Note

Go to the end to download the full example code.

Chatbot Tutorial#

Created On: Aug 14, 2018 | Last Updated: Jan 24, 2025 | Last Verified: Nov 05, 2024

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.

> 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

Handle loading and preprocessing of Cornell Movie-Dialogs Corpus dataset
Implement a sequence-to-sequence model with Luong attention mechanism(s)
Jointly train encoder and decoder models using mini-batches
Implement greedy-search decoding module
Interact with trained chatbot

Acknowledgments

This tutorial borrows code from the following sources:

Yuan-Kuei Wu’s pytorch-chatbot implementation: ywk991112/pytorch-chatbot
Sean Robertson’s practical-pytorch seq2seq-translation example: spro/practical-pytorch
FloydHub Cornell Movie Corpus preprocessing code: floydhub/textutil-preprocess-cornell-movie-corpus

Preparations#

To get started, download the Movie-Dialogs Corpus zip file.

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

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


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

Using cuda device

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

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

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


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

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

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

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:

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

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([[7172,   19,   40,   22,  280],
        [   6,    4,   11,  294,  137],
        [ 197,   24,   93,  140,    6],
        [ 816,  136,  531,   10,    2],
        [2193,  172,  187,    2,    0],
        [  22,   72,    2,    0,    0],
        [ 488,   10,    0,    0,    0],
        [  10,    2,    0,    0,    0],
        [   2,    0,    0,    0,    0]])
lengths: tensor([9, 8, 6, 5, 4])
target_variable: tensor([[   7,   85,   24,  254,   13],
        [ 154,   17,  113,  857,  208],
        [  37,   19,   42,   14,  135],
        [  14,   24,  187,    2, 1914],
        [   2,  136, 2795,    0,  160],
        [   0,  172,  295,    0,   14],
        [   0,   72,   24,    0,    2],
        [   0,   14,   83,    0,    0],
        [   0,    2,   14,    0,    0],
        [   0,    0,    2,    0,    0]])
mask: tensor([[ True,  True,  True,  True,  True],
        [ True,  True,  True,  True,  True],
        [ True,  True,  True,  True,  True],
        [ True,  True,  True,  True,  True],
        [ True,  True,  True, False,  True],
        [False,  True,  True, False,  True],
        [False,  True,  True, False,  True],
        [False,  True,  True, False, False],
        [False,  True,  True, False, False],
        [False, False,  True, False, False]])
max_target_len: 10

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.

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:

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:

Convert word indexes to embeddings.

Pack padded batch of sequences for RNN module.

Forward pass through GRU.

Unpack padding.

Sum bidirectional GRU outputs.

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

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

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:

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”:

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).

# 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:

Get embedding of current input word.

Forward through unidirectional GRU.

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

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

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

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

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.

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

Sequence of Operations:

Forward pass entire input batch through encoder.

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

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

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

Calculate and accumulate loss.

Perform backpropagation.

Clip gradients.

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 backpropagation
    loss.backward()

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

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

    return sum(print_losses) / n_totals

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:

Forward input through encoder model.

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

Initialize decoder’s first input as SOS_token.

Initialize tensors to append decoded words to.

Iteratively decode one word token at a time:

Forward pass through decoder.

Obtain most likely word token and its softmax score.

Record token and score.

Prepare current token to be next decoder input.

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

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

Sample code to load from a checkpoint:

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

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

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

Building optimizers ...
Starting Training!
Initializing ...
Training...
Iteration: 1; Percent complete: 0.0%; Average loss: 8.9587
Iteration: 2; Percent complete: 0.1%; Average loss: 8.8558
Iteration: 3; Percent complete: 0.1%; Average loss: 8.6964
Iteration: 4; Percent complete: 0.1%; Average loss: 8.4079
Iteration: 5; Percent complete: 0.1%; Average loss: 8.0556
Iteration: 6; Percent complete: 0.1%; Average loss: 7.4081
Iteration: 7; Percent complete: 0.2%; Average loss: 6.9985
Iteration: 8; Percent complete: 0.2%; Average loss: 6.8681
Iteration: 9; Percent complete: 0.2%; Average loss: 6.9717
Iteration: 10; Percent complete: 0.2%; Average loss: 6.8892
Iteration: 11; Percent complete: 0.3%; Average loss: 6.5066
Iteration: 12; Percent complete: 0.3%; Average loss: 5.8133
Iteration: 13; Percent complete: 0.3%; Average loss: 5.5833
Iteration: 14; Percent complete: 0.4%; Average loss: 5.6613
Iteration: 15; Percent complete: 0.4%; Average loss: 5.5783
Iteration: 16; Percent complete: 0.4%; Average loss: 5.3537
Iteration: 17; Percent complete: 0.4%; Average loss: 5.3598
Iteration: 18; Percent complete: 0.4%; Average loss: 5.3769
Iteration: 19; Percent complete: 0.5%; Average loss: 5.0302
Iteration: 20; Percent complete: 0.5%; Average loss: 4.8278
Iteration: 21; Percent complete: 0.5%; Average loss: 4.8026
Iteration: 22; Percent complete: 0.5%; Average loss: 4.6577
Iteration: 23; Percent complete: 0.6%; Average loss: 4.9549
Iteration: 24; Percent complete: 0.6%; Average loss: 4.8526
Iteration: 25; Percent complete: 0.6%; Average loss: 4.8454
Iteration: 26; Percent complete: 0.7%; Average loss: 4.9693
Iteration: 27; Percent complete: 0.7%; Average loss: 5.0812
Iteration: 28; Percent complete: 0.7%; Average loss: 4.9316
Iteration: 29; Percent complete: 0.7%; Average loss: 4.6428
Iteration: 30; Percent complete: 0.8%; Average loss: 4.7246
Iteration: 31; Percent complete: 0.8%; Average loss: 4.6890
Iteration: 32; Percent complete: 0.8%; Average loss: 4.6278
Iteration: 33; Percent complete: 0.8%; Average loss: 4.8001
Iteration: 34; Percent complete: 0.9%; Average loss: 4.8752
Iteration: 35; Percent complete: 0.9%; Average loss: 4.6795
Iteration: 36; Percent complete: 0.9%; Average loss: 4.5764
Iteration: 37; Percent complete: 0.9%; Average loss: 4.7004
Iteration: 38; Percent complete: 0.9%; Average loss: 4.7144
Iteration: 39; Percent complete: 1.0%; Average loss: 5.1447
Iteration: 40; Percent complete: 1.0%; Average loss: 4.5304
Iteration: 41; Percent complete: 1.0%; Average loss: 4.7713
Iteration: 42; Percent complete: 1.1%; Average loss: 4.6504
Iteration: 43; Percent complete: 1.1%; Average loss: 4.9181
Iteration: 44; Percent complete: 1.1%; Average loss: 4.7371
Iteration: 45; Percent complete: 1.1%; Average loss: 4.6165
Iteration: 46; Percent complete: 1.1%; Average loss: 4.8145
Iteration: 47; Percent complete: 1.2%; Average loss: 4.5658
Iteration: 48; Percent complete: 1.2%; Average loss: 4.4256
Iteration: 49; Percent complete: 1.2%; Average loss: 4.7142
Iteration: 50; Percent complete: 1.2%; Average loss: 4.8448
Iteration: 51; Percent complete: 1.3%; Average loss: 4.6573
Iteration: 52; Percent complete: 1.3%; Average loss: 4.6873
Iteration: 53; Percent complete: 1.3%; Average loss: 4.5108
Iteration: 54; Percent complete: 1.4%; Average loss: 4.5683
Iteration: 55; Percent complete: 1.4%; Average loss: 4.6385
Iteration: 56; Percent complete: 1.4%; Average loss: 4.7451
Iteration: 57; Percent complete: 1.4%; Average loss: 4.4902
Iteration: 58; Percent complete: 1.5%; Average loss: 4.5547
Iteration: 59; Percent complete: 1.5%; Average loss: 4.6997
Iteration: 60; Percent complete: 1.5%; Average loss: 4.5469
Iteration: 61; Percent complete: 1.5%; Average loss: 4.6751
Iteration: 62; Percent complete: 1.6%; Average loss: 4.5925
Iteration: 63; Percent complete: 1.6%; Average loss: 4.5139
Iteration: 64; Percent complete: 1.6%; Average loss: 4.5119
Iteration: 65; Percent complete: 1.6%; Average loss: 4.4231
Iteration: 66; Percent complete: 1.7%; Average loss: 4.1942
Iteration: 67; Percent complete: 1.7%; Average loss: 4.6982
Iteration: 68; Percent complete: 1.7%; Average loss: 4.4867
Iteration: 69; Percent complete: 1.7%; Average loss: 4.4911
Iteration: 70; Percent complete: 1.8%; Average loss: 4.6815
Iteration: 71; Percent complete: 1.8%; Average loss: 4.3873
Iteration: 72; Percent complete: 1.8%; Average loss: 4.5475
Iteration: 73; Percent complete: 1.8%; Average loss: 4.6293
Iteration: 74; Percent complete: 1.8%; Average loss: 4.7213
Iteration: 75; Percent complete: 1.9%; Average loss: 4.2926
Iteration: 76; Percent complete: 1.9%; Average loss: 4.5070
Iteration: 77; Percent complete: 1.9%; Average loss: 4.5638
Iteration: 78; Percent complete: 1.9%; Average loss: 4.6557
Iteration: 79; Percent complete: 2.0%; Average loss: 4.4342
Iteration: 80; Percent complete: 2.0%; Average loss: 4.5381
Iteration: 81; Percent complete: 2.0%; Average loss: 4.6097
Iteration: 82; Percent complete: 2.1%; Average loss: 4.3991
Iteration: 83; Percent complete: 2.1%; Average loss: 4.3945
Iteration: 84; Percent complete: 2.1%; Average loss: 4.6147
Iteration: 85; Percent complete: 2.1%; Average loss: 4.4419
Iteration: 86; Percent complete: 2.1%; Average loss: 4.4509
Iteration: 87; Percent complete: 2.2%; Average loss: 4.5773
Iteration: 88; Percent complete: 2.2%; Average loss: 4.5624
Iteration: 89; Percent complete: 2.2%; Average loss: 4.6437
Iteration: 90; Percent complete: 2.2%; Average loss: 4.3479
Iteration: 91; Percent complete: 2.3%; Average loss: 4.5756
Iteration: 92; Percent complete: 2.3%; Average loss: 4.2600
Iteration: 93; Percent complete: 2.3%; Average loss: 4.2565
Iteration: 94; Percent complete: 2.4%; Average loss: 4.5068
Iteration: 95; Percent complete: 2.4%; Average loss: 4.6716
Iteration: 96; Percent complete: 2.4%; Average loss: 4.3539
Iteration: 97; Percent complete: 2.4%; Average loss: 4.4949
Iteration: 98; Percent complete: 2.5%; Average loss: 4.5734
Iteration: 99; Percent complete: 2.5%; Average loss: 4.5238
Iteration: 100; Percent complete: 2.5%; Average loss: 4.4307
Iteration: 101; Percent complete: 2.5%; Average loss: 4.4919
Iteration: 102; Percent complete: 2.5%; Average loss: 4.5960
Iteration: 103; Percent complete: 2.6%; Average loss: 4.3821
Iteration: 104; Percent complete: 2.6%; Average loss: 4.4545
Iteration: 105; Percent complete: 2.6%; Average loss: 4.2481
Iteration: 106; Percent complete: 2.6%; Average loss: 4.3890
Iteration: 107; Percent complete: 2.7%; Average loss: 4.3253
Iteration: 108; Percent complete: 2.7%; Average loss: 4.3298
Iteration: 109; Percent complete: 2.7%; Average loss: 4.5262
Iteration: 110; Percent complete: 2.8%; Average loss: 4.3278
Iteration: 111; Percent complete: 2.8%; Average loss: 4.4208
Iteration: 112; Percent complete: 2.8%; Average loss: 4.4431
Iteration: 113; Percent complete: 2.8%; Average loss: 4.2705
Iteration: 114; Percent complete: 2.9%; Average loss: 4.3958
Iteration: 115; Percent complete: 2.9%; Average loss: 4.3547
Iteration: 116; Percent complete: 2.9%; Average loss: 4.6566
Iteration: 117; Percent complete: 2.9%; Average loss: 3.9883
Iteration: 118; Percent complete: 2.9%; Average loss: 4.1592
Iteration: 119; Percent complete: 3.0%; Average loss: 4.1093
Iteration: 120; Percent complete: 3.0%; Average loss: 4.5839
Iteration: 121; Percent complete: 3.0%; Average loss: 4.3132
Iteration: 122; Percent complete: 3.0%; Average loss: 4.1267
Iteration: 123; Percent complete: 3.1%; Average loss: 4.6022
Iteration: 124; Percent complete: 3.1%; Average loss: 4.5048
Iteration: 125; Percent complete: 3.1%; Average loss: 4.5984
Iteration: 126; Percent complete: 3.1%; Average loss: 4.2592
Iteration: 127; Percent complete: 3.2%; Average loss: 4.2728
Iteration: 128; Percent complete: 3.2%; Average loss: 4.4041
Iteration: 129; Percent complete: 3.2%; Average loss: 4.1167
Iteration: 130; Percent complete: 3.2%; Average loss: 4.2902
Iteration: 131; Percent complete: 3.3%; Average loss: 4.3239
Iteration: 132; Percent complete: 3.3%; Average loss: 3.9690
Iteration: 133; Percent complete: 3.3%; Average loss: 4.5888
Iteration: 134; Percent complete: 3.4%; Average loss: 4.2743
Iteration: 135; Percent complete: 3.4%; Average loss: 4.4480
Iteration: 136; Percent complete: 3.4%; Average loss: 4.2776
Iteration: 137; Percent complete: 3.4%; Average loss: 4.2427
Iteration: 138; Percent complete: 3.5%; Average loss: 4.2280
Iteration: 139; Percent complete: 3.5%; Average loss: 4.5619
Iteration: 140; Percent complete: 3.5%; Average loss: 4.3062
Iteration: 141; Percent complete: 3.5%; Average loss: 4.1579
Iteration: 142; Percent complete: 3.5%; Average loss: 4.2275
Iteration: 143; Percent complete: 3.6%; Average loss: 4.2674
Iteration: 144; Percent complete: 3.6%; Average loss: 4.4624
Iteration: 145; Percent complete: 3.6%; Average loss: 4.3913
Iteration: 146; Percent complete: 3.6%; Average loss: 4.2383
Iteration: 147; Percent complete: 3.7%; Average loss: 4.6558
Iteration: 148; Percent complete: 3.7%; Average loss: 4.4415
Iteration: 149; Percent complete: 3.7%; Average loss: 4.3892
Iteration: 150; Percent complete: 3.8%; Average loss: 4.2281
Iteration: 151; Percent complete: 3.8%; Average loss: 4.0087
Iteration: 152; Percent complete: 3.8%; Average loss: 4.2443
Iteration: 153; Percent complete: 3.8%; Average loss: 4.2702
Iteration: 154; Percent complete: 3.9%; Average loss: 4.3593
Iteration: 155; Percent complete: 3.9%; Average loss: 4.1313
Iteration: 156; Percent complete: 3.9%; Average loss: 4.0903
Iteration: 157; Percent complete: 3.9%; Average loss: 4.3475
Iteration: 158; Percent complete: 4.0%; Average loss: 4.4043
Iteration: 159; Percent complete: 4.0%; Average loss: 4.2327
Iteration: 160; Percent complete: 4.0%; Average loss: 4.2191
Iteration: 161; Percent complete: 4.0%; Average loss: 4.0864
Iteration: 162; Percent complete: 4.0%; Average loss: 4.0765
Iteration: 163; Percent complete: 4.1%; Average loss: 4.4349
Iteration: 164; Percent complete: 4.1%; Average loss: 4.2219
Iteration: 165; Percent complete: 4.1%; Average loss: 4.2703
Iteration: 166; Percent complete: 4.2%; Average loss: 4.1064
Iteration: 167; Percent complete: 4.2%; Average loss: 4.2336
Iteration: 168; Percent complete: 4.2%; Average loss: 4.1168
Iteration: 169; Percent complete: 4.2%; Average loss: 4.3094
Iteration: 170; Percent complete: 4.2%; Average loss: 4.2827
Iteration: 171; Percent complete: 4.3%; Average loss: 4.3003
Iteration: 172; Percent complete: 4.3%; Average loss: 4.1680
Iteration: 173; Percent complete: 4.3%; Average loss: 4.3871
Iteration: 174; Percent complete: 4.3%; Average loss: 3.9258
Iteration: 175; Percent complete: 4.4%; Average loss: 4.2213
Iteration: 176; Percent complete: 4.4%; Average loss: 4.3930
Iteration: 177; Percent complete: 4.4%; Average loss: 4.0515
Iteration: 178; Percent complete: 4.5%; Average loss: 4.3861
Iteration: 179; Percent complete: 4.5%; Average loss: 4.0839
Iteration: 180; Percent complete: 4.5%; Average loss: 4.1058
Iteration: 181; Percent complete: 4.5%; Average loss: 4.1950
Iteration: 182; Percent complete: 4.5%; Average loss: 4.2480
Iteration: 183; Percent complete: 4.6%; Average loss: 4.2944
Iteration: 184; Percent complete: 4.6%; Average loss: 3.9714
Iteration: 185; Percent complete: 4.6%; Average loss: 4.2254
Iteration: 186; Percent complete: 4.7%; Average loss: 4.2176
Iteration: 187; Percent complete: 4.7%; Average loss: 3.8928
Iteration: 188; Percent complete: 4.7%; Average loss: 3.7808
Iteration: 189; Percent complete: 4.7%; Average loss: 4.1281
Iteration: 190; Percent complete: 4.8%; Average loss: 4.0888
Iteration: 191; Percent complete: 4.8%; Average loss: 4.2477
Iteration: 192; Percent complete: 4.8%; Average loss: 4.3644
Iteration: 193; Percent complete: 4.8%; Average loss: 4.1355
Iteration: 194; Percent complete: 4.9%; Average loss: 3.9431
Iteration: 195; Percent complete: 4.9%; Average loss: 4.1101
Iteration: 196; Percent complete: 4.9%; Average loss: 4.0614
Iteration: 197; Percent complete: 4.9%; Average loss: 4.2453
Iteration: 198; Percent complete: 5.0%; Average loss: 4.1002
Iteration: 199; Percent complete: 5.0%; Average loss: 4.1976
Iteration: 200; Percent complete: 5.0%; Average loss: 4.4196
Iteration: 201; Percent complete: 5.0%; Average loss: 4.0907
Iteration: 202; Percent complete: 5.1%; Average loss: 4.0073
Iteration: 203; Percent complete: 5.1%; Average loss: 4.1036
Iteration: 204; Percent complete: 5.1%; Average loss: 3.9099
Iteration: 205; Percent complete: 5.1%; Average loss: 4.0088
Iteration: 206; Percent complete: 5.1%; Average loss: 4.2245
Iteration: 207; Percent complete: 5.2%; Average loss: 3.8717
Iteration: 208; Percent complete: 5.2%; Average loss: 4.0494
Iteration: 209; Percent complete: 5.2%; Average loss: 3.7720
Iteration: 210; Percent complete: 5.2%; Average loss: 4.2903
Iteration: 211; Percent complete: 5.3%; Average loss: 4.1756
Iteration: 212; Percent complete: 5.3%; Average loss: 4.2451
Iteration: 213; Percent complete: 5.3%; Average loss: 4.0309
Iteration: 214; Percent complete: 5.3%; Average loss: 3.9616
Iteration: 215; Percent complete: 5.4%; Average loss: 3.8793
Iteration: 216; Percent complete: 5.4%; Average loss: 3.7865
Iteration: 217; Percent complete: 5.4%; Average loss: 4.1419
Iteration: 218; Percent complete: 5.5%; Average loss: 4.0573
Iteration: 219; Percent complete: 5.5%; Average loss: 4.2558
Iteration: 220; Percent complete: 5.5%; Average loss: 4.2297
Iteration: 221; Percent complete: 5.5%; Average loss: 4.2998
Iteration: 222; Percent complete: 5.5%; Average loss: 4.1966
Iteration: 223; Percent complete: 5.6%; Average loss: 4.2740
Iteration: 224; Percent complete: 5.6%; Average loss: 4.1005
Iteration: 225; Percent complete: 5.6%; Average loss: 4.0881
Iteration: 226; Percent complete: 5.7%; Average loss: 3.8530
Iteration: 227; Percent complete: 5.7%; Average loss: 3.9941
Iteration: 228; Percent complete: 5.7%; Average loss: 4.0344
Iteration: 229; Percent complete: 5.7%; Average loss: 4.1955
Iteration: 230; Percent complete: 5.8%; Average loss: 4.0155
Iteration: 231; Percent complete: 5.8%; Average loss: 4.3376
Iteration: 232; Percent complete: 5.8%; Average loss: 4.0016
Iteration: 233; Percent complete: 5.8%; Average loss: 4.0855
Iteration: 234; Percent complete: 5.9%; Average loss: 3.9696
Iteration: 235; Percent complete: 5.9%; Average loss: 4.1048
Iteration: 236; Percent complete: 5.9%; Average loss: 3.9458
Iteration: 237; Percent complete: 5.9%; Average loss: 4.1141
Iteration: 238; Percent complete: 5.9%; Average loss: 3.9269
Iteration: 239; Percent complete: 6.0%; Average loss: 4.0120
Iteration: 240; Percent complete: 6.0%; Average loss: 3.9014
Iteration: 241; Percent complete: 6.0%; Average loss: 4.2421
Iteration: 242; Percent complete: 6.0%; Average loss: 3.9933
Iteration: 243; Percent complete: 6.1%; Average loss: 4.0724
Iteration: 244; Percent complete: 6.1%; Average loss: 3.8687
Iteration: 245; Percent complete: 6.1%; Average loss: 3.7559
Iteration: 246; Percent complete: 6.2%; Average loss: 3.7654
Iteration: 247; Percent complete: 6.2%; Average loss: 4.0019
Iteration: 248; Percent complete: 6.2%; Average loss: 4.0243
Iteration: 249; Percent complete: 6.2%; Average loss: 3.8941
Iteration: 250; Percent complete: 6.2%; Average loss: 4.1526
Iteration: 251; Percent complete: 6.3%; Average loss: 4.2126
Iteration: 252; Percent complete: 6.3%; Average loss: 4.0441
Iteration: 253; Percent complete: 6.3%; Average loss: 4.1515
Iteration: 254; Percent complete: 6.3%; Average loss: 4.0912
Iteration: 255; Percent complete: 6.4%; Average loss: 4.1035
Iteration: 256; Percent complete: 6.4%; Average loss: 4.1854
Iteration: 257; Percent complete: 6.4%; Average loss: 3.9876
Iteration: 258; Percent complete: 6.5%; Average loss: 3.8694
Iteration: 259; Percent complete: 6.5%; Average loss: 4.0220
Iteration: 260; Percent complete: 6.5%; Average loss: 3.7973
Iteration: 261; Percent complete: 6.5%; Average loss: 4.1424
Iteration: 262; Percent complete: 6.6%; Average loss: 3.7746
Iteration: 263; Percent complete: 6.6%; Average loss: 3.8471
Iteration: 264; Percent complete: 6.6%; Average loss: 4.2517
Iteration: 265; Percent complete: 6.6%; Average loss: 3.8260
Iteration: 266; Percent complete: 6.7%; Average loss: 3.7984
Iteration: 267; Percent complete: 6.7%; Average loss: 3.9898
Iteration: 268; Percent complete: 6.7%; Average loss: 3.8398
Iteration: 269; Percent complete: 6.7%; Average loss: 3.9862
Iteration: 270; Percent complete: 6.8%; Average loss: 4.1090
Iteration: 271; Percent complete: 6.8%; Average loss: 4.1301
Iteration: 272; Percent complete: 6.8%; Average loss: 3.9006
Iteration: 273; Percent complete: 6.8%; Average loss: 4.0014
Iteration: 274; Percent complete: 6.9%; Average loss: 4.0018
Iteration: 275; Percent complete: 6.9%; Average loss: 3.8429
Iteration: 276; Percent complete: 6.9%; Average loss: 3.8679
Iteration: 277; Percent complete: 6.9%; Average loss: 4.0321
Iteration: 278; Percent complete: 7.0%; Average loss: 3.8535
Iteration: 279; Percent complete: 7.0%; Average loss: 4.0866
Iteration: 280; Percent complete: 7.0%; Average loss: 3.7320
Iteration: 281; Percent complete: 7.0%; Average loss: 3.9603
Iteration: 282; Percent complete: 7.0%; Average loss: 3.8745
Iteration: 283; Percent complete: 7.1%; Average loss: 3.8218
Iteration: 284; Percent complete: 7.1%; Average loss: 3.6000
Iteration: 285; Percent complete: 7.1%; Average loss: 3.8131
Iteration: 286; Percent complete: 7.1%; Average loss: 4.1985
Iteration: 287; Percent complete: 7.2%; Average loss: 3.7923
Iteration: 288; Percent complete: 7.2%; Average loss: 3.9655
Iteration: 289; Percent complete: 7.2%; Average loss: 3.7393
Iteration: 290; Percent complete: 7.2%; Average loss: 3.9306
Iteration: 291; Percent complete: 7.3%; Average loss: 3.7395
Iteration: 292; Percent complete: 7.3%; Average loss: 4.0620
Iteration: 293; Percent complete: 7.3%; Average loss: 3.7870
Iteration: 294; Percent complete: 7.3%; Average loss: 3.9996
Iteration: 295; Percent complete: 7.4%; Average loss: 3.7924
Iteration: 296; Percent complete: 7.4%; Average loss: 4.1162
Iteration: 297; Percent complete: 7.4%; Average loss: 3.8912
Iteration: 298; Percent complete: 7.4%; Average loss: 3.9222
Iteration: 299; Percent complete: 7.5%; Average loss: 3.9792
Iteration: 300; Percent complete: 7.5%; Average loss: 4.0407
Iteration: 301; Percent complete: 7.5%; Average loss: 3.9300
Iteration: 302; Percent complete: 7.5%; Average loss: 4.0981
Iteration: 303; Percent complete: 7.6%; Average loss: 3.8725
Iteration: 304; Percent complete: 7.6%; Average loss: 3.9682
Iteration: 305; Percent complete: 7.6%; Average loss: 4.1074
Iteration: 306; Percent complete: 7.6%; Average loss: 3.7981
Iteration: 307; Percent complete: 7.7%; Average loss: 3.8091
Iteration: 308; Percent complete: 7.7%; Average loss: 3.9535
Iteration: 309; Percent complete: 7.7%; Average loss: 3.8877
Iteration: 310; Percent complete: 7.8%; Average loss: 4.1132
Iteration: 311; Percent complete: 7.8%; Average loss: 4.0542
Iteration: 312; Percent complete: 7.8%; Average loss: 3.8581
Iteration: 313; Percent complete: 7.8%; Average loss: 3.9396
Iteration: 314; Percent complete: 7.8%; Average loss: 4.0255
Iteration: 315; Percent complete: 7.9%; Average loss: 3.9558
Iteration: 316; Percent complete: 7.9%; Average loss: 4.0541
Iteration: 317; Percent complete: 7.9%; Average loss: 3.9437
Iteration: 318; Percent complete: 8.0%; Average loss: 4.1534
Iteration: 319; Percent complete: 8.0%; Average loss: 3.7784
Iteration: 320; Percent complete: 8.0%; Average loss: 4.0941
Iteration: 321; Percent complete: 8.0%; Average loss: 4.0760
Iteration: 322; Percent complete: 8.1%; Average loss: 3.9337
Iteration: 323; Percent complete: 8.1%; Average loss: 4.0079
Iteration: 324; Percent complete: 8.1%; Average loss: 3.8674
Iteration: 325; Percent complete: 8.1%; Average loss: 3.9905
Iteration: 326; Percent complete: 8.2%; Average loss: 3.7140
Iteration: 327; Percent complete: 8.2%; Average loss: 3.5000
Iteration: 328; Percent complete: 8.2%; Average loss: 4.0762
Iteration: 329; Percent complete: 8.2%; Average loss: 3.9644
Iteration: 330; Percent complete: 8.2%; Average loss: 4.0178
Iteration: 331; Percent complete: 8.3%; Average loss: 3.8876
Iteration: 332; Percent complete: 8.3%; Average loss: 3.6584
Iteration: 333; Percent complete: 8.3%; Average loss: 3.6822
Iteration: 334; Percent complete: 8.3%; Average loss: 4.0070
Iteration: 335; Percent complete: 8.4%; Average loss: 4.0182
Iteration: 336; Percent complete: 8.4%; Average loss: 3.8365
Iteration: 337; Percent complete: 8.4%; Average loss: 3.6690
Iteration: 338; Percent complete: 8.5%; Average loss: 3.8371
Iteration: 339; Percent complete: 8.5%; Average loss: 4.1749
Iteration: 340; Percent complete: 8.5%; Average loss: 3.8761
Iteration: 341; Percent complete: 8.5%; Average loss: 4.0539
Iteration: 342; Percent complete: 8.6%; Average loss: 3.6812
Iteration: 343; Percent complete: 8.6%; Average loss: 3.9775
Iteration: 344; Percent complete: 8.6%; Average loss: 3.9347
Iteration: 345; Percent complete: 8.6%; Average loss: 3.7484
Iteration: 346; Percent complete: 8.6%; Average loss: 4.1441
Iteration: 347; Percent complete: 8.7%; Average loss: 3.7551
Iteration: 348; Percent complete: 8.7%; Average loss: 3.8560
Iteration: 349; Percent complete: 8.7%; Average loss: 3.8650
Iteration: 350; Percent complete: 8.8%; Average loss: 3.8124
Iteration: 351; Percent complete: 8.8%; Average loss: 3.7302
Iteration: 352; Percent complete: 8.8%; Average loss: 3.7174
Iteration: 353; Percent complete: 8.8%; Average loss: 3.9428
Iteration: 354; Percent complete: 8.8%; Average loss: 3.8179
Iteration: 355; Percent complete: 8.9%; Average loss: 3.7707
Iteration: 356; Percent complete: 8.9%; Average loss: 3.8544
Iteration: 357; Percent complete: 8.9%; Average loss: 3.9263
Iteration: 358; Percent complete: 8.9%; Average loss: 3.6431
Iteration: 359; Percent complete: 9.0%; Average loss: 3.8236
Iteration: 360; Percent complete: 9.0%; Average loss: 4.0158
Iteration: 361; Percent complete: 9.0%; Average loss: 4.0566
Iteration: 362; Percent complete: 9.0%; Average loss: 3.7364
Iteration: 363; Percent complete: 9.1%; Average loss: 3.7533
Iteration: 364; Percent complete: 9.1%; Average loss: 3.6915
Iteration: 365; Percent complete: 9.1%; Average loss: 3.6658
Iteration: 366; Percent complete: 9.2%; Average loss: 3.9975
Iteration: 367; Percent complete: 9.2%; Average loss: 3.6979
Iteration: 368; Percent complete: 9.2%; Average loss: 3.6716
Iteration: 369; Percent complete: 9.2%; Average loss: 3.7626
Iteration: 370; Percent complete: 9.2%; Average loss: 4.0177
Iteration: 371; Percent complete: 9.3%; Average loss: 3.9617
Iteration: 372; Percent complete: 9.3%; Average loss: 3.9413
Iteration: 373; Percent complete: 9.3%; Average loss: 3.7162
Iteration: 374; Percent complete: 9.3%; Average loss: 3.6078
Iteration: 375; Percent complete: 9.4%; Average loss: 3.8092
Iteration: 376; Percent complete: 9.4%; Average loss: 3.8828
Iteration: 377; Percent complete: 9.4%; Average loss: 3.8430
Iteration: 378; Percent complete: 9.4%; Average loss: 3.6886
Iteration: 379; Percent complete: 9.5%; Average loss: 3.6805
Iteration: 380; Percent complete: 9.5%; Average loss: 3.8289
Iteration: 381; Percent complete: 9.5%; Average loss: 4.0075
Iteration: 382; Percent complete: 9.6%; Average loss: 3.8599
Iteration: 383; Percent complete: 9.6%; Average loss: 3.7677
Iteration: 384; Percent complete: 9.6%; Average loss: 3.5699
Iteration: 385; Percent complete: 9.6%; Average loss: 3.8512
Iteration: 386; Percent complete: 9.7%; Average loss: 3.9712
Iteration: 387; Percent complete: 9.7%; Average loss: 3.8764
Iteration: 388; Percent complete: 9.7%; Average loss: 3.9600
Iteration: 389; Percent complete: 9.7%; Average loss: 3.6385
Iteration: 390; Percent complete: 9.8%; Average loss: 3.6580
Iteration: 391; Percent complete: 9.8%; Average loss: 3.6062
Iteration: 392; Percent complete: 9.8%; Average loss: 3.6047
Iteration: 393; Percent complete: 9.8%; Average loss: 3.9892
Iteration: 394; Percent complete: 9.8%; Average loss: 3.5876
Iteration: 395; Percent complete: 9.9%; Average loss: 3.8088
Iteration: 396; Percent complete: 9.9%; Average loss: 4.0577
Iteration: 397; Percent complete: 9.9%; Average loss: 3.7609
Iteration: 398; Percent complete: 10.0%; Average loss: 3.7888
Iteration: 399; Percent complete: 10.0%; Average loss: 4.0559
Iteration: 400; Percent complete: 10.0%; Average loss: 3.5125
Iteration: 401; Percent complete: 10.0%; Average loss: 3.7740
Iteration: 402; Percent complete: 10.1%; Average loss: 3.8201
Iteration: 403; Percent complete: 10.1%; Average loss: 3.9438
Iteration: 404; Percent complete: 10.1%; Average loss: 3.8825
Iteration: 405; Percent complete: 10.1%; Average loss: 4.0953
Iteration: 406; Percent complete: 10.2%; Average loss: 3.8853
Iteration: 407; Percent complete: 10.2%; Average loss: 3.8566
Iteration: 408; Percent complete: 10.2%; Average loss: 3.6935
Iteration: 409; Percent complete: 10.2%; Average loss: 3.9165
Iteration: 410; Percent complete: 10.2%; Average loss: 3.9742
Iteration: 411; Percent complete: 10.3%; Average loss: 3.8041
Iteration: 412; Percent complete: 10.3%; Average loss: 3.9028
Iteration: 413; Percent complete: 10.3%; Average loss: 3.9837
Iteration: 414; Percent complete: 10.3%; Average loss: 4.1293
Iteration: 415; Percent complete: 10.4%; Average loss: 3.7593
Iteration: 416; Percent complete: 10.4%; Average loss: 3.7233
Iteration: 417; Percent complete: 10.4%; Average loss: 3.5163
Iteration: 418; Percent complete: 10.4%; Average loss: 3.4863
Iteration: 419; Percent complete: 10.5%; Average loss: 3.7289
Iteration: 420; Percent complete: 10.5%; Average loss: 3.9365
Iteration: 421; Percent complete: 10.5%; Average loss: 4.0733
Iteration: 422; Percent complete: 10.5%; Average loss: 3.6051
Iteration: 423; Percent complete: 10.6%; Average loss: 3.6895
Iteration: 424; Percent complete: 10.6%; Average loss: 3.7129
Iteration: 425; Percent complete: 10.6%; Average loss: 3.9097
Iteration: 426; Percent complete: 10.7%; Average loss: 3.8554
Iteration: 427; Percent complete: 10.7%; Average loss: 3.7231
Iteration: 428; Percent complete: 10.7%; Average loss: 3.7505
Iteration: 429; Percent complete: 10.7%; Average loss: 3.8238
Iteration: 430; Percent complete: 10.8%; Average loss: 3.6398
Iteration: 431; Percent complete: 10.8%; Average loss: 4.1369
Iteration: 432; Percent complete: 10.8%; Average loss: 3.7168
Iteration: 433; Percent complete: 10.8%; Average loss: 4.0312
Iteration: 434; Percent complete: 10.8%; Average loss: 3.5766
Iteration: 435; Percent complete: 10.9%; Average loss: 3.9004
Iteration: 436; Percent complete: 10.9%; Average loss: 3.9336
Iteration: 437; Percent complete: 10.9%; Average loss: 3.4620
Iteration: 438; Percent complete: 10.9%; Average loss: 3.5905
Iteration: 439; Percent complete: 11.0%; Average loss: 3.6774
Iteration: 440; Percent complete: 11.0%; Average loss: 3.9519
Iteration: 441; Percent complete: 11.0%; Average loss: 3.5160
Iteration: 442; Percent complete: 11.1%; Average loss: 3.5762
Iteration: 443; Percent complete: 11.1%; Average loss: 3.9588
Iteration: 444; Percent complete: 11.1%; Average loss: 3.5846
Iteration: 445; Percent complete: 11.1%; Average loss: 3.8492
Iteration: 446; Percent complete: 11.2%; Average loss: 4.1510
Iteration: 447; Percent complete: 11.2%; Average loss: 3.7433
Iteration: 448; Percent complete: 11.2%; Average loss: 3.7358
Iteration: 449; Percent complete: 11.2%; Average loss: 3.8090
Iteration: 450; Percent complete: 11.2%; Average loss: 3.7246
Iteration: 451; Percent complete: 11.3%; Average loss: 3.7199
Iteration: 452; Percent complete: 11.3%; Average loss: 3.9772
Iteration: 453; Percent complete: 11.3%; Average loss: 3.5047
Iteration: 454; Percent complete: 11.3%; Average loss: 3.7228
Iteration: 455; Percent complete: 11.4%; Average loss: 4.0082
Iteration: 456; Percent complete: 11.4%; Average loss: 3.7188
Iteration: 457; Percent complete: 11.4%; Average loss: 3.5588
Iteration: 458; Percent complete: 11.5%; Average loss: 3.9903
Iteration: 459; Percent complete: 11.5%; Average loss: 3.7791
Iteration: 460; Percent complete: 11.5%; Average loss: 3.9779
Iteration: 461; Percent complete: 11.5%; Average loss: 3.9308
Iteration: 462; Percent complete: 11.6%; Average loss: 3.5943
Iteration: 463; Percent complete: 11.6%; Average loss: 3.8414
Iteration: 464; Percent complete: 11.6%; Average loss: 3.9493
Iteration: 465; Percent complete: 11.6%; Average loss: 3.8025
Iteration: 466; Percent complete: 11.7%; Average loss: 3.7804
Iteration: 467; Percent complete: 11.7%; Average loss: 3.5507
Iteration: 468; Percent complete: 11.7%; Average loss: 3.7307
Iteration: 469; Percent complete: 11.7%; Average loss: 3.7787
Iteration: 470; Percent complete: 11.8%; Average loss: 3.4986
Iteration: 471; Percent complete: 11.8%; Average loss: 4.0678
Iteration: 472; Percent complete: 11.8%; Average loss: 3.8038
Iteration: 473; Percent complete: 11.8%; Average loss: 3.7379
Iteration: 474; Percent complete: 11.8%; Average loss: 3.6463
Iteration: 475; Percent complete: 11.9%; Average loss: 4.0131
Iteration: 476; Percent complete: 11.9%; Average loss: 3.6231
Iteration: 477; Percent complete: 11.9%; Average loss: 3.8157
Iteration: 478; Percent complete: 11.9%; Average loss: 3.8522
Iteration: 479; Percent complete: 12.0%; Average loss: 3.9219
Iteration: 480; Percent complete: 12.0%; Average loss: 3.7767
Iteration: 481; Percent complete: 12.0%; Average loss: 3.9962
Iteration: 482; Percent complete: 12.0%; Average loss: 3.6501
Iteration: 483; Percent complete: 12.1%; Average loss: 3.8773
Iteration: 484; Percent complete: 12.1%; Average loss: 3.5169
Iteration: 485; Percent complete: 12.1%; Average loss: 3.8600
Iteration: 486; Percent complete: 12.2%; Average loss: 3.8165
Iteration: 487; Percent complete: 12.2%; Average loss: 3.6259
Iteration: 488; Percent complete: 12.2%; Average loss: 3.6828
Iteration: 489; Percent complete: 12.2%; Average loss: 3.6737
Iteration: 490; Percent complete: 12.2%; Average loss: 3.5316
Iteration: 491; Percent complete: 12.3%; Average loss: 3.3865
Iteration: 492; Percent complete: 12.3%; Average loss: 3.8753
Iteration: 493; Percent complete: 12.3%; Average loss: 3.7648
Iteration: 494; Percent complete: 12.3%; Average loss: 3.7006
Iteration: 495; Percent complete: 12.4%; Average loss: 3.6448
Iteration: 496; Percent complete: 12.4%; Average loss: 3.8506
Iteration: 497; Percent complete: 12.4%; Average loss: 3.6684
Iteration: 498; Percent complete: 12.4%; Average loss: 3.8890
Iteration: 499; Percent complete: 12.5%; Average loss: 3.9270
Iteration: 500; Percent complete: 12.5%; Average loss: 3.6858
Iteration: 501; Percent complete: 12.5%; Average loss: 3.8648
Iteration: 502; Percent complete: 12.6%; Average loss: 3.5656
Iteration: 503; Percent complete: 12.6%; Average loss: 3.7992
Iteration: 504; Percent complete: 12.6%; Average loss: 3.7534
Iteration: 505; Percent complete: 12.6%; Average loss: 3.7532
Iteration: 506; Percent complete: 12.7%; Average loss: 3.9354
Iteration: 507; Percent complete: 12.7%; Average loss: 4.0706
Iteration: 508; Percent complete: 12.7%; Average loss: 3.6948
Iteration: 509; Percent complete: 12.7%; Average loss: 3.6843
Iteration: 510; Percent complete: 12.8%; Average loss: 3.6640
Iteration: 511; Percent complete: 12.8%; Average loss: 3.4568
Iteration: 512; Percent complete: 12.8%; Average loss: 3.8969
Iteration: 513; Percent complete: 12.8%; Average loss: 3.8002
Iteration: 514; Percent complete: 12.8%; Average loss: 3.3593
Iteration: 515; Percent complete: 12.9%; Average loss: 3.8775
Iteration: 516; Percent complete: 12.9%; Average loss: 3.6912
Iteration: 517; Percent complete: 12.9%; Average loss: 3.8779
Iteration: 518; Percent complete: 13.0%; Average loss: 3.8942
Iteration: 519; Percent complete: 13.0%; Average loss: 3.6611
Iteration: 520; Percent complete: 13.0%; Average loss: 3.8453
Iteration: 521; Percent complete: 13.0%; Average loss: 3.5016
Iteration: 522; Percent complete: 13.1%; Average loss: 3.4140
Iteration: 523; Percent complete: 13.1%; Average loss: 3.5682
Iteration: 524; Percent complete: 13.1%; Average loss: 3.6574
Iteration: 525; Percent complete: 13.1%; Average loss: 3.7318
Iteration: 526; Percent complete: 13.2%; Average loss: 4.0695
Iteration: 527; Percent complete: 13.2%; Average loss: 3.4824
Iteration: 528; Percent complete: 13.2%; Average loss: 3.5883
Iteration: 529; Percent complete: 13.2%; Average loss: 3.8566
Iteration: 530; Percent complete: 13.2%; Average loss: 3.5933
Iteration: 531; Percent complete: 13.3%; Average loss: 3.5227
Iteration: 532; Percent complete: 13.3%; Average loss: 3.5617
Iteration: 533; Percent complete: 13.3%; Average loss: 3.8357
Iteration: 534; Percent complete: 13.4%; Average loss: 3.8391
Iteration: 535; Percent complete: 13.4%; Average loss: 3.8641
Iteration: 536; Percent complete: 13.4%; Average loss: 3.8595
Iteration: 537; Percent complete: 13.4%; Average loss: 3.7270
Iteration: 538; Percent complete: 13.5%; Average loss: 3.5266
Iteration: 539; Percent complete: 13.5%; Average loss: 3.7545
Iteration: 540; Percent complete: 13.5%; Average loss: 3.9106
Iteration: 541; Percent complete: 13.5%; Average loss: 4.0815
Iteration: 542; Percent complete: 13.6%; Average loss: 3.5456
Iteration: 543; Percent complete: 13.6%; Average loss: 3.5863
Iteration: 544; Percent complete: 13.6%; Average loss: 3.5864
Iteration: 545; Percent complete: 13.6%; Average loss: 3.5691
Iteration: 546; Percent complete: 13.7%; Average loss: 3.7764
Iteration: 547; Percent complete: 13.7%; Average loss: 3.7320
Iteration: 548; Percent complete: 13.7%; Average loss: 3.6282
Iteration: 549; Percent complete: 13.7%; Average loss: 3.5636
Iteration: 550; Percent complete: 13.8%; Average loss: 3.6372
Iteration: 551; Percent complete: 13.8%; Average loss: 3.8180
Iteration: 552; Percent complete: 13.8%; Average loss: 3.5863
Iteration: 553; Percent complete: 13.8%; Average loss: 3.5809
Iteration: 554; Percent complete: 13.9%; Average loss: 3.6575
Iteration: 555; Percent complete: 13.9%; Average loss: 4.0985
Iteration: 556; Percent complete: 13.9%; Average loss: 3.7108
Iteration: 557; Percent complete: 13.9%; Average loss: 3.6089
Iteration: 558; Percent complete: 14.0%; Average loss: 3.8163
Iteration: 559; Percent complete: 14.0%; Average loss: 3.7077
Iteration: 560; Percent complete: 14.0%; Average loss: 3.8928
Iteration: 561; Percent complete: 14.0%; Average loss: 3.6607
Iteration: 562; Percent complete: 14.1%; Average loss: 3.7288
Iteration: 563; Percent complete: 14.1%; Average loss: 3.6750
Iteration: 564; Percent complete: 14.1%; Average loss: 3.6826
Iteration: 565; Percent complete: 14.1%; Average loss: 3.6171
Iteration: 566; Percent complete: 14.1%; Average loss: 3.7392
Iteration: 567; Percent complete: 14.2%; Average loss: 3.7285
Iteration: 568; Percent complete: 14.2%; Average loss: 3.8026
Iteration: 569; Percent complete: 14.2%; Average loss: 3.2489
Iteration: 570; Percent complete: 14.2%; Average loss: 3.4433
Iteration: 571; Percent complete: 14.3%; Average loss: 3.5821
Iteration: 572; Percent complete: 14.3%; Average loss: 3.6454
Iteration: 573; Percent complete: 14.3%; Average loss: 3.4271
Iteration: 574; Percent complete: 14.3%; Average loss: 3.7525
Iteration: 575; Percent complete: 14.4%; Average loss: 3.6738
Iteration: 576; Percent complete: 14.4%; Average loss: 3.4803
Iteration: 577; Percent complete: 14.4%; Average loss: 3.7395
Iteration: 578; Percent complete: 14.4%; Average loss: 3.5804
Iteration: 579; Percent complete: 14.5%; Average loss: 3.6638
Iteration: 580; Percent complete: 14.5%; Average loss: 3.7486
Iteration: 581; Percent complete: 14.5%; Average loss: 3.5139
Iteration: 582; Percent complete: 14.5%; Average loss: 3.6896
Iteration: 583; Percent complete: 14.6%; Average loss: 3.6992
Iteration: 584; Percent complete: 14.6%; Average loss: 4.0828
Iteration: 585; Percent complete: 14.6%; Average loss: 3.7297
Iteration: 586; Percent complete: 14.6%; Average loss: 3.5422
Iteration: 587; Percent complete: 14.7%; Average loss: 3.5529
Iteration: 588; Percent complete: 14.7%; Average loss: 3.5438
Iteration: 589; Percent complete: 14.7%; Average loss: 3.9019
Iteration: 590; Percent complete: 14.8%; Average loss: 3.5927
Iteration: 591; Percent complete: 14.8%; Average loss: 3.7202
Iteration: 592; Percent complete: 14.8%; Average loss: 3.5574
Iteration: 593; Percent complete: 14.8%; Average loss: 3.6360
Iteration: 594; Percent complete: 14.8%; Average loss: 3.7163
Iteration: 595; Percent complete: 14.9%; Average loss: 3.5686
Iteration: 596; Percent complete: 14.9%; Average loss: 3.5673
Iteration: 597; Percent complete: 14.9%; Average loss: 3.5624
Iteration: 598; Percent complete: 14.9%; Average loss: 3.8295
Iteration: 599; Percent complete: 15.0%; Average loss: 3.6720
Iteration: 600; Percent complete: 15.0%; Average loss: 3.4616
Iteration: 601; Percent complete: 15.0%; Average loss: 3.5129
Iteration: 602; Percent complete: 15.0%; Average loss: 3.6423
Iteration: 603; Percent complete: 15.1%; Average loss: 3.5815
Iteration: 604; Percent complete: 15.1%; Average loss: 3.8741
Iteration: 605; Percent complete: 15.1%; Average loss: 3.8240
Iteration: 606; Percent complete: 15.2%; Average loss: 3.5439
Iteration: 607; Percent complete: 15.2%; Average loss: 3.8685
Iteration: 608; Percent complete: 15.2%; Average loss: 3.7293
Iteration: 609; Percent complete: 15.2%; Average loss: 3.9096
Iteration: 610; Percent complete: 15.2%; Average loss: 3.9120
Iteration: 611; Percent complete: 15.3%; Average loss: 3.8516
Iteration: 612; Percent complete: 15.3%; Average loss: 3.5966
Iteration: 613; Percent complete: 15.3%; Average loss: 3.8609
Iteration: 614; Percent complete: 15.3%; Average loss: 3.6721
Iteration: 615; Percent complete: 15.4%; Average loss: 3.5047
Iteration: 616; Percent complete: 15.4%; Average loss: 3.6832
Iteration: 617; Percent complete: 15.4%; Average loss: 3.4896
Iteration: 618; Percent complete: 15.4%; Average loss: 3.6379
Iteration: 619; Percent complete: 15.5%; Average loss: 3.5213
Iteration: 620; Percent complete: 15.5%; Average loss: 3.9457
Iteration: 621; Percent complete: 15.5%; Average loss: 3.6625
Iteration: 622; Percent complete: 15.6%; Average loss: 3.6678
Iteration: 623; Percent complete: 15.6%; Average loss: 3.5820
Iteration: 624; Percent complete: 15.6%; Average loss: 3.5191
Iteration: 625; Percent complete: 15.6%; Average loss: 3.4955
Iteration: 626; Percent complete: 15.7%; Average loss: 3.6388
Iteration: 627; Percent complete: 15.7%; Average loss: 3.7585
Iteration: 628; Percent complete: 15.7%; Average loss: 3.6049
Iteration: 629; Percent complete: 15.7%; Average loss: 3.6361
Iteration: 630; Percent complete: 15.8%; Average loss: 3.6595
Iteration: 631; Percent complete: 15.8%; Average loss: 3.6012
Iteration: 632; Percent complete: 15.8%; Average loss: 3.8127
Iteration: 633; Percent complete: 15.8%; Average loss: 3.4393
Iteration: 634; Percent complete: 15.8%; Average loss: 3.8249
Iteration: 635; Percent complete: 15.9%; Average loss: 3.5550
Iteration: 636; Percent complete: 15.9%; Average loss: 3.6297
Iteration: 637; Percent complete: 15.9%; Average loss: 3.7689
Iteration: 638; Percent complete: 16.0%; Average loss: 3.9896
Iteration: 639; Percent complete: 16.0%; Average loss: 3.5181
Iteration: 640; Percent complete: 16.0%; Average loss: 3.8997
Iteration: 641; Percent complete: 16.0%; Average loss: 3.2100
Iteration: 642; Percent complete: 16.1%; Average loss: 3.7425
Iteration: 643; Percent complete: 16.1%; Average loss: 3.8352
Iteration: 644; Percent complete: 16.1%; Average loss: 4.0133
Iteration: 645; Percent complete: 16.1%; Average loss: 3.7050
Iteration: 646; Percent complete: 16.2%; Average loss: 3.7413
Iteration: 647; Percent complete: 16.2%; Average loss: 3.5154
Iteration: 648; Percent complete: 16.2%; Average loss: 3.7848
Iteration: 649; Percent complete: 16.2%; Average loss: 3.6491
Iteration: 650; Percent complete: 16.2%; Average loss: 3.5545
Iteration: 651; Percent complete: 16.3%; Average loss: 3.4397
Iteration: 652; Percent complete: 16.3%; Average loss: 3.5494
Iteration: 653; Percent complete: 16.3%; Average loss: 3.6259
Iteration: 654; Percent complete: 16.4%; Average loss: 3.3234
Iteration: 655; Percent complete: 16.4%; Average loss: 3.5058
Iteration: 656; Percent complete: 16.4%; Average loss: 3.5539
Iteration: 657; Percent complete: 16.4%; Average loss: 3.4997
Iteration: 658; Percent complete: 16.4%; Average loss: 3.7334
Iteration: 659; Percent complete: 16.5%; Average loss: 3.6200
Iteration: 660; Percent complete: 16.5%; Average loss: 3.4679
Iteration: 661; Percent complete: 16.5%; Average loss: 3.7299
Iteration: 662; Percent complete: 16.6%; Average loss: 3.7611
Iteration: 663; Percent complete: 16.6%; Average loss: 3.3234
Iteration: 664; Percent complete: 16.6%; Average loss: 3.5061
Iteration: 665; Percent complete: 16.6%; Average loss: 3.7131
Iteration: 666; Percent complete: 16.7%; Average loss: 3.7012
Iteration: 667; Percent complete: 16.7%; Average loss: 3.4424
Iteration: 668; Percent complete: 16.7%; Average loss: 3.7631
Iteration: 669; Percent complete: 16.7%; Average loss: 3.3408
Iteration: 670; Percent complete: 16.8%; Average loss: 3.7692
Iteration: 671; Percent complete: 16.8%; Average loss: 3.5913
Iteration: 672; Percent complete: 16.8%; Average loss: 3.5578
Iteration: 673; Percent complete: 16.8%; Average loss: 3.8392
Iteration: 674; Percent complete: 16.9%; Average loss: 3.4686
Iteration: 675; Percent complete: 16.9%; Average loss: 3.8345
Iteration: 676; Percent complete: 16.9%; Average loss: 3.6884
Iteration: 677; Percent complete: 16.9%; Average loss: 3.4818
Iteration: 678; Percent complete: 17.0%; Average loss: 4.0692
Iteration: 679; Percent complete: 17.0%; Average loss: 3.6727
Iteration: 680; Percent complete: 17.0%; Average loss: 3.6192
Iteration: 681; Percent complete: 17.0%; Average loss: 3.6381
Iteration: 682; Percent complete: 17.1%; Average loss: 3.6611
Iteration: 683; Percent complete: 17.1%; Average loss: 3.6278
Iteration: 684; Percent complete: 17.1%; Average loss: 3.6480
Iteration: 685; Percent complete: 17.1%; Average loss: 3.4624
Iteration: 686; Percent complete: 17.2%; Average loss: 3.7633
Iteration: 687; Percent complete: 17.2%; Average loss: 3.5824
Iteration: 688; Percent complete: 17.2%; Average loss: 3.7127
Iteration: 689; Percent complete: 17.2%; Average loss: 3.8422
Iteration: 690; Percent complete: 17.2%; Average loss: 3.4120
Iteration: 691; Percent complete: 17.3%; Average loss: 3.7663
Iteration: 692; Percent complete: 17.3%; Average loss: 3.7646
Iteration: 693; Percent complete: 17.3%; Average loss: 3.3140
Iteration: 694; Percent complete: 17.3%; Average loss: 3.4518
Iteration: 695; Percent complete: 17.4%; Average loss: 3.6704
Iteration: 696; Percent complete: 17.4%; Average loss: 3.7376
Iteration: 697; Percent complete: 17.4%; Average loss: 3.5426
Iteration: 698; Percent complete: 17.4%; Average loss: 3.5937
Iteration: 699; Percent complete: 17.5%; Average loss: 3.6626
Iteration: 700; Percent complete: 17.5%; Average loss: 3.5850
Iteration: 701; Percent complete: 17.5%; Average loss: 3.4583
Iteration: 702; Percent complete: 17.5%; Average loss: 3.7103
Iteration: 703; Percent complete: 17.6%; Average loss: 3.9024
Iteration: 704; Percent complete: 17.6%; Average loss: 3.4301
Iteration: 705; Percent complete: 17.6%; Average loss: 3.7826
Iteration: 706; Percent complete: 17.6%; Average loss: 3.8148
Iteration: 707; Percent complete: 17.7%; Average loss: 3.5800
Iteration: 708; Percent complete: 17.7%; Average loss: 3.5419
Iteration: 709; Percent complete: 17.7%; Average loss: 3.7315
Iteration: 710; Percent complete: 17.8%; Average loss: 3.5885
Iteration: 711; Percent complete: 17.8%; Average loss: 3.6927
Iteration: 712; Percent complete: 17.8%; Average loss: 3.7611
Iteration: 713; Percent complete: 17.8%; Average loss: 3.8282
Iteration: 714; Percent complete: 17.8%; Average loss: 3.5244
Iteration: 715; Percent complete: 17.9%; Average loss: 3.5224
Iteration: 716; Percent complete: 17.9%; Average loss: 3.8873
Iteration: 717; Percent complete: 17.9%; Average loss: 3.4307
Iteration: 718; Percent complete: 17.9%; Average loss: 3.7715
Iteration: 719; Percent complete: 18.0%; Average loss: 3.7569
Iteration: 720; Percent complete: 18.0%; Average loss: 3.7385
Iteration: 721; Percent complete: 18.0%; Average loss: 3.4012
Iteration: 722; Percent complete: 18.1%; Average loss: 3.8215
Iteration: 723; Percent complete: 18.1%; Average loss: 3.9432
Iteration: 724; Percent complete: 18.1%; Average loss: 3.6242
Iteration: 725; Percent complete: 18.1%; Average loss: 3.7281
Iteration: 726; Percent complete: 18.1%; Average loss: 3.5294
Iteration: 727; Percent complete: 18.2%; Average loss: 3.5836
Iteration: 728; Percent complete: 18.2%; Average loss: 3.5120
Iteration: 729; Percent complete: 18.2%; Average loss: 3.8797
Iteration: 730; Percent complete: 18.2%; Average loss: 3.5411
Iteration: 731; Percent complete: 18.3%; Average loss: 3.4661
Iteration: 732; Percent complete: 18.3%; Average loss: 3.5124
Iteration: 733; Percent complete: 18.3%; Average loss: 3.5316
Iteration: 734; Percent complete: 18.4%; Average loss: 3.2739
Iteration: 735; Percent complete: 18.4%; Average loss: 3.4917
Iteration: 736; Percent complete: 18.4%; Average loss: 3.4056
Iteration: 737; Percent complete: 18.4%; Average loss: 3.8022
Iteration: 738; Percent complete: 18.4%; Average loss: 3.5341
Iteration: 739; Percent complete: 18.5%; Average loss: 3.4999
Iteration: 740; Percent complete: 18.5%; Average loss: 3.5678
Iteration: 741; Percent complete: 18.5%; Average loss: 3.4834
Iteration: 742; Percent complete: 18.6%; Average loss: 3.6431
Iteration: 743; Percent complete: 18.6%; Average loss: 3.3214
Iteration: 744; Percent complete: 18.6%; Average loss: 3.3482
Iteration: 745; Percent complete: 18.6%; Average loss: 3.7048
Iteration: 746; Percent complete: 18.6%; Average loss: 3.5157
Iteration: 747; Percent complete: 18.7%; Average loss: 3.7517
Iteration: 748; Percent complete: 18.7%; Average loss: 3.4466
Iteration: 749; Percent complete: 18.7%; Average loss: 3.5778
Iteration: 750; Percent complete: 18.8%; Average loss: 3.5279
Iteration: 751; Percent complete: 18.8%; Average loss: 3.8677
Iteration: 752; Percent complete: 18.8%; Average loss: 3.8202
Iteration: 753; Percent complete: 18.8%; Average loss: 3.7111
Iteration: 754; Percent complete: 18.9%; Average loss: 3.8228
Iteration: 755; Percent complete: 18.9%; Average loss: 3.7128
Iteration: 756; Percent complete: 18.9%; Average loss: 3.5929
Iteration: 757; Percent complete: 18.9%; Average loss: 3.6097
Iteration: 758; Percent complete: 18.9%; Average loss: 3.6956
Iteration: 759; Percent complete: 19.0%; Average loss: 3.3143
Iteration: 760; Percent complete: 19.0%; Average loss: 3.3571
Iteration: 761; Percent complete: 19.0%; Average loss: 3.4684
Iteration: 762; Percent complete: 19.1%; Average loss: 3.6087
Iteration: 763; Percent complete: 19.1%; Average loss: 3.2748
Iteration: 764; Percent complete: 19.1%; Average loss: 3.4040
Iteration: 765; Percent complete: 19.1%; Average loss: 3.5789
Iteration: 766; Percent complete: 19.1%; Average loss: 3.4251
Iteration: 767; Percent complete: 19.2%; Average loss: 3.4108
Iteration: 768; Percent complete: 19.2%; Average loss: 3.4712
Iteration: 769; Percent complete: 19.2%; Average loss: 3.5493
Iteration: 770; Percent complete: 19.2%; Average loss: 3.3467
Iteration: 771; Percent complete: 19.3%; Average loss: 3.6849
Iteration: 772; Percent complete: 19.3%; Average loss: 3.3979
Iteration: 773; Percent complete: 19.3%; Average loss: 3.5435
Iteration: 774; Percent complete: 19.4%; Average loss: 3.6303
Iteration: 775; Percent complete: 19.4%; Average loss: 3.7298
Iteration: 776; Percent complete: 19.4%; Average loss: 3.8633
Iteration: 777; Percent complete: 19.4%; Average loss: 3.1968
Iteration: 778; Percent complete: 19.4%; Average loss: 3.6722
Iteration: 779; Percent complete: 19.5%; Average loss: 3.4686
Iteration: 780; Percent complete: 19.5%; Average loss: 3.5733
Iteration: 781; Percent complete: 19.5%; Average loss: 3.4332
Iteration: 782; Percent complete: 19.6%; Average loss: 3.4074
Iteration: 783; Percent complete: 19.6%; Average loss: 3.6566
Iteration: 784; Percent complete: 19.6%; Average loss: 3.7298
Iteration: 785; Percent complete: 19.6%; Average loss: 3.5465
Iteration: 786; Percent complete: 19.7%; Average loss: 3.6077
Iteration: 787; Percent complete: 19.7%; Average loss: 3.5899
Iteration: 788; Percent complete: 19.7%; Average loss: 3.7438
Iteration: 789; Percent complete: 19.7%; Average loss: 3.7517
Iteration: 790; Percent complete: 19.8%; Average loss: 3.4139
Iteration: 791; Percent complete: 19.8%; Average loss: 3.7143
Iteration: 792; Percent complete: 19.8%; Average loss: 3.5834
Iteration: 793; Percent complete: 19.8%; Average loss: 3.7153
Iteration: 794; Percent complete: 19.9%; Average loss: 3.6179
Iteration: 795; Percent complete: 19.9%; Average loss: 3.5752
Iteration: 796; Percent complete: 19.9%; Average loss: 3.7292
Iteration: 797; Percent complete: 19.9%; Average loss: 3.5932
Iteration: 798; Percent complete: 20.0%; Average loss: 3.4287
Iteration: 799; Percent complete: 20.0%; Average loss: 3.7330
Iteration: 800; Percent complete: 20.0%; Average loss: 3.5458
Iteration: 801; Percent complete: 20.0%; Average loss: 3.2530
Iteration: 802; Percent complete: 20.1%; Average loss: 3.5857
Iteration: 803; Percent complete: 20.1%; Average loss: 3.5481
Iteration: 804; Percent complete: 20.1%; Average loss: 3.7058
Iteration: 805; Percent complete: 20.1%; Average loss: 3.4853
Iteration: 806; Percent complete: 20.2%; Average loss: 3.5554
Iteration: 807; Percent complete: 20.2%; Average loss: 3.7296
Iteration: 808; Percent complete: 20.2%; Average loss: 3.4903
Iteration: 809; Percent complete: 20.2%; Average loss: 3.5373
Iteration: 810; Percent complete: 20.2%; Average loss: 3.5337
Iteration: 811; Percent complete: 20.3%; Average loss: 3.5749
Iteration: 812; Percent complete: 20.3%; Average loss: 3.5308
Iteration: 813; Percent complete: 20.3%; Average loss: 3.7132
Iteration: 814; Percent complete: 20.3%; Average loss: 3.6978
Iteration: 815; Percent complete: 20.4%; Average loss: 3.3791
Iteration: 816; Percent complete: 20.4%; Average loss: 3.4956
Iteration: 817; Percent complete: 20.4%; Average loss: 3.4804
Iteration: 818; Percent complete: 20.4%; Average loss: 3.6038
Iteration: 819; Percent complete: 20.5%; Average loss: 3.3766
Iteration: 820; Percent complete: 20.5%; Average loss: 3.5784
Iteration: 821; Percent complete: 20.5%; Average loss: 3.5964
Iteration: 822; Percent complete: 20.5%; Average loss: 3.7050
Iteration: 823; Percent complete: 20.6%; Average loss: 3.4423
Iteration: 824; Percent complete: 20.6%; Average loss: 3.3870
Iteration: 825; Percent complete: 20.6%; Average loss: 3.7119
Iteration: 826; Percent complete: 20.6%; Average loss: 3.3961
Iteration: 827; Percent complete: 20.7%; Average loss: 3.7005
Iteration: 828; Percent complete: 20.7%; Average loss: 3.3807
Iteration: 829; Percent complete: 20.7%; Average loss: 3.4879
Iteration: 830; Percent complete: 20.8%; Average loss: 3.5211
Iteration: 831; Percent complete: 20.8%; Average loss: 3.7406
Iteration: 832; Percent complete: 20.8%; Average loss: 3.6951
Iteration: 833; Percent complete: 20.8%; Average loss: 3.1115
Iteration: 834; Percent complete: 20.8%; Average loss: 3.6501
Iteration: 835; Percent complete: 20.9%; Average loss: 3.5542
Iteration: 836; Percent complete: 20.9%; Average loss: 3.9192
Iteration: 837; Percent complete: 20.9%; Average loss: 3.4126
Iteration: 838; Percent complete: 20.9%; Average loss: 3.6271
Iteration: 839; Percent complete: 21.0%; Average loss: 3.4601
Iteration: 840; Percent complete: 21.0%; Average loss: 3.9118
Iteration: 841; Percent complete: 21.0%; Average loss: 3.4351
Iteration: 842; Percent complete: 21.1%; Average loss: 3.4319
Iteration: 843; Percent complete: 21.1%; Average loss: 3.4220
Iteration: 844; Percent complete: 21.1%; Average loss: 3.3626
Iteration: 845; Percent complete: 21.1%; Average loss: 3.5328
Iteration: 846; Percent complete: 21.1%; Average loss: 3.6536
Iteration: 847; Percent complete: 21.2%; Average loss: 3.2538
Iteration: 848; Percent complete: 21.2%; Average loss: 3.3455
Iteration: 849; Percent complete: 21.2%; Average loss: 3.3217
Iteration: 850; Percent complete: 21.2%; Average loss: 3.6183
Iteration: 851; Percent complete: 21.3%; Average loss: 3.4967
Iteration: 852; Percent complete: 21.3%; Average loss: 3.2881
Iteration: 853; Percent complete: 21.3%; Average loss: 3.4958
Iteration: 854; Percent complete: 21.3%; Average loss: 3.3984
Iteration: 855; Percent complete: 21.4%; Average loss: 3.4839
Iteration: 856; Percent complete: 21.4%; Average loss: 3.8626
Iteration: 857; Percent complete: 21.4%; Average loss: 3.2025
Iteration: 858; Percent complete: 21.4%; Average loss: 3.7635
Iteration: 859; Percent complete: 21.5%; Average loss: 3.6026
Iteration: 860; Percent complete: 21.5%; Average loss: 3.5611
Iteration: 861; Percent complete: 21.5%; Average loss: 3.4292
Iteration: 862; Percent complete: 21.6%; Average loss: 3.6004
Iteration: 863; Percent complete: 21.6%; Average loss: 3.6275
Iteration: 864; Percent complete: 21.6%; Average loss: 3.4817
Iteration: 865; Percent complete: 21.6%; Average loss: 3.5320
Iteration: 866; Percent complete: 21.6%; Average loss: 3.5217
Iteration: 867; Percent complete: 21.7%; Average loss: 3.7100
Iteration: 868; Percent complete: 21.7%; Average loss: 3.4670
Iteration: 869; Percent complete: 21.7%; Average loss: 3.8253
Iteration: 870; Percent complete: 21.8%; Average loss: 3.4951
Iteration: 871; Percent complete: 21.8%; Average loss: 3.4239
Iteration: 872; Percent complete: 21.8%; Average loss: 3.3015
Iteration: 873; Percent complete: 21.8%; Average loss: 3.4889
Iteration: 874; Percent complete: 21.9%; Average loss: 3.6395
Iteration: 875; Percent complete: 21.9%; Average loss: 3.2619
Iteration: 876; Percent complete: 21.9%; Average loss: 3.2781
Iteration: 877; Percent complete: 21.9%; Average loss: 3.6407
Iteration: 878; Percent complete: 21.9%; Average loss: 3.5084
Iteration: 879; Percent complete: 22.0%; Average loss: 3.6051
Iteration: 880; Percent complete: 22.0%; Average loss: 3.5216
Iteration: 881; Percent complete: 22.0%; Average loss: 3.4577
Iteration: 882; Percent complete: 22.1%; Average loss: 3.6322
Iteration: 883; Percent complete: 22.1%; Average loss: 3.6998
Iteration: 884; Percent complete: 22.1%; Average loss: 3.6739
Iteration: 885; Percent complete: 22.1%; Average loss: 3.5329
Iteration: 886; Percent complete: 22.1%; Average loss: 3.4409
Iteration: 887; Percent complete: 22.2%; Average loss: 3.5776
Iteration: 888; Percent complete: 22.2%; Average loss: 3.4755
Iteration: 889; Percent complete: 22.2%; Average loss: 3.4089
Iteration: 890; Percent complete: 22.2%; Average loss: 3.6271
Iteration: 891; Percent complete: 22.3%; Average loss: 3.4250
Iteration: 892; Percent complete: 22.3%; Average loss: 3.7126
Iteration: 893; Percent complete: 22.3%; Average loss: 3.3928
Iteration: 894; Percent complete: 22.4%; Average loss: 3.7690
Iteration: 895; Percent complete: 22.4%; Average loss: 3.8597
Iteration: 896; Percent complete: 22.4%; Average loss: 3.7331
Iteration: 897; Percent complete: 22.4%; Average loss: 3.6395
Iteration: 898; Percent complete: 22.4%; Average loss: 3.5832
Iteration: 899; Percent complete: 22.5%; Average loss: 3.4562
Iteration: 900; Percent complete: 22.5%; Average loss: 3.5767
Iteration: 901; Percent complete: 22.5%; Average loss: 3.4273
Iteration: 902; Percent complete: 22.6%; Average loss: 3.5107
Iteration: 903; Percent complete: 22.6%; Average loss: 3.2288
Iteration: 904; Percent complete: 22.6%; Average loss: 3.9166
Iteration: 905; Percent complete: 22.6%; Average loss: 3.8803
Iteration: 906; Percent complete: 22.7%; Average loss: 3.3036
Iteration: 907; Percent complete: 22.7%; Average loss: 3.5674
Iteration: 908; Percent complete: 22.7%; Average loss: 3.3631
Iteration: 909; Percent complete: 22.7%; Average loss: 3.4468
Iteration: 910; Percent complete: 22.8%; Average loss: 3.2338
Iteration: 911; Percent complete: 22.8%; Average loss: 3.4297
Iteration: 912; Percent complete: 22.8%; Average loss: 3.5078
Iteration: 913; Percent complete: 22.8%; Average loss: 3.5835
Iteration: 914; Percent complete: 22.9%; Average loss: 3.4219
Iteration: 915; Percent complete: 22.9%; Average loss: 3.4275
Iteration: 916; Percent complete: 22.9%; Average loss: 3.3288
Iteration: 917; Percent complete: 22.9%; Average loss: 3.5546
Iteration: 918; Percent complete: 22.9%; Average loss: 3.6703
Iteration: 919; Percent complete: 23.0%; Average loss: 3.6955
Iteration: 920; Percent complete: 23.0%; Average loss: 3.4032
Iteration: 921; Percent complete: 23.0%; Average loss: 3.5279
Iteration: 922; Percent complete: 23.1%; Average loss: 3.6403
Iteration: 923; Percent complete: 23.1%; Average loss: 3.3477
Iteration: 924; Percent complete: 23.1%; Average loss: 3.6114
Iteration: 925; Percent complete: 23.1%; Average loss: 3.3100
Iteration: 926; Percent complete: 23.2%; Average loss: 3.6581
Iteration: 927; Percent complete: 23.2%; Average loss: 3.5613
Iteration: 928; Percent complete: 23.2%; Average loss: 3.6885
Iteration: 929; Percent complete: 23.2%; Average loss: 3.5867
Iteration: 930; Percent complete: 23.2%; Average loss: 3.5415
Iteration: 931; Percent complete: 23.3%; Average loss: 3.3617
Iteration: 932; Percent complete: 23.3%; Average loss: 3.6667
Iteration: 933; Percent complete: 23.3%; Average loss: 3.2743
Iteration: 934; Percent complete: 23.4%; Average loss: 3.6447
Iteration: 935; Percent complete: 23.4%; Average loss: 3.2637
Iteration: 936; Percent complete: 23.4%; Average loss: 3.4175
Iteration: 937; Percent complete: 23.4%; Average loss: 3.5630
Iteration: 938; Percent complete: 23.4%; Average loss: 3.5465
Iteration: 939; Percent complete: 23.5%; Average loss: 3.4492
Iteration: 940; Percent complete: 23.5%; Average loss: 3.5105
Iteration: 941; Percent complete: 23.5%; Average loss: 3.6913
Iteration: 942; Percent complete: 23.5%; Average loss: 3.2652
Iteration: 943; Percent complete: 23.6%; Average loss: 3.3209
Iteration: 944; Percent complete: 23.6%; Average loss: 3.3807
Iteration: 945; Percent complete: 23.6%; Average loss: 3.4914
Iteration: 946; Percent complete: 23.6%; Average loss: 3.6288
Iteration: 947; Percent complete: 23.7%; Average loss: 3.5179
Iteration: 948; Percent complete: 23.7%; Average loss: 3.2859
Iteration: 949; Percent complete: 23.7%; Average loss: 3.6039
Iteration: 950; Percent complete: 23.8%; Average loss: 3.5433
Iteration: 951; Percent complete: 23.8%; Average loss: 3.6325
Iteration: 952; Percent complete: 23.8%; Average loss: 3.6152
Iteration: 953; Percent complete: 23.8%; Average loss: 3.3825
Iteration: 954; Percent complete: 23.8%; Average loss: 3.7854
Iteration: 955; Percent complete: 23.9%; Average loss: 3.5193
Iteration: 956; Percent complete: 23.9%; Average loss: 3.4739
Iteration: 957; Percent complete: 23.9%; Average loss: 3.6727
Iteration: 958; Percent complete: 23.9%; Average loss: 3.7514
Iteration: 959; Percent complete: 24.0%; Average loss: 3.4902
Iteration: 960; Percent complete: 24.0%; Average loss: 3.6153
Iteration: 961; Percent complete: 24.0%; Average loss: 3.4575
Iteration: 962; Percent complete: 24.1%; Average loss: 3.3103
Iteration: 963; Percent complete: 24.1%; Average loss: 3.2598
Iteration: 964; Percent complete: 24.1%; Average loss: 3.4304
Iteration: 965; Percent complete: 24.1%; Average loss: 3.6612
Iteration: 966; Percent complete: 24.1%; Average loss: 3.6446
Iteration: 967; Percent complete: 24.2%; Average loss: 3.3220
Iteration: 968; Percent complete: 24.2%; Average loss: 3.5096
Iteration: 969; Percent complete: 24.2%; Average loss: 3.5953
Iteration: 970; Percent complete: 24.2%; Average loss: 3.4911
Iteration: 971; Percent complete: 24.3%; Average loss: 3.6296
Iteration: 972; Percent complete: 24.3%; Average loss: 4.0127
Iteration: 973; Percent complete: 24.3%; Average loss: 3.5518
Iteration: 974; Percent complete: 24.3%; Average loss: 3.5101
Iteration: 975; Percent complete: 24.4%; Average loss: 3.3551
Iteration: 976; Percent complete: 24.4%; Average loss: 3.7072
Iteration: 977; Percent complete: 24.4%; Average loss: 3.4965
Iteration: 978; Percent complete: 24.4%; Average loss: 3.4301
Iteration: 979; Percent complete: 24.5%; Average loss: 3.5964
Iteration: 980; Percent complete: 24.5%; Average loss: 3.2374
Iteration: 981; Percent complete: 24.5%; Average loss: 3.5781
Iteration: 982; Percent complete: 24.6%; Average loss: 3.2656
Iteration: 983; Percent complete: 24.6%; Average loss: 3.2651
Iteration: 984; Percent complete: 24.6%; Average loss: 3.4323
Iteration: 985; Percent complete: 24.6%; Average loss: 3.4932
Iteration: 986; Percent complete: 24.6%; Average loss: 3.3543
Iteration: 987; Percent complete: 24.7%; Average loss: 3.4522
Iteration: 988; Percent complete: 24.7%; Average loss: 3.4572
Iteration: 989; Percent complete: 24.7%; Average loss: 3.3384
Iteration: 990; Percent complete: 24.8%; Average loss: 3.2737
Iteration: 991; Percent complete: 24.8%; Average loss: 3.5052
Iteration: 992; Percent complete: 24.8%; Average loss: 3.6843
Iteration: 993; Percent complete: 24.8%; Average loss: 3.5612
Iteration: 994; Percent complete: 24.9%; Average loss: 3.4009
Iteration: 995; Percent complete: 24.9%; Average loss: 3.5901
Iteration: 996; Percent complete: 24.9%; Average loss: 3.4473
Iteration: 997; Percent complete: 24.9%; Average loss: 3.5092
Iteration: 998; Percent complete: 24.9%; Average loss: 3.3160
Iteration: 999; Percent complete: 25.0%; Average loss: 3.5034
Iteration: 1000; Percent complete: 25.0%; Average loss: 3.3872
Iteration: 1001; Percent complete: 25.0%; Average loss: 3.6176
Iteration: 1002; Percent complete: 25.1%; Average loss: 3.5074
Iteration: 1003; Percent complete: 25.1%; Average loss: 3.3478
Iteration: 1004; Percent complete: 25.1%; Average loss: 3.4539
Iteration: 1005; Percent complete: 25.1%; Average loss: 3.3821
Iteration: 1006; Percent complete: 25.1%; Average loss: 3.2286
Iteration: 1007; Percent complete: 25.2%; Average loss: 3.4137
Iteration: 1008; Percent complete: 25.2%; Average loss: 3.3979
Iteration: 1009; Percent complete: 25.2%; Average loss: 3.3097
Iteration: 1010; Percent complete: 25.2%; Average loss: 3.4907
Iteration: 1011; Percent complete: 25.3%; Average loss: 3.4213
Iteration: 1012; Percent complete: 25.3%; Average loss: 3.3849
Iteration: 1013; Percent complete: 25.3%; Average loss: 3.8333
Iteration: 1014; Percent complete: 25.4%; Average loss: 3.5824
Iteration: 1015; Percent complete: 25.4%; Average loss: 3.5555
Iteration: 1016; Percent complete: 25.4%; Average loss: 3.4677
Iteration: 1017; Percent complete: 25.4%; Average loss: 3.4047
Iteration: 1018; Percent complete: 25.4%; Average loss: 3.5361
Iteration: 1019; Percent complete: 25.5%; Average loss: 3.3935
Iteration: 1020; Percent complete: 25.5%; Average loss: 3.4130
Iteration: 1021; Percent complete: 25.5%; Average loss: 3.4416
Iteration: 1022; Percent complete: 25.6%; Average loss: 3.2832
Iteration: 1023; Percent complete: 25.6%; Average loss: 3.6428
Iteration: 1024; Percent complete: 25.6%; Average loss: 3.4738
Iteration: 1025; Percent complete: 25.6%; Average loss: 3.5749
Iteration: 1026; Percent complete: 25.7%; Average loss: 3.4997
Iteration: 1027; Percent complete: 25.7%; Average loss: 3.6424
Iteration: 1028; Percent complete: 25.7%; Average loss: 3.4578
Iteration: 1029; Percent complete: 25.7%; Average loss: 3.4320
Iteration: 1030; Percent complete: 25.8%; Average loss: 3.7541
Iteration: 1031; Percent complete: 25.8%; Average loss: 3.7178
Iteration: 1032; Percent complete: 25.8%; Average loss: 3.3377
Iteration: 1033; Percent complete: 25.8%; Average loss: 3.3766
Iteration: 1034; Percent complete: 25.9%; Average loss: 3.5205
Iteration: 1035; Percent complete: 25.9%; Average loss: 3.1723
Iteration: 1036; Percent complete: 25.9%; Average loss: 3.6877
Iteration: 1037; Percent complete: 25.9%; Average loss: 3.2361
Iteration: 1038; Percent complete: 25.9%; Average loss: 3.6354
Iteration: 1039; Percent complete: 26.0%; Average loss: 3.3773
Iteration: 1040; Percent complete: 26.0%; Average loss: 3.4551
Iteration: 1041; Percent complete: 26.0%; Average loss: 3.5552
Iteration: 1042; Percent complete: 26.1%; Average loss: 3.4467
Iteration: 1043; Percent complete: 26.1%; Average loss: 3.5802
Iteration: 1044; Percent complete: 26.1%; Average loss: 3.4186
Iteration: 1045; Percent complete: 26.1%; Average loss: 3.7280
Iteration: 1046; Percent complete: 26.2%; Average loss: 3.6026
Iteration: 1047; Percent complete: 26.2%; Average loss: 3.5541
Iteration: 1048; Percent complete: 26.2%; Average loss: 3.4015
Iteration: 1049; Percent complete: 26.2%; Average loss: 3.5285
Iteration: 1050; Percent complete: 26.2%; Average loss: 3.7783
Iteration: 1051; Percent complete: 26.3%; Average loss: 3.5026
Iteration: 1052; Percent complete: 26.3%; Average loss: 3.5360
Iteration: 1053; Percent complete: 26.3%; Average loss: 3.3916
Iteration: 1054; Percent complete: 26.4%; Average loss: 3.6447
Iteration: 1055; Percent complete: 26.4%; Average loss: 3.4521
Iteration: 1056; Percent complete: 26.4%; Average loss: 3.4877
Iteration: 1057; Percent complete: 26.4%; Average loss: 3.5799
Iteration: 1058; Percent complete: 26.5%; Average loss: 3.4133
Iteration: 1059; Percent complete: 26.5%; Average loss: 3.5374
Iteration: 1060; Percent complete: 26.5%; Average loss: 3.4139
Iteration: 1061; Percent complete: 26.5%; Average loss: 3.7061
Iteration: 1062; Percent complete: 26.6%; Average loss: 3.5155
Iteration: 1063; Percent complete: 26.6%; Average loss: 3.5238
Iteration: 1064; Percent complete: 26.6%; Average loss: 3.4775
Iteration: 1065; Percent complete: 26.6%; Average loss: 3.4264
Iteration: 1066; Percent complete: 26.7%; Average loss: 3.3041
Iteration: 1067; Percent complete: 26.7%; Average loss: 3.3806
Iteration: 1068; Percent complete: 26.7%; Average loss: 3.6134
Iteration: 1069; Percent complete: 26.7%; Average loss: 3.4955
Iteration: 1070; Percent complete: 26.8%; Average loss: 3.4523
Iteration: 1071; Percent complete: 26.8%; Average loss: 3.6726
Iteration: 1072; Percent complete: 26.8%; Average loss: 3.2785
Iteration: 1073; Percent complete: 26.8%; Average loss: 3.5983
Iteration: 1074; Percent complete: 26.9%; Average loss: 3.4765
Iteration: 1075; Percent complete: 26.9%; Average loss: 3.4971
Iteration: 1076; Percent complete: 26.9%; Average loss: 3.4343
Iteration: 1077; Percent complete: 26.9%; Average loss: 3.3858
Iteration: 1078; Percent complete: 27.0%; Average loss: 3.4173
Iteration: 1079; Percent complete: 27.0%; Average loss: 3.4688
Iteration: 1080; Percent complete: 27.0%; Average loss: 3.5690
Iteration: 1081; Percent complete: 27.0%; Average loss: 3.8801
Iteration: 1082; Percent complete: 27.1%; Average loss: 3.4976
Iteration: 1083; Percent complete: 27.1%; Average loss: 3.5161
Iteration: 1084; Percent complete: 27.1%; Average loss: 3.6758
Iteration: 1085; Percent complete: 27.1%; Average loss: 3.5067
Iteration: 1086; Percent complete: 27.2%; Average loss: 3.5535
Iteration: 1087; Percent complete: 27.2%; Average loss: 3.4354
Iteration: 1088; Percent complete: 27.2%; Average loss: 3.4590
Iteration: 1089; Percent complete: 27.2%; Average loss: 3.2690
Iteration: 1090; Percent complete: 27.3%; Average loss: 3.3485
Iteration: 1091; Percent complete: 27.3%; Average loss: 3.2184
Iteration: 1092; Percent complete: 27.3%; Average loss: 3.3553
Iteration: 1093; Percent complete: 27.3%; Average loss: 3.1230
Iteration: 1094; Percent complete: 27.4%; Average loss: 3.3368
Iteration: 1095; Percent complete: 27.4%; Average loss: 3.4659
Iteration: 1096; Percent complete: 27.4%; Average loss: 3.3517
Iteration: 1097; Percent complete: 27.4%; Average loss: 3.7139
Iteration: 1098; Percent complete: 27.5%; Average loss: 3.5193
Iteration: 1099; Percent complete: 27.5%; Average loss: 3.4673
Iteration: 1100; Percent complete: 27.5%; Average loss: 3.5255
Iteration: 1101; Percent complete: 27.5%; Average loss: 3.2527
Iteration: 1102; Percent complete: 27.6%; Average loss: 3.2564
Iteration: 1103; Percent complete: 27.6%; Average loss: 3.4082
Iteration: 1104; Percent complete: 27.6%; Average loss: 3.5351
Iteration: 1105; Percent complete: 27.6%; Average loss: 3.5676
Iteration: 1106; Percent complete: 27.7%; Average loss: 3.5821
Iteration: 1107; Percent complete: 27.7%; Average loss: 3.2084
Iteration: 1108; Percent complete: 27.7%; Average loss: 3.5376
Iteration: 1109; Percent complete: 27.7%; Average loss: 3.3753
Iteration: 1110; Percent complete: 27.8%; Average loss: 3.3031
Iteration: 1111; Percent complete: 27.8%; Average loss: 3.5694
Iteration: 1112; Percent complete: 27.8%; Average loss: 3.4473
Iteration: 1113; Percent complete: 27.8%; Average loss: 3.5750
Iteration: 1114; Percent complete: 27.9%; Average loss: 3.3851
Iteration: 1115; Percent complete: 27.9%; Average loss: 3.3841
Iteration: 1116; Percent complete: 27.9%; Average loss: 3.4771
Iteration: 1117; Percent complete: 27.9%; Average loss: 3.3554
Iteration: 1118; Percent complete: 28.0%; Average loss: 3.4253
Iteration: 1119; Percent complete: 28.0%; Average loss: 3.4388
Iteration: 1120; Percent complete: 28.0%; Average loss: 3.6465
Iteration: 1121; Percent complete: 28.0%; Average loss: 3.4528
Iteration: 1122; Percent complete: 28.1%; Average loss: 3.5638
Iteration: 1123; Percent complete: 28.1%; Average loss: 3.2631
Iteration: 1124; Percent complete: 28.1%; Average loss: 3.8819
Iteration: 1125; Percent complete: 28.1%; Average loss: 3.3133
Iteration: 1126; Percent complete: 28.1%; Average loss: 3.4335
Iteration: 1127; Percent complete: 28.2%; Average loss: 3.1958
Iteration: 1128; Percent complete: 28.2%; Average loss: 3.5565
Iteration: 1129; Percent complete: 28.2%; Average loss: 3.2165
Iteration: 1130; Percent complete: 28.2%; Average loss: 3.2032
Iteration: 1131; Percent complete: 28.3%; Average loss: 3.3435
Iteration: 1132; Percent complete: 28.3%; Average loss: 3.7164
Iteration: 1133; Percent complete: 28.3%; Average loss: 3.6865
Iteration: 1134; Percent complete: 28.3%; Average loss: 3.6347
Iteration: 1135; Percent complete: 28.4%; Average loss: 3.3842
Iteration: 1136; Percent complete: 28.4%; Average loss: 3.3085
Iteration: 1137; Percent complete: 28.4%; Average loss: 3.3746
Iteration: 1138; Percent complete: 28.4%; Average loss: 3.2507
Iteration: 1139; Percent complete: 28.5%; Average loss: 3.4352
Iteration: 1140; Percent complete: 28.5%; Average loss: 3.3706
Iteration: 1141; Percent complete: 28.5%; Average loss: 3.3028
Iteration: 1142; Percent complete: 28.5%; Average loss: 3.3652
Iteration: 1143; Percent complete: 28.6%; Average loss: 3.2473
Iteration: 1144; Percent complete: 28.6%; Average loss: 3.4581
Iteration: 1145; Percent complete: 28.6%; Average loss: 3.5149
Iteration: 1146; Percent complete: 28.6%; Average loss: 3.2174
Iteration: 1147; Percent complete: 28.7%; Average loss: 3.3500
Iteration: 1148; Percent complete: 28.7%; Average loss: 3.6042
Iteration: 1149; Percent complete: 28.7%; Average loss: 3.5810
Iteration: 1150; Percent complete: 28.7%; Average loss: 3.4844
Iteration: 1151; Percent complete: 28.8%; Average loss: 3.3319
Iteration: 1152; Percent complete: 28.8%; Average loss: 3.2157
Iteration: 1153; Percent complete: 28.8%; Average loss: 3.1543
Iteration: 1154; Percent complete: 28.8%; Average loss: 3.6244
Iteration: 1155; Percent complete: 28.9%; Average loss: 3.4746
Iteration: 1156; Percent complete: 28.9%; Average loss: 3.6319
Iteration: 1157; Percent complete: 28.9%; Average loss: 3.2532
Iteration: 1158; Percent complete: 28.9%; Average loss: 3.1981
Iteration: 1159; Percent complete: 29.0%; Average loss: 3.3384
Iteration: 1160; Percent complete: 29.0%; Average loss: 3.5070
Iteration: 1161; Percent complete: 29.0%; Average loss: 3.3525
Iteration: 1162; Percent complete: 29.0%; Average loss: 3.3268
Iteration: 1163; Percent complete: 29.1%; Average loss: 3.4437
Iteration: 1164; Percent complete: 29.1%; Average loss: 3.4911
Iteration: 1165; Percent complete: 29.1%; Average loss: 3.2905
Iteration: 1166; Percent complete: 29.1%; Average loss: 3.1727
Iteration: 1167; Percent complete: 29.2%; Average loss: 3.4324
Iteration: 1168; Percent complete: 29.2%; Average loss: 3.4718
Iteration: 1169; Percent complete: 29.2%; Average loss: 3.5908
Iteration: 1170; Percent complete: 29.2%; Average loss: 3.3928
Iteration: 1171; Percent complete: 29.3%; Average loss: 3.4880
Iteration: 1172; Percent complete: 29.3%; Average loss: 3.3918
Iteration: 1173; Percent complete: 29.3%; Average loss: 3.4306
Iteration: 1174; Percent complete: 29.3%; Average loss: 3.4301
Iteration: 1175; Percent complete: 29.4%; Average loss: 3.1713
Iteration: 1176; Percent complete: 29.4%; Average loss: 3.4263
Iteration: 1177; Percent complete: 29.4%; Average loss: 3.3537
Iteration: 1178; Percent complete: 29.4%; Average loss: 3.2603
Iteration: 1179; Percent complete: 29.5%; Average loss: 3.4674
Iteration: 1180; Percent complete: 29.5%; Average loss: 3.1925
Iteration: 1181; Percent complete: 29.5%; Average loss: 3.3597
Iteration: 1182; Percent complete: 29.5%; Average loss: 3.4981
Iteration: 1183; Percent complete: 29.6%; Average loss: 3.3948
Iteration: 1184; Percent complete: 29.6%; Average loss: 3.4291
Iteration: 1185; Percent complete: 29.6%; Average loss: 3.2670
Iteration: 1186; Percent complete: 29.6%; Average loss: 3.4312
Iteration: 1187; Percent complete: 29.7%; Average loss: 3.4100
Iteration: 1188; Percent complete: 29.7%; Average loss: 3.2473
Iteration: 1189; Percent complete: 29.7%; Average loss: 3.5041
Iteration: 1190; Percent complete: 29.8%; Average loss: 3.4077
Iteration: 1191; Percent complete: 29.8%; Average loss: 3.2063
Iteration: 1192; Percent complete: 29.8%; Average loss: 3.3387
Iteration: 1193; Percent complete: 29.8%; Average loss: 3.3183
Iteration: 1194; Percent complete: 29.8%; Average loss: 3.1464
Iteration: 1195; Percent complete: 29.9%; Average loss: 3.3611
Iteration: 1196; Percent complete: 29.9%; Average loss: 3.5375
Iteration: 1197; Percent complete: 29.9%; Average loss: 3.1752
Iteration: 1198; Percent complete: 29.9%; Average loss: 3.4015
Iteration: 1199; Percent complete: 30.0%; Average loss: 3.3806
Iteration: 1200; Percent complete: 30.0%; Average loss: 3.4059
Iteration: 1201; Percent complete: 30.0%; Average loss: 3.4659
Iteration: 1202; Percent complete: 30.0%; Average loss: 3.3599
Iteration: 1203; Percent complete: 30.1%; Average loss: 3.3622
Iteration: 1204; Percent complete: 30.1%; Average loss: 3.2808
Iteration: 1205; Percent complete: 30.1%; Average loss: 3.2623
Iteration: 1206; Percent complete: 30.1%; Average loss: 3.5497
Iteration: 1207; Percent complete: 30.2%; Average loss: 3.6933
Iteration: 1208; Percent complete: 30.2%; Average loss: 3.5621
Iteration: 1209; Percent complete: 30.2%; Average loss: 3.7496
Iteration: 1210; Percent complete: 30.2%; Average loss: 3.4447
Iteration: 1211; Percent complete: 30.3%; Average loss: 3.2669
Iteration: 1212; Percent complete: 30.3%; Average loss: 3.3443
Iteration: 1213; Percent complete: 30.3%; Average loss: 3.4784
Iteration: 1214; Percent complete: 30.3%; Average loss: 3.3964
Iteration: 1215; Percent complete: 30.4%; Average loss: 3.3447
Iteration: 1216; Percent complete: 30.4%; Average loss: 3.5195
Iteration: 1217; Percent complete: 30.4%; Average loss: 3.6938
Iteration: 1218; Percent complete: 30.4%; Average loss: 3.3778
Iteration: 1219; Percent complete: 30.5%; Average loss: 3.2625
Iteration: 1220; Percent complete: 30.5%; Average loss: 3.4875
Iteration: 1221; Percent complete: 30.5%; Average loss: 3.6505
Iteration: 1222; Percent complete: 30.6%; Average loss: 3.3422
Iteration: 1223; Percent complete: 30.6%; Average loss: 3.2015
Iteration: 1224; Percent complete: 30.6%; Average loss: 3.2870
Iteration: 1225; Percent complete: 30.6%; Average loss: 3.6464
Iteration: 1226; Percent complete: 30.6%; Average loss: 3.2888
Iteration: 1227; Percent complete: 30.7%; Average loss: 3.4714
Iteration: 1228; Percent complete: 30.7%; Average loss: 3.2517
Iteration: 1229; Percent complete: 30.7%; Average loss: 3.4616
Iteration: 1230; Percent complete: 30.8%; Average loss: 3.6769
Iteration: 1231; Percent complete: 30.8%; Average loss: 3.1743
Iteration: 1232; Percent complete: 30.8%; Average loss: 3.2648
Iteration: 1233; Percent complete: 30.8%; Average loss: 3.4319
Iteration: 1234; Percent complete: 30.9%; Average loss: 3.1460
Iteration: 1235; Percent complete: 30.9%; Average loss: 3.3409
Iteration: 1236; Percent complete: 30.9%; Average loss: 3.0774
Iteration: 1237; Percent complete: 30.9%; Average loss: 3.3175
Iteration: 1238; Percent complete: 30.9%; Average loss: 3.2406
Iteration: 1239; Percent complete: 31.0%; Average loss: 3.6997
Iteration: 1240; Percent complete: 31.0%; Average loss: 3.1899
Iteration: 1241; Percent complete: 31.0%; Average loss: 3.3777
Iteration: 1242; Percent complete: 31.1%; Average loss: 3.1286
Iteration: 1243; Percent complete: 31.1%; Average loss: 3.2859
Iteration: 1244; Percent complete: 31.1%; Average loss: 3.8868
Iteration: 1245; Percent complete: 31.1%; Average loss: 3.3260
Iteration: 1246; Percent complete: 31.1%; Average loss: 3.4629
Iteration: 1247; Percent complete: 31.2%; Average loss: 3.3334
Iteration: 1248; Percent complete: 31.2%; Average loss: 3.3436
Iteration: 1249; Percent complete: 31.2%; Average loss: 3.6649
Iteration: 1250; Percent complete: 31.2%; Average loss: 3.2950
Iteration: 1251; Percent complete: 31.3%; Average loss: 3.2887
Iteration: 1252; Percent complete: 31.3%; Average loss: 3.2451
Iteration: 1253; Percent complete: 31.3%; Average loss: 3.3062
Iteration: 1254; Percent complete: 31.4%; Average loss: 3.3957
Iteration: 1255; Percent complete: 31.4%; Average loss: 3.2114
Iteration: 1256; Percent complete: 31.4%; Average loss: 3.1895
Iteration: 1257; Percent complete: 31.4%; Average loss: 3.2282
Iteration: 1258; Percent complete: 31.4%; Average loss: 3.3502
Iteration: 1259; Percent complete: 31.5%; Average loss: 3.2188
Iteration: 1260; Percent complete: 31.5%; Average loss: 3.3059
Iteration: 1261; Percent complete: 31.5%; Average loss: 3.5433
Iteration: 1262; Percent complete: 31.6%; Average loss: 3.5313
Iteration: 1263; Percent complete: 31.6%; Average loss: 3.1341
Iteration: 1264; Percent complete: 31.6%; Average loss: 3.2920
Iteration: 1265; Percent complete: 31.6%; Average loss: 3.3438
Iteration: 1266; Percent complete: 31.6%; Average loss: 3.5913
Iteration: 1267; Percent complete: 31.7%; Average loss: 3.5953
Iteration: 1268; Percent complete: 31.7%; Average loss: 3.3783
Iteration: 1269; Percent complete: 31.7%; Average loss: 3.4235
Iteration: 1270; Percent complete: 31.8%; Average loss: 3.2385
Iteration: 1271; Percent complete: 31.8%; Average loss: 3.5379
Iteration: 1272; Percent complete: 31.8%; Average loss: 3.4946
Iteration: 1273; Percent complete: 31.8%; Average loss: 3.3337
Iteration: 1274; Percent complete: 31.9%; Average loss: 3.3789
Iteration: 1275; Percent complete: 31.9%; Average loss: 3.4174
Iteration: 1276; Percent complete: 31.9%; Average loss: 3.6621
Iteration: 1277; Percent complete: 31.9%; Average loss: 3.2177
Iteration: 1278; Percent complete: 31.9%; Average loss: 3.3591
Iteration: 1279; Percent complete: 32.0%; Average loss: 3.3155
Iteration: 1280; Percent complete: 32.0%; Average loss: 3.4312
Iteration: 1281; Percent complete: 32.0%; Average loss: 3.4504
Iteration: 1282; Percent complete: 32.0%; Average loss: 3.2221
Iteration: 1283; Percent complete: 32.1%; Average loss: 3.4875
Iteration: 1284; Percent complete: 32.1%; Average loss: 3.5767
Iteration: 1285; Percent complete: 32.1%; Average loss: 3.1730
Iteration: 1286; Percent complete: 32.1%; Average loss: 3.3286
Iteration: 1287; Percent complete: 32.2%; Average loss: 3.3728
Iteration: 1288; Percent complete: 32.2%; Average loss: 3.4238
Iteration: 1289; Percent complete: 32.2%; Average loss: 3.4899
Iteration: 1290; Percent complete: 32.2%; Average loss: 3.5883
Iteration: 1291; Percent complete: 32.3%; Average loss: 3.5726
Iteration: 1292; Percent complete: 32.3%; Average loss: 3.4723
Iteration: 1293; Percent complete: 32.3%; Average loss: 3.3609
Iteration: 1294; Percent complete: 32.4%; Average loss: 3.3521
Iteration: 1295; Percent complete: 32.4%; Average loss: 3.1982
Iteration: 1296; Percent complete: 32.4%; Average loss: 3.3127
Iteration: 1297; Percent complete: 32.4%; Average loss: 3.6624
Iteration: 1298; Percent complete: 32.5%; Average loss: 3.2705
Iteration: 1299; Percent complete: 32.5%; Average loss: 3.3721
Iteration: 1300; Percent complete: 32.5%; Average loss: 3.3773
Iteration: 1301; Percent complete: 32.5%; Average loss: 3.4046
Iteration: 1302; Percent complete: 32.6%; Average loss: 3.3400
Iteration: 1303; Percent complete: 32.6%; Average loss: 3.3976
Iteration: 1304; Percent complete: 32.6%; Average loss: 3.4205
Iteration: 1305; Percent complete: 32.6%; Average loss: 3.3147
Iteration: 1306; Percent complete: 32.6%; Average loss: 3.2262
Iteration: 1307; Percent complete: 32.7%; Average loss: 3.3857
Iteration: 1308; Percent complete: 32.7%; Average loss: 3.4247
Iteration: 1309; Percent complete: 32.7%; Average loss: 3.1991
Iteration: 1310; Percent complete: 32.8%; Average loss: 3.3080
Iteration: 1311; Percent complete: 32.8%; Average loss: 3.1998
Iteration: 1312; Percent complete: 32.8%; Average loss: 3.4287
Iteration: 1313; Percent complete: 32.8%; Average loss: 3.4507
Iteration: 1314; Percent complete: 32.9%; Average loss: 3.4074
Iteration: 1315; Percent complete: 32.9%; Average loss: 3.2346
Iteration: 1316; Percent complete: 32.9%; Average loss: 3.3921
Iteration: 1317; Percent complete: 32.9%; Average loss: 3.3555
Iteration: 1318; Percent complete: 33.0%; Average loss: 3.2813
Iteration: 1319; Percent complete: 33.0%; Average loss: 3.2896
Iteration: 1320; Percent complete: 33.0%; Average loss: 3.7127
Iteration: 1321; Percent complete: 33.0%; Average loss: 3.3317
Iteration: 1322; Percent complete: 33.1%; Average loss: 3.6062
Iteration: 1323; Percent complete: 33.1%; Average loss: 3.1908
Iteration: 1324; Percent complete: 33.1%; Average loss: 3.4946
Iteration: 1325; Percent complete: 33.1%; Average loss: 3.3032
Iteration: 1326; Percent complete: 33.1%; Average loss: 3.2391
Iteration: 1327; Percent complete: 33.2%; Average loss: 3.4793
Iteration: 1328; Percent complete: 33.2%; Average loss: 3.3446
Iteration: 1329; Percent complete: 33.2%; Average loss: 3.3201
Iteration: 1330; Percent complete: 33.2%; Average loss: 3.7476
Iteration: 1331; Percent complete: 33.3%; Average loss: 3.1935
Iteration: 1332; Percent complete: 33.3%; Average loss: 3.4310
Iteration: 1333; Percent complete: 33.3%; Average loss: 3.5357
Iteration: 1334; Percent complete: 33.4%; Average loss: 3.2525
Iteration: 1335; Percent complete: 33.4%; Average loss: 3.1851
Iteration: 1336; Percent complete: 33.4%; Average loss: 3.0682
Iteration: 1337; Percent complete: 33.4%; Average loss: 3.2425
Iteration: 1338; Percent complete: 33.5%; Average loss: 3.3473
Iteration: 1339; Percent complete: 33.5%; Average loss: 3.2215
Iteration: 1340; Percent complete: 33.5%; Average loss: 3.2414
Iteration: 1341; Percent complete: 33.5%; Average loss: 3.4469
Iteration: 1342; Percent complete: 33.6%; Average loss: 3.1616
Iteration: 1343; Percent complete: 33.6%; Average loss: 3.2215
Iteration: 1344; Percent complete: 33.6%; Average loss: 3.1797
Iteration: 1345; Percent complete: 33.6%; Average loss: 3.4437
Iteration: 1346; Percent complete: 33.7%; Average loss: 3.4797
Iteration: 1347; Percent complete: 33.7%; Average loss: 3.5285
Iteration: 1348; Percent complete: 33.7%; Average loss: 3.1984
Iteration: 1349; Percent complete: 33.7%; Average loss: 3.4634
Iteration: 1350; Percent complete: 33.8%; Average loss: 3.1656
Iteration: 1351; Percent complete: 33.8%; Average loss: 3.4325
Iteration: 1352; Percent complete: 33.8%; Average loss: 3.3377
Iteration: 1353; Percent complete: 33.8%; Average loss: 3.4801
Iteration: 1354; Percent complete: 33.9%; Average loss: 3.4763
Iteration: 1355; Percent complete: 33.9%; Average loss: 3.5643
Iteration: 1356; Percent complete: 33.9%; Average loss: 3.5974
Iteration: 1357; Percent complete: 33.9%; Average loss: 3.3708
Iteration: 1358; Percent complete: 34.0%; Average loss: 3.5323
Iteration: 1359; Percent complete: 34.0%; Average loss: 3.4760
Iteration: 1360; Percent complete: 34.0%; Average loss: 3.0330
Iteration: 1361; Percent complete: 34.0%; Average loss: 3.3250
Iteration: 1362; Percent complete: 34.1%; Average loss: 3.3141
Iteration: 1363; Percent complete: 34.1%; Average loss: 3.3765
Iteration: 1364; Percent complete: 34.1%; Average loss: 3.6455
Iteration: 1365; Percent complete: 34.1%; Average loss: 3.4159
Iteration: 1366; Percent complete: 34.2%; Average loss: 3.4527
Iteration: 1367; Percent complete: 34.2%; Average loss: 3.3012
Iteration: 1368; Percent complete: 34.2%; Average loss: 3.2147
Iteration: 1369; Percent complete: 34.2%; Average loss: 3.2953
Iteration: 1370; Percent complete: 34.2%; Average loss: 3.1443
Iteration: 1371; Percent complete: 34.3%; Average loss: 3.2039
Iteration: 1372; Percent complete: 34.3%; Average loss: 3.3058
Iteration: 1373; Percent complete: 34.3%; Average loss: 3.1765
Iteration: 1374; Percent complete: 34.4%; Average loss: 3.1203
Iteration: 1375; Percent complete: 34.4%; Average loss: 3.3940
Iteration: 1376; Percent complete: 34.4%; Average loss: 3.3342
Iteration: 1377; Percent complete: 34.4%; Average loss: 3.7103
Iteration: 1378; Percent complete: 34.4%; Average loss: 3.2093
Iteration: 1379; Percent complete: 34.5%; Average loss: 3.3510
Iteration: 1380; Percent complete: 34.5%; Average loss: 3.3386
Iteration: 1381; Percent complete: 34.5%; Average loss: 3.5393
Iteration: 1382; Percent complete: 34.5%; Average loss: 3.3137
Iteration: 1383; Percent complete: 34.6%; Average loss: 3.2978
Iteration: 1384; Percent complete: 34.6%; Average loss: 3.1925
Iteration: 1385; Percent complete: 34.6%; Average loss: 3.4860
Iteration: 1386; Percent complete: 34.6%; Average loss: 3.1457
Iteration: 1387; Percent complete: 34.7%; Average loss: 3.4422
Iteration: 1388; Percent complete: 34.7%; Average loss: 3.5036
Iteration: 1389; Percent complete: 34.7%; Average loss: 3.5444
Iteration: 1390; Percent complete: 34.8%; Average loss: 3.2687
Iteration: 1391; Percent complete: 34.8%; Average loss: 3.3285
Iteration: 1392; Percent complete: 34.8%; Average loss: 3.2000
Iteration: 1393; Percent complete: 34.8%; Average loss: 3.1737
Iteration: 1394; Percent complete: 34.8%; Average loss: 3.2509
Iteration: 1395; Percent complete: 34.9%; Average loss: 3.4366
Iteration: 1396; Percent complete: 34.9%; Average loss: 3.3680
Iteration: 1397; Percent complete: 34.9%; Average loss: 3.2837
Iteration: 1398; Percent complete: 34.9%; Average loss: 3.1826
Iteration: 1399; Percent complete: 35.0%; Average loss: 3.2043
Iteration: 1400; Percent complete: 35.0%; Average loss: 3.2738
Iteration: 1401; Percent complete: 35.0%; Average loss: 3.4842
Iteration: 1402; Percent complete: 35.0%; Average loss: 3.5221
Iteration: 1403; Percent complete: 35.1%; Average loss: 3.5402
Iteration: 1404; Percent complete: 35.1%; Average loss: 3.2239
Iteration: 1405; Percent complete: 35.1%; Average loss: 3.3735
Iteration: 1406; Percent complete: 35.1%; Average loss: 3.3155
Iteration: 1407; Percent complete: 35.2%; Average loss: 3.2428
Iteration: 1408; Percent complete: 35.2%; Average loss: 3.3451
Iteration: 1409; Percent complete: 35.2%; Average loss: 3.3496
Iteration: 1410; Percent complete: 35.2%; Average loss: 3.4052
Iteration: 1411; Percent complete: 35.3%; Average loss: 3.1069
Iteration: 1412; Percent complete: 35.3%; Average loss: 3.6331
Iteration: 1413; Percent complete: 35.3%; Average loss: 3.3631
Iteration: 1414; Percent complete: 35.4%; Average loss: 3.3216
Iteration: 1415; Percent complete: 35.4%; Average loss: 3.3869
Iteration: 1416; Percent complete: 35.4%; Average loss: 3.3637
Iteration: 1417; Percent complete: 35.4%; Average loss: 3.1567
Iteration: 1418; Percent complete: 35.4%; Average loss: 3.5345
Iteration: 1419; Percent complete: 35.5%; Average loss: 3.2925
Iteration: 1420; Percent complete: 35.5%; Average loss: 3.1524
Iteration: 1421; Percent complete: 35.5%; Average loss: 3.3058
Iteration: 1422; Percent complete: 35.5%; Average loss: 3.4017
Iteration: 1423; Percent complete: 35.6%; Average loss: 3.3100
Iteration: 1424; Percent complete: 35.6%; Average loss: 3.5436
Iteration: 1425; Percent complete: 35.6%; Average loss: 3.4219
Iteration: 1426; Percent complete: 35.6%; Average loss: 3.2691
Iteration: 1427; Percent complete: 35.7%; Average loss: 3.0077
Iteration: 1428; Percent complete: 35.7%; Average loss: 3.2422
Iteration: 1429; Percent complete: 35.7%; Average loss: 3.3453
Iteration: 1430; Percent complete: 35.8%; Average loss: 3.4065
Iteration: 1431; Percent complete: 35.8%; Average loss: 3.2871
Iteration: 1432; Percent complete: 35.8%; Average loss: 3.3113
Iteration: 1433; Percent complete: 35.8%; Average loss: 3.5550
Iteration: 1434; Percent complete: 35.9%; Average loss: 3.1870
Iteration: 1435; Percent complete: 35.9%; Average loss: 3.3221
Iteration: 1436; Percent complete: 35.9%; Average loss: 3.2881
Iteration: 1437; Percent complete: 35.9%; Average loss: 3.2394
Iteration: 1438; Percent complete: 35.9%; Average loss: 3.6978
Iteration: 1439; Percent complete: 36.0%; Average loss: 3.1782
Iteration: 1440; Percent complete: 36.0%; Average loss: 3.1991
Iteration: 1441; Percent complete: 36.0%; Average loss: 3.3800
Iteration: 1442; Percent complete: 36.0%; Average loss: 3.3493
Iteration: 1443; Percent complete: 36.1%; Average loss: 3.1407
Iteration: 1444; Percent complete: 36.1%; Average loss: 3.0884
Iteration: 1445; Percent complete: 36.1%; Average loss: 3.4826
Iteration: 1446; Percent complete: 36.1%; Average loss: 3.3941
Iteration: 1447; Percent complete: 36.2%; Average loss: 3.4228
Iteration: 1448; Percent complete: 36.2%; Average loss: 3.3336
Iteration: 1449; Percent complete: 36.2%; Average loss: 3.3328
Iteration: 1450; Percent complete: 36.2%; Average loss: 3.2691
Iteration: 1451; Percent complete: 36.3%; Average loss: 3.3716
Iteration: 1452; Percent complete: 36.3%; Average loss: 3.3959
Iteration: 1453; Percent complete: 36.3%; Average loss: 3.1884
Iteration: 1454; Percent complete: 36.4%; Average loss: 3.6490
Iteration: 1455; Percent complete: 36.4%; Average loss: 3.1956
Iteration: 1456; Percent complete: 36.4%; Average loss: 3.1968
Iteration: 1457; Percent complete: 36.4%; Average loss: 3.2392
Iteration: 1458; Percent complete: 36.4%; Average loss: 3.1922
Iteration: 1459; Percent complete: 36.5%; Average loss: 3.1299
Iteration: 1460; Percent complete: 36.5%; Average loss: 3.3977
Iteration: 1461; Percent complete: 36.5%; Average loss: 3.4176
Iteration: 1462; Percent complete: 36.5%; Average loss: 3.4699
Iteration: 1463; Percent complete: 36.6%; Average loss: 3.4276
Iteration: 1464; Percent complete: 36.6%; Average loss: 3.3380
Iteration: 1465; Percent complete: 36.6%; Average loss: 3.1718
Iteration: 1466; Percent complete: 36.6%; Average loss: 3.3861
Iteration: 1467; Percent complete: 36.7%; Average loss: 3.1235
Iteration: 1468; Percent complete: 36.7%; Average loss: 3.3179
Iteration: 1469; Percent complete: 36.7%; Average loss: 2.9812
Iteration: 1470; Percent complete: 36.8%; Average loss: 3.4358
Iteration: 1471; Percent complete: 36.8%; Average loss: 3.3423
Iteration: 1472; Percent complete: 36.8%; Average loss: 3.2552
Iteration: 1473; Percent complete: 36.8%; Average loss: 2.9940
Iteration: 1474; Percent complete: 36.9%; Average loss: 3.0954
Iteration: 1475; Percent complete: 36.9%; Average loss: 3.1989
Iteration: 1476; Percent complete: 36.9%; Average loss: 3.3628
Iteration: 1477; Percent complete: 36.9%; Average loss: 3.2993
Iteration: 1478; Percent complete: 37.0%; Average loss: 3.4484
Iteration: 1479; Percent complete: 37.0%; Average loss: 3.2298
Iteration: 1480; Percent complete: 37.0%; Average loss: 2.9960
Iteration: 1481; Percent complete: 37.0%; Average loss: 3.3468
Iteration: 1482; Percent complete: 37.0%; Average loss: 3.2415
Iteration: 1483; Percent complete: 37.1%; Average loss: 3.3592
Iteration: 1484; Percent complete: 37.1%; Average loss: 3.5061
Iteration: 1485; Percent complete: 37.1%; Average loss: 3.5000
Iteration: 1486; Percent complete: 37.1%; Average loss: 3.1012
Iteration: 1487; Percent complete: 37.2%; Average loss: 3.3880
Iteration: 1488; Percent complete: 37.2%; Average loss: 3.3581
Iteration: 1489; Percent complete: 37.2%; Average loss: 3.4152
Iteration: 1490; Percent complete: 37.2%; Average loss: 3.2516
Iteration: 1491; Percent complete: 37.3%; Average loss: 3.1909
Iteration: 1492; Percent complete: 37.3%; Average loss: 3.2895
Iteration: 1493; Percent complete: 37.3%; Average loss: 3.2459
Iteration: 1494; Percent complete: 37.4%; Average loss: 3.3874
Iteration: 1495; Percent complete: 37.4%; Average loss: 3.4317
Iteration: 1496; Percent complete: 37.4%; Average loss: 3.4450
Iteration: 1497; Percent complete: 37.4%; Average loss: 3.3801
Iteration: 1498; Percent complete: 37.5%; Average loss: 3.4150
Iteration: 1499; Percent complete: 37.5%; Average loss: 3.3883
Iteration: 1500; Percent complete: 37.5%; Average loss: 3.2960
Iteration: 1501; Percent complete: 37.5%; Average loss: 3.1358
Iteration: 1502; Percent complete: 37.5%; Average loss: 3.2916
Iteration: 1503; Percent complete: 37.6%; Average loss: 3.2488
Iteration: 1504; Percent complete: 37.6%; Average loss: 3.4729
Iteration: 1505; Percent complete: 37.6%; Average loss: 3.3460
Iteration: 1506; Percent complete: 37.6%; Average loss: 3.2957
Iteration: 1507; Percent complete: 37.7%; Average loss: 3.3839
Iteration: 1508; Percent complete: 37.7%; Average loss: 3.3932
Iteration: 1509; Percent complete: 37.7%; Average loss: 3.3352
Iteration: 1510; Percent complete: 37.8%; Average loss: 3.1525
Iteration: 1511; Percent complete: 37.8%; Average loss: 3.2951
Iteration: 1512; Percent complete: 37.8%; Average loss: 3.5240
Iteration: 1513; Percent complete: 37.8%; Average loss: 3.2628
Iteration: 1514; Percent complete: 37.9%; Average loss: 3.3240
Iteration: 1515; Percent complete: 37.9%; Average loss: 3.3871
Iteration: 1516; Percent complete: 37.9%; Average loss: 3.4254
Iteration: 1517; Percent complete: 37.9%; Average loss: 3.1982
Iteration: 1518; Percent complete: 38.0%; Average loss: 3.1493
Iteration: 1519; Percent complete: 38.0%; Average loss: 3.3732
Iteration: 1520; Percent complete: 38.0%; Average loss: 3.3931
Iteration: 1521; Percent complete: 38.0%; Average loss: 3.2644
Iteration: 1522; Percent complete: 38.0%; Average loss: 3.0833
Iteration: 1523; Percent complete: 38.1%; Average loss: 3.2689
Iteration: 1524; Percent complete: 38.1%; Average loss: 3.0632
Iteration: 1525; Percent complete: 38.1%; Average loss: 3.1977
Iteration: 1526; Percent complete: 38.1%; Average loss: 3.2688
Iteration: 1527; Percent complete: 38.2%; Average loss: 3.2850
Iteration: 1528; Percent complete: 38.2%; Average loss: 3.4724
Iteration: 1529; Percent complete: 38.2%; Average loss: 3.3380
Iteration: 1530; Percent complete: 38.2%; Average loss: 3.3280
Iteration: 1531; Percent complete: 38.3%; Average loss: 3.0307
Iteration: 1532; Percent complete: 38.3%; Average loss: 3.3462
Iteration: 1533; Percent complete: 38.3%; Average loss: 3.2358
Iteration: 1534; Percent complete: 38.4%; Average loss: 2.9710
Iteration: 1535; Percent complete: 38.4%; Average loss: 3.3268
Iteration: 1536; Percent complete: 38.4%; Average loss: 3.3278
Iteration: 1537; Percent complete: 38.4%; Average loss: 3.4775
Iteration: 1538; Percent complete: 38.5%; Average loss: 3.5306
Iteration: 1539; Percent complete: 38.5%; Average loss: 3.3473
Iteration: 1540; Percent complete: 38.5%; Average loss: 3.3447
Iteration: 1541; Percent complete: 38.5%; Average loss: 3.4531
Iteration: 1542; Percent complete: 38.6%; Average loss: 3.4024
Iteration: 1543; Percent complete: 38.6%; Average loss: 3.2982
Iteration: 1544; Percent complete: 38.6%; Average loss: 3.3788
Iteration: 1545; Percent complete: 38.6%; Average loss: 3.0544
Iteration: 1546; Percent complete: 38.6%; Average loss: 2.9499
Iteration: 1547; Percent complete: 38.7%; Average loss: 3.1385
Iteration: 1548; Percent complete: 38.7%; Average loss: 3.4021
Iteration: 1549; Percent complete: 38.7%; Average loss: 3.5271
Iteration: 1550; Percent complete: 38.8%; Average loss: 3.1626
Iteration: 1551; Percent complete: 38.8%; Average loss: 3.2277
Iteration: 1552; Percent complete: 38.8%; Average loss: 3.2281
Iteration: 1553; Percent complete: 38.8%; Average loss: 3.1274
Iteration: 1554; Percent complete: 38.9%; Average loss: 3.3091
Iteration: 1555; Percent complete: 38.9%; Average loss: 3.0497
Iteration: 1556; Percent complete: 38.9%; Average loss: 3.2795
Iteration: 1557; Percent complete: 38.9%; Average loss: 3.6284
Iteration: 1558; Percent complete: 39.0%; Average loss: 3.1701
Iteration: 1559; Percent complete: 39.0%; Average loss: 3.4908
Iteration: 1560; Percent complete: 39.0%; Average loss: 3.4878
Iteration: 1561; Percent complete: 39.0%; Average loss: 3.2522
Iteration: 1562; Percent complete: 39.1%; Average loss: 3.3409
Iteration: 1563; Percent complete: 39.1%; Average loss: 3.1154
Iteration: 1564; Percent complete: 39.1%; Average loss: 3.2254
Iteration: 1565; Percent complete: 39.1%; Average loss: 3.2950
Iteration: 1566; Percent complete: 39.1%; Average loss: 3.2004
Iteration: 1567; Percent complete: 39.2%; Average loss: 3.3896
Iteration: 1568; Percent complete: 39.2%; Average loss: 3.3454
Iteration: 1569; Percent complete: 39.2%; Average loss: 3.2043
Iteration: 1570; Percent complete: 39.2%; Average loss: 3.2335
Iteration: 1571; Percent complete: 39.3%; Average loss: 3.2136
Iteration: 1572; Percent complete: 39.3%; Average loss: 3.1157
Iteration: 1573; Percent complete: 39.3%; Average loss: 3.4886
Iteration: 1574; Percent complete: 39.4%; Average loss: 3.5173
Iteration: 1575; Percent complete: 39.4%; Average loss: 3.1949
Iteration: 1576; Percent complete: 39.4%; Average loss: 3.3321
Iteration: 1577; Percent complete: 39.4%; Average loss: 3.4113
Iteration: 1578; Percent complete: 39.5%; Average loss: 3.2322
Iteration: 1579; Percent complete: 39.5%; Average loss: 3.2941
Iteration: 1580; Percent complete: 39.5%; Average loss: 3.1955
Iteration: 1581; Percent complete: 39.5%; Average loss: 3.4320
Iteration: 1582; Percent complete: 39.6%; Average loss: 3.1923
Iteration: 1583; Percent complete: 39.6%; Average loss: 3.2718
Iteration: 1584; Percent complete: 39.6%; Average loss: 3.2890
Iteration: 1585; Percent complete: 39.6%; Average loss: 3.3876
Iteration: 1586; Percent complete: 39.6%; Average loss: 3.3318
Iteration: 1587; Percent complete: 39.7%; Average loss: 3.3816
Iteration: 1588; Percent complete: 39.7%; Average loss: 3.1954
Iteration: 1589; Percent complete: 39.7%; Average loss: 3.4320
Iteration: 1590; Percent complete: 39.8%; Average loss: 3.4359
Iteration: 1591; Percent complete: 39.8%; Average loss: 3.3321
Iteration: 1592; Percent complete: 39.8%; Average loss: 3.3661
Iteration: 1593; Percent complete: 39.8%; Average loss: 3.2224
Iteration: 1594; Percent complete: 39.9%; Average loss: 3.3155
Iteration: 1595; Percent complete: 39.9%; Average loss: 3.2290
Iteration: 1596; Percent complete: 39.9%; Average loss: 3.1562
Iteration: 1597; Percent complete: 39.9%; Average loss: 2.9548
Iteration: 1598; Percent complete: 40.0%; Average loss: 3.0294
Iteration: 1599; Percent complete: 40.0%; Average loss: 3.2381
Iteration: 1600; Percent complete: 40.0%; Average loss: 3.2935
Iteration: 1601; Percent complete: 40.0%; Average loss: 3.4866
Iteration: 1602; Percent complete: 40.1%; Average loss: 3.2064
Iteration: 1603; Percent complete: 40.1%; Average loss: 3.3309
Iteration: 1604; Percent complete: 40.1%; Average loss: 3.1827
Iteration: 1605; Percent complete: 40.1%; Average loss: 3.4053
Iteration: 1606; Percent complete: 40.2%; Average loss: 3.3345
Iteration: 1607; Percent complete: 40.2%; Average loss: 2.9923
Iteration: 1608; Percent complete: 40.2%; Average loss: 2.9953
Iteration: 1609; Percent complete: 40.2%; Average loss: 3.4158
Iteration: 1610; Percent complete: 40.2%; Average loss: 3.3237
Iteration: 1611; Percent complete: 40.3%; Average loss: 3.0402
Iteration: 1612; Percent complete: 40.3%; Average loss: 3.2249
Iteration: 1613; Percent complete: 40.3%; Average loss: 3.0592
Iteration: 1614; Percent complete: 40.4%; Average loss: 3.1454
Iteration: 1615; Percent complete: 40.4%; Average loss: 3.2312
Iteration: 1616; Percent complete: 40.4%; Average loss: 3.6180
Iteration: 1617; Percent complete: 40.4%; Average loss: 3.3030
Iteration: 1618; Percent complete: 40.5%; Average loss: 3.1753
Iteration: 1619; Percent complete: 40.5%; Average loss: 3.1131
Iteration: 1620; Percent complete: 40.5%; Average loss: 3.2807
Iteration: 1621; Percent complete: 40.5%; Average loss: 3.3777
Iteration: 1622; Percent complete: 40.6%; Average loss: 3.3314
Iteration: 1623; Percent complete: 40.6%; Average loss: 3.1773
Iteration: 1624; Percent complete: 40.6%; Average loss: 3.3144
Iteration: 1625; Percent complete: 40.6%; Average loss: 3.3859
Iteration: 1626; Percent complete: 40.6%; Average loss: 3.3579
Iteration: 1627; Percent complete: 40.7%; Average loss: 3.2489
Iteration: 1628; Percent complete: 40.7%; Average loss: 3.0818
Iteration: 1629; Percent complete: 40.7%; Average loss: 3.3471
Iteration: 1630; Percent complete: 40.8%; Average loss: 3.2208
Iteration: 1631; Percent complete: 40.8%; Average loss: 3.1339
Iteration: 1632; Percent complete: 40.8%; Average loss: 3.1815
Iteration: 1633; Percent complete: 40.8%; Average loss: 3.4320
Iteration: 1634; Percent complete: 40.8%; Average loss: 3.3056
Iteration: 1635; Percent complete: 40.9%; Average loss: 2.9481
Iteration: 1636; Percent complete: 40.9%; Average loss: 3.0510
Iteration: 1637; Percent complete: 40.9%; Average loss: 3.3004
Iteration: 1638; Percent complete: 40.9%; Average loss: 3.3078
Iteration: 1639; Percent complete: 41.0%; Average loss: 3.1029
Iteration: 1640; Percent complete: 41.0%; Average loss: 2.9498
Iteration: 1641; Percent complete: 41.0%; Average loss: 3.1169
Iteration: 1642; Percent complete: 41.0%; Average loss: 3.2134
Iteration: 1643; Percent complete: 41.1%; Average loss: 3.3596
Iteration: 1644; Percent complete: 41.1%; Average loss: 3.1523
Iteration: 1645; Percent complete: 41.1%; Average loss: 3.3887
Iteration: 1646; Percent complete: 41.1%; Average loss: 3.2006
Iteration: 1647; Percent complete: 41.2%; Average loss: 3.1073
Iteration: 1648; Percent complete: 41.2%; Average loss: 3.0432
Iteration: 1649; Percent complete: 41.2%; Average loss: 3.3127
Iteration: 1650; Percent complete: 41.2%; Average loss: 3.5233
Iteration: 1651; Percent complete: 41.3%; Average loss: 3.2294
Iteration: 1652; Percent complete: 41.3%; Average loss: 3.4409
Iteration: 1653; Percent complete: 41.3%; Average loss: 3.1956
Iteration: 1654; Percent complete: 41.3%; Average loss: 3.2224
Iteration: 1655; Percent complete: 41.4%; Average loss: 3.2168
Iteration: 1656; Percent complete: 41.4%; Average loss: 3.3445
Iteration: 1657; Percent complete: 41.4%; Average loss: 3.2004
Iteration: 1658; Percent complete: 41.4%; Average loss: 3.0321
Iteration: 1659; Percent complete: 41.5%; Average loss: 3.4523
Iteration: 1660; Percent complete: 41.5%; Average loss: 3.0721
Iteration: 1661; Percent complete: 41.5%; Average loss: 3.2148
Iteration: 1662; Percent complete: 41.5%; Average loss: 3.3994
Iteration: 1663; Percent complete: 41.6%; Average loss: 3.3921
Iteration: 1664; Percent complete: 41.6%; Average loss: 3.1090
Iteration: 1665; Percent complete: 41.6%; Average loss: 3.1138
Iteration: 1666; Percent complete: 41.6%; Average loss: 3.2349
Iteration: 1667; Percent complete: 41.7%; Average loss: 3.4068
Iteration: 1668; Percent complete: 41.7%; Average loss: 3.4325
Iteration: 1669; Percent complete: 41.7%; Average loss: 3.2966
Iteration: 1670; Percent complete: 41.8%; Average loss: 3.4177
Iteration: 1671; Percent complete: 41.8%; Average loss: 3.0980
Iteration: 1672; Percent complete: 41.8%; Average loss: 3.0882
Iteration: 1673; Percent complete: 41.8%; Average loss: 3.1185
Iteration: 1674; Percent complete: 41.9%; Average loss: 3.2177
Iteration: 1675; Percent complete: 41.9%; Average loss: 3.1361
Iteration: 1676; Percent complete: 41.9%; Average loss: 3.3482
Iteration: 1677; Percent complete: 41.9%; Average loss: 3.0652
Iteration: 1678; Percent complete: 41.9%; Average loss: 3.3642
Iteration: 1679; Percent complete: 42.0%; Average loss: 3.2794
Iteration: 1680; Percent complete: 42.0%; Average loss: 3.2389
Iteration: 1681; Percent complete: 42.0%; Average loss: 3.5020
Iteration: 1682; Percent complete: 42.0%; Average loss: 3.3340
Iteration: 1683; Percent complete: 42.1%; Average loss: 3.1171
Iteration: 1684; Percent complete: 42.1%; Average loss: 3.2265
Iteration: 1685; Percent complete: 42.1%; Average loss: 3.2580
Iteration: 1686; Percent complete: 42.1%; Average loss: 3.0468
Iteration: 1687; Percent complete: 42.2%; Average loss: 3.3552
Iteration: 1688; Percent complete: 42.2%; Average loss: 3.1134
Iteration: 1689; Percent complete: 42.2%; Average loss: 3.3999
Iteration: 1690; Percent complete: 42.2%; Average loss: 3.4420
Iteration: 1691; Percent complete: 42.3%; Average loss: 3.1306
Iteration: 1692; Percent complete: 42.3%; Average loss: 3.1264
Iteration: 1693; Percent complete: 42.3%; Average loss: 3.0586
Iteration: 1694; Percent complete: 42.4%; Average loss: 3.1567
Iteration: 1695; Percent complete: 42.4%; Average loss: 3.4474
Iteration: 1696; Percent complete: 42.4%; Average loss: 3.2387
Iteration: 1697; Percent complete: 42.4%; Average loss: 3.2473
Iteration: 1698; Percent complete: 42.4%; Average loss: 3.5169
Iteration: 1699; Percent complete: 42.5%; Average loss: 3.2564
Iteration: 1700; Percent complete: 42.5%; Average loss: 3.0983
Iteration: 1701; Percent complete: 42.5%; Average loss: 3.4025
Iteration: 1702; Percent complete: 42.5%; Average loss: 3.1845
Iteration: 1703; Percent complete: 42.6%; Average loss: 3.0976
Iteration: 1704; Percent complete: 42.6%; Average loss: 3.0156
Iteration: 1705; Percent complete: 42.6%; Average loss: 3.5147
Iteration: 1706; Percent complete: 42.6%; Average loss: 3.1562
Iteration: 1707; Percent complete: 42.7%; Average loss: 3.2660
Iteration: 1708; Percent complete: 42.7%; Average loss: 3.2311
Iteration: 1709; Percent complete: 42.7%; Average loss: 3.2027
Iteration: 1710; Percent complete: 42.8%; Average loss: 3.0445
Iteration: 1711; Percent complete: 42.8%; Average loss: 3.2716
Iteration: 1712; Percent complete: 42.8%; Average loss: 3.2747
Iteration: 1713; Percent complete: 42.8%; Average loss: 3.3243
Iteration: 1714; Percent complete: 42.9%; Average loss: 3.2487
Iteration: 1715; Percent complete: 42.9%; Average loss: 3.3440
Iteration: 1716; Percent complete: 42.9%; Average loss: 3.1619
Iteration: 1717; Percent complete: 42.9%; Average loss: 3.4700
Iteration: 1718; Percent complete: 43.0%; Average loss: 3.1694
Iteration: 1719; Percent complete: 43.0%; Average loss: 3.3859
Iteration: 1720; Percent complete: 43.0%; Average loss: 2.9034
Iteration: 1721; Percent complete: 43.0%; Average loss: 3.1182
Iteration: 1722; Percent complete: 43.0%; Average loss: 3.2064
Iteration: 1723; Percent complete: 43.1%; Average loss: 3.4968
Iteration: 1724; Percent complete: 43.1%; Average loss: 3.4280
Iteration: 1725; Percent complete: 43.1%; Average loss: 3.1182
Iteration: 1726; Percent complete: 43.1%; Average loss: 3.1568
Iteration: 1727; Percent complete: 43.2%; Average loss: 3.3230
Iteration: 1728; Percent complete: 43.2%; Average loss: 3.3245
Iteration: 1729; Percent complete: 43.2%; Average loss: 3.3262
Iteration: 1730; Percent complete: 43.2%; Average loss: 3.3640
Iteration: 1731; Percent complete: 43.3%; Average loss: 3.3996
Iteration: 1732; Percent complete: 43.3%; Average loss: 3.2747
Iteration: 1733; Percent complete: 43.3%; Average loss: 3.0275
Iteration: 1734; Percent complete: 43.4%; Average loss: 3.1759
Iteration: 1735; Percent complete: 43.4%; Average loss: 2.9218
Iteration: 1736; Percent complete: 43.4%; Average loss: 3.2900
Iteration: 1737; Percent complete: 43.4%; Average loss: 3.3163
Iteration: 1738; Percent complete: 43.5%; Average loss: 3.2556
Iteration: 1739; Percent complete: 43.5%; Average loss: 3.1289
Iteration: 1740; Percent complete: 43.5%; Average loss: 3.1343
Iteration: 1741; Percent complete: 43.5%; Average loss: 3.3478
Iteration: 1742; Percent complete: 43.5%; Average loss: 2.7951
Iteration: 1743; Percent complete: 43.6%; Average loss: 3.0688
Iteration: 1744; Percent complete: 43.6%; Average loss: 3.2403
Iteration: 1745; Percent complete: 43.6%; Average loss: 3.5066
Iteration: 1746; Percent complete: 43.6%; Average loss: 3.2515
Iteration: 1747; Percent complete: 43.7%; Average loss: 3.4171
Iteration: 1748; Percent complete: 43.7%; Average loss: 3.1015
Iteration: 1749; Percent complete: 43.7%; Average loss: 3.2261
Iteration: 1750; Percent complete: 43.8%; Average loss: 3.0061
Iteration: 1751; Percent complete: 43.8%; Average loss: 3.0864
Iteration: 1752; Percent complete: 43.8%; Average loss: 3.1282
Iteration: 1753; Percent complete: 43.8%; Average loss: 3.2391
Iteration: 1754; Percent complete: 43.9%; Average loss: 3.2598
Iteration: 1755; Percent complete: 43.9%; Average loss: 3.1961
Iteration: 1756; Percent complete: 43.9%; Average loss: 3.1890
Iteration: 1757; Percent complete: 43.9%; Average loss: 3.2172
Iteration: 1758; Percent complete: 44.0%; Average loss: 3.0639
Iteration: 1759; Percent complete: 44.0%; Average loss: 3.2656
Iteration: 1760; Percent complete: 44.0%; Average loss: 3.1703
Iteration: 1761; Percent complete: 44.0%; Average loss: 3.1944
Iteration: 1762; Percent complete: 44.0%; Average loss: 3.1518
Iteration: 1763; Percent complete: 44.1%; Average loss: 3.0405
Iteration: 1764; Percent complete: 44.1%; Average loss: 3.1080
Iteration: 1765; Percent complete: 44.1%; Average loss: 2.9570
Iteration: 1766; Percent complete: 44.1%; Average loss: 3.4100
Iteration: 1767; Percent complete: 44.2%; Average loss: 3.0806
Iteration: 1768; Percent complete: 44.2%; Average loss: 3.4196
Iteration: 1769; Percent complete: 44.2%; Average loss: 3.1831
Iteration: 1770; Percent complete: 44.2%; Average loss: 3.0352
Iteration: 1771; Percent complete: 44.3%; Average loss: 3.1750
Iteration: 1772; Percent complete: 44.3%; Average loss: 3.3299
Iteration: 1773; Percent complete: 44.3%; Average loss: 3.2406
Iteration: 1774; Percent complete: 44.4%; Average loss: 3.2103
Iteration: 1775; Percent complete: 44.4%; Average loss: 3.3501
Iteration: 1776; Percent complete: 44.4%; Average loss: 3.4641
Iteration: 1777; Percent complete: 44.4%; Average loss: 3.2959
Iteration: 1778; Percent complete: 44.5%; Average loss: 3.1953
Iteration: 1779; Percent complete: 44.5%; Average loss: 3.2167
Iteration: 1780; Percent complete: 44.5%; Average loss: 3.2068
Iteration: 1781; Percent complete: 44.5%; Average loss: 3.2112
Iteration: 1782; Percent complete: 44.5%; Average loss: 3.5708
Iteration: 1783; Percent complete: 44.6%; Average loss: 3.6170
Iteration: 1784; Percent complete: 44.6%; Average loss: 3.3594
Iteration: 1785; Percent complete: 44.6%; Average loss: 3.4277
Iteration: 1786; Percent complete: 44.6%; Average loss: 3.2827
Iteration: 1787; Percent complete: 44.7%; Average loss: 2.9224
Iteration: 1788; Percent complete: 44.7%; Average loss: 3.1505
Iteration: 1789; Percent complete: 44.7%; Average loss: 3.0895
Iteration: 1790; Percent complete: 44.8%; Average loss: 3.1225
Iteration: 1791; Percent complete: 44.8%; Average loss: 3.1822
Iteration: 1792; Percent complete: 44.8%; Average loss: 3.5800
Iteration: 1793; Percent complete: 44.8%; Average loss: 3.2678
Iteration: 1794; Percent complete: 44.9%; Average loss: 3.3244
Iteration: 1795; Percent complete: 44.9%; Average loss: 3.4952
Iteration: 1796; Percent complete: 44.9%; Average loss: 3.1467
Iteration: 1797; Percent complete: 44.9%; Average loss: 3.2730
Iteration: 1798; Percent complete: 45.0%; Average loss: 3.2031
Iteration: 1799; Percent complete: 45.0%; Average loss: 3.1842
Iteration: 1800; Percent complete: 45.0%; Average loss: 3.1218
Iteration: 1801; Percent complete: 45.0%; Average loss: 3.1473
Iteration: 1802; Percent complete: 45.1%; Average loss: 3.4249
Iteration: 1803; Percent complete: 45.1%; Average loss: 3.0603
Iteration: 1804; Percent complete: 45.1%; Average loss: 3.1634
Iteration: 1805; Percent complete: 45.1%; Average loss: 3.2061
Iteration: 1806; Percent complete: 45.1%; Average loss: 3.2054
Iteration: 1807; Percent complete: 45.2%; Average loss: 3.4791
Iteration: 1808; Percent complete: 45.2%; Average loss: 3.1937
Iteration: 1809; Percent complete: 45.2%; Average loss: 3.5026
Iteration: 1810; Percent complete: 45.2%; Average loss: 3.1966
Iteration: 1811; Percent complete: 45.3%; Average loss: 3.0074
Iteration: 1812; Percent complete: 45.3%; Average loss: 3.2076
Iteration: 1813; Percent complete: 45.3%; Average loss: 3.4527
Iteration: 1814; Percent complete: 45.4%; Average loss: 3.0772
Iteration: 1815; Percent complete: 45.4%; Average loss: 3.1365
Iteration: 1816; Percent complete: 45.4%; Average loss: 3.1656
Iteration: 1817; Percent complete: 45.4%; Average loss: 3.4658
Iteration: 1818; Percent complete: 45.5%; Average loss: 3.3335
Iteration: 1819; Percent complete: 45.5%; Average loss: 3.1462
Iteration: 1820; Percent complete: 45.5%; Average loss: 2.9132
Iteration: 1821; Percent complete: 45.5%; Average loss: 2.9583
Iteration: 1822; Percent complete: 45.6%; Average loss: 3.0623
Iteration: 1823; Percent complete: 45.6%; Average loss: 3.2294
Iteration: 1824; Percent complete: 45.6%; Average loss: 3.0353
Iteration: 1825; Percent complete: 45.6%; Average loss: 3.3204
Iteration: 1826; Percent complete: 45.6%; Average loss: 3.1093
Iteration: 1827; Percent complete: 45.7%; Average loss: 3.1637
Iteration: 1828; Percent complete: 45.7%; Average loss: 3.2796
Iteration: 1829; Percent complete: 45.7%; Average loss: 3.3940
Iteration: 1830; Percent complete: 45.8%; Average loss: 2.8941
Iteration: 1831; Percent complete: 45.8%; Average loss: 2.9028
Iteration: 1832; Percent complete: 45.8%; Average loss: 3.2795
Iteration: 1833; Percent complete: 45.8%; Average loss: 3.3510
Iteration: 1834; Percent complete: 45.9%; Average loss: 3.0514
Iteration: 1835; Percent complete: 45.9%; Average loss: 3.0578
Iteration: 1836; Percent complete: 45.9%; Average loss: 3.0260
Iteration: 1837; Percent complete: 45.9%; Average loss: 3.1527
Iteration: 1838; Percent complete: 46.0%; Average loss: 3.1605
Iteration: 1839; Percent complete: 46.0%; Average loss: 2.6732
Iteration: 1840; Percent complete: 46.0%; Average loss: 3.0944
Iteration: 1841; Percent complete: 46.0%; Average loss: 3.2436
Iteration: 1842; Percent complete: 46.1%; Average loss: 3.3013
Iteration: 1843; Percent complete: 46.1%; Average loss: 3.1623
Iteration: 1844; Percent complete: 46.1%; Average loss: 3.4729
Iteration: 1845; Percent complete: 46.1%; Average loss: 3.2865
Iteration: 1846; Percent complete: 46.2%; Average loss: 3.2384
Iteration: 1847; Percent complete: 46.2%; Average loss: 3.1851
Iteration: 1848; Percent complete: 46.2%; Average loss: 3.2685
Iteration: 1849; Percent complete: 46.2%; Average loss: 3.3831
Iteration: 1850; Percent complete: 46.2%; Average loss: 3.3347
Iteration: 1851; Percent complete: 46.3%; Average loss: 3.2907
Iteration: 1852; Percent complete: 46.3%; Average loss: 3.3569
Iteration: 1853; Percent complete: 46.3%; Average loss: 3.1481
Iteration: 1854; Percent complete: 46.4%; Average loss: 3.4101
Iteration: 1855; Percent complete: 46.4%; Average loss: 3.2101
Iteration: 1856; Percent complete: 46.4%; Average loss: 2.9550
Iteration: 1857; Percent complete: 46.4%; Average loss: 3.1924
Iteration: 1858; Percent complete: 46.5%; Average loss: 2.9980
Iteration: 1859; Percent complete: 46.5%; Average loss: 3.0349
Iteration: 1860; Percent complete: 46.5%; Average loss: 3.0372
Iteration: 1861; Percent complete: 46.5%; Average loss: 3.2499
Iteration: 1862; Percent complete: 46.6%; Average loss: 3.1568
Iteration: 1863; Percent complete: 46.6%; Average loss: 3.3339
Iteration: 1864; Percent complete: 46.6%; Average loss: 3.1336
Iteration: 1865; Percent complete: 46.6%; Average loss: 3.2455
Iteration: 1866; Percent complete: 46.7%; Average loss: 3.3861
Iteration: 1867; Percent complete: 46.7%; Average loss: 3.3128
Iteration: 1868; Percent complete: 46.7%; Average loss: 3.1057
Iteration: 1869; Percent complete: 46.7%; Average loss: 3.1638
Iteration: 1870; Percent complete: 46.8%; Average loss: 3.1195
Iteration: 1871; Percent complete: 46.8%; Average loss: 3.1767
Iteration: 1872; Percent complete: 46.8%; Average loss: 3.1574
Iteration: 1873; Percent complete: 46.8%; Average loss: 3.0154
Iteration: 1874; Percent complete: 46.9%; Average loss: 3.3629
Iteration: 1875; Percent complete: 46.9%; Average loss: 3.3521
Iteration: 1876; Percent complete: 46.9%; Average loss: 3.2537
Iteration: 1877; Percent complete: 46.9%; Average loss: 3.1974
Iteration: 1878; Percent complete: 46.9%; Average loss: 3.1456
Iteration: 1879; Percent complete: 47.0%; Average loss: 3.0644
Iteration: 1880; Percent complete: 47.0%; Average loss: 2.9051
Iteration: 1881; Percent complete: 47.0%; Average loss: 3.2719
Iteration: 1882; Percent complete: 47.0%; Average loss: 3.0329
Iteration: 1883; Percent complete: 47.1%; Average loss: 3.1279
Iteration: 1884; Percent complete: 47.1%; Average loss: 3.2778
Iteration: 1885; Percent complete: 47.1%; Average loss: 3.2951
Iteration: 1886; Percent complete: 47.1%; Average loss: 3.2333
Iteration: 1887; Percent complete: 47.2%; Average loss: 3.2373
Iteration: 1888; Percent complete: 47.2%; Average loss: 2.9642
Iteration: 1889; Percent complete: 47.2%; Average loss: 3.3250
Iteration: 1890; Percent complete: 47.2%; Average loss: 3.2148
Iteration: 1891; Percent complete: 47.3%; Average loss: 3.4125
Iteration: 1892; Percent complete: 47.3%; Average loss: 3.1035
Iteration: 1893; Percent complete: 47.3%; Average loss: 3.2349
Iteration: 1894; Percent complete: 47.3%; Average loss: 3.3031
Iteration: 1895; Percent complete: 47.4%; Average loss: 3.1335
Iteration: 1896; Percent complete: 47.4%; Average loss: 2.9637
Iteration: 1897; Percent complete: 47.4%; Average loss: 3.2792
Iteration: 1898; Percent complete: 47.4%; Average loss: 2.9328
Iteration: 1899; Percent complete: 47.5%; Average loss: 3.0548
Iteration: 1900; Percent complete: 47.5%; Average loss: 3.5831
Iteration: 1901; Percent complete: 47.5%; Average loss: 3.4324
Iteration: 1902; Percent complete: 47.5%; Average loss: 3.0291
Iteration: 1903; Percent complete: 47.6%; Average loss: 3.3461
Iteration: 1904; Percent complete: 47.6%; Average loss: 3.1719
Iteration: 1905; Percent complete: 47.6%; Average loss: 2.9159
Iteration: 1906; Percent complete: 47.6%; Average loss: 3.3328
Iteration: 1907; Percent complete: 47.7%; Average loss: 3.1990
Iteration: 1908; Percent complete: 47.7%; Average loss: 3.1080
Iteration: 1909; Percent complete: 47.7%; Average loss: 3.4542
Iteration: 1910; Percent complete: 47.8%; Average loss: 3.0312
Iteration: 1911; Percent complete: 47.8%; Average loss: 3.2689
Iteration: 1912; Percent complete: 47.8%; Average loss: 3.0660
Iteration: 1913; Percent complete: 47.8%; Average loss: 3.2238
Iteration: 1914; Percent complete: 47.9%; Average loss: 3.2421
Iteration: 1915; Percent complete: 47.9%; Average loss: 3.1925
Iteration: 1916; Percent complete: 47.9%; Average loss: 3.1364
Iteration: 1917; Percent complete: 47.9%; Average loss: 3.2122
Iteration: 1918; Percent complete: 47.9%; Average loss: 3.4639
Iteration: 1919; Percent complete: 48.0%; Average loss: 2.9498
Iteration: 1920; Percent complete: 48.0%; Average loss: 3.1861
Iteration: 1921; Percent complete: 48.0%; Average loss: 3.1705
Iteration: 1922; Percent complete: 48.0%; Average loss: 3.3255
Iteration: 1923; Percent complete: 48.1%; Average loss: 3.1905
Iteration: 1924; Percent complete: 48.1%; Average loss: 3.2311
Iteration: 1925; Percent complete: 48.1%; Average loss: 3.4154
Iteration: 1926; Percent complete: 48.1%; Average loss: 3.0786
Iteration: 1927; Percent complete: 48.2%; Average loss: 3.3169
Iteration: 1928; Percent complete: 48.2%; Average loss: 3.3001
Iteration: 1929; Percent complete: 48.2%; Average loss: 3.0750
Iteration: 1930; Percent complete: 48.2%; Average loss: 2.9378
Iteration: 1931; Percent complete: 48.3%; Average loss: 3.1319
Iteration: 1932; Percent complete: 48.3%; Average loss: 3.1666
Iteration: 1933; Percent complete: 48.3%; Average loss: 3.2500
Iteration: 1934; Percent complete: 48.4%; Average loss: 3.1574
Iteration: 1935; Percent complete: 48.4%; Average loss: 3.1090
Iteration: 1936; Percent complete: 48.4%; Average loss: 3.1957
Iteration: 1937; Percent complete: 48.4%; Average loss: 3.0343
Iteration: 1938; Percent complete: 48.4%; Average loss: 3.0702
Iteration: 1939; Percent complete: 48.5%; Average loss: 3.1012
Iteration: 1940; Percent complete: 48.5%; Average loss: 3.3291
Iteration: 1941; Percent complete: 48.5%; Average loss: 3.0974
Iteration: 1942; Percent complete: 48.5%; Average loss: 3.1788
Iteration: 1943; Percent complete: 48.6%; Average loss: 3.1611
Iteration: 1944; Percent complete: 48.6%; Average loss: 3.1166
Iteration: 1945; Percent complete: 48.6%; Average loss: 3.1521
Iteration: 1946; Percent complete: 48.6%; Average loss: 3.2538
Iteration: 1947; Percent complete: 48.7%; Average loss: 3.3099
Iteration: 1948; Percent complete: 48.7%; Average loss: 3.2441
Iteration: 1949; Percent complete: 48.7%; Average loss: 3.3674
Iteration: 1950; Percent complete: 48.8%; Average loss: 3.4937
Iteration: 1951; Percent complete: 48.8%; Average loss: 3.0969
Iteration: 1952; Percent complete: 48.8%; Average loss: 3.3420
Iteration: 1953; Percent complete: 48.8%; Average loss: 3.2692
Iteration: 1954; Percent complete: 48.9%; Average loss: 3.2218
Iteration: 1955; Percent complete: 48.9%; Average loss: 3.3409
Iteration: 1956; Percent complete: 48.9%; Average loss: 3.0702
Iteration: 1957; Percent complete: 48.9%; Average loss: 3.1722
Iteration: 1958; Percent complete: 48.9%; Average loss: 3.2948
Iteration: 1959; Percent complete: 49.0%; Average loss: 3.0495
Iteration: 1960; Percent complete: 49.0%; Average loss: 3.3335
Iteration: 1961; Percent complete: 49.0%; Average loss: 3.1226
Iteration: 1962; Percent complete: 49.0%; Average loss: 3.1369
Iteration: 1963; Percent complete: 49.1%; Average loss: 3.3936
Iteration: 1964; Percent complete: 49.1%; Average loss: 3.1568
Iteration: 1965; Percent complete: 49.1%; Average loss: 3.0606
Iteration: 1966; Percent complete: 49.1%; Average loss: 3.2556
Iteration: 1967; Percent complete: 49.2%; Average loss: 3.2175
Iteration: 1968; Percent complete: 49.2%; Average loss: 3.3224
Iteration: 1969; Percent complete: 49.2%; Average loss: 2.9267
Iteration: 1970; Percent complete: 49.2%; Average loss: 3.2557
Iteration: 1971; Percent complete: 49.3%; Average loss: 3.2936
Iteration: 1972; Percent complete: 49.3%; Average loss: 3.1539
Iteration: 1973; Percent complete: 49.3%; Average loss: 3.2144
Iteration: 1974; Percent complete: 49.4%; Average loss: 3.1972
Iteration: 1975; Percent complete: 49.4%; Average loss: 2.7308
Iteration: 1976; Percent complete: 49.4%; Average loss: 3.4357
Iteration: 1977; Percent complete: 49.4%; Average loss: 3.3192
Iteration: 1978; Percent complete: 49.5%; Average loss: 3.1392
Iteration: 1979; Percent complete: 49.5%; Average loss: 3.2228
Iteration: 1980; Percent complete: 49.5%; Average loss: 3.4258
Iteration: 1981; Percent complete: 49.5%; Average loss: 3.0522
Iteration: 1982; Percent complete: 49.5%; Average loss: 3.0788
Iteration: 1983; Percent complete: 49.6%; Average loss: 3.0244
Iteration: 1984; Percent complete: 49.6%; Average loss: 3.2252
Iteration: 1985; Percent complete: 49.6%; Average loss: 2.9899
Iteration: 1986; Percent complete: 49.6%; Average loss: 3.1490
Iteration: 1987; Percent complete: 49.7%; Average loss: 3.2383
Iteration: 1988; Percent complete: 49.7%; Average loss: 3.3993
Iteration: 1989; Percent complete: 49.7%; Average loss: 3.0678
Iteration: 1990; Percent complete: 49.8%; Average loss: 3.0243
Iteration: 1991; Percent complete: 49.8%; Average loss: 3.3331
Iteration: 1992; Percent complete: 49.8%; Average loss: 2.9865
Iteration: 1993; Percent complete: 49.8%; Average loss: 3.2493
Iteration: 1994; Percent complete: 49.9%; Average loss: 3.2466
Iteration: 1995; Percent complete: 49.9%; Average loss: 3.2383
Iteration: 1996; Percent complete: 49.9%; Average loss: 3.2652
Iteration: 1997; Percent complete: 49.9%; Average loss: 3.0662
Iteration: 1998; Percent complete: 50.0%; Average loss: 3.2569
Iteration: 1999; Percent complete: 50.0%; Average loss: 3.2541
Iteration: 2000; Percent complete: 50.0%; Average loss: 3.4669
Iteration: 2001; Percent complete: 50.0%; Average loss: 3.0366
Iteration: 2002; Percent complete: 50.0%; Average loss: 3.1787
Iteration: 2003; Percent complete: 50.1%; Average loss: 3.3028
Iteration: 2004; Percent complete: 50.1%; Average loss: 3.1879
Iteration: 2005; Percent complete: 50.1%; Average loss: 2.9825
Iteration: 2006; Percent complete: 50.1%; Average loss: 3.2294
Iteration: 2007; Percent complete: 50.2%; Average loss: 3.1420
Iteration: 2008; Percent complete: 50.2%; Average loss: 3.2402
Iteration: 2009; Percent complete: 50.2%; Average loss: 2.9325
Iteration: 2010; Percent complete: 50.2%; Average loss: 2.9561
Iteration: 2011; Percent complete: 50.3%; Average loss: 3.0799
Iteration: 2012; Percent complete: 50.3%; Average loss: 3.2673
Iteration: 2013; Percent complete: 50.3%; Average loss: 3.1812
Iteration: 2014; Percent complete: 50.3%; Average loss: 3.1301
Iteration: 2015; Percent complete: 50.4%; Average loss: 3.1345
Iteration: 2016; Percent complete: 50.4%; Average loss: 2.8795
Iteration: 2017; Percent complete: 50.4%; Average loss: 3.1060
Iteration: 2018; Percent complete: 50.4%; Average loss: 3.0060
Iteration: 2019; Percent complete: 50.5%; Average loss: 3.4339
Iteration: 2020; Percent complete: 50.5%; Average loss: 3.3483
Iteration: 2021; Percent complete: 50.5%; Average loss: 3.1473
Iteration: 2022; Percent complete: 50.5%; Average loss: 3.0969
Iteration: 2023; Percent complete: 50.6%; Average loss: 2.8676
Iteration: 2024; Percent complete: 50.6%; Average loss: 3.1239
Iteration: 2025; Percent complete: 50.6%; Average loss: 2.9368
Iteration: 2026; Percent complete: 50.6%; Average loss: 2.9128
Iteration: 2027; Percent complete: 50.7%; Average loss: 3.1567
Iteration: 2028; Percent complete: 50.7%; Average loss: 3.2675
Iteration: 2029; Percent complete: 50.7%; Average loss: 3.0604
Iteration: 2030; Percent complete: 50.7%; Average loss: 2.8761
Iteration: 2031; Percent complete: 50.8%; Average loss: 3.1035
Iteration: 2032; Percent complete: 50.8%; Average loss: 3.5478
Iteration: 2033; Percent complete: 50.8%; Average loss: 3.2746
Iteration: 2034; Percent complete: 50.8%; Average loss: 3.1343
Iteration: 2035; Percent complete: 50.9%; Average loss: 3.2982
Iteration: 2036; Percent complete: 50.9%; Average loss: 2.8947
Iteration: 2037; Percent complete: 50.9%; Average loss: 3.2447
Iteration: 2038; Percent complete: 50.9%; Average loss: 3.2577
Iteration: 2039; Percent complete: 51.0%; Average loss: 3.0421
Iteration: 2040; Percent complete: 51.0%; Average loss: 3.0378
Iteration: 2041; Percent complete: 51.0%; Average loss: 3.2223
Iteration: 2042; Percent complete: 51.0%; Average loss: 3.1576
Iteration: 2043; Percent complete: 51.1%; Average loss: 2.8679
Iteration: 2044; Percent complete: 51.1%; Average loss: 3.2512
Iteration: 2045; Percent complete: 51.1%; Average loss: 3.1809
Iteration: 2046; Percent complete: 51.1%; Average loss: 3.1020
Iteration: 2047; Percent complete: 51.2%; Average loss: 3.1864
Iteration: 2048; Percent complete: 51.2%; Average loss: 3.0693
Iteration: 2049; Percent complete: 51.2%; Average loss: 3.3192
Iteration: 2050; Percent complete: 51.2%; Average loss: 3.0207
Iteration: 2051; Percent complete: 51.3%; Average loss: 2.7781
Iteration: 2052; Percent complete: 51.3%; Average loss: 3.2378
Iteration: 2053; Percent complete: 51.3%; Average loss: 3.1266
Iteration: 2054; Percent complete: 51.3%; Average loss: 3.2742
Iteration: 2055; Percent complete: 51.4%; Average loss: 3.2571
Iteration: 2056; Percent complete: 51.4%; Average loss: 3.2459
Iteration: 2057; Percent complete: 51.4%; Average loss: 3.1352
Iteration: 2058; Percent complete: 51.4%; Average loss: 3.1744
Iteration: 2059; Percent complete: 51.5%; Average loss: 2.9088
Iteration: 2060; Percent complete: 51.5%; Average loss: 3.2942
Iteration: 2061; Percent complete: 51.5%; Average loss: 3.1455
Iteration: 2062; Percent complete: 51.5%; Average loss: 3.0390
Iteration: 2063; Percent complete: 51.6%; Average loss: 3.3695
Iteration: 2064; Percent complete: 51.6%; Average loss: 3.3086
Iteration: 2065; Percent complete: 51.6%; Average loss: 3.1772
Iteration: 2066; Percent complete: 51.6%; Average loss: 3.2005
Iteration: 2067; Percent complete: 51.7%; Average loss: 3.1829
Iteration: 2068; Percent complete: 51.7%; Average loss: 3.0749
Iteration: 2069; Percent complete: 51.7%; Average loss: 3.1530
Iteration: 2070; Percent complete: 51.7%; Average loss: 3.3780
Iteration: 2071; Percent complete: 51.8%; Average loss: 3.3929
Iteration: 2072; Percent complete: 51.8%; Average loss: 3.3388
Iteration: 2073; Percent complete: 51.8%; Average loss: 3.1018
Iteration: 2074; Percent complete: 51.8%; Average loss: 3.2188
Iteration: 2075; Percent complete: 51.9%; Average loss: 3.2833
Iteration: 2076; Percent complete: 51.9%; Average loss: 3.1261
Iteration: 2077; Percent complete: 51.9%; Average loss: 3.3275
Iteration: 2078; Percent complete: 51.9%; Average loss: 3.0628
Iteration: 2079; Percent complete: 52.0%; Average loss: 3.2375
Iteration: 2080; Percent complete: 52.0%; Average loss: 3.0079
Iteration: 2081; Percent complete: 52.0%; Average loss: 3.1012
Iteration: 2082; Percent complete: 52.0%; Average loss: 3.2102
Iteration: 2083; Percent complete: 52.1%; Average loss: 3.0187
Iteration: 2084; Percent complete: 52.1%; Average loss: 2.8798
Iteration: 2085; Percent complete: 52.1%; Average loss: 3.1631
Iteration: 2086; Percent complete: 52.1%; Average loss: 3.1456
Iteration: 2087; Percent complete: 52.2%; Average loss: 3.3132
Iteration: 2088; Percent complete: 52.2%; Average loss: 3.2101
Iteration: 2089; Percent complete: 52.2%; Average loss: 3.0517
Iteration: 2090; Percent complete: 52.2%; Average loss: 3.2999
Iteration: 2091; Percent complete: 52.3%; Average loss: 3.1362
Iteration: 2092; Percent complete: 52.3%; Average loss: 3.2270
Iteration: 2093; Percent complete: 52.3%; Average loss: 3.2066
Iteration: 2094; Percent complete: 52.3%; Average loss: 3.2182
Iteration: 2095; Percent complete: 52.4%; Average loss: 3.0090
Iteration: 2096; Percent complete: 52.4%; Average loss: 3.3372
Iteration: 2097; Percent complete: 52.4%; Average loss: 2.9713
Iteration: 2098; Percent complete: 52.4%; Average loss: 3.1547
Iteration: 2099; Percent complete: 52.5%; Average loss: 3.4074
Iteration: 2100; Percent complete: 52.5%; Average loss: 3.1147
Iteration: 2101; Percent complete: 52.5%; Average loss: 3.0186
Iteration: 2102; Percent complete: 52.5%; Average loss: 3.2042
Iteration: 2103; Percent complete: 52.6%; Average loss: 3.2989
Iteration: 2104; Percent complete: 52.6%; Average loss: 3.1700
Iteration: 2105; Percent complete: 52.6%; Average loss: 3.2418
Iteration: 2106; Percent complete: 52.6%; Average loss: 2.9703
Iteration: 2107; Percent complete: 52.7%; Average loss: 3.1723
Iteration: 2108; Percent complete: 52.7%; Average loss: 2.7437
Iteration: 2109; Percent complete: 52.7%; Average loss: 3.0116
Iteration: 2110; Percent complete: 52.8%; Average loss: 3.1332
Iteration: 2111; Percent complete: 52.8%; Average loss: 3.0597
Iteration: 2112; Percent complete: 52.8%; Average loss: 3.1963
Iteration: 2113; Percent complete: 52.8%; Average loss: 2.9038
Iteration: 2114; Percent complete: 52.8%; Average loss: 3.0414
Iteration: 2115; Percent complete: 52.9%; Average loss: 3.1992
Iteration: 2116; Percent complete: 52.9%; Average loss: 3.0455
Iteration: 2117; Percent complete: 52.9%; Average loss: 3.2541
Iteration: 2118; Percent complete: 52.9%; Average loss: 3.3036
Iteration: 2119; Percent complete: 53.0%; Average loss: 3.0831
Iteration: 2120; Percent complete: 53.0%; Average loss: 3.3455
Iteration: 2121; Percent complete: 53.0%; Average loss: 2.9825
Iteration: 2122; Percent complete: 53.0%; Average loss: 3.2205
Iteration: 2123; Percent complete: 53.1%; Average loss: 3.1735
Iteration: 2124; Percent complete: 53.1%; Average loss: 3.1637
Iteration: 2125; Percent complete: 53.1%; Average loss: 3.0643
Iteration: 2126; Percent complete: 53.1%; Average loss: 3.1614
Iteration: 2127; Percent complete: 53.2%; Average loss: 3.0786
Iteration: 2128; Percent complete: 53.2%; Average loss: 3.2029
Iteration: 2129; Percent complete: 53.2%; Average loss: 3.1584
Iteration: 2130; Percent complete: 53.2%; Average loss: 3.0173
Iteration: 2131; Percent complete: 53.3%; Average loss: 3.1375
Iteration: 2132; Percent complete: 53.3%; Average loss: 2.9747
Iteration: 2133; Percent complete: 53.3%; Average loss: 3.0363
Iteration: 2134; Percent complete: 53.3%; Average loss: 3.1394
Iteration: 2135; Percent complete: 53.4%; Average loss: 3.0349
Iteration: 2136; Percent complete: 53.4%; Average loss: 3.2630
Iteration: 2137; Percent complete: 53.4%; Average loss: 3.0306
Iteration: 2138; Percent complete: 53.4%; Average loss: 2.9818
Iteration: 2139; Percent complete: 53.5%; Average loss: 3.1970
Iteration: 2140; Percent complete: 53.5%; Average loss: 2.9720
Iteration: 2141; Percent complete: 53.5%; Average loss: 3.2738
Iteration: 2142; Percent complete: 53.5%; Average loss: 3.0025
Iteration: 2143; Percent complete: 53.6%; Average loss: 3.1334
Iteration: 2144; Percent complete: 53.6%; Average loss: 3.2800
Iteration: 2145; Percent complete: 53.6%; Average loss: 2.8998
Iteration: 2146; Percent complete: 53.6%; Average loss: 2.8095
Iteration: 2147; Percent complete: 53.7%; Average loss: 3.2831
Iteration: 2148; Percent complete: 53.7%; Average loss: 3.0090
Iteration: 2149; Percent complete: 53.7%; Average loss: 3.1354
Iteration: 2150; Percent complete: 53.8%; Average loss: 3.3507
Iteration: 2151; Percent complete: 53.8%; Average loss: 3.0470
Iteration: 2152; Percent complete: 53.8%; Average loss: 2.8264
Iteration: 2153; Percent complete: 53.8%; Average loss: 3.2745
Iteration: 2154; Percent complete: 53.8%; Average loss: 3.0731
Iteration: 2155; Percent complete: 53.9%; Average loss: 3.1453
Iteration: 2156; Percent complete: 53.9%; Average loss: 3.1477
Iteration: 2157; Percent complete: 53.9%; Average loss: 3.1081
Iteration: 2158; Percent complete: 53.9%; Average loss: 3.2681
Iteration: 2159; Percent complete: 54.0%; Average loss: 2.9471
Iteration: 2160; Percent complete: 54.0%; Average loss: 3.1266
Iteration: 2161; Percent complete: 54.0%; Average loss: 3.1301
Iteration: 2162; Percent complete: 54.0%; Average loss: 3.0963
Iteration: 2163; Percent complete: 54.1%; Average loss: 3.1395
Iteration: 2164; Percent complete: 54.1%; Average loss: 2.9446
Iteration: 2165; Percent complete: 54.1%; Average loss: 3.2281
Iteration: 2166; Percent complete: 54.1%; Average loss: 3.4299
Iteration: 2167; Percent complete: 54.2%; Average loss: 3.0411
Iteration: 2168; Percent complete: 54.2%; Average loss: 3.1745
Iteration: 2169; Percent complete: 54.2%; Average loss: 3.0736
Iteration: 2170; Percent complete: 54.2%; Average loss: 3.2661
Iteration: 2171; Percent complete: 54.3%; Average loss: 3.1467
Iteration: 2172; Percent complete: 54.3%; Average loss: 2.7534
Iteration: 2173; Percent complete: 54.3%; Average loss: 3.1058
Iteration: 2174; Percent complete: 54.4%; Average loss: 2.9104
Iteration: 2175; Percent complete: 54.4%; Average loss: 2.9686
Iteration: 2176; Percent complete: 54.4%; Average loss: 3.1114
Iteration: 2177; Percent complete: 54.4%; Average loss: 2.9860
Iteration: 2178; Percent complete: 54.4%; Average loss: 3.0246
Iteration: 2179; Percent complete: 54.5%; Average loss: 3.1939
Iteration: 2180; Percent complete: 54.5%; Average loss: 3.1825
Iteration: 2181; Percent complete: 54.5%; Average loss: 3.1789
Iteration: 2182; Percent complete: 54.5%; Average loss: 3.0860
Iteration: 2183; Percent complete: 54.6%; Average loss: 3.0036
Iteration: 2184; Percent complete: 54.6%; Average loss: 3.1669
Iteration: 2185; Percent complete: 54.6%; Average loss: 3.1326
Iteration: 2186; Percent complete: 54.6%; Average loss: 3.2761
Iteration: 2187; Percent complete: 54.7%; Average loss: 3.0138
Iteration: 2188; Percent complete: 54.7%; Average loss: 2.9971
Iteration: 2189; Percent complete: 54.7%; Average loss: 3.1004
Iteration: 2190; Percent complete: 54.8%; Average loss: 3.2182
Iteration: 2191; Percent complete: 54.8%; Average loss: 3.0677
Iteration: 2192; Percent complete: 54.8%; Average loss: 2.9855
Iteration: 2193; Percent complete: 54.8%; Average loss: 3.2107
Iteration: 2194; Percent complete: 54.9%; Average loss: 2.7193
Iteration: 2195; Percent complete: 54.9%; Average loss: 2.6279
Iteration: 2196; Percent complete: 54.9%; Average loss: 3.2774
Iteration: 2197; Percent complete: 54.9%; Average loss: 3.2326
Iteration: 2198; Percent complete: 54.9%; Average loss: 3.2699
Iteration: 2199; Percent complete: 55.0%; Average loss: 2.8903
Iteration: 2200; Percent complete: 55.0%; Average loss: 2.8346
Iteration: 2201; Percent complete: 55.0%; Average loss: 3.0542
Iteration: 2202; Percent complete: 55.0%; Average loss: 3.1161
Iteration: 2203; Percent complete: 55.1%; Average loss: 3.0885
Iteration: 2204; Percent complete: 55.1%; Average loss: 3.0479
Iteration: 2205; Percent complete: 55.1%; Average loss: 2.9757
Iteration: 2206; Percent complete: 55.1%; Average loss: 3.1660
Iteration: 2207; Percent complete: 55.2%; Average loss: 3.2372
Iteration: 2208; Percent complete: 55.2%; Average loss: 2.8240
Iteration: 2209; Percent complete: 55.2%; Average loss: 3.3955
Iteration: 2210; Percent complete: 55.2%; Average loss: 3.2072
Iteration: 2211; Percent complete: 55.3%; Average loss: 3.2903
Iteration: 2212; Percent complete: 55.3%; Average loss: 3.0548
Iteration: 2213; Percent complete: 55.3%; Average loss: 3.2703
Iteration: 2214; Percent complete: 55.4%; Average loss: 3.1498
Iteration: 2215; Percent complete: 55.4%; Average loss: 3.1052
Iteration: 2216; Percent complete: 55.4%; Average loss: 3.2419
Iteration: 2217; Percent complete: 55.4%; Average loss: 2.8384
Iteration: 2218; Percent complete: 55.5%; Average loss: 2.8381
Iteration: 2219; Percent complete: 55.5%; Average loss: 3.0782
Iteration: 2220; Percent complete: 55.5%; Average loss: 3.0533
Iteration: 2221; Percent complete: 55.5%; Average loss: 3.0838
Iteration: 2222; Percent complete: 55.5%; Average loss: 2.8333
Iteration: 2223; Percent complete: 55.6%; Average loss: 3.0831
Iteration: 2224; Percent complete: 55.6%; Average loss: 3.0372
Iteration: 2225; Percent complete: 55.6%; Average loss: 3.1821
Iteration: 2226; Percent complete: 55.6%; Average loss: 3.0850
Iteration: 2227; Percent complete: 55.7%; Average loss: 3.2853
Iteration: 2228; Percent complete: 55.7%; Average loss: 3.0405
Iteration: 2229; Percent complete: 55.7%; Average loss: 2.9675
Iteration: 2230; Percent complete: 55.8%; Average loss: 3.0148
Iteration: 2231; Percent complete: 55.8%; Average loss: 3.0007
Iteration: 2232; Percent complete: 55.8%; Average loss: 3.1362
Iteration: 2233; Percent complete: 55.8%; Average loss: 3.2396
Iteration: 2234; Percent complete: 55.9%; Average loss: 3.1737
Iteration: 2235; Percent complete: 55.9%; Average loss: 3.1801
Iteration: 2236; Percent complete: 55.9%; Average loss: 3.2120
Iteration: 2237; Percent complete: 55.9%; Average loss: 3.2593
Iteration: 2238; Percent complete: 56.0%; Average loss: 3.2114
Iteration: 2239; Percent complete: 56.0%; Average loss: 2.9755
Iteration: 2240; Percent complete: 56.0%; Average loss: 3.2571
Iteration: 2241; Percent complete: 56.0%; Average loss: 2.9760
Iteration: 2242; Percent complete: 56.0%; Average loss: 3.2055
Iteration: 2243; Percent complete: 56.1%; Average loss: 2.8420
Iteration: 2244; Percent complete: 56.1%; Average loss: 2.9784
Iteration: 2245; Percent complete: 56.1%; Average loss: 2.9684
Iteration: 2246; Percent complete: 56.1%; Average loss: 3.0740
Iteration: 2247; Percent complete: 56.2%; Average loss: 3.1568
Iteration: 2248; Percent complete: 56.2%; Average loss: 3.0356
Iteration: 2249; Percent complete: 56.2%; Average loss: 3.1420
Iteration: 2250; Percent complete: 56.2%; Average loss: 3.2930
Iteration: 2251; Percent complete: 56.3%; Average loss: 3.2371
Iteration: 2252; Percent complete: 56.3%; Average loss: 2.9946
Iteration: 2253; Percent complete: 56.3%; Average loss: 3.1748
Iteration: 2254; Percent complete: 56.4%; Average loss: 3.2371
Iteration: 2255; Percent complete: 56.4%; Average loss: 3.1888
Iteration: 2256; Percent complete: 56.4%; Average loss: 3.2556
Iteration: 2257; Percent complete: 56.4%; Average loss: 2.8311
Iteration: 2258; Percent complete: 56.5%; Average loss: 2.9935
Iteration: 2259; Percent complete: 56.5%; Average loss: 3.0426
Iteration: 2260; Percent complete: 56.5%; Average loss: 3.0659
Iteration: 2261; Percent complete: 56.5%; Average loss: 3.1162
Iteration: 2262; Percent complete: 56.5%; Average loss: 2.9385
Iteration: 2263; Percent complete: 56.6%; Average loss: 3.2193
Iteration: 2264; Percent complete: 56.6%; Average loss: 3.1631
Iteration: 2265; Percent complete: 56.6%; Average loss: 3.2265
Iteration: 2266; Percent complete: 56.6%; Average loss: 3.0982
Iteration: 2267; Percent complete: 56.7%; Average loss: 2.9707
Iteration: 2268; Percent complete: 56.7%; Average loss: 2.9163
Iteration: 2269; Percent complete: 56.7%; Average loss: 3.1338
Iteration: 2270; Percent complete: 56.8%; Average loss: 3.0912
Iteration: 2271; Percent complete: 56.8%; Average loss: 3.1048
Iteration: 2272; Percent complete: 56.8%; Average loss: 3.2464
Iteration: 2273; Percent complete: 56.8%; Average loss: 3.1827
Iteration: 2274; Percent complete: 56.9%; Average loss: 3.2877
Iteration: 2275; Percent complete: 56.9%; Average loss: 3.0032
Iteration: 2276; Percent complete: 56.9%; Average loss: 2.7811
Iteration: 2277; Percent complete: 56.9%; Average loss: 3.0686
Iteration: 2278; Percent complete: 57.0%; Average loss: 3.1135
Iteration: 2279; Percent complete: 57.0%; Average loss: 2.9476
Iteration: 2280; Percent complete: 57.0%; Average loss: 3.0272
Iteration: 2281; Percent complete: 57.0%; Average loss: 3.1886
Iteration: 2282; Percent complete: 57.0%; Average loss: 2.8014
Iteration: 2283; Percent complete: 57.1%; Average loss: 3.1877
Iteration: 2284; Percent complete: 57.1%; Average loss: 3.1117
Iteration: 2285; Percent complete: 57.1%; Average loss: 2.8363
Iteration: 2286; Percent complete: 57.1%; Average loss: 2.8774
Iteration: 2287; Percent complete: 57.2%; Average loss: 3.1559
Iteration: 2288; Percent complete: 57.2%; Average loss: 3.1068
Iteration: 2289; Percent complete: 57.2%; Average loss: 3.1455
Iteration: 2290; Percent complete: 57.2%; Average loss: 2.9732
Iteration: 2291; Percent complete: 57.3%; Average loss: 2.9567
Iteration: 2292; Percent complete: 57.3%; Average loss: 3.1956
Iteration: 2293; Percent complete: 57.3%; Average loss: 3.0122
Iteration: 2294; Percent complete: 57.4%; Average loss: 3.1170
Iteration: 2295; Percent complete: 57.4%; Average loss: 3.0311
Iteration: 2296; Percent complete: 57.4%; Average loss: 2.9600
Iteration: 2297; Percent complete: 57.4%; Average loss: 2.8681
Iteration: 2298; Percent complete: 57.5%; Average loss: 3.0366
Iteration: 2299; Percent complete: 57.5%; Average loss: 2.9815
Iteration: 2300; Percent complete: 57.5%; Average loss: 3.0159
Iteration: 2301; Percent complete: 57.5%; Average loss: 3.1047
Iteration: 2302; Percent complete: 57.6%; Average loss: 2.7576
Iteration: 2303; Percent complete: 57.6%; Average loss: 2.8719
Iteration: 2304; Percent complete: 57.6%; Average loss: 3.0503
Iteration: 2305; Percent complete: 57.6%; Average loss: 3.1899
Iteration: 2306; Percent complete: 57.6%; Average loss: 2.9873
Iteration: 2307; Percent complete: 57.7%; Average loss: 2.9500
Iteration: 2308; Percent complete: 57.7%; Average loss: 3.0110
Iteration: 2309; Percent complete: 57.7%; Average loss: 3.1390
Iteration: 2310; Percent complete: 57.8%; Average loss: 3.2256
Iteration: 2311; Percent complete: 57.8%; Average loss: 3.3814
Iteration: 2312; Percent complete: 57.8%; Average loss: 2.9531
Iteration: 2313; Percent complete: 57.8%; Average loss: 2.8186
Iteration: 2314; Percent complete: 57.9%; Average loss: 3.1671
Iteration: 2315; Percent complete: 57.9%; Average loss: 3.1986
Iteration: 2316; Percent complete: 57.9%; Average loss: 3.0003
Iteration: 2317; Percent complete: 57.9%; Average loss: 2.8998
Iteration: 2318; Percent complete: 58.0%; Average loss: 3.3645
Iteration: 2319; Percent complete: 58.0%; Average loss: 2.8024
Iteration: 2320; Percent complete: 58.0%; Average loss: 3.3875
Iteration: 2321; Percent complete: 58.0%; Average loss: 3.0104
Iteration: 2322; Percent complete: 58.1%; Average loss: 3.0573
Iteration: 2323; Percent complete: 58.1%; Average loss: 2.8679
Iteration: 2324; Percent complete: 58.1%; Average loss: 3.2934
Iteration: 2325; Percent complete: 58.1%; Average loss: 3.0064
Iteration: 2326; Percent complete: 58.1%; Average loss: 2.8418
Iteration: 2327; Percent complete: 58.2%; Average loss: 2.9836
Iteration: 2328; Percent complete: 58.2%; Average loss: 2.9516
Iteration: 2329; Percent complete: 58.2%; Average loss: 3.1289
Iteration: 2330; Percent complete: 58.2%; Average loss: 3.0988
Iteration: 2331; Percent complete: 58.3%; Average loss: 3.0837
Iteration: 2332; Percent complete: 58.3%; Average loss: 2.7522
Iteration: 2333; Percent complete: 58.3%; Average loss: 3.2279
Iteration: 2334; Percent complete: 58.4%; Average loss: 2.9395
Iteration: 2335; Percent complete: 58.4%; Average loss: 3.4656
Iteration: 2336; Percent complete: 58.4%; Average loss: 2.9158
Iteration: 2337; Percent complete: 58.4%; Average loss: 2.8607
Iteration: 2338; Percent complete: 58.5%; Average loss: 3.0872
Iteration: 2339; Percent complete: 58.5%; Average loss: 3.2855
Iteration: 2340; Percent complete: 58.5%; Average loss: 3.1031
Iteration: 2341; Percent complete: 58.5%; Average loss: 2.9364
Iteration: 2342; Percent complete: 58.6%; Average loss: 3.5225
Iteration: 2343; Percent complete: 58.6%; Average loss: 3.0404
Iteration: 2344; Percent complete: 58.6%; Average loss: 2.9311
Iteration: 2345; Percent complete: 58.6%; Average loss: 2.9976
Iteration: 2346; Percent complete: 58.7%; Average loss: 2.9114
Iteration: 2347; Percent complete: 58.7%; Average loss: 3.1316
Iteration: 2348; Percent complete: 58.7%; Average loss: 2.9776
Iteration: 2349; Percent complete: 58.7%; Average loss: 2.8523
Iteration: 2350; Percent complete: 58.8%; Average loss: 2.9698
Iteration: 2351; Percent complete: 58.8%; Average loss: 3.3423
Iteration: 2352; Percent complete: 58.8%; Average loss: 3.1668
Iteration: 2353; Percent complete: 58.8%; Average loss: 3.0035
Iteration: 2354; Percent complete: 58.9%; Average loss: 2.8970
Iteration: 2355; Percent complete: 58.9%; Average loss: 3.0419
Iteration: 2356; Percent complete: 58.9%; Average loss: 2.9204
Iteration: 2357; Percent complete: 58.9%; Average loss: 3.2171
Iteration: 2358; Percent complete: 59.0%; Average loss: 2.8641
Iteration: 2359; Percent complete: 59.0%; Average loss: 3.0888
Iteration: 2360; Percent complete: 59.0%; Average loss: 3.1273
Iteration: 2361; Percent complete: 59.0%; Average loss: 3.1028
Iteration: 2362; Percent complete: 59.1%; Average loss: 2.9603
Iteration: 2363; Percent complete: 59.1%; Average loss: 3.0472
Iteration: 2364; Percent complete: 59.1%; Average loss: 3.3028
Iteration: 2365; Percent complete: 59.1%; Average loss: 3.1480
Iteration: 2366; Percent complete: 59.2%; Average loss: 3.2928
Iteration: 2367; Percent complete: 59.2%; Average loss: 2.9939
Iteration: 2368; Percent complete: 59.2%; Average loss: 3.2399
Iteration: 2369; Percent complete: 59.2%; Average loss: 3.1847
Iteration: 2370; Percent complete: 59.2%; Average loss: 3.0630
Iteration: 2371; Percent complete: 59.3%; Average loss: 3.2035
Iteration: 2372; Percent complete: 59.3%; Average loss: 3.1218
Iteration: 2373; Percent complete: 59.3%; Average loss: 2.9090
Iteration: 2374; Percent complete: 59.4%; Average loss: 3.1070
Iteration: 2375; Percent complete: 59.4%; Average loss: 3.1192
Iteration: 2376; Percent complete: 59.4%; Average loss: 3.0898
Iteration: 2377; Percent complete: 59.4%; Average loss: 2.8827
Iteration: 2378; Percent complete: 59.5%; Average loss: 2.8498
Iteration: 2379; Percent complete: 59.5%; Average loss: 2.9666
Iteration: 2380; Percent complete: 59.5%; Average loss: 3.0622
Iteration: 2381; Percent complete: 59.5%; Average loss: 2.9334
Iteration: 2382; Percent complete: 59.6%; Average loss: 2.9086
Iteration: 2383; Percent complete: 59.6%; Average loss: 3.0633
Iteration: 2384; Percent complete: 59.6%; Average loss: 3.1984
Iteration: 2385; Percent complete: 59.6%; Average loss: 3.1292
Iteration: 2386; Percent complete: 59.7%; Average loss: 2.9146
Iteration: 2387; Percent complete: 59.7%; Average loss: 3.0311
Iteration: 2388; Percent complete: 59.7%; Average loss: 2.9564
Iteration: 2389; Percent complete: 59.7%; Average loss: 2.9607
Iteration: 2390; Percent complete: 59.8%; Average loss: 2.9749
Iteration: 2391; Percent complete: 59.8%; Average loss: 2.9014
Iteration: 2392; Percent complete: 59.8%; Average loss: 3.0619
Iteration: 2393; Percent complete: 59.8%; Average loss: 2.7304
Iteration: 2394; Percent complete: 59.9%; Average loss: 2.8756
Iteration: 2395; Percent complete: 59.9%; Average loss: 3.0887
Iteration: 2396; Percent complete: 59.9%; Average loss: 2.7501
Iteration: 2397; Percent complete: 59.9%; Average loss: 3.2327
Iteration: 2398; Percent complete: 60.0%; Average loss: 3.3432
Iteration: 2399; Percent complete: 60.0%; Average loss: 3.0189
Iteration: 2400; Percent complete: 60.0%; Average loss: 3.1909
Iteration: 2401; Percent complete: 60.0%; Average loss: 2.9633
Iteration: 2402; Percent complete: 60.1%; Average loss: 3.0129
Iteration: 2403; Percent complete: 60.1%; Average loss: 3.0634
Iteration: 2404; Percent complete: 60.1%; Average loss: 2.9068
Iteration: 2405; Percent complete: 60.1%; Average loss: 3.2041
Iteration: 2406; Percent complete: 60.2%; Average loss: 3.2791
Iteration: 2407; Percent complete: 60.2%; Average loss: 3.1195
Iteration: 2408; Percent complete: 60.2%; Average loss: 2.9219
Iteration: 2409; Percent complete: 60.2%; Average loss: 2.8502
Iteration: 2410; Percent complete: 60.2%; Average loss: 2.9841
Iteration: 2411; Percent complete: 60.3%; Average loss: 3.0969
Iteration: 2412; Percent complete: 60.3%; Average loss: 3.0805
Iteration: 2413; Percent complete: 60.3%; Average loss: 3.0896
Iteration: 2414; Percent complete: 60.4%; Average loss: 3.1388
Iteration: 2415; Percent complete: 60.4%; Average loss: 2.9527
Iteration: 2416; Percent complete: 60.4%; Average loss: 2.8441
Iteration: 2417; Percent complete: 60.4%; Average loss: 3.2087
Iteration: 2418; Percent complete: 60.5%; Average loss: 3.0716
Iteration: 2419; Percent complete: 60.5%; Average loss: 3.0743
Iteration: 2420; Percent complete: 60.5%; Average loss: 2.7726
Iteration: 2421; Percent complete: 60.5%; Average loss: 2.9378
Iteration: 2422; Percent complete: 60.6%; Average loss: 3.2058
Iteration: 2423; Percent complete: 60.6%; Average loss: 3.0497
Iteration: 2424; Percent complete: 60.6%; Average loss: 3.1941
Iteration: 2425; Percent complete: 60.6%; Average loss: 2.9513
Iteration: 2426; Percent complete: 60.7%; Average loss: 3.0144
Iteration: 2427; Percent complete: 60.7%; Average loss: 2.8443
Iteration: 2428; Percent complete: 60.7%; Average loss: 3.0520
Iteration: 2429; Percent complete: 60.7%; Average loss: 3.2639
Iteration: 2430; Percent complete: 60.8%; Average loss: 3.0331
Iteration: 2431; Percent complete: 60.8%; Average loss: 3.1475
Iteration: 2432; Percent complete: 60.8%; Average loss: 3.2202
Iteration: 2433; Percent complete: 60.8%; Average loss: 2.9492
Iteration: 2434; Percent complete: 60.9%; Average loss: 2.8390
Iteration: 2435; Percent complete: 60.9%; Average loss: 3.3507
Iteration: 2436; Percent complete: 60.9%; Average loss: 3.0734
Iteration: 2437; Percent complete: 60.9%; Average loss: 2.6659
Iteration: 2438; Percent complete: 61.0%; Average loss: 3.0532
Iteration: 2439; Percent complete: 61.0%; Average loss: 2.8028
Iteration: 2440; Percent complete: 61.0%; Average loss: 3.0505
Iteration: 2441; Percent complete: 61.0%; Average loss: 3.1479
Iteration: 2442; Percent complete: 61.1%; Average loss: 2.9936
Iteration: 2443; Percent complete: 61.1%; Average loss: 3.0925
Iteration: 2444; Percent complete: 61.1%; Average loss: 3.0473
Iteration: 2445; Percent complete: 61.1%; Average loss: 3.0821
Iteration: 2446; Percent complete: 61.2%; Average loss: 2.8505
Iteration: 2447; Percent complete: 61.2%; Average loss: 3.3669
Iteration: 2448; Percent complete: 61.2%; Average loss: 3.0771
Iteration: 2449; Percent complete: 61.2%; Average loss: 2.7598
Iteration: 2450; Percent complete: 61.3%; Average loss: 3.2072
Iteration: 2451; Percent complete: 61.3%; Average loss: 3.0982
Iteration: 2452; Percent complete: 61.3%; Average loss: 2.9239
Iteration: 2453; Percent complete: 61.3%; Average loss: 2.9794
Iteration: 2454; Percent complete: 61.4%; Average loss: 2.8975
Iteration: 2455; Percent complete: 61.4%; Average loss: 3.0294
Iteration: 2456; Percent complete: 61.4%; Average loss: 2.8766
Iteration: 2457; Percent complete: 61.4%; Average loss: 2.9170
Iteration: 2458; Percent complete: 61.5%; Average loss: 2.8650
Iteration: 2459; Percent complete: 61.5%; Average loss: 2.7662
Iteration: 2460; Percent complete: 61.5%; Average loss: 2.9594
Iteration: 2461; Percent complete: 61.5%; Average loss: 2.9847
Iteration: 2462; Percent complete: 61.6%; Average loss: 2.7917
Iteration: 2463; Percent complete: 61.6%; Average loss: 2.9638
Iteration: 2464; Percent complete: 61.6%; Average loss: 3.0465
Iteration: 2465; Percent complete: 61.6%; Average loss: 3.0712
Iteration: 2466; Percent complete: 61.7%; Average loss: 2.9428
Iteration: 2467; Percent complete: 61.7%; Average loss: 2.8538
Iteration: 2468; Percent complete: 61.7%; Average loss: 3.0717
Iteration: 2469; Percent complete: 61.7%; Average loss: 2.8607
Iteration: 2470; Percent complete: 61.8%; Average loss: 3.3859
Iteration: 2471; Percent complete: 61.8%; Average loss: 3.1657
Iteration: 2472; Percent complete: 61.8%; Average loss: 3.0556
Iteration: 2473; Percent complete: 61.8%; Average loss: 2.9828
Iteration: 2474; Percent complete: 61.9%; Average loss: 2.9084
Iteration: 2475; Percent complete: 61.9%; Average loss: 3.2858
Iteration: 2476; Percent complete: 61.9%; Average loss: 2.9112
Iteration: 2477; Percent complete: 61.9%; Average loss: 2.9353
Iteration: 2478; Percent complete: 62.0%; Average loss: 2.8877
Iteration: 2479; Percent complete: 62.0%; Average loss: 3.1133
Iteration: 2480; Percent complete: 62.0%; Average loss: 2.7552
Iteration: 2481; Percent complete: 62.0%; Average loss: 3.0352
Iteration: 2482; Percent complete: 62.1%; Average loss: 3.1405
Iteration: 2483; Percent complete: 62.1%; Average loss: 2.9975
Iteration: 2484; Percent complete: 62.1%; Average loss: 2.9169
Iteration: 2485; Percent complete: 62.1%; Average loss: 3.1496
Iteration: 2486; Percent complete: 62.2%; Average loss: 3.2242
Iteration: 2487; Percent complete: 62.2%; Average loss: 2.9275
Iteration: 2488; Percent complete: 62.2%; Average loss: 3.0136
Iteration: 2489; Percent complete: 62.2%; Average loss: 2.9503
Iteration: 2490; Percent complete: 62.3%; Average loss: 3.2949
Iteration: 2491; Percent complete: 62.3%; Average loss: 3.0693
Iteration: 2492; Percent complete: 62.3%; Average loss: 3.1240
Iteration: 2493; Percent complete: 62.3%; Average loss: 2.7953
Iteration: 2494; Percent complete: 62.4%; Average loss: 3.0673
Iteration: 2495; Percent complete: 62.4%; Average loss: 3.0448
Iteration: 2496; Percent complete: 62.4%; Average loss: 3.1121
Iteration: 2497; Percent complete: 62.4%; Average loss: 3.3487
Iteration: 2498; Percent complete: 62.5%; Average loss: 3.0423
Iteration: 2499; Percent complete: 62.5%; Average loss: 2.9772
Iteration: 2500; Percent complete: 62.5%; Average loss: 3.1227
Iteration: 2501; Percent complete: 62.5%; Average loss: 3.0527
Iteration: 2502; Percent complete: 62.5%; Average loss: 2.6549
Iteration: 2503; Percent complete: 62.6%; Average loss: 3.1474
Iteration: 2504; Percent complete: 62.6%; Average loss: 2.8289
Iteration: 2505; Percent complete: 62.6%; Average loss: 2.9173
Iteration: 2506; Percent complete: 62.6%; Average loss: 3.2078
Iteration: 2507; Percent complete: 62.7%; Average loss: 2.9981
Iteration: 2508; Percent complete: 62.7%; Average loss: 3.1018
Iteration: 2509; Percent complete: 62.7%; Average loss: 2.8679
Iteration: 2510; Percent complete: 62.7%; Average loss: 2.8727
Iteration: 2511; Percent complete: 62.8%; Average loss: 2.9114
Iteration: 2512; Percent complete: 62.8%; Average loss: 2.8529
Iteration: 2513; Percent complete: 62.8%; Average loss: 2.9436
Iteration: 2514; Percent complete: 62.8%; Average loss: 2.9625
Iteration: 2515; Percent complete: 62.9%; Average loss: 3.0053
Iteration: 2516; Percent complete: 62.9%; Average loss: 3.1094
Iteration: 2517; Percent complete: 62.9%; Average loss: 2.8753
Iteration: 2518; Percent complete: 62.9%; Average loss: 3.0166
Iteration: 2519; Percent complete: 63.0%; Average loss: 2.8860
Iteration: 2520; Percent complete: 63.0%; Average loss: 3.0660
Iteration: 2521; Percent complete: 63.0%; Average loss: 3.1766
Iteration: 2522; Percent complete: 63.0%; Average loss: 3.3318
Iteration: 2523; Percent complete: 63.1%; Average loss: 3.1848
Iteration: 2524; Percent complete: 63.1%; Average loss: 3.1210
Iteration: 2525; Percent complete: 63.1%; Average loss: 3.0779
Iteration: 2526; Percent complete: 63.1%; Average loss: 2.8904
Iteration: 2527; Percent complete: 63.2%; Average loss: 2.8877
Iteration: 2528; Percent complete: 63.2%; Average loss: 3.1215
Iteration: 2529; Percent complete: 63.2%; Average loss: 3.1834
Iteration: 2530; Percent complete: 63.2%; Average loss: 3.1493
Iteration: 2531; Percent complete: 63.3%; Average loss: 3.1596
Iteration: 2532; Percent complete: 63.3%; Average loss: 2.9561
Iteration: 2533; Percent complete: 63.3%; Average loss: 3.0203
Iteration: 2534; Percent complete: 63.3%; Average loss: 3.1531
Iteration: 2535; Percent complete: 63.4%; Average loss: 2.9548
Iteration: 2536; Percent complete: 63.4%; Average loss: 3.1695
Iteration: 2537; Percent complete: 63.4%; Average loss: 3.0324
Iteration: 2538; Percent complete: 63.4%; Average loss: 2.9709
Iteration: 2539; Percent complete: 63.5%; Average loss: 3.0374
Iteration: 2540; Percent complete: 63.5%; Average loss: 3.1637
Iteration: 2541; Percent complete: 63.5%; Average loss: 2.7971
Iteration: 2542; Percent complete: 63.5%; Average loss: 3.2620
Iteration: 2543; Percent complete: 63.6%; Average loss: 2.9409
Iteration: 2544; Percent complete: 63.6%; Average loss: 3.0232
Iteration: 2545; Percent complete: 63.6%; Average loss: 3.0737
Iteration: 2546; Percent complete: 63.6%; Average loss: 3.1610
Iteration: 2547; Percent complete: 63.7%; Average loss: 2.9726
Iteration: 2548; Percent complete: 63.7%; Average loss: 3.2810
Iteration: 2549; Percent complete: 63.7%; Average loss: 2.8967
Iteration: 2550; Percent complete: 63.7%; Average loss: 3.0726
Iteration: 2551; Percent complete: 63.8%; Average loss: 2.8915
Iteration: 2552; Percent complete: 63.8%; Average loss: 2.7401
Iteration: 2553; Percent complete: 63.8%; Average loss: 3.0572
Iteration: 2554; Percent complete: 63.8%; Average loss: 2.9803
Iteration: 2555; Percent complete: 63.9%; Average loss: 2.9613
Iteration: 2556; Percent complete: 63.9%; Average loss: 3.0838
Iteration: 2557; Percent complete: 63.9%; Average loss: 2.8653
Iteration: 2558; Percent complete: 63.9%; Average loss: 2.9550
Iteration: 2559; Percent complete: 64.0%; Average loss: 2.9617
Iteration: 2560; Percent complete: 64.0%; Average loss: 3.1288
Iteration: 2561; Percent complete: 64.0%; Average loss: 2.8757
Iteration: 2562; Percent complete: 64.0%; Average loss: 2.9445
Iteration: 2563; Percent complete: 64.1%; Average loss: 3.0542
Iteration: 2564; Percent complete: 64.1%; Average loss: 2.9134
Iteration: 2565; Percent complete: 64.1%; Average loss: 2.9120
Iteration: 2566; Percent complete: 64.1%; Average loss: 3.1193
Iteration: 2567; Percent complete: 64.2%; Average loss: 2.7767
Iteration: 2568; Percent complete: 64.2%; Average loss: 3.0739
Iteration: 2569; Percent complete: 64.2%; Average loss: 3.0736
Iteration: 2570; Percent complete: 64.2%; Average loss: 3.0911
Iteration: 2571; Percent complete: 64.3%; Average loss: 3.0083
Iteration: 2572; Percent complete: 64.3%; Average loss: 3.0708
Iteration: 2573; Percent complete: 64.3%; Average loss: 2.8733
Iteration: 2574; Percent complete: 64.3%; Average loss: 2.7602
Iteration: 2575; Percent complete: 64.4%; Average loss: 3.1140
Iteration: 2576; Percent complete: 64.4%; Average loss: 2.8605
Iteration: 2577; Percent complete: 64.4%; Average loss: 3.0810
Iteration: 2578; Percent complete: 64.5%; Average loss: 3.0846
Iteration: 2579; Percent complete: 64.5%; Average loss: 2.9916
Iteration: 2580; Percent complete: 64.5%; Average loss: 2.9705
Iteration: 2581; Percent complete: 64.5%; Average loss: 2.9104
Iteration: 2582; Percent complete: 64.5%; Average loss: 2.9124
Iteration: 2583; Percent complete: 64.6%; Average loss: 3.3690
Iteration: 2584; Percent complete: 64.6%; Average loss: 3.0211
Iteration: 2585; Percent complete: 64.6%; Average loss: 3.0468
Iteration: 2586; Percent complete: 64.6%; Average loss: 2.8358
Iteration: 2587; Percent complete: 64.7%; Average loss: 3.0289
Iteration: 2588; Percent complete: 64.7%; Average loss: 3.0642
Iteration: 2589; Percent complete: 64.7%; Average loss: 2.7701
Iteration: 2590; Percent complete: 64.8%; Average loss: 3.0113
Iteration: 2591; Percent complete: 64.8%; Average loss: 2.8754
Iteration: 2592; Percent complete: 64.8%; Average loss: 2.9437
Iteration: 2593; Percent complete: 64.8%; Average loss: 2.8941
Iteration: 2594; Percent complete: 64.8%; Average loss: 2.8153
Iteration: 2595; Percent complete: 64.9%; Average loss: 3.1834
Iteration: 2596; Percent complete: 64.9%; Average loss: 2.8895
Iteration: 2597; Percent complete: 64.9%; Average loss: 3.0555
Iteration: 2598; Percent complete: 65.0%; Average loss: 3.1120
Iteration: 2599; Percent complete: 65.0%; Average loss: 3.1804
Iteration: 2600; Percent complete: 65.0%; Average loss: 2.9596
Iteration: 2601; Percent complete: 65.0%; Average loss: 2.9142
Iteration: 2602; Percent complete: 65.0%; Average loss: 2.9972
Iteration: 2603; Percent complete: 65.1%; Average loss: 2.7719
Iteration: 2604; Percent complete: 65.1%; Average loss: 3.1992
Iteration: 2605; Percent complete: 65.1%; Average loss: 2.8547
Iteration: 2606; Percent complete: 65.1%; Average loss: 3.1616
Iteration: 2607; Percent complete: 65.2%; Average loss: 2.9712
Iteration: 2608; Percent complete: 65.2%; Average loss: 2.9822
Iteration: 2609; Percent complete: 65.2%; Average loss: 2.9641
Iteration: 2610; Percent complete: 65.2%; Average loss: 3.0246
Iteration: 2611; Percent complete: 65.3%; Average loss: 2.8813
Iteration: 2612; Percent complete: 65.3%; Average loss: 3.0032
Iteration: 2613; Percent complete: 65.3%; Average loss: 2.7805
Iteration: 2614; Percent complete: 65.3%; Average loss: 2.9478
Iteration: 2615; Percent complete: 65.4%; Average loss: 2.8110
Iteration: 2616; Percent complete: 65.4%; Average loss: 2.8145
Iteration: 2617; Percent complete: 65.4%; Average loss: 2.8264
Iteration: 2618; Percent complete: 65.5%; Average loss: 3.1391
Iteration: 2619; Percent complete: 65.5%; Average loss: 3.0225
Iteration: 2620; Percent complete: 65.5%; Average loss: 3.0074
Iteration: 2621; Percent complete: 65.5%; Average loss: 2.9702
Iteration: 2622; Percent complete: 65.5%; Average loss: 2.9880
Iteration: 2623; Percent complete: 65.6%; Average loss: 2.9163
Iteration: 2624; Percent complete: 65.6%; Average loss: 2.7737
Iteration: 2625; Percent complete: 65.6%; Average loss: 3.0222
Iteration: 2626; Percent complete: 65.6%; Average loss: 2.8623
Iteration: 2627; Percent complete: 65.7%; Average loss: 2.7386
Iteration: 2628; Percent complete: 65.7%; Average loss: 3.0055
Iteration: 2629; Percent complete: 65.7%; Average loss: 2.9194
Iteration: 2630; Percent complete: 65.8%; Average loss: 3.0529
Iteration: 2631; Percent complete: 65.8%; Average loss: 3.1262
Iteration: 2632; Percent complete: 65.8%; Average loss: 2.9851
Iteration: 2633; Percent complete: 65.8%; Average loss: 2.7946
Iteration: 2634; Percent complete: 65.8%; Average loss: 2.7837
Iteration: 2635; Percent complete: 65.9%; Average loss: 3.0516
Iteration: 2636; Percent complete: 65.9%; Average loss: 3.0121
Iteration: 2637; Percent complete: 65.9%; Average loss: 3.1042
Iteration: 2638; Percent complete: 66.0%; Average loss: 3.0505
Iteration: 2639; Percent complete: 66.0%; Average loss: 2.9568
Iteration: 2640; Percent complete: 66.0%; Average loss: 2.9888
Iteration: 2641; Percent complete: 66.0%; Average loss: 2.8055
Iteration: 2642; Percent complete: 66.0%; Average loss: 2.9727
Iteration: 2643; Percent complete: 66.1%; Average loss: 3.0356
Iteration: 2644; Percent complete: 66.1%; Average loss: 3.0019
Iteration: 2645; Percent complete: 66.1%; Average loss: 3.1844
Iteration: 2646; Percent complete: 66.1%; Average loss: 2.9170
Iteration: 2647; Percent complete: 66.2%; Average loss: 2.9639
Iteration: 2648; Percent complete: 66.2%; Average loss: 3.0874
Iteration: 2649; Percent complete: 66.2%; Average loss: 3.2178
Iteration: 2650; Percent complete: 66.2%; Average loss: 2.8646
Iteration: 2651; Percent complete: 66.3%; Average loss: 2.8056
Iteration: 2652; Percent complete: 66.3%; Average loss: 2.8480
Iteration: 2653; Percent complete: 66.3%; Average loss: 2.9534
Iteration: 2654; Percent complete: 66.3%; Average loss: 3.0186
Iteration: 2655; Percent complete: 66.4%; Average loss: 3.0180
Iteration: 2656; Percent complete: 66.4%; Average loss: 3.1863
Iteration: 2657; Percent complete: 66.4%; Average loss: 2.8211
Iteration: 2658; Percent complete: 66.5%; Average loss: 3.1008
Iteration: 2659; Percent complete: 66.5%; Average loss: 2.8501
Iteration: 2660; Percent complete: 66.5%; Average loss: 3.1591
Iteration: 2661; Percent complete: 66.5%; Average loss: 2.7989
Iteration: 2662; Percent complete: 66.5%; Average loss: 3.0764
Iteration: 2663; Percent complete: 66.6%; Average loss: 3.0340
Iteration: 2664; Percent complete: 66.6%; Average loss: 2.9590
Iteration: 2665; Percent complete: 66.6%; Average loss: 3.1210
Iteration: 2666; Percent complete: 66.6%; Average loss: 2.8410
Iteration: 2667; Percent complete: 66.7%; Average loss: 2.8628
Iteration: 2668; Percent complete: 66.7%; Average loss: 2.7845
Iteration: 2669; Percent complete: 66.7%; Average loss: 3.0168
Iteration: 2670; Percent complete: 66.8%; Average loss: 3.2142
Iteration: 2671; Percent complete: 66.8%; Average loss: 2.8247
Iteration: 2672; Percent complete: 66.8%; Average loss: 3.0331
Iteration: 2673; Percent complete: 66.8%; Average loss: 2.8125
Iteration: 2674; Percent complete: 66.8%; Average loss: 3.1454
Iteration: 2675; Percent complete: 66.9%; Average loss: 3.0940
Iteration: 2676; Percent complete: 66.9%; Average loss: 2.9942
Iteration: 2677; Percent complete: 66.9%; Average loss: 2.9925
Iteration: 2678; Percent complete: 67.0%; Average loss: 3.0798
Iteration: 2679; Percent complete: 67.0%; Average loss: 2.9739
Iteration: 2680; Percent complete: 67.0%; Average loss: 3.0063
Iteration: 2681; Percent complete: 67.0%; Average loss: 2.9207
Iteration: 2682; Percent complete: 67.0%; Average loss: 3.0625
Iteration: 2683; Percent complete: 67.1%; Average loss: 2.8147
Iteration: 2684; Percent complete: 67.1%; Average loss: 2.7946
Iteration: 2685; Percent complete: 67.1%; Average loss: 2.8448
Iteration: 2686; Percent complete: 67.2%; Average loss: 2.8792
Iteration: 2687; Percent complete: 67.2%; Average loss: 3.0468
Iteration: 2688; Percent complete: 67.2%; Average loss: 3.2045
Iteration: 2689; Percent complete: 67.2%; Average loss: 2.9171
Iteration: 2690; Percent complete: 67.2%; Average loss: 3.0605
Iteration: 2691; Percent complete: 67.3%; Average loss: 2.7415
Iteration: 2692; Percent complete: 67.3%; Average loss: 3.1861
Iteration: 2693; Percent complete: 67.3%; Average loss: 2.9913
Iteration: 2694; Percent complete: 67.3%; Average loss: 2.9526
Iteration: 2695; Percent complete: 67.4%; Average loss: 3.0482
Iteration: 2696; Percent complete: 67.4%; Average loss: 3.0366
Iteration: 2697; Percent complete: 67.4%; Average loss: 2.8972
Iteration: 2698; Percent complete: 67.5%; Average loss: 2.9566
Iteration: 2699; Percent complete: 67.5%; Average loss: 3.0285
Iteration: 2700; Percent complete: 67.5%; Average loss: 3.0490
Iteration: 2701; Percent complete: 67.5%; Average loss: 3.0667
Iteration: 2702; Percent complete: 67.5%; Average loss: 2.8982
Iteration: 2703; Percent complete: 67.6%; Average loss: 2.9966
Iteration: 2704; Percent complete: 67.6%; Average loss: 2.9088
Iteration: 2705; Percent complete: 67.6%; Average loss: 2.9677
Iteration: 2706; Percent complete: 67.7%; Average loss: 3.1885
Iteration: 2707; Percent complete: 67.7%; Average loss: 3.0620
Iteration: 2708; Percent complete: 67.7%; Average loss: 2.8553
Iteration: 2709; Percent complete: 67.7%; Average loss: 2.6977
Iteration: 2710; Percent complete: 67.8%; Average loss: 3.2035
Iteration: 2711; Percent complete: 67.8%; Average loss: 2.7705
Iteration: 2712; Percent complete: 67.8%; Average loss: 3.1005
Iteration: 2713; Percent complete: 67.8%; Average loss: 2.9460
Iteration: 2714; Percent complete: 67.8%; Average loss: 3.0165
Iteration: 2715; Percent complete: 67.9%; Average loss: 2.9372
Iteration: 2716; Percent complete: 67.9%; Average loss: 3.0093
Iteration: 2717; Percent complete: 67.9%; Average loss: 2.7945
Iteration: 2718; Percent complete: 68.0%; Average loss: 2.9692
Iteration: 2719; Percent complete: 68.0%; Average loss: 2.9772
Iteration: 2720; Percent complete: 68.0%; Average loss: 3.0948
Iteration: 2721; Percent complete: 68.0%; Average loss: 3.3565
Iteration: 2722; Percent complete: 68.0%; Average loss: 2.9739
Iteration: 2723; Percent complete: 68.1%; Average loss: 3.1946
Iteration: 2724; Percent complete: 68.1%; Average loss: 3.0223
Iteration: 2725; Percent complete: 68.1%; Average loss: 3.1614
Iteration: 2726; Percent complete: 68.2%; Average loss: 2.8610
Iteration: 2727; Percent complete: 68.2%; Average loss: 2.9759
Iteration: 2728; Percent complete: 68.2%; Average loss: 2.7944
Iteration: 2729; Percent complete: 68.2%; Average loss: 2.9474
Iteration: 2730; Percent complete: 68.2%; Average loss: 2.8850
Iteration: 2731; Percent complete: 68.3%; Average loss: 2.9846
Iteration: 2732; Percent complete: 68.3%; Average loss: 3.0426
Iteration: 2733; Percent complete: 68.3%; Average loss: 3.1031
Iteration: 2734; Percent complete: 68.3%; Average loss: 2.8215
Iteration: 2735; Percent complete: 68.4%; Average loss: 2.9154
Iteration: 2736; Percent complete: 68.4%; Average loss: 2.8784
Iteration: 2737; Percent complete: 68.4%; Average loss: 2.9302
Iteration: 2738; Percent complete: 68.5%; Average loss: 2.7952
Iteration: 2739; Percent complete: 68.5%; Average loss: 3.0929
Iteration: 2740; Percent complete: 68.5%; Average loss: 3.0098
Iteration: 2741; Percent complete: 68.5%; Average loss: 3.0116
Iteration: 2742; Percent complete: 68.5%; Average loss: 3.0368
Iteration: 2743; Percent complete: 68.6%; Average loss: 2.9094
Iteration: 2744; Percent complete: 68.6%; Average loss: 2.9248
Iteration: 2745; Percent complete: 68.6%; Average loss: 2.9020
Iteration: 2746; Percent complete: 68.7%; Average loss: 3.0161
Iteration: 2747; Percent complete: 68.7%; Average loss: 2.9696
Iteration: 2748; Percent complete: 68.7%; Average loss: 2.9697
Iteration: 2749; Percent complete: 68.7%; Average loss: 2.8230
Iteration: 2750; Percent complete: 68.8%; Average loss: 3.0676
Iteration: 2751; Percent complete: 68.8%; Average loss: 3.0247
Iteration: 2752; Percent complete: 68.8%; Average loss: 2.8992
Iteration: 2753; Percent complete: 68.8%; Average loss: 2.8254
Iteration: 2754; Percent complete: 68.8%; Average loss: 3.0576
Iteration: 2755; Percent complete: 68.9%; Average loss: 3.1001
Iteration: 2756; Percent complete: 68.9%; Average loss: 2.9477
Iteration: 2757; Percent complete: 68.9%; Average loss: 2.9080
Iteration: 2758; Percent complete: 69.0%; Average loss: 2.9446
Iteration: 2759; Percent complete: 69.0%; Average loss: 3.1763
Iteration: 2760; Percent complete: 69.0%; Average loss: 2.6825
Iteration: 2761; Percent complete: 69.0%; Average loss: 2.8507
Iteration: 2762; Percent complete: 69.0%; Average loss: 2.9979
Iteration: 2763; Percent complete: 69.1%; Average loss: 2.6120
Iteration: 2764; Percent complete: 69.1%; Average loss: 2.9937
Iteration: 2765; Percent complete: 69.1%; Average loss: 2.7755
Iteration: 2766; Percent complete: 69.2%; Average loss: 3.0178
Iteration: 2767; Percent complete: 69.2%; Average loss: 2.8687
Iteration: 2768; Percent complete: 69.2%; Average loss: 3.2516
Iteration: 2769; Percent complete: 69.2%; Average loss: 2.6445
Iteration: 2770; Percent complete: 69.2%; Average loss: 2.6730
Iteration: 2771; Percent complete: 69.3%; Average loss: 2.7887
Iteration: 2772; Percent complete: 69.3%; Average loss: 3.0567
Iteration: 2773; Percent complete: 69.3%; Average loss: 3.3605
Iteration: 2774; Percent complete: 69.3%; Average loss: 2.7451
Iteration: 2775; Percent complete: 69.4%; Average loss: 3.2611
Iteration: 2776; Percent complete: 69.4%; Average loss: 2.9017
Iteration: 2777; Percent complete: 69.4%; Average loss: 2.9335
Iteration: 2778; Percent complete: 69.5%; Average loss: 3.0780
Iteration: 2779; Percent complete: 69.5%; Average loss: 2.8999
Iteration: 2780; Percent complete: 69.5%; Average loss: 3.1712
Iteration: 2781; Percent complete: 69.5%; Average loss: 2.9541
Iteration: 2782; Percent complete: 69.5%; Average loss: 2.9662
Iteration: 2783; Percent complete: 69.6%; Average loss: 2.9987
Iteration: 2784; Percent complete: 69.6%; Average loss: 3.0323
Iteration: 2785; Percent complete: 69.6%; Average loss: 2.9933
Iteration: 2786; Percent complete: 69.7%; Average loss: 3.0206
Iteration: 2787; Percent complete: 69.7%; Average loss: 3.0869
Iteration: 2788; Percent complete: 69.7%; Average loss: 2.9484
Iteration: 2789; Percent complete: 69.7%; Average loss: 3.0862
Iteration: 2790; Percent complete: 69.8%; Average loss: 2.8601
Iteration: 2791; Percent complete: 69.8%; Average loss: 2.7820
Iteration: 2792; Percent complete: 69.8%; Average loss: 3.0333
Iteration: 2793; Percent complete: 69.8%; Average loss: 3.0051
Iteration: 2794; Percent complete: 69.8%; Average loss: 3.2872
Iteration: 2795; Percent complete: 69.9%; Average loss: 3.0808
Iteration: 2796; Percent complete: 69.9%; Average loss: 2.9135
Iteration: 2797; Percent complete: 69.9%; Average loss: 2.8388
Iteration: 2798; Percent complete: 70.0%; Average loss: 2.9134
Iteration: 2799; Percent complete: 70.0%; Average loss: 3.1646
Iteration: 2800; Percent complete: 70.0%; Average loss: 2.9806
Iteration: 2801; Percent complete: 70.0%; Average loss: 2.7947
Iteration: 2802; Percent complete: 70.0%; Average loss: 2.8253
Iteration: 2803; Percent complete: 70.1%; Average loss: 3.2065
Iteration: 2804; Percent complete: 70.1%; Average loss: 3.0452
Iteration: 2805; Percent complete: 70.1%; Average loss: 3.2215
Iteration: 2806; Percent complete: 70.2%; Average loss: 2.9850
Iteration: 2807; Percent complete: 70.2%; Average loss: 2.9669
Iteration: 2808; Percent complete: 70.2%; Average loss: 2.7334
Iteration: 2809; Percent complete: 70.2%; Average loss: 3.1532
Iteration: 2810; Percent complete: 70.2%; Average loss: 2.9449
Iteration: 2811; Percent complete: 70.3%; Average loss: 2.9595
Iteration: 2812; Percent complete: 70.3%; Average loss: 2.9542
Iteration: 2813; Percent complete: 70.3%; Average loss: 2.8357
Iteration: 2814; Percent complete: 70.3%; Average loss: 2.7023
Iteration: 2815; Percent complete: 70.4%; Average loss: 3.0342
Iteration: 2816; Percent complete: 70.4%; Average loss: 2.9228
Iteration: 2817; Percent complete: 70.4%; Average loss: 2.9472
Iteration: 2818; Percent complete: 70.5%; Average loss: 3.0345
Iteration: 2819; Percent complete: 70.5%; Average loss: 2.7067
Iteration: 2820; Percent complete: 70.5%; Average loss: 3.1160
Iteration: 2821; Percent complete: 70.5%; Average loss: 2.7901
Iteration: 2822; Percent complete: 70.5%; Average loss: 2.9923
Iteration: 2823; Percent complete: 70.6%; Average loss: 2.8875
Iteration: 2824; Percent complete: 70.6%; Average loss: 2.7210
Iteration: 2825; Percent complete: 70.6%; Average loss: 2.9304
Iteration: 2826; Percent complete: 70.7%; Average loss: 2.8658
Iteration: 2827; Percent complete: 70.7%; Average loss: 3.0988
Iteration: 2828; Percent complete: 70.7%; Average loss: 2.9960
Iteration: 2829; Percent complete: 70.7%; Average loss: 3.1759
Iteration: 2830; Percent complete: 70.8%; Average loss: 3.0901
Iteration: 2831; Percent complete: 70.8%; Average loss: 3.0989
Iteration: 2832; Percent complete: 70.8%; Average loss: 2.9344
Iteration: 2833; Percent complete: 70.8%; Average loss: 3.0802
Iteration: 2834; Percent complete: 70.9%; Average loss: 2.9917
Iteration: 2835; Percent complete: 70.9%; Average loss: 2.7705
Iteration: 2836; Percent complete: 70.9%; Average loss: 2.9888
Iteration: 2837; Percent complete: 70.9%; Average loss: 3.0433
Iteration: 2838; Percent complete: 71.0%; Average loss: 2.8495
Iteration: 2839; Percent complete: 71.0%; Average loss: 2.8109
Iteration: 2840; Percent complete: 71.0%; Average loss: 2.9700
Iteration: 2841; Percent complete: 71.0%; Average loss: 3.1330
Iteration: 2842; Percent complete: 71.0%; Average loss: 2.9889
Iteration: 2843; Percent complete: 71.1%; Average loss: 2.9486
Iteration: 2844; Percent complete: 71.1%; Average loss: 2.7033
Iteration: 2845; Percent complete: 71.1%; Average loss: 3.0765
Iteration: 2846; Percent complete: 71.2%; Average loss: 2.9363
Iteration: 2847; Percent complete: 71.2%; Average loss: 3.0490
Iteration: 2848; Percent complete: 71.2%; Average loss: 3.1330
Iteration: 2849; Percent complete: 71.2%; Average loss: 3.1013
Iteration: 2850; Percent complete: 71.2%; Average loss: 3.0270
Iteration: 2851; Percent complete: 71.3%; Average loss: 3.2056
Iteration: 2852; Percent complete: 71.3%; Average loss: 2.9041
Iteration: 2853; Percent complete: 71.3%; Average loss: 2.7791
Iteration: 2854; Percent complete: 71.4%; Average loss: 3.3532
Iteration: 2855; Percent complete: 71.4%; Average loss: 2.9132
Iteration: 2856; Percent complete: 71.4%; Average loss: 2.8367
Iteration: 2857; Percent complete: 71.4%; Average loss: 2.8502
Iteration: 2858; Percent complete: 71.5%; Average loss: 2.8888
Iteration: 2859; Percent complete: 71.5%; Average loss: 2.8908
Iteration: 2860; Percent complete: 71.5%; Average loss: 3.0384
Iteration: 2861; Percent complete: 71.5%; Average loss: 2.7431
Iteration: 2862; Percent complete: 71.5%; Average loss: 3.0406
Iteration: 2863; Percent complete: 71.6%; Average loss: 2.8206
Iteration: 2864; Percent complete: 71.6%; Average loss: 2.9002
Iteration: 2865; Percent complete: 71.6%; Average loss: 2.7009
Iteration: 2866; Percent complete: 71.7%; Average loss: 2.8125
Iteration: 2867; Percent complete: 71.7%; Average loss: 2.8690
Iteration: 2868; Percent complete: 71.7%; Average loss: 3.0374
Iteration: 2869; Percent complete: 71.7%; Average loss: 3.0781
Iteration: 2870; Percent complete: 71.8%; Average loss: 2.8043
Iteration: 2871; Percent complete: 71.8%; Average loss: 2.9631
Iteration: 2872; Percent complete: 71.8%; Average loss: 3.0256
Iteration: 2873; Percent complete: 71.8%; Average loss: 2.6432
Iteration: 2874; Percent complete: 71.9%; Average loss: 3.0037
Iteration: 2875; Percent complete: 71.9%; Average loss: 3.1094
Iteration: 2876; Percent complete: 71.9%; Average loss: 3.0542
Iteration: 2877; Percent complete: 71.9%; Average loss: 2.9081
Iteration: 2878; Percent complete: 72.0%; Average loss: 2.9753
Iteration: 2879; Percent complete: 72.0%; Average loss: 2.9716
Iteration: 2880; Percent complete: 72.0%; Average loss: 3.0494
Iteration: 2881; Percent complete: 72.0%; Average loss: 2.8332
Iteration: 2882; Percent complete: 72.0%; Average loss: 2.9685
Iteration: 2883; Percent complete: 72.1%; Average loss: 2.9499
Iteration: 2884; Percent complete: 72.1%; Average loss: 3.1240
Iteration: 2885; Percent complete: 72.1%; Average loss: 3.0149
Iteration: 2886; Percent complete: 72.2%; Average loss: 2.6261
Iteration: 2887; Percent complete: 72.2%; Average loss: 2.9607
Iteration: 2888; Percent complete: 72.2%; Average loss: 2.8686
Iteration: 2889; Percent complete: 72.2%; Average loss: 2.8032
Iteration: 2890; Percent complete: 72.2%; Average loss: 3.1227
Iteration: 2891; Percent complete: 72.3%; Average loss: 2.9024
Iteration: 2892; Percent complete: 72.3%; Average loss: 2.6231
Iteration: 2893; Percent complete: 72.3%; Average loss: 3.0743
Iteration: 2894; Percent complete: 72.4%; Average loss: 2.9886
Iteration: 2895; Percent complete: 72.4%; Average loss: 2.8734
Iteration: 2896; Percent complete: 72.4%; Average loss: 2.9927
Iteration: 2897; Percent complete: 72.4%; Average loss: 3.0223
Iteration: 2898; Percent complete: 72.5%; Average loss: 2.9785
Iteration: 2899; Percent complete: 72.5%; Average loss: 2.9738
Iteration: 2900; Percent complete: 72.5%; Average loss: 2.9882
Iteration: 2901; Percent complete: 72.5%; Average loss: 3.2275
Iteration: 2902; Percent complete: 72.5%; Average loss: 3.2586
Iteration: 2903; Percent complete: 72.6%; Average loss: 2.8413
Iteration: 2904; Percent complete: 72.6%; Average loss: 2.9338
Iteration: 2905; Percent complete: 72.6%; Average loss: 2.7597
Iteration: 2906; Percent complete: 72.7%; Average loss: 2.9418
Iteration: 2907; Percent complete: 72.7%; Average loss: 2.8114
Iteration: 2908; Percent complete: 72.7%; Average loss: 2.7196
Iteration: 2909; Percent complete: 72.7%; Average loss: 2.8765
Iteration: 2910; Percent complete: 72.8%; Average loss: 2.7016
Iteration: 2911; Percent complete: 72.8%; Average loss: 3.1893
Iteration: 2912; Percent complete: 72.8%; Average loss: 3.0277
Iteration: 2913; Percent complete: 72.8%; Average loss: 3.0130
Iteration: 2914; Percent complete: 72.9%; Average loss: 3.0386
Iteration: 2915; Percent complete: 72.9%; Average loss: 2.7597
Iteration: 2916; Percent complete: 72.9%; Average loss: 2.9162
Iteration: 2917; Percent complete: 72.9%; Average loss: 2.9503
Iteration: 2918; Percent complete: 73.0%; Average loss: 2.8623
Iteration: 2919; Percent complete: 73.0%; Average loss: 2.9362
Iteration: 2920; Percent complete: 73.0%; Average loss: 2.8200
Iteration: 2921; Percent complete: 73.0%; Average loss: 3.1760
Iteration: 2922; Percent complete: 73.0%; Average loss: 2.9860
Iteration: 2923; Percent complete: 73.1%; Average loss: 2.8793
Iteration: 2924; Percent complete: 73.1%; Average loss: 2.9857
Iteration: 2925; Percent complete: 73.1%; Average loss: 3.1963
Iteration: 2926; Percent complete: 73.2%; Average loss: 2.8654
Iteration: 2927; Percent complete: 73.2%; Average loss: 2.8221
Iteration: 2928; Percent complete: 73.2%; Average loss: 2.8794
Iteration: 2929; Percent complete: 73.2%; Average loss: 2.8473
Iteration: 2930; Percent complete: 73.2%; Average loss: 3.0017
Iteration: 2931; Percent complete: 73.3%; Average loss: 2.7845
Iteration: 2932; Percent complete: 73.3%; Average loss: 2.7041
Iteration: 2933; Percent complete: 73.3%; Average loss: 2.9632
Iteration: 2934; Percent complete: 73.4%; Average loss: 2.9396
Iteration: 2935; Percent complete: 73.4%; Average loss: 2.9924
Iteration: 2936; Percent complete: 73.4%; Average loss: 3.0404
Iteration: 2937; Percent complete: 73.4%; Average loss: 2.7496
Iteration: 2938; Percent complete: 73.5%; Average loss: 2.8020
Iteration: 2939; Percent complete: 73.5%; Average loss: 2.8361
Iteration: 2940; Percent complete: 73.5%; Average loss: 2.9944
Iteration: 2941; Percent complete: 73.5%; Average loss: 3.1932
Iteration: 2942; Percent complete: 73.6%; Average loss: 2.7749
Iteration: 2943; Percent complete: 73.6%; Average loss: 2.7110
Iteration: 2944; Percent complete: 73.6%; Average loss: 2.7925
Iteration: 2945; Percent complete: 73.6%; Average loss: 2.7751
Iteration: 2946; Percent complete: 73.7%; Average loss: 2.8028
Iteration: 2947; Percent complete: 73.7%; Average loss: 2.9800
Iteration: 2948; Percent complete: 73.7%; Average loss: 2.8967
Iteration: 2949; Percent complete: 73.7%; Average loss: 2.7928
Iteration: 2950; Percent complete: 73.8%; Average loss: 2.8382
Iteration: 2951; Percent complete: 73.8%; Average loss: 2.5290
Iteration: 2952; Percent complete: 73.8%; Average loss: 2.7980
Iteration: 2953; Percent complete: 73.8%; Average loss: 2.8209
Iteration: 2954; Percent complete: 73.9%; Average loss: 2.8182
Iteration: 2955; Percent complete: 73.9%; Average loss: 2.8566
Iteration: 2956; Percent complete: 73.9%; Average loss: 3.0781
Iteration: 2957; Percent complete: 73.9%; Average loss: 2.8076
Iteration: 2958; Percent complete: 74.0%; Average loss: 2.9473
Iteration: 2959; Percent complete: 74.0%; Average loss: 2.8265
Iteration: 2960; Percent complete: 74.0%; Average loss: 2.7631
Iteration: 2961; Percent complete: 74.0%; Average loss: 3.0349
Iteration: 2962; Percent complete: 74.1%; Average loss: 2.9082
Iteration: 2963; Percent complete: 74.1%; Average loss: 2.9376
Iteration: 2964; Percent complete: 74.1%; Average loss: 2.6917
Iteration: 2965; Percent complete: 74.1%; Average loss: 2.7786
Iteration: 2966; Percent complete: 74.2%; Average loss: 2.7253
Iteration: 2967; Percent complete: 74.2%; Average loss: 2.9270
Iteration: 2968; Percent complete: 74.2%; Average loss: 2.8246
Iteration: 2969; Percent complete: 74.2%; Average loss: 2.7985
Iteration: 2970; Percent complete: 74.2%; Average loss: 2.6955
Iteration: 2971; Percent complete: 74.3%; Average loss: 3.0062
Iteration: 2972; Percent complete: 74.3%; Average loss: 2.8112
Iteration: 2973; Percent complete: 74.3%; Average loss: 2.4977
Iteration: 2974; Percent complete: 74.4%; Average loss: 2.8775
Iteration: 2975; Percent complete: 74.4%; Average loss: 2.9371
Iteration: 2976; Percent complete: 74.4%; Average loss: 3.0420
Iteration: 2977; Percent complete: 74.4%; Average loss: 3.1377
Iteration: 2978; Percent complete: 74.5%; Average loss: 2.9644
Iteration: 2979; Percent complete: 74.5%; Average loss: 2.8032
Iteration: 2980; Percent complete: 74.5%; Average loss: 2.7388
Iteration: 2981; Percent complete: 74.5%; Average loss: 3.1760
Iteration: 2982; Percent complete: 74.6%; Average loss: 2.9323
Iteration: 2983; Percent complete: 74.6%; Average loss: 2.8650
Iteration: 2984; Percent complete: 74.6%; Average loss: 2.7718
Iteration: 2985; Percent complete: 74.6%; Average loss: 2.8908
Iteration: 2986; Percent complete: 74.7%; Average loss: 3.1276
Iteration: 2987; Percent complete: 74.7%; Average loss: 2.9196
Iteration: 2988; Percent complete: 74.7%; Average loss: 2.8775
Iteration: 2989; Percent complete: 74.7%; Average loss: 2.8760
Iteration: 2990; Percent complete: 74.8%; Average loss: 2.8145
Iteration: 2991; Percent complete: 74.8%; Average loss: 3.1743
Iteration: 2992; Percent complete: 74.8%; Average loss: 2.8701
Iteration: 2993; Percent complete: 74.8%; Average loss: 3.2578
Iteration: 2994; Percent complete: 74.9%; Average loss: 2.7091
Iteration: 2995; Percent complete: 74.9%; Average loss: 2.8527
Iteration: 2996; Percent complete: 74.9%; Average loss: 2.8016
Iteration: 2997; Percent complete: 74.9%; Average loss: 2.9922
Iteration: 2998; Percent complete: 75.0%; Average loss: 2.9376
Iteration: 2999; Percent complete: 75.0%; Average loss: 2.9149
Iteration: 3000; Percent complete: 75.0%; Average loss: 2.6242
Iteration: 3001; Percent complete: 75.0%; Average loss: 2.7964
Iteration: 3002; Percent complete: 75.0%; Average loss: 2.6780
Iteration: 3003; Percent complete: 75.1%; Average loss: 2.9705
Iteration: 3004; Percent complete: 75.1%; Average loss: 2.6405
Iteration: 3005; Percent complete: 75.1%; Average loss: 2.9321
Iteration: 3006; Percent complete: 75.1%; Average loss: 2.8544
Iteration: 3007; Percent complete: 75.2%; Average loss: 2.7976
Iteration: 3008; Percent complete: 75.2%; Average loss: 2.8186
Iteration: 3009; Percent complete: 75.2%; Average loss: 2.9566
Iteration: 3010; Percent complete: 75.2%; Average loss: 2.6482
Iteration: 3011; Percent complete: 75.3%; Average loss: 2.6913
Iteration: 3012; Percent complete: 75.3%; Average loss: 2.6775
Iteration: 3013; Percent complete: 75.3%; Average loss: 3.1438
Iteration: 3014; Percent complete: 75.3%; Average loss: 2.8347
Iteration: 3015; Percent complete: 75.4%; Average loss: 2.8381
Iteration: 3016; Percent complete: 75.4%; Average loss: 2.6134
Iteration: 3017; Percent complete: 75.4%; Average loss: 2.6054
Iteration: 3018; Percent complete: 75.4%; Average loss: 2.8644
Iteration: 3019; Percent complete: 75.5%; Average loss: 2.8851
Iteration: 3020; Percent complete: 75.5%; Average loss: 2.9968
Iteration: 3021; Percent complete: 75.5%; Average loss: 3.0286
Iteration: 3022; Percent complete: 75.5%; Average loss: 2.9989
Iteration: 3023; Percent complete: 75.6%; Average loss: 2.9843
Iteration: 3024; Percent complete: 75.6%; Average loss: 3.0128
Iteration: 3025; Percent complete: 75.6%; Average loss: 2.9071
Iteration: 3026; Percent complete: 75.6%; Average loss: 2.8109
Iteration: 3027; Percent complete: 75.7%; Average loss: 2.7149
Iteration: 3028; Percent complete: 75.7%; Average loss: 2.9492
Iteration: 3029; Percent complete: 75.7%; Average loss: 2.9816
Iteration: 3030; Percent complete: 75.8%; Average loss: 2.8134
Iteration: 3031; Percent complete: 75.8%; Average loss: 2.7333
Iteration: 3032; Percent complete: 75.8%; Average loss: 3.0724
Iteration: 3033; Percent complete: 75.8%; Average loss: 2.9915
Iteration: 3034; Percent complete: 75.8%; Average loss: 2.7874
Iteration: 3035; Percent complete: 75.9%; Average loss: 2.8881
Iteration: 3036; Percent complete: 75.9%; Average loss: 2.6663
Iteration: 3037; Percent complete: 75.9%; Average loss: 2.9158
Iteration: 3038; Percent complete: 75.9%; Average loss: 3.0049
Iteration: 3039; Percent complete: 76.0%; Average loss: 2.9130
Iteration: 3040; Percent complete: 76.0%; Average loss: 2.8699
Iteration: 3041; Percent complete: 76.0%; Average loss: 3.0205
Iteration: 3042; Percent complete: 76.0%; Average loss: 2.6067
Iteration: 3043; Percent complete: 76.1%; Average loss: 2.8115
Iteration: 3044; Percent complete: 76.1%; Average loss: 2.9302
Iteration: 3045; Percent complete: 76.1%; Average loss: 2.9237
Iteration: 3046; Percent complete: 76.1%; Average loss: 2.7952
Iteration: 3047; Percent complete: 76.2%; Average loss: 2.8650
Iteration: 3048; Percent complete: 76.2%; Average loss: 2.9606
Iteration: 3049; Percent complete: 76.2%; Average loss: 3.0633
Iteration: 3050; Percent complete: 76.2%; Average loss: 2.6682
Iteration: 3051; Percent complete: 76.3%; Average loss: 3.0707
Iteration: 3052; Percent complete: 76.3%; Average loss: 2.8893
Iteration: 3053; Percent complete: 76.3%; Average loss: 3.0451
Iteration: 3054; Percent complete: 76.3%; Average loss: 2.8968
Iteration: 3055; Percent complete: 76.4%; Average loss: 2.9049
Iteration: 3056; Percent complete: 76.4%; Average loss: 2.9691
Iteration: 3057; Percent complete: 76.4%; Average loss: 2.7106
Iteration: 3058; Percent complete: 76.4%; Average loss: 2.7891
Iteration: 3059; Percent complete: 76.5%; Average loss: 2.9639
Iteration: 3060; Percent complete: 76.5%; Average loss: 3.0979
Iteration: 3061; Percent complete: 76.5%; Average loss: 3.1699
Iteration: 3062; Percent complete: 76.5%; Average loss: 2.7563
Iteration: 3063; Percent complete: 76.6%; Average loss: 2.8801
Iteration: 3064; Percent complete: 76.6%; Average loss: 3.0450
Iteration: 3065; Percent complete: 76.6%; Average loss: 2.7655
Iteration: 3066; Percent complete: 76.6%; Average loss: 2.7551
Iteration: 3067; Percent complete: 76.7%; Average loss: 3.1276
Iteration: 3068; Percent complete: 76.7%; Average loss: 3.0136
Iteration: 3069; Percent complete: 76.7%; Average loss: 2.8939
Iteration: 3070; Percent complete: 76.8%; Average loss: 2.6920
Iteration: 3071; Percent complete: 76.8%; Average loss: 2.6633
Iteration: 3072; Percent complete: 76.8%; Average loss: 2.8892
Iteration: 3073; Percent complete: 76.8%; Average loss: 2.6650
Iteration: 3074; Percent complete: 76.8%; Average loss: 3.0387
Iteration: 3075; Percent complete: 76.9%; Average loss: 2.7291
Iteration: 3076; Percent complete: 76.9%; Average loss: 2.9658
Iteration: 3077; Percent complete: 76.9%; Average loss: 2.7659
Iteration: 3078; Percent complete: 77.0%; Average loss: 3.0597
Iteration: 3079; Percent complete: 77.0%; Average loss: 2.6785
Iteration: 3080; Percent complete: 77.0%; Average loss: 3.0717
Iteration: 3081; Percent complete: 77.0%; Average loss: 2.8924
Iteration: 3082; Percent complete: 77.0%; Average loss: 2.8978
Iteration: 3083; Percent complete: 77.1%; Average loss: 2.7524
Iteration: 3084; Percent complete: 77.1%; Average loss: 3.0962
Iteration: 3085; Percent complete: 77.1%; Average loss: 2.5903
Iteration: 3086; Percent complete: 77.1%; Average loss: 3.0515
Iteration: 3087; Percent complete: 77.2%; Average loss: 2.8423
Iteration: 3088; Percent complete: 77.2%; Average loss: 2.7104
Iteration: 3089; Percent complete: 77.2%; Average loss: 2.7525
Iteration: 3090; Percent complete: 77.2%; Average loss: 2.7130
Iteration: 3091; Percent complete: 77.3%; Average loss: 2.9396
Iteration: 3092; Percent complete: 77.3%; Average loss: 2.8218
Iteration: 3093; Percent complete: 77.3%; Average loss: 2.7980
Iteration: 3094; Percent complete: 77.3%; Average loss: 2.9745
Iteration: 3095; Percent complete: 77.4%; Average loss: 2.8757
Iteration: 3096; Percent complete: 77.4%; Average loss: 2.8382
Iteration: 3097; Percent complete: 77.4%; Average loss: 2.6290
Iteration: 3098; Percent complete: 77.5%; Average loss: 2.6303
Iteration: 3099; Percent complete: 77.5%; Average loss: 2.8228
Iteration: 3100; Percent complete: 77.5%; Average loss: 2.8898
Iteration: 3101; Percent complete: 77.5%; Average loss: 2.7676
Iteration: 3102; Percent complete: 77.5%; Average loss: 2.5490
Iteration: 3103; Percent complete: 77.6%; Average loss: 2.8948
Iteration: 3104; Percent complete: 77.6%; Average loss: 3.0377
Iteration: 3105; Percent complete: 77.6%; Average loss: 2.8406
Iteration: 3106; Percent complete: 77.6%; Average loss: 2.8163
Iteration: 3107; Percent complete: 77.7%; Average loss: 2.7284
Iteration: 3108; Percent complete: 77.7%; Average loss: 3.0281
Iteration: 3109; Percent complete: 77.7%; Average loss: 2.7526
Iteration: 3110; Percent complete: 77.8%; Average loss: 2.5625
Iteration: 3111; Percent complete: 77.8%; Average loss: 2.6545
Iteration: 3112; Percent complete: 77.8%; Average loss: 2.8998
Iteration: 3113; Percent complete: 77.8%; Average loss: 3.0164
Iteration: 3114; Percent complete: 77.8%; Average loss: 2.8629
Iteration: 3115; Percent complete: 77.9%; Average loss: 2.8047
Iteration: 3116; Percent complete: 77.9%; Average loss: 2.7697
Iteration: 3117; Percent complete: 77.9%; Average loss: 2.9619
Iteration: 3118; Percent complete: 78.0%; Average loss: 2.9858
Iteration: 3119; Percent complete: 78.0%; Average loss: 3.2879
Iteration: 3120; Percent complete: 78.0%; Average loss: 2.7351
Iteration: 3121; Percent complete: 78.0%; Average loss: 2.7744
Iteration: 3122; Percent complete: 78.0%; Average loss: 3.0016
Iteration: 3123; Percent complete: 78.1%; Average loss: 2.7477
Iteration: 3124; Percent complete: 78.1%; Average loss: 2.7663
Iteration: 3125; Percent complete: 78.1%; Average loss: 2.7739
Iteration: 3126; Percent complete: 78.1%; Average loss: 2.7898
Iteration: 3127; Percent complete: 78.2%; Average loss: 2.9981
Iteration: 3128; Percent complete: 78.2%; Average loss: 3.0319
Iteration: 3129; Percent complete: 78.2%; Average loss: 2.8771
Iteration: 3130; Percent complete: 78.2%; Average loss: 2.7822
Iteration: 3131; Percent complete: 78.3%; Average loss: 3.0483
Iteration: 3132; Percent complete: 78.3%; Average loss: 2.8762
Iteration: 3133; Percent complete: 78.3%; Average loss: 2.9394
Iteration: 3134; Percent complete: 78.3%; Average loss: 2.6474
Iteration: 3135; Percent complete: 78.4%; Average loss: 2.7710
Iteration: 3136; Percent complete: 78.4%; Average loss: 2.8967
Iteration: 3137; Percent complete: 78.4%; Average loss: 3.1527
Iteration: 3138; Percent complete: 78.5%; Average loss: 2.8268
Iteration: 3139; Percent complete: 78.5%; Average loss: 2.9600
Iteration: 3140; Percent complete: 78.5%; Average loss: 2.9639
Iteration: 3141; Percent complete: 78.5%; Average loss: 2.8916
Iteration: 3142; Percent complete: 78.5%; Average loss: 2.5673
Iteration: 3143; Percent complete: 78.6%; Average loss: 2.9809
Iteration: 3144; Percent complete: 78.6%; Average loss: 2.9602
Iteration: 3145; Percent complete: 78.6%; Average loss: 3.0884
Iteration: 3146; Percent complete: 78.6%; Average loss: 3.0111
Iteration: 3147; Percent complete: 78.7%; Average loss: 2.8066
Iteration: 3148; Percent complete: 78.7%; Average loss: 3.0844
Iteration: 3149; Percent complete: 78.7%; Average loss: 2.7369
Iteration: 3150; Percent complete: 78.8%; Average loss: 3.0391
Iteration: 3151; Percent complete: 78.8%; Average loss: 2.8969
Iteration: 3152; Percent complete: 78.8%; Average loss: 2.8860
Iteration: 3153; Percent complete: 78.8%; Average loss: 2.6842
Iteration: 3154; Percent complete: 78.8%; Average loss: 2.6595
Iteration: 3155; Percent complete: 78.9%; Average loss: 2.7334
Iteration: 3156; Percent complete: 78.9%; Average loss: 2.7765
Iteration: 3157; Percent complete: 78.9%; Average loss: 2.6658
Iteration: 3158; Percent complete: 79.0%; Average loss: 2.6786
Iteration: 3159; Percent complete: 79.0%; Average loss: 2.8140
Iteration: 3160; Percent complete: 79.0%; Average loss: 3.0834
Iteration: 3161; Percent complete: 79.0%; Average loss: 2.8027
Iteration: 3162; Percent complete: 79.0%; Average loss: 2.6787
Iteration: 3163; Percent complete: 79.1%; Average loss: 3.1694
Iteration: 3164; Percent complete: 79.1%; Average loss: 3.0616
Iteration: 3165; Percent complete: 79.1%; Average loss: 2.7717
Iteration: 3166; Percent complete: 79.1%; Average loss: 2.7569
Iteration: 3167; Percent complete: 79.2%; Average loss: 2.7684
Iteration: 3168; Percent complete: 79.2%; Average loss: 3.1131
Iteration: 3169; Percent complete: 79.2%; Average loss: 2.6871
Iteration: 3170; Percent complete: 79.2%; Average loss: 2.7752
Iteration: 3171; Percent complete: 79.3%; Average loss: 2.9622
Iteration: 3172; Percent complete: 79.3%; Average loss: 2.7386
Iteration: 3173; Percent complete: 79.3%; Average loss: 2.7403
Iteration: 3174; Percent complete: 79.3%; Average loss: 2.9255
Iteration: 3175; Percent complete: 79.4%; Average loss: 2.6633
Iteration: 3176; Percent complete: 79.4%; Average loss: 2.6922
Iteration: 3177; Percent complete: 79.4%; Average loss: 2.7888
Iteration: 3178; Percent complete: 79.5%; Average loss: 2.6829
Iteration: 3179; Percent complete: 79.5%; Average loss: 2.7782
Iteration: 3180; Percent complete: 79.5%; Average loss: 2.8841
Iteration: 3181; Percent complete: 79.5%; Average loss: 2.7548
Iteration: 3182; Percent complete: 79.5%; Average loss: 2.8123
Iteration: 3183; Percent complete: 79.6%; Average loss: 2.8559
Iteration: 3184; Percent complete: 79.6%; Average loss: 3.0460
Iteration: 3185; Percent complete: 79.6%; Average loss: 2.7481
Iteration: 3186; Percent complete: 79.7%; Average loss: 2.9397
Iteration: 3187; Percent complete: 79.7%; Average loss: 2.9905
Iteration: 3188; Percent complete: 79.7%; Average loss: 2.8221
Iteration: 3189; Percent complete: 79.7%; Average loss: 2.9053
Iteration: 3190; Percent complete: 79.8%; Average loss: 3.0343
Iteration: 3191; Percent complete: 79.8%; Average loss: 2.7995
Iteration: 3192; Percent complete: 79.8%; Average loss: 2.8203
Iteration: 3193; Percent complete: 79.8%; Average loss: 2.9414
Iteration: 3194; Percent complete: 79.8%; Average loss: 2.6310
Iteration: 3195; Percent complete: 79.9%; Average loss: 2.7295
Iteration: 3196; Percent complete: 79.9%; Average loss: 2.8526
Iteration: 3197; Percent complete: 79.9%; Average loss: 2.7639
Iteration: 3198; Percent complete: 80.0%; Average loss: 2.9806
Iteration: 3199; Percent complete: 80.0%; Average loss: 2.7316
Iteration: 3200; Percent complete: 80.0%; Average loss: 2.7386
Iteration: 3201; Percent complete: 80.0%; Average loss: 2.5997
Iteration: 3202; Percent complete: 80.0%; Average loss: 2.6774
Iteration: 3203; Percent complete: 80.1%; Average loss: 2.7609
Iteration: 3204; Percent complete: 80.1%; Average loss: 2.9497
Iteration: 3205; Percent complete: 80.1%; Average loss: 2.9958
Iteration: 3206; Percent complete: 80.2%; Average loss: 2.8428
Iteration: 3207; Percent complete: 80.2%; Average loss: 2.8677
Iteration: 3208; Percent complete: 80.2%; Average loss: 3.0135
Iteration: 3209; Percent complete: 80.2%; Average loss: 2.9496
Iteration: 3210; Percent complete: 80.2%; Average loss: 2.8623
Iteration: 3211; Percent complete: 80.3%; Average loss: 2.7450
Iteration: 3212; Percent complete: 80.3%; Average loss: 2.9045
Iteration: 3213; Percent complete: 80.3%; Average loss: 2.6218
Iteration: 3214; Percent complete: 80.3%; Average loss: 2.6681
Iteration: 3215; Percent complete: 80.4%; Average loss: 3.0020
Iteration: 3216; Percent complete: 80.4%; Average loss: 2.7562
Iteration: 3217; Percent complete: 80.4%; Average loss: 2.9767
Iteration: 3218; Percent complete: 80.5%; Average loss: 2.8164
Iteration: 3219; Percent complete: 80.5%; Average loss: 2.9320
Iteration: 3220; Percent complete: 80.5%; Average loss: 2.8393
Iteration: 3221; Percent complete: 80.5%; Average loss: 3.1581
Iteration: 3222; Percent complete: 80.5%; Average loss: 3.0175
Iteration: 3223; Percent complete: 80.6%; Average loss: 2.8919
Iteration: 3224; Percent complete: 80.6%; Average loss: 2.7274
Iteration: 3225; Percent complete: 80.6%; Average loss: 3.1212
Iteration: 3226; Percent complete: 80.7%; Average loss: 2.9020
Iteration: 3227; Percent complete: 80.7%; Average loss: 3.2038
Iteration: 3228; Percent complete: 80.7%; Average loss: 2.7859
Iteration: 3229; Percent complete: 80.7%; Average loss: 2.6142
Iteration: 3230; Percent complete: 80.8%; Average loss: 2.8852
Iteration: 3231; Percent complete: 80.8%; Average loss: 2.7387
Iteration: 3232; Percent complete: 80.8%; Average loss: 2.7603
Iteration: 3233; Percent complete: 80.8%; Average loss: 2.9474
Iteration: 3234; Percent complete: 80.8%; Average loss: 2.7993
Iteration: 3235; Percent complete: 80.9%; Average loss: 2.8349
Iteration: 3236; Percent complete: 80.9%; Average loss: 2.5828
Iteration: 3237; Percent complete: 80.9%; Average loss: 2.7600
Iteration: 3238; Percent complete: 81.0%; Average loss: 2.6386
Iteration: 3239; Percent complete: 81.0%; Average loss: 2.7388
Iteration: 3240; Percent complete: 81.0%; Average loss: 2.8107
Iteration: 3241; Percent complete: 81.0%; Average loss: 3.0313
Iteration: 3242; Percent complete: 81.0%; Average loss: 2.8291
Iteration: 3243; Percent complete: 81.1%; Average loss: 2.7545
Iteration: 3244; Percent complete: 81.1%; Average loss: 2.9032
Iteration: 3245; Percent complete: 81.1%; Average loss: 2.7587
Iteration: 3246; Percent complete: 81.2%; Average loss: 2.4858
Iteration: 3247; Percent complete: 81.2%; Average loss: 2.9207
Iteration: 3248; Percent complete: 81.2%; Average loss: 2.9140
Iteration: 3249; Percent complete: 81.2%; Average loss: 2.8905
Iteration: 3250; Percent complete: 81.2%; Average loss: 2.9274
Iteration: 3251; Percent complete: 81.3%; Average loss: 2.6542
Iteration: 3252; Percent complete: 81.3%; Average loss: 2.7560
Iteration: 3253; Percent complete: 81.3%; Average loss: 2.7232
Iteration: 3254; Percent complete: 81.3%; Average loss: 2.8156
Iteration: 3255; Percent complete: 81.4%; Average loss: 2.7225
Iteration: 3256; Percent complete: 81.4%; Average loss: 2.6373
Iteration: 3257; Percent complete: 81.4%; Average loss: 2.5828
Iteration: 3258; Percent complete: 81.5%; Average loss: 2.8992
Iteration: 3259; Percent complete: 81.5%; Average loss: 2.8716
Iteration: 3260; Percent complete: 81.5%; Average loss: 2.9765
Iteration: 3261; Percent complete: 81.5%; Average loss: 2.8564
Iteration: 3262; Percent complete: 81.5%; Average loss: 2.9752
Iteration: 3263; Percent complete: 81.6%; Average loss: 2.7985
Iteration: 3264; Percent complete: 81.6%; Average loss: 2.6953
Iteration: 3265; Percent complete: 81.6%; Average loss: 2.5804
Iteration: 3266; Percent complete: 81.7%; Average loss: 2.7514
Iteration: 3267; Percent complete: 81.7%; Average loss: 2.7396
Iteration: 3268; Percent complete: 81.7%; Average loss: 2.8171
Iteration: 3269; Percent complete: 81.7%; Average loss: 2.6972
Iteration: 3270; Percent complete: 81.8%; Average loss: 2.9469
Iteration: 3271; Percent complete: 81.8%; Average loss: 2.8022
Iteration: 3272; Percent complete: 81.8%; Average loss: 2.8337
Iteration: 3273; Percent complete: 81.8%; Average loss: 2.7486
Iteration: 3274; Percent complete: 81.8%; Average loss: 2.8680
Iteration: 3275; Percent complete: 81.9%; Average loss: 2.7409
Iteration: 3276; Percent complete: 81.9%; Average loss: 2.6766
Iteration: 3277; Percent complete: 81.9%; Average loss: 2.6786
Iteration: 3278; Percent complete: 82.0%; Average loss: 2.7273
Iteration: 3279; Percent complete: 82.0%; Average loss: 3.0130
Iteration: 3280; Percent complete: 82.0%; Average loss: 2.8521
Iteration: 3281; Percent complete: 82.0%; Average loss: 2.6882
Iteration: 3282; Percent complete: 82.0%; Average loss: 2.9401
Iteration: 3283; Percent complete: 82.1%; Average loss: 2.7337
Iteration: 3284; Percent complete: 82.1%; Average loss: 2.7809
Iteration: 3285; Percent complete: 82.1%; Average loss: 2.8149
Iteration: 3286; Percent complete: 82.2%; Average loss: 3.0433
Iteration: 3287; Percent complete: 82.2%; Average loss: 2.7973
Iteration: 3288; Percent complete: 82.2%; Average loss: 2.8402
Iteration: 3289; Percent complete: 82.2%; Average loss: 2.6708
Iteration: 3290; Percent complete: 82.2%; Average loss: 3.0419
Iteration: 3291; Percent complete: 82.3%; Average loss: 2.7839
Iteration: 3292; Percent complete: 82.3%; Average loss: 2.9211
Iteration: 3293; Percent complete: 82.3%; Average loss: 2.9474
Iteration: 3294; Percent complete: 82.3%; Average loss: 3.0004
Iteration: 3295; Percent complete: 82.4%; Average loss: 2.5997
Iteration: 3296; Percent complete: 82.4%; Average loss: 2.8769
Iteration: 3297; Percent complete: 82.4%; Average loss: 2.8241
Iteration: 3298; Percent complete: 82.5%; Average loss: 2.8870
Iteration: 3299; Percent complete: 82.5%; Average loss: 2.7323
Iteration: 3300; Percent complete: 82.5%; Average loss: 2.6440
Iteration: 3301; Percent complete: 82.5%; Average loss: 2.7840
Iteration: 3302; Percent complete: 82.5%; Average loss: 2.6776
Iteration: 3303; Percent complete: 82.6%; Average loss: 2.8437
Iteration: 3304; Percent complete: 82.6%; Average loss: 2.9143
Iteration: 3305; Percent complete: 82.6%; Average loss: 3.0553
Iteration: 3306; Percent complete: 82.7%; Average loss: 2.7630
Iteration: 3307; Percent complete: 82.7%; Average loss: 2.7381
Iteration: 3308; Percent complete: 82.7%; Average loss: 2.6475
Iteration: 3309; Percent complete: 82.7%; Average loss: 2.6079
Iteration: 3310; Percent complete: 82.8%; Average loss: 2.8188
Iteration: 3311; Percent complete: 82.8%; Average loss: 2.8434
Iteration: 3312; Percent complete: 82.8%; Average loss: 2.9253
Iteration: 3313; Percent complete: 82.8%; Average loss: 2.6866
Iteration: 3314; Percent complete: 82.8%; Average loss: 2.6874
Iteration: 3315; Percent complete: 82.9%; Average loss: 2.4247
Iteration: 3316; Percent complete: 82.9%; Average loss: 2.8938
Iteration: 3317; Percent complete: 82.9%; Average loss: 2.7826
Iteration: 3318; Percent complete: 83.0%; Average loss: 2.8425
Iteration: 3319; Percent complete: 83.0%; Average loss: 2.5376
Iteration: 3320; Percent complete: 83.0%; Average loss: 3.1666
Iteration: 3321; Percent complete: 83.0%; Average loss: 2.7223
Iteration: 3322; Percent complete: 83.0%; Average loss: 2.6968
Iteration: 3323; Percent complete: 83.1%; Average loss: 2.9768
Iteration: 3324; Percent complete: 83.1%; Average loss: 2.8555
Iteration: 3325; Percent complete: 83.1%; Average loss: 2.6961
Iteration: 3326; Percent complete: 83.2%; Average loss: 2.7596
Iteration: 3327; Percent complete: 83.2%; Average loss: 2.7224
Iteration: 3328; Percent complete: 83.2%; Average loss: 2.8452
Iteration: 3329; Percent complete: 83.2%; Average loss: 2.7394
Iteration: 3330; Percent complete: 83.2%; Average loss: 2.9509
Iteration: 3331; Percent complete: 83.3%; Average loss: 2.7813
Iteration: 3332; Percent complete: 83.3%; Average loss: 2.7864
Iteration: 3333; Percent complete: 83.3%; Average loss: 2.8216
Iteration: 3334; Percent complete: 83.4%; Average loss: 2.7190
Iteration: 3335; Percent complete: 83.4%; Average loss: 2.6001
Iteration: 3336; Percent complete: 83.4%; Average loss: 2.6150
Iteration: 3337; Percent complete: 83.4%; Average loss: 3.0534
Iteration: 3338; Percent complete: 83.5%; Average loss: 2.6879
Iteration: 3339; Percent complete: 83.5%; Average loss: 2.7493
Iteration: 3340; Percent complete: 83.5%; Average loss: 2.4289
Iteration: 3341; Percent complete: 83.5%; Average loss: 2.8010
Iteration: 3342; Percent complete: 83.5%; Average loss: 2.9152
Iteration: 3343; Percent complete: 83.6%; Average loss: 2.6943
Iteration: 3344; Percent complete: 83.6%; Average loss: 2.8937
Iteration: 3345; Percent complete: 83.6%; Average loss: 2.5551
Iteration: 3346; Percent complete: 83.7%; Average loss: 2.7279
Iteration: 3347; Percent complete: 83.7%; Average loss: 2.9076
Iteration: 3348; Percent complete: 83.7%; Average loss: 2.8197
Iteration: 3349; Percent complete: 83.7%; Average loss: 2.6157
Iteration: 3350; Percent complete: 83.8%; Average loss: 2.6768
Iteration: 3351; Percent complete: 83.8%; Average loss: 2.7151
Iteration: 3352; Percent complete: 83.8%; Average loss: 2.8396
Iteration: 3353; Percent complete: 83.8%; Average loss: 2.7556
Iteration: 3354; Percent complete: 83.9%; Average loss: 2.7521
Iteration: 3355; Percent complete: 83.9%; Average loss: 2.6818
Iteration: 3356; Percent complete: 83.9%; Average loss: 3.1943
Iteration: 3357; Percent complete: 83.9%; Average loss: 2.7795
Iteration: 3358; Percent complete: 84.0%; Average loss: 2.8323
Iteration: 3359; Percent complete: 84.0%; Average loss: 2.8504
Iteration: 3360; Percent complete: 84.0%; Average loss: 2.9734
Iteration: 3361; Percent complete: 84.0%; Average loss: 2.7796
Iteration: 3362; Percent complete: 84.0%; Average loss: 2.6401
Iteration: 3363; Percent complete: 84.1%; Average loss: 2.6170
Iteration: 3364; Percent complete: 84.1%; Average loss: 2.8366
Iteration: 3365; Percent complete: 84.1%; Average loss: 2.6066
Iteration: 3366; Percent complete: 84.2%; Average loss: 2.7253
Iteration: 3367; Percent complete: 84.2%; Average loss: 2.7324
Iteration: 3368; Percent complete: 84.2%; Average loss: 2.5694
Iteration: 3369; Percent complete: 84.2%; Average loss: 2.8917
Iteration: 3370; Percent complete: 84.2%; Average loss: 3.1584
Iteration: 3371; Percent complete: 84.3%; Average loss: 2.5844
Iteration: 3372; Percent complete: 84.3%; Average loss: 2.7806
Iteration: 3373; Percent complete: 84.3%; Average loss: 2.7495
Iteration: 3374; Percent complete: 84.4%; Average loss: 2.5544
Iteration: 3375; Percent complete: 84.4%; Average loss: 2.6888
Iteration: 3376; Percent complete: 84.4%; Average loss: 2.5898
Iteration: 3377; Percent complete: 84.4%; Average loss: 3.1126
Iteration: 3378; Percent complete: 84.5%; Average loss: 2.9139
Iteration: 3379; Percent complete: 84.5%; Average loss: 2.8553
Iteration: 3380; Percent complete: 84.5%; Average loss: 2.7058
Iteration: 3381; Percent complete: 84.5%; Average loss: 2.7932
Iteration: 3382; Percent complete: 84.5%; Average loss: 2.9187
Iteration: 3383; Percent complete: 84.6%; Average loss: 2.6735
Iteration: 3384; Percent complete: 84.6%; Average loss: 2.7646
Iteration: 3385; Percent complete: 84.6%; Average loss: 2.9090
Iteration: 3386; Percent complete: 84.7%; Average loss: 2.9615
Iteration: 3387; Percent complete: 84.7%; Average loss: 2.8000
Iteration: 3388; Percent complete: 84.7%; Average loss: 2.7636
Iteration: 3389; Percent complete: 84.7%; Average loss: 2.8837
Iteration: 3390; Percent complete: 84.8%; Average loss: 2.9148
Iteration: 3391; Percent complete: 84.8%; Average loss: 2.7413
Iteration: 3392; Percent complete: 84.8%; Average loss: 2.6638
Iteration: 3393; Percent complete: 84.8%; Average loss: 2.8493
Iteration: 3394; Percent complete: 84.9%; Average loss: 2.6542
Iteration: 3395; Percent complete: 84.9%; Average loss: 2.5783
Iteration: 3396; Percent complete: 84.9%; Average loss: 2.7492
Iteration: 3397; Percent complete: 84.9%; Average loss: 2.6282
Iteration: 3398; Percent complete: 85.0%; Average loss: 2.8926
Iteration: 3399; Percent complete: 85.0%; Average loss: 2.7392
Iteration: 3400; Percent complete: 85.0%; Average loss: 2.6821
Iteration: 3401; Percent complete: 85.0%; Average loss: 2.8219
Iteration: 3402; Percent complete: 85.0%; Average loss: 2.7198
Iteration: 3403; Percent complete: 85.1%; Average loss: 2.6768
Iteration: 3404; Percent complete: 85.1%; Average loss: 2.7610
Iteration: 3405; Percent complete: 85.1%; Average loss: 2.7270
Iteration: 3406; Percent complete: 85.2%; Average loss: 2.7944
Iteration: 3407; Percent complete: 85.2%; Average loss: 2.7464
Iteration: 3408; Percent complete: 85.2%; Average loss: 2.5919
Iteration: 3409; Percent complete: 85.2%; Average loss: 2.7688
Iteration: 3410; Percent complete: 85.2%; Average loss: 2.6252
Iteration: 3411; Percent complete: 85.3%; Average loss: 2.5705
Iteration: 3412; Percent complete: 85.3%; Average loss: 2.6022
Iteration: 3413; Percent complete: 85.3%; Average loss: 2.5292
Iteration: 3414; Percent complete: 85.4%; Average loss: 2.7382
Iteration: 3415; Percent complete: 85.4%; Average loss: 2.8638
Iteration: 3416; Percent complete: 85.4%; Average loss: 2.8652
Iteration: 3417; Percent complete: 85.4%; Average loss: 2.8134
Iteration: 3418; Percent complete: 85.5%; Average loss: 2.8611
Iteration: 3419; Percent complete: 85.5%; Average loss: 2.7865
Iteration: 3420; Percent complete: 85.5%; Average loss: 2.6500
Iteration: 3421; Percent complete: 85.5%; Average loss: 2.9360
Iteration: 3422; Percent complete: 85.5%; Average loss: 2.7955
Iteration: 3423; Percent complete: 85.6%; Average loss: 2.6710
Iteration: 3424; Percent complete: 85.6%; Average loss: 2.4800
Iteration: 3425; Percent complete: 85.6%; Average loss: 2.7618
Iteration: 3426; Percent complete: 85.7%; Average loss: 2.5895
Iteration: 3427; Percent complete: 85.7%; Average loss: 2.8285
Iteration: 3428; Percent complete: 85.7%; Average loss: 2.7017
Iteration: 3429; Percent complete: 85.7%; Average loss: 2.7465
Iteration: 3430; Percent complete: 85.8%; Average loss: 2.5668
Iteration: 3431; Percent complete: 85.8%; Average loss: 2.7962
Iteration: 3432; Percent complete: 85.8%; Average loss: 2.9969
Iteration: 3433; Percent complete: 85.8%; Average loss: 2.8319
Iteration: 3434; Percent complete: 85.9%; Average loss: 2.7241
Iteration: 3435; Percent complete: 85.9%; Average loss: 2.7073
Iteration: 3436; Percent complete: 85.9%; Average loss: 2.6720
Iteration: 3437; Percent complete: 85.9%; Average loss: 2.9037
Iteration: 3438; Percent complete: 86.0%; Average loss: 2.7735
Iteration: 3439; Percent complete: 86.0%; Average loss: 2.7305
Iteration: 3440; Percent complete: 86.0%; Average loss: 2.5305
Iteration: 3441; Percent complete: 86.0%; Average loss: 2.8367
Iteration: 3442; Percent complete: 86.1%; Average loss: 2.7938
Iteration: 3443; Percent complete: 86.1%; Average loss: 2.6750
Iteration: 3444; Percent complete: 86.1%; Average loss: 2.9326
Iteration: 3445; Percent complete: 86.1%; Average loss: 2.8704
Iteration: 3446; Percent complete: 86.2%; Average loss: 2.8081
Iteration: 3447; Percent complete: 86.2%; Average loss: 2.8162
Iteration: 3448; Percent complete: 86.2%; Average loss: 2.8305
Iteration: 3449; Percent complete: 86.2%; Average loss: 2.7268
Iteration: 3450; Percent complete: 86.2%; Average loss: 2.7154
Iteration: 3451; Percent complete: 86.3%; Average loss: 2.7800
Iteration: 3452; Percent complete: 86.3%; Average loss: 2.8625
Iteration: 3453; Percent complete: 86.3%; Average loss: 2.6317
Iteration: 3454; Percent complete: 86.4%; Average loss: 2.7789
Iteration: 3455; Percent complete: 86.4%; Average loss: 2.7830
Iteration: 3456; Percent complete: 86.4%; Average loss: 2.7804
Iteration: 3457; Percent complete: 86.4%; Average loss: 2.8478
Iteration: 3458; Percent complete: 86.5%; Average loss: 2.8521
Iteration: 3459; Percent complete: 86.5%; Average loss: 2.9539
Iteration: 3460; Percent complete: 86.5%; Average loss: 2.5714
Iteration: 3461; Percent complete: 86.5%; Average loss: 2.8285
Iteration: 3462; Percent complete: 86.6%; Average loss: 2.7718
Iteration: 3463; Percent complete: 86.6%; Average loss: 2.9978
Iteration: 3464; Percent complete: 86.6%; Average loss: 2.9234
Iteration: 3465; Percent complete: 86.6%; Average loss: 2.5924
Iteration: 3466; Percent complete: 86.7%; Average loss: 2.9133
Iteration: 3467; Percent complete: 86.7%; Average loss: 2.8284
Iteration: 3468; Percent complete: 86.7%; Average loss: 2.8439
Iteration: 3469; Percent complete: 86.7%; Average loss: 2.8155
Iteration: 3470; Percent complete: 86.8%; Average loss: 3.0402
Iteration: 3471; Percent complete: 86.8%; Average loss: 2.8653
Iteration: 3472; Percent complete: 86.8%; Average loss: 2.6976
Iteration: 3473; Percent complete: 86.8%; Average loss: 2.7836
Iteration: 3474; Percent complete: 86.9%; Average loss: 2.8406
Iteration: 3475; Percent complete: 86.9%; Average loss: 2.8597
Iteration: 3476; Percent complete: 86.9%; Average loss: 2.8647
Iteration: 3477; Percent complete: 86.9%; Average loss: 2.7668
Iteration: 3478; Percent complete: 87.0%; Average loss: 2.7189
Iteration: 3479; Percent complete: 87.0%; Average loss: 2.7321
Iteration: 3480; Percent complete: 87.0%; Average loss: 2.7385
Iteration: 3481; Percent complete: 87.0%; Average loss: 2.6588
Iteration: 3482; Percent complete: 87.1%; Average loss: 2.6734
Iteration: 3483; Percent complete: 87.1%; Average loss: 2.9597
Iteration: 3484; Percent complete: 87.1%; Average loss: 2.7408
Iteration: 3485; Percent complete: 87.1%; Average loss: 2.9850
Iteration: 3486; Percent complete: 87.2%; Average loss: 2.5644
Iteration: 3487; Percent complete: 87.2%; Average loss: 2.7785
Iteration: 3488; Percent complete: 87.2%; Average loss: 2.5412
Iteration: 3489; Percent complete: 87.2%; Average loss: 2.9264
Iteration: 3490; Percent complete: 87.2%; Average loss: 2.5931
Iteration: 3491; Percent complete: 87.3%; Average loss: 2.6779
Iteration: 3492; Percent complete: 87.3%; Average loss: 2.5905
Iteration: 3493; Percent complete: 87.3%; Average loss: 2.5178
Iteration: 3494; Percent complete: 87.4%; Average loss: 2.6562
Iteration: 3495; Percent complete: 87.4%; Average loss: 2.6404
Iteration: 3496; Percent complete: 87.4%; Average loss: 2.6159
Iteration: 3497; Percent complete: 87.4%; Average loss: 2.7761
Iteration: 3498; Percent complete: 87.5%; Average loss: 2.6828
Iteration: 3499; Percent complete: 87.5%; Average loss: 2.6990
Iteration: 3500; Percent complete: 87.5%; Average loss: 2.5053
Iteration: 3501; Percent complete: 87.5%; Average loss: 2.8263
Iteration: 3502; Percent complete: 87.5%; Average loss: 2.8448
Iteration: 3503; Percent complete: 87.6%; Average loss: 2.9517
Iteration: 3504; Percent complete: 87.6%; Average loss: 2.7639
Iteration: 3505; Percent complete: 87.6%; Average loss: 2.5380
Iteration: 3506; Percent complete: 87.6%; Average loss: 2.6144
Iteration: 3507; Percent complete: 87.7%; Average loss: 2.7905
Iteration: 3508; Percent complete: 87.7%; Average loss: 2.6004
Iteration: 3509; Percent complete: 87.7%; Average loss: 2.6636
Iteration: 3510; Percent complete: 87.8%; Average loss: 2.9349
Iteration: 3511; Percent complete: 87.8%; Average loss: 2.7995
Iteration: 3512; Percent complete: 87.8%; Average loss: 2.7583
Iteration: 3513; Percent complete: 87.8%; Average loss: 2.6913
Iteration: 3514; Percent complete: 87.8%; Average loss: 2.9188
Iteration: 3515; Percent complete: 87.9%; Average loss: 2.6878
Iteration: 3516; Percent complete: 87.9%; Average loss: 3.0394
Iteration: 3517; Percent complete: 87.9%; Average loss: 2.8108
Iteration: 3518; Percent complete: 87.9%; Average loss: 2.7937
Iteration: 3519; Percent complete: 88.0%; Average loss: 2.7802
Iteration: 3520; Percent complete: 88.0%; Average loss: 2.6986
Iteration: 3521; Percent complete: 88.0%; Average loss: 2.6820
Iteration: 3522; Percent complete: 88.0%; Average loss: 2.6519
Iteration: 3523; Percent complete: 88.1%; Average loss: 2.6779
Iteration: 3524; Percent complete: 88.1%; Average loss: 2.4995
Iteration: 3525; Percent complete: 88.1%; Average loss: 2.8180
Iteration: 3526; Percent complete: 88.1%; Average loss: 2.5307
Iteration: 3527; Percent complete: 88.2%; Average loss: 2.9525
Iteration: 3528; Percent complete: 88.2%; Average loss: 2.6931
Iteration: 3529; Percent complete: 88.2%; Average loss: 2.6674
Iteration: 3530; Percent complete: 88.2%; Average loss: 2.6920
Iteration: 3531; Percent complete: 88.3%; Average loss: 2.6667
Iteration: 3532; Percent complete: 88.3%; Average loss: 2.6368
Iteration: 3533; Percent complete: 88.3%; Average loss: 2.8406
Iteration: 3534; Percent complete: 88.3%; Average loss: 2.9018
Iteration: 3535; Percent complete: 88.4%; Average loss: 2.8826
Iteration: 3536; Percent complete: 88.4%; Average loss: 2.6630
Iteration: 3537; Percent complete: 88.4%; Average loss: 2.7805
Iteration: 3538; Percent complete: 88.4%; Average loss: 2.8308
Iteration: 3539; Percent complete: 88.5%; Average loss: 2.8770
Iteration: 3540; Percent complete: 88.5%; Average loss: 2.8550
Iteration: 3541; Percent complete: 88.5%; Average loss: 2.6487
Iteration: 3542; Percent complete: 88.5%; Average loss: 2.7326
Iteration: 3543; Percent complete: 88.6%; Average loss: 2.7016
Iteration: 3544; Percent complete: 88.6%; Average loss: 2.7845
Iteration: 3545; Percent complete: 88.6%; Average loss: 2.9239
Iteration: 3546; Percent complete: 88.6%; Average loss: 2.8010
Iteration: 3547; Percent complete: 88.7%; Average loss: 2.8138
Iteration: 3548; Percent complete: 88.7%; Average loss: 2.8559
Iteration: 3549; Percent complete: 88.7%; Average loss: 2.4779
Iteration: 3550; Percent complete: 88.8%; Average loss: 2.6249
Iteration: 3551; Percent complete: 88.8%; Average loss: 2.8561
Iteration: 3552; Percent complete: 88.8%; Average loss: 2.6662
Iteration: 3553; Percent complete: 88.8%; Average loss: 2.8100
Iteration: 3554; Percent complete: 88.8%; Average loss: 2.7756
Iteration: 3555; Percent complete: 88.9%; Average loss: 2.6976
Iteration: 3556; Percent complete: 88.9%; Average loss: 2.7245
Iteration: 3557; Percent complete: 88.9%; Average loss: 2.8302
Iteration: 3558; Percent complete: 88.9%; Average loss: 2.7133
Iteration: 3559; Percent complete: 89.0%; Average loss: 2.7390
Iteration: 3560; Percent complete: 89.0%; Average loss: 2.6025
Iteration: 3561; Percent complete: 89.0%; Average loss: 2.8029
Iteration: 3562; Percent complete: 89.0%; Average loss: 3.0459
Iteration: 3563; Percent complete: 89.1%; Average loss: 2.6208
Iteration: 3564; Percent complete: 89.1%; Average loss: 2.6996
Iteration: 3565; Percent complete: 89.1%; Average loss: 2.6936
Iteration: 3566; Percent complete: 89.1%; Average loss: 2.8183
Iteration: 3567; Percent complete: 89.2%; Average loss: 2.8965
Iteration: 3568; Percent complete: 89.2%; Average loss: 2.5935
Iteration: 3569; Percent complete: 89.2%; Average loss: 2.9512
Iteration: 3570; Percent complete: 89.2%; Average loss: 2.6225
Iteration: 3571; Percent complete: 89.3%; Average loss: 2.7859
Iteration: 3572; Percent complete: 89.3%; Average loss: 2.9855
Iteration: 3573; Percent complete: 89.3%; Average loss: 2.7592
Iteration: 3574; Percent complete: 89.3%; Average loss: 2.5955
Iteration: 3575; Percent complete: 89.4%; Average loss: 2.6354
Iteration: 3576; Percent complete: 89.4%; Average loss: 2.7498
Iteration: 3577; Percent complete: 89.4%; Average loss: 2.5250
Iteration: 3578; Percent complete: 89.5%; Average loss: 2.7327
Iteration: 3579; Percent complete: 89.5%; Average loss: 2.7987
Iteration: 3580; Percent complete: 89.5%; Average loss: 2.6663
Iteration: 3581; Percent complete: 89.5%; Average loss: 2.8016
Iteration: 3582; Percent complete: 89.5%; Average loss: 2.6786
Iteration: 3583; Percent complete: 89.6%; Average loss: 2.8015
Iteration: 3584; Percent complete: 89.6%; Average loss: 2.8123
Iteration: 3585; Percent complete: 89.6%; Average loss: 2.5820
Iteration: 3586; Percent complete: 89.6%; Average loss: 2.8231
Iteration: 3587; Percent complete: 89.7%; Average loss: 2.7760
Iteration: 3588; Percent complete: 89.7%; Average loss: 2.8643
Iteration: 3589; Percent complete: 89.7%; Average loss: 2.6638
Iteration: 3590; Percent complete: 89.8%; Average loss: 2.5192
Iteration: 3591; Percent complete: 89.8%; Average loss: 2.8847
Iteration: 3592; Percent complete: 89.8%; Average loss: 2.8685
Iteration: 3593; Percent complete: 89.8%; Average loss: 2.6730
Iteration: 3594; Percent complete: 89.8%; Average loss: 2.9256
Iteration: 3595; Percent complete: 89.9%; Average loss: 2.8430
Iteration: 3596; Percent complete: 89.9%; Average loss: 3.2173
Iteration: 3597; Percent complete: 89.9%; Average loss: 2.8631
Iteration: 3598; Percent complete: 90.0%; Average loss: 2.6101
Iteration: 3599; Percent complete: 90.0%; Average loss: 2.4930
Iteration: 3600; Percent complete: 90.0%; Average loss: 2.7918
Iteration: 3601; Percent complete: 90.0%; Average loss: 2.7679
Iteration: 3602; Percent complete: 90.0%; Average loss: 2.4102
Iteration: 3603; Percent complete: 90.1%; Average loss: 2.5656
Iteration: 3604; Percent complete: 90.1%; Average loss: 2.7609
Iteration: 3605; Percent complete: 90.1%; Average loss: 2.6010
Iteration: 3606; Percent complete: 90.1%; Average loss: 2.7506
Iteration: 3607; Percent complete: 90.2%; Average loss: 2.6787
Iteration: 3608; Percent complete: 90.2%; Average loss: 2.7379
Iteration: 3609; Percent complete: 90.2%; Average loss: 2.9095
Iteration: 3610; Percent complete: 90.2%; Average loss: 2.7009
Iteration: 3611; Percent complete: 90.3%; Average loss: 2.6273
Iteration: 3612; Percent complete: 90.3%; Average loss: 2.8212
Iteration: 3613; Percent complete: 90.3%; Average loss: 2.4934
Iteration: 3614; Percent complete: 90.3%; Average loss: 2.7221
Iteration: 3615; Percent complete: 90.4%; Average loss: 2.6415
Iteration: 3616; Percent complete: 90.4%; Average loss: 2.7661
Iteration: 3617; Percent complete: 90.4%; Average loss: 2.5497
Iteration: 3618; Percent complete: 90.5%; Average loss: 2.8425
Iteration: 3619; Percent complete: 90.5%; Average loss: 2.7610
Iteration: 3620; Percent complete: 90.5%; Average loss: 2.7215
Iteration: 3621; Percent complete: 90.5%; Average loss: 2.4540
Iteration: 3622; Percent complete: 90.5%; Average loss: 2.5833
Iteration: 3623; Percent complete: 90.6%; Average loss: 2.8226
Iteration: 3624; Percent complete: 90.6%; Average loss: 2.8585
Iteration: 3625; Percent complete: 90.6%; Average loss: 2.8008
Iteration: 3626; Percent complete: 90.6%; Average loss: 2.6779
Iteration: 3627; Percent complete: 90.7%; Average loss: 2.7273
Iteration: 3628; Percent complete: 90.7%; Average loss: 2.8209
Iteration: 3629; Percent complete: 90.7%; Average loss: 2.8491
Iteration: 3630; Percent complete: 90.8%; Average loss: 2.7156
Iteration: 3631; Percent complete: 90.8%; Average loss: 2.5817
Iteration: 3632; Percent complete: 90.8%; Average loss: 2.7403
Iteration: 3633; Percent complete: 90.8%; Average loss: 2.8495
Iteration: 3634; Percent complete: 90.8%; Average loss: 2.5502
Iteration: 3635; Percent complete: 90.9%; Average loss: 2.6772
Iteration: 3636; Percent complete: 90.9%; Average loss: 2.8079
Iteration: 3637; Percent complete: 90.9%; Average loss: 2.7461
Iteration: 3638; Percent complete: 91.0%; Average loss: 2.8359
Iteration: 3639; Percent complete: 91.0%; Average loss: 2.8246
Iteration: 3640; Percent complete: 91.0%; Average loss: 2.6408
Iteration: 3641; Percent complete: 91.0%; Average loss: 2.6588
Iteration: 3642; Percent complete: 91.0%; Average loss: 2.7935
Iteration: 3643; Percent complete: 91.1%; Average loss: 2.6705
Iteration: 3644; Percent complete: 91.1%; Average loss: 2.6887
Iteration: 3645; Percent complete: 91.1%; Average loss: 2.5441
Iteration: 3646; Percent complete: 91.1%; Average loss: 2.7482
Iteration: 3647; Percent complete: 91.2%; Average loss: 2.7734
Iteration: 3648; Percent complete: 91.2%; Average loss: 2.6691
Iteration: 3649; Percent complete: 91.2%; Average loss: 3.0208
Iteration: 3650; Percent complete: 91.2%; Average loss: 2.6222
Iteration: 3651; Percent complete: 91.3%; Average loss: 2.5873
Iteration: 3652; Percent complete: 91.3%; Average loss: 2.5940
Iteration: 3653; Percent complete: 91.3%; Average loss: 2.7552
Iteration: 3654; Percent complete: 91.3%; Average loss: 2.5510
Iteration: 3655; Percent complete: 91.4%; Average loss: 2.7779
Iteration: 3656; Percent complete: 91.4%; Average loss: 2.5791
Iteration: 3657; Percent complete: 91.4%; Average loss: 2.6592
Iteration: 3658; Percent complete: 91.5%; Average loss: 2.6685
Iteration: 3659; Percent complete: 91.5%; Average loss: 2.7234
Iteration: 3660; Percent complete: 91.5%; Average loss: 2.5132
Iteration: 3661; Percent complete: 91.5%; Average loss: 2.7795
Iteration: 3662; Percent complete: 91.5%; Average loss: 2.7764
Iteration: 3663; Percent complete: 91.6%; Average loss: 2.6297
Iteration: 3664; Percent complete: 91.6%; Average loss: 2.8221
Iteration: 3665; Percent complete: 91.6%; Average loss: 2.5908
Iteration: 3666; Percent complete: 91.6%; Average loss: 2.7720
Iteration: 3667; Percent complete: 91.7%; Average loss: 2.7871
Iteration: 3668; Percent complete: 91.7%; Average loss: 2.6357
Iteration: 3669; Percent complete: 91.7%; Average loss: 2.5497
Iteration: 3670; Percent complete: 91.8%; Average loss: 2.8003
Iteration: 3671; Percent complete: 91.8%; Average loss: 2.5532
Iteration: 3672; Percent complete: 91.8%; Average loss: 2.6955
Iteration: 3673; Percent complete: 91.8%; Average loss: 2.6871
Iteration: 3674; Percent complete: 91.8%; Average loss: 2.8180
Iteration: 3675; Percent complete: 91.9%; Average loss: 2.7039
Iteration: 3676; Percent complete: 91.9%; Average loss: 2.4339
Iteration: 3677; Percent complete: 91.9%; Average loss: 2.6782
Iteration: 3678; Percent complete: 92.0%; Average loss: 2.7393
Iteration: 3679; Percent complete: 92.0%; Average loss: 2.7773
Iteration: 3680; Percent complete: 92.0%; Average loss: 2.7570
Iteration: 3681; Percent complete: 92.0%; Average loss: 2.5224
Iteration: 3682; Percent complete: 92.0%; Average loss: 2.6674
Iteration: 3683; Percent complete: 92.1%; Average loss: 2.7501
Iteration: 3684; Percent complete: 92.1%; Average loss: 2.6017
Iteration: 3685; Percent complete: 92.1%; Average loss: 2.7862
Iteration: 3686; Percent complete: 92.2%; Average loss: 2.6591
Iteration: 3687; Percent complete: 92.2%; Average loss: 2.8077
Iteration: 3688; Percent complete: 92.2%; Average loss: 2.6913
Iteration: 3689; Percent complete: 92.2%; Average loss: 2.6811
Iteration: 3690; Percent complete: 92.2%; Average loss: 2.5934
Iteration: 3691; Percent complete: 92.3%; Average loss: 2.9954
Iteration: 3692; Percent complete: 92.3%; Average loss: 2.4964
Iteration: 3693; Percent complete: 92.3%; Average loss: 2.7288
Iteration: 3694; Percent complete: 92.3%; Average loss: 2.4979
Iteration: 3695; Percent complete: 92.4%; Average loss: 2.5191
Iteration: 3696; Percent complete: 92.4%; Average loss: 2.6190
Iteration: 3697; Percent complete: 92.4%; Average loss: 2.6915
Iteration: 3698; Percent complete: 92.5%; Average loss: 2.8198
Iteration: 3699; Percent complete: 92.5%; Average loss: 2.9990
Iteration: 3700; Percent complete: 92.5%; Average loss: 2.7907
Iteration: 3701; Percent complete: 92.5%; Average loss: 2.6429
Iteration: 3702; Percent complete: 92.5%; Average loss: 2.4627
Iteration: 3703; Percent complete: 92.6%; Average loss: 2.7007
Iteration: 3704; Percent complete: 92.6%; Average loss: 2.5672
Iteration: 3705; Percent complete: 92.6%; Average loss: 2.8261
Iteration: 3706; Percent complete: 92.7%; Average loss: 2.6466
Iteration: 3707; Percent complete: 92.7%; Average loss: 2.6348
Iteration: 3708; Percent complete: 92.7%; Average loss: 2.8244
Iteration: 3709; Percent complete: 92.7%; Average loss: 2.7529
Iteration: 3710; Percent complete: 92.8%; Average loss: 2.4966
Iteration: 3711; Percent complete: 92.8%; Average loss: 2.7310
Iteration: 3712; Percent complete: 92.8%; Average loss: 2.6197
Iteration: 3713; Percent complete: 92.8%; Average loss: 2.8724
Iteration: 3714; Percent complete: 92.8%; Average loss: 2.7668
Iteration: 3715; Percent complete: 92.9%; Average loss: 2.8070
Iteration: 3716; Percent complete: 92.9%; Average loss: 2.5632
Iteration: 3717; Percent complete: 92.9%; Average loss: 2.7299
Iteration: 3718; Percent complete: 93.0%; Average loss: 2.8199
Iteration: 3719; Percent complete: 93.0%; Average loss: 2.8979
Iteration: 3720; Percent complete: 93.0%; Average loss: 2.6347
Iteration: 3721; Percent complete: 93.0%; Average loss: 2.8335
Iteration: 3722; Percent complete: 93.0%; Average loss: 2.7110
Iteration: 3723; Percent complete: 93.1%; Average loss: 2.5592
Iteration: 3724; Percent complete: 93.1%; Average loss: 2.8761
Iteration: 3725; Percent complete: 93.1%; Average loss: 2.6474
Iteration: 3726; Percent complete: 93.2%; Average loss: 2.7088
Iteration: 3727; Percent complete: 93.2%; Average loss: 2.6295
Iteration: 3728; Percent complete: 93.2%; Average loss: 2.8269
Iteration: 3729; Percent complete: 93.2%; Average loss: 2.7469
Iteration: 3730; Percent complete: 93.2%; Average loss: 2.6272
Iteration: 3731; Percent complete: 93.3%; Average loss: 2.7281
Iteration: 3732; Percent complete: 93.3%; Average loss: 2.6917
Iteration: 3733; Percent complete: 93.3%; Average loss: 2.4558
Iteration: 3734; Percent complete: 93.3%; Average loss: 2.6535
Iteration: 3735; Percent complete: 93.4%; Average loss: 2.6433
Iteration: 3736; Percent complete: 93.4%; Average loss: 2.7229
Iteration: 3737; Percent complete: 93.4%; Average loss: 2.6625
Iteration: 3738; Percent complete: 93.5%; Average loss: 2.5508
Iteration: 3739; Percent complete: 93.5%; Average loss: 2.6513
Iteration: 3740; Percent complete: 93.5%; Average loss: 2.8346
Iteration: 3741; Percent complete: 93.5%; Average loss: 2.6162
Iteration: 3742; Percent complete: 93.5%; Average loss: 2.5286
Iteration: 3743; Percent complete: 93.6%; Average loss: 2.9646
Iteration: 3744; Percent complete: 93.6%; Average loss: 2.6915
Iteration: 3745; Percent complete: 93.6%; Average loss: 2.5408
Iteration: 3746; Percent complete: 93.7%; Average loss: 2.6223
Iteration: 3747; Percent complete: 93.7%; Average loss: 2.5957
Iteration: 3748; Percent complete: 93.7%; Average loss: 2.8091
Iteration: 3749; Percent complete: 93.7%; Average loss: 2.5725
Iteration: 3750; Percent complete: 93.8%; Average loss: 2.5526
Iteration: 3751; Percent complete: 93.8%; Average loss: 2.7900
Iteration: 3752; Percent complete: 93.8%; Average loss: 2.7525
Iteration: 3753; Percent complete: 93.8%; Average loss: 2.6860
Iteration: 3754; Percent complete: 93.8%; Average loss: 2.9896
Iteration: 3755; Percent complete: 93.9%; Average loss: 2.6640
Iteration: 3756; Percent complete: 93.9%; Average loss: 2.7394
Iteration: 3757; Percent complete: 93.9%; Average loss: 2.5573
Iteration: 3758; Percent complete: 94.0%; Average loss: 2.6956
Iteration: 3759; Percent complete: 94.0%; Average loss: 2.6676
Iteration: 3760; Percent complete: 94.0%; Average loss: 2.7583
Iteration: 3761; Percent complete: 94.0%; Average loss: 2.6454
Iteration: 3762; Percent complete: 94.0%; Average loss: 2.4432
Iteration: 3763; Percent complete: 94.1%; Average loss: 2.5405
Iteration: 3764; Percent complete: 94.1%; Average loss: 2.7911
Iteration: 3765; Percent complete: 94.1%; Average loss: 2.4608
Iteration: 3766; Percent complete: 94.2%; Average loss: 2.6099
Iteration: 3767; Percent complete: 94.2%; Average loss: 2.8247
Iteration: 3768; Percent complete: 94.2%; Average loss: 2.7472
Iteration: 3769; Percent complete: 94.2%; Average loss: 2.7803
Iteration: 3770; Percent complete: 94.2%; Average loss: 2.7128
Iteration: 3771; Percent complete: 94.3%; Average loss: 2.6855
Iteration: 3772; Percent complete: 94.3%; Average loss: 2.6182
Iteration: 3773; Percent complete: 94.3%; Average loss: 2.4629
Iteration: 3774; Percent complete: 94.3%; Average loss: 2.6807
Iteration: 3775; Percent complete: 94.4%; Average loss: 2.7774
Iteration: 3776; Percent complete: 94.4%; Average loss: 2.6394
Iteration: 3777; Percent complete: 94.4%; Average loss: 2.6097
Iteration: 3778; Percent complete: 94.5%; Average loss: 2.5608
Iteration: 3779; Percent complete: 94.5%; Average loss: 2.8561
Iteration: 3780; Percent complete: 94.5%; Average loss: 2.8598
Iteration: 3781; Percent complete: 94.5%; Average loss: 2.6363
Iteration: 3782; Percent complete: 94.5%; Average loss: 2.6629
Iteration: 3783; Percent complete: 94.6%; Average loss: 2.6383
Iteration: 3784; Percent complete: 94.6%; Average loss: 2.6218
Iteration: 3785; Percent complete: 94.6%; Average loss: 2.5559
Iteration: 3786; Percent complete: 94.7%; Average loss: 2.8126
Iteration: 3787; Percent complete: 94.7%; Average loss: 2.6917
Iteration: 3788; Percent complete: 94.7%; Average loss: 2.4148
Iteration: 3789; Percent complete: 94.7%; Average loss: 2.7768
Iteration: 3790; Percent complete: 94.8%; Average loss: 2.6128
Iteration: 3791; Percent complete: 94.8%; Average loss: 2.7527
Iteration: 3792; Percent complete: 94.8%; Average loss: 2.7272
Iteration: 3793; Percent complete: 94.8%; Average loss: 2.6603
Iteration: 3794; Percent complete: 94.8%; Average loss: 2.5739
Iteration: 3795; Percent complete: 94.9%; Average loss: 2.5993
Iteration: 3796; Percent complete: 94.9%; Average loss: 2.3996
Iteration: 3797; Percent complete: 94.9%; Average loss: 2.6524
Iteration: 3798; Percent complete: 95.0%; Average loss: 2.4585
Iteration: 3799; Percent complete: 95.0%; Average loss: 2.7486
Iteration: 3800; Percent complete: 95.0%; Average loss: 2.7671
Iteration: 3801; Percent complete: 95.0%; Average loss: 2.8356
Iteration: 3802; Percent complete: 95.0%; Average loss: 2.7340
Iteration: 3803; Percent complete: 95.1%; Average loss: 2.4723
Iteration: 3804; Percent complete: 95.1%; Average loss: 2.6206
Iteration: 3805; Percent complete: 95.1%; Average loss: 2.7049
Iteration: 3806; Percent complete: 95.2%; Average loss: 2.6044
Iteration: 3807; Percent complete: 95.2%; Average loss: 2.7898
Iteration: 3808; Percent complete: 95.2%; Average loss: 2.6858
Iteration: 3809; Percent complete: 95.2%; Average loss: 2.7191
Iteration: 3810; Percent complete: 95.2%; Average loss: 2.6715
Iteration: 3811; Percent complete: 95.3%; Average loss: 2.6553
Iteration: 3812; Percent complete: 95.3%; Average loss: 2.6447
Iteration: 3813; Percent complete: 95.3%; Average loss: 2.6492
Iteration: 3814; Percent complete: 95.3%; Average loss: 2.5205
Iteration: 3815; Percent complete: 95.4%; Average loss: 2.8394
Iteration: 3816; Percent complete: 95.4%; Average loss: 2.7275
Iteration: 3817; Percent complete: 95.4%; Average loss: 2.6907
Iteration: 3818; Percent complete: 95.5%; Average loss: 2.5662
Iteration: 3819; Percent complete: 95.5%; Average loss: 2.4524
Iteration: 3820; Percent complete: 95.5%; Average loss: 2.8430
Iteration: 3821; Percent complete: 95.5%; Average loss: 2.6837
Iteration: 3822; Percent complete: 95.5%; Average loss: 2.4702
Iteration: 3823; Percent complete: 95.6%; Average loss: 2.5644
Iteration: 3824; Percent complete: 95.6%; Average loss: 2.5607
Iteration: 3825; Percent complete: 95.6%; Average loss: 2.5682
Iteration: 3826; Percent complete: 95.7%; Average loss: 2.6211
Iteration: 3827; Percent complete: 95.7%; Average loss: 2.6655
Iteration: 3828; Percent complete: 95.7%; Average loss: 2.7223
Iteration: 3829; Percent complete: 95.7%; Average loss: 2.6346
Iteration: 3830; Percent complete: 95.8%; Average loss: 2.5789
Iteration: 3831; Percent complete: 95.8%; Average loss: 2.5225
Iteration: 3832; Percent complete: 95.8%; Average loss: 2.6177
Iteration: 3833; Percent complete: 95.8%; Average loss: 2.7631
Iteration: 3834; Percent complete: 95.9%; Average loss: 2.7497
Iteration: 3835; Percent complete: 95.9%; Average loss: 2.6593
Iteration: 3836; Percent complete: 95.9%; Average loss: 2.6897
Iteration: 3837; Percent complete: 95.9%; Average loss: 2.4183
Iteration: 3838; Percent complete: 96.0%; Average loss: 2.4601
Iteration: 3839; Percent complete: 96.0%; Average loss: 2.5294
Iteration: 3840; Percent complete: 96.0%; Average loss: 2.5812
Iteration: 3841; Percent complete: 96.0%; Average loss: 2.6926
Iteration: 3842; Percent complete: 96.0%; Average loss: 2.5171
Iteration: 3843; Percent complete: 96.1%; Average loss: 2.5500
Iteration: 3844; Percent complete: 96.1%; Average loss: 2.6995
Iteration: 3845; Percent complete: 96.1%; Average loss: 2.5309
Iteration: 3846; Percent complete: 96.2%; Average loss: 2.8408
Iteration: 3847; Percent complete: 96.2%; Average loss: 2.7136
Iteration: 3848; Percent complete: 96.2%; Average loss: 2.4924
Iteration: 3849; Percent complete: 96.2%; Average loss: 2.6366
Iteration: 3850; Percent complete: 96.2%; Average loss: 2.7409
Iteration: 3851; Percent complete: 96.3%; Average loss: 2.3557
Iteration: 3852; Percent complete: 96.3%; Average loss: 2.5590
Iteration: 3853; Percent complete: 96.3%; Average loss: 2.6891
Iteration: 3854; Percent complete: 96.4%; Average loss: 2.6093
Iteration: 3855; Percent complete: 96.4%; Average loss: 2.5314
Iteration: 3856; Percent complete: 96.4%; Average loss: 2.7210
Iteration: 3857; Percent complete: 96.4%; Average loss: 2.9012
Iteration: 3858; Percent complete: 96.5%; Average loss: 2.5196
Iteration: 3859; Percent complete: 96.5%; Average loss: 2.7154
Iteration: 3860; Percent complete: 96.5%; Average loss: 2.5493
Iteration: 3861; Percent complete: 96.5%; Average loss: 2.7869
Iteration: 3862; Percent complete: 96.5%; Average loss: 2.6262
Iteration: 3863; Percent complete: 96.6%; Average loss: 2.6623
Iteration: 3864; Percent complete: 96.6%; Average loss: 2.6769
Iteration: 3865; Percent complete: 96.6%; Average loss: 2.7249
Iteration: 3866; Percent complete: 96.7%; Average loss: 2.6612
Iteration: 3867; Percent complete: 96.7%; Average loss: 2.7216
Iteration: 3868; Percent complete: 96.7%; Average loss: 2.4095
Iteration: 3869; Percent complete: 96.7%; Average loss: 2.8086
Iteration: 3870; Percent complete: 96.8%; Average loss: 2.6507
Iteration: 3871; Percent complete: 96.8%; Average loss: 2.6173
Iteration: 3872; Percent complete: 96.8%; Average loss: 2.7212
Iteration: 3873; Percent complete: 96.8%; Average loss: 2.5248
Iteration: 3874; Percent complete: 96.9%; Average loss: 2.7212
Iteration: 3875; Percent complete: 96.9%; Average loss: 2.5622
Iteration: 3876; Percent complete: 96.9%; Average loss: 2.6034
Iteration: 3877; Percent complete: 96.9%; Average loss: 2.6369
Iteration: 3878; Percent complete: 97.0%; Average loss: 2.7819
Iteration: 3879; Percent complete: 97.0%; Average loss: 2.5877
Iteration: 3880; Percent complete: 97.0%; Average loss: 2.6774
Iteration: 3881; Percent complete: 97.0%; Average loss: 2.8616
Iteration: 3882; Percent complete: 97.0%; Average loss: 2.7539
Iteration: 3883; Percent complete: 97.1%; Average loss: 2.7085
Iteration: 3884; Percent complete: 97.1%; Average loss: 2.5687
Iteration: 3885; Percent complete: 97.1%; Average loss: 2.6336
Iteration: 3886; Percent complete: 97.2%; Average loss: 2.6069
Iteration: 3887; Percent complete: 97.2%; Average loss: 2.6985
Iteration: 3888; Percent complete: 97.2%; Average loss: 2.7057
Iteration: 3889; Percent complete: 97.2%; Average loss: 2.6469
Iteration: 3890; Percent complete: 97.2%; Average loss: 2.6663
Iteration: 3891; Percent complete: 97.3%; Average loss: 2.5523
Iteration: 3892; Percent complete: 97.3%; Average loss: 2.5193
Iteration: 3893; Percent complete: 97.3%; Average loss: 2.5325
Iteration: 3894; Percent complete: 97.4%; Average loss: 2.5272
Iteration: 3895; Percent complete: 97.4%; Average loss: 2.7119
Iteration: 3896; Percent complete: 97.4%; Average loss: 2.7157
Iteration: 3897; Percent complete: 97.4%; Average loss: 2.5842
Iteration: 3898; Percent complete: 97.5%; Average loss: 2.5872
Iteration: 3899; Percent complete: 97.5%; Average loss: 2.6158
Iteration: 3900; Percent complete: 97.5%; Average loss: 2.6915
Iteration: 3901; Percent complete: 97.5%; Average loss: 2.6576
Iteration: 3902; Percent complete: 97.5%; Average loss: 2.8430
Iteration: 3903; Percent complete: 97.6%; Average loss: 2.8007
Iteration: 3904; Percent complete: 97.6%; Average loss: 2.6593
Iteration: 3905; Percent complete: 97.6%; Average loss: 2.6067
Iteration: 3906; Percent complete: 97.7%; Average loss: 2.7410
Iteration: 3907; Percent complete: 97.7%; Average loss: 2.6357
Iteration: 3908; Percent complete: 97.7%; Average loss: 2.7173
Iteration: 3909; Percent complete: 97.7%; Average loss: 2.5214
Iteration: 3910; Percent complete: 97.8%; Average loss: 2.7987
Iteration: 3911; Percent complete: 97.8%; Average loss: 2.7157
Iteration: 3912; Percent complete: 97.8%; Average loss: 2.7135
Iteration: 3913; Percent complete: 97.8%; Average loss: 2.5996
Iteration: 3914; Percent complete: 97.9%; Average loss: 2.6937
Iteration: 3915; Percent complete: 97.9%; Average loss: 2.7439
Iteration: 3916; Percent complete: 97.9%; Average loss: 2.5646
Iteration: 3917; Percent complete: 97.9%; Average loss: 2.5993
Iteration: 3918; Percent complete: 98.0%; Average loss: 2.7204
Iteration: 3919; Percent complete: 98.0%; Average loss: 2.5835
Iteration: 3920; Percent complete: 98.0%; Average loss: 2.6339
Iteration: 3921; Percent complete: 98.0%; Average loss: 2.4427
Iteration: 3922; Percent complete: 98.0%; Average loss: 2.5414
Iteration: 3923; Percent complete: 98.1%; Average loss: 2.8485
Iteration: 3924; Percent complete: 98.1%; Average loss: 2.6588
Iteration: 3925; Percent complete: 98.1%; Average loss: 2.6613
Iteration: 3926; Percent complete: 98.2%; Average loss: 2.7626
Iteration: 3927; Percent complete: 98.2%; Average loss: 2.7920
Iteration: 3928; Percent complete: 98.2%; Average loss: 2.7326
Iteration: 3929; Percent complete: 98.2%; Average loss: 2.5637
Iteration: 3930; Percent complete: 98.2%; Average loss: 2.8119
Iteration: 3931; Percent complete: 98.3%; Average loss: 2.6247
Iteration: 3932; Percent complete: 98.3%; Average loss: 2.5506
Iteration: 3933; Percent complete: 98.3%; Average loss: 2.9735
Iteration: 3934; Percent complete: 98.4%; Average loss: 2.8371
Iteration: 3935; Percent complete: 98.4%; Average loss: 2.5926
Iteration: 3936; Percent complete: 98.4%; Average loss: 2.8374
Iteration: 3937; Percent complete: 98.4%; Average loss: 2.4103
Iteration: 3938; Percent complete: 98.5%; Average loss: 2.5940
Iteration: 3939; Percent complete: 98.5%; Average loss: 2.7509
Iteration: 3940; Percent complete: 98.5%; Average loss: 2.5295
Iteration: 3941; Percent complete: 98.5%; Average loss: 2.7757
Iteration: 3942; Percent complete: 98.6%; Average loss: 2.6015
Iteration: 3943; Percent complete: 98.6%; Average loss: 2.7657
Iteration: 3944; Percent complete: 98.6%; Average loss: 2.4731
Iteration: 3945; Percent complete: 98.6%; Average loss: 2.7745
Iteration: 3946; Percent complete: 98.7%; Average loss: 2.7143
Iteration: 3947; Percent complete: 98.7%; Average loss: 2.5027
Iteration: 3948; Percent complete: 98.7%; Average loss: 2.6717
Iteration: 3949; Percent complete: 98.7%; Average loss: 2.5658
Iteration: 3950; Percent complete: 98.8%; Average loss: 2.4687
Iteration: 3951; Percent complete: 98.8%; Average loss: 2.4805
Iteration: 3952; Percent complete: 98.8%; Average loss: 2.5667
Iteration: 3953; Percent complete: 98.8%; Average loss: 3.0631
Iteration: 3954; Percent complete: 98.9%; Average loss: 2.5823
Iteration: 3955; Percent complete: 98.9%; Average loss: 2.8339
Iteration: 3956; Percent complete: 98.9%; Average loss: 2.8615
Iteration: 3957; Percent complete: 98.9%; Average loss: 2.6588
Iteration: 3958; Percent complete: 99.0%; Average loss: 2.5301
Iteration: 3959; Percent complete: 99.0%; Average loss: 2.7468
Iteration: 3960; Percent complete: 99.0%; Average loss: 2.6881
Iteration: 3961; Percent complete: 99.0%; Average loss: 2.7597
Iteration: 3962; Percent complete: 99.1%; Average loss: 2.7946
Iteration: 3963; Percent complete: 99.1%; Average loss: 2.6907
Iteration: 3964; Percent complete: 99.1%; Average loss: 2.4175
Iteration: 3965; Percent complete: 99.1%; Average loss: 2.6755
Iteration: 3966; Percent complete: 99.2%; Average loss: 2.5886
Iteration: 3967; Percent complete: 99.2%; Average loss: 2.4337
Iteration: 3968; Percent complete: 99.2%; Average loss: 2.4551
Iteration: 3969; Percent complete: 99.2%; Average loss: 2.5875
Iteration: 3970; Percent complete: 99.2%; Average loss: 2.6980
Iteration: 3971; Percent complete: 99.3%; Average loss: 2.5556
Iteration: 3972; Percent complete: 99.3%; Average loss: 2.7615
Iteration: 3973; Percent complete: 99.3%; Average loss: 2.5624
Iteration: 3974; Percent complete: 99.4%; Average loss: 2.7647
Iteration: 3975; Percent complete: 99.4%; Average loss: 2.5152
Iteration: 3976; Percent complete: 99.4%; Average loss: 2.5695
Iteration: 3977; Percent complete: 99.4%; Average loss: 2.7580
Iteration: 3978; Percent complete: 99.5%; Average loss: 2.5666
Iteration: 3979; Percent complete: 99.5%; Average loss: 2.6077
Iteration: 3980; Percent complete: 99.5%; Average loss: 2.5679
Iteration: 3981; Percent complete: 99.5%; Average loss: 2.5040
Iteration: 3982; Percent complete: 99.6%; Average loss: 2.7187
Iteration: 3983; Percent complete: 99.6%; Average loss: 2.7429
Iteration: 3984; Percent complete: 99.6%; Average loss: 2.5520
Iteration: 3985; Percent complete: 99.6%; Average loss: 2.6479
Iteration: 3986; Percent complete: 99.7%; Average loss: 2.7023
Iteration: 3987; Percent complete: 99.7%; Average loss: 2.4082
Iteration: 3988; Percent complete: 99.7%; Average loss: 2.6502
Iteration: 3989; Percent complete: 99.7%; Average loss: 2.6171
Iteration: 3990; Percent complete: 99.8%; Average loss: 2.6850
Iteration: 3991; Percent complete: 99.8%; Average loss: 2.7525
Iteration: 3992; Percent complete: 99.8%; Average loss: 2.4466
Iteration: 3993; Percent complete: 99.8%; Average loss: 2.4498
Iteration: 3994; Percent complete: 99.9%; Average loss: 2.8871
Iteration: 3995; Percent complete: 99.9%; Average loss: 2.5888
Iteration: 3996; Percent complete: 99.9%; Average loss: 2.6939
Iteration: 3997; Percent complete: 99.9%; Average loss: 2.6596
Iteration: 3998; Percent complete: 100.0%; Average loss: 2.5631
Iteration: 3999; Percent complete: 100.0%; Average loss: 2.5900
Iteration: 4000; Percent complete: 100.0%; Average loss: 2.5179

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: (2 minutes 30.520 seconds)

Chatbot Tutorial#

Preparations#

Load & Preprocess Data#

Create formatted data file#

Load and trim data#

Prepare Data for Models#

Define Models#

Seq2Seq Model#

Encoder#

Decoder#

Define Training Procedure#

Masked loss#

Single training iteration#

Training iterations#

Define Evaluation#

Greedy decoding#

Evaluate my text#

Run Model#

Run Training#

Run Evaluation#

Conclusion#

Docs

Tutorials

Resources