Rate this Page

★ ★ ★ ★ ★

beginner/chatbot_tutorial

Run in Google Colab

Note

Go to the end to download the full example code.

Chatbot Tutorial#

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

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:

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

Preparations#

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

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

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


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

Using cuda device

Load & Preprocess Data#

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

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

220,579 conversational exchanges between 10,292 pairs of movie characters
9,035 characters from 617 movies
304,713 total utterances

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

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

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

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

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

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

Create formatted data file#

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

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

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

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

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

    return lines, conversations


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

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

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

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

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

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

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

Processing corpus into lines and conversations...

Writing newly formatted file...

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

Load and trim data#

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

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

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

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

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

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

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

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

        keep_words = []

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

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

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

        for word in keep_words:
            self.addWord(word)

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

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

MAX_LENGTH = 10  # Maximum sentence length to consider

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

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

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

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

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

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


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

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

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

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

Trim words used under MIN_COUNT threshold using the voc.trim function.
Filter out pairs with trimmed words.

MIN_COUNT = 3    # Minimum word count threshold for trimming

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

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

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


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

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

Prepare Data for Models#

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

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

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

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

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

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

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

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


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

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

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

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

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


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

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

input_variable: tensor([[  36,  103, 5603, 1366, 2392],
        [ 210,   11,   10,   10,    2],
        [  90,  208,    2,    2,    0],
        [  79,  135,    0,    0,    0],
        [ 304,  694,    0,    0,    0],
        [  14,   10,    0,    0,    0],
        [   2,    2,    0,    0,    0]])
lengths: tensor([7, 7, 3, 3, 2])
target_variable: tensor([[  19,    5,  296,  280,  111],
        [  10, 1415,   14,   14,   11],
        [   2,  161,   61,    2,  359],
        [   0,   85,  126,    0,   79],
        [   0,  385,   14,    0, 2661],
        [   0,  209,    2,    0,  132],
        [   0,   56,    0,    0, 7049],
        [   0, 2513,    0,    0,  575],
        [   0,   14,    0,    0,   10],
        [   0,    2,    0,    0,    2]])
mask: tensor([[ True,  True,  True,  True,  True],
        [ True,  True,  True,  True,  True],
        [ True,  True,  True,  True,  True],
        [False,  True,  True, False,  True],
        [False,  True,  True, False,  True],
        [False,  True,  True, False,  True],
        [False,  True, False, False,  True],
        [False,  True, False, False,  True],
        [False,  True, False, False,  True],
        [False,  True, False, False,  True]])
max_target_len: 10

Define Models#

Seq2Seq Model#

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

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

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

Encoder#

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

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

Bidirectional RNN:

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

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

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

Computation Graph:

Convert word indexes to embeddings.

Pack padded batch of sequences for RNN module.

Forward pass through GRU.

Unpack padding.

Sum bidirectional GRU outputs.

Return output and final hidden state.

Inputs:

input_seq: batch of input sentences; shape=(max_length, batch_size)
input_lengths: list of sentence lengths corresponding to each sentence in the batch; shape=(batch_size)
hidden: hidden state; shape=(n_layers x num_directions, batch_size, hidden_size)

Outputs:

outputs: output features from the last hidden layer of the GRU (sum of bidirectional outputs); shape=(max_length, batch_size, hidden_size)
hidden: updated hidden state from GRU; shape=(n_layers x num_directions, batch_size, hidden_size)

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

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

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

Decoder#

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

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

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

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

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

Overall, the Global attention mechanism can be summarized by the following figure. Note that we will implement the “Attention Layer” as a separate nn.Module called Attn. The output of this module is a softmax normalized weights tensor of shape (batch_size, 1, max_length).

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

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

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

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

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

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

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

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

Computation Graph:

Get embedding of current input word.

Forward through unidirectional GRU.

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

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

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

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

Return output and final hidden state.

Inputs:

input_step: one time step (one word) of input sequence batch; shape=(1, batch_size)
last_hidden: final hidden layer of GRU; shape=(n_layers x num_directions, batch_size, hidden_size)
encoder_outputs: encoder model’s output; shape=(max_length, batch_size, hidden_size)

Outputs:

output: softmax normalized tensor giving probabilities of each word being the correct next word in the decoded sequence; shape=(batch_size, voc.num_words)
hidden: final hidden state of GRU; shape=(n_layers x num_directions, batch_size, hidden_size)

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

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

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

        self.attn = Attn(attn_model, hidden_size)

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

Define Training Procedure#

Masked loss#

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

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

Single training iteration#

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

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

The first trick is using teacher forcing. This means that at some probability, set by teacher_forcing_ratio, we use the current target word as the decoder’s next input rather than using the decoder’s current guess. This technique acts as training wheels for the decoder, aiding in more efficient training. However, teacher forcing can lead to model instability during inference, as the decoder may not have a sufficient chance to truly craft its own output sequences during training. Thus, we must be mindful of how we are setting the teacher_forcing_ratio, and not be fooled by fast convergence.
The second trick that we implement is gradient clipping. This is a commonly used technique for countering the “exploding gradient” problem. In essence, by clipping or thresholding gradients to a maximum value, we prevent the gradients from growing exponentially and either overflow (NaN), or overshoot steep cliffs in the cost function.

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

Sequence of Operations:

Forward pass entire input batch through encoder.

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

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

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

Calculate and accumulate loss.

Perform backpropagation.

Clip gradients.

Update encoder and decoder model parameters.

Note

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

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

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

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

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

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

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

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

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

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

    # Perform backpropagation
    loss.backward()

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

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

    return sum(print_losses) / n_totals

Training iterations#

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

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

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

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

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

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

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

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

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

Define Evaluation#

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

Greedy decoding#

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

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

Computation Graph:

Forward input through encoder model.

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

Initialize decoder’s first input as SOS_token.

Initialize tensors to append decoded words to.

Iteratively decode one word token at a time:

Forward pass through decoder.

Obtain most likely word token and its softmax score.

Record token and score.

Prepare current token to be next decoder input.

Return collections of word tokens and scores.

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

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

Evaluate my text#

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

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

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

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


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

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

Run Model#

Finally, it is time to run our model!

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

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

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

Sample code to load from a checkpoint:

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

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


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

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

Run Training#

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

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

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

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

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

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

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

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

Building optimizers ...
Starting Training!
Initializing ...
Training...
Iteration: 1; Percent complete: 0.0%; Average loss: 8.9805
Iteration: 2; Percent complete: 0.1%; Average loss: 8.8640
Iteration: 3; Percent complete: 0.1%; Average loss: 8.6762
Iteration: 4; Percent complete: 0.1%; Average loss: 8.4488
Iteration: 5; Percent complete: 0.1%; Average loss: 7.9925
Iteration: 6; Percent complete: 0.1%; Average loss: 7.5720
Iteration: 7; Percent complete: 0.2%; Average loss: 6.9443
Iteration: 8; Percent complete: 0.2%; Average loss: 6.6994
Iteration: 9; Percent complete: 0.2%; Average loss: 6.9488
Iteration: 10; Percent complete: 0.2%; Average loss: 6.6621
Iteration: 11; Percent complete: 0.3%; Average loss: 6.2289
Iteration: 12; Percent complete: 0.3%; Average loss: 5.7667
Iteration: 13; Percent complete: 0.3%; Average loss: 5.6863
Iteration: 14; Percent complete: 0.4%; Average loss: 5.9016
Iteration: 15; Percent complete: 0.4%; Average loss: 5.5881
Iteration: 16; Percent complete: 0.4%; Average loss: 5.3003
Iteration: 17; Percent complete: 0.4%; Average loss: 5.2852
Iteration: 18; Percent complete: 0.4%; Average loss: 5.2823
Iteration: 19; Percent complete: 0.5%; Average loss: 5.1860
Iteration: 20; Percent complete: 0.5%; Average loss: 4.9362
Iteration: 21; Percent complete: 0.5%; Average loss: 5.0758
Iteration: 22; Percent complete: 0.5%; Average loss: 5.0116
Iteration: 23; Percent complete: 0.6%; Average loss: 4.8056
Iteration: 24; Percent complete: 0.6%; Average loss: 4.7855
Iteration: 25; Percent complete: 0.6%; Average loss: 4.8945
Iteration: 26; Percent complete: 0.7%; Average loss: 4.9933
Iteration: 27; Percent complete: 0.7%; Average loss: 4.9065
Iteration: 28; Percent complete: 0.7%; Average loss: 4.8195
Iteration: 29; Percent complete: 0.7%; Average loss: 4.7197
Iteration: 30; Percent complete: 0.8%; Average loss: 4.4959
Iteration: 31; Percent complete: 0.8%; Average loss: 4.6646
Iteration: 32; Percent complete: 0.8%; Average loss: 4.8027
Iteration: 33; Percent complete: 0.8%; Average loss: 4.7015
Iteration: 34; Percent complete: 0.9%; Average loss: 4.9361
Iteration: 35; Percent complete: 0.9%; Average loss: 4.6114
Iteration: 36; Percent complete: 0.9%; Average loss: 4.7296
Iteration: 37; Percent complete: 0.9%; Average loss: 4.8784
Iteration: 38; Percent complete: 0.9%; Average loss: 4.7937
Iteration: 39; Percent complete: 1.0%; Average loss: 4.7479
Iteration: 40; Percent complete: 1.0%; Average loss: 4.6339
Iteration: 41; Percent complete: 1.0%; Average loss: 4.6859
Iteration: 42; Percent complete: 1.1%; Average loss: 4.6461
Iteration: 43; Percent complete: 1.1%; Average loss: 4.8349
Iteration: 44; Percent complete: 1.1%; Average loss: 4.7407
Iteration: 45; Percent complete: 1.1%; Average loss: 4.6520
Iteration: 46; Percent complete: 1.1%; Average loss: 4.7556
Iteration: 47; Percent complete: 1.2%; Average loss: 4.5120
Iteration: 48; Percent complete: 1.2%; Average loss: 4.8107
Iteration: 49; Percent complete: 1.2%; Average loss: 4.3842
Iteration: 50; Percent complete: 1.2%; Average loss: 4.6379
Iteration: 51; Percent complete: 1.3%; Average loss: 4.7177
Iteration: 52; Percent complete: 1.3%; Average loss: 4.6099
Iteration: 53; Percent complete: 1.3%; Average loss: 4.6926
Iteration: 54; Percent complete: 1.4%; Average loss: 4.4162
Iteration: 55; Percent complete: 1.4%; Average loss: 4.4940
Iteration: 56; Percent complete: 1.4%; Average loss: 4.6498
Iteration: 57; Percent complete: 1.4%; Average loss: 4.6582
Iteration: 58; Percent complete: 1.5%; Average loss: 4.5231
Iteration: 59; Percent complete: 1.5%; Average loss: 4.6649
Iteration: 60; Percent complete: 1.5%; Average loss: 4.5530
Iteration: 61; Percent complete: 1.5%; Average loss: 4.7554
Iteration: 62; Percent complete: 1.6%; Average loss: 4.6064
Iteration: 63; Percent complete: 1.6%; Average loss: 4.7768
Iteration: 64; Percent complete: 1.6%; Average loss: 4.5966
Iteration: 65; Percent complete: 1.6%; Average loss: 4.5634
Iteration: 66; Percent complete: 1.7%; Average loss: 4.4659
Iteration: 67; Percent complete: 1.7%; Average loss: 4.4262
Iteration: 68; Percent complete: 1.7%; Average loss: 4.7122
Iteration: 69; Percent complete: 1.7%; Average loss: 4.6269
Iteration: 70; Percent complete: 1.8%; Average loss: 4.6748
Iteration: 71; Percent complete: 1.8%; Average loss: 4.6217
Iteration: 72; Percent complete: 1.8%; Average loss: 4.8677
Iteration: 73; Percent complete: 1.8%; Average loss: 4.7501
Iteration: 74; Percent complete: 1.8%; Average loss: 4.6200
Iteration: 75; Percent complete: 1.9%; Average loss: 4.9301
Iteration: 76; Percent complete: 1.9%; Average loss: 4.6848
Iteration: 77; Percent complete: 1.9%; Average loss: 4.5697
Iteration: 78; Percent complete: 1.9%; Average loss: 4.7967
Iteration: 79; Percent complete: 2.0%; Average loss: 4.6622
Iteration: 80; Percent complete: 2.0%; Average loss: 4.3720
Iteration: 81; Percent complete: 2.0%; Average loss: 4.5007
Iteration: 82; Percent complete: 2.1%; Average loss: 4.3720
Iteration: 83; Percent complete: 2.1%; Average loss: 4.3101
Iteration: 84; Percent complete: 2.1%; Average loss: 4.5836
Iteration: 85; Percent complete: 2.1%; Average loss: 4.6730
Iteration: 86; Percent complete: 2.1%; Average loss: 4.5328
Iteration: 87; Percent complete: 2.2%; Average loss: 4.1596
Iteration: 88; Percent complete: 2.2%; Average loss: 4.4911
Iteration: 89; Percent complete: 2.2%; Average loss: 4.6935
Iteration: 90; Percent complete: 2.2%; Average loss: 4.4195
Iteration: 91; Percent complete: 2.3%; Average loss: 4.6541
Iteration: 92; Percent complete: 2.3%; Average loss: 4.5435
Iteration: 93; Percent complete: 2.3%; Average loss: 4.3434
Iteration: 94; Percent complete: 2.4%; Average loss: 4.3078
Iteration: 95; Percent complete: 2.4%; Average loss: 4.5218
Iteration: 96; Percent complete: 2.4%; Average loss: 4.3769
Iteration: 97; Percent complete: 2.4%; Average loss: 4.4072
Iteration: 98; Percent complete: 2.5%; Average loss: 4.4619
Iteration: 99; Percent complete: 2.5%; Average loss: 4.4078
Iteration: 100; Percent complete: 2.5%; Average loss: 4.4816
Iteration: 101; Percent complete: 2.5%; Average loss: 4.4088
Iteration: 102; Percent complete: 2.5%; Average loss: 4.5272
Iteration: 103; Percent complete: 2.6%; Average loss: 4.4730
Iteration: 104; Percent complete: 2.6%; Average loss: 4.5280
Iteration: 105; Percent complete: 2.6%; Average loss: 4.3903
Iteration: 106; Percent complete: 2.6%; Average loss: 4.5638
Iteration: 107; Percent complete: 2.7%; Average loss: 4.4948
Iteration: 108; Percent complete: 2.7%; Average loss: 4.5891
Iteration: 109; Percent complete: 2.7%; Average loss: 4.3919
Iteration: 110; Percent complete: 2.8%; Average loss: 4.2858
Iteration: 111; Percent complete: 2.8%; Average loss: 4.3557
Iteration: 112; Percent complete: 2.8%; Average loss: 4.3432
Iteration: 113; Percent complete: 2.8%; Average loss: 4.3922
Iteration: 114; Percent complete: 2.9%; Average loss: 4.4448
Iteration: 115; Percent complete: 2.9%; Average loss: 4.4079
Iteration: 116; Percent complete: 2.9%; Average loss: 4.2424
Iteration: 117; Percent complete: 2.9%; Average loss: 4.3812
Iteration: 118; Percent complete: 2.9%; Average loss: 4.5241
Iteration: 119; Percent complete: 3.0%; Average loss: 4.2490
Iteration: 120; Percent complete: 3.0%; Average loss: 4.3525
Iteration: 121; Percent complete: 3.0%; Average loss: 4.2470
Iteration: 122; Percent complete: 3.0%; Average loss: 4.2984
Iteration: 123; Percent complete: 3.1%; Average loss: 4.4957
Iteration: 124; Percent complete: 3.1%; Average loss: 4.3794
Iteration: 125; Percent complete: 3.1%; Average loss: 4.3991
Iteration: 126; Percent complete: 3.1%; Average loss: 4.4600
Iteration: 127; Percent complete: 3.2%; Average loss: 4.5427
Iteration: 128; Percent complete: 3.2%; Average loss: 4.2568
Iteration: 129; Percent complete: 3.2%; Average loss: 4.4333
Iteration: 130; Percent complete: 3.2%; Average loss: 4.2192
Iteration: 131; Percent complete: 3.3%; Average loss: 4.2398
Iteration: 132; Percent complete: 3.3%; Average loss: 4.3185
Iteration: 133; Percent complete: 3.3%; Average loss: 4.5117
Iteration: 134; Percent complete: 3.4%; Average loss: 4.3453
Iteration: 135; Percent complete: 3.4%; Average loss: 4.2029
Iteration: 136; Percent complete: 3.4%; Average loss: 4.2851
Iteration: 137; Percent complete: 3.4%; Average loss: 4.3342
Iteration: 138; Percent complete: 3.5%; Average loss: 4.4003
Iteration: 139; Percent complete: 3.5%; Average loss: 4.3063
Iteration: 140; Percent complete: 3.5%; Average loss: 4.3201
Iteration: 141; Percent complete: 3.5%; Average loss: 4.3048
Iteration: 142; Percent complete: 3.5%; Average loss: 4.5147
Iteration: 143; Percent complete: 3.6%; Average loss: 4.4085
Iteration: 144; Percent complete: 3.6%; Average loss: 4.2837
Iteration: 145; Percent complete: 3.6%; Average loss: 4.5685
Iteration: 146; Percent complete: 3.6%; Average loss: 4.1705
Iteration: 147; Percent complete: 3.7%; Average loss: 4.2874
Iteration: 148; Percent complete: 3.7%; Average loss: 4.3377
Iteration: 149; Percent complete: 3.7%; Average loss: 3.9432
Iteration: 150; Percent complete: 3.8%; Average loss: 3.9515
Iteration: 151; Percent complete: 3.8%; Average loss: 4.1781
Iteration: 152; Percent complete: 3.8%; Average loss: 4.2613
Iteration: 153; Percent complete: 3.8%; Average loss: 4.2383
Iteration: 154; Percent complete: 3.9%; Average loss: 4.0392
Iteration: 155; Percent complete: 3.9%; Average loss: 4.2138
Iteration: 156; Percent complete: 3.9%; Average loss: 4.2333
Iteration: 157; Percent complete: 3.9%; Average loss: 4.1497
Iteration: 158; Percent complete: 4.0%; Average loss: 3.9494
Iteration: 159; Percent complete: 4.0%; Average loss: 4.0105
Iteration: 160; Percent complete: 4.0%; Average loss: 4.3232
Iteration: 161; Percent complete: 4.0%; Average loss: 3.8002
Iteration: 162; Percent complete: 4.0%; Average loss: 4.1510
Iteration: 163; Percent complete: 4.1%; Average loss: 4.0646
Iteration: 164; Percent complete: 4.1%; Average loss: 4.4010
Iteration: 165; Percent complete: 4.1%; Average loss: 4.2892
Iteration: 166; Percent complete: 4.2%; Average loss: 4.3108
Iteration: 167; Percent complete: 4.2%; Average loss: 4.3003
Iteration: 168; Percent complete: 4.2%; Average loss: 4.4317
Iteration: 169; Percent complete: 4.2%; Average loss: 4.3454
Iteration: 170; Percent complete: 4.2%; Average loss: 3.7718
Iteration: 171; Percent complete: 4.3%; Average loss: 4.5357
Iteration: 172; Percent complete: 4.3%; Average loss: 4.4699
Iteration: 173; Percent complete: 4.3%; Average loss: 4.2117
Iteration: 174; Percent complete: 4.3%; Average loss: 4.1175
Iteration: 175; Percent complete: 4.4%; Average loss: 4.3096
Iteration: 176; Percent complete: 4.4%; Average loss: 4.2732
Iteration: 177; Percent complete: 4.4%; Average loss: 4.2199
Iteration: 178; Percent complete: 4.5%; Average loss: 3.9470
Iteration: 179; Percent complete: 4.5%; Average loss: 4.3404
Iteration: 180; Percent complete: 4.5%; Average loss: 3.9123
Iteration: 181; Percent complete: 4.5%; Average loss: 3.8511
Iteration: 182; Percent complete: 4.5%; Average loss: 4.3161
Iteration: 183; Percent complete: 4.6%; Average loss: 4.4204
Iteration: 184; Percent complete: 4.6%; Average loss: 4.0602
Iteration: 185; Percent complete: 4.6%; Average loss: 3.9645
Iteration: 186; Percent complete: 4.7%; Average loss: 4.1277
Iteration: 187; Percent complete: 4.7%; Average loss: 3.7628
Iteration: 188; Percent complete: 4.7%; Average loss: 4.3312
Iteration: 189; Percent complete: 4.7%; Average loss: 4.0349
Iteration: 190; Percent complete: 4.8%; Average loss: 4.1657
Iteration: 191; Percent complete: 4.8%; Average loss: 4.1908
Iteration: 192; Percent complete: 4.8%; Average loss: 4.4456
Iteration: 193; Percent complete: 4.8%; Average loss: 3.8648
Iteration: 194; Percent complete: 4.9%; Average loss: 3.9302
Iteration: 195; Percent complete: 4.9%; Average loss: 4.0739
Iteration: 196; Percent complete: 4.9%; Average loss: 4.0729
Iteration: 197; Percent complete: 4.9%; Average loss: 3.9492
Iteration: 198; Percent complete: 5.0%; Average loss: 4.4185
Iteration: 199; Percent complete: 5.0%; Average loss: 4.1727
Iteration: 200; Percent complete: 5.0%; Average loss: 4.2287
Iteration: 201; Percent complete: 5.0%; Average loss: 3.9709
Iteration: 202; Percent complete: 5.1%; Average loss: 3.9123
Iteration: 203; Percent complete: 5.1%; Average loss: 4.2010
Iteration: 204; Percent complete: 5.1%; Average loss: 4.0986
Iteration: 205; Percent complete: 5.1%; Average loss: 4.0407
Iteration: 206; Percent complete: 5.1%; Average loss: 4.2846
Iteration: 207; Percent complete: 5.2%; Average loss: 4.0724
Iteration: 208; Percent complete: 5.2%; Average loss: 4.2272
Iteration: 209; Percent complete: 5.2%; Average loss: 4.0182
Iteration: 210; Percent complete: 5.2%; Average loss: 4.0203
Iteration: 211; Percent complete: 5.3%; Average loss: 3.9389
Iteration: 212; Percent complete: 5.3%; Average loss: 3.8807
Iteration: 213; Percent complete: 5.3%; Average loss: 4.1303
Iteration: 214; Percent complete: 5.3%; Average loss: 3.8626
Iteration: 215; Percent complete: 5.4%; Average loss: 3.9214
Iteration: 216; Percent complete: 5.4%; Average loss: 4.3535
Iteration: 217; Percent complete: 5.4%; Average loss: 3.9029
Iteration: 218; Percent complete: 5.5%; Average loss: 3.9785
Iteration: 219; Percent complete: 5.5%; Average loss: 4.0630
Iteration: 220; Percent complete: 5.5%; Average loss: 4.1546
Iteration: 221; Percent complete: 5.5%; Average loss: 3.9536
Iteration: 222; Percent complete: 5.5%; Average loss: 4.2303
Iteration: 223; Percent complete: 5.6%; Average loss: 3.7681
Iteration: 224; Percent complete: 5.6%; Average loss: 4.1038
Iteration: 225; Percent complete: 5.6%; Average loss: 4.0132
Iteration: 226; Percent complete: 5.7%; Average loss: 3.9337
Iteration: 227; Percent complete: 5.7%; Average loss: 4.0749
Iteration: 228; Percent complete: 5.7%; Average loss: 4.0711
Iteration: 229; Percent complete: 5.7%; Average loss: 4.0495
Iteration: 230; Percent complete: 5.8%; Average loss: 3.7342
Iteration: 231; Percent complete: 5.8%; Average loss: 4.0269
Iteration: 232; Percent complete: 5.8%; Average loss: 3.9718
Iteration: 233; Percent complete: 5.8%; Average loss: 4.1166
Iteration: 234; Percent complete: 5.9%; Average loss: 3.8560
Iteration: 235; Percent complete: 5.9%; Average loss: 3.8310
Iteration: 236; Percent complete: 5.9%; Average loss: 4.0625
Iteration: 237; Percent complete: 5.9%; Average loss: 4.1674
Iteration: 238; Percent complete: 5.9%; Average loss: 4.1736
Iteration: 239; Percent complete: 6.0%; Average loss: 4.2521
Iteration: 240; Percent complete: 6.0%; Average loss: 4.1198
Iteration: 241; Percent complete: 6.0%; Average loss: 4.0421
Iteration: 242; Percent complete: 6.0%; Average loss: 4.1174
Iteration: 243; Percent complete: 6.1%; Average loss: 3.7198
Iteration: 244; Percent complete: 6.1%; Average loss: 4.2416
Iteration: 245; Percent complete: 6.1%; Average loss: 4.0426
Iteration: 246; Percent complete: 6.2%; Average loss: 4.1656
Iteration: 247; Percent complete: 6.2%; Average loss: 3.8809
Iteration: 248; Percent complete: 6.2%; Average loss: 3.8059
Iteration: 249; Percent complete: 6.2%; Average loss: 4.0578
Iteration: 250; Percent complete: 6.2%; Average loss: 3.9852
Iteration: 251; Percent complete: 6.3%; Average loss: 3.8521
Iteration: 252; Percent complete: 6.3%; Average loss: 4.2174
Iteration: 253; Percent complete: 6.3%; Average loss: 4.0730
Iteration: 254; Percent complete: 6.3%; Average loss: 3.8828
Iteration: 255; Percent complete: 6.4%; Average loss: 4.2152
Iteration: 256; Percent complete: 6.4%; Average loss: 4.0803
Iteration: 257; Percent complete: 6.4%; Average loss: 4.0320
Iteration: 258; Percent complete: 6.5%; Average loss: 3.9481
Iteration: 259; Percent complete: 6.5%; Average loss: 3.7441
Iteration: 260; Percent complete: 6.5%; Average loss: 4.2559
Iteration: 261; Percent complete: 6.5%; Average loss: 4.2263
Iteration: 262; Percent complete: 6.6%; Average loss: 4.1559
Iteration: 263; Percent complete: 6.6%; Average loss: 4.1557
Iteration: 264; Percent complete: 6.6%; Average loss: 3.9026
Iteration: 265; Percent complete: 6.6%; Average loss: 4.0111
Iteration: 266; Percent complete: 6.7%; Average loss: 3.8710
Iteration: 267; Percent complete: 6.7%; Average loss: 3.9262
Iteration: 268; Percent complete: 6.7%; Average loss: 3.7321
Iteration: 269; Percent complete: 6.7%; Average loss: 4.2117
Iteration: 270; Percent complete: 6.8%; Average loss: 3.6908
Iteration: 271; Percent complete: 6.8%; Average loss: 3.8620
Iteration: 272; Percent complete: 6.8%; Average loss: 4.0893
Iteration: 273; Percent complete: 6.8%; Average loss: 3.6348
Iteration: 274; Percent complete: 6.9%; Average loss: 3.9458
Iteration: 275; Percent complete: 6.9%; Average loss: 3.8481
Iteration: 276; Percent complete: 6.9%; Average loss: 3.7934
Iteration: 277; Percent complete: 6.9%; Average loss: 3.9341
Iteration: 278; Percent complete: 7.0%; Average loss: 4.0392
Iteration: 279; Percent complete: 7.0%; Average loss: 3.8813
Iteration: 280; Percent complete: 7.0%; Average loss: 4.0929
Iteration: 281; Percent complete: 7.0%; Average loss: 4.1366
Iteration: 282; Percent complete: 7.0%; Average loss: 3.8123
Iteration: 283; Percent complete: 7.1%; Average loss: 3.9263
Iteration: 284; Percent complete: 7.1%; Average loss: 3.8147
Iteration: 285; Percent complete: 7.1%; Average loss: 4.0534
Iteration: 286; Percent complete: 7.1%; Average loss: 4.0475
Iteration: 287; Percent complete: 7.2%; Average loss: 3.7961
Iteration: 288; Percent complete: 7.2%; Average loss: 3.8092
Iteration: 289; Percent complete: 7.2%; Average loss: 3.9630
Iteration: 290; Percent complete: 7.2%; Average loss: 4.0164
Iteration: 291; Percent complete: 7.3%; Average loss: 3.9463
Iteration: 292; Percent complete: 7.3%; Average loss: 3.9801
Iteration: 293; Percent complete: 7.3%; Average loss: 3.9458
Iteration: 294; Percent complete: 7.3%; Average loss: 3.7338
Iteration: 295; Percent complete: 7.4%; Average loss: 3.9671
Iteration: 296; Percent complete: 7.4%; Average loss: 3.9936
Iteration: 297; Percent complete: 7.4%; Average loss: 3.8279
Iteration: 298; Percent complete: 7.4%; Average loss: 4.0563
Iteration: 299; Percent complete: 7.5%; Average loss: 4.2012
Iteration: 300; Percent complete: 7.5%; Average loss: 4.0788
Iteration: 301; Percent complete: 7.5%; Average loss: 3.8038
Iteration: 302; Percent complete: 7.5%; Average loss: 3.7937
Iteration: 303; Percent complete: 7.6%; Average loss: 4.0383
Iteration: 304; Percent complete: 7.6%; Average loss: 4.0493
Iteration: 305; Percent complete: 7.6%; Average loss: 3.8959
Iteration: 306; Percent complete: 7.6%; Average loss: 4.0099
Iteration: 307; Percent complete: 7.7%; Average loss: 4.0811
Iteration: 308; Percent complete: 7.7%; Average loss: 3.9829
Iteration: 309; Percent complete: 7.7%; Average loss: 3.6139
Iteration: 310; Percent complete: 7.8%; Average loss: 4.0619
Iteration: 311; Percent complete: 7.8%; Average loss: 3.9033
Iteration: 312; Percent complete: 7.8%; Average loss: 3.8556
Iteration: 313; Percent complete: 7.8%; Average loss: 3.5662
Iteration: 314; Percent complete: 7.8%; Average loss: 3.7703
Iteration: 315; Percent complete: 7.9%; Average loss: 3.9608
Iteration: 316; Percent complete: 7.9%; Average loss: 3.7983
Iteration: 317; Percent complete: 7.9%; Average loss: 3.8855
Iteration: 318; Percent complete: 8.0%; Average loss: 4.2671
Iteration: 319; Percent complete: 8.0%; Average loss: 3.9697
Iteration: 320; Percent complete: 8.0%; Average loss: 4.1539
Iteration: 321; Percent complete: 8.0%; Average loss: 3.7078
Iteration: 322; Percent complete: 8.1%; Average loss: 4.1167
Iteration: 323; Percent complete: 8.1%; Average loss: 4.0918
Iteration: 324; Percent complete: 8.1%; Average loss: 3.6250
Iteration: 325; Percent complete: 8.1%; Average loss: 3.9312
Iteration: 326; Percent complete: 8.2%; Average loss: 3.6855
Iteration: 327; Percent complete: 8.2%; Average loss: 3.7000
Iteration: 328; Percent complete: 8.2%; Average loss: 3.8713
Iteration: 329; Percent complete: 8.2%; Average loss: 4.0460
Iteration: 330; Percent complete: 8.2%; Average loss: 3.7199
Iteration: 331; Percent complete: 8.3%; Average loss: 3.8276
Iteration: 332; Percent complete: 8.3%; Average loss: 3.7674
Iteration: 333; Percent complete: 8.3%; Average loss: 4.0343
Iteration: 334; Percent complete: 8.3%; Average loss: 3.8197
Iteration: 335; Percent complete: 8.4%; Average loss: 3.9502
Iteration: 336; Percent complete: 8.4%; Average loss: 4.0870
Iteration: 337; Percent complete: 8.4%; Average loss: 3.7869
Iteration: 338; Percent complete: 8.5%; Average loss: 3.9096
Iteration: 339; Percent complete: 8.5%; Average loss: 3.6676
Iteration: 340; Percent complete: 8.5%; Average loss: 4.0009
Iteration: 341; Percent complete: 8.5%; Average loss: 3.8909
Iteration: 342; Percent complete: 8.6%; Average loss: 3.8348
Iteration: 343; Percent complete: 8.6%; Average loss: 3.9552
Iteration: 344; Percent complete: 8.6%; Average loss: 3.7998
Iteration: 345; Percent complete: 8.6%; Average loss: 3.7069
Iteration: 346; Percent complete: 8.6%; Average loss: 3.8881
Iteration: 347; Percent complete: 8.7%; Average loss: 3.9393
Iteration: 348; Percent complete: 8.7%; Average loss: 3.6879
Iteration: 349; Percent complete: 8.7%; Average loss: 3.6981
Iteration: 350; Percent complete: 8.8%; Average loss: 3.7787
Iteration: 351; Percent complete: 8.8%; Average loss: 3.7665
Iteration: 352; Percent complete: 8.8%; Average loss: 3.6808
Iteration: 353; Percent complete: 8.8%; Average loss: 3.6937
Iteration: 354; Percent complete: 8.8%; Average loss: 3.8636
Iteration: 355; Percent complete: 8.9%; Average loss: 3.9653
Iteration: 356; Percent complete: 8.9%; Average loss: 3.9601
Iteration: 357; Percent complete: 8.9%; Average loss: 3.9847
Iteration: 358; Percent complete: 8.9%; Average loss: 3.9119
Iteration: 359; Percent complete: 9.0%; Average loss: 3.6183
Iteration: 360; Percent complete: 9.0%; Average loss: 4.1868
Iteration: 361; Percent complete: 9.0%; Average loss: 3.9584
Iteration: 362; Percent complete: 9.0%; Average loss: 3.8021
Iteration: 363; Percent complete: 9.1%; Average loss: 3.8941
Iteration: 364; Percent complete: 9.1%; Average loss: 3.8390
Iteration: 365; Percent complete: 9.1%; Average loss: 3.6788
Iteration: 366; Percent complete: 9.2%; Average loss: 3.8905
Iteration: 367; Percent complete: 9.2%; Average loss: 3.7703
Iteration: 368; Percent complete: 9.2%; Average loss: 4.0236
Iteration: 369; Percent complete: 9.2%; Average loss: 4.0576
Iteration: 370; Percent complete: 9.2%; Average loss: 3.8503
Iteration: 371; Percent complete: 9.3%; Average loss: 4.1343
Iteration: 372; Percent complete: 9.3%; Average loss: 3.7677
Iteration: 373; Percent complete: 9.3%; Average loss: 3.8589
Iteration: 374; Percent complete: 9.3%; Average loss: 3.9906
Iteration: 375; Percent complete: 9.4%; Average loss: 3.5401
Iteration: 376; Percent complete: 9.4%; Average loss: 3.8314
Iteration: 377; Percent complete: 9.4%; Average loss: 3.7426
Iteration: 378; Percent complete: 9.4%; Average loss: 3.6426
Iteration: 379; Percent complete: 9.5%; Average loss: 3.9398
Iteration: 380; Percent complete: 9.5%; Average loss: 3.7955
Iteration: 381; Percent complete: 9.5%; Average loss: 3.7567
Iteration: 382; Percent complete: 9.6%; Average loss: 3.6548
Iteration: 383; Percent complete: 9.6%; Average loss: 3.7885
Iteration: 384; Percent complete: 9.6%; Average loss: 3.6924
Iteration: 385; Percent complete: 9.6%; Average loss: 3.7826
Iteration: 386; Percent complete: 9.7%; Average loss: 4.0001
Iteration: 387; Percent complete: 9.7%; Average loss: 3.5820
Iteration: 388; Percent complete: 9.7%; Average loss: 3.6135
Iteration: 389; Percent complete: 9.7%; Average loss: 3.7509
Iteration: 390; Percent complete: 9.8%; Average loss: 3.9233
Iteration: 391; Percent complete: 9.8%; Average loss: 4.0335
Iteration: 392; Percent complete: 9.8%; Average loss: 3.8094
Iteration: 393; Percent complete: 9.8%; Average loss: 3.7433
Iteration: 394; Percent complete: 9.8%; Average loss: 3.9218
Iteration: 395; Percent complete: 9.9%; Average loss: 3.7697
Iteration: 396; Percent complete: 9.9%; Average loss: 3.8501
Iteration: 397; Percent complete: 9.9%; Average loss: 4.0130
Iteration: 398; Percent complete: 10.0%; Average loss: 3.7915
Iteration: 399; Percent complete: 10.0%; Average loss: 3.6361
Iteration: 400; Percent complete: 10.0%; Average loss: 3.7598
Iteration: 401; Percent complete: 10.0%; Average loss: 3.7093
Iteration: 402; Percent complete: 10.1%; Average loss: 3.8975
Iteration: 403; Percent complete: 10.1%; Average loss: 3.6164
Iteration: 404; Percent complete: 10.1%; Average loss: 3.7668
Iteration: 405; Percent complete: 10.1%; Average loss: 4.1661
Iteration: 406; Percent complete: 10.2%; Average loss: 3.6392
Iteration: 407; Percent complete: 10.2%; Average loss: 3.6151
Iteration: 408; Percent complete: 10.2%; Average loss: 3.7178
Iteration: 409; Percent complete: 10.2%; Average loss: 4.0570
Iteration: 410; Percent complete: 10.2%; Average loss: 3.5842
Iteration: 411; Percent complete: 10.3%; Average loss: 3.7787
Iteration: 412; Percent complete: 10.3%; Average loss: 3.9193
Iteration: 413; Percent complete: 10.3%; Average loss: 3.7134
Iteration: 414; Percent complete: 10.3%; Average loss: 4.0642
Iteration: 415; Percent complete: 10.4%; Average loss: 3.7109
Iteration: 416; Percent complete: 10.4%; Average loss: 3.7155
Iteration: 417; Percent complete: 10.4%; Average loss: 3.6441
Iteration: 418; Percent complete: 10.4%; Average loss: 3.6755
Iteration: 419; Percent complete: 10.5%; Average loss: 3.8400
Iteration: 420; Percent complete: 10.5%; Average loss: 3.5646
Iteration: 421; Percent complete: 10.5%; Average loss: 4.1315
Iteration: 422; Percent complete: 10.5%; Average loss: 3.6023
Iteration: 423; Percent complete: 10.6%; Average loss: 3.7363
Iteration: 424; Percent complete: 10.6%; Average loss: 4.0496
Iteration: 425; Percent complete: 10.6%; Average loss: 3.6382
Iteration: 426; Percent complete: 10.7%; Average loss: 3.7639
Iteration: 427; Percent complete: 10.7%; Average loss: 3.5576
Iteration: 428; Percent complete: 10.7%; Average loss: 3.6075
Iteration: 429; Percent complete: 10.7%; Average loss: 3.9523
Iteration: 430; Percent complete: 10.8%; Average loss: 3.8566
Iteration: 431; Percent complete: 10.8%; Average loss: 3.4859
Iteration: 432; Percent complete: 10.8%; Average loss: 3.9147
Iteration: 433; Percent complete: 10.8%; Average loss: 3.6692
Iteration: 434; Percent complete: 10.8%; Average loss: 3.7174
Iteration: 435; Percent complete: 10.9%; Average loss: 3.7613
Iteration: 436; Percent complete: 10.9%; Average loss: 3.8794
Iteration: 437; Percent complete: 10.9%; Average loss: 3.7588
Iteration: 438; Percent complete: 10.9%; Average loss: 3.9498
Iteration: 439; Percent complete: 11.0%; Average loss: 3.6647
Iteration: 440; Percent complete: 11.0%; Average loss: 3.6310
Iteration: 441; Percent complete: 11.0%; Average loss: 4.1041
Iteration: 442; Percent complete: 11.1%; Average loss: 3.7663
Iteration: 443; Percent complete: 11.1%; Average loss: 3.9741
Iteration: 444; Percent complete: 11.1%; Average loss: 3.9414
Iteration: 445; Percent complete: 11.1%; Average loss: 3.8506
Iteration: 446; Percent complete: 11.2%; Average loss: 3.5485
Iteration: 447; Percent complete: 11.2%; Average loss: 3.8743
Iteration: 448; Percent complete: 11.2%; Average loss: 4.0443
Iteration: 449; Percent complete: 11.2%; Average loss: 3.5959
Iteration: 450; Percent complete: 11.2%; Average loss: 3.7260
Iteration: 451; Percent complete: 11.3%; Average loss: 3.7396
Iteration: 452; Percent complete: 11.3%; Average loss: 3.7733
Iteration: 453; Percent complete: 11.3%; Average loss: 3.8312
Iteration: 454; Percent complete: 11.3%; Average loss: 3.8359
Iteration: 455; Percent complete: 11.4%; Average loss: 3.5748
Iteration: 456; Percent complete: 11.4%; Average loss: 3.7913
Iteration: 457; Percent complete: 11.4%; Average loss: 3.7979
Iteration: 458; Percent complete: 11.5%; Average loss: 3.8094
Iteration: 459; Percent complete: 11.5%; Average loss: 3.8680
Iteration: 460; Percent complete: 11.5%; Average loss: 3.5837
Iteration: 461; Percent complete: 11.5%; Average loss: 3.6962
Iteration: 462; Percent complete: 11.6%; Average loss: 3.6446
Iteration: 463; Percent complete: 11.6%; Average loss: 3.7683
Iteration: 464; Percent complete: 11.6%; Average loss: 3.7209
Iteration: 465; Percent complete: 11.6%; Average loss: 4.3343
Iteration: 466; Percent complete: 11.7%; Average loss: 3.6103
Iteration: 467; Percent complete: 11.7%; Average loss: 3.7885
Iteration: 468; Percent complete: 11.7%; Average loss: 3.8288
Iteration: 469; Percent complete: 11.7%; Average loss: 3.7744
Iteration: 470; Percent complete: 11.8%; Average loss: 3.8478
Iteration: 471; Percent complete: 11.8%; Average loss: 3.8439
Iteration: 472; Percent complete: 11.8%; Average loss: 3.6536
Iteration: 473; Percent complete: 11.8%; Average loss: 3.7214
Iteration: 474; Percent complete: 11.8%; Average loss: 3.9514
Iteration: 475; Percent complete: 11.9%; Average loss: 3.8638
Iteration: 476; Percent complete: 11.9%; Average loss: 3.9848
Iteration: 477; Percent complete: 11.9%; Average loss: 3.7056
Iteration: 478; Percent complete: 11.9%; Average loss: 3.4698
Iteration: 479; Percent complete: 12.0%; Average loss: 3.7352
Iteration: 480; Percent complete: 12.0%; Average loss: 3.9960
Iteration: 481; Percent complete: 12.0%; Average loss: 3.7169
Iteration: 482; Percent complete: 12.0%; Average loss: 3.8791
Iteration: 483; Percent complete: 12.1%; Average loss: 3.8649
Iteration: 484; Percent complete: 12.1%; Average loss: 3.8895
Iteration: 485; Percent complete: 12.1%; Average loss: 3.9222
Iteration: 486; Percent complete: 12.2%; Average loss: 3.6523
Iteration: 487; Percent complete: 12.2%; Average loss: 3.7231
Iteration: 488; Percent complete: 12.2%; Average loss: 3.8101
Iteration: 489; Percent complete: 12.2%; Average loss: 3.8054
Iteration: 490; Percent complete: 12.2%; Average loss: 3.7968
Iteration: 491; Percent complete: 12.3%; Average loss: 3.8136
Iteration: 492; Percent complete: 12.3%; Average loss: 3.8922
Iteration: 493; Percent complete: 12.3%; Average loss: 3.7039
Iteration: 494; Percent complete: 12.3%; Average loss: 3.6924
Iteration: 495; Percent complete: 12.4%; Average loss: 3.8478
Iteration: 496; Percent complete: 12.4%; Average loss: 3.9187
Iteration: 497; Percent complete: 12.4%; Average loss: 3.8580
Iteration: 498; Percent complete: 12.4%; Average loss: 3.8211
Iteration: 499; Percent complete: 12.5%; Average loss: 3.7753
Iteration: 500; Percent complete: 12.5%; Average loss: 3.5595
Iteration: 501; Percent complete: 12.5%; Average loss: 3.8372
Iteration: 502; Percent complete: 12.6%; Average loss: 3.7579
Iteration: 503; Percent complete: 12.6%; Average loss: 3.8436
Iteration: 504; Percent complete: 12.6%; Average loss: 3.7599
Iteration: 505; Percent complete: 12.6%; Average loss: 3.7905
Iteration: 506; Percent complete: 12.7%; Average loss: 3.7977
Iteration: 507; Percent complete: 12.7%; Average loss: 3.7898
Iteration: 508; Percent complete: 12.7%; Average loss: 3.7270
Iteration: 509; Percent complete: 12.7%; Average loss: 3.8321
Iteration: 510; Percent complete: 12.8%; Average loss: 3.7141
Iteration: 511; Percent complete: 12.8%; Average loss: 3.9440
Iteration: 512; Percent complete: 12.8%; Average loss: 3.8182
Iteration: 513; Percent complete: 12.8%; Average loss: 3.7253
Iteration: 514; Percent complete: 12.8%; Average loss: 3.7486
Iteration: 515; Percent complete: 12.9%; Average loss: 3.8285
Iteration: 516; Percent complete: 12.9%; Average loss: 3.6045
Iteration: 517; Percent complete: 12.9%; Average loss: 3.4103
Iteration: 518; Percent complete: 13.0%; Average loss: 3.7862
Iteration: 519; Percent complete: 13.0%; Average loss: 3.8480
Iteration: 520; Percent complete: 13.0%; Average loss: 3.7697
Iteration: 521; Percent complete: 13.0%; Average loss: 3.8474
Iteration: 522; Percent complete: 13.1%; Average loss: 3.6112
Iteration: 523; Percent complete: 13.1%; Average loss: 3.7605
Iteration: 524; Percent complete: 13.1%; Average loss: 3.6125
Iteration: 525; Percent complete: 13.1%; Average loss: 3.7886
Iteration: 526; Percent complete: 13.2%; Average loss: 3.7009
Iteration: 527; Percent complete: 13.2%; Average loss: 3.6846
Iteration: 528; Percent complete: 13.2%; Average loss: 3.6423
Iteration: 529; Percent complete: 13.2%; Average loss: 3.8948
Iteration: 530; Percent complete: 13.2%; Average loss: 3.9363
Iteration: 531; Percent complete: 13.3%; Average loss: 3.9528
Iteration: 532; Percent complete: 13.3%; Average loss: 3.8290
Iteration: 533; Percent complete: 13.3%; Average loss: 3.6325
Iteration: 534; Percent complete: 13.4%; Average loss: 3.5971
Iteration: 535; Percent complete: 13.4%; Average loss: 3.7452
Iteration: 536; Percent complete: 13.4%; Average loss: 3.8327
Iteration: 537; Percent complete: 13.4%; Average loss: 3.3272
Iteration: 538; Percent complete: 13.5%; Average loss: 3.6930
Iteration: 539; Percent complete: 13.5%; Average loss: 3.6875
Iteration: 540; Percent complete: 13.5%; Average loss: 3.6424
Iteration: 541; Percent complete: 13.5%; Average loss: 3.4391
Iteration: 542; Percent complete: 13.6%; Average loss: 3.7813
Iteration: 543; Percent complete: 13.6%; Average loss: 3.5158
Iteration: 544; Percent complete: 13.6%; Average loss: 3.6139
Iteration: 545; Percent complete: 13.6%; Average loss: 4.0003
Iteration: 546; Percent complete: 13.7%; Average loss: 3.7048
Iteration: 547; Percent complete: 13.7%; Average loss: 3.7784
Iteration: 548; Percent complete: 13.7%; Average loss: 3.6010
Iteration: 549; Percent complete: 13.7%; Average loss: 3.7491
Iteration: 550; Percent complete: 13.8%; Average loss: 3.6737
Iteration: 551; Percent complete: 13.8%; Average loss: 3.7342
Iteration: 552; Percent complete: 13.8%; Average loss: 3.8012
Iteration: 553; Percent complete: 13.8%; Average loss: 3.6688
Iteration: 554; Percent complete: 13.9%; Average loss: 3.8175
Iteration: 555; Percent complete: 13.9%; Average loss: 3.3496
Iteration: 556; Percent complete: 13.9%; Average loss: 3.9794
Iteration: 557; Percent complete: 13.9%; Average loss: 3.4588
Iteration: 558; Percent complete: 14.0%; Average loss: 3.6046
Iteration: 559; Percent complete: 14.0%; Average loss: 3.6086
Iteration: 560; Percent complete: 14.0%; Average loss: 3.5221
Iteration: 561; Percent complete: 14.0%; Average loss: 3.8503
Iteration: 562; Percent complete: 14.1%; Average loss: 3.6574
Iteration: 563; Percent complete: 14.1%; Average loss: 3.9696
Iteration: 564; Percent complete: 14.1%; Average loss: 3.6994
Iteration: 565; Percent complete: 14.1%; Average loss: 3.6610
Iteration: 566; Percent complete: 14.1%; Average loss: 3.8482
Iteration: 567; Percent complete: 14.2%; Average loss: 3.8236
Iteration: 568; Percent complete: 14.2%; Average loss: 3.6816
Iteration: 569; Percent complete: 14.2%; Average loss: 3.6662
Iteration: 570; Percent complete: 14.2%; Average loss: 3.4117
Iteration: 571; Percent complete: 14.3%; Average loss: 3.3914
Iteration: 572; Percent complete: 14.3%; Average loss: 3.8807
Iteration: 573; Percent complete: 14.3%; Average loss: 3.5650
Iteration: 574; Percent complete: 14.3%; Average loss: 3.7457
Iteration: 575; Percent complete: 14.4%; Average loss: 3.7577
Iteration: 576; Percent complete: 14.4%; Average loss: 3.7234
Iteration: 577; Percent complete: 14.4%; Average loss: 3.6049
Iteration: 578; Percent complete: 14.4%; Average loss: 3.8498
Iteration: 579; Percent complete: 14.5%; Average loss: 3.6847
Iteration: 580; Percent complete: 14.5%; Average loss: 3.6687
Iteration: 581; Percent complete: 14.5%; Average loss: 3.6371
Iteration: 582; Percent complete: 14.5%; Average loss: 3.7998
Iteration: 583; Percent complete: 14.6%; Average loss: 3.4707
Iteration: 584; Percent complete: 14.6%; Average loss: 3.6243
Iteration: 585; Percent complete: 14.6%; Average loss: 3.5212
Iteration: 586; Percent complete: 14.6%; Average loss: 3.7010
Iteration: 587; Percent complete: 14.7%; Average loss: 3.5703
Iteration: 588; Percent complete: 14.7%; Average loss: 3.8750
Iteration: 589; Percent complete: 14.7%; Average loss: 3.5823
Iteration: 590; Percent complete: 14.8%; Average loss: 3.6998
Iteration: 591; Percent complete: 14.8%; Average loss: 3.5026
Iteration: 592; Percent complete: 14.8%; Average loss: 3.6773
Iteration: 593; Percent complete: 14.8%; Average loss: 3.3856
Iteration: 594; Percent complete: 14.8%; Average loss: 3.5606
Iteration: 595; Percent complete: 14.9%; Average loss: 3.5777
Iteration: 596; Percent complete: 14.9%; Average loss: 3.9264
Iteration: 597; Percent complete: 14.9%; Average loss: 3.8755
Iteration: 598; Percent complete: 14.9%; Average loss: 3.8140
Iteration: 599; Percent complete: 15.0%; Average loss: 3.5909
Iteration: 600; Percent complete: 15.0%; Average loss: 3.4369
Iteration: 601; Percent complete: 15.0%; Average loss: 3.9030
Iteration: 602; Percent complete: 15.0%; Average loss: 3.5716
Iteration: 603; Percent complete: 15.1%; Average loss: 3.7163
Iteration: 604; Percent complete: 15.1%; Average loss: 3.8608
Iteration: 605; Percent complete: 15.1%; Average loss: 3.5056
Iteration: 606; Percent complete: 15.2%; Average loss: 3.6911
Iteration: 607; Percent complete: 15.2%; Average loss: 3.8124
Iteration: 608; Percent complete: 15.2%; Average loss: 3.6629
Iteration: 609; Percent complete: 15.2%; Average loss: 3.6384
Iteration: 610; Percent complete: 15.2%; Average loss: 3.7114
Iteration: 611; Percent complete: 15.3%; Average loss: 3.8014
Iteration: 612; Percent complete: 15.3%; Average loss: 3.6078
Iteration: 613; Percent complete: 15.3%; Average loss: 3.4315
Iteration: 614; Percent complete: 15.3%; Average loss: 3.5538
Iteration: 615; Percent complete: 15.4%; Average loss: 4.0976
Iteration: 616; Percent complete: 15.4%; Average loss: 3.7025
Iteration: 617; Percent complete: 15.4%; Average loss: 3.7462
Iteration: 618; Percent complete: 15.4%; Average loss: 3.7873
Iteration: 619; Percent complete: 15.5%; Average loss: 3.5007
Iteration: 620; Percent complete: 15.5%; Average loss: 3.5780
Iteration: 621; Percent complete: 15.5%; Average loss: 3.5091
Iteration: 622; Percent complete: 15.6%; Average loss: 3.8072
Iteration: 623; Percent complete: 15.6%; Average loss: 3.5295
Iteration: 624; Percent complete: 15.6%; Average loss: 3.3647
Iteration: 625; Percent complete: 15.6%; Average loss: 3.7141
Iteration: 626; Percent complete: 15.7%; Average loss: 3.9200
Iteration: 627; Percent complete: 15.7%; Average loss: 3.7087
Iteration: 628; Percent complete: 15.7%; Average loss: 3.4311
Iteration: 629; Percent complete: 15.7%; Average loss: 3.8228
Iteration: 630; Percent complete: 15.8%; Average loss: 3.8693
Iteration: 631; Percent complete: 15.8%; Average loss: 3.4289
Iteration: 632; Percent complete: 15.8%; Average loss: 3.8191
Iteration: 633; Percent complete: 15.8%; Average loss: 3.7956
Iteration: 634; Percent complete: 15.8%; Average loss: 4.0097
Iteration: 635; Percent complete: 15.9%; Average loss: 3.6917
Iteration: 636; Percent complete: 15.9%; Average loss: 3.5918
Iteration: 637; Percent complete: 15.9%; Average loss: 3.4137
Iteration: 638; Percent complete: 16.0%; Average loss: 3.4545
Iteration: 639; Percent complete: 16.0%; Average loss: 3.5923
Iteration: 640; Percent complete: 16.0%; Average loss: 3.4965
Iteration: 641; Percent complete: 16.0%; Average loss: 3.6546
Iteration: 642; Percent complete: 16.1%; Average loss: 3.6258
Iteration: 643; Percent complete: 16.1%; Average loss: 3.8003
Iteration: 644; Percent complete: 16.1%; Average loss: 3.4882
Iteration: 645; Percent complete: 16.1%; Average loss: 3.6592
Iteration: 646; Percent complete: 16.2%; Average loss: 3.5887
Iteration: 647; Percent complete: 16.2%; Average loss: 3.7669
Iteration: 648; Percent complete: 16.2%; Average loss: 3.6286
Iteration: 649; Percent complete: 16.2%; Average loss: 3.6328
Iteration: 650; Percent complete: 16.2%; Average loss: 3.4804
Iteration: 651; Percent complete: 16.3%; Average loss: 3.5114
Iteration: 652; Percent complete: 16.3%; Average loss: 3.8865
Iteration: 653; Percent complete: 16.3%; Average loss: 3.5723
Iteration: 654; Percent complete: 16.4%; Average loss: 3.8237
Iteration: 655; Percent complete: 16.4%; Average loss: 3.8019
Iteration: 656; Percent complete: 16.4%; Average loss: 3.7159
Iteration: 657; Percent complete: 16.4%; Average loss: 3.3461
Iteration: 658; Percent complete: 16.4%; Average loss: 3.5983
Iteration: 659; Percent complete: 16.5%; Average loss: 3.5048
Iteration: 660; Percent complete: 16.5%; Average loss: 3.8291
Iteration: 661; Percent complete: 16.5%; Average loss: 3.7856
Iteration: 662; Percent complete: 16.6%; Average loss: 3.6334
Iteration: 663; Percent complete: 16.6%; Average loss: 3.8066
Iteration: 664; Percent complete: 16.6%; Average loss: 3.4593
Iteration: 665; Percent complete: 16.6%; Average loss: 3.4958
Iteration: 666; Percent complete: 16.7%; Average loss: 3.3351
Iteration: 667; Percent complete: 16.7%; Average loss: 3.6960
Iteration: 668; Percent complete: 16.7%; Average loss: 3.6842
Iteration: 669; Percent complete: 16.7%; Average loss: 3.8627
Iteration: 670; Percent complete: 16.8%; Average loss: 3.6775
Iteration: 671; Percent complete: 16.8%; Average loss: 3.7298
Iteration: 672; Percent complete: 16.8%; Average loss: 3.4647
Iteration: 673; Percent complete: 16.8%; Average loss: 3.3942
Iteration: 674; Percent complete: 16.9%; Average loss: 3.9276
Iteration: 675; Percent complete: 16.9%; Average loss: 3.6693
Iteration: 676; Percent complete: 16.9%; Average loss: 3.6797
Iteration: 677; Percent complete: 16.9%; Average loss: 3.7429
Iteration: 678; Percent complete: 17.0%; Average loss: 3.8278
Iteration: 679; Percent complete: 17.0%; Average loss: 3.8523
Iteration: 680; Percent complete: 17.0%; Average loss: 3.6598
Iteration: 681; Percent complete: 17.0%; Average loss: 3.5800
Iteration: 682; Percent complete: 17.1%; Average loss: 3.8206
Iteration: 683; Percent complete: 17.1%; Average loss: 3.4254
Iteration: 684; Percent complete: 17.1%; Average loss: 3.7361
Iteration: 685; Percent complete: 17.1%; Average loss: 3.5785
Iteration: 686; Percent complete: 17.2%; Average loss: 3.5147
Iteration: 687; Percent complete: 17.2%; Average loss: 3.6552
Iteration: 688; Percent complete: 17.2%; Average loss: 3.4959
Iteration: 689; Percent complete: 17.2%; Average loss: 3.5813
Iteration: 690; Percent complete: 17.2%; Average loss: 3.6523
Iteration: 691; Percent complete: 17.3%; Average loss: 3.7074
Iteration: 692; Percent complete: 17.3%; Average loss: 3.5161
Iteration: 693; Percent complete: 17.3%; Average loss: 3.6601
Iteration: 694; Percent complete: 17.3%; Average loss: 3.5952
Iteration: 695; Percent complete: 17.4%; Average loss: 3.7429
Iteration: 696; Percent complete: 17.4%; Average loss: 3.5905
Iteration: 697; Percent complete: 17.4%; Average loss: 3.8225
Iteration: 698; Percent complete: 17.4%; Average loss: 3.5359
Iteration: 699; Percent complete: 17.5%; Average loss: 3.6634
Iteration: 700; Percent complete: 17.5%; Average loss: 3.3689
Iteration: 701; Percent complete: 17.5%; Average loss: 3.6367
Iteration: 702; Percent complete: 17.5%; Average loss: 3.3406
Iteration: 703; Percent complete: 17.6%; Average loss: 3.5143
Iteration: 704; Percent complete: 17.6%; Average loss: 3.6925
Iteration: 705; Percent complete: 17.6%; Average loss: 3.6842
Iteration: 706; Percent complete: 17.6%; Average loss: 3.4285
Iteration: 707; Percent complete: 17.7%; Average loss: 3.5443
Iteration: 708; Percent complete: 17.7%; Average loss: 3.4150
Iteration: 709; Percent complete: 17.7%; Average loss: 3.5995
Iteration: 710; Percent complete: 17.8%; Average loss: 3.6274
Iteration: 711; Percent complete: 17.8%; Average loss: 3.5795
Iteration: 712; Percent complete: 17.8%; Average loss: 3.5078
Iteration: 713; Percent complete: 17.8%; Average loss: 3.8686
Iteration: 714; Percent complete: 17.8%; Average loss: 3.3813
Iteration: 715; Percent complete: 17.9%; Average loss: 3.5310
Iteration: 716; Percent complete: 17.9%; Average loss: 3.3259
Iteration: 717; Percent complete: 17.9%; Average loss: 3.7382
Iteration: 718; Percent complete: 17.9%; Average loss: 3.6143
Iteration: 719; Percent complete: 18.0%; Average loss: 3.1545
Iteration: 720; Percent complete: 18.0%; Average loss: 3.7794
Iteration: 721; Percent complete: 18.0%; Average loss: 3.6446
Iteration: 722; Percent complete: 18.1%; Average loss: 3.4741
Iteration: 723; Percent complete: 18.1%; Average loss: 3.2853
Iteration: 724; Percent complete: 18.1%; Average loss: 3.4865
Iteration: 725; Percent complete: 18.1%; Average loss: 3.2853
Iteration: 726; Percent complete: 18.1%; Average loss: 3.5662
Iteration: 727; Percent complete: 18.2%; Average loss: 3.6966
Iteration: 728; Percent complete: 18.2%; Average loss: 3.5694
Iteration: 729; Percent complete: 18.2%; Average loss: 3.5183
Iteration: 730; Percent complete: 18.2%; Average loss: 3.6998
Iteration: 731; Percent complete: 18.3%; Average loss: 3.6042
Iteration: 732; Percent complete: 18.3%; Average loss: 3.4941
Iteration: 733; Percent complete: 18.3%; Average loss: 3.4955
Iteration: 734; Percent complete: 18.4%; Average loss: 3.2205
Iteration: 735; Percent complete: 18.4%; Average loss: 3.5977
Iteration: 736; Percent complete: 18.4%; Average loss: 3.7931
Iteration: 737; Percent complete: 18.4%; Average loss: 3.4473
Iteration: 738; Percent complete: 18.4%; Average loss: 3.5658
Iteration: 739; Percent complete: 18.5%; Average loss: 3.5194
Iteration: 740; Percent complete: 18.5%; Average loss: 3.5046
Iteration: 741; Percent complete: 18.5%; Average loss: 3.4083
Iteration: 742; Percent complete: 18.6%; Average loss: 3.6867
Iteration: 743; Percent complete: 18.6%; Average loss: 3.2977
Iteration: 744; Percent complete: 18.6%; Average loss: 4.0171
Iteration: 745; Percent complete: 18.6%; Average loss: 3.5290
Iteration: 746; Percent complete: 18.6%; Average loss: 3.8247
Iteration: 747; Percent complete: 18.7%; Average loss: 3.6692
Iteration: 748; Percent complete: 18.7%; Average loss: 3.4850
Iteration: 749; Percent complete: 18.7%; Average loss: 3.6337
Iteration: 750; Percent complete: 18.8%; Average loss: 3.4798
Iteration: 751; Percent complete: 18.8%; Average loss: 3.6789
Iteration: 752; Percent complete: 18.8%; Average loss: 3.6867
Iteration: 753; Percent complete: 18.8%; Average loss: 3.6455
Iteration: 754; Percent complete: 18.9%; Average loss: 3.4236
Iteration: 755; Percent complete: 18.9%; Average loss: 3.6748
Iteration: 756; Percent complete: 18.9%; Average loss: 3.5334
Iteration: 757; Percent complete: 18.9%; Average loss: 3.7983
Iteration: 758; Percent complete: 18.9%; Average loss: 3.4341
Iteration: 759; Percent complete: 19.0%; Average loss: 3.4889
Iteration: 760; Percent complete: 19.0%; Average loss: 3.6290
Iteration: 761; Percent complete: 19.0%; Average loss: 3.6854
Iteration: 762; Percent complete: 19.1%; Average loss: 3.1955
Iteration: 763; Percent complete: 19.1%; Average loss: 3.6312
Iteration: 764; Percent complete: 19.1%; Average loss: 3.7165
Iteration: 765; Percent complete: 19.1%; Average loss: 3.6576
Iteration: 766; Percent complete: 19.1%; Average loss: 3.4002
Iteration: 767; Percent complete: 19.2%; Average loss: 3.5289
Iteration: 768; Percent complete: 19.2%; Average loss: 3.7428
Iteration: 769; Percent complete: 19.2%; Average loss: 3.5122
Iteration: 770; Percent complete: 19.2%; Average loss: 3.6972
Iteration: 771; Percent complete: 19.3%; Average loss: 3.8040
Iteration: 772; Percent complete: 19.3%; Average loss: 3.7030
Iteration: 773; Percent complete: 19.3%; Average loss: 3.6061
Iteration: 774; Percent complete: 19.4%; Average loss: 3.5927
Iteration: 775; Percent complete: 19.4%; Average loss: 3.5479
Iteration: 776; Percent complete: 19.4%; Average loss: 3.6114
Iteration: 777; Percent complete: 19.4%; Average loss: 3.6431
Iteration: 778; Percent complete: 19.4%; Average loss: 3.5061
Iteration: 779; Percent complete: 19.5%; Average loss: 3.6290
Iteration: 780; Percent complete: 19.5%; Average loss: 3.5192
Iteration: 781; Percent complete: 19.5%; Average loss: 3.6444
Iteration: 782; Percent complete: 19.6%; Average loss: 3.3959
Iteration: 783; Percent complete: 19.6%; Average loss: 3.4529
Iteration: 784; Percent complete: 19.6%; Average loss: 3.6000
Iteration: 785; Percent complete: 19.6%; Average loss: 3.6877
Iteration: 786; Percent complete: 19.7%; Average loss: 3.5129
Iteration: 787; Percent complete: 19.7%; Average loss: 3.4775
Iteration: 788; Percent complete: 19.7%; Average loss: 3.2618
Iteration: 789; Percent complete: 19.7%; Average loss: 3.8633
Iteration: 790; Percent complete: 19.8%; Average loss: 3.7174
Iteration: 791; Percent complete: 19.8%; Average loss: 3.3068
Iteration: 792; Percent complete: 19.8%; Average loss: 3.5936
Iteration: 793; Percent complete: 19.8%; Average loss: 3.5675
Iteration: 794; Percent complete: 19.9%; Average loss: 3.3942
Iteration: 795; Percent complete: 19.9%; Average loss: 3.6092
Iteration: 796; Percent complete: 19.9%; Average loss: 3.5045
Iteration: 797; Percent complete: 19.9%; Average loss: 3.2829
Iteration: 798; Percent complete: 20.0%; Average loss: 3.5599
Iteration: 799; Percent complete: 20.0%; Average loss: 3.4254
Iteration: 800; Percent complete: 20.0%; Average loss: 3.4599
Iteration: 801; Percent complete: 20.0%; Average loss: 3.6175
Iteration: 802; Percent complete: 20.1%; Average loss: 3.5054
Iteration: 803; Percent complete: 20.1%; Average loss: 3.4125
Iteration: 804; Percent complete: 20.1%; Average loss: 3.7149
Iteration: 805; Percent complete: 20.1%; Average loss: 3.6753
Iteration: 806; Percent complete: 20.2%; Average loss: 3.7001
Iteration: 807; Percent complete: 20.2%; Average loss: 3.5722
Iteration: 808; Percent complete: 20.2%; Average loss: 3.6064
Iteration: 809; Percent complete: 20.2%; Average loss: 3.6690
Iteration: 810; Percent complete: 20.2%; Average loss: 3.3677
Iteration: 811; Percent complete: 20.3%; Average loss: 3.5187
Iteration: 812; Percent complete: 20.3%; Average loss: 3.5693
Iteration: 813; Percent complete: 20.3%; Average loss: 3.5616
Iteration: 814; Percent complete: 20.3%; Average loss: 3.5103
Iteration: 815; Percent complete: 20.4%; Average loss: 3.5304
Iteration: 816; Percent complete: 20.4%; Average loss: 3.4232
Iteration: 817; Percent complete: 20.4%; Average loss: 3.5692
Iteration: 818; Percent complete: 20.4%; Average loss: 3.8671
Iteration: 819; Percent complete: 20.5%; Average loss: 3.6525
Iteration: 820; Percent complete: 20.5%; Average loss: 3.3907
Iteration: 821; Percent complete: 20.5%; Average loss: 3.3271
Iteration: 822; Percent complete: 20.5%; Average loss: 3.9455
Iteration: 823; Percent complete: 20.6%; Average loss: 3.7826
Iteration: 824; Percent complete: 20.6%; Average loss: 3.6585
Iteration: 825; Percent complete: 20.6%; Average loss: 3.6320
Iteration: 826; Percent complete: 20.6%; Average loss: 3.3856
Iteration: 827; Percent complete: 20.7%; Average loss: 3.3246
Iteration: 828; Percent complete: 20.7%; Average loss: 3.2958
Iteration: 829; Percent complete: 20.7%; Average loss: 4.0321
Iteration: 830; Percent complete: 20.8%; Average loss: 3.8395
Iteration: 831; Percent complete: 20.8%; Average loss: 3.5166
Iteration: 832; Percent complete: 20.8%; Average loss: 3.5145
Iteration: 833; Percent complete: 20.8%; Average loss: 3.6956
Iteration: 834; Percent complete: 20.8%; Average loss: 3.6417
Iteration: 835; Percent complete: 20.9%; Average loss: 3.3920
Iteration: 836; Percent complete: 20.9%; Average loss: 3.4279
Iteration: 837; Percent complete: 20.9%; Average loss: 3.3509
Iteration: 838; Percent complete: 20.9%; Average loss: 3.4642
Iteration: 839; Percent complete: 21.0%; Average loss: 3.2938
Iteration: 840; Percent complete: 21.0%; Average loss: 3.3078
Iteration: 841; Percent complete: 21.0%; Average loss: 3.6151
Iteration: 842; Percent complete: 21.1%; Average loss: 3.5223
Iteration: 843; Percent complete: 21.1%; Average loss: 3.5927
Iteration: 844; Percent complete: 21.1%; Average loss: 3.7757
Iteration: 845; Percent complete: 21.1%; Average loss: 3.5131
Iteration: 846; Percent complete: 21.1%; Average loss: 3.4103
Iteration: 847; Percent complete: 21.2%; Average loss: 3.5920
Iteration: 848; Percent complete: 21.2%; Average loss: 3.8861
Iteration: 849; Percent complete: 21.2%; Average loss: 3.4884
Iteration: 850; Percent complete: 21.2%; Average loss: 3.2916
Iteration: 851; Percent complete: 21.3%; Average loss: 3.5920
Iteration: 852; Percent complete: 21.3%; Average loss: 3.3914
Iteration: 853; Percent complete: 21.3%; Average loss: 3.4206
Iteration: 854; Percent complete: 21.3%; Average loss: 3.4730
Iteration: 855; Percent complete: 21.4%; Average loss: 3.7381
Iteration: 856; Percent complete: 21.4%; Average loss: 3.6839
Iteration: 857; Percent complete: 21.4%; Average loss: 3.3600
Iteration: 858; Percent complete: 21.4%; Average loss: 3.2919
Iteration: 859; Percent complete: 21.5%; Average loss: 3.7279
Iteration: 860; Percent complete: 21.5%; Average loss: 3.8020
Iteration: 861; Percent complete: 21.5%; Average loss: 3.6494
Iteration: 862; Percent complete: 21.6%; Average loss: 3.6777
Iteration: 863; Percent complete: 21.6%; Average loss: 3.4284
Iteration: 864; Percent complete: 21.6%; Average loss: 3.4051
Iteration: 865; Percent complete: 21.6%; Average loss: 3.3563
Iteration: 866; Percent complete: 21.6%; Average loss: 3.3445
Iteration: 867; Percent complete: 21.7%; Average loss: 3.5496
Iteration: 868; Percent complete: 21.7%; Average loss: 3.6451
Iteration: 869; Percent complete: 21.7%; Average loss: 3.5275
Iteration: 870; Percent complete: 21.8%; Average loss: 3.5792
Iteration: 871; Percent complete: 21.8%; Average loss: 3.3439
Iteration: 872; Percent complete: 21.8%; Average loss: 3.6119
Iteration: 873; Percent complete: 21.8%; Average loss: 3.5167
Iteration: 874; Percent complete: 21.9%; Average loss: 3.3495
Iteration: 875; Percent complete: 21.9%; Average loss: 3.4796
Iteration: 876; Percent complete: 21.9%; Average loss: 3.6945
Iteration: 877; Percent complete: 21.9%; Average loss: 3.5594
Iteration: 878; Percent complete: 21.9%; Average loss: 3.6370
Iteration: 879; Percent complete: 22.0%; Average loss: 3.5919
Iteration: 880; Percent complete: 22.0%; Average loss: 3.6127
Iteration: 881; Percent complete: 22.0%; Average loss: 3.3113
Iteration: 882; Percent complete: 22.1%; Average loss: 3.4357
Iteration: 883; Percent complete: 22.1%; Average loss: 3.6136
Iteration: 884; Percent complete: 22.1%; Average loss: 3.4578
Iteration: 885; Percent complete: 22.1%; Average loss: 3.5339
Iteration: 886; Percent complete: 22.1%; Average loss: 3.3638
Iteration: 887; Percent complete: 22.2%; Average loss: 3.4294
Iteration: 888; Percent complete: 22.2%; Average loss: 3.6419
Iteration: 889; Percent complete: 22.2%; Average loss: 3.3993
Iteration: 890; Percent complete: 22.2%; Average loss: 3.7105
Iteration: 891; Percent complete: 22.3%; Average loss: 3.4253
Iteration: 892; Percent complete: 22.3%; Average loss: 3.7279
Iteration: 893; Percent complete: 22.3%; Average loss: 3.4512
Iteration: 894; Percent complete: 22.4%; Average loss: 3.7204
Iteration: 895; Percent complete: 22.4%; Average loss: 3.5283
Iteration: 896; Percent complete: 22.4%; Average loss: 3.3892
Iteration: 897; Percent complete: 22.4%; Average loss: 3.5199
Iteration: 898; Percent complete: 22.4%; Average loss: 3.3954
Iteration: 899; Percent complete: 22.5%; Average loss: 3.5539
Iteration: 900; Percent complete: 22.5%; Average loss: 3.4421
Iteration: 901; Percent complete: 22.5%; Average loss: 3.6336
Iteration: 902; Percent complete: 22.6%; Average loss: 3.7759
Iteration: 903; Percent complete: 22.6%; Average loss: 3.4099
Iteration: 904; Percent complete: 22.6%; Average loss: 3.6749
Iteration: 905; Percent complete: 22.6%; Average loss: 3.7969
Iteration: 906; Percent complete: 22.7%; Average loss: 3.4689
Iteration: 907; Percent complete: 22.7%; Average loss: 3.4663
Iteration: 908; Percent complete: 22.7%; Average loss: 3.6163
Iteration: 909; Percent complete: 22.7%; Average loss: 3.6292
Iteration: 910; Percent complete: 22.8%; Average loss: 3.6447
Iteration: 911; Percent complete: 22.8%; Average loss: 3.2344
Iteration: 912; Percent complete: 22.8%; Average loss: 3.2370
Iteration: 913; Percent complete: 22.8%; Average loss: 3.4605
Iteration: 914; Percent complete: 22.9%; Average loss: 3.3008
Iteration: 915; Percent complete: 22.9%; Average loss: 3.5109
Iteration: 916; Percent complete: 22.9%; Average loss: 3.5321
Iteration: 917; Percent complete: 22.9%; Average loss: 3.5228
Iteration: 918; Percent complete: 22.9%; Average loss: 3.4677
Iteration: 919; Percent complete: 23.0%; Average loss: 3.4179
Iteration: 920; Percent complete: 23.0%; Average loss: 3.4971
Iteration: 921; Percent complete: 23.0%; Average loss: 3.2841
Iteration: 922; Percent complete: 23.1%; Average loss: 3.4898
Iteration: 923; Percent complete: 23.1%; Average loss: 3.4973
Iteration: 924; Percent complete: 23.1%; Average loss: 3.4052
Iteration: 925; Percent complete: 23.1%; Average loss: 3.6709
Iteration: 926; Percent complete: 23.2%; Average loss: 3.6052
Iteration: 927; Percent complete: 23.2%; Average loss: 3.5663
Iteration: 928; Percent complete: 23.2%; Average loss: 3.6795
Iteration: 929; Percent complete: 23.2%; Average loss: 3.5629
Iteration: 930; Percent complete: 23.2%; Average loss: 3.2213
Iteration: 931; Percent complete: 23.3%; Average loss: 3.6367
Iteration: 932; Percent complete: 23.3%; Average loss: 3.3947
Iteration: 933; Percent complete: 23.3%; Average loss: 3.7016
Iteration: 934; Percent complete: 23.4%; Average loss: 4.0185
Iteration: 935; Percent complete: 23.4%; Average loss: 3.4051
Iteration: 936; Percent complete: 23.4%; Average loss: 3.5441
Iteration: 937; Percent complete: 23.4%; Average loss: 3.5705
Iteration: 938; Percent complete: 23.4%; Average loss: 3.5357
Iteration: 939; Percent complete: 23.5%; Average loss: 3.5797
Iteration: 940; Percent complete: 23.5%; Average loss: 3.4606
Iteration: 941; Percent complete: 23.5%; Average loss: 3.5793
Iteration: 942; Percent complete: 23.5%; Average loss: 3.5003
Iteration: 943; Percent complete: 23.6%; Average loss: 3.4197
Iteration: 944; Percent complete: 23.6%; Average loss: 3.1522
Iteration: 945; Percent complete: 23.6%; Average loss: 3.8001
Iteration: 946; Percent complete: 23.6%; Average loss: 3.5623
Iteration: 947; Percent complete: 23.7%; Average loss: 3.4104
Iteration: 948; Percent complete: 23.7%; Average loss: 3.5652
Iteration: 949; Percent complete: 23.7%; Average loss: 3.2307
Iteration: 950; Percent complete: 23.8%; Average loss: 3.5895
Iteration: 951; Percent complete: 23.8%; Average loss: 3.4740
Iteration: 952; Percent complete: 23.8%; Average loss: 3.5870
Iteration: 953; Percent complete: 23.8%; Average loss: 3.4771
Iteration: 954; Percent complete: 23.8%; Average loss: 3.7522
Iteration: 955; Percent complete: 23.9%; Average loss: 3.2247
Iteration: 956; Percent complete: 23.9%; Average loss: 3.6205
Iteration: 957; Percent complete: 23.9%; Average loss: 3.3319
Iteration: 958; Percent complete: 23.9%; Average loss: 3.2852
Iteration: 959; Percent complete: 24.0%; Average loss: 3.6311
Iteration: 960; Percent complete: 24.0%; Average loss: 3.2940
Iteration: 961; Percent complete: 24.0%; Average loss: 3.5623
Iteration: 962; Percent complete: 24.1%; Average loss: 3.7793
Iteration: 963; Percent complete: 24.1%; Average loss: 3.3388
Iteration: 964; Percent complete: 24.1%; Average loss: 3.5835
Iteration: 965; Percent complete: 24.1%; Average loss: 3.6042
Iteration: 966; Percent complete: 24.1%; Average loss: 3.6115
Iteration: 967; Percent complete: 24.2%; Average loss: 3.5618
Iteration: 968; Percent complete: 24.2%; Average loss: 3.5665
Iteration: 969; Percent complete: 24.2%; Average loss: 3.6532
Iteration: 970; Percent complete: 24.2%; Average loss: 3.2969
Iteration: 971; Percent complete: 24.3%; Average loss: 3.4011
Iteration: 972; Percent complete: 24.3%; Average loss: 3.4558
Iteration: 973; Percent complete: 24.3%; Average loss: 3.7898
Iteration: 974; Percent complete: 24.3%; Average loss: 3.7102
Iteration: 975; Percent complete: 24.4%; Average loss: 3.4862
Iteration: 976; Percent complete: 24.4%; Average loss: 3.2615
Iteration: 977; Percent complete: 24.4%; Average loss: 3.2486
Iteration: 978; Percent complete: 24.4%; Average loss: 3.5089
Iteration: 979; Percent complete: 24.5%; Average loss: 3.6713
Iteration: 980; Percent complete: 24.5%; Average loss: 3.5465
Iteration: 981; Percent complete: 24.5%; Average loss: 3.8432
Iteration: 982; Percent complete: 24.6%; Average loss: 3.4477
Iteration: 983; Percent complete: 24.6%; Average loss: 3.6911
Iteration: 984; Percent complete: 24.6%; Average loss: 3.5928
Iteration: 985; Percent complete: 24.6%; Average loss: 3.6246
Iteration: 986; Percent complete: 24.6%; Average loss: 3.7299
Iteration: 987; Percent complete: 24.7%; Average loss: 3.6409
Iteration: 988; Percent complete: 24.7%; Average loss: 3.6712
Iteration: 989; Percent complete: 24.7%; Average loss: 3.3114
Iteration: 990; Percent complete: 24.8%; Average loss: 3.3227
Iteration: 991; Percent complete: 24.8%; Average loss: 3.3279
Iteration: 992; Percent complete: 24.8%; Average loss: 3.2483
Iteration: 993; Percent complete: 24.8%; Average loss: 3.3183
Iteration: 994; Percent complete: 24.9%; Average loss: 3.3163
Iteration: 995; Percent complete: 24.9%; Average loss: 3.4955
Iteration: 996; Percent complete: 24.9%; Average loss: 3.5789
Iteration: 997; Percent complete: 24.9%; Average loss: 3.4565
Iteration: 998; Percent complete: 24.9%; Average loss: 3.6388
Iteration: 999; Percent complete: 25.0%; Average loss: 3.3603
Iteration: 1000; Percent complete: 25.0%; Average loss: 3.4548
Iteration: 1001; Percent complete: 25.0%; Average loss: 3.2867
Iteration: 1002; Percent complete: 25.1%; Average loss: 3.3617
Iteration: 1003; Percent complete: 25.1%; Average loss: 3.3609
Iteration: 1004; Percent complete: 25.1%; Average loss: 3.5119
Iteration: 1005; Percent complete: 25.1%; Average loss: 3.3823
Iteration: 1006; Percent complete: 25.1%; Average loss: 3.4620
Iteration: 1007; Percent complete: 25.2%; Average loss: 3.3487
Iteration: 1008; Percent complete: 25.2%; Average loss: 3.4509
Iteration: 1009; Percent complete: 25.2%; Average loss: 3.2853
Iteration: 1010; Percent complete: 25.2%; Average loss: 3.4922
Iteration: 1011; Percent complete: 25.3%; Average loss: 3.4301
Iteration: 1012; Percent complete: 25.3%; Average loss: 3.2980
Iteration: 1013; Percent complete: 25.3%; Average loss: 3.6335
Iteration: 1014; Percent complete: 25.4%; Average loss: 3.6488
Iteration: 1015; Percent complete: 25.4%; Average loss: 3.4789
Iteration: 1016; Percent complete: 25.4%; Average loss: 3.6074
Iteration: 1017; Percent complete: 25.4%; Average loss: 3.7262
Iteration: 1018; Percent complete: 25.4%; Average loss: 3.3425
Iteration: 1019; Percent complete: 25.5%; Average loss: 3.1063
Iteration: 1020; Percent complete: 25.5%; Average loss: 3.4742
Iteration: 1021; Percent complete: 25.5%; Average loss: 3.3213
Iteration: 1022; Percent complete: 25.6%; Average loss: 3.3051
Iteration: 1023; Percent complete: 25.6%; Average loss: 3.2463
Iteration: 1024; Percent complete: 25.6%; Average loss: 3.5758
Iteration: 1025; Percent complete: 25.6%; Average loss: 3.3897
Iteration: 1026; Percent complete: 25.7%; Average loss: 3.4407
Iteration: 1027; Percent complete: 25.7%; Average loss: 3.3621
Iteration: 1028; Percent complete: 25.7%; Average loss: 3.3521
Iteration: 1029; Percent complete: 25.7%; Average loss: 3.4299
Iteration: 1030; Percent complete: 25.8%; Average loss: 3.3599
Iteration: 1031; Percent complete: 25.8%; Average loss: 3.5505
Iteration: 1032; Percent complete: 25.8%; Average loss: 3.3801
Iteration: 1033; Percent complete: 25.8%; Average loss: 3.4702
Iteration: 1034; Percent complete: 25.9%; Average loss: 3.7960
Iteration: 1035; Percent complete: 25.9%; Average loss: 3.2438
Iteration: 1036; Percent complete: 25.9%; Average loss: 3.1762
Iteration: 1037; Percent complete: 25.9%; Average loss: 3.4994
Iteration: 1038; Percent complete: 25.9%; Average loss: 3.4640
Iteration: 1039; Percent complete: 26.0%; Average loss: 3.5689
Iteration: 1040; Percent complete: 26.0%; Average loss: 3.2876
Iteration: 1041; Percent complete: 26.0%; Average loss: 3.5872
Iteration: 1042; Percent complete: 26.1%; Average loss: 3.2976
Iteration: 1043; Percent complete: 26.1%; Average loss: 3.4157
Iteration: 1044; Percent complete: 26.1%; Average loss: 3.4484
Iteration: 1045; Percent complete: 26.1%; Average loss: 3.5871
Iteration: 1046; Percent complete: 26.2%; Average loss: 3.5001
Iteration: 1047; Percent complete: 26.2%; Average loss: 3.5523
Iteration: 1048; Percent complete: 26.2%; Average loss: 3.3578
Iteration: 1049; Percent complete: 26.2%; Average loss: 3.7554
Iteration: 1050; Percent complete: 26.2%; Average loss: 3.8685
Iteration: 1051; Percent complete: 26.3%; Average loss: 3.3891
Iteration: 1052; Percent complete: 26.3%; Average loss: 3.6778
Iteration: 1053; Percent complete: 26.3%; Average loss: 3.8468
Iteration: 1054; Percent complete: 26.4%; Average loss: 3.7080
Iteration: 1055; Percent complete: 26.4%; Average loss: 3.4768
Iteration: 1056; Percent complete: 26.4%; Average loss: 3.7953
Iteration: 1057; Percent complete: 26.4%; Average loss: 3.1755
Iteration: 1058; Percent complete: 26.5%; Average loss: 3.6643
Iteration: 1059; Percent complete: 26.5%; Average loss: 3.6391
Iteration: 1060; Percent complete: 26.5%; Average loss: 3.5675
Iteration: 1061; Percent complete: 26.5%; Average loss: 3.2642
Iteration: 1062; Percent complete: 26.6%; Average loss: 3.6157
Iteration: 1063; Percent complete: 26.6%; Average loss: 3.5255
Iteration: 1064; Percent complete: 26.6%; Average loss: 3.6690
Iteration: 1065; Percent complete: 26.6%; Average loss: 3.3706
Iteration: 1066; Percent complete: 26.7%; Average loss: 3.3929
Iteration: 1067; Percent complete: 26.7%; Average loss: 3.3588
Iteration: 1068; Percent complete: 26.7%; Average loss: 3.2778
Iteration: 1069; Percent complete: 26.7%; Average loss: 3.6179
Iteration: 1070; Percent complete: 26.8%; Average loss: 3.5936
Iteration: 1071; Percent complete: 26.8%; Average loss: 3.7091
Iteration: 1072; Percent complete: 26.8%; Average loss: 3.5014
Iteration: 1073; Percent complete: 26.8%; Average loss: 3.3331
Iteration: 1074; Percent complete: 26.9%; Average loss: 3.5231
Iteration: 1075; Percent complete: 26.9%; Average loss: 3.6121
Iteration: 1076; Percent complete: 26.9%; Average loss: 3.7340
Iteration: 1077; Percent complete: 26.9%; Average loss: 3.4594
Iteration: 1078; Percent complete: 27.0%; Average loss: 3.6394
Iteration: 1079; Percent complete: 27.0%; Average loss: 3.5605
Iteration: 1080; Percent complete: 27.0%; Average loss: 3.5799
Iteration: 1081; Percent complete: 27.0%; Average loss: 3.6012
Iteration: 1082; Percent complete: 27.1%; Average loss: 3.1943
Iteration: 1083; Percent complete: 27.1%; Average loss: 3.3373
Iteration: 1084; Percent complete: 27.1%; Average loss: 3.8870
Iteration: 1085; Percent complete: 27.1%; Average loss: 3.3998
Iteration: 1086; Percent complete: 27.2%; Average loss: 3.5472
Iteration: 1087; Percent complete: 27.2%; Average loss: 3.3007
Iteration: 1088; Percent complete: 27.2%; Average loss: 3.4421
Iteration: 1089; Percent complete: 27.2%; Average loss: 3.2649
Iteration: 1090; Percent complete: 27.3%; Average loss: 3.4051
Iteration: 1091; Percent complete: 27.3%; Average loss: 3.4100
Iteration: 1092; Percent complete: 27.3%; Average loss: 3.3702
Iteration: 1093; Percent complete: 27.3%; Average loss: 3.3966
Iteration: 1094; Percent complete: 27.4%; Average loss: 3.3942
Iteration: 1095; Percent complete: 27.4%; Average loss: 3.4173
Iteration: 1096; Percent complete: 27.4%; Average loss: 3.4266
Iteration: 1097; Percent complete: 27.4%; Average loss: 3.4455
Iteration: 1098; Percent complete: 27.5%; Average loss: 3.4569
Iteration: 1099; Percent complete: 27.5%; Average loss: 3.5104
Iteration: 1100; Percent complete: 27.5%; Average loss: 3.7834
Iteration: 1101; Percent complete: 27.5%; Average loss: 3.3699
Iteration: 1102; Percent complete: 27.6%; Average loss: 3.1456
Iteration: 1103; Percent complete: 27.6%; Average loss: 3.5037
Iteration: 1104; Percent complete: 27.6%; Average loss: 3.6351
Iteration: 1105; Percent complete: 27.6%; Average loss: 3.5245
Iteration: 1106; Percent complete: 27.7%; Average loss: 3.4391
Iteration: 1107; Percent complete: 27.7%; Average loss: 3.4972
Iteration: 1108; Percent complete: 27.7%; Average loss: 3.4870
Iteration: 1109; Percent complete: 27.7%; Average loss: 3.2390
Iteration: 1110; Percent complete: 27.8%; Average loss: 3.6867
Iteration: 1111; Percent complete: 27.8%; Average loss: 3.3055
Iteration: 1112; Percent complete: 27.8%; Average loss: 3.4601
Iteration: 1113; Percent complete: 27.8%; Average loss: 3.3814
Iteration: 1114; Percent complete: 27.9%; Average loss: 3.1821
Iteration: 1115; Percent complete: 27.9%; Average loss: 3.5797
Iteration: 1116; Percent complete: 27.9%; Average loss: 3.5715
Iteration: 1117; Percent complete: 27.9%; Average loss: 3.2922
Iteration: 1118; Percent complete: 28.0%; Average loss: 3.4026
Iteration: 1119; Percent complete: 28.0%; Average loss: 3.3459
Iteration: 1120; Percent complete: 28.0%; Average loss: 3.3743
Iteration: 1121; Percent complete: 28.0%; Average loss: 3.3946
Iteration: 1122; Percent complete: 28.1%; Average loss: 3.5134
Iteration: 1123; Percent complete: 28.1%; Average loss: 3.6111
Iteration: 1124; Percent complete: 28.1%; Average loss: 3.4610
Iteration: 1125; Percent complete: 28.1%; Average loss: 3.6592
Iteration: 1126; Percent complete: 28.1%; Average loss: 3.5029
Iteration: 1127; Percent complete: 28.2%; Average loss: 3.6148
Iteration: 1128; Percent complete: 28.2%; Average loss: 3.5672
Iteration: 1129; Percent complete: 28.2%; Average loss: 3.1095
Iteration: 1130; Percent complete: 28.2%; Average loss: 3.5365
Iteration: 1131; Percent complete: 28.3%; Average loss: 3.2473
Iteration: 1132; Percent complete: 28.3%; Average loss: 3.3726
Iteration: 1133; Percent complete: 28.3%; Average loss: 3.4661
Iteration: 1134; Percent complete: 28.3%; Average loss: 3.5201
Iteration: 1135; Percent complete: 28.4%; Average loss: 3.3933
Iteration: 1136; Percent complete: 28.4%; Average loss: 3.3348
Iteration: 1137; Percent complete: 28.4%; Average loss: 3.2511
Iteration: 1138; Percent complete: 28.4%; Average loss: 3.4730
Iteration: 1139; Percent complete: 28.5%; Average loss: 3.5647
Iteration: 1140; Percent complete: 28.5%; Average loss: 3.5916
Iteration: 1141; Percent complete: 28.5%; Average loss: 3.5995
Iteration: 1142; Percent complete: 28.5%; Average loss: 3.4693
Iteration: 1143; Percent complete: 28.6%; Average loss: 3.3370
Iteration: 1144; Percent complete: 28.6%; Average loss: 3.4666
Iteration: 1145; Percent complete: 28.6%; Average loss: 3.2944
Iteration: 1146; Percent complete: 28.6%; Average loss: 3.5599
Iteration: 1147; Percent complete: 28.7%; Average loss: 3.4139
Iteration: 1148; Percent complete: 28.7%; Average loss: 3.3178
Iteration: 1149; Percent complete: 28.7%; Average loss: 3.2732
Iteration: 1150; Percent complete: 28.7%; Average loss: 3.4332
Iteration: 1151; Percent complete: 28.8%; Average loss: 3.6489
Iteration: 1152; Percent complete: 28.8%; Average loss: 3.3424
Iteration: 1153; Percent complete: 28.8%; Average loss: 3.3944
Iteration: 1154; Percent complete: 28.8%; Average loss: 3.2307
Iteration: 1155; Percent complete: 28.9%; Average loss: 3.2652
Iteration: 1156; Percent complete: 28.9%; Average loss: 3.2606
Iteration: 1157; Percent complete: 28.9%; Average loss: 3.5040
Iteration: 1158; Percent complete: 28.9%; Average loss: 3.3676
Iteration: 1159; Percent complete: 29.0%; Average loss: 3.5117
Iteration: 1160; Percent complete: 29.0%; Average loss: 3.2271
Iteration: 1161; Percent complete: 29.0%; Average loss: 3.8758
Iteration: 1162; Percent complete: 29.0%; Average loss: 3.2797
Iteration: 1163; Percent complete: 29.1%; Average loss: 3.5964
Iteration: 1164; Percent complete: 29.1%; Average loss: 3.3994
Iteration: 1165; Percent complete: 29.1%; Average loss: 3.4783
Iteration: 1166; Percent complete: 29.1%; Average loss: 2.9819
Iteration: 1167; Percent complete: 29.2%; Average loss: 3.3562
Iteration: 1168; Percent complete: 29.2%; Average loss: 3.4636
Iteration: 1169; Percent complete: 29.2%; Average loss: 3.2531
Iteration: 1170; Percent complete: 29.2%; Average loss: 3.4576
Iteration: 1171; Percent complete: 29.3%; Average loss: 3.3938
Iteration: 1172; Percent complete: 29.3%; Average loss: 3.3472
Iteration: 1173; Percent complete: 29.3%; Average loss: 3.2537
Iteration: 1174; Percent complete: 29.3%; Average loss: 3.4916
Iteration: 1175; Percent complete: 29.4%; Average loss: 3.3859
Iteration: 1176; Percent complete: 29.4%; Average loss: 3.1454
Iteration: 1177; Percent complete: 29.4%; Average loss: 3.4638
Iteration: 1178; Percent complete: 29.4%; Average loss: 3.4266
Iteration: 1179; Percent complete: 29.5%; Average loss: 3.2244
Iteration: 1180; Percent complete: 29.5%; Average loss: 3.3497
Iteration: 1181; Percent complete: 29.5%; Average loss: 3.2832
Iteration: 1182; Percent complete: 29.5%; Average loss: 3.5991
Iteration: 1183; Percent complete: 29.6%; Average loss: 3.3359
Iteration: 1184; Percent complete: 29.6%; Average loss: 3.5834
Iteration: 1185; Percent complete: 29.6%; Average loss: 3.3835
Iteration: 1186; Percent complete: 29.6%; Average loss: 3.1769
Iteration: 1187; Percent complete: 29.7%; Average loss: 3.2822
Iteration: 1188; Percent complete: 29.7%; Average loss: 3.5365
Iteration: 1189; Percent complete: 29.7%; Average loss: 3.2111
Iteration: 1190; Percent complete: 29.8%; Average loss: 3.1375
Iteration: 1191; Percent complete: 29.8%; Average loss: 3.1108
Iteration: 1192; Percent complete: 29.8%; Average loss: 3.4758
Iteration: 1193; Percent complete: 29.8%; Average loss: 3.4786
Iteration: 1194; Percent complete: 29.8%; Average loss: 3.5638
Iteration: 1195; Percent complete: 29.9%; Average loss: 3.4687
Iteration: 1196; Percent complete: 29.9%; Average loss: 3.5200
Iteration: 1197; Percent complete: 29.9%; Average loss: 3.2057
Iteration: 1198; Percent complete: 29.9%; Average loss: 3.4139
Iteration: 1199; Percent complete: 30.0%; Average loss: 3.4093
Iteration: 1200; Percent complete: 30.0%; Average loss: 3.3150
Iteration: 1201; Percent complete: 30.0%; Average loss: 3.3717
Iteration: 1202; Percent complete: 30.0%; Average loss: 3.4793
Iteration: 1203; Percent complete: 30.1%; Average loss: 3.4634
Iteration: 1204; Percent complete: 30.1%; Average loss: 3.3121
Iteration: 1205; Percent complete: 30.1%; Average loss: 3.5753
Iteration: 1206; Percent complete: 30.1%; Average loss: 3.5452
Iteration: 1207; Percent complete: 30.2%; Average loss: 3.3289
Iteration: 1208; Percent complete: 30.2%; Average loss: 3.6163
Iteration: 1209; Percent complete: 30.2%; Average loss: 3.5076
Iteration: 1210; Percent complete: 30.2%; Average loss: 3.3484
Iteration: 1211; Percent complete: 30.3%; Average loss: 3.2458
Iteration: 1212; Percent complete: 30.3%; Average loss: 2.9291
Iteration: 1213; Percent complete: 30.3%; Average loss: 3.3303
Iteration: 1214; Percent complete: 30.3%; Average loss: 3.3343
Iteration: 1215; Percent complete: 30.4%; Average loss: 3.2602
Iteration: 1216; Percent complete: 30.4%; Average loss: 3.6849
Iteration: 1217; Percent complete: 30.4%; Average loss: 3.4303
Iteration: 1218; Percent complete: 30.4%; Average loss: 3.3981
Iteration: 1219; Percent complete: 30.5%; Average loss: 3.4759
Iteration: 1220; Percent complete: 30.5%; Average loss: 3.5010
Iteration: 1221; Percent complete: 30.5%; Average loss: 3.2210
Iteration: 1222; Percent complete: 30.6%; Average loss: 3.3957
Iteration: 1223; Percent complete: 30.6%; Average loss: 3.5280
Iteration: 1224; Percent complete: 30.6%; Average loss: 3.3877
Iteration: 1225; Percent complete: 30.6%; Average loss: 3.2998
Iteration: 1226; Percent complete: 30.6%; Average loss: 3.3731
Iteration: 1227; Percent complete: 30.7%; Average loss: 3.2689
Iteration: 1228; Percent complete: 30.7%; Average loss: 3.2714
Iteration: 1229; Percent complete: 30.7%; Average loss: 3.5459
Iteration: 1230; Percent complete: 30.8%; Average loss: 3.4216
Iteration: 1231; Percent complete: 30.8%; Average loss: 3.2552
Iteration: 1232; Percent complete: 30.8%; Average loss: 3.3596
Iteration: 1233; Percent complete: 30.8%; Average loss: 3.5056
Iteration: 1234; Percent complete: 30.9%; Average loss: 3.2234
Iteration: 1235; Percent complete: 30.9%; Average loss: 3.4651
Iteration: 1236; Percent complete: 30.9%; Average loss: 3.3257
Iteration: 1237; Percent complete: 30.9%; Average loss: 3.2370
Iteration: 1238; Percent complete: 30.9%; Average loss: 3.3546
Iteration: 1239; Percent complete: 31.0%; Average loss: 3.1612
Iteration: 1240; Percent complete: 31.0%; Average loss: 3.3674
Iteration: 1241; Percent complete: 31.0%; Average loss: 3.2331
Iteration: 1242; Percent complete: 31.1%; Average loss: 3.8040
Iteration: 1243; Percent complete: 31.1%; Average loss: 3.4495
Iteration: 1244; Percent complete: 31.1%; Average loss: 3.2709
Iteration: 1245; Percent complete: 31.1%; Average loss: 3.5323
Iteration: 1246; Percent complete: 31.1%; Average loss: 3.4986
Iteration: 1247; Percent complete: 31.2%; Average loss: 3.4936
Iteration: 1248; Percent complete: 31.2%; Average loss: 3.6521
Iteration: 1249; Percent complete: 31.2%; Average loss: 3.2507
Iteration: 1250; Percent complete: 31.2%; Average loss: 3.3323
Iteration: 1251; Percent complete: 31.3%; Average loss: 3.4249
Iteration: 1252; Percent complete: 31.3%; Average loss: 3.3161
Iteration: 1253; Percent complete: 31.3%; Average loss: 3.3895
Iteration: 1254; Percent complete: 31.4%; Average loss: 3.1340
Iteration: 1255; Percent complete: 31.4%; Average loss: 3.3265
Iteration: 1256; Percent complete: 31.4%; Average loss: 3.3542
Iteration: 1257; Percent complete: 31.4%; Average loss: 3.7028
Iteration: 1258; Percent complete: 31.4%; Average loss: 3.3781
Iteration: 1259; Percent complete: 31.5%; Average loss: 3.1335
Iteration: 1260; Percent complete: 31.5%; Average loss: 3.3598
Iteration: 1261; Percent complete: 31.5%; Average loss: 3.2698
Iteration: 1262; Percent complete: 31.6%; Average loss: 3.2759
Iteration: 1263; Percent complete: 31.6%; Average loss: 3.2719
Iteration: 1264; Percent complete: 31.6%; Average loss: 3.2332
Iteration: 1265; Percent complete: 31.6%; Average loss: 3.4713
Iteration: 1266; Percent complete: 31.6%; Average loss: 3.5247
Iteration: 1267; Percent complete: 31.7%; Average loss: 3.3273
Iteration: 1268; Percent complete: 31.7%; Average loss: 3.4274
Iteration: 1269; Percent complete: 31.7%; Average loss: 3.5504
Iteration: 1270; Percent complete: 31.8%; Average loss: 3.6867
Iteration: 1271; Percent complete: 31.8%; Average loss: 3.5317
Iteration: 1272; Percent complete: 31.8%; Average loss: 3.2871
Iteration: 1273; Percent complete: 31.8%; Average loss: 3.4216
Iteration: 1274; Percent complete: 31.9%; Average loss: 3.3848
Iteration: 1275; Percent complete: 31.9%; Average loss: 3.4436
Iteration: 1276; Percent complete: 31.9%; Average loss: 3.2870
Iteration: 1277; Percent complete: 31.9%; Average loss: 3.4743
Iteration: 1278; Percent complete: 31.9%; Average loss: 3.1625
Iteration: 1279; Percent complete: 32.0%; Average loss: 3.5047
Iteration: 1280; Percent complete: 32.0%; Average loss: 3.4031
Iteration: 1281; Percent complete: 32.0%; Average loss: 3.1676
Iteration: 1282; Percent complete: 32.0%; Average loss: 3.3681
Iteration: 1283; Percent complete: 32.1%; Average loss: 3.3364
Iteration: 1284; Percent complete: 32.1%; Average loss: 3.4215
Iteration: 1285; Percent complete: 32.1%; Average loss: 3.5260
Iteration: 1286; Percent complete: 32.1%; Average loss: 3.2290
Iteration: 1287; Percent complete: 32.2%; Average loss: 3.4819
Iteration: 1288; Percent complete: 32.2%; Average loss: 3.6096
Iteration: 1289; Percent complete: 32.2%; Average loss: 3.4259
Iteration: 1290; Percent complete: 32.2%; Average loss: 3.3375
Iteration: 1291; Percent complete: 32.3%; Average loss: 3.4419
Iteration: 1292; Percent complete: 32.3%; Average loss: 3.4965
Iteration: 1293; Percent complete: 32.3%; Average loss: 3.3510
Iteration: 1294; Percent complete: 32.4%; Average loss: 3.4803
Iteration: 1295; Percent complete: 32.4%; Average loss: 3.1194
Iteration: 1296; Percent complete: 32.4%; Average loss: 3.1609
Iteration: 1297; Percent complete: 32.4%; Average loss: 3.3583
Iteration: 1298; Percent complete: 32.5%; Average loss: 3.2570
Iteration: 1299; Percent complete: 32.5%; Average loss: 3.6762
Iteration: 1300; Percent complete: 32.5%; Average loss: 3.1108
Iteration: 1301; Percent complete: 32.5%; Average loss: 3.5382
Iteration: 1302; Percent complete: 32.6%; Average loss: 3.4044
Iteration: 1303; Percent complete: 32.6%; Average loss: 3.3819
Iteration: 1304; Percent complete: 32.6%; Average loss: 3.4178
Iteration: 1305; Percent complete: 32.6%; Average loss: 3.3179
Iteration: 1306; Percent complete: 32.6%; Average loss: 3.3427
Iteration: 1307; Percent complete: 32.7%; Average loss: 3.5758
Iteration: 1308; Percent complete: 32.7%; Average loss: 3.5347
Iteration: 1309; Percent complete: 32.7%; Average loss: 3.6861
Iteration: 1310; Percent complete: 32.8%; Average loss: 3.0980
Iteration: 1311; Percent complete: 32.8%; Average loss: 3.3659
Iteration: 1312; Percent complete: 32.8%; Average loss: 3.2271
Iteration: 1313; Percent complete: 32.8%; Average loss: 3.0861
Iteration: 1314; Percent complete: 32.9%; Average loss: 3.3291
Iteration: 1315; Percent complete: 32.9%; Average loss: 3.0941
Iteration: 1316; Percent complete: 32.9%; Average loss: 3.2128
Iteration: 1317; Percent complete: 32.9%; Average loss: 3.5756
Iteration: 1318; Percent complete: 33.0%; Average loss: 3.1972
Iteration: 1319; Percent complete: 33.0%; Average loss: 3.2861
Iteration: 1320; Percent complete: 33.0%; Average loss: 3.4914
Iteration: 1321; Percent complete: 33.0%; Average loss: 3.6736
Iteration: 1322; Percent complete: 33.1%; Average loss: 3.2498
Iteration: 1323; Percent complete: 33.1%; Average loss: 3.7435
Iteration: 1324; Percent complete: 33.1%; Average loss: 3.4862
Iteration: 1325; Percent complete: 33.1%; Average loss: 3.3002
Iteration: 1326; Percent complete: 33.1%; Average loss: 3.2597
Iteration: 1327; Percent complete: 33.2%; Average loss: 3.2688
Iteration: 1328; Percent complete: 33.2%; Average loss: 3.2666
Iteration: 1329; Percent complete: 33.2%; Average loss: 3.4370
Iteration: 1330; Percent complete: 33.2%; Average loss: 3.3377
Iteration: 1331; Percent complete: 33.3%; Average loss: 3.4199
Iteration: 1332; Percent complete: 33.3%; Average loss: 3.1750
Iteration: 1333; Percent complete: 33.3%; Average loss: 3.4724
Iteration: 1334; Percent complete: 33.4%; Average loss: 3.3957
Iteration: 1335; Percent complete: 33.4%; Average loss: 3.5540
Iteration: 1336; Percent complete: 33.4%; Average loss: 3.7063
Iteration: 1337; Percent complete: 33.4%; Average loss: 3.5114
Iteration: 1338; Percent complete: 33.5%; Average loss: 3.5363
Iteration: 1339; Percent complete: 33.5%; Average loss: 3.4130
Iteration: 1340; Percent complete: 33.5%; Average loss: 3.2631
Iteration: 1341; Percent complete: 33.5%; Average loss: 3.1359
Iteration: 1342; Percent complete: 33.6%; Average loss: 3.2647
Iteration: 1343; Percent complete: 33.6%; Average loss: 3.0988
Iteration: 1344; Percent complete: 33.6%; Average loss: 3.0757
Iteration: 1345; Percent complete: 33.6%; Average loss: 3.3439
Iteration: 1346; Percent complete: 33.7%; Average loss: 3.4663
Iteration: 1347; Percent complete: 33.7%; Average loss: 3.5144
Iteration: 1348; Percent complete: 33.7%; Average loss: 3.2143
Iteration: 1349; Percent complete: 33.7%; Average loss: 3.4537
Iteration: 1350; Percent complete: 33.8%; Average loss: 3.4171
Iteration: 1351; Percent complete: 33.8%; Average loss: 3.2054
Iteration: 1352; Percent complete: 33.8%; Average loss: 3.1659
Iteration: 1353; Percent complete: 33.8%; Average loss: 3.3616
Iteration: 1354; Percent complete: 33.9%; Average loss: 3.5357
Iteration: 1355; Percent complete: 33.9%; Average loss: 3.4946
Iteration: 1356; Percent complete: 33.9%; Average loss: 3.2943
Iteration: 1357; Percent complete: 33.9%; Average loss: 3.3019
Iteration: 1358; Percent complete: 34.0%; Average loss: 3.4397
Iteration: 1359; Percent complete: 34.0%; Average loss: 3.3460
Iteration: 1360; Percent complete: 34.0%; Average loss: 3.1675
Iteration: 1361; Percent complete: 34.0%; Average loss: 3.4587
Iteration: 1362; Percent complete: 34.1%; Average loss: 3.2623
Iteration: 1363; Percent complete: 34.1%; Average loss: 3.1113
Iteration: 1364; Percent complete: 34.1%; Average loss: 3.2573
Iteration: 1365; Percent complete: 34.1%; Average loss: 3.0535
Iteration: 1366; Percent complete: 34.2%; Average loss: 3.5450
Iteration: 1367; Percent complete: 34.2%; Average loss: 3.3001
Iteration: 1368; Percent complete: 34.2%; Average loss: 3.4279
Iteration: 1369; Percent complete: 34.2%; Average loss: 3.4599
Iteration: 1370; Percent complete: 34.2%; Average loss: 3.3522
Iteration: 1371; Percent complete: 34.3%; Average loss: 3.4892
Iteration: 1372; Percent complete: 34.3%; Average loss: 3.3632
Iteration: 1373; Percent complete: 34.3%; Average loss: 3.6422
Iteration: 1374; Percent complete: 34.4%; Average loss: 3.1200
Iteration: 1375; Percent complete: 34.4%; Average loss: 3.5205
Iteration: 1376; Percent complete: 34.4%; Average loss: 3.4586
Iteration: 1377; Percent complete: 34.4%; Average loss: 3.1537
Iteration: 1378; Percent complete: 34.4%; Average loss: 3.4827
Iteration: 1379; Percent complete: 34.5%; Average loss: 3.3260
Iteration: 1380; Percent complete: 34.5%; Average loss: 3.5084
Iteration: 1381; Percent complete: 34.5%; Average loss: 3.2833
Iteration: 1382; Percent complete: 34.5%; Average loss: 3.5416
Iteration: 1383; Percent complete: 34.6%; Average loss: 3.5246
Iteration: 1384; Percent complete: 34.6%; Average loss: 3.1797
Iteration: 1385; Percent complete: 34.6%; Average loss: 3.4317
Iteration: 1386; Percent complete: 34.6%; Average loss: 3.8139
Iteration: 1387; Percent complete: 34.7%; Average loss: 3.2452
Iteration: 1388; Percent complete: 34.7%; Average loss: 3.4170
Iteration: 1389; Percent complete: 34.7%; Average loss: 3.3104
Iteration: 1390; Percent complete: 34.8%; Average loss: 3.0783
Iteration: 1391; Percent complete: 34.8%; Average loss: 3.3672
Iteration: 1392; Percent complete: 34.8%; Average loss: 2.9904
Iteration: 1393; Percent complete: 34.8%; Average loss: 3.1740
Iteration: 1394; Percent complete: 34.8%; Average loss: 3.6988
Iteration: 1395; Percent complete: 34.9%; Average loss: 3.4341
Iteration: 1396; Percent complete: 34.9%; Average loss: 3.3764
Iteration: 1397; Percent complete: 34.9%; Average loss: 3.4969
Iteration: 1398; Percent complete: 34.9%; Average loss: 3.1759
Iteration: 1399; Percent complete: 35.0%; Average loss: 3.1298
Iteration: 1400; Percent complete: 35.0%; Average loss: 3.1506
Iteration: 1401; Percent complete: 35.0%; Average loss: 3.5259
Iteration: 1402; Percent complete: 35.0%; Average loss: 3.2984
Iteration: 1403; Percent complete: 35.1%; Average loss: 3.1599
Iteration: 1404; Percent complete: 35.1%; Average loss: 3.5043
Iteration: 1405; Percent complete: 35.1%; Average loss: 3.1549
Iteration: 1406; Percent complete: 35.1%; Average loss: 3.0538
Iteration: 1407; Percent complete: 35.2%; Average loss: 3.6515
Iteration: 1408; Percent complete: 35.2%; Average loss: 3.2856
Iteration: 1409; Percent complete: 35.2%; Average loss: 3.4773
Iteration: 1410; Percent complete: 35.2%; Average loss: 3.5371
Iteration: 1411; Percent complete: 35.3%; Average loss: 3.5376
Iteration: 1412; Percent complete: 35.3%; Average loss: 3.3196
Iteration: 1413; Percent complete: 35.3%; Average loss: 3.0799
Iteration: 1414; Percent complete: 35.4%; Average loss: 3.1929
Iteration: 1415; Percent complete: 35.4%; Average loss: 3.3732
Iteration: 1416; Percent complete: 35.4%; Average loss: 3.6159
Iteration: 1417; Percent complete: 35.4%; Average loss: 3.5393
Iteration: 1418; Percent complete: 35.4%; Average loss: 3.3835
Iteration: 1419; Percent complete: 35.5%; Average loss: 3.0447
Iteration: 1420; Percent complete: 35.5%; Average loss: 3.2970
Iteration: 1421; Percent complete: 35.5%; Average loss: 3.2040
Iteration: 1422; Percent complete: 35.5%; Average loss: 3.4139
Iteration: 1423; Percent complete: 35.6%; Average loss: 3.3422
Iteration: 1424; Percent complete: 35.6%; Average loss: 3.2577
Iteration: 1425; Percent complete: 35.6%; Average loss: 3.3400
Iteration: 1426; Percent complete: 35.6%; Average loss: 3.1545
Iteration: 1427; Percent complete: 35.7%; Average loss: 3.4584
Iteration: 1428; Percent complete: 35.7%; Average loss: 3.3420
Iteration: 1429; Percent complete: 35.7%; Average loss: 3.0758
Iteration: 1430; Percent complete: 35.8%; Average loss: 3.2699
Iteration: 1431; Percent complete: 35.8%; Average loss: 3.3854
Iteration: 1432; Percent complete: 35.8%; Average loss: 3.2227
Iteration: 1433; Percent complete: 35.8%; Average loss: 3.1288
Iteration: 1434; Percent complete: 35.9%; Average loss: 3.4874
Iteration: 1435; Percent complete: 35.9%; Average loss: 3.2307
Iteration: 1436; Percent complete: 35.9%; Average loss: 3.6324
Iteration: 1437; Percent complete: 35.9%; Average loss: 3.4073
Iteration: 1438; Percent complete: 35.9%; Average loss: 3.4511
Iteration: 1439; Percent complete: 36.0%; Average loss: 3.2300
Iteration: 1440; Percent complete: 36.0%; Average loss: 3.3860
Iteration: 1441; Percent complete: 36.0%; Average loss: 3.2979
Iteration: 1442; Percent complete: 36.0%; Average loss: 3.2962
Iteration: 1443; Percent complete: 36.1%; Average loss: 3.2524
Iteration: 1444; Percent complete: 36.1%; Average loss: 3.1189
Iteration: 1445; Percent complete: 36.1%; Average loss: 3.3233
Iteration: 1446; Percent complete: 36.1%; Average loss: 3.2350
Iteration: 1447; Percent complete: 36.2%; Average loss: 3.4016
Iteration: 1448; Percent complete: 36.2%; Average loss: 3.0902
Iteration: 1449; Percent complete: 36.2%; Average loss: 3.1149
Iteration: 1450; Percent complete: 36.2%; Average loss: 3.2523
Iteration: 1451; Percent complete: 36.3%; Average loss: 3.5377
Iteration: 1452; Percent complete: 36.3%; Average loss: 3.2961
Iteration: 1453; Percent complete: 36.3%; Average loss: 3.2211
Iteration: 1454; Percent complete: 36.4%; Average loss: 3.2315
Iteration: 1455; Percent complete: 36.4%; Average loss: 3.2800
Iteration: 1456; Percent complete: 36.4%; Average loss: 3.3603
Iteration: 1457; Percent complete: 36.4%; Average loss: 3.4360
Iteration: 1458; Percent complete: 36.4%; Average loss: 3.1670
Iteration: 1459; Percent complete: 36.5%; Average loss: 3.3400
Iteration: 1460; Percent complete: 36.5%; Average loss: 3.5830
Iteration: 1461; Percent complete: 36.5%; Average loss: 3.5440
Iteration: 1462; Percent complete: 36.5%; Average loss: 3.1900
Iteration: 1463; Percent complete: 36.6%; Average loss: 3.3266
Iteration: 1464; Percent complete: 36.6%; Average loss: 3.2473
Iteration: 1465; Percent complete: 36.6%; Average loss: 3.3994
Iteration: 1466; Percent complete: 36.6%; Average loss: 3.4053
Iteration: 1467; Percent complete: 36.7%; Average loss: 3.3682
Iteration: 1468; Percent complete: 36.7%; Average loss: 3.3537
Iteration: 1469; Percent complete: 36.7%; Average loss: 3.1584
Iteration: 1470; Percent complete: 36.8%; Average loss: 3.4073
Iteration: 1471; Percent complete: 36.8%; Average loss: 3.5664
Iteration: 1472; Percent complete: 36.8%; Average loss: 3.4380
Iteration: 1473; Percent complete: 36.8%; Average loss: 3.3586
Iteration: 1474; Percent complete: 36.9%; Average loss: 3.0584
Iteration: 1475; Percent complete: 36.9%; Average loss: 3.2985
Iteration: 1476; Percent complete: 36.9%; Average loss: 3.3735
Iteration: 1477; Percent complete: 36.9%; Average loss: 3.3197
Iteration: 1478; Percent complete: 37.0%; Average loss: 3.2007
Iteration: 1479; Percent complete: 37.0%; Average loss: 3.5072
Iteration: 1480; Percent complete: 37.0%; Average loss: 3.1298
Iteration: 1481; Percent complete: 37.0%; Average loss: 3.3083
Iteration: 1482; Percent complete: 37.0%; Average loss: 3.1861
Iteration: 1483; Percent complete: 37.1%; Average loss: 3.1370
Iteration: 1484; Percent complete: 37.1%; Average loss: 3.5573
Iteration: 1485; Percent complete: 37.1%; Average loss: 3.1278
Iteration: 1486; Percent complete: 37.1%; Average loss: 3.1749
Iteration: 1487; Percent complete: 37.2%; Average loss: 2.9898
Iteration: 1488; Percent complete: 37.2%; Average loss: 3.4996
Iteration: 1489; Percent complete: 37.2%; Average loss: 3.4838
Iteration: 1490; Percent complete: 37.2%; Average loss: 3.3070
Iteration: 1491; Percent complete: 37.3%; Average loss: 3.4018
Iteration: 1492; Percent complete: 37.3%; Average loss: 3.3786
Iteration: 1493; Percent complete: 37.3%; Average loss: 3.5179
Iteration: 1494; Percent complete: 37.4%; Average loss: 3.0675
Iteration: 1495; Percent complete: 37.4%; Average loss: 3.5832
Iteration: 1496; Percent complete: 37.4%; Average loss: 3.2939
Iteration: 1497; Percent complete: 37.4%; Average loss: 3.4452
Iteration: 1498; Percent complete: 37.5%; Average loss: 3.1576
Iteration: 1499; Percent complete: 37.5%; Average loss: 3.5365
Iteration: 1500; Percent complete: 37.5%; Average loss: 3.2461
Iteration: 1501; Percent complete: 37.5%; Average loss: 3.4180
Iteration: 1502; Percent complete: 37.5%; Average loss: 3.3238
Iteration: 1503; Percent complete: 37.6%; Average loss: 3.2443
Iteration: 1504; Percent complete: 37.6%; Average loss: 3.4585
Iteration: 1505; Percent complete: 37.6%; Average loss: 3.3468
Iteration: 1506; Percent complete: 37.6%; Average loss: 3.0928
Iteration: 1507; Percent complete: 37.7%; Average loss: 3.3216
Iteration: 1508; Percent complete: 37.7%; Average loss: 3.2282
Iteration: 1509; Percent complete: 37.7%; Average loss: 3.1588
Iteration: 1510; Percent complete: 37.8%; Average loss: 3.5032
Iteration: 1511; Percent complete: 37.8%; Average loss: 3.2146
Iteration: 1512; Percent complete: 37.8%; Average loss: 3.1929
Iteration: 1513; Percent complete: 37.8%; Average loss: 3.3456
Iteration: 1514; Percent complete: 37.9%; Average loss: 3.3569
Iteration: 1515; Percent complete: 37.9%; Average loss: 3.4053
Iteration: 1516; Percent complete: 37.9%; Average loss: 3.3012
Iteration: 1517; Percent complete: 37.9%; Average loss: 3.2296
Iteration: 1518; Percent complete: 38.0%; Average loss: 3.1668
Iteration: 1519; Percent complete: 38.0%; Average loss: 3.2044
Iteration: 1520; Percent complete: 38.0%; Average loss: 3.3301
Iteration: 1521; Percent complete: 38.0%; Average loss: 3.2701
Iteration: 1522; Percent complete: 38.0%; Average loss: 3.2114
Iteration: 1523; Percent complete: 38.1%; Average loss: 3.3450
Iteration: 1524; Percent complete: 38.1%; Average loss: 3.3581
Iteration: 1525; Percent complete: 38.1%; Average loss: 3.4364
Iteration: 1526; Percent complete: 38.1%; Average loss: 3.3670
Iteration: 1527; Percent complete: 38.2%; Average loss: 3.3028
Iteration: 1528; Percent complete: 38.2%; Average loss: 3.2232
Iteration: 1529; Percent complete: 38.2%; Average loss: 3.5061
Iteration: 1530; Percent complete: 38.2%; Average loss: 3.3374
Iteration: 1531; Percent complete: 38.3%; Average loss: 3.3459
Iteration: 1532; Percent complete: 38.3%; Average loss: 3.2943
Iteration: 1533; Percent complete: 38.3%; Average loss: 3.3788
Iteration: 1534; Percent complete: 38.4%; Average loss: 3.2214
Iteration: 1535; Percent complete: 38.4%; Average loss: 3.4922
Iteration: 1536; Percent complete: 38.4%; Average loss: 3.4101
Iteration: 1537; Percent complete: 38.4%; Average loss: 3.4807
Iteration: 1538; Percent complete: 38.5%; Average loss: 3.2740
Iteration: 1539; Percent complete: 38.5%; Average loss: 3.4294
Iteration: 1540; Percent complete: 38.5%; Average loss: 3.1078
Iteration: 1541; Percent complete: 38.5%; Average loss: 3.5184
Iteration: 1542; Percent complete: 38.6%; Average loss: 3.3079
Iteration: 1543; Percent complete: 38.6%; Average loss: 3.5642
Iteration: 1544; Percent complete: 38.6%; Average loss: 3.1258
Iteration: 1545; Percent complete: 38.6%; Average loss: 2.9809
Iteration: 1546; Percent complete: 38.6%; Average loss: 3.2320
Iteration: 1547; Percent complete: 38.7%; Average loss: 3.2361
Iteration: 1548; Percent complete: 38.7%; Average loss: 3.3021
Iteration: 1549; Percent complete: 38.7%; Average loss: 3.2033
Iteration: 1550; Percent complete: 38.8%; Average loss: 3.5144
Iteration: 1551; Percent complete: 38.8%; Average loss: 3.4873
Iteration: 1552; Percent complete: 38.8%; Average loss: 3.2863
Iteration: 1553; Percent complete: 38.8%; Average loss: 3.2510
Iteration: 1554; Percent complete: 38.9%; Average loss: 3.7237
Iteration: 1555; Percent complete: 38.9%; Average loss: 3.2485
Iteration: 1556; Percent complete: 38.9%; Average loss: 3.4129
Iteration: 1557; Percent complete: 38.9%; Average loss: 3.4772
Iteration: 1558; Percent complete: 39.0%; Average loss: 3.1736
Iteration: 1559; Percent complete: 39.0%; Average loss: 3.1334
Iteration: 1560; Percent complete: 39.0%; Average loss: 3.4604
Iteration: 1561; Percent complete: 39.0%; Average loss: 3.4463
Iteration: 1562; Percent complete: 39.1%; Average loss: 3.0458
Iteration: 1563; Percent complete: 39.1%; Average loss: 3.3169
Iteration: 1564; Percent complete: 39.1%; Average loss: 3.3559
Iteration: 1565; Percent complete: 39.1%; Average loss: 3.2317
Iteration: 1566; Percent complete: 39.1%; Average loss: 3.2742
Iteration: 1567; Percent complete: 39.2%; Average loss: 3.1584
Iteration: 1568; Percent complete: 39.2%; Average loss: 3.2131
Iteration: 1569; Percent complete: 39.2%; Average loss: 3.2916
Iteration: 1570; Percent complete: 39.2%; Average loss: 3.3236
Iteration: 1571; Percent complete: 39.3%; Average loss: 3.1899
Iteration: 1572; Percent complete: 39.3%; Average loss: 3.1504
Iteration: 1573; Percent complete: 39.3%; Average loss: 3.2814
Iteration: 1574; Percent complete: 39.4%; Average loss: 3.1565
Iteration: 1575; Percent complete: 39.4%; Average loss: 3.3328
Iteration: 1576; Percent complete: 39.4%; Average loss: 3.3805
Iteration: 1577; Percent complete: 39.4%; Average loss: 3.1967
Iteration: 1578; Percent complete: 39.5%; Average loss: 3.1255
Iteration: 1579; Percent complete: 39.5%; Average loss: 3.2526
Iteration: 1580; Percent complete: 39.5%; Average loss: 3.0879
Iteration: 1581; Percent complete: 39.5%; Average loss: 3.3160
Iteration: 1582; Percent complete: 39.6%; Average loss: 3.1447
Iteration: 1583; Percent complete: 39.6%; Average loss: 3.3598
Iteration: 1584; Percent complete: 39.6%; Average loss: 3.4662
Iteration: 1585; Percent complete: 39.6%; Average loss: 3.2761
Iteration: 1586; Percent complete: 39.6%; Average loss: 3.3406
Iteration: 1587; Percent complete: 39.7%; Average loss: 3.2850
Iteration: 1588; Percent complete: 39.7%; Average loss: 3.3480
Iteration: 1589; Percent complete: 39.7%; Average loss: 3.1109
Iteration: 1590; Percent complete: 39.8%; Average loss: 3.1778
Iteration: 1591; Percent complete: 39.8%; Average loss: 3.3683
Iteration: 1592; Percent complete: 39.8%; Average loss: 3.3394
Iteration: 1593; Percent complete: 39.8%; Average loss: 3.3271
Iteration: 1594; Percent complete: 39.9%; Average loss: 3.2918
Iteration: 1595; Percent complete: 39.9%; Average loss: 3.3293
Iteration: 1596; Percent complete: 39.9%; Average loss: 3.5273
Iteration: 1597; Percent complete: 39.9%; Average loss: 3.2138
Iteration: 1598; Percent complete: 40.0%; Average loss: 3.1820
Iteration: 1599; Percent complete: 40.0%; Average loss: 3.1534
Iteration: 1600; Percent complete: 40.0%; Average loss: 3.1277
Iteration: 1601; Percent complete: 40.0%; Average loss: 3.2253
Iteration: 1602; Percent complete: 40.1%; Average loss: 3.3755
Iteration: 1603; Percent complete: 40.1%; Average loss: 3.1980
Iteration: 1604; Percent complete: 40.1%; Average loss: 3.0196
Iteration: 1605; Percent complete: 40.1%; Average loss: 3.2735
Iteration: 1606; Percent complete: 40.2%; Average loss: 3.2917
Iteration: 1607; Percent complete: 40.2%; Average loss: 3.3923
Iteration: 1608; Percent complete: 40.2%; Average loss: 3.2476
Iteration: 1609; Percent complete: 40.2%; Average loss: 3.2421
Iteration: 1610; Percent complete: 40.2%; Average loss: 3.0517
Iteration: 1611; Percent complete: 40.3%; Average loss: 3.0987
Iteration: 1612; Percent complete: 40.3%; Average loss: 3.1933
Iteration: 1613; Percent complete: 40.3%; Average loss: 3.2882
Iteration: 1614; Percent complete: 40.4%; Average loss: 3.3523
Iteration: 1615; Percent complete: 40.4%; Average loss: 3.3485
Iteration: 1616; Percent complete: 40.4%; Average loss: 3.0161
Iteration: 1617; Percent complete: 40.4%; Average loss: 3.5864
Iteration: 1618; Percent complete: 40.5%; Average loss: 3.3352
Iteration: 1619; Percent complete: 40.5%; Average loss: 3.0911
Iteration: 1620; Percent complete: 40.5%; Average loss: 3.5671
Iteration: 1621; Percent complete: 40.5%; Average loss: 3.4470
Iteration: 1622; Percent complete: 40.6%; Average loss: 3.3423
Iteration: 1623; Percent complete: 40.6%; Average loss: 3.3670
Iteration: 1624; Percent complete: 40.6%; Average loss: 3.2025
Iteration: 1625; Percent complete: 40.6%; Average loss: 3.3643
Iteration: 1626; Percent complete: 40.6%; Average loss: 3.3534
Iteration: 1627; Percent complete: 40.7%; Average loss: 3.2235
Iteration: 1628; Percent complete: 40.7%; Average loss: 3.0952
Iteration: 1629; Percent complete: 40.7%; Average loss: 3.1812
Iteration: 1630; Percent complete: 40.8%; Average loss: 3.1337
Iteration: 1631; Percent complete: 40.8%; Average loss: 3.3078
Iteration: 1632; Percent complete: 40.8%; Average loss: 3.3309
Iteration: 1633; Percent complete: 40.8%; Average loss: 3.2617
Iteration: 1634; Percent complete: 40.8%; Average loss: 3.0427
Iteration: 1635; Percent complete: 40.9%; Average loss: 3.1361
Iteration: 1636; Percent complete: 40.9%; Average loss: 3.4611
Iteration: 1637; Percent complete: 40.9%; Average loss: 2.9211
Iteration: 1638; Percent complete: 40.9%; Average loss: 3.1808
Iteration: 1639; Percent complete: 41.0%; Average loss: 3.2183
Iteration: 1640; Percent complete: 41.0%; Average loss: 3.2842
Iteration: 1641; Percent complete: 41.0%; Average loss: 3.1625
Iteration: 1642; Percent complete: 41.0%; Average loss: 3.1357
Iteration: 1643; Percent complete: 41.1%; Average loss: 3.6010
Iteration: 1644; Percent complete: 41.1%; Average loss: 3.2214
Iteration: 1645; Percent complete: 41.1%; Average loss: 3.2867
Iteration: 1646; Percent complete: 41.1%; Average loss: 3.2358
Iteration: 1647; Percent complete: 41.2%; Average loss: 3.4100
Iteration: 1648; Percent complete: 41.2%; Average loss: 3.3110
Iteration: 1649; Percent complete: 41.2%; Average loss: 3.2798
Iteration: 1650; Percent complete: 41.2%; Average loss: 3.2173
Iteration: 1651; Percent complete: 41.3%; Average loss: 3.1358
Iteration: 1652; Percent complete: 41.3%; Average loss: 3.1043
Iteration: 1653; Percent complete: 41.3%; Average loss: 3.4644
Iteration: 1654; Percent complete: 41.3%; Average loss: 3.1014
Iteration: 1655; Percent complete: 41.4%; Average loss: 3.3874
Iteration: 1656; Percent complete: 41.4%; Average loss: 3.3654
Iteration: 1657; Percent complete: 41.4%; Average loss: 3.3795
Iteration: 1658; Percent complete: 41.4%; Average loss: 3.3728
Iteration: 1659; Percent complete: 41.5%; Average loss: 3.1146
Iteration: 1660; Percent complete: 41.5%; Average loss: 3.3107
Iteration: 1661; Percent complete: 41.5%; Average loss: 3.0969
Iteration: 1662; Percent complete: 41.5%; Average loss: 3.1231
Iteration: 1663; Percent complete: 41.6%; Average loss: 3.2778
Iteration: 1664; Percent complete: 41.6%; Average loss: 2.9871
Iteration: 1665; Percent complete: 41.6%; Average loss: 3.4220
Iteration: 1666; Percent complete: 41.6%; Average loss: 3.1432
Iteration: 1667; Percent complete: 41.7%; Average loss: 3.2903
Iteration: 1668; Percent complete: 41.7%; Average loss: 3.2125
Iteration: 1669; Percent complete: 41.7%; Average loss: 3.3675
Iteration: 1670; Percent complete: 41.8%; Average loss: 3.1442
Iteration: 1671; Percent complete: 41.8%; Average loss: 3.2532
Iteration: 1672; Percent complete: 41.8%; Average loss: 3.0395
Iteration: 1673; Percent complete: 41.8%; Average loss: 3.4541
Iteration: 1674; Percent complete: 41.9%; Average loss: 3.4244
Iteration: 1675; Percent complete: 41.9%; Average loss: 3.2628
Iteration: 1676; Percent complete: 41.9%; Average loss: 3.3471
Iteration: 1677; Percent complete: 41.9%; Average loss: 3.2237
Iteration: 1678; Percent complete: 41.9%; Average loss: 3.2859
Iteration: 1679; Percent complete: 42.0%; Average loss: 3.1904
Iteration: 1680; Percent complete: 42.0%; Average loss: 3.3102
Iteration: 1681; Percent complete: 42.0%; Average loss: 3.4800
Iteration: 1682; Percent complete: 42.0%; Average loss: 3.1281
Iteration: 1683; Percent complete: 42.1%; Average loss: 3.2387
Iteration: 1684; Percent complete: 42.1%; Average loss: 3.3366
Iteration: 1685; Percent complete: 42.1%; Average loss: 3.3480
Iteration: 1686; Percent complete: 42.1%; Average loss: 3.1753
Iteration: 1687; Percent complete: 42.2%; Average loss: 3.1738
Iteration: 1688; Percent complete: 42.2%; Average loss: 3.3958
Iteration: 1689; Percent complete: 42.2%; Average loss: 3.3101
Iteration: 1690; Percent complete: 42.2%; Average loss: 3.4121
Iteration: 1691; Percent complete: 42.3%; Average loss: 3.4102
Iteration: 1692; Percent complete: 42.3%; Average loss: 3.5010
Iteration: 1693; Percent complete: 42.3%; Average loss: 3.0428
Iteration: 1694; Percent complete: 42.4%; Average loss: 3.3756
Iteration: 1695; Percent complete: 42.4%; Average loss: 3.2059
Iteration: 1696; Percent complete: 42.4%; Average loss: 3.2982
Iteration: 1697; Percent complete: 42.4%; Average loss: 3.2891
Iteration: 1698; Percent complete: 42.4%; Average loss: 3.2172
Iteration: 1699; Percent complete: 42.5%; Average loss: 3.1256
Iteration: 1700; Percent complete: 42.5%; Average loss: 3.2065
Iteration: 1701; Percent complete: 42.5%; Average loss: 3.2470
Iteration: 1702; Percent complete: 42.5%; Average loss: 3.3088
Iteration: 1703; Percent complete: 42.6%; Average loss: 3.1560
Iteration: 1704; Percent complete: 42.6%; Average loss: 3.1029
Iteration: 1705; Percent complete: 42.6%; Average loss: 3.1410
Iteration: 1706; Percent complete: 42.6%; Average loss: 3.2769
Iteration: 1707; Percent complete: 42.7%; Average loss: 3.2297
Iteration: 1708; Percent complete: 42.7%; Average loss: 3.2768
Iteration: 1709; Percent complete: 42.7%; Average loss: 3.3655
Iteration: 1710; Percent complete: 42.8%; Average loss: 3.3652
Iteration: 1711; Percent complete: 42.8%; Average loss: 3.1899
Iteration: 1712; Percent complete: 42.8%; Average loss: 3.1731
Iteration: 1713; Percent complete: 42.8%; Average loss: 3.2208
Iteration: 1714; Percent complete: 42.9%; Average loss: 3.5474
Iteration: 1715; Percent complete: 42.9%; Average loss: 3.3663
Iteration: 1716; Percent complete: 42.9%; Average loss: 2.9405
Iteration: 1717; Percent complete: 42.9%; Average loss: 3.2099
Iteration: 1718; Percent complete: 43.0%; Average loss: 3.1192
Iteration: 1719; Percent complete: 43.0%; Average loss: 3.1533
Iteration: 1720; Percent complete: 43.0%; Average loss: 3.0366
Iteration: 1721; Percent complete: 43.0%; Average loss: 3.3928
Iteration: 1722; Percent complete: 43.0%; Average loss: 3.3003
Iteration: 1723; Percent complete: 43.1%; Average loss: 3.2264
Iteration: 1724; Percent complete: 43.1%; Average loss: 3.2936
Iteration: 1725; Percent complete: 43.1%; Average loss: 3.2963
Iteration: 1726; Percent complete: 43.1%; Average loss: 3.1672
Iteration: 1727; Percent complete: 43.2%; Average loss: 3.5738
Iteration: 1728; Percent complete: 43.2%; Average loss: 3.3886
Iteration: 1729; Percent complete: 43.2%; Average loss: 3.0949
Iteration: 1730; Percent complete: 43.2%; Average loss: 3.1863
Iteration: 1731; Percent complete: 43.3%; Average loss: 3.1344
Iteration: 1732; Percent complete: 43.3%; Average loss: 3.1959
Iteration: 1733; Percent complete: 43.3%; Average loss: 3.4818
Iteration: 1734; Percent complete: 43.4%; Average loss: 3.1163
Iteration: 1735; Percent complete: 43.4%; Average loss: 3.5104
Iteration: 1736; Percent complete: 43.4%; Average loss: 3.2059
Iteration: 1737; Percent complete: 43.4%; Average loss: 3.1390
Iteration: 1738; Percent complete: 43.5%; Average loss: 3.4624
Iteration: 1739; Percent complete: 43.5%; Average loss: 2.9192
Iteration: 1740; Percent complete: 43.5%; Average loss: 3.1496
Iteration: 1741; Percent complete: 43.5%; Average loss: 3.2417
Iteration: 1742; Percent complete: 43.5%; Average loss: 3.1934
Iteration: 1743; Percent complete: 43.6%; Average loss: 3.1027
Iteration: 1744; Percent complete: 43.6%; Average loss: 3.2758
Iteration: 1745; Percent complete: 43.6%; Average loss: 3.4474
Iteration: 1746; Percent complete: 43.6%; Average loss: 3.3032
Iteration: 1747; Percent complete: 43.7%; Average loss: 3.3029
Iteration: 1748; Percent complete: 43.7%; Average loss: 2.8596
Iteration: 1749; Percent complete: 43.7%; Average loss: 3.3504
Iteration: 1750; Percent complete: 43.8%; Average loss: 3.2225
Iteration: 1751; Percent complete: 43.8%; Average loss: 3.3202
Iteration: 1752; Percent complete: 43.8%; Average loss: 2.9846
Iteration: 1753; Percent complete: 43.8%; Average loss: 3.3020
Iteration: 1754; Percent complete: 43.9%; Average loss: 3.3958
Iteration: 1755; Percent complete: 43.9%; Average loss: 3.2448
Iteration: 1756; Percent complete: 43.9%; Average loss: 3.2098
Iteration: 1757; Percent complete: 43.9%; Average loss: 3.2755
Iteration: 1758; Percent complete: 44.0%; Average loss: 3.0808
Iteration: 1759; Percent complete: 44.0%; Average loss: 3.3198
Iteration: 1760; Percent complete: 44.0%; Average loss: 3.0646
Iteration: 1761; Percent complete: 44.0%; Average loss: 3.3760
Iteration: 1762; Percent complete: 44.0%; Average loss: 2.9908
Iteration: 1763; Percent complete: 44.1%; Average loss: 3.0478
Iteration: 1764; Percent complete: 44.1%; Average loss: 3.3041
Iteration: 1765; Percent complete: 44.1%; Average loss: 3.2267
Iteration: 1766; Percent complete: 44.1%; Average loss: 3.2762
Iteration: 1767; Percent complete: 44.2%; Average loss: 3.3374
Iteration: 1768; Percent complete: 44.2%; Average loss: 3.3124
Iteration: 1769; Percent complete: 44.2%; Average loss: 3.3538
Iteration: 1770; Percent complete: 44.2%; Average loss: 3.3510
Iteration: 1771; Percent complete: 44.3%; Average loss: 3.0936
Iteration: 1772; Percent complete: 44.3%; Average loss: 3.3620
Iteration: 1773; Percent complete: 44.3%; Average loss: 3.3563
Iteration: 1774; Percent complete: 44.4%; Average loss: 3.0610
Iteration: 1775; Percent complete: 44.4%; Average loss: 3.1420
Iteration: 1776; Percent complete: 44.4%; Average loss: 3.2514
Iteration: 1777; Percent complete: 44.4%; Average loss: 3.0816
Iteration: 1778; Percent complete: 44.5%; Average loss: 3.1750
Iteration: 1779; Percent complete: 44.5%; Average loss: 3.5646
Iteration: 1780; Percent complete: 44.5%; Average loss: 2.9880
Iteration: 1781; Percent complete: 44.5%; Average loss: 3.2489
Iteration: 1782; Percent complete: 44.5%; Average loss: 3.4500
Iteration: 1783; Percent complete: 44.6%; Average loss: 3.2293
Iteration: 1784; Percent complete: 44.6%; Average loss: 3.2410
Iteration: 1785; Percent complete: 44.6%; Average loss: 3.2092
Iteration: 1786; Percent complete: 44.6%; Average loss: 3.5147
Iteration: 1787; Percent complete: 44.7%; Average loss: 3.1371
Iteration: 1788; Percent complete: 44.7%; Average loss: 3.0312
Iteration: 1789; Percent complete: 44.7%; Average loss: 3.4560
Iteration: 1790; Percent complete: 44.8%; Average loss: 3.4297
Iteration: 1791; Percent complete: 44.8%; Average loss: 3.3989
Iteration: 1792; Percent complete: 44.8%; Average loss: 3.4241
Iteration: 1793; Percent complete: 44.8%; Average loss: 3.3459
Iteration: 1794; Percent complete: 44.9%; Average loss: 3.1613
Iteration: 1795; Percent complete: 44.9%; Average loss: 2.9817
Iteration: 1796; Percent complete: 44.9%; Average loss: 3.1412
Iteration: 1797; Percent complete: 44.9%; Average loss: 3.0840
Iteration: 1798; Percent complete: 45.0%; Average loss: 3.0566
Iteration: 1799; Percent complete: 45.0%; Average loss: 3.1785
Iteration: 1800; Percent complete: 45.0%; Average loss: 3.2800
Iteration: 1801; Percent complete: 45.0%; Average loss: 3.2651
Iteration: 1802; Percent complete: 45.1%; Average loss: 2.9159
Iteration: 1803; Percent complete: 45.1%; Average loss: 3.1327
Iteration: 1804; Percent complete: 45.1%; Average loss: 3.0748
Iteration: 1805; Percent complete: 45.1%; Average loss: 3.2320
Iteration: 1806; Percent complete: 45.1%; Average loss: 3.1310
Iteration: 1807; Percent complete: 45.2%; Average loss: 3.1140
Iteration: 1808; Percent complete: 45.2%; Average loss: 3.4001
Iteration: 1809; Percent complete: 45.2%; Average loss: 3.1217
Iteration: 1810; Percent complete: 45.2%; Average loss: 3.5594
Iteration: 1811; Percent complete: 45.3%; Average loss: 3.2348
Iteration: 1812; Percent complete: 45.3%; Average loss: 3.1640
Iteration: 1813; Percent complete: 45.3%; Average loss: 3.0947
Iteration: 1814; Percent complete: 45.4%; Average loss: 3.3919
Iteration: 1815; Percent complete: 45.4%; Average loss: 3.2597
Iteration: 1816; Percent complete: 45.4%; Average loss: 2.9775
Iteration: 1817; Percent complete: 45.4%; Average loss: 3.3173
Iteration: 1818; Percent complete: 45.5%; Average loss: 3.4232
Iteration: 1819; Percent complete: 45.5%; Average loss: 3.2398
Iteration: 1820; Percent complete: 45.5%; Average loss: 3.2704
Iteration: 1821; Percent complete: 45.5%; Average loss: 3.3638
Iteration: 1822; Percent complete: 45.6%; Average loss: 3.1260
Iteration: 1823; Percent complete: 45.6%; Average loss: 3.3770
Iteration: 1824; Percent complete: 45.6%; Average loss: 3.2303
Iteration: 1825; Percent complete: 45.6%; Average loss: 3.1679
Iteration: 1826; Percent complete: 45.6%; Average loss: 3.2849
Iteration: 1827; Percent complete: 45.7%; Average loss: 3.0193
Iteration: 1828; Percent complete: 45.7%; Average loss: 2.8409
Iteration: 1829; Percent complete: 45.7%; Average loss: 3.2382
Iteration: 1830; Percent complete: 45.8%; Average loss: 3.2839
Iteration: 1831; Percent complete: 45.8%; Average loss: 3.1522
Iteration: 1832; Percent complete: 45.8%; Average loss: 3.0198
Iteration: 1833; Percent complete: 45.8%; Average loss: 3.1336
Iteration: 1834; Percent complete: 45.9%; Average loss: 3.1911
Iteration: 1835; Percent complete: 45.9%; Average loss: 3.2876
Iteration: 1836; Percent complete: 45.9%; Average loss: 3.1655
Iteration: 1837; Percent complete: 45.9%; Average loss: 3.0997
Iteration: 1838; Percent complete: 46.0%; Average loss: 3.0383
Iteration: 1839; Percent complete: 46.0%; Average loss: 3.1148
Iteration: 1840; Percent complete: 46.0%; Average loss: 3.2299
Iteration: 1841; Percent complete: 46.0%; Average loss: 3.0972
Iteration: 1842; Percent complete: 46.1%; Average loss: 3.3014
Iteration: 1843; Percent complete: 46.1%; Average loss: 3.3358
Iteration: 1844; Percent complete: 46.1%; Average loss: 3.0556
Iteration: 1845; Percent complete: 46.1%; Average loss: 3.1180
Iteration: 1846; Percent complete: 46.2%; Average loss: 3.1450
Iteration: 1847; Percent complete: 46.2%; Average loss: 3.3095
Iteration: 1848; Percent complete: 46.2%; Average loss: 3.1495
Iteration: 1849; Percent complete: 46.2%; Average loss: 3.1230
Iteration: 1850; Percent complete: 46.2%; Average loss: 3.2731
Iteration: 1851; Percent complete: 46.3%; Average loss: 3.2698
Iteration: 1852; Percent complete: 46.3%; Average loss: 3.0344
Iteration: 1853; Percent complete: 46.3%; Average loss: 2.9859
Iteration: 1854; Percent complete: 46.4%; Average loss: 3.2625
Iteration: 1855; Percent complete: 46.4%; Average loss: 3.2045
Iteration: 1856; Percent complete: 46.4%; Average loss: 3.1715
Iteration: 1857; Percent complete: 46.4%; Average loss: 3.2834
Iteration: 1858; Percent complete: 46.5%; Average loss: 3.2568
Iteration: 1859; Percent complete: 46.5%; Average loss: 3.1675
Iteration: 1860; Percent complete: 46.5%; Average loss: 3.1806
Iteration: 1861; Percent complete: 46.5%; Average loss: 3.1825
Iteration: 1862; Percent complete: 46.6%; Average loss: 3.3715
Iteration: 1863; Percent complete: 46.6%; Average loss: 3.3366
Iteration: 1864; Percent complete: 46.6%; Average loss: 2.9682
Iteration: 1865; Percent complete: 46.6%; Average loss: 3.0840
Iteration: 1866; Percent complete: 46.7%; Average loss: 3.0214
Iteration: 1867; Percent complete: 46.7%; Average loss: 3.3470
Iteration: 1868; Percent complete: 46.7%; Average loss: 3.2685
Iteration: 1869; Percent complete: 46.7%; Average loss: 3.1105
Iteration: 1870; Percent complete: 46.8%; Average loss: 3.3509
Iteration: 1871; Percent complete: 46.8%; Average loss: 3.1869
Iteration: 1872; Percent complete: 46.8%; Average loss: 3.1510
Iteration: 1873; Percent complete: 46.8%; Average loss: 3.0787
Iteration: 1874; Percent complete: 46.9%; Average loss: 3.3809
Iteration: 1875; Percent complete: 46.9%; Average loss: 3.4428
Iteration: 1876; Percent complete: 46.9%; Average loss: 3.1887
Iteration: 1877; Percent complete: 46.9%; Average loss: 3.4763
Iteration: 1878; Percent complete: 46.9%; Average loss: 3.1604
Iteration: 1879; Percent complete: 47.0%; Average loss: 3.2071
Iteration: 1880; Percent complete: 47.0%; Average loss: 3.4262
Iteration: 1881; Percent complete: 47.0%; Average loss: 3.3590
Iteration: 1882; Percent complete: 47.0%; Average loss: 3.2651
Iteration: 1883; Percent complete: 47.1%; Average loss: 3.4615
Iteration: 1884; Percent complete: 47.1%; Average loss: 3.2514
Iteration: 1885; Percent complete: 47.1%; Average loss: 3.0731
Iteration: 1886; Percent complete: 47.1%; Average loss: 3.2607
Iteration: 1887; Percent complete: 47.2%; Average loss: 3.2473
Iteration: 1888; Percent complete: 47.2%; Average loss: 3.5979
Iteration: 1889; Percent complete: 47.2%; Average loss: 3.1324
Iteration: 1890; Percent complete: 47.2%; Average loss: 3.0360
Iteration: 1891; Percent complete: 47.3%; Average loss: 3.2705
Iteration: 1892; Percent complete: 47.3%; Average loss: 3.1805
Iteration: 1893; Percent complete: 47.3%; Average loss: 3.1857
Iteration: 1894; Percent complete: 47.3%; Average loss: 3.0958
Iteration: 1895; Percent complete: 47.4%; Average loss: 3.1851
Iteration: 1896; Percent complete: 47.4%; Average loss: 3.3600
Iteration: 1897; Percent complete: 47.4%; Average loss: 3.0202
Iteration: 1898; Percent complete: 47.4%; Average loss: 3.0983
Iteration: 1899; Percent complete: 47.5%; Average loss: 3.0865
Iteration: 1900; Percent complete: 47.5%; Average loss: 2.9469
Iteration: 1901; Percent complete: 47.5%; Average loss: 3.2858
Iteration: 1902; Percent complete: 47.5%; Average loss: 2.9268
Iteration: 1903; Percent complete: 47.6%; Average loss: 3.5500
Iteration: 1904; Percent complete: 47.6%; Average loss: 3.2402
Iteration: 1905; Percent complete: 47.6%; Average loss: 3.2246
Iteration: 1906; Percent complete: 47.6%; Average loss: 3.3385
Iteration: 1907; Percent complete: 47.7%; Average loss: 3.4250
Iteration: 1908; Percent complete: 47.7%; Average loss: 3.1344
Iteration: 1909; Percent complete: 47.7%; Average loss: 3.1453
Iteration: 1910; Percent complete: 47.8%; Average loss: 3.3346
Iteration: 1911; Percent complete: 47.8%; Average loss: 3.2473
Iteration: 1912; Percent complete: 47.8%; Average loss: 3.2376
Iteration: 1913; Percent complete: 47.8%; Average loss: 3.2169
Iteration: 1914; Percent complete: 47.9%; Average loss: 3.0620
Iteration: 1915; Percent complete: 47.9%; Average loss: 3.2661
Iteration: 1916; Percent complete: 47.9%; Average loss: 3.2265
Iteration: 1917; Percent complete: 47.9%; Average loss: 3.1505
Iteration: 1918; Percent complete: 47.9%; Average loss: 2.9907
Iteration: 1919; Percent complete: 48.0%; Average loss: 3.2642
Iteration: 1920; Percent complete: 48.0%; Average loss: 3.3238
Iteration: 1921; Percent complete: 48.0%; Average loss: 2.9069
Iteration: 1922; Percent complete: 48.0%; Average loss: 3.1741
Iteration: 1923; Percent complete: 48.1%; Average loss: 3.2482
Iteration: 1924; Percent complete: 48.1%; Average loss: 3.0287
Iteration: 1925; Percent complete: 48.1%; Average loss: 3.0711
Iteration: 1926; Percent complete: 48.1%; Average loss: 3.1304
Iteration: 1927; Percent complete: 48.2%; Average loss: 3.5392
Iteration: 1928; Percent complete: 48.2%; Average loss: 3.0471
Iteration: 1929; Percent complete: 48.2%; Average loss: 3.2865
Iteration: 1930; Percent complete: 48.2%; Average loss: 3.0241
Iteration: 1931; Percent complete: 48.3%; Average loss: 3.3287
Iteration: 1932; Percent complete: 48.3%; Average loss: 3.1369
Iteration: 1933; Percent complete: 48.3%; Average loss: 3.4693
Iteration: 1934; Percent complete: 48.4%; Average loss: 3.2070
Iteration: 1935; Percent complete: 48.4%; Average loss: 3.2716
Iteration: 1936; Percent complete: 48.4%; Average loss: 3.2274
Iteration: 1937; Percent complete: 48.4%; Average loss: 2.9853
Iteration: 1938; Percent complete: 48.4%; Average loss: 3.2132
Iteration: 1939; Percent complete: 48.5%; Average loss: 3.1635
Iteration: 1940; Percent complete: 48.5%; Average loss: 3.1784
Iteration: 1941; Percent complete: 48.5%; Average loss: 3.3177
Iteration: 1942; Percent complete: 48.5%; Average loss: 3.4860
Iteration: 1943; Percent complete: 48.6%; Average loss: 3.1364
Iteration: 1944; Percent complete: 48.6%; Average loss: 3.2897
Iteration: 1945; Percent complete: 48.6%; Average loss: 2.7045
Iteration: 1946; Percent complete: 48.6%; Average loss: 3.2703
Iteration: 1947; Percent complete: 48.7%; Average loss: 3.2479
Iteration: 1948; Percent complete: 48.7%; Average loss: 3.4708
Iteration: 1949; Percent complete: 48.7%; Average loss: 3.2437
Iteration: 1950; Percent complete: 48.8%; Average loss: 3.1065
Iteration: 1951; Percent complete: 48.8%; Average loss: 3.0791
Iteration: 1952; Percent complete: 48.8%; Average loss: 3.2052
Iteration: 1953; Percent complete: 48.8%; Average loss: 3.1054
Iteration: 1954; Percent complete: 48.9%; Average loss: 3.0942
Iteration: 1955; Percent complete: 48.9%; Average loss: 3.2920
Iteration: 1956; Percent complete: 48.9%; Average loss: 3.4357
Iteration: 1957; Percent complete: 48.9%; Average loss: 3.3365
Iteration: 1958; Percent complete: 48.9%; Average loss: 3.1336
Iteration: 1959; Percent complete: 49.0%; Average loss: 3.2036
Iteration: 1960; Percent complete: 49.0%; Average loss: 3.1072
Iteration: 1961; Percent complete: 49.0%; Average loss: 3.1260
Iteration: 1962; Percent complete: 49.0%; Average loss: 3.1649
Iteration: 1963; Percent complete: 49.1%; Average loss: 3.2040
Iteration: 1964; Percent complete: 49.1%; Average loss: 3.0346
Iteration: 1965; Percent complete: 49.1%; Average loss: 3.0644
Iteration: 1966; Percent complete: 49.1%; Average loss: 3.1042
Iteration: 1967; Percent complete: 49.2%; Average loss: 3.0429
Iteration: 1968; Percent complete: 49.2%; Average loss: 3.2558
Iteration: 1969; Percent complete: 49.2%; Average loss: 3.0409
Iteration: 1970; Percent complete: 49.2%; Average loss: 3.2037
Iteration: 1971; Percent complete: 49.3%; Average loss: 3.0921
Iteration: 1972; Percent complete: 49.3%; Average loss: 3.0512
Iteration: 1973; Percent complete: 49.3%; Average loss: 3.2344
Iteration: 1974; Percent complete: 49.4%; Average loss: 2.8960
Iteration: 1975; Percent complete: 49.4%; Average loss: 2.8336
Iteration: 1976; Percent complete: 49.4%; Average loss: 3.0386
Iteration: 1977; Percent complete: 49.4%; Average loss: 3.0551
Iteration: 1978; Percent complete: 49.5%; Average loss: 3.1907
Iteration: 1979; Percent complete: 49.5%; Average loss: 3.2041
Iteration: 1980; Percent complete: 49.5%; Average loss: 3.3300
Iteration: 1981; Percent complete: 49.5%; Average loss: 3.3061
Iteration: 1982; Percent complete: 49.5%; Average loss: 3.0935
Iteration: 1983; Percent complete: 49.6%; Average loss: 3.3127
Iteration: 1984; Percent complete: 49.6%; Average loss: 3.0735
Iteration: 1985; Percent complete: 49.6%; Average loss: 3.3961
Iteration: 1986; Percent complete: 49.6%; Average loss: 3.3684
Iteration: 1987; Percent complete: 49.7%; Average loss: 3.2883
Iteration: 1988; Percent complete: 49.7%; Average loss: 3.4938
Iteration: 1989; Percent complete: 49.7%; Average loss: 3.0131
Iteration: 1990; Percent complete: 49.8%; Average loss: 3.1073
Iteration: 1991; Percent complete: 49.8%; Average loss: 3.0273
Iteration: 1992; Percent complete: 49.8%; Average loss: 3.0475
Iteration: 1993; Percent complete: 49.8%; Average loss: 3.2725
Iteration: 1994; Percent complete: 49.9%; Average loss: 3.2420
Iteration: 1995; Percent complete: 49.9%; Average loss: 3.1786
Iteration: 1996; Percent complete: 49.9%; Average loss: 2.9148
Iteration: 1997; Percent complete: 49.9%; Average loss: 3.3422
Iteration: 1998; Percent complete: 50.0%; Average loss: 3.2229
Iteration: 1999; Percent complete: 50.0%; Average loss: 3.0386
Iteration: 2000; Percent complete: 50.0%; Average loss: 3.1885
Iteration: 2001; Percent complete: 50.0%; Average loss: 3.2798
Iteration: 2002; Percent complete: 50.0%; Average loss: 3.1214
Iteration: 2003; Percent complete: 50.1%; Average loss: 2.8565
Iteration: 2004; Percent complete: 50.1%; Average loss: 3.2035
Iteration: 2005; Percent complete: 50.1%; Average loss: 3.0742
Iteration: 2006; Percent complete: 50.1%; Average loss: 3.1385
Iteration: 2007; Percent complete: 50.2%; Average loss: 3.0997
Iteration: 2008; Percent complete: 50.2%; Average loss: 3.3137
Iteration: 2009; Percent complete: 50.2%; Average loss: 3.0754
Iteration: 2010; Percent complete: 50.2%; Average loss: 3.0767
Iteration: 2011; Percent complete: 50.3%; Average loss: 3.1843
Iteration: 2012; Percent complete: 50.3%; Average loss: 2.9766
Iteration: 2013; Percent complete: 50.3%; Average loss: 3.0399
Iteration: 2014; Percent complete: 50.3%; Average loss: 3.1906
Iteration: 2015; Percent complete: 50.4%; Average loss: 2.8984
Iteration: 2016; Percent complete: 50.4%; Average loss: 2.9797
Iteration: 2017; Percent complete: 50.4%; Average loss: 3.2122
Iteration: 2018; Percent complete: 50.4%; Average loss: 3.2790
Iteration: 2019; Percent complete: 50.5%; Average loss: 3.1770
Iteration: 2020; Percent complete: 50.5%; Average loss: 3.2402
Iteration: 2021; Percent complete: 50.5%; Average loss: 3.2121
Iteration: 2022; Percent complete: 50.5%; Average loss: 3.1358
Iteration: 2023; Percent complete: 50.6%; Average loss: 3.0520
Iteration: 2024; Percent complete: 50.6%; Average loss: 3.2629
Iteration: 2025; Percent complete: 50.6%; Average loss: 3.1253
Iteration: 2026; Percent complete: 50.6%; Average loss: 3.1365
Iteration: 2027; Percent complete: 50.7%; Average loss: 3.3201
Iteration: 2028; Percent complete: 50.7%; Average loss: 3.3793
Iteration: 2029; Percent complete: 50.7%; Average loss: 3.0653
Iteration: 2030; Percent complete: 50.7%; Average loss: 3.2130
Iteration: 2031; Percent complete: 50.8%; Average loss: 2.8600
Iteration: 2032; Percent complete: 50.8%; Average loss: 3.2671
Iteration: 2033; Percent complete: 50.8%; Average loss: 3.0220
Iteration: 2034; Percent complete: 50.8%; Average loss: 3.0985
Iteration: 2035; Percent complete: 50.9%; Average loss: 3.4451
Iteration: 2036; Percent complete: 50.9%; Average loss: 3.0782
Iteration: 2037; Percent complete: 50.9%; Average loss: 3.0855
Iteration: 2038; Percent complete: 50.9%; Average loss: 3.3773
Iteration: 2039; Percent complete: 51.0%; Average loss: 3.2152
Iteration: 2040; Percent complete: 51.0%; Average loss: 3.0248
Iteration: 2041; Percent complete: 51.0%; Average loss: 3.2214
Iteration: 2042; Percent complete: 51.0%; Average loss: 3.2299
Iteration: 2043; Percent complete: 51.1%; Average loss: 3.4753
Iteration: 2044; Percent complete: 51.1%; Average loss: 3.0757
Iteration: 2045; Percent complete: 51.1%; Average loss: 3.2033
Iteration: 2046; Percent complete: 51.1%; Average loss: 3.2806
Iteration: 2047; Percent complete: 51.2%; Average loss: 3.1475
Iteration: 2048; Percent complete: 51.2%; Average loss: 3.3100
Iteration: 2049; Percent complete: 51.2%; Average loss: 3.0632
Iteration: 2050; Percent complete: 51.2%; Average loss: 2.9671
Iteration: 2051; Percent complete: 51.3%; Average loss: 3.2118
Iteration: 2052; Percent complete: 51.3%; Average loss: 3.1385
Iteration: 2053; Percent complete: 51.3%; Average loss: 3.1402
Iteration: 2054; Percent complete: 51.3%; Average loss: 3.0690
Iteration: 2055; Percent complete: 51.4%; Average loss: 3.2058
Iteration: 2056; Percent complete: 51.4%; Average loss: 3.1688
Iteration: 2057; Percent complete: 51.4%; Average loss: 3.3319
Iteration: 2058; Percent complete: 51.4%; Average loss: 3.1324
Iteration: 2059; Percent complete: 51.5%; Average loss: 3.1883
Iteration: 2060; Percent complete: 51.5%; Average loss: 3.1043
Iteration: 2061; Percent complete: 51.5%; Average loss: 3.4056
Iteration: 2062; Percent complete: 51.5%; Average loss: 3.3334
Iteration: 2063; Percent complete: 51.6%; Average loss: 3.1752
Iteration: 2064; Percent complete: 51.6%; Average loss: 2.8773
Iteration: 2065; Percent complete: 51.6%; Average loss: 3.1951
Iteration: 2066; Percent complete: 51.6%; Average loss: 3.3045
Iteration: 2067; Percent complete: 51.7%; Average loss: 3.3515
Iteration: 2068; Percent complete: 51.7%; Average loss: 3.4054
Iteration: 2069; Percent complete: 51.7%; Average loss: 3.0235
Iteration: 2070; Percent complete: 51.7%; Average loss: 3.3373
Iteration: 2071; Percent complete: 51.8%; Average loss: 3.0042
Iteration: 2072; Percent complete: 51.8%; Average loss: 2.8903
Iteration: 2073; Percent complete: 51.8%; Average loss: 3.1922
Iteration: 2074; Percent complete: 51.8%; Average loss: 2.9601
Iteration: 2075; Percent complete: 51.9%; Average loss: 3.2391
Iteration: 2076; Percent complete: 51.9%; Average loss: 3.2074
Iteration: 2077; Percent complete: 51.9%; Average loss: 3.0672
Iteration: 2078; Percent complete: 51.9%; Average loss: 2.9583
Iteration: 2079; Percent complete: 52.0%; Average loss: 3.0848
Iteration: 2080; Percent complete: 52.0%; Average loss: 3.0431
Iteration: 2081; Percent complete: 52.0%; Average loss: 3.2110
Iteration: 2082; Percent complete: 52.0%; Average loss: 3.4781
Iteration: 2083; Percent complete: 52.1%; Average loss: 3.1190
Iteration: 2084; Percent complete: 52.1%; Average loss: 3.0829
Iteration: 2085; Percent complete: 52.1%; Average loss: 3.3524
Iteration: 2086; Percent complete: 52.1%; Average loss: 2.6940
Iteration: 2087; Percent complete: 52.2%; Average loss: 2.8690
Iteration: 2088; Percent complete: 52.2%; Average loss: 3.2673
Iteration: 2089; Percent complete: 52.2%; Average loss: 3.2644
Iteration: 2090; Percent complete: 52.2%; Average loss: 3.0440
Iteration: 2091; Percent complete: 52.3%; Average loss: 3.2501
Iteration: 2092; Percent complete: 52.3%; Average loss: 3.0635
Iteration: 2093; Percent complete: 52.3%; Average loss: 2.9801
Iteration: 2094; Percent complete: 52.3%; Average loss: 2.9995
Iteration: 2095; Percent complete: 52.4%; Average loss: 3.2192
Iteration: 2096; Percent complete: 52.4%; Average loss: 3.2653
Iteration: 2097; Percent complete: 52.4%; Average loss: 3.1847
Iteration: 2098; Percent complete: 52.4%; Average loss: 3.2581
Iteration: 2099; Percent complete: 52.5%; Average loss: 3.2885
Iteration: 2100; Percent complete: 52.5%; Average loss: 3.3471
Iteration: 2101; Percent complete: 52.5%; Average loss: 3.1951
Iteration: 2102; Percent complete: 52.5%; Average loss: 3.1524
Iteration: 2103; Percent complete: 52.6%; Average loss: 3.0525
Iteration: 2104; Percent complete: 52.6%; Average loss: 2.8778
Iteration: 2105; Percent complete: 52.6%; Average loss: 3.1565
Iteration: 2106; Percent complete: 52.6%; Average loss: 3.1879
Iteration: 2107; Percent complete: 52.7%; Average loss: 3.0379
Iteration: 2108; Percent complete: 52.7%; Average loss: 2.9813
Iteration: 2109; Percent complete: 52.7%; Average loss: 3.1054
Iteration: 2110; Percent complete: 52.8%; Average loss: 3.0271
Iteration: 2111; Percent complete: 52.8%; Average loss: 2.9230
Iteration: 2112; Percent complete: 52.8%; Average loss: 3.2731
Iteration: 2113; Percent complete: 52.8%; Average loss: 3.4646
Iteration: 2114; Percent complete: 52.8%; Average loss: 3.3418
Iteration: 2115; Percent complete: 52.9%; Average loss: 2.8846
Iteration: 2116; Percent complete: 52.9%; Average loss: 3.1280
Iteration: 2117; Percent complete: 52.9%; Average loss: 2.9832
Iteration: 2118; Percent complete: 52.9%; Average loss: 3.1778
Iteration: 2119; Percent complete: 53.0%; Average loss: 2.9044
Iteration: 2120; Percent complete: 53.0%; Average loss: 3.2774
Iteration: 2121; Percent complete: 53.0%; Average loss: 3.0731
Iteration: 2122; Percent complete: 53.0%; Average loss: 2.9673
Iteration: 2123; Percent complete: 53.1%; Average loss: 2.9695
Iteration: 2124; Percent complete: 53.1%; Average loss: 3.1615
Iteration: 2125; Percent complete: 53.1%; Average loss: 3.1231
Iteration: 2126; Percent complete: 53.1%; Average loss: 3.1567
Iteration: 2127; Percent complete: 53.2%; Average loss: 3.0974
Iteration: 2128; Percent complete: 53.2%; Average loss: 3.0872
Iteration: 2129; Percent complete: 53.2%; Average loss: 3.1908
Iteration: 2130; Percent complete: 53.2%; Average loss: 3.1331
Iteration: 2131; Percent complete: 53.3%; Average loss: 3.2270
Iteration: 2132; Percent complete: 53.3%; Average loss: 2.9268
Iteration: 2133; Percent complete: 53.3%; Average loss: 3.1645
Iteration: 2134; Percent complete: 53.3%; Average loss: 3.1789
Iteration: 2135; Percent complete: 53.4%; Average loss: 3.1944
Iteration: 2136; Percent complete: 53.4%; Average loss: 3.1191
Iteration: 2137; Percent complete: 53.4%; Average loss: 3.1026
Iteration: 2138; Percent complete: 53.4%; Average loss: 3.0710
Iteration: 2139; Percent complete: 53.5%; Average loss: 2.8133
Iteration: 2140; Percent complete: 53.5%; Average loss: 2.9651
Iteration: 2141; Percent complete: 53.5%; Average loss: 3.2367
Iteration: 2142; Percent complete: 53.5%; Average loss: 3.1923
Iteration: 2143; Percent complete: 53.6%; Average loss: 3.1042
Iteration: 2144; Percent complete: 53.6%; Average loss: 2.8803
Iteration: 2145; Percent complete: 53.6%; Average loss: 3.1843
Iteration: 2146; Percent complete: 53.6%; Average loss: 2.9970
Iteration: 2147; Percent complete: 53.7%; Average loss: 3.0298
Iteration: 2148; Percent complete: 53.7%; Average loss: 2.8902
Iteration: 2149; Percent complete: 53.7%; Average loss: 3.0483
Iteration: 2150; Percent complete: 53.8%; Average loss: 3.2024
Iteration: 2151; Percent complete: 53.8%; Average loss: 2.8153
Iteration: 2152; Percent complete: 53.8%; Average loss: 3.1378
Iteration: 2153; Percent complete: 53.8%; Average loss: 3.2825
Iteration: 2154; Percent complete: 53.8%; Average loss: 3.1788
Iteration: 2155; Percent complete: 53.9%; Average loss: 3.3989
Iteration: 2156; Percent complete: 53.9%; Average loss: 3.1609
Iteration: 2157; Percent complete: 53.9%; Average loss: 3.0459
Iteration: 2158; Percent complete: 53.9%; Average loss: 3.1879
Iteration: 2159; Percent complete: 54.0%; Average loss: 3.4214
Iteration: 2160; Percent complete: 54.0%; Average loss: 3.1671
Iteration: 2161; Percent complete: 54.0%; Average loss: 3.1472
Iteration: 2162; Percent complete: 54.0%; Average loss: 3.2832
Iteration: 2163; Percent complete: 54.1%; Average loss: 3.0838
Iteration: 2164; Percent complete: 54.1%; Average loss: 3.4100
Iteration: 2165; Percent complete: 54.1%; Average loss: 3.2934
Iteration: 2166; Percent complete: 54.1%; Average loss: 3.1999
Iteration: 2167; Percent complete: 54.2%; Average loss: 2.9813
Iteration: 2168; Percent complete: 54.2%; Average loss: 3.1093
Iteration: 2169; Percent complete: 54.2%; Average loss: 3.0978
Iteration: 2170; Percent complete: 54.2%; Average loss: 3.1414
Iteration: 2171; Percent complete: 54.3%; Average loss: 3.4463
Iteration: 2172; Percent complete: 54.3%; Average loss: 2.9501
Iteration: 2173; Percent complete: 54.3%; Average loss: 3.0975
Iteration: 2174; Percent complete: 54.4%; Average loss: 3.0241
Iteration: 2175; Percent complete: 54.4%; Average loss: 3.1217
Iteration: 2176; Percent complete: 54.4%; Average loss: 3.1918
Iteration: 2177; Percent complete: 54.4%; Average loss: 3.3318
Iteration: 2178; Percent complete: 54.4%; Average loss: 3.1768
Iteration: 2179; Percent complete: 54.5%; Average loss: 3.3286
Iteration: 2180; Percent complete: 54.5%; Average loss: 3.0488
Iteration: 2181; Percent complete: 54.5%; Average loss: 3.1515
Iteration: 2182; Percent complete: 54.5%; Average loss: 3.0943
Iteration: 2183; Percent complete: 54.6%; Average loss: 3.0244
Iteration: 2184; Percent complete: 54.6%; Average loss: 2.9802
Iteration: 2185; Percent complete: 54.6%; Average loss: 3.1952
Iteration: 2186; Percent complete: 54.6%; Average loss: 3.2138
Iteration: 2187; Percent complete: 54.7%; Average loss: 3.1693
Iteration: 2188; Percent complete: 54.7%; Average loss: 2.9843
Iteration: 2189; Percent complete: 54.7%; Average loss: 3.0168
Iteration: 2190; Percent complete: 54.8%; Average loss: 3.1766
Iteration: 2191; Percent complete: 54.8%; Average loss: 3.0570
Iteration: 2192; Percent complete: 54.8%; Average loss: 2.9697
Iteration: 2193; Percent complete: 54.8%; Average loss: 2.8644
Iteration: 2194; Percent complete: 54.9%; Average loss: 3.1582
Iteration: 2195; Percent complete: 54.9%; Average loss: 3.0865
Iteration: 2196; Percent complete: 54.9%; Average loss: 2.8316
Iteration: 2197; Percent complete: 54.9%; Average loss: 3.3788
Iteration: 2198; Percent complete: 54.9%; Average loss: 3.1026
Iteration: 2199; Percent complete: 55.0%; Average loss: 3.1368
Iteration: 2200; Percent complete: 55.0%; Average loss: 3.3400
Iteration: 2201; Percent complete: 55.0%; Average loss: 3.0765
Iteration: 2202; Percent complete: 55.0%; Average loss: 3.0646
Iteration: 2203; Percent complete: 55.1%; Average loss: 3.2502
Iteration: 2204; Percent complete: 55.1%; Average loss: 3.3486
Iteration: 2205; Percent complete: 55.1%; Average loss: 3.0242
Iteration: 2206; Percent complete: 55.1%; Average loss: 2.9812
Iteration: 2207; Percent complete: 55.2%; Average loss: 3.1025
Iteration: 2208; Percent complete: 55.2%; Average loss: 3.3482
Iteration: 2209; Percent complete: 55.2%; Average loss: 3.2573
Iteration: 2210; Percent complete: 55.2%; Average loss: 3.1652
Iteration: 2211; Percent complete: 55.3%; Average loss: 3.0922
Iteration: 2212; Percent complete: 55.3%; Average loss: 2.8757
Iteration: 2213; Percent complete: 55.3%; Average loss: 3.1065
Iteration: 2214; Percent complete: 55.4%; Average loss: 2.9581
Iteration: 2215; Percent complete: 55.4%; Average loss: 3.2639
Iteration: 2216; Percent complete: 55.4%; Average loss: 2.8609
Iteration: 2217; Percent complete: 55.4%; Average loss: 3.0074
Iteration: 2218; Percent complete: 55.5%; Average loss: 2.9949
Iteration: 2219; Percent complete: 55.5%; Average loss: 2.8469
Iteration: 2220; Percent complete: 55.5%; Average loss: 2.9474
Iteration: 2221; Percent complete: 55.5%; Average loss: 2.9614
Iteration: 2222; Percent complete: 55.5%; Average loss: 3.2017
Iteration: 2223; Percent complete: 55.6%; Average loss: 3.3687
Iteration: 2224; Percent complete: 55.6%; Average loss: 3.2196
Iteration: 2225; Percent complete: 55.6%; Average loss: 3.1698
Iteration: 2226; Percent complete: 55.6%; Average loss: 2.9210
Iteration: 2227; Percent complete: 55.7%; Average loss: 3.0623
Iteration: 2228; Percent complete: 55.7%; Average loss: 2.8399
Iteration: 2229; Percent complete: 55.7%; Average loss: 2.9974
Iteration: 2230; Percent complete: 55.8%; Average loss: 2.9579
Iteration: 2231; Percent complete: 55.8%; Average loss: 3.0262
Iteration: 2232; Percent complete: 55.8%; Average loss: 3.1370
Iteration: 2233; Percent complete: 55.8%; Average loss: 3.2111
Iteration: 2234; Percent complete: 55.9%; Average loss: 3.1803
Iteration: 2235; Percent complete: 55.9%; Average loss: 3.0590
Iteration: 2236; Percent complete: 55.9%; Average loss: 3.0746
Iteration: 2237; Percent complete: 55.9%; Average loss: 3.1180
Iteration: 2238; Percent complete: 56.0%; Average loss: 2.9758
Iteration: 2239; Percent complete: 56.0%; Average loss: 2.7995
Iteration: 2240; Percent complete: 56.0%; Average loss: 3.2813
Iteration: 2241; Percent complete: 56.0%; Average loss: 3.3612
Iteration: 2242; Percent complete: 56.0%; Average loss: 3.1778
Iteration: 2243; Percent complete: 56.1%; Average loss: 3.0810
Iteration: 2244; Percent complete: 56.1%; Average loss: 2.8012
Iteration: 2245; Percent complete: 56.1%; Average loss: 3.0384
Iteration: 2246; Percent complete: 56.1%; Average loss: 3.1409
Iteration: 2247; Percent complete: 56.2%; Average loss: 3.1149
Iteration: 2248; Percent complete: 56.2%; Average loss: 3.2284
Iteration: 2249; Percent complete: 56.2%; Average loss: 3.0364
Iteration: 2250; Percent complete: 56.2%; Average loss: 3.1924
Iteration: 2251; Percent complete: 56.3%; Average loss: 2.9805
Iteration: 2252; Percent complete: 56.3%; Average loss: 3.0967
Iteration: 2253; Percent complete: 56.3%; Average loss: 3.0162
Iteration: 2254; Percent complete: 56.4%; Average loss: 3.1016
Iteration: 2255; Percent complete: 56.4%; Average loss: 2.8262
Iteration: 2256; Percent complete: 56.4%; Average loss: 3.0577
Iteration: 2257; Percent complete: 56.4%; Average loss: 3.0260
Iteration: 2258; Percent complete: 56.5%; Average loss: 2.8472
Iteration: 2259; Percent complete: 56.5%; Average loss: 3.0317
Iteration: 2260; Percent complete: 56.5%; Average loss: 3.2581
Iteration: 2261; Percent complete: 56.5%; Average loss: 3.1369
Iteration: 2262; Percent complete: 56.5%; Average loss: 3.0738
Iteration: 2263; Percent complete: 56.6%; Average loss: 2.8910
Iteration: 2264; Percent complete: 56.6%; Average loss: 3.1521
Iteration: 2265; Percent complete: 56.6%; Average loss: 3.1234
Iteration: 2266; Percent complete: 56.6%; Average loss: 3.1126
Iteration: 2267; Percent complete: 56.7%; Average loss: 3.1601
Iteration: 2268; Percent complete: 56.7%; Average loss: 3.0718
Iteration: 2269; Percent complete: 56.7%; Average loss: 3.4267
Iteration: 2270; Percent complete: 56.8%; Average loss: 3.2064
Iteration: 2271; Percent complete: 56.8%; Average loss: 3.3755
Iteration: 2272; Percent complete: 56.8%; Average loss: 2.8809
Iteration: 2273; Percent complete: 56.8%; Average loss: 3.0771
Iteration: 2274; Percent complete: 56.9%; Average loss: 3.0610
Iteration: 2275; Percent complete: 56.9%; Average loss: 2.9614
Iteration: 2276; Percent complete: 56.9%; Average loss: 2.9576
Iteration: 2277; Percent complete: 56.9%; Average loss: 2.9867
Iteration: 2278; Percent complete: 57.0%; Average loss: 3.0540
Iteration: 2279; Percent complete: 57.0%; Average loss: 2.9509
Iteration: 2280; Percent complete: 57.0%; Average loss: 3.0314
Iteration: 2281; Percent complete: 57.0%; Average loss: 3.0769
Iteration: 2282; Percent complete: 57.0%; Average loss: 3.1794
Iteration: 2283; Percent complete: 57.1%; Average loss: 3.0178
Iteration: 2284; Percent complete: 57.1%; Average loss: 3.3490
Iteration: 2285; Percent complete: 57.1%; Average loss: 3.1315
Iteration: 2286; Percent complete: 57.1%; Average loss: 3.1162
Iteration: 2287; Percent complete: 57.2%; Average loss: 3.1713
Iteration: 2288; Percent complete: 57.2%; Average loss: 2.9722
Iteration: 2289; Percent complete: 57.2%; Average loss: 3.0943
Iteration: 2290; Percent complete: 57.2%; Average loss: 2.9709
Iteration: 2291; Percent complete: 57.3%; Average loss: 3.1759
Iteration: 2292; Percent complete: 57.3%; Average loss: 3.2766
Iteration: 2293; Percent complete: 57.3%; Average loss: 2.8917
Iteration: 2294; Percent complete: 57.4%; Average loss: 3.1286
Iteration: 2295; Percent complete: 57.4%; Average loss: 3.2461
Iteration: 2296; Percent complete: 57.4%; Average loss: 2.9210
Iteration: 2297; Percent complete: 57.4%; Average loss: 2.9506
Iteration: 2298; Percent complete: 57.5%; Average loss: 3.1549
Iteration: 2299; Percent complete: 57.5%; Average loss: 3.1420
Iteration: 2300; Percent complete: 57.5%; Average loss: 3.0256
Iteration: 2301; Percent complete: 57.5%; Average loss: 3.0765
Iteration: 2302; Percent complete: 57.6%; Average loss: 3.2814
Iteration: 2303; Percent complete: 57.6%; Average loss: 2.9943
Iteration: 2304; Percent complete: 57.6%; Average loss: 3.2805
Iteration: 2305; Percent complete: 57.6%; Average loss: 2.9521
Iteration: 2306; Percent complete: 57.6%; Average loss: 3.1465
Iteration: 2307; Percent complete: 57.7%; Average loss: 3.2121
Iteration: 2308; Percent complete: 57.7%; Average loss: 3.1370
Iteration: 2309; Percent complete: 57.7%; Average loss: 3.3185
Iteration: 2310; Percent complete: 57.8%; Average loss: 3.0885
Iteration: 2311; Percent complete: 57.8%; Average loss: 3.0326
Iteration: 2312; Percent complete: 57.8%; Average loss: 3.0677
Iteration: 2313; Percent complete: 57.8%; Average loss: 3.1301
Iteration: 2314; Percent complete: 57.9%; Average loss: 2.8898
Iteration: 2315; Percent complete: 57.9%; Average loss: 3.0179
Iteration: 2316; Percent complete: 57.9%; Average loss: 3.1309
Iteration: 2317; Percent complete: 57.9%; Average loss: 2.8813
Iteration: 2318; Percent complete: 58.0%; Average loss: 2.8218
Iteration: 2319; Percent complete: 58.0%; Average loss: 3.1092
Iteration: 2320; Percent complete: 58.0%; Average loss: 3.0440
Iteration: 2321; Percent complete: 58.0%; Average loss: 3.0820
Iteration: 2322; Percent complete: 58.1%; Average loss: 3.2727
Iteration: 2323; Percent complete: 58.1%; Average loss: 3.0688
Iteration: 2324; Percent complete: 58.1%; Average loss: 2.9237
Iteration: 2325; Percent complete: 58.1%; Average loss: 3.1290
Iteration: 2326; Percent complete: 58.1%; Average loss: 2.8989
Iteration: 2327; Percent complete: 58.2%; Average loss: 3.0278
Iteration: 2328; Percent complete: 58.2%; Average loss: 3.0471
Iteration: 2329; Percent complete: 58.2%; Average loss: 3.1413
Iteration: 2330; Percent complete: 58.2%; Average loss: 3.1216
Iteration: 2331; Percent complete: 58.3%; Average loss: 2.8327
Iteration: 2332; Percent complete: 58.3%; Average loss: 2.9773
Iteration: 2333; Percent complete: 58.3%; Average loss: 2.9962
Iteration: 2334; Percent complete: 58.4%; Average loss: 2.9372
Iteration: 2335; Percent complete: 58.4%; Average loss: 3.1247
Iteration: 2336; Percent complete: 58.4%; Average loss: 3.1584
Iteration: 2337; Percent complete: 58.4%; Average loss: 3.1736
Iteration: 2338; Percent complete: 58.5%; Average loss: 2.8532
Iteration: 2339; Percent complete: 58.5%; Average loss: 2.9371
Iteration: 2340; Percent complete: 58.5%; Average loss: 3.2757
Iteration: 2341; Percent complete: 58.5%; Average loss: 2.7779
Iteration: 2342; Percent complete: 58.6%; Average loss: 3.2676
Iteration: 2343; Percent complete: 58.6%; Average loss: 3.2478
Iteration: 2344; Percent complete: 58.6%; Average loss: 3.0013
Iteration: 2345; Percent complete: 58.6%; Average loss: 2.8251
Iteration: 2346; Percent complete: 58.7%; Average loss: 2.8290
Iteration: 2347; Percent complete: 58.7%; Average loss: 3.1245
Iteration: 2348; Percent complete: 58.7%; Average loss: 2.9675
Iteration: 2349; Percent complete: 58.7%; Average loss: 3.0120
Iteration: 2350; Percent complete: 58.8%; Average loss: 3.0836
Iteration: 2351; Percent complete: 58.8%; Average loss: 3.1796
Iteration: 2352; Percent complete: 58.8%; Average loss: 2.9652
Iteration: 2353; Percent complete: 58.8%; Average loss: 2.9008
Iteration: 2354; Percent complete: 58.9%; Average loss: 2.8571
Iteration: 2355; Percent complete: 58.9%; Average loss: 3.3899
Iteration: 2356; Percent complete: 58.9%; Average loss: 3.2797
Iteration: 2357; Percent complete: 58.9%; Average loss: 3.2116
Iteration: 2358; Percent complete: 59.0%; Average loss: 2.8788
Iteration: 2359; Percent complete: 59.0%; Average loss: 3.3218
Iteration: 2360; Percent complete: 59.0%; Average loss: 3.1450
Iteration: 2361; Percent complete: 59.0%; Average loss: 3.1551
Iteration: 2362; Percent complete: 59.1%; Average loss: 3.1687
Iteration: 2363; Percent complete: 59.1%; Average loss: 3.3348
Iteration: 2364; Percent complete: 59.1%; Average loss: 3.0719
Iteration: 2365; Percent complete: 59.1%; Average loss: 2.7468
Iteration: 2366; Percent complete: 59.2%; Average loss: 2.9465
Iteration: 2367; Percent complete: 59.2%; Average loss: 3.1869
Iteration: 2368; Percent complete: 59.2%; Average loss: 2.9814
Iteration: 2369; Percent complete: 59.2%; Average loss: 2.9689
Iteration: 2370; Percent complete: 59.2%; Average loss: 3.0697
Iteration: 2371; Percent complete: 59.3%; Average loss: 3.3275
Iteration: 2372; Percent complete: 59.3%; Average loss: 3.1246
Iteration: 2373; Percent complete: 59.3%; Average loss: 2.9814
Iteration: 2374; Percent complete: 59.4%; Average loss: 3.3031
Iteration: 2375; Percent complete: 59.4%; Average loss: 3.0846
Iteration: 2376; Percent complete: 59.4%; Average loss: 2.9283
Iteration: 2377; Percent complete: 59.4%; Average loss: 3.2088
Iteration: 2378; Percent complete: 59.5%; Average loss: 3.0812
Iteration: 2379; Percent complete: 59.5%; Average loss: 3.1183
Iteration: 2380; Percent complete: 59.5%; Average loss: 3.0911
Iteration: 2381; Percent complete: 59.5%; Average loss: 3.1512
Iteration: 2382; Percent complete: 59.6%; Average loss: 3.1545
Iteration: 2383; Percent complete: 59.6%; Average loss: 3.1464
Iteration: 2384; Percent complete: 59.6%; Average loss: 2.9574
Iteration: 2385; Percent complete: 59.6%; Average loss: 3.0957
Iteration: 2386; Percent complete: 59.7%; Average loss: 2.9608
Iteration: 2387; Percent complete: 59.7%; Average loss: 3.2603
Iteration: 2388; Percent complete: 59.7%; Average loss: 2.9044
Iteration: 2389; Percent complete: 59.7%; Average loss: 3.1969
Iteration: 2390; Percent complete: 59.8%; Average loss: 3.0691
Iteration: 2391; Percent complete: 59.8%; Average loss: 2.9014
Iteration: 2392; Percent complete: 59.8%; Average loss: 3.0873
Iteration: 2393; Percent complete: 59.8%; Average loss: 3.3207
Iteration: 2394; Percent complete: 59.9%; Average loss: 3.0908
Iteration: 2395; Percent complete: 59.9%; Average loss: 2.8936
Iteration: 2396; Percent complete: 59.9%; Average loss: 3.1893
Iteration: 2397; Percent complete: 59.9%; Average loss: 2.7825
Iteration: 2398; Percent complete: 60.0%; Average loss: 3.1908
Iteration: 2399; Percent complete: 60.0%; Average loss: 2.8886
Iteration: 2400; Percent complete: 60.0%; Average loss: 3.0214
Iteration: 2401; Percent complete: 60.0%; Average loss: 3.3402
Iteration: 2402; Percent complete: 60.1%; Average loss: 3.1693
Iteration: 2403; Percent complete: 60.1%; Average loss: 3.0312
Iteration: 2404; Percent complete: 60.1%; Average loss: 3.0791
Iteration: 2405; Percent complete: 60.1%; Average loss: 2.9219
Iteration: 2406; Percent complete: 60.2%; Average loss: 3.2236
Iteration: 2407; Percent complete: 60.2%; Average loss: 2.8136
Iteration: 2408; Percent complete: 60.2%; Average loss: 2.9028
Iteration: 2409; Percent complete: 60.2%; Average loss: 3.0340
Iteration: 2410; Percent complete: 60.2%; Average loss: 2.7716
Iteration: 2411; Percent complete: 60.3%; Average loss: 3.0266
Iteration: 2412; Percent complete: 60.3%; Average loss: 3.1723
Iteration: 2413; Percent complete: 60.3%; Average loss: 3.3084
Iteration: 2414; Percent complete: 60.4%; Average loss: 2.8961
Iteration: 2415; Percent complete: 60.4%; Average loss: 3.1446
Iteration: 2416; Percent complete: 60.4%; Average loss: 2.9899
Iteration: 2417; Percent complete: 60.4%; Average loss: 3.1306
Iteration: 2418; Percent complete: 60.5%; Average loss: 2.9058
Iteration: 2419; Percent complete: 60.5%; Average loss: 2.9460
Iteration: 2420; Percent complete: 60.5%; Average loss: 2.9559
Iteration: 2421; Percent complete: 60.5%; Average loss: 3.1326
Iteration: 2422; Percent complete: 60.6%; Average loss: 3.0309
Iteration: 2423; Percent complete: 60.6%; Average loss: 3.0342
Iteration: 2424; Percent complete: 60.6%; Average loss: 3.0159
Iteration: 2425; Percent complete: 60.6%; Average loss: 3.1978
Iteration: 2426; Percent complete: 60.7%; Average loss: 3.0665
Iteration: 2427; Percent complete: 60.7%; Average loss: 2.9932
Iteration: 2428; Percent complete: 60.7%; Average loss: 3.0661
Iteration: 2429; Percent complete: 60.7%; Average loss: 3.2710
Iteration: 2430; Percent complete: 60.8%; Average loss: 3.2208
Iteration: 2431; Percent complete: 60.8%; Average loss: 2.9489
Iteration: 2432; Percent complete: 60.8%; Average loss: 2.9550
Iteration: 2433; Percent complete: 60.8%; Average loss: 3.0354
Iteration: 2434; Percent complete: 60.9%; Average loss: 2.9881
Iteration: 2435; Percent complete: 60.9%; Average loss: 3.0334
Iteration: 2436; Percent complete: 60.9%; Average loss: 3.2165
Iteration: 2437; Percent complete: 60.9%; Average loss: 2.8622
Iteration: 2438; Percent complete: 61.0%; Average loss: 2.9002
Iteration: 2439; Percent complete: 61.0%; Average loss: 2.9894
Iteration: 2440; Percent complete: 61.0%; Average loss: 3.0656
Iteration: 2441; Percent complete: 61.0%; Average loss: 3.0998
Iteration: 2442; Percent complete: 61.1%; Average loss: 2.7171
Iteration: 2443; Percent complete: 61.1%; Average loss: 2.8431
Iteration: 2444; Percent complete: 61.1%; Average loss: 3.0061
Iteration: 2445; Percent complete: 61.1%; Average loss: 3.1404
Iteration: 2446; Percent complete: 61.2%; Average loss: 3.3706
Iteration: 2447; Percent complete: 61.2%; Average loss: 2.9799
Iteration: 2448; Percent complete: 61.2%; Average loss: 3.0131
Iteration: 2449; Percent complete: 61.2%; Average loss: 3.0876
Iteration: 2450; Percent complete: 61.3%; Average loss: 3.0130
Iteration: 2451; Percent complete: 61.3%; Average loss: 3.0794
Iteration: 2452; Percent complete: 61.3%; Average loss: 2.9115
Iteration: 2453; Percent complete: 61.3%; Average loss: 3.2102
Iteration: 2454; Percent complete: 61.4%; Average loss: 2.9494
Iteration: 2455; Percent complete: 61.4%; Average loss: 3.1256
Iteration: 2456; Percent complete: 61.4%; Average loss: 2.8421
Iteration: 2457; Percent complete: 61.4%; Average loss: 3.2796
Iteration: 2458; Percent complete: 61.5%; Average loss: 2.9985
Iteration: 2459; Percent complete: 61.5%; Average loss: 3.0632
Iteration: 2460; Percent complete: 61.5%; Average loss: 2.9508
Iteration: 2461; Percent complete: 61.5%; Average loss: 3.4307
Iteration: 2462; Percent complete: 61.6%; Average loss: 2.9871
Iteration: 2463; Percent complete: 61.6%; Average loss: 2.7180
Iteration: 2464; Percent complete: 61.6%; Average loss: 3.0876
Iteration: 2465; Percent complete: 61.6%; Average loss: 2.9628
Iteration: 2466; Percent complete: 61.7%; Average loss: 3.0350
Iteration: 2467; Percent complete: 61.7%; Average loss: 3.2305
Iteration: 2468; Percent complete: 61.7%; Average loss: 3.0565
Iteration: 2469; Percent complete: 61.7%; Average loss: 3.2771
Iteration: 2470; Percent complete: 61.8%; Average loss: 3.1715
Iteration: 2471; Percent complete: 61.8%; Average loss: 2.9543
Iteration: 2472; Percent complete: 61.8%; Average loss: 2.9739
Iteration: 2473; Percent complete: 61.8%; Average loss: 2.9877
Iteration: 2474; Percent complete: 61.9%; Average loss: 2.9525
Iteration: 2475; Percent complete: 61.9%; Average loss: 2.9614
Iteration: 2476; Percent complete: 61.9%; Average loss: 3.2932
Iteration: 2477; Percent complete: 61.9%; Average loss: 3.0055
Iteration: 2478; Percent complete: 62.0%; Average loss: 3.0409
Iteration: 2479; Percent complete: 62.0%; Average loss: 3.2281
Iteration: 2480; Percent complete: 62.0%; Average loss: 3.0566
Iteration: 2481; Percent complete: 62.0%; Average loss: 2.8094
Iteration: 2482; Percent complete: 62.1%; Average loss: 3.2462
Iteration: 2483; Percent complete: 62.1%; Average loss: 3.3124
Iteration: 2484; Percent complete: 62.1%; Average loss: 3.0894
Iteration: 2485; Percent complete: 62.1%; Average loss: 3.0414
Iteration: 2486; Percent complete: 62.2%; Average loss: 2.7987
Iteration: 2487; Percent complete: 62.2%; Average loss: 2.9899
Iteration: 2488; Percent complete: 62.2%; Average loss: 2.8995
Iteration: 2489; Percent complete: 62.2%; Average loss: 3.3667
Iteration: 2490; Percent complete: 62.3%; Average loss: 3.0882
Iteration: 2491; Percent complete: 62.3%; Average loss: 3.1680
Iteration: 2492; Percent complete: 62.3%; Average loss: 3.1315
Iteration: 2493; Percent complete: 62.3%; Average loss: 2.8414
Iteration: 2494; Percent complete: 62.4%; Average loss: 3.0416
Iteration: 2495; Percent complete: 62.4%; Average loss: 2.7278
Iteration: 2496; Percent complete: 62.4%; Average loss: 3.1049
Iteration: 2497; Percent complete: 62.4%; Average loss: 3.0155
Iteration: 2498; Percent complete: 62.5%; Average loss: 3.0376
Iteration: 2499; Percent complete: 62.5%; Average loss: 3.0464
Iteration: 2500; Percent complete: 62.5%; Average loss: 3.2910
Iteration: 2501; Percent complete: 62.5%; Average loss: 2.7962
Iteration: 2502; Percent complete: 62.5%; Average loss: 3.2267
Iteration: 2503; Percent complete: 62.6%; Average loss: 2.8288
Iteration: 2504; Percent complete: 62.6%; Average loss: 3.1614
Iteration: 2505; Percent complete: 62.6%; Average loss: 2.9846
Iteration: 2506; Percent complete: 62.6%; Average loss: 3.0191
Iteration: 2507; Percent complete: 62.7%; Average loss: 2.7547
Iteration: 2508; Percent complete: 62.7%; Average loss: 2.8725
Iteration: 2509; Percent complete: 62.7%; Average loss: 2.8855
Iteration: 2510; Percent complete: 62.7%; Average loss: 3.1688
Iteration: 2511; Percent complete: 62.8%; Average loss: 2.7911
Iteration: 2512; Percent complete: 62.8%; Average loss: 2.8006
Iteration: 2513; Percent complete: 62.8%; Average loss: 3.0403
Iteration: 2514; Percent complete: 62.8%; Average loss: 3.0640
Iteration: 2515; Percent complete: 62.9%; Average loss: 3.1657
Iteration: 2516; Percent complete: 62.9%; Average loss: 3.0269
Iteration: 2517; Percent complete: 62.9%; Average loss: 2.9447
Iteration: 2518; Percent complete: 62.9%; Average loss: 3.0420
Iteration: 2519; Percent complete: 63.0%; Average loss: 2.9414
Iteration: 2520; Percent complete: 63.0%; Average loss: 3.0638
Iteration: 2521; Percent complete: 63.0%; Average loss: 3.0130
Iteration: 2522; Percent complete: 63.0%; Average loss: 3.1651
Iteration: 2523; Percent complete: 63.1%; Average loss: 3.0998
Iteration: 2524; Percent complete: 63.1%; Average loss: 2.8677
Iteration: 2525; Percent complete: 63.1%; Average loss: 2.9797
Iteration: 2526; Percent complete: 63.1%; Average loss: 2.8549
Iteration: 2527; Percent complete: 63.2%; Average loss: 3.1656
Iteration: 2528; Percent complete: 63.2%; Average loss: 3.1684
Iteration: 2529; Percent complete: 63.2%; Average loss: 3.1961
Iteration: 2530; Percent complete: 63.2%; Average loss: 3.3735
Iteration: 2531; Percent complete: 63.3%; Average loss: 3.4309
Iteration: 2532; Percent complete: 63.3%; Average loss: 3.0507
Iteration: 2533; Percent complete: 63.3%; Average loss: 2.9819
Iteration: 2534; Percent complete: 63.3%; Average loss: 3.1189
Iteration: 2535; Percent complete: 63.4%; Average loss: 3.0160
Iteration: 2536; Percent complete: 63.4%; Average loss: 3.0901
Iteration: 2537; Percent complete: 63.4%; Average loss: 2.9879
Iteration: 2538; Percent complete: 63.4%; Average loss: 3.1696
Iteration: 2539; Percent complete: 63.5%; Average loss: 3.0573
Iteration: 2540; Percent complete: 63.5%; Average loss: 2.8336
Iteration: 2541; Percent complete: 63.5%; Average loss: 3.0748
Iteration: 2542; Percent complete: 63.5%; Average loss: 3.0668
Iteration: 2543; Percent complete: 63.6%; Average loss: 3.0631
Iteration: 2544; Percent complete: 63.6%; Average loss: 2.9578
Iteration: 2545; Percent complete: 63.6%; Average loss: 3.1082
Iteration: 2546; Percent complete: 63.6%; Average loss: 3.0380
Iteration: 2547; Percent complete: 63.7%; Average loss: 3.0315
Iteration: 2548; Percent complete: 63.7%; Average loss: 3.0879
Iteration: 2549; Percent complete: 63.7%; Average loss: 3.1167
Iteration: 2550; Percent complete: 63.7%; Average loss: 3.0085
Iteration: 2551; Percent complete: 63.8%; Average loss: 2.9578
Iteration: 2552; Percent complete: 63.8%; Average loss: 2.9789
Iteration: 2553; Percent complete: 63.8%; Average loss: 2.8517
Iteration: 2554; Percent complete: 63.8%; Average loss: 2.9497
Iteration: 2555; Percent complete: 63.9%; Average loss: 3.3323
Iteration: 2556; Percent complete: 63.9%; Average loss: 2.7615
Iteration: 2557; Percent complete: 63.9%; Average loss: 2.7704
Iteration: 2558; Percent complete: 63.9%; Average loss: 3.2037
Iteration: 2559; Percent complete: 64.0%; Average loss: 3.1580
Iteration: 2560; Percent complete: 64.0%; Average loss: 3.0580
Iteration: 2561; Percent complete: 64.0%; Average loss: 2.8348
Iteration: 2562; Percent complete: 64.0%; Average loss: 3.0915
Iteration: 2563; Percent complete: 64.1%; Average loss: 2.9932
Iteration: 2564; Percent complete: 64.1%; Average loss: 2.8975
Iteration: 2565; Percent complete: 64.1%; Average loss: 2.7228
Iteration: 2566; Percent complete: 64.1%; Average loss: 2.9773
Iteration: 2567; Percent complete: 64.2%; Average loss: 3.1981
Iteration: 2568; Percent complete: 64.2%; Average loss: 3.0341
Iteration: 2569; Percent complete: 64.2%; Average loss: 2.9958
Iteration: 2570; Percent complete: 64.2%; Average loss: 3.1875
Iteration: 2571; Percent complete: 64.3%; Average loss: 2.9266
Iteration: 2572; Percent complete: 64.3%; Average loss: 3.0367
Iteration: 2573; Percent complete: 64.3%; Average loss: 3.0299
Iteration: 2574; Percent complete: 64.3%; Average loss: 2.8756
Iteration: 2575; Percent complete: 64.4%; Average loss: 3.0623
Iteration: 2576; Percent complete: 64.4%; Average loss: 2.6953
Iteration: 2577; Percent complete: 64.4%; Average loss: 3.1712
Iteration: 2578; Percent complete: 64.5%; Average loss: 2.8114
Iteration: 2579; Percent complete: 64.5%; Average loss: 2.9153
Iteration: 2580; Percent complete: 64.5%; Average loss: 2.9391
Iteration: 2581; Percent complete: 64.5%; Average loss: 2.8657
Iteration: 2582; Percent complete: 64.5%; Average loss: 3.0246
Iteration: 2583; Percent complete: 64.6%; Average loss: 3.1247
Iteration: 2584; Percent complete: 64.6%; Average loss: 2.9787
Iteration: 2585; Percent complete: 64.6%; Average loss: 2.7838
Iteration: 2586; Percent complete: 64.6%; Average loss: 2.9669
Iteration: 2587; Percent complete: 64.7%; Average loss: 3.1565
Iteration: 2588; Percent complete: 64.7%; Average loss: 2.8653
Iteration: 2589; Percent complete: 64.7%; Average loss: 2.8550
Iteration: 2590; Percent complete: 64.8%; Average loss: 3.0698
Iteration: 2591; Percent complete: 64.8%; Average loss: 3.0232
Iteration: 2592; Percent complete: 64.8%; Average loss: 2.8753
Iteration: 2593; Percent complete: 64.8%; Average loss: 2.7967
Iteration: 2594; Percent complete: 64.8%; Average loss: 3.0293
Iteration: 2595; Percent complete: 64.9%; Average loss: 2.9555
Iteration: 2596; Percent complete: 64.9%; Average loss: 3.1037
Iteration: 2597; Percent complete: 64.9%; Average loss: 2.9715
Iteration: 2598; Percent complete: 65.0%; Average loss: 2.8317
Iteration: 2599; Percent complete: 65.0%; Average loss: 2.9679
Iteration: 2600; Percent complete: 65.0%; Average loss: 2.9209
Iteration: 2601; Percent complete: 65.0%; Average loss: 2.9364
Iteration: 2602; Percent complete: 65.0%; Average loss: 2.8680
Iteration: 2603; Percent complete: 65.1%; Average loss: 3.0793
Iteration: 2604; Percent complete: 65.1%; Average loss: 2.9019
Iteration: 2605; Percent complete: 65.1%; Average loss: 3.0276
Iteration: 2606; Percent complete: 65.1%; Average loss: 2.5844
Iteration: 2607; Percent complete: 65.2%; Average loss: 2.9064
Iteration: 2608; Percent complete: 65.2%; Average loss: 2.9383
Iteration: 2609; Percent complete: 65.2%; Average loss: 2.8438
Iteration: 2610; Percent complete: 65.2%; Average loss: 3.0245
Iteration: 2611; Percent complete: 65.3%; Average loss: 2.9027
Iteration: 2612; Percent complete: 65.3%; Average loss: 3.0997
Iteration: 2613; Percent complete: 65.3%; Average loss: 3.0337
Iteration: 2614; Percent complete: 65.3%; Average loss: 2.8755
Iteration: 2615; Percent complete: 65.4%; Average loss: 2.9813
Iteration: 2616; Percent complete: 65.4%; Average loss: 2.8400
Iteration: 2617; Percent complete: 65.4%; Average loss: 2.7029
Iteration: 2618; Percent complete: 65.5%; Average loss: 2.8675
Iteration: 2619; Percent complete: 65.5%; Average loss: 2.7814
Iteration: 2620; Percent complete: 65.5%; Average loss: 3.1414
Iteration: 2621; Percent complete: 65.5%; Average loss: 2.9745
Iteration: 2622; Percent complete: 65.5%; Average loss: 3.1813
Iteration: 2623; Percent complete: 65.6%; Average loss: 2.8233
Iteration: 2624; Percent complete: 65.6%; Average loss: 2.9917
Iteration: 2625; Percent complete: 65.6%; Average loss: 2.6634
Iteration: 2626; Percent complete: 65.6%; Average loss: 2.9527
Iteration: 2627; Percent complete: 65.7%; Average loss: 3.0379
Iteration: 2628; Percent complete: 65.7%; Average loss: 2.8873
Iteration: 2629; Percent complete: 65.7%; Average loss: 2.8803
Iteration: 2630; Percent complete: 65.8%; Average loss: 3.0417
Iteration: 2631; Percent complete: 65.8%; Average loss: 3.1301
Iteration: 2632; Percent complete: 65.8%; Average loss: 2.8497
Iteration: 2633; Percent complete: 65.8%; Average loss: 2.8533
Iteration: 2634; Percent complete: 65.8%; Average loss: 2.9041
Iteration: 2635; Percent complete: 65.9%; Average loss: 3.0851
Iteration: 2636; Percent complete: 65.9%; Average loss: 2.9533
Iteration: 2637; Percent complete: 65.9%; Average loss: 3.0825
Iteration: 2638; Percent complete: 66.0%; Average loss: 3.1072
Iteration: 2639; Percent complete: 66.0%; Average loss: 3.0687
Iteration: 2640; Percent complete: 66.0%; Average loss: 2.9362
Iteration: 2641; Percent complete: 66.0%; Average loss: 3.1621
Iteration: 2642; Percent complete: 66.0%; Average loss: 3.0305
Iteration: 2643; Percent complete: 66.1%; Average loss: 3.1279
Iteration: 2644; Percent complete: 66.1%; Average loss: 2.9669
Iteration: 2645; Percent complete: 66.1%; Average loss: 2.8448
Iteration: 2646; Percent complete: 66.1%; Average loss: 3.1079
Iteration: 2647; Percent complete: 66.2%; Average loss: 3.0986
Iteration: 2648; Percent complete: 66.2%; Average loss: 2.7767
Iteration: 2649; Percent complete: 66.2%; Average loss: 3.0855
Iteration: 2650; Percent complete: 66.2%; Average loss: 2.9951
Iteration: 2651; Percent complete: 66.3%; Average loss: 3.1033
Iteration: 2652; Percent complete: 66.3%; Average loss: 3.0550
Iteration: 2653; Percent complete: 66.3%; Average loss: 3.0045
Iteration: 2654; Percent complete: 66.3%; Average loss: 2.8476
Iteration: 2655; Percent complete: 66.4%; Average loss: 2.9918
Iteration: 2656; Percent complete: 66.4%; Average loss: 3.0394
Iteration: 2657; Percent complete: 66.4%; Average loss: 2.9384
Iteration: 2658; Percent complete: 66.5%; Average loss: 3.0271
Iteration: 2659; Percent complete: 66.5%; Average loss: 2.8694
Iteration: 2660; Percent complete: 66.5%; Average loss: 2.9136
Iteration: 2661; Percent complete: 66.5%; Average loss: 2.9460
Iteration: 2662; Percent complete: 66.5%; Average loss: 3.2821
Iteration: 2663; Percent complete: 66.6%; Average loss: 3.0390
Iteration: 2664; Percent complete: 66.6%; Average loss: 3.2020
Iteration: 2665; Percent complete: 66.6%; Average loss: 3.1271
Iteration: 2666; Percent complete: 66.6%; Average loss: 2.9983
Iteration: 2667; Percent complete: 66.7%; Average loss: 2.8060
Iteration: 2668; Percent complete: 66.7%; Average loss: 2.8623
Iteration: 2669; Percent complete: 66.7%; Average loss: 2.9533
Iteration: 2670; Percent complete: 66.8%; Average loss: 2.8702
Iteration: 2671; Percent complete: 66.8%; Average loss: 2.8363
Iteration: 2672; Percent complete: 66.8%; Average loss: 3.0121
Iteration: 2673; Percent complete: 66.8%; Average loss: 3.2229
Iteration: 2674; Percent complete: 66.8%; Average loss: 3.0737
Iteration: 2675; Percent complete: 66.9%; Average loss: 2.9727
Iteration: 2676; Percent complete: 66.9%; Average loss: 3.0722
Iteration: 2677; Percent complete: 66.9%; Average loss: 2.8983
Iteration: 2678; Percent complete: 67.0%; Average loss: 2.9997
Iteration: 2679; Percent complete: 67.0%; Average loss: 2.9525
Iteration: 2680; Percent complete: 67.0%; Average loss: 3.0649
Iteration: 2681; Percent complete: 67.0%; Average loss: 2.7430
Iteration: 2682; Percent complete: 67.0%; Average loss: 2.7245
Iteration: 2683; Percent complete: 67.1%; Average loss: 2.7234
Iteration: 2684; Percent complete: 67.1%; Average loss: 3.0943
Iteration: 2685; Percent complete: 67.1%; Average loss: 3.0342
Iteration: 2686; Percent complete: 67.2%; Average loss: 3.2602
Iteration: 2687; Percent complete: 67.2%; Average loss: 3.1741
Iteration: 2688; Percent complete: 67.2%; Average loss: 2.9404
Iteration: 2689; Percent complete: 67.2%; Average loss: 3.1768
Iteration: 2690; Percent complete: 67.2%; Average loss: 3.0616
Iteration: 2691; Percent complete: 67.3%; Average loss: 3.0770
Iteration: 2692; Percent complete: 67.3%; Average loss: 3.0263
Iteration: 2693; Percent complete: 67.3%; Average loss: 3.0875
Iteration: 2694; Percent complete: 67.3%; Average loss: 2.9156
Iteration: 2695; Percent complete: 67.4%; Average loss: 3.1547
Iteration: 2696; Percent complete: 67.4%; Average loss: 2.9138
Iteration: 2697; Percent complete: 67.4%; Average loss: 3.0966
Iteration: 2698; Percent complete: 67.5%; Average loss: 3.0188
Iteration: 2699; Percent complete: 67.5%; Average loss: 2.8635
Iteration: 2700; Percent complete: 67.5%; Average loss: 2.7390
Iteration: 2701; Percent complete: 67.5%; Average loss: 2.9633
Iteration: 2702; Percent complete: 67.5%; Average loss: 3.2830
Iteration: 2703; Percent complete: 67.6%; Average loss: 2.8357
Iteration: 2704; Percent complete: 67.6%; Average loss: 2.9204
Iteration: 2705; Percent complete: 67.6%; Average loss: 2.7462
Iteration: 2706; Percent complete: 67.7%; Average loss: 2.7174
Iteration: 2707; Percent complete: 67.7%; Average loss: 2.9996
Iteration: 2708; Percent complete: 67.7%; Average loss: 2.9815
Iteration: 2709; Percent complete: 67.7%; Average loss: 2.9880
Iteration: 2710; Percent complete: 67.8%; Average loss: 2.9891
Iteration: 2711; Percent complete: 67.8%; Average loss: 3.1633
Iteration: 2712; Percent complete: 67.8%; Average loss: 3.0903
Iteration: 2713; Percent complete: 67.8%; Average loss: 2.7653
Iteration: 2714; Percent complete: 67.8%; Average loss: 2.8346
Iteration: 2715; Percent complete: 67.9%; Average loss: 3.0279
Iteration: 2716; Percent complete: 67.9%; Average loss: 2.9792
Iteration: 2717; Percent complete: 67.9%; Average loss: 3.1257
Iteration: 2718; Percent complete: 68.0%; Average loss: 2.9511
Iteration: 2719; Percent complete: 68.0%; Average loss: 3.0714
Iteration: 2720; Percent complete: 68.0%; Average loss: 3.0316
Iteration: 2721; Percent complete: 68.0%; Average loss: 3.1529
Iteration: 2722; Percent complete: 68.0%; Average loss: 2.8772
Iteration: 2723; Percent complete: 68.1%; Average loss: 3.0001
Iteration: 2724; Percent complete: 68.1%; Average loss: 3.1078
Iteration: 2725; Percent complete: 68.1%; Average loss: 2.8800
Iteration: 2726; Percent complete: 68.2%; Average loss: 2.8678
Iteration: 2727; Percent complete: 68.2%; Average loss: 2.9117
Iteration: 2728; Percent complete: 68.2%; Average loss: 2.9751
Iteration: 2729; Percent complete: 68.2%; Average loss: 3.1858
Iteration: 2730; Percent complete: 68.2%; Average loss: 3.2352
Iteration: 2731; Percent complete: 68.3%; Average loss: 2.7107
Iteration: 2732; Percent complete: 68.3%; Average loss: 2.8268
Iteration: 2733; Percent complete: 68.3%; Average loss: 2.9579
Iteration: 2734; Percent complete: 68.3%; Average loss: 3.0132
Iteration: 2735; Percent complete: 68.4%; Average loss: 2.9946
Iteration: 2736; Percent complete: 68.4%; Average loss: 2.8636
Iteration: 2737; Percent complete: 68.4%; Average loss: 2.8118
Iteration: 2738; Percent complete: 68.5%; Average loss: 2.9177
Iteration: 2739; Percent complete: 68.5%; Average loss: 2.9388
Iteration: 2740; Percent complete: 68.5%; Average loss: 3.1437
Iteration: 2741; Percent complete: 68.5%; Average loss: 3.1664
Iteration: 2742; Percent complete: 68.5%; Average loss: 2.9957
Iteration: 2743; Percent complete: 68.6%; Average loss: 2.9834
Iteration: 2744; Percent complete: 68.6%; Average loss: 3.1440
Iteration: 2745; Percent complete: 68.6%; Average loss: 2.9768
Iteration: 2746; Percent complete: 68.7%; Average loss: 2.9452
Iteration: 2747; Percent complete: 68.7%; Average loss: 3.1373
Iteration: 2748; Percent complete: 68.7%; Average loss: 2.7995
Iteration: 2749; Percent complete: 68.7%; Average loss: 3.1264
Iteration: 2750; Percent complete: 68.8%; Average loss: 2.9575
Iteration: 2751; Percent complete: 68.8%; Average loss: 2.9820
Iteration: 2752; Percent complete: 68.8%; Average loss: 2.8312
Iteration: 2753; Percent complete: 68.8%; Average loss: 3.0749
Iteration: 2754; Percent complete: 68.8%; Average loss: 2.8963
Iteration: 2755; Percent complete: 68.9%; Average loss: 2.8581
Iteration: 2756; Percent complete: 68.9%; Average loss: 3.0615
Iteration: 2757; Percent complete: 68.9%; Average loss: 2.6937
Iteration: 2758; Percent complete: 69.0%; Average loss: 2.9648
Iteration: 2759; Percent complete: 69.0%; Average loss: 3.0099
Iteration: 2760; Percent complete: 69.0%; Average loss: 3.0034
Iteration: 2761; Percent complete: 69.0%; Average loss: 3.0230
Iteration: 2762; Percent complete: 69.0%; Average loss: 2.9225
Iteration: 2763; Percent complete: 69.1%; Average loss: 3.1353
Iteration: 2764; Percent complete: 69.1%; Average loss: 2.8674
Iteration: 2765; Percent complete: 69.1%; Average loss: 2.7676
Iteration: 2766; Percent complete: 69.2%; Average loss: 2.9497
Iteration: 2767; Percent complete: 69.2%; Average loss: 3.0816
Iteration: 2768; Percent complete: 69.2%; Average loss: 3.1329
Iteration: 2769; Percent complete: 69.2%; Average loss: 3.0849
Iteration: 2770; Percent complete: 69.2%; Average loss: 3.0649
Iteration: 2771; Percent complete: 69.3%; Average loss: 2.7936
Iteration: 2772; Percent complete: 69.3%; Average loss: 2.8804
Iteration: 2773; Percent complete: 69.3%; Average loss: 2.6062
Iteration: 2774; Percent complete: 69.3%; Average loss: 2.8385
Iteration: 2775; Percent complete: 69.4%; Average loss: 2.9798
Iteration: 2776; Percent complete: 69.4%; Average loss: 2.8971
Iteration: 2777; Percent complete: 69.4%; Average loss: 2.9023
Iteration: 2778; Percent complete: 69.5%; Average loss: 2.7889
Iteration: 2779; Percent complete: 69.5%; Average loss: 3.2626
Iteration: 2780; Percent complete: 69.5%; Average loss: 2.7391
Iteration: 2781; Percent complete: 69.5%; Average loss: 2.8715
Iteration: 2782; Percent complete: 69.5%; Average loss: 3.1454
Iteration: 2783; Percent complete: 69.6%; Average loss: 2.8917
Iteration: 2784; Percent complete: 69.6%; Average loss: 2.9779
Iteration: 2785; Percent complete: 69.6%; Average loss: 2.7052
Iteration: 2786; Percent complete: 69.7%; Average loss: 2.7181
Iteration: 2787; Percent complete: 69.7%; Average loss: 2.7609
Iteration: 2788; Percent complete: 69.7%; Average loss: 3.2141
Iteration: 2789; Percent complete: 69.7%; Average loss: 2.9127
Iteration: 2790; Percent complete: 69.8%; Average loss: 3.0567
Iteration: 2791; Percent complete: 69.8%; Average loss: 2.9271
Iteration: 2792; Percent complete: 69.8%; Average loss: 3.1288
Iteration: 2793; Percent complete: 69.8%; Average loss: 3.0996
Iteration: 2794; Percent complete: 69.8%; Average loss: 2.9294
Iteration: 2795; Percent complete: 69.9%; Average loss: 2.9767
Iteration: 2796; Percent complete: 69.9%; Average loss: 2.7852
Iteration: 2797; Percent complete: 69.9%; Average loss: 2.6590
Iteration: 2798; Percent complete: 70.0%; Average loss: 2.9496
Iteration: 2799; Percent complete: 70.0%; Average loss: 2.8399
Iteration: 2800; Percent complete: 70.0%; Average loss: 3.0233
Iteration: 2801; Percent complete: 70.0%; Average loss: 2.8783
Iteration: 2802; Percent complete: 70.0%; Average loss: 3.0236
Iteration: 2803; Percent complete: 70.1%; Average loss: 2.8823
Iteration: 2804; Percent complete: 70.1%; Average loss: 2.9222
Iteration: 2805; Percent complete: 70.1%; Average loss: 2.8778
Iteration: 2806; Percent complete: 70.2%; Average loss: 2.8941
Iteration: 2807; Percent complete: 70.2%; Average loss: 3.0149
Iteration: 2808; Percent complete: 70.2%; Average loss: 2.7227
Iteration: 2809; Percent complete: 70.2%; Average loss: 2.9589
Iteration: 2810; Percent complete: 70.2%; Average loss: 2.7326
Iteration: 2811; Percent complete: 70.3%; Average loss: 3.1111
Iteration: 2812; Percent complete: 70.3%; Average loss: 2.9522
Iteration: 2813; Percent complete: 70.3%; Average loss: 2.8398
Iteration: 2814; Percent complete: 70.3%; Average loss: 2.9349
Iteration: 2815; Percent complete: 70.4%; Average loss: 2.8986
Iteration: 2816; Percent complete: 70.4%; Average loss: 3.1519
Iteration: 2817; Percent complete: 70.4%; Average loss: 2.8592
Iteration: 2818; Percent complete: 70.5%; Average loss: 2.8337
Iteration: 2819; Percent complete: 70.5%; Average loss: 2.6062
Iteration: 2820; Percent complete: 70.5%; Average loss: 2.9451
Iteration: 2821; Percent complete: 70.5%; Average loss: 2.8561
Iteration: 2822; Percent complete: 70.5%; Average loss: 2.9072
Iteration: 2823; Percent complete: 70.6%; Average loss: 2.6595
Iteration: 2824; Percent complete: 70.6%; Average loss: 3.1172
Iteration: 2825; Percent complete: 70.6%; Average loss: 2.7703
Iteration: 2826; Percent complete: 70.7%; Average loss: 3.0334
Iteration: 2827; Percent complete: 70.7%; Average loss: 3.2055
Iteration: 2828; Percent complete: 70.7%; Average loss: 2.7394
Iteration: 2829; Percent complete: 70.7%; Average loss: 2.9643
Iteration: 2830; Percent complete: 70.8%; Average loss: 2.7786
Iteration: 2831; Percent complete: 70.8%; Average loss: 3.0462
Iteration: 2832; Percent complete: 70.8%; Average loss: 2.9568
Iteration: 2833; Percent complete: 70.8%; Average loss: 2.8000
Iteration: 2834; Percent complete: 70.9%; Average loss: 2.9447
Iteration: 2835; Percent complete: 70.9%; Average loss: 2.9406
Iteration: 2836; Percent complete: 70.9%; Average loss: 3.0376
Iteration: 2837; Percent complete: 70.9%; Average loss: 2.8685
Iteration: 2838; Percent complete: 71.0%; Average loss: 2.9296
Iteration: 2839; Percent complete: 71.0%; Average loss: 2.9893
Iteration: 2840; Percent complete: 71.0%; Average loss: 2.9168
Iteration: 2841; Percent complete: 71.0%; Average loss: 3.1228
Iteration: 2842; Percent complete: 71.0%; Average loss: 2.9671
Iteration: 2843; Percent complete: 71.1%; Average loss: 2.9859
Iteration: 2844; Percent complete: 71.1%; Average loss: 2.6766
Iteration: 2845; Percent complete: 71.1%; Average loss: 2.9546
Iteration: 2846; Percent complete: 71.2%; Average loss: 2.8594
Iteration: 2847; Percent complete: 71.2%; Average loss: 2.8461
Iteration: 2848; Percent complete: 71.2%; Average loss: 2.6030
Iteration: 2849; Percent complete: 71.2%; Average loss: 3.0628
Iteration: 2850; Percent complete: 71.2%; Average loss: 2.8484
Iteration: 2851; Percent complete: 71.3%; Average loss: 3.0551
Iteration: 2852; Percent complete: 71.3%; Average loss: 2.8599
Iteration: 2853; Percent complete: 71.3%; Average loss: 2.9298
Iteration: 2854; Percent complete: 71.4%; Average loss: 3.0442
Iteration: 2855; Percent complete: 71.4%; Average loss: 3.0302
Iteration: 2856; Percent complete: 71.4%; Average loss: 2.9143
Iteration: 2857; Percent complete: 71.4%; Average loss: 2.8541
Iteration: 2858; Percent complete: 71.5%; Average loss: 3.0461
Iteration: 2859; Percent complete: 71.5%; Average loss: 2.9279
Iteration: 2860; Percent complete: 71.5%; Average loss: 2.6260
Iteration: 2861; Percent complete: 71.5%; Average loss: 3.1262
Iteration: 2862; Percent complete: 71.5%; Average loss: 2.8937
Iteration: 2863; Percent complete: 71.6%; Average loss: 2.9756
Iteration: 2864; Percent complete: 71.6%; Average loss: 2.8434
Iteration: 2865; Percent complete: 71.6%; Average loss: 3.0386
Iteration: 2866; Percent complete: 71.7%; Average loss: 2.9404
Iteration: 2867; Percent complete: 71.7%; Average loss: 2.9892
Iteration: 2868; Percent complete: 71.7%; Average loss: 2.8888
Iteration: 2869; Percent complete: 71.7%; Average loss: 2.5713
Iteration: 2870; Percent complete: 71.8%; Average loss: 2.9031
Iteration: 2871; Percent complete: 71.8%; Average loss: 2.9761
Iteration: 2872; Percent complete: 71.8%; Average loss: 2.8192
Iteration: 2873; Percent complete: 71.8%; Average loss: 3.1464
Iteration: 2874; Percent complete: 71.9%; Average loss: 2.6966
Iteration: 2875; Percent complete: 71.9%; Average loss: 2.8819
Iteration: 2876; Percent complete: 71.9%; Average loss: 2.7040
Iteration: 2877; Percent complete: 71.9%; Average loss: 3.1110
Iteration: 2878; Percent complete: 72.0%; Average loss: 2.8691
Iteration: 2879; Percent complete: 72.0%; Average loss: 2.8656
Iteration: 2880; Percent complete: 72.0%; Average loss: 2.8628
Iteration: 2881; Percent complete: 72.0%; Average loss: 2.9888
Iteration: 2882; Percent complete: 72.0%; Average loss: 2.9500
Iteration: 2883; Percent complete: 72.1%; Average loss: 2.9286
Iteration: 2884; Percent complete: 72.1%; Average loss: 2.8367
Iteration: 2885; Percent complete: 72.1%; Average loss: 2.9530
Iteration: 2886; Percent complete: 72.2%; Average loss: 2.9803
Iteration: 2887; Percent complete: 72.2%; Average loss: 2.9825
Iteration: 2888; Percent complete: 72.2%; Average loss: 2.9596
Iteration: 2889; Percent complete: 72.2%; Average loss: 2.7301
Iteration: 2890; Percent complete: 72.2%; Average loss: 2.8983
Iteration: 2891; Percent complete: 72.3%; Average loss: 2.9194
Iteration: 2892; Percent complete: 72.3%; Average loss: 2.9646
Iteration: 2893; Percent complete: 72.3%; Average loss: 2.7501
Iteration: 2894; Percent complete: 72.4%; Average loss: 3.0922
Iteration: 2895; Percent complete: 72.4%; Average loss: 2.6334
Iteration: 2896; Percent complete: 72.4%; Average loss: 2.9412
Iteration: 2897; Percent complete: 72.4%; Average loss: 2.8051
Iteration: 2898; Percent complete: 72.5%; Average loss: 3.1374
Iteration: 2899; Percent complete: 72.5%; Average loss: 3.0887
Iteration: 2900; Percent complete: 72.5%; Average loss: 2.8058
Iteration: 2901; Percent complete: 72.5%; Average loss: 3.0982
Iteration: 2902; Percent complete: 72.5%; Average loss: 2.8920
Iteration: 2903; Percent complete: 72.6%; Average loss: 2.7519
Iteration: 2904; Percent complete: 72.6%; Average loss: 2.9822
Iteration: 2905; Percent complete: 72.6%; Average loss: 2.8033
Iteration: 2906; Percent complete: 72.7%; Average loss: 2.8843
Iteration: 2907; Percent complete: 72.7%; Average loss: 3.0786
Iteration: 2908; Percent complete: 72.7%; Average loss: 2.9767
Iteration: 2909; Percent complete: 72.7%; Average loss: 2.9948
Iteration: 2910; Percent complete: 72.8%; Average loss: 2.9522
Iteration: 2911; Percent complete: 72.8%; Average loss: 3.0920
Iteration: 2912; Percent complete: 72.8%; Average loss: 2.9788
Iteration: 2913; Percent complete: 72.8%; Average loss: 2.9581
Iteration: 2914; Percent complete: 72.9%; Average loss: 2.9997
Iteration: 2915; Percent complete: 72.9%; Average loss: 3.0224
Iteration: 2916; Percent complete: 72.9%; Average loss: 2.8298
Iteration: 2917; Percent complete: 72.9%; Average loss: 3.0478
Iteration: 2918; Percent complete: 73.0%; Average loss: 3.0813
Iteration: 2919; Percent complete: 73.0%; Average loss: 3.3120
Iteration: 2920; Percent complete: 73.0%; Average loss: 2.8750
Iteration: 2921; Percent complete: 73.0%; Average loss: 3.1349
Iteration: 2922; Percent complete: 73.0%; Average loss: 2.8791
Iteration: 2923; Percent complete: 73.1%; Average loss: 3.1766
Iteration: 2924; Percent complete: 73.1%; Average loss: 2.9858
Iteration: 2925; Percent complete: 73.1%; Average loss: 2.9147
Iteration: 2926; Percent complete: 73.2%; Average loss: 2.8527
Iteration: 2927; Percent complete: 73.2%; Average loss: 3.0305
Iteration: 2928; Percent complete: 73.2%; Average loss: 3.0725
Iteration: 2929; Percent complete: 73.2%; Average loss: 2.8410
Iteration: 2930; Percent complete: 73.2%; Average loss: 2.8212
Iteration: 2931; Percent complete: 73.3%; Average loss: 3.1191
Iteration: 2932; Percent complete: 73.3%; Average loss: 2.7108
Iteration: 2933; Percent complete: 73.3%; Average loss: 2.9424
Iteration: 2934; Percent complete: 73.4%; Average loss: 3.1465
Iteration: 2935; Percent complete: 73.4%; Average loss: 2.8604
Iteration: 2936; Percent complete: 73.4%; Average loss: 2.6838
Iteration: 2937; Percent complete: 73.4%; Average loss: 2.7398
Iteration: 2938; Percent complete: 73.5%; Average loss: 2.8968
Iteration: 2939; Percent complete: 73.5%; Average loss: 2.7747
Iteration: 2940; Percent complete: 73.5%; Average loss: 3.0132
Iteration: 2941; Percent complete: 73.5%; Average loss: 2.7823
Iteration: 2942; Percent complete: 73.6%; Average loss: 2.8050
Iteration: 2943; Percent complete: 73.6%; Average loss: 2.7625
Iteration: 2944; Percent complete: 73.6%; Average loss: 2.8743
Iteration: 2945; Percent complete: 73.6%; Average loss: 2.7375
Iteration: 2946; Percent complete: 73.7%; Average loss: 3.1428
Iteration: 2947; Percent complete: 73.7%; Average loss: 2.8646
Iteration: 2948; Percent complete: 73.7%; Average loss: 2.7954
Iteration: 2949; Percent complete: 73.7%; Average loss: 2.8303
Iteration: 2950; Percent complete: 73.8%; Average loss: 2.9766
Iteration: 2951; Percent complete: 73.8%; Average loss: 2.9100
Iteration: 2952; Percent complete: 73.8%; Average loss: 3.1049
Iteration: 2953; Percent complete: 73.8%; Average loss: 2.7974
Iteration: 2954; Percent complete: 73.9%; Average loss: 2.7091
Iteration: 2955; Percent complete: 73.9%; Average loss: 2.8354
Iteration: 2956; Percent complete: 73.9%; Average loss: 2.9494
Iteration: 2957; Percent complete: 73.9%; Average loss: 2.8124
Iteration: 2958; Percent complete: 74.0%; Average loss: 2.8941
Iteration: 2959; Percent complete: 74.0%; Average loss: 2.9280
Iteration: 2960; Percent complete: 74.0%; Average loss: 2.8093
Iteration: 2961; Percent complete: 74.0%; Average loss: 2.9262
Iteration: 2962; Percent complete: 74.1%; Average loss: 3.0962
Iteration: 2963; Percent complete: 74.1%; Average loss: 2.8192
Iteration: 2964; Percent complete: 74.1%; Average loss: 2.8498
Iteration: 2965; Percent complete: 74.1%; Average loss: 2.6917
Iteration: 2966; Percent complete: 74.2%; Average loss: 2.8314
Iteration: 2967; Percent complete: 74.2%; Average loss: 2.9211
Iteration: 2968; Percent complete: 74.2%; Average loss: 3.0047
Iteration: 2969; Percent complete: 74.2%; Average loss: 2.7648
Iteration: 2970; Percent complete: 74.2%; Average loss: 2.7826
Iteration: 2971; Percent complete: 74.3%; Average loss: 2.8498
Iteration: 2972; Percent complete: 74.3%; Average loss: 2.8192
Iteration: 2973; Percent complete: 74.3%; Average loss: 2.6538
Iteration: 2974; Percent complete: 74.4%; Average loss: 2.9265
Iteration: 2975; Percent complete: 74.4%; Average loss: 3.0818
Iteration: 2976; Percent complete: 74.4%; Average loss: 2.8877
Iteration: 2977; Percent complete: 74.4%; Average loss: 2.7921
Iteration: 2978; Percent complete: 74.5%; Average loss: 2.8873
Iteration: 2979; Percent complete: 74.5%; Average loss: 2.7614
Iteration: 2980; Percent complete: 74.5%; Average loss: 2.7814
Iteration: 2981; Percent complete: 74.5%; Average loss: 2.8252
Iteration: 2982; Percent complete: 74.6%; Average loss: 2.9071
Iteration: 2983; Percent complete: 74.6%; Average loss: 3.1637
Iteration: 2984; Percent complete: 74.6%; Average loss: 2.8821
Iteration: 2985; Percent complete: 74.6%; Average loss: 2.8378
Iteration: 2986; Percent complete: 74.7%; Average loss: 2.8818
Iteration: 2987; Percent complete: 74.7%; Average loss: 2.7175
Iteration: 2988; Percent complete: 74.7%; Average loss: 2.7891
Iteration: 2989; Percent complete: 74.7%; Average loss: 2.9699
Iteration: 2990; Percent complete: 74.8%; Average loss: 2.8150
Iteration: 2991; Percent complete: 74.8%; Average loss: 2.8513
Iteration: 2992; Percent complete: 74.8%; Average loss: 2.7885
Iteration: 2993; Percent complete: 74.8%; Average loss: 2.7467
Iteration: 2994; Percent complete: 74.9%; Average loss: 2.7799
Iteration: 2995; Percent complete: 74.9%; Average loss: 2.9456
Iteration: 2996; Percent complete: 74.9%; Average loss: 2.7516
Iteration: 2997; Percent complete: 74.9%; Average loss: 2.7986
Iteration: 2998; Percent complete: 75.0%; Average loss: 2.9217
Iteration: 2999; Percent complete: 75.0%; Average loss: 3.0917
Iteration: 3000; Percent complete: 75.0%; Average loss: 2.8591
Iteration: 3001; Percent complete: 75.0%; Average loss: 3.0370
Iteration: 3002; Percent complete: 75.0%; Average loss: 2.8224
Iteration: 3003; Percent complete: 75.1%; Average loss: 2.9319
Iteration: 3004; Percent complete: 75.1%; Average loss: 2.9910
Iteration: 3005; Percent complete: 75.1%; Average loss: 2.9531
Iteration: 3006; Percent complete: 75.1%; Average loss: 2.6682
Iteration: 3007; Percent complete: 75.2%; Average loss: 2.8707
Iteration: 3008; Percent complete: 75.2%; Average loss: 2.9902
Iteration: 3009; Percent complete: 75.2%; Average loss: 2.9372
Iteration: 3010; Percent complete: 75.2%; Average loss: 2.9733
Iteration: 3011; Percent complete: 75.3%; Average loss: 2.8931
Iteration: 3012; Percent complete: 75.3%; Average loss: 2.9302
Iteration: 3013; Percent complete: 75.3%; Average loss: 2.9829
Iteration: 3014; Percent complete: 75.3%; Average loss: 2.8161
Iteration: 3015; Percent complete: 75.4%; Average loss: 2.7352
Iteration: 3016; Percent complete: 75.4%; Average loss: 2.8646
Iteration: 3017; Percent complete: 75.4%; Average loss: 2.9150
Iteration: 3018; Percent complete: 75.4%; Average loss: 2.9822
Iteration: 3019; Percent complete: 75.5%; Average loss: 3.0144
Iteration: 3020; Percent complete: 75.5%; Average loss: 2.8617
Iteration: 3021; Percent complete: 75.5%; Average loss: 2.9820
Iteration: 3022; Percent complete: 75.5%; Average loss: 2.8942
Iteration: 3023; Percent complete: 75.6%; Average loss: 2.7454
Iteration: 3024; Percent complete: 75.6%; Average loss: 2.9618
Iteration: 3025; Percent complete: 75.6%; Average loss: 2.7480
Iteration: 3026; Percent complete: 75.6%; Average loss: 2.7725
Iteration: 3027; Percent complete: 75.7%; Average loss: 2.9132
Iteration: 3028; Percent complete: 75.7%; Average loss: 2.7108
Iteration: 3029; Percent complete: 75.7%; Average loss: 2.9266
Iteration: 3030; Percent complete: 75.8%; Average loss: 2.8461
Iteration: 3031; Percent complete: 75.8%; Average loss: 2.9125
Iteration: 3032; Percent complete: 75.8%; Average loss: 3.1152
Iteration: 3033; Percent complete: 75.8%; Average loss: 2.8274
Iteration: 3034; Percent complete: 75.8%; Average loss: 2.8614
Iteration: 3035; Percent complete: 75.9%; Average loss: 2.9409
Iteration: 3036; Percent complete: 75.9%; Average loss: 3.0184
Iteration: 3037; Percent complete: 75.9%; Average loss: 2.8051
Iteration: 3038; Percent complete: 75.9%; Average loss: 2.7265
Iteration: 3039; Percent complete: 76.0%; Average loss: 2.7976
Iteration: 3040; Percent complete: 76.0%; Average loss: 2.9185
Iteration: 3041; Percent complete: 76.0%; Average loss: 3.0075
Iteration: 3042; Percent complete: 76.0%; Average loss: 2.8705
Iteration: 3043; Percent complete: 76.1%; Average loss: 2.7827
Iteration: 3044; Percent complete: 76.1%; Average loss: 2.7131
Iteration: 3045; Percent complete: 76.1%; Average loss: 3.0581
Iteration: 3046; Percent complete: 76.1%; Average loss: 2.8069
Iteration: 3047; Percent complete: 76.2%; Average loss: 2.6766
Iteration: 3048; Percent complete: 76.2%; Average loss: 2.8343
Iteration: 3049; Percent complete: 76.2%; Average loss: 2.9300
Iteration: 3050; Percent complete: 76.2%; Average loss: 2.9640
Iteration: 3051; Percent complete: 76.3%; Average loss: 2.8812
Iteration: 3052; Percent complete: 76.3%; Average loss: 3.0487
Iteration: 3053; Percent complete: 76.3%; Average loss: 2.8706
Iteration: 3054; Percent complete: 76.3%; Average loss: 2.9612
Iteration: 3055; Percent complete: 76.4%; Average loss: 3.0247
Iteration: 3056; Percent complete: 76.4%; Average loss: 2.8752
Iteration: 3057; Percent complete: 76.4%; Average loss: 2.8365
Iteration: 3058; Percent complete: 76.4%; Average loss: 3.1265
Iteration: 3059; Percent complete: 76.5%; Average loss: 2.7782
Iteration: 3060; Percent complete: 76.5%; Average loss: 2.9383
Iteration: 3061; Percent complete: 76.5%; Average loss: 2.7965
Iteration: 3062; Percent complete: 76.5%; Average loss: 3.0478
Iteration: 3063; Percent complete: 76.6%; Average loss: 2.8904
Iteration: 3064; Percent complete: 76.6%; Average loss: 2.9017
Iteration: 3065; Percent complete: 76.6%; Average loss: 2.8395
Iteration: 3066; Percent complete: 76.6%; Average loss: 2.9493
Iteration: 3067; Percent complete: 76.7%; Average loss: 2.8655
Iteration: 3068; Percent complete: 76.7%; Average loss: 3.0305
Iteration: 3069; Percent complete: 76.7%; Average loss: 2.9573
Iteration: 3070; Percent complete: 76.8%; Average loss: 2.5275
Iteration: 3071; Percent complete: 76.8%; Average loss: 3.0997
Iteration: 3072; Percent complete: 76.8%; Average loss: 3.1733
Iteration: 3073; Percent complete: 76.8%; Average loss: 2.8711
Iteration: 3074; Percent complete: 76.8%; Average loss: 2.8863
Iteration: 3075; Percent complete: 76.9%; Average loss: 2.8189
Iteration: 3076; Percent complete: 76.9%; Average loss: 2.9943
Iteration: 3077; Percent complete: 76.9%; Average loss: 3.0117
Iteration: 3078; Percent complete: 77.0%; Average loss: 2.9884
Iteration: 3079; Percent complete: 77.0%; Average loss: 2.8153
Iteration: 3080; Percent complete: 77.0%; Average loss: 2.9217
Iteration: 3081; Percent complete: 77.0%; Average loss: 2.5758
Iteration: 3082; Percent complete: 77.0%; Average loss: 2.9704
Iteration: 3083; Percent complete: 77.1%; Average loss: 2.9940
Iteration: 3084; Percent complete: 77.1%; Average loss: 2.8355
Iteration: 3085; Percent complete: 77.1%; Average loss: 2.9395
Iteration: 3086; Percent complete: 77.1%; Average loss: 2.9973
Iteration: 3087; Percent complete: 77.2%; Average loss: 2.7151
Iteration: 3088; Percent complete: 77.2%; Average loss: 2.7456
Iteration: 3089; Percent complete: 77.2%; Average loss: 2.9603
Iteration: 3090; Percent complete: 77.2%; Average loss: 2.5961
Iteration: 3091; Percent complete: 77.3%; Average loss: 2.8791
Iteration: 3092; Percent complete: 77.3%; Average loss: 2.7676
Iteration: 3093; Percent complete: 77.3%; Average loss: 2.9275
Iteration: 3094; Percent complete: 77.3%; Average loss: 3.0090
Iteration: 3095; Percent complete: 77.4%; Average loss: 3.0676
Iteration: 3096; Percent complete: 77.4%; Average loss: 2.8064
Iteration: 3097; Percent complete: 77.4%; Average loss: 2.6371
Iteration: 3098; Percent complete: 77.5%; Average loss: 2.9928
Iteration: 3099; Percent complete: 77.5%; Average loss: 3.0680
Iteration: 3100; Percent complete: 77.5%; Average loss: 2.5660
Iteration: 3101; Percent complete: 77.5%; Average loss: 2.8491
Iteration: 3102; Percent complete: 77.5%; Average loss: 2.9215
Iteration: 3103; Percent complete: 77.6%; Average loss: 2.8220
Iteration: 3104; Percent complete: 77.6%; Average loss: 2.7861
Iteration: 3105; Percent complete: 77.6%; Average loss: 2.8626
Iteration: 3106; Percent complete: 77.6%; Average loss: 2.9046
Iteration: 3107; Percent complete: 77.7%; Average loss: 2.8420
Iteration: 3108; Percent complete: 77.7%; Average loss: 2.7289
Iteration: 3109; Percent complete: 77.7%; Average loss: 2.9157
Iteration: 3110; Percent complete: 77.8%; Average loss: 2.8027
Iteration: 3111; Percent complete: 77.8%; Average loss: 3.0217
Iteration: 3112; Percent complete: 77.8%; Average loss: 2.9742
Iteration: 3113; Percent complete: 77.8%; Average loss: 2.8298
Iteration: 3114; Percent complete: 77.8%; Average loss: 2.9136
Iteration: 3115; Percent complete: 77.9%; Average loss: 3.1584
Iteration: 3116; Percent complete: 77.9%; Average loss: 3.1197
Iteration: 3117; Percent complete: 77.9%; Average loss: 3.1262
Iteration: 3118; Percent complete: 78.0%; Average loss: 2.8534
Iteration: 3119; Percent complete: 78.0%; Average loss: 2.8816
Iteration: 3120; Percent complete: 78.0%; Average loss: 2.7999
Iteration: 3121; Percent complete: 78.0%; Average loss: 2.7444
Iteration: 3122; Percent complete: 78.0%; Average loss: 2.8909
Iteration: 3123; Percent complete: 78.1%; Average loss: 2.7937
Iteration: 3124; Percent complete: 78.1%; Average loss: 2.9175
Iteration: 3125; Percent complete: 78.1%; Average loss: 2.6785
Iteration: 3126; Percent complete: 78.1%; Average loss: 2.8899
Iteration: 3127; Percent complete: 78.2%; Average loss: 2.8970
Iteration: 3128; Percent complete: 78.2%; Average loss: 2.8008
Iteration: 3129; Percent complete: 78.2%; Average loss: 2.8736
Iteration: 3130; Percent complete: 78.2%; Average loss: 2.8256
Iteration: 3131; Percent complete: 78.3%; Average loss: 2.8828
Iteration: 3132; Percent complete: 78.3%; Average loss: 2.7026
Iteration: 3133; Percent complete: 78.3%; Average loss: 2.8961
Iteration: 3134; Percent complete: 78.3%; Average loss: 2.6233
Iteration: 3135; Percent complete: 78.4%; Average loss: 2.8776
Iteration: 3136; Percent complete: 78.4%; Average loss: 2.9573
Iteration: 3137; Percent complete: 78.4%; Average loss: 2.7752
Iteration: 3138; Percent complete: 78.5%; Average loss: 2.9611
Iteration: 3139; Percent complete: 78.5%; Average loss: 2.8055
Iteration: 3140; Percent complete: 78.5%; Average loss: 2.8628
Iteration: 3141; Percent complete: 78.5%; Average loss: 2.8767
Iteration: 3142; Percent complete: 78.5%; Average loss: 2.6783
Iteration: 3143; Percent complete: 78.6%; Average loss: 2.9402
Iteration: 3144; Percent complete: 78.6%; Average loss: 2.9294
Iteration: 3145; Percent complete: 78.6%; Average loss: 2.8643
Iteration: 3146; Percent complete: 78.6%; Average loss: 3.1251
Iteration: 3147; Percent complete: 78.7%; Average loss: 2.8311
Iteration: 3148; Percent complete: 78.7%; Average loss: 2.8213
Iteration: 3149; Percent complete: 78.7%; Average loss: 2.8499
Iteration: 3150; Percent complete: 78.8%; Average loss: 2.7309
Iteration: 3151; Percent complete: 78.8%; Average loss: 2.9502
Iteration: 3152; Percent complete: 78.8%; Average loss: 2.9031
Iteration: 3153; Percent complete: 78.8%; Average loss: 2.9500
Iteration: 3154; Percent complete: 78.8%; Average loss: 2.7926
Iteration: 3155; Percent complete: 78.9%; Average loss: 2.8846
Iteration: 3156; Percent complete: 78.9%; Average loss: 3.0010
Iteration: 3157; Percent complete: 78.9%; Average loss: 2.9151
Iteration: 3158; Percent complete: 79.0%; Average loss: 2.7173
Iteration: 3159; Percent complete: 79.0%; Average loss: 2.9918
Iteration: 3160; Percent complete: 79.0%; Average loss: 2.7114
Iteration: 3161; Percent complete: 79.0%; Average loss: 2.9936
Iteration: 3162; Percent complete: 79.0%; Average loss: 2.6535
Iteration: 3163; Percent complete: 79.1%; Average loss: 3.1871
Iteration: 3164; Percent complete: 79.1%; Average loss: 2.9718
Iteration: 3165; Percent complete: 79.1%; Average loss: 3.0770
Iteration: 3166; Percent complete: 79.1%; Average loss: 2.9949
Iteration: 3167; Percent complete: 79.2%; Average loss: 2.6021
Iteration: 3168; Percent complete: 79.2%; Average loss: 2.6898
Iteration: 3169; Percent complete: 79.2%; Average loss: 3.0128
Iteration: 3170; Percent complete: 79.2%; Average loss: 2.6041
Iteration: 3171; Percent complete: 79.3%; Average loss: 2.7658
Iteration: 3172; Percent complete: 79.3%; Average loss: 2.5954
Iteration: 3173; Percent complete: 79.3%; Average loss: 2.8868
Iteration: 3174; Percent complete: 79.3%; Average loss: 2.8689
Iteration: 3175; Percent complete: 79.4%; Average loss: 2.8349
Iteration: 3176; Percent complete: 79.4%; Average loss: 2.8658
Iteration: 3177; Percent complete: 79.4%; Average loss: 2.9778
Iteration: 3178; Percent complete: 79.5%; Average loss: 3.0890
Iteration: 3179; Percent complete: 79.5%; Average loss: 2.9121
Iteration: 3180; Percent complete: 79.5%; Average loss: 2.7656
Iteration: 3181; Percent complete: 79.5%; Average loss: 2.9389
Iteration: 3182; Percent complete: 79.5%; Average loss: 2.8439
Iteration: 3183; Percent complete: 79.6%; Average loss: 2.7727
Iteration: 3184; Percent complete: 79.6%; Average loss: 2.7934
Iteration: 3185; Percent complete: 79.6%; Average loss: 2.7528
Iteration: 3186; Percent complete: 79.7%; Average loss: 2.9906
Iteration: 3187; Percent complete: 79.7%; Average loss: 2.8266
Iteration: 3188; Percent complete: 79.7%; Average loss: 2.9635
Iteration: 3189; Percent complete: 79.7%; Average loss: 2.9194
Iteration: 3190; Percent complete: 79.8%; Average loss: 2.8321
Iteration: 3191; Percent complete: 79.8%; Average loss: 2.7935
Iteration: 3192; Percent complete: 79.8%; Average loss: 2.6851
Iteration: 3193; Percent complete: 79.8%; Average loss: 2.9056
Iteration: 3194; Percent complete: 79.8%; Average loss: 2.8960
Iteration: 3195; Percent complete: 79.9%; Average loss: 2.8010
Iteration: 3196; Percent complete: 79.9%; Average loss: 2.9156
Iteration: 3197; Percent complete: 79.9%; Average loss: 3.0693
Iteration: 3198; Percent complete: 80.0%; Average loss: 2.8062
Iteration: 3199; Percent complete: 80.0%; Average loss: 2.8817
Iteration: 3200; Percent complete: 80.0%; Average loss: 2.8197
Iteration: 3201; Percent complete: 80.0%; Average loss: 2.7843
Iteration: 3202; Percent complete: 80.0%; Average loss: 2.9685
Iteration: 3203; Percent complete: 80.1%; Average loss: 2.6553
Iteration: 3204; Percent complete: 80.1%; Average loss: 2.9467
Iteration: 3205; Percent complete: 80.1%; Average loss: 2.9671
Iteration: 3206; Percent complete: 80.2%; Average loss: 3.0080
Iteration: 3207; Percent complete: 80.2%; Average loss: 2.8404
Iteration: 3208; Percent complete: 80.2%; Average loss: 2.9388
Iteration: 3209; Percent complete: 80.2%; Average loss: 2.8811
Iteration: 3210; Percent complete: 80.2%; Average loss: 2.9463
Iteration: 3211; Percent complete: 80.3%; Average loss: 2.7968
Iteration: 3212; Percent complete: 80.3%; Average loss: 2.5487
Iteration: 3213; Percent complete: 80.3%; Average loss: 2.6484
Iteration: 3214; Percent complete: 80.3%; Average loss: 2.6904
Iteration: 3215; Percent complete: 80.4%; Average loss: 2.7655
Iteration: 3216; Percent complete: 80.4%; Average loss: 2.8047
Iteration: 3217; Percent complete: 80.4%; Average loss: 2.8337
Iteration: 3218; Percent complete: 80.5%; Average loss: 2.9420
Iteration: 3219; Percent complete: 80.5%; Average loss: 2.6745
Iteration: 3220; Percent complete: 80.5%; Average loss: 2.6966
Iteration: 3221; Percent complete: 80.5%; Average loss: 2.8527
Iteration: 3222; Percent complete: 80.5%; Average loss: 3.0930
Iteration: 3223; Percent complete: 80.6%; Average loss: 3.0975
Iteration: 3224; Percent complete: 80.6%; Average loss: 2.9190
Iteration: 3225; Percent complete: 80.6%; Average loss: 2.5939
Iteration: 3226; Percent complete: 80.7%; Average loss: 3.0035
Iteration: 3227; Percent complete: 80.7%; Average loss: 2.9247
Iteration: 3228; Percent complete: 80.7%; Average loss: 2.7793
Iteration: 3229; Percent complete: 80.7%; Average loss: 2.9564
Iteration: 3230; Percent complete: 80.8%; Average loss: 2.7978
Iteration: 3231; Percent complete: 80.8%; Average loss: 2.7270
Iteration: 3232; Percent complete: 80.8%; Average loss: 3.0221
Iteration: 3233; Percent complete: 80.8%; Average loss: 3.0074
Iteration: 3234; Percent complete: 80.8%; Average loss: 2.9855
Iteration: 3235; Percent complete: 80.9%; Average loss: 2.8492
Iteration: 3236; Percent complete: 80.9%; Average loss: 2.7577
Iteration: 3237; Percent complete: 80.9%; Average loss: 2.7446
Iteration: 3238; Percent complete: 81.0%; Average loss: 2.7586
Iteration: 3239; Percent complete: 81.0%; Average loss: 2.7481
Iteration: 3240; Percent complete: 81.0%; Average loss: 2.8496
Iteration: 3241; Percent complete: 81.0%; Average loss: 2.9279
Iteration: 3242; Percent complete: 81.0%; Average loss: 2.6050
Iteration: 3243; Percent complete: 81.1%; Average loss: 2.6909
Iteration: 3244; Percent complete: 81.1%; Average loss: 2.6930
Iteration: 3245; Percent complete: 81.1%; Average loss: 2.6386
Iteration: 3246; Percent complete: 81.2%; Average loss: 2.8056
Iteration: 3247; Percent complete: 81.2%; Average loss: 2.8823
Iteration: 3248; Percent complete: 81.2%; Average loss: 2.7536
Iteration: 3249; Percent complete: 81.2%; Average loss: 3.0566
Iteration: 3250; Percent complete: 81.2%; Average loss: 2.6988
Iteration: 3251; Percent complete: 81.3%; Average loss: 2.7331
Iteration: 3252; Percent complete: 81.3%; Average loss: 2.6939
Iteration: 3253; Percent complete: 81.3%; Average loss: 2.8494
Iteration: 3254; Percent complete: 81.3%; Average loss: 2.5908
Iteration: 3255; Percent complete: 81.4%; Average loss: 2.8440
Iteration: 3256; Percent complete: 81.4%; Average loss: 2.9846
Iteration: 3257; Percent complete: 81.4%; Average loss: 2.9861
Iteration: 3258; Percent complete: 81.5%; Average loss: 2.7561
Iteration: 3259; Percent complete: 81.5%; Average loss: 2.9001
Iteration: 3260; Percent complete: 81.5%; Average loss: 2.7334
Iteration: 3261; Percent complete: 81.5%; Average loss: 2.7977
Iteration: 3262; Percent complete: 81.5%; Average loss: 2.7724
Iteration: 3263; Percent complete: 81.6%; Average loss: 2.6847
Iteration: 3264; Percent complete: 81.6%; Average loss: 2.6263
Iteration: 3265; Percent complete: 81.6%; Average loss: 2.8449
Iteration: 3266; Percent complete: 81.7%; Average loss: 2.9701
Iteration: 3267; Percent complete: 81.7%; Average loss: 2.7187
Iteration: 3268; Percent complete: 81.7%; Average loss: 2.6809
Iteration: 3269; Percent complete: 81.7%; Average loss: 2.6846
Iteration: 3270; Percent complete: 81.8%; Average loss: 2.9414
Iteration: 3271; Percent complete: 81.8%; Average loss: 2.6781
Iteration: 3272; Percent complete: 81.8%; Average loss: 2.8289
Iteration: 3273; Percent complete: 81.8%; Average loss: 2.8920
Iteration: 3274; Percent complete: 81.8%; Average loss: 2.7875
Iteration: 3275; Percent complete: 81.9%; Average loss: 2.5464
Iteration: 3276; Percent complete: 81.9%; Average loss: 3.0702
Iteration: 3277; Percent complete: 81.9%; Average loss: 2.8934
Iteration: 3278; Percent complete: 82.0%; Average loss: 2.6599
Iteration: 3279; Percent complete: 82.0%; Average loss: 2.9096
Iteration: 3280; Percent complete: 82.0%; Average loss: 2.5894
Iteration: 3281; Percent complete: 82.0%; Average loss: 2.7822
Iteration: 3282; Percent complete: 82.0%; Average loss: 2.9429
Iteration: 3283; Percent complete: 82.1%; Average loss: 2.6813
Iteration: 3284; Percent complete: 82.1%; Average loss: 2.8127
Iteration: 3285; Percent complete: 82.1%; Average loss: 2.7651
Iteration: 3286; Percent complete: 82.2%; Average loss: 2.7618
Iteration: 3287; Percent complete: 82.2%; Average loss: 2.9912
Iteration: 3288; Percent complete: 82.2%; Average loss: 2.8848
Iteration: 3289; Percent complete: 82.2%; Average loss: 2.6877
Iteration: 3290; Percent complete: 82.2%; Average loss: 2.8331
Iteration: 3291; Percent complete: 82.3%; Average loss: 3.0230
Iteration: 3292; Percent complete: 82.3%; Average loss: 2.6619
Iteration: 3293; Percent complete: 82.3%; Average loss: 2.8259
Iteration: 3294; Percent complete: 82.3%; Average loss: 2.9549
Iteration: 3295; Percent complete: 82.4%; Average loss: 2.7744
Iteration: 3296; Percent complete: 82.4%; Average loss: 2.6704
Iteration: 3297; Percent complete: 82.4%; Average loss: 2.6971
Iteration: 3298; Percent complete: 82.5%; Average loss: 2.8286
Iteration: 3299; Percent complete: 82.5%; Average loss: 2.9463
Iteration: 3300; Percent complete: 82.5%; Average loss: 2.8034
Iteration: 3301; Percent complete: 82.5%; Average loss: 2.8187
Iteration: 3302; Percent complete: 82.5%; Average loss: 2.7679
Iteration: 3303; Percent complete: 82.6%; Average loss: 2.4501
Iteration: 3304; Percent complete: 82.6%; Average loss: 2.9099
Iteration: 3305; Percent complete: 82.6%; Average loss: 2.7811
Iteration: 3306; Percent complete: 82.7%; Average loss: 2.9040
Iteration: 3307; Percent complete: 82.7%; Average loss: 2.7987
Iteration: 3308; Percent complete: 82.7%; Average loss: 2.6067
Iteration: 3309; Percent complete: 82.7%; Average loss: 2.6495
Iteration: 3310; Percent complete: 82.8%; Average loss: 3.0471
Iteration: 3311; Percent complete: 82.8%; Average loss: 2.8978
Iteration: 3312; Percent complete: 82.8%; Average loss: 2.7285
Iteration: 3313; Percent complete: 82.8%; Average loss: 2.9519
Iteration: 3314; Percent complete: 82.8%; Average loss: 2.8302
Iteration: 3315; Percent complete: 82.9%; Average loss: 2.7902
Iteration: 3316; Percent complete: 82.9%; Average loss: 3.0395
Iteration: 3317; Percent complete: 82.9%; Average loss: 2.7884
Iteration: 3318; Percent complete: 83.0%; Average loss: 3.1049
Iteration: 3319; Percent complete: 83.0%; Average loss: 2.8701
Iteration: 3320; Percent complete: 83.0%; Average loss: 2.9410
Iteration: 3321; Percent complete: 83.0%; Average loss: 2.5215
Iteration: 3322; Percent complete: 83.0%; Average loss: 2.8978
Iteration: 3323; Percent complete: 83.1%; Average loss: 2.8641
Iteration: 3324; Percent complete: 83.1%; Average loss: 2.7177
Iteration: 3325; Percent complete: 83.1%; Average loss: 2.6855
Iteration: 3326; Percent complete: 83.2%; Average loss: 2.7112
Iteration: 3327; Percent complete: 83.2%; Average loss: 2.9151
Iteration: 3328; Percent complete: 83.2%; Average loss: 2.7646
Iteration: 3329; Percent complete: 83.2%; Average loss: 2.5503
Iteration: 3330; Percent complete: 83.2%; Average loss: 3.0422
Iteration: 3331; Percent complete: 83.3%; Average loss: 2.9367
Iteration: 3332; Percent complete: 83.3%; Average loss: 2.8277
Iteration: 3333; Percent complete: 83.3%; Average loss: 2.7832
Iteration: 3334; Percent complete: 83.4%; Average loss: 2.8259
Iteration: 3335; Percent complete: 83.4%; Average loss: 2.6796
Iteration: 3336; Percent complete: 83.4%; Average loss: 2.8591
Iteration: 3337; Percent complete: 83.4%; Average loss: 2.7097
Iteration: 3338; Percent complete: 83.5%; Average loss: 2.9406
Iteration: 3339; Percent complete: 83.5%; Average loss: 2.7272
Iteration: 3340; Percent complete: 83.5%; Average loss: 3.0089
Iteration: 3341; Percent complete: 83.5%; Average loss: 2.6358
Iteration: 3342; Percent complete: 83.5%; Average loss: 3.0569
Iteration: 3343; Percent complete: 83.6%; Average loss: 2.8354
Iteration: 3344; Percent complete: 83.6%; Average loss: 2.7050
Iteration: 3345; Percent complete: 83.6%; Average loss: 2.8237
Iteration: 3346; Percent complete: 83.7%; Average loss: 2.8448
Iteration: 3347; Percent complete: 83.7%; Average loss: 2.8783
Iteration: 3348; Percent complete: 83.7%; Average loss: 3.0246
Iteration: 3349; Percent complete: 83.7%; Average loss: 2.9073
Iteration: 3350; Percent complete: 83.8%; Average loss: 2.9559
Iteration: 3351; Percent complete: 83.8%; Average loss: 2.8980
Iteration: 3352; Percent complete: 83.8%; Average loss: 2.8174
Iteration: 3353; Percent complete: 83.8%; Average loss: 2.8192
Iteration: 3354; Percent complete: 83.9%; Average loss: 2.8994
Iteration: 3355; Percent complete: 83.9%; Average loss: 3.0847
Iteration: 3356; Percent complete: 83.9%; Average loss: 2.5398
Iteration: 3357; Percent complete: 83.9%; Average loss: 2.7635
Iteration: 3358; Percent complete: 84.0%; Average loss: 2.7532
Iteration: 3359; Percent complete: 84.0%; Average loss: 2.8338
Iteration: 3360; Percent complete: 84.0%; Average loss: 2.6340
Iteration: 3361; Percent complete: 84.0%; Average loss: 2.9590
Iteration: 3362; Percent complete: 84.0%; Average loss: 3.0363
Iteration: 3363; Percent complete: 84.1%; Average loss: 2.6899
Iteration: 3364; Percent complete: 84.1%; Average loss: 2.9050
Iteration: 3365; Percent complete: 84.1%; Average loss: 2.7825
Iteration: 3366; Percent complete: 84.2%; Average loss: 2.8437
Iteration: 3367; Percent complete: 84.2%; Average loss: 2.8601
Iteration: 3368; Percent complete: 84.2%; Average loss: 2.7874
Iteration: 3369; Percent complete: 84.2%; Average loss: 2.6700
Iteration: 3370; Percent complete: 84.2%; Average loss: 2.7006
Iteration: 3371; Percent complete: 84.3%; Average loss: 2.8662
Iteration: 3372; Percent complete: 84.3%; Average loss: 2.6810
Iteration: 3373; Percent complete: 84.3%; Average loss: 2.8386
Iteration: 3374; Percent complete: 84.4%; Average loss: 2.8532
Iteration: 3375; Percent complete: 84.4%; Average loss: 2.7266
Iteration: 3376; Percent complete: 84.4%; Average loss: 2.7618
Iteration: 3377; Percent complete: 84.4%; Average loss: 2.6686
Iteration: 3378; Percent complete: 84.5%; Average loss: 2.7448
Iteration: 3379; Percent complete: 84.5%; Average loss: 2.8504
Iteration: 3380; Percent complete: 84.5%; Average loss: 3.1116
Iteration: 3381; Percent complete: 84.5%; Average loss: 2.8124
Iteration: 3382; Percent complete: 84.5%; Average loss: 2.7370
Iteration: 3383; Percent complete: 84.6%; Average loss: 2.6556
Iteration: 3384; Percent complete: 84.6%; Average loss: 3.0693
Iteration: 3385; Percent complete: 84.6%; Average loss: 3.0704
Iteration: 3386; Percent complete: 84.7%; Average loss: 2.6262
Iteration: 3387; Percent complete: 84.7%; Average loss: 2.7617
Iteration: 3388; Percent complete: 84.7%; Average loss: 2.7249
Iteration: 3389; Percent complete: 84.7%; Average loss: 2.6859
Iteration: 3390; Percent complete: 84.8%; Average loss: 2.8988
Iteration: 3391; Percent complete: 84.8%; Average loss: 2.6891
Iteration: 3392; Percent complete: 84.8%; Average loss: 2.8238
Iteration: 3393; Percent complete: 84.8%; Average loss: 2.8171
Iteration: 3394; Percent complete: 84.9%; Average loss: 3.0173
Iteration: 3395; Percent complete: 84.9%; Average loss: 2.7811
Iteration: 3396; Percent complete: 84.9%; Average loss: 2.8134
Iteration: 3397; Percent complete: 84.9%; Average loss: 2.8791
Iteration: 3398; Percent complete: 85.0%; Average loss: 2.6300
Iteration: 3399; Percent complete: 85.0%; Average loss: 2.7146
Iteration: 3400; Percent complete: 85.0%; Average loss: 2.8532
Iteration: 3401; Percent complete: 85.0%; Average loss: 2.9273
Iteration: 3402; Percent complete: 85.0%; Average loss: 2.8817
Iteration: 3403; Percent complete: 85.1%; Average loss: 2.6712
Iteration: 3404; Percent complete: 85.1%; Average loss: 2.5923
Iteration: 3405; Percent complete: 85.1%; Average loss: 2.7368
Iteration: 3406; Percent complete: 85.2%; Average loss: 2.7822
Iteration: 3407; Percent complete: 85.2%; Average loss: 2.6522
Iteration: 3408; Percent complete: 85.2%; Average loss: 2.8989
Iteration: 3409; Percent complete: 85.2%; Average loss: 2.6617
Iteration: 3410; Percent complete: 85.2%; Average loss: 2.7569
Iteration: 3411; Percent complete: 85.3%; Average loss: 2.7613
Iteration: 3412; Percent complete: 85.3%; Average loss: 2.9305
Iteration: 3413; Percent complete: 85.3%; Average loss: 2.7493
Iteration: 3414; Percent complete: 85.4%; Average loss: 2.7133
Iteration: 3415; Percent complete: 85.4%; Average loss: 2.7041
Iteration: 3416; Percent complete: 85.4%; Average loss: 2.8515
Iteration: 3417; Percent complete: 85.4%; Average loss: 2.8284
Iteration: 3418; Percent complete: 85.5%; Average loss: 2.7975
Iteration: 3419; Percent complete: 85.5%; Average loss: 2.9267
Iteration: 3420; Percent complete: 85.5%; Average loss: 3.0244
Iteration: 3421; Percent complete: 85.5%; Average loss: 2.6267
Iteration: 3422; Percent complete: 85.5%; Average loss: 2.8479
Iteration: 3423; Percent complete: 85.6%; Average loss: 2.7525
Iteration: 3424; Percent complete: 85.6%; Average loss: 2.9226
Iteration: 3425; Percent complete: 85.6%; Average loss: 2.5924
Iteration: 3426; Percent complete: 85.7%; Average loss: 2.8340
Iteration: 3427; Percent complete: 85.7%; Average loss: 2.9001
Iteration: 3428; Percent complete: 85.7%; Average loss: 2.7072
Iteration: 3429; Percent complete: 85.7%; Average loss: 3.0208
Iteration: 3430; Percent complete: 85.8%; Average loss: 2.6922
Iteration: 3431; Percent complete: 85.8%; Average loss: 2.9038
Iteration: 3432; Percent complete: 85.8%; Average loss: 2.7547
Iteration: 3433; Percent complete: 85.8%; Average loss: 3.0429
Iteration: 3434; Percent complete: 85.9%; Average loss: 2.6946
Iteration: 3435; Percent complete: 85.9%; Average loss: 2.9966
Iteration: 3436; Percent complete: 85.9%; Average loss: 2.8544
Iteration: 3437; Percent complete: 85.9%; Average loss: 2.7535
Iteration: 3438; Percent complete: 86.0%; Average loss: 2.7494
Iteration: 3439; Percent complete: 86.0%; Average loss: 2.8781
Iteration: 3440; Percent complete: 86.0%; Average loss: 2.6929
Iteration: 3441; Percent complete: 86.0%; Average loss: 2.7179
Iteration: 3442; Percent complete: 86.1%; Average loss: 2.7426
Iteration: 3443; Percent complete: 86.1%; Average loss: 2.7539
Iteration: 3444; Percent complete: 86.1%; Average loss: 2.7957
Iteration: 3445; Percent complete: 86.1%; Average loss: 2.9981
Iteration: 3446; Percent complete: 86.2%; Average loss: 2.7104
Iteration: 3447; Percent complete: 86.2%; Average loss: 2.6130
Iteration: 3448; Percent complete: 86.2%; Average loss: 2.8932
Iteration: 3449; Percent complete: 86.2%; Average loss: 2.7080
Iteration: 3450; Percent complete: 86.2%; Average loss: 2.8490
Iteration: 3451; Percent complete: 86.3%; Average loss: 2.6909
Iteration: 3452; Percent complete: 86.3%; Average loss: 2.7758
Iteration: 3453; Percent complete: 86.3%; Average loss: 2.6364
Iteration: 3454; Percent complete: 86.4%; Average loss: 2.8344
Iteration: 3455; Percent complete: 86.4%; Average loss: 2.7098
Iteration: 3456; Percent complete: 86.4%; Average loss: 2.6597
Iteration: 3457; Percent complete: 86.4%; Average loss: 2.8076
Iteration: 3458; Percent complete: 86.5%; Average loss: 2.6250
Iteration: 3459; Percent complete: 86.5%; Average loss: 2.7078
Iteration: 3460; Percent complete: 86.5%; Average loss: 2.6320
Iteration: 3461; Percent complete: 86.5%; Average loss: 2.8139
Iteration: 3462; Percent complete: 86.6%; Average loss: 2.9925
Iteration: 3463; Percent complete: 86.6%; Average loss: 2.5981
Iteration: 3464; Percent complete: 86.6%; Average loss: 2.8686
Iteration: 3465; Percent complete: 86.6%; Average loss: 2.5892
Iteration: 3466; Percent complete: 86.7%; Average loss: 3.0269
Iteration: 3467; Percent complete: 86.7%; Average loss: 2.9405
Iteration: 3468; Percent complete: 86.7%; Average loss: 2.6048
Iteration: 3469; Percent complete: 86.7%; Average loss: 2.6615
Iteration: 3470; Percent complete: 86.8%; Average loss: 2.5544
Iteration: 3471; Percent complete: 86.8%; Average loss: 2.9750
Iteration: 3472; Percent complete: 86.8%; Average loss: 2.6509
Iteration: 3473; Percent complete: 86.8%; Average loss: 2.8651
Iteration: 3474; Percent complete: 86.9%; Average loss: 2.7054
Iteration: 3475; Percent complete: 86.9%; Average loss: 2.6520
Iteration: 3476; Percent complete: 86.9%; Average loss: 2.8902
Iteration: 3477; Percent complete: 86.9%; Average loss: 2.6773
Iteration: 3478; Percent complete: 87.0%; Average loss: 2.8565
Iteration: 3479; Percent complete: 87.0%; Average loss: 2.6690
Iteration: 3480; Percent complete: 87.0%; Average loss: 3.0867
Iteration: 3481; Percent complete: 87.0%; Average loss: 2.7359
Iteration: 3482; Percent complete: 87.1%; Average loss: 2.6664
Iteration: 3483; Percent complete: 87.1%; Average loss: 2.8154
Iteration: 3484; Percent complete: 87.1%; Average loss: 2.9886
Iteration: 3485; Percent complete: 87.1%; Average loss: 2.6688
Iteration: 3486; Percent complete: 87.2%; Average loss: 2.8723
Iteration: 3487; Percent complete: 87.2%; Average loss: 2.7465
Iteration: 3488; Percent complete: 87.2%; Average loss: 2.8812
Iteration: 3489; Percent complete: 87.2%; Average loss: 2.6145
Iteration: 3490; Percent complete: 87.2%; Average loss: 2.5099
Iteration: 3491; Percent complete: 87.3%; Average loss: 2.7621
Iteration: 3492; Percent complete: 87.3%; Average loss: 2.7466
Iteration: 3493; Percent complete: 87.3%; Average loss: 2.8071
Iteration: 3494; Percent complete: 87.4%; Average loss: 2.7222
Iteration: 3495; Percent complete: 87.4%; Average loss: 2.6997
Iteration: 3496; Percent complete: 87.4%; Average loss: 2.5572
Iteration: 3497; Percent complete: 87.4%; Average loss: 2.8296
Iteration: 3498; Percent complete: 87.5%; Average loss: 2.9342
Iteration: 3499; Percent complete: 87.5%; Average loss: 2.6147
Iteration: 3500; Percent complete: 87.5%; Average loss: 2.9481
Iteration: 3501; Percent complete: 87.5%; Average loss: 2.6283
Iteration: 3502; Percent complete: 87.5%; Average loss: 2.6750
Iteration: 3503; Percent complete: 87.6%; Average loss: 2.7780
Iteration: 3504; Percent complete: 87.6%; Average loss: 2.8026
Iteration: 3505; Percent complete: 87.6%; Average loss: 2.8265
Iteration: 3506; Percent complete: 87.6%; Average loss: 2.9365
Iteration: 3507; Percent complete: 87.7%; Average loss: 2.8080
Iteration: 3508; Percent complete: 87.7%; Average loss: 2.7771
Iteration: 3509; Percent complete: 87.7%; Average loss: 2.7334
Iteration: 3510; Percent complete: 87.8%; Average loss: 2.8914
Iteration: 3511; Percent complete: 87.8%; Average loss: 2.6428
Iteration: 3512; Percent complete: 87.8%; Average loss: 2.5487
Iteration: 3513; Percent complete: 87.8%; Average loss: 2.7668
Iteration: 3514; Percent complete: 87.8%; Average loss: 2.9188
Iteration: 3515; Percent complete: 87.9%; Average loss: 2.6267
Iteration: 3516; Percent complete: 87.9%; Average loss: 3.0195
Iteration: 3517; Percent complete: 87.9%; Average loss: 2.7132
Iteration: 3518; Percent complete: 87.9%; Average loss: 2.5591
Iteration: 3519; Percent complete: 88.0%; Average loss: 2.5849
Iteration: 3520; Percent complete: 88.0%; Average loss: 2.5221
Iteration: 3521; Percent complete: 88.0%; Average loss: 2.6822
Iteration: 3522; Percent complete: 88.0%; Average loss: 2.8045
Iteration: 3523; Percent complete: 88.1%; Average loss: 2.7636
Iteration: 3524; Percent complete: 88.1%; Average loss: 2.9799
Iteration: 3525; Percent complete: 88.1%; Average loss: 2.7653
Iteration: 3526; Percent complete: 88.1%; Average loss: 2.9233
Iteration: 3527; Percent complete: 88.2%; Average loss: 2.6488
Iteration: 3528; Percent complete: 88.2%; Average loss: 2.6621
Iteration: 3529; Percent complete: 88.2%; Average loss: 2.8946
Iteration: 3530; Percent complete: 88.2%; Average loss: 2.6212
Iteration: 3531; Percent complete: 88.3%; Average loss: 2.6811
Iteration: 3532; Percent complete: 88.3%; Average loss: 2.6720
Iteration: 3533; Percent complete: 88.3%; Average loss: 2.8970
Iteration: 3534; Percent complete: 88.3%; Average loss: 2.7379
Iteration: 3535; Percent complete: 88.4%; Average loss: 2.7567
Iteration: 3536; Percent complete: 88.4%; Average loss: 2.6398
Iteration: 3537; Percent complete: 88.4%; Average loss: 2.7239
Iteration: 3538; Percent complete: 88.4%; Average loss: 2.6311
Iteration: 3539; Percent complete: 88.5%; Average loss: 2.8313
Iteration: 3540; Percent complete: 88.5%; Average loss: 2.7208
Iteration: 3541; Percent complete: 88.5%; Average loss: 2.6788
Iteration: 3542; Percent complete: 88.5%; Average loss: 2.8477
Iteration: 3543; Percent complete: 88.6%; Average loss: 2.7757
Iteration: 3544; Percent complete: 88.6%; Average loss: 2.7421
Iteration: 3545; Percent complete: 88.6%; Average loss: 2.5662
Iteration: 3546; Percent complete: 88.6%; Average loss: 2.7110
Iteration: 3547; Percent complete: 88.7%; Average loss: 2.8621
Iteration: 3548; Percent complete: 88.7%; Average loss: 3.0315
Iteration: 3549; Percent complete: 88.7%; Average loss: 2.7885
Iteration: 3550; Percent complete: 88.8%; Average loss: 2.8232
Iteration: 3551; Percent complete: 88.8%; Average loss: 2.6269
Iteration: 3552; Percent complete: 88.8%; Average loss: 2.8046
Iteration: 3553; Percent complete: 88.8%; Average loss: 2.8751
Iteration: 3554; Percent complete: 88.8%; Average loss: 2.7339
Iteration: 3555; Percent complete: 88.9%; Average loss: 2.6459
Iteration: 3556; Percent complete: 88.9%; Average loss: 2.7370
Iteration: 3557; Percent complete: 88.9%; Average loss: 2.7303
Iteration: 3558; Percent complete: 88.9%; Average loss: 2.7691
Iteration: 3559; Percent complete: 89.0%; Average loss: 2.8449
Iteration: 3560; Percent complete: 89.0%; Average loss: 2.7175
Iteration: 3561; Percent complete: 89.0%; Average loss: 2.9046
Iteration: 3562; Percent complete: 89.0%; Average loss: 2.8577
Iteration: 3563; Percent complete: 89.1%; Average loss: 2.7129
Iteration: 3564; Percent complete: 89.1%; Average loss: 2.6265
Iteration: 3565; Percent complete: 89.1%; Average loss: 2.7243
Iteration: 3566; Percent complete: 89.1%; Average loss: 2.8371
Iteration: 3567; Percent complete: 89.2%; Average loss: 2.5382
Iteration: 3568; Percent complete: 89.2%; Average loss: 2.8322
Iteration: 3569; Percent complete: 89.2%; Average loss: 2.6188
Iteration: 3570; Percent complete: 89.2%; Average loss: 2.6884
Iteration: 3571; Percent complete: 89.3%; Average loss: 2.7414
Iteration: 3572; Percent complete: 89.3%; Average loss: 2.8275
Iteration: 3573; Percent complete: 89.3%; Average loss: 2.9285
Iteration: 3574; Percent complete: 89.3%; Average loss: 2.5385
Iteration: 3575; Percent complete: 89.4%; Average loss: 2.7138
Iteration: 3576; Percent complete: 89.4%; Average loss: 2.7291
Iteration: 3577; Percent complete: 89.4%; Average loss: 2.9285
Iteration: 3578; Percent complete: 89.5%; Average loss: 2.6214
Iteration: 3579; Percent complete: 89.5%; Average loss: 2.8209
Iteration: 3580; Percent complete: 89.5%; Average loss: 2.6785
Iteration: 3581; Percent complete: 89.5%; Average loss: 2.5499
Iteration: 3582; Percent complete: 89.5%; Average loss: 2.7689
Iteration: 3583; Percent complete: 89.6%; Average loss: 2.9266
Iteration: 3584; Percent complete: 89.6%; Average loss: 2.9971
Iteration: 3585; Percent complete: 89.6%; Average loss: 2.8706
Iteration: 3586; Percent complete: 89.6%; Average loss: 2.7400
Iteration: 3587; Percent complete: 89.7%; Average loss: 2.8496
Iteration: 3588; Percent complete: 89.7%; Average loss: 2.6338
Iteration: 3589; Percent complete: 89.7%; Average loss: 2.7606
Iteration: 3590; Percent complete: 89.8%; Average loss: 2.4954
Iteration: 3591; Percent complete: 89.8%; Average loss: 2.8249
Iteration: 3592; Percent complete: 89.8%; Average loss: 2.6683
Iteration: 3593; Percent complete: 89.8%; Average loss: 2.7079
Iteration: 3594; Percent complete: 89.8%; Average loss: 2.7270
Iteration: 3595; Percent complete: 89.9%; Average loss: 2.5208
Iteration: 3596; Percent complete: 89.9%; Average loss: 2.5758
Iteration: 3597; Percent complete: 89.9%; Average loss: 2.5565
Iteration: 3598; Percent complete: 90.0%; Average loss: 2.7206
Iteration: 3599; Percent complete: 90.0%; Average loss: 2.8679
Iteration: 3600; Percent complete: 90.0%; Average loss: 2.7978
Iteration: 3601; Percent complete: 90.0%; Average loss: 2.7805
Iteration: 3602; Percent complete: 90.0%; Average loss: 2.7312
Iteration: 3603; Percent complete: 90.1%; Average loss: 2.7251
Iteration: 3604; Percent complete: 90.1%; Average loss: 2.7965
Iteration: 3605; Percent complete: 90.1%; Average loss: 2.5605
Iteration: 3606; Percent complete: 90.1%; Average loss: 2.7757
Iteration: 3607; Percent complete: 90.2%; Average loss: 2.6802
Iteration: 3608; Percent complete: 90.2%; Average loss: 2.8923
Iteration: 3609; Percent complete: 90.2%; Average loss: 2.7359
Iteration: 3610; Percent complete: 90.2%; Average loss: 2.6599
Iteration: 3611; Percent complete: 90.3%; Average loss: 2.7632
Iteration: 3612; Percent complete: 90.3%; Average loss: 2.6786
Iteration: 3613; Percent complete: 90.3%; Average loss: 2.6161
Iteration: 3614; Percent complete: 90.3%; Average loss: 2.8393
Iteration: 3615; Percent complete: 90.4%; Average loss: 2.6421
Iteration: 3616; Percent complete: 90.4%; Average loss: 2.8796
Iteration: 3617; Percent complete: 90.4%; Average loss: 2.6013
Iteration: 3618; Percent complete: 90.5%; Average loss: 2.9843
Iteration: 3619; Percent complete: 90.5%; Average loss: 2.7328
Iteration: 3620; Percent complete: 90.5%; Average loss: 2.7319
Iteration: 3621; Percent complete: 90.5%; Average loss: 2.8193
Iteration: 3622; Percent complete: 90.5%; Average loss: 2.9318
Iteration: 3623; Percent complete: 90.6%; Average loss: 2.7047
Iteration: 3624; Percent complete: 90.6%; Average loss: 2.5255
Iteration: 3625; Percent complete: 90.6%; Average loss: 2.7421
Iteration: 3626; Percent complete: 90.6%; Average loss: 2.7364
Iteration: 3627; Percent complete: 90.7%; Average loss: 2.6150
Iteration: 3628; Percent complete: 90.7%; Average loss: 2.8597
Iteration: 3629; Percent complete: 90.7%; Average loss: 2.7144
Iteration: 3630; Percent complete: 90.8%; Average loss: 2.6444
Iteration: 3631; Percent complete: 90.8%; Average loss: 2.5500
Iteration: 3632; Percent complete: 90.8%; Average loss: 2.7936
Iteration: 3633; Percent complete: 90.8%; Average loss: 2.7117
Iteration: 3634; Percent complete: 90.8%; Average loss: 2.9818
Iteration: 3635; Percent complete: 90.9%; Average loss: 2.5725
Iteration: 3636; Percent complete: 90.9%; Average loss: 2.6687
Iteration: 3637; Percent complete: 90.9%; Average loss: 2.7567
Iteration: 3638; Percent complete: 91.0%; Average loss: 2.5483
Iteration: 3639; Percent complete: 91.0%; Average loss: 2.4368
Iteration: 3640; Percent complete: 91.0%; Average loss: 2.4663
Iteration: 3641; Percent complete: 91.0%; Average loss: 2.6717
Iteration: 3642; Percent complete: 91.0%; Average loss: 2.5941
Iteration: 3643; Percent complete: 91.1%; Average loss: 2.7992
Iteration: 3644; Percent complete: 91.1%; Average loss: 2.9068
Iteration: 3645; Percent complete: 91.1%; Average loss: 2.9053
Iteration: 3646; Percent complete: 91.1%; Average loss: 2.5113
Iteration: 3647; Percent complete: 91.2%; Average loss: 2.9811
Iteration: 3648; Percent complete: 91.2%; Average loss: 2.6278
Iteration: 3649; Percent complete: 91.2%; Average loss: 2.7281
Iteration: 3650; Percent complete: 91.2%; Average loss: 2.6856
Iteration: 3651; Percent complete: 91.3%; Average loss: 2.7732
Iteration: 3652; Percent complete: 91.3%; Average loss: 2.6732
Iteration: 3653; Percent complete: 91.3%; Average loss: 2.9407
Iteration: 3654; Percent complete: 91.3%; Average loss: 2.7160
Iteration: 3655; Percent complete: 91.4%; Average loss: 2.8962
Iteration: 3656; Percent complete: 91.4%; Average loss: 2.9121
Iteration: 3657; Percent complete: 91.4%; Average loss: 2.5549
Iteration: 3658; Percent complete: 91.5%; Average loss: 2.6935
Iteration: 3659; Percent complete: 91.5%; Average loss: 2.7572
Iteration: 3660; Percent complete: 91.5%; Average loss: 2.8760
Iteration: 3661; Percent complete: 91.5%; Average loss: 2.8685
Iteration: 3662; Percent complete: 91.5%; Average loss: 2.9243
Iteration: 3663; Percent complete: 91.6%; Average loss: 2.6306
Iteration: 3664; Percent complete: 91.6%; Average loss: 2.6148
Iteration: 3665; Percent complete: 91.6%; Average loss: 2.7278
Iteration: 3666; Percent complete: 91.6%; Average loss: 2.6936
Iteration: 3667; Percent complete: 91.7%; Average loss: 2.7202
Iteration: 3668; Percent complete: 91.7%; Average loss: 2.5002
Iteration: 3669; Percent complete: 91.7%; Average loss: 2.7430
Iteration: 3670; Percent complete: 91.8%; Average loss: 2.5486
Iteration: 3671; Percent complete: 91.8%; Average loss: 2.7810
Iteration: 3672; Percent complete: 91.8%; Average loss: 2.5332
Iteration: 3673; Percent complete: 91.8%; Average loss: 2.5237
Iteration: 3674; Percent complete: 91.8%; Average loss: 2.7639
Iteration: 3675; Percent complete: 91.9%; Average loss: 2.5344
Iteration: 3676; Percent complete: 91.9%; Average loss: 2.4672
Iteration: 3677; Percent complete: 91.9%; Average loss: 2.6343
Iteration: 3678; Percent complete: 92.0%; Average loss: 2.8695
Iteration: 3679; Percent complete: 92.0%; Average loss: 2.7125
Iteration: 3680; Percent complete: 92.0%; Average loss: 2.8307
Iteration: 3681; Percent complete: 92.0%; Average loss: 2.7140
Iteration: 3682; Percent complete: 92.0%; Average loss: 2.6311
Iteration: 3683; Percent complete: 92.1%; Average loss: 2.6001
Iteration: 3684; Percent complete: 92.1%; Average loss: 2.8614
Iteration: 3685; Percent complete: 92.1%; Average loss: 2.8632
Iteration: 3686; Percent complete: 92.2%; Average loss: 2.5586
Iteration: 3687; Percent complete: 92.2%; Average loss: 2.9473
Iteration: 3688; Percent complete: 92.2%; Average loss: 2.5319
Iteration: 3689; Percent complete: 92.2%; Average loss: 2.7202
Iteration: 3690; Percent complete: 92.2%; Average loss: 2.7837
Iteration: 3691; Percent complete: 92.3%; Average loss: 2.5305
Iteration: 3692; Percent complete: 92.3%; Average loss: 2.5668
Iteration: 3693; Percent complete: 92.3%; Average loss: 2.7149
Iteration: 3694; Percent complete: 92.3%; Average loss: 2.6735
Iteration: 3695; Percent complete: 92.4%; Average loss: 2.4322
Iteration: 3696; Percent complete: 92.4%; Average loss: 2.5483
Iteration: 3697; Percent complete: 92.4%; Average loss: 2.7975
Iteration: 3698; Percent complete: 92.5%; Average loss: 2.7479
Iteration: 3699; Percent complete: 92.5%; Average loss: 2.7191
Iteration: 3700; Percent complete: 92.5%; Average loss: 2.8111
Iteration: 3701; Percent complete: 92.5%; Average loss: 2.5752
Iteration: 3702; Percent complete: 92.5%; Average loss: 2.6854
Iteration: 3703; Percent complete: 92.6%; Average loss: 2.5552
Iteration: 3704; Percent complete: 92.6%; Average loss: 2.6709
Iteration: 3705; Percent complete: 92.6%; Average loss: 2.7727
Iteration: 3706; Percent complete: 92.7%; Average loss: 2.7901
Iteration: 3707; Percent complete: 92.7%; Average loss: 2.7961
Iteration: 3708; Percent complete: 92.7%; Average loss: 2.8012
Iteration: 3709; Percent complete: 92.7%; Average loss: 2.5483
Iteration: 3710; Percent complete: 92.8%; Average loss: 2.6113
Iteration: 3711; Percent complete: 92.8%; Average loss: 2.7090
Iteration: 3712; Percent complete: 92.8%; Average loss: 2.5675
Iteration: 3713; Percent complete: 92.8%; Average loss: 2.5888
Iteration: 3714; Percent complete: 92.8%; Average loss: 2.5271
Iteration: 3715; Percent complete: 92.9%; Average loss: 2.7520
Iteration: 3716; Percent complete: 92.9%; Average loss: 2.7057
Iteration: 3717; Percent complete: 92.9%; Average loss: 2.9007
Iteration: 3718; Percent complete: 93.0%; Average loss: 2.7466
Iteration: 3719; Percent complete: 93.0%; Average loss: 2.4001
Iteration: 3720; Percent complete: 93.0%; Average loss: 2.6847
Iteration: 3721; Percent complete: 93.0%; Average loss: 2.5400
Iteration: 3722; Percent complete: 93.0%; Average loss: 2.6797
Iteration: 3723; Percent complete: 93.1%; Average loss: 2.7437
Iteration: 3724; Percent complete: 93.1%; Average loss: 3.0102
Iteration: 3725; Percent complete: 93.1%; Average loss: 2.7793
Iteration: 3726; Percent complete: 93.2%; Average loss: 2.6107
Iteration: 3727; Percent complete: 93.2%; Average loss: 2.9473
Iteration: 3728; Percent complete: 93.2%; Average loss: 2.8766
Iteration: 3729; Percent complete: 93.2%; Average loss: 2.6096
Iteration: 3730; Percent complete: 93.2%; Average loss: 2.7301
Iteration: 3731; Percent complete: 93.3%; Average loss: 2.8683
Iteration: 3732; Percent complete: 93.3%; Average loss: 2.7813
Iteration: 3733; Percent complete: 93.3%; Average loss: 2.6941
Iteration: 3734; Percent complete: 93.3%; Average loss: 2.4968
Iteration: 3735; Percent complete: 93.4%; Average loss: 2.5977
Iteration: 3736; Percent complete: 93.4%; Average loss: 2.8034
Iteration: 3737; Percent complete: 93.4%; Average loss: 2.6825
Iteration: 3738; Percent complete: 93.5%; Average loss: 2.7477
Iteration: 3739; Percent complete: 93.5%; Average loss: 2.6298
Iteration: 3740; Percent complete: 93.5%; Average loss: 2.7750
Iteration: 3741; Percent complete: 93.5%; Average loss: 2.5233
Iteration: 3742; Percent complete: 93.5%; Average loss: 2.5772
Iteration: 3743; Percent complete: 93.6%; Average loss: 2.5236
Iteration: 3744; Percent complete: 93.6%; Average loss: 2.7461
Iteration: 3745; Percent complete: 93.6%; Average loss: 2.7723
Iteration: 3746; Percent complete: 93.7%; Average loss: 2.8520
Iteration: 3747; Percent complete: 93.7%; Average loss: 2.7897
Iteration: 3748; Percent complete: 93.7%; Average loss: 2.5492
Iteration: 3749; Percent complete: 93.7%; Average loss: 2.6327
Iteration: 3750; Percent complete: 93.8%; Average loss: 2.7653
Iteration: 3751; Percent complete: 93.8%; Average loss: 2.3823
Iteration: 3752; Percent complete: 93.8%; Average loss: 2.8005
Iteration: 3753; Percent complete: 93.8%; Average loss: 2.5262
Iteration: 3754; Percent complete: 93.8%; Average loss: 2.5968
Iteration: 3755; Percent complete: 93.9%; Average loss: 2.9705
Iteration: 3756; Percent complete: 93.9%; Average loss: 2.6793
Iteration: 3757; Percent complete: 93.9%; Average loss: 2.6938
Iteration: 3758; Percent complete: 94.0%; Average loss: 2.7175
Iteration: 3759; Percent complete: 94.0%; Average loss: 2.7476
Iteration: 3760; Percent complete: 94.0%; Average loss: 2.6821
Iteration: 3761; Percent complete: 94.0%; Average loss: 2.7563
Iteration: 3762; Percent complete: 94.0%; Average loss: 2.4211
Iteration: 3763; Percent complete: 94.1%; Average loss: 2.6575
Iteration: 3764; Percent complete: 94.1%; Average loss: 2.5663
Iteration: 3765; Percent complete: 94.1%; Average loss: 2.6575
Iteration: 3766; Percent complete: 94.2%; Average loss: 2.6833
Iteration: 3767; Percent complete: 94.2%; Average loss: 2.5467
Iteration: 3768; Percent complete: 94.2%; Average loss: 2.7672
Iteration: 3769; Percent complete: 94.2%; Average loss: 2.8091
Iteration: 3770; Percent complete: 94.2%; Average loss: 2.5893
Iteration: 3771; Percent complete: 94.3%; Average loss: 2.5235
Iteration: 3772; Percent complete: 94.3%; Average loss: 2.8396
Iteration: 3773; Percent complete: 94.3%; Average loss: 2.8842
Iteration: 3774; Percent complete: 94.3%; Average loss: 2.8166
Iteration: 3775; Percent complete: 94.4%; Average loss: 2.8232
Iteration: 3776; Percent complete: 94.4%; Average loss: 2.5385
Iteration: 3777; Percent complete: 94.4%; Average loss: 2.6833
Iteration: 3778; Percent complete: 94.5%; Average loss: 2.6074
Iteration: 3779; Percent complete: 94.5%; Average loss: 2.8641
Iteration: 3780; Percent complete: 94.5%; Average loss: 2.7841
Iteration: 3781; Percent complete: 94.5%; Average loss: 2.6378
Iteration: 3782; Percent complete: 94.5%; Average loss: 2.7058
Iteration: 3783; Percent complete: 94.6%; Average loss: 2.7272
Iteration: 3784; Percent complete: 94.6%; Average loss: 2.6726
Iteration: 3785; Percent complete: 94.6%; Average loss: 2.5650
Iteration: 3786; Percent complete: 94.7%; Average loss: 2.7934
Iteration: 3787; Percent complete: 94.7%; Average loss: 2.7885
Iteration: 3788; Percent complete: 94.7%; Average loss: 2.8663
Iteration: 3789; Percent complete: 94.7%; Average loss: 2.7104
Iteration: 3790; Percent complete: 94.8%; Average loss: 2.7135
Iteration: 3791; Percent complete: 94.8%; Average loss: 2.9194
Iteration: 3792; Percent complete: 94.8%; Average loss: 2.7984
Iteration: 3793; Percent complete: 94.8%; Average loss: 2.9135
Iteration: 3794; Percent complete: 94.8%; Average loss: 2.4967
Iteration: 3795; Percent complete: 94.9%; Average loss: 2.7250
Iteration: 3796; Percent complete: 94.9%; Average loss: 2.6041
Iteration: 3797; Percent complete: 94.9%; Average loss: 2.6721
Iteration: 3798; Percent complete: 95.0%; Average loss: 2.8082
Iteration: 3799; Percent complete: 95.0%; Average loss: 2.6714
Iteration: 3800; Percent complete: 95.0%; Average loss: 2.5728
Iteration: 3801; Percent complete: 95.0%; Average loss: 2.4715
Iteration: 3802; Percent complete: 95.0%; Average loss: 2.6771
Iteration: 3803; Percent complete: 95.1%; Average loss: 2.6367
Iteration: 3804; Percent complete: 95.1%; Average loss: 2.8160
Iteration: 3805; Percent complete: 95.1%; Average loss: 2.6974
Iteration: 3806; Percent complete: 95.2%; Average loss: 2.6064
Iteration: 3807; Percent complete: 95.2%; Average loss: 2.9247
Iteration: 3808; Percent complete: 95.2%; Average loss: 2.9512
Iteration: 3809; Percent complete: 95.2%; Average loss: 2.8399
Iteration: 3810; Percent complete: 95.2%; Average loss: 2.6301
Iteration: 3811; Percent complete: 95.3%; Average loss: 2.7354
Iteration: 3812; Percent complete: 95.3%; Average loss: 2.5630
Iteration: 3813; Percent complete: 95.3%; Average loss: 2.6929
Iteration: 3814; Percent complete: 95.3%; Average loss: 2.8394
Iteration: 3815; Percent complete: 95.4%; Average loss: 2.5861
Iteration: 3816; Percent complete: 95.4%; Average loss: 2.5943
Iteration: 3817; Percent complete: 95.4%; Average loss: 2.6736
Iteration: 3818; Percent complete: 95.5%; Average loss: 2.7110
Iteration: 3819; Percent complete: 95.5%; Average loss: 2.9031
Iteration: 3820; Percent complete: 95.5%; Average loss: 2.6066
Iteration: 3821; Percent complete: 95.5%; Average loss: 2.9312
Iteration: 3822; Percent complete: 95.5%; Average loss: 2.6957
Iteration: 3823; Percent complete: 95.6%; Average loss: 2.5373
Iteration: 3824; Percent complete: 95.6%; Average loss: 2.7260
Iteration: 3825; Percent complete: 95.6%; Average loss: 2.6427
Iteration: 3826; Percent complete: 95.7%; Average loss: 2.5507
Iteration: 3827; Percent complete: 95.7%; Average loss: 2.5602
Iteration: 3828; Percent complete: 95.7%; Average loss: 2.9442
Iteration: 3829; Percent complete: 95.7%; Average loss: 2.5425
Iteration: 3830; Percent complete: 95.8%; Average loss: 2.5630
Iteration: 3831; Percent complete: 95.8%; Average loss: 2.7419
Iteration: 3832; Percent complete: 95.8%; Average loss: 2.9029
Iteration: 3833; Percent complete: 95.8%; Average loss: 2.6371
Iteration: 3834; Percent complete: 95.9%; Average loss: 2.6609
Iteration: 3835; Percent complete: 95.9%; Average loss: 2.6216
Iteration: 3836; Percent complete: 95.9%; Average loss: 3.1128
Iteration: 3837; Percent complete: 95.9%; Average loss: 2.8250
Iteration: 3838; Percent complete: 96.0%; Average loss: 2.7302
Iteration: 3839; Percent complete: 96.0%; Average loss: 2.6904
Iteration: 3840; Percent complete: 96.0%; Average loss: 2.6700
Iteration: 3841; Percent complete: 96.0%; Average loss: 2.9753
Iteration: 3842; Percent complete: 96.0%; Average loss: 2.5086
Iteration: 3843; Percent complete: 96.1%; Average loss: 2.5214
Iteration: 3844; Percent complete: 96.1%; Average loss: 2.7649
Iteration: 3845; Percent complete: 96.1%; Average loss: 2.6289
Iteration: 3846; Percent complete: 96.2%; Average loss: 2.6503
Iteration: 3847; Percent complete: 96.2%; Average loss: 2.6718
Iteration: 3848; Percent complete: 96.2%; Average loss: 2.7157
Iteration: 3849; Percent complete: 96.2%; Average loss: 2.5285
Iteration: 3850; Percent complete: 96.2%; Average loss: 2.8039
Iteration: 3851; Percent complete: 96.3%; Average loss: 2.4141
Iteration: 3852; Percent complete: 96.3%; Average loss: 2.7743
Iteration: 3853; Percent complete: 96.3%; Average loss: 2.5910
Iteration: 3854; Percent complete: 96.4%; Average loss: 2.5532
Iteration: 3855; Percent complete: 96.4%; Average loss: 2.7406
Iteration: 3856; Percent complete: 96.4%; Average loss: 2.7272
Iteration: 3857; Percent complete: 96.4%; Average loss: 2.6023
Iteration: 3858; Percent complete: 96.5%; Average loss: 2.7463
Iteration: 3859; Percent complete: 96.5%; Average loss: 2.7139
Iteration: 3860; Percent complete: 96.5%; Average loss: 2.6671
Iteration: 3861; Percent complete: 96.5%; Average loss: 2.8736
Iteration: 3862; Percent complete: 96.5%; Average loss: 2.6894
Iteration: 3863; Percent complete: 96.6%; Average loss: 2.3750
Iteration: 3864; Percent complete: 96.6%; Average loss: 2.4605
Iteration: 3865; Percent complete: 96.6%; Average loss: 2.7480
Iteration: 3866; Percent complete: 96.7%; Average loss: 2.7670
Iteration: 3867; Percent complete: 96.7%; Average loss: 2.6865
Iteration: 3868; Percent complete: 96.7%; Average loss: 2.7617
Iteration: 3869; Percent complete: 96.7%; Average loss: 2.8280
Iteration: 3870; Percent complete: 96.8%; Average loss: 2.6631
Iteration: 3871; Percent complete: 96.8%; Average loss: 2.6081
Iteration: 3872; Percent complete: 96.8%; Average loss: 2.6377
Iteration: 3873; Percent complete: 96.8%; Average loss: 2.7923
Iteration: 3874; Percent complete: 96.9%; Average loss: 2.4645
Iteration: 3875; Percent complete: 96.9%; Average loss: 2.7607
Iteration: 3876; Percent complete: 96.9%; Average loss: 2.7651
Iteration: 3877; Percent complete: 96.9%; Average loss: 2.5758
Iteration: 3878; Percent complete: 97.0%; Average loss: 2.5233
Iteration: 3879; Percent complete: 97.0%; Average loss: 2.5571
Iteration: 3880; Percent complete: 97.0%; Average loss: 2.8894
Iteration: 3881; Percent complete: 97.0%; Average loss: 2.6726
Iteration: 3882; Percent complete: 97.0%; Average loss: 2.4804
Iteration: 3883; Percent complete: 97.1%; Average loss: 2.7361
Iteration: 3884; Percent complete: 97.1%; Average loss: 2.8497
Iteration: 3885; Percent complete: 97.1%; Average loss: 2.6150
Iteration: 3886; Percent complete: 97.2%; Average loss: 2.8203
Iteration: 3887; Percent complete: 97.2%; Average loss: 2.6512
Iteration: 3888; Percent complete: 97.2%; Average loss: 2.3146
Iteration: 3889; Percent complete: 97.2%; Average loss: 2.7217
Iteration: 3890; Percent complete: 97.2%; Average loss: 2.6425
Iteration: 3891; Percent complete: 97.3%; Average loss: 2.5378
Iteration: 3892; Percent complete: 97.3%; Average loss: 2.6920
Iteration: 3893; Percent complete: 97.3%; Average loss: 2.6833
Iteration: 3894; Percent complete: 97.4%; Average loss: 2.6799
Iteration: 3895; Percent complete: 97.4%; Average loss: 2.7808
Iteration: 3896; Percent complete: 97.4%; Average loss: 2.7416
Iteration: 3897; Percent complete: 97.4%; Average loss: 2.7673
Iteration: 3898; Percent complete: 97.5%; Average loss: 2.4965
Iteration: 3899; Percent complete: 97.5%; Average loss: 2.7090
Iteration: 3900; Percent complete: 97.5%; Average loss: 2.8942
Iteration: 3901; Percent complete: 97.5%; Average loss: 2.6634
Iteration: 3902; Percent complete: 97.5%; Average loss: 2.6948
Iteration: 3903; Percent complete: 97.6%; Average loss: 2.6435
Iteration: 3904; Percent complete: 97.6%; Average loss: 2.8506
Iteration: 3905; Percent complete: 97.6%; Average loss: 2.5460
Iteration: 3906; Percent complete: 97.7%; Average loss: 2.7100
Iteration: 3907; Percent complete: 97.7%; Average loss: 2.4893
Iteration: 3908; Percent complete: 97.7%; Average loss: 2.6329
Iteration: 3909; Percent complete: 97.7%; Average loss: 2.5531
Iteration: 3910; Percent complete: 97.8%; Average loss: 2.7290
Iteration: 3911; Percent complete: 97.8%; Average loss: 2.7149
Iteration: 3912; Percent complete: 97.8%; Average loss: 2.6510
Iteration: 3913; Percent complete: 97.8%; Average loss: 2.6585
Iteration: 3914; Percent complete: 97.9%; Average loss: 2.6071
Iteration: 3915; Percent complete: 97.9%; Average loss: 2.7052
Iteration: 3916; Percent complete: 97.9%; Average loss: 2.8115
Iteration: 3917; Percent complete: 97.9%; Average loss: 2.6736
Iteration: 3918; Percent complete: 98.0%; Average loss: 2.6441
Iteration: 3919; Percent complete: 98.0%; Average loss: 2.7012
Iteration: 3920; Percent complete: 98.0%; Average loss: 2.5902
Iteration: 3921; Percent complete: 98.0%; Average loss: 2.7146
Iteration: 3922; Percent complete: 98.0%; Average loss: 2.6488
Iteration: 3923; Percent complete: 98.1%; Average loss: 2.6527
Iteration: 3924; Percent complete: 98.1%; Average loss: 2.7309
Iteration: 3925; Percent complete: 98.1%; Average loss: 2.5669
Iteration: 3926; Percent complete: 98.2%; Average loss: 2.5474
Iteration: 3927; Percent complete: 98.2%; Average loss: 2.4622
Iteration: 3928; Percent complete: 98.2%; Average loss: 2.7264
Iteration: 3929; Percent complete: 98.2%; Average loss: 2.8862
Iteration: 3930; Percent complete: 98.2%; Average loss: 2.7426
Iteration: 3931; Percent complete: 98.3%; Average loss: 2.6448
Iteration: 3932; Percent complete: 98.3%; Average loss: 2.7587
Iteration: 3933; Percent complete: 98.3%; Average loss: 2.4502
Iteration: 3934; Percent complete: 98.4%; Average loss: 2.4764
Iteration: 3935; Percent complete: 98.4%; Average loss: 2.4853
Iteration: 3936; Percent complete: 98.4%; Average loss: 2.8631
Iteration: 3937; Percent complete: 98.4%; Average loss: 2.6105
Iteration: 3938; Percent complete: 98.5%; Average loss: 2.5268
Iteration: 3939; Percent complete: 98.5%; Average loss: 2.8069
Iteration: 3940; Percent complete: 98.5%; Average loss: 2.6835
Iteration: 3941; Percent complete: 98.5%; Average loss: 2.7616
Iteration: 3942; Percent complete: 98.6%; Average loss: 2.6584
Iteration: 3943; Percent complete: 98.6%; Average loss: 2.6707
Iteration: 3944; Percent complete: 98.6%; Average loss: 2.4646
Iteration: 3945; Percent complete: 98.6%; Average loss: 2.8146
Iteration: 3946; Percent complete: 98.7%; Average loss: 2.6327
Iteration: 3947; Percent complete: 98.7%; Average loss: 2.7211
Iteration: 3948; Percent complete: 98.7%; Average loss: 2.7396
Iteration: 3949; Percent complete: 98.7%; Average loss: 2.5786
Iteration: 3950; Percent complete: 98.8%; Average loss: 2.4315
Iteration: 3951; Percent complete: 98.8%; Average loss: 2.8739
Iteration: 3952; Percent complete: 98.8%; Average loss: 2.8038
Iteration: 3953; Percent complete: 98.8%; Average loss: 2.7785
Iteration: 3954; Percent complete: 98.9%; Average loss: 2.6200
Iteration: 3955; Percent complete: 98.9%; Average loss: 2.5646
Iteration: 3956; Percent complete: 98.9%; Average loss: 2.4705
Iteration: 3957; Percent complete: 98.9%; Average loss: 2.6574
Iteration: 3958; Percent complete: 99.0%; Average loss: 2.6061
Iteration: 3959; Percent complete: 99.0%; Average loss: 2.4275
Iteration: 3960; Percent complete: 99.0%; Average loss: 2.5401
Iteration: 3961; Percent complete: 99.0%; Average loss: 2.5700
Iteration: 3962; Percent complete: 99.1%; Average loss: 2.8620
Iteration: 3963; Percent complete: 99.1%; Average loss: 2.6855
Iteration: 3964; Percent complete: 99.1%; Average loss: 2.5324
Iteration: 3965; Percent complete: 99.1%; Average loss: 2.8401
Iteration: 3966; Percent complete: 99.2%; Average loss: 2.6541
Iteration: 3967; Percent complete: 99.2%; Average loss: 2.6913
Iteration: 3968; Percent complete: 99.2%; Average loss: 2.4323
Iteration: 3969; Percent complete: 99.2%; Average loss: 2.5544
Iteration: 3970; Percent complete: 99.2%; Average loss: 2.6103
Iteration: 3971; Percent complete: 99.3%; Average loss: 2.7237
Iteration: 3972; Percent complete: 99.3%; Average loss: 2.4466
Iteration: 3973; Percent complete: 99.3%; Average loss: 2.7704
Iteration: 3974; Percent complete: 99.4%; Average loss: 2.6467
Iteration: 3975; Percent complete: 99.4%; Average loss: 2.7228
Iteration: 3976; Percent complete: 99.4%; Average loss: 2.6482
Iteration: 3977; Percent complete: 99.4%; Average loss: 2.7635
Iteration: 3978; Percent complete: 99.5%; Average loss: 2.6193
Iteration: 3979; Percent complete: 99.5%; Average loss: 2.7478
Iteration: 3980; Percent complete: 99.5%; Average loss: 2.5559
Iteration: 3981; Percent complete: 99.5%; Average loss: 2.6186
Iteration: 3982; Percent complete: 99.6%; Average loss: 2.7932
Iteration: 3983; Percent complete: 99.6%; Average loss: 2.7155
Iteration: 3984; Percent complete: 99.6%; Average loss: 2.6393
Iteration: 3985; Percent complete: 99.6%; Average loss: 2.7582
Iteration: 3986; Percent complete: 99.7%; Average loss: 2.6424
Iteration: 3987; Percent complete: 99.7%; Average loss: 2.7592
Iteration: 3988; Percent complete: 99.7%; Average loss: 2.5976
Iteration: 3989; Percent complete: 99.7%; Average loss: 2.6695
Iteration: 3990; Percent complete: 99.8%; Average loss: 2.9082
Iteration: 3991; Percent complete: 99.8%; Average loss: 2.6914
Iteration: 3992; Percent complete: 99.8%; Average loss: 2.5387
Iteration: 3993; Percent complete: 99.8%; Average loss: 2.8128
Iteration: 3994; Percent complete: 99.9%; Average loss: 2.5408
Iteration: 3995; Percent complete: 99.9%; Average loss: 2.3835
Iteration: 3996; Percent complete: 99.9%; Average loss: 2.5489
Iteration: 3997; Percent complete: 99.9%; Average loss: 2.5340
Iteration: 3998; Percent complete: 100.0%; Average loss: 2.7456
Iteration: 3999; Percent complete: 100.0%; Average loss: 2.7207
Iteration: 4000; Percent complete: 100.0%; Average loss: 2.5589

Run Evaluation#

To chat with your model, run the following block.

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

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

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

Conclusion#

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

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

Total running time of the script: (2 minutes 19.130 seconds)

Chatbot Tutorial#

Preparations#

Load & Preprocess Data#

Create formatted data file#

Load and trim data#

Prepare Data for Models#

Define Models#

Seq2Seq Model#

Encoder#

Decoder#

Define Training Procedure#

Masked loss#

Single training iteration#

Training iterations#

Define Evaluation#

Greedy decoding#

Evaluate my text#

Run Model#

Run Training#

Run Evaluation#

Conclusion#

Docs

Tutorials

Resources