Shortcuts

Chatbot Tutorial

Author: Matthew Inkawhich

In this tutorial, we explore a fun and interesting use-case of recurrent sequence-to-sequence models. We will train a simple chatbot using movie scripts from the Cornell Movie-Dialogs Corpus.

Conversational models are a hot topic in artificial intelligence research. Chatbots can be found in a variety of settings, including customer service applications and online helpdesks. These bots are often powered by retrieval-based models, which output predefined responses to questions of certain forms. In a highly restricted domain like a company’s IT helpdesk, these models may be sufficient, however, they are not robust enough for more general use-cases. Teaching a machine to carry out a meaningful conversation with a human in multiple domains is a research question that is far from solved. Recently, the deep learning boom has allowed for powerful generative models like Google’s Neural Conversational Model, which marks a large step towards multi-domain generative conversational models. In this tutorial, we will implement this kind of model in PyTorch.

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 .

Tutorial Highlights

Acknowledgements

This tutorial borrows code from the following sources:

  1. Yuan-Kuei Wu’s pytorch-chatbot implementation: https://github.com/ywk991112/pytorch-chatbot

  2. Sean Robertson’s practical-pytorch seq2seq-translation example: https://github.com/spro/practical-pytorch/tree/master/seq2seq-translation

  3. FloydHub’s Cornell Movie Corpus preprocessing code: https://github.com/floydhub/textutil-preprocess-cornell-movie-corpus

Preparations

To start, Download the data ZIP file here

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

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals

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


USE_CUDA = torch.cuda.is_available()
device = torch.device("cuda" if USE_CUDA else "cpu")

Load & Preprocess Data

The next step is to reformat our data file and load the data into structures that we can work with.

The Cornell Movie-Dialogs Corpus is a rich dataset of movie character dialog:

  • 220,579 conversational exchanges between 10,292 pairs of movie characters

  • 9,035 characters from 617 movies

  • 304,713 total utterances

This dataset is large and diverse, and there is a great variation of language formality, time periods, sentiment, etc. Our hope is that this diversity makes our model robust to many forms of inputs and queries.

First, we’ll take a look at some lines of our datafile to see the original format.

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'

Create formatted data file

For convenience, we’ll create a nicely formatted data file in which each line contains a tab-separated query sentence and a response sentence pair.

The following functions facilitate the parsing of the raw utterances.jsonl data file.

  • loadLinesAndConversations splits each line of the file into a dictionary of lines with fields: lineID, characterID, and text and then groups them into conversations with fields: conversationID, movieID, and lines.

  • extractSentencePairs extracts pairs of sentences from conversations

# 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

Now we’ll call these functions and create the file. We’ll call it 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"

Load and trim data

Our next order of business is to create a vocabulary and load query/response sentence pairs into memory.

Note that we are dealing with sequences of words, which do not have an implicit mapping to a discrete numerical space. Thus, we must create one by mapping each unique word that we encounter in our dataset to an index value.

For this we define a Voc class, which keeps a mapping from words to indexes, a reverse mapping of indexes to words, a count of each word and a total word count. The class provides methods for adding a word to the vocabulary (addWord), adding all words in a sentence (addSentence) and trimming infrequently seen words (trim). More on trimming later.

# 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)

Now we can assemble our vocabulary and query/response sentence pairs. Before we are ready to use this data, we must perform some preprocessing.

First, we must convert the Unicode strings to ASCII using unicodeToAscii. Next, we should convert all letters to lowercase and trim all non-letter characters except for basic punctuation (normalizeString). Finally, to aid in training convergence, we will filter out sentences with length greater than the MAX_LENGTH threshold (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 iff 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 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']

Another tactic that is beneficial to achieving faster convergence during training is trimming rarely used words out of our vocabulary. Decreasing the feature space will also soften the difficulty of the function that the model must learn to approximate. We will do this as a two-step process:

  1. Trim words used under MIN_COUNT threshold using the voc.trim function.

  2. Filter out pairs with trimmed words.

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

Prepare Data for Models

Although we have put a great deal of effort into preparing and massaging our data into a nice vocabulary object and list of sentence pairs, our models will ultimately expect numerical torch tensors as inputs. One way to prepare the processed data for the models can be found in the seq2seq translation tutorial. In that tutorial, we use a batch size of 1, meaning that all we have to do is convert the words in our sentence pairs to their corresponding indexes from the vocabulary and feed this to the models.

However, if you’re interested in speeding up training and/or would like to leverage GPU parallelization capabilities, you will need to train with mini-batches.

Using mini-batches also means that we must be mindful of the variation of sentence length in our batches. To accommodate sentences of different sizes in the same batch, we will make our batched input tensor of shape (max_length, batch_size), where sentences shorter than the max_length are zero padded after an EOS_token.

If we simply convert our English sentences to tensors by converting words to their indexes(indexesFromSentence) and zero-pad, our tensor would have shape (batch_size, max_length) and indexing the first dimension would return a full sequence across all time-steps. However, we need to be able to index our batch along time, and across all sequences in the batch. Therefore, we transpose our input batch shape to (max_length, batch_size), so that indexing across the first dimension returns a time step across all sentences in the batch. We handle this transpose implicitly in the zeroPadding function.

batches

The inputVar function handles the process of converting sentences to tensor, ultimately creating a correctly shaped zero-padded tensor. It also returns a tensor of lengths for each of the sequences in the batch which will be passed to our decoder later.

The outputVar function performs a similar function to inputVar, but instead of returning a lengths tensor, it returns a binary mask tensor and a maximum target sentence length. The binary mask tensor has the same shape as the output target tensor, but every element that is a PAD_token is 0 and all others are 1.

batch2TrainData simply takes a bunch of pairs and returns the input and target tensors using the aforementioned functions.

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([[7811,  186,   86,  132, 1789],
        [2581,  925,   96,   10,   14],
        [  24,  187, 1973,    2,    2],
        [ 132,   14,    6,    0,    0],
        [  24,    2,    2,    0,    0],
        [2839,    0,    0,    0,    0],
        [  85,    0,    0,    0,    0],
        [  14,    0,    0,    0,    0],
        [   2,    0,    0,    0,    0]])
lengths: tensor([9, 5, 5, 3, 3])
target_variable: tensor([[  85,   34, 5901,   24,  280],
        [3930,   14,   14,   64,   10],
        [  62,    2,    2, 2163,    2],
        [1320,    0,    0,    6,    0],
        [  14,    0,    0,    2,    0],
        [  14,    0,    0,    0,    0],
        [  14,    0,    0,    0,    0],
        [   6,    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, False, False,  True, False],
        [ True, False, False,  True, False],
        [ True, False, False, False, False],
        [ True, False, False, False, False],
        [ True, False, False, False, False],
        [ True, False, False, False, False]])
max_target_len: 9

Define Models

Seq2Seq Model

The brains of our chatbot is a sequence-to-sequence (seq2seq) model. The goal of a seq2seq model is to take a variable-length sequence as an input, and return a variable-length sequence as an output using a fixed-sized model.

Sutskever et al. discovered that by using two separate recurrent neural nets together, we can accomplish this task. One RNN acts as an encoder, which encodes a variable length input sequence to a fixed-length context vector. In theory, this context vector (the final hidden layer of the RNN) will contain semantic information about the query sentence that is input to the bot. The second RNN is a decoder, which takes an input word and the context vector, and returns a guess for the next word in the sequence and a hidden state to use in the next iteration.

model

Image source: https://jeddy92.github.io/JEddy92.github.io/ts_seq2seq_intro/

Encoder

The encoder RNN iterates through the input sentence one token (e.g. word) at a time, at each time step outputting an “output” vector and a “hidden state” vector. The hidden state vector is then passed to the next time step, while the output vector is recorded. The encoder transforms the context it saw at each point in the sequence into a set of points in a high-dimensional space, which the decoder will use to generate a meaningful output for the given task.

At the heart of our encoder is a multi-layered Gated Recurrent Unit, invented by Cho et al. in 2014. We will use a bidirectional variant of the GRU, meaning that there are essentially two independent RNNs: one that is fed the input sequence in normal sequential order, and one that is fed the input sequence in reverse order. The outputs of each network are summed at each time step. Using a bidirectional GRU will give us the advantage of encoding both past and future contexts.

Bidirectional RNN:

rnn_bidir

Image source: https://colah.github.io/posts/2015-09-NN-Types-FP/

Note that an embedding layer is used to encode our word indices in an arbitrarily sized feature space. For our models, this layer will map each word to a feature space of size hidden_size. When trained, these values should encode semantic similarity between similar meaning words.

Finally, if passing a padded batch of sequences to an RNN module, we must pack and unpack padding around the RNN pass using nn.utils.rnn.pack_padded_sequence and nn.utils.rnn.pad_packed_sequence respectively.

Computation Graph:

  1. Convert word indexes to embeddings.

  2. Pack padded batch of sequences for RNN module.

  3. Forward pass through GRU.

  4. Unpack padding.

  5. Sum bidirectional GRU outputs.

  6. Return output and final hidden state.

Inputs:

  • input_seq: batch of input sentences; shape=(max_length, batch_size)

  • input_lengths: list of sentence lengths corresponding to each sentence in the batch; shape=(batch_size)

  • hidden: hidden state; shape=(n_layers x num_directions, batch_size, hidden_size)

Outputs:

  • outputs: output features from the last hidden layer of the GRU (sum of bidirectional outputs); shape=(max_length, batch_size, hidden_size)

  • hidden: updated hidden state from GRU; shape=(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 params 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

Decoder

The decoder RNN generates the response sentence in a token-by-token fashion. It uses the encoder’s context vectors, and internal hidden states to generate the next word in the sequence. It continues generating words until it outputs an EOS_token, representing the end of the sentence. A common problem with a vanilla seq2seq decoder is that if we rely solely on the context vector to encode the entire input sequence’s meaning, it is likely that we will have information loss. This is especially the case when dealing with long input sequences, greatly limiting the capability of our decoder.

To combat this, Bahdanau et al. created an “attention mechanism” that allows the decoder to pay attention to certain parts of the input sequence, rather than using the entire fixed context at every step.

At a high level, attention is calculated using the decoder’s current hidden state and the encoder’s outputs. The output attention weights have the same shape as the input sequence, allowing us to multiply them by the encoder outputs, giving us a weighted sum which indicates the parts of encoder output to pay attention to. Sean Robertson’s figure describes this very well:

attn2

Luong et al. improved upon Bahdanau et al.’s groundwork by creating “Global attention”. The key difference is that with “Global attention”, we consider all of the encoder’s hidden states, as opposed to Bahdanau et al.’s “Local attention”, which only considers the encoder’s hidden state from the current time step. Another difference is that with “Global attention”, we calculate attention weights, or energies, using the hidden state of the decoder from the current time step only. Bahdanau et al.’s attention calculation requires knowledge of the decoder’s state from the previous time step. Also, Luong et al. provides various methods to calculate the attention energies between the encoder output and decoder output which are called “score functions”:

scores

where \(h_t\) = current target decoder state and \(\bar{h}_s\) = all encoder states.

Overall, the Global attention mechanism can be summarized by the following figure. Note that we will implement the “Attention Layer” as a separate nn.Module called Attn. The output of this module is a softmax normalized weights tensor of shape (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)

Now that we have defined our attention submodule, we can implement the actual decoder model. For the decoder, we will manually feed our batch one time step at a time. This means that our embedded word tensor and GRU output will both have shape (1, batch_size, hidden_size).

Computation Graph:

  1. Get embedding of current input word.

  2. Forward through unidirectional GRU.

  3. Calculate attention weights from the current GRU output from (2).

  4. Multiply attention weights to encoder outputs to get new “weighted sum” context vector.

  5. Concatenate weighted context vector and GRU output using Luong eq. 5.

  6. Predict next word using Luong eq. 6 (without softmax).

  7. Return output and final hidden state.

Inputs:

  • input_step: one time step (one word) of input sequence batch; shape=(1, batch_size)

  • last_hidden: final hidden layer of GRU; shape=(n_layers x num_directions, batch_size, hidden_size)

  • encoder_outputs: encoder model’s output; shape=(max_length, batch_size, hidden_size)

Outputs:

  • output: softmax normalized tensor giving probabilities of each word being the correct next word in the decoded sequence; shape=(batch_size, voc.num_words)

  • hidden: final hidden state of GRU; shape=(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

Define Training Procedure

Masked loss

Since we are dealing with batches of padded sequences, we cannot simply consider all elements of the tensor when calculating loss. We define maskNLLLoss to calculate our loss based on our decoder’s output tensor, the target tensor, and a binary mask tensor describing the padding of the target tensor. This loss function calculates the average negative log likelihood of the elements that correspond to a 1 in the mask tensor.

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()

Single training iteration

The train function contains the algorithm for a single training iteration (a single batch of inputs).

We will use a couple of clever tricks to aid in convergence:

  • The first trick is using teacher forcing. This means that at some probability, set by teacher_forcing_ratio, we use the current target word as the decoder’s next input rather than using the decoder’s current guess. This technique acts as training wheels for the decoder, aiding in more efficient training. However, teacher forcing can lead to model instability during inference, as the decoder may not have a sufficient chance to truly craft its own output sequences during training. Thus, we must be mindful of how we are setting the teacher_forcing_ratio, and not be fooled by fast convergence.

  • The second trick that we implement is gradient clipping. This is a commonly used technique for countering the “exploding gradient” problem. In essence, by clipping or thresholding gradients to a maximum value, we prevent the gradients from growing exponentially and either overflow (NaN), or overshoot steep cliffs in the cost function.

grad_clip

Image source: Goodfellow et al. Deep Learning. 2016. https://www.deeplearningbook.org/

Sequence of Operations:

  1. Forward pass entire input batch through encoder.

  2. Initialize decoder inputs as SOS_token, and hidden state as the encoder’s final hidden state.

  3. Forward input batch sequence through decoder one time step at a time.

  4. If teacher forcing: set next decoder input as the current target; else: set next decoder input as current decoder output.

  5. Calculate and accumulate loss.

  6. Perform backpropagation.

  7. Clip gradients.

  8. Update encoder and decoder model parameters.

Note

PyTorch’s RNN modules (RNN, LSTM, GRU) can be used like any other non-recurrent layers by simply passing them the entire input sequence (or batch of sequences). We use the GRU layer like this in the encoder. The reality is that under the hood, there is an iterative process looping over each time step calculating hidden states. Alternatively, you can run these modules one time-step at a time. In this case, we manually loop over the sequences during the training process like we must do for the decoder model. As long as you maintain the correct conceptual model of these modules, implementing sequential models can be very straightforward.

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 backpropatation
    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

Training iterations

It is finally time to tie the full training procedure together with the data. The trainIters function is responsible for running n_iterations of training given the passed models, optimizers, data, etc. This function is quite self explanatory, as we have done the heavy lifting with the train function.

One thing to note is that when we save our model, we save a tarball containing the encoder and decoder state_dicts (parameters), the optimizers’ state_dicts, the loss, the iteration, etc. Saving the model in this way will give us the ultimate flexibility with the checkpoint. After loading a checkpoint, we will be able to use the model parameters to run inference, or we can continue training right where we left off.

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')))

Define Evaluation

After training a model, we want to be able to talk to the bot ourselves. First, we must define how we want the model to decode the encoded input.

Greedy decoding

Greedy decoding is the decoding method that we use during training when we are NOT using teacher forcing. In other words, for each time step, we simply choose the word from decoder_output with the highest softmax value. This decoding method is optimal on a single time-step level.

To facilitate the greedy decoding operation, we define a GreedySearchDecoder class. When run, an object of this class takes an input sequence (input_seq) of shape (input_seq length, 1), a scalar input length (input_length) tensor, and a max_length to bound the response sentence length. The input sentence is evaluated using the following computational graph:

Computation Graph:

  1. Forward input through encoder model.

  2. Prepare encoder’s final hidden layer to be first hidden input to the decoder.

  3. Initialize decoder’s first input as SOS_token.

  4. Initialize tensors to append decoded words to.

  5. Iteratively decode one word token at a time:
    1. Forward pass through decoder.

    2. Obtain most likely word token and its softmax score.

    3. Record token and score.

    4. Prepare current token to be next decoder input.

  6. Return collections of word tokens and scores.

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[: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

Evaluate my text

Now that we have our decoding method defined, we can write functions for evaluating a string input sentence. The evaluate function manages the low-level process of handling the input sentence. We first format the sentence as an input batch of word indexes with batch_size==1. We do this by converting the words of the sentence to their corresponding indexes, and transposing the dimensions to prepare the tensor for our models. We also create a lengths tensor which contains the length of our input sentence. In this case, lengths is scalar because we are only evaluating one sentence at a time (batch_size==1). Next, we obtain the decoded response sentence tensor using our GreedySearchDecoder object (searcher). Finally, we convert the response’s indexes to words and return the list of decoded words.

evaluateInput acts as the user interface for our chatbot. When called, an input text field will spawn in which we can enter our query sentence. After typing our input sentence and pressing Enter, our text is normalized in the same way as our training data, and is ultimately fed to the evaluate function to obtain a decoded output sentence. We loop this process, so we can keep chatting with our bot until we enter either “q” or “quit”.

Finally, if a sentence is entered that contains a word that is not in the vocabulary, we handle this gracefully by printing an error message and prompting the user to enter another sentence.

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.")

Run Model

Finally, it is time to run our model!

Regardless of whether we want to train or test the chatbot model, we must initialize the individual encoder and decoder models. In the following block, we set our desired configurations, choose to start from scratch or set a checkpoint to load from, and build and initialize the models. Feel free to play with different model configurations to optimize performance.

# 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
#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!

Run Training

Run the following block if you want to train the model.

First we set training parameters, then we initialize our optimizers, and finally we call the trainIters function to run our training iterations.

# 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 cuda, configure cuda to call
for state in encoder_optimizer.state.values():
    for k, v in state.items():
        if isinstance(v, torch.Tensor):
            state[k] = v.cuda()

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

# 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: 8.9577
Iteration: 2; Percent complete: 0.1%; Average loss: 8.8478
Iteration: 3; Percent complete: 0.1%; Average loss: 8.6441
Iteration: 4; Percent complete: 0.1%; Average loss: 8.3520
Iteration: 5; Percent complete: 0.1%; Average loss: 7.8956
Iteration: 6; Percent complete: 0.1%; Average loss: 7.4060
Iteration: 7; Percent complete: 0.2%; Average loss: 7.1124
Iteration: 8; Percent complete: 0.2%; Average loss: 7.0317
Iteration: 9; Percent complete: 0.2%; Average loss: 6.9958
Iteration: 10; Percent complete: 0.2%; Average loss: 6.9493
Iteration: 11; Percent complete: 0.3%; Average loss: 6.1319
Iteration: 12; Percent complete: 0.3%; Average loss: 5.8829
Iteration: 13; Percent complete: 0.3%; Average loss: 5.3574
Iteration: 14; Percent complete: 0.4%; Average loss: 5.5890
Iteration: 15; Percent complete: 0.4%; Average loss: 5.5436
Iteration: 16; Percent complete: 0.4%; Average loss: 5.3420
Iteration: 17; Percent complete: 0.4%; Average loss: 5.3514
Iteration: 18; Percent complete: 0.4%; Average loss: 5.0247
Iteration: 19; Percent complete: 0.5%; Average loss: 4.9170
Iteration: 20; Percent complete: 0.5%; Average loss: 5.0501
Iteration: 21; Percent complete: 0.5%; Average loss: 4.8626
Iteration: 22; Percent complete: 0.5%; Average loss: 5.0103
Iteration: 23; Percent complete: 0.6%; Average loss: 4.8578
Iteration: 24; Percent complete: 0.6%; Average loss: 4.9791
Iteration: 25; Percent complete: 0.6%; Average loss: 4.8883
Iteration: 26; Percent complete: 0.7%; Average loss: 4.7079
Iteration: 27; Percent complete: 0.7%; Average loss: 4.8833
Iteration: 28; Percent complete: 0.7%; Average loss: 4.6881
Iteration: 29; Percent complete: 0.7%; Average loss: 4.6613
Iteration: 30; Percent complete: 0.8%; Average loss: 4.7378
Iteration: 31; Percent complete: 0.8%; Average loss: 4.8833
Iteration: 32; Percent complete: 0.8%; Average loss: 4.8396
Iteration: 33; Percent complete: 0.8%; Average loss: 4.6109
Iteration: 34; Percent complete: 0.9%; Average loss: 4.7441
Iteration: 35; Percent complete: 0.9%; Average loss: 4.7439
Iteration: 36; Percent complete: 0.9%; Average loss: 4.7423
Iteration: 37; Percent complete: 0.9%; Average loss: 4.8129
Iteration: 38; Percent complete: 0.9%; Average loss: 4.8241
Iteration: 39; Percent complete: 1.0%; Average loss: 4.8009
Iteration: 40; Percent complete: 1.0%; Average loss: 4.7653
Iteration: 41; Percent complete: 1.0%; Average loss: 4.6611
Iteration: 42; Percent complete: 1.1%; Average loss: 4.7144
Iteration: 43; Percent complete: 1.1%; Average loss: 4.7548
Iteration: 44; Percent complete: 1.1%; Average loss: 4.6137
Iteration: 45; Percent complete: 1.1%; Average loss: 4.5211
Iteration: 46; Percent complete: 1.1%; Average loss: 4.8810
Iteration: 47; Percent complete: 1.2%; Average loss: 4.6554
Iteration: 48; Percent complete: 1.2%; Average loss: 4.7230
Iteration: 49; Percent complete: 1.2%; Average loss: 4.7542
Iteration: 50; Percent complete: 1.2%; Average loss: 4.7461
Iteration: 51; Percent complete: 1.3%; Average loss: 4.4936
Iteration: 52; Percent complete: 1.3%; Average loss: 4.7791
Iteration: 53; Percent complete: 1.3%; Average loss: 4.5616
Iteration: 54; Percent complete: 1.4%; Average loss: 4.5895
Iteration: 55; Percent complete: 1.4%; Average loss: 4.4248
Iteration: 56; Percent complete: 1.4%; Average loss: 4.7711
Iteration: 57; Percent complete: 1.4%; Average loss: 4.5278
Iteration: 58; Percent complete: 1.5%; Average loss: 4.6920
Iteration: 59; Percent complete: 1.5%; Average loss: 4.7376
Iteration: 60; Percent complete: 1.5%; Average loss: 4.4090
Iteration: 61; Percent complete: 1.5%; Average loss: 4.7043
Iteration: 62; Percent complete: 1.6%; Average loss: 4.6161
Iteration: 63; Percent complete: 1.6%; Average loss: 4.6926
Iteration: 64; Percent complete: 1.6%; Average loss: 4.5066
Iteration: 65; Percent complete: 1.6%; Average loss: 4.5668
Iteration: 66; Percent complete: 1.7%; Average loss: 4.3899
Iteration: 67; Percent complete: 1.7%; Average loss: 4.5143
Iteration: 68; Percent complete: 1.7%; Average loss: 4.6151
Iteration: 69; Percent complete: 1.7%; Average loss: 4.7697
Iteration: 70; Percent complete: 1.8%; Average loss: 4.4050
Iteration: 71; Percent complete: 1.8%; Average loss: 4.3362
Iteration: 72; Percent complete: 1.8%; Average loss: 4.3104
Iteration: 73; Percent complete: 1.8%; Average loss: 4.6098
Iteration: 74; Percent complete: 1.8%; Average loss: 4.5180
Iteration: 75; Percent complete: 1.9%; Average loss: 4.6648
Iteration: 76; Percent complete: 1.9%; Average loss: 4.5536
Iteration: 77; Percent complete: 1.9%; Average loss: 4.4562
Iteration: 78; Percent complete: 1.9%; Average loss: 4.4667
Iteration: 79; Percent complete: 2.0%; Average loss: 4.1920
Iteration: 80; Percent complete: 2.0%; Average loss: 4.5305
Iteration: 81; Percent complete: 2.0%; Average loss: 4.4479
Iteration: 82; Percent complete: 2.1%; Average loss: 4.5120
Iteration: 83; Percent complete: 2.1%; Average loss: 4.5762
Iteration: 84; Percent complete: 2.1%; Average loss: 4.2781
Iteration: 85; Percent complete: 2.1%; Average loss: 4.4609
Iteration: 86; Percent complete: 2.1%; Average loss: 4.2480
Iteration: 87; Percent complete: 2.2%; Average loss: 4.6070
Iteration: 88; Percent complete: 2.2%; Average loss: 4.4771
Iteration: 89; Percent complete: 2.2%; Average loss: 4.4956
Iteration: 90; Percent complete: 2.2%; Average loss: 4.5954
Iteration: 91; Percent complete: 2.3%; Average loss: 4.3444
Iteration: 92; Percent complete: 2.3%; Average loss: 4.6681
Iteration: 93; Percent complete: 2.3%; Average loss: 4.6124
Iteration: 94; Percent complete: 2.4%; Average loss: 4.5809
Iteration: 95; Percent complete: 2.4%; Average loss: 4.4711
Iteration: 96; Percent complete: 2.4%; Average loss: 4.6990
Iteration: 97; Percent complete: 2.4%; Average loss: 4.6677
Iteration: 98; Percent complete: 2.5%; Average loss: 4.5701
Iteration: 99; Percent complete: 2.5%; Average loss: 4.5366
Iteration: 100; Percent complete: 2.5%; Average loss: 4.4524
Iteration: 101; Percent complete: 2.5%; Average loss: 4.4822
Iteration: 102; Percent complete: 2.5%; Average loss: 4.3321
Iteration: 103; Percent complete: 2.6%; Average loss: 4.4066
Iteration: 104; Percent complete: 2.6%; Average loss: 4.4683
Iteration: 105; Percent complete: 2.6%; Average loss: 4.4681
Iteration: 106; Percent complete: 2.6%; Average loss: 4.2972
Iteration: 107; Percent complete: 2.7%; Average loss: 4.4215
Iteration: 108; Percent complete: 2.7%; Average loss: 4.5836
Iteration: 109; Percent complete: 2.7%; Average loss: 4.5267
Iteration: 110; Percent complete: 2.8%; Average loss: 4.3515
Iteration: 111; Percent complete: 2.8%; Average loss: 4.3383
Iteration: 112; Percent complete: 2.8%; Average loss: 4.4202
Iteration: 113; Percent complete: 2.8%; Average loss: 4.4328
Iteration: 114; Percent complete: 2.9%; Average loss: 4.3722
Iteration: 115; Percent complete: 2.9%; Average loss: 4.2465
Iteration: 116; Percent complete: 2.9%; Average loss: 4.2519
Iteration: 117; Percent complete: 2.9%; Average loss: 4.3193
Iteration: 118; Percent complete: 2.9%; Average loss: 4.5584
Iteration: 119; Percent complete: 3.0%; Average loss: 4.2162
Iteration: 120; Percent complete: 3.0%; Average loss: 4.5967
Iteration: 121; Percent complete: 3.0%; Average loss: 4.2325
Iteration: 122; Percent complete: 3.0%; Average loss: 4.5564
Iteration: 123; Percent complete: 3.1%; Average loss: 4.4842
Iteration: 124; Percent complete: 3.1%; Average loss: 4.4240
Iteration: 125; Percent complete: 3.1%; Average loss: 4.1497
Iteration: 126; Percent complete: 3.1%; Average loss: 4.3774
Iteration: 127; Percent complete: 3.2%; Average loss: 4.3348
Iteration: 128; Percent complete: 3.2%; Average loss: 4.2659
Iteration: 129; Percent complete: 3.2%; Average loss: 4.5492
Iteration: 130; Percent complete: 3.2%; Average loss: 4.2790
Iteration: 131; Percent complete: 3.3%; Average loss: 4.3678
Iteration: 132; Percent complete: 3.3%; Average loss: 4.6730
Iteration: 133; Percent complete: 3.3%; Average loss: 4.3277
Iteration: 134; Percent complete: 3.4%; Average loss: 4.3593
Iteration: 135; Percent complete: 3.4%; Average loss: 4.4202
Iteration: 136; Percent complete: 3.4%; Average loss: 4.2632
Iteration: 137; Percent complete: 3.4%; Average loss: 4.0299
Iteration: 138; Percent complete: 3.5%; Average loss: 4.2048
Iteration: 139; Percent complete: 3.5%; Average loss: 4.2275
Iteration: 140; Percent complete: 3.5%; Average loss: 3.9120
Iteration: 141; Percent complete: 3.5%; Average loss: 4.3891
Iteration: 142; Percent complete: 3.5%; Average loss: 4.1807
Iteration: 143; Percent complete: 3.6%; Average loss: 4.3106
Iteration: 144; Percent complete: 3.6%; Average loss: 4.1574
Iteration: 145; Percent complete: 3.6%; Average loss: 4.3570
Iteration: 146; Percent complete: 3.6%; Average loss: 4.2581
Iteration: 147; Percent complete: 3.7%; Average loss: 4.2648
Iteration: 148; Percent complete: 3.7%; Average loss: 4.1256
Iteration: 149; Percent complete: 3.7%; Average loss: 4.3575
Iteration: 150; Percent complete: 3.8%; Average loss: 4.2496
Iteration: 151; Percent complete: 3.8%; Average loss: 4.3019
Iteration: 152; Percent complete: 3.8%; Average loss: 4.3497
Iteration: 153; Percent complete: 3.8%; Average loss: 4.5071
Iteration: 154; Percent complete: 3.9%; Average loss: 4.1937
Iteration: 155; Percent complete: 3.9%; Average loss: 4.0939
Iteration: 156; Percent complete: 3.9%; Average loss: 4.2265
Iteration: 157; Percent complete: 3.9%; Average loss: 4.3297
Iteration: 158; Percent complete: 4.0%; Average loss: 4.3847
Iteration: 159; Percent complete: 4.0%; Average loss: 4.2416
Iteration: 160; Percent complete: 4.0%; Average loss: 4.0889
Iteration: 161; Percent complete: 4.0%; Average loss: 4.3328
Iteration: 162; Percent complete: 4.0%; Average loss: 4.1369
Iteration: 163; Percent complete: 4.1%; Average loss: 4.2246
Iteration: 164; Percent complete: 4.1%; Average loss: 4.1169
Iteration: 165; Percent complete: 4.1%; Average loss: 4.3033
Iteration: 166; Percent complete: 4.2%; Average loss: 4.1309
Iteration: 167; Percent complete: 4.2%; Average loss: 4.0056
Iteration: 168; Percent complete: 4.2%; Average loss: 4.0921
Iteration: 169; Percent complete: 4.2%; Average loss: 4.1412
Iteration: 170; Percent complete: 4.2%; Average loss: 3.7545
Iteration: 171; Percent complete: 4.3%; Average loss: 4.4137
Iteration: 172; Percent complete: 4.3%; Average loss: 4.1447
Iteration: 173; Percent complete: 4.3%; Average loss: 4.2317
Iteration: 174; Percent complete: 4.3%; Average loss: 4.2344
Iteration: 175; Percent complete: 4.4%; Average loss: 3.9041
Iteration: 176; Percent complete: 4.4%; Average loss: 3.9120
Iteration: 177; Percent complete: 4.4%; Average loss: 4.2152
Iteration: 178; Percent complete: 4.5%; Average loss: 4.3937
Iteration: 179; Percent complete: 4.5%; Average loss: 3.9123
Iteration: 180; Percent complete: 4.5%; Average loss: 4.4875
Iteration: 181; Percent complete: 4.5%; Average loss: 4.0667
Iteration: 182; Percent complete: 4.5%; Average loss: 3.9944
Iteration: 183; Percent complete: 4.6%; Average loss: 4.1984
Iteration: 184; Percent complete: 4.6%; Average loss: 4.1860
Iteration: 185; Percent complete: 4.6%; Average loss: 4.2536
Iteration: 186; Percent complete: 4.7%; Average loss: 4.1357
Iteration: 187; Percent complete: 4.7%; Average loss: 4.0858
Iteration: 188; Percent complete: 4.7%; Average loss: 4.3693
Iteration: 189; Percent complete: 4.7%; Average loss: 4.2968
Iteration: 190; Percent complete: 4.8%; Average loss: 4.0624
Iteration: 191; Percent complete: 4.8%; Average loss: 4.0982
Iteration: 192; Percent complete: 4.8%; Average loss: 4.0727
Iteration: 193; Percent complete: 4.8%; Average loss: 4.1386
Iteration: 194; Percent complete: 4.9%; Average loss: 4.1181
Iteration: 195; Percent complete: 4.9%; Average loss: 4.0722
Iteration: 196; Percent complete: 4.9%; Average loss: 4.0469
Iteration: 197; Percent complete: 4.9%; Average loss: 4.2784
Iteration: 198; Percent complete: 5.0%; Average loss: 4.1116
Iteration: 199; Percent complete: 5.0%; Average loss: 4.0474
Iteration: 200; Percent complete: 5.0%; Average loss: 4.2721
Iteration: 201; Percent complete: 5.0%; Average loss: 4.2097
Iteration: 202; Percent complete: 5.1%; Average loss: 4.3014
Iteration: 203; Percent complete: 5.1%; Average loss: 4.2025
Iteration: 204; Percent complete: 5.1%; Average loss: 4.1446
Iteration: 205; Percent complete: 5.1%; Average loss: 4.2650
Iteration: 206; Percent complete: 5.1%; Average loss: 4.1110
Iteration: 207; Percent complete: 5.2%; Average loss: 4.0878
Iteration: 208; Percent complete: 5.2%; Average loss: 3.9701
Iteration: 209; Percent complete: 5.2%; Average loss: 4.1672
Iteration: 210; Percent complete: 5.2%; Average loss: 4.2173
Iteration: 211; Percent complete: 5.3%; Average loss: 4.0548
Iteration: 212; Percent complete: 5.3%; Average loss: 3.8820
Iteration: 213; Percent complete: 5.3%; Average loss: 4.0837
Iteration: 214; Percent complete: 5.3%; Average loss: 4.1166
Iteration: 215; Percent complete: 5.4%; Average loss: 4.0493
Iteration: 216; Percent complete: 5.4%; Average loss: 3.9350
Iteration: 217; Percent complete: 5.4%; Average loss: 4.0892
Iteration: 218; Percent complete: 5.5%; Average loss: 4.1439
Iteration: 219; Percent complete: 5.5%; Average loss: 3.9034
Iteration: 220; Percent complete: 5.5%; Average loss: 4.1197
Iteration: 221; Percent complete: 5.5%; Average loss: 4.2393
Iteration: 222; Percent complete: 5.5%; Average loss: 4.3288
Iteration: 223; Percent complete: 5.6%; Average loss: 4.0723
Iteration: 224; Percent complete: 5.6%; Average loss: 3.9849
Iteration: 225; Percent complete: 5.6%; Average loss: 4.0015
Iteration: 226; Percent complete: 5.7%; Average loss: 4.3345
Iteration: 227; Percent complete: 5.7%; Average loss: 4.2265
Iteration: 228; Percent complete: 5.7%; Average loss: 3.9398
Iteration: 229; Percent complete: 5.7%; Average loss: 4.1795
Iteration: 230; Percent complete: 5.8%; Average loss: 3.8882
Iteration: 231; Percent complete: 5.8%; Average loss: 3.9904
Iteration: 232; Percent complete: 5.8%; Average loss: 4.0183
Iteration: 233; Percent complete: 5.8%; Average loss: 3.8845
Iteration: 234; Percent complete: 5.9%; Average loss: 4.0219
Iteration: 235; Percent complete: 5.9%; Average loss: 4.2129
Iteration: 236; Percent complete: 5.9%; Average loss: 4.0585
Iteration: 237; Percent complete: 5.9%; Average loss: 4.0582
Iteration: 238; Percent complete: 5.9%; Average loss: 3.9499
Iteration: 239; Percent complete: 6.0%; Average loss: 4.1006
Iteration: 240; Percent complete: 6.0%; Average loss: 4.2461
Iteration: 241; Percent complete: 6.0%; Average loss: 4.2531
Iteration: 242; Percent complete: 6.0%; Average loss: 4.0780
Iteration: 243; Percent complete: 6.1%; Average loss: 3.7833
Iteration: 244; Percent complete: 6.1%; Average loss: 4.1149
Iteration: 245; Percent complete: 6.1%; Average loss: 3.9838
Iteration: 246; Percent complete: 6.2%; Average loss: 4.2387
Iteration: 247; Percent complete: 6.2%; Average loss: 3.9032
Iteration: 248; Percent complete: 6.2%; Average loss: 4.0694
Iteration: 249; Percent complete: 6.2%; Average loss: 3.9232
Iteration: 250; Percent complete: 6.2%; Average loss: 3.8756
Iteration: 251; Percent complete: 6.3%; Average loss: 3.8740
Iteration: 252; Percent complete: 6.3%; Average loss: 4.0005
Iteration: 253; Percent complete: 6.3%; Average loss: 3.8898
Iteration: 254; Percent complete: 6.3%; Average loss: 3.9524
Iteration: 255; Percent complete: 6.4%; Average loss: 4.0130
Iteration: 256; Percent complete: 6.4%; Average loss: 4.1196
Iteration: 257; Percent complete: 6.4%; Average loss: 4.0423
Iteration: 258; Percent complete: 6.5%; Average loss: 3.8158
Iteration: 259; Percent complete: 6.5%; Average loss: 3.9823
Iteration: 260; Percent complete: 6.5%; Average loss: 3.7922
Iteration: 261; Percent complete: 6.5%; Average loss: 4.0099
Iteration: 262; Percent complete: 6.6%; Average loss: 4.0226
Iteration: 263; Percent complete: 6.6%; Average loss: 3.8020
Iteration: 264; Percent complete: 6.6%; Average loss: 3.9969
Iteration: 265; Percent complete: 6.6%; Average loss: 4.0535
Iteration: 266; Percent complete: 6.7%; Average loss: 4.2032
Iteration: 267; Percent complete: 6.7%; Average loss: 4.1416
Iteration: 268; Percent complete: 6.7%; Average loss: 4.0353
Iteration: 269; Percent complete: 6.7%; Average loss: 4.1106
Iteration: 270; Percent complete: 6.8%; Average loss: 3.9944
Iteration: 271; Percent complete: 6.8%; Average loss: 4.2950
Iteration: 272; Percent complete: 6.8%; Average loss: 4.2719
Iteration: 273; Percent complete: 6.8%; Average loss: 3.8977
Iteration: 274; Percent complete: 6.9%; Average loss: 3.7772
Iteration: 275; Percent complete: 6.9%; Average loss: 4.1655
Iteration: 276; Percent complete: 6.9%; Average loss: 3.8115
Iteration: 277; Percent complete: 6.9%; Average loss: 3.8313
Iteration: 278; Percent complete: 7.0%; Average loss: 4.2113
Iteration: 279; Percent complete: 7.0%; Average loss: 3.9176
Iteration: 280; Percent complete: 7.0%; Average loss: 4.1361
Iteration: 281; Percent complete: 7.0%; Average loss: 3.8968
Iteration: 282; Percent complete: 7.0%; Average loss: 3.7135
Iteration: 283; Percent complete: 7.1%; Average loss: 3.9953
Iteration: 284; Percent complete: 7.1%; Average loss: 3.9219
Iteration: 285; Percent complete: 7.1%; Average loss: 4.0048
Iteration: 286; Percent complete: 7.1%; Average loss: 4.1548
Iteration: 287; Percent complete: 7.2%; Average loss: 4.1632
Iteration: 288; Percent complete: 7.2%; Average loss: 3.8992
Iteration: 289; Percent complete: 7.2%; Average loss: 3.8496
Iteration: 290; Percent complete: 7.2%; Average loss: 4.1029
Iteration: 291; Percent complete: 7.3%; Average loss: 3.7104
Iteration: 292; Percent complete: 7.3%; Average loss: 3.7358
Iteration: 293; Percent complete: 7.3%; Average loss: 3.9897
Iteration: 294; Percent complete: 7.3%; Average loss: 4.0086
Iteration: 295; Percent complete: 7.4%; Average loss: 3.9679
Iteration: 296; Percent complete: 7.4%; Average loss: 3.9783
Iteration: 297; Percent complete: 7.4%; Average loss: 4.0035
Iteration: 298; Percent complete: 7.4%; Average loss: 3.8489
Iteration: 299; Percent complete: 7.5%; Average loss: 4.0252
Iteration: 300; Percent complete: 7.5%; Average loss: 3.8615
Iteration: 301; Percent complete: 7.5%; Average loss: 4.1507
Iteration: 302; Percent complete: 7.5%; Average loss: 4.2074
Iteration: 303; Percent complete: 7.6%; Average loss: 3.9969
Iteration: 304; Percent complete: 7.6%; Average loss: 4.1543
Iteration: 305; Percent complete: 7.6%; Average loss: 3.7555
Iteration: 306; Percent complete: 7.6%; Average loss: 3.7588
Iteration: 307; Percent complete: 7.7%; Average loss: 3.8901
Iteration: 308; Percent complete: 7.7%; Average loss: 3.9048
Iteration: 309; Percent complete: 7.7%; Average loss: 3.6640
Iteration: 310; Percent complete: 7.8%; Average loss: 3.9327
Iteration: 311; Percent complete: 7.8%; Average loss: 3.9962
Iteration: 312; Percent complete: 7.8%; Average loss: 3.7578
Iteration: 313; Percent complete: 7.8%; Average loss: 3.9791
Iteration: 314; Percent complete: 7.8%; Average loss: 3.8866
Iteration: 315; Percent complete: 7.9%; Average loss: 3.8616
Iteration: 316; Percent complete: 7.9%; Average loss: 3.9084
Iteration: 317; Percent complete: 7.9%; Average loss: 4.0325
Iteration: 318; Percent complete: 8.0%; Average loss: 3.9576
Iteration: 319; Percent complete: 8.0%; Average loss: 3.9994
Iteration: 320; Percent complete: 8.0%; Average loss: 4.0809
Iteration: 321; Percent complete: 8.0%; Average loss: 3.7020
Iteration: 322; Percent complete: 8.1%; Average loss: 3.9604
Iteration: 323; Percent complete: 8.1%; Average loss: 3.9150
Iteration: 324; Percent complete: 8.1%; Average loss: 3.9143
Iteration: 325; Percent complete: 8.1%; Average loss: 3.9215
Iteration: 326; Percent complete: 8.2%; Average loss: 3.8734
Iteration: 327; Percent complete: 8.2%; Average loss: 4.0688
Iteration: 328; Percent complete: 8.2%; Average loss: 3.8310
Iteration: 329; Percent complete: 8.2%; Average loss: 3.9041
Iteration: 330; Percent complete: 8.2%; Average loss: 4.1323
Iteration: 331; Percent complete: 8.3%; Average loss: 3.9040
Iteration: 332; Percent complete: 8.3%; Average loss: 3.9340
Iteration: 333; Percent complete: 8.3%; Average loss: 4.0727
Iteration: 334; Percent complete: 8.3%; Average loss: 3.8961
Iteration: 335; Percent complete: 8.4%; Average loss: 3.6956
Iteration: 336; Percent complete: 8.4%; Average loss: 3.8647
Iteration: 337; Percent complete: 8.4%; Average loss: 4.1740
Iteration: 338; Percent complete: 8.5%; Average loss: 3.6610
Iteration: 339; Percent complete: 8.5%; Average loss: 3.9712
Iteration: 340; Percent complete: 8.5%; Average loss: 3.7858
Iteration: 341; Percent complete: 8.5%; Average loss: 3.7333
Iteration: 342; Percent complete: 8.6%; Average loss: 3.9014
Iteration: 343; Percent complete: 8.6%; Average loss: 3.9452
Iteration: 344; Percent complete: 8.6%; Average loss: 3.8430
Iteration: 345; Percent complete: 8.6%; Average loss: 3.8878
Iteration: 346; Percent complete: 8.6%; Average loss: 3.6782
Iteration: 347; Percent complete: 8.7%; Average loss: 4.0744
Iteration: 348; Percent complete: 8.7%; Average loss: 3.8816
Iteration: 349; Percent complete: 8.7%; Average loss: 3.9740
Iteration: 350; Percent complete: 8.8%; Average loss: 3.9343
Iteration: 351; Percent complete: 8.8%; Average loss: 3.9442
Iteration: 352; Percent complete: 8.8%; Average loss: 3.8620
Iteration: 353; Percent complete: 8.8%; Average loss: 3.7489
Iteration: 354; Percent complete: 8.8%; Average loss: 3.5421
Iteration: 355; Percent complete: 8.9%; Average loss: 3.7942
Iteration: 356; Percent complete: 8.9%; Average loss: 4.0969
Iteration: 357; Percent complete: 8.9%; Average loss: 3.7684
Iteration: 358; Percent complete: 8.9%; Average loss: 3.7660
Iteration: 359; Percent complete: 9.0%; Average loss: 4.0253
Iteration: 360; Percent complete: 9.0%; Average loss: 3.9609
Iteration: 361; Percent complete: 9.0%; Average loss: 4.0578
Iteration: 362; Percent complete: 9.0%; Average loss: 4.1455
Iteration: 363; Percent complete: 9.1%; Average loss: 3.9409
Iteration: 364; Percent complete: 9.1%; Average loss: 3.8164
Iteration: 365; Percent complete: 9.1%; Average loss: 4.1810
Iteration: 366; Percent complete: 9.2%; Average loss: 4.1057
Iteration: 367; Percent complete: 9.2%; Average loss: 4.0828
Iteration: 368; Percent complete: 9.2%; Average loss: 3.9430
Iteration: 369; Percent complete: 9.2%; Average loss: 3.8564
Iteration: 370; Percent complete: 9.2%; Average loss: 3.6531
Iteration: 371; Percent complete: 9.3%; Average loss: 3.9398
Iteration: 372; Percent complete: 9.3%; Average loss: 3.9459
Iteration: 373; Percent complete: 9.3%; Average loss: 3.9446
Iteration: 374; Percent complete: 9.3%; Average loss: 3.8153
Iteration: 375; Percent complete: 9.4%; Average loss: 3.8656
Iteration: 376; Percent complete: 9.4%; Average loss: 3.9978
Iteration: 377; Percent complete: 9.4%; Average loss: 3.7329
Iteration: 378; Percent complete: 9.4%; Average loss: 3.8581
Iteration: 379; Percent complete: 9.5%; Average loss: 3.8538
Iteration: 380; Percent complete: 9.5%; Average loss: 3.6356
Iteration: 381; Percent complete: 9.5%; Average loss: 3.7338
Iteration: 382; Percent complete: 9.6%; Average loss: 3.6993
Iteration: 383; Percent complete: 9.6%; Average loss: 3.9925
Iteration: 384; Percent complete: 9.6%; Average loss: 3.8905
Iteration: 385; Percent complete: 9.6%; Average loss: 3.7942
Iteration: 386; Percent complete: 9.7%; Average loss: 3.6367
Iteration: 387; Percent complete: 9.7%; Average loss: 3.5780
Iteration: 388; Percent complete: 9.7%; Average loss: 4.1032
Iteration: 389; Percent complete: 9.7%; Average loss: 3.8633
Iteration: 390; Percent complete: 9.8%; Average loss: 3.6750
Iteration: 391; Percent complete: 9.8%; Average loss: 3.6950
Iteration: 392; Percent complete: 9.8%; Average loss: 3.6973
Iteration: 393; Percent complete: 9.8%; Average loss: 3.8940
Iteration: 394; Percent complete: 9.8%; Average loss: 3.7647
Iteration: 395; Percent complete: 9.9%; Average loss: 3.8767
Iteration: 396; Percent complete: 9.9%; Average loss: 3.9807
Iteration: 397; Percent complete: 9.9%; Average loss: 3.7955
Iteration: 398; Percent complete: 10.0%; Average loss: 3.7716
Iteration: 399; Percent complete: 10.0%; Average loss: 3.8848
Iteration: 400; Percent complete: 10.0%; Average loss: 4.0531
Iteration: 401; Percent complete: 10.0%; Average loss: 3.9449
Iteration: 402; Percent complete: 10.1%; Average loss: 3.8826
Iteration: 403; Percent complete: 10.1%; Average loss: 3.8065
Iteration: 404; Percent complete: 10.1%; Average loss: 3.7801
Iteration: 405; Percent complete: 10.1%; Average loss: 3.6150
Iteration: 406; Percent complete: 10.2%; Average loss: 3.7561
Iteration: 407; Percent complete: 10.2%; Average loss: 3.6536
Iteration: 408; Percent complete: 10.2%; Average loss: 3.6676
Iteration: 409; Percent complete: 10.2%; Average loss: 3.7420
Iteration: 410; Percent complete: 10.2%; Average loss: 3.8521
Iteration: 411; Percent complete: 10.3%; Average loss: 3.7315
Iteration: 412; Percent complete: 10.3%; Average loss: 3.8264
Iteration: 413; Percent complete: 10.3%; Average loss: 3.6060
Iteration: 414; Percent complete: 10.3%; Average loss: 3.7846
Iteration: 415; Percent complete: 10.4%; Average loss: 3.7399
Iteration: 416; Percent complete: 10.4%; Average loss: 3.9678
Iteration: 417; Percent complete: 10.4%; Average loss: 3.8637
Iteration: 418; Percent complete: 10.4%; Average loss: 3.7670
Iteration: 419; Percent complete: 10.5%; Average loss: 3.6916
Iteration: 420; Percent complete: 10.5%; Average loss: 4.1884
Iteration: 421; Percent complete: 10.5%; Average loss: 3.8025
Iteration: 422; Percent complete: 10.5%; Average loss: 3.7347
Iteration: 423; Percent complete: 10.6%; Average loss: 3.8727
Iteration: 424; Percent complete: 10.6%; Average loss: 3.8672
Iteration: 425; Percent complete: 10.6%; Average loss: 3.5676
Iteration: 426; Percent complete: 10.7%; Average loss: 3.9451
Iteration: 427; Percent complete: 10.7%; Average loss: 3.6002
Iteration: 428; Percent complete: 10.7%; Average loss: 3.6895
Iteration: 429; Percent complete: 10.7%; Average loss: 3.6356
Iteration: 430; Percent complete: 10.8%; Average loss: 3.9880
Iteration: 431; Percent complete: 10.8%; Average loss: 3.6816
Iteration: 432; Percent complete: 10.8%; Average loss: 3.9660
Iteration: 433; Percent complete: 10.8%; Average loss: 4.0097
Iteration: 434; Percent complete: 10.8%; Average loss: 3.9064
Iteration: 435; Percent complete: 10.9%; Average loss: 4.0887
Iteration: 436; Percent complete: 10.9%; Average loss: 3.7445
Iteration: 437; Percent complete: 10.9%; Average loss: 4.0307
Iteration: 438; Percent complete: 10.9%; Average loss: 3.7592
Iteration: 439; Percent complete: 11.0%; Average loss: 3.6941
Iteration: 440; Percent complete: 11.0%; Average loss: 3.9221
Iteration: 441; Percent complete: 11.0%; Average loss: 3.9027
Iteration: 442; Percent complete: 11.1%; Average loss: 3.6453
Iteration: 443; Percent complete: 11.1%; Average loss: 3.3236
Iteration: 444; Percent complete: 11.1%; Average loss: 4.0256
Iteration: 445; Percent complete: 11.1%; Average loss: 3.3795
Iteration: 446; Percent complete: 11.2%; Average loss: 3.7216
Iteration: 447; Percent complete: 11.2%; Average loss: 3.9463
Iteration: 448; Percent complete: 11.2%; Average loss: 3.6858
Iteration: 449; Percent complete: 11.2%; Average loss: 3.9827
Iteration: 450; Percent complete: 11.2%; Average loss: 3.7627
Iteration: 451; Percent complete: 11.3%; Average loss: 3.8321
Iteration: 452; Percent complete: 11.3%; Average loss: 3.9232
Iteration: 453; Percent complete: 11.3%; Average loss: 3.9187
Iteration: 454; Percent complete: 11.3%; Average loss: 3.8741
Iteration: 455; Percent complete: 11.4%; Average loss: 3.7153
Iteration: 456; Percent complete: 11.4%; Average loss: 3.8658
Iteration: 457; Percent complete: 11.4%; Average loss: 3.5668
Iteration: 458; Percent complete: 11.5%; Average loss: 3.5900
Iteration: 459; Percent complete: 11.5%; Average loss: 3.7215
Iteration: 460; Percent complete: 11.5%; Average loss: 3.7400
Iteration: 461; Percent complete: 11.5%; Average loss: 3.8779
Iteration: 462; Percent complete: 11.6%; Average loss: 3.6062
Iteration: 463; Percent complete: 11.6%; Average loss: 3.4971
Iteration: 464; Percent complete: 11.6%; Average loss: 3.6849
Iteration: 465; Percent complete: 11.6%; Average loss: 3.7161
Iteration: 466; Percent complete: 11.7%; Average loss: 3.6217
Iteration: 467; Percent complete: 11.7%; Average loss: 3.5901
Iteration: 468; Percent complete: 11.7%; Average loss: 3.6446
Iteration: 469; Percent complete: 11.7%; Average loss: 3.5538
Iteration: 470; Percent complete: 11.8%; Average loss: 3.8062
Iteration: 471; Percent complete: 11.8%; Average loss: 3.6658
Iteration: 472; Percent complete: 11.8%; Average loss: 3.8664
Iteration: 473; Percent complete: 11.8%; Average loss: 4.0326
Iteration: 474; Percent complete: 11.8%; Average loss: 3.9019
Iteration: 475; Percent complete: 11.9%; Average loss: 4.0576
Iteration: 476; Percent complete: 11.9%; Average loss: 3.8176
Iteration: 477; Percent complete: 11.9%; Average loss: 3.6816
Iteration: 478; Percent complete: 11.9%; Average loss: 3.8400
Iteration: 479; Percent complete: 12.0%; Average loss: 3.6681
Iteration: 480; Percent complete: 12.0%; Average loss: 3.7599
Iteration: 481; Percent complete: 12.0%; Average loss: 3.8039
Iteration: 482; Percent complete: 12.0%; Average loss: 3.6631
Iteration: 483; Percent complete: 12.1%; Average loss: 3.6408
Iteration: 484; Percent complete: 12.1%; Average loss: 3.8108
Iteration: 485; Percent complete: 12.1%; Average loss: 3.8582
Iteration: 486; Percent complete: 12.2%; Average loss: 3.9836
Iteration: 487; Percent complete: 12.2%; Average loss: 3.9755
Iteration: 488; Percent complete: 12.2%; Average loss: 3.9450
Iteration: 489; Percent complete: 12.2%; Average loss: 3.8238
Iteration: 490; Percent complete: 12.2%; Average loss: 3.5234
Iteration: 491; Percent complete: 12.3%; Average loss: 3.9653
Iteration: 492; Percent complete: 12.3%; Average loss: 3.5464
Iteration: 493; Percent complete: 12.3%; Average loss: 3.7838
Iteration: 494; Percent complete: 12.3%; Average loss: 3.7585
Iteration: 495; Percent complete: 12.4%; Average loss: 3.7362
Iteration: 496; Percent complete: 12.4%; Average loss: 3.5346
Iteration: 497; Percent complete: 12.4%; Average loss: 3.8067
Iteration: 498; Percent complete: 12.4%; Average loss: 3.9402
Iteration: 499; Percent complete: 12.5%; Average loss: 3.6958
Iteration: 500; Percent complete: 12.5%; Average loss: 3.8177
Iteration: 501; Percent complete: 12.5%; Average loss: 3.5796
Iteration: 502; Percent complete: 12.6%; Average loss: 3.7693
Iteration: 503; Percent complete: 12.6%; Average loss: 3.5390
Iteration: 504; Percent complete: 12.6%; Average loss: 3.9347
Iteration: 505; Percent complete: 12.6%; Average loss: 3.6017
Iteration: 506; Percent complete: 12.7%; Average loss: 4.0165
Iteration: 507; Percent complete: 12.7%; Average loss: 3.5649
Iteration: 508; Percent complete: 12.7%; Average loss: 3.8218
Iteration: 509; Percent complete: 12.7%; Average loss: 3.7699
Iteration: 510; Percent complete: 12.8%; Average loss: 3.8929
Iteration: 511; Percent complete: 12.8%; Average loss: 3.7488
Iteration: 512; Percent complete: 12.8%; Average loss: 3.9316
Iteration: 513; Percent complete: 12.8%; Average loss: 3.6357
Iteration: 514; Percent complete: 12.8%; Average loss: 3.7015
Iteration: 515; Percent complete: 12.9%; Average loss: 3.5981
Iteration: 516; Percent complete: 12.9%; Average loss: 3.6031
Iteration: 517; Percent complete: 12.9%; Average loss: 3.5340
Iteration: 518; Percent complete: 13.0%; Average loss: 3.7253
Iteration: 519; Percent complete: 13.0%; Average loss: 3.6268
Iteration: 520; Percent complete: 13.0%; Average loss: 3.8284
Iteration: 521; Percent complete: 13.0%; Average loss: 3.7426
Iteration: 522; Percent complete: 13.1%; Average loss: 3.9540
Iteration: 523; Percent complete: 13.1%; Average loss: 3.7241
Iteration: 524; Percent complete: 13.1%; Average loss: 3.9106
Iteration: 525; Percent complete: 13.1%; Average loss: 3.6254
Iteration: 526; Percent complete: 13.2%; Average loss: 3.9028
Iteration: 527; Percent complete: 13.2%; Average loss: 3.6593
Iteration: 528; Percent complete: 13.2%; Average loss: 3.7854
Iteration: 529; Percent complete: 13.2%; Average loss: 3.8344
Iteration: 530; Percent complete: 13.2%; Average loss: 3.5855
Iteration: 531; Percent complete: 13.3%; Average loss: 3.6544
Iteration: 532; Percent complete: 13.3%; Average loss: 3.7290
Iteration: 533; Percent complete: 13.3%; Average loss: 3.6803
Iteration: 534; Percent complete: 13.4%; Average loss: 3.5467
Iteration: 535; Percent complete: 13.4%; Average loss: 3.6832
Iteration: 536; Percent complete: 13.4%; Average loss: 3.9414
Iteration: 537; Percent complete: 13.4%; Average loss: 3.6216
Iteration: 538; Percent complete: 13.5%; Average loss: 4.0160
Iteration: 539; Percent complete: 13.5%; Average loss: 3.7638
Iteration: 540; Percent complete: 13.5%; Average loss: 3.7645
Iteration: 541; Percent complete: 13.5%; Average loss: 3.7423
Iteration: 542; Percent complete: 13.6%; Average loss: 3.8253
Iteration: 543; Percent complete: 13.6%; Average loss: 3.4632
Iteration: 544; Percent complete: 13.6%; Average loss: 3.8153
Iteration: 545; Percent complete: 13.6%; Average loss: 3.5440
Iteration: 546; Percent complete: 13.7%; Average loss: 3.6903
Iteration: 547; Percent complete: 13.7%; Average loss: 3.6183
Iteration: 548; Percent complete: 13.7%; Average loss: 3.5635
Iteration: 549; Percent complete: 13.7%; Average loss: 3.5831
Iteration: 550; Percent complete: 13.8%; Average loss: 3.7164
Iteration: 551; Percent complete: 13.8%; Average loss: 3.6852
Iteration: 552; Percent complete: 13.8%; Average loss: 3.4175
Iteration: 553; Percent complete: 13.8%; Average loss: 3.7314
Iteration: 554; Percent complete: 13.9%; Average loss: 3.8395
Iteration: 555; Percent complete: 13.9%; Average loss: 3.5997
Iteration: 556; Percent complete: 13.9%; Average loss: 3.7209
Iteration: 557; Percent complete: 13.9%; Average loss: 3.6592
Iteration: 558; Percent complete: 14.0%; Average loss: 3.6259
Iteration: 559; Percent complete: 14.0%; Average loss: 3.6126
Iteration: 560; Percent complete: 14.0%; Average loss: 3.8208
Iteration: 561; Percent complete: 14.0%; Average loss: 3.5672
Iteration: 562; Percent complete: 14.1%; Average loss: 3.7041
Iteration: 563; Percent complete: 14.1%; Average loss: 3.5783
Iteration: 564; Percent complete: 14.1%; Average loss: 3.7498
Iteration: 565; Percent complete: 14.1%; Average loss: 3.4335
Iteration: 566; Percent complete: 14.1%; Average loss: 3.3694
Iteration: 567; Percent complete: 14.2%; Average loss: 3.6804
Iteration: 568; Percent complete: 14.2%; Average loss: 3.5445
Iteration: 569; Percent complete: 14.2%; Average loss: 3.4854
Iteration: 570; Percent complete: 14.2%; Average loss: 3.6799
Iteration: 571; Percent complete: 14.3%; Average loss: 3.5096
Iteration: 572; Percent complete: 14.3%; Average loss: 3.8587
Iteration: 573; Percent complete: 14.3%; Average loss: 3.6763
Iteration: 574; Percent complete: 14.3%; Average loss: 3.5197
Iteration: 575; Percent complete: 14.4%; Average loss: 3.6212
Iteration: 576; Percent complete: 14.4%; Average loss: 3.9722
Iteration: 577; Percent complete: 14.4%; Average loss: 3.5333
Iteration: 578; Percent complete: 14.4%; Average loss: 3.7667
Iteration: 579; Percent complete: 14.5%; Average loss: 3.6126
Iteration: 580; Percent complete: 14.5%; Average loss: 3.5095
Iteration: 581; Percent complete: 14.5%; Average loss: 3.7131
Iteration: 582; Percent complete: 14.5%; Average loss: 3.4824
Iteration: 583; Percent complete: 14.6%; Average loss: 3.7136
Iteration: 584; Percent complete: 14.6%; Average loss: 3.7006
Iteration: 585; Percent complete: 14.6%; Average loss: 3.5040
Iteration: 586; Percent complete: 14.6%; Average loss: 3.7351
Iteration: 587; Percent complete: 14.7%; Average loss: 3.8026
Iteration: 588; Percent complete: 14.7%; Average loss: 3.5955
Iteration: 589; Percent complete: 14.7%; Average loss: 3.6418
Iteration: 590; Percent complete: 14.8%; Average loss: 3.8947
Iteration: 591; Percent complete: 14.8%; Average loss: 3.6055
Iteration: 592; Percent complete: 14.8%; Average loss: 3.4527
Iteration: 593; Percent complete: 14.8%; Average loss: 3.4118
Iteration: 594; Percent complete: 14.8%; Average loss: 3.6328
Iteration: 595; Percent complete: 14.9%; Average loss: 3.7927
Iteration: 596; Percent complete: 14.9%; Average loss: 3.7776
Iteration: 597; Percent complete: 14.9%; Average loss: 3.3929
Iteration: 598; Percent complete: 14.9%; Average loss: 3.7096
Iteration: 599; Percent complete: 15.0%; Average loss: 3.5729
Iteration: 600; Percent complete: 15.0%; Average loss: 4.0789
Iteration: 601; Percent complete: 15.0%; Average loss: 3.7082
Iteration: 602; Percent complete: 15.0%; Average loss: 3.6352
Iteration: 603; Percent complete: 15.1%; Average loss: 3.5640
Iteration: 604; Percent complete: 15.1%; Average loss: 3.7568
Iteration: 605; Percent complete: 15.1%; Average loss: 3.6980
Iteration: 606; Percent complete: 15.2%; Average loss: 3.5082
Iteration: 607; Percent complete: 15.2%; Average loss: 3.5011
Iteration: 608; Percent complete: 15.2%; Average loss: 3.5055
Iteration: 609; Percent complete: 15.2%; Average loss: 3.9747
Iteration: 610; Percent complete: 15.2%; Average loss: 3.7085
Iteration: 611; Percent complete: 15.3%; Average loss: 3.5780
Iteration: 612; Percent complete: 15.3%; Average loss: 3.7357
Iteration: 613; Percent complete: 15.3%; Average loss: 3.6498
Iteration: 614; Percent complete: 15.3%; Average loss: 3.3262
Iteration: 615; Percent complete: 15.4%; Average loss: 3.9856
Iteration: 616; Percent complete: 15.4%; Average loss: 3.8086
Iteration: 617; Percent complete: 15.4%; Average loss: 3.4060
Iteration: 618; Percent complete: 15.4%; Average loss: 3.5620
Iteration: 619; Percent complete: 15.5%; Average loss: 3.6595
Iteration: 620; Percent complete: 15.5%; Average loss: 3.4699
Iteration: 621; Percent complete: 15.5%; Average loss: 3.6085
Iteration: 622; Percent complete: 15.6%; Average loss: 3.9330
Iteration: 623; Percent complete: 15.6%; Average loss: 3.7022
Iteration: 624; Percent complete: 15.6%; Average loss: 3.5014
Iteration: 625; Percent complete: 15.6%; Average loss: 3.5168
Iteration: 626; Percent complete: 15.7%; Average loss: 3.5496
Iteration: 627; Percent complete: 15.7%; Average loss: 3.7469
Iteration: 628; Percent complete: 15.7%; Average loss: 3.7942
Iteration: 629; Percent complete: 15.7%; Average loss: 3.5890
Iteration: 630; Percent complete: 15.8%; Average loss: 3.6471
Iteration: 631; Percent complete: 15.8%; Average loss: 3.8927
Iteration: 632; Percent complete: 15.8%; Average loss: 3.6403
Iteration: 633; Percent complete: 15.8%; Average loss: 3.6587
Iteration: 634; Percent complete: 15.8%; Average loss: 3.6226
Iteration: 635; Percent complete: 15.9%; Average loss: 3.4347
Iteration: 636; Percent complete: 15.9%; Average loss: 3.5147
Iteration: 637; Percent complete: 15.9%; Average loss: 3.4698
Iteration: 638; Percent complete: 16.0%; Average loss: 3.6770
Iteration: 639; Percent complete: 16.0%; Average loss: 3.8554
Iteration: 640; Percent complete: 16.0%; Average loss: 3.7760
Iteration: 641; Percent complete: 16.0%; Average loss: 3.5134
Iteration: 642; Percent complete: 16.1%; Average loss: 3.8401
Iteration: 643; Percent complete: 16.1%; Average loss: 3.7535
Iteration: 644; Percent complete: 16.1%; Average loss: 3.4270
Iteration: 645; Percent complete: 16.1%; Average loss: 3.3931
Iteration: 646; Percent complete: 16.2%; Average loss: 3.5442
Iteration: 647; Percent complete: 16.2%; Average loss: 3.7576
Iteration: 648; Percent complete: 16.2%; Average loss: 3.4460
Iteration: 649; Percent complete: 16.2%; Average loss: 3.4096
Iteration: 650; Percent complete: 16.2%; Average loss: 3.5109
Iteration: 651; Percent complete: 16.3%; Average loss: 3.5425
Iteration: 652; Percent complete: 16.3%; Average loss: 3.5941
Iteration: 653; Percent complete: 16.3%; Average loss: 3.3845
Iteration: 654; Percent complete: 16.4%; Average loss: 3.5560
Iteration: 655; Percent complete: 16.4%; Average loss: 3.5032
Iteration: 656; Percent complete: 16.4%; Average loss: 3.6769
Iteration: 657; Percent complete: 16.4%; Average loss: 3.4648
Iteration: 658; Percent complete: 16.4%; Average loss: 3.7191
Iteration: 659; Percent complete: 16.5%; Average loss: 3.6132
Iteration: 660; Percent complete: 16.5%; Average loss: 3.7367
Iteration: 661; Percent complete: 16.5%; Average loss: 3.6619
Iteration: 662; Percent complete: 16.6%; Average loss: 3.5959
Iteration: 663; Percent complete: 16.6%; Average loss: 3.7393
Iteration: 664; Percent complete: 16.6%; Average loss: 3.9596
Iteration: 665; Percent complete: 16.6%; Average loss: 3.5581
Iteration: 666; Percent complete: 16.7%; Average loss: 3.6270
Iteration: 667; Percent complete: 16.7%; Average loss: 3.7599
Iteration: 668; Percent complete: 16.7%; Average loss: 3.9231
Iteration: 669; Percent complete: 16.7%; Average loss: 3.5459
Iteration: 670; Percent complete: 16.8%; Average loss: 3.5234
Iteration: 671; Percent complete: 16.8%; Average loss: 3.6072
Iteration: 672; Percent complete: 16.8%; Average loss: 3.8640
Iteration: 673; Percent complete: 16.8%; Average loss: 3.6960
Iteration: 674; Percent complete: 16.9%; Average loss: 3.6804
Iteration: 675; Percent complete: 16.9%; Average loss: 3.5089
Iteration: 676; Percent complete: 16.9%; Average loss: 3.5373
Iteration: 677; Percent complete: 16.9%; Average loss: 3.5219
Iteration: 678; Percent complete: 17.0%; Average loss: 3.5939
Iteration: 679; Percent complete: 17.0%; Average loss: 3.3519
Iteration: 680; Percent complete: 17.0%; Average loss: 3.6908
Iteration: 681; Percent complete: 17.0%; Average loss: 3.5440
Iteration: 682; Percent complete: 17.1%; Average loss: 3.7029
Iteration: 683; Percent complete: 17.1%; Average loss: 3.5381
Iteration: 684; Percent complete: 17.1%; Average loss: 3.8099
Iteration: 685; Percent complete: 17.1%; Average loss: 3.5060
Iteration: 686; Percent complete: 17.2%; Average loss: 3.2485
Iteration: 687; Percent complete: 17.2%; Average loss: 3.7024
Iteration: 688; Percent complete: 17.2%; Average loss: 3.8054
Iteration: 689; Percent complete: 17.2%; Average loss: 3.5234
Iteration: 690; Percent complete: 17.2%; Average loss: 3.5223
Iteration: 691; Percent complete: 17.3%; Average loss: 3.5884
Iteration: 692; Percent complete: 17.3%; Average loss: 3.6683
Iteration: 693; Percent complete: 17.3%; Average loss: 3.7030
Iteration: 694; Percent complete: 17.3%; Average loss: 3.8575
Iteration: 695; Percent complete: 17.4%; Average loss: 3.5754
Iteration: 696; Percent complete: 17.4%; Average loss: 3.7578
Iteration: 697; Percent complete: 17.4%; Average loss: 3.5604
Iteration: 698; Percent complete: 17.4%; Average loss: 3.7163
Iteration: 699; Percent complete: 17.5%; Average loss: 3.8038
Iteration: 700; Percent complete: 17.5%; Average loss: 3.7309
Iteration: 701; Percent complete: 17.5%; Average loss: 3.6451
Iteration: 702; Percent complete: 17.5%; Average loss: 3.5818
Iteration: 703; Percent complete: 17.6%; Average loss: 3.5369
Iteration: 704; Percent complete: 17.6%; Average loss: 3.4466
Iteration: 705; Percent complete: 17.6%; Average loss: 3.6867
Iteration: 706; Percent complete: 17.6%; Average loss: 3.6440
Iteration: 707; Percent complete: 17.7%; Average loss: 3.2505
Iteration: 708; Percent complete: 17.7%; Average loss: 3.6628
Iteration: 709; Percent complete: 17.7%; Average loss: 3.5933
Iteration: 710; Percent complete: 17.8%; Average loss: 3.6315
Iteration: 711; Percent complete: 17.8%; Average loss: 3.9361
Iteration: 712; Percent complete: 17.8%; Average loss: 3.4633
Iteration: 713; Percent complete: 17.8%; Average loss: 3.7686
Iteration: 714; Percent complete: 17.8%; Average loss: 3.5218
Iteration: 715; Percent complete: 17.9%; Average loss: 3.4806
Iteration: 716; Percent complete: 17.9%; Average loss: 3.9042
Iteration: 717; Percent complete: 17.9%; Average loss: 3.5261
Iteration: 718; Percent complete: 17.9%; Average loss: 3.7538
Iteration: 719; Percent complete: 18.0%; Average loss: 3.5387
Iteration: 720; Percent complete: 18.0%; Average loss: 3.6051
Iteration: 721; Percent complete: 18.0%; Average loss: 3.8446
Iteration: 722; Percent complete: 18.1%; Average loss: 3.6275
Iteration: 723; Percent complete: 18.1%; Average loss: 3.5333
Iteration: 724; Percent complete: 18.1%; Average loss: 3.8268
Iteration: 725; Percent complete: 18.1%; Average loss: 3.6199
Iteration: 726; Percent complete: 18.1%; Average loss: 3.6704
Iteration: 727; Percent complete: 18.2%; Average loss: 3.7106
Iteration: 728; Percent complete: 18.2%; Average loss: 3.7449
Iteration: 729; Percent complete: 18.2%; Average loss: 3.6526
Iteration: 730; Percent complete: 18.2%; Average loss: 3.6033
Iteration: 731; Percent complete: 18.3%; Average loss: 3.5430
Iteration: 732; Percent complete: 18.3%; Average loss: 3.4483
Iteration: 733; Percent complete: 18.3%; Average loss: 3.7703
Iteration: 734; Percent complete: 18.4%; Average loss: 3.5028
Iteration: 735; Percent complete: 18.4%; Average loss: 3.5649
Iteration: 736; Percent complete: 18.4%; Average loss: 3.5716
Iteration: 737; Percent complete: 18.4%; Average loss: 3.4415
Iteration: 738; Percent complete: 18.4%; Average loss: 3.5189
Iteration: 739; Percent complete: 18.5%; Average loss: 3.5510
Iteration: 740; Percent complete: 18.5%; Average loss: 3.5001
Iteration: 741; Percent complete: 18.5%; Average loss: 3.5607
Iteration: 742; Percent complete: 18.6%; Average loss: 3.7192
Iteration: 743; Percent complete: 18.6%; Average loss: 3.2937
Iteration: 744; Percent complete: 18.6%; Average loss: 3.4294
Iteration: 745; Percent complete: 18.6%; Average loss: 3.5442
Iteration: 746; Percent complete: 18.6%; Average loss: 3.4983
Iteration: 747; Percent complete: 18.7%; Average loss: 3.6282
Iteration: 748; Percent complete: 18.7%; Average loss: 3.5127
Iteration: 749; Percent complete: 18.7%; Average loss: 3.6601
Iteration: 750; Percent complete: 18.8%; Average loss: 3.5956
Iteration: 751; Percent complete: 18.8%; Average loss: 3.6034
Iteration: 752; Percent complete: 18.8%; Average loss: 3.4119
Iteration: 753; Percent complete: 18.8%; Average loss: 3.5439
Iteration: 754; Percent complete: 18.9%; Average loss: 3.7810
Iteration: 755; Percent complete: 18.9%; Average loss: 3.6817
Iteration: 756; Percent complete: 18.9%; Average loss: 3.7452
Iteration: 757; Percent complete: 18.9%; Average loss: 3.3991
Iteration: 758; Percent complete: 18.9%; Average loss: 3.5962
Iteration: 759; Percent complete: 19.0%; Average loss: 3.5627
Iteration: 760; Percent complete: 19.0%; Average loss: 3.6700
Iteration: 761; Percent complete: 19.0%; Average loss: 3.4617
Iteration: 762; Percent complete: 19.1%; Average loss: 3.6228
Iteration: 763; Percent complete: 19.1%; Average loss: 3.4080
Iteration: 764; Percent complete: 19.1%; Average loss: 3.5373
Iteration: 765; Percent complete: 19.1%; Average loss: 3.8630
Iteration: 766; Percent complete: 19.1%; Average loss: 3.6988
Iteration: 767; Percent complete: 19.2%; Average loss: 3.3610
Iteration: 768; Percent complete: 19.2%; Average loss: 3.5926
Iteration: 769; Percent complete: 19.2%; Average loss: 3.5666
Iteration: 770; Percent complete: 19.2%; Average loss: 3.4787
Iteration: 771; Percent complete: 19.3%; Average loss: 3.6949
Iteration: 772; Percent complete: 19.3%; Average loss: 3.6449
Iteration: 773; Percent complete: 19.3%; Average loss: 3.8243
Iteration: 774; Percent complete: 19.4%; Average loss: 3.7991
Iteration: 775; Percent complete: 19.4%; Average loss: 3.6870
Iteration: 776; Percent complete: 19.4%; Average loss: 3.7231
Iteration: 777; Percent complete: 19.4%; Average loss: 3.4145
Iteration: 778; Percent complete: 19.4%; Average loss: 3.1950
Iteration: 779; Percent complete: 19.5%; Average loss: 3.3746
Iteration: 780; Percent complete: 19.5%; Average loss: 3.4834
Iteration: 781; Percent complete: 19.5%; Average loss: 3.6879
Iteration: 782; Percent complete: 19.6%; Average loss: 3.5713
Iteration: 783; Percent complete: 19.6%; Average loss: 3.5165
Iteration: 784; Percent complete: 19.6%; Average loss: 3.7472
Iteration: 785; Percent complete: 19.6%; Average loss: 3.5102
Iteration: 786; Percent complete: 19.7%; Average loss: 3.5255
Iteration: 787; Percent complete: 19.7%; Average loss: 3.5747
Iteration: 788; Percent complete: 19.7%; Average loss: 3.5226
Iteration: 789; Percent complete: 19.7%; Average loss: 3.3927
Iteration: 790; Percent complete: 19.8%; Average loss: 3.2129
Iteration: 791; Percent complete: 19.8%; Average loss: 3.8750
Iteration: 792; Percent complete: 19.8%; Average loss: 3.5089
Iteration: 793; Percent complete: 19.8%; Average loss: 3.7127
Iteration: 794; Percent complete: 19.9%; Average loss: 3.8381
Iteration: 795; Percent complete: 19.9%; Average loss: 3.6084
Iteration: 796; Percent complete: 19.9%; Average loss: 3.4780
Iteration: 797; Percent complete: 19.9%; Average loss: 3.6517
Iteration: 798; Percent complete: 20.0%; Average loss: 3.6618
Iteration: 799; Percent complete: 20.0%; Average loss: 3.3791
Iteration: 800; Percent complete: 20.0%; Average loss: 3.1961
Iteration: 801; Percent complete: 20.0%; Average loss: 3.4364
Iteration: 802; Percent complete: 20.1%; Average loss: 3.6136
Iteration: 803; Percent complete: 20.1%; Average loss: 3.4656
Iteration: 804; Percent complete: 20.1%; Average loss: 3.6172
Iteration: 805; Percent complete: 20.1%; Average loss: 3.5568
Iteration: 806; Percent complete: 20.2%; Average loss: 3.5634
Iteration: 807; Percent complete: 20.2%; Average loss: 3.6856
Iteration: 808; Percent complete: 20.2%; Average loss: 3.7901
Iteration: 809; Percent complete: 20.2%; Average loss: 3.6872
Iteration: 810; Percent complete: 20.2%; Average loss: 3.4119
Iteration: 811; Percent complete: 20.3%; Average loss: 3.5427
Iteration: 812; Percent complete: 20.3%; Average loss: 3.5931
Iteration: 813; Percent complete: 20.3%; Average loss: 3.6826
Iteration: 814; Percent complete: 20.3%; Average loss: 3.4551
Iteration: 815; Percent complete: 20.4%; Average loss: 3.4747
Iteration: 816; Percent complete: 20.4%; Average loss: 3.6448
Iteration: 817; Percent complete: 20.4%; Average loss: 3.3901
Iteration: 818; Percent complete: 20.4%; Average loss: 3.4568
Iteration: 819; Percent complete: 20.5%; Average loss: 3.4487
Iteration: 820; Percent complete: 20.5%; Average loss: 3.5114
Iteration: 821; Percent complete: 20.5%; Average loss: 3.5482
Iteration: 822; Percent complete: 20.5%; Average loss: 3.5666
Iteration: 823; Percent complete: 20.6%; Average loss: 3.4519
Iteration: 824; Percent complete: 20.6%; Average loss: 3.3560
Iteration: 825; Percent complete: 20.6%; Average loss: 3.5821
Iteration: 826; Percent complete: 20.6%; Average loss: 3.5422
Iteration: 827; Percent complete: 20.7%; Average loss: 3.7669
Iteration: 828; Percent complete: 20.7%; Average loss: 3.6009
Iteration: 829; Percent complete: 20.7%; Average loss: 3.3450
Iteration: 830; Percent complete: 20.8%; Average loss: 3.6293
Iteration: 831; Percent complete: 20.8%; Average loss: 3.4512
Iteration: 832; Percent complete: 20.8%; Average loss: 3.4127
Iteration: 833; Percent complete: 20.8%; Average loss: 3.5597
Iteration: 834; Percent complete: 20.8%; Average loss: 3.5395
Iteration: 835; Percent complete: 20.9%; Average loss: 3.5463
Iteration: 836; Percent complete: 20.9%; Average loss: 3.5266
Iteration: 837; Percent complete: 20.9%; Average loss: 3.3577
Iteration: 838; Percent complete: 20.9%; Average loss: 3.4996
Iteration: 839; Percent complete: 21.0%; Average loss: 3.4866
Iteration: 840; Percent complete: 21.0%; Average loss: 3.4047
Iteration: 841; Percent complete: 21.0%; Average loss: 3.5299
Iteration: 842; Percent complete: 21.1%; Average loss: 3.7441
Iteration: 843; Percent complete: 21.1%; Average loss: 3.7133
Iteration: 844; Percent complete: 21.1%; Average loss: 3.7845
Iteration: 845; Percent complete: 21.1%; Average loss: 3.3313
Iteration: 846; Percent complete: 21.1%; Average loss: 3.5622
Iteration: 847; Percent complete: 21.2%; Average loss: 3.8793
Iteration: 848; Percent complete: 21.2%; Average loss: 3.6371
Iteration: 849; Percent complete: 21.2%; Average loss: 3.6572
Iteration: 850; Percent complete: 21.2%; Average loss: 3.4636
Iteration: 851; Percent complete: 21.3%; Average loss: 3.3291
Iteration: 852; Percent complete: 21.3%; Average loss: 3.7540
Iteration: 853; Percent complete: 21.3%; Average loss: 3.4164
Iteration: 854; Percent complete: 21.3%; Average loss: 3.7421
Iteration: 855; Percent complete: 21.4%; Average loss: 3.5339
Iteration: 856; Percent complete: 21.4%; Average loss: 3.8153
Iteration: 857; Percent complete: 21.4%; Average loss: 3.3342
Iteration: 858; Percent complete: 21.4%; Average loss: 3.6280
Iteration: 859; Percent complete: 21.5%; Average loss: 3.5970
Iteration: 860; Percent complete: 21.5%; Average loss: 3.6509
Iteration: 861; Percent complete: 21.5%; Average loss: 3.3699
Iteration: 862; Percent complete: 21.6%; Average loss: 3.3373
Iteration: 863; Percent complete: 21.6%; Average loss: 3.5586
Iteration: 864; Percent complete: 21.6%; Average loss: 3.5201
Iteration: 865; Percent complete: 21.6%; Average loss: 3.6364
Iteration: 866; Percent complete: 21.6%; Average loss: 3.6750
Iteration: 867; Percent complete: 21.7%; Average loss: 3.5580
Iteration: 868; Percent complete: 21.7%; Average loss: 3.6598
Iteration: 869; Percent complete: 21.7%; Average loss: 3.6048
Iteration: 870; Percent complete: 21.8%; Average loss: 3.6213
Iteration: 871; Percent complete: 21.8%; Average loss: 3.6052
Iteration: 872; Percent complete: 21.8%; Average loss: 3.3949
Iteration: 873; Percent complete: 21.8%; Average loss: 3.7283
Iteration: 874; Percent complete: 21.9%; Average loss: 3.7077
Iteration: 875; Percent complete: 21.9%; Average loss: 3.5276
Iteration: 876; Percent complete: 21.9%; Average loss: 3.4351
Iteration: 877; Percent complete: 21.9%; Average loss: 3.6242
Iteration: 878; Percent complete: 21.9%; Average loss: 3.7275
Iteration: 879; Percent complete: 22.0%; Average loss: 3.6714
Iteration: 880; Percent complete: 22.0%; Average loss: 3.5002
Iteration: 881; Percent complete: 22.0%; Average loss: 3.4760
Iteration: 882; Percent complete: 22.1%; Average loss: 3.4449
Iteration: 883; Percent complete: 22.1%; Average loss: 3.5648
Iteration: 884; Percent complete: 22.1%; Average loss: 3.5894
Iteration: 885; Percent complete: 22.1%; Average loss: 3.5077
Iteration: 886; Percent complete: 22.1%; Average loss: 3.7189
Iteration: 887; Percent complete: 22.2%; Average loss: 3.4769
Iteration: 888; Percent complete: 22.2%; Average loss: 3.4990
Iteration: 889; Percent complete: 22.2%; Average loss: 3.5900
Iteration: 890; Percent complete: 22.2%; Average loss: 3.5102
Iteration: 891; Percent complete: 22.3%; Average loss: 3.7007
Iteration: 892; Percent complete: 22.3%; Average loss: 3.4332
Iteration: 893; Percent complete: 22.3%; Average loss: 3.6545
Iteration: 894; Percent complete: 22.4%; Average loss: 3.4610
Iteration: 895; Percent complete: 22.4%; Average loss: 3.3102
Iteration: 896; Percent complete: 22.4%; Average loss: 3.4768
Iteration: 897; Percent complete: 22.4%; Average loss: 3.6503
Iteration: 898; Percent complete: 22.4%; Average loss: 3.4464
Iteration: 899; Percent complete: 22.5%; Average loss: 3.6245
Iteration: 900; Percent complete: 22.5%; Average loss: 3.7292
Iteration: 901; Percent complete: 22.5%; Average loss: 3.8095
Iteration: 902; Percent complete: 22.6%; Average loss: 3.3607
Iteration: 903; Percent complete: 22.6%; Average loss: 3.7301
Iteration: 904; Percent complete: 22.6%; Average loss: 3.7304
Iteration: 905; Percent complete: 22.6%; Average loss: 3.7498
Iteration: 906; Percent complete: 22.7%; Average loss: 3.4345
Iteration: 907; Percent complete: 22.7%; Average loss: 3.5782
Iteration: 908; Percent complete: 22.7%; Average loss: 3.6354
Iteration: 909; Percent complete: 22.7%; Average loss: 3.4767
Iteration: 910; Percent complete: 22.8%; Average loss: 3.7287
Iteration: 911; Percent complete: 22.8%; Average loss: 3.5483
Iteration: 912; Percent complete: 22.8%; Average loss: 3.2453
Iteration: 913; Percent complete: 22.8%; Average loss: 3.6089
Iteration: 914; Percent complete: 22.9%; Average loss: 3.6241
Iteration: 915; Percent complete: 22.9%; Average loss: 3.4863
Iteration: 916; Percent complete: 22.9%; Average loss: 3.6550
Iteration: 917; Percent complete: 22.9%; Average loss: 3.2411
Iteration: 918; Percent complete: 22.9%; Average loss: 3.3915
Iteration: 919; Percent complete: 23.0%; Average loss: 3.4256
Iteration: 920; Percent complete: 23.0%; Average loss: 3.7126
Iteration: 921; Percent complete: 23.0%; Average loss: 3.2153
Iteration: 922; Percent complete: 23.1%; Average loss: 3.1516
Iteration: 923; Percent complete: 23.1%; Average loss: 3.6325
Iteration: 924; Percent complete: 23.1%; Average loss: 3.5060
Iteration: 925; Percent complete: 23.1%; Average loss: 3.5855
Iteration: 926; Percent complete: 23.2%; Average loss: 3.3788
Iteration: 927; Percent complete: 23.2%; Average loss: 3.6288
Iteration: 928; Percent complete: 23.2%; Average loss: 3.8069
Iteration: 929; Percent complete: 23.2%; Average loss: 3.2903
Iteration: 930; Percent complete: 23.2%; Average loss: 3.5675
Iteration: 931; Percent complete: 23.3%; Average loss: 3.4171
Iteration: 932; Percent complete: 23.3%; Average loss: 3.3767
Iteration: 933; Percent complete: 23.3%; Average loss: 3.4159
Iteration: 934; Percent complete: 23.4%; Average loss: 3.6454
Iteration: 935; Percent complete: 23.4%; Average loss: 3.5633
Iteration: 936; Percent complete: 23.4%; Average loss: 3.3908
Iteration: 937; Percent complete: 23.4%; Average loss: 3.4022
Iteration: 938; Percent complete: 23.4%; Average loss: 3.3989
Iteration: 939; Percent complete: 23.5%; Average loss: 3.5596
Iteration: 940; Percent complete: 23.5%; Average loss: 3.2231
Iteration: 941; Percent complete: 23.5%; Average loss: 3.4666
Iteration: 942; Percent complete: 23.5%; Average loss: 3.6955
Iteration: 943; Percent complete: 23.6%; Average loss: 3.2919
Iteration: 944; Percent complete: 23.6%; Average loss: 3.3328
Iteration: 945; Percent complete: 23.6%; Average loss: 3.5496
Iteration: 946; Percent complete: 23.6%; Average loss: 3.3955
Iteration: 947; Percent complete: 23.7%; Average loss: 3.7611
Iteration: 948; Percent complete: 23.7%; Average loss: 3.5491
Iteration: 949; Percent complete: 23.7%; Average loss: 3.3513
Iteration: 950; Percent complete: 23.8%; Average loss: 3.4742
Iteration: 951; Percent complete: 23.8%; Average loss: 3.6348
Iteration: 952; Percent complete: 23.8%; Average loss: 3.3298
Iteration: 953; Percent complete: 23.8%; Average loss: 3.3832
Iteration: 954; Percent complete: 23.8%; Average loss: 3.6115
Iteration: 955; Percent complete: 23.9%; Average loss: 3.3426
Iteration: 956; Percent complete: 23.9%; Average loss: 3.4193
Iteration: 957; Percent complete: 23.9%; Average loss: 3.4382
Iteration: 958; Percent complete: 23.9%; Average loss: 3.5729
Iteration: 959; Percent complete: 24.0%; Average loss: 3.7491
Iteration: 960; Percent complete: 24.0%; Average loss: 3.4278
Iteration: 961; Percent complete: 24.0%; Average loss: 3.3262
Iteration: 962; Percent complete: 24.1%; Average loss: 3.5968
Iteration: 963; Percent complete: 24.1%; Average loss: 3.6769
Iteration: 964; Percent complete: 24.1%; Average loss: 3.5585
Iteration: 965; Percent complete: 24.1%; Average loss: 3.6417
Iteration: 966; Percent complete: 24.1%; Average loss: 3.2922
Iteration: 967; Percent complete: 24.2%; Average loss: 3.2557
Iteration: 968; Percent complete: 24.2%; Average loss: 3.2463
Iteration: 969; Percent complete: 24.2%; Average loss: 3.5277
Iteration: 970; Percent complete: 24.2%; Average loss: 3.3623
Iteration: 971; Percent complete: 24.3%; Average loss: 3.5758
Iteration: 972; Percent complete: 24.3%; Average loss: 3.3855
Iteration: 973; Percent complete: 24.3%; Average loss: 3.4320
Iteration: 974; Percent complete: 24.3%; Average loss: 3.5007
Iteration: 975; Percent complete: 24.4%; Average loss: 3.5207
Iteration: 976; Percent complete: 24.4%; Average loss: 3.7938
Iteration: 977; Percent complete: 24.4%; Average loss: 3.3626
Iteration: 978; Percent complete: 24.4%; Average loss: 3.4587
Iteration: 979; Percent complete: 24.5%; Average loss: 3.2838
Iteration: 980; Percent complete: 24.5%; Average loss: 3.4506
Iteration: 981; Percent complete: 24.5%; Average loss: 3.4422
Iteration: 982; Percent complete: 24.6%; Average loss: 3.5944
Iteration: 983; Percent complete: 24.6%; Average loss: 3.4577
Iteration: 984; Percent complete: 24.6%; Average loss: 3.7290
Iteration: 985; Percent complete: 24.6%; Average loss: 3.3739
Iteration: 986; Percent complete: 24.6%; Average loss: 3.6035
Iteration: 987; Percent complete: 24.7%; Average loss: 3.5740
Iteration: 988; Percent complete: 24.7%; Average loss: 3.2382
Iteration: 989; Percent complete: 24.7%; Average loss: 3.6056
Iteration: 990; Percent complete: 24.8%; Average loss: 3.6560
Iteration: 991; Percent complete: 24.8%; Average loss: 3.5596
Iteration: 992; Percent complete: 24.8%; Average loss: 3.5069
Iteration: 993; Percent complete: 24.8%; Average loss: 3.4478
Iteration: 994; Percent complete: 24.9%; Average loss: 3.4028
Iteration: 995; Percent complete: 24.9%; Average loss: 3.4434
Iteration: 996; Percent complete: 24.9%; Average loss: 4.0430
Iteration: 997; Percent complete: 24.9%; Average loss: 3.4207
Iteration: 998; Percent complete: 24.9%; Average loss: 3.3880
Iteration: 999; Percent complete: 25.0%; Average loss: 3.6182
Iteration: 1000; Percent complete: 25.0%; Average loss: 3.4791
Iteration: 1001; Percent complete: 25.0%; Average loss: 3.5265
Iteration: 1002; Percent complete: 25.1%; Average loss: 3.5585
Iteration: 1003; Percent complete: 25.1%; Average loss: 3.3031
Iteration: 1004; Percent complete: 25.1%; Average loss: 3.3736
Iteration: 1005; Percent complete: 25.1%; Average loss: 3.5539
Iteration: 1006; Percent complete: 25.1%; Average loss: 3.6528
Iteration: 1007; Percent complete: 25.2%; Average loss: 3.6255
Iteration: 1008; Percent complete: 25.2%; Average loss: 3.5901
Iteration: 1009; Percent complete: 25.2%; Average loss: 3.2328
Iteration: 1010; Percent complete: 25.2%; Average loss: 3.2111
Iteration: 1011; Percent complete: 25.3%; Average loss: 3.6215
Iteration: 1012; Percent complete: 25.3%; Average loss: 3.3889
Iteration: 1013; Percent complete: 25.3%; Average loss: 3.3118
Iteration: 1014; Percent complete: 25.4%; Average loss: 3.3349
Iteration: 1015; Percent complete: 25.4%; Average loss: 3.6207
Iteration: 1016; Percent complete: 25.4%; Average loss: 3.4241
Iteration: 1017; Percent complete: 25.4%; Average loss: 3.4811
Iteration: 1018; Percent complete: 25.4%; Average loss: 3.4217
Iteration: 1019; Percent complete: 25.5%; Average loss: 3.1722
Iteration: 1020; Percent complete: 25.5%; Average loss: 3.2828
Iteration: 1021; Percent complete: 25.5%; Average loss: 3.4394
Iteration: 1022; Percent complete: 25.6%; Average loss: 3.5775
Iteration: 1023; Percent complete: 25.6%; Average loss: 3.4644
Iteration: 1024; Percent complete: 25.6%; Average loss: 3.5613
Iteration: 1025; Percent complete: 25.6%; Average loss: 3.5537
Iteration: 1026; Percent complete: 25.7%; Average loss: 3.5922
Iteration: 1027; Percent complete: 25.7%; Average loss: 3.3806
Iteration: 1028; Percent complete: 25.7%; Average loss: 3.5493
Iteration: 1029; Percent complete: 25.7%; Average loss: 3.6030
Iteration: 1030; Percent complete: 25.8%; Average loss: 3.1212
Iteration: 1031; Percent complete: 25.8%; Average loss: 3.5683
Iteration: 1032; Percent complete: 25.8%; Average loss: 3.2882
Iteration: 1033; Percent complete: 25.8%; Average loss: 3.5736
Iteration: 1034; Percent complete: 25.9%; Average loss: 3.5268
Iteration: 1035; Percent complete: 25.9%; Average loss: 3.3451
Iteration: 1036; Percent complete: 25.9%; Average loss: 3.3609
Iteration: 1037; Percent complete: 25.9%; Average loss: 3.6103
Iteration: 1038; Percent complete: 25.9%; Average loss: 3.4350
Iteration: 1039; Percent complete: 26.0%; Average loss: 3.4346
Iteration: 1040; Percent complete: 26.0%; Average loss: 3.5604
Iteration: 1041; Percent complete: 26.0%; Average loss: 3.6656
Iteration: 1042; Percent complete: 26.1%; Average loss: 3.1949
Iteration: 1043; Percent complete: 26.1%; Average loss: 3.6656
Iteration: 1044; Percent complete: 26.1%; Average loss: 3.2483
Iteration: 1045; Percent complete: 26.1%; Average loss: 3.7150
Iteration: 1046; Percent complete: 26.2%; Average loss: 3.2489
Iteration: 1047; Percent complete: 26.2%; Average loss: 3.3666
Iteration: 1048; Percent complete: 26.2%; Average loss: 3.5643
Iteration: 1049; Percent complete: 26.2%; Average loss: 3.5886
Iteration: 1050; Percent complete: 26.2%; Average loss: 3.5478
Iteration: 1051; Percent complete: 26.3%; Average loss: 3.4145
Iteration: 1052; Percent complete: 26.3%; Average loss: 3.1213
Iteration: 1053; Percent complete: 26.3%; Average loss: 3.7220
Iteration: 1054; Percent complete: 26.4%; Average loss: 3.1940
Iteration: 1055; Percent complete: 26.4%; Average loss: 3.4511
Iteration: 1056; Percent complete: 26.4%; Average loss: 3.5021
Iteration: 1057; Percent complete: 26.4%; Average loss: 3.5087
Iteration: 1058; Percent complete: 26.5%; Average loss: 3.4328
Iteration: 1059; Percent complete: 26.5%; Average loss: 3.4139
Iteration: 1060; Percent complete: 26.5%; Average loss: 3.3943
Iteration: 1061; Percent complete: 26.5%; Average loss: 3.4194
Iteration: 1062; Percent complete: 26.6%; Average loss: 3.3475
Iteration: 1063; Percent complete: 26.6%; Average loss: 3.4141
Iteration: 1064; Percent complete: 26.6%; Average loss: 3.4210
Iteration: 1065; Percent complete: 26.6%; Average loss: 3.6069
Iteration: 1066; Percent complete: 26.7%; Average loss: 3.5755
Iteration: 1067; Percent complete: 26.7%; Average loss: 3.5037
Iteration: 1068; Percent complete: 26.7%; Average loss: 3.5420
Iteration: 1069; Percent complete: 26.7%; Average loss: 3.3449
Iteration: 1070; Percent complete: 26.8%; Average loss: 3.4783
Iteration: 1071; Percent complete: 26.8%; Average loss: 3.4133
Iteration: 1072; Percent complete: 26.8%; Average loss: 3.3924
Iteration: 1073; Percent complete: 26.8%; Average loss: 3.4977
Iteration: 1074; Percent complete: 26.9%; Average loss: 3.4761
Iteration: 1075; Percent complete: 26.9%; Average loss: 3.4263
Iteration: 1076; Percent complete: 26.9%; Average loss: 3.2807
Iteration: 1077; Percent complete: 26.9%; Average loss: 3.4369
Iteration: 1078; Percent complete: 27.0%; Average loss: 3.2126
Iteration: 1079; Percent complete: 27.0%; Average loss: 3.4493
Iteration: 1080; Percent complete: 27.0%; Average loss: 3.2236
Iteration: 1081; Percent complete: 27.0%; Average loss: 3.6805
Iteration: 1082; Percent complete: 27.1%; Average loss: 3.4129
Iteration: 1083; Percent complete: 27.1%; Average loss: 3.2779
Iteration: 1084; Percent complete: 27.1%; Average loss: 3.4074
Iteration: 1085; Percent complete: 27.1%; Average loss: 3.2575
Iteration: 1086; Percent complete: 27.2%; Average loss: 3.5099
Iteration: 1087; Percent complete: 27.2%; Average loss: 3.6564
Iteration: 1088; Percent complete: 27.2%; Average loss: 3.4482
Iteration: 1089; Percent complete: 27.2%; Average loss: 3.4197
Iteration: 1090; Percent complete: 27.3%; Average loss: 3.4391
Iteration: 1091; Percent complete: 27.3%; Average loss: 3.6922
Iteration: 1092; Percent complete: 27.3%; Average loss: 3.5320
Iteration: 1093; Percent complete: 27.3%; Average loss: 3.2901
Iteration: 1094; Percent complete: 27.4%; Average loss: 3.6574
Iteration: 1095; Percent complete: 27.4%; Average loss: 3.5634
Iteration: 1096; Percent complete: 27.4%; Average loss: 3.1949
Iteration: 1097; Percent complete: 27.4%; Average loss: 3.6465
Iteration: 1098; Percent complete: 27.5%; Average loss: 3.2579
Iteration: 1099; Percent complete: 27.5%; Average loss: 3.3714
Iteration: 1100; Percent complete: 27.5%; Average loss: 3.3420
Iteration: 1101; Percent complete: 27.5%; Average loss: 3.5086
Iteration: 1102; Percent complete: 27.6%; Average loss: 3.5058
Iteration: 1103; Percent complete: 27.6%; Average loss: 3.3221
Iteration: 1104; Percent complete: 27.6%; Average loss: 3.6323
Iteration: 1105; Percent complete: 27.6%; Average loss: 3.5060
Iteration: 1106; Percent complete: 27.7%; Average loss: 3.4759
Iteration: 1107; Percent complete: 27.7%; Average loss: 3.3893
Iteration: 1108; Percent complete: 27.7%; Average loss: 3.1702
Iteration: 1109; Percent complete: 27.7%; Average loss: 3.8340
Iteration: 1110; Percent complete: 27.8%; Average loss: 3.3206
Iteration: 1111; Percent complete: 27.8%; Average loss: 3.4365
Iteration: 1112; Percent complete: 27.8%; Average loss: 3.6680
Iteration: 1113; Percent complete: 27.8%; Average loss: 3.4618
Iteration: 1114; Percent complete: 27.9%; Average loss: 3.5950
Iteration: 1115; Percent complete: 27.9%; Average loss: 3.5912
Iteration: 1116; Percent complete: 27.9%; Average loss: 3.5461
Iteration: 1117; Percent complete: 27.9%; Average loss: 3.4293
Iteration: 1118; Percent complete: 28.0%; Average loss: 3.5301
Iteration: 1119; Percent complete: 28.0%; Average loss: 3.7124
Iteration: 1120; Percent complete: 28.0%; Average loss: 3.5029
Iteration: 1121; Percent complete: 28.0%; Average loss: 3.5691
Iteration: 1122; Percent complete: 28.1%; Average loss: 3.4268
Iteration: 1123; Percent complete: 28.1%; Average loss: 3.3504
Iteration: 1124; Percent complete: 28.1%; Average loss: 3.4160
Iteration: 1125; Percent complete: 28.1%; Average loss: 3.3086
Iteration: 1126; Percent complete: 28.1%; Average loss: 3.5504
Iteration: 1127; Percent complete: 28.2%; Average loss: 3.2866
Iteration: 1128; Percent complete: 28.2%; Average loss: 3.4305
Iteration: 1129; Percent complete: 28.2%; Average loss: 3.2484
Iteration: 1130; Percent complete: 28.2%; Average loss: 3.4562
Iteration: 1131; Percent complete: 28.3%; Average loss: 3.2908
Iteration: 1132; Percent complete: 28.3%; Average loss: 3.1675
Iteration: 1133; Percent complete: 28.3%; Average loss: 3.3916
Iteration: 1134; Percent complete: 28.3%; Average loss: 3.2933
Iteration: 1135; Percent complete: 28.4%; Average loss: 3.1527
Iteration: 1136; Percent complete: 28.4%; Average loss: 3.3094
Iteration: 1137; Percent complete: 28.4%; Average loss: 3.2400
Iteration: 1138; Percent complete: 28.4%; Average loss: 3.2605
Iteration: 1139; Percent complete: 28.5%; Average loss: 3.4817
Iteration: 1140; Percent complete: 28.5%; Average loss: 3.3993
Iteration: 1141; Percent complete: 28.5%; Average loss: 3.3791
Iteration: 1142; Percent complete: 28.5%; Average loss: 3.6890
Iteration: 1143; Percent complete: 28.6%; Average loss: 3.4668
Iteration: 1144; Percent complete: 28.6%; Average loss: 3.5288
Iteration: 1145; Percent complete: 28.6%; Average loss: 3.3795
Iteration: 1146; Percent complete: 28.6%; Average loss: 3.0910
Iteration: 1147; Percent complete: 28.7%; Average loss: 3.4790
Iteration: 1148; Percent complete: 28.7%; Average loss: 3.5801
Iteration: 1149; Percent complete: 28.7%; Average loss: 3.2696
Iteration: 1150; Percent complete: 28.7%; Average loss: 3.4947
Iteration: 1151; Percent complete: 28.8%; Average loss: 3.3406
Iteration: 1152; Percent complete: 28.8%; Average loss: 3.4047
Iteration: 1153; Percent complete: 28.8%; Average loss: 3.7315
Iteration: 1154; Percent complete: 28.8%; Average loss: 3.3732
Iteration: 1155; Percent complete: 28.9%; Average loss: 3.7971
Iteration: 1156; Percent complete: 28.9%; Average loss: 3.3513
Iteration: 1157; Percent complete: 28.9%; Average loss: 3.3886
Iteration: 1158; Percent complete: 28.9%; Average loss: 3.4245
Iteration: 1159; Percent complete: 29.0%; Average loss: 3.6295
Iteration: 1160; Percent complete: 29.0%; Average loss: 3.2518
Iteration: 1161; Percent complete: 29.0%; Average loss: 3.3968
Iteration: 1162; Percent complete: 29.0%; Average loss: 3.5494
Iteration: 1163; Percent complete: 29.1%; Average loss: 3.2757
Iteration: 1164; Percent complete: 29.1%; Average loss: 3.5448
Iteration: 1165; Percent complete: 29.1%; Average loss: 3.5376
Iteration: 1166; Percent complete: 29.1%; Average loss: 3.5449
Iteration: 1167; Percent complete: 29.2%; Average loss: 3.8531
Iteration: 1168; Percent complete: 29.2%; Average loss: 3.5158
Iteration: 1169; Percent complete: 29.2%; Average loss: 3.5266
Iteration: 1170; Percent complete: 29.2%; Average loss: 3.3165
Iteration: 1171; Percent complete: 29.3%; Average loss: 3.3694
Iteration: 1172; Percent complete: 29.3%; Average loss: 3.5267
Iteration: 1173; Percent complete: 29.3%; Average loss: 3.4585
Iteration: 1174; Percent complete: 29.3%; Average loss: 3.1296
Iteration: 1175; Percent complete: 29.4%; Average loss: 3.3750
Iteration: 1176; Percent complete: 29.4%; Average loss: 3.5357
Iteration: 1177; Percent complete: 29.4%; Average loss: 3.6176
Iteration: 1178; Percent complete: 29.4%; Average loss: 3.2599
Iteration: 1179; Percent complete: 29.5%; Average loss: 3.3060
Iteration: 1180; Percent complete: 29.5%; Average loss: 3.2495
Iteration: 1181; Percent complete: 29.5%; Average loss: 3.1928
Iteration: 1182; Percent complete: 29.5%; Average loss: 3.1807
Iteration: 1183; Percent complete: 29.6%; Average loss: 3.3338
Iteration: 1184; Percent complete: 29.6%; Average loss: 3.3444
Iteration: 1185; Percent complete: 29.6%; Average loss: 3.3910
Iteration: 1186; Percent complete: 29.6%; Average loss: 3.3649
Iteration: 1187; Percent complete: 29.7%; Average loss: 3.3846
Iteration: 1188; Percent complete: 29.7%; Average loss: 3.1934
Iteration: 1189; Percent complete: 29.7%; Average loss: 3.3473
Iteration: 1190; Percent complete: 29.8%; Average loss: 3.5270
Iteration: 1191; Percent complete: 29.8%; Average loss: 3.8433
Iteration: 1192; Percent complete: 29.8%; Average loss: 3.2840
Iteration: 1193; Percent complete: 29.8%; Average loss: 3.3730
Iteration: 1194; Percent complete: 29.8%; Average loss: 3.1534
Iteration: 1195; Percent complete: 29.9%; Average loss: 3.2464
Iteration: 1196; Percent complete: 29.9%; Average loss: 3.2180
Iteration: 1197; Percent complete: 29.9%; Average loss: 3.4091
Iteration: 1198; Percent complete: 29.9%; Average loss: 3.5906
Iteration: 1199; Percent complete: 30.0%; Average loss: 3.3590
Iteration: 1200; Percent complete: 30.0%; Average loss: 3.1050
Iteration: 1201; Percent complete: 30.0%; Average loss: 3.3815
Iteration: 1202; Percent complete: 30.0%; Average loss: 3.3262
Iteration: 1203; Percent complete: 30.1%; Average loss: 3.0591
Iteration: 1204; Percent complete: 30.1%; Average loss: 3.3252
Iteration: 1205; Percent complete: 30.1%; Average loss: 3.4651
Iteration: 1206; Percent complete: 30.1%; Average loss: 3.3437
Iteration: 1207; Percent complete: 30.2%; Average loss: 3.3224
Iteration: 1208; Percent complete: 30.2%; Average loss: 3.3949
Iteration: 1209; Percent complete: 30.2%; Average loss: 3.3809
Iteration: 1210; Percent complete: 30.2%; Average loss: 3.5774
Iteration: 1211; Percent complete: 30.3%; Average loss: 3.4936
Iteration: 1212; Percent complete: 30.3%; Average loss: 3.3997
Iteration: 1213; Percent complete: 30.3%; Average loss: 3.3930
Iteration: 1214; Percent complete: 30.3%; Average loss: 3.6016
Iteration: 1215; Percent complete: 30.4%; Average loss: 3.4145
Iteration: 1216; Percent complete: 30.4%; Average loss: 3.2374
Iteration: 1217; Percent complete: 30.4%; Average loss: 3.5117
Iteration: 1218; Percent complete: 30.4%; Average loss: 3.2152
Iteration: 1219; Percent complete: 30.5%; Average loss: 3.4283
Iteration: 1220; Percent complete: 30.5%; Average loss: 3.3946
Iteration: 1221; Percent complete: 30.5%; Average loss: 3.3950
Iteration: 1222; Percent complete: 30.6%; Average loss: 3.3214
Iteration: 1223; Percent complete: 30.6%; Average loss: 3.6849
Iteration: 1224; Percent complete: 30.6%; Average loss: 3.4003
Iteration: 1225; Percent complete: 30.6%; Average loss: 3.2879
Iteration: 1226; Percent complete: 30.6%; Average loss: 3.5873
Iteration: 1227; Percent complete: 30.7%; Average loss: 3.3635
Iteration: 1228; Percent complete: 30.7%; Average loss: 3.2149
Iteration: 1229; Percent complete: 30.7%; Average loss: 3.2299
Iteration: 1230; Percent complete: 30.8%; Average loss: 3.4670
Iteration: 1231; Percent complete: 30.8%; Average loss: 3.5283
Iteration: 1232; Percent complete: 30.8%; Average loss: 3.3002
Iteration: 1233; Percent complete: 30.8%; Average loss: 3.1820
Iteration: 1234; Percent complete: 30.9%; Average loss: 3.3778
Iteration: 1235; Percent complete: 30.9%; Average loss: 3.4963
Iteration: 1236; Percent complete: 30.9%; Average loss: 3.4976
Iteration: 1237; Percent complete: 30.9%; Average loss: 3.4460
Iteration: 1238; Percent complete: 30.9%; Average loss: 3.5362
Iteration: 1239; Percent complete: 31.0%; Average loss: 3.4327
Iteration: 1240; Percent complete: 31.0%; Average loss: 3.3710
Iteration: 1241; Percent complete: 31.0%; Average loss: 3.4202
Iteration: 1242; Percent complete: 31.1%; Average loss: 3.3866
Iteration: 1243; Percent complete: 31.1%; Average loss: 3.2327
Iteration: 1244; Percent complete: 31.1%; Average loss: 3.5727
Iteration: 1245; Percent complete: 31.1%; Average loss: 3.5181
Iteration: 1246; Percent complete: 31.1%; Average loss: 3.4227
Iteration: 1247; Percent complete: 31.2%; Average loss: 3.3577
Iteration: 1248; Percent complete: 31.2%; Average loss: 3.3763
Iteration: 1249; Percent complete: 31.2%; Average loss: 3.4824
Iteration: 1250; Percent complete: 31.2%; Average loss: 3.3855
Iteration: 1251; Percent complete: 31.3%; Average loss: 3.5070
Iteration: 1252; Percent complete: 31.3%; Average loss: 3.5071
Iteration: 1253; Percent complete: 31.3%; Average loss: 3.5173
Iteration: 1254; Percent complete: 31.4%; Average loss: 3.5316
Iteration: 1255; Percent complete: 31.4%; Average loss: 3.3398
Iteration: 1256; Percent complete: 31.4%; Average loss: 3.5217
Iteration: 1257; Percent complete: 31.4%; Average loss: 3.4185
Iteration: 1258; Percent complete: 31.4%; Average loss: 3.1484
Iteration: 1259; Percent complete: 31.5%; Average loss: 3.3958
Iteration: 1260; Percent complete: 31.5%; Average loss: 3.5192
Iteration: 1261; Percent complete: 31.5%; Average loss: 3.4432
Iteration: 1262; Percent complete: 31.6%; Average loss: 3.5833
Iteration: 1263; Percent complete: 31.6%; Average loss: 3.4419
Iteration: 1264; Percent complete: 31.6%; Average loss: 3.6054
Iteration: 1265; Percent complete: 31.6%; Average loss: 3.4790
Iteration: 1266; Percent complete: 31.6%; Average loss: 3.3411
Iteration: 1267; Percent complete: 31.7%; Average loss: 3.2623
Iteration: 1268; Percent complete: 31.7%; Average loss: 3.3840
Iteration: 1269; Percent complete: 31.7%; Average loss: 3.4129
Iteration: 1270; Percent complete: 31.8%; Average loss: 3.3269
Iteration: 1271; Percent complete: 31.8%; Average loss: 3.1116
Iteration: 1272; Percent complete: 31.8%; Average loss: 3.5592
Iteration: 1273; Percent complete: 31.8%; Average loss: 3.3348
Iteration: 1274; Percent complete: 31.9%; Average loss: 3.4229
Iteration: 1275; Percent complete: 31.9%; Average loss: 3.3457
Iteration: 1276; Percent complete: 31.9%; Average loss: 3.4039
Iteration: 1277; Percent complete: 31.9%; Average loss: 3.6894
Iteration: 1278; Percent complete: 31.9%; Average loss: 3.4253
Iteration: 1279; Percent complete: 32.0%; Average loss: 3.2540
Iteration: 1280; Percent complete: 32.0%; Average loss: 3.3148
Iteration: 1281; Percent complete: 32.0%; Average loss: 3.3196
Iteration: 1282; Percent complete: 32.0%; Average loss: 3.2914
Iteration: 1283; Percent complete: 32.1%; Average loss: 3.4682
Iteration: 1284; Percent complete: 32.1%; Average loss: 3.0097
Iteration: 1285; Percent complete: 32.1%; Average loss: 3.5407
Iteration: 1286; Percent complete: 32.1%; Average loss: 3.2971
Iteration: 1287; Percent complete: 32.2%; Average loss: 3.7135
Iteration: 1288; Percent complete: 32.2%; Average loss: 3.5315
Iteration: 1289; Percent complete: 32.2%; Average loss: 3.2698
Iteration: 1290; Percent complete: 32.2%; Average loss: 3.1276
Iteration: 1291; Percent complete: 32.3%; Average loss: 3.4680
Iteration: 1292; Percent complete: 32.3%; Average loss: 3.6707
Iteration: 1293; Percent complete: 32.3%; Average loss: 3.1626
Iteration: 1294; Percent complete: 32.4%; Average loss: 3.1614
Iteration: 1295; Percent complete: 32.4%; Average loss: 3.3031
Iteration: 1296; Percent complete: 32.4%; Average loss: 3.3949
Iteration: 1297; Percent complete: 32.4%; Average loss: 3.5961
Iteration: 1298; Percent complete: 32.5%; Average loss: 3.3041
Iteration: 1299; Percent complete: 32.5%; Average loss: 3.3799
Iteration: 1300; Percent complete: 32.5%; Average loss: 3.2941
Iteration: 1301; Percent complete: 32.5%; Average loss: 3.2335
Iteration: 1302; Percent complete: 32.6%; Average loss: 3.3944
Iteration: 1303; Percent complete: 32.6%; Average loss: 3.5501
Iteration: 1304; Percent complete: 32.6%; Average loss: 3.5126
Iteration: 1305; Percent complete: 32.6%; Average loss: 3.5412
Iteration: 1306; Percent complete: 32.6%; Average loss: 3.4425
Iteration: 1307; Percent complete: 32.7%; Average loss: 3.4681
Iteration: 1308; Percent complete: 32.7%; Average loss: 3.3840
Iteration: 1309; Percent complete: 32.7%; Average loss: 3.5433
Iteration: 1310; Percent complete: 32.8%; Average loss: 3.4310
Iteration: 1311; Percent complete: 32.8%; Average loss: 3.6317
Iteration: 1312; Percent complete: 32.8%; Average loss: 3.4442
Iteration: 1313; Percent complete: 32.8%; Average loss: 3.8114
Iteration: 1314; Percent complete: 32.9%; Average loss: 3.4693
Iteration: 1315; Percent complete: 32.9%; Average loss: 3.4131
Iteration: 1316; Percent complete: 32.9%; Average loss: 3.1376
Iteration: 1317; Percent complete: 32.9%; Average loss: 3.2553
Iteration: 1318; Percent complete: 33.0%; Average loss: 3.1063
Iteration: 1319; Percent complete: 33.0%; Average loss: 3.4271
Iteration: 1320; Percent complete: 33.0%; Average loss: 3.4041
Iteration: 1321; Percent complete: 33.0%; Average loss: 3.5371
Iteration: 1322; Percent complete: 33.1%; Average loss: 3.5956
Iteration: 1323; Percent complete: 33.1%; Average loss: 3.5512
Iteration: 1324; Percent complete: 33.1%; Average loss: 3.2985
Iteration: 1325; Percent complete: 33.1%; Average loss: 3.2304
Iteration: 1326; Percent complete: 33.1%; Average loss: 3.2232
Iteration: 1327; Percent complete: 33.2%; Average loss: 3.4544
Iteration: 1328; Percent complete: 33.2%; Average loss: 3.4440
Iteration: 1329; Percent complete: 33.2%; Average loss: 3.4857
Iteration: 1330; Percent complete: 33.2%; Average loss: 3.3934
Iteration: 1331; Percent complete: 33.3%; Average loss: 3.1614
Iteration: 1332; Percent complete: 33.3%; Average loss: 3.5011
Iteration: 1333; Percent complete: 33.3%; Average loss: 3.4793
Iteration: 1334; Percent complete: 33.4%; Average loss: 3.4609
Iteration: 1335; Percent complete: 33.4%; Average loss: 3.1695
Iteration: 1336; Percent complete: 33.4%; Average loss: 3.1640
Iteration: 1337; Percent complete: 33.4%; Average loss: 3.2156
Iteration: 1338; Percent complete: 33.5%; Average loss: 3.3315
Iteration: 1339; Percent complete: 33.5%; Average loss: 3.1406
Iteration: 1340; Percent complete: 33.5%; Average loss: 3.4230
Iteration: 1341; Percent complete: 33.5%; Average loss: 3.3965
Iteration: 1342; Percent complete: 33.6%; Average loss: 3.4447
Iteration: 1343; Percent complete: 33.6%; Average loss: 3.1371
Iteration: 1344; Percent complete: 33.6%; Average loss: 3.4563
Iteration: 1345; Percent complete: 33.6%; Average loss: 3.2153
Iteration: 1346; Percent complete: 33.7%; Average loss: 3.3159
Iteration: 1347; Percent complete: 33.7%; Average loss: 3.4610
Iteration: 1348; Percent complete: 33.7%; Average loss: 3.3049
Iteration: 1349; Percent complete: 33.7%; Average loss: 3.1393
Iteration: 1350; Percent complete: 33.8%; Average loss: 3.3195
Iteration: 1351; Percent complete: 33.8%; Average loss: 3.3421
Iteration: 1352; Percent complete: 33.8%; Average loss: 3.2516
Iteration: 1353; Percent complete: 33.8%; Average loss: 3.1615
Iteration: 1354; Percent complete: 33.9%; Average loss: 3.1589
Iteration: 1355; Percent complete: 33.9%; Average loss: 3.2528
Iteration: 1356; Percent complete: 33.9%; Average loss: 3.4888
Iteration: 1357; Percent complete: 33.9%; Average loss: 3.4426
Iteration: 1358; Percent complete: 34.0%; Average loss: 3.3759
Iteration: 1359; Percent complete: 34.0%; Average loss: 3.4697
Iteration: 1360; Percent complete: 34.0%; Average loss: 3.4682
Iteration: 1361; Percent complete: 34.0%; Average loss: 3.2125
Iteration: 1362; Percent complete: 34.1%; Average loss: 3.4404
Iteration: 1363; Percent complete: 34.1%; Average loss: 3.2868
Iteration: 1364; Percent complete: 34.1%; Average loss: 3.5116
Iteration: 1365; Percent complete: 34.1%; Average loss: 3.4652
Iteration: 1366; Percent complete: 34.2%; Average loss: 3.0613
Iteration: 1367; Percent complete: 34.2%; Average loss: 3.6621
Iteration: 1368; Percent complete: 34.2%; Average loss: 3.2751
Iteration: 1369; Percent complete: 34.2%; Average loss: 2.9960
Iteration: 1370; Percent complete: 34.2%; Average loss: 3.3961
Iteration: 1371; Percent complete: 34.3%; Average loss: 3.2235
Iteration: 1372; Percent complete: 34.3%; Average loss: 3.5627
Iteration: 1373; Percent complete: 34.3%; Average loss: 3.4833
Iteration: 1374; Percent complete: 34.4%; Average loss: 3.1291
Iteration: 1375; Percent complete: 34.4%; Average loss: 3.2652
Iteration: 1376; Percent complete: 34.4%; Average loss: 3.4318
Iteration: 1377; Percent complete: 34.4%; Average loss: 3.4221
Iteration: 1378; Percent complete: 34.4%; Average loss: 3.4047
Iteration: 1379; Percent complete: 34.5%; Average loss: 3.3853
Iteration: 1380; Percent complete: 34.5%; Average loss: 3.2326
Iteration: 1381; Percent complete: 34.5%; Average loss: 3.1839
Iteration: 1382; Percent complete: 34.5%; Average loss: 3.2786
Iteration: 1383; Percent complete: 34.6%; Average loss: 3.7843
Iteration: 1384; Percent complete: 34.6%; Average loss: 3.2426
Iteration: 1385; Percent complete: 34.6%; Average loss: 3.2868
Iteration: 1386; Percent complete: 34.6%; Average loss: 3.2439
Iteration: 1387; Percent complete: 34.7%; Average loss: 3.1001
Iteration: 1388; Percent complete: 34.7%; Average loss: 3.2434
Iteration: 1389; Percent complete: 34.7%; Average loss: 3.6946
Iteration: 1390; Percent complete: 34.8%; Average loss: 3.3149
Iteration: 1391; Percent complete: 34.8%; Average loss: 3.5436
Iteration: 1392; Percent complete: 34.8%; Average loss: 3.5218
Iteration: 1393; Percent complete: 34.8%; Average loss: 3.5441
Iteration: 1394; Percent complete: 34.8%; Average loss: 3.1997
Iteration: 1395; Percent complete: 34.9%; Average loss: 3.2896
Iteration: 1396; Percent complete: 34.9%; Average loss: 3.4100
Iteration: 1397; Percent complete: 34.9%; Average loss: 3.3695
Iteration: 1398; Percent complete: 34.9%; Average loss: 3.5974
Iteration: 1399; Percent complete: 35.0%; Average loss: 3.1592
Iteration: 1400; Percent complete: 35.0%; Average loss: 3.3298
Iteration: 1401; Percent complete: 35.0%; Average loss: 3.3777
Iteration: 1402; Percent complete: 35.0%; Average loss: 3.3672
Iteration: 1403; Percent complete: 35.1%; Average loss: 3.4130
Iteration: 1404; Percent complete: 35.1%; Average loss: 3.5133
Iteration: 1405; Percent complete: 35.1%; Average loss: 3.6309
Iteration: 1406; Percent complete: 35.1%; Average loss: 3.3521
Iteration: 1407; Percent complete: 35.2%; Average loss: 3.3504
Iteration: 1408; Percent complete: 35.2%; Average loss: 3.4004
Iteration: 1409; Percent complete: 35.2%; Average loss: 3.2658
Iteration: 1410; Percent complete: 35.2%; Average loss: 3.5259
Iteration: 1411; Percent complete: 35.3%; Average loss: 3.1941
Iteration: 1412; Percent complete: 35.3%; Average loss: 3.3196
Iteration: 1413; Percent complete: 35.3%; Average loss: 3.3881
Iteration: 1414; Percent complete: 35.4%; Average loss: 3.5106
Iteration: 1415; Percent complete: 35.4%; Average loss: 3.4215
Iteration: 1416; Percent complete: 35.4%; Average loss: 3.1325
Iteration: 1417; Percent complete: 35.4%; Average loss: 3.0492
Iteration: 1418; Percent complete: 35.4%; Average loss: 3.3180
Iteration: 1419; Percent complete: 35.5%; Average loss: 3.3116
Iteration: 1420; Percent complete: 35.5%; Average loss: 3.4288
Iteration: 1421; Percent complete: 35.5%; Average loss: 3.3611
Iteration: 1422; Percent complete: 35.5%; Average loss: 3.3225
Iteration: 1423; Percent complete: 35.6%; Average loss: 3.1884
Iteration: 1424; Percent complete: 35.6%; Average loss: 3.2446
Iteration: 1425; Percent complete: 35.6%; Average loss: 3.1888
Iteration: 1426; Percent complete: 35.6%; Average loss: 3.3257
Iteration: 1427; Percent complete: 35.7%; Average loss: 3.5093
Iteration: 1428; Percent complete: 35.7%; Average loss: 3.2949
Iteration: 1429; Percent complete: 35.7%; Average loss: 3.0959
Iteration: 1430; Percent complete: 35.8%; Average loss: 3.4297
Iteration: 1431; Percent complete: 35.8%; Average loss: 3.3662
Iteration: 1432; Percent complete: 35.8%; Average loss: 3.2003
Iteration: 1433; Percent complete: 35.8%; Average loss: 3.7307
Iteration: 1434; Percent complete: 35.9%; Average loss: 3.2726
Iteration: 1435; Percent complete: 35.9%; Average loss: 3.1541
Iteration: 1436; Percent complete: 35.9%; Average loss: 3.4538
Iteration: 1437; Percent complete: 35.9%; Average loss: 3.3354
Iteration: 1438; Percent complete: 35.9%; Average loss: 3.4106
Iteration: 1439; Percent complete: 36.0%; Average loss: 3.3617
Iteration: 1440; Percent complete: 36.0%; Average loss: 3.1184
Iteration: 1441; Percent complete: 36.0%; Average loss: 3.2064
Iteration: 1442; Percent complete: 36.0%; Average loss: 3.2746
Iteration: 1443; Percent complete: 36.1%; Average loss: 3.1972
Iteration: 1444; Percent complete: 36.1%; Average loss: 3.3654
Iteration: 1445; Percent complete: 36.1%; Average loss: 3.3533
Iteration: 1446; Percent complete: 36.1%; Average loss: 3.3825
Iteration: 1447; Percent complete: 36.2%; Average loss: 3.1101
Iteration: 1448; Percent complete: 36.2%; Average loss: 3.3950
Iteration: 1449; Percent complete: 36.2%; Average loss: 3.0984
Iteration: 1450; Percent complete: 36.2%; Average loss: 3.1534
Iteration: 1451; Percent complete: 36.3%; Average loss: 3.1321
Iteration: 1452; Percent complete: 36.3%; Average loss: 3.4567
Iteration: 1453; Percent complete: 36.3%; Average loss: 3.3707
Iteration: 1454; Percent complete: 36.4%; Average loss: 3.4844
Iteration: 1455; Percent complete: 36.4%; Average loss: 3.3046
Iteration: 1456; Percent complete: 36.4%; Average loss: 3.3382
Iteration: 1457; Percent complete: 36.4%; Average loss: 3.5500
Iteration: 1458; Percent complete: 36.4%; Average loss: 3.3544
Iteration: 1459; Percent complete: 36.5%; Average loss: 3.1427
Iteration: 1460; Percent complete: 36.5%; Average loss: 3.4967
Iteration: 1461; Percent complete: 36.5%; Average loss: 3.0727
Iteration: 1462; Percent complete: 36.5%; Average loss: 3.2411
Iteration: 1463; Percent complete: 36.6%; Average loss: 3.2637
Iteration: 1464; Percent complete: 36.6%; Average loss: 3.3069
Iteration: 1465; Percent complete: 36.6%; Average loss: 3.1976
Iteration: 1466; Percent complete: 36.6%; Average loss: 3.1064
Iteration: 1467; Percent complete: 36.7%; Average loss: 3.1428
Iteration: 1468; Percent complete: 36.7%; Average loss: 3.3172
Iteration: 1469; Percent complete: 36.7%; Average loss: 3.1498
Iteration: 1470; Percent complete: 36.8%; Average loss: 3.2200
Iteration: 1471; Percent complete: 36.8%; Average loss: 3.4463
Iteration: 1472; Percent complete: 36.8%; Average loss: 3.4407
Iteration: 1473; Percent complete: 36.8%; Average loss: 3.3482
Iteration: 1474; Percent complete: 36.9%; Average loss: 3.4018
Iteration: 1475; Percent complete: 36.9%; Average loss: 3.1923
Iteration: 1476; Percent complete: 36.9%; Average loss: 3.4623
Iteration: 1477; Percent complete: 36.9%; Average loss: 3.3186
Iteration: 1478; Percent complete: 37.0%; Average loss: 3.3715
Iteration: 1479; Percent complete: 37.0%; Average loss: 3.2744
Iteration: 1480; Percent complete: 37.0%; Average loss: 3.1848
Iteration: 1481; Percent complete: 37.0%; Average loss: 3.2652
Iteration: 1482; Percent complete: 37.0%; Average loss: 3.4939
Iteration: 1483; Percent complete: 37.1%; Average loss: 3.2872
Iteration: 1484; Percent complete: 37.1%; Average loss: 3.2156
Iteration: 1485; Percent complete: 37.1%; Average loss: 3.1620
Iteration: 1486; Percent complete: 37.1%; Average loss: 3.5946
Iteration: 1487; Percent complete: 37.2%; Average loss: 3.3287
Iteration: 1488; Percent complete: 37.2%; Average loss: 3.1629
Iteration: 1489; Percent complete: 37.2%; Average loss: 3.6373
Iteration: 1490; Percent complete: 37.2%; Average loss: 3.7212
Iteration: 1491; Percent complete: 37.3%; Average loss: 3.1819
Iteration: 1492; Percent complete: 37.3%; Average loss: 3.1992
Iteration: 1493; Percent complete: 37.3%; Average loss: 3.5014
Iteration: 1494; Percent complete: 37.4%; Average loss: 3.4246
Iteration: 1495; Percent complete: 37.4%; Average loss: 3.1877
Iteration: 1496; Percent complete: 37.4%; Average loss: 3.2147
Iteration: 1497; Percent complete: 37.4%; Average loss: 3.4572
Iteration: 1498; Percent complete: 37.5%; Average loss: 3.3022
Iteration: 1499; Percent complete: 37.5%; Average loss: 3.1509
Iteration: 1500; Percent complete: 37.5%; Average loss: 3.3804
Iteration: 1501; Percent complete: 37.5%; Average loss: 3.1727
Iteration: 1502; Percent complete: 37.5%; Average loss: 3.0013
Iteration: 1503; Percent complete: 37.6%; Average loss: 3.3775
Iteration: 1504; Percent complete: 37.6%; Average loss: 3.1436
Iteration: 1505; Percent complete: 37.6%; Average loss: 3.2079
Iteration: 1506; Percent complete: 37.6%; Average loss: 3.4313
Iteration: 1507; Percent complete: 37.7%; Average loss: 3.3878
Iteration: 1508; Percent complete: 37.7%; Average loss: 3.3156
Iteration: 1509; Percent complete: 37.7%; Average loss: 3.2859
Iteration: 1510; Percent complete: 37.8%; Average loss: 3.4479
Iteration: 1511; Percent complete: 37.8%; Average loss: 3.3667
Iteration: 1512; Percent complete: 37.8%; Average loss: 2.9804
Iteration: 1513; Percent complete: 37.8%; Average loss: 3.2906
Iteration: 1514; Percent complete: 37.9%; Average loss: 3.3354
Iteration: 1515; Percent complete: 37.9%; Average loss: 3.1496
Iteration: 1516; Percent complete: 37.9%; Average loss: 3.3221
Iteration: 1517; Percent complete: 37.9%; Average loss: 3.2909
Iteration: 1518; Percent complete: 38.0%; Average loss: 3.3370
Iteration: 1519; Percent complete: 38.0%; Average loss: 3.3068
Iteration: 1520; Percent complete: 38.0%; Average loss: 3.5364
Iteration: 1521; Percent complete: 38.0%; Average loss: 3.2304
Iteration: 1522; Percent complete: 38.0%; Average loss: 3.1582
Iteration: 1523; Percent complete: 38.1%; Average loss: 3.4144
Iteration: 1524; Percent complete: 38.1%; Average loss: 3.4319
Iteration: 1525; Percent complete: 38.1%; Average loss: 3.0073
Iteration: 1526; Percent complete: 38.1%; Average loss: 3.3497
Iteration: 1527; Percent complete: 38.2%; Average loss: 3.3872
Iteration: 1528; Percent complete: 38.2%; Average loss: 3.2004
Iteration: 1529; Percent complete: 38.2%; Average loss: 3.2785
Iteration: 1530; Percent complete: 38.2%; Average loss: 3.3237
Iteration: 1531; Percent complete: 38.3%; Average loss: 3.3261
Iteration: 1532; Percent complete: 38.3%; Average loss: 2.9581
Iteration: 1533; Percent complete: 38.3%; Average loss: 3.5612
Iteration: 1534; Percent complete: 38.4%; Average loss: 3.2130
Iteration: 1535; Percent complete: 38.4%; Average loss: 3.2411
Iteration: 1536; Percent complete: 38.4%; Average loss: 3.3731
Iteration: 1537; Percent complete: 38.4%; Average loss: 3.2636
Iteration: 1538; Percent complete: 38.5%; Average loss: 3.1227
Iteration: 1539; Percent complete: 38.5%; Average loss: 3.4256
Iteration: 1540; Percent complete: 38.5%; Average loss: 3.5424
Iteration: 1541; Percent complete: 38.5%; Average loss: 3.3783
Iteration: 1542; Percent complete: 38.6%; Average loss: 3.2644
Iteration: 1543; Percent complete: 38.6%; Average loss: 3.3612
Iteration: 1544; Percent complete: 38.6%; Average loss: 3.3179
Iteration: 1545; Percent complete: 38.6%; Average loss: 3.2040
Iteration: 1546; Percent complete: 38.6%; Average loss: 3.3189
Iteration: 1547; Percent complete: 38.7%; Average loss: 3.2334
Iteration: 1548; Percent complete: 38.7%; Average loss: 3.2489
Iteration: 1549; Percent complete: 38.7%; Average loss: 3.1690
Iteration: 1550; Percent complete: 38.8%; Average loss: 3.4142
Iteration: 1551; Percent complete: 38.8%; Average loss: 3.5214
Iteration: 1552; Percent complete: 38.8%; Average loss: 3.2788
Iteration: 1553; Percent complete: 38.8%; Average loss: 3.5172
Iteration: 1554; Percent complete: 38.9%; Average loss: 3.1886
Iteration: 1555; Percent complete: 38.9%; Average loss: 3.5120
Iteration: 1556; Percent complete: 38.9%; Average loss: 3.1987
Iteration: 1557; Percent complete: 38.9%; Average loss: 3.3861
Iteration: 1558; Percent complete: 39.0%; Average loss: 3.1394
Iteration: 1559; Percent complete: 39.0%; Average loss: 3.3271
Iteration: 1560; Percent complete: 39.0%; Average loss: 3.2532
Iteration: 1561; Percent complete: 39.0%; Average loss: 3.3441
Iteration: 1562; Percent complete: 39.1%; Average loss: 3.3153
Iteration: 1563; Percent complete: 39.1%; Average loss: 3.5049
Iteration: 1564; Percent complete: 39.1%; Average loss: 3.3049
Iteration: 1565; Percent complete: 39.1%; Average loss: 3.1363
Iteration: 1566; Percent complete: 39.1%; Average loss: 3.1016
Iteration: 1567; Percent complete: 39.2%; Average loss: 3.2327
Iteration: 1568; Percent complete: 39.2%; Average loss: 3.1518
Iteration: 1569; Percent complete: 39.2%; Average loss: 3.3787
Iteration: 1570; Percent complete: 39.2%; Average loss: 3.1691
Iteration: 1571; Percent complete: 39.3%; Average loss: 3.0466
Iteration: 1572; Percent complete: 39.3%; Average loss: 3.5374
Iteration: 1573; Percent complete: 39.3%; Average loss: 3.3401
Iteration: 1574; Percent complete: 39.4%; Average loss: 3.2407
Iteration: 1575; Percent complete: 39.4%; Average loss: 3.3653
Iteration: 1576; Percent complete: 39.4%; Average loss: 3.4464
Iteration: 1577; Percent complete: 39.4%; Average loss: 3.3720
Iteration: 1578; Percent complete: 39.5%; Average loss: 3.2854
Iteration: 1579; Percent complete: 39.5%; Average loss: 3.3192
Iteration: 1580; Percent complete: 39.5%; Average loss: 3.2125
Iteration: 1581; Percent complete: 39.5%; Average loss: 3.3693
Iteration: 1582; Percent complete: 39.6%; Average loss: 3.3652
Iteration: 1583; Percent complete: 39.6%; Average loss: 3.4687
Iteration: 1584; Percent complete: 39.6%; Average loss: 3.4662
Iteration: 1585; Percent complete: 39.6%; Average loss: 3.0277
Iteration: 1586; Percent complete: 39.6%; Average loss: 3.3980
Iteration: 1587; Percent complete: 39.7%; Average loss: 3.3067
Iteration: 1588; Percent complete: 39.7%; Average loss: 3.2563
Iteration: 1589; Percent complete: 39.7%; Average loss: 2.9678
Iteration: 1590; Percent complete: 39.8%; Average loss: 3.4420
Iteration: 1591; Percent complete: 39.8%; Average loss: 3.2105
Iteration: 1592; Percent complete: 39.8%; Average loss: 3.4130
Iteration: 1593; Percent complete: 39.8%; Average loss: 3.5602
Iteration: 1594; Percent complete: 39.9%; Average loss: 3.4251
Iteration: 1595; Percent complete: 39.9%; Average loss: 3.3788
Iteration: 1596; Percent complete: 39.9%; Average loss: 2.9168
Iteration: 1597; Percent complete: 39.9%; Average loss: 3.4721
Iteration: 1598; Percent complete: 40.0%; Average loss: 3.0924
Iteration: 1599; Percent complete: 40.0%; Average loss: 3.3678
Iteration: 1600; Percent complete: 40.0%; Average loss: 3.3817
Iteration: 1601; Percent complete: 40.0%; Average loss: 3.1652
Iteration: 1602; Percent complete: 40.1%; Average loss: 3.1635
Iteration: 1603; Percent complete: 40.1%; Average loss: 3.2696
Iteration: 1604; Percent complete: 40.1%; Average loss: 3.3125
Iteration: 1605; Percent complete: 40.1%; Average loss: 3.1741
Iteration: 1606; Percent complete: 40.2%; Average loss: 3.2087
Iteration: 1607; Percent complete: 40.2%; Average loss: 3.4882
Iteration: 1608; Percent complete: 40.2%; Average loss: 3.4454
Iteration: 1609; Percent complete: 40.2%; Average loss: 3.3640
Iteration: 1610; Percent complete: 40.2%; Average loss: 3.1037
Iteration: 1611; Percent complete: 40.3%; Average loss: 3.2685
Iteration: 1612; Percent complete: 40.3%; Average loss: 3.2749
Iteration: 1613; Percent complete: 40.3%; Average loss: 3.3404
Iteration: 1614; Percent complete: 40.4%; Average loss: 3.1896
Iteration: 1615; Percent complete: 40.4%; Average loss: 3.3961
Iteration: 1616; Percent complete: 40.4%; Average loss: 3.4232
Iteration: 1617; Percent complete: 40.4%; Average loss: 3.2066
Iteration: 1618; Percent complete: 40.5%; Average loss: 3.7104
Iteration: 1619; Percent complete: 40.5%; Average loss: 3.2504
Iteration: 1620; Percent complete: 40.5%; Average loss: 3.5159
Iteration: 1621; Percent complete: 40.5%; Average loss: 3.0322
Iteration: 1622; Percent complete: 40.6%; Average loss: 3.1223
Iteration: 1623; Percent complete: 40.6%; Average loss: 3.1582
Iteration: 1624; Percent complete: 40.6%; Average loss: 3.4548
Iteration: 1625; Percent complete: 40.6%; Average loss: 3.0996
Iteration: 1626; Percent complete: 40.6%; Average loss: 3.2310
Iteration: 1627; Percent complete: 40.7%; Average loss: 3.2063
Iteration: 1628; Percent complete: 40.7%; Average loss: 3.1018
Iteration: 1629; Percent complete: 40.7%; Average loss: 3.3060
Iteration: 1630; Percent complete: 40.8%; Average loss: 3.1249
Iteration: 1631; Percent complete: 40.8%; Average loss: 3.1515
Iteration: 1632; Percent complete: 40.8%; Average loss: 3.5000
Iteration: 1633; Percent complete: 40.8%; Average loss: 3.2617
Iteration: 1634; Percent complete: 40.8%; Average loss: 3.4114
Iteration: 1635; Percent complete: 40.9%; Average loss: 2.9934
Iteration: 1636; Percent complete: 40.9%; Average loss: 3.2320
Iteration: 1637; Percent complete: 40.9%; Average loss: 3.5565
Iteration: 1638; Percent complete: 40.9%; Average loss: 3.3017
Iteration: 1639; Percent complete: 41.0%; Average loss: 3.2635
Iteration: 1640; Percent complete: 41.0%; Average loss: 3.2718
Iteration: 1641; Percent complete: 41.0%; Average loss: 3.2216
Iteration: 1642; Percent complete: 41.0%; Average loss: 3.3322
Iteration: 1643; Percent complete: 41.1%; Average loss: 3.1930
Iteration: 1644; Percent complete: 41.1%; Average loss: 3.1721
Iteration: 1645; Percent complete: 41.1%; Average loss: 3.2828
Iteration: 1646; Percent complete: 41.1%; Average loss: 3.0279
Iteration: 1647; Percent complete: 41.2%; Average loss: 3.6980
Iteration: 1648; Percent complete: 41.2%; Average loss: 3.1776
Iteration: 1649; Percent complete: 41.2%; Average loss: 3.4167
Iteration: 1650; Percent complete: 41.2%; Average loss: 3.4955
Iteration: 1651; Percent complete: 41.3%; Average loss: 3.2672
Iteration: 1652; Percent complete: 41.3%; Average loss: 3.4407
Iteration: 1653; Percent complete: 41.3%; Average loss: 3.2567
Iteration: 1654; Percent complete: 41.3%; Average loss: 3.3773
Iteration: 1655; Percent complete: 41.4%; Average loss: 3.2395
Iteration: 1656; Percent complete: 41.4%; Average loss: 3.3244
Iteration: 1657; Percent complete: 41.4%; Average loss: 3.2086
Iteration: 1658; Percent complete: 41.4%; Average loss: 3.1537
Iteration: 1659; Percent complete: 41.5%; Average loss: 3.3469
Iteration: 1660; Percent complete: 41.5%; Average loss: 3.4224
Iteration: 1661; Percent complete: 41.5%; Average loss: 3.5685
Iteration: 1662; Percent complete: 41.5%; Average loss: 3.4418
Iteration: 1663; Percent complete: 41.6%; Average loss: 3.1362
Iteration: 1664; Percent complete: 41.6%; Average loss: 3.3857
Iteration: 1665; Percent complete: 41.6%; Average loss: 3.0900
Iteration: 1666; Percent complete: 41.6%; Average loss: 3.4043
Iteration: 1667; Percent complete: 41.7%; Average loss: 3.2178
Iteration: 1668; Percent complete: 41.7%; Average loss: 3.3986
Iteration: 1669; Percent complete: 41.7%; Average loss: 3.3512
Iteration: 1670; Percent complete: 41.8%; Average loss: 3.2368
Iteration: 1671; Percent complete: 41.8%; Average loss: 3.3456
Iteration: 1672; Percent complete: 41.8%; Average loss: 3.3785
Iteration: 1673; Percent complete: 41.8%; Average loss: 3.2354
Iteration: 1674; Percent complete: 41.9%; Average loss: 3.4616
Iteration: 1675; Percent complete: 41.9%; Average loss: 3.0706
Iteration: 1676; Percent complete: 41.9%; Average loss: 3.2215
Iteration: 1677; Percent complete: 41.9%; Average loss: 3.2281
Iteration: 1678; Percent complete: 41.9%; Average loss: 3.6604
Iteration: 1679; Percent complete: 42.0%; Average loss: 3.3734
Iteration: 1680; Percent complete: 42.0%; Average loss: 2.9573
Iteration: 1681; Percent complete: 42.0%; Average loss: 3.3493
Iteration: 1682; Percent complete: 42.0%; Average loss: 3.0956
Iteration: 1683; Percent complete: 42.1%; Average loss: 3.0937
Iteration: 1684; Percent complete: 42.1%; Average loss: 3.1124
Iteration: 1685; Percent complete: 42.1%; Average loss: 3.4036
Iteration: 1686; Percent complete: 42.1%; Average loss: 3.3757
Iteration: 1687; Percent complete: 42.2%; Average loss: 3.1713
Iteration: 1688; Percent complete: 42.2%; Average loss: 3.1843
Iteration: 1689; Percent complete: 42.2%; Average loss: 3.3624
Iteration: 1690; Percent complete: 42.2%; Average loss: 3.1620
Iteration: 1691; Percent complete: 42.3%; Average loss: 3.5701
Iteration: 1692; Percent complete: 42.3%; Average loss: 3.3073
Iteration: 1693; Percent complete: 42.3%; Average loss: 3.3009
Iteration: 1694; Percent complete: 42.4%; Average loss: 3.3925
Iteration: 1695; Percent complete: 42.4%; Average loss: 3.2882
Iteration: 1696; Percent complete: 42.4%; Average loss: 3.3192
Iteration: 1697; Percent complete: 42.4%; Average loss: 3.2963
Iteration: 1698; Percent complete: 42.4%; Average loss: 3.1505
Iteration: 1699; Percent complete: 42.5%; Average loss: 3.4272
Iteration: 1700; Percent complete: 42.5%; Average loss: 3.4429
Iteration: 1701; Percent complete: 42.5%; Average loss: 3.2531
Iteration: 1702; Percent complete: 42.5%; Average loss: 3.0582
Iteration: 1703; Percent complete: 42.6%; Average loss: 3.2854
Iteration: 1704; Percent complete: 42.6%; Average loss: 3.0758
Iteration: 1705; Percent complete: 42.6%; Average loss: 3.3367
Iteration: 1706; Percent complete: 42.6%; Average loss: 3.0525
Iteration: 1707; Percent complete: 42.7%; Average loss: 3.3004
Iteration: 1708; Percent complete: 42.7%; Average loss: 3.2107
Iteration: 1709; Percent complete: 42.7%; Average loss: 3.4669
Iteration: 1710; Percent complete: 42.8%; Average loss: 3.2699
Iteration: 1711; Percent complete: 42.8%; Average loss: 3.1321
Iteration: 1712; Percent complete: 42.8%; Average loss: 3.0941
Iteration: 1713; Percent complete: 42.8%; Average loss: 3.2334
Iteration: 1714; Percent complete: 42.9%; Average loss: 3.1924
Iteration: 1715; Percent complete: 42.9%; Average loss: 3.2795
Iteration: 1716; Percent complete: 42.9%; Average loss: 3.2375
Iteration: 1717; Percent complete: 42.9%; Average loss: 3.5032
Iteration: 1718; Percent complete: 43.0%; Average loss: 3.2421
Iteration: 1719; Percent complete: 43.0%; Average loss: 3.3058
Iteration: 1720; Percent complete: 43.0%; Average loss: 3.3190
Iteration: 1721; Percent complete: 43.0%; Average loss: 3.1477
Iteration: 1722; Percent complete: 43.0%; Average loss: 3.1798
Iteration: 1723; Percent complete: 43.1%; Average loss: 3.2205
Iteration: 1724; Percent complete: 43.1%; Average loss: 3.2657
Iteration: 1725; Percent complete: 43.1%; Average loss: 3.0949
Iteration: 1726; Percent complete: 43.1%; Average loss: 3.1220
Iteration: 1727; Percent complete: 43.2%; Average loss: 3.2732
Iteration: 1728; Percent complete: 43.2%; Average loss: 3.1663
Iteration: 1729; Percent complete: 43.2%; Average loss: 3.1827
Iteration: 1730; Percent complete: 43.2%; Average loss: 3.1089
Iteration: 1731; Percent complete: 43.3%; Average loss: 3.3160
Iteration: 1732; Percent complete: 43.3%; Average loss: 3.1902
Iteration: 1733; Percent complete: 43.3%; Average loss: 3.1222
Iteration: 1734; Percent complete: 43.4%; Average loss: 3.0925
Iteration: 1735; Percent complete: 43.4%; Average loss: 3.2637
Iteration: 1736; Percent complete: 43.4%; Average loss: 3.2772
Iteration: 1737; Percent complete: 43.4%; Average loss: 3.1176
Iteration: 1738; Percent complete: 43.5%; Average loss: 3.3201
Iteration: 1739; Percent complete: 43.5%; Average loss: 3.0940
Iteration: 1740; Percent complete: 43.5%; Average loss: 3.0474
Iteration: 1741; Percent complete: 43.5%; Average loss: 3.4070
Iteration: 1742; Percent complete: 43.5%; Average loss: 3.3393
Iteration: 1743; Percent complete: 43.6%; Average loss: 3.5027
Iteration: 1744; Percent complete: 43.6%; Average loss: 3.4383
Iteration: 1745; Percent complete: 43.6%; Average loss: 3.1728
Iteration: 1746; Percent complete: 43.6%; Average loss: 3.1473
Iteration: 1747; Percent complete: 43.7%; Average loss: 3.2346
Iteration: 1748; Percent complete: 43.7%; Average loss: 3.2270
Iteration: 1749; Percent complete: 43.7%; Average loss: 3.3951
Iteration: 1750; Percent complete: 43.8%; Average loss: 3.2164
Iteration: 1751; Percent complete: 43.8%; Average loss: 3.4912
Iteration: 1752; Percent complete: 43.8%; Average loss: 3.0002
Iteration: 1753; Percent complete: 43.8%; Average loss: 3.1068
Iteration: 1754; Percent complete: 43.9%; Average loss: 3.2496
Iteration: 1755; Percent complete: 43.9%; Average loss: 3.2798
Iteration: 1756; Percent complete: 43.9%; Average loss: 3.3984
Iteration: 1757; Percent complete: 43.9%; Average loss: 3.1300
Iteration: 1758; Percent complete: 44.0%; Average loss: 2.9910
Iteration: 1759; Percent complete: 44.0%; Average loss: 3.0780
Iteration: 1760; Percent complete: 44.0%; Average loss: 3.4111
Iteration: 1761; Percent complete: 44.0%; Average loss: 3.2972
Iteration: 1762; Percent complete: 44.0%; Average loss: 3.2766
Iteration: 1763; Percent complete: 44.1%; Average loss: 3.2918
Iteration: 1764; Percent complete: 44.1%; Average loss: 3.2309
Iteration: 1765; Percent complete: 44.1%; Average loss: 3.4194
Iteration: 1766; Percent complete: 44.1%; Average loss: 3.5132
Iteration: 1767; Percent complete: 44.2%; Average loss: 3.3610
Iteration: 1768; Percent complete: 44.2%; Average loss: 3.1755
Iteration: 1769; Percent complete: 44.2%; Average loss: 3.4473
Iteration: 1770; Percent complete: 44.2%; Average loss: 3.5579
Iteration: 1771; Percent complete: 44.3%; Average loss: 3.0912
Iteration: 1772; Percent complete: 44.3%; Average loss: 3.4153
Iteration: 1773; Percent complete: 44.3%; Average loss: 3.0673
Iteration: 1774; Percent complete: 44.4%; Average loss: 3.3380
Iteration: 1775; Percent complete: 44.4%; Average loss: 3.2408
Iteration: 1776; Percent complete: 44.4%; Average loss: 3.2966
Iteration: 1777; Percent complete: 44.4%; Average loss: 3.1866
Iteration: 1778; Percent complete: 44.5%; Average loss: 3.0335
Iteration: 1779; Percent complete: 44.5%; Average loss: 3.4976
Iteration: 1780; Percent complete: 44.5%; Average loss: 3.1421
Iteration: 1781; Percent complete: 44.5%; Average loss: 2.9110
Iteration: 1782; Percent complete: 44.5%; Average loss: 3.4209
Iteration: 1783; Percent complete: 44.6%; Average loss: 3.3041
Iteration: 1784; Percent complete: 44.6%; Average loss: 3.2903
Iteration: 1785; Percent complete: 44.6%; Average loss: 3.2818
Iteration: 1786; Percent complete: 44.6%; Average loss: 3.1219
Iteration: 1787; Percent complete: 44.7%; Average loss: 3.1699
Iteration: 1788; Percent complete: 44.7%; Average loss: 3.2132
Iteration: 1789; Percent complete: 44.7%; Average loss: 3.2578
Iteration: 1790; Percent complete: 44.8%; Average loss: 3.1936
Iteration: 1791; Percent complete: 44.8%; Average loss: 3.3682
Iteration: 1792; Percent complete: 44.8%; Average loss: 3.1340
Iteration: 1793; Percent complete: 44.8%; Average loss: 3.1663
Iteration: 1794; Percent complete: 44.9%; Average loss: 3.2152
Iteration: 1795; Percent complete: 44.9%; Average loss: 3.0882
Iteration: 1796; Percent complete: 44.9%; Average loss: 3.1557
Iteration: 1797; Percent complete: 44.9%; Average loss: 3.0517
Iteration: 1798; Percent complete: 45.0%; Average loss: 3.2255
Iteration: 1799; Percent complete: 45.0%; Average loss: 3.3505
Iteration: 1800; Percent complete: 45.0%; Average loss: 3.2122
Iteration: 1801; Percent complete: 45.0%; Average loss: 3.2972
Iteration: 1802; Percent complete: 45.1%; Average loss: 3.1466
Iteration: 1803; Percent complete: 45.1%; Average loss: 3.0986
Iteration: 1804; Percent complete: 45.1%; Average loss: 3.1609
Iteration: 1805; Percent complete: 45.1%; Average loss: 3.1977
Iteration: 1806; Percent complete: 45.1%; Average loss: 3.3261
Iteration: 1807; Percent complete: 45.2%; Average loss: 3.2229
Iteration: 1808; Percent complete: 45.2%; Average loss: 3.2200
Iteration: 1809; Percent complete: 45.2%; Average loss: 3.2128
Iteration: 1810; Percent complete: 45.2%; Average loss: 3.2031
Iteration: 1811; Percent complete: 45.3%; Average loss: 3.1261
Iteration: 1812; Percent complete: 45.3%; Average loss: 3.3599
Iteration: 1813; Percent complete: 45.3%; Average loss: 3.4481
Iteration: 1814; Percent complete: 45.4%; Average loss: 3.2998
Iteration: 1815; Percent complete: 45.4%; Average loss: 3.1319
Iteration: 1816; Percent complete: 45.4%; Average loss: 2.8948
Iteration: 1817; Percent complete: 45.4%; Average loss: 3.0838
Iteration: 1818; Percent complete: 45.5%; Average loss: 3.2117
Iteration: 1819; Percent complete: 45.5%; Average loss: 3.3102
Iteration: 1820; Percent complete: 45.5%; Average loss: 2.9065
Iteration: 1821; Percent complete: 45.5%; Average loss: 3.3644
Iteration: 1822; Percent complete: 45.6%; Average loss: 3.3043
Iteration: 1823; Percent complete: 45.6%; Average loss: 3.2176
Iteration: 1824; Percent complete: 45.6%; Average loss: 3.2931
Iteration: 1825; Percent complete: 45.6%; Average loss: 2.9723
Iteration: 1826; Percent complete: 45.6%; Average loss: 2.8818
Iteration: 1827; Percent complete: 45.7%; Average loss: 3.0329
Iteration: 1828; Percent complete: 45.7%; Average loss: 3.2497
Iteration: 1829; Percent complete: 45.7%; Average loss: 3.2604
Iteration: 1830; Percent complete: 45.8%; Average loss: 3.0930
Iteration: 1831; Percent complete: 45.8%; Average loss: 3.2844
Iteration: 1832; Percent complete: 45.8%; Average loss: 3.2285
Iteration: 1833; Percent complete: 45.8%; Average loss: 2.9494
Iteration: 1834; Percent complete: 45.9%; Average loss: 3.1861
Iteration: 1835; Percent complete: 45.9%; Average loss: 3.2493
Iteration: 1836; Percent complete: 45.9%; Average loss: 3.2908
Iteration: 1837; Percent complete: 45.9%; Average loss: 3.0787
Iteration: 1838; Percent complete: 46.0%; Average loss: 2.9943
Iteration: 1839; Percent complete: 46.0%; Average loss: 3.3569
Iteration: 1840; Percent complete: 46.0%; Average loss: 2.9784
Iteration: 1841; Percent complete: 46.0%; Average loss: 3.2687
Iteration: 1842; Percent complete: 46.1%; Average loss: 3.1961
Iteration: 1843; Percent complete: 46.1%; Average loss: 3.1140
Iteration: 1844; Percent complete: 46.1%; Average loss: 3.0257
Iteration: 1845; Percent complete: 46.1%; Average loss: 3.3713
Iteration: 1846; Percent complete: 46.2%; Average loss: 3.1349
Iteration: 1847; Percent complete: 46.2%; Average loss: 3.2852
Iteration: 1848; Percent complete: 46.2%; Average loss: 2.9546
Iteration: 1849; Percent complete: 46.2%; Average loss: 3.2786
Iteration: 1850; Percent complete: 46.2%; Average loss: 3.1029
Iteration: 1851; Percent complete: 46.3%; Average loss: 3.1169
Iteration: 1852; Percent complete: 46.3%; Average loss: 3.1227
Iteration: 1853; Percent complete: 46.3%; Average loss: 3.3475
Iteration: 1854; Percent complete: 46.4%; Average loss: 3.0562
Iteration: 1855; Percent complete: 46.4%; Average loss: 3.1300
Iteration: 1856; Percent complete: 46.4%; Average loss: 3.1695
Iteration: 1857; Percent complete: 46.4%; Average loss: 3.1442
Iteration: 1858; Percent complete: 46.5%; Average loss: 3.0572
Iteration: 1859; Percent complete: 46.5%; Average loss: 3.1276
Iteration: 1860; Percent complete: 46.5%; Average loss: 3.3567
Iteration: 1861; Percent complete: 46.5%; Average loss: 3.2934
Iteration: 1862; Percent complete: 46.6%; Average loss: 3.4307
Iteration: 1863; Percent complete: 46.6%; Average loss: 3.0212
Iteration: 1864; Percent complete: 46.6%; Average loss: 3.0923
Iteration: 1865; Percent complete: 46.6%; Average loss: 3.1389
Iteration: 1866; Percent complete: 46.7%; Average loss: 3.4707
Iteration: 1867; Percent complete: 46.7%; Average loss: 3.1021
Iteration: 1868; Percent complete: 46.7%; Average loss: 3.1006
Iteration: 1869; Percent complete: 46.7%; Average loss: 3.1938
Iteration: 1870; Percent complete: 46.8%; Average loss: 3.0076
Iteration: 1871; Percent complete: 46.8%; Average loss: 2.8374
Iteration: 1872; Percent complete: 46.8%; Average loss: 3.3850
Iteration: 1873; Percent complete: 46.8%; Average loss: 3.1834
Iteration: 1874; Percent complete: 46.9%; Average loss: 3.2462
Iteration: 1875; Percent complete: 46.9%; Average loss: 3.4919
Iteration: 1876; Percent complete: 46.9%; Average loss: 3.1074
Iteration: 1877; Percent complete: 46.9%; Average loss: 3.4334
Iteration: 1878; Percent complete: 46.9%; Average loss: 3.2406
Iteration: 1879; Percent complete: 47.0%; Average loss: 3.1739
Iteration: 1880; Percent complete: 47.0%; Average loss: 3.0466
Iteration: 1881; Percent complete: 47.0%; Average loss: 3.1751
Iteration: 1882; Percent complete: 47.0%; Average loss: 3.1317
Iteration: 1883; Percent complete: 47.1%; Average loss: 3.1897
Iteration: 1884; Percent complete: 47.1%; Average loss: 3.2480
Iteration: 1885; Percent complete: 47.1%; Average loss: 2.9664
Iteration: 1886; Percent complete: 47.1%; Average loss: 3.1537
Iteration: 1887; Percent complete: 47.2%; Average loss: 3.2135
Iteration: 1888; Percent complete: 47.2%; Average loss: 3.2277
Iteration: 1889; Percent complete: 47.2%; Average loss: 3.2027
Iteration: 1890; Percent complete: 47.2%; Average loss: 3.2842
Iteration: 1891; Percent complete: 47.3%; Average loss: 3.3373
Iteration: 1892; Percent complete: 47.3%; Average loss: 2.9561
Iteration: 1893; Percent complete: 47.3%; Average loss: 3.1712
Iteration: 1894; Percent complete: 47.3%; Average loss: 3.0639
Iteration: 1895; Percent complete: 47.4%; Average loss: 3.2612
Iteration: 1896; Percent complete: 47.4%; Average loss: 3.2300
Iteration: 1897; Percent complete: 47.4%; Average loss: 3.0884
Iteration: 1898; Percent complete: 47.4%; Average loss: 3.1823
Iteration: 1899; Percent complete: 47.5%; Average loss: 3.1720
Iteration: 1900; Percent complete: 47.5%; Average loss: 3.1968
Iteration: 1901; Percent complete: 47.5%; Average loss: 3.2676
Iteration: 1902; Percent complete: 47.5%; Average loss: 3.1226
Iteration: 1903; Percent complete: 47.6%; Average loss: 3.2837
Iteration: 1904; Percent complete: 47.6%; Average loss: 2.9103
Iteration: 1905; Percent complete: 47.6%; Average loss: 3.5864
Iteration: 1906; Percent complete: 47.6%; Average loss: 3.0055
Iteration: 1907; Percent complete: 47.7%; Average loss: 3.0011
Iteration: 1908; Percent complete: 47.7%; Average loss: 3.0790
Iteration: 1909; Percent complete: 47.7%; Average loss: 3.3383
Iteration: 1910; Percent complete: 47.8%; Average loss: 3.2701
Iteration: 1911; Percent complete: 47.8%; Average loss: 3.3906
Iteration: 1912; Percent complete: 47.8%; Average loss: 3.2511
Iteration: 1913; Percent complete: 47.8%; Average loss: 2.8778
Iteration: 1914; Percent complete: 47.9%; Average loss: 3.2365
Iteration: 1915; Percent complete: 47.9%; Average loss: 3.0596
Iteration: 1916; Percent complete: 47.9%; Average loss: 3.1871
Iteration: 1917; Percent complete: 47.9%; Average loss: 3.0157
Iteration: 1918; Percent complete: 47.9%; Average loss: 2.9842
Iteration: 1919; Percent complete: 48.0%; Average loss: 3.2317
Iteration: 1920; Percent complete: 48.0%; Average loss: 3.3197
Iteration: 1921; Percent complete: 48.0%; Average loss: 3.1826
Iteration: 1922; Percent complete: 48.0%; Average loss: 3.1170
Iteration: 1923; Percent complete: 48.1%; Average loss: 3.2538
Iteration: 1924; Percent complete: 48.1%; Average loss: 3.1800
Iteration: 1925; Percent complete: 48.1%; Average loss: 2.9099
Iteration: 1926; Percent complete: 48.1%; Average loss: 3.0238
Iteration: 1927; Percent complete: 48.2%; Average loss: 2.9856
Iteration: 1928; Percent complete: 48.2%; Average loss: 3.4100
Iteration: 1929; Percent complete: 48.2%; Average loss: 3.1524
Iteration: 1930; Percent complete: 48.2%; Average loss: 3.2214
Iteration: 1931; Percent complete: 48.3%; Average loss: 3.3879
Iteration: 1932; Percent complete: 48.3%; Average loss: 3.2174
Iteration: 1933; Percent complete: 48.3%; Average loss: 3.4420
Iteration: 1934; Percent complete: 48.4%; Average loss: 3.2831
Iteration: 1935; Percent complete: 48.4%; Average loss: 3.0012
Iteration: 1936; Percent complete: 48.4%; Average loss: 3.1104
Iteration: 1937; Percent complete: 48.4%; Average loss: 3.0324
Iteration: 1938; Percent complete: 48.4%; Average loss: 3.0382
Iteration: 1939; Percent complete: 48.5%; Average loss: 3.3329
Iteration: 1940; Percent complete: 48.5%; Average loss: 3.3361
Iteration: 1941; Percent complete: 48.5%; Average loss: 3.2672
Iteration: 1942; Percent complete: 48.5%; Average loss: 3.1163
Iteration: 1943; Percent complete: 48.6%; Average loss: 2.9739
Iteration: 1944; Percent complete: 48.6%; Average loss: 3.1718
Iteration: 1945; Percent complete: 48.6%; Average loss: 3.1455
Iteration: 1946; Percent complete: 48.6%; Average loss: 3.3304
Iteration: 1947; Percent complete: 48.7%; Average loss: 3.1952
Iteration: 1948; Percent complete: 48.7%; Average loss: 3.2927
Iteration: 1949; Percent complete: 48.7%; Average loss: 3.3690
Iteration: 1950; Percent complete: 48.8%; Average loss: 3.2286
Iteration: 1951; Percent complete: 48.8%; Average loss: 3.0475
Iteration: 1952; Percent complete: 48.8%; Average loss: 3.1186
Iteration: 1953; Percent complete: 48.8%; Average loss: 3.3768
Iteration: 1954; Percent complete: 48.9%; Average loss: 3.1344
Iteration: 1955; Percent complete: 48.9%; Average loss: 3.0389
Iteration: 1956; Percent complete: 48.9%; Average loss: 3.1499
Iteration: 1957; Percent complete: 48.9%; Average loss: 3.2770
Iteration: 1958; Percent complete: 48.9%; Average loss: 3.4794
Iteration: 1959; Percent complete: 49.0%; Average loss: 3.2967
Iteration: 1960; Percent complete: 49.0%; Average loss: 3.2645
Iteration: 1961; Percent complete: 49.0%; Average loss: 3.1888
Iteration: 1962; Percent complete: 49.0%; Average loss: 3.3991
Iteration: 1963; Percent complete: 49.1%; Average loss: 3.1521
Iteration: 1964; Percent complete: 49.1%; Average loss: 3.2218
Iteration: 1965; Percent complete: 49.1%; Average loss: 3.1426
Iteration: 1966; Percent complete: 49.1%; Average loss: 3.0384
Iteration: 1967; Percent complete: 49.2%; Average loss: 3.0126
Iteration: 1968; Percent complete: 49.2%; Average loss: 3.0920
Iteration: 1969; Percent complete: 49.2%; Average loss: 3.1507
Iteration: 1970; Percent complete: 49.2%; Average loss: 3.3941
Iteration: 1971; Percent complete: 49.3%; Average loss: 3.1781
Iteration: 1972; Percent complete: 49.3%; Average loss: 3.1666
Iteration: 1973; Percent complete: 49.3%; Average loss: 3.2454
Iteration: 1974; Percent complete: 49.4%; Average loss: 3.0139
Iteration: 1975; Percent complete: 49.4%; Average loss: 3.0182
Iteration: 1976; Percent complete: 49.4%; Average loss: 3.1365
Iteration: 1977; Percent complete: 49.4%; Average loss: 3.2795
Iteration: 1978; Percent complete: 49.5%; Average loss: 3.0545
Iteration: 1979; Percent complete: 49.5%; Average loss: 3.1130
Iteration: 1980; Percent complete: 49.5%; Average loss: 2.9957
Iteration: 1981; Percent complete: 49.5%; Average loss: 3.3198
Iteration: 1982; Percent complete: 49.5%; Average loss: 3.2120
Iteration: 1983; Percent complete: 49.6%; Average loss: 3.0831
Iteration: 1984; Percent complete: 49.6%; Average loss: 2.9019
Iteration: 1985; Percent complete: 49.6%; Average loss: 3.3077
Iteration: 1986; Percent complete: 49.6%; Average loss: 3.3702
Iteration: 1987; Percent complete: 49.7%; Average loss: 3.2954
Iteration: 1988; Percent complete: 49.7%; Average loss: 2.9952
Iteration: 1989; Percent complete: 49.7%; Average loss: 3.0973
Iteration: 1990; Percent complete: 49.8%; Average loss: 3.1981
Iteration: 1991; Percent complete: 49.8%; Average loss: 3.1525
Iteration: 1992; Percent complete: 49.8%; Average loss: 3.4121
Iteration: 1993; Percent complete: 49.8%; Average loss: 3.4215
Iteration: 1994; Percent complete: 49.9%; Average loss: 3.3823
Iteration: 1995; Percent complete: 49.9%; Average loss: 3.1170
Iteration: 1996; Percent complete: 49.9%; Average loss: 2.8712
Iteration: 1997; Percent complete: 49.9%; Average loss: 3.3261
Iteration: 1998; Percent complete: 50.0%; Average loss: 3.1472
Iteration: 1999; Percent complete: 50.0%; Average loss: 3.1286
Iteration: 2000; Percent complete: 50.0%; Average loss: 3.3593
Iteration: 2001; Percent complete: 50.0%; Average loss: 3.2781
Iteration: 2002; Percent complete: 50.0%; Average loss: 3.1783
Iteration: 2003; Percent complete: 50.1%; Average loss: 3.0564
Iteration: 2004; Percent complete: 50.1%; Average loss: 3.3438
Iteration: 2005; Percent complete: 50.1%; Average loss: 3.4974
Iteration: 2006; Percent complete: 50.1%; Average loss: 3.2001
Iteration: 2007; Percent complete: 50.2%; Average loss: 3.4013
Iteration: 2008; Percent complete: 50.2%; Average loss: 3.2014
Iteration: 2009; Percent complete: 50.2%; Average loss: 3.2025
Iteration: 2010; Percent complete: 50.2%; Average loss: 3.2049
Iteration: 2011; Percent complete: 50.3%; Average loss: 3.0050
Iteration: 2012; Percent complete: 50.3%; Average loss: 3.3481
Iteration: 2013; Percent complete: 50.3%; Average loss: 3.2625
Iteration: 2014; Percent complete: 50.3%; Average loss: 3.1280
Iteration: 2015; Percent complete: 50.4%; Average loss: 3.1879
Iteration: 2016; Percent complete: 50.4%; Average loss: 3.2918
Iteration: 2017; Percent complete: 50.4%; Average loss: 3.1338
Iteration: 2018; Percent complete: 50.4%; Average loss: 3.1863
Iteration: 2019; Percent complete: 50.5%; Average loss: 3.1189
Iteration: 2020; Percent complete: 50.5%; Average loss: 3.0227
Iteration: 2021; Percent complete: 50.5%; Average loss: 3.0429
Iteration: 2022; Percent complete: 50.5%; Average loss: 3.2679
Iteration: 2023; Percent complete: 50.6%; Average loss: 3.1031
Iteration: 2024; Percent complete: 50.6%; Average loss: 3.0075
Iteration: 2025; Percent complete: 50.6%; Average loss: 3.1078
Iteration: 2026; Percent complete: 50.6%; Average loss: 3.1053
Iteration: 2027; Percent complete: 50.7%; Average loss: 2.9700
Iteration: 2028; Percent complete: 50.7%; Average loss: 3.1790
Iteration: 2029; Percent complete: 50.7%; Average loss: 3.0708
Iteration: 2030; Percent complete: 50.7%; Average loss: 3.0688
Iteration: 2031; Percent complete: 50.8%; Average loss: 3.1557
Iteration: 2032; Percent complete: 50.8%; Average loss: 3.1540
Iteration: 2033; Percent complete: 50.8%; Average loss: 3.1698
Iteration: 2034; Percent complete: 50.8%; Average loss: 3.1109
Iteration: 2035; Percent complete: 50.9%; Average loss: 3.3948
Iteration: 2036; Percent complete: 50.9%; Average loss: 3.1810
Iteration: 2037; Percent complete: 50.9%; Average loss: 2.8249
Iteration: 2038; Percent complete: 50.9%; Average loss: 3.3671
Iteration: 2039; Percent complete: 51.0%; Average loss: 3.2590
Iteration: 2040; Percent complete: 51.0%; Average loss: 3.2250
Iteration: 2041; Percent complete: 51.0%; Average loss: 3.2478
Iteration: 2042; Percent complete: 51.0%; Average loss: 3.2610
Iteration: 2043; Percent complete: 51.1%; Average loss: 3.2723
Iteration: 2044; Percent complete: 51.1%; Average loss: 3.1372
Iteration: 2045; Percent complete: 51.1%; Average loss: 3.0880
Iteration: 2046; Percent complete: 51.1%; Average loss: 2.8252
Iteration: 2047; Percent complete: 51.2%; Average loss: 2.9774
Iteration: 2048; Percent complete: 51.2%; Average loss: 3.2966
Iteration: 2049; Percent complete: 51.2%; Average loss: 3.3512
Iteration: 2050; Percent complete: 51.2%; Average loss: 3.1990
Iteration: 2051; Percent complete: 51.3%; Average loss: 2.8674
Iteration: 2052; Percent complete: 51.3%; Average loss: 3.1836
Iteration: 2053; Percent complete: 51.3%; Average loss: 3.2720
Iteration: 2054; Percent complete: 51.3%; Average loss: 3.1552
Iteration: 2055; Percent complete: 51.4%; Average loss: 3.2852
Iteration: 2056; Percent complete: 51.4%; Average loss: 2.9577
Iteration: 2057; Percent complete: 51.4%; Average loss: 3.1383
Iteration: 2058; Percent complete: 51.4%; Average loss: 2.8904
Iteration: 2059; Percent complete: 51.5%; Average loss: 3.1465
Iteration: 2060; Percent complete: 51.5%; Average loss: 3.3516
Iteration: 2061; Percent complete: 51.5%; Average loss: 3.1742
Iteration: 2062; Percent complete: 51.5%; Average loss: 3.0851
Iteration: 2063; Percent complete: 51.6%; Average loss: 3.0067
Iteration: 2064; Percent complete: 51.6%; Average loss: 3.1036
Iteration: 2065; Percent complete: 51.6%; Average loss: 3.2203
Iteration: 2066; Percent complete: 51.6%; Average loss: 2.9472
Iteration: 2067; Percent complete: 51.7%; Average loss: 3.1078
Iteration: 2068; Percent complete: 51.7%; Average loss: 3.0818
Iteration: 2069; Percent complete: 51.7%; Average loss: 3.2711
Iteration: 2070; Percent complete: 51.7%; Average loss: 3.2505
Iteration: 2071; Percent complete: 51.8%; Average loss: 3.0520
Iteration: 2072; Percent complete: 51.8%; Average loss: 3.2647
Iteration: 2073; Percent complete: 51.8%; Average loss: 3.0702
Iteration: 2074; Percent complete: 51.8%; Average loss: 3.1122
Iteration: 2075; Percent complete: 51.9%; Average loss: 3.0506
Iteration: 2076; Percent complete: 51.9%; Average loss: 3.4043
Iteration: 2077; Percent complete: 51.9%; Average loss: 3.1056
Iteration: 2078; Percent complete: 51.9%; Average loss: 3.1265
Iteration: 2079; Percent complete: 52.0%; Average loss: 3.3503
Iteration: 2080; Percent complete: 52.0%; Average loss: 3.2104
Iteration: 2081; Percent complete: 52.0%; Average loss: 2.7776
Iteration: 2082; Percent complete: 52.0%; Average loss: 3.2850
Iteration: 2083; Percent complete: 52.1%; Average loss: 3.0096
Iteration: 2084; Percent complete: 52.1%; Average loss: 2.9968
Iteration: 2085; Percent complete: 52.1%; Average loss: 3.0102
Iteration: 2086; Percent complete: 52.1%; Average loss: 3.1437
Iteration: 2087; Percent complete: 52.2%; Average loss: 3.4894
Iteration: 2088; Percent complete: 52.2%; Average loss: 3.2858
Iteration: 2089; Percent complete: 52.2%; Average loss: 3.2198
Iteration: 2090; Percent complete: 52.2%; Average loss: 3.2621
Iteration: 2091; Percent complete: 52.3%; Average loss: 3.0958
Iteration: 2092; Percent complete: 52.3%; Average loss: 2.9907
Iteration: 2093; Percent complete: 52.3%; Average loss: 3.0221
Iteration: 2094; Percent complete: 52.3%; Average loss: 2.9417
Iteration: 2095; Percent complete: 52.4%; Average loss: 3.4665
Iteration: 2096; Percent complete: 52.4%; Average loss: 3.3668
Iteration: 2097; Percent complete: 52.4%; Average loss: 3.1840
Iteration: 2098; Percent complete: 52.4%; Average loss: 2.9172
Iteration: 2099; Percent complete: 52.5%; Average loss: 3.1899
Iteration: 2100; Percent complete: 52.5%; Average loss: 3.3063
Iteration: 2101; Percent complete: 52.5%; Average loss: 2.8933
Iteration: 2102; Percent complete: 52.5%; Average loss: 3.1146
Iteration: 2103; Percent complete: 52.6%; Average loss: 3.0352
Iteration: 2104; Percent complete: 52.6%; Average loss: 3.0570
Iteration: 2105; Percent complete: 52.6%; Average loss: 3.2136
Iteration: 2106; Percent complete: 52.6%; Average loss: 3.1297
Iteration: 2107; Percent complete: 52.7%; Average loss: 3.4729
Iteration: 2108; Percent complete: 52.7%; Average loss: 3.2894
Iteration: 2109; Percent complete: 52.7%; Average loss: 3.1082
Iteration: 2110; Percent complete: 52.8%; Average loss: 3.1940
Iteration: 2111; Percent complete: 52.8%; Average loss: 2.9639
Iteration: 2112; Percent complete: 52.8%; Average loss: 3.3272
Iteration: 2113; Percent complete: 52.8%; Average loss: 3.0325
Iteration: 2114; Percent complete: 52.8%; Average loss: 3.2841
Iteration: 2115; Percent complete: 52.9%; Average loss: 3.1430
Iteration: 2116; Percent complete: 52.9%; Average loss: 3.1251
Iteration: 2117; Percent complete: 52.9%; Average loss: 3.1507
Iteration: 2118; Percent complete: 52.9%; Average loss: 2.9010
Iteration: 2119; Percent complete: 53.0%; Average loss: 3.1435
Iteration: 2120; Percent complete: 53.0%; Average loss: 3.2530
Iteration: 2121; Percent complete: 53.0%; Average loss: 3.3178
Iteration: 2122; Percent complete: 53.0%; Average loss: 3.1748
Iteration: 2123; Percent complete: 53.1%; Average loss: 3.2062
Iteration: 2124; Percent complete: 53.1%; Average loss: 3.0636
Iteration: 2125; Percent complete: 53.1%; Average loss: 3.1843
Iteration: 2126; Percent complete: 53.1%; Average loss: 3.0632
Iteration: 2127; Percent complete: 53.2%; Average loss: 3.0792
Iteration: 2128; Percent complete: 53.2%; Average loss: 3.1114
Iteration: 2129; Percent complete: 53.2%; Average loss: 2.9372
Iteration: 2130; Percent complete: 53.2%; Average loss: 3.2236
Iteration: 2131; Percent complete: 53.3%; Average loss: 3.2296
Iteration: 2132; Percent complete: 53.3%; Average loss: 3.0481
Iteration: 2133; Percent complete: 53.3%; Average loss: 3.1910
Iteration: 2134; Percent complete: 53.3%; Average loss: 3.0024
Iteration: 2135; Percent complete: 53.4%; Average loss: 3.2764
Iteration: 2136; Percent complete: 53.4%; Average loss: 3.1148
Iteration: 2137; Percent complete: 53.4%; Average loss: 3.2154
Iteration: 2138; Percent complete: 53.4%; Average loss: 3.0035
Iteration: 2139; Percent complete: 53.5%; Average loss: 3.1575
Iteration: 2140; Percent complete: 53.5%; Average loss: 3.2742
Iteration: 2141; Percent complete: 53.5%; Average loss: 3.0635
Iteration: 2142; Percent complete: 53.5%; Average loss: 3.1083
Iteration: 2143; Percent complete: 53.6%; Average loss: 3.1685
Iteration: 2144; Percent complete: 53.6%; Average loss: 3.3646
Iteration: 2145; Percent complete: 53.6%; Average loss: 3.0891
Iteration: 2146; Percent complete: 53.6%; Average loss: 3.3298
Iteration: 2147; Percent complete: 53.7%; Average loss: 3.0222
Iteration: 2148; Percent complete: 53.7%; Average loss: 3.0559
Iteration: 2149; Percent complete: 53.7%; Average loss: 3.0406
Iteration: 2150; Percent complete: 53.8%; Average loss: 3.2016
Iteration: 2151; Percent complete: 53.8%; Average loss: 2.9581
Iteration: 2152; Percent complete: 53.8%; Average loss: 3.0767
Iteration: 2153; Percent complete: 53.8%; Average loss: 3.1398
Iteration: 2154; Percent complete: 53.8%; Average loss: 3.3250
Iteration: 2155; Percent complete: 53.9%; Average loss: 3.3132
Iteration: 2156; Percent complete: 53.9%; Average loss: 3.0706
Iteration: 2157; Percent complete: 53.9%; Average loss: 3.2047
Iteration: 2158; Percent complete: 53.9%; Average loss: 3.0202
Iteration: 2159; Percent complete: 54.0%; Average loss: 3.1476
Iteration: 2160; Percent complete: 54.0%; Average loss: 3.2525
Iteration: 2161; Percent complete: 54.0%; Average loss: 3.2010
Iteration: 2162; Percent complete: 54.0%; Average loss: 3.1092
Iteration: 2163; Percent complete: 54.1%; Average loss: 3.1001
Iteration: 2164; Percent complete: 54.1%; Average loss: 3.2170
Iteration: 2165; Percent complete: 54.1%; Average loss: 3.2062
Iteration: 2166; Percent complete: 54.1%; Average loss: 3.0244
Iteration: 2167; Percent complete: 54.2%; Average loss: 3.1171
Iteration: 2168; Percent complete: 54.2%; Average loss: 2.9706
Iteration: 2169; Percent complete: 54.2%; Average loss: 3.0195
Iteration: 2170; Percent complete: 54.2%; Average loss: 3.4841
Iteration: 2171; Percent complete: 54.3%; Average loss: 3.0447
Iteration: 2172; Percent complete: 54.3%; Average loss: 2.8833
Iteration: 2173; Percent complete: 54.3%; Average loss: 3.4621
Iteration: 2174; Percent complete: 54.4%; Average loss: 3.2740
Iteration: 2175; Percent complete: 54.4%; Average loss: 3.0142
Iteration: 2176; Percent complete: 54.4%; Average loss: 3.1822
Iteration: 2177; Percent complete: 54.4%; Average loss: 3.1696
Iteration: 2178; Percent complete: 54.4%; Average loss: 3.1691
Iteration: 2179; Percent complete: 54.5%; Average loss: 3.1056
Iteration: 2180; Percent complete: 54.5%; Average loss: 3.2588
Iteration: 2181; Percent complete: 54.5%; Average loss: 3.0990
Iteration: 2182; Percent complete: 54.5%; Average loss: 2.9836
Iteration: 2183; Percent complete: 54.6%; Average loss: 3.3451
Iteration: 2184; Percent complete: 54.6%; Average loss: 3.0110
Iteration: 2185; Percent complete: 54.6%; Average loss: 2.9454
Iteration: 2186; Percent complete: 54.6%; Average loss: 2.9516
Iteration: 2187; Percent complete: 54.7%; Average loss: 3.0065
Iteration: 2188; Percent complete: 54.7%; Average loss: 3.0850
Iteration: 2189; Percent complete: 54.7%; Average loss: 2.9975
Iteration: 2190; Percent complete: 54.8%; Average loss: 3.1063
Iteration: 2191; Percent complete: 54.8%; Average loss: 3.0364
Iteration: 2192; Percent complete: 54.8%; Average loss: 3.3181
Iteration: 2193; Percent complete: 54.8%; Average loss: 3.1865
Iteration: 2194; Percent complete: 54.9%; Average loss: 3.0631
Iteration: 2195; Percent complete: 54.9%; Average loss: 3.1457
Iteration: 2196; Percent complete: 54.9%; Average loss: 3.2559
Iteration: 2197; Percent complete: 54.9%; Average loss: 3.0247
Iteration: 2198; Percent complete: 54.9%; Average loss: 2.9756
Iteration: 2199; Percent complete: 55.0%; Average loss: 2.9108
Iteration: 2200; Percent complete: 55.0%; Average loss: 3.0184
Iteration: 2201; Percent complete: 55.0%; Average loss: 3.1331
Iteration: 2202; Percent complete: 55.0%; Average loss: 3.1312
Iteration: 2203; Percent complete: 55.1%; Average loss: 3.0252
Iteration: 2204; Percent complete: 55.1%; Average loss: 3.2476
Iteration: 2205; Percent complete: 55.1%; Average loss: 3.1722
Iteration: 2206; Percent complete: 55.1%; Average loss: 2.8811
Iteration: 2207; Percent complete: 55.2%; Average loss: 3.2437
Iteration: 2208; Percent complete: 55.2%; Average loss: 3.2201
Iteration: 2209; Percent complete: 55.2%; Average loss: 3.1335
Iteration: 2210; Percent complete: 55.2%; Average loss: 2.9919
Iteration: 2211; Percent complete: 55.3%; Average loss: 3.1924
Iteration: 2212; Percent complete: 55.3%; Average loss: 2.8428
Iteration: 2213; Percent complete: 55.3%; Average loss: 3.2485
Iteration: 2214; Percent complete: 55.4%; Average loss: 3.1587
Iteration: 2215; Percent complete: 55.4%; Average loss: 2.8926
Iteration: 2216; Percent complete: 55.4%; Average loss: 3.1476
Iteration: 2217; Percent complete: 55.4%; Average loss: 3.1595
Iteration: 2218; Percent complete: 55.5%; Average loss: 3.1497
Iteration: 2219; Percent complete: 55.5%; Average loss: 2.8873
Iteration: 2220; Percent complete: 55.5%; Average loss: 2.9977
Iteration: 2221; Percent complete: 55.5%; Average loss: 3.1800
Iteration: 2222; Percent complete: 55.5%; Average loss: 3.0823
Iteration: 2223; Percent complete: 55.6%; Average loss: 2.9690
Iteration: 2224; Percent complete: 55.6%; Average loss: 2.9888
Iteration: 2225; Percent complete: 55.6%; Average loss: 3.2317
Iteration: 2226; Percent complete: 55.6%; Average loss: 3.3860
Iteration: 2227; Percent complete: 55.7%; Average loss: 3.2808
Iteration: 2228; Percent complete: 55.7%; Average loss: 2.9666
Iteration: 2229; Percent complete: 55.7%; Average loss: 3.1158
Iteration: 2230; Percent complete: 55.8%; Average loss: 3.1989
Iteration: 2231; Percent complete: 55.8%; Average loss: 3.1336
Iteration: 2232; Percent complete: 55.8%; Average loss: 3.1118
Iteration: 2233; Percent complete: 55.8%; Average loss: 3.0329
Iteration: 2234; Percent complete: 55.9%; Average loss: 2.8292
Iteration: 2235; Percent complete: 55.9%; Average loss: 3.1878
Iteration: 2236; Percent complete: 55.9%; Average loss: 2.9097
Iteration: 2237; Percent complete: 55.9%; Average loss: 2.9905
Iteration: 2238; Percent complete: 56.0%; Average loss: 3.0687
Iteration: 2239; Percent complete: 56.0%; Average loss: 3.1091
Iteration: 2240; Percent complete: 56.0%; Average loss: 3.2270
Iteration: 2241; Percent complete: 56.0%; Average loss: 3.1429
Iteration: 2242; Percent complete: 56.0%; Average loss: 3.2919
Iteration: 2243; Percent complete: 56.1%; Average loss: 3.1878
Iteration: 2244; Percent complete: 56.1%; Average loss: 3.1091
Iteration: 2245; Percent complete: 56.1%; Average loss: 3.1505
Iteration: 2246; Percent complete: 56.1%; Average loss: 3.2327
Iteration: 2247; Percent complete: 56.2%; Average loss: 3.0754
Iteration: 2248; Percent complete: 56.2%; Average loss: 2.9578
Iteration: 2249; Percent complete: 56.2%; Average loss: 3.2381
Iteration: 2250; Percent complete: 56.2%; Average loss: 2.9333
Iteration: 2251; Percent complete: 56.3%; Average loss: 3.0956
Iteration: 2252; Percent complete: 56.3%; Average loss: 3.1703
Iteration: 2253; Percent complete: 56.3%; Average loss: 3.1170
Iteration: 2254; Percent complete: 56.4%; Average loss: 3.1892
Iteration: 2255; Percent complete: 56.4%; Average loss: 2.9158
Iteration: 2256; Percent complete: 56.4%; Average loss: 3.2446
Iteration: 2257; Percent complete: 56.4%; Average loss: 3.1241
Iteration: 2258; Percent complete: 56.5%; Average loss: 3.0515
Iteration: 2259; Percent complete: 56.5%; Average loss: 2.8668
Iteration: 2260; Percent complete: 56.5%; Average loss: 3.0966
Iteration: 2261; Percent complete: 56.5%; Average loss: 3.0690
Iteration: 2262; Percent complete: 56.5%; Average loss: 3.2744
Iteration: 2263; Percent complete: 56.6%; Average loss: 3.1943
Iteration: 2264; Percent complete: 56.6%; Average loss: 3.0579
Iteration: 2265; Percent complete: 56.6%; Average loss: 3.0933
Iteration: 2266; Percent complete: 56.6%; Average loss: 2.7985
Iteration: 2267; Percent complete: 56.7%; Average loss: 3.0712
Iteration: 2268; Percent complete: 56.7%; Average loss: 2.9232
Iteration: 2269; Percent complete: 56.7%; Average loss: 2.9803
Iteration: 2270; Percent complete: 56.8%; Average loss: 3.0317
Iteration: 2271; Percent complete: 56.8%; Average loss: 3.0709
Iteration: 2272; Percent complete: 56.8%; Average loss: 2.8748
Iteration: 2273; Percent complete: 56.8%; Average loss: 3.1032
Iteration: 2274; Percent complete: 56.9%; Average loss: 2.8478
Iteration: 2275; Percent complete: 56.9%; Average loss: 3.0094
Iteration: 2276; Percent complete: 56.9%; Average loss: 3.1180
Iteration: 2277; Percent complete: 56.9%; Average loss: 3.1989
Iteration: 2278; Percent complete: 57.0%; Average loss: 3.2995
Iteration: 2279; Percent complete: 57.0%; Average loss: 3.3404
Iteration: 2280; Percent complete: 57.0%; Average loss: 3.0274
Iteration: 2281; Percent complete: 57.0%; Average loss: 3.0093
Iteration: 2282; Percent complete: 57.0%; Average loss: 3.0670
Iteration: 2283; Percent complete: 57.1%; Average loss: 3.0203
Iteration: 2284; Percent complete: 57.1%; Average loss: 3.1193
Iteration: 2285; Percent complete: 57.1%; Average loss: 2.8879
Iteration: 2286; Percent complete: 57.1%; Average loss: 3.2321
Iteration: 2287; Percent complete: 57.2%; Average loss: 3.1129
Iteration: 2288; Percent complete: 57.2%; Average loss: 3.3667
Iteration: 2289; Percent complete: 57.2%; Average loss: 3.1725
Iteration: 2290; Percent complete: 57.2%; Average loss: 3.2881
Iteration: 2291; Percent complete: 57.3%; Average loss: 3.2896
Iteration: 2292; Percent complete: 57.3%; Average loss: 3.1024
Iteration: 2293; Percent complete: 57.3%; Average loss: 3.2209
Iteration: 2294; Percent complete: 57.4%; Average loss: 2.9479
Iteration: 2295; Percent complete: 57.4%; Average loss: 3.0584
Iteration: 2296; Percent complete: 57.4%; Average loss: 2.9475
Iteration: 2297; Percent complete: 57.4%; Average loss: 3.0282
Iteration: 2298; Percent complete: 57.5%; Average loss: 3.1840
Iteration: 2299; Percent complete: 57.5%; Average loss: 2.7361
Iteration: 2300; Percent complete: 57.5%; Average loss: 3.1572
Iteration: 2301; Percent complete: 57.5%; Average loss: 2.9846
Iteration: 2302; Percent complete: 57.6%; Average loss: 3.2051
Iteration: 2303; Percent complete: 57.6%; Average loss: 3.0927
Iteration: 2304; Percent complete: 57.6%; Average loss: 3.2008
Iteration: 2305; Percent complete: 57.6%; Average loss: 3.1023
Iteration: 2306; Percent complete: 57.6%; Average loss: 3.0559
Iteration: 2307; Percent complete: 57.7%; Average loss: 3.0489
Iteration: 2308; Percent complete: 57.7%; Average loss: 2.9264
Iteration: 2309; Percent complete: 57.7%; Average loss: 3.0868
Iteration: 2310; Percent complete: 57.8%; Average loss: 2.9740
Iteration: 2311; Percent complete: 57.8%; Average loss: 2.9293
Iteration: 2312; Percent complete: 57.8%; Average loss: 2.9583
Iteration: 2313; Percent complete: 57.8%; Average loss: 2.9286
Iteration: 2314; Percent complete: 57.9%; Average loss: 2.8709
Iteration: 2315; Percent complete: 57.9%; Average loss: 3.0199
Iteration: 2316; Percent complete: 57.9%; Average loss: 2.8842
Iteration: 2317; Percent complete: 57.9%; Average loss: 3.2661
Iteration: 2318; Percent complete: 58.0%; Average loss: 2.9369
Iteration: 2319; Percent complete: 58.0%; Average loss: 3.0676
Iteration: 2320; Percent complete: 58.0%; Average loss: 3.0264
Iteration: 2321; Percent complete: 58.0%; Average loss: 3.2364
Iteration: 2322; Percent complete: 58.1%; Average loss: 3.0556
Iteration: 2323; Percent complete: 58.1%; Average loss: 3.1681
Iteration: 2324; Percent complete: 58.1%; Average loss: 3.0584
Iteration: 2325; Percent complete: 58.1%; Average loss: 2.9994
Iteration: 2326; Percent complete: 58.1%; Average loss: 3.0850
Iteration: 2327; Percent complete: 58.2%; Average loss: 3.0767
Iteration: 2328; Percent complete: 58.2%; Average loss: 2.7646
Iteration: 2329; Percent complete: 58.2%; Average loss: 3.1999
Iteration: 2330; Percent complete: 58.2%; Average loss: 2.7880
Iteration: 2331; Percent complete: 58.3%; Average loss: 3.1961
Iteration: 2332; Percent complete: 58.3%; Average loss: 3.0822
Iteration: 2333; Percent complete: 58.3%; Average loss: 3.1245
Iteration: 2334; Percent complete: 58.4%; Average loss: 3.0748
Iteration: 2335; Percent complete: 58.4%; Average loss: 3.1380
Iteration: 2336; Percent complete: 58.4%; Average loss: 2.9185
Iteration: 2337; Percent complete: 58.4%; Average loss: 3.2103
Iteration: 2338; Percent complete: 58.5%; Average loss: 3.2515
Iteration: 2339; Percent complete: 58.5%; Average loss: 3.0806
Iteration: 2340; Percent complete: 58.5%; Average loss: 2.9293
Iteration: 2341; Percent complete: 58.5%; Average loss: 2.9860
Iteration: 2342; Percent complete: 58.6%; Average loss: 3.1167
Iteration: 2343; Percent complete: 58.6%; Average loss: 3.1953
Iteration: 2344; Percent complete: 58.6%; Average loss: 2.9976
Iteration: 2345; Percent complete: 58.6%; Average loss: 3.0476
Iteration: 2346; Percent complete: 58.7%; Average loss: 3.2325
Iteration: 2347; Percent complete: 58.7%; Average loss: 3.1083
Iteration: 2348; Percent complete: 58.7%; Average loss: 3.1298
Iteration: 2349; Percent complete: 58.7%; Average loss: 3.1164
Iteration: 2350; Percent complete: 58.8%; Average loss: 3.1967
Iteration: 2351; Percent complete: 58.8%; Average loss: 3.2684
Iteration: 2352; Percent complete: 58.8%; Average loss: 3.0507
Iteration: 2353; Percent complete: 58.8%; Average loss: 2.8463
Iteration: 2354; Percent complete: 58.9%; Average loss: 2.9605
Iteration: 2355; Percent complete: 58.9%; Average loss: 3.0432
Iteration: 2356; Percent complete: 58.9%; Average loss: 3.0611
Iteration: 2357; Percent complete: 58.9%; Average loss: 2.9462
Iteration: 2358; Percent complete: 59.0%; Average loss: 3.0495
Iteration: 2359; Percent complete: 59.0%; Average loss: 2.6303
Iteration: 2360; Percent complete: 59.0%; Average loss: 3.1164
Iteration: 2361; Percent complete: 59.0%; Average loss: 2.6739
Iteration: 2362; Percent complete: 59.1%; Average loss: 2.9460
Iteration: 2363; Percent complete: 59.1%; Average loss: 3.0754
Iteration: 2364; Percent complete: 59.1%; Average loss: 2.9371
Iteration: 2365; Percent complete: 59.1%; Average loss: 3.0131
Iteration: 2366; Percent complete: 59.2%; Average loss: 2.9040
Iteration: 2367; Percent complete: 59.2%; Average loss: 2.8738
Iteration: 2368; Percent complete: 59.2%; Average loss: 3.0801
Iteration: 2369; Percent complete: 59.2%; Average loss: 3.1026
Iteration: 2370; Percent complete: 59.2%; Average loss: 2.8946
Iteration: 2371; Percent complete: 59.3%; Average loss: 2.9561
Iteration: 2372; Percent complete: 59.3%; Average loss: 2.9097
Iteration: 2373; Percent complete: 59.3%; Average loss: 2.8101
Iteration: 2374; Percent complete: 59.4%; Average loss: 2.9470
Iteration: 2375; Percent complete: 59.4%; Average loss: 3.0878
Iteration: 2376; Percent complete: 59.4%; Average loss: 2.9615
Iteration: 2377; Percent complete: 59.4%; Average loss: 2.9140
Iteration: 2378; Percent complete: 59.5%; Average loss: 3.4373
Iteration: 2379; Percent complete: 59.5%; Average loss: 3.3040
Iteration: 2380; Percent complete: 59.5%; Average loss: 3.1210
Iteration: 2381; Percent complete: 59.5%; Average loss: 2.9079
Iteration: 2382; Percent complete: 59.6%; Average loss: 2.9305
Iteration: 2383; Percent complete: 59.6%; Average loss: 3.1773
Iteration: 2384; Percent complete: 59.6%; Average loss: 3.0588
Iteration: 2385; Percent complete: 59.6%; Average loss: 3.1984
Iteration: 2386; Percent complete: 59.7%; Average loss: 3.1137
Iteration: 2387; Percent complete: 59.7%; Average loss: 2.6998
Iteration: 2388; Percent complete: 59.7%; Average loss: 3.1678
Iteration: 2389; Percent complete: 59.7%; Average loss: 2.9990
Iteration: 2390; Percent complete: 59.8%; Average loss: 2.7670
Iteration: 2391; Percent complete: 59.8%; Average loss: 3.1175
Iteration: 2392; Percent complete: 59.8%; Average loss: 3.1336
Iteration: 2393; Percent complete: 59.8%; Average loss: 3.2136
Iteration: 2394; Percent complete: 59.9%; Average loss: 3.0126
Iteration: 2395; Percent complete: 59.9%; Average loss: 2.7770
Iteration: 2396; Percent complete: 59.9%; Average loss: 3.1142
Iteration: 2397; Percent complete: 59.9%; Average loss: 3.1404
Iteration: 2398; Percent complete: 60.0%; Average loss: 3.1136
Iteration: 2399; Percent complete: 60.0%; Average loss: 3.1346
Iteration: 2400; Percent complete: 60.0%; Average loss: 2.9270
Iteration: 2401; Percent complete: 60.0%; Average loss: 3.0191
Iteration: 2402; Percent complete: 60.1%; Average loss: 3.2830
Iteration: 2403; Percent complete: 60.1%; Average loss: 2.6741
Iteration: 2404; Percent complete: 60.1%; Average loss: 2.9909
Iteration: 2405; Percent complete: 60.1%; Average loss: 3.1838
Iteration: 2406; Percent complete: 60.2%; Average loss: 2.9139
Iteration: 2407; Percent complete: 60.2%; Average loss: 3.3358
Iteration: 2408; Percent complete: 60.2%; Average loss: 3.0651
Iteration: 2409; Percent complete: 60.2%; Average loss: 3.2189
Iteration: 2410; Percent complete: 60.2%; Average loss: 3.2898
Iteration: 2411; Percent complete: 60.3%; Average loss: 2.9586
Iteration: 2412; Percent complete: 60.3%; Average loss: 2.9817
Iteration: 2413; Percent complete: 60.3%; Average loss: 2.8652
Iteration: 2414; Percent complete: 60.4%; Average loss: 2.9916
Iteration: 2415; Percent complete: 60.4%; Average loss: 3.1831
Iteration: 2416; Percent complete: 60.4%; Average loss: 3.0409
Iteration: 2417; Percent complete: 60.4%; Average loss: 3.2090
Iteration: 2418; Percent complete: 60.5%; Average loss: 3.0323
Iteration: 2419; Percent complete: 60.5%; Average loss: 3.2659
Iteration: 2420; Percent complete: 60.5%; Average loss: 2.7408
Iteration: 2421; Percent complete: 60.5%; Average loss: 3.2082
Iteration: 2422; Percent complete: 60.6%; Average loss: 2.9187
Iteration: 2423; Percent complete: 60.6%; Average loss: 3.2142
Iteration: 2424; Percent complete: 60.6%; Average loss: 2.9945
Iteration: 2425; Percent complete: 60.6%; Average loss: 2.8236
Iteration: 2426; Percent complete: 60.7%; Average loss: 2.8205
Iteration: 2427; Percent complete: 60.7%; Average loss: 3.1916
Iteration: 2428; Percent complete: 60.7%; Average loss: 3.0663
Iteration: 2429; Percent complete: 60.7%; Average loss: 3.1043
Iteration: 2430; Percent complete: 60.8%; Average loss: 3.1047
Iteration: 2431; Percent complete: 60.8%; Average loss: 3.1283
Iteration: 2432; Percent complete: 60.8%; Average loss: 2.8950
Iteration: 2433; Percent complete: 60.8%; Average loss: 3.2227
Iteration: 2434; Percent complete: 60.9%; Average loss: 3.1002
Iteration: 2435; Percent complete: 60.9%; Average loss: 2.8897
Iteration: 2436; Percent complete: 60.9%; Average loss: 3.0482
Iteration: 2437; Percent complete: 60.9%; Average loss: 3.3153
Iteration: 2438; Percent complete: 61.0%; Average loss: 3.3484
Iteration: 2439; Percent complete: 61.0%; Average loss: 3.2498
Iteration: 2440; Percent complete: 61.0%; Average loss: 3.3530
Iteration: 2441; Percent complete: 61.0%; Average loss: 3.5377
Iteration: 2442; Percent complete: 61.1%; Average loss: 2.7728
Iteration: 2443; Percent complete: 61.1%; Average loss: 3.2266
Iteration: 2444; Percent complete: 61.1%; Average loss: 3.0720
Iteration: 2445; Percent complete: 61.1%; Average loss: 3.1562
Iteration: 2446; Percent complete: 61.2%; Average loss: 3.0311
Iteration: 2447; Percent complete: 61.2%; Average loss: 2.9387
Iteration: 2448; Percent complete: 61.2%; Average loss: 3.1394
Iteration: 2449; Percent complete: 61.2%; Average loss: 2.9644
Iteration: 2450; Percent complete: 61.3%; Average loss: 2.8478
Iteration: 2451; Percent complete: 61.3%; Average loss: 2.8823
Iteration: 2452; Percent complete: 61.3%; Average loss: 2.9943
Iteration: 2453; Percent complete: 61.3%; Average loss: 3.1483
Iteration: 2454; Percent complete: 61.4%; Average loss: 3.3668
Iteration: 2455; Percent complete: 61.4%; Average loss: 3.1274
Iteration: 2456; Percent complete: 61.4%; Average loss: 3.0962
Iteration: 2457; Percent complete: 61.4%; Average loss: 3.1019
Iteration: 2458; Percent complete: 61.5%; Average loss: 3.1198
Iteration: 2459; Percent complete: 61.5%; Average loss: 3.1114
Iteration: 2460; Percent complete: 61.5%; Average loss: 3.0514
Iteration: 2461; Percent complete: 61.5%; Average loss: 2.9606
Iteration: 2462; Percent complete: 61.6%; Average loss: 3.2557
Iteration: 2463; Percent complete: 61.6%; Average loss: 2.9342
Iteration: 2464; Percent complete: 61.6%; Average loss: 3.0481
Iteration: 2465; Percent complete: 61.6%; Average loss: 3.0797
Iteration: 2466; Percent complete: 61.7%; Average loss: 3.1338
Iteration: 2467; Percent complete: 61.7%; Average loss: 3.2095
Iteration: 2468; Percent complete: 61.7%; Average loss: 3.1855
Iteration: 2469; Percent complete: 61.7%; Average loss: 3.0536
Iteration: 2470; Percent complete: 61.8%; Average loss: 3.2663
Iteration: 2471; Percent complete: 61.8%; Average loss: 2.9917
Iteration: 2472; Percent complete: 61.8%; Average loss: 2.9360
Iteration: 2473; Percent complete: 61.8%; Average loss: 3.0998
Iteration: 2474; Percent complete: 61.9%; Average loss: 3.1602
Iteration: 2475; Percent complete: 61.9%; Average loss: 3.0668
Iteration: 2476; Percent complete: 61.9%; Average loss: 3.0732
Iteration: 2477; Percent complete: 61.9%; Average loss: 3.0148
Iteration: 2478; Percent complete: 62.0%; Average loss: 2.9730
Iteration: 2479; Percent complete: 62.0%; Average loss: 2.7996
Iteration: 2480; Percent complete: 62.0%; Average loss: 2.9773
Iteration: 2481; Percent complete: 62.0%; Average loss: 3.4396
Iteration: 2482; Percent complete: 62.1%; Average loss: 2.9860
Iteration: 2483; Percent complete: 62.1%; Average loss: 3.2539
Iteration: 2484; Percent complete: 62.1%; Average loss: 3.2556
Iteration: 2485; Percent complete: 62.1%; Average loss: 2.9251
Iteration: 2486; Percent complete: 62.2%; Average loss: 2.9623
Iteration: 2487; Percent complete: 62.2%; Average loss: 2.9372
Iteration: 2488; Percent complete: 62.2%; Average loss: 2.8656
Iteration: 2489; Percent complete: 62.2%; Average loss: 3.2499
Iteration: 2490; Percent complete: 62.3%; Average loss: 3.0876
Iteration: 2491; Percent complete: 62.3%; Average loss: 2.8614
Iteration: 2492; Percent complete: 62.3%; Average loss: 3.0903
Iteration: 2493; Percent complete: 62.3%; Average loss: 2.9076
Iteration: 2494; Percent complete: 62.4%; Average loss: 2.9312
Iteration: 2495; Percent complete: 62.4%; Average loss: 3.1414
Iteration: 2496; Percent complete: 62.4%; Average loss: 3.1567
Iteration: 2497; Percent complete: 62.4%; Average loss: 3.1202
Iteration: 2498; Percent complete: 62.5%; Average loss: 2.9009
Iteration: 2499; Percent complete: 62.5%; Average loss: 2.8448
Iteration: 2500; Percent complete: 62.5%; Average loss: 2.9355
Iteration: 2501; Percent complete: 62.5%; Average loss: 2.9661
Iteration: 2502; Percent complete: 62.5%; Average loss: 2.9595
Iteration: 2503; Percent complete: 62.6%; Average loss: 2.8890
Iteration: 2504; Percent complete: 62.6%; Average loss: 3.1014
Iteration: 2505; Percent complete: 62.6%; Average loss: 2.9594
Iteration: 2506; Percent complete: 62.6%; Average loss: 3.2393
Iteration: 2507; Percent complete: 62.7%; Average loss: 2.9846
Iteration: 2508; Percent complete: 62.7%; Average loss: 3.3017
Iteration: 2509; Percent complete: 62.7%; Average loss: 2.9696
Iteration: 2510; Percent complete: 62.7%; Average loss: 3.0835
Iteration: 2511; Percent complete: 62.8%; Average loss: 3.1411
Iteration: 2512; Percent complete: 62.8%; Average loss: 3.2069
Iteration: 2513; Percent complete: 62.8%; Average loss: 3.0062
Iteration: 2514; Percent complete: 62.8%; Average loss: 2.7595
Iteration: 2515; Percent complete: 62.9%; Average loss: 2.8372
Iteration: 2516; Percent complete: 62.9%; Average loss: 3.0439
Iteration: 2517; Percent complete: 62.9%; Average loss: 3.1462
Iteration: 2518; Percent complete: 62.9%; Average loss: 2.9037
Iteration: 2519; Percent complete: 63.0%; Average loss: 3.1476
Iteration: 2520; Percent complete: 63.0%; Average loss: 3.0364
Iteration: 2521; Percent complete: 63.0%; Average loss: 3.4011
Iteration: 2522; Percent complete: 63.0%; Average loss: 2.9003
Iteration: 2523; Percent complete: 63.1%; Average loss: 3.0336
Iteration: 2524; Percent complete: 63.1%; Average loss: 3.3352
Iteration: 2525; Percent complete: 63.1%; Average loss: 3.1378
Iteration: 2526; Percent complete: 63.1%; Average loss: 3.2024
Iteration: 2527; Percent complete: 63.2%; Average loss: 3.0554
Iteration: 2528; Percent complete: 63.2%; Average loss: 2.9113
Iteration: 2529; Percent complete: 63.2%; Average loss: 2.9068
Iteration: 2530; Percent complete: 63.2%; Average loss: 3.1081
Iteration: 2531; Percent complete: 63.3%; Average loss: 3.2542
Iteration: 2532; Percent complete: 63.3%; Average loss: 3.0430
Iteration: 2533; Percent complete: 63.3%; Average loss: 2.8937
Iteration: 2534; Percent complete: 63.3%; Average loss: 3.0504
Iteration: 2535; Percent complete: 63.4%; Average loss: 3.0003
Iteration: 2536; Percent complete: 63.4%; Average loss: 2.9316
Iteration: 2537; Percent complete: 63.4%; Average loss: 2.9067
Iteration: 2538; Percent complete: 63.4%; Average loss: 2.7255
Iteration: 2539; Percent complete: 63.5%; Average loss: 3.0195
Iteration: 2540; Percent complete: 63.5%; Average loss: 2.8316
Iteration: 2541; Percent complete: 63.5%; Average loss: 3.2135
Iteration: 2542; Percent complete: 63.5%; Average loss: 2.8460
Iteration: 2543; Percent complete: 63.6%; Average loss: 3.0587
Iteration: 2544; Percent complete: 63.6%; Average loss: 2.9998
Iteration: 2545; Percent complete: 63.6%; Average loss: 2.6977
Iteration: 2546; Percent complete: 63.6%; Average loss: 2.8672
Iteration: 2547; Percent complete: 63.7%; Average loss: 3.0082
Iteration: 2548; Percent complete: 63.7%; Average loss: 3.1403
Iteration: 2549; Percent complete: 63.7%; Average loss: 2.9836
Iteration: 2550; Percent complete: 63.7%; Average loss: 3.0452
Iteration: 2551; Percent complete: 63.8%; Average loss: 2.8799
Iteration: 2552; Percent complete: 63.8%; Average loss: 2.8718
Iteration: 2553; Percent complete: 63.8%; Average loss: 3.0115
Iteration: 2554; Percent complete: 63.8%; Average loss: 3.1079
Iteration: 2555; Percent complete: 63.9%; Average loss: 3.0869
Iteration: 2556; Percent complete: 63.9%; Average loss: 2.9076
Iteration: 2557; Percent complete: 63.9%; Average loss: 3.2141
Iteration: 2558; Percent complete: 63.9%; Average loss: 3.0465
Iteration: 2559; Percent complete: 64.0%; Average loss: 3.1568
Iteration: 2560; Percent complete: 64.0%; Average loss: 3.1163
Iteration: 2561; Percent complete: 64.0%; Average loss: 2.8426
Iteration: 2562; Percent complete: 64.0%; Average loss: 2.9379
Iteration: 2563; Percent complete: 64.1%; Average loss: 2.9739
Iteration: 2564; Percent complete: 64.1%; Average loss: 3.0044
Iteration: 2565; Percent complete: 64.1%; Average loss: 3.0928
Iteration: 2566; Percent complete: 64.1%; Average loss: 2.9890
Iteration: 2567; Percent complete: 64.2%; Average loss: 3.0188
Iteration: 2568; Percent complete: 64.2%; Average loss: 2.8687
Iteration: 2569; Percent complete: 64.2%; Average loss: 2.9687
Iteration: 2570; Percent complete: 64.2%; Average loss: 3.0677
Iteration: 2571; Percent complete: 64.3%; Average loss: 2.8930
Iteration: 2572; Percent complete: 64.3%; Average loss: 2.9179
Iteration: 2573; Percent complete: 64.3%; Average loss: 3.0476
Iteration: 2574; Percent complete: 64.3%; Average loss: 3.0311
Iteration: 2575; Percent complete: 64.4%; Average loss: 2.9559
Iteration: 2576; Percent complete: 64.4%; Average loss: 3.2449
Iteration: 2577; Percent complete: 64.4%; Average loss: 2.9934
Iteration: 2578; Percent complete: 64.5%; Average loss: 2.9027
Iteration: 2579; Percent complete: 64.5%; Average loss: 3.1682
Iteration: 2580; Percent complete: 64.5%; Average loss: 3.1815
Iteration: 2581; Percent complete: 64.5%; Average loss: 2.9928
Iteration: 2582; Percent complete: 64.5%; Average loss: 3.0819
Iteration: 2583; Percent complete: 64.6%; Average loss: 3.2173
Iteration: 2584; Percent complete: 64.6%; Average loss: 3.1443
Iteration: 2585; Percent complete: 64.6%; Average loss: 3.0505
Iteration: 2586; Percent complete: 64.6%; Average loss: 3.1380
Iteration: 2587; Percent complete: 64.7%; Average loss: 3.0875
Iteration: 2588; Percent complete: 64.7%; Average loss: 2.8634
Iteration: 2589; Percent complete: 64.7%; Average loss: 3.1066
Iteration: 2590; Percent complete: 64.8%; Average loss: 2.9277
Iteration: 2591; Percent complete: 64.8%; Average loss: 2.8848
Iteration: 2592; Percent complete: 64.8%; Average loss: 3.0421
Iteration: 2593; Percent complete: 64.8%; Average loss: 2.9727
Iteration: 2594; Percent complete: 64.8%; Average loss: 3.2276
Iteration: 2595; Percent complete: 64.9%; Average loss: 2.9792
Iteration: 2596; Percent complete: 64.9%; Average loss: 2.8373
Iteration: 2597; Percent complete: 64.9%; Average loss: 2.9272
Iteration: 2598; Percent complete: 65.0%; Average loss: 2.8824
Iteration: 2599; Percent complete: 65.0%; Average loss: 3.0161
Iteration: 2600; Percent complete: 65.0%; Average loss: 2.9615
Iteration: 2601; Percent complete: 65.0%; Average loss: 3.0535
Iteration: 2602; Percent complete: 65.0%; Average loss: 2.9141
Iteration: 2603; Percent complete: 65.1%; Average loss: 3.0235
Iteration: 2604; Percent complete: 65.1%; Average loss: 3.0475
Iteration: 2605; Percent complete: 65.1%; Average loss: 3.0169
Iteration: 2606; Percent complete: 65.1%; Average loss: 2.8941
Iteration: 2607; Percent complete: 65.2%; Average loss: 2.7843
Iteration: 2608; Percent complete: 65.2%; Average loss: 3.0388
Iteration: 2609; Percent complete: 65.2%; Average loss: 2.8500
Iteration: 2610; Percent complete: 65.2%; Average loss: 2.9518
Iteration: 2611; Percent complete: 65.3%; Average loss: 2.9639
Iteration: 2612; Percent complete: 65.3%; Average loss: 3.1398
Iteration: 2613; Percent complete: 65.3%; Average loss: 2.8817
Iteration: 2614; Percent complete: 65.3%; Average loss: 2.8399
Iteration: 2615; Percent complete: 65.4%; Average loss: 3.1665
Iteration: 2616; Percent complete: 65.4%; Average loss: 3.0726
Iteration: 2617; Percent complete: 65.4%; Average loss: 2.8647
Iteration: 2618; Percent complete: 65.5%; Average loss: 2.9136
Iteration: 2619; Percent complete: 65.5%; Average loss: 2.9368
Iteration: 2620; Percent complete: 65.5%; Average loss: 2.8186
Iteration: 2621; Percent complete: 65.5%; Average loss: 2.7740
Iteration: 2622; Percent complete: 65.5%; Average loss: 2.8873
Iteration: 2623; Percent complete: 65.6%; Average loss: 3.2336
Iteration: 2624; Percent complete: 65.6%; Average loss: 2.7283
Iteration: 2625; Percent complete: 65.6%; Average loss: 3.1083
Iteration: 2626; Percent complete: 65.6%; Average loss: 3.0690
Iteration: 2627; Percent complete: 65.7%; Average loss: 2.8398
Iteration: 2628; Percent complete: 65.7%; Average loss: 3.0230
Iteration: 2629; Percent complete: 65.7%; Average loss: 2.9239
Iteration: 2630; Percent complete: 65.8%; Average loss: 3.2398
Iteration: 2631; Percent complete: 65.8%; Average loss: 2.7797
Iteration: 2632; Percent complete: 65.8%; Average loss: 2.8604
Iteration: 2633; Percent complete: 65.8%; Average loss: 2.7783
Iteration: 2634; Percent complete: 65.8%; Average loss: 2.8167
Iteration: 2635; Percent complete: 65.9%; Average loss: 2.7858
Iteration: 2636; Percent complete: 65.9%; Average loss: 3.0448
Iteration: 2637; Percent complete: 65.9%; Average loss: 2.9829
Iteration: 2638; Percent complete: 66.0%; Average loss: 2.8344
Iteration: 2639; Percent complete: 66.0%; Average loss: 2.6554
Iteration: 2640; Percent complete: 66.0%; Average loss: 3.1042
Iteration: 2641; Percent complete: 66.0%; Average loss: 3.0561
Iteration: 2642; Percent complete: 66.0%; Average loss: 3.0776
Iteration: 2643; Percent complete: 66.1%; Average loss: 2.9170
Iteration: 2644; Percent complete: 66.1%; Average loss: 2.9930
Iteration: 2645; Percent complete: 66.1%; Average loss: 3.2361
Iteration: 2646; Percent complete: 66.1%; Average loss: 3.0419
Iteration: 2647; Percent complete: 66.2%; Average loss: 3.2237
Iteration: 2648; Percent complete: 66.2%; Average loss: 2.9689
Iteration: 2649; Percent complete: 66.2%; Average loss: 2.9738
Iteration: 2650; Percent complete: 66.2%; Average loss: 2.8569
Iteration: 2651; Percent complete: 66.3%; Average loss: 3.1658
Iteration: 2652; Percent complete: 66.3%; Average loss: 2.9169
Iteration: 2653; Percent complete: 66.3%; Average loss: 2.9460
Iteration: 2654; Percent complete: 66.3%; Average loss: 3.0425
Iteration: 2655; Percent complete: 66.4%; Average loss: 3.0070
Iteration: 2656; Percent complete: 66.4%; Average loss: 3.2243
Iteration: 2657; Percent complete: 66.4%; Average loss: 2.7285
Iteration: 2658; Percent complete: 66.5%; Average loss: 3.1740
Iteration: 2659; Percent complete: 66.5%; Average loss: 2.7846
Iteration: 2660; Percent complete: 66.5%; Average loss: 3.1268
Iteration: 2661; Percent complete: 66.5%; Average loss: 2.9474
Iteration: 2662; Percent complete: 66.5%; Average loss: 2.8790
Iteration: 2663; Percent complete: 66.6%; Average loss: 3.0577
Iteration: 2664; Percent complete: 66.6%; Average loss: 2.7397
Iteration: 2665; Percent complete: 66.6%; Average loss: 2.8498
Iteration: 2666; Percent complete: 66.6%; Average loss: 3.0377
Iteration: 2667; Percent complete: 66.7%; Average loss: 3.0740
Iteration: 2668; Percent complete: 66.7%; Average loss: 3.0402
Iteration: 2669; Percent complete: 66.7%; Average loss: 2.8667
Iteration: 2670; Percent complete: 66.8%; Average loss: 3.0069
Iteration: 2671; Percent complete: 66.8%; Average loss: 2.7977
Iteration: 2672; Percent complete: 66.8%; Average loss: 3.0537
Iteration: 2673; Percent complete: 66.8%; Average loss: 2.9546
Iteration: 2674; Percent complete: 66.8%; Average loss: 2.8062
Iteration: 2675; Percent complete: 66.9%; Average loss: 3.0377
Iteration: 2676; Percent complete: 66.9%; Average loss: 3.0561
Iteration: 2677; Percent complete: 66.9%; Average loss: 2.7084
Iteration: 2678; Percent complete: 67.0%; Average loss: 3.1807
Iteration: 2679; Percent complete: 67.0%; Average loss: 2.8054
Iteration: 2680; Percent complete: 67.0%; Average loss: 2.8156
Iteration: 2681; Percent complete: 67.0%; Average loss: 3.0970
Iteration: 2682; Percent complete: 67.0%; Average loss: 2.8925
Iteration: 2683; Percent complete: 67.1%; Average loss: 2.9639
Iteration: 2684; Percent complete: 67.1%; Average loss: 2.8981
Iteration: 2685; Percent complete: 67.1%; Average loss: 3.0453
Iteration: 2686; Percent complete: 67.2%; Average loss: 3.0576
Iteration: 2687; Percent complete: 67.2%; Average loss: 3.1270
Iteration: 2688; Percent complete: 67.2%; Average loss: 3.1314
Iteration: 2689; Percent complete: 67.2%; Average loss: 2.9358
Iteration: 2690; Percent complete: 67.2%; Average loss: 3.0472
Iteration: 2691; Percent complete: 67.3%; Average loss: 3.0844
Iteration: 2692; Percent complete: 67.3%; Average loss: 2.9461
Iteration: 2693; Percent complete: 67.3%; Average loss: 2.9072
Iteration: 2694; Percent complete: 67.3%; Average loss: 3.0807
Iteration: 2695; Percent complete: 67.4%; Average loss: 3.2415
Iteration: 2696; Percent complete: 67.4%; Average loss: 3.1970
Iteration: 2697; Percent complete: 67.4%; Average loss: 2.7298
Iteration: 2698; Percent complete: 67.5%; Average loss: 3.0153
Iteration: 2699; Percent complete: 67.5%; Average loss: 3.0049
Iteration: 2700; Percent complete: 67.5%; Average loss: 2.9486
Iteration: 2701; Percent complete: 67.5%; Average loss: 3.1610
Iteration: 2702; Percent complete: 67.5%; Average loss: 3.1623
Iteration: 2703; Percent complete: 67.6%; Average loss: 2.8561
Iteration: 2704; Percent complete: 67.6%; Average loss: 3.2048
Iteration: 2705; Percent complete: 67.6%; Average loss: 2.8015
Iteration: 2706; Percent complete: 67.7%; Average loss: 2.7743
Iteration: 2707; Percent complete: 67.7%; Average loss: 3.0813
Iteration: 2708; Percent complete: 67.7%; Average loss: 2.8849
Iteration: 2709; Percent complete: 67.7%; Average loss: 3.0292
Iteration: 2710; Percent complete: 67.8%; Average loss: 3.0923
Iteration: 2711; Percent complete: 67.8%; Average loss: 2.9029
Iteration: 2712; Percent complete: 67.8%; Average loss: 2.8992
Iteration: 2713; Percent complete: 67.8%; Average loss: 3.0258
Iteration: 2714; Percent complete: 67.8%; Average loss: 2.8310
Iteration: 2715; Percent complete: 67.9%; Average loss: 3.0365
Iteration: 2716; Percent complete: 67.9%; Average loss: 3.1492
Iteration: 2717; Percent complete: 67.9%; Average loss: 3.0621
Iteration: 2718; Percent complete: 68.0%; Average loss: 2.7177
Iteration: 2719; Percent complete: 68.0%; Average loss: 2.9054
Iteration: 2720; Percent complete: 68.0%; Average loss: 2.9458
Iteration: 2721; Percent complete: 68.0%; Average loss: 3.0993
Iteration: 2722; Percent complete: 68.0%; Average loss: 3.2192
Iteration: 2723; Percent complete: 68.1%; Average loss: 2.9896
Iteration: 2724; Percent complete: 68.1%; Average loss: 2.9362
Iteration: 2725; Percent complete: 68.1%; Average loss: 3.0292
Iteration: 2726; Percent complete: 68.2%; Average loss: 2.6568
Iteration: 2727; Percent complete: 68.2%; Average loss: 2.9717
Iteration: 2728; Percent complete: 68.2%; Average loss: 3.0508
Iteration: 2729; Percent complete: 68.2%; Average loss: 3.1902
Iteration: 2730; Percent complete: 68.2%; Average loss: 3.0547
Iteration: 2731; Percent complete: 68.3%; Average loss: 2.9717
Iteration: 2732; Percent complete: 68.3%; Average loss: 2.9576
Iteration: 2733; Percent complete: 68.3%; Average loss: 2.9271
Iteration: 2734; Percent complete: 68.3%; Average loss: 2.5505
Iteration: 2735; Percent complete: 68.4%; Average loss: 2.7709
Iteration: 2736; Percent complete: 68.4%; Average loss: 2.9647
Iteration: 2737; Percent complete: 68.4%; Average loss: 3.0167
Iteration: 2738; Percent complete: 68.5%; Average loss: 3.0522
Iteration: 2739; Percent complete: 68.5%; Average loss: 2.9972
Iteration: 2740; Percent complete: 68.5%; Average loss: 3.0270
Iteration: 2741; Percent complete: 68.5%; Average loss: 2.9670
Iteration: 2742; Percent complete: 68.5%; Average loss: 2.9071
Iteration: 2743; Percent complete: 68.6%; Average loss: 3.0345
Iteration: 2744; Percent complete: 68.6%; Average loss: 2.8053
Iteration: 2745; Percent complete: 68.6%; Average loss: 2.7867
Iteration: 2746; Percent complete: 68.7%; Average loss: 2.9976
Iteration: 2747; Percent complete: 68.7%; Average loss: 3.0095
Iteration: 2748; Percent complete: 68.7%; Average loss: 2.9431
Iteration: 2749; Percent complete: 68.7%; Average loss: 3.0791
Iteration: 2750; Percent complete: 68.8%; Average loss: 2.7569
Iteration: 2751; Percent complete: 68.8%; Average loss: 2.9633
Iteration: 2752; Percent complete: 68.8%; Average loss: 2.8777
Iteration: 2753; Percent complete: 68.8%; Average loss: 2.8421
Iteration: 2754; Percent complete: 68.8%; Average loss: 2.9731
Iteration: 2755; Percent complete: 68.9%; Average loss: 2.9287
Iteration: 2756; Percent complete: 68.9%; Average loss: 2.8804
Iteration: 2757; Percent complete: 68.9%; Average loss: 3.0379
Iteration: 2758; Percent complete: 69.0%; Average loss: 2.6869
Iteration: 2759; Percent complete: 69.0%; Average loss: 3.0353
Iteration: 2760; Percent complete: 69.0%; Average loss: 2.9663
Iteration: 2761; Percent complete: 69.0%; Average loss: 2.9756
Iteration: 2762; Percent complete: 69.0%; Average loss: 2.8213
Iteration: 2763; Percent complete: 69.1%; Average loss: 3.0277
Iteration: 2764; Percent complete: 69.1%; Average loss: 2.7942
Iteration: 2765; Percent complete: 69.1%; Average loss: 2.9317
Iteration: 2766; Percent complete: 69.2%; Average loss: 3.2072
Iteration: 2767; Percent complete: 69.2%; Average loss: 2.8142
Iteration: 2768; Percent complete: 69.2%; Average loss: 2.5997
Iteration: 2769; Percent complete: 69.2%; Average loss: 2.6786
Iteration: 2770; Percent complete: 69.2%; Average loss: 3.0547
Iteration: 2771; Percent complete: 69.3%; Average loss: 2.9465
Iteration: 2772; Percent complete: 69.3%; Average loss: 2.9966
Iteration: 2773; Percent complete: 69.3%; Average loss: 2.8742
Iteration: 2774; Percent complete: 69.3%; Average loss: 2.9296
Iteration: 2775; Percent complete: 69.4%; Average loss: 2.8945
Iteration: 2776; Percent complete: 69.4%; Average loss: 2.8471
Iteration: 2777; Percent complete: 69.4%; Average loss: 2.9830
Iteration: 2778; Percent complete: 69.5%; Average loss: 2.8666
Iteration: 2779; Percent complete: 69.5%; Average loss: 3.0622
Iteration: 2780; Percent complete: 69.5%; Average loss: 2.6315
Iteration: 2781; Percent complete: 69.5%; Average loss: 2.8723
Iteration: 2782; Percent complete: 69.5%; Average loss: 2.7370
Iteration: 2783; Percent complete: 69.6%; Average loss: 2.7890
Iteration: 2784; Percent complete: 69.6%; Average loss: 2.9218
Iteration: 2785; Percent complete: 69.6%; Average loss: 3.0377
Iteration: 2786; Percent complete: 69.7%; Average loss: 2.9206
Iteration: 2787; Percent complete: 69.7%; Average loss: 2.8995
Iteration: 2788; Percent complete: 69.7%; Average loss: 3.0124
Iteration: 2789; Percent complete: 69.7%; Average loss: 2.8189
Iteration: 2790; Percent complete: 69.8%; Average loss: 2.7054
Iteration: 2791; Percent complete: 69.8%; Average loss: 2.8325
Iteration: 2792; Percent complete: 69.8%; Average loss: 3.0890
Iteration: 2793; Percent complete: 69.8%; Average loss: 3.0763
Iteration: 2794; Percent complete: 69.8%; Average loss: 2.9146
Iteration: 2795; Percent complete: 69.9%; Average loss: 2.9099
Iteration: 2796; Percent complete: 69.9%; Average loss: 2.8230
Iteration: 2797; Percent complete: 69.9%; Average loss: 2.9403
Iteration: 2798; Percent complete: 70.0%; Average loss: 2.9827
Iteration: 2799; Percent complete: 70.0%; Average loss: 3.2581
Iteration: 2800; Percent complete: 70.0%; Average loss: 2.9417
Iteration: 2801; Percent complete: 70.0%; Average loss: 2.8834
Iteration: 2802; Percent complete: 70.0%; Average loss: 2.9270
Iteration: 2803; Percent complete: 70.1%; Average loss: 2.9751
Iteration: 2804; Percent complete: 70.1%; Average loss: 2.9054
Iteration: 2805; Percent complete: 70.1%; Average loss: 2.6767
Iteration: 2806; Percent complete: 70.2%; Average loss: 3.1635
Iteration: 2807; Percent complete: 70.2%; Average loss: 2.9460
Iteration: 2808; Percent complete: 70.2%; Average loss: 2.7654
Iteration: 2809; Percent complete: 70.2%; Average loss: 3.0395
Iteration: 2810; Percent complete: 70.2%; Average loss: 3.1087
Iteration: 2811; Percent complete: 70.3%; Average loss: 3.2306
Iteration: 2812; Percent complete: 70.3%; Average loss: 2.9651
Iteration: 2813; Percent complete: 70.3%; Average loss: 2.9556
Iteration: 2814; Percent complete: 70.3%; Average loss: 2.8877
Iteration: 2815; Percent complete: 70.4%; Average loss: 3.0409
Iteration: 2816; Percent complete: 70.4%; Average loss: 2.7521
Iteration: 2817; Percent complete: 70.4%; Average loss: 2.7741
Iteration: 2818; Percent complete: 70.5%; Average loss: 3.0364
Iteration: 2819; Percent complete: 70.5%; Average loss: 2.9560
Iteration: 2820; Percent complete: 70.5%; Average loss: 3.0159
Iteration: 2821; Percent complete: 70.5%; Average loss: 2.8927
Iteration: 2822; Percent complete: 70.5%; Average loss: 2.9780
Iteration: 2823; Percent complete: 70.6%; Average loss: 2.8191
Iteration: 2824; Percent complete: 70.6%; Average loss: 2.9608
Iteration: 2825; Percent complete: 70.6%; Average loss: 2.8626
Iteration: 2826; Percent complete: 70.7%; Average loss: 3.0603
Iteration: 2827; Percent complete: 70.7%; Average loss: 2.8197
Iteration: 2828; Percent complete: 70.7%; Average loss: 3.1970
Iteration: 2829; Percent complete: 70.7%; Average loss: 2.9013
Iteration: 2830; Percent complete: 70.8%; Average loss: 2.9795
Iteration: 2831; Percent complete: 70.8%; Average loss: 3.0089
Iteration: 2832; Percent complete: 70.8%; Average loss: 3.0277
Iteration: 2833; Percent complete: 70.8%; Average loss: 3.1063
Iteration: 2834; Percent complete: 70.9%; Average loss: 2.7668
Iteration: 2835; Percent complete: 70.9%; Average loss: 2.8286
Iteration: 2836; Percent complete: 70.9%; Average loss: 2.9361
Iteration: 2837; Percent complete: 70.9%; Average loss: 2.9310
Iteration: 2838; Percent complete: 71.0%; Average loss: 3.0039
Iteration: 2839; Percent complete: 71.0%; Average loss: 2.8970
Iteration: 2840; Percent complete: 71.0%; Average loss: 2.9291
Iteration: 2841; Percent complete: 71.0%; Average loss: 2.8819
Iteration: 2842; Percent complete: 71.0%; Average loss: 3.0863
Iteration: 2843; Percent complete: 71.1%; Average loss: 2.6394
Iteration: 2844; Percent complete: 71.1%; Average loss: 2.9348
Iteration: 2845; Percent complete: 71.1%; Average loss: 3.1114
Iteration: 2846; Percent complete: 71.2%; Average loss: 2.8215
Iteration: 2847; Percent complete: 71.2%; Average loss: 2.9153
Iteration: 2848; Percent complete: 71.2%; Average loss: 2.9311
Iteration: 2849; Percent complete: 71.2%; Average loss: 2.9871
Iteration: 2850; Percent complete: 71.2%; Average loss: 2.8614
Iteration: 2851; Percent complete: 71.3%; Average loss: 2.7660
Iteration: 2852; Percent complete: 71.3%; Average loss: 2.9781
Iteration: 2853; Percent complete: 71.3%; Average loss: 2.7347
Iteration: 2854; Percent complete: 71.4%; Average loss: 2.9163
Iteration: 2855; Percent complete: 71.4%; Average loss: 2.8098
Iteration: 2856; Percent complete: 71.4%; Average loss: 2.8163
Iteration: 2857; Percent complete: 71.4%; Average loss: 2.9679
Iteration: 2858; Percent complete: 71.5%; Average loss: 2.9589
Iteration: 2859; Percent complete: 71.5%; Average loss: 3.0173
Iteration: 2860; Percent complete: 71.5%; Average loss: 3.0027
Iteration: 2861; Percent complete: 71.5%; Average loss: 2.8703
Iteration: 2862; Percent complete: 71.5%; Average loss: 2.6733
Iteration: 2863; Percent complete: 71.6%; Average loss: 2.8453
Iteration: 2864; Percent complete: 71.6%; Average loss: 2.6232
Iteration: 2865; Percent complete: 71.6%; Average loss: 2.9986
Iteration: 2866; Percent complete: 71.7%; Average loss: 3.0415
Iteration: 2867; Percent complete: 71.7%; Average loss: 2.9659
Iteration: 2868; Percent complete: 71.7%; Average loss: 3.0781
Iteration: 2869; Percent complete: 71.7%; Average loss: 2.9968
Iteration: 2870; Percent complete: 71.8%; Average loss: 2.7787
Iteration: 2871; Percent complete: 71.8%; Average loss: 2.7331
Iteration: 2872; Percent complete: 71.8%; Average loss: 2.9204
Iteration: 2873; Percent complete: 71.8%; Average loss: 2.9224
Iteration: 2874; Percent complete: 71.9%; Average loss: 2.9392
Iteration: 2875; Percent complete: 71.9%; Average loss: 2.6358
Iteration: 2876; Percent complete: 71.9%; Average loss: 2.9588
Iteration: 2877; Percent complete: 71.9%; Average loss: 2.8789
Iteration: 2878; Percent complete: 72.0%; Average loss: 2.8664
Iteration: 2879; Percent complete: 72.0%; Average loss: 2.8955
Iteration: 2880; Percent complete: 72.0%; Average loss: 3.0325
Iteration: 2881; Percent complete: 72.0%; Average loss: 2.7657
Iteration: 2882; Percent complete: 72.0%; Average loss: 3.0326
Iteration: 2883; Percent complete: 72.1%; Average loss: 2.9221
Iteration: 2884; Percent complete: 72.1%; Average loss: 2.7208
Iteration: 2885; Percent complete: 72.1%; Average loss: 2.9218
Iteration: 2886; Percent complete: 72.2%; Average loss: 2.8158
Iteration: 2887; Percent complete: 72.2%; Average loss: 3.1238
Iteration: 2888; Percent complete: 72.2%; Average loss: 2.6999
Iteration: 2889; Percent complete: 72.2%; Average loss: 2.9802
Iteration: 2890; Percent complete: 72.2%; Average loss: 2.8802
Iteration: 2891; Percent complete: 72.3%; Average loss: 2.9755
Iteration: 2892; Percent complete: 72.3%; Average loss: 3.1688
Iteration: 2893; Percent complete: 72.3%; Average loss: 2.8267
Iteration: 2894; Percent complete: 72.4%; Average loss: 2.7903
Iteration: 2895; Percent complete: 72.4%; Average loss: 2.7194
Iteration: 2896; Percent complete: 72.4%; Average loss: 2.5960
Iteration: 2897; Percent complete: 72.4%; Average loss: 2.9016
Iteration: 2898; Percent complete: 72.5%; Average loss: 2.8871
Iteration: 2899; Percent complete: 72.5%; Average loss: 3.0371
Iteration: 2900; Percent complete: 72.5%; Average loss: 3.1020
Iteration: 2901; Percent complete: 72.5%; Average loss: 2.7905
Iteration: 2902; Percent complete: 72.5%; Average loss: 2.7924
Iteration: 2903; Percent complete: 72.6%; Average loss: 3.0748
Iteration: 2904; Percent complete: 72.6%; Average loss: 2.8920
Iteration: 2905; Percent complete: 72.6%; Average loss: 3.1847
Iteration: 2906; Percent complete: 72.7%; Average loss: 3.0028
Iteration: 2907; Percent complete: 72.7%; Average loss: 2.8668
Iteration: 2908; Percent complete: 72.7%; Average loss: 2.8638
Iteration: 2909; Percent complete: 72.7%; Average loss: 2.8289
Iteration: 2910; Percent complete: 72.8%; Average loss: 2.8922
Iteration: 2911; Percent complete: 72.8%; Average loss: 2.9593
Iteration: 2912; Percent complete: 72.8%; Average loss: 2.9480
Iteration: 2913; Percent complete: 72.8%; Average loss: 2.8309
Iteration: 2914; Percent complete: 72.9%; Average loss: 2.9550
Iteration: 2915; Percent complete: 72.9%; Average loss: 3.0876
Iteration: 2916; Percent complete: 72.9%; Average loss: 3.2063
Iteration: 2917; Percent complete: 72.9%; Average loss: 2.5412
Iteration: 2918; Percent complete: 73.0%; Average loss: 2.9458
Iteration: 2919; Percent complete: 73.0%; Average loss: 2.6762
Iteration: 2920; Percent complete: 73.0%; Average loss: 2.9643
Iteration: 2921; Percent complete: 73.0%; Average loss: 2.7471
Iteration: 2922; Percent complete: 73.0%; Average loss: 2.9055
Iteration: 2923; Percent complete: 73.1%; Average loss: 2.6870
Iteration: 2924; Percent complete: 73.1%; Average loss: 2.8987
Iteration: 2925; Percent complete: 73.1%; Average loss: 2.8747
Iteration: 2926; Percent complete: 73.2%; Average loss: 2.9027
Iteration: 2927; Percent complete: 73.2%; Average loss: 3.0430
Iteration: 2928; Percent complete: 73.2%; Average loss: 2.7246
Iteration: 2929; Percent complete: 73.2%; Average loss: 2.8276
Iteration: 2930; Percent complete: 73.2%; Average loss: 2.9423
Iteration: 2931; Percent complete: 73.3%; Average loss: 2.9408
Iteration: 2932; Percent complete: 73.3%; Average loss: 2.9225
Iteration: 2933; Percent complete: 73.3%; Average loss: 2.9160
Iteration: 2934; Percent complete: 73.4%; Average loss: 2.8370
Iteration: 2935; Percent complete: 73.4%; Average loss: 2.7629
Iteration: 2936; Percent complete: 73.4%; Average loss: 2.7076
Iteration: 2937; Percent complete: 73.4%; Average loss: 2.9560
Iteration: 2938; Percent complete: 73.5%; Average loss: 2.8627
Iteration: 2939; Percent complete: 73.5%; Average loss: 3.1815
Iteration: 2940; Percent complete: 73.5%; Average loss: 2.9783
Iteration: 2941; Percent complete: 73.5%; Average loss: 3.1008
Iteration: 2942; Percent complete: 73.6%; Average loss: 2.9506
Iteration: 2943; Percent complete: 73.6%; Average loss: 3.1042
Iteration: 2944; Percent complete: 73.6%; Average loss: 2.8855
Iteration: 2945; Percent complete: 73.6%; Average loss: 3.0191
Iteration: 2946; Percent complete: 73.7%; Average loss: 2.7113
Iteration: 2947; Percent complete: 73.7%; Average loss: 3.0386
Iteration: 2948; Percent complete: 73.7%; Average loss: 2.9149
Iteration: 2949; Percent complete: 73.7%; Average loss: 3.0394
Iteration: 2950; Percent complete: 73.8%; Average loss: 2.8364
Iteration: 2951; Percent complete: 73.8%; Average loss: 3.0107
Iteration: 2952; Percent complete: 73.8%; Average loss: 2.8930
Iteration: 2953; Percent complete: 73.8%; Average loss: 2.7382
Iteration: 2954; Percent complete: 73.9%; Average loss: 3.0050
Iteration: 2955; Percent complete: 73.9%; Average loss: 3.1993
Iteration: 2956; Percent complete: 73.9%; Average loss: 2.8620
Iteration: 2957; Percent complete: 73.9%; Average loss: 2.6217
Iteration: 2958; Percent complete: 74.0%; Average loss: 2.6285
Iteration: 2959; Percent complete: 74.0%; Average loss: 2.8976
Iteration: 2960; Percent complete: 74.0%; Average loss: 2.8802
Iteration: 2961; Percent complete: 74.0%; Average loss: 2.8825
Iteration: 2962; Percent complete: 74.1%; Average loss: 2.9542
Iteration: 2963; Percent complete: 74.1%; Average loss: 2.8943
Iteration: 2964; Percent complete: 74.1%; Average loss: 2.8291
Iteration: 2965; Percent complete: 74.1%; Average loss: 2.6692
Iteration: 2966; Percent complete: 74.2%; Average loss: 2.7747
Iteration: 2967; Percent complete: 74.2%; Average loss: 2.8936
Iteration: 2968; Percent complete: 74.2%; Average loss: 2.6761
Iteration: 2969; Percent complete: 74.2%; Average loss: 2.9355
Iteration: 2970; Percent complete: 74.2%; Average loss: 3.0769
Iteration: 2971; Percent complete: 74.3%; Average loss: 2.9473
Iteration: 2972; Percent complete: 74.3%; Average loss: 2.9760
Iteration: 2973; Percent complete: 74.3%; Average loss: 2.8988
Iteration: 2974; Percent complete: 74.4%; Average loss: 3.1716
Iteration: 2975; Percent complete: 74.4%; Average loss: 2.9502
Iteration: 2976; Percent complete: 74.4%; Average loss: 2.7489
Iteration: 2977; Percent complete: 74.4%; Average loss: 3.0325
Iteration: 2978; Percent complete: 74.5%; Average loss: 2.7966
Iteration: 2979; Percent complete: 74.5%; Average loss: 2.7851
Iteration: 2980; Percent complete: 74.5%; Average loss: 3.0834
Iteration: 2981; Percent complete: 74.5%; Average loss: 2.9716
Iteration: 2982; Percent complete: 74.6%; Average loss: 2.8311
Iteration: 2983; Percent complete: 74.6%; Average loss: 2.8296
Iteration: 2984; Percent complete: 74.6%; Average loss: 2.8976
Iteration: 2985; Percent complete: 74.6%; Average loss: 2.9410
Iteration: 2986; Percent complete: 74.7%; Average loss: 2.9001
Iteration: 2987; Percent complete: 74.7%; Average loss: 3.0233
Iteration: 2988; Percent complete: 74.7%; Average loss: 2.9915
Iteration: 2989; Percent complete: 74.7%; Average loss: 3.1040
Iteration: 2990; Percent complete: 74.8%; Average loss: 2.8874
Iteration: 2991; Percent complete: 74.8%; Average loss: 2.9394
Iteration: 2992; Percent complete: 74.8%; Average loss: 2.7837
Iteration: 2993; Percent complete: 74.8%; Average loss: 2.8235
Iteration: 2994; Percent complete: 74.9%; Average loss: 3.0272
Iteration: 2995; Percent complete: 74.9%; Average loss: 2.9155
Iteration: 2996; Percent complete: 74.9%; Average loss: 2.7217
Iteration: 2997; Percent complete: 74.9%; Average loss: 3.0345
Iteration: 2998; Percent complete: 75.0%; Average loss: 3.0742
Iteration: 2999; Percent complete: 75.0%; Average loss: 2.8833
Iteration: 3000; Percent complete: 75.0%; Average loss: 2.9884
Iteration: 3001; Percent complete: 75.0%; Average loss: 2.6857
Iteration: 3002; Percent complete: 75.0%; Average loss: 2.8286
Iteration: 3003; Percent complete: 75.1%; Average loss: 2.8315
Iteration: 3004; Percent complete: 75.1%; Average loss: 2.8887
Iteration: 3005; Percent complete: 75.1%; Average loss: 2.7470
Iteration: 3006; Percent complete: 75.1%; Average loss: 2.8378
Iteration: 3007; Percent complete: 75.2%; Average loss: 2.9549
Iteration: 3008; Percent complete: 75.2%; Average loss: 2.7856
Iteration: 3009; Percent complete: 75.2%; Average loss: 3.1808
Iteration: 3010; Percent complete: 75.2%; Average loss: 2.9165
Iteration: 3011; Percent complete: 75.3%; Average loss: 2.8818
Iteration: 3012; Percent complete: 75.3%; Average loss: 2.9672
Iteration: 3013; Percent complete: 75.3%; Average loss: 2.7461
Iteration: 3014; Percent complete: 75.3%; Average loss: 2.8709
Iteration: 3015; Percent complete: 75.4%; Average loss: 3.0813
Iteration: 3016; Percent complete: 75.4%; Average loss: 2.7659
Iteration: 3017; Percent complete: 75.4%; Average loss: 2.8060
Iteration: 3018; Percent complete: 75.4%; Average loss: 3.0147
Iteration: 3019; Percent complete: 75.5%; Average loss: 2.9621
Iteration: 3020; Percent complete: 75.5%; Average loss: 2.8376
Iteration: 3021; Percent complete: 75.5%; Average loss: 2.8500
Iteration: 3022; Percent complete: 75.5%; Average loss: 3.1592
Iteration: 3023; Percent complete: 75.6%; Average loss: 2.9425
Iteration: 3024; Percent complete: 75.6%; Average loss: 2.9300
Iteration: 3025; Percent complete: 75.6%; Average loss: 2.9499
Iteration: 3026; Percent complete: 75.6%; Average loss: 2.5102
Iteration: 3027; Percent complete: 75.7%; Average loss: 2.8035
Iteration: 3028; Percent complete: 75.7%; Average loss: 3.1474
Iteration: 3029; Percent complete: 75.7%; Average loss: 2.9023
Iteration: 3030; Percent complete: 75.8%; Average loss: 2.8771
Iteration: 3031; Percent complete: 75.8%; Average loss: 2.8880
Iteration: 3032; Percent complete: 75.8%; Average loss: 2.9380
Iteration: 3033; Percent complete: 75.8%; Average loss: 3.1448
Iteration: 3034; Percent complete: 75.8%; Average loss: 3.0058
Iteration: 3035; Percent complete: 75.9%; Average loss: 3.0650
Iteration: 3036; Percent complete: 75.9%; Average loss: 3.0485
Iteration: 3037; Percent complete: 75.9%; Average loss: 3.1779
Iteration: 3038; Percent complete: 75.9%; Average loss: 2.8285
Iteration: 3039; Percent complete: 76.0%; Average loss: 2.6189
Iteration: 3040; Percent complete: 76.0%; Average loss: 2.7901
Iteration: 3041; Percent complete: 76.0%; Average loss: 2.9138
Iteration: 3042; Percent complete: 76.0%; Average loss: 2.9890
Iteration: 3043; Percent complete: 76.1%; Average loss: 3.0307
Iteration: 3044; Percent complete: 76.1%; Average loss: 2.8008
Iteration: 3045; Percent complete: 76.1%; Average loss: 3.1497
Iteration: 3046; Percent complete: 76.1%; Average loss: 2.7321
Iteration: 3047; Percent complete: 76.2%; Average loss: 2.7855
Iteration: 3048; Percent complete: 76.2%; Average loss: 2.9089
Iteration: 3049; Percent complete: 76.2%; Average loss: 3.0558
Iteration: 3050; Percent complete: 76.2%; Average loss: 2.7835
Iteration: 3051; Percent complete: 76.3%; Average loss: 2.8061
Iteration: 3052; Percent complete: 76.3%; Average loss: 2.8449
Iteration: 3053; Percent complete: 76.3%; Average loss: 2.7583
Iteration: 3054; Percent complete: 76.3%; Average loss: 3.0407
Iteration: 3055; Percent complete: 76.4%; Average loss: 2.5439
Iteration: 3056; Percent complete: 76.4%; Average loss: 2.9010
Iteration: 3057; Percent complete: 76.4%; Average loss: 3.0791
Iteration: 3058; Percent complete: 76.4%; Average loss: 2.8889
Iteration: 3059; Percent complete: 76.5%; Average loss: 2.7593
Iteration: 3060; Percent complete: 76.5%; Average loss: 2.9266
Iteration: 3061; Percent complete: 76.5%; Average loss: 2.9429
Iteration: 3062; Percent complete: 76.5%; Average loss: 2.8666
Iteration: 3063; Percent complete: 76.6%; Average loss: 2.6961
Iteration: 3064; Percent complete: 76.6%; Average loss: 2.9048
Iteration: 3065; Percent complete: 76.6%; Average loss: 2.8606
Iteration: 3066; Percent complete: 76.6%; Average loss: 2.6420
Iteration: 3067; Percent complete: 76.7%; Average loss: 3.1063
Iteration: 3068; Percent complete: 76.7%; Average loss: 2.5725
Iteration: 3069; Percent complete: 76.7%; Average loss: 3.0855
Iteration: 3070; Percent complete: 76.8%; Average loss: 2.7674
Iteration: 3071; Percent complete: 76.8%; Average loss: 2.7953
Iteration: 3072; Percent complete: 76.8%; Average loss: 2.8579
Iteration: 3073; Percent complete: 76.8%; Average loss: 3.0572
Iteration: 3074; Percent complete: 76.8%; Average loss: 2.6725
Iteration: 3075; Percent complete: 76.9%; Average loss: 2.5775
Iteration: 3076; Percent complete: 76.9%; Average loss: 2.9853
Iteration: 3077; Percent complete: 76.9%; Average loss: 2.8300
Iteration: 3078; Percent complete: 77.0%; Average loss: 2.9584
Iteration: 3079; Percent complete: 77.0%; Average loss: 2.8922
Iteration: 3080; Percent complete: 77.0%; Average loss: 2.7470
Iteration: 3081; Percent complete: 77.0%; Average loss: 3.0050
Iteration: 3082; Percent complete: 77.0%; Average loss: 2.7675
Iteration: 3083; Percent complete: 77.1%; Average loss: 2.9228
Iteration: 3084; Percent complete: 77.1%; Average loss: 2.7477
Iteration: 3085; Percent complete: 77.1%; Average loss: 3.0036
Iteration: 3086; Percent complete: 77.1%; Average loss: 2.7998
Iteration: 3087; Percent complete: 77.2%; Average loss: 2.9611
Iteration: 3088; Percent complete: 77.2%; Average loss: 2.8424
Iteration: 3089; Percent complete: 77.2%; Average loss: 2.7842
Iteration: 3090; Percent complete: 77.2%; Average loss: 2.7830
Iteration: 3091; Percent complete: 77.3%; Average loss: 3.0301
Iteration: 3092; Percent complete: 77.3%; Average loss: 2.9004
Iteration: 3093; Percent complete: 77.3%; Average loss: 2.7387
Iteration: 3094; Percent complete: 77.3%; Average loss: 2.8290
Iteration: 3095; Percent complete: 77.4%; Average loss: 2.8650
Iteration: 3096; Percent complete: 77.4%; Average loss: 2.7496
Iteration: 3097; Percent complete: 77.4%; Average loss: 2.9633
Iteration: 3098; Percent complete: 77.5%; Average loss: 2.7170
Iteration: 3099; Percent complete: 77.5%; Average loss: 2.8154
Iteration: 3100; Percent complete: 77.5%; Average loss: 2.8415
Iteration: 3101; Percent complete: 77.5%; Average loss: 2.6146
Iteration: 3102; Percent complete: 77.5%; Average loss: 2.9294
Iteration: 3103; Percent complete: 77.6%; Average loss: 2.9478
Iteration: 3104; Percent complete: 77.6%; Average loss: 3.1276
Iteration: 3105; Percent complete: 77.6%; Average loss: 2.5726
Iteration: 3106; Percent complete: 77.6%; Average loss: 2.7223
Iteration: 3107; Percent complete: 77.7%; Average loss: 2.9503
Iteration: 3108; Percent complete: 77.7%; Average loss: 2.8260
Iteration: 3109; Percent complete: 77.7%; Average loss: 2.8200
Iteration: 3110; Percent complete: 77.8%; Average loss: 2.8826
Iteration: 3111; Percent complete: 77.8%; Average loss: 2.9325
Iteration: 3112; Percent complete: 77.8%; Average loss: 2.9183
Iteration: 3113; Percent complete: 77.8%; Average loss: 2.8386
Iteration: 3114; Percent complete: 77.8%; Average loss: 3.0016
Iteration: 3115; Percent complete: 77.9%; Average loss: 2.7742
Iteration: 3116; Percent complete: 77.9%; Average loss: 2.6192
Iteration: 3117; Percent complete: 77.9%; Average loss: 2.9764
Iteration: 3118; Percent complete: 78.0%; Average loss: 2.7090
Iteration: 3119; Percent complete: 78.0%; Average loss: 2.9444
Iteration: 3120; Percent complete: 78.0%; Average loss: 2.7403
Iteration: 3121; Percent complete: 78.0%; Average loss: 3.0307
Iteration: 3122; Percent complete: 78.0%; Average loss: 2.9098
Iteration: 3123; Percent complete: 78.1%; Average loss: 2.6630
Iteration: 3124; Percent complete: 78.1%; Average loss: 2.6670
Iteration: 3125; Percent complete: 78.1%; Average loss: 2.8538
Iteration: 3126; Percent complete: 78.1%; Average loss: 3.0020
Iteration: 3127; Percent complete: 78.2%; Average loss: 2.7311
Iteration: 3128; Percent complete: 78.2%; Average loss: 2.9006
Iteration: 3129; Percent complete: 78.2%; Average loss: 2.7860
Iteration: 3130; Percent complete: 78.2%; Average loss: 2.9452
Iteration: 3131; Percent complete: 78.3%; Average loss: 2.7264
Iteration: 3132; Percent complete: 78.3%; Average loss: 2.8137
Iteration: 3133; Percent complete: 78.3%; Average loss: 2.7710
Iteration: 3134; Percent complete: 78.3%; Average loss: 2.7646
Iteration: 3135; Percent complete: 78.4%; Average loss: 3.0110
Iteration: 3136; Percent complete: 78.4%; Average loss: 3.0078
Iteration: 3137; Percent complete: 78.4%; Average loss: 2.8264
Iteration: 3138; Percent complete: 78.5%; Average loss: 2.8163
Iteration: 3139; Percent complete: 78.5%; Average loss: 2.8316
Iteration: 3140; Percent complete: 78.5%; Average loss: 2.6272
Iteration: 3141; Percent complete: 78.5%; Average loss: 2.9734
Iteration: 3142; Percent complete: 78.5%; Average loss: 2.8391
Iteration: 3143; Percent complete: 78.6%; Average loss: 2.9339
Iteration: 3144; Percent complete: 78.6%; Average loss: 3.0001
Iteration: 3145; Percent complete: 78.6%; Average loss: 2.8414
Iteration: 3146; Percent complete: 78.6%; Average loss: 2.8985
Iteration: 3147; Percent complete: 78.7%; Average loss: 2.8593
Iteration: 3148; Percent complete: 78.7%; Average loss: 2.8808
Iteration: 3149; Percent complete: 78.7%; Average loss: 2.8374
Iteration: 3150; Percent complete: 78.8%; Average loss: 2.7935
Iteration: 3151; Percent complete: 78.8%; Average loss: 2.7930
Iteration: 3152; Percent complete: 78.8%; Average loss: 2.9538
Iteration: 3153; Percent complete: 78.8%; Average loss: 2.8085
Iteration: 3154; Percent complete: 78.8%; Average loss: 2.9253
Iteration: 3155; Percent complete: 78.9%; Average loss: 2.8324
Iteration: 3156; Percent complete: 78.9%; Average loss: 2.7200
Iteration: 3157; Percent complete: 78.9%; Average loss: 2.9270
Iteration: 3158; Percent complete: 79.0%; Average loss: 3.0796
Iteration: 3159; Percent complete: 79.0%; Average loss: 2.7215
Iteration: 3160; Percent complete: 79.0%; Average loss: 2.7815
Iteration: 3161; Percent complete: 79.0%; Average loss: 2.8623
Iteration: 3162; Percent complete: 79.0%; Average loss: 2.7945
Iteration: 3163; Percent complete: 79.1%; Average loss: 2.8134
Iteration: 3164; Percent complete: 79.1%; Average loss: 2.7114
Iteration: 3165; Percent complete: 79.1%; Average loss: 3.0967
Iteration: 3166; Percent complete: 79.1%; Average loss: 2.8234
Iteration: 3167; Percent complete: 79.2%; Average loss: 2.8519
Iteration: 3168; Percent complete: 79.2%; Average loss: 2.8932
Iteration: 3169; Percent complete: 79.2%; Average loss: 3.0236
Iteration: 3170; Percent complete: 79.2%; Average loss: 2.8551
Iteration: 3171; Percent complete: 79.3%; Average loss: 2.7795
Iteration: 3172; Percent complete: 79.3%; Average loss: 2.8332
Iteration: 3173; Percent complete: 79.3%; Average loss: 2.9908
Iteration: 3174; Percent complete: 79.3%; Average loss: 2.9192
Iteration: 3175; Percent complete: 79.4%; Average loss: 2.9251
Iteration: 3176; Percent complete: 79.4%; Average loss: 2.9251
Iteration: 3177; Percent complete: 79.4%; Average loss: 2.8341
Iteration: 3178; Percent complete: 79.5%; Average loss: 2.8201
Iteration: 3179; Percent complete: 79.5%; Average loss: 2.7674
Iteration: 3180; Percent complete: 79.5%; Average loss: 2.9577
Iteration: 3181; Percent complete: 79.5%; Average loss: 2.8900
Iteration: 3182; Percent complete: 79.5%; Average loss: 2.5796
Iteration: 3183; Percent complete: 79.6%; Average loss: 2.6507
Iteration: 3184; Percent complete: 79.6%; Average loss: 2.8070
Iteration: 3185; Percent complete: 79.6%; Average loss: 2.8306
Iteration: 3186; Percent complete: 79.7%; Average loss: 3.0005
Iteration: 3187; Percent complete: 79.7%; Average loss: 2.8807
Iteration: 3188; Percent complete: 79.7%; Average loss: 2.9221
Iteration: 3189; Percent complete: 79.7%; Average loss: 2.8282
Iteration: 3190; Percent complete: 79.8%; Average loss: 2.7867
Iteration: 3191; Percent complete: 79.8%; Average loss: 2.6943
Iteration: 3192; Percent complete: 79.8%; Average loss: 2.9298
Iteration: 3193; Percent complete: 79.8%; Average loss: 2.9932
Iteration: 3194; Percent complete: 79.8%; Average loss: 2.7203
Iteration: 3195; Percent complete: 79.9%; Average loss: 2.8783
Iteration: 3196; Percent complete: 79.9%; Average loss: 2.8322
Iteration: 3197; Percent complete: 79.9%; Average loss: 3.0444
Iteration: 3198; Percent complete: 80.0%; Average loss: 2.6447
Iteration: 3199; Percent complete: 80.0%; Average loss: 3.1449
Iteration: 3200; Percent complete: 80.0%; Average loss: 2.8691
Iteration: 3201; Percent complete: 80.0%; Average loss: 2.7992
Iteration: 3202; Percent complete: 80.0%; Average loss: 2.8497
Iteration: 3203; Percent complete: 80.1%; Average loss: 2.4671
Iteration: 3204; Percent complete: 80.1%; Average loss: 2.6941
Iteration: 3205; Percent complete: 80.1%; Average loss: 2.8914
Iteration: 3206; Percent complete: 80.2%; Average loss: 2.6959
Iteration: 3207; Percent complete: 80.2%; Average loss: 3.0594
Iteration: 3208; Percent complete: 80.2%; Average loss: 3.1237
Iteration: 3209; Percent complete: 80.2%; Average loss: 2.9610
Iteration: 3210; Percent complete: 80.2%; Average loss: 2.6563
Iteration: 3211; Percent complete: 80.3%; Average loss: 3.0440
Iteration: 3212; Percent complete: 80.3%; Average loss: 2.9981
Iteration: 3213; Percent complete: 80.3%; Average loss: 2.8852
Iteration: 3214; Percent complete: 80.3%; Average loss: 2.8475
Iteration: 3215; Percent complete: 80.4%; Average loss: 2.7203
Iteration: 3216; Percent complete: 80.4%; Average loss: 2.9303
Iteration: 3217; Percent complete: 80.4%; Average loss: 2.8172
Iteration: 3218; Percent complete: 80.5%; Average loss: 2.6762
Iteration: 3219; Percent complete: 80.5%; Average loss: 2.7204
Iteration: 3220; Percent complete: 80.5%; Average loss: 2.5223
Iteration: 3221; Percent complete: 80.5%; Average loss: 3.0958
Iteration: 3222; Percent complete: 80.5%; Average loss: 2.8735
Iteration: 3223; Percent complete: 80.6%; Average loss: 2.8201
Iteration: 3224; Percent complete: 80.6%; Average loss: 2.8945
Iteration: 3225; Percent complete: 80.6%; Average loss: 2.7677
Iteration: 3226; Percent complete: 80.7%; Average loss: 2.5932
Iteration: 3227; Percent complete: 80.7%; Average loss: 2.9787
Iteration: 3228; Percent complete: 80.7%; Average loss: 2.5725
Iteration: 3229; Percent complete: 80.7%; Average loss: 2.9291
Iteration: 3230; Percent complete: 80.8%; Average loss: 2.8884
Iteration: 3231; Percent complete: 80.8%; Average loss: 2.6949
Iteration: 3232; Percent complete: 80.8%; Average loss: 2.9188
Iteration: 3233; Percent complete: 80.8%; Average loss: 2.8318
Iteration: 3234; Percent complete: 80.8%; Average loss: 2.7087
Iteration: 3235; Percent complete: 80.9%; Average loss: 2.8553
Iteration: 3236; Percent complete: 80.9%; Average loss: 2.8642
Iteration: 3237; Percent complete: 80.9%; Average loss: 2.7217
Iteration: 3238; Percent complete: 81.0%; Average loss: 2.8327
Iteration: 3239; Percent complete: 81.0%; Average loss: 2.6220
Iteration: 3240; Percent complete: 81.0%; Average loss: 3.0024
Iteration: 3241; Percent complete: 81.0%; Average loss: 2.8433
Iteration: 3242; Percent complete: 81.0%; Average loss: 2.8660
Iteration: 3243; Percent complete: 81.1%; Average loss: 2.9835
Iteration: 3244; Percent complete: 81.1%; Average loss: 2.7789
Iteration: 3245; Percent complete: 81.1%; Average loss: 2.7196
Iteration: 3246; Percent complete: 81.2%; Average loss: 2.8354
Iteration: 3247; Percent complete: 81.2%; Average loss: 2.9684
Iteration: 3248; Percent complete: 81.2%; Average loss: 3.0573
Iteration: 3249; Percent complete: 81.2%; Average loss: 2.5273
Iteration: 3250; Percent complete: 81.2%; Average loss: 2.7733
Iteration: 3251; Percent complete: 81.3%; Average loss: 2.8401
Iteration: 3252; Percent complete: 81.3%; Average loss: 2.8466
Iteration: 3253; Percent complete: 81.3%; Average loss: 2.7187
Iteration: 3254; Percent complete: 81.3%; Average loss: 2.8170
Iteration: 3255; Percent complete: 81.4%; Average loss: 2.8208
Iteration: 3256; Percent complete: 81.4%; Average loss: 2.7290
Iteration: 3257; Percent complete: 81.4%; Average loss: 2.9257
Iteration: 3258; Percent complete: 81.5%; Average loss: 2.7091
Iteration: 3259; Percent complete: 81.5%; Average loss: 3.0676
Iteration: 3260; Percent complete: 81.5%; Average loss: 2.9473
Iteration: 3261; Percent complete: 81.5%; Average loss: 2.9535
Iteration: 3262; Percent complete: 81.5%; Average loss: 2.8607
Iteration: 3263; Percent complete: 81.6%; Average loss: 2.7985
Iteration: 3264; Percent complete: 81.6%; Average loss: 2.9635
Iteration: 3265; Percent complete: 81.6%; Average loss: 2.6956
Iteration: 3266; Percent complete: 81.7%; Average loss: 2.6121
Iteration: 3267; Percent complete: 81.7%; Average loss: 2.6886
Iteration: 3268; Percent complete: 81.7%; Average loss: 2.8081
Iteration: 3269; Percent complete: 81.7%; Average loss: 2.8387
Iteration: 3270; Percent complete: 81.8%; Average loss: 2.6826
Iteration: 3271; Percent complete: 81.8%; Average loss: 2.5688
Iteration: 3272; Percent complete: 81.8%; Average loss: 2.7328
Iteration: 3273; Percent complete: 81.8%; Average loss: 2.9001
Iteration: 3274; Percent complete: 81.8%; Average loss: 2.9637
Iteration: 3275; Percent complete: 81.9%; Average loss: 2.8041
Iteration: 3276; Percent complete: 81.9%; Average loss: 3.0126
Iteration: 3277; Percent complete: 81.9%; Average loss: 2.6901
Iteration: 3278; Percent complete: 82.0%; Average loss: 2.8555
Iteration: 3279; Percent complete: 82.0%; Average loss: 2.8311
Iteration: 3280; Percent complete: 82.0%; Average loss: 2.9059
Iteration: 3281; Percent complete: 82.0%; Average loss: 2.8084
Iteration: 3282; Percent complete: 82.0%; Average loss: 2.9284
Iteration: 3283; Percent complete: 82.1%; Average loss: 2.9189
Iteration: 3284; Percent complete: 82.1%; Average loss: 2.7496
Iteration: 3285; Percent complete: 82.1%; Average loss: 2.7184
Iteration: 3286; Percent complete: 82.2%; Average loss: 2.6511
Iteration: 3287; Percent complete: 82.2%; Average loss: 2.8794
Iteration: 3288; Percent complete: 82.2%; Average loss: 2.9232
Iteration: 3289; Percent complete: 82.2%; Average loss: 2.8783
Iteration: 3290; Percent complete: 82.2%; Average loss: 2.8027
Iteration: 3291; Percent complete: 82.3%; Average loss: 2.6321
Iteration: 3292; Percent complete: 82.3%; Average loss: 3.0577
Iteration: 3293; Percent complete: 82.3%; Average loss: 2.5855
Iteration: 3294; Percent complete: 82.3%; Average loss: 2.9875
Iteration: 3295; Percent complete: 82.4%; Average loss: 2.6811
Iteration: 3296; Percent complete: 82.4%; Average loss: 2.8992
Iteration: 3297; Percent complete: 82.4%; Average loss: 2.5065
Iteration: 3298; Percent complete: 82.5%; Average loss: 3.0675
Iteration: 3299; Percent complete: 82.5%; Average loss: 2.9829
Iteration: 3300; Percent complete: 82.5%; Average loss: 3.0906
Iteration: 3301; Percent complete: 82.5%; Average loss: 2.9660
Iteration: 3302; Percent complete: 82.5%; Average loss: 2.7108
Iteration: 3303; Percent complete: 82.6%; Average loss: 2.8309
Iteration: 3304; Percent complete: 82.6%; Average loss: 2.8713
Iteration: 3305; Percent complete: 82.6%; Average loss: 2.8123
Iteration: 3306; Percent complete: 82.7%; Average loss: 2.8151
Iteration: 3307; Percent complete: 82.7%; Average loss: 2.5703
Iteration: 3308; Percent complete: 82.7%; Average loss: 2.8555
Iteration: 3309; Percent complete: 82.7%; Average loss: 2.7689
Iteration: 3310; Percent complete: 82.8%; Average loss: 2.6571
Iteration: 3311; Percent complete: 82.8%; Average loss: 2.6593
Iteration: 3312; Percent complete: 82.8%; Average loss: 2.8599
Iteration: 3313; Percent complete: 82.8%; Average loss: 2.7456
Iteration: 3314; Percent complete: 82.8%; Average loss: 3.2370
Iteration: 3315; Percent complete: 82.9%; Average loss: 2.5824
Iteration: 3316; Percent complete: 82.9%; Average loss: 2.8240
Iteration: 3317; Percent complete: 82.9%; Average loss: 2.7773
Iteration: 3318; Percent complete: 83.0%; Average loss: 2.6889
Iteration: 3319; Percent complete: 83.0%; Average loss: 2.7250
Iteration: 3320; Percent complete: 83.0%; Average loss: 2.8141
Iteration: 3321; Percent complete: 83.0%; Average loss: 2.9037
Iteration: 3322; Percent complete: 83.0%; Average loss: 2.7594
Iteration: 3323; Percent complete: 83.1%; Average loss: 2.8628
Iteration: 3324; Percent complete: 83.1%; Average loss: 2.7421
Iteration: 3325; Percent complete: 83.1%; Average loss: 2.9480
Iteration: 3326; Percent complete: 83.2%; Average loss: 2.7866
Iteration: 3327; Percent complete: 83.2%; Average loss: 2.9669
Iteration: 3328; Percent complete: 83.2%; Average loss: 2.8995
Iteration: 3329; Percent complete: 83.2%; Average loss: 2.8106
Iteration: 3330; Percent complete: 83.2%; Average loss: 2.8117
Iteration: 3331; Percent complete: 83.3%; Average loss: 3.2377
Iteration: 3332; Percent complete: 83.3%; Average loss: 2.7896
Iteration: 3333; Percent complete: 83.3%; Average loss: 2.6604
Iteration: 3334; Percent complete: 83.4%; Average loss: 2.7268
Iteration: 3335; Percent complete: 83.4%; Average loss: 2.6920
Iteration: 3336; Percent complete: 83.4%; Average loss: 2.8593
Iteration: 3337; Percent complete: 83.4%; Average loss: 2.8250
Iteration: 3338; Percent complete: 83.5%; Average loss: 2.9525
Iteration: 3339; Percent complete: 83.5%; Average loss: 2.6762
Iteration: 3340; Percent complete: 83.5%; Average loss: 2.5518
Iteration: 3341; Percent complete: 83.5%; Average loss: 2.5090
Iteration: 3342; Percent complete: 83.5%; Average loss: 2.7235
Iteration: 3343; Percent complete: 83.6%; Average loss: 3.0031
Iteration: 3344; Percent complete: 83.6%; Average loss: 2.6327
Iteration: 3345; Percent complete: 83.6%; Average loss: 2.9872
Iteration: 3346; Percent complete: 83.7%; Average loss: 2.6927
Iteration: 3347; Percent complete: 83.7%; Average loss: 3.0501
Iteration: 3348; Percent complete: 83.7%; Average loss: 2.7392
Iteration: 3349; Percent complete: 83.7%; Average loss: 2.8168
Iteration: 3350; Percent complete: 83.8%; Average loss: 2.8138
Iteration: 3351; Percent complete: 83.8%; Average loss: 2.7340
Iteration: 3352; Percent complete: 83.8%; Average loss: 2.8355
Iteration: 3353; Percent complete: 83.8%; Average loss: 2.6144
Iteration: 3354; Percent complete: 83.9%; Average loss: 2.6712
Iteration: 3355; Percent complete: 83.9%; Average loss: 2.7298
Iteration: 3356; Percent complete: 83.9%; Average loss: 2.7193
Iteration: 3357; Percent complete: 83.9%; Average loss: 2.8557
Iteration: 3358; Percent complete: 84.0%; Average loss: 2.7701
Iteration: 3359; Percent complete: 84.0%; Average loss: 2.8581
Iteration: 3360; Percent complete: 84.0%; Average loss: 2.6864
Iteration: 3361; Percent complete: 84.0%; Average loss: 2.9035
Iteration: 3362; Percent complete: 84.0%; Average loss: 2.6547
Iteration: 3363; Percent complete: 84.1%; Average loss: 2.8392
Iteration: 3364; Percent complete: 84.1%; Average loss: 2.8830
Iteration: 3365; Percent complete: 84.1%; Average loss: 2.7235
Iteration: 3366; Percent complete: 84.2%; Average loss: 2.7842
Iteration: 3367; Percent complete: 84.2%; Average loss: 2.6290
Iteration: 3368; Percent complete: 84.2%; Average loss: 2.9388
Iteration: 3369; Percent complete: 84.2%; Average loss: 2.4899
Iteration: 3370; Percent complete: 84.2%; Average loss: 2.6345
Iteration: 3371; Percent complete: 84.3%; Average loss: 2.8460
Iteration: 3372; Percent complete: 84.3%; Average loss: 2.7728
Iteration: 3373; Percent complete: 84.3%; Average loss: 2.8134
Iteration: 3374; Percent complete: 84.4%; Average loss: 2.7512
Iteration: 3375; Percent complete: 84.4%; Average loss: 2.8554
Iteration: 3376; Percent complete: 84.4%; Average loss: 2.7899
Iteration: 3377; Percent complete: 84.4%; Average loss: 2.8001
Iteration: 3378; Percent complete: 84.5%; Average loss: 2.8420
Iteration: 3379; Percent complete: 84.5%; Average loss: 3.0820
Iteration: 3380; Percent complete: 84.5%; Average loss: 2.7047
Iteration: 3381; Percent complete: 84.5%; Average loss: 2.7728
Iteration: 3382; Percent complete: 84.5%; Average loss: 2.8300
Iteration: 3383; Percent complete: 84.6%; Average loss: 2.6151
Iteration: 3384; Percent complete: 84.6%; Average loss: 2.7125
Iteration: 3385; Percent complete: 84.6%; Average loss: 2.6769
Iteration: 3386; Percent complete: 84.7%; Average loss: 2.7223
Iteration: 3387; Percent complete: 84.7%; Average loss: 2.8727
Iteration: 3388; Percent complete: 84.7%; Average loss: 2.6571
Iteration: 3389; Percent complete: 84.7%; Average loss: 2.9501
Iteration: 3390; Percent complete: 84.8%; Average loss: 2.7346
Iteration: 3391; Percent complete: 84.8%; Average loss: 2.5165
Iteration: 3392; Percent complete: 84.8%; Average loss: 2.6042
Iteration: 3393; Percent complete: 84.8%; Average loss: 2.9004
Iteration: 3394; Percent complete: 84.9%; Average loss: 2.8674
Iteration: 3395; Percent complete: 84.9%; Average loss: 2.5646
Iteration: 3396; Percent complete: 84.9%; Average loss: 2.9486
Iteration: 3397; Percent complete: 84.9%; Average loss: 2.7653
Iteration: 3398; Percent complete: 85.0%; Average loss: 2.9023
Iteration: 3399; Percent complete: 85.0%; Average loss: 2.6147
Iteration: 3400; Percent complete: 85.0%; Average loss: 2.7827
Iteration: 3401; Percent complete: 85.0%; Average loss: 2.9842
Iteration: 3402; Percent complete: 85.0%; Average loss: 2.5746
Iteration: 3403; Percent complete: 85.1%; Average loss: 2.7923
Iteration: 3404; Percent complete: 85.1%; Average loss: 2.8411
Iteration: 3405; Percent complete: 85.1%; Average loss: 2.8373
Iteration: 3406; Percent complete: 85.2%; Average loss: 2.8526
Iteration: 3407; Percent complete: 85.2%; Average loss: 2.6705
Iteration: 3408; Percent complete: 85.2%; Average loss: 2.6924
Iteration: 3409; Percent complete: 85.2%; Average loss: 2.7232
Iteration: 3410; Percent complete: 85.2%; Average loss: 2.8857
Iteration: 3411; Percent complete: 85.3%; Average loss: 2.6142
Iteration: 3412; Percent complete: 85.3%; Average loss: 3.0156
Iteration: 3413; Percent complete: 85.3%; Average loss: 2.7420
Iteration: 3414; Percent complete: 85.4%; Average loss: 2.8581
Iteration: 3415; Percent complete: 85.4%; Average loss: 2.7026
Iteration: 3416; Percent complete: 85.4%; Average loss: 2.6317
Iteration: 3417; Percent complete: 85.4%; Average loss: 2.6547
Iteration: 3418; Percent complete: 85.5%; Average loss: 2.7558
Iteration: 3419; Percent complete: 85.5%; Average loss: 2.7759
Iteration: 3420; Percent complete: 85.5%; Average loss: 2.7797
Iteration: 3421; Percent complete: 85.5%; Average loss: 2.8983
Iteration: 3422; Percent complete: 85.5%; Average loss: 2.8906
Iteration: 3423; Percent complete: 85.6%; Average loss: 2.8003
Iteration: 3424; Percent complete: 85.6%; Average loss: 2.8551
Iteration: 3425; Percent complete: 85.6%; Average loss: 2.7942
Iteration: 3426; Percent complete: 85.7%; Average loss: 3.0901
Iteration: 3427; Percent complete: 85.7%; Average loss: 2.7756
Iteration: 3428; Percent complete: 85.7%; Average loss: 2.5581
Iteration: 3429; Percent complete: 85.7%; Average loss: 2.8419
Iteration: 3430; Percent complete: 85.8%; Average loss: 2.8665
Iteration: 3431; Percent complete: 85.8%; Average loss: 2.7857
Iteration: 3432; Percent complete: 85.8%; Average loss: 2.6739
Iteration: 3433; Percent complete: 85.8%; Average loss: 2.8003
Iteration: 3434; Percent complete: 85.9%; Average loss: 2.6590
Iteration: 3435; Percent complete: 85.9%; Average loss: 2.6428
Iteration: 3436; Percent complete: 85.9%; Average loss: 2.8210
Iteration: 3437; Percent complete: 85.9%; Average loss: 2.7870
Iteration: 3438; Percent complete: 86.0%; Average loss: 2.6938
Iteration: 3439; Percent complete: 86.0%; Average loss: 2.6372
Iteration: 3440; Percent complete: 86.0%; Average loss: 2.6846
Iteration: 3441; Percent complete: 86.0%; Average loss: 2.8460
Iteration: 3442; Percent complete: 86.1%; Average loss: 2.6693
Iteration: 3443; Percent complete: 86.1%; Average loss: 2.7460
Iteration: 3444; Percent complete: 86.1%; Average loss: 2.6157
Iteration: 3445; Percent complete: 86.1%; Average loss: 2.8158
Iteration: 3446; Percent complete: 86.2%; Average loss: 3.0826
Iteration: 3447; Percent complete: 86.2%; Average loss: 2.7306
Iteration: 3448; Percent complete: 86.2%; Average loss: 2.8874
Iteration: 3449; Percent complete: 86.2%; Average loss: 2.9370
Iteration: 3450; Percent complete: 86.2%; Average loss: 2.6276
Iteration: 3451; Percent complete: 86.3%; Average loss: 2.7562
Iteration: 3452; Percent complete: 86.3%; Average loss: 2.7894
Iteration: 3453; Percent complete: 86.3%; Average loss: 2.9537
Iteration: 3454; Percent complete: 86.4%; Average loss: 2.8358
Iteration: 3455; Percent complete: 86.4%; Average loss: 2.7046
Iteration: 3456; Percent complete: 86.4%; Average loss: 2.8650
Iteration: 3457; Percent complete: 86.4%; Average loss: 2.6330
Iteration: 3458; Percent complete: 86.5%; Average loss: 2.7084
Iteration: 3459; Percent complete: 86.5%; Average loss: 2.7895
Iteration: 3460; Percent complete: 86.5%; Average loss: 2.6841
Iteration: 3461; Percent complete: 86.5%; Average loss: 2.6645
Iteration: 3462; Percent complete: 86.6%; Average loss: 2.8445
Iteration: 3463; Percent complete: 86.6%; Average loss: 2.5983
Iteration: 3464; Percent complete: 86.6%; Average loss: 2.6579
Iteration: 3465; Percent complete: 86.6%; Average loss: 2.9958
Iteration: 3466; Percent complete: 86.7%; Average loss: 2.8689
Iteration: 3467; Percent complete: 86.7%; Average loss: 2.6508
Iteration: 3468; Percent complete: 86.7%; Average loss: 2.6562
Iteration: 3469; Percent complete: 86.7%; Average loss: 2.9309
Iteration: 3470; Percent complete: 86.8%; Average loss: 2.8597
Iteration: 3471; Percent complete: 86.8%; Average loss: 2.7744
Iteration: 3472; Percent complete: 86.8%; Average loss: 2.6567
Iteration: 3473; Percent complete: 86.8%; Average loss: 3.0218
Iteration: 3474; Percent complete: 86.9%; Average loss: 2.5893
Iteration: 3475; Percent complete: 86.9%; Average loss: 2.6728
Iteration: 3476; Percent complete: 86.9%; Average loss: 3.1543
Iteration: 3477; Percent complete: 86.9%; Average loss: 2.6378
Iteration: 3478; Percent complete: 87.0%; Average loss: 2.8748
Iteration: 3479; Percent complete: 87.0%; Average loss: 2.9087
Iteration: 3480; Percent complete: 87.0%; Average loss: 2.8507
Iteration: 3481; Percent complete: 87.0%; Average loss: 2.4830
Iteration: 3482; Percent complete: 87.1%; Average loss: 2.7180
Iteration: 3483; Percent complete: 87.1%; Average loss: 2.9004
Iteration: 3484; Percent complete: 87.1%; Average loss: 2.9185
Iteration: 3485; Percent complete: 87.1%; Average loss: 2.6202
Iteration: 3486; Percent complete: 87.2%; Average loss: 2.7963
Iteration: 3487; Percent complete: 87.2%; Average loss: 2.6440
Iteration: 3488; Percent complete: 87.2%; Average loss: 2.7415
Iteration: 3489; Percent complete: 87.2%; Average loss: 2.6805
Iteration: 3490; Percent complete: 87.2%; Average loss: 2.5840
Iteration: 3491; Percent complete: 87.3%; Average loss: 2.7423
Iteration: 3492; Percent complete: 87.3%; Average loss: 2.5752
Iteration: 3493; Percent complete: 87.3%; Average loss: 2.7212
Iteration: 3494; Percent complete: 87.4%; Average loss: 2.8618
Iteration: 3495; Percent complete: 87.4%; Average loss: 2.7177
Iteration: 3496; Percent complete: 87.4%; Average loss: 2.7626
Iteration: 3497; Percent complete: 87.4%; Average loss: 2.7071
Iteration: 3498; Percent complete: 87.5%; Average loss: 2.5556
Iteration: 3499; Percent complete: 87.5%; Average loss: 2.9111
Iteration: 3500; Percent complete: 87.5%; Average loss: 2.6867
Iteration: 3501; Percent complete: 87.5%; Average loss: 2.5953
Iteration: 3502; Percent complete: 87.5%; Average loss: 2.6189
Iteration: 3503; Percent complete: 87.6%; Average loss: 2.4894
Iteration: 3504; Percent complete: 87.6%; Average loss: 2.9171
Iteration: 3505; Percent complete: 87.6%; Average loss: 2.6179
Iteration: 3506; Percent complete: 87.6%; Average loss: 2.7177
Iteration: 3507; Percent complete: 87.7%; Average loss: 2.8672
Iteration: 3508; Percent complete: 87.7%; Average loss: 2.6319
Iteration: 3509; Percent complete: 87.7%; Average loss: 2.7588
Iteration: 3510; Percent complete: 87.8%; Average loss: 2.8781
Iteration: 3511; Percent complete: 87.8%; Average loss: 2.5571
Iteration: 3512; Percent complete: 87.8%; Average loss: 2.8151
Iteration: 3513; Percent complete: 87.8%; Average loss: 2.6496
Iteration: 3514; Percent complete: 87.8%; Average loss: 2.7816
Iteration: 3515; Percent complete: 87.9%; Average loss: 2.6411
Iteration: 3516; Percent complete: 87.9%; Average loss: 2.6755
Iteration: 3517; Percent complete: 87.9%; Average loss: 2.5469
Iteration: 3518; Percent complete: 87.9%; Average loss: 2.7131
Iteration: 3519; Percent complete: 88.0%; Average loss: 2.8863
Iteration: 3520; Percent complete: 88.0%; Average loss: 2.6000
Iteration: 3521; Percent complete: 88.0%; Average loss: 2.7671
Iteration: 3522; Percent complete: 88.0%; Average loss: 2.9299
Iteration: 3523; Percent complete: 88.1%; Average loss: 3.0479
Iteration: 3524; Percent complete: 88.1%; Average loss: 2.9460
Iteration: 3525; Percent complete: 88.1%; Average loss: 2.6721
Iteration: 3526; Percent complete: 88.1%; Average loss: 2.9540
Iteration: 3527; Percent complete: 88.2%; Average loss: 2.6508
Iteration: 3528; Percent complete: 88.2%; Average loss: 2.4597
Iteration: 3529; Percent complete: 88.2%; Average loss: 3.0012
Iteration: 3530; Percent complete: 88.2%; Average loss: 2.5870
Iteration: 3531; Percent complete: 88.3%; Average loss: 2.8256
Iteration: 3532; Percent complete: 88.3%; Average loss: 2.8360
Iteration: 3533; Percent complete: 88.3%; Average loss: 2.5811
Iteration: 3534; Percent complete: 88.3%; Average loss: 2.9346
Iteration: 3535; Percent complete: 88.4%; Average loss: 2.8081
Iteration: 3536; Percent complete: 88.4%; Average loss: 2.6994
Iteration: 3537; Percent complete: 88.4%; Average loss: 2.7158
Iteration: 3538; Percent complete: 88.4%; Average loss: 2.6438
Iteration: 3539; Percent complete: 88.5%; Average loss: 2.3766
Iteration: 3540; Percent complete: 88.5%; Average loss: 2.9284
Iteration: 3541; Percent complete: 88.5%; Average loss: 2.5962
Iteration: 3542; Percent complete: 88.5%; Average loss: 2.6492
Iteration: 3543; Percent complete: 88.6%; Average loss: 2.7524
Iteration: 3544; Percent complete: 88.6%; Average loss: 2.5711
Iteration: 3545; Percent complete: 88.6%; Average loss: 2.8324
Iteration: 3546; Percent complete: 88.6%; Average loss: 2.6669
Iteration: 3547; Percent complete: 88.7%; Average loss: 2.5303
Iteration: 3548; Percent complete: 88.7%; Average loss: 2.7545
Iteration: 3549; Percent complete: 88.7%; Average loss: 2.6318
Iteration: 3550; Percent complete: 88.8%; Average loss: 2.5449
Iteration: 3551; Percent complete: 88.8%; Average loss: 2.5592
Iteration: 3552; Percent complete: 88.8%; Average loss: 2.7126
Iteration: 3553; Percent complete: 88.8%; Average loss: 2.8191
Iteration: 3554; Percent complete: 88.8%; Average loss: 2.7438
Iteration: 3555; Percent complete: 88.9%; Average loss: 2.5631
Iteration: 3556; Percent complete: 88.9%; Average loss: 2.9460
Iteration: 3557; Percent complete: 88.9%; Average loss: 2.5237
Iteration: 3558; Percent complete: 88.9%; Average loss: 2.7742
Iteration: 3559; Percent complete: 89.0%; Average loss: 2.5833
Iteration: 3560; Percent complete: 89.0%; Average loss: 2.6436
Iteration: 3561; Percent complete: 89.0%; Average loss: 2.7545
Iteration: 3562; Percent complete: 89.0%; Average loss: 2.6458
Iteration: 3563; Percent complete: 89.1%; Average loss: 2.8444
Iteration: 3564; Percent complete: 89.1%; Average loss: 2.7360
Iteration: 3565; Percent complete: 89.1%; Average loss: 2.5548
Iteration: 3566; Percent complete: 89.1%; Average loss: 2.7849
Iteration: 3567; Percent complete: 89.2%; Average loss: 2.7392
Iteration: 3568; Percent complete: 89.2%; Average loss: 2.7625
Iteration: 3569; Percent complete: 89.2%; Average loss: 2.8940
Iteration: 3570; Percent complete: 89.2%; Average loss: 2.7157
Iteration: 3571; Percent complete: 89.3%; Average loss: 2.8600
Iteration: 3572; Percent complete: 89.3%; Average loss: 2.8331
Iteration: 3573; Percent complete: 89.3%; Average loss: 2.9302
Iteration: 3574; Percent complete: 89.3%; Average loss: 2.8578
Iteration: 3575; Percent complete: 89.4%; Average loss: 2.5860
Iteration: 3576; Percent complete: 89.4%; Average loss: 2.9221
Iteration: 3577; Percent complete: 89.4%; Average loss: 2.6842
Iteration: 3578; Percent complete: 89.5%; Average loss: 2.7252
Iteration: 3579; Percent complete: 89.5%; Average loss: 2.6479
Iteration: 3580; Percent complete: 89.5%; Average loss: 2.8545
Iteration: 3581; Percent complete: 89.5%; Average loss: 2.5585
Iteration: 3582; Percent complete: 89.5%; Average loss: 2.8316
Iteration: 3583; Percent complete: 89.6%; Average loss: 2.6297
Iteration: 3584; Percent complete: 89.6%; Average loss: 2.7157
Iteration: 3585; Percent complete: 89.6%; Average loss: 2.7602
Iteration: 3586; Percent complete: 89.6%; Average loss: 2.6080
Iteration: 3587; Percent complete: 89.7%; Average loss: 2.4435
Iteration: 3588; Percent complete: 89.7%; Average loss: 2.7942
Iteration: 3589; Percent complete: 89.7%; Average loss: 2.8601
Iteration: 3590; Percent complete: 89.8%; Average loss: 2.7250
Iteration: 3591; Percent complete: 89.8%; Average loss: 2.7028
Iteration: 3592; Percent complete: 89.8%; Average loss: 2.6650
Iteration: 3593; Percent complete: 89.8%; Average loss: 2.6377
Iteration: 3594; Percent complete: 89.8%; Average loss: 2.7574
Iteration: 3595; Percent complete: 89.9%; Average loss: 2.7063
Iteration: 3596; Percent complete: 89.9%; Average loss: 2.6871
Iteration: 3597; Percent complete: 89.9%; Average loss: 2.6530
Iteration: 3598; Percent complete: 90.0%; Average loss: 2.6301
Iteration: 3599; Percent complete: 90.0%; Average loss: 2.7370
Iteration: 3600; Percent complete: 90.0%; Average loss: 2.8548
Iteration: 3601; Percent complete: 90.0%; Average loss: 2.4939
Iteration: 3602; Percent complete: 90.0%; Average loss: 2.7414
Iteration: 3603; Percent complete: 90.1%; Average loss: 2.8696
Iteration: 3604; Percent complete: 90.1%; Average loss: 2.7491
Iteration: 3605; Percent complete: 90.1%; Average loss: 2.8922
Iteration: 3606; Percent complete: 90.1%; Average loss: 2.8856
Iteration: 3607; Percent complete: 90.2%; Average loss: 2.8876
Iteration: 3608; Percent complete: 90.2%; Average loss: 2.8192
Iteration: 3609; Percent complete: 90.2%; Average loss: 2.7504
Iteration: 3610; Percent complete: 90.2%; Average loss: 2.5639
Iteration: 3611; Percent complete: 90.3%; Average loss: 2.5734
Iteration: 3612; Percent complete: 90.3%; Average loss: 2.6616
Iteration: 3613; Percent complete: 90.3%; Average loss: 2.6862
Iteration: 3614; Percent complete: 90.3%; Average loss: 2.4596
Iteration: 3615; Percent complete: 90.4%; Average loss: 2.7684
Iteration: 3616; Percent complete: 90.4%; Average loss: 2.6842
Iteration: 3617; Percent complete: 90.4%; Average loss: 2.5483
Iteration: 3618; Percent complete: 90.5%; Average loss: 2.5575
Iteration: 3619; Percent complete: 90.5%; Average loss: 2.7260
Iteration: 3620; Percent complete: 90.5%; Average loss: 2.5148
Iteration: 3621; Percent complete: 90.5%; Average loss: 2.8196
Iteration: 3622; Percent complete: 90.5%; Average loss: 2.7632
Iteration: 3623; Percent complete: 90.6%; Average loss: 2.9208
Iteration: 3624; Percent complete: 90.6%; Average loss: 2.7342
Iteration: 3625; Percent complete: 90.6%; Average loss: 2.5218
Iteration: 3626; Percent complete: 90.6%; Average loss: 2.7242
Iteration: 3627; Percent complete: 90.7%; Average loss: 2.8138
Iteration: 3628; Percent complete: 90.7%; Average loss: 2.9252
Iteration: 3629; Percent complete: 90.7%; Average loss: 2.6953
Iteration: 3630; Percent complete: 90.8%; Average loss: 2.6328
Iteration: 3631; Percent complete: 90.8%; Average loss: 2.7790
Iteration: 3632; Percent complete: 90.8%; Average loss: 2.4393
Iteration: 3633; Percent complete: 90.8%; Average loss: 2.8253
Iteration: 3634; Percent complete: 90.8%; Average loss: 2.6023
Iteration: 3635; Percent complete: 90.9%; Average loss: 2.7103
Iteration: 3636; Percent complete: 90.9%; Average loss: 2.6269
Iteration: 3637; Percent complete: 90.9%; Average loss: 2.6204
Iteration: 3638; Percent complete: 91.0%; Average loss: 2.7043
Iteration: 3639; Percent complete: 91.0%; Average loss: 2.7751
Iteration: 3640; Percent complete: 91.0%; Average loss: 2.7613
Iteration: 3641; Percent complete: 91.0%; Average loss: 2.8797
Iteration: 3642; Percent complete: 91.0%; Average loss: 2.8774
Iteration: 3643; Percent complete: 91.1%; Average loss: 2.7501
Iteration: 3644; Percent complete: 91.1%; Average loss: 2.6048
Iteration: 3645; Percent complete: 91.1%; Average loss: 2.7410
Iteration: 3646; Percent complete: 91.1%; Average loss: 2.6422
Iteration: 3647; Percent complete: 91.2%; Average loss: 2.6440
Iteration: 3648; Percent complete: 91.2%; Average loss: 2.6316
Iteration: 3649; Percent complete: 91.2%; Average loss: 2.6351
Iteration: 3650; Percent complete: 91.2%; Average loss: 2.9178
Iteration: 3651; Percent complete: 91.3%; Average loss: 2.5953
Iteration: 3652; Percent complete: 91.3%; Average loss: 2.8704
Iteration: 3653; Percent complete: 91.3%; Average loss: 2.8670
Iteration: 3654; Percent complete: 91.3%; Average loss: 2.9795
Iteration: 3655; Percent complete: 91.4%; Average loss: 2.6376
Iteration: 3656; Percent complete: 91.4%; Average loss: 2.5279
Iteration: 3657; Percent complete: 91.4%; Average loss: 2.7249
Iteration: 3658; Percent complete: 91.5%; Average loss: 2.7430
Iteration: 3659; Percent complete: 91.5%; Average loss: 2.6359
Iteration: 3660; Percent complete: 91.5%; Average loss: 2.8735
Iteration: 3661; Percent complete: 91.5%; Average loss: 2.6204
Iteration: 3662; Percent complete: 91.5%; Average loss: 2.7629
Iteration: 3663; Percent complete: 91.6%; Average loss: 2.7139
Iteration: 3664; Percent complete: 91.6%; Average loss: 2.8237
Iteration: 3665; Percent complete: 91.6%; Average loss: 2.7409
Iteration: 3666; Percent complete: 91.6%; Average loss: 2.8350
Iteration: 3667; Percent complete: 91.7%; Average loss: 2.6042
Iteration: 3668; Percent complete: 91.7%; Average loss: 2.8461
Iteration: 3669; Percent complete: 91.7%; Average loss: 2.7045
Iteration: 3670; Percent complete: 91.8%; Average loss: 2.7948
Iteration: 3671; Percent complete: 91.8%; Average loss: 2.5426
Iteration: 3672; Percent complete: 91.8%; Average loss: 2.7070
Iteration: 3673; Percent complete: 91.8%; Average loss: 2.8257
Iteration: 3674; Percent complete: 91.8%; Average loss: 2.9771
Iteration: 3675; Percent complete: 91.9%; Average loss: 2.5526
Iteration: 3676; Percent complete: 91.9%; Average loss: 2.7384
Iteration: 3677; Percent complete: 91.9%; Average loss: 2.7259
Iteration: 3678; Percent complete: 92.0%; Average loss: 2.4618
Iteration: 3679; Percent complete: 92.0%; Average loss: 2.5725
Iteration: 3680; Percent complete: 92.0%; Average loss: 2.8893
Iteration: 3681; Percent complete: 92.0%; Average loss: 2.6327
Iteration: 3682; Percent complete: 92.0%; Average loss: 2.9446
Iteration: 3683; Percent complete: 92.1%; Average loss: 2.8237
Iteration: 3684; Percent complete: 92.1%; Average loss: 2.5703
Iteration: 3685; Percent complete: 92.1%; Average loss: 2.6409
Iteration: 3686; Percent complete: 92.2%; Average loss: 2.8209
Iteration: 3687; Percent complete: 92.2%; Average loss: 2.6935
Iteration: 3688; Percent complete: 92.2%; Average loss: 2.7092
Iteration: 3689; Percent complete: 92.2%; Average loss: 2.4699
Iteration: 3690; Percent complete: 92.2%; Average loss: 2.7224
Iteration: 3691; Percent complete: 92.3%; Average loss: 2.9105
Iteration: 3692; Percent complete: 92.3%; Average loss: 2.8280
Iteration: 3693; Percent complete: 92.3%; Average loss: 2.7287
Iteration: 3694; Percent complete: 92.3%; Average loss: 2.7633
Iteration: 3695; Percent complete: 92.4%; Average loss: 2.6821
Iteration: 3696; Percent complete: 92.4%; Average loss: 2.6989
Iteration: 3697; Percent complete: 92.4%; Average loss: 2.5961
Iteration: 3698; Percent complete: 92.5%; Average loss: 2.8826
Iteration: 3699; Percent complete: 92.5%; Average loss: 2.8288
Iteration: 3700; Percent complete: 92.5%; Average loss: 2.7418
Iteration: 3701; Percent complete: 92.5%; Average loss: 2.5191
Iteration: 3702; Percent complete: 92.5%; Average loss: 2.7897
Iteration: 3703; Percent complete: 92.6%; Average loss: 2.7585
Iteration: 3704; Percent complete: 92.6%; Average loss: 2.5108
Iteration: 3705; Percent complete: 92.6%; Average loss: 2.8609
Iteration: 3706; Percent complete: 92.7%; Average loss: 2.8562
Iteration: 3707; Percent complete: 92.7%; Average loss: 2.6774
Iteration: 3708; Percent complete: 92.7%; Average loss: 2.9053
Iteration: 3709; Percent complete: 92.7%; Average loss: 2.6452
Iteration: 3710; Percent complete: 92.8%; Average loss: 2.5384
Iteration: 3711; Percent complete: 92.8%; Average loss: 2.6756
Iteration: 3712; Percent complete: 92.8%; Average loss: 2.8678
Iteration: 3713; Percent complete: 92.8%; Average loss: 2.5508
Iteration: 3714; Percent complete: 92.8%; Average loss: 2.6692
Iteration: 3715; Percent complete: 92.9%; Average loss: 2.7476
Iteration: 3716; Percent complete: 92.9%; Average loss: 2.2736
Iteration: 3717; Percent complete: 92.9%; Average loss: 2.8411
Iteration: 3718; Percent complete: 93.0%; Average loss: 2.8753
Iteration: 3719; Percent complete: 93.0%; Average loss: 2.8455
Iteration: 3720; Percent complete: 93.0%; Average loss: 2.4852
Iteration: 3721; Percent complete: 93.0%; Average loss: 2.9287
Iteration: 3722; Percent complete: 93.0%; Average loss: 2.5453
Iteration: 3723; Percent complete: 93.1%; Average loss: 2.6184
Iteration: 3724; Percent complete: 93.1%; Average loss: 2.5829
Iteration: 3725; Percent complete: 93.1%; Average loss: 2.7422
Iteration: 3726; Percent complete: 93.2%; Average loss: 2.7931
Iteration: 3727; Percent complete: 93.2%; Average loss: 2.7806
Iteration: 3728; Percent complete: 93.2%; Average loss: 3.0934
Iteration: 3729; Percent complete: 93.2%; Average loss: 2.5104
Iteration: 3730; Percent complete: 93.2%; Average loss: 2.7854
Iteration: 3731; Percent complete: 93.3%; Average loss: 2.6941
Iteration: 3732; Percent complete: 93.3%; Average loss: 2.4704
Iteration: 3733; Percent complete: 93.3%; Average loss: 2.5033
Iteration: 3734; Percent complete: 93.3%; Average loss: 2.7192
Iteration: 3735; Percent complete: 93.4%; Average loss: 2.6379
Iteration: 3736; Percent complete: 93.4%; Average loss: 2.9183
Iteration: 3737; Percent complete: 93.4%; Average loss: 2.8788
Iteration: 3738; Percent complete: 93.5%; Average loss: 3.0513
Iteration: 3739; Percent complete: 93.5%; Average loss: 2.5573
Iteration: 3740; Percent complete: 93.5%; Average loss: 2.6924
Iteration: 3741; Percent complete: 93.5%; Average loss: 2.7363
Iteration: 3742; Percent complete: 93.5%; Average loss: 2.8312
Iteration: 3743; Percent complete: 93.6%; Average loss: 2.8704
Iteration: 3744; Percent complete: 93.6%; Average loss: 3.0553
Iteration: 3745; Percent complete: 93.6%; Average loss: 2.8927
Iteration: 3746; Percent complete: 93.7%; Average loss: 2.6767
Iteration: 3747; Percent complete: 93.7%; Average loss: 2.6841
Iteration: 3748; Percent complete: 93.7%; Average loss: 2.5251
Iteration: 3749; Percent complete: 93.7%; Average loss: 2.6503
Iteration: 3750; Percent complete: 93.8%; Average loss: 2.7670
Iteration: 3751; Percent complete: 93.8%; Average loss: 2.6335
Iteration: 3752; Percent complete: 93.8%; Average loss: 2.7145
Iteration: 3753; Percent complete: 93.8%; Average loss: 2.6286
Iteration: 3754; Percent complete: 93.8%; Average loss: 2.5933
Iteration: 3755; Percent complete: 93.9%; Average loss: 2.8053
Iteration: 3756; Percent complete: 93.9%; Average loss: 2.6317
Iteration: 3757; Percent complete: 93.9%; Average loss: 2.6815
Iteration: 3758; Percent complete: 94.0%; Average loss: 2.6664
Iteration: 3759; Percent complete: 94.0%; Average loss: 2.6182
Iteration: 3760; Percent complete: 94.0%; Average loss: 2.8135
Iteration: 3761; Percent complete: 94.0%; Average loss: 2.7857
Iteration: 3762; Percent complete: 94.0%; Average loss: 2.4804
Iteration: 3763; Percent complete: 94.1%; Average loss: 2.5638
Iteration: 3764; Percent complete: 94.1%; Average loss: 2.5625
Iteration: 3765; Percent complete: 94.1%; Average loss: 2.9376
Iteration: 3766; Percent complete: 94.2%; Average loss: 2.5402
Iteration: 3767; Percent complete: 94.2%; Average loss: 2.6412
Iteration: 3768; Percent complete: 94.2%; Average loss: 2.8802
Iteration: 3769; Percent complete: 94.2%; Average loss: 2.5866
Iteration: 3770; Percent complete: 94.2%; Average loss: 2.5204
Iteration: 3771; Percent complete: 94.3%; Average loss: 2.8393
Iteration: 3772; Percent complete: 94.3%; Average loss: 2.6224
Iteration: 3773; Percent complete: 94.3%; Average loss: 2.6619
Iteration: 3774; Percent complete: 94.3%; Average loss: 2.5691
Iteration: 3775; Percent complete: 94.4%; Average loss: 2.6863
Iteration: 3776; Percent complete: 94.4%; Average loss: 2.6338
Iteration: 3777; Percent complete: 94.4%; Average loss: 2.8398
Iteration: 3778; Percent complete: 94.5%; Average loss: 2.5563
Iteration: 3779; Percent complete: 94.5%; Average loss: 2.8237
Iteration: 3780; Percent complete: 94.5%; Average loss: 2.4876
Iteration: 3781; Percent complete: 94.5%; Average loss: 2.8584
Iteration: 3782; Percent complete: 94.5%; Average loss: 2.6027
Iteration: 3783; Percent complete: 94.6%; Average loss: 2.4725
Iteration: 3784; Percent complete: 94.6%; Average loss: 2.5678
Iteration: 3785; Percent complete: 94.6%; Average loss: 2.8965
Iteration: 3786; Percent complete: 94.7%; Average loss: 2.5324
Iteration: 3787; Percent complete: 94.7%; Average loss: 2.7744
Iteration: 3788; Percent complete: 94.7%; Average loss: 2.7455
Iteration: 3789; Percent complete: 94.7%; Average loss: 2.7909
Iteration: 3790; Percent complete: 94.8%; Average loss: 2.6322
Iteration: 3791; Percent complete: 94.8%; Average loss: 2.7379
Iteration: 3792; Percent complete: 94.8%; Average loss: 2.7744
Iteration: 3793; Percent complete: 94.8%; Average loss: 2.6233
Iteration: 3794; Percent complete: 94.8%; Average loss: 2.9122
Iteration: 3795; Percent complete: 94.9%; Average loss: 2.8248
Iteration: 3796; Percent complete: 94.9%; Average loss: 2.6944
Iteration: 3797; Percent complete: 94.9%; Average loss: 2.7646
Iteration: 3798; Percent complete: 95.0%; Average loss: 2.6259
Iteration: 3799; Percent complete: 95.0%; Average loss: 2.5933
Iteration: 3800; Percent complete: 95.0%; Average loss: 2.7169
Iteration: 3801; Percent complete: 95.0%; Average loss: 2.5168
Iteration: 3802; Percent complete: 95.0%; Average loss: 2.9230
Iteration: 3803; Percent complete: 95.1%; Average loss: 2.5125
Iteration: 3804; Percent complete: 95.1%; Average loss: 2.6977
Iteration: 3805; Percent complete: 95.1%; Average loss: 2.8546
Iteration: 3806; Percent complete: 95.2%; Average loss: 2.5126
Iteration: 3807; Percent complete: 95.2%; Average loss: 2.7847
Iteration: 3808; Percent complete: 95.2%; Average loss: 2.6380
Iteration: 3809; Percent complete: 95.2%; Average loss: 2.5557
Iteration: 3810; Percent complete: 95.2%; Average loss: 2.6592
Iteration: 3811; Percent complete: 95.3%; Average loss: 2.4581
Iteration: 3812; Percent complete: 95.3%; Average loss: 2.7821
Iteration: 3813; Percent complete: 95.3%; Average loss: 2.4795
Iteration: 3814; Percent complete: 95.3%; Average loss: 2.7577
Iteration: 3815; Percent complete: 95.4%; Average loss: 2.8705
Iteration: 3816; Percent complete: 95.4%; Average loss: 2.6634
Iteration: 3817; Percent complete: 95.4%; Average loss: 2.7513
Iteration: 3818; Percent complete: 95.5%; Average loss: 2.5826
Iteration: 3819; Percent complete: 95.5%; Average loss: 2.7438
Iteration: 3820; Percent complete: 95.5%; Average loss: 2.8001
Iteration: 3821; Percent complete: 95.5%; Average loss: 2.6715
Iteration: 3822; Percent complete: 95.5%; Average loss: 2.6402
Iteration: 3823; Percent complete: 95.6%; Average loss: 2.4990
Iteration: 3824; Percent complete: 95.6%; Average loss: 2.8053
Iteration: 3825; Percent complete: 95.6%; Average loss: 2.6073
Iteration: 3826; Percent complete: 95.7%; Average loss: 2.3903
Iteration: 3827; Percent complete: 95.7%; Average loss: 2.6923
Iteration: 3828; Percent complete: 95.7%; Average loss: 2.5252
Iteration: 3829; Percent complete: 95.7%; Average loss: 2.5632
Iteration: 3830; Percent complete: 95.8%; Average loss: 2.7106
Iteration: 3831; Percent complete: 95.8%; Average loss: 2.5651
Iteration: 3832; Percent complete: 95.8%; Average loss: 2.5584
Iteration: 3833; Percent complete: 95.8%; Average loss: 2.6265
Iteration: 3834; Percent complete: 95.9%; Average loss: 2.6342
Iteration: 3835; Percent complete: 95.9%; Average loss: 2.7974
Iteration: 3836; Percent complete: 95.9%; Average loss: 2.7173
Iteration: 3837; Percent complete: 95.9%; Average loss: 2.5848
Iteration: 3838; Percent complete: 96.0%; Average loss: 2.6093
Iteration: 3839; Percent complete: 96.0%; Average loss: 2.7593
Iteration: 3840; Percent complete: 96.0%; Average loss: 2.8286
Iteration: 3841; Percent complete: 96.0%; Average loss: 2.7316
Iteration: 3842; Percent complete: 96.0%; Average loss: 2.5692
Iteration: 3843; Percent complete: 96.1%; Average loss: 2.8870
Iteration: 3844; Percent complete: 96.1%; Average loss: 2.5242
Iteration: 3845; Percent complete: 96.1%; Average loss: 2.6321
Iteration: 3846; Percent complete: 96.2%; Average loss: 2.7619
Iteration: 3847; Percent complete: 96.2%; Average loss: 2.6850
Iteration: 3848; Percent complete: 96.2%; Average loss: 2.6538
Iteration: 3849; Percent complete: 96.2%; Average loss: 2.7051
Iteration: 3850; Percent complete: 96.2%; Average loss: 2.6633
Iteration: 3851; Percent complete: 96.3%; Average loss: 2.6822
Iteration: 3852; Percent complete: 96.3%; Average loss: 2.3225
Iteration: 3853; Percent complete: 96.3%; Average loss: 2.5003
Iteration: 3854; Percent complete: 96.4%; Average loss: 2.6223
Iteration: 3855; Percent complete: 96.4%; Average loss: 2.6392
Iteration: 3856; Percent complete: 96.4%; Average loss: 2.5614
Iteration: 3857; Percent complete: 96.4%; Average loss: 2.6369
Iteration: 3858; Percent complete: 96.5%; Average loss: 2.5507
Iteration: 3859; Percent complete: 96.5%; Average loss: 2.7534
Iteration: 3860; Percent complete: 96.5%; Average loss: 2.6955
Iteration: 3861; Percent complete: 96.5%; Average loss: 2.5819
Iteration: 3862; Percent complete: 96.5%; Average loss: 2.6534
Iteration: 3863; Percent complete: 96.6%; Average loss: 2.4515
Iteration: 3864; Percent complete: 96.6%; Average loss: 2.7493
Iteration: 3865; Percent complete: 96.6%; Average loss: 2.4687
Iteration: 3866; Percent complete: 96.7%; Average loss: 2.7402
Iteration: 3867; Percent complete: 96.7%; Average loss: 2.4355
Iteration: 3868; Percent complete: 96.7%; Average loss: 2.6718
Iteration: 3869; Percent complete: 96.7%; Average loss: 2.4134
Iteration: 3870; Percent complete: 96.8%; Average loss: 2.8465
Iteration: 3871; Percent complete: 96.8%; Average loss: 2.7492
Iteration: 3872; Percent complete: 96.8%; Average loss: 2.5461
Iteration: 3873; Percent complete: 96.8%; Average loss: 2.5542
Iteration: 3874; Percent complete: 96.9%; Average loss: 2.6845
Iteration: 3875; Percent complete: 96.9%; Average loss: 2.6585
Iteration: 3876; Percent complete: 96.9%; Average loss: 2.7740
Iteration: 3877; Percent complete: 96.9%; Average loss: 2.3354
Iteration: 3878; Percent complete: 97.0%; Average loss: 2.5119
Iteration: 3879; Percent complete: 97.0%; Average loss: 2.7194
Iteration: 3880; Percent complete: 97.0%; Average loss: 2.6618
Iteration: 3881; Percent complete: 97.0%; Average loss: 2.6865
Iteration: 3882; Percent complete: 97.0%; Average loss: 2.6857
Iteration: 3883; Percent complete: 97.1%; Average loss: 2.8556
Iteration: 3884; Percent complete: 97.1%; Average loss: 2.7352
Iteration: 3885; Percent complete: 97.1%; Average loss: 2.5993
Iteration: 3886; Percent complete: 97.2%; Average loss: 2.6042
Iteration: 3887; Percent complete: 97.2%; Average loss: 2.6271
Iteration: 3888; Percent complete: 97.2%; Average loss: 2.6833
Iteration: 3889; Percent complete: 97.2%; Average loss: 2.5704
Iteration: 3890; Percent complete: 97.2%; Average loss: 2.7891
Iteration: 3891; Percent complete: 97.3%; Average loss: 2.6339
Iteration: 3892; Percent complete: 97.3%; Average loss: 2.4595
Iteration: 3893; Percent complete: 97.3%; Average loss: 2.5158
Iteration: 3894; Percent complete: 97.4%; Average loss: 2.5977
Iteration: 3895; Percent complete: 97.4%; Average loss: 2.6829
Iteration: 3896; Percent complete: 97.4%; Average loss: 2.7905
Iteration: 3897; Percent complete: 97.4%; Average loss: 2.5284
Iteration: 3898; Percent complete: 97.5%; Average loss: 2.5469
Iteration: 3899; Percent complete: 97.5%; Average loss: 2.5922
Iteration: 3900; Percent complete: 97.5%; Average loss: 2.3264
Iteration: 3901; Percent complete: 97.5%; Average loss: 2.4475
Iteration: 3902; Percent complete: 97.5%; Average loss: 2.7190
Iteration: 3903; Percent complete: 97.6%; Average loss: 2.4901
Iteration: 3904; Percent complete: 97.6%; Average loss: 2.6449
Iteration: 3905; Percent complete: 97.6%; Average loss: 2.6619
Iteration: 3906; Percent complete: 97.7%; Average loss: 2.6838
Iteration: 3907; Percent complete: 97.7%; Average loss: 2.6197
Iteration: 3908; Percent complete: 97.7%; Average loss: 2.6591
Iteration: 3909; Percent complete: 97.7%; Average loss: 2.4767
Iteration: 3910; Percent complete: 97.8%; Average loss: 2.5998
Iteration: 3911; Percent complete: 97.8%; Average loss: 2.6389
Iteration: 3912; Percent complete: 97.8%; Average loss: 2.7103
Iteration: 3913; Percent complete: 97.8%; Average loss: 2.7104
Iteration: 3914; Percent complete: 97.9%; Average loss: 2.6026
Iteration: 3915; Percent complete: 97.9%; Average loss: 2.5175
Iteration: 3916; Percent complete: 97.9%; Average loss: 2.7894
Iteration: 3917; Percent complete: 97.9%; Average loss: 2.5681
Iteration: 3918; Percent complete: 98.0%; Average loss: 2.6036
Iteration: 3919; Percent complete: 98.0%; Average loss: 2.5966
Iteration: 3920; Percent complete: 98.0%; Average loss: 2.3330
Iteration: 3921; Percent complete: 98.0%; Average loss: 2.4551
Iteration: 3922; Percent complete: 98.0%; Average loss: 2.7551
Iteration: 3923; Percent complete: 98.1%; Average loss: 2.7084
Iteration: 3924; Percent complete: 98.1%; Average loss: 2.6424
Iteration: 3925; Percent complete: 98.1%; Average loss: 2.9980
Iteration: 3926; Percent complete: 98.2%; Average loss: 2.6149
Iteration: 3927; Percent complete: 98.2%; Average loss: 2.5085
Iteration: 3928; Percent complete: 98.2%; Average loss: 2.5134
Iteration: 3929; Percent complete: 98.2%; Average loss: 2.8486
Iteration: 3930; Percent complete: 98.2%; Average loss: 2.7040
Iteration: 3931; Percent complete: 98.3%; Average loss: 2.5472
Iteration: 3932; Percent complete: 98.3%; Average loss: 2.4525
Iteration: 3933; Percent complete: 98.3%; Average loss: 2.6737
Iteration: 3934; Percent complete: 98.4%; Average loss: 2.7022
Iteration: 3935; Percent complete: 98.4%; Average loss: 2.6267
Iteration: 3936; Percent complete: 98.4%; Average loss: 2.4451
Iteration: 3937; Percent complete: 98.4%; Average loss: 2.5987
Iteration: 3938; Percent complete: 98.5%; Average loss: 2.6552
Iteration: 3939; Percent complete: 98.5%; Average loss: 2.3497
Iteration: 3940; Percent complete: 98.5%; Average loss: 2.7079
Iteration: 3941; Percent complete: 98.5%; Average loss: 2.7521
Iteration: 3942; Percent complete: 98.6%; Average loss: 2.6990
Iteration: 3943; Percent complete: 98.6%; Average loss: 2.7761
Iteration: 3944; Percent complete: 98.6%; Average loss: 2.6669
Iteration: 3945; Percent complete: 98.6%; Average loss: 2.5236
Iteration: 3946; Percent complete: 98.7%; Average loss: 2.6241
Iteration: 3947; Percent complete: 98.7%; Average loss: 2.9071
Iteration: 3948; Percent complete: 98.7%; Average loss: 2.6902
Iteration: 3949; Percent complete: 98.7%; Average loss: 2.5955
Iteration: 3950; Percent complete: 98.8%; Average loss: 2.8841
Iteration: 3951; Percent complete: 98.8%; Average loss: 2.6313
Iteration: 3952; Percent complete: 98.8%; Average loss: 2.6170
Iteration: 3953; Percent complete: 98.8%; Average loss: 2.4074
Iteration: 3954; Percent complete: 98.9%; Average loss: 2.6852
Iteration: 3955; Percent complete: 98.9%; Average loss: 2.7340
Iteration: 3956; Percent complete: 98.9%; Average loss: 2.5586
Iteration: 3957; Percent complete: 98.9%; Average loss: 2.8389
Iteration: 3958; Percent complete: 99.0%; Average loss: 2.5891
Iteration: 3959; Percent complete: 99.0%; Average loss: 2.6777
Iteration: 3960; Percent complete: 99.0%; Average loss: 2.7540
Iteration: 3961; Percent complete: 99.0%; Average loss: 2.5177
Iteration: 3962; Percent complete: 99.1%; Average loss: 2.4543
Iteration: 3963; Percent complete: 99.1%; Average loss: 2.5390
Iteration: 3964; Percent complete: 99.1%; Average loss: 2.7954
Iteration: 3965; Percent complete: 99.1%; Average loss: 2.6316
Iteration: 3966; Percent complete: 99.2%; Average loss: 2.5968
Iteration: 3967; Percent complete: 99.2%; Average loss: 2.7417
Iteration: 3968; Percent complete: 99.2%; Average loss: 2.5618
Iteration: 3969; Percent complete: 99.2%; Average loss: 2.6872
Iteration: 3970; Percent complete: 99.2%; Average loss: 2.5543
Iteration: 3971; Percent complete: 99.3%; Average loss: 2.5453
Iteration: 3972; Percent complete: 99.3%; Average loss: 2.5476
Iteration: 3973; Percent complete: 99.3%; Average loss: 2.4566
Iteration: 3974; Percent complete: 99.4%; Average loss: 2.5454
Iteration: 3975; Percent complete: 99.4%; Average loss: 2.7893
Iteration: 3976; Percent complete: 99.4%; Average loss: 2.7494
Iteration: 3977; Percent complete: 99.4%; Average loss: 2.3692
Iteration: 3978; Percent complete: 99.5%; Average loss: 2.6872
Iteration: 3979; Percent complete: 99.5%; Average loss: 2.6009
Iteration: 3980; Percent complete: 99.5%; Average loss: 2.7809
Iteration: 3981; Percent complete: 99.5%; Average loss: 2.8676
Iteration: 3982; Percent complete: 99.6%; Average loss: 2.5266
Iteration: 3983; Percent complete: 99.6%; Average loss: 2.6390
Iteration: 3984; Percent complete: 99.6%; Average loss: 2.7540
Iteration: 3985; Percent complete: 99.6%; Average loss: 2.6988
Iteration: 3986; Percent complete: 99.7%; Average loss: 2.6547
Iteration: 3987; Percent complete: 99.7%; Average loss: 2.7775
Iteration: 3988; Percent complete: 99.7%; Average loss: 2.5928
Iteration: 3989; Percent complete: 99.7%; Average loss: 2.8121
Iteration: 3990; Percent complete: 99.8%; Average loss: 2.6493
Iteration: 3991; Percent complete: 99.8%; Average loss: 2.5778
Iteration: 3992; Percent complete: 99.8%; Average loss: 2.9669
Iteration: 3993; Percent complete: 99.8%; Average loss: 2.6051
Iteration: 3994; Percent complete: 99.9%; Average loss: 2.7225
Iteration: 3995; Percent complete: 99.9%; Average loss: 2.5854
Iteration: 3996; Percent complete: 99.9%; Average loss: 2.6573
Iteration: 3997; Percent complete: 99.9%; Average loss: 2.6933
Iteration: 3998; Percent complete: 100.0%; Average loss: 2.7302
Iteration: 3999; Percent complete: 100.0%; Average loss: 2.7529
Iteration: 4000; Percent complete: 100.0%; Average loss: 2.8014

Run Evaluation

To chat with your model, run the following block.

# 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)

Conclusion

That’s all for this one, folks. Congratulations, you now know the fundamentals to building a generative chatbot model! If you’re interested, you can try tailoring the chatbot’s behavior by tweaking the model and training parameters and customizing the data that you train the model on.

Check out the other tutorials for more cool deep learning applications in PyTorch!

Total running time of the script: ( 5 minutes 47.227 seconds)

Gallery generated by Sphinx-Gallery

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources