beginner/chatbot_tutorial

Run in Google Colab

Colab

Download Notebook

Notebook

View on GitHub

GitHub

Chatbot Tutorial

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

Author: Matthew Inkawhich

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

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

> 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:

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

2. Sean Robertson’s practical-pytorch seq2seq-translation example: spro/practical-pytorch

3. 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:

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

2. Filter out pairs with trimmed words.

MIN_COUNT = 3    # Minimum word count threshold for trimming

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

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

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


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

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

Prepare Data for Models

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

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

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

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

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([[ 717,  401,   34,   24, 1109],
        [ 135,   24, 6672,  683,   14],
        [ 146,  230,   14,   45,    2],
        [  19,   72,   14,   10,    0],
        [  17,  484,   14,    2,    0],
        [  22,   10,    2,    0,    0],
        [1188,    2,    0,    0,    0],
        [  10,    0,    0,    0,    0],
        [   2,    0,    0,    0,    0]])
lengths: tensor([9, 7, 6, 5, 3])
target_variable: tensor([[  19,   19,   11,  162, 4168],
        [  10,   10,   44,   14,  132],
        [   2,    2,    5,    2, 4169],
        [   0,    0,  402,    0,   14],
        [   0,    0,  160,    0,    2],
        [   0,    0,    6,    0,    0],
        [   0,    0,    2,    0,    0]])
mask: tensor([[ True,  True,  True,  True,  True],
        [ True,  True,  True,  True,  True],
        [ True,  True,  True,  True,  True],
        [False, False,  True, False,  True],
        [False, False,  True, False,  True],
        [False, False,  True, False, False],
        [False, False,  True, False, False]])
max_target_len: 7

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:

1. Convert word indexes to embeddings.

2. Pack padded batch of sequences for RNN module.

3. Forward pass through GRU.

4. Unpack padding.

5. Sum bidirectional GRU outputs.

6. Return output and final hidden state.

Inputs:

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

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

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

Outputs:

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

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

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

        # Initialize GRU; the input_size and hidden_size 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:

1. Get embedding of current input word.

2. Forward through unidirectional GRU.

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

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

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

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

7. Return output and final hidden state.

Inputs:

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

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

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

Outputs:

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

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

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

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

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

        self.attn = Attn(attn_model, hidden_size)

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

Define Training Procedure

Masked loss

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

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

Single training iteration

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

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

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

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

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

Sequence of Operations:

1. Forward pass entire input batch through encoder.

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

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

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

5. Calculate and accumulate loss.

6. Perform backpropagation.

7. Clip gradients.

8. Update encoder and decoder model parameters.

Note

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

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

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

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

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

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

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

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

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

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

    # Perform 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:

1. Forward input through encoder model.

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

3. Initialize decoder’s first input as SOS_token.

4. Initialize tensors to append decoded words to.

5. Iteratively decode one word token at a time:

   1. Forward pass through decoder.

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

   3. Record token and score.

   4. Prepare current token to be next decoder input.

6. Return collections of word tokens and scores.

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

    def forward(self, input_seq, input_length, max_length):
        # Forward input through encoder model
        encoder_outputs, encoder_hidden = self.encoder(input_seq, input_length)
        # Prepare encoder's final hidden layer to be first hidden input to the decoder
        decoder_hidden = encoder_hidden[: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: 8.9516
Iteration: 2; Percent complete: 0.1%; Average loss: 8.8102
Iteration: 3; Percent complete: 0.1%; Average loss: 8.5676
Iteration: 4; Percent complete: 0.1%; Average loss: 8.3551
Iteration: 5; Percent complete: 0.1%; Average loss: 7.8486
Iteration: 6; Percent complete: 0.1%; Average loss: 7.2814
Iteration: 7; Percent complete: 0.2%; Average loss: 6.9774
Iteration: 8; Percent complete: 0.2%; Average loss: 6.7910
Iteration: 9; Percent complete: 0.2%; Average loss: 6.9464
Iteration: 10; Percent complete: 0.2%; Average loss: 6.4354
Iteration: 11; Percent complete: 0.3%; Average loss: 6.0079
Iteration: 12; Percent complete: 0.3%; Average loss: 5.5444
Iteration: 13; Percent complete: 0.3%; Average loss: 5.8192
Iteration: 14; Percent complete: 0.4%; Average loss: 5.9187
Iteration: 15; Percent complete: 0.4%; Average loss: 5.6708
Iteration: 16; Percent complete: 0.4%; Average loss: 5.2285
Iteration: 17; Percent complete: 0.4%; Average loss: 5.0051
Iteration: 18; Percent complete: 0.4%; Average loss: 5.0300
Iteration: 19; Percent complete: 0.5%; Average loss: 4.8286
Iteration: 20; Percent complete: 0.5%; Average loss: 4.8555
Iteration: 21; Percent complete: 0.5%; Average loss: 4.9850
Iteration: 22; Percent complete: 0.5%; Average loss: 4.9311
Iteration: 23; Percent complete: 0.6%; Average loss: 4.8933
Iteration: 24; Percent complete: 0.6%; Average loss: 5.0421
Iteration: 25; Percent complete: 0.6%; Average loss: 4.7200
Iteration: 26; Percent complete: 0.7%; Average loss: 4.8294
Iteration: 27; Percent complete: 0.7%; Average loss: 4.6354
Iteration: 28; Percent complete: 0.7%; Average loss: 4.7096
Iteration: 29; Percent complete: 0.7%; Average loss: 4.7049
Iteration: 30; Percent complete: 0.8%; Average loss: 4.6290
Iteration: 31; Percent complete: 0.8%; Average loss: 4.7662
Iteration: 32; Percent complete: 0.8%; Average loss: 4.8133
Iteration: 33; Percent complete: 0.8%; Average loss: 4.6759
Iteration: 34; Percent complete: 0.9%; Average loss: 4.5918
Iteration: 35; Percent complete: 0.9%; Average loss: 4.8374
Iteration: 36; Percent complete: 0.9%; Average loss: 4.7879
Iteration: 37; Percent complete: 0.9%; Average loss: 4.6058
Iteration: 38; Percent complete: 0.9%; Average loss: 4.6372
Iteration: 39; Percent complete: 1.0%; Average loss: 4.5088
Iteration: 40; Percent complete: 1.0%; Average loss: 4.6180
Iteration: 41; Percent complete: 1.0%; Average loss: 4.5743
Iteration: 42; Percent complete: 1.1%; Average loss: 4.8210
Iteration: 43; Percent complete: 1.1%; Average loss: 4.6155
Iteration: 44; Percent complete: 1.1%; Average loss: 4.5063
Iteration: 45; Percent complete: 1.1%; Average loss: 4.7138
Iteration: 46; Percent complete: 1.1%; Average loss: 4.5992
Iteration: 47; Percent complete: 1.2%; Average loss: 4.6917
Iteration: 48; Percent complete: 1.2%; Average loss: 4.6144
Iteration: 49; Percent complete: 1.2%; Average loss: 4.6724
Iteration: 50; Percent complete: 1.2%; Average loss: 4.3839
Iteration: 51; Percent complete: 1.3%; Average loss: 4.6438
Iteration: 52; Percent complete: 1.3%; Average loss: 4.5926
Iteration: 53; Percent complete: 1.3%; Average loss: 4.6493
Iteration: 54; Percent complete: 1.4%; Average loss: 4.5766
Iteration: 55; Percent complete: 1.4%; Average loss: 4.6453
Iteration: 56; Percent complete: 1.4%; Average loss: 4.3924
Iteration: 57; Percent complete: 1.4%; Average loss: 4.6693
Iteration: 58; Percent complete: 1.5%; Average loss: 4.7254
Iteration: 59; Percent complete: 1.5%; Average loss: 4.4552
Iteration: 60; Percent complete: 1.5%; Average loss: 4.5950
Iteration: 61; Percent complete: 1.5%; Average loss: 4.6686
Iteration: 62; Percent complete: 1.6%; Average loss: 4.6971
Iteration: 63; Percent complete: 1.6%; Average loss: 4.6723
Iteration: 64; Percent complete: 1.6%; Average loss: 4.6520
Iteration: 65; Percent complete: 1.6%; Average loss: 4.5245
Iteration: 66; Percent complete: 1.7%; Average loss: 4.7066
Iteration: 67; Percent complete: 1.7%; Average loss: 4.3399
Iteration: 68; Percent complete: 1.7%; Average loss: 4.5826
Iteration: 69; Percent complete: 1.7%; Average loss: 4.5942
Iteration: 70; Percent complete: 1.8%; Average loss: 4.2953
Iteration: 71; Percent complete: 1.8%; Average loss: 4.5304
Iteration: 72; Percent complete: 1.8%; Average loss: 4.4440
Iteration: 73; Percent complete: 1.8%; Average loss: 4.5131
Iteration: 74; Percent complete: 1.8%; Average loss: 4.5470
Iteration: 75; Percent complete: 1.9%; Average loss: 4.4504
Iteration: 76; Percent complete: 1.9%; Average loss: 4.2656
Iteration: 77; Percent complete: 1.9%; Average loss: 4.4989
Iteration: 78; Percent complete: 1.9%; Average loss: 4.6016
Iteration: 79; Percent complete: 2.0%; Average loss: 4.3784
Iteration: 80; Percent complete: 2.0%; Average loss: 4.6603
Iteration: 81; Percent complete: 2.0%; Average loss: 4.3769
Iteration: 82; Percent complete: 2.1%; Average loss: 4.5862
Iteration: 83; Percent complete: 2.1%; Average loss: 4.3879
Iteration: 84; Percent complete: 2.1%; Average loss: 4.4411
Iteration: 85; Percent complete: 2.1%; Average loss: 4.4575
Iteration: 86; Percent complete: 2.1%; Average loss: 4.6048
Iteration: 87; Percent complete: 2.2%; Average loss: 4.3712
Iteration: 88; Percent complete: 2.2%; Average loss: 4.1894
Iteration: 89; Percent complete: 2.2%; Average loss: 4.6206
Iteration: 90; Percent complete: 2.2%; Average loss: 4.2691
Iteration: 91; Percent complete: 2.3%; Average loss: 4.7136
Iteration: 92; Percent complete: 2.3%; Average loss: 4.4096
Iteration: 93; Percent complete: 2.3%; Average loss: 4.4742
Iteration: 94; Percent complete: 2.4%; Average loss: 4.3909
Iteration: 95; Percent complete: 2.4%; Average loss: 4.2673
Iteration: 96; Percent complete: 2.4%; Average loss: 4.2814
Iteration: 97; Percent complete: 2.4%; Average loss: 4.5022
Iteration: 98; Percent complete: 2.5%; Average loss: 4.2081
Iteration: 99; Percent complete: 2.5%; Average loss: 4.6432
Iteration: 100; Percent complete: 2.5%; Average loss: 4.4103
Iteration: 101; Percent complete: 2.5%; Average loss: 4.4589
Iteration: 102; Percent complete: 2.5%; Average loss: 4.3049
Iteration: 103; Percent complete: 2.6%; Average loss: 4.5530
Iteration: 104; Percent complete: 2.6%; Average loss: 4.5942
Iteration: 105; Percent complete: 2.6%; Average loss: 4.4061
Iteration: 106; Percent complete: 2.6%; Average loss: 4.4322
Iteration: 107; Percent complete: 2.7%; Average loss: 4.3265
Iteration: 108; Percent complete: 2.7%; Average loss: 4.6552
Iteration: 109; Percent complete: 2.7%; Average loss: 4.4088
Iteration: 110; Percent complete: 2.8%; Average loss: 4.5262
Iteration: 111; Percent complete: 2.8%; Average loss: 4.5969
Iteration: 112; Percent complete: 2.8%; Average loss: 4.2022
Iteration: 113; Percent complete: 2.8%; Average loss: 4.3788
Iteration: 114; Percent complete: 2.9%; Average loss: 4.1297
Iteration: 115; Percent complete: 2.9%; Average loss: 4.5820
Iteration: 116; Percent complete: 2.9%; Average loss: 4.4166
Iteration: 117; Percent complete: 2.9%; Average loss: 4.2516
Iteration: 118; Percent complete: 2.9%; Average loss: 4.3124
Iteration: 119; Percent complete: 3.0%; Average loss: 4.5505
Iteration: 120; Percent complete: 3.0%; Average loss: 4.3053
Iteration: 121; Percent complete: 3.0%; Average loss: 4.4650
Iteration: 122; Percent complete: 3.0%; Average loss: 4.4164
Iteration: 123; Percent complete: 3.1%; Average loss: 4.3182
Iteration: 124; Percent complete: 3.1%; Average loss: 4.4824
Iteration: 125; Percent complete: 3.1%; Average loss: 4.2390
Iteration: 126; Percent complete: 3.1%; Average loss: 4.4206
Iteration: 127; Percent complete: 3.2%; Average loss: 4.4350
Iteration: 128; Percent complete: 3.2%; Average loss: 4.2723
Iteration: 129; Percent complete: 3.2%; Average loss: 4.2864
Iteration: 130; Percent complete: 3.2%; Average loss: 4.3057
Iteration: 131; Percent complete: 3.3%; Average loss: 4.7270
Iteration: 132; Percent complete: 3.3%; Average loss: 4.3884
Iteration: 133; Percent complete: 3.3%; Average loss: 4.3900
Iteration: 134; Percent complete: 3.4%; Average loss: 4.4105
Iteration: 135; Percent complete: 3.4%; Average loss: 4.3432
Iteration: 136; Percent complete: 3.4%; Average loss: 4.2327
Iteration: 137; Percent complete: 3.4%; Average loss: 4.2707
Iteration: 138; Percent complete: 3.5%; Average loss: 4.3925
Iteration: 139; Percent complete: 3.5%; Average loss: 4.5105
Iteration: 140; Percent complete: 3.5%; Average loss: 4.0501
Iteration: 141; Percent complete: 3.5%; Average loss: 4.6726
Iteration: 142; Percent complete: 3.5%; Average loss: 4.4020
Iteration: 143; Percent complete: 3.6%; Average loss: 4.2582
Iteration: 144; Percent complete: 3.6%; Average loss: 4.3270
Iteration: 145; Percent complete: 3.6%; Average loss: 4.2551
Iteration: 146; Percent complete: 3.6%; Average loss: 4.3545
Iteration: 147; Percent complete: 3.7%; Average loss: 4.4727
Iteration: 148; Percent complete: 3.7%; Average loss: 4.3389
Iteration: 149; Percent complete: 3.7%; Average loss: 4.2899
Iteration: 150; Percent complete: 3.8%; Average loss: 4.4732
Iteration: 151; Percent complete: 3.8%; Average loss: 4.2159
Iteration: 152; Percent complete: 3.8%; Average loss: 4.3978
Iteration: 153; Percent complete: 3.8%; Average loss: 4.2330
Iteration: 154; Percent complete: 3.9%; Average loss: 4.2043
Iteration: 155; Percent complete: 3.9%; Average loss: 4.5734
Iteration: 156; Percent complete: 3.9%; Average loss: 4.2264
Iteration: 157; Percent complete: 3.9%; Average loss: 4.0778
Iteration: 158; Percent complete: 4.0%; Average loss: 4.4431
Iteration: 159; Percent complete: 4.0%; Average loss: 4.1159
Iteration: 160; Percent complete: 4.0%; Average loss: 4.1473
Iteration: 161; Percent complete: 4.0%; Average loss: 4.3001
Iteration: 162; Percent complete: 4.0%; Average loss: 4.0131
Iteration: 163; Percent complete: 4.1%; Average loss: 4.3526
Iteration: 164; Percent complete: 4.1%; Average loss: 4.0693
Iteration: 165; Percent complete: 4.1%; Average loss: 4.1535
Iteration: 166; Percent complete: 4.2%; Average loss: 4.0516
Iteration: 167; Percent complete: 4.2%; Average loss: 4.0681
Iteration: 168; Percent complete: 4.2%; Average loss: 4.2163
Iteration: 169; Percent complete: 4.2%; Average loss: 3.8283
Iteration: 170; Percent complete: 4.2%; Average loss: 4.1196
Iteration: 171; Percent complete: 4.3%; Average loss: 4.0993
Iteration: 172; Percent complete: 4.3%; Average loss: 3.9836
Iteration: 173; Percent complete: 4.3%; Average loss: 4.1990
Iteration: 174; Percent complete: 4.3%; Average loss: 4.2719
Iteration: 175; Percent complete: 4.4%; Average loss: 4.3850
Iteration: 176; Percent complete: 4.4%; Average loss: 4.0672
Iteration: 177; Percent complete: 4.4%; Average loss: 3.9965
Iteration: 178; Percent complete: 4.5%; Average loss: 3.9799
Iteration: 179; Percent complete: 4.5%; Average loss: 4.1256
Iteration: 180; Percent complete: 4.5%; Average loss: 4.1047
Iteration: 181; Percent complete: 4.5%; Average loss: 4.0450
Iteration: 182; Percent complete: 4.5%; Average loss: 4.1143
Iteration: 183; Percent complete: 4.6%; Average loss: 4.0996
Iteration: 184; Percent complete: 4.6%; Average loss: 4.1921
Iteration: 185; Percent complete: 4.6%; Average loss: 4.2726
Iteration: 186; Percent complete: 4.7%; Average loss: 4.1350
Iteration: 187; Percent complete: 4.7%; Average loss: 4.2417
Iteration: 188; Percent complete: 4.7%; Average loss: 4.2028
Iteration: 189; Percent complete: 4.7%; Average loss: 4.3230
Iteration: 190; Percent complete: 4.8%; Average loss: 4.2065
Iteration: 191; Percent complete: 4.8%; Average loss: 3.9828
Iteration: 192; Percent complete: 4.8%; Average loss: 4.1994
Iteration: 193; Percent complete: 4.8%; Average loss: 3.9572
Iteration: 194; Percent complete: 4.9%; Average loss: 4.3489
Iteration: 195; Percent complete: 4.9%; Average loss: 3.9682
Iteration: 196; Percent complete: 4.9%; Average loss: 4.0313
Iteration: 197; Percent complete: 4.9%; Average loss: 4.3754
Iteration: 198; Percent complete: 5.0%; Average loss: 3.8743
Iteration: 199; Percent complete: 5.0%; Average loss: 4.2747
Iteration: 200; Percent complete: 5.0%; Average loss: 4.0594
Iteration: 201; Percent complete: 5.0%; Average loss: 4.2032
Iteration: 202; Percent complete: 5.1%; Average loss: 3.9814
Iteration: 203; Percent complete: 5.1%; Average loss: 4.0723
Iteration: 204; Percent complete: 5.1%; Average loss: 4.0752
Iteration: 205; Percent complete: 5.1%; Average loss: 3.8928
Iteration: 206; Percent complete: 5.1%; Average loss: 4.0022
Iteration: 207; Percent complete: 5.2%; Average loss: 4.0389
Iteration: 208; Percent complete: 5.2%; Average loss: 3.9064
Iteration: 209; Percent complete: 5.2%; Average loss: 4.0795
Iteration: 210; Percent complete: 5.2%; Average loss: 3.9540
Iteration: 211; Percent complete: 5.3%; Average loss: 3.8491
Iteration: 212; Percent complete: 5.3%; Average loss: 4.0165
Iteration: 213; Percent complete: 5.3%; Average loss: 3.8470
Iteration: 214; Percent complete: 5.3%; Average loss: 4.3260
Iteration: 215; Percent complete: 5.4%; Average loss: 4.0265
Iteration: 216; Percent complete: 5.4%; Average loss: 4.2550
Iteration: 217; Percent complete: 5.4%; Average loss: 4.2468
Iteration: 218; Percent complete: 5.5%; Average loss: 3.9038
Iteration: 219; Percent complete: 5.5%; Average loss: 3.9488
Iteration: 220; Percent complete: 5.5%; Average loss: 4.3047
Iteration: 221; Percent complete: 5.5%; Average loss: 3.9693
Iteration: 222; Percent complete: 5.5%; Average loss: 3.9704
Iteration: 223; Percent complete: 5.6%; Average loss: 4.0696
Iteration: 224; Percent complete: 5.6%; Average loss: 3.9342
Iteration: 225; Percent complete: 5.6%; Average loss: 3.9886
Iteration: 226; Percent complete: 5.7%; Average loss: 3.9767
Iteration: 227; Percent complete: 5.7%; Average loss: 4.2925
Iteration: 228; Percent complete: 5.7%; Average loss: 4.0094
Iteration: 229; Percent complete: 5.7%; Average loss: 4.3015
Iteration: 230; Percent complete: 5.8%; Average loss: 4.2258
Iteration: 231; Percent complete: 5.8%; Average loss: 3.8462
Iteration: 232; Percent complete: 5.8%; Average loss: 3.9811
Iteration: 233; Percent complete: 5.8%; Average loss: 3.9419
Iteration: 234; Percent complete: 5.9%; Average loss: 3.9354
Iteration: 235; Percent complete: 5.9%; Average loss: 3.8824
Iteration: 236; Percent complete: 5.9%; Average loss: 4.1468
Iteration: 237; Percent complete: 5.9%; Average loss: 4.0186
Iteration: 238; Percent complete: 5.9%; Average loss: 4.2475
Iteration: 239; Percent complete: 6.0%; Average loss: 3.9620
Iteration: 240; Percent complete: 6.0%; Average loss: 3.9879
Iteration: 241; Percent complete: 6.0%; Average loss: 3.9631
Iteration: 242; Percent complete: 6.0%; Average loss: 3.9444
Iteration: 243; Percent complete: 6.1%; Average loss: 4.1252
Iteration: 244; Percent complete: 6.1%; Average loss: 3.8996
Iteration: 245; Percent complete: 6.1%; Average loss: 3.9800
Iteration: 246; Percent complete: 6.2%; Average loss: 3.9477
Iteration: 247; Percent complete: 6.2%; Average loss: 4.0252
Iteration: 248; Percent complete: 6.2%; Average loss: 4.1389
Iteration: 249; Percent complete: 6.2%; Average loss: 3.9576
Iteration: 250; Percent complete: 6.2%; Average loss: 3.9641
Iteration: 251; Percent complete: 6.3%; Average loss: 4.0415
Iteration: 252; Percent complete: 6.3%; Average loss: 4.0676
Iteration: 253; Percent complete: 6.3%; Average loss: 3.8515
Iteration: 254; Percent complete: 6.3%; Average loss: 3.9775
Iteration: 255; Percent complete: 6.4%; Average loss: 4.0839
Iteration: 256; Percent complete: 6.4%; Average loss: 3.9790
Iteration: 257; Percent complete: 6.4%; Average loss: 3.8574
Iteration: 258; Percent complete: 6.5%; Average loss: 3.8868
Iteration: 259; Percent complete: 6.5%; Average loss: 3.9538
Iteration: 260; Percent complete: 6.5%; Average loss: 3.9321
Iteration: 261; Percent complete: 6.5%; Average loss: 4.0157
Iteration: 262; Percent complete: 6.6%; Average loss: 3.6764
Iteration: 263; Percent complete: 6.6%; Average loss: 3.7707
Iteration: 264; Percent complete: 6.6%; Average loss: 3.8487
Iteration: 265; Percent complete: 6.6%; Average loss: 3.9516
Iteration: 266; Percent complete: 6.7%; Average loss: 3.7694
Iteration: 267; Percent complete: 6.7%; Average loss: 3.7702
Iteration: 268; Percent complete: 6.7%; Average loss: 3.9940
Iteration: 269; Percent complete: 6.7%; Average loss: 4.0568
Iteration: 270; Percent complete: 6.8%; Average loss: 3.7610
Iteration: 271; Percent complete: 6.8%; Average loss: 3.9639
Iteration: 272; Percent complete: 6.8%; Average loss: 4.0983
Iteration: 273; Percent complete: 6.8%; Average loss: 4.0821
Iteration: 274; Percent complete: 6.9%; Average loss: 3.7249
Iteration: 275; Percent complete: 6.9%; Average loss: 3.9394
Iteration: 276; Percent complete: 6.9%; Average loss: 3.6908
Iteration: 277; Percent complete: 6.9%; Average loss: 3.8396
Iteration: 278; Percent complete: 7.0%; Average loss: 3.9713
Iteration: 279; Percent complete: 7.0%; Average loss: 4.3731
Iteration: 280; Percent complete: 7.0%; Average loss: 3.9162
Iteration: 281; Percent complete: 7.0%; Average loss: 3.9334
Iteration: 282; Percent complete: 7.0%; Average loss: 3.7345
Iteration: 283; Percent complete: 7.1%; Average loss: 4.1207
Iteration: 284; Percent complete: 7.1%; Average loss: 4.0426
Iteration: 285; Percent complete: 7.1%; Average loss: 3.8983
Iteration: 286; Percent complete: 7.1%; Average loss: 3.6550
Iteration: 287; Percent complete: 7.2%; Average loss: 3.8880
Iteration: 288; Percent complete: 7.2%; Average loss: 3.9416
Iteration: 289; Percent complete: 7.2%; Average loss: 3.9746
Iteration: 290; Percent complete: 7.2%; Average loss: 3.8450
Iteration: 291; Percent complete: 7.3%; Average loss: 3.9382
Iteration: 292; Percent complete: 7.3%; Average loss: 3.9605
Iteration: 293; Percent complete: 7.3%; Average loss: 3.8625
Iteration: 294; Percent complete: 7.3%; Average loss: 3.9327
Iteration: 295; Percent complete: 7.4%; Average loss: 3.8024
Iteration: 296; Percent complete: 7.4%; Average loss: 3.5303
Iteration: 297; Percent complete: 7.4%; Average loss: 3.8046
Iteration: 298; Percent complete: 7.4%; Average loss: 4.0053
Iteration: 299; Percent complete: 7.5%; Average loss: 4.1883
Iteration: 300; Percent complete: 7.5%; Average loss: 3.8417
Iteration: 301; Percent complete: 7.5%; Average loss: 3.9661
Iteration: 302; Percent complete: 7.5%; Average loss: 4.0462
Iteration: 303; Percent complete: 7.6%; Average loss: 3.7482
Iteration: 304; Percent complete: 7.6%; Average loss: 4.0314
Iteration: 305; Percent complete: 7.6%; Average loss: 4.1059
Iteration: 306; Percent complete: 7.6%; Average loss: 3.9703
Iteration: 307; Percent complete: 7.7%; Average loss: 3.8571
Iteration: 308; Percent complete: 7.7%; Average loss: 3.7326
Iteration: 309; Percent complete: 7.7%; Average loss: 4.0578
Iteration: 310; Percent complete: 7.8%; Average loss: 4.0311
Iteration: 311; Percent complete: 7.8%; Average loss: 4.0146
Iteration: 312; Percent complete: 7.8%; Average loss: 3.8723
Iteration: 313; Percent complete: 7.8%; Average loss: 3.8557
Iteration: 314; Percent complete: 7.8%; Average loss: 3.9972
Iteration: 315; Percent complete: 7.9%; Average loss: 4.1481
Iteration: 316; Percent complete: 7.9%; Average loss: 3.8697
Iteration: 317; Percent complete: 7.9%; Average loss: 3.9854
Iteration: 318; Percent complete: 8.0%; Average loss: 3.7658
Iteration: 319; Percent complete: 8.0%; Average loss: 3.7864
Iteration: 320; Percent complete: 8.0%; Average loss: 4.1250
Iteration: 321; Percent complete: 8.0%; Average loss: 3.6193
Iteration: 322; Percent complete: 8.1%; Average loss: 3.9191
Iteration: 323; Percent complete: 8.1%; Average loss: 3.6298
Iteration: 324; Percent complete: 8.1%; Average loss: 3.9180
Iteration: 325; Percent complete: 8.1%; Average loss: 3.7662
Iteration: 326; Percent complete: 8.2%; Average loss: 3.8943
Iteration: 327; Percent complete: 8.2%; Average loss: 4.1592
Iteration: 328; Percent complete: 8.2%; Average loss: 3.7149
Iteration: 329; Percent complete: 8.2%; Average loss: 3.8076
Iteration: 330; Percent complete: 8.2%; Average loss: 4.0675
Iteration: 331; Percent complete: 8.3%; Average loss: 3.6746
Iteration: 332; Percent complete: 8.3%; Average loss: 4.0138
Iteration: 333; Percent complete: 8.3%; Average loss: 3.9227
Iteration: 334; Percent complete: 8.3%; Average loss: 3.9811
Iteration: 335; Percent complete: 8.4%; Average loss: 4.1930
Iteration: 336; Percent complete: 8.4%; Average loss: 3.8515
Iteration: 337; Percent complete: 8.4%; Average loss: 3.7124
Iteration: 338; Percent complete: 8.5%; Average loss: 4.0356
Iteration: 339; Percent complete: 8.5%; Average loss: 4.0495
Iteration: 340; Percent complete: 8.5%; Average loss: 3.9958
Iteration: 341; Percent complete: 8.5%; Average loss: 3.9605
Iteration: 342; Percent complete: 8.6%; Average loss: 3.9374
Iteration: 343; Percent complete: 8.6%; Average loss: 3.7350
Iteration: 344; Percent complete: 8.6%; Average loss: 3.8181
Iteration: 345; Percent complete: 8.6%; Average loss: 4.0419
Iteration: 346; Percent complete: 8.6%; Average loss: 3.9642
Iteration: 347; Percent complete: 8.7%; Average loss: 3.5633
Iteration: 348; Percent complete: 8.7%; Average loss: 4.0011
Iteration: 349; Percent complete: 8.7%; Average loss: 3.9996
Iteration: 350; Percent complete: 8.8%; Average loss: 3.8567
Iteration: 351; Percent complete: 8.8%; Average loss: 3.9922
Iteration: 352; Percent complete: 8.8%; Average loss: 3.9843
Iteration: 353; Percent complete: 8.8%; Average loss: 3.8018
Iteration: 354; Percent complete: 8.8%; Average loss: 4.0173
Iteration: 355; Percent complete: 8.9%; Average loss: 4.0550
Iteration: 356; Percent complete: 8.9%; Average loss: 3.9398
Iteration: 357; Percent complete: 8.9%; Average loss: 3.8519
Iteration: 358; Percent complete: 8.9%; Average loss: 3.7939
Iteration: 359; Percent complete: 9.0%; Average loss: 3.7180
Iteration: 360; Percent complete: 9.0%; Average loss: 4.0724
Iteration: 361; Percent complete: 9.0%; Average loss: 4.0768
Iteration: 362; Percent complete: 9.0%; Average loss: 3.9965
Iteration: 363; Percent complete: 9.1%; Average loss: 3.8528
Iteration: 364; Percent complete: 9.1%; Average loss: 3.7543
Iteration: 365; Percent complete: 9.1%; Average loss: 3.4452
Iteration: 366; Percent complete: 9.2%; Average loss: 3.9286
Iteration: 367; Percent complete: 9.2%; Average loss: 3.7746
Iteration: 368; Percent complete: 9.2%; Average loss: 4.1940
Iteration: 369; Percent complete: 9.2%; Average loss: 3.9084
Iteration: 370; Percent complete: 9.2%; Average loss: 3.8007
Iteration: 371; Percent complete: 9.3%; Average loss: 3.6455
Iteration: 372; Percent complete: 9.3%; Average loss: 3.8716
Iteration: 373; Percent complete: 9.3%; Average loss: 3.9057
Iteration: 374; Percent complete: 9.3%; Average loss: 3.7308
Iteration: 375; Percent complete: 9.4%; Average loss: 3.7467
Iteration: 376; Percent complete: 9.4%; Average loss: 3.9455
Iteration: 377; Percent complete: 9.4%; Average loss: 4.0915
Iteration: 378; Percent complete: 9.4%; Average loss: 3.9036
Iteration: 379; Percent complete: 9.5%; Average loss: 3.8750
Iteration: 380; Percent complete: 9.5%; Average loss: 4.0524
Iteration: 381; Percent complete: 9.5%; Average loss: 3.7265
Iteration: 382; Percent complete: 9.6%; Average loss: 3.6716
Iteration: 383; Percent complete: 9.6%; Average loss: 3.9046
Iteration: 384; Percent complete: 9.6%; Average loss: 3.9190
Iteration: 385; Percent complete: 9.6%; Average loss: 3.9595
Iteration: 386; Percent complete: 9.7%; Average loss: 3.7641
Iteration: 387; Percent complete: 9.7%; Average loss: 3.7986
Iteration: 388; Percent complete: 9.7%; Average loss: 3.9947
Iteration: 389; Percent complete: 9.7%; Average loss: 3.7499
Iteration: 390; Percent complete: 9.8%; Average loss: 3.7495
Iteration: 391; Percent complete: 9.8%; Average loss: 3.7406
Iteration: 392; Percent complete: 9.8%; Average loss: 3.8985
Iteration: 393; Percent complete: 9.8%; Average loss: 3.7373
Iteration: 394; Percent complete: 9.8%; Average loss: 3.5979
Iteration: 395; Percent complete: 9.9%; Average loss: 3.7307
Iteration: 396; Percent complete: 9.9%; Average loss: 3.7438
Iteration: 397; Percent complete: 9.9%; Average loss: 3.6861
Iteration: 398; Percent complete: 10.0%; Average loss: 3.6330
Iteration: 399; Percent complete: 10.0%; Average loss: 3.7463
Iteration: 400; Percent complete: 10.0%; Average loss: 3.4811
Iteration: 401; Percent complete: 10.0%; Average loss: 4.0406
Iteration: 402; Percent complete: 10.1%; Average loss: 3.6962
Iteration: 403; Percent complete: 10.1%; Average loss: 3.8242
Iteration: 404; Percent complete: 10.1%; Average loss: 3.6773
Iteration: 405; Percent complete: 10.1%; Average loss: 3.8525
Iteration: 406; Percent complete: 10.2%; Average loss: 3.8972
Iteration: 407; Percent complete: 10.2%; Average loss: 3.9393
Iteration: 408; Percent complete: 10.2%; Average loss: 4.0095
Iteration: 409; Percent complete: 10.2%; Average loss: 3.8615
Iteration: 410; Percent complete: 10.2%; Average loss: 3.7357
Iteration: 411; Percent complete: 10.3%; Average loss: 3.8479
Iteration: 412; Percent complete: 10.3%; Average loss: 3.8312
Iteration: 413; Percent complete: 10.3%; Average loss: 3.9091
Iteration: 414; Percent complete: 10.3%; Average loss: 3.6879
Iteration: 415; Percent complete: 10.4%; Average loss: 3.8744
Iteration: 416; Percent complete: 10.4%; Average loss: 4.0836
Iteration: 417; Percent complete: 10.4%; Average loss: 3.7784
Iteration: 418; Percent complete: 10.4%; Average loss: 4.2321
Iteration: 419; Percent complete: 10.5%; Average loss: 3.7582
Iteration: 420; Percent complete: 10.5%; Average loss: 3.7463
Iteration: 421; Percent complete: 10.5%; Average loss: 3.9190
Iteration: 422; Percent complete: 10.5%; Average loss: 3.7395
Iteration: 423; Percent complete: 10.6%; Average loss: 3.7139
Iteration: 424; Percent complete: 10.6%; Average loss: 3.9816
Iteration: 425; Percent complete: 10.6%; Average loss: 3.7049
Iteration: 426; Percent complete: 10.7%; Average loss: 3.6032
Iteration: 427; Percent complete: 10.7%; Average loss: 3.6556
Iteration: 428; Percent complete: 10.7%; Average loss: 3.7190
Iteration: 429; Percent complete: 10.7%; Average loss: 3.5294
Iteration: 430; Percent complete: 10.8%; Average loss: 4.0807
Iteration: 431; Percent complete: 10.8%; Average loss: 3.7578
Iteration: 432; Percent complete: 10.8%; Average loss: 3.7326
Iteration: 433; Percent complete: 10.8%; Average loss: 4.1445
Iteration: 434; Percent complete: 10.8%; Average loss: 3.7715
Iteration: 435; Percent complete: 10.9%; Average loss: 3.6979
Iteration: 436; Percent complete: 10.9%; Average loss: 3.5882
Iteration: 437; Percent complete: 10.9%; Average loss: 4.0154
Iteration: 438; Percent complete: 10.9%; Average loss: 3.6416
Iteration: 439; Percent complete: 11.0%; Average loss: 3.9806
Iteration: 440; Percent complete: 11.0%; Average loss: 3.8563
Iteration: 441; Percent complete: 11.0%; Average loss: 3.9332
Iteration: 442; Percent complete: 11.1%; Average loss: 3.9278
Iteration: 443; Percent complete: 11.1%; Average loss: 3.9189
Iteration: 444; Percent complete: 11.1%; Average loss: 3.9897
Iteration: 445; Percent complete: 11.1%; Average loss: 3.6589
Iteration: 446; Percent complete: 11.2%; Average loss: 3.9923
Iteration: 447; Percent complete: 11.2%; Average loss: 3.9215
Iteration: 448; Percent complete: 11.2%; Average loss: 3.8865
Iteration: 449; Percent complete: 11.2%; Average loss: 3.8394
Iteration: 450; Percent complete: 11.2%; Average loss: 3.8630
Iteration: 451; Percent complete: 11.3%; Average loss: 3.8219
Iteration: 452; Percent complete: 11.3%; Average loss: 3.9491
Iteration: 453; Percent complete: 11.3%; Average loss: 3.7711
Iteration: 454; Percent complete: 11.3%; Average loss: 3.7786
Iteration: 455; Percent complete: 11.4%; Average loss: 3.7503
Iteration: 456; Percent complete: 11.4%; Average loss: 3.9661
Iteration: 457; Percent complete: 11.4%; Average loss: 3.8339
Iteration: 458; Percent complete: 11.5%; Average loss: 3.8284
Iteration: 459; Percent complete: 11.5%; Average loss: 3.9642
Iteration: 460; Percent complete: 11.5%; Average loss: 3.9241
Iteration: 461; Percent complete: 11.5%; Average loss: 3.8260
Iteration: 462; Percent complete: 11.6%; Average loss: 3.7136
Iteration: 463; Percent complete: 11.6%; Average loss: 3.8062
Iteration: 464; Percent complete: 11.6%; Average loss: 3.8395
Iteration: 465; Percent complete: 11.6%; Average loss: 3.7453
Iteration: 466; Percent complete: 11.7%; Average loss: 3.8703
Iteration: 467; Percent complete: 11.7%; Average loss: 3.4843
Iteration: 468; Percent complete: 11.7%; Average loss: 3.8081
Iteration: 469; Percent complete: 11.7%; Average loss: 3.7020
Iteration: 470; Percent complete: 11.8%; Average loss: 3.8177
Iteration: 471; Percent complete: 11.8%; Average loss: 3.8681
Iteration: 472; Percent complete: 11.8%; Average loss: 3.7093
Iteration: 473; Percent complete: 11.8%; Average loss: 4.0975
Iteration: 474; Percent complete: 11.8%; Average loss: 3.7750
Iteration: 475; Percent complete: 11.9%; Average loss: 3.8566
Iteration: 476; Percent complete: 11.9%; Average loss: 3.7300
Iteration: 477; Percent complete: 11.9%; Average loss: 3.7616
Iteration: 478; Percent complete: 11.9%; Average loss: 3.5056
Iteration: 479; Percent complete: 12.0%; Average loss: 4.0384
Iteration: 480; Percent complete: 12.0%; Average loss: 3.7939
Iteration: 481; Percent complete: 12.0%; Average loss: 3.5687
Iteration: 482; Percent complete: 12.0%; Average loss: 3.6314
Iteration: 483; Percent complete: 12.1%; Average loss: 3.9224
Iteration: 484; Percent complete: 12.1%; Average loss: 3.9492
Iteration: 485; Percent complete: 12.1%; Average loss: 3.8914
Iteration: 486; Percent complete: 12.2%; Average loss: 3.6678
Iteration: 487; Percent complete: 12.2%; Average loss: 3.4429
Iteration: 488; Percent complete: 12.2%; Average loss: 3.9443
Iteration: 489; Percent complete: 12.2%; Average loss: 4.0646
Iteration: 490; Percent complete: 12.2%; Average loss: 3.6593
Iteration: 491; Percent complete: 12.3%; Average loss: 3.5716
Iteration: 492; Percent complete: 12.3%; Average loss: 3.9517
Iteration: 493; Percent complete: 12.3%; Average loss: 3.8461
Iteration: 494; Percent complete: 12.3%; Average loss: 3.6324
Iteration: 495; Percent complete: 12.4%; Average loss: 3.7644
Iteration: 496; Percent complete: 12.4%; Average loss: 3.7222
Iteration: 497; Percent complete: 12.4%; Average loss: 3.8800
Iteration: 498; Percent complete: 12.4%; Average loss: 3.7936
Iteration: 499; Percent complete: 12.5%; Average loss: 3.4458
Iteration: 500; Percent complete: 12.5%; Average loss: 3.4604
Iteration: 501; Percent complete: 12.5%; Average loss: 3.6298
Iteration: 502; Percent complete: 12.6%; Average loss: 3.4557
Iteration: 503; Percent complete: 12.6%; Average loss: 3.5953
Iteration: 504; Percent complete: 12.6%; Average loss: 3.6977
Iteration: 505; Percent complete: 12.6%; Average loss: 3.5810
Iteration: 506; Percent complete: 12.7%; Average loss: 3.7920
Iteration: 507; Percent complete: 12.7%; Average loss: 3.7083
Iteration: 508; Percent complete: 12.7%; Average loss: 3.9403
Iteration: 509; Percent complete: 12.7%; Average loss: 3.6566
Iteration: 510; Percent complete: 12.8%; Average loss: 3.8332
Iteration: 511; Percent complete: 12.8%; Average loss: 3.5031
Iteration: 512; Percent complete: 12.8%; Average loss: 3.6648
Iteration: 513; Percent complete: 12.8%; Average loss: 3.6669
Iteration: 514; Percent complete: 12.8%; Average loss: 3.9442
Iteration: 515; Percent complete: 12.9%; Average loss: 3.8731
Iteration: 516; Percent complete: 12.9%; Average loss: 3.6627
Iteration: 517; Percent complete: 12.9%; Average loss: 3.7798
Iteration: 518; Percent complete: 13.0%; Average loss: 3.8474
Iteration: 519; Percent complete: 13.0%; Average loss: 3.7126
Iteration: 520; Percent complete: 13.0%; Average loss: 3.6872
Iteration: 521; Percent complete: 13.0%; Average loss: 3.6031
Iteration: 522; Percent complete: 13.1%; Average loss: 3.8619
Iteration: 523; Percent complete: 13.1%; Average loss: 3.5401
Iteration: 524; Percent complete: 13.1%; Average loss: 3.6149
Iteration: 525; Percent complete: 13.1%; Average loss: 3.5347
Iteration: 526; Percent complete: 13.2%; Average loss: 3.7922
Iteration: 527; Percent complete: 13.2%; Average loss: 3.5691
Iteration: 528; Percent complete: 13.2%; Average loss: 3.8737
Iteration: 529; Percent complete: 13.2%; Average loss: 3.5714
Iteration: 530; Percent complete: 13.2%; Average loss: 3.7013
Iteration: 531; Percent complete: 13.3%; Average loss: 3.8462
Iteration: 532; Percent complete: 13.3%; Average loss: 3.6490
Iteration: 533; Percent complete: 13.3%; Average loss: 3.5422
Iteration: 534; Percent complete: 13.4%; Average loss: 3.5698
Iteration: 535; Percent complete: 13.4%; Average loss: 3.6404
Iteration: 536; Percent complete: 13.4%; Average loss: 3.6548
Iteration: 537; Percent complete: 13.4%; Average loss: 3.7309
Iteration: 538; Percent complete: 13.5%; Average loss: 3.7271
Iteration: 539; Percent complete: 13.5%; Average loss: 3.8326
Iteration: 540; Percent complete: 13.5%; Average loss: 3.8594
Iteration: 541; Percent complete: 13.5%; Average loss: 3.8865
Iteration: 542; Percent complete: 13.6%; Average loss: 3.5588
Iteration: 543; Percent complete: 13.6%; Average loss: 3.9147
Iteration: 544; Percent complete: 13.6%; Average loss: 3.7405
Iteration: 545; Percent complete: 13.6%; Average loss: 3.4708
Iteration: 546; Percent complete: 13.7%; Average loss: 3.4381
Iteration: 547; Percent complete: 13.7%; Average loss: 3.5448
Iteration: 548; Percent complete: 13.7%; Average loss: 3.7309
Iteration: 549; Percent complete: 13.7%; Average loss: 3.6204
Iteration: 550; Percent complete: 13.8%; Average loss: 3.3608
Iteration: 551; Percent complete: 13.8%; Average loss: 3.6287
Iteration: 552; Percent complete: 13.8%; Average loss: 3.3902
Iteration: 553; Percent complete: 13.8%; Average loss: 3.6749
Iteration: 554; Percent complete: 13.9%; Average loss: 3.5303
Iteration: 555; Percent complete: 13.9%; Average loss: 3.5995
Iteration: 556; Percent complete: 13.9%; Average loss: 3.3835
Iteration: 557; Percent complete: 13.9%; Average loss: 3.6927
Iteration: 558; Percent complete: 14.0%; Average loss: 3.5116
Iteration: 559; Percent complete: 14.0%; Average loss: 3.9322
Iteration: 560; Percent complete: 14.0%; Average loss: 3.5423
Iteration: 561; Percent complete: 14.0%; Average loss: 3.2892
Iteration: 562; Percent complete: 14.1%; Average loss: 3.8602
Iteration: 563; Percent complete: 14.1%; Average loss: 3.7594
Iteration: 564; Percent complete: 14.1%; Average loss: 3.6034
Iteration: 565; Percent complete: 14.1%; Average loss: 3.8527
Iteration: 566; Percent complete: 14.1%; Average loss: 3.7467
Iteration: 567; Percent complete: 14.2%; Average loss: 3.9749
Iteration: 568; Percent complete: 14.2%; Average loss: 3.6715
Iteration: 569; Percent complete: 14.2%; Average loss: 3.7061
Iteration: 570; Percent complete: 14.2%; Average loss: 3.8522
Iteration: 571; Percent complete: 14.3%; Average loss: 3.6752
Iteration: 572; Percent complete: 14.3%; Average loss: 3.9697
Iteration: 573; Percent complete: 14.3%; Average loss: 3.5206
Iteration: 574; Percent complete: 14.3%; Average loss: 3.7087
Iteration: 575; Percent complete: 14.4%; Average loss: 3.5549
Iteration: 576; Percent complete: 14.4%; Average loss: 3.5164
Iteration: 577; Percent complete: 14.4%; Average loss: 3.6718
Iteration: 578; Percent complete: 14.4%; Average loss: 3.6587
Iteration: 579; Percent complete: 14.5%; Average loss: 3.5858
Iteration: 580; Percent complete: 14.5%; Average loss: 3.5238
Iteration: 581; Percent complete: 14.5%; Average loss: 4.0591
Iteration: 582; Percent complete: 14.5%; Average loss: 3.5916
Iteration: 583; Percent complete: 14.6%; Average loss: 3.5468
Iteration: 584; Percent complete: 14.6%; Average loss: 3.8788
Iteration: 585; Percent complete: 14.6%; Average loss: 3.5269
Iteration: 586; Percent complete: 14.6%; Average loss: 3.6817
Iteration: 587; Percent complete: 14.7%; Average loss: 3.6310
Iteration: 588; Percent complete: 14.7%; Average loss: 3.6576
Iteration: 589; Percent complete: 14.7%; Average loss: 3.6254
Iteration: 590; Percent complete: 14.8%; Average loss: 3.7308
Iteration: 591; Percent complete: 14.8%; Average loss: 3.7916
Iteration: 592; Percent complete: 14.8%; Average loss: 3.7594
Iteration: 593; Percent complete: 14.8%; Average loss: 3.5131
Iteration: 594; Percent complete: 14.8%; Average loss: 3.8691
Iteration: 595; Percent complete: 14.9%; Average loss: 3.6233
Iteration: 596; Percent complete: 14.9%; Average loss: 3.7845
Iteration: 597; Percent complete: 14.9%; Average loss: 3.7780
Iteration: 598; Percent complete: 14.9%; Average loss: 3.6875
Iteration: 599; Percent complete: 15.0%; Average loss: 3.8932
Iteration: 600; Percent complete: 15.0%; Average loss: 3.5316
Iteration: 601; Percent complete: 15.0%; Average loss: 3.5943
Iteration: 602; Percent complete: 15.0%; Average loss: 3.9541
Iteration: 603; Percent complete: 15.1%; Average loss: 3.8495
Iteration: 604; Percent complete: 15.1%; Average loss: 3.6743
Iteration: 605; Percent complete: 15.1%; Average loss: 3.7035
Iteration: 606; Percent complete: 15.2%; Average loss: 3.4116
Iteration: 607; Percent complete: 15.2%; Average loss: 3.8092
Iteration: 608; Percent complete: 15.2%; Average loss: 3.5560
Iteration: 609; Percent complete: 15.2%; Average loss: 3.8860
Iteration: 610; Percent complete: 15.2%; Average loss: 3.7971
Iteration: 611; Percent complete: 15.3%; Average loss: 3.6133
Iteration: 612; Percent complete: 15.3%; Average loss: 3.4982
Iteration: 613; Percent complete: 15.3%; Average loss: 3.5760
Iteration: 614; Percent complete: 15.3%; Average loss: 3.6483
Iteration: 615; Percent complete: 15.4%; Average loss: 3.7550
Iteration: 616; Percent complete: 15.4%; Average loss: 3.4886
Iteration: 617; Percent complete: 15.4%; Average loss: 3.6660
Iteration: 618; Percent complete: 15.4%; Average loss: 3.4735
Iteration: 619; Percent complete: 15.5%; Average loss: 3.6875
Iteration: 620; Percent complete: 15.5%; Average loss: 3.8454
Iteration: 621; Percent complete: 15.5%; Average loss: 3.6986
Iteration: 622; Percent complete: 15.6%; Average loss: 3.6204
Iteration: 623; Percent complete: 15.6%; Average loss: 3.7526
Iteration: 624; Percent complete: 15.6%; Average loss: 3.4304
Iteration: 625; Percent complete: 15.6%; Average loss: 3.5081
Iteration: 626; Percent complete: 15.7%; Average loss: 3.5803
Iteration: 627; Percent complete: 15.7%; Average loss: 3.6328
Iteration: 628; Percent complete: 15.7%; Average loss: 3.7374
Iteration: 629; Percent complete: 15.7%; Average loss: 3.3234
Iteration: 630; Percent complete: 15.8%; Average loss: 3.5815
Iteration: 631; Percent complete: 15.8%; Average loss: 3.8098
Iteration: 632; Percent complete: 15.8%; Average loss: 3.7005
Iteration: 633; Percent complete: 15.8%; Average loss: 3.5137
Iteration: 634; Percent complete: 15.8%; Average loss: 3.6431
Iteration: 635; Percent complete: 15.9%; Average loss: 3.5786
Iteration: 636; Percent complete: 15.9%; Average loss: 3.4803
Iteration: 637; Percent complete: 15.9%; Average loss: 3.5748
Iteration: 638; Percent complete: 16.0%; Average loss: 3.6516
Iteration: 639; Percent complete: 16.0%; Average loss: 3.8531
Iteration: 640; Percent complete: 16.0%; Average loss: 3.3929
Iteration: 641; Percent complete: 16.0%; Average loss: 3.5847
Iteration: 642; Percent complete: 16.1%; Average loss: 3.7683
Iteration: 643; Percent complete: 16.1%; Average loss: 3.6909
Iteration: 644; Percent complete: 16.1%; Average loss: 3.4147
Iteration: 645; Percent complete: 16.1%; Average loss: 3.7126
Iteration: 646; Percent complete: 16.2%; Average loss: 3.5151
Iteration: 647; Percent complete: 16.2%; Average loss: 3.9913
Iteration: 648; Percent complete: 16.2%; Average loss: 3.6994
Iteration: 649; Percent complete: 16.2%; Average loss: 3.8093
Iteration: 650; Percent complete: 16.2%; Average loss: 3.5525
Iteration: 651; Percent complete: 16.3%; Average loss: 3.6081
Iteration: 652; Percent complete: 16.3%; Average loss: 3.4405
Iteration: 653; Percent complete: 16.3%; Average loss: 3.8614
Iteration: 654; Percent complete: 16.4%; Average loss: 3.5080
Iteration: 655; Percent complete: 16.4%; Average loss: 3.5944
Iteration: 656; Percent complete: 16.4%; Average loss: 3.5282
Iteration: 657; Percent complete: 16.4%; Average loss: 3.7934
Iteration: 658; Percent complete: 16.4%; Average loss: 3.5923
Iteration: 659; Percent complete: 16.5%; Average loss: 3.6357
Iteration: 660; Percent complete: 16.5%; Average loss: 3.4355
Iteration: 661; Percent complete: 16.5%; Average loss: 3.6106
Iteration: 662; Percent complete: 16.6%; Average loss: 3.6383
Iteration: 663; Percent complete: 16.6%; Average loss: 3.6083
Iteration: 664; Percent complete: 16.6%; Average loss: 3.5615
Iteration: 665; Percent complete: 16.6%; Average loss: 3.4058
Iteration: 666; Percent complete: 16.7%; Average loss: 3.7492
Iteration: 667; Percent complete: 16.7%; Average loss: 3.3376
Iteration: 668; Percent complete: 16.7%; Average loss: 3.5089
Iteration: 669; Percent complete: 16.7%; Average loss: 3.9327
Iteration: 670; Percent complete: 16.8%; Average loss: 3.5806
Iteration: 671; Percent complete: 16.8%; Average loss: 3.5950
Iteration: 672; Percent complete: 16.8%; Average loss: 3.6892
Iteration: 673; Percent complete: 16.8%; Average loss: 3.5486
Iteration: 674; Percent complete: 16.9%; Average loss: 3.5061
Iteration: 675; Percent complete: 16.9%; Average loss: 3.5666
Iteration: 676; Percent complete: 16.9%; Average loss: 3.6357
Iteration: 677; Percent complete: 16.9%; Average loss: 3.5964
Iteration: 678; Percent complete: 17.0%; Average loss: 3.7453
Iteration: 679; Percent complete: 17.0%; Average loss: 3.3644
Iteration: 680; Percent complete: 17.0%; Average loss: 3.6354
Iteration: 681; Percent complete: 17.0%; Average loss: 3.5593
Iteration: 682; Percent complete: 17.1%; Average loss: 3.5841
Iteration: 683; Percent complete: 17.1%; Average loss: 3.4904
Iteration: 684; Percent complete: 17.1%; Average loss: 3.4741
Iteration: 685; Percent complete: 17.1%; Average loss: 3.5841
Iteration: 686; Percent complete: 17.2%; Average loss: 3.4595
Iteration: 687; Percent complete: 17.2%; Average loss: 3.5880
Iteration: 688; Percent complete: 17.2%; Average loss: 3.5756
Iteration: 689; Percent complete: 17.2%; Average loss: 3.5891
Iteration: 690; Percent complete: 17.2%; Average loss: 3.8458
Iteration: 691; Percent complete: 17.3%; Average loss: 3.6641
Iteration: 692; Percent complete: 17.3%; Average loss: 3.4188
Iteration: 693; Percent complete: 17.3%; Average loss: 3.8883
Iteration: 694; Percent complete: 17.3%; Average loss: 3.7066
Iteration: 695; Percent complete: 17.4%; Average loss: 3.8945
Iteration: 696; Percent complete: 17.4%; Average loss: 3.5265
Iteration: 697; Percent complete: 17.4%; Average loss: 3.7621
Iteration: 698; Percent complete: 17.4%; Average loss: 3.7241
Iteration: 699; Percent complete: 17.5%; Average loss: 3.4673
Iteration: 700; Percent complete: 17.5%; Average loss: 3.5502
Iteration: 701; Percent complete: 17.5%; Average loss: 3.5681
Iteration: 702; Percent complete: 17.5%; Average loss: 3.7174
Iteration: 703; Percent complete: 17.6%; Average loss: 3.4430
Iteration: 704; Percent complete: 17.6%; Average loss: 3.4131
Iteration: 705; Percent complete: 17.6%; Average loss: 3.8544
Iteration: 706; Percent complete: 17.6%; Average loss: 3.6626
Iteration: 707; Percent complete: 17.7%; Average loss: 3.5382
Iteration: 708; Percent complete: 17.7%; Average loss: 3.4694
Iteration: 709; Percent complete: 17.7%; Average loss: 3.6218
Iteration: 710; Percent complete: 17.8%; Average loss: 3.7196
Iteration: 711; Percent complete: 17.8%; Average loss: 3.4319
Iteration: 712; Percent complete: 17.8%; Average loss: 3.6700
Iteration: 713; Percent complete: 17.8%; Average loss: 3.6625
Iteration: 714; Percent complete: 17.8%; Average loss: 3.6359
Iteration: 715; Percent complete: 17.9%; Average loss: 3.5672
Iteration: 716; Percent complete: 17.9%; Average loss: 3.6320
Iteration: 717; Percent complete: 17.9%; Average loss: 3.8134
Iteration: 718; Percent complete: 17.9%; Average loss: 3.6111
Iteration: 719; Percent complete: 18.0%; Average loss: 3.8561
Iteration: 720; Percent complete: 18.0%; Average loss: 3.7646
Iteration: 721; Percent complete: 18.0%; Average loss: 3.5233
Iteration: 722; Percent complete: 18.1%; Average loss: 3.3087
Iteration: 723; Percent complete: 18.1%; Average loss: 3.5905
Iteration: 724; Percent complete: 18.1%; Average loss: 3.6196
Iteration: 725; Percent complete: 18.1%; Average loss: 3.5264
Iteration: 726; Percent complete: 18.1%; Average loss: 3.6376
Iteration: 727; Percent complete: 18.2%; Average loss: 3.7227
Iteration: 728; Percent complete: 18.2%; Average loss: 3.4774
Iteration: 729; Percent complete: 18.2%; Average loss: 3.6659
Iteration: 730; Percent complete: 18.2%; Average loss: 3.5753
Iteration: 731; Percent complete: 18.3%; Average loss: 3.6667
Iteration: 732; Percent complete: 18.3%; Average loss: 3.2384
Iteration: 733; Percent complete: 18.3%; Average loss: 3.8003
Iteration: 734; Percent complete: 18.4%; Average loss: 3.5311
Iteration: 735; Percent complete: 18.4%; Average loss: 3.6345
Iteration: 736; Percent complete: 18.4%; Average loss: 3.5890
Iteration: 737; Percent complete: 18.4%; Average loss: 3.6890
Iteration: 738; Percent complete: 18.4%; Average loss: 3.6854
Iteration: 739; Percent complete: 18.5%; Average loss: 3.7068
Iteration: 740; Percent complete: 18.5%; Average loss: 3.4308
Iteration: 741; Percent complete: 18.5%; Average loss: 3.6185
Iteration: 742; Percent complete: 18.6%; Average loss: 3.5428
Iteration: 743; Percent complete: 18.6%; Average loss: 3.6241
Iteration: 744; Percent complete: 18.6%; Average loss: 3.6582
Iteration: 745; Percent complete: 18.6%; Average loss: 3.4181
Iteration: 746; Percent complete: 18.6%; Average loss: 3.3757
Iteration: 747; Percent complete: 18.7%; Average loss: 3.7190
Iteration: 748; Percent complete: 18.7%; Average loss: 3.7385
Iteration: 749; Percent complete: 18.7%; Average loss: 3.4830
Iteration: 750; Percent complete: 18.8%; Average loss: 3.4656
Iteration: 751; Percent complete: 18.8%; Average loss: 3.6508
Iteration: 752; Percent complete: 18.8%; Average loss: 3.6646
Iteration: 753; Percent complete: 18.8%; Average loss: 3.6272
Iteration: 754; Percent complete: 18.9%; Average loss: 3.6253
Iteration: 755; Percent complete: 18.9%; Average loss: 3.4988
Iteration: 756; Percent complete: 18.9%; Average loss: 3.7459
Iteration: 757; Percent complete: 18.9%; Average loss: 3.4946
Iteration: 758; Percent complete: 18.9%; Average loss: 3.5565
Iteration: 759; Percent complete: 19.0%; Average loss: 3.6404
Iteration: 760; Percent complete: 19.0%; Average loss: 3.7723
Iteration: 761; Percent complete: 19.0%; Average loss: 3.6505
Iteration: 762; Percent complete: 19.1%; Average loss: 3.4920
Iteration: 763; Percent complete: 19.1%; Average loss: 3.6900
Iteration: 764; Percent complete: 19.1%; Average loss: 3.6156
Iteration: 765; Percent complete: 19.1%; Average loss: 3.5272
Iteration: 766; Percent complete: 19.1%; Average loss: 3.7132
Iteration: 767; Percent complete: 19.2%; Average loss: 3.3877
Iteration: 768; Percent complete: 19.2%; Average loss: 3.7493
Iteration: 769; Percent complete: 19.2%; Average loss: 3.4897
Iteration: 770; Percent complete: 19.2%; Average loss: 3.3443
Iteration: 771; Percent complete: 19.3%; Average loss: 3.6237
Iteration: 772; Percent complete: 19.3%; Average loss: 3.3772
Iteration: 773; Percent complete: 19.3%; Average loss: 3.4785
Iteration: 774; Percent complete: 19.4%; Average loss: 3.7043
Iteration: 775; Percent complete: 19.4%; Average loss: 3.1721
Iteration: 776; Percent complete: 19.4%; Average loss: 3.2707
Iteration: 777; Percent complete: 19.4%; Average loss: 3.5599
Iteration: 778; Percent complete: 19.4%; Average loss: 3.7322
Iteration: 779; Percent complete: 19.5%; Average loss: 3.4846
Iteration: 780; Percent complete: 19.5%; Average loss: 3.5628
Iteration: 781; Percent complete: 19.5%; Average loss: 3.6346
Iteration: 782; Percent complete: 19.6%; Average loss: 3.5495
Iteration: 783; Percent complete: 19.6%; Average loss: 3.6749
Iteration: 784; Percent complete: 19.6%; Average loss: 3.5321
Iteration: 785; Percent complete: 19.6%; Average loss: 3.6934
Iteration: 786; Percent complete: 19.7%; Average loss: 3.5936
Iteration: 787; Percent complete: 19.7%; Average loss: 3.8772
Iteration: 788; Percent complete: 19.7%; Average loss: 3.5232
Iteration: 789; Percent complete: 19.7%; Average loss: 3.6242
Iteration: 790; Percent complete: 19.8%; Average loss: 3.6138
Iteration: 791; Percent complete: 19.8%; Average loss: 3.3712
Iteration: 792; Percent complete: 19.8%; Average loss: 3.6419
Iteration: 793; Percent complete: 19.8%; Average loss: 3.5591
Iteration: 794; Percent complete: 19.9%; Average loss: 3.4915
Iteration: 795; Percent complete: 19.9%; Average loss: 3.2472
Iteration: 796; Percent complete: 19.9%; Average loss: 3.4892
Iteration: 797; Percent complete: 19.9%; Average loss: 3.8064
Iteration: 798; Percent complete: 20.0%; Average loss: 3.5247
Iteration: 799; Percent complete: 20.0%; Average loss: 3.5711
Iteration: 800; Percent complete: 20.0%; Average loss: 3.5744
Iteration: 801; Percent complete: 20.0%; Average loss: 3.8650
Iteration: 802; Percent complete: 20.1%; Average loss: 3.5467
Iteration: 803; Percent complete: 20.1%; Average loss: 3.8009
Iteration: 804; Percent complete: 20.1%; Average loss: 3.5194
Iteration: 805; Percent complete: 20.1%; Average loss: 3.6164
Iteration: 806; Percent complete: 20.2%; Average loss: 3.6016
Iteration: 807; Percent complete: 20.2%; Average loss: 3.4110
Iteration: 808; Percent complete: 20.2%; Average loss: 3.5067
Iteration: 809; Percent complete: 20.2%; Average loss: 3.4007
Iteration: 810; Percent complete: 20.2%; Average loss: 3.5372
Iteration: 811; Percent complete: 20.3%; Average loss: 3.4447
Iteration: 812; Percent complete: 20.3%; Average loss: 3.5551
Iteration: 813; Percent complete: 20.3%; Average loss: 3.4058
Iteration: 814; Percent complete: 20.3%; Average loss: 3.6025
Iteration: 815; Percent complete: 20.4%; Average loss: 3.6720
Iteration: 816; Percent complete: 20.4%; Average loss: 3.3518
Iteration: 817; Percent complete: 20.4%; Average loss: 3.6395
Iteration: 818; Percent complete: 20.4%; Average loss: 3.4298
Iteration: 819; Percent complete: 20.5%; Average loss: 3.3910
Iteration: 820; Percent complete: 20.5%; Average loss: 3.7036
Iteration: 821; Percent complete: 20.5%; Average loss: 3.5333
Iteration: 822; Percent complete: 20.5%; Average loss: 3.4906
Iteration: 823; Percent complete: 20.6%; Average loss: 3.4778
Iteration: 824; Percent complete: 20.6%; Average loss: 3.3392
Iteration: 825; Percent complete: 20.6%; Average loss: 3.5824
Iteration: 826; Percent complete: 20.6%; Average loss: 3.7306
Iteration: 827; Percent complete: 20.7%; Average loss: 3.6351
Iteration: 828; Percent complete: 20.7%; Average loss: 3.2074
Iteration: 829; Percent complete: 20.7%; Average loss: 3.5350
Iteration: 830; Percent complete: 20.8%; Average loss: 3.4070
Iteration: 831; Percent complete: 20.8%; Average loss: 3.4736
Iteration: 832; Percent complete: 20.8%; Average loss: 3.4883
Iteration: 833; Percent complete: 20.8%; Average loss: 3.9587
Iteration: 834; Percent complete: 20.8%; Average loss: 3.7099
Iteration: 835; Percent complete: 20.9%; Average loss: 3.4950
Iteration: 836; Percent complete: 20.9%; Average loss: 3.5556
Iteration: 837; Percent complete: 20.9%; Average loss: 3.6227
Iteration: 838; Percent complete: 20.9%; Average loss: 3.5533
Iteration: 839; Percent complete: 21.0%; Average loss: 3.6363
Iteration: 840; Percent complete: 21.0%; Average loss: 3.6102
Iteration: 841; Percent complete: 21.0%; Average loss: 3.4344
Iteration: 842; Percent complete: 21.1%; Average loss: 3.3045
Iteration: 843; Percent complete: 21.1%; Average loss: 3.8062
Iteration: 844; Percent complete: 21.1%; Average loss: 3.5319
Iteration: 845; Percent complete: 21.1%; Average loss: 3.4006
Iteration: 846; Percent complete: 21.1%; Average loss: 3.4454
Iteration: 847; Percent complete: 21.2%; Average loss: 3.3453
Iteration: 848; Percent complete: 21.2%; Average loss: 3.5814
Iteration: 849; Percent complete: 21.2%; Average loss: 3.0711
Iteration: 850; Percent complete: 21.2%; Average loss: 3.3668
Iteration: 851; Percent complete: 21.3%; Average loss: 3.6176
Iteration: 852; Percent complete: 21.3%; Average loss: 3.5335
Iteration: 853; Percent complete: 21.3%; Average loss: 3.4143
Iteration: 854; Percent complete: 21.3%; Average loss: 3.5213
Iteration: 855; Percent complete: 21.4%; Average loss: 3.6010
Iteration: 856; Percent complete: 21.4%; Average loss: 3.3916
Iteration: 857; Percent complete: 21.4%; Average loss: 3.6156
Iteration: 858; Percent complete: 21.4%; Average loss: 3.3428
Iteration: 859; Percent complete: 21.5%; Average loss: 3.6296
Iteration: 860; Percent complete: 21.5%; Average loss: 3.5802
Iteration: 861; Percent complete: 21.5%; Average loss: 3.4371
Iteration: 862; Percent complete: 21.6%; Average loss: 3.4996
Iteration: 863; Percent complete: 21.6%; Average loss: 3.5690
Iteration: 864; Percent complete: 21.6%; Average loss: 3.4207
Iteration: 865; Percent complete: 21.6%; Average loss: 3.4667
Iteration: 866; Percent complete: 21.6%; Average loss: 3.8160
Iteration: 867; Percent complete: 21.7%; Average loss: 3.4662
Iteration: 868; Percent complete: 21.7%; Average loss: 3.6294
Iteration: 869; Percent complete: 21.7%; Average loss: 3.7101
Iteration: 870; Percent complete: 21.8%; Average loss: 3.5751
Iteration: 871; Percent complete: 21.8%; Average loss: 3.4885
Iteration: 872; Percent complete: 21.8%; Average loss: 3.5130
Iteration: 873; Percent complete: 21.8%; Average loss: 3.5538
Iteration: 874; Percent complete: 21.9%; Average loss: 3.4571
Iteration: 875; Percent complete: 21.9%; Average loss: 3.6530
Iteration: 876; Percent complete: 21.9%; Average loss: 3.7904
Iteration: 877; Percent complete: 21.9%; Average loss: 3.7813
Iteration: 878; Percent complete: 21.9%; Average loss: 3.4373
Iteration: 879; Percent complete: 22.0%; Average loss: 3.7144
Iteration: 880; Percent complete: 22.0%; Average loss: 3.5786
Iteration: 881; Percent complete: 22.0%; Average loss: 3.3297
Iteration: 882; Percent complete: 22.1%; Average loss: 3.6995
Iteration: 883; Percent complete: 22.1%; Average loss: 3.6927
Iteration: 884; Percent complete: 22.1%; Average loss: 3.4087
Iteration: 885; Percent complete: 22.1%; Average loss: 3.4683
Iteration: 886; Percent complete: 22.1%; Average loss: 3.8509
Iteration: 887; Percent complete: 22.2%; Average loss: 3.7336
Iteration: 888; Percent complete: 22.2%; Average loss: 3.5339
Iteration: 889; Percent complete: 22.2%; Average loss: 3.1469
Iteration: 890; Percent complete: 22.2%; Average loss: 3.7242
Iteration: 891; Percent complete: 22.3%; Average loss: 3.4822
Iteration: 892; Percent complete: 22.3%; Average loss: 3.7383
Iteration: 893; Percent complete: 22.3%; Average loss: 3.1291
Iteration: 894; Percent complete: 22.4%; Average loss: 3.4309
Iteration: 895; Percent complete: 22.4%; Average loss: 3.3481
Iteration: 896; Percent complete: 22.4%; Average loss: 3.5762
Iteration: 897; Percent complete: 22.4%; Average loss: 3.5725
Iteration: 898; Percent complete: 22.4%; Average loss: 3.6255
Iteration: 899; Percent complete: 22.5%; Average loss: 3.2855
Iteration: 900; Percent complete: 22.5%; Average loss: 3.7390
Iteration: 901; Percent complete: 22.5%; Average loss: 3.6091
Iteration: 902; Percent complete: 22.6%; Average loss: 3.2720
Iteration: 903; Percent complete: 22.6%; Average loss: 3.3765
Iteration: 904; Percent complete: 22.6%; Average loss: 3.4358
Iteration: 905; Percent complete: 22.6%; Average loss: 3.6894
Iteration: 906; Percent complete: 22.7%; Average loss: 3.3182
Iteration: 907; Percent complete: 22.7%; Average loss: 3.7389
Iteration: 908; Percent complete: 22.7%; Average loss: 3.3752
Iteration: 909; Percent complete: 22.7%; Average loss: 3.3401
Iteration: 910; Percent complete: 22.8%; Average loss: 3.4395
Iteration: 911; Percent complete: 22.8%; Average loss: 3.3792
Iteration: 912; Percent complete: 22.8%; Average loss: 3.8456
Iteration: 913; Percent complete: 22.8%; Average loss: 3.5351
Iteration: 914; Percent complete: 22.9%; Average loss: 3.4632
Iteration: 915; Percent complete: 22.9%; Average loss: 3.2192
Iteration: 916; Percent complete: 22.9%; Average loss: 3.4135
Iteration: 917; Percent complete: 22.9%; Average loss: 3.4822
Iteration: 918; Percent complete: 22.9%; Average loss: 3.5011
Iteration: 919; Percent complete: 23.0%; Average loss: 3.5099
Iteration: 920; Percent complete: 23.0%; Average loss: 3.4362
Iteration: 921; Percent complete: 23.0%; Average loss: 3.9112
Iteration: 922; Percent complete: 23.1%; Average loss: 3.2558
Iteration: 923; Percent complete: 23.1%; Average loss: 3.3541
Iteration: 924; Percent complete: 23.1%; Average loss: 3.6750
Iteration: 925; Percent complete: 23.1%; Average loss: 3.7539
Iteration: 926; Percent complete: 23.2%; Average loss: 3.4820
Iteration: 927; Percent complete: 23.2%; Average loss: 3.4128
Iteration: 928; Percent complete: 23.2%; Average loss: 3.5709
Iteration: 929; Percent complete: 23.2%; Average loss: 3.7278
Iteration: 930; Percent complete: 23.2%; Average loss: 3.4969
Iteration: 931; Percent complete: 23.3%; Average loss: 3.5084
Iteration: 932; Percent complete: 23.3%; Average loss: 3.5903
Iteration: 933; Percent complete: 23.3%; Average loss: 3.7065
Iteration: 934; Percent complete: 23.4%; Average loss: 3.6217
Iteration: 935; Percent complete: 23.4%; Average loss: 3.2778
Iteration: 936; Percent complete: 23.4%; Average loss: 3.5429
Iteration: 937; Percent complete: 23.4%; Average loss: 3.4679
Iteration: 938; Percent complete: 23.4%; Average loss: 3.4018
Iteration: 939; Percent complete: 23.5%; Average loss: 3.4154
Iteration: 940; Percent complete: 23.5%; Average loss: 3.6677
Iteration: 941; Percent complete: 23.5%; Average loss: 3.8141
Iteration: 942; Percent complete: 23.5%; Average loss: 3.6688
Iteration: 943; Percent complete: 23.6%; Average loss: 3.3519
Iteration: 944; Percent complete: 23.6%; Average loss: 3.3799
Iteration: 945; Percent complete: 23.6%; Average loss: 3.5635
Iteration: 946; Percent complete: 23.6%; Average loss: 3.2482
Iteration: 947; Percent complete: 23.7%; Average loss: 3.3443
Iteration: 948; Percent complete: 23.7%; Average loss: 3.4903
Iteration: 949; Percent complete: 23.7%; Average loss: 3.5469
Iteration: 950; Percent complete: 23.8%; Average loss: 3.4598
Iteration: 951; Percent complete: 23.8%; Average loss: 3.3806
Iteration: 952; Percent complete: 23.8%; Average loss: 3.4236
Iteration: 953; Percent complete: 23.8%; Average loss: 3.1250
Iteration: 954; Percent complete: 23.8%; Average loss: 3.6699
Iteration: 955; Percent complete: 23.9%; Average loss: 3.4848
Iteration: 956; Percent complete: 23.9%; Average loss: 3.5505
Iteration: 957; Percent complete: 23.9%; Average loss: 3.5440
Iteration: 958; Percent complete: 23.9%; Average loss: 3.7216
Iteration: 959; Percent complete: 24.0%; Average loss: 3.5475
Iteration: 960; Percent complete: 24.0%; Average loss: 3.4343
Iteration: 961; Percent complete: 24.0%; Average loss: 3.4603
Iteration: 962; Percent complete: 24.1%; Average loss: 3.4173
Iteration: 963; Percent complete: 24.1%; Average loss: 3.3571
Iteration: 964; Percent complete: 24.1%; Average loss: 3.5184
Iteration: 965; Percent complete: 24.1%; Average loss: 3.4721
Iteration: 966; Percent complete: 24.1%; Average loss: 3.4121
Iteration: 967; Percent complete: 24.2%; Average loss: 3.4786
Iteration: 968; Percent complete: 24.2%; Average loss: 3.2925
Iteration: 969; Percent complete: 24.2%; Average loss: 3.5745
Iteration: 970; Percent complete: 24.2%; Average loss: 3.3619
Iteration: 971; Percent complete: 24.3%; Average loss: 3.8356
Iteration: 972; Percent complete: 24.3%; Average loss: 3.4570
Iteration: 973; Percent complete: 24.3%; Average loss: 3.5211
Iteration: 974; Percent complete: 24.3%; Average loss: 3.2807
Iteration: 975; Percent complete: 24.4%; Average loss: 3.5198
Iteration: 976; Percent complete: 24.4%; Average loss: 3.3928
Iteration: 977; Percent complete: 24.4%; Average loss: 3.4621
Iteration: 978; Percent complete: 24.4%; Average loss: 3.6033
Iteration: 979; Percent complete: 24.5%; Average loss: 3.6771
Iteration: 980; Percent complete: 24.5%; Average loss: 3.3828
Iteration: 981; Percent complete: 24.5%; Average loss: 3.7393
Iteration: 982; Percent complete: 24.6%; Average loss: 3.7904
Iteration: 983; Percent complete: 24.6%; Average loss: 3.1925
Iteration: 984; Percent complete: 24.6%; Average loss: 3.3882
Iteration: 985; Percent complete: 24.6%; Average loss: 3.4904
Iteration: 986; Percent complete: 24.6%; Average loss: 3.3643
Iteration: 987; Percent complete: 24.7%; Average loss: 3.3921
Iteration: 988; Percent complete: 24.7%; Average loss: 3.4651
Iteration: 989; Percent complete: 24.7%; Average loss: 3.5108
Iteration: 990; Percent complete: 24.8%; Average loss: 3.3441
Iteration: 991; Percent complete: 24.8%; Average loss: 3.2384
Iteration: 992; Percent complete: 24.8%; Average loss: 3.6283
Iteration: 993; Percent complete: 24.8%; Average loss: 3.5021
Iteration: 994; Percent complete: 24.9%; Average loss: 3.3586
Iteration: 995; Percent complete: 24.9%; Average loss: 3.3469
Iteration: 996; Percent complete: 24.9%; Average loss: 3.5247
Iteration: 997; Percent complete: 24.9%; Average loss: 3.6872
Iteration: 998; Percent complete: 24.9%; Average loss: 3.2640
Iteration: 999; Percent complete: 25.0%; Average loss: 3.2856
Iteration: 1000; Percent complete: 25.0%; Average loss: 3.6344
Iteration: 1001; Percent complete: 25.0%; Average loss: 3.3557
Iteration: 1002; Percent complete: 25.1%; Average loss: 3.4999
Iteration: 1003; Percent complete: 25.1%; Average loss: 3.3111
Iteration: 1004; Percent complete: 25.1%; Average loss: 3.3482
Iteration: 1005; Percent complete: 25.1%; Average loss: 3.8167
Iteration: 1006; Percent complete: 25.1%; Average loss: 3.1977
Iteration: 1007; Percent complete: 25.2%; Average loss: 3.4654
Iteration: 1008; Percent complete: 25.2%; Average loss: 3.6412
Iteration: 1009; Percent complete: 25.2%; Average loss: 3.1567
Iteration: 1010; Percent complete: 25.2%; Average loss: 3.6159
Iteration: 1011; Percent complete: 25.3%; Average loss: 3.2725
Iteration: 1012; Percent complete: 25.3%; Average loss: 3.5881
Iteration: 1013; Percent complete: 25.3%; Average loss: 3.3604
Iteration: 1014; Percent complete: 25.4%; Average loss: 3.7070
Iteration: 1015; Percent complete: 25.4%; Average loss: 3.4405
Iteration: 1016; Percent complete: 25.4%; Average loss: 3.4307
Iteration: 1017; Percent complete: 25.4%; Average loss: 3.4127
Iteration: 1018; Percent complete: 25.4%; Average loss: 3.5964
Iteration: 1019; Percent complete: 25.5%; Average loss: 3.5586
Iteration: 1020; Percent complete: 25.5%; Average loss: 3.2618
Iteration: 1021; Percent complete: 25.5%; Average loss: 3.3934
Iteration: 1022; Percent complete: 25.6%; Average loss: 3.5024
Iteration: 1023; Percent complete: 25.6%; Average loss: 3.7790
Iteration: 1024; Percent complete: 25.6%; Average loss: 3.6504
Iteration: 1025; Percent complete: 25.6%; Average loss: 3.3159
Iteration: 1026; Percent complete: 25.7%; Average loss: 3.7646
Iteration: 1027; Percent complete: 25.7%; Average loss: 3.2594
Iteration: 1028; Percent complete: 25.7%; Average loss: 3.5171
Iteration: 1029; Percent complete: 25.7%; Average loss: 3.6674
Iteration: 1030; Percent complete: 25.8%; Average loss: 3.3055
Iteration: 1031; Percent complete: 25.8%; Average loss: 3.6595
Iteration: 1032; Percent complete: 25.8%; Average loss: 3.6035
Iteration: 1033; Percent complete: 25.8%; Average loss: 3.6519
Iteration: 1034; Percent complete: 25.9%; Average loss: 3.6477
Iteration: 1035; Percent complete: 25.9%; Average loss: 3.0719
Iteration: 1036; Percent complete: 25.9%; Average loss: 3.4190
Iteration: 1037; Percent complete: 25.9%; Average loss: 3.6478
Iteration: 1038; Percent complete: 25.9%; Average loss: 3.5899
Iteration: 1039; Percent complete: 26.0%; Average loss: 3.6157
Iteration: 1040; Percent complete: 26.0%; Average loss: 3.4649
Iteration: 1041; Percent complete: 26.0%; Average loss: 3.5416
Iteration: 1042; Percent complete: 26.1%; Average loss: 3.6732
Iteration: 1043; Percent complete: 26.1%; Average loss: 3.4781
Iteration: 1044; Percent complete: 26.1%; Average loss: 3.3957
Iteration: 1045; Percent complete: 26.1%; Average loss: 3.5128
Iteration: 1046; Percent complete: 26.2%; Average loss: 3.4722
Iteration: 1047; Percent complete: 26.2%; Average loss: 3.2138
Iteration: 1048; Percent complete: 26.2%; Average loss: 3.3561
Iteration: 1049; Percent complete: 26.2%; Average loss: 3.5700
Iteration: 1050; Percent complete: 26.2%; Average loss: 3.3810
Iteration: 1051; Percent complete: 26.3%; Average loss: 3.3118
Iteration: 1052; Percent complete: 26.3%; Average loss: 3.3260
Iteration: 1053; Percent complete: 26.3%; Average loss: 3.7338
Iteration: 1054; Percent complete: 26.4%; Average loss: 3.4693
Iteration: 1055; Percent complete: 26.4%; Average loss: 3.4016
Iteration: 1056; Percent complete: 26.4%; Average loss: 3.1929
Iteration: 1057; Percent complete: 26.4%; Average loss: 3.6294
Iteration: 1058; Percent complete: 26.5%; Average loss: 3.3399
Iteration: 1059; Percent complete: 26.5%; Average loss: 3.6128
Iteration: 1060; Percent complete: 26.5%; Average loss: 3.3338
Iteration: 1061; Percent complete: 26.5%; Average loss: 3.2872
Iteration: 1062; Percent complete: 26.6%; Average loss: 3.4288
Iteration: 1063; Percent complete: 26.6%; Average loss: 3.4632
Iteration: 1064; Percent complete: 26.6%; Average loss: 3.5245
Iteration: 1065; Percent complete: 26.6%; Average loss: 3.4133
Iteration: 1066; Percent complete: 26.7%; Average loss: 3.2545
Iteration: 1067; Percent complete: 26.7%; Average loss: 3.4531
Iteration: 1068; Percent complete: 26.7%; Average loss: 3.3497
Iteration: 1069; Percent complete: 26.7%; Average loss: 3.3815
Iteration: 1070; Percent complete: 26.8%; Average loss: 3.3785
Iteration: 1071; Percent complete: 26.8%; Average loss: 3.3717
Iteration: 1072; Percent complete: 26.8%; Average loss: 3.4654
Iteration: 1073; Percent complete: 26.8%; Average loss: 3.3588
Iteration: 1074; Percent complete: 26.9%; Average loss: 3.4444
Iteration: 1075; Percent complete: 26.9%; Average loss: 3.4807
Iteration: 1076; Percent complete: 26.9%; Average loss: 3.3847
Iteration: 1077; Percent complete: 26.9%; Average loss: 3.4125
Iteration: 1078; Percent complete: 27.0%; Average loss: 3.6388
Iteration: 1079; Percent complete: 27.0%; Average loss: 3.3841
Iteration: 1080; Percent complete: 27.0%; Average loss: 3.4101
Iteration: 1081; Percent complete: 27.0%; Average loss: 3.6217
Iteration: 1082; Percent complete: 27.1%; Average loss: 3.7533
Iteration: 1083; Percent complete: 27.1%; Average loss: 3.3991
Iteration: 1084; Percent complete: 27.1%; Average loss: 3.5137
Iteration: 1085; Percent complete: 27.1%; Average loss: 3.4251
Iteration: 1086; Percent complete: 27.2%; Average loss: 3.4854
Iteration: 1087; Percent complete: 27.2%; Average loss: 3.4987
Iteration: 1088; Percent complete: 27.2%; Average loss: 3.5133
Iteration: 1089; Percent complete: 27.2%; Average loss: 3.5719
Iteration: 1090; Percent complete: 27.3%; Average loss: 3.4034
Iteration: 1091; Percent complete: 27.3%; Average loss: 3.6290
Iteration: 1092; Percent complete: 27.3%; Average loss: 3.5630
Iteration: 1093; Percent complete: 27.3%; Average loss: 3.4548
Iteration: 1094; Percent complete: 27.4%; Average loss: 3.3807
Iteration: 1095; Percent complete: 27.4%; Average loss: 3.3724
Iteration: 1096; Percent complete: 27.4%; Average loss: 3.4102
Iteration: 1097; Percent complete: 27.4%; Average loss: 3.6381
Iteration: 1098; Percent complete: 27.5%; Average loss: 3.5828
Iteration: 1099; Percent complete: 27.5%; Average loss: 3.3238
Iteration: 1100; Percent complete: 27.5%; Average loss: 3.4135
Iteration: 1101; Percent complete: 27.5%; Average loss: 3.0500
Iteration: 1102; Percent complete: 27.6%; Average loss: 3.4654
Iteration: 1103; Percent complete: 27.6%; Average loss: 3.3331
Iteration: 1104; Percent complete: 27.6%; Average loss: 3.2811
Iteration: 1105; Percent complete: 27.6%; Average loss: 3.4092
Iteration: 1106; Percent complete: 27.7%; Average loss: 3.3151
Iteration: 1107; Percent complete: 27.7%; Average loss: 3.4467
Iteration: 1108; Percent complete: 27.7%; Average loss: 3.5167
Iteration: 1109; Percent complete: 27.7%; Average loss: 3.3036
Iteration: 1110; Percent complete: 27.8%; Average loss: 3.4781
Iteration: 1111; Percent complete: 27.8%; Average loss: 3.3126
Iteration: 1112; Percent complete: 27.8%; Average loss: 3.4112
Iteration: 1113; Percent complete: 27.8%; Average loss: 3.3026
Iteration: 1114; Percent complete: 27.9%; Average loss: 3.3577
Iteration: 1115; Percent complete: 27.9%; Average loss: 3.4695
Iteration: 1116; Percent complete: 27.9%; Average loss: 3.5409
Iteration: 1117; Percent complete: 27.9%; Average loss: 3.1290
Iteration: 1118; Percent complete: 28.0%; Average loss: 3.3386
Iteration: 1119; Percent complete: 28.0%; Average loss: 3.3838
Iteration: 1120; Percent complete: 28.0%; Average loss: 3.6034
Iteration: 1121; Percent complete: 28.0%; Average loss: 3.3144
Iteration: 1122; Percent complete: 28.1%; Average loss: 3.2160
Iteration: 1123; Percent complete: 28.1%; Average loss: 3.4916
Iteration: 1124; Percent complete: 28.1%; Average loss: 3.5112
Iteration: 1125; Percent complete: 28.1%; Average loss: 3.2558
Iteration: 1126; Percent complete: 28.1%; Average loss: 3.3465
Iteration: 1127; Percent complete: 28.2%; Average loss: 3.2299
Iteration: 1128; Percent complete: 28.2%; Average loss: 3.0455
Iteration: 1129; Percent complete: 28.2%; Average loss: 3.2863
Iteration: 1130; Percent complete: 28.2%; Average loss: 3.5126
Iteration: 1131; Percent complete: 28.3%; Average loss: 3.3640
Iteration: 1132; Percent complete: 28.3%; Average loss: 3.3768
Iteration: 1133; Percent complete: 28.3%; Average loss: 3.4895
Iteration: 1134; Percent complete: 28.3%; Average loss: 3.5495
Iteration: 1135; Percent complete: 28.4%; Average loss: 3.6043
Iteration: 1136; Percent complete: 28.4%; Average loss: 3.3547
Iteration: 1137; Percent complete: 28.4%; Average loss: 3.4982
Iteration: 1138; Percent complete: 28.4%; Average loss: 3.5709
Iteration: 1139; Percent complete: 28.5%; Average loss: 3.3597
Iteration: 1140; Percent complete: 28.5%; Average loss: 3.4802
Iteration: 1141; Percent complete: 28.5%; Average loss: 3.3167
Iteration: 1142; Percent complete: 28.5%; Average loss: 3.4754
Iteration: 1143; Percent complete: 28.6%; Average loss: 3.5907
Iteration: 1144; Percent complete: 28.6%; Average loss: 3.3072
Iteration: 1145; Percent complete: 28.6%; Average loss: 3.3822
Iteration: 1146; Percent complete: 28.6%; Average loss: 3.3530
Iteration: 1147; Percent complete: 28.7%; Average loss: 3.3792
Iteration: 1148; Percent complete: 28.7%; Average loss: 3.1629
Iteration: 1149; Percent complete: 28.7%; Average loss: 3.2851
Iteration: 1150; Percent complete: 28.7%; Average loss: 3.1867
Iteration: 1151; Percent complete: 28.8%; Average loss: 3.3705
Iteration: 1152; Percent complete: 28.8%; Average loss: 3.4683
Iteration: 1153; Percent complete: 28.8%; Average loss: 3.5187
Iteration: 1154; Percent complete: 28.8%; Average loss: 3.2467
Iteration: 1155; Percent complete: 28.9%; Average loss: 3.5410
Iteration: 1156; Percent complete: 28.9%; Average loss: 3.3555
Iteration: 1157; Percent complete: 28.9%; Average loss: 3.5891
Iteration: 1158; Percent complete: 28.9%; Average loss: 3.1611
Iteration: 1159; Percent complete: 29.0%; Average loss: 3.4567
Iteration: 1160; Percent complete: 29.0%; Average loss: 3.4420
Iteration: 1161; Percent complete: 29.0%; Average loss: 3.2794
Iteration: 1162; Percent complete: 29.0%; Average loss: 3.2571
Iteration: 1163; Percent complete: 29.1%; Average loss: 3.4736
Iteration: 1164; Percent complete: 29.1%; Average loss: 3.7988
Iteration: 1165; Percent complete: 29.1%; Average loss: 3.4963
Iteration: 1166; Percent complete: 29.1%; Average loss: 3.6633
Iteration: 1167; Percent complete: 29.2%; Average loss: 3.4230
Iteration: 1168; Percent complete: 29.2%; Average loss: 3.3817
Iteration: 1169; Percent complete: 29.2%; Average loss: 3.3973
Iteration: 1170; Percent complete: 29.2%; Average loss: 3.3064
Iteration: 1171; Percent complete: 29.3%; Average loss: 3.5471
Iteration: 1172; Percent complete: 29.3%; Average loss: 3.3540
Iteration: 1173; Percent complete: 29.3%; Average loss: 3.3911
Iteration: 1174; Percent complete: 29.3%; Average loss: 3.2646
Iteration: 1175; Percent complete: 29.4%; Average loss: 3.4524
Iteration: 1176; Percent complete: 29.4%; Average loss: 3.2398
Iteration: 1177; Percent complete: 29.4%; Average loss: 3.7454
Iteration: 1178; Percent complete: 29.4%; Average loss: 3.4311
Iteration: 1179; Percent complete: 29.5%; Average loss: 3.2237
Iteration: 1180; Percent complete: 29.5%; Average loss: 3.4645
Iteration: 1181; Percent complete: 29.5%; Average loss: 3.4301
Iteration: 1182; Percent complete: 29.5%; Average loss: 3.3515
Iteration: 1183; Percent complete: 29.6%; Average loss: 3.6014
Iteration: 1184; Percent complete: 29.6%; Average loss: 3.4307
Iteration: 1185; Percent complete: 29.6%; Average loss: 3.3872
Iteration: 1186; Percent complete: 29.6%; Average loss: 3.5243
Iteration: 1187; Percent complete: 29.7%; Average loss: 3.4857
Iteration: 1188; Percent complete: 29.7%; Average loss: 3.4571
Iteration: 1189; Percent complete: 29.7%; Average loss: 3.3295
Iteration: 1190; Percent complete: 29.8%; Average loss: 3.3657
Iteration: 1191; Percent complete: 29.8%; Average loss: 3.3523
Iteration: 1192; Percent complete: 29.8%; Average loss: 3.3539
Iteration: 1193; Percent complete: 29.8%; Average loss: 3.4012
Iteration: 1194; Percent complete: 29.8%; Average loss: 3.4454
Iteration: 1195; Percent complete: 29.9%; Average loss: 3.3727
Iteration: 1196; Percent complete: 29.9%; Average loss: 3.3332
Iteration: 1197; Percent complete: 29.9%; Average loss: 3.5099
Iteration: 1198; Percent complete: 29.9%; Average loss: 3.6037
Iteration: 1199; Percent complete: 30.0%; Average loss: 3.3960
Iteration: 1200; Percent complete: 30.0%; Average loss: 3.2995
Iteration: 1201; Percent complete: 30.0%; Average loss: 3.3612
Iteration: 1202; Percent complete: 30.0%; Average loss: 3.5049
Iteration: 1203; Percent complete: 30.1%; Average loss: 3.6731
Iteration: 1204; Percent complete: 30.1%; Average loss: 3.4515
Iteration: 1205; Percent complete: 30.1%; Average loss: 3.6891
Iteration: 1206; Percent complete: 30.1%; Average loss: 3.4113
Iteration: 1207; Percent complete: 30.2%; Average loss: 3.4439
Iteration: 1208; Percent complete: 30.2%; Average loss: 3.3608
Iteration: 1209; Percent complete: 30.2%; Average loss: 3.3670
Iteration: 1210; Percent complete: 30.2%; Average loss: 3.6276
Iteration: 1211; Percent complete: 30.3%; Average loss: 3.5181
Iteration: 1212; Percent complete: 30.3%; Average loss: 3.5343
Iteration: 1213; Percent complete: 30.3%; Average loss: 3.4858
Iteration: 1214; Percent complete: 30.3%; Average loss: 3.4249
Iteration: 1215; Percent complete: 30.4%; Average loss: 3.2873
Iteration: 1216; Percent complete: 30.4%; Average loss: 3.4201
Iteration: 1217; Percent complete: 30.4%; Average loss: 3.5356
Iteration: 1218; Percent complete: 30.4%; Average loss: 3.0910
Iteration: 1219; Percent complete: 30.5%; Average loss: 3.2853
Iteration: 1220; Percent complete: 30.5%; Average loss: 3.4095
Iteration: 1221; Percent complete: 30.5%; Average loss: 3.6145
Iteration: 1222; Percent complete: 30.6%; Average loss: 3.5679
Iteration: 1223; Percent complete: 30.6%; Average loss: 3.5057
Iteration: 1224; Percent complete: 30.6%; Average loss: 3.1806
Iteration: 1225; Percent complete: 30.6%; Average loss: 3.2828
Iteration: 1226; Percent complete: 30.6%; Average loss: 3.3814
Iteration: 1227; Percent complete: 30.7%; Average loss: 3.4939
Iteration: 1228; Percent complete: 30.7%; Average loss: 3.0973
Iteration: 1229; Percent complete: 30.7%; Average loss: 3.5677
Iteration: 1230; Percent complete: 30.8%; Average loss: 3.6633
Iteration: 1231; Percent complete: 30.8%; Average loss: 3.4758
Iteration: 1232; Percent complete: 30.8%; Average loss: 3.5527
Iteration: 1233; Percent complete: 30.8%; Average loss: 3.4431
Iteration: 1234; Percent complete: 30.9%; Average loss: 3.5476
Iteration: 1235; Percent complete: 30.9%; Average loss: 3.2155
Iteration: 1236; Percent complete: 30.9%; Average loss: 3.2396
Iteration: 1237; Percent complete: 30.9%; Average loss: 3.3594
Iteration: 1238; Percent complete: 30.9%; Average loss: 3.4031
Iteration: 1239; Percent complete: 31.0%; Average loss: 3.6784
Iteration: 1240; Percent complete: 31.0%; Average loss: 3.4399
Iteration: 1241; Percent complete: 31.0%; Average loss: 3.3147
Iteration: 1242; Percent complete: 31.1%; Average loss: 3.4906
Iteration: 1243; Percent complete: 31.1%; Average loss: 3.2530
Iteration: 1244; Percent complete: 31.1%; Average loss: 3.4263
Iteration: 1245; Percent complete: 31.1%; Average loss: 3.5248
Iteration: 1246; Percent complete: 31.1%; Average loss: 3.5499
Iteration: 1247; Percent complete: 31.2%; Average loss: 3.3287
Iteration: 1248; Percent complete: 31.2%; Average loss: 3.5964
Iteration: 1249; Percent complete: 31.2%; Average loss: 3.5001
Iteration: 1250; Percent complete: 31.2%; Average loss: 3.3728
Iteration: 1251; Percent complete: 31.3%; Average loss: 3.4890
Iteration: 1252; Percent complete: 31.3%; Average loss: 3.3556
Iteration: 1253; Percent complete: 31.3%; Average loss: 3.0470
Iteration: 1254; Percent complete: 31.4%; Average loss: 3.2561
Iteration: 1255; Percent complete: 31.4%; Average loss: 3.4112
Iteration: 1256; Percent complete: 31.4%; Average loss: 3.2358
Iteration: 1257; Percent complete: 31.4%; Average loss: 3.4496
Iteration: 1258; Percent complete: 31.4%; Average loss: 3.4225
Iteration: 1259; Percent complete: 31.5%; Average loss: 3.3897
Iteration: 1260; Percent complete: 31.5%; Average loss: 3.3921
Iteration: 1261; Percent complete: 31.5%; Average loss: 3.2807
Iteration: 1262; Percent complete: 31.6%; Average loss: 3.5185
Iteration: 1263; Percent complete: 31.6%; Average loss: 3.5175
Iteration: 1264; Percent complete: 31.6%; Average loss: 3.3817
Iteration: 1265; Percent complete: 31.6%; Average loss: 3.5473
Iteration: 1266; Percent complete: 31.6%; Average loss: 3.2850
Iteration: 1267; Percent complete: 31.7%; Average loss: 3.7204
Iteration: 1268; Percent complete: 31.7%; Average loss: 3.3668
Iteration: 1269; Percent complete: 31.7%; Average loss: 3.3679
Iteration: 1270; Percent complete: 31.8%; Average loss: 2.9841
Iteration: 1271; Percent complete: 31.8%; Average loss: 3.6793
Iteration: 1272; Percent complete: 31.8%; Average loss: 3.2475
Iteration: 1273; Percent complete: 31.8%; Average loss: 3.6738
Iteration: 1274; Percent complete: 31.9%; Average loss: 3.4221
Iteration: 1275; Percent complete: 31.9%; Average loss: 3.4800
Iteration: 1276; Percent complete: 31.9%; Average loss: 3.3375
Iteration: 1277; Percent complete: 31.9%; Average loss: 3.3550
Iteration: 1278; Percent complete: 31.9%; Average loss: 3.3156
Iteration: 1279; Percent complete: 32.0%; Average loss: 3.4752
Iteration: 1280; Percent complete: 32.0%; Average loss: 3.2377
Iteration: 1281; Percent complete: 32.0%; Average loss: 3.3096
Iteration: 1282; Percent complete: 32.0%; Average loss: 3.3690
Iteration: 1283; Percent complete: 32.1%; Average loss: 3.3386
Iteration: 1284; Percent complete: 32.1%; Average loss: 3.3791
Iteration: 1285; Percent complete: 32.1%; Average loss: 3.3691
Iteration: 1286; Percent complete: 32.1%; Average loss: 3.4706
Iteration: 1287; Percent complete: 32.2%; Average loss: 3.6579
Iteration: 1288; Percent complete: 32.2%; Average loss: 3.5406
Iteration: 1289; Percent complete: 32.2%; Average loss: 3.2602
Iteration: 1290; Percent complete: 32.2%; Average loss: 3.1971
Iteration: 1291; Percent complete: 32.3%; Average loss: 3.2424
Iteration: 1292; Percent complete: 32.3%; Average loss: 3.2982
Iteration: 1293; Percent complete: 32.3%; Average loss: 3.5036
Iteration: 1294; Percent complete: 32.4%; Average loss: 3.4529
Iteration: 1295; Percent complete: 32.4%; Average loss: 3.2036
Iteration: 1296; Percent complete: 32.4%; Average loss: 3.4956
Iteration: 1297; Percent complete: 32.4%; Average loss: 3.5694
Iteration: 1298; Percent complete: 32.5%; Average loss: 3.2693
Iteration: 1299; Percent complete: 32.5%; Average loss: 3.3764
Iteration: 1300; Percent complete: 32.5%; Average loss: 3.4729
Iteration: 1301; Percent complete: 32.5%; Average loss: 3.3528
Iteration: 1302; Percent complete: 32.6%; Average loss: 3.4835
Iteration: 1303; Percent complete: 32.6%; Average loss: 3.3961
Iteration: 1304; Percent complete: 32.6%; Average loss: 3.4081
Iteration: 1305; Percent complete: 32.6%; Average loss: 3.2740
Iteration: 1306; Percent complete: 32.6%; Average loss: 3.3406
Iteration: 1307; Percent complete: 32.7%; Average loss: 3.3965
Iteration: 1308; Percent complete: 32.7%; Average loss: 3.5712
Iteration: 1309; Percent complete: 32.7%; Average loss: 3.4132
Iteration: 1310; Percent complete: 32.8%; Average loss: 3.3108
Iteration: 1311; Percent complete: 32.8%; Average loss: 3.0395
Iteration: 1312; Percent complete: 32.8%; Average loss: 3.2254
Iteration: 1313; Percent complete: 32.8%; Average loss: 3.4167
Iteration: 1314; Percent complete: 32.9%; Average loss: 3.5567
Iteration: 1315; Percent complete: 32.9%; Average loss: 3.3774
Iteration: 1316; Percent complete: 32.9%; Average loss: 3.2843
Iteration: 1317; Percent complete: 32.9%; Average loss: 3.3873
Iteration: 1318; Percent complete: 33.0%; Average loss: 3.4159
Iteration: 1319; Percent complete: 33.0%; Average loss: 3.6578
Iteration: 1320; Percent complete: 33.0%; Average loss: 3.3917
Iteration: 1321; Percent complete: 33.0%; Average loss: 3.2282
Iteration: 1322; Percent complete: 33.1%; Average loss: 3.3629
Iteration: 1323; Percent complete: 33.1%; Average loss: 3.4147
Iteration: 1324; Percent complete: 33.1%; Average loss: 3.5469
Iteration: 1325; Percent complete: 33.1%; Average loss: 3.3477
Iteration: 1326; Percent complete: 33.1%; Average loss: 3.2999
Iteration: 1327; Percent complete: 33.2%; Average loss: 3.6014
Iteration: 1328; Percent complete: 33.2%; Average loss: 3.1619
Iteration: 1329; Percent complete: 33.2%; Average loss: 3.1355
Iteration: 1330; Percent complete: 33.2%; Average loss: 3.1820
Iteration: 1331; Percent complete: 33.3%; Average loss: 3.2316
Iteration: 1332; Percent complete: 33.3%; Average loss: 3.6391
Iteration: 1333; Percent complete: 33.3%; Average loss: 3.1833
Iteration: 1334; Percent complete: 33.4%; Average loss: 3.4084
Iteration: 1335; Percent complete: 33.4%; Average loss: 3.3018
Iteration: 1336; Percent complete: 33.4%; Average loss: 3.4183
Iteration: 1337; Percent complete: 33.4%; Average loss: 3.1171
Iteration: 1338; Percent complete: 33.5%; Average loss: 3.2053
Iteration: 1339; Percent complete: 33.5%; Average loss: 3.3139
Iteration: 1340; Percent complete: 33.5%; Average loss: 3.3699
Iteration: 1341; Percent complete: 33.5%; Average loss: 3.3469
Iteration: 1342; Percent complete: 33.6%; Average loss: 3.4531
Iteration: 1343; Percent complete: 33.6%; Average loss: 2.9908
Iteration: 1344; Percent complete: 33.6%; Average loss: 3.5352
Iteration: 1345; Percent complete: 33.6%; Average loss: 3.4950
Iteration: 1346; Percent complete: 33.7%; Average loss: 3.3309
Iteration: 1347; Percent complete: 33.7%; Average loss: 3.4137
Iteration: 1348; Percent complete: 33.7%; Average loss: 3.3953
Iteration: 1349; Percent complete: 33.7%; Average loss: 3.1983
Iteration: 1350; Percent complete: 33.8%; Average loss: 2.9791
Iteration: 1351; Percent complete: 33.8%; Average loss: 3.3358
Iteration: 1352; Percent complete: 33.8%; Average loss: 3.3515
Iteration: 1353; Percent complete: 33.8%; Average loss: 3.4441
Iteration: 1354; Percent complete: 33.9%; Average loss: 3.4748
Iteration: 1355; Percent complete: 33.9%; Average loss: 3.2151
Iteration: 1356; Percent complete: 33.9%; Average loss: 3.5369
Iteration: 1357; Percent complete: 33.9%; Average loss: 3.6263
Iteration: 1358; Percent complete: 34.0%; Average loss: 3.3766
Iteration: 1359; Percent complete: 34.0%; Average loss: 3.1563
Iteration: 1360; Percent complete: 34.0%; Average loss: 3.3140
Iteration: 1361; Percent complete: 34.0%; Average loss: 3.2291
Iteration: 1362; Percent complete: 34.1%; Average loss: 3.2671
Iteration: 1363; Percent complete: 34.1%; Average loss: 3.3742
Iteration: 1364; Percent complete: 34.1%; Average loss: 3.3175
Iteration: 1365; Percent complete: 34.1%; Average loss: 3.5485
Iteration: 1366; Percent complete: 34.2%; Average loss: 3.4972
Iteration: 1367; Percent complete: 34.2%; Average loss: 3.5028
Iteration: 1368; Percent complete: 34.2%; Average loss: 3.2650
Iteration: 1369; Percent complete: 34.2%; Average loss: 3.4138
Iteration: 1370; Percent complete: 34.2%; Average loss: 3.2776
Iteration: 1371; Percent complete: 34.3%; Average loss: 3.1125
Iteration: 1372; Percent complete: 34.3%; Average loss: 3.4378
Iteration: 1373; Percent complete: 34.3%; Average loss: 3.1906
Iteration: 1374; Percent complete: 34.4%; Average loss: 3.1139
Iteration: 1375; Percent complete: 34.4%; Average loss: 3.3402
Iteration: 1376; Percent complete: 34.4%; Average loss: 3.5281
Iteration: 1377; Percent complete: 34.4%; Average loss: 3.1351
Iteration: 1378; Percent complete: 34.4%; Average loss: 3.1681
Iteration: 1379; Percent complete: 34.5%; Average loss: 3.1776
Iteration: 1380; Percent complete: 34.5%; Average loss: 3.1625
Iteration: 1381; Percent complete: 34.5%; Average loss: 3.3978
Iteration: 1382; Percent complete: 34.5%; Average loss: 3.4203
Iteration: 1383; Percent complete: 34.6%; Average loss: 3.2432
Iteration: 1384; Percent complete: 34.6%; Average loss: 3.5077
Iteration: 1385; Percent complete: 34.6%; Average loss: 3.2336
Iteration: 1386; Percent complete: 34.6%; Average loss: 3.4480
Iteration: 1387; Percent complete: 34.7%; Average loss: 3.5162
Iteration: 1388; Percent complete: 34.7%; Average loss: 3.2058
Iteration: 1389; Percent complete: 34.7%; Average loss: 3.3179
Iteration: 1390; Percent complete: 34.8%; Average loss: 3.3401
Iteration: 1391; Percent complete: 34.8%; Average loss: 3.1896
Iteration: 1392; Percent complete: 34.8%; Average loss: 3.2421
Iteration: 1393; Percent complete: 34.8%; Average loss: 3.3959
Iteration: 1394; Percent complete: 34.8%; Average loss: 3.2440
Iteration: 1395; Percent complete: 34.9%; Average loss: 3.5844
Iteration: 1396; Percent complete: 34.9%; Average loss: 3.2310
Iteration: 1397; Percent complete: 34.9%; Average loss: 3.3752
Iteration: 1398; Percent complete: 34.9%; Average loss: 3.3072
Iteration: 1399; Percent complete: 35.0%; Average loss: 3.2432
Iteration: 1400; Percent complete: 35.0%; Average loss: 3.1780
Iteration: 1401; Percent complete: 35.0%; Average loss: 3.4486
Iteration: 1402; Percent complete: 35.0%; Average loss: 3.0594
Iteration: 1403; Percent complete: 35.1%; Average loss: 3.5374
Iteration: 1404; Percent complete: 35.1%; Average loss: 3.5770
Iteration: 1405; Percent complete: 35.1%; Average loss: 3.3777
Iteration: 1406; Percent complete: 35.1%; Average loss: 3.0432
Iteration: 1407; Percent complete: 35.2%; Average loss: 3.3580
Iteration: 1408; Percent complete: 35.2%; Average loss: 3.3683
Iteration: 1409; Percent complete: 35.2%; Average loss: 3.4061
Iteration: 1410; Percent complete: 35.2%; Average loss: 3.4857
Iteration: 1411; Percent complete: 35.3%; Average loss: 3.3569
Iteration: 1412; Percent complete: 35.3%; Average loss: 3.6793
Iteration: 1413; Percent complete: 35.3%; Average loss: 3.5898
Iteration: 1414; Percent complete: 35.4%; Average loss: 3.3733
Iteration: 1415; Percent complete: 35.4%; Average loss: 3.1844
Iteration: 1416; Percent complete: 35.4%; Average loss: 3.3518
Iteration: 1417; Percent complete: 35.4%; Average loss: 3.3875
Iteration: 1418; Percent complete: 35.4%; Average loss: 3.4643
Iteration: 1419; Percent complete: 35.5%; Average loss: 3.4284
Iteration: 1420; Percent complete: 35.5%; Average loss: 3.4719
Iteration: 1421; Percent complete: 35.5%; Average loss: 3.3416
Iteration: 1422; Percent complete: 35.5%; Average loss: 3.0334
Iteration: 1423; Percent complete: 35.6%; Average loss: 3.2296
Iteration: 1424; Percent complete: 35.6%; Average loss: 3.7466
Iteration: 1425; Percent complete: 35.6%; Average loss: 3.3668
Iteration: 1426; Percent complete: 35.6%; Average loss: 3.4503
Iteration: 1427; Percent complete: 35.7%; Average loss: 3.3245
Iteration: 1428; Percent complete: 35.7%; Average loss: 3.3041
Iteration: 1429; Percent complete: 35.7%; Average loss: 3.4035
Iteration: 1430; Percent complete: 35.8%; Average loss: 3.3838
Iteration: 1431; Percent complete: 35.8%; Average loss: 3.3279
Iteration: 1432; Percent complete: 35.8%; Average loss: 3.2498
Iteration: 1433; Percent complete: 35.8%; Average loss: 3.1052
Iteration: 1434; Percent complete: 35.9%; Average loss: 3.3336
Iteration: 1435; Percent complete: 35.9%; Average loss: 3.3809
Iteration: 1436; Percent complete: 35.9%; Average loss: 3.2971
Iteration: 1437; Percent complete: 35.9%; Average loss: 3.3670
Iteration: 1438; Percent complete: 35.9%; Average loss: 3.1845
Iteration: 1439; Percent complete: 36.0%; Average loss: 3.3484
Iteration: 1440; Percent complete: 36.0%; Average loss: 3.5092
Iteration: 1441; Percent complete: 36.0%; Average loss: 3.2103
Iteration: 1442; Percent complete: 36.0%; Average loss: 3.2373
Iteration: 1443; Percent complete: 36.1%; Average loss: 3.2637
Iteration: 1444; Percent complete: 36.1%; Average loss: 3.0115
Iteration: 1445; Percent complete: 36.1%; Average loss: 3.2642
Iteration: 1446; Percent complete: 36.1%; Average loss: 3.4586
Iteration: 1447; Percent complete: 36.2%; Average loss: 3.1145
Iteration: 1448; Percent complete: 36.2%; Average loss: 3.3798
Iteration: 1449; Percent complete: 36.2%; Average loss: 3.0565
Iteration: 1450; Percent complete: 36.2%; Average loss: 3.4058
Iteration: 1451; Percent complete: 36.3%; Average loss: 3.4100
Iteration: 1452; Percent complete: 36.3%; Average loss: 3.1424
Iteration: 1453; Percent complete: 36.3%; Average loss: 3.3501
Iteration: 1454; Percent complete: 36.4%; Average loss: 3.3508
Iteration: 1455; Percent complete: 36.4%; Average loss: 3.4051
Iteration: 1456; Percent complete: 36.4%; Average loss: 3.6073
Iteration: 1457; Percent complete: 36.4%; Average loss: 3.4933
Iteration: 1458; Percent complete: 36.4%; Average loss: 3.4897
Iteration: 1459; Percent complete: 36.5%; Average loss: 3.3954
Iteration: 1460; Percent complete: 36.5%; Average loss: 3.4267
Iteration: 1461; Percent complete: 36.5%; Average loss: 3.1165
Iteration: 1462; Percent complete: 36.5%; Average loss: 3.3756
Iteration: 1463; Percent complete: 36.6%; Average loss: 3.0379
Iteration: 1464; Percent complete: 36.6%; Average loss: 3.2308
Iteration: 1465; Percent complete: 36.6%; Average loss: 3.3674
Iteration: 1466; Percent complete: 36.6%; Average loss: 3.3031
Iteration: 1467; Percent complete: 36.7%; Average loss: 3.4673
Iteration: 1468; Percent complete: 36.7%; Average loss: 3.2669
Iteration: 1469; Percent complete: 36.7%; Average loss: 3.2578
Iteration: 1470; Percent complete: 36.8%; Average loss: 3.2411
Iteration: 1471; Percent complete: 36.8%; Average loss: 3.4563
Iteration: 1472; Percent complete: 36.8%; Average loss: 3.2029
Iteration: 1473; Percent complete: 36.8%; Average loss: 3.3177
Iteration: 1474; Percent complete: 36.9%; Average loss: 3.5074
Iteration: 1475; Percent complete: 36.9%; Average loss: 3.2161
Iteration: 1476; Percent complete: 36.9%; Average loss: 3.4091
Iteration: 1477; Percent complete: 36.9%; Average loss: 3.3088
Iteration: 1478; Percent complete: 37.0%; Average loss: 3.3201
Iteration: 1479; Percent complete: 37.0%; Average loss: 3.5430
Iteration: 1480; Percent complete: 37.0%; Average loss: 3.2542
Iteration: 1481; Percent complete: 37.0%; Average loss: 3.6075
Iteration: 1482; Percent complete: 37.0%; Average loss: 3.2844
Iteration: 1483; Percent complete: 37.1%; Average loss: 3.3889
Iteration: 1484; Percent complete: 37.1%; Average loss: 3.5752
Iteration: 1485; Percent complete: 37.1%; Average loss: 3.1790
Iteration: 1486; Percent complete: 37.1%; Average loss: 3.3092
Iteration: 1487; Percent complete: 37.2%; Average loss: 3.2531
Iteration: 1488; Percent complete: 37.2%; Average loss: 3.1786
Iteration: 1489; Percent complete: 37.2%; Average loss: 3.0550
Iteration: 1490; Percent complete: 37.2%; Average loss: 3.2546
Iteration: 1491; Percent complete: 37.3%; Average loss: 3.3910
Iteration: 1492; Percent complete: 37.3%; Average loss: 3.1879
Iteration: 1493; Percent complete: 37.3%; Average loss: 3.3595
Iteration: 1494; Percent complete: 37.4%; Average loss: 3.3587
Iteration: 1495; Percent complete: 37.4%; Average loss: 3.4953
Iteration: 1496; Percent complete: 37.4%; Average loss: 3.6447
Iteration: 1497; Percent complete: 37.4%; Average loss: 3.1064
Iteration: 1498; Percent complete: 37.5%; Average loss: 3.3906
Iteration: 1499; Percent complete: 37.5%; Average loss: 3.3185
Iteration: 1500; Percent complete: 37.5%; Average loss: 3.1993
Iteration: 1501; Percent complete: 37.5%; Average loss: 3.4278
Iteration: 1502; Percent complete: 37.5%; Average loss: 3.3946
Iteration: 1503; Percent complete: 37.6%; Average loss: 3.3704
Iteration: 1504; Percent complete: 37.6%; Average loss: 3.3012
Iteration: 1505; Percent complete: 37.6%; Average loss: 3.5243
Iteration: 1506; Percent complete: 37.6%; Average loss: 3.4580
Iteration: 1507; Percent complete: 37.7%; Average loss: 3.3400
Iteration: 1508; Percent complete: 37.7%; Average loss: 3.0216
Iteration: 1509; Percent complete: 37.7%; Average loss: 3.4791
Iteration: 1510; Percent complete: 37.8%; Average loss: 3.2597
Iteration: 1511; Percent complete: 37.8%; Average loss: 3.2425
Iteration: 1512; Percent complete: 37.8%; Average loss: 3.3691
Iteration: 1513; Percent complete: 37.8%; Average loss: 3.2540
Iteration: 1514; Percent complete: 37.9%; Average loss: 3.1947
Iteration: 1515; Percent complete: 37.9%; Average loss: 3.0295
Iteration: 1516; Percent complete: 37.9%; Average loss: 3.3932
Iteration: 1517; Percent complete: 37.9%; Average loss: 3.1295
Iteration: 1518; Percent complete: 38.0%; Average loss: 3.2070
Iteration: 1519; Percent complete: 38.0%; Average loss: 3.3205
Iteration: 1520; Percent complete: 38.0%; Average loss: 3.2467
Iteration: 1521; Percent complete: 38.0%; Average loss: 3.4494
Iteration: 1522; Percent complete: 38.0%; Average loss: 3.3684
Iteration: 1523; Percent complete: 38.1%; Average loss: 3.3705
Iteration: 1524; Percent complete: 38.1%; Average loss: 3.3328
Iteration: 1525; Percent complete: 38.1%; Average loss: 3.1326
Iteration: 1526; Percent complete: 38.1%; Average loss: 3.3021
Iteration: 1527; Percent complete: 38.2%; Average loss: 3.2095
Iteration: 1528; Percent complete: 38.2%; Average loss: 3.6061
Iteration: 1529; Percent complete: 38.2%; Average loss: 3.3291
Iteration: 1530; Percent complete: 38.2%; Average loss: 3.1350
Iteration: 1531; Percent complete: 38.3%; Average loss: 3.3989
Iteration: 1532; Percent complete: 38.3%; Average loss: 3.2962
Iteration: 1533; Percent complete: 38.3%; Average loss: 3.3437
Iteration: 1534; Percent complete: 38.4%; Average loss: 3.2370
Iteration: 1535; Percent complete: 38.4%; Average loss: 3.2109
Iteration: 1536; Percent complete: 38.4%; Average loss: 3.2953
Iteration: 1537; Percent complete: 38.4%; Average loss: 3.2413
Iteration: 1538; Percent complete: 38.5%; Average loss: 3.1064
Iteration: 1539; Percent complete: 38.5%; Average loss: 3.2217
Iteration: 1540; Percent complete: 38.5%; Average loss: 3.2373
Iteration: 1541; Percent complete: 38.5%; Average loss: 3.1695
Iteration: 1542; Percent complete: 38.6%; Average loss: 3.1699
Iteration: 1543; Percent complete: 38.6%; Average loss: 3.2389
Iteration: 1544; Percent complete: 38.6%; Average loss: 3.0465
Iteration: 1545; Percent complete: 38.6%; Average loss: 3.3977
Iteration: 1546; Percent complete: 38.6%; Average loss: 3.4519
Iteration: 1547; Percent complete: 38.7%; Average loss: 3.0075
Iteration: 1548; Percent complete: 38.7%; Average loss: 2.9337
Iteration: 1549; Percent complete: 38.7%; Average loss: 3.3409
Iteration: 1550; Percent complete: 38.8%; Average loss: 3.3181
Iteration: 1551; Percent complete: 38.8%; Average loss: 3.2603
Iteration: 1552; Percent complete: 38.8%; Average loss: 3.2429
Iteration: 1553; Percent complete: 38.8%; Average loss: 3.2663
Iteration: 1554; Percent complete: 38.9%; Average loss: 3.1158
Iteration: 1555; Percent complete: 38.9%; Average loss: 3.2886
Iteration: 1556; Percent complete: 38.9%; Average loss: 3.2492
Iteration: 1557; Percent complete: 38.9%; Average loss: 3.4235
Iteration: 1558; Percent complete: 39.0%; Average loss: 3.1917
Iteration: 1559; Percent complete: 39.0%; Average loss: 3.5011
Iteration: 1560; Percent complete: 39.0%; Average loss: 3.2944
Iteration: 1561; Percent complete: 39.0%; Average loss: 3.3772
Iteration: 1562; Percent complete: 39.1%; Average loss: 3.3989
Iteration: 1563; Percent complete: 39.1%; Average loss: 3.0033
Iteration: 1564; Percent complete: 39.1%; Average loss: 3.1707
Iteration: 1565; Percent complete: 39.1%; Average loss: 3.4896
Iteration: 1566; Percent complete: 39.1%; Average loss: 3.2488
Iteration: 1567; Percent complete: 39.2%; Average loss: 3.2768
Iteration: 1568; Percent complete: 39.2%; Average loss: 3.3139
Iteration: 1569; Percent complete: 39.2%; Average loss: 3.2253
Iteration: 1570; Percent complete: 39.2%; Average loss: 3.1332
Iteration: 1571; Percent complete: 39.3%; Average loss: 2.9962
Iteration: 1572; Percent complete: 39.3%; Average loss: 3.2932
Iteration: 1573; Percent complete: 39.3%; Average loss: 3.3990
Iteration: 1574; Percent complete: 39.4%; Average loss: 3.3040
Iteration: 1575; Percent complete: 39.4%; Average loss: 3.4925
Iteration: 1576; Percent complete: 39.4%; Average loss: 3.2405
Iteration: 1577; Percent complete: 39.4%; Average loss: 3.4899
Iteration: 1578; Percent complete: 39.5%; Average loss: 3.4162
Iteration: 1579; Percent complete: 39.5%; Average loss: 3.2730
Iteration: 1580; Percent complete: 39.5%; Average loss: 3.2627
Iteration: 1581; Percent complete: 39.5%; Average loss: 3.4713
Iteration: 1582; Percent complete: 39.6%; Average loss: 3.2726
Iteration: 1583; Percent complete: 39.6%; Average loss: 3.2876
Iteration: 1584; Percent complete: 39.6%; Average loss: 3.4332
Iteration: 1585; Percent complete: 39.6%; Average loss: 3.2349
Iteration: 1586; Percent complete: 39.6%; Average loss: 3.0991
Iteration: 1587; Percent complete: 39.7%; Average loss: 3.3122
Iteration: 1588; Percent complete: 39.7%; Average loss: 3.4182
Iteration: 1589; Percent complete: 39.7%; Average loss: 3.3688
Iteration: 1590; Percent complete: 39.8%; Average loss: 3.3557
Iteration: 1591; Percent complete: 39.8%; Average loss: 3.3419
Iteration: 1592; Percent complete: 39.8%; Average loss: 3.1716
Iteration: 1593; Percent complete: 39.8%; Average loss: 3.1117
Iteration: 1594; Percent complete: 39.9%; Average loss: 3.4304
Iteration: 1595; Percent complete: 39.9%; Average loss: 3.4447
Iteration: 1596; Percent complete: 39.9%; Average loss: 3.4075
Iteration: 1597; Percent complete: 39.9%; Average loss: 2.9159
Iteration: 1598; Percent complete: 40.0%; Average loss: 3.3219
Iteration: 1599; Percent complete: 40.0%; Average loss: 3.2919
Iteration: 1600; Percent complete: 40.0%; Average loss: 3.4034
Iteration: 1601; Percent complete: 40.0%; Average loss: 3.3935
Iteration: 1602; Percent complete: 40.1%; Average loss: 3.3581
Iteration: 1603; Percent complete: 40.1%; Average loss: 3.3503
Iteration: 1604; Percent complete: 40.1%; Average loss: 3.1718
Iteration: 1605; Percent complete: 40.1%; Average loss: 3.1767
Iteration: 1606; Percent complete: 40.2%; Average loss: 3.2421
Iteration: 1607; Percent complete: 40.2%; Average loss: 3.2191
Iteration: 1608; Percent complete: 40.2%; Average loss: 3.2856
Iteration: 1609; Percent complete: 40.2%; Average loss: 3.1244
Iteration: 1610; Percent complete: 40.2%; Average loss: 3.1797
Iteration: 1611; Percent complete: 40.3%; Average loss: 3.4183
Iteration: 1612; Percent complete: 40.3%; Average loss: 3.3743
Iteration: 1613; Percent complete: 40.3%; Average loss: 3.1083
Iteration: 1614; Percent complete: 40.4%; Average loss: 3.6284
Iteration: 1615; Percent complete: 40.4%; Average loss: 3.2277
Iteration: 1616; Percent complete: 40.4%; Average loss: 3.2691
Iteration: 1617; Percent complete: 40.4%; Average loss: 3.1325
Iteration: 1618; Percent complete: 40.5%; Average loss: 3.3298
Iteration: 1619; Percent complete: 40.5%; Average loss: 3.1512
Iteration: 1620; Percent complete: 40.5%; Average loss: 3.1428
Iteration: 1621; Percent complete: 40.5%; Average loss: 3.5807
Iteration: 1622; Percent complete: 40.6%; Average loss: 3.0017
Iteration: 1623; Percent complete: 40.6%; Average loss: 3.4082
Iteration: 1624; Percent complete: 40.6%; Average loss: 3.4250
Iteration: 1625; Percent complete: 40.6%; Average loss: 3.3106
Iteration: 1626; Percent complete: 40.6%; Average loss: 3.3577
Iteration: 1627; Percent complete: 40.7%; Average loss: 3.1845
Iteration: 1628; Percent complete: 40.7%; Average loss: 3.0695
Iteration: 1629; Percent complete: 40.7%; Average loss: 3.2094
Iteration: 1630; Percent complete: 40.8%; Average loss: 3.1988
Iteration: 1631; Percent complete: 40.8%; Average loss: 3.0750
Iteration: 1632; Percent complete: 40.8%; Average loss: 3.4583
Iteration: 1633; Percent complete: 40.8%; Average loss: 3.5434
Iteration: 1634; Percent complete: 40.8%; Average loss: 3.4978
Iteration: 1635; Percent complete: 40.9%; Average loss: 3.1609
Iteration: 1636; Percent complete: 40.9%; Average loss: 3.2037
Iteration: 1637; Percent complete: 40.9%; Average loss: 3.1697
Iteration: 1638; Percent complete: 40.9%; Average loss: 3.2127
Iteration: 1639; Percent complete: 41.0%; Average loss: 3.3877
Iteration: 1640; Percent complete: 41.0%; Average loss: 2.8019
Iteration: 1641; Percent complete: 41.0%; Average loss: 3.2452
Iteration: 1642; Percent complete: 41.0%; Average loss: 3.2646
Iteration: 1643; Percent complete: 41.1%; Average loss: 3.1473
Iteration: 1644; Percent complete: 41.1%; Average loss: 3.4208
Iteration: 1645; Percent complete: 41.1%; Average loss: 3.5139
Iteration: 1646; Percent complete: 41.1%; Average loss: 3.4143
Iteration: 1647; Percent complete: 41.2%; Average loss: 3.5822
Iteration: 1648; Percent complete: 41.2%; Average loss: 3.1926
Iteration: 1649; Percent complete: 41.2%; Average loss: 3.2917
Iteration: 1650; Percent complete: 41.2%; Average loss: 3.2557
Iteration: 1651; Percent complete: 41.3%; Average loss: 3.1764
Iteration: 1652; Percent complete: 41.3%; Average loss: 3.6743
Iteration: 1653; Percent complete: 41.3%; Average loss: 3.4226
Iteration: 1654; Percent complete: 41.3%; Average loss: 3.3360
Iteration: 1655; Percent complete: 41.4%; Average loss: 2.9744
Iteration: 1656; Percent complete: 41.4%; Average loss: 3.4134
Iteration: 1657; Percent complete: 41.4%; Average loss: 3.1194
Iteration: 1658; Percent complete: 41.4%; Average loss: 3.4117
Iteration: 1659; Percent complete: 41.5%; Average loss: 3.3923
Iteration: 1660; Percent complete: 41.5%; Average loss: 3.2580
Iteration: 1661; Percent complete: 41.5%; Average loss: 3.1439
Iteration: 1662; Percent complete: 41.5%; Average loss: 3.2885
Iteration: 1663; Percent complete: 41.6%; Average loss: 3.2151
Iteration: 1664; Percent complete: 41.6%; Average loss: 3.0904
Iteration: 1665; Percent complete: 41.6%; Average loss: 3.1955
Iteration: 1666; Percent complete: 41.6%; Average loss: 3.2789
Iteration: 1667; Percent complete: 41.7%; Average loss: 3.4571
Iteration: 1668; Percent complete: 41.7%; Average loss: 3.1506
Iteration: 1669; Percent complete: 41.7%; Average loss: 3.3698
Iteration: 1670; Percent complete: 41.8%; Average loss: 3.0923
Iteration: 1671; Percent complete: 41.8%; Average loss: 3.1845
Iteration: 1672; Percent complete: 41.8%; Average loss: 3.3247
Iteration: 1673; Percent complete: 41.8%; Average loss: 3.2804
Iteration: 1674; Percent complete: 41.9%; Average loss: 3.0637
Iteration: 1675; Percent complete: 41.9%; Average loss: 3.2708
Iteration: 1676; Percent complete: 41.9%; Average loss: 3.3830
Iteration: 1677; Percent complete: 41.9%; Average loss: 3.2079
Iteration: 1678; Percent complete: 41.9%; Average loss: 3.3947
Iteration: 1679; Percent complete: 42.0%; Average loss: 3.2599
Iteration: 1680; Percent complete: 42.0%; Average loss: 3.3344
Iteration: 1681; Percent complete: 42.0%; Average loss: 3.4562
Iteration: 1682; Percent complete: 42.0%; Average loss: 3.1697
Iteration: 1683; Percent complete: 42.1%; Average loss: 3.3026
Iteration: 1684; Percent complete: 42.1%; Average loss: 3.0495
Iteration: 1685; Percent complete: 42.1%; Average loss: 3.2860
Iteration: 1686; Percent complete: 42.1%; Average loss: 3.0693
Iteration: 1687; Percent complete: 42.2%; Average loss: 3.1018
Iteration: 1688; Percent complete: 42.2%; Average loss: 3.1220
Iteration: 1689; Percent complete: 42.2%; Average loss: 3.4092
Iteration: 1690; Percent complete: 42.2%; Average loss: 3.1732
Iteration: 1691; Percent complete: 42.3%; Average loss: 3.1082
Iteration: 1692; Percent complete: 42.3%; Average loss: 3.2811
Iteration: 1693; Percent complete: 42.3%; Average loss: 3.4488
Iteration: 1694; Percent complete: 42.4%; Average loss: 3.0438
Iteration: 1695; Percent complete: 42.4%; Average loss: 3.2211
Iteration: 1696; Percent complete: 42.4%; Average loss: 3.1632
Iteration: 1697; Percent complete: 42.4%; Average loss: 3.4875
Iteration: 1698; Percent complete: 42.4%; Average loss: 3.2091
Iteration: 1699; Percent complete: 42.5%; Average loss: 3.1149
Iteration: 1700; Percent complete: 42.5%; Average loss: 3.3949
Iteration: 1701; Percent complete: 42.5%; Average loss: 3.0700
Iteration: 1702; Percent complete: 42.5%; Average loss: 3.0659
Iteration: 1703; Percent complete: 42.6%; Average loss: 3.5446
Iteration: 1704; Percent complete: 42.6%; Average loss: 3.1649
Iteration: 1705; Percent complete: 42.6%; Average loss: 3.4957
Iteration: 1706; Percent complete: 42.6%; Average loss: 3.2964
Iteration: 1707; Percent complete: 42.7%; Average loss: 3.3829
Iteration: 1708; Percent complete: 42.7%; Average loss: 3.0778
Iteration: 1709; Percent complete: 42.7%; Average loss: 3.4790
Iteration: 1710; Percent complete: 42.8%; Average loss: 3.2742
Iteration: 1711; Percent complete: 42.8%; Average loss: 3.0023
Iteration: 1712; Percent complete: 42.8%; Average loss: 3.4360
Iteration: 1713; Percent complete: 42.8%; Average loss: 3.0858
Iteration: 1714; Percent complete: 42.9%; Average loss: 3.2347
Iteration: 1715; Percent complete: 42.9%; Average loss: 3.1097
Iteration: 1716; Percent complete: 42.9%; Average loss: 2.9337
Iteration: 1717; Percent complete: 42.9%; Average loss: 3.2540
Iteration: 1718; Percent complete: 43.0%; Average loss: 3.1672
Iteration: 1719; Percent complete: 43.0%; Average loss: 3.4191
Iteration: 1720; Percent complete: 43.0%; Average loss: 3.1307
Iteration: 1721; Percent complete: 43.0%; Average loss: 3.1305
Iteration: 1722; Percent complete: 43.0%; Average loss: 2.9793
Iteration: 1723; Percent complete: 43.1%; Average loss: 2.8967
Iteration: 1724; Percent complete: 43.1%; Average loss: 3.2613
Iteration: 1725; Percent complete: 43.1%; Average loss: 2.9677
Iteration: 1726; Percent complete: 43.1%; Average loss: 3.3039
Iteration: 1727; Percent complete: 43.2%; Average loss: 3.1704
Iteration: 1728; Percent complete: 43.2%; Average loss: 3.1733
Iteration: 1729; Percent complete: 43.2%; Average loss: 3.1873
Iteration: 1730; Percent complete: 43.2%; Average loss: 3.2346
Iteration: 1731; Percent complete: 43.3%; Average loss: 3.3443
Iteration: 1732; Percent complete: 43.3%; Average loss: 3.3663
Iteration: 1733; Percent complete: 43.3%; Average loss: 3.2154
Iteration: 1734; Percent complete: 43.4%; Average loss: 3.1386
Iteration: 1735; Percent complete: 43.4%; Average loss: 3.4079
Iteration: 1736; Percent complete: 43.4%; Average loss: 3.1870
Iteration: 1737; Percent complete: 43.4%; Average loss: 3.2665
Iteration: 1738; Percent complete: 43.5%; Average loss: 3.1365
Iteration: 1739; Percent complete: 43.5%; Average loss: 3.2191
Iteration: 1740; Percent complete: 43.5%; Average loss: 3.4038
Iteration: 1741; Percent complete: 43.5%; Average loss: 3.1548
Iteration: 1742; Percent complete: 43.5%; Average loss: 3.2982
Iteration: 1743; Percent complete: 43.6%; Average loss: 3.3055
Iteration: 1744; Percent complete: 43.6%; Average loss: 3.1219
Iteration: 1745; Percent complete: 43.6%; Average loss: 3.2526
Iteration: 1746; Percent complete: 43.6%; Average loss: 3.3709
Iteration: 1747; Percent complete: 43.7%; Average loss: 3.1760
Iteration: 1748; Percent complete: 43.7%; Average loss: 3.0158
Iteration: 1749; Percent complete: 43.7%; Average loss: 2.8841
Iteration: 1750; Percent complete: 43.8%; Average loss: 3.3626
Iteration: 1751; Percent complete: 43.8%; Average loss: 3.0427
Iteration: 1752; Percent complete: 43.8%; Average loss: 3.2019
Iteration: 1753; Percent complete: 43.8%; Average loss: 3.1572
Iteration: 1754; Percent complete: 43.9%; Average loss: 3.1906
Iteration: 1755; Percent complete: 43.9%; Average loss: 3.3370
Iteration: 1756; Percent complete: 43.9%; Average loss: 3.0967
Iteration: 1757; Percent complete: 43.9%; Average loss: 3.3877
Iteration: 1758; Percent complete: 44.0%; Average loss: 3.5892
Iteration: 1759; Percent complete: 44.0%; Average loss: 3.5209
Iteration: 1760; Percent complete: 44.0%; Average loss: 3.4073
Iteration: 1761; Percent complete: 44.0%; Average loss: 3.3430
Iteration: 1762; Percent complete: 44.0%; Average loss: 3.1881
Iteration: 1763; Percent complete: 44.1%; Average loss: 2.9805
Iteration: 1764; Percent complete: 44.1%; Average loss: 3.5688
Iteration: 1765; Percent complete: 44.1%; Average loss: 3.4285
Iteration: 1766; Percent complete: 44.1%; Average loss: 3.2705
Iteration: 1767; Percent complete: 44.2%; Average loss: 3.4302
Iteration: 1768; Percent complete: 44.2%; Average loss: 3.1261
Iteration: 1769; Percent complete: 44.2%; Average loss: 3.3258
Iteration: 1770; Percent complete: 44.2%; Average loss: 3.1202
Iteration: 1771; Percent complete: 44.3%; Average loss: 3.1719
Iteration: 1772; Percent complete: 44.3%; Average loss: 3.1382
Iteration: 1773; Percent complete: 44.3%; Average loss: 3.2385
Iteration: 1774; Percent complete: 44.4%; Average loss: 3.1169
Iteration: 1775; Percent complete: 44.4%; Average loss: 3.3329
Iteration: 1776; Percent complete: 44.4%; Average loss: 3.3033
Iteration: 1777; Percent complete: 44.4%; Average loss: 3.1323
Iteration: 1778; Percent complete: 44.5%; Average loss: 2.9840
Iteration: 1779; Percent complete: 44.5%; Average loss: 2.8962
Iteration: 1780; Percent complete: 44.5%; Average loss: 3.0089
Iteration: 1781; Percent complete: 44.5%; Average loss: 3.1693
Iteration: 1782; Percent complete: 44.5%; Average loss: 3.7328
Iteration: 1783; Percent complete: 44.6%; Average loss: 3.0365
Iteration: 1784; Percent complete: 44.6%; Average loss: 3.1186
Iteration: 1785; Percent complete: 44.6%; Average loss: 3.0520
Iteration: 1786; Percent complete: 44.6%; Average loss: 3.2002
Iteration: 1787; Percent complete: 44.7%; Average loss: 3.0694
Iteration: 1788; Percent complete: 44.7%; Average loss: 3.0006
Iteration: 1789; Percent complete: 44.7%; Average loss: 3.0832
Iteration: 1790; Percent complete: 44.8%; Average loss: 3.2441
Iteration: 1791; Percent complete: 44.8%; Average loss: 3.0224
Iteration: 1792; Percent complete: 44.8%; Average loss: 3.4466
Iteration: 1793; Percent complete: 44.8%; Average loss: 3.2938
Iteration: 1794; Percent complete: 44.9%; Average loss: 3.4894
Iteration: 1795; Percent complete: 44.9%; Average loss: 3.2461
Iteration: 1796; Percent complete: 44.9%; Average loss: 3.1399
Iteration: 1797; Percent complete: 44.9%; Average loss: 3.3953
Iteration: 1798; Percent complete: 45.0%; Average loss: 3.1698
Iteration: 1799; Percent complete: 45.0%; Average loss: 3.2502
Iteration: 1800; Percent complete: 45.0%; Average loss: 3.3267
Iteration: 1801; Percent complete: 45.0%; Average loss: 2.8578
Iteration: 1802; Percent complete: 45.1%; Average loss: 3.0669
Iteration: 1803; Percent complete: 45.1%; Average loss: 3.1895
Iteration: 1804; Percent complete: 45.1%; Average loss: 3.4229
Iteration: 1805; Percent complete: 45.1%; Average loss: 3.2917
Iteration: 1806; Percent complete: 45.1%; Average loss: 3.4765
Iteration: 1807; Percent complete: 45.2%; Average loss: 3.2163
Iteration: 1808; Percent complete: 45.2%; Average loss: 3.2141
Iteration: 1809; Percent complete: 45.2%; Average loss: 3.3279
Iteration: 1810; Percent complete: 45.2%; Average loss: 3.3940
Iteration: 1811; Percent complete: 45.3%; Average loss: 3.2792
Iteration: 1812; Percent complete: 45.3%; Average loss: 3.3701
Iteration: 1813; Percent complete: 45.3%; Average loss: 2.9532
Iteration: 1814; Percent complete: 45.4%; Average loss: 3.1811
Iteration: 1815; Percent complete: 45.4%; Average loss: 3.3154
Iteration: 1816; Percent complete: 45.4%; Average loss: 2.8483
Iteration: 1817; Percent complete: 45.4%; Average loss: 3.2903
Iteration: 1818; Percent complete: 45.5%; Average loss: 3.2330
Iteration: 1819; Percent complete: 45.5%; Average loss: 3.2367
Iteration: 1820; Percent complete: 45.5%; Average loss: 3.1520
Iteration: 1821; Percent complete: 45.5%; Average loss: 3.1655
Iteration: 1822; Percent complete: 45.6%; Average loss: 3.4645
Iteration: 1823; Percent complete: 45.6%; Average loss: 3.3092
Iteration: 1824; Percent complete: 45.6%; Average loss: 3.2791
Iteration: 1825; Percent complete: 45.6%; Average loss: 3.3487
Iteration: 1826; Percent complete: 45.6%; Average loss: 3.2013
Iteration: 1827; Percent complete: 45.7%; Average loss: 3.3409
Iteration: 1828; Percent complete: 45.7%; Average loss: 3.3292
Iteration: 1829; Percent complete: 45.7%; Average loss: 2.9395
Iteration: 1830; Percent complete: 45.8%; Average loss: 2.9582
Iteration: 1831; Percent complete: 45.8%; Average loss: 3.0708
Iteration: 1832; Percent complete: 45.8%; Average loss: 3.1703
Iteration: 1833; Percent complete: 45.8%; Average loss: 3.2108
Iteration: 1834; Percent complete: 45.9%; Average loss: 3.2607
Iteration: 1835; Percent complete: 45.9%; Average loss: 3.3950
Iteration: 1836; Percent complete: 45.9%; Average loss: 3.2749
Iteration: 1837; Percent complete: 45.9%; Average loss: 3.2980
Iteration: 1838; Percent complete: 46.0%; Average loss: 3.2300
Iteration: 1839; Percent complete: 46.0%; Average loss: 3.2847
Iteration: 1840; Percent complete: 46.0%; Average loss: 3.1075
Iteration: 1841; Percent complete: 46.0%; Average loss: 3.0578
Iteration: 1842; Percent complete: 46.1%; Average loss: 3.2330
Iteration: 1843; Percent complete: 46.1%; Average loss: 2.8886
Iteration: 1844; Percent complete: 46.1%; Average loss: 3.3630
Iteration: 1845; Percent complete: 46.1%; Average loss: 3.2262
Iteration: 1846; Percent complete: 46.2%; Average loss: 3.0328
Iteration: 1847; Percent complete: 46.2%; Average loss: 3.2365
Iteration: 1848; Percent complete: 46.2%; Average loss: 3.0282
Iteration: 1849; Percent complete: 46.2%; Average loss: 3.6267
Iteration: 1850; Percent complete: 46.2%; Average loss: 3.4386
Iteration: 1851; Percent complete: 46.3%; Average loss: 3.3634
Iteration: 1852; Percent complete: 46.3%; Average loss: 3.0345
Iteration: 1853; Percent complete: 46.3%; Average loss: 2.9798
Iteration: 1854; Percent complete: 46.4%; Average loss: 3.0996
Iteration: 1855; Percent complete: 46.4%; Average loss: 3.2036
Iteration: 1856; Percent complete: 46.4%; Average loss: 3.1654
Iteration: 1857; Percent complete: 46.4%; Average loss: 3.3329
Iteration: 1858; Percent complete: 46.5%; Average loss: 3.3038
Iteration: 1859; Percent complete: 46.5%; Average loss: 3.1607
Iteration: 1860; Percent complete: 46.5%; Average loss: 3.3581
Iteration: 1861; Percent complete: 46.5%; Average loss: 3.2167
Iteration: 1862; Percent complete: 46.6%; Average loss: 3.1005
Iteration: 1863; Percent complete: 46.6%; Average loss: 3.1082
Iteration: 1864; Percent complete: 46.6%; Average loss: 3.2747
Iteration: 1865; Percent complete: 46.6%; Average loss: 3.3146
Iteration: 1866; Percent complete: 46.7%; Average loss: 3.4367
Iteration: 1867; Percent complete: 46.7%; Average loss: 3.1596
Iteration: 1868; Percent complete: 46.7%; Average loss: 3.2477
Iteration: 1869; Percent complete: 46.7%; Average loss: 3.3759
Iteration: 1870; Percent complete: 46.8%; Average loss: 3.1870
Iteration: 1871; Percent complete: 46.8%; Average loss: 3.2158
Iteration: 1872; Percent complete: 46.8%; Average loss: 3.1084
Iteration: 1873; Percent complete: 46.8%; Average loss: 3.0620
Iteration: 1874; Percent complete: 46.9%; Average loss: 3.3857
Iteration: 1875; Percent complete: 46.9%; Average loss: 3.3025
Iteration: 1876; Percent complete: 46.9%; Average loss: 3.2009
Iteration: 1877; Percent complete: 46.9%; Average loss: 3.1912
Iteration: 1878; Percent complete: 46.9%; Average loss: 3.2299
Iteration: 1879; Percent complete: 47.0%; Average loss: 2.9868
Iteration: 1880; Percent complete: 47.0%; Average loss: 3.1356
Iteration: 1881; Percent complete: 47.0%; Average loss: 3.1307
Iteration: 1882; Percent complete: 47.0%; Average loss: 3.0313
Iteration: 1883; Percent complete: 47.1%; Average loss: 3.4380
Iteration: 1884; Percent complete: 47.1%; Average loss: 2.7916
Iteration: 1885; Percent complete: 47.1%; Average loss: 3.4165
Iteration: 1886; Percent complete: 47.1%; Average loss: 3.4885
Iteration: 1887; Percent complete: 47.2%; Average loss: 3.1972
Iteration: 1888; Percent complete: 47.2%; Average loss: 3.0633
Iteration: 1889; Percent complete: 47.2%; Average loss: 3.3731
Iteration: 1890; Percent complete: 47.2%; Average loss: 3.5016
Iteration: 1891; Percent complete: 47.3%; Average loss: 3.2181
Iteration: 1892; Percent complete: 47.3%; Average loss: 3.1485
Iteration: 1893; Percent complete: 47.3%; Average loss: 3.1729
Iteration: 1894; Percent complete: 47.3%; Average loss: 3.2938
Iteration: 1895; Percent complete: 47.4%; Average loss: 3.1572
Iteration: 1896; Percent complete: 47.4%; Average loss: 3.3781
Iteration: 1897; Percent complete: 47.4%; Average loss: 3.2135
Iteration: 1898; Percent complete: 47.4%; Average loss: 3.2112
Iteration: 1899; Percent complete: 47.5%; Average loss: 3.0717
Iteration: 1900; Percent complete: 47.5%; Average loss: 2.9593
Iteration: 1901; Percent complete: 47.5%; Average loss: 3.1980
Iteration: 1902; Percent complete: 47.5%; Average loss: 3.1369
Iteration: 1903; Percent complete: 47.6%; Average loss: 3.2616
Iteration: 1904; Percent complete: 47.6%; Average loss: 3.0204
Iteration: 1905; Percent complete: 47.6%; Average loss: 3.2028
Iteration: 1906; Percent complete: 47.6%; Average loss: 3.1661
Iteration: 1907; Percent complete: 47.7%; Average loss: 3.2108
Iteration: 1908; Percent complete: 47.7%; Average loss: 3.0556
Iteration: 1909; Percent complete: 47.7%; Average loss: 3.1632
Iteration: 1910; Percent complete: 47.8%; Average loss: 3.1692
Iteration: 1911; Percent complete: 47.8%; Average loss: 3.6585
Iteration: 1912; Percent complete: 47.8%; Average loss: 3.0866
Iteration: 1913; Percent complete: 47.8%; Average loss: 3.3203
Iteration: 1914; Percent complete: 47.9%; Average loss: 3.1576
Iteration: 1915; Percent complete: 47.9%; Average loss: 3.1009
Iteration: 1916; Percent complete: 47.9%; Average loss: 3.0758
Iteration: 1917; Percent complete: 47.9%; Average loss: 3.2283
Iteration: 1918; Percent complete: 47.9%; Average loss: 3.2102
Iteration: 1919; Percent complete: 48.0%; Average loss: 3.0251
Iteration: 1920; Percent complete: 48.0%; Average loss: 3.0709
Iteration: 1921; Percent complete: 48.0%; Average loss: 3.2879
Iteration: 1922; Percent complete: 48.0%; Average loss: 3.1048
Iteration: 1923; Percent complete: 48.1%; Average loss: 3.1224
Iteration: 1924; Percent complete: 48.1%; Average loss: 3.0839
Iteration: 1925; Percent complete: 48.1%; Average loss: 3.3651
Iteration: 1926; Percent complete: 48.1%; Average loss: 3.0941
Iteration: 1927; Percent complete: 48.2%; Average loss: 2.9026
Iteration: 1928; Percent complete: 48.2%; Average loss: 3.2135
Iteration: 1929; Percent complete: 48.2%; Average loss: 3.1552
Iteration: 1930; Percent complete: 48.2%; Average loss: 3.0855
Iteration: 1931; Percent complete: 48.3%; Average loss: 3.2268
Iteration: 1932; Percent complete: 48.3%; Average loss: 2.9366
Iteration: 1933; Percent complete: 48.3%; Average loss: 3.1282
Iteration: 1934; Percent complete: 48.4%; Average loss: 3.0548
Iteration: 1935; Percent complete: 48.4%; Average loss: 3.2356
Iteration: 1936; Percent complete: 48.4%; Average loss: 3.3350
Iteration: 1937; Percent complete: 48.4%; Average loss: 2.9862
Iteration: 1938; Percent complete: 48.4%; Average loss: 2.9964
Iteration: 1939; Percent complete: 48.5%; Average loss: 3.2477
Iteration: 1940; Percent complete: 48.5%; Average loss: 3.1922
Iteration: 1941; Percent complete: 48.5%; Average loss: 3.2496
Iteration: 1942; Percent complete: 48.5%; Average loss: 3.2744
Iteration: 1943; Percent complete: 48.6%; Average loss: 3.1174
Iteration: 1944; Percent complete: 48.6%; Average loss: 3.2950
Iteration: 1945; Percent complete: 48.6%; Average loss: 3.0411
Iteration: 1946; Percent complete: 48.6%; Average loss: 3.1265
Iteration: 1947; Percent complete: 48.7%; Average loss: 3.1614
Iteration: 1948; Percent complete: 48.7%; Average loss: 2.8645
Iteration: 1949; Percent complete: 48.7%; Average loss: 3.1959
Iteration: 1950; Percent complete: 48.8%; Average loss: 3.1906
Iteration: 1951; Percent complete: 48.8%; Average loss: 3.1575
Iteration: 1952; Percent complete: 48.8%; Average loss: 3.0930
Iteration: 1953; Percent complete: 48.8%; Average loss: 3.1678
Iteration: 1954; Percent complete: 48.9%; Average loss: 2.9240
Iteration: 1955; Percent complete: 48.9%; Average loss: 3.1338
Iteration: 1956; Percent complete: 48.9%; Average loss: 3.0251
Iteration: 1957; Percent complete: 48.9%; Average loss: 3.2895
Iteration: 1958; Percent complete: 48.9%; Average loss: 3.2715
Iteration: 1959; Percent complete: 49.0%; Average loss: 3.3309
Iteration: 1960; Percent complete: 49.0%; Average loss: 3.1917
Iteration: 1961; Percent complete: 49.0%; Average loss: 3.3181
Iteration: 1962; Percent complete: 49.0%; Average loss: 3.0958
Iteration: 1963; Percent complete: 49.1%; Average loss: 3.2041
Iteration: 1964; Percent complete: 49.1%; Average loss: 2.9564
Iteration: 1965; Percent complete: 49.1%; Average loss: 3.2486
Iteration: 1966; Percent complete: 49.1%; Average loss: 3.1039
Iteration: 1967; Percent complete: 49.2%; Average loss: 3.3042
Iteration: 1968; Percent complete: 49.2%; Average loss: 3.3871
Iteration: 1969; Percent complete: 49.2%; Average loss: 3.1386
Iteration: 1970; Percent complete: 49.2%; Average loss: 3.1573
Iteration: 1971; Percent complete: 49.3%; Average loss: 3.1636
Iteration: 1972; Percent complete: 49.3%; Average loss: 3.2130
Iteration: 1973; Percent complete: 49.3%; Average loss: 3.1707
Iteration: 1974; Percent complete: 49.4%; Average loss: 3.2108
Iteration: 1975; Percent complete: 49.4%; Average loss: 3.0280
Iteration: 1976; Percent complete: 49.4%; Average loss: 3.0961
Iteration: 1977; Percent complete: 49.4%; Average loss: 3.2261
Iteration: 1978; Percent complete: 49.5%; Average loss: 3.5336
Iteration: 1979; Percent complete: 49.5%; Average loss: 3.0474
Iteration: 1980; Percent complete: 49.5%; Average loss: 3.0440
Iteration: 1981; Percent complete: 49.5%; Average loss: 3.0692
Iteration: 1982; Percent complete: 49.5%; Average loss: 2.9696
Iteration: 1983; Percent complete: 49.6%; Average loss: 3.2897
Iteration: 1984; Percent complete: 49.6%; Average loss: 3.1695
Iteration: 1985; Percent complete: 49.6%; Average loss: 2.9875
Iteration: 1986; Percent complete: 49.6%; Average loss: 3.1519
Iteration: 1987; Percent complete: 49.7%; Average loss: 3.0502
Iteration: 1988; Percent complete: 49.7%; Average loss: 2.9199
Iteration: 1989; Percent complete: 49.7%; Average loss: 2.9096
Iteration: 1990; Percent complete: 49.8%; Average loss: 2.8041
Iteration: 1991; Percent complete: 49.8%; Average loss: 2.9460
Iteration: 1992; Percent complete: 49.8%; Average loss: 3.1810
Iteration: 1993; Percent complete: 49.8%; Average loss: 3.0075
Iteration: 1994; Percent complete: 49.9%; Average loss: 2.8245
Iteration: 1995; Percent complete: 49.9%; Average loss: 3.0909
Iteration: 1996; Percent complete: 49.9%; Average loss: 2.8000
Iteration: 1997; Percent complete: 49.9%; Average loss: 3.2303
Iteration: 1998; Percent complete: 50.0%; Average loss: 3.2561
Iteration: 1999; Percent complete: 50.0%; Average loss: 3.1260
Iteration: 2000; Percent complete: 50.0%; Average loss: 3.0753
Iteration: 2001; Percent complete: 50.0%; Average loss: 2.9826
Iteration: 2002; Percent complete: 50.0%; Average loss: 3.3101
Iteration: 2003; Percent complete: 50.1%; Average loss: 3.2453
Iteration: 2004; Percent complete: 50.1%; Average loss: 3.2032
Iteration: 2005; Percent complete: 50.1%; Average loss: 3.3290
Iteration: 2006; Percent complete: 50.1%; Average loss: 2.9706
Iteration: 2007; Percent complete: 50.2%; Average loss: 3.2893
Iteration: 2008; Percent complete: 50.2%; Average loss: 3.1209
Iteration: 2009; Percent complete: 50.2%; Average loss: 3.2444
Iteration: 2010; Percent complete: 50.2%; Average loss: 3.1810
Iteration: 2011; Percent complete: 50.3%; Average loss: 2.9522
Iteration: 2012; Percent complete: 50.3%; Average loss: 3.1798
Iteration: 2013; Percent complete: 50.3%; Average loss: 3.0576
Iteration: 2014; Percent complete: 50.3%; Average loss: 3.4078
Iteration: 2015; Percent complete: 50.4%; Average loss: 2.8849
Iteration: 2016; Percent complete: 50.4%; Average loss: 3.2559
Iteration: 2017; Percent complete: 50.4%; Average loss: 2.8208
Iteration: 2018; Percent complete: 50.4%; Average loss: 3.2541
Iteration: 2019; Percent complete: 50.5%; Average loss: 3.1983
Iteration: 2020; Percent complete: 50.5%; Average loss: 3.1429
Iteration: 2021; Percent complete: 50.5%; Average loss: 3.2963
Iteration: 2022; Percent complete: 50.5%; Average loss: 3.0957
Iteration: 2023; Percent complete: 50.6%; Average loss: 3.1778
Iteration: 2024; Percent complete: 50.6%; Average loss: 2.9783
Iteration: 2025; Percent complete: 50.6%; Average loss: 3.1034
Iteration: 2026; Percent complete: 50.6%; Average loss: 3.2374
Iteration: 2027; Percent complete: 50.7%; Average loss: 3.2381
Iteration: 2028; Percent complete: 50.7%; Average loss: 3.2036
Iteration: 2029; Percent complete: 50.7%; Average loss: 3.2510
Iteration: 2030; Percent complete: 50.7%; Average loss: 3.1364
Iteration: 2031; Percent complete: 50.8%; Average loss: 3.3281
Iteration: 2032; Percent complete: 50.8%; Average loss: 3.1086
Iteration: 2033; Percent complete: 50.8%; Average loss: 3.2584
Iteration: 2034; Percent complete: 50.8%; Average loss: 3.2639
Iteration: 2035; Percent complete: 50.9%; Average loss: 3.0564
Iteration: 2036; Percent complete: 50.9%; Average loss: 3.1989
Iteration: 2037; Percent complete: 50.9%; Average loss: 3.0333
Iteration: 2038; Percent complete: 50.9%; Average loss: 3.1995
Iteration: 2039; Percent complete: 51.0%; Average loss: 3.3693
Iteration: 2040; Percent complete: 51.0%; Average loss: 3.0107
Iteration: 2041; Percent complete: 51.0%; Average loss: 3.1871
Iteration: 2042; Percent complete: 51.0%; Average loss: 3.2352
Iteration: 2043; Percent complete: 51.1%; Average loss: 3.3647
Iteration: 2044; Percent complete: 51.1%; Average loss: 3.2512
Iteration: 2045; Percent complete: 51.1%; Average loss: 3.3678
Iteration: 2046; Percent complete: 51.1%; Average loss: 3.2580
Iteration: 2047; Percent complete: 51.2%; Average loss: 3.1695
Iteration: 2048; Percent complete: 51.2%; Average loss: 3.4137
Iteration: 2049; Percent complete: 51.2%; Average loss: 3.1824
Iteration: 2050; Percent complete: 51.2%; Average loss: 3.0975
Iteration: 2051; Percent complete: 51.3%; Average loss: 3.0288
Iteration: 2052; Percent complete: 51.3%; Average loss: 3.0049
Iteration: 2053; Percent complete: 51.3%; Average loss: 3.2460
Iteration: 2054; Percent complete: 51.3%; Average loss: 3.1307
Iteration: 2055; Percent complete: 51.4%; Average loss: 3.0381
Iteration: 2056; Percent complete: 51.4%; Average loss: 3.0917
Iteration: 2057; Percent complete: 51.4%; Average loss: 3.2493
Iteration: 2058; Percent complete: 51.4%; Average loss: 3.3373
Iteration: 2059; Percent complete: 51.5%; Average loss: 3.2329
Iteration: 2060; Percent complete: 51.5%; Average loss: 3.0089
Iteration: 2061; Percent complete: 51.5%; Average loss: 3.0280
Iteration: 2062; Percent complete: 51.5%; Average loss: 3.0851
Iteration: 2063; Percent complete: 51.6%; Average loss: 3.1684
Iteration: 2064; Percent complete: 51.6%; Average loss: 3.0780
Iteration: 2065; Percent complete: 51.6%; Average loss: 2.8850
Iteration: 2066; Percent complete: 51.6%; Average loss: 3.0750
Iteration: 2067; Percent complete: 51.7%; Average loss: 3.1129
Iteration: 2068; Percent complete: 51.7%; Average loss: 3.3670
Iteration: 2069; Percent complete: 51.7%; Average loss: 3.1074
Iteration: 2070; Percent complete: 51.7%; Average loss: 3.1645
Iteration: 2071; Percent complete: 51.8%; Average loss: 3.1215
Iteration: 2072; Percent complete: 51.8%; Average loss: 3.0364
Iteration: 2073; Percent complete: 51.8%; Average loss: 2.9970
Iteration: 2074; Percent complete: 51.8%; Average loss: 3.0477
Iteration: 2075; Percent complete: 51.9%; Average loss: 3.0278
Iteration: 2076; Percent complete: 51.9%; Average loss: 3.2413
Iteration: 2077; Percent complete: 51.9%; Average loss: 3.1168
Iteration: 2078; Percent complete: 51.9%; Average loss: 3.1762
Iteration: 2079; Percent complete: 52.0%; Average loss: 3.0646
Iteration: 2080; Percent complete: 52.0%; Average loss: 3.2369
Iteration: 2081; Percent complete: 52.0%; Average loss: 2.9949
Iteration: 2082; Percent complete: 52.0%; Average loss: 3.2505
Iteration: 2083; Percent complete: 52.1%; Average loss: 3.2619
Iteration: 2084; Percent complete: 52.1%; Average loss: 3.0418
Iteration: 2085; Percent complete: 52.1%; Average loss: 3.1803
Iteration: 2086; Percent complete: 52.1%; Average loss: 3.2060
Iteration: 2087; Percent complete: 52.2%; Average loss: 2.9044
Iteration: 2088; Percent complete: 52.2%; Average loss: 3.3093
Iteration: 2089; Percent complete: 52.2%; Average loss: 3.2404
Iteration: 2090; Percent complete: 52.2%; Average loss: 3.0789
Iteration: 2091; Percent complete: 52.3%; Average loss: 3.4120
Iteration: 2092; Percent complete: 52.3%; Average loss: 2.9743
Iteration: 2093; Percent complete: 52.3%; Average loss: 3.0818
Iteration: 2094; Percent complete: 52.3%; Average loss: 3.1822
Iteration: 2095; Percent complete: 52.4%; Average loss: 3.1572
Iteration: 2096; Percent complete: 52.4%; Average loss: 3.2989
Iteration: 2097; Percent complete: 52.4%; Average loss: 2.9970
Iteration: 2098; Percent complete: 52.4%; Average loss: 3.1277
Iteration: 2099; Percent complete: 52.5%; Average loss: 3.1038
Iteration: 2100; Percent complete: 52.5%; Average loss: 2.9343
Iteration: 2101; Percent complete: 52.5%; Average loss: 3.1599
Iteration: 2102; Percent complete: 52.5%; Average loss: 3.1459
Iteration: 2103; Percent complete: 52.6%; Average loss: 3.0161
Iteration: 2104; Percent complete: 52.6%; Average loss: 3.3051
Iteration: 2105; Percent complete: 52.6%; Average loss: 3.1562
Iteration: 2106; Percent complete: 52.6%; Average loss: 3.1636
Iteration: 2107; Percent complete: 52.7%; Average loss: 3.1441
Iteration: 2108; Percent complete: 52.7%; Average loss: 3.2261
Iteration: 2109; Percent complete: 52.7%; Average loss: 3.1090
Iteration: 2110; Percent complete: 52.8%; Average loss: 2.9255
Iteration: 2111; Percent complete: 52.8%; Average loss: 2.8333
Iteration: 2112; Percent complete: 52.8%; Average loss: 3.3860
Iteration: 2113; Percent complete: 52.8%; Average loss: 3.0791
Iteration: 2114; Percent complete: 52.8%; Average loss: 3.0676
Iteration: 2115; Percent complete: 52.9%; Average loss: 3.2693
Iteration: 2116; Percent complete: 52.9%; Average loss: 3.3779
Iteration: 2117; Percent complete: 52.9%; Average loss: 3.0320
Iteration: 2118; Percent complete: 52.9%; Average loss: 3.2922
Iteration: 2119; Percent complete: 53.0%; Average loss: 2.9883
Iteration: 2120; Percent complete: 53.0%; Average loss: 3.0914
Iteration: 2121; Percent complete: 53.0%; Average loss: 3.2872
Iteration: 2122; Percent complete: 53.0%; Average loss: 2.8847
Iteration: 2123; Percent complete: 53.1%; Average loss: 3.0453
Iteration: 2124; Percent complete: 53.1%; Average loss: 3.0850
Iteration: 2125; Percent complete: 53.1%; Average loss: 3.2234
Iteration: 2126; Percent complete: 53.1%; Average loss: 2.9332
Iteration: 2127; Percent complete: 53.2%; Average loss: 3.2146
Iteration: 2128; Percent complete: 53.2%; Average loss: 3.1367
Iteration: 2129; Percent complete: 53.2%; Average loss: 3.1905
Iteration: 2130; Percent complete: 53.2%; Average loss: 3.2241
Iteration: 2131; Percent complete: 53.3%; Average loss: 3.2361
Iteration: 2132; Percent complete: 53.3%; Average loss: 3.2721
Iteration: 2133; Percent complete: 53.3%; Average loss: 3.2142
Iteration: 2134; Percent complete: 53.3%; Average loss: 3.1908
Iteration: 2135; Percent complete: 53.4%; Average loss: 3.3025
Iteration: 2136; Percent complete: 53.4%; Average loss: 3.1388
Iteration: 2137; Percent complete: 53.4%; Average loss: 2.8392
Iteration: 2138; Percent complete: 53.4%; Average loss: 3.2234
Iteration: 2139; Percent complete: 53.5%; Average loss: 2.9826
Iteration: 2140; Percent complete: 53.5%; Average loss: 3.1818
Iteration: 2141; Percent complete: 53.5%; Average loss: 3.1086
Iteration: 2142; Percent complete: 53.5%; Average loss: 3.1645
Iteration: 2143; Percent complete: 53.6%; Average loss: 3.1557
Iteration: 2144; Percent complete: 53.6%; Average loss: 3.2386
Iteration: 2145; Percent complete: 53.6%; Average loss: 3.2112
Iteration: 2146; Percent complete: 53.6%; Average loss: 3.1104
Iteration: 2147; Percent complete: 53.7%; Average loss: 2.9972
Iteration: 2148; Percent complete: 53.7%; Average loss: 3.0829
Iteration: 2149; Percent complete: 53.7%; Average loss: 3.1121
Iteration: 2150; Percent complete: 53.8%; Average loss: 3.1750
Iteration: 2151; Percent complete: 53.8%; Average loss: 3.1896
Iteration: 2152; Percent complete: 53.8%; Average loss: 3.0521
Iteration: 2153; Percent complete: 53.8%; Average loss: 2.9863
Iteration: 2154; Percent complete: 53.8%; Average loss: 3.1756
Iteration: 2155; Percent complete: 53.9%; Average loss: 3.0921
Iteration: 2156; Percent complete: 53.9%; Average loss: 3.0474
Iteration: 2157; Percent complete: 53.9%; Average loss: 3.1833
Iteration: 2158; Percent complete: 53.9%; Average loss: 3.0158
Iteration: 2159; Percent complete: 54.0%; Average loss: 3.2623
Iteration: 2160; Percent complete: 54.0%; Average loss: 3.2068
Iteration: 2161; Percent complete: 54.0%; Average loss: 3.0909
Iteration: 2162; Percent complete: 54.0%; Average loss: 3.2259
Iteration: 2163; Percent complete: 54.1%; Average loss: 2.7856
Iteration: 2164; Percent complete: 54.1%; Average loss: 3.1105
Iteration: 2165; Percent complete: 54.1%; Average loss: 3.0539
Iteration: 2166; Percent complete: 54.1%; Average loss: 3.3316
Iteration: 2167; Percent complete: 54.2%; Average loss: 3.2178
Iteration: 2168; Percent complete: 54.2%; Average loss: 3.0915
Iteration: 2169; Percent complete: 54.2%; Average loss: 3.0287
Iteration: 2170; Percent complete: 54.2%; Average loss: 3.1480
Iteration: 2171; Percent complete: 54.3%; Average loss: 3.4808
Iteration: 2172; Percent complete: 54.3%; Average loss: 3.1200
Iteration: 2173; Percent complete: 54.3%; Average loss: 3.0442
Iteration: 2174; Percent complete: 54.4%; Average loss: 2.8464
Iteration: 2175; Percent complete: 54.4%; Average loss: 2.9868
Iteration: 2176; Percent complete: 54.4%; Average loss: 3.1926
Iteration: 2177; Percent complete: 54.4%; Average loss: 3.1844
Iteration: 2178; Percent complete: 54.4%; Average loss: 3.1924
Iteration: 2179; Percent complete: 54.5%; Average loss: 3.3563
Iteration: 2180; Percent complete: 54.5%; Average loss: 3.1778
Iteration: 2181; Percent complete: 54.5%; Average loss: 2.9863
Iteration: 2182; Percent complete: 54.5%; Average loss: 3.0928
Iteration: 2183; Percent complete: 54.6%; Average loss: 3.0813
Iteration: 2184; Percent complete: 54.6%; Average loss: 3.3560
Iteration: 2185; Percent complete: 54.6%; Average loss: 3.2420
Iteration: 2186; Percent complete: 54.6%; Average loss: 3.1521
Iteration: 2187; Percent complete: 54.7%; Average loss: 3.0901
Iteration: 2188; Percent complete: 54.7%; Average loss: 3.1274
Iteration: 2189; Percent complete: 54.7%; Average loss: 2.9603
Iteration: 2190; Percent complete: 54.8%; Average loss: 2.9538
Iteration: 2191; Percent complete: 54.8%; Average loss: 3.0783
Iteration: 2192; Percent complete: 54.8%; Average loss: 2.8482
Iteration: 2193; Percent complete: 54.8%; Average loss: 3.2197
Iteration: 2194; Percent complete: 54.9%; Average loss: 3.2698
Iteration: 2195; Percent complete: 54.9%; Average loss: 3.0194
Iteration: 2196; Percent complete: 54.9%; Average loss: 3.3105
Iteration: 2197; Percent complete: 54.9%; Average loss: 3.0747
Iteration: 2198; Percent complete: 54.9%; Average loss: 3.2370
Iteration: 2199; Percent complete: 55.0%; Average loss: 3.0488
Iteration: 2200; Percent complete: 55.0%; Average loss: 3.1231
Iteration: 2201; Percent complete: 55.0%; Average loss: 3.0505
Iteration: 2202; Percent complete: 55.0%; Average loss: 3.2257
Iteration: 2203; Percent complete: 55.1%; Average loss: 2.8299
Iteration: 2204; Percent complete: 55.1%; Average loss: 3.2059
Iteration: 2205; Percent complete: 55.1%; Average loss: 2.8618
Iteration: 2206; Percent complete: 55.1%; Average loss: 2.9096
Iteration: 2207; Percent complete: 55.2%; Average loss: 3.0730
Iteration: 2208; Percent complete: 55.2%; Average loss: 3.2029
Iteration: 2209; Percent complete: 55.2%; Average loss: 3.3394
Iteration: 2210; Percent complete: 55.2%; Average loss: 3.2630
Iteration: 2211; Percent complete: 55.3%; Average loss: 3.3103
Iteration: 2212; Percent complete: 55.3%; Average loss: 2.9919
Iteration: 2213; Percent complete: 55.3%; Average loss: 3.0287
Iteration: 2214; Percent complete: 55.4%; Average loss: 3.2720
Iteration: 2215; Percent complete: 55.4%; Average loss: 3.1706
Iteration: 2216; Percent complete: 55.4%; Average loss: 3.2859
Iteration: 2217; Percent complete: 55.4%; Average loss: 2.9741
Iteration: 2218; Percent complete: 55.5%; Average loss: 3.0053
Iteration: 2219; Percent complete: 55.5%; Average loss: 3.1007
Iteration: 2220; Percent complete: 55.5%; Average loss: 3.3030
Iteration: 2221; Percent complete: 55.5%; Average loss: 2.9621
Iteration: 2222; Percent complete: 55.5%; Average loss: 2.9786
Iteration: 2223; Percent complete: 55.6%; Average loss: 3.0168
Iteration: 2224; Percent complete: 55.6%; Average loss: 3.1138
Iteration: 2225; Percent complete: 55.6%; Average loss: 2.9788
Iteration: 2226; Percent complete: 55.6%; Average loss: 3.0578
Iteration: 2227; Percent complete: 55.7%; Average loss: 3.2477
Iteration: 2228; Percent complete: 55.7%; Average loss: 3.0655
Iteration: 2229; Percent complete: 55.7%; Average loss: 2.9583
Iteration: 2230; Percent complete: 55.8%; Average loss: 3.4396
Iteration: 2231; Percent complete: 55.8%; Average loss: 3.2418
Iteration: 2232; Percent complete: 55.8%; Average loss: 3.1236
Iteration: 2233; Percent complete: 55.8%; Average loss: 2.6807
Iteration: 2234; Percent complete: 55.9%; Average loss: 3.0042
Iteration: 2235; Percent complete: 55.9%; Average loss: 3.1489
Iteration: 2236; Percent complete: 55.9%; Average loss: 3.2439
Iteration: 2237; Percent complete: 55.9%; Average loss: 3.0651
Iteration: 2238; Percent complete: 56.0%; Average loss: 3.1998
Iteration: 2239; Percent complete: 56.0%; Average loss: 2.9859
Iteration: 2240; Percent complete: 56.0%; Average loss: 3.0832
Iteration: 2241; Percent complete: 56.0%; Average loss: 3.1638
Iteration: 2242; Percent complete: 56.0%; Average loss: 3.3065
Iteration: 2243; Percent complete: 56.1%; Average loss: 3.1226
Iteration: 2244; Percent complete: 56.1%; Average loss: 3.0984
Iteration: 2245; Percent complete: 56.1%; Average loss: 3.1661
Iteration: 2246; Percent complete: 56.1%; Average loss: 3.2391
Iteration: 2247; Percent complete: 56.2%; Average loss: 3.0148
Iteration: 2248; Percent complete: 56.2%; Average loss: 3.0975
Iteration: 2249; Percent complete: 56.2%; Average loss: 3.3278
Iteration: 2250; Percent complete: 56.2%; Average loss: 3.0485
Iteration: 2251; Percent complete: 56.3%; Average loss: 2.9501
Iteration: 2252; Percent complete: 56.3%; Average loss: 3.2133
Iteration: 2253; Percent complete: 56.3%; Average loss: 3.2273
Iteration: 2254; Percent complete: 56.4%; Average loss: 3.1881
Iteration: 2255; Percent complete: 56.4%; Average loss: 3.1644
Iteration: 2256; Percent complete: 56.4%; Average loss: 3.2065
Iteration: 2257; Percent complete: 56.4%; Average loss: 2.7638
Iteration: 2258; Percent complete: 56.5%; Average loss: 2.9163
Iteration: 2259; Percent complete: 56.5%; Average loss: 3.1675
Iteration: 2260; Percent complete: 56.5%; Average loss: 3.0662
Iteration: 2261; Percent complete: 56.5%; Average loss: 2.9228
Iteration: 2262; Percent complete: 56.5%; Average loss: 2.9248
Iteration: 2263; Percent complete: 56.6%; Average loss: 3.1133
Iteration: 2264; Percent complete: 56.6%; Average loss: 2.9204
Iteration: 2265; Percent complete: 56.6%; Average loss: 3.2658
Iteration: 2266; Percent complete: 56.6%; Average loss: 3.1339
Iteration: 2267; Percent complete: 56.7%; Average loss: 3.2279
Iteration: 2268; Percent complete: 56.7%; Average loss: 2.7296
Iteration: 2269; Percent complete: 56.7%; Average loss: 2.9177
Iteration: 2270; Percent complete: 56.8%; Average loss: 3.1928
Iteration: 2271; Percent complete: 56.8%; Average loss: 2.9310
Iteration: 2272; Percent complete: 56.8%; Average loss: 3.1057
Iteration: 2273; Percent complete: 56.8%; Average loss: 2.9879
Iteration: 2274; Percent complete: 56.9%; Average loss: 3.2481
Iteration: 2275; Percent complete: 56.9%; Average loss: 3.0523
Iteration: 2276; Percent complete: 56.9%; Average loss: 3.3918
Iteration: 2277; Percent complete: 56.9%; Average loss: 2.9579
Iteration: 2278; Percent complete: 57.0%; Average loss: 3.2189
Iteration: 2279; Percent complete: 57.0%; Average loss: 3.0758
Iteration: 2280; Percent complete: 57.0%; Average loss: 3.1428
Iteration: 2281; Percent complete: 57.0%; Average loss: 3.0158
Iteration: 2282; Percent complete: 57.0%; Average loss: 2.8672
Iteration: 2283; Percent complete: 57.1%; Average loss: 3.0428
Iteration: 2284; Percent complete: 57.1%; Average loss: 3.1566
Iteration: 2285; Percent complete: 57.1%; Average loss: 3.0334
Iteration: 2286; Percent complete: 57.1%; Average loss: 3.0447
Iteration: 2287; Percent complete: 57.2%; Average loss: 3.1513
Iteration: 2288; Percent complete: 57.2%; Average loss: 2.8910
Iteration: 2289; Percent complete: 57.2%; Average loss: 2.7464
Iteration: 2290; Percent complete: 57.2%; Average loss: 2.7983
Iteration: 2291; Percent complete: 57.3%; Average loss: 2.9267
Iteration: 2292; Percent complete: 57.3%; Average loss: 2.9716
Iteration: 2293; Percent complete: 57.3%; Average loss: 3.0318
Iteration: 2294; Percent complete: 57.4%; Average loss: 3.0002
Iteration: 2295; Percent complete: 57.4%; Average loss: 2.9196
Iteration: 2296; Percent complete: 57.4%; Average loss: 2.9746
Iteration: 2297; Percent complete: 57.4%; Average loss: 2.9197
Iteration: 2298; Percent complete: 57.5%; Average loss: 2.9157
Iteration: 2299; Percent complete: 57.5%; Average loss: 3.1165
Iteration: 2300; Percent complete: 57.5%; Average loss: 2.9812
Iteration: 2301; Percent complete: 57.5%; Average loss: 3.1715
Iteration: 2302; Percent complete: 57.6%; Average loss: 3.2487
Iteration: 2303; Percent complete: 57.6%; Average loss: 3.1243
Iteration: 2304; Percent complete: 57.6%; Average loss: 3.4569
Iteration: 2305; Percent complete: 57.6%; Average loss: 3.1228
Iteration: 2306; Percent complete: 57.6%; Average loss: 2.8564
Iteration: 2307; Percent complete: 57.7%; Average loss: 3.0309
Iteration: 2308; Percent complete: 57.7%; Average loss: 3.2079
Iteration: 2309; Percent complete: 57.7%; Average loss: 3.2042
Iteration: 2310; Percent complete: 57.8%; Average loss: 3.0031
Iteration: 2311; Percent complete: 57.8%; Average loss: 3.2199
Iteration: 2312; Percent complete: 57.8%; Average loss: 2.8610
Iteration: 2313; Percent complete: 57.8%; Average loss: 2.9920
Iteration: 2314; Percent complete: 57.9%; Average loss: 3.0161
Iteration: 2315; Percent complete: 57.9%; Average loss: 3.0431
Iteration: 2316; Percent complete: 57.9%; Average loss: 3.1741
Iteration: 2317; Percent complete: 57.9%; Average loss: 3.0592
Iteration: 2318; Percent complete: 58.0%; Average loss: 2.8462
Iteration: 2319; Percent complete: 58.0%; Average loss: 2.9762
Iteration: 2320; Percent complete: 58.0%; Average loss: 3.0967
Iteration: 2321; Percent complete: 58.0%; Average loss: 2.7448
Iteration: 2322; Percent complete: 58.1%; Average loss: 2.8410
Iteration: 2323; Percent complete: 58.1%; Average loss: 3.1431
Iteration: 2324; Percent complete: 58.1%; Average loss: 2.7998
Iteration: 2325; Percent complete: 58.1%; Average loss: 2.9250
Iteration: 2326; Percent complete: 58.1%; Average loss: 2.9286
Iteration: 2327; Percent complete: 58.2%; Average loss: 3.1496
Iteration: 2328; Percent complete: 58.2%; Average loss: 3.1513
Iteration: 2329; Percent complete: 58.2%; Average loss: 2.8130
Iteration: 2330; Percent complete: 58.2%; Average loss: 3.0630
Iteration: 2331; Percent complete: 58.3%; Average loss: 2.9140
Iteration: 2332; Percent complete: 58.3%; Average loss: 3.0392
Iteration: 2333; Percent complete: 58.3%; Average loss: 3.2950
Iteration: 2334; Percent complete: 58.4%; Average loss: 2.9779
Iteration: 2335; Percent complete: 58.4%; Average loss: 3.0412
Iteration: 2336; Percent complete: 58.4%; Average loss: 2.8906
Iteration: 2337; Percent complete: 58.4%; Average loss: 3.1028
Iteration: 2338; Percent complete: 58.5%; Average loss: 2.9757
Iteration: 2339; Percent complete: 58.5%; Average loss: 2.9162
Iteration: 2340; Percent complete: 58.5%; Average loss: 3.1587
Iteration: 2341; Percent complete: 58.5%; Average loss: 2.8970
Iteration: 2342; Percent complete: 58.6%; Average loss: 3.1487
Iteration: 2343; Percent complete: 58.6%; Average loss: 3.1504
Iteration: 2344; Percent complete: 58.6%; Average loss: 2.9992
Iteration: 2345; Percent complete: 58.6%; Average loss: 2.9479
Iteration: 2346; Percent complete: 58.7%; Average loss: 3.1695
Iteration: 2347; Percent complete: 58.7%; Average loss: 3.0145
Iteration: 2348; Percent complete: 58.7%; Average loss: 3.1151
Iteration: 2349; Percent complete: 58.7%; Average loss: 3.0206
Iteration: 2350; Percent complete: 58.8%; Average loss: 3.2651
Iteration: 2351; Percent complete: 58.8%; Average loss: 3.0460
Iteration: 2352; Percent complete: 58.8%; Average loss: 3.4052
Iteration: 2353; Percent complete: 58.8%; Average loss: 2.9835
Iteration: 2354; Percent complete: 58.9%; Average loss: 3.0277
Iteration: 2355; Percent complete: 58.9%; Average loss: 3.1289
Iteration: 2356; Percent complete: 58.9%; Average loss: 3.1370
Iteration: 2357; Percent complete: 58.9%; Average loss: 2.9932
Iteration: 2358; Percent complete: 59.0%; Average loss: 3.1582
Iteration: 2359; Percent complete: 59.0%; Average loss: 3.0172
Iteration: 2360; Percent complete: 59.0%; Average loss: 3.0839
Iteration: 2361; Percent complete: 59.0%; Average loss: 3.1213
Iteration: 2362; Percent complete: 59.1%; Average loss: 2.9984
Iteration: 2363; Percent complete: 59.1%; Average loss: 3.2241
Iteration: 2364; Percent complete: 59.1%; Average loss: 3.2124
Iteration: 2365; Percent complete: 59.1%; Average loss: 2.9807
Iteration: 2366; Percent complete: 59.2%; Average loss: 3.0751
Iteration: 2367; Percent complete: 59.2%; Average loss: 3.0526
Iteration: 2368; Percent complete: 59.2%; Average loss: 3.1717
Iteration: 2369; Percent complete: 59.2%; Average loss: 2.8977
Iteration: 2370; Percent complete: 59.2%; Average loss: 3.1760
Iteration: 2371; Percent complete: 59.3%; Average loss: 3.1045
Iteration: 2372; Percent complete: 59.3%; Average loss: 3.1193
Iteration: 2373; Percent complete: 59.3%; Average loss: 3.1218
Iteration: 2374; Percent complete: 59.4%; Average loss: 2.8393
Iteration: 2375; Percent complete: 59.4%; Average loss: 3.1723
Iteration: 2376; Percent complete: 59.4%; Average loss: 3.1783
Iteration: 2377; Percent complete: 59.4%; Average loss: 3.0857
Iteration: 2378; Percent complete: 59.5%; Average loss: 2.8801
Iteration: 2379; Percent complete: 59.5%; Average loss: 2.9213
Iteration: 2380; Percent complete: 59.5%; Average loss: 3.0821
Iteration: 2381; Percent complete: 59.5%; Average loss: 2.8580
Iteration: 2382; Percent complete: 59.6%; Average loss: 2.9438
Iteration: 2383; Percent complete: 59.6%; Average loss: 3.1223
Iteration: 2384; Percent complete: 59.6%; Average loss: 3.2895
Iteration: 2385; Percent complete: 59.6%; Average loss: 2.8803
Iteration: 2386; Percent complete: 59.7%; Average loss: 2.9845
Iteration: 2387; Percent complete: 59.7%; Average loss: 3.1931
Iteration: 2388; Percent complete: 59.7%; Average loss: 3.3353
Iteration: 2389; Percent complete: 59.7%; Average loss: 3.0654
Iteration: 2390; Percent complete: 59.8%; Average loss: 2.9505
Iteration: 2391; Percent complete: 59.8%; Average loss: 3.2205
Iteration: 2392; Percent complete: 59.8%; Average loss: 2.9006
Iteration: 2393; Percent complete: 59.8%; Average loss: 2.9996
Iteration: 2394; Percent complete: 59.9%; Average loss: 3.1644
Iteration: 2395; Percent complete: 59.9%; Average loss: 2.9035
Iteration: 2396; Percent complete: 59.9%; Average loss: 3.0843
Iteration: 2397; Percent complete: 59.9%; Average loss: 2.9191
Iteration: 2398; Percent complete: 60.0%; Average loss: 2.9765
Iteration: 2399; Percent complete: 60.0%; Average loss: 2.9268
Iteration: 2400; Percent complete: 60.0%; Average loss: 2.9732
Iteration: 2401; Percent complete: 60.0%; Average loss: 3.2247
Iteration: 2402; Percent complete: 60.1%; Average loss: 3.1392
Iteration: 2403; Percent complete: 60.1%; Average loss: 3.3645
Iteration: 2404; Percent complete: 60.1%; Average loss: 3.1642
Iteration: 2405; Percent complete: 60.1%; Average loss: 2.9731
Iteration: 2406; Percent complete: 60.2%; Average loss: 3.0518
Iteration: 2407; Percent complete: 60.2%; Average loss: 2.6977
Iteration: 2408; Percent complete: 60.2%; Average loss: 3.0120
Iteration: 2409; Percent complete: 60.2%; Average loss: 3.3835
Iteration: 2410; Percent complete: 60.2%; Average loss: 3.0959
Iteration: 2411; Percent complete: 60.3%; Average loss: 3.0034
Iteration: 2412; Percent complete: 60.3%; Average loss: 2.9105
Iteration: 2413; Percent complete: 60.3%; Average loss: 3.0349
Iteration: 2414; Percent complete: 60.4%; Average loss: 3.1348
Iteration: 2415; Percent complete: 60.4%; Average loss: 2.8816
Iteration: 2416; Percent complete: 60.4%; Average loss: 2.9565
Iteration: 2417; Percent complete: 60.4%; Average loss: 3.0528
Iteration: 2418; Percent complete: 60.5%; Average loss: 2.9998
Iteration: 2419; Percent complete: 60.5%; Average loss: 3.2099
Iteration: 2420; Percent complete: 60.5%; Average loss: 2.8816
Iteration: 2421; Percent complete: 60.5%; Average loss: 2.9204
Iteration: 2422; Percent complete: 60.6%; Average loss: 3.0352
Iteration: 2423; Percent complete: 60.6%; Average loss: 2.9626
Iteration: 2424; Percent complete: 60.6%; Average loss: 3.0117
Iteration: 2425; Percent complete: 60.6%; Average loss: 3.0908
Iteration: 2426; Percent complete: 60.7%; Average loss: 3.1747
Iteration: 2427; Percent complete: 60.7%; Average loss: 2.9736
Iteration: 2428; Percent complete: 60.7%; Average loss: 2.8416
Iteration: 2429; Percent complete: 60.7%; Average loss: 3.1694
Iteration: 2430; Percent complete: 60.8%; Average loss: 3.0886
Iteration: 2431; Percent complete: 60.8%; Average loss: 2.9765
Iteration: 2432; Percent complete: 60.8%; Average loss: 2.9080
Iteration: 2433; Percent complete: 60.8%; Average loss: 3.0060
Iteration: 2434; Percent complete: 60.9%; Average loss: 3.1530
Iteration: 2435; Percent complete: 60.9%; Average loss: 3.2079
Iteration: 2436; Percent complete: 60.9%; Average loss: 3.0090
Iteration: 2437; Percent complete: 60.9%; Average loss: 3.2785
Iteration: 2438; Percent complete: 61.0%; Average loss: 2.9573
Iteration: 2439; Percent complete: 61.0%; Average loss: 2.9110
Iteration: 2440; Percent complete: 61.0%; Average loss: 3.0268
Iteration: 2441; Percent complete: 61.0%; Average loss: 2.9220
Iteration: 2442; Percent complete: 61.1%; Average loss: 3.1547
Iteration: 2443; Percent complete: 61.1%; Average loss: 2.9219
Iteration: 2444; Percent complete: 61.1%; Average loss: 2.9076
Iteration: 2445; Percent complete: 61.1%; Average loss: 3.0772
Iteration: 2446; Percent complete: 61.2%; Average loss: 3.2113
Iteration: 2447; Percent complete: 61.2%; Average loss: 2.8676
Iteration: 2448; Percent complete: 61.2%; Average loss: 2.9556
Iteration: 2449; Percent complete: 61.2%; Average loss: 2.8963
Iteration: 2450; Percent complete: 61.3%; Average loss: 2.9662
Iteration: 2451; Percent complete: 61.3%; Average loss: 3.1052
Iteration: 2452; Percent complete: 61.3%; Average loss: 2.8623
Iteration: 2453; Percent complete: 61.3%; Average loss: 3.2011
Iteration: 2454; Percent complete: 61.4%; Average loss: 2.9601
Iteration: 2455; Percent complete: 61.4%; Average loss: 2.8555
Iteration: 2456; Percent complete: 61.4%; Average loss: 2.8474
Iteration: 2457; Percent complete: 61.4%; Average loss: 2.8591
Iteration: 2458; Percent complete: 61.5%; Average loss: 2.9801
Iteration: 2459; Percent complete: 61.5%; Average loss: 2.9931
Iteration: 2460; Percent complete: 61.5%; Average loss: 3.1892
Iteration: 2461; Percent complete: 61.5%; Average loss: 2.8353
Iteration: 2462; Percent complete: 61.6%; Average loss: 3.0264
Iteration: 2463; Percent complete: 61.6%; Average loss: 3.2437
Iteration: 2464; Percent complete: 61.6%; Average loss: 2.9460
Iteration: 2465; Percent complete: 61.6%; Average loss: 3.1235
Iteration: 2466; Percent complete: 61.7%; Average loss: 3.2745
Iteration: 2467; Percent complete: 61.7%; Average loss: 3.0105
Iteration: 2468; Percent complete: 61.7%; Average loss: 3.1564
Iteration: 2469; Percent complete: 61.7%; Average loss: 2.9493
Iteration: 2470; Percent complete: 61.8%; Average loss: 2.9828
Iteration: 2471; Percent complete: 61.8%; Average loss: 3.1325
Iteration: 2472; Percent complete: 61.8%; Average loss: 2.9926
Iteration: 2473; Percent complete: 61.8%; Average loss: 3.0115
Iteration: 2474; Percent complete: 61.9%; Average loss: 2.8053
Iteration: 2475; Percent complete: 61.9%; Average loss: 2.9337
Iteration: 2476; Percent complete: 61.9%; Average loss: 3.0375
Iteration: 2477; Percent complete: 61.9%; Average loss: 3.1667
Iteration: 2478; Percent complete: 62.0%; Average loss: 3.1879
Iteration: 2479; Percent complete: 62.0%; Average loss: 3.0244
Iteration: 2480; Percent complete: 62.0%; Average loss: 2.9220
Iteration: 2481; Percent complete: 62.0%; Average loss: 3.1733
Iteration: 2482; Percent complete: 62.1%; Average loss: 2.9524
Iteration: 2483; Percent complete: 62.1%; Average loss: 2.9973
Iteration: 2484; Percent complete: 62.1%; Average loss: 3.0526
Iteration: 2485; Percent complete: 62.1%; Average loss: 3.0021
Iteration: 2486; Percent complete: 62.2%; Average loss: 3.1101
Iteration: 2487; Percent complete: 62.2%; Average loss: 3.0176
Iteration: 2488; Percent complete: 62.2%; Average loss: 3.1183
Iteration: 2489; Percent complete: 62.2%; Average loss: 3.0697
Iteration: 2490; Percent complete: 62.3%; Average loss: 2.9935
Iteration: 2491; Percent complete: 62.3%; Average loss: 2.9545
Iteration: 2492; Percent complete: 62.3%; Average loss: 3.0314
Iteration: 2493; Percent complete: 62.3%; Average loss: 2.9253
Iteration: 2494; Percent complete: 62.4%; Average loss: 2.8941
Iteration: 2495; Percent complete: 62.4%; Average loss: 3.1192
Iteration: 2496; Percent complete: 62.4%; Average loss: 2.8628
Iteration: 2497; Percent complete: 62.4%; Average loss: 3.2439
Iteration: 2498; Percent complete: 62.5%; Average loss: 2.9405
Iteration: 2499; Percent complete: 62.5%; Average loss: 3.1385
Iteration: 2500; Percent complete: 62.5%; Average loss: 2.8171
Iteration: 2501; Percent complete: 62.5%; Average loss: 2.9833
Iteration: 2502; Percent complete: 62.5%; Average loss: 2.9744
Iteration: 2503; Percent complete: 62.6%; Average loss: 2.9391
Iteration: 2504; Percent complete: 62.6%; Average loss: 2.9802
Iteration: 2505; Percent complete: 62.6%; Average loss: 2.9581
Iteration: 2506; Percent complete: 62.6%; Average loss: 3.0010
Iteration: 2507; Percent complete: 62.7%; Average loss: 2.9388
Iteration: 2508; Percent complete: 62.7%; Average loss: 2.8311
Iteration: 2509; Percent complete: 62.7%; Average loss: 2.9233
Iteration: 2510; Percent complete: 62.7%; Average loss: 3.1429
Iteration: 2511; Percent complete: 62.8%; Average loss: 2.7536
Iteration: 2512; Percent complete: 62.8%; Average loss: 3.0557
Iteration: 2513; Percent complete: 62.8%; Average loss: 2.9018
Iteration: 2514; Percent complete: 62.8%; Average loss: 2.9158
Iteration: 2515; Percent complete: 62.9%; Average loss: 3.1022
Iteration: 2516; Percent complete: 62.9%; Average loss: 2.9125
Iteration: 2517; Percent complete: 62.9%; Average loss: 2.8339
Iteration: 2518; Percent complete: 62.9%; Average loss: 3.1135
Iteration: 2519; Percent complete: 63.0%; Average loss: 3.3360
Iteration: 2520; Percent complete: 63.0%; Average loss: 3.0596
Iteration: 2521; Percent complete: 63.0%; Average loss: 2.9489
Iteration: 2522; Percent complete: 63.0%; Average loss: 2.8568
Iteration: 2523; Percent complete: 63.1%; Average loss: 2.8294
Iteration: 2524; Percent complete: 63.1%; Average loss: 2.9901
Iteration: 2525; Percent complete: 63.1%; Average loss: 3.1754
Iteration: 2526; Percent complete: 63.1%; Average loss: 2.8787
Iteration: 2527; Percent complete: 63.2%; Average loss: 3.1208
Iteration: 2528; Percent complete: 63.2%; Average loss: 3.1434
Iteration: 2529; Percent complete: 63.2%; Average loss: 2.9007
Iteration: 2530; Percent complete: 63.2%; Average loss: 2.7679
Iteration: 2531; Percent complete: 63.3%; Average loss: 3.0811
Iteration: 2532; Percent complete: 63.3%; Average loss: 2.8495
Iteration: 2533; Percent complete: 63.3%; Average loss: 2.7789
Iteration: 2534; Percent complete: 63.3%; Average loss: 2.9329
Iteration: 2535; Percent complete: 63.4%; Average loss: 3.0399
Iteration: 2536; Percent complete: 63.4%; Average loss: 3.1179
Iteration: 2537; Percent complete: 63.4%; Average loss: 2.9511
Iteration: 2538; Percent complete: 63.4%; Average loss: 3.3850
Iteration: 2539; Percent complete: 63.5%; Average loss: 3.0428
Iteration: 2540; Percent complete: 63.5%; Average loss: 2.9734
Iteration: 2541; Percent complete: 63.5%; Average loss: 3.0346
Iteration: 2542; Percent complete: 63.5%; Average loss: 3.1346
Iteration: 2543; Percent complete: 63.6%; Average loss: 3.0429
Iteration: 2544; Percent complete: 63.6%; Average loss: 3.0293
Iteration: 2545; Percent complete: 63.6%; Average loss: 2.8512
Iteration: 2546; Percent complete: 63.6%; Average loss: 3.0069
Iteration: 2547; Percent complete: 63.7%; Average loss: 3.0358
Iteration: 2548; Percent complete: 63.7%; Average loss: 2.9176
Iteration: 2549; Percent complete: 63.7%; Average loss: 3.1494
Iteration: 2550; Percent complete: 63.7%; Average loss: 2.8454
Iteration: 2551; Percent complete: 63.8%; Average loss: 2.9188
Iteration: 2552; Percent complete: 63.8%; Average loss: 2.6890
Iteration: 2553; Percent complete: 63.8%; Average loss: 2.9009
Iteration: 2554; Percent complete: 63.8%; Average loss: 3.0091
Iteration: 2555; Percent complete: 63.9%; Average loss: 2.9836
Iteration: 2556; Percent complete: 63.9%; Average loss: 3.1802
Iteration: 2557; Percent complete: 63.9%; Average loss: 3.0665
Iteration: 2558; Percent complete: 63.9%; Average loss: 3.0492
Iteration: 2559; Percent complete: 64.0%; Average loss: 2.9150
Iteration: 2560; Percent complete: 64.0%; Average loss: 2.6551
Iteration: 2561; Percent complete: 64.0%; Average loss: 3.0929
Iteration: 2562; Percent complete: 64.0%; Average loss: 2.8986
Iteration: 2563; Percent complete: 64.1%; Average loss: 2.8988
Iteration: 2564; Percent complete: 64.1%; Average loss: 2.9940
Iteration: 2565; Percent complete: 64.1%; Average loss: 2.9709
Iteration: 2566; Percent complete: 64.1%; Average loss: 2.6880
Iteration: 2567; Percent complete: 64.2%; Average loss: 3.1667
Iteration: 2568; Percent complete: 64.2%; Average loss: 3.1475
Iteration: 2569; Percent complete: 64.2%; Average loss: 3.0655
Iteration: 2570; Percent complete: 64.2%; Average loss: 2.9824
Iteration: 2571; Percent complete: 64.3%; Average loss: 2.7554
Iteration: 2572; Percent complete: 64.3%; Average loss: 3.0554
Iteration: 2573; Percent complete: 64.3%; Average loss: 2.8496
Iteration: 2574; Percent complete: 64.3%; Average loss: 2.7199
Iteration: 2575; Percent complete: 64.4%; Average loss: 3.0461
Iteration: 2576; Percent complete: 64.4%; Average loss: 2.7460
Iteration: 2577; Percent complete: 64.4%; Average loss: 2.8950
Iteration: 2578; Percent complete: 64.5%; Average loss: 2.7632
Iteration: 2579; Percent complete: 64.5%; Average loss: 2.7157
Iteration: 2580; Percent complete: 64.5%; Average loss: 3.0351
Iteration: 2581; Percent complete: 64.5%; Average loss: 2.9816
Iteration: 2582; Percent complete: 64.5%; Average loss: 3.0475
Iteration: 2583; Percent complete: 64.6%; Average loss: 3.1992
Iteration: 2584; Percent complete: 64.6%; Average loss: 2.9923
Iteration: 2585; Percent complete: 64.6%; Average loss: 2.9536
Iteration: 2586; Percent complete: 64.6%; Average loss: 3.0604
Iteration: 2587; Percent complete: 64.7%; Average loss: 3.1048
Iteration: 2588; Percent complete: 64.7%; Average loss: 3.1882
Iteration: 2589; Percent complete: 64.7%; Average loss: 2.7107
Iteration: 2590; Percent complete: 64.8%; Average loss: 2.9341
Iteration: 2591; Percent complete: 64.8%; Average loss: 2.9562
Iteration: 2592; Percent complete: 64.8%; Average loss: 3.2448
Iteration: 2593; Percent complete: 64.8%; Average loss: 3.1826
Iteration: 2594; Percent complete: 64.8%; Average loss: 3.0490
Iteration: 2595; Percent complete: 64.9%; Average loss: 2.7483
Iteration: 2596; Percent complete: 64.9%; Average loss: 2.9058
Iteration: 2597; Percent complete: 64.9%; Average loss: 2.8956
Iteration: 2598; Percent complete: 65.0%; Average loss: 3.1356
Iteration: 2599; Percent complete: 65.0%; Average loss: 2.7935
Iteration: 2600; Percent complete: 65.0%; Average loss: 2.9572
Iteration: 2601; Percent complete: 65.0%; Average loss: 2.9209
Iteration: 2602; Percent complete: 65.0%; Average loss: 3.1578
Iteration: 2603; Percent complete: 65.1%; Average loss: 3.1081
Iteration: 2604; Percent complete: 65.1%; Average loss: 2.6687
Iteration: 2605; Percent complete: 65.1%; Average loss: 3.1763
Iteration: 2606; Percent complete: 65.1%; Average loss: 2.9953
Iteration: 2607; Percent complete: 65.2%; Average loss: 2.9120
Iteration: 2608; Percent complete: 65.2%; Average loss: 3.1248
Iteration: 2609; Percent complete: 65.2%; Average loss: 3.1135
Iteration: 2610; Percent complete: 65.2%; Average loss: 2.9197
Iteration: 2611; Percent complete: 65.3%; Average loss: 3.1876
Iteration: 2612; Percent complete: 65.3%; Average loss: 2.8877
Iteration: 2613; Percent complete: 65.3%; Average loss: 3.1298
Iteration: 2614; Percent complete: 65.3%; Average loss: 2.9319
Iteration: 2615; Percent complete: 65.4%; Average loss: 3.1518
Iteration: 2616; Percent complete: 65.4%; Average loss: 2.9744
Iteration: 2617; Percent complete: 65.4%; Average loss: 3.0065
Iteration: 2618; Percent complete: 65.5%; Average loss: 2.8252
Iteration: 2619; Percent complete: 65.5%; Average loss: 2.9315
Iteration: 2620; Percent complete: 65.5%; Average loss: 3.0046
Iteration: 2621; Percent complete: 65.5%; Average loss: 2.9792
Iteration: 2622; Percent complete: 65.5%; Average loss: 3.2520
Iteration: 2623; Percent complete: 65.6%; Average loss: 2.9975
Iteration: 2624; Percent complete: 65.6%; Average loss: 3.0153
Iteration: 2625; Percent complete: 65.6%; Average loss: 2.9332
Iteration: 2626; Percent complete: 65.6%; Average loss: 2.9931
Iteration: 2627; Percent complete: 65.7%; Average loss: 2.9861
Iteration: 2628; Percent complete: 65.7%; Average loss: 2.8734
Iteration: 2629; Percent complete: 65.7%; Average loss: 2.9268
Iteration: 2630; Percent complete: 65.8%; Average loss: 2.9835
Iteration: 2631; Percent complete: 65.8%; Average loss: 3.0037
Iteration: 2632; Percent complete: 65.8%; Average loss: 3.0867
Iteration: 2633; Percent complete: 65.8%; Average loss: 3.3324
Iteration: 2634; Percent complete: 65.8%; Average loss: 2.9979
Iteration: 2635; Percent complete: 65.9%; Average loss: 3.0396
Iteration: 2636; Percent complete: 65.9%; Average loss: 3.0550
Iteration: 2637; Percent complete: 65.9%; Average loss: 3.1689
Iteration: 2638; Percent complete: 66.0%; Average loss: 2.9740
Iteration: 2639; Percent complete: 66.0%; Average loss: 3.2187
Iteration: 2640; Percent complete: 66.0%; Average loss: 2.8781
Iteration: 2641; Percent complete: 66.0%; Average loss: 3.0443
Iteration: 2642; Percent complete: 66.0%; Average loss: 3.0320
Iteration: 2643; Percent complete: 66.1%; Average loss: 2.9156
Iteration: 2644; Percent complete: 66.1%; Average loss: 3.0361
Iteration: 2645; Percent complete: 66.1%; Average loss: 3.0162
Iteration: 2646; Percent complete: 66.1%; Average loss: 2.9324
Iteration: 2647; Percent complete: 66.2%; Average loss: 2.8822
Iteration: 2648; Percent complete: 66.2%; Average loss: 2.8319
Iteration: 2649; Percent complete: 66.2%; Average loss: 2.7876
Iteration: 2650; Percent complete: 66.2%; Average loss: 3.0303
Iteration: 2651; Percent complete: 66.3%; Average loss: 3.1917
Iteration: 2652; Percent complete: 66.3%; Average loss: 2.9490
Iteration: 2653; Percent complete: 66.3%; Average loss: 2.7875
Iteration: 2654; Percent complete: 66.3%; Average loss: 2.9659
Iteration: 2655; Percent complete: 66.4%; Average loss: 2.9887
Iteration: 2656; Percent complete: 66.4%; Average loss: 2.8908
Iteration: 2657; Percent complete: 66.4%; Average loss: 3.0185
Iteration: 2658; Percent complete: 66.5%; Average loss: 2.8203
Iteration: 2659; Percent complete: 66.5%; Average loss: 2.9080
Iteration: 2660; Percent complete: 66.5%; Average loss: 2.7844
Iteration: 2661; Percent complete: 66.5%; Average loss: 2.9378
Iteration: 2662; Percent complete: 66.5%; Average loss: 3.0107
Iteration: 2663; Percent complete: 66.6%; Average loss: 3.2191
Iteration: 2664; Percent complete: 66.6%; Average loss: 2.7391
Iteration: 2665; Percent complete: 66.6%; Average loss: 2.8222
Iteration: 2666; Percent complete: 66.6%; Average loss: 3.0467
Iteration: 2667; Percent complete: 66.7%; Average loss: 2.7877
Iteration: 2668; Percent complete: 66.7%; Average loss: 2.8578
Iteration: 2669; Percent complete: 66.7%; Average loss: 2.8309
Iteration: 2670; Percent complete: 66.8%; Average loss: 2.7006
Iteration: 2671; Percent complete: 66.8%; Average loss: 3.1315
Iteration: 2672; Percent complete: 66.8%; Average loss: 2.9766
Iteration: 2673; Percent complete: 66.8%; Average loss: 3.1869
Iteration: 2674; Percent complete: 66.8%; Average loss: 2.7988
Iteration: 2675; Percent complete: 66.9%; Average loss: 3.0594
Iteration: 2676; Percent complete: 66.9%; Average loss: 2.9842
Iteration: 2677; Percent complete: 66.9%; Average loss: 3.1795
Iteration: 2678; Percent complete: 67.0%; Average loss: 2.9927
Iteration: 2679; Percent complete: 67.0%; Average loss: 3.0349
Iteration: 2680; Percent complete: 67.0%; Average loss: 2.8727
Iteration: 2681; Percent complete: 67.0%; Average loss: 3.2003
Iteration: 2682; Percent complete: 67.0%; Average loss: 2.8664
Iteration: 2683; Percent complete: 67.1%; Average loss: 3.2751
Iteration: 2684; Percent complete: 67.1%; Average loss: 2.8388
Iteration: 2685; Percent complete: 67.1%; Average loss: 2.7977
Iteration: 2686; Percent complete: 67.2%; Average loss: 2.9610
Iteration: 2687; Percent complete: 67.2%; Average loss: 2.8854
Iteration: 2688; Percent complete: 67.2%; Average loss: 3.0576
Iteration: 2689; Percent complete: 67.2%; Average loss: 3.0319
Iteration: 2690; Percent complete: 67.2%; Average loss: 3.0969
Iteration: 2691; Percent complete: 67.3%; Average loss: 2.9085
Iteration: 2692; Percent complete: 67.3%; Average loss: 2.9624
Iteration: 2693; Percent complete: 67.3%; Average loss: 2.9119
Iteration: 2694; Percent complete: 67.3%; Average loss: 3.0543
Iteration: 2695; Percent complete: 67.4%; Average loss: 3.0917
Iteration: 2696; Percent complete: 67.4%; Average loss: 3.1484
Iteration: 2697; Percent complete: 67.4%; Average loss: 3.1310
Iteration: 2698; Percent complete: 67.5%; Average loss: 2.9634
Iteration: 2699; Percent complete: 67.5%; Average loss: 2.9887
Iteration: 2700; Percent complete: 67.5%; Average loss: 3.0870
Iteration: 2701; Percent complete: 67.5%; Average loss: 3.0360
Iteration: 2702; Percent complete: 67.5%; Average loss: 3.0397
Iteration: 2703; Percent complete: 67.6%; Average loss: 2.7578
Iteration: 2704; Percent complete: 67.6%; Average loss: 3.0241
Iteration: 2705; Percent complete: 67.6%; Average loss: 3.1623
Iteration: 2706; Percent complete: 67.7%; Average loss: 3.1693
Iteration: 2707; Percent complete: 67.7%; Average loss: 2.8241
Iteration: 2708; Percent complete: 67.7%; Average loss: 2.8149
Iteration: 2709; Percent complete: 67.7%; Average loss: 2.9341
Iteration: 2710; Percent complete: 67.8%; Average loss: 2.7664
Iteration: 2711; Percent complete: 67.8%; Average loss: 2.7661
Iteration: 2712; Percent complete: 67.8%; Average loss: 2.8582
Iteration: 2713; Percent complete: 67.8%; Average loss: 2.8344
Iteration: 2714; Percent complete: 67.8%; Average loss: 2.9204
Iteration: 2715; Percent complete: 67.9%; Average loss: 3.2171
Iteration: 2716; Percent complete: 67.9%; Average loss: 3.0141
Iteration: 2717; Percent complete: 67.9%; Average loss: 2.8693
Iteration: 2718; Percent complete: 68.0%; Average loss: 3.2085
Iteration: 2719; Percent complete: 68.0%; Average loss: 3.0159
Iteration: 2720; Percent complete: 68.0%; Average loss: 2.9131
Iteration: 2721; Percent complete: 68.0%; Average loss: 3.1875
Iteration: 2722; Percent complete: 68.0%; Average loss: 3.0138
Iteration: 2723; Percent complete: 68.1%; Average loss: 2.9734
Iteration: 2724; Percent complete: 68.1%; Average loss: 2.9147
Iteration: 2725; Percent complete: 68.1%; Average loss: 3.1628
Iteration: 2726; Percent complete: 68.2%; Average loss: 3.0118
Iteration: 2727; Percent complete: 68.2%; Average loss: 3.1707
Iteration: 2728; Percent complete: 68.2%; Average loss: 2.7622
Iteration: 2729; Percent complete: 68.2%; Average loss: 2.7788
Iteration: 2730; Percent complete: 68.2%; Average loss: 3.0295
Iteration: 2731; Percent complete: 68.3%; Average loss: 2.8495
Iteration: 2732; Percent complete: 68.3%; Average loss: 2.8609
Iteration: 2733; Percent complete: 68.3%; Average loss: 2.9823
Iteration: 2734; Percent complete: 68.3%; Average loss: 3.0454
Iteration: 2735; Percent complete: 68.4%; Average loss: 2.8889
Iteration: 2736; Percent complete: 68.4%; Average loss: 2.7369
Iteration: 2737; Percent complete: 68.4%; Average loss: 2.8772
Iteration: 2738; Percent complete: 68.5%; Average loss: 2.8005
Iteration: 2739; Percent complete: 68.5%; Average loss: 2.9068
Iteration: 2740; Percent complete: 68.5%; Average loss: 2.7097
Iteration: 2741; Percent complete: 68.5%; Average loss: 2.8537
Iteration: 2742; Percent complete: 68.5%; Average loss: 2.8363
Iteration: 2743; Percent complete: 68.6%; Average loss: 2.6225
Iteration: 2744; Percent complete: 68.6%; Average loss: 2.8475
Iteration: 2745; Percent complete: 68.6%; Average loss: 2.9714
Iteration: 2746; Percent complete: 68.7%; Average loss: 3.0617
Iteration: 2747; Percent complete: 68.7%; Average loss: 2.9521
Iteration: 2748; Percent complete: 68.7%; Average loss: 2.7701
Iteration: 2749; Percent complete: 68.7%; Average loss: 2.9163
Iteration: 2750; Percent complete: 68.8%; Average loss: 2.9433
Iteration: 2751; Percent complete: 68.8%; Average loss: 3.0333
Iteration: 2752; Percent complete: 68.8%; Average loss: 2.9192
Iteration: 2753; Percent complete: 68.8%; Average loss: 3.0843
Iteration: 2754; Percent complete: 68.8%; Average loss: 2.7378
Iteration: 2755; Percent complete: 68.9%; Average loss: 2.7887
Iteration: 2756; Percent complete: 68.9%; Average loss: 2.7997
Iteration: 2757; Percent complete: 68.9%; Average loss: 3.0256
Iteration: 2758; Percent complete: 69.0%; Average loss: 2.9560
Iteration: 2759; Percent complete: 69.0%; Average loss: 2.8989
Iteration: 2760; Percent complete: 69.0%; Average loss: 2.8329
Iteration: 2761; Percent complete: 69.0%; Average loss: 2.8123
Iteration: 2762; Percent complete: 69.0%; Average loss: 2.6750
Iteration: 2763; Percent complete: 69.1%; Average loss: 2.7992
Iteration: 2764; Percent complete: 69.1%; Average loss: 2.9423
Iteration: 2765; Percent complete: 69.1%; Average loss: 2.9550
Iteration: 2766; Percent complete: 69.2%; Average loss: 2.9024
Iteration: 2767; Percent complete: 69.2%; Average loss: 2.7846
Iteration: 2768; Percent complete: 69.2%; Average loss: 2.9249
Iteration: 2769; Percent complete: 69.2%; Average loss: 2.9643
Iteration: 2770; Percent complete: 69.2%; Average loss: 3.1543
Iteration: 2771; Percent complete: 69.3%; Average loss: 2.9984
Iteration: 2772; Percent complete: 69.3%; Average loss: 2.8268
Iteration: 2773; Percent complete: 69.3%; Average loss: 2.8558
Iteration: 2774; Percent complete: 69.3%; Average loss: 3.0864
Iteration: 2775; Percent complete: 69.4%; Average loss: 2.9380
Iteration: 2776; Percent complete: 69.4%; Average loss: 3.2542
Iteration: 2777; Percent complete: 69.4%; Average loss: 2.9894
Iteration: 2778; Percent complete: 69.5%; Average loss: 3.0883
Iteration: 2779; Percent complete: 69.5%; Average loss: 2.8778
Iteration: 2780; Percent complete: 69.5%; Average loss: 3.0581
Iteration: 2781; Percent complete: 69.5%; Average loss: 2.9117
Iteration: 2782; Percent complete: 69.5%; Average loss: 2.9412
Iteration: 2783; Percent complete: 69.6%; Average loss: 2.8774
Iteration: 2784; Percent complete: 69.6%; Average loss: 2.5030
Iteration: 2785; Percent complete: 69.6%; Average loss: 2.8014
Iteration: 2786; Percent complete: 69.7%; Average loss: 2.8829
Iteration: 2787; Percent complete: 69.7%; Average loss: 3.1632
Iteration: 2788; Percent complete: 69.7%; Average loss: 2.9188
Iteration: 2789; Percent complete: 69.7%; Average loss: 2.9454
Iteration: 2790; Percent complete: 69.8%; Average loss: 2.8793
Iteration: 2791; Percent complete: 69.8%; Average loss: 2.8018
Iteration: 2792; Percent complete: 69.8%; Average loss: 2.8671
Iteration: 2793; Percent complete: 69.8%; Average loss: 2.8587
Iteration: 2794; Percent complete: 69.8%; Average loss: 2.9135
Iteration: 2795; Percent complete: 69.9%; Average loss: 2.8698
Iteration: 2796; Percent complete: 69.9%; Average loss: 3.0718
Iteration: 2797; Percent complete: 69.9%; Average loss: 3.1923
Iteration: 2798; Percent complete: 70.0%; Average loss: 2.8131
Iteration: 2799; Percent complete: 70.0%; Average loss: 2.9671
Iteration: 2800; Percent complete: 70.0%; Average loss: 2.9118
Iteration: 2801; Percent complete: 70.0%; Average loss: 2.9811
Iteration: 2802; Percent complete: 70.0%; Average loss: 2.8700
Iteration: 2803; Percent complete: 70.1%; Average loss: 2.9446
Iteration: 2804; Percent complete: 70.1%; Average loss: 2.6425
Iteration: 2805; Percent complete: 70.1%; Average loss: 2.9349
Iteration: 2806; Percent complete: 70.2%; Average loss: 2.9210
Iteration: 2807; Percent complete: 70.2%; Average loss: 2.8685
Iteration: 2808; Percent complete: 70.2%; Average loss: 2.8317
Iteration: 2809; Percent complete: 70.2%; Average loss: 2.8813
Iteration: 2810; Percent complete: 70.2%; Average loss: 2.9897
Iteration: 2811; Percent complete: 70.3%; Average loss: 2.6800
Iteration: 2812; Percent complete: 70.3%; Average loss: 2.7893
Iteration: 2813; Percent complete: 70.3%; Average loss: 2.9202
Iteration: 2814; Percent complete: 70.3%; Average loss: 2.8314
Iteration: 2815; Percent complete: 70.4%; Average loss: 2.8180
Iteration: 2816; Percent complete: 70.4%; Average loss: 2.7399
Iteration: 2817; Percent complete: 70.4%; Average loss: 2.8171
Iteration: 2818; Percent complete: 70.5%; Average loss: 2.9670
Iteration: 2819; Percent complete: 70.5%; Average loss: 2.7279
Iteration: 2820; Percent complete: 70.5%; Average loss: 2.9538
Iteration: 2821; Percent complete: 70.5%; Average loss: 2.9039
Iteration: 2822; Percent complete: 70.5%; Average loss: 2.7024
Iteration: 2823; Percent complete: 70.6%; Average loss: 2.8774
Iteration: 2824; Percent complete: 70.6%; Average loss: 2.6414
Iteration: 2825; Percent complete: 70.6%; Average loss: 2.7814
Iteration: 2826; Percent complete: 70.7%; Average loss: 2.9600
Iteration: 2827; Percent complete: 70.7%; Average loss: 2.8373
Iteration: 2828; Percent complete: 70.7%; Average loss: 2.8249
Iteration: 2829; Percent complete: 70.7%; Average loss: 2.7443
Iteration: 2830; Percent complete: 70.8%; Average loss: 2.8702
Iteration: 2831; Percent complete: 70.8%; Average loss: 2.9592
Iteration: 2832; Percent complete: 70.8%; Average loss: 3.0201
Iteration: 2833; Percent complete: 70.8%; Average loss: 2.8334
Iteration: 2834; Percent complete: 70.9%; Average loss: 2.8935
Iteration: 2835; Percent complete: 70.9%; Average loss: 2.8954
Iteration: 2836; Percent complete: 70.9%; Average loss: 2.8996
Iteration: 2837; Percent complete: 70.9%; Average loss: 2.9693
Iteration: 2838; Percent complete: 71.0%; Average loss: 2.9708
Iteration: 2839; Percent complete: 71.0%; Average loss: 2.7992
Iteration: 2840; Percent complete: 71.0%; Average loss: 2.9129
Iteration: 2841; Percent complete: 71.0%; Average loss: 3.0217
Iteration: 2842; Percent complete: 71.0%; Average loss: 3.0321
Iteration: 2843; Percent complete: 71.1%; Average loss: 2.7418
Iteration: 2844; Percent complete: 71.1%; Average loss: 2.8843
Iteration: 2845; Percent complete: 71.1%; Average loss: 2.9101
Iteration: 2846; Percent complete: 71.2%; Average loss: 2.8142
Iteration: 2847; Percent complete: 71.2%; Average loss: 2.8380
Iteration: 2848; Percent complete: 71.2%; Average loss: 3.1818
Iteration: 2849; Percent complete: 71.2%; Average loss: 2.9256
Iteration: 2850; Percent complete: 71.2%; Average loss: 2.9900
Iteration: 2851; Percent complete: 71.3%; Average loss: 2.8107
Iteration: 2852; Percent complete: 71.3%; Average loss: 3.1073
Iteration: 2853; Percent complete: 71.3%; Average loss: 2.8881
Iteration: 2854; Percent complete: 71.4%; Average loss: 3.0945
Iteration: 2855; Percent complete: 71.4%; Average loss: 2.8600
Iteration: 2856; Percent complete: 71.4%; Average loss: 3.1735
Iteration: 2857; Percent complete: 71.4%; Average loss: 2.8685
Iteration: 2858; Percent complete: 71.5%; Average loss: 2.6396
Iteration: 2859; Percent complete: 71.5%; Average loss: 2.9886
Iteration: 2860; Percent complete: 71.5%; Average loss: 2.8549
Iteration: 2861; Percent complete: 71.5%; Average loss: 3.0388
Iteration: 2862; Percent complete: 71.5%; Average loss: 2.9153
Iteration: 2863; Percent complete: 71.6%; Average loss: 3.0808
Iteration: 2864; Percent complete: 71.6%; Average loss: 2.9581
Iteration: 2865; Percent complete: 71.6%; Average loss: 2.8749
Iteration: 2866; Percent complete: 71.7%; Average loss: 3.0133
Iteration: 2867; Percent complete: 71.7%; Average loss: 2.8826
Iteration: 2868; Percent complete: 71.7%; Average loss: 3.1071
Iteration: 2869; Percent complete: 71.7%; Average loss: 3.2357
Iteration: 2870; Percent complete: 71.8%; Average loss: 2.9616
Iteration: 2871; Percent complete: 71.8%; Average loss: 2.9917
Iteration: 2872; Percent complete: 71.8%; Average loss: 2.7713
Iteration: 2873; Percent complete: 71.8%; Average loss: 3.0956
Iteration: 2874; Percent complete: 71.9%; Average loss: 3.1460
Iteration: 2875; Percent complete: 71.9%; Average loss: 2.8301
Iteration: 2876; Percent complete: 71.9%; Average loss: 2.8530
Iteration: 2877; Percent complete: 71.9%; Average loss: 2.8746
Iteration: 2878; Percent complete: 72.0%; Average loss: 2.6993
Iteration: 2879; Percent complete: 72.0%; Average loss: 2.8553
Iteration: 2880; Percent complete: 72.0%; Average loss: 2.8745
Iteration: 2881; Percent complete: 72.0%; Average loss: 2.9519
Iteration: 2882; Percent complete: 72.0%; Average loss: 2.7980
Iteration: 2883; Percent complete: 72.1%; Average loss: 3.0907
Iteration: 2884; Percent complete: 72.1%; Average loss: 3.0783
Iteration: 2885; Percent complete: 72.1%; Average loss: 2.8224
Iteration: 2886; Percent complete: 72.2%; Average loss: 3.0733
Iteration: 2887; Percent complete: 72.2%; Average loss: 2.9005
Iteration: 2888; Percent complete: 72.2%; Average loss: 2.9899
Iteration: 2889; Percent complete: 72.2%; Average loss: 2.7864
Iteration: 2890; Percent complete: 72.2%; Average loss: 2.9380
Iteration: 2891; Percent complete: 72.3%; Average loss: 3.0320
Iteration: 2892; Percent complete: 72.3%; Average loss: 2.9091
Iteration: 2893; Percent complete: 72.3%; Average loss: 2.8753
Iteration: 2894; Percent complete: 72.4%; Average loss: 2.7640
Iteration: 2895; Percent complete: 72.4%; Average loss: 3.0131
Iteration: 2896; Percent complete: 72.4%; Average loss: 2.7306
Iteration: 2897; Percent complete: 72.4%; Average loss: 2.7809
Iteration: 2898; Percent complete: 72.5%; Average loss: 2.8922
Iteration: 2899; Percent complete: 72.5%; Average loss: 3.0250
Iteration: 2900; Percent complete: 72.5%; Average loss: 3.2211
Iteration: 2901; Percent complete: 72.5%; Average loss: 2.8617
Iteration: 2902; Percent complete: 72.5%; Average loss: 2.9290
Iteration: 2903; Percent complete: 72.6%; Average loss: 2.8763
Iteration: 2904; Percent complete: 72.6%; Average loss: 3.3053
Iteration: 2905; Percent complete: 72.6%; Average loss: 3.3923
Iteration: 2906; Percent complete: 72.7%; Average loss: 2.7208
Iteration: 2907; Percent complete: 72.7%; Average loss: 2.9043
Iteration: 2908; Percent complete: 72.7%; Average loss: 3.1014
Iteration: 2909; Percent complete: 72.7%; Average loss: 2.8586
Iteration: 2910; Percent complete: 72.8%; Average loss: 2.7219
Iteration: 2911; Percent complete: 72.8%; Average loss: 3.0506
Iteration: 2912; Percent complete: 72.8%; Average loss: 2.9639
Iteration: 2913; Percent complete: 72.8%; Average loss: 3.0229
Iteration: 2914; Percent complete: 72.9%; Average loss: 3.0561
Iteration: 2915; Percent complete: 72.9%; Average loss: 2.9056
Iteration: 2916; Percent complete: 72.9%; Average loss: 2.7049
Iteration: 2917; Percent complete: 72.9%; Average loss: 2.8612
Iteration: 2918; Percent complete: 73.0%; Average loss: 2.7637
Iteration: 2919; Percent complete: 73.0%; Average loss: 2.9806
Iteration: 2920; Percent complete: 73.0%; Average loss: 2.5532
Iteration: 2921; Percent complete: 73.0%; Average loss: 3.0009
Iteration: 2922; Percent complete: 73.0%; Average loss: 2.6663
Iteration: 2923; Percent complete: 73.1%; Average loss: 2.6665
Iteration: 2924; Percent complete: 73.1%; Average loss: 2.9118
Iteration: 2925; Percent complete: 73.1%; Average loss: 2.8275
Iteration: 2926; Percent complete: 73.2%; Average loss: 2.7824
Iteration: 2927; Percent complete: 73.2%; Average loss: 2.8759
Iteration: 2928; Percent complete: 73.2%; Average loss: 3.0964
Iteration: 2929; Percent complete: 73.2%; Average loss: 2.9035
Iteration: 2930; Percent complete: 73.2%; Average loss: 2.7819
Iteration: 2931; Percent complete: 73.3%; Average loss: 2.7995
Iteration: 2932; Percent complete: 73.3%; Average loss: 2.7955
Iteration: 2933; Percent complete: 73.3%; Average loss: 2.9388
Iteration: 2934; Percent complete: 73.4%; Average loss: 2.9923
Iteration: 2935; Percent complete: 73.4%; Average loss: 2.9422
Iteration: 2936; Percent complete: 73.4%; Average loss: 2.9020
Iteration: 2937; Percent complete: 73.4%; Average loss: 2.8759
Iteration: 2938; Percent complete: 73.5%; Average loss: 2.9994
Iteration: 2939; Percent complete: 73.5%; Average loss: 2.7546
Iteration: 2940; Percent complete: 73.5%; Average loss: 2.5402
Iteration: 2941; Percent complete: 73.5%; Average loss: 2.9686
Iteration: 2942; Percent complete: 73.6%; Average loss: 2.7507
Iteration: 2943; Percent complete: 73.6%; Average loss: 2.8401
Iteration: 2944; Percent complete: 73.6%; Average loss: 2.9707
Iteration: 2945; Percent complete: 73.6%; Average loss: 3.0471
Iteration: 2946; Percent complete: 73.7%; Average loss: 2.6422
Iteration: 2947; Percent complete: 73.7%; Average loss: 2.9047
Iteration: 2948; Percent complete: 73.7%; Average loss: 2.6692
Iteration: 2949; Percent complete: 73.7%; Average loss: 2.6201
Iteration: 2950; Percent complete: 73.8%; Average loss: 3.0588
Iteration: 2951; Percent complete: 73.8%; Average loss: 2.8152
Iteration: 2952; Percent complete: 73.8%; Average loss: 2.9004
Iteration: 2953; Percent complete: 73.8%; Average loss: 3.0115
Iteration: 2954; Percent complete: 73.9%; Average loss: 2.7453
Iteration: 2955; Percent complete: 73.9%; Average loss: 3.0708
Iteration: 2956; Percent complete: 73.9%; Average loss: 2.9296
Iteration: 2957; Percent complete: 73.9%; Average loss: 2.8374
Iteration: 2958; Percent complete: 74.0%; Average loss: 2.9627
Iteration: 2959; Percent complete: 74.0%; Average loss: 2.6941
Iteration: 2960; Percent complete: 74.0%; Average loss: 3.0331
Iteration: 2961; Percent complete: 74.0%; Average loss: 2.9437
Iteration: 2962; Percent complete: 74.1%; Average loss: 2.8836
Iteration: 2963; Percent complete: 74.1%; Average loss: 2.9721
Iteration: 2964; Percent complete: 74.1%; Average loss: 3.0878
Iteration: 2965; Percent complete: 74.1%; Average loss: 3.0725
Iteration: 2966; Percent complete: 74.2%; Average loss: 2.8592
Iteration: 2967; Percent complete: 74.2%; Average loss: 2.9025
Iteration: 2968; Percent complete: 74.2%; Average loss: 2.9519
Iteration: 2969; Percent complete: 74.2%; Average loss: 2.5462
Iteration: 2970; Percent complete: 74.2%; Average loss: 3.0838
Iteration: 2971; Percent complete: 74.3%; Average loss: 3.0493
Iteration: 2972; Percent complete: 74.3%; Average loss: 2.6883
Iteration: 2973; Percent complete: 74.3%; Average loss: 2.9625
Iteration: 2974; Percent complete: 74.4%; Average loss: 2.9734
Iteration: 2975; Percent complete: 74.4%; Average loss: 2.9519
Iteration: 2976; Percent complete: 74.4%; Average loss: 2.8478
Iteration: 2977; Percent complete: 74.4%; Average loss: 3.2129
Iteration: 2978; Percent complete: 74.5%; Average loss: 2.8505
Iteration: 2979; Percent complete: 74.5%; Average loss: 2.8885
Iteration: 2980; Percent complete: 74.5%; Average loss: 2.9940
Iteration: 2981; Percent complete: 74.5%; Average loss: 2.9672
Iteration: 2982; Percent complete: 74.6%; Average loss: 3.1369
Iteration: 2983; Percent complete: 74.6%; Average loss: 2.8661
Iteration: 2984; Percent complete: 74.6%; Average loss: 2.9915
Iteration: 2985; Percent complete: 74.6%; Average loss: 3.2091
Iteration: 2986; Percent complete: 74.7%; Average loss: 2.7903
Iteration: 2987; Percent complete: 74.7%; Average loss: 2.9809
Iteration: 2988; Percent complete: 74.7%; Average loss: 2.5772
Iteration: 2989; Percent complete: 74.7%; Average loss: 2.8088
Iteration: 2990; Percent complete: 74.8%; Average loss: 2.7880
Iteration: 2991; Percent complete: 74.8%; Average loss: 2.7351
Iteration: 2992; Percent complete: 74.8%; Average loss: 2.9241
Iteration: 2993; Percent complete: 74.8%; Average loss: 2.7081
Iteration: 2994; Percent complete: 74.9%; Average loss: 3.0224
Iteration: 2995; Percent complete: 74.9%; Average loss: 2.8570
Iteration: 2996; Percent complete: 74.9%; Average loss: 3.1771
Iteration: 2997; Percent complete: 74.9%; Average loss: 2.8559
Iteration: 2998; Percent complete: 75.0%; Average loss: 2.8876
Iteration: 2999; Percent complete: 75.0%; Average loss: 2.6920
Iteration: 3000; Percent complete: 75.0%; Average loss: 2.9551
Iteration: 3001; Percent complete: 75.0%; Average loss: 2.9592
Iteration: 3002; Percent complete: 75.0%; Average loss: 2.8250
Iteration: 3003; Percent complete: 75.1%; Average loss: 2.8671
Iteration: 3004; Percent complete: 75.1%; Average loss: 2.7073
Iteration: 3005; Percent complete: 75.1%; Average loss: 2.8676
Iteration: 3006; Percent complete: 75.1%; Average loss: 2.9598
Iteration: 3007; Percent complete: 75.2%; Average loss: 3.1265
Iteration: 3008; Percent complete: 75.2%; Average loss: 2.9801
Iteration: 3009; Percent complete: 75.2%; Average loss: 3.1653
Iteration: 3010; Percent complete: 75.2%; Average loss: 2.8028
Iteration: 3011; Percent complete: 75.3%; Average loss: 2.8378
Iteration: 3012; Percent complete: 75.3%; Average loss: 2.6585
Iteration: 3013; Percent complete: 75.3%; Average loss: 2.9260
Iteration: 3014; Percent complete: 75.3%; Average loss: 2.9786
Iteration: 3015; Percent complete: 75.4%; Average loss: 2.8713
Iteration: 3016; Percent complete: 75.4%; Average loss: 2.9116
Iteration: 3017; Percent complete: 75.4%; Average loss: 2.8133
Iteration: 3018; Percent complete: 75.4%; Average loss: 3.0380
Iteration: 3019; Percent complete: 75.5%; Average loss: 2.6278
Iteration: 3020; Percent complete: 75.5%; Average loss: 2.8031
Iteration: 3021; Percent complete: 75.5%; Average loss: 2.6456
Iteration: 3022; Percent complete: 75.5%; Average loss: 2.8884
Iteration: 3023; Percent complete: 75.6%; Average loss: 2.7799
Iteration: 3024; Percent complete: 75.6%; Average loss: 2.8636
Iteration: 3025; Percent complete: 75.6%; Average loss: 2.7724
Iteration: 3026; Percent complete: 75.6%; Average loss: 2.7070
Iteration: 3027; Percent complete: 75.7%; Average loss: 2.8070
Iteration: 3028; Percent complete: 75.7%; Average loss: 2.9286
Iteration: 3029; Percent complete: 75.7%; Average loss: 3.2154
Iteration: 3030; Percent complete: 75.8%; Average loss: 2.9059
Iteration: 3031; Percent complete: 75.8%; Average loss: 2.8551
Iteration: 3032; Percent complete: 75.8%; Average loss: 3.0419
Iteration: 3033; Percent complete: 75.8%; Average loss: 2.9976
Iteration: 3034; Percent complete: 75.8%; Average loss: 2.9452
Iteration: 3035; Percent complete: 75.9%; Average loss: 2.8696
Iteration: 3036; Percent complete: 75.9%; Average loss: 2.9450
Iteration: 3037; Percent complete: 75.9%; Average loss: 2.6354
Iteration: 3038; Percent complete: 75.9%; Average loss: 2.9982
Iteration: 3039; Percent complete: 76.0%; Average loss: 2.7800
Iteration: 3040; Percent complete: 76.0%; Average loss: 2.9933
Iteration: 3041; Percent complete: 76.0%; Average loss: 2.8763
Iteration: 3042; Percent complete: 76.0%; Average loss: 3.0441
Iteration: 3043; Percent complete: 76.1%; Average loss: 2.9083
Iteration: 3044; Percent complete: 76.1%; Average loss: 2.9248
Iteration: 3045; Percent complete: 76.1%; Average loss: 2.5974
Iteration: 3046; Percent complete: 76.1%; Average loss: 2.7652
Iteration: 3047; Percent complete: 76.2%; Average loss: 3.3830
Iteration: 3048; Percent complete: 76.2%; Average loss: 2.9253
Iteration: 3049; Percent complete: 76.2%; Average loss: 2.9386
Iteration: 3050; Percent complete: 76.2%; Average loss: 2.7508
Iteration: 3051; Percent complete: 76.3%; Average loss: 2.9059
Iteration: 3052; Percent complete: 76.3%; Average loss: 2.9770
Iteration: 3053; Percent complete: 76.3%; Average loss: 2.8495
Iteration: 3054; Percent complete: 76.3%; Average loss: 2.7221
Iteration: 3055; Percent complete: 76.4%; Average loss: 2.9746
Iteration: 3056; Percent complete: 76.4%; Average loss: 2.8234
Iteration: 3057; Percent complete: 76.4%; Average loss: 2.6954
Iteration: 3058; Percent complete: 76.4%; Average loss: 2.7937
Iteration: 3059; Percent complete: 76.5%; Average loss: 2.7768
Iteration: 3060; Percent complete: 76.5%; Average loss: 2.9833
Iteration: 3061; Percent complete: 76.5%; Average loss: 2.8907
Iteration: 3062; Percent complete: 76.5%; Average loss: 2.6126
Iteration: 3063; Percent complete: 76.6%; Average loss: 2.8169
Iteration: 3064; Percent complete: 76.6%; Average loss: 2.7705
Iteration: 3065; Percent complete: 76.6%; Average loss: 2.8540
Iteration: 3066; Percent complete: 76.6%; Average loss: 3.1109
Iteration: 3067; Percent complete: 76.7%; Average loss: 2.7784
Iteration: 3068; Percent complete: 76.7%; Average loss: 2.8276
Iteration: 3069; Percent complete: 76.7%; Average loss: 2.7408
Iteration: 3070; Percent complete: 76.8%; Average loss: 3.0796
Iteration: 3071; Percent complete: 76.8%; Average loss: 2.9490
Iteration: 3072; Percent complete: 76.8%; Average loss: 2.8555
Iteration: 3073; Percent complete: 76.8%; Average loss: 3.0500
Iteration: 3074; Percent complete: 76.8%; Average loss: 2.9371
Iteration: 3075; Percent complete: 76.9%; Average loss: 3.0052
Iteration: 3076; Percent complete: 76.9%; Average loss: 2.9716
Iteration: 3077; Percent complete: 76.9%; Average loss: 2.7871
Iteration: 3078; Percent complete: 77.0%; Average loss: 2.5921
Iteration: 3079; Percent complete: 77.0%; Average loss: 3.0084
Iteration: 3080; Percent complete: 77.0%; Average loss: 2.8960
Iteration: 3081; Percent complete: 77.0%; Average loss: 2.9838
Iteration: 3082; Percent complete: 77.0%; Average loss: 2.9344
Iteration: 3083; Percent complete: 77.1%; Average loss: 3.0274
Iteration: 3084; Percent complete: 77.1%; Average loss: 3.1397
Iteration: 3085; Percent complete: 77.1%; Average loss: 2.6717
Iteration: 3086; Percent complete: 77.1%; Average loss: 2.7067
Iteration: 3087; Percent complete: 77.2%; Average loss: 2.7979
Iteration: 3088; Percent complete: 77.2%; Average loss: 2.6653
Iteration: 3089; Percent complete: 77.2%; Average loss: 2.8012
Iteration: 3090; Percent complete: 77.2%; Average loss: 2.7663
Iteration: 3091; Percent complete: 77.3%; Average loss: 3.1427
Iteration: 3092; Percent complete: 77.3%; Average loss: 2.8504
Iteration: 3093; Percent complete: 77.3%; Average loss: 3.1476
Iteration: 3094; Percent complete: 77.3%; Average loss: 2.9567
Iteration: 3095; Percent complete: 77.4%; Average loss: 2.9380
Iteration: 3096; Percent complete: 77.4%; Average loss: 3.1203
Iteration: 3097; Percent complete: 77.4%; Average loss: 2.8814
Iteration: 3098; Percent complete: 77.5%; Average loss: 2.7560
Iteration: 3099; Percent complete: 77.5%; Average loss: 2.7662
Iteration: 3100; Percent complete: 77.5%; Average loss: 2.9002
Iteration: 3101; Percent complete: 77.5%; Average loss: 2.9256
Iteration: 3102; Percent complete: 77.5%; Average loss: 3.0169
Iteration: 3103; Percent complete: 77.6%; Average loss: 2.7053
Iteration: 3104; Percent complete: 77.6%; Average loss: 2.7635
Iteration: 3105; Percent complete: 77.6%; Average loss: 2.8494
Iteration: 3106; Percent complete: 77.6%; Average loss: 2.7226
Iteration: 3107; Percent complete: 77.7%; Average loss: 3.0140
Iteration: 3108; Percent complete: 77.7%; Average loss: 2.6474
Iteration: 3109; Percent complete: 77.7%; Average loss: 2.9945
Iteration: 3110; Percent complete: 77.8%; Average loss: 2.9153
Iteration: 3111; Percent complete: 77.8%; Average loss: 2.7695
Iteration: 3112; Percent complete: 77.8%; Average loss: 2.5487
Iteration: 3113; Percent complete: 77.8%; Average loss: 2.6419
Iteration: 3114; Percent complete: 77.8%; Average loss: 2.8179
Iteration: 3115; Percent complete: 77.9%; Average loss: 2.9157
Iteration: 3116; Percent complete: 77.9%; Average loss: 2.9509
Iteration: 3117; Percent complete: 77.9%; Average loss: 2.8491
Iteration: 3118; Percent complete: 78.0%; Average loss: 2.6643
Iteration: 3119; Percent complete: 78.0%; Average loss: 2.7473
Iteration: 3120; Percent complete: 78.0%; Average loss: 2.7705
Iteration: 3121; Percent complete: 78.0%; Average loss: 2.7430
Iteration: 3122; Percent complete: 78.0%; Average loss: 2.7276
Iteration: 3123; Percent complete: 78.1%; Average loss: 2.9550
Iteration: 3124; Percent complete: 78.1%; Average loss: 2.9999
Iteration: 3125; Percent complete: 78.1%; Average loss: 3.0608
Iteration: 3126; Percent complete: 78.1%; Average loss: 2.5541
Iteration: 3127; Percent complete: 78.2%; Average loss: 2.6712
Iteration: 3128; Percent complete: 78.2%; Average loss: 2.9031
Iteration: 3129; Percent complete: 78.2%; Average loss: 2.6747
Iteration: 3130; Percent complete: 78.2%; Average loss: 2.9037
Iteration: 3131; Percent complete: 78.3%; Average loss: 2.8685
Iteration: 3132; Percent complete: 78.3%; Average loss: 2.8096
Iteration: 3133; Percent complete: 78.3%; Average loss: 2.7588
Iteration: 3134; Percent complete: 78.3%; Average loss: 3.0390
Iteration: 3135; Percent complete: 78.4%; Average loss: 2.9556
Iteration: 3136; Percent complete: 78.4%; Average loss: 2.9863
Iteration: 3137; Percent complete: 78.4%; Average loss: 2.8065
Iteration: 3138; Percent complete: 78.5%; Average loss: 3.1022
Iteration: 3139; Percent complete: 78.5%; Average loss: 2.8406
Iteration: 3140; Percent complete: 78.5%; Average loss: 3.0147
Iteration: 3141; Percent complete: 78.5%; Average loss: 2.6985
Iteration: 3142; Percent complete: 78.5%; Average loss: 2.8304
Iteration: 3143; Percent complete: 78.6%; Average loss: 2.9119
Iteration: 3144; Percent complete: 78.6%; Average loss: 2.8280
Iteration: 3145; Percent complete: 78.6%; Average loss: 2.8837
Iteration: 3146; Percent complete: 78.6%; Average loss: 2.6585
Iteration: 3147; Percent complete: 78.7%; Average loss: 2.9342
Iteration: 3148; Percent complete: 78.7%; Average loss: 2.7473
Iteration: 3149; Percent complete: 78.7%; Average loss: 2.7168
Iteration: 3150; Percent complete: 78.8%; Average loss: 2.8037
Iteration: 3151; Percent complete: 78.8%; Average loss: 2.7045
Iteration: 3152; Percent complete: 78.8%; Average loss: 2.8495
Iteration: 3153; Percent complete: 78.8%; Average loss: 2.8935
Iteration: 3154; Percent complete: 78.8%; Average loss: 2.8624
Iteration: 3155; Percent complete: 78.9%; Average loss: 2.9018
Iteration: 3156; Percent complete: 78.9%; Average loss: 2.9404
Iteration: 3157; Percent complete: 78.9%; Average loss: 3.0534
Iteration: 3158; Percent complete: 79.0%; Average loss: 2.6724
Iteration: 3159; Percent complete: 79.0%; Average loss: 2.6302
Iteration: 3160; Percent complete: 79.0%; Average loss: 2.9754
Iteration: 3161; Percent complete: 79.0%; Average loss: 2.7955
Iteration: 3162; Percent complete: 79.0%; Average loss: 2.8641
Iteration: 3163; Percent complete: 79.1%; Average loss: 2.9094
Iteration: 3164; Percent complete: 79.1%; Average loss: 2.8439
Iteration: 3165; Percent complete: 79.1%; Average loss: 3.0143
Iteration: 3166; Percent complete: 79.1%; Average loss: 2.9868
Iteration: 3167; Percent complete: 79.2%; Average loss: 2.7194
Iteration: 3168; Percent complete: 79.2%; Average loss: 2.7173
Iteration: 3169; Percent complete: 79.2%; Average loss: 3.0905
Iteration: 3170; Percent complete: 79.2%; Average loss: 2.6980
Iteration: 3171; Percent complete: 79.3%; Average loss: 2.8439
Iteration: 3172; Percent complete: 79.3%; Average loss: 2.8850
Iteration: 3173; Percent complete: 79.3%; Average loss: 2.5393
Iteration: 3174; Percent complete: 79.3%; Average loss: 3.0660
Iteration: 3175; Percent complete: 79.4%; Average loss: 2.6187
Iteration: 3176; Percent complete: 79.4%; Average loss: 2.9337
Iteration: 3177; Percent complete: 79.4%; Average loss: 2.7865
Iteration: 3178; Percent complete: 79.5%; Average loss: 2.8676
Iteration: 3179; Percent complete: 79.5%; Average loss: 2.6473
Iteration: 3180; Percent complete: 79.5%; Average loss: 2.7889
Iteration: 3181; Percent complete: 79.5%; Average loss: 2.8757
Iteration: 3182; Percent complete: 79.5%; Average loss: 2.6943
Iteration: 3183; Percent complete: 79.6%; Average loss: 3.0013
Iteration: 3184; Percent complete: 79.6%; Average loss: 2.8629
Iteration: 3185; Percent complete: 79.6%; Average loss: 2.7262
Iteration: 3186; Percent complete: 79.7%; Average loss: 3.1166
Iteration: 3187; Percent complete: 79.7%; Average loss: 3.0477
Iteration: 3188; Percent complete: 79.7%; Average loss: 2.7943
Iteration: 3189; Percent complete: 79.7%; Average loss: 2.8522
Iteration: 3190; Percent complete: 79.8%; Average loss: 2.7360
Iteration: 3191; Percent complete: 79.8%; Average loss: 2.8209
Iteration: 3192; Percent complete: 79.8%; Average loss: 2.6706
Iteration: 3193; Percent complete: 79.8%; Average loss: 2.9482
Iteration: 3194; Percent complete: 79.8%; Average loss: 3.0257
Iteration: 3195; Percent complete: 79.9%; Average loss: 2.6995
Iteration: 3196; Percent complete: 79.9%; Average loss: 2.9866
Iteration: 3197; Percent complete: 79.9%; Average loss: 2.9204
Iteration: 3198; Percent complete: 80.0%; Average loss: 3.0464
Iteration: 3199; Percent complete: 80.0%; Average loss: 2.5378
Iteration: 3200; Percent complete: 80.0%; Average loss: 2.9085
Iteration: 3201; Percent complete: 80.0%; Average loss: 2.8102
Iteration: 3202; Percent complete: 80.0%; Average loss: 2.7568
Iteration: 3203; Percent complete: 80.1%; Average loss: 3.0065
Iteration: 3204; Percent complete: 80.1%; Average loss: 3.0461
Iteration: 3205; Percent complete: 80.1%; Average loss: 2.7609
Iteration: 3206; Percent complete: 80.2%; Average loss: 2.4783
Iteration: 3207; Percent complete: 80.2%; Average loss: 2.8791
Iteration: 3208; Percent complete: 80.2%; Average loss: 2.4955
Iteration: 3209; Percent complete: 80.2%; Average loss: 2.7766
Iteration: 3210; Percent complete: 80.2%; Average loss: 2.6001
Iteration: 3211; Percent complete: 80.3%; Average loss: 2.7390
Iteration: 3212; Percent complete: 80.3%; Average loss: 2.8399
Iteration: 3213; Percent complete: 80.3%; Average loss: 3.0602
Iteration: 3214; Percent complete: 80.3%; Average loss: 2.8646
Iteration: 3215; Percent complete: 80.4%; Average loss: 2.8032
Iteration: 3216; Percent complete: 80.4%; Average loss: 2.8182
Iteration: 3217; Percent complete: 80.4%; Average loss: 2.9538
Iteration: 3218; Percent complete: 80.5%; Average loss: 2.7836
Iteration: 3219; Percent complete: 80.5%; Average loss: 2.7246
Iteration: 3220; Percent complete: 80.5%; Average loss: 2.8527
Iteration: 3221; Percent complete: 80.5%; Average loss: 2.9855
Iteration: 3222; Percent complete: 80.5%; Average loss: 2.7087
Iteration: 3223; Percent complete: 80.6%; Average loss: 2.7110
Iteration: 3224; Percent complete: 80.6%; Average loss: 3.1160
Iteration: 3225; Percent complete: 80.6%; Average loss: 2.6477
Iteration: 3226; Percent complete: 80.7%; Average loss: 2.8123
Iteration: 3227; Percent complete: 80.7%; Average loss: 2.6358
Iteration: 3228; Percent complete: 80.7%; Average loss: 2.7402
Iteration: 3229; Percent complete: 80.7%; Average loss: 2.7354
Iteration: 3230; Percent complete: 80.8%; Average loss: 2.6390
Iteration: 3231; Percent complete: 80.8%; Average loss: 3.0539
Iteration: 3232; Percent complete: 80.8%; Average loss: 2.8548
Iteration: 3233; Percent complete: 80.8%; Average loss: 2.7192
Iteration: 3234; Percent complete: 80.8%; Average loss: 2.7484
Iteration: 3235; Percent complete: 80.9%; Average loss: 3.0582
Iteration: 3236; Percent complete: 80.9%; Average loss: 2.9951
Iteration: 3237; Percent complete: 80.9%; Average loss: 2.9128
Iteration: 3238; Percent complete: 81.0%; Average loss: 2.6498
Iteration: 3239; Percent complete: 81.0%; Average loss: 2.9537
Iteration: 3240; Percent complete: 81.0%; Average loss: 2.7367
Iteration: 3241; Percent complete: 81.0%; Average loss: 2.5423
Iteration: 3242; Percent complete: 81.0%; Average loss: 2.9838
Iteration: 3243; Percent complete: 81.1%; Average loss: 2.9244
Iteration: 3244; Percent complete: 81.1%; Average loss: 3.1432
Iteration: 3245; Percent complete: 81.1%; Average loss: 2.7648
Iteration: 3246; Percent complete: 81.2%; Average loss: 2.7794
Iteration: 3247; Percent complete: 81.2%; Average loss: 2.7271
Iteration: 3248; Percent complete: 81.2%; Average loss: 2.6781
Iteration: 3249; Percent complete: 81.2%; Average loss: 2.8716
Iteration: 3250; Percent complete: 81.2%; Average loss: 2.9953
Iteration: 3251; Percent complete: 81.3%; Average loss: 2.9032
Iteration: 3252; Percent complete: 81.3%; Average loss: 2.6974
Iteration: 3253; Percent complete: 81.3%; Average loss: 2.8385
Iteration: 3254; Percent complete: 81.3%; Average loss: 2.6393
Iteration: 3255; Percent complete: 81.4%; Average loss: 2.8297
Iteration: 3256; Percent complete: 81.4%; Average loss: 2.7779
Iteration: 3257; Percent complete: 81.4%; Average loss: 3.0016
Iteration: 3258; Percent complete: 81.5%; Average loss: 2.8590
Iteration: 3259; Percent complete: 81.5%; Average loss: 2.9891
Iteration: 3260; Percent complete: 81.5%; Average loss: 2.7934
Iteration: 3261; Percent complete: 81.5%; Average loss: 2.7506
Iteration: 3262; Percent complete: 81.5%; Average loss: 2.8969
Iteration: 3263; Percent complete: 81.6%; Average loss: 2.9620
Iteration: 3264; Percent complete: 81.6%; Average loss: 2.9155
Iteration: 3265; Percent complete: 81.6%; Average loss: 2.8590
Iteration: 3266; Percent complete: 81.7%; Average loss: 2.7342
Iteration: 3267; Percent complete: 81.7%; Average loss: 2.4983
Iteration: 3268; Percent complete: 81.7%; Average loss: 3.1366
Iteration: 3269; Percent complete: 81.7%; Average loss: 2.7277
Iteration: 3270; Percent complete: 81.8%; Average loss: 2.7544
Iteration: 3271; Percent complete: 81.8%; Average loss: 2.8867
Iteration: 3272; Percent complete: 81.8%; Average loss: 2.9044
Iteration: 3273; Percent complete: 81.8%; Average loss: 2.8342
Iteration: 3274; Percent complete: 81.8%; Average loss: 2.9616
Iteration: 3275; Percent complete: 81.9%; Average loss: 2.9662
Iteration: 3276; Percent complete: 81.9%; Average loss: 2.6908
Iteration: 3277; Percent complete: 81.9%; Average loss: 2.7105
Iteration: 3278; Percent complete: 82.0%; Average loss: 2.9533
Iteration: 3279; Percent complete: 82.0%; Average loss: 2.7678
Iteration: 3280; Percent complete: 82.0%; Average loss: 2.7783
Iteration: 3281; Percent complete: 82.0%; Average loss: 3.0240
Iteration: 3282; Percent complete: 82.0%; Average loss: 2.8667
Iteration: 3283; Percent complete: 82.1%; Average loss: 2.4206
Iteration: 3284; Percent complete: 82.1%; Average loss: 2.5887
Iteration: 3285; Percent complete: 82.1%; Average loss: 2.7474
Iteration: 3286; Percent complete: 82.2%; Average loss: 2.6744
Iteration: 3287; Percent complete: 82.2%; Average loss: 2.7599
Iteration: 3288; Percent complete: 82.2%; Average loss: 2.7319
Iteration: 3289; Percent complete: 82.2%; Average loss: 2.8890
Iteration: 3290; Percent complete: 82.2%; Average loss: 2.7897
Iteration: 3291; Percent complete: 82.3%; Average loss: 3.0323
Iteration: 3292; Percent complete: 82.3%; Average loss: 3.0953
Iteration: 3293; Percent complete: 82.3%; Average loss: 2.8777
Iteration: 3294; Percent complete: 82.3%; Average loss: 2.7272
Iteration: 3295; Percent complete: 82.4%; Average loss: 2.8878
Iteration: 3296; Percent complete: 82.4%; Average loss: 2.8193
Iteration: 3297; Percent complete: 82.4%; Average loss: 3.1207
Iteration: 3298; Percent complete: 82.5%; Average loss: 3.1490
Iteration: 3299; Percent complete: 82.5%; Average loss: 2.8408
Iteration: 3300; Percent complete: 82.5%; Average loss: 2.9247
Iteration: 3301; Percent complete: 82.5%; Average loss: 2.8317
Iteration: 3302; Percent complete: 82.5%; Average loss: 2.9446
Iteration: 3303; Percent complete: 82.6%; Average loss: 3.0757
Iteration: 3304; Percent complete: 82.6%; Average loss: 2.7314
Iteration: 3305; Percent complete: 82.6%; Average loss: 2.6743
Iteration: 3306; Percent complete: 82.7%; Average loss: 2.6091
Iteration: 3307; Percent complete: 82.7%; Average loss: 2.6027
Iteration: 3308; Percent complete: 82.7%; Average loss: 2.8239
Iteration: 3309; Percent complete: 82.7%; Average loss: 2.7397
Iteration: 3310; Percent complete: 82.8%; Average loss: 2.5235
Iteration: 3311; Percent complete: 82.8%; Average loss: 3.0264
Iteration: 3312; Percent complete: 82.8%; Average loss: 2.6555
Iteration: 3313; Percent complete: 82.8%; Average loss: 2.5860
Iteration: 3314; Percent complete: 82.8%; Average loss: 2.5421
Iteration: 3315; Percent complete: 82.9%; Average loss: 2.9353
Iteration: 3316; Percent complete: 82.9%; Average loss: 2.8540
Iteration: 3317; Percent complete: 82.9%; Average loss: 2.7146
Iteration: 3318; Percent complete: 83.0%; Average loss: 2.7529
Iteration: 3319; Percent complete: 83.0%; Average loss: 2.6568
Iteration: 3320; Percent complete: 83.0%; Average loss: 2.9375
Iteration: 3321; Percent complete: 83.0%; Average loss: 2.5839
Iteration: 3322; Percent complete: 83.0%; Average loss: 2.7416
Iteration: 3323; Percent complete: 83.1%; Average loss: 3.0291
Iteration: 3324; Percent complete: 83.1%; Average loss: 2.7899
Iteration: 3325; Percent complete: 83.1%; Average loss: 2.8709
Iteration: 3326; Percent complete: 83.2%; Average loss: 2.8720
Iteration: 3327; Percent complete: 83.2%; Average loss: 2.7199
Iteration: 3328; Percent complete: 83.2%; Average loss: 2.7671
Iteration: 3329; Percent complete: 83.2%; Average loss: 2.9566
Iteration: 3330; Percent complete: 83.2%; Average loss: 2.6549
Iteration: 3331; Percent complete: 83.3%; Average loss: 2.5972
Iteration: 3332; Percent complete: 83.3%; Average loss: 2.7617
Iteration: 3333; Percent complete: 83.3%; Average loss: 2.6858
Iteration: 3334; Percent complete: 83.4%; Average loss: 2.8418
Iteration: 3335; Percent complete: 83.4%; Average loss: 2.8228
Iteration: 3336; Percent complete: 83.4%; Average loss: 2.8591
Iteration: 3337; Percent complete: 83.4%; Average loss: 2.6260
Iteration: 3338; Percent complete: 83.5%; Average loss: 2.9087
Iteration: 3339; Percent complete: 83.5%; Average loss: 2.9432
Iteration: 3340; Percent complete: 83.5%; Average loss: 2.7240
Iteration: 3341; Percent complete: 83.5%; Average loss: 2.8710
Iteration: 3342; Percent complete: 83.5%; Average loss: 2.7159
Iteration: 3343; Percent complete: 83.6%; Average loss: 2.8511
Iteration: 3344; Percent complete: 83.6%; Average loss: 2.7811
Iteration: 3345; Percent complete: 83.6%; Average loss: 2.8811
Iteration: 3346; Percent complete: 83.7%; Average loss: 2.7097
Iteration: 3347; Percent complete: 83.7%; Average loss: 2.7894
Iteration: 3348; Percent complete: 83.7%; Average loss: 2.7067
Iteration: 3349; Percent complete: 83.7%; Average loss: 2.5929
Iteration: 3350; Percent complete: 83.8%; Average loss: 2.8412
Iteration: 3351; Percent complete: 83.8%; Average loss: 2.9509
Iteration: 3352; Percent complete: 83.8%; Average loss: 2.6684
Iteration: 3353; Percent complete: 83.8%; Average loss: 2.6747
Iteration: 3354; Percent complete: 83.9%; Average loss: 2.6587
Iteration: 3355; Percent complete: 83.9%; Average loss: 2.8418
Iteration: 3356; Percent complete: 83.9%; Average loss: 2.8670
Iteration: 3357; Percent complete: 83.9%; Average loss: 2.9058
Iteration: 3358; Percent complete: 84.0%; Average loss: 2.7535
Iteration: 3359; Percent complete: 84.0%; Average loss: 2.7278
Iteration: 3360; Percent complete: 84.0%; Average loss: 2.8658
Iteration: 3361; Percent complete: 84.0%; Average loss: 2.6887
Iteration: 3362; Percent complete: 84.0%; Average loss: 2.6770
Iteration: 3363; Percent complete: 84.1%; Average loss: 3.0016
Iteration: 3364; Percent complete: 84.1%; Average loss: 2.9456
Iteration: 3365; Percent complete: 84.1%; Average loss: 2.5117
Iteration: 3366; Percent complete: 84.2%; Average loss: 2.8248
Iteration: 3367; Percent complete: 84.2%; Average loss: 2.6991
Iteration: 3368; Percent complete: 84.2%; Average loss: 2.9277
Iteration: 3369; Percent complete: 84.2%; Average loss: 2.9189
Iteration: 3370; Percent complete: 84.2%; Average loss: 2.7498
Iteration: 3371; Percent complete: 84.3%; Average loss: 2.6708
Iteration: 3372; Percent complete: 84.3%; Average loss: 3.0526
Iteration: 3373; Percent complete: 84.3%; Average loss: 2.7482
Iteration: 3374; Percent complete: 84.4%; Average loss: 2.6814
Iteration: 3375; Percent complete: 84.4%; Average loss: 2.7371
Iteration: 3376; Percent complete: 84.4%; Average loss: 2.8510
Iteration: 3377; Percent complete: 84.4%; Average loss: 2.7440
Iteration: 3378; Percent complete: 84.5%; Average loss: 2.7062
Iteration: 3379; Percent complete: 84.5%; Average loss: 2.6337
Iteration: 3380; Percent complete: 84.5%; Average loss: 2.6725
Iteration: 3381; Percent complete: 84.5%; Average loss: 2.7420
Iteration: 3382; Percent complete: 84.5%; Average loss: 2.7800
Iteration: 3383; Percent complete: 84.6%; Average loss: 2.8117
Iteration: 3384; Percent complete: 84.6%; Average loss: 2.7297
Iteration: 3385; Percent complete: 84.6%; Average loss: 2.4936
Iteration: 3386; Percent complete: 84.7%; Average loss: 2.8700
Iteration: 3387; Percent complete: 84.7%; Average loss: 2.4834
Iteration: 3388; Percent complete: 84.7%; Average loss: 2.8538
Iteration: 3389; Percent complete: 84.7%; Average loss: 3.0764
Iteration: 3390; Percent complete: 84.8%; Average loss: 2.7254
Iteration: 3391; Percent complete: 84.8%; Average loss: 2.8652
Iteration: 3392; Percent complete: 84.8%; Average loss: 2.8805
Iteration: 3393; Percent complete: 84.8%; Average loss: 2.6279
Iteration: 3394; Percent complete: 84.9%; Average loss: 2.6172
Iteration: 3395; Percent complete: 84.9%; Average loss: 2.8391
Iteration: 3396; Percent complete: 84.9%; Average loss: 2.8813
Iteration: 3397; Percent complete: 84.9%; Average loss: 2.9044
Iteration: 3398; Percent complete: 85.0%; Average loss: 2.8642
Iteration: 3399; Percent complete: 85.0%; Average loss: 2.7775
Iteration: 3400; Percent complete: 85.0%; Average loss: 2.4265
Iteration: 3401; Percent complete: 85.0%; Average loss: 2.9858
Iteration: 3402; Percent complete: 85.0%; Average loss: 2.6082
Iteration: 3403; Percent complete: 85.1%; Average loss: 2.7344
Iteration: 3404; Percent complete: 85.1%; Average loss: 2.7256
Iteration: 3405; Percent complete: 85.1%; Average loss: 2.7152
Iteration: 3406; Percent complete: 85.2%; Average loss: 2.8109
Iteration: 3407; Percent complete: 85.2%; Average loss: 2.7704
Iteration: 3408; Percent complete: 85.2%; Average loss: 3.0013
Iteration: 3409; Percent complete: 85.2%; Average loss: 2.9458
Iteration: 3410; Percent complete: 85.2%; Average loss: 2.7367
Iteration: 3411; Percent complete: 85.3%; Average loss: 2.5098
Iteration: 3412; Percent complete: 85.3%; Average loss: 2.8251
Iteration: 3413; Percent complete: 85.3%; Average loss: 2.7923
Iteration: 3414; Percent complete: 85.4%; Average loss: 2.8584
Iteration: 3415; Percent complete: 85.4%; Average loss: 2.7574
Iteration: 3416; Percent complete: 85.4%; Average loss: 2.8313
Iteration: 3417; Percent complete: 85.4%; Average loss: 2.8724
Iteration: 3418; Percent complete: 85.5%; Average loss: 2.9367
Iteration: 3419; Percent complete: 85.5%; Average loss: 2.7616
Iteration: 3420; Percent complete: 85.5%; Average loss: 2.6613
Iteration: 3421; Percent complete: 85.5%; Average loss: 2.6575
Iteration: 3422; Percent complete: 85.5%; Average loss: 2.8365
Iteration: 3423; Percent complete: 85.6%; Average loss: 2.9774
Iteration: 3424; Percent complete: 85.6%; Average loss: 2.7625
Iteration: 3425; Percent complete: 85.6%; Average loss: 2.6489
Iteration: 3426; Percent complete: 85.7%; Average loss: 2.6609
Iteration: 3427; Percent complete: 85.7%; Average loss: 2.5135
Iteration: 3428; Percent complete: 85.7%; Average loss: 2.6420
Iteration: 3429; Percent complete: 85.7%; Average loss: 2.6579
Iteration: 3430; Percent complete: 85.8%; Average loss: 2.8539
Iteration: 3431; Percent complete: 85.8%; Average loss: 2.5174
Iteration: 3432; Percent complete: 85.8%; Average loss: 2.7501
Iteration: 3433; Percent complete: 85.8%; Average loss: 2.9384
Iteration: 3434; Percent complete: 85.9%; Average loss: 2.9910
Iteration: 3435; Percent complete: 85.9%; Average loss: 2.6698
Iteration: 3436; Percent complete: 85.9%; Average loss: 2.6245
Iteration: 3437; Percent complete: 85.9%; Average loss: 2.8270
Iteration: 3438; Percent complete: 86.0%; Average loss: 2.8099
Iteration: 3439; Percent complete: 86.0%; Average loss: 2.9314
Iteration: 3440; Percent complete: 86.0%; Average loss: 2.6509
Iteration: 3441; Percent complete: 86.0%; Average loss: 2.5749
Iteration: 3442; Percent complete: 86.1%; Average loss: 2.7451
Iteration: 3443; Percent complete: 86.1%; Average loss: 2.9653
Iteration: 3444; Percent complete: 86.1%; Average loss: 2.8928
Iteration: 3445; Percent complete: 86.1%; Average loss: 2.7608
Iteration: 3446; Percent complete: 86.2%; Average loss: 2.8794
Iteration: 3447; Percent complete: 86.2%; Average loss: 2.7256
Iteration: 3448; Percent complete: 86.2%; Average loss: 2.9894
Iteration: 3449; Percent complete: 86.2%; Average loss: 2.9677
Iteration: 3450; Percent complete: 86.2%; Average loss: 2.6806
Iteration: 3451; Percent complete: 86.3%; Average loss: 2.8963
Iteration: 3452; Percent complete: 86.3%; Average loss: 2.7197
Iteration: 3453; Percent complete: 86.3%; Average loss: 2.8464
Iteration: 3454; Percent complete: 86.4%; Average loss: 2.8628
Iteration: 3455; Percent complete: 86.4%; Average loss: 2.7329
Iteration: 3456; Percent complete: 86.4%; Average loss: 2.6890
Iteration: 3457; Percent complete: 86.4%; Average loss: 2.9136
Iteration: 3458; Percent complete: 86.5%; Average loss: 2.6619
Iteration: 3459; Percent complete: 86.5%; Average loss: 2.7192
Iteration: 3460; Percent complete: 86.5%; Average loss: 2.6443
Iteration: 3461; Percent complete: 86.5%; Average loss: 2.7005
Iteration: 3462; Percent complete: 86.6%; Average loss: 2.7267
Iteration: 3463; Percent complete: 86.6%; Average loss: 3.0087
Iteration: 3464; Percent complete: 86.6%; Average loss: 2.7936
Iteration: 3465; Percent complete: 86.6%; Average loss: 2.7390
Iteration: 3466; Percent complete: 86.7%; Average loss: 2.6207
Iteration: 3467; Percent complete: 86.7%; Average loss: 2.5004
Iteration: 3468; Percent complete: 86.7%; Average loss: 2.8131
Iteration: 3469; Percent complete: 86.7%; Average loss: 2.8574
Iteration: 3470; Percent complete: 86.8%; Average loss: 2.9339
Iteration: 3471; Percent complete: 86.8%; Average loss: 2.7134
Iteration: 3472; Percent complete: 86.8%; Average loss: 2.5678
Iteration: 3473; Percent complete: 86.8%; Average loss: 2.7276
Iteration: 3474; Percent complete: 86.9%; Average loss: 2.6348
Iteration: 3475; Percent complete: 86.9%; Average loss: 2.8819
Iteration: 3476; Percent complete: 86.9%; Average loss: 2.8928
Iteration: 3477; Percent complete: 86.9%; Average loss: 2.9133
Iteration: 3478; Percent complete: 87.0%; Average loss: 2.4824
Iteration: 3479; Percent complete: 87.0%; Average loss: 2.7104
Iteration: 3480; Percent complete: 87.0%; Average loss: 2.9585
Iteration: 3481; Percent complete: 87.0%; Average loss: 2.8938
Iteration: 3482; Percent complete: 87.1%; Average loss: 2.4942
Iteration: 3483; Percent complete: 87.1%; Average loss: 2.7205
Iteration: 3484; Percent complete: 87.1%; Average loss: 2.6165
Iteration: 3485; Percent complete: 87.1%; Average loss: 2.8302
Iteration: 3486; Percent complete: 87.2%; Average loss: 2.7662
Iteration: 3487; Percent complete: 87.2%; Average loss: 2.9824
Iteration: 3488; Percent complete: 87.2%; Average loss: 2.8298
Iteration: 3489; Percent complete: 87.2%; Average loss: 2.6927
Iteration: 3490; Percent complete: 87.2%; Average loss: 2.6925
Iteration: 3491; Percent complete: 87.3%; Average loss: 2.9118
Iteration: 3492; Percent complete: 87.3%; Average loss: 2.6680
Iteration: 3493; Percent complete: 87.3%; Average loss: 2.6561
Iteration: 3494; Percent complete: 87.4%; Average loss: 2.7721
Iteration: 3495; Percent complete: 87.4%; Average loss: 2.6832
Iteration: 3496; Percent complete: 87.4%; Average loss: 2.6893
Iteration: 3497; Percent complete: 87.4%; Average loss: 2.8766
Iteration: 3498; Percent complete: 87.5%; Average loss: 2.5967
Iteration: 3499; Percent complete: 87.5%; Average loss: 2.7473
Iteration: 3500; Percent complete: 87.5%; Average loss: 2.8906
Iteration: 3501; Percent complete: 87.5%; Average loss: 2.5412
Iteration: 3502; Percent complete: 87.5%; Average loss: 2.7464
Iteration: 3503; Percent complete: 87.6%; Average loss: 2.6508
Iteration: 3504; Percent complete: 87.6%; Average loss: 2.5722
Iteration: 3505; Percent complete: 87.6%; Average loss: 2.8391
Iteration: 3506; Percent complete: 87.6%; Average loss: 2.6499
Iteration: 3507; Percent complete: 87.7%; Average loss: 2.7357
Iteration: 3508; Percent complete: 87.7%; Average loss: 2.6871
Iteration: 3509; Percent complete: 87.7%; Average loss: 2.5235
Iteration: 3510; Percent complete: 87.8%; Average loss: 2.7598
Iteration: 3511; Percent complete: 87.8%; Average loss: 2.7950
Iteration: 3512; Percent complete: 87.8%; Average loss: 2.4731
Iteration: 3513; Percent complete: 87.8%; Average loss: 2.7937
Iteration: 3514; Percent complete: 87.8%; Average loss: 2.7844
Iteration: 3515; Percent complete: 87.9%; Average loss: 2.6537
Iteration: 3516; Percent complete: 87.9%; Average loss: 2.6735
Iteration: 3517; Percent complete: 87.9%; Average loss: 2.7808
Iteration: 3518; Percent complete: 87.9%; Average loss: 3.0576
Iteration: 3519; Percent complete: 88.0%; Average loss: 2.7402
Iteration: 3520; Percent complete: 88.0%; Average loss: 2.7610
Iteration: 3521; Percent complete: 88.0%; Average loss: 2.6101
Iteration: 3522; Percent complete: 88.0%; Average loss: 2.6009
Iteration: 3523; Percent complete: 88.1%; Average loss: 2.6410
Iteration: 3524; Percent complete: 88.1%; Average loss: 2.8200
Iteration: 3525; Percent complete: 88.1%; Average loss: 2.4989
Iteration: 3526; Percent complete: 88.1%; Average loss: 2.7217
Iteration: 3527; Percent complete: 88.2%; Average loss: 2.6282
Iteration: 3528; Percent complete: 88.2%; Average loss: 2.7499
Iteration: 3529; Percent complete: 88.2%; Average loss: 2.5551
Iteration: 3530; Percent complete: 88.2%; Average loss: 2.8411
Iteration: 3531; Percent complete: 88.3%; Average loss: 2.6522
Iteration: 3532; Percent complete: 88.3%; Average loss: 2.8053
Iteration: 3533; Percent complete: 88.3%; Average loss: 2.7293
Iteration: 3534; Percent complete: 88.3%; Average loss: 2.7515
Iteration: 3535; Percent complete: 88.4%; Average loss: 2.5897
Iteration: 3536; Percent complete: 88.4%; Average loss: 2.6916
Iteration: 3537; Percent complete: 88.4%; Average loss: 2.5947
Iteration: 3538; Percent complete: 88.4%; Average loss: 2.7368
Iteration: 3539; Percent complete: 88.5%; Average loss: 2.5869
Iteration: 3540; Percent complete: 88.5%; Average loss: 2.6993
Iteration: 3541; Percent complete: 88.5%; Average loss: 2.6683
Iteration: 3542; Percent complete: 88.5%; Average loss: 2.8862
Iteration: 3543; Percent complete: 88.6%; Average loss: 2.6386
Iteration: 3544; Percent complete: 88.6%; Average loss: 2.7141
Iteration: 3545; Percent complete: 88.6%; Average loss: 2.7899
Iteration: 3546; Percent complete: 88.6%; Average loss: 2.5029
Iteration: 3547; Percent complete: 88.7%; Average loss: 2.7711
Iteration: 3548; Percent complete: 88.7%; Average loss: 2.7013
Iteration: 3549; Percent complete: 88.7%; Average loss: 2.9328
Iteration: 3550; Percent complete: 88.8%; Average loss: 2.7211
Iteration: 3551; Percent complete: 88.8%; Average loss: 2.7420
Iteration: 3552; Percent complete: 88.8%; Average loss: 2.5704
Iteration: 3553; Percent complete: 88.8%; Average loss: 2.6984
Iteration: 3554; Percent complete: 88.8%; Average loss: 2.6532
Iteration: 3555; Percent complete: 88.9%; Average loss: 2.7569
Iteration: 3556; Percent complete: 88.9%; Average loss: 2.6562
Iteration: 3557; Percent complete: 88.9%; Average loss: 2.9728
Iteration: 3558; Percent complete: 88.9%; Average loss: 2.9622
Iteration: 3559; Percent complete: 89.0%; Average loss: 2.9101
Iteration: 3560; Percent complete: 89.0%; Average loss: 2.8860
Iteration: 3561; Percent complete: 89.0%; Average loss: 2.7694
Iteration: 3562; Percent complete: 89.0%; Average loss: 2.7809
Iteration: 3563; Percent complete: 89.1%; Average loss: 2.7795
Iteration: 3564; Percent complete: 89.1%; Average loss: 2.6589
Iteration: 3565; Percent complete: 89.1%; Average loss: 2.7409
Iteration: 3566; Percent complete: 89.1%; Average loss: 2.7473
Iteration: 3567; Percent complete: 89.2%; Average loss: 2.7135
Iteration: 3568; Percent complete: 89.2%; Average loss: 2.6145
Iteration: 3569; Percent complete: 89.2%; Average loss: 2.9850
Iteration: 3570; Percent complete: 89.2%; Average loss: 2.6410
Iteration: 3571; Percent complete: 89.3%; Average loss: 2.7087
Iteration: 3572; Percent complete: 89.3%; Average loss: 2.7743
Iteration: 3573; Percent complete: 89.3%; Average loss: 2.6860
Iteration: 3574; Percent complete: 89.3%; Average loss: 2.6862
Iteration: 3575; Percent complete: 89.4%; Average loss: 2.8821
Iteration: 3576; Percent complete: 89.4%; Average loss: 2.6124
Iteration: 3577; Percent complete: 89.4%; Average loss: 2.5345
Iteration: 3578; Percent complete: 89.5%; Average loss: 2.6116
Iteration: 3579; Percent complete: 89.5%; Average loss: 2.6823
Iteration: 3580; Percent complete: 89.5%; Average loss: 2.4180
Iteration: 3581; Percent complete: 89.5%; Average loss: 2.4850
Iteration: 3582; Percent complete: 89.5%; Average loss: 2.6987
Iteration: 3583; Percent complete: 89.6%; Average loss: 2.9682
Iteration: 3584; Percent complete: 89.6%; Average loss: 2.6675
Iteration: 3585; Percent complete: 89.6%; Average loss: 2.7295
Iteration: 3586; Percent complete: 89.6%; Average loss: 2.6765
Iteration: 3587; Percent complete: 89.7%; Average loss: 2.9168
Iteration: 3588; Percent complete: 89.7%; Average loss: 2.6278
Iteration: 3589; Percent complete: 89.7%; Average loss: 2.6914
Iteration: 3590; Percent complete: 89.8%; Average loss: 2.8912
Iteration: 3591; Percent complete: 89.8%; Average loss: 2.5523
Iteration: 3592; Percent complete: 89.8%; Average loss: 2.4363
Iteration: 3593; Percent complete: 89.8%; Average loss: 2.6741
Iteration: 3594; Percent complete: 89.8%; Average loss: 2.7257
Iteration: 3595; Percent complete: 89.9%; Average loss: 2.6902
Iteration: 3596; Percent complete: 89.9%; Average loss: 2.6120
Iteration: 3597; Percent complete: 89.9%; Average loss: 2.8970
Iteration: 3598; Percent complete: 90.0%; Average loss: 2.4757
Iteration: 3599; Percent complete: 90.0%; Average loss: 2.5976
Iteration: 3600; Percent complete: 90.0%; Average loss: 2.6893
Iteration: 3601; Percent complete: 90.0%; Average loss: 2.6901
Iteration: 3602; Percent complete: 90.0%; Average loss: 2.7066
Iteration: 3603; Percent complete: 90.1%; Average loss: 2.7514
Iteration: 3604; Percent complete: 90.1%; Average loss: 2.7218
Iteration: 3605; Percent complete: 90.1%; Average loss: 2.7965
Iteration: 3606; Percent complete: 90.1%; Average loss: 2.3842
Iteration: 3607; Percent complete: 90.2%; Average loss: 2.6543
Iteration: 3608; Percent complete: 90.2%; Average loss: 2.6635
Iteration: 3609; Percent complete: 90.2%; Average loss: 2.8082
Iteration: 3610; Percent complete: 90.2%; Average loss: 2.6142
Iteration: 3611; Percent complete: 90.3%; Average loss: 2.6731
Iteration: 3612; Percent complete: 90.3%; Average loss: 2.8559
Iteration: 3613; Percent complete: 90.3%; Average loss: 2.6766
Iteration: 3614; Percent complete: 90.3%; Average loss: 2.8854
Iteration: 3615; Percent complete: 90.4%; Average loss: 2.7290
Iteration: 3616; Percent complete: 90.4%; Average loss: 2.6954
Iteration: 3617; Percent complete: 90.4%; Average loss: 2.6327
Iteration: 3618; Percent complete: 90.5%; Average loss: 2.5334
Iteration: 3619; Percent complete: 90.5%; Average loss: 2.9488
Iteration: 3620; Percent complete: 90.5%; Average loss: 2.7540
Iteration: 3621; Percent complete: 90.5%; Average loss: 2.6709
Iteration: 3622; Percent complete: 90.5%; Average loss: 2.6482
Iteration: 3623; Percent complete: 90.6%; Average loss: 2.5687
Iteration: 3624; Percent complete: 90.6%; Average loss: 2.8184
Iteration: 3625; Percent complete: 90.6%; Average loss: 2.8663
Iteration: 3626; Percent complete: 90.6%; Average loss: 2.7451
Iteration: 3627; Percent complete: 90.7%; Average loss: 2.7402
Iteration: 3628; Percent complete: 90.7%; Average loss: 2.8694
Iteration: 3629; Percent complete: 90.7%; Average loss: 2.5437
Iteration: 3630; Percent complete: 90.8%; Average loss: 2.6052
Iteration: 3631; Percent complete: 90.8%; Average loss: 2.7026
Iteration: 3632; Percent complete: 90.8%; Average loss: 2.6275
Iteration: 3633; Percent complete: 90.8%; Average loss: 2.6166
Iteration: 3634; Percent complete: 90.8%; Average loss: 2.5653
Iteration: 3635; Percent complete: 90.9%; Average loss: 2.9091
Iteration: 3636; Percent complete: 90.9%; Average loss: 2.7571
Iteration: 3637; Percent complete: 90.9%; Average loss: 2.5667
Iteration: 3638; Percent complete: 91.0%; Average loss: 2.6501
Iteration: 3639; Percent complete: 91.0%; Average loss: 2.8794
Iteration: 3640; Percent complete: 91.0%; Average loss: 2.9100
Iteration: 3641; Percent complete: 91.0%; Average loss: 2.5725
Iteration: 3642; Percent complete: 91.0%; Average loss: 2.6162
Iteration: 3643; Percent complete: 91.1%; Average loss: 2.7682
Iteration: 3644; Percent complete: 91.1%; Average loss: 2.7770
Iteration: 3645; Percent complete: 91.1%; Average loss: 3.0201
Iteration: 3646; Percent complete: 91.1%; Average loss: 2.7481
Iteration: 3647; Percent complete: 91.2%; Average loss: 2.5906
Iteration: 3648; Percent complete: 91.2%; Average loss: 2.3802
Iteration: 3649; Percent complete: 91.2%; Average loss: 2.8526
Iteration: 3650; Percent complete: 91.2%; Average loss: 2.7903
Iteration: 3651; Percent complete: 91.3%; Average loss: 2.7708
Iteration: 3652; Percent complete: 91.3%; Average loss: 2.8952
Iteration: 3653; Percent complete: 91.3%; Average loss: 2.8230
Iteration: 3654; Percent complete: 91.3%; Average loss: 2.6665
Iteration: 3655; Percent complete: 91.4%; Average loss: 2.7681
Iteration: 3656; Percent complete: 91.4%; Average loss: 2.6748
Iteration: 3657; Percent complete: 91.4%; Average loss: 2.6649
Iteration: 3658; Percent complete: 91.5%; Average loss: 2.5703
Iteration: 3659; Percent complete: 91.5%; Average loss: 2.5642
Iteration: 3660; Percent complete: 91.5%; Average loss: 2.6657
Iteration: 3661; Percent complete: 91.5%; Average loss: 2.7418
Iteration: 3662; Percent complete: 91.5%; Average loss: 2.7777
Iteration: 3663; Percent complete: 91.6%; Average loss: 2.7045
Iteration: 3664; Percent complete: 91.6%; Average loss: 2.9317
Iteration: 3665; Percent complete: 91.6%; Average loss: 2.7881
Iteration: 3666; Percent complete: 91.6%; Average loss: 2.8499
Iteration: 3667; Percent complete: 91.7%; Average loss: 2.8790
Iteration: 3668; Percent complete: 91.7%; Average loss: 2.7564
Iteration: 3669; Percent complete: 91.7%; Average loss: 2.8827
Iteration: 3670; Percent complete: 91.8%; Average loss: 2.6498
Iteration: 3671; Percent complete: 91.8%; Average loss: 2.6329
Iteration: 3672; Percent complete: 91.8%; Average loss: 2.5931
Iteration: 3673; Percent complete: 91.8%; Average loss: 2.9471
Iteration: 3674; Percent complete: 91.8%; Average loss: 2.4731
Iteration: 3675; Percent complete: 91.9%; Average loss: 2.7990
Iteration: 3676; Percent complete: 91.9%; Average loss: 2.6261
Iteration: 3677; Percent complete: 91.9%; Average loss: 2.3988
Iteration: 3678; Percent complete: 92.0%; Average loss: 2.6089
Iteration: 3679; Percent complete: 92.0%; Average loss: 2.5930
Iteration: 3680; Percent complete: 92.0%; Average loss: 2.6752
Iteration: 3681; Percent complete: 92.0%; Average loss: 2.7578
Iteration: 3682; Percent complete: 92.0%; Average loss: 2.6721
Iteration: 3683; Percent complete: 92.1%; Average loss: 2.6864
Iteration: 3684; Percent complete: 92.1%; Average loss: 2.8032
Iteration: 3685; Percent complete: 92.1%; Average loss: 3.0292
Iteration: 3686; Percent complete: 92.2%; Average loss: 2.5995
Iteration: 3687; Percent complete: 92.2%; Average loss: 2.8337
Iteration: 3688; Percent complete: 92.2%; Average loss: 2.8318
Iteration: 3689; Percent complete: 92.2%; Average loss: 2.8167
Iteration: 3690; Percent complete: 92.2%; Average loss: 2.7070
Iteration: 3691; Percent complete: 92.3%; Average loss: 2.7699
Iteration: 3692; Percent complete: 92.3%; Average loss: 2.4563
Iteration: 3693; Percent complete: 92.3%; Average loss: 2.7950
Iteration: 3694; Percent complete: 92.3%; Average loss: 2.4459
Iteration: 3695; Percent complete: 92.4%; Average loss: 2.7062
Iteration: 3696; Percent complete: 92.4%; Average loss: 2.6604
Iteration: 3697; Percent complete: 92.4%; Average loss: 2.6035
Iteration: 3698; Percent complete: 92.5%; Average loss: 2.5846
Iteration: 3699; Percent complete: 92.5%; Average loss: 2.9317
Iteration: 3700; Percent complete: 92.5%; Average loss: 2.4883
Iteration: 3701; Percent complete: 92.5%; Average loss: 2.6868
Iteration: 3702; Percent complete: 92.5%; Average loss: 2.6464
Iteration: 3703; Percent complete: 92.6%; Average loss: 2.7093
Iteration: 3704; Percent complete: 92.6%; Average loss: 2.7912
Iteration: 3705; Percent complete: 92.6%; Average loss: 2.7512
Iteration: 3706; Percent complete: 92.7%; Average loss: 2.6123
Iteration: 3707; Percent complete: 92.7%; Average loss: 2.6892
Iteration: 3708; Percent complete: 92.7%; Average loss: 2.4445
Iteration: 3709; Percent complete: 92.7%; Average loss: 2.7458
Iteration: 3710; Percent complete: 92.8%; Average loss: 2.5257
Iteration: 3711; Percent complete: 92.8%; Average loss: 2.3926
Iteration: 3712; Percent complete: 92.8%; Average loss: 2.8170
Iteration: 3713; Percent complete: 92.8%; Average loss: 2.7948
Iteration: 3714; Percent complete: 92.8%; Average loss: 2.6361
Iteration: 3715; Percent complete: 92.9%; Average loss: 2.7091
Iteration: 3716; Percent complete: 92.9%; Average loss: 2.8230
Iteration: 3717; Percent complete: 92.9%; Average loss: 2.5294
Iteration: 3718; Percent complete: 93.0%; Average loss: 2.6854
Iteration: 3719; Percent complete: 93.0%; Average loss: 2.7498
Iteration: 3720; Percent complete: 93.0%; Average loss: 2.6728
Iteration: 3721; Percent complete: 93.0%; Average loss: 2.7686
Iteration: 3722; Percent complete: 93.0%; Average loss: 2.6759
Iteration: 3723; Percent complete: 93.1%; Average loss: 2.6673
Iteration: 3724; Percent complete: 93.1%; Average loss: 2.8904
Iteration: 3725; Percent complete: 93.1%; Average loss: 2.5035
Iteration: 3726; Percent complete: 93.2%; Average loss: 2.4082
Iteration: 3727; Percent complete: 93.2%; Average loss: 2.6972
Iteration: 3728; Percent complete: 93.2%; Average loss: 2.7041
Iteration: 3729; Percent complete: 93.2%; Average loss: 2.6620
Iteration: 3730; Percent complete: 93.2%; Average loss: 2.7041
Iteration: 3731; Percent complete: 93.3%; Average loss: 2.5819
Iteration: 3732; Percent complete: 93.3%; Average loss: 2.7687
Iteration: 3733; Percent complete: 93.3%; Average loss: 2.7559
Iteration: 3734; Percent complete: 93.3%; Average loss: 2.8003
Iteration: 3735; Percent complete: 93.4%; Average loss: 2.9992
Iteration: 3736; Percent complete: 93.4%; Average loss: 2.7581
Iteration: 3737; Percent complete: 93.4%; Average loss: 2.8514
Iteration: 3738; Percent complete: 93.5%; Average loss: 2.6934
Iteration: 3739; Percent complete: 93.5%; Average loss: 2.8100
Iteration: 3740; Percent complete: 93.5%; Average loss: 2.7526
Iteration: 3741; Percent complete: 93.5%; Average loss: 2.5773
Iteration: 3742; Percent complete: 93.5%; Average loss: 2.8110
Iteration: 3743; Percent complete: 93.6%; Average loss: 2.5757
Iteration: 3744; Percent complete: 93.6%; Average loss: 2.8500
Iteration: 3745; Percent complete: 93.6%; Average loss: 2.2860
Iteration: 3746; Percent complete: 93.7%; Average loss: 2.3219
Iteration: 3747; Percent complete: 93.7%; Average loss: 2.6171
Iteration: 3748; Percent complete: 93.7%; Average loss: 2.8238
Iteration: 3749; Percent complete: 93.7%; Average loss: 2.8108
Iteration: 3750; Percent complete: 93.8%; Average loss: 2.4562
Iteration: 3751; Percent complete: 93.8%; Average loss: 2.7079
Iteration: 3752; Percent complete: 93.8%; Average loss: 2.8380
Iteration: 3753; Percent complete: 93.8%; Average loss: 2.7944
Iteration: 3754; Percent complete: 93.8%; Average loss: 2.7780
Iteration: 3755; Percent complete: 93.9%; Average loss: 2.7921
Iteration: 3756; Percent complete: 93.9%; Average loss: 2.8326
Iteration: 3757; Percent complete: 93.9%; Average loss: 2.7472
Iteration: 3758; Percent complete: 94.0%; Average loss: 2.6823
Iteration: 3759; Percent complete: 94.0%; Average loss: 2.7915
Iteration: 3760; Percent complete: 94.0%; Average loss: 2.6679
Iteration: 3761; Percent complete: 94.0%; Average loss: 2.8662
Iteration: 3762; Percent complete: 94.0%; Average loss: 2.3749
Iteration: 3763; Percent complete: 94.1%; Average loss: 2.5393
Iteration: 3764; Percent complete: 94.1%; Average loss: 2.5800
Iteration: 3765; Percent complete: 94.1%; Average loss: 2.7516
Iteration: 3766; Percent complete: 94.2%; Average loss: 2.7368
Iteration: 3767; Percent complete: 94.2%; Average loss: 2.8884
Iteration: 3768; Percent complete: 94.2%; Average loss: 2.6849
Iteration: 3769; Percent complete: 94.2%; Average loss: 2.5795
Iteration: 3770; Percent complete: 94.2%; Average loss: 2.6022
Iteration: 3771; Percent complete: 94.3%; Average loss: 2.6807
Iteration: 3772; Percent complete: 94.3%; Average loss: 2.7493
Iteration: 3773; Percent complete: 94.3%; Average loss: 2.7163
Iteration: 3774; Percent complete: 94.3%; Average loss: 2.7237
Iteration: 3775; Percent complete: 94.4%; Average loss: 2.7343
Iteration: 3776; Percent complete: 94.4%; Average loss: 2.5645
Iteration: 3777; Percent complete: 94.4%; Average loss: 2.6346
Iteration: 3778; Percent complete: 94.5%; Average loss: 2.6738
Iteration: 3779; Percent complete: 94.5%; Average loss: 2.7188
Iteration: 3780; Percent complete: 94.5%; Average loss: 2.5662
Iteration: 3781; Percent complete: 94.5%; Average loss: 3.0738
Iteration: 3782; Percent complete: 94.5%; Average loss: 2.7980
Iteration: 3783; Percent complete: 94.6%; Average loss: 2.4385
Iteration: 3784; Percent complete: 94.6%; Average loss: 2.7370
Iteration: 3785; Percent complete: 94.6%; Average loss: 2.6562
Iteration: 3786; Percent complete: 94.7%; Average loss: 2.6734
Iteration: 3787; Percent complete: 94.7%; Average loss: 2.6245
Iteration: 3788; Percent complete: 94.7%; Average loss: 2.6693
Iteration: 3789; Percent complete: 94.7%; Average loss: 2.7944
Iteration: 3790; Percent complete: 94.8%; Average loss: 2.7089
Iteration: 3791; Percent complete: 94.8%; Average loss: 2.4640
Iteration: 3792; Percent complete: 94.8%; Average loss: 2.5614
Iteration: 3793; Percent complete: 94.8%; Average loss: 2.6428
Iteration: 3794; Percent complete: 94.8%; Average loss: 2.8420
Iteration: 3795; Percent complete: 94.9%; Average loss: 2.5034
Iteration: 3796; Percent complete: 94.9%; Average loss: 2.8100
Iteration: 3797; Percent complete: 94.9%; Average loss: 2.8232
Iteration: 3798; Percent complete: 95.0%; Average loss: 2.9494
Iteration: 3799; Percent complete: 95.0%; Average loss: 2.7076
Iteration: 3800; Percent complete: 95.0%; Average loss: 2.6249
Iteration: 3801; Percent complete: 95.0%; Average loss: 2.7706
Iteration: 3802; Percent complete: 95.0%; Average loss: 2.5015
Iteration: 3803; Percent complete: 95.1%; Average loss: 2.7087
Iteration: 3804; Percent complete: 95.1%; Average loss: 2.7052
Iteration: 3805; Percent complete: 95.1%; Average loss: 2.5570
Iteration: 3806; Percent complete: 95.2%; Average loss: 2.5367
Iteration: 3807; Percent complete: 95.2%; Average loss: 2.7054
Iteration: 3808; Percent complete: 95.2%; Average loss: 2.5679
Iteration: 3809; Percent complete: 95.2%; Average loss: 2.7968
Iteration: 3810; Percent complete: 95.2%; Average loss: 2.7841
Iteration: 3811; Percent complete: 95.3%; Average loss: 2.5134
Iteration: 3812; Percent complete: 95.3%; Average loss: 2.5460
Iteration: 3813; Percent complete: 95.3%; Average loss: 2.7319
Iteration: 3814; Percent complete: 95.3%; Average loss: 2.6895
Iteration: 3815; Percent complete: 95.4%; Average loss: 2.6457
Iteration: 3816; Percent complete: 95.4%; Average loss: 2.5615
Iteration: 3817; Percent complete: 95.4%; Average loss: 2.4267
Iteration: 3818; Percent complete: 95.5%; Average loss: 2.7526
Iteration: 3819; Percent complete: 95.5%; Average loss: 2.5006
Iteration: 3820; Percent complete: 95.5%; Average loss: 2.6876
Iteration: 3821; Percent complete: 95.5%; Average loss: 2.6569
Iteration: 3822; Percent complete: 95.5%; Average loss: 2.5635
Iteration: 3823; Percent complete: 95.6%; Average loss: 2.5977
Iteration: 3824; Percent complete: 95.6%; Average loss: 2.8094
Iteration: 3825; Percent complete: 95.6%; Average loss: 2.6628
Iteration: 3826; Percent complete: 95.7%; Average loss: 2.6088
Iteration: 3827; Percent complete: 95.7%; Average loss: 2.6130
Iteration: 3828; Percent complete: 95.7%; Average loss: 2.8241
Iteration: 3829; Percent complete: 95.7%; Average loss: 2.6017
Iteration: 3830; Percent complete: 95.8%; Average loss: 2.6520
Iteration: 3831; Percent complete: 95.8%; Average loss: 2.4805
Iteration: 3832; Percent complete: 95.8%; Average loss: 2.6928
Iteration: 3833; Percent complete: 95.8%; Average loss: 2.7885
Iteration: 3834; Percent complete: 95.9%; Average loss: 2.9402
Iteration: 3835; Percent complete: 95.9%; Average loss: 2.4172
Iteration: 3836; Percent complete: 95.9%; Average loss: 2.5994
Iteration: 3837; Percent complete: 95.9%; Average loss: 2.6269
Iteration: 3838; Percent complete: 96.0%; Average loss: 2.5278
Iteration: 3839; Percent complete: 96.0%; Average loss: 2.8515
Iteration: 3840; Percent complete: 96.0%; Average loss: 2.6785
Iteration: 3841; Percent complete: 96.0%; Average loss: 2.5009
Iteration: 3842; Percent complete: 96.0%; Average loss: 2.7488
Iteration: 3843; Percent complete: 96.1%; Average loss: 2.5522
Iteration: 3844; Percent complete: 96.1%; Average loss: 2.4692
Iteration: 3845; Percent complete: 96.1%; Average loss: 2.7028
Iteration: 3846; Percent complete: 96.2%; Average loss: 2.5228
Iteration: 3847; Percent complete: 96.2%; Average loss: 2.6191
Iteration: 3848; Percent complete: 96.2%; Average loss: 2.6031
Iteration: 3849; Percent complete: 96.2%; Average loss: 2.7515
Iteration: 3850; Percent complete: 96.2%; Average loss: 2.6511
Iteration: 3851; Percent complete: 96.3%; Average loss: 2.7260
Iteration: 3852; Percent complete: 96.3%; Average loss: 2.7562
Iteration: 3853; Percent complete: 96.3%; Average loss: 2.6716
Iteration: 3854; Percent complete: 96.4%; Average loss: 2.7154
Iteration: 3855; Percent complete: 96.4%; Average loss: 2.6871
Iteration: 3856; Percent complete: 96.4%; Average loss: 2.4789
Iteration: 3857; Percent complete: 96.4%; Average loss: 2.5004
Iteration: 3858; Percent complete: 96.5%; Average loss: 2.6522
Iteration: 3859; Percent complete: 96.5%; Average loss: 2.4688
Iteration: 3860; Percent complete: 96.5%; Average loss: 2.6142
Iteration: 3861; Percent complete: 96.5%; Average loss: 2.5717
Iteration: 3862; Percent complete: 96.5%; Average loss: 2.7307
Iteration: 3863; Percent complete: 96.6%; Average loss: 2.6544
Iteration: 3864; Percent complete: 96.6%; Average loss: 2.6732
Iteration: 3865; Percent complete: 96.6%; Average loss: 2.5529
Iteration: 3866; Percent complete: 96.7%; Average loss: 2.7571
Iteration: 3867; Percent complete: 96.7%; Average loss: 2.5325
Iteration: 3868; Percent complete: 96.7%; Average loss: 2.4369
Iteration: 3869; Percent complete: 96.7%; Average loss: 2.5809
Iteration: 3870; Percent complete: 96.8%; Average loss: 2.6642
Iteration: 3871; Percent complete: 96.8%; Average loss: 2.5287
Iteration: 3872; Percent complete: 96.8%; Average loss: 2.5098
Iteration: 3873; Percent complete: 96.8%; Average loss: 2.7216
Iteration: 3874; Percent complete: 96.9%; Average loss: 2.4496
Iteration: 3875; Percent complete: 96.9%; Average loss: 2.7748
Iteration: 3876; Percent complete: 96.9%; Average loss: 2.8619
Iteration: 3877; Percent complete: 96.9%; Average loss: 2.8166
Iteration: 3878; Percent complete: 97.0%; Average loss: 2.6269
Iteration: 3879; Percent complete: 97.0%; Average loss: 2.9621
Iteration: 3880; Percent complete: 97.0%; Average loss: 2.7324
Iteration: 3881; Percent complete: 97.0%; Average loss: 2.6598
Iteration: 3882; Percent complete: 97.0%; Average loss: 2.7003
Iteration: 3883; Percent complete: 97.1%; Average loss: 2.5350
Iteration: 3884; Percent complete: 97.1%; Average loss: 2.5756
Iteration: 3885; Percent complete: 97.1%; Average loss: 2.6131
Iteration: 3886; Percent complete: 97.2%; Average loss: 2.8010
Iteration: 3887; Percent complete: 97.2%; Average loss: 2.9183
Iteration: 3888; Percent complete: 97.2%; Average loss: 2.5648
Iteration: 3889; Percent complete: 97.2%; Average loss: 2.5177
Iteration: 3890; Percent complete: 97.2%; Average loss: 2.7289
Iteration: 3891; Percent complete: 97.3%; Average loss: 2.7023
Iteration: 3892; Percent complete: 97.3%; Average loss: 2.4335
Iteration: 3893; Percent complete: 97.3%; Average loss: 2.5694
Iteration: 3894; Percent complete: 97.4%; Average loss: 2.5491
Iteration: 3895; Percent complete: 97.4%; Average loss: 2.5079
Iteration: 3896; Percent complete: 97.4%; Average loss: 2.7339
Iteration: 3897; Percent complete: 97.4%; Average loss: 2.4658
Iteration: 3898; Percent complete: 97.5%; Average loss: 2.6498
Iteration: 3899; Percent complete: 97.5%; Average loss: 2.6535
Iteration: 3900; Percent complete: 97.5%; Average loss: 2.6084
Iteration: 3901; Percent complete: 97.5%; Average loss: 2.7179
Iteration: 3902; Percent complete: 97.5%; Average loss: 2.8730
Iteration: 3903; Percent complete: 97.6%; Average loss: 2.7499
Iteration: 3904; Percent complete: 97.6%; Average loss: 2.4912
Iteration: 3905; Percent complete: 97.6%; Average loss: 2.8387
Iteration: 3906; Percent complete: 97.7%; Average loss: 2.5180
Iteration: 3907; Percent complete: 97.7%; Average loss: 2.7198
Iteration: 3908; Percent complete: 97.7%; Average loss: 2.7953
Iteration: 3909; Percent complete: 97.7%; Average loss: 2.5516
Iteration: 3910; Percent complete: 97.8%; Average loss: 2.4185
Iteration: 3911; Percent complete: 97.8%; Average loss: 2.4607
Iteration: 3912; Percent complete: 97.8%; Average loss: 2.9013
Iteration: 3913; Percent complete: 97.8%; Average loss: 2.5558
Iteration: 3914; Percent complete: 97.9%; Average loss: 2.6834
Iteration: 3915; Percent complete: 97.9%; Average loss: 2.5332
Iteration: 3916; Percent complete: 97.9%; Average loss: 2.5852
Iteration: 3917; Percent complete: 97.9%; Average loss: 2.5701
Iteration: 3918; Percent complete: 98.0%; Average loss: 2.5402
Iteration: 3919; Percent complete: 98.0%; Average loss: 2.6810
Iteration: 3920; Percent complete: 98.0%; Average loss: 2.7138
Iteration: 3921; Percent complete: 98.0%; Average loss: 2.8294
Iteration: 3922; Percent complete: 98.0%; Average loss: 2.7853
Iteration: 3923; Percent complete: 98.1%; Average loss: 2.5544
Iteration: 3924; Percent complete: 98.1%; Average loss: 2.9703
Iteration: 3925; Percent complete: 98.1%; Average loss: 2.7109
Iteration: 3926; Percent complete: 98.2%; Average loss: 2.6768
Iteration: 3927; Percent complete: 98.2%; Average loss: 2.6027
Iteration: 3928; Percent complete: 98.2%; Average loss: 2.8197
Iteration: 3929; Percent complete: 98.2%; Average loss: 2.7087
Iteration: 3930; Percent complete: 98.2%; Average loss: 2.6483
Iteration: 3931; Percent complete: 98.3%; Average loss: 2.7562
Iteration: 3932; Percent complete: 98.3%; Average loss: 2.7205
Iteration: 3933; Percent complete: 98.3%; Average loss: 2.6767
Iteration: 3934; Percent complete: 98.4%; Average loss: 2.4585
Iteration: 3935; Percent complete: 98.4%; Average loss: 2.6629
Iteration: 3936; Percent complete: 98.4%; Average loss: 2.5610
Iteration: 3937; Percent complete: 98.4%; Average loss: 2.4277
Iteration: 3938; Percent complete: 98.5%; Average loss: 2.4558
Iteration: 3939; Percent complete: 98.5%; Average loss: 2.7912
Iteration: 3940; Percent complete: 98.5%; Average loss: 2.6408
Iteration: 3941; Percent complete: 98.5%; Average loss: 2.3999
Iteration: 3942; Percent complete: 98.6%; Average loss: 2.4742
Iteration: 3943; Percent complete: 98.6%; Average loss: 2.6837
Iteration: 3944; Percent complete: 98.6%; Average loss: 2.4962
Iteration: 3945; Percent complete: 98.6%; Average loss: 2.6854
Iteration: 3946; Percent complete: 98.7%; Average loss: 2.5754
Iteration: 3947; Percent complete: 98.7%; Average loss: 2.8755
Iteration: 3948; Percent complete: 98.7%; Average loss: 2.5435
Iteration: 3949; Percent complete: 98.7%; Average loss: 2.6399
Iteration: 3950; Percent complete: 98.8%; Average loss: 2.7013
Iteration: 3951; Percent complete: 98.8%; Average loss: 2.8869
Iteration: 3952; Percent complete: 98.8%; Average loss: 2.4747
Iteration: 3953; Percent complete: 98.8%; Average loss: 2.7612
Iteration: 3954; Percent complete: 98.9%; Average loss: 2.7922
Iteration: 3955; Percent complete: 98.9%; Average loss: 2.6711
Iteration: 3956; Percent complete: 98.9%; Average loss: 2.6181
Iteration: 3957; Percent complete: 98.9%; Average loss: 2.5807
Iteration: 3958; Percent complete: 99.0%; Average loss: 2.6406
Iteration: 3959; Percent complete: 99.0%; Average loss: 2.6330
Iteration: 3960; Percent complete: 99.0%; Average loss: 2.5593
Iteration: 3961; Percent complete: 99.0%; Average loss: 2.5647
Iteration: 3962; Percent complete: 99.1%; Average loss: 2.6617
Iteration: 3963; Percent complete: 99.1%; Average loss: 2.5763
Iteration: 3964; Percent complete: 99.1%; Average loss: 2.5274
Iteration: 3965; Percent complete: 99.1%; Average loss: 2.5042
Iteration: 3966; Percent complete: 99.2%; Average loss: 2.6537
Iteration: 3967; Percent complete: 99.2%; Average loss: 2.6554
Iteration: 3968; Percent complete: 99.2%; Average loss: 2.6007
Iteration: 3969; Percent complete: 99.2%; Average loss: 2.7657
Iteration: 3970; Percent complete: 99.2%; Average loss: 2.6209
Iteration: 3971; Percent complete: 99.3%; Average loss: 2.5966
Iteration: 3972; Percent complete: 99.3%; Average loss: 2.6002
Iteration: 3973; Percent complete: 99.3%; Average loss: 2.5532
Iteration: 3974; Percent complete: 99.4%; Average loss: 2.8353
Iteration: 3975; Percent complete: 99.4%; Average loss: 2.6621
Iteration: 3976; Percent complete: 99.4%; Average loss: 2.5751
Iteration: 3977; Percent complete: 99.4%; Average loss: 2.7055
Iteration: 3978; Percent complete: 99.5%; Average loss: 2.5002
Iteration: 3979; Percent complete: 99.5%; Average loss: 2.9251
Iteration: 3980; Percent complete: 99.5%; Average loss: 2.7042
Iteration: 3981; Percent complete: 99.5%; Average loss: 2.6399
Iteration: 3982; Percent complete: 99.6%; Average loss: 2.7698
Iteration: 3983; Percent complete: 99.6%; Average loss: 2.4617
Iteration: 3984; Percent complete: 99.6%; Average loss: 2.5260
Iteration: 3985; Percent complete: 99.6%; Average loss: 2.6685
Iteration: 3986; Percent complete: 99.7%; Average loss: 2.9054
Iteration: 3987; Percent complete: 99.7%; Average loss: 2.6386
Iteration: 3988; Percent complete: 99.7%; Average loss: 2.4812
Iteration: 3989; Percent complete: 99.7%; Average loss: 2.6486
Iteration: 3990; Percent complete: 99.8%; Average loss: 2.5372
Iteration: 3991; Percent complete: 99.8%; Average loss: 2.2769
Iteration: 3992; Percent complete: 99.8%; Average loss: 2.8056
Iteration: 3993; Percent complete: 99.8%; Average loss: 2.7563
Iteration: 3994; Percent complete: 99.9%; Average loss: 2.5527
Iteration: 3995; Percent complete: 99.9%; Average loss: 2.6118
Iteration: 3996; Percent complete: 99.9%; Average loss: 2.5692
Iteration: 3997; Percent complete: 99.9%; Average loss: 2.5346
Iteration: 3998; Percent complete: 100.0%; Average loss: 2.4108
Iteration: 3999; Percent complete: 100.0%; Average loss: 2.6901
Iteration: 4000; Percent complete: 100.0%; Average loss: 2.5437

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!