评价此页
★ ★ ★ ★ ★
beginner/chatbot_tutorial

注意

转到结尾下载完整的示例代码。

聊天机器人教程#

创建日期：2018年8月14日 | 最后更新日期：2025年1月24日 | 最后验证日期：2024年11月5日

作者：Matthew Inkawhich

在本教程中，我们将探讨循环序列到序列模型的一个有趣用例。我们将使用康奈尔电影对话语料库中的电影剧本训练一个简单的聊天机器人。

对话模型是人工智能研究中的一个热门话题。聊天机器人可见于各种场景，包括客户服务应用和在线帮助台。这些机器人通常由基于检索的模型驱动，这些模型对特定形式的问题输出预定义的响应。在像公司IT帮助台这样高度受限的领域，这些模型可能已经足够，但它们对于更普遍的用例来说不够健壮。教会机器在多个领域与人类进行有意义的对话，是一个远未解决的研究问题。最近，深度学习的蓬勃发展催生了像谷歌的神经对话模型这样强大的生成模型，这标志着向多领域生成式对话模型迈出了一大步。在本教程中，我们将在PyTorch中实现这种模型。

bot 
> hello?
Bot: hello .
> where am I?
Bot: you re in a hospital .
> who are you?
Bot: i m a lawyer .
> how are you doing?
Bot: i m fine .
> are you my friend?
Bot: no .
> you're under arrest
Bot: i m trying to help you !
> i'm just kidding
Bot: i m sorry .
> where are you from?
Bot: san francisco .
> it's time for me to leave
Bot: i know .
> goodbye
Bot: goodbye .

教程要点

  • 处理康奈尔电影对话语料库数据集的加载和预处理

  • 使用Luong注意力机制实现序列到序列模型

  • 使用小批量数据联合训练编码器和解码器模型

  • 实现贪心搜索解码模块

  • 与训练好的聊天机器人互动

致谢

本教程借鉴了以下来源的代码：

  1. Yuan-Kuei Wu 的 pytorch-chatbot 实现：ywk991112/pytorch-chatbot

  2. Sean Robertson的practical-pytorch seq2seq-translation示例：spro/practical-pytorch

  3. FloydHub Cornell Movie Corpus 预处理代码：floydhub/textutil-preprocess-cornell-movie-corpus

准备工作#

要开始，请下载电影对话语料库的zip文件。

# and put in a ``data/`` directory under the current directory.
#
# After that, let’s import some necessities.
#

import torch
from torch.jit import script, trace
import torch.nn as nn
from torch import optim
import torch.nn.functional as F
import csv
import random
import re
import os
import unicodedata
import codecs
from io import open
import itertools
import math
import json


# If the current `accelerator <https://pytorch.ac.cn/docs/stable/torch.html#accelerators>`__ is available,
# we will use it. Otherwise, we use the CPU.
device = torch.accelerator.current_accelerator().type if torch.accelerator.is_available() else "cpu"
print(f"Using {device} device")

Using cuda device

加载和预处理数据#

下一步是重新格式化我们的数据文件，并将数据加载到我们可以使用的结构中。

康奈尔电影对话语料库是一个包含丰富电影角色对话的数据集：

  • 10,292对电影角色之间的220,579次对话交流

  • 来自617部电影的9,035个角色

  • 总共304,713句对白

该数据集庞大且多样，语言的正式性、时间段、情感等方面存在很大差异。我们希望这种多样性使我们的模型对多种形式的输入和查询具有鲁棒性。

首先，我们来看一下数据文件的几行，以了解其原始格式。

corpus_name = "movie-corpus"
corpus = os.path.join("data", corpus_name)

def printLines(file, n=10):
    with open(file, 'rb') as datafile:
        lines = datafile.readlines()
    for line in lines[:n]:
        print(line)

printLines(os.path.join(corpus, "utterances.jsonl"))

b'{"id": "L1045", "conversation_id": "L1044", "text": "They do not!", "speaker": "u0", "meta": {"movie_id": "m0", "parsed": [{"rt": 1, "toks": [{"tok": "They", "tag": "PRP", "dep": "nsubj", "up": 1, "dn": []}, {"tok": "do", "tag": "VBP", "dep": "ROOT", "dn": [0, 2, 3]}, {"tok": "not", "tag": "RB", "dep": "neg", "up": 1, "dn": []}, {"tok": "!", "tag": ".", "dep": "punct", "up": 1, "dn": []}]}]}, "reply-to": "L1044", "timestamp": null, "vectors": []}\n'
b'{"id": "L1044", "conversation_id": "L1044", "text": "They do to!", "speaker": "u2", "meta": {"movie_id": "m0", "parsed": [{"rt": 1, "toks": [{"tok": "They", "tag": "PRP", "dep": "nsubj", "up": 1, "dn": []}, {"tok": "do", "tag": "VBP", "dep": "ROOT", "dn": [0, 2, 3]}, {"tok": "to", "tag": "TO", "dep": "dobj", "up": 1, "dn": []}, {"tok": "!", "tag": ".", "dep": "punct", "up": 1, "dn": []}]}]}, "reply-to": null, "timestamp": null, "vectors": []}\n'
b'{"id": "L985", "conversation_id": "L984", "text": "I hope so.", "speaker": "u0", "meta": {"movie_id": "m0", "parsed": [{"rt": 1, "toks": [{"tok": "I", "tag": "PRP", "dep": "nsubj", "up": 1, "dn": []}, {"tok": "hope", "tag": "VBP", "dep": "ROOT", "dn": [0, 2, 3]}, {"tok": "so", "tag": "RB", "dep": "advmod", "up": 1, "dn": []}, {"tok": ".", "tag": ".", "dep": "punct", "up": 1, "dn": []}]}]}, "reply-to": "L984", "timestamp": null, "vectors": []}\n'
b'{"id": "L984", "conversation_id": "L984", "text": "She okay?", "speaker": "u2", "meta": {"movie_id": "m0", "parsed": [{"rt": 1, "toks": [{"tok": "She", "tag": "PRP", "dep": "nsubj", "up": 1, "dn": []}, {"tok": "okay", "tag": "RB", "dep": "ROOT", "dn": [0, 2]}, {"tok": "?", "tag": ".", "dep": "punct", "up": 1, "dn": []}]}]}, "reply-to": null, "timestamp": null, "vectors": []}\n'
b'{"id": "L925", "conversation_id": "L924", "text": "Let\'s go.", "speaker": "u0", "meta": {"movie_id": "m0", "parsed": [{"rt": 0, "toks": [{"tok": "Let", "tag": "VB", "dep": "ROOT", "dn": [2, 3]}, {"tok": "\'s", "tag": "PRP", "dep": "nsubj", "up": 2, "dn": []}, {"tok": "go", "tag": "VB", "dep": "ccomp", "up": 0, "dn": [1]}, {"tok": ".", "tag": ".", "dep": "punct", "up": 0, "dn": []}]}]}, "reply-to": "L924", "timestamp": null, "vectors": []}\n'
b'{"id": "L924", "conversation_id": "L924", "text": "Wow", "speaker": "u2", "meta": {"movie_id": "m0", "parsed": [{"rt": 0, "toks": [{"tok": "Wow", "tag": "UH", "dep": "ROOT", "dn": []}]}]}, "reply-to": null, "timestamp": null, "vectors": []}\n'
b'{"id": "L872", "conversation_id": "L870", "text": "Okay -- you\'re gonna need to learn how to lie.", "speaker": "u0", "meta": {"movie_id": "m0", "parsed": [{"rt": 4, "toks": [{"tok": "Okay", "tag": "UH", "dep": "intj", "up": 4, "dn": []}, {"tok": "--", "tag": ":", "dep": "punct", "up": 4, "dn": []}, {"tok": "you", "tag": "PRP", "dep": "nsubj", "up": 4, "dn": []}, {"tok": "\'re", "tag": "VBP", "dep": "aux", "up": 4, "dn": []}, {"tok": "gon", "tag": "VBG", "dep": "ROOT", "dn": [0, 1, 2, 3, 6, 12]}, {"tok": "na", "tag": "TO", "dep": "aux", "up": 6, "dn": []}, {"tok": "need", "tag": "VB", "dep": "xcomp", "up": 4, "dn": [5, 8]}, {"tok": "to", "tag": "TO", "dep": "aux", "up": 8, "dn": []}, {"tok": "learn", "tag": "VB", "dep": "xcomp", "up": 6, "dn": [7, 11]}, {"tok": "how", "tag": "WRB", "dep": "advmod", "up": 11, "dn": []}, {"tok": "to", "tag": "TO", "dep": "aux", "up": 11, "dn": []}, {"tok": "lie", "tag": "VB", "dep": "xcomp", "up": 8, "dn": [9, 10]}, {"tok": ".", "tag": ".", "dep": "punct", "up": 4, "dn": []}]}]}, "reply-to": "L871", "timestamp": null, "vectors": []}\n'
b'{"id": "L871", "conversation_id": "L870", "text": "No", "speaker": "u2", "meta": {"movie_id": "m0", "parsed": [{"rt": 0, "toks": [{"tok": "No", "tag": "UH", "dep": "ROOT", "dn": []}]}]}, "reply-to": "L870", "timestamp": null, "vectors": []}\n'
b'{"id": "L870", "conversation_id": "L870", "text": "I\'m kidding.  You know how sometimes you just become this \\"persona\\"?  And you don\'t know how to quit?", "speaker": "u0", "meta": {"movie_id": "m0", "parsed": [{"rt": 2, "toks": [{"tok": "I", "tag": "PRP", "dep": "nsubj", "up": 2, "dn": []}, {"tok": "\'m", "tag": "VBP", "dep": "aux", "up": 2, "dn": []}, {"tok": "kidding", "tag": "VBG", "dep": "ROOT", "dn": [0, 1, 3]}, {"tok": ".", "tag": ".", "dep": "punct", "up": 2, "dn": [4]}, {"tok": " ", "tag": "_SP", "dep": "", "up": 3, "dn": []}]}, {"rt": 1, "toks": [{"tok": "You", "tag": "PRP", "dep": "nsubj", "up": 1, "dn": []}, {"tok": "know", "tag": "VBP", "dep": "ROOT", "dn": [0, 6, 11]}, {"tok": "how", "tag": "WRB", "dep": "advmod", "up": 3, "dn": []}, {"tok": "sometimes", "tag": "RB", "dep": "advmod", "up": 6, "dn": [2]}, {"tok": "you", "tag": "PRP", "dep": "nsubj", "up": 6, "dn": []}, {"tok": "just", "tag": "RB", "dep": "advmod", "up": 6, "dn": []}, {"tok": "become", "tag": "VBP", "dep": "ccomp", "up": 1, "dn": [3, 4, 5, 9]}, {"tok": "this", "tag": "DT", "dep": "det", "up": 9, "dn": []}, {"tok": "\\"", "tag": "``", "dep": "punct", "up": 9, "dn": []}, {"tok": "persona", "tag": "NN", "dep": "attr", "up": 6, "dn": [7, 8, 10]}, {"tok": "\\"", "tag": "\'\'", "dep": "punct", "up": 9, "dn": []}, {"tok": "?", "tag": ".", "dep": "punct", "up": 1, "dn": [12]}, {"tok": " ", "tag": "_SP", "dep": "", "up": 11, "dn": []}]}, {"rt": 4, "toks": [{"tok": "And", "tag": "CC", "dep": "cc", "up": 4, "dn": []}, {"tok": "you", "tag": "PRP", "dep": "nsubj", "up": 4, "dn": []}, {"tok": "do", "tag": "VBP", "dep": "aux", "up": 4, "dn": []}, {"tok": "n\'t", "tag": "RB", "dep": "neg", "up": 4, "dn": []}, {"tok": "know", "tag": "VB", "dep": "ROOT", "dn": [0, 1, 2, 3, 7, 8]}, {"tok": "how", "tag": "WRB", "dep": "advmod", "up": 7, "dn": []}, {"tok": "to", "tag": "TO", "dep": "aux", "up": 7, "dn": []}, {"tok": "quit", "tag": "VB", "dep": "xcomp", "up": 4, "dn": [5, 6]}, {"tok": "?", "tag": ".", "dep": "punct", "up": 4, "dn": []}]}]}, "reply-to": null, "timestamp": null, "vectors": []}\n'
b'{"id": "L869", "conversation_id": "L866", "text": "Like my fear of wearing pastels?", "speaker": "u0", "meta": {"movie_id": "m0", "parsed": [{"rt": 0, "toks": [{"tok": "Like", "tag": "IN", "dep": "ROOT", "dn": [2, 6]}, {"tok": "my", "tag": "PRP$", "dep": "poss", "up": 2, "dn": []}, {"tok": "fear", "tag": "NN", "dep": "pobj", "up": 0, "dn": [1, 3]}, {"tok": "of", "tag": "IN", "dep": "prep", "up": 2, "dn": [4]}, {"tok": "wearing", "tag": "VBG", "dep": "pcomp", "up": 3, "dn": [5]}, {"tok": "pastels", "tag": "NNS", "dep": "dobj", "up": 4, "dn": []}, {"tok": "?", "tag": ".", "dep": "punct", "up": 0, "dn": []}]}]}, "reply-to": "L868", "timestamp": null, "vectors": []}\n'

创建格式化数据文件#

为方便起见，我们将创建一个格式良好的数据文件，其中每行包含一个以制表符分隔的*查询句子*和*响应句子*对。

以下函数有助于解析原始的 utterances.jsonl 数据文件。

  • loadLinesAndConversations 将文件的每一行分割成一个包含字段的行字典：lineID、characterID 和文本，然后将它们分组为包含字段的对话：conversationID、movieID 和行。

  • extractSentencePairs 从对话中提取句子对。

# Splits each line of the file to create lines and conversations
def loadLinesAndConversations(fileName):
    lines = {}
    conversations = {}
    with open(fileName, 'r', encoding='iso-8859-1') as f:
        for line in f:
            lineJson = json.loads(line)
            # Extract fields for line object
            lineObj = {}
            lineObj["lineID"] = lineJson["id"]
            lineObj["characterID"] = lineJson["speaker"]
            lineObj["text"] = lineJson["text"]
            lines[lineObj['lineID']] = lineObj

            # Extract fields for conversation object
            if lineJson["conversation_id"] not in conversations:
                convObj = {}
                convObj["conversationID"] = lineJson["conversation_id"]
                convObj["movieID"] = lineJson["meta"]["movie_id"]
                convObj["lines"] = [lineObj]
            else:
                convObj = conversations[lineJson["conversation_id"]]
                convObj["lines"].insert(0, lineObj)
            conversations[convObj["conversationID"]] = convObj

    return lines, conversations


# Extracts pairs of sentences from conversations
def extractSentencePairs(conversations):
    qa_pairs = []
    for conversation in conversations.values():
        # Iterate over all the lines of the conversation
        for i in range(len(conversation["lines"]) - 1):  # We ignore the last line (no answer for it)
            inputLine = conversation["lines"][i]["text"].strip()
            targetLine = conversation["lines"][i+1]["text"].strip()
            # Filter wrong samples (if one of the lists is empty)
            if inputLine and targetLine:
                qa_pairs.append([inputLine, targetLine])
    return qa_pairs

现在我们将调用这些函数并创建文件。我们将其命名为 formatted_movie_lines.txt。

# Define path to new file
datafile = os.path.join(corpus, "formatted_movie_lines.txt")

delimiter = '\t'
# Unescape the delimiter
delimiter = str(codecs.decode(delimiter, "unicode_escape"))

# Initialize lines dict and conversations dict
lines = {}
conversations = {}
# Load lines and conversations
print("\nProcessing corpus into lines and conversations...")
lines, conversations = loadLinesAndConversations(os.path.join(corpus, "utterances.jsonl"))

# Write new csv file
print("\nWriting newly formatted file...")
with open(datafile, 'w', encoding='utf-8') as outputfile:
    writer = csv.writer(outputfile, delimiter=delimiter, lineterminator='\n')
    for pair in extractSentencePairs(conversations):
        writer.writerow(pair)

# Print a sample of lines
print("\nSample lines from file:")
printLines(datafile)

Processing corpus into lines and conversations...

Writing newly formatted file...

Sample lines from file:
b'They do to!\tThey do not!\n'
b'She okay?\tI hope so.\n'
b"Wow\tLet's go.\n"
b'"I\'m kidding.  You know how sometimes you just become this ""persona""?  And you don\'t know how to quit?"\tNo\n'
b"No\tOkay -- you're gonna need to learn how to lie.\n"
b"I figured you'd get to the good stuff eventually.\tWhat good stuff?\n"
b'What good stuff?\t"The ""real you""."\n'
b'"The ""real you""."\tLike my fear of wearing pastels?\n'
b'do you listen to this crap?\tWhat crap?\n'
b"What crap?\tMe.  This endless ...blonde babble. I'm like, boring myself.\n"

加载和修剪数据#

我们的下一个任务是创建一个词汇表，并将查询/响应句子对加载到内存中。

请注意，我们处理的是**单词**序列，它们没有到离散数值空间的隐式映射。因此，我们必须通过将数据集中遇到的每个唯一单词映射到一个索引值来创建一个映射。

为此，我们定义了一个 Voc 类，它维护一个从单词到索引的映射、一个从索引到单词的反向映射、每个单词的计数以及总词数。该类提供了将单词添加到词汇表（addWord）、添加句子中的所有单词（addSentence）和修剪不常见单词（trim）的方法。关于修剪的更多内容将在稍后介绍。

# Default word tokens
PAD_token = 0  # Used for padding short sentences
SOS_token = 1  # Start-of-sentence token
EOS_token = 2  # End-of-sentence token

class Voc:
    def __init__(self, name):
        self.name = name
        self.trimmed = False
        self.word2index = {}
        self.word2count = {}
        self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"}
        self.num_words = 3  # Count SOS, EOS, PAD

    def addSentence(self, sentence):
        for word in sentence.split(' '):
            self.addWord(word)

    def addWord(self, word):
        if word not in self.word2index:
            self.word2index[word] = self.num_words
            self.word2count[word] = 1
            self.index2word[self.num_words] = word
            self.num_words += 1
        else:
            self.word2count[word] += 1

    # Remove words below a certain count threshold
    def trim(self, min_count):
        if self.trimmed:
            return
        self.trimmed = True

        keep_words = []

        for k, v in self.word2count.items():
            if v >= min_count:
                keep_words.append(k)

        print('keep_words {} / {} = {:.4f}'.format(
            len(keep_words), len(self.word2index), len(keep_words) / len(self.word2index)
        ))

        # Reinitialize dictionaries
        self.word2index = {}
        self.word2count = {}
        self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"}
        self.num_words = 3 # Count default tokens

        for word in keep_words:
            self.addWord(word)

现在我们可以组建我们的词汇表和查询/响应句子对。在我们准备好使用这些数据之前，我们必须进行一些预处理。

首先，我们必须使用 unicodeToAscii 将Unicode字符串转换为ASCII。接下来，我们应该将所有字母转换为小写，并修剪掉除基本标点符号外的所有非字母字符（normalizeString）。最后，为了帮助训练收敛，我们将过滤掉长度大于 MAX_LENGTH 阈值的句子（filterPairs）。

MAX_LENGTH = 10  # Maximum sentence length to consider

# Turn a Unicode string to plain ASCII, thanks to
# https://stackoverflow.com/a/518232/2809427
def unicodeToAscii(s):
    return ''.join(
        c for c in unicodedata.normalize('NFD', s)
        if unicodedata.category(c) != 'Mn'
    )

# Lowercase, trim, and remove non-letter characters
def normalizeString(s):
    s = unicodeToAscii(s.lower().strip())
    s = re.sub(r"([.!?])", r" \1", s)
    s = re.sub(r"[^a-zA-Z.!?]+", r" ", s)
    s = re.sub(r"\s+", r" ", s).strip()
    return s

# Read query/response pairs and return a voc object
def readVocs(datafile, corpus_name):
    print("Reading lines...")
    # Read the file and split into lines
    lines = open(datafile, encoding='utf-8').\
        read().strip().split('\n')
    # Split every line into pairs and normalize
    pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines]
    voc = Voc(corpus_name)
    return voc, pairs

# Returns True if both sentences in a pair 'p' are under the MAX_LENGTH threshold
def filterPair(p):
    # Input sequences need to preserve the last word for EOS token
    return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH

# Filter pairs using the ``filterPair`` condition
def filterPairs(pairs):
    return [pair for pair in pairs if filterPair(pair)]

# Using the functions defined above, return a populated voc object and pairs list
def loadPrepareData(corpus, corpus_name, datafile, save_dir):
    print("Start preparing training data ...")
    voc, pairs = readVocs(datafile, corpus_name)
    print("Read {!s} sentence pairs".format(len(pairs)))
    pairs = filterPairs(pairs)
    print("Trimmed to {!s} sentence pairs".format(len(pairs)))
    print("Counting words...")
    for pair in pairs:
        voc.addSentence(pair[0])
        voc.addSentence(pair[1])
    print("Counted words:", voc.num_words)
    return voc, pairs


# Load/Assemble voc and pairs
save_dir = os.path.join("data", "save")
voc, pairs = loadPrepareData(corpus, corpus_name, datafile, save_dir)
# Print some pairs to validate
print("\npairs:")
for pair in pairs[:10]:
    print(pair)

Start preparing training data ...
Reading lines...
Read 221282 sentence pairs
Trimmed to 64313 sentence pairs
Counting words...
Counted words: 18082

pairs:
['they do to !', 'they do not !']
['she okay ?', 'i hope so .']
['wow', 'let s go .']
['what good stuff ?', 'the real you .']
['the real you .', 'like my fear of wearing pastels ?']
['do you listen to this crap ?', 'what crap ?']
['well no . . .', 'then that s all you had to say .']
['then that s all you had to say .', 'but']
['but', 'you always been this selfish ?']
['have fun tonight ?', 'tons']

另一个有助于在训练期间实现更快收敛的策略是，从我们的词汇表中修剪掉很少使用的单词。减少特征空间也会降低模型必须学习近似的函数的难度。我们将分两步完成此操作：

  1. 使用 voc.trim 函数修剪使用次数低于 MIN_COUNT 阈值的单词。

  2. 过滤掉包含被修剪单词的句子对。

MIN_COUNT = 3    # Minimum word count threshold for trimming

def trimRareWords(voc, pairs, MIN_COUNT):
    # Trim words used under the MIN_COUNT from the voc
    voc.trim(MIN_COUNT)
    # Filter out pairs with trimmed words
    keep_pairs = []
    for pair in pairs:
        input_sentence = pair[0]
        output_sentence = pair[1]
        keep_input = True
        keep_output = True
        # Check input sentence
        for word in input_sentence.split(' '):
            if word not in voc.word2index:
                keep_input = False
                break
        # Check output sentence
        for word in output_sentence.split(' '):
            if word not in voc.word2index:
                keep_output = False
                break

        # Only keep pairs that do not contain trimmed word(s) in their input or output sentence
        if keep_input and keep_output:
            keep_pairs.append(pair)

    print("Trimmed from {} pairs to {}, {:.4f} of total".format(len(pairs), len(keep_pairs), len(keep_pairs) / len(pairs)))
    return keep_pairs


# Trim voc and pairs
pairs = trimRareWords(voc, pairs, MIN_COUNT)

keep_words 7833 / 18079 = 0.4333
Trimmed from 64313 pairs to 53131, 0.8261 of total

为模型准备数据#

尽管我们已经花费了大量精力准备和处理数据，将其整理成一个漂亮的词汇表对象和句子对列表，但我们的模型最终期望的是数值化的torch张量作为输入。在seq2seq翻译教程中可以找到一种为模型准备处理后数据的方法。在该教程中，我们使用的批大小为1，这意味着我们所要做的就是将句子对中的单词转换为词汇表中对应的索引，然后将其输入模型。

然而，如果您有兴趣加快训练速度和/或希望利用GPU的并行化能力，您将需要使用小批量进行训练。

使用小批量也意味着我们必须注意批次中句子长度的变化。为了在同一批次中容纳不同大小的句子，我们将使批次输入张量的形状为 *(max_length, batch_size)*，其中比 *max_length* 短的句子在 *EOS_token* 之后进行零填充。

如果我们简单地通过将单词转换为它们的索引（indexesFromSentence）并将英文句子转换为张量并进行零填充，我们的张量形状将是 *(batch_size, max_length)*，索引第一维将返回一个跨越所有时间步的完整序列。然而，我们需要能够沿时间轴并在批次中的所有序列上索引我们的批次。因此，我们将输入批次的形状转置为 *(max_length, batch_size)*，以便索引第一维可以返回批次中所有句子的一个时间步。我们在 zeroPadding 函数中隐式处理了这个转置。

batches

inputVar 函数处理将句子转换为张量的过程，最终创建一个形状正确、零填充的张量。它还返回批次中每个序列的 lengths 张量，该张量稍后将传递给我们的解码器。

outputVar 函数执行与 inputVar 类似的功能，但它不返回 lengths 张量，而是返回一个二进制掩码张量和一个最大目标句子长度。二进制掩码张量与输出目标张量具有相同的形状，但每个是 *PAD_token* 的元素为0，其他所有元素为1。

batch2TrainData 简单地接收一批句子对，并使用上述函数返回输入和目标张量。

def indexesFromSentence(voc, sentence):
    return [voc.word2index[word] for word in sentence.split(' ')] + [EOS_token]


def zeroPadding(l, fillvalue=PAD_token):
    return list(itertools.zip_longest(*l, fillvalue=fillvalue))

def binaryMatrix(l, value=PAD_token):
    m = []
    for i, seq in enumerate(l):
        m.append([])
        for token in seq:
            if token == PAD_token:
                m[i].append(0)
            else:
                m[i].append(1)
    return m

# Returns padded input sequence tensor and lengths
def inputVar(l, voc):
    indexes_batch = [indexesFromSentence(voc, sentence) for sentence in l]
    lengths = torch.tensor([len(indexes) for indexes in indexes_batch])
    padList = zeroPadding(indexes_batch)
    padVar = torch.LongTensor(padList)
    return padVar, lengths

# Returns padded target sequence tensor, padding mask, and max target length
def outputVar(l, voc):
    indexes_batch = [indexesFromSentence(voc, sentence) for sentence in l]
    max_target_len = max([len(indexes) for indexes in indexes_batch])
    padList = zeroPadding(indexes_batch)
    mask = binaryMatrix(padList)
    mask = torch.BoolTensor(mask)
    padVar = torch.LongTensor(padList)
    return padVar, mask, max_target_len

# Returns all items for a given batch of pairs
def batch2TrainData(voc, pair_batch):
    pair_batch.sort(key=lambda x: len(x[0].split(" ")), reverse=True)
    input_batch, output_batch = [], []
    for pair in pair_batch:
        input_batch.append(pair[0])
        output_batch.append(pair[1])
    inp, lengths = inputVar(input_batch, voc)
    output, mask, max_target_len = outputVar(output_batch, voc)
    return inp, lengths, output, mask, max_target_len


# Example for validation
small_batch_size = 5
batches = batch2TrainData(voc, [random.choice(pairs) for _ in range(small_batch_size)])
input_variable, lengths, target_variable, mask, max_target_len = batches

print("input_variable:", input_variable)
print("lengths:", lengths)
print("target_variable:", target_variable)
print("mask:", mask)
print("max_target_len:", max_target_len)

input_variable: tensor([[  24,   19,  635,   20,   26],
        [  44,  362,  158, 2780, 1427],
        [  52,    5,  404,   14,   14],
        [1480, 1831,   14,    2,    2],
        [ 789,   10,    2,    0,    0],
        [1779,    2,    0,    0,    0],
        [2764,    0,    0,    0,    0],
        [  14,    0,    0,    0,    0],
        [   2,    0,    0,    0,    0]])
lengths: tensor([9, 6, 5, 4, 4])
target_variable: tensor([[3883,   11,  585,   24,    8],
        [   6,  246,   14,   64,   17],
        [ 170,  135,    2,  444,  321],
        [ 140,  547,    0, 1199,   14],
        [  90,  160,    0,  555,    2],
        [  79,    2,    0,   14,    0],
        [1848,    0,    0,    2,    0],
        [  10,    0,    0,    0,    0],
        [   2,    0,    0,    0,    0]])
mask: tensor([[ True,  True,  True,  True,  True],
        [ True,  True,  True,  True,  True],
        [ True,  True,  True,  True,  True],
        [ True,  True, False,  True,  True],
        [ True,  True, False,  True,  True],
        [ True,  True, False,  True, False],
        [ True, False, False,  True, False],
        [ True, False, False, False, False],
        [ True, False, False, False, False]])
max_target_len: 9

定义模型#

Seq2Seq 模型#

我们聊天机器人的大脑是一个序列到序列（seq2seq）模型。seq2seq模型的目标是接收一个可变长度的序列作为输入，并使用一个固定大小的模型返回一个可变长度的序列作为输出。

Sutskever等人发现，通过将两个独立的循环神经网络结合使用，我们可以完成这项任务。一个RNN充当**编码器**，它将一个可变长度的输入序列编码为一个固定长度的上下文向量。理论上，这个上下文向量（RNN的最后一个隐藏层）将包含关于输入到机器人的查询句子的语义信息。第二个RNN是**解码器**，它接收一个输入词和上下文向量，并返回序列中下一个词的猜测以及在下一次迭代中使用的隐藏状态。

model

图片来源：https://jeddy92.github.io/JEddy92.github.io/ts_seq2seq_intro/

编码器#

编码器RNN一次一个标记（例如，一个词）地遍历输入句子，在每个时间步输出一个“输出”向量和一个“隐藏状态”向量。隐藏状态向量随后被传递到下一个时间步，而输出向量则被记录下来。编码器将其在序列中每个点看到的上下文转换成高维空间中的一组点，解码器将使用这些点为给定任务生成有意义的输出。

我们编码器的核心是一个多层门控循环单元（Gated Recurrent Unit），由Cho等人在2014年发明。我们将使用GRU的一个双向变体，这意味着基本上有两个独立的RNN：一个按正常顺序接收输入序列，另一个按相反顺序接收输入序列。每个网络的输出在每个时间步相加。使用双向GRU将使我们能够编码过去和未来的上下文。

双向RNN

rnn_bidir

图片来源：https://colah.github.io/posts/2015-09-NN-Types-FP/

请注意，使用了一个embedding层来将我们的词索引编码到一个任意大小的特征空间中。对于我们的模型，该层会将每个词映射到一个大小为 *hidden_size* 的特征空间。训练后，这些值应能编码含义相近的词之间的语义相似性。

最后，如果将一个填充过的序列批次传递给RNN模块，我们必须在RNN传递前后使用 nn.utils.rnn.pack_padded_sequence 和 nn.utils.rnn.pad_packed_sequence 分别打包和解包填充。

计算图

  1. 将词索引转换为词嵌入。

  2. 为RNN模块打包填充的序列批次。

  3. 通过GRU进行前向传播。

  4. 解包填充。

  5. 对双向GRU的输出求和。

  6. 返回输出和最终隐藏状态。

输入

  • input_seq：输入句子批次；形状=*(max_length, batch_size)*

  • input_lengths：与批次中每个句子对应的句子长度列表；形状=*(batch_size)*

  • hidden：隐藏状态；形状=*(n_layers x num_directions, batch_size, hidden_size)*

输出

  • outputs: GRU最后一个隐藏层的输出特征（双向输出之和）；形状=*(max_length, batch_size, hidden_size)*

  • hidden: GRU 更新后的隐藏状态；形状=*(n_layers x num_directions, batch_size, hidden_size)*

class EncoderRNN(nn.Module):
    def __init__(self, hidden_size, embedding, n_layers=1, dropout=0):
        super(EncoderRNN, self).__init__()
        self.n_layers = n_layers
        self.hidden_size = hidden_size
        self.embedding = embedding

        # Initialize GRU; the input_size and hidden_size parameters are both set to 'hidden_size'
        #   because our input size is a word embedding with number of features == hidden_size
        self.gru = nn.GRU(hidden_size, hidden_size, n_layers,
                          dropout=(0 if n_layers == 1 else dropout), bidirectional=True)

    def forward(self, input_seq, input_lengths, hidden=None):
        # Convert word indexes to embeddings
        embedded = self.embedding(input_seq)
        # Pack padded batch of sequences for RNN module
        packed = nn.utils.rnn.pack_padded_sequence(embedded, input_lengths)
        # Forward pass through GRU
        outputs, hidden = self.gru(packed, hidden)
        # Unpack padding
        outputs, _ = nn.utils.rnn.pad_packed_sequence(outputs)
        # Sum bidirectional GRU outputs
        outputs = outputs[:, :, :self.hidden_size] + outputs[:, : ,self.hidden_size:]
        # Return output and final hidden state
        return outputs, hidden

解码器#

解码器RNN以逐个标记的方式生成响应句子。它使用编码器的上下文向量和内部隐藏状态来生成序列中的下一个词。它会一直生成词，直到输出一个*EOS_token*，表示句子结束。传统seq2seq解码器的一个常见问题是，如果我们仅仅依赖上下文向量来编码整个输入序列的含义，很可能会发生信息丢失。在处理长输入序列时尤其如此，这极大地限制了解码器的能力。

为了解决这个问题，Bahdanau等人创建了一种“注意力机制”，它允许解码器关注输入序列的某些部分，而不是在每一步都使用整个固定的上下文。

从高层次来看，注意力是使用解码器当前的隐藏状态和编码器的输出来计算的。输出的注意力权重与输入序列具有相同的形状，这使我们能够将它们与编码器输出相乘，得到一个加权和，该加权和指示了需要关注的编码器输出部分。Sean Robertson的图表很好地描述了这一点。

attn2

Luong等人在Bahdanau等人的基础上进行了改进，创建了“全局注意力”。关键区别在于，使用“全局注意力”时，我们考虑编码器的所有隐藏状态，而Bahdanau等人的“局部注意力”仅考虑当前时间步的编码器隐藏状态。另一个区别是，使用“全局注意力”时，我们仅使用当前时间步的解码器隐藏状态来计算注意力权重或能量。Bahdanau等人的注意力计算需要知道前一时间步的解码器状态。此外，Luong等人提供了多种方法来计算编码器输出和解码器输出之间的注意力能量，这些方法被称为“评分函数”。

scores

其中 \(h_t\) = 当前目标解码器状态，而 \(\bar{h}_s\) = 所有编码器状态。

总的来说，全局注意力机制可以用下图来概括。请注意，我们将把“注意力层”实现为一个单独的 nn.Module，名为 Attn。该模块的输出是一个经过softmax归一化的权重张量，形状为 *(batch_size, 1, max_length)*。

global_attn 
# Luong attention layer
class Attn(nn.Module):
    def __init__(self, method, hidden_size):
        super(Attn, self).__init__()
        self.method = method
        if self.method not in ['dot', 'general', 'concat']:
            raise ValueError(self.method, "is not an appropriate attention method.")
        self.hidden_size = hidden_size
        if self.method == 'general':
            self.attn = nn.Linear(self.hidden_size, hidden_size)
        elif self.method == 'concat':
            self.attn = nn.Linear(self.hidden_size * 2, hidden_size)
            self.v = nn.Parameter(torch.FloatTensor(hidden_size))

    def dot_score(self, hidden, encoder_output):
        return torch.sum(hidden * encoder_output, dim=2)

    def general_score(self, hidden, encoder_output):
        energy = self.attn(encoder_output)
        return torch.sum(hidden * energy, dim=2)

    def concat_score(self, hidden, encoder_output):
        energy = self.attn(torch.cat((hidden.expand(encoder_output.size(0), -1, -1), encoder_output), 2)).tanh()
        return torch.sum(self.v * energy, dim=2)

    def forward(self, hidden, encoder_outputs):
        # Calculate the attention weights (energies) based on the given method
        if self.method == 'general':
            attn_energies = self.general_score(hidden, encoder_outputs)
        elif self.method == 'concat':
            attn_energies = self.concat_score(hidden, encoder_outputs)
        elif self.method == 'dot':
            attn_energies = self.dot_score(hidden, encoder_outputs)

        # Transpose max_length and batch_size dimensions
        attn_energies = attn_energies.t()

        # Return the softmax normalized probability scores (with added dimension)
        return F.softmax(attn_energies, dim=1).unsqueeze(1)

现在我们已经定义了注意力子模块，我们可以实现实际的解码器模型。对于解码器，我们将手动一次一个时间步地输入我们的批次。这意味着我们的嵌入词张量和GRU输出的形状都将是 *(1, batch_size, hidden_size)*。

计算图

  1. 获取当前输入词的嵌入。

  2. 通过单向GRU进行前向传播。

  3. 根据(2)中的当前GRU输出计算注意力权重。

  4. 将注意力权重与编码器输出相乘以获得新的“加权和”上下文向量。

  5. 使用Luong公式5连接加权上下文向量和GRU输出。

  6. 使用Luong公式6（不带softmax）预测下一个词。

  7. 返回输出和最终隐藏状态。

输入

  • input_step：输入序列批次的一个时间步（一个词）；形状=*(1, batch_size)*

  • last_hidden：GRU的最终隐藏层；形状=*(n_layers x num_directions, batch_size, hidden_size)*

  • encoder_outputs：编码器模型的输出；形状=*(max_length, batch_size, hidden_size)*

输出

  • output: softmax归一化张量，给出每个词成为解码序列中下一个正确词的概率；形状=*(batch_size, voc.num_words)*

  • hidden: GRU 的最终隐藏状态；形状=*(n_layers x num_directions, batch_size, hidden_size)*

class LuongAttnDecoderRNN(nn.Module):
    def __init__(self, attn_model, embedding, hidden_size, output_size, n_layers=1, dropout=0.1):
        super(LuongAttnDecoderRNN, self).__init__()

        # Keep for reference
        self.attn_model = attn_model
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.n_layers = n_layers
        self.dropout = dropout

        # Define layers
        self.embedding = embedding
        self.embedding_dropout = nn.Dropout(dropout)
        self.gru = nn.GRU(hidden_size, hidden_size, n_layers, dropout=(0 if n_layers == 1 else dropout))
        self.concat = nn.Linear(hidden_size * 2, hidden_size)
        self.out = nn.Linear(hidden_size, output_size)

        self.attn = Attn(attn_model, hidden_size)

    def forward(self, input_step, last_hidden, encoder_outputs):
        # Note: we run this one step (word) at a time
        # Get embedding of current input word
        embedded = self.embedding(input_step)
        embedded = self.embedding_dropout(embedded)
        # Forward through unidirectional GRU
        rnn_output, hidden = self.gru(embedded, last_hidden)
        # Calculate attention weights from the current GRU output
        attn_weights = self.attn(rnn_output, encoder_outputs)
        # Multiply attention weights to encoder outputs to get new "weighted sum" context vector
        context = attn_weights.bmm(encoder_outputs.transpose(0, 1))
        # Concatenate weighted context vector and GRU output using Luong eq. 5
        rnn_output = rnn_output.squeeze(0)
        context = context.squeeze(1)
        concat_input = torch.cat((rnn_output, context), 1)
        concat_output = torch.tanh(self.concat(concat_input))
        # Predict next word using Luong eq. 6
        output = self.out(concat_output)
        output = F.softmax(output, dim=1)
        # Return output and final hidden state
        return output, hidden

定义训练过程#

掩码损失#

由于我们处理的是填充序列的批次，因此在计算损失时，我们不能简单地考虑张量的所有元素。我们定义 maskNLLLoss 来根据解码器的输出张量、目标张量以及描述目标张量填充情况的二进制掩码张量来计算我们的损失。该损失函数计算掩码张量中对应于*1*的元素的平均负对数似然。

def maskNLLLoss(inp, target, mask):
    nTotal = mask.sum()
    crossEntropy = -torch.log(torch.gather(inp, 1, target.view(-1, 1)).squeeze(1))
    loss = crossEntropy.masked_select(mask).mean()
    loss = loss.to(device)
    return loss, nTotal.item()

单次训练迭代#

train 函数包含单次训练迭代（单个输入批次）的算法。

我们将使用几个巧妙的技巧来帮助收敛：

  • 第一个技巧是使用**教师强制（teacher forcing）**。这意味着以由 teacher_forcing_ratio 设置的某个概率，我们使用当前的目标词作为解码器的下一个输入，而不是使用解码器当前的猜测。这种技术就像解码器的“辅助轮”，有助于更高效的训练。然而，教师强制可能导致模型在推理过程中的不稳定性，因为解码器在训练期间可能没有足够的机会真正地构建自己的输出序列。因此，我们必须注意如何设置 teacher_forcing_ratio，不要被快速收敛所迷惑。

  • 我们实现的第二个技巧是**梯度裁剪**。这是一种常用于对抗“梯度爆炸”问题的技术。本质上，通过将梯度裁剪或阈值化到一个最大值，我们防止梯度指数级增长，从而避免溢出（NaN）或在代价函数中越过陡峭的悬崖。

grad_clip

图片来源：Goodfellow 等人，《深度学习》，2016年。 https://www.deeplearningbook.org/

操作序列

  1. 将整个输入批次通过编码器进行前向传播。

  2. 将解码器输入初始化为SOS_token，隐藏状态初始化为编码器的最终隐藏状态。

  3. 将输入批次序列逐个时间步通过解码器进行前向传播。

  4. 如果使用教师强制：将下一个解码器输入设置为当前目标；否则：将下一个解码器输入设置为当前解码器输出。

  5. 计算并累积损失。

  6. 执行反向传播。

  7. 裁剪梯度。

  8. 更新编码器和解码器模型参数。

注意

PyTorch的RNN模块（RNN, LSTM, GRU）可以像任何其他非循环层一样使用，只需将整个输入序列（或序列批次）传递给它们即可。我们在encoder中就是这样使用GRU层的。实际上，其底层是一个在每个时间步上循环计算隐藏状态的迭代过程。或者，你也可以一次一个时间步地运行这些模块。在这种情况下，我们在训练过程中手动循环遍历序列，就像我们必须为decoder模型所做的那样。只要你对这些模块保持正确的概念模型，实现序列模型就会变得非常直接。

def train(input_variable, lengths, target_variable, mask, max_target_len, encoder, decoder, embedding,
          encoder_optimizer, decoder_optimizer, batch_size, clip, max_length=MAX_LENGTH):

    # Zero gradients
    encoder_optimizer.zero_grad()
    decoder_optimizer.zero_grad()

    # Set device options
    input_variable = input_variable.to(device)
    target_variable = target_variable.to(device)
    mask = mask.to(device)
    # Lengths for RNN packing should always be on the CPU
    lengths = lengths.to("cpu")

    # Initialize variables
    loss = 0
    print_losses = []
    n_totals = 0

    # Forward pass through encoder
    encoder_outputs, encoder_hidden = encoder(input_variable, lengths)

    # Create initial decoder input (start with SOS tokens for each sentence)
    decoder_input = torch.LongTensor([[SOS_token for _ in range(batch_size)]])
    decoder_input = decoder_input.to(device)

    # Set initial decoder hidden state to the encoder's final hidden state
    decoder_hidden = encoder_hidden[:decoder.n_layers]

    # Determine if we are using teacher forcing this iteration
    use_teacher_forcing = True if random.random() < teacher_forcing_ratio else False

    # Forward batch of sequences through decoder one time step at a time
    if use_teacher_forcing:
        for t in range(max_target_len):
            decoder_output, decoder_hidden = decoder(
                decoder_input, decoder_hidden, encoder_outputs
            )
            # Teacher forcing: next input is current target
            decoder_input = target_variable[t].view(1, -1)
            # Calculate and accumulate loss
            mask_loss, nTotal = maskNLLLoss(decoder_output, target_variable[t], mask[t])
            loss += mask_loss
            print_losses.append(mask_loss.item() * nTotal)
            n_totals += nTotal
    else:
        for t in range(max_target_len):
            decoder_output, decoder_hidden = decoder(
                decoder_input, decoder_hidden, encoder_outputs
            )
            # No teacher forcing: next input is decoder's own current output
            _, topi = decoder_output.topk(1)
            decoder_input = torch.LongTensor([[topi[i][0] for i in range(batch_size)]])
            decoder_input = decoder_input.to(device)
            # Calculate and accumulate loss
            mask_loss, nTotal = maskNLLLoss(decoder_output, target_variable[t], mask[t])
            loss += mask_loss
            print_losses.append(mask_loss.item() * nTotal)
            n_totals += nTotal

    # Perform backpropagation
    loss.backward()

    # Clip gradients: gradients are modified in place
    _ = nn.utils.clip_grad_norm_(encoder.parameters(), clip)
    _ = nn.utils.clip_grad_norm_(decoder.parameters(), clip)

    # Adjust model weights
    encoder_optimizer.step()
    decoder_optimizer.step()

    return sum(print_losses) / n_totals

训练迭代#

现在终于到了将完整的训练过程与数据结合起来的时候了。`trainIters` 函数负责在给定模型、优化器、数据等条件下运行 `n_iterations` 次训练。这个函数非常不言自明，因为我们已经用 `train` 函数完成了繁重的工作。

需要注意的一点是，当我们保存模型时，我们保存的是一个包含编码器和解码器 state_dicts（参数）、优化器的 state_dicts、损失、迭代次数等的tarball。以这种方式保存模型将为我们提供检查点的终极灵活性。加载检查点后，我们可以使用模型参数来运行推理，或者我们可以从上次离开的地方继续训练。

def trainIters(model_name, voc, pairs, encoder, decoder, encoder_optimizer, decoder_optimizer, embedding, encoder_n_layers, decoder_n_layers, save_dir, n_iteration, batch_size, print_every, save_every, clip, corpus_name, loadFilename):

    # Load batches for each iteration
    training_batches = [batch2TrainData(voc, [random.choice(pairs) for _ in range(batch_size)])
                      for _ in range(n_iteration)]

    # Initializations
    print('Initializing ...')
    start_iteration = 1
    print_loss = 0
    if loadFilename:
        start_iteration = checkpoint['iteration'] + 1

    # Training loop
    print("Training...")
    for iteration in range(start_iteration, n_iteration + 1):
        training_batch = training_batches[iteration - 1]
        # Extract fields from batch
        input_variable, lengths, target_variable, mask, max_target_len = training_batch

        # Run a training iteration with batch
        loss = train(input_variable, lengths, target_variable, mask, max_target_len, encoder,
                     decoder, embedding, encoder_optimizer, decoder_optimizer, batch_size, clip)
        print_loss += loss

        # Print progress
        if iteration % print_every == 0:
            print_loss_avg = print_loss / print_every
            print("Iteration: {}; Percent complete: {:.1f}%; Average loss: {:.4f}".format(iteration, iteration / n_iteration * 100, print_loss_avg))
            print_loss = 0

        # Save checkpoint
        if (iteration % save_every == 0):
            directory = os.path.join(save_dir, model_name, corpus_name, '{}-{}_{}'.format(encoder_n_layers, decoder_n_layers, hidden_size))
            if not os.path.exists(directory):
                os.makedirs(directory)
            torch.save({
                'iteration': iteration,
                'en': encoder.state_dict(),
                'de': decoder.state_dict(),
                'en_opt': encoder_optimizer.state_dict(),
                'de_opt': decoder_optimizer.state_dict(),
                'loss': loss,
                'voc_dict': voc.__dict__,
                'embedding': embedding.state_dict()
            }, os.path.join(directory, '{}_{}.tar'.format(iteration, 'checkpoint')))

定义评估#

在训练模型之后，我们希望能够自己与机器人对话。首先，我们必须定义我们希望模型如何解码编码后的输入。

贪婪解码#

贪婪解码是我们在**不**使用教师强制进行训练时使用的解码方法。换句话说，对于每个时间步，我们简单地从 decoder_output 中选择具有最高 softmax 值的词。这种解码方法在单个时间步级别上是最优的。

为了方便贪婪解码操作，我们定义了一个 GreedySearchDecoder 类。运行时，该类的对象接收一个形状为 *(input_seq length, 1)* 的输入序列（input_seq），一个标量输入长度（input_length）张量，以及一个用于限制响应句子长度的 max_length。输入句子使用以下计算图进行评估：

计算图

  1. 通过编码器模型进行前向输入。

  2. 准备编码器的最终隐藏层，作为解码器的第一个隐藏输入。

  3. 将解码器的第一个输入初始化为 SOS_token。

  4. 初始化张量以附加解码后的单词。

  5. 迭代地一次解码一个词元

    1. 通过解码器进行前向传播。

    2. 获取最可能的词元及其softmax分数。

    3. 记录词元和分数。

    4. 准备当前词元作为下一个解码器输入。

  6. 返回单词标记和分数的集合。

class GreedySearchDecoder(nn.Module):
    def __init__(self, encoder, decoder):
        super(GreedySearchDecoder, self).__init__()
        self.encoder = encoder
        self.decoder = decoder

    def forward(self, input_seq, input_length, max_length):
        # Forward input through encoder model
        encoder_outputs, encoder_hidden = self.encoder(input_seq, input_length)
        # Prepare encoder's final hidden layer to be first hidden input to the decoder
        decoder_hidden = encoder_hidden[:self.decoder.n_layers]
        # Initialize decoder input with SOS_token
        decoder_input = torch.ones(1, 1, device=device, dtype=torch.long) * SOS_token
        # Initialize tensors to append decoded words to
        all_tokens = torch.zeros([0], device=device, dtype=torch.long)
        all_scores = torch.zeros([0], device=device)
        # Iteratively decode one word token at a time
        for _ in range(max_length):
            # Forward pass through decoder
            decoder_output, decoder_hidden = self.decoder(decoder_input, decoder_hidden, encoder_outputs)
            # Obtain most likely word token and its softmax score
            decoder_scores, decoder_input = torch.max(decoder_output, dim=1)
            # Record token and score
            all_tokens = torch.cat((all_tokens, decoder_input), dim=0)
            all_scores = torch.cat((all_scores, decoder_scores), dim=0)
            # Prepare current token to be next decoder input (add a dimension)
            decoder_input = torch.unsqueeze(decoder_input, 0)
        # Return collections of word tokens and scores
        return all_tokens, all_scores

评估我的文本#

现在我们已经定义了解码方法，我们可以编写用于评估字符串输入句子的函数。`evaluate` 函数管理处理输入句子的底层过程。我们首先将句子格式化为一个词索引的输入批次，其中 *batch_size==1*。我们通过将句子中的词转换为它们对应的索引，并转置维度来为我们的模型准备张量。我们还创建了一个 `lengths` 张量，其中包含我们输入句子的长度。在这种情况下，`lengths` 是一个标量，因为我们一次只评估一个句子（batch_size==1）。接下来，我们使用我们的 `GreedySearchDecoder` 对象（`searcher`）获得解码后的响应句子张量。最后，我们将响应的索引转换为词，并返回解码后的词列表。

evaluateInput 充当我们聊天机器人的用户界面。调用时，会生成一个输入文本字段，我们可以在其中输入我们的查询句子。在输入我们的句子并按 *Enter* 键后，我们的文本会像训练数据一样进行归一化，并最终被送入 evaluate 函数以获得解码后的输出句子。我们循环这个过程，这样我们就可以一直和我们的机器人聊天，直到我们输入“q”或“quit”。

最后，如果输入的句子中包含词汇表中没有的词，我们会通过打印错误消息并提示用户输入另一个句子来优雅地处理这种情况。

def evaluate(encoder, decoder, searcher, voc, sentence, max_length=MAX_LENGTH):
    ### Format input sentence as a batch
    # words -> indexes
    indexes_batch = [indexesFromSentence(voc, sentence)]
    # Create lengths tensor
    lengths = torch.tensor([len(indexes) for indexes in indexes_batch])
    # Transpose dimensions of batch to match models' expectations
    input_batch = torch.LongTensor(indexes_batch).transpose(0, 1)
    # Use appropriate device
    input_batch = input_batch.to(device)
    lengths = lengths.to("cpu")
    # Decode sentence with searcher
    tokens, scores = searcher(input_batch, lengths, max_length)
    # indexes -> words
    decoded_words = [voc.index2word[token.item()] for token in tokens]
    return decoded_words


def evaluateInput(encoder, decoder, searcher, voc):
    input_sentence = ''
    while(1):
        try:
            # Get input sentence
            input_sentence = input('> ')
            # Check if it is quit case
            if input_sentence == 'q' or input_sentence == 'quit': break
            # Normalize sentence
            input_sentence = normalizeString(input_sentence)
            # Evaluate sentence
            output_words = evaluate(encoder, decoder, searcher, voc, input_sentence)
            # Format and print response sentence
            output_words[:] = [x for x in output_words if not (x == 'EOS' or x == 'PAD')]
            print('Bot:', ' '.join(output_words))

        except KeyError:
            print("Error: Encountered unknown word.")

运行模型#

终于，是时候运行我们的模型了！

无论我们是想训练还是测试聊天机器人模型，我们都必须初始化各个编码器和解码器模型。在下面的代码块中，我们设置我们期望的配置，选择从头开始或设置一个要加载的检查点，然后构建并初始化模型。您可以随意尝试不同的模型配置来优化性能。

# Configure models
model_name = 'cb_model'
attn_model = 'dot'
#``attn_model = 'general'``
#``attn_model = 'concat'``
hidden_size = 500
encoder_n_layers = 2
decoder_n_layers = 2
dropout = 0.1
batch_size = 64

# Set checkpoint to load from; set to None if starting from scratch
loadFilename = None
checkpoint_iter = 4000

从检查点加载的示例代码

loadFilename = os.path.join(save_dir, model_name, corpus_name,
                    '{}-{}_{}'.format(encoder_n_layers, decoder_n_layers, hidden_size),
                    '{}_checkpoint.tar'.format(checkpoint_iter))

# Load model if a ``loadFilename`` is provided
if loadFilename:
    # If loading on same machine the model was trained on
    checkpoint = torch.load(loadFilename)
    # If loading a model trained on GPU to CPU
    #checkpoint = torch.load(loadFilename, map_location=torch.device('cpu'))
    encoder_sd = checkpoint['en']
    decoder_sd = checkpoint['de']
    encoder_optimizer_sd = checkpoint['en_opt']
    decoder_optimizer_sd = checkpoint['de_opt']
    embedding_sd = checkpoint['embedding']
    voc.__dict__ = checkpoint['voc_dict']


print('Building encoder and decoder ...')
# Initialize word embeddings
embedding = nn.Embedding(voc.num_words, hidden_size)
if loadFilename:
    embedding.load_state_dict(embedding_sd)
# Initialize encoder & decoder models
encoder = EncoderRNN(hidden_size, embedding, encoder_n_layers, dropout)
decoder = LuongAttnDecoderRNN(attn_model, embedding, hidden_size, voc.num_words, decoder_n_layers, dropout)
if loadFilename:
    encoder.load_state_dict(encoder_sd)
    decoder.load_state_dict(decoder_sd)
# Use appropriate device
encoder = encoder.to(device)
decoder = decoder.to(device)
print('Models built and ready to go!')

Building encoder and decoder ...
Models built and ready to go!

运行训练#

如果你想训练模型，请运行以下代码块。

首先我们设置训练参数，然后初始化我们的优化器，最后我们调用 trainIters 函数来运行我们的训练迭代。

# Configure training/optimization
clip = 50.0
teacher_forcing_ratio = 1.0
learning_rate = 0.0001
decoder_learning_ratio = 5.0
n_iteration = 4000
print_every = 1
save_every = 500

# Ensure dropout layers are in train mode
encoder.train()
decoder.train()

# Initialize optimizers
print('Building optimizers ...')
encoder_optimizer = optim.Adam(encoder.parameters(), lr=learning_rate)
decoder_optimizer = optim.Adam(decoder.parameters(), lr=learning_rate * decoder_learning_ratio)
if loadFilename:
    encoder_optimizer.load_state_dict(encoder_optimizer_sd)
    decoder_optimizer.load_state_dict(decoder_optimizer_sd)

# If you have an accelerator, configure it to call
for state in encoder_optimizer.state.values():
    for k, v in state.items():
        if isinstance(v, torch.Tensor):
            state[k] = v.to(device)

for state in decoder_optimizer.state.values():
    for k, v in state.items():
        if isinstance(v, torch.Tensor):
            state[k] = v.to(device)

# Run training iterations
print("Starting Training!")
trainIters(model_name, voc, pairs, encoder, decoder, encoder_optimizer, decoder_optimizer,
           embedding, encoder_n_layers, decoder_n_layers, save_dir, n_iteration, batch_size,
           print_every, save_every, clip, corpus_name, loadFilename)

Building optimizers ...
Starting Training!
Initializing ...
Training...
Iteration: 1; Percent complete: 0.0%; Average loss: 8.9467
Iteration: 2; Percent complete: 0.1%; Average loss: 8.8271
Iteration: 3; Percent complete: 0.1%; Average loss: 8.6025
Iteration: 4; Percent complete: 0.1%; Average loss: 8.3564
Iteration: 5; Percent complete: 0.1%; Average loss: 7.8171
Iteration: 6; Percent complete: 0.1%; Average loss: 7.2491
Iteration: 7; Percent complete: 0.2%; Average loss: 6.8805
Iteration: 8; Percent complete: 0.2%; Average loss: 6.6440
Iteration: 9; Percent complete: 0.2%; Average loss: 6.8184
Iteration: 10; Percent complete: 0.2%; Average loss: 6.3030
Iteration: 11; Percent complete: 0.3%; Average loss: 6.1474
Iteration: 12; Percent complete: 0.3%; Average loss: 5.6996
Iteration: 13; Percent complete: 0.3%; Average loss: 5.7101
Iteration: 14; Percent complete: 0.4%; Average loss: 5.8071
Iteration: 15; Percent complete: 0.4%; Average loss: 5.4277
Iteration: 16; Percent complete: 0.4%; Average loss: 5.4439
Iteration: 17; Percent complete: 0.4%; Average loss: 5.1960
Iteration: 18; Percent complete: 0.4%; Average loss: 5.1737
Iteration: 19; Percent complete: 0.5%; Average loss: 5.1072
Iteration: 20; Percent complete: 0.5%; Average loss: 5.1311
Iteration: 21; Percent complete: 0.5%; Average loss: 5.1324
Iteration: 22; Percent complete: 0.5%; Average loss: 4.7760
Iteration: 23; Percent complete: 0.6%; Average loss: 5.0146
Iteration: 24; Percent complete: 0.6%; Average loss: 4.7979
Iteration: 25; Percent complete: 0.6%; Average loss: 4.7358
Iteration: 26; Percent complete: 0.7%; Average loss: 4.9171
Iteration: 27; Percent complete: 0.7%; Average loss: 4.9107
Iteration: 28; Percent complete: 0.7%; Average loss: 4.7415
Iteration: 29; Percent complete: 0.7%; Average loss: 4.8302
Iteration: 30; Percent complete: 0.8%; Average loss: 4.7074
Iteration: 31; Percent complete: 0.8%; Average loss: 4.8030
Iteration: 32; Percent complete: 0.8%; Average loss: 4.6387
Iteration: 33; Percent complete: 0.8%; Average loss: 4.7052
Iteration: 34; Percent complete: 0.9%; Average loss: 4.6821
Iteration: 35; Percent complete: 0.9%; Average loss: 4.8937
Iteration: 36; Percent complete: 0.9%; Average loss: 4.5948
Iteration: 37; Percent complete: 0.9%; Average loss: 4.6735
Iteration: 38; Percent complete: 0.9%; Average loss: 4.5256
Iteration: 39; Percent complete: 1.0%; Average loss: 4.5923
Iteration: 40; Percent complete: 1.0%; Average loss: 4.9001
Iteration: 41; Percent complete: 1.0%; Average loss: 4.7212
Iteration: 42; Percent complete: 1.1%; Average loss: 4.5769
Iteration: 43; Percent complete: 1.1%; Average loss: 4.7433
Iteration: 44; Percent complete: 1.1%; Average loss: 4.6424
Iteration: 45; Percent complete: 1.1%; Average loss: 4.7173
Iteration: 46; Percent complete: 1.1%; Average loss: 4.7993
Iteration: 47; Percent complete: 1.2%; Average loss: 4.5270
Iteration: 48; Percent complete: 1.2%; Average loss: 4.6125
Iteration: 49; Percent complete: 1.2%; Average loss: 4.4017
Iteration: 50; Percent complete: 1.2%; Average loss: 4.6191
Iteration: 51; Percent complete: 1.3%; Average loss: 4.8091
Iteration: 52; Percent complete: 1.3%; Average loss: 4.5436
Iteration: 53; Percent complete: 1.3%; Average loss: 4.7453
Iteration: 54; Percent complete: 1.4%; Average loss: 4.4759
Iteration: 55; Percent complete: 1.4%; Average loss: 4.8501
Iteration: 56; Percent complete: 1.4%; Average loss: 4.4664
Iteration: 57; Percent complete: 1.4%; Average loss: 4.5900
Iteration: 58; Percent complete: 1.5%; Average loss: 4.5616
Iteration: 59; Percent complete: 1.5%; Average loss: 4.2985
Iteration: 60; Percent complete: 1.5%; Average loss: 4.5873
Iteration: 61; Percent complete: 1.5%; Average loss: 4.5795
Iteration: 62; Percent complete: 1.6%; Average loss: 4.6256
Iteration: 63; Percent complete: 1.6%; Average loss: 4.3966
Iteration: 64; Percent complete: 1.6%; Average loss: 4.4275
Iteration: 65; Percent complete: 1.6%; Average loss: 4.2374
Iteration: 66; Percent complete: 1.7%; Average loss: 4.7001
Iteration: 67; Percent complete: 1.7%; Average loss: 4.5131
Iteration: 68; Percent complete: 1.7%; Average loss: 4.7413
Iteration: 69; Percent complete: 1.7%; Average loss: 4.6518
Iteration: 70; Percent complete: 1.8%; Average loss: 4.3340
Iteration: 71; Percent complete: 1.8%; Average loss: 4.6533
Iteration: 72; Percent complete: 1.8%; Average loss: 4.8399
Iteration: 73; Percent complete: 1.8%; Average loss: 4.5712
Iteration: 74; Percent complete: 1.8%; Average loss: 4.4596
Iteration: 75; Percent complete: 1.9%; Average loss: 4.5564
Iteration: 76; Percent complete: 1.9%; Average loss: 4.3838
Iteration: 77; Percent complete: 1.9%; Average loss: 4.6225
Iteration: 78; Percent complete: 1.9%; Average loss: 4.5330
Iteration: 79; Percent complete: 2.0%; Average loss: 4.2838
Iteration: 80; Percent complete: 2.0%; Average loss: 4.6578
Iteration: 81; Percent complete: 2.0%; Average loss: 4.3034
Iteration: 82; Percent complete: 2.1%; Average loss: 4.4697
Iteration: 83; Percent complete: 2.1%; Average loss: 4.3332
Iteration: 84; Percent complete: 2.1%; Average loss: 4.4698
Iteration: 85; Percent complete: 2.1%; Average loss: 4.7620
Iteration: 86; Percent complete: 2.1%; Average loss: 4.4647
Iteration: 87; Percent complete: 2.2%; Average loss: 4.4432
Iteration: 88; Percent complete: 2.2%; Average loss: 4.6857
Iteration: 89; Percent complete: 2.2%; Average loss: 4.4747
Iteration: 90; Percent complete: 2.2%; Average loss: 4.3528
Iteration: 91; Percent complete: 2.3%; Average loss: 4.4845
Iteration: 92; Percent complete: 2.3%; Average loss: 4.6255
Iteration: 93; Percent complete: 2.3%; Average loss: 4.2389
Iteration: 94; Percent complete: 2.4%; Average loss: 4.4988
Iteration: 95; Percent complete: 2.4%; Average loss: 4.2779
Iteration: 96; Percent complete: 2.4%; Average loss: 4.5053
Iteration: 97; Percent complete: 2.4%; Average loss: 4.3857
Iteration: 98; Percent complete: 2.5%; Average loss: 4.6461
Iteration: 99; Percent complete: 2.5%; Average loss: 4.2555
Iteration: 100; Percent complete: 2.5%; Average loss: 4.3580
Iteration: 101; Percent complete: 2.5%; Average loss: 4.3637
Iteration: 102; Percent complete: 2.5%; Average loss: 4.5728
Iteration: 103; Percent complete: 2.6%; Average loss: 4.3295
Iteration: 104; Percent complete: 2.6%; Average loss: 4.5410
Iteration: 105; Percent complete: 2.6%; Average loss: 4.1388
Iteration: 106; Percent complete: 2.6%; Average loss: 4.3178
Iteration: 107; Percent complete: 2.7%; Average loss: 4.3899
Iteration: 108; Percent complete: 2.7%; Average loss: 4.3042
Iteration: 109; Percent complete: 2.7%; Average loss: 4.4736
Iteration: 110; Percent complete: 2.8%; Average loss: 4.4113
Iteration: 111; Percent complete: 2.8%; Average loss: 4.5032
Iteration: 112; Percent complete: 2.8%; Average loss: 4.3677
Iteration: 113; Percent complete: 2.8%; Average loss: 4.0799
Iteration: 114; Percent complete: 2.9%; Average loss: 4.3233
Iteration: 115; Percent complete: 2.9%; Average loss: 4.4207
Iteration: 116; Percent complete: 2.9%; Average loss: 4.2056
Iteration: 117; Percent complete: 2.9%; Average loss: 4.4616
Iteration: 118; Percent complete: 2.9%; Average loss: 4.2670
Iteration: 119; Percent complete: 3.0%; Average loss: 4.3081
Iteration: 120; Percent complete: 3.0%; Average loss: 4.4989
Iteration: 121; Percent complete: 3.0%; Average loss: 4.2837
Iteration: 122; Percent complete: 3.0%; Average loss: 4.3578
Iteration: 123; Percent complete: 3.1%; Average loss: 4.4282
Iteration: 124; Percent complete: 3.1%; Average loss: 4.0691
Iteration: 125; Percent complete: 3.1%; Average loss: 4.6033
Iteration: 126; Percent complete: 3.1%; Average loss: 4.0956
Iteration: 127; Percent complete: 3.2%; Average loss: 4.4626
Iteration: 128; Percent complete: 3.2%; Average loss: 4.1972
Iteration: 129; Percent complete: 3.2%; Average loss: 4.4937
Iteration: 130; Percent complete: 3.2%; Average loss: 4.3171
Iteration: 131; Percent complete: 3.3%; Average loss: 4.4323
Iteration: 132; Percent complete: 3.3%; Average loss: 4.2319
Iteration: 133; Percent complete: 3.3%; Average loss: 4.4083
Iteration: 134; Percent complete: 3.4%; Average loss: 4.4906
Iteration: 135; Percent complete: 3.4%; Average loss: 4.3129
Iteration: 136; Percent complete: 3.4%; Average loss: 4.3877
Iteration: 137; Percent complete: 3.4%; Average loss: 4.3208
Iteration: 138; Percent complete: 3.5%; Average loss: 4.4134
Iteration: 139; Percent complete: 3.5%; Average loss: 4.2312
Iteration: 140; Percent complete: 3.5%; Average loss: 4.2504
Iteration: 141; Percent complete: 3.5%; Average loss: 4.1968
Iteration: 142; Percent complete: 3.5%; Average loss: 4.3694
Iteration: 143; Percent complete: 3.6%; Average loss: 4.1191
Iteration: 144; Percent complete: 3.6%; Average loss: 4.2169
Iteration: 145; Percent complete: 3.6%; Average loss: 4.4834
Iteration: 146; Percent complete: 3.6%; Average loss: 4.3574
Iteration: 147; Percent complete: 3.7%; Average loss: 4.1382
Iteration: 148; Percent complete: 3.7%; Average loss: 4.3156
Iteration: 149; Percent complete: 3.7%; Average loss: 4.4835
Iteration: 150; Percent complete: 3.8%; Average loss: 4.3526
Iteration: 151; Percent complete: 3.8%; Average loss: 4.2936
Iteration: 152; Percent complete: 3.8%; Average loss: 4.1964
Iteration: 153; Percent complete: 3.8%; Average loss: 4.2498
Iteration: 154; Percent complete: 3.9%; Average loss: 3.9990
Iteration: 155; Percent complete: 3.9%; Average loss: 4.1088
Iteration: 156; Percent complete: 3.9%; Average loss: 4.2011
Iteration: 157; Percent complete: 3.9%; Average loss: 4.2027
Iteration: 158; Percent complete: 4.0%; Average loss: 4.0999
Iteration: 159; Percent complete: 4.0%; Average loss: 4.2145
Iteration: 160; Percent complete: 4.0%; Average loss: 4.1515
Iteration: 161; Percent complete: 4.0%; Average loss: 4.2982
Iteration: 162; Percent complete: 4.0%; Average loss: 4.2875
Iteration: 163; Percent complete: 4.1%; Average loss: 4.4697
Iteration: 164; Percent complete: 4.1%; Average loss: 3.9532
Iteration: 165; Percent complete: 4.1%; Average loss: 4.0942
Iteration: 166; Percent complete: 4.2%; Average loss: 4.0493
Iteration: 167; Percent complete: 4.2%; Average loss: 4.2278
Iteration: 168; Percent complete: 4.2%; Average loss: 4.3307
Iteration: 169; Percent complete: 4.2%; Average loss: 4.2528
Iteration: 170; Percent complete: 4.2%; Average loss: 4.1844
Iteration: 171; Percent complete: 4.3%; Average loss: 4.2673
Iteration: 172; Percent complete: 4.3%; Average loss: 4.1450
Iteration: 173; Percent complete: 4.3%; Average loss: 4.3987
Iteration: 174; Percent complete: 4.3%; Average loss: 4.3828
Iteration: 175; Percent complete: 4.4%; Average loss: 4.0869
Iteration: 176; Percent complete: 4.4%; Average loss: 4.3395
Iteration: 177; Percent complete: 4.4%; Average loss: 4.1059
Iteration: 178; Percent complete: 4.5%; Average loss: 4.0391
Iteration: 179; Percent complete: 4.5%; Average loss: 4.1702
Iteration: 180; Percent complete: 4.5%; Average loss: 3.9654
Iteration: 181; Percent complete: 4.5%; Average loss: 4.1418
Iteration: 182; Percent complete: 4.5%; Average loss: 4.0016
Iteration: 183; Percent complete: 4.6%; Average loss: 4.1365
Iteration: 184; Percent complete: 4.6%; Average loss: 4.1052
Iteration: 185; Percent complete: 4.6%; Average loss: 4.0087
Iteration: 186; Percent complete: 4.7%; Average loss: 4.0972
Iteration: 187; Percent complete: 4.7%; Average loss: 4.3946
Iteration: 188; Percent complete: 4.7%; Average loss: 4.2330
Iteration: 189; Percent complete: 4.7%; Average loss: 4.0721
Iteration: 190; Percent complete: 4.8%; Average loss: 4.1999
Iteration: 191; Percent complete: 4.8%; Average loss: 3.9205
Iteration: 192; Percent complete: 4.8%; Average loss: 4.0288
Iteration: 193; Percent complete: 4.8%; Average loss: 4.3090
Iteration: 194; Percent complete: 4.9%; Average loss: 4.0617
Iteration: 195; Percent complete: 4.9%; Average loss: 4.2166
Iteration: 196; Percent complete: 4.9%; Average loss: 4.0283
Iteration: 197; Percent complete: 4.9%; Average loss: 4.0594
Iteration: 198; Percent complete: 5.0%; Average loss: 4.0217
Iteration: 199; Percent complete: 5.0%; Average loss: 4.3710
Iteration: 200; Percent complete: 5.0%; Average loss: 4.0982
Iteration: 201; Percent complete: 5.0%; Average loss: 4.0091
Iteration: 202; Percent complete: 5.1%; Average loss: 3.7647
Iteration: 203; Percent complete: 5.1%; Average loss: 4.1095
Iteration: 204; Percent complete: 5.1%; Average loss: 4.0884
Iteration: 205; Percent complete: 5.1%; Average loss: 4.0065
Iteration: 206; Percent complete: 5.1%; Average loss: 4.0229
Iteration: 207; Percent complete: 5.2%; Average loss: 4.1111
Iteration: 208; Percent complete: 5.2%; Average loss: 4.2939
Iteration: 209; Percent complete: 5.2%; Average loss: 3.7805
Iteration: 210; Percent complete: 5.2%; Average loss: 4.1052
Iteration: 211; Percent complete: 5.3%; Average loss: 3.7981
Iteration: 212; Percent complete: 5.3%; Average loss: 4.0878
Iteration: 213; Percent complete: 5.3%; Average loss: 3.9325
Iteration: 214; Percent complete: 5.3%; Average loss: 4.0493
Iteration: 215; Percent complete: 5.4%; Average loss: 4.3026
Iteration: 216; Percent complete: 5.4%; Average loss: 3.8126
Iteration: 217; Percent complete: 5.4%; Average loss: 4.1389
Iteration: 218; Percent complete: 5.5%; Average loss: 4.0890
Iteration: 219; Percent complete: 5.5%; Average loss: 4.2162
Iteration: 220; Percent complete: 5.5%; Average loss: 4.0876
Iteration: 221; Percent complete: 5.5%; Average loss: 4.1665
Iteration: 222; Percent complete: 5.5%; Average loss: 4.0869
Iteration: 223; Percent complete: 5.6%; Average loss: 4.1202
Iteration: 224; Percent complete: 5.6%; Average loss: 3.9614
Iteration: 225; Percent complete: 5.6%; Average loss: 3.8392
Iteration: 226; Percent complete: 5.7%; Average loss: 4.1971
Iteration: 227; Percent complete: 5.7%; Average loss: 4.1896
Iteration: 228; Percent complete: 5.7%; Average loss: 3.9803
Iteration: 229; Percent complete: 5.7%; Average loss: 3.8830
Iteration: 230; Percent complete: 5.8%; Average loss: 4.0103
Iteration: 231; Percent complete: 5.8%; Average loss: 3.8873
Iteration: 232; Percent complete: 5.8%; Average loss: 4.0125
Iteration: 233; Percent complete: 5.8%; Average loss: 4.0564
Iteration: 234; Percent complete: 5.9%; Average loss: 3.9390
Iteration: 235; Percent complete: 5.9%; Average loss: 4.0069
Iteration: 236; Percent complete: 5.9%; Average loss: 3.6424
Iteration: 237; Percent complete: 5.9%; Average loss: 4.1182
Iteration: 238; Percent complete: 5.9%; Average loss: 4.2024
Iteration: 239; Percent complete: 6.0%; Average loss: 4.0105
Iteration: 240; Percent complete: 6.0%; Average loss: 3.9034
Iteration: 241; Percent complete: 6.0%; Average loss: 3.6855
Iteration: 242; Percent complete: 6.0%; Average loss: 3.8477
Iteration: 243; Percent complete: 6.1%; Average loss: 3.7236
Iteration: 244; Percent complete: 6.1%; Average loss: 3.9149
Iteration: 245; Percent complete: 6.1%; Average loss: 4.2695
Iteration: 246; Percent complete: 6.2%; Average loss: 4.1198
Iteration: 247; Percent complete: 6.2%; Average loss: 3.9692
Iteration: 248; Percent complete: 6.2%; Average loss: 4.2504
Iteration: 249; Percent complete: 6.2%; Average loss: 3.8005
Iteration: 250; Percent complete: 6.2%; Average loss: 4.2137
Iteration: 251; Percent complete: 6.3%; Average loss: 4.0363
Iteration: 252; Percent complete: 6.3%; Average loss: 4.0036
Iteration: 253; Percent complete: 6.3%; Average loss: 3.9562
Iteration: 254; Percent complete: 6.3%; Average loss: 3.6598
Iteration: 255; Percent complete: 6.4%; Average loss: 4.2735
Iteration: 256; Percent complete: 6.4%; Average loss: 3.9023
Iteration: 257; Percent complete: 6.4%; Average loss: 3.9973
Iteration: 258; Percent complete: 6.5%; Average loss: 3.8942
Iteration: 259; Percent complete: 6.5%; Average loss: 3.9469
Iteration: 260; Percent complete: 6.5%; Average loss: 3.9349
Iteration: 261; Percent complete: 6.5%; Average loss: 4.1809
Iteration: 262; Percent complete: 6.6%; Average loss: 4.0508
Iteration: 263; Percent complete: 6.6%; Average loss: 4.1499
Iteration: 264; Percent complete: 6.6%; Average loss: 4.0263
Iteration: 265; Percent complete: 6.6%; Average loss: 3.8692
Iteration: 266; Percent complete: 6.7%; Average loss: 3.9985
Iteration: 267; Percent complete: 6.7%; Average loss: 3.8352
Iteration: 268; Percent complete: 6.7%; Average loss: 4.0140
Iteration: 269; Percent complete: 6.7%; Average loss: 4.0824
Iteration: 270; Percent complete: 6.8%; Average loss: 3.9185
Iteration: 271; Percent complete: 6.8%; Average loss: 4.0936
Iteration: 272; Percent complete: 6.8%; Average loss: 3.9395
Iteration: 273; Percent complete: 6.8%; Average loss: 3.8744
Iteration: 274; Percent complete: 6.9%; Average loss: 4.0172
Iteration: 275; Percent complete: 6.9%; Average loss: 4.0311
Iteration: 276; Percent complete: 6.9%; Average loss: 3.7386
Iteration: 277; Percent complete: 6.9%; Average loss: 3.9475
Iteration: 278; Percent complete: 7.0%; Average loss: 3.8419
Iteration: 279; Percent complete: 7.0%; Average loss: 3.9830
Iteration: 280; Percent complete: 7.0%; Average loss: 3.9593
Iteration: 281; Percent complete: 7.0%; Average loss: 3.9336
Iteration: 282; Percent complete: 7.0%; Average loss: 3.9331
Iteration: 283; Percent complete: 7.1%; Average loss: 4.0036
Iteration: 284; Percent complete: 7.1%; Average loss: 3.8337
Iteration: 285; Percent complete: 7.1%; Average loss: 4.0986
Iteration: 286; Percent complete: 7.1%; Average loss: 4.0814
Iteration: 287; Percent complete: 7.2%; Average loss: 4.0168
Iteration: 288; Percent complete: 7.2%; Average loss: 3.9384
Iteration: 289; Percent complete: 7.2%; Average loss: 3.8782
Iteration: 290; Percent complete: 7.2%; Average loss: 4.0496
Iteration: 291; Percent complete: 7.3%; Average loss: 4.0502
Iteration: 292; Percent complete: 7.3%; Average loss: 3.9324
Iteration: 293; Percent complete: 7.3%; Average loss: 4.1144
Iteration: 294; Percent complete: 7.3%; Average loss: 3.9734
Iteration: 295; Percent complete: 7.4%; Average loss: 3.9025
Iteration: 296; Percent complete: 7.4%; Average loss: 4.1202
Iteration: 297; Percent complete: 7.4%; Average loss: 4.1853
Iteration: 298; Percent complete: 7.4%; Average loss: 4.0651
Iteration: 299; Percent complete: 7.5%; Average loss: 3.8875
Iteration: 300; Percent complete: 7.5%; Average loss: 3.9562
Iteration: 301; Percent complete: 7.5%; Average loss: 3.7878
Iteration: 302; Percent complete: 7.5%; Average loss: 3.8581
Iteration: 303; Percent complete: 7.6%; Average loss: 4.1073
Iteration: 304; Percent complete: 7.6%; Average loss: 3.9726
Iteration: 305; Percent complete: 7.6%; Average loss: 3.6949
Iteration: 306; Percent complete: 7.6%; Average loss: 3.8159
Iteration: 307; Percent complete: 7.7%; Average loss: 4.1399
Iteration: 308; Percent complete: 7.7%; Average loss: 4.0836
Iteration: 309; Percent complete: 7.7%; Average loss: 3.9597
Iteration: 310; Percent complete: 7.8%; Average loss: 3.8037
Iteration: 311; Percent complete: 7.8%; Average loss: 3.8835
Iteration: 312; Percent complete: 7.8%; Average loss: 3.9866
Iteration: 313; Percent complete: 7.8%; Average loss: 3.7882
Iteration: 314; Percent complete: 7.8%; Average loss: 3.7799
Iteration: 315; Percent complete: 7.9%; Average loss: 3.9082
Iteration: 316; Percent complete: 7.9%; Average loss: 3.9901
Iteration: 317; Percent complete: 7.9%; Average loss: 3.8813
Iteration: 318; Percent complete: 8.0%; Average loss: 3.8709
Iteration: 319; Percent complete: 8.0%; Average loss: 3.8676
Iteration: 320; Percent complete: 8.0%; Average loss: 3.9246
Iteration: 321; Percent complete: 8.0%; Average loss: 3.9619
Iteration: 322; Percent complete: 8.1%; Average loss: 4.0323
Iteration: 323; Percent complete: 8.1%; Average loss: 3.6593
Iteration: 324; Percent complete: 8.1%; Average loss: 3.9090
Iteration: 325; Percent complete: 8.1%; Average loss: 4.1465
Iteration: 326; Percent complete: 8.2%; Average loss: 3.7273
Iteration: 327; Percent complete: 8.2%; Average loss: 3.5930
Iteration: 328; Percent complete: 8.2%; Average loss: 3.9104
Iteration: 329; Percent complete: 8.2%; Average loss: 3.9441
Iteration: 330; Percent complete: 8.2%; Average loss: 4.3175
Iteration: 331; Percent complete: 8.3%; Average loss: 3.8381
Iteration: 332; Percent complete: 8.3%; Average loss: 3.8008
Iteration: 333; Percent complete: 8.3%; Average loss: 3.9297
Iteration: 334; Percent complete: 8.3%; Average loss: 3.9645
Iteration: 335; Percent complete: 8.4%; Average loss: 3.9415
Iteration: 336; Percent complete: 8.4%; Average loss: 3.7098
Iteration: 337; Percent complete: 8.4%; Average loss: 3.8722
Iteration: 338; Percent complete: 8.5%; Average loss: 3.6527
Iteration: 339; Percent complete: 8.5%; Average loss: 3.8391
Iteration: 340; Percent complete: 8.5%; Average loss: 3.6013
Iteration: 341; Percent complete: 8.5%; Average loss: 4.0307
Iteration: 342; Percent complete: 8.6%; Average loss: 3.9830
Iteration: 343; Percent complete: 8.6%; Average loss: 3.7976
Iteration: 344; Percent complete: 8.6%; Average loss: 3.8227
Iteration: 345; Percent complete: 8.6%; Average loss: 3.8976
Iteration: 346; Percent complete: 8.6%; Average loss: 3.6276
Iteration: 347; Percent complete: 8.7%; Average loss: 3.7161
Iteration: 348; Percent complete: 8.7%; Average loss: 3.6922
Iteration: 349; Percent complete: 8.7%; Average loss: 3.8490
Iteration: 350; Percent complete: 8.8%; Average loss: 3.5736
Iteration: 351; Percent complete: 8.8%; Average loss: 3.8414
Iteration: 352; Percent complete: 8.8%; Average loss: 3.6222
Iteration: 353; Percent complete: 8.8%; Average loss: 3.6662
Iteration: 354; Percent complete: 8.8%; Average loss: 4.1063
Iteration: 355; Percent complete: 8.9%; Average loss: 3.9359
Iteration: 356; Percent complete: 8.9%; Average loss: 3.9760
Iteration: 357; Percent complete: 8.9%; Average loss: 3.6645
Iteration: 358; Percent complete: 8.9%; Average loss: 3.9002
Iteration: 359; Percent complete: 9.0%; Average loss: 4.1305
Iteration: 360; Percent complete: 9.0%; Average loss: 3.9099
Iteration: 361; Percent complete: 9.0%; Average loss: 3.7931
Iteration: 362; Percent complete: 9.0%; Average loss: 3.8985
Iteration: 363; Percent complete: 9.1%; Average loss: 4.0900
Iteration: 364; Percent complete: 9.1%; Average loss: 4.0107
Iteration: 365; Percent complete: 9.1%; Average loss: 3.8491
Iteration: 366; Percent complete: 9.2%; Average loss: 3.9591
Iteration: 367; Percent complete: 9.2%; Average loss: 3.8329
Iteration: 368; Percent complete: 9.2%; Average loss: 4.0219
Iteration: 369; Percent complete: 9.2%; Average loss: 3.9347
Iteration: 370; Percent complete: 9.2%; Average loss: 3.9485
Iteration: 371; Percent complete: 9.3%; Average loss: 3.8588
Iteration: 372; Percent complete: 9.3%; Average loss: 3.6933
Iteration: 373; Percent complete: 9.3%; Average loss: 4.0289
Iteration: 374; Percent complete: 9.3%; Average loss: 3.9471
Iteration: 375; Percent complete: 9.4%; Average loss: 3.6941
Iteration: 376; Percent complete: 9.4%; Average loss: 3.7341
Iteration: 377; Percent complete: 9.4%; Average loss: 3.9390
Iteration: 378; Percent complete: 9.4%; Average loss: 3.9145
Iteration: 379; Percent complete: 9.5%; Average loss: 3.6447
Iteration: 380; Percent complete: 9.5%; Average loss: 3.8348
Iteration: 381; Percent complete: 9.5%; Average loss: 3.7274
Iteration: 382; Percent complete: 9.6%; Average loss: 4.1321
Iteration: 383; Percent complete: 9.6%; Average loss: 3.7824
Iteration: 384; Percent complete: 9.6%; Average loss: 3.6840
Iteration: 385; Percent complete: 9.6%; Average loss: 4.0317
Iteration: 386; Percent complete: 9.7%; Average loss: 3.6311
Iteration: 387; Percent complete: 9.7%; Average loss: 3.6368
Iteration: 388; Percent complete: 9.7%; Average loss: 3.9384
Iteration: 389; Percent complete: 9.7%; Average loss: 3.9344
Iteration: 390; Percent complete: 9.8%; Average loss: 3.5532
Iteration: 391; Percent complete: 9.8%; Average loss: 3.4616
Iteration: 392; Percent complete: 9.8%; Average loss: 3.9613
Iteration: 393; Percent complete: 9.8%; Average loss: 3.7296
Iteration: 394; Percent complete: 9.8%; Average loss: 3.7313
Iteration: 395; Percent complete: 9.9%; Average loss: 3.8865
Iteration: 396; Percent complete: 9.9%; Average loss: 3.7064
Iteration: 397; Percent complete: 9.9%; Average loss: 3.8623
Iteration: 398; Percent complete: 10.0%; Average loss: 3.8631
Iteration: 399; Percent complete: 10.0%; Average loss: 3.6312
Iteration: 400; Percent complete: 10.0%; Average loss: 3.7673
Iteration: 401; Percent complete: 10.0%; Average loss: 3.5608
Iteration: 402; Percent complete: 10.1%; Average loss: 3.8913
Iteration: 403; Percent complete: 10.1%; Average loss: 3.8569
Iteration: 404; Percent complete: 10.1%; Average loss: 3.7100
Iteration: 405; Percent complete: 10.1%; Average loss: 3.7379
Iteration: 406; Percent complete: 10.2%; Average loss: 3.5784
Iteration: 407; Percent complete: 10.2%; Average loss: 3.6956
Iteration: 408; Percent complete: 10.2%; Average loss: 3.6799
Iteration: 409; Percent complete: 10.2%; Average loss: 3.9141
Iteration: 410; Percent complete: 10.2%; Average loss: 3.8793
Iteration: 411; Percent complete: 10.3%; Average loss: 3.9216
Iteration: 412; Percent complete: 10.3%; Average loss: 3.9336
Iteration: 413; Percent complete: 10.3%; Average loss: 4.0373
Iteration: 414; Percent complete: 10.3%; Average loss: 3.6945
Iteration: 415; Percent complete: 10.4%; Average loss: 3.7114
Iteration: 416; Percent complete: 10.4%; Average loss: 3.8539
Iteration: 417; Percent complete: 10.4%; Average loss: 3.7215
Iteration: 418; Percent complete: 10.4%; Average loss: 4.1428
Iteration: 419; Percent complete: 10.5%; Average loss: 3.7562
Iteration: 420; Percent complete: 10.5%; Average loss: 4.0272
Iteration: 421; Percent complete: 10.5%; Average loss: 3.7399
Iteration: 422; Percent complete: 10.5%; Average loss: 3.7288
Iteration: 423; Percent complete: 10.6%; Average loss: 4.0798
Iteration: 424; Percent complete: 10.6%; Average loss: 3.6014
Iteration: 425; Percent complete: 10.6%; Average loss: 3.7664
Iteration: 426; Percent complete: 10.7%; Average loss: 3.9485
Iteration: 427; Percent complete: 10.7%; Average loss: 3.9143
Iteration: 428; Percent complete: 10.7%; Average loss: 3.9289
Iteration: 429; Percent complete: 10.7%; Average loss: 3.5306
Iteration: 430; Percent complete: 10.8%; Average loss: 4.0006
Iteration: 431; Percent complete: 10.8%; Average loss: 3.7556
Iteration: 432; Percent complete: 10.8%; Average loss: 3.7407
Iteration: 433; Percent complete: 10.8%; Average loss: 3.7655
Iteration: 434; Percent complete: 10.8%; Average loss: 3.6605
Iteration: 435; Percent complete: 10.9%; Average loss: 3.5980
Iteration: 436; Percent complete: 10.9%; Average loss: 3.6906
Iteration: 437; Percent complete: 10.9%; Average loss: 3.7897
Iteration: 438; Percent complete: 10.9%; Average loss: 3.7414
Iteration: 439; Percent complete: 11.0%; Average loss: 3.7839
Iteration: 440; Percent complete: 11.0%; Average loss: 3.7198
Iteration: 441; Percent complete: 11.0%; Average loss: 3.9850
Iteration: 442; Percent complete: 11.1%; Average loss: 3.6715
Iteration: 443; Percent complete: 11.1%; Average loss: 3.8559
Iteration: 444; Percent complete: 11.1%; Average loss: 3.8565
Iteration: 445; Percent complete: 11.1%; Average loss: 3.8572
Iteration: 446; Percent complete: 11.2%; Average loss: 3.7731
Iteration: 447; Percent complete: 11.2%; Average loss: 3.5797
Iteration: 448; Percent complete: 11.2%; Average loss: 3.8073
Iteration: 449; Percent complete: 11.2%; Average loss: 3.6091
Iteration: 450; Percent complete: 11.2%; Average loss: 3.6493
Iteration: 451; Percent complete: 11.3%; Average loss: 3.8250
Iteration: 452; Percent complete: 11.3%; Average loss: 3.8141
Iteration: 453; Percent complete: 11.3%; Average loss: 3.6972
Iteration: 454; Percent complete: 11.3%; Average loss: 3.6483
Iteration: 455; Percent complete: 11.4%; Average loss: 3.6606
Iteration: 456; Percent complete: 11.4%; Average loss: 3.7099
Iteration: 457; Percent complete: 11.4%; Average loss: 3.9018
Iteration: 458; Percent complete: 11.5%; Average loss: 3.4958
Iteration: 459; Percent complete: 11.5%; Average loss: 3.6578
Iteration: 460; Percent complete: 11.5%; Average loss: 3.7306
Iteration: 461; Percent complete: 11.5%; Average loss: 3.9495
Iteration: 462; Percent complete: 11.6%; Average loss: 3.6450
Iteration: 463; Percent complete: 11.6%; Average loss: 3.6913
Iteration: 464; Percent complete: 11.6%; Average loss: 3.7125
Iteration: 465; Percent complete: 11.6%; Average loss: 3.8105
Iteration: 466; Percent complete: 11.7%; Average loss: 3.6656
Iteration: 467; Percent complete: 11.7%; Average loss: 3.6602
Iteration: 468; Percent complete: 11.7%; Average loss: 3.5656
Iteration: 469; Percent complete: 11.7%; Average loss: 3.6944
Iteration: 470; Percent complete: 11.8%; Average loss: 3.7346
Iteration: 471; Percent complete: 11.8%; Average loss: 3.7114
Iteration: 472; Percent complete: 11.8%; Average loss: 3.6425
Iteration: 473; Percent complete: 11.8%; Average loss: 3.8167
Iteration: 474; Percent complete: 11.8%; Average loss: 3.8009
Iteration: 475; Percent complete: 11.9%; Average loss: 3.7616
Iteration: 476; Percent complete: 11.9%; Average loss: 3.8613
Iteration: 477; Percent complete: 11.9%; Average loss: 3.7626
Iteration: 478; Percent complete: 11.9%; Average loss: 3.7461
Iteration: 479; Percent complete: 12.0%; Average loss: 3.7788
Iteration: 480; Percent complete: 12.0%; Average loss: 3.4848
Iteration: 481; Percent complete: 12.0%; Average loss: 3.8531
Iteration: 482; Percent complete: 12.0%; Average loss: 3.6986
Iteration: 483; Percent complete: 12.1%; Average loss: 3.9122
Iteration: 484; Percent complete: 12.1%; Average loss: 3.5155
Iteration: 485; Percent complete: 12.1%; Average loss: 3.7182
Iteration: 486; Percent complete: 12.2%; Average loss: 3.7287
Iteration: 487; Percent complete: 12.2%; Average loss: 3.7258
Iteration: 488; Percent complete: 12.2%; Average loss: 3.6258
Iteration: 489; Percent complete: 12.2%; Average loss: 3.7610
Iteration: 490; Percent complete: 12.2%; Average loss: 3.4927
Iteration: 491; Percent complete: 12.3%; Average loss: 3.8851
Iteration: 492; Percent complete: 12.3%; Average loss: 3.7708
Iteration: 493; Percent complete: 12.3%; Average loss: 3.9443
Iteration: 494; Percent complete: 12.3%; Average loss: 3.6176
Iteration: 495; Percent complete: 12.4%; Average loss: 3.5575
Iteration: 496; Percent complete: 12.4%; Average loss: 3.7427
Iteration: 497; Percent complete: 12.4%; Average loss: 3.5525
Iteration: 498; Percent complete: 12.4%; Average loss: 3.8968
Iteration: 499; Percent complete: 12.5%; Average loss: 3.7377
Iteration: 500; Percent complete: 12.5%; Average loss: 3.5727
Iteration: 501; Percent complete: 12.5%; Average loss: 3.7151
Iteration: 502; Percent complete: 12.6%; Average loss: 3.4931
Iteration: 503; Percent complete: 12.6%; Average loss: 3.8755
Iteration: 504; Percent complete: 12.6%; Average loss: 3.7015
Iteration: 505; Percent complete: 12.6%; Average loss: 3.7943
Iteration: 506; Percent complete: 12.7%; Average loss: 3.7577
Iteration: 507; Percent complete: 12.7%; Average loss: 3.6722
Iteration: 508; Percent complete: 12.7%; Average loss: 3.8040
Iteration: 509; Percent complete: 12.7%; Average loss: 3.5294
Iteration: 510; Percent complete: 12.8%; Average loss: 3.7556
Iteration: 511; Percent complete: 12.8%; Average loss: 3.7798
Iteration: 512; Percent complete: 12.8%; Average loss: 3.5429
Iteration: 513; Percent complete: 12.8%; Average loss: 3.8102
Iteration: 514; Percent complete: 12.8%; Average loss: 3.7360
Iteration: 515; Percent complete: 12.9%; Average loss: 4.1645
Iteration: 516; Percent complete: 12.9%; Average loss: 3.7958
Iteration: 517; Percent complete: 12.9%; Average loss: 3.8648
Iteration: 518; Percent complete: 13.0%; Average loss: 3.5512
Iteration: 519; Percent complete: 13.0%; Average loss: 3.7437
Iteration: 520; Percent complete: 13.0%; Average loss: 3.9365
Iteration: 521; Percent complete: 13.0%; Average loss: 3.6938
Iteration: 522; Percent complete: 13.1%; Average loss: 3.5977
Iteration: 523; Percent complete: 13.1%; Average loss: 3.7834
Iteration: 524; Percent complete: 13.1%; Average loss: 3.9605
Iteration: 525; Percent complete: 13.1%; Average loss: 3.6458
Iteration: 526; Percent complete: 13.2%; Average loss: 3.6740
Iteration: 527; Percent complete: 13.2%; Average loss: 3.8104
Iteration: 528; Percent complete: 13.2%; Average loss: 3.7681
Iteration: 529; Percent complete: 13.2%; Average loss: 3.6885
Iteration: 530; Percent complete: 13.2%; Average loss: 3.6623
Iteration: 531; Percent complete: 13.3%; Average loss: 3.3639
Iteration: 532; Percent complete: 13.3%; Average loss: 3.8640
Iteration: 533; Percent complete: 13.3%; Average loss: 3.6320
Iteration: 534; Percent complete: 13.4%; Average loss: 3.8649
Iteration: 535; Percent complete: 13.4%; Average loss: 3.8132
Iteration: 536; Percent complete: 13.4%; Average loss: 3.7965
Iteration: 537; Percent complete: 13.4%; Average loss: 3.9199
Iteration: 538; Percent complete: 13.5%; Average loss: 3.7882
Iteration: 539; Percent complete: 13.5%; Average loss: 4.0227
Iteration: 540; Percent complete: 13.5%; Average loss: 3.6868
Iteration: 541; Percent complete: 13.5%; Average loss: 3.6229
Iteration: 542; Percent complete: 13.6%; Average loss: 3.5668
Iteration: 543; Percent complete: 13.6%; Average loss: 3.6396
Iteration: 544; Percent complete: 13.6%; Average loss: 3.6187
Iteration: 545; Percent complete: 13.6%; Average loss: 3.6759
Iteration: 546; Percent complete: 13.7%; Average loss: 3.6350
Iteration: 547; Percent complete: 13.7%; Average loss: 3.8221
Iteration: 548; Percent complete: 13.7%; Average loss: 3.7731
Iteration: 549; Percent complete: 13.7%; Average loss: 3.6920
Iteration: 550; Percent complete: 13.8%; Average loss: 3.8313
Iteration: 551; Percent complete: 13.8%; Average loss: 3.9038
Iteration: 552; Percent complete: 13.8%; Average loss: 3.8158
Iteration: 553; Percent complete: 13.8%; Average loss: 3.8327
Iteration: 554; Percent complete: 13.9%; Average loss: 3.9651
Iteration: 555; Percent complete: 13.9%; Average loss: 3.5296
Iteration: 556; Percent complete: 13.9%; Average loss: 3.8322
Iteration: 557; Percent complete: 13.9%; Average loss: 3.4161
Iteration: 558; Percent complete: 14.0%; Average loss: 3.5561
Iteration: 559; Percent complete: 14.0%; Average loss: 3.8895
Iteration: 560; Percent complete: 14.0%; Average loss: 3.5619
Iteration: 561; Percent complete: 14.0%; Average loss: 3.7444
Iteration: 562; Percent complete: 14.1%; Average loss: 3.8519
Iteration: 563; Percent complete: 14.1%; Average loss: 3.6356
Iteration: 564; Percent complete: 14.1%; Average loss: 3.6071
Iteration: 565; Percent complete: 14.1%; Average loss: 3.5624
Iteration: 566; Percent complete: 14.1%; Average loss: 3.7380
Iteration: 567; Percent complete: 14.2%; Average loss: 3.6641
Iteration: 568; Percent complete: 14.2%; Average loss: 4.0719
Iteration: 569; Percent complete: 14.2%; Average loss: 3.6583
Iteration: 570; Percent complete: 14.2%; Average loss: 3.4781
Iteration: 571; Percent complete: 14.3%; Average loss: 3.7384
Iteration: 572; Percent complete: 14.3%; Average loss: 3.6090
Iteration: 573; Percent complete: 14.3%; Average loss: 3.7939
Iteration: 574; Percent complete: 14.3%; Average loss: 3.9175
Iteration: 575; Percent complete: 14.4%; Average loss: 3.7516
Iteration: 576; Percent complete: 14.4%; Average loss: 3.6613
Iteration: 577; Percent complete: 14.4%; Average loss: 3.4435
Iteration: 578; Percent complete: 14.4%; Average loss: 3.7193
Iteration: 579; Percent complete: 14.5%; Average loss: 3.7621
Iteration: 580; Percent complete: 14.5%; Average loss: 3.4907
Iteration: 581; Percent complete: 14.5%; Average loss: 3.3521
Iteration: 582; Percent complete: 14.5%; Average loss: 3.3923
Iteration: 583; Percent complete: 14.6%; Average loss: 3.6233
Iteration: 584; Percent complete: 14.6%; Average loss: 3.4187
Iteration: 585; Percent complete: 14.6%; Average loss: 3.7513
Iteration: 586; Percent complete: 14.6%; Average loss: 3.7195
Iteration: 587; Percent complete: 14.7%; Average loss: 3.7587
Iteration: 588; Percent complete: 14.7%; Average loss: 3.6136
Iteration: 589; Percent complete: 14.7%; Average loss: 3.5320
Iteration: 590; Percent complete: 14.8%; Average loss: 3.8580
Iteration: 591; Percent complete: 14.8%; Average loss: 3.9025
Iteration: 592; Percent complete: 14.8%; Average loss: 3.5942
Iteration: 593; Percent complete: 14.8%; Average loss: 3.4829
Iteration: 594; Percent complete: 14.8%; Average loss: 3.7167
Iteration: 595; Percent complete: 14.9%; Average loss: 3.6980
Iteration: 596; Percent complete: 14.9%; Average loss: 3.6387
Iteration: 597; Percent complete: 14.9%; Average loss: 3.7149
Iteration: 598; Percent complete: 14.9%; Average loss: 3.5385
Iteration: 599; Percent complete: 15.0%; Average loss: 3.8817
Iteration: 600; Percent complete: 15.0%; Average loss: 3.4826
Iteration: 601; Percent complete: 15.0%; Average loss: 3.8166
Iteration: 602; Percent complete: 15.0%; Average loss: 3.6540
Iteration: 603; Percent complete: 15.1%; Average loss: 3.7987
Iteration: 604; Percent complete: 15.1%; Average loss: 3.4129
Iteration: 605; Percent complete: 15.1%; Average loss: 3.4222
Iteration: 606; Percent complete: 15.2%; Average loss: 3.6654
Iteration: 607; Percent complete: 15.2%; Average loss: 3.7225
Iteration: 608; Percent complete: 15.2%; Average loss: 3.5616
Iteration: 609; Percent complete: 15.2%; Average loss: 3.6154
Iteration: 610; Percent complete: 15.2%; Average loss: 3.6312
Iteration: 611; Percent complete: 15.3%; Average loss: 3.9421
Iteration: 612; Percent complete: 15.3%; Average loss: 3.5484
Iteration: 613; Percent complete: 15.3%; Average loss: 3.5769
Iteration: 614; Percent complete: 15.3%; Average loss: 3.4761
Iteration: 615; Percent complete: 15.4%; Average loss: 3.6347
Iteration: 616; Percent complete: 15.4%; Average loss: 3.6078
Iteration: 617; Percent complete: 15.4%; Average loss: 3.5473
Iteration: 618; Percent complete: 15.4%; Average loss: 3.7847
Iteration: 619; Percent complete: 15.5%; Average loss: 3.7241
Iteration: 620; Percent complete: 15.5%; Average loss: 3.6317
Iteration: 621; Percent complete: 15.5%; Average loss: 3.6756
Iteration: 622; Percent complete: 15.6%; Average loss: 3.4804
Iteration: 623; Percent complete: 15.6%; Average loss: 3.5836
Iteration: 624; Percent complete: 15.6%; Average loss: 3.6889
Iteration: 625; Percent complete: 15.6%; Average loss: 3.6265
Iteration: 626; Percent complete: 15.7%; Average loss: 3.7825
Iteration: 627; Percent complete: 15.7%; Average loss: 3.7927
Iteration: 628; Percent complete: 15.7%; Average loss: 3.6270
Iteration: 629; Percent complete: 15.7%; Average loss: 3.6606
Iteration: 630; Percent complete: 15.8%; Average loss: 3.6412
Iteration: 631; Percent complete: 15.8%; Average loss: 3.5436
Iteration: 632; Percent complete: 15.8%; Average loss: 3.5139
Iteration: 633; Percent complete: 15.8%; Average loss: 3.6964
Iteration: 634; Percent complete: 15.8%; Average loss: 3.6398
Iteration: 635; Percent complete: 15.9%; Average loss: 3.9063
Iteration: 636; Percent complete: 15.9%; Average loss: 3.6900
Iteration: 637; Percent complete: 15.9%; Average loss: 3.6274
Iteration: 638; Percent complete: 16.0%; Average loss: 3.6267
Iteration: 639; Percent complete: 16.0%; Average loss: 3.5963
Iteration: 640; Percent complete: 16.0%; Average loss: 3.5884
Iteration: 641; Percent complete: 16.0%; Average loss: 3.6606
Iteration: 642; Percent complete: 16.1%; Average loss: 3.5993
Iteration: 643; Percent complete: 16.1%; Average loss: 3.6751
Iteration: 644; Percent complete: 16.1%; Average loss: 3.5053
Iteration: 645; Percent complete: 16.1%; Average loss: 3.6254
Iteration: 646; Percent complete: 16.2%; Average loss: 3.4618
Iteration: 647; Percent complete: 16.2%; Average loss: 3.8544
Iteration: 648; Percent complete: 16.2%; Average loss: 3.6414
Iteration: 649; Percent complete: 16.2%; Average loss: 3.6373
Iteration: 650; Percent complete: 16.2%; Average loss: 3.9163
Iteration: 651; Percent complete: 16.3%; Average loss: 3.7072
Iteration: 652; Percent complete: 16.3%; Average loss: 3.2147
Iteration: 653; Percent complete: 16.3%; Average loss: 3.5654
Iteration: 654; Percent complete: 16.4%; Average loss: 3.7620
Iteration: 655; Percent complete: 16.4%; Average loss: 3.7383
Iteration: 656; Percent complete: 16.4%; Average loss: 3.8160
Iteration: 657; Percent complete: 16.4%; Average loss: 3.6370
Iteration: 658; Percent complete: 16.4%; Average loss: 3.5588
Iteration: 659; Percent complete: 16.5%; Average loss: 3.4140
Iteration: 660; Percent complete: 16.5%; Average loss: 3.8455
Iteration: 661; Percent complete: 16.5%; Average loss: 3.7899
Iteration: 662; Percent complete: 16.6%; Average loss: 3.3075
Iteration: 663; Percent complete: 16.6%; Average loss: 3.5242
Iteration: 664; Percent complete: 16.6%; Average loss: 3.5142
Iteration: 665; Percent complete: 16.6%; Average loss: 3.7421
Iteration: 666; Percent complete: 16.7%; Average loss: 3.3352
Iteration: 667; Percent complete: 16.7%; Average loss: 3.6031
Iteration: 668; Percent complete: 16.7%; Average loss: 3.4817
Iteration: 669; Percent complete: 16.7%; Average loss: 3.3138
Iteration: 670; Percent complete: 16.8%; Average loss: 3.4794
Iteration: 671; Percent complete: 16.8%; Average loss: 3.6634
Iteration: 672; Percent complete: 16.8%; Average loss: 3.6202
Iteration: 673; Percent complete: 16.8%; Average loss: 3.4466
Iteration: 674; Percent complete: 16.9%; Average loss: 3.7260
Iteration: 675; Percent complete: 16.9%; Average loss: 3.4744
Iteration: 676; Percent complete: 16.9%; Average loss: 3.9665
Iteration: 677; Percent complete: 16.9%; Average loss: 3.7981
Iteration: 678; Percent complete: 17.0%; Average loss: 3.5636
Iteration: 679; Percent complete: 17.0%; Average loss: 3.5306
Iteration: 680; Percent complete: 17.0%; Average loss: 3.7548
Iteration: 681; Percent complete: 17.0%; Average loss: 3.8728
Iteration: 682; Percent complete: 17.1%; Average loss: 3.4438
Iteration: 683; Percent complete: 17.1%; Average loss: 3.7450
Iteration: 684; Percent complete: 17.1%; Average loss: 3.4951
Iteration: 685; Percent complete: 17.1%; Average loss: 3.6532
Iteration: 686; Percent complete: 17.2%; Average loss: 3.6963
Iteration: 687; Percent complete: 17.2%; Average loss: 3.3863
Iteration: 688; Percent complete: 17.2%; Average loss: 3.6743
Iteration: 689; Percent complete: 17.2%; Average loss: 3.4703
Iteration: 690; Percent complete: 17.2%; Average loss: 3.6152
Iteration: 691; Percent complete: 17.3%; Average loss: 3.5729
Iteration: 692; Percent complete: 17.3%; Average loss: 3.7238
Iteration: 693; Percent complete: 17.3%; Average loss: 3.6817
Iteration: 694; Percent complete: 17.3%; Average loss: 3.8210
Iteration: 695; Percent complete: 17.4%; Average loss: 3.6726
Iteration: 696; Percent complete: 17.4%; Average loss: 3.5239
Iteration: 697; Percent complete: 17.4%; Average loss: 3.8996
Iteration: 698; Percent complete: 17.4%; Average loss: 3.5211
Iteration: 699; Percent complete: 17.5%; Average loss: 3.6021
Iteration: 700; Percent complete: 17.5%; Average loss: 3.6629
Iteration: 701; Percent complete: 17.5%; Average loss: 3.8223
Iteration: 702; Percent complete: 17.5%; Average loss: 3.5615
Iteration: 703; Percent complete: 17.6%; Average loss: 3.5871
Iteration: 704; Percent complete: 17.6%; Average loss: 3.6780
Iteration: 705; Percent complete: 17.6%; Average loss: 3.5766
Iteration: 706; Percent complete: 17.6%; Average loss: 3.8248
Iteration: 707; Percent complete: 17.7%; Average loss: 3.3607
Iteration: 708; Percent complete: 17.7%; Average loss: 3.9429
Iteration: 709; Percent complete: 17.7%; Average loss: 3.5245
Iteration: 710; Percent complete: 17.8%; Average loss: 3.5383
Iteration: 711; Percent complete: 17.8%; Average loss: 3.4526
Iteration: 712; Percent complete: 17.8%; Average loss: 3.5073
Iteration: 713; Percent complete: 17.8%; Average loss: 3.6642
Iteration: 714; Percent complete: 17.8%; Average loss: 3.6344
Iteration: 715; Percent complete: 17.9%; Average loss: 3.5727
Iteration: 716; Percent complete: 17.9%; Average loss: 3.7407
Iteration: 717; Percent complete: 17.9%; Average loss: 3.4670
Iteration: 718; Percent complete: 17.9%; Average loss: 3.5144
Iteration: 719; Percent complete: 18.0%; Average loss: 3.5764
Iteration: 720; Percent complete: 18.0%; Average loss: 3.4506
Iteration: 721; Percent complete: 18.0%; Average loss: 3.4045
Iteration: 722; Percent complete: 18.1%; Average loss: 3.6030
Iteration: 723; Percent complete: 18.1%; Average loss: 3.5534
Iteration: 724; Percent complete: 18.1%; Average loss: 3.7328
Iteration: 725; Percent complete: 18.1%; Average loss: 3.5407
Iteration: 726; Percent complete: 18.1%; Average loss: 3.5222
Iteration: 727; Percent complete: 18.2%; Average loss: 3.6757
Iteration: 728; Percent complete: 18.2%; Average loss: 3.5590
Iteration: 729; Percent complete: 18.2%; Average loss: 3.5861
Iteration: 730; Percent complete: 18.2%; Average loss: 3.6394
Iteration: 731; Percent complete: 18.3%; Average loss: 3.5381
Iteration: 732; Percent complete: 18.3%; Average loss: 3.7433
Iteration: 733; Percent complete: 18.3%; Average loss: 3.5274
Iteration: 734; Percent complete: 18.4%; Average loss: 3.6682
Iteration: 735; Percent complete: 18.4%; Average loss: 3.4658
Iteration: 736; Percent complete: 18.4%; Average loss: 3.6021
Iteration: 737; Percent complete: 18.4%; Average loss: 3.4824
Iteration: 738; Percent complete: 18.4%; Average loss: 3.6935
Iteration: 739; Percent complete: 18.5%; Average loss: 3.5674
Iteration: 740; Percent complete: 18.5%; Average loss: 3.6377
Iteration: 741; Percent complete: 18.5%; Average loss: 3.7723
Iteration: 742; Percent complete: 18.6%; Average loss: 3.7500
Iteration: 743; Percent complete: 18.6%; Average loss: 3.6103
Iteration: 744; Percent complete: 18.6%; Average loss: 3.6217
Iteration: 745; Percent complete: 18.6%; Average loss: 3.7909
Iteration: 746; Percent complete: 18.6%; Average loss: 3.3940
Iteration: 747; Percent complete: 18.7%; Average loss: 3.7081
Iteration: 748; Percent complete: 18.7%; Average loss: 3.6269
Iteration: 749; Percent complete: 18.7%; Average loss: 3.4627
Iteration: 750; Percent complete: 18.8%; Average loss: 3.4989
Iteration: 751; Percent complete: 18.8%; Average loss: 3.7976
Iteration: 752; Percent complete: 18.8%; Average loss: 3.6433
Iteration: 753; Percent complete: 18.8%; Average loss: 3.4819
Iteration: 754; Percent complete: 18.9%; Average loss: 3.5833
Iteration: 755; Percent complete: 18.9%; Average loss: 3.7984
Iteration: 756; Percent complete: 18.9%; Average loss: 3.6393
Iteration: 757; Percent complete: 18.9%; Average loss: 3.4014
Iteration: 758; Percent complete: 18.9%; Average loss: 3.6010
Iteration: 759; Percent complete: 19.0%; Average loss: 3.5856
Iteration: 760; Percent complete: 19.0%; Average loss: 3.5406
Iteration: 761; Percent complete: 19.0%; Average loss: 3.3574
Iteration: 762; Percent complete: 19.1%; Average loss: 3.5825
Iteration: 763; Percent complete: 19.1%; Average loss: 3.7414
Iteration: 764; Percent complete: 19.1%; Average loss: 3.6878
Iteration: 765; Percent complete: 19.1%; Average loss: 3.4194
Iteration: 766; Percent complete: 19.1%; Average loss: 3.2980
Iteration: 767; Percent complete: 19.2%; Average loss: 3.5233
Iteration: 768; Percent complete: 19.2%; Average loss: 3.5771
Iteration: 769; Percent complete: 19.2%; Average loss: 3.8150
Iteration: 770; Percent complete: 19.2%; Average loss: 3.6141
Iteration: 771; Percent complete: 19.3%; Average loss: 3.2751
Iteration: 772; Percent complete: 19.3%; Average loss: 3.7005
Iteration: 773; Percent complete: 19.3%; Average loss: 3.4115
Iteration: 774; Percent complete: 19.4%; Average loss: 3.5883
Iteration: 775; Percent complete: 19.4%; Average loss: 3.4039
Iteration: 776; Percent complete: 19.4%; Average loss: 3.2770
Iteration: 777; Percent complete: 19.4%; Average loss: 3.3425
Iteration: 778; Percent complete: 19.4%; Average loss: 3.5559
Iteration: 779; Percent complete: 19.5%; Average loss: 3.2952
Iteration: 780; Percent complete: 19.5%; Average loss: 3.5342
Iteration: 781; Percent complete: 19.5%; Average loss: 3.5028
Iteration: 782; Percent complete: 19.6%; Average loss: 3.8357
Iteration: 783; Percent complete: 19.6%; Average loss: 3.5149
Iteration: 784; Percent complete: 19.6%; Average loss: 3.6447
Iteration: 785; Percent complete: 19.6%; Average loss: 3.7093
Iteration: 786; Percent complete: 19.7%; Average loss: 3.4871
Iteration: 787; Percent complete: 19.7%; Average loss: 3.3004
Iteration: 788; Percent complete: 19.7%; Average loss: 3.7540
Iteration: 789; Percent complete: 19.7%; Average loss: 3.6776
Iteration: 790; Percent complete: 19.8%; Average loss: 3.5872
Iteration: 791; Percent complete: 19.8%; Average loss: 3.6108
Iteration: 792; Percent complete: 19.8%; Average loss: 3.4710
Iteration: 793; Percent complete: 19.8%; Average loss: 3.6528
Iteration: 794; Percent complete: 19.9%; Average loss: 3.4303
Iteration: 795; Percent complete: 19.9%; Average loss: 3.4701
Iteration: 796; Percent complete: 19.9%; Average loss: 3.4332
Iteration: 797; Percent complete: 19.9%; Average loss: 3.4482
Iteration: 798; Percent complete: 20.0%; Average loss: 3.5367
Iteration: 799; Percent complete: 20.0%; Average loss: 3.6794
Iteration: 800; Percent complete: 20.0%; Average loss: 3.3255
Iteration: 801; Percent complete: 20.0%; Average loss: 3.6549
Iteration: 802; Percent complete: 20.1%; Average loss: 3.4173
Iteration: 803; Percent complete: 20.1%; Average loss: 3.4840
Iteration: 804; Percent complete: 20.1%; Average loss: 3.4812
Iteration: 805; Percent complete: 20.1%; Average loss: 3.7589
Iteration: 806; Percent complete: 20.2%; Average loss: 3.5295
Iteration: 807; Percent complete: 20.2%; Average loss: 3.3249
Iteration: 808; Percent complete: 20.2%; Average loss: 3.5157
Iteration: 809; Percent complete: 20.2%; Average loss: 3.4382
Iteration: 810; Percent complete: 20.2%; Average loss: 3.3747
Iteration: 811; Percent complete: 20.3%; Average loss: 3.7458
Iteration: 812; Percent complete: 20.3%; Average loss: 3.4069
Iteration: 813; Percent complete: 20.3%; Average loss: 3.7558
Iteration: 814; Percent complete: 20.3%; Average loss: 3.2873
Iteration: 815; Percent complete: 20.4%; Average loss: 3.5278
Iteration: 816; Percent complete: 20.4%; Average loss: 3.6849
Iteration: 817; Percent complete: 20.4%; Average loss: 3.4083
Iteration: 818; Percent complete: 20.4%; Average loss: 3.4112
Iteration: 819; Percent complete: 20.5%; Average loss: 3.8965
Iteration: 820; Percent complete: 20.5%; Average loss: 3.5038
Iteration: 821; Percent complete: 20.5%; Average loss: 3.4165
Iteration: 822; Percent complete: 20.5%; Average loss: 3.6525
Iteration: 823; Percent complete: 20.6%; Average loss: 3.3718
Iteration: 824; Percent complete: 20.6%; Average loss: 3.5262
Iteration: 825; Percent complete: 20.6%; Average loss: 3.4979
Iteration: 826; Percent complete: 20.6%; Average loss: 3.3582
Iteration: 827; Percent complete: 20.7%; Average loss: 3.7005
Iteration: 828; Percent complete: 20.7%; Average loss: 3.5064
Iteration: 829; Percent complete: 20.7%; Average loss: 3.6414
Iteration: 830; Percent complete: 20.8%; Average loss: 3.2227
Iteration: 831; Percent complete: 20.8%; Average loss: 3.5424
Iteration: 832; Percent complete: 20.8%; Average loss: 3.2432
Iteration: 833; Percent complete: 20.8%; Average loss: 3.1112
Iteration: 834; Percent complete: 20.8%; Average loss: 3.4203
Iteration: 835; Percent complete: 20.9%; Average loss: 3.4439
Iteration: 836; Percent complete: 20.9%; Average loss: 3.5556
Iteration: 837; Percent complete: 20.9%; Average loss: 3.4619
Iteration: 838; Percent complete: 20.9%; Average loss: 3.5484
Iteration: 839; Percent complete: 21.0%; Average loss: 3.5405
Iteration: 840; Percent complete: 21.0%; Average loss: 3.5985
Iteration: 841; Percent complete: 21.0%; Average loss: 3.5439
Iteration: 842; Percent complete: 21.1%; Average loss: 3.7257
Iteration: 843; Percent complete: 21.1%; Average loss: 3.6000
Iteration: 844; Percent complete: 21.1%; Average loss: 3.4936
Iteration: 845; Percent complete: 21.1%; Average loss: 3.4952
Iteration: 846; Percent complete: 21.1%; Average loss: 3.5860
Iteration: 847; Percent complete: 21.2%; Average loss: 3.4516
Iteration: 848; Percent complete: 21.2%; Average loss: 3.7534
Iteration: 849; Percent complete: 21.2%; Average loss: 3.6189
Iteration: 850; Percent complete: 21.2%; Average loss: 3.5668
Iteration: 851; Percent complete: 21.3%; Average loss: 3.8510
Iteration: 852; Percent complete: 21.3%; Average loss: 3.5052
Iteration: 853; Percent complete: 21.3%; Average loss: 3.5136
Iteration: 854; Percent complete: 21.3%; Average loss: 3.3478
Iteration: 855; Percent complete: 21.4%; Average loss: 3.5401
Iteration: 856; Percent complete: 21.4%; Average loss: 3.6082
Iteration: 857; Percent complete: 21.4%; Average loss: 3.9259
Iteration: 858; Percent complete: 21.4%; Average loss: 3.4504
Iteration: 859; Percent complete: 21.5%; Average loss: 3.8125
Iteration: 860; Percent complete: 21.5%; Average loss: 3.4016
Iteration: 861; Percent complete: 21.5%; Average loss: 3.4420
Iteration: 862; Percent complete: 21.6%; Average loss: 3.4928
Iteration: 863; Percent complete: 21.6%; Average loss: 3.3688
Iteration: 864; Percent complete: 21.6%; Average loss: 3.7096
Iteration: 865; Percent complete: 21.6%; Average loss: 3.6277
Iteration: 866; Percent complete: 21.6%; Average loss: 3.5116
Iteration: 867; Percent complete: 21.7%; Average loss: 3.7375
Iteration: 868; Percent complete: 21.7%; Average loss: 3.3587
Iteration: 869; Percent complete: 21.7%; Average loss: 3.3676
Iteration: 870; Percent complete: 21.8%; Average loss: 3.4681
Iteration: 871; Percent complete: 21.8%; Average loss: 3.5728
Iteration: 872; Percent complete: 21.8%; Average loss: 3.5097
Iteration: 873; Percent complete: 21.8%; Average loss: 3.7028
Iteration: 874; Percent complete: 21.9%; Average loss: 3.5048
Iteration: 875; Percent complete: 21.9%; Average loss: 3.4060
Iteration: 876; Percent complete: 21.9%; Average loss: 3.5212
Iteration: 877; Percent complete: 21.9%; Average loss: 3.4912
Iteration: 878; Percent complete: 21.9%; Average loss: 3.3415
Iteration: 879; Percent complete: 22.0%; Average loss: 3.6140
Iteration: 880; Percent complete: 22.0%; Average loss: 3.3549
Iteration: 881; Percent complete: 22.0%; Average loss: 3.6812
Iteration: 882; Percent complete: 22.1%; Average loss: 3.5239
Iteration: 883; Percent complete: 22.1%; Average loss: 3.7391
Iteration: 884; Percent complete: 22.1%; Average loss: 3.5923
Iteration: 885; Percent complete: 22.1%; Average loss: 3.5051
Iteration: 886; Percent complete: 22.1%; Average loss: 3.3182
Iteration: 887; Percent complete: 22.2%; Average loss: 3.5474
Iteration: 888; Percent complete: 22.2%; Average loss: 3.6914
Iteration: 889; Percent complete: 22.2%; Average loss: 3.4885
Iteration: 890; Percent complete: 22.2%; Average loss: 3.4719
Iteration: 891; Percent complete: 22.3%; Average loss: 3.4753
Iteration: 892; Percent complete: 22.3%; Average loss: 3.5064
Iteration: 893; Percent complete: 22.3%; Average loss: 3.6590
Iteration: 894; Percent complete: 22.4%; Average loss: 3.6318
Iteration: 895; Percent complete: 22.4%; Average loss: 3.4207
Iteration: 896; Percent complete: 22.4%; Average loss: 3.4886
Iteration: 897; Percent complete: 22.4%; Average loss: 3.4991
Iteration: 898; Percent complete: 22.4%; Average loss: 3.4023
Iteration: 899; Percent complete: 22.5%; Average loss: 3.5476
Iteration: 900; Percent complete: 22.5%; Average loss: 3.5635
Iteration: 901; Percent complete: 22.5%; Average loss: 3.6534
Iteration: 902; Percent complete: 22.6%; Average loss: 3.5360
Iteration: 903; Percent complete: 22.6%; Average loss: 3.5163
Iteration: 904; Percent complete: 22.6%; Average loss: 3.4580
Iteration: 905; Percent complete: 22.6%; Average loss: 3.4535
Iteration: 906; Percent complete: 22.7%; Average loss: 3.5290
Iteration: 907; Percent complete: 22.7%; Average loss: 3.4881
Iteration: 908; Percent complete: 22.7%; Average loss: 3.8438
Iteration: 909; Percent complete: 22.7%; Average loss: 3.8332
Iteration: 910; Percent complete: 22.8%; Average loss: 3.6569
Iteration: 911; Percent complete: 22.8%; Average loss: 3.4314
Iteration: 912; Percent complete: 22.8%; Average loss: 3.7218
Iteration: 913; Percent complete: 22.8%; Average loss: 3.7374
Iteration: 914; Percent complete: 22.9%; Average loss: 3.2967
Iteration: 915; Percent complete: 22.9%; Average loss: 3.8117
Iteration: 916; Percent complete: 22.9%; Average loss: 3.6658
Iteration: 917; Percent complete: 22.9%; Average loss: 3.6482
Iteration: 918; Percent complete: 22.9%; Average loss: 3.5940
Iteration: 919; Percent complete: 23.0%; Average loss: 3.6847
Iteration: 920; Percent complete: 23.0%; Average loss: 3.5818
Iteration: 921; Percent complete: 23.0%; Average loss: 3.5820
Iteration: 922; Percent complete: 23.1%; Average loss: 3.2771
Iteration: 923; Percent complete: 23.1%; Average loss: 3.4800
Iteration: 924; Percent complete: 23.1%; Average loss: 3.6292
Iteration: 925; Percent complete: 23.1%; Average loss: 3.3974
Iteration: 926; Percent complete: 23.2%; Average loss: 3.2396
Iteration: 927; Percent complete: 23.2%; Average loss: 3.5219
Iteration: 928; Percent complete: 23.2%; Average loss: 3.3047
Iteration: 929; Percent complete: 23.2%; Average loss: 3.7158
Iteration: 930; Percent complete: 23.2%; Average loss: 3.6794
Iteration: 931; Percent complete: 23.3%; Average loss: 3.3138
Iteration: 932; Percent complete: 23.3%; Average loss: 3.3433
Iteration: 933; Percent complete: 23.3%; Average loss: 3.6114
Iteration: 934; Percent complete: 23.4%; Average loss: 3.2817
Iteration: 935; Percent complete: 23.4%; Average loss: 3.3582
Iteration: 936; Percent complete: 23.4%; Average loss: 3.4414
Iteration: 937; Percent complete: 23.4%; Average loss: 3.3069
Iteration: 938; Percent complete: 23.4%; Average loss: 3.5288
Iteration: 939; Percent complete: 23.5%; Average loss: 3.3259
Iteration: 940; Percent complete: 23.5%; Average loss: 3.4090
Iteration: 941; Percent complete: 23.5%; Average loss: 3.6627
Iteration: 942; Percent complete: 23.5%; Average loss: 3.5979
Iteration: 943; Percent complete: 23.6%; Average loss: 3.2824
Iteration: 944; Percent complete: 23.6%; Average loss: 3.5318
Iteration: 945; Percent complete: 23.6%; Average loss: 3.4188
Iteration: 946; Percent complete: 23.6%; Average loss: 3.4888
Iteration: 947; Percent complete: 23.7%; Average loss: 3.2712
Iteration: 948; Percent complete: 23.7%; Average loss: 3.3025
Iteration: 949; Percent complete: 23.7%; Average loss: 3.5539
Iteration: 950; Percent complete: 23.8%; Average loss: 3.3492
Iteration: 951; Percent complete: 23.8%; Average loss: 3.5978
Iteration: 952; Percent complete: 23.8%; Average loss: 3.6692
Iteration: 953; Percent complete: 23.8%; Average loss: 3.2664
Iteration: 954; Percent complete: 23.8%; Average loss: 3.5350
Iteration: 955; Percent complete: 23.9%; Average loss: 3.2591
Iteration: 956; Percent complete: 23.9%; Average loss: 3.5863
Iteration: 957; Percent complete: 23.9%; Average loss: 3.3107
Iteration: 958; Percent complete: 23.9%; Average loss: 3.6183
Iteration: 959; Percent complete: 24.0%; Average loss: 3.6079
Iteration: 960; Percent complete: 24.0%; Average loss: 3.9513
Iteration: 961; Percent complete: 24.0%; Average loss: 3.4022
Iteration: 962; Percent complete: 24.1%; Average loss: 3.2416
Iteration: 963; Percent complete: 24.1%; Average loss: 3.2979
Iteration: 964; Percent complete: 24.1%; Average loss: 3.5859
Iteration: 965; Percent complete: 24.1%; Average loss: 3.3096
Iteration: 966; Percent complete: 24.1%; Average loss: 3.6344
Iteration: 967; Percent complete: 24.2%; Average loss: 3.6604
Iteration: 968; Percent complete: 24.2%; Average loss: 3.4128
Iteration: 969; Percent complete: 24.2%; Average loss: 3.3689
Iteration: 970; Percent complete: 24.2%; Average loss: 3.4219
Iteration: 971; Percent complete: 24.3%; Average loss: 3.3851
Iteration: 972; Percent complete: 24.3%; Average loss: 3.3019
Iteration: 973; Percent complete: 24.3%; Average loss: 3.4812
Iteration: 974; Percent complete: 24.3%; Average loss: 3.4450
Iteration: 975; Percent complete: 24.4%; Average loss: 3.5425
Iteration: 976; Percent complete: 24.4%; Average loss: 3.7328
Iteration: 977; Percent complete: 24.4%; Average loss: 3.6101
Iteration: 978; Percent complete: 24.4%; Average loss: 3.5190
Iteration: 979; Percent complete: 24.5%; Average loss: 3.4356
Iteration: 980; Percent complete: 24.5%; Average loss: 3.7153
Iteration: 981; Percent complete: 24.5%; Average loss: 3.6033
Iteration: 982; Percent complete: 24.6%; Average loss: 3.5837
Iteration: 983; Percent complete: 24.6%; Average loss: 3.4331
Iteration: 984; Percent complete: 24.6%; Average loss: 3.4142
Iteration: 985; Percent complete: 24.6%; Average loss: 3.6807
Iteration: 986; Percent complete: 24.6%; Average loss: 3.1575
Iteration: 987; Percent complete: 24.7%; Average loss: 3.6179
Iteration: 988; Percent complete: 24.7%; Average loss: 3.3839
Iteration: 989; Percent complete: 24.7%; Average loss: 3.2327
Iteration: 990; Percent complete: 24.8%; Average loss: 3.6237
Iteration: 991; Percent complete: 24.8%; Average loss: 3.4526
Iteration: 992; Percent complete: 24.8%; Average loss: 3.7106
Iteration: 993; Percent complete: 24.8%; Average loss: 3.4683
Iteration: 994; Percent complete: 24.9%; Average loss: 3.4347
Iteration: 995; Percent complete: 24.9%; Average loss: 3.3628
Iteration: 996; Percent complete: 24.9%; Average loss: 3.5258
Iteration: 997; Percent complete: 24.9%; Average loss: 3.6514
Iteration: 998; Percent complete: 24.9%; Average loss: 3.3868
Iteration: 999; Percent complete: 25.0%; Average loss: 3.4223
Iteration: 1000; Percent complete: 25.0%; Average loss: 3.4813
Iteration: 1001; Percent complete: 25.0%; Average loss: 3.5060
Iteration: 1002; Percent complete: 25.1%; Average loss: 3.5207
Iteration: 1003; Percent complete: 25.1%; Average loss: 3.4856
Iteration: 1004; Percent complete: 25.1%; Average loss: 3.2808
Iteration: 1005; Percent complete: 25.1%; Average loss: 3.3030
Iteration: 1006; Percent complete: 25.1%; Average loss: 3.6059
Iteration: 1007; Percent complete: 25.2%; Average loss: 3.4075
Iteration: 1008; Percent complete: 25.2%; Average loss: 3.8115
Iteration: 1009; Percent complete: 25.2%; Average loss: 3.4858
Iteration: 1010; Percent complete: 25.2%; Average loss: 3.3726
Iteration: 1011; Percent complete: 25.3%; Average loss: 3.5041
Iteration: 1012; Percent complete: 25.3%; Average loss: 3.5345
Iteration: 1013; Percent complete: 25.3%; Average loss: 3.5518
Iteration: 1014; Percent complete: 25.4%; Average loss: 3.3735
Iteration: 1015; Percent complete: 25.4%; Average loss: 3.2969
Iteration: 1016; Percent complete: 25.4%; Average loss: 3.5636
Iteration: 1017; Percent complete: 25.4%; Average loss: 3.6398
Iteration: 1018; Percent complete: 25.4%; Average loss: 3.2623
Iteration: 1019; Percent complete: 25.5%; Average loss: 3.5827
Iteration: 1020; Percent complete: 25.5%; Average loss: 3.4494
Iteration: 1021; Percent complete: 25.5%; Average loss: 3.5986
Iteration: 1022; Percent complete: 25.6%; Average loss: 3.4086
Iteration: 1023; Percent complete: 25.6%; Average loss: 3.2403
Iteration: 1024; Percent complete: 25.6%; Average loss: 3.4060
Iteration: 1025; Percent complete: 25.6%; Average loss: 3.2873
Iteration: 1026; Percent complete: 25.7%; Average loss: 3.2835
Iteration: 1027; Percent complete: 25.7%; Average loss: 3.3564
Iteration: 1028; Percent complete: 25.7%; Average loss: 3.3624
Iteration: 1029; Percent complete: 25.7%; Average loss: 3.4794
Iteration: 1030; Percent complete: 25.8%; Average loss: 3.4229
Iteration: 1031; Percent complete: 25.8%; Average loss: 3.6891
Iteration: 1032; Percent complete: 25.8%; Average loss: 3.3099
Iteration: 1033; Percent complete: 25.8%; Average loss: 3.5711
Iteration: 1034; Percent complete: 25.9%; Average loss: 3.2329
Iteration: 1035; Percent complete: 25.9%; Average loss: 3.3758
Iteration: 1036; Percent complete: 25.9%; Average loss: 3.2009
Iteration: 1037; Percent complete: 25.9%; Average loss: 3.3143
Iteration: 1038; Percent complete: 25.9%; Average loss: 3.5289
Iteration: 1039; Percent complete: 26.0%; Average loss: 3.4229
Iteration: 1040; Percent complete: 26.0%; Average loss: 3.4587
Iteration: 1041; Percent complete: 26.0%; Average loss: 3.5902
Iteration: 1042; Percent complete: 26.1%; Average loss: 3.6259
Iteration: 1043; Percent complete: 26.1%; Average loss: 3.2550
Iteration: 1044; Percent complete: 26.1%; Average loss: 3.3765
Iteration: 1045; Percent complete: 26.1%; Average loss: 3.4482
Iteration: 1046; Percent complete: 26.2%; Average loss: 3.7280
Iteration: 1047; Percent complete: 26.2%; Average loss: 3.4341
Iteration: 1048; Percent complete: 26.2%; Average loss: 3.4515
Iteration: 1049; Percent complete: 26.2%; Average loss: 3.4746
Iteration: 1050; Percent complete: 26.2%; Average loss: 3.4147
Iteration: 1051; Percent complete: 26.3%; Average loss: 3.5425
Iteration: 1052; Percent complete: 26.3%; Average loss: 3.4673
Iteration: 1053; Percent complete: 26.3%; Average loss: 3.4459
Iteration: 1054; Percent complete: 26.4%; Average loss: 3.6628
Iteration: 1055; Percent complete: 26.4%; Average loss: 3.6016
Iteration: 1056; Percent complete: 26.4%; Average loss: 3.5085
Iteration: 1057; Percent complete: 26.4%; Average loss: 3.5781
Iteration: 1058; Percent complete: 26.5%; Average loss: 3.1800
Iteration: 1059; Percent complete: 26.5%; Average loss: 3.3683
Iteration: 1060; Percent complete: 26.5%; Average loss: 3.4801
Iteration: 1061; Percent complete: 26.5%; Average loss: 3.4120
Iteration: 1062; Percent complete: 26.6%; Average loss: 3.5047
Iteration: 1063; Percent complete: 26.6%; Average loss: 3.3455
Iteration: 1064; Percent complete: 26.6%; Average loss: 3.4092
Iteration: 1065; Percent complete: 26.6%; Average loss: 3.4727
Iteration: 1066; Percent complete: 26.7%; Average loss: 3.4097
Iteration: 1067; Percent complete: 26.7%; Average loss: 3.3211
Iteration: 1068; Percent complete: 26.7%; Average loss: 3.4733
Iteration: 1069; Percent complete: 26.7%; Average loss: 3.2715
Iteration: 1070; Percent complete: 26.8%; Average loss: 3.3719
Iteration: 1071; Percent complete: 26.8%; Average loss: 3.5124
Iteration: 1072; Percent complete: 26.8%; Average loss: 3.6041
Iteration: 1073; Percent complete: 26.8%; Average loss: 3.4412
Iteration: 1074; Percent complete: 26.9%; Average loss: 3.5782
Iteration: 1075; Percent complete: 26.9%; Average loss: 3.5624
Iteration: 1076; Percent complete: 26.9%; Average loss: 3.3413
Iteration: 1077; Percent complete: 26.9%; Average loss: 3.4345
Iteration: 1078; Percent complete: 27.0%; Average loss: 3.4462
Iteration: 1079; Percent complete: 27.0%; Average loss: 3.4764
Iteration: 1080; Percent complete: 27.0%; Average loss: 3.2089
Iteration: 1081; Percent complete: 27.0%; Average loss: 3.5635
Iteration: 1082; Percent complete: 27.1%; Average loss: 3.4924
Iteration: 1083; Percent complete: 27.1%; Average loss: 3.5994
Iteration: 1084; Percent complete: 27.1%; Average loss: 3.5816
Iteration: 1085; Percent complete: 27.1%; Average loss: 3.4784
Iteration: 1086; Percent complete: 27.2%; Average loss: 3.3473
Iteration: 1087; Percent complete: 27.2%; Average loss: 3.4107
Iteration: 1088; Percent complete: 27.2%; Average loss: 3.5129
Iteration: 1089; Percent complete: 27.2%; Average loss: 3.4045
Iteration: 1090; Percent complete: 27.3%; Average loss: 3.0675
Iteration: 1091; Percent complete: 27.3%; Average loss: 3.8222
Iteration: 1092; Percent complete: 27.3%; Average loss: 3.4830
Iteration: 1093; Percent complete: 27.3%; Average loss: 3.4790
Iteration: 1094; Percent complete: 27.4%; Average loss: 3.3336
Iteration: 1095; Percent complete: 27.4%; Average loss: 3.3948
Iteration: 1096; Percent complete: 27.4%; Average loss: 3.4695
Iteration: 1097; Percent complete: 27.4%; Average loss: 3.4460
Iteration: 1098; Percent complete: 27.5%; Average loss: 3.4543
Iteration: 1099; Percent complete: 27.5%; Average loss: 3.5630
Iteration: 1100; Percent complete: 27.5%; Average loss: 3.6456
Iteration: 1101; Percent complete: 27.5%; Average loss: 3.4832
Iteration: 1102; Percent complete: 27.6%; Average loss: 3.6015
Iteration: 1103; Percent complete: 27.6%; Average loss: 3.6396
Iteration: 1104; Percent complete: 27.6%; Average loss: 3.4644
Iteration: 1105; Percent complete: 27.6%; Average loss: 3.7271
Iteration: 1106; Percent complete: 27.7%; Average loss: 3.2966
Iteration: 1107; Percent complete: 27.7%; Average loss: 3.3820
Iteration: 1108; Percent complete: 27.7%; Average loss: 3.7481
Iteration: 1109; Percent complete: 27.7%; Average loss: 3.3497
Iteration: 1110; Percent complete: 27.8%; Average loss: 3.5283
Iteration: 1111; Percent complete: 27.8%; Average loss: 3.1717
Iteration: 1112; Percent complete: 27.8%; Average loss: 3.4094
Iteration: 1113; Percent complete: 27.8%; Average loss: 3.3331
Iteration: 1114; Percent complete: 27.9%; Average loss: 3.4084
Iteration: 1115; Percent complete: 27.9%; Average loss: 3.5384
Iteration: 1116; Percent complete: 27.9%; Average loss: 3.4238
Iteration: 1117; Percent complete: 27.9%; Average loss: 3.2686
Iteration: 1118; Percent complete: 28.0%; Average loss: 3.4995
Iteration: 1119; Percent complete: 28.0%; Average loss: 3.3862
Iteration: 1120; Percent complete: 28.0%; Average loss: 3.4552
Iteration: 1121; Percent complete: 28.0%; Average loss: 3.7337
Iteration: 1122; Percent complete: 28.1%; Average loss: 3.2465
Iteration: 1123; Percent complete: 28.1%; Average loss: 3.2779
Iteration: 1124; Percent complete: 28.1%; Average loss: 3.0914
Iteration: 1125; Percent complete: 28.1%; Average loss: 3.4329
Iteration: 1126; Percent complete: 28.1%; Average loss: 3.4906
Iteration: 1127; Percent complete: 28.2%; Average loss: 3.3851
Iteration: 1128; Percent complete: 28.2%; Average loss: 3.4372
Iteration: 1129; Percent complete: 28.2%; Average loss: 3.5990
Iteration: 1130; Percent complete: 28.2%; Average loss: 3.2696
Iteration: 1131; Percent complete: 28.3%; Average loss: 3.5561
Iteration: 1132; Percent complete: 28.3%; Average loss: 3.5819
Iteration: 1133; Percent complete: 28.3%; Average loss: 3.4134
Iteration: 1134; Percent complete: 28.3%; Average loss: 3.4175
Iteration: 1135; Percent complete: 28.4%; Average loss: 3.3094
Iteration: 1136; Percent complete: 28.4%; Average loss: 3.5000
Iteration: 1137; Percent complete: 28.4%; Average loss: 3.4134
Iteration: 1138; Percent complete: 28.4%; Average loss: 3.4053
Iteration: 1139; Percent complete: 28.5%; Average loss: 3.4350
Iteration: 1140; Percent complete: 28.5%; Average loss: 3.6993
Iteration: 1141; Percent complete: 28.5%; Average loss: 3.3380
Iteration: 1142; Percent complete: 28.5%; Average loss: 3.2484
Iteration: 1143; Percent complete: 28.6%; Average loss: 3.0565
Iteration: 1144; Percent complete: 28.6%; Average loss: 3.2968
Iteration: 1145; Percent complete: 28.6%; Average loss: 3.4510
Iteration: 1146; Percent complete: 28.6%; Average loss: 3.5586
Iteration: 1147; Percent complete: 28.7%; Average loss: 3.1900
Iteration: 1148; Percent complete: 28.7%; Average loss: 3.7570
Iteration: 1149; Percent complete: 28.7%; Average loss: 3.4628
Iteration: 1150; Percent complete: 28.7%; Average loss: 3.5933
Iteration: 1151; Percent complete: 28.8%; Average loss: 3.4070
Iteration: 1152; Percent complete: 28.8%; Average loss: 3.5460
Iteration: 1153; Percent complete: 28.8%; Average loss: 3.3178
Iteration: 1154; Percent complete: 28.8%; Average loss: 3.3737
Iteration: 1155; Percent complete: 28.9%; Average loss: 3.5340
Iteration: 1156; Percent complete: 28.9%; Average loss: 3.4991
Iteration: 1157; Percent complete: 28.9%; Average loss: 3.4627
Iteration: 1158; Percent complete: 28.9%; Average loss: 3.1897
Iteration: 1159; Percent complete: 29.0%; Average loss: 3.2801
Iteration: 1160; Percent complete: 29.0%; Average loss: 3.6638
Iteration: 1161; Percent complete: 29.0%; Average loss: 3.2685
Iteration: 1162; Percent complete: 29.0%; Average loss: 3.2692
Iteration: 1163; Percent complete: 29.1%; Average loss: 3.2662
Iteration: 1164; Percent complete: 29.1%; Average loss: 3.4210
Iteration: 1165; Percent complete: 29.1%; Average loss: 3.5164
Iteration: 1166; Percent complete: 29.1%; Average loss: 3.3242
Iteration: 1167; Percent complete: 29.2%; Average loss: 3.6866
Iteration: 1168; Percent complete: 29.2%; Average loss: 3.4543
Iteration: 1169; Percent complete: 29.2%; Average loss: 3.5528
Iteration: 1170; Percent complete: 29.2%; Average loss: 3.2622
Iteration: 1171; Percent complete: 29.3%; Average loss: 3.3762
Iteration: 1172; Percent complete: 29.3%; Average loss: 3.4578
Iteration: 1173; Percent complete: 29.3%; Average loss: 3.3270
Iteration: 1174; Percent complete: 29.3%; Average loss: 3.1683
Iteration: 1175; Percent complete: 29.4%; Average loss: 3.4129
Iteration: 1176; Percent complete: 29.4%; Average loss: 3.2856
Iteration: 1177; Percent complete: 29.4%; Average loss: 3.5762
Iteration: 1178; Percent complete: 29.4%; Average loss: 3.5318
Iteration: 1179; Percent complete: 29.5%; Average loss: 3.7474
Iteration: 1180; Percent complete: 29.5%; Average loss: 3.7096
Iteration: 1181; Percent complete: 29.5%; Average loss: 3.2309
Iteration: 1182; Percent complete: 29.5%; Average loss: 3.4048
Iteration: 1183; Percent complete: 29.6%; Average loss: 3.3448
Iteration: 1184; Percent complete: 29.6%; Average loss: 3.1982
Iteration: 1185; Percent complete: 29.6%; Average loss: 3.2169
Iteration: 1186; Percent complete: 29.6%; Average loss: 3.4855
Iteration: 1187; Percent complete: 29.7%; Average loss: 3.4163
Iteration: 1188; Percent complete: 29.7%; Average loss: 3.5548
Iteration: 1189; Percent complete: 29.7%; Average loss: 3.5129
Iteration: 1190; Percent complete: 29.8%; Average loss: 3.3432
Iteration: 1191; Percent complete: 29.8%; Average loss: 3.5501
Iteration: 1192; Percent complete: 29.8%; Average loss: 3.3007
Iteration: 1193; Percent complete: 29.8%; Average loss: 3.5204
Iteration: 1194; Percent complete: 29.8%; Average loss: 3.3660
Iteration: 1195; Percent complete: 29.9%; Average loss: 3.0651
Iteration: 1196; Percent complete: 29.9%; Average loss: 3.3406
Iteration: 1197; Percent complete: 29.9%; Average loss: 3.2537
Iteration: 1198; Percent complete: 29.9%; Average loss: 3.2823
Iteration: 1199; Percent complete: 30.0%; Average loss: 3.2845
Iteration: 1200; Percent complete: 30.0%; Average loss: 3.1833
Iteration: 1201; Percent complete: 30.0%; Average loss: 3.4131
Iteration: 1202; Percent complete: 30.0%; Average loss: 3.3916
Iteration: 1203; Percent complete: 30.1%; Average loss: 3.2350
Iteration: 1204; Percent complete: 30.1%; Average loss: 3.3762
Iteration: 1205; Percent complete: 30.1%; Average loss: 3.7027
Iteration: 1206; Percent complete: 30.1%; Average loss: 3.1062
Iteration: 1207; Percent complete: 30.2%; Average loss: 3.4157
Iteration: 1208; Percent complete: 30.2%; Average loss: 3.2670
Iteration: 1209; Percent complete: 30.2%; Average loss: 3.3664
Iteration: 1210; Percent complete: 30.2%; Average loss: 3.2814
Iteration: 1211; Percent complete: 30.3%; Average loss: 3.6732
Iteration: 1212; Percent complete: 30.3%; Average loss: 3.3626
Iteration: 1213; Percent complete: 30.3%; Average loss: 3.1800
Iteration: 1214; Percent complete: 30.3%; Average loss: 3.6571
Iteration: 1215; Percent complete: 30.4%; Average loss: 3.6372
Iteration: 1216; Percent complete: 30.4%; Average loss: 3.2649
Iteration: 1217; Percent complete: 30.4%; Average loss: 3.2089
Iteration: 1218; Percent complete: 30.4%; Average loss: 3.5383
Iteration: 1219; Percent complete: 30.5%; Average loss: 3.4440
Iteration: 1220; Percent complete: 30.5%; Average loss: 3.3387
Iteration: 1221; Percent complete: 30.5%; Average loss: 3.5978
Iteration: 1222; Percent complete: 30.6%; Average loss: 3.7087
Iteration: 1223; Percent complete: 30.6%; Average loss: 3.4341
Iteration: 1224; Percent complete: 30.6%; Average loss: 3.6464
Iteration: 1225; Percent complete: 30.6%; Average loss: 3.4355
Iteration: 1226; Percent complete: 30.6%; Average loss: 3.3076
Iteration: 1227; Percent complete: 30.7%; Average loss: 3.3709
Iteration: 1228; Percent complete: 30.7%; Average loss: 3.2392
Iteration: 1229; Percent complete: 30.7%; Average loss: 3.2649
Iteration: 1230; Percent complete: 30.8%; Average loss: 3.2450
Iteration: 1231; Percent complete: 30.8%; Average loss: 3.3734
Iteration: 1232; Percent complete: 30.8%; Average loss: 3.2774
Iteration: 1233; Percent complete: 30.8%; Average loss: 3.3026
Iteration: 1234; Percent complete: 30.9%; Average loss: 3.3874
Iteration: 1235; Percent complete: 30.9%; Average loss: 3.1631
Iteration: 1236; Percent complete: 30.9%; Average loss: 3.2718
Iteration: 1237; Percent complete: 30.9%; Average loss: 3.3907
Iteration: 1238; Percent complete: 30.9%; Average loss: 3.1805
Iteration: 1239; Percent complete: 31.0%; Average loss: 3.3544
Iteration: 1240; Percent complete: 31.0%; Average loss: 3.5651
Iteration: 1241; Percent complete: 31.0%; Average loss: 3.3434
Iteration: 1242; Percent complete: 31.1%; Average loss: 3.5947
Iteration: 1243; Percent complete: 31.1%; Average loss: 3.1731
Iteration: 1244; Percent complete: 31.1%; Average loss: 3.3713
Iteration: 1245; Percent complete: 31.1%; Average loss: 3.5403
Iteration: 1246; Percent complete: 31.1%; Average loss: 3.0893
Iteration: 1247; Percent complete: 31.2%; Average loss: 3.8623
Iteration: 1248; Percent complete: 31.2%; Average loss: 3.3759
Iteration: 1249; Percent complete: 31.2%; Average loss: 3.3791
Iteration: 1250; Percent complete: 31.2%; Average loss: 3.2800
Iteration: 1251; Percent complete: 31.3%; Average loss: 3.6362
Iteration: 1252; Percent complete: 31.3%; Average loss: 3.2028
Iteration: 1253; Percent complete: 31.3%; Average loss: 3.7603
Iteration: 1254; Percent complete: 31.4%; Average loss: 3.5565
Iteration: 1255; Percent complete: 31.4%; Average loss: 3.1703
Iteration: 1256; Percent complete: 31.4%; Average loss: 3.4383
Iteration: 1257; Percent complete: 31.4%; Average loss: 3.4993
Iteration: 1258; Percent complete: 31.4%; Average loss: 3.2581
Iteration: 1259; Percent complete: 31.5%; Average loss: 3.4442
Iteration: 1260; Percent complete: 31.5%; Average loss: 3.3334
Iteration: 1261; Percent complete: 31.5%; Average loss: 3.1748
Iteration: 1262; Percent complete: 31.6%; Average loss: 3.3153
Iteration: 1263; Percent complete: 31.6%; Average loss: 3.4620
Iteration: 1264; Percent complete: 31.6%; Average loss: 3.3976
Iteration: 1265; Percent complete: 31.6%; Average loss: 3.3311
Iteration: 1266; Percent complete: 31.6%; Average loss: 3.0986
Iteration: 1267; Percent complete: 31.7%; Average loss: 3.1470
Iteration: 1268; Percent complete: 31.7%; Average loss: 3.2275
Iteration: 1269; Percent complete: 31.7%; Average loss: 3.5107
Iteration: 1270; Percent complete: 31.8%; Average loss: 3.5117
Iteration: 1271; Percent complete: 31.8%; Average loss: 3.3775
Iteration: 1272; Percent complete: 31.8%; Average loss: 3.5080
Iteration: 1273; Percent complete: 31.8%; Average loss: 3.4974
Iteration: 1274; Percent complete: 31.9%; Average loss: 3.2805
Iteration: 1275; Percent complete: 31.9%; Average loss: 3.3193
Iteration: 1276; Percent complete: 31.9%; Average loss: 3.3507
Iteration: 1277; Percent complete: 31.9%; Average loss: 3.3143
Iteration: 1278; Percent complete: 31.9%; Average loss: 3.2900
Iteration: 1279; Percent complete: 32.0%; Average loss: 2.9402
Iteration: 1280; Percent complete: 32.0%; Average loss: 3.0911
Iteration: 1281; Percent complete: 32.0%; Average loss: 3.5604
Iteration: 1282; Percent complete: 32.0%; Average loss: 3.3370
Iteration: 1283; Percent complete: 32.1%; Average loss: 3.3367
Iteration: 1284; Percent complete: 32.1%; Average loss: 3.1858
Iteration: 1285; Percent complete: 32.1%; Average loss: 3.3832
Iteration: 1286; Percent complete: 32.1%; Average loss: 3.2287
Iteration: 1287; Percent complete: 32.2%; Average loss: 3.2354
Iteration: 1288; Percent complete: 32.2%; Average loss: 3.2534
Iteration: 1289; Percent complete: 32.2%; Average loss: 3.4997
Iteration: 1290; Percent complete: 32.2%; Average loss: 3.4556
Iteration: 1291; Percent complete: 32.3%; Average loss: 3.4042
Iteration: 1292; Percent complete: 32.3%; Average loss: 3.2319
Iteration: 1293; Percent complete: 32.3%; Average loss: 3.1525
Iteration: 1294; Percent complete: 32.4%; Average loss: 3.1652
Iteration: 1295; Percent complete: 32.4%; Average loss: 3.4275
Iteration: 1296; Percent complete: 32.4%; Average loss: 3.4211
Iteration: 1297; Percent complete: 32.4%; Average loss: 3.5077
Iteration: 1298; Percent complete: 32.5%; Average loss: 3.2737
Iteration: 1299; Percent complete: 32.5%; Average loss: 3.5173
Iteration: 1300; Percent complete: 32.5%; Average loss: 3.4427
Iteration: 1301; Percent complete: 32.5%; Average loss: 3.1633
Iteration: 1302; Percent complete: 32.6%; Average loss: 3.6042
Iteration: 1303; Percent complete: 32.6%; Average loss: 3.0996
Iteration: 1304; Percent complete: 32.6%; Average loss: 3.3029
Iteration: 1305; Percent complete: 32.6%; Average loss: 3.2820
Iteration: 1306; Percent complete: 32.6%; Average loss: 3.3936
Iteration: 1307; Percent complete: 32.7%; Average loss: 3.3530
Iteration: 1308; Percent complete: 32.7%; Average loss: 3.2173
Iteration: 1309; Percent complete: 32.7%; Average loss: 3.5341
Iteration: 1310; Percent complete: 32.8%; Average loss: 3.5659
Iteration: 1311; Percent complete: 32.8%; Average loss: 3.3528
Iteration: 1312; Percent complete: 32.8%; Average loss: 3.2386
Iteration: 1313; Percent complete: 32.8%; Average loss: 3.1855
Iteration: 1314; Percent complete: 32.9%; Average loss: 3.1992
Iteration: 1315; Percent complete: 32.9%; Average loss: 3.2693
Iteration: 1316; Percent complete: 32.9%; Average loss: 3.4891
Iteration: 1317; Percent complete: 32.9%; Average loss: 3.3884
Iteration: 1318; Percent complete: 33.0%; Average loss: 3.3530
Iteration: 1319; Percent complete: 33.0%; Average loss: 3.6204
Iteration: 1320; Percent complete: 33.0%; Average loss: 3.4573
Iteration: 1321; Percent complete: 33.0%; Average loss: 3.1112
Iteration: 1322; Percent complete: 33.1%; Average loss: 3.2313
Iteration: 1323; Percent complete: 33.1%; Average loss: 3.1863
Iteration: 1324; Percent complete: 33.1%; Average loss: 3.3960
Iteration: 1325; Percent complete: 33.1%; Average loss: 3.1199
Iteration: 1326; Percent complete: 33.1%; Average loss: 3.1297
Iteration: 1327; Percent complete: 33.2%; Average loss: 3.5372
Iteration: 1328; Percent complete: 33.2%; Average loss: 3.2909
Iteration: 1329; Percent complete: 33.2%; Average loss: 3.4175
Iteration: 1330; Percent complete: 33.2%; Average loss: 3.3982
Iteration: 1331; Percent complete: 33.3%; Average loss: 3.1626
Iteration: 1332; Percent complete: 33.3%; Average loss: 3.2685
Iteration: 1333; Percent complete: 33.3%; Average loss: 3.5230
Iteration: 1334; Percent complete: 33.4%; Average loss: 3.2398
Iteration: 1335; Percent complete: 33.4%; Average loss: 3.3111
Iteration: 1336; Percent complete: 33.4%; Average loss: 3.5751
Iteration: 1337; Percent complete: 33.4%; Average loss: 3.4853
Iteration: 1338; Percent complete: 33.5%; Average loss: 3.1034
Iteration: 1339; Percent complete: 33.5%; Average loss: 3.1738
Iteration: 1340; Percent complete: 33.5%; Average loss: 3.0674
Iteration: 1341; Percent complete: 33.5%; Average loss: 3.5223
Iteration: 1342; Percent complete: 33.6%; Average loss: 3.3946
Iteration: 1343; Percent complete: 33.6%; Average loss: 3.2841
Iteration: 1344; Percent complete: 33.6%; Average loss: 3.2851
Iteration: 1345; Percent complete: 33.6%; Average loss: 3.3882
Iteration: 1346; Percent complete: 33.7%; Average loss: 3.4355
Iteration: 1347; Percent complete: 33.7%; Average loss: 3.5213
Iteration: 1348; Percent complete: 33.7%; Average loss: 3.6864
Iteration: 1349; Percent complete: 33.7%; Average loss: 3.4078
Iteration: 1350; Percent complete: 33.8%; Average loss: 3.4647
Iteration: 1351; Percent complete: 33.8%; Average loss: 3.4567
Iteration: 1352; Percent complete: 33.8%; Average loss: 3.4308
Iteration: 1353; Percent complete: 33.8%; Average loss: 3.1504
Iteration: 1354; Percent complete: 33.9%; Average loss: 3.5881
Iteration: 1355; Percent complete: 33.9%; Average loss: 3.4189
Iteration: 1356; Percent complete: 33.9%; Average loss: 3.1255
Iteration: 1357; Percent complete: 33.9%; Average loss: 3.4866
Iteration: 1358; Percent complete: 34.0%; Average loss: 3.2661
Iteration: 1359; Percent complete: 34.0%; Average loss: 3.4653
Iteration: 1360; Percent complete: 34.0%; Average loss: 3.4964
Iteration: 1361; Percent complete: 34.0%; Average loss: 3.3757
Iteration: 1362; Percent complete: 34.1%; Average loss: 3.4358
Iteration: 1363; Percent complete: 34.1%; Average loss: 3.3141
Iteration: 1364; Percent complete: 34.1%; Average loss: 3.3387
Iteration: 1365; Percent complete: 34.1%; Average loss: 3.1193
Iteration: 1366; Percent complete: 34.2%; Average loss: 3.4000
Iteration: 1367; Percent complete: 34.2%; Average loss: 3.2339
Iteration: 1368; Percent complete: 34.2%; Average loss: 3.2376
Iteration: 1369; Percent complete: 34.2%; Average loss: 3.4569
Iteration: 1370; Percent complete: 34.2%; Average loss: 3.6432
Iteration: 1371; Percent complete: 34.3%; Average loss: 3.1381
Iteration: 1372; Percent complete: 34.3%; Average loss: 3.5059
Iteration: 1373; Percent complete: 34.3%; Average loss: 2.8985
Iteration: 1374; Percent complete: 34.4%; Average loss: 3.5610
Iteration: 1375; Percent complete: 34.4%; Average loss: 3.4131
Iteration: 1376; Percent complete: 34.4%; Average loss: 3.4150
Iteration: 1377; Percent complete: 34.4%; Average loss: 3.1530
Iteration: 1378; Percent complete: 34.4%; Average loss: 3.3469
Iteration: 1379; Percent complete: 34.5%; Average loss: 3.1743
Iteration: 1380; Percent complete: 34.5%; Average loss: 3.1326
Iteration: 1381; Percent complete: 34.5%; Average loss: 3.4994
Iteration: 1382; Percent complete: 34.5%; Average loss: 3.3689
Iteration: 1383; Percent complete: 34.6%; Average loss: 3.2557
Iteration: 1384; Percent complete: 34.6%; Average loss: 3.2298
Iteration: 1385; Percent complete: 34.6%; Average loss: 3.5445
Iteration: 1386; Percent complete: 34.6%; Average loss: 3.2382
Iteration: 1387; Percent complete: 34.7%; Average loss: 3.2333
Iteration: 1388; Percent complete: 34.7%; Average loss: 3.4375
Iteration: 1389; Percent complete: 34.7%; Average loss: 3.4540
Iteration: 1390; Percent complete: 34.8%; Average loss: 3.1494
Iteration: 1391; Percent complete: 34.8%; Average loss: 3.0882
Iteration: 1392; Percent complete: 34.8%; Average loss: 3.1679
Iteration: 1393; Percent complete: 34.8%; Average loss: 3.1431
Iteration: 1394; Percent complete: 34.8%; Average loss: 3.3454
Iteration: 1395; Percent complete: 34.9%; Average loss: 3.3890
Iteration: 1396; Percent complete: 34.9%; Average loss: 3.3387
Iteration: 1397; Percent complete: 34.9%; Average loss: 3.0803
Iteration: 1398; Percent complete: 34.9%; Average loss: 3.3290
Iteration: 1399; Percent complete: 35.0%; Average loss: 3.4177
Iteration: 1400; Percent complete: 35.0%; Average loss: 3.5349
Iteration: 1401; Percent complete: 35.0%; Average loss: 3.4292
Iteration: 1402; Percent complete: 35.0%; Average loss: 3.2320
Iteration: 1403; Percent complete: 35.1%; Average loss: 3.5652
Iteration: 1404; Percent complete: 35.1%; Average loss: 3.3696
Iteration: 1405; Percent complete: 35.1%; Average loss: 3.4491
Iteration: 1406; Percent complete: 35.1%; Average loss: 3.1871
Iteration: 1407; Percent complete: 35.2%; Average loss: 3.3726
Iteration: 1408; Percent complete: 35.2%; Average loss: 3.3187
Iteration: 1409; Percent complete: 35.2%; Average loss: 3.4043
Iteration: 1410; Percent complete: 35.2%; Average loss: 3.1506
Iteration: 1411; Percent complete: 35.3%; Average loss: 3.4850
Iteration: 1412; Percent complete: 35.3%; Average loss: 3.4366
Iteration: 1413; Percent complete: 35.3%; Average loss: 3.3844
Iteration: 1414; Percent complete: 35.4%; Average loss: 3.3121
Iteration: 1415; Percent complete: 35.4%; Average loss: 3.4262
Iteration: 1416; Percent complete: 35.4%; Average loss: 3.6187
Iteration: 1417; Percent complete: 35.4%; Average loss: 3.6896
Iteration: 1418; Percent complete: 35.4%; Average loss: 3.4232
Iteration: 1419; Percent complete: 35.5%; Average loss: 3.4830
Iteration: 1420; Percent complete: 35.5%; Average loss: 3.3398
Iteration: 1421; Percent complete: 35.5%; Average loss: 2.9651
Iteration: 1422; Percent complete: 35.5%; Average loss: 3.4389
Iteration: 1423; Percent complete: 35.6%; Average loss: 3.3326
Iteration: 1424; Percent complete: 35.6%; Average loss: 3.4026
Iteration: 1425; Percent complete: 35.6%; Average loss: 3.3764
Iteration: 1426; Percent complete: 35.6%; Average loss: 3.2156
Iteration: 1427; Percent complete: 35.7%; Average loss: 3.1132
Iteration: 1428; Percent complete: 35.7%; Average loss: 3.2816
Iteration: 1429; Percent complete: 35.7%; Average loss: 3.0103
Iteration: 1430; Percent complete: 35.8%; Average loss: 3.2510
Iteration: 1431; Percent complete: 35.8%; Average loss: 3.1781
Iteration: 1432; Percent complete: 35.8%; Average loss: 3.0688
Iteration: 1433; Percent complete: 35.8%; Average loss: 3.3226
Iteration: 1434; Percent complete: 35.9%; Average loss: 3.1927
Iteration: 1435; Percent complete: 35.9%; Average loss: 3.3289
Iteration: 1436; Percent complete: 35.9%; Average loss: 3.3724
Iteration: 1437; Percent complete: 35.9%; Average loss: 3.3136
Iteration: 1438; Percent complete: 35.9%; Average loss: 3.2725
Iteration: 1439; Percent complete: 36.0%; Average loss: 3.5537
Iteration: 1440; Percent complete: 36.0%; Average loss: 3.1600
Iteration: 1441; Percent complete: 36.0%; Average loss: 3.1757
Iteration: 1442; Percent complete: 36.0%; Average loss: 3.4382
Iteration: 1443; Percent complete: 36.1%; Average loss: 3.0625
Iteration: 1444; Percent complete: 36.1%; Average loss: 3.3754
Iteration: 1445; Percent complete: 36.1%; Average loss: 3.7824
Iteration: 1446; Percent complete: 36.1%; Average loss: 3.0064
Iteration: 1447; Percent complete: 36.2%; Average loss: 3.5722
Iteration: 1448; Percent complete: 36.2%; Average loss: 3.3067
Iteration: 1449; Percent complete: 36.2%; Average loss: 3.2944
Iteration: 1450; Percent complete: 36.2%; Average loss: 3.4852
Iteration: 1451; Percent complete: 36.3%; Average loss: 3.3219
Iteration: 1452; Percent complete: 36.3%; Average loss: 3.0814
Iteration: 1453; Percent complete: 36.3%; Average loss: 3.6219
Iteration: 1454; Percent complete: 36.4%; Average loss: 3.4135
Iteration: 1455; Percent complete: 36.4%; Average loss: 3.3805
Iteration: 1456; Percent complete: 36.4%; Average loss: 3.5449
Iteration: 1457; Percent complete: 36.4%; Average loss: 3.3533
Iteration: 1458; Percent complete: 36.4%; Average loss: 3.3986
Iteration: 1459; Percent complete: 36.5%; Average loss: 3.3050
Iteration: 1460; Percent complete: 36.5%; Average loss: 3.2994
Iteration: 1461; Percent complete: 36.5%; Average loss: 3.2603
Iteration: 1462; Percent complete: 36.5%; Average loss: 3.3868
Iteration: 1463; Percent complete: 36.6%; Average loss: 3.3738
Iteration: 1464; Percent complete: 36.6%; Average loss: 3.2170
Iteration: 1465; Percent complete: 36.6%; Average loss: 3.1203
Iteration: 1466; Percent complete: 36.6%; Average loss: 3.1289
Iteration: 1467; Percent complete: 36.7%; Average loss: 3.2703
Iteration: 1468; Percent complete: 36.7%; Average loss: 3.2879
Iteration: 1469; Percent complete: 36.7%; Average loss: 3.4883
Iteration: 1470; Percent complete: 36.8%; Average loss: 3.4257
Iteration: 1471; Percent complete: 36.8%; Average loss: 3.4098
Iteration: 1472; Percent complete: 36.8%; Average loss: 3.4540
Iteration: 1473; Percent complete: 36.8%; Average loss: 3.6240
Iteration: 1474; Percent complete: 36.9%; Average loss: 3.3243
Iteration: 1475; Percent complete: 36.9%; Average loss: 3.5697
Iteration: 1476; Percent complete: 36.9%; Average loss: 3.2995
Iteration: 1477; Percent complete: 36.9%; Average loss: 3.5922
Iteration: 1478; Percent complete: 37.0%; Average loss: 2.9715
Iteration: 1479; Percent complete: 37.0%; Average loss: 3.3829
Iteration: 1480; Percent complete: 37.0%; Average loss: 3.4152
Iteration: 1481; Percent complete: 37.0%; Average loss: 3.3574
Iteration: 1482; Percent complete: 37.0%; Average loss: 3.0695
Iteration: 1483; Percent complete: 37.1%; Average loss: 3.2222
Iteration: 1484; Percent complete: 37.1%; Average loss: 3.1017
Iteration: 1485; Percent complete: 37.1%; Average loss: 3.1269
Iteration: 1486; Percent complete: 37.1%; Average loss: 3.1446
Iteration: 1487; Percent complete: 37.2%; Average loss: 3.3709
Iteration: 1488; Percent complete: 37.2%; Average loss: 3.2735
Iteration: 1489; Percent complete: 37.2%; Average loss: 3.3960
Iteration: 1490; Percent complete: 37.2%; Average loss: 3.2903
Iteration: 1491; Percent complete: 37.3%; Average loss: 3.2926
Iteration: 1492; Percent complete: 37.3%; Average loss: 3.3672
Iteration: 1493; Percent complete: 37.3%; Average loss: 3.2539
Iteration: 1494; Percent complete: 37.4%; Average loss: 3.2673
Iteration: 1495; Percent complete: 37.4%; Average loss: 3.1027
Iteration: 1496; Percent complete: 37.4%; Average loss: 3.5287
Iteration: 1497; Percent complete: 37.4%; Average loss: 3.4074
Iteration: 1498; Percent complete: 37.5%; Average loss: 3.5921
Iteration: 1499; Percent complete: 37.5%; Average loss: 3.2045
Iteration: 1500; Percent complete: 37.5%; Average loss: 3.2513
Iteration: 1501; Percent complete: 37.5%; Average loss: 3.4354
Iteration: 1502; Percent complete: 37.5%; Average loss: 3.4794
Iteration: 1503; Percent complete: 37.6%; Average loss: 3.3489
Iteration: 1504; Percent complete: 37.6%; Average loss: 3.3477
Iteration: 1505; Percent complete: 37.6%; Average loss: 3.2199
Iteration: 1506; Percent complete: 37.6%; Average loss: 3.2962
Iteration: 1507; Percent complete: 37.7%; Average loss: 3.4231
Iteration: 1508; Percent complete: 37.7%; Average loss: 3.2195
Iteration: 1509; Percent complete: 37.7%; Average loss: 3.4028
Iteration: 1510; Percent complete: 37.8%; Average loss: 3.0980
Iteration: 1511; Percent complete: 37.8%; Average loss: 3.4903
Iteration: 1512; Percent complete: 37.8%; Average loss: 3.3653
Iteration: 1513; Percent complete: 37.8%; Average loss: 3.2930
Iteration: 1514; Percent complete: 37.9%; Average loss: 3.3151
Iteration: 1515; Percent complete: 37.9%; Average loss: 3.4224
Iteration: 1516; Percent complete: 37.9%; Average loss: 3.1510
Iteration: 1517; Percent complete: 37.9%; Average loss: 3.2070
Iteration: 1518; Percent complete: 38.0%; Average loss: 3.3829
Iteration: 1519; Percent complete: 38.0%; Average loss: 3.4100
Iteration: 1520; Percent complete: 38.0%; Average loss: 3.2663
Iteration: 1521; Percent complete: 38.0%; Average loss: 3.0151
Iteration: 1522; Percent complete: 38.0%; Average loss: 3.3116
Iteration: 1523; Percent complete: 38.1%; Average loss: 3.5209
Iteration: 1524; Percent complete: 38.1%; Average loss: 3.3698
Iteration: 1525; Percent complete: 38.1%; Average loss: 3.4823
Iteration: 1526; Percent complete: 38.1%; Average loss: 3.2972
Iteration: 1527; Percent complete: 38.2%; Average loss: 2.9142
Iteration: 1528; Percent complete: 38.2%; Average loss: 3.2115
Iteration: 1529; Percent complete: 38.2%; Average loss: 3.3862
Iteration: 1530; Percent complete: 38.2%; Average loss: 3.2656
Iteration: 1531; Percent complete: 38.3%; Average loss: 3.1518
Iteration: 1532; Percent complete: 38.3%; Average loss: 3.1626
Iteration: 1533; Percent complete: 38.3%; Average loss: 3.2816
Iteration: 1534; Percent complete: 38.4%; Average loss: 3.3210
Iteration: 1535; Percent complete: 38.4%; Average loss: 3.5152
Iteration: 1536; Percent complete: 38.4%; Average loss: 3.3017
Iteration: 1537; Percent complete: 38.4%; Average loss: 3.4442
Iteration: 1538; Percent complete: 38.5%; Average loss: 3.2913
Iteration: 1539; Percent complete: 38.5%; Average loss: 3.2998
Iteration: 1540; Percent complete: 38.5%; Average loss: 3.3148
Iteration: 1541; Percent complete: 38.5%; Average loss: 3.2479
Iteration: 1542; Percent complete: 38.6%; Average loss: 3.3578
Iteration: 1543; Percent complete: 38.6%; Average loss: 3.3500
Iteration: 1544; Percent complete: 38.6%; Average loss: 3.1843
Iteration: 1545; Percent complete: 38.6%; Average loss: 3.2701
Iteration: 1546; Percent complete: 38.6%; Average loss: 3.3497
Iteration: 1547; Percent complete: 38.7%; Average loss: 3.4981
Iteration: 1548; Percent complete: 38.7%; Average loss: 3.2544
Iteration: 1549; Percent complete: 38.7%; Average loss: 3.3265
Iteration: 1550; Percent complete: 38.8%; Average loss: 3.4052
Iteration: 1551; Percent complete: 38.8%; Average loss: 3.1552
Iteration: 1552; Percent complete: 38.8%; Average loss: 3.0703
Iteration: 1553; Percent complete: 38.8%; Average loss: 3.2767
Iteration: 1554; Percent complete: 38.9%; Average loss: 3.2137
Iteration: 1555; Percent complete: 38.9%; Average loss: 3.3896
Iteration: 1556; Percent complete: 38.9%; Average loss: 3.2041
Iteration: 1557; Percent complete: 38.9%; Average loss: 3.1776
Iteration: 1558; Percent complete: 39.0%; Average loss: 3.3803
Iteration: 1559; Percent complete: 39.0%; Average loss: 3.2107
Iteration: 1560; Percent complete: 39.0%; Average loss: 3.3415
Iteration: 1561; Percent complete: 39.0%; Average loss: 2.8124
Iteration: 1562; Percent complete: 39.1%; Average loss: 3.2354
Iteration: 1563; Percent complete: 39.1%; Average loss: 3.1282
Iteration: 1564; Percent complete: 39.1%; Average loss: 3.3741
Iteration: 1565; Percent complete: 39.1%; Average loss: 3.0770
Iteration: 1566; Percent complete: 39.1%; Average loss: 3.1319
Iteration: 1567; Percent complete: 39.2%; Average loss: 3.2401
Iteration: 1568; Percent complete: 39.2%; Average loss: 2.9713
Iteration: 1569; Percent complete: 39.2%; Average loss: 3.1067
Iteration: 1570; Percent complete: 39.2%; Average loss: 3.2198
Iteration: 1571; Percent complete: 39.3%; Average loss: 3.5742
Iteration: 1572; Percent complete: 39.3%; Average loss: 3.5007
Iteration: 1573; Percent complete: 39.3%; Average loss: 3.2848
Iteration: 1574; Percent complete: 39.4%; Average loss: 3.0240
Iteration: 1575; Percent complete: 39.4%; Average loss: 3.2381
Iteration: 1576; Percent complete: 39.4%; Average loss: 3.0195
Iteration: 1577; Percent complete: 39.4%; Average loss: 3.5234
Iteration: 1578; Percent complete: 39.5%; Average loss: 3.1801
Iteration: 1579; Percent complete: 39.5%; Average loss: 3.3518
Iteration: 1580; Percent complete: 39.5%; Average loss: 3.2581
Iteration: 1581; Percent complete: 39.5%; Average loss: 3.4182
Iteration: 1582; Percent complete: 39.6%; Average loss: 3.2776
Iteration: 1583; Percent complete: 39.6%; Average loss: 3.3297
Iteration: 1584; Percent complete: 39.6%; Average loss: 3.2241
Iteration: 1585; Percent complete: 39.6%; Average loss: 3.4464
Iteration: 1586; Percent complete: 39.6%; Average loss: 3.2175
Iteration: 1587; Percent complete: 39.7%; Average loss: 3.4706
Iteration: 1588; Percent complete: 39.7%; Average loss: 3.4378
Iteration: 1589; Percent complete: 39.7%; Average loss: 3.1883
Iteration: 1590; Percent complete: 39.8%; Average loss: 3.1110
Iteration: 1591; Percent complete: 39.8%; Average loss: 3.2361
Iteration: 1592; Percent complete: 39.8%; Average loss: 3.1440
Iteration: 1593; Percent complete: 39.8%; Average loss: 3.2289
Iteration: 1594; Percent complete: 39.9%; Average loss: 3.4716
Iteration: 1595; Percent complete: 39.9%; Average loss: 3.3143
Iteration: 1596; Percent complete: 39.9%; Average loss: 3.1716
Iteration: 1597; Percent complete: 39.9%; Average loss: 3.1942
Iteration: 1598; Percent complete: 40.0%; Average loss: 3.1427
Iteration: 1599; Percent complete: 40.0%; Average loss: 3.4205
Iteration: 1600; Percent complete: 40.0%; Average loss: 3.3265
Iteration: 1601; Percent complete: 40.0%; Average loss: 3.2314
Iteration: 1602; Percent complete: 40.1%; Average loss: 3.6121
Iteration: 1603; Percent complete: 40.1%; Average loss: 3.3534
Iteration: 1604; Percent complete: 40.1%; Average loss: 3.2094
Iteration: 1605; Percent complete: 40.1%; Average loss: 3.1857
Iteration: 1606; Percent complete: 40.2%; Average loss: 3.2568
Iteration: 1607; Percent complete: 40.2%; Average loss: 2.8751
Iteration: 1608; Percent complete: 40.2%; Average loss: 3.3672
Iteration: 1609; Percent complete: 40.2%; Average loss: 3.3231
Iteration: 1610; Percent complete: 40.2%; Average loss: 3.3542
Iteration: 1611; Percent complete: 40.3%; Average loss: 3.3105
Iteration: 1612; Percent complete: 40.3%; Average loss: 3.1739
Iteration: 1613; Percent complete: 40.3%; Average loss: 3.0232
Iteration: 1614; Percent complete: 40.4%; Average loss: 3.4867
Iteration: 1615; Percent complete: 40.4%; Average loss: 3.0403
Iteration: 1616; Percent complete: 40.4%; Average loss: 3.2538
Iteration: 1617; Percent complete: 40.4%; Average loss: 3.3182
Iteration: 1618; Percent complete: 40.5%; Average loss: 3.3562
Iteration: 1619; Percent complete: 40.5%; Average loss: 3.3511
Iteration: 1620; Percent complete: 40.5%; Average loss: 3.2831
Iteration: 1621; Percent complete: 40.5%; Average loss: 3.3902
Iteration: 1622; Percent complete: 40.6%; Average loss: 3.0785
Iteration: 1623; Percent complete: 40.6%; Average loss: 3.1989
Iteration: 1624; Percent complete: 40.6%; Average loss: 3.2905
Iteration: 1625; Percent complete: 40.6%; Average loss: 3.4452
Iteration: 1626; Percent complete: 40.6%; Average loss: 3.4091
Iteration: 1627; Percent complete: 40.7%; Average loss: 2.9285
Iteration: 1628; Percent complete: 40.7%; Average loss: 3.2887
Iteration: 1629; Percent complete: 40.7%; Average loss: 3.3705
Iteration: 1630; Percent complete: 40.8%; Average loss: 3.2905
Iteration: 1631; Percent complete: 40.8%; Average loss: 3.3073
Iteration: 1632; Percent complete: 40.8%; Average loss: 3.1023
Iteration: 1633; Percent complete: 40.8%; Average loss: 3.2013
Iteration: 1634; Percent complete: 40.8%; Average loss: 3.2658
Iteration: 1635; Percent complete: 40.9%; Average loss: 3.3256
Iteration: 1636; Percent complete: 40.9%; Average loss: 3.2803
Iteration: 1637; Percent complete: 40.9%; Average loss: 3.2426
Iteration: 1638; Percent complete: 40.9%; Average loss: 3.2538
Iteration: 1639; Percent complete: 41.0%; Average loss: 3.0942
Iteration: 1640; Percent complete: 41.0%; Average loss: 3.4004
Iteration: 1641; Percent complete: 41.0%; Average loss: 3.1116
Iteration: 1642; Percent complete: 41.0%; Average loss: 3.2129
Iteration: 1643; Percent complete: 41.1%; Average loss: 3.2793
Iteration: 1644; Percent complete: 41.1%; Average loss: 3.3505
Iteration: 1645; Percent complete: 41.1%; Average loss: 3.0573
Iteration: 1646; Percent complete: 41.1%; Average loss: 3.5942
Iteration: 1647; Percent complete: 41.2%; Average loss: 3.3812
Iteration: 1648; Percent complete: 41.2%; Average loss: 3.3079
Iteration: 1649; Percent complete: 41.2%; Average loss: 3.1821
Iteration: 1650; Percent complete: 41.2%; Average loss: 3.3175
Iteration: 1651; Percent complete: 41.3%; Average loss: 3.1487
Iteration: 1652; Percent complete: 41.3%; Average loss: 3.2141
Iteration: 1653; Percent complete: 41.3%; Average loss: 3.3327
Iteration: 1654; Percent complete: 41.3%; Average loss: 3.3598
Iteration: 1655; Percent complete: 41.4%; Average loss: 3.3558
Iteration: 1656; Percent complete: 41.4%; Average loss: 3.3078
Iteration: 1657; Percent complete: 41.4%; Average loss: 3.3432
Iteration: 1658; Percent complete: 41.4%; Average loss: 2.8925
Iteration: 1659; Percent complete: 41.5%; Average loss: 3.0783
Iteration: 1660; Percent complete: 41.5%; Average loss: 3.2795
Iteration: 1661; Percent complete: 41.5%; Average loss: 2.9529
Iteration: 1662; Percent complete: 41.5%; Average loss: 3.2150
Iteration: 1663; Percent complete: 41.6%; Average loss: 3.2491
Iteration: 1664; Percent complete: 41.6%; Average loss: 3.4761
Iteration: 1665; Percent complete: 41.6%; Average loss: 3.1080
Iteration: 1666; Percent complete: 41.6%; Average loss: 3.2157
Iteration: 1667; Percent complete: 41.7%; Average loss: 3.3097
Iteration: 1668; Percent complete: 41.7%; Average loss: 3.1572
Iteration: 1669; Percent complete: 41.7%; Average loss: 3.4070
Iteration: 1670; Percent complete: 41.8%; Average loss: 3.1305
Iteration: 1671; Percent complete: 41.8%; Average loss: 3.2099
Iteration: 1672; Percent complete: 41.8%; Average loss: 3.1848
Iteration: 1673; Percent complete: 41.8%; Average loss: 3.2959
Iteration: 1674; Percent complete: 41.9%; Average loss: 3.3104
Iteration: 1675; Percent complete: 41.9%; Average loss: 3.2377
Iteration: 1676; Percent complete: 41.9%; Average loss: 3.3166
Iteration: 1677; Percent complete: 41.9%; Average loss: 3.2049
Iteration: 1678; Percent complete: 41.9%; Average loss: 3.2637
Iteration: 1679; Percent complete: 42.0%; Average loss: 3.3159
Iteration: 1680; Percent complete: 42.0%; Average loss: 3.5735
Iteration: 1681; Percent complete: 42.0%; Average loss: 3.1216
Iteration: 1682; Percent complete: 42.0%; Average loss: 3.3771
Iteration: 1683; Percent complete: 42.1%; Average loss: 3.4872
Iteration: 1684; Percent complete: 42.1%; Average loss: 3.2501
Iteration: 1685; Percent complete: 42.1%; Average loss: 3.1111
Iteration: 1686; Percent complete: 42.1%; Average loss: 3.1123
Iteration: 1687; Percent complete: 42.2%; Average loss: 3.1611
Iteration: 1688; Percent complete: 42.2%; Average loss: 3.4695
Iteration: 1689; Percent complete: 42.2%; Average loss: 3.3202
Iteration: 1690; Percent complete: 42.2%; Average loss: 3.0154
Iteration: 1691; Percent complete: 42.3%; Average loss: 3.2373
Iteration: 1692; Percent complete: 42.3%; Average loss: 3.5879
Iteration: 1693; Percent complete: 42.3%; Average loss: 3.1520
Iteration: 1694; Percent complete: 42.4%; Average loss: 3.2998
Iteration: 1695; Percent complete: 42.4%; Average loss: 3.1251
Iteration: 1696; Percent complete: 42.4%; Average loss: 3.3398
Iteration: 1697; Percent complete: 42.4%; Average loss: 3.0215
Iteration: 1698; Percent complete: 42.4%; Average loss: 3.1697
Iteration: 1699; Percent complete: 42.5%; Average loss: 3.1079
Iteration: 1700; Percent complete: 42.5%; Average loss: 2.9508
Iteration: 1701; Percent complete: 42.5%; Average loss: 3.3100
Iteration: 1702; Percent complete: 42.5%; Average loss: 3.2871
Iteration: 1703; Percent complete: 42.6%; Average loss: 3.1984
Iteration: 1704; Percent complete: 42.6%; Average loss: 3.0862
Iteration: 1705; Percent complete: 42.6%; Average loss: 3.4542
Iteration: 1706; Percent complete: 42.6%; Average loss: 3.1600
Iteration: 1707; Percent complete: 42.7%; Average loss: 3.3895
Iteration: 1708; Percent complete: 42.7%; Average loss: 3.3433
Iteration: 1709; Percent complete: 42.7%; Average loss: 3.0480
Iteration: 1710; Percent complete: 42.8%; Average loss: 3.4129
Iteration: 1711; Percent complete: 42.8%; Average loss: 3.2369
Iteration: 1712; Percent complete: 42.8%; Average loss: 3.3014
Iteration: 1713; Percent complete: 42.8%; Average loss: 3.0749
Iteration: 1714; Percent complete: 42.9%; Average loss: 3.2809
Iteration: 1715; Percent complete: 42.9%; Average loss: 3.1237
Iteration: 1716; Percent complete: 42.9%; Average loss: 3.3035
Iteration: 1717; Percent complete: 42.9%; Average loss: 3.4059
Iteration: 1718; Percent complete: 43.0%; Average loss: 3.1069
Iteration: 1719; Percent complete: 43.0%; Average loss: 3.1894
Iteration: 1720; Percent complete: 43.0%; Average loss: 3.2561
Iteration: 1721; Percent complete: 43.0%; Average loss: 3.2217
Iteration: 1722; Percent complete: 43.0%; Average loss: 3.4093
Iteration: 1723; Percent complete: 43.1%; Average loss: 3.3487
Iteration: 1724; Percent complete: 43.1%; Average loss: 3.0878
Iteration: 1725; Percent complete: 43.1%; Average loss: 3.3616
Iteration: 1726; Percent complete: 43.1%; Average loss: 3.3090
Iteration: 1727; Percent complete: 43.2%; Average loss: 3.2800
Iteration: 1728; Percent complete: 43.2%; Average loss: 3.2471
Iteration: 1729; Percent complete: 43.2%; Average loss: 3.2661
Iteration: 1730; Percent complete: 43.2%; Average loss: 3.1878
Iteration: 1731; Percent complete: 43.3%; Average loss: 3.0538
Iteration: 1732; Percent complete: 43.3%; Average loss: 3.3536
Iteration: 1733; Percent complete: 43.3%; Average loss: 3.0993
Iteration: 1734; Percent complete: 43.4%; Average loss: 2.9269
Iteration: 1735; Percent complete: 43.4%; Average loss: 3.1193
Iteration: 1736; Percent complete: 43.4%; Average loss: 3.1214
Iteration: 1737; Percent complete: 43.4%; Average loss: 3.0283
Iteration: 1738; Percent complete: 43.5%; Average loss: 3.1211
Iteration: 1739; Percent complete: 43.5%; Average loss: 3.2273
Iteration: 1740; Percent complete: 43.5%; Average loss: 3.1589
Iteration: 1741; Percent complete: 43.5%; Average loss: 3.1835
Iteration: 1742; Percent complete: 43.5%; Average loss: 3.2610
Iteration: 1743; Percent complete: 43.6%; Average loss: 3.1729
Iteration: 1744; Percent complete: 43.6%; Average loss: 3.3588
Iteration: 1745; Percent complete: 43.6%; Average loss: 3.0267
Iteration: 1746; Percent complete: 43.6%; Average loss: 3.0484
Iteration: 1747; Percent complete: 43.7%; Average loss: 3.4701
Iteration: 1748; Percent complete: 43.7%; Average loss: 3.2783
Iteration: 1749; Percent complete: 43.7%; Average loss: 3.1200
Iteration: 1750; Percent complete: 43.8%; Average loss: 2.9558
Iteration: 1751; Percent complete: 43.8%; Average loss: 3.1693
Iteration: 1752; Percent complete: 43.8%; Average loss: 3.0413
Iteration: 1753; Percent complete: 43.8%; Average loss: 3.3381
Iteration: 1754; Percent complete: 43.9%; Average loss: 3.1479
Iteration: 1755; Percent complete: 43.9%; Average loss: 3.3464
Iteration: 1756; Percent complete: 43.9%; Average loss: 3.1285
Iteration: 1757; Percent complete: 43.9%; Average loss: 3.3990
Iteration: 1758; Percent complete: 44.0%; Average loss: 3.1664
Iteration: 1759; Percent complete: 44.0%; Average loss: 3.1611
Iteration: 1760; Percent complete: 44.0%; Average loss: 3.3502
Iteration: 1761; Percent complete: 44.0%; Average loss: 3.0243
Iteration: 1762; Percent complete: 44.0%; Average loss: 3.2586
Iteration: 1763; Percent complete: 44.1%; Average loss: 3.4153
Iteration: 1764; Percent complete: 44.1%; Average loss: 3.3059
Iteration: 1765; Percent complete: 44.1%; Average loss: 3.5333
Iteration: 1766; Percent complete: 44.1%; Average loss: 2.9984
Iteration: 1767; Percent complete: 44.2%; Average loss: 3.5294
Iteration: 1768; Percent complete: 44.2%; Average loss: 3.2697
Iteration: 1769; Percent complete: 44.2%; Average loss: 3.3785
Iteration: 1770; Percent complete: 44.2%; Average loss: 3.4528
Iteration: 1771; Percent complete: 44.3%; Average loss: 3.2912
Iteration: 1772; Percent complete: 44.3%; Average loss: 3.1710
Iteration: 1773; Percent complete: 44.3%; Average loss: 3.1072
Iteration: 1774; Percent complete: 44.4%; Average loss: 3.0724
Iteration: 1775; Percent complete: 44.4%; Average loss: 3.1787
Iteration: 1776; Percent complete: 44.4%; Average loss: 3.2585
Iteration: 1777; Percent complete: 44.4%; Average loss: 3.0975
Iteration: 1778; Percent complete: 44.5%; Average loss: 2.9003
Iteration: 1779; Percent complete: 44.5%; Average loss: 3.1685
Iteration: 1780; Percent complete: 44.5%; Average loss: 3.4216
Iteration: 1781; Percent complete: 44.5%; Average loss: 3.1733
Iteration: 1782; Percent complete: 44.5%; Average loss: 3.0225
Iteration: 1783; Percent complete: 44.6%; Average loss: 3.3654
Iteration: 1784; Percent complete: 44.6%; Average loss: 2.9353
Iteration: 1785; Percent complete: 44.6%; Average loss: 3.1515
Iteration: 1786; Percent complete: 44.6%; Average loss: 3.1702
Iteration: 1787; Percent complete: 44.7%; Average loss: 3.2136
Iteration: 1788; Percent complete: 44.7%; Average loss: 3.3323
Iteration: 1789; Percent complete: 44.7%; Average loss: 3.4034
Iteration: 1790; Percent complete: 44.8%; Average loss: 3.4719
Iteration: 1791; Percent complete: 44.8%; Average loss: 3.2665
Iteration: 1792; Percent complete: 44.8%; Average loss: 3.1569
Iteration: 1793; Percent complete: 44.8%; Average loss: 3.1784
Iteration: 1794; Percent complete: 44.9%; Average loss: 3.2220
Iteration: 1795; Percent complete: 44.9%; Average loss: 3.2589
Iteration: 1796; Percent complete: 44.9%; Average loss: 3.1306
Iteration: 1797; Percent complete: 44.9%; Average loss: 3.4654
Iteration: 1798; Percent complete: 45.0%; Average loss: 3.1510
Iteration: 1799; Percent complete: 45.0%; Average loss: 3.3566
Iteration: 1800; Percent complete: 45.0%; Average loss: 3.5151
Iteration: 1801; Percent complete: 45.0%; Average loss: 3.0563
Iteration: 1802; Percent complete: 45.1%; Average loss: 3.3945
Iteration: 1803; Percent complete: 45.1%; Average loss: 3.5410
Iteration: 1804; Percent complete: 45.1%; Average loss: 3.3115
Iteration: 1805; Percent complete: 45.1%; Average loss: 3.0064
Iteration: 1806; Percent complete: 45.1%; Average loss: 3.2743
Iteration: 1807; Percent complete: 45.2%; Average loss: 3.2277
Iteration: 1808; Percent complete: 45.2%; Average loss: 3.3199
Iteration: 1809; Percent complete: 45.2%; Average loss: 3.1046
Iteration: 1810; Percent complete: 45.2%; Average loss: 3.3910
Iteration: 1811; Percent complete: 45.3%; Average loss: 2.9474
Iteration: 1812; Percent complete: 45.3%; Average loss: 3.3222
Iteration: 1813; Percent complete: 45.3%; Average loss: 3.2255
Iteration: 1814; Percent complete: 45.4%; Average loss: 3.0802
Iteration: 1815; Percent complete: 45.4%; Average loss: 3.2206
Iteration: 1816; Percent complete: 45.4%; Average loss: 3.0473
Iteration: 1817; Percent complete: 45.4%; Average loss: 3.4612
Iteration: 1818; Percent complete: 45.5%; Average loss: 3.1674
Iteration: 1819; Percent complete: 45.5%; Average loss: 3.2722
Iteration: 1820; Percent complete: 45.5%; Average loss: 3.0950
Iteration: 1821; Percent complete: 45.5%; Average loss: 2.9561
Iteration: 1822; Percent complete: 45.6%; Average loss: 3.1331
Iteration: 1823; Percent complete: 45.6%; Average loss: 3.3261
Iteration: 1824; Percent complete: 45.6%; Average loss: 2.8709
Iteration: 1825; Percent complete: 45.6%; Average loss: 3.4153
Iteration: 1826; Percent complete: 45.6%; Average loss: 3.0131
Iteration: 1827; Percent complete: 45.7%; Average loss: 3.3757
Iteration: 1828; Percent complete: 45.7%; Average loss: 3.1802
Iteration: 1829; Percent complete: 45.7%; Average loss: 3.2779
Iteration: 1830; Percent complete: 45.8%; Average loss: 3.4582
Iteration: 1831; Percent complete: 45.8%; Average loss: 3.2420
Iteration: 1832; Percent complete: 45.8%; Average loss: 3.2694
Iteration: 1833; Percent complete: 45.8%; Average loss: 3.3076
Iteration: 1834; Percent complete: 45.9%; Average loss: 3.0677
Iteration: 1835; Percent complete: 45.9%; Average loss: 3.2360
Iteration: 1836; Percent complete: 45.9%; Average loss: 3.2752
Iteration: 1837; Percent complete: 45.9%; Average loss: 3.2703
Iteration: 1838; Percent complete: 46.0%; Average loss: 3.2102
Iteration: 1839; Percent complete: 46.0%; Average loss: 3.1061
Iteration: 1840; Percent complete: 46.0%; Average loss: 3.1877
Iteration: 1841; Percent complete: 46.0%; Average loss: 3.1912
Iteration: 1842; Percent complete: 46.1%; Average loss: 3.1829
Iteration: 1843; Percent complete: 46.1%; Average loss: 3.0365
Iteration: 1844; Percent complete: 46.1%; Average loss: 3.1262
Iteration: 1845; Percent complete: 46.1%; Average loss: 3.0926
Iteration: 1846; Percent complete: 46.2%; Average loss: 3.0315
Iteration: 1847; Percent complete: 46.2%; Average loss: 3.3566
Iteration: 1848; Percent complete: 46.2%; Average loss: 3.3644
Iteration: 1849; Percent complete: 46.2%; Average loss: 3.1089
Iteration: 1850; Percent complete: 46.2%; Average loss: 3.3636
Iteration: 1851; Percent complete: 46.3%; Average loss: 3.0658
Iteration: 1852; Percent complete: 46.3%; Average loss: 2.9920
Iteration: 1853; Percent complete: 46.3%; Average loss: 3.2803
Iteration: 1854; Percent complete: 46.4%; Average loss: 3.1211
Iteration: 1855; Percent complete: 46.4%; Average loss: 3.3826
Iteration: 1856; Percent complete: 46.4%; Average loss: 3.1360
Iteration: 1857; Percent complete: 46.4%; Average loss: 2.8996
Iteration: 1858; Percent complete: 46.5%; Average loss: 3.1261
Iteration: 1859; Percent complete: 46.5%; Average loss: 3.0025
Iteration: 1860; Percent complete: 46.5%; Average loss: 3.2659
Iteration: 1861; Percent complete: 46.5%; Average loss: 3.0919
Iteration: 1862; Percent complete: 46.6%; Average loss: 3.1813
Iteration: 1863; Percent complete: 46.6%; Average loss: 3.1184
Iteration: 1864; Percent complete: 46.6%; Average loss: 3.1412
Iteration: 1865; Percent complete: 46.6%; Average loss: 2.9379
Iteration: 1866; Percent complete: 46.7%; Average loss: 3.2816
Iteration: 1867; Percent complete: 46.7%; Average loss: 3.1564
Iteration: 1868; Percent complete: 46.7%; Average loss: 2.9056
Iteration: 1869; Percent complete: 46.7%; Average loss: 3.1437
Iteration: 1870; Percent complete: 46.8%; Average loss: 3.2347
Iteration: 1871; Percent complete: 46.8%; Average loss: 3.3947
Iteration: 1872; Percent complete: 46.8%; Average loss: 3.0747
Iteration: 1873; Percent complete: 46.8%; Average loss: 3.0071
Iteration: 1874; Percent complete: 46.9%; Average loss: 3.0352
Iteration: 1875; Percent complete: 46.9%; Average loss: 3.2274
Iteration: 1876; Percent complete: 46.9%; Average loss: 3.1689
Iteration: 1877; Percent complete: 46.9%; Average loss: 3.0380
Iteration: 1878; Percent complete: 46.9%; Average loss: 3.3100
Iteration: 1879; Percent complete: 47.0%; Average loss: 3.2255
Iteration: 1880; Percent complete: 47.0%; Average loss: 3.1758
Iteration: 1881; Percent complete: 47.0%; Average loss: 3.1924
Iteration: 1882; Percent complete: 47.0%; Average loss: 3.3661
Iteration: 1883; Percent complete: 47.1%; Average loss: 3.0658
Iteration: 1884; Percent complete: 47.1%; Average loss: 3.1817
Iteration: 1885; Percent complete: 47.1%; Average loss: 3.0748
Iteration: 1886; Percent complete: 47.1%; Average loss: 3.2424
Iteration: 1887; Percent complete: 47.2%; Average loss: 2.9664
Iteration: 1888; Percent complete: 47.2%; Average loss: 3.2357
Iteration: 1889; Percent complete: 47.2%; Average loss: 3.1394
Iteration: 1890; Percent complete: 47.2%; Average loss: 3.0718
Iteration: 1891; Percent complete: 47.3%; Average loss: 3.2589
Iteration: 1892; Percent complete: 47.3%; Average loss: 3.2358
Iteration: 1893; Percent complete: 47.3%; Average loss: 3.2648
Iteration: 1894; Percent complete: 47.3%; Average loss: 3.1515
Iteration: 1895; Percent complete: 47.4%; Average loss: 3.3702
Iteration: 1896; Percent complete: 47.4%; Average loss: 3.1695
Iteration: 1897; Percent complete: 47.4%; Average loss: 2.9680
Iteration: 1898; Percent complete: 47.4%; Average loss: 3.0865
Iteration: 1899; Percent complete: 47.5%; Average loss: 3.1460
Iteration: 1900; Percent complete: 47.5%; Average loss: 3.2196
Iteration: 1901; Percent complete: 47.5%; Average loss: 3.2792
Iteration: 1902; Percent complete: 47.5%; Average loss: 3.1665
Iteration: 1903; Percent complete: 47.6%; Average loss: 3.1749
Iteration: 1904; Percent complete: 47.6%; Average loss: 3.0404
Iteration: 1905; Percent complete: 47.6%; Average loss: 3.1976
Iteration: 1906; Percent complete: 47.6%; Average loss: 2.9766
Iteration: 1907; Percent complete: 47.7%; Average loss: 3.2813
Iteration: 1908; Percent complete: 47.7%; Average loss: 3.1437
Iteration: 1909; Percent complete: 47.7%; Average loss: 3.4470
Iteration: 1910; Percent complete: 47.8%; Average loss: 3.1994
Iteration: 1911; Percent complete: 47.8%; Average loss: 3.2526
Iteration: 1912; Percent complete: 47.8%; Average loss: 3.1024
Iteration: 1913; Percent complete: 47.8%; Average loss: 3.1274
Iteration: 1914; Percent complete: 47.9%; Average loss: 3.2944
Iteration: 1915; Percent complete: 47.9%; Average loss: 3.2553
Iteration: 1916; Percent complete: 47.9%; Average loss: 3.1658
Iteration: 1917; Percent complete: 47.9%; Average loss: 3.2785
Iteration: 1918; Percent complete: 47.9%; Average loss: 3.0904
Iteration: 1919; Percent complete: 48.0%; Average loss: 3.3073
Iteration: 1920; Percent complete: 48.0%; Average loss: 3.0818
Iteration: 1921; Percent complete: 48.0%; Average loss: 3.0863
Iteration: 1922; Percent complete: 48.0%; Average loss: 3.3146
Iteration: 1923; Percent complete: 48.1%; Average loss: 3.2413
Iteration: 1924; Percent complete: 48.1%; Average loss: 2.9764
Iteration: 1925; Percent complete: 48.1%; Average loss: 3.1290
Iteration: 1926; Percent complete: 48.1%; Average loss: 3.2581
Iteration: 1927; Percent complete: 48.2%; Average loss: 3.2115
Iteration: 1928; Percent complete: 48.2%; Average loss: 3.1798
Iteration: 1929; Percent complete: 48.2%; Average loss: 3.2008
Iteration: 1930; Percent complete: 48.2%; Average loss: 3.3786
Iteration: 1931; Percent complete: 48.3%; Average loss: 3.4713
Iteration: 1932; Percent complete: 48.3%; Average loss: 3.3717
Iteration: 1933; Percent complete: 48.3%; Average loss: 3.0430
Iteration: 1934; Percent complete: 48.4%; Average loss: 3.2243
Iteration: 1935; Percent complete: 48.4%; Average loss: 3.1069
Iteration: 1936; Percent complete: 48.4%; Average loss: 3.2390
Iteration: 1937; Percent complete: 48.4%; Average loss: 3.3759
Iteration: 1938; Percent complete: 48.4%; Average loss: 2.8256
Iteration: 1939; Percent complete: 48.5%; Average loss: 3.1027
Iteration: 1940; Percent complete: 48.5%; Average loss: 3.2979
Iteration: 1941; Percent complete: 48.5%; Average loss: 3.0118
Iteration: 1942; Percent complete: 48.5%; Average loss: 3.3311
Iteration: 1943; Percent complete: 48.6%; Average loss: 3.2717
Iteration: 1944; Percent complete: 48.6%; Average loss: 2.9668
Iteration: 1945; Percent complete: 48.6%; Average loss: 2.9585
Iteration: 1946; Percent complete: 48.6%; Average loss: 3.2501
Iteration: 1947; Percent complete: 48.7%; Average loss: 3.1529
Iteration: 1948; Percent complete: 48.7%; Average loss: 3.1187
Iteration: 1949; Percent complete: 48.7%; Average loss: 3.3039
Iteration: 1950; Percent complete: 48.8%; Average loss: 3.1675
Iteration: 1951; Percent complete: 48.8%; Average loss: 3.1151
Iteration: 1952; Percent complete: 48.8%; Average loss: 3.2471
Iteration: 1953; Percent complete: 48.8%; Average loss: 3.1475
Iteration: 1954; Percent complete: 48.9%; Average loss: 2.9699
Iteration: 1955; Percent complete: 48.9%; Average loss: 3.4026
Iteration: 1956; Percent complete: 48.9%; Average loss: 3.2610
Iteration: 1957; Percent complete: 48.9%; Average loss: 2.9698
Iteration: 1958; Percent complete: 48.9%; Average loss: 3.1014
Iteration: 1959; Percent complete: 49.0%; Average loss: 2.9904
Iteration: 1960; Percent complete: 49.0%; Average loss: 3.0239
Iteration: 1961; Percent complete: 49.0%; Average loss: 3.2027
Iteration: 1962; Percent complete: 49.0%; Average loss: 2.9343
Iteration: 1963; Percent complete: 49.1%; Average loss: 2.9822
Iteration: 1964; Percent complete: 49.1%; Average loss: 3.0407
Iteration: 1965; Percent complete: 49.1%; Average loss: 2.9366
Iteration: 1966; Percent complete: 49.1%; Average loss: 3.2640
Iteration: 1967; Percent complete: 49.2%; Average loss: 3.1929
Iteration: 1968; Percent complete: 49.2%; Average loss: 3.2709
Iteration: 1969; Percent complete: 49.2%; Average loss: 3.3117
Iteration: 1970; Percent complete: 49.2%; Average loss: 3.2832
Iteration: 1971; Percent complete: 49.3%; Average loss: 3.1499
Iteration: 1972; Percent complete: 49.3%; Average loss: 3.1422
Iteration: 1973; Percent complete: 49.3%; Average loss: 3.3057
Iteration: 1974; Percent complete: 49.4%; Average loss: 3.1289
Iteration: 1975; Percent complete: 49.4%; Average loss: 3.3076
Iteration: 1976; Percent complete: 49.4%; Average loss: 3.0463
Iteration: 1977; Percent complete: 49.4%; Average loss: 3.1155
Iteration: 1978; Percent complete: 49.5%; Average loss: 2.9186
Iteration: 1979; Percent complete: 49.5%; Average loss: 3.1344
Iteration: 1980; Percent complete: 49.5%; Average loss: 3.0798
Iteration: 1981; Percent complete: 49.5%; Average loss: 3.2132
Iteration: 1982; Percent complete: 49.5%; Average loss: 3.1166
Iteration: 1983; Percent complete: 49.6%; Average loss: 2.8944
Iteration: 1984; Percent complete: 49.6%; Average loss: 3.1531
Iteration: 1985; Percent complete: 49.6%; Average loss: 3.1763
Iteration: 1986; Percent complete: 49.6%; Average loss: 3.5200
Iteration: 1987; Percent complete: 49.7%; Average loss: 3.1963
Iteration: 1988; Percent complete: 49.7%; Average loss: 3.0417
Iteration: 1989; Percent complete: 49.7%; Average loss: 3.2398
Iteration: 1990; Percent complete: 49.8%; Average loss: 3.2703
Iteration: 1991; Percent complete: 49.8%; Average loss: 3.1547
Iteration: 1992; Percent complete: 49.8%; Average loss: 3.2381
Iteration: 1993; Percent complete: 49.8%; Average loss: 2.9893
Iteration: 1994; Percent complete: 49.9%; Average loss: 3.1484
Iteration: 1995; Percent complete: 49.9%; Average loss: 3.2658
Iteration: 1996; Percent complete: 49.9%; Average loss: 3.1762
Iteration: 1997; Percent complete: 49.9%; Average loss: 3.0956
Iteration: 1998; Percent complete: 50.0%; Average loss: 3.2832
Iteration: 1999; Percent complete: 50.0%; Average loss: 3.1968
Iteration: 2000; Percent complete: 50.0%; Average loss: 2.9797
Iteration: 2001; Percent complete: 50.0%; Average loss: 3.0523
Iteration: 2002; Percent complete: 50.0%; Average loss: 2.9543
Iteration: 2003; Percent complete: 50.1%; Average loss: 3.1488
Iteration: 2004; Percent complete: 50.1%; Average loss: 3.3702
Iteration: 2005; Percent complete: 50.1%; Average loss: 3.1784
Iteration: 2006; Percent complete: 50.1%; Average loss: 2.9331
Iteration: 2007; Percent complete: 50.2%; Average loss: 3.2671
Iteration: 2008; Percent complete: 50.2%; Average loss: 3.0974
Iteration: 2009; Percent complete: 50.2%; Average loss: 3.2098
Iteration: 2010; Percent complete: 50.2%; Average loss: 3.1465
Iteration: 2011; Percent complete: 50.3%; Average loss: 3.2643
Iteration: 2012; Percent complete: 50.3%; Average loss: 3.4542
Iteration: 2013; Percent complete: 50.3%; Average loss: 3.1317
Iteration: 2014; Percent complete: 50.3%; Average loss: 3.1502
Iteration: 2015; Percent complete: 50.4%; Average loss: 3.0599
Iteration: 2016; Percent complete: 50.4%; Average loss: 3.3691
Iteration: 2017; Percent complete: 50.4%; Average loss: 3.0417
Iteration: 2018; Percent complete: 50.4%; Average loss: 2.8706
Iteration: 2019; Percent complete: 50.5%; Average loss: 3.1221
Iteration: 2020; Percent complete: 50.5%; Average loss: 3.1089
Iteration: 2021; Percent complete: 50.5%; Average loss: 3.3108
Iteration: 2022; Percent complete: 50.5%; Average loss: 3.2910
Iteration: 2023; Percent complete: 50.6%; Average loss: 3.2038
Iteration: 2024; Percent complete: 50.6%; Average loss: 3.1596
Iteration: 2025; Percent complete: 50.6%; Average loss: 3.3256
Iteration: 2026; Percent complete: 50.6%; Average loss: 3.3482
Iteration: 2027; Percent complete: 50.7%; Average loss: 3.1644
Iteration: 2028; Percent complete: 50.7%; Average loss: 3.1361
Iteration: 2029; Percent complete: 50.7%; Average loss: 3.2253
Iteration: 2030; Percent complete: 50.7%; Average loss: 3.0291
Iteration: 2031; Percent complete: 50.8%; Average loss: 3.1562
Iteration: 2032; Percent complete: 50.8%; Average loss: 3.1138
Iteration: 2033; Percent complete: 50.8%; Average loss: 3.1857
Iteration: 2034; Percent complete: 50.8%; Average loss: 3.0990
Iteration: 2035; Percent complete: 50.9%; Average loss: 3.0997
Iteration: 2036; Percent complete: 50.9%; Average loss: 3.3142
Iteration: 2037; Percent complete: 50.9%; Average loss: 3.2002
Iteration: 2038; Percent complete: 50.9%; Average loss: 3.0560
Iteration: 2039; Percent complete: 51.0%; Average loss: 3.2014
Iteration: 2040; Percent complete: 51.0%; Average loss: 3.2247
Iteration: 2041; Percent complete: 51.0%; Average loss: 3.1517
Iteration: 2042; Percent complete: 51.0%; Average loss: 3.2389
Iteration: 2043; Percent complete: 51.1%; Average loss: 2.9913
Iteration: 2044; Percent complete: 51.1%; Average loss: 3.2712
Iteration: 2045; Percent complete: 51.1%; Average loss: 3.1153
Iteration: 2046; Percent complete: 51.1%; Average loss: 2.9798
Iteration: 2047; Percent complete: 51.2%; Average loss: 3.0915
Iteration: 2048; Percent complete: 51.2%; Average loss: 3.1078
Iteration: 2049; Percent complete: 51.2%; Average loss: 2.9665
Iteration: 2050; Percent complete: 51.2%; Average loss: 3.0883
Iteration: 2051; Percent complete: 51.3%; Average loss: 3.2264
Iteration: 2052; Percent complete: 51.3%; Average loss: 3.2168
Iteration: 2053; Percent complete: 51.3%; Average loss: 3.3416
Iteration: 2054; Percent complete: 51.3%; Average loss: 3.3070
Iteration: 2055; Percent complete: 51.4%; Average loss: 3.2836
Iteration: 2056; Percent complete: 51.4%; Average loss: 2.9652
Iteration: 2057; Percent complete: 51.4%; Average loss: 2.8636
Iteration: 2058; Percent complete: 51.4%; Average loss: 3.1555
Iteration: 2059; Percent complete: 51.5%; Average loss: 3.0214
Iteration: 2060; Percent complete: 51.5%; Average loss: 3.3392
Iteration: 2061; Percent complete: 51.5%; Average loss: 3.4377
Iteration: 2062; Percent complete: 51.5%; Average loss: 2.9923
Iteration: 2063; Percent complete: 51.6%; Average loss: 3.0432
Iteration: 2064; Percent complete: 51.6%; Average loss: 3.1049
Iteration: 2065; Percent complete: 51.6%; Average loss: 3.1117
Iteration: 2066; Percent complete: 51.6%; Average loss: 3.3618
Iteration: 2067; Percent complete: 51.7%; Average loss: 2.9363
Iteration: 2068; Percent complete: 51.7%; Average loss: 3.1880
Iteration: 2069; Percent complete: 51.7%; Average loss: 2.9503
Iteration: 2070; Percent complete: 51.7%; Average loss: 3.0353
Iteration: 2071; Percent complete: 51.8%; Average loss: 3.1759
Iteration: 2072; Percent complete: 51.8%; Average loss: 3.3033
Iteration: 2073; Percent complete: 51.8%; Average loss: 3.1362
Iteration: 2074; Percent complete: 51.8%; Average loss: 3.2220
Iteration: 2075; Percent complete: 51.9%; Average loss: 3.2796
Iteration: 2076; Percent complete: 51.9%; Average loss: 3.1060
Iteration: 2077; Percent complete: 51.9%; Average loss: 2.9112
Iteration: 2078; Percent complete: 51.9%; Average loss: 2.9653
Iteration: 2079; Percent complete: 52.0%; Average loss: 3.1008
Iteration: 2080; Percent complete: 52.0%; Average loss: 2.9339
Iteration: 2081; Percent complete: 52.0%; Average loss: 2.9429
Iteration: 2082; Percent complete: 52.0%; Average loss: 3.0743
Iteration: 2083; Percent complete: 52.1%; Average loss: 3.2896
Iteration: 2084; Percent complete: 52.1%; Average loss: 3.0963
Iteration: 2085; Percent complete: 52.1%; Average loss: 3.1076
Iteration: 2086; Percent complete: 52.1%; Average loss: 3.4169
Iteration: 2087; Percent complete: 52.2%; Average loss: 3.1518
Iteration: 2088; Percent complete: 52.2%; Average loss: 3.2424
Iteration: 2089; Percent complete: 52.2%; Average loss: 3.1133
Iteration: 2090; Percent complete: 52.2%; Average loss: 3.1366
Iteration: 2091; Percent complete: 52.3%; Average loss: 3.1260
Iteration: 2092; Percent complete: 52.3%; Average loss: 3.1784
Iteration: 2093; Percent complete: 52.3%; Average loss: 3.2637
Iteration: 2094; Percent complete: 52.3%; Average loss: 3.1177
Iteration: 2095; Percent complete: 52.4%; Average loss: 3.1153
Iteration: 2096; Percent complete: 52.4%; Average loss: 2.9925
Iteration: 2097; Percent complete: 52.4%; Average loss: 3.2188
Iteration: 2098; Percent complete: 52.4%; Average loss: 3.0690
Iteration: 2099; Percent complete: 52.5%; Average loss: 3.1057
Iteration: 2100; Percent complete: 52.5%; Average loss: 3.1747
Iteration: 2101; Percent complete: 52.5%; Average loss: 3.2247
Iteration: 2102; Percent complete: 52.5%; Average loss: 3.0825
Iteration: 2103; Percent complete: 52.6%; Average loss: 3.0037
Iteration: 2104; Percent complete: 52.6%; Average loss: 2.9889
Iteration: 2105; Percent complete: 52.6%; Average loss: 3.0795
Iteration: 2106; Percent complete: 52.6%; Average loss: 3.3426
Iteration: 2107; Percent complete: 52.7%; Average loss: 3.3885
Iteration: 2108; Percent complete: 52.7%; Average loss: 3.2041
Iteration: 2109; Percent complete: 52.7%; Average loss: 3.1306
Iteration: 2110; Percent complete: 52.8%; Average loss: 2.8241
Iteration: 2111; Percent complete: 52.8%; Average loss: 3.1024
Iteration: 2112; Percent complete: 52.8%; Average loss: 3.1371
Iteration: 2113; Percent complete: 52.8%; Average loss: 3.0191
Iteration: 2114; Percent complete: 52.8%; Average loss: 2.8564
Iteration: 2115; Percent complete: 52.9%; Average loss: 3.3807
Iteration: 2116; Percent complete: 52.9%; Average loss: 3.1214
Iteration: 2117; Percent complete: 52.9%; Average loss: 2.9468
Iteration: 2118; Percent complete: 52.9%; Average loss: 3.3518
Iteration: 2119; Percent complete: 53.0%; Average loss: 2.8473
Iteration: 2120; Percent complete: 53.0%; Average loss: 3.1174
Iteration: 2121; Percent complete: 53.0%; Average loss: 3.2489
Iteration: 2122; Percent complete: 53.0%; Average loss: 3.1182
Iteration: 2123; Percent complete: 53.1%; Average loss: 2.9893
Iteration: 2124; Percent complete: 53.1%; Average loss: 3.3804
Iteration: 2125; Percent complete: 53.1%; Average loss: 2.8867
Iteration: 2126; Percent complete: 53.1%; Average loss: 3.1193
Iteration: 2127; Percent complete: 53.2%; Average loss: 3.1684
Iteration: 2128; Percent complete: 53.2%; Average loss: 3.2207
Iteration: 2129; Percent complete: 53.2%; Average loss: 3.0455
Iteration: 2130; Percent complete: 53.2%; Average loss: 3.2051
Iteration: 2131; Percent complete: 53.3%; Average loss: 3.0574
Iteration: 2132; Percent complete: 53.3%; Average loss: 2.9863
Iteration: 2133; Percent complete: 53.3%; Average loss: 3.0791
Iteration: 2134; Percent complete: 53.3%; Average loss: 3.2206
Iteration: 2135; Percent complete: 53.4%; Average loss: 3.1561
Iteration: 2136; Percent complete: 53.4%; Average loss: 2.9960
Iteration: 2137; Percent complete: 53.4%; Average loss: 2.8964
Iteration: 2138; Percent complete: 53.4%; Average loss: 3.0186
Iteration: 2139; Percent complete: 53.5%; Average loss: 2.9508
Iteration: 2140; Percent complete: 53.5%; Average loss: 3.2148
Iteration: 2141; Percent complete: 53.5%; Average loss: 2.8597
Iteration: 2142; Percent complete: 53.5%; Average loss: 3.2534
Iteration: 2143; Percent complete: 53.6%; Average loss: 3.2314
Iteration: 2144; Percent complete: 53.6%; Average loss: 3.1652
Iteration: 2145; Percent complete: 53.6%; Average loss: 3.0362
Iteration: 2146; Percent complete: 53.6%; Average loss: 2.9430
Iteration: 2147; Percent complete: 53.7%; Average loss: 3.0752
Iteration: 2148; Percent complete: 53.7%; Average loss: 2.9908
Iteration: 2149; Percent complete: 53.7%; Average loss: 3.0139
Iteration: 2150; Percent complete: 53.8%; Average loss: 2.8768
Iteration: 2151; Percent complete: 53.8%; Average loss: 3.0151
Iteration: 2152; Percent complete: 53.8%; Average loss: 3.2164
Iteration: 2153; Percent complete: 53.8%; Average loss: 2.9636
Iteration: 2154; Percent complete: 53.8%; Average loss: 3.3555
Iteration: 2155; Percent complete: 53.9%; Average loss: 3.2250
Iteration: 2156; Percent complete: 53.9%; Average loss: 2.9098
Iteration: 2157; Percent complete: 53.9%; Average loss: 2.8771
Iteration: 2158; Percent complete: 53.9%; Average loss: 3.0214
Iteration: 2159; Percent complete: 54.0%; Average loss: 3.0523
Iteration: 2160; Percent complete: 54.0%; Average loss: 3.1575
Iteration: 2161; Percent complete: 54.0%; Average loss: 3.3685
Iteration: 2162; Percent complete: 54.0%; Average loss: 3.2327
Iteration: 2163; Percent complete: 54.1%; Average loss: 2.9557
Iteration: 2164; Percent complete: 54.1%; Average loss: 3.0800
Iteration: 2165; Percent complete: 54.1%; Average loss: 3.3638
Iteration: 2166; Percent complete: 54.1%; Average loss: 3.1911
Iteration: 2167; Percent complete: 54.2%; Average loss: 3.1880
Iteration: 2168; Percent complete: 54.2%; Average loss: 3.1138
Iteration: 2169; Percent complete: 54.2%; Average loss: 3.0583
Iteration: 2170; Percent complete: 54.2%; Average loss: 3.1984
Iteration: 2171; Percent complete: 54.3%; Average loss: 3.0556
Iteration: 2172; Percent complete: 54.3%; Average loss: 3.1642
Iteration: 2173; Percent complete: 54.3%; Average loss: 3.3203
Iteration: 2174; Percent complete: 54.4%; Average loss: 3.0620
Iteration: 2175; Percent complete: 54.4%; Average loss: 3.0736
Iteration: 2176; Percent complete: 54.4%; Average loss: 3.0151
Iteration: 2177; Percent complete: 54.4%; Average loss: 3.0929
Iteration: 2178; Percent complete: 54.4%; Average loss: 3.1754
Iteration: 2179; Percent complete: 54.5%; Average loss: 3.1552
Iteration: 2180; Percent complete: 54.5%; Average loss: 3.0865
Iteration: 2181; Percent complete: 54.5%; Average loss: 3.0518
Iteration: 2182; Percent complete: 54.5%; Average loss: 3.0631
Iteration: 2183; Percent complete: 54.6%; Average loss: 3.0880
Iteration: 2184; Percent complete: 54.6%; Average loss: 3.2554
Iteration: 2185; Percent complete: 54.6%; Average loss: 3.1331
Iteration: 2186; Percent complete: 54.6%; Average loss: 3.2332
Iteration: 2187; Percent complete: 54.7%; Average loss: 2.9617
Iteration: 2188; Percent complete: 54.7%; Average loss: 2.9064
Iteration: 2189; Percent complete: 54.7%; Average loss: 2.8995
Iteration: 2190; Percent complete: 54.8%; Average loss: 2.8358
Iteration: 2191; Percent complete: 54.8%; Average loss: 2.9895
Iteration: 2192; Percent complete: 54.8%; Average loss: 3.0812
Iteration: 2193; Percent complete: 54.8%; Average loss: 2.9347
Iteration: 2194; Percent complete: 54.9%; Average loss: 3.1368
Iteration: 2195; Percent complete: 54.9%; Average loss: 3.2701
Iteration: 2196; Percent complete: 54.9%; Average loss: 3.0737
Iteration: 2197; Percent complete: 54.9%; Average loss: 3.1131
Iteration: 2198; Percent complete: 54.9%; Average loss: 3.0079
Iteration: 2199; Percent complete: 55.0%; Average loss: 2.9557
Iteration: 2200; Percent complete: 55.0%; Average loss: 3.1696
Iteration: 2201; Percent complete: 55.0%; Average loss: 3.2011
Iteration: 2202; Percent complete: 55.0%; Average loss: 3.2657
Iteration: 2203; Percent complete: 55.1%; Average loss: 3.4015
Iteration: 2204; Percent complete: 55.1%; Average loss: 3.0744
Iteration: 2205; Percent complete: 55.1%; Average loss: 3.1814
Iteration: 2206; Percent complete: 55.1%; Average loss: 3.0765
Iteration: 2207; Percent complete: 55.2%; Average loss: 3.0675
Iteration: 2208; Percent complete: 55.2%; Average loss: 3.1871
Iteration: 2209; Percent complete: 55.2%; Average loss: 2.9776
Iteration: 2210; Percent complete: 55.2%; Average loss: 3.0834
Iteration: 2211; Percent complete: 55.3%; Average loss: 3.3229
Iteration: 2212; Percent complete: 55.3%; Average loss: 3.1068
Iteration: 2213; Percent complete: 55.3%; Average loss: 3.0999
Iteration: 2214; Percent complete: 55.4%; Average loss: 3.2804
Iteration: 2215; Percent complete: 55.4%; Average loss: 3.1729
Iteration: 2216; Percent complete: 55.4%; Average loss: 3.1026
Iteration: 2217; Percent complete: 55.4%; Average loss: 2.8636
Iteration: 2218; Percent complete: 55.5%; Average loss: 3.1784
Iteration: 2219; Percent complete: 55.5%; Average loss: 2.8664
Iteration: 2220; Percent complete: 55.5%; Average loss: 2.9165
Iteration: 2221; Percent complete: 55.5%; Average loss: 3.0692
Iteration: 2222; Percent complete: 55.5%; Average loss: 3.1265
Iteration: 2223; Percent complete: 55.6%; Average loss: 2.9585
Iteration: 2224; Percent complete: 55.6%; Average loss: 2.9258
Iteration: 2225; Percent complete: 55.6%; Average loss: 2.9687
Iteration: 2226; Percent complete: 55.6%; Average loss: 3.1656
Iteration: 2227; Percent complete: 55.7%; Average loss: 3.1539
Iteration: 2228; Percent complete: 55.7%; Average loss: 3.0362
Iteration: 2229; Percent complete: 55.7%; Average loss: 2.9175
Iteration: 2230; Percent complete: 55.8%; Average loss: 2.9667
Iteration: 2231; Percent complete: 55.8%; Average loss: 2.8577
Iteration: 2232; Percent complete: 55.8%; Average loss: 2.8300
Iteration: 2233; Percent complete: 55.8%; Average loss: 2.9364
Iteration: 2234; Percent complete: 55.9%; Average loss: 3.1096
Iteration: 2235; Percent complete: 55.9%; Average loss: 2.8886
Iteration: 2236; Percent complete: 55.9%; Average loss: 3.1767
Iteration: 2237; Percent complete: 55.9%; Average loss: 3.0691
Iteration: 2238; Percent complete: 56.0%; Average loss: 2.9516
Iteration: 2239; Percent complete: 56.0%; Average loss: 3.3435
Iteration: 2240; Percent complete: 56.0%; Average loss: 3.2448
Iteration: 2241; Percent complete: 56.0%; Average loss: 3.3192
Iteration: 2242; Percent complete: 56.0%; Average loss: 2.8171
Iteration: 2243; Percent complete: 56.1%; Average loss: 3.0064
Iteration: 2244; Percent complete: 56.1%; Average loss: 3.1817
Iteration: 2245; Percent complete: 56.1%; Average loss: 3.1784
Iteration: 2246; Percent complete: 56.1%; Average loss: 3.1308
Iteration: 2247; Percent complete: 56.2%; Average loss: 3.0442
Iteration: 2248; Percent complete: 56.2%; Average loss: 3.0327
Iteration: 2249; Percent complete: 56.2%; Average loss: 2.9928
Iteration: 2250; Percent complete: 56.2%; Average loss: 3.2747
Iteration: 2251; Percent complete: 56.3%; Average loss: 3.1445
Iteration: 2252; Percent complete: 56.3%; Average loss: 2.9269
Iteration: 2253; Percent complete: 56.3%; Average loss: 3.2437
Iteration: 2254; Percent complete: 56.4%; Average loss: 3.2246
Iteration: 2255; Percent complete: 56.4%; Average loss: 2.9377
Iteration: 2256; Percent complete: 56.4%; Average loss: 3.1832
Iteration: 2257; Percent complete: 56.4%; Average loss: 3.1028
Iteration: 2258; Percent complete: 56.5%; Average loss: 2.9830
Iteration: 2259; Percent complete: 56.5%; Average loss: 3.0708
Iteration: 2260; Percent complete: 56.5%; Average loss: 3.2836
Iteration: 2261; Percent complete: 56.5%; Average loss: 2.9774
Iteration: 2262; Percent complete: 56.5%; Average loss: 3.2996
Iteration: 2263; Percent complete: 56.6%; Average loss: 3.0043
Iteration: 2264; Percent complete: 56.6%; Average loss: 3.1899
Iteration: 2265; Percent complete: 56.6%; Average loss: 2.9472
Iteration: 2266; Percent complete: 56.6%; Average loss: 3.0521
Iteration: 2267; Percent complete: 56.7%; Average loss: 3.3516
Iteration: 2268; Percent complete: 56.7%; Average loss: 2.9364
Iteration: 2269; Percent complete: 56.7%; Average loss: 3.0638
Iteration: 2270; Percent complete: 56.8%; Average loss: 2.7368
Iteration: 2271; Percent complete: 56.8%; Average loss: 3.2606
Iteration: 2272; Percent complete: 56.8%; Average loss: 3.1033
Iteration: 2273; Percent complete: 56.8%; Average loss: 3.1994
Iteration: 2274; Percent complete: 56.9%; Average loss: 2.8651
Iteration: 2275; Percent complete: 56.9%; Average loss: 3.0923
Iteration: 2276; Percent complete: 56.9%; Average loss: 3.0435
Iteration: 2277; Percent complete: 56.9%; Average loss: 2.9957
Iteration: 2278; Percent complete: 57.0%; Average loss: 3.0598
Iteration: 2279; Percent complete: 57.0%; Average loss: 2.9631
Iteration: 2280; Percent complete: 57.0%; Average loss: 3.4182
Iteration: 2281; Percent complete: 57.0%; Average loss: 3.0649
Iteration: 2282; Percent complete: 57.0%; Average loss: 2.9557
Iteration: 2283; Percent complete: 57.1%; Average loss: 2.9948
Iteration: 2284; Percent complete: 57.1%; Average loss: 3.0877
Iteration: 2285; Percent complete: 57.1%; Average loss: 3.1802
Iteration: 2286; Percent complete: 57.1%; Average loss: 3.0927
Iteration: 2287; Percent complete: 57.2%; Average loss: 3.3525
Iteration: 2288; Percent complete: 57.2%; Average loss: 3.3282
Iteration: 2289; Percent complete: 57.2%; Average loss: 3.0856
Iteration: 2290; Percent complete: 57.2%; Average loss: 3.0425
Iteration: 2291; Percent complete: 57.3%; Average loss: 3.0198
Iteration: 2292; Percent complete: 57.3%; Average loss: 2.9113
Iteration: 2293; Percent complete: 57.3%; Average loss: 3.2569
Iteration: 2294; Percent complete: 57.4%; Average loss: 3.2331
Iteration: 2295; Percent complete: 57.4%; Average loss: 2.9933
Iteration: 2296; Percent complete: 57.4%; Average loss: 3.1533
Iteration: 2297; Percent complete: 57.4%; Average loss: 3.0874
Iteration: 2298; Percent complete: 57.5%; Average loss: 3.1192
Iteration: 2299; Percent complete: 57.5%; Average loss: 3.1887
Iteration: 2300; Percent complete: 57.5%; Average loss: 3.1792
Iteration: 2301; Percent complete: 57.5%; Average loss: 3.3550
Iteration: 2302; Percent complete: 57.6%; Average loss: 3.0684
Iteration: 2303; Percent complete: 57.6%; Average loss: 2.8909
Iteration: 2304; Percent complete: 57.6%; Average loss: 3.0304
Iteration: 2305; Percent complete: 57.6%; Average loss: 2.9932
Iteration: 2306; Percent complete: 57.6%; Average loss: 3.0787
Iteration: 2307; Percent complete: 57.7%; Average loss: 3.0890
Iteration: 2308; Percent complete: 57.7%; Average loss: 3.0024
Iteration: 2309; Percent complete: 57.7%; Average loss: 3.0058
Iteration: 2310; Percent complete: 57.8%; Average loss: 3.0121
Iteration: 2311; Percent complete: 57.8%; Average loss: 2.8940
Iteration: 2312; Percent complete: 57.8%; Average loss: 3.0991
Iteration: 2313; Percent complete: 57.8%; Average loss: 2.8738
Iteration: 2314; Percent complete: 57.9%; Average loss: 2.9867
Iteration: 2315; Percent complete: 57.9%; Average loss: 3.0089
Iteration: 2316; Percent complete: 57.9%; Average loss: 2.9603
Iteration: 2317; Percent complete: 57.9%; Average loss: 3.1599
Iteration: 2318; Percent complete: 58.0%; Average loss: 2.7323
Iteration: 2319; Percent complete: 58.0%; Average loss: 3.0491
Iteration: 2320; Percent complete: 58.0%; Average loss: 3.1092
Iteration: 2321; Percent complete: 58.0%; Average loss: 3.1554
Iteration: 2322; Percent complete: 58.1%; Average loss: 3.2724
Iteration: 2323; Percent complete: 58.1%; Average loss: 2.7900
Iteration: 2324; Percent complete: 58.1%; Average loss: 3.2629
Iteration: 2325; Percent complete: 58.1%; Average loss: 2.7799
Iteration: 2326; Percent complete: 58.1%; Average loss: 2.8708
Iteration: 2327; Percent complete: 58.2%; Average loss: 3.0286
Iteration: 2328; Percent complete: 58.2%; Average loss: 3.0521
Iteration: 2329; Percent complete: 58.2%; Average loss: 2.9188
Iteration: 2330; Percent complete: 58.2%; Average loss: 3.2054
Iteration: 2331; Percent complete: 58.3%; Average loss: 3.0083
Iteration: 2332; Percent complete: 58.3%; Average loss: 3.1533
Iteration: 2333; Percent complete: 58.3%; Average loss: 2.9660
Iteration: 2334; Percent complete: 58.4%; Average loss: 2.9599
Iteration: 2335; Percent complete: 58.4%; Average loss: 3.0441
Iteration: 2336; Percent complete: 58.4%; Average loss: 2.9355
Iteration: 2337; Percent complete: 58.4%; Average loss: 3.2427
Iteration: 2338; Percent complete: 58.5%; Average loss: 2.8837
Iteration: 2339; Percent complete: 58.5%; Average loss: 2.9495
Iteration: 2340; Percent complete: 58.5%; Average loss: 3.0307
Iteration: 2341; Percent complete: 58.5%; Average loss: 3.1929
Iteration: 2342; Percent complete: 58.6%; Average loss: 3.0859
Iteration: 2343; Percent complete: 58.6%; Average loss: 3.1777
Iteration: 2344; Percent complete: 58.6%; Average loss: 3.2009
Iteration: 2345; Percent complete: 58.6%; Average loss: 3.1184
Iteration: 2346; Percent complete: 58.7%; Average loss: 3.3162
Iteration: 2347; Percent complete: 58.7%; Average loss: 2.8868
Iteration: 2348; Percent complete: 58.7%; Average loss: 2.8783
Iteration: 2349; Percent complete: 58.7%; Average loss: 2.8946
Iteration: 2350; Percent complete: 58.8%; Average loss: 2.9211
Iteration: 2351; Percent complete: 58.8%; Average loss: 3.1107
Iteration: 2352; Percent complete: 58.8%; Average loss: 2.9700
Iteration: 2353; Percent complete: 58.8%; Average loss: 2.8999
Iteration: 2354; Percent complete: 58.9%; Average loss: 2.9296
Iteration: 2355; Percent complete: 58.9%; Average loss: 2.9820
Iteration: 2356; Percent complete: 58.9%; Average loss: 2.9151
Iteration: 2357; Percent complete: 58.9%; Average loss: 2.8835
Iteration: 2358; Percent complete: 59.0%; Average loss: 2.8253
Iteration: 2359; Percent complete: 59.0%; Average loss: 2.8533
Iteration: 2360; Percent complete: 59.0%; Average loss: 3.0226
Iteration: 2361; Percent complete: 59.0%; Average loss: 3.1111
Iteration: 2362; Percent complete: 59.1%; Average loss: 2.8557
Iteration: 2363; Percent complete: 59.1%; Average loss: 3.1064
Iteration: 2364; Percent complete: 59.1%; Average loss: 3.2405
Iteration: 2365; Percent complete: 59.1%; Average loss: 2.9855
Iteration: 2366; Percent complete: 59.2%; Average loss: 2.9244
Iteration: 2367; Percent complete: 59.2%; Average loss: 2.9256
Iteration: 2368; Percent complete: 59.2%; Average loss: 3.4796
Iteration: 2369; Percent complete: 59.2%; Average loss: 2.8346
Iteration: 2370; Percent complete: 59.2%; Average loss: 2.9573
Iteration: 2371; Percent complete: 59.3%; Average loss: 3.1234
Iteration: 2372; Percent complete: 59.3%; Average loss: 3.0912
Iteration: 2373; Percent complete: 59.3%; Average loss: 2.8599
Iteration: 2374; Percent complete: 59.4%; Average loss: 3.1779
Iteration: 2375; Percent complete: 59.4%; Average loss: 3.0494
Iteration: 2376; Percent complete: 59.4%; Average loss: 3.2608
Iteration: 2377; Percent complete: 59.4%; Average loss: 3.1679
Iteration: 2378; Percent complete: 59.5%; Average loss: 3.0681
Iteration: 2379; Percent complete: 59.5%; Average loss: 3.0272
Iteration: 2380; Percent complete: 59.5%; Average loss: 3.0031
Iteration: 2381; Percent complete: 59.5%; Average loss: 2.8955
Iteration: 2382; Percent complete: 59.6%; Average loss: 2.9648
Iteration: 2383; Percent complete: 59.6%; Average loss: 3.0620
Iteration: 2384; Percent complete: 59.6%; Average loss: 3.2767
Iteration: 2385; Percent complete: 59.6%; Average loss: 3.1094
Iteration: 2386; Percent complete: 59.7%; Average loss: 2.9677
Iteration: 2387; Percent complete: 59.7%; Average loss: 3.1573
Iteration: 2388; Percent complete: 59.7%; Average loss: 3.1384
Iteration: 2389; Percent complete: 59.7%; Average loss: 2.8820
Iteration: 2390; Percent complete: 59.8%; Average loss: 2.9785
Iteration: 2391; Percent complete: 59.8%; Average loss: 3.0496
Iteration: 2392; Percent complete: 59.8%; Average loss: 2.9117
Iteration: 2393; Percent complete: 59.8%; Average loss: 2.8239
Iteration: 2394; Percent complete: 59.9%; Average loss: 2.9475
Iteration: 2395; Percent complete: 59.9%; Average loss: 2.9806
Iteration: 2396; Percent complete: 59.9%; Average loss: 3.1835
Iteration: 2397; Percent complete: 59.9%; Average loss: 3.0377
Iteration: 2398; Percent complete: 60.0%; Average loss: 2.9001
Iteration: 2399; Percent complete: 60.0%; Average loss: 2.9861
Iteration: 2400; Percent complete: 60.0%; Average loss: 2.9735
Iteration: 2401; Percent complete: 60.0%; Average loss: 3.2056
Iteration: 2402; Percent complete: 60.1%; Average loss: 3.0990
Iteration: 2403; Percent complete: 60.1%; Average loss: 3.2420
Iteration: 2404; Percent complete: 60.1%; Average loss: 2.7897
Iteration: 2405; Percent complete: 60.1%; Average loss: 3.1239
Iteration: 2406; Percent complete: 60.2%; Average loss: 2.9644
Iteration: 2407; Percent complete: 60.2%; Average loss: 3.0224
Iteration: 2408; Percent complete: 60.2%; Average loss: 3.0556
Iteration: 2409; Percent complete: 60.2%; Average loss: 2.8425
Iteration: 2410; Percent complete: 60.2%; Average loss: 3.0867
Iteration: 2411; Percent complete: 60.3%; Average loss: 3.1178
Iteration: 2412; Percent complete: 60.3%; Average loss: 2.8798
Iteration: 2413; Percent complete: 60.3%; Average loss: 2.8683
Iteration: 2414; Percent complete: 60.4%; Average loss: 3.0835
Iteration: 2415; Percent complete: 60.4%; Average loss: 3.1261
Iteration: 2416; Percent complete: 60.4%; Average loss: 2.9222
Iteration: 2417; Percent complete: 60.4%; Average loss: 2.8564
Iteration: 2418; Percent complete: 60.5%; Average loss: 3.0241
Iteration: 2419; Percent complete: 60.5%; Average loss: 2.8237
Iteration: 2420; Percent complete: 60.5%; Average loss: 3.0608
Iteration: 2421; Percent complete: 60.5%; Average loss: 2.9877
Iteration: 2422; Percent complete: 60.6%; Average loss: 3.0225
Iteration: 2423; Percent complete: 60.6%; Average loss: 2.9738
Iteration: 2424; Percent complete: 60.6%; Average loss: 2.8247
Iteration: 2425; Percent complete: 60.6%; Average loss: 3.1213
Iteration: 2426; Percent complete: 60.7%; Average loss: 3.0708
Iteration: 2427; Percent complete: 60.7%; Average loss: 2.8760
Iteration: 2428; Percent complete: 60.7%; Average loss: 2.8930
Iteration: 2429; Percent complete: 60.7%; Average loss: 2.9542
Iteration: 2430; Percent complete: 60.8%; Average loss: 2.9337
Iteration: 2431; Percent complete: 60.8%; Average loss: 2.8218
Iteration: 2432; Percent complete: 60.8%; Average loss: 3.0455
Iteration: 2433; Percent complete: 60.8%; Average loss: 3.2762
Iteration: 2434; Percent complete: 60.9%; Average loss: 3.0626
Iteration: 2435; Percent complete: 60.9%; Average loss: 2.9849
Iteration: 2436; Percent complete: 60.9%; Average loss: 3.0260
Iteration: 2437; Percent complete: 60.9%; Average loss: 3.0636
Iteration: 2438; Percent complete: 61.0%; Average loss: 3.0905
Iteration: 2439; Percent complete: 61.0%; Average loss: 3.0730
Iteration: 2440; Percent complete: 61.0%; Average loss: 2.9130
Iteration: 2441; Percent complete: 61.0%; Average loss: 3.3787
Iteration: 2442; Percent complete: 61.1%; Average loss: 2.9487
Iteration: 2443; Percent complete: 61.1%; Average loss: 3.0314
Iteration: 2444; Percent complete: 61.1%; Average loss: 2.9382
Iteration: 2445; Percent complete: 61.1%; Average loss: 2.9859
Iteration: 2446; Percent complete: 61.2%; Average loss: 3.1225
Iteration: 2447; Percent complete: 61.2%; Average loss: 3.0939
Iteration: 2448; Percent complete: 61.2%; Average loss: 2.7899
Iteration: 2449; Percent complete: 61.2%; Average loss: 2.8495
Iteration: 2450; Percent complete: 61.3%; Average loss: 2.9094
Iteration: 2451; Percent complete: 61.3%; Average loss: 3.0219
Iteration: 2452; Percent complete: 61.3%; Average loss: 3.3174
Iteration: 2453; Percent complete: 61.3%; Average loss: 2.9701
Iteration: 2454; Percent complete: 61.4%; Average loss: 3.1013
Iteration: 2455; Percent complete: 61.4%; Average loss: 2.9966
Iteration: 2456; Percent complete: 61.4%; Average loss: 2.9458
Iteration: 2457; Percent complete: 61.4%; Average loss: 3.1848
Iteration: 2458; Percent complete: 61.5%; Average loss: 3.3593
Iteration: 2459; Percent complete: 61.5%; Average loss: 3.0510
Iteration: 2460; Percent complete: 61.5%; Average loss: 3.0218
Iteration: 2461; Percent complete: 61.5%; Average loss: 2.9258
Iteration: 2462; Percent complete: 61.6%; Average loss: 2.9169
Iteration: 2463; Percent complete: 61.6%; Average loss: 2.9373
Iteration: 2464; Percent complete: 61.6%; Average loss: 2.9231
Iteration: 2465; Percent complete: 61.6%; Average loss: 3.0251
Iteration: 2466; Percent complete: 61.7%; Average loss: 2.9118
Iteration: 2467; Percent complete: 61.7%; Average loss: 2.9867
Iteration: 2468; Percent complete: 61.7%; Average loss: 2.9710
Iteration: 2469; Percent complete: 61.7%; Average loss: 3.0369
Iteration: 2470; Percent complete: 61.8%; Average loss: 3.0062
Iteration: 2471; Percent complete: 61.8%; Average loss: 3.2176
Iteration: 2472; Percent complete: 61.8%; Average loss: 2.9488
Iteration: 2473; Percent complete: 61.8%; Average loss: 3.1591
Iteration: 2474; Percent complete: 61.9%; Average loss: 3.2393
Iteration: 2475; Percent complete: 61.9%; Average loss: 3.2137
Iteration: 2476; Percent complete: 61.9%; Average loss: 3.1526
Iteration: 2477; Percent complete: 61.9%; Average loss: 3.0191
Iteration: 2478; Percent complete: 62.0%; Average loss: 3.0692
Iteration: 2479; Percent complete: 62.0%; Average loss: 2.9727
Iteration: 2480; Percent complete: 62.0%; Average loss: 3.0875
Iteration: 2481; Percent complete: 62.0%; Average loss: 3.0384
Iteration: 2482; Percent complete: 62.1%; Average loss: 2.8868
Iteration: 2483; Percent complete: 62.1%; Average loss: 3.0306
Iteration: 2484; Percent complete: 62.1%; Average loss: 3.1510
Iteration: 2485; Percent complete: 62.1%; Average loss: 2.9885
Iteration: 2486; Percent complete: 62.2%; Average loss: 3.0975
Iteration: 2487; Percent complete: 62.2%; Average loss: 2.9866
Iteration: 2488; Percent complete: 62.2%; Average loss: 2.9826
Iteration: 2489; Percent complete: 62.2%; Average loss: 2.9450
Iteration: 2490; Percent complete: 62.3%; Average loss: 2.9636
Iteration: 2491; Percent complete: 62.3%; Average loss: 3.1667
Iteration: 2492; Percent complete: 62.3%; Average loss: 3.0833
Iteration: 2493; Percent complete: 62.3%; Average loss: 3.0118
Iteration: 2494; Percent complete: 62.4%; Average loss: 3.0626
Iteration: 2495; Percent complete: 62.4%; Average loss: 2.8494
Iteration: 2496; Percent complete: 62.4%; Average loss: 3.1242
Iteration: 2497; Percent complete: 62.4%; Average loss: 3.0951
Iteration: 2498; Percent complete: 62.5%; Average loss: 3.0914
Iteration: 2499; Percent complete: 62.5%; Average loss: 3.0099
Iteration: 2500; Percent complete: 62.5%; Average loss: 2.9272
Iteration: 2501; Percent complete: 62.5%; Average loss: 3.0447
Iteration: 2502; Percent complete: 62.5%; Average loss: 3.1067
Iteration: 2503; Percent complete: 62.6%; Average loss: 2.7985
Iteration: 2504; Percent complete: 62.6%; Average loss: 3.0675
Iteration: 2505; Percent complete: 62.6%; Average loss: 2.9005
Iteration: 2506; Percent complete: 62.6%; Average loss: 2.6793
Iteration: 2507; Percent complete: 62.7%; Average loss: 2.9956
Iteration: 2508; Percent complete: 62.7%; Average loss: 2.9077
Iteration: 2509; Percent complete: 62.7%; Average loss: 2.7452
Iteration: 2510; Percent complete: 62.7%; Average loss: 3.0782
Iteration: 2511; Percent complete: 62.8%; Average loss: 3.0708
Iteration: 2512; Percent complete: 62.8%; Average loss: 3.0729
Iteration: 2513; Percent complete: 62.8%; Average loss: 2.7645
Iteration: 2514; Percent complete: 62.8%; Average loss: 3.1400
Iteration: 2515; Percent complete: 62.9%; Average loss: 3.0920
Iteration: 2516; Percent complete: 62.9%; Average loss: 3.1327
Iteration: 2517; Percent complete: 62.9%; Average loss: 2.9622
Iteration: 2518; Percent complete: 62.9%; Average loss: 3.0865
Iteration: 2519; Percent complete: 63.0%; Average loss: 2.7654
Iteration: 2520; Percent complete: 63.0%; Average loss: 3.1237
Iteration: 2521; Percent complete: 63.0%; Average loss: 3.5286
Iteration: 2522; Percent complete: 63.0%; Average loss: 2.8947
Iteration: 2523; Percent complete: 63.1%; Average loss: 3.1222
Iteration: 2524; Percent complete: 63.1%; Average loss: 3.0845
Iteration: 2525; Percent complete: 63.1%; Average loss: 3.0248
Iteration: 2526; Percent complete: 63.1%; Average loss: 3.0662
Iteration: 2527; Percent complete: 63.2%; Average loss: 2.7586
Iteration: 2528; Percent complete: 63.2%; Average loss: 2.8579
Iteration: 2529; Percent complete: 63.2%; Average loss: 3.1032
Iteration: 2530; Percent complete: 63.2%; Average loss: 2.9265
Iteration: 2531; Percent complete: 63.3%; Average loss: 3.1859
Iteration: 2532; Percent complete: 63.3%; Average loss: 2.6980
Iteration: 2533; Percent complete: 63.3%; Average loss: 3.2416
Iteration: 2534; Percent complete: 63.3%; Average loss: 2.7081
Iteration: 2535; Percent complete: 63.4%; Average loss: 2.9933
Iteration: 2536; Percent complete: 63.4%; Average loss: 3.2147
Iteration: 2537; Percent complete: 63.4%; Average loss: 2.9764
Iteration: 2538; Percent complete: 63.4%; Average loss: 2.8565
Iteration: 2539; Percent complete: 63.5%; Average loss: 2.9412
Iteration: 2540; Percent complete: 63.5%; Average loss: 2.9817
Iteration: 2541; Percent complete: 63.5%; Average loss: 2.7875
Iteration: 2542; Percent complete: 63.5%; Average loss: 3.0887
Iteration: 2543; Percent complete: 63.6%; Average loss: 3.1188
Iteration: 2544; Percent complete: 63.6%; Average loss: 2.7172
Iteration: 2545; Percent complete: 63.6%; Average loss: 2.9966
Iteration: 2546; Percent complete: 63.6%; Average loss: 2.9932
Iteration: 2547; Percent complete: 63.7%; Average loss: 2.8102
Iteration: 2548; Percent complete: 63.7%; Average loss: 3.1880
Iteration: 2549; Percent complete: 63.7%; Average loss: 2.9817
Iteration: 2550; Percent complete: 63.7%; Average loss: 2.9050
Iteration: 2551; Percent complete: 63.8%; Average loss: 2.8727
Iteration: 2552; Percent complete: 63.8%; Average loss: 3.0780
Iteration: 2553; Percent complete: 63.8%; Average loss: 3.0755
Iteration: 2554; Percent complete: 63.8%; Average loss: 3.1382
Iteration: 2555; Percent complete: 63.9%; Average loss: 2.9382
Iteration: 2556; Percent complete: 63.9%; Average loss: 3.0722
Iteration: 2557; Percent complete: 63.9%; Average loss: 2.8828
Iteration: 2558; Percent complete: 63.9%; Average loss: 3.0761
Iteration: 2559; Percent complete: 64.0%; Average loss: 2.8257
Iteration: 2560; Percent complete: 64.0%; Average loss: 2.9416
Iteration: 2561; Percent complete: 64.0%; Average loss: 2.8609
Iteration: 2562; Percent complete: 64.0%; Average loss: 2.9512
Iteration: 2563; Percent complete: 64.1%; Average loss: 2.9373
Iteration: 2564; Percent complete: 64.1%; Average loss: 2.8936
Iteration: 2565; Percent complete: 64.1%; Average loss: 2.8758
Iteration: 2566; Percent complete: 64.1%; Average loss: 2.8234
Iteration: 2567; Percent complete: 64.2%; Average loss: 3.1803
Iteration: 2568; Percent complete: 64.2%; Average loss: 2.7758
Iteration: 2569; Percent complete: 64.2%; Average loss: 2.9814
Iteration: 2570; Percent complete: 64.2%; Average loss: 3.0229
Iteration: 2571; Percent complete: 64.3%; Average loss: 2.8329
Iteration: 2572; Percent complete: 64.3%; Average loss: 3.0024
Iteration: 2573; Percent complete: 64.3%; Average loss: 2.7964
Iteration: 2574; Percent complete: 64.3%; Average loss: 2.7860
Iteration: 2575; Percent complete: 64.4%; Average loss: 2.9712
Iteration: 2576; Percent complete: 64.4%; Average loss: 3.3941
Iteration: 2577; Percent complete: 64.4%; Average loss: 2.8964
Iteration: 2578; Percent complete: 64.5%; Average loss: 2.8683
Iteration: 2579; Percent complete: 64.5%; Average loss: 2.9017
Iteration: 2580; Percent complete: 64.5%; Average loss: 2.9019
Iteration: 2581; Percent complete: 64.5%; Average loss: 3.0311
Iteration: 2582; Percent complete: 64.5%; Average loss: 2.8544
Iteration: 2583; Percent complete: 64.6%; Average loss: 2.9710
Iteration: 2584; Percent complete: 64.6%; Average loss: 3.0743
Iteration: 2585; Percent complete: 64.6%; Average loss: 3.1647
Iteration: 2586; Percent complete: 64.6%; Average loss: 3.1711
Iteration: 2587; Percent complete: 64.7%; Average loss: 3.0447
Iteration: 2588; Percent complete: 64.7%; Average loss: 2.9196
Iteration: 2589; Percent complete: 64.7%; Average loss: 2.9562
Iteration: 2590; Percent complete: 64.8%; Average loss: 2.8786
Iteration: 2591; Percent complete: 64.8%; Average loss: 2.7809
Iteration: 2592; Percent complete: 64.8%; Average loss: 2.9117
Iteration: 2593; Percent complete: 64.8%; Average loss: 3.1481
Iteration: 2594; Percent complete: 64.8%; Average loss: 3.0135
Iteration: 2595; Percent complete: 64.9%; Average loss: 3.0051
Iteration: 2596; Percent complete: 64.9%; Average loss: 2.7462
Iteration: 2597; Percent complete: 64.9%; Average loss: 2.8476
Iteration: 2598; Percent complete: 65.0%; Average loss: 3.1186
Iteration: 2599; Percent complete: 65.0%; Average loss: 2.9688
Iteration: 2600; Percent complete: 65.0%; Average loss: 3.1120
Iteration: 2601; Percent complete: 65.0%; Average loss: 2.9193
Iteration: 2602; Percent complete: 65.0%; Average loss: 2.9242
Iteration: 2603; Percent complete: 65.1%; Average loss: 3.0100
Iteration: 2604; Percent complete: 65.1%; Average loss: 2.7821
Iteration: 2605; Percent complete: 65.1%; Average loss: 3.1127
Iteration: 2606; Percent complete: 65.1%; Average loss: 2.7925
Iteration: 2607; Percent complete: 65.2%; Average loss: 2.9649
Iteration: 2608; Percent complete: 65.2%; Average loss: 3.0471
Iteration: 2609; Percent complete: 65.2%; Average loss: 2.8493
Iteration: 2610; Percent complete: 65.2%; Average loss: 2.9860
Iteration: 2611; Percent complete: 65.3%; Average loss: 2.9163
Iteration: 2612; Percent complete: 65.3%; Average loss: 3.0729
Iteration: 2613; Percent complete: 65.3%; Average loss: 2.8687
Iteration: 2614; Percent complete: 65.3%; Average loss: 2.8445
Iteration: 2615; Percent complete: 65.4%; Average loss: 3.0537
Iteration: 2616; Percent complete: 65.4%; Average loss: 3.0785
Iteration: 2617; Percent complete: 65.4%; Average loss: 2.9158
Iteration: 2618; Percent complete: 65.5%; Average loss: 2.9617
Iteration: 2619; Percent complete: 65.5%; Average loss: 3.1121
Iteration: 2620; Percent complete: 65.5%; Average loss: 3.0930
Iteration: 2621; Percent complete: 65.5%; Average loss: 2.9414
Iteration: 2622; Percent complete: 65.5%; Average loss: 3.0939
Iteration: 2623; Percent complete: 65.6%; Average loss: 2.8168
Iteration: 2624; Percent complete: 65.6%; Average loss: 2.9047
Iteration: 2625; Percent complete: 65.6%; Average loss: 3.0462
Iteration: 2626; Percent complete: 65.6%; Average loss: 2.6562
Iteration: 2627; Percent complete: 65.7%; Average loss: 3.3668
Iteration: 2628; Percent complete: 65.7%; Average loss: 2.9033
Iteration: 2629; Percent complete: 65.7%; Average loss: 3.0840
Iteration: 2630; Percent complete: 65.8%; Average loss: 2.9416
Iteration: 2631; Percent complete: 65.8%; Average loss: 3.0944
Iteration: 2632; Percent complete: 65.8%; Average loss: 3.2970
Iteration: 2633; Percent complete: 65.8%; Average loss: 3.0960
Iteration: 2634; Percent complete: 65.8%; Average loss: 2.9804
Iteration: 2635; Percent complete: 65.9%; Average loss: 3.1809
Iteration: 2636; Percent complete: 65.9%; Average loss: 2.9816
Iteration: 2637; Percent complete: 65.9%; Average loss: 2.8232
Iteration: 2638; Percent complete: 66.0%; Average loss: 2.9402
Iteration: 2639; Percent complete: 66.0%; Average loss: 2.7477
Iteration: 2640; Percent complete: 66.0%; Average loss: 3.3133
Iteration: 2641; Percent complete: 66.0%; Average loss: 2.8625
Iteration: 2642; Percent complete: 66.0%; Average loss: 3.0539
Iteration: 2643; Percent complete: 66.1%; Average loss: 3.1937
Iteration: 2644; Percent complete: 66.1%; Average loss: 2.9656
Iteration: 2645; Percent complete: 66.1%; Average loss: 2.8871
Iteration: 2646; Percent complete: 66.1%; Average loss: 2.9426
Iteration: 2647; Percent complete: 66.2%; Average loss: 2.9085
Iteration: 2648; Percent complete: 66.2%; Average loss: 3.1038
Iteration: 2649; Percent complete: 66.2%; Average loss: 2.6853
Iteration: 2650; Percent complete: 66.2%; Average loss: 2.9365
Iteration: 2651; Percent complete: 66.3%; Average loss: 2.7479
Iteration: 2652; Percent complete: 66.3%; Average loss: 3.1054
Iteration: 2653; Percent complete: 66.3%; Average loss: 2.7868
Iteration: 2654; Percent complete: 66.3%; Average loss: 2.9324
Iteration: 2655; Percent complete: 66.4%; Average loss: 2.9199
Iteration: 2656; Percent complete: 66.4%; Average loss: 3.0769
Iteration: 2657; Percent complete: 66.4%; Average loss: 3.1359
Iteration: 2658; Percent complete: 66.5%; Average loss: 3.2105
Iteration: 2659; Percent complete: 66.5%; Average loss: 2.9905
Iteration: 2660; Percent complete: 66.5%; Average loss: 2.9795
Iteration: 2661; Percent complete: 66.5%; Average loss: 3.1011
Iteration: 2662; Percent complete: 66.5%; Average loss: 3.0042
Iteration: 2663; Percent complete: 66.6%; Average loss: 3.0021
Iteration: 2664; Percent complete: 66.6%; Average loss: 2.7995
Iteration: 2665; Percent complete: 66.6%; Average loss: 2.9679
Iteration: 2666; Percent complete: 66.6%; Average loss: 3.1795
Iteration: 2667; Percent complete: 66.7%; Average loss: 3.0431
Iteration: 2668; Percent complete: 66.7%; Average loss: 3.1600
Iteration: 2669; Percent complete: 66.7%; Average loss: 2.9618
Iteration: 2670; Percent complete: 66.8%; Average loss: 2.9966
Iteration: 2671; Percent complete: 66.8%; Average loss: 3.1632
Iteration: 2672; Percent complete: 66.8%; Average loss: 2.7569
Iteration: 2673; Percent complete: 66.8%; Average loss: 3.0156
Iteration: 2674; Percent complete: 66.8%; Average loss: 3.0048
Iteration: 2675; Percent complete: 66.9%; Average loss: 3.1438
Iteration: 2676; Percent complete: 66.9%; Average loss: 2.9328
Iteration: 2677; Percent complete: 66.9%; Average loss: 2.7986
Iteration: 2678; Percent complete: 67.0%; Average loss: 2.8806
Iteration: 2679; Percent complete: 67.0%; Average loss: 2.8529
Iteration: 2680; Percent complete: 67.0%; Average loss: 3.0817
Iteration: 2681; Percent complete: 67.0%; Average loss: 2.9472
Iteration: 2682; Percent complete: 67.0%; Average loss: 3.1008
Iteration: 2683; Percent complete: 67.1%; Average loss: 3.0752
Iteration: 2684; Percent complete: 67.1%; Average loss: 2.8492
Iteration: 2685; Percent complete: 67.1%; Average loss: 3.1171
Iteration: 2686; Percent complete: 67.2%; Average loss: 3.1525
Iteration: 2687; Percent complete: 67.2%; Average loss: 3.0192
Iteration: 2688; Percent complete: 67.2%; Average loss: 3.0422
Iteration: 2689; Percent complete: 67.2%; Average loss: 3.0127
Iteration: 2690; Percent complete: 67.2%; Average loss: 2.8239
Iteration: 2691; Percent complete: 67.3%; Average loss: 2.9442
Iteration: 2692; Percent complete: 67.3%; Average loss: 3.0033
Iteration: 2693; Percent complete: 67.3%; Average loss: 3.0745
Iteration: 2694; Percent complete: 67.3%; Average loss: 2.7302
Iteration: 2695; Percent complete: 67.4%; Average loss: 2.5993
Iteration: 2696; Percent complete: 67.4%; Average loss: 3.0402
Iteration: 2697; Percent complete: 67.4%; Average loss: 2.9783
Iteration: 2698; Percent complete: 67.5%; Average loss: 2.9640
Iteration: 2699; Percent complete: 67.5%; Average loss: 2.8231
Iteration: 2700; Percent complete: 67.5%; Average loss: 2.7472
Iteration: 2701; Percent complete: 67.5%; Average loss: 2.8270
Iteration: 2702; Percent complete: 67.5%; Average loss: 3.0380
Iteration: 2703; Percent complete: 67.6%; Average loss: 2.8762
Iteration: 2704; Percent complete: 67.6%; Average loss: 2.7284
Iteration: 2705; Percent complete: 67.6%; Average loss: 2.7389
Iteration: 2706; Percent complete: 67.7%; Average loss: 2.8906
Iteration: 2707; Percent complete: 67.7%; Average loss: 3.0958
Iteration: 2708; Percent complete: 67.7%; Average loss: 2.8918
Iteration: 2709; Percent complete: 67.7%; Average loss: 3.0970
Iteration: 2710; Percent complete: 67.8%; Average loss: 3.3643
Iteration: 2711; Percent complete: 67.8%; Average loss: 3.0380
Iteration: 2712; Percent complete: 67.8%; Average loss: 2.9761
Iteration: 2713; Percent complete: 67.8%; Average loss: 2.9249
Iteration: 2714; Percent complete: 67.8%; Average loss: 2.7980
Iteration: 2715; Percent complete: 67.9%; Average loss: 2.8472
Iteration: 2716; Percent complete: 67.9%; Average loss: 2.9752
Iteration: 2717; Percent complete: 67.9%; Average loss: 2.8949
Iteration: 2718; Percent complete: 68.0%; Average loss: 3.0266
Iteration: 2719; Percent complete: 68.0%; Average loss: 3.0382
Iteration: 2720; Percent complete: 68.0%; Average loss: 2.8912
Iteration: 2721; Percent complete: 68.0%; Average loss: 2.8622
Iteration: 2722; Percent complete: 68.0%; Average loss: 2.7644
Iteration: 2723; Percent complete: 68.1%; Average loss: 3.0418
Iteration: 2724; Percent complete: 68.1%; Average loss: 3.2735
Iteration: 2725; Percent complete: 68.1%; Average loss: 3.1534
Iteration: 2726; Percent complete: 68.2%; Average loss: 3.0718
Iteration: 2727; Percent complete: 68.2%; Average loss: 3.1144
Iteration: 2728; Percent complete: 68.2%; Average loss: 3.0329
Iteration: 2729; Percent complete: 68.2%; Average loss: 2.8895
Iteration: 2730; Percent complete: 68.2%; Average loss: 2.9182
Iteration: 2731; Percent complete: 68.3%; Average loss: 2.8491
Iteration: 2732; Percent complete: 68.3%; Average loss: 2.8031
Iteration: 2733; Percent complete: 68.3%; Average loss: 3.2134
Iteration: 2734; Percent complete: 68.3%; Average loss: 2.7587
Iteration: 2735; Percent complete: 68.4%; Average loss: 2.9970
Iteration: 2736; Percent complete: 68.4%; Average loss: 2.9677
Iteration: 2737; Percent complete: 68.4%; Average loss: 2.8827
Iteration: 2738; Percent complete: 68.5%; Average loss: 2.9391
Iteration: 2739; Percent complete: 68.5%; Average loss: 2.9512
Iteration: 2740; Percent complete: 68.5%; Average loss: 2.9054
Iteration: 2741; Percent complete: 68.5%; Average loss: 3.0123
Iteration: 2742; Percent complete: 68.5%; Average loss: 2.9714
Iteration: 2743; Percent complete: 68.6%; Average loss: 2.8163
Iteration: 2744; Percent complete: 68.6%; Average loss: 2.9975
Iteration: 2745; Percent complete: 68.6%; Average loss: 2.8484
Iteration: 2746; Percent complete: 68.7%; Average loss: 2.9039
Iteration: 2747; Percent complete: 68.7%; Average loss: 2.8442
Iteration: 2748; Percent complete: 68.7%; Average loss: 3.1301
Iteration: 2749; Percent complete: 68.7%; Average loss: 2.9369
Iteration: 2750; Percent complete: 68.8%; Average loss: 2.8231
Iteration: 2751; Percent complete: 68.8%; Average loss: 2.7714
Iteration: 2752; Percent complete: 68.8%; Average loss: 2.9736
Iteration: 2753; Percent complete: 68.8%; Average loss: 3.0964
Iteration: 2754; Percent complete: 68.8%; Average loss: 2.7044
Iteration: 2755; Percent complete: 68.9%; Average loss: 3.1442
Iteration: 2756; Percent complete: 68.9%; Average loss: 2.7361
Iteration: 2757; Percent complete: 68.9%; Average loss: 3.0283
Iteration: 2758; Percent complete: 69.0%; Average loss: 3.1732
Iteration: 2759; Percent complete: 69.0%; Average loss: 2.9654
Iteration: 2760; Percent complete: 69.0%; Average loss: 2.9369
Iteration: 2761; Percent complete: 69.0%; Average loss: 2.9389
Iteration: 2762; Percent complete: 69.0%; Average loss: 2.9793
Iteration: 2763; Percent complete: 69.1%; Average loss: 2.8259
Iteration: 2764; Percent complete: 69.1%; Average loss: 2.8507
Iteration: 2765; Percent complete: 69.1%; Average loss: 2.7174
Iteration: 2766; Percent complete: 69.2%; Average loss: 2.8009
Iteration: 2767; Percent complete: 69.2%; Average loss: 3.1146
Iteration: 2768; Percent complete: 69.2%; Average loss: 2.9615
Iteration: 2769; Percent complete: 69.2%; Average loss: 2.8969
Iteration: 2770; Percent complete: 69.2%; Average loss: 3.0287
Iteration: 2771; Percent complete: 69.3%; Average loss: 3.1968
Iteration: 2772; Percent complete: 69.3%; Average loss: 2.8953
Iteration: 2773; Percent complete: 69.3%; Average loss: 3.1711
Iteration: 2774; Percent complete: 69.3%; Average loss: 2.9167
Iteration: 2775; Percent complete: 69.4%; Average loss: 3.1445
Iteration: 2776; Percent complete: 69.4%; Average loss: 2.9364
Iteration: 2777; Percent complete: 69.4%; Average loss: 3.0063
Iteration: 2778; Percent complete: 69.5%; Average loss: 2.9451
Iteration: 2779; Percent complete: 69.5%; Average loss: 2.8330
Iteration: 2780; Percent complete: 69.5%; Average loss: 2.9532
Iteration: 2781; Percent complete: 69.5%; Average loss: 2.8425
Iteration: 2782; Percent complete: 69.5%; Average loss: 2.9329
Iteration: 2783; Percent complete: 69.6%; Average loss: 2.8254
Iteration: 2784; Percent complete: 69.6%; Average loss: 2.8339
Iteration: 2785; Percent complete: 69.6%; Average loss: 3.2010
Iteration: 2786; Percent complete: 69.7%; Average loss: 3.0451
Iteration: 2787; Percent complete: 69.7%; Average loss: 3.0059
Iteration: 2788; Percent complete: 69.7%; Average loss: 3.0095
Iteration: 2789; Percent complete: 69.7%; Average loss: 2.9883
Iteration: 2790; Percent complete: 69.8%; Average loss: 3.1494
Iteration: 2791; Percent complete: 69.8%; Average loss: 2.8504
Iteration: 2792; Percent complete: 69.8%; Average loss: 3.0644
Iteration: 2793; Percent complete: 69.8%; Average loss: 2.9742
Iteration: 2794; Percent complete: 69.8%; Average loss: 2.9775
Iteration: 2795; Percent complete: 69.9%; Average loss: 2.9919
Iteration: 2796; Percent complete: 69.9%; Average loss: 2.9564
Iteration: 2797; Percent complete: 69.9%; Average loss: 3.0261
Iteration: 2798; Percent complete: 70.0%; Average loss: 2.9046
Iteration: 2799; Percent complete: 70.0%; Average loss: 3.1015
Iteration: 2800; Percent complete: 70.0%; Average loss: 3.0768
Iteration: 2801; Percent complete: 70.0%; Average loss: 2.8206
Iteration: 2802; Percent complete: 70.0%; Average loss: 2.8677
Iteration: 2803; Percent complete: 70.1%; Average loss: 2.7339
Iteration: 2804; Percent complete: 70.1%; Average loss: 3.0897
Iteration: 2805; Percent complete: 70.1%; Average loss: 2.9402
Iteration: 2806; Percent complete: 70.2%; Average loss: 2.9693
Iteration: 2807; Percent complete: 70.2%; Average loss: 2.9627
Iteration: 2808; Percent complete: 70.2%; Average loss: 2.9832
Iteration: 2809; Percent complete: 70.2%; Average loss: 2.9448
Iteration: 2810; Percent complete: 70.2%; Average loss: 2.7023
Iteration: 2811; Percent complete: 70.3%; Average loss: 2.9223
Iteration: 2812; Percent complete: 70.3%; Average loss: 3.1415
Iteration: 2813; Percent complete: 70.3%; Average loss: 3.1201
Iteration: 2814; Percent complete: 70.3%; Average loss: 2.8994
Iteration: 2815; Percent complete: 70.4%; Average loss: 2.8783
Iteration: 2816; Percent complete: 70.4%; Average loss: 3.0878
Iteration: 2817; Percent complete: 70.4%; Average loss: 2.9166
Iteration: 2818; Percent complete: 70.5%; Average loss: 2.9211
Iteration: 2819; Percent complete: 70.5%; Average loss: 2.9191
Iteration: 2820; Percent complete: 70.5%; Average loss: 2.9293
Iteration: 2821; Percent complete: 70.5%; Average loss: 2.9105
Iteration: 2822; Percent complete: 70.5%; Average loss: 2.7359
Iteration: 2823; Percent complete: 70.6%; Average loss: 2.9971
Iteration: 2824; Percent complete: 70.6%; Average loss: 2.9425
Iteration: 2825; Percent complete: 70.6%; Average loss: 2.7322
Iteration: 2826; Percent complete: 70.7%; Average loss: 2.7787
Iteration: 2827; Percent complete: 70.7%; Average loss: 2.7718
Iteration: 2828; Percent complete: 70.7%; Average loss: 3.1033
Iteration: 2829; Percent complete: 70.7%; Average loss: 3.0359
Iteration: 2830; Percent complete: 70.8%; Average loss: 2.9961
Iteration: 2831; Percent complete: 70.8%; Average loss: 2.8202
Iteration: 2832; Percent complete: 70.8%; Average loss: 2.9837
Iteration: 2833; Percent complete: 70.8%; Average loss: 2.6535
Iteration: 2834; Percent complete: 70.9%; Average loss: 2.8324
Iteration: 2835; Percent complete: 70.9%; Average loss: 2.8582
Iteration: 2836; Percent complete: 70.9%; Average loss: 2.9552
Iteration: 2837; Percent complete: 70.9%; Average loss: 3.0509
Iteration: 2838; Percent complete: 71.0%; Average loss: 2.8955
Iteration: 2839; Percent complete: 71.0%; Average loss: 2.8223
Iteration: 2840; Percent complete: 71.0%; Average loss: 3.1087
Iteration: 2841; Percent complete: 71.0%; Average loss: 2.8232
Iteration: 2842; Percent complete: 71.0%; Average loss: 2.7902
Iteration: 2843; Percent complete: 71.1%; Average loss: 2.7335
Iteration: 2844; Percent complete: 71.1%; Average loss: 3.0899
Iteration: 2845; Percent complete: 71.1%; Average loss: 3.1988
Iteration: 2846; Percent complete: 71.2%; Average loss: 2.8715
Iteration: 2847; Percent complete: 71.2%; Average loss: 2.9427
Iteration: 2848; Percent complete: 71.2%; Average loss: 2.6844
Iteration: 2849; Percent complete: 71.2%; Average loss: 3.0219
Iteration: 2850; Percent complete: 71.2%; Average loss: 2.8173
Iteration: 2851; Percent complete: 71.3%; Average loss: 2.8035
Iteration: 2852; Percent complete: 71.3%; Average loss: 2.8384
Iteration: 2853; Percent complete: 71.3%; Average loss: 2.9238
Iteration: 2854; Percent complete: 71.4%; Average loss: 3.2486
Iteration: 2855; Percent complete: 71.4%; Average loss: 2.6359
Iteration: 2856; Percent complete: 71.4%; Average loss: 3.1458
Iteration: 2857; Percent complete: 71.4%; Average loss: 2.9568
Iteration: 2858; Percent complete: 71.5%; Average loss: 2.8495
Iteration: 2859; Percent complete: 71.5%; Average loss: 2.8385
Iteration: 2860; Percent complete: 71.5%; Average loss: 2.9420
Iteration: 2861; Percent complete: 71.5%; Average loss: 2.7527
Iteration: 2862; Percent complete: 71.5%; Average loss: 2.8608
Iteration: 2863; Percent complete: 71.6%; Average loss: 3.0607
Iteration: 2864; Percent complete: 71.6%; Average loss: 2.9887
Iteration: 2865; Percent complete: 71.6%; Average loss: 2.8010
Iteration: 2866; Percent complete: 71.7%; Average loss: 2.8562
Iteration: 2867; Percent complete: 71.7%; Average loss: 3.0340
Iteration: 2868; Percent complete: 71.7%; Average loss: 2.9920
Iteration: 2869; Percent complete: 71.7%; Average loss: 2.9768
Iteration: 2870; Percent complete: 71.8%; Average loss: 2.6479
Iteration: 2871; Percent complete: 71.8%; Average loss: 3.2894
Iteration: 2872; Percent complete: 71.8%; Average loss: 2.8302
Iteration: 2873; Percent complete: 71.8%; Average loss: 2.6893
Iteration: 2874; Percent complete: 71.9%; Average loss: 2.7631
Iteration: 2875; Percent complete: 71.9%; Average loss: 3.1190
Iteration: 2876; Percent complete: 71.9%; Average loss: 2.9034
Iteration: 2877; Percent complete: 71.9%; Average loss: 3.0729
Iteration: 2878; Percent complete: 72.0%; Average loss: 2.9492
Iteration: 2879; Percent complete: 72.0%; Average loss: 3.1265
Iteration: 2880; Percent complete: 72.0%; Average loss: 2.7098
Iteration: 2881; Percent complete: 72.0%; Average loss: 2.8763
Iteration: 2882; Percent complete: 72.0%; Average loss: 3.2258
Iteration: 2883; Percent complete: 72.1%; Average loss: 3.0677
Iteration: 2884; Percent complete: 72.1%; Average loss: 3.0563
Iteration: 2885; Percent complete: 72.1%; Average loss: 2.8981
Iteration: 2886; Percent complete: 72.2%; Average loss: 2.9236
Iteration: 2887; Percent complete: 72.2%; Average loss: 3.1113
Iteration: 2888; Percent complete: 72.2%; Average loss: 2.8047
Iteration: 2889; Percent complete: 72.2%; Average loss: 2.6573
Iteration: 2890; Percent complete: 72.2%; Average loss: 2.8640
Iteration: 2891; Percent complete: 72.3%; Average loss: 2.7356
Iteration: 2892; Percent complete: 72.3%; Average loss: 2.8947
Iteration: 2893; Percent complete: 72.3%; Average loss: 2.9475
Iteration: 2894; Percent complete: 72.4%; Average loss: 2.7810
Iteration: 2895; Percent complete: 72.4%; Average loss: 2.8197
Iteration: 2896; Percent complete: 72.4%; Average loss: 2.9267
Iteration: 2897; Percent complete: 72.4%; Average loss: 2.9897
Iteration: 2898; Percent complete: 72.5%; Average loss: 2.7607
Iteration: 2899; Percent complete: 72.5%; Average loss: 3.1689
Iteration: 2900; Percent complete: 72.5%; Average loss: 2.8933
Iteration: 2901; Percent complete: 72.5%; Average loss: 2.8443
Iteration: 2902; Percent complete: 72.5%; Average loss: 2.9109
Iteration: 2903; Percent complete: 72.6%; Average loss: 2.8230
Iteration: 2904; Percent complete: 72.6%; Average loss: 2.9019
Iteration: 2905; Percent complete: 72.6%; Average loss: 2.7374
Iteration: 2906; Percent complete: 72.7%; Average loss: 2.6625
Iteration: 2907; Percent complete: 72.7%; Average loss: 2.8279
Iteration: 2908; Percent complete: 72.7%; Average loss: 2.9893
Iteration: 2909; Percent complete: 72.7%; Average loss: 3.1092
Iteration: 2910; Percent complete: 72.8%; Average loss: 3.0339
Iteration: 2911; Percent complete: 72.8%; Average loss: 2.9496
Iteration: 2912; Percent complete: 72.8%; Average loss: 2.9910
Iteration: 2913; Percent complete: 72.8%; Average loss: 3.1144
Iteration: 2914; Percent complete: 72.9%; Average loss: 2.7099
Iteration: 2915; Percent complete: 72.9%; Average loss: 2.8321
Iteration: 2916; Percent complete: 72.9%; Average loss: 2.8489
Iteration: 2917; Percent complete: 72.9%; Average loss: 3.1067
Iteration: 2918; Percent complete: 73.0%; Average loss: 3.0124
Iteration: 2919; Percent complete: 73.0%; Average loss: 2.9246
Iteration: 2920; Percent complete: 73.0%; Average loss: 3.0800
Iteration: 2921; Percent complete: 73.0%; Average loss: 2.8941
Iteration: 2922; Percent complete: 73.0%; Average loss: 2.8555
Iteration: 2923; Percent complete: 73.1%; Average loss: 2.9342
Iteration: 2924; Percent complete: 73.1%; Average loss: 2.8419
Iteration: 2925; Percent complete: 73.1%; Average loss: 2.8568
Iteration: 2926; Percent complete: 73.2%; Average loss: 2.6802
Iteration: 2927; Percent complete: 73.2%; Average loss: 2.9343
Iteration: 2928; Percent complete: 73.2%; Average loss: 2.8320
Iteration: 2929; Percent complete: 73.2%; Average loss: 2.6058
Iteration: 2930; Percent complete: 73.2%; Average loss: 3.0177
Iteration: 2931; Percent complete: 73.3%; Average loss: 2.7788
Iteration: 2932; Percent complete: 73.3%; Average loss: 2.9032
Iteration: 2933; Percent complete: 73.3%; Average loss: 2.8477
Iteration: 2934; Percent complete: 73.4%; Average loss: 2.7491
Iteration: 2935; Percent complete: 73.4%; Average loss: 3.0103
Iteration: 2936; Percent complete: 73.4%; Average loss: 2.9764
Iteration: 2937; Percent complete: 73.4%; Average loss: 2.6959
Iteration: 2938; Percent complete: 73.5%; Average loss: 2.8097
Iteration: 2939; Percent complete: 73.5%; Average loss: 2.8815
Iteration: 2940; Percent complete: 73.5%; Average loss: 2.8826
Iteration: 2941; Percent complete: 73.5%; Average loss: 2.9982
Iteration: 2942; Percent complete: 73.6%; Average loss: 3.0386
Iteration: 2943; Percent complete: 73.6%; Average loss: 2.7343
Iteration: 2944; Percent complete: 73.6%; Average loss: 3.0957
Iteration: 2945; Percent complete: 73.6%; Average loss: 2.9752
Iteration: 2946; Percent complete: 73.7%; Average loss: 2.9040
Iteration: 2947; Percent complete: 73.7%; Average loss: 2.6276
Iteration: 2948; Percent complete: 73.7%; Average loss: 2.9456
Iteration: 2949; Percent complete: 73.7%; Average loss: 3.2412
Iteration: 2950; Percent complete: 73.8%; Average loss: 2.9467
Iteration: 2951; Percent complete: 73.8%; Average loss: 3.3124
Iteration: 2952; Percent complete: 73.8%; Average loss: 2.9829
Iteration: 2953; Percent complete: 73.8%; Average loss: 2.8319
Iteration: 2954; Percent complete: 73.9%; Average loss: 2.9243
Iteration: 2955; Percent complete: 73.9%; Average loss: 2.8046
Iteration: 2956; Percent complete: 73.9%; Average loss: 2.6140
Iteration: 2957; Percent complete: 73.9%; Average loss: 2.7964
Iteration: 2958; Percent complete: 74.0%; Average loss: 2.8288
Iteration: 2959; Percent complete: 74.0%; Average loss: 2.5227
Iteration: 2960; Percent complete: 74.0%; Average loss: 3.0393
Iteration: 2961; Percent complete: 74.0%; Average loss: 2.8242
Iteration: 2962; Percent complete: 74.1%; Average loss: 2.7618
Iteration: 2963; Percent complete: 74.1%; Average loss: 2.7878
Iteration: 2964; Percent complete: 74.1%; Average loss: 3.1090
Iteration: 2965; Percent complete: 74.1%; Average loss: 2.9940
Iteration: 2966; Percent complete: 74.2%; Average loss: 2.8308
Iteration: 2967; Percent complete: 74.2%; Average loss: 2.8643
Iteration: 2968; Percent complete: 74.2%; Average loss: 2.8314
Iteration: 2969; Percent complete: 74.2%; Average loss: 2.8609
Iteration: 2970; Percent complete: 74.2%; Average loss: 2.8881
Iteration: 2971; Percent complete: 74.3%; Average loss: 2.9803
Iteration: 2972; Percent complete: 74.3%; Average loss: 2.8499
Iteration: 2973; Percent complete: 74.3%; Average loss: 2.7824
Iteration: 2974; Percent complete: 74.4%; Average loss: 2.8128
Iteration: 2975; Percent complete: 74.4%; Average loss: 2.7931
Iteration: 2976; Percent complete: 74.4%; Average loss: 2.8975
Iteration: 2977; Percent complete: 74.4%; Average loss: 2.9235
Iteration: 2978; Percent complete: 74.5%; Average loss: 2.6971
Iteration: 2979; Percent complete: 74.5%; Average loss: 2.8818
Iteration: 2980; Percent complete: 74.5%; Average loss: 3.0544
Iteration: 2981; Percent complete: 74.5%; Average loss: 2.9490
Iteration: 2982; Percent complete: 74.6%; Average loss: 2.8962
Iteration: 2983; Percent complete: 74.6%; Average loss: 2.9056
Iteration: 2984; Percent complete: 74.6%; Average loss: 2.7601
Iteration: 2985; Percent complete: 74.6%; Average loss: 2.9927
Iteration: 2986; Percent complete: 74.7%; Average loss: 3.1958
Iteration: 2987; Percent complete: 74.7%; Average loss: 2.7462
Iteration: 2988; Percent complete: 74.7%; Average loss: 2.5627
Iteration: 2989; Percent complete: 74.7%; Average loss: 2.9047
Iteration: 2990; Percent complete: 74.8%; Average loss: 2.8425
Iteration: 2991; Percent complete: 74.8%; Average loss: 2.8067
Iteration: 2992; Percent complete: 74.8%; Average loss: 2.7727
Iteration: 2993; Percent complete: 74.8%; Average loss: 2.8382
Iteration: 2994; Percent complete: 74.9%; Average loss: 2.8236
Iteration: 2995; Percent complete: 74.9%; Average loss: 2.9442
Iteration: 2996; Percent complete: 74.9%; Average loss: 2.7826
Iteration: 2997; Percent complete: 74.9%; Average loss: 2.8191
Iteration: 2998; Percent complete: 75.0%; Average loss: 2.7772
Iteration: 2999; Percent complete: 75.0%; Average loss: 2.9050
Iteration: 3000; Percent complete: 75.0%; Average loss: 3.0546
Iteration: 3001; Percent complete: 75.0%; Average loss: 2.8587
Iteration: 3002; Percent complete: 75.0%; Average loss: 2.9793
Iteration: 3003; Percent complete: 75.1%; Average loss: 3.0673
Iteration: 3004; Percent complete: 75.1%; Average loss: 2.8734
Iteration: 3005; Percent complete: 75.1%; Average loss: 2.6025
Iteration: 3006; Percent complete: 75.1%; Average loss: 2.7976
Iteration: 3007; Percent complete: 75.2%; Average loss: 2.9167
Iteration: 3008; Percent complete: 75.2%; Average loss: 2.7596
Iteration: 3009; Percent complete: 75.2%; Average loss: 2.9541
Iteration: 3010; Percent complete: 75.2%; Average loss: 2.6632
Iteration: 3011; Percent complete: 75.3%; Average loss: 2.4667
Iteration: 3012; Percent complete: 75.3%; Average loss: 2.8601
Iteration: 3013; Percent complete: 75.3%; Average loss: 2.5457
Iteration: 3014; Percent complete: 75.3%; Average loss: 2.7740
Iteration: 3015; Percent complete: 75.4%; Average loss: 3.0232
Iteration: 3016; Percent complete: 75.4%; Average loss: 2.7858
Iteration: 3017; Percent complete: 75.4%; Average loss: 2.9366
Iteration: 3018; Percent complete: 75.4%; Average loss: 2.6683
Iteration: 3019; Percent complete: 75.5%; Average loss: 2.9528
Iteration: 3020; Percent complete: 75.5%; Average loss: 2.9856
Iteration: 3021; Percent complete: 75.5%; Average loss: 2.6938
Iteration: 3022; Percent complete: 75.5%; Average loss: 2.9706
Iteration: 3023; Percent complete: 75.6%; Average loss: 2.7653
Iteration: 3024; Percent complete: 75.6%; Average loss: 2.8969
Iteration: 3025; Percent complete: 75.6%; Average loss: 2.7458
Iteration: 3026; Percent complete: 75.6%; Average loss: 2.8504
Iteration: 3027; Percent complete: 75.7%; Average loss: 2.6671
Iteration: 3028; Percent complete: 75.7%; Average loss: 2.8499
Iteration: 3029; Percent complete: 75.7%; Average loss: 2.8456
Iteration: 3030; Percent complete: 75.8%; Average loss: 3.0699
Iteration: 3031; Percent complete: 75.8%; Average loss: 2.7379
Iteration: 3032; Percent complete: 75.8%; Average loss: 2.8573
Iteration: 3033; Percent complete: 75.8%; Average loss: 2.8130
Iteration: 3034; Percent complete: 75.8%; Average loss: 2.9637
Iteration: 3035; Percent complete: 75.9%; Average loss: 2.6470
Iteration: 3036; Percent complete: 75.9%; Average loss: 2.9488
Iteration: 3037; Percent complete: 75.9%; Average loss: 2.6848
Iteration: 3038; Percent complete: 75.9%; Average loss: 2.9243
Iteration: 3039; Percent complete: 76.0%; Average loss: 2.8795
Iteration: 3040; Percent complete: 76.0%; Average loss: 2.7874
Iteration: 3041; Percent complete: 76.0%; Average loss: 2.8162
Iteration: 3042; Percent complete: 76.0%; Average loss: 2.8245
Iteration: 3043; Percent complete: 76.1%; Average loss: 2.9331
Iteration: 3044; Percent complete: 76.1%; Average loss: 2.7103
Iteration: 3045; Percent complete: 76.1%; Average loss: 2.9528
Iteration: 3046; Percent complete: 76.1%; Average loss: 2.8349
Iteration: 3047; Percent complete: 76.2%; Average loss: 2.8437
Iteration: 3048; Percent complete: 76.2%; Average loss: 2.9718
Iteration: 3049; Percent complete: 76.2%; Average loss: 2.9424
Iteration: 3050; Percent complete: 76.2%; Average loss: 2.7092
Iteration: 3051; Percent complete: 76.3%; Average loss: 2.8973
Iteration: 3052; Percent complete: 76.3%; Average loss: 2.9067
Iteration: 3053; Percent complete: 76.3%; Average loss: 2.6488
Iteration: 3054; Percent complete: 76.3%; Average loss: 2.7969
Iteration: 3055; Percent complete: 76.4%; Average loss: 2.8451
Iteration: 3056; Percent complete: 76.4%; Average loss: 2.9018
Iteration: 3057; Percent complete: 76.4%; Average loss: 2.9594
Iteration: 3058; Percent complete: 76.4%; Average loss: 2.9698
Iteration: 3059; Percent complete: 76.5%; Average loss: 3.0493
Iteration: 3060; Percent complete: 76.5%; Average loss: 2.9506
Iteration: 3061; Percent complete: 76.5%; Average loss: 2.9485
Iteration: 3062; Percent complete: 76.5%; Average loss: 2.7113
Iteration: 3063; Percent complete: 76.6%; Average loss: 2.9838
Iteration: 3064; Percent complete: 76.6%; Average loss: 2.7076
Iteration: 3065; Percent complete: 76.6%; Average loss: 2.9074
Iteration: 3066; Percent complete: 76.6%; Average loss: 2.9030
Iteration: 3067; Percent complete: 76.7%; Average loss: 2.8616
Iteration: 3068; Percent complete: 76.7%; Average loss: 2.7224
Iteration: 3069; Percent complete: 76.7%; Average loss: 3.1266
Iteration: 3070; Percent complete: 76.8%; Average loss: 3.0627
Iteration: 3071; Percent complete: 76.8%; Average loss: 3.0655
Iteration: 3072; Percent complete: 76.8%; Average loss: 2.7055
Iteration: 3073; Percent complete: 76.8%; Average loss: 3.0330
Iteration: 3074; Percent complete: 76.8%; Average loss: 3.2618
Iteration: 3075; Percent complete: 76.9%; Average loss: 3.0110
Iteration: 3076; Percent complete: 76.9%; Average loss: 2.8713
Iteration: 3077; Percent complete: 76.9%; Average loss: 2.7976
Iteration: 3078; Percent complete: 77.0%; Average loss: 2.9974
Iteration: 3079; Percent complete: 77.0%; Average loss: 3.1696
Iteration: 3080; Percent complete: 77.0%; Average loss: 3.0519
Iteration: 3081; Percent complete: 77.0%; Average loss: 2.6382
Iteration: 3082; Percent complete: 77.0%; Average loss: 3.0620
Iteration: 3083; Percent complete: 77.1%; Average loss: 2.7077
Iteration: 3084; Percent complete: 77.1%; Average loss: 2.9109
Iteration: 3085; Percent complete: 77.1%; Average loss: 2.8020
Iteration: 3086; Percent complete: 77.1%; Average loss: 2.7643
Iteration: 3087; Percent complete: 77.2%; Average loss: 3.0044
Iteration: 3088; Percent complete: 77.2%; Average loss: 2.9923
Iteration: 3089; Percent complete: 77.2%; Average loss: 2.9989
Iteration: 3090; Percent complete: 77.2%; Average loss: 2.8321
Iteration: 3091; Percent complete: 77.3%; Average loss: 2.6683
Iteration: 3092; Percent complete: 77.3%; Average loss: 2.7432
Iteration: 3093; Percent complete: 77.3%; Average loss: 2.7310
Iteration: 3094; Percent complete: 77.3%; Average loss: 2.8650
Iteration: 3095; Percent complete: 77.4%; Average loss: 2.8768
Iteration: 3096; Percent complete: 77.4%; Average loss: 2.7313
Iteration: 3097; Percent complete: 77.4%; Average loss: 3.0108
Iteration: 3098; Percent complete: 77.5%; Average loss: 2.6381
Iteration: 3099; Percent complete: 77.5%; Average loss: 2.7838
Iteration: 3100; Percent complete: 77.5%; Average loss: 2.7593
Iteration: 3101; Percent complete: 77.5%; Average loss: 2.7777
Iteration: 3102; Percent complete: 77.5%; Average loss: 2.7867
Iteration: 3103; Percent complete: 77.6%; Average loss: 2.9246
Iteration: 3104; Percent complete: 77.6%; Average loss: 2.8639
Iteration: 3105; Percent complete: 77.6%; Average loss: 2.6905
Iteration: 3106; Percent complete: 77.6%; Average loss: 2.8801
Iteration: 3107; Percent complete: 77.7%; Average loss: 3.1708
Iteration: 3108; Percent complete: 77.7%; Average loss: 2.9556
Iteration: 3109; Percent complete: 77.7%; Average loss: 2.8989
Iteration: 3110; Percent complete: 77.8%; Average loss: 2.9737
Iteration: 3111; Percent complete: 77.8%; Average loss: 2.5938
Iteration: 3112; Percent complete: 77.8%; Average loss: 2.7231
Iteration: 3113; Percent complete: 77.8%; Average loss: 2.7281
Iteration: 3114; Percent complete: 77.8%; Average loss: 2.8108
Iteration: 3115; Percent complete: 77.9%; Average loss: 2.9731
Iteration: 3116; Percent complete: 77.9%; Average loss: 2.9347
Iteration: 3117; Percent complete: 77.9%; Average loss: 2.9279
Iteration: 3118; Percent complete: 78.0%; Average loss: 2.7342
Iteration: 3119; Percent complete: 78.0%; Average loss: 2.8997
Iteration: 3120; Percent complete: 78.0%; Average loss: 2.9326
Iteration: 3121; Percent complete: 78.0%; Average loss: 2.8903
Iteration: 3122; Percent complete: 78.0%; Average loss: 2.7972
Iteration: 3123; Percent complete: 78.1%; Average loss: 2.8500
Iteration: 3124; Percent complete: 78.1%; Average loss: 2.9556
Iteration: 3125; Percent complete: 78.1%; Average loss: 2.8308
Iteration: 3126; Percent complete: 78.1%; Average loss: 2.7901
Iteration: 3127; Percent complete: 78.2%; Average loss: 2.8386
Iteration: 3128; Percent complete: 78.2%; Average loss: 2.9051
Iteration: 3129; Percent complete: 78.2%; Average loss: 3.0043
Iteration: 3130; Percent complete: 78.2%; Average loss: 2.6878
Iteration: 3131; Percent complete: 78.3%; Average loss: 3.3059
Iteration: 3132; Percent complete: 78.3%; Average loss: 2.7117
Iteration: 3133; Percent complete: 78.3%; Average loss: 2.9684
Iteration: 3134; Percent complete: 78.3%; Average loss: 2.8638
Iteration: 3135; Percent complete: 78.4%; Average loss: 2.9162
Iteration: 3136; Percent complete: 78.4%; Average loss: 2.9234
Iteration: 3137; Percent complete: 78.4%; Average loss: 3.1295
Iteration: 3138; Percent complete: 78.5%; Average loss: 2.9527
Iteration: 3139; Percent complete: 78.5%; Average loss: 2.8827
Iteration: 3140; Percent complete: 78.5%; Average loss: 2.6240
Iteration: 3141; Percent complete: 78.5%; Average loss: 2.8228
Iteration: 3142; Percent complete: 78.5%; Average loss: 2.8219
Iteration: 3143; Percent complete: 78.6%; Average loss: 2.9634
Iteration: 3144; Percent complete: 78.6%; Average loss: 2.9158
Iteration: 3145; Percent complete: 78.6%; Average loss: 2.8741
Iteration: 3146; Percent complete: 78.6%; Average loss: 2.7674
Iteration: 3147; Percent complete: 78.7%; Average loss: 2.9808
Iteration: 3148; Percent complete: 78.7%; Average loss: 2.7214
Iteration: 3149; Percent complete: 78.7%; Average loss: 2.8644
Iteration: 3150; Percent complete: 78.8%; Average loss: 2.8772
Iteration: 3151; Percent complete: 78.8%; Average loss: 2.7739
Iteration: 3152; Percent complete: 78.8%; Average loss: 2.9096
Iteration: 3153; Percent complete: 78.8%; Average loss: 2.8030
Iteration: 3154; Percent complete: 78.8%; Average loss: 2.9739
Iteration: 3155; Percent complete: 78.9%; Average loss: 2.8258
Iteration: 3156; Percent complete: 78.9%; Average loss: 2.6306
Iteration: 3157; Percent complete: 78.9%; Average loss: 2.7678
Iteration: 3158; Percent complete: 79.0%; Average loss: 3.1018
Iteration: 3159; Percent complete: 79.0%; Average loss: 3.1525
Iteration: 3160; Percent complete: 79.0%; Average loss: 2.9418
Iteration: 3161; Percent complete: 79.0%; Average loss: 2.8937
Iteration: 3162; Percent complete: 79.0%; Average loss: 2.6787
Iteration: 3163; Percent complete: 79.1%; Average loss: 2.6787
Iteration: 3164; Percent complete: 79.1%; Average loss: 2.7501
Iteration: 3165; Percent complete: 79.1%; Average loss: 2.7510
Iteration: 3166; Percent complete: 79.1%; Average loss: 2.6047
Iteration: 3167; Percent complete: 79.2%; Average loss: 2.8250
Iteration: 3168; Percent complete: 79.2%; Average loss: 2.5614
Iteration: 3169; Percent complete: 79.2%; Average loss: 2.7312
Iteration: 3170; Percent complete: 79.2%; Average loss: 2.9529
Iteration: 3171; Percent complete: 79.3%; Average loss: 2.6724
Iteration: 3172; Percent complete: 79.3%; Average loss: 2.8749
Iteration: 3173; Percent complete: 79.3%; Average loss: 2.8412
Iteration: 3174; Percent complete: 79.3%; Average loss: 2.5138
Iteration: 3175; Percent complete: 79.4%; Average loss: 2.8443
Iteration: 3176; Percent complete: 79.4%; Average loss: 2.6025
Iteration: 3177; Percent complete: 79.4%; Average loss: 2.8724
Iteration: 3178; Percent complete: 79.5%; Average loss: 2.6315
Iteration: 3179; Percent complete: 79.5%; Average loss: 2.8966
Iteration: 3180; Percent complete: 79.5%; Average loss: 2.8272
Iteration: 3181; Percent complete: 79.5%; Average loss: 2.6966
Iteration: 3182; Percent complete: 79.5%; Average loss: 2.8469
Iteration: 3183; Percent complete: 79.6%; Average loss: 2.8146
Iteration: 3184; Percent complete: 79.6%; Average loss: 3.0306
Iteration: 3185; Percent complete: 79.6%; Average loss: 2.7750
Iteration: 3186; Percent complete: 79.7%; Average loss: 2.7919
Iteration: 3187; Percent complete: 79.7%; Average loss: 2.9776
Iteration: 3188; Percent complete: 79.7%; Average loss: 2.7174
Iteration: 3189; Percent complete: 79.7%; Average loss: 2.9389
Iteration: 3190; Percent complete: 79.8%; Average loss: 2.9758
Iteration: 3191; Percent complete: 79.8%; Average loss: 3.0040
Iteration: 3192; Percent complete: 79.8%; Average loss: 2.7337
Iteration: 3193; Percent complete: 79.8%; Average loss: 2.6275
Iteration: 3194; Percent complete: 79.8%; Average loss: 2.9270
Iteration: 3195; Percent complete: 79.9%; Average loss: 3.0033
Iteration: 3196; Percent complete: 79.9%; Average loss: 2.8431
Iteration: 3197; Percent complete: 79.9%; Average loss: 2.9682
Iteration: 3198; Percent complete: 80.0%; Average loss: 2.7355
Iteration: 3199; Percent complete: 80.0%; Average loss: 2.7956
Iteration: 3200; Percent complete: 80.0%; Average loss: 3.2112
Iteration: 3201; Percent complete: 80.0%; Average loss: 2.9380
Iteration: 3202; Percent complete: 80.0%; Average loss: 2.9938
Iteration: 3203; Percent complete: 80.1%; Average loss: 2.9799
Iteration: 3204; Percent complete: 80.1%; Average loss: 2.8687
Iteration: 3205; Percent complete: 80.1%; Average loss: 2.9556
Iteration: 3206; Percent complete: 80.2%; Average loss: 2.8546
Iteration: 3207; Percent complete: 80.2%; Average loss: 2.8831
Iteration: 3208; Percent complete: 80.2%; Average loss: 2.8853
Iteration: 3209; Percent complete: 80.2%; Average loss: 3.0548
Iteration: 3210; Percent complete: 80.2%; Average loss: 2.8351
Iteration: 3211; Percent complete: 80.3%; Average loss: 2.8171
Iteration: 3212; Percent complete: 80.3%; Average loss: 3.0142
Iteration: 3213; Percent complete: 80.3%; Average loss: 2.8852
Iteration: 3214; Percent complete: 80.3%; Average loss: 2.6787
Iteration: 3215; Percent complete: 80.4%; Average loss: 2.6801
Iteration: 3216; Percent complete: 80.4%; Average loss: 2.6086
Iteration: 3217; Percent complete: 80.4%; Average loss: 2.7020
Iteration: 3218; Percent complete: 80.5%; Average loss: 2.8204
Iteration: 3219; Percent complete: 80.5%; Average loss: 2.7611
Iteration: 3220; Percent complete: 80.5%; Average loss: 2.8100
Iteration: 3221; Percent complete: 80.5%; Average loss: 2.7193
Iteration: 3222; Percent complete: 80.5%; Average loss: 2.7878
Iteration: 3223; Percent complete: 80.6%; Average loss: 2.9002
Iteration: 3224; Percent complete: 80.6%; Average loss: 2.9002
Iteration: 3225; Percent complete: 80.6%; Average loss: 2.7574
Iteration: 3226; Percent complete: 80.7%; Average loss: 2.8231
Iteration: 3227; Percent complete: 80.7%; Average loss: 2.8985
Iteration: 3228; Percent complete: 80.7%; Average loss: 2.9236
Iteration: 3229; Percent complete: 80.7%; Average loss: 2.9018
Iteration: 3230; Percent complete: 80.8%; Average loss: 2.8950
Iteration: 3231; Percent complete: 80.8%; Average loss: 2.8703
Iteration: 3232; Percent complete: 80.8%; Average loss: 2.8327
Iteration: 3233; Percent complete: 80.8%; Average loss: 2.7636
Iteration: 3234; Percent complete: 80.8%; Average loss: 3.0147
Iteration: 3235; Percent complete: 80.9%; Average loss: 2.8564
Iteration: 3236; Percent complete: 80.9%; Average loss: 2.9260
Iteration: 3237; Percent complete: 80.9%; Average loss: 2.7000
Iteration: 3238; Percent complete: 81.0%; Average loss: 2.7887
Iteration: 3239; Percent complete: 81.0%; Average loss: 2.8435
Iteration: 3240; Percent complete: 81.0%; Average loss: 2.7793
Iteration: 3241; Percent complete: 81.0%; Average loss: 2.7622
Iteration: 3242; Percent complete: 81.0%; Average loss: 2.8055
Iteration: 3243; Percent complete: 81.1%; Average loss: 2.7754
Iteration: 3244; Percent complete: 81.1%; Average loss: 2.9222
Iteration: 3245; Percent complete: 81.1%; Average loss: 2.8776
Iteration: 3246; Percent complete: 81.2%; Average loss: 2.9250
Iteration: 3247; Percent complete: 81.2%; Average loss: 2.5542
Iteration: 3248; Percent complete: 81.2%; Average loss: 2.8974
Iteration: 3249; Percent complete: 81.2%; Average loss: 2.5909
Iteration: 3250; Percent complete: 81.2%; Average loss: 2.5863
Iteration: 3251; Percent complete: 81.3%; Average loss: 2.8170
Iteration: 3252; Percent complete: 81.3%; Average loss: 2.9905
Iteration: 3253; Percent complete: 81.3%; Average loss: 2.8611
Iteration: 3254; Percent complete: 81.3%; Average loss: 2.7945
Iteration: 3255; Percent complete: 81.4%; Average loss: 2.6035
Iteration: 3256; Percent complete: 81.4%; Average loss: 2.6458
Iteration: 3257; Percent complete: 81.4%; Average loss: 2.8851
Iteration: 3258; Percent complete: 81.5%; Average loss: 2.5434
Iteration: 3259; Percent complete: 81.5%; Average loss: 2.5340
Iteration: 3260; Percent complete: 81.5%; Average loss: 2.9576
Iteration: 3261; Percent complete: 81.5%; Average loss: 2.7820
Iteration: 3262; Percent complete: 81.5%; Average loss: 2.9320
Iteration: 3263; Percent complete: 81.6%; Average loss: 2.7215
Iteration: 3264; Percent complete: 81.6%; Average loss: 2.7612
Iteration: 3265; Percent complete: 81.6%; Average loss: 2.8139
Iteration: 3266; Percent complete: 81.7%; Average loss: 2.7261
Iteration: 3267; Percent complete: 81.7%; Average loss: 2.8110
Iteration: 3268; Percent complete: 81.7%; Average loss: 2.7340
Iteration: 3269; Percent complete: 81.7%; Average loss: 2.6171
Iteration: 3270; Percent complete: 81.8%; Average loss: 2.6634
Iteration: 3271; Percent complete: 81.8%; Average loss: 2.7463
Iteration: 3272; Percent complete: 81.8%; Average loss: 2.5632
Iteration: 3273; Percent complete: 81.8%; Average loss: 2.6967
Iteration: 3274; Percent complete: 81.8%; Average loss: 2.7715
Iteration: 3275; Percent complete: 81.9%; Average loss: 2.8343
Iteration: 3276; Percent complete: 81.9%; Average loss: 2.9419
Iteration: 3277; Percent complete: 81.9%; Average loss: 2.9368
Iteration: 3278; Percent complete: 82.0%; Average loss: 2.6006
Iteration: 3279; Percent complete: 82.0%; Average loss: 2.9375
Iteration: 3280; Percent complete: 82.0%; Average loss: 2.8737
Iteration: 3281; Percent complete: 82.0%; Average loss: 2.6803
Iteration: 3282; Percent complete: 82.0%; Average loss: 2.7821
Iteration: 3283; Percent complete: 82.1%; Average loss: 3.0078
Iteration: 3284; Percent complete: 82.1%; Average loss: 2.8751
Iteration: 3285; Percent complete: 82.1%; Average loss: 2.9546
Iteration: 3286; Percent complete: 82.2%; Average loss: 2.6896
Iteration: 3287; Percent complete: 82.2%; Average loss: 3.0282
Iteration: 3288; Percent complete: 82.2%; Average loss: 2.8039
Iteration: 3289; Percent complete: 82.2%; Average loss: 2.9433
Iteration: 3290; Percent complete: 82.2%; Average loss: 2.8877
Iteration: 3291; Percent complete: 82.3%; Average loss: 2.6177
Iteration: 3292; Percent complete: 82.3%; Average loss: 3.0118
Iteration: 3293; Percent complete: 82.3%; Average loss: 3.0148
Iteration: 3294; Percent complete: 82.3%; Average loss: 2.8902
Iteration: 3295; Percent complete: 82.4%; Average loss: 2.8522
Iteration: 3296; Percent complete: 82.4%; Average loss: 2.8387
Iteration: 3297; Percent complete: 82.4%; Average loss: 2.7802
Iteration: 3298; Percent complete: 82.5%; Average loss: 2.6937
Iteration: 3299; Percent complete: 82.5%; Average loss: 2.9415
Iteration: 3300; Percent complete: 82.5%; Average loss: 2.7310
Iteration: 3301; Percent complete: 82.5%; Average loss: 2.7931
Iteration: 3302; Percent complete: 82.5%; Average loss: 2.8934
Iteration: 3303; Percent complete: 82.6%; Average loss: 2.9526
Iteration: 3304; Percent complete: 82.6%; Average loss: 2.8138
Iteration: 3305; Percent complete: 82.6%; Average loss: 2.6599
Iteration: 3306; Percent complete: 82.7%; Average loss: 2.8087
Iteration: 3307; Percent complete: 82.7%; Average loss: 2.8085
Iteration: 3308; Percent complete: 82.7%; Average loss: 2.9075
Iteration: 3309; Percent complete: 82.7%; Average loss: 2.6912
Iteration: 3310; Percent complete: 82.8%; Average loss: 2.8787
Iteration: 3311; Percent complete: 82.8%; Average loss: 2.8042
Iteration: 3312; Percent complete: 82.8%; Average loss: 2.9365
Iteration: 3313; Percent complete: 82.8%; Average loss: 3.0656
Iteration: 3314; Percent complete: 82.8%; Average loss: 2.8228
Iteration: 3315; Percent complete: 82.9%; Average loss: 2.6660
Iteration: 3316; Percent complete: 82.9%; Average loss: 2.8154
Iteration: 3317; Percent complete: 82.9%; Average loss: 2.7574
Iteration: 3318; Percent complete: 83.0%; Average loss: 2.8536
Iteration: 3319; Percent complete: 83.0%; Average loss: 2.7485
Iteration: 3320; Percent complete: 83.0%; Average loss: 2.9517
Iteration: 3321; Percent complete: 83.0%; Average loss: 2.8301
Iteration: 3322; Percent complete: 83.0%; Average loss: 2.8075
Iteration: 3323; Percent complete: 83.1%; Average loss: 3.0243
Iteration: 3324; Percent complete: 83.1%; Average loss: 2.8074
Iteration: 3325; Percent complete: 83.1%; Average loss: 2.7535
Iteration: 3326; Percent complete: 83.2%; Average loss: 2.8926
Iteration: 3327; Percent complete: 83.2%; Average loss: 2.7915
Iteration: 3328; Percent complete: 83.2%; Average loss: 2.6500
Iteration: 3329; Percent complete: 83.2%; Average loss: 2.7185
Iteration: 3330; Percent complete: 83.2%; Average loss: 2.9005
Iteration: 3331; Percent complete: 83.3%; Average loss: 2.6587
Iteration: 3332; Percent complete: 83.3%; Average loss: 2.8801
Iteration: 3333; Percent complete: 83.3%; Average loss: 2.8033
Iteration: 3334; Percent complete: 83.4%; Average loss: 2.9333
Iteration: 3335; Percent complete: 83.4%; Average loss: 2.9766
Iteration: 3336; Percent complete: 83.4%; Average loss: 2.8049
Iteration: 3337; Percent complete: 83.4%; Average loss: 2.7930
Iteration: 3338; Percent complete: 83.5%; Average loss: 2.5989
Iteration: 3339; Percent complete: 83.5%; Average loss: 2.7854
Iteration: 3340; Percent complete: 83.5%; Average loss: 2.8153
Iteration: 3341; Percent complete: 83.5%; Average loss: 2.8255
Iteration: 3342; Percent complete: 83.5%; Average loss: 2.8123
Iteration: 3343; Percent complete: 83.6%; Average loss: 2.8308
Iteration: 3344; Percent complete: 83.6%; Average loss: 2.7446
Iteration: 3345; Percent complete: 83.6%; Average loss: 2.6034
Iteration: 3346; Percent complete: 83.7%; Average loss: 2.7807
Iteration: 3347; Percent complete: 83.7%; Average loss: 2.7482
Iteration: 3348; Percent complete: 83.7%; Average loss: 2.6531
Iteration: 3349; Percent complete: 83.7%; Average loss: 2.8505
Iteration: 3350; Percent complete: 83.8%; Average loss: 2.7336
Iteration: 3351; Percent complete: 83.8%; Average loss: 2.7182
Iteration: 3352; Percent complete: 83.8%; Average loss: 2.7830
Iteration: 3353; Percent complete: 83.8%; Average loss: 2.7235
Iteration: 3354; Percent complete: 83.9%; Average loss: 2.7684
Iteration: 3355; Percent complete: 83.9%; Average loss: 2.4995
Iteration: 3356; Percent complete: 83.9%; Average loss: 2.8513
Iteration: 3357; Percent complete: 83.9%; Average loss: 2.8914
Iteration: 3358; Percent complete: 84.0%; Average loss: 2.5909
Iteration: 3359; Percent complete: 84.0%; Average loss: 2.8187
Iteration: 3360; Percent complete: 84.0%; Average loss: 2.8083
Iteration: 3361; Percent complete: 84.0%; Average loss: 2.5520
Iteration: 3362; Percent complete: 84.0%; Average loss: 2.6641
Iteration: 3363; Percent complete: 84.1%; Average loss: 3.0144
Iteration: 3364; Percent complete: 84.1%; Average loss: 2.8847
Iteration: 3365; Percent complete: 84.1%; Average loss: 2.9102
Iteration: 3366; Percent complete: 84.2%; Average loss: 2.7069
Iteration: 3367; Percent complete: 84.2%; Average loss: 2.8219
Iteration: 3368; Percent complete: 84.2%; Average loss: 2.8835
Iteration: 3369; Percent complete: 84.2%; Average loss: 2.5611
Iteration: 3370; Percent complete: 84.2%; Average loss: 3.0482
Iteration: 3371; Percent complete: 84.3%; Average loss: 2.7424
Iteration: 3372; Percent complete: 84.3%; Average loss: 2.8269
Iteration: 3373; Percent complete: 84.3%; Average loss: 2.7690
Iteration: 3374; Percent complete: 84.4%; Average loss: 2.6762
Iteration: 3375; Percent complete: 84.4%; Average loss: 2.7957
Iteration: 3376; Percent complete: 84.4%; Average loss: 2.9840
Iteration: 3377; Percent complete: 84.4%; Average loss: 2.5509
Iteration: 3378; Percent complete: 84.5%; Average loss: 2.8155
Iteration: 3379; Percent complete: 84.5%; Average loss: 2.5827
Iteration: 3380; Percent complete: 84.5%; Average loss: 2.9275
Iteration: 3381; Percent complete: 84.5%; Average loss: 3.0982
Iteration: 3382; Percent complete: 84.5%; Average loss: 2.7371
Iteration: 3383; Percent complete: 84.6%; Average loss: 2.7469
Iteration: 3384; Percent complete: 84.6%; Average loss: 2.7698
Iteration: 3385; Percent complete: 84.6%; Average loss: 2.6997
Iteration: 3386; Percent complete: 84.7%; Average loss: 2.7593
Iteration: 3387; Percent complete: 84.7%; Average loss: 2.6831
Iteration: 3388; Percent complete: 84.7%; Average loss: 2.7832
Iteration: 3389; Percent complete: 84.7%; Average loss: 2.6635
Iteration: 3390; Percent complete: 84.8%; Average loss: 2.7884
Iteration: 3391; Percent complete: 84.8%; Average loss: 2.5400
Iteration: 3392; Percent complete: 84.8%; Average loss: 2.8807
Iteration: 3393; Percent complete: 84.8%; Average loss: 2.8824
Iteration: 3394; Percent complete: 84.9%; Average loss: 3.0978
Iteration: 3395; Percent complete: 84.9%; Average loss: 3.0837
Iteration: 3396; Percent complete: 84.9%; Average loss: 2.4372
Iteration: 3397; Percent complete: 84.9%; Average loss: 2.8035
Iteration: 3398; Percent complete: 85.0%; Average loss: 2.7471
Iteration: 3399; Percent complete: 85.0%; Average loss: 2.7652
Iteration: 3400; Percent complete: 85.0%; Average loss: 2.6629
Iteration: 3401; Percent complete: 85.0%; Average loss: 2.7831
Iteration: 3402; Percent complete: 85.0%; Average loss: 2.8638
Iteration: 3403; Percent complete: 85.1%; Average loss: 2.9225
Iteration: 3404; Percent complete: 85.1%; Average loss: 2.7632
Iteration: 3405; Percent complete: 85.1%; Average loss: 2.7390
Iteration: 3406; Percent complete: 85.2%; Average loss: 2.8405
Iteration: 3407; Percent complete: 85.2%; Average loss: 2.6064
Iteration: 3408; Percent complete: 85.2%; Average loss: 2.7296
Iteration: 3409; Percent complete: 85.2%; Average loss: 2.9395
Iteration: 3410; Percent complete: 85.2%; Average loss: 2.7799
Iteration: 3411; Percent complete: 85.3%; Average loss: 2.7803
Iteration: 3412; Percent complete: 85.3%; Average loss: 2.7834
Iteration: 3413; Percent complete: 85.3%; Average loss: 2.8412
Iteration: 3414; Percent complete: 85.4%; Average loss: 2.8424
Iteration: 3415; Percent complete: 85.4%; Average loss: 2.6551
Iteration: 3416; Percent complete: 85.4%; Average loss: 2.6661
Iteration: 3417; Percent complete: 85.4%; Average loss: 2.9025
Iteration: 3418; Percent complete: 85.5%; Average loss: 2.7240
Iteration: 3419; Percent complete: 85.5%; Average loss: 2.7896
Iteration: 3420; Percent complete: 85.5%; Average loss: 2.6865
Iteration: 3421; Percent complete: 85.5%; Average loss: 2.7555
Iteration: 3422; Percent complete: 85.5%; Average loss: 2.7074
Iteration: 3423; Percent complete: 85.6%; Average loss: 2.9179
Iteration: 3424; Percent complete: 85.6%; Average loss: 2.8463
Iteration: 3425; Percent complete: 85.6%; Average loss: 2.5574
Iteration: 3426; Percent complete: 85.7%; Average loss: 2.9442
Iteration: 3427; Percent complete: 85.7%; Average loss: 2.9042
Iteration: 3428; Percent complete: 85.7%; Average loss: 2.7356
Iteration: 3429; Percent complete: 85.7%; Average loss: 2.8111
Iteration: 3430; Percent complete: 85.8%; Average loss: 2.6483
Iteration: 3431; Percent complete: 85.8%; Average loss: 2.8881
Iteration: 3432; Percent complete: 85.8%; Average loss: 2.7860
Iteration: 3433; Percent complete: 85.8%; Average loss: 2.8451
Iteration: 3434; Percent complete: 85.9%; Average loss: 2.9411
Iteration: 3435; Percent complete: 85.9%; Average loss: 2.6920
Iteration: 3436; Percent complete: 85.9%; Average loss: 2.8592
Iteration: 3437; Percent complete: 85.9%; Average loss: 2.6893
Iteration: 3438; Percent complete: 86.0%; Average loss: 3.0505
Iteration: 3439; Percent complete: 86.0%; Average loss: 2.8046
Iteration: 3440; Percent complete: 86.0%; Average loss: 2.6199
Iteration: 3441; Percent complete: 86.0%; Average loss: 2.8975
Iteration: 3442; Percent complete: 86.1%; Average loss: 2.8469
Iteration: 3443; Percent complete: 86.1%; Average loss: 2.9622
Iteration: 3444; Percent complete: 86.1%; Average loss: 2.7945
Iteration: 3445; Percent complete: 86.1%; Average loss: 2.7920
Iteration: 3446; Percent complete: 86.2%; Average loss: 2.6423
Iteration: 3447; Percent complete: 86.2%; Average loss: 3.0416
Iteration: 3448; Percent complete: 86.2%; Average loss: 2.8024
Iteration: 3449; Percent complete: 86.2%; Average loss: 2.8038
Iteration: 3450; Percent complete: 86.2%; Average loss: 2.8919
Iteration: 3451; Percent complete: 86.3%; Average loss: 2.8758
Iteration: 3452; Percent complete: 86.3%; Average loss: 2.6744
Iteration: 3453; Percent complete: 86.3%; Average loss: 2.8678
Iteration: 3454; Percent complete: 86.4%; Average loss: 2.7144
Iteration: 3455; Percent complete: 86.4%; Average loss: 2.6201
Iteration: 3456; Percent complete: 86.4%; Average loss: 2.7168
Iteration: 3457; Percent complete: 86.4%; Average loss: 2.6806
Iteration: 3458; Percent complete: 86.5%; Average loss: 2.7102
Iteration: 3459; Percent complete: 86.5%; Average loss: 2.5211
Iteration: 3460; Percent complete: 86.5%; Average loss: 2.5987
Iteration: 3461; Percent complete: 86.5%; Average loss: 2.6071
Iteration: 3462; Percent complete: 86.6%; Average loss: 2.7358
Iteration: 3463; Percent complete: 86.6%; Average loss: 2.7396
Iteration: 3464; Percent complete: 86.6%; Average loss: 2.8341
Iteration: 3465; Percent complete: 86.6%; Average loss: 2.9149
Iteration: 3466; Percent complete: 86.7%; Average loss: 2.7237
Iteration: 3467; Percent complete: 86.7%; Average loss: 2.9334
Iteration: 3468; Percent complete: 86.7%; Average loss: 2.9335
Iteration: 3469; Percent complete: 86.7%; Average loss: 2.5303
Iteration: 3470; Percent complete: 86.8%; Average loss: 2.6601
Iteration: 3471; Percent complete: 86.8%; Average loss: 2.6725
Iteration: 3472; Percent complete: 86.8%; Average loss: 2.8910
Iteration: 3473; Percent complete: 86.8%; Average loss: 2.9287
Iteration: 3474; Percent complete: 86.9%; Average loss: 2.8503
Iteration: 3475; Percent complete: 86.9%; Average loss: 2.6318
Iteration: 3476; Percent complete: 86.9%; Average loss: 2.8145
Iteration: 3477; Percent complete: 86.9%; Average loss: 2.7990
Iteration: 3478; Percent complete: 87.0%; Average loss: 3.0011
Iteration: 3479; Percent complete: 87.0%; Average loss: 2.8759
Iteration: 3480; Percent complete: 87.0%; Average loss: 2.9689
Iteration: 3481; Percent complete: 87.0%; Average loss: 2.7658
Iteration: 3482; Percent complete: 87.1%; Average loss: 2.9499
Iteration: 3483; Percent complete: 87.1%; Average loss: 2.7878
Iteration: 3484; Percent complete: 87.1%; Average loss: 2.5167
Iteration: 3485; Percent complete: 87.1%; Average loss: 2.7200
Iteration: 3486; Percent complete: 87.2%; Average loss: 2.7712
Iteration: 3487; Percent complete: 87.2%; Average loss: 2.6997
Iteration: 3488; Percent complete: 87.2%; Average loss: 2.8523
Iteration: 3489; Percent complete: 87.2%; Average loss: 2.9020
Iteration: 3490; Percent complete: 87.2%; Average loss: 2.7949
Iteration: 3491; Percent complete: 87.3%; Average loss: 2.7403
Iteration: 3492; Percent complete: 87.3%; Average loss: 3.0373
Iteration: 3493; Percent complete: 87.3%; Average loss: 3.0916
Iteration: 3494; Percent complete: 87.4%; Average loss: 2.7324
Iteration: 3495; Percent complete: 87.4%; Average loss: 2.7255
Iteration: 3496; Percent complete: 87.4%; Average loss: 2.7818
Iteration: 3497; Percent complete: 87.4%; Average loss: 2.6360
Iteration: 3498; Percent complete: 87.5%; Average loss: 2.7477
Iteration: 3499; Percent complete: 87.5%; Average loss: 2.6353
Iteration: 3500; Percent complete: 87.5%; Average loss: 2.5939
Iteration: 3501; Percent complete: 87.5%; Average loss: 3.0684
Iteration: 3502; Percent complete: 87.5%; Average loss: 2.6184
Iteration: 3503; Percent complete: 87.6%; Average loss: 2.4917
Iteration: 3504; Percent complete: 87.6%; Average loss: 2.6747
Iteration: 3505; Percent complete: 87.6%; Average loss: 2.7785
Iteration: 3506; Percent complete: 87.6%; Average loss: 2.5308
Iteration: 3507; Percent complete: 87.7%; Average loss: 2.7350
Iteration: 3508; Percent complete: 87.7%; Average loss: 2.8961
Iteration: 3509; Percent complete: 87.7%; Average loss: 2.7672
Iteration: 3510; Percent complete: 87.8%; Average loss: 2.6063
Iteration: 3511; Percent complete: 87.8%; Average loss: 2.8637
Iteration: 3512; Percent complete: 87.8%; Average loss: 2.5648
Iteration: 3513; Percent complete: 87.8%; Average loss: 2.9259
Iteration: 3514; Percent complete: 87.8%; Average loss: 2.6274
Iteration: 3515; Percent complete: 87.9%; Average loss: 2.6859
Iteration: 3516; Percent complete: 87.9%; Average loss: 2.8593
Iteration: 3517; Percent complete: 87.9%; Average loss: 2.8579
Iteration: 3518; Percent complete: 87.9%; Average loss: 2.7135
Iteration: 3519; Percent complete: 88.0%; Average loss: 2.7027
Iteration: 3520; Percent complete: 88.0%; Average loss: 2.7027
Iteration: 3521; Percent complete: 88.0%; Average loss: 2.7247
Iteration: 3522; Percent complete: 88.0%; Average loss: 2.6654
Iteration: 3523; Percent complete: 88.1%; Average loss: 2.7148
Iteration: 3524; Percent complete: 88.1%; Average loss: 2.6763
Iteration: 3525; Percent complete: 88.1%; Average loss: 2.7548
Iteration: 3526; Percent complete: 88.1%; Average loss: 2.6364
Iteration: 3527; Percent complete: 88.2%; Average loss: 2.7668
Iteration: 3528; Percent complete: 88.2%; Average loss: 2.7096
Iteration: 3529; Percent complete: 88.2%; Average loss: 2.6602
Iteration: 3530; Percent complete: 88.2%; Average loss: 2.5433
Iteration: 3531; Percent complete: 88.3%; Average loss: 2.9488
Iteration: 3532; Percent complete: 88.3%; Average loss: 2.9553
Iteration: 3533; Percent complete: 88.3%; Average loss: 2.6651
Iteration: 3534; Percent complete: 88.3%; Average loss: 2.7674
Iteration: 3535; Percent complete: 88.4%; Average loss: 2.8122
Iteration: 3536; Percent complete: 88.4%; Average loss: 2.6777
Iteration: 3537; Percent complete: 88.4%; Average loss: 2.4979
Iteration: 3538; Percent complete: 88.4%; Average loss: 2.5697
Iteration: 3539; Percent complete: 88.5%; Average loss: 2.9752
Iteration: 3540; Percent complete: 88.5%; Average loss: 2.8454
Iteration: 3541; Percent complete: 88.5%; Average loss: 2.6527
Iteration: 3542; Percent complete: 88.5%; Average loss: 2.5441
Iteration: 3543; Percent complete: 88.6%; Average loss: 2.7909
Iteration: 3544; Percent complete: 88.6%; Average loss: 2.7513
Iteration: 3545; Percent complete: 88.6%; Average loss: 2.8592
Iteration: 3546; Percent complete: 88.6%; Average loss: 2.8769
Iteration: 3547; Percent complete: 88.7%; Average loss: 2.6474
Iteration: 3548; Percent complete: 88.7%; Average loss: 2.6369
Iteration: 3549; Percent complete: 88.7%; Average loss: 2.7989
Iteration: 3550; Percent complete: 88.8%; Average loss: 2.4709
Iteration: 3551; Percent complete: 88.8%; Average loss: 2.7206
Iteration: 3552; Percent complete: 88.8%; Average loss: 2.7204
Iteration: 3553; Percent complete: 88.8%; Average loss: 2.7597
Iteration: 3554; Percent complete: 88.8%; Average loss: 2.5420
Iteration: 3555; Percent complete: 88.9%; Average loss: 2.8010
Iteration: 3556; Percent complete: 88.9%; Average loss: 2.6412
Iteration: 3557; Percent complete: 88.9%; Average loss: 2.7757
Iteration: 3558; Percent complete: 88.9%; Average loss: 2.6769
Iteration: 3559; Percent complete: 89.0%; Average loss: 2.6916
Iteration: 3560; Percent complete: 89.0%; Average loss: 2.8177
Iteration: 3561; Percent complete: 89.0%; Average loss: 2.5685
Iteration: 3562; Percent complete: 89.0%; Average loss: 2.6957
Iteration: 3563; Percent complete: 89.1%; Average loss: 2.5895
Iteration: 3564; Percent complete: 89.1%; Average loss: 2.8674
Iteration: 3565; Percent complete: 89.1%; Average loss: 2.8484
Iteration: 3566; Percent complete: 89.1%; Average loss: 2.8165
Iteration: 3567; Percent complete: 89.2%; Average loss: 2.7834
Iteration: 3568; Percent complete: 89.2%; Average loss: 2.7777
Iteration: 3569; Percent complete: 89.2%; Average loss: 2.7216
Iteration: 3570; Percent complete: 89.2%; Average loss: 2.6511
Iteration: 3571; Percent complete: 89.3%; Average loss: 2.7624
Iteration: 3572; Percent complete: 89.3%; Average loss: 2.8222
Iteration: 3573; Percent complete: 89.3%; Average loss: 2.8946
Iteration: 3574; Percent complete: 89.3%; Average loss: 2.7078
Iteration: 3575; Percent complete: 89.4%; Average loss: 2.8331
Iteration: 3576; Percent complete: 89.4%; Average loss: 2.8259
Iteration: 3577; Percent complete: 89.4%; Average loss: 2.6727
Iteration: 3578; Percent complete: 89.5%; Average loss: 2.9077
Iteration: 3579; Percent complete: 89.5%; Average loss: 2.6417
Iteration: 3580; Percent complete: 89.5%; Average loss: 2.7440
Iteration: 3581; Percent complete: 89.5%; Average loss: 2.7838
Iteration: 3582; Percent complete: 89.5%; Average loss: 2.7429
Iteration: 3583; Percent complete: 89.6%; Average loss: 2.8356
Iteration: 3584; Percent complete: 89.6%; Average loss: 2.7930
Iteration: 3585; Percent complete: 89.6%; Average loss: 2.7249
Iteration: 3586; Percent complete: 89.6%; Average loss: 2.8303
Iteration: 3587; Percent complete: 89.7%; Average loss: 2.6355
Iteration: 3588; Percent complete: 89.7%; Average loss: 2.7479
Iteration: 3589; Percent complete: 89.7%; Average loss: 2.7516
Iteration: 3590; Percent complete: 89.8%; Average loss: 2.7083
Iteration: 3591; Percent complete: 89.8%; Average loss: 2.8269
Iteration: 3592; Percent complete: 89.8%; Average loss: 2.7410
Iteration: 3593; Percent complete: 89.8%; Average loss: 2.5859
Iteration: 3594; Percent complete: 89.8%; Average loss: 2.5302
Iteration: 3595; Percent complete: 89.9%; Average loss: 2.6338
Iteration: 3596; Percent complete: 89.9%; Average loss: 2.8172
Iteration: 3597; Percent complete: 89.9%; Average loss: 2.7741
Iteration: 3598; Percent complete: 90.0%; Average loss: 2.8413
Iteration: 3599; Percent complete: 90.0%; Average loss: 2.7927
Iteration: 3600; Percent complete: 90.0%; Average loss: 2.7057
Iteration: 3601; Percent complete: 90.0%; Average loss: 2.8502
Iteration: 3602; Percent complete: 90.0%; Average loss: 2.6934
Iteration: 3603; Percent complete: 90.1%; Average loss: 2.6298
Iteration: 3604; Percent complete: 90.1%; Average loss: 2.7250
Iteration: 3605; Percent complete: 90.1%; Average loss: 2.5299
Iteration: 3606; Percent complete: 90.1%; Average loss: 2.8030
Iteration: 3607; Percent complete: 90.2%; Average loss: 2.8549
Iteration: 3608; Percent complete: 90.2%; Average loss: 2.7037
Iteration: 3609; Percent complete: 90.2%; Average loss: 2.6524
Iteration: 3610; Percent complete: 90.2%; Average loss: 2.6422
Iteration: 3611; Percent complete: 90.3%; Average loss: 2.7980
Iteration: 3612; Percent complete: 90.3%; Average loss: 2.7709
Iteration: 3613; Percent complete: 90.3%; Average loss: 2.7566
Iteration: 3614; Percent complete: 90.3%; Average loss: 2.5458
Iteration: 3615; Percent complete: 90.4%; Average loss: 2.5879
Iteration: 3616; Percent complete: 90.4%; Average loss: 2.9715
Iteration: 3617; Percent complete: 90.4%; Average loss: 2.5320
Iteration: 3618; Percent complete: 90.5%; Average loss: 2.6394
Iteration: 3619; Percent complete: 90.5%; Average loss: 2.5182
Iteration: 3620; Percent complete: 90.5%; Average loss: 2.5726
Iteration: 3621; Percent complete: 90.5%; Average loss: 2.7604
Iteration: 3622; Percent complete: 90.5%; Average loss: 2.5815
Iteration: 3623; Percent complete: 90.6%; Average loss: 2.6774
Iteration: 3624; Percent complete: 90.6%; Average loss: 2.8286
Iteration: 3625; Percent complete: 90.6%; Average loss: 2.7797
Iteration: 3626; Percent complete: 90.6%; Average loss: 2.5811
Iteration: 3627; Percent complete: 90.7%; Average loss: 2.6576
Iteration: 3628; Percent complete: 90.7%; Average loss: 2.7300
Iteration: 3629; Percent complete: 90.7%; Average loss: 2.5772
Iteration: 3630; Percent complete: 90.8%; Average loss: 2.7209
Iteration: 3631; Percent complete: 90.8%; Average loss: 2.6484
Iteration: 3632; Percent complete: 90.8%; Average loss: 2.6346
Iteration: 3633; Percent complete: 90.8%; Average loss: 2.5249
Iteration: 3634; Percent complete: 90.8%; Average loss: 2.5477
Iteration: 3635; Percent complete: 90.9%; Average loss: 2.5973
Iteration: 3636; Percent complete: 90.9%; Average loss: 2.6982
Iteration: 3637; Percent complete: 90.9%; Average loss: 2.8545
Iteration: 3638; Percent complete: 91.0%; Average loss: 2.8487
Iteration: 3639; Percent complete: 91.0%; Average loss: 2.5253
Iteration: 3640; Percent complete: 91.0%; Average loss: 2.5157
Iteration: 3641; Percent complete: 91.0%; Average loss: 2.7274
Iteration: 3642; Percent complete: 91.0%; Average loss: 2.7221
Iteration: 3643; Percent complete: 91.1%; Average loss: 2.8262
Iteration: 3644; Percent complete: 91.1%; Average loss: 2.7135
Iteration: 3645; Percent complete: 91.1%; Average loss: 2.6354
Iteration: 3646; Percent complete: 91.1%; Average loss: 2.8132
Iteration: 3647; Percent complete: 91.2%; Average loss: 2.8196
Iteration: 3648; Percent complete: 91.2%; Average loss: 2.7007
Iteration: 3649; Percent complete: 91.2%; Average loss: 2.3956
Iteration: 3650; Percent complete: 91.2%; Average loss: 2.5618
Iteration: 3651; Percent complete: 91.3%; Average loss: 2.8122
Iteration: 3652; Percent complete: 91.3%; Average loss: 2.7099
Iteration: 3653; Percent complete: 91.3%; Average loss: 2.6196
Iteration: 3654; Percent complete: 91.3%; Average loss: 2.6768
Iteration: 3655; Percent complete: 91.4%; Average loss: 2.5756
Iteration: 3656; Percent complete: 91.4%; Average loss: 2.8527
Iteration: 3657; Percent complete: 91.4%; Average loss: 2.5574
Iteration: 3658; Percent complete: 91.5%; Average loss: 2.5253
Iteration: 3659; Percent complete: 91.5%; Average loss: 2.6116
Iteration: 3660; Percent complete: 91.5%; Average loss: 2.6761
Iteration: 3661; Percent complete: 91.5%; Average loss: 2.5970
Iteration: 3662; Percent complete: 91.5%; Average loss: 2.9317
Iteration: 3663; Percent complete: 91.6%; Average loss: 2.8409
Iteration: 3664; Percent complete: 91.6%; Average loss: 2.4385
Iteration: 3665; Percent complete: 91.6%; Average loss: 2.7977
Iteration: 3666; Percent complete: 91.6%; Average loss: 2.6989
Iteration: 3667; Percent complete: 91.7%; Average loss: 2.7103
Iteration: 3668; Percent complete: 91.7%; Average loss: 2.7813
Iteration: 3669; Percent complete: 91.7%; Average loss: 2.7868
Iteration: 3670; Percent complete: 91.8%; Average loss: 2.6806
Iteration: 3671; Percent complete: 91.8%; Average loss: 2.6062
Iteration: 3672; Percent complete: 91.8%; Average loss: 2.7170
Iteration: 3673; Percent complete: 91.8%; Average loss: 2.5898
Iteration: 3674; Percent complete: 91.8%; Average loss: 2.7720
Iteration: 3675; Percent complete: 91.9%; Average loss: 2.7087
Iteration: 3676; Percent complete: 91.9%; Average loss: 2.6237
Iteration: 3677; Percent complete: 91.9%; Average loss: 2.8634
Iteration: 3678; Percent complete: 92.0%; Average loss: 2.4951
Iteration: 3679; Percent complete: 92.0%; Average loss: 2.5817
Iteration: 3680; Percent complete: 92.0%; Average loss: 2.8531
Iteration: 3681; Percent complete: 92.0%; Average loss: 2.6293
Iteration: 3682; Percent complete: 92.0%; Average loss: 2.4641
Iteration: 3683; Percent complete: 92.1%; Average loss: 2.5996
Iteration: 3684; Percent complete: 92.1%; Average loss: 2.6760
Iteration: 3685; Percent complete: 92.1%; Average loss: 2.7913
Iteration: 3686; Percent complete: 92.2%; Average loss: 2.6064
Iteration: 3687; Percent complete: 92.2%; Average loss: 2.7701
Iteration: 3688; Percent complete: 92.2%; Average loss: 2.4914
Iteration: 3689; Percent complete: 92.2%; Average loss: 2.6398
Iteration: 3690; Percent complete: 92.2%; Average loss: 2.6947
Iteration: 3691; Percent complete: 92.3%; Average loss: 2.6968
Iteration: 3692; Percent complete: 92.3%; Average loss: 2.6784
Iteration: 3693; Percent complete: 92.3%; Average loss: 2.4768
Iteration: 3694; Percent complete: 92.3%; Average loss: 2.8091
Iteration: 3695; Percent complete: 92.4%; Average loss: 2.7903
Iteration: 3696; Percent complete: 92.4%; Average loss: 2.6174
Iteration: 3697; Percent complete: 92.4%; Average loss: 2.7349
Iteration: 3698; Percent complete: 92.5%; Average loss: 2.7267
Iteration: 3699; Percent complete: 92.5%; Average loss: 2.6319
Iteration: 3700; Percent complete: 92.5%; Average loss: 2.7686
Iteration: 3701; Percent complete: 92.5%; Average loss: 2.8088
Iteration: 3702; Percent complete: 92.5%; Average loss: 2.5267
Iteration: 3703; Percent complete: 92.6%; Average loss: 2.8486
Iteration: 3704; Percent complete: 92.6%; Average loss: 2.5669
Iteration: 3705; Percent complete: 92.6%; Average loss: 2.4554
Iteration: 3706; Percent complete: 92.7%; Average loss: 2.6749
Iteration: 3707; Percent complete: 92.7%; Average loss: 2.4573
Iteration: 3708; Percent complete: 92.7%; Average loss: 2.5687
Iteration: 3709; Percent complete: 92.7%; Average loss: 2.8265
Iteration: 3710; Percent complete: 92.8%; Average loss: 2.8339
Iteration: 3711; Percent complete: 92.8%; Average loss: 2.7088
Iteration: 3712; Percent complete: 92.8%; Average loss: 2.7651
Iteration: 3713; Percent complete: 92.8%; Average loss: 2.9020
Iteration: 3714; Percent complete: 92.8%; Average loss: 2.6961
Iteration: 3715; Percent complete: 92.9%; Average loss: 2.7515
Iteration: 3716; Percent complete: 92.9%; Average loss: 2.9858
Iteration: 3717; Percent complete: 92.9%; Average loss: 2.6720
Iteration: 3718; Percent complete: 93.0%; Average loss: 2.8384
Iteration: 3719; Percent complete: 93.0%; Average loss: 2.6182
Iteration: 3720; Percent complete: 93.0%; Average loss: 2.7093
Iteration: 3721; Percent complete: 93.0%; Average loss: 2.4799
Iteration: 3722; Percent complete: 93.0%; Average loss: 2.6914
Iteration: 3723; Percent complete: 93.1%; Average loss: 2.5354
Iteration: 3724; Percent complete: 93.1%; Average loss: 2.8056
Iteration: 3725; Percent complete: 93.1%; Average loss: 2.8189
Iteration: 3726; Percent complete: 93.2%; Average loss: 2.6410
Iteration: 3727; Percent complete: 93.2%; Average loss: 2.9287
Iteration: 3728; Percent complete: 93.2%; Average loss: 2.8641
Iteration: 3729; Percent complete: 93.2%; Average loss: 2.7533
Iteration: 3730; Percent complete: 93.2%; Average loss: 2.6770
Iteration: 3731; Percent complete: 93.3%; Average loss: 2.6183
Iteration: 3732; Percent complete: 93.3%; Average loss: 2.8573
Iteration: 3733; Percent complete: 93.3%; Average loss: 2.5076
Iteration: 3734; Percent complete: 93.3%; Average loss: 2.6605
Iteration: 3735; Percent complete: 93.4%; Average loss: 2.4432
Iteration: 3736; Percent complete: 93.4%; Average loss: 2.5583
Iteration: 3737; Percent complete: 93.4%; Average loss: 2.5568
Iteration: 3738; Percent complete: 93.5%; Average loss: 2.7325
Iteration: 3739; Percent complete: 93.5%; Average loss: 2.6403
Iteration: 3740; Percent complete: 93.5%; Average loss: 2.6621
Iteration: 3741; Percent complete: 93.5%; Average loss: 2.6663
Iteration: 3742; Percent complete: 93.5%; Average loss: 2.4109
Iteration: 3743; Percent complete: 93.6%; Average loss: 2.7668
Iteration: 3744; Percent complete: 93.6%; Average loss: 2.7114
Iteration: 3745; Percent complete: 93.6%; Average loss: 2.6902
Iteration: 3746; Percent complete: 93.7%; Average loss: 2.8747
Iteration: 3747; Percent complete: 93.7%; Average loss: 2.7068
Iteration: 3748; Percent complete: 93.7%; Average loss: 2.8944
Iteration: 3749; Percent complete: 93.7%; Average loss: 2.5884
Iteration: 3750; Percent complete: 93.8%; Average loss: 2.6991
Iteration: 3751; Percent complete: 93.8%; Average loss: 2.6690
Iteration: 3752; Percent complete: 93.8%; Average loss: 2.9135
Iteration: 3753; Percent complete: 93.8%; Average loss: 2.6717
Iteration: 3754; Percent complete: 93.8%; Average loss: 2.7336
Iteration: 3755; Percent complete: 93.9%; Average loss: 2.7663
Iteration: 3756; Percent complete: 93.9%; Average loss: 2.4726
Iteration: 3757; Percent complete: 93.9%; Average loss: 2.5573
Iteration: 3758; Percent complete: 94.0%; Average loss: 2.5862
Iteration: 3759; Percent complete: 94.0%; Average loss: 2.7125
Iteration: 3760; Percent complete: 94.0%; Average loss: 2.5971
Iteration: 3761; Percent complete: 94.0%; Average loss: 2.5806
Iteration: 3762; Percent complete: 94.0%; Average loss: 2.5861
Iteration: 3763; Percent complete: 94.1%; Average loss: 2.6263
Iteration: 3764; Percent complete: 94.1%; Average loss: 2.5781
Iteration: 3765; Percent complete: 94.1%; Average loss: 2.6185
Iteration: 3766; Percent complete: 94.2%; Average loss: 2.6598
Iteration: 3767; Percent complete: 94.2%; Average loss: 2.8242
Iteration: 3768; Percent complete: 94.2%; Average loss: 2.8376
Iteration: 3769; Percent complete: 94.2%; Average loss: 2.5112
Iteration: 3770; Percent complete: 94.2%; Average loss: 2.7960
Iteration: 3771; Percent complete: 94.3%; Average loss: 2.6003
Iteration: 3772; Percent complete: 94.3%; Average loss: 2.6147
Iteration: 3773; Percent complete: 94.3%; Average loss: 2.6321
Iteration: 3774; Percent complete: 94.3%; Average loss: 2.5365
Iteration: 3775; Percent complete: 94.4%; Average loss: 2.6773
Iteration: 3776; Percent complete: 94.4%; Average loss: 2.8665
Iteration: 3777; Percent complete: 94.4%; Average loss: 2.5630
Iteration: 3778; Percent complete: 94.5%; Average loss: 2.5273
Iteration: 3779; Percent complete: 94.5%; Average loss: 2.7934
Iteration: 3780; Percent complete: 94.5%; Average loss: 2.8084
Iteration: 3781; Percent complete: 94.5%; Average loss: 2.7224
Iteration: 3782; Percent complete: 94.5%; Average loss: 2.6657
Iteration: 3783; Percent complete: 94.6%; Average loss: 2.7110
Iteration: 3784; Percent complete: 94.6%; Average loss: 2.7535
Iteration: 3785; Percent complete: 94.6%; Average loss: 2.6111
Iteration: 3786; Percent complete: 94.7%; Average loss: 2.7727
Iteration: 3787; Percent complete: 94.7%; Average loss: 2.7030
Iteration: 3788; Percent complete: 94.7%; Average loss: 2.5264
Iteration: 3789; Percent complete: 94.7%; Average loss: 2.8590
Iteration: 3790; Percent complete: 94.8%; Average loss: 2.6402
Iteration: 3791; Percent complete: 94.8%; Average loss: 2.6569
Iteration: 3792; Percent complete: 94.8%; Average loss: 2.7162
Iteration: 3793; Percent complete: 94.8%; Average loss: 2.8032
Iteration: 3794; Percent complete: 94.8%; Average loss: 2.7875
Iteration: 3795; Percent complete: 94.9%; Average loss: 2.5683
Iteration: 3796; Percent complete: 94.9%; Average loss: 2.8229
Iteration: 3797; Percent complete: 94.9%; Average loss: 2.5843
Iteration: 3798; Percent complete: 95.0%; Average loss: 2.9212
Iteration: 3799; Percent complete: 95.0%; Average loss: 2.3624
Iteration: 3800; Percent complete: 95.0%; Average loss: 2.6249
Iteration: 3801; Percent complete: 95.0%; Average loss: 2.7721
Iteration: 3802; Percent complete: 95.0%; Average loss: 2.8521
Iteration: 3803; Percent complete: 95.1%; Average loss: 2.5963
Iteration: 3804; Percent complete: 95.1%; Average loss: 2.6018
Iteration: 3805; Percent complete: 95.1%; Average loss: 2.5974
Iteration: 3806; Percent complete: 95.2%; Average loss: 2.8184
Iteration: 3807; Percent complete: 95.2%; Average loss: 2.6737
Iteration: 3808; Percent complete: 95.2%; Average loss: 2.6513
Iteration: 3809; Percent complete: 95.2%; Average loss: 2.6334
Iteration: 3810; Percent complete: 95.2%; Average loss: 2.8038
Iteration: 3811; Percent complete: 95.3%; Average loss: 2.7135
Iteration: 3812; Percent complete: 95.3%; Average loss: 2.9291
Iteration: 3813; Percent complete: 95.3%; Average loss: 2.6394
Iteration: 3814; Percent complete: 95.3%; Average loss: 2.5216
Iteration: 3815; Percent complete: 95.4%; Average loss: 2.4896
Iteration: 3816; Percent complete: 95.4%; Average loss: 2.7490
Iteration: 3817; Percent complete: 95.4%; Average loss: 2.7820
Iteration: 3818; Percent complete: 95.5%; Average loss: 2.6710
Iteration: 3819; Percent complete: 95.5%; Average loss: 2.8333
Iteration: 3820; Percent complete: 95.5%; Average loss: 2.3522
Iteration: 3821; Percent complete: 95.5%; Average loss: 2.6359
Iteration: 3822; Percent complete: 95.5%; Average loss: 2.6973
Iteration: 3823; Percent complete: 95.6%; Average loss: 2.7681
Iteration: 3824; Percent complete: 95.6%; Average loss: 3.0274
Iteration: 3825; Percent complete: 95.6%; Average loss: 3.0042
Iteration: 3826; Percent complete: 95.7%; Average loss: 2.5439
Iteration: 3827; Percent complete: 95.7%; Average loss: 2.4210
Iteration: 3828; Percent complete: 95.7%; Average loss: 2.6347
Iteration: 3829; Percent complete: 95.7%; Average loss: 2.5957
Iteration: 3830; Percent complete: 95.8%; Average loss: 2.6179
Iteration: 3831; Percent complete: 95.8%; Average loss: 2.7992
Iteration: 3832; Percent complete: 95.8%; Average loss: 2.6113
Iteration: 3833; Percent complete: 95.8%; Average loss: 2.5012
Iteration: 3834; Percent complete: 95.9%; Average loss: 2.5556
Iteration: 3835; Percent complete: 95.9%; Average loss: 2.6886
Iteration: 3836; Percent complete: 95.9%; Average loss: 2.7226
Iteration: 3837; Percent complete: 95.9%; Average loss: 2.7405
Iteration: 3838; Percent complete: 96.0%; Average loss: 2.7059
Iteration: 3839; Percent complete: 96.0%; Average loss: 2.8017
Iteration: 3840; Percent complete: 96.0%; Average loss: 2.5021
Iteration: 3841; Percent complete: 96.0%; Average loss: 2.5082
Iteration: 3842; Percent complete: 96.0%; Average loss: 2.4441
Iteration: 3843; Percent complete: 96.1%; Average loss: 2.8468
Iteration: 3844; Percent complete: 96.1%; Average loss: 2.6596
Iteration: 3845; Percent complete: 96.1%; Average loss: 2.5254
Iteration: 3846; Percent complete: 96.2%; Average loss: 2.7352
Iteration: 3847; Percent complete: 96.2%; Average loss: 2.5914
Iteration: 3848; Percent complete: 96.2%; Average loss: 2.7758
Iteration: 3849; Percent complete: 96.2%; Average loss: 2.7991
Iteration: 3850; Percent complete: 96.2%; Average loss: 2.5284
Iteration: 3851; Percent complete: 96.3%; Average loss: 2.5967
Iteration: 3852; Percent complete: 96.3%; Average loss: 2.6984
Iteration: 3853; Percent complete: 96.3%; Average loss: 2.6186
Iteration: 3854; Percent complete: 96.4%; Average loss: 2.7311
Iteration: 3855; Percent complete: 96.4%; Average loss: 2.6562
Iteration: 3856; Percent complete: 96.4%; Average loss: 2.4253
Iteration: 3857; Percent complete: 96.4%; Average loss: 2.5766
Iteration: 3858; Percent complete: 96.5%; Average loss: 2.6160
Iteration: 3859; Percent complete: 96.5%; Average loss: 2.6859
Iteration: 3860; Percent complete: 96.5%; Average loss: 2.7153
Iteration: 3861; Percent complete: 96.5%; Average loss: 2.5115
Iteration: 3862; Percent complete: 96.5%; Average loss: 2.7500
Iteration: 3863; Percent complete: 96.6%; Average loss: 2.5455
Iteration: 3864; Percent complete: 96.6%; Average loss: 2.6888
Iteration: 3865; Percent complete: 96.6%; Average loss: 2.4964
Iteration: 3866; Percent complete: 96.7%; Average loss: 2.6177
Iteration: 3867; Percent complete: 96.7%; Average loss: 2.5935
Iteration: 3868; Percent complete: 96.7%; Average loss: 2.6079
Iteration: 3869; Percent complete: 96.7%; Average loss: 2.6266
Iteration: 3870; Percent complete: 96.8%; Average loss: 2.5959
Iteration: 3871; Percent complete: 96.8%; Average loss: 2.6474
Iteration: 3872; Percent complete: 96.8%; Average loss: 2.6950
Iteration: 3873; Percent complete: 96.8%; Average loss: 2.4716
Iteration: 3874; Percent complete: 96.9%; Average loss: 2.6527
Iteration: 3875; Percent complete: 96.9%; Average loss: 2.7984
Iteration: 3876; Percent complete: 96.9%; Average loss: 2.5576
Iteration: 3877; Percent complete: 96.9%; Average loss: 2.4601
Iteration: 3878; Percent complete: 97.0%; Average loss: 2.9031
Iteration: 3879; Percent complete: 97.0%; Average loss: 2.6511
Iteration: 3880; Percent complete: 97.0%; Average loss: 2.8801
Iteration: 3881; Percent complete: 97.0%; Average loss: 2.4147
Iteration: 3882; Percent complete: 97.0%; Average loss: 2.5973
Iteration: 3883; Percent complete: 97.1%; Average loss: 2.5859
Iteration: 3884; Percent complete: 97.1%; Average loss: 2.6727
Iteration: 3885; Percent complete: 97.1%; Average loss: 2.6246
Iteration: 3886; Percent complete: 97.2%; Average loss: 2.5993
Iteration: 3887; Percent complete: 97.2%; Average loss: 2.4089
Iteration: 3888; Percent complete: 97.2%; Average loss: 2.6774
Iteration: 3889; Percent complete: 97.2%; Average loss: 2.5232
Iteration: 3890; Percent complete: 97.2%; Average loss: 2.5799
Iteration: 3891; Percent complete: 97.3%; Average loss: 2.5538
Iteration: 3892; Percent complete: 97.3%; Average loss: 2.4889
Iteration: 3893; Percent complete: 97.3%; Average loss: 2.5868
Iteration: 3894; Percent complete: 97.4%; Average loss: 2.7218
Iteration: 3895; Percent complete: 97.4%; Average loss: 2.6642
Iteration: 3896; Percent complete: 97.4%; Average loss: 2.5856
Iteration: 3897; Percent complete: 97.4%; Average loss: 2.5501
Iteration: 3898; Percent complete: 97.5%; Average loss: 2.6937
Iteration: 3899; Percent complete: 97.5%; Average loss: 2.8086
Iteration: 3900; Percent complete: 97.5%; Average loss: 2.7388
Iteration: 3901; Percent complete: 97.5%; Average loss: 2.5753
Iteration: 3902; Percent complete: 97.5%; Average loss: 2.7949
Iteration: 3903; Percent complete: 97.6%; Average loss: 2.7547
Iteration: 3904; Percent complete: 97.6%; Average loss: 2.5188
Iteration: 3905; Percent complete: 97.6%; Average loss: 2.8542
Iteration: 3906; Percent complete: 97.7%; Average loss: 2.4565
Iteration: 3907; Percent complete: 97.7%; Average loss: 2.4833
Iteration: 3908; Percent complete: 97.7%; Average loss: 2.5136
Iteration: 3909; Percent complete: 97.7%; Average loss: 2.8899
Iteration: 3910; Percent complete: 97.8%; Average loss: 2.7563
Iteration: 3911; Percent complete: 97.8%; Average loss: 2.6679
Iteration: 3912; Percent complete: 97.8%; Average loss: 2.5091
Iteration: 3913; Percent complete: 97.8%; Average loss: 2.7079
Iteration: 3914; Percent complete: 97.9%; Average loss: 2.3882
Iteration: 3915; Percent complete: 97.9%; Average loss: 2.6876
Iteration: 3916; Percent complete: 97.9%; Average loss: 2.8179
Iteration: 3917; Percent complete: 97.9%; Average loss: 2.6920
Iteration: 3918; Percent complete: 98.0%; Average loss: 2.5457
Iteration: 3919; Percent complete: 98.0%; Average loss: 2.5011
Iteration: 3920; Percent complete: 98.0%; Average loss: 2.5173
Iteration: 3921; Percent complete: 98.0%; Average loss: 2.4579
Iteration: 3922; Percent complete: 98.0%; Average loss: 2.6517
Iteration: 3923; Percent complete: 98.1%; Average loss: 2.6071
Iteration: 3924; Percent complete: 98.1%; Average loss: 2.6173
Iteration: 3925; Percent complete: 98.1%; Average loss: 2.3913
Iteration: 3926; Percent complete: 98.2%; Average loss: 2.6010
Iteration: 3927; Percent complete: 98.2%; Average loss: 2.6300
Iteration: 3928; Percent complete: 98.2%; Average loss: 2.6307
Iteration: 3929; Percent complete: 98.2%; Average loss: 2.6683
Iteration: 3930; Percent complete: 98.2%; Average loss: 2.4259
Iteration: 3931; Percent complete: 98.3%; Average loss: 2.6590
Iteration: 3932; Percent complete: 98.3%; Average loss: 2.5497
Iteration: 3933; Percent complete: 98.3%; Average loss: 2.5096
Iteration: 3934; Percent complete: 98.4%; Average loss: 2.6638
Iteration: 3935; Percent complete: 98.4%; Average loss: 2.3415
Iteration: 3936; Percent complete: 98.4%; Average loss: 2.7372
Iteration: 3937; Percent complete: 98.4%; Average loss: 2.7666
Iteration: 3938; Percent complete: 98.5%; Average loss: 2.6587
Iteration: 3939; Percent complete: 98.5%; Average loss: 2.6571
Iteration: 3940; Percent complete: 98.5%; Average loss: 2.5981
Iteration: 3941; Percent complete: 98.5%; Average loss: 2.7395
Iteration: 3942; Percent complete: 98.6%; Average loss: 2.5875
Iteration: 3943; Percent complete: 98.6%; Average loss: 2.7834
Iteration: 3944; Percent complete: 98.6%; Average loss: 2.6520
Iteration: 3945; Percent complete: 98.6%; Average loss: 2.5196
Iteration: 3946; Percent complete: 98.7%; Average loss: 2.6321
Iteration: 3947; Percent complete: 98.7%; Average loss: 2.4965
Iteration: 3948; Percent complete: 98.7%; Average loss: 2.6945
Iteration: 3949; Percent complete: 98.7%; Average loss: 2.8068
Iteration: 3950; Percent complete: 98.8%; Average loss: 2.4792
Iteration: 3951; Percent complete: 98.8%; Average loss: 2.7882
Iteration: 3952; Percent complete: 98.8%; Average loss: 2.6095
Iteration: 3953; Percent complete: 98.8%; Average loss: 2.5496
Iteration: 3954; Percent complete: 98.9%; Average loss: 2.5684
Iteration: 3955; Percent complete: 98.9%; Average loss: 2.7776
Iteration: 3956; Percent complete: 98.9%; Average loss: 2.5131
Iteration: 3957; Percent complete: 98.9%; Average loss: 2.5416
Iteration: 3958; Percent complete: 99.0%; Average loss: 2.5243
Iteration: 3959; Percent complete: 99.0%; Average loss: 2.5718
Iteration: 3960; Percent complete: 99.0%; Average loss: 2.5479
Iteration: 3961; Percent complete: 99.0%; Average loss: 2.4459
Iteration: 3962; Percent complete: 99.1%; Average loss: 2.5510
Iteration: 3963; Percent complete: 99.1%; Average loss: 2.7196
Iteration: 3964; Percent complete: 99.1%; Average loss: 2.8936
Iteration: 3965; Percent complete: 99.1%; Average loss: 2.6459
Iteration: 3966; Percent complete: 99.2%; Average loss: 2.4110
Iteration: 3967; Percent complete: 99.2%; Average loss: 2.3959
Iteration: 3968; Percent complete: 99.2%; Average loss: 2.6071
Iteration: 3969; Percent complete: 99.2%; Average loss: 2.5447
Iteration: 3970; Percent complete: 99.2%; Average loss: 2.6053
Iteration: 3971; Percent complete: 99.3%; Average loss: 2.6155
Iteration: 3972; Percent complete: 99.3%; Average loss: 2.7927
Iteration: 3973; Percent complete: 99.3%; Average loss: 2.6370
Iteration: 3974; Percent complete: 99.4%; Average loss: 2.7856
Iteration: 3975; Percent complete: 99.4%; Average loss: 2.6902
Iteration: 3976; Percent complete: 99.4%; Average loss: 2.7160
Iteration: 3977; Percent complete: 99.4%; Average loss: 2.6766
Iteration: 3978; Percent complete: 99.5%; Average loss: 2.5083
Iteration: 3979; Percent complete: 99.5%; Average loss: 2.7127
Iteration: 3980; Percent complete: 99.5%; Average loss: 2.4937
Iteration: 3981; Percent complete: 99.5%; Average loss: 2.4349
Iteration: 3982; Percent complete: 99.6%; Average loss: 2.7078
Iteration: 3983; Percent complete: 99.6%; Average loss: 2.6619
Iteration: 3984; Percent complete: 99.6%; Average loss: 2.6372
Iteration: 3985; Percent complete: 99.6%; Average loss: 2.5567
Iteration: 3986; Percent complete: 99.7%; Average loss: 2.8338
Iteration: 3987; Percent complete: 99.7%; Average loss: 2.6483
Iteration: 3988; Percent complete: 99.7%; Average loss: 2.6850
Iteration: 3989; Percent complete: 99.7%; Average loss: 2.5406
Iteration: 3990; Percent complete: 99.8%; Average loss: 2.5803
Iteration: 3991; Percent complete: 99.8%; Average loss: 2.5839
Iteration: 3992; Percent complete: 99.8%; Average loss: 2.5512
Iteration: 3993; Percent complete: 99.8%; Average loss: 2.6530
Iteration: 3994; Percent complete: 99.9%; Average loss: 2.5612
Iteration: 3995; Percent complete: 99.9%; Average loss: 2.4608
Iteration: 3996; Percent complete: 99.9%; Average loss: 2.4449
Iteration: 3997; Percent complete: 99.9%; Average loss: 2.5732
Iteration: 3998; Percent complete: 100.0%; Average loss: 2.5469
Iteration: 3999; Percent complete: 100.0%; Average loss: 2.4864
Iteration: 4000; Percent complete: 100.0%; Average loss: 2.5328

运行评估#

要与您的模型聊天，请运行以下代码块。

# Set dropout layers to ``eval`` mode
encoder.eval()
decoder.eval()

# Initialize search module
searcher = GreedySearchDecoder(encoder, decoder)

# Begin chatting (uncomment and run the following line to begin)
# evaluateInput(encoder, decoder, searcher, voc)

结论#

各位，本教程到此结束。恭喜，您现在掌握了构建生成式聊天机器人模型的基础知识！如果您感兴趣，可以尝试通过调整模型和训练参数，以及自定义训练模型的数据来定制聊天机器人的行为。

查看其他教程，了解 PyTorch 中更多酷炫的深度学习应用！

脚本总运行时间：（2 分 17.453 秒）

© 版权所有 2024, PyTorch。

使用 PyData Sphinx 主题 0.15.4 构建。

在此页面上
PyTorch 库