GRU

Cho et. al proposed the Gated Recurrent Unit (GRU) to improve on LSTM and Elman cells. The predictions at each time are given by a fully connected decoder.

References
-Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, Yoshua Bengio (2014). “Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling”.
-Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, Yoshua Bengio (2014). “On the Properties of Neural Machine Translation: Encoder-Decoder Approaches”.

Figure 1. Gated Recurrent Unit Cell.

---

source

GRU

 GRU (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 0x7f9235a1e320>,
      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 = GRU(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['GRU'] = 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, 16.06it/s]Epoch 0: 100%|##########| 1/1 [00:00<00:00, 15.89it/s, loss=0.77, v_num=4, train_loss_step=0.770]Epoch 0: 100%|##########| 1/1 [00:00<00:00, 15.70it/s, loss=0.77, v_num=4, train_loss_step=0.770, train_loss_epoch=0.770]Epoch 0:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.77, v_num=4, train_loss_step=0.770, train_loss_epoch=0.770]        Epoch 1:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.77, v_num=4, train_loss_step=0.770, train_loss_epoch=0.770]Epoch 1: 100%|##########| 1/1 [00:00<00:00, 22.09it/s, loss=0.77, v_num=4, train_loss_step=0.770, train_loss_epoch=0.770]Epoch 1: 100%|##########| 1/1 [00:00<00:00, 21.84it/s, loss=0.743, v_num=4, train_loss_step=0.715, train_loss_epoch=0.770]Epoch 1: 100%|##########| 1/1 [00:00<00:00, 21.58it/s, loss=0.743, v_num=4, train_loss_step=0.715, train_loss_epoch=0.715]Epoch 1:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.743, v_num=4, train_loss_step=0.715, train_loss_epoch=0.715]        Epoch 2:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.743, v_num=4, train_loss_step=0.715, train_loss_epoch=0.715]Epoch 2: 100%|##########| 1/1 [00:00<00:00, 22.79it/s, loss=0.743, v_num=4, train_loss_step=0.715, train_loss_epoch=0.715]Epoch 2: 100%|##########| 1/1 [00:00<00:00, 22.62it/s, loss=0.715, v_num=4, train_loss_step=0.659, train_loss_epoch=0.715]Epoch 2: 100%|##########| 1/1 [00:00<00:00, 22.34it/s, loss=0.715, v_num=4, train_loss_step=0.659, train_loss_epoch=0.659]Epoch 2:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.715, v_num=4, train_loss_step=0.659, train_loss_epoch=0.659]        Epoch 3:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.715, v_num=4, train_loss_step=0.659, train_loss_epoch=0.659]Epoch 3: 100%|##########| 1/1 [00:00<00:00, 23.17it/s, loss=0.715, v_num=4, train_loss_step=0.659, train_loss_epoch=0.659]Epoch 3: 100%|##########| 1/1 [00:00<00:00, 22.98it/s, loss=0.686, v_num=4, train_loss_step=0.598, train_loss_epoch=0.659]Epoch 3: 100%|##########| 1/1 [00:00<00:00, 22.65it/s, loss=0.686, v_num=4, train_loss_step=0.598, train_loss_epoch=0.598]Epoch 3:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.686, v_num=4, train_loss_step=0.598, train_loss_epoch=0.598]        Epoch 4:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.686, v_num=4, train_loss_step=0.598, train_loss_epoch=0.598]Epoch 4: 100%|##########| 1/1 [00:00<00:00, 23.00it/s, loss=0.686, v_num=4, train_loss_step=0.598, train_loss_epoch=0.598]Epoch 4: 100%|##########| 1/1 [00:00<00:00, 22.73it/s, loss=0.656, v_num=4, train_loss_step=0.536, train_loss_epoch=0.598]Epoch 4: 100%|##########| 1/1 [00:00<00:00, 22.40it/s, loss=0.656, v_num=4, train_loss_step=0.536, train_loss_epoch=0.536]Epoch 4:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.656, v_num=4, train_loss_step=0.536, train_loss_epoch=0.536]        Epoch 5:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.656, v_num=4, train_loss_step=0.536, train_loss_epoch=0.536]Epoch 5: 100%|##########| 1/1 [00:00<00:00, 22.92it/s, loss=0.656, v_num=4, train_loss_step=0.536, train_loss_epoch=0.536]Epoch 5: 100%|##########| 1/1 [00:00<00:00, 22.73it/s, loss=0.627, v_num=4, train_loss_step=0.486, train_loss_epoch=0.536]Epoch 5: 100%|##########| 1/1 [00:00<00:00, 22.42it/s, loss=0.627, v_num=4, train_loss_step=0.486, train_loss_epoch=0.486]Epoch 5:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.627, v_num=4, train_loss_step=0.486, train_loss_epoch=0.486]        Epoch 6:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.627, v_num=4, train_loss_step=0.486, train_loss_epoch=0.486]Epoch 6: 100%|##########| 1/1 [00:00<00:00, 23.53it/s, loss=0.627, v_num=4, train_loss_step=0.486, train_loss_epoch=0.486]Epoch 6: 100%|##########| 1/1 [00:00<00:00, 23.24it/s, loss=0.603, v_num=4, train_loss_step=0.457, train_loss_epoch=0.486]Epoch 6: 100%|##########| 1/1 [00:00<00:00, 22.88it/s, loss=0.603, v_num=4, train_loss_step=0.457, train_loss_epoch=0.457]Epoch 6:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.603, v_num=4, train_loss_step=0.457, train_loss_epoch=0.457]        Epoch 7:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.603, v_num=4, train_loss_step=0.457, train_loss_epoch=0.457]Epoch 7: 100%|##########| 1/1 [00:00<00:00, 23.56it/s, loss=0.603, v_num=4, train_loss_step=0.457, train_loss_epoch=0.457]Epoch 7: 100%|##########| 1/1 [00:00<00:00, 23.26it/s, loss=0.582, v_num=4, train_loss_step=0.435, train_loss_epoch=0.457]Epoch 7: 100%|##########| 1/1 [00:00<00:00, 22.91it/s, loss=0.582, v_num=4, train_loss_step=0.435, train_loss_epoch=0.435]Epoch 7:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.582, v_num=4, train_loss_step=0.435, train_loss_epoch=0.435]        Epoch 8:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.582, v_num=4, train_loss_step=0.435, train_loss_epoch=0.435]Epoch 8: 100%|##########| 1/1 [00:00<00:00, 22.31it/s, loss=0.582, v_num=4, train_loss_step=0.435, train_loss_epoch=0.435]Epoch 8: 100%|##########| 1/1 [00:00<00:00, 22.03it/s, loss=0.562, v_num=4, train_loss_step=0.407, train_loss_epoch=0.435]Epoch 8: 100%|##########| 1/1 [00:00<00:00, 21.75it/s, loss=0.562, v_num=4, train_loss_step=0.407, train_loss_epoch=0.407]Epoch 8:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.562, v_num=4, train_loss_step=0.407, train_loss_epoch=0.407]        Epoch 9:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.562, v_num=4, train_loss_step=0.407, train_loss_epoch=0.407]Epoch 9: 100%|##########| 1/1 [00:00<00:00, 22.75it/s, loss=0.562, v_num=4, train_loss_step=0.407, train_loss_epoch=0.407]Epoch 9: 100%|##########| 1/1 [00:00<00:00, 22.56it/s, loss=0.545, v_num=4, train_loss_step=0.390, train_loss_epoch=0.407]Epoch 9: 100%|##########| 1/1 [00:00<00:00, 22.24it/s, loss=0.545, v_num=4, train_loss_step=0.390, train_loss_epoch=0.390]Epoch 9:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.545, v_num=4, train_loss_step=0.390, train_loss_epoch=0.390]        Epoch 10:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.545, v_num=4, train_loss_step=0.390, train_loss_epoch=0.390]Epoch 10: 100%|##########| 1/1 [00:00<00:00, 22.63it/s, loss=0.545, v_num=4, train_loss_step=0.390, train_loss_epoch=0.390]Epoch 10: 100%|##########| 1/1 [00:00<00:00, 22.44it/s, loss=0.531, v_num=4, train_loss_step=0.391, train_loss_epoch=0.390]Epoch 10: 100%|##########| 1/1 [00:00<00:00, 22.15it/s, loss=0.531, v_num=4, train_loss_step=0.391, train_loss_epoch=0.391]Epoch 10:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.531, v_num=4, train_loss_step=0.391, train_loss_epoch=0.391]        Epoch 11:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.531, v_num=4, train_loss_step=0.391, train_loss_epoch=0.391]Epoch 11: 100%|##########| 1/1 [00:00<00:00, 23.83it/s, loss=0.531, v_num=4, train_loss_step=0.391, train_loss_epoch=0.391]Epoch 11: 100%|##########| 1/1 [00:00<00:00, 23.52it/s, loss=0.52, v_num=4, train_loss_step=0.398, train_loss_epoch=0.391] Epoch 11: 100%|##########| 1/1 [00:00<00:00, 23.19it/s, loss=0.52, v_num=4, train_loss_step=0.398, train_loss_epoch=0.398]Epoch 11:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.52, v_num=4, train_loss_step=0.398, train_loss_epoch=0.398]        Epoch 12:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.52, v_num=4, train_loss_step=0.398, train_loss_epoch=0.398]Epoch 12: 100%|##########| 1/1 [00:00<00:00, 23.86it/s, loss=0.52, v_num=4, train_loss_step=0.398, train_loss_epoch=0.398]Epoch 12: 100%|##########| 1/1 [00:00<00:00, 23.67it/s, loss=0.511, v_num=4, train_loss_step=0.395, train_loss_epoch=0.398]Epoch 12: 100%|##########| 1/1 [00:00<00:00, 23.38it/s, loss=0.511, v_num=4, train_loss_step=0.395, train_loss_epoch=0.395]Epoch 12:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.511, v_num=4, train_loss_step=0.395, train_loss_epoch=0.395]        Epoch 13:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.511, v_num=4, train_loss_step=0.395, train_loss_epoch=0.395]Epoch 13: 100%|##########| 1/1 [00:00<00:00, 23.58it/s, loss=0.511, v_num=4, train_loss_step=0.395, train_loss_epoch=0.395]Epoch 13: 100%|##########| 1/1 [00:00<00:00, 23.30it/s, loss=0.501, v_num=4, train_loss_step=0.381, train_loss_epoch=0.395]Epoch 13: 100%|##########| 1/1 [00:00<00:00, 22.97it/s, loss=0.501, v_num=4, train_loss_step=0.381, train_loss_epoch=0.381]Epoch 13:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.501, v_num=4, train_loss_step=0.381, train_loss_epoch=0.381]        Epoch 14:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.501, v_num=4, train_loss_step=0.381, train_loss_epoch=0.381]Epoch 14: 100%|##########| 1/1 [00:00<00:00, 23.44it/s, loss=0.501, v_num=4, train_loss_step=0.381, train_loss_epoch=0.381]Epoch 14: 100%|##########| 1/1 [00:00<00:00, 23.19it/s, loss=0.492, v_num=4, train_loss_step=0.360, train_loss_epoch=0.381]Epoch 14: 100%|##########| 1/1 [00:00<00:00, 22.86it/s, loss=0.492, v_num=4, train_loss_step=0.360, train_loss_epoch=0.360]Epoch 14:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.492, v_num=4, train_loss_step=0.360, train_loss_epoch=0.360]        Epoch 15:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.492, v_num=4, train_loss_step=0.360, train_loss_epoch=0.360]Epoch 15: 100%|##########| 1/1 [00:00<00:00, 22.55it/s, loss=0.492, v_num=4, train_loss_step=0.360, train_loss_epoch=0.360]Epoch 15: 100%|##########| 1/1 [00:00<00:00, 22.26it/s, loss=0.482, v_num=4, train_loss_step=0.340, train_loss_epoch=0.360]Epoch 15: 100%|##########| 1/1 [00:00<00:00, 21.96it/s, loss=0.482, v_num=4, train_loss_step=0.340, train_loss_epoch=0.340]Epoch 15:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.482, v_num=4, train_loss_step=0.340, train_loss_epoch=0.340]        Epoch 16:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.482, v_num=4, train_loss_step=0.340, train_loss_epoch=0.340]Epoch 16: 100%|##########| 1/1 [00:00<00:00, 22.58it/s, loss=0.482, v_num=4, train_loss_step=0.340, train_loss_epoch=0.340]Epoch 16: 100%|##########| 1/1 [00:00<00:00, 22.33it/s, loss=0.473, v_num=4, train_loss_step=0.324, train_loss_epoch=0.340]Epoch 16: 100%|##########| 1/1 [00:00<00:00, 22.01it/s, loss=0.473, v_num=4, train_loss_step=0.324, train_loss_epoch=0.324]Epoch 16:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.473, v_num=4, train_loss_step=0.324, train_loss_epoch=0.324]        Epoch 17:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.473, v_num=4, train_loss_step=0.324, train_loss_epoch=0.324]Epoch 17: 100%|##########| 1/1 [00:00<00:00, 21.79it/s, loss=0.473, v_num=4, train_loss_step=0.324, train_loss_epoch=0.324]Epoch 17: 100%|##########| 1/1 [00:00<00:00, 21.55it/s, loss=0.464, v_num=4, train_loss_step=0.312, train_loss_epoch=0.324]Epoch 17: 100%|##########| 1/1 [00:00<00:00, 21.25it/s, loss=0.464, v_num=4, train_loss_step=0.312, train_loss_epoch=0.312]Epoch 17:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.464, v_num=4, train_loss_step=0.312, train_loss_epoch=0.312]        Epoch 18:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.464, v_num=4, train_loss_step=0.312, train_loss_epoch=0.312]Epoch 18: 100%|##########| 1/1 [00:00<00:00, 22.52it/s, loss=0.464, v_num=4, train_loss_step=0.312, train_loss_epoch=0.312]Epoch 18: 100%|##########| 1/1 [00:00<00:00, 22.21it/s, loss=0.455, v_num=4, train_loss_step=0.300, train_loss_epoch=0.312]Epoch 18: 100%|##########| 1/1 [00:00<00:00, 21.92it/s, loss=0.455, v_num=4, train_loss_step=0.300, train_loss_epoch=0.300]Epoch 18:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.455, v_num=4, train_loss_step=0.300, train_loss_epoch=0.300]        Epoch 19:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.455, v_num=4, train_loss_step=0.300, train_loss_epoch=0.300]Epoch 19: 100%|##########| 1/1 [00:00<00:00, 22.91it/s, loss=0.455, v_num=4, train_loss_step=0.300, train_loss_epoch=0.300]Epoch 19: 100%|##########| 1/1 [00:00<00:00, 22.69it/s, loss=0.447, v_num=4, train_loss_step=0.288, train_loss_epoch=0.300]Epoch 19: 100%|##########| 1/1 [00:00<00:00, 22.40it/s, loss=0.447, v_num=4, train_loss_step=0.288, train_loss_epoch=0.288]Epoch 19:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.447, v_num=4, train_loss_step=0.288, train_loss_epoch=0.288]        Epoch 20:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.447, v_num=4, train_loss_step=0.288, train_loss_epoch=0.288]Epoch 20: 100%|##########| 1/1 [00:00<00:00, 23.60it/s, loss=0.447, v_num=4, train_loss_step=0.288, train_loss_epoch=0.288]Epoch 20: 100%|##########| 1/1 [00:00<00:00, 23.41it/s, loss=0.422, v_num=4, train_loss_step=0.277, train_loss_epoch=0.288]Epoch 20: 100%|##########| 1/1 [00:00<00:00, 23.11it/s, loss=0.422, v_num=4, train_loss_step=0.277, train_loss_epoch=0.277]Epoch 20:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.422, v_num=4, train_loss_step=0.277, train_loss_epoch=0.277]        Epoch 21:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.422, v_num=4, train_loss_step=0.277, train_loss_epoch=0.277]Epoch 21: 100%|##########| 1/1 [00:00<00:00, 24.61it/s, loss=0.422, v_num=4, train_loss_step=0.277, train_loss_epoch=0.277]Epoch 21: 100%|##########| 1/1 [00:00<00:00, 24.39it/s, loss=0.4, v_num=4, train_loss_step=0.268, train_loss_epoch=0.277]  Epoch 21: 100%|##########| 1/1 [00:00<00:00, 24.03it/s, loss=0.4, v_num=4, train_loss_step=0.268, train_loss_epoch=0.268]Epoch 21:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.4, v_num=4, train_loss_step=0.268, train_loss_epoch=0.268]        Epoch 22:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.4, v_num=4, train_loss_step=0.268, train_loss_epoch=0.268]Epoch 22: 100%|##########| 1/1 [00:00<00:00, 23.41it/s, loss=0.4, v_num=4, train_loss_step=0.268, train_loss_epoch=0.268]Epoch 22: 100%|##########| 1/1 [00:00<00:00, 23.19it/s, loss=0.38, v_num=4, train_loss_step=0.259, train_loss_epoch=0.268]Epoch 22: 100%|##########| 1/1 [00:00<00:00, 22.86it/s, loss=0.38, v_num=4, train_loss_step=0.259, train_loss_epoch=0.259]Epoch 22:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.38, v_num=4, train_loss_step=0.259, train_loss_epoch=0.259]        Epoch 23:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.38, v_num=4, train_loss_step=0.259, train_loss_epoch=0.259]Epoch 23: 100%|##########| 1/1 [00:00<00:00, 23.45it/s, loss=0.38, v_num=4, train_loss_step=0.259, train_loss_epoch=0.259]Epoch 23: 100%|##########| 1/1 [00:00<00:00, 23.11it/s, loss=0.363, v_num=4, train_loss_step=0.250, train_loss_epoch=0.259]Epoch 23: 100%|##########| 1/1 [00:00<00:00, 22.76it/s, loss=0.363, v_num=4, train_loss_step=0.250, train_loss_epoch=0.250]Epoch 23:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.363, v_num=4, train_loss_step=0.250, train_loss_epoch=0.250]        Epoch 24:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.363, v_num=4, train_loss_step=0.250, train_loss_epoch=0.250]Epoch 24: 100%|##########| 1/1 [00:00<00:00, 23.52it/s, loss=0.363, v_num=4, train_loss_step=0.250, train_loss_epoch=0.250]Epoch 24: 100%|##########| 1/1 [00:00<00:00, 23.25it/s, loss=0.348, v_num=4, train_loss_step=0.241, train_loss_epoch=0.250]Epoch 24: 100%|##########| 1/1 [00:00<00:00, 22.95it/s, loss=0.348, v_num=4, train_loss_step=0.241, train_loss_epoch=0.241]Epoch 24:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.348, v_num=4, train_loss_step=0.241, train_loss_epoch=0.241]        Epoch 25:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.348, v_num=4, train_loss_step=0.241, train_loss_epoch=0.241]Epoch 25: 100%|##########| 1/1 [00:00<00:00, 23.04it/s, loss=0.348, v_num=4, train_loss_step=0.241, train_loss_epoch=0.241]Epoch 25: 100%|##########| 1/1 [00:00<00:00, 22.74it/s, loss=0.336, v_num=4, train_loss_step=0.238, train_loss_epoch=0.241]Epoch 25: 100%|##########| 1/1 [00:00<00:00, 22.43it/s, loss=0.336, v_num=4, train_loss_step=0.238, train_loss_epoch=0.238]Epoch 25:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.336, v_num=4, train_loss_step=0.238, train_loss_epoch=0.238]        Epoch 26:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.336, v_num=4, train_loss_step=0.238, train_loss_epoch=0.238]Epoch 26: 100%|##########| 1/1 [00:00<00:00, 22.29it/s, loss=0.336, v_num=4, train_loss_step=0.238, train_loss_epoch=0.238]Epoch 26: 100%|##########| 1/1 [00:00<00:00, 22.07it/s, loss=0.325, v_num=4, train_loss_step=0.241, train_loss_epoch=0.238]Epoch 26: 100%|##########| 1/1 [00:00<00:00, 21.78it/s, loss=0.325, v_num=4, train_loss_step=0.241, train_loss_epoch=0.241]Epoch 26:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.325, v_num=4, train_loss_step=0.241, train_loss_epoch=0.241]        Epoch 27:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.325, v_num=4, train_loss_step=0.241, train_loss_epoch=0.241]Epoch 27: 100%|##########| 1/1 [00:00<00:00, 23.53it/s, loss=0.325, v_num=4, train_loss_step=0.241, train_loss_epoch=0.241]Epoch 27: 100%|##########| 1/1 [00:00<00:00, 23.24it/s, loss=0.315, v_num=4, train_loss_step=0.242, train_loss_epoch=0.241]Epoch 27: 100%|##########| 1/1 [00:00<00:00, 22.93it/s, loss=0.315, v_num=4, train_loss_step=0.242, train_loss_epoch=0.242]Epoch 27:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.315, v_num=4, train_loss_step=0.242, train_loss_epoch=0.242]        Epoch 28:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.315, v_num=4, train_loss_step=0.242, train_loss_epoch=0.242]Epoch 28: 100%|##########| 1/1 [00:00<00:00, 23.81it/s, loss=0.315, v_num=4, train_loss_step=0.242, train_loss_epoch=0.242]Epoch 28: 100%|##########| 1/1 [00:00<00:00, 23.63it/s, loss=0.307, v_num=4, train_loss_step=0.238, train_loss_epoch=0.242]Epoch 28: 100%|##########| 1/1 [00:00<00:00, 23.30it/s, loss=0.307, v_num=4, train_loss_step=0.238, train_loss_epoch=0.238]Epoch 28:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.307, v_num=4, train_loss_step=0.238, train_loss_epoch=0.238]        Epoch 29:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.307, v_num=4, train_loss_step=0.238, train_loss_epoch=0.238]Epoch 29: 100%|##########| 1/1 [00:00<00:00, 24.49it/s, loss=0.307, v_num=4, train_loss_step=0.238, train_loss_epoch=0.238]Epoch 29: 100%|##########| 1/1 [00:00<00:00, 24.24it/s, loss=0.299, v_num=4, train_loss_step=0.231, train_loss_epoch=0.238]Epoch 29: 100%|##########| 1/1 [00:00<00:00, 23.91it/s, loss=0.299, v_num=4, train_loss_step=0.231, train_loss_epoch=0.231]Epoch 29:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.299, v_num=4, train_loss_step=0.231, train_loss_epoch=0.231]        Epoch 30:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.299, v_num=4, train_loss_step=0.231, train_loss_epoch=0.231]Epoch 30: 100%|##########| 1/1 [00:00<00:00, 23.87it/s, loss=0.299, v_num=4, train_loss_step=0.231, train_loss_epoch=0.231]Epoch 30: 100%|##########| 1/1 [00:00<00:00, 23.67it/s, loss=0.29, v_num=4, train_loss_step=0.224, train_loss_epoch=0.231] Epoch 30: 100%|##########| 1/1 [00:00<00:00, 23.34it/s, loss=0.29, v_num=4, train_loss_step=0.224, train_loss_epoch=0.224]Epoch 30:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.29, v_num=4, train_loss_step=0.224, train_loss_epoch=0.224]        Epoch 31:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.29, v_num=4, train_loss_step=0.224, train_loss_epoch=0.224]Epoch 31: 100%|##########| 1/1 [00:00<00:00, 23.52it/s, loss=0.29, v_num=4, train_loss_step=0.224, train_loss_epoch=0.224]Epoch 31: 100%|##########| 1/1 [00:00<00:00, 23.29it/s, loss=0.281, v_num=4, train_loss_step=0.218, train_loss_epoch=0.224]Epoch 31: 100%|##########| 1/1 [00:00<00:00, 22.98it/s, loss=0.281, v_num=4, train_loss_step=0.218, train_loss_epoch=0.218]Epoch 31:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.281, v_num=4, train_loss_step=0.218, train_loss_epoch=0.218]        Epoch 32:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.281, v_num=4, train_loss_step=0.218, train_loss_epoch=0.218]Epoch 32: 100%|##########| 1/1 [00:00<00:00, 22.50it/s, loss=0.281, v_num=4, train_loss_step=0.218, train_loss_epoch=0.218]Epoch 32: 100%|##########| 1/1 [00:00<00:00, 22.21it/s, loss=0.272, v_num=4, train_loss_step=0.215, train_loss_epoch=0.218]Epoch 32: 100%|##########| 1/1 [00:00<00:00, 21.91it/s, loss=0.272, v_num=4, train_loss_step=0.215, train_loss_epoch=0.215]Epoch 32:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.272, v_num=4, train_loss_step=0.215, train_loss_epoch=0.215]        Epoch 33:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.272, v_num=4, train_loss_step=0.215, train_loss_epoch=0.215]Epoch 33: 100%|##########| 1/1 [00:00<00:00, 22.81it/s, loss=0.272, v_num=4, train_loss_step=0.215, train_loss_epoch=0.215]Epoch 33: 100%|##########| 1/1 [00:00<00:00, 22.53it/s, loss=0.264, v_num=4, train_loss_step=0.213, train_loss_epoch=0.215]Epoch 33: 100%|##########| 1/1 [00:00<00:00, 22.23it/s, loss=0.264, v_num=4, train_loss_step=0.213, train_loss_epoch=0.213]Epoch 33:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.264, v_num=4, train_loss_step=0.213, train_loss_epoch=0.213]        Epoch 34:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.264, v_num=4, train_loss_step=0.213, train_loss_epoch=0.213]Epoch 34: 100%|##########| 1/1 [00:00<00:00, 21.85it/s, loss=0.264, v_num=4, train_loss_step=0.213, train_loss_epoch=0.213]Epoch 34: 100%|##########| 1/1 [00:00<00:00, 21.57it/s, loss=0.256, v_num=4, train_loss_step=0.210, train_loss_epoch=0.213]Epoch 34: 100%|##########| 1/1 [00:00<00:00, 21.28it/s, loss=0.256, v_num=4, train_loss_step=0.210, train_loss_epoch=0.210]Epoch 34:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.256, v_num=4, train_loss_step=0.210, train_loss_epoch=0.210]        Epoch 35:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.256, v_num=4, train_loss_step=0.210, train_loss_epoch=0.210]Epoch 35: 100%|##########| 1/1 [00:00<00:00, 22.91it/s, loss=0.256, v_num=4, train_loss_step=0.210, train_loss_epoch=0.210]Epoch 35: 100%|##########| 1/1 [00:00<00:00, 22.67it/s, loss=0.25, v_num=4, train_loss_step=0.208, train_loss_epoch=0.210] Epoch 35: 100%|##########| 1/1 [00:00<00:00, 22.38it/s, loss=0.25, v_num=4, train_loss_step=0.208, train_loss_epoch=0.208]Epoch 35:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.25, v_num=4, train_loss_step=0.208, train_loss_epoch=0.208]        Epoch 36:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.25, v_num=4, train_loss_step=0.208, train_loss_epoch=0.208]Epoch 36: 100%|##########| 1/1 [00:00<00:00, 22.64it/s, loss=0.25, v_num=4, train_loss_step=0.208, train_loss_epoch=0.208]Epoch 36: 100%|##########| 1/1 [00:00<00:00, 22.45it/s, loss=0.244, v_num=4, train_loss_step=0.205, train_loss_epoch=0.208]Epoch 36: 100%|##########| 1/1 [00:00<00:00, 22.14it/s, loss=0.244, v_num=4, train_loss_step=0.205, train_loss_epoch=0.205]Epoch 36:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.244, v_num=4, train_loss_step=0.205, train_loss_epoch=0.205]        Epoch 37:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.244, v_num=4, train_loss_step=0.205, train_loss_epoch=0.205]Epoch 37: 100%|##########| 1/1 [00:00<00:00, 23.33it/s, loss=0.244, v_num=4, train_loss_step=0.205, train_loss_epoch=0.205]Epoch 37: 100%|##########| 1/1 [00:00<00:00, 23.12it/s, loss=0.238, v_num=4, train_loss_step=0.201, train_loss_epoch=0.205]Epoch 37: 100%|##########| 1/1 [00:00<00:00, 22.85it/s, loss=0.238, v_num=4, train_loss_step=0.201, train_loss_epoch=0.201]Epoch 37:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.238, v_num=4, train_loss_step=0.201, train_loss_epoch=0.201]        Epoch 38:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.238, v_num=4, train_loss_step=0.201, train_loss_epoch=0.201]Epoch 38: 100%|##########| 1/1 [00:00<00:00, 23.46it/s, loss=0.238, v_num=4, train_loss_step=0.201, train_loss_epoch=0.201]Epoch 38: 100%|##########| 1/1 [00:00<00:00, 23.20it/s, loss=0.233, v_num=4, train_loss_step=0.196, train_loss_epoch=0.201]Epoch 38: 100%|##########| 1/1 [00:00<00:00, 22.87it/s, loss=0.233, v_num=4, train_loss_step=0.196, train_loss_epoch=0.196]Epoch 38:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.233, v_num=4, train_loss_step=0.196, train_loss_epoch=0.196]        Epoch 39:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.233, v_num=4, train_loss_step=0.196, train_loss_epoch=0.196]Epoch 39: 100%|##########| 1/1 [00:00<00:00, 22.70it/s, loss=0.233, v_num=4, train_loss_step=0.196, train_loss_epoch=0.196]Epoch 39: 100%|##########| 1/1 [00:00<00:00, 22.42it/s, loss=0.228, v_num=4, train_loss_step=0.190, train_loss_epoch=0.196]Epoch 39: 100%|##########| 1/1 [00:00<00:00, 22.12it/s, loss=0.228, v_num=4, train_loss_step=0.190, train_loss_epoch=0.190]Epoch 39:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.228, v_num=4, train_loss_step=0.190, train_loss_epoch=0.190]        Epoch 40:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.228, v_num=4, train_loss_step=0.190, train_loss_epoch=0.190]Epoch 40: 100%|##########| 1/1 [00:00<00:00, 23.47it/s, loss=0.228, v_num=4, train_loss_step=0.190, train_loss_epoch=0.190]Epoch 40: 100%|##########| 1/1 [00:00<00:00, 23.17it/s, loss=0.224, v_num=4, train_loss_step=0.185, train_loss_epoch=0.190]Epoch 40: 100%|##########| 1/1 [00:00<00:00, 22.84it/s, loss=0.224, v_num=4, train_loss_step=0.185, train_loss_epoch=0.185]Epoch 40:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.224, v_num=4, train_loss_step=0.185, train_loss_epoch=0.185]        Epoch 41:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.224, v_num=4, train_loss_step=0.185, train_loss_epoch=0.185]Epoch 41: 100%|##########| 1/1 [00:00<00:00, 22.91it/s, loss=0.224, v_num=4, train_loss_step=0.185, train_loss_epoch=0.185]Epoch 41: 100%|##########| 1/1 [00:00<00:00, 22.64it/s, loss=0.219, v_num=4, train_loss_step=0.180, train_loss_epoch=0.185]Epoch 41: 100%|##########| 1/1 [00:00<00:00, 22.38it/s, loss=0.219, v_num=4, train_loss_step=0.180, train_loss_epoch=0.180]Epoch 41:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.219, v_num=4, train_loss_step=0.180, train_loss_epoch=0.180]        Epoch 42:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.219, v_num=4, train_loss_step=0.180, train_loss_epoch=0.180]Epoch 42: 100%|##########| 1/1 [00:00<00:00, 23.96it/s, loss=0.219, v_num=4, train_loss_step=0.180, train_loss_epoch=0.180]Epoch 42: 100%|##########| 1/1 [00:00<00:00, 23.66it/s, loss=0.215, v_num=4, train_loss_step=0.175, train_loss_epoch=0.180]Epoch 42: 100%|##########| 1/1 [00:00<00:00, 23.33it/s, loss=0.215, v_num=4, train_loss_step=0.175, train_loss_epoch=0.175]Epoch 42:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.215, v_num=4, train_loss_step=0.175, train_loss_epoch=0.175]        Epoch 43:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.215, v_num=4, train_loss_step=0.175, train_loss_epoch=0.175]Epoch 43: 100%|##########| 1/1 [00:00<00:00, 24.29it/s, loss=0.215, v_num=4, train_loss_step=0.175, train_loss_epoch=0.175]Epoch 43: 100%|##########| 1/1 [00:00<00:00, 24.05it/s, loss=0.211, v_num=4, train_loss_step=0.172, train_loss_epoch=0.175]Epoch 43: 100%|##########| 1/1 [00:00<00:00, 23.73it/s, loss=0.211, v_num=4, train_loss_step=0.172, train_loss_epoch=0.172]Epoch 43:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.211, v_num=4, train_loss_step=0.172, train_loss_epoch=0.172]        Epoch 44:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.211, v_num=4, train_loss_step=0.172, train_loss_epoch=0.172]Epoch 44: 100%|##########| 1/1 [00:00<00:00, 22.99it/s, loss=0.211, v_num=4, train_loss_step=0.172, train_loss_epoch=0.172]Epoch 44: 100%|##########| 1/1 [00:00<00:00, 22.70it/s, loss=0.208, v_num=4, train_loss_step=0.168, train_loss_epoch=0.172]Epoch 44: 100%|##########| 1/1 [00:00<00:00, 22.39it/s, loss=0.208, v_num=4, train_loss_step=0.168, train_loss_epoch=0.168]Epoch 44:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.208, v_num=4, train_loss_step=0.168, train_loss_epoch=0.168]        Epoch 45:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.208, v_num=4, train_loss_step=0.168, train_loss_epoch=0.168]Epoch 45: 100%|##########| 1/1 [00:00<00:00, 23.06it/s, loss=0.208, v_num=4, train_loss_step=0.168, train_loss_epoch=0.168]Epoch 45: 100%|##########| 1/1 [00:00<00:00, 22.79it/s, loss=0.204, v_num=4, train_loss_step=0.163, train_loss_epoch=0.168]Epoch 45: 100%|##########| 1/1 [00:00<00:00, 22.46it/s, loss=0.204, v_num=4, train_loss_step=0.163, train_loss_epoch=0.163]Epoch 45:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.204, v_num=4, train_loss_step=0.163, train_loss_epoch=0.163]        Epoch 46:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.204, v_num=4, train_loss_step=0.163, train_loss_epoch=0.163]Epoch 46: 100%|##########| 1/1 [00:00<00:00, 24.01it/s, loss=0.204, v_num=4, train_loss_step=0.163, train_loss_epoch=0.163]Epoch 46: 100%|##########| 1/1 [00:00<00:00, 23.74it/s, loss=0.2, v_num=4, train_loss_step=0.159, train_loss_epoch=0.163]  Epoch 46: 100%|##########| 1/1 [00:00<00:00, 23.43it/s, loss=0.2, v_num=4, train_loss_step=0.159, train_loss_epoch=0.159]Epoch 46:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.2, v_num=4, train_loss_step=0.159, train_loss_epoch=0.159]        Epoch 47:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.2, v_num=4, train_loss_step=0.159, train_loss_epoch=0.159]Epoch 47: 100%|##########| 1/1 [00:00<00:00, 23.75it/s, loss=0.2, v_num=4, train_loss_step=0.159, train_loss_epoch=0.159]Epoch 47: 100%|##########| 1/1 [00:00<00:00, 23.45it/s, loss=0.195, v_num=4, train_loss_step=0.155, train_loss_epoch=0.159]Epoch 47: 100%|##########| 1/1 [00:00<00:00, 23.15it/s, loss=0.195, v_num=4, train_loss_step=0.155, train_loss_epoch=0.155]Epoch 47:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.195, v_num=4, train_loss_step=0.155, train_loss_epoch=0.155]        Epoch 48:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.195, v_num=4, train_loss_step=0.155, train_loss_epoch=0.155]Epoch 48: 100%|##########| 1/1 [00:00<00:00, 23.79it/s, loss=0.195, v_num=4, train_loss_step=0.155, train_loss_epoch=0.155]Epoch 48: 100%|##########| 1/1 [00:00<00:00, 23.48it/s, loss=0.191, v_num=4, train_loss_step=0.150, train_loss_epoch=0.155]Epoch 48: 100%|##########| 1/1 [00:00<00:00, 23.16it/s, loss=0.191, v_num=4, train_loss_step=0.150, train_loss_epoch=0.150]Epoch 48:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.191, v_num=4, train_loss_step=0.150, train_loss_epoch=0.150]        Epoch 49:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.191, v_num=4, train_loss_step=0.150, train_loss_epoch=0.150]Epoch 49: 100%|##########| 1/1 [00:00<00:00, 24.34it/s, loss=0.191, v_num=4, train_loss_step=0.150, train_loss_epoch=0.150]Epoch 49: 100%|##########| 1/1 [00:00<00:00, 24.05it/s, loss=0.187, v_num=4, train_loss_step=0.146, train_loss_epoch=0.150]Epoch 49: 100%|##########| 1/1 [00:00<00:00, 23.41it/s, loss=0.187, v_num=4, train_loss_step=0.146, train_loss_epoch=0.146]Epoch 49:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.187, v_num=4, train_loss_step=0.146, train_loss_epoch=0.146]        Epoch 50:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.187, v_num=4, train_loss_step=0.146, train_loss_epoch=0.146]Epoch 50: 100%|##########| 1/1 [00:00<00:00, 25.04it/s, loss=0.187, v_num=4, train_loss_step=0.146, train_loss_epoch=0.146]Epoch 50: 100%|##########| 1/1 [00:00<00:00, 24.75it/s, loss=0.183, v_num=4, train_loss_step=0.144, train_loss_epoch=0.146]Epoch 50: 100%|##########| 1/1 [00:00<00:00, 24.41it/s, loss=0.183, v_num=4, train_loss_step=0.144, train_loss_epoch=0.144]Epoch 50:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.183, v_num=4, train_loss_step=0.144, train_loss_epoch=0.144]        Epoch 51:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.183, v_num=4, train_loss_step=0.144, train_loss_epoch=0.144]Epoch 51: 100%|##########| 1/1 [00:00<00:00, 24.10it/s, loss=0.183, v_num=4, train_loss_step=0.144, train_loss_epoch=0.144]Epoch 51: 100%|##########| 1/1 [00:00<00:00, 23.79it/s, loss=0.179, v_num=4, train_loss_step=0.142, train_loss_epoch=0.144]Epoch 51: 100%|##########| 1/1 [00:00<00:00, 23.44it/s, loss=0.179, v_num=4, train_loss_step=0.142, train_loss_epoch=0.142]Epoch 51:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.179, v_num=4, train_loss_step=0.142, train_loss_epoch=0.142]        Epoch 52:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.179, v_num=4, train_loss_step=0.142, train_loss_epoch=0.142]Epoch 52: 100%|##########| 1/1 [00:00<00:00, 22.98it/s, loss=0.179, v_num=4, train_loss_step=0.142, train_loss_epoch=0.142]Epoch 52: 100%|##########| 1/1 [00:00<00:00, 22.68it/s, loss=0.175, v_num=4, train_loss_step=0.140, train_loss_epoch=0.142]Epoch 52: 100%|##########| 1/1 [00:00<00:00, 22.37it/s, loss=0.175, v_num=4, train_loss_step=0.140, train_loss_epoch=0.140]Epoch 52:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.175, v_num=4, train_loss_step=0.140, train_loss_epoch=0.140]        Epoch 53:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.175, v_num=4, train_loss_step=0.140, train_loss_epoch=0.140]Epoch 53: 100%|##########| 1/1 [00:00<00:00, 23.61it/s, loss=0.175, v_num=4, train_loss_step=0.140, train_loss_epoch=0.140]Epoch 53: 100%|##########| 1/1 [00:00<00:00, 23.29it/s, loss=0.171, v_num=4, train_loss_step=0.138, train_loss_epoch=0.140]Epoch 53: 100%|##########| 1/1 [00:00<00:00, 22.93it/s, loss=0.171, v_num=4, train_loss_step=0.138, train_loss_epoch=0.138]Epoch 53:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.171, v_num=4, train_loss_step=0.138, train_loss_epoch=0.138]        Epoch 54:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.171, v_num=4, train_loss_step=0.138, train_loss_epoch=0.138]Epoch 54: 100%|##########| 1/1 [00:00<00:00, 23.81it/s, loss=0.171, v_num=4, train_loss_step=0.138, train_loss_epoch=0.138]Epoch 54: 100%|##########| 1/1 [00:00<00:00, 23.56it/s, loss=0.168, v_num=4, train_loss_step=0.136, train_loss_epoch=0.138]Epoch 54: 100%|##########| 1/1 [00:00<00:00, 23.28it/s, loss=0.168, v_num=4, train_loss_step=0.136, train_loss_epoch=0.136]Epoch 54:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.168, v_num=4, train_loss_step=0.136, train_loss_epoch=0.136]        Epoch 55:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.168, v_num=4, train_loss_step=0.136, train_loss_epoch=0.136]Epoch 55: 100%|##########| 1/1 [00:00<00:00, 24.07it/s, loss=0.168, v_num=4, train_loss_step=0.136, train_loss_epoch=0.136]Epoch 55: 100%|##########| 1/1 [00:00<00:00, 23.83it/s, loss=0.164, v_num=4, train_loss_step=0.135, train_loss_epoch=0.136]Epoch 55: 100%|##########| 1/1 [00:00<00:00, 23.49it/s, loss=0.164, v_num=4, train_loss_step=0.135, train_loss_epoch=0.135]Epoch 55:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.164, v_num=4, train_loss_step=0.135, train_loss_epoch=0.135]        Epoch 56:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.164, v_num=4, train_loss_step=0.135, train_loss_epoch=0.135]Epoch 56: 100%|##########| 1/1 [00:00<00:00, 22.35it/s, loss=0.164, v_num=4, train_loss_step=0.135, train_loss_epoch=0.135]Epoch 56: 100%|##########| 1/1 [00:00<00:00, 22.03it/s, loss=0.16, v_num=4, train_loss_step=0.134, train_loss_epoch=0.135] Epoch 56: 100%|##########| 1/1 [00:00<00:00, 21.72it/s, loss=0.16, v_num=4, train_loss_step=0.134, train_loss_epoch=0.134]Epoch 56:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.16, v_num=4, train_loss_step=0.134, train_loss_epoch=0.134]        Epoch 57:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.16, v_num=4, train_loss_step=0.134, train_loss_epoch=0.134]Epoch 57: 100%|##########| 1/1 [00:00<00:00, 22.44it/s, loss=0.16, v_num=4, train_loss_step=0.134, train_loss_epoch=0.134]Epoch 57: 100%|##########| 1/1 [00:00<00:00, 22.21it/s, loss=0.157, v_num=4, train_loss_step=0.133, train_loss_epoch=0.134]Epoch 57: 100%|##########| 1/1 [00:00<00:00, 21.93it/s, loss=0.157, v_num=4, train_loss_step=0.133, train_loss_epoch=0.133]Epoch 57:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.157, v_num=4, train_loss_step=0.133, train_loss_epoch=0.133]        Epoch 58:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.157, v_num=4, train_loss_step=0.133, train_loss_epoch=0.133]Epoch 58: 100%|##########| 1/1 [00:00<00:00, 23.01it/s, loss=0.157, v_num=4, train_loss_step=0.133, train_loss_epoch=0.133]Epoch 58: 100%|##########| 1/1 [00:00<00:00, 22.73it/s, loss=0.154, v_num=4, train_loss_step=0.131, train_loss_epoch=0.133]Epoch 58: 100%|##########| 1/1 [00:00<00:00, 22.40it/s, loss=0.154, v_num=4, train_loss_step=0.131, train_loss_epoch=0.131]Epoch 58:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.154, v_num=4, train_loss_step=0.131, train_loss_epoch=0.131]        Epoch 59:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.154, v_num=4, train_loss_step=0.131, train_loss_epoch=0.131]Epoch 59: 100%|##########| 1/1 [00:00<00:00, 23.99it/s, loss=0.154, v_num=4, train_loss_step=0.131, train_loss_epoch=0.131]Epoch 59: 100%|##########| 1/1 [00:00<00:00, 23.75it/s, loss=0.151, v_num=4, train_loss_step=0.130, train_loss_epoch=0.131]Epoch 59: 100%|##########| 1/1 [00:00<00:00, 23.44it/s, loss=0.151, v_num=4, train_loss_step=0.130, train_loss_epoch=0.130]Epoch 59:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.151, v_num=4, train_loss_step=0.130, train_loss_epoch=0.130]        Epoch 60:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.151, v_num=4, train_loss_step=0.130, train_loss_epoch=0.130]Epoch 60: 100%|##########| 1/1 [00:00<00:00, 23.81it/s, loss=0.151, v_num=4, train_loss_step=0.130, train_loss_epoch=0.130]Epoch 60: 100%|##########| 1/1 [00:00<00:00, 23.53it/s, loss=0.148, v_num=4, train_loss_step=0.129, train_loss_epoch=0.130]Epoch 60: 100%|##########| 1/1 [00:00<00:00, 23.20it/s, loss=0.148, v_num=4, train_loss_step=0.129, train_loss_epoch=0.129]Epoch 60:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.148, v_num=4, train_loss_step=0.129, train_loss_epoch=0.129]        Epoch 61:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.148, v_num=4, train_loss_step=0.129, train_loss_epoch=0.129]Epoch 61: 100%|##########| 1/1 [00:00<00:00, 23.32it/s, loss=0.148, v_num=4, train_loss_step=0.129, train_loss_epoch=0.129]Epoch 61: 100%|##########| 1/1 [00:00<00:00, 23.01it/s, loss=0.145, v_num=4, train_loss_step=0.127, train_loss_epoch=0.129]Epoch 61: 100%|##########| 1/1 [00:00<00:00, 22.68it/s, loss=0.145, v_num=4, train_loss_step=0.127, train_loss_epoch=0.127]Epoch 61:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.145, v_num=4, train_loss_step=0.127, train_loss_epoch=0.127]        Epoch 62:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.145, v_num=4, train_loss_step=0.127, train_loss_epoch=0.127]Epoch 62: 100%|##########| 1/1 [00:00<00:00, 22.37it/s, loss=0.145, v_num=4, train_loss_step=0.127, train_loss_epoch=0.127]Epoch 62: 100%|##########| 1/1 [00:00<00:00, 22.10it/s, loss=0.143, v_num=4, train_loss_step=0.126, train_loss_epoch=0.127]Epoch 62: 100%|##########| 1/1 [00:00<00:00, 21.80it/s, loss=0.143, v_num=4, train_loss_step=0.126, train_loss_epoch=0.126]Epoch 62:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.143, v_num=4, train_loss_step=0.126, train_loss_epoch=0.126]        Epoch 63:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.143, v_num=4, train_loss_step=0.126, train_loss_epoch=0.126]Epoch 63: 100%|##########| 1/1 [00:00<00:00, 24.06it/s, loss=0.143, v_num=4, train_loss_step=0.126, train_loss_epoch=0.126]Epoch 63: 100%|##########| 1/1 [00:00<00:00, 23.77it/s, loss=0.141, v_num=4, train_loss_step=0.125, train_loss_epoch=0.126]Epoch 63: 100%|##########| 1/1 [00:00<00:00, 23.42it/s, loss=0.141, v_num=4, train_loss_step=0.125, train_loss_epoch=0.125]Epoch 63:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.141, v_num=4, train_loss_step=0.125, train_loss_epoch=0.125]        Epoch 64:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.141, v_num=4, train_loss_step=0.125, train_loss_epoch=0.125]Epoch 64: 100%|##########| 1/1 [00:00<00:00, 23.23it/s, loss=0.141, v_num=4, train_loss_step=0.125, train_loss_epoch=0.125]Epoch 64: 100%|##########| 1/1 [00:00<00:00, 23.05it/s, loss=0.138, v_num=4, train_loss_step=0.123, train_loss_epoch=0.125]Epoch 64: 100%|##########| 1/1 [00:00<00:00, 22.73it/s, loss=0.138, v_num=4, train_loss_step=0.123, train_loss_epoch=0.123]Epoch 64:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.138, v_num=4, train_loss_step=0.123, train_loss_epoch=0.123]        Epoch 65:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.138, v_num=4, train_loss_step=0.123, train_loss_epoch=0.123]Epoch 65: 100%|##########| 1/1 [00:00<00:00, 23.74it/s, loss=0.138, v_num=4, train_loss_step=0.123, train_loss_epoch=0.123]Epoch 65: 100%|##########| 1/1 [00:00<00:00, 23.54it/s, loss=0.136, v_num=4, train_loss_step=0.122, train_loss_epoch=0.123]Epoch 65: 100%|##########| 1/1 [00:00<00:00, 23.18it/s, loss=0.136, v_num=4, train_loss_step=0.122, train_loss_epoch=0.122]Epoch 65:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.136, v_num=4, train_loss_step=0.122, train_loss_epoch=0.122]        Epoch 66:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.136, v_num=4, train_loss_step=0.122, train_loss_epoch=0.122]Epoch 66: 100%|##########| 1/1 [00:00<00:00, 23.97it/s, loss=0.136, v_num=4, train_loss_step=0.122, train_loss_epoch=0.122]Epoch 66: 100%|##########| 1/1 [00:00<00:00, 23.71it/s, loss=0.134, v_num=4, train_loss_step=0.120, train_loss_epoch=0.122]Epoch 66: 100%|##########| 1/1 [00:00<00:00, 23.40it/s, loss=0.134, v_num=4, train_loss_step=0.120, train_loss_epoch=0.120]Epoch 66:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.134, v_num=4, train_loss_step=0.120, train_loss_epoch=0.120]        Epoch 67:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.134, v_num=4, train_loss_step=0.120, train_loss_epoch=0.120]Epoch 67: 100%|##########| 1/1 [00:00<00:00, 23.30it/s, loss=0.134, v_num=4, train_loss_step=0.120, train_loss_epoch=0.120]Epoch 67: 100%|##########| 1/1 [00:00<00:00, 23.13it/s, loss=0.132, v_num=4, train_loss_step=0.119, train_loss_epoch=0.120]Epoch 67: 100%|##########| 1/1 [00:00<00:00, 22.85it/s, loss=0.132, v_num=4, train_loss_step=0.119, train_loss_epoch=0.119]Epoch 67:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.132, v_num=4, train_loss_step=0.119, train_loss_epoch=0.119]        Epoch 68:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.132, v_num=4, train_loss_step=0.119, train_loss_epoch=0.119]Epoch 68: 100%|##########| 1/1 [00:00<00:00, 23.34it/s, loss=0.132, v_num=4, train_loss_step=0.119, train_loss_epoch=0.119]Epoch 68: 100%|##########| 1/1 [00:00<00:00, 23.00it/s, loss=0.131, v_num=4, train_loss_step=0.118, train_loss_epoch=0.119]Epoch 68: 100%|##########| 1/1 [00:00<00:00, 22.68it/s, loss=0.131, v_num=4, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 68:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.131, v_num=4, train_loss_step=0.118, train_loss_epoch=0.118]        Epoch 69:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.131, v_num=4, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 69: 100%|##########| 1/1 [00:00<00:00, 22.65it/s, loss=0.131, v_num=4, train_loss_step=0.118, train_loss_epoch=0.118]Epoch 69: 100%|##########| 1/1 [00:00<00:00, 22.44it/s, loss=0.129, v_num=4, train_loss_step=0.117, train_loss_epoch=0.118]Epoch 69: 100%|##########| 1/1 [00:00<00:00, 22.15it/s, loss=0.129, v_num=4, train_loss_step=0.117, train_loss_epoch=0.117]Epoch 69:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.129, v_num=4, train_loss_step=0.117, train_loss_epoch=0.117]        Epoch 70:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.129, v_num=4, train_loss_step=0.117, train_loss_epoch=0.117]Epoch 70: 100%|##########| 1/1 [00:00<00:00, 23.50it/s, loss=0.129, v_num=4, train_loss_step=0.117, train_loss_epoch=0.117]Epoch 70: 100%|##########| 1/1 [00:00<00:00, 23.18it/s, loss=0.128, v_num=4, train_loss_step=0.116, train_loss_epoch=0.117]Epoch 70: 100%|##########| 1/1 [00:00<00:00, 22.87it/s, loss=0.128, v_num=4, train_loss_step=0.116, train_loss_epoch=0.116]Epoch 70:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.128, v_num=4, train_loss_step=0.116, train_loss_epoch=0.116]        Epoch 71:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.128, v_num=4, train_loss_step=0.116, train_loss_epoch=0.116]Epoch 71: 100%|##########| 1/1 [00:00<00:00, 24.07it/s, loss=0.128, v_num=4, train_loss_step=0.116, train_loss_epoch=0.116]Epoch 71: 100%|##########| 1/1 [00:00<00:00, 23.74it/s, loss=0.127, v_num=4, train_loss_step=0.115, train_loss_epoch=0.116]Epoch 71: 100%|##########| 1/1 [00:00<00:00, 23.39it/s, loss=0.127, v_num=4, train_loss_step=0.115, train_loss_epoch=0.115]Epoch 71:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.127, v_num=4, train_loss_step=0.115, train_loss_epoch=0.115]        Epoch 72:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.127, v_num=4, train_loss_step=0.115, train_loss_epoch=0.115]Epoch 72: 100%|##########| 1/1 [00:00<00:00, 22.87it/s, loss=0.127, v_num=4, train_loss_step=0.115, train_loss_epoch=0.115]Epoch 72: 100%|##########| 1/1 [00:00<00:00, 22.58it/s, loss=0.125, v_num=4, train_loss_step=0.114, train_loss_epoch=0.115]Epoch 72: 100%|##########| 1/1 [00:00<00:00, 22.28it/s, loss=0.125, v_num=4, train_loss_step=0.114, train_loss_epoch=0.114]Epoch 72:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.125, v_num=4, train_loss_step=0.114, train_loss_epoch=0.114]        Epoch 73:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.125, v_num=4, train_loss_step=0.114, train_loss_epoch=0.114]Epoch 73: 100%|##########| 1/1 [00:00<00:00, 23.40it/s, loss=0.125, v_num=4, train_loss_step=0.114, train_loss_epoch=0.114]Epoch 73: 100%|##########| 1/1 [00:00<00:00, 23.18it/s, loss=0.124, v_num=4, train_loss_step=0.113, train_loss_epoch=0.114]Epoch 73: 100%|##########| 1/1 [00:00<00:00, 22.91it/s, loss=0.124, v_num=4, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 73:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.124, v_num=4, train_loss_step=0.113, train_loss_epoch=0.113]        Epoch 74:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.124, v_num=4, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 74: 100%|##########| 1/1 [00:00<00:00, 22.93it/s, loss=0.124, v_num=4, train_loss_step=0.113, train_loss_epoch=0.113]Epoch 74: 100%|##########| 1/1 [00:00<00:00, 22.65it/s, loss=0.123, v_num=4, train_loss_step=0.112, train_loss_epoch=0.113]Epoch 74: 100%|##########| 1/1 [00:00<00:00, 22.33it/s, loss=0.123, v_num=4, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 74:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.123, v_num=4, train_loss_step=0.112, train_loss_epoch=0.112]        Epoch 75:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.123, v_num=4, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 75: 100%|##########| 1/1 [00:00<00:00, 24.36it/s, loss=0.123, v_num=4, train_loss_step=0.112, train_loss_epoch=0.112]Epoch 75: 100%|##########| 1/1 [00:00<00:00, 24.02it/s, loss=0.122, v_num=4, train_loss_step=0.111, train_loss_epoch=0.112]Epoch 75: 100%|##########| 1/1 [00:00<00:00, 23.66it/s, loss=0.122, v_num=4, train_loss_step=0.111, train_loss_epoch=0.111]Epoch 75:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.122, v_num=4, train_loss_step=0.111, train_loss_epoch=0.111]        Epoch 76:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.122, v_num=4, train_loss_step=0.111, train_loss_epoch=0.111]Epoch 76: 100%|##########| 1/1 [00:00<00:00, 23.44it/s, loss=0.122, v_num=4, train_loss_step=0.111, train_loss_epoch=0.111]Epoch 76: 100%|##########| 1/1 [00:00<00:00, 23.24it/s, loss=0.12, v_num=4, train_loss_step=0.110, train_loss_epoch=0.111] Epoch 76: 100%|##########| 1/1 [00:00<00:00, 22.93it/s, loss=0.12, v_num=4, train_loss_step=0.110, train_loss_epoch=0.110]Epoch 76:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.12, v_num=4, train_loss_step=0.110, train_loss_epoch=0.110]        Epoch 77:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.12, v_num=4, train_loss_step=0.110, train_loss_epoch=0.110]Epoch 77: 100%|##########| 1/1 [00:00<00:00, 23.95it/s, loss=0.12, v_num=4, train_loss_step=0.110, train_loss_epoch=0.110]Epoch 77: 100%|##########| 1/1 [00:00<00:00, 23.70it/s, loss=0.119, v_num=4, train_loss_step=0.109, train_loss_epoch=0.110]Epoch 77: 100%|##########| 1/1 [00:00<00:00, 23.39it/s, loss=0.119, v_num=4, train_loss_step=0.109, train_loss_epoch=0.109]Epoch 77:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.119, v_num=4, train_loss_step=0.109, train_loss_epoch=0.109]        Epoch 78:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.119, v_num=4, train_loss_step=0.109, train_loss_epoch=0.109]Epoch 78: 100%|##########| 1/1 [00:00<00:00, 24.74it/s, loss=0.119, v_num=4, train_loss_step=0.109, train_loss_epoch=0.109]Epoch 78: 100%|##########| 1/1 [00:00<00:00, 24.48it/s, loss=0.118, v_num=4, train_loss_step=0.108, train_loss_epoch=0.109]Epoch 78: 100%|##########| 1/1 [00:00<00:00, 24.15it/s, loss=0.118, v_num=4, train_loss_step=0.108, train_loss_epoch=0.108]Epoch 78:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.118, v_num=4, train_loss_step=0.108, train_loss_epoch=0.108]        Epoch 79:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.118, v_num=4, train_loss_step=0.108, train_loss_epoch=0.108]Epoch 79: 100%|##########| 1/1 [00:00<00:00, 23.30it/s, loss=0.118, v_num=4, train_loss_step=0.108, train_loss_epoch=0.108]Epoch 79: 100%|##########| 1/1 [00:00<00:00, 23.06it/s, loss=0.117, v_num=4, train_loss_step=0.107, train_loss_epoch=0.108]Epoch 79: 100%|##########| 1/1 [00:00<00:00, 22.79it/s, loss=0.117, v_num=4, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 79:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.117, v_num=4, train_loss_step=0.107, train_loss_epoch=0.107]        Epoch 80:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.117, v_num=4, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 80: 100%|##########| 1/1 [00:00<00:00, 23.70it/s, loss=0.117, v_num=4, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 80: 100%|##########| 1/1 [00:00<00:00, 23.42it/s, loss=0.116, v_num=4, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 80: 100%|##########| 1/1 [00:00<00:00, 23.11it/s, loss=0.116, v_num=4, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 80:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.116, v_num=4, train_loss_step=0.107, train_loss_epoch=0.107]        Epoch 81:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.116, v_num=4, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 81: 100%|##########| 1/1 [00:00<00:00, 24.12it/s, loss=0.116, v_num=4, train_loss_step=0.107, train_loss_epoch=0.107]Epoch 81: 100%|##########| 1/1 [00:00<00:00, 23.87it/s, loss=0.115, v_num=4, train_loss_step=0.105, train_loss_epoch=0.107]Epoch 81: 100%|##########| 1/1 [00:00<00:00, 23.53it/s, loss=0.115, v_num=4, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 81:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.115, v_num=4, train_loss_step=0.105, train_loss_epoch=0.105]        Epoch 82:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.115, v_num=4, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 82: 100%|##########| 1/1 [00:00<00:00, 23.82it/s, loss=0.115, v_num=4, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 82: 100%|##########| 1/1 [00:00<00:00, 23.55it/s, loss=0.114, v_num=4, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 82: 100%|##########| 1/1 [00:00<00:00, 23.22it/s, loss=0.114, v_num=4, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 82:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.114, v_num=4, train_loss_step=0.105, train_loss_epoch=0.105]        Epoch 83:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.114, v_num=4, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 83: 100%|##########| 1/1 [00:00<00:00, 23.63it/s, loss=0.114, v_num=4, train_loss_step=0.105, train_loss_epoch=0.105]Epoch 83: 100%|##########| 1/1 [00:00<00:00, 23.33it/s, loss=0.113, v_num=4, train_loss_step=0.104, train_loss_epoch=0.105]Epoch 83: 100%|##########| 1/1 [00:00<00:00, 23.02it/s, loss=0.113, v_num=4, train_loss_step=0.104, train_loss_epoch=0.104]Epoch 83:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.113, v_num=4, train_loss_step=0.104, train_loss_epoch=0.104]        Epoch 84:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.113, v_num=4, train_loss_step=0.104, train_loss_epoch=0.104]Epoch 84: 100%|##########| 1/1 [00:00<00:00, 23.80it/s, loss=0.113, v_num=4, train_loss_step=0.104, train_loss_epoch=0.104]Epoch 84: 100%|##########| 1/1 [00:00<00:00, 23.51it/s, loss=0.112, v_num=4, train_loss_step=0.103, train_loss_epoch=0.104]Epoch 84: 100%|##########| 1/1 [00:00<00:00, 23.22it/s, loss=0.112, v_num=4, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 84:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.112, v_num=4, train_loss_step=0.103, train_loss_epoch=0.103]        Epoch 85:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.112, v_num=4, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 85: 100%|##########| 1/1 [00:00<00:00, 21.53it/s, loss=0.112, v_num=4, train_loss_step=0.103, train_loss_epoch=0.103]Epoch 85: 100%|##########| 1/1 [00:00<00:00, 21.26it/s, loss=0.111, v_num=4, train_loss_step=0.102, train_loss_epoch=0.103]Epoch 85: 100%|##########| 1/1 [00:00<00:00, 20.98it/s, loss=0.111, v_num=4, train_loss_step=0.102, train_loss_epoch=0.102]Epoch 85:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.111, v_num=4, train_loss_step=0.102, train_loss_epoch=0.102]        Epoch 86:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.111, v_num=4, train_loss_step=0.102, train_loss_epoch=0.102]Epoch 86: 100%|##########| 1/1 [00:00<00:00, 22.32it/s, loss=0.111, v_num=4, train_loss_step=0.102, train_loss_epoch=0.102]Epoch 86: 100%|##########| 1/1 [00:00<00:00, 22.08it/s, loss=0.11, v_num=4, train_loss_step=0.101, train_loss_epoch=0.102] Epoch 86: 100%|##########| 1/1 [00:00<00:00, 21.81it/s, loss=0.11, v_num=4, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 86:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.11, v_num=4, train_loss_step=0.101, train_loss_epoch=0.101]        Epoch 87:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.11, v_num=4, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 87: 100%|##########| 1/1 [00:00<00:00, 22.85it/s, loss=0.11, v_num=4, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 87: 100%|##########| 1/1 [00:00<00:00, 22.56it/s, loss=0.109, v_num=4, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 87: 100%|##########| 1/1 [00:00<00:00, 22.27it/s, loss=0.109, v_num=4, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 87:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.109, v_num=4, train_loss_step=0.101, train_loss_epoch=0.101]        Epoch 88:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.109, v_num=4, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 88: 100%|##########| 1/1 [00:00<00:00, 22.55it/s, loss=0.109, v_num=4, train_loss_step=0.101, train_loss_epoch=0.101]Epoch 88: 100%|##########| 1/1 [00:00<00:00, 22.28it/s, loss=0.108, v_num=4, train_loss_step=0.0997, train_loss_epoch=0.101]Epoch 88: 100%|##########| 1/1 [00:00<00:00, 21.97it/s, loss=0.108, v_num=4, train_loss_step=0.0997, train_loss_epoch=0.0997]Epoch 88:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.108, v_num=4, train_loss_step=0.0997, train_loss_epoch=0.0997]        Epoch 89:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.108, v_num=4, train_loss_step=0.0997, train_loss_epoch=0.0997]Epoch 89: 100%|##########| 1/1 [00:00<00:00, 23.08it/s, loss=0.108, v_num=4, train_loss_step=0.0997, train_loss_epoch=0.0997]Epoch 89: 100%|##########| 1/1 [00:00<00:00, 22.79it/s, loss=0.107, v_num=4, train_loss_step=0.0988, train_loss_epoch=0.0997]Epoch 89: 100%|##########| 1/1 [00:00<00:00, 22.48it/s, loss=0.107, v_num=4, train_loss_step=0.0988, train_loss_epoch=0.0988]Epoch 89:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.107, v_num=4, train_loss_step=0.0988, train_loss_epoch=0.0988]        Epoch 90:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.107, v_num=4, train_loss_step=0.0988, train_loss_epoch=0.0988]Epoch 90: 100%|##########| 1/1 [00:00<00:00, 23.34it/s, loss=0.107, v_num=4, train_loss_step=0.0988, train_loss_epoch=0.0988]Epoch 90: 100%|##########| 1/1 [00:00<00:00, 23.05it/s, loss=0.106, v_num=4, train_loss_step=0.0984, train_loss_epoch=0.0988]Epoch 90: 100%|##########| 1/1 [00:00<00:00, 22.78it/s, loss=0.106, v_num=4, train_loss_step=0.0984, train_loss_epoch=0.0984]Epoch 90:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.106, v_num=4, train_loss_step=0.0984, train_loss_epoch=0.0984]        Epoch 91:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.106, v_num=4, train_loss_step=0.0984, train_loss_epoch=0.0984]Epoch 91: 100%|##########| 1/1 [00:00<00:00, 23.66it/s, loss=0.106, v_num=4, train_loss_step=0.0984, train_loss_epoch=0.0984]Epoch 91: 100%|##########| 1/1 [00:00<00:00, 23.39it/s, loss=0.105, v_num=4, train_loss_step=0.0973, train_loss_epoch=0.0984]Epoch 91: 100%|##########| 1/1 [00:00<00:00, 23.11it/s, loss=0.105, v_num=4, train_loss_step=0.0973, train_loss_epoch=0.0973]Epoch 91:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.105, v_num=4, train_loss_step=0.0973, train_loss_epoch=0.0973]        Epoch 92:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.105, v_num=4, train_loss_step=0.0973, train_loss_epoch=0.0973]Epoch 92: 100%|##########| 1/1 [00:00<00:00, 23.63it/s, loss=0.105, v_num=4, train_loss_step=0.0973, train_loss_epoch=0.0973]Epoch 92: 100%|##########| 1/1 [00:00<00:00, 23.34it/s, loss=0.104, v_num=4, train_loss_step=0.0963, train_loss_epoch=0.0973]Epoch 92: 100%|##########| 1/1 [00:00<00:00, 23.03it/s, loss=0.104, v_num=4, train_loss_step=0.0963, train_loss_epoch=0.0963]Epoch 92:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.104, v_num=4, train_loss_step=0.0963, train_loss_epoch=0.0963]        Epoch 93:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.104, v_num=4, train_loss_step=0.0963, train_loss_epoch=0.0963]Epoch 93: 100%|##########| 1/1 [00:00<00:00, 24.17it/s, loss=0.104, v_num=4, train_loss_step=0.0963, train_loss_epoch=0.0963]Epoch 93: 100%|##########| 1/1 [00:00<00:00, 23.87it/s, loss=0.104, v_num=4, train_loss_step=0.0955, train_loss_epoch=0.0963]Epoch 93: 100%|##########| 1/1 [00:00<00:00, 23.54it/s, loss=0.104, v_num=4, train_loss_step=0.0955, train_loss_epoch=0.0955]Epoch 93:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.104, v_num=4, train_loss_step=0.0955, train_loss_epoch=0.0955]        Epoch 94:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.104, v_num=4, train_loss_step=0.0955, train_loss_epoch=0.0955]Epoch 94: 100%|##########| 1/1 [00:00<00:00, 23.87it/s, loss=0.104, v_num=4, train_loss_step=0.0955, train_loss_epoch=0.0955]Epoch 94: 100%|##########| 1/1 [00:00<00:00, 23.57it/s, loss=0.103, v_num=4, train_loss_step=0.0947, train_loss_epoch=0.0955]Epoch 94: 100%|##########| 1/1 [00:00<00:00, 23.25it/s, loss=0.103, v_num=4, train_loss_step=0.0947, train_loss_epoch=0.0947]Epoch 94:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.103, v_num=4, train_loss_step=0.0947, train_loss_epoch=0.0947]        Epoch 95:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.103, v_num=4, train_loss_step=0.0947, train_loss_epoch=0.0947]Epoch 95: 100%|##########| 1/1 [00:00<00:00, 22.97it/s, loss=0.103, v_num=4, train_loss_step=0.0947, train_loss_epoch=0.0947]Epoch 95: 100%|##########| 1/1 [00:00<00:00, 22.66it/s, loss=0.102, v_num=4, train_loss_step=0.0938, train_loss_epoch=0.0947]Epoch 95: 100%|##########| 1/1 [00:00<00:00, 22.33it/s, loss=0.102, v_num=4, train_loss_step=0.0938, train_loss_epoch=0.0938]Epoch 95:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.102, v_num=4, train_loss_step=0.0938, train_loss_epoch=0.0938]        Epoch 96:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.102, v_num=4, train_loss_step=0.0938, train_loss_epoch=0.0938]Epoch 96: 100%|##########| 1/1 [00:00<00:00, 23.22it/s, loss=0.102, v_num=4, train_loss_step=0.0938, train_loss_epoch=0.0938]Epoch 96: 100%|##########| 1/1 [00:00<00:00, 22.94it/s, loss=0.101, v_num=4, train_loss_step=0.0928, train_loss_epoch=0.0938]Epoch 96: 100%|##########| 1/1 [00:00<00:00, 22.65it/s, loss=0.101, v_num=4, train_loss_step=0.0928, train_loss_epoch=0.0928]Epoch 96:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.101, v_num=4, train_loss_step=0.0928, train_loss_epoch=0.0928]        Epoch 97:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.101, v_num=4, train_loss_step=0.0928, train_loss_epoch=0.0928]Epoch 97: 100%|##########| 1/1 [00:00<00:00, 23.85it/s, loss=0.101, v_num=4, train_loss_step=0.0928, train_loss_epoch=0.0928]Epoch 97: 100%|##########| 1/1 [00:00<00:00, 23.55it/s, loss=0.1, v_num=4, train_loss_step=0.0921, train_loss_epoch=0.0928]  Epoch 97: 100%|##########| 1/1 [00:00<00:00, 23.27it/s, loss=0.1, v_num=4, train_loss_step=0.0921, train_loss_epoch=0.0921]Epoch 97:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.1, v_num=4, train_loss_step=0.0921, train_loss_epoch=0.0921]        Epoch 98:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.1, v_num=4, train_loss_step=0.0921, train_loss_epoch=0.0921]Epoch 98: 100%|##########| 1/1 [00:00<00:00, 22.20it/s, loss=0.1, v_num=4, train_loss_step=0.0921, train_loss_epoch=0.0921]Epoch 98: 100%|##########| 1/1 [00:00<00:00, 21.91it/s, loss=0.0993, v_num=4, train_loss_step=0.0911, train_loss_epoch=0.0921]Epoch 98: 100%|##########| 1/1 [00:00<00:00, 21.62it/s, loss=0.0993, v_num=4, train_loss_step=0.0911, train_loss_epoch=0.0911]Epoch 98:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0993, v_num=4, train_loss_step=0.0911, train_loss_epoch=0.0911]        Epoch 99:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0993, v_num=4, train_loss_step=0.0911, train_loss_epoch=0.0911]Epoch 99: 100%|##########| 1/1 [00:00<00:00, 23.43it/s, loss=0.0993, v_num=4, train_loss_step=0.0911, train_loss_epoch=0.0911]Epoch 99: 100%|##########| 1/1 [00:00<00:00, 23.15it/s, loss=0.0984, v_num=4, train_loss_step=0.0903, train_loss_epoch=0.0911]Epoch 99: 100%|##########| 1/1 [00:00<00:00, 22.54it/s, loss=0.0984, v_num=4, train_loss_step=0.0903, train_loss_epoch=0.0903]Epoch 99:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0984, v_num=4, train_loss_step=0.0903, train_loss_epoch=0.0903]        Epoch 100:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0984, v_num=4, train_loss_step=0.0903, train_loss_epoch=0.0903]Epoch 100: 100%|##########| 1/1 [00:00<00:00, 23.24it/s, loss=0.0984, v_num=4, train_loss_step=0.0903, train_loss_epoch=0.0903]Epoch 100: 100%|##########| 1/1 [00:00<00:00, 22.93it/s, loss=0.0976, v_num=4, train_loss_step=0.0892, train_loss_epoch=0.0903]Epoch 100: 100%|##########| 1/1 [00:00<00:00, 22.61it/s, loss=0.0976, v_num=4, train_loss_step=0.0892, train_loss_epoch=0.0892]Epoch 100:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0976, v_num=4, train_loss_step=0.0892, train_loss_epoch=0.0892]        Epoch 101:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0976, v_num=4, train_loss_step=0.0892, train_loss_epoch=0.0892]Epoch 101: 100%|##########| 1/1 [00:00<00:00, 22.48it/s, loss=0.0976, v_num=4, train_loss_step=0.0892, train_loss_epoch=0.0892]Epoch 101: 100%|##########| 1/1 [00:00<00:00, 22.18it/s, loss=0.0967, v_num=4, train_loss_step=0.0884, train_loss_epoch=0.0892]Epoch 101: 100%|##########| 1/1 [00:00<00:00, 21.89it/s, loss=0.0967, v_num=4, train_loss_step=0.0884, train_loss_epoch=0.0884]Epoch 101:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0967, v_num=4, train_loss_step=0.0884, train_loss_epoch=0.0884]        Epoch 102:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0967, v_num=4, train_loss_step=0.0884, train_loss_epoch=0.0884]Epoch 102: 100%|##########| 1/1 [00:00<00:00, 22.76it/s, loss=0.0967, v_num=4, train_loss_step=0.0884, train_loss_epoch=0.0884]Epoch 102: 100%|##########| 1/1 [00:00<00:00, 22.51it/s, loss=0.0958, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0884]Epoch 102: 100%|##########| 1/1 [00:00<00:00, 22.20it/s, loss=0.0958, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0873]Epoch 102:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0958, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0873]        Epoch 103:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0958, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0873]Epoch 103: 100%|##########| 1/1 [00:00<00:00, 22.68it/s, loss=0.0958, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0873]Epoch 103: 100%|##########| 1/1 [00:00<00:00, 22.38it/s, loss=0.095, v_num=4, train_loss_step=0.0867, train_loss_epoch=0.0873] Epoch 103: 100%|##########| 1/1 [00:00<00:00, 22.08it/s, loss=0.095, v_num=4, train_loss_step=0.0867, train_loss_epoch=0.0867]Epoch 103:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.095, v_num=4, train_loss_step=0.0867, train_loss_epoch=0.0867]        Epoch 104:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.095, v_num=4, train_loss_step=0.0867, train_loss_epoch=0.0867]Epoch 104: 100%|##########| 1/1 [00:00<00:00, 23.10it/s, loss=0.095, v_num=4, train_loss_step=0.0867, train_loss_epoch=0.0867]Epoch 104: 100%|##########| 1/1 [00:00<00:00, 22.79it/s, loss=0.0941, v_num=4, train_loss_step=0.0862, train_loss_epoch=0.0867]Epoch 104: 100%|##########| 1/1 [00:00<00:00, 22.49it/s, loss=0.0941, v_num=4, train_loss_step=0.0862, train_loss_epoch=0.0862]Epoch 104:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0941, v_num=4, train_loss_step=0.0862, train_loss_epoch=0.0862]        Epoch 105:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0941, v_num=4, train_loss_step=0.0862, train_loss_epoch=0.0862]Epoch 105: 100%|##########| 1/1 [00:00<00:00, 23.05it/s, loss=0.0941, v_num=4, train_loss_step=0.0862, train_loss_epoch=0.0862]Epoch 105: 100%|##########| 1/1 [00:00<00:00, 22.77it/s, loss=0.0934, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0862]Epoch 105: 100%|##########| 1/1 [00:00<00:00, 22.47it/s, loss=0.0934, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0873]Epoch 105:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0934, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0873]        Epoch 106:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0934, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0873]Epoch 106: 100%|##########| 1/1 [00:00<00:00, 21.47it/s, loss=0.0934, v_num=4, train_loss_step=0.0873, train_loss_epoch=0.0873]Epoch 106: 100%|##########| 1/1 [00:00<00:00, 21.19it/s, loss=0.0928, v_num=4, train_loss_step=0.0896, train_loss_epoch=0.0873]Epoch 106: 100%|##########| 1/1 [00:00<00:00, 20.92it/s, loss=0.0928, v_num=4, train_loss_step=0.0896, train_loss_epoch=0.0896]Epoch 106:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0928, v_num=4, train_loss_step=0.0896, train_loss_epoch=0.0896]        Epoch 107:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0928, v_num=4, train_loss_step=0.0896, train_loss_epoch=0.0896]Epoch 107: 100%|##########| 1/1 [00:00<00:00, 23.47it/s, loss=0.0928, v_num=4, train_loss_step=0.0896, train_loss_epoch=0.0896]Epoch 107: 100%|##########| 1/1 [00:00<00:00, 23.23it/s, loss=0.0922, v_num=4, train_loss_step=0.0889, train_loss_epoch=0.0896]Epoch 107: 100%|##########| 1/1 [00:00<00:00, 22.93it/s, loss=0.0922, v_num=4, train_loss_step=0.0889, train_loss_epoch=0.0889]Epoch 107:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0922, v_num=4, train_loss_step=0.0889, train_loss_epoch=0.0889]        Epoch 108:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0922, v_num=4, train_loss_step=0.0889, train_loss_epoch=0.0889]Epoch 108: 100%|##########| 1/1 [00:00<00:00, 19.70it/s, loss=0.0922, v_num=4, train_loss_step=0.0889, train_loss_epoch=0.0889]Epoch 108: 100%|##########| 1/1 [00:00<00:00, 19.48it/s, loss=0.0914, v_num=4, train_loss_step=0.0823, train_loss_epoch=0.0889]Epoch 108: 100%|##########| 1/1 [00:00<00:00, 19.25it/s, loss=0.0914, v_num=4, train_loss_step=0.0823, train_loss_epoch=0.0823]Epoch 108:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0914, v_num=4, train_loss_step=0.0823, train_loss_epoch=0.0823]        Epoch 109:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0914, v_num=4, train_loss_step=0.0823, train_loss_epoch=0.0823]Epoch 109: 100%|##########| 1/1 [00:00<00:00, 23.04it/s, loss=0.0914, v_num=4, train_loss_step=0.0823, train_loss_epoch=0.0823]Epoch 109: 100%|##########| 1/1 [00:00<00:00, 22.78it/s, loss=0.0906, v_num=4, train_loss_step=0.083, train_loss_epoch=0.0823] Epoch 109: 100%|##########| 1/1 [00:00<00:00, 22.51it/s, loss=0.0906, v_num=4, train_loss_step=0.083, train_loss_epoch=0.083] Epoch 109:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0906, v_num=4, train_loss_step=0.083, train_loss_epoch=0.083]        Epoch 110:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0906, v_num=4, train_loss_step=0.083, train_loss_epoch=0.083]Epoch 110: 100%|##########| 1/1 [00:00<00:00, 24.09it/s, loss=0.0906, v_num=4, train_loss_step=0.083, train_loss_epoch=0.083]Epoch 110: 100%|##########| 1/1 [00:00<00:00, 23.86it/s, loss=0.09, v_num=4, train_loss_step=0.0872, train_loss_epoch=0.083] Epoch 110: 100%|##########| 1/1 [00:00<00:00, 23.53it/s, loss=0.09, v_num=4, train_loss_step=0.0872, train_loss_epoch=0.0872]Epoch 110:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.09, v_num=4, train_loss_step=0.0872, train_loss_epoch=0.0872]        Epoch 111:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.09, v_num=4, train_loss_step=0.0872, train_loss_epoch=0.0872]Epoch 111: 100%|##########| 1/1 [00:00<00:00, 24.28it/s, loss=0.09, v_num=4, train_loss_step=0.0872, train_loss_epoch=0.0872]Epoch 111: 100%|##########| 1/1 [00:00<00:00, 23.99it/s, loss=0.0892, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0872]Epoch 111: 100%|##########| 1/1 [00:00<00:00, 23.64it/s, loss=0.0892, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0818]Epoch 111:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0892, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0818]        Epoch 112:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0892, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0818]Epoch 112: 100%|##########| 1/1 [00:00<00:00, 23.87it/s, loss=0.0892, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0818]Epoch 112: 100%|##########| 1/1 [00:00<00:00, 23.69it/s, loss=0.0884, v_num=4, train_loss_step=0.0788, train_loss_epoch=0.0818]Epoch 112: 100%|##########| 1/1 [00:00<00:00, 23.41it/s, loss=0.0884, v_num=4, train_loss_step=0.0788, train_loss_epoch=0.0788]Epoch 112:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0884, v_num=4, train_loss_step=0.0788, train_loss_epoch=0.0788]        Epoch 113:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0884, v_num=4, train_loss_step=0.0788, train_loss_epoch=0.0788]Epoch 113: 100%|##########| 1/1 [00:00<00:00, 24.27it/s, loss=0.0884, v_num=4, train_loss_step=0.0788, train_loss_epoch=0.0788]Epoch 113: 100%|##########| 1/1 [00:00<00:00, 24.08it/s, loss=0.0877, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0788]Epoch 113: 100%|##########| 1/1 [00:00<00:00, 23.74it/s, loss=0.0877, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0818]Epoch 113:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0877, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0818]        Epoch 114:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0877, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0818]Epoch 114: 100%|##########| 1/1 [00:00<00:00, 22.92it/s, loss=0.0877, v_num=4, train_loss_step=0.0818, train_loss_epoch=0.0818]Epoch 114: 100%|##########| 1/1 [00:00<00:00, 22.70it/s, loss=0.087, v_num=4, train_loss_step=0.0814, train_loss_epoch=0.0818] Epoch 114: 100%|##########| 1/1 [00:00<00:00, 22.40it/s, loss=0.087, v_num=4, train_loss_step=0.0814, train_loss_epoch=0.0814]Epoch 114:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.087, v_num=4, train_loss_step=0.0814, train_loss_epoch=0.0814]        Epoch 115:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.087, v_num=4, train_loss_step=0.0814, train_loss_epoch=0.0814]Epoch 115: 100%|##########| 1/1 [00:00<00:00, 24.12it/s, loss=0.087, v_num=4, train_loss_step=0.0814, train_loss_epoch=0.0814]Epoch 115: 100%|##########| 1/1 [00:00<00:00, 23.83it/s, loss=0.0861, v_num=4, train_loss_step=0.0763, train_loss_epoch=0.0814]Epoch 115: 100%|##########| 1/1 [00:00<00:00, 23.51it/s, loss=0.0861, v_num=4, train_loss_step=0.0763, train_loss_epoch=0.0763]Epoch 115:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0861, v_num=4, train_loss_step=0.0763, train_loss_epoch=0.0763]        Epoch 116:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0861, v_num=4, train_loss_step=0.0763, train_loss_epoch=0.0763]Epoch 116: 100%|##########| 1/1 [00:00<00:00, 23.16it/s, loss=0.0861, v_num=4, train_loss_step=0.0763, train_loss_epoch=0.0763]Epoch 116: 100%|##########| 1/1 [00:00<00:00, 22.96it/s, loss=0.0854, v_num=4, train_loss_step=0.0775, train_loss_epoch=0.0763]Epoch 116: 100%|##########| 1/1 [00:00<00:00, 22.64it/s, loss=0.0854, v_num=4, train_loss_step=0.0775, train_loss_epoch=0.0775]Epoch 116:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0854, v_num=4, train_loss_step=0.0775, train_loss_epoch=0.0775]        Epoch 117:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0854, v_num=4, train_loss_step=0.0775, train_loss_epoch=0.0775]Epoch 117: 100%|##########| 1/1 [00:00<00:00, 23.24it/s, loss=0.0854, v_num=4, train_loss_step=0.0775, train_loss_epoch=0.0775]Epoch 117: 100%|##########| 1/1 [00:00<00:00, 22.96it/s, loss=0.0847, v_num=4, train_loss_step=0.0787, train_loss_epoch=0.0775]Epoch 117: 100%|##########| 1/1 [00:00<00:00, 22.65it/s, loss=0.0847, v_num=4, train_loss_step=0.0787, train_loss_epoch=0.0787]Epoch 117:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0847, v_num=4, train_loss_step=0.0787, train_loss_epoch=0.0787]        Epoch 118:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0847, v_num=4, train_loss_step=0.0787, train_loss_epoch=0.0787]Epoch 118: 100%|##########| 1/1 [00:00<00:00, 23.39it/s, loss=0.0847, v_num=4, train_loss_step=0.0787, train_loss_epoch=0.0787]Epoch 118: 100%|##########| 1/1 [00:00<00:00, 23.17it/s, loss=0.0839, v_num=4, train_loss_step=0.0759, train_loss_epoch=0.0787]Epoch 118: 100%|##########| 1/1 [00:00<00:00, 22.85it/s, loss=0.0839, v_num=4, train_loss_step=0.0759, train_loss_epoch=0.0759]Epoch 118:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0839, v_num=4, train_loss_step=0.0759, train_loss_epoch=0.0759]        Epoch 119:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0839, v_num=4, train_loss_step=0.0759, train_loss_epoch=0.0759]Epoch 119: 100%|##########| 1/1 [00:00<00:00, 22.45it/s, loss=0.0839, v_num=4, train_loss_step=0.0759, train_loss_epoch=0.0759]Epoch 119: 100%|##########| 1/1 [00:00<00:00, 22.26it/s, loss=0.0831, v_num=4, train_loss_step=0.0727, train_loss_epoch=0.0759]Epoch 119: 100%|##########| 1/1 [00:00<00:00, 21.98it/s, loss=0.0831, v_num=4, train_loss_step=0.0727, train_loss_epoch=0.0727]Epoch 119:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0831, v_num=4, train_loss_step=0.0727, train_loss_epoch=0.0727]        Epoch 120:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0831, v_num=4, train_loss_step=0.0727, train_loss_epoch=0.0727]Epoch 120: 100%|##########| 1/1 [00:00<00:00, 22.36it/s, loss=0.0831, v_num=4, train_loss_step=0.0727, train_loss_epoch=0.0727]Epoch 120: 100%|##########| 1/1 [00:00<00:00, 22.11it/s, loss=0.0824, v_num=4, train_loss_step=0.0752, train_loss_epoch=0.0727]Epoch 120: 100%|##########| 1/1 [00:00<00:00, 21.77it/s, loss=0.0824, v_num=4, train_loss_step=0.0752, train_loss_epoch=0.0752]Epoch 120:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0824, v_num=4, train_loss_step=0.0752, train_loss_epoch=0.0752]        Epoch 121:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0824, v_num=4, train_loss_step=0.0752, train_loss_epoch=0.0752]Epoch 121: 100%|##########| 1/1 [00:00<00:00, 21.87it/s, loss=0.0824, v_num=4, train_loss_step=0.0752, train_loss_epoch=0.0752]Epoch 121: 100%|##########| 1/1 [00:00<00:00, 21.68it/s, loss=0.0818, v_num=4, train_loss_step=0.0776, train_loss_epoch=0.0752]Epoch 121: 100%|##########| 1/1 [00:00<00:00, 21.39it/s, loss=0.0818, v_num=4, train_loss_step=0.0776, train_loss_epoch=0.0776]Epoch 121:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0818, v_num=4, train_loss_step=0.0776, train_loss_epoch=0.0776]        Epoch 122:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0818, v_num=4, train_loss_step=0.0776, train_loss_epoch=0.0776]Epoch 122: 100%|##########| 1/1 [00:00<00:00, 22.25it/s, loss=0.0818, v_num=4, train_loss_step=0.0776, train_loss_epoch=0.0776]Epoch 122: 100%|##########| 1/1 [00:00<00:00, 22.06it/s, loss=0.081, v_num=4, train_loss_step=0.0714, train_loss_epoch=0.0776] Epoch 122: 100%|##########| 1/1 [00:00<00:00, 21.74it/s, loss=0.081, v_num=4, train_loss_step=0.0714, train_loss_epoch=0.0714]Epoch 122:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.081, v_num=4, train_loss_step=0.0714, train_loss_epoch=0.0714]        Epoch 123:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.081, v_num=4, train_loss_step=0.0714, train_loss_epoch=0.0714]Epoch 123: 100%|##########| 1/1 [00:00<00:00, 23.28it/s, loss=0.081, v_num=4, train_loss_step=0.0714, train_loss_epoch=0.0714]Epoch 123: 100%|##########| 1/1 [00:00<00:00, 23.00it/s, loss=0.0802, v_num=4, train_loss_step=0.0713, train_loss_epoch=0.0714]Epoch 123: 100%|##########| 1/1 [00:00<00:00, 22.70it/s, loss=0.0802, v_num=4, train_loss_step=0.0713, train_loss_epoch=0.0713]Epoch 123:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0802, v_num=4, train_loss_step=0.0713, train_loss_epoch=0.0713]        Epoch 124:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0802, v_num=4, train_loss_step=0.0713, train_loss_epoch=0.0713]Epoch 124: 100%|##########| 1/1 [00:00<00:00, 22.89it/s, loss=0.0802, v_num=4, train_loss_step=0.0713, train_loss_epoch=0.0713]Epoch 124: 100%|##########| 1/1 [00:00<00:00, 22.61it/s, loss=0.0797, v_num=4, train_loss_step=0.0747, train_loss_epoch=0.0713]Epoch 124: 100%|##########| 1/1 [00:00<00:00, 22.32it/s, loss=0.0797, v_num=4, train_loss_step=0.0747, train_loss_epoch=0.0747]Epoch 124:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0797, v_num=4, train_loss_step=0.0747, train_loss_epoch=0.0747]        Epoch 125:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0797, v_num=4, train_loss_step=0.0747, train_loss_epoch=0.0747]Epoch 125: 100%|##########| 1/1 [00:00<00:00, 21.56it/s, loss=0.0797, v_num=4, train_loss_step=0.0747, train_loss_epoch=0.0747]Epoch 125: 100%|##########| 1/1 [00:00<00:00, 21.35it/s, loss=0.0788, v_num=4, train_loss_step=0.069, train_loss_epoch=0.0747] Epoch 125: 100%|##########| 1/1 [00:00<00:00, 21.09it/s, loss=0.0788, v_num=4, train_loss_step=0.069, train_loss_epoch=0.069] Epoch 125:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0788, v_num=4, train_loss_step=0.069, train_loss_epoch=0.069]        Epoch 126:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0788, v_num=4, train_loss_step=0.069, train_loss_epoch=0.069]Epoch 126: 100%|##########| 1/1 [00:00<00:00, 23.84it/s, loss=0.0788, v_num=4, train_loss_step=0.069, train_loss_epoch=0.069]Epoch 126: 100%|##########| 1/1 [00:00<00:00, 23.63it/s, loss=0.0777, v_num=4, train_loss_step=0.0676, train_loss_epoch=0.069]Epoch 126: 100%|##########| 1/1 [00:00<00:00, 23.30it/s, loss=0.0777, v_num=4, train_loss_step=0.0676, train_loss_epoch=0.0676]Epoch 126:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0777, v_num=4, train_loss_step=0.0676, train_loss_epoch=0.0676]        Epoch 127:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0777, v_num=4, train_loss_step=0.0676, train_loss_epoch=0.0676]Epoch 127: 100%|##########| 1/1 [00:00<00:00, 23.31it/s, loss=0.0777, v_num=4, train_loss_step=0.0676, train_loss_epoch=0.0676]Epoch 127: 100%|##########| 1/1 [00:00<00:00, 23.12it/s, loss=0.0767, v_num=4, train_loss_step=0.0693, train_loss_epoch=0.0676]Epoch 127: 100%|##########| 1/1 [00:00<00:00, 22.82it/s, loss=0.0767, v_num=4, train_loss_step=0.0693, train_loss_epoch=0.0693]Epoch 127:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0767, v_num=4, train_loss_step=0.0693, train_loss_epoch=0.0693]        Epoch 128:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0767, v_num=4, train_loss_step=0.0693, train_loss_epoch=0.0693]Epoch 128: 100%|##########| 1/1 [00:00<00:00, 23.07it/s, loss=0.0767, v_num=4, train_loss_step=0.0693, train_loss_epoch=0.0693]Epoch 128: 100%|##########| 1/1 [00:00<00:00, 22.86it/s, loss=0.076, v_num=4, train_loss_step=0.0678, train_loss_epoch=0.0693] Epoch 128: 100%|##########| 1/1 [00:00<00:00, 22.54it/s, loss=0.076, v_num=4, train_loss_step=0.0678, train_loss_epoch=0.0678]Epoch 128:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.076, v_num=4, train_loss_step=0.0678, train_loss_epoch=0.0678]        Epoch 129:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.076, v_num=4, train_loss_step=0.0678, train_loss_epoch=0.0678]Epoch 129: 100%|##########| 1/1 [00:00<00:00, 22.92it/s, loss=0.076, v_num=4, train_loss_step=0.0678, train_loss_epoch=0.0678]Epoch 129: 100%|##########| 1/1 [00:00<00:00, 22.64it/s, loss=0.075, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0678]Epoch 129: 100%|##########| 1/1 [00:00<00:00, 22.33it/s, loss=0.075, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0644]Epoch 129:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.075, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0644]        Epoch 130:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.075, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0644]Epoch 130: 100%|##########| 1/1 [00:00<00:00, 24.11it/s, loss=0.075, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0644]Epoch 130: 100%|##########| 1/1 [00:00<00:00, 23.86it/s, loss=0.0738, v_num=4, train_loss_step=0.0628, train_loss_epoch=0.0644]Epoch 130: 100%|##########| 1/1 [00:00<00:00, 23.54it/s, loss=0.0738, v_num=4, train_loss_step=0.0628, train_loss_epoch=0.0628]Epoch 130:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0738, v_num=4, train_loss_step=0.0628, train_loss_epoch=0.0628]        Epoch 131:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0738, v_num=4, train_loss_step=0.0628, train_loss_epoch=0.0628]Epoch 131: 100%|##########| 1/1 [00:00<00:00, 23.90it/s, loss=0.0738, v_num=4, train_loss_step=0.0628, train_loss_epoch=0.0628]Epoch 131: 100%|##########| 1/1 [00:00<00:00, 23.74it/s, loss=0.073, v_num=4, train_loss_step=0.0663, train_loss_epoch=0.0628] Epoch 131: 100%|##########| 1/1 [00:00<00:00, 23.47it/s, loss=0.073, v_num=4, train_loss_step=0.0663, train_loss_epoch=0.0663]Epoch 131:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.073, v_num=4, train_loss_step=0.0663, train_loss_epoch=0.0663]        Epoch 132:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.073, v_num=4, train_loss_step=0.0663, train_loss_epoch=0.0663]Epoch 132: 100%|##########| 1/1 [00:00<00:00, 24.54it/s, loss=0.073, v_num=4, train_loss_step=0.0663, train_loss_epoch=0.0663]Epoch 132: 100%|##########| 1/1 [00:00<00:00, 24.35it/s, loss=0.0725, v_num=4, train_loss_step=0.0692, train_loss_epoch=0.0663]Epoch 132: 100%|##########| 1/1 [00:00<00:00, 24.06it/s, loss=0.0725, v_num=4, train_loss_step=0.0692, train_loss_epoch=0.0692]Epoch 132:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0725, v_num=4, train_loss_step=0.0692, train_loss_epoch=0.0692]        Epoch 133:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0725, v_num=4, train_loss_step=0.0692, train_loss_epoch=0.0692]Epoch 133: 100%|##########| 1/1 [00:00<00:00, 24.17it/s, loss=0.0725, v_num=4, train_loss_step=0.0692, train_loss_epoch=0.0692]Epoch 133: 100%|##########| 1/1 [00:00<00:00, 23.93it/s, loss=0.0716, v_num=4, train_loss_step=0.0638, train_loss_epoch=0.0692]Epoch 133: 100%|##########| 1/1 [00:00<00:00, 23.62it/s, loss=0.0716, v_num=4, train_loss_step=0.0638, train_loss_epoch=0.0638]Epoch 133:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0716, v_num=4, train_loss_step=0.0638, train_loss_epoch=0.0638]        Epoch 134:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0716, v_num=4, train_loss_step=0.0638, train_loss_epoch=0.0638]Epoch 134: 100%|##########| 1/1 [00:00<00:00, 23.57it/s, loss=0.0716, v_num=4, train_loss_step=0.0638, train_loss_epoch=0.0638]Epoch 134: 100%|##########| 1/1 [00:00<00:00, 23.30it/s, loss=0.0706, v_num=4, train_loss_step=0.0603, train_loss_epoch=0.0638]Epoch 134: 100%|##########| 1/1 [00:00<00:00, 23.02it/s, loss=0.0706, v_num=4, train_loss_step=0.0603, train_loss_epoch=0.0603]Epoch 134:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0706, v_num=4, train_loss_step=0.0603, train_loss_epoch=0.0603]        Epoch 135:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0706, v_num=4, train_loss_step=0.0603, train_loss_epoch=0.0603]Epoch 135: 100%|##########| 1/1 [00:00<00:00, 23.89it/s, loss=0.0706, v_num=4, train_loss_step=0.0603, train_loss_epoch=0.0603]Epoch 135: 100%|##########| 1/1 [00:00<00:00, 23.71it/s, loss=0.0701, v_num=4, train_loss_step=0.0657, train_loss_epoch=0.0603]Epoch 135: 100%|##########| 1/1 [00:00<00:00, 23.43it/s, loss=0.0701, v_num=4, train_loss_step=0.0657, train_loss_epoch=0.0657]Epoch 135:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0701, v_num=4, train_loss_step=0.0657, train_loss_epoch=0.0657]        Epoch 136:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0701, v_num=4, train_loss_step=0.0657, train_loss_epoch=0.0657]Epoch 136: 100%|##########| 1/1 [00:00<00:00, 23.57it/s, loss=0.0701, v_num=4, train_loss_step=0.0657, train_loss_epoch=0.0657]Epoch 136: 100%|##########| 1/1 [00:00<00:00, 23.30it/s, loss=0.0696, v_num=4, train_loss_step=0.0689, train_loss_epoch=0.0657]Epoch 136: 100%|##########| 1/1 [00:00<00:00, 22.99it/s, loss=0.0696, v_num=4, train_loss_step=0.0689, train_loss_epoch=0.0689]Epoch 136:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0696, v_num=4, train_loss_step=0.0689, train_loss_epoch=0.0689]        Epoch 137:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0696, v_num=4, train_loss_step=0.0689, train_loss_epoch=0.0689]Epoch 137: 100%|##########| 1/1 [00:00<00:00, 23.00it/s, loss=0.0696, v_num=4, train_loss_step=0.0689, train_loss_epoch=0.0689]Epoch 137: 100%|##########| 1/1 [00:00<00:00, 22.80it/s, loss=0.0687, v_num=4, train_loss_step=0.0602, train_loss_epoch=0.0689]Epoch 137: 100%|##########| 1/1 [00:00<00:00, 22.45it/s, loss=0.0687, v_num=4, train_loss_step=0.0602, train_loss_epoch=0.0602]Epoch 137:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0687, v_num=4, train_loss_step=0.0602, train_loss_epoch=0.0602]        Epoch 138:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0687, v_num=4, train_loss_step=0.0602, train_loss_epoch=0.0602]Epoch 138: 100%|##########| 1/1 [00:00<00:00, 22.87it/s, loss=0.0687, v_num=4, train_loss_step=0.0602, train_loss_epoch=0.0602]Epoch 138: 100%|##########| 1/1 [00:00<00:00, 22.62it/s, loss=0.0679, v_num=4, train_loss_step=0.0598, train_loss_epoch=0.0602]Epoch 138: 100%|##########| 1/1 [00:00<00:00, 22.32it/s, loss=0.0679, v_num=4, train_loss_step=0.0598, train_loss_epoch=0.0598]Epoch 138:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0679, v_num=4, train_loss_step=0.0598, train_loss_epoch=0.0598]        Epoch 139:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0679, v_num=4, train_loss_step=0.0598, train_loss_epoch=0.0598]Epoch 139: 100%|##########| 1/1 [00:00<00:00, 22.92it/s, loss=0.0679, v_num=4, train_loss_step=0.0598, train_loss_epoch=0.0598]Epoch 139: 100%|##########| 1/1 [00:00<00:00, 22.72it/s, loss=0.0675, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0598]Epoch 139: 100%|##########| 1/1 [00:00<00:00, 22.41it/s, loss=0.0675, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0644]Epoch 139:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0675, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0644]        Epoch 140:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0675, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0644]Epoch 140: 100%|##########| 1/1 [00:00<00:00, 22.10it/s, loss=0.0675, v_num=4, train_loss_step=0.0644, train_loss_epoch=0.0644]Epoch 140: 100%|##########| 1/1 [00:00<00:00, 21.85it/s, loss=0.0666, v_num=4, train_loss_step=0.0582, train_loss_epoch=0.0644]Epoch 140: 100%|##########| 1/1 [00:00<00:00, 21.54it/s, loss=0.0666, v_num=4, train_loss_step=0.0582, train_loss_epoch=0.0582]Epoch 140:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0666, v_num=4, train_loss_step=0.0582, train_loss_epoch=0.0582]        Epoch 141:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0666, v_num=4, train_loss_step=0.0582, train_loss_epoch=0.0582]Epoch 141: 100%|##########| 1/1 [00:00<00:00, 22.23it/s, loss=0.0666, v_num=4, train_loss_step=0.0582, train_loss_epoch=0.0582]Epoch 141: 100%|##########| 1/1 [00:00<00:00, 22.05it/s, loss=0.0657, v_num=4, train_loss_step=0.0579, train_loss_epoch=0.0582]Epoch 141: 100%|##########| 1/1 [00:00<00:00, 21.75it/s, loss=0.0657, v_num=4, train_loss_step=0.0579, train_loss_epoch=0.0579]Epoch 141:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0657, v_num=4, train_loss_step=0.0579, train_loss_epoch=0.0579]        Epoch 142:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0657, v_num=4, train_loss_step=0.0579, train_loss_epoch=0.0579]Epoch 142: 100%|##########| 1/1 [00:00<00:00, 23.05it/s, loss=0.0657, v_num=4, train_loss_step=0.0579, train_loss_epoch=0.0579]Epoch 142: 100%|##########| 1/1 [00:00<00:00, 22.79it/s, loss=0.065, v_num=4, train_loss_step=0.059, train_loss_epoch=0.0579]  Epoch 142: 100%|##########| 1/1 [00:00<00:00, 22.49it/s, loss=0.065, v_num=4, train_loss_step=0.059, train_loss_epoch=0.059] Epoch 142:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.065, v_num=4, train_loss_step=0.059, train_loss_epoch=0.059]        Epoch 143:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.065, v_num=4, train_loss_step=0.059, train_loss_epoch=0.059]Epoch 143: 100%|##########| 1/1 [00:00<00:00, 21.65it/s, loss=0.065, v_num=4, train_loss_step=0.059, train_loss_epoch=0.059]Epoch 143: 100%|##########| 1/1 [00:00<00:00, 21.47it/s, loss=0.0643, v_num=4, train_loss_step=0.0559, train_loss_epoch=0.059]Epoch 143: 100%|##########| 1/1 [00:00<00:00, 21.19it/s, loss=0.0643, v_num=4, train_loss_step=0.0559, train_loss_epoch=0.0559]Epoch 143:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0643, v_num=4, train_loss_step=0.0559, train_loss_epoch=0.0559]        Epoch 144:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0643, v_num=4, train_loss_step=0.0559, train_loss_epoch=0.0559]Epoch 144: 100%|##########| 1/1 [00:00<00:00, 22.75it/s, loss=0.0643, v_num=4, train_loss_step=0.0559, train_loss_epoch=0.0559]Epoch 144: 100%|##########| 1/1 [00:00<00:00, 22.49it/s, loss=0.0632, v_num=4, train_loss_step=0.0539, train_loss_epoch=0.0559]Epoch 144: 100%|##########| 1/1 [00:00<00:00, 22.19it/s, loss=0.0632, v_num=4, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 144:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0632, v_num=4, train_loss_step=0.0539, train_loss_epoch=0.0539]        Epoch 145:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0632, v_num=4, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 145: 100%|##########| 1/1 [00:00<00:00, 23.78it/s, loss=0.0632, v_num=4, train_loss_step=0.0539, train_loss_epoch=0.0539]Epoch 145: 100%|##########| 1/1 [00:00<00:00, 23.59it/s, loss=0.0627, v_num=4, train_loss_step=0.0581, train_loss_epoch=0.0539]Epoch 145: 100%|##########| 1/1 [00:00<00:00, 23.28it/s, loss=0.0627, v_num=4, train_loss_step=0.0581, train_loss_epoch=0.0581]Epoch 145:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0627, v_num=4, train_loss_step=0.0581, train_loss_epoch=0.0581]        Epoch 146:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0627, v_num=4, train_loss_step=0.0581, train_loss_epoch=0.0581]Epoch 146: 100%|##########| 1/1 [00:00<00:00, 24.47it/s, loss=0.0627, v_num=4, train_loss_step=0.0581, train_loss_epoch=0.0581]Epoch 146: 100%|##########| 1/1 [00:00<00:00, 24.18it/s, loss=0.0622, v_num=4, train_loss_step=0.0583, train_loss_epoch=0.0581]Epoch 146: 100%|##########| 1/1 [00:00<00:00, 23.85it/s, loss=0.0622, v_num=4, train_loss_step=0.0583, train_loss_epoch=0.0583]Epoch 146:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0622, v_num=4, train_loss_step=0.0583, train_loss_epoch=0.0583]        Epoch 147:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0622, v_num=4, train_loss_step=0.0583, train_loss_epoch=0.0583]Epoch 147: 100%|##########| 1/1 [00:00<00:00, 23.25it/s, loss=0.0622, v_num=4, train_loss_step=0.0583, train_loss_epoch=0.0583]Epoch 147: 100%|##########| 1/1 [00:00<00:00, 23.03it/s, loss=0.0614, v_num=4, train_loss_step=0.0533, train_loss_epoch=0.0583]Epoch 147: 100%|##########| 1/1 [00:00<00:00, 22.71it/s, loss=0.0614, v_num=4, train_loss_step=0.0533, train_loss_epoch=0.0533]Epoch 147:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0614, v_num=4, train_loss_step=0.0533, train_loss_epoch=0.0533]        Epoch 148:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0614, v_num=4, train_loss_step=0.0533, train_loss_epoch=0.0533]Epoch 148: 100%|##########| 1/1 [00:00<00:00, 22.69it/s, loss=0.0614, v_num=4, train_loss_step=0.0533, train_loss_epoch=0.0533]Epoch 148: 100%|##########| 1/1 [00:00<00:00, 22.46it/s, loss=0.0607, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0533]Epoch 148: 100%|##########| 1/1 [00:00<00:00, 22.17it/s, loss=0.0607, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0527]Epoch 148:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0607, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0527]        Epoch 149:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0607, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0527]Epoch 149: 100%|##########| 1/1 [00:00<00:00, 22.55it/s, loss=0.0607, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0527]Epoch 149: 100%|##########| 1/1 [00:00<00:00, 22.35it/s, loss=0.0601, v_num=4, train_loss_step=0.0528, train_loss_epoch=0.0527]Epoch 149: 100%|##########| 1/1 [00:00<00:00, 21.79it/s, loss=0.0601, v_num=4, train_loss_step=0.0528, train_loss_epoch=0.0528]Epoch 149:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0601, v_num=4, train_loss_step=0.0528, train_loss_epoch=0.0528]        Epoch 150:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0601, v_num=4, train_loss_step=0.0528, train_loss_epoch=0.0528]Epoch 150: 100%|##########| 1/1 [00:00<00:00, 23.13it/s, loss=0.0601, v_num=4, train_loss_step=0.0528, train_loss_epoch=0.0528]Epoch 150: 100%|##########| 1/1 [00:00<00:00, 22.84it/s, loss=0.0597, v_num=4, train_loss_step=0.0549, train_loss_epoch=0.0528]Epoch 150: 100%|##########| 1/1 [00:00<00:00, 22.52it/s, loss=0.0597, v_num=4, train_loss_step=0.0549, train_loss_epoch=0.0549]Epoch 150:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0597, v_num=4, train_loss_step=0.0549, train_loss_epoch=0.0549]        Epoch 151:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0597, v_num=4, train_loss_step=0.0549, train_loss_epoch=0.0549]Epoch 151: 100%|##########| 1/1 [00:00<00:00, 23.14it/s, loss=0.0597, v_num=4, train_loss_step=0.0549, train_loss_epoch=0.0549]Epoch 151: 100%|##########| 1/1 [00:00<00:00, 22.95it/s, loss=0.059, v_num=4, train_loss_step=0.0521, train_loss_epoch=0.0549] Epoch 151: 100%|##########| 1/1 [00:00<00:00, 22.65it/s, loss=0.059, v_num=4, train_loss_step=0.0521, train_loss_epoch=0.0521]Epoch 151:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.059, v_num=4, train_loss_step=0.0521, train_loss_epoch=0.0521]        Epoch 152:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.059, v_num=4, train_loss_step=0.0521, train_loss_epoch=0.0521]Epoch 152: 100%|##########| 1/1 [00:00<00:00, 23.35it/s, loss=0.059, v_num=4, train_loss_step=0.0521, train_loss_epoch=0.0521]Epoch 152: 100%|##########| 1/1 [00:00<00:00, 23.07it/s, loss=0.058, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0521]Epoch 152: 100%|##########| 1/1 [00:00<00:00, 22.79it/s, loss=0.058, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0495]Epoch 152:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.058, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0495]        Epoch 153:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.058, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0495]Epoch 153: 100%|##########| 1/1 [00:00<00:00, 22.35it/s, loss=0.058, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0495]Epoch 153: 100%|##########| 1/1 [00:00<00:00, 22.15it/s, loss=0.0572, v_num=4, train_loss_step=0.0487, train_loss_epoch=0.0495]Epoch 153: 100%|##########| 1/1 [00:00<00:00, 21.87it/s, loss=0.0572, v_num=4, train_loss_step=0.0487, train_loss_epoch=0.0487]Epoch 153:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0572, v_num=4, train_loss_step=0.0487, train_loss_epoch=0.0487]        Epoch 154:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0572, v_num=4, train_loss_step=0.0487, train_loss_epoch=0.0487]Epoch 154: 100%|##########| 1/1 [00:00<00:00, 22.80it/s, loss=0.0572, v_num=4, train_loss_step=0.0487, train_loss_epoch=0.0487]Epoch 154: 100%|##########| 1/1 [00:00<00:00, 22.60it/s, loss=0.0566, v_num=4, train_loss_step=0.047, train_loss_epoch=0.0487] Epoch 154: 100%|##########| 1/1 [00:00<00:00, 22.31it/s, loss=0.0566, v_num=4, train_loss_step=0.047, train_loss_epoch=0.047] Epoch 154:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0566, v_num=4, train_loss_step=0.047, train_loss_epoch=0.047]        Epoch 155:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0566, v_num=4, train_loss_step=0.047, train_loss_epoch=0.047]Epoch 155: 100%|##########| 1/1 [00:00<00:00, 22.72it/s, loss=0.0566, v_num=4, train_loss_step=0.047, train_loss_epoch=0.047]Epoch 155: 100%|##########| 1/1 [00:00<00:00, 22.48it/s, loss=0.0556, v_num=4, train_loss_step=0.0463, train_loss_epoch=0.047]Epoch 155: 100%|##########| 1/1 [00:00<00:00, 22.19it/s, loss=0.0556, v_num=4, train_loss_step=0.0463, train_loss_epoch=0.0463]Epoch 155:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0556, v_num=4, train_loss_step=0.0463, train_loss_epoch=0.0463]        Epoch 156:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0556, v_num=4, train_loss_step=0.0463, train_loss_epoch=0.0463]Epoch 156: 100%|##########| 1/1 [00:00<00:00, 23.05it/s, loss=0.0556, v_num=4, train_loss_step=0.0463, train_loss_epoch=0.0463]Epoch 156: 100%|##########| 1/1 [00:00<00:00, 22.81it/s, loss=0.0545, v_num=4, train_loss_step=0.0468, train_loss_epoch=0.0463]Epoch 156: 100%|##########| 1/1 [00:00<00:00, 22.49it/s, loss=0.0545, v_num=4, train_loss_step=0.0468, train_loss_epoch=0.0468]Epoch 156:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0545, v_num=4, train_loss_step=0.0468, train_loss_epoch=0.0468]        Epoch 157:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0545, v_num=4, train_loss_step=0.0468, train_loss_epoch=0.0468]Epoch 157: 100%|##########| 1/1 [00:00<00:00, 23.27it/s, loss=0.0545, v_num=4, train_loss_step=0.0468, train_loss_epoch=0.0468]Epoch 157: 100%|##########| 1/1 [00:00<00:00, 23.02it/s, loss=0.054, v_num=4, train_loss_step=0.0507, train_loss_epoch=0.0468] Epoch 157: 100%|##########| 1/1 [00:00<00:00, 22.72it/s, loss=0.054, v_num=4, train_loss_step=0.0507, train_loss_epoch=0.0507]Epoch 157:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.054, v_num=4, train_loss_step=0.0507, train_loss_epoch=0.0507]        Epoch 158:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.054, v_num=4, train_loss_step=0.0507, train_loss_epoch=0.0507]Epoch 158: 100%|##########| 1/1 [00:00<00:00, 21.74it/s, loss=0.054, v_num=4, train_loss_step=0.0507, train_loss_epoch=0.0507]Epoch 158: 100%|##########| 1/1 [00:00<00:00, 21.51it/s, loss=0.0537, v_num=4, train_loss_step=0.0534, train_loss_epoch=0.0507]Epoch 158: 100%|##########| 1/1 [00:00<00:00, 21.26it/s, loss=0.0537, v_num=4, train_loss_step=0.0534, train_loss_epoch=0.0534]Epoch 158:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0537, v_num=4, train_loss_step=0.0534, train_loss_epoch=0.0534]        Epoch 159:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0537, v_num=4, train_loss_step=0.0534, train_loss_epoch=0.0534]Epoch 159: 100%|##########| 1/1 [00:00<00:00, 23.04it/s, loss=0.0537, v_num=4, train_loss_step=0.0534, train_loss_epoch=0.0534]Epoch 159: 100%|##########| 1/1 [00:00<00:00, 22.75it/s, loss=0.053, v_num=4, train_loss_step=0.0511, train_loss_epoch=0.0534] Epoch 159: 100%|##########| 1/1 [00:00<00:00, 22.45it/s, loss=0.053, v_num=4, train_loss_step=0.0511, train_loss_epoch=0.0511]Epoch 159:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.053, v_num=4, train_loss_step=0.0511, train_loss_epoch=0.0511]        Epoch 160:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.053, v_num=4, train_loss_step=0.0511, train_loss_epoch=0.0511]Epoch 160: 100%|##########| 1/1 [00:00<00:00, 22.53it/s, loss=0.053, v_num=4, train_loss_step=0.0511, train_loss_epoch=0.0511]Epoch 160: 100%|##########| 1/1 [00:00<00:00, 22.33it/s, loss=0.0524, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0511]Epoch 160: 100%|##########| 1/1 [00:00<00:00, 22.06it/s, loss=0.0524, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0457]Epoch 160:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0524, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0457]        Epoch 161:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0524, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0457]Epoch 161: 100%|##########| 1/1 [00:00<00:00, 23.63it/s, loss=0.0524, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0457]Epoch 161: 100%|##########| 1/1 [00:00<00:00, 23.44it/s, loss=0.0517, v_num=4, train_loss_step=0.0441, train_loss_epoch=0.0457]Epoch 161: 100%|##########| 1/1 [00:00<00:00, 23.15it/s, loss=0.0517, v_num=4, train_loss_step=0.0441, train_loss_epoch=0.0441]Epoch 161:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0517, v_num=4, train_loss_step=0.0441, train_loss_epoch=0.0441]        Epoch 162:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0517, v_num=4, train_loss_step=0.0441, train_loss_epoch=0.0441]Epoch 162: 100%|##########| 1/1 [00:00<00:00, 23.49it/s, loss=0.0517, v_num=4, train_loss_step=0.0441, train_loss_epoch=0.0441]Epoch 162: 100%|##########| 1/1 [00:00<00:00, 23.31it/s, loss=0.0509, v_num=4, train_loss_step=0.0437, train_loss_epoch=0.0441]Epoch 162: 100%|##########| 1/1 [00:00<00:00, 23.04it/s, loss=0.0509, v_num=4, train_loss_step=0.0437, train_loss_epoch=0.0437]Epoch 162:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0509, v_num=4, train_loss_step=0.0437, train_loss_epoch=0.0437]        Epoch 163:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0509, v_num=4, train_loss_step=0.0437, train_loss_epoch=0.0437]Epoch 163: 100%|##########| 1/1 [00:00<00:00, 23.44it/s, loss=0.0509, v_num=4, train_loss_step=0.0437, train_loss_epoch=0.0437]Epoch 163: 100%|##########| 1/1 [00:00<00:00, 23.20it/s, loss=0.0505, v_num=4, train_loss_step=0.0471, train_loss_epoch=0.0437]Epoch 163: 100%|##########| 1/1 [00:00<00:00, 22.87it/s, loss=0.0505, v_num=4, train_loss_step=0.0471, train_loss_epoch=0.0471]Epoch 163:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0505, v_num=4, train_loss_step=0.0471, train_loss_epoch=0.0471]        Epoch 164:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0505, v_num=4, train_loss_step=0.0471, train_loss_epoch=0.0471]Epoch 164: 100%|##########| 1/1 [00:00<00:00, 23.85it/s, loss=0.0505, v_num=4, train_loss_step=0.0471, train_loss_epoch=0.0471]Epoch 164: 100%|##########| 1/1 [00:00<00:00, 23.57it/s, loss=0.0503, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0471]Epoch 164: 100%|##########| 1/1 [00:00<00:00, 23.24it/s, loss=0.0503, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0502]Epoch 164:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0503, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0502]        Epoch 165:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0503, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0502]Epoch 165: 100%|##########| 1/1 [00:00<00:00, 24.03it/s, loss=0.0503, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0502]Epoch 165: 100%|##########| 1/1 [00:00<00:00, 23.85it/s, loss=0.0498, v_num=4, train_loss_step=0.0484, train_loss_epoch=0.0502]Epoch 165: 100%|##########| 1/1 [00:00<00:00, 23.56it/s, loss=0.0498, v_num=4, train_loss_step=0.0484, train_loss_epoch=0.0484]Epoch 165:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0498, v_num=4, train_loss_step=0.0484, train_loss_epoch=0.0484]        Epoch 166:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0498, v_num=4, train_loss_step=0.0484, train_loss_epoch=0.0484]Epoch 166: 100%|##########| 1/1 [00:00<00:00, 24.75it/s, loss=0.0498, v_num=4, train_loss_step=0.0484, train_loss_epoch=0.0484]Epoch 166: 100%|##########| 1/1 [00:00<00:00, 24.45it/s, loss=0.0491, v_num=4, train_loss_step=0.0432, train_loss_epoch=0.0484]Epoch 166: 100%|##########| 1/1 [00:00<00:00, 24.15it/s, loss=0.0491, v_num=4, train_loss_step=0.0432, train_loss_epoch=0.0432]Epoch 166:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0491, v_num=4, train_loss_step=0.0432, train_loss_epoch=0.0432]        Epoch 167:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0491, v_num=4, train_loss_step=0.0432, train_loss_epoch=0.0432]Epoch 167: 100%|##########| 1/1 [00:00<00:00, 24.31it/s, loss=0.0491, v_num=4, train_loss_step=0.0432, train_loss_epoch=0.0432]Epoch 167: 100%|##########| 1/1 [00:00<00:00, 24.10it/s, loss=0.0485, v_num=4, train_loss_step=0.0417, train_loss_epoch=0.0432]Epoch 167: 100%|##########| 1/1 [00:00<00:00, 23.75it/s, loss=0.0485, v_num=4, train_loss_step=0.0417, train_loss_epoch=0.0417]Epoch 167:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0485, v_num=4, train_loss_step=0.0417, train_loss_epoch=0.0417]        Epoch 168:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0485, v_num=4, train_loss_step=0.0417, train_loss_epoch=0.0417]Epoch 168: 100%|##########| 1/1 [00:00<00:00, 23.13it/s, loss=0.0485, v_num=4, train_loss_step=0.0417, train_loss_epoch=0.0417]Epoch 168: 100%|##########| 1/1 [00:00<00:00, 22.93it/s, loss=0.0484, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0417]Epoch 168: 100%|##########| 1/1 [00:00<00:00, 22.62it/s, loss=0.0484, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0502]Epoch 168:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0484, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0502]        Epoch 169:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0484, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0502]Epoch 169: 100%|##########| 1/1 [00:00<00:00, 22.95it/s, loss=0.0484, v_num=4, train_loss_step=0.0502, train_loss_epoch=0.0502]Epoch 169: 100%|##########| 1/1 [00:00<00:00, 22.70it/s, loss=0.0483, v_num=4, train_loss_step=0.0522, train_loss_epoch=0.0502]Epoch 169: 100%|##########| 1/1 [00:00<00:00, 22.38it/s, loss=0.0483, v_num=4, train_loss_step=0.0522, train_loss_epoch=0.0522]Epoch 169:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0483, v_num=4, train_loss_step=0.0522, train_loss_epoch=0.0522]        Epoch 170:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0483, v_num=4, train_loss_step=0.0522, train_loss_epoch=0.0522]Epoch 170: 100%|##########| 1/1 [00:00<00:00, 22.87it/s, loss=0.0483, v_num=4, train_loss_step=0.0522, train_loss_epoch=0.0522]Epoch 170: 100%|##########| 1/1 [00:00<00:00, 22.54it/s, loss=0.0477, v_num=4, train_loss_step=0.0424, train_loss_epoch=0.0522]Epoch 170: 100%|##########| 1/1 [00:00<00:00, 22.22it/s, loss=0.0477, v_num=4, train_loss_step=0.0424, train_loss_epoch=0.0424]Epoch 170:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0477, v_num=4, train_loss_step=0.0424, train_loss_epoch=0.0424]        Epoch 171:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0477, v_num=4, train_loss_step=0.0424, train_loss_epoch=0.0424]Epoch 171: 100%|##########| 1/1 [00:00<00:00, 22.51it/s, loss=0.0477, v_num=4, train_loss_step=0.0424, train_loss_epoch=0.0424]Epoch 171: 100%|##########| 1/1 [00:00<00:00, 22.27it/s, loss=0.0476, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0424]Epoch 171: 100%|##########| 1/1 [00:00<00:00, 21.98it/s, loss=0.0476, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0495]Epoch 171:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0476, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0495]        Epoch 172:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0476, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0495]Epoch 172: 100%|##########| 1/1 [00:00<00:00, 23.44it/s, loss=0.0476, v_num=4, train_loss_step=0.0495, train_loss_epoch=0.0495]Epoch 172: 100%|##########| 1/1 [00:00<00:00, 23.21it/s, loss=0.0478, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0495]Epoch 172: 100%|##########| 1/1 [00:00<00:00, 22.94it/s, loss=0.0478, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0527]Epoch 172:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0478, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0527]        Epoch 173:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0478, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0527]Epoch 173: 100%|##########| 1/1 [00:00<00:00, 23.52it/s, loss=0.0478, v_num=4, train_loss_step=0.0527, train_loss_epoch=0.0527]Epoch 173: 100%|##########| 1/1 [00:00<00:00, 23.33it/s, loss=0.0475, v_num=4, train_loss_step=0.043, train_loss_epoch=0.0527] Epoch 173: 100%|##########| 1/1 [00:00<00:00, 23.01it/s, loss=0.0475, v_num=4, train_loss_step=0.043, train_loss_epoch=0.043] Epoch 173:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0475, v_num=4, train_loss_step=0.043, train_loss_epoch=0.043]        Epoch 174:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0475, v_num=4, train_loss_step=0.043, train_loss_epoch=0.043]Epoch 174: 100%|##########| 1/1 [00:00<00:00, 22.48it/s, loss=0.0475, v_num=4, train_loss_step=0.043, train_loss_epoch=0.043]Epoch 174: 100%|##########| 1/1 [00:00<00:00, 22.29it/s, loss=0.048, v_num=4, train_loss_step=0.0578, train_loss_epoch=0.043]Epoch 174: 100%|##########| 1/1 [00:00<00:00, 22.01it/s, loss=0.048, v_num=4, train_loss_step=0.0578, train_loss_epoch=0.0578]Epoch 174:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.048, v_num=4, train_loss_step=0.0578, train_loss_epoch=0.0578]        Epoch 175:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.048, v_num=4, train_loss_step=0.0578, train_loss_epoch=0.0578]Epoch 175: 100%|##########| 1/1 [00:00<00:00, 21.50it/s, loss=0.048, v_num=4, train_loss_step=0.0578, train_loss_epoch=0.0578]Epoch 175: 100%|##########| 1/1 [00:00<00:00, 21.34it/s, loss=0.0478, v_num=4, train_loss_step=0.0428, train_loss_epoch=0.0578]Epoch 175: 100%|##########| 1/1 [00:00<00:00, 21.08it/s, loss=0.0478, v_num=4, train_loss_step=0.0428, train_loss_epoch=0.0428]Epoch 175:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0478, v_num=4, train_loss_step=0.0428, train_loss_epoch=0.0428]        Epoch 176:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0478, v_num=4, train_loss_step=0.0428, train_loss_epoch=0.0428]Epoch 176: 100%|##########| 1/1 [00:00<00:00, 21.83it/s, loss=0.0478, v_num=4, train_loss_step=0.0428, train_loss_epoch=0.0428]Epoch 176: 100%|##########| 1/1 [00:00<00:00, 21.56it/s, loss=0.0478, v_num=4, train_loss_step=0.0469, train_loss_epoch=0.0428]Epoch 176: 100%|##########| 1/1 [00:00<00:00, 21.29it/s, loss=0.0478, v_num=4, train_loss_step=0.0469, train_loss_epoch=0.0469]Epoch 176:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0478, v_num=4, train_loss_step=0.0469, train_loss_epoch=0.0469]        Epoch 177:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0478, v_num=4, train_loss_step=0.0469, train_loss_epoch=0.0469]Epoch 177: 100%|##########| 1/1 [00:00<00:00, 23.73it/s, loss=0.0478, v_num=4, train_loss_step=0.0469, train_loss_epoch=0.0469]Epoch 177: 100%|##########| 1/1 [00:00<00:00, 23.47it/s, loss=0.0476, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0469]Epoch 177: 100%|##########| 1/1 [00:00<00:00, 23.19it/s, loss=0.0476, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0457]Epoch 177:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0476, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0457]        Epoch 178:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0476, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0457]Epoch 178: 100%|##########| 1/1 [00:00<00:00, 23.70it/s, loss=0.0476, v_num=4, train_loss_step=0.0457, train_loss_epoch=0.0457]Epoch 178: 100%|##########| 1/1 [00:00<00:00, 23.40it/s, loss=0.0469, v_num=4, train_loss_step=0.0403, train_loss_epoch=0.0457]Epoch 178: 100%|##########| 1/1 [00:00<00:00, 23.03it/s, loss=0.0469, v_num=4, train_loss_step=0.0403, train_loss_epoch=0.0403]Epoch 178:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0469, v_num=4, train_loss_step=0.0403, train_loss_epoch=0.0403]        Epoch 179:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0469, v_num=4, train_loss_step=0.0403, train_loss_epoch=0.0403]Epoch 179: 100%|##########| 1/1 [00:00<00:00, 23.56it/s, loss=0.0469, v_num=4, train_loss_step=0.0403, train_loss_epoch=0.0403]Epoch 179: 100%|##########| 1/1 [00:00<00:00, 23.31it/s, loss=0.0465, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0403]Epoch 179: 100%|##########| 1/1 [00:00<00:00, 22.98it/s, loss=0.0465, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0426]Epoch 179:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0465, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0426]        Epoch 180:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0465, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0426]Epoch 180: 100%|##########| 1/1 [00:00<00:00, 23.31it/s, loss=0.0465, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0426]Epoch 180: 100%|##########| 1/1 [00:00<00:00, 23.11it/s, loss=0.0464, v_num=4, train_loss_step=0.0435, train_loss_epoch=0.0426]Epoch 180: 100%|##########| 1/1 [00:00<00:00, 22.81it/s, loss=0.0464, v_num=4, train_loss_step=0.0435, train_loss_epoch=0.0435]Epoch 180:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0464, v_num=4, train_loss_step=0.0435, train_loss_epoch=0.0435]        Epoch 181:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0464, v_num=4, train_loss_step=0.0435, train_loss_epoch=0.0435]Epoch 181: 100%|##########| 1/1 [00:00<00:00, 22.87it/s, loss=0.0464, v_num=4, train_loss_step=0.0435, train_loss_epoch=0.0435]Epoch 181: 100%|##########| 1/1 [00:00<00:00, 22.67it/s, loss=0.0461, v_num=4, train_loss_step=0.0382, train_loss_epoch=0.0435]Epoch 181: 100%|##########| 1/1 [00:00<00:00, 22.34it/s, loss=0.0461, v_num=4, train_loss_step=0.0382, train_loss_epoch=0.0382]Epoch 181:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0461, v_num=4, train_loss_step=0.0382, train_loss_epoch=0.0382]        Epoch 182:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0461, v_num=4, train_loss_step=0.0382, train_loss_epoch=0.0382]Epoch 182: 100%|##########| 1/1 [00:00<00:00, 23.94it/s, loss=0.0461, v_num=4, train_loss_step=0.0382, train_loss_epoch=0.0382]Epoch 182: 100%|##########| 1/1 [00:00<00:00, 23.74it/s, loss=0.0462, v_num=4, train_loss_step=0.0449, train_loss_epoch=0.0382]Epoch 182: 100%|##########| 1/1 [00:00<00:00, 23.41it/s, loss=0.0462, v_num=4, train_loss_step=0.0449, train_loss_epoch=0.0449]Epoch 182:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0462, v_num=4, train_loss_step=0.0449, train_loss_epoch=0.0449]        Epoch 183:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0462, v_num=4, train_loss_step=0.0449, train_loss_epoch=0.0449]Epoch 183: 100%|##########| 1/1 [00:00<00:00, 23.11it/s, loss=0.0462, v_num=4, train_loss_step=0.0449, train_loss_epoch=0.0449]Epoch 183: 100%|##########| 1/1 [00:00<00:00, 22.90it/s, loss=0.0458, v_num=4, train_loss_step=0.0406, train_loss_epoch=0.0449]Epoch 183: 100%|##########| 1/1 [00:00<00:00, 22.57it/s, loss=0.0458, v_num=4, train_loss_step=0.0406, train_loss_epoch=0.0406]Epoch 183:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0458, v_num=4, train_loss_step=0.0406, train_loss_epoch=0.0406]        Epoch 184:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0458, v_num=4, train_loss_step=0.0406, train_loss_epoch=0.0406]Epoch 184: 100%|##########| 1/1 [00:00<00:00, 22.42it/s, loss=0.0458, v_num=4, train_loss_step=0.0406, train_loss_epoch=0.0406]Epoch 184: 100%|##########| 1/1 [00:00<00:00, 22.22it/s, loss=0.0453, v_num=4, train_loss_step=0.0397, train_loss_epoch=0.0406]Epoch 184: 100%|##########| 1/1 [00:00<00:00, 21.90it/s, loss=0.0453, v_num=4, train_loss_step=0.0397, train_loss_epoch=0.0397]Epoch 184:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0453, v_num=4, train_loss_step=0.0397, train_loss_epoch=0.0397]        Epoch 185:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0453, v_num=4, train_loss_step=0.0397, train_loss_epoch=0.0397]Epoch 185: 100%|##########| 1/1 [00:00<00:00, 22.72it/s, loss=0.0453, v_num=4, train_loss_step=0.0397, train_loss_epoch=0.0397]Epoch 185: 100%|##########| 1/1 [00:00<00:00, 22.54it/s, loss=0.0448, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.0397]Epoch 185: 100%|##########| 1/1 [00:00<00:00, 22.23it/s, loss=0.0448, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.0388]Epoch 185:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0448, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.0388]        Epoch 186:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0448, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.0388]Epoch 186: 100%|##########| 1/1 [00:00<00:00, 24.21it/s, loss=0.0448, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.0388]Epoch 186: 100%|##########| 1/1 [00:00<00:00, 24.01it/s, loss=0.0447, v_num=4, train_loss_step=0.0411, train_loss_epoch=0.0388]Epoch 186: 100%|##########| 1/1 [00:00<00:00, 23.69it/s, loss=0.0447, v_num=4, train_loss_step=0.0411, train_loss_epoch=0.0411]Epoch 186:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0447, v_num=4, train_loss_step=0.0411, train_loss_epoch=0.0411]        Epoch 187:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0447, v_num=4, train_loss_step=0.0411, train_loss_epoch=0.0411]Epoch 187: 100%|##########| 1/1 [00:00<00:00, 23.87it/s, loss=0.0447, v_num=4, train_loss_step=0.0411, train_loss_epoch=0.0411]Epoch 187: 100%|##########| 1/1 [00:00<00:00, 23.71it/s, loss=0.0445, v_num=4, train_loss_step=0.0381, train_loss_epoch=0.0411]Epoch 187: 100%|##########| 1/1 [00:00<00:00, 23.42it/s, loss=0.0445, v_num=4, train_loss_step=0.0381, train_loss_epoch=0.0381]Epoch 187:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0445, v_num=4, train_loss_step=0.0381, train_loss_epoch=0.0381]        Epoch 188:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0445, v_num=4, train_loss_step=0.0381, train_loss_epoch=0.0381]Epoch 188: 100%|##########| 1/1 [00:00<00:00, 14.92it/s, loss=0.0445, v_num=4, train_loss_step=0.0381, train_loss_epoch=0.0381]Epoch 188: 100%|##########| 1/1 [00:00<00:00, 14.78it/s, loss=0.0442, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0381]Epoch 188: 100%|##########| 1/1 [00:00<00:00, 14.65it/s, loss=0.0442, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0426]Epoch 188:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0442, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0426]        Epoch 189:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0442, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0426]Epoch 189: 100%|##########| 1/1 [00:00<00:00, 23.25it/s, loss=0.0442, v_num=4, train_loss_step=0.0426, train_loss_epoch=0.0426]Epoch 189: 100%|##########| 1/1 [00:00<00:00, 22.95it/s, loss=0.0434, v_num=4, train_loss_step=0.0365, train_loss_epoch=0.0426]Epoch 189: 100%|##########| 1/1 [00:00<00:00, 22.63it/s, loss=0.0434, v_num=4, train_loss_step=0.0365, train_loss_epoch=0.0365]Epoch 189:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0434, v_num=4, train_loss_step=0.0365, train_loss_epoch=0.0365]        Epoch 190:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0434, v_num=4, train_loss_step=0.0365, train_loss_epoch=0.0365]Epoch 190: 100%|##########| 1/1 [00:00<00:00, 17.00it/s, loss=0.0434, v_num=4, train_loss_step=0.0365, train_loss_epoch=0.0365]Epoch 190: 100%|##########| 1/1 [00:00<00:00, 16.88it/s, loss=0.0431, v_num=4, train_loss_step=0.0366, train_loss_epoch=0.0365]Epoch 190: 100%|##########| 1/1 [00:00<00:00, 16.67it/s, loss=0.0431, v_num=4, train_loss_step=0.0366, train_loss_epoch=0.0366]Epoch 190:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0431, v_num=4, train_loss_step=0.0366, train_loss_epoch=0.0366]        Epoch 191:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0431, v_num=4, train_loss_step=0.0366, train_loss_epoch=0.0366]Epoch 191: 100%|##########| 1/1 [00:00<00:00, 17.95it/s, loss=0.0431, v_num=4, train_loss_step=0.0366, train_loss_epoch=0.0366]Epoch 191: 100%|##########| 1/1 [00:00<00:00, 17.73it/s, loss=0.0425, v_num=4, train_loss_step=0.0371, train_loss_epoch=0.0366]Epoch 191: 100%|##########| 1/1 [00:00<00:00, 17.51it/s, loss=0.0425, v_num=4, train_loss_step=0.0371, train_loss_epoch=0.0371]Epoch 191:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0425, v_num=4, train_loss_step=0.0371, train_loss_epoch=0.0371]        Epoch 192:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0425, v_num=4, train_loss_step=0.0371, train_loss_epoch=0.0371]Epoch 192: 100%|##########| 1/1 [00:00<00:00, 21.22it/s, loss=0.0425, v_num=4, train_loss_step=0.0371, train_loss_epoch=0.0371]Epoch 192: 100%|##########| 1/1 [00:00<00:00, 20.95it/s, loss=0.0416, v_num=4, train_loss_step=0.0349, train_loss_epoch=0.0371]Epoch 192: 100%|##########| 1/1 [00:00<00:00, 20.68it/s, loss=0.0416, v_num=4, train_loss_step=0.0349, train_loss_epoch=0.0349]Epoch 192:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0416, v_num=4, train_loss_step=0.0349, train_loss_epoch=0.0349]        Epoch 193:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0416, v_num=4, train_loss_step=0.0349, train_loss_epoch=0.0349]Epoch 193: 100%|##########| 1/1 [00:00<00:00, 19.63it/s, loss=0.0416, v_num=4, train_loss_step=0.0349, train_loss_epoch=0.0349]Epoch 193: 100%|##########| 1/1 [00:00<00:00, 19.41it/s, loss=0.0412, v_num=4, train_loss_step=0.0356, train_loss_epoch=0.0349]Epoch 193: 100%|##########| 1/1 [00:00<00:00, 19.17it/s, loss=0.0412, v_num=4, train_loss_step=0.0356, train_loss_epoch=0.0356]Epoch 193:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0412, v_num=4, train_loss_step=0.0356, train_loss_epoch=0.0356]        Epoch 194:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0412, v_num=4, train_loss_step=0.0356, train_loss_epoch=0.0356]Epoch 194: 100%|##########| 1/1 [00:00<00:00, 20.88it/s, loss=0.0412, v_num=4, train_loss_step=0.0356, train_loss_epoch=0.0356]Epoch 194: 100%|##########| 1/1 [00:00<00:00, 20.63it/s, loss=0.0401, v_num=4, train_loss_step=0.0354, train_loss_epoch=0.0356]Epoch 194: 100%|##########| 1/1 [00:00<00:00, 20.38it/s, loss=0.0401, v_num=4, train_loss_step=0.0354, train_loss_epoch=0.0354]Epoch 194:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0401, v_num=4, train_loss_step=0.0354, train_loss_epoch=0.0354]        Epoch 195:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0401, v_num=4, train_loss_step=0.0354, train_loss_epoch=0.0354]Epoch 195: 100%|##########| 1/1 [00:00<00:00, 22.55it/s, loss=0.0401, v_num=4, train_loss_step=0.0354, train_loss_epoch=0.0354]Epoch 195: 100%|##########| 1/1 [00:00<00:00, 22.37it/s, loss=0.0398, v_num=4, train_loss_step=0.0363, train_loss_epoch=0.0354]Epoch 195: 100%|##########| 1/1 [00:00<00:00, 22.07it/s, loss=0.0398, v_num=4, train_loss_step=0.0363, train_loss_epoch=0.0363]Epoch 195:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0398, v_num=4, train_loss_step=0.0363, train_loss_epoch=0.0363]        Epoch 196:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0398, v_num=4, train_loss_step=0.0363, train_loss_epoch=0.0363]Epoch 196: 100%|##########| 1/1 [00:00<00:00, 21.28it/s, loss=0.0398, v_num=4, train_loss_step=0.0363, train_loss_epoch=0.0363]Epoch 196: 100%|##########| 1/1 [00:00<00:00, 21.08it/s, loss=0.0392, v_num=4, train_loss_step=0.036, train_loss_epoch=0.0363] Epoch 196: 100%|##########| 1/1 [00:00<00:00, 20.85it/s, loss=0.0392, v_num=4, train_loss_step=0.036, train_loss_epoch=0.036] Epoch 196:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0392, v_num=4, train_loss_step=0.036, train_loss_epoch=0.036]        Epoch 197:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0392, v_num=4, train_loss_step=0.036, train_loss_epoch=0.036]Epoch 197: 100%|##########| 1/1 [00:00<00:00, 23.14it/s, loss=0.0392, v_num=4, train_loss_step=0.036, train_loss_epoch=0.036]Epoch 197: 100%|##########| 1/1 [00:00<00:00, 22.88it/s, loss=0.0389, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.036]Epoch 197: 100%|##########| 1/1 [00:00<00:00, 22.54it/s, loss=0.0389, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.0388]Epoch 197:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0389, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.0388]        Epoch 198:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0389, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.0388]Epoch 198: 100%|##########| 1/1 [00:00<00:00, 18.42it/s, loss=0.0389, v_num=4, train_loss_step=0.0388, train_loss_epoch=0.0388]Epoch 198: 100%|##########| 1/1 [00:00<00:00, 18.29it/s, loss=0.0387, v_num=4, train_loss_step=0.0359, train_loss_epoch=0.0388]Epoch 198: 100%|##########| 1/1 [00:00<00:00, 18.10it/s, loss=0.0387, v_num=4, train_loss_step=0.0359, train_loss_epoch=0.0359]Epoch 198:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0387, v_num=4, train_loss_step=0.0359, train_loss_epoch=0.0359]        Epoch 199:   0%|          | 0/1 [00:00<?, ?it/s, loss=0.0387, v_num=4, train_loss_step=0.0359, train_loss_epoch=0.0359]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 20.90it/s, loss=0.0387, v_num=4, train_loss_step=0.0359, train_loss_epoch=0.0359]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 20.66it/s, loss=0.0383, v_num=4, train_loss_step=0.0347, train_loss_epoch=0.0359]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 20.12it/s, loss=0.0383, v_num=4, train_loss_step=0.0347, train_loss_epoch=0.0347]Epoch 199: 100%|##########| 1/1 [00:00<00:00, 16.18it/s, loss=0.0383, v_num=4, train_loss_step=0.0347, train_loss_epoch=0.0347]
Predicting: 1it [00:00, ?it/s]Predicting:   0%|          | 0/1 [00:00<00:00, -31300.78it/s]Predicting DataLoader 0:   0%|          | 0/1 [00:00<?, ?it/s]Predicting DataLoader 0: 100%|##########| 1/1 [00:00<00:00, 162.23it/s]Predicting DataLoader 0: 100%|##########| 1/1 [00:00<00:00, 153.49it/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()