0335, train_loss_epoch=0.0339]Epoch 187: 100%|##########| 1/1 [00:00<00:00, 20.27it/s, loss=0.0373, v_num=3, train_loss_step=0.0335, train_loss_epoch=0.0335]Epoch 187:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0373, v_num=3, train_loss_step=0.0335, train_loss_epoch=0.0335]        Epoch 188:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0373, v_num=3, train_loss_step=0.0335, train_loss_epoch=0.0335]Epoch 188: 100%|##########| 1/1 [00:00<00:00, 21.26it/s, loss=0.0373, v_num=3, train_loss_step=0.0335, train_loss_epoch=0.0335]Epoch 188: 100%|##########| 1/1 [00:00<00:00, 21.10it/s, loss=0.0368, v_num=3, train_loss_step=0.0351, train_loss_epoch=0.0335]Epoch 188: 100%|##########| 1/1 [00:00<00:00, 20.84it/s, loss=0.0368, v_num=3, train_loss_step=0.0351, train_loss_epoch=0.0351]Epoch 188:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0368, v_num=3, train_loss_step=0.0351, train_loss_epoch=0.0351]        Epoch 189:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0368, v_num=3, train_loss_step=0.0351, train_loss_epoch=0.0351]Epoch 189: 100%|##########| 1/1 [00:00<00:00, 20.75it/s, loss=0.0368, v_num=3, train_loss_step=0.0351, train_loss_epoch=0.0351]Epoch 189: 100%|##########| 1/1 [00:00<00:00, 20.54it/s, loss=0.0364, v_num=3, train_loss_step=0.0323, train_loss_epoch=0.0351]Epoch 189: 100%|##########| 1/1 [00:00<00:00, 20.28it/s, loss=0.0364, v_num=3, train_loss_step=0.0323, train_loss_epoch=0.0323]Epoch 189:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0364, v_num=3, train_loss_step=0.0323, train_loss_epoch=0.0323]        Epoch 190:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0364, v_num=3, train_loss_step=0.0323, train_loss_epoch=0.0323]Epoch 190: 100%|##########| 1/1 [00:00<00:00, 20.27it/s, loss=0.0364, v_num=3, train_loss_step=0.0323, train_loss_epoch=0.0323]Epoch 190: 100%|##########| 1/1 [00:00<00:00, 20.11it/s, loss=0.0359, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0323]Epoch 190: 100%|##########| 1/1 [00:00<00:00, 19.88it/s, loss=0.0359, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0333]Epoch 190:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0359, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0333]        Epoch 191:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0359, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0333]Epoch 191: 100%|##########| 1/1 [00:00<00:00, 19.07it/s, loss=0.0359, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0333]Epoch 191: 100%|##########| 1/1 [00:00<00:00, 18.89it/s, loss=0.0356, v_num=3, train_loss_step=0.0307, train_loss_epoch=0.0333]Epoch 191: 100%|##########| 1/1 [00:00<00:00, 18.67it/s, loss=0.0356, v_num=3, train_loss_step=0.0307, train_loss_epoch=0.0307]Epoch 191:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0356, v_num=3, train_loss_step=0.0307, train_loss_epoch=0.0307]        Epoch 192:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0356, v_num=3, train_loss_step=0.0307, train_loss_epoch=0.0307]Epoch 192: 100%|##########| 1/1 [00:00<00:00, 20.40it/s, loss=0.0356, v_num=3, train_loss_step=0.0307, train_loss_epoch=0.0307]Epoch 192: 100%|##########| 1/1 [00:00<00:00, 20.24it/s, loss=0.035, v_num=3, train_loss_step=0.0308, train_loss_epoch=0.0307] Epoch 192: 100%|##########| 1/1 [00:00<00:00, 20.01it/s, loss=0.035, v_num=3, train_loss_step=0.0308, train_loss_epoch=0.0308]Epoch 192:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.035, v_num=3, train_loss_step=0.0308, train_loss_epoch=0.0308]        Epoch 193:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.035, v_num=3, train_loss_step=0.0308, train_loss_epoch=0.0308]Epoch 193: 100%|##########| 1/1 [00:00<00:00, 20.97it/s, loss=0.035, v_num=3, train_loss_step=0.0308, train_loss_epoch=0.0308]Epoch 193: 100%|##########| 1/1 [00:00<00:00, 20.76it/s, loss=0.0345, v_num=3, train_loss_step=0.0293, train_loss_epoch=0.0308]Epoch 193: 100%|##########| 1/1 [00:00<00:00, 20.52it/s, loss=0.0345, v_num=3, train_loss_step=0.0293, train_loss_epoch=0.0293]Epoch 193:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0345, v_num=3, train_loss_step=0.0293, train_loss_epoch=0.0293]        Epoch 194:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0345, v_num=3, train_loss_step=0.0293, train_loss_epoch=0.0293]Epoch 194: 100%|##########| 1/1 [00:00<00:00, 20.34it/s, loss=0.0345, v_num=3, train_loss_step=0.0293, train_loss_epoch=0.0293]Epoch 194: 100%|##########| 1/1 [00:00<00:00, 20.17it/s, loss=0.0342, v_num=3, train_loss_step=0.0322, train_loss_epoch=0.0293]Epoch 194: 100%|##########| 1/1 [00:00<00:00, 19.93it/s, loss=0.0342, v_num=3, train_loss_step=0.0322, train_loss_epoch=0.0322]Epoch 194:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0342, v_num=3, train_loss_step=0.0322, train_loss_epoch=0.0322]        Epoch 195:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0342, v_num=3, train_loss_step=0.0322, train_loss_epoch=0.0322]Epoch 195: 100%|##########| 1/1 [00:00<00:00, 20.59it/s, loss=0.0342, v_num=3, train_loss_step=0.0322, train_loss_epoch=0.0322]Epoch 195: 100%|##########| 1/1 [00:00<00:00, 20.38it/s, loss=0.0341, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0322]Epoch 195: 100%|##########| 1/1 [00:00<00:00, 20.13it/s, loss=0.0341, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0333]Epoch 195:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0341, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0333]        Epoch 196:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0341, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0333]Epoch 196: 100%|##########| 1/1 [00:00<00:00, 21.58it/s, loss=0.0341, v_num=3, train_loss_step=0.0333, train_loss_epoch=0.0333]Epoch 196: 100%|##########| 1/1 [00:00<00:00, 21.38it/s, loss=0.0337, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0333]Epoch 196: 100%|##########| 1/1 [00:00<00:00, 21.10it/s, loss=0.0337, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0318]Epoch 196:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0337, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0318]        Epoch 197:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0337, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0318]Epoch 197: 100%|##########| 1/1 [00:00<00:00, 21.59it/s, loss=0.0337, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0318]Epoch 197: 100%|##########| 1/1 [00:00<00:00, 21.39it/s, loss=0.0335, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0318]Epoch 197: 100%|##########| 1/1 [00:00<00:00, 21.15it/s, loss=0.0335, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0318]Epoch 197:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0335, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0318]        Epoch 198:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0335, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0318]Epoch 198: 100%|##########| 1/1 [00:00<00:00, 21.61it/s, loss=0.0335, v_num=3, train_loss_step=0.0318, train_loss_epoch=0.0318]Epoch 198: 100%|##########| 1/1 [00:00<00:00, 21.45it/s, loss=0.0331, v_num=3, train_loss_step=0.0295, train_loss_epoch=0.0318]Epoch 198: 100%|##########| 1/1 [00:00<00:00, 21.19it/s, loss=0.0331, v_num=3, train_loss_step=0.0295, train_loss_epoch=0.0295]Epoch 198:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0331, v_num=3, train_loss_step=0.0295, train_loss_epoch=0.0295]        Epoch 199:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0331, v_num=3, train_loss_step=0.0295, train_loss_epoch=0.0295]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 22.04it/s, loss=0.0331, v_num=3, train_loss_step=0.0295, train_loss_epoch=0.0295]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 21.82it/s, loss=0.0327, v_num=3, train_loss_step=0.0287, train_loss_epoch=0.0295]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 21.30it/s, loss=0.0327, v_num=3, train_loss_step=0.0287, train_loss_epoch=0.0287]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 16.58it/s, loss=0.0327, v_num=3, train_loss_step=0.0287, train_loss_epoch=0.0287]
Predicting: 1it [00:00, ?it/s]Predicting:   0%|          | 0/1 [00:00<00:00, -36157.79it/s]Predicting DataLoader 0:   0%|          | 0/1 [00:00<?, ?it/s]Predicting DataLoader 0: 100%|##########| 1/1 [00:00<00:00, 173.50it/s]Predicting DataLoader 0: 100%|##########| 1/1 [00:00<00:00, 162.96it/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()