beginner/chatbot_tutorial
Run in Google Colab
Colab
Download Notebook
Notebook
View on GitHub
GitHub
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.
loadLinesAndConversationssplits 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.extractSentencePairsextracts 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_COUNTthreshold using thevoc.trimfunction.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([[ 20, 175, 128, 1781, 85],
[2780, 176, 34, 1090, 17],
[ 26, 24, 14, 183, 9],
[2929, 25, 14, 10, 14],
[ 140, 36, 14, 2, 2],
[1326, 819, 2, 0, 0],
[ 445, 10, 0, 0, 0],
[ 14, 2, 0, 0, 0],
[ 2, 0, 0, 0, 0]])
lengths: tensor([9, 8, 6, 5, 5])
target_variable: tensor([[ 20, 20, 8, 36, 162],
[2780, 85, 17, 17, 10],
[ 884, 105, 531, 284, 2],
[ 14, 37, 5, 14, 0],
[3743, 284, 244, 2, 0],
[ 14, 14, 24, 0, 0],
[ 2, 2, 2, 0, 0]])
mask: tensor([[ True, True, True, True, True],
[ True, True, True, True, True],
[ True, True, True, True, True],
[ True, True, True, True, False],
[ True, True, True, True, False],
[ True, True, True, False, False],
[ True, True, True, False, False]])
max_target_len: 7
Define Models#
Seq2Seq Model#
The brains of our chatbot is a sequence-to-sequence (seq2seq) model. The goal of a seq2seq model is to take a variable-length sequence as an input, and return a variable-length sequence as an output using a fixed-sized model.
Sutskever et al. discovered that by using two separate recurrent neural nets together, we can accomplish this task. One RNN acts as an encoder, which encodes a variable length input sequence to a fixed-length context vector. In theory, this context vector (the final hidden layer of the RNN) will contain semantic information about the query sentence that is input to the bot. The second RNN is a decoder, which takes an input word and the context vector, and returns a guess for the next word in the sequence and a hidden state to use in the next iteration.
Image source: https://jeddy92.github.io/JEddy92.github.io/ts_seq2seq_intro/
Encoder#
The encoder RNN iterates through the input sentence one token (e.g. word) at a time, at each time step outputting an “output” vector and a “hidden state” vector. The hidden state vector is then passed to the next time step, while the output vector is recorded. The encoder transforms the context it saw at each point in the sequence into a set of points in a high-dimensional space, which the decoder will use to generate a meaningful output for the given task.
At the heart of our encoder is a multi-layered Gated Recurrent Unit, invented by Cho et al. in 2014. We will use a bidirectional variant of the GRU, meaning that there are essentially two independent RNNs: one that is fed the input sequence in normal sequential order, and one that is fed the input sequence in reverse order. The outputs of each network are summed at each time step. Using a bidirectional GRU will give us the advantage of encoding both past and future contexts.
Bidirectional RNN:
Image source: https://colah.github.io/posts/2015-09-NN-Types-FP/
Note that an embedding layer is used to encode our word indices in
an arbitrarily sized feature space. For our models, this layer will map
each word to a feature space of size hidden_size. When trained, these
values should encode semantic similarity between similar meaning words.
Finally, if passing a padded batch of sequences to an RNN module, we
must pack and unpack padding around the RNN pass using
nn.utils.rnn.pack_padded_sequence and
nn.utils.rnn.pad_packed_sequence respectively.
Computation Graph:
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 theteacher_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: 8.9793
Iteration: 2; Percent complete: 0.1%; Average loss: 8.8568
Iteration: 3; Percent complete: 0.1%; Average loss: 8.6617
Iteration: 4; Percent complete: 0.1%; Average loss: 8.3368
Iteration: 5; Percent complete: 0.1%; Average loss: 7.9502
Iteration: 6; Percent complete: 0.1%; Average loss: 7.4526
Iteration: 7; Percent complete: 0.2%; Average loss: 6.9682
Iteration: 8; Percent complete: 0.2%; Average loss: 6.7947
Iteration: 9; Percent complete: 0.2%; Average loss: 6.9586
Iteration: 10; Percent complete: 0.2%; Average loss: 6.3289
Iteration: 11; Percent complete: 0.3%; Average loss: 6.2887
Iteration: 12; Percent complete: 0.3%; Average loss: 5.9958
Iteration: 13; Percent complete: 0.3%; Average loss: 5.8433
Iteration: 14; Percent complete: 0.4%; Average loss: 5.7482
Iteration: 15; Percent complete: 0.4%; Average loss: 5.5558
Iteration: 16; Percent complete: 0.4%; Average loss: 5.3294
Iteration: 17; Percent complete: 0.4%; Average loss: 5.3761
Iteration: 18; Percent complete: 0.4%; Average loss: 4.9341
Iteration: 19; Percent complete: 0.5%; Average loss: 5.1392
Iteration: 20; Percent complete: 0.5%; Average loss: 4.9830
Iteration: 21; Percent complete: 0.5%; Average loss: 4.9543
Iteration: 22; Percent complete: 0.5%; Average loss: 4.8795
Iteration: 23; Percent complete: 0.6%; Average loss: 4.8508
Iteration: 24; Percent complete: 0.6%; Average loss: 5.0241
Iteration: 25; Percent complete: 0.6%; Average loss: 5.1123
Iteration: 26; Percent complete: 0.7%; Average loss: 4.7390
Iteration: 27; Percent complete: 0.7%; Average loss: 4.9910
Iteration: 28; Percent complete: 0.7%; Average loss: 4.7957
Iteration: 29; Percent complete: 0.7%; Average loss: 4.8753
Iteration: 30; Percent complete: 0.8%; Average loss: 4.5929
Iteration: 31; Percent complete: 0.8%; Average loss: 4.5588
Iteration: 32; Percent complete: 0.8%; Average loss: 4.8063
Iteration: 33; Percent complete: 0.8%; Average loss: 4.8837
Iteration: 34; Percent complete: 0.9%; Average loss: 4.7502
Iteration: 35; Percent complete: 0.9%; Average loss: 4.8255
Iteration: 36; Percent complete: 0.9%; Average loss: 4.5765
Iteration: 37; Percent complete: 0.9%; Average loss: 4.7595
Iteration: 38; Percent complete: 0.9%; Average loss: 4.5515
Iteration: 39; Percent complete: 1.0%; Average loss: 4.6893
Iteration: 40; Percent complete: 1.0%; Average loss: 4.7205
Iteration: 41; Percent complete: 1.0%; Average loss: 4.9326
Iteration: 42; Percent complete: 1.1%; Average loss: 4.8408
Iteration: 43; Percent complete: 1.1%; Average loss: 4.7292
Iteration: 44; Percent complete: 1.1%; Average loss: 4.5929
Iteration: 45; Percent complete: 1.1%; Average loss: 4.5069
Iteration: 46; Percent complete: 1.1%; Average loss: 4.8185
Iteration: 47; Percent complete: 1.2%; Average loss: 4.7361
Iteration: 48; Percent complete: 1.2%; Average loss: 4.6534
Iteration: 49; Percent complete: 1.2%; Average loss: 4.6587
Iteration: 50; Percent complete: 1.2%; Average loss: 4.6257
Iteration: 51; Percent complete: 1.3%; Average loss: 4.7588
Iteration: 52; Percent complete: 1.3%; Average loss: 4.7821
Iteration: 53; Percent complete: 1.3%; Average loss: 4.6240
Iteration: 54; Percent complete: 1.4%; Average loss: 4.7440
Iteration: 55; Percent complete: 1.4%; Average loss: 4.6143
Iteration: 56; Percent complete: 1.4%; Average loss: 4.6437
Iteration: 57; Percent complete: 1.4%; Average loss: 4.7543
Iteration: 58; Percent complete: 1.5%; Average loss: 4.4656
Iteration: 59; Percent complete: 1.5%; Average loss: 4.5050
Iteration: 60; Percent complete: 1.5%; Average loss: 4.6436
Iteration: 61; Percent complete: 1.5%; Average loss: 4.5598
Iteration: 62; Percent complete: 1.6%; Average loss: 4.5717
Iteration: 63; Percent complete: 1.6%; Average loss: 4.6277
Iteration: 64; Percent complete: 1.6%; Average loss: 4.3085
Iteration: 65; Percent complete: 1.6%; Average loss: 4.4575
Iteration: 66; Percent complete: 1.7%; Average loss: 4.5695
Iteration: 67; Percent complete: 1.7%; Average loss: 4.5638
Iteration: 68; Percent complete: 1.7%; Average loss: 4.6067
Iteration: 69; Percent complete: 1.7%; Average loss: 4.5351
Iteration: 70; Percent complete: 1.8%; Average loss: 4.5548
Iteration: 71; Percent complete: 1.8%; Average loss: 4.4590
Iteration: 72; Percent complete: 1.8%; Average loss: 4.7020
Iteration: 73; Percent complete: 1.8%; Average loss: 4.5959
Iteration: 74; Percent complete: 1.8%; Average loss: 4.5388
Iteration: 75; Percent complete: 1.9%; Average loss: 4.4706
Iteration: 76; Percent complete: 1.9%; Average loss: 4.5673
Iteration: 77; Percent complete: 1.9%; Average loss: 4.4962
Iteration: 78; Percent complete: 1.9%; Average loss: 4.5723
Iteration: 79; Percent complete: 2.0%; Average loss: 4.4733
Iteration: 80; Percent complete: 2.0%; Average loss: 4.6170
Iteration: 81; Percent complete: 2.0%; Average loss: 4.4496
Iteration: 82; Percent complete: 2.1%; Average loss: 4.4590
Iteration: 83; Percent complete: 2.1%; Average loss: 4.2256
Iteration: 84; Percent complete: 2.1%; Average loss: 4.2333
Iteration: 85; Percent complete: 2.1%; Average loss: 4.5472
Iteration: 86; Percent complete: 2.1%; Average loss: 4.3750
Iteration: 87; Percent complete: 2.2%; Average loss: 4.3958
Iteration: 88; Percent complete: 2.2%; Average loss: 4.2631
Iteration: 89; Percent complete: 2.2%; Average loss: 4.3257
Iteration: 90; Percent complete: 2.2%; Average loss: 4.4835
Iteration: 91; Percent complete: 2.3%; Average loss: 4.6432
Iteration: 92; Percent complete: 2.3%; Average loss: 4.3473
Iteration: 93; Percent complete: 2.3%; Average loss: 4.3237
Iteration: 94; Percent complete: 2.4%; Average loss: 4.5255
Iteration: 95; Percent complete: 2.4%; Average loss: 4.3995
Iteration: 96; Percent complete: 2.4%; Average loss: 4.2677
Iteration: 97; Percent complete: 2.4%; Average loss: 4.6993
Iteration: 98; Percent complete: 2.5%; Average loss: 4.5458
Iteration: 99; Percent complete: 2.5%; Average loss: 4.3222
Iteration: 100; Percent complete: 2.5%; Average loss: 4.4231
Iteration: 101; Percent complete: 2.5%; Average loss: 4.3345
Iteration: 102; Percent complete: 2.5%; Average loss: 4.9935
Iteration: 103; Percent complete: 2.6%; Average loss: 4.4011
Iteration: 104; Percent complete: 2.6%; Average loss: 4.3102
Iteration: 105; Percent complete: 2.6%; Average loss: 4.2761
Iteration: 106; Percent complete: 2.6%; Average loss: 4.4608
Iteration: 107; Percent complete: 2.7%; Average loss: 4.4624
Iteration: 108; Percent complete: 2.7%; Average loss: 4.2454
Iteration: 109; Percent complete: 2.7%; Average loss: 4.4358
Iteration: 110; Percent complete: 2.8%; Average loss: 4.4588
Iteration: 111; Percent complete: 2.8%; Average loss: 4.4069
Iteration: 112; Percent complete: 2.8%; Average loss: 4.1899
Iteration: 113; Percent complete: 2.8%; Average loss: 4.3775
Iteration: 114; Percent complete: 2.9%; Average loss: 4.4198
Iteration: 115; Percent complete: 2.9%; Average loss: 4.3813
Iteration: 116; Percent complete: 2.9%; Average loss: 4.2369
Iteration: 117; Percent complete: 2.9%; Average loss: 4.3079
Iteration: 118; Percent complete: 2.9%; Average loss: 4.4152
Iteration: 119; Percent complete: 3.0%; Average loss: 4.4499
Iteration: 120; Percent complete: 3.0%; Average loss: 4.3179
Iteration: 121; Percent complete: 3.0%; Average loss: 4.1039
Iteration: 122; Percent complete: 3.0%; Average loss: 4.4443
Iteration: 123; Percent complete: 3.1%; Average loss: 4.4015
Iteration: 124; Percent complete: 3.1%; Average loss: 4.2493
Iteration: 125; Percent complete: 3.1%; Average loss: 4.2802
Iteration: 126; Percent complete: 3.1%; Average loss: 4.1070
Iteration: 127; Percent complete: 3.2%; Average loss: 4.2487
Iteration: 128; Percent complete: 3.2%; Average loss: 4.4327
Iteration: 129; Percent complete: 3.2%; Average loss: 4.3333
Iteration: 130; Percent complete: 3.2%; Average loss: 4.5188
Iteration: 131; Percent complete: 3.3%; Average loss: 4.2720
Iteration: 132; Percent complete: 3.3%; Average loss: 4.0597
Iteration: 133; Percent complete: 3.3%; Average loss: 4.1483
Iteration: 134; Percent complete: 3.4%; Average loss: 4.3079
Iteration: 135; Percent complete: 3.4%; Average loss: 4.6298
Iteration: 136; Percent complete: 3.4%; Average loss: 4.2333
Iteration: 137; Percent complete: 3.4%; Average loss: 4.1919
Iteration: 138; Percent complete: 3.5%; Average loss: 4.3622
Iteration: 139; Percent complete: 3.5%; Average loss: 4.2518
Iteration: 140; Percent complete: 3.5%; Average loss: 4.2927
Iteration: 141; Percent complete: 3.5%; Average loss: 4.3490
Iteration: 142; Percent complete: 3.5%; Average loss: 4.2068
Iteration: 143; Percent complete: 3.6%; Average loss: 4.2244
Iteration: 144; Percent complete: 3.6%; Average loss: 3.8074
Iteration: 145; Percent complete: 3.6%; Average loss: 4.3538
Iteration: 146; Percent complete: 3.6%; Average loss: 4.1965
Iteration: 147; Percent complete: 3.7%; Average loss: 3.9278
Iteration: 148; Percent complete: 3.7%; Average loss: 4.5257
Iteration: 149; Percent complete: 3.7%; Average loss: 4.1998
Iteration: 150; Percent complete: 3.8%; Average loss: 4.2945
Iteration: 151; Percent complete: 3.8%; Average loss: 4.2827
Iteration: 152; Percent complete: 3.8%; Average loss: 4.1739
Iteration: 153; Percent complete: 3.8%; Average loss: 4.1591
Iteration: 154; Percent complete: 3.9%; Average loss: 4.2239
Iteration: 155; Percent complete: 3.9%; Average loss: 4.3438
Iteration: 156; Percent complete: 3.9%; Average loss: 4.1831
Iteration: 157; Percent complete: 3.9%; Average loss: 4.0644
Iteration: 158; Percent complete: 4.0%; Average loss: 4.0868
Iteration: 159; Percent complete: 4.0%; Average loss: 4.6138
Iteration: 160; Percent complete: 4.0%; Average loss: 4.2954
Iteration: 161; Percent complete: 4.0%; Average loss: 4.3184
Iteration: 162; Percent complete: 4.0%; Average loss: 4.4453
Iteration: 163; Percent complete: 4.1%; Average loss: 4.4176
Iteration: 164; Percent complete: 4.1%; Average loss: 4.0673
Iteration: 165; Percent complete: 4.1%; Average loss: 4.2087
Iteration: 166; Percent complete: 4.2%; Average loss: 4.1547
Iteration: 167; Percent complete: 4.2%; Average loss: 4.2184
Iteration: 168; Percent complete: 4.2%; Average loss: 4.1864
Iteration: 169; Percent complete: 4.2%; Average loss: 3.9857
Iteration: 170; Percent complete: 4.2%; Average loss: 4.1503
Iteration: 171; Percent complete: 4.3%; Average loss: 4.2388
Iteration: 172; Percent complete: 4.3%; Average loss: 4.0073
Iteration: 173; Percent complete: 4.3%; Average loss: 4.4512
Iteration: 174; Percent complete: 4.3%; Average loss: 4.1751
Iteration: 175; Percent complete: 4.4%; Average loss: 3.9909
Iteration: 176; Percent complete: 4.4%; Average loss: 4.2158
Iteration: 177; Percent complete: 4.4%; Average loss: 4.2455
Iteration: 178; Percent complete: 4.5%; Average loss: 4.0307
Iteration: 179; Percent complete: 4.5%; Average loss: 4.2639
Iteration: 180; Percent complete: 4.5%; Average loss: 4.2511
Iteration: 181; Percent complete: 4.5%; Average loss: 4.1811
Iteration: 182; Percent complete: 4.5%; Average loss: 4.3229
Iteration: 183; Percent complete: 4.6%; Average loss: 4.1598
Iteration: 184; Percent complete: 4.6%; Average loss: 4.0079
Iteration: 185; Percent complete: 4.6%; Average loss: 4.0261
Iteration: 186; Percent complete: 4.7%; Average loss: 3.8890
Iteration: 187; Percent complete: 4.7%; Average loss: 4.3580
Iteration: 188; Percent complete: 4.7%; Average loss: 4.1216
Iteration: 189; Percent complete: 4.7%; Average loss: 3.9345
Iteration: 190; Percent complete: 4.8%; Average loss: 4.1196
Iteration: 191; Percent complete: 4.8%; Average loss: 4.0906
Iteration: 192; Percent complete: 4.8%; Average loss: 4.1708
Iteration: 193; Percent complete: 4.8%; Average loss: 4.3057
Iteration: 194; Percent complete: 4.9%; Average loss: 4.1236
Iteration: 195; Percent complete: 4.9%; Average loss: 4.0101
Iteration: 196; Percent complete: 4.9%; Average loss: 3.8809
Iteration: 197; Percent complete: 4.9%; Average loss: 4.1320
Iteration: 198; Percent complete: 5.0%; Average loss: 4.2253
Iteration: 199; Percent complete: 5.0%; Average loss: 4.1915
Iteration: 200; Percent complete: 5.0%; Average loss: 4.0507
Iteration: 201; Percent complete: 5.0%; Average loss: 4.1651
Iteration: 202; Percent complete: 5.1%; Average loss: 4.0147
Iteration: 203; Percent complete: 5.1%; Average loss: 4.2262
Iteration: 204; Percent complete: 5.1%; Average loss: 4.0375
Iteration: 205; Percent complete: 5.1%; Average loss: 4.1981
Iteration: 206; Percent complete: 5.1%; Average loss: 3.8108
Iteration: 207; Percent complete: 5.2%; Average loss: 3.7975
Iteration: 208; Percent complete: 5.2%; Average loss: 3.8946
Iteration: 209; Percent complete: 5.2%; Average loss: 4.0750
Iteration: 210; Percent complete: 5.2%; Average loss: 4.2759
Iteration: 211; Percent complete: 5.3%; Average loss: 4.0671
Iteration: 212; Percent complete: 5.3%; Average loss: 4.0212
Iteration: 213; Percent complete: 5.3%; Average loss: 3.8350
Iteration: 214; Percent complete: 5.3%; Average loss: 4.2220
Iteration: 215; Percent complete: 5.4%; Average loss: 3.8453
Iteration: 216; Percent complete: 5.4%; Average loss: 3.9646
Iteration: 217; Percent complete: 5.4%; Average loss: 4.0085
Iteration: 218; Percent complete: 5.5%; Average loss: 4.1679
Iteration: 219; Percent complete: 5.5%; Average loss: 3.9408
Iteration: 220; Percent complete: 5.5%; Average loss: 4.2120
Iteration: 221; Percent complete: 5.5%; Average loss: 3.8112
Iteration: 222; Percent complete: 5.5%; Average loss: 3.7111
Iteration: 223; Percent complete: 5.6%; Average loss: 3.7570
Iteration: 224; Percent complete: 5.6%; Average loss: 4.3248
Iteration: 225; Percent complete: 5.6%; Average loss: 3.9466
Iteration: 226; Percent complete: 5.7%; Average loss: 4.1263
Iteration: 227; Percent complete: 5.7%; Average loss: 4.0674
Iteration: 228; Percent complete: 5.7%; Average loss: 4.1753
Iteration: 229; Percent complete: 5.7%; Average loss: 3.7138
Iteration: 230; Percent complete: 5.8%; Average loss: 4.2363
Iteration: 231; Percent complete: 5.8%; Average loss: 3.8415
Iteration: 232; Percent complete: 5.8%; Average loss: 3.8713
Iteration: 233; Percent complete: 5.8%; Average loss: 3.8231
Iteration: 234; Percent complete: 5.9%; Average loss: 3.8180
Iteration: 235; Percent complete: 5.9%; Average loss: 3.8245
Iteration: 236; Percent complete: 5.9%; Average loss: 3.9158
Iteration: 237; Percent complete: 5.9%; Average loss: 4.0258
Iteration: 238; Percent complete: 5.9%; Average loss: 4.1798
Iteration: 239; Percent complete: 6.0%; Average loss: 4.0381
Iteration: 240; Percent complete: 6.0%; Average loss: 4.1759
Iteration: 241; Percent complete: 6.0%; Average loss: 4.2849
Iteration: 242; Percent complete: 6.0%; Average loss: 3.8370
Iteration: 243; Percent complete: 6.1%; Average loss: 4.1715
Iteration: 244; Percent complete: 6.1%; Average loss: 3.8356
Iteration: 245; Percent complete: 6.1%; Average loss: 3.9408
Iteration: 246; Percent complete: 6.2%; Average loss: 3.9607
Iteration: 247; Percent complete: 6.2%; Average loss: 4.2124
Iteration: 248; Percent complete: 6.2%; Average loss: 3.8667
Iteration: 249; Percent complete: 6.2%; Average loss: 4.0809
Iteration: 250; Percent complete: 6.2%; Average loss: 4.1673
Iteration: 251; Percent complete: 6.3%; Average loss: 3.8508
Iteration: 252; Percent complete: 6.3%; Average loss: 3.9144
Iteration: 253; Percent complete: 6.3%; Average loss: 3.9199
Iteration: 254; Percent complete: 6.3%; Average loss: 3.9627
Iteration: 255; Percent complete: 6.4%; Average loss: 3.9111
Iteration: 256; Percent complete: 6.4%; Average loss: 4.0458
Iteration: 257; Percent complete: 6.4%; Average loss: 4.1888
Iteration: 258; Percent complete: 6.5%; Average loss: 3.9778
Iteration: 259; Percent complete: 6.5%; Average loss: 4.0642
Iteration: 260; Percent complete: 6.5%; Average loss: 4.1662
Iteration: 261; Percent complete: 6.5%; Average loss: 4.1265
Iteration: 262; Percent complete: 6.6%; Average loss: 4.1303
Iteration: 263; Percent complete: 6.6%; Average loss: 3.9795
Iteration: 264; Percent complete: 6.6%; Average loss: 3.7491
Iteration: 265; Percent complete: 6.6%; Average loss: 3.9645
Iteration: 266; Percent complete: 6.7%; Average loss: 4.0622
Iteration: 267; Percent complete: 6.7%; Average loss: 3.8776
Iteration: 268; Percent complete: 6.7%; Average loss: 4.0844
Iteration: 269; Percent complete: 6.7%; Average loss: 3.9677
Iteration: 270; Percent complete: 6.8%; Average loss: 3.9859
Iteration: 271; Percent complete: 6.8%; Average loss: 4.2091
Iteration: 272; Percent complete: 6.8%; Average loss: 4.1585
Iteration: 273; Percent complete: 6.8%; Average loss: 3.7064
Iteration: 274; Percent complete: 6.9%; Average loss: 3.9300
Iteration: 275; Percent complete: 6.9%; Average loss: 3.8223
Iteration: 276; Percent complete: 6.9%; Average loss: 4.0276
Iteration: 277; Percent complete: 6.9%; Average loss: 3.9353
Iteration: 278; Percent complete: 7.0%; Average loss: 3.7512
Iteration: 279; Percent complete: 7.0%; Average loss: 3.8118
Iteration: 280; Percent complete: 7.0%; Average loss: 3.9216
Iteration: 281; Percent complete: 7.0%; Average loss: 4.1044
Iteration: 282; Percent complete: 7.0%; Average loss: 3.8125
Iteration: 283; Percent complete: 7.1%; Average loss: 3.8701
Iteration: 284; Percent complete: 7.1%; Average loss: 3.8444
Iteration: 285; Percent complete: 7.1%; Average loss: 3.9598
Iteration: 286; Percent complete: 7.1%; Average loss: 3.9859
Iteration: 287; Percent complete: 7.2%; Average loss: 3.7883
Iteration: 288; Percent complete: 7.2%; Average loss: 4.1673
Iteration: 289; Percent complete: 7.2%; Average loss: 4.2887
Iteration: 290; Percent complete: 7.2%; Average loss: 3.7061
Iteration: 291; Percent complete: 7.3%; Average loss: 3.7478
Iteration: 292; Percent complete: 7.3%; Average loss: 3.8040
Iteration: 293; Percent complete: 7.3%; Average loss: 3.9251
Iteration: 294; Percent complete: 7.3%; Average loss: 4.2769
Iteration: 295; Percent complete: 7.4%; Average loss: 3.9809
Iteration: 296; Percent complete: 7.4%; Average loss: 4.0746
Iteration: 297; Percent complete: 7.4%; Average loss: 4.0792
Iteration: 298; Percent complete: 7.4%; Average loss: 3.7982
Iteration: 299; Percent complete: 7.5%; Average loss: 3.8237
Iteration: 300; Percent complete: 7.5%; Average loss: 3.9699
Iteration: 301; Percent complete: 7.5%; Average loss: 3.7004
Iteration: 302; Percent complete: 7.5%; Average loss: 3.8584
Iteration: 303; Percent complete: 7.6%; Average loss: 3.8249
Iteration: 304; Percent complete: 7.6%; Average loss: 3.6528
Iteration: 305; Percent complete: 7.6%; Average loss: 4.0010
Iteration: 306; Percent complete: 7.6%; Average loss: 4.1984
Iteration: 307; Percent complete: 7.7%; Average loss: 3.9106
Iteration: 308; Percent complete: 7.7%; Average loss: 3.9603
Iteration: 309; Percent complete: 7.7%; Average loss: 3.9292
Iteration: 310; Percent complete: 7.8%; Average loss: 3.8664
Iteration: 311; Percent complete: 7.8%; Average loss: 3.9256
Iteration: 312; Percent complete: 7.8%; Average loss: 3.7844
Iteration: 313; Percent complete: 7.8%; Average loss: 3.6784
Iteration: 314; Percent complete: 7.8%; Average loss: 3.8522
Iteration: 315; Percent complete: 7.9%; Average loss: 3.9044
Iteration: 316; Percent complete: 7.9%; Average loss: 3.8611
Iteration: 317; Percent complete: 7.9%; Average loss: 4.2478
Iteration: 318; Percent complete: 8.0%; Average loss: 4.0617
Iteration: 319; Percent complete: 8.0%; Average loss: 3.6319
Iteration: 320; Percent complete: 8.0%; Average loss: 3.9686
Iteration: 321; Percent complete: 8.0%; Average loss: 3.7940
Iteration: 322; Percent complete: 8.1%; Average loss: 3.8485
Iteration: 323; Percent complete: 8.1%; Average loss: 4.0244
Iteration: 324; Percent complete: 8.1%; Average loss: 3.7994
Iteration: 325; Percent complete: 8.1%; Average loss: 3.7378
Iteration: 326; Percent complete: 8.2%; Average loss: 4.0453
Iteration: 327; Percent complete: 8.2%; Average loss: 4.0631
Iteration: 328; Percent complete: 8.2%; Average loss: 4.0902
Iteration: 329; Percent complete: 8.2%; Average loss: 4.2165
Iteration: 330; Percent complete: 8.2%; Average loss: 4.0198
Iteration: 331; Percent complete: 8.3%; Average loss: 3.8711
Iteration: 332; Percent complete: 8.3%; Average loss: 3.9017
Iteration: 333; Percent complete: 8.3%; Average loss: 4.0250
Iteration: 334; Percent complete: 8.3%; Average loss: 3.7445
Iteration: 335; Percent complete: 8.4%; Average loss: 4.1287
Iteration: 336; Percent complete: 8.4%; Average loss: 3.8333
Iteration: 337; Percent complete: 8.4%; Average loss: 3.8567
Iteration: 338; Percent complete: 8.5%; Average loss: 4.0629
Iteration: 339; Percent complete: 8.5%; Average loss: 3.8852
Iteration: 340; Percent complete: 8.5%; Average loss: 4.2063
Iteration: 341; Percent complete: 8.5%; Average loss: 3.6772
Iteration: 342; Percent complete: 8.6%; Average loss: 4.0703
Iteration: 343; Percent complete: 8.6%; Average loss: 3.8006
Iteration: 344; Percent complete: 8.6%; Average loss: 4.1307
Iteration: 345; Percent complete: 8.6%; Average loss: 3.7745
Iteration: 346; Percent complete: 8.6%; Average loss: 4.0163
Iteration: 347; Percent complete: 8.7%; Average loss: 3.7888
Iteration: 348; Percent complete: 8.7%; Average loss: 3.9892
Iteration: 349; Percent complete: 8.7%; Average loss: 3.8558
Iteration: 350; Percent complete: 8.8%; Average loss: 3.8063
Iteration: 351; Percent complete: 8.8%; Average loss: 3.7121
Iteration: 352; Percent complete: 8.8%; Average loss: 3.7181
Iteration: 353; Percent complete: 8.8%; Average loss: 3.8750
Iteration: 354; Percent complete: 8.8%; Average loss: 3.9782
Iteration: 355; Percent complete: 8.9%; Average loss: 3.9273
Iteration: 356; Percent complete: 8.9%; Average loss: 3.9664
Iteration: 357; Percent complete: 8.9%; Average loss: 3.7055
Iteration: 358; Percent complete: 8.9%; Average loss: 3.9640
Iteration: 359; Percent complete: 9.0%; Average loss: 4.1520
Iteration: 360; Percent complete: 9.0%; Average loss: 3.9085
Iteration: 361; Percent complete: 9.0%; Average loss: 4.0591
Iteration: 362; Percent complete: 9.0%; Average loss: 3.5045
Iteration: 363; Percent complete: 9.1%; Average loss: 3.5678
Iteration: 364; Percent complete: 9.1%; Average loss: 3.6562
Iteration: 365; Percent complete: 9.1%; Average loss: 3.5123
Iteration: 366; Percent complete: 9.2%; Average loss: 3.8067
Iteration: 367; Percent complete: 9.2%; Average loss: 3.7951
Iteration: 368; Percent complete: 9.2%; Average loss: 3.5521
Iteration: 369; Percent complete: 9.2%; Average loss: 4.0801
Iteration: 370; Percent complete: 9.2%; Average loss: 3.7967
Iteration: 371; Percent complete: 9.3%; Average loss: 3.9588
Iteration: 372; Percent complete: 9.3%; Average loss: 3.8304
Iteration: 373; Percent complete: 9.3%; Average loss: 3.9148
Iteration: 374; Percent complete: 9.3%; Average loss: 3.5831
Iteration: 375; Percent complete: 9.4%; Average loss: 3.9543
Iteration: 376; Percent complete: 9.4%; Average loss: 3.8451
Iteration: 377; Percent complete: 9.4%; Average loss: 3.5942
Iteration: 378; Percent complete: 9.4%; Average loss: 3.7539
Iteration: 379; Percent complete: 9.5%; Average loss: 3.6899
Iteration: 380; Percent complete: 9.5%; Average loss: 4.1826
Iteration: 381; Percent complete: 9.5%; Average loss: 3.7325
Iteration: 382; Percent complete: 9.6%; Average loss: 3.6135
Iteration: 383; Percent complete: 9.6%; Average loss: 3.7132
Iteration: 384; Percent complete: 9.6%; Average loss: 3.6840
Iteration: 385; Percent complete: 9.6%; Average loss: 3.9021
Iteration: 386; Percent complete: 9.7%; Average loss: 3.6047
Iteration: 387; Percent complete: 9.7%; Average loss: 3.8078
Iteration: 388; Percent complete: 9.7%; Average loss: 4.0739
Iteration: 389; Percent complete: 9.7%; Average loss: 3.6689
Iteration: 390; Percent complete: 9.8%; Average loss: 3.6585
Iteration: 391; Percent complete: 9.8%; Average loss: 3.9000
Iteration: 392; Percent complete: 9.8%; Average loss: 3.8900
Iteration: 393; Percent complete: 9.8%; Average loss: 3.4849
Iteration: 394; Percent complete: 9.8%; Average loss: 3.5329
Iteration: 395; Percent complete: 9.9%; Average loss: 3.9817
Iteration: 396; Percent complete: 9.9%; Average loss: 3.9054
Iteration: 397; Percent complete: 9.9%; Average loss: 3.5847
Iteration: 398; Percent complete: 10.0%; Average loss: 3.6555
Iteration: 399; Percent complete: 10.0%; Average loss: 3.6527
Iteration: 400; Percent complete: 10.0%; Average loss: 3.6535
Iteration: 401; Percent complete: 10.0%; Average loss: 3.9709
Iteration: 402; Percent complete: 10.1%; Average loss: 3.7845
Iteration: 403; Percent complete: 10.1%; Average loss: 4.0464
Iteration: 404; Percent complete: 10.1%; Average loss: 3.3105
Iteration: 405; Percent complete: 10.1%; Average loss: 4.0267
Iteration: 406; Percent complete: 10.2%; Average loss: 3.6483
Iteration: 407; Percent complete: 10.2%; Average loss: 3.7555
Iteration: 408; Percent complete: 10.2%; Average loss: 3.6918
Iteration: 409; Percent complete: 10.2%; Average loss: 3.7228
Iteration: 410; Percent complete: 10.2%; Average loss: 3.8008
Iteration: 411; Percent complete: 10.3%; Average loss: 3.8273
Iteration: 412; Percent complete: 10.3%; Average loss: 3.9284
Iteration: 413; Percent complete: 10.3%; Average loss: 3.5428
Iteration: 414; Percent complete: 10.3%; Average loss: 3.5216
Iteration: 415; Percent complete: 10.4%; Average loss: 3.7657
Iteration: 416; Percent complete: 10.4%; Average loss: 3.8094
Iteration: 417; Percent complete: 10.4%; Average loss: 3.8265
Iteration: 418; Percent complete: 10.4%; Average loss: 3.7385
Iteration: 419; Percent complete: 10.5%; Average loss: 3.8707
Iteration: 420; Percent complete: 10.5%; Average loss: 3.8395
Iteration: 421; Percent complete: 10.5%; Average loss: 3.9639
Iteration: 422; Percent complete: 10.5%; Average loss: 3.6601
Iteration: 423; Percent complete: 10.6%; Average loss: 3.9243
Iteration: 424; Percent complete: 10.6%; Average loss: 3.7299
Iteration: 425; Percent complete: 10.6%; Average loss: 3.8132
Iteration: 426; Percent complete: 10.7%; Average loss: 3.7359
Iteration: 427; Percent complete: 10.7%; Average loss: 3.5591
Iteration: 428; Percent complete: 10.7%; Average loss: 3.7797
Iteration: 429; Percent complete: 10.7%; Average loss: 3.7842
Iteration: 430; Percent complete: 10.8%; Average loss: 3.7655
Iteration: 431; Percent complete: 10.8%; Average loss: 3.7746
Iteration: 432; Percent complete: 10.8%; Average loss: 3.9083
Iteration: 433; Percent complete: 10.8%; Average loss: 3.8230
Iteration: 434; Percent complete: 10.8%; Average loss: 3.6959
Iteration: 435; Percent complete: 10.9%; Average loss: 3.6419
Iteration: 436; Percent complete: 10.9%; Average loss: 3.9244
Iteration: 437; Percent complete: 10.9%; Average loss: 3.8528
Iteration: 438; Percent complete: 10.9%; Average loss: 4.1106
Iteration: 439; Percent complete: 11.0%; Average loss: 4.3204
Iteration: 440; Percent complete: 11.0%; Average loss: 3.6270
Iteration: 441; Percent complete: 11.0%; Average loss: 3.8246
Iteration: 442; Percent complete: 11.1%; Average loss: 3.4898
Iteration: 443; Percent complete: 11.1%; Average loss: 3.8216
Iteration: 444; Percent complete: 11.1%; Average loss: 3.9267
Iteration: 445; Percent complete: 11.1%; Average loss: 3.7313
Iteration: 446; Percent complete: 11.2%; Average loss: 3.6117
Iteration: 447; Percent complete: 11.2%; Average loss: 3.8009
Iteration: 448; Percent complete: 11.2%; Average loss: 3.8050
Iteration: 449; Percent complete: 11.2%; Average loss: 3.6527
Iteration: 450; Percent complete: 11.2%; Average loss: 3.6076
Iteration: 451; Percent complete: 11.3%; Average loss: 3.5856
Iteration: 452; Percent complete: 11.3%; Average loss: 3.9611
Iteration: 453; Percent complete: 11.3%; Average loss: 3.6902
Iteration: 454; Percent complete: 11.3%; Average loss: 3.4954
Iteration: 455; Percent complete: 11.4%; Average loss: 3.4401
Iteration: 456; Percent complete: 11.4%; Average loss: 3.7879
Iteration: 457; Percent complete: 11.4%; Average loss: 3.7849
Iteration: 458; Percent complete: 11.5%; Average loss: 3.6108
Iteration: 459; Percent complete: 11.5%; Average loss: 3.8619
Iteration: 460; Percent complete: 11.5%; Average loss: 3.5184
Iteration: 461; Percent complete: 11.5%; Average loss: 3.7529
Iteration: 462; Percent complete: 11.6%; Average loss: 3.5440
Iteration: 463; Percent complete: 11.6%; Average loss: 3.6282
Iteration: 464; Percent complete: 11.6%; Average loss: 3.7979
Iteration: 465; Percent complete: 11.6%; Average loss: 3.9137
Iteration: 466; Percent complete: 11.7%; Average loss: 3.8731
Iteration: 467; Percent complete: 11.7%; Average loss: 3.9886
Iteration: 468; Percent complete: 11.7%; Average loss: 3.6798
Iteration: 469; Percent complete: 11.7%; Average loss: 3.9654
Iteration: 470; Percent complete: 11.8%; Average loss: 3.5193
Iteration: 471; Percent complete: 11.8%; Average loss: 3.9005
Iteration: 472; Percent complete: 11.8%; Average loss: 3.6216
Iteration: 473; Percent complete: 11.8%; Average loss: 3.7492
Iteration: 474; Percent complete: 11.8%; Average loss: 3.6896
Iteration: 475; Percent complete: 11.9%; Average loss: 3.7769
Iteration: 476; Percent complete: 11.9%; Average loss: 4.0197
Iteration: 477; Percent complete: 11.9%; Average loss: 3.8809
Iteration: 478; Percent complete: 11.9%; Average loss: 3.8014
Iteration: 479; Percent complete: 12.0%; Average loss: 3.7307
Iteration: 480; Percent complete: 12.0%; Average loss: 3.8227
Iteration: 481; Percent complete: 12.0%; Average loss: 3.8204
Iteration: 482; Percent complete: 12.0%; Average loss: 3.9664
Iteration: 483; Percent complete: 12.1%; Average loss: 3.6478
Iteration: 484; Percent complete: 12.1%; Average loss: 3.6978
Iteration: 485; Percent complete: 12.1%; Average loss: 3.8238
Iteration: 486; Percent complete: 12.2%; Average loss: 3.8359
Iteration: 487; Percent complete: 12.2%; Average loss: 3.7725
Iteration: 488; Percent complete: 12.2%; Average loss: 3.8660
Iteration: 489; Percent complete: 12.2%; Average loss: 3.7343
Iteration: 490; Percent complete: 12.2%; Average loss: 3.6687
Iteration: 491; Percent complete: 12.3%; Average loss: 3.8383
Iteration: 492; Percent complete: 12.3%; Average loss: 3.7823
Iteration: 493; Percent complete: 12.3%; Average loss: 3.7854
Iteration: 494; Percent complete: 12.3%; Average loss: 3.8764
Iteration: 495; Percent complete: 12.4%; Average loss: 3.5627
Iteration: 496; Percent complete: 12.4%; Average loss: 3.9098
Iteration: 497; Percent complete: 12.4%; Average loss: 3.7522
Iteration: 498; Percent complete: 12.4%; Average loss: 3.9762
Iteration: 499; Percent complete: 12.5%; Average loss: 3.8971
Iteration: 500; Percent complete: 12.5%; Average loss: 3.8443
Iteration: 501; Percent complete: 12.5%; Average loss: 3.8578
Iteration: 502; Percent complete: 12.6%; Average loss: 3.6785
Iteration: 503; Percent complete: 12.6%; Average loss: 3.8431
Iteration: 504; Percent complete: 12.6%; Average loss: 3.9675
Iteration: 505; Percent complete: 12.6%; Average loss: 3.5606
Iteration: 506; Percent complete: 12.7%; Average loss: 3.6555
Iteration: 507; Percent complete: 12.7%; Average loss: 3.5853
Iteration: 508; Percent complete: 12.7%; Average loss: 3.7845
Iteration: 509; Percent complete: 12.7%; Average loss: 3.6129
Iteration: 510; Percent complete: 12.8%; Average loss: 3.5707
Iteration: 511; Percent complete: 12.8%; Average loss: 3.7428
Iteration: 512; Percent complete: 12.8%; Average loss: 3.9342
Iteration: 513; Percent complete: 12.8%; Average loss: 3.7768
Iteration: 514; Percent complete: 12.8%; Average loss: 3.4731
Iteration: 515; Percent complete: 12.9%; Average loss: 4.0041
Iteration: 516; Percent complete: 12.9%; Average loss: 3.8659
Iteration: 517; Percent complete: 12.9%; Average loss: 3.6929
Iteration: 518; Percent complete: 13.0%; Average loss: 3.7852
Iteration: 519; Percent complete: 13.0%; Average loss: 3.6383
Iteration: 520; Percent complete: 13.0%; Average loss: 3.7835
Iteration: 521; Percent complete: 13.0%; Average loss: 3.3783
Iteration: 522; Percent complete: 13.1%; Average loss: 3.6430
Iteration: 523; Percent complete: 13.1%; Average loss: 3.6352
Iteration: 524; Percent complete: 13.1%; Average loss: 3.8019
Iteration: 525; Percent complete: 13.1%; Average loss: 3.5566
Iteration: 526; Percent complete: 13.2%; Average loss: 3.7358
Iteration: 527; Percent complete: 13.2%; Average loss: 3.7298
Iteration: 528; Percent complete: 13.2%; Average loss: 3.7052
Iteration: 529; Percent complete: 13.2%; Average loss: 3.8192
Iteration: 530; Percent complete: 13.2%; Average loss: 3.6672
Iteration: 531; Percent complete: 13.3%; Average loss: 3.8825
Iteration: 532; Percent complete: 13.3%; Average loss: 3.7940
Iteration: 533; Percent complete: 13.3%; Average loss: 3.8047
Iteration: 534; Percent complete: 13.4%; Average loss: 3.5203
Iteration: 535; Percent complete: 13.4%; Average loss: 3.7640
Iteration: 536; Percent complete: 13.4%; Average loss: 3.4629
Iteration: 537; Percent complete: 13.4%; Average loss: 3.6431
Iteration: 538; Percent complete: 13.5%; Average loss: 3.6037
Iteration: 539; Percent complete: 13.5%; Average loss: 3.8311
Iteration: 540; Percent complete: 13.5%; Average loss: 3.7389
Iteration: 541; Percent complete: 13.5%; Average loss: 3.7302
Iteration: 542; Percent complete: 13.6%; Average loss: 3.4959
Iteration: 543; Percent complete: 13.6%; Average loss: 3.4293
Iteration: 544; Percent complete: 13.6%; Average loss: 3.6159
Iteration: 545; Percent complete: 13.6%; Average loss: 3.4428
Iteration: 546; Percent complete: 13.7%; Average loss: 3.4309
Iteration: 547; Percent complete: 13.7%; Average loss: 3.6730
Iteration: 548; Percent complete: 13.7%; Average loss: 3.5269
Iteration: 549; Percent complete: 13.7%; Average loss: 3.3286
Iteration: 550; Percent complete: 13.8%; Average loss: 3.6839
Iteration: 551; Percent complete: 13.8%; Average loss: 3.6421
Iteration: 552; Percent complete: 13.8%; Average loss: 3.7144
Iteration: 553; Percent complete: 13.8%; Average loss: 3.8568
Iteration: 554; Percent complete: 13.9%; Average loss: 3.7252
Iteration: 555; Percent complete: 13.9%; Average loss: 3.7966
Iteration: 556; Percent complete: 13.9%; Average loss: 3.7315
Iteration: 557; Percent complete: 13.9%; Average loss: 3.5817
Iteration: 558; Percent complete: 14.0%; Average loss: 3.8149
Iteration: 559; Percent complete: 14.0%; Average loss: 3.5735
Iteration: 560; Percent complete: 14.0%; Average loss: 3.9055
Iteration: 561; Percent complete: 14.0%; Average loss: 3.9445
Iteration: 562; Percent complete: 14.1%; Average loss: 4.0037
Iteration: 563; Percent complete: 14.1%; Average loss: 3.7483
Iteration: 564; Percent complete: 14.1%; Average loss: 3.5932
Iteration: 565; Percent complete: 14.1%; Average loss: 3.6953
Iteration: 566; Percent complete: 14.1%; Average loss: 3.6612
Iteration: 567; Percent complete: 14.2%; Average loss: 3.6411
Iteration: 568; Percent complete: 14.2%; Average loss: 3.7749
Iteration: 569; Percent complete: 14.2%; Average loss: 3.4676
Iteration: 570; Percent complete: 14.2%; Average loss: 3.5714
Iteration: 571; Percent complete: 14.3%; Average loss: 3.7008
Iteration: 572; Percent complete: 14.3%; Average loss: 3.7485
Iteration: 573; Percent complete: 14.3%; Average loss: 3.6396
Iteration: 574; Percent complete: 14.3%; Average loss: 3.7002
Iteration: 575; Percent complete: 14.4%; Average loss: 3.7428
Iteration: 576; Percent complete: 14.4%; Average loss: 3.6196
Iteration: 577; Percent complete: 14.4%; Average loss: 3.4621
Iteration: 578; Percent complete: 14.4%; Average loss: 3.4717
Iteration: 579; Percent complete: 14.5%; Average loss: 3.5380
Iteration: 580; Percent complete: 14.5%; Average loss: 3.8051
Iteration: 581; Percent complete: 14.5%; Average loss: 3.6499
Iteration: 582; Percent complete: 14.5%; Average loss: 3.5395
Iteration: 583; Percent complete: 14.6%; Average loss: 3.7646
Iteration: 584; Percent complete: 14.6%; Average loss: 3.3206
Iteration: 585; Percent complete: 14.6%; Average loss: 3.8617
Iteration: 586; Percent complete: 14.6%; Average loss: 3.8347
Iteration: 587; Percent complete: 14.7%; Average loss: 3.6101
Iteration: 588; Percent complete: 14.7%; Average loss: 4.1218
Iteration: 589; Percent complete: 14.7%; Average loss: 3.8254
Iteration: 590; Percent complete: 14.8%; Average loss: 3.5735
Iteration: 591; Percent complete: 14.8%; Average loss: 3.8031
Iteration: 592; Percent complete: 14.8%; Average loss: 3.9112
Iteration: 593; Percent complete: 14.8%; Average loss: 3.7947
Iteration: 594; Percent complete: 14.8%; Average loss: 3.6583
Iteration: 595; Percent complete: 14.9%; Average loss: 3.6229
Iteration: 596; Percent complete: 14.9%; Average loss: 3.8647
Iteration: 597; Percent complete: 14.9%; Average loss: 3.7426
Iteration: 598; Percent complete: 14.9%; Average loss: 3.6811
Iteration: 599; Percent complete: 15.0%; Average loss: 3.5621
Iteration: 600; Percent complete: 15.0%; Average loss: 3.6954
Iteration: 601; Percent complete: 15.0%; Average loss: 3.6410
Iteration: 602; Percent complete: 15.0%; Average loss: 3.7006
Iteration: 603; Percent complete: 15.1%; Average loss: 3.6936
Iteration: 604; Percent complete: 15.1%; Average loss: 3.5890
Iteration: 605; Percent complete: 15.1%; Average loss: 3.6833
Iteration: 606; Percent complete: 15.2%; Average loss: 3.7346
Iteration: 607; Percent complete: 15.2%; Average loss: 3.5438
Iteration: 608; Percent complete: 15.2%; Average loss: 3.5988
Iteration: 609; Percent complete: 15.2%; Average loss: 3.4914
Iteration: 610; Percent complete: 15.2%; Average loss: 3.7328
Iteration: 611; Percent complete: 15.3%; Average loss: 3.6886
Iteration: 612; Percent complete: 15.3%; Average loss: 3.5011
Iteration: 613; Percent complete: 15.3%; Average loss: 3.5905
Iteration: 614; Percent complete: 15.3%; Average loss: 3.3449
Iteration: 615; Percent complete: 15.4%; Average loss: 3.6333
Iteration: 616; Percent complete: 15.4%; Average loss: 3.7445
Iteration: 617; Percent complete: 15.4%; Average loss: 3.6038
Iteration: 618; Percent complete: 15.4%; Average loss: 3.5699
Iteration: 619; Percent complete: 15.5%; Average loss: 3.6859
Iteration: 620; Percent complete: 15.5%; Average loss: 3.7818
Iteration: 621; Percent complete: 15.5%; Average loss: 3.6227
Iteration: 622; Percent complete: 15.6%; Average loss: 3.8519
Iteration: 623; Percent complete: 15.6%; Average loss: 3.6132
Iteration: 624; Percent complete: 15.6%; Average loss: 3.5021
Iteration: 625; Percent complete: 15.6%; Average loss: 3.5146
Iteration: 626; Percent complete: 15.7%; Average loss: 3.7911
Iteration: 627; Percent complete: 15.7%; Average loss: 3.5778
Iteration: 628; Percent complete: 15.7%; Average loss: 3.5418
Iteration: 629; Percent complete: 15.7%; Average loss: 3.5003
Iteration: 630; Percent complete: 15.8%; Average loss: 3.7390
Iteration: 631; Percent complete: 15.8%; Average loss: 3.6259
Iteration: 632; Percent complete: 15.8%; Average loss: 3.4520
Iteration: 633; Percent complete: 15.8%; Average loss: 3.9344
Iteration: 634; Percent complete: 15.8%; Average loss: 3.7931
Iteration: 635; Percent complete: 15.9%; Average loss: 3.6989
Iteration: 636; Percent complete: 15.9%; Average loss: 3.6441
Iteration: 637; Percent complete: 15.9%; Average loss: 3.6639
Iteration: 638; Percent complete: 16.0%; Average loss: 3.7482
Iteration: 639; Percent complete: 16.0%; Average loss: 3.6005
Iteration: 640; Percent complete: 16.0%; Average loss: 3.7773
Iteration: 641; Percent complete: 16.0%; Average loss: 3.8785
Iteration: 642; Percent complete: 16.1%; Average loss: 3.6223
Iteration: 643; Percent complete: 16.1%; Average loss: 3.5432
Iteration: 644; Percent complete: 16.1%; Average loss: 3.5701
Iteration: 645; Percent complete: 16.1%; Average loss: 3.6383
Iteration: 646; Percent complete: 16.2%; Average loss: 3.4799
Iteration: 647; Percent complete: 16.2%; Average loss: 3.7404
Iteration: 648; Percent complete: 16.2%; Average loss: 3.7907
Iteration: 649; Percent complete: 16.2%; Average loss: 3.7443
Iteration: 650; Percent complete: 16.2%; Average loss: 3.6425
Iteration: 651; Percent complete: 16.3%; Average loss: 3.6233
Iteration: 652; Percent complete: 16.3%; Average loss: 3.5370
Iteration: 653; Percent complete: 16.3%; Average loss: 3.6429
Iteration: 654; Percent complete: 16.4%; Average loss: 3.5076
Iteration: 655; Percent complete: 16.4%; Average loss: 3.9320
Iteration: 656; Percent complete: 16.4%; Average loss: 3.5847
Iteration: 657; Percent complete: 16.4%; Average loss: 3.5279
Iteration: 658; Percent complete: 16.4%; Average loss: 3.2586
Iteration: 659; Percent complete: 16.5%; Average loss: 3.7477
Iteration: 660; Percent complete: 16.5%; Average loss: 3.8719
Iteration: 661; Percent complete: 16.5%; Average loss: 3.6519
Iteration: 662; Percent complete: 16.6%; Average loss: 3.5084
Iteration: 663; Percent complete: 16.6%; Average loss: 3.4642
Iteration: 664; Percent complete: 16.6%; Average loss: 3.6035
Iteration: 665; Percent complete: 16.6%; Average loss: 3.7895
Iteration: 666; Percent complete: 16.7%; Average loss: 3.6341
Iteration: 667; Percent complete: 16.7%; Average loss: 3.6581
Iteration: 668; Percent complete: 16.7%; Average loss: 3.6516
Iteration: 669; Percent complete: 16.7%; Average loss: 3.5813
Iteration: 670; Percent complete: 16.8%; Average loss: 3.4644
Iteration: 671; Percent complete: 16.8%; Average loss: 3.4962
Iteration: 672; Percent complete: 16.8%; Average loss: 3.4254
Iteration: 673; Percent complete: 16.8%; Average loss: 3.5626
Iteration: 674; Percent complete: 16.9%; Average loss: 3.4555
Iteration: 675; Percent complete: 16.9%; Average loss: 3.7209
Iteration: 676; Percent complete: 16.9%; Average loss: 3.6550
Iteration: 677; Percent complete: 16.9%; Average loss: 3.3962
Iteration: 678; Percent complete: 17.0%; Average loss: 3.3630
Iteration: 679; Percent complete: 17.0%; Average loss: 3.7879
Iteration: 680; Percent complete: 17.0%; Average loss: 3.5917
Iteration: 681; Percent complete: 17.0%; Average loss: 3.5587
Iteration: 682; Percent complete: 17.1%; Average loss: 3.7298
Iteration: 683; Percent complete: 17.1%; Average loss: 3.5889
Iteration: 684; Percent complete: 17.1%; Average loss: 3.7172
Iteration: 685; Percent complete: 17.1%; Average loss: 3.6941
Iteration: 686; Percent complete: 17.2%; Average loss: 3.8654
Iteration: 687; Percent complete: 17.2%; Average loss: 3.5856
Iteration: 688; Percent complete: 17.2%; Average loss: 3.6782
Iteration: 689; Percent complete: 17.2%; Average loss: 3.6838
Iteration: 690; Percent complete: 17.2%; Average loss: 3.6500
Iteration: 691; Percent complete: 17.3%; Average loss: 3.8943
Iteration: 692; Percent complete: 17.3%; Average loss: 3.4856
Iteration: 693; Percent complete: 17.3%; Average loss: 3.4030
Iteration: 694; Percent complete: 17.3%; Average loss: 3.7832
Iteration: 695; Percent complete: 17.4%; Average loss: 3.8341
Iteration: 696; Percent complete: 17.4%; Average loss: 3.4688
Iteration: 697; Percent complete: 17.4%; Average loss: 3.5889
Iteration: 698; Percent complete: 17.4%; Average loss: 3.5711
Iteration: 699; Percent complete: 17.5%; Average loss: 3.2315
Iteration: 700; Percent complete: 17.5%; Average loss: 3.4214
Iteration: 701; Percent complete: 17.5%; Average loss: 3.8140
Iteration: 702; Percent complete: 17.5%; Average loss: 3.4216
Iteration: 703; Percent complete: 17.6%; Average loss: 3.5473
Iteration: 704; Percent complete: 17.6%; Average loss: 3.4563
Iteration: 705; Percent complete: 17.6%; Average loss: 3.7022
Iteration: 706; Percent complete: 17.6%; Average loss: 3.6510
Iteration: 707; Percent complete: 17.7%; Average loss: 3.7713
Iteration: 708; Percent complete: 17.7%; Average loss: 3.6983
Iteration: 709; Percent complete: 17.7%; Average loss: 3.6630
Iteration: 710; Percent complete: 17.8%; Average loss: 3.6703
Iteration: 711; Percent complete: 17.8%; Average loss: 3.8029
Iteration: 712; Percent complete: 17.8%; Average loss: 3.6889
Iteration: 713; Percent complete: 17.8%; Average loss: 3.6391
Iteration: 714; Percent complete: 17.8%; Average loss: 3.4117
Iteration: 715; Percent complete: 17.9%; Average loss: 3.4896
Iteration: 716; Percent complete: 17.9%; Average loss: 3.2530
Iteration: 717; Percent complete: 17.9%; Average loss: 3.6130
Iteration: 718; Percent complete: 17.9%; Average loss: 3.5898
Iteration: 719; Percent complete: 18.0%; Average loss: 3.8261
Iteration: 720; Percent complete: 18.0%; Average loss: 3.6366
Iteration: 721; Percent complete: 18.0%; Average loss: 3.7325
Iteration: 722; Percent complete: 18.1%; Average loss: 3.4161
Iteration: 723; Percent complete: 18.1%; Average loss: 3.5767
Iteration: 724; Percent complete: 18.1%; Average loss: 3.5353
Iteration: 725; Percent complete: 18.1%; Average loss: 3.5944
Iteration: 726; Percent complete: 18.1%; Average loss: 3.6324
Iteration: 727; Percent complete: 18.2%; Average loss: 3.6242
Iteration: 728; Percent complete: 18.2%; Average loss: 3.6760
Iteration: 729; Percent complete: 18.2%; Average loss: 3.5795
Iteration: 730; Percent complete: 18.2%; Average loss: 3.8486
Iteration: 731; Percent complete: 18.3%; Average loss: 3.9450
Iteration: 732; Percent complete: 18.3%; Average loss: 3.5197
Iteration: 733; Percent complete: 18.3%; Average loss: 3.2764
Iteration: 734; Percent complete: 18.4%; Average loss: 3.5320
Iteration: 735; Percent complete: 18.4%; Average loss: 3.5938
Iteration: 736; Percent complete: 18.4%; Average loss: 3.5662
Iteration: 737; Percent complete: 18.4%; Average loss: 3.4127
Iteration: 738; Percent complete: 18.4%; Average loss: 3.6317
Iteration: 739; Percent complete: 18.5%; Average loss: 3.4564
Iteration: 740; Percent complete: 18.5%; Average loss: 3.6655
Iteration: 741; Percent complete: 18.5%; Average loss: 3.4565
Iteration: 742; Percent complete: 18.6%; Average loss: 3.5849
Iteration: 743; Percent complete: 18.6%; Average loss: 3.4086
Iteration: 744; Percent complete: 18.6%; Average loss: 3.8317
Iteration: 745; Percent complete: 18.6%; Average loss: 3.4758
Iteration: 746; Percent complete: 18.6%; Average loss: 3.6426
Iteration: 747; Percent complete: 18.7%; Average loss: 3.4438
Iteration: 748; Percent complete: 18.7%; Average loss: 3.7176
Iteration: 749; Percent complete: 18.7%; Average loss: 3.3363
Iteration: 750; Percent complete: 18.8%; Average loss: 3.7838
Iteration: 751; Percent complete: 18.8%; Average loss: 3.3575
Iteration: 752; Percent complete: 18.8%; Average loss: 3.3846
Iteration: 753; Percent complete: 18.8%; Average loss: 3.6147
Iteration: 754; Percent complete: 18.9%; Average loss: 3.4214
Iteration: 755; Percent complete: 18.9%; Average loss: 3.4977
Iteration: 756; Percent complete: 18.9%; Average loss: 3.4851
Iteration: 757; Percent complete: 18.9%; Average loss: 3.7762
Iteration: 758; Percent complete: 18.9%; Average loss: 3.5665
Iteration: 759; Percent complete: 19.0%; Average loss: 3.6770
Iteration: 760; Percent complete: 19.0%; Average loss: 3.4211
Iteration: 761; Percent complete: 19.0%; Average loss: 3.4705
Iteration: 762; Percent complete: 19.1%; Average loss: 3.5862
Iteration: 763; Percent complete: 19.1%; Average loss: 3.5156
Iteration: 764; Percent complete: 19.1%; Average loss: 3.5882
Iteration: 765; Percent complete: 19.1%; Average loss: 3.6118
Iteration: 766; Percent complete: 19.1%; Average loss: 3.6642
Iteration: 767; Percent complete: 19.2%; Average loss: 3.5478
Iteration: 768; Percent complete: 19.2%; Average loss: 3.6393
Iteration: 769; Percent complete: 19.2%; Average loss: 3.4588
Iteration: 770; Percent complete: 19.2%; Average loss: 3.5446
Iteration: 771; Percent complete: 19.3%; Average loss: 3.3095
Iteration: 772; Percent complete: 19.3%; Average loss: 3.4084
Iteration: 773; Percent complete: 19.3%; Average loss: 3.7833
Iteration: 774; Percent complete: 19.4%; Average loss: 3.3703
Iteration: 775; Percent complete: 19.4%; Average loss: 3.6305
Iteration: 776; Percent complete: 19.4%; Average loss: 3.2662
Iteration: 777; Percent complete: 19.4%; Average loss: 3.7274
Iteration: 778; Percent complete: 19.4%; Average loss: 3.4566
Iteration: 779; Percent complete: 19.5%; Average loss: 3.5080
Iteration: 780; Percent complete: 19.5%; Average loss: 3.3430
Iteration: 781; Percent complete: 19.5%; Average loss: 3.9381
Iteration: 782; Percent complete: 19.6%; Average loss: 3.5992
Iteration: 783; Percent complete: 19.6%; Average loss: 3.4590
Iteration: 784; Percent complete: 19.6%; Average loss: 3.7020
Iteration: 785; Percent complete: 19.6%; Average loss: 3.5820
Iteration: 786; Percent complete: 19.7%; Average loss: 3.7113
Iteration: 787; Percent complete: 19.7%; Average loss: 3.4725
Iteration: 788; Percent complete: 19.7%; Average loss: 3.7242
Iteration: 789; Percent complete: 19.7%; Average loss: 3.4253
Iteration: 790; Percent complete: 19.8%; Average loss: 3.5673
Iteration: 791; Percent complete: 19.8%; Average loss: 3.3981
Iteration: 792; Percent complete: 19.8%; Average loss: 3.4866
Iteration: 793; Percent complete: 19.8%; Average loss: 3.4433
Iteration: 794; Percent complete: 19.9%; Average loss: 3.4497
Iteration: 795; Percent complete: 19.9%; Average loss: 3.5450
Iteration: 796; Percent complete: 19.9%; Average loss: 3.7501
Iteration: 797; Percent complete: 19.9%; Average loss: 3.4295
Iteration: 798; Percent complete: 20.0%; Average loss: 3.4194
Iteration: 799; Percent complete: 20.0%; Average loss: 3.5427
Iteration: 800; Percent complete: 20.0%; Average loss: 3.6805
Iteration: 801; Percent complete: 20.0%; Average loss: 3.5216
Iteration: 802; Percent complete: 20.1%; Average loss: 3.7295
Iteration: 803; Percent complete: 20.1%; Average loss: 3.5218
Iteration: 804; Percent complete: 20.1%; Average loss: 3.7313
Iteration: 805; Percent complete: 20.1%; Average loss: 3.5711
Iteration: 806; Percent complete: 20.2%; Average loss: 3.8876
Iteration: 807; Percent complete: 20.2%; Average loss: 3.8004
Iteration: 808; Percent complete: 20.2%; Average loss: 3.5613
Iteration: 809; Percent complete: 20.2%; Average loss: 3.5837
Iteration: 810; Percent complete: 20.2%; Average loss: 3.4812
Iteration: 811; Percent complete: 20.3%; Average loss: 3.2519
Iteration: 812; Percent complete: 20.3%; Average loss: 3.4426
Iteration: 813; Percent complete: 20.3%; Average loss: 3.4241
Iteration: 814; Percent complete: 20.3%; Average loss: 3.6264
Iteration: 815; Percent complete: 20.4%; Average loss: 3.5390
Iteration: 816; Percent complete: 20.4%; Average loss: 3.5542
Iteration: 817; Percent complete: 20.4%; Average loss: 3.7322
Iteration: 818; Percent complete: 20.4%; Average loss: 3.6787
Iteration: 819; Percent complete: 20.5%; Average loss: 3.7217
Iteration: 820; Percent complete: 20.5%; Average loss: 3.5045
Iteration: 821; Percent complete: 20.5%; Average loss: 3.7779
Iteration: 822; Percent complete: 20.5%; Average loss: 3.5286
Iteration: 823; Percent complete: 20.6%; Average loss: 3.4237
Iteration: 824; Percent complete: 20.6%; Average loss: 3.5843
Iteration: 825; Percent complete: 20.6%; Average loss: 3.4446
Iteration: 826; Percent complete: 20.6%; Average loss: 3.2634
Iteration: 827; Percent complete: 20.7%; Average loss: 3.6859
Iteration: 828; Percent complete: 20.7%; Average loss: 3.5717
Iteration: 829; Percent complete: 20.7%; Average loss: 3.7518
Iteration: 830; Percent complete: 20.8%; Average loss: 3.3592
Iteration: 831; Percent complete: 20.8%; Average loss: 3.4076
Iteration: 832; Percent complete: 20.8%; Average loss: 3.4805
Iteration: 833; Percent complete: 20.8%; Average loss: 3.5505
Iteration: 834; Percent complete: 20.8%; Average loss: 3.5872
Iteration: 835; Percent complete: 20.9%; Average loss: 3.6357
Iteration: 836; Percent complete: 20.9%; Average loss: 3.3643
Iteration: 837; Percent complete: 20.9%; Average loss: 3.5742
Iteration: 838; Percent complete: 20.9%; Average loss: 3.4408
Iteration: 839; Percent complete: 21.0%; Average loss: 3.5843
Iteration: 840; Percent complete: 21.0%; Average loss: 3.7818
Iteration: 841; Percent complete: 21.0%; Average loss: 3.4087
Iteration: 842; Percent complete: 21.1%; Average loss: 3.3745
Iteration: 843; Percent complete: 21.1%; Average loss: 3.5560
Iteration: 844; Percent complete: 21.1%; Average loss: 3.5139
Iteration: 845; Percent complete: 21.1%; Average loss: 3.4575
Iteration: 846; Percent complete: 21.1%; Average loss: 3.5060
Iteration: 847; Percent complete: 21.2%; Average loss: 3.4350
Iteration: 848; Percent complete: 21.2%; Average loss: 3.8076
Iteration: 849; Percent complete: 21.2%; Average loss: 3.3394
Iteration: 850; Percent complete: 21.2%; Average loss: 3.6581
Iteration: 851; Percent complete: 21.3%; Average loss: 3.3543
Iteration: 852; Percent complete: 21.3%; Average loss: 3.1862
Iteration: 853; Percent complete: 21.3%; Average loss: 3.3700
Iteration: 854; Percent complete: 21.3%; Average loss: 3.3086
Iteration: 855; Percent complete: 21.4%; Average loss: 3.2587
Iteration: 856; Percent complete: 21.4%; Average loss: 3.1206
Iteration: 857; Percent complete: 21.4%; Average loss: 3.2506
Iteration: 858; Percent complete: 21.4%; Average loss: 3.3328
Iteration: 859; Percent complete: 21.5%; Average loss: 3.3211
Iteration: 860; Percent complete: 21.5%; Average loss: 3.4508
Iteration: 861; Percent complete: 21.5%; Average loss: 3.4638
Iteration: 862; Percent complete: 21.6%; Average loss: 3.6048
Iteration: 863; Percent complete: 21.6%; Average loss: 3.6054
Iteration: 864; Percent complete: 21.6%; Average loss: 3.2653
Iteration: 865; Percent complete: 21.6%; Average loss: 3.6941
Iteration: 866; Percent complete: 21.6%; Average loss: 3.7396
Iteration: 867; Percent complete: 21.7%; Average loss: 3.6303
Iteration: 868; Percent complete: 21.7%; Average loss: 3.5385
Iteration: 869; Percent complete: 21.7%; Average loss: 3.7202
Iteration: 870; Percent complete: 21.8%; Average loss: 3.6867
Iteration: 871; Percent complete: 21.8%; Average loss: 3.5490
Iteration: 872; Percent complete: 21.8%; Average loss: 3.5276
Iteration: 873; Percent complete: 21.8%; Average loss: 3.5505
Iteration: 874; Percent complete: 21.9%; Average loss: 3.4956
Iteration: 875; Percent complete: 21.9%; Average loss: 3.4490
Iteration: 876; Percent complete: 21.9%; Average loss: 3.4818
Iteration: 877; Percent complete: 21.9%; Average loss: 3.6916
Iteration: 878; Percent complete: 21.9%; Average loss: 3.8761
Iteration: 879; Percent complete: 22.0%; Average loss: 3.3340
Iteration: 880; Percent complete: 22.0%; Average loss: 3.3679
Iteration: 881; Percent complete: 22.0%; Average loss: 3.5034
Iteration: 882; Percent complete: 22.1%; Average loss: 3.4527
Iteration: 883; Percent complete: 22.1%; Average loss: 3.3423
Iteration: 884; Percent complete: 22.1%; Average loss: 3.6301
Iteration: 885; Percent complete: 22.1%; Average loss: 3.6129
Iteration: 886; Percent complete: 22.1%; Average loss: 3.5523
Iteration: 887; Percent complete: 22.2%; Average loss: 3.2349
Iteration: 888; Percent complete: 22.2%; Average loss: 3.7320
Iteration: 889; Percent complete: 22.2%; Average loss: 3.5496
Iteration: 890; Percent complete: 22.2%; Average loss: 3.6282
Iteration: 891; Percent complete: 22.3%; Average loss: 3.4005
Iteration: 892; Percent complete: 22.3%; Average loss: 3.5655
Iteration: 893; Percent complete: 22.3%; Average loss: 3.7706
Iteration: 894; Percent complete: 22.4%; Average loss: 3.3833
Iteration: 895; Percent complete: 22.4%; Average loss: 3.4245
Iteration: 896; Percent complete: 22.4%; Average loss: 3.6885
Iteration: 897; Percent complete: 22.4%; Average loss: 3.4717
Iteration: 898; Percent complete: 22.4%; Average loss: 3.2488
Iteration: 899; Percent complete: 22.5%; Average loss: 3.8002
Iteration: 900; Percent complete: 22.5%; Average loss: 3.2960
Iteration: 901; Percent complete: 22.5%; Average loss: 3.5404
Iteration: 902; Percent complete: 22.6%; Average loss: 3.3580
Iteration: 903; Percent complete: 22.6%; Average loss: 3.6026
Iteration: 904; Percent complete: 22.6%; Average loss: 3.4267
Iteration: 905; Percent complete: 22.6%; Average loss: 3.5342
Iteration: 906; Percent complete: 22.7%; Average loss: 3.7263
Iteration: 907; Percent complete: 22.7%; Average loss: 3.3756
Iteration: 908; Percent complete: 22.7%; Average loss: 3.4405
Iteration: 909; Percent complete: 22.7%; Average loss: 3.6541
Iteration: 910; Percent complete: 22.8%; Average loss: 3.7007
Iteration: 911; Percent complete: 22.8%; Average loss: 3.7741
Iteration: 912; Percent complete: 22.8%; Average loss: 3.7083
Iteration: 913; Percent complete: 22.8%; Average loss: 3.6069
Iteration: 914; Percent complete: 22.9%; Average loss: 3.5493
Iteration: 915; Percent complete: 22.9%; Average loss: 3.1530
Iteration: 916; Percent complete: 22.9%; Average loss: 3.5598
Iteration: 917; Percent complete: 22.9%; Average loss: 3.5812
Iteration: 918; Percent complete: 22.9%; Average loss: 3.7068
Iteration: 919; Percent complete: 23.0%; Average loss: 3.5434
Iteration: 920; Percent complete: 23.0%; Average loss: 3.5249
Iteration: 921; Percent complete: 23.0%; Average loss: 3.4057
Iteration: 922; Percent complete: 23.1%; Average loss: 3.3361
Iteration: 923; Percent complete: 23.1%; Average loss: 3.6581
Iteration: 924; Percent complete: 23.1%; Average loss: 3.4334
Iteration: 925; Percent complete: 23.1%; Average loss: 3.3122
Iteration: 926; Percent complete: 23.2%; Average loss: 3.6086
Iteration: 927; Percent complete: 23.2%; Average loss: 3.2519
Iteration: 928; Percent complete: 23.2%; Average loss: 3.4103
Iteration: 929; Percent complete: 23.2%; Average loss: 3.5852
Iteration: 930; Percent complete: 23.2%; Average loss: 3.5237
Iteration: 931; Percent complete: 23.3%; Average loss: 3.3416
Iteration: 932; Percent complete: 23.3%; Average loss: 3.4267
Iteration: 933; Percent complete: 23.3%; Average loss: 3.4497
Iteration: 934; Percent complete: 23.4%; Average loss: 3.4280
Iteration: 935; Percent complete: 23.4%; Average loss: 3.4118
Iteration: 936; Percent complete: 23.4%; Average loss: 2.9920
Iteration: 937; Percent complete: 23.4%; Average loss: 3.7022
Iteration: 938; Percent complete: 23.4%; Average loss: 3.5387
Iteration: 939; Percent complete: 23.5%; Average loss: 3.4482
Iteration: 940; Percent complete: 23.5%; Average loss: 3.4772
Iteration: 941; Percent complete: 23.5%; Average loss: 3.7735
Iteration: 942; Percent complete: 23.5%; Average loss: 3.5350
Iteration: 943; Percent complete: 23.6%; Average loss: 3.5726
Iteration: 944; Percent complete: 23.6%; Average loss: 3.2926
Iteration: 945; Percent complete: 23.6%; Average loss: 3.6496
Iteration: 946; Percent complete: 23.6%; Average loss: 3.3772
Iteration: 947; Percent complete: 23.7%; Average loss: 3.4197
Iteration: 948; Percent complete: 23.7%; Average loss: 3.3574
Iteration: 949; Percent complete: 23.7%; Average loss: 3.4403
Iteration: 950; Percent complete: 23.8%; Average loss: 3.5550
Iteration: 951; Percent complete: 23.8%; Average loss: 3.5011
Iteration: 952; Percent complete: 23.8%; Average loss: 3.3371
Iteration: 953; Percent complete: 23.8%; Average loss: 3.5995
Iteration: 954; Percent complete: 23.8%; Average loss: 3.7638
Iteration: 955; Percent complete: 23.9%; Average loss: 3.3351
Iteration: 956; Percent complete: 23.9%; Average loss: 3.8473
Iteration: 957; Percent complete: 23.9%; Average loss: 3.2562
Iteration: 958; Percent complete: 23.9%; Average loss: 3.1558
Iteration: 959; Percent complete: 24.0%; Average loss: 3.6481
Iteration: 960; Percent complete: 24.0%; Average loss: 3.2416
Iteration: 961; Percent complete: 24.0%; Average loss: 3.6058
Iteration: 962; Percent complete: 24.1%; Average loss: 3.4046
Iteration: 963; Percent complete: 24.1%; Average loss: 3.3254
Iteration: 964; Percent complete: 24.1%; Average loss: 3.6348
Iteration: 965; Percent complete: 24.1%; Average loss: 3.5972
Iteration: 966; Percent complete: 24.1%; Average loss: 3.5502
Iteration: 967; Percent complete: 24.2%; Average loss: 3.2132
Iteration: 968; Percent complete: 24.2%; Average loss: 3.7087
Iteration: 969; Percent complete: 24.2%; Average loss: 3.4843
Iteration: 970; Percent complete: 24.2%; Average loss: 3.5286
Iteration: 971; Percent complete: 24.3%; Average loss: 3.5631
Iteration: 972; Percent complete: 24.3%; Average loss: 3.5113
Iteration: 973; Percent complete: 24.3%; Average loss: 3.4928
Iteration: 974; Percent complete: 24.3%; Average loss: 3.4213
Iteration: 975; Percent complete: 24.4%; Average loss: 3.4718
Iteration: 976; Percent complete: 24.4%; Average loss: 3.6388
Iteration: 977; Percent complete: 24.4%; Average loss: 3.2551
Iteration: 978; Percent complete: 24.4%; Average loss: 3.5667
Iteration: 979; Percent complete: 24.5%; Average loss: 3.5608
Iteration: 980; Percent complete: 24.5%; Average loss: 3.4118
Iteration: 981; Percent complete: 24.5%; Average loss: 3.6957
Iteration: 982; Percent complete: 24.6%; Average loss: 3.3617
Iteration: 983; Percent complete: 24.6%; Average loss: 3.4345
Iteration: 984; Percent complete: 24.6%; Average loss: 3.4242
Iteration: 985; Percent complete: 24.6%; Average loss: 3.3471
Iteration: 986; Percent complete: 24.6%; Average loss: 3.6313
Iteration: 987; Percent complete: 24.7%; Average loss: 3.6549
Iteration: 988; Percent complete: 24.7%; Average loss: 3.4344
Iteration: 989; Percent complete: 24.7%; Average loss: 3.2033
Iteration: 990; Percent complete: 24.8%; Average loss: 3.2014
Iteration: 991; Percent complete: 24.8%; Average loss: 3.3612
Iteration: 992; Percent complete: 24.8%; Average loss: 3.6580
Iteration: 993; Percent complete: 24.8%; Average loss: 3.4833
Iteration: 994; Percent complete: 24.9%; Average loss: 3.5319
Iteration: 995; Percent complete: 24.9%; Average loss: 3.8015
Iteration: 996; Percent complete: 24.9%; Average loss: 3.4618
Iteration: 997; Percent complete: 24.9%; Average loss: 3.5248
Iteration: 998; Percent complete: 24.9%; Average loss: 3.6033
Iteration: 999; Percent complete: 25.0%; Average loss: 3.3636
Iteration: 1000; Percent complete: 25.0%; Average loss: 3.0907
Iteration: 1001; Percent complete: 25.0%; Average loss: 3.4679
Iteration: 1002; Percent complete: 25.1%; Average loss: 3.7920
Iteration: 1003; Percent complete: 25.1%; Average loss: 3.5498
Iteration: 1004; Percent complete: 25.1%; Average loss: 3.4723
Iteration: 1005; Percent complete: 25.1%; Average loss: 3.4978
Iteration: 1006; Percent complete: 25.1%; Average loss: 3.5527
Iteration: 1007; Percent complete: 25.2%; Average loss: 3.5089
Iteration: 1008; Percent complete: 25.2%; Average loss: 3.2789
Iteration: 1009; Percent complete: 25.2%; Average loss: 3.3890
Iteration: 1010; Percent complete: 25.2%; Average loss: 3.3513
Iteration: 1011; Percent complete: 25.3%; Average loss: 3.3312
Iteration: 1012; Percent complete: 25.3%; Average loss: 3.2388
Iteration: 1013; Percent complete: 25.3%; Average loss: 3.5314
Iteration: 1014; Percent complete: 25.4%; Average loss: 3.4156
Iteration: 1015; Percent complete: 25.4%; Average loss: 3.2838
Iteration: 1016; Percent complete: 25.4%; Average loss: 3.2824
Iteration: 1017; Percent complete: 25.4%; Average loss: 3.3023
Iteration: 1018; Percent complete: 25.4%; Average loss: 3.3650
Iteration: 1019; Percent complete: 25.5%; Average loss: 3.5485
Iteration: 1020; Percent complete: 25.5%; Average loss: 3.4793
Iteration: 1021; Percent complete: 25.5%; Average loss: 3.4340
Iteration: 1022; Percent complete: 25.6%; Average loss: 3.5981
Iteration: 1023; Percent complete: 25.6%; Average loss: 3.4508
Iteration: 1024; Percent complete: 25.6%; Average loss: 3.6715
Iteration: 1025; Percent complete: 25.6%; Average loss: 3.6553
Iteration: 1026; Percent complete: 25.7%; Average loss: 3.6291
Iteration: 1027; Percent complete: 25.7%; Average loss: 3.6612
Iteration: 1028; Percent complete: 25.7%; Average loss: 3.6334
Iteration: 1029; Percent complete: 25.7%; Average loss: 3.5296
Iteration: 1030; Percent complete: 25.8%; Average loss: 3.2595
Iteration: 1031; Percent complete: 25.8%; Average loss: 3.3590
Iteration: 1032; Percent complete: 25.8%; Average loss: 3.5684
Iteration: 1033; Percent complete: 25.8%; Average loss: 3.5974
Iteration: 1034; Percent complete: 25.9%; Average loss: 3.5366
Iteration: 1035; Percent complete: 25.9%; Average loss: 3.2076
Iteration: 1036; Percent complete: 25.9%; Average loss: 3.5000
Iteration: 1037; Percent complete: 25.9%; Average loss: 3.3464
Iteration: 1038; Percent complete: 25.9%; Average loss: 3.5554
Iteration: 1039; Percent complete: 26.0%; Average loss: 3.3542
Iteration: 1040; Percent complete: 26.0%; Average loss: 3.4326
Iteration: 1041; Percent complete: 26.0%; Average loss: 3.3562
Iteration: 1042; Percent complete: 26.1%; Average loss: 3.2979
Iteration: 1043; Percent complete: 26.1%; Average loss: 3.2173
Iteration: 1044; Percent complete: 26.1%; Average loss: 3.3527
Iteration: 1045; Percent complete: 26.1%; Average loss: 3.6351
Iteration: 1046; Percent complete: 26.2%; Average loss: 3.1517
Iteration: 1047; Percent complete: 26.2%; Average loss: 3.5019
Iteration: 1048; Percent complete: 26.2%; Average loss: 3.3982
Iteration: 1049; Percent complete: 26.2%; Average loss: 3.5893
Iteration: 1050; Percent complete: 26.2%; Average loss: 3.2277
Iteration: 1051; Percent complete: 26.3%; Average loss: 3.6421
Iteration: 1052; Percent complete: 26.3%; Average loss: 3.5678
Iteration: 1053; Percent complete: 26.3%; Average loss: 3.6230
Iteration: 1054; Percent complete: 26.4%; Average loss: 3.4713
Iteration: 1055; Percent complete: 26.4%; Average loss: 3.5456
Iteration: 1056; Percent complete: 26.4%; Average loss: 3.3226
Iteration: 1057; Percent complete: 26.4%; Average loss: 3.2185
Iteration: 1058; Percent complete: 26.5%; Average loss: 3.6009
Iteration: 1059; Percent complete: 26.5%; Average loss: 3.5495
Iteration: 1060; Percent complete: 26.5%; Average loss: 3.5399
Iteration: 1061; Percent complete: 26.5%; Average loss: 3.6278
Iteration: 1062; Percent complete: 26.6%; Average loss: 3.1301
Iteration: 1063; Percent complete: 26.6%; Average loss: 3.5081
Iteration: 1064; Percent complete: 26.6%; Average loss: 3.4297
Iteration: 1065; Percent complete: 26.6%; Average loss: 3.5478
Iteration: 1066; Percent complete: 26.7%; Average loss: 3.3468
Iteration: 1067; Percent complete: 26.7%; Average loss: 3.7530
Iteration: 1068; Percent complete: 26.7%; Average loss: 3.4673
Iteration: 1069; Percent complete: 26.7%; Average loss: 3.5382
Iteration: 1070; Percent complete: 26.8%; Average loss: 3.5209
Iteration: 1071; Percent complete: 26.8%; Average loss: 3.4681
Iteration: 1072; Percent complete: 26.8%; Average loss: 3.4814
Iteration: 1073; Percent complete: 26.8%; Average loss: 3.4651
Iteration: 1074; Percent complete: 26.9%; Average loss: 3.8683
Iteration: 1075; Percent complete: 26.9%; Average loss: 3.2567
Iteration: 1076; Percent complete: 26.9%; Average loss: 3.8165
Iteration: 1077; Percent complete: 26.9%; Average loss: 3.3712
Iteration: 1078; Percent complete: 27.0%; Average loss: 3.6081
Iteration: 1079; Percent complete: 27.0%; Average loss: 3.3472
Iteration: 1080; Percent complete: 27.0%; Average loss: 3.3750
Iteration: 1081; Percent complete: 27.0%; Average loss: 3.4174
Iteration: 1082; Percent complete: 27.1%; Average loss: 3.7241
Iteration: 1083; Percent complete: 27.1%; Average loss: 3.4729
Iteration: 1084; Percent complete: 27.1%; Average loss: 3.4585
Iteration: 1085; Percent complete: 27.1%; Average loss: 3.5329
Iteration: 1086; Percent complete: 27.2%; Average loss: 4.0124
Iteration: 1087; Percent complete: 27.2%; Average loss: 3.6472
Iteration: 1088; Percent complete: 27.2%; Average loss: 3.2946
Iteration: 1089; Percent complete: 27.2%; Average loss: 3.4105
Iteration: 1090; Percent complete: 27.3%; Average loss: 3.5034
Iteration: 1091; Percent complete: 27.3%; Average loss: 3.5743
Iteration: 1092; Percent complete: 27.3%; Average loss: 3.3523
Iteration: 1093; Percent complete: 27.3%; Average loss: 3.5170
Iteration: 1094; Percent complete: 27.4%; Average loss: 3.3578
Iteration: 1095; Percent complete: 27.4%; Average loss: 3.4702
Iteration: 1096; Percent complete: 27.4%; Average loss: 3.5891
Iteration: 1097; Percent complete: 27.4%; Average loss: 3.4781
Iteration: 1098; Percent complete: 27.5%; Average loss: 3.4957
Iteration: 1099; Percent complete: 27.5%; Average loss: 3.4974
Iteration: 1100; Percent complete: 27.5%; Average loss: 3.3882
Iteration: 1101; Percent complete: 27.5%; Average loss: 3.5061
Iteration: 1102; Percent complete: 27.6%; Average loss: 3.6145
Iteration: 1103; Percent complete: 27.6%; Average loss: 3.4991
Iteration: 1104; Percent complete: 27.6%; Average loss: 3.4801
Iteration: 1105; Percent complete: 27.6%; Average loss: 3.1711
Iteration: 1106; Percent complete: 27.7%; Average loss: 3.2265
Iteration: 1107; Percent complete: 27.7%; Average loss: 3.3394
Iteration: 1108; Percent complete: 27.7%; Average loss: 3.4169
Iteration: 1109; Percent complete: 27.7%; Average loss: 3.6196
Iteration: 1110; Percent complete: 27.8%; Average loss: 3.3817
Iteration: 1111; Percent complete: 27.8%; Average loss: 3.3362
Iteration: 1112; Percent complete: 27.8%; Average loss: 3.6724
Iteration: 1113; Percent complete: 27.8%; Average loss: 3.5753
Iteration: 1114; Percent complete: 27.9%; Average loss: 3.5538
Iteration: 1115; Percent complete: 27.9%; Average loss: 3.6430
Iteration: 1116; Percent complete: 27.9%; Average loss: 3.6422
Iteration: 1117; Percent complete: 27.9%; Average loss: 3.6259
Iteration: 1118; Percent complete: 28.0%; Average loss: 3.3626
Iteration: 1119; Percent complete: 28.0%; Average loss: 3.3178
Iteration: 1120; Percent complete: 28.0%; Average loss: 3.5001
Iteration: 1121; Percent complete: 28.0%; Average loss: 3.4987
Iteration: 1122; Percent complete: 28.1%; Average loss: 3.7353
Iteration: 1123; Percent complete: 28.1%; Average loss: 4.0050
Iteration: 1124; Percent complete: 28.1%; Average loss: 3.2509
Iteration: 1125; Percent complete: 28.1%; Average loss: 3.2404
Iteration: 1126; Percent complete: 28.1%; Average loss: 3.2755
Iteration: 1127; Percent complete: 28.2%; Average loss: 3.2477
Iteration: 1128; Percent complete: 28.2%; Average loss: 3.4191
Iteration: 1129; Percent complete: 28.2%; Average loss: 3.6383
Iteration: 1130; Percent complete: 28.2%; Average loss: 3.4967
Iteration: 1131; Percent complete: 28.3%; Average loss: 3.7078
Iteration: 1132; Percent complete: 28.3%; Average loss: 3.6016
Iteration: 1133; Percent complete: 28.3%; Average loss: 3.4613
Iteration: 1134; Percent complete: 28.3%; Average loss: 3.6241
Iteration: 1135; Percent complete: 28.4%; Average loss: 3.6426
Iteration: 1136; Percent complete: 28.4%; Average loss: 3.6533
Iteration: 1137; Percent complete: 28.4%; Average loss: 3.5775
Iteration: 1138; Percent complete: 28.4%; Average loss: 3.2966
Iteration: 1139; Percent complete: 28.5%; Average loss: 3.3687
Iteration: 1140; Percent complete: 28.5%; Average loss: 3.4772
Iteration: 1141; Percent complete: 28.5%; Average loss: 3.2899
Iteration: 1142; Percent complete: 28.5%; Average loss: 3.5623
Iteration: 1143; Percent complete: 28.6%; Average loss: 3.4180
Iteration: 1144; Percent complete: 28.6%; Average loss: 3.2936
Iteration: 1145; Percent complete: 28.6%; Average loss: 3.7231
Iteration: 1146; Percent complete: 28.6%; Average loss: 3.3436
Iteration: 1147; Percent complete: 28.7%; Average loss: 3.3498
Iteration: 1148; Percent complete: 28.7%; Average loss: 3.2709
Iteration: 1149; Percent complete: 28.7%; Average loss: 3.4882
Iteration: 1150; Percent complete: 28.7%; Average loss: 3.6411
Iteration: 1151; Percent complete: 28.8%; Average loss: 3.4678
Iteration: 1152; Percent complete: 28.8%; Average loss: 3.5878
Iteration: 1153; Percent complete: 28.8%; Average loss: 3.2391
Iteration: 1154; Percent complete: 28.8%; Average loss: 3.3042
Iteration: 1155; Percent complete: 28.9%; Average loss: 3.6544
Iteration: 1156; Percent complete: 28.9%; Average loss: 3.1748
Iteration: 1157; Percent complete: 28.9%; Average loss: 3.4720
Iteration: 1158; Percent complete: 28.9%; Average loss: 3.7204
Iteration: 1159; Percent complete: 29.0%; Average loss: 3.2732
Iteration: 1160; Percent complete: 29.0%; Average loss: 3.3944
Iteration: 1161; Percent complete: 29.0%; Average loss: 3.4619
Iteration: 1162; Percent complete: 29.0%; Average loss: 3.5434
Iteration: 1163; Percent complete: 29.1%; Average loss: 3.5489
Iteration: 1164; Percent complete: 29.1%; Average loss: 3.1614
Iteration: 1165; Percent complete: 29.1%; Average loss: 3.4954
Iteration: 1166; Percent complete: 29.1%; Average loss: 3.1455
Iteration: 1167; Percent complete: 29.2%; Average loss: 3.6280
Iteration: 1168; Percent complete: 29.2%; Average loss: 3.6670
Iteration: 1169; Percent complete: 29.2%; Average loss: 3.3930
Iteration: 1170; Percent complete: 29.2%; Average loss: 3.4199
Iteration: 1171; Percent complete: 29.3%; Average loss: 3.3279
Iteration: 1172; Percent complete: 29.3%; Average loss: 3.4254
Iteration: 1173; Percent complete: 29.3%; Average loss: 3.4072
Iteration: 1174; Percent complete: 29.3%; Average loss: 3.7085
Iteration: 1175; Percent complete: 29.4%; Average loss: 3.4445
Iteration: 1176; Percent complete: 29.4%; Average loss: 3.3371
Iteration: 1177; Percent complete: 29.4%; Average loss: 3.2345
Iteration: 1178; Percent complete: 29.4%; Average loss: 3.5889
Iteration: 1179; Percent complete: 29.5%; Average loss: 3.5452
Iteration: 1180; Percent complete: 29.5%; Average loss: 3.2887
Iteration: 1181; Percent complete: 29.5%; Average loss: 3.4193
Iteration: 1182; Percent complete: 29.5%; Average loss: 3.3754
Iteration: 1183; Percent complete: 29.6%; Average loss: 3.2858
Iteration: 1184; Percent complete: 29.6%; Average loss: 3.4431
Iteration: 1185; Percent complete: 29.6%; Average loss: 3.6141
Iteration: 1186; Percent complete: 29.6%; Average loss: 3.5981
Iteration: 1187; Percent complete: 29.7%; Average loss: 3.4639
Iteration: 1188; Percent complete: 29.7%; Average loss: 3.4802
Iteration: 1189; Percent complete: 29.7%; Average loss: 3.4666
Iteration: 1190; Percent complete: 29.8%; Average loss: 3.4267
Iteration: 1191; Percent complete: 29.8%; Average loss: 3.4691
Iteration: 1192; Percent complete: 29.8%; Average loss: 3.5970
Iteration: 1193; Percent complete: 29.8%; Average loss: 3.4431
Iteration: 1194; Percent complete: 29.8%; Average loss: 3.4999
Iteration: 1195; Percent complete: 29.9%; Average loss: 3.7230
Iteration: 1196; Percent complete: 29.9%; Average loss: 3.3184
Iteration: 1197; Percent complete: 29.9%; Average loss: 3.4187
Iteration: 1198; Percent complete: 29.9%; Average loss: 3.4297
Iteration: 1199; Percent complete: 30.0%; Average loss: 3.3851
Iteration: 1200; Percent complete: 30.0%; Average loss: 3.3177
Iteration: 1201; Percent complete: 30.0%; Average loss: 3.3330
Iteration: 1202; Percent complete: 30.0%; Average loss: 3.4486
Iteration: 1203; Percent complete: 30.1%; Average loss: 3.1144
Iteration: 1204; Percent complete: 30.1%; Average loss: 3.3143
Iteration: 1205; Percent complete: 30.1%; Average loss: 3.1941
Iteration: 1206; Percent complete: 30.1%; Average loss: 3.4494
Iteration: 1207; Percent complete: 30.2%; Average loss: 3.4491
Iteration: 1208; Percent complete: 30.2%; Average loss: 3.0573
Iteration: 1209; Percent complete: 30.2%; Average loss: 3.5227
Iteration: 1210; Percent complete: 30.2%; Average loss: 3.4988
Iteration: 1211; Percent complete: 30.3%; Average loss: 3.4374
Iteration: 1212; Percent complete: 30.3%; Average loss: 3.8298
Iteration: 1213; Percent complete: 30.3%; Average loss: 3.4504
Iteration: 1214; Percent complete: 30.3%; Average loss: 3.4259
Iteration: 1215; Percent complete: 30.4%; Average loss: 3.4372
Iteration: 1216; Percent complete: 30.4%; Average loss: 3.4567
Iteration: 1217; Percent complete: 30.4%; Average loss: 3.5772
Iteration: 1218; Percent complete: 30.4%; Average loss: 3.6178
Iteration: 1219; Percent complete: 30.5%; Average loss: 3.4272
Iteration: 1220; Percent complete: 30.5%; Average loss: 3.3651
Iteration: 1221; Percent complete: 30.5%; Average loss: 3.1793
Iteration: 1222; Percent complete: 30.6%; Average loss: 3.2696
Iteration: 1223; Percent complete: 30.6%; Average loss: 3.4508
Iteration: 1224; Percent complete: 30.6%; Average loss: 3.4307
Iteration: 1225; Percent complete: 30.6%; Average loss: 3.5810
Iteration: 1226; Percent complete: 30.6%; Average loss: 3.2437
Iteration: 1227; Percent complete: 30.7%; Average loss: 3.3249
Iteration: 1228; Percent complete: 30.7%; Average loss: 3.5207
Iteration: 1229; Percent complete: 30.7%; Average loss: 3.1935
Iteration: 1230; Percent complete: 30.8%; Average loss: 3.4934
Iteration: 1231; Percent complete: 30.8%; Average loss: 3.0637
Iteration: 1232; Percent complete: 30.8%; Average loss: 3.6063
Iteration: 1233; Percent complete: 30.8%; Average loss: 3.5834
Iteration: 1234; Percent complete: 30.9%; Average loss: 3.2822
Iteration: 1235; Percent complete: 30.9%; Average loss: 3.2873
Iteration: 1236; Percent complete: 30.9%; Average loss: 3.1860
Iteration: 1237; Percent complete: 30.9%; Average loss: 3.1887
Iteration: 1238; Percent complete: 30.9%; Average loss: 3.2565
Iteration: 1239; Percent complete: 31.0%; Average loss: 3.6054
Iteration: 1240; Percent complete: 31.0%; Average loss: 3.4825
Iteration: 1241; Percent complete: 31.0%; Average loss: 3.4327
Iteration: 1242; Percent complete: 31.1%; Average loss: 3.1823
Iteration: 1243; Percent complete: 31.1%; Average loss: 3.7780
Iteration: 1244; Percent complete: 31.1%; Average loss: 3.5877
Iteration: 1245; Percent complete: 31.1%; Average loss: 3.2746
Iteration: 1246; Percent complete: 31.1%; Average loss: 3.2823
Iteration: 1247; Percent complete: 31.2%; Average loss: 3.3905
Iteration: 1248; Percent complete: 31.2%; Average loss: 3.4513
Iteration: 1249; Percent complete: 31.2%; Average loss: 3.2638
Iteration: 1250; Percent complete: 31.2%; Average loss: 3.2519
Iteration: 1251; Percent complete: 31.3%; Average loss: 3.1900
Iteration: 1252; Percent complete: 31.3%; Average loss: 3.3331
Iteration: 1253; Percent complete: 31.3%; Average loss: 3.5404
Iteration: 1254; Percent complete: 31.4%; Average loss: 3.6794
Iteration: 1255; Percent complete: 31.4%; Average loss: 3.6284
Iteration: 1256; Percent complete: 31.4%; Average loss: 3.4088
Iteration: 1257; Percent complete: 31.4%; Average loss: 3.5975
Iteration: 1258; Percent complete: 31.4%; Average loss: 3.1118
Iteration: 1259; Percent complete: 31.5%; Average loss: 3.3838
Iteration: 1260; Percent complete: 31.5%; Average loss: 3.3852
Iteration: 1261; Percent complete: 31.5%; Average loss: 3.3439
Iteration: 1262; Percent complete: 31.6%; Average loss: 3.2922
Iteration: 1263; Percent complete: 31.6%; Average loss: 3.5525
Iteration: 1264; Percent complete: 31.6%; Average loss: 3.4361
Iteration: 1265; Percent complete: 31.6%; Average loss: 3.3199
Iteration: 1266; Percent complete: 31.6%; Average loss: 3.3466
Iteration: 1267; Percent complete: 31.7%; Average loss: 3.1660
Iteration: 1268; Percent complete: 31.7%; Average loss: 3.4664
Iteration: 1269; Percent complete: 31.7%; Average loss: 3.2818
Iteration: 1270; Percent complete: 31.8%; Average loss: 3.4039
Iteration: 1271; Percent complete: 31.8%; Average loss: 3.5034
Iteration: 1272; Percent complete: 31.8%; Average loss: 3.5090
Iteration: 1273; Percent complete: 31.8%; Average loss: 3.3170
Iteration: 1274; Percent complete: 31.9%; Average loss: 3.4326
Iteration: 1275; Percent complete: 31.9%; Average loss: 3.0441
Iteration: 1276; Percent complete: 31.9%; Average loss: 3.5475
Iteration: 1277; Percent complete: 31.9%; Average loss: 3.5596
Iteration: 1278; Percent complete: 31.9%; Average loss: 3.5120
Iteration: 1279; Percent complete: 32.0%; Average loss: 3.4794
Iteration: 1280; Percent complete: 32.0%; Average loss: 3.2136
Iteration: 1281; Percent complete: 32.0%; Average loss: 3.3946
Iteration: 1282; Percent complete: 32.0%; Average loss: 3.2084
Iteration: 1283; Percent complete: 32.1%; Average loss: 3.2988
Iteration: 1284; Percent complete: 32.1%; Average loss: 3.1562
Iteration: 1285; Percent complete: 32.1%; Average loss: 3.3739
Iteration: 1286; Percent complete: 32.1%; Average loss: 3.6238
Iteration: 1287; Percent complete: 32.2%; Average loss: 3.3753
Iteration: 1288; Percent complete: 32.2%; Average loss: 3.1893
Iteration: 1289; Percent complete: 32.2%; Average loss: 3.3587
Iteration: 1290; Percent complete: 32.2%; Average loss: 3.3265
Iteration: 1291; Percent complete: 32.3%; Average loss: 3.5713
Iteration: 1292; Percent complete: 32.3%; Average loss: 3.5725
Iteration: 1293; Percent complete: 32.3%; Average loss: 3.4933
Iteration: 1294; Percent complete: 32.4%; Average loss: 3.4076
Iteration: 1295; Percent complete: 32.4%; Average loss: 3.3229
Iteration: 1296; Percent complete: 32.4%; Average loss: 3.5792
Iteration: 1297; Percent complete: 32.4%; Average loss: 3.5907
Iteration: 1298; Percent complete: 32.5%; Average loss: 3.3673
Iteration: 1299; Percent complete: 32.5%; Average loss: 3.2634
Iteration: 1300; Percent complete: 32.5%; Average loss: 3.3317
Iteration: 1301; Percent complete: 32.5%; Average loss: 3.2951
Iteration: 1302; Percent complete: 32.6%; Average loss: 3.4687
Iteration: 1303; Percent complete: 32.6%; Average loss: 3.3752
Iteration: 1304; Percent complete: 32.6%; Average loss: 3.2691
Iteration: 1305; Percent complete: 32.6%; Average loss: 3.2269
Iteration: 1306; Percent complete: 32.6%; Average loss: 3.0712
Iteration: 1307; Percent complete: 32.7%; Average loss: 3.4516
Iteration: 1308; Percent complete: 32.7%; Average loss: 3.5235
Iteration: 1309; Percent complete: 32.7%; Average loss: 3.4615
Iteration: 1310; Percent complete: 32.8%; Average loss: 3.5969
Iteration: 1311; Percent complete: 32.8%; Average loss: 3.3960
Iteration: 1312; Percent complete: 32.8%; Average loss: 3.3345
Iteration: 1313; Percent complete: 32.8%; Average loss: 3.5167
Iteration: 1314; Percent complete: 32.9%; Average loss: 3.2904
Iteration: 1315; Percent complete: 32.9%; Average loss: 3.4669
Iteration: 1316; Percent complete: 32.9%; Average loss: 3.3296
Iteration: 1317; Percent complete: 32.9%; Average loss: 3.2666
Iteration: 1318; Percent complete: 33.0%; Average loss: 3.4186
Iteration: 1319; Percent complete: 33.0%; Average loss: 3.5847
Iteration: 1320; Percent complete: 33.0%; Average loss: 3.3041
Iteration: 1321; Percent complete: 33.0%; Average loss: 3.1852
Iteration: 1322; Percent complete: 33.1%; Average loss: 3.2602
Iteration: 1323; Percent complete: 33.1%; Average loss: 3.3243
Iteration: 1324; Percent complete: 33.1%; Average loss: 3.2441
Iteration: 1325; Percent complete: 33.1%; Average loss: 3.2815
Iteration: 1326; Percent complete: 33.1%; Average loss: 3.3934
Iteration: 1327; Percent complete: 33.2%; Average loss: 3.2794
Iteration: 1328; Percent complete: 33.2%; Average loss: 3.3275
Iteration: 1329; Percent complete: 33.2%; Average loss: 3.2741
Iteration: 1330; Percent complete: 33.2%; Average loss: 3.2246
Iteration: 1331; Percent complete: 33.3%; Average loss: 3.0712
Iteration: 1332; Percent complete: 33.3%; Average loss: 3.3093
Iteration: 1333; Percent complete: 33.3%; Average loss: 3.3446
Iteration: 1334; Percent complete: 33.4%; Average loss: 3.3785
Iteration: 1335; Percent complete: 33.4%; Average loss: 3.1417
Iteration: 1336; Percent complete: 33.4%; Average loss: 3.3119
Iteration: 1337; Percent complete: 33.4%; Average loss: 3.4033
Iteration: 1338; Percent complete: 33.5%; Average loss: 3.3844
Iteration: 1339; Percent complete: 33.5%; Average loss: 3.3580
Iteration: 1340; Percent complete: 33.5%; Average loss: 3.2958
Iteration: 1341; Percent complete: 33.5%; Average loss: 3.6543
Iteration: 1342; Percent complete: 33.6%; Average loss: 3.2642
Iteration: 1343; Percent complete: 33.6%; Average loss: 3.2765
Iteration: 1344; Percent complete: 33.6%; Average loss: 3.2467
Iteration: 1345; Percent complete: 33.6%; Average loss: 3.3105
Iteration: 1346; Percent complete: 33.7%; Average loss: 3.1729
Iteration: 1347; Percent complete: 33.7%; Average loss: 3.3994
Iteration: 1348; Percent complete: 33.7%; Average loss: 3.4380
Iteration: 1349; Percent complete: 33.7%; Average loss: 3.2723
Iteration: 1350; Percent complete: 33.8%; Average loss: 3.2071
Iteration: 1351; Percent complete: 33.8%; Average loss: 3.2797
Iteration: 1352; Percent complete: 33.8%; Average loss: 3.3811
Iteration: 1353; Percent complete: 33.8%; Average loss: 3.2029
Iteration: 1354; Percent complete: 33.9%; Average loss: 2.9315
Iteration: 1355; Percent complete: 33.9%; Average loss: 3.6322
Iteration: 1356; Percent complete: 33.9%; Average loss: 3.1321
Iteration: 1357; Percent complete: 33.9%; Average loss: 3.4265
Iteration: 1358; Percent complete: 34.0%; Average loss: 3.4137
Iteration: 1359; Percent complete: 34.0%; Average loss: 3.4954
Iteration: 1360; Percent complete: 34.0%; Average loss: 3.5431
Iteration: 1361; Percent complete: 34.0%; Average loss: 3.2416
Iteration: 1362; Percent complete: 34.1%; Average loss: 3.1698
Iteration: 1363; Percent complete: 34.1%; Average loss: 3.2473
Iteration: 1364; Percent complete: 34.1%; Average loss: 3.5457
Iteration: 1365; Percent complete: 34.1%; Average loss: 3.1664
Iteration: 1366; Percent complete: 34.2%; Average loss: 3.1971
Iteration: 1367; Percent complete: 34.2%; Average loss: 3.4476
Iteration: 1368; Percent complete: 34.2%; Average loss: 3.3403
Iteration: 1369; Percent complete: 34.2%; Average loss: 3.0095
Iteration: 1370; Percent complete: 34.2%; Average loss: 3.6047
Iteration: 1371; Percent complete: 34.3%; Average loss: 3.4075
Iteration: 1372; Percent complete: 34.3%; Average loss: 3.2581
Iteration: 1373; Percent complete: 34.3%; Average loss: 3.2901
Iteration: 1374; Percent complete: 34.4%; Average loss: 3.3657
Iteration: 1375; Percent complete: 34.4%; Average loss: 3.2434
Iteration: 1376; Percent complete: 34.4%; Average loss: 3.2153
Iteration: 1377; Percent complete: 34.4%; Average loss: 3.2757
Iteration: 1378; Percent complete: 34.4%; Average loss: 3.6989
Iteration: 1379; Percent complete: 34.5%; Average loss: 3.3494
Iteration: 1380; Percent complete: 34.5%; Average loss: 3.4650
Iteration: 1381; Percent complete: 34.5%; Average loss: 3.4472
Iteration: 1382; Percent complete: 34.5%; Average loss: 3.3278
Iteration: 1383; Percent complete: 34.6%; Average loss: 3.6952
Iteration: 1384; Percent complete: 34.6%; Average loss: 3.4046
Iteration: 1385; Percent complete: 34.6%; Average loss: 3.5070
Iteration: 1386; Percent complete: 34.6%; Average loss: 3.4204
Iteration: 1387; Percent complete: 34.7%; Average loss: 3.5797
Iteration: 1388; Percent complete: 34.7%; Average loss: 3.1317
Iteration: 1389; Percent complete: 34.7%; Average loss: 3.3931
Iteration: 1390; Percent complete: 34.8%; Average loss: 3.3594
Iteration: 1391; Percent complete: 34.8%; Average loss: 3.3252
Iteration: 1392; Percent complete: 34.8%; Average loss: 3.3562
Iteration: 1393; Percent complete: 34.8%; Average loss: 3.1988
Iteration: 1394; Percent complete: 34.8%; Average loss: 3.4665
Iteration: 1395; Percent complete: 34.9%; Average loss: 3.3890
Iteration: 1396; Percent complete: 34.9%; Average loss: 3.4959
Iteration: 1397; Percent complete: 34.9%; Average loss: 3.2614
Iteration: 1398; Percent complete: 34.9%; Average loss: 3.4302
Iteration: 1399; Percent complete: 35.0%; Average loss: 3.3355
Iteration: 1400; Percent complete: 35.0%; Average loss: 3.4508
Iteration: 1401; Percent complete: 35.0%; Average loss: 3.4246
Iteration: 1402; Percent complete: 35.0%; Average loss: 3.4483
Iteration: 1403; Percent complete: 35.1%; Average loss: 3.4753
Iteration: 1404; Percent complete: 35.1%; Average loss: 3.3570
Iteration: 1405; Percent complete: 35.1%; Average loss: 3.4591
Iteration: 1406; Percent complete: 35.1%; Average loss: 3.2720
Iteration: 1407; Percent complete: 35.2%; Average loss: 3.6617
Iteration: 1408; Percent complete: 35.2%; Average loss: 3.2260
Iteration: 1409; Percent complete: 35.2%; Average loss: 3.0634
Iteration: 1410; Percent complete: 35.2%; Average loss: 3.5104
Iteration: 1411; Percent complete: 35.3%; Average loss: 3.1639
Iteration: 1412; Percent complete: 35.3%; Average loss: 3.5743
Iteration: 1413; Percent complete: 35.3%; Average loss: 3.2895
Iteration: 1414; Percent complete: 35.4%; Average loss: 3.3706
Iteration: 1415; Percent complete: 35.4%; Average loss: 3.2847
Iteration: 1416; Percent complete: 35.4%; Average loss: 3.1635
Iteration: 1417; Percent complete: 35.4%; Average loss: 3.1810
Iteration: 1418; Percent complete: 35.4%; Average loss: 3.2175
Iteration: 1419; Percent complete: 35.5%; Average loss: 3.5544
Iteration: 1420; Percent complete: 35.5%; Average loss: 3.2886
Iteration: 1421; Percent complete: 35.5%; Average loss: 3.6129
Iteration: 1422; Percent complete: 35.5%; Average loss: 3.1775
Iteration: 1423; Percent complete: 35.6%; Average loss: 3.4782
Iteration: 1424; Percent complete: 35.6%; Average loss: 3.5748
Iteration: 1425; Percent complete: 35.6%; Average loss: 3.2718
Iteration: 1426; Percent complete: 35.6%; Average loss: 3.5165
Iteration: 1427; Percent complete: 35.7%; Average loss: 3.3831
Iteration: 1428; Percent complete: 35.7%; Average loss: 3.0585
Iteration: 1429; Percent complete: 35.7%; Average loss: 3.3742
Iteration: 1430; Percent complete: 35.8%; Average loss: 3.2675
Iteration: 1431; Percent complete: 35.8%; Average loss: 3.5839
Iteration: 1432; Percent complete: 35.8%; Average loss: 3.1093
Iteration: 1433; Percent complete: 35.8%; Average loss: 3.4096
Iteration: 1434; Percent complete: 35.9%; Average loss: 3.5476
Iteration: 1435; Percent complete: 35.9%; Average loss: 3.4267
Iteration: 1436; Percent complete: 35.9%; Average loss: 3.2102
Iteration: 1437; Percent complete: 35.9%; Average loss: 3.5568
Iteration: 1438; Percent complete: 35.9%; Average loss: 3.0909
Iteration: 1439; Percent complete: 36.0%; Average loss: 3.6621
Iteration: 1440; Percent complete: 36.0%; Average loss: 3.5166
Iteration: 1441; Percent complete: 36.0%; Average loss: 3.4266
Iteration: 1442; Percent complete: 36.0%; Average loss: 3.3252
Iteration: 1443; Percent complete: 36.1%; Average loss: 3.2641
Iteration: 1444; Percent complete: 36.1%; Average loss: 3.5368
Iteration: 1445; Percent complete: 36.1%; Average loss: 3.1125
Iteration: 1446; Percent complete: 36.1%; Average loss: 3.3456
Iteration: 1447; Percent complete: 36.2%; Average loss: 3.4547
Iteration: 1448; Percent complete: 36.2%; Average loss: 2.9301
Iteration: 1449; Percent complete: 36.2%; Average loss: 3.3454
Iteration: 1450; Percent complete: 36.2%; Average loss: 3.1364
Iteration: 1451; Percent complete: 36.3%; Average loss: 3.5854
Iteration: 1452; Percent complete: 36.3%; Average loss: 3.3519
Iteration: 1453; Percent complete: 36.3%; Average loss: 3.2353
Iteration: 1454; Percent complete: 36.4%; Average loss: 3.2364
Iteration: 1455; Percent complete: 36.4%; Average loss: 3.6808
Iteration: 1456; Percent complete: 36.4%; Average loss: 3.2394
Iteration: 1457; Percent complete: 36.4%; Average loss: 3.4449
Iteration: 1458; Percent complete: 36.4%; Average loss: 3.1905
Iteration: 1459; Percent complete: 36.5%; Average loss: 3.0333
Iteration: 1460; Percent complete: 36.5%; Average loss: 3.3269
Iteration: 1461; Percent complete: 36.5%; Average loss: 3.2835
Iteration: 1462; Percent complete: 36.5%; Average loss: 3.3993
Iteration: 1463; Percent complete: 36.6%; Average loss: 3.1485
Iteration: 1464; Percent complete: 36.6%; Average loss: 3.3645
Iteration: 1465; Percent complete: 36.6%; Average loss: 3.2057
Iteration: 1466; Percent complete: 36.6%; Average loss: 3.4610
Iteration: 1467; Percent complete: 36.7%; Average loss: 3.6454
Iteration: 1468; Percent complete: 36.7%; Average loss: 3.2338
Iteration: 1469; Percent complete: 36.7%; Average loss: 3.5420
Iteration: 1470; Percent complete: 36.8%; Average loss: 3.4384
Iteration: 1471; Percent complete: 36.8%; Average loss: 3.4718
Iteration: 1472; Percent complete: 36.8%; Average loss: 3.2973
Iteration: 1473; Percent complete: 36.8%; Average loss: 3.2917
Iteration: 1474; Percent complete: 36.9%; Average loss: 3.2332
Iteration: 1475; Percent complete: 36.9%; Average loss: 3.3793
Iteration: 1476; Percent complete: 36.9%; Average loss: 3.1979
Iteration: 1477; Percent complete: 36.9%; Average loss: 3.4976
Iteration: 1478; Percent complete: 37.0%; Average loss: 3.3699
Iteration: 1479; Percent complete: 37.0%; Average loss: 3.0860
Iteration: 1480; Percent complete: 37.0%; Average loss: 3.4782
Iteration: 1481; Percent complete: 37.0%; Average loss: 3.4197
Iteration: 1482; Percent complete: 37.0%; Average loss: 3.1786
Iteration: 1483; Percent complete: 37.1%; Average loss: 3.3963
Iteration: 1484; Percent complete: 37.1%; Average loss: 3.2496
Iteration: 1485; Percent complete: 37.1%; Average loss: 3.5331
Iteration: 1486; Percent complete: 37.1%; Average loss: 3.1829
Iteration: 1487; Percent complete: 37.2%; Average loss: 3.2890
Iteration: 1488; Percent complete: 37.2%; Average loss: 3.5364
Iteration: 1489; Percent complete: 37.2%; Average loss: 3.3530
Iteration: 1490; Percent complete: 37.2%; Average loss: 3.2712
Iteration: 1491; Percent complete: 37.3%; Average loss: 3.2014
Iteration: 1492; Percent complete: 37.3%; Average loss: 3.2548
Iteration: 1493; Percent complete: 37.3%; Average loss: 3.5346
Iteration: 1494; Percent complete: 37.4%; Average loss: 3.3389
Iteration: 1495; Percent complete: 37.4%; Average loss: 3.0445
Iteration: 1496; Percent complete: 37.4%; Average loss: 3.4171
Iteration: 1497; Percent complete: 37.4%; Average loss: 3.0463
Iteration: 1498; Percent complete: 37.5%; Average loss: 3.5788
Iteration: 1499; Percent complete: 37.5%; Average loss: 3.4100
Iteration: 1500; Percent complete: 37.5%; Average loss: 3.2812
Iteration: 1501; Percent complete: 37.5%; Average loss: 3.1907
Iteration: 1502; Percent complete: 37.5%; Average loss: 3.1327
Iteration: 1503; Percent complete: 37.6%; Average loss: 3.1440
Iteration: 1504; Percent complete: 37.6%; Average loss: 3.1873
Iteration: 1505; Percent complete: 37.6%; Average loss: 3.5017
Iteration: 1506; Percent complete: 37.6%; Average loss: 3.3793
Iteration: 1507; Percent complete: 37.7%; Average loss: 3.0727
Iteration: 1508; Percent complete: 37.7%; Average loss: 3.3407
Iteration: 1509; Percent complete: 37.7%; Average loss: 3.5082
Iteration: 1510; Percent complete: 37.8%; Average loss: 3.2031
Iteration: 1511; Percent complete: 37.8%; Average loss: 3.0916
Iteration: 1512; Percent complete: 37.8%; Average loss: 2.9203
Iteration: 1513; Percent complete: 37.8%; Average loss: 3.1710
Iteration: 1514; Percent complete: 37.9%; Average loss: 3.4475
Iteration: 1515; Percent complete: 37.9%; Average loss: 3.3504
Iteration: 1516; Percent complete: 37.9%; Average loss: 3.2834
Iteration: 1517; Percent complete: 37.9%; Average loss: 3.2948
Iteration: 1518; Percent complete: 38.0%; Average loss: 3.3305
Iteration: 1519; Percent complete: 38.0%; Average loss: 3.3952
Iteration: 1520; Percent complete: 38.0%; Average loss: 3.3702
Iteration: 1521; Percent complete: 38.0%; Average loss: 3.2594
Iteration: 1522; Percent complete: 38.0%; Average loss: 3.1882
Iteration: 1523; Percent complete: 38.1%; Average loss: 3.1969
Iteration: 1524; Percent complete: 38.1%; Average loss: 3.2832
Iteration: 1525; Percent complete: 38.1%; Average loss: 3.3393
Iteration: 1526; Percent complete: 38.1%; Average loss: 3.3638
Iteration: 1527; Percent complete: 38.2%; Average loss: 3.2710
Iteration: 1528; Percent complete: 38.2%; Average loss: 3.1596
Iteration: 1529; Percent complete: 38.2%; Average loss: 3.4296
Iteration: 1530; Percent complete: 38.2%; Average loss: 3.2420
Iteration: 1531; Percent complete: 38.3%; Average loss: 3.0766
Iteration: 1532; Percent complete: 38.3%; Average loss: 3.2113
Iteration: 1533; Percent complete: 38.3%; Average loss: 3.2136
Iteration: 1534; Percent complete: 38.4%; Average loss: 3.2197
Iteration: 1535; Percent complete: 38.4%; Average loss: 3.2656
Iteration: 1536; Percent complete: 38.4%; Average loss: 3.3498
Iteration: 1537; Percent complete: 38.4%; Average loss: 3.1988
Iteration: 1538; Percent complete: 38.5%; Average loss: 3.4297
Iteration: 1539; Percent complete: 38.5%; Average loss: 3.4551
Iteration: 1540; Percent complete: 38.5%; Average loss: 3.1921
Iteration: 1541; Percent complete: 38.5%; Average loss: 3.0757
Iteration: 1542; Percent complete: 38.6%; Average loss: 3.5737
Iteration: 1543; Percent complete: 38.6%; Average loss: 3.4768
Iteration: 1544; Percent complete: 38.6%; Average loss: 3.1506
Iteration: 1545; Percent complete: 38.6%; Average loss: 3.2474
Iteration: 1546; Percent complete: 38.6%; Average loss: 3.3309
Iteration: 1547; Percent complete: 38.7%; Average loss: 3.3298
Iteration: 1548; Percent complete: 38.7%; Average loss: 3.1990
Iteration: 1549; Percent complete: 38.7%; Average loss: 3.4775
Iteration: 1550; Percent complete: 38.8%; Average loss: 3.2400
Iteration: 1551; Percent complete: 38.8%; Average loss: 3.2617
Iteration: 1552; Percent complete: 38.8%; Average loss: 3.0736
Iteration: 1553; Percent complete: 38.8%; Average loss: 3.2753
Iteration: 1554; Percent complete: 38.9%; Average loss: 3.3640
Iteration: 1555; Percent complete: 38.9%; Average loss: 3.2909
Iteration: 1556; Percent complete: 38.9%; Average loss: 3.3011
Iteration: 1557; Percent complete: 38.9%; Average loss: 3.1034
Iteration: 1558; Percent complete: 39.0%; Average loss: 3.1445
Iteration: 1559; Percent complete: 39.0%; Average loss: 3.3783
Iteration: 1560; Percent complete: 39.0%; Average loss: 3.3779
Iteration: 1561; Percent complete: 39.0%; Average loss: 3.1936
Iteration: 1562; Percent complete: 39.1%; Average loss: 3.4143
Iteration: 1563; Percent complete: 39.1%; Average loss: 3.4965
Iteration: 1564; Percent complete: 39.1%; Average loss: 3.3960
Iteration: 1565; Percent complete: 39.1%; Average loss: 3.5439
Iteration: 1566; Percent complete: 39.1%; Average loss: 3.5087
Iteration: 1567; Percent complete: 39.2%; Average loss: 3.2433
Iteration: 1568; Percent complete: 39.2%; Average loss: 3.3628
Iteration: 1569; Percent complete: 39.2%; Average loss: 3.3404
Iteration: 1570; Percent complete: 39.2%; Average loss: 3.2549
Iteration: 1571; Percent complete: 39.3%; Average loss: 3.3139
Iteration: 1572; Percent complete: 39.3%; Average loss: 3.4320
Iteration: 1573; Percent complete: 39.3%; Average loss: 3.1786
Iteration: 1574; Percent complete: 39.4%; Average loss: 3.3775
Iteration: 1575; Percent complete: 39.4%; Average loss: 3.2563
Iteration: 1576; Percent complete: 39.4%; Average loss: 3.2581
Iteration: 1577; Percent complete: 39.4%; Average loss: 3.2202
Iteration: 1578; Percent complete: 39.5%; Average loss: 3.4295
Iteration: 1579; Percent complete: 39.5%; Average loss: 3.3213
Iteration: 1580; Percent complete: 39.5%; Average loss: 3.3158
Iteration: 1581; Percent complete: 39.5%; Average loss: 3.3669
Iteration: 1582; Percent complete: 39.6%; Average loss: 3.2651
Iteration: 1583; Percent complete: 39.6%; Average loss: 3.3953
Iteration: 1584; Percent complete: 39.6%; Average loss: 2.9900
Iteration: 1585; Percent complete: 39.6%; Average loss: 3.3819
Iteration: 1586; Percent complete: 39.6%; Average loss: 3.2228
Iteration: 1587; Percent complete: 39.7%; Average loss: 3.2717
Iteration: 1588; Percent complete: 39.7%; Average loss: 3.3015
Iteration: 1589; Percent complete: 39.7%; Average loss: 2.9519
Iteration: 1590; Percent complete: 39.8%; Average loss: 3.1393
Iteration: 1591; Percent complete: 39.8%; Average loss: 3.1102
Iteration: 1592; Percent complete: 39.8%; Average loss: 3.3259
Iteration: 1593; Percent complete: 39.8%; Average loss: 3.1103
Iteration: 1594; Percent complete: 39.9%; Average loss: 3.4129
Iteration: 1595; Percent complete: 39.9%; Average loss: 3.3817
Iteration: 1596; Percent complete: 39.9%; Average loss: 3.2731
Iteration: 1597; Percent complete: 39.9%; Average loss: 3.1004
Iteration: 1598; Percent complete: 40.0%; Average loss: 3.4039
Iteration: 1599; Percent complete: 40.0%; Average loss: 3.4865
Iteration: 1600; Percent complete: 40.0%; Average loss: 3.1641
Iteration: 1601; Percent complete: 40.0%; Average loss: 3.2821
Iteration: 1602; Percent complete: 40.1%; Average loss: 3.4477
Iteration: 1603; Percent complete: 40.1%; Average loss: 3.2501
Iteration: 1604; Percent complete: 40.1%; Average loss: 3.2741
Iteration: 1605; Percent complete: 40.1%; Average loss: 3.2188
Iteration: 1606; Percent complete: 40.2%; Average loss: 3.2394
Iteration: 1607; Percent complete: 40.2%; Average loss: 3.2460
Iteration: 1608; Percent complete: 40.2%; Average loss: 3.0195
Iteration: 1609; Percent complete: 40.2%; Average loss: 3.3425
Iteration: 1610; Percent complete: 40.2%; Average loss: 3.4246
Iteration: 1611; Percent complete: 40.3%; Average loss: 3.0238
Iteration: 1612; Percent complete: 40.3%; Average loss: 3.2689
Iteration: 1613; Percent complete: 40.3%; Average loss: 3.2530
Iteration: 1614; Percent complete: 40.4%; Average loss: 3.4361
Iteration: 1615; Percent complete: 40.4%; Average loss: 3.3082
Iteration: 1616; Percent complete: 40.4%; Average loss: 3.1163
Iteration: 1617; Percent complete: 40.4%; Average loss: 3.3114
Iteration: 1618; Percent complete: 40.5%; Average loss: 3.0291
Iteration: 1619; Percent complete: 40.5%; Average loss: 3.2646
Iteration: 1620; Percent complete: 40.5%; Average loss: 3.2820
Iteration: 1621; Percent complete: 40.5%; Average loss: 2.8409
Iteration: 1622; Percent complete: 40.6%; Average loss: 3.1038
Iteration: 1623; Percent complete: 40.6%; Average loss: 3.2085
Iteration: 1624; Percent complete: 40.6%; Average loss: 3.4111
Iteration: 1625; Percent complete: 40.6%; Average loss: 3.0686
Iteration: 1626; Percent complete: 40.6%; Average loss: 3.3653
Iteration: 1627; Percent complete: 40.7%; Average loss: 3.1668
Iteration: 1628; Percent complete: 40.7%; Average loss: 3.2700
Iteration: 1629; Percent complete: 40.7%; Average loss: 3.1382
Iteration: 1630; Percent complete: 40.8%; Average loss: 3.0475
Iteration: 1631; Percent complete: 40.8%; Average loss: 3.3539
Iteration: 1632; Percent complete: 40.8%; Average loss: 3.4449
Iteration: 1633; Percent complete: 40.8%; Average loss: 3.1754
Iteration: 1634; Percent complete: 40.8%; Average loss: 3.4433
Iteration: 1635; Percent complete: 40.9%; Average loss: 3.2483
Iteration: 1636; Percent complete: 40.9%; Average loss: 3.3337
Iteration: 1637; Percent complete: 40.9%; Average loss: 3.1980
Iteration: 1638; Percent complete: 40.9%; Average loss: 3.1268
Iteration: 1639; Percent complete: 41.0%; Average loss: 3.5175
Iteration: 1640; Percent complete: 41.0%; Average loss: 3.2695
Iteration: 1641; Percent complete: 41.0%; Average loss: 3.2887
Iteration: 1642; Percent complete: 41.0%; Average loss: 3.4741
Iteration: 1643; Percent complete: 41.1%; Average loss: 3.1975
Iteration: 1644; Percent complete: 41.1%; Average loss: 3.3871
Iteration: 1645; Percent complete: 41.1%; Average loss: 3.3108
Iteration: 1646; Percent complete: 41.1%; Average loss: 3.4483
Iteration: 1647; Percent complete: 41.2%; Average loss: 3.2163
Iteration: 1648; Percent complete: 41.2%; Average loss: 3.2434
Iteration: 1649; Percent complete: 41.2%; Average loss: 3.4353
Iteration: 1650; Percent complete: 41.2%; Average loss: 3.0791
Iteration: 1651; Percent complete: 41.3%; Average loss: 3.2387
Iteration: 1652; Percent complete: 41.3%; Average loss: 3.2072
Iteration: 1653; Percent complete: 41.3%; Average loss: 3.2860
Iteration: 1654; Percent complete: 41.3%; Average loss: 3.2998
Iteration: 1655; Percent complete: 41.4%; Average loss: 3.0556
Iteration: 1656; Percent complete: 41.4%; Average loss: 3.1713
Iteration: 1657; Percent complete: 41.4%; Average loss: 3.1640
Iteration: 1658; Percent complete: 41.4%; Average loss: 3.0706
Iteration: 1659; Percent complete: 41.5%; Average loss: 3.1172
Iteration: 1660; Percent complete: 41.5%; Average loss: 3.0548
Iteration: 1661; Percent complete: 41.5%; Average loss: 3.3320
Iteration: 1662; Percent complete: 41.5%; Average loss: 3.5092
Iteration: 1663; Percent complete: 41.6%; Average loss: 3.3343
Iteration: 1664; Percent complete: 41.6%; Average loss: 3.2005
Iteration: 1665; Percent complete: 41.6%; Average loss: 3.1267
Iteration: 1666; Percent complete: 41.6%; Average loss: 3.3434
Iteration: 1667; Percent complete: 41.7%; Average loss: 3.0253
Iteration: 1668; Percent complete: 41.7%; Average loss: 3.4350
Iteration: 1669; Percent complete: 41.7%; Average loss: 3.0384
Iteration: 1670; Percent complete: 41.8%; Average loss: 3.3070
Iteration: 1671; Percent complete: 41.8%; Average loss: 3.4749
Iteration: 1672; Percent complete: 41.8%; Average loss: 3.2366
Iteration: 1673; Percent complete: 41.8%; Average loss: 3.2283
Iteration: 1674; Percent complete: 41.9%; Average loss: 3.2808
Iteration: 1675; Percent complete: 41.9%; Average loss: 3.7510
Iteration: 1676; Percent complete: 41.9%; Average loss: 3.3065
Iteration: 1677; Percent complete: 41.9%; Average loss: 3.3247
Iteration: 1678; Percent complete: 41.9%; Average loss: 3.4860
Iteration: 1679; Percent complete: 42.0%; Average loss: 3.1809
Iteration: 1680; Percent complete: 42.0%; Average loss: 3.1354
Iteration: 1681; Percent complete: 42.0%; Average loss: 3.3469
Iteration: 1682; Percent complete: 42.0%; Average loss: 3.4750
Iteration: 1683; Percent complete: 42.1%; Average loss: 3.0724
Iteration: 1684; Percent complete: 42.1%; Average loss: 3.2341
Iteration: 1685; Percent complete: 42.1%; Average loss: 3.1769
Iteration: 1686; Percent complete: 42.1%; Average loss: 3.5817
Iteration: 1687; Percent complete: 42.2%; Average loss: 3.2510
Iteration: 1688; Percent complete: 42.2%; Average loss: 3.2664
Iteration: 1689; Percent complete: 42.2%; Average loss: 3.0255
Iteration: 1690; Percent complete: 42.2%; Average loss: 3.2927
Iteration: 1691; Percent complete: 42.3%; Average loss: 3.1604
Iteration: 1692; Percent complete: 42.3%; Average loss: 3.2377
Iteration: 1693; Percent complete: 42.3%; Average loss: 3.1479
Iteration: 1694; Percent complete: 42.4%; Average loss: 3.3360
Iteration: 1695; Percent complete: 42.4%; Average loss: 3.2428
Iteration: 1696; Percent complete: 42.4%; Average loss: 3.2074
Iteration: 1697; Percent complete: 42.4%; Average loss: 3.3207
Iteration: 1698; Percent complete: 42.4%; Average loss: 3.1116
Iteration: 1699; Percent complete: 42.5%; Average loss: 3.3992
Iteration: 1700; Percent complete: 42.5%; Average loss: 3.3687
Iteration: 1701; Percent complete: 42.5%; Average loss: 3.4345
Iteration: 1702; Percent complete: 42.5%; Average loss: 3.4556
Iteration: 1703; Percent complete: 42.6%; Average loss: 3.5068
Iteration: 1704; Percent complete: 42.6%; Average loss: 3.3290
Iteration: 1705; Percent complete: 42.6%; Average loss: 2.9787
Iteration: 1706; Percent complete: 42.6%; Average loss: 3.4652
Iteration: 1707; Percent complete: 42.7%; Average loss: 2.9023
Iteration: 1708; Percent complete: 42.7%; Average loss: 3.1921
Iteration: 1709; Percent complete: 42.7%; Average loss: 3.3296
Iteration: 1710; Percent complete: 42.8%; Average loss: 3.2465
Iteration: 1711; Percent complete: 42.8%; Average loss: 3.2551
Iteration: 1712; Percent complete: 42.8%; Average loss: 3.2320
Iteration: 1713; Percent complete: 42.8%; Average loss: 3.1680
Iteration: 1714; Percent complete: 42.9%; Average loss: 3.2554
Iteration: 1715; Percent complete: 42.9%; Average loss: 3.2912
Iteration: 1716; Percent complete: 42.9%; Average loss: 3.1432
Iteration: 1717; Percent complete: 42.9%; Average loss: 3.3968
Iteration: 1718; Percent complete: 43.0%; Average loss: 3.3723
Iteration: 1719; Percent complete: 43.0%; Average loss: 3.1358
Iteration: 1720; Percent complete: 43.0%; Average loss: 3.3814
Iteration: 1721; Percent complete: 43.0%; Average loss: 3.0631
Iteration: 1722; Percent complete: 43.0%; Average loss: 3.2770
Iteration: 1723; Percent complete: 43.1%; Average loss: 2.9860
Iteration: 1724; Percent complete: 43.1%; Average loss: 3.0491
Iteration: 1725; Percent complete: 43.1%; Average loss: 3.4710
Iteration: 1726; Percent complete: 43.1%; Average loss: 3.2254
Iteration: 1727; Percent complete: 43.2%; Average loss: 3.2735
Iteration: 1728; Percent complete: 43.2%; Average loss: 3.2418
Iteration: 1729; Percent complete: 43.2%; Average loss: 3.2214
Iteration: 1730; Percent complete: 43.2%; Average loss: 3.3442
Iteration: 1731; Percent complete: 43.3%; Average loss: 3.3187
Iteration: 1732; Percent complete: 43.3%; Average loss: 3.2781
Iteration: 1733; Percent complete: 43.3%; Average loss: 3.2711
Iteration: 1734; Percent complete: 43.4%; Average loss: 3.1849
Iteration: 1735; Percent complete: 43.4%; Average loss: 3.0365
Iteration: 1736; Percent complete: 43.4%; Average loss: 3.1030
Iteration: 1737; Percent complete: 43.4%; Average loss: 2.9479
Iteration: 1738; Percent complete: 43.5%; Average loss: 3.1006
Iteration: 1739; Percent complete: 43.5%; Average loss: 3.1410
Iteration: 1740; Percent complete: 43.5%; Average loss: 3.2556
Iteration: 1741; Percent complete: 43.5%; Average loss: 3.4319
Iteration: 1742; Percent complete: 43.5%; Average loss: 2.9996
Iteration: 1743; Percent complete: 43.6%; Average loss: 3.3251
Iteration: 1744; Percent complete: 43.6%; Average loss: 3.2464
Iteration: 1745; Percent complete: 43.6%; Average loss: 3.1460
Iteration: 1746; Percent complete: 43.6%; Average loss: 3.1150
Iteration: 1747; Percent complete: 43.7%; Average loss: 2.9802
Iteration: 1748; Percent complete: 43.7%; Average loss: 3.1368
Iteration: 1749; Percent complete: 43.7%; Average loss: 3.1761
Iteration: 1750; Percent complete: 43.8%; Average loss: 3.2666
Iteration: 1751; Percent complete: 43.8%; Average loss: 2.9008
Iteration: 1752; Percent complete: 43.8%; Average loss: 2.9455
Iteration: 1753; Percent complete: 43.8%; Average loss: 3.3938
Iteration: 1754; Percent complete: 43.9%; Average loss: 2.9728
Iteration: 1755; Percent complete: 43.9%; Average loss: 3.0104
Iteration: 1756; Percent complete: 43.9%; Average loss: 3.0751
Iteration: 1757; Percent complete: 43.9%; Average loss: 3.1175
Iteration: 1758; Percent complete: 44.0%; Average loss: 3.4711
Iteration: 1759; Percent complete: 44.0%; Average loss: 3.1300
Iteration: 1760; Percent complete: 44.0%; Average loss: 3.5402
Iteration: 1761; Percent complete: 44.0%; Average loss: 3.3931
Iteration: 1762; Percent complete: 44.0%; Average loss: 3.1958
Iteration: 1763; Percent complete: 44.1%; Average loss: 3.0110
Iteration: 1764; Percent complete: 44.1%; Average loss: 3.3822
Iteration: 1765; Percent complete: 44.1%; Average loss: 3.3683
Iteration: 1766; Percent complete: 44.1%; Average loss: 3.3147
Iteration: 1767; Percent complete: 44.2%; Average loss: 3.4166
Iteration: 1768; Percent complete: 44.2%; Average loss: 3.3376
Iteration: 1769; Percent complete: 44.2%; Average loss: 3.2617
Iteration: 1770; Percent complete: 44.2%; Average loss: 3.4233
Iteration: 1771; Percent complete: 44.3%; Average loss: 3.3108
Iteration: 1772; Percent complete: 44.3%; Average loss: 3.2764
Iteration: 1773; Percent complete: 44.3%; Average loss: 3.0368
Iteration: 1774; Percent complete: 44.4%; Average loss: 3.4421
Iteration: 1775; Percent complete: 44.4%; Average loss: 3.3433
Iteration: 1776; Percent complete: 44.4%; Average loss: 3.4233
Iteration: 1777; Percent complete: 44.4%; Average loss: 3.3250
Iteration: 1778; Percent complete: 44.5%; Average loss: 3.4766
Iteration: 1779; Percent complete: 44.5%; Average loss: 3.1497
Iteration: 1780; Percent complete: 44.5%; Average loss: 3.3348
Iteration: 1781; Percent complete: 44.5%; Average loss: 3.1031
Iteration: 1782; Percent complete: 44.5%; Average loss: 3.3679
Iteration: 1783; Percent complete: 44.6%; Average loss: 3.1156
Iteration: 1784; Percent complete: 44.6%; Average loss: 3.2750
Iteration: 1785; Percent complete: 44.6%; Average loss: 3.1469
Iteration: 1786; Percent complete: 44.6%; Average loss: 3.0610
Iteration: 1787; Percent complete: 44.7%; Average loss: 3.1469
Iteration: 1788; Percent complete: 44.7%; Average loss: 3.2356
Iteration: 1789; Percent complete: 44.7%; Average loss: 3.1675
Iteration: 1790; Percent complete: 44.8%; Average loss: 3.2582
Iteration: 1791; Percent complete: 44.8%; Average loss: 3.1928
Iteration: 1792; Percent complete: 44.8%; Average loss: 3.1263
Iteration: 1793; Percent complete: 44.8%; Average loss: 3.3593
Iteration: 1794; Percent complete: 44.9%; Average loss: 3.3356
Iteration: 1795; Percent complete: 44.9%; Average loss: 3.1471
Iteration: 1796; Percent complete: 44.9%; Average loss: 3.3278
Iteration: 1797; Percent complete: 44.9%; Average loss: 3.1469
Iteration: 1798; Percent complete: 45.0%; Average loss: 2.9564
Iteration: 1799; Percent complete: 45.0%; Average loss: 2.8867
Iteration: 1800; Percent complete: 45.0%; Average loss: 3.2373
Iteration: 1801; Percent complete: 45.0%; Average loss: 3.0331
Iteration: 1802; Percent complete: 45.1%; Average loss: 2.9918
Iteration: 1803; Percent complete: 45.1%; Average loss: 2.8216
Iteration: 1804; Percent complete: 45.1%; Average loss: 3.0109
Iteration: 1805; Percent complete: 45.1%; Average loss: 3.3296
Iteration: 1806; Percent complete: 45.1%; Average loss: 3.1304
Iteration: 1807; Percent complete: 45.2%; Average loss: 3.1252
Iteration: 1808; Percent complete: 45.2%; Average loss: 3.2117
Iteration: 1809; Percent complete: 45.2%; Average loss: 3.0441
Iteration: 1810; Percent complete: 45.2%; Average loss: 3.4108
Iteration: 1811; Percent complete: 45.3%; Average loss: 3.1508
Iteration: 1812; Percent complete: 45.3%; Average loss: 3.0143
Iteration: 1813; Percent complete: 45.3%; Average loss: 3.1754
Iteration: 1814; Percent complete: 45.4%; Average loss: 3.0871
Iteration: 1815; Percent complete: 45.4%; Average loss: 3.3820
Iteration: 1816; Percent complete: 45.4%; Average loss: 3.3138
Iteration: 1817; Percent complete: 45.4%; Average loss: 3.2978
Iteration: 1818; Percent complete: 45.5%; Average loss: 3.0960
Iteration: 1819; Percent complete: 45.5%; Average loss: 3.2807
Iteration: 1820; Percent complete: 45.5%; Average loss: 3.3966
Iteration: 1821; Percent complete: 45.5%; Average loss: 3.2723
Iteration: 1822; Percent complete: 45.6%; Average loss: 3.2585
Iteration: 1823; Percent complete: 45.6%; Average loss: 3.1870
Iteration: 1824; Percent complete: 45.6%; Average loss: 3.2165
Iteration: 1825; Percent complete: 45.6%; Average loss: 3.2384
Iteration: 1826; Percent complete: 45.6%; Average loss: 3.1306
Iteration: 1827; Percent complete: 45.7%; Average loss: 3.1949
Iteration: 1828; Percent complete: 45.7%; Average loss: 3.1543
Iteration: 1829; Percent complete: 45.7%; Average loss: 3.4710
Iteration: 1830; Percent complete: 45.8%; Average loss: 3.3324
Iteration: 1831; Percent complete: 45.8%; Average loss: 3.0288
Iteration: 1832; Percent complete: 45.8%; Average loss: 3.2238
Iteration: 1833; Percent complete: 45.8%; Average loss: 3.1652
Iteration: 1834; Percent complete: 45.9%; Average loss: 2.9206
Iteration: 1835; Percent complete: 45.9%; Average loss: 3.3675
Iteration: 1836; Percent complete: 45.9%; Average loss: 3.0440
Iteration: 1837; Percent complete: 45.9%; Average loss: 3.2471
Iteration: 1838; Percent complete: 46.0%; Average loss: 3.1384
Iteration: 1839; Percent complete: 46.0%; Average loss: 3.2600
Iteration: 1840; Percent complete: 46.0%; Average loss: 3.0336
Iteration: 1841; Percent complete: 46.0%; Average loss: 3.1220
Iteration: 1842; Percent complete: 46.1%; Average loss: 3.0474
Iteration: 1843; Percent complete: 46.1%; Average loss: 2.9871
Iteration: 1844; Percent complete: 46.1%; Average loss: 3.2290
Iteration: 1845; Percent complete: 46.1%; Average loss: 3.2930
Iteration: 1846; Percent complete: 46.2%; Average loss: 3.0617
Iteration: 1847; Percent complete: 46.2%; Average loss: 3.3113
Iteration: 1848; Percent complete: 46.2%; Average loss: 3.4377
Iteration: 1849; Percent complete: 46.2%; Average loss: 3.0459
Iteration: 1850; Percent complete: 46.2%; Average loss: 3.0606
Iteration: 1851; Percent complete: 46.3%; Average loss: 3.2012
Iteration: 1852; Percent complete: 46.3%; Average loss: 3.3647
Iteration: 1853; Percent complete: 46.3%; Average loss: 3.0866
Iteration: 1854; Percent complete: 46.4%; Average loss: 2.8833
Iteration: 1855; Percent complete: 46.4%; Average loss: 3.2855
Iteration: 1856; Percent complete: 46.4%; Average loss: 3.3490
Iteration: 1857; Percent complete: 46.4%; Average loss: 3.1131
Iteration: 1858; Percent complete: 46.5%; Average loss: 3.2936
Iteration: 1859; Percent complete: 46.5%; Average loss: 3.0074
Iteration: 1860; Percent complete: 46.5%; Average loss: 3.1520
Iteration: 1861; Percent complete: 46.5%; Average loss: 2.9167
Iteration: 1862; Percent complete: 46.6%; Average loss: 3.0821
Iteration: 1863; Percent complete: 46.6%; Average loss: 3.1632
Iteration: 1864; Percent complete: 46.6%; Average loss: 3.0014
Iteration: 1865; Percent complete: 46.6%; Average loss: 3.3349
Iteration: 1866; Percent complete: 46.7%; Average loss: 3.4606
Iteration: 1867; Percent complete: 46.7%; Average loss: 3.0371
Iteration: 1868; Percent complete: 46.7%; Average loss: 3.3523
Iteration: 1869; Percent complete: 46.7%; Average loss: 3.2480
Iteration: 1870; Percent complete: 46.8%; Average loss: 3.2137
Iteration: 1871; Percent complete: 46.8%; Average loss: 3.0060
Iteration: 1872; Percent complete: 46.8%; Average loss: 3.1994
Iteration: 1873; Percent complete: 46.8%; Average loss: 3.0295
Iteration: 1874; Percent complete: 46.9%; Average loss: 3.1932
Iteration: 1875; Percent complete: 46.9%; Average loss: 3.0354
Iteration: 1876; Percent complete: 46.9%; Average loss: 3.5359
Iteration: 1877; Percent complete: 46.9%; Average loss: 2.9777
Iteration: 1878; Percent complete: 46.9%; Average loss: 3.4524
Iteration: 1879; Percent complete: 47.0%; Average loss: 3.2076
Iteration: 1880; Percent complete: 47.0%; Average loss: 3.3238
Iteration: 1881; Percent complete: 47.0%; Average loss: 2.9997
Iteration: 1882; Percent complete: 47.0%; Average loss: 3.0763
Iteration: 1883; Percent complete: 47.1%; Average loss: 3.1085
Iteration: 1884; Percent complete: 47.1%; Average loss: 2.8463
Iteration: 1885; Percent complete: 47.1%; Average loss: 3.3302
Iteration: 1886; Percent complete: 47.1%; Average loss: 3.1206
Iteration: 1887; Percent complete: 47.2%; Average loss: 2.9624
Iteration: 1888; Percent complete: 47.2%; Average loss: 2.9980
Iteration: 1889; Percent complete: 47.2%; Average loss: 3.1008
Iteration: 1890; Percent complete: 47.2%; Average loss: 3.1400
Iteration: 1891; Percent complete: 47.3%; Average loss: 3.2394
Iteration: 1892; Percent complete: 47.3%; Average loss: 3.4291
Iteration: 1893; Percent complete: 47.3%; Average loss: 3.2148
Iteration: 1894; Percent complete: 47.3%; Average loss: 3.2070
Iteration: 1895; Percent complete: 47.4%; Average loss: 3.4345
Iteration: 1896; Percent complete: 47.4%; Average loss: 3.1881
Iteration: 1897; Percent complete: 47.4%; Average loss: 3.2004
Iteration: 1898; Percent complete: 47.4%; Average loss: 3.0563
Iteration: 1899; Percent complete: 47.5%; Average loss: 3.1958
Iteration: 1900; Percent complete: 47.5%; Average loss: 3.2970
Iteration: 1901; Percent complete: 47.5%; Average loss: 3.1294
Iteration: 1902; Percent complete: 47.5%; Average loss: 3.4094
Iteration: 1903; Percent complete: 47.6%; Average loss: 3.3613
Iteration: 1904; Percent complete: 47.6%; Average loss: 3.1076
Iteration: 1905; Percent complete: 47.6%; Average loss: 3.1644
Iteration: 1906; Percent complete: 47.6%; Average loss: 3.3587
Iteration: 1907; Percent complete: 47.7%; Average loss: 3.1619
Iteration: 1908; Percent complete: 47.7%; Average loss: 3.0949
Iteration: 1909; Percent complete: 47.7%; Average loss: 3.0776
Iteration: 1910; Percent complete: 47.8%; Average loss: 3.1216
Iteration: 1911; Percent complete: 47.8%; Average loss: 3.1365
Iteration: 1912; Percent complete: 47.8%; Average loss: 3.2835
Iteration: 1913; Percent complete: 47.8%; Average loss: 3.4048
Iteration: 1914; Percent complete: 47.9%; Average loss: 3.1377
Iteration: 1915; Percent complete: 47.9%; Average loss: 3.0568
Iteration: 1916; Percent complete: 47.9%; Average loss: 3.1165
Iteration: 1917; Percent complete: 47.9%; Average loss: 3.0334
Iteration: 1918; Percent complete: 47.9%; Average loss: 3.3165
Iteration: 1919; Percent complete: 48.0%; Average loss: 3.1112
Iteration: 1920; Percent complete: 48.0%; Average loss: 3.5032
Iteration: 1921; Percent complete: 48.0%; Average loss: 3.0649
Iteration: 1922; Percent complete: 48.0%; Average loss: 3.2197
Iteration: 1923; Percent complete: 48.1%; Average loss: 2.9448
Iteration: 1924; Percent complete: 48.1%; Average loss: 3.0583
Iteration: 1925; Percent complete: 48.1%; Average loss: 3.4552
Iteration: 1926; Percent complete: 48.1%; Average loss: 2.9174
Iteration: 1927; Percent complete: 48.2%; Average loss: 3.2752
Iteration: 1928; Percent complete: 48.2%; Average loss: 3.1704
Iteration: 1929; Percent complete: 48.2%; Average loss: 3.2422
Iteration: 1930; Percent complete: 48.2%; Average loss: 3.0928
Iteration: 1931; Percent complete: 48.3%; Average loss: 2.8759
Iteration: 1932; Percent complete: 48.3%; Average loss: 3.1786
Iteration: 1933; Percent complete: 48.3%; Average loss: 3.3297
Iteration: 1934; Percent complete: 48.4%; Average loss: 3.3804
Iteration: 1935; Percent complete: 48.4%; Average loss: 3.2561
Iteration: 1936; Percent complete: 48.4%; Average loss: 3.1197
Iteration: 1937; Percent complete: 48.4%; Average loss: 3.0231
Iteration: 1938; Percent complete: 48.4%; Average loss: 3.0511
Iteration: 1939; Percent complete: 48.5%; Average loss: 3.1814
Iteration: 1940; Percent complete: 48.5%; Average loss: 3.3117
Iteration: 1941; Percent complete: 48.5%; Average loss: 3.1189
Iteration: 1942; Percent complete: 48.5%; Average loss: 3.2406
Iteration: 1943; Percent complete: 48.6%; Average loss: 3.4130
Iteration: 1944; Percent complete: 48.6%; Average loss: 2.6988
Iteration: 1945; Percent complete: 48.6%; Average loss: 3.3306
Iteration: 1946; Percent complete: 48.6%; Average loss: 3.5815
Iteration: 1947; Percent complete: 48.7%; Average loss: 3.1635
Iteration: 1948; Percent complete: 48.7%; Average loss: 3.0425
Iteration: 1949; Percent complete: 48.7%; Average loss: 2.9371
Iteration: 1950; Percent complete: 48.8%; Average loss: 3.2649
Iteration: 1951; Percent complete: 48.8%; Average loss: 3.2861
Iteration: 1952; Percent complete: 48.8%; Average loss: 3.0233
Iteration: 1953; Percent complete: 48.8%; Average loss: 3.2027
Iteration: 1954; Percent complete: 48.9%; Average loss: 3.2156
Iteration: 1955; Percent complete: 48.9%; Average loss: 3.2381
Iteration: 1956; Percent complete: 48.9%; Average loss: 3.3339
Iteration: 1957; Percent complete: 48.9%; Average loss: 3.3140
Iteration: 1958; Percent complete: 48.9%; Average loss: 3.4496
Iteration: 1959; Percent complete: 49.0%; Average loss: 2.9838
Iteration: 1960; Percent complete: 49.0%; Average loss: 3.2808
Iteration: 1961; Percent complete: 49.0%; Average loss: 2.7883
Iteration: 1962; Percent complete: 49.0%; Average loss: 3.1464
Iteration: 1963; Percent complete: 49.1%; Average loss: 3.1114
Iteration: 1964; Percent complete: 49.1%; Average loss: 3.1854
Iteration: 1965; Percent complete: 49.1%; Average loss: 3.0680
Iteration: 1966; Percent complete: 49.1%; Average loss: 3.0427
Iteration: 1967; Percent complete: 49.2%; Average loss: 3.1569
Iteration: 1968; Percent complete: 49.2%; Average loss: 3.4173
Iteration: 1969; Percent complete: 49.2%; Average loss: 3.2423
Iteration: 1970; Percent complete: 49.2%; Average loss: 3.2374
Iteration: 1971; Percent complete: 49.3%; Average loss: 3.1324
Iteration: 1972; Percent complete: 49.3%; Average loss: 3.1777
Iteration: 1973; Percent complete: 49.3%; Average loss: 3.3069
Iteration: 1974; Percent complete: 49.4%; Average loss: 3.1164
Iteration: 1975; Percent complete: 49.4%; Average loss: 3.3031
Iteration: 1976; Percent complete: 49.4%; Average loss: 3.0033
Iteration: 1977; Percent complete: 49.4%; Average loss: 3.2671
Iteration: 1978; Percent complete: 49.5%; Average loss: 2.9778
Iteration: 1979; Percent complete: 49.5%; Average loss: 3.1918
Iteration: 1980; Percent complete: 49.5%; Average loss: 3.1500
Iteration: 1981; Percent complete: 49.5%; Average loss: 3.3410
Iteration: 1982; Percent complete: 49.5%; Average loss: 3.1225
Iteration: 1983; Percent complete: 49.6%; Average loss: 3.3317
Iteration: 1984; Percent complete: 49.6%; Average loss: 3.2404
Iteration: 1985; Percent complete: 49.6%; Average loss: 3.0790
Iteration: 1986; Percent complete: 49.6%; Average loss: 3.1973
Iteration: 1987; Percent complete: 49.7%; Average loss: 3.2047
Iteration: 1988; Percent complete: 49.7%; Average loss: 3.1138
Iteration: 1989; Percent complete: 49.7%; Average loss: 3.1805
Iteration: 1990; Percent complete: 49.8%; Average loss: 3.2029
Iteration: 1991; Percent complete: 49.8%; Average loss: 3.3414
Iteration: 1992; Percent complete: 49.8%; Average loss: 3.2226
Iteration: 1993; Percent complete: 49.8%; Average loss: 2.9840
Iteration: 1994; Percent complete: 49.9%; Average loss: 3.4299
Iteration: 1995; Percent complete: 49.9%; Average loss: 2.8922
Iteration: 1996; Percent complete: 49.9%; Average loss: 3.3716
Iteration: 1997; Percent complete: 49.9%; Average loss: 3.1934
Iteration: 1998; Percent complete: 50.0%; Average loss: 3.0273
Iteration: 1999; Percent complete: 50.0%; Average loss: 3.1069
Iteration: 2000; Percent complete: 50.0%; Average loss: 3.0468
Iteration: 2001; Percent complete: 50.0%; Average loss: 2.9919
Iteration: 2002; Percent complete: 50.0%; Average loss: 3.0743
Iteration: 2003; Percent complete: 50.1%; Average loss: 3.1612
Iteration: 2004; Percent complete: 50.1%; Average loss: 2.8985
Iteration: 2005; Percent complete: 50.1%; Average loss: 3.3755
Iteration: 2006; Percent complete: 50.1%; Average loss: 3.1730
Iteration: 2007; Percent complete: 50.2%; Average loss: 3.2085
Iteration: 2008; Percent complete: 50.2%; Average loss: 3.1524
Iteration: 2009; Percent complete: 50.2%; Average loss: 3.0946
Iteration: 2010; Percent complete: 50.2%; Average loss: 3.0953
Iteration: 2011; Percent complete: 50.3%; Average loss: 2.9898
Iteration: 2012; Percent complete: 50.3%; Average loss: 3.0114
Iteration: 2013; Percent complete: 50.3%; Average loss: 2.8545
Iteration: 2014; Percent complete: 50.3%; Average loss: 3.2409
Iteration: 2015; Percent complete: 50.4%; Average loss: 3.1731
Iteration: 2016; Percent complete: 50.4%; Average loss: 2.9828
Iteration: 2017; Percent complete: 50.4%; Average loss: 3.2227
Iteration: 2018; Percent complete: 50.4%; Average loss: 3.3582
Iteration: 2019; Percent complete: 50.5%; Average loss: 3.3072
Iteration: 2020; Percent complete: 50.5%; Average loss: 3.0507
Iteration: 2021; Percent complete: 50.5%; Average loss: 3.1601
Iteration: 2022; Percent complete: 50.5%; Average loss: 3.1751
Iteration: 2023; Percent complete: 50.6%; Average loss: 3.1235
Iteration: 2024; Percent complete: 50.6%; Average loss: 3.0423
Iteration: 2025; Percent complete: 50.6%; Average loss: 3.3649
Iteration: 2026; Percent complete: 50.6%; Average loss: 3.0401
Iteration: 2027; Percent complete: 50.7%; Average loss: 3.1975
Iteration: 2028; Percent complete: 50.7%; Average loss: 3.1615
Iteration: 2029; Percent complete: 50.7%; Average loss: 3.1446
Iteration: 2030; Percent complete: 50.7%; Average loss: 3.2985
Iteration: 2031; Percent complete: 50.8%; Average loss: 2.9135
Iteration: 2032; Percent complete: 50.8%; Average loss: 3.0064
Iteration: 2033; Percent complete: 50.8%; Average loss: 3.0763
Iteration: 2034; Percent complete: 50.8%; Average loss: 3.3259
Iteration: 2035; Percent complete: 50.9%; Average loss: 3.2632
Iteration: 2036; Percent complete: 50.9%; Average loss: 3.0372
Iteration: 2037; Percent complete: 50.9%; Average loss: 3.0967
Iteration: 2038; Percent complete: 50.9%; Average loss: 3.4065
Iteration: 2039; Percent complete: 51.0%; Average loss: 3.0525
Iteration: 2040; Percent complete: 51.0%; Average loss: 3.3436
Iteration: 2041; Percent complete: 51.0%; Average loss: 3.1675
Iteration: 2042; Percent complete: 51.0%; Average loss: 3.4039
Iteration: 2043; Percent complete: 51.1%; Average loss: 3.3248
Iteration: 2044; Percent complete: 51.1%; Average loss: 3.3137
Iteration: 2045; Percent complete: 51.1%; Average loss: 3.1912
Iteration: 2046; Percent complete: 51.1%; Average loss: 3.2564
Iteration: 2047; Percent complete: 51.2%; Average loss: 2.9440
Iteration: 2048; Percent complete: 51.2%; Average loss: 3.0266
Iteration: 2049; Percent complete: 51.2%; Average loss: 2.9340
Iteration: 2050; Percent complete: 51.2%; Average loss: 3.1424
Iteration: 2051; Percent complete: 51.3%; Average loss: 2.8371
Iteration: 2052; Percent complete: 51.3%; Average loss: 2.9547
Iteration: 2053; Percent complete: 51.3%; Average loss: 3.4292
Iteration: 2054; Percent complete: 51.3%; Average loss: 3.3662
Iteration: 2055; Percent complete: 51.4%; Average loss: 3.2478
Iteration: 2056; Percent complete: 51.4%; Average loss: 3.1410
Iteration: 2057; Percent complete: 51.4%; Average loss: 3.0780
Iteration: 2058; Percent complete: 51.4%; Average loss: 3.2875
Iteration: 2059; Percent complete: 51.5%; Average loss: 3.1541
Iteration: 2060; Percent complete: 51.5%; Average loss: 3.2976
Iteration: 2061; Percent complete: 51.5%; Average loss: 3.4135
Iteration: 2062; Percent complete: 51.5%; Average loss: 3.4588
Iteration: 2063; Percent complete: 51.6%; Average loss: 3.0244
Iteration: 2064; Percent complete: 51.6%; Average loss: 3.0768
Iteration: 2065; Percent complete: 51.6%; Average loss: 3.2503
Iteration: 2066; Percent complete: 51.6%; Average loss: 3.2420
Iteration: 2067; Percent complete: 51.7%; Average loss: 3.2605
Iteration: 2068; Percent complete: 51.7%; Average loss: 2.9377
Iteration: 2069; Percent complete: 51.7%; Average loss: 3.0964
Iteration: 2070; Percent complete: 51.7%; Average loss: 3.1223
Iteration: 2071; Percent complete: 51.8%; Average loss: 3.2545
Iteration: 2072; Percent complete: 51.8%; Average loss: 3.0649
Iteration: 2073; Percent complete: 51.8%; Average loss: 2.9656
Iteration: 2074; Percent complete: 51.8%; Average loss: 3.0558
Iteration: 2075; Percent complete: 51.9%; Average loss: 2.9626
Iteration: 2076; Percent complete: 51.9%; Average loss: 3.1142
Iteration: 2077; Percent complete: 51.9%; Average loss: 3.2410
Iteration: 2078; Percent complete: 51.9%; Average loss: 3.1833
Iteration: 2079; Percent complete: 52.0%; Average loss: 3.2496
Iteration: 2080; Percent complete: 52.0%; Average loss: 3.1361
Iteration: 2081; Percent complete: 52.0%; Average loss: 3.1832
Iteration: 2082; Percent complete: 52.0%; Average loss: 3.1461
Iteration: 2083; Percent complete: 52.1%; Average loss: 3.0046
Iteration: 2084; Percent complete: 52.1%; Average loss: 3.5619
Iteration: 2085; Percent complete: 52.1%; Average loss: 3.2265
Iteration: 2086; Percent complete: 52.1%; Average loss: 3.3608
Iteration: 2087; Percent complete: 52.2%; Average loss: 3.1606
Iteration: 2088; Percent complete: 52.2%; Average loss: 3.0875
Iteration: 2089; Percent complete: 52.2%; Average loss: 3.0021
Iteration: 2090; Percent complete: 52.2%; Average loss: 3.1763
Iteration: 2091; Percent complete: 52.3%; Average loss: 2.9283
Iteration: 2092; Percent complete: 52.3%; Average loss: 2.9637
Iteration: 2093; Percent complete: 52.3%; Average loss: 3.3094
Iteration: 2094; Percent complete: 52.3%; Average loss: 3.3737
Iteration: 2095; Percent complete: 52.4%; Average loss: 3.0099
Iteration: 2096; Percent complete: 52.4%; Average loss: 3.1903
Iteration: 2097; Percent complete: 52.4%; Average loss: 3.2410
Iteration: 2098; Percent complete: 52.4%; Average loss: 3.1833
Iteration: 2099; Percent complete: 52.5%; Average loss: 2.9560
Iteration: 2100; Percent complete: 52.5%; Average loss: 3.1563
Iteration: 2101; Percent complete: 52.5%; Average loss: 3.3537
Iteration: 2102; Percent complete: 52.5%; Average loss: 2.9673
Iteration: 2103; Percent complete: 52.6%; Average loss: 3.2382
Iteration: 2104; Percent complete: 52.6%; Average loss: 3.2620
Iteration: 2105; Percent complete: 52.6%; Average loss: 3.2273
Iteration: 2106; Percent complete: 52.6%; Average loss: 3.3076
Iteration: 2107; Percent complete: 52.7%; Average loss: 3.3106
Iteration: 2108; Percent complete: 52.7%; Average loss: 3.0131
Iteration: 2109; Percent complete: 52.7%; Average loss: 3.2840
Iteration: 2110; Percent complete: 52.8%; Average loss: 3.4864
Iteration: 2111; Percent complete: 52.8%; Average loss: 3.2883
Iteration: 2112; Percent complete: 52.8%; Average loss: 3.4005
Iteration: 2113; Percent complete: 52.8%; Average loss: 3.2385
Iteration: 2114; Percent complete: 52.8%; Average loss: 3.1891
Iteration: 2115; Percent complete: 52.9%; Average loss: 2.9677
Iteration: 2116; Percent complete: 52.9%; Average loss: 3.1098
Iteration: 2117; Percent complete: 52.9%; Average loss: 2.8840
Iteration: 2118; Percent complete: 52.9%; Average loss: 3.2036
Iteration: 2119; Percent complete: 53.0%; Average loss: 3.0110
Iteration: 2120; Percent complete: 53.0%; Average loss: 3.2709
Iteration: 2121; Percent complete: 53.0%; Average loss: 3.1163
Iteration: 2122; Percent complete: 53.0%; Average loss: 2.9895
Iteration: 2123; Percent complete: 53.1%; Average loss: 2.8220
Iteration: 2124; Percent complete: 53.1%; Average loss: 3.2575
Iteration: 2125; Percent complete: 53.1%; Average loss: 2.9561
Iteration: 2126; Percent complete: 53.1%; Average loss: 3.3197
Iteration: 2127; Percent complete: 53.2%; Average loss: 3.0627
Iteration: 2128; Percent complete: 53.2%; Average loss: 2.9614
Iteration: 2129; Percent complete: 53.2%; Average loss: 2.9056
Iteration: 2130; Percent complete: 53.2%; Average loss: 3.1445
Iteration: 2131; Percent complete: 53.3%; Average loss: 2.7744
Iteration: 2132; Percent complete: 53.3%; Average loss: 2.9235
Iteration: 2133; Percent complete: 53.3%; Average loss: 3.1485
Iteration: 2134; Percent complete: 53.3%; Average loss: 2.9800
Iteration: 2135; Percent complete: 53.4%; Average loss: 3.1514
Iteration: 2136; Percent complete: 53.4%; Average loss: 3.1167
Iteration: 2137; Percent complete: 53.4%; Average loss: 3.0918
Iteration: 2138; Percent complete: 53.4%; Average loss: 2.9410
Iteration: 2139; Percent complete: 53.5%; Average loss: 3.2131
Iteration: 2140; Percent complete: 53.5%; Average loss: 3.2240
Iteration: 2141; Percent complete: 53.5%; Average loss: 2.9054
Iteration: 2142; Percent complete: 53.5%; Average loss: 3.2246
Iteration: 2143; Percent complete: 53.6%; Average loss: 3.0670
Iteration: 2144; Percent complete: 53.6%; Average loss: 3.0627
Iteration: 2145; Percent complete: 53.6%; Average loss: 3.2054
Iteration: 2146; Percent complete: 53.6%; Average loss: 3.0503
Iteration: 2147; Percent complete: 53.7%; Average loss: 3.1043
Iteration: 2148; Percent complete: 53.7%; Average loss: 3.0593
Iteration: 2149; Percent complete: 53.7%; Average loss: 3.0762
Iteration: 2150; Percent complete: 53.8%; Average loss: 3.2246
Iteration: 2151; Percent complete: 53.8%; Average loss: 3.0608
Iteration: 2152; Percent complete: 53.8%; Average loss: 3.1357
Iteration: 2153; Percent complete: 53.8%; Average loss: 3.0535
Iteration: 2154; Percent complete: 53.8%; Average loss: 3.3894
Iteration: 2155; Percent complete: 53.9%; Average loss: 3.3296
Iteration: 2156; Percent complete: 53.9%; Average loss: 3.3039
Iteration: 2157; Percent complete: 53.9%; Average loss: 3.4348
Iteration: 2158; Percent complete: 53.9%; Average loss: 3.1091
Iteration: 2159; Percent complete: 54.0%; Average loss: 3.3914
Iteration: 2160; Percent complete: 54.0%; Average loss: 3.2130
Iteration: 2161; Percent complete: 54.0%; Average loss: 2.8019
Iteration: 2162; Percent complete: 54.0%; Average loss: 3.2013
Iteration: 2163; Percent complete: 54.1%; Average loss: 2.9476
Iteration: 2164; Percent complete: 54.1%; Average loss: 2.9427
Iteration: 2165; Percent complete: 54.1%; Average loss: 3.1398
Iteration: 2166; Percent complete: 54.1%; Average loss: 2.9246
Iteration: 2167; Percent complete: 54.2%; Average loss: 3.1694
Iteration: 2168; Percent complete: 54.2%; Average loss: 3.4513
Iteration: 2169; Percent complete: 54.2%; Average loss: 2.9841
Iteration: 2170; Percent complete: 54.2%; Average loss: 3.1991
Iteration: 2171; Percent complete: 54.3%; Average loss: 3.0858
Iteration: 2172; Percent complete: 54.3%; Average loss: 3.1161
Iteration: 2173; Percent complete: 54.3%; Average loss: 3.3176
Iteration: 2174; Percent complete: 54.4%; Average loss: 3.1585
Iteration: 2175; Percent complete: 54.4%; Average loss: 2.8255
Iteration: 2176; Percent complete: 54.4%; Average loss: 2.9365
Iteration: 2177; Percent complete: 54.4%; Average loss: 3.0054
Iteration: 2178; Percent complete: 54.4%; Average loss: 3.2178
Iteration: 2179; Percent complete: 54.5%; Average loss: 3.2628
Iteration: 2180; Percent complete: 54.5%; Average loss: 3.1129
Iteration: 2181; Percent complete: 54.5%; Average loss: 3.1002
Iteration: 2182; Percent complete: 54.5%; Average loss: 3.1866
Iteration: 2183; Percent complete: 54.6%; Average loss: 3.3061
Iteration: 2184; Percent complete: 54.6%; Average loss: 3.1616
Iteration: 2185; Percent complete: 54.6%; Average loss: 2.9772
Iteration: 2186; Percent complete: 54.6%; Average loss: 3.1246
Iteration: 2187; Percent complete: 54.7%; Average loss: 3.1846
Iteration: 2188; Percent complete: 54.7%; Average loss: 3.1178
Iteration: 2189; Percent complete: 54.7%; Average loss: 3.1101
Iteration: 2190; Percent complete: 54.8%; Average loss: 3.0056
Iteration: 2191; Percent complete: 54.8%; Average loss: 3.1565
Iteration: 2192; Percent complete: 54.8%; Average loss: 2.9601
Iteration: 2193; Percent complete: 54.8%; Average loss: 2.8791
Iteration: 2194; Percent complete: 54.9%; Average loss: 2.9492
Iteration: 2195; Percent complete: 54.9%; Average loss: 3.1553
Iteration: 2196; Percent complete: 54.9%; Average loss: 2.8387
Iteration: 2197; Percent complete: 54.9%; Average loss: 3.1471
Iteration: 2198; Percent complete: 54.9%; Average loss: 3.2474
Iteration: 2199; Percent complete: 55.0%; Average loss: 3.1561
Iteration: 2200; Percent complete: 55.0%; Average loss: 2.9035
Iteration: 2201; Percent complete: 55.0%; Average loss: 2.9126
Iteration: 2202; Percent complete: 55.0%; Average loss: 3.1476
Iteration: 2203; Percent complete: 55.1%; Average loss: 3.0651
Iteration: 2204; Percent complete: 55.1%; Average loss: 2.9406
Iteration: 2205; Percent complete: 55.1%; Average loss: 3.1232
Iteration: 2206; Percent complete: 55.1%; Average loss: 3.2191
Iteration: 2207; Percent complete: 55.2%; Average loss: 3.1466
Iteration: 2208; Percent complete: 55.2%; Average loss: 3.2559
Iteration: 2209; Percent complete: 55.2%; Average loss: 3.1746
Iteration: 2210; Percent complete: 55.2%; Average loss: 3.0229
Iteration: 2211; Percent complete: 55.3%; Average loss: 2.9698
Iteration: 2212; Percent complete: 55.3%; Average loss: 3.3040
Iteration: 2213; Percent complete: 55.3%; Average loss: 3.1646
Iteration: 2214; Percent complete: 55.4%; Average loss: 2.8767
Iteration: 2215; Percent complete: 55.4%; Average loss: 3.1841
Iteration: 2216; Percent complete: 55.4%; Average loss: 2.8719
Iteration: 2217; Percent complete: 55.4%; Average loss: 3.0137
Iteration: 2218; Percent complete: 55.5%; Average loss: 3.3067
Iteration: 2219; Percent complete: 55.5%; Average loss: 3.0371
Iteration: 2220; Percent complete: 55.5%; Average loss: 3.0511
Iteration: 2221; Percent complete: 55.5%; Average loss: 3.3484
Iteration: 2222; Percent complete: 55.5%; Average loss: 3.2422
Iteration: 2223; Percent complete: 55.6%; Average loss: 3.1122
Iteration: 2224; Percent complete: 55.6%; Average loss: 2.9285
Iteration: 2225; Percent complete: 55.6%; Average loss: 3.0090
Iteration: 2226; Percent complete: 55.6%; Average loss: 3.1387
Iteration: 2227; Percent complete: 55.7%; Average loss: 3.1111
Iteration: 2228; Percent complete: 55.7%; Average loss: 2.9445
Iteration: 2229; Percent complete: 55.7%; Average loss: 3.3006
Iteration: 2230; Percent complete: 55.8%; Average loss: 2.9250
Iteration: 2231; Percent complete: 55.8%; Average loss: 3.2313
Iteration: 2232; Percent complete: 55.8%; Average loss: 2.8838
Iteration: 2233; Percent complete: 55.8%; Average loss: 2.9440
Iteration: 2234; Percent complete: 55.9%; Average loss: 2.9531
Iteration: 2235; Percent complete: 55.9%; Average loss: 3.0496
Iteration: 2236; Percent complete: 55.9%; Average loss: 3.1531
Iteration: 2237; Percent complete: 55.9%; Average loss: 2.9759
Iteration: 2238; Percent complete: 56.0%; Average loss: 2.8456
Iteration: 2239; Percent complete: 56.0%; Average loss: 3.0397
Iteration: 2240; Percent complete: 56.0%; Average loss: 3.2976
Iteration: 2241; Percent complete: 56.0%; Average loss: 3.0014
Iteration: 2242; Percent complete: 56.0%; Average loss: 3.0820
Iteration: 2243; Percent complete: 56.1%; Average loss: 3.0847
Iteration: 2244; Percent complete: 56.1%; Average loss: 2.9996
Iteration: 2245; Percent complete: 56.1%; Average loss: 2.9837
Iteration: 2246; Percent complete: 56.1%; Average loss: 3.2074
Iteration: 2247; Percent complete: 56.2%; Average loss: 3.4474
Iteration: 2248; Percent complete: 56.2%; Average loss: 3.1624
Iteration: 2249; Percent complete: 56.2%; Average loss: 3.1716
Iteration: 2250; Percent complete: 56.2%; Average loss: 3.0650
Iteration: 2251; Percent complete: 56.3%; Average loss: 3.0765
Iteration: 2252; Percent complete: 56.3%; Average loss: 3.2249
Iteration: 2253; Percent complete: 56.3%; Average loss: 3.0901
Iteration: 2254; Percent complete: 56.4%; Average loss: 3.0172
Iteration: 2255; Percent complete: 56.4%; Average loss: 3.1972
Iteration: 2256; Percent complete: 56.4%; Average loss: 3.3846
Iteration: 2257; Percent complete: 56.4%; Average loss: 2.9470
Iteration: 2258; Percent complete: 56.5%; Average loss: 3.4132
Iteration: 2259; Percent complete: 56.5%; Average loss: 3.0813
Iteration: 2260; Percent complete: 56.5%; Average loss: 3.0478
Iteration: 2261; Percent complete: 56.5%; Average loss: 3.1148
Iteration: 2262; Percent complete: 56.5%; Average loss: 3.2391
Iteration: 2263; Percent complete: 56.6%; Average loss: 3.2856
Iteration: 2264; Percent complete: 56.6%; Average loss: 2.9680
Iteration: 2265; Percent complete: 56.6%; Average loss: 3.2485
Iteration: 2266; Percent complete: 56.6%; Average loss: 2.8832
Iteration: 2267; Percent complete: 56.7%; Average loss: 3.2106
Iteration: 2268; Percent complete: 56.7%; Average loss: 2.9153
Iteration: 2269; Percent complete: 56.7%; Average loss: 3.2974
Iteration: 2270; Percent complete: 56.8%; Average loss: 2.8517
Iteration: 2271; Percent complete: 56.8%; Average loss: 3.3728
Iteration: 2272; Percent complete: 56.8%; Average loss: 3.4709
Iteration: 2273; Percent complete: 56.8%; Average loss: 3.2637
Iteration: 2274; Percent complete: 56.9%; Average loss: 3.1683
Iteration: 2275; Percent complete: 56.9%; Average loss: 3.1402
Iteration: 2276; Percent complete: 56.9%; Average loss: 3.1166
Iteration: 2277; Percent complete: 56.9%; Average loss: 3.1568
Iteration: 2278; Percent complete: 57.0%; Average loss: 2.9959
Iteration: 2279; Percent complete: 57.0%; Average loss: 3.0282
Iteration: 2280; Percent complete: 57.0%; Average loss: 3.1700
Iteration: 2281; Percent complete: 57.0%; Average loss: 3.2971
Iteration: 2282; Percent complete: 57.0%; Average loss: 2.9529
Iteration: 2283; Percent complete: 57.1%; Average loss: 2.9907
Iteration: 2284; Percent complete: 57.1%; Average loss: 3.1973
Iteration: 2285; Percent complete: 57.1%; Average loss: 3.1242
Iteration: 2286; Percent complete: 57.1%; Average loss: 3.1663
Iteration: 2287; Percent complete: 57.2%; Average loss: 3.1531
Iteration: 2288; Percent complete: 57.2%; Average loss: 3.0373
Iteration: 2289; Percent complete: 57.2%; Average loss: 2.9571
Iteration: 2290; Percent complete: 57.2%; Average loss: 3.0114
Iteration: 2291; Percent complete: 57.3%; Average loss: 3.1018
Iteration: 2292; Percent complete: 57.3%; Average loss: 3.2074
Iteration: 2293; Percent complete: 57.3%; Average loss: 2.9726
Iteration: 2294; Percent complete: 57.4%; Average loss: 3.1561
Iteration: 2295; Percent complete: 57.4%; Average loss: 3.1122
Iteration: 2296; Percent complete: 57.4%; Average loss: 3.1633
Iteration: 2297; Percent complete: 57.4%; Average loss: 2.9655
Iteration: 2298; Percent complete: 57.5%; Average loss: 2.8682
Iteration: 2299; Percent complete: 57.5%; Average loss: 3.1086
Iteration: 2300; Percent complete: 57.5%; Average loss: 3.2204
Iteration: 2301; Percent complete: 57.5%; Average loss: 3.1759
Iteration: 2302; Percent complete: 57.6%; Average loss: 2.9884
Iteration: 2303; Percent complete: 57.6%; Average loss: 3.2419
Iteration: 2304; Percent complete: 57.6%; Average loss: 3.0212
Iteration: 2305; Percent complete: 57.6%; Average loss: 3.1073
Iteration: 2306; Percent complete: 57.6%; Average loss: 3.0212
Iteration: 2307; Percent complete: 57.7%; Average loss: 2.7597
Iteration: 2308; Percent complete: 57.7%; Average loss: 3.2904
Iteration: 2309; Percent complete: 57.7%; Average loss: 3.0951
Iteration: 2310; Percent complete: 57.8%; Average loss: 3.1117
Iteration: 2311; Percent complete: 57.8%; Average loss: 2.8359
Iteration: 2312; Percent complete: 57.8%; Average loss: 2.8868
Iteration: 2313; Percent complete: 57.8%; Average loss: 2.9131
Iteration: 2314; Percent complete: 57.9%; Average loss: 2.9432
Iteration: 2315; Percent complete: 57.9%; Average loss: 2.9631
Iteration: 2316; Percent complete: 57.9%; Average loss: 2.8315
Iteration: 2317; Percent complete: 57.9%; Average loss: 3.1313
Iteration: 2318; Percent complete: 58.0%; Average loss: 3.0795
Iteration: 2319; Percent complete: 58.0%; Average loss: 3.1662
Iteration: 2320; Percent complete: 58.0%; Average loss: 3.1227
Iteration: 2321; Percent complete: 58.0%; Average loss: 3.2228
Iteration: 2322; Percent complete: 58.1%; Average loss: 2.8589
Iteration: 2323; Percent complete: 58.1%; Average loss: 3.0864
Iteration: 2324; Percent complete: 58.1%; Average loss: 3.1471
Iteration: 2325; Percent complete: 58.1%; Average loss: 3.1048
Iteration: 2326; Percent complete: 58.1%; Average loss: 3.0815
Iteration: 2327; Percent complete: 58.2%; Average loss: 3.2158
Iteration: 2328; Percent complete: 58.2%; Average loss: 3.1665
Iteration: 2329; Percent complete: 58.2%; Average loss: 3.2231
Iteration: 2330; Percent complete: 58.2%; Average loss: 3.0141
Iteration: 2331; Percent complete: 58.3%; Average loss: 3.2529
Iteration: 2332; Percent complete: 58.3%; Average loss: 2.9499
Iteration: 2333; Percent complete: 58.3%; Average loss: 2.9502
Iteration: 2334; Percent complete: 58.4%; Average loss: 3.2439
Iteration: 2335; Percent complete: 58.4%; Average loss: 3.2356
Iteration: 2336; Percent complete: 58.4%; Average loss: 3.2214
Iteration: 2337; Percent complete: 58.4%; Average loss: 3.1328
Iteration: 2338; Percent complete: 58.5%; Average loss: 3.0529
Iteration: 2339; Percent complete: 58.5%; Average loss: 2.7721
Iteration: 2340; Percent complete: 58.5%; Average loss: 2.9613
Iteration: 2341; Percent complete: 58.5%; Average loss: 3.0709
Iteration: 2342; Percent complete: 58.6%; Average loss: 3.0007
Iteration: 2343; Percent complete: 58.6%; Average loss: 3.4009
Iteration: 2344; Percent complete: 58.6%; Average loss: 3.1364
Iteration: 2345; Percent complete: 58.6%; Average loss: 3.1233
Iteration: 2346; Percent complete: 58.7%; Average loss: 3.0902
Iteration: 2347; Percent complete: 58.7%; Average loss: 2.9090
Iteration: 2348; Percent complete: 58.7%; Average loss: 3.0342
Iteration: 2349; Percent complete: 58.7%; Average loss: 3.3858
Iteration: 2350; Percent complete: 58.8%; Average loss: 3.1725
Iteration: 2351; Percent complete: 58.8%; Average loss: 3.0437
Iteration: 2352; Percent complete: 58.8%; Average loss: 3.1224
Iteration: 2353; Percent complete: 58.8%; Average loss: 3.1245
Iteration: 2354; Percent complete: 58.9%; Average loss: 2.7404
Iteration: 2355; Percent complete: 58.9%; Average loss: 3.1437
Iteration: 2356; Percent complete: 58.9%; Average loss: 3.2438
Iteration: 2357; Percent complete: 58.9%; Average loss: 3.0121
Iteration: 2358; Percent complete: 59.0%; Average loss: 3.0273
Iteration: 2359; Percent complete: 59.0%; Average loss: 3.0112
Iteration: 2360; Percent complete: 59.0%; Average loss: 2.8888
Iteration: 2361; Percent complete: 59.0%; Average loss: 3.0330
Iteration: 2362; Percent complete: 59.1%; Average loss: 2.9521
Iteration: 2363; Percent complete: 59.1%; Average loss: 3.0572
Iteration: 2364; Percent complete: 59.1%; Average loss: 2.9980
Iteration: 2365; Percent complete: 59.1%; Average loss: 2.8912
Iteration: 2366; Percent complete: 59.2%; Average loss: 2.9751
Iteration: 2367; Percent complete: 59.2%; Average loss: 3.2970
Iteration: 2368; Percent complete: 59.2%; Average loss: 3.1946
Iteration: 2369; Percent complete: 59.2%; Average loss: 2.9045
Iteration: 2370; Percent complete: 59.2%; Average loss: 3.4196
Iteration: 2371; Percent complete: 59.3%; Average loss: 3.0701
Iteration: 2372; Percent complete: 59.3%; Average loss: 3.3721
Iteration: 2373; Percent complete: 59.3%; Average loss: 2.8926
Iteration: 2374; Percent complete: 59.4%; Average loss: 3.1241
Iteration: 2375; Percent complete: 59.4%; Average loss: 3.0384
Iteration: 2376; Percent complete: 59.4%; Average loss: 3.2218
Iteration: 2377; Percent complete: 59.4%; Average loss: 3.0597
Iteration: 2378; Percent complete: 59.5%; Average loss: 3.1601
Iteration: 2379; Percent complete: 59.5%; Average loss: 3.1307
Iteration: 2380; Percent complete: 59.5%; Average loss: 2.8887
Iteration: 2381; Percent complete: 59.5%; Average loss: 3.2588
Iteration: 2382; Percent complete: 59.6%; Average loss: 3.0041
Iteration: 2383; Percent complete: 59.6%; Average loss: 3.0006
Iteration: 2384; Percent complete: 59.6%; Average loss: 2.8410
Iteration: 2385; Percent complete: 59.6%; Average loss: 3.1281
Iteration: 2386; Percent complete: 59.7%; Average loss: 3.1199
Iteration: 2387; Percent complete: 59.7%; Average loss: 3.2016
Iteration: 2388; Percent complete: 59.7%; Average loss: 2.9501
Iteration: 2389; Percent complete: 59.7%; Average loss: 3.0883
Iteration: 2390; Percent complete: 59.8%; Average loss: 3.1099
Iteration: 2391; Percent complete: 59.8%; Average loss: 3.0261
Iteration: 2392; Percent complete: 59.8%; Average loss: 2.9515
Iteration: 2393; Percent complete: 59.8%; Average loss: 3.0353
Iteration: 2394; Percent complete: 59.9%; Average loss: 3.0927
Iteration: 2395; Percent complete: 59.9%; Average loss: 3.0133
Iteration: 2396; Percent complete: 59.9%; Average loss: 2.9730
Iteration: 2397; Percent complete: 59.9%; Average loss: 3.2592
Iteration: 2398; Percent complete: 60.0%; Average loss: 2.8194
Iteration: 2399; Percent complete: 60.0%; Average loss: 2.8685
Iteration: 2400; Percent complete: 60.0%; Average loss: 3.1976
Iteration: 2401; Percent complete: 60.0%; Average loss: 2.9810
Iteration: 2402; Percent complete: 60.1%; Average loss: 3.0638
Iteration: 2403; Percent complete: 60.1%; Average loss: 2.9733
Iteration: 2404; Percent complete: 60.1%; Average loss: 3.0744
Iteration: 2405; Percent complete: 60.1%; Average loss: 3.0599
Iteration: 2406; Percent complete: 60.2%; Average loss: 3.1011
Iteration: 2407; Percent complete: 60.2%; Average loss: 2.8933
Iteration: 2408; Percent complete: 60.2%; Average loss: 3.0949
Iteration: 2409; Percent complete: 60.2%; Average loss: 2.8902
Iteration: 2410; Percent complete: 60.2%; Average loss: 2.9410
Iteration: 2411; Percent complete: 60.3%; Average loss: 3.1055
Iteration: 2412; Percent complete: 60.3%; Average loss: 2.9914
Iteration: 2413; Percent complete: 60.3%; Average loss: 3.1066
Iteration: 2414; Percent complete: 60.4%; Average loss: 3.2094
Iteration: 2415; Percent complete: 60.4%; Average loss: 2.8322
Iteration: 2416; Percent complete: 60.4%; Average loss: 3.0028
Iteration: 2417; Percent complete: 60.4%; Average loss: 3.1487
Iteration: 2418; Percent complete: 60.5%; Average loss: 3.1136
Iteration: 2419; Percent complete: 60.5%; Average loss: 3.0790
Iteration: 2420; Percent complete: 60.5%; Average loss: 2.8786
Iteration: 2421; Percent complete: 60.5%; Average loss: 2.9155
Iteration: 2422; Percent complete: 60.6%; Average loss: 2.8894
Iteration: 2423; Percent complete: 60.6%; Average loss: 2.9949
Iteration: 2424; Percent complete: 60.6%; Average loss: 3.1366
Iteration: 2425; Percent complete: 60.6%; Average loss: 2.9274
Iteration: 2426; Percent complete: 60.7%; Average loss: 3.1176
Iteration: 2427; Percent complete: 60.7%; Average loss: 3.0860
Iteration: 2428; Percent complete: 60.7%; Average loss: 2.7938
Iteration: 2429; Percent complete: 60.7%; Average loss: 2.9811
Iteration: 2430; Percent complete: 60.8%; Average loss: 2.9621
Iteration: 2431; Percent complete: 60.8%; Average loss: 3.1894
Iteration: 2432; Percent complete: 60.8%; Average loss: 3.1627
Iteration: 2433; Percent complete: 60.8%; Average loss: 3.0004
Iteration: 2434; Percent complete: 60.9%; Average loss: 2.9945
Iteration: 2435; Percent complete: 60.9%; Average loss: 2.9241
Iteration: 2436; Percent complete: 60.9%; Average loss: 3.0096
Iteration: 2437; Percent complete: 60.9%; Average loss: 3.2964
Iteration: 2438; Percent complete: 61.0%; Average loss: 2.9902
Iteration: 2439; Percent complete: 61.0%; Average loss: 2.9527
Iteration: 2440; Percent complete: 61.0%; Average loss: 3.0485
Iteration: 2441; Percent complete: 61.0%; Average loss: 2.8999
Iteration: 2442; Percent complete: 61.1%; Average loss: 2.9495
Iteration: 2443; Percent complete: 61.1%; Average loss: 3.0901
Iteration: 2444; Percent complete: 61.1%; Average loss: 3.0211
Iteration: 2445; Percent complete: 61.1%; Average loss: 3.1896
Iteration: 2446; Percent complete: 61.2%; Average loss: 2.8791
Iteration: 2447; Percent complete: 61.2%; Average loss: 3.1565
Iteration: 2448; Percent complete: 61.2%; Average loss: 3.1074
Iteration: 2449; Percent complete: 61.2%; Average loss: 3.4186
Iteration: 2450; Percent complete: 61.3%; Average loss: 3.1579
Iteration: 2451; Percent complete: 61.3%; Average loss: 2.9871
Iteration: 2452; Percent complete: 61.3%; Average loss: 3.0753
Iteration: 2453; Percent complete: 61.3%; Average loss: 3.0467
Iteration: 2454; Percent complete: 61.4%; Average loss: 3.2476
Iteration: 2455; Percent complete: 61.4%; Average loss: 3.0091
Iteration: 2456; Percent complete: 61.4%; Average loss: 2.9467
Iteration: 2457; Percent complete: 61.4%; Average loss: 3.0247
Iteration: 2458; Percent complete: 61.5%; Average loss: 2.9012
Iteration: 2459; Percent complete: 61.5%; Average loss: 2.9739
Iteration: 2460; Percent complete: 61.5%; Average loss: 3.2009
Iteration: 2461; Percent complete: 61.5%; Average loss: 2.9979
Iteration: 2462; Percent complete: 61.6%; Average loss: 3.1020
Iteration: 2463; Percent complete: 61.6%; Average loss: 3.1805
Iteration: 2464; Percent complete: 61.6%; Average loss: 2.8591
Iteration: 2465; Percent complete: 61.6%; Average loss: 2.8740
Iteration: 2466; Percent complete: 61.7%; Average loss: 3.1289
Iteration: 2467; Percent complete: 61.7%; Average loss: 2.8646
Iteration: 2468; Percent complete: 61.7%; Average loss: 2.8958
Iteration: 2469; Percent complete: 61.7%; Average loss: 3.1335
Iteration: 2470; Percent complete: 61.8%; Average loss: 2.9966
Iteration: 2471; Percent complete: 61.8%; Average loss: 2.9861
Iteration: 2472; Percent complete: 61.8%; Average loss: 3.0842
Iteration: 2473; Percent complete: 61.8%; Average loss: 2.9325
Iteration: 2474; Percent complete: 61.9%; Average loss: 2.9143
Iteration: 2475; Percent complete: 61.9%; Average loss: 3.0073
Iteration: 2476; Percent complete: 61.9%; Average loss: 2.9462
Iteration: 2477; Percent complete: 61.9%; Average loss: 2.8441
Iteration: 2478; Percent complete: 62.0%; Average loss: 3.3323
Iteration: 2479; Percent complete: 62.0%; Average loss: 2.9632
Iteration: 2480; Percent complete: 62.0%; Average loss: 3.1820
Iteration: 2481; Percent complete: 62.0%; Average loss: 2.6469
Iteration: 2482; Percent complete: 62.1%; Average loss: 3.1154
Iteration: 2483; Percent complete: 62.1%; Average loss: 3.0054
Iteration: 2484; Percent complete: 62.1%; Average loss: 3.1167
Iteration: 2485; Percent complete: 62.1%; Average loss: 2.9941
Iteration: 2486; Percent complete: 62.2%; Average loss: 3.3289
Iteration: 2487; Percent complete: 62.2%; Average loss: 2.9214
Iteration: 2488; Percent complete: 62.2%; Average loss: 2.9341
Iteration: 2489; Percent complete: 62.2%; Average loss: 3.0584
Iteration: 2490; Percent complete: 62.3%; Average loss: 2.9539
Iteration: 2491; Percent complete: 62.3%; Average loss: 3.1737
Iteration: 2492; Percent complete: 62.3%; Average loss: 3.0041
Iteration: 2493; Percent complete: 62.3%; Average loss: 3.0037
Iteration: 2494; Percent complete: 62.4%; Average loss: 3.2213
Iteration: 2495; Percent complete: 62.4%; Average loss: 3.2341
Iteration: 2496; Percent complete: 62.4%; Average loss: 3.1597
Iteration: 2497; Percent complete: 62.4%; Average loss: 2.9201
Iteration: 2498; Percent complete: 62.5%; Average loss: 2.8501
Iteration: 2499; Percent complete: 62.5%; Average loss: 2.9597
Iteration: 2500; Percent complete: 62.5%; Average loss: 2.9183
Iteration: 2501; Percent complete: 62.5%; Average loss: 3.2740
Iteration: 2502; Percent complete: 62.5%; Average loss: 3.0823
Iteration: 2503; Percent complete: 62.6%; Average loss: 3.0290
Iteration: 2504; Percent complete: 62.6%; Average loss: 2.9310
Iteration: 2505; Percent complete: 62.6%; Average loss: 3.0071
Iteration: 2506; Percent complete: 62.6%; Average loss: 2.9145
Iteration: 2507; Percent complete: 62.7%; Average loss: 2.7839
Iteration: 2508; Percent complete: 62.7%; Average loss: 3.0654
Iteration: 2509; Percent complete: 62.7%; Average loss: 3.2784
Iteration: 2510; Percent complete: 62.7%; Average loss: 2.9003
Iteration: 2511; Percent complete: 62.8%; Average loss: 3.0582
Iteration: 2512; Percent complete: 62.8%; Average loss: 3.0528
Iteration: 2513; Percent complete: 62.8%; Average loss: 3.4254
Iteration: 2514; Percent complete: 62.8%; Average loss: 2.9577
Iteration: 2515; Percent complete: 62.9%; Average loss: 3.0702
Iteration: 2516; Percent complete: 62.9%; Average loss: 2.9743
Iteration: 2517; Percent complete: 62.9%; Average loss: 3.0506
Iteration: 2518; Percent complete: 62.9%; Average loss: 2.9568
Iteration: 2519; Percent complete: 63.0%; Average loss: 2.7954
Iteration: 2520; Percent complete: 63.0%; Average loss: 2.5037
Iteration: 2521; Percent complete: 63.0%; Average loss: 3.0958
Iteration: 2522; Percent complete: 63.0%; Average loss: 2.8539
Iteration: 2523; Percent complete: 63.1%; Average loss: 3.0180
Iteration: 2524; Percent complete: 63.1%; Average loss: 3.0427
Iteration: 2525; Percent complete: 63.1%; Average loss: 3.2436
Iteration: 2526; Percent complete: 63.1%; Average loss: 3.2097
Iteration: 2527; Percent complete: 63.2%; Average loss: 2.8462
Iteration: 2528; Percent complete: 63.2%; Average loss: 3.2655
Iteration: 2529; Percent complete: 63.2%; Average loss: 2.8970
Iteration: 2530; Percent complete: 63.2%; Average loss: 3.0226
Iteration: 2531; Percent complete: 63.3%; Average loss: 2.8780
Iteration: 2532; Percent complete: 63.3%; Average loss: 3.3004
Iteration: 2533; Percent complete: 63.3%; Average loss: 3.1440
Iteration: 2534; Percent complete: 63.3%; Average loss: 3.0814
Iteration: 2535; Percent complete: 63.4%; Average loss: 3.1218
Iteration: 2536; Percent complete: 63.4%; Average loss: 3.1315
Iteration: 2537; Percent complete: 63.4%; Average loss: 2.9232
Iteration: 2538; Percent complete: 63.4%; Average loss: 2.8684
Iteration: 2539; Percent complete: 63.5%; Average loss: 2.9485
Iteration: 2540; Percent complete: 63.5%; Average loss: 3.0483
Iteration: 2541; Percent complete: 63.5%; Average loss: 2.9017
Iteration: 2542; Percent complete: 63.5%; Average loss: 3.2824
Iteration: 2543; Percent complete: 63.6%; Average loss: 2.9286
Iteration: 2544; Percent complete: 63.6%; Average loss: 3.0823
Iteration: 2545; Percent complete: 63.6%; Average loss: 3.1103
Iteration: 2546; Percent complete: 63.6%; Average loss: 3.1722
Iteration: 2547; Percent complete: 63.7%; Average loss: 3.0119
Iteration: 2548; Percent complete: 63.7%; Average loss: 3.0489
Iteration: 2549; Percent complete: 63.7%; Average loss: 2.7897
Iteration: 2550; Percent complete: 63.7%; Average loss: 3.0870
Iteration: 2551; Percent complete: 63.8%; Average loss: 2.9866
Iteration: 2552; Percent complete: 63.8%; Average loss: 2.9566
Iteration: 2553; Percent complete: 63.8%; Average loss: 3.0693
Iteration: 2554; Percent complete: 63.8%; Average loss: 3.0184
Iteration: 2555; Percent complete: 63.9%; Average loss: 3.0440
Iteration: 2556; Percent complete: 63.9%; Average loss: 3.0046
Iteration: 2557; Percent complete: 63.9%; Average loss: 3.1953
Iteration: 2558; Percent complete: 63.9%; Average loss: 3.2769
Iteration: 2559; Percent complete: 64.0%; Average loss: 3.0863
Iteration: 2560; Percent complete: 64.0%; Average loss: 3.1346
Iteration: 2561; Percent complete: 64.0%; Average loss: 3.0649
Iteration: 2562; Percent complete: 64.0%; Average loss: 2.9306
Iteration: 2563; Percent complete: 64.1%; Average loss: 2.9918
Iteration: 2564; Percent complete: 64.1%; Average loss: 3.2307
Iteration: 2565; Percent complete: 64.1%; Average loss: 2.9998
Iteration: 2566; Percent complete: 64.1%; Average loss: 3.0457
Iteration: 2567; Percent complete: 64.2%; Average loss: 2.7984
Iteration: 2568; Percent complete: 64.2%; Average loss: 2.8487
Iteration: 2569; Percent complete: 64.2%; Average loss: 2.9064
Iteration: 2570; Percent complete: 64.2%; Average loss: 3.0951
Iteration: 2571; Percent complete: 64.3%; Average loss: 3.0599
Iteration: 2572; Percent complete: 64.3%; Average loss: 2.9704
Iteration: 2573; Percent complete: 64.3%; Average loss: 2.7340
Iteration: 2574; Percent complete: 64.3%; Average loss: 2.8847
Iteration: 2575; Percent complete: 64.4%; Average loss: 3.0765
Iteration: 2576; Percent complete: 64.4%; Average loss: 3.0623
Iteration: 2577; Percent complete: 64.4%; Average loss: 3.5018
Iteration: 2578; Percent complete: 64.5%; Average loss: 3.0526
Iteration: 2579; Percent complete: 64.5%; Average loss: 3.2973
Iteration: 2580; Percent complete: 64.5%; Average loss: 2.9863
Iteration: 2581; Percent complete: 64.5%; Average loss: 3.2647
Iteration: 2582; Percent complete: 64.5%; Average loss: 3.0383
Iteration: 2583; Percent complete: 64.6%; Average loss: 3.1173
Iteration: 2584; Percent complete: 64.6%; Average loss: 2.9709
Iteration: 2585; Percent complete: 64.6%; Average loss: 3.0725
Iteration: 2586; Percent complete: 64.6%; Average loss: 2.9644
Iteration: 2587; Percent complete: 64.7%; Average loss: 2.9838
Iteration: 2588; Percent complete: 64.7%; Average loss: 2.8758
Iteration: 2589; Percent complete: 64.7%; Average loss: 2.8667
Iteration: 2590; Percent complete: 64.8%; Average loss: 2.9940
Iteration: 2591; Percent complete: 64.8%; Average loss: 2.9165
Iteration: 2592; Percent complete: 64.8%; Average loss: 3.0146
Iteration: 2593; Percent complete: 64.8%; Average loss: 3.1150
Iteration: 2594; Percent complete: 64.8%; Average loss: 3.3044
Iteration: 2595; Percent complete: 64.9%; Average loss: 2.9242
Iteration: 2596; Percent complete: 64.9%; Average loss: 2.9431
Iteration: 2597; Percent complete: 64.9%; Average loss: 3.1833
Iteration: 2598; Percent complete: 65.0%; Average loss: 2.8571
Iteration: 2599; Percent complete: 65.0%; Average loss: 2.8761
Iteration: 2600; Percent complete: 65.0%; Average loss: 3.0111
Iteration: 2601; Percent complete: 65.0%; Average loss: 2.7766
Iteration: 2602; Percent complete: 65.0%; Average loss: 2.9687
Iteration: 2603; Percent complete: 65.1%; Average loss: 3.1023
Iteration: 2604; Percent complete: 65.1%; Average loss: 2.6160
Iteration: 2605; Percent complete: 65.1%; Average loss: 3.0536
Iteration: 2606; Percent complete: 65.1%; Average loss: 2.8985
Iteration: 2607; Percent complete: 65.2%; Average loss: 3.1014
Iteration: 2608; Percent complete: 65.2%; Average loss: 3.0940
Iteration: 2609; Percent complete: 65.2%; Average loss: 2.8279
Iteration: 2610; Percent complete: 65.2%; Average loss: 2.7030
Iteration: 2611; Percent complete: 65.3%; Average loss: 2.9758
Iteration: 2612; Percent complete: 65.3%; Average loss: 3.0122
Iteration: 2613; Percent complete: 65.3%; Average loss: 2.9703
Iteration: 2614; Percent complete: 65.3%; Average loss: 2.9237
Iteration: 2615; Percent complete: 65.4%; Average loss: 2.9687
Iteration: 2616; Percent complete: 65.4%; Average loss: 2.9093
Iteration: 2617; Percent complete: 65.4%; Average loss: 3.0957
Iteration: 2618; Percent complete: 65.5%; Average loss: 2.8774
Iteration: 2619; Percent complete: 65.5%; Average loss: 2.8620
Iteration: 2620; Percent complete: 65.5%; Average loss: 2.9461
Iteration: 2621; Percent complete: 65.5%; Average loss: 2.8189
Iteration: 2622; Percent complete: 65.5%; Average loss: 2.9598
Iteration: 2623; Percent complete: 65.6%; Average loss: 2.9346
Iteration: 2624; Percent complete: 65.6%; Average loss: 3.2517
Iteration: 2625; Percent complete: 65.6%; Average loss: 2.9234
Iteration: 2626; Percent complete: 65.6%; Average loss: 3.0442
Iteration: 2627; Percent complete: 65.7%; Average loss: 2.8944
Iteration: 2628; Percent complete: 65.7%; Average loss: 2.7898
Iteration: 2629; Percent complete: 65.7%; Average loss: 2.7518
Iteration: 2630; Percent complete: 65.8%; Average loss: 3.0938
Iteration: 2631; Percent complete: 65.8%; Average loss: 2.7649
Iteration: 2632; Percent complete: 65.8%; Average loss: 2.9861
Iteration: 2633; Percent complete: 65.8%; Average loss: 2.8905
Iteration: 2634; Percent complete: 65.8%; Average loss: 2.5952
Iteration: 2635; Percent complete: 65.9%; Average loss: 2.8756
Iteration: 2636; Percent complete: 65.9%; Average loss: 2.8716
Iteration: 2637; Percent complete: 65.9%; Average loss: 3.0535
Iteration: 2638; Percent complete: 66.0%; Average loss: 2.9625
Iteration: 2639; Percent complete: 66.0%; Average loss: 2.9717
Iteration: 2640; Percent complete: 66.0%; Average loss: 2.9757
Iteration: 2641; Percent complete: 66.0%; Average loss: 3.0071
Iteration: 2642; Percent complete: 66.0%; Average loss: 2.8444
Iteration: 2643; Percent complete: 66.1%; Average loss: 2.9163
Iteration: 2644; Percent complete: 66.1%; Average loss: 3.0189
Iteration: 2645; Percent complete: 66.1%; Average loss: 3.0306
Iteration: 2646; Percent complete: 66.1%; Average loss: 3.0543
Iteration: 2647; Percent complete: 66.2%; Average loss: 3.0204
Iteration: 2648; Percent complete: 66.2%; Average loss: 3.0640
Iteration: 2649; Percent complete: 66.2%; Average loss: 3.1099
Iteration: 2650; Percent complete: 66.2%; Average loss: 3.1587
Iteration: 2651; Percent complete: 66.3%; Average loss: 3.0683
Iteration: 2652; Percent complete: 66.3%; Average loss: 2.9645
Iteration: 2653; Percent complete: 66.3%; Average loss: 2.8370
Iteration: 2654; Percent complete: 66.3%; Average loss: 2.8616
Iteration: 2655; Percent complete: 66.4%; Average loss: 2.9107
Iteration: 2656; Percent complete: 66.4%; Average loss: 2.8261
Iteration: 2657; Percent complete: 66.4%; Average loss: 3.0864
Iteration: 2658; Percent complete: 66.5%; Average loss: 3.0036
Iteration: 2659; Percent complete: 66.5%; Average loss: 3.1892
Iteration: 2660; Percent complete: 66.5%; Average loss: 2.9358
Iteration: 2661; Percent complete: 66.5%; Average loss: 2.8743
Iteration: 2662; Percent complete: 66.5%; Average loss: 2.9145
Iteration: 2663; Percent complete: 66.6%; Average loss: 2.9675
Iteration: 2664; Percent complete: 66.6%; Average loss: 3.0101
Iteration: 2665; Percent complete: 66.6%; Average loss: 3.0819
Iteration: 2666; Percent complete: 66.6%; Average loss: 3.0430
Iteration: 2667; Percent complete: 66.7%; Average loss: 3.1648
Iteration: 2668; Percent complete: 66.7%; Average loss: 2.6881
Iteration: 2669; Percent complete: 66.7%; Average loss: 2.9969
Iteration: 2670; Percent complete: 66.8%; Average loss: 3.0859
Iteration: 2671; Percent complete: 66.8%; Average loss: 2.9756
Iteration: 2672; Percent complete: 66.8%; Average loss: 2.9932
Iteration: 2673; Percent complete: 66.8%; Average loss: 2.9672
Iteration: 2674; Percent complete: 66.8%; Average loss: 3.1559
Iteration: 2675; Percent complete: 66.9%; Average loss: 2.8119
Iteration: 2676; Percent complete: 66.9%; Average loss: 2.7983
Iteration: 2677; Percent complete: 66.9%; Average loss: 2.9670
Iteration: 2678; Percent complete: 67.0%; Average loss: 2.8790
Iteration: 2679; Percent complete: 67.0%; Average loss: 2.7970
Iteration: 2680; Percent complete: 67.0%; Average loss: 2.8400
Iteration: 2681; Percent complete: 67.0%; Average loss: 2.9722
Iteration: 2682; Percent complete: 67.0%; Average loss: 3.0635
Iteration: 2683; Percent complete: 67.1%; Average loss: 3.1305
Iteration: 2684; Percent complete: 67.1%; Average loss: 2.9739
Iteration: 2685; Percent complete: 67.1%; Average loss: 2.7942
Iteration: 2686; Percent complete: 67.2%; Average loss: 2.8884
Iteration: 2687; Percent complete: 67.2%; Average loss: 3.1346
Iteration: 2688; Percent complete: 67.2%; Average loss: 2.7545
Iteration: 2689; Percent complete: 67.2%; Average loss: 2.9450
Iteration: 2690; Percent complete: 67.2%; Average loss: 2.7335
Iteration: 2691; Percent complete: 67.3%; Average loss: 2.8841
Iteration: 2692; Percent complete: 67.3%; Average loss: 3.2128
Iteration: 2693; Percent complete: 67.3%; Average loss: 2.8642
Iteration: 2694; Percent complete: 67.3%; Average loss: 2.8929
Iteration: 2695; Percent complete: 67.4%; Average loss: 3.0185
Iteration: 2696; Percent complete: 67.4%; Average loss: 2.8266
Iteration: 2697; Percent complete: 67.4%; Average loss: 2.8563
Iteration: 2698; Percent complete: 67.5%; Average loss: 2.8544
Iteration: 2699; Percent complete: 67.5%; Average loss: 3.0885
Iteration: 2700; Percent complete: 67.5%; Average loss: 2.9875
Iteration: 2701; Percent complete: 67.5%; Average loss: 3.3414
Iteration: 2702; Percent complete: 67.5%; Average loss: 3.1434
Iteration: 2703; Percent complete: 67.6%; Average loss: 3.0942
Iteration: 2704; Percent complete: 67.6%; Average loss: 2.9475
Iteration: 2705; Percent complete: 67.6%; Average loss: 2.8844
Iteration: 2706; Percent complete: 67.7%; Average loss: 3.0038
Iteration: 2707; Percent complete: 67.7%; Average loss: 2.9268
Iteration: 2708; Percent complete: 67.7%; Average loss: 3.1496
Iteration: 2709; Percent complete: 67.7%; Average loss: 2.7641
Iteration: 2710; Percent complete: 67.8%; Average loss: 3.1480
Iteration: 2711; Percent complete: 67.8%; Average loss: 2.7447
Iteration: 2712; Percent complete: 67.8%; Average loss: 2.9242
Iteration: 2713; Percent complete: 67.8%; Average loss: 2.8552
Iteration: 2714; Percent complete: 67.8%; Average loss: 3.0703
Iteration: 2715; Percent complete: 67.9%; Average loss: 2.9561
Iteration: 2716; Percent complete: 67.9%; Average loss: 2.8416
Iteration: 2717; Percent complete: 67.9%; Average loss: 2.9149
Iteration: 2718; Percent complete: 68.0%; Average loss: 2.9417
Iteration: 2719; Percent complete: 68.0%; Average loss: 2.7774
Iteration: 2720; Percent complete: 68.0%; Average loss: 2.9809
Iteration: 2721; Percent complete: 68.0%; Average loss: 2.7288
Iteration: 2722; Percent complete: 68.0%; Average loss: 2.8437
Iteration: 2723; Percent complete: 68.1%; Average loss: 3.0188
Iteration: 2724; Percent complete: 68.1%; Average loss: 3.0146
Iteration: 2725; Percent complete: 68.1%; Average loss: 2.7690
Iteration: 2726; Percent complete: 68.2%; Average loss: 3.0799
Iteration: 2727; Percent complete: 68.2%; Average loss: 3.0711
Iteration: 2728; Percent complete: 68.2%; Average loss: 2.8918
Iteration: 2729; Percent complete: 68.2%; Average loss: 2.8550
Iteration: 2730; Percent complete: 68.2%; Average loss: 2.8719
Iteration: 2731; Percent complete: 68.3%; Average loss: 2.6918
Iteration: 2732; Percent complete: 68.3%; Average loss: 2.9291
Iteration: 2733; Percent complete: 68.3%; Average loss: 2.9491
Iteration: 2734; Percent complete: 68.3%; Average loss: 2.7997
Iteration: 2735; Percent complete: 68.4%; Average loss: 3.1129
Iteration: 2736; Percent complete: 68.4%; Average loss: 2.7494
Iteration: 2737; Percent complete: 68.4%; Average loss: 2.8057
Iteration: 2738; Percent complete: 68.5%; Average loss: 3.2436
Iteration: 2739; Percent complete: 68.5%; Average loss: 3.0734
Iteration: 2740; Percent complete: 68.5%; Average loss: 3.0793
Iteration: 2741; Percent complete: 68.5%; Average loss: 3.1486
Iteration: 2742; Percent complete: 68.5%; Average loss: 3.1827
Iteration: 2743; Percent complete: 68.6%; Average loss: 2.9490
Iteration: 2744; Percent complete: 68.6%; Average loss: 3.0123
Iteration: 2745; Percent complete: 68.6%; Average loss: 2.8400
Iteration: 2746; Percent complete: 68.7%; Average loss: 3.1747
Iteration: 2747; Percent complete: 68.7%; Average loss: 3.1291
Iteration: 2748; Percent complete: 68.7%; Average loss: 2.8687
Iteration: 2749; Percent complete: 68.7%; Average loss: 3.0817
Iteration: 2750; Percent complete: 68.8%; Average loss: 2.8043
Iteration: 2751; Percent complete: 68.8%; Average loss: 2.8640
Iteration: 2752; Percent complete: 68.8%; Average loss: 2.8980
Iteration: 2753; Percent complete: 68.8%; Average loss: 2.9857
Iteration: 2754; Percent complete: 68.8%; Average loss: 2.9948
Iteration: 2755; Percent complete: 68.9%; Average loss: 3.0504
Iteration: 2756; Percent complete: 68.9%; Average loss: 2.7494
Iteration: 2757; Percent complete: 68.9%; Average loss: 2.7597
Iteration: 2758; Percent complete: 69.0%; Average loss: 3.1207
Iteration: 2759; Percent complete: 69.0%; Average loss: 2.8895
Iteration: 2760; Percent complete: 69.0%; Average loss: 3.0490
Iteration: 2761; Percent complete: 69.0%; Average loss: 3.2052
Iteration: 2762; Percent complete: 69.0%; Average loss: 3.0874
Iteration: 2763; Percent complete: 69.1%; Average loss: 3.0916
Iteration: 2764; Percent complete: 69.1%; Average loss: 2.8170
Iteration: 2765; Percent complete: 69.1%; Average loss: 2.8461
Iteration: 2766; Percent complete: 69.2%; Average loss: 3.0460
Iteration: 2767; Percent complete: 69.2%; Average loss: 2.8767
Iteration: 2768; Percent complete: 69.2%; Average loss: 2.9373
Iteration: 2769; Percent complete: 69.2%; Average loss: 2.8161
Iteration: 2770; Percent complete: 69.2%; Average loss: 3.0127
Iteration: 2771; Percent complete: 69.3%; Average loss: 2.9031
Iteration: 2772; Percent complete: 69.3%; Average loss: 2.9562
Iteration: 2773; Percent complete: 69.3%; Average loss: 3.1156
Iteration: 2774; Percent complete: 69.3%; Average loss: 2.8737
Iteration: 2775; Percent complete: 69.4%; Average loss: 3.1512
Iteration: 2776; Percent complete: 69.4%; Average loss: 2.8296
Iteration: 2777; Percent complete: 69.4%; Average loss: 2.7940
Iteration: 2778; Percent complete: 69.5%; Average loss: 2.7153
Iteration: 2779; Percent complete: 69.5%; Average loss: 3.0354
Iteration: 2780; Percent complete: 69.5%; Average loss: 2.9249
Iteration: 2781; Percent complete: 69.5%; Average loss: 3.0664
Iteration: 2782; Percent complete: 69.5%; Average loss: 2.9213
Iteration: 2783; Percent complete: 69.6%; Average loss: 2.9103
Iteration: 2784; Percent complete: 69.6%; Average loss: 3.1576
Iteration: 2785; Percent complete: 69.6%; Average loss: 2.9867
Iteration: 2786; Percent complete: 69.7%; Average loss: 2.7189
Iteration: 2787; Percent complete: 69.7%; Average loss: 2.7629
Iteration: 2788; Percent complete: 69.7%; Average loss: 2.8105
Iteration: 2789; Percent complete: 69.7%; Average loss: 2.9711
Iteration: 2790; Percent complete: 69.8%; Average loss: 2.8965
Iteration: 2791; Percent complete: 69.8%; Average loss: 3.2654
Iteration: 2792; Percent complete: 69.8%; Average loss: 2.9324
Iteration: 2793; Percent complete: 69.8%; Average loss: 2.7120
Iteration: 2794; Percent complete: 69.8%; Average loss: 2.9327
Iteration: 2795; Percent complete: 69.9%; Average loss: 2.8764
Iteration: 2796; Percent complete: 69.9%; Average loss: 2.9770
Iteration: 2797; Percent complete: 69.9%; Average loss: 3.0003
Iteration: 2798; Percent complete: 70.0%; Average loss: 3.1404
Iteration: 2799; Percent complete: 70.0%; Average loss: 2.8782
Iteration: 2800; Percent complete: 70.0%; Average loss: 2.8999
Iteration: 2801; Percent complete: 70.0%; Average loss: 3.1313
Iteration: 2802; Percent complete: 70.0%; Average loss: 2.7809
Iteration: 2803; Percent complete: 70.1%; Average loss: 2.9790
Iteration: 2804; Percent complete: 70.1%; Average loss: 2.9608
Iteration: 2805; Percent complete: 70.1%; Average loss: 2.9166
Iteration: 2806; Percent complete: 70.2%; Average loss: 2.9541
Iteration: 2807; Percent complete: 70.2%; Average loss: 2.9520
Iteration: 2808; Percent complete: 70.2%; Average loss: 2.7423
Iteration: 2809; Percent complete: 70.2%; Average loss: 2.9148
Iteration: 2810; Percent complete: 70.2%; Average loss: 3.1220
Iteration: 2811; Percent complete: 70.3%; Average loss: 2.9271
Iteration: 2812; Percent complete: 70.3%; Average loss: 2.9235
Iteration: 2813; Percent complete: 70.3%; Average loss: 2.7449
Iteration: 2814; Percent complete: 70.3%; Average loss: 2.9001
Iteration: 2815; Percent complete: 70.4%; Average loss: 2.7543
Iteration: 2816; Percent complete: 70.4%; Average loss: 2.8848
Iteration: 2817; Percent complete: 70.4%; Average loss: 2.8829
Iteration: 2818; Percent complete: 70.5%; Average loss: 2.9026
Iteration: 2819; Percent complete: 70.5%; Average loss: 3.1228
Iteration: 2820; Percent complete: 70.5%; Average loss: 2.8893
Iteration: 2821; Percent complete: 70.5%; Average loss: 3.0893
Iteration: 2822; Percent complete: 70.5%; Average loss: 2.9021
Iteration: 2823; Percent complete: 70.6%; Average loss: 3.1917
Iteration: 2824; Percent complete: 70.6%; Average loss: 2.9161
Iteration: 2825; Percent complete: 70.6%; Average loss: 2.8128
Iteration: 2826; Percent complete: 70.7%; Average loss: 2.7882
Iteration: 2827; Percent complete: 70.7%; Average loss: 3.0644
Iteration: 2828; Percent complete: 70.7%; Average loss: 2.8237
Iteration: 2829; Percent complete: 70.7%; Average loss: 2.8072
Iteration: 2830; Percent complete: 70.8%; Average loss: 3.1509
Iteration: 2831; Percent complete: 70.8%; Average loss: 2.8956
Iteration: 2832; Percent complete: 70.8%; Average loss: 2.7683
Iteration: 2833; Percent complete: 70.8%; Average loss: 3.0475
Iteration: 2834; Percent complete: 70.9%; Average loss: 3.2712
Iteration: 2835; Percent complete: 70.9%; Average loss: 2.8595
Iteration: 2836; Percent complete: 70.9%; Average loss: 2.6399
Iteration: 2837; Percent complete: 70.9%; Average loss: 3.0951
Iteration: 2838; Percent complete: 71.0%; Average loss: 2.8395
Iteration: 2839; Percent complete: 71.0%; Average loss: 3.0910
Iteration: 2840; Percent complete: 71.0%; Average loss: 2.9852
Iteration: 2841; Percent complete: 71.0%; Average loss: 2.8835
Iteration: 2842; Percent complete: 71.0%; Average loss: 3.0358
Iteration: 2843; Percent complete: 71.1%; Average loss: 2.8991
Iteration: 2844; Percent complete: 71.1%; Average loss: 3.0619
Iteration: 2845; Percent complete: 71.1%; Average loss: 3.0389
Iteration: 2846; Percent complete: 71.2%; Average loss: 2.9901
Iteration: 2847; Percent complete: 71.2%; Average loss: 3.0098
Iteration: 2848; Percent complete: 71.2%; Average loss: 2.9333
Iteration: 2849; Percent complete: 71.2%; Average loss: 2.9108
Iteration: 2850; Percent complete: 71.2%; Average loss: 2.8617
Iteration: 2851; Percent complete: 71.3%; Average loss: 2.9575
Iteration: 2852; Percent complete: 71.3%; Average loss: 3.0816
Iteration: 2853; Percent complete: 71.3%; Average loss: 2.7980
Iteration: 2854; Percent complete: 71.4%; Average loss: 2.8507
Iteration: 2855; Percent complete: 71.4%; Average loss: 2.9715
Iteration: 2856; Percent complete: 71.4%; Average loss: 2.6252
Iteration: 2857; Percent complete: 71.4%; Average loss: 2.9581
Iteration: 2858; Percent complete: 71.5%; Average loss: 2.7857
Iteration: 2859; Percent complete: 71.5%; Average loss: 2.9074
Iteration: 2860; Percent complete: 71.5%; Average loss: 2.9117
Iteration: 2861; Percent complete: 71.5%; Average loss: 3.0044
Iteration: 2862; Percent complete: 71.5%; Average loss: 3.2331
Iteration: 2863; Percent complete: 71.6%; Average loss: 2.8453
Iteration: 2864; Percent complete: 71.6%; Average loss: 2.7100
Iteration: 2865; Percent complete: 71.6%; Average loss: 3.0719
Iteration: 2866; Percent complete: 71.7%; Average loss: 2.8400
Iteration: 2867; Percent complete: 71.7%; Average loss: 2.8601
Iteration: 2868; Percent complete: 71.7%; Average loss: 2.9369
Iteration: 2869; Percent complete: 71.7%; Average loss: 2.8851
Iteration: 2870; Percent complete: 71.8%; Average loss: 3.0165
Iteration: 2871; Percent complete: 71.8%; Average loss: 2.7894
Iteration: 2872; Percent complete: 71.8%; Average loss: 2.7396
Iteration: 2873; Percent complete: 71.8%; Average loss: 2.7262
Iteration: 2874; Percent complete: 71.9%; Average loss: 3.1168
Iteration: 2875; Percent complete: 71.9%; Average loss: 3.0388
Iteration: 2876; Percent complete: 71.9%; Average loss: 3.0912
Iteration: 2877; Percent complete: 71.9%; Average loss: 2.7449
Iteration: 2878; Percent complete: 72.0%; Average loss: 2.9881
Iteration: 2879; Percent complete: 72.0%; Average loss: 2.8661
Iteration: 2880; Percent complete: 72.0%; Average loss: 2.8316
Iteration: 2881; Percent complete: 72.0%; Average loss: 2.7432
Iteration: 2882; Percent complete: 72.0%; Average loss: 2.8791
Iteration: 2883; Percent complete: 72.1%; Average loss: 3.0415
Iteration: 2884; Percent complete: 72.1%; Average loss: 2.9192
Iteration: 2885; Percent complete: 72.1%; Average loss: 2.8962
Iteration: 2886; Percent complete: 72.2%; Average loss: 3.1473
Iteration: 2887; Percent complete: 72.2%; Average loss: 2.9693
Iteration: 2888; Percent complete: 72.2%; Average loss: 2.8085
Iteration: 2889; Percent complete: 72.2%; Average loss: 2.8593
Iteration: 2890; Percent complete: 72.2%; Average loss: 3.0156
Iteration: 2891; Percent complete: 72.3%; Average loss: 3.0384
Iteration: 2892; Percent complete: 72.3%; Average loss: 2.8264
Iteration: 2893; Percent complete: 72.3%; Average loss: 3.0621
Iteration: 2894; Percent complete: 72.4%; Average loss: 2.8786
Iteration: 2895; Percent complete: 72.4%; Average loss: 3.0367
Iteration: 2896; Percent complete: 72.4%; Average loss: 2.9662
Iteration: 2897; Percent complete: 72.4%; Average loss: 2.8647
Iteration: 2898; Percent complete: 72.5%; Average loss: 2.7587
Iteration: 2899; Percent complete: 72.5%; Average loss: 2.9613
Iteration: 2900; Percent complete: 72.5%; Average loss: 2.8853
Iteration: 2901; Percent complete: 72.5%; Average loss: 3.0503
Iteration: 2902; Percent complete: 72.5%; Average loss: 3.0256
Iteration: 2903; Percent complete: 72.6%; Average loss: 3.0295
Iteration: 2904; Percent complete: 72.6%; Average loss: 3.1172
Iteration: 2905; Percent complete: 72.6%; Average loss: 2.9650
Iteration: 2906; Percent complete: 72.7%; Average loss: 2.7838
Iteration: 2907; Percent complete: 72.7%; Average loss: 3.1399
Iteration: 2908; Percent complete: 72.7%; Average loss: 2.8163
Iteration: 2909; Percent complete: 72.7%; Average loss: 2.9252
Iteration: 2910; Percent complete: 72.8%; Average loss: 2.7691
Iteration: 2911; Percent complete: 72.8%; Average loss: 2.7865
Iteration: 2912; Percent complete: 72.8%; Average loss: 2.6251
Iteration: 2913; Percent complete: 72.8%; Average loss: 2.7124
Iteration: 2914; Percent complete: 72.9%; Average loss: 2.9140
Iteration: 2915; Percent complete: 72.9%; Average loss: 3.0425
Iteration: 2916; Percent complete: 72.9%; Average loss: 2.8355
Iteration: 2917; Percent complete: 72.9%; Average loss: 2.8639
Iteration: 2918; Percent complete: 73.0%; Average loss: 2.8050
Iteration: 2919; Percent complete: 73.0%; Average loss: 2.8783
Iteration: 2920; Percent complete: 73.0%; Average loss: 2.9388
Iteration: 2921; Percent complete: 73.0%; Average loss: 3.3532
Iteration: 2922; Percent complete: 73.0%; Average loss: 2.9215
Iteration: 2923; Percent complete: 73.1%; Average loss: 2.7694
Iteration: 2924; Percent complete: 73.1%; Average loss: 2.7496
Iteration: 2925; Percent complete: 73.1%; Average loss: 2.8938
Iteration: 2926; Percent complete: 73.2%; Average loss: 3.0474
Iteration: 2927; Percent complete: 73.2%; Average loss: 2.9187
Iteration: 2928; Percent complete: 73.2%; Average loss: 2.9586
Iteration: 2929; Percent complete: 73.2%; Average loss: 2.9121
Iteration: 2930; Percent complete: 73.2%; Average loss: 2.8113
Iteration: 2931; Percent complete: 73.3%; Average loss: 2.8301
Iteration: 2932; Percent complete: 73.3%; Average loss: 2.9842
Iteration: 2933; Percent complete: 73.3%; Average loss: 2.8894
Iteration: 2934; Percent complete: 73.4%; Average loss: 2.8440
Iteration: 2935; Percent complete: 73.4%; Average loss: 3.0825
Iteration: 2936; Percent complete: 73.4%; Average loss: 2.8570
Iteration: 2937; Percent complete: 73.4%; Average loss: 2.9055
Iteration: 2938; Percent complete: 73.5%; Average loss: 2.8523
Iteration: 2939; Percent complete: 73.5%; Average loss: 3.0032
Iteration: 2940; Percent complete: 73.5%; Average loss: 2.9155
Iteration: 2941; Percent complete: 73.5%; Average loss: 2.9513
Iteration: 2942; Percent complete: 73.6%; Average loss: 2.9128
Iteration: 2943; Percent complete: 73.6%; Average loss: 3.0086
Iteration: 2944; Percent complete: 73.6%; Average loss: 2.8858
Iteration: 2945; Percent complete: 73.6%; Average loss: 2.5803
Iteration: 2946; Percent complete: 73.7%; Average loss: 2.8912
Iteration: 2947; Percent complete: 73.7%; Average loss: 3.1233
Iteration: 2948; Percent complete: 73.7%; Average loss: 3.0066
Iteration: 2949; Percent complete: 73.7%; Average loss: 3.3643
Iteration: 2950; Percent complete: 73.8%; Average loss: 2.9135
Iteration: 2951; Percent complete: 73.8%; Average loss: 3.1219
Iteration: 2952; Percent complete: 73.8%; Average loss: 2.8906
Iteration: 2953; Percent complete: 73.8%; Average loss: 3.0209
Iteration: 2954; Percent complete: 73.9%; Average loss: 3.1232
Iteration: 2955; Percent complete: 73.9%; Average loss: 2.9514
Iteration: 2956; Percent complete: 73.9%; Average loss: 3.0638
Iteration: 2957; Percent complete: 73.9%; Average loss: 2.8434
Iteration: 2958; Percent complete: 74.0%; Average loss: 2.9658
Iteration: 2959; Percent complete: 74.0%; Average loss: 2.9018
Iteration: 2960; Percent complete: 74.0%; Average loss: 2.7989
Iteration: 2961; Percent complete: 74.0%; Average loss: 2.6910
Iteration: 2962; Percent complete: 74.1%; Average loss: 2.7533
Iteration: 2963; Percent complete: 74.1%; Average loss: 3.0538
Iteration: 2964; Percent complete: 74.1%; Average loss: 2.7777
Iteration: 2965; Percent complete: 74.1%; Average loss: 2.9879
Iteration: 2966; Percent complete: 74.2%; Average loss: 2.9049
Iteration: 2967; Percent complete: 74.2%; Average loss: 3.0860
Iteration: 2968; Percent complete: 74.2%; Average loss: 3.0165
Iteration: 2969; Percent complete: 74.2%; Average loss: 2.7628
Iteration: 2970; Percent complete: 74.2%; Average loss: 3.0060
Iteration: 2971; Percent complete: 74.3%; Average loss: 2.9365
Iteration: 2972; Percent complete: 74.3%; Average loss: 2.7894
Iteration: 2973; Percent complete: 74.3%; Average loss: 3.0332
Iteration: 2974; Percent complete: 74.4%; Average loss: 2.7896
Iteration: 2975; Percent complete: 74.4%; Average loss: 2.8192
Iteration: 2976; Percent complete: 74.4%; Average loss: 2.9803
Iteration: 2977; Percent complete: 74.4%; Average loss: 3.0179
Iteration: 2978; Percent complete: 74.5%; Average loss: 2.8376
Iteration: 2979; Percent complete: 74.5%; Average loss: 2.8989
Iteration: 2980; Percent complete: 74.5%; Average loss: 2.9930
Iteration: 2981; Percent complete: 74.5%; Average loss: 2.7104
Iteration: 2982; Percent complete: 74.6%; Average loss: 2.6975
Iteration: 2983; Percent complete: 74.6%; Average loss: 2.9894
Iteration: 2984; Percent complete: 74.6%; Average loss: 2.7420
Iteration: 2985; Percent complete: 74.6%; Average loss: 2.8446
Iteration: 2986; Percent complete: 74.7%; Average loss: 2.8319
Iteration: 2987; Percent complete: 74.7%; Average loss: 2.9663
Iteration: 2988; Percent complete: 74.7%; Average loss: 2.8592
Iteration: 2989; Percent complete: 74.7%; Average loss: 2.8092
Iteration: 2990; Percent complete: 74.8%; Average loss: 2.8237
Iteration: 2991; Percent complete: 74.8%; Average loss: 2.7850
Iteration: 2992; Percent complete: 74.8%; Average loss: 2.7294
Iteration: 2993; Percent complete: 74.8%; Average loss: 2.8064
Iteration: 2994; Percent complete: 74.9%; Average loss: 2.7342
Iteration: 2995; Percent complete: 74.9%; Average loss: 2.7269
Iteration: 2996; Percent complete: 74.9%; Average loss: 2.9424
Iteration: 2997; Percent complete: 74.9%; Average loss: 3.0187
Iteration: 2998; Percent complete: 75.0%; Average loss: 3.0586
Iteration: 2999; Percent complete: 75.0%; Average loss: 2.7726
Iteration: 3000; Percent complete: 75.0%; Average loss: 3.1243
Iteration: 3001; Percent complete: 75.0%; Average loss: 3.0895
Iteration: 3002; Percent complete: 75.0%; Average loss: 2.8032
Iteration: 3003; Percent complete: 75.1%; Average loss: 3.0509
Iteration: 3004; Percent complete: 75.1%; Average loss: 2.9524
Iteration: 3005; Percent complete: 75.1%; Average loss: 2.7015
Iteration: 3006; Percent complete: 75.1%; Average loss: 2.7732
Iteration: 3007; Percent complete: 75.2%; Average loss: 2.8460
Iteration: 3008; Percent complete: 75.2%; Average loss: 2.8565
Iteration: 3009; Percent complete: 75.2%; Average loss: 2.8566
Iteration: 3010; Percent complete: 75.2%; Average loss: 2.7777
Iteration: 3011; Percent complete: 75.3%; Average loss: 2.8249
Iteration: 3012; Percent complete: 75.3%; Average loss: 2.8883
Iteration: 3013; Percent complete: 75.3%; Average loss: 2.8350
Iteration: 3014; Percent complete: 75.3%; Average loss: 2.8779
Iteration: 3015; Percent complete: 75.4%; Average loss: 3.1752
Iteration: 3016; Percent complete: 75.4%; Average loss: 2.9306
Iteration: 3017; Percent complete: 75.4%; Average loss: 2.8928
Iteration: 3018; Percent complete: 75.4%; Average loss: 3.1122
Iteration: 3019; Percent complete: 75.5%; Average loss: 2.8815
Iteration: 3020; Percent complete: 75.5%; Average loss: 2.7591
Iteration: 3021; Percent complete: 75.5%; Average loss: 2.8278
Iteration: 3022; Percent complete: 75.5%; Average loss: 2.8143
Iteration: 3023; Percent complete: 75.6%; Average loss: 2.9691
Iteration: 3024; Percent complete: 75.6%; Average loss: 2.8150
Iteration: 3025; Percent complete: 75.6%; Average loss: 3.0399
Iteration: 3026; Percent complete: 75.6%; Average loss: 2.9410
Iteration: 3027; Percent complete: 75.7%; Average loss: 3.0093
Iteration: 3028; Percent complete: 75.7%; Average loss: 2.7007
Iteration: 3029; Percent complete: 75.7%; Average loss: 2.9830
Iteration: 3030; Percent complete: 75.8%; Average loss: 2.9666
Iteration: 3031; Percent complete: 75.8%; Average loss: 2.8381
Iteration: 3032; Percent complete: 75.8%; Average loss: 3.2507
Iteration: 3033; Percent complete: 75.8%; Average loss: 2.8992
Iteration: 3034; Percent complete: 75.8%; Average loss: 2.7221
Iteration: 3035; Percent complete: 75.9%; Average loss: 2.9153
Iteration: 3036; Percent complete: 75.9%; Average loss: 2.8718
Iteration: 3037; Percent complete: 75.9%; Average loss: 3.2713
Iteration: 3038; Percent complete: 75.9%; Average loss: 2.8133
Iteration: 3039; Percent complete: 76.0%; Average loss: 3.0715
Iteration: 3040; Percent complete: 76.0%; Average loss: 2.9838
Iteration: 3041; Percent complete: 76.0%; Average loss: 2.8325
Iteration: 3042; Percent complete: 76.0%; Average loss: 2.5996
Iteration: 3043; Percent complete: 76.1%; Average loss: 3.0352
Iteration: 3044; Percent complete: 76.1%; Average loss: 2.8153
Iteration: 3045; Percent complete: 76.1%; Average loss: 2.9095
Iteration: 3046; Percent complete: 76.1%; Average loss: 2.9045
Iteration: 3047; Percent complete: 76.2%; Average loss: 2.8828
Iteration: 3048; Percent complete: 76.2%; Average loss: 3.0644
Iteration: 3049; Percent complete: 76.2%; Average loss: 2.9079
Iteration: 3050; Percent complete: 76.2%; Average loss: 3.0439
Iteration: 3051; Percent complete: 76.3%; Average loss: 2.8408
Iteration: 3052; Percent complete: 76.3%; Average loss: 2.9716
Iteration: 3053; Percent complete: 76.3%; Average loss: 2.8834
Iteration: 3054; Percent complete: 76.3%; Average loss: 2.6497
Iteration: 3055; Percent complete: 76.4%; Average loss: 3.0850
Iteration: 3056; Percent complete: 76.4%; Average loss: 2.8679
Iteration: 3057; Percent complete: 76.4%; Average loss: 2.9319
Iteration: 3058; Percent complete: 76.4%; Average loss: 2.8833
Iteration: 3059; Percent complete: 76.5%; Average loss: 2.8696
Iteration: 3060; Percent complete: 76.5%; Average loss: 2.9854
Iteration: 3061; Percent complete: 76.5%; Average loss: 2.7210
Iteration: 3062; Percent complete: 76.5%; Average loss: 2.7309
Iteration: 3063; Percent complete: 76.6%; Average loss: 2.8030
Iteration: 3064; Percent complete: 76.6%; Average loss: 2.7753
Iteration: 3065; Percent complete: 76.6%; Average loss: 3.1564
Iteration: 3066; Percent complete: 76.6%; Average loss: 2.8929
Iteration: 3067; Percent complete: 76.7%; Average loss: 2.7825
Iteration: 3068; Percent complete: 76.7%; Average loss: 2.6352
Iteration: 3069; Percent complete: 76.7%; Average loss: 2.7377
Iteration: 3070; Percent complete: 76.8%; Average loss: 2.5959
Iteration: 3071; Percent complete: 76.8%; Average loss: 2.7294
Iteration: 3072; Percent complete: 76.8%; Average loss: 2.6846
Iteration: 3073; Percent complete: 76.8%; Average loss: 2.8018
Iteration: 3074; Percent complete: 76.8%; Average loss: 2.6701
Iteration: 3075; Percent complete: 76.9%; Average loss: 2.8273
Iteration: 3076; Percent complete: 76.9%; Average loss: 2.8092
Iteration: 3077; Percent complete: 76.9%; Average loss: 3.0056
Iteration: 3078; Percent complete: 77.0%; Average loss: 2.9151
Iteration: 3079; Percent complete: 77.0%; Average loss: 2.8727
Iteration: 3080; Percent complete: 77.0%; Average loss: 2.7882
Iteration: 3081; Percent complete: 77.0%; Average loss: 2.9473
Iteration: 3082; Percent complete: 77.0%; Average loss: 3.0839
Iteration: 3083; Percent complete: 77.1%; Average loss: 2.8521
Iteration: 3084; Percent complete: 77.1%; Average loss: 2.9143
Iteration: 3085; Percent complete: 77.1%; Average loss: 2.7532
Iteration: 3086; Percent complete: 77.1%; Average loss: 3.0589
Iteration: 3087; Percent complete: 77.2%; Average loss: 2.9103
Iteration: 3088; Percent complete: 77.2%; Average loss: 2.7587
Iteration: 3089; Percent complete: 77.2%; Average loss: 2.9268
Iteration: 3090; Percent complete: 77.2%; Average loss: 2.9380
Iteration: 3091; Percent complete: 77.3%; Average loss: 2.9371
Iteration: 3092; Percent complete: 77.3%; Average loss: 3.0010
Iteration: 3093; Percent complete: 77.3%; Average loss: 2.9463
Iteration: 3094; Percent complete: 77.3%; Average loss: 2.6900
Iteration: 3095; Percent complete: 77.4%; Average loss: 2.9300
Iteration: 3096; Percent complete: 77.4%; Average loss: 3.0152
Iteration: 3097; Percent complete: 77.4%; Average loss: 3.0207
Iteration: 3098; Percent complete: 77.5%; Average loss: 2.9245
Iteration: 3099; Percent complete: 77.5%; Average loss: 2.8669
Iteration: 3100; Percent complete: 77.5%; Average loss: 2.7795
Iteration: 3101; Percent complete: 77.5%; Average loss: 3.0013
Iteration: 3102; Percent complete: 77.5%; Average loss: 3.0065
Iteration: 3103; Percent complete: 77.6%; Average loss: 2.9352
Iteration: 3104; Percent complete: 77.6%; Average loss: 2.8128
Iteration: 3105; Percent complete: 77.6%; Average loss: 2.7730
Iteration: 3106; Percent complete: 77.6%; Average loss: 2.8396
Iteration: 3107; Percent complete: 77.7%; Average loss: 2.5567
Iteration: 3108; Percent complete: 77.7%; Average loss: 2.8146
Iteration: 3109; Percent complete: 77.7%; Average loss: 2.9636
Iteration: 3110; Percent complete: 77.8%; Average loss: 2.8527
Iteration: 3111; Percent complete: 77.8%; Average loss: 2.9330
Iteration: 3112; Percent complete: 77.8%; Average loss: 2.7998
Iteration: 3113; Percent complete: 77.8%; Average loss: 2.7558
Iteration: 3114; Percent complete: 77.8%; Average loss: 2.7419
Iteration: 3115; Percent complete: 77.9%; Average loss: 2.9029
Iteration: 3116; Percent complete: 77.9%; Average loss: 2.8139
Iteration: 3117; Percent complete: 77.9%; Average loss: 2.7247
Iteration: 3118; Percent complete: 78.0%; Average loss: 2.5344
Iteration: 3119; Percent complete: 78.0%; Average loss: 2.9181
Iteration: 3120; Percent complete: 78.0%; Average loss: 2.7623
Iteration: 3121; Percent complete: 78.0%; Average loss: 2.9234
Iteration: 3122; Percent complete: 78.0%; Average loss: 2.8146
Iteration: 3123; Percent complete: 78.1%; Average loss: 2.6730
Iteration: 3124; Percent complete: 78.1%; Average loss: 2.9078
Iteration: 3125; Percent complete: 78.1%; Average loss: 2.8143
Iteration: 3126; Percent complete: 78.1%; Average loss: 2.5757
Iteration: 3127; Percent complete: 78.2%; Average loss: 2.9071
Iteration: 3128; Percent complete: 78.2%; Average loss: 3.0858
Iteration: 3129; Percent complete: 78.2%; Average loss: 2.7022
Iteration: 3130; Percent complete: 78.2%; Average loss: 2.9308
Iteration: 3131; Percent complete: 78.3%; Average loss: 2.7488
Iteration: 3132; Percent complete: 78.3%; Average loss: 3.0155
Iteration: 3133; Percent complete: 78.3%; Average loss: 2.7563
Iteration: 3134; Percent complete: 78.3%; Average loss: 2.6605
Iteration: 3135; Percent complete: 78.4%; Average loss: 2.9569
Iteration: 3136; Percent complete: 78.4%; Average loss: 3.0465
Iteration: 3137; Percent complete: 78.4%; Average loss: 2.6796
Iteration: 3138; Percent complete: 78.5%; Average loss: 2.7565
Iteration: 3139; Percent complete: 78.5%; Average loss: 2.8707
Iteration: 3140; Percent complete: 78.5%; Average loss: 2.8845
Iteration: 3141; Percent complete: 78.5%; Average loss: 2.9103
Iteration: 3142; Percent complete: 78.5%; Average loss: 2.7591
Iteration: 3143; Percent complete: 78.6%; Average loss: 2.4520
Iteration: 3144; Percent complete: 78.6%; Average loss: 2.8896
Iteration: 3145; Percent complete: 78.6%; Average loss: 2.8914
Iteration: 3146; Percent complete: 78.6%; Average loss: 2.7968
Iteration: 3147; Percent complete: 78.7%; Average loss: 3.0161
Iteration: 3148; Percent complete: 78.7%; Average loss: 2.9972
Iteration: 3149; Percent complete: 78.7%; Average loss: 2.9644
Iteration: 3150; Percent complete: 78.8%; Average loss: 2.4958
Iteration: 3151; Percent complete: 78.8%; Average loss: 2.7467
Iteration: 3152; Percent complete: 78.8%; Average loss: 2.9444
Iteration: 3153; Percent complete: 78.8%; Average loss: 2.7484
Iteration: 3154; Percent complete: 78.8%; Average loss: 2.8603
Iteration: 3155; Percent complete: 78.9%; Average loss: 2.8431
Iteration: 3156; Percent complete: 78.9%; Average loss: 2.9371
Iteration: 3157; Percent complete: 78.9%; Average loss: 2.8150
Iteration: 3158; Percent complete: 79.0%; Average loss: 2.9244
Iteration: 3159; Percent complete: 79.0%; Average loss: 2.8596
Iteration: 3160; Percent complete: 79.0%; Average loss: 2.6765
Iteration: 3161; Percent complete: 79.0%; Average loss: 2.6203
Iteration: 3162; Percent complete: 79.0%; Average loss: 2.8717
Iteration: 3163; Percent complete: 79.1%; Average loss: 2.8638
Iteration: 3164; Percent complete: 79.1%; Average loss: 2.7465
Iteration: 3165; Percent complete: 79.1%; Average loss: 3.0092
Iteration: 3166; Percent complete: 79.1%; Average loss: 3.0416
Iteration: 3167; Percent complete: 79.2%; Average loss: 2.9050
Iteration: 3168; Percent complete: 79.2%; Average loss: 2.8484
Iteration: 3169; Percent complete: 79.2%; Average loss: 2.7662
Iteration: 3170; Percent complete: 79.2%; Average loss: 2.9379
Iteration: 3171; Percent complete: 79.3%; Average loss: 2.9784
Iteration: 3172; Percent complete: 79.3%; Average loss: 2.7334
Iteration: 3173; Percent complete: 79.3%; Average loss: 2.6837
Iteration: 3174; Percent complete: 79.3%; Average loss: 2.7303
Iteration: 3175; Percent complete: 79.4%; Average loss: 2.7781
Iteration: 3176; Percent complete: 79.4%; Average loss: 2.5749
Iteration: 3177; Percent complete: 79.4%; Average loss: 2.8814
Iteration: 3178; Percent complete: 79.5%; Average loss: 2.7445
Iteration: 3179; Percent complete: 79.5%; Average loss: 2.9002
Iteration: 3180; Percent complete: 79.5%; Average loss: 2.7440
Iteration: 3181; Percent complete: 79.5%; Average loss: 2.9962
Iteration: 3182; Percent complete: 79.5%; Average loss: 2.6816
Iteration: 3183; Percent complete: 79.6%; Average loss: 2.6560
Iteration: 3184; Percent complete: 79.6%; Average loss: 3.1739
Iteration: 3185; Percent complete: 79.6%; Average loss: 2.7368
Iteration: 3186; Percent complete: 79.7%; Average loss: 2.8628
Iteration: 3187; Percent complete: 79.7%; Average loss: 2.6619
Iteration: 3188; Percent complete: 79.7%; Average loss: 2.5792
Iteration: 3189; Percent complete: 79.7%; Average loss: 2.8710
Iteration: 3190; Percent complete: 79.8%; Average loss: 2.8249
Iteration: 3191; Percent complete: 79.8%; Average loss: 3.0028
Iteration: 3192; Percent complete: 79.8%; Average loss: 2.7619
Iteration: 3193; Percent complete: 79.8%; Average loss: 2.8748
Iteration: 3194; Percent complete: 79.8%; Average loss: 2.6811
Iteration: 3195; Percent complete: 79.9%; Average loss: 2.7370
Iteration: 3196; Percent complete: 79.9%; Average loss: 2.7623
Iteration: 3197; Percent complete: 79.9%; Average loss: 2.8235
Iteration: 3198; Percent complete: 80.0%; Average loss: 2.7803
Iteration: 3199; Percent complete: 80.0%; Average loss: 2.8271
Iteration: 3200; Percent complete: 80.0%; Average loss: 2.8164
Iteration: 3201; Percent complete: 80.0%; Average loss: 2.5833
Iteration: 3202; Percent complete: 80.0%; Average loss: 2.8440
Iteration: 3203; Percent complete: 80.1%; Average loss: 2.9008
Iteration: 3204; Percent complete: 80.1%; Average loss: 2.9041
Iteration: 3205; Percent complete: 80.1%; Average loss: 2.7272
Iteration: 3206; Percent complete: 80.2%; Average loss: 2.8531
Iteration: 3207; Percent complete: 80.2%; Average loss: 2.8509
Iteration: 3208; Percent complete: 80.2%; Average loss: 2.6326
Iteration: 3209; Percent complete: 80.2%; Average loss: 2.6022
Iteration: 3210; Percent complete: 80.2%; Average loss: 3.0264
Iteration: 3211; Percent complete: 80.3%; Average loss: 2.9752
Iteration: 3212; Percent complete: 80.3%; Average loss: 2.6281
Iteration: 3213; Percent complete: 80.3%; Average loss: 2.9629
Iteration: 3214; Percent complete: 80.3%; Average loss: 2.8548
Iteration: 3215; Percent complete: 80.4%; Average loss: 2.7176
Iteration: 3216; Percent complete: 80.4%; Average loss: 2.5634
Iteration: 3217; Percent complete: 80.4%; Average loss: 2.7975
Iteration: 3218; Percent complete: 80.5%; Average loss: 2.8106
Iteration: 3219; Percent complete: 80.5%; Average loss: 2.8457
Iteration: 3220; Percent complete: 80.5%; Average loss: 2.6507
Iteration: 3221; Percent complete: 80.5%; Average loss: 3.0848
Iteration: 3222; Percent complete: 80.5%; Average loss: 2.6923
Iteration: 3223; Percent complete: 80.6%; Average loss: 2.5108
Iteration: 3224; Percent complete: 80.6%; Average loss: 3.0260
Iteration: 3225; Percent complete: 80.6%; Average loss: 3.1970
Iteration: 3226; Percent complete: 80.7%; Average loss: 2.5569
Iteration: 3227; Percent complete: 80.7%; Average loss: 2.6654
Iteration: 3228; Percent complete: 80.7%; Average loss: 2.7784
Iteration: 3229; Percent complete: 80.7%; Average loss: 2.6431
Iteration: 3230; Percent complete: 80.8%; Average loss: 2.8410
Iteration: 3231; Percent complete: 80.8%; Average loss: 2.9411
Iteration: 3232; Percent complete: 80.8%; Average loss: 2.7751
Iteration: 3233; Percent complete: 80.8%; Average loss: 2.6402
Iteration: 3234; Percent complete: 80.8%; Average loss: 2.8856
Iteration: 3235; Percent complete: 80.9%; Average loss: 2.9154
Iteration: 3236; Percent complete: 80.9%; Average loss: 2.9407
Iteration: 3237; Percent complete: 80.9%; Average loss: 2.7493
Iteration: 3238; Percent complete: 81.0%; Average loss: 2.8303
Iteration: 3239; Percent complete: 81.0%; Average loss: 2.5745
Iteration: 3240; Percent complete: 81.0%; Average loss: 2.9197
Iteration: 3241; Percent complete: 81.0%; Average loss: 2.5187
Iteration: 3242; Percent complete: 81.0%; Average loss: 2.8580
Iteration: 3243; Percent complete: 81.1%; Average loss: 2.9762
Iteration: 3244; Percent complete: 81.1%; Average loss: 2.9971
Iteration: 3245; Percent complete: 81.1%; Average loss: 2.8435
Iteration: 3246; Percent complete: 81.2%; Average loss: 2.7810
Iteration: 3247; Percent complete: 81.2%; Average loss: 2.7276
Iteration: 3248; Percent complete: 81.2%; Average loss: 2.6887
Iteration: 3249; Percent complete: 81.2%; Average loss: 2.8009
Iteration: 3250; Percent complete: 81.2%; Average loss: 2.8584
Iteration: 3251; Percent complete: 81.3%; Average loss: 2.6645
Iteration: 3252; Percent complete: 81.3%; Average loss: 2.7404
Iteration: 3253; Percent complete: 81.3%; Average loss: 2.4967
Iteration: 3254; Percent complete: 81.3%; Average loss: 3.0598
Iteration: 3255; Percent complete: 81.4%; Average loss: 3.0342
Iteration: 3256; Percent complete: 81.4%; Average loss: 2.6513
Iteration: 3257; Percent complete: 81.4%; Average loss: 2.9291
Iteration: 3258; Percent complete: 81.5%; Average loss: 2.9681
Iteration: 3259; Percent complete: 81.5%; Average loss: 2.8688
Iteration: 3260; Percent complete: 81.5%; Average loss: 2.9927
Iteration: 3261; Percent complete: 81.5%; Average loss: 2.9716
Iteration: 3262; Percent complete: 81.5%; Average loss: 2.8805
Iteration: 3263; Percent complete: 81.6%; Average loss: 2.7508
Iteration: 3264; Percent complete: 81.6%; Average loss: 2.9476
Iteration: 3265; Percent complete: 81.6%; Average loss: 2.6578
Iteration: 3266; Percent complete: 81.7%; Average loss: 2.6801
Iteration: 3267; Percent complete: 81.7%; Average loss: 2.9694
Iteration: 3268; Percent complete: 81.7%; Average loss: 2.9351
Iteration: 3269; Percent complete: 81.7%; Average loss: 2.8311
Iteration: 3270; Percent complete: 81.8%; Average loss: 2.8795
Iteration: 3271; Percent complete: 81.8%; Average loss: 2.8587
Iteration: 3272; Percent complete: 81.8%; Average loss: 2.5886
Iteration: 3273; Percent complete: 81.8%; Average loss: 2.6202
Iteration: 3274; Percent complete: 81.8%; Average loss: 2.8409
Iteration: 3275; Percent complete: 81.9%; Average loss: 2.9162
Iteration: 3276; Percent complete: 81.9%; Average loss: 2.4786
Iteration: 3277; Percent complete: 81.9%; Average loss: 2.7931
Iteration: 3278; Percent complete: 82.0%; Average loss: 2.5686
Iteration: 3279; Percent complete: 82.0%; Average loss: 2.6688
Iteration: 3280; Percent complete: 82.0%; Average loss: 3.0293
Iteration: 3281; Percent complete: 82.0%; Average loss: 2.8250
Iteration: 3282; Percent complete: 82.0%; Average loss: 2.7234
Iteration: 3283; Percent complete: 82.1%; Average loss: 2.6039
Iteration: 3284; Percent complete: 82.1%; Average loss: 2.6400
Iteration: 3285; Percent complete: 82.1%; Average loss: 2.7960
Iteration: 3286; Percent complete: 82.2%; Average loss: 2.9027
Iteration: 3287; Percent complete: 82.2%; Average loss: 3.0389
Iteration: 3288; Percent complete: 82.2%; Average loss: 3.0638
Iteration: 3289; Percent complete: 82.2%; Average loss: 2.8155
Iteration: 3290; Percent complete: 82.2%; Average loss: 3.0225
Iteration: 3291; Percent complete: 82.3%; Average loss: 2.7452
Iteration: 3292; Percent complete: 82.3%; Average loss: 2.7378
Iteration: 3293; Percent complete: 82.3%; Average loss: 2.6110
Iteration: 3294; Percent complete: 82.3%; Average loss: 2.7500
Iteration: 3295; Percent complete: 82.4%; Average loss: 2.7260
Iteration: 3296; Percent complete: 82.4%; Average loss: 2.8895
Iteration: 3297; Percent complete: 82.4%; Average loss: 2.8395
Iteration: 3298; Percent complete: 82.5%; Average loss: 2.8919
Iteration: 3299; Percent complete: 82.5%; Average loss: 2.9079
Iteration: 3300; Percent complete: 82.5%; Average loss: 2.8094
Iteration: 3301; Percent complete: 82.5%; Average loss: 2.7524
Iteration: 3302; Percent complete: 82.5%; Average loss: 2.8841
Iteration: 3303; Percent complete: 82.6%; Average loss: 2.7039
Iteration: 3304; Percent complete: 82.6%; Average loss: 2.8585
Iteration: 3305; Percent complete: 82.6%; Average loss: 2.8905
Iteration: 3306; Percent complete: 82.7%; Average loss: 2.8969
Iteration: 3307; Percent complete: 82.7%; Average loss: 2.9616
Iteration: 3308; Percent complete: 82.7%; Average loss: 2.8733
Iteration: 3309; Percent complete: 82.7%; Average loss: 2.7676
Iteration: 3310; Percent complete: 82.8%; Average loss: 2.8621
Iteration: 3311; Percent complete: 82.8%; Average loss: 2.9051
Iteration: 3312; Percent complete: 82.8%; Average loss: 3.0581
Iteration: 3313; Percent complete: 82.8%; Average loss: 3.1238
Iteration: 3314; Percent complete: 82.8%; Average loss: 2.7523
Iteration: 3315; Percent complete: 82.9%; Average loss: 2.7010
Iteration: 3316; Percent complete: 82.9%; Average loss: 2.5870
Iteration: 3317; Percent complete: 82.9%; Average loss: 2.8923
Iteration: 3318; Percent complete: 83.0%; Average loss: 2.8558
Iteration: 3319; Percent complete: 83.0%; Average loss: 2.7237
Iteration: 3320; Percent complete: 83.0%; Average loss: 2.7092
Iteration: 3321; Percent complete: 83.0%; Average loss: 2.9096
Iteration: 3322; Percent complete: 83.0%; Average loss: 2.8661
Iteration: 3323; Percent complete: 83.1%; Average loss: 2.9493
Iteration: 3324; Percent complete: 83.1%; Average loss: 2.7036
Iteration: 3325; Percent complete: 83.1%; Average loss: 2.6767
Iteration: 3326; Percent complete: 83.2%; Average loss: 2.8127
Iteration: 3327; Percent complete: 83.2%; Average loss: 2.7927
Iteration: 3328; Percent complete: 83.2%; Average loss: 2.9525
Iteration: 3329; Percent complete: 83.2%; Average loss: 2.8466
Iteration: 3330; Percent complete: 83.2%; Average loss: 2.6770
Iteration: 3331; Percent complete: 83.3%; Average loss: 2.7835
Iteration: 3332; Percent complete: 83.3%; Average loss: 2.8117
Iteration: 3333; Percent complete: 83.3%; Average loss: 2.5684
Iteration: 3334; Percent complete: 83.4%; Average loss: 2.8516
Iteration: 3335; Percent complete: 83.4%; Average loss: 2.7080
Iteration: 3336; Percent complete: 83.4%; Average loss: 2.7813
Iteration: 3337; Percent complete: 83.4%; Average loss: 3.1113
Iteration: 3338; Percent complete: 83.5%; Average loss: 2.8779
Iteration: 3339; Percent complete: 83.5%; Average loss: 2.8255
Iteration: 3340; Percent complete: 83.5%; Average loss: 2.7428
Iteration: 3341; Percent complete: 83.5%; Average loss: 2.7654
Iteration: 3342; Percent complete: 83.5%; Average loss: 2.6694
Iteration: 3343; Percent complete: 83.6%; Average loss: 2.5614
Iteration: 3344; Percent complete: 83.6%; Average loss: 2.8096
Iteration: 3345; Percent complete: 83.6%; Average loss: 2.9200
Iteration: 3346; Percent complete: 83.7%; Average loss: 2.7117
Iteration: 3347; Percent complete: 83.7%; Average loss: 2.6664
Iteration: 3348; Percent complete: 83.7%; Average loss: 3.0594
Iteration: 3349; Percent complete: 83.7%; Average loss: 2.7424
Iteration: 3350; Percent complete: 83.8%; Average loss: 2.5804
Iteration: 3351; Percent complete: 83.8%; Average loss: 2.5596
Iteration: 3352; Percent complete: 83.8%; Average loss: 2.8961
Iteration: 3353; Percent complete: 83.8%; Average loss: 2.6715
Iteration: 3354; Percent complete: 83.9%; Average loss: 2.7150
Iteration: 3355; Percent complete: 83.9%; Average loss: 2.6047
Iteration: 3356; Percent complete: 83.9%; Average loss: 2.4764
Iteration: 3357; Percent complete: 83.9%; Average loss: 2.7142
Iteration: 3358; Percent complete: 84.0%; Average loss: 2.7785
Iteration: 3359; Percent complete: 84.0%; Average loss: 2.7781
Iteration: 3360; Percent complete: 84.0%; Average loss: 3.0555
Iteration: 3361; Percent complete: 84.0%; Average loss: 2.6823
Iteration: 3362; Percent complete: 84.0%; Average loss: 2.6907
Iteration: 3363; Percent complete: 84.1%; Average loss: 2.6170
Iteration: 3364; Percent complete: 84.1%; Average loss: 2.7666
Iteration: 3365; Percent complete: 84.1%; Average loss: 2.8901
Iteration: 3366; Percent complete: 84.2%; Average loss: 2.8600
Iteration: 3367; Percent complete: 84.2%; Average loss: 2.8073
Iteration: 3368; Percent complete: 84.2%; Average loss: 2.7118
Iteration: 3369; Percent complete: 84.2%; Average loss: 2.4247
Iteration: 3370; Percent complete: 84.2%; Average loss: 3.0172
Iteration: 3371; Percent complete: 84.3%; Average loss: 2.8768
Iteration: 3372; Percent complete: 84.3%; Average loss: 2.7173
Iteration: 3373; Percent complete: 84.3%; Average loss: 2.7968
Iteration: 3374; Percent complete: 84.4%; Average loss: 2.5727
Iteration: 3375; Percent complete: 84.4%; Average loss: 2.7751
Iteration: 3376; Percent complete: 84.4%; Average loss: 2.8807
Iteration: 3377; Percent complete: 84.4%; Average loss: 2.7138
Iteration: 3378; Percent complete: 84.5%; Average loss: 2.8202
Iteration: 3379; Percent complete: 84.5%; Average loss: 2.8355
Iteration: 3380; Percent complete: 84.5%; Average loss: 2.7658
Iteration: 3381; Percent complete: 84.5%; Average loss: 2.6616
Iteration: 3382; Percent complete: 84.5%; Average loss: 2.6352
Iteration: 3383; Percent complete: 84.6%; Average loss: 2.6446
Iteration: 3384; Percent complete: 84.6%; Average loss: 2.8259
Iteration: 3385; Percent complete: 84.6%; Average loss: 2.5062
Iteration: 3386; Percent complete: 84.7%; Average loss: 2.7619
Iteration: 3387; Percent complete: 84.7%; Average loss: 2.8880
Iteration: 3388; Percent complete: 84.7%; Average loss: 2.6881
Iteration: 3389; Percent complete: 84.7%; Average loss: 2.6626
Iteration: 3390; Percent complete: 84.8%; Average loss: 2.6687
Iteration: 3391; Percent complete: 84.8%; Average loss: 2.8720
Iteration: 3392; Percent complete: 84.8%; Average loss: 2.7890
Iteration: 3393; Percent complete: 84.8%; Average loss: 2.6336
Iteration: 3394; Percent complete: 84.9%; Average loss: 3.0073
Iteration: 3395; Percent complete: 84.9%; Average loss: 2.9984
Iteration: 3396; Percent complete: 84.9%; Average loss: 2.7266
Iteration: 3397; Percent complete: 84.9%; Average loss: 2.8255
Iteration: 3398; Percent complete: 85.0%; Average loss: 2.7940
Iteration: 3399; Percent complete: 85.0%; Average loss: 2.7219
Iteration: 3400; Percent complete: 85.0%; Average loss: 2.8354
Iteration: 3401; Percent complete: 85.0%; Average loss: 2.8630
Iteration: 3402; Percent complete: 85.0%; Average loss: 2.6015
Iteration: 3403; Percent complete: 85.1%; Average loss: 2.9659
Iteration: 3404; Percent complete: 85.1%; Average loss: 2.4824
Iteration: 3405; Percent complete: 85.1%; Average loss: 2.9497
Iteration: 3406; Percent complete: 85.2%; Average loss: 2.4586
Iteration: 3407; Percent complete: 85.2%; Average loss: 2.6579
Iteration: 3408; Percent complete: 85.2%; Average loss: 2.5156
Iteration: 3409; Percent complete: 85.2%; Average loss: 2.5047
Iteration: 3410; Percent complete: 85.2%; Average loss: 2.9132
Iteration: 3411; Percent complete: 85.3%; Average loss: 2.9651
Iteration: 3412; Percent complete: 85.3%; Average loss: 2.6153
Iteration: 3413; Percent complete: 85.3%; Average loss: 3.0726
Iteration: 3414; Percent complete: 85.4%; Average loss: 2.6187
Iteration: 3415; Percent complete: 85.4%; Average loss: 2.9346
Iteration: 3416; Percent complete: 85.4%; Average loss: 2.8672
Iteration: 3417; Percent complete: 85.4%; Average loss: 2.9195
Iteration: 3418; Percent complete: 85.5%; Average loss: 2.7774
Iteration: 3419; Percent complete: 85.5%; Average loss: 2.8096
Iteration: 3420; Percent complete: 85.5%; Average loss: 2.6866
Iteration: 3421; Percent complete: 85.5%; Average loss: 2.6525
Iteration: 3422; Percent complete: 85.5%; Average loss: 2.9867
Iteration: 3423; Percent complete: 85.6%; Average loss: 2.9070
Iteration: 3424; Percent complete: 85.6%; Average loss: 2.7717
Iteration: 3425; Percent complete: 85.6%; Average loss: 2.5779
Iteration: 3426; Percent complete: 85.7%; Average loss: 2.8981
Iteration: 3427; Percent complete: 85.7%; Average loss: 2.8618
Iteration: 3428; Percent complete: 85.7%; Average loss: 2.7666
Iteration: 3429; Percent complete: 85.7%; Average loss: 2.9267
Iteration: 3430; Percent complete: 85.8%; Average loss: 2.6929
Iteration: 3431; Percent complete: 85.8%; Average loss: 2.9493
Iteration: 3432; Percent complete: 85.8%; Average loss: 2.6125
Iteration: 3433; Percent complete: 85.8%; Average loss: 2.8205
Iteration: 3434; Percent complete: 85.9%; Average loss: 2.8379
Iteration: 3435; Percent complete: 85.9%; Average loss: 2.8751
Iteration: 3436; Percent complete: 85.9%; Average loss: 2.8807
Iteration: 3437; Percent complete: 85.9%; Average loss: 2.6096
Iteration: 3438; Percent complete: 86.0%; Average loss: 2.7553
Iteration: 3439; Percent complete: 86.0%; Average loss: 2.8667
Iteration: 3440; Percent complete: 86.0%; Average loss: 2.8557
Iteration: 3441; Percent complete: 86.0%; Average loss: 2.7105
Iteration: 3442; Percent complete: 86.1%; Average loss: 2.7680
Iteration: 3443; Percent complete: 86.1%; Average loss: 2.7785
Iteration: 3444; Percent complete: 86.1%; Average loss: 2.7354
Iteration: 3445; Percent complete: 86.1%; Average loss: 2.7992
Iteration: 3446; Percent complete: 86.2%; Average loss: 2.7091
Iteration: 3447; Percent complete: 86.2%; Average loss: 2.6282
Iteration: 3448; Percent complete: 86.2%; Average loss: 2.9048
Iteration: 3449; Percent complete: 86.2%; Average loss: 2.7056
Iteration: 3450; Percent complete: 86.2%; Average loss: 2.8926
Iteration: 3451; Percent complete: 86.3%; Average loss: 2.6790
Iteration: 3452; Percent complete: 86.3%; Average loss: 2.9585
Iteration: 3453; Percent complete: 86.3%; Average loss: 2.8282
Iteration: 3454; Percent complete: 86.4%; Average loss: 2.6541
Iteration: 3455; Percent complete: 86.4%; Average loss: 2.9175
Iteration: 3456; Percent complete: 86.4%; Average loss: 2.4908
Iteration: 3457; Percent complete: 86.4%; Average loss: 2.9156
Iteration: 3458; Percent complete: 86.5%; Average loss: 2.8644
Iteration: 3459; Percent complete: 86.5%; Average loss: 2.6478
Iteration: 3460; Percent complete: 86.5%; Average loss: 2.8448
Iteration: 3461; Percent complete: 86.5%; Average loss: 2.6600
Iteration: 3462; Percent complete: 86.6%; Average loss: 2.7076
Iteration: 3463; Percent complete: 86.6%; Average loss: 2.9560
Iteration: 3464; Percent complete: 86.6%; Average loss: 2.6891
Iteration: 3465; Percent complete: 86.6%; Average loss: 3.0382
Iteration: 3466; Percent complete: 86.7%; Average loss: 2.6106
Iteration: 3467; Percent complete: 86.7%; Average loss: 2.4815
Iteration: 3468; Percent complete: 86.7%; Average loss: 3.0143
Iteration: 3469; Percent complete: 86.7%; Average loss: 2.8234
Iteration: 3470; Percent complete: 86.8%; Average loss: 2.8715
Iteration: 3471; Percent complete: 86.8%; Average loss: 2.7909
Iteration: 3472; Percent complete: 86.8%; Average loss: 2.8155
Iteration: 3473; Percent complete: 86.8%; Average loss: 2.6992
Iteration: 3474; Percent complete: 86.9%; Average loss: 2.8330
Iteration: 3475; Percent complete: 86.9%; Average loss: 2.6941
Iteration: 3476; Percent complete: 86.9%; Average loss: 2.8476
Iteration: 3477; Percent complete: 86.9%; Average loss: 2.7138
Iteration: 3478; Percent complete: 87.0%; Average loss: 2.7075
Iteration: 3479; Percent complete: 87.0%; Average loss: 2.7653
Iteration: 3480; Percent complete: 87.0%; Average loss: 2.7057
Iteration: 3481; Percent complete: 87.0%; Average loss: 2.8038
Iteration: 3482; Percent complete: 87.1%; Average loss: 2.5443
Iteration: 3483; Percent complete: 87.1%; Average loss: 2.8644
Iteration: 3484; Percent complete: 87.1%; Average loss: 2.7919
Iteration: 3485; Percent complete: 87.1%; Average loss: 3.0007
Iteration: 3486; Percent complete: 87.2%; Average loss: 2.8077
Iteration: 3487; Percent complete: 87.2%; Average loss: 2.7783
Iteration: 3488; Percent complete: 87.2%; Average loss: 2.5777
Iteration: 3489; Percent complete: 87.2%; Average loss: 2.8101
Iteration: 3490; Percent complete: 87.2%; Average loss: 2.8722
Iteration: 3491; Percent complete: 87.3%; Average loss: 2.5206
Iteration: 3492; Percent complete: 87.3%; Average loss: 2.8237
Iteration: 3493; Percent complete: 87.3%; Average loss: 2.5615
Iteration: 3494; Percent complete: 87.4%; Average loss: 2.8507
Iteration: 3495; Percent complete: 87.4%; Average loss: 3.1050
Iteration: 3496; Percent complete: 87.4%; Average loss: 2.5624
Iteration: 3497; Percent complete: 87.4%; Average loss: 2.8244
Iteration: 3498; Percent complete: 87.5%; Average loss: 2.7335
Iteration: 3499; Percent complete: 87.5%; Average loss: 2.9600
Iteration: 3500; Percent complete: 87.5%; Average loss: 2.8500
Iteration: 3501; Percent complete: 87.5%; Average loss: 2.6470
Iteration: 3502; Percent complete: 87.5%; Average loss: 2.6880
Iteration: 3503; Percent complete: 87.6%; Average loss: 2.7934
Iteration: 3504; Percent complete: 87.6%; Average loss: 2.8369
Iteration: 3505; Percent complete: 87.6%; Average loss: 2.9431
Iteration: 3506; Percent complete: 87.6%; Average loss: 2.5942
Iteration: 3507; Percent complete: 87.7%; Average loss: 2.9053
Iteration: 3508; Percent complete: 87.7%; Average loss: 2.5051
Iteration: 3509; Percent complete: 87.7%; Average loss: 2.5756
Iteration: 3510; Percent complete: 87.8%; Average loss: 2.9364
Iteration: 3511; Percent complete: 87.8%; Average loss: 2.6477
Iteration: 3512; Percent complete: 87.8%; Average loss: 2.8245
Iteration: 3513; Percent complete: 87.8%; Average loss: 3.0058
Iteration: 3514; Percent complete: 87.8%; Average loss: 2.7686
Iteration: 3515; Percent complete: 87.9%; Average loss: 2.8590
Iteration: 3516; Percent complete: 87.9%; Average loss: 2.6487
Iteration: 3517; Percent complete: 87.9%; Average loss: 2.8351
Iteration: 3518; Percent complete: 87.9%; Average loss: 2.7727
Iteration: 3519; Percent complete: 88.0%; Average loss: 2.8025
Iteration: 3520; Percent complete: 88.0%; Average loss: 2.7664
Iteration: 3521; Percent complete: 88.0%; Average loss: 2.5028
Iteration: 3522; Percent complete: 88.0%; Average loss: 2.6571
Iteration: 3523; Percent complete: 88.1%; Average loss: 2.7582
Iteration: 3524; Percent complete: 88.1%; Average loss: 2.8729
Iteration: 3525; Percent complete: 88.1%; Average loss: 2.8832
Iteration: 3526; Percent complete: 88.1%; Average loss: 2.7556
Iteration: 3527; Percent complete: 88.2%; Average loss: 2.6413
Iteration: 3528; Percent complete: 88.2%; Average loss: 2.7945
Iteration: 3529; Percent complete: 88.2%; Average loss: 2.7763
Iteration: 3530; Percent complete: 88.2%; Average loss: 2.6786
Iteration: 3531; Percent complete: 88.3%; Average loss: 2.6492
Iteration: 3532; Percent complete: 88.3%; Average loss: 2.8672
Iteration: 3533; Percent complete: 88.3%; Average loss: 2.8236
Iteration: 3534; Percent complete: 88.3%; Average loss: 2.6451
Iteration: 3535; Percent complete: 88.4%; Average loss: 2.6855
Iteration: 3536; Percent complete: 88.4%; Average loss: 2.7670
Iteration: 3537; Percent complete: 88.4%; Average loss: 2.5727
Iteration: 3538; Percent complete: 88.4%; Average loss: 2.8058
Iteration: 3539; Percent complete: 88.5%; Average loss: 2.6705
Iteration: 3540; Percent complete: 88.5%; Average loss: 2.6360
Iteration: 3541; Percent complete: 88.5%; Average loss: 2.7632
Iteration: 3542; Percent complete: 88.5%; Average loss: 2.5943
Iteration: 3543; Percent complete: 88.6%; Average loss: 2.6123
Iteration: 3544; Percent complete: 88.6%; Average loss: 2.9912
Iteration: 3545; Percent complete: 88.6%; Average loss: 2.4629
Iteration: 3546; Percent complete: 88.6%; Average loss: 2.9337
Iteration: 3547; Percent complete: 88.7%; Average loss: 2.8922
Iteration: 3548; Percent complete: 88.7%; Average loss: 2.7772
Iteration: 3549; Percent complete: 88.7%; Average loss: 2.7429
Iteration: 3550; Percent complete: 88.8%; Average loss: 2.8476
Iteration: 3551; Percent complete: 88.8%; Average loss: 2.7800
Iteration: 3552; Percent complete: 88.8%; Average loss: 2.8223
Iteration: 3553; Percent complete: 88.8%; Average loss: 2.8987
Iteration: 3554; Percent complete: 88.8%; Average loss: 3.0089
Iteration: 3555; Percent complete: 88.9%; Average loss: 2.8265
Iteration: 3556; Percent complete: 88.9%; Average loss: 2.7458
Iteration: 3557; Percent complete: 88.9%; Average loss: 2.5786
Iteration: 3558; Percent complete: 88.9%; Average loss: 2.5901
Iteration: 3559; Percent complete: 89.0%; Average loss: 2.7098
Iteration: 3560; Percent complete: 89.0%; Average loss: 2.5939
Iteration: 3561; Percent complete: 89.0%; Average loss: 2.9936
Iteration: 3562; Percent complete: 89.0%; Average loss: 2.6592
Iteration: 3563; Percent complete: 89.1%; Average loss: 2.7173
Iteration: 3564; Percent complete: 89.1%; Average loss: 2.8519
Iteration: 3565; Percent complete: 89.1%; Average loss: 2.6322
Iteration: 3566; Percent complete: 89.1%; Average loss: 2.7219
Iteration: 3567; Percent complete: 89.2%; Average loss: 2.7884
Iteration: 3568; Percent complete: 89.2%; Average loss: 2.8861
Iteration: 3569; Percent complete: 89.2%; Average loss: 2.6845
Iteration: 3570; Percent complete: 89.2%; Average loss: 2.5903
Iteration: 3571; Percent complete: 89.3%; Average loss: 2.7217
Iteration: 3572; Percent complete: 89.3%; Average loss: 2.7645
Iteration: 3573; Percent complete: 89.3%; Average loss: 2.7132
Iteration: 3574; Percent complete: 89.3%; Average loss: 2.7421
Iteration: 3575; Percent complete: 89.4%; Average loss: 2.7938
Iteration: 3576; Percent complete: 89.4%; Average loss: 2.8211
Iteration: 3577; Percent complete: 89.4%; Average loss: 2.9227
Iteration: 3578; Percent complete: 89.5%; Average loss: 2.5457
Iteration: 3579; Percent complete: 89.5%; Average loss: 2.8128
Iteration: 3580; Percent complete: 89.5%; Average loss: 2.5541
Iteration: 3581; Percent complete: 89.5%; Average loss: 2.5247
Iteration: 3582; Percent complete: 89.5%; Average loss: 2.4968
Iteration: 3583; Percent complete: 89.6%; Average loss: 2.6619
Iteration: 3584; Percent complete: 89.6%; Average loss: 2.6573
Iteration: 3585; Percent complete: 89.6%; Average loss: 2.7980
Iteration: 3586; Percent complete: 89.6%; Average loss: 2.7569
Iteration: 3587; Percent complete: 89.7%; Average loss: 2.7904
Iteration: 3588; Percent complete: 89.7%; Average loss: 2.6542
Iteration: 3589; Percent complete: 89.7%; Average loss: 2.8144
Iteration: 3590; Percent complete: 89.8%; Average loss: 2.6776
Iteration: 3591; Percent complete: 89.8%; Average loss: 2.6465
Iteration: 3592; Percent complete: 89.8%; Average loss: 2.6469
Iteration: 3593; Percent complete: 89.8%; Average loss: 2.7466
Iteration: 3594; Percent complete: 89.8%; Average loss: 2.8005
Iteration: 3595; Percent complete: 89.9%; Average loss: 2.6576
Iteration: 3596; Percent complete: 89.9%; Average loss: 2.6832
Iteration: 3597; Percent complete: 89.9%; Average loss: 2.7236
Iteration: 3598; Percent complete: 90.0%; Average loss: 2.5707
Iteration: 3599; Percent complete: 90.0%; Average loss: 2.6917
Iteration: 3600; Percent complete: 90.0%; Average loss: 2.7171
Iteration: 3601; Percent complete: 90.0%; Average loss: 2.6960
Iteration: 3602; Percent complete: 90.0%; Average loss: 2.6240
Iteration: 3603; Percent complete: 90.1%; Average loss: 2.8094
Iteration: 3604; Percent complete: 90.1%; Average loss: 2.6838
Iteration: 3605; Percent complete: 90.1%; Average loss: 2.7536
Iteration: 3606; Percent complete: 90.1%; Average loss: 2.8535
Iteration: 3607; Percent complete: 90.2%; Average loss: 2.8113
Iteration: 3608; Percent complete: 90.2%; Average loss: 2.5538
Iteration: 3609; Percent complete: 90.2%; Average loss: 2.9542
Iteration: 3610; Percent complete: 90.2%; Average loss: 2.5807
Iteration: 3611; Percent complete: 90.3%; Average loss: 2.9310
Iteration: 3612; Percent complete: 90.3%; Average loss: 2.5558
Iteration: 3613; Percent complete: 90.3%; Average loss: 2.6573
Iteration: 3614; Percent complete: 90.3%; Average loss: 2.9581
Iteration: 3615; Percent complete: 90.4%; Average loss: 2.7868
Iteration: 3616; Percent complete: 90.4%; Average loss: 2.7419
Iteration: 3617; Percent complete: 90.4%; Average loss: 2.6592
Iteration: 3618; Percent complete: 90.5%; Average loss: 2.9337
Iteration: 3619; Percent complete: 90.5%; Average loss: 2.7412
Iteration: 3620; Percent complete: 90.5%; Average loss: 2.5186
Iteration: 3621; Percent complete: 90.5%; Average loss: 2.9244
Iteration: 3622; Percent complete: 90.5%; Average loss: 2.5896
Iteration: 3623; Percent complete: 90.6%; Average loss: 2.6743
Iteration: 3624; Percent complete: 90.6%; Average loss: 2.8344
Iteration: 3625; Percent complete: 90.6%; Average loss: 2.9306
Iteration: 3626; Percent complete: 90.6%; Average loss: 2.4142
Iteration: 3627; Percent complete: 90.7%; Average loss: 2.8788
Iteration: 3628; Percent complete: 90.7%; Average loss: 2.8094
Iteration: 3629; Percent complete: 90.7%; Average loss: 2.7569
Iteration: 3630; Percent complete: 90.8%; Average loss: 2.5844
Iteration: 3631; Percent complete: 90.8%; Average loss: 2.7865
Iteration: 3632; Percent complete: 90.8%; Average loss: 2.6263
Iteration: 3633; Percent complete: 90.8%; Average loss: 2.5419
Iteration: 3634; Percent complete: 90.8%; Average loss: 2.9536
Iteration: 3635; Percent complete: 90.9%; Average loss: 2.9117
Iteration: 3636; Percent complete: 90.9%; Average loss: 2.6965
Iteration: 3637; Percent complete: 90.9%; Average loss: 2.7271
Iteration: 3638; Percent complete: 91.0%; Average loss: 2.7856
Iteration: 3639; Percent complete: 91.0%; Average loss: 2.8331
Iteration: 3640; Percent complete: 91.0%; Average loss: 2.7198
Iteration: 3641; Percent complete: 91.0%; Average loss: 2.8181
Iteration: 3642; Percent complete: 91.0%; Average loss: 2.8555
Iteration: 3643; Percent complete: 91.1%; Average loss: 2.7277
Iteration: 3644; Percent complete: 91.1%; Average loss: 2.9345
Iteration: 3645; Percent complete: 91.1%; Average loss: 2.4495
Iteration: 3646; Percent complete: 91.1%; Average loss: 2.8994
Iteration: 3647; Percent complete: 91.2%; Average loss: 2.8730
Iteration: 3648; Percent complete: 91.2%; Average loss: 2.8066
Iteration: 3649; Percent complete: 91.2%; Average loss: 2.6124
Iteration: 3650; Percent complete: 91.2%; Average loss: 2.3599
Iteration: 3651; Percent complete: 91.3%; Average loss: 2.5714
Iteration: 3652; Percent complete: 91.3%; Average loss: 2.7205
Iteration: 3653; Percent complete: 91.3%; Average loss: 2.7925
Iteration: 3654; Percent complete: 91.3%; Average loss: 2.9260
Iteration: 3655; Percent complete: 91.4%; Average loss: 2.8047
Iteration: 3656; Percent complete: 91.4%; Average loss: 2.8127
Iteration: 3657; Percent complete: 91.4%; Average loss: 2.6889
Iteration: 3658; Percent complete: 91.5%; Average loss: 2.3977
Iteration: 3659; Percent complete: 91.5%; Average loss: 2.6312
Iteration: 3660; Percent complete: 91.5%; Average loss: 2.4262
Iteration: 3661; Percent complete: 91.5%; Average loss: 2.5037
Iteration: 3662; Percent complete: 91.5%; Average loss: 2.7494
Iteration: 3663; Percent complete: 91.6%; Average loss: 2.6109
Iteration: 3664; Percent complete: 91.6%; Average loss: 2.7354
Iteration: 3665; Percent complete: 91.6%; Average loss: 2.9323
Iteration: 3666; Percent complete: 91.6%; Average loss: 2.7386
Iteration: 3667; Percent complete: 91.7%; Average loss: 2.8920
Iteration: 3668; Percent complete: 91.7%; Average loss: 2.7586
Iteration: 3669; Percent complete: 91.7%; Average loss: 2.9513
Iteration: 3670; Percent complete: 91.8%; Average loss: 2.7179
Iteration: 3671; Percent complete: 91.8%; Average loss: 2.8550
Iteration: 3672; Percent complete: 91.8%; Average loss: 2.5243
Iteration: 3673; Percent complete: 91.8%; Average loss: 2.4683
Iteration: 3674; Percent complete: 91.8%; Average loss: 2.7738
Iteration: 3675; Percent complete: 91.9%; Average loss: 2.5395
Iteration: 3676; Percent complete: 91.9%; Average loss: 2.5554
Iteration: 3677; Percent complete: 91.9%; Average loss: 2.7883
Iteration: 3678; Percent complete: 92.0%; Average loss: 2.5655
Iteration: 3679; Percent complete: 92.0%; Average loss: 2.7138
Iteration: 3680; Percent complete: 92.0%; Average loss: 2.7963
Iteration: 3681; Percent complete: 92.0%; Average loss: 2.6066
Iteration: 3682; Percent complete: 92.0%; Average loss: 2.8573
Iteration: 3683; Percent complete: 92.1%; Average loss: 2.8574
Iteration: 3684; Percent complete: 92.1%; Average loss: 2.9195
Iteration: 3685; Percent complete: 92.1%; Average loss: 2.9262
Iteration: 3686; Percent complete: 92.2%; Average loss: 2.8515
Iteration: 3687; Percent complete: 92.2%; Average loss: 2.8767
Iteration: 3688; Percent complete: 92.2%; Average loss: 2.7377
Iteration: 3689; Percent complete: 92.2%; Average loss: 2.5811
Iteration: 3690; Percent complete: 92.2%; Average loss: 2.6533
Iteration: 3691; Percent complete: 92.3%; Average loss: 2.4159
Iteration: 3692; Percent complete: 92.3%; Average loss: 2.6473
Iteration: 3693; Percent complete: 92.3%; Average loss: 2.7073
Iteration: 3694; Percent complete: 92.3%; Average loss: 2.6638
Iteration: 3695; Percent complete: 92.4%; Average loss: 2.5513
Iteration: 3696; Percent complete: 92.4%; Average loss: 2.9140
Iteration: 3697; Percent complete: 92.4%; Average loss: 2.5843
Iteration: 3698; Percent complete: 92.5%; Average loss: 2.8045
Iteration: 3699; Percent complete: 92.5%; Average loss: 2.7185
Iteration: 3700; Percent complete: 92.5%; Average loss: 2.4776
Iteration: 3701; Percent complete: 92.5%; Average loss: 2.6103
Iteration: 3702; Percent complete: 92.5%; Average loss: 2.6123
Iteration: 3703; Percent complete: 92.6%; Average loss: 2.7158
Iteration: 3704; Percent complete: 92.6%; Average loss: 2.6857
Iteration: 3705; Percent complete: 92.6%; Average loss: 2.7070
Iteration: 3706; Percent complete: 92.7%; Average loss: 2.6314
Iteration: 3707; Percent complete: 92.7%; Average loss: 2.8436
Iteration: 3708; Percent complete: 92.7%; Average loss: 2.5625
Iteration: 3709; Percent complete: 92.7%; Average loss: 2.6426
Iteration: 3710; Percent complete: 92.8%; Average loss: 2.5144
Iteration: 3711; Percent complete: 92.8%; Average loss: 2.8085
Iteration: 3712; Percent complete: 92.8%; Average loss: 2.5570
Iteration: 3713; Percent complete: 92.8%; Average loss: 2.9083
Iteration: 3714; Percent complete: 92.8%; Average loss: 2.8350
Iteration: 3715; Percent complete: 92.9%; Average loss: 2.7106
Iteration: 3716; Percent complete: 92.9%; Average loss: 2.6206
Iteration: 3717; Percent complete: 92.9%; Average loss: 2.6315
Iteration: 3718; Percent complete: 93.0%; Average loss: 2.5202
Iteration: 3719; Percent complete: 93.0%; Average loss: 2.9275
Iteration: 3720; Percent complete: 93.0%; Average loss: 2.7637
Iteration: 3721; Percent complete: 93.0%; Average loss: 2.3723
Iteration: 3722; Percent complete: 93.0%; Average loss: 2.4069
Iteration: 3723; Percent complete: 93.1%; Average loss: 2.8063
Iteration: 3724; Percent complete: 93.1%; Average loss: 2.5419
Iteration: 3725; Percent complete: 93.1%; Average loss: 2.7951
Iteration: 3726; Percent complete: 93.2%; Average loss: 2.8226
Iteration: 3727; Percent complete: 93.2%; Average loss: 2.5288
Iteration: 3728; Percent complete: 93.2%; Average loss: 2.4905
Iteration: 3729; Percent complete: 93.2%; Average loss: 2.9239
Iteration: 3730; Percent complete: 93.2%; Average loss: 2.8547
Iteration: 3731; Percent complete: 93.3%; Average loss: 2.6703
Iteration: 3732; Percent complete: 93.3%; Average loss: 2.7960
Iteration: 3733; Percent complete: 93.3%; Average loss: 2.9794
Iteration: 3734; Percent complete: 93.3%; Average loss: 2.4646
Iteration: 3735; Percent complete: 93.4%; Average loss: 2.8199
Iteration: 3736; Percent complete: 93.4%; Average loss: 2.7885
Iteration: 3737; Percent complete: 93.4%; Average loss: 2.7589
Iteration: 3738; Percent complete: 93.5%; Average loss: 2.5107
Iteration: 3739; Percent complete: 93.5%; Average loss: 2.7360
Iteration: 3740; Percent complete: 93.5%; Average loss: 2.6093
Iteration: 3741; Percent complete: 93.5%; Average loss: 2.7690
Iteration: 3742; Percent complete: 93.5%; Average loss: 2.5646
Iteration: 3743; Percent complete: 93.6%; Average loss: 2.6378
Iteration: 3744; Percent complete: 93.6%; Average loss: 2.7264
Iteration: 3745; Percent complete: 93.6%; Average loss: 2.7803
Iteration: 3746; Percent complete: 93.7%; Average loss: 2.7896
Iteration: 3747; Percent complete: 93.7%; Average loss: 2.5977
Iteration: 3748; Percent complete: 93.7%; Average loss: 2.9345
Iteration: 3749; Percent complete: 93.7%; Average loss: 2.6823
Iteration: 3750; Percent complete: 93.8%; Average loss: 2.5242
Iteration: 3751; Percent complete: 93.8%; Average loss: 2.8854
Iteration: 3752; Percent complete: 93.8%; Average loss: 2.9358
Iteration: 3753; Percent complete: 93.8%; Average loss: 2.7383
Iteration: 3754; Percent complete: 93.8%; Average loss: 2.8275
Iteration: 3755; Percent complete: 93.9%; Average loss: 2.7721
Iteration: 3756; Percent complete: 93.9%; Average loss: 2.8305
Iteration: 3757; Percent complete: 93.9%; Average loss: 2.9072
Iteration: 3758; Percent complete: 94.0%; Average loss: 2.8913
Iteration: 3759; Percent complete: 94.0%; Average loss: 2.4525
Iteration: 3760; Percent complete: 94.0%; Average loss: 2.7066
Iteration: 3761; Percent complete: 94.0%; Average loss: 2.7362
Iteration: 3762; Percent complete: 94.0%; Average loss: 2.6547
Iteration: 3763; Percent complete: 94.1%; Average loss: 2.8453
Iteration: 3764; Percent complete: 94.1%; Average loss: 2.4435
Iteration: 3765; Percent complete: 94.1%; Average loss: 2.7294
Iteration: 3766; Percent complete: 94.2%; Average loss: 2.5824
Iteration: 3767; Percent complete: 94.2%; Average loss: 2.8365
Iteration: 3768; Percent complete: 94.2%; Average loss: 2.9345
Iteration: 3769; Percent complete: 94.2%; Average loss: 2.7829
Iteration: 3770; Percent complete: 94.2%; Average loss: 2.8222
Iteration: 3771; Percent complete: 94.3%; Average loss: 2.7517
Iteration: 3772; Percent complete: 94.3%; Average loss: 2.5461
Iteration: 3773; Percent complete: 94.3%; Average loss: 2.6672
Iteration: 3774; Percent complete: 94.3%; Average loss: 2.6060
Iteration: 3775; Percent complete: 94.4%; Average loss: 2.6302
Iteration: 3776; Percent complete: 94.4%; Average loss: 2.5679
Iteration: 3777; Percent complete: 94.4%; Average loss: 2.8592
Iteration: 3778; Percent complete: 94.5%; Average loss: 2.7212
Iteration: 3779; Percent complete: 94.5%; Average loss: 2.7124
Iteration: 3780; Percent complete: 94.5%; Average loss: 2.7530
Iteration: 3781; Percent complete: 94.5%; Average loss: 2.5464
Iteration: 3782; Percent complete: 94.5%; Average loss: 2.5246
Iteration: 3783; Percent complete: 94.6%; Average loss: 2.6491
Iteration: 3784; Percent complete: 94.6%; Average loss: 2.7643
Iteration: 3785; Percent complete: 94.6%; Average loss: 2.9072
Iteration: 3786; Percent complete: 94.7%; Average loss: 2.6514
Iteration: 3787; Percent complete: 94.7%; Average loss: 2.6156
Iteration: 3788; Percent complete: 94.7%; Average loss: 2.6841
Iteration: 3789; Percent complete: 94.7%; Average loss: 2.9180
Iteration: 3790; Percent complete: 94.8%; Average loss: 2.6295
Iteration: 3791; Percent complete: 94.8%; Average loss: 2.5265
Iteration: 3792; Percent complete: 94.8%; Average loss: 2.8420
Iteration: 3793; Percent complete: 94.8%; Average loss: 2.5820
Iteration: 3794; Percent complete: 94.8%; Average loss: 2.6845
Iteration: 3795; Percent complete: 94.9%; Average loss: 2.7930
Iteration: 3796; Percent complete: 94.9%; Average loss: 2.6047
Iteration: 3797; Percent complete: 94.9%; Average loss: 2.8883
Iteration: 3798; Percent complete: 95.0%; Average loss: 2.5566
Iteration: 3799; Percent complete: 95.0%; Average loss: 2.4828
Iteration: 3800; Percent complete: 95.0%; Average loss: 2.6927
Iteration: 3801; Percent complete: 95.0%; Average loss: 2.5629
Iteration: 3802; Percent complete: 95.0%; Average loss: 2.5238
Iteration: 3803; Percent complete: 95.1%; Average loss: 2.8142
Iteration: 3804; Percent complete: 95.1%; Average loss: 2.5845
Iteration: 3805; Percent complete: 95.1%; Average loss: 2.4143
Iteration: 3806; Percent complete: 95.2%; Average loss: 2.7611
Iteration: 3807; Percent complete: 95.2%; Average loss: 2.7656
Iteration: 3808; Percent complete: 95.2%; Average loss: 2.7193
Iteration: 3809; Percent complete: 95.2%; Average loss: 2.7625
Iteration: 3810; Percent complete: 95.2%; Average loss: 2.5836
Iteration: 3811; Percent complete: 95.3%; Average loss: 2.6784
Iteration: 3812; Percent complete: 95.3%; Average loss: 2.8573
Iteration: 3813; Percent complete: 95.3%; Average loss: 2.5007
Iteration: 3814; Percent complete: 95.3%; Average loss: 2.6860
Iteration: 3815; Percent complete: 95.4%; Average loss: 2.6515
Iteration: 3816; Percent complete: 95.4%; Average loss: 2.7354
Iteration: 3817; Percent complete: 95.4%; Average loss: 2.5423
Iteration: 3818; Percent complete: 95.5%; Average loss: 2.9477
Iteration: 3819; Percent complete: 95.5%; Average loss: 2.6485
Iteration: 3820; Percent complete: 95.5%; Average loss: 2.8498
Iteration: 3821; Percent complete: 95.5%; Average loss: 2.8109
Iteration: 3822; Percent complete: 95.5%; Average loss: 2.5077
Iteration: 3823; Percent complete: 95.6%; Average loss: 2.5580
Iteration: 3824; Percent complete: 95.6%; Average loss: 3.0945
Iteration: 3825; Percent complete: 95.6%; Average loss: 2.7066
Iteration: 3826; Percent complete: 95.7%; Average loss: 2.6901
Iteration: 3827; Percent complete: 95.7%; Average loss: 2.5853
Iteration: 3828; Percent complete: 95.7%; Average loss: 2.6811
Iteration: 3829; Percent complete: 95.7%; Average loss: 2.9072
Iteration: 3830; Percent complete: 95.8%; Average loss: 2.8413
Iteration: 3831; Percent complete: 95.8%; Average loss: 2.5272
Iteration: 3832; Percent complete: 95.8%; Average loss: 2.3703
Iteration: 3833; Percent complete: 95.8%; Average loss: 2.6229
Iteration: 3834; Percent complete: 95.9%; Average loss: 2.7241
Iteration: 3835; Percent complete: 95.9%; Average loss: 2.3875
Iteration: 3836; Percent complete: 95.9%; Average loss: 2.8266
Iteration: 3837; Percent complete: 95.9%; Average loss: 2.7259
Iteration: 3838; Percent complete: 96.0%; Average loss: 2.8418
Iteration: 3839; Percent complete: 96.0%; Average loss: 2.6658
Iteration: 3840; Percent complete: 96.0%; Average loss: 2.6583
Iteration: 3841; Percent complete: 96.0%; Average loss: 2.5611
Iteration: 3842; Percent complete: 96.0%; Average loss: 2.7610
Iteration: 3843; Percent complete: 96.1%; Average loss: 2.4891
Iteration: 3844; Percent complete: 96.1%; Average loss: 2.5294
Iteration: 3845; Percent complete: 96.1%; Average loss: 2.4090
Iteration: 3846; Percent complete: 96.2%; Average loss: 2.6624
Iteration: 3847; Percent complete: 96.2%; Average loss: 2.4550
Iteration: 3848; Percent complete: 96.2%; Average loss: 2.7882
Iteration: 3849; Percent complete: 96.2%; Average loss: 2.8097
Iteration: 3850; Percent complete: 96.2%; Average loss: 2.7522
Iteration: 3851; Percent complete: 96.3%; Average loss: 2.6550
Iteration: 3852; Percent complete: 96.3%; Average loss: 2.5670
Iteration: 3853; Percent complete: 96.3%; Average loss: 2.7467
Iteration: 3854; Percent complete: 96.4%; Average loss: 2.6002
Iteration: 3855; Percent complete: 96.4%; Average loss: 2.5665
Iteration: 3856; Percent complete: 96.4%; Average loss: 2.7107
Iteration: 3857; Percent complete: 96.4%; Average loss: 2.7387
Iteration: 3858; Percent complete: 96.5%; Average loss: 2.6009
Iteration: 3859; Percent complete: 96.5%; Average loss: 2.3953
Iteration: 3860; Percent complete: 96.5%; Average loss: 2.5238
Iteration: 3861; Percent complete: 96.5%; Average loss: 2.7786
Iteration: 3862; Percent complete: 96.5%; Average loss: 2.7488
Iteration: 3863; Percent complete: 96.6%; Average loss: 2.8042
Iteration: 3864; Percent complete: 96.6%; Average loss: 2.4991
Iteration: 3865; Percent complete: 96.6%; Average loss: 2.5600
Iteration: 3866; Percent complete: 96.7%; Average loss: 2.6140
Iteration: 3867; Percent complete: 96.7%; Average loss: 2.8259
Iteration: 3868; Percent complete: 96.7%; Average loss: 2.6103
Iteration: 3869; Percent complete: 96.7%; Average loss: 2.7022
Iteration: 3870; Percent complete: 96.8%; Average loss: 2.7166
Iteration: 3871; Percent complete: 96.8%; Average loss: 2.6965
Iteration: 3872; Percent complete: 96.8%; Average loss: 2.7937
Iteration: 3873; Percent complete: 96.8%; Average loss: 2.6897
Iteration: 3874; Percent complete: 96.9%; Average loss: 2.8033
Iteration: 3875; Percent complete: 96.9%; Average loss: 2.4331
Iteration: 3876; Percent complete: 96.9%; Average loss: 2.7478
Iteration: 3877; Percent complete: 96.9%; Average loss: 2.7823
Iteration: 3878; Percent complete: 97.0%; Average loss: 2.5634
Iteration: 3879; Percent complete: 97.0%; Average loss: 2.4917
Iteration: 3880; Percent complete: 97.0%; Average loss: 2.5527
Iteration: 3881; Percent complete: 97.0%; Average loss: 2.6292
Iteration: 3882; Percent complete: 97.0%; Average loss: 2.6273
Iteration: 3883; Percent complete: 97.1%; Average loss: 2.5358
Iteration: 3884; Percent complete: 97.1%; Average loss: 2.8261
Iteration: 3885; Percent complete: 97.1%; Average loss: 2.9105
Iteration: 3886; Percent complete: 97.2%; Average loss: 2.8057
Iteration: 3887; Percent complete: 97.2%; Average loss: 2.6698
Iteration: 3888; Percent complete: 97.2%; Average loss: 2.6492
Iteration: 3889; Percent complete: 97.2%; Average loss: 2.6992
Iteration: 3890; Percent complete: 97.2%; Average loss: 2.6946
Iteration: 3891; Percent complete: 97.3%; Average loss: 2.8203
Iteration: 3892; Percent complete: 97.3%; Average loss: 2.7382
Iteration: 3893; Percent complete: 97.3%; Average loss: 2.6431
Iteration: 3894; Percent complete: 97.4%; Average loss: 2.7770
Iteration: 3895; Percent complete: 97.4%; Average loss: 2.5978
Iteration: 3896; Percent complete: 97.4%; Average loss: 2.8080
Iteration: 3897; Percent complete: 97.4%; Average loss: 2.7084
Iteration: 3898; Percent complete: 97.5%; Average loss: 2.5001
Iteration: 3899; Percent complete: 97.5%; Average loss: 2.5069
Iteration: 3900; Percent complete: 97.5%; Average loss: 2.6954
Iteration: 3901; Percent complete: 97.5%; Average loss: 2.5620
Iteration: 3902; Percent complete: 97.5%; Average loss: 2.4736
Iteration: 3903; Percent complete: 97.6%; Average loss: 2.6671
Iteration: 3904; Percent complete: 97.6%; Average loss: 2.6346
Iteration: 3905; Percent complete: 97.6%; Average loss: 2.4240
Iteration: 3906; Percent complete: 97.7%; Average loss: 2.8334
Iteration: 3907; Percent complete: 97.7%; Average loss: 2.7037
Iteration: 3908; Percent complete: 97.7%; Average loss: 2.5544
Iteration: 3909; Percent complete: 97.7%; Average loss: 2.7228
Iteration: 3910; Percent complete: 97.8%; Average loss: 2.7329
Iteration: 3911; Percent complete: 97.8%; Average loss: 2.4770
Iteration: 3912; Percent complete: 97.8%; Average loss: 2.5929
Iteration: 3913; Percent complete: 97.8%; Average loss: 2.4706
Iteration: 3914; Percent complete: 97.9%; Average loss: 2.5443
Iteration: 3915; Percent complete: 97.9%; Average loss: 2.7279
Iteration: 3916; Percent complete: 97.9%; Average loss: 2.7289
Iteration: 3917; Percent complete: 97.9%; Average loss: 2.6517
Iteration: 3918; Percent complete: 98.0%; Average loss: 2.5417
Iteration: 3919; Percent complete: 98.0%; Average loss: 2.6132
Iteration: 3920; Percent complete: 98.0%; Average loss: 2.4366
Iteration: 3921; Percent complete: 98.0%; Average loss: 2.6143
Iteration: 3922; Percent complete: 98.0%; Average loss: 2.7200
Iteration: 3923; Percent complete: 98.1%; Average loss: 2.5937
Iteration: 3924; Percent complete: 98.1%; Average loss: 2.7850
Iteration: 3925; Percent complete: 98.1%; Average loss: 2.8211
Iteration: 3926; Percent complete: 98.2%; Average loss: 2.6312
Iteration: 3927; Percent complete: 98.2%; Average loss: 2.5740
Iteration: 3928; Percent complete: 98.2%; Average loss: 2.5098
Iteration: 3929; Percent complete: 98.2%; Average loss: 2.4742
Iteration: 3930; Percent complete: 98.2%; Average loss: 2.5898
Iteration: 3931; Percent complete: 98.3%; Average loss: 2.3552
Iteration: 3932; Percent complete: 98.3%; Average loss: 2.4744
Iteration: 3933; Percent complete: 98.3%; Average loss: 2.5627
Iteration: 3934; Percent complete: 98.4%; Average loss: 2.5222
Iteration: 3935; Percent complete: 98.4%; Average loss: 2.7236
Iteration: 3936; Percent complete: 98.4%; Average loss: 2.6839
Iteration: 3937; Percent complete: 98.4%; Average loss: 2.6895
Iteration: 3938; Percent complete: 98.5%; Average loss: 2.6995
Iteration: 3939; Percent complete: 98.5%; Average loss: 2.4699
Iteration: 3940; Percent complete: 98.5%; Average loss: 2.5273
Iteration: 3941; Percent complete: 98.5%; Average loss: 2.6663
Iteration: 3942; Percent complete: 98.6%; Average loss: 2.5172
Iteration: 3943; Percent complete: 98.6%; Average loss: 2.7461
Iteration: 3944; Percent complete: 98.6%; Average loss: 2.7212
Iteration: 3945; Percent complete: 98.6%; Average loss: 2.7469
Iteration: 3946; Percent complete: 98.7%; Average loss: 2.7494
Iteration: 3947; Percent complete: 98.7%; Average loss: 2.8664
Iteration: 3948; Percent complete: 98.7%; Average loss: 2.4325
Iteration: 3949; Percent complete: 98.7%; Average loss: 2.6654
Iteration: 3950; Percent complete: 98.8%; Average loss: 2.5831
Iteration: 3951; Percent complete: 98.8%; Average loss: 2.7077
Iteration: 3952; Percent complete: 98.8%; Average loss: 2.5410
Iteration: 3953; Percent complete: 98.8%; Average loss: 2.8247
Iteration: 3954; Percent complete: 98.9%; Average loss: 2.6324
Iteration: 3955; Percent complete: 98.9%; Average loss: 2.5515
Iteration: 3956; Percent complete: 98.9%; Average loss: 2.6278
Iteration: 3957; Percent complete: 98.9%; Average loss: 2.3857
Iteration: 3958; Percent complete: 99.0%; Average loss: 2.5704
Iteration: 3959; Percent complete: 99.0%; Average loss: 2.5790
Iteration: 3960; Percent complete: 99.0%; Average loss: 2.3171
Iteration: 3961; Percent complete: 99.0%; Average loss: 2.5974
Iteration: 3962; Percent complete: 99.1%; Average loss: 2.5724
Iteration: 3963; Percent complete: 99.1%; Average loss: 2.5709
Iteration: 3964; Percent complete: 99.1%; Average loss: 2.5367
Iteration: 3965; Percent complete: 99.1%; Average loss: 2.4603
Iteration: 3966; Percent complete: 99.2%; Average loss: 2.8597
Iteration: 3967; Percent complete: 99.2%; Average loss: 2.5297
Iteration: 3968; Percent complete: 99.2%; Average loss: 2.4921
Iteration: 3969; Percent complete: 99.2%; Average loss: 2.5754
Iteration: 3970; Percent complete: 99.2%; Average loss: 2.4294
Iteration: 3971; Percent complete: 99.3%; Average loss: 2.5672
Iteration: 3972; Percent complete: 99.3%; Average loss: 2.5263
Iteration: 3973; Percent complete: 99.3%; Average loss: 2.6760
Iteration: 3974; Percent complete: 99.4%; Average loss: 2.6919
Iteration: 3975; Percent complete: 99.4%; Average loss: 2.6101
Iteration: 3976; Percent complete: 99.4%; Average loss: 2.6650
Iteration: 3977; Percent complete: 99.4%; Average loss: 2.4396
Iteration: 3978; Percent complete: 99.5%; Average loss: 2.6433
Iteration: 3979; Percent complete: 99.5%; Average loss: 2.8252
Iteration: 3980; Percent complete: 99.5%; Average loss: 2.6519
Iteration: 3981; Percent complete: 99.5%; Average loss: 2.7519
Iteration: 3982; Percent complete: 99.6%; Average loss: 2.5592
Iteration: 3983; Percent complete: 99.6%; Average loss: 2.4463
Iteration: 3984; Percent complete: 99.6%; Average loss: 2.7892
Iteration: 3985; Percent complete: 99.6%; Average loss: 2.8153
Iteration: 3986; Percent complete: 99.7%; Average loss: 2.5519
Iteration: 3987; Percent complete: 99.7%; Average loss: 2.6672
Iteration: 3988; Percent complete: 99.7%; Average loss: 2.4963
Iteration: 3989; Percent complete: 99.7%; Average loss: 2.6487
Iteration: 3990; Percent complete: 99.8%; Average loss: 2.5973
Iteration: 3991; Percent complete: 99.8%; Average loss: 2.7017
Iteration: 3992; Percent complete: 99.8%; Average loss: 2.4897
Iteration: 3993; Percent complete: 99.8%; Average loss: 2.7056
Iteration: 3994; Percent complete: 99.9%; Average loss: 2.8678
Iteration: 3995; Percent complete: 99.9%; Average loss: 2.5414
Iteration: 3996; Percent complete: 99.9%; Average loss: 2.7594
Iteration: 3997; Percent complete: 99.9%; Average loss: 2.4641
Iteration: 3998; Percent complete: 100.0%; Average loss: 2.4931
Iteration: 3999; Percent complete: 100.0%; Average loss: 2.4878
Iteration: 4000; Percent complete: 100.0%; Average loss: 2.5858
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 18.270 seconds)
