Chatbot Tutorial — PyTorch Tutorials 1.12.1+cu102 documentation (2022)

Shortcuts

beginner/chatbot_tutorial

Chatbot Tutorial — PyTorch Tutorials 1.12.1+cu102 documentation (1)

Run in Google Colab

Colab

Chatbot Tutorial — PyTorch Tutorials 1.12.1+cu102 documentation (2)

Download Notebook

Notebook

Chatbot Tutorial — PyTorch Tutorials 1.12.1+cu102 documentation (3)

View on GitHub

GitHub

Note

Click hereto download the full example code

Author: Matthew Inkawhich

In this tutorial, we explore a fun and interesting use-case of recurrentsequence-to-sequence models. We will train a simple chatbot using moviescripts from the Cornell Movie-DialogsCorpus.

Conversational models are a hot topic in artificial intelligenceresearch. Chatbots can be found in a variety of settings, includingcustomer service applications and online helpdesks. These bots are oftenpowered by retrieval-based models, which output predefined responses toquestions of certain forms. In a highly restricted domain like acompany’s IT helpdesk, these models may be sufficient, however, they arenot robust enough for more general use-cases. Teaching a machine tocarry out a meaningful conversation with a human in multiple domains isa research question that is far from solved. Recently, the deep learningboom has allowed for powerful generative models like Google’s NeuralConversational Model, which marksa large step towards multi-domain generative conversational models. Inthis tutorial, we will implement this kind of model in PyTorch.

Chatbot Tutorial — PyTorch Tutorials 1.12.1+cu102 documentation (4)

> 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 arrestBot: i m trying to help you !> i'm just kiddingBot: i m sorry .> where are you from?Bot: san francisco .> it's time for me to leaveBot: i know .> goodbyeBot: goodbye .

Tutorial Highlights

Acknowledgements

This tutorial borrows code from the following sources:

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

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

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

Preparations

To start, Download the data ZIP filehere

# and put in a ``data/`` directory under the current directory.## After that, let’s import some necessities.#from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionfrom __future__ import unicode_literalsimport torchfrom torch.jit import script, traceimport torch.nn as nnfrom torch import optimimport torch.nn.functional as Fimport csvimport randomimport reimport osimport unicodedataimport codecsfrom io import openimport itertoolsimport mathimport jsonUSE_CUDA = torch.cuda.is_available()device = torch.device("cuda" if USE_CUDA else "cpu")

Load & Preprocess Data

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

The Cornell Movie-DialogsCorpusis a rich dataset of movie character dialog:

  • 220,579 conversational exchanges between 10,292 pairs of moviecharacters

  • 9,035 characters from 617 movies

  • 304,713 total utterances

This dataset is large and diverse, and there is a great variation oflanguage formality, time periods, sentiment, etc. Our hope is that thisdiversity 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 theoriginal 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 linecontains a tab-separated query sentence and a response sentence pair.

The following functions facilitate the parsing of the rawutterances.jsonl data file.

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

  • extractSentencePairs extracts pairs of sentences fromconversations

# Splits each line of the file to create lines and conversationsdef 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 conversationsdef 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 itformatted_movie_lines.txt.

# Define path to new filedatafile = os.path.join(corpus, "formatted_movie_lines.txt")delimiter = '\t'# Unescape the delimiterdelimiter = str(codecs.decode(delimiter, "unicode_escape"))# Initialize lines dict and conversations dictlines = {}conversations = {}# Load lines and conversationsprint("\nProcessing corpus into lines and conversations...")lines, conversations = loadLinesAndConversations(os.path.join(corpus, "utterances.jsonl"))# Write new csv fileprint("\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 linesprint("\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 loadquery/response sentence pairs into memory.

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

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

# Default word tokensPAD_token = 0 # Used for padding short sentencesSOS_token = 1 # Start-of-sentence tokenEOS_token = 2 # End-of-sentence tokenclass 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 somepreprocessing.

First, we must convert the Unicode strings to ASCII usingunicodeToAscii. Next, we should convert all letters to lowercase andtrim all non-letter characters except for basic punctuation(normalizeString). Finally, to aid in training convergence, we willfilter out sentences with length greater than the MAX_LENGTHthreshold (filterPairs).

MAX_LENGTH = 10 # Maximum sentence length to consider# Turn a Unicode string to plain ASCII, thanks to# https://stackoverflow.com/a/518232/2809427def unicodeToAscii(s): return ''.join( c for c in unicodedata.normalize('NFD', s) if unicodedata.category(c) != 'Mn' )# Lowercase, trim, and remove non-letter charactersdef 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 objectdef readVocs(datafile, corpus_name): print("Reading lines...") # Read the file and split into lines lines = open(datafile, encoding='utf-8').\ read().strip().split('\n') # Split every line into pairs and normalize pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines] voc = Voc(corpus_name) return voc, pairs# Returns True iff both sentences in a pair 'p' are under the MAX_LENGTH thresholddef filterPair(p): # Input sequences need to preserve the last word for EOS token return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH# Filter pairs using filterPair conditiondef filterPairs(pairs): return [pair for pair in pairs if filterPair(pair)]# Using the functions defined above, return a populated voc object and pairs listdef 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 pairssave_dir = os.path.join("data", "save")voc, pairs = loadPrepareData(corpus, corpus_name, datafile, save_dir)# Print some pairs to validateprint("\npairs:")for pair in pairs[:10]: print(pair)
Start preparing training data ...Reading lines...Read 221282 sentence pairsTrimmed to 64313 sentence pairsCounting words...Counted words: 18082pairs:['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 duringtraining is trimming rarely used words out of our vocabulary. Decreasingthe feature space will also soften the difficulty of the function thatthe model must learn to approximate. We will do this as a two-stepprocess:

  1. Trim words used under MIN_COUNT threshold using the voc.trimfunction.

  2. Filter out pairs with trimmed words.

MIN_COUNT = 3 # Minimum word count threshold for trimmingdef 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 pairspairs = trimRareWords(voc, pairs, MIN_COUNT)
keep_words 7833 / 18079 = 0.4333Trimmed 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 ourdata into a nice vocabulary object and list of sentence pairs, our modelswill ultimately expect numerical torch tensors as inputs. One way toprepare the processed data for the models can be found in the seq2seqtranslationtutorial.In that tutorial, we use a batch size of 1, meaning that all we have todo is convert the words in our sentence pairs to their correspondingindexes from the vocabulary and feed this to the models.

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

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

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

Chatbot Tutorial — PyTorch Tutorials 1.12.1+cu102 documentation (5)

The inputVar function handles the process of converting sentences totensor, ultimately creating a correctly shaped zero-padded tensor. Italso returns a tensor of lengths for each of the sequences in thebatch 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 masktensor and a maximum target sentence length. The binary mask tensor hasthe same shape as the output target tensor, but every element that is aPAD_token is 0 and all others are 1.

batch2TrainData simply takes a bunch of pairs and returns the inputand 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 lengthsdef 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 lengthdef 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 pairsdef 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 validationsmall_batch_size = 5batches = batch2TrainData(voc, [random.choice(pairs) for _ in range(small_batch_size)])input_variable, lengths, target_variable, mask, max_target_len = batchesprint("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([[1226, 132, 85, 19, 4287], [ 14, 194, 401, 362, 10], [ 13, 160, 10, 10, 2], [ 24, 7, 2, 2, 0], [ 77, 5, 0, 0, 0], [ 960, 1554, 0, 0, 0], [2803, 14, 0, 0, 0], [ 10, 2, 0, 0, 0], [ 2, 0, 0, 0, 0]])lengths: tensor([9, 8, 4, 4, 3])target_variable: tensor([[162, 280, 234, 50, 8], [ 14, 585, 59, 505, 755], [ 62, 14, 14, 451, 101], [570, 2, 2, 14, 123], [217, 0, 0, 2, 14], [448, 0, 0, 0, 2], [ 14, 0, 0, 0, 0], [ 2, 0, 0, 0, 0]])mask: tensor([[ True, True, True, True, True], [ True, True, True, True, True], [ True, True, True, True, True], [ True, True, True, True, True], [ True, False, False, True, True], [ True, False, False, False, True], [ True, False, False, False, False], [ True, False, False, False, False]])max_target_len: 8

Define Models

Seq2Seq Model

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

Sutskever et al. discovered thatby using two separate recurrent neural nets together, we can accomplishthis task. One RNN acts as an encoder, which encodes a variablelength input sequence to a fixed-length context vector. In theory, thiscontext vector (the final hidden layer of the RNN) will contain semanticinformation about the query sentence that is input to the bot. Thesecond RNN is a decoder, which takes an input word and the contextvector, and returns a guess for the next word in the sequence and ahidden state to use in the next iteration.

Chatbot Tutorial — PyTorch Tutorials 1.12.1+cu102 documentation (6)

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” vectorand a “hidden state” vector. The hidden state vector is then passed tothe next time step, while the output vector is recorded. The encodertransforms the context it saw at each point in the sequence into a setof points in a high-dimensional space, which the decoder will use togenerate 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. in2014. We will use a bidirectional variant of the GRU, meaning that thereare essentially two independent RNNs: one that is fed the input sequencein normal sequential order, and one that is fed the input sequence inreverse order. The outputs of each network are summed at each time step.Using a bidirectional GRU will give us the advantage of encoding bothpast 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 inan arbitrarily sized feature space. For our models, this layer will mapeach word to a feature space of size hidden_size. When trained, thesevalues should encode semantic similarity between similar meaning words.

Finally, if passing a padded batch of sequences to an RNN module, wemust pack and unpack padding around the RNN pass usingnn.utils.rnn.pack_padded_sequence andnn.utils.rnn.pad_packed_sequence respectively.

Computation Graph:

  1. Convert word indexes to embeddings.

  2. Pack padded batch of sequences for RNN module.

  3. Forward pass through GRU.

  4. Unpack padding.

  5. Sum bidirectional GRU outputs.

  6. Return output and final hidden state.

Inputs:

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

  • input_lengths: list of sentence lengths corresponding to eachsentence 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 xnum_directions, batch_size, hidden_size)

class EncoderRNN(nn.Module): def __init__(self, hidden_size, embedding, n_layers=1, dropout=0): super(EncoderRNN, self).__init__() self.n_layers = n_layers self.hidden_size = hidden_size self.embedding = embedding # Initialize GRU; the input_size and hidden_size params are both set to 'hidden_size' # because our input size is a word embedding with number of features == hidden_size self.gru = nn.GRU(hidden_size, hidden_size, n_layers, dropout=(0 if n_layers == 1 else dropout), bidirectional=True) def forward(self, input_seq, input_lengths, hidden=None): # Convert word indexes to embeddings embedded = self.embedding(input_seq) # Pack padded batch of sequences for RNN module packed = nn.utils.rnn.pack_padded_sequence(embedded, input_lengths) # Forward pass through GRU outputs, hidden = self.gru(packed, hidden) # Unpack padding outputs, _ = nn.utils.rnn.pad_packed_sequence(outputs) # Sum bidirectional GRU outputs outputs = outputs[:, :, :self.hidden_size] + outputs[:, : ,self.hidden_size:] # Return output and final hidden state return outputs, hidden

Decoder

The decoder RNN generates the response sentence in a token-by-tokenfashion. It uses the encoder’s context vectors, and internal hiddenstates to generate the next word in the sequence. It continuesgenerating words until it outputs an EOS_token, representing the endof the sentence. A common problem with a vanilla seq2seq decoder is thatif we rely solely on the context vector to encode the entire inputsequence’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 payattention to certain parts of the input sequence, rather than using theentire fixed context at every step.

At a high level, attention is calculated using the decoder’s currenthidden state and the encoder’s outputs. The output attention weightshave the same shape as the input sequence, allowing us to multiply themby the encoder outputs, giving us a weighted sum which indicates theparts of encoder output to pay attention to. SeanRobertson’s figure describes this verywell:

Chatbot Tutorial — PyTorch Tutorials 1.12.1+cu102 documentation (8)

Luong et al. improved uponBahdanau et al.’s groundwork by creating “Global attention”. The keydifference is that with “Global attention”, we consider all of theencoder’s hidden states, as opposed to Bahdanau et al.’s “Localattention”, which only considers the encoder’s hidden state from thecurrent time step. Another difference is that with “Global attention”,we calculate attention weights, or energies, using the hidden state ofthe decoder from the current time step only. Bahdanau et al.’s attentioncalculation requires knowledge of the decoder’s state from the previoustime step. Also, Luong et al.provides various methods to calculate theattention energies between the encoder output and decoder output whichare 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 thefollowing figure. Note that we will implement the “Attention Layer” as aseparate nn.Module called Attn. The output of this module is asoftmax normalized weights tensor of shape (batch_size, 1,max_length).

# Luong attention layerclass 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 theactual decoder model. For the decoder, we will manually feed our batchone time step at a time. This means that our embedded word tensor andGRU output will both have shape (1, batch_size, hidden_size).

Computation Graph:

  1. Get embedding of current input word.

  2. Forward through unidirectional GRU.

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

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

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

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

  7. Return output and final hidden state.

Inputs:

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

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

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

Outputs:

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 simplyconsider all elements of the tensor when calculating loss. We definemaskNLLLoss to calculate our loss based on our decoder’s outputtensor, the target tensor, and a binary mask tensor describing thepadding of the target tensor. This loss function calculates the averagenegative log likelihood of the elements that correspond to a 1 in themask 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 trainingiteration (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 someprobability, set by teacher_forcing_ratio, we use the currenttarget word as the decoder’s next input rather than using thedecoder’s current guess. This technique acts as training wheels forthe decoder, aiding in more efficient training. However, teacherforcing can lead to model instability during inference, as thedecoder may not have a sufficient chance to truly craft its ownoutput sequences during training. Thus, we must be mindful of how weare setting the teacher_forcing_ratio, and not be fooled by fastconvergence.

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

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

Sequence of Operations:

  1. Forward pass entire input batch through encoder.

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

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

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

  5. Calculate and accumulate loss.

  6. Perform backpropagation.

  7. Clip gradients.

  8. Update encoder and decoder model parameters.

Note

PyTorch’s RNN modules (RNN, LSTM, GRU) can be used like anyother non-recurrent layers by simply passing them the entire inputsequence (or batch of sequences). We use the GRU layer like this inthe encoder. The reality is that under the hood, there is aniterative process looping over each time step calculating hidden states.Alternatively, you can run these modules one time-step at a time. Inthis case, we manually loop over the sequences during the trainingprocess like we must do for the decoder model. As long as youmaintain the correct conceptual model of these modules, implementingsequential models can be very straightforward.

def train(input_variable, lengths, target_variable, mask, max_target_len, encoder, decoder, embedding, encoder_optimizer, decoder_optimizer, batch_size, clip, max_length=MAX_LENGTH): # Zero gradients encoder_optimizer.zero_grad() decoder_optimizer.zero_grad() # Set device options input_variable = input_variable.to(device) target_variable = target_variable.to(device) mask = mask.to(device) # Lengths for rnn packing should always be on the cpu lengths = lengths.to("cpu") # Initialize variables loss = 0 print_losses = [] n_totals = 0 # Forward pass through encoder encoder_outputs, encoder_hidden = encoder(input_variable, lengths) # Create initial decoder input (start with SOS tokens for each sentence) decoder_input = torch.LongTensor([[SOS_token for _ in range(batch_size)]]) decoder_input = decoder_input.to(device) # Set initial decoder hidden state to the encoder's final hidden state decoder_hidden = encoder_hidden[:decoder.n_layers] # Determine if we are using teacher forcing this iteration use_teacher_forcing = True if random.random() < teacher_forcing_ratio else False # Forward batch of sequences through decoder one time step at a time if use_teacher_forcing: for t in range(max_target_len): decoder_output, decoder_hidden = decoder( decoder_input, decoder_hidden, encoder_outputs ) # Teacher forcing: next input is current target decoder_input = target_variable[t].view(1, -1) # Calculate and accumulate loss mask_loss, nTotal = maskNLLLoss(decoder_output, target_variable[t], mask[t]) loss += mask_loss print_losses.append(mask_loss.item() * nTotal) n_totals += nTotal else: for t in range(max_target_len): decoder_output, decoder_hidden = decoder( decoder_input, decoder_hidden, encoder_outputs ) # No teacher forcing: next input is decoder's own current output _, topi = decoder_output.topk(1) decoder_input = torch.LongTensor([[topi[i][0] for i in range(batch_size)]]) decoder_input = decoder_input.to(device) # Calculate and accumulate loss mask_loss, nTotal = maskNLLLoss(decoder_output, target_variable[t], mask[t]) loss += mask_loss print_losses.append(mask_loss.item() * nTotal) n_totals += nTotal # Perform backpropatation loss.backward() # Clip gradients: gradients are modified in place _ = nn.utils.clip_grad_norm_(encoder.parameters(), clip) _ = nn.utils.clip_grad_norm_(decoder.parameters(), clip) # Adjust model weights encoder_optimizer.step() decoder_optimizer.step() return sum(print_losses) / n_totals

Training iterations

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

One thing to note is that when we save our model, we save a tarballcontaining the encoder and decoder state_dicts (parameters), theoptimizers’ state_dicts, the loss, the iteration, etc. Saving the modelin this way will give us the ultimate flexibility with the checkpoint.After loading a checkpoint, we will be able to use the model parametersto 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 whenwe are NOT using teacher forcing. In other words, for each timestep, we simply choose the word from decoder_output with the highestsoftmax value. This decoding method is optimal on a single time-steplevel.

To facilitate the greedy decoding operation, we define aGreedySearchDecoder class. When run, an object of this class takesan input sequence (input_seq) of shape (input_seq length, 1), ascalar input length (input_length) tensor, and a max_length tobound the response sentence length. The input sentence is evaluatedusing the following computational graph:

Computation Graph:

  1. Forward input through encoder model.

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

  3. Initialize decoder’s first input as SOS_token.

  4. Initialize tensors to append decoded words to.

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

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

    3. Record token and score.

    4. Prepare current token to be next decoder input.

  6. Return collections of word tokens and scores.

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

Evaluate my text

Now that we have our decoding method defined, we can write functions forevaluating a string input sentence. The evaluate function managesthe low-level process of handling the input sentence. We first formatthe sentence as an input batch of word indexes with batch_size==1. Wedo this by converting the words of the sentence to their correspondingindexes, and transposing the dimensions to prepare the tensor for ourmodels. We also create a lengths tensor which contains the length ofour input sentence. In this case, lengths is scalar because we areonly evaluating one sentence at a time (batch_size==1). Next, we obtainthe decoded response sentence tensor using our GreedySearchDecoderobject (searcher). Finally, we convert the response’s indexes towords and return the list of decoded words.

evaluateInput acts as the user interface for our chatbot. Whencalled, an input text field will spawn in which we can enter our querysentence. After typing our input sentence and pressing Enter, our textis normalized in the same way as our training data, and is ultimatelyfed to the evaluate function to obtain a decoded output sentence. Weloop this process, so we can keep chatting with our bot until we entereither “q” or “quit”.

Finally, if a sentence is entered that contains a word that is not inthe vocabulary, we handle this gracefully by printing an error messageand 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_wordsdef 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, wemust initialize the individual encoder and decoder models. In thefollowing block, we set our desired configurations, choose to start fromscratch or set a checkpoint to load from, and build and initialize themodels. Feel free to play with different model configurations tooptimize performance.

# Configure modelsmodel_name = 'cb_model'attn_model = 'dot'#attn_model = 'general'#attn_model = 'concat'hidden_size = 500encoder_n_layers = 2decoder_n_layers = 2dropout = 0.1batch_size = 64# Set checkpoint to load from; set to None if starting from scratchloadFilename = Nonecheckpoint_iter = 4000#loadFilename = os.path.join(save_dir, model_name, corpus_name,# '{}-{}_{}'.format(encoder_n_layers, decoder_n_layers, hidden_size),# '{}_checkpoint.tar'.format(checkpoint_iter))# Load model if a loadFilename is providedif 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 embeddingsembedding = nn.Embedding(voc.num_words, hidden_size)if loadFilename: embedding.load_state_dict(embedding_sd)# Initialize encoder & decoder modelsencoder = 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 deviceencoder = 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, andfinally we call the trainIters function to run our trainingiterations.

# Configure training/optimizationclip = 50.0teacher_forcing_ratio = 1.0learning_rate = 0.0001decoder_learning_ratio = 5.0n_iteration = 4000print_every = 1save_every = 500# Ensure dropout layers are in train modeencoder.train()decoder.train()# Initialize optimizersprint('Building optimizers ...')encoder_optimizer = optim.Adam(encoder.parameters(), lr=learning_rate)decoder_optimizer = optim.Adam(decoder.parameters(), lr=learning_rate * decoder_learning_ratio)if loadFilename: encoder_optimizer.load_state_dict(encoder_optimizer_sd) decoder_optimizer.load_state_dict(decoder_optimizer_sd)# If you have cuda, configure cuda to callfor state in encoder_optimizer.state.values(): for k, v in state.items(): if isinstance(v, torch.Tensor): state[k] = v.cuda()for state in decoder_optimizer.state.values(): for k, v in state.items(): if isinstance(v, torch.Tensor): state[k] = v.cuda()# Run training iterationsprint("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: 8.9716Iteration: 2; Percent complete: 0.1%; Average loss: 8.8676Iteration: 3; Percent complete: 0.1%; Average loss: 8.6980Iteration: 4; Percent complete: 0.1%; Average loss: 8.4362Iteration: 5; Percent complete: 0.1%; Average loss: 8.0069Iteration: 6; Percent complete: 0.1%; Average loss: 7.4526Iteration: 7; Percent complete: 0.2%; Average loss: 6.8929Iteration: 8; Percent complete: 0.2%; Average loss: 6.9325Iteration: 9; Percent complete: 0.2%; Average loss: 6.9028Iteration: 10; Percent complete: 0.2%; Average loss: 6.6299Iteration: 11; Percent complete: 0.3%; Average loss: 6.3223Iteration: 12; Percent complete: 0.3%; Average loss: 5.9146Iteration: 13; Percent complete: 0.3%; Average loss: 5.4930Iteration: 14; Percent complete: 0.4%; Average loss: 5.8827Iteration: 15; Percent complete: 0.4%; Average loss: 5.5235Iteration: 16; Percent complete: 0.4%; Average loss: 5.4083Iteration: 17; Percent complete: 0.4%; Average loss: 5.5017Iteration: 18; Percent complete: 0.4%; Average loss: 5.2804Iteration: 19; Percent complete: 0.5%; Average loss: 5.1546Iteration: 20; Percent complete: 0.5%; Average loss: 4.8682Iteration: 21; Percent complete: 0.5%; Average loss: 5.2809Iteration: 22; Percent complete: 0.5%; Average loss: 5.0896Iteration: 23; Percent complete: 0.6%; Average loss: 5.0576Iteration: 24; Percent complete: 0.6%; Average loss: 4.9131Iteration: 25; Percent complete: 0.6%; Average loss: 4.8066Iteration: 26; Percent complete: 0.7%; Average loss: 4.8146Iteration: 27; Percent complete: 0.7%; Average loss: 4.7814Iteration: 28; Percent complete: 0.7%; Average loss: 4.8551Iteration: 29; Percent complete: 0.7%; Average loss: 4.7186Iteration: 30; Percent complete: 0.8%; Average loss: 4.9818Iteration: 31; Percent complete: 0.8%; Average loss: 4.6451Iteration: 32; Percent complete: 0.8%; Average loss: 4.6774Iteration: 33; Percent complete: 0.8%; Average loss: 4.8147Iteration: 34; Percent complete: 0.9%; Average loss: 4.9338Iteration: 35; Percent complete: 0.9%; Average loss: 4.8691Iteration: 36; Percent complete: 0.9%; Average loss: 4.7004Iteration: 37; Percent complete: 0.9%; Average loss: 4.5484Iteration: 38; Percent complete: 0.9%; Average loss: 4.9248Iteration: 39; Percent complete: 1.0%; Average loss: 4.6390Iteration: 40; Percent complete: 1.0%; Average loss: 4.8137Iteration: 41; Percent complete: 1.0%; Average loss: 4.7377Iteration: 42; Percent complete: 1.1%; Average loss: 4.6400Iteration: 43; Percent complete: 1.1%; Average loss: 4.4907Iteration: 44; Percent complete: 1.1%; Average loss: 4.6990Iteration: 45; Percent complete: 1.1%; Average loss: 4.6266Iteration: 46; Percent complete: 1.1%; Average loss: 4.4552Iteration: 47; Percent complete: 1.2%; Average loss: 4.6599Iteration: 48; Percent complete: 1.2%; Average loss: 4.7291Iteration: 49; Percent complete: 1.2%; Average loss: 4.4911Iteration: 50; Percent complete: 1.2%; Average loss: 4.6573Iteration: 51; Percent complete: 1.3%; Average loss: 4.5815Iteration: 52; Percent complete: 1.3%; Average loss: 4.7271Iteration: 53; Percent complete: 1.3%; Average loss: 4.6250Iteration: 54; Percent complete: 1.4%; Average loss: 4.4752Iteration: 55; Percent complete: 1.4%; Average loss: 4.6616Iteration: 56; Percent complete: 1.4%; Average loss: 4.6699Iteration: 57; Percent complete: 1.4%; Average loss: 4.5631Iteration: 58; Percent complete: 1.5%; Average loss: 4.5837Iteration: 59; Percent complete: 1.5%; Average loss: 4.4836Iteration: 60; Percent complete: 1.5%; Average loss: 4.5956Iteration: 61; Percent complete: 1.5%; Average loss: 4.8835Iteration: 62; Percent complete: 1.6%; Average loss: 4.6898Iteration: 63; Percent complete: 1.6%; Average loss: 4.7783Iteration: 64; Percent complete: 1.6%; Average loss: 4.6931Iteration: 65; Percent complete: 1.6%; Average loss: 4.6443Iteration: 66; Percent complete: 1.7%; Average loss: 4.5481Iteration: 67; Percent complete: 1.7%; Average loss: 4.6460Iteration: 68; Percent complete: 1.7%; Average loss: 4.4497Iteration: 69; Percent complete: 1.7%; Average loss: 4.7292Iteration: 70; Percent complete: 1.8%; Average loss: 4.6079Iteration: 71; Percent complete: 1.8%; Average loss: 4.5212Iteration: 72; Percent complete: 1.8%; Average loss: 4.5575Iteration: 73; Percent complete: 1.8%; Average loss: 4.8734Iteration: 74; Percent complete: 1.8%; Average loss: 4.6225Iteration: 75; Percent complete: 1.9%; Average loss: 4.6293Iteration: 76; Percent complete: 1.9%; Average loss: 4.5314Iteration: 77; Percent complete: 1.9%; Average loss: 4.5414Iteration: 78; Percent complete: 1.9%; Average loss: 4.5831Iteration: 79; Percent complete: 2.0%; Average loss: 4.6125Iteration: 80; Percent complete: 2.0%; Average loss: 4.6784Iteration: 81; Percent complete: 2.0%; Average loss: 4.5669Iteration: 82; Percent complete: 2.1%; Average loss: 4.7558Iteration: 83; Percent complete: 2.1%; Average loss: 4.5563Iteration: 84; Percent complete: 2.1%; Average loss: 4.5063Iteration: 85; Percent complete: 2.1%; Average loss: 4.4900Iteration: 86; Percent complete: 2.1%; Average loss: 4.4406Iteration: 87; Percent complete: 2.2%; Average loss: 4.4359Iteration: 88; Percent complete: 2.2%; Average loss: 4.3465Iteration: 89; Percent complete: 2.2%; Average loss: 4.4928Iteration: 90; Percent complete: 2.2%; Average loss: 4.4059Iteration: 91; Percent complete: 2.3%; Average loss: 4.5071Iteration: 92; Percent complete: 2.3%; Average loss: 4.6460Iteration: 93; Percent complete: 2.3%; Average loss: 4.3669Iteration: 94; Percent complete: 2.4%; Average loss: 4.3018Iteration: 95; Percent complete: 2.4%; Average loss: 4.2788Iteration: 96; Percent complete: 2.4%; Average loss: 4.4043Iteration: 97; Percent complete: 2.4%; Average loss: 4.2207Iteration: 98; Percent complete: 2.5%; Average loss: 4.4644Iteration: 99; Percent complete: 2.5%; Average loss: 4.4374Iteration: 100; Percent complete: 2.5%; Average loss: 4.6028Iteration: 101; Percent complete: 2.5%; Average loss: 4.3129Iteration: 102; Percent complete: 2.5%; Average loss: 4.1298Iteration: 103; Percent complete: 2.6%; Average loss: 4.3090Iteration: 104; Percent complete: 2.6%; Average loss: 4.3621Iteration: 105; Percent complete: 2.6%; Average loss: 4.5836Iteration: 106; Percent complete: 2.6%; Average loss: 4.5324Iteration: 107; Percent complete: 2.7%; Average loss: 4.3709Iteration: 108; Percent complete: 2.7%; Average loss: 4.3480Iteration: 109; Percent complete: 2.7%; Average loss: 4.4770Iteration: 110; Percent complete: 2.8%; Average loss: 4.5222Iteration: 111; Percent complete: 2.8%; Average loss: 4.5571Iteration: 112; Percent complete: 2.8%; Average loss: 4.4374Iteration: 113; Percent complete: 2.8%; Average loss: 4.2358Iteration: 114; Percent complete: 2.9%; Average loss: 4.4278Iteration: 115; Percent complete: 2.9%; Average loss: 4.2767Iteration: 116; Percent complete: 2.9%; Average loss: 4.3563Iteration: 117; Percent complete: 2.9%; Average loss: 4.5250Iteration: 118; Percent complete: 2.9%; Average loss: 4.4544Iteration: 119; Percent complete: 3.0%; Average loss: 4.4414Iteration: 120; Percent complete: 3.0%; Average loss: 4.3399Iteration: 121; Percent complete: 3.0%; Average loss: 4.3555Iteration: 122; Percent complete: 3.0%; Average loss: 4.5200Iteration: 123; Percent complete: 3.1%; Average loss: 4.4048Iteration: 124; Percent complete: 3.1%; Average loss: 4.5335Iteration: 125; Percent complete: 3.1%; Average loss: 4.3556Iteration: 126; Percent complete: 3.1%; Average loss: 4.6126Iteration: 127; Percent complete: 3.2%; Average loss: 4.0999Iteration: 128; Percent complete: 3.2%; Average loss: 4.1021Iteration: 129; Percent complete: 3.2%; Average loss: 4.1472Iteration: 130; Percent complete: 3.2%; Average loss: 4.4950Iteration: 131; Percent complete: 3.3%; Average loss: 4.2408Iteration: 132; Percent complete: 3.3%; Average loss: 4.5721Iteration: 133; Percent complete: 3.3%; Average loss: 4.3044Iteration: 134; Percent complete: 3.4%; Average loss: 4.5626Iteration: 135; Percent complete: 3.4%; Average loss: 4.2127Iteration: 136; Percent complete: 3.4%; Average loss: 4.4160Iteration: 137; Percent complete: 3.4%; Average loss: 4.3775Iteration: 138; Percent complete: 3.5%; Average loss: 3.9821Iteration: 139; Percent complete: 3.5%; Average loss: 4.2730Iteration: 140; Percent complete: 3.5%; Average loss: 4.1993Iteration: 141; Percent complete: 3.5%; Average loss: 4.2492Iteration: 142; Percent complete: 3.5%; Average loss: 4.2018Iteration: 143; Percent complete: 3.6%; Average loss: 4.3884Iteration: 144; Percent complete: 3.6%; Average loss: 4.1938Iteration: 145; Percent complete: 3.6%; Average loss: 4.0707Iteration: 146; Percent complete: 3.6%; Average loss: 4.0890Iteration: 147; Percent complete: 3.7%; Average loss: 4.2665Iteration: 148; Percent complete: 3.7%; Average loss: 4.3544Iteration: 149; Percent complete: 3.7%; Average loss: 4.0889Iteration: 150; Percent complete: 3.8%; Average loss: 4.3342Iteration: 151; Percent complete: 3.8%; Average loss: 4.0235Iteration: 152; Percent complete: 3.8%; Average loss: 4.2781Iteration: 153; Percent complete: 3.8%; Average loss: 4.4679Iteration: 154; Percent complete: 3.9%; Average loss: 3.8887Iteration: 155; Percent complete: 3.9%; Average loss: 4.0449Iteration: 156; Percent complete: 3.9%; Average loss: 4.3096Iteration: 157; Percent complete: 3.9%; Average loss: 4.3608Iteration: 158; Percent complete: 4.0%; Average loss: 4.2855Iteration: 159; Percent complete: 4.0%; Average loss: 4.1601Iteration: 160; Percent complete: 4.0%; Average loss: 4.1248Iteration: 161; Percent complete: 4.0%; Average loss: 4.3227Iteration: 162; Percent complete: 4.0%; Average loss: 4.3033Iteration: 163; Percent complete: 4.1%; Average loss: 4.3028Iteration: 164; Percent complete: 4.1%; Average loss: 4.2136Iteration: 165; Percent complete: 4.1%; Average loss: 4.2468Iteration: 166; Percent complete: 4.2%; Average loss: 4.2268Iteration: 167; Percent complete: 4.2%; Average loss: 4.2169Iteration: 168; Percent complete: 4.2%; Average loss: 4.3091Iteration: 169; Percent complete: 4.2%; Average loss: 4.1916Iteration: 170; Percent complete: 4.2%; Average loss: 3.9933Iteration: 171; Percent complete: 4.3%; Average loss: 4.2003Iteration: 172; Percent complete: 4.3%; Average loss: 4.2260Iteration: 173; Percent complete: 4.3%; Average loss: 4.0948Iteration: 174; Percent complete: 4.3%; Average loss: 4.1836Iteration: 175; Percent complete: 4.4%; Average loss: 4.2736Iteration: 176; Percent complete: 4.4%; Average loss: 4.1150Iteration: 177; Percent complete: 4.4%; Average loss: 3.9957Iteration: 178; Percent complete: 4.5%; Average loss: 4.1495Iteration: 179; Percent complete: 4.5%; Average loss: 4.0956Iteration: 180; Percent complete: 4.5%; Average loss: 4.1616Iteration: 181; Percent complete: 4.5%; Average loss: 4.3249Iteration: 182; Percent complete: 4.5%; Average loss: 4.4006Iteration: 183; Percent complete: 4.6%; Average loss: 4.1727Iteration: 184; Percent complete: 4.6%; Average loss: 4.1772Iteration: 185; Percent complete: 4.6%; Average loss: 4.2010Iteration: 186; Percent complete: 4.7%; Average loss: 4.0788Iteration: 187; Percent complete: 4.7%; Average loss: 4.1969Iteration: 188; Percent complete: 4.7%; Average loss: 3.9840Iteration: 189; Percent complete: 4.7%; Average loss: 4.2110Iteration: 190; Percent complete: 4.8%; Average loss: 4.2007Iteration: 191; Percent complete: 4.8%; Average loss: 4.1375Iteration: 192; Percent complete: 4.8%; Average loss: 4.1290Iteration: 193; Percent complete: 4.8%; Average loss: 4.1819Iteration: 194; Percent complete: 4.9%; Average loss: 4.0585Iteration: 195; Percent complete: 4.9%; Average loss: 4.1692Iteration: 196; Percent complete: 4.9%; Average loss: 3.9034Iteration: 197; Percent complete: 4.9%; Average loss: 4.3482Iteration: 198; Percent complete: 5.0%; Average loss: 4.1125Iteration: 199; Percent complete: 5.0%; Average loss: 3.9822Iteration: 200; Percent complete: 5.0%; Average loss: 3.8289Iteration: 201; Percent complete: 5.0%; Average loss: 3.9062Iteration: 202; Percent complete: 5.1%; Average loss: 4.0444Iteration: 203; Percent complete: 5.1%; Average loss: 4.1914Iteration: 204; Percent complete: 5.1%; Average loss: 4.2485Iteration: 205; Percent complete: 5.1%; Average loss: 4.3697Iteration: 206; Percent complete: 5.1%; Average loss: 3.9752Iteration: 207; Percent complete: 5.2%; Average loss: 4.0744Iteration: 208; Percent complete: 5.2%; Average loss: 4.2317Iteration: 209; Percent complete: 5.2%; Average loss: 4.3916Iteration: 210; Percent complete: 5.2%; Average loss: 4.1534Iteration: 211; Percent complete: 5.3%; Average loss: 4.0518Iteration: 212; Percent complete: 5.3%; Average loss: 3.8822Iteration: 213; Percent complete: 5.3%; Average loss: 4.2409Iteration: 214; Percent complete: 5.3%; Average loss: 3.9098Iteration: 215; Percent complete: 5.4%; Average loss: 4.0061Iteration: 216; Percent complete: 5.4%; Average loss: 4.2719Iteration: 217; Percent complete: 5.4%; Average loss: 4.1049Iteration: 218; Percent complete: 5.5%; Average loss: 4.0702Iteration: 219; Percent complete: 5.5%; Average loss: 4.2367Iteration: 220; Percent complete: 5.5%; Average loss: 4.0964Iteration: 221; Percent complete: 5.5%; Average loss: 4.1455Iteration: 222; Percent complete: 5.5%; Average loss: 3.9822Iteration: 223; Percent complete: 5.6%; Average loss: 3.9646Iteration: 224; Percent complete: 5.6%; Average loss: 4.0537Iteration: 225; Percent complete: 5.6%; Average loss: 4.0131Iteration: 226; Percent complete: 5.7%; Average loss: 4.3133Iteration: 227; Percent complete: 5.7%; Average loss: 3.9793Iteration: 228; Percent complete: 5.7%; Average loss: 3.7277Iteration: 229; Percent complete: 5.7%; Average loss: 4.0036Iteration: 230; Percent complete: 5.8%; Average loss: 4.1430Iteration: 231; Percent complete: 5.8%; Average loss: 3.9947Iteration: 232; Percent complete: 5.8%; Average loss: 4.0779Iteration: 233; Percent complete: 5.8%; Average loss: 4.0935Iteration: 234; Percent complete: 5.9%; Average loss: 4.1733Iteration: 235; Percent complete: 5.9%; Average loss: 4.1225Iteration: 236; Percent complete: 5.9%; Average loss: 3.7810Iteration: 237; Percent complete: 5.9%; Average loss: 3.8575Iteration: 238; Percent complete: 5.9%; Average loss: 4.1205Iteration: 239; Percent complete: 6.0%; Average loss: 4.0496Iteration: 240; Percent complete: 6.0%; Average loss: 3.9853Iteration: 241; Percent complete: 6.0%; Average loss: 3.9062Iteration: 242; Percent complete: 6.0%; Average loss: 3.9607Iteration: 243; Percent complete: 6.1%; Average loss: 3.9887Iteration: 244; Percent complete: 6.1%; Average loss: 3.9976Iteration: 245; Percent complete: 6.1%; Average loss: 4.2124Iteration: 246; Percent complete: 6.2%; Average loss: 3.9670Iteration: 247; Percent complete: 6.2%; Average loss: 4.0622Iteration: 248; Percent complete: 6.2%; Average loss: 3.7607Iteration: 249; Percent complete: 6.2%; Average loss: 3.8996Iteration: 250; Percent complete: 6.2%; Average loss: 4.0101Iteration: 251; Percent complete: 6.3%; Average loss: 3.9336Iteration: 252; Percent complete: 6.3%; Average loss: 3.9375Iteration: 253; Percent complete: 6.3%; Average loss: 4.0515Iteration: 254; Percent complete: 6.3%; Average loss: 4.0196Iteration: 255; Percent complete: 6.4%; Average loss: 4.1079Iteration: 256; Percent complete: 6.4%; Average loss: 3.8238Iteration: 257; Percent complete: 6.4%; Average loss: 3.8917Iteration: 258; Percent complete: 6.5%; Average loss: 4.2874Iteration: 259; Percent complete: 6.5%; Average loss: 4.0801Iteration: 260; Percent complete: 6.5%; Average loss: 3.7299Iteration: 261; Percent complete: 6.5%; Average loss: 4.0764Iteration: 262; Percent complete: 6.6%; Average loss: 3.8839Iteration: 263; Percent complete: 6.6%; Average loss: 3.9457Iteration: 264; Percent complete: 6.6%; Average loss: 4.1159Iteration: 265; Percent complete: 6.6%; Average loss: 3.7118Iteration: 266; Percent complete: 6.7%; Average loss: 3.9698Iteration: 267; Percent complete: 6.7%; Average loss: 4.0807Iteration: 268; Percent complete: 6.7%; Average loss: 3.9220Iteration: 269; Percent complete: 6.7%; Average loss: 4.0598Iteration: 270; Percent complete: 6.8%; Average loss: 3.8040Iteration: 271; Percent complete: 6.8%; Average loss: 4.0189Iteration: 272; Percent complete: 6.8%; Average loss: 4.1640Iteration: 273; Percent complete: 6.8%; Average loss: 3.9675Iteration: 274; Percent complete: 6.9%; Average loss: 3.7380Iteration: 275; Percent complete: 6.9%; Average loss: 3.6369Iteration: 276; Percent complete: 6.9%; Average loss: 4.0447Iteration: 277; Percent complete: 6.9%; Average loss: 4.0512Iteration: 278; Percent complete: 7.0%; Average loss: 4.1883Iteration: 279; Percent complete: 7.0%; Average loss: 3.9578Iteration: 280; Percent complete: 7.0%; Average loss: 3.8590Iteration: 281; Percent complete: 7.0%; Average loss: 3.9957Iteration: 282; Percent complete: 7.0%; Average loss: 3.9324Iteration: 283; Percent complete: 7.1%; Average loss: 3.8116Iteration: 284; Percent complete: 7.1%; Average loss: 4.0538Iteration: 285; Percent complete: 7.1%; Average loss: 3.8508Iteration: 286; Percent complete: 7.1%; Average loss: 3.9172Iteration: 287; Percent complete: 7.2%; Average loss: 3.7712Iteration: 288; Percent complete: 7.2%; Average loss: 3.8386Iteration: 289; Percent complete: 7.2%; Average loss: 3.7042Iteration: 290; Percent complete: 7.2%; Average loss: 3.8136Iteration: 291; Percent complete: 7.3%; Average loss: 3.9029Iteration: 292; Percent complete: 7.3%; Average loss: 4.3380Iteration: 293; Percent complete: 7.3%; Average loss: 3.9696Iteration: 294; Percent complete: 7.3%; Average loss: 3.8008Iteration: 295; Percent complete: 7.4%; Average loss: 3.7762Iteration: 296; Percent complete: 7.4%; Average loss: 3.8031Iteration: 297; Percent complete: 7.4%; Average loss: 4.0077Iteration: 298; Percent complete: 7.4%; Average loss: 4.0874Iteration: 299; Percent complete: 7.5%; Average loss: 3.6881Iteration: 300; Percent complete: 7.5%; Average loss: 3.9824Iteration: 301; Percent complete: 7.5%; Average loss: 3.8351Iteration: 302; Percent complete: 7.5%; Average loss: 3.9729Iteration: 303; Percent complete: 7.6%; Average loss: 3.9185Iteration: 304; Percent complete: 7.6%; Average loss: 3.7008Iteration: 305; Percent complete: 7.6%; Average loss: 4.0095Iteration: 306; Percent complete: 7.6%; Average loss: 3.7087Iteration: 307; Percent complete: 7.7%; Average loss: 4.1641Iteration: 308; Percent complete: 7.7%; Average loss: 4.0835Iteration: 309; Percent complete: 7.7%; Average loss: 4.0173Iteration: 310; Percent complete: 7.8%; Average loss: 4.1002Iteration: 311; Percent complete: 7.8%; Average loss: 3.7487Iteration: 312; Percent complete: 7.8%; Average loss: 3.9940Iteration: 313; Percent complete: 7.8%; Average loss: 4.0087Iteration: 314; Percent complete: 7.8%; Average loss: 3.9336Iteration: 315; Percent complete: 7.9%; Average loss: 4.2495Iteration: 316; Percent complete: 7.9%; Average loss: 3.7383Iteration: 317; Percent complete: 7.9%; Average loss: 4.0672Iteration: 318; Percent complete: 8.0%; Average loss: 4.1663Iteration: 319; Percent complete: 8.0%; Average loss: 3.9180Iteration: 320; Percent complete: 8.0%; Average loss: 3.7498Iteration: 321; Percent complete: 8.0%; Average loss: 3.7348Iteration: 322; Percent complete: 8.1%; Average loss: 3.7325Iteration: 323; Percent complete: 8.1%; Average loss: 3.9307Iteration: 324; Percent complete: 8.1%; Average loss: 3.9121Iteration: 325; Percent complete: 8.1%; Average loss: 4.2834Iteration: 326; Percent complete: 8.2%; Average loss: 3.8033Iteration: 327; Percent complete: 8.2%; Average loss: 3.6776Iteration: 328; Percent complete: 8.2%; Average loss: 3.9371Iteration: 329; Percent complete: 8.2%; Average loss: 3.7657Iteration: 330; Percent complete: 8.2%; Average loss: 4.0765Iteration: 331; Percent complete: 8.3%; Average loss: 3.6908Iteration: 332; Percent complete: 8.3%; Average loss: 3.8421Iteration: 333; Percent complete: 8.3%; Average loss: 4.0330Iteration: 334; Percent complete: 8.3%; Average loss: 3.7228Iteration: 335; Percent complete: 8.4%; Average loss: 3.9744Iteration: 336; Percent complete: 8.4%; Average loss: 4.1249Iteration: 337; Percent complete: 8.4%; Average loss: 3.7346Iteration: 338; Percent complete: 8.5%; Average loss: 3.8231Iteration: 339; Percent complete: 8.5%; Average loss: 3.8073Iteration: 340; Percent complete: 8.5%; Average loss: 3.9375Iteration: 341; Percent complete: 8.5%; Average loss: 3.8730Iteration: 342; Percent complete: 8.6%; Average loss: 3.8045Iteration: 343; Percent complete: 8.6%; Average loss: 3.8542Iteration: 344; Percent complete: 8.6%; Average loss: 3.7362Iteration: 345; Percent complete: 8.6%; Average loss: 3.7150Iteration: 346; Percent complete: 8.6%; Average loss: 3.9083Iteration: 347; Percent complete: 8.7%; Average loss: 3.7771Iteration: 348; Percent complete: 8.7%; Average loss: 3.7957Iteration: 349; Percent complete: 8.7%; Average loss: 3.7115Iteration: 350; Percent complete: 8.8%; Average loss: 4.0563Iteration: 351; Percent complete: 8.8%; Average loss: 4.0686Iteration: 352; Percent complete: 8.8%; Average loss: 3.7211Iteration: 353; Percent complete: 8.8%; Average loss: 3.8555Iteration: 354; Percent complete: 8.8%; Average loss: 3.6090Iteration: 355; Percent complete: 8.9%; Average loss: 4.1943Iteration: 356; Percent complete: 8.9%; Average loss: 3.8566Iteration: 357; Percent complete: 8.9%; Average loss: 3.7724Iteration: 358; Percent complete: 8.9%; Average loss: 3.8297Iteration: 359; Percent complete: 9.0%; Average loss: 3.7953Iteration: 360; Percent complete: 9.0%; Average loss: 3.7304Iteration: 361; Percent complete: 9.0%; Average loss: 4.1178Iteration: 362; Percent complete: 9.0%; Average loss: 3.8011Iteration: 363; Percent complete: 9.1%; Average loss: 3.6152Iteration: 364; Percent complete: 9.1%; Average loss: 3.7864Iteration: 365; Percent complete: 9.1%; Average loss: 3.7487Iteration: 366; Percent complete: 9.2%; Average loss: 3.9742Iteration: 367; Percent complete: 9.2%; Average loss: 3.7032Iteration: 368; Percent complete: 9.2%; Average loss: 3.5345Iteration: 369; Percent complete: 9.2%; Average loss: 3.8361Iteration: 370; Percent complete: 9.2%; Average loss: 3.9262Iteration: 371; Percent complete: 9.3%; Average loss: 3.9982Iteration: 372; Percent complete: 9.3%; Average loss: 3.6307Iteration: 373; Percent complete: 9.3%; Average loss: 3.7818Iteration: 374; Percent complete: 9.3%; Average loss: 3.7116Iteration: 375; Percent complete: 9.4%; Average loss: 4.0164Iteration: 376; Percent complete: 9.4%; Average loss: 3.8940Iteration: 377; Percent complete: 9.4%; Average loss: 3.5458Iteration: 378; Percent complete: 9.4%; Average loss: 3.9715Iteration: 379; Percent complete: 9.5%; Average loss: 3.9781Iteration: 380; Percent complete: 9.5%; Average loss: 3.7142Iteration: 381; Percent complete: 9.5%; Average loss: 3.8697Iteration: 382; Percent complete: 9.6%; Average loss: 4.1558Iteration: 383; Percent complete: 9.6%; Average loss: 3.8169Iteration: 384; Percent complete: 9.6%; Average loss: 3.8270Iteration: 385; Percent complete: 9.6%; Average loss: 3.9233Iteration: 386; Percent complete: 9.7%; Average loss: 3.8760Iteration: 387; Percent complete: 9.7%; Average loss: 3.7914Iteration: 388; Percent complete: 9.7%; Average loss: 4.1266Iteration: 389; Percent complete: 9.7%; Average loss: 4.0109Iteration: 390; Percent complete: 9.8%; Average loss: 3.8964Iteration: 391; Percent complete: 9.8%; Average loss: 3.9620Iteration: 392; Percent complete: 9.8%; Average loss: 3.6056Iteration: 393; Percent complete: 9.8%; Average loss: 3.7177Iteration: 394; Percent complete: 9.8%; Average loss: 3.8391Iteration: 395; Percent complete: 9.9%; Average loss: 3.8544Iteration: 396; Percent complete: 9.9%; Average loss: 3.9946Iteration: 397; Percent complete: 9.9%; Average loss: 3.7864Iteration: 398; Percent complete: 10.0%; Average loss: 3.6605Iteration: 399; Percent complete: 10.0%; Average loss: 3.7534Iteration: 400; Percent complete: 10.0%; Average loss: 4.0527Iteration: 401; Percent complete: 10.0%; Average loss: 4.1087Iteration: 402; Percent complete: 10.1%; Average loss: 3.8078Iteration: 403; Percent complete: 10.1%; Average loss: 3.9756Iteration: 404; Percent complete: 10.1%; Average loss: 4.0022Iteration: 405; Percent complete: 10.1%; Average loss: 4.0887Iteration: 406; Percent complete: 10.2%; Average loss: 3.6733Iteration: 407; Percent complete: 10.2%; Average loss: 3.7503Iteration: 408; Percent complete: 10.2%; Average loss: 3.7066Iteration: 409; Percent complete: 10.2%; Average loss: 3.5046Iteration: 410; Percent complete: 10.2%; Average loss: 3.8303Iteration: 411; Percent complete: 10.3%; Average loss: 3.7434Iteration: 412; Percent complete: 10.3%; Average loss: 3.7604Iteration: 413; Percent complete: 10.3%; Average loss: 3.6285Iteration: 414; Percent complete: 10.3%; Average loss: 3.6445Iteration: 415; Percent complete: 10.4%; Average loss: 3.9711Iteration: 416; Percent complete: 10.4%; Average loss: 3.7630Iteration: 417; Percent complete: 10.4%; Average loss: 3.6181Iteration: 418; Percent complete: 10.4%; Average loss: 3.8825Iteration: 419; Percent complete: 10.5%; Average loss: 3.6475Iteration: 420; Percent complete: 10.5%; Average loss: 3.7990Iteration: 421; Percent complete: 10.5%; Average loss: 3.8482Iteration: 422; Percent complete: 10.5%; Average loss: 3.7953Iteration: 423; Percent complete: 10.6%; Average loss: 3.8723Iteration: 424; Percent complete: 10.6%; Average loss: 4.0172Iteration: 425; Percent complete: 10.6%; Average loss: 3.9111Iteration: 426; Percent complete: 10.7%; Average loss: 3.9590Iteration: 427; Percent complete: 10.7%; Average loss: 3.7027Iteration: 428; Percent complete: 10.7%; Average loss: 4.0430Iteration: 429; Percent complete: 10.7%; Average loss: 3.8174Iteration: 430; Percent complete: 10.8%; Average loss: 3.8138Iteration: 431; Percent complete: 10.8%; Average loss: 3.9095Iteration: 432; Percent complete: 10.8%; Average loss: 3.6484Iteration: 433; Percent complete: 10.8%; Average loss: 3.6151Iteration: 434; Percent complete: 10.8%; Average loss: 3.8108Iteration: 435; Percent complete: 10.9%; Average loss: 3.9096Iteration: 436; Percent complete: 10.9%; Average loss: 3.6313Iteration: 437; Percent complete: 10.9%; Average loss: 3.6476Iteration: 438; Percent complete: 10.9%; Average loss: 3.8727Iteration: 439; Percent complete: 11.0%; Average loss: 3.3812Iteration: 440; Percent complete: 11.0%; Average loss: 3.7605Iteration: 441; Percent complete: 11.0%; Average loss: 3.8408Iteration: 442; Percent complete: 11.1%; Average loss: 4.0094Iteration: 443; Percent complete: 11.1%; Average loss: 3.6765Iteration: 444; Percent complete: 11.1%; Average loss: 3.5218Iteration: 445; Percent complete: 11.1%; Average loss: 3.9277Iteration: 446; Percent complete: 11.2%; Average loss: 3.9160Iteration: 447; Percent complete: 11.2%; Average loss: 3.5977Iteration: 448; Percent complete: 11.2%; Average loss: 3.7418Iteration: 449; Percent complete: 11.2%; Average loss: 3.7400Iteration: 450; Percent complete: 11.2%; Average loss: 3.9512Iteration: 451; Percent complete: 11.3%; Average loss: 3.8342Iteration: 452; Percent complete: 11.3%; Average loss: 3.9347Iteration: 453; Percent complete: 11.3%; Average loss: 3.7728Iteration: 454; Percent complete: 11.3%; Average loss: 3.6536Iteration: 455; Percent complete: 11.4%; Average loss: 3.8567Iteration: 456; Percent complete: 11.4%; Average loss: 3.8864Iteration: 457; Percent complete: 11.4%; Average loss: 3.9279Iteration: 458; Percent complete: 11.5%; Average loss: 3.4763Iteration: 459; Percent complete: 11.5%; Average loss: 3.7669Iteration: 460; Percent complete: 11.5%; Average loss: 3.8258Iteration: 461; Percent complete: 11.5%; Average loss: 3.8350Iteration: 462; Percent complete: 11.6%; Average loss: 3.5926Iteration: 463; Percent complete: 11.6%; Average loss: 3.7001Iteration: 464; Percent complete: 11.6%; Average loss: 3.7438Iteration: 465; Percent complete: 11.6%; Average loss: 3.7029Iteration: 466; Percent complete: 11.7%; Average loss: 3.6874Iteration: 467; Percent complete: 11.7%; Average loss: 3.9848Iteration: 468; Percent complete: 11.7%; Average loss: 3.8929Iteration: 469; Percent complete: 11.7%; Average loss: 3.5855Iteration: 470; Percent complete: 11.8%; Average loss: 3.9977Iteration: 471; Percent complete: 11.8%; Average loss: 3.9007Iteration: 472; Percent complete: 11.8%; Average loss: 3.8063Iteration: 473; Percent complete: 11.8%; Average loss: 3.7966Iteration: 474; Percent complete: 11.8%; Average loss: 3.8286Iteration: 475; Percent complete: 11.9%; Average loss: 3.9092Iteration: 476; Percent complete: 11.9%; Average loss: 3.6890Iteration: 477; Percent complete: 11.9%; Average loss: 3.7348Iteration: 478; Percent complete: 11.9%; Average loss: 3.8428Iteration: 479; Percent complete: 12.0%; Average loss: 3.6014Iteration: 480; Percent complete: 12.0%; Average loss: 3.8230Iteration: 481; Percent complete: 12.0%; Average loss: 3.8703Iteration: 482; Percent complete: 12.0%; Average loss: 3.7374Iteration: 483; Percent complete: 12.1%; Average loss: 3.8983Iteration: 484; Percent complete: 12.1%; Average loss: 3.9977Iteration: 485; Percent complete: 12.1%; Average loss: 3.5309Iteration: 486; Percent complete: 12.2%; Average loss: 3.5250Iteration: 487; Percent complete: 12.2%; Average loss: 3.8316Iteration: 488; Percent complete: 12.2%; Average loss: 3.7381Iteration: 489; Percent complete: 12.2%; Average loss: 3.7075Iteration: 490; Percent complete: 12.2%; Average loss: 3.6891Iteration: 491; Percent complete: 12.3%; Average loss: 3.8561Iteration: 492; Percent complete: 12.3%; Average loss: 3.5626Iteration: 493; Percent complete: 12.3%; Average loss: 3.6261Iteration: 494; Percent complete: 12.3%; Average loss: 3.8343Iteration: 495; Percent complete: 12.4%; Average loss: 3.4062Iteration: 496; Percent complete: 12.4%; Average loss: 4.0323Iteration: 497; Percent complete: 12.4%; Average loss: 3.5452Iteration: 498; Percent complete: 12.4%; Average loss: 3.8475Iteration: 499; Percent complete: 12.5%; Average loss: 3.7456Iteration: 500; Percent complete: 12.5%; Average loss: 3.8637Iteration: 501; Percent complete: 12.5%; Average loss: 3.7652Iteration: 502; Percent complete: 12.6%; Average loss: 4.0148Iteration: 503; Percent complete: 12.6%; Average loss: 3.8648Iteration: 504; Percent complete: 12.6%; Average loss: 3.7738Iteration: 505; Percent complete: 12.6%; Average loss: 3.7889Iteration: 506; Percent complete: 12.7%; Average loss: 3.8678Iteration: 507; Percent complete: 12.7%; Average loss: 3.9891Iteration: 508; Percent complete: 12.7%; Average loss: 3.9940Iteration: 509; Percent complete: 12.7%; Average loss: 3.7455Iteration: 510; Percent complete: 12.8%; Average loss: 3.6661Iteration: 511; Percent complete: 12.8%; Average loss: 3.5054Iteration: 512; Percent complete: 12.8%; Average loss: 3.7300Iteration: 513; Percent complete: 12.8%; Average loss: 3.9580Iteration: 514; Percent complete: 12.8%; Average loss: 3.7289Iteration: 515; Percent complete: 12.9%; Average loss: 3.6071Iteration: 516; Percent complete: 12.9%; Average loss: 3.5066Iteration: 517; Percent complete: 12.9%; Average loss: 3.6788Iteration: 518; Percent complete: 13.0%; Average loss: 3.5839Iteration: 519; Percent complete: 13.0%; Average loss: 3.6792Iteration: 520; Percent complete: 13.0%; Average loss: 3.8681Iteration: 521; Percent complete: 13.0%; Average loss: 3.7145Iteration: 522; Percent complete: 13.1%; Average loss: 3.9020Iteration: 523; Percent complete: 13.1%; Average loss: 3.9487Iteration: 524; Percent complete: 13.1%; Average loss: 3.5911Iteration: 525; Percent complete: 13.1%; Average loss: 3.6162Iteration: 526; Percent complete: 13.2%; Average loss: 3.4481Iteration: 527; Percent complete: 13.2%; Average loss: 3.5143Iteration: 528; Percent complete: 13.2%; Average loss: 3.5716Iteration: 529; Percent complete: 13.2%; Average loss: 3.6717Iteration: 530; Percent complete: 13.2%; Average loss: 3.7291Iteration: 531; Percent complete: 13.3%; Average loss: 3.7530Iteration: 532; Percent complete: 13.3%; Average loss: 4.0028Iteration: 533; Percent complete: 13.3%; Average loss: 3.8037Iteration: 534; Percent complete: 13.4%; Average loss: 3.6446Iteration: 535; Percent complete: 13.4%; Average loss: 3.5653Iteration: 536; Percent complete: 13.4%; Average loss: 3.4246Iteration: 537; Percent complete: 13.4%; Average loss: 3.7952Iteration: 538; Percent complete: 13.5%; Average loss: 3.9276Iteration: 539; Percent complete: 13.5%; Average loss: 3.8789Iteration: 540; Percent complete: 13.5%; Average loss: 3.6500Iteration: 541; Percent complete: 13.5%; Average loss: 3.6371Iteration: 542; Percent complete: 13.6%; Average loss: 4.0061Iteration: 543; Percent complete: 13.6%; Average loss: 3.6538Iteration: 544; Percent complete: 13.6%; Average loss: 3.4200Iteration: 545; Percent complete: 13.6%; Average loss: 3.6908Iteration: 546; Percent complete: 13.7%; Average loss: 3.8827Iteration: 547; Percent complete: 13.7%; Average loss: 3.4342Iteration: 548; Percent complete: 13.7%; Average loss: 3.3367Iteration: 549; Percent complete: 13.7%; Average loss: 3.4748Iteration: 550; Percent complete: 13.8%; Average loss: 3.7418Iteration: 551; Percent complete: 13.8%; Average loss: 3.8032Iteration: 552; Percent complete: 13.8%; Average loss: 3.6290Iteration: 553; Percent complete: 13.8%; Average loss: 3.7492Iteration: 554; Percent complete: 13.9%; Average loss: 3.4134Iteration: 555; Percent complete: 13.9%; Average loss: 3.8274Iteration: 556; Percent complete: 13.9%; Average loss: 3.6931Iteration: 557; Percent complete: 13.9%; Average loss: 3.7156Iteration: 558; Percent complete: 14.0%; Average loss: 3.8773Iteration: 559; Percent complete: 14.0%; Average loss: 3.8127Iteration: 560; Percent complete: 14.0%; Average loss: 3.7427Iteration: 561; Percent complete: 14.0%; Average loss: 3.4631Iteration: 562; Percent complete: 14.1%; Average loss: 3.5918Iteration: 563; Percent complete: 14.1%; Average loss: 3.5136Iteration: 564; Percent complete: 14.1%; Average loss: 3.7089Iteration: 565; Percent complete: 14.1%; Average loss: 3.7091Iteration: 566; Percent complete: 14.1%; Average loss: 3.5927Iteration: 567; Percent complete: 14.2%; Average loss: 3.5698Iteration: 568; Percent complete: 14.2%; Average loss: 3.8187Iteration: 569; Percent complete: 14.2%; Average loss: 3.6311Iteration: 570; Percent complete: 14.2%; Average loss: 3.6367Iteration: 571; Percent complete: 14.3%; Average loss: 3.8691Iteration: 572; Percent complete: 14.3%; Average loss: 3.7286Iteration: 573; Percent complete: 14.3%; Average loss: 3.6155Iteration: 574; Percent complete: 14.3%; Average loss: 3.6273Iteration: 575; Percent complete: 14.4%; Average loss: 3.5882Iteration: 576; Percent complete: 14.4%; Average loss: 3.4556Iteration: 577; Percent complete: 14.4%; Average loss: 3.7138Iteration: 578; Percent complete: 14.4%; Average loss: 3.6751Iteration: 579; Percent complete: 14.5%; Average loss: 3.7370Iteration: 580; Percent complete: 14.5%; Average loss: 3.8121Iteration: 581; Percent complete: 14.5%; Average loss: 3.8051Iteration: 582; Percent complete: 14.5%; Average loss: 3.8412Iteration: 583; Percent complete: 14.6%; Average loss: 3.6812Iteration: 584; Percent complete: 14.6%; Average loss: 3.8694Iteration: 585; Percent complete: 14.6%; Average loss: 3.6165Iteration: 586; Percent complete: 14.6%; Average loss: 3.7748Iteration: 587; Percent complete: 14.7%; Average loss: 3.9127Iteration: 588; Percent complete: 14.7%; Average loss: 3.8554Iteration: 589; Percent complete: 14.7%; Average loss: 3.9846Iteration: 590; Percent complete: 14.8%; Average loss: 3.6568Iteration: 591; Percent complete: 14.8%; Average loss: 3.7023Iteration: 592; Percent complete: 14.8%; Average loss: 3.5937Iteration: 593; Percent complete: 14.8%; Average loss: 3.4524Iteration: 594; Percent complete: 14.8%; Average loss: 3.5986Iteration: 595; Percent complete: 14.9%; Average loss: 3.9544Iteration: 596; Percent complete: 14.9%; Average loss: 3.7183Iteration: 597; Percent complete: 14.9%; Average loss: 3.6370Iteration: 598; Percent complete: 14.9%; Average loss: 3.6892Iteration: 599; Percent complete: 15.0%; Average loss: 3.6195Iteration: 600; Percent complete: 15.0%; Average loss: 3.7184Iteration: 601; Percent complete: 15.0%; Average loss: 3.7451Iteration: 602; Percent complete: 15.0%; Average loss: 3.5696Iteration: 603; Percent complete: 15.1%; Average loss: 3.7238Iteration: 604; Percent complete: 15.1%; Average loss: 3.8023Iteration: 605; Percent complete: 15.1%; Average loss: 3.4286Iteration: 606; Percent complete: 15.2%; Average loss: 4.1069Iteration: 607; Percent complete: 15.2%; Average loss: 3.6786Iteration: 608; Percent complete: 15.2%; Average loss: 3.7342Iteration: 609; Percent complete: 15.2%; Average loss: 3.8520Iteration: 610; Percent complete: 15.2%; Average loss: 3.5130Iteration: 611; Percent complete: 15.3%; Average loss: 3.5048Iteration: 612; Percent complete: 15.3%; Average loss: 3.4831Iteration: 613; Percent complete: 15.3%; Average loss: 3.7389Iteration: 614; Percent complete: 15.3%; Average loss: 3.6407Iteration: 615; Percent complete: 15.4%; Average loss: 3.6051Iteration: 616; Percent complete: 15.4%; Average loss: 3.9449Iteration: 617; Percent complete: 15.4%; Average loss: 3.6278Iteration: 618; Percent complete: 15.4%; Average loss: 3.5868Iteration: 619; Percent complete: 15.5%; Average loss: 3.5832Iteration: 620; Percent complete: 15.5%; Average loss: 3.5856Iteration: 621; Percent complete: 15.5%; Average loss: 3.7956Iteration: 622; Percent complete: 15.6%; Average loss: 3.3273Iteration: 623; Percent complete: 15.6%; Average loss: 3.5771Iteration: 624; Percent complete: 15.6%; Average loss: 3.5306Iteration: 625; Percent complete: 15.6%; Average loss: 3.5494Iteration: 626; Percent complete: 15.7%; Average loss: 3.4668Iteration: 627; Percent complete: 15.7%; Average loss: 3.7830Iteration: 628; Percent complete: 15.7%; Average loss: 3.5998Iteration: 629; Percent complete: 15.7%; Average loss: 3.6198Iteration: 630; Percent complete: 15.8%; Average loss: 3.6197Iteration: 631; Percent complete: 15.8%; Average loss: 3.9601Iteration: 632; Percent complete: 15.8%; Average loss: 3.8072Iteration: 633; Percent complete: 15.8%; Average loss: 3.7873Iteration: 634; Percent complete: 15.8%; Average loss: 3.7797Iteration: 635; Percent complete: 15.9%; Average loss: 3.6852Iteration: 636; Percent complete: 15.9%; Average loss: 3.6762Iteration: 637; Percent complete: 15.9%; Average loss: 3.3951Iteration: 638; Percent complete: 16.0%; Average loss: 3.5516Iteration: 639; Percent complete: 16.0%; Average loss: 3.7657Iteration: 640; Percent complete: 16.0%; Average loss: 3.4996Iteration: 641; Percent complete: 16.0%; Average loss: 3.4923Iteration: 642; Percent complete: 16.1%; Average loss: 3.8609Iteration: 643; Percent complete: 16.1%; Average loss: 3.7858Iteration: 644; Percent complete: 16.1%; Average loss: 3.7066Iteration: 645; Percent complete: 16.1%; Average loss: 3.5678Iteration: 646; Percent complete: 16.2%; Average loss: 3.8044Iteration: 647; Percent complete: 16.2%; Average loss: 3.3476Iteration: 648; Percent complete: 16.2%; Average loss: 3.7116Iteration: 649; Percent complete: 16.2%; Average loss: 3.5505Iteration: 650; Percent complete: 16.2%; Average loss: 3.8505Iteration: 651; Percent complete: 16.3%; Average loss: 3.7075Iteration: 652; Percent complete: 16.3%; Average loss: 3.6516Iteration: 653; Percent complete: 16.3%; Average loss: 3.7661Iteration: 654; Percent complete: 16.4%; Average loss: 3.8846Iteration: 655; Percent complete: 16.4%; Average loss: 3.5961Iteration: 656; Percent complete: 16.4%; Average loss: 3.6665Iteration: 657; Percent complete: 16.4%; Average loss: 3.5023Iteration: 658; Percent complete: 16.4%; Average loss: 3.8226Iteration: 659; Percent complete: 16.5%; Average loss: 3.7637Iteration: 660; Percent complete: 16.5%; Average loss: 3.6677Iteration: 661; Percent complete: 16.5%; Average loss: 3.6136Iteration: 662; Percent complete: 16.6%; Average loss: 3.6437Iteration: 663; Percent complete: 16.6%; Average loss: 3.5712Iteration: 664; Percent complete: 16.6%; Average loss: 3.7752Iteration: 665; Percent complete: 16.6%; Average loss: 3.6532Iteration: 666; Percent complete: 16.7%; Average loss: 3.7227Iteration: 667; Percent complete: 16.7%; Average loss: 3.8792Iteration: 668; Percent complete: 16.7%; Average loss: 3.8657Iteration: 669; Percent complete: 16.7%; Average loss: 3.7447Iteration: 670; Percent complete: 16.8%; Average loss: 3.6995Iteration: 671; Percent complete: 16.8%; Average loss: 3.4760Iteration: 672; Percent complete: 16.8%; Average loss: 3.3135Iteration: 673; Percent complete: 16.8%; Average loss: 3.4351Iteration: 674; Percent complete: 16.9%; Average loss: 3.4934Iteration: 675; Percent complete: 16.9%; Average loss: 3.5466Iteration: 676; Percent complete: 16.9%; Average loss: 3.5504Iteration: 677; Percent complete: 16.9%; Average loss: 3.5459Iteration: 678; Percent complete: 17.0%; Average loss: 3.6323Iteration: 679; Percent complete: 17.0%; Average loss: 3.5515Iteration: 680; Percent complete: 17.0%; Average loss: 3.7319Iteration: 681; Percent complete: 17.0%; Average loss: 3.6372Iteration: 682; Percent complete: 17.1%; Average loss: 3.6414Iteration: 683; Percent complete: 17.1%; Average loss: 3.3564Iteration: 684; Percent complete: 17.1%; Average loss: 3.6190Iteration: 685; Percent complete: 17.1%; Average loss: 3.7474Iteration: 686; Percent complete: 17.2%; Average loss: 3.5780Iteration: 687; Percent complete: 17.2%; Average loss: 3.5173Iteration: 688; Percent complete: 17.2%; Average loss: 3.3603Iteration: 689; Percent complete: 17.2%; Average loss: 3.6873Iteration: 690; Percent complete: 17.2%; Average loss: 3.3923Iteration: 691; Percent complete: 17.3%; Average loss: 3.4358Iteration: 692; Percent complete: 17.3%; Average loss: 3.5249Iteration: 693; Percent complete: 17.3%; Average loss: 3.6325Iteration: 694; Percent complete: 17.3%; Average loss: 3.8561Iteration: 695; Percent complete: 17.4%; Average loss: 3.5393Iteration: 696; Percent complete: 17.4%; Average loss: 3.4921Iteration: 697; Percent complete: 17.4%; Average loss: 3.7518Iteration: 698; Percent complete: 17.4%; Average loss: 3.5621Iteration: 699; Percent complete: 17.5%; Average loss: 3.4621Iteration: 700; Percent complete: 17.5%; Average loss: 3.4711Iteration: 701; Percent complete: 17.5%; Average loss: 3.4794Iteration: 702; Percent complete: 17.5%; Average loss: 3.3435Iteration: 703; Percent complete: 17.6%; Average loss: 3.6918Iteration: 704; Percent complete: 17.6%; Average loss: 3.4601Iteration: 705; Percent complete: 17.6%; Average loss: 3.6754Iteration: 706; Percent complete: 17.6%; Average loss: 3.5791Iteration: 707; Percent complete: 17.7%; Average loss: 3.5524Iteration: 708; Percent complete: 17.7%; Average loss: 3.5909Iteration: 709; Percent complete: 17.7%; Average loss: 3.2965Iteration: 710; Percent complete: 17.8%; Average loss: 3.7653Iteration: 711; Percent complete: 17.8%; Average loss: 3.6818Iteration: 712; Percent complete: 17.8%; Average loss: 3.4800Iteration: 713; Percent complete: 17.8%; Average loss: 3.6509Iteration: 714; Percent complete: 17.8%; Average loss: 3.5581Iteration: 715; Percent complete: 17.9%; Average loss: 3.4973Iteration: 716; Percent complete: 17.9%; Average loss: 3.7856Iteration: 717; Percent complete: 17.9%; Average loss: 3.4794Iteration: 718; Percent complete: 17.9%; Average loss: 3.5918Iteration: 719; Percent complete: 18.0%; Average loss: 3.4582Iteration: 720; Percent complete: 18.0%; Average loss: 3.8769Iteration: 721; Percent complete: 18.0%; Average loss: 3.5539Iteration: 722; Percent complete: 18.1%; Average loss: 3.8524Iteration: 723; Percent complete: 18.1%; Average loss: 3.7431Iteration: 724; Percent complete: 18.1%; Average loss: 3.5683Iteration: 725; Percent complete: 18.1%; Average loss: 3.4982Iteration: 726; Percent complete: 18.1%; Average loss: 3.7727Iteration: 727; Percent complete: 18.2%; Average loss: 3.5351Iteration: 728; Percent complete: 18.2%; Average loss: 3.5198Iteration: 729; Percent complete: 18.2%; Average loss: 3.7054Iteration: 730; Percent complete: 18.2%; Average loss: 3.6512Iteration: 731; Percent complete: 18.3%; Average loss: 3.4878Iteration: 732; Percent complete: 18.3%; Average loss: 3.3838Iteration: 733; Percent complete: 18.3%; Average loss: 3.5644Iteration: 734; Percent complete: 18.4%; Average loss: 3.7135Iteration: 735; Percent complete: 18.4%; Average loss: 3.7132Iteration: 736; Percent complete: 18.4%; Average loss: 3.5175Iteration: 737; Percent complete: 18.4%; Average loss: 3.7586Iteration: 738; Percent complete: 18.4%; Average loss: 3.6380Iteration: 739; Percent complete: 18.5%; Average loss: 3.6420Iteration: 740; Percent complete: 18.5%; Average loss: 3.5054Iteration: 741; Percent complete: 18.5%; Average loss: 3.9497Iteration: 742; Percent complete: 18.6%; Average loss: 3.5407Iteration: 743; Percent complete: 18.6%; Average loss: 3.6397Iteration: 744; Percent complete: 18.6%; Average loss: 3.6619Iteration: 745; Percent complete: 18.6%; Average loss: 3.4289Iteration: 746; Percent complete: 18.6%; Average loss: 3.7921Iteration: 747; Percent complete: 18.7%; Average loss: 3.5952Iteration: 748; Percent complete: 18.7%; Average loss: 3.5441Iteration: 749; Percent complete: 18.7%; Average loss: 3.4627Iteration: 750; Percent complete: 18.8%; Average loss: 3.5462Iteration: 751; Percent complete: 18.8%; Average loss: 3.5410Iteration: 752; Percent complete: 18.8%; Average loss: 3.2688Iteration: 753; Percent complete: 18.8%; Average loss: 3.3565Iteration: 754; Percent complete: 18.9%; Average loss: 3.5264Iteration: 755; Percent complete: 18.9%; Average loss: 3.6872Iteration: 756; Percent complete: 18.9%; Average loss: 3.5387Iteration: 757; Percent complete: 18.9%; Average loss: 3.6147Iteration: 758; Percent complete: 18.9%; Average loss: 3.5117Iteration: 759; Percent complete: 19.0%; Average loss: 3.1118Iteration: 760; Percent complete: 19.0%; Average loss: 3.4282Iteration: 761; Percent complete: 19.0%; Average loss: 3.4923Iteration: 762; Percent complete: 19.1%; Average loss: 3.8123Iteration: 763; Percent complete: 19.1%; Average loss: 3.5608Iteration: 764; Percent complete: 19.1%; Average loss: 3.5303Iteration: 765; Percent complete: 19.1%; Average loss: 3.7822Iteration: 766; Percent complete: 19.1%; Average loss: 3.7254Iteration: 767; Percent complete: 19.2%; Average loss: 3.6879Iteration: 768; Percent complete: 19.2%; Average loss: 3.5436Iteration: 769; Percent complete: 19.2%; Average loss: 3.6730Iteration: 770; Percent complete: 19.2%; Average loss: 3.6692Iteration: 771; Percent complete: 19.3%; Average loss: 3.4955Iteration: 772; Percent complete: 19.3%; Average loss: 3.3592Iteration: 773; Percent complete: 19.3%; Average loss: 3.7113Iteration: 774; Percent complete: 19.4%; Average loss: 3.4287Iteration: 775; Percent complete: 19.4%; Average loss: 3.6074Iteration: 776; Percent complete: 19.4%; Average loss: 3.3847Iteration: 777; Percent complete: 19.4%; Average loss: 3.4552Iteration: 778; Percent complete: 19.4%; Average loss: 3.6010Iteration: 779; Percent complete: 19.5%; Average loss: 3.4439Iteration: 780; Percent complete: 19.5%; Average loss: 3.6570Iteration: 781; Percent complete: 19.5%; Average loss: 3.4018Iteration: 782; Percent complete: 19.6%; Average loss: 3.6593Iteration: 783; Percent complete: 19.6%; Average loss: 3.5984Iteration: 784; Percent complete: 19.6%; Average loss: 3.5572Iteration: 785; Percent complete: 19.6%; Average loss: 3.7994Iteration: 786; Percent complete: 19.7%; Average loss: 3.6013Iteration: 787; Percent complete: 19.7%; Average loss: 3.6401Iteration: 788; Percent complete: 19.7%; Average loss: 3.6387Iteration: 789; Percent complete: 19.7%; Average loss: 3.5459Iteration: 790; Percent complete: 19.8%; Average loss: 3.3501Iteration: 791; Percent complete: 19.8%; Average loss: 3.5844Iteration: 792; Percent complete: 19.8%; Average loss: 3.6802Iteration: 793; Percent complete: 19.8%; Average loss: 3.2674Iteration: 794; Percent complete: 19.9%; Average loss: 3.8575Iteration: 795; Percent complete: 19.9%; Average loss: 3.7621Iteration: 796; Percent complete: 19.9%; Average loss: 3.6067Iteration: 797; Percent complete: 19.9%; Average loss: 3.5533Iteration: 798; Percent complete: 20.0%; Average loss: 3.4504Iteration: 799; Percent complete: 20.0%; Average loss: 3.5598Iteration: 800; Percent complete: 20.0%; Average loss: 3.3810Iteration: 801; Percent complete: 20.0%; Average loss: 3.5847Iteration: 802; Percent complete: 20.1%; Average loss: 3.7636Iteration: 803; Percent complete: 20.1%; Average loss: 3.5755Iteration: 804; Percent complete: 20.1%; Average loss: 3.4430Iteration: 805; Percent complete: 20.1%; Average loss: 3.5664Iteration: 806; Percent complete: 20.2%; Average loss: 3.8114Iteration: 807; Percent complete: 20.2%; Average loss: 3.3342Iteration: 808; Percent complete: 20.2%; Average loss: 3.8201Iteration: 809; Percent complete: 20.2%; Average loss: 3.5775Iteration: 810; Percent complete: 20.2%; Average loss: 3.6790Iteration: 811; Percent complete: 20.3%; Average loss: 3.3636Iteration: 812; Percent complete: 20.3%; Average loss: 3.6918Iteration: 813; Percent complete: 20.3%; Average loss: 3.5263Iteration: 814; Percent complete: 20.3%; Average loss: 3.4876Iteration: 815; Percent complete: 20.4%; Average loss: 3.4195Iteration: 816; Percent complete: 20.4%; Average loss: 3.6392Iteration: 817; Percent complete: 20.4%; Average loss: 3.3143Iteration: 818; Percent complete: 20.4%; Average loss: 3.3317Iteration: 819; Percent complete: 20.5%; Average loss: 3.4081Iteration: 820; Percent complete: 20.5%; Average loss: 3.2196Iteration: 821; Percent complete: 20.5%; Average loss: 3.5283Iteration: 822; Percent complete: 20.5%; Average loss: 3.4640Iteration: 823; Percent complete: 20.6%; Average loss: 3.4669Iteration: 824; Percent complete: 20.6%; Average loss: 3.4164Iteration: 825; Percent complete: 20.6%; Average loss: 3.4232Iteration: 826; Percent complete: 20.6%; Average loss: 3.3968Iteration: 827; Percent complete: 20.7%; Average loss: 3.7004Iteration: 828; Percent complete: 20.7%; Average loss: 3.7613Iteration: 829; Percent complete: 20.7%; Average loss: 3.7992Iteration: 830; Percent complete: 20.8%; Average loss: 3.3268Iteration: 831; Percent complete: 20.8%; Average loss: 3.5000Iteration: 832; Percent complete: 20.8%; Average loss: 3.5033Iteration: 833; Percent complete: 20.8%; Average loss: 3.8432Iteration: 834; Percent complete: 20.8%; Average loss: 3.7289Iteration: 835; Percent complete: 20.9%; Average loss: 3.5982Iteration: 836; Percent complete: 20.9%; Average loss: 3.4970Iteration: 837; Percent complete: 20.9%; Average loss: 3.7043Iteration: 838; Percent complete: 20.9%; Average loss: 3.6234Iteration: 839; Percent complete: 21.0%; Average loss: 3.8169Iteration: 840; Percent complete: 21.0%; Average loss: 3.4173Iteration: 841; Percent complete: 21.0%; Average loss: 3.4486Iteration: 842; Percent complete: 21.1%; Average loss: 3.5512Iteration: 843; Percent complete: 21.1%; Average loss: 3.5438Iteration: 844; Percent complete: 21.1%; Average loss: 3.5767Iteration: 845; Percent complete: 21.1%; Average loss: 3.4337Iteration: 846; Percent complete: 21.1%; Average loss: 3.5646Iteration: 847; Percent complete: 21.2%; Average loss: 3.7386Iteration: 848; Percent complete: 21.2%; Average loss: 3.4782Iteration: 849; Percent complete: 21.2%; Average loss: 3.8799Iteration: 850; Percent complete: 21.2%; Average loss: 3.5760Iteration: 851; Percent complete: 21.3%; Average loss: 3.6554Iteration: 852; Percent complete: 21.3%; Average loss: 3.4507Iteration: 853; Percent complete: 21.3%; Average loss: 3.5258Iteration: 854; Percent complete: 21.3%; Average loss: 3.3390Iteration: 855; Percent complete: 21.4%; Average loss: 3.6114Iteration: 856; Percent complete: 21.4%; Average loss: 3.4432Iteration: 857; Percent complete: 21.4%; Average loss: 3.5232Iteration: 858; Percent complete: 21.4%; Average loss: 3.4400Iteration: 859; Percent complete: 21.5%; Average loss: 3.5444Iteration: 860; Percent complete: 21.5%; Average loss: 3.3676Iteration: 861; Percent complete: 21.5%; Average loss: 3.6455Iteration: 862; Percent complete: 21.6%; Average loss: 3.3370Iteration: 863; Percent complete: 21.6%; Average loss: 3.5480Iteration: 864; Percent complete: 21.6%; Average loss: 3.3595Iteration: 865; Percent complete: 21.6%; Average loss: 3.6283Iteration: 866; Percent complete: 21.6%; Average loss: 3.7147Iteration: 867; Percent complete: 21.7%; Average loss: 3.4525Iteration: 868; Percent complete: 21.7%; Average loss: 3.4343Iteration: 869; Percent complete: 21.7%; Average loss: 3.2477Iteration: 870; Percent complete: 21.8%; Average loss: 3.5365Iteration: 871; Percent complete: 21.8%; Average loss: 3.6691Iteration: 872; Percent complete: 21.8%; Average loss: 3.6751Iteration: 873; Percent complete: 21.8%; Average loss: 3.6541Iteration: 874; Percent complete: 21.9%; Average loss: 3.6469Iteration: 875; Percent complete: 21.9%; Average loss: 3.4103Iteration: 876; Percent complete: 21.9%; Average loss: 3.2825Iteration: 877; Percent complete: 21.9%; Average loss: 3.2114Iteration: 878; Percent complete: 21.9%; Average loss: 3.3977Iteration: 879; Percent complete: 22.0%; Average loss: 3.6545Iteration: 880; Percent complete: 22.0%; Average loss: 3.5630Iteration: 881; Percent complete: 22.0%; Average loss: 3.3862Iteration: 882; Percent complete: 22.1%; Average loss: 3.6798Iteration: 883; Percent complete: 22.1%; Average loss: 3.3177Iteration: 884; Percent complete: 22.1%; Average loss: 3.5939Iteration: 885; Percent complete: 22.1%; Average loss: 3.5382Iteration: 886; Percent complete: 22.1%; Average loss: 3.4560Iteration: 887; Percent complete: 22.2%; Average loss: 3.0264Iteration: 888; Percent complete: 22.2%; Average loss: 3.6159Iteration: 889; Percent complete: 22.2%; Average loss: 3.2934Iteration: 890; Percent complete: 22.2%; Average loss: 3.5563Iteration: 891; Percent complete: 22.3%; Average loss: 3.4753Iteration: 892; Percent complete: 22.3%; Average loss: 3.6632Iteration: 893; Percent complete: 22.3%; Average loss: 3.5452Iteration: 894; Percent complete: 22.4%; Average loss: 3.5704Iteration: 895; Percent complete: 22.4%; Average loss: 3.6098Iteration: 896; Percent complete: 22.4%; Average loss: 3.2751Iteration: 897; Percent complete: 22.4%; Average loss: 3.5669Iteration: 898; Percent complete: 22.4%; Average loss: 3.6339Iteration: 899; Percent complete: 22.5%; Average loss: 3.5087Iteration: 900; Percent complete: 22.5%; Average loss: 3.4495Iteration: 901; Percent complete: 22.5%; Average loss: 3.5360Iteration: 902; Percent complete: 22.6%; Average loss: 3.5263Iteration: 903; Percent complete: 22.6%; Average loss: 3.4129Iteration: 904; Percent complete: 22.6%; Average loss: 3.7305Iteration: 905; Percent complete: 22.6%; Average loss: 3.6788Iteration: 906; Percent complete: 22.7%; Average loss: 3.4712Iteration: 907; Percent complete: 22.7%; Average loss: 3.5296Iteration: 908; Percent complete: 22.7%; Average loss: 3.2729Iteration: 909; Percent complete: 22.7%; Average loss: 3.6267Iteration: 910; Percent complete: 22.8%; Average loss: 3.7182Iteration: 911; Percent complete: 22.8%; Average loss: 3.5293Iteration: 912; Percent complete: 22.8%; Average loss: 3.7549Iteration: 913; Percent complete: 22.8%; Average loss: 3.4024Iteration: 914; Percent complete: 22.9%; Average loss: 3.5118Iteration: 915; Percent complete: 22.9%; Average loss: 3.4186Iteration: 916; Percent complete: 22.9%; Average loss: 3.6017Iteration: 917; Percent complete: 22.9%; Average loss: 3.4542Iteration: 918; Percent complete: 22.9%; Average loss: 3.3118Iteration: 919; Percent complete: 23.0%; Average loss: 3.2720Iteration: 920; Percent complete: 23.0%; Average loss: 3.2578Iteration: 921; Percent complete: 23.0%; Average loss: 3.6098Iteration: 922; Percent complete: 23.1%; Average loss: 3.5619Iteration: 923; Percent complete: 23.1%; Average loss: 3.5533Iteration: 924; Percent complete: 23.1%; Average loss: 3.2588Iteration: 925; Percent complete: 23.1%; Average loss: 3.4663Iteration: 926; Percent complete: 23.2%; Average loss: 3.2145Iteration: 927; Percent complete: 23.2%; Average loss: 3.4074Iteration: 928; Percent complete: 23.2%; Average loss: 3.6742Iteration: 929; Percent complete: 23.2%; Average loss: 3.4356Iteration: 930; Percent complete: 23.2%; Average loss: 3.4078Iteration: 931; Percent complete: 23.3%; Average loss: 3.6956Iteration: 932; Percent complete: 23.3%; Average loss: 3.5146Iteration: 933; Percent complete: 23.3%; Average loss: 3.4873Iteration: 934; Percent complete: 23.4%; Average loss: 3.5704Iteration: 935; Percent complete: 23.4%; Average loss: 3.7044Iteration: 936; Percent complete: 23.4%; Average loss: 3.2354Iteration: 937; Percent complete: 23.4%; Average loss: 3.6065Iteration: 938; Percent complete: 23.4%; Average loss: 3.5104Iteration: 939; Percent complete: 23.5%; Average loss: 3.5636Iteration: 940; Percent complete: 23.5%; Average loss: 3.7151Iteration: 941; Percent complete: 23.5%; Average loss: 3.5884Iteration: 942; Percent complete: 23.5%; Average loss: 3.2944Iteration: 943; Percent complete: 23.6%; Average loss: 3.2923Iteration: 944; Percent complete: 23.6%; Average loss: 3.4452Iteration: 945; Percent complete: 23.6%; Average loss: 3.7689Iteration: 946; Percent complete: 23.6%; Average loss: 3.3128Iteration: 947; Percent complete: 23.7%; Average loss: 3.5018Iteration: 948; Percent complete: 23.7%; Average loss: 3.5428Iteration: 949; Percent complete: 23.7%; Average loss: 3.1980Iteration: 950; Percent complete: 23.8%; Average loss: 3.4962Iteration: 951; Percent complete: 23.8%; Average loss: 3.5463Iteration: 952; Percent complete: 23.8%; Average loss: 3.6260Iteration: 953; Percent complete: 23.8%; Average loss: 3.3665Iteration: 954; Percent complete: 23.8%; Average loss: 3.4916Iteration: 955; Percent complete: 23.9%; Average loss: 3.4944Iteration: 956; Percent complete: 23.9%; Average loss: 3.5904Iteration: 957; Percent complete: 23.9%; Average loss: 3.4101Iteration: 958; Percent complete: 23.9%; Average loss: 3.2496Iteration: 959; Percent complete: 24.0%; Average loss: 3.5565Iteration: 960; Percent complete: 24.0%; Average loss: 3.6001Iteration: 961; Percent complete: 24.0%; Average loss: 3.7049Iteration: 962; Percent complete: 24.1%; Average loss: 3.2483Iteration: 963; Percent complete: 24.1%; Average loss: 3.4287Iteration: 964; Percent complete: 24.1%; Average loss: 3.5874Iteration: 965; Percent complete: 24.1%; Average loss: 3.6788Iteration: 966; Percent complete: 24.1%; Average loss: 3.7579Iteration: 967; Percent complete: 24.2%; Average loss: 3.8236Iteration: 968; Percent complete: 24.2%; Average loss: 3.4406Iteration: 969; Percent complete: 24.2%; Average loss: 3.6640Iteration: 970; Percent complete: 24.2%; Average loss: 3.6300Iteration: 971; Percent complete: 24.3%; Average loss: 3.4417Iteration: 972; Percent complete: 24.3%; Average loss: 3.4492Iteration: 973; Percent complete: 24.3%; Average loss: 3.4356Iteration: 974; Percent complete: 24.3%; Average loss: 3.5793Iteration: 975; Percent complete: 24.4%; Average loss: 3.4942Iteration: 976; Percent complete: 24.4%; Average loss: 3.4834Iteration: 977; Percent complete: 24.4%; Average loss: 3.5403Iteration: 978; Percent complete: 24.4%; Average loss: 3.3249Iteration: 979; Percent complete: 24.5%; Average loss: 3.3791Iteration: 980; Percent complete: 24.5%; Average loss: 3.5912Iteration: 981; Percent complete: 24.5%; Average loss: 3.5039Iteration: 982; Percent complete: 24.6%; Average loss: 3.4364Iteration: 983; Percent complete: 24.6%; Average loss: 3.4137Iteration: 984; Percent complete: 24.6%; Average loss: 3.3872Iteration: 985; Percent complete: 24.6%; Average loss: 3.3406Iteration: 986; Percent complete: 24.6%; Average loss: 3.4965Iteration: 987; Percent complete: 24.7%; Average loss: 3.6338Iteration: 988; Percent complete: 24.7%; Average loss: 3.4323Iteration: 989; Percent complete: 24.7%; Average loss: 3.4854Iteration: 990; Percent complete: 24.8%; Average loss: 3.3648Iteration: 991; Percent complete: 24.8%; Average loss: 3.2904Iteration: 992; Percent complete: 24.8%; Average loss: 3.5488Iteration: 993; Percent complete: 24.8%; Average loss: 3.5292Iteration: 994; Percent complete: 24.9%; Average loss: 3.4604Iteration: 995; Percent complete: 24.9%; Average loss: 3.4765Iteration: 996; Percent complete: 24.9%; Average loss: 3.2887Iteration: 997; Percent complete: 24.9%; Average loss: 3.4171Iteration: 998; Percent complete: 24.9%; Average loss: 3.5462Iteration: 999; Percent complete: 25.0%; Average loss: 3.6950Iteration: 1000; Percent complete: 25.0%; Average loss: 3.5013Iteration: 1001; Percent complete: 25.0%; Average loss: 3.6464Iteration: 1002; Percent complete: 25.1%; Average loss: 3.4249Iteration: 1003; Percent complete: 25.1%; Average loss: 3.3661Iteration: 1004; Percent complete: 25.1%; Average loss: 3.3132Iteration: 1005; Percent complete: 25.1%; Average loss: 3.6630Iteration: 1006; Percent complete: 25.1%; Average loss: 3.5538Iteration: 1007; Percent complete: 25.2%; Average loss: 3.3751Iteration: 1008; Percent complete: 25.2%; Average loss: 3.4636Iteration: 1009; Percent complete: 25.2%; Average loss: 3.3829Iteration: 1010; Percent complete: 25.2%; Average loss: 3.3041Iteration: 1011; Percent complete: 25.3%; Average loss: 3.2490Iteration: 1012; Percent complete: 25.3%; Average loss: 3.2800Iteration: 1013; Percent complete: 25.3%; Average loss: 3.4626Iteration: 1014; Percent complete: 25.4%; Average loss: 3.4295Iteration: 1015; Percent complete: 25.4%; Average loss: 3.3300Iteration: 1016; Percent complete: 25.4%; Average loss: 3.4070Iteration: 1017; Percent complete: 25.4%; Average loss: 3.5102Iteration: 1018; Percent complete: 25.4%; Average loss: 3.2876Iteration: 1019; Percent complete: 25.5%; Average loss: 3.4514Iteration: 1020; Percent complete: 25.5%; Average loss: 3.5416Iteration: 1021; Percent complete: 25.5%; Average loss: 3.1231Iteration: 1022; Percent complete: 25.6%; Average loss: 3.6172Iteration: 1023; Percent complete: 25.6%; Average loss: 3.4862Iteration: 1024; Percent complete: 25.6%; Average loss: 3.4311Iteration: 1025; Percent complete: 25.6%; Average loss: 3.3377Iteration: 1026; Percent complete: 25.7%; Average loss: 3.4297Iteration: 1027; Percent complete: 25.7%; Average loss: 3.5747Iteration: 1028; Percent complete: 25.7%; Average loss: 3.3220Iteration: 1029; Percent complete: 25.7%; Average loss: 3.4714Iteration: 1030; Percent complete: 25.8%; Average loss: 3.4698Iteration: 1031; Percent complete: 25.8%; Average loss: 3.4686Iteration: 1032; Percent complete: 25.8%; Average loss: 3.3514Iteration: 1033; Percent complete: 25.8%; Average loss: 3.3770Iteration: 1034; Percent complete: 25.9%; Average loss: 3.1892Iteration: 1035; Percent complete: 25.9%; Average loss: 3.2069Iteration: 1036; Percent complete: 25.9%; Average loss: 3.6535Iteration: 1037; Percent complete: 25.9%; Average loss: 3.5384Iteration: 1038; Percent complete: 25.9%; Average loss: 3.4306Iteration: 1039; Percent complete: 26.0%; Average loss: 3.2332Iteration: 1040; Percent complete: 26.0%; Average loss: 3.7424Iteration: 1041; Percent complete: 26.0%; Average loss: 3.6434Iteration: 1042; Percent complete: 26.1%; Average loss: 3.4566Iteration: 1043; Percent complete: 26.1%; Average loss: 3.4762Iteration: 1044; Percent complete: 26.1%; Average loss: 3.6980Iteration: 1045; Percent complete: 26.1%; Average loss: 3.4439Iteration: 1046; Percent complete: 26.2%; Average loss: 3.4565Iteration: 1047; Percent complete: 26.2%; Average loss: 3.1455Iteration: 1048; Percent complete: 26.2%; Average loss: 3.3571Iteration: 1049; Percent complete: 26.2%; Average loss: 3.5684Iteration: 1050; Percent complete: 26.2%; Average loss: 3.6311Iteration: 1051; Percent complete: 26.3%; Average loss: 3.0905Iteration: 1052; Percent complete: 26.3%; Average loss: 3.3879Iteration: 1053; Percent complete: 26.3%; Average loss: 3.5997Iteration: 1054; Percent complete: 26.4%; Average loss: 3.7076Iteration: 1055; Percent complete: 26.4%; Average loss: 3.4371Iteration: 1056; Percent complete: 26.4%; Average loss: 3.5650Iteration: 1057; Percent complete: 26.4%; Average loss: 3.2555Iteration: 1058; Percent complete: 26.5%; Average loss: 3.3830Iteration: 1059; Percent complete: 26.5%; Average loss: 3.4656Iteration: 1060; Percent complete: 26.5%; Average loss: 3.4664Iteration: 1061; Percent complete: 26.5%; Average loss: 3.2791Iteration: 1062; Percent complete: 26.6%; Average loss: 3.4059Iteration: 1063; Percent complete: 26.6%; Average loss: 3.5831Iteration: 1064; Percent complete: 26.6%; Average loss: 3.7627Iteration: 1065; Percent complete: 26.6%; Average loss: 3.4564Iteration: 1066; Percent complete: 26.7%; Average loss: 3.2914Iteration: 1067; Percent complete: 26.7%; Average loss: 3.2026Iteration: 1068; Percent complete: 26.7%; Average loss: 3.4156Iteration: 1069; Percent complete: 26.7%; Average loss: 3.3793Iteration: 1070; Percent complete: 26.8%; Average loss: 3.6384Iteration: 1071; Percent complete: 26.8%; Average loss: 3.4372Iteration: 1072; Percent complete: 26.8%; Average loss: 3.5658Iteration: 1073; Percent complete: 26.8%; Average loss: 3.3983Iteration: 1074; Percent complete: 26.9%; Average loss: 3.4970Iteration: 1075; Percent complete: 26.9%; Average loss: 3.7483Iteration: 1076; Percent complete: 26.9%; Average loss: 3.4011Iteration: 1077; Percent complete: 26.9%; Average loss: 3.4383Iteration: 1078; Percent complete: 27.0%; Average loss: 3.4844Iteration: 1079; Percent complete: 27.0%; Average loss: 3.6654Iteration: 1080; Percent complete: 27.0%; Average loss: 3.4890Iteration: 1081; Percent complete: 27.0%; Average loss: 3.8529Iteration: 1082; Percent complete: 27.1%; Average loss: 2.9260Iteration: 1083; Percent complete: 27.1%; Average loss: 3.6430Iteration: 1084; Percent complete: 27.1%; Average loss: 3.4314Iteration: 1085; Percent complete: 27.1%; Average loss: 3.6121Iteration: 1086; Percent complete: 27.2%; Average loss: 3.2962Iteration: 1087; Percent complete: 27.2%; Average loss: 3.3264Iteration: 1088; Percent complete: 27.2%; Average loss: 3.4940Iteration: 1089; Percent complete: 27.2%; Average loss: 3.1954Iteration: 1090; Percent complete: 27.3%; Average loss: 3.6389Iteration: 1091; Percent complete: 27.3%; Average loss: 3.1642Iteration: 1092; Percent complete: 27.3%; Average loss: 3.4314Iteration: 1093; Percent complete: 27.3%; Average loss: 3.5454Iteration: 1094; Percent complete: 27.4%; Average loss: 3.5462Iteration: 1095; Percent complete: 27.4%; Average loss: 3.4023Iteration: 1096; Percent complete: 27.4%; Average loss: 3.2687Iteration: 1097; Percent complete: 27.4%; Average loss: 3.3778Iteration: 1098; Percent complete: 27.5%; Average loss: 3.5652Iteration: 1099; Percent complete: 27.5%; Average loss: 3.5189Iteration: 1100; Percent complete: 27.5%; Average loss: 3.6275Iteration: 1101; Percent complete: 27.5%; Average loss: 3.3685Iteration: 1102; Percent complete: 27.6%; Average loss: 3.2361Iteration: 1103; Percent complete: 27.6%; Average loss: 3.4623Iteration: 1104; Percent complete: 27.6%; Average loss: 3.5044Iteration: 1105; Percent complete: 27.6%; Average loss: 3.2375Iteration: 1106; Percent complete: 27.7%; Average loss: 3.6186Iteration: 1107; Percent complete: 27.7%; Average loss: 3.1069Iteration: 1108; Percent complete: 27.7%; Average loss: 3.3504Iteration: 1109; Percent complete: 27.7%; Average loss: 3.7140Iteration: 1110; Percent complete: 27.8%; Average loss: 3.5077Iteration: 1111; Percent complete: 27.8%; Average loss: 3.4796Iteration: 1112; Percent complete: 27.8%; Average loss: 3.6006Iteration: 1113; Percent complete: 27.8%; Average loss: 3.4220Iteration: 1114; Percent complete: 27.9%; Average loss: 3.2938Iteration: 1115; Percent complete: 27.9%; Average loss: 3.4396Iteration: 1116; Percent complete: 27.9%; Average loss: 3.3446Iteration: 1117; Percent complete: 27.9%; Average loss: 3.4104Iteration: 1118; Percent complete: 28.0%; Average loss: 3.3198Iteration: 1119; Percent complete: 28.0%; Average loss: 3.4505Iteration: 1120; Percent complete: 28.0%; Average loss: 3.6936Iteration: 1121; Percent complete: 28.0%; Average loss: 3.3487Iteration: 1122; Percent complete: 28.1%; Average loss: 3.4097Iteration: 1123; Percent complete: 28.1%; Average loss: 3.2892Iteration: 1124; Percent complete: 28.1%; Average loss: 3.2826Iteration: 1125; Percent complete: 28.1%; Average loss: 3.2282Iteration: 1126; Percent complete: 28.1%; Average loss: 3.5347Iteration: 1127; Percent complete: 28.2%; Average loss: 3.6368Iteration: 1128; Percent complete: 28.2%; Average loss: 3.5227Iteration: 1129; Percent complete: 28.2%; Average loss: 3.2822Iteration: 1130; Percent complete: 28.2%; Average loss: 3.1646Iteration: 1131; Percent complete: 28.3%; Average loss: 3.7442Iteration: 1132; Percent complete: 28.3%; Average loss: 3.2573Iteration: 1133; Percent complete: 28.3%; Average loss: 3.5346Iteration: 1134; Percent complete: 28.3%; Average loss: 3.5549Iteration: 1135; Percent complete: 28.4%; Average loss: 3.7803Iteration: 1136; Percent complete: 28.4%; Average loss: 3.1745Iteration: 1137; Percent complete: 28.4%; Average loss: 3.5782Iteration: 1138; Percent complete: 28.4%; Average loss: 3.6201Iteration: 1139; Percent complete: 28.5%; Average loss: 3.3860Iteration: 1140; Percent complete: 28.5%; Average loss: 3.5974Iteration: 1141; Percent complete: 28.5%; Average loss: 3.3202Iteration: 1142; Percent complete: 28.5%; Average loss: 3.1807Iteration: 1143; Percent complete: 28.6%; Average loss: 3.5277Iteration: 1144; Percent complete: 28.6%; Average loss: 3.4723Iteration: 1145; Percent complete: 28.6%; Average loss: 3.6172Iteration: 1146; Percent complete: 28.6%; Average loss: 3.5083Iteration: 1147; Percent complete: 28.7%; Average loss: 3.1717Iteration: 1148; Percent complete: 28.7%; Average loss: 3.6527Iteration: 1149; Percent complete: 28.7%; Average loss: 3.2360Iteration: 1150; Percent complete: 28.7%; Average loss: 3.4396Iteration: 1151; Percent complete: 28.8%; Average loss: 3.1910Iteration: 1152; Percent complete: 28.8%; Average loss: 3.6058Iteration: 1153; Percent complete: 28.8%; Average loss: 3.5982Iteration: 1154; Percent complete: 28.8%; Average loss: 3.3476Iteration: 1155; Percent complete: 28.9%; Average loss: 3.4052Iteration: 1156; Percent complete: 28.9%; Average loss: 3.1498Iteration: 1157; Percent complete: 28.9%; Average loss: 3.3498Iteration: 1158; Percent complete: 28.9%; Average loss: 3.5004Iteration: 1159; Percent complete: 29.0%; Average loss: 3.8108Iteration: 1160; Percent complete: 29.0%; Average loss: 3.5649Iteration: 1161; Percent complete: 29.0%; Average loss: 3.4980Iteration: 1162; Percent complete: 29.0%; Average loss: 3.6006Iteration: 1163; Percent complete: 29.1%; Average loss: 3.4976Iteration: 1164; Percent complete: 29.1%; Average loss: 3.4439Iteration: 1165; Percent complete: 29.1%; Average loss: 3.6694Iteration: 1166; Percent complete: 29.1%; Average loss: 3.2099Iteration: 1167; Percent complete: 29.2%; Average loss: 3.3692Iteration: 1168; Percent complete: 29.2%; Average loss: 3.6302Iteration: 1169; Percent complete: 29.2%; Average loss: 3.5384Iteration: 1170; Percent complete: 29.2%; Average loss: 3.5669Iteration: 1171; Percent complete: 29.3%; Average loss: 3.3949Iteration: 1172; Percent complete: 29.3%; Average loss: 3.2900Iteration: 1173; Percent complete: 29.3%; Average loss: 3.6825Iteration: 1174; Percent complete: 29.3%; Average loss: 3.5677Iteration: 1175; Percent complete: 29.4%; Average loss: 3.5144Iteration: 1176; Percent complete: 29.4%; Average loss: 3.4555Iteration: 1177; Percent complete: 29.4%; Average loss: 3.2780Iteration: 1178; Percent complete: 29.4%; Average loss: 3.5044Iteration: 1179; Percent complete: 29.5%; Average loss: 3.6036Iteration: 1180; Percent complete: 29.5%; Average loss: 3.4417Iteration: 1181; Percent complete: 29.5%; Average loss: 3.4034Iteration: 1182; Percent complete: 29.5%; Average loss: 3.7229Iteration: 1183; Percent complete: 29.6%; Average loss: 3.3143Iteration: 1184; Percent complete: 29.6%; Average loss: 3.3841Iteration: 1185; Percent complete: 29.6%; Average loss: 3.0159Iteration: 1186; Percent complete: 29.6%; Average loss: 3.3383Iteration: 1187; Percent complete: 29.7%; Average loss: 3.5566Iteration: 1188; Percent complete: 29.7%; Average loss: 3.4854Iteration: 1189; Percent complete: 29.7%; Average loss: 3.4538Iteration: 1190; Percent complete: 29.8%; Average loss: 3.4629Iteration: 1191; Percent complete: 29.8%; Average loss: 3.1429Iteration: 1192; Percent complete: 29.8%; Average loss: 3.3879Iteration: 1193; Percent complete: 29.8%; Average loss: 3.5256Iteration: 1194; Percent complete: 29.8%; Average loss: 3.4556Iteration: 1195; Percent complete: 29.9%; Average loss: 3.4537Iteration: 1196; Percent complete: 29.9%; Average loss: 3.5113Iteration: 1197; Percent complete: 29.9%; Average loss: 3.3586Iteration: 1198; Percent complete: 29.9%; Average loss: 3.4415Iteration: 1199; Percent complete: 30.0%; Average loss: 3.4853Iteration: 1200; Percent complete: 30.0%; Average loss: 3.5113Iteration: 1201; Percent complete: 30.0%; Average loss: 3.6824Iteration: 1202; Percent complete: 30.0%; Average loss: 3.1903Iteration: 1203; Percent complete: 30.1%; Average loss: 3.4258Iteration: 1204; Percent complete: 30.1%; Average loss: 3.4361Iteration: 1205; Percent complete: 30.1%; Average loss: 3.3465Iteration: 1206; Percent complete: 30.1%; Average loss: 3.4490Iteration: 1207; Percent complete: 30.2%; Average loss: 3.3449Iteration: 1208; Percent complete: 30.2%; Average loss: 3.5493Iteration: 1209; Percent complete: 30.2%; Average loss: 3.5034Iteration: 1210; Percent complete: 30.2%; Average loss: 3.3737Iteration: 1211; Percent complete: 30.3%; Average loss: 3.3051Iteration: 1212; Percent complete: 30.3%; Average loss: 3.2414Iteration: 1213; Percent complete: 30.3%; Average loss: 3.5738Iteration: 1214; Percent complete: 30.3%; Average loss: 3.4250Iteration: 1215; Percent complete: 30.4%; Average loss: 3.4152Iteration: 1216; Percent complete: 30.4%; Average loss: 3.3783Iteration: 1217; Percent complete: 30.4%; Average loss: 3.5382Iteration: 1218; Percent complete: 30.4%; Average loss: 3.4592Iteration: 1219; Percent complete: 30.5%; Average loss: 3.3885Iteration: 1220; Percent complete: 30.5%; Average loss: 3.4402Iteration: 1221; Percent complete: 30.5%; Average loss: 3.3418Iteration: 1222; Percent complete: 30.6%; Average loss: 3.2057Iteration: 1223; Percent complete: 30.6%; Average loss: 3.3983Iteration: 1224; Percent complete: 30.6%; Average loss: 3.6310Iteration: 1225; Percent complete: 30.6%; Average loss: 3.5101Iteration: 1226; Percent complete: 30.6%; Average loss: 3.3765Iteration: 1227; Percent complete: 30.7%; Average loss: 3.3952Iteration: 1228; Percent complete: 30.7%; Average loss: 3.5772Iteration: 1229; Percent complete: 30.7%; Average loss: 3.2604Iteration: 1230; Percent complete: 30.8%; Average loss: 3.1483Iteration: 1231; Percent complete: 30.8%; Average loss: 3.2702Iteration: 1232; Percent complete: 30.8%; Average loss: 3.3282Iteration: 1233; Percent complete: 30.8%; Average loss: 3.2308Iteration: 1234; Percent complete: 30.9%; Average loss: 3.2600Iteration: 1235; Percent complete: 30.9%; Average loss: 3.1862Iteration: 1236; Percent complete: 30.9%; Average loss: 3.2931Iteration: 1237; Percent complete: 30.9%; Average loss: 3.3940Iteration: 1238; Percent complete: 30.9%; Average loss: 3.3462Iteration: 1239; Percent complete: 31.0%; Average loss: 3.4245Iteration: 1240; Percent complete: 31.0%; Average loss: 3.2197Iteration: 1241; Percent complete: 31.0%; Average loss: 3.1165Iteration: 1242; Percent complete: 31.1%; Average loss: 3.4255Iteration: 1243; Percent complete: 31.1%; Average loss: 3.2863Iteration: 1244; Percent complete: 31.1%; Average loss: 3.2583Iteration: 1245; Percent complete: 31.1%; Average loss: 3.1897Iteration: 1246; Percent complete: 31.1%; Average loss: 3.2355Iteration: 1247; Percent complete: 31.2%; Average loss: 3.0343Iteration: 1248; Percent complete: 31.2%; Average loss: 3.3908Iteration: 1249; Percent complete: 31.2%; Average loss: 3.3241Iteration: 1250; Percent complete: 31.2%; Average loss: 3.1954Iteration: 1251; Percent complete: 31.3%; Average loss: 3.0228Iteration: 1252; Percent complete: 31.3%; Average loss: 3.2462Iteration: 1253; Percent complete: 31.3%; Average loss: 3.5869Iteration: 1254; Percent complete: 31.4%; Average loss: 3.4405Iteration: 1255; Percent complete: 31.4%; Average loss: 3.2538Iteration: 1256; Percent complete: 31.4%; Average loss: 3.3199Iteration: 1257; Percent complete: 31.4%; Average loss: 3.3229Iteration: 1258; Percent complete: 31.4%; Average loss: 3.3963Iteration: 1259; Percent complete: 31.5%; Average loss: 3.4635Iteration: 1260; Percent complete: 31.5%; Average loss: 3.5515Iteration: 1261; Percent complete: 31.5%; Average loss: 3.3443Iteration: 1262; Percent complete: 31.6%; Average loss: 3.3746Iteration: 1263; Percent complete: 31.6%; Average loss: 3.5301Iteration: 1264; Percent complete: 31.6%; Average loss: 3.3242Iteration: 1265; Percent complete: 31.6%; Average loss: 3.1335Iteration: 1266; Percent complete: 31.6%; Average loss: 3.1527Iteration: 1267; Percent complete: 31.7%; Average loss: 3.3077Iteration: 1268; Percent complete: 31.7%; Average loss: 3.4511Iteration: 1269; Percent complete: 31.7%; Average loss: 3.5524Iteration: 1270; Percent complete: 31.8%; Average loss: 3.3616Iteration: 1271; Percent complete: 31.8%; Average loss: 3.2862Iteration: 1272; Percent complete: 31.8%; Average loss: 3.4913Iteration: 1273; Percent complete: 31.8%; Average loss: 3.6480Iteration: 1274; Percent complete: 31.9%; Average loss: 3.0928Iteration: 1275; Percent complete: 31.9%; Average loss: 3.4313Iteration: 1276; Percent complete: 31.9%; Average loss: 3.7055Iteration: 1277; Percent complete: 31.9%; Average loss: 3.8617Iteration: 1278; Percent complete: 31.9%; Average loss: 3.2961Iteration: 1279; Percent complete: 32.0%; Average loss: 3.3946Iteration: 1280; Percent complete: 32.0%; Average loss: 3.2520Iteration: 1281; Percent complete: 32.0%; Average loss: 3.1006Iteration: 1282; Percent complete: 32.0%; Average loss: 3.1648Iteration: 1283; Percent complete: 32.1%; Average loss: 3.5625Iteration: 1284; Percent complete: 32.1%; Average loss: 3.5290Iteration: 1285; Percent complete: 32.1%; Average loss: 3.4984Iteration: 1286; Percent complete: 32.1%; Average loss: 3.3592Iteration: 1287; Percent complete: 32.2%; Average loss: 3.4584Iteration: 1288; Percent complete: 32.2%; Average loss: 3.0914Iteration: 1289; Percent complete: 32.2%; Average loss: 3.0810Iteration: 1290; Percent complete: 32.2%; Average loss: 3.1847Iteration: 1291; Percent complete: 32.3%; Average loss: 3.6247Iteration: 1292; Percent complete: 32.3%; Average loss: 3.4194Iteration: 1293; Percent complete: 32.3%; Average loss: 3.4869Iteration: 1294; Percent complete: 32.4%; Average loss: 3.4202Iteration: 1295; Percent complete: 32.4%; Average loss: 3.4309Iteration: 1296; Percent complete: 32.4%; Average loss: 3.3381Iteration: 1297; Percent complete: 32.4%; Average loss: 3.1818Iteration: 1298; Percent complete: 32.5%; Average loss: 3.4659Iteration: 1299; Percent complete: 32.5%; Average loss: 3.4478Iteration: 1300; Percent complete: 32.5%; Average loss: 3.3064Iteration: 1301; Percent complete: 32.5%; Average loss: 3.3115Iteration: 1302; Percent complete: 32.6%; Average loss: 3.5502Iteration: 1303; Percent complete: 32.6%; Average loss: 3.5243Iteration: 1304; Percent complete: 32.6%; Average loss: 3.4826Iteration: 1305; Percent complete: 32.6%; Average loss: 3.5788Iteration: 1306; Percent complete: 32.6%; Average loss: 3.4841Iteration: 1307; Percent complete: 32.7%; Average loss: 3.1750Iteration: 1308; Percent complete: 32.7%; Average loss: 3.2277Iteration: 1309; Percent complete: 32.7%; Average loss: 3.4109Iteration: 1310; Percent complete: 32.8%; Average loss: 3.3088Iteration: 1311; Percent complete: 32.8%; Average loss: 3.3152Iteration: 1312; Percent complete: 32.8%; Average loss: 3.2366Iteration: 1313; Percent complete: 32.8%; Average loss: 3.3096Iteration: 1314; Percent complete: 32.9%; Average loss: 3.3125Iteration: 1315; Percent complete: 32.9%; Average loss: 3.4585Iteration: 1316; Percent complete: 32.9%; Average loss: 3.3373Iteration: 1317; Percent complete: 32.9%; Average loss: 3.2799Iteration: 1318; Percent complete: 33.0%; Average loss: 3.1428Iteration: 1319; Percent complete: 33.0%; Average loss: 3.2528Iteration: 1320; Percent complete: 33.0%; Average loss: 3.2274Iteration: 1321; Percent complete: 33.0%; Average loss: 3.4907Iteration: 1322; Percent complete: 33.1%; Average loss: 3.4711Iteration: 1323; Percent complete: 33.1%; Average loss: 3.4932Iteration: 1324; Percent complete: 33.1%; Average loss: 3.3868Iteration: 1325; Percent complete: 33.1%; Average loss: 3.4240Iteration: 1326; Percent complete: 33.1%; Average loss: 3.4178Iteration: 1327; Percent complete: 33.2%; Average loss: 3.2333Iteration: 1328; Percent complete: 33.2%; Average loss: 3.2863Iteration: 1329; Percent complete: 33.2%; Average loss: 3.2421Iteration: 1330; Percent complete: 33.2%; Average loss: 3.3384Iteration: 1331; Percent complete: 33.3%; Average loss: 3.1235Iteration: 1332; Percent complete: 33.3%; Average loss: 3.2565Iteration: 1333; Percent complete: 33.3%; Average loss: 3.3130Iteration: 1334; Percent complete: 33.4%; Average loss: 3.4720Iteration: 1335; Percent complete: 33.4%; Average loss: 3.1951Iteration: 1336; Percent complete: 33.4%; Average loss: 3.5387Iteration: 1337; Percent complete: 33.4%; Average loss: 3.3063Iteration: 1338; Percent complete: 33.5%; Average loss: 3.4310Iteration: 1339; Percent complete: 33.5%; Average loss: 3.2019Iteration: 1340; Percent complete: 33.5%; Average loss: 3.2799Iteration: 1341; Percent complete: 33.5%; Average loss: 3.4221Iteration: 1342; Percent complete: 33.6%; Average loss: 3.4430Iteration: 1343; Percent complete: 33.6%; Average loss: 3.4220Iteration: 1344; Percent complete: 33.6%; Average loss: 3.5079Iteration: 1345; Percent complete: 33.6%; Average loss: 3.4936Iteration: 1346; Percent complete: 33.7%; Average loss: 3.1109Iteration: 1347; Percent complete: 33.7%; Average loss: 3.5157Iteration: 1348; Percent complete: 33.7%; Average loss: 3.2075Iteration: 1349; Percent complete: 33.7%; Average loss: 3.1537Iteration: 1350; Percent complete: 33.8%; Average loss: 3.7093Iteration: 1351; Percent complete: 33.8%; Average loss: 3.2867Iteration: 1352; Percent complete: 33.8%; Average loss: 3.4799Iteration: 1353; Percent complete: 33.8%; Average loss: 3.3470Iteration: 1354; Percent complete: 33.9%; Average loss: 3.2471Iteration: 1355; Percent complete: 33.9%; Average loss: 3.3990Iteration: 1356; Percent complete: 33.9%; Average loss: 3.2850Iteration: 1357; Percent complete: 33.9%; Average loss: 3.1213Iteration: 1358; Percent complete: 34.0%; Average loss: 3.1368Iteration: 1359; Percent complete: 34.0%; Average loss: 3.3456Iteration: 1360; Percent complete: 34.0%; Average loss: 3.2262Iteration: 1361; Percent complete: 34.0%; Average loss: 3.3460Iteration: 1362; Percent complete: 34.1%; Average loss: 3.2746Iteration: 1363; Percent complete: 34.1%; Average loss: 3.5915Iteration: 1364; Percent complete: 34.1%; Average loss: 3.4694Iteration: 1365; Percent complete: 34.1%; Average loss: 3.2308Iteration: 1366; Percent complete: 34.2%; Average loss: 3.2806Iteration: 1367; Percent complete: 34.2%; Average loss: 3.2687Iteration: 1368; Percent complete: 34.2%; Average loss: 3.4416Iteration: 1369; Percent complete: 34.2%; Average loss: 3.3305Iteration: 1370; Percent complete: 34.2%; Average loss: 3.4977Iteration: 1371; Percent complete: 34.3%; Average loss: 3.0259Iteration: 1372; Percent complete: 34.3%; Average loss: 3.2745Iteration: 1373; Percent complete: 34.3%; Average loss: 3.2031Iteration: 1374; Percent complete: 34.4%; Average loss: 3.2353Iteration: 1375; Percent complete: 34.4%; Average loss: 3.5895Iteration: 1376; Percent complete: 34.4%; Average loss: 3.2618Iteration: 1377; Percent complete: 34.4%; Average loss: 3.4747Iteration: 1378; Percent complete: 34.4%; Average loss: 3.4604Iteration: 1379; Percent complete: 34.5%; Average loss: 3.3372Iteration: 1380; Percent complete: 34.5%; Average loss: 3.3893Iteration: 1381; Percent complete: 34.5%; Average loss: 3.4994Iteration: 1382; Percent complete: 34.5%; Average loss: 3.6076Iteration: 1383; Percent complete: 34.6%; Average loss: 3.3641Iteration: 1384; Percent complete: 34.6%; Average loss: 3.4077Iteration: 1385; Percent complete: 34.6%; Average loss: 3.5129Iteration: 1386; Percent complete: 34.6%; Average loss: 3.5096Iteration: 1387; Percent complete: 34.7%; Average loss: 3.3306Iteration: 1388; Percent complete: 34.7%; Average loss: 3.3461Iteration: 1389; Percent complete: 34.7%; Average loss: 3.2720Iteration: 1390; Percent complete: 34.8%; Average loss: 3.1723Iteration: 1391; Percent complete: 34.8%; Average loss: 3.2438Iteration: 1392; Percent complete: 34.8%; Average loss: 3.4626Iteration: 1393; Percent complete: 34.8%; Average loss: 2.9481Iteration: 1394; Percent complete: 34.8%; Average loss: 3.3751Iteration: 1395; Percent complete: 34.9%; Average loss: 3.1364Iteration: 1396; Percent complete: 34.9%; Average loss: 3.3793Iteration: 1397; Percent complete: 34.9%; Average loss: 3.2960Iteration: 1398; Percent complete: 34.9%; Average loss: 3.3865Iteration: 1399; Percent complete: 35.0%; Average loss: 3.2995Iteration: 1400; Percent complete: 35.0%; Average loss: 3.0302Iteration: 1401; Percent complete: 35.0%; Average loss: 3.1878Iteration: 1402; Percent complete: 35.0%; Average loss: 3.3430Iteration: 1403; Percent complete: 35.1%; Average loss: 3.4577Iteration: 1404; Percent complete: 35.1%; Average loss: 3.4808Iteration: 1405; Percent complete: 35.1%; Average loss: 3.0934Iteration: 1406; Percent complete: 35.1%; Average loss: 3.4789Iteration: 1407; Percent complete: 35.2%; Average loss: 3.2595Iteration: 1408; Percent complete: 35.2%; Average loss: 3.2492Iteration: 1409; Percent complete: 35.2%; Average loss: 3.0552Iteration: 1410; Percent complete: 35.2%; Average loss: 3.4256Iteration: 1411; Percent complete: 35.3%; Average loss: 3.2867Iteration: 1412; Percent complete: 35.3%; Average loss: 3.0850Iteration: 1413; Percent complete: 35.3%; Average loss: 2.9854Iteration: 1414; Percent complete: 35.4%; Average loss: 3.3832Iteration: 1415; Percent complete: 35.4%; Average loss: 3.0969Iteration: 1416; Percent complete: 35.4%; Average loss: 3.5027Iteration: 1417; Percent complete: 35.4%; Average loss: 3.0796Iteration: 1418; Percent complete: 35.4%; Average loss: 3.5941Iteration: 1419; Percent complete: 35.5%; Average loss: 3.0673Iteration: 1420; Percent complete: 35.5%; Average loss: 3.3238Iteration: 1421; Percent complete: 35.5%; Average loss: 3.1930Iteration: 1422; Percent complete: 35.5%; Average loss: 3.2909Iteration: 1423; Percent complete: 35.6%; Average loss: 3.3611Iteration: 1424; Percent complete: 35.6%; Average loss: 3.2585Iteration: 1425; Percent complete: 35.6%; Average loss: 3.2677Iteration: 1426; Percent complete: 35.6%; Average loss: 3.1003Iteration: 1427; Percent complete: 35.7%; Average loss: 3.0681Iteration: 1428; Percent complete: 35.7%; Average loss: 3.1357Iteration: 1429; Percent complete: 35.7%; Average loss: 3.3914Iteration: 1430; Percent complete: 35.8%; Average loss: 3.0309Iteration: 1431; Percent complete: 35.8%; Average loss: 3.1685Iteration: 1432; Percent complete: 35.8%; Average loss: 3.3739Iteration: 1433; Percent complete: 35.8%; Average loss: 3.2827Iteration: 1434; Percent complete: 35.9%; Average loss: 3.1481Iteration: 1435; Percent complete: 35.9%; Average loss: 3.4240Iteration: 1436; Percent complete: 35.9%; Average loss: 3.5213Iteration: 1437; Percent complete: 35.9%; Average loss: 3.4101Iteration: 1438; Percent complete: 35.9%; Average loss: 3.4574Iteration: 1439; Percent complete: 36.0%; Average loss: 3.2038Iteration: 1440; Percent complete: 36.0%; Average loss: 3.3998Iteration: 1441; Percent complete: 36.0%; Average loss: 3.3488Iteration: 1442; Percent complete: 36.0%; Average loss: 3.3923Iteration: 1443; Percent complete: 36.1%; Average loss: 3.2729Iteration: 1444; Percent complete: 36.1%; Average loss: 3.5520Iteration: 1445; Percent complete: 36.1%; Average loss: 3.3685Iteration: 1446; Percent complete: 36.1%; Average loss: 3.5247Iteration: 1447; Percent complete: 36.2%; Average loss: 3.3764Iteration: 1448; Percent complete: 36.2%; Average loss: 3.5342Iteration: 1449; Percent complete: 36.2%; Average loss: 3.2875Iteration: 1450; Percent complete: 36.2%; Average loss: 3.2452Iteration: 1451; Percent complete: 36.3%; Average loss: 3.1907Iteration: 1452; Percent complete: 36.3%; Average loss: 3.3185Iteration: 1453; Percent complete: 36.3%; Average loss: 3.2397Iteration: 1454; Percent complete: 36.4%; Average loss: 3.0991Iteration: 1455; Percent complete: 36.4%; Average loss: 3.2389Iteration: 1456; Percent complete: 36.4%; Average loss: 3.1761Iteration: 1457; Percent complete: 36.4%; Average loss: 3.4675Iteration: 1458; Percent complete: 36.4%; Average loss: 3.2817Iteration: 1459; Percent complete: 36.5%; Average loss: 3.3173Iteration: 1460; Percent complete: 36.5%; Average loss: 3.3328Iteration: 1461; Percent complete: 36.5%; Average loss: 3.2374Iteration: 1462; Percent complete: 36.5%; Average loss: 3.3790Iteration: 1463; Percent complete: 36.6%; Average loss: 3.5624Iteration: 1464; Percent complete: 36.6%; Average loss: 3.4367Iteration: 1465; Percent complete: 36.6%; Average loss: 3.4970Iteration: 1466; Percent complete: 36.6%; Average loss: 3.1718Iteration: 1467; Percent complete: 36.7%; Average loss: 3.4680Iteration: 1468; Percent complete: 36.7%; Average loss: 3.0726Iteration: 1469; Percent complete: 36.7%; Average loss: 3.1939Iteration: 1470; Percent complete: 36.8%; Average loss: 3.4144Iteration: 1471; Percent complete: 36.8%; Average loss: 3.3825Iteration: 1472; Percent complete: 36.8%; Average loss: 3.2660Iteration: 1473; Percent complete: 36.8%; Average loss: 3.3104Iteration: 1474; Percent complete: 36.9%; Average loss: 2.9227Iteration: 1475; Percent complete: 36.9%; Average loss: 3.3245Iteration: 1476; Percent complete: 36.9%; Average loss: 3.2662Iteration: 1477; Percent complete: 36.9%; Average loss: 3.2953Iteration: 1478; Percent complete: 37.0%; Average loss: 3.4875Iteration: 1479; Percent complete: 37.0%; Average loss: 3.1860Iteration: 1480; Percent complete: 37.0%; Average loss: 3.0735Iteration: 1481; Percent complete: 37.0%; Average loss: 3.5094Iteration: 1482; Percent complete: 37.0%; Average loss: 3.2504Iteration: 1483; Percent complete: 37.1%; Average loss: 3.3288Iteration: 1484; Percent complete: 37.1%; Average loss: 2.9987Iteration: 1485; Percent complete: 37.1%; Average loss: 3.2181Iteration: 1486; Percent complete: 37.1%; Average loss: 3.2172Iteration: 1487; Percent complete: 37.2%; Average loss: 3.4318Iteration: 1488; Percent complete: 37.2%; Average loss: 3.3491Iteration: 1489; Percent complete: 37.2%; Average loss: 3.3553Iteration: 1490; Percent complete: 37.2%; Average loss: 3.4959Iteration: 1491; Percent complete: 37.3%; Average loss: 3.1321Iteration: 1492; Percent complete: 37.3%; Average loss: 3.1588Iteration: 1493; Percent complete: 37.3%; Average loss: 3.3996Iteration: 1494; Percent complete: 37.4%; Average loss: 3.1645Iteration: 1495; Percent complete: 37.4%; Average loss: 3.3754Iteration: 1496; Percent complete: 37.4%; Average loss: 3.4006Iteration: 1497; Percent complete: 37.4%; Average loss: 3.4163Iteration: 1498; Percent complete: 37.5%; Average loss: 3.5607Iteration: 1499; Percent complete: 37.5%; Average loss: 3.3529Iteration: 1500; Percent complete: 37.5%; Average loss: 3.2433Iteration: 1501; Percent complete: 37.5%; Average loss: 3.6478Iteration: 1502; Percent complete: 37.5%; Average loss: 3.4193Iteration: 1503; Percent complete: 37.6%; Average loss: 3.3895Iteration: 1504; Percent complete: 37.6%; Average loss: 3.3300Iteration: 1505; Percent complete: 37.6%; Average loss: 3.5156Iteration: 1506; Percent complete: 37.6%; Average loss: 3.4109Iteration: 1507; Percent complete: 37.7%; Average loss: 3.2843Iteration: 1508; Percent complete: 37.7%; Average loss: 3.3143Iteration: 1509; Percent complete: 37.7%; Average loss: 3.2357Iteration: 1510; Percent complete: 37.8%; Average loss: 3.3901Iteration: 1511; Percent complete: 37.8%; Average loss: 3.4478Iteration: 1512; Percent complete: 37.8%; Average loss: 3.3435Iteration: 1513; Percent complete: 37.8%; Average loss: 3.1914Iteration: 1514; Percent complete: 37.9%; Average loss: 3.3859Iteration: 1515; Percent complete: 37.9%; Average loss: 3.3998Iteration: 1516; Percent complete: 37.9%; Average loss: 3.5175Iteration: 1517; Percent complete: 37.9%; Average loss: 3.3856Iteration: 1518; Percent complete: 38.0%; Average loss: 3.4922Iteration: 1519; Percent complete: 38.0%; Average loss: 3.3067Iteration: 1520; Percent complete: 38.0%; Average loss: 3.2161Iteration: 1521; Percent complete: 38.0%; Average loss: 3.4084Iteration: 1522; Percent complete: 38.0%; Average loss: 3.2961Iteration: 1523; Percent complete: 38.1%; Average loss: 3.1211Iteration: 1524; Percent complete: 38.1%; Average loss: 3.3216Iteration: 1525; Percent complete: 38.1%; Average loss: 3.3366Iteration: 1526; Percent complete: 38.1%; Average loss: 3.3046Iteration: 1527; Percent complete: 38.2%; Average loss: 3.2112Iteration: 1528; Percent complete: 38.2%; Average loss: 3.4449Iteration: 1529; Percent complete: 38.2%; Average loss: 3.3272Iteration: 1530; Percent complete: 38.2%; Average loss: 3.4564Iteration: 1531; Percent complete: 38.3%; Average loss: 3.2305Iteration: 1532; Percent complete: 38.3%; Average loss: 3.3710Iteration: 1533; Percent complete: 38.3%; Average loss: 3.3791Iteration: 1534; Percent complete: 38.4%; Average loss: 3.5189Iteration: 1535; Percent complete: 38.4%; Average loss: 3.3409Iteration: 1536; Percent complete: 38.4%; Average loss: 3.1401Iteration: 1537; Percent complete: 38.4%; Average loss: 3.2091Iteration: 1538; Percent complete: 38.5%; Average loss: 3.2662Iteration: 1539; Percent complete: 38.5%; Average loss: 3.2748Iteration: 1540; Percent complete: 38.5%; Average loss: 3.3925Iteration: 1541; Percent complete: 38.5%; Average loss: 3.2310Iteration: 1542; Percent complete: 38.6%; Average loss: 3.5550Iteration: 1543; Percent complete: 38.6%; Average loss: 3.4032Iteration: 1544; Percent complete: 38.6%; Average loss: 3.3527Iteration: 1545; Percent complete: 38.6%; Average loss: 3.2912Iteration: 1546; Percent complete: 38.6%; Average loss: 3.2219Iteration: 1547; Percent complete: 38.7%; Average loss: 3.1705Iteration: 1548; Percent complete: 38.7%; Average loss: 3.2673Iteration: 1549; Percent complete: 38.7%; Average loss: 3.5523Iteration: 1550; Percent complete: 38.8%; Average loss: 3.0841Iteration: 1551; Percent complete: 38.8%; Average loss: 3.2512Iteration: 1552; Percent complete: 38.8%; Average loss: 3.3382Iteration: 1553; Percent complete: 38.8%; Average loss: 3.6052Iteration: 1554; Percent complete: 38.9%; Average loss: 3.1594Iteration: 1555; Percent complete: 38.9%; Average loss: 3.1588Iteration: 1556; Percent complete: 38.9%; Average loss: 3.4274Iteration: 1557; Percent complete: 38.9%; Average loss: 3.3653Iteration: 1558; Percent complete: 39.0%; Average loss: 3.0972Iteration: 1559; Percent complete: 39.0%; Average loss: 3.2722Iteration: 1560; Percent complete: 39.0%; Average loss: 3.2740Iteration: 1561; Percent complete: 39.0%; Average loss: 3.5884Iteration: 1562; Percent complete: 39.1%; Average loss: 3.2083Iteration: 1563; Percent complete: 39.1%; Average loss: 3.3733Iteration: 1564; Percent complete: 39.1%; Average loss: 3.0672Iteration: 1565; Percent complete: 39.1%; Average loss: 3.1518Iteration: 1566; Percent complete: 39.1%; Average loss: 3.1684Iteration: 1567; Percent complete: 39.2%; Average loss: 3.0941Iteration: 1568; Percent complete: 39.2%; Average loss: 3.4483Iteration: 1569; Percent complete: 39.2%; Average loss: 3.4232Iteration: 1570; Percent complete: 39.2%; Average loss: 3.3852Iteration: 1571; Percent complete: 39.3%; Average loss: 3.2590Iteration: 1572; Percent complete: 39.3%; Average loss: 3.0071Iteration: 1573; Percent complete: 39.3%; Average loss: 3.3271Iteration: 1574; Percent complete: 39.4%; Average loss: 3.4749Iteration: 1575; Percent complete: 39.4%; Average loss: 3.3897Iteration: 1576; Percent complete: 39.4%; Average loss: 3.2667Iteration: 1577; Percent complete: 39.4%; Average loss: 3.2263Iteration: 1578; Percent complete: 39.5%; Average loss: 3.2840Iteration: 1579; Percent complete: 39.5%; Average loss: 3.4020Iteration: 1580; Percent complete: 39.5%; Average loss: 3.2618Iteration: 1581; Percent complete: 39.5%; Average loss: 3.2550Iteration: 1582; Percent complete: 39.6%; Average loss: 3.2973Iteration: 1583; Percent complete: 39.6%; Average loss: 3.3862Iteration: 1584; Percent complete: 39.6%; Average loss: 3.5161Iteration: 1585; Percent complete: 39.6%; Average loss: 3.3844Iteration: 1586; Percent complete: 39.6%; Average loss: 3.1230Iteration: 1587; Percent complete: 39.7%; Average loss: 3.2308Iteration: 1588; Percent complete: 39.7%; Average loss: 3.1491Iteration: 1589; Percent complete: 39.7%; Average loss: 3.1074Iteration: 1590; Percent complete: 39.8%; Average loss: 3.0619Iteration: 1591; Percent complete: 39.8%; Average loss: 3.2000Iteration: 1592; Percent complete: 39.8%; Average loss: 3.1809Iteration: 1593; Percent complete: 39.8%; Average loss: 3.2494Iteration: 1594; Percent complete: 39.9%; Average loss: 3.2509Iteration: 1595; Percent complete: 39.9%; Average loss: 3.1319Iteration: 1596; Percent complete: 39.9%; Average loss: 3.3572Iteration: 1597; Percent complete: 39.9%; Average loss: 3.4370Iteration: 1598; Percent complete: 40.0%; Average loss: 3.2377Iteration: 1599; Percent complete: 40.0%; Average loss: 3.0586Iteration: 1600; Percent complete: 40.0%; Average loss: 3.0794Iteration: 1601; Percent complete: 40.0%; Average loss: 3.1125Iteration: 1602; Percent complete: 40.1%; Average loss: 3.0954Iteration: 1603; Percent complete: 40.1%; Average loss: 3.3040Iteration: 1604; Percent complete: 40.1%; Average loss: 3.2242Iteration: 1605; Percent complete: 40.1%; Average loss: 3.1444Iteration: 1606; Percent complete: 40.2%; Average loss: 3.0485Iteration: 1607; Percent complete: 40.2%; Average loss: 2.9862Iteration: 1608; Percent complete: 40.2%; Average loss: 3.3951Iteration: 1609; Percent complete: 40.2%; Average loss: 3.4704Iteration: 1610; Percent complete: 40.2%; Average loss: 3.1896Iteration: 1611; Percent complete: 40.3%; Average loss: 3.1136Iteration: 1612; Percent complete: 40.3%; Average loss: 3.6329Iteration: 1613; Percent complete: 40.3%; Average loss: 3.2146Iteration: 1614; Percent complete: 40.4%; Average loss: 3.3593Iteration: 1615; Percent complete: 40.4%; Average loss: 3.3343Iteration: 1616; Percent complete: 40.4%; Average loss: 3.2684Iteration: 1617; Percent complete: 40.4%; Average loss: 3.5018Iteration: 1618; Percent complete: 40.5%; Average loss: 3.3905Iteration: 1619; Percent complete: 40.5%; Average loss: 3.2717Iteration: 1620; Percent complete: 40.5%; Average loss: 3.2225Iteration: 1621; Percent complete: 40.5%; Average loss: 3.2980Iteration: 1622; Percent complete: 40.6%; Average loss: 3.3720Iteration: 1623; Percent complete: 40.6%; Average loss: 3.2574Iteration: 1624; Percent complete: 40.6%; Average loss: 3.3126Iteration: 1625; Percent complete: 40.6%; Average loss: 3.3462Iteration: 1626; Percent complete: 40.6%; Average loss: 3.2474Iteration: 1627; Percent complete: 40.7%; Average loss: 3.3502Iteration: 1628; Percent complete: 40.7%; Average loss: 3.1517Iteration: 1629; Percent complete: 40.7%; Average loss: 3.2514Iteration: 1630; Percent complete: 40.8%; Average loss: 3.2084Iteration: 1631; Percent complete: 40.8%; Average loss: 3.5094Iteration: 1632; Percent complete: 40.8%; Average loss: 3.2715Iteration: 1633; Percent complete: 40.8%; Average loss: 3.0346Iteration: 1634; Percent complete: 40.8%; Average loss: 3.2390Iteration: 1635; Percent complete: 40.9%; Average loss: 3.2868Iteration: 1636; Percent complete: 40.9%; Average loss: 3.1767Iteration: 1637; Percent complete: 40.9%; Average loss: 3.4806Iteration: 1638; Percent complete: 40.9%; Average loss: 3.1302Iteration: 1639; Percent complete: 41.0%; Average loss: 3.4483Iteration: 1640; Percent complete: 41.0%; Average loss: 3.3039Iteration: 1641; Percent complete: 41.0%; Average loss: 3.1761Iteration: 1642; Percent complete: 41.0%; Average loss: 2.9534Iteration: 1643; Percent complete: 41.1%; Average loss: 3.2950Iteration: 1644; Percent complete: 41.1%; Average loss: 3.1773Iteration: 1645; Percent complete: 41.1%; Average loss: 3.1531Iteration: 1646; Percent complete: 41.1%; Average loss: 3.4275Iteration: 1647; Percent complete: 41.2%; Average loss: 3.1909Iteration: 1648; Percent complete: 41.2%; Average loss: 3.1847Iteration: 1649; Percent complete: 41.2%; Average loss: 3.3098Iteration: 1650; Percent complete: 41.2%; Average loss: 3.2036Iteration: 1651; Percent complete: 41.3%; Average loss: 3.2024Iteration: 1652; Percent complete: 41.3%; Average loss: 3.4103Iteration: 1653; Percent complete: 41.3%; Average loss: 3.3518Iteration: 1654; Percent complete: 41.3%; Average loss: 3.3332Iteration: 1655; Percent complete: 41.4%; Average loss: 3.3783Iteration: 1656; Percent complete: 41.4%; Average loss: 3.0748Iteration: 1657; Percent complete: 41.4%; Average loss: 3.4252Iteration: 1658; Percent complete: 41.4%; Average loss: 3.4047Iteration: 1659; Percent complete: 41.5%; Average loss: 3.2532Iteration: 1660; Percent complete: 41.5%; Average loss: 2.9858Iteration: 1661; Percent complete: 41.5%; Average loss: 3.1961Iteration: 1662; Percent complete: 41.5%; Average loss: 3.0404Iteration: 1663; Percent complete: 41.6%; Average loss: 3.1858Iteration: 1664; Percent complete: 41.6%; Average loss: 3.0455Iteration: 1665; Percent complete: 41.6%; Average loss: 3.3054Iteration: 1666; Percent complete: 41.6%; Average loss: 3.4189Iteration: 1667; Percent complete: 41.7%; Average loss: 3.2395Iteration: 1668; Percent complete: 41.7%; Average loss: 3.2149Iteration: 1669; Percent complete: 41.7%; Average loss: 3.4814Iteration: 1670; Percent complete: 41.8%; Average loss: 3.5856Iteration: 1671; Percent complete: 41.8%; Average loss: 3.0059Iteration: 1672; Percent complete: 41.8%; Average loss: 3.4912Iteration: 1673; Percent complete: 41.8%; Average loss: 3.0133Iteration: 1674; Percent complete: 41.9%; Average loss: 2.9582Iteration: 1675; Percent complete: 41.9%; Average loss: 3.2951Iteration: 1676; Percent complete: 41.9%; Average loss: 3.2150Iteration: 1677; Percent complete: 41.9%; Average loss: 3.4550Iteration: 1678; Percent complete: 41.9%; Average loss: 3.2926Iteration: 1679; Percent complete: 42.0%; Average loss: 3.1359Iteration: 1680; Percent complete: 42.0%; Average loss: 3.3243Iteration: 1681; Percent complete: 42.0%; Average loss: 3.2430Iteration: 1682; Percent complete: 42.0%; Average loss: 3.1797Iteration: 1683; Percent complete: 42.1%; Average loss: 3.2372Iteration: 1684; Percent complete: 42.1%; Average loss: 3.1638Iteration: 1685; Percent complete: 42.1%; Average loss: 3.4854Iteration: 1686; Percent complete: 42.1%; Average loss: 3.2980Iteration: 1687; Percent complete: 42.2%; Average loss: 3.2711Iteration: 1688; Percent complete: 42.2%; Average loss: 3.2887Iteration: 1689; Percent complete: 42.2%; Average loss: 3.3493Iteration: 1690; Percent complete: 42.2%; Average loss: 3.4426Iteration: 1691; Percent complete: 42.3%; Average loss: 3.4467Iteration: 1692; Percent complete: 42.3%; Average loss: 3.2744Iteration: 1693; Percent complete: 42.3%; Average loss: 3.3238Iteration: 1694; Percent complete: 42.4%; Average loss: 3.1018Iteration: 1695; Percent complete: 42.4%; Average loss: 2.9750Iteration: 1696; Percent complete: 42.4%; Average loss: 3.0012Iteration: 1697; Percent complete: 42.4%; Average loss: 3.2177Iteration: 1698; Percent complete: 42.4%; Average loss: 3.0507Iteration: 1699; Percent complete: 42.5%; Average loss: 3.0575Iteration: 1700; Percent complete: 42.5%; Average loss: 3.4129Iteration: 1701; Percent complete: 42.5%; Average loss: 3.4844Iteration: 1702; Percent complete: 42.5%; Average loss: 3.2915Iteration: 1703; Percent complete: 42.6%; Average loss: 3.2230Iteration: 1704; Percent complete: 42.6%; Average loss: 3.2781Iteration: 1705; Percent complete: 42.6%; Average loss: 3.5054Iteration: 1706; Percent complete: 42.6%; Average loss: 3.1932Iteration: 1707; Percent complete: 42.7%; Average loss: 3.1555Iteration: 1708; Percent complete: 42.7%; Average loss: 3.4297Iteration: 1709; Percent complete: 42.7%; Average loss: 3.3330Iteration: 1710; Percent complete: 42.8%; Average loss: 3.1169Iteration: 1711; Percent complete: 42.8%; Average loss: 3.0416Iteration: 1712; Percent complete: 42.8%; Average loss: 3.1648Iteration: 1713; Percent complete: 42.8%; Average loss: 3.6119Iteration: 1714; Percent complete: 42.9%; Average loss: 3.0394Iteration: 1715; Percent complete: 42.9%; Average loss: 2.8459Iteration: 1716; Percent complete: 42.9%; Average loss: 3.1285Iteration: 1717; Percent complete: 42.9%; Average loss: 3.0892Iteration: 1718; Percent complete: 43.0%; Average loss: 3.1653Iteration: 1719; Percent complete: 43.0%; Average loss: 3.2471Iteration: 1720; Percent complete: 43.0%; Average loss: 3.2612Iteration: 1721; Percent complete: 43.0%; Average loss: 3.1595Iteration: 1722; Percent complete: 43.0%; Average loss: 3.1835Iteration: 1723; Percent complete: 43.1%; Average loss: 3.1501Iteration: 1724; Percent complete: 43.1%; Average loss: 3.0192Iteration: 1725; Percent complete: 43.1%; Average loss: 3.0560Iteration: 1726; Percent complete: 43.1%; Average loss: 3.0870Iteration: 1727; Percent complete: 43.2%; Average loss: 3.0498Iteration: 1728; Percent complete: 43.2%; Average loss: 3.2723Iteration: 1729; Percent complete: 43.2%; Average loss: 3.2375Iteration: 1730; Percent complete: 43.2%; Average loss: 3.0313Iteration: 1731; Percent complete: 43.3%; Average loss: 3.3517Iteration: 1732; Percent complete: 43.3%; Average loss: 3.1731Iteration: 1733; Percent complete: 43.3%; Average loss: 3.4931Iteration: 1734; Percent complete: 43.4%; Average loss: 3.2560Iteration: 1735; Percent complete: 43.4%; Average loss: 3.1350Iteration: 1736; Percent complete: 43.4%; Average loss: 3.2859Iteration: 1737; Percent complete: 43.4%; Average loss: 3.4171Iteration: 1738; Percent complete: 43.5%; Average loss: 3.2572Iteration: 1739; Percent complete: 43.5%; Average loss: 3.3135Iteration: 1740; Percent complete: 43.5%; Average loss: 3.1880Iteration: 1741; Percent complete: 43.5%; Average loss: 3.2681Iteration: 1742; Percent complete: 43.5%; Average loss: 3.3647Iteration: 1743; Percent complete: 43.6%; Average loss: 3.3517Iteration: 1744; Percent complete: 43.6%; Average loss: 3.1158Iteration: 1745; Percent complete: 43.6%; Average loss: 3.3597Iteration: 1746; Percent complete: 43.6%; Average loss: 3.4773Iteration: 1747; Percent complete: 43.7%; Average loss: 2.9957Iteration: 1748; Percent complete: 43.7%; Average loss: 3.3100Iteration: 1749; Percent complete: 43.7%; Average loss: 3.2171Iteration: 1750; Percent complete: 43.8%; Average loss: 3.3651Iteration: 1751; Percent complete: 43.8%; Average loss: 3.2016Iteration: 1752; Percent complete: 43.8%; Average loss: 3.1385Iteration: 1753; Percent complete: 43.8%; Average loss: 3.2088Iteration: 1754; Percent complete: 43.9%; Average loss: 3.2972Iteration: 1755; Percent complete: 43.9%; Average loss: 3.2039Iteration: 1756; Percent complete: 43.9%; Average loss: 3.1759Iteration: 1757; Percent complete: 43.9%; Average loss: 2.8781Iteration: 1758; Percent complete: 44.0%; Average loss: 3.0313Iteration: 1759; Percent complete: 44.0%; Average loss: 3.1720Iteration: 1760; Percent complete: 44.0%; Average loss: 3.2865Iteration: 1761; Percent complete: 44.0%; Average loss: 2.9170Iteration: 1762; Percent complete: 44.0%; Average loss: 3.1968Iteration: 1763; Percent complete: 44.1%; Average loss: 3.2707Iteration: 1764; Percent complete: 44.1%; Average loss: 3.3670Iteration: 1765; Percent complete: 44.1%; Average loss: 3.0016Iteration: 1766; Percent complete: 44.1%; Average loss: 3.3048Iteration: 1767; Percent complete: 44.2%; Average loss: 3.2714Iteration: 1768; Percent complete: 44.2%; Average loss: 3.1444Iteration: 1769; Percent complete: 44.2%; Average loss: 3.2567Iteration: 1770; Percent complete: 44.2%; Average loss: 3.0407Iteration: 1771; Percent complete: 44.3%; Average loss: 3.2274Iteration: 1772; Percent complete: 44.3%; Average loss: 3.0692Iteration: 1773; Percent complete: 44.3%; Average loss: 3.3168Iteration: 1774; Percent complete: 44.4%; Average loss: 3.2587Iteration: 1775; Percent complete: 44.4%; Average loss: 3.3551Iteration: 1776; Percent complete: 44.4%; Average loss: 3.1867Iteration: 1777; Percent complete: 44.4%; Average loss: 3.1564Iteration: 1778; Percent complete: 44.5%; Average loss: 3.1960Iteration: 1779; Percent complete: 44.5%; Average loss: 2.9283Iteration: 1780; Percent complete: 44.5%; Average loss: 3.1984Iteration: 1781; Percent complete: 44.5%; Average loss: 3.3542Iteration: 1782; Percent complete: 44.5%; Average loss: 3.1883Iteration: 1783; Percent complete: 44.6%; Average loss: 3.2973Iteration: 1784; Percent complete: 44.6%; Average loss: 3.3233Iteration: 1785; Percent complete: 44.6%; Average loss: 3.4340Iteration: 1786; Percent complete: 44.6%; Average loss: 3.1468Iteration: 1787; Percent complete: 44.7%; Average loss: 3.2340Iteration: 1788; Percent complete: 44.7%; Average loss: 3.1868Iteration: 1789; Percent complete: 44.7%; Average loss: 2.9949Iteration: 1790; Percent complete: 44.8%; Average loss: 3.3989Iteration: 1791; Percent complete: 44.8%; Average loss: 2.9306Iteration: 1792; Percent complete: 44.8%; Average loss: 3.1442Iteration: 1793; Percent complete: 44.8%; Average loss: 3.2406Iteration: 1794; Percent complete: 44.9%; Average loss: 3.2007Iteration: 1795; Percent complete: 44.9%; Average loss: 3.2737Iteration: 1796; Percent complete: 44.9%; Average loss: 3.0523Iteration: 1797; Percent complete: 44.9%; Average loss: 2.9437Iteration: 1798; Percent complete: 45.0%; Average loss: 3.1589Iteration: 1799; Percent complete: 45.0%; Average loss: 3.2824Iteration: 1800; Percent complete: 45.0%; Average loss: 3.2014Iteration: 1801; Percent complete: 45.0%; Average loss: 3.1048Iteration: 1802; Percent complete: 45.1%; Average loss: 3.6083Iteration: 1803; Percent complete: 45.1%; Average loss: 3.2026Iteration: 1804; Percent complete: 45.1%; Average loss: 3.2305Iteration: 1805; Percent complete: 45.1%; Average loss: 3.1613Iteration: 1806; Percent complete: 45.1%; Average loss: 3.1896Iteration: 1807; Percent complete: 45.2%; Average loss: 3.0757Iteration: 1808; Percent complete: 45.2%; Average loss: 3.1177Iteration: 1809; Percent complete: 45.2%; Average loss: 2.9514Iteration: 1810; Percent complete: 45.2%; Average loss: 3.1082Iteration: 1811; Percent complete: 45.3%; Average loss: 3.5766Iteration: 1812; Percent complete: 45.3%; Average loss: 3.0796Iteration: 1813; Percent complete: 45.3%; Average loss: 3.1918Iteration: 1814; Percent complete: 45.4%; Average loss: 3.1492Iteration: 1815; Percent complete: 45.4%; Average loss: 3.0776Iteration: 1816; Percent complete: 45.4%; Average loss: 3.1357Iteration: 1817; Percent complete: 45.4%; Average loss: 3.2396Iteration: 1818; Percent complete: 45.5%; Average loss: 2.9571Iteration: 1819; Percent complete: 45.5%; Average loss: 3.2818Iteration: 1820; Percent complete: 45.5%; Average loss: 2.9988Iteration: 1821; Percent complete: 45.5%; Average loss: 3.3552Iteration: 1822; Percent complete: 45.6%; Average loss: 3.2129Iteration: 1823; Percent complete: 45.6%; Average loss: 3.1479Iteration: 1824; Percent complete: 45.6%; Average loss: 3.0510Iteration: 1825; Percent complete: 45.6%; Average loss: 3.2088Iteration: 1826; Percent complete: 45.6%; Average loss: 3.0501Iteration: 1827; Percent complete: 45.7%; Average loss: 3.0588Iteration: 1828; Percent complete: 45.7%; Average loss: 3.2093Iteration: 1829; Percent complete: 45.7%; Average loss: 3.2237Iteration: 1830; Percent complete: 45.8%; Average loss: 3.2353Iteration: 1831; Percent complete: 45.8%; Average loss: 3.1009Iteration: 1832; Percent complete: 45.8%; Average loss: 3.2094Iteration: 1833; Percent complete: 45.8%; Average loss: 3.3604Iteration: 1834; Percent complete: 45.9%; Average loss: 3.1964Iteration: 1835; Percent complete: 45.9%; Average loss: 3.0555Iteration: 1836; Percent complete: 45.9%; Average loss: 3.0616Iteration: 1837; Percent complete: 45.9%; Average loss: 3.2029Iteration: 1838; Percent complete: 46.0%; Average loss: 3.3174Iteration: 1839; Percent complete: 46.0%; Average loss: 3.1730Iteration: 1840; Percent complete: 46.0%; Average loss: 3.1068Iteration: 1841; Percent complete: 46.0%; Average loss: 3.2970Iteration: 1842; Percent complete: 46.1%; Average loss: 2.9600Iteration: 1843; Percent complete: 46.1%; Average loss: 3.0534Iteration: 1844; Percent complete: 46.1%; Average loss: 3.3637Iteration: 1845; Percent complete: 46.1%; Average loss: 3.1806Iteration: 1846; Percent complete: 46.2%; Average loss: 3.2643Iteration: 1847; Percent complete: 46.2%; Average loss: 3.4046Iteration: 1848; Percent complete: 46.2%; Average loss: 3.3849Iteration: 1849; Percent complete: 46.2%; Average loss: 3.1413Iteration: 1850; Percent complete: 46.2%; Average loss: 3.3806Iteration: 1851; Percent complete: 46.3%; Average loss: 3.2545Iteration: 1852; Percent complete: 46.3%; Average loss: 3.3541Iteration: 1853; Percent complete: 46.3%; Average loss: 3.3548Iteration: 1854; Percent complete: 46.4%; Average loss: 3.3045Iteration: 1855; Percent complete: 46.4%; Average loss: 3.1581Iteration: 1856; Percent complete: 46.4%; Average loss: 3.4239Iteration: 1857; Percent complete: 46.4%; Average loss: 3.3319Iteration: 1858; Percent complete: 46.5%; Average loss: 3.2225Iteration: 1859; Percent complete: 46.5%; Average loss: 2.9366Iteration: 1860; Percent complete: 46.5%; Average loss: 3.2228Iteration: 1861; Percent complete: 46.5%; Average loss: 3.1699Iteration: 1862; Percent complete: 46.6%; Average loss: 2.9754Iteration: 1863; Percent complete: 46.6%; Average loss: 3.1416Iteration: 1864; Percent complete: 46.6%; Average loss: 3.3355Iteration: 1865; Percent complete: 46.6%; Average loss: 3.0161Iteration: 1866; Percent complete: 46.7%; Average loss: 3.1410Iteration: 1867; Percent complete: 46.7%; Average loss: 3.2460Iteration: 1868; Percent complete: 46.7%; Average loss: 3.2015Iteration: 1869; Percent complete: 46.7%; Average loss: 3.4162Iteration: 1870; Percent complete: 46.8%; Average loss: 3.4329Iteration: 1871; Percent complete: 46.8%; Average loss: 3.1590Iteration: 1872; Percent complete: 46.8%; Average loss: 3.2059Iteration: 1873; Percent complete: 46.8%; Average loss: 3.0877Iteration: 1874; Percent complete: 46.9%; Average loss: 3.7065Iteration: 1875; Percent complete: 46.9%; Average loss: 3.3204Iteration: 1876; Percent complete: 46.9%; Average loss: 3.3781Iteration: 1877; Percent complete: 46.9%; Average loss: 3.1999Iteration: 1878; Percent complete: 46.9%; Average loss: 3.0446Iteration: 1879; Percent complete: 47.0%; Average loss: 3.2241Iteration: 1880; Percent complete: 47.0%; Average loss: 3.3362Iteration: 1881; Percent complete: 47.0%; Average loss: 3.3641Iteration: 1882; Percent complete: 47.0%; Average loss: 3.1912Iteration: 1883; Percent complete: 47.1%; Average loss: 3.1525Iteration: 1884; Percent complete: 47.1%; Average loss: 3.4459Iteration: 1885; Percent complete: 47.1%; Average loss: 2.9580Iteration: 1886; Percent complete: 47.1%; Average loss: 3.1937Iteration: 1887; Percent complete: 47.2%; Average loss: 3.2762Iteration: 1888; Percent complete: 47.2%; Average loss: 3.3791Iteration: 1889; Percent complete: 47.2%; Average loss: 3.3086Iteration: 1890; Percent complete: 47.2%; Average loss: 3.4766Iteration: 1891; Percent complete: 47.3%; Average loss: 3.5223Iteration: 1892; Percent complete: 47.3%; Average loss: 2.8884Iteration: 1893; Percent complete: 47.3%; Average loss: 3.0968Iteration: 1894; Percent complete: 47.3%; Average loss: 3.0655Iteration: 1895; Percent complete: 47.4%; Average loss: 3.4206Iteration: 1896; Percent complete: 47.4%; Average loss: 3.3129Iteration: 1897; Percent complete: 47.4%; Average loss: 3.2507Iteration: 1898; Percent complete: 47.4%; Average loss: 3.1265Iteration: 1899; Percent complete: 47.5%; Average loss: 3.1239Iteration: 1900; Percent complete: 47.5%; Average loss: 3.3559Iteration: 1901; Percent complete: 47.5%; Average loss: 2.9055Iteration: 1902; Percent complete: 47.5%; Average loss: 3.1725Iteration: 1903; Percent complete: 47.6%; Average loss: 3.1264Iteration: 1904; Percent complete: 47.6%; Average loss: 3.3116Iteration: 1905; Percent complete: 47.6%; Average loss: 3.0102Iteration: 1906; Percent complete: 47.6%; Average loss: 3.1450Iteration: 1907; Percent complete: 47.7%; Average loss: 3.2915Iteration: 1908; Percent complete: 47.7%; Average loss: 3.1987Iteration: 1909; Percent complete: 47.7%; Average loss: 3.1831Iteration: 1910; Percent complete: 47.8%; Average loss: 2.9137Iteration: 1911; Percent complete: 47.8%; Average loss: 3.2316Iteration: 1912; Percent complete: 47.8%; Average loss: 3.1149Iteration: 1913; Percent complete: 47.8%; Average loss: 3.1255Iteration: 1914; Percent complete: 47.9%; Average loss: 3.3119Iteration: 1915; Percent complete: 47.9%; Average loss: 2.9574Iteration: 1916; Percent complete: 47.9%; Average loss: 3.3265Iteration: 1917; Percent complete: 47.9%; Average loss: 3.0859Iteration: 1918; Percent complete: 47.9%; Average loss: 2.7510Iteration: 1919; Percent complete: 48.0%; Average loss: 3.0224Iteration: 1920; Percent complete: 48.0%; Average loss: 2.9392Iteration: 1921; Percent complete: 48.0%; Average loss: 3.1523Iteration: 1922; Percent complete: 48.0%; Average loss: 3.2717Iteration: 1923; Percent complete: 48.1%; Average loss: 3.0386Iteration: 1924; Percent complete: 48.1%; Average loss: 3.0570Iteration: 1925; Percent complete: 48.1%; Average loss: 2.9362Iteration: 1926; Percent complete: 48.1%; Average loss: 3.1960Iteration: 1927; Percent complete: 48.2%; Average loss: 3.0342Iteration: 1928; Percent complete: 48.2%; Average loss: 3.2440Iteration: 1929; Percent complete: 48.2%; Average loss: 3.1595Iteration: 1930; Percent complete: 48.2%; Average loss: 3.3408Iteration: 1931; Percent complete: 48.3%; Average loss: 3.1976Iteration: 1932; Percent complete: 48.3%; Average loss: 3.3860Iteration: 1933; Percent complete: 48.3%; Average loss: 3.0246Iteration: 1934; Percent complete: 48.4%; Average loss: 3.3184Iteration: 1935; Percent complete: 48.4%; Average loss: 3.3176Iteration: 1936; Percent complete: 48.4%; Average loss: 3.3086Iteration: 1937; Percent complete: 48.4%; Average loss: 3.3213Iteration: 1938; Percent complete: 48.4%; Average loss: 3.2714Iteration: 1939; Percent complete: 48.5%; Average loss: 3.1290Iteration: 1940; Percent complete: 48.5%; Average loss: 3.1532Iteration: 1941; Percent complete: 48.5%; Average loss: 3.2434Iteration: 1942; Percent complete: 48.5%; Average loss: 3.1102Iteration: 1943; Percent complete: 48.6%; Average loss: 3.0509Iteration: 1944; Percent complete: 48.6%; Average loss: 3.2823Iteration: 1945; Percent complete: 48.6%; Average loss: 3.0170Iteration: 1946; Percent complete: 48.6%; Average loss: 3.1839Iteration: 1947; Percent complete: 48.7%; Average loss: 3.0417Iteration: 1948; Percent complete: 48.7%; Average loss: 3.0507Iteration: 1949; Percent complete: 48.7%; Average loss: 3.2243Iteration: 1950; Percent complete: 48.8%; Average loss: 3.2711Iteration: 1951; Percent complete: 48.8%; Average loss: 2.9954Iteration: 1952; Percent complete: 48.8%; Average loss: 3.1221Iteration: 1953; Percent complete: 48.8%; Average loss: 3.0931Iteration: 1954; Percent complete: 48.9%; Average loss: 3.1806Iteration: 1955; Percent complete: 48.9%; Average loss: 3.2161Iteration: 1956; Percent complete: 48.9%; Average loss: 3.1012Iteration: 1957; Percent complete: 48.9%; Average loss: 3.3672Iteration: 1958; Percent complete: 48.9%; Average loss: 3.1304Iteration: 1959; Percent complete: 49.0%; Average loss: 3.2130Iteration: 1960; Percent complete: 49.0%; Average loss: 3.2077Iteration: 1961; Percent complete: 49.0%; Average loss: 3.3836Iteration: 1962; Percent complete: 49.0%; Average loss: 3.3141Iteration: 1963; Percent complete: 49.1%; Average loss: 3.3986Iteration: 1964; Percent complete: 49.1%; Average loss: 2.9934Iteration: 1965; Percent complete: 49.1%; Average loss: 3.0305Iteration: 1966; Percent complete: 49.1%; Average loss: 3.2129Iteration: 1967; Percent complete: 49.2%; Average loss: 3.2486Iteration: 1968; Percent complete: 49.2%; Average loss: 3.2679Iteration: 1969; Percent complete: 49.2%; Average loss: 3.0595Iteration: 1970; Percent complete: 49.2%; Average loss: 3.1609Iteration: 1971; Percent complete: 49.3%; Average loss: 3.0296Iteration: 1972; Percent complete: 49.3%; Average loss: 3.2570Iteration: 1973; Percent complete: 49.3%; Average loss: 3.1990Iteration: 1974; Percent complete: 49.4%; Average loss: 3.2579Iteration: 1975; Percent complete: 49.4%; Average loss: 3.1654Iteration: 1976; Percent complete: 49.4%; Average loss: 3.1044Iteration: 1977; Percent complete: 49.4%; Average loss: 3.1266Iteration: 1978; Percent complete: 49.5%; Average loss: 3.2581Iteration: 1979; Percent complete: 49.5%; Average loss: 3.0719Iteration: 1980; Percent complete: 49.5%; Average loss: 2.8921Iteration: 1981; Percent complete: 49.5%; Average loss: 3.4378Iteration: 1982; Percent complete: 49.5%; Average loss: 3.0629Iteration: 1983; Percent complete: 49.6%; Average loss: 3.1076Iteration: 1984; Percent complete: 49.6%; Average loss: 3.1432Iteration: 1985; Percent complete: 49.6%; Average loss: 3.3237Iteration: 1986; Percent complete: 49.6%; Average loss: 3.2793Iteration: 1987; Percent complete: 49.7%; Average loss: 3.3113Iteration: 1988; Percent complete: 49.7%; Average loss: 3.0005Iteration: 1989; Percent complete: 49.7%; Average loss: 3.1849Iteration: 1990; Percent complete: 49.8%; Average loss: 3.3377Iteration: 1991; Percent complete: 49.8%; Average loss: 3.0142Iteration: 1992; Percent complete: 49.8%; Average loss: 3.1064Iteration: 1993; Percent complete: 49.8%; Average loss: 3.2555Iteration: 1994; Percent complete: 49.9%; Average loss: 3.1999Iteration: 1995; Percent complete: 49.9%; Average loss: 3.1136Iteration: 1996; Percent complete: 49.9%; Average loss: 3.3391Iteration: 1997; Percent complete: 49.9%; Average loss: 3.1486Iteration: 1998; Percent complete: 50.0%; Average loss: 3.3442Iteration: 1999; Percent complete: 50.0%; Average loss: 3.2271Iteration: 2000; Percent complete: 50.0%; Average loss: 2.8477Iteration: 2001; Percent complete: 50.0%; Average loss: 3.0131Iteration: 2002; Percent complete: 50.0%; Average loss: 3.2004Iteration: 2003; Percent complete: 50.1%; Average loss: 3.0243Iteration: 2004; Percent complete: 50.1%; Average loss: 2.9715Iteration: 2005; Percent complete: 50.1%; Average loss: 2.9658Iteration: 2006; Percent complete: 50.1%; Average loss: 3.0886Iteration: 2007; Percent complete: 50.2%; Average loss: 3.2197Iteration: 2008; Percent complete: 50.2%; Average loss: 3.1178Iteration: 2009; Percent complete: 50.2%; Average loss: 3.2531Iteration: 2010; Percent complete: 50.2%; Average loss: 3.1746Iteration: 2011; Percent complete: 50.3%; Average loss: 3.2116Iteration: 2012; Percent complete: 50.3%; Average loss: 3.1443Iteration: 2013; Percent complete: 50.3%; Average loss: 3.1335Iteration: 2014; Percent complete: 50.3%; Average loss: 3.0665Iteration: 2015; Percent complete: 50.4%; Average loss: 3.1257Iteration: 2016; Percent complete: 50.4%; Average loss: 2.9231Iteration: 2017; Percent complete: 50.4%; Average loss: 3.2386Iteration: 2018; Percent complete: 50.4%; Average loss: 3.0411Iteration: 2019; Percent complete: 50.5%; Average loss: 2.9972Iteration: 2020; Percent complete: 50.5%; Average loss: 3.0263Iteration: 2021; Percent complete: 50.5%; Average loss: 3.3173Iteration: 2022; Percent complete: 50.5%; Average loss: 3.2521Iteration: 2023; Percent complete: 50.6%; Average loss: 3.0981Iteration: 2024; Percent complete: 50.6%; Average loss: 3.1722Iteration: 2025; Percent complete: 50.6%; Average loss: 3.4951Iteration: 2026; Percent complete: 50.6%; Average loss: 3.1812Iteration: 2027; Percent complete: 50.7%; Average loss: 3.1808Iteration: 2028; Percent complete: 50.7%; Average loss: 3.1328Iteration: 2029; Percent complete: 50.7%; Average loss: 2.9512Iteration: 2030; Percent complete: 50.7%; Average loss: 3.0232Iteration: 2031; Percent complete: 50.8%; Average loss: 2.9350Iteration: 2032; Percent complete: 50.8%; Average loss: 2.9674Iteration: 2033; Percent complete: 50.8%; Average loss: 3.1353Iteration: 2034; Percent complete: 50.8%; Average loss: 3.1544Iteration: 2035; Percent complete: 50.9%; Average loss: 3.1246Iteration: 2036; Percent complete: 50.9%; Average loss: 3.2434Iteration: 2037; Percent complete: 50.9%; Average loss: 3.4759Iteration: 2038; Percent complete: 50.9%; Average loss: 2.9599Iteration: 2039; Percent complete: 51.0%; Average loss: 3.3280Iteration: 2040; Percent complete: 51.0%; Average loss: 2.9560Iteration: 2041; Percent complete: 51.0%; Average loss: 3.0722Iteration: 2042; Percent complete: 51.0%; Average loss: 2.9234Iteration: 2043; Percent complete: 51.1%; Average loss: 3.0057Iteration: 2044; Percent complete: 51.1%; Average loss: 3.2317Iteration: 2045; Percent complete: 51.1%; Average loss: 3.1269Iteration: 2046; Percent complete: 51.1%; Average loss: 3.0111Iteration: 2047; Percent complete: 51.2%; Average loss: 3.0724Iteration: 2048; Percent complete: 51.2%; Average loss: 3.0016Iteration: 2049; Percent complete: 51.2%; Average loss: 2.9856Iteration: 2050; Percent complete: 51.2%; Average loss: 3.0785Iteration: 2051; Percent complete: 51.3%; Average loss: 3.2700Iteration: 2052; Percent complete: 51.3%; Average loss: 3.0418Iteration: 2053; Percent complete: 51.3%; Average loss: 3.0946Iteration: 2054; Percent complete: 51.3%; Average loss: 2.9603Iteration: 2055; Percent complete: 51.4%; Average loss: 3.0212Iteration: 2056; Percent complete: 51.4%; Average loss: 3.0736Iteration: 2057; Percent complete: 51.4%; Average loss: 3.2463Iteration: 2058; Percent complete: 51.4%; Average loss: 3.1418Iteration: 2059; Percent complete: 51.5%; Average loss: 3.2419Iteration: 2060; Percent complete: 51.5%; Average loss: 2.9515Iteration: 2061; Percent complete: 51.5%; Average loss: 3.2214Iteration: 2062; Percent complete: 51.5%; Average loss: 3.1913Iteration: 2063; Percent complete: 51.6%; Average loss: 3.2262Iteration: 2064; Percent complete: 51.6%; Average loss: 3.2009Iteration: 2065; Percent complete: 51.6%; Average loss: 2.9670Iteration: 2066; Percent complete: 51.6%; Average loss: 3.1198Iteration: 2067; Percent complete: 51.7%; Average loss: 3.1346Iteration: 2068; Percent complete: 51.7%; Average loss: 2.9746Iteration: 2069; Percent complete: 51.7%; Average loss: 3.3173Iteration: 2070; Percent complete: 51.7%; Average loss: 3.1461Iteration: 2071; Percent complete: 51.8%; Average loss: 3.2017Iteration: 2072; Percent complete: 51.8%; Average loss: 3.0638Iteration: 2073; Percent complete: 51.8%; Average loss: 3.1416Iteration: 2074; Percent complete: 51.8%; Average loss: 3.2515Iteration: 2075; Percent complete: 51.9%; Average loss: 3.1850Iteration: 2076; Percent complete: 51.9%; Average loss: 3.0228Iteration: 2077; Percent complete: 51.9%; Average loss: 3.1631Iteration: 2078; Percent complete: 51.9%; Average loss: 2.9616Iteration: 2079; Percent complete: 52.0%; Average loss: 3.2735Iteration: 2080; Percent complete: 52.0%; Average loss: 3.0323Iteration: 2081; Percent complete: 52.0%; Average loss: 3.2751Iteration: 2082; Percent complete: 52.0%; Average loss: 3.2617Iteration: 2083; Percent complete: 52.1%; Average loss: 3.2035Iteration: 2084; Percent complete: 52.1%; Average loss: 3.0756Iteration: 2085; Percent complete: 52.1%; Average loss: 2.8496Iteration: 2086; Percent complete: 52.1%; Average loss: 3.0616Iteration: 2087; Percent complete: 52.2%; Average loss: 3.1525Iteration: 2088; Percent complete: 52.2%; Average loss: 3.2151Iteration: 2089; Percent complete: 52.2%; Average loss: 2.9627Iteration: 2090; Percent complete: 52.2%; Average loss: 3.4131Iteration: 2091; Percent complete: 52.3%; Average loss: 3.0612Iteration: 2092; Percent complete: 52.3%; Average loss: 3.0928Iteration: 2093; Percent complete: 52.3%; Average loss: 3.4241Iteration: 2094; Percent complete: 52.3%; Average loss: 2.8225Iteration: 2095; Percent complete: 52.4%; Average loss: 3.2122Iteration: 2096; Percent complete: 52.4%; Average loss: 3.0447Iteration: 2097; Percent complete: 52.4%; Average loss: 3.1840Iteration: 2098; Percent complete: 52.4%; Average loss: 2.9481Iteration: 2099; Percent complete: 52.5%; Average loss: 2.9055Iteration: 2100; Percent complete: 52.5%; Average loss: 3.2678Iteration: 2101; Percent complete: 52.5%; Average loss: 3.1254Iteration: 2102; Percent complete: 52.5%; Average loss: 2.9121Iteration: 2103; Percent complete: 52.6%; Average loss: 3.1531Iteration: 2104; Percent complete: 52.6%; Average loss: 3.0678Iteration: 2105; Percent complete: 52.6%; Average loss: 3.1461Iteration: 2106; Percent complete: 52.6%; Average loss: 3.1779Iteration: 2107; Percent complete: 52.7%; Average loss: 3.2032Iteration: 2108; Percent complete: 52.7%; Average loss: 3.1192Iteration: 2109; Percent complete: 52.7%; Average loss: 3.1919Iteration: 2110; Percent complete: 52.8%; Average loss: 3.0435Iteration: 2111; Percent complete: 52.8%; Average loss: 3.2328Iteration: 2112; Percent complete: 52.8%; Average loss: 3.2456Iteration: 2113; Percent complete: 52.8%; Average loss: 3.0699Iteration: 2114; Percent complete: 52.8%; Average loss: 2.9058Iteration: 2115; Percent complete: 52.9%; Average loss: 3.1366Iteration: 2116; Percent complete: 52.9%; Average loss: 3.2177Iteration: 2117; Percent complete: 52.9%; Average loss: 3.0965Iteration: 2118; Percent complete: 52.9%; Average loss: 2.9977Iteration: 2119; Percent complete: 53.0%; Average loss: 3.0654Iteration: 2120; Percent complete: 53.0%; Average loss: 3.1072Iteration: 2121; Percent complete: 53.0%; Average loss: 2.9501Iteration: 2122; Percent complete: 53.0%; Average loss: 3.3006Iteration: 2123; Percent complete: 53.1%; Average loss: 3.1228Iteration: 2124; Percent complete: 53.1%; Average loss: 3.3356Iteration: 2125; Percent complete: 53.1%; Average loss: 3.1462Iteration: 2126; Percent complete: 53.1%; Average loss: 3.1353Iteration: 2127; Percent complete: 53.2%; Average loss: 3.2856Iteration: 2128; Percent complete: 53.2%; Average loss: 2.9857Iteration: 2129; Percent complete: 53.2%; Average loss: 2.9858Iteration: 2130; Percent complete: 53.2%; Average loss: 3.0336Iteration: 2131; Percent complete: 53.3%; Average loss: 3.1602Iteration: 2132; Percent complete: 53.3%; Average loss: 2.9517Iteration: 2133; Percent complete: 53.3%; Average loss: 3.0235Iteration: 2134; Percent complete: 53.3%; Average loss: 3.0864Iteration: 2135; Percent complete: 53.4%; Average loss: 2.9890Iteration: 2136; Percent complete: 53.4%; Average loss: 2.9550Iteration: 2137; Percent complete: 53.4%; Average loss: 3.1047Iteration: 2138; Percent complete: 53.4%; Average loss: 3.2303Iteration: 2139; Percent complete: 53.5%; Average loss: 3.1845Iteration: 2140; Percent complete: 53.5%; Average loss: 3.1575Iteration: 2141; Percent complete: 53.5%; Average loss: 2.8449Iteration: 2142; Percent complete: 53.5%; Average loss: 3.1063Iteration: 2143; Percent complete: 53.6%; Average loss: 3.0196Iteration: 2144; Percent complete: 53.6%; Average loss: 3.2437Iteration: 2145; Percent complete: 53.6%; Average loss: 3.0012Iteration: 2146; Percent complete: 53.6%; Average loss: 2.9687Iteration: 2147; Percent complete: 53.7%; Average loss: 3.2898Iteration: 2148; Percent complete: 53.7%; Average loss: 3.1743Iteration: 2149; Percent complete: 53.7%; Average loss: 3.1343Iteration: 2150; Percent complete: 53.8%; Average loss: 3.1880Iteration: 2151; Percent complete: 53.8%; Average loss: 3.0406Iteration: 2152; Percent complete: 53.8%; Average loss: 3.1257Iteration: 2153; Percent complete: 53.8%; Average loss: 3.2817Iteration: 2154; Percent complete: 53.8%; Average loss: 2.9455Iteration: 2155; Percent complete: 53.9%; Average loss: 2.9255Iteration: 2156; Percent complete: 53.9%; Average loss: 3.1944Iteration: 2157; Percent complete: 53.9%; Average loss: 3.2152Iteration: 2158; Percent complete: 53.9%; Average loss: 3.0952Iteration: 2159; Percent complete: 54.0%; Average loss: 3.3671Iteration: 2160; Percent complete: 54.0%; Average loss: 3.0827Iteration: 2161; Percent complete: 54.0%; Average loss: 2.8667Iteration: 2162; Percent complete: 54.0%; Average loss: 2.9982Iteration: 2163; Percent complete: 54.1%; Average loss: 2.9980Iteration: 2164; Percent complete: 54.1%; Average loss: 3.2749Iteration: 2165; Percent complete: 54.1%; Average loss: 3.3642Iteration: 2166; Percent complete: 54.1%; Average loss: 2.7825Iteration: 2167; Percent complete: 54.2%; Average loss: 3.0195Iteration: 2168; Percent complete: 54.2%; Average loss: 3.0523Iteration: 2169; Percent complete: 54.2%; Average loss: 2.9601Iteration: 2170; Percent complete: 54.2%; Average loss: 2.9987Iteration: 2171; Percent complete: 54.3%; Average loss: 2.8599Iteration: 2172; Percent complete: 54.3%; Average loss: 3.1722Iteration: 2173; Percent complete: 54.3%; Average loss: 3.1202Iteration: 2174; Percent complete: 54.4%; Average loss: 3.1573Iteration: 2175; Percent complete: 54.4%; Average loss: 2.9234Iteration: 2176; Percent complete: 54.4%; Average loss: 3.1321Iteration: 2177; Percent complete: 54.4%; Average loss: 3.0327Iteration: 2178; Percent complete: 54.4%; Average loss: 3.1415Iteration: 2179; Percent complete: 54.5%; Average loss: 3.0556Iteration: 2180; Percent complete: 54.5%; Average loss: 3.0637Iteration: 2181; Percent complete: 54.5%; Average loss: 3.2604Iteration: 2182; Percent complete: 54.5%; Average loss: 3.0376Iteration: 2183; Percent complete: 54.6%; Average loss: 3.0596Iteration: 2184; Percent complete: 54.6%; Average loss: 3.1040Iteration: 2185; Percent complete: 54.6%; Average loss: 3.2931Iteration: 2186; Percent complete: 54.6%; Average loss: 3.1831Iteration: 2187; Percent complete: 54.7%; Average loss: 3.1947Iteration: 2188; Percent complete: 54.7%; Average loss: 3.0647Iteration: 2189; Percent complete: 54.7%; Average loss: 2.9993Iteration: 2190; Percent complete: 54.8%; Average loss: 3.0445Iteration: 2191; Percent complete: 54.8%; Average loss: 3.0619Iteration: 2192; Percent complete: 54.8%; Average loss: 3.0395Iteration: 2193; Percent complete: 54.8%; Average loss: 2.8772Iteration: 2194; Percent complete: 54.9%; Average loss: 3.0691Iteration: 2195; Percent complete: 54.9%; Average loss: 2.9741Iteration: 2196; Percent complete: 54.9%; Average loss: 3.2455Iteration: 2197; Percent complete: 54.9%; Average loss: 3.0136Iteration: 2198; Percent complete: 54.9%; Average loss: 3.0117Iteration: 2199; Percent complete: 55.0%; Average loss: 3.0718Iteration: 2200; Percent complete: 55.0%; Average loss: 2.9256Iteration: 2201; Percent complete: 55.0%; Average loss: 3.1930Iteration: 2202; Percent complete: 55.0%; Average loss: 3.1227Iteration: 2203; Percent complete: 55.1%; Average loss: 2.9515Iteration: 2204; Percent complete: 55.1%; Average loss: 3.0635Iteration: 2205; Percent complete: 55.1%; Average loss: 2.9964Iteration: 2206; Percent complete: 55.1%; Average loss: 3.1216Iteration: 2207; Percent complete: 55.2%; Average loss: 3.1465Iteration: 2208; Percent complete: 55.2%; Average loss: 3.2126Iteration: 2209; Percent complete: 55.2%; Average loss: 3.2875Iteration: 2210; Percent complete: 55.2%; Average loss: 3.0844Iteration: 2211; Percent complete: 55.3%; Average loss: 3.1798Iteration: 2212; Percent complete: 55.3%; Average loss: 2.9799Iteration: 2213; Percent complete: 55.3%; Average loss: 2.7945Iteration: 2214; Percent complete: 55.4%; Average loss: 3.3221Iteration: 2215; Percent complete: 55.4%; Average loss: 3.3011Iteration: 2216; Percent complete: 55.4%; Average loss: 3.2008Iteration: 2217; Percent complete: 55.4%; Average loss: 2.9908Iteration: 2218; Percent complete: 55.5%; Average loss: 3.0786Iteration: 2219; Percent complete: 55.5%; Average loss: 3.1238Iteration: 2220; Percent complete: 55.5%; Average loss: 3.1081Iteration: 2221; Percent complete: 55.5%; Average loss: 3.1500Iteration: 2222; Percent complete: 55.5%; Average loss: 3.3150Iteration: 2223; Percent complete: 55.6%; Average loss: 3.2887Iteration: 2224; Percent complete: 55.6%; Average loss: 3.1839Iteration: 2225; Percent complete: 55.6%; Average loss: 3.1687Iteration: 2226; Percent complete: 55.6%; Average loss: 2.9688Iteration: 2227; Percent complete: 55.7%; Average loss: 3.0184Iteration: 2228; Percent complete: 55.7%; Average loss: 2.9103Iteration: 2229; Percent complete: 55.7%; Average loss: 3.0270Iteration: 2230; Percent complete: 55.8%; Average loss: 3.1199Iteration: 2231; Percent complete: 55.8%; Average loss: 3.0559Iteration: 2232; Percent complete: 55.8%; Average loss: 3.1788Iteration: 2233; Percent complete: 55.8%; Average loss: 2.8440Iteration: 2234; Percent complete: 55.9%; Average loss: 2.9088Iteration: 2235; Percent complete: 55.9%; Average loss: 3.2656Iteration: 2236; Percent complete: 55.9%; Average loss: 3.0030Iteration: 2237; Percent complete: 55.9%; Average loss: 3.0536Iteration: 2238; Percent complete: 56.0%; Average loss: 3.0435Iteration: 2239; Percent complete: 56.0%; Average loss: 2.7870Iteration: 2240; Percent complete: 56.0%; Average loss: 3.2788Iteration: 2241; Percent complete: 56.0%; Average loss: 3.2890Iteration: 2242; Percent complete: 56.0%; Average loss: 2.8888Iteration: 2243; Percent complete: 56.1%; Average loss: 2.9175Iteration: 2244; Percent complete: 56.1%; Average loss: 3.1952Iteration: 2245; Percent complete: 56.1%; Average loss: 2.9839Iteration: 2246; Percent complete: 56.1%; Average loss: 3.4289Iteration: 2247; Percent complete: 56.2%; Average loss: 3.2162Iteration: 2248; Percent complete: 56.2%; Average loss: 3.1567Iteration: 2249; Percent complete: 56.2%; Average loss: 2.9321Iteration: 2250; Percent complete: 56.2%; Average loss: 3.1001Iteration: 2251; Percent complete: 56.3%; Average loss: 3.0603Iteration: 2252; Percent complete: 56.3%; Average loss: 3.4013Iteration: 2253; Percent complete: 56.3%; Average loss: 2.7202Iteration: 2254; Percent complete: 56.4%; Average loss: 2.9781Iteration: 2255; Percent complete: 56.4%; Average loss: 3.0727Iteration: 2256; Percent complete: 56.4%; Average loss: 3.2855Iteration: 2257; Percent complete: 56.4%; Average loss: 3.3998Iteration: 2258; Percent complete: 56.5%; Average loss: 3.0182Iteration: 2259; Percent complete: 56.5%; Average loss: 3.1793Iteration: 2260; Percent complete: 56.5%; Average loss: 3.0053Iteration: 2261; Percent complete: 56.5%; Average loss: 3.0199Iteration: 2262; Percent complete: 56.5%; Average loss: 3.0859Iteration: 2263; Percent complete: 56.6%; Average loss: 3.2096Iteration: 2264; Percent complete: 56.6%; Average loss: 3.0063Iteration: 2265; Percent complete: 56.6%; Average loss: 3.1188Iteration: 2266; Percent complete: 56.6%; Average loss: 3.0367Iteration: 2267; Percent complete: 56.7%; Average loss: 3.0119Iteration: 2268; Percent complete: 56.7%; Average loss: 3.0814Iteration: 2269; Percent complete: 56.7%; Average loss: 3.1761Iteration: 2270; Percent complete: 56.8%; Average loss: 3.2947Iteration: 2271; Percent complete: 56.8%; Average loss: 2.9422Iteration: 2272; Percent complete: 56.8%; Average loss: 2.9443Iteration: 2273; Percent complete: 56.8%; Average loss: 3.0588Iteration: 2274; Percent complete: 56.9%; Average loss: 3.0338Iteration: 2275; Percent complete: 56.9%; Average loss: 3.0740Iteration: 2276; Percent complete: 56.9%; Average loss: 3.0609Iteration: 2277; Percent complete: 56.9%; Average loss: 3.1834Iteration: 2278; Percent complete: 57.0%; Average loss: 3.0642Iteration: 2279; Percent complete: 57.0%; Average loss: 3.1648Iteration: 2280; Percent complete: 57.0%; Average loss: 3.0938Iteration: 2281; Percent complete: 57.0%; Average loss: 3.0913Iteration: 2282; Percent complete: 57.0%; Average loss: 3.1526Iteration: 2283; Percent complete: 57.1%; Average loss: 3.0018Iteration: 2284; Percent complete: 57.1%; Average loss: 3.3101Iteration: 2285; Percent complete: 57.1%; Average loss: 3.0473Iteration: 2286; Percent complete: 57.1%; Average loss: 2.9327Iteration: 2287; Percent complete: 57.2%; Average loss: 3.1681Iteration: 2288; Percent complete: 57.2%; Average loss: 2.8754Iteration: 2289; Percent complete: 57.2%; Average loss: 2.8999Iteration: 2290; Percent complete: 57.2%; Average loss: 3.1187Iteration: 2291; Percent complete: 57.3%; Average loss: 3.3921Iteration: 2292; Percent complete: 57.3%; Average loss: 3.1144Iteration: 2293; Percent complete: 57.3%; Average loss: 3.1225Iteration: 2294; Percent complete: 57.4%; Average loss: 3.1615Iteration: 2295; Percent complete: 57.4%; Average loss: 3.1243Iteration: 2296; Percent complete: 57.4%; Average loss: 2.9496Iteration: 2297; Percent complete: 57.4%; Average loss: 2.9425Iteration: 2298; Percent complete: 57.5%; Average loss: 3.0164Iteration: 2299; Percent complete: 57.5%; Average loss: 3.3394Iteration: 2300; Percent complete: 57.5%; Average loss: 3.2158Iteration: 2301; Percent complete: 57.5%; Average loss: 2.9333Iteration: 2302; Percent complete: 57.6%; Average loss: 2.9420Iteration: 2303; Percent complete: 57.6%; Average loss: 3.0865Iteration: 2304; Percent complete: 57.6%; Average loss: 2.9205Iteration: 2305; Percent complete: 57.6%; Average loss: 2.9915Iteration: 2306; Percent complete: 57.6%; Average loss: 3.0182Iteration: 2307; Percent complete: 57.7%; Average loss: 3.0401Iteration: 2308; Percent complete: 57.7%; Average loss: 3.0760Iteration: 2309; Percent complete: 57.7%; Average loss: 2.9943Iteration: 2310; Percent complete: 57.8%; Average loss: 3.0269Iteration: 2311; Percent complete: 57.8%; Average loss: 3.1959Iteration: 2312; Percent complete: 57.8%; Average loss: 2.6817Iteration: 2313; Percent complete: 57.8%; Average loss: 3.1107Iteration: 2314; Percent complete: 57.9%; Average loss: 3.0756Iteration: 2315; Percent complete: 57.9%; Average loss: 3.1503Iteration: 2316; Percent complete: 57.9%; Average loss: 2.9428Iteration: 2317; Percent complete: 57.9%; Average loss: 3.1790Iteration: 2318; Percent complete: 58.0%; Average loss: 3.0392Iteration: 2319; Percent complete: 58.0%; Average loss: 2.8491Iteration: 2320; Percent complete: 58.0%; Average loss: 2.9298Iteration: 2321; Percent complete: 58.0%; Average loss: 3.0370Iteration: 2322; Percent complete: 58.1%; Average loss: 3.3107Iteration: 2323; Percent complete: 58.1%; Average loss: 2.8939Iteration: 2324; Percent complete: 58.1%; Average loss: 2.9256Iteration: 2325; Percent complete: 58.1%; Average loss: 3.1769Iteration: 2326; Percent complete: 58.1%; Average loss: 2.8282Iteration: 2327; Percent complete: 58.2%; Average loss: 3.0023Iteration: 2328; Percent complete: 58.2%; Average loss: 3.1176Iteration: 2329; Percent complete: 58.2%; Average loss: 2.9524Iteration: 2330; Percent complete: 58.2%; Average loss: 3.2931Iteration: 2331; Percent complete: 58.3%; Average loss: 2.9033Iteration: 2332; Percent complete: 58.3%; Average loss: 3.1855Iteration: 2333; Percent complete: 58.3%; Average loss: 3.2571Iteration: 2334; Percent complete: 58.4%; Average loss: 2.8068Iteration: 2335; Percent complete: 58.4%; Average loss: 2.8080Iteration: 2336; Percent complete: 58.4%; Average loss: 3.1426Iteration: 2337; Percent complete: 58.4%; Average loss: 3.1959Iteration: 2338; Percent complete: 58.5%; Average loss: 2.9326Iteration: 2339; Percent complete: 58.5%; Average loss: 3.0202Iteration: 2340; Percent complete: 58.5%; Average loss: 3.1399Iteration: 2341; Percent complete: 58.5%; Average loss: 3.1992Iteration: 2342; Percent complete: 58.6%; Average loss: 3.1730Iteration: 2343; Percent complete: 58.6%; Average loss: 2.9390Iteration: 2344; Percent complete: 58.6%; Average loss: 2.9086Iteration: 2345; Percent complete: 58.6%; Average loss: 3.0277Iteration: 2346; Percent complete: 58.7%; Average loss: 2.9323Iteration: 2347; Percent complete: 58.7%; Average loss: 3.3242Iteration: 2348; Percent complete: 58.7%; Average loss: 2.9875Iteration: 2349; Percent complete: 58.7%; Average loss: 2.8434Iteration: 2350; Percent complete: 58.8%; Average loss: 3.0609Iteration: 2351; Percent complete: 58.8%; Average loss: 2.9311Iteration: 2352; Percent complete: 58.8%; Average loss: 3.1988Iteration: 2353; Percent complete: 58.8%; Average loss: 3.0857Iteration: 2354; Percent complete: 58.9%; Average loss: 2.8889Iteration: 2355; Percent complete: 58.9%; Average loss: 3.1677Iteration: 2356; Percent complete: 58.9%; Average loss: 2.9062Iteration: 2357; Percent complete: 58.9%; Average loss: 3.2199Iteration: 2358; Percent complete: 59.0%; Average loss: 3.0683Iteration: 2359; Percent complete: 59.0%; Average loss: 3.0646Iteration: 2360; Percent complete: 59.0%; Average loss: 3.1089Iteration: 2361; Percent complete: 59.0%; Average loss: 2.9415Iteration: 2362; Percent complete: 59.1%; Average loss: 3.4124Iteration: 2363; Percent complete: 59.1%; Average loss: 3.1921Iteration: 2364; Percent complete: 59.1%; Average loss: 2.9182Iteration: 2365; Percent complete: 59.1%; Average loss: 3.0457Iteration: 2366; Percent complete: 59.2%; Average loss: 3.1623Iteration: 2367; Percent complete: 59.2%; Average loss: 3.0460Iteration: 2368; Percent complete: 59.2%; Average loss: 2.8285Iteration: 2369; Percent complete: 59.2%; Average loss: 3.0307Iteration: 2370; Percent complete: 59.2%; Average loss: 3.1381Iteration: 2371; Percent complete: 59.3%; Average loss: 2.8734Iteration: 2372; Percent complete: 59.3%; Average loss: 3.0924Iteration: 2373; Percent complete: 59.3%; Average loss: 3.0230Iteration: 2374; Percent complete: 59.4%; Average loss: 3.4407Iteration: 2375; Percent complete: 59.4%; Average loss: 3.1558Iteration: 2376; Percent complete: 59.4%; Average loss: 2.9559Iteration: 2377; Percent complete: 59.4%; Average loss: 3.0942Iteration: 2378; Percent complete: 59.5%; Average loss: 3.2425Iteration: 2379; Percent complete: 59.5%; Average loss: 2.8669Iteration: 2380; Percent complete: 59.5%; Average loss: 3.1167Iteration: 2381; Percent complete: 59.5%; Average loss: 2.7892Iteration: 2382; Percent complete: 59.6%; Average loss: 2.9135Iteration: 2383; Percent complete: 59.6%; Average loss: 3.0676Iteration: 2384; Percent complete: 59.6%; Average loss: 2.8829Iteration: 2385; Percent complete: 59.6%; Average loss: 3.1322Iteration: 2386; Percent complete: 59.7%; Average loss: 2.8022Iteration: 2387; Percent complete: 59.7%; Average loss: 2.7995Iteration: 2388; Percent complete: 59.7%; Average loss: 3.1133Iteration: 2389; Percent complete: 59.7%; Average loss: 3.0652Iteration: 2390; Percent complete: 59.8%; Average loss: 3.2591Iteration: 2391; Percent complete: 59.8%; Average loss: 3.0339Iteration: 2392; Percent complete: 59.8%; Average loss: 3.0619Iteration: 2393; Percent complete: 59.8%; Average loss: 3.0511Iteration: 2394; Percent complete: 59.9%; Average loss: 2.9348Iteration: 2395; Percent complete: 59.9%; Average loss: 3.0633Iteration: 2396; Percent complete: 59.9%; Average loss: 3.2155Iteration: 2397; Percent complete: 59.9%; Average loss: 2.9817Iteration: 2398; Percent complete: 60.0%; Average loss: 2.9081Iteration: 2399; Percent complete: 60.0%; Average loss: 2.9447Iteration: 2400; Percent complete: 60.0%; Average loss: 3.1198Iteration: 2401; Percent complete: 60.0%; Average loss: 2.5753Iteration: 2402; Percent complete: 60.1%; Average loss: 2.8686Iteration: 2403; Percent complete: 60.1%; Average loss: 3.0220Iteration: 2404; Percent complete: 60.1%; Average loss: 2.8802Iteration: 2405; Percent complete: 60.1%; Average loss: 3.1751Iteration: 2406; Percent complete: 60.2%; Average loss: 3.3396Iteration: 2407; Percent complete: 60.2%; Average loss: 2.9510Iteration: 2408; Percent complete: 60.2%; Average loss: 3.1279Iteration: 2409; Percent complete: 60.2%; Average loss: 3.0807Iteration: 2410; Percent complete: 60.2%; Average loss: 2.8878Iteration: 2411; Percent complete: 60.3%; Average loss: 3.1810Iteration: 2412; Percent complete: 60.3%; Average loss: 3.0701Iteration: 2413; Percent complete: 60.3%; Average loss: 3.0911Iteration: 2414; Percent complete: 60.4%; Average loss: 2.9597Iteration: 2415; Percent complete: 60.4%; Average loss: 3.0980Iteration: 2416; Percent complete: 60.4%; Average loss: 2.7482Iteration: 2417; Percent complete: 60.4%; Average loss: 2.9337Iteration: 2418; Percent complete: 60.5%; Average loss: 2.9410Iteration: 2419; Percent complete: 60.5%; Average loss: 2.9243Iteration: 2420; Percent complete: 60.5%; Average loss: 2.9420Iteration: 2421; Percent complete: 60.5%; Average loss: 3.1218Iteration: 2422; Percent complete: 60.6%; Average loss: 3.0947Iteration: 2423; Percent complete: 60.6%; Average loss: 2.8317Iteration: 2424; Percent complete: 60.6%; Average loss: 2.9403Iteration: 2425; Percent complete: 60.6%; Average loss: 3.0772Iteration: 2426; Percent complete: 60.7%; Average loss: 2.7146Iteration: 2427; Percent complete: 60.7%; Average loss: 3.0969Iteration: 2428; Percent complete: 60.7%; Average loss: 3.3522Iteration: 2429; Percent complete: 60.7%; Average loss: 3.0099Iteration: 2430; Percent complete: 60.8%; Average loss: 2.7203Iteration: 2431; Percent complete: 60.8%; Average loss: 3.2027Iteration: 2432; Percent complete: 60.8%; Average loss: 3.1164Iteration: 2433; Percent complete: 60.8%; Average loss: 3.2563Iteration: 2434; Percent complete: 60.9%; Average loss: 2.9220Iteration: 2435; Percent complete: 60.9%; Average loss: 3.1470Iteration: 2436; Percent complete: 60.9%; Average loss: 2.8882Iteration: 2437; Percent complete: 60.9%; Average loss: 2.9847Iteration: 2438; Percent complete: 61.0%; Average loss: 3.0069Iteration: 2439; Percent complete: 61.0%; Average loss: 2.8875Iteration: 2440; Percent complete: 61.0%; Average loss: 2.8405Iteration: 2441; Percent complete: 61.0%; Average loss: 3.1002Iteration: 2442; Percent complete: 61.1%; Average loss: 3.0625Iteration: 2443; Percent complete: 61.1%; Average loss: 3.1600Iteration: 2444; Percent complete: 61.1%; Average loss: 2.9541Iteration: 2445; Percent complete: 61.1%; Average loss: 2.9507Iteration: 2446; Percent complete: 61.2%; Average loss: 2.9191Iteration: 2447; Percent complete: 61.2%; Average loss: 3.1006Iteration: 2448; Percent complete: 61.2%; Average loss: 2.9962Iteration: 2449; Percent complete: 61.2%; Average loss: 3.0592Iteration: 2450; Percent complete: 61.3%; Average loss: 2.9469Iteration: 2451; Percent complete: 61.3%; Average loss: 2.7421Iteration: 2452; Percent complete: 61.3%; Average loss: 3.3498Iteration: 2453; Percent complete: 61.3%; Average loss: 3.1890Iteration: 2454; Percent complete: 61.4%; Average loss: 2.9104Iteration: 2455; Percent complete: 61.4%; Average loss: 3.1513Iteration: 2456; Percent complete: 61.4%; Average loss: 2.9640Iteration: 2457; Percent complete: 61.4%; Average loss: 2.8352Iteration: 2458; Percent complete: 61.5%; Average loss: 2.8200Iteration: 2459; Percent complete: 61.5%; Average loss: 2.9300Iteration: 2460; Percent complete: 61.5%; Average loss: 2.9987Iteration: 2461; Percent complete: 61.5%; Average loss: 3.0879Iteration: 2462; Percent complete: 61.6%; Average loss: 3.0989Iteration: 2463; Percent complete: 61.6%; Average loss: 3.0788Iteration: 2464; Percent complete: 61.6%; Average loss: 3.0331Iteration: 2465; Percent complete: 61.6%; Average loss: 3.0212Iteration: 2466; Percent complete: 61.7%; Average loss: 2.8171Iteration: 2467; Percent complete: 61.7%; Average loss: 2.9717Iteration: 2468; Percent complete: 61.7%; Average loss: 3.1028Iteration: 2469; Percent complete: 61.7%; Average loss: 3.0144Iteration: 2470; Percent complete: 61.8%; Average loss: 3.1387Iteration: 2471; Percent complete: 61.8%; Average loss: 3.2257Iteration: 2472; Percent complete: 61.8%; Average loss: 3.0410Iteration: 2473; Percent complete: 61.8%; Average loss: 3.0210Iteration: 2474; Percent complete: 61.9%; Average loss: 2.8546Iteration: 2475; Percent complete: 61.9%; Average loss: 2.9583Iteration: 2476; Percent complete: 61.9%; Average loss: 3.1098Iteration: 2477; Percent complete: 61.9%; Average loss: 2.9360Iteration: 2478; Percent complete: 62.0%; Average loss: 2.7005Iteration: 2479; Percent complete: 62.0%; Average loss: 2.9524Iteration: 2480; Percent complete: 62.0%; Average loss: 2.7628Iteration: 2481; Percent complete: 62.0%; Average loss: 2.9820Iteration: 2482; Percent complete: 62.1%; Average loss: 2.9976Iteration: 2483; Percent complete: 62.1%; Average loss: 3.0076Iteration: 2484; Percent complete: 62.1%; Average loss: 2.8711Iteration: 2485; Percent complete: 62.1%; Average loss: 3.1683Iteration: 2486; Percent complete: 62.2%; Average loss: 2.8344Iteration: 2487; Percent complete: 62.2%; Average loss: 3.2452Iteration: 2488; Percent complete: 62.2%; Average loss: 2.8347Iteration: 2489; Percent complete: 62.2%; Average loss: 2.9476Iteration: 2490; Percent complete: 62.3%; Average loss: 2.8867Iteration: 2491; Percent complete: 62.3%; Average loss: 2.9338Iteration: 2492; Percent complete: 62.3%; Average loss: 3.1065Iteration: 2493; Percent complete: 62.3%; Average loss: 3.3605Iteration: 2494; Percent complete: 62.4%; Average loss: 3.1943Iteration: 2495; Percent complete: 62.4%; Average loss: 2.7444Iteration: 2496; Percent complete: 62.4%; Average loss: 2.9900Iteration: 2497; Percent complete: 62.4%; Average loss: 3.1096Iteration: 2498; Percent complete: 62.5%; Average loss: 2.8055Iteration: 2499; Percent complete: 62.5%; Average loss: 3.0107Iteration: 2500; Percent complete: 62.5%; Average loss: 3.3209Iteration: 2501; Percent complete: 62.5%; Average loss: 2.9224Iteration: 2502; Percent complete: 62.5%; Average loss: 3.1661Iteration: 2503; Percent complete: 62.6%; Average loss: 3.2153Iteration: 2504; Percent complete: 62.6%; Average loss: 2.9512Iteration: 2505; Percent complete: 62.6%; Average loss: 3.0929Iteration: 2506; Percent complete: 62.6%; Average loss: 2.9692Iteration: 2507; Percent complete: 62.7%; Average loss: 2.9623Iteration: 2508; Percent complete: 62.7%; Average loss: 2.8705Iteration: 2509; Percent complete: 62.7%; Average loss: 3.0200Iteration: 2510; Percent complete: 62.7%; Average loss: 3.2045Iteration: 2511; Percent complete: 62.8%; Average loss: 3.1089Iteration: 2512; Percent complete: 62.8%; Average loss: 2.9376Iteration: 2513; Percent complete: 62.8%; Average loss: 3.2245Iteration: 2514; Percent complete: 62.8%; Average loss: 2.8970Iteration: 2515; Percent complete: 62.9%; Average loss: 2.9406Iteration: 2516; Percent complete: 62.9%; Average loss: 3.1666Iteration: 2517; Percent complete: 62.9%; Average loss: 2.9772Iteration: 2518; Percent complete: 62.9%; Average loss: 3.2606Iteration: 2519; Percent complete: 63.0%; Average loss: 3.0074Iteration: 2520; Percent complete: 63.0%; Average loss: 2.8121Iteration: 2521; Percent complete: 63.0%; Average loss: 3.1088Iteration: 2522; Percent complete: 63.0%; Average loss: 3.1537Iteration: 2523; Percent complete: 63.1%; Average loss: 3.1598Iteration: 2524; Percent complete: 63.1%; Average loss: 3.0874Iteration: 2525; Percent complete: 63.1%; Average loss: 2.8295Iteration: 2526; Percent complete: 63.1%; Average loss: 3.2157Iteration: 2527; Percent complete: 63.2%; Average loss: 2.9623Iteration: 2528; Percent complete: 63.2%; Average loss: 3.0779Iteration: 2529; Percent complete: 63.2%; Average loss: 3.2013Iteration: 2530; Percent complete: 63.2%; Average loss: 3.0547Iteration: 2531; Percent complete: 63.3%; Average loss: 3.0858Iteration: 2532; Percent complete: 63.3%; Average loss: 2.8852Iteration: 2533; Percent complete: 63.3%; Average loss: 3.0678Iteration: 2534; Percent complete: 63.3%; Average loss: 3.2038Iteration: 2535; Percent complete: 63.4%; Average loss: 2.9399Iteration: 2536; Percent complete: 63.4%; Average loss: 3.1086Iteration: 2537; Percent complete: 63.4%; Average loss: 3.1169Iteration: 2538; Percent complete: 63.4%; Average loss: 3.0543Iteration: 2539; Percent complete: 63.5%; Average loss: 2.9218Iteration: 2540; Percent complete: 63.5%; Average loss: 2.7269Iteration: 2541; Percent complete: 63.5%; Average loss: 3.0568Iteration: 2542; Percent complete: 63.5%; Average loss: 2.8455Iteration: 2543; Percent complete: 63.6%; Average loss: 3.0106Iteration: 2544; Percent complete: 63.6%; Average loss: 2.8244Iteration: 2545; Percent complete: 63.6%; Average loss: 3.1182Iteration: 2546; Percent complete: 63.6%; Average loss: 2.8952Iteration: 2547; Percent complete: 63.7%; Average loss: 3.0327Iteration: 2548; Percent complete: 63.7%; Average loss: 3.0314Iteration: 2549; Percent complete: 63.7%; Average loss: 3.0534Iteration: 2550; Percent complete: 63.7%; Average loss: 3.0033Iteration: 2551; Percent complete: 63.8%; Average loss: 2.8908Iteration: 2552; Percent complete: 63.8%; Average loss: 3.0334Iteration: 2553; Percent complete: 63.8%; Average loss: 3.1038Iteration: 2554; Percent complete: 63.8%; Average loss: 3.1185Iteration: 2555; Percent complete: 63.9%; Average loss: 3.1513Iteration: 2556; Percent complete: 63.9%; Average loss: 2.8982Iteration: 2557; Percent complete: 63.9%; Average loss: 3.1666Iteration: 2558; Percent complete: 63.9%; Average loss: 3.0847Iteration: 2559; Percent complete: 64.0%; Average loss: 3.0358Iteration: 2560; Percent complete: 64.0%; Average loss: 2.7586Iteration: 2561; Percent complete: 64.0%; Average loss: 2.8892Iteration: 2562; Percent complete: 64.0%; Average loss: 3.0247Iteration: 2563; Percent complete: 64.1%; Average loss: 2.9731Iteration: 2564; Percent complete: 64.1%; Average loss: 3.0110Iteration: 2565; Percent complete: 64.1%; Average loss: 2.9414Iteration: 2566; Percent complete: 64.1%; Average loss: 2.9633Iteration: 2567; Percent complete: 64.2%; Average loss: 3.0625Iteration: 2568; Percent complete: 64.2%; Average loss: 3.3137Iteration: 2569; Percent complete: 64.2%; Average loss: 2.9020Iteration: 2570; Percent complete: 64.2%; Average loss: 3.0830Iteration: 2571; Percent complete: 64.3%; Average loss: 3.1259Iteration: 2572; Percent complete: 64.3%; Average loss: 2.7820Iteration: 2573; Percent complete: 64.3%; Average loss: 3.1764Iteration: 2574; Percent complete: 64.3%; Average loss: 3.0204Iteration: 2575; Percent complete: 64.4%; Average loss: 3.1588Iteration: 2576; Percent complete: 64.4%; Average loss: 3.0016Iteration: 2577; Percent complete: 64.4%; Average loss: 3.0537Iteration: 2578; Percent complete: 64.5%; Average loss: 2.8276Iteration: 2579; Percent complete: 64.5%; Average loss: 3.2948Iteration: 2580; Percent complete: 64.5%; Average loss: 2.6471Iteration: 2581; Percent complete: 64.5%; Average loss: 2.8602Iteration: 2582; Percent complete: 64.5%; Average loss: 2.9494Iteration: 2583; Percent complete: 64.6%; Average loss: 2.9586Iteration: 2584; Percent complete: 64.6%; Average loss: 3.1029Iteration: 2585; Percent complete: 64.6%; Average loss: 2.9954Iteration: 2586; Percent complete: 64.6%; Average loss: 2.6455Iteration: 2587; Percent complete: 64.7%; Average loss: 3.0910Iteration: 2588; Percent complete: 64.7%; Average loss: 2.8634Iteration: 2589; Percent complete: 64.7%; Average loss: 2.9244Iteration: 2590; Percent complete: 64.8%; Average loss: 3.2814Iteration: 2591; Percent complete: 64.8%; Average loss: 3.1109Iteration: 2592; Percent complete: 64.8%; Average loss: 2.9494Iteration: 2593; Percent complete: 64.8%; Average loss: 2.8289Iteration: 2594; Percent complete: 64.8%; Average loss: 3.1752Iteration: 2595; Percent complete: 64.9%; Average loss: 3.1870Iteration: 2596; Percent complete: 64.9%; Average loss: 3.0767Iteration: 2597; Percent complete: 64.9%; Average loss: 2.6923Iteration: 2598; Percent complete: 65.0%; Average loss: 3.1987Iteration: 2599; Percent complete: 65.0%; Average loss: 2.9336Iteration: 2600; Percent complete: 65.0%; Average loss: 2.9793Iteration: 2601; Percent complete: 65.0%; Average loss: 3.0989Iteration: 2602; Percent complete: 65.0%; Average loss: 3.0243Iteration: 2603; Percent complete: 65.1%; Average loss: 2.9633Iteration: 2604; Percent complete: 65.1%; Average loss: 3.0468Iteration: 2605; Percent complete: 65.1%; Average loss: 2.8972Iteration: 2606; Percent complete: 65.1%; Average loss: 3.1200Iteration: 2607; Percent complete: 65.2%; Average loss: 2.9260Iteration: 2608; Percent complete: 65.2%; Average loss: 2.9308Iteration: 2609; Percent complete: 65.2%; Average loss: 3.1065Iteration: 2610; Percent complete: 65.2%; Average loss: 3.1305Iteration: 2611; Percent complete: 65.3%; Average loss: 3.1361Iteration: 2612; Percent complete: 65.3%; Average loss: 3.0918Iteration: 2613; Percent complete: 65.3%; Average loss: 3.1053Iteration: 2614; Percent complete: 65.3%; Average loss: 2.8739Iteration: 2615; Percent complete: 65.4%; Average loss: 2.9586Iteration: 2616; Percent complete: 65.4%; Average loss: 2.9082Iteration: 2617; Percent complete: 65.4%; Average loss: 2.8821Iteration: 2618; Percent complete: 65.5%; Average loss: 3.0930Iteration: 2619; Percent complete: 65.5%; Average loss: 3.0873Iteration: 2620; Percent complete: 65.5%; Average loss: 3.1722Iteration: 2621; Percent complete: 65.5%; Average loss: 2.9083Iteration: 2622; Percent complete: 65.5%; Average loss: 3.1023Iteration: 2623; Percent complete: 65.6%; Average loss: 2.9911Iteration: 2624; Percent complete: 65.6%; Average loss: 3.1253Iteration: 2625; Percent complete: 65.6%; Average loss: 3.0089Iteration: 2626; Percent complete: 65.6%; Average loss: 2.9776Iteration: 2627; Percent complete: 65.7%; Average loss: 2.7549Iteration: 2628; Percent complete: 65.7%; Average loss: 3.1304Iteration: 2629; Percent complete: 65.7%; Average loss: 2.9702Iteration: 2630; Percent complete: 65.8%; Average loss: 2.9968Iteration: 2631; Percent complete: 65.8%; Average loss: 2.7960Iteration: 2632; Percent complete: 65.8%; Average loss: 3.0535Iteration: 2633; Percent complete: 65.8%; Average loss: 3.0695Iteration: 2634; Percent complete: 65.8%; Average loss: 3.0636Iteration: 2635; Percent complete: 65.9%; Average loss: 2.8301Iteration: 2636; Percent complete: 65.9%; Average loss: 2.8831Iteration: 2637; Percent complete: 65.9%; Average loss: 3.1080Iteration: 2638; Percent complete: 66.0%; Average loss: 2.8778Iteration: 2639; Percent complete: 66.0%; Average loss: 2.9142Iteration: 2640; Percent complete: 66.0%; Average loss: 2.7362Iteration: 2641; Percent complete: 66.0%; Average loss: 3.0816Iteration: 2642; Percent complete: 66.0%; Average loss: 3.1421Iteration: 2643; Percent complete: 66.1%; Average loss: 3.0466Iteration: 2644; Percent complete: 66.1%; Average loss: 3.0470Iteration: 2645; Percent complete: 66.1%; Average loss: 2.9286Iteration: 2646; Percent complete: 66.1%; Average loss: 2.8998Iteration: 2647; Percent complete: 66.2%; Average loss: 3.0333Iteration: 2648; Percent complete: 66.2%; Average loss: 3.0077Iteration: 2649; Percent complete: 66.2%; Average loss: 2.9256Iteration: 2650; Percent complete: 66.2%; Average loss: 3.0864Iteration: 2651; Percent complete: 66.3%; Average loss: 2.9425Iteration: 2652; Percent complete: 66.3%; Average loss: 2.8912Iteration: 2653; Percent complete: 66.3%; Average loss: 3.0589Iteration: 2654; Percent complete: 66.3%; Average loss: 3.0505Iteration: 2655; Percent complete: 66.4%; Average loss: 2.7716Iteration: 2656; Percent complete: 66.4%; Average loss: 2.6984Iteration: 2657; Percent complete: 66.4%; Average loss: 2.8399Iteration: 2658; Percent complete: 66.5%; Average loss: 3.0367Iteration: 2659; Percent complete: 66.5%; Average loss: 2.9540Iteration: 2660; Percent complete: 66.5%; Average loss: 2.7381Iteration: 2661; Percent complete: 66.5%; Average loss: 2.8457Iteration: 2662; Percent complete: 66.5%; Average loss: 2.7660Iteration: 2663; Percent complete: 66.6%; Average loss: 3.0593Iteration: 2664; Percent complete: 66.6%; Average loss: 3.2064Iteration: 2665; Percent complete: 66.6%; Average loss: 3.2220Iteration: 2666; Percent complete: 66.6%; Average loss: 3.1113Iteration: 2667; Percent complete: 66.7%; Average loss: 2.9029Iteration: 2668; Percent complete: 66.7%; Average loss: 2.7289Iteration: 2669; Percent complete: 66.7%; Average loss: 2.9706Iteration: 2670; Percent complete: 66.8%; Average loss: 2.7835Iteration: 2671; Percent complete: 66.8%; Average loss: 3.1147Iteration: 2672; Percent complete: 66.8%; Average loss: 3.1798Iteration: 2673; Percent complete: 66.8%; Average loss: 2.9992Iteration: 2674; Percent complete: 66.8%; Average loss: 2.8683Iteration: 2675; Percent complete: 66.9%; Average loss: 2.8396Iteration: 2676; Percent complete: 66.9%; Average loss: 2.8044Iteration: 2677; Percent complete: 66.9%; Average loss: 2.8206Iteration: 2678; Percent complete: 67.0%; Average loss: 2.9643Iteration: 2679; Percent complete: 67.0%; Average loss: 3.0132Iteration: 2680; Percent complete: 67.0%; Average loss: 2.9957Iteration: 2681; Percent complete: 67.0%; Average loss: 2.7519Iteration: 2682; Percent complete: 67.0%; Average loss: 2.9276Iteration: 2683; Percent complete: 67.1%; Average loss: 2.9201Iteration: 2684; Percent complete: 67.1%; Average loss: 2.9693Iteration: 2685; Percent complete: 67.1%; Average loss: 2.8700Iteration: 2686; Percent complete: 67.2%; Average loss: 3.0122Iteration: 2687; Percent complete: 67.2%; Average loss: 3.0424Iteration: 2688; Percent complete: 67.2%; Average loss: 3.0147Iteration: 2689; Percent complete: 67.2%; Average loss: 3.0480Iteration: 2690; Percent complete: 67.2%; Average loss: 2.9874Iteration: 2691; Percent complete: 67.3%; Average loss: 3.1045Iteration: 2692; Percent complete: 67.3%; Average loss: 2.8287Iteration: 2693; Percent complete: 67.3%; Average loss: 2.9505Iteration: 2694; Percent complete: 67.3%; Average loss: 2.9146Iteration: 2695; Percent complete: 67.4%; Average loss: 2.8622Iteration: 2696; Percent complete: 67.4%; Average loss: 3.0581Iteration: 2697; Percent complete: 67.4%; Average loss: 2.8853Iteration: 2698; Percent complete: 67.5%; Average loss: 2.8526Iteration: 2699; Percent complete: 67.5%; Average loss: 3.0998Iteration: 2700; Percent complete: 67.5%; Average loss: 2.9699Iteration: 2701; Percent complete: 67.5%; Average loss: 3.1042Iteration: 2702; Percent complete: 67.5%; Average loss: 3.0899Iteration: 2703; Percent complete: 67.6%; Average loss: 2.8040Iteration: 2704; Percent complete: 67.6%; Average loss: 3.0500Iteration: 2705; Percent complete: 67.6%; Average loss: 2.7381Iteration: 2706; Percent complete: 67.7%; Average loss: 3.0373Iteration: 2707; Percent complete: 67.7%; Average loss: 2.9033Iteration: 2708; Percent complete: 67.7%; Average loss: 3.0459Iteration: 2709; Percent complete: 67.7%; Average loss: 3.1245Iteration: 2710; Percent complete: 67.8%; Average loss: 2.8167Iteration: 2711; Percent complete: 67.8%; Average loss: 3.0451Iteration: 2712; Percent complete: 67.8%; Average loss: 3.1043Iteration: 2713; Percent complete: 67.8%; Average loss: 3.0758Iteration: 2714; Percent complete: 67.8%; Average loss: 2.5672Iteration: 2715; Percent complete: 67.9%; Average loss: 3.0512Iteration: 2716; Percent complete: 67.9%; Average loss: 2.7523Iteration: 2717; Percent complete: 67.9%; Average loss: 2.9516Iteration: 2718; Percent complete: 68.0%; Average loss: 3.1151Iteration: 2719; Percent complete: 68.0%; Average loss: 3.0103Iteration: 2720; Percent complete: 68.0%; Average loss: 2.9349Iteration: 2721; Percent complete: 68.0%; Average loss: 2.9334Iteration: 2722; Percent complete: 68.0%; Average loss: 2.8608Iteration: 2723; Percent complete: 68.1%; Average loss: 3.0996Iteration: 2724; Percent complete: 68.1%; Average loss: 2.7324Iteration: 2725; Percent complete: 68.1%; Average loss: 2.7929Iteration: 2726; Percent complete: 68.2%; Average loss: 2.8730Iteration: 2727; Percent complete: 68.2%; Average loss: 2.8273Iteration: 2728; Percent complete: 68.2%; Average loss: 3.0422Iteration: 2729; Percent complete: 68.2%; Average loss: 2.8839Iteration: 2730; Percent complete: 68.2%; Average loss: 3.1852Iteration: 2731; Percent complete: 68.3%; Average loss: 2.7196Iteration: 2732; Percent complete: 68.3%; Average loss: 2.9429Iteration: 2733; Percent complete: 68.3%; Average loss: 2.8433Iteration: 2734; Percent complete: 68.3%; Average loss: 2.8180Iteration: 2735; Percent complete: 68.4%; Average loss: 3.0801Iteration: 2736; Percent complete: 68.4%; Average loss: 2.9708Iteration: 2737; Percent complete: 68.4%; Average loss: 2.9303Iteration: 2738; Percent complete: 68.5%; Average loss: 3.1813Iteration: 2739; Percent complete: 68.5%; Average loss: 2.9808Iteration: 2740; Percent complete: 68.5%; Average loss: 3.0690Iteration: 2741; Percent complete: 68.5%; Average loss: 2.9564Iteration: 2742; Percent complete: 68.5%; Average loss: 2.9809Iteration: 2743; Percent complete: 68.6%; Average loss: 3.0779Iteration: 2744; Percent complete: 68.6%; Average loss: 3.0691Iteration: 2745; Percent complete: 68.6%; Average loss: 2.7665Iteration: 2746; Percent complete: 68.7%; Average loss: 3.1858Iteration: 2747; Percent complete: 68.7%; Average loss: 2.7204Iteration: 2748; Percent complete: 68.7%; Average loss: 2.8780Iteration: 2749; Percent complete: 68.7%; Average loss: 2.8689Iteration: 2750; Percent complete: 68.8%; Average loss: 2.6028Iteration: 2751; Percent complete: 68.8%; Average loss: 2.8882Iteration: 2752; Percent complete: 68.8%; Average loss: 2.9944Iteration: 2753; Percent complete: 68.8%; Average loss: 3.0328Iteration: 2754; Percent complete: 68.8%; Average loss: 2.6240Iteration: 2755; Percent complete: 68.9%; Average loss: 2.8152Iteration: 2756; Percent complete: 68.9%; Average loss: 2.8104Iteration: 2757; Percent complete: 68.9%; Average loss: 2.8483Iteration: 2758; Percent complete: 69.0%; Average loss: 3.0103Iteration: 2759; Percent complete: 69.0%; Average loss: 2.9635Iteration: 2760; Percent complete: 69.0%; Average loss: 2.8464Iteration: 2761; Percent complete: 69.0%; Average loss: 3.0326Iteration: 2762; Percent complete: 69.0%; Average loss: 2.6561Iteration: 2763; Percent complete: 69.1%; Average loss: 3.0011Iteration: 2764; Percent complete: 69.1%; Average loss: 3.0027Iteration: 2765; Percent complete: 69.1%; Average loss: 2.8526Iteration: 2766; Percent complete: 69.2%; Average loss: 2.9449Iteration: 2767; Percent complete: 69.2%; Average loss: 3.0466Iteration: 2768; Percent complete: 69.2%; Average loss: 2.9351Iteration: 2769; Percent complete: 69.2%; Average loss: 3.1888Iteration: 2770; Percent complete: 69.2%; Average loss: 2.7618Iteration: 2771; Percent complete: 69.3%; Average loss: 2.7608Iteration: 2772; Percent complete: 69.3%; Average loss: 2.8776Iteration: 2773; Percent complete: 69.3%; Average loss: 2.8797Iteration: 2774; Percent complete: 69.3%; Average loss: 3.0369Iteration: 2775; Percent complete: 69.4%; Average loss: 3.0072Iteration: 2776; Percent complete: 69.4%; Average loss: 2.8334Iteration: 2777; Percent complete: 69.4%; Average loss: 2.8780Iteration: 2778; Percent complete: 69.5%; Average loss: 2.9699Iteration: 2779; Percent complete: 69.5%; Average loss: 3.1398Iteration: 2780; Percent complete: 69.5%; Average loss: 2.8560Iteration: 2781; Percent complete: 69.5%; Average loss: 2.8666Iteration: 2782; Percent complete: 69.5%; Average loss: 3.0472Iteration: 2783; Percent complete: 69.6%; Average loss: 2.6288Iteration: 2784; Percent complete: 69.6%; Average loss: 2.8582Iteration: 2785; Percent complete: 69.6%; Average loss: 2.9635Iteration: 2786; Percent complete: 69.7%; Average loss: 3.0783Iteration: 2787; Percent complete: 69.7%; Average loss: 2.8418Iteration: 2788; Percent complete: 69.7%; Average loss: 2.9418Iteration: 2789; Percent complete: 69.7%; Average loss: 2.7807Iteration: 2790; Percent complete: 69.8%; Average loss: 3.0538Iteration: 2791; Percent complete: 69.8%; Average loss: 2.8036Iteration: 2792; Percent complete: 69.8%; Average loss: 2.5346Iteration: 2793; Percent complete: 69.8%; Average loss: 2.9419Iteration: 2794; Percent complete: 69.8%; Average loss: 2.7497Iteration: 2795; Percent complete: 69.9%; Average loss: 2.9079Iteration: 2796; Percent complete: 69.9%; Average loss: 2.9455Iteration: 2797; Percent complete: 69.9%; Average loss: 2.7418Iteration: 2798; Percent complete: 70.0%; Average loss: 2.9082Iteration: 2799; Percent complete: 70.0%; Average loss: 2.8748Iteration: 2800; Percent complete: 70.0%; Average loss: 2.9285Iteration: 2801; Percent complete: 70.0%; Average loss: 2.8626Iteration: 2802; Percent complete: 70.0%; Average loss: 2.8483Iteration: 2803; Percent complete: 70.1%; Average loss: 2.9614Iteration: 2804; Percent complete: 70.1%; Average loss: 2.6811Iteration: 2805; Percent complete: 70.1%; Average loss: 2.8303Iteration: 2806; Percent complete: 70.2%; Average loss: 3.0331Iteration: 2807; Percent complete: 70.2%; Average loss: 3.0227Iteration: 2808; Percent complete: 70.2%; Average loss: 2.9889Iteration: 2809; Percent complete: 70.2%; Average loss: 2.9404Iteration: 2810; Percent complete: 70.2%; Average loss: 2.8801Iteration: 2811; Percent complete: 70.3%; Average loss: 2.9568Iteration: 2812; Percent complete: 70.3%; Average loss: 3.0551Iteration: 2813; Percent complete: 70.3%; Average loss: 2.7867Iteration: 2814; Percent complete: 70.3%; Average loss: 2.8754Iteration: 2815; Percent complete: 70.4%; Average loss: 2.8469Iteration: 2816; Percent complete: 70.4%; Average loss: 2.7465Iteration: 2817; Percent complete: 70.4%; Average loss: 2.9069Iteration: 2818; Percent complete: 70.5%; Average loss: 3.1660Iteration: 2819; Percent complete: 70.5%; Average loss: 2.8445Iteration: 2820; Percent complete: 70.5%; Average loss: 2.9378Iteration: 2821; Percent complete: 70.5%; Average loss: 2.8986Iteration: 2822; Percent complete: 70.5%; Average loss: 2.9591Iteration: 2823; Percent complete: 70.6%; Average loss: 3.0688Iteration: 2824; Percent complete: 70.6%; Average loss: 2.9703Iteration: 2825; Percent complete: 70.6%; Average loss: 2.8676Iteration: 2826; Percent complete: 70.7%; Average loss: 2.7090Iteration: 2827; Percent complete: 70.7%; Average loss: 2.6904Iteration: 2828; Percent complete: 70.7%; Average loss: 3.0686Iteration: 2829; Percent complete: 70.7%; Average loss: 2.9763Iteration: 2830; Percent complete: 70.8%; Average loss: 2.9824Iteration: 2831; Percent complete: 70.8%; Average loss: 3.1216Iteration: 2832; Percent complete: 70.8%; Average loss: 2.9536Iteration: 2833; Percent complete: 70.8%; Average loss: 2.8420Iteration: 2834; Percent complete: 70.9%; Average loss: 2.8161Iteration: 2835; Percent complete: 70.9%; Average loss: 2.8385Iteration: 2836; Percent complete: 70.9%; Average loss: 3.0925Iteration: 2837; Percent complete: 70.9%; Average loss: 2.9720Iteration: 2838; Percent complete: 71.0%; Average loss: 2.8210Iteration: 2839; Percent complete: 71.0%; Average loss: 2.8822Iteration: 2840; Percent complete: 71.0%; Average loss: 2.8664Iteration: 2841; Percent complete: 71.0%; Average loss: 2.7008Iteration: 2842; Percent complete: 71.0%; Average loss: 2.8969Iteration: 2843; Percent complete: 71.1%; Average loss: 3.1444Iteration: 2844; Percent complete: 71.1%; Average loss: 3.0082Iteration: 2845; Percent complete: 71.1%; Average loss: 3.0966Iteration: 2846; Percent complete: 71.2%; Average loss: 2.7894Iteration: 2847; Percent complete: 71.2%; Average loss: 2.5854Iteration: 2848; Percent complete: 71.2%; Average loss: 2.8858Iteration: 2849; Percent complete: 71.2%; Average loss: 2.7197Iteration: 2850; Percent complete: 71.2%; Average loss: 2.7281Iteration: 2851; Percent complete: 71.3%; Average loss: 3.0198Iteration: 2852; Percent complete: 71.3%; Average loss: 2.9117Iteration: 2853; Percent complete: 71.3%; Average loss: 2.9760Iteration: 2854; Percent complete: 71.4%; Average loss: 3.0476Iteration: 2855; Percent complete: 71.4%; Average loss: 2.9546Iteration: 2856; Percent complete: 71.4%; Average loss: 3.0079Iteration: 2857; Percent complete: 71.4%; Average loss: 3.0382Iteration: 2858; Percent complete: 71.5%; Average loss: 2.8184Iteration: 2859; Percent complete: 71.5%; Average loss: 2.8478Iteration: 2860; Percent complete: 71.5%; Average loss: 3.0847Iteration: 2861; Percent complete: 71.5%; Average loss: 2.9569Iteration: 2862; Percent complete: 71.5%; Average loss: 3.1023Iteration: 2863; Percent complete: 71.6%; Average loss: 2.8658Iteration: 2864; Percent complete: 71.6%; Average loss: 3.0877Iteration: 2865; Percent complete: 71.6%; Average loss: 2.6609Iteration: 2866; Percent complete: 71.7%; Average loss: 2.6570Iteration: 2867; Percent complete: 71.7%; Average loss: 2.8278Iteration: 2868; Percent complete: 71.7%; Average loss: 2.9769Iteration: 2869; Percent complete: 71.7%; Average loss: 2.8695Iteration: 2870; Percent complete: 71.8%; Average loss: 3.2060Iteration: 2871; Percent complete: 71.8%; Average loss: 3.0602Iteration: 2872; Percent complete: 71.8%; Average loss: 2.9784Iteration: 2873; Percent complete: 71.8%; Average loss: 2.7662Iteration: 2874; Percent complete: 71.9%; Average loss: 2.8137Iteration: 2875; Percent complete: 71.9%; Average loss: 2.9090Iteration: 2876; Percent complete: 71.9%; Average loss: 3.1297Iteration: 2877; Percent complete: 71.9%; Average loss: 2.9445Iteration: 2878; Percent complete: 72.0%; Average loss: 2.9041Iteration: 2879; Percent complete: 72.0%; Average loss: 2.7675Iteration: 2880; Percent complete: 72.0%; Average loss: 2.9351Iteration: 2881; Percent complete: 72.0%; Average loss: 3.0342Iteration: 2882; Percent complete: 72.0%; Average loss: 2.7539Iteration: 2883; Percent complete: 72.1%; Average loss: 3.0197Iteration: 2884; Percent complete: 72.1%; Average loss: 2.7018Iteration: 2885; Percent complete: 72.1%; Average loss: 2.9288Iteration: 2886; Percent complete: 72.2%; Average loss: 2.9050Iteration: 2887; Percent complete: 72.2%; Average loss: 2.8217Iteration: 2888; Percent complete: 72.2%; Average loss: 2.9081Iteration: 2889; Percent complete: 72.2%; Average loss: 2.8320Iteration: 2890; Percent complete: 72.2%; Average loss: 2.8493Iteration: 2891; Percent complete: 72.3%; Average loss: 3.0205Iteration: 2892; Percent complete: 72.3%; Average loss: 2.7789Iteration: 2893; Percent complete: 72.3%; Average loss: 2.7936Iteration: 2894; Percent complete: 72.4%; Average loss: 3.1636Iteration: 2895; Percent complete: 72.4%; Average loss: 2.7843Iteration: 2896; Percent complete: 72.4%; Average loss: 2.9121Iteration: 2897; Percent complete: 72.4%; Average loss: 2.8350Iteration: 2898; Percent complete: 72.5%; Average loss: 3.2157Iteration: 2899; Percent complete: 72.5%; Average loss: 3.2005Iteration: 2900; Percent complete: 72.5%; Average loss: 2.6721Iteration: 2901; Percent complete: 72.5%; Average loss: 2.4843Iteration: 2902; Percent complete: 72.5%; Average loss: 2.7543Iteration: 2903; Percent complete: 72.6%; Average loss: 2.8714Iteration: 2904; Percent complete: 72.6%; Average loss: 2.7005Iteration: 2905; Percent complete: 72.6%; Average loss: 3.0314Iteration: 2906; Percent complete: 72.7%; Average loss: 2.9894Iteration: 2907; Percent complete: 72.7%; Average loss: 2.5905Iteration: 2908; Percent complete: 72.7%; Average loss: 2.9735Iteration: 2909; Percent complete: 72.7%; Average loss: 2.9450Iteration: 2910; Percent complete: 72.8%; Average loss: 2.9348Iteration: 2911; Percent complete: 72.8%; Average loss: 2.8056Iteration: 2912; Percent complete: 72.8%; Average loss: 3.0140Iteration: 2913; Percent complete: 72.8%; Average loss: 2.7964Iteration: 2914; Percent complete: 72.9%; Average loss: 3.1251Iteration: 2915; Percent complete: 72.9%; Average loss: 2.9456Iteration: 2916; Percent complete: 72.9%; Average loss: 2.8917Iteration: 2917; Percent complete: 72.9%; Average loss: 3.1197Iteration: 2918; Percent complete: 73.0%; Average loss: 2.7063Iteration: 2919; Percent complete: 73.0%; Average loss: 2.7439Iteration: 2920; Percent complete: 73.0%; Average loss: 2.9135Iteration: 2921; Percent complete: 73.0%; Average loss: 2.9853Iteration: 2922; Percent complete: 73.0%; Average loss: 2.5898Iteration: 2923; Percent complete: 73.1%; Average loss: 2.7110Iteration: 2924; Percent complete: 73.1%; Average loss: 2.9859Iteration: 2925; Percent complete: 73.1%; Average loss: 2.9874Iteration: 2926; Percent complete: 73.2%; Average loss: 3.0992Iteration: 2927; Percent complete: 73.2%; Average loss: 3.0344Iteration: 2928; Percent complete: 73.2%; Average loss: 2.6505Iteration: 2929; Percent complete: 73.2%; Average loss: 2.9067Iteration: 2930; Percent complete: 73.2%; Average loss: 2.9094Iteration: 2931; Percent complete: 73.3%; Average loss: 2.7356Iteration: 2932; Percent complete: 73.3%; Average loss: 3.0369Iteration: 2933; Percent complete: 73.3%; Average loss: 2.8683Iteration: 2934; Percent complete: 73.4%; Average loss: 2.7209Iteration: 2935; Percent complete: 73.4%; Average loss: 2.8274Iteration: 2936; Percent complete: 73.4%; Average loss: 3.0078Iteration: 2937; Percent complete: 73.4%; Average loss: 3.0090Iteration: 2938; Percent complete: 73.5%; Average loss: 2.8685Iteration: 2939; Percent complete: 73.5%; Average loss: 2.8749Iteration: 2940; Percent complete: 73.5%; Average loss: 2.6556Iteration: 2941; Percent complete: 73.5%; Average loss: 3.0873Iteration: 2942; Percent complete: 73.6%; Average loss: 2.9322Iteration: 2943; Percent complete: 73.6%; Average loss: 2.8608Iteration: 2944; Percent complete: 73.6%; Average loss: 2.8027Iteration: 2945; Percent complete: 73.6%; Average loss: 2.8128Iteration: 2946; Percent complete: 73.7%; Average loss: 2.7402Iteration: 2947; Percent complete: 73.7%; Average loss: 2.9589Iteration: 2948; Percent complete: 73.7%; Average loss: 3.1067Iteration: 2949; Percent complete: 73.7%; Average loss: 3.0030Iteration: 2950; Percent complete: 73.8%; Average loss: 2.8013Iteration: 2951; Percent complete: 73.8%; Average loss: 2.6268Iteration: 2952; Percent complete: 73.8%; Average loss: 2.7214Iteration: 2953; Percent complete: 73.8%; Average loss: 2.6874Iteration: 2954; Percent complete: 73.9%; Average loss: 2.7631Iteration: 2955; Percent complete: 73.9%; Average loss: 2.9985Iteration: 2956; Percent complete: 73.9%; Average loss: 2.7673Iteration: 2957; Percent complete: 73.9%; Average loss: 2.6170Iteration: 2958; Percent complete: 74.0%; Average loss: 2.8535Iteration: 2959; Percent complete: 74.0%; Average loss: 2.7144Iteration: 2960; Percent complete: 74.0%; Average loss: 2.8289Iteration: 2961; Percent complete: 74.0%; Average loss: 2.9725Iteration: 2962; Percent complete: 74.1%; Average loss: 2.8801Iteration: 2963; Percent complete: 74.1%; Average loss: 2.9577Iteration: 2964; Percent complete: 74.1%; Average loss: 3.1214Iteration: 2965; Percent complete: 74.1%; Average loss: 2.8516Iteration: 2966; Percent complete: 74.2%; Average loss: 2.7764Iteration: 2967; Percent complete: 74.2%; Average loss: 2.9271Iteration: 2968; Percent complete: 74.2%; Average loss: 2.8703Iteration: 2969; Percent complete: 74.2%; Average loss: 2.9766Iteration: 2970; Percent complete: 74.2%; Average loss: 2.9356Iteration: 2971; Percent complete: 74.3%; Average loss: 2.9600Iteration: 2972; Percent complete: 74.3%; Average loss: 2.9768Iteration: 2973; Percent complete: 74.3%; Average loss: 2.8980Iteration: 2974; Percent complete: 74.4%; Average loss: 2.6896Iteration: 2975; Percent complete: 74.4%; Average loss: 2.8253Iteration: 2976; Percent complete: 74.4%; Average loss: 2.9390Iteration: 2977; Percent complete: 74.4%; Average loss: 2.9040Iteration: 2978; Percent complete: 74.5%; Average loss: 2.8719Iteration: 2979; Percent complete: 74.5%; Average loss: 2.9051Iteration: 2980; Percent complete: 74.5%; Average loss: 3.1661Iteration: 2981; Percent complete: 74.5%; Average loss: 3.1263Iteration: 2982; Percent complete: 74.6%; Average loss: 3.0173Iteration: 2983; Percent complete: 74.6%; Average loss: 2.9101Iteration: 2984; Percent complete: 74.6%; Average loss: 2.7052Iteration: 2985; Percent complete: 74.6%; Average loss: 2.7419Iteration: 2986; Percent complete: 74.7%; Average loss: 2.9287Iteration: 2987; Percent complete: 74.7%; Average loss: 3.0079Iteration: 2988; Percent complete: 74.7%; Average loss: 2.7417Iteration: 2989; Percent complete: 74.7%; Average loss: 3.3850Iteration: 2990; Percent complete: 74.8%; Average loss: 2.8981Iteration: 2991; Percent complete: 74.8%; Average loss: 2.9831Iteration: 2992; Percent complete: 74.8%; Average loss: 2.7272Iteration: 2993; Percent complete: 74.8%; Average loss: 2.8817Iteration: 2994; Percent complete: 74.9%; Average loss: 2.9655Iteration: 2995; Percent complete: 74.9%; Average loss: 2.6032Iteration: 2996; Percent complete: 74.9%; Average loss: 2.7950Iteration: 2997; Percent complete: 74.9%; Average loss: 2.9825Iteration: 2998; Percent complete: 75.0%; Average loss: 3.0339Iteration: 2999; Percent complete: 75.0%; Average loss: 2.8077Iteration: 3000; Percent complete: 75.0%; Average loss: 2.7899Iteration: 3001; Percent complete: 75.0%; Average loss: 2.7351Iteration: 3002; Percent complete: 75.0%; Average loss: 2.8143Iteration: 3003; Percent complete: 75.1%; Average loss: 3.0890Iteration: 3004; Percent complete: 75.1%; Average loss: 3.0212Iteration: 3005; Percent complete: 75.1%; Average loss: 2.8382Iteration: 3006; Percent complete: 75.1%; Average loss: 2.8749Iteration: 3007; Percent complete: 75.2%; Average loss: 3.0122Iteration: 3008; Percent complete: 75.2%; Average loss: 2.7478Iteration: 3009; Percent complete: 75.2%; Average loss: 3.0995Iteration: 3010; Percent complete: 75.2%; Average loss: 2.8727Iteration: 3011; Percent complete: 75.3%; Average loss: 2.9472Iteration: 3012; Percent complete: 75.3%; Average loss: 3.1316Iteration: 3013; Percent complete: 75.3%; Average loss: 2.7886Iteration: 3014; Percent complete: 75.3%; Average loss: 2.8232Iteration: 3015; Percent complete: 75.4%; Average loss: 2.8439Iteration: 3016; Percent complete: 75.4%; Average loss: 2.8194Iteration: 3017; Percent complete: 75.4%; Average loss: 2.9118Iteration: 3018; Percent complete: 75.4%; Average loss: 2.9427Iteration: 3019; Percent complete: 75.5%; Average loss: 2.7700Iteration: 3020; Percent complete: 75.5%; Average loss: 2.8480Iteration: 3021; Percent complete: 75.5%; Average loss: 2.9539Iteration: 3022; Percent complete: 75.5%; Average loss: 2.7681Iteration: 3023; Percent complete: 75.6%; Average loss: 2.8650Iteration: 3024; Percent complete: 75.6%; Average loss: 2.8799Iteration: 3025; Percent complete: 75.6%; Average loss: 2.9127Iteration: 3026; Percent complete: 75.6%; Average loss: 2.8906Iteration: 3027; Percent complete: 75.7%; Average loss: 2.8616Iteration: 3028; Percent complete: 75.7%; Average loss: 2.7744Iteration: 3029; Percent complete: 75.7%; Average loss: 3.0723Iteration: 3030; Percent complete: 75.8%; Average loss: 3.0585Iteration: 3031; Percent complete: 75.8%; Average loss: 2.7825Iteration: 3032; Percent complete: 75.8%; Average loss: 3.0319Iteration: 3033; Percent complete: 75.8%; Average loss: 2.9899Iteration: 3034; Percent complete: 75.8%; Average loss: 2.8934Iteration: 3035; Percent complete: 75.9%; Average loss: 3.0766Iteration: 3036; Percent complete: 75.9%; Average loss: 2.8674Iteration: 3037; Percent complete: 75.9%; Average loss: 2.8958Iteration: 3038; Percent complete: 75.9%; Average loss: 2.8514Iteration: 3039; Percent complete: 76.0%; Average loss: 2.8123Iteration: 3040; Percent complete: 76.0%; Average loss: 2.9167Iteration: 3041; Percent complete: 76.0%; Average loss: 2.6072Iteration: 3042; Percent complete: 76.0%; Average loss: 2.8483Iteration: 3043; Percent complete: 76.1%; Average loss: 2.9147Iteration: 3044; Percent complete: 76.1%; Average loss: 2.7425Iteration: 3045; Percent complete: 76.1%; Average loss: 2.8461Iteration: 3046; Percent complete: 76.1%; Average loss: 2.6889Iteration: 3047; Percent complete: 76.2%; Average loss: 2.7869Iteration: 3048; Percent complete: 76.2%; Average loss: 2.9450Iteration: 3049; Percent complete: 76.2%; Average loss: 2.9788Iteration: 3050; Percent complete: 76.2%; Average loss: 2.6734Iteration: 3051; Percent complete: 76.3%; Average loss: 2.9239Iteration: 3052; Percent complete: 76.3%; Average loss: 3.1225Iteration: 3053; Percent complete: 76.3%; Average loss: 2.5962Iteration: 3054; Percent complete: 76.3%; Average loss: 3.1673Iteration: 3055; Percent complete: 76.4%; Average loss: 2.8989Iteration: 3056; Percent complete: 76.4%; Average loss: 2.8840Iteration: 3057; Percent complete: 76.4%; Average loss: 2.9492Iteration: 3058; Percent complete: 76.4%; Average loss: 2.9870Iteration: 3059; Percent complete: 76.5%; Average loss: 2.8032Iteration: 3060; Percent complete: 76.5%; Average loss: 2.6045Iteration: 3061; Percent complete: 76.5%; Average loss: 2.7935Iteration: 3062; Percent complete: 76.5%; Average loss: 2.9165Iteration: 3063; Percent complete: 76.6%; Average loss: 2.9225Iteration: 3064; Percent complete: 76.6%; Average loss: 2.6755Iteration: 3065; Percent complete: 76.6%; Average loss: 2.8185Iteration: 3066; Percent complete: 76.6%; Average loss: 2.9792Iteration: 3067; Percent complete: 76.7%; Average loss: 2.7536Iteration: 3068; Percent complete: 76.7%; Average loss: 2.9512Iteration: 3069; Percent complete: 76.7%; Average loss: 2.9628Iteration: 3070; Percent complete: 76.8%; Average loss: 2.7480Iteration: 3071; Percent complete: 76.8%; Average loss: 2.9060Iteration: 3072; Percent complete: 76.8%; Average loss: 3.0949Iteration: 3073; Percent complete: 76.8%; Average loss: 2.8703Iteration: 3074; Percent complete: 76.8%; Average loss: 2.7269Iteration: 3075; Percent complete: 76.9%; Average loss: 2.8085Iteration: 3076; Percent complete: 76.9%; Average loss: 2.6447Iteration: 3077; Percent complete: 76.9%; Average loss: 2.7914Iteration: 3078; Percent complete: 77.0%; Average loss: 3.0739Iteration: 3079; Percent complete: 77.0%; Average loss: 2.6804Iteration: 3080; Percent complete: 77.0%; Average loss: 2.8302Iteration: 3081; Percent complete: 77.0%; Average loss: 2.6999Iteration: 3082; Percent complete: 77.0%; Average loss: 2.9623Iteration: 3083; Percent complete: 77.1%; Average loss: 2.7547Iteration: 3084; Percent complete: 77.1%; Average loss: 2.8911Iteration: 3085; Percent complete: 77.1%; Average loss: 2.9191Iteration: 3086; Percent complete: 77.1%; Average loss: 2.6848Iteration: 3087; Percent complete: 77.2%; Average loss: 2.8081Iteration: 3088; Percent complete: 77.2%; Average loss: 3.0529Iteration: 3089; Percent complete: 77.2%; Average loss: 3.0748Iteration: 3090; Percent complete: 77.2%; Average loss: 2.9938Iteration: 3091; Percent complete: 77.3%; Average loss: 2.8953Iteration: 3092; Percent complete: 77.3%; Average loss: 2.8184Iteration: 3093; Percent complete: 77.3%; Average loss: 3.0675Iteration: 3094; Percent complete: 77.3%; Average loss: 2.7274Iteration: 3095; Percent complete: 77.4%; Average loss: 2.8729Iteration: 3096; Percent complete: 77.4%; Average loss: 2.8449Iteration: 3097; Percent complete: 77.4%; Average loss: 2.8823Iteration: 3098; Percent complete: 77.5%; Average loss: 2.8928Iteration: 3099; Percent complete: 77.5%; Average loss: 2.9469Iteration: 3100; Percent complete: 77.5%; Average loss: 2.9013Iteration: 3101; Percent complete: 77.5%; Average loss: 2.8617Iteration: 3102; Percent complete: 77.5%; Average loss: 2.7538Iteration: 3103; Percent complete: 77.6%; Average loss: 2.6433Iteration: 3104; Percent complete: 77.6%; Average loss: 2.8643Iteration: 3105; Percent complete: 77.6%; Average loss: 2.7596Iteration: 3106; Percent complete: 77.6%; Average loss: 3.0444Iteration: 3107; Percent complete: 77.7%; Average loss: 2.8296Iteration: 3108; Percent complete: 77.7%; Average loss: 3.1046Iteration: 3109; Percent complete: 77.7%; Average loss: 2.7888Iteration: 3110; Percent complete: 77.8%; Average loss: 2.7657Iteration: 3111; Percent complete: 77.8%; Average loss: 3.0682Iteration: 3112; Percent complete: 77.8%; Average loss: 2.8335Iteration: 3113; Percent complete: 77.8%; Average loss: 3.0002Iteration: 3114; Percent complete: 77.8%; Average loss: 2.8449Iteration: 3115; Percent complete: 77.9%; Average loss: 2.8390Iteration: 3116; Percent complete: 77.9%; Average loss: 2.9566Iteration: 3117; Percent complete: 77.9%; Average loss: 3.0688Iteration: 3118; Percent complete: 78.0%; Average loss: 2.9207Iteration: 3119; Percent complete: 78.0%; Average loss: 3.0331Iteration: 3120; Percent complete: 78.0%; Average loss: 2.8837Iteration: 3121; Percent complete: 78.0%; Average loss: 2.7431Iteration: 3122; Percent complete: 78.0%; Average loss: 2.7211Iteration: 3123; Percent complete: 78.1%; Average loss: 2.8122Iteration: 3124; Percent complete: 78.1%; Average loss: 2.9347Iteration: 3125; Percent complete: 78.1%; Average loss: 2.8631Iteration: 3126; Percent complete: 78.1%; Average loss: 2.6710Iteration: 3127; Percent complete: 78.2%; Average loss: 2.6201Iteration: 3128; Percent complete: 78.2%; Average loss: 3.0715Iteration: 3129; Percent complete: 78.2%; Average loss: 2.9649Iteration: 3130; Percent complete: 78.2%; Average loss: 2.5354Iteration: 3131; Percent complete: 78.3%; Average loss: 2.6453Iteration: 3132; Percent complete: 78.3%; Average loss: 2.9577Iteration: 3133; Percent complete: 78.3%; Average loss: 2.8514Iteration: 3134; Percent complete: 78.3%; Average loss: 2.9510Iteration: 3135; Percent complete: 78.4%; Average loss: 2.9039Iteration: 3136; Percent complete: 78.4%; Average loss: 2.5325Iteration: 3137; Percent complete: 78.4%; Average loss: 2.8197Iteration: 3138; Percent complete: 78.5%; Average loss: 3.0393Iteration: 3139; Percent complete: 78.5%; Average loss: 2.7285Iteration: 3140; Percent complete: 78.5%; Average loss: 2.5939Iteration: 3141; Percent complete: 78.5%; Average loss: 2.9910Iteration: 3142; Percent complete: 78.5%; Average loss: 2.6164Iteration: 3143; Percent complete: 78.6%; Average loss: 2.5292Iteration: 3144; Percent complete: 78.6%; Average loss: 2.6987Iteration: 3145; Percent complete: 78.6%; Average loss: 2.9205Iteration: 3146; Percent complete: 78.6%; Average loss: 2.9152Iteration: 3147; Percent complete: 78.7%; Average loss: 2.9171Iteration: 3148; Percent complete: 78.7%; Average loss: 2.7064Iteration: 3149; Percent complete: 78.7%; Average loss: 2.9506Iteration: 3150; Percent complete: 78.8%; Average loss: 3.0144Iteration: 3151; Percent complete: 78.8%; Average loss: 2.8640Iteration: 3152; Percent complete: 78.8%; Average loss: 2.5423Iteration: 3153; Percent complete: 78.8%; Average loss: 3.0515Iteration: 3154; Percent complete: 78.8%; Average loss: 2.8252Iteration: 3155; Percent complete: 78.9%; Average loss: 2.9059Iteration: 3156; Percent complete: 78.9%; Average loss: 3.0011Iteration: 3157; Percent complete: 78.9%; Average loss: 2.6973Iteration: 3158; Percent complete: 79.0%; Average loss: 2.6124Iteration: 3159; Percent complete: 79.0%; Average loss: 2.8291Iteration: 3160; Percent complete: 79.0%; Average loss: 2.9603Iteration: 3161; Percent complete: 79.0%; Average loss: 2.6465Iteration: 3162; Percent complete: 79.0%; Average loss: 2.8190Iteration: 3163; Percent complete: 79.1%; Average loss: 2.8996Iteration: 3164; Percent complete: 79.1%; Average loss: 2.9150Iteration: 3165; Percent complete: 79.1%; Average loss: 2.8567Iteration: 3166; Percent complete: 79.1%; Average loss: 2.7363Iteration: 3167; Percent complete: 79.2%; Average loss: 2.8702Iteration: 3168; Percent complete: 79.2%; Average loss: 2.7712Iteration: 3169; Percent complete: 79.2%; Average loss: 2.8482Iteration: 3170; Percent complete: 79.2%; Average loss: 2.6626Iteration: 3171; Percent complete: 79.3%; Average loss: 3.0775Iteration: 3172; Percent complete: 79.3%; Average loss: 2.5896Iteration: 3173; Percent complete: 79.3%; Average loss: 2.8436Iteration: 3174; Percent complete: 79.3%; Average loss: 2.9684Iteration: 3175; Percent complete: 79.4%; Average loss: 2.8534Iteration: 3176; Percent complete: 79.4%; Average loss: 3.1410Iteration: 3177; Percent complete: 79.4%; Average loss: 2.8693Iteration: 3178; Percent complete: 79.5%; Average loss: 2.5838Iteration: 3179; Percent complete: 79.5%; Average loss: 2.7645Iteration: 3180; Percent complete: 79.5%; Average loss: 2.9373Iteration: 3181; Percent complete: 79.5%; Average loss: 2.7658Iteration: 3182; Percent complete: 79.5%; Average loss: 3.0155Iteration: 3183; Percent complete: 79.6%; Average loss: 2.8191Iteration: 3184; Percent complete: 79.6%; Average loss: 2.7181Iteration: 3185; Percent complete: 79.6%; Average loss: 2.8752Iteration: 3186; Percent complete: 79.7%; Average loss: 2.6024Iteration: 3187; Percent complete: 79.7%; Average loss: 3.0564Iteration: 3188; Percent complete: 79.7%; Average loss: 2.7027Iteration: 3189; Percent complete: 79.7%; Average loss: 2.8988Iteration: 3190; Percent complete: 79.8%; Average loss: 2.9225Iteration: 3191; Percent complete: 79.8%; Average loss: 2.7286Iteration: 3192; Percent complete: 79.8%; Average loss: 2.7310Iteration: 3193; Percent complete: 79.8%; Average loss: 2.5218Iteration: 3194; Percent complete: 79.8%; Average loss: 2.7205Iteration: 3195; Percent complete: 79.9%; Average loss: 2.8402Iteration: 3196; Percent complete: 79.9%; Average loss: 2.8716Iteration: 3197; Percent complete: 79.9%; Average loss: 2.7118Iteration: 3198; Percent complete: 80.0%; Average loss: 2.6950Iteration: 3199; Percent complete: 80.0%; Average loss: 2.8748Iteration: 3200; Percent complete: 80.0%; Average loss: 3.0065Iteration: 3201; Percent complete: 80.0%; Average loss: 2.8466Iteration: 3202; Percent complete: 80.0%; Average loss: 3.0101Iteration: 3203; Percent complete: 80.1%; Average loss: 2.9880Iteration: 3204; Percent complete: 80.1%; Average loss: 2.9092Iteration: 3205; Percent complete: 80.1%; Average loss: 2.9782Iteration: 3206; Percent complete: 80.2%; Average loss: 2.7754Iteration: 3207; Percent complete: 80.2%; Average loss: 2.8616Iteration: 3208; Percent complete: 80.2%; Average loss: 2.7914Iteration: 3209; Percent complete: 80.2%; Average loss: 2.6099Iteration: 3210; Percent complete: 80.2%; Average loss: 2.8957Iteration: 3211; Percent complete: 80.3%; Average loss: 2.7733Iteration: 3212; Percent complete: 80.3%; Average loss: 2.6211Iteration: 3213; Percent complete: 80.3%; Average loss: 2.5853Iteration: 3214; Percent complete: 80.3%; Average loss: 3.0070Iteration: 3215; Percent complete: 80.4%; Average loss: 2.7292Iteration: 3216; Percent complete: 80.4%; Average loss: 2.7708Iteration: 3217; Percent complete: 80.4%; Average loss: 2.7201Iteration: 3218; Percent complete: 80.5%; Average loss: 2.8113Iteration: 3219; Percent complete: 80.5%; Average loss: 2.9232Iteration: 3220; Percent complete: 80.5%; Average loss: 2.8965Iteration: 3221; Percent complete: 80.5%; Average loss: 3.0884Iteration: 3222; Percent complete: 80.5%; Average loss: 3.0979Iteration: 3223; Percent complete: 80.6%; Average loss: 2.5472Iteration: 3224; Percent complete: 80.6%; Average loss: 2.6512Iteration: 3225; Percent complete: 80.6%; Average loss: 3.1693Iteration: 3226; Percent complete: 80.7%; Average loss: 2.9931Iteration: 3227; Percent complete: 80.7%; Average loss: 2.6725Iteration: 3228; Percent complete: 80.7%; Average loss: 2.8924Iteration: 3229; Percent complete: 80.7%; Average loss: 2.6582Iteration: 3230; Percent complete: 80.8%; Average loss: 2.7221Iteration: 3231; Percent complete: 80.8%; Average loss: 2.5130Iteration: 3232; Percent complete: 80.8%; Average loss: 2.6829Iteration: 3233; Percent complete: 80.8%; Average loss: 2.7508Iteration: 3234; Percent complete: 80.8%; Average loss: 2.6458Iteration: 3235; Percent complete: 80.9%; Average loss: 3.1131Iteration: 3236; Percent complete: 80.9%; Average loss: 2.8703Iteration: 3237; Percent complete: 80.9%; Average loss: 2.5646Iteration: 3238; Percent complete: 81.0%; Average loss: 2.7302Iteration: 3239; Percent complete: 81.0%; Average loss: 2.7134Iteration: 3240; Percent complete: 81.0%; Average loss: 2.7546Iteration: 3241; Percent complete: 81.0%; Average loss: 2.9637Iteration: 3242; Percent complete: 81.0%; Average loss: 2.6806Iteration: 3243; Percent complete: 81.1%; Average loss: 2.8198Iteration: 3244; Percent complete: 81.1%; Average loss: 2.6193Iteration: 3245; Percent complete: 81.1%; Average loss: 2.7219Iteration: 3246; Percent complete: 81.2%; Average loss: 2.7419Iteration: 3247; Percent complete: 81.2%; Average loss: 2.8324Iteration: 3248; Percent complete: 81.2%; Average loss: 2.7615Iteration: 3249; Percent complete: 81.2%; Average loss: 2.8948Iteration: 3250; Percent complete: 81.2%; Average loss: 2.7256Iteration: 3251; Percent complete: 81.3%; Average loss: 2.6940Iteration: 3252; Percent complete: 81.3%; Average loss: 2.9456Iteration: 3253; Percent complete: 81.3%; Average loss: 2.7692Iteration: 3254; Percent complete: 81.3%; Average loss: 2.7589Iteration: 3255; Percent complete: 81.4%; Average loss: 2.8623Iteration: 3256; Percent complete: 81.4%; Average loss: 2.9854Iteration: 3257; Percent complete: 81.4%; Average loss: 2.7780Iteration: 3258; Percent complete: 81.5%; Average loss: 2.8341Iteration: 3259; Percent complete: 81.5%; Average loss: 2.9191Iteration: 3260; Percent complete: 81.5%; Average loss: 2.8097Iteration: 3261; Percent complete: 81.5%; Average loss: 2.7202Iteration: 3262; Percent complete: 81.5%; Average loss: 2.9406Iteration: 3263; Percent complete: 81.6%; Average loss: 2.6784Iteration: 3264; Percent complete: 81.6%; Average loss: 2.8794Iteration: 3265; Percent complete: 81.6%; Average loss: 2.7516Iteration: 3266; Percent complete: 81.7%; Average loss: 2.6853Iteration: 3267; Percent complete: 81.7%; Average loss: 2.7483Iteration: 3268; Percent complete: 81.7%; Average loss: 2.9048Iteration: 3269; Percent complete: 81.7%; Average loss: 2.8026Iteration: 3270; Percent complete: 81.8%; Average loss: 2.9269Iteration: 3271; Percent complete: 81.8%; Average loss: 2.7944Iteration: 3272; Percent complete: 81.8%; Average loss: 2.7164Iteration: 3273; Percent complete: 81.8%; Average loss: 2.8392Iteration: 3274; Percent complete: 81.8%; Average loss: 2.9566Iteration: 3275; Percent complete: 81.9%; Average loss: 2.8731Iteration: 3276; Percent complete: 81.9%; Average loss: 2.6272Iteration: 3277; Percent complete: 81.9%; Average loss: 2.7271Iteration: 3278; Percent complete: 82.0%; Average loss: 2.5454Iteration: 3279; Percent complete: 82.0%; Average loss: 2.8777Iteration: 3280; Percent complete: 82.0%; Average loss: 2.9384Iteration: 3281; Percent complete: 82.0%; Average loss: 2.8183Iteration: 3282; Percent complete: 82.0%; Average loss: 2.9460Iteration: 3283; Percent complete: 82.1%; Average loss: 2.5676Iteration: 3284; Percent complete: 82.1%; Average loss: 2.9771Iteration: 3285; Percent complete: 82.1%; Average loss: 2.5363Iteration: 3286; Percent complete: 82.2%; Average loss: 2.6962Iteration: 3287; Percent complete: 82.2%; Average loss: 2.8675Iteration: 3288; Percent complete: 82.2%; Average loss: 2.5667Iteration: 3289; Percent complete: 82.2%; Average loss: 2.8300Iteration: 3290; Percent complete: 82.2%; Average loss: 2.9872Iteration: 3291; Percent complete: 82.3%; Average loss: 2.5753Iteration: 3292; Percent complete: 82.3%; Average loss: 2.8756Iteration: 3293; Percent complete: 82.3%; Average loss: 2.5655Iteration: 3294; Percent complete: 82.3%; Average loss: 2.9230Iteration: 3295; Percent complete: 82.4%; Average loss: 2.7033Iteration: 3296; Percent complete: 82.4%; Average loss: 2.7054Iteration: 3297; Percent complete: 82.4%; Average loss: 3.0353Iteration: 3298; Percent complete: 82.5%; Average loss: 2.8155Iteration: 3299; Percent complete: 82.5%; Average loss: 2.8159Iteration: 3300; Percent complete: 82.5%; Average loss: 2.8821Iteration: 3301; Percent complete: 82.5%; Average loss: 2.8145Iteration: 3302; Percent complete: 82.5%; Average loss: 2.7506Iteration: 3303; Percent complete: 82.6%; Average loss: 2.7383Iteration: 3304; Percent complete: 82.6%; Average loss: 2.7802Iteration: 3305; Percent complete: 82.6%; Average loss: 3.0443Iteration: 3306; Percent complete: 82.7%; Average loss: 2.7603Iteration: 3307; Percent complete: 82.7%; Average loss: 2.5127Iteration: 3308; Percent complete: 82.7%; Average loss: 2.5235Iteration: 3309; Percent complete: 82.7%; Average loss: 2.8742Iteration: 3310; Percent complete: 82.8%; Average loss: 2.6602Iteration: 3311; Percent complete: 82.8%; Average loss: 2.6527Iteration: 3312; Percent complete: 82.8%; Average loss: 2.6917Iteration: 3313; Percent complete: 82.8%; Average loss: 2.8221Iteration: 3314; Percent complete: 82.8%; Average loss: 2.5160Iteration: 3315; Percent complete: 82.9%; Average loss: 2.6727Iteration: 3316; Percent complete: 82.9%; Average loss: 2.7768Iteration: 3317; Percent complete: 82.9%; Average loss: 2.6702Iteration: 3318; Percent complete: 83.0%; Average loss: 2.5979Iteration: 3319; Percent complete: 83.0%; Average loss: 2.5991Iteration: 3320; Percent complete: 83.0%; Average loss: 2.8574Iteration: 3321; Percent complete: 83.0%; Average loss: 2.9338Iteration: 3322; Percent complete: 83.0%; Average loss: 2.8609Iteration: 3323; Percent complete: 83.1%; Average loss: 2.8003Iteration: 3324; Percent complete: 83.1%; Average loss: 2.6635Iteration: 3325; Percent complete: 83.1%; Average loss: 3.0863Iteration: 3326; Percent complete: 83.2%; Average loss: 2.7647Iteration: 3327; Percent complete: 83.2%; Average loss: 2.7512Iteration: 3328; Percent complete: 83.2%; Average loss: 2.6368Iteration: 3329; Percent complete: 83.2%; Average loss: 2.8987Iteration: 3330; Percent complete: 83.2%; Average loss: 2.9127Iteration: 3331; Percent complete: 83.3%; Average loss: 2.6401Iteration: 3332; Percent complete: 83.3%; Average loss: 2.8618Iteration: 3333; Percent complete: 83.3%; Average loss: 2.8022Iteration: 3334; Percent complete: 83.4%; Average loss: 2.9527Iteration: 3335; Percent complete: 83.4%; Average loss: 2.6588Iteration: 3336; Percent complete: 83.4%; Average loss: 2.9222Iteration: 3337; Percent complete: 83.4%; Average loss: 2.8205Iteration: 3338; Percent complete: 83.5%; Average loss: 2.7081Iteration: 3339; Percent complete: 83.5%; Average loss: 2.6127Iteration: 3340; Percent complete: 83.5%; Average loss: 2.7427Iteration: 3341; Percent complete: 83.5%; Average loss: 2.9246Iteration: 3342; Percent complete: 83.5%; Average loss: 3.0163Iteration: 3343; Percent complete: 83.6%; Average loss: 2.7306Iteration: 3344; Percent complete: 83.6%; Average loss: 2.7776Iteration: 3345; Percent complete: 83.6%; Average loss: 2.8737Iteration: 3346; Percent complete: 83.7%; Average loss: 2.6581Iteration: 3347; Percent complete: 83.7%; Average loss: 2.7919Iteration: 3348; Percent complete: 83.7%; Average loss: 2.9067Iteration: 3349; Percent complete: 83.7%; Average loss: 2.6940Iteration: 3350; Percent complete: 83.8%; Average loss: 2.4810Iteration: 3351; Percent complete: 83.8%; Average loss: 2.8310Iteration: 3352; Percent complete: 83.8%; Average loss: 2.7538Iteration: 3353; Percent complete: 83.8%; Average loss: 2.5702Iteration: 3354; Percent complete: 83.9%; Average loss: 2.9048Iteration: 3355; Percent complete: 83.9%; Average loss: 2.8656Iteration: 3356; Percent complete: 83.9%; Average loss: 2.8474Iteration: 3357; Percent complete: 83.9%; Average loss: 2.5790Iteration: 3358; Percent complete: 84.0%; Average loss: 2.7122Iteration: 3359; Percent complete: 84.0%; Average loss: 2.6770Iteration: 3360; Percent complete: 84.0%; Average loss: 2.8741Iteration: 3361; Percent complete: 84.0%; Average loss: 2.9063Iteration: 3362; Percent complete: 84.0%; Average loss: 2.6793Iteration: 3363; Percent complete: 84.1%; Average loss: 2.5661Iteration: 3364; Percent complete: 84.1%; Average loss: 2.8421Iteration: 3365; Percent complete: 84.1%; Average loss: 2.6650Iteration: 3366; Percent complete: 84.2%; Average loss: 3.0381Iteration: 3367; Percent complete: 84.2%; Average loss: 2.5793Iteration: 3368; Percent complete: 84.2%; Average loss: 2.8422Iteration: 3369; Percent complete: 84.2%; Average loss: 2.7794Iteration: 3370; Percent complete: 84.2%; Average loss: 2.9170Iteration: 3371; Percent complete: 84.3%; Average loss: 2.7929Iteration: 3372; Percent complete: 84.3%; Average loss: 2.6542Iteration: 3373; Percent complete: 84.3%; Average loss: 2.7768Iteration: 3374; Percent complete: 84.4%; Average loss: 2.7498Iteration: 3375; Percent complete: 84.4%; Average loss: 2.5922Iteration: 3376; Percent complete: 84.4%; Average loss: 2.5564Iteration: 3377; Percent complete: 84.4%; Average loss: 2.8590Iteration: 3378; Percent complete: 84.5%; Average loss: 2.5549Iteration: 3379; Percent complete: 84.5%; Average loss: 2.7124Iteration: 3380; Percent complete: 84.5%; Average loss: 3.0262Iteration: 3381; Percent complete: 84.5%; Average loss: 2.6700Iteration: 3382; Percent complete: 84.5%; Average loss: 2.6654Iteration: 3383; Percent complete: 84.6%; Average loss: 2.8298Iteration: 3384; Percent complete: 84.6%; Average loss: 2.8828Iteration: 3385; Percent complete: 84.6%; Average loss: 2.8595Iteration: 3386; Percent complete: 84.7%; Average loss: 2.9535Iteration: 3387; Percent complete: 84.7%; Average loss: 2.6943Iteration: 3388; Percent complete: 84.7%; Average loss: 2.5959Iteration: 3389; Percent complete: 84.7%; Average loss: 2.8483Iteration: 3390; Percent complete: 84.8%; Average loss: 2.8736Iteration: 3391; Percent complete: 84.8%; Average loss: 2.8062Iteration: 3392; Percent complete: 84.8%; Average loss: 2.6624Iteration: 3393; Percent complete: 84.8%; Average loss: 2.9625Iteration: 3394; Percent complete: 84.9%; Average loss: 2.6475Iteration: 3395; Percent complete: 84.9%; Average loss: 2.6649Iteration: 3396; Percent complete: 84.9%; Average loss: 2.6500Iteration: 3397; Percent complete: 84.9%; Average loss: 2.6999Iteration: 3398; Percent complete: 85.0%; Average loss: 2.6004Iteration: 3399; Percent complete: 85.0%; Average loss: 2.7684Iteration: 3400; Percent complete: 85.0%; Average loss: 2.8418Iteration: 3401; Percent complete: 85.0%; Average loss: 2.8936Iteration: 3402; Percent complete: 85.0%; Average loss: 2.7652Iteration: 3403; Percent complete: 85.1%; Average loss: 2.9072Iteration: 3404; Percent complete: 85.1%; Average loss: 2.6819Iteration: 3405; Percent complete: 85.1%; Average loss: 2.8973Iteration: 3406; Percent complete: 85.2%; Average loss: 2.8362Iteration: 3407; Percent complete: 85.2%; Average loss: 2.6720Iteration: 3408; Percent complete: 85.2%; Average loss: 2.6302Iteration: 3409; Percent complete: 85.2%; Average loss: 2.6947Iteration: 3410; Percent complete: 85.2%; Average loss: 2.6399Iteration: 3411; Percent complete: 85.3%; Average loss: 2.8657Iteration: 3412; Percent complete: 85.3%; Average loss: 2.6508Iteration: 3413; Percent complete: 85.3%; Average loss: 2.5536Iteration: 3414; Percent complete: 85.4%; Average loss: 2.5364Iteration: 3415; Percent complete: 85.4%; Average loss: 2.9034Iteration: 3416; Percent complete: 85.4%; Average loss: 2.8874Iteration: 3417; Percent complete: 85.4%; Average loss: 2.7500Iteration: 3418; Percent complete: 85.5%; Average loss: 2.8323Iteration: 3419; Percent complete: 85.5%; Average loss: 2.6622Iteration: 3420; Percent complete: 85.5%; Average loss: 2.7073Iteration: 3421; Percent complete: 85.5%; Average loss: 2.9196Iteration: 3422; Percent complete: 85.5%; Average loss: 2.8490Iteration: 3423; Percent complete: 85.6%; Average loss: 2.7017Iteration: 3424; Percent complete: 85.6%; Average loss: 2.9119Iteration: 3425; Percent complete: 85.6%; Average loss: 2.7596Iteration: 3426; Percent complete: 85.7%; Average loss: 2.6157Iteration: 3427; Percent complete: 85.7%; Average loss: 2.6753Iteration: 3428; Percent complete: 85.7%; Average loss: 2.5919Iteration: 3429; Percent complete: 85.7%; Average loss: 2.4756Iteration: 3430; Percent complete: 85.8%; Average loss: 2.8078Iteration: 3431; Percent complete: 85.8%; Average loss: 2.6943Iteration: 3432; Percent complete: 85.8%; Average loss: 2.8011Iteration: 3433; Percent complete: 85.8%; Average loss: 2.6940Iteration: 3434; Percent complete: 85.9%; Average loss: 2.6011Iteration: 3435; Percent complete: 85.9%; Average loss: 2.6354Iteration: 3436; Percent complete: 85.9%; Average loss: 2.7264Iteration: 3437; Percent complete: 85.9%; Average loss: 2.6488Iteration: 3438; Percent complete: 86.0%; Average loss: 2.7312Iteration: 3439; Percent complete: 86.0%; Average loss: 2.7478Iteration: 3440; Percent complete: 86.0%; Average loss: 2.6421Iteration: 3441; Percent complete: 86.0%; Average loss: 2.6732Iteration: 3442; Percent complete: 86.1%; Average loss: 2.7196Iteration: 3443; Percent complete: 86.1%; Average loss: 2.8462Iteration: 3444; Percent complete: 86.1%; Average loss: 2.7582Iteration: 3445; Percent complete: 86.1%; Average loss: 2.5356Iteration: 3446; Percent complete: 86.2%; Average loss: 2.8401Iteration: 3447; Percent complete: 86.2%; Average loss: 2.8897Iteration: 3448; Percent complete: 86.2%; Average loss: 2.6684Iteration: 3449; Percent complete: 86.2%; Average loss: 2.8414Iteration: 3450; Percent complete: 86.2%; Average loss: 2.6977Iteration: 3451; Percent complete: 86.3%; Average loss: 2.7652Iteration: 3452; Percent complete: 86.3%; Average loss: 2.7211Iteration: 3453; Percent complete: 86.3%; Average loss: 2.8969Iteration: 3454; Percent complete: 86.4%; Average loss: 3.0403Iteration: 3455; Percent complete: 86.4%; Average loss: 2.5516Iteration: 3456; Percent complete: 86.4%; Average loss: 2.7218Iteration: 3457; Percent complete: 86.4%; Average loss: 2.6693Iteration: 3458; Percent complete: 86.5%; Average loss: 2.7050Iteration: 3459; Percent complete: 86.5%; Average loss: 2.7935Iteration: 3460; Percent complete: 86.5%; Average loss: 2.7399Iteration: 3461; Percent complete: 86.5%; Average loss: 2.8562Iteration: 3462; Percent complete: 86.6%; Average loss: 2.6435Iteration: 3463; Percent complete: 86.6%; Average loss: 2.5694Iteration: 3464; Percent complete: 86.6%; Average loss: 2.6611Iteration: 3465; Percent complete: 86.6%; Average loss: 2.7130Iteration: 3466; Percent complete: 86.7%; Average loss: 2.5907Iteration: 3467; Percent complete: 86.7%; Average loss: 2.6204Iteration: 3468; Percent complete: 86.7%; Average loss: 2.7445Iteration: 3469; Percent complete: 86.7%; Average loss: 2.5632Iteration: 3470; Percent complete: 86.8%; Average loss: 2.4806Iteration: 3471; Percent complete: 86.8%; Average loss: 2.7513Iteration: 3472; Percent complete: 86.8%; Average loss: 2.7590Iteration: 3473; Percent complete: 86.8%; Average loss: 2.6189Iteration: 3474; Percent complete: 86.9%; Average loss: 2.9661Iteration: 3475; Percent complete: 86.9%; Average loss: 2.9597Iteration: 3476; Percent complete: 86.9%; Average loss: 2.7872Iteration: 3477; Percent complete: 86.9%; Average loss: 2.6795Iteration: 3478; Percent complete: 87.0%; Average loss: 2.6413Iteration: 3479; Percent complete: 87.0%; Average loss: 2.7275Iteration: 3480; Percent complete: 87.0%; Average loss: 2.5688Iteration: 3481; Percent complete: 87.0%; Average loss: 2.7265Iteration: 3482; Percent complete: 87.1%; Average loss: 2.9719Iteration: 3483; Percent complete: 87.1%; Average loss: 2.9076Iteration: 3484; Percent complete: 87.1%; Average loss: 2.5567Iteration: 3485; Percent complete: 87.1%; Average loss: 2.7412Iteration: 3486; Percent complete: 87.2%; Average loss: 2.6455Iteration: 3487; Percent complete: 87.2%; Average loss: 2.9077Iteration: 3488; Percent complete: 87.2%; Average loss: 2.7935Iteration: 3489; Percent complete: 87.2%; Average loss: 2.7883Iteration: 3490; Percent complete: 87.2%; Average loss: 2.7326Iteration: 3491; Percent complete: 87.3%; Average loss: 2.8549Iteration: 3492; Percent complete: 87.3%; Average loss: 2.7588Iteration: 3493; Percent complete: 87.3%; Average loss: 2.8767Iteration: 3494; Percent complete: 87.4%; Average loss: 2.7017Iteration: 3495; Percent complete: 87.4%; Average loss: 3.0078Iteration: 3496; Percent complete: 87.4%; Average loss: 2.6120Iteration: 3497; Percent complete: 87.4%; Average loss: 2.8813Iteration: 3498; Percent complete: 87.5%; Average loss: 2.8323Iteration: 3499; Percent complete: 87.5%; Average loss: 2.8437Iteration: 3500; Percent complete: 87.5%; Average loss: 2.6999Iteration: 3501; Percent complete: 87.5%; Average loss: 2.7902Iteration: 3502; Percent complete: 87.5%; Average loss: 2.5967Iteration: 3503; Percent complete: 87.6%; Average loss: 2.7637Iteration: 3504; Percent complete: 87.6%; Average loss: 2.8620Iteration: 3505; Percent complete: 87.6%; Average loss: 2.7565Iteration: 3506; Percent complete: 87.6%; Average loss: 2.6878Iteration: 3507; Percent complete: 87.7%; Average loss: 3.0395Iteration: 3508; Percent complete: 87.7%; Average loss: 2.5446Iteration: 3509; Percent complete: 87.7%; Average loss: 2.5834Iteration: 3510; Percent complete: 87.8%; Average loss: 2.8374Iteration: 3511; Percent complete: 87.8%; Average loss: 2.5945Iteration: 3512; Percent complete: 87.8%; Average loss: 2.5418Iteration: 3513; Percent complete: 87.8%; Average loss: 2.6806Iteration: 3514; Percent complete: 87.8%; Average loss: 2.6809Iteration: 3515; Percent complete: 87.9%; Average loss: 2.7061Iteration: 3516; Percent complete: 87.9%; Average loss: 2.5845Iteration: 3517; Percent complete: 87.9%; Average loss: 2.8783Iteration: 3518; Percent complete: 87.9%; Average loss: 2.8438Iteration: 3519; Percent complete: 88.0%; Average loss: 2.8821Iteration: 3520; Percent complete: 88.0%; Average loss: 2.6596Iteration: 3521; Percent complete: 88.0%; Average loss: 2.8538Iteration: 3522; Percent complete: 88.0%; Average loss: 2.9693Iteration: 3523; Percent complete: 88.1%; Average loss: 2.7837Iteration: 3524; Percent complete: 88.1%; Average loss: 2.7444Iteration: 3525; Percent complete: 88.1%; Average loss: 3.0118Iteration: 3526; Percent complete: 88.1%; Average loss: 2.6087Iteration: 3527; Percent complete: 88.2%; Average loss: 3.0418Iteration: 3528; Percent complete: 88.2%; Average loss: 2.4687Iteration: 3529; Percent complete: 88.2%; Average loss: 2.7113Iteration: 3530; Percent complete: 88.2%; Average loss: 2.7996Iteration: 3531; Percent complete: 88.3%; Average loss: 2.8728Iteration: 3532; Percent complete: 88.3%; Average loss: 2.7468Iteration: 3533; Percent complete: 88.3%; Average loss: 2.7151Iteration: 3534; Percent complete: 88.3%; Average loss: 2.5994Iteration: 3535; Percent complete: 88.4%; Average loss: 2.7552Iteration: 3536; Percent complete: 88.4%; Average loss: 2.6547Iteration: 3537; Percent complete: 88.4%; Average loss: 2.8489Iteration: 3538; Percent complete: 88.4%; Average loss: 2.9150Iteration: 3539; Percent complete: 88.5%; Average loss: 2.6086Iteration: 3540; Percent complete: 88.5%; Average loss: 2.9318Iteration: 3541; Percent complete: 88.5%; Average loss: 2.8520Iteration: 3542; Percent complete: 88.5%; Average loss: 2.9594Iteration: 3543; Percent complete: 88.6%; Average loss: 2.7798Iteration: 3544; Percent complete: 88.6%; Average loss: 2.7345Iteration: 3545; Percent complete: 88.6%; Average loss: 2.6346Iteration: 3546; Percent complete: 88.6%; Average loss: 2.5831Iteration: 3547; Percent complete: 88.7%; Average loss: 2.7532Iteration: 3548; Percent complete: 88.7%; Average loss: 2.6435Iteration: 3549; Percent complete: 88.7%; Average loss: 2.7247Iteration: 3550; Percent complete: 88.8%; Average loss: 2.9731Iteration: 3551; Percent complete: 88.8%; Average loss: 2.9382Iteration: 3552; Percent complete: 88.8%; Average loss: 2.8991Iteration: 3553; Percent complete: 88.8%; Average loss: 2.7931Iteration: 3554; Percent complete: 88.8%; Average loss: 2.9214Iteration: 3555; Percent complete: 88.9%; Average loss: 2.6834Iteration: 3556; Percent complete: 88.9%; Average loss: 2.5871Iteration: 3557; Percent complete: 88.9%; Average loss: 3.0121Iteration: 3558; Percent complete: 88.9%; Average loss: 2.8818Iteration: 3559; Percent complete: 89.0%; Average loss: 2.9191Iteration: 3560; Percent complete: 89.0%; Average loss: 2.7674Iteration: 3561; Percent complete: 89.0%; Average loss: 2.6214Iteration: 3562; Percent complete: 89.0%; Average loss: 2.7227Iteration: 3563; Percent complete: 89.1%; Average loss: 2.9200Iteration: 3564; Percent complete: 89.1%; Average loss: 2.8446Iteration: 3565; Percent complete: 89.1%; Average loss: 2.6237Iteration: 3566; Percent complete: 89.1%; Average loss: 2.8918Iteration: 3567; Percent complete: 89.2%; Average loss: 2.9579Iteration: 3568; Percent complete: 89.2%; Average loss: 2.7773Iteration: 3569; Percent complete: 89.2%; Average loss: 2.7477Iteration: 3570; Percent complete: 89.2%; Average loss: 2.7277Iteration: 3571; Percent complete: 89.3%; Average loss: 2.9649Iteration: 3572; Percent complete: 89.3%; Average loss: 2.7897Iteration: 3573; Percent complete: 89.3%; Average loss: 2.8816Iteration: 3574; Percent complete: 89.3%; Average loss: 2.7086Iteration: 3575; Percent complete: 89.4%; Average loss: 2.5480Iteration: 3576; Percent complete: 89.4%; Average loss: 2.6838Iteration: 3577; Percent complete: 89.4%; Average loss: 2.4731Iteration: 3578; Percent complete: 89.5%; Average loss: 2.8113Iteration: 3579; Percent complete: 89.5%; Average loss: 2.6570Iteration: 3580; Percent complete: 89.5%; Average loss: 2.7444Iteration: 3581; Percent complete: 89.5%; Average loss: 2.6167Iteration: 3582; Percent complete: 89.5%; Average loss: 2.7363Iteration: 3583; Percent complete: 89.6%; Average loss: 2.4266Iteration: 3584; Percent complete: 89.6%; Average loss: 2.7327Iteration: 3585; Percent complete: 89.6%; Average loss: 2.5742Iteration: 3586; Percent complete: 89.6%; Average loss: 2.6104Iteration: 3587; Percent complete: 89.7%; Average loss: 2.8191Iteration: 3588; Percent complete: 89.7%; Average loss: 2.8862Iteration: 3589; Percent complete: 89.7%; Average loss: 2.6768Iteration: 3590; Percent complete: 89.8%; Average loss: 2.6467Iteration: 3591; Percent complete: 89.8%; Average loss: 2.6122Iteration: 3592; Percent complete: 89.8%; Average loss: 2.7347Iteration: 3593; Percent complete: 89.8%; Average loss: 2.9529Iteration: 3594; Percent complete: 89.8%; Average loss: 2.7697Iteration: 3595; Percent complete: 89.9%; Average loss: 2.7815Iteration: 3596; Percent complete: 89.9%; Average loss: 2.9244Iteration: 3597; Percent complete: 89.9%; Average loss: 2.6582Iteration: 3598; Percent complete: 90.0%; Average loss: 2.5851Iteration: 3599; Percent complete: 90.0%; Average loss: 2.7476Iteration: 3600; Percent complete: 90.0%; Average loss: 2.6965Iteration: 3601; Percent complete: 90.0%; Average loss: 2.7647Iteration: 3602; Percent complete: 90.0%; Average loss: 2.7360Iteration: 3603; Percent complete: 90.1%; Average loss: 2.5928Iteration: 3604; Percent complete: 90.1%; Average loss: 2.9503Iteration: 3605; Percent complete: 90.1%; Average loss: 2.7086Iteration: 3606; Percent complete: 90.1%; Average loss: 2.7276Iteration: 3607; Percent complete: 90.2%; Average loss: 2.7422Iteration: 3608; Percent complete: 90.2%; Average loss: 2.5780Iteration: 3609; Percent complete: 90.2%; Average loss: 2.6110Iteration: 3610; Percent complete: 90.2%; Average loss: 2.7220Iteration: 3611; Percent complete: 90.3%; Average loss: 2.6561Iteration: 3612; Percent complete: 90.3%; Average loss: 2.8663Iteration: 3613; Percent complete: 90.3%; Average loss: 2.6072Iteration: 3614; Percent complete: 90.3%; Average loss: 2.6454Iteration: 3615; Percent complete: 90.4%; Average loss: 2.6188Iteration: 3616; Percent complete: 90.4%; Average loss: 2.6172Iteration: 3617; Percent complete: 90.4%; Average loss: 2.6485Iteration: 3618; Percent complete: 90.5%; Average loss: 2.5841Iteration: 3619; Percent complete: 90.5%; Average loss: 2.4991Iteration: 3620; Percent complete: 90.5%; Average loss: 2.8375Iteration: 3621; Percent complete: 90.5%; Average loss: 2.9891Iteration: 3622; Percent complete: 90.5%; Average loss: 2.5736Iteration: 3623; Percent complete: 90.6%; Average loss: 2.6689Iteration: 3624; Percent complete: 90.6%; Average loss: 2.6697Iteration: 3625; Percent complete: 90.6%; Average loss: 2.7385Iteration: 3626; Percent complete: 90.6%; Average loss: 2.6746Iteration: 3627; Percent complete: 90.7%; Average loss: 2.4139Iteration: 3628; Percent complete: 90.7%; Average loss: 2.9540Iteration: 3629; Percent complete: 90.7%; Average loss: 2.7738Iteration: 3630; Percent complete: 90.8%; Average loss: 2.7902Iteration: 3631; Percent complete: 90.8%; Average loss: 2.4355Iteration: 3632; Percent complete: 90.8%; Average loss: 2.8662Iteration: 3633; Percent complete: 90.8%; Average loss: 2.9874Iteration: 3634; Percent complete: 90.8%; Average loss: 2.7439Iteration: 3635; Percent complete: 90.9%; Average loss: 2.6461Iteration: 3636; Percent complete: 90.9%; Average loss: 2.6615Iteration: 3637; Percent complete: 90.9%; Average loss: 2.8372Iteration: 3638; Percent complete: 91.0%; Average loss: 2.8628Iteration: 3639; Percent complete: 91.0%; Average loss: 2.8371Iteration: 3640; Percent complete: 91.0%; Average loss: 2.6483Iteration: 3641; Percent complete: 91.0%; Average loss: 2.5336Iteration: 3642; Percent complete: 91.0%; Average loss: 2.8295Iteration: 3643; Percent complete: 91.1%; Average loss: 2.7454Iteration: 3644; Percent complete: 91.1%; Average loss: 2.5288Iteration: 3645; Percent complete: 91.1%; Average loss: 2.9867Iteration: 3646; Percent complete: 91.1%; Average loss: 2.6999Iteration: 3647; Percent complete: 91.2%; Average loss: 2.7001Iteration: 3648; Percent complete: 91.2%; Average loss: 2.6417Iteration: 3649; Percent complete: 91.2%; Average loss: 2.7845Iteration: 3650; Percent complete: 91.2%; Average loss: 2.4415Iteration: 3651; Percent complete: 91.3%; Average loss: 2.7730Iteration: 3652; Percent complete: 91.3%; Average loss: 2.6791Iteration: 3653; Percent complete: 91.3%; Average loss: 2.6183Iteration: 3654; Percent complete: 91.3%; Average loss: 2.8281Iteration: 3655; Percent complete: 91.4%; Average loss: 2.7096Iteration: 3656; Percent complete: 91.4%; Average loss: 2.5970Iteration: 3657; Percent complete: 91.4%; Average loss: 2.7527Iteration: 3658; Percent complete: 91.5%; Average loss: 2.6894Iteration: 3659; Percent complete: 91.5%; Average loss: 2.6093Iteration: 3660; Percent complete: 91.5%; Average loss: 2.7567Iteration: 3661; Percent complete: 91.5%; Average loss: 2.7096Iteration: 3662; Percent complete: 91.5%; Average loss: 2.6950Iteration: 3663; Percent complete: 91.6%; Average loss: 2.8530Iteration: 3664; Percent complete: 91.6%; Average loss: 2.6495Iteration: 3665; Percent complete: 91.6%; Average loss: 2.9393Iteration: 3666; Percent complete: 91.6%; Average loss: 2.6079Iteration: 3667; Percent complete: 91.7%; Average loss: 2.7802Iteration: 3668; Percent complete: 91.7%; Average loss: 2.5308Iteration: 3669; Percent complete: 91.7%; Average loss: 2.6307Iteration: 3670; Percent complete: 91.8%; Average loss: 2.5985Iteration: 3671; Percent complete: 91.8%; Average loss: 2.7377Iteration: 3672; Percent complete: 91.8%; Average loss: 2.8275Iteration: 3673; Percent complete: 91.8%; Average loss: 2.5423Iteration: 3674; Percent complete: 91.8%; Average loss: 2.8655Iteration: 3675; Percent complete: 91.9%; Average loss: 2.6001Iteration: 3676; Percent complete: 91.9%; Average loss: 2.6727Iteration: 3677; Percent complete: 91.9%; Average loss: 2.6383Iteration: 3678; Percent complete: 92.0%; Average loss: 2.5541Iteration: 3679; Percent complete: 92.0%; Average loss: 2.9775Iteration: 3680; Percent complete: 92.0%; Average loss: 2.5630Iteration: 3681; Percent complete: 92.0%; Average loss: 2.7679Iteration: 3682; Percent complete: 92.0%; Average loss: 2.4726Iteration: 3683; Percent complete: 92.1%; Average loss: 2.7183Iteration: 3684; Percent complete: 92.1%; Average loss: 2.7493Iteration: 3685; Percent complete: 92.1%; Average loss: 2.2568Iteration: 3686; Percent complete: 92.2%; Average loss: 2.7957Iteration: 3687; Percent complete: 92.2%; Average loss: 3.0499Iteration: 3688; Percent complete: 92.2%; Average loss: 2.4311Iteration: 3689; Percent complete: 92.2%; Average loss: 2.4076Iteration: 3690; Percent complete: 92.2%; Average loss: 2.8730Iteration: 3691; Percent complete: 92.3%; Average loss: 2.9451Iteration: 3692; Percent complete: 92.3%; Average loss: 2.5903Iteration: 3693; Percent complete: 92.3%; Average loss: 2.9505Iteration: 3694; Percent complete: 92.3%; Average loss: 2.7531Iteration: 3695; Percent complete: 92.4%; Average loss: 3.1360Iteration: 3696; Percent complete: 92.4%; Average loss: 2.5436Iteration: 3697; Percent complete: 92.4%; Average loss: 2.6408Iteration: 3698; Percent complete: 92.5%; Average loss: 2.5578Iteration: 3699; Percent complete: 92.5%; Average loss: 2.8016Iteration: 3700; Percent complete: 92.5%; Average loss: 2.8416Iteration: 3701; Percent complete: 92.5%; Average loss: 2.5087Iteration: 3702; Percent complete: 92.5%; Average loss: 2.5718Iteration: 3703; Percent complete: 92.6%; Average loss: 2.7516Iteration: 3704; Percent complete: 92.6%; Average loss: 2.5927Iteration: 3705; Percent complete: 92.6%; Average loss: 2.4466Iteration: 3706; Percent complete: 92.7%; Average loss: 2.6214Iteration: 3707; Percent complete: 92.7%; Average loss: 2.7981Iteration: 3708; Percent complete: 92.7%; Average loss: 2.5368Iteration: 3709; Percent complete: 92.7%; Average loss: 2.8735Iteration: 3710; Percent complete: 92.8%; Average loss: 2.7763Iteration: 3711; Percent complete: 92.8%; Average loss: 2.5895Iteration: 3712; Percent complete: 92.8%; Average loss: 2.5489Iteration: 3713; Percent complete: 92.8%; Average loss: 2.5438Iteration: 3714; Percent complete: 92.8%; Average loss: 2.5967Iteration: 3715; Percent complete: 92.9%; Average loss: 2.6169Iteration: 3716; Percent complete: 92.9%; Average loss: 2.4558Iteration: 3717; Percent complete: 92.9%; Average loss: 2.7583Iteration: 3718; Percent complete: 93.0%; Average loss: 2.6875Iteration: 3719; Percent complete: 93.0%; Average loss: 2.7560Iteration: 3720; Percent complete: 93.0%; Average loss: 2.6825Iteration: 3721; Percent complete: 93.0%; Average loss: 2.5325Iteration: 3722; Percent complete: 93.0%; Average loss: 2.6424Iteration: 3723; Percent complete: 93.1%; Average loss: 2.6581Iteration: 3724; Percent complete: 93.1%; Average loss: 2.5011Iteration: 3725; Percent complete: 93.1%; Average loss: 2.8894Iteration: 3726; Percent complete: 93.2%; Average loss: 2.7340Iteration: 3727; Percent complete: 93.2%; Average loss: 2.5976Iteration: 3728; Percent complete: 93.2%; Average loss: 2.8053Iteration: 3729; Percent complete: 93.2%; Average loss: 2.6624Iteration: 3730; Percent complete: 93.2%; Average loss: 2.6046Iteration: 3731; Percent complete: 93.3%; Average loss: 2.5017Iteration: 3732; Percent complete: 93.3%; Average loss: 2.6339Iteration: 3733; Percent complete: 93.3%; Average loss: 2.6814Iteration: 3734; Percent complete: 93.3%; Average loss: 2.6579Iteration: 3735; Percent complete: 93.4%; Average loss: 2.5978Iteration: 3736; Percent complete: 93.4%; Average loss: 2.9092Iteration: 3737; Percent complete: 93.4%; Average loss: 2.4497Iteration: 3738; Percent complete: 93.5%; Average loss: 2.8230Iteration: 3739; Percent complete: 93.5%; Average loss: 2.7689Iteration: 3740; Percent complete: 93.5%; Average loss: 2.7932Iteration: 3741; Percent complete: 93.5%; Average loss: 2.3966Iteration: 3742; Percent complete: 93.5%; Average loss: 2.6276Iteration: 3743; Percent complete: 93.6%; Average loss: 2.8120Iteration: 3744; Percent complete: 93.6%; Average loss: 2.6189Iteration: 3745; Percent complete: 93.6%; Average loss: 2.6839Iteration: 3746; Percent complete: 93.7%; Average loss: 2.6939Iteration: 3747; Percent complete: 93.7%; Average loss: 2.5294Iteration: 3748; Percent complete: 93.7%; Average loss: 2.9118Iteration: 3749; Percent complete: 93.7%; Average loss: 2.7792Iteration: 3750; Percent complete: 93.8%; Average loss: 2.7231Iteration: 3751; Percent complete: 93.8%; Average loss: 2.5396Iteration: 3752; Percent complete: 93.8%; Average loss: 2.4460Iteration: 3753; Percent complete: 93.8%; Average loss: 2.7601Iteration: 3754; Percent complete: 93.8%; Average loss: 2.4582Iteration: 3755; Percent complete: 93.9%; Average loss: 2.5843Iteration: 3756; Percent complete: 93.9%; Average loss: 2.6371Iteration: 3757; Percent complete: 93.9%; Average loss: 2.7001Iteration: 3758; Percent complete: 94.0%; Average loss: 2.3796Iteration: 3759; Percent complete: 94.0%; Average loss: 2.7185Iteration: 3760; Percent complete: 94.0%; Average loss: 2.6447Iteration: 3761; Percent complete: 94.0%; Average loss: 2.6863Iteration: 3762; Percent complete: 94.0%; Average loss: 2.8426Iteration: 3763; Percent complete: 94.1%; Average loss: 2.7108Iteration: 3764; Percent complete: 94.1%; Average loss: 2.6015Iteration: 3765; Percent complete: 94.1%; Average loss: 2.6973Iteration: 3766; Percent complete: 94.2%; Average loss: 2.8001Iteration: 3767; Percent complete: 94.2%; Average loss: 2.3891Iteration: 3768; Percent complete: 94.2%; Average loss: 2.6042Iteration: 3769; Percent complete: 94.2%; Average loss: 2.9498Iteration: 3770; Percent complete: 94.2%; Average loss: 2.9139Iteration: 3771; Percent complete: 94.3%; Average loss: 2.7375Iteration: 3772; Percent complete: 94.3%; Average loss: 2.5760Iteration: 3773; Percent complete: 94.3%; Average loss: 2.7647Iteration: 3774; Percent complete: 94.3%; Average loss: 2.7539Iteration: 3775; Percent complete: 94.4%; Average loss: 2.7910Iteration: 3776; Percent complete: 94.4%; Average loss: 2.4891Iteration: 3777; Percent complete: 94.4%; Average loss: 2.7445Iteration: 3778; Percent complete: 94.5%; Average loss: 2.7339Iteration: 3779; Percent complete: 94.5%; Average loss: 2.6373Iteration: 3780; Percent complete: 94.5%; Average loss: 2.8488Iteration: 3781; Percent complete: 94.5%; Average loss: 2.5968Iteration: 3782; Percent complete: 94.5%; Average loss: 2.7535Iteration: 3783; Percent complete: 94.6%; Average loss: 2.6355Iteration: 3784; Percent complete: 94.6%; Average loss: 2.6338Iteration: 3785; Percent complete: 94.6%; Average loss: 2.7173Iteration: 3786; Percent complete: 94.7%; Average loss: 2.8115Iteration: 3787; Percent complete: 94.7%; Average loss: 2.4762Iteration: 3788; Percent complete: 94.7%; Average loss: 2.7264Iteration: 3789; Percent complete: 94.7%; Average loss: 2.6231Iteration: 3790; Percent complete: 94.8%; Average loss: 2.5545Iteration: 3791; Percent complete: 94.8%; Average loss: 2.6700Iteration: 3792; Percent complete: 94.8%; Average loss: 2.5802Iteration: 3793; Percent complete: 94.8%; Average loss: 2.6268Iteration: 3794; Percent complete: 94.8%; Average loss: 2.7600Iteration: 3795; Percent complete: 94.9%; Average loss: 2.6410Iteration: 3796; Percent complete: 94.9%; Average loss: 2.4489Iteration: 3797; Percent complete: 94.9%; Average loss: 2.6256Iteration: 3798; Percent complete: 95.0%; Average loss: 2.5027Iteration: 3799; Percent complete: 95.0%; Average loss: 2.7256Iteration: 3800; Percent complete: 95.0%; Average loss: 2.5804Iteration: 3801; Percent complete: 95.0%; Average loss: 2.6291Iteration: 3802; Percent complete: 95.0%; Average loss: 2.6540Iteration: 3803; Percent complete: 95.1%; Average loss: 2.5494Iteration: 3804; Percent complete: 95.1%; Average loss: 2.6153Iteration: 3805; Percent complete: 95.1%; Average loss: 2.4604Iteration: 3806; Percent complete: 95.2%; Average loss: 2.4775Iteration: 3807; Percent complete: 95.2%; Average loss: 2.5052Iteration: 3808; Percent complete: 95.2%; Average loss: 2.7440Iteration: 3809; Percent complete: 95.2%; Average loss: 2.6917Iteration: 3810; Percent complete: 95.2%; Average loss: 2.7146Iteration: 3811; Percent complete: 95.3%; Average loss: 2.6879Iteration: 3812; Percent complete: 95.3%; Average loss: 2.8053Iteration: 3813; Percent complete: 95.3%; Average loss: 2.6715Iteration: 3814; Percent complete: 95.3%; Average loss: 2.7538Iteration: 3815; Percent complete: 95.4%; Average loss: 2.9519Iteration: 3816; Percent complete: 95.4%; Average loss: 2.4258Iteration: 3817; Percent complete: 95.4%; Average loss: 2.6715Iteration: 3818; Percent complete: 95.5%; Average loss: 2.5647Iteration: 3819; Percent complete: 95.5%; Average loss: 2.5399Iteration: 3820; Percent complete: 95.5%; Average loss: 2.7257Iteration: 3821; Percent complete: 95.5%; Average loss: 2.5309Iteration: 3822; Percent complete: 95.5%; Average loss: 2.3913Iteration: 3823; Percent complete: 95.6%; Average loss: 2.5623Iteration: 3824; Percent complete: 95.6%; Average loss: 2.5528Iteration: 3825; Percent complete: 95.6%; Average loss: 2.6006Iteration: 3826; Percent complete: 95.7%; Average loss: 2.5261Iteration: 3827; Percent complete: 95.7%; Average loss: 2.7419Iteration: 3828; Percent complete: 95.7%; Average loss: 2.7327Iteration: 3829; Percent complete: 95.7%; Average loss: 2.5286Iteration: 3830; Percent complete: 95.8%; Average loss: 2.6300Iteration: 3831; Percent complete: 95.8%; Average loss: 2.6292Iteration: 3832; Percent complete: 95.8%; Average loss: 2.7109Iteration: 3833; Percent complete: 95.8%; Average loss: 2.6891Iteration: 3834; Percent complete: 95.9%; Average loss: 2.6458Iteration: 3835; Percent complete: 95.9%; Average loss: 2.7185Iteration: 3836; Percent complete: 95.9%; Average loss: 2.7819Iteration: 3837; Percent complete: 95.9%; Average loss: 2.9305Iteration: 3838; Percent complete: 96.0%; Average loss: 2.5474Iteration: 3839; Percent complete: 96.0%; Average loss: 2.5746Iteration: 3840; Percent complete: 96.0%; Average loss: 2.6555Iteration: 3841; Percent complete: 96.0%; Average loss: 2.8002Iteration: 3842; Percent complete: 96.0%; Average loss: 3.0145Iteration: 3843; Percent complete: 96.1%; Average loss: 2.6843Iteration: 3844; Percent complete: 96.1%; Average loss: 2.7259Iteration: 3845; Percent complete: 96.1%; Average loss: 2.5957Iteration: 3846; Percent complete: 96.2%; Average loss: 2.6648Iteration: 3847; Percent complete: 96.2%; Average loss: 2.5444Iteration: 3848; Percent complete: 96.2%; Average loss: 2.4706Iteration: 3849; Percent complete: 96.2%; Average loss: 2.4037Iteration: 3850; Percent complete: 96.2%; Average loss: 2.8534Iteration: 3851; Percent complete: 96.3%; Average loss: 2.6835Iteration: 3852; Percent complete: 96.3%; Average loss: 2.6534Iteration: 3853; Percent complete: 96.3%; Average loss: 2.5461Iteration: 3854; Percent complete: 96.4%; Average loss: 2.5379Iteration: 3855; Percent complete: 96.4%; Average loss: 2.7815Iteration: 3856; Percent complete: 96.4%; Average loss: 2.7132Iteration: 3857; Percent complete: 96.4%; Average loss: 2.6906Iteration: 3858; Percent complete: 96.5%; Average loss: 2.6559Iteration: 3859; Percent complete: 96.5%; Average loss: 2.6858Iteration: 3860; Percent complete: 96.5%; Average loss: 2.6408Iteration: 3861; Percent complete: 96.5%; Average loss: 2.5946Iteration: 3862; Percent complete: 96.5%; Average loss: 2.4838Iteration: 3863; Percent complete: 96.6%; Average loss: 2.6571Iteration: 3864; Percent complete: 96.6%; Average loss: 2.5970Iteration: 3865; Percent complete: 96.6%; Average loss: 2.7227Iteration: 3866; Percent complete: 96.7%; Average loss: 2.6848Iteration: 3867; Percent complete: 96.7%; Average loss: 2.9051Iteration: 3868; Percent complete: 96.7%; Average loss: 2.6828Iteration: 3869; Percent complete: 96.7%; Average loss: 2.5392Iteration: 3870; Percent complete: 96.8%; Average loss: 2.4545Iteration: 3871; Percent complete: 96.8%; Average loss: 2.7665Iteration: 3872; Percent complete: 96.8%; Average loss: 2.6516Iteration: 3873; Percent complete: 96.8%; Average loss: 2.5422Iteration: 3874; Percent complete: 96.9%; Average loss: 2.6578Iteration: 3875; Percent complete: 96.9%; Average loss: 2.6143Iteration: 3876; Percent complete: 96.9%; Average loss: 2.5596Iteration: 3877; Percent complete: 96.9%; Average loss: 2.6615Iteration: 3878; Percent complete: 97.0%; Average loss: 2.7480Iteration: 3879; Percent complete: 97.0%; Average loss: 2.5483Iteration: 3880; Percent complete: 97.0%; Average loss: 2.8031Iteration: 3881; Percent complete: 97.0%; Average loss: 2.7845Iteration: 3882; Percent complete: 97.0%; Average loss: 2.9314Iteration: 3883; Percent complete: 97.1%; Average loss: 2.7137Iteration: 3884; Percent complete: 97.1%; Average loss: 2.5847Iteration: 3885; Percent complete: 97.1%; Average loss: 2.5767Iteration: 3886; Percent complete: 97.2%; Average loss: 2.7125Iteration: 3887; Percent complete: 97.2%; Average loss: 2.4914Iteration: 3888; Percent complete: 97.2%; Average loss: 2.4217Iteration: 3889; Percent complete: 97.2%; Average loss: 2.6207Iteration: 3890; Percent complete: 97.2%; Average loss: 2.6245Iteration: 3891; Percent complete: 97.3%; Average loss: 2.5659Iteration: 3892; Percent complete: 97.3%; Average loss: 2.4425Iteration: 3893; Percent complete: 97.3%; Average loss: 2.5936Iteration: 3894; Percent complete: 97.4%; Average loss: 2.6715Iteration: 3895; Percent complete: 97.4%; Average loss: 2.4515Iteration: 3896; Percent complete: 97.4%; Average loss: 2.6394Iteration: 3897; Percent complete: 97.4%; Average loss: 2.6741Iteration: 3898; Percent complete: 97.5%; Average loss: 2.6650Iteration: 3899; Percent complete: 97.5%; Average loss: 2.8173Iteration: 3900; Percent complete: 97.5%; Average loss: 2.4765Iteration: 3901; Percent complete: 97.5%; Average loss: 2.6503Iteration: 3902; Percent complete: 97.5%; Average loss: 2.5180Iteration: 3903; Percent complete: 97.6%; Average loss: 2.6335Iteration: 3904; Percent complete: 97.6%; Average loss: 2.7138Iteration: 3905; Percent complete: 97.6%; Average loss: 2.7969Iteration: 3906; Percent complete: 97.7%; Average loss: 2.7600Iteration: 3907; Percent complete: 97.7%; Average loss: 2.7332Iteration: 3908; Percent complete: 97.7%; Average loss: 2.5120Iteration: 3909; Percent complete: 97.7%; Average loss: 2.6500Iteration: 3910; Percent complete: 97.8%; Average loss: 2.6272Iteration: 3911; Percent complete: 97.8%; Average loss: 2.7586Iteration: 3912; Percent complete: 97.8%; Average loss: 2.8686Iteration: 3913; Percent complete: 97.8%; Average loss: 2.5038Iteration: 3914; Percent complete: 97.9%; Average loss: 2.3052Iteration: 3915; Percent complete: 97.9%; Average loss: 2.6093Iteration: 3916; Percent complete: 97.9%; Average loss: 2.7208Iteration: 3917; Percent complete: 97.9%; Average loss: 2.7261Iteration: 3918; Percent complete: 98.0%; Average loss: 2.6017Iteration: 3919; Percent complete: 98.0%; Average loss: 2.5675Iteration: 3920; Percent complete: 98.0%; Average loss: 2.5596Iteration: 3921; Percent complete: 98.0%; Average loss: 2.7163Iteration: 3922; Percent complete: 98.0%; Average loss: 2.6231Iteration: 3923; Percent complete: 98.1%; Average loss: 2.6944Iteration: 3924; Percent complete: 98.1%; Average loss: 2.3871Iteration: 3925; Percent complete: 98.1%; Average loss: 2.5862Iteration: 3926; Percent complete: 98.2%; Average loss: 2.7340Iteration: 3927; Percent complete: 98.2%; Average loss: 2.3263Iteration: 3928; Percent complete: 98.2%; Average loss: 2.6027Iteration: 3929; Percent complete: 98.2%; Average loss: 2.6757Iteration: 3930; Percent complete: 98.2%; Average loss: 2.7221Iteration: 3931; Percent complete: 98.3%; Average loss: 2.7570Iteration: 3932; Percent complete: 98.3%; Average loss: 2.5692Iteration: 3933; Percent complete: 98.3%; Average loss: 2.5586Iteration: 3934; Percent complete: 98.4%; Average loss: 2.7850Iteration: 3935; Percent complete: 98.4%; Average loss: 2.7019Iteration: 3936; Percent complete: 98.4%; Average loss: 2.6292Iteration: 3937; Percent complete: 98.4%; Average loss: 2.7480Iteration: 3938; Percent complete: 98.5%; Average loss: 2.7671Iteration: 3939; Percent complete: 98.5%; Average loss: 2.5684Iteration: 3940; Percent complete: 98.5%; Average loss: 2.4672Iteration: 3941; Percent complete: 98.5%; Average loss: 2.5685Iteration: 3942; Percent complete: 98.6%; Average loss: 2.3637Iteration: 3943; Percent complete: 98.6%; Average loss: 2.6921Iteration: 3944; Percent complete: 98.6%; Average loss: 2.5522Iteration: 3945; Percent complete: 98.6%; Average loss: 2.4589Iteration: 3946; Percent complete: 98.7%; Average loss: 2.7159Iteration: 3947; Percent complete: 98.7%; Average loss: 2.3967Iteration: 3948; Percent complete: 98.7%; Average loss: 2.7828Iteration: 3949; Percent complete: 98.7%; Average loss: 2.4329Iteration: 3950; Percent complete: 98.8%; Average loss: 2.8618Iteration: 3951; Percent complete: 98.8%; Average loss: 2.7402Iteration: 3952; Percent complete: 98.8%; Average loss: 2.4842Iteration: 3953; Percent complete: 98.8%; Average loss: 2.6892Iteration: 3954; Percent complete: 98.9%; Average loss: 2.7283Iteration: 3955; Percent complete: 98.9%; Average loss: 2.7701Iteration: 3956; Percent complete: 98.9%; Average loss: 2.8278Iteration: 3957; Percent complete: 98.9%; Average loss: 2.4877Iteration: 3958; Percent complete: 99.0%; Average loss: 2.6255Iteration: 3959; Percent complete: 99.0%; Average loss: 2.5936Iteration: 3960; Percent complete: 99.0%; Average loss: 2.5287Iteration: 3961; Percent complete: 99.0%; Average loss: 2.7331Iteration: 3962; Percent complete: 99.1%; Average loss: 2.6277Iteration: 3963; Percent complete: 99.1%; Average loss: 2.6045Iteration: 3964; Percent complete: 99.1%; Average loss: 2.4580Iteration: 3965; Percent complete: 99.1%; Average loss: 2.5699Iteration: 3966; Percent complete: 99.2%; Average loss: 2.6613Iteration: 3967; Percent complete: 99.2%; Average loss: 2.4294Iteration: 3968; Percent complete: 99.2%; Average loss: 2.6265Iteration: 3969; Percent complete: 99.2%; Average loss: 2.6986Iteration: 3970; Percent complete: 99.2%; Average loss: 2.5936Iteration: 3971; Percent complete: 99.3%; Average loss: 2.5685Iteration: 3972; Percent complete: 99.3%; Average loss: 2.6609Iteration: 3973; Percent complete: 99.3%; Average loss: 2.5549Iteration: 3974; Percent complete: 99.4%; Average loss: 2.6534Iteration: 3975; Percent complete: 99.4%; Average loss: 2.6924Iteration: 3976; Percent complete: 99.4%; Average loss: 2.5701Iteration: 3977; Percent complete: 99.4%; Average loss: 2.5068Iteration: 3978; Percent complete: 99.5%; Average loss: 2.7295Iteration: 3979; Percent complete: 99.5%; Average loss: 2.8068Iteration: 3980; Percent complete: 99.5%; Average loss: 2.8939Iteration: 3981; Percent complete: 99.5%; Average loss: 2.7198Iteration: 3982; Percent complete: 99.6%; Average loss: 2.7092Iteration: 3983; Percent complete: 99.6%; Average loss: 2.7277Iteration: 3984; Percent complete: 99.6%; Average loss: 2.5092Iteration: 3985; Percent complete: 99.6%; Average loss: 2.6994Iteration: 3986; Percent complete: 99.7%; Average loss: 2.5774Iteration: 3987; Percent complete: 99.7%; Average loss: 2.6884Iteration: 3988; Percent complete: 99.7%; Average loss: 2.9172Iteration: 3989; Percent complete: 99.7%; Average loss: 2.7558Iteration: 3990; Percent complete: 99.8%; Average loss: 2.6956Iteration: 3991; Percent complete: 99.8%; Average loss: 2.5077Iteration: 3992; Percent complete: 99.8%; Average loss: 2.6667Iteration: 3993; Percent complete: 99.8%; Average loss: 2.6748Iteration: 3994; Percent complete: 99.9%; Average loss: 2.4651Iteration: 3995; Percent complete: 99.9%; Average loss: 2.6372Iteration: 3996; Percent complete: 99.9%; Average loss: 2.6633Iteration: 3997; Percent complete: 99.9%; Average loss: 2.5944Iteration: 3998; Percent complete: 100.0%; Average loss: 2.5219Iteration: 3999; Percent complete: 100.0%; Average loss: 2.8060Iteration: 4000; Percent complete: 100.0%; Average loss: 2.6751

Run Evaluation

To chat with your model, run the following block.

# Set dropout layers to eval modeencoder.eval()decoder.eval()# Initialize search modulesearcher = 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 thefundamentals to building a generative chatbot model! If you’reinterested, you can try tailoring the chatbot’s behavior by tweaking themodel and training parameters and customizing the data that you trainthe model on.

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

Total running time of the script: ( 5 minutes 48.806 seconds)

Gallery generated by Sphinx-Gallery

' document.getElementById("pytorch-article").insertAdjacentHTML('afterBegin', div) }

You might also like

Latest Posts

Article information

Author: Arline Emard IV

Last Updated: 07/15/2022

Views: 5769

Rating: 4.1 / 5 (72 voted)

Reviews: 95% of readers found this page helpful

Author information

Name: Arline Emard IV

Birthday: 1996-07-10

Address: 8912 Hintz Shore, West Louie, AZ 69363-0747

Phone: +13454700762376

Job: Administration Technician

Hobby: Paintball, Horseback riding, Cycling, Running, Macrame, Playing musical instruments, Soapmaking

Introduction: My name is Arline Emard IV, I am a cheerful, gorgeous, colorful, joyous, excited, super, inquisitive person who loves writing and wants to share my knowledge and understanding with you.