克隆策略

In [1]:

# 本代码由可视化策略环境自动生成 2021年6月29日10:40
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


from tensorflow.keras.layers import Layer
import tensorflow as tf


class Time2Vector(Layer):
    def __init__(self, seq_len, **kwargs):
        super(Time2Vector, self).__init__(**kwargs)
        self.seq_len = seq_len

    def build(self, input_shape):
        self.weights_linear = self.add_weight(name='weight_linear',
                                    shape=(int(self.seq_len),),
                                    initializer='uniform',
                                    trainable=True)

        self.bias_linear = self.add_weight(name='bias_linear',
                                    shape=(int(self.seq_len),),
                                    initializer='uniform',
                                    trainable=True)

        self.weights_periodic = self.add_weight(name='weight_periodic',
                                    shape=(int(self.seq_len),),
                                    initializer='uniform',
                                    trainable=True)

        self.bias_periodic = self.add_weight(name='bias_periodic',
                                    shape=(int(self.seq_len),),
                                    initializer='uniform',
                                    trainable=True)

    def call(self, x):
        # Convert (batch, seq_len, 7) to (batch, seq_len)
        x = tf.math.reduce_mean(x[:, :, :], axis=-1)
        time_linear = self.weights_linear * x + self.bias_linear
        time_linear = tf.expand_dims(time_linear, axis=-1)

        time_periodic = tf.math.sin(tf.multiply(x, self.weights_periodic) + self.bias_periodic)
        time_periodic = tf.expand_dims(time_periodic, axis=-1)
        return tf.concat([time_linear, time_periodic], axis=-1)
    
    def get_config(self):
        config = {"seq_len": self.seq_len}
        base_config = super(Time2Vector, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))

m17_layer_class_bigquant_run = Time2Vector

from tensorflow.keras.layers import Layer, Dropout, Dense, LayerNormalization, Conv1D
import tensorflow as tf

class SingleAttention(Layer):
    def __init__(self, d_k, d_v):
        super(SingleAttention, self).__init__()
        self.d_k = d_k
        self.d_v = d_v

    def build(self, input_shape):
        self.query = Dense(self.d_k, input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')
        self.key = Dense(self.d_k, input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')
        self.value = Dense(self.d_v, input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')

    def call(self, inputs): # inputs = (in_seq, in_seq, in_seq)
        q = self.query(inputs[0])
        k = self.key(inputs[1])

        attn_weights = tf.matmul(q, k, transpose_b=True)
        attn_weights = tf.map_fn(lambda x: x/np.sqrt(self.d_k), attn_weights)
        attn_weights = tf.nn.softmax(attn_weights, axis=-1)

        v = self.value(inputs[2])
        attn_out = tf.matmul(attn_weights, v)
        return attn_out
    
class MultiAttention(Layer):
    def __init__(self, d_k, d_v, n_heads):
        super(MultiAttention, self).__init__()
        self.d_k = d_k
        self.d_v = d_v
        self.n_heads = n_heads
        self.attn_heads = list()

    def build(self, input_shape):
        for n in range(self.n_heads):
            self.attn_heads.append(SingleAttention(self.d_k, self.d_v))  
        self.linear = Dense(input_shape[-1][-1], input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')

    def call(self, inputs):
        attn = [self.attn_heads[i](inputs) for i in range(self.n_heads)]
        concat_attn = tf.concat(attn, axis=-1)
        multi_linear = self.linear(concat_attn)
        return multi_linear 
    
class TransformerEncoder1(Layer):
    def __init__(self, d_k, d_v, n_heads, ff_dim, dropout=0.1, **kwargs):
        super(TransformerEncoder1, self).__init__(**kwargs)
        self.d_k = d_k
        self.d_v = d_v
        self.n_heads = n_heads
        self.ff_dim = ff_dim
        self.attn_heads = list()
        self.dropout_rate = dropout

    def build(self, input_shape):
        self.attn_multi = MultiAttention(self.d_k, self.d_v, self.n_heads)
        self.attn_dropout = Dropout(self.dropout_rate)
        self.attn_normalize = LayerNormalization(input_shape=input_shape, epsilon=1e-6)

        self.ff_conv1D_1 = Conv1D(filters=self.ff_dim, kernel_size=1, activation='relu')
        self.ff_conv1D_2 = Conv1D(filters=input_shape[-1][-1], kernel_size=1)
        self.ff_dropout = Dropout(self.dropout_rate)
        self.ff_normalize = LayerNormalization(input_shape=input_shape, epsilon=1e-6)    

    def call(self, inputs):
        attn_layer = self.attn_multi(inputs)
        attn_layer = self.attn_dropout(attn_layer)
        attn_layer = self.attn_normalize(inputs[0] + attn_layer)
        ff_layer = self.ff_conv1D_1(attn_layer)
        ff_layer = self.ff_conv1D_2(ff_layer)
        ff_layer = self.ff_dropout(ff_layer)
        ff_layer = self.ff_normalize(inputs[0] + ff_layer)
        return ff_layer 
    
    def get_config(self):
        config = {"d_k": self.d_k, "d_v": self.d_v, "n_heads": self.n_heads, "ff_dim": self.ff_dim, "dropout": self.dropout_rate}
        base_config = super(TransformerEncoder1, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))

m23_layer_class_bigquant_run = TransformerEncoder1

from tensorflow.keras.layers import Layer, Dropout, Dense, LayerNormalization, Conv1D
import tensorflow as tf

# class SingleAttention(Layer):
#     def __init__(self, d_k, d_v):
#         super(SingleAttention, self).__init__()
#         self.d_k = d_k
#         self.d_v = d_v

#     def build(self, input_shape):
#         self.query = Dense(self.d_k, input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')
#         self.key = Dense(self.d_k, input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')
#         self.value = Dense(self.d_v, input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')

#     def call(self, inputs): # inputs = (in_seq, in_seq, in_seq)
#         q = self.query(inputs[0])
#         k = self.key(inputs[1])

#         attn_weights = tf.matmul(q, k, transpose_b=True)
#         attn_weights = tf.map_fn(lambda x: x/np.sqrt(self.d_k), attn_weights)
#         attn_weights = tf.nn.softmax(attn_weights, axis=-1)

#         v = self.value(inputs[2])
#         attn_out = tf.matmul(attn_weights, v)
#         return attn_out
    
# class MultiAttention(Layer):
#     def __init__(self, d_k, d_v, n_heads): # , out_dim
#         super(MultiAttention, self).__init__()
#         self.d_k = d_k
#         self.d_v = d_v
#         self.n_heads = n_heads
#         self.attn_heads = list()

#     def build(self, input_shape):
#         for n in range(self.n_heads):
#             self.attn_heads.append(SingleAttention(self.d_k, self.d_v))  
#         self.linear = Dense(input_shape[-1][-1], input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')

#     def call(self, inputs):
#         attn = [self.attn_heads[i](inputs) for i in range(self.n_heads)]
#         concat_attn = tf.concat(attn, axis=-1)
#         multi_linear = self.linear(concat_attn)
#         return multi_linear 
    
class TransformerEncoder2(Layer):
    def __init__(self, d_k, d_v, n_heads, ff_dim, dropout=0.1, **kwargs):
        super(TransformerEncoder2, self).__init__(**kwargs)
        self.d_k = d_k
        self.d_v = d_v
        self.n_heads = n_heads
        self.ff_dim = ff_dim
        self.attn_heads = list()
        self.dropout_rate = dropout

    def build(self, input_shape):
        self.attn_multi = MultiAttention(self.d_k, self.d_v, self.n_heads)
        self.attn_dropout = Dropout(self.dropout_rate)
        self.attn_normalize = LayerNormalization(input_shape=input_shape, epsilon=1e-6)

        self.ff_conv1D_1 = Conv1D(filters=self.ff_dim, kernel_size=1, activation='relu')
        self.ff_conv1D_2 = Conv1D(filters=input_shape[-1][-1], kernel_size=1)
        self.ff_dropout = Dropout(self.dropout_rate)
        self.ff_normalize = LayerNormalization(input_shape=input_shape, epsilon=1e-6)    

    def call(self, inputs):
        attn_layer = self.attn_multi(inputs)
        attn_layer = self.attn_dropout(attn_layer)
        attn_layer = self.attn_normalize(inputs[0] + attn_layer)
        ff_layer = self.ff_conv1D_1(attn_layer)
        ff_layer = self.ff_conv1D_2(ff_layer)
        ff_layer = self.ff_dropout(ff_layer)
        ff_layer = self.ff_normalize(inputs[0] + ff_layer)
        return ff_layer 
    
    def get_config(self):
        config = {"d_k": self.d_k, "d_v": self.d_v, "n_heads": self.n_heads, "ff_dim": self.ff_dim, "dropout": self.dropout_rate}
        base_config = super(TransformerEncoder2, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))

m20_layer_class_bigquant_run = TransformerEncoder2

from tensorflow.keras.layers import Layer, Dropout, Dense, LayerNormalization, Conv1D
import tensorflow as tf

# class SingleAttention(Layer):
#     def __init__(self, d_k, d_v):
#         super(SingleAttention, self).__init__()
#         self.d_k = d_k
#         self.d_v = d_v

#     def build(self, input_shape):
#         self.query = Dense(self.d_k, input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')
#         self.key = Dense(self.d_k, input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')
#         self.value = Dense(self.d_v, input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')

#     def call(self, inputs): # inputs = (in_seq, in_seq, in_seq)
#         q = self.query(inputs[0])
#         k = self.key(inputs[1])

#         attn_weights = tf.matmul(q, k, transpose_b=True)
#         attn_weights = tf.map_fn(lambda x: x/np.sqrt(self.d_k), attn_weights)
#         attn_weights = tf.nn.softmax(attn_weights, axis=-1)

#         v = self.value(inputs[2])
#         attn_out = tf.matmul(attn_weights, v)
#         return attn_out
    
# class MultiAttention(Layer):
#     def __init__(self, d_k, d_v, n_heads): # , out_dim
#         super(MultiAttention, self).__init__()
#         self.d_k = d_k
#         self.d_v = d_v
#         self.n_heads = n_heads
#         self.attn_heads = list()

#     def build(self, input_shape):
#         for n in range(self.n_heads):
#             self.attn_heads.append(SingleAttention(self.d_k, self.d_v))  
#         self.linear = Dense(input_shape[-1][-1], input_shape=input_shape, kernel_initializer='glorot_uniform', bias_initializer='glorot_uniform')

#     def call(self, inputs):
#         attn = [self.attn_heads[i](inputs) for i in range(self.n_heads)]
#         concat_attn = tf.concat(attn, axis=-1)
#         multi_linear = self.linear(concat_attn)
#         return multi_linear 
    
class TransformerEncoder3(Layer):
    def __init__(self, d_k, d_v, n_heads, ff_dim, dropout=0.1, **kwargs):
        super(TransformerEncoder3, self).__init__(**kwargs)
        self.d_k = d_k
        self.d_v = d_v
        self.n_heads = n_heads
        self.ff_dim = ff_dim
        self.attn_heads = list()
        self.dropout_rate = dropout

    def build(self, input_shape):
        self.attn_multi = MultiAttention(self.d_k, self.d_v, self.n_heads)
        self.attn_dropout = Dropout(self.dropout_rate)
        self.attn_normalize = LayerNormalization(input_shape=input_shape, epsilon=1e-6)

        self.ff_conv1D_1 = Conv1D(filters=self.ff_dim, kernel_size=1, activation='relu')
        self.ff_conv1D_2 = Conv1D(filters=input_shape[-1][-1], kernel_size=1)
        self.ff_dropout = Dropout(self.dropout_rate)
        self.ff_normalize = LayerNormalization(input_shape=input_shape, epsilon=1e-6)    

    def call(self, inputs):
        attn_layer = self.attn_multi(inputs)
        attn_layer = self.attn_dropout(attn_layer)
        attn_layer = self.attn_normalize(inputs[0] + attn_layer)
        ff_layer = self.ff_conv1D_1(attn_layer)
        ff_layer = self.ff_conv1D_2(ff_layer)
        ff_layer = self.ff_dropout(ff_layer)
        ff_layer = self.ff_normalize(inputs[0] + ff_layer)
        return ff_layer 
    
    def get_config(self):
        config = {"d_k": self.d_k, "d_v": self.d_v, "n_heads": self.n_heads, "ff_dim": self.ff_dim, "dropout": self.dropout_rate}
        base_config = super(TransformerEncoder3, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))

m21_layer_class_bigquant_run = TransformerEncoder3

m28_custom_objects_bigquant_run = {
    "Time2Vector": Time2Vector,
    "TransformerEncoder1": TransformerEncoder1,
    "TransformerEncoder2": TransformerEncoder2,
    "TransformerEncoder3": TransformerEncoder3
}

# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m30_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    pred = input_1.read()
#     pred = DataSource("d73724f7124c4f48ade645d9973f34e4T").read()
    test = input_2.read()
    df_trade = pd.DataFrame({'pred_label': pred[:, 0], 'instrument': test["instrument"], 'date': test["date"]})
    df_trade.sort_values(['date', 'pred_label'], inplace=True, ascending=[True, False])
    return Outputs(data_1=DataSource.write_df(df_trade))

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m30_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m29_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_df()

    # 系统已经设置了默认的交易手续费和滑点，要修改手续费可使用如下函数
    context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
    # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)
    # 设置买入的股票数量，这里买入预测股票列表排名靠前的5只
    stock_count = 5
    # 每只的股票的权重，如下的权重分配会使得靠前的股票分配多一点的资金，[0.339160, 0.213986, 0.169580, ..]
    context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 0.2
    context.hold_days = 5

# 回测引擎：每日数据处理函数，每天执行一次
def m29_handle_data_bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]

    # 1. 资金分配
    # 平均持仓时间是hold_days，每日都将买入股票，每日预期使用 1/hold_days 的资金
    # 实际操作中，会存在一定的买入误差，所以在前hold_days天，等量使用资金；之后，尽量使用剩余资金（这里设置最多用等量的1.5倍）
    is_staging = context.trading_day_index < context.hold_days # 是否在建仓期间（前 hold_days 天）
    cash_avg = context.portfolio.portfolio_value / context.hold_days
    cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
    cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
    positions = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.perf_tracker.position_tracker.positions.items()}

    # 2. 生成卖出订单：hold_days天之后才开始卖出；对持仓的股票，按StockRanker预测的排序末位淘汰
    if not is_staging and cash_for_sell > 0:
        equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
        # print('rank order for sell %s' % instruments)
        for instrument in instruments:
            context.order_target(context.symbol(instrument), 0)
            cash_for_sell -= positions[instrument]
            if cash_for_sell <= 0:
                break

    # 3. 生成买入订单：按StockRanker预测的排序，买入前面的stock_count只股票
    buy_cash_weights = context.stock_weights
    buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    for i, instrument in enumerate(buy_instruments):
        cash = cash_for_buy * buy_cash_weights[i]
        if cash > max_cash_per_instrument - positions.get(instrument, 0):
            # 确保股票持仓量不会超过每次股票最大的占用资金量
            cash = max_cash_per_instrument - positions.get(instrument, 0)
        if cash > 0:
            context.order_value(context.symbol(instrument), cash)

# 回测引擎：准备数据，只执行一次
def m29_prepare_bigquant_run(context):
    pass

# 回测引擎：每个单位时间开始前调用一次，即每日开盘前调用一次。
def m29_before_trading_start_bigquant_run(context, data):
    pass


m1 = M.instruments.v2(
    start_date='2015-01-01',
    end_date='2016-01-01',
    market='CN_STOCK_A',
    instrument_list=' ',
    max_count=0
)

m2 = M.advanced_auto_labeler.v2(
    instruments=m1.data,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
#   添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_

# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -5) / shift(open, -1)-1

# 极值处理：用1%和99%分位的值做clip
clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))

# 过滤掉一字涨停的情况 (设置label为NaN，在后续处理和训练中会忽略NaN的label)
where(shift(high, -1) == shift(low, -1), NaN, label)
""",
    start_date='',
    end_date='',
    benchmark='000300.SHA',
    drop_na_label=True,
    cast_label_int=False
)

m13 = M.standardlize.v8(
    input_1=m2.data,
    columns_input='label'
)

m3 = M.input_features.v1(
    features="""close_0/mean(close_0,5)
close_0/mean(close_0,10)
# close_0/mean(close_0,20)
# close_0/open_0
# open_0/mean(close_0,5)
# open_0/mean(close_0,10)
# open_0/mean(close_0,20)"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=30
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m14 = M.standardlize.v8(
    input_1=m16.data,
    input_2=m3.data,
    columns_input='[]'
)

m7 = M.join.v3(
    data1=m13.data,
    data2=m14.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m26 = M.dl_convert_to_bin.v2(
    input_data=m7.data,
    features=m3.data,
    window_size=5,
    feature_clip=5,
    flatten=False,
    window_along_col='instrument'
)

m5 = M.instruments.v2(
    start_date='2016-01-01',
    end_date='2017-01-01',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m6 = M.general_feature_extractor.v7(
    instruments=m5.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=30
)

m8 = M.derived_feature_extractor.v3(
    input_data=m6.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m9 = M.standardlize.v8(
    input_1=m8.data,
    input_2=m3.data,
    columns_input='[]'
)

m10 = M.dl_convert_to_bin.v2(
    input_data=m9.data,
    features=m3.data,
    window_size=5,
    feature_clip=5,
    flatten=False,
    window_along_col='instrument'
)

m12 = M.dl_layer_input.v1(
    shape='5,2',
    batch_shape='',
    dtype='float32',
    sparse=False,
    name='test'
)

m17 = M.dl_layer_userlayer.v1(
    input1=m12.data,
    layer_class=m17_layer_class_bigquant_run,
    params="""{
    "seq_len": 5
}""",
    name=''
)

m18 = M.dl_layer_concatenate.v1(
    input1=m17.data,
    input2=m12.data,
    axis=-1,
    name=''
)

m23 = M.dl_layer_userlayer.v1(
    input1=m18.data,
    input2=m18.data,
    input3=m18.data,
    layer_class=m23_layer_class_bigquant_run,
    params="""{
    "d_k": 100,
    "d_v": 100,
    "n_heads": 1,
    "ff_dim": 256
}""",
    name=''
)

m20 = M.dl_layer_userlayer.v1(
    input1=m23.data,
    input2=m23.data,
    input3=m23.data,
    layer_class=m20_layer_class_bigquant_run,
    params="""{
    "d_k": 100,
    "d_v": 100,
    "n_heads": 1,
    "ff_dim": 256
}""",
    name=''
)

m21 = M.dl_layer_userlayer.v1(
    input1=m20.data,
    input2=m20.data,
    input3=m20.data,
    layer_class=m21_layer_class_bigquant_run,
    params="""{
    "d_k": 100,
    "d_v": 100,
    "n_heads": 1,
    "ff_dim": 256
}""",
    name=''
)

m19 = M.dl_layer_globalaveragepooling1d.v1(
    inputs=m21.data,
    name=''
)

m22 = M.dl_layer_dropout.v1(
    inputs=m19.data,
    rate=0.1,
    noise_shape='',
    seed=111,
    name=''
)

m24 = M.dl_layer_dense.v1(
    inputs=m22.data,
    units=256,
    activation='relu',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    bias_initializer='Zeros',
    kernel_regularizer='None',
    kernel_regularizer_l1=0,
    kernel_regularizer_l2=0,
    bias_regularizer='None',
    bias_regularizer_l1=0,
    bias_regularizer_l2=0,
    activity_regularizer='None',
    activity_regularizer_l1=0,
    activity_regularizer_l2=0,
    kernel_constraint='None',
    bias_constraint='None',
    name=''
)

m25 = M.dl_layer_dense.v1(
    inputs=m24.data,
    units=1,
    activation='linear',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    bias_initializer='Zeros',
    kernel_regularizer='None',
    kernel_regularizer_l1=0,
    kernel_regularizer_l2=0,
    bias_regularizer='None',
    bias_regularizer_l1=0,
    bias_regularizer_l2=0,
    activity_regularizer='None',
    activity_regularizer_l1=0,
    activity_regularizer_l2=0,
    kernel_constraint='None',
    bias_constraint='None',
    name=''
)

m27 = M.dl_model_init.v1(
    inputs=m12.data,
    outputs=m25.data
)

m28 = M.dl_model_train.v1(
    input_model=m27.data,
    training_data=m26.data,
    optimizer='Adam',
    loss='mean_squared_error',
    metrics='mae',
    batch_size=1024,
    epochs=1,
    custom_objects=m28_custom_objects_bigquant_run,
    n_gpus=1,
    verbose='1:输出进度条记录'
)

m4 = M.dl_model_predict.v1(
    trained_model=m28.data,
    input_data=m10.data,
    batch_size=1024,
    n_gpus=0,
    verbose='2:每个epoch输出一行记录'
)

m30 = M.cached.v3(
    input_1=m4.data,
    input_2=m9.data,
    run=m30_run_bigquant_run,
    post_run=m30_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m29 = M.trade.v4(
    instruments=m5.data,
    options_data=m30.data_1,
    start_date='',
    end_date='',
    initialize=m29_initialize_bigquant_run,
    handle_data=m29_handle_data_bigquant_run,
    prepare=m29_prepare_bigquant_run,
    before_trading_start=m29_before_trading_start_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=1000000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark=''
)

[2021-06-28 11:05:00.835882] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-06-28 11:05:00.883574] INFO: moduleinvoker: 命中缓存

[2021-06-28 11:05:00.885155] INFO: moduleinvoker: instruments.v2 运行完成[0.04932s].

[2021-06-28 11:05:00.889976] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-06-28 11:05:04.244330] INFO: 自动标注(股票): 加载历史数据: 569698 行

[2021-06-28 11:05:04.248122] INFO: 自动标注(股票): 开始标注 ..

[2021-06-28 11:05:05.987035] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[5.097043s].

[2021-06-28 11:05:06.093799] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-06-28 11:05:07.378869] INFO: moduleinvoker: standardlize.v8 运行完成[1.285064s].

[2021-06-28 11:05:07.385141] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-06-28 11:05:07.393082] INFO: moduleinvoker: 命中缓存

[2021-06-28 11:05:07.394417] INFO: moduleinvoker: input_features.v1 运行完成[0.009285s].

[2021-06-28 11:05:07.404571] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-06-28 11:05:07.904819] INFO: 基础特征抽取: 年份 2014, 特征行数=51091

[2021-06-28 11:05:09.801647] INFO: 基础特征抽取: 年份 2015, 特征行数=569698

[2021-06-28 11:05:10.174055] INFO: 基础特征抽取: 年份 2016, 特征行数=0

[2021-06-28 11:05:10.360245] INFO: 基础特征抽取: 总行数: 620789

[2021-06-28 11:05:10.367484] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[2.962921s].

[2021-06-28 11:05:10.374598] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-06-28 11:05:13.240699] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,5), 0.616s

[2021-06-28 11:05:13.843005] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,10), 0.600s

[2021-06-28 11:05:14.072728] INFO: derived_feature_extractor: /y_2014, 51091

[2021-06-28 11:05:16.224782] INFO: derived_feature_extractor: /y_2015, 569698

[2021-06-28 11:05:16.917526] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[6.542917s].

[2021-06-28 11:05:16.920107] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-06-28 11:05:18.627704] INFO: moduleinvoker: standardlize.v8 运行完成[1.707556s].

[2021-06-28 11:05:18.657185] INFO: moduleinvoker: join.v3 开始运行..

[2021-06-28 11:05:23.848204] INFO: join: /data, 行数=545248/595553, 耗时=3.073819s

[2021-06-28 11:05:24.011489] INFO: join: 最终行数: 545248

[2021-06-28 11:05:24.037203] INFO: moduleinvoker: join.v3 运行完成[5.380025s].

[2021-06-28 11:05:24.150549] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-06-28 11:05:56.202168] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[32.051651s].

[2021-06-28 11:05:56.205135] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-06-28 11:05:56.212405] INFO: moduleinvoker: 命中缓存

[2021-06-28 11:05:56.213810] INFO: moduleinvoker: instruments.v2 运行完成[0.008686s].

[2021-06-28 11:05:56.221405] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-06-28 11:05:56.228399] INFO: moduleinvoker: 命中缓存

[2021-06-28 11:05:56.231561] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.01012s].

[2021-06-28 11:05:56.237480] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-06-28 11:05:56.250766] INFO: moduleinvoker: 命中缓存

[2021-06-28 11:05:56.254180] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.016702s].

[2021-06-28 11:05:56.258892] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-06-28 11:05:56.267314] INFO: moduleinvoker: 命中缓存

[2021-06-28 11:05:56.269353] INFO: moduleinvoker: standardlize.v8 运行完成[0.010488s].

[2021-06-28 11:05:56.278365] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-06-28 11:05:56.284876] INFO: moduleinvoker: 命中缓存

[2021-06-28 11:05:56.286337] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.007997s].

[2021-06-28 11:05:56.438268] INFO: moduleinvoker: dl_layer_input.v1 运行完成[0.068077s].

[2021-06-28 11:06:01.507553] INFO: moduleinvoker: dl_layer_userlayer.v1 运行完成[4.919758s].

[2021-06-28 11:06:01.724812] INFO: moduleinvoker: dl_layer_concatenate.v1 运行完成[0.006617s].

[2021-06-28 11:06:02.280189] INFO: moduleinvoker: dl_layer_userlayer.v1 运行完成[0.552409s].

[2021-06-28 11:06:02.602196] INFO: moduleinvoker: dl_layer_userlayer.v1 运行完成[0.318941s].

[2021-06-28 11:06:02.924251] INFO: moduleinvoker: dl_layer_userlayer.v1 运行完成[0.319205s].

[2021-06-28 11:06:03.005484] INFO: moduleinvoker: dl_layer_globalaveragepooling1d.v1 运行完成[0.005537s].

[2021-06-28 11:06:03.012915] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.003435s].

[2021-06-28 11:06:03.108894] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.010938s].

[2021-06-28 11:06:03.120773] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.008958s].

[2021-06-28 11:06:03.175603] INFO: moduleinvoker: cached.v3 开始运行..

[2021-06-28 11:06:03.185445] INFO: moduleinvoker: 命中缓存

[2021-06-28 11:06:03.187246] INFO: moduleinvoker: cached.v3 运行完成[0.011662s].

[2021-06-28 11:06:03.190409] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.066012s].

[2021-06-28 11:06:03.296496] INFO: moduleinvoker: dl_model_train.v1 开始运行..

[2021-06-28 11:06:04.320970] INFO: dl_model_train: 准备训练，训练样本个数：545248，迭代次数：1

[2021-06-28 11:18:15.936496] INFO: dl_model_train: 训练结束，耗时：731.61s

[2021-06-28 11:18:16.049699] INFO: moduleinvoker: dl_model_train.v1 运行完成[732.753174s].

[2021-06-28 11:18:16.147040] INFO: moduleinvoker: dl_model_predict.v1 开始运行..

[2021-06-28 11:25:03.988840] INFO: moduleinvoker: dl_model_predict.v1 运行完成[407.841811s].

[2021-06-28 11:25:03.996013] INFO: moduleinvoker: cached.v3 开始运行..

[2021-06-28 11:25:05.928267] INFO: moduleinvoker: cached.v3 运行完成[1.932235s].

[2021-06-28 11:25:07.935373] INFO: moduleinvoker: backtest.v8 开始运行..

[2021-06-28 11:25:07.942553] INFO: backtest: biglearning backtest:V8.5.0

[2021-06-28 11:25:07.944869] INFO: backtest: product_type:stock by specified

[2021-06-28 11:25:08.417496] INFO: moduleinvoker: cached.v2 开始运行..

[2021-06-28 11:25:08.427579] INFO: moduleinvoker: 命中缓存

[2021-06-28 11:25:08.430505] INFO: moduleinvoker: cached.v2 运行完成[0.013023s].

[2021-06-28 11:25:10.976665] INFO: algo: TradingAlgorithm V1.8.3

[2021-06-28 11:25:11.735977] INFO: algo: trading transform...

[2021-06-28 11:25:14.892267] INFO: algo: handle_splits get splits [dt:2016-05-06 00:00:00+00:00] [asset:Equity(192 [002534.SZA]), ratio:0.6623618006706238]

[2021-06-28 11:25:14.893689] INFO: Position: position stock handle split[sid:192, orig_amount:2500, new_amount:3774.0, orig_cost:15.280001918277248, new_cost:10.1209, ratio:0.6623618006706238, last_sale_price:10.770004272460938]

[2021-06-28 11:25:14.894819] INFO: Position: after split: PositionStock(asset:Equity(192 [002534.SZA]), amount:3774.0, cost_basis:10.1209, last_sale_price:16.26000213623047)

[2021-06-28 11:25:14.895686] INFO: Position: returning cash: 4.0091

[2021-06-28 11:25:15.126791] INFO: algo: handle_splits get splits [dt:2016-05-17 00:00:00+00:00] [asset:Equity(389 [002130.SZA]), ratio:0.9925575256347656]

[2021-06-28 11:25:15.406215] INFO: algo: handle_splits get splits [dt:2016-05-30 00:00:00+00:00] [asset:Equity(1558 [002461.SZA]), ratio:0.9956592917442322]

[2021-06-28 11:25:15.482654] INFO: algo: handle_splits get splits [dt:2016-06-01 00:00:00+00:00] [asset:Equity(2310 [601566.SHA]), ratio:0.9691546559333801]

[2021-06-28 11:25:15.484169] INFO: algo: handle_splits get splits [dt:2016-06-01 00:00:00+00:00] [asset:Equity(493 [600197.SHA]), ratio:0.9713056683540344]

[2021-06-28 11:25:15.485401] INFO: Position: position stock handle split[sid:2310, orig_amount:2300, new_amount:2373.0, orig_cost:15.479999062027611, new_cost:15.0025, ratio:0.9691546559333801, last_sale_price:15.709996223449707]

[2021-06-28 11:25:15.486338] INFO: Position: after split: PositionStock(asset:Equity(2310 [601566.SHA]), amount:2373.0, cost_basis:15.0025, last_sale_price:16.209999084472656)

[2021-06-28 11:25:15.487133] INFO: Position: returning cash: 3.1772

[2021-06-28 11:25:15.552117] INFO: algo: handle_splits get splits [dt:2016-06-03 00:00:00+00:00] [asset:Equity(772 [600356.SHA]), ratio:0.9915013909339905]

[2021-06-28 11:25:15.554406] INFO: Position: position stock handle split[sid:772, orig_amount:5300, new_amount:5345.0, orig_cost:10.000001725662802, new_cost:9.915, ratio:0.9915013909339905, last_sale_price:10.5]

[2021-06-28 11:25:15.556634] INFO: Position: after split: PositionStock(asset:Equity(772 [600356.SHA]), amount:5345.0, cost_basis:9.915, last_sale_price:10.59000015258789)

[2021-06-28 11:25:15.558523] INFO: Position: returning cash: 4.5014

[2021-06-28 11:25:15.758333] INFO: algo: handle_splits get splits [dt:2016-06-15 00:00:00+00:00] [asset:Equity(2021 [000538.SZA]), ratio:0.9903846383094788]

[2021-06-28 11:25:15.761203] INFO: Position: position stock handle split[sid:2021, orig_amount:600, new_amount:605.0, orig_cost:63.4899980715824, new_cost:62.8795, ratio:0.9903846383094788, last_sale_price:61.80000305175781]

[2021-06-28 11:25:15.764278] INFO: Position: after split: PositionStock(asset:Equity(2021 [000538.SZA]), amount:605.0, cost_basis:62.8795, last_sale_price:62.400001525878906)

[2021-06-28 11:25:15.767055] INFO: Position: returning cash: 50.9991

[2021-06-28 11:25:15.821351] INFO: algo: handle_splits get splits [dt:2016-06-17 00:00:00+00:00] [asset:Equity(2089 [002051.SZA]), ratio:0.8223886489868164]

[2021-06-28 11:25:15.932831] INFO: algo: handle_splits get splits [dt:2016-06-22 00:00:00+00:00] [asset:Equity(1929 [600325.SHA]), ratio:0.9861495494842529]

[2021-06-28 11:25:15.935575] INFO: algo: handle_splits get splits [dt:2016-06-22 00:00:00+00:00] [asset:Equity(253 [000700.SZA]), ratio:0.4978102445602417]

[2021-06-28 11:25:15.938485] INFO: Position: position stock handle split[sid:1929, orig_amount:4100, new_amount:4157.0, orig_cost:11.000000283385305, new_cost:10.8476, ratio:0.9861495494842529, last_sale_price:10.679999351501465]

[2021-06-28 11:25:15.941648] INFO: Position: after split: PositionStock(asset:Equity(1929 [600325.SHA]), amount:4157.0, cost_basis:10.8476, last_sale_price:10.829999923706055)

[2021-06-28 11:25:15.943203] INFO: Position: returning cash: 6.2416

[2021-06-28 11:25:15.945315] INFO: Position: position stock handle split[sid:253, orig_amount:2000, new_amount:4017.0, orig_cost:21.4300006752805, new_cost:10.6681, ratio:0.4978102445602417, last_sale_price:10.230000495910645]

[2021-06-28 11:25:15.947460] INFO: Position: after split: PositionStock(asset:Equity(253 [000700.SZA]), amount:4017.0, cost_basis:10.6681, last_sale_price:20.549999237060547)

[2021-06-28 11:25:15.949115] INFO: Position: returning cash: 6.0879

[2021-06-28 11:25:16.016450] INFO: algo: handle_splits get splits [dt:2016-06-24 00:00:00+00:00] [asset:Equity(3020 [300303.SZA]), ratio:0.9935732483863831]

[2021-06-28 11:25:16.017887] INFO: Position: position stock handle split[sid:3020, orig_amount:9000, new_amount:9058.0, orig_cost:7.550000750969848, new_cost:7.5015, ratio:0.9935732483863831, last_sale_price:7.730000019073486]

[2021-06-28 11:25:16.018980] INFO: Position: after split: PositionStock(asset:Equity(3020 [300303.SZA]), amount:9058.0, cost_basis:7.5015, last_sale_price:7.78000020980835)

[2021-06-28 11:25:16.019875] INFO: Position: returning cash: 1.6612

[2021-06-28 11:25:16.121479] INFO: algo: handle_splits get splits [dt:2016-06-29 00:00:00+00:00] [asset:Equity(2839 [300011.SZA]), ratio:0.9974270462989807]

[2021-06-28 11:25:16.455807] INFO: algo: handle_splits get splits [dt:2016-07-13 00:00:00+00:00] [asset:Equity(3108 [002650.SZA]), ratio:0.9946308732032776]

[2021-06-28 11:25:16.457791] INFO: Position: position stock handle split[sid:3108, orig_amount:7700, new_amount:7741.0, orig_cost:7.4000003133467365, new_cost:7.3603, ratio:0.9946308732032776, last_sale_price:7.409999847412109]

[2021-06-28 11:25:16.460213] INFO: Position: after split: PositionStock(asset:Equity(3108 [002650.SZA]), amount:7741.0, cost_basis:7.3603, last_sale_price:7.449999809265137)

[2021-06-28 11:25:16.462566] INFO: Position: returning cash: 4.19

[2021-06-28 11:25:18.899615] INFO: algo: handle_splits get splits [dt:2016-10-18 00:00:00+00:00] [asset:Equity(307 [002421.SZA]), ratio:0.3334870934486389]

[2021-06-28 11:25:20.598323] INFO: Performance: Simulated 244 trading days out of 244.

[2021-06-28 11:25:20.599622] INFO: Performance: first open: 2016-01-04 09:30:00+00:00

[2021-06-28 11:25:20.600659] INFO: Performance: last close: 2016-12-30 15:00:00+00:00

[2021-06-28 11:25:25.334970] INFO: moduleinvoker: backtest.v8 运行完成[17.399605s].

[2021-06-28 11:25:25.337644] INFO: moduleinvoker: trade.v4 运行完成[19.401221s].

  1/533 [..............................] - ETA: 5:11:25 - loss: 1.0668 - mae: 0.7582  2/533 [..............................] - ETA: 11:30 - loss: 1.0847 - mae: 0.7629    3/533 [..............................] - ETA: 11:36 - loss: 1.0774 - mae: 0.7596  4/533 [..............................] - ETA: 11:31 - loss: 1.0728 - mae: 0.7581  5/533 [..............................] - ETA: 11:38 - loss: 1.0678 - mae: 0.7567  6/533 [..............................] - ETA: 11:40 - loss: 1.0621 - mae: 0.7551  7/533 [..............................] - ETA: 11:40 - loss: 1.0571 - mae: 0.7535  8/533 [..............................] - ETA: 11:45 - loss: 1.0524 - mae: 0.7522  9/533 [..............................] - ETA: 11:48 - loss: 1.0490 - mae: 0.7514 10/533 [..............................] - ETA: 11:44 - loss: 1.0458 - mae: 0.7506 11/533 [..............................] - ETA: 11:50 - loss: 1.0434 - mae: 0.7498 12/533 [..............................] - ETA: 11:48 - loss: 1.0416 - mae: 0.7493 13/533 [..............................] - ETA: 11:49 - loss: 1.0393 - mae: 0.7487 14/533 [..............................] - ETA: 11:49 - loss: 1.0373 - mae: 0.7481 15/533 [..............................] - ETA: 11:48 - loss: 1.0352 - mae: 0.7475 16/533 [..............................] - ETA: 11:48 - loss: 1.0329 - mae: 0.7469 17/533 [..............................] - ETA: 11:50 - loss: 1.0306 - mae: 0.7462 18/533 [>.............................] - ETA: 11:51 - loss: 1.0285 - mae: 0.7455 19/533 [>.............................] - ETA: 11:49 - loss: 1.0265 - mae: 0.7450 20/533 [>.............................] - ETA: 11:48 - loss: 1.0246 - mae: 0.7444 21/533 [>.............................] - ETA: 11:49 - loss: 1.0229 - mae: 0.7439 22/533 [>.............................] - ETA: 11:49 - loss: 1.0216 - mae: 0.7434 23/533 [>.............................] - ETA: 11:49 - loss: 1.0205 - mae: 0.7430 24/533 [>.............................] - ETA: 11:45 - loss: 1.0196 - mae: 0.7427 25/533 [>.............................] - ETA: 11:41 - loss: 1.0186 - mae: 0.7423 26/533 [>.............................] - ETA: 11:39 - loss: 1.0176 - mae: 0.7420 27/533 [>.............................] - ETA: 11:36 - loss: 1.0167 - mae: 0.7417 28/533 [>.............................] - ETA: 11:32 - loss: 1.0159 - mae: 0.7414 29/533 [>.............................] - ETA: 11:30 - loss: 1.0152 - mae: 0.7411 30/533 [>.............................] - ETA: 11:27 - loss: 1.0145 - mae: 0.7408 31/533 [>.............................] - ETA: 11:24 - loss: 1.0139 - mae: 0.7406 32/533 [>.............................] - ETA: 11:23 - loss: 1.0134 - mae: 0.7403 33/533 [>.............................] - ETA: 11:20 - loss: 1.0127 - mae: 0.7401 34/533 [>.............................] - ETA: 11:17 - loss: 1.0121 - mae: 0.7398 35/533 [>.............................] - ETA: 11:15 - loss: 1.0115 - mae: 0.7396 36/533 [=>............................] - ETA: 11:14 - loss: 1.0110 - mae: 0.7393 37/533 [=>............................] - ETA: 11:13 - loss: 1.0104 - mae: 0.7391 38/533 [=>............................] - ETA: 11:10 - loss: 1.0098 - mae: 0.7388 39/533 [=>............................] - ETA: 11:08 - loss: 1.0091 - mae: 0.7385 40/533 [=>............................] - ETA: 11:05 - loss: 1.0085 - mae: 0.7383 41/533 [=>............................] - ETA: 11:02 - loss: 1.0078 - mae: 0.7380 42/533 [=>............................] - ETA: 10:58 - loss: 1.0072 - mae: 0.7377 43/533 [=>............................] - ETA: 10:56 - loss: 1.0066 - mae: 0.7375 44/533 [=>............................] - ETA: 10:55 - loss: 1.0060 - mae: 0.7373 45/533 [=>............................] - ETA: 10:53 - loss: 1.0056 - mae: 0.7370 46/533 [=>............................] - ETA: 10:52 - loss: 1.0052 - mae: 0.7368 47/533 [=>............................] - ETA: 10:50 - loss: 1.0048 - mae: 0.7366 48/533 [=>............................] - ETA: 10:48 - loss: 1.0044 - mae: 0.7364 49/533 [=>............................] - ETA: 10:48 - loss: 1.0040 - mae: 0.7362 50/533 [=>............................] - ETA: 10:48 - loss: 1.0037 - mae: 0.7361 51/533 [=>............................] - ETA: 10:46 - loss: 1.0034 - mae: 0.7359 52/533 [=>............................] - ETA: 10:46 - loss: 1.0030 - mae: 0.7357 53/533 [=>............................] - ETA: 10:45 - loss: 1.0027 - mae: 0.7356 54/533 [==>...........................] - ETA: 10:44 - loss: 1.0024 - mae: 0.7354 55/533 [==>...........................] - ETA: 10:43 - loss: 1.0022 - mae: 0.7353 56/533 [==>...........................] - ETA: 10:43 - loss: 1.0019 - mae: 0.7352 57/533 [==>...........................] - ETA: 10:41 - loss: 1.0017 - mae: 0.7350 58/533 [==>...........................] - ETA: 10:41 - loss: 1.0015 - mae: 0.7349 59/533 [==>...........................] - ETA: 10:39 - loss: 1.0013 - mae: 0.7348 60/533 [==>...........................] - ETA: 10:38 - loss: 1.0011 - mae: 0.7347 61/533 [==>...........................] - ETA: 10:36 - loss: 1.0009 - mae: 0.7346 62/533 [==>...........................] - ETA: 10:35 - loss: 1.0008 - mae: 0.7345 63/533 [==>...........................] - ETA: 10:33 - loss: 1.0006 - mae: 0.7344 64/533 [==>...........................] - ETA: 10:32 - loss: 1.0004 - mae: 0.7343 65/533 [==>...........................] - ETA: 10:31 - loss: 1.0003 - mae: 0.7343 66/533 [==>...........................] - ETA: 10:30 - loss: 1.0002 - mae: 0.7342 67/533 [==>...........................] - ETA: 10:28 - loss: 1.0001 - mae: 0.7341 68/533 [==>...........................] - ETA: 10:27 - loss: 1.0000 - mae: 0.7341 69/533 [==>...........................] - ETA: 10:26 - loss: 0.9999 - mae: 0.7340 70/533 [==>...........................] - ETA: 10:24 - loss: 0.9998 - mae: 0.7339 71/533 [==>...........................] - ETA: 10:22 - loss: 0.9997 - mae: 0.7339 72/533 [===>..........................] - ETA: 10:21 - loss: 0.9997 - mae: 0.7338 73/533 [===>..........................] - ETA: 10:19 - loss: 0.9996 - mae: 0.7338 74/533 [===>..........................] - ETA: 10:18 - loss: 0.9995 - mae: 0.7337 75/533 [===>..........................] - ETA: 10:17 - loss: 0.9994 - mae: 0.7337 76/533 [===>..........................] - ETA: 10:15 - loss: 0.9993 - mae: 0.7336 77/533 [===>..........................] - ETA: 10:14 - loss: 0.9993 - mae: 0.7336 78/533 [===>..........................] - ETA: 10:12 - loss: 0.9992 - mae: 0.7335 79/533 [===>..........................] - ETA: 10:10 - loss: 0.9991 - mae: 0.7335 80/533 [===>..........................] - ETA: 10:09 - loss: 0.9990 - mae: 0.7334 81/533 [===>..........................] - ETA: 10:07 - loss: 0.9990 - mae: 0.7334 82/533 [===>..........................] - ETA: 10:06 - loss: 0.9989 - mae: 0.7333 83/533 [===>..........................] - ETA: 10:04 - loss: 0.9988 - mae: 0.7333 84/533 [===>..........................] - ETA: 10:03 - loss: 0.9987 - mae: 0.7332 85/533 [===>..........................] - ETA: 10:01 - loss: 0.9986 - mae: 0.7332 86/533 [===>..........................] - ETA: 9:59 - loss: 0.9986 - mae: 0.7332  87/533 [===>..........................] - ETA: 9:57 - loss: 0.9985 - mae: 0.7331 88/533 [===>..........................] - ETA: 9:55 - loss: 0.9984 - mae: 0.7331 89/533 [====>.........................] - ETA: 9:53 - loss: 0.9984 - mae: 0.7331 90/533 [====>.........................] - ETA: 9:50 - loss: 0.9983 - mae: 0.7330 91/533 [====>.........................] - ETA: 9:49 - loss: 0.9983 - mae: 0.7330 92/533 [====>.........................] - ETA: 9:47 - loss: 0.9982 - mae: 0.7330 93/533 [====>.........................] - ETA: 9:46 - loss: 0.9982 - mae: 0.7330 94/533 [====>.........................] - ETA: 9:44 - loss: 0.9981 - mae: 0.7329 95/533 [====>.........................] - ETA: 9:42 - loss: 0.9981 - mae: 0.7329 96/533 [====>.........................] - ETA: 9:40 - loss: 0.9981 - mae: 0.7329 97/533 [====>.........................] - ETA: 9:39 - loss: 0.9980 - mae: 0.7329 98/533 [====>.........................] - ETA: 9:37 - loss: 0.9980 - mae: 0.7328 99/533 [====>.........................] - ETA: 9:35 - loss: 0.9980 - mae: 0.7328100/533 [====>.........................] - ETA: 9:33 - loss: 0.9980 - mae: 0.7328101/533 [====>.........................] - ETA: 9:31 - loss: 0.9980 - mae: 0.7328102/533 [====>.........................] - ETA: 9:29 - loss: 0.9979 - mae: 0.7328103/533 [====>.........................] - ETA: 9:28 - loss: 0.9979 - mae: 0.7327104/533 [====>.........................] - ETA: 9:26 - loss: 0.9979 - mae: 0.7327105/533 [====>.........................] - ETA: 9:25 - loss: 0.9979 - mae: 0.7327106/533 [====>.........................] - ETA: 9:24 - loss: 0.9979 - mae: 0.7327107/533 [=====>........................] - ETA: 9:22 - loss: 0.9979 - mae: 0.7327108/533 [=====>........................] - ETA: 9:21 - loss: 0.9978 - mae: 0.7327109/533 [=====>........................] - ETA: 9:20 - loss: 0.9978 - mae: 0.7326110/533 [=====>........................] - ETA: 9:18 - loss: 0.9978 - mae: 0.7326111/533 [=====>........................] - ETA: 9:17 - loss: 0.9978 - mae: 0.7326112/533 [=====>........................] - ETA: 9:16 - loss: 0.9977 - mae: 0.7326113/533 [=====>........................] - ETA: 9:15 - loss: 0.9977 - mae: 0.7326114/533 [=====>........................] - ETA: 9:13 - loss: 0.9977 - mae: 0.7325115/533 [=====>........................] - ETA: 9:12 - loss: 0.9976 - mae: 0.7325116/533 [=====>........................] - ETA: 9:11 - loss: 0.9976 - mae: 0.7325117/533 [=====>........................] - ETA: 9:09 - loss: 0.9976 - mae: 0.7325118/533 [=====>........................] - ETA: 9:08 - loss: 0.9975 - mae: 0.7325119/533 [=====>........................] - ETA: 9:07 - loss: 0.9975 - mae: 0.7325120/533 [=====>........................] - ETA: 9:06 - loss: 0.9974 - mae: 0.7324121/533 [=====>........................] - ETA: 9:04 - loss: 0.9974 - mae: 0.7324122/533 [=====>........................] - ETA: 9:03 - loss: 0.9974 - mae: 0.7324123/533 [=====>........................] - ETA: 9:02 - loss: 0.9974 - mae: 0.7324124/533 [=====>........................] - ETA: 9:00 - loss: 0.9974 - mae: 0.7324125/533 [======>.......................] - ETA: 8:59 - loss: 0.9973 - mae: 0.7324126/533 [======>.......................] - ETA: 8:58 - loss: 0.9973 - mae: 0.7324127/533 [======>.......................] - ETA: 8:56 - loss: 0.9973 - mae: 0.7324128/533 [======>.......................] - ETA: 8:55 - loss: 0.9973 - mae: 0.7324129/533 [======>.......................] - ETA: 8:54 - loss: 0.9973 - mae: 0.7323130/533 [======>.......................] - ETA: 8:53 - loss: 0.9973 - mae: 0.7323131/533 [======>.......................] - ETA: 8:51 - loss: 0.9972 - mae: 0.7323132/533 [======>.......................] - ETA: 8:50 - loss: 0.9972 - mae: 0.7323133/533 [======>.......................] - ETA: 8:49 - loss: 0.9972 - mae: 0.7323134/533 [======>.......................] - ETA: 8:48 - loss: 0.9972 - mae: 0.7323135/533 [======>.......................] - ETA: 8:47 - loss: 0.9972 - mae: 0.7323136/533 [======>.......................] - ETA: 8:46 - loss: 0.9972 - mae: 0.7323137/533 [======>.......................] - ETA: 8:45 - loss: 0.9972 - mae: 0.7323138/533 [======>.......................] - ETA: 8:44 - loss: 0.9972 - mae: 0.7323139/533 [======>.......................] - ETA: 8:42 - loss: 0.9971 - mae: 0.7322140/533 [======>.......................] - ETA: 8:41 - loss: 0.9971 - mae: 0.7322141/533 [======>.......................] - ETA: 8:39 - loss: 0.9971 - mae: 0.7322142/533 [======>.......................] - ETA: 8:38 - loss: 0.9971 - mae: 0.7322143/533 [=======>......................] - ETA: 8:37 - loss: 0.9971 - mae: 0.7322144/533 [=======>......................] - ETA: 8:35 - loss: 0.9970 - mae: 0.7322145/533 [=======>......................] - ETA: 8:34 - loss: 0.9970 - mae: 0.7322146/533 [=======>......................] - ETA: 8:33 - loss: 0.9970 - mae: 0.7322147/533 [=======>......................] - ETA: 8:32 - loss: 0.9970 - mae: 0.7321148/533 [=======>......................] - ETA: 8:30 - loss: 0.9969 - mae: 0.7321149/533 [=======>......................] - ETA: 8:29 - loss: 0.9969 - mae: 0.7321150/533 [=======>......................] - ETA: 8:28 - loss: 0.9969 - mae: 0.7321151/533 [=======>......................] - ETA: 8:26 - loss: 0.9969 - mae: 0.7321152/533 [=======>......................] - ETA: 8:25 - loss: 0.9968 - mae: 0.7321153/533 [=======>......................] - ETA: 8:24 - loss: 0.9968 - mae: 0.7321154/533 [=======>......................] - ETA: 8:22 - loss: 0.9968 - mae: 0.7321155/533 [=======>......................] - ETA: 8:21 - loss: 0.9967 - mae: 0.7320156/533 [=======>......................] - ETA: 8:19 - loss: 0.9967 - mae: 0.7320157/533 [=======>......................] - ETA: 8:18 - loss: 0.9967 - mae: 0.7320158/533 [=======>......................] - ETA: 8:17 - loss: 0.9967 - mae: 0.7320159/533 [=======>......................] - ETA: 8:16 - loss: 0.9966 - mae: 0.7320160/533 [========>.....................] - ETA: 8:14 - loss: 0.9966 - mae: 0.7320161/533 [========>.....................] - ETA: 8:13 - loss: 0.9966 - mae: 0.7320162/533 [========>.....................] - ETA: 8:12 - loss: 0.9965 - mae: 0.7320163/533 [========>.....................] - ETA: 8:10 - loss: 0.9965 - mae: 0.7319164/533 [========>.....................] - ETA: 8:09 - loss: 0.9965 - mae: 0.7319165/533 [========>.....................] - ETA: 8:07 - loss: 0.9964 - mae: 0.7319166/533 [========>.....................] - ETA: 8:06 - loss: 0.9964 - mae: 0.7319167/533 [========>.....................] - ETA: 8:05 - loss: 0.9964 - mae: 0.7319168/533 [========>.....................] - ETA: 8:03 - loss: 0.9964 - mae: 0.7319169/533 [========>.....................] - ETA: 8:02 - loss: 0.9963 - mae: 0.7319170/533 [========>.....................] - ETA: 8:00 - loss: 0.9963 - mae: 0.7319171/533 [========>.....................] - ETA: 7:59 - loss: 0.9963 - mae: 0.7319172/533 [========>.....................] - ETA: 7:58 - loss: 0.9963 - mae: 0.7318173/533 [========>.....................] - ETA: 7:56 - loss: 0.9962 - mae: 0.7318174/533 [========>.....................] - ETA: 7:55 - loss: 0.9962 - mae: 0.7318175/533 [========>.....................] - ETA: 7:54 - loss: 0.9962 - mae: 0.7318176/533 [========>.....................] - ETA: 7:53 - loss: 0.9962 - mae: 0.7318177/533 [========>.....................] - ETA: 7:51 - loss: 0.9961 - mae: 0.7318178/533 [=========>....................] - ETA: 7:50 - loss: 0.9961 - mae: 0.7318179/533 [=========>....................] - ETA: 7:49 - loss: 0.9961 - mae: 0.7318180/533 [=========>....................] - ETA: 7:47 - loss: 0.9961 - mae: 0.7318181/533 [=========>....................] - ETA: 7:46 - loss: 0.9961 - mae: 0.7318182/533 [=========>....................] - ETA: 7:45 - loss: 0.9961 - mae: 0.7318183/533 [=========>....................] - ETA: 7:44 - loss: 0.9961 - mae: 0.7318184/533 [=========>....................] - ETA: 7:43 - loss: 0.9961 - mae: 0.7317185/533 [=========>....................] - ETA: 7:42 - loss: 0.9960 - mae: 0.7317186/533 [=========>....................] - ETA: 7:40 - loss: 0.9960 - mae: 0.7317187/533 [=========>....................] - ETA: 7:39 - loss: 0.9960 - mae: 0.7317188/533 [=========>....................] - ETA: 7:38 - loss: 0.9960 - mae: 0.7317189/533 [=========>....................] - ETA: 7:37 - loss: 0.9960 - mae: 0.7317190/533 [=========>....................] - ETA: 7:35 - loss: 0.9960 - mae: 0.7317191/533 [=========>....................] - ETA: 7:34 - loss: 0.9959 - mae: 0.7317192/533 [=========>....................] - ETA: 7:33 - loss: 0.9959 - mae: 0.7317193/533 [=========>....................] - ETA: 7:31 - loss: 0.9959 - mae: 0.7317194/533 [=========>....................] - ETA: 7:30 - loss: 0.9959 - mae: 0.7317195/533 [=========>....................] - ETA: 7:29 - loss: 0.9959 - mae: 0.7317196/533 [==========>...................] - ETA: 7:28 - loss: 0.9959 - mae: 0.7317197/533 [==========>...................] - ETA: 7:27 - loss: 0.9959 - mae: 0.7317198/533 [==========>...................] - ETA: 7:25 - loss: 0.9959 - mae: 0.7317199/533 [==========>...................] - ETA: 7:24 - loss: 0.9959 - mae: 0.7317200/533 [==========>...................] - ETA: 7:23 - loss: 0.9959 - mae: 0.7317201/533 [==========>...................] - ETA: 7:21 - loss: 0.9959 - mae: 0.7317202/533 [==========>...................] - ETA: 7:20 - loss: 0.9959 - mae: 0.7317203/533 [==========>...................] - ETA: 7:19 - loss: 0.9959 - mae: 0.7317204/533 [==========>...................] - ETA: 7:17 - loss: 0.9959 - mae: 0.7317205/533 [==========>...................] - ETA: 7:16 - loss: 0.9959 - mae: 0.7317206/533 [==========>...................] - ETA: 7:15 - loss: 0.9959 - mae: 0.7317207/533 [==========>...................] - ETA: 7:14 - loss: 0.9959 - mae: 0.7317208/533 [==========>...................] - ETA: 7:12 - loss: 0.9959 - mae: 0.7317209/533 [==========>...................] - ETA: 7:11 - loss: 0.9959 - mae: 0.7317210/533 [==========>...................] - ETA: 7:10 - loss: 0.9959 - mae: 0.7317211/533 [==========>...................] - ETA: 7:09 - loss: 0.9959 - mae: 0.7317212/533 [==========>...................] - ETA: 7:07 - loss: 0.9959 - mae: 0.7317213/533 [==========>...................] - ETA: 7:06 - loss: 0.9959 - mae: 0.7317214/533 [===========>..................] - ETA: 7:05 - loss: 0.9959 - mae: 0.7317215/533 [===========>..................] - ETA: 7:04 - loss: 0.9959 - mae: 0.7317216/533 [===========>..................] - ETA: 7:02 - loss: 0.9959 - mae: 0.7317217/533 [===========>..................] - ETA: 7:01 - loss: 0.9959 - mae: 0.7317218/533 [===========>..................] - ETA: 7:00 - loss: 0.9959 - mae: 0.7317219/533 [===========>..................] - ETA: 6:59 - loss: 0.9959 - mae: 0.7317220/533 [===========>..................] - ETA: 6:58 - loss: 0.9959 - mae: 0.7317221/533 [===========>..................] - ETA: 6:57 - loss: 0.9959 - mae: 0.7317222/533 [===========>..................] - ETA: 6:55 - loss: 0.9959 - mae: 0.7317223/533 [===========>..................] - ETA: 6:54 - loss: 0.9959 - mae: 0.7317224/533 [===========>..................] - ETA: 6:53 - loss: 0.9958 - mae: 0.7317225/533 [===========>..................] - ETA: 6:52 - loss: 0.9958 - mae: 0.7317226/533 [===========>..................] - ETA: 6:51 - loss: 0.9958 - mae: 0.7317227/533 [===========>..................] - ETA: 6:50 - loss: 0.9958 - mae: 0.7317228/533 [===========>..................] - ETA: 6:49 - loss: 0.9958 - mae: 0.7317229/533 [===========>..................] - ETA: 6:47 - loss: 0.9958 - mae: 0.7317230/533 [===========>..................] - ETA: 6:46 - loss: 0.9958 - mae: 0.7317231/533 [============>.................] - ETA: 6:45 - loss: 0.9958 - mae: 0.7317232/533 [============>.................] - ETA: 6:43 - loss: 0.9958 - mae: 0.7317233/533 [============>.................] - ETA: 6:42 - loss: 0.9958 - mae: 0.7317234/533 [============>.................] - ETA: 6:41 - loss: 0.9958 - mae: 0.7317235/533 [============>.................] - ETA: 6:39 - loss: 0.9958 - mae: 0.7317236/533 [============>.................] - ETA: 6:38 - loss: 0.9958 - mae: 0.7317237/533 [============>.................] - ETA: 6:37 - loss: 0.9958 - mae: 0.7317238/533 [============>.................] - ETA: 6:35 - loss: 0.9958 - mae: 0.7317239/533 [============>.................] - ETA: 6:34 - loss: 0.9958 - mae: 0.7317240/533 [============>.................] - ETA: 6:33 - loss: 0.9958 - mae: 0.7317241/533 [============>.................] - ETA: 6:31 - loss: 0.9958 - mae: 0.7317242/533 [============>.................] - ETA: 6:30 - loss: 0.9958 - mae: 0.7317243/533 [============>.................] - ETA: 6:29 - loss: 0.9958 - mae: 0.7317244/533 [============>.................] - ETA: 6:27 - loss: 0.9958 - mae: 0.7317245/533 [============>.................] - ETA: 6:26 - loss: 0.9958 - mae: 0.7317246/533 [============>.................] - ETA: 6:25 - loss: 0.9958 - mae: 0.7317247/533 [============>.................] - ETA: 6:23 - loss: 0.9958 - mae: 0.7317248/533 [============>.................] - ETA: 6:22 - loss: 0.9958 - mae: 0.7317249/533 [=============>................] - ETA: 6:21 - loss: 0.9958 - mae: 0.7317250/533 [=============>................] - ETA: 6:19 - loss: 0.9958 - mae: 0.7317251/533 [=============>................] - ETA: 6:18 - loss: 0.9958 - mae: 0.7317252/533 [=============>................] - ETA: 6:16 - loss: 0.9958 - mae: 0.7317253/533 [=============>................] - ETA: 6:15 - loss: 0.9958 - mae: 0.7317254/533 [=============>................] - ETA: 6:14 - loss: 0.9958 - mae: 0.7317255/533 [=============>................] - ETA: 6:12 - loss: 0.9958 - mae: 0.7317256/533 [=============>................] - ETA: 6:11 - loss: 0.9958 - mae: 0.7317257/533 [=============>................] - ETA: 6:10 - loss: 0.9958 - mae: 0.7317258/533 [=============>................] - ETA: 6:08 - loss: 0.9958 - mae: 0.7317259/533 [=============>................] - ETA: 6:07 - loss: 0.9958 - mae: 0.7317260/533 [=============>................] - ETA: 6:05 - loss: 0.9957 - mae: 0.7317261/533 [=============>................] - ETA: 6:04 - loss: 0.9957 - mae: 0.7317262/533 [=============>................] - ETA: 6:02 - loss: 0.9957 - mae: 0.7316263/533 [=============>................] - ETA: 6:01 - loss: 0.9957 - mae: 0.7316264/533 [=============>................] - ETA: 5:59 - loss: 0.9957 - mae: 0.7316265/533 [=============>................] - ETA: 5:58 - loss: 0.9957 - mae: 0.7316266/533 [=============>................] - ETA: 5:56 - loss: 0.9957 - mae: 0.7316267/533 [==============>...............] - ETA: 5:55 - loss: 0.9957 - mae: 0.7316268/533 [==============>...............] - ETA: 5:53 - loss: 0.9957 - mae: 0.7316269/533 [==============>...............] - ETA: 5:52 - loss: 0.9956 - mae: 0.7316270/533 [==============>...............] - ETA: 5:50 - loss: 0.9956 - mae: 0.7316271/533 [==============>...............] - ETA: 5:49 - loss: 0.9956 - mae: 0.7316272/533 [==============>...............] - ETA: 5:48 - loss: 0.9956 - mae: 0.7316273/533 [==============>...............] - ETA: 5:46 - loss: 0.9956 - mae: 0.7316274/533 [==============>...............] - ETA: 5:45 - loss: 0.9956 - mae: 0.7316275/533 [==============>...............] - ETA: 5:43 - loss: 0.9956 - mae: 0.7316276/533 [==============>...............] - ETA: 5:42 - loss: 0.9956 - mae: 0.7316277/533 [==============>...............] - ETA: 5:40 - loss: 0.9956 - mae: 0.7316278/533 [==============>...............] - ETA: 5:39 - loss: 0.9956 - mae: 0.7316279/533 [==============>...............] - ETA: 5:38 - loss: 0.9956 - mae: 0.7316280/533 [==============>...............] - ETA: 5:36 - loss: 0.9955 - mae: 0.7316281/533 [==============>...............] - ETA: 5:35 - loss: 0.9955 - mae: 0.7316282/533 [==============>...............] - ETA: 5:34 - loss: 0.9955 - mae: 0.7316283/533 [==============>...............] - ETA: 5:32 - loss: 0.9955 - mae: 0.7316284/533 [==============>...............] - ETA: 5:31 - loss: 0.9955 - mae: 0.7316285/533 [===============>..............] - ETA: 5:30 - loss: 0.9955 - mae: 0.7316286/533 [===============>..............] - ETA: 5:29 - loss: 0.9955 - mae: 0.7316287/533 [===============>..............] - ETA: 5:27 - loss: 0.9955 - mae: 0.7316288/533 [===============>..............] - ETA: 5:26 - loss: 0.9954 - mae: 0.7316289/533 [===============>..............] - ETA: 5:25 - loss: 0.9954 - mae: 0.7316290/533 [===============>..............] - ETA: 5:24 - loss: 0.9954 - mae: 0.7316291/533 [===============>..............] - ETA: 5:22 - loss: 0.9954 - mae: 0.7316292/533 [===============>..............] - ETA: 5:21 - loss: 0.9954 - mae: 0.7316293/533 [===============>..............] - ETA: 5:20 - loss: 0.9954 - mae: 0.7316294/533 [===============>..............] - ETA: 5:18 - loss: 0.9954 - mae: 0.7316295/533 [===============>..............] - ETA: 5:17 - loss: 0.9954 - mae: 0.7315296/533 [===============>..............] - ETA: 5:16 - loss: 0.9954 - mae: 0.7315297/533 [===============>..............] - ETA: 5:14 - loss: 0.9953 - mae: 0.7315298/533 [===============>..............] - ETA: 5:13 - loss: 0.9953 - mae: 0.7315299/533 [===============>..............] - ETA: 5:12 - loss: 0.9953 - mae: 0.7315300/533 [===============>..............] - ETA: 5:10 - loss: 0.9953 - mae: 0.7315301/533 [===============>..............] - ETA: 5:09 - loss: 0.9953 - mae: 0.7315302/533 [===============>..............] - ETA: 5:08 - loss: 0.9953 - mae: 0.7315303/533 [================>.............] - ETA: 5:06 - loss: 0.9953 - mae: 0.7315304/533 [================>.............] - ETA: 5:05 - loss: 0.9953 - mae: 0.7315305/533 [================>.............] - ETA: 5:04 - loss: 0.9953 - mae: 0.7315306/533 [================>.............] - ETA: 5:02 - loss: 0.9953 - mae: 0.7315307/533 [================>.............] - ETA: 5:01 - loss: 0.9952 - mae: 0.7315308/533 [================>.............] - ETA: 5:00 - loss: 0.9952 - mae: 0.7315309/533 [================>.............] - ETA: 4:58 - loss: 0.9952 - mae: 0.7315310/533 [================>.............] - ETA: 4:57 - loss: 0.9952 - mae: 0.7315311/533 [================>.............] - ETA: 4:56 - loss: 0.9952 - mae: 0.7315312/533 [================>.............] - ETA: 4:54 - loss: 0.9952 - mae: 0.7315313/533 [================>.............] - ETA: 4:53 - loss: 0.9952 - mae: 0.7315314/533 [================>.............] - ETA: 4:52 - loss: 0.9952 - mae: 0.7315315/533 [================>.............] - ETA: 4:50 - loss: 0.9952 - mae: 0.7315316/533 [================>.............] - ETA: 4:49 - loss: 0.9952 - mae: 0.7315317/533 [================>.............] - ETA: 4:48 - loss: 0.9951 - mae: 0.7315318/533 [================>.............] - ETA: 4:47 - loss: 0.9951 - mae: 0.7315319/533 [================>.............] - ETA: 4:45 - loss: 0.9951 - mae: 0.7315320/533 [=================>............] - ETA: 4:44 - loss: 0.9951 - mae: 0.7315321/533 [=================>............] - ETA: 4:43 - loss: 0.9951 - mae: 0.7315322/533 [=================>............] - ETA: 4:41 - loss: 0.9951 - mae: 0.7315323/533 [=================>............] - ETA: 4:40 - loss: 0.9951 - mae: 0.7315324/533 [=================>............] - ETA: 4:39 - loss: 0.9951 - mae: 0.7315325/533 [=================>............] - ETA: 4:37 - loss: 0.9951 - mae: 0.7315326/533 [=================>............] - ETA: 4:36 - loss: 0.9950 - mae: 0.7315327/533 [=================>............] - ETA: 4:35 - loss: 0.9950 - mae: 0.7314328/533 [=================>............] - ETA: 4:33 - loss: 0.9950 - mae: 0.7314329/533 [=================>............] - ETA: 4:32 - loss: 0.9950 - mae: 0.7314330/533 [=================>............] - ETA: 4:31 - loss: 0.9950 - mae: 0.7314331/533 [=================>............] - ETA: 4:29 - loss: 0.9950 - mae: 0.7314332/533 [=================>............] - ETA: 4:28 - loss: 0.9950 - mae: 0.7314333/533 [=================>............] - ETA: 4:27 - loss: 0.9950 - mae: 0.7314334/533 [=================>............] - ETA: 4:25 - loss: 0.9950 - mae: 0.7314335/533 [=================>............] - ETA: 4:24 - loss: 0.9950 - mae: 0.7314336/533 [=================>............] - ETA: 4:23 - loss: 0.9950 - mae: 0.7314337/533 [=================>............] - ETA: 4:21 - loss: 0.9949 - mae: 0.7314338/533 [==================>...........] - ETA: 4:20 - loss: 0.9949 - mae: 0.7314339/533 [==================>...........] - ETA: 4:19 - loss: 0.9949 - mae: 0.7314340/533 [==================>...........] - ETA: 4:17 - loss: 0.9949 - mae: 0.7314341/533 [==================>...........] - ETA: 4:16 - loss: 0.9949 - mae: 0.7314342/533 [==================>...........] - ETA: 4:15 - loss: 0.9949 - mae: 0.7314343/533 [==================>...........] - ETA: 4:13 - loss: 0.9949 - mae: 0.7314344/533 [==================>...........] - ETA: 4:12 - loss: 0.9949 - mae: 0.7314345/533 [==================>...........] - ETA: 4:11 - loss: 0.9949 - mae: 0.7314346/533 [==================>...........] - ETA: 4:09 - loss: 0.9949 - mae: 0.7314347/533 [==================>...........] - ETA: 4:08 - loss: 0.9948 - mae: 0.7314348/533 [==================>...........] - ETA: 4:06 - loss: 0.9948 - mae: 0.7314349/533 [==================>...........] - ETA: 4:05 - loss: 0.9948 - mae: 0.7314350/533 [==================>...........] - ETA: 4:04 - loss: 0.9948 - mae: 0.7314351/533 [==================>...........] - ETA: 4:02 - loss: 0.9948 - mae: 0.7314352/533 [==================>...........] - ETA: 4:01 - loss: 0.9948 - mae: 0.7314353/533 [==================>...........] - ETA: 4:00 - loss: 0.9948 - mae: 0.7314354/533 [==================>...........] - ETA: 3:58 - loss: 0.9948 - mae: 0.7314355/533 [==================>...........] - ETA: 3:57 - loss: 0.9948 - mae: 0.7314356/533 [===================>..........] - ETA: 3:55 - loss: 0.9948 - mae: 0.7313357/533 [===================>..........] - ETA: 3:54 - loss: 0.9948 - mae: 0.7313358/533 [===================>..........] - ETA: 3:53 - loss: 0.9948 - mae: 0.7313359/533 [===================>..........] - ETA: 3:51 - loss: 0.9948 - mae: 0.7313360/533 [===================>..........] - ETA: 3:50 - loss: 0.9948 - mae: 0.7313361/533 [===================>..........] - ETA: 3:49 - loss: 0.9947 - mae: 0.7313362/533 [===================>..........] - ETA: 3:47 - loss: 0.9947 - mae: 0.7313363/533 [===================>..........] - ETA: 3:46 - loss: 0.9947 - mae: 0.7313364/533 [===================>..........] - ETA: 3:44 - loss: 0.9947 - mae: 0.7313365/533 [===================>..........] - ETA: 3:43 - loss: 0.9947 - mae: 0.7313366/533 [===================>..........] - ETA: 3:42 - loss: 0.9947 - mae: 0.7313367/533 [===================>..........] - ETA: 3:40 - loss: 0.9947 - mae: 0.7313368/533 [===================>..........] - ETA: 3:39 - loss: 0.9947 - mae: 0.7313369/533 [===================>..........] - ETA: 3:38 - loss: 0.9947 - mae: 0.7313370/533 [===================>..........] - ETA: 3:36 - loss: 0.9947 - mae: 0.7313371/533 [===================>..........] - ETA: 3:35 - loss: 0.9947 - mae: 0.7313372/533 [===================>..........] - ETA: 3:33 - loss: 0.9947 - mae: 0.7313373/533 [===================>..........] - ETA: 3:32 - loss: 0.9947 - mae: 0.7313374/533 [====================>.........] - ETA: 3:31 - loss: 0.9947 - mae: 0.7313375/533 [====================>.........] - ETA: 3:29 - loss: 0.9947 - mae: 0.7313376/533 [====================>.........] - ETA: 3:28 - loss: 0.9947 - mae: 0.7313377/533 [====================>.........] - ETA: 3:27 - loss: 0.9947 - mae: 0.7313378/533 [====================>.........] - ETA: 3:25 - loss: 0.9947 - mae: 0.7313379/533 [====================>.........] - ETA: 3:24 - loss: 0.9947 - mae: 0.7313380/533 [====================>.........] - ETA: 3:22 - loss: 0.9947 - mae: 0.7313381/533 [====================>.........] - ETA: 3:21 - loss: 0.9947 - mae: 0.7313382/533 [====================>.........] - ETA: 3:20 - loss: 0.9947 - mae: 0.7313383/533 [====================>.........] - ETA: 3:18 - loss: 0.9946 - mae: 0.7313384/533 [====================>.........] - ETA: 3:17 - loss: 0.9946 - mae: 0.7313385/533 [====================>.........] - ETA: 3:16 - loss: 0.9946 - mae: 0.7313386/533 [====================>.........] - ETA: 3:14 - loss: 0.9946 - mae: 0.7313387/533 [====================>.........] - ETA: 3:13 - loss: 0.9946 - mae: 0.7313388/533 [====================>.........] - ETA: 3:12 - loss: 0.9946 - mae: 0.7313389/533 [====================>.........] - ETA: 3:10 - loss: 0.9946 - mae: 0.7313390/533 [====================>.........] - ETA: 3:09 - loss: 0.9946 - mae: 0.7313391/533 [=====================>........] - ETA: 3:08 - loss: 0.9946 - mae: 0.7313392/533 [=====================>........] - ETA: 3:06 - loss: 0.9946 - mae: 0.7313393/533 [=====================>........] - ETA: 3:05 - loss: 0.9946 - mae: 0.7313394/533 [=====================>........] - ETA: 3:04 - loss: 0.9946 - mae: 0.7313395/533 [=====================>........] - ETA: 3:02 - loss: 0.9946 - mae: 0.7313396/533 [=====================>........] - ETA: 3:01 - loss: 0.9946 - mae: 0.7313397/533 [=====================>........] - ETA: 3:00 - loss: 0.9946 - mae: 0.7313398/533 [=====================>........] - ETA: 2:58 - loss: 0.9946 - mae: 0.7313399/533 [=====================>........] - ETA: 2:57 - loss: 0.9946 - mae: 0.7313400/533 [=====================>........] - ETA: 2:56 - loss: 0.9946 - mae: 0.7313401/533 [=====================>........] - ETA: 2:54 - loss: 0.9946 - mae: 0.7313402/533 [=====================>........] - ETA: 2:53 - loss: 0.9946 - mae: 0.7313403/533 [=====================>........] - ETA: 2:52 - loss: 0.9946 - mae: 0.7313404/533 [=====================>........] - ETA: 2:50 - loss: 0.9946 - mae: 0.7313405/533 [=====================>........] - ETA: 2:49 - loss: 0.9946 - mae: 0.7313406/533 [=====================>........] - ETA: 2:48 - loss: 0.9946 - mae: 0.7313407/533 [=====================>........] - ETA: 2:46 - loss: 0.9946 - mae: 0.7313408/533 [=====================>........] - ETA: 2:45 - loss: 0.9946 - mae: 0.7313409/533 [======================>.......] - ETA: 2:44 - loss: 0.9946 - mae: 0.7313410/533 [======================>.......] - ETA: 2:42 - loss: 0.9946 - mae: 0.7313411/533 [======================>.......] - ETA: 2:41 - loss: 0.9946 - mae: 0.7313412/533 [======================>.......] - ETA: 2:40 - loss: 0.9946 - mae: 0.7313413/533 [======================>.......] - ETA: 2:38 - loss: 0.9946 - mae: 0.7313414/533 [======================>.......] - ETA: 2:37 - loss: 0.9946 - mae: 0.7313415/533 [======================>.......] - ETA: 2:36 - loss: 0.9946 - mae: 0.7313416/533 [======================>.......] - ETA: 2:34 - loss: 0.9946 - mae: 0.7313417/533 [======================>.......] - ETA: 2:33 - loss: 0.9946 - mae: 0.7313418/533 [======================>.......] - ETA: 2:32 - loss: 0.9946 - mae: 0.7313419/533 [======================>.......] - ETA: 2:30 - loss: 0.9946 - mae: 0.7313420/533 [======================>.......] - ETA: 2:29 - loss: 0.9946 - mae: 0.7313421/533 [======================>.......] - ETA: 2:28 - loss: 0.9946 - mae: 0.7313422/533 [======================>.......] - ETA: 2:26 - loss: 0.9946 - mae: 0.7313423/533 [======================>.......] - ETA: 2:25 - loss: 0.9946 - mae: 0.7313424/533 [======================>.......] - ETA: 2:23 - loss: 0.9946 - mae: 0.7313425/533 [======================>.......] - ETA: 2:22 - loss: 0.9946 - mae: 0.7313426/533 [======================>.......] - ETA: 2:21 - loss: 0.9946 - mae: 0.7312427/533 [=======================>......] - ETA: 2:19 - loss: 0.9946 - mae: 0.7312428/533 [=======================>......] - ETA: 2:18 - loss: 0.9946 - mae: 0.7312429/533 [=======================>......] - ETA: 2:17 - loss: 0.9946 - mae: 0.7312430/533 [=======================>......] - ETA: 2:15 - loss: 0.9946 - mae: 0.7312431/533 [=======================>......] - ETA: 2:14 - loss: 0.9946 - mae: 0.7312432/533 [=======================>......] - ETA: 2:13 - loss: 0.9946 - mae: 0.7312433/533 [=======================>......] - ETA: 2:11 - loss: 0.9946 - mae: 0.7312434/533 [=======================>......] - ETA: 2:10 - loss: 0.9946 - mae: 0.7312435/533 [=======================>......] - ETA: 2:09 - loss: 0.9946 - mae: 0.7312436/533 [=======================>......] - ETA: 2:07 - loss: 0.9946 - mae: 0.7312437/533 [=======================>......] - ETA: 2:06 - loss: 0.9946 - mae: 0.7312438/533 [=======================>......] - ETA: 2:05 - loss: 0.9946 - mae: 0.7312439/533 [=======================>......] - ETA: 2:03 - loss: 0.9946 - mae: 0.7312440/533 [=======================>......] - ETA: 2:02 - loss: 0.9946 - mae: 0.7312441/533 [=======================>......] - ETA: 2:01 - loss: 0.9946 - mae: 0.7312442/533 [=======================>......] - ETA: 2:00 - loss: 0.9946 - mae: 0.7312443/533 [=======================>......] - ETA: 1:58 - loss: 0.9946 - mae: 0.7312444/533 [=======================>......] - ETA: 1:57 - loss: 0.9946 - mae: 0.7312445/533 [========================>.....] - ETA: 1:55 - loss: 0.9946 - mae: 0.7312446/533 [========================>.....] - ETA: 1:54 - loss: 0.9946 - mae: 0.7312447/533 [========================>.....] - ETA: 1:53 - loss: 0.9946 - mae: 0.7312448/533 [========================>.....] - ETA: 1:52 - loss: 0.9946 - mae: 0.7312449/533 [========================>.....] - ETA: 1:50 - loss: 0.9946 - mae: 0.7312450/533 [========================>.....] - ETA: 1:49 - loss: 0.9946 - mae: 0.7312451/533 [========================>.....] - ETA: 1:48 - loss: 0.9946 - mae: 0.7312452/533 [========================>.....] - ETA: 1:46 - loss: 0.9946 - mae: 0.7312453/533 [========================>.....] - ETA: 1:45 - loss: 0.9946 - mae: 0.7312454/533 [========================>.....] - ETA: 1:44 - loss: 0.9946 - mae: 0.7312455/533 [========================>.....] - ETA: 1:42 - loss: 0.9946 - mae: 0.7312456/533 [========================>.....] - ETA: 1:41 - loss: 0.9946 - mae: 0.7312457/533 [========================>.....] - ETA: 1:40 - loss: 0.9946 - mae: 0.7312458/533 [========================>.....] - ETA: 1:38 - loss: 0.9946 - mae: 0.7312459/533 [========================>.....] - ETA: 1:37 - loss: 0.9945 - mae: 0.7312460/533 [========================>.....] - ETA: 1:36 - loss: 0.9945 - mae: 0.7312461/533 [========================>.....] - ETA: 1:34 - loss: 0.9945 - mae: 0.7312462/533 [=========================>....] - ETA: 1:33 - loss: 0.9945 - mae: 0.7312463/533 [=========================>....] - ETA: 1:32 - loss: 0.9945 - mae: 0.7312464/533 [=========================>....] - ETA: 1:30 - loss: 0.9945 - mae: 0.7312465/533 [=========================>....] - ETA: 1:29 - loss: 0.9945 - mae: 0.7312466/533 [=========================>....] - ETA: 1:28 - loss: 0.9945 - mae: 0.7312467/533 [=========================>....] - ETA: 1:26 - loss: 0.9945 - mae: 0.7312468/533 [=========================>....] - ETA: 1:25 - loss: 0.9945 - mae: 0.7312469/533 [=========================>....] - ETA: 1:24 - loss: 0.9945 - mae: 0.7312470/533 [=========================>....] - ETA: 1:22 - loss: 0.9945 - mae: 0.7312471/533 [=========================>....] - ETA: 1:21 - loss: 0.9945 - mae: 0.7312472/533 [=========================>....] - ETA: 1:20 - loss: 0.9945 - mae: 0.7312473/533 [=========================>....] - ETA: 1:18 - loss: 0.9945 - mae: 0.7312474/533 [=========================>....] - ETA: 1:17 - loss: 0.9945 - mae: 0.7312475/533 [=========================>....] - ETA: 1:16 - loss: 0.9945 - mae: 0.7312476/533 [=========================>....] - ETA: 1:14 - loss: 0.9945 - mae: 0.7312477/533 [=========================>....] - ETA: 1:13 - loss: 0.9945 - mae: 0.7312478/533 [=========================>....] - ETA: 1:12 - loss: 0.9945 - mae: 0.7312479/533 [=========================>....] - ETA: 1:10 - loss: 0.9945 - mae: 0.7312480/533 [==========================>...] - ETA: 1:09 - loss: 0.9945 - mae: 0.7312481/533 [==========================>...] - ETA: 1:08 - loss: 0.9945 - mae: 0.7312482/533 [==========================>...] - ETA: 1:06 - loss: 0.9945 - mae: 0.7312483/533 [==========================>...] - ETA: 1:05 - loss: 0.9945 - mae: 0.7312484/533 [==========================>...] - ETA: 1:04 - loss: 0.9945 - mae: 0.7312485/533 [==========================>...] - ETA: 1:03 - loss: 0.9945 - mae: 0.7312486/533 [==========================>...] - ETA: 1:01 - loss: 0.9945 - mae: 0.7312487/533 [==========================>...] - ETA: 1:00 - loss: 0.9945 - mae: 0.7312488/533 [==========================>...] - ETA: 59s - loss: 0.9945 - mae: 0.7312 489/533 [==========================>...] - ETA: 57s - loss: 0.9945 - mae: 0.7312490/533 [==========================>...] - ETA: 56s - loss: 0.9945 - mae: 0.7312491/533 [==========================>...] - ETA: 55s - loss: 0.9945 - mae: 0.7312492/533 [==========================>...] - ETA: 53s - loss: 0.9945 - mae: 0.7312493/533 [==========================>...] - ETA: 52s - loss: 0.9945 - mae: 0.7312494/533 [==========================>...] - ETA: 51s - loss: 0.9945 - mae: 0.7312495/533 [==========================>...] - ETA: 49s - loss: 0.9945 - mae: 0.7312496/533 [==========================>...] - ETA: 48s - loss: 0.9945 - mae: 0.7312497/533 [==========================>...] - ETA: 47s - loss: 0.9945 - mae: 0.7312498/533 [===========================>..] - ETA: 45s - loss: 0.9945 - mae: 0.7312499/533 [===========================>..] - ETA: 44s - loss: 0.9945 - mae: 0.7312500/533 [===========================>..] - ETA: 43s - loss: 0.9945 - mae: 0.7312501/533 [===========================>..] - ETA: 42s - loss: 0.9945 - mae: 0.7312502/533 [===========================>..] - ETA: 40s - loss: 0.9945 - mae: 0.7312503/533 [===========================>..] - ETA: 39s - loss: 0.9945 - mae: 0.7312504/533 [===========================>..] - ETA: 38s - loss: 0.9945 - mae: 0.7312505/533 [===========================>..] - ETA: 36s - loss: 0.9945 - mae: 0.7312506/533 [===========================>..] - ETA: 35s - loss: 0.9945 - mae: 0.7312507/533 [===========================>..] - ETA: 34s - loss: 0.9945 - mae: 0.7312508/533 [===========================>..] - ETA: 32s - loss: 0.9945 - mae: 0.7312509/533 [===========================>..] - ETA: 31s - loss: 0.9944 - mae: 0.7312510/533 [===========================>..] - ETA: 30s - loss: 0.9944 - mae: 0.7312511/533 [===========================>..] - ETA: 28s - loss: 0.9944 - mae: 0.7312512/533 [===========================>..] - ETA: 27s - loss: 0.9944 - mae: 0.7312513/533 [===========================>..] - ETA: 26s - loss: 0.9944 - mae: 0.7312514/533 [===========================>..] - ETA: 24s - loss: 0.9944 - mae: 0.7312515/533 [===========================>..] - ETA: 23s - loss: 0.9944 - mae: 0.7312516/533 [============================>.] - ETA: 22s - loss: 0.9944 - mae: 0.7312517/533 [============================>.] - ETA: 20s - loss: 0.9944 - mae: 0.7312518/533 [============================>.] - ETA: 19s - loss: 0.9944 - mae: 0.7312519/533 [============================>.] - ETA: 18s - loss: 0.9944 - mae: 0.7312520/533 [============================>.] - ETA: 17s - loss: 0.9944 - mae: 0.7312521/533 [============================>.] - ETA: 15s - loss: 0.9944 - mae: 0.7312522/533 [============================>.] - ETA: 14s - loss: 0.9944 - mae: 0.7312523/533 [============================>.] - ETA: 13s - loss: 0.9944 - mae: 0.7312524/533 [============================>.] - ETA: 11s - loss: 0.9944 - mae: 0.7312525/533 [============================>.] - ETA: 10s - loss: 0.9944 - mae: 0.7312526/533 [============================>.] - ETA: 9s - loss: 0.9944 - mae: 0.7312 527/533 [============================>.] - ETA: 7s - loss: 0.9944 - mae: 0.7312528/533 [============================>.] - ETA: 6s - loss: 0.9944 - mae: 0.7312529/533 [============================>.] - ETA: 5s - loss: 0.9944 - mae: 0.7312530/533 [============================>.] - ETA: 3s - loss: 0.9944 - mae: 0.7312531/533 [============================>.] - ETA: 2s - loss: 0.9944 - mae: 0.7312532/533 [============================>.] - ETA: 1s - loss: 0.9944 - mae: 0.7312533/533 [==============================] - ETA: 0s - loss: 0.9944 - mae: 0.7312533/533 [==============================] - 731s 1s/step - loss: 0.9944 - mae: 0.7312

654/654 - 407s
DataSource(891c8e2fb49b4c33b8691613eb320a5aT)

收益率12.2%
年化收益率12.63%
基准收益率-11.28%
阿尔法0.34
贝塔1.18
夏普比率0.44
胜率0.54
盈亏比0.96
收益波动率32.31%
信息比率0.09
最大回撤22.81%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-bb596a46a46e4a7691e0b296f4a6c0c7"}/bigcharts-data-end

In [6]:

m10.data.read()["x"].shape

Out[6]:

(669547, 10)