.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "beginner/chatbot_tutorial.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note Click :ref:`here ` to download the full example code .. rst-class:: sphx-glr-example-title .. _sphx_glr_beginner_chatbot_tutorial.py: Chatbot Tutorial ================ **Author:** `Matthew Inkawhich `_ .. GENERATED FROM PYTHON SOURCE LINES 11-81 In this tutorial, we explore a fun and interesting use-case of recurrent sequence-to-sequence models. We will train a simple chatbot using movie scripts from the `Cornell Movie-Dialogs Corpus `__. Conversational models are a hot topic in artificial intelligence research. Chatbots can be found in a variety of settings, including customer service applications and online helpdesks. These bots are often powered by retrieval-based models, which output predefined responses to questions of certain forms. In a highly restricted domain like a company’s IT helpdesk, these models may be sufficient, however, they are not robust enough for more general use-cases. Teaching a machine to carry out a meaningful conversation with a human in multiple domains is a research question that is far from solved. Recently, the deep learning boom has allowed for powerful generative models like Google’s `Neural Conversational Model `__, which marks a large step towards multi-domain generative conversational models. In this tutorial, we will implement this kind of model in PyTorch. .. figure:: /_static/img/chatbot/bot.png :align: center :alt: bot .. code-block:: python > hello? Bot: hello . > where am I? Bot: you re in a hospital . > who are you? Bot: i m a lawyer . > how are you doing? Bot: i m fine . > are you my friend? Bot: no . > you're under arrest Bot: i m trying to help you ! > i'm just kidding Bot: i m sorry . > where are you from? Bot: san francisco . > it's time for me to leave Bot: i know . > goodbye Bot: goodbye . **Tutorial Highlights** - Handle loading and preprocessing of `Cornell Movie-Dialogs Corpus `__ dataset - Implement a sequence-to-sequence model with `Luong attention mechanism(s) `__ - Jointly train encoder and decoder models using mini-batches - Implement greedy-search decoding module - Interact with trained chatbot **Acknowledgments** This tutorial borrows code from the following sources: 1) Yuan-Kuei Wu’s pytorch-chatbot implementation: 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 Cornell Movie Corpus preprocessing code: https://github.com/floydhub/textutil-preprocess-cornell-movie-corpus .. GENERATED FROM PYTHON SOURCE LINES 84-89 Preparations ------------ To start, Download the data ZIP file `here `__ .. GENERATED FROM PYTHON SOURCE LINES 89-116 .. code-block:: default # and put in a ``data/`` directory under the current directory. # # After that, let’s import some necessities. # import torch from torch.jit import script, trace import torch.nn as nn from torch import optim import torch.nn.functional as F import csv import random import re import os import unicodedata import codecs from io import open import itertools import math import json USE_CUDA = torch.cuda.is_available() device = torch.device("cuda" if USE_CUDA else "cpu") .. GENERATED FROM PYTHON SOURCE LINES 117-139 Load & Preprocess Data ---------------------- The next step is to reformat our data file and load the data into structures that we can work with. The `Cornell Movie-Dialogs Corpus `__ is a rich dataset of movie character dialog: - 220,579 conversational exchanges between 10,292 pairs of movie characters - 9,035 characters from 617 movies - 304,713 total utterances This dataset is large and diverse, and there is a great variation of language formality, time periods, sentiment, etc. Our hope is that this diversity makes our model robust to many forms of inputs and queries. First, we’ll take a look at some lines of our datafile to see the original format. .. GENERATED FROM PYTHON SOURCE LINES 139-152 .. code-block:: default 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")) .. rst-class:: sphx-glr-script-out .. code-block:: none 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' .. GENERATED FROM PYTHON SOURCE LINES 153-168 Create formatted data file ~~~~~~~~~~~~~~~~~~~~~~~~~~ For convenience, we'll create a nicely formatted data file in which each line contains a tab-separated *query sentence* and a *response sentence* pair. The following functions facilitate the parsing of the raw ``utterances.jsonl`` data file. - ``loadLinesAndConversations`` splits each line of the file into a dictionary of lines with fields: ``lineID``, ``characterID``, and text and then groups them into conversations with fields: ``conversationID``, ``movieID``, and lines. - ``extractSentencePairs`` extracts pairs of sentences from conversations .. GENERATED FROM PYTHON SOURCE LINES 168-211 .. code-block:: default # Splits each line of the file to create lines and conversations def loadLinesAndConversations(fileName): lines = {} conversations = {} with open(fileName, 'r', encoding='iso-8859-1') as f: for line in f: lineJson = json.loads(line) # Extract fields for line object lineObj = {} lineObj["lineID"] = lineJson["id"] lineObj["characterID"] = lineJson["speaker"] lineObj["text"] = lineJson["text"] lines[lineObj['lineID']] = lineObj # Extract fields for conversation object if lineJson["conversation_id"] not in conversations: convObj = {} convObj["conversationID"] = lineJson["conversation_id"] convObj["movieID"] = lineJson["meta"]["movie_id"] convObj["lines"] = [lineObj] else: convObj = conversations[lineJson["conversation_id"]] convObj["lines"].insert(0, lineObj) conversations[convObj["conversationID"]] = convObj return lines, conversations # Extracts pairs of sentences from conversations def extractSentencePairs(conversations): qa_pairs = [] for conversation in conversations.values(): # Iterate over all the lines of the conversation for i in range(len(conversation["lines"]) - 1): # We ignore the last line (no answer for it) inputLine = conversation["lines"][i]["text"].strip() targetLine = conversation["lines"][i+1]["text"].strip() # Filter wrong samples (if one of the lists is empty) if inputLine and targetLine: qa_pairs.append([inputLine, targetLine]) return qa_pairs .. GENERATED FROM PYTHON SOURCE LINES 212-215 Now we’ll call these functions and create the file. We’ll call it ``formatted_movie_lines.txt``. .. GENERATED FROM PYTHON SOURCE LINES 215-242 .. code-block:: default # Define path to new file datafile = os.path.join(corpus, "formatted_movie_lines.txt") delimiter = '\t' # Unescape the delimiter delimiter = str(codecs.decode(delimiter, "unicode_escape")) # Initialize lines dict and conversations dict lines = {} conversations = {} # Load lines and conversations print("\nProcessing corpus into lines and conversations...") lines, conversations = loadLinesAndConversations(os.path.join(corpus, "utterances.jsonl")) # Write new csv file print("\nWriting newly formatted file...") with open(datafile, 'w', encoding='utf-8') as outputfile: writer = csv.writer(outputfile, delimiter=delimiter, lineterminator='\n') for pair in extractSentencePairs(conversations): writer.writerow(pair) # Print a sample of lines print("\nSample lines from file:") printLines(datafile) .. rst-class:: sphx-glr-script-out .. code-block:: none 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" .. GENERATED FROM PYTHON SOURCE LINES 243-261 Load and trim data ~~~~~~~~~~~~~~~~~~ Our next order of business is to create a vocabulary and load query/response sentence pairs into memory. Note that we are dealing with sequences of **words**, which do not have an implicit mapping to a discrete numerical space. Thus, we must create one by mapping each unique word that we encounter in our dataset to an index value. For this we define a ``Voc`` class, which keeps a mapping from words to indexes, a reverse mapping of indexes to words, a count of each word and a total word count. The class provides methods for adding a word to the vocabulary (``addWord``), adding all words in a sentence (``addSentence``) and trimming infrequently seen words (``trim``). More on trimming later. .. GENERATED FROM PYTHON SOURCE LINES 261-315 .. code-block:: default # Default word tokens PAD_token = 0 # Used for padding short sentences SOS_token = 1 # Start-of-sentence token EOS_token = 2 # End-of-sentence token class Voc: def __init__(self, name): self.name = name self.trimmed = False self.word2index = {} self.word2count = {} self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"} self.num_words = 3 # Count SOS, EOS, PAD def addSentence(self, sentence): for word in sentence.split(' '): self.addWord(word) def addWord(self, word): if word not in self.word2index: self.word2index[word] = self.num_words self.word2count[word] = 1 self.index2word[self.num_words] = word self.num_words += 1 else: self.word2count[word] += 1 # Remove words below a certain count threshold def trim(self, min_count): if self.trimmed: return self.trimmed = True keep_words = [] for k, v in self.word2count.items(): if v >= min_count: keep_words.append(k) print('keep_words {} / {} = {:.4f}'.format( len(keep_words), len(self.word2index), len(keep_words) / len(self.word2index) )) # Reinitialize dictionaries self.word2index = {} self.word2count = {} self.index2word = {PAD_token: "PAD", SOS_token: "SOS", EOS_token: "EOS"} self.num_words = 3 # Count default tokens for word in keep_words: self.addWord(word) .. GENERATED FROM PYTHON SOURCE LINES 316-327 Now we can assemble our vocabulary and query/response sentence pairs. Before we are ready to use this data, we must perform some preprocessing. First, we must convert the Unicode strings to ASCII using ``unicodeToAscii``. Next, we should convert all letters to lowercase and trim all non-letter characters except for basic punctuation (``normalizeString``). Finally, to aid in training convergence, we will filter out sentences with length greater than the ``MAX_LENGTH`` threshold (``filterPairs``). .. GENERATED FROM PYTHON SOURCE LINES 327-390 .. code-block:: default MAX_LENGTH = 10 # Maximum sentence length to consider # Turn a Unicode string to plain ASCII, thanks to # https://stackoverflow.com/a/518232/2809427 def unicodeToAscii(s): return ''.join( c for c in unicodedata.normalize('NFD', s) if unicodedata.category(c) != 'Mn' ) # Lowercase, trim, and remove non-letter characters def normalizeString(s): s = unicodeToAscii(s.lower().strip()) s = re.sub(r"([.!?])", r" \1", s) s = re.sub(r"[^a-zA-Z.!?]+", r" ", s) s = re.sub(r"\s+", r" ", s).strip() return s # Read query/response pairs and return a voc object def readVocs(datafile, corpus_name): print("Reading lines...") # Read the file and split into lines lines = open(datafile, encoding='utf-8').\ read().strip().split('\n') # Split every line into pairs and normalize pairs = [[normalizeString(s) for s in l.split('\t')] for l in lines] voc = Voc(corpus_name) return voc, pairs # Returns True if both sentences in a pair 'p' are under the MAX_LENGTH threshold def filterPair(p): # Input sequences need to preserve the last word for EOS token return len(p[0].split(' ')) < MAX_LENGTH and len(p[1].split(' ')) < MAX_LENGTH # Filter pairs using the ``filterPair`` condition def filterPairs(pairs): return [pair for pair in pairs if filterPair(pair)] # Using the functions defined above, return a populated voc object and pairs list def loadPrepareData(corpus, corpus_name, datafile, save_dir): print("Start preparing training data ...") voc, pairs = readVocs(datafile, corpus_name) print("Read {!s} sentence pairs".format(len(pairs))) pairs = filterPairs(pairs) print("Trimmed to {!s} sentence pairs".format(len(pairs))) print("Counting words...") for pair in pairs: voc.addSentence(pair[0]) voc.addSentence(pair[1]) print("Counted words:", voc.num_words) return voc, pairs # Load/Assemble voc and pairs save_dir = os.path.join("data", "save") voc, pairs = loadPrepareData(corpus, corpus_name, datafile, save_dir) # Print some pairs to validate print("\npairs:") for pair in pairs[:10]: print(pair) .. rst-class:: sphx-glr-script-out .. code-block:: none Start preparing training data ... Reading lines... Read 221282 sentence pairs Trimmed to 64313 sentence pairs Counting words... Counted words: 18082 pairs: ['they do to !', 'they do not !'] ['she okay ?', 'i hope so .'] ['wow', 'let s go .'] ['what good stuff ?', 'the real you .'] ['the real you .', 'like my fear of wearing pastels ?'] ['do you listen to this crap ?', 'what crap ?'] ['well no . . .', 'then that s all you had to say .'] ['then that s all you had to say .', 'but'] ['but', 'you always been this selfish ?'] ['have fun tonight ?', 'tons'] .. GENERATED FROM PYTHON SOURCE LINES 391-402 Another tactic that is beneficial to achieving faster convergence during training is trimming rarely used words out of our vocabulary. Decreasing the feature space will also soften the difficulty of the function that the model must learn to approximate. We will do this as a two-step process: 1) Trim words used under ``MIN_COUNT`` threshold using the ``voc.trim`` function. 2) Filter out pairs with trimmed words. .. GENERATED FROM PYTHON SOURCE LINES 402-438 .. code-block:: default MIN_COUNT = 3 # Minimum word count threshold for trimming def trimRareWords(voc, pairs, MIN_COUNT): # Trim words used under the MIN_COUNT from the voc voc.trim(MIN_COUNT) # Filter out pairs with trimmed words keep_pairs = [] for pair in pairs: input_sentence = pair[0] output_sentence = pair[1] keep_input = True keep_output = True # Check input sentence for word in input_sentence.split(' '): if word not in voc.word2index: keep_input = False break # Check output sentence for word in output_sentence.split(' '): if word not in voc.word2index: keep_output = False break # Only keep pairs that do not contain trimmed word(s) in their input or output sentence if keep_input and keep_output: keep_pairs.append(pair) print("Trimmed from {} pairs to {}, {:.4f} of total".format(len(pairs), len(keep_pairs), len(keep_pairs) / len(pairs))) return keep_pairs # Trim voc and pairs pairs = trimRareWords(voc, pairs, MIN_COUNT) .. rst-class:: sphx-glr-script-out .. code-block:: none keep_words 7833 / 18079 = 0.4333 Trimmed from 64313 pairs to 53131, 0.8261 of total .. GENERATED FROM PYTHON SOURCE LINES 439-490 Prepare Data for Models ----------------------- Although we have put a great deal of effort into preparing and massaging our data into a nice vocabulary object and list of sentence pairs, our models will ultimately expect numerical torch tensors as inputs. One way to prepare the processed data for the models can be found in the `seq2seq translation tutorial `__. In that tutorial, we use a batch size of 1, meaning that all we have to do is convert the words in our sentence pairs to their corresponding indexes from the vocabulary and feed this to the models. However, if you’re interested in speeding up training and/or would like to leverage GPU parallelization capabilities, you will need to train with mini-batches. Using mini-batches also means that we must be mindful of the variation of sentence length in our batches. To accommodate sentences of different sizes in the same batch, we will make our batched input tensor of shape *(max_length, batch_size)*, where sentences shorter than the *max_length* are zero padded after an *EOS_token*. If we simply convert our English sentences to tensors by converting words to their indexes(\ ``indexesFromSentence``) and zero-pad, our tensor would have shape *(batch_size, max_length)* and indexing the first dimension would return a full sequence across all time-steps. However, we need to be able to index our batch along time, and across all sequences in the batch. Therefore, we transpose our input batch shape to *(max_length, batch_size)*, so that indexing across the first dimension returns a time step across all sentences in the batch. We handle this transpose implicitly in the ``zeroPadding`` function. .. figure:: /_static/img/chatbot/seq2seq_batches.png :align: center :alt: batches The ``inputVar`` function handles the process of converting sentences to tensor, ultimately creating a correctly shaped zero-padded tensor. It also returns a tensor of ``lengths`` for each of the sequences in the batch which will be passed to our decoder later. The ``outputVar`` function performs a similar function to ``inputVar``, but instead of returning a ``lengths`` tensor, it returns a binary mask tensor and a maximum target sentence length. The binary mask tensor has the same shape as the output target tensor, but every element that is a *PAD_token* is 0 and all others are 1. ``batch2TrainData`` simply takes a bunch of pairs and returns the input and target tensors using the aforementioned functions. .. GENERATED FROM PYTHON SOURCE LINES 490-551 .. code-block:: default def indexesFromSentence(voc, sentence): return [voc.word2index[word] for word in sentence.split(' ')] + [EOS_token] def zeroPadding(l, fillvalue=PAD_token): return list(itertools.zip_longest(*l, fillvalue=fillvalue)) def binaryMatrix(l, value=PAD_token): m = [] for i, seq in enumerate(l): m.append([]) for token in seq: if token == PAD_token: m[i].append(0) else: m[i].append(1) return m # Returns padded input sequence tensor and lengths def inputVar(l, voc): indexes_batch = [indexesFromSentence(voc, sentence) for sentence in l] lengths = torch.tensor([len(indexes) for indexes in indexes_batch]) padList = zeroPadding(indexes_batch) padVar = torch.LongTensor(padList) return padVar, lengths # Returns padded target sequence tensor, padding mask, and max target length def outputVar(l, voc): indexes_batch = [indexesFromSentence(voc, sentence) for sentence in l] max_target_len = max([len(indexes) for indexes in indexes_batch]) padList = zeroPadding(indexes_batch) mask = binaryMatrix(padList) mask = torch.BoolTensor(mask) padVar = torch.LongTensor(padList) return padVar, mask, max_target_len # Returns all items for a given batch of pairs def batch2TrainData(voc, pair_batch): pair_batch.sort(key=lambda x: len(x[0].split(" ")), reverse=True) input_batch, output_batch = [], [] for pair in pair_batch: input_batch.append(pair[0]) output_batch.append(pair[1]) inp, lengths = inputVar(input_batch, voc) output, mask, max_target_len = outputVar(output_batch, voc) return inp, lengths, output, mask, max_target_len # Example for validation small_batch_size = 5 batches = batch2TrainData(voc, [random.choice(pairs) for _ in range(small_batch_size)]) input_variable, lengths, target_variable, mask, max_target_len = batches print("input_variable:", input_variable) print("lengths:", lengths) print("target_variable:", target_variable) print("mask:", mask) print("max_target_len:", max_target_len) .. rst-class:: sphx-glr-script-out .. code-block:: none input_variable: tensor([[ 86, 24, 140, 829, 62], [ 6, 355, 1362, 206, 566], [ 36, 735, 14, 72, 1919], [ 17, 140, 140, 2160, 85], [ 62, 28, 158, 14, 14], [1012, 461, 140, 2, 2], [3223, 10, 14, 0, 0], [1012, 2, 2, 0, 0], [ 6, 0, 0, 0, 0], [ 2, 0, 0, 0, 0]]) lengths: tensor([10, 8, 8, 6, 6]) target_variable: tensor([[ 18, 11, 101, 93, 277], [ 483, 113, 19, 311, 72], [ 5, 241, 10, 72, 10], [ 22, 706, 2, 19, 2], [2010, 14, 0, 24, 0], [1556, 2, 0, 136, 0], [ 14, 0, 0, 5, 0], [ 2, 0, 0, 48, 0], [ 0, 0, 0, 14, 0], [ 0, 0, 0, 2, 0]]) mask: tensor([[ True, True, True, True, True], [ True, True, True, True, True], [ True, True, True, True, True], [ True, True, True, True, True], [ True, True, False, True, False], [ True, True, False, True, False], [ True, False, False, True, False], [ True, False, False, True, False], [False, False, False, True, False], [False, False, False, True, False]]) max_target_len: 10 .. GENERATED FROM PYTHON SOURCE LINES 552-580 Define Models ------------- Seq2Seq Model ~~~~~~~~~~~~~ The brains of our chatbot is a sequence-to-sequence (seq2seq) model. The goal of a seq2seq model is to take a variable-length sequence as an input, and return a variable-length sequence as an output using a fixed-sized model. `Sutskever et al. `__ discovered that by using two separate recurrent neural nets together, we can accomplish this task. One RNN acts as an **encoder**, which encodes a variable length input sequence to a fixed-length context vector. In theory, this context vector (the final hidden layer of the RNN) will contain semantic information about the query sentence that is input to the bot. The second RNN is a **decoder**, which takes an input word and the context vector, and returns a guess for the next word in the sequence and a hidden state to use in the next iteration. .. figure:: /_static/img/chatbot/seq2seq_ts.png :align: center :alt: model Image source: https://jeddy92.github.io/JEddy92.github.io/ts_seq2seq_intro/ .. GENERATED FROM PYTHON SOURCE LINES 583-649 Encoder ~~~~~~~ The encoder RNN iterates through the input sentence one token (e.g. word) at a time, at each time step outputting an “output” vector and a “hidden state” vector. The hidden state vector is then passed to the next time step, while the output vector is recorded. The encoder transforms the context it saw at each point in the sequence into a set of points in a high-dimensional space, which the decoder will use to generate a meaningful output for the given task. At the heart of our encoder is a multi-layered Gated Recurrent Unit, invented by `Cho et al. `__ in 2014. We will use a bidirectional variant of the GRU, meaning that there are essentially two independent RNNs: one that is fed the input sequence in normal sequential order, and one that is fed the input sequence in reverse order. The outputs of each network are summed at each time step. Using a bidirectional GRU will give us the advantage of encoding both past and future contexts. Bidirectional RNN: .. figure:: /_static/img/chatbot/RNN-bidirectional.png :width: 70% :align: center :alt: rnn_bidir Image source: https://colah.github.io/posts/2015-09-NN-Types-FP/ Note that an ``embedding`` layer is used to encode our word indices in an arbitrarily sized feature space. For our models, this layer will map each word to a feature space of size *hidden_size*. When trained, these values should encode semantic similarity between similar meaning words. Finally, if passing a padded batch of sequences to an RNN module, we must pack and unpack padding around the RNN pass using ``nn.utils.rnn.pack_padded_sequence`` and ``nn.utils.rnn.pad_packed_sequence`` respectively. **Computation Graph:** 1) Convert word indexes to embeddings. 2) Pack padded batch of sequences for RNN module. 3) Forward pass through GRU. 4) Unpack padding. 5) Sum bidirectional GRU outputs. 6) Return output and final hidden state. **Inputs:** - ``input_seq``: batch of input sentences; shape=\ *(max_length, batch_size)* - ``input_lengths``: list of sentence lengths corresponding to each sentence in the batch; shape=\ *(batch_size)* - ``hidden``: hidden state; shape=\ *(n_layers x num_directions, batch_size, hidden_size)* **Outputs:** - ``outputs``: output features from the last hidden layer of the GRU (sum of bidirectional outputs); shape=\ *(max_length, batch_size, hidden_size)* - ``hidden``: updated hidden state from GRU; shape=\ *(n_layers x num_directions, batch_size, hidden_size)* .. GENERATED FROM PYTHON SOURCE LINES 649-677 .. code-block:: default class EncoderRNN(nn.Module): def __init__(self, hidden_size, embedding, n_layers=1, dropout=0): super(EncoderRNN, self).__init__() self.n_layers = n_layers self.hidden_size = hidden_size self.embedding = embedding # Initialize GRU; the input_size and hidden_size parameters are both set to 'hidden_size' # because our input size is a word embedding with number of features == hidden_size self.gru = nn.GRU(hidden_size, hidden_size, n_layers, dropout=(0 if n_layers == 1 else dropout), bidirectional=True) def forward(self, input_seq, input_lengths, hidden=None): # Convert word indexes to embeddings embedded = self.embedding(input_seq) # Pack padded batch of sequences for RNN module packed = nn.utils.rnn.pack_padded_sequence(embedded, input_lengths) # Forward pass through GRU outputs, hidden = self.gru(packed, hidden) # Unpack padding outputs, _ = nn.utils.rnn.pad_packed_sequence(outputs) # Sum bidirectional GRU outputs outputs = outputs[:, :, :self.hidden_size] + outputs[:, : ,self.hidden_size:] # Return output and final hidden state return outputs, hidden .. GENERATED FROM PYTHON SOURCE LINES 678-740 Decoder ~~~~~~~ The decoder RNN generates the response sentence in a token-by-token fashion. It uses the encoder’s context vectors, and internal hidden states to generate the next word in the sequence. It continues generating words until it outputs an *EOS_token*, representing the end of the sentence. A common problem with a vanilla seq2seq decoder is that if we rely solely on the context vector to encode the entire input sequence’s meaning, it is likely that we will have information loss. This is especially the case when dealing with long input sequences, greatly limiting the capability of our decoder. To combat this, `Bahdanau et al. `__ created an “attention mechanism” that allows the decoder to pay attention to certain parts of the input sequence, rather than using the entire fixed context at every step. At a high level, attention is calculated using the decoder’s current hidden state and the encoder’s outputs. The output attention weights have the same shape as the input sequence, allowing us to multiply them by the encoder outputs, giving us a weighted sum which indicates the parts of encoder output to pay attention to. `Sean Robertson’s `__ figure describes this very well: .. figure:: /_static/img/chatbot/attn2.png :align: center :alt: attn2 `Luong et al. `__ improved upon Bahdanau et al.’s groundwork by creating “Global attention”. The key difference is that with “Global attention”, we consider all of the encoder’s hidden states, as opposed to Bahdanau et al.’s “Local attention”, which only considers the encoder’s hidden state from the current time step. Another difference is that with “Global attention”, we calculate attention weights, or energies, using the hidden state of the decoder from the current time step only. Bahdanau et al.’s attention calculation requires knowledge of the decoder’s state from the previous time step. Also, Luong et al. provides various methods to calculate the attention energies between the encoder output and decoder output which are called “score functions”: .. figure:: /_static/img/chatbot/scores.png :width: 60% :align: center :alt: scores where :math:`h_t` = current target decoder state and :math:`\bar{h}_s` = all encoder states. Overall, the Global attention mechanism can be summarized by the following figure. Note that we will implement the “Attention Layer” as a separate ``nn.Module`` called ``Attn``. The output of this module is a softmax normalized weights tensor of shape *(batch_size, 1, max_length)*. .. figure:: /_static/img/chatbot/global_attn.png :align: center :width: 60% :alt: global_attn .. GENERATED FROM PYTHON SOURCE LINES 740-782 .. code-block:: default # Luong attention layer class Attn(nn.Module): def __init__(self, method, hidden_size): super(Attn, self).__init__() self.method = method if self.method not in ['dot', 'general', 'concat']: raise ValueError(self.method, "is not an appropriate attention method.") self.hidden_size = hidden_size if self.method == 'general': self.attn = nn.Linear(self.hidden_size, hidden_size) elif self.method == 'concat': self.attn = nn.Linear(self.hidden_size * 2, hidden_size) self.v = nn.Parameter(torch.FloatTensor(hidden_size)) def dot_score(self, hidden, encoder_output): return torch.sum(hidden * encoder_output, dim=2) def general_score(self, hidden, encoder_output): energy = self.attn(encoder_output) return torch.sum(hidden * energy, dim=2) def concat_score(self, hidden, encoder_output): energy = self.attn(torch.cat((hidden.expand(encoder_output.size(0), -1, -1), encoder_output), 2)).tanh() return torch.sum(self.v * energy, dim=2) def forward(self, hidden, encoder_outputs): # Calculate the attention weights (energies) based on the given method if self.method == 'general': attn_energies = self.general_score(hidden, encoder_outputs) elif self.method == 'concat': attn_energies = self.concat_score(hidden, encoder_outputs) elif self.method == 'dot': attn_energies = self.dot_score(hidden, encoder_outputs) # Transpose max_length and batch_size dimensions attn_energies = attn_energies.t() # Return the softmax normalized probability scores (with added dimension) return F.softmax(attn_energies, dim=1).unsqueeze(1) .. GENERATED FROM PYTHON SOURCE LINES 783-815 Now that we have defined our attention submodule, we can implement the actual decoder model. For the decoder, we will manually feed our batch one time step at a time. This means that our embedded word tensor and GRU output will both have shape *(1, batch_size, hidden_size)*. **Computation Graph:** 1) Get embedding of current input word. 2) Forward through unidirectional GRU. 3) Calculate attention weights from the current GRU output from (2). 4) Multiply attention weights to encoder outputs to get new "weighted sum" context vector. 5) Concatenate weighted context vector and GRU output using Luong eq. 5. 6) Predict next word using Luong eq. 6 (without softmax). 7) Return output and final hidden state. **Inputs:** - ``input_step``: one time step (one word) of input sequence batch; shape=\ *(1, batch_size)* - ``last_hidden``: final hidden layer of GRU; shape=\ *(n_layers x num_directions, batch_size, hidden_size)* - ``encoder_outputs``: encoder model’s output; shape=\ *(max_length, batch_size, hidden_size)* **Outputs:** - ``output``: softmax normalized tensor giving probabilities of each word being the correct next word in the decoded sequence; shape=\ *(batch_size, voc.num_words)* - ``hidden``: final hidden state of GRU; shape=\ *(n_layers x num_directions, batch_size, hidden_size)* .. GENERATED FROM PYTHON SOURCE LINES 815-859 .. code-block:: default 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 .. GENERATED FROM PYTHON SOURCE LINES 860-874 Define Training Procedure ------------------------- Masked loss ~~~~~~~~~~~ Since we are dealing with batches of padded sequences, we cannot simply consider all elements of the tensor when calculating loss. We define ``maskNLLLoss`` to calculate our loss based on our decoder’s output tensor, the target tensor, and a binary mask tensor describing the padding of the target tensor. This loss function calculates the average negative log likelihood of the elements that correspond to a *1* in the mask tensor. .. GENERATED FROM PYTHON SOURCE LINES 874-883 .. code-block:: default 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() .. GENERATED FROM PYTHON SOURCE LINES 884-943 Single training iteration ~~~~~~~~~~~~~~~~~~~~~~~~~ The ``train`` function contains the algorithm for a single training iteration (a single batch of inputs). We will use a couple of clever tricks to aid in convergence: - The first trick is using **teacher forcing**. This means that at some probability, set by ``teacher_forcing_ratio``, we use the current target word as the decoder’s next input rather than using the decoder’s current guess. This technique acts as training wheels for the decoder, aiding in more efficient training. However, teacher forcing can lead to model instability during inference, as the decoder may not have a sufficient chance to truly craft its own output sequences during training. Thus, we must be mindful of how we are setting the ``teacher_forcing_ratio``, and not be fooled by fast convergence. - The second trick that we implement is **gradient clipping**. This is a commonly used technique for countering the “exploding gradient” problem. In essence, by clipping or thresholding gradients to a maximum value, we prevent the gradients from growing exponentially and either overflow (NaN), or overshoot steep cliffs in the cost function. .. figure:: /_static/img/chatbot/grad_clip.png :align: center :width: 60% :alt: grad_clip Image source: Goodfellow et al. *Deep Learning*. 2016. https://www.deeplearningbook.org/ **Sequence of Operations:** 1) Forward pass entire input batch through encoder. 2) Initialize decoder inputs as SOS_token, and hidden state as the encoder's final hidden state. 3) Forward input batch sequence through decoder one time step at a time. 4) If teacher forcing: set next decoder input as the current target; else: set next decoder input as current decoder output. 5) Calculate and accumulate loss. 6) Perform backpropagation. 7) Clip gradients. 8) Update encoder and decoder model parameters. .. Note :: PyTorch’s RNN modules (``RNN``, ``LSTM``, ``GRU``) can be used like any other non-recurrent layers by simply passing them the entire input sequence (or batch of sequences). We use the ``GRU`` layer like this in the ``encoder``. The reality is that under the hood, there is an iterative process looping over each time step calculating hidden states. Alternatively, you can run these modules one time-step at a time. In this case, we manually loop over the sequences during the training process like we must do for the ``decoder`` model. As long as you maintain the correct conceptual model of these modules, implementing sequential models can be very straightforward. .. GENERATED FROM PYTHON SOURCE LINES 943-1019 .. code-block:: default def train(input_variable, lengths, target_variable, mask, max_target_len, encoder, decoder, embedding, encoder_optimizer, decoder_optimizer, batch_size, clip, max_length=MAX_LENGTH): # Zero gradients encoder_optimizer.zero_grad() decoder_optimizer.zero_grad() # Set device options input_variable = input_variable.to(device) target_variable = target_variable.to(device) mask = mask.to(device) # Lengths for RNN packing should always be on the CPU lengths = lengths.to("cpu") # Initialize variables loss = 0 print_losses = [] n_totals = 0 # Forward pass through encoder encoder_outputs, encoder_hidden = encoder(input_variable, lengths) # Create initial decoder input (start with SOS tokens for each sentence) decoder_input = torch.LongTensor([[SOS_token for _ in range(batch_size)]]) decoder_input = decoder_input.to(device) # Set initial decoder hidden state to the encoder's final hidden state decoder_hidden = encoder_hidden[:decoder.n_layers] # Determine if we are using teacher forcing this iteration use_teacher_forcing = True if random.random() < teacher_forcing_ratio else False # Forward batch of sequences through decoder one time step at a time if use_teacher_forcing: for t in range(max_target_len): decoder_output, decoder_hidden = decoder( decoder_input, decoder_hidden, encoder_outputs ) # Teacher forcing: next input is current target decoder_input = target_variable[t].view(1, -1) # Calculate and accumulate loss mask_loss, nTotal = maskNLLLoss(decoder_output, target_variable[t], mask[t]) loss += mask_loss print_losses.append(mask_loss.item() * nTotal) n_totals += nTotal else: for t in range(max_target_len): decoder_output, decoder_hidden = decoder( decoder_input, decoder_hidden, encoder_outputs ) # No teacher forcing: next input is decoder's own current output _, topi = decoder_output.topk(1) decoder_input = torch.LongTensor([[topi[i][0] for i in range(batch_size)]]) decoder_input = decoder_input.to(device) # Calculate and accumulate loss mask_loss, nTotal = maskNLLLoss(decoder_output, target_variable[t], mask[t]) loss += mask_loss print_losses.append(mask_loss.item() * nTotal) n_totals += nTotal # Perform backpropagation loss.backward() # Clip gradients: gradients are modified in place _ = nn.utils.clip_grad_norm_(encoder.parameters(), clip) _ = nn.utils.clip_grad_norm_(decoder.parameters(), clip) # Adjust model weights encoder_optimizer.step() decoder_optimizer.step() return sum(print_losses) / n_totals .. GENERATED FROM PYTHON SOURCE LINES 1020-1036 Training iterations ~~~~~~~~~~~~~~~~~~~ It is finally time to tie the full training procedure together with the data. The ``trainIters`` function is responsible for running ``n_iterations`` of training given the passed models, optimizers, data, etc. This function is quite self explanatory, as we have done the heavy lifting with the ``train`` function. One thing to note is that when we save our model, we save a tarball containing the encoder and decoder ``state_dicts`` (parameters), the optimizers’ ``state_dicts``, the loss, the iteration, etc. Saving the model in this way will give us the ultimate flexibility with the checkpoint. After loading a checkpoint, we will be able to use the model parameters to run inference, or we can continue training right where we left off. .. GENERATED FROM PYTHON SOURCE LINES 1036-1085 .. code-block:: default 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'))) .. GENERATED FROM PYTHON SOURCE LINES 1086-1121 Define Evaluation ----------------- After training a model, we want to be able to talk to the bot ourselves. First, we must define how we want the model to decode the encoded input. Greedy decoding ~~~~~~~~~~~~~~~ Greedy decoding is the decoding method that we use during training when we are **NOT** using teacher forcing. In other words, for each time step, we simply choose the word from ``decoder_output`` with the highest softmax value. This decoding method is optimal on a single time-step level. To facilitate the greedy decoding operation, we define a ``GreedySearchDecoder`` class. When run, an object of this class takes an input sequence (``input_seq``) of shape *(input_seq length, 1)*, a scalar input length (``input_length``) tensor, and a ``max_length`` to bound the response sentence length. The input sentence is evaluated using the following computational graph: **Computation Graph:** 1) Forward input through encoder model. 2) Prepare encoder's final hidden layer to be first hidden input to the decoder. 3) Initialize decoder's first input as SOS_token. 4) Initialize tensors to append decoded words to. 5) Iteratively decode one word token at a time: a) Forward pass through decoder. b) Obtain most likely word token and its softmax score. c) Record token and score. d) Prepare current token to be next decoder input. 6) Return collections of word tokens and scores. .. GENERATED FROM PYTHON SOURCE LINES 1121-1153 .. code-block:: default 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 .. GENERATED FROM PYTHON SOURCE LINES 1154-1182 Evaluate my text ~~~~~~~~~~~~~~~~ Now that we have our decoding method defined, we can write functions for evaluating a string input sentence. The ``evaluate`` function manages the low-level process of handling the input sentence. We first format the sentence as an input batch of word indexes with *batch_size==1*. We do this by converting the words of the sentence to their corresponding indexes, and transposing the dimensions to prepare the tensor for our models. We also create a ``lengths`` tensor which contains the length of our input sentence. In this case, ``lengths`` is scalar because we are only evaluating one sentence at a time (batch_size==1). Next, we obtain the decoded response sentence tensor using our ``GreedySearchDecoder`` object (``searcher``). Finally, we convert the response’s indexes to words and return the list of decoded words. ``evaluateInput`` acts as the user interface for our chatbot. When called, an input text field will spawn in which we can enter our query sentence. After typing our input sentence and pressing *Enter*, our text is normalized in the same way as our training data, and is ultimately fed to the ``evaluate`` function to obtain a decoded output sentence. We loop this process, so we can keep chatting with our bot until we enter either “q” or “quit”. Finally, if a sentence is entered that contains a word that is not in the vocabulary, we handle this gracefully by printing an error message and prompting the user to enter another sentence. .. GENERATED FROM PYTHON SOURCE LINES 1182-1221 .. code-block:: default def evaluate(encoder, decoder, searcher, voc, sentence, max_length=MAX_LENGTH): ### Format input sentence as a batch # words -> indexes indexes_batch = [indexesFromSentence(voc, sentence)] # Create lengths tensor lengths = torch.tensor([len(indexes) for indexes in indexes_batch]) # Transpose dimensions of batch to match models' expectations input_batch = torch.LongTensor(indexes_batch).transpose(0, 1) # Use appropriate device input_batch = input_batch.to(device) lengths = lengths.to("cpu") # Decode sentence with searcher tokens, scores = searcher(input_batch, lengths, max_length) # indexes -> words decoded_words = [voc.index2word[token.item()] for token in tokens] return decoded_words def evaluateInput(encoder, decoder, searcher, voc): input_sentence = '' while(1): try: # Get input sentence input_sentence = input('> ') # Check if it is quit case if input_sentence == 'q' or input_sentence == 'quit': break # Normalize sentence input_sentence = normalizeString(input_sentence) # Evaluate sentence output_words = evaluate(encoder, decoder, searcher, voc, input_sentence) # Format and print response sentence output_words[:] = [x for x in output_words if not (x == 'EOS' or x == 'PAD')] print('Bot:', ' '.join(output_words)) except KeyError: print("Error: Encountered unknown word.") .. GENERATED FROM PYTHON SOURCE LINES 1222-1234 Run Model --------- Finally, it is time to run our model! Regardless of whether we want to train or test the chatbot model, we must initialize the individual encoder and decoder models. In the following block, we set our desired configurations, choose to start from scratch or set a checkpoint to load from, and build and initialize the models. Feel free to play with different model configurations to optimize performance. .. GENERATED FROM PYTHON SOURCE LINES 1234-1250 .. code-block:: default # Configure models model_name = 'cb_model' attn_model = 'dot' #``attn_model = 'general'`` #``attn_model = 'concat'`` hidden_size = 500 encoder_n_layers = 2 decoder_n_layers = 2 dropout = 0.1 batch_size = 64 # Set checkpoint to load from; set to None if starting from scratch loadFilename = None checkpoint_iter = 4000 .. GENERATED FROM PYTHON SOURCE LINES 1251-1258 Sample code to load from a checkpoint: .. code-block:: python loadFilename = os.path.join(save_dir, model_name, corpus_name, '{}-{}_{}'.format(encoder_n_layers, decoder_n_layers, hidden_size), '{}_checkpoint.tar'.format(checkpoint_iter)) .. GENERATED FROM PYTHON SOURCE LINES 1258-1290 .. code-block:: default # Load model if a ``loadFilename`` is provided if loadFilename: # If loading on same machine the model was trained on checkpoint = torch.load(loadFilename) # If loading a model trained on GPU to CPU #checkpoint = torch.load(loadFilename, map_location=torch.device('cpu')) encoder_sd = checkpoint['en'] decoder_sd = checkpoint['de'] encoder_optimizer_sd = checkpoint['en_opt'] decoder_optimizer_sd = checkpoint['de_opt'] embedding_sd = checkpoint['embedding'] voc.__dict__ = checkpoint['voc_dict'] print('Building encoder and decoder ...') # Initialize word embeddings embedding = nn.Embedding(voc.num_words, hidden_size) if loadFilename: embedding.load_state_dict(embedding_sd) # Initialize encoder & decoder models encoder = EncoderRNN(hidden_size, embedding, encoder_n_layers, dropout) decoder = LuongAttnDecoderRNN(attn_model, embedding, hidden_size, voc.num_words, decoder_n_layers, dropout) if loadFilename: encoder.load_state_dict(encoder_sd) decoder.load_state_dict(decoder_sd) # Use appropriate device encoder = encoder.to(device) decoder = decoder.to(device) print('Models built and ready to go!') .. rst-class:: sphx-glr-script-out .. code-block:: none Building encoder and decoder ... Models built and ready to go! .. GENERATED FROM PYTHON SOURCE LINES 1291-1300 Run Training ~~~~~~~~~~~~ Run the following block if you want to train the model. First we set training parameters, then we initialize our optimizers, and finally we call the ``trainIters`` function to run our training iterations. .. GENERATED FROM PYTHON SOURCE LINES 1300-1340 .. code-block:: default # Configure training/optimization clip = 50.0 teacher_forcing_ratio = 1.0 learning_rate = 0.0001 decoder_learning_ratio = 5.0 n_iteration = 4000 print_every = 1 save_every = 500 # Ensure dropout layers are in train mode encoder.train() decoder.train() # Initialize optimizers print('Building optimizers ...') encoder_optimizer = optim.Adam(encoder.parameters(), lr=learning_rate) decoder_optimizer = optim.Adam(decoder.parameters(), lr=learning_rate * decoder_learning_ratio) if loadFilename: encoder_optimizer.load_state_dict(encoder_optimizer_sd) decoder_optimizer.load_state_dict(decoder_optimizer_sd) # If you have CUDA, configure CUDA to call for 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 iterations print("Starting Training!") trainIters(model_name, voc, pairs, encoder, decoder, encoder_optimizer, decoder_optimizer, embedding, encoder_n_layers, decoder_n_layers, save_dir, n_iteration, batch_size, print_every, save_every, clip, corpus_name, loadFilename) .. rst-class:: sphx-glr-script-out .. code-block:: none Building optimizers ... Starting Training! Initializing ... Training... Iteration: 1; Percent complete: 0.0%; Average loss: 8.9557 Iteration: 2; Percent complete: 0.1%; Average loss: 8.8304 Iteration: 3; Percent complete: 0.1%; Average loss: 8.5958 Iteration: 4; Percent complete: 0.1%; Average loss: 8.2952 Iteration: 5; Percent complete: 0.1%; Average loss: 7.9417 Iteration: 6; Percent complete: 0.1%; Average loss: 7.3314 Iteration: 7; Percent complete: 0.2%; Average loss: 6.8537 Iteration: 8; Percent complete: 0.2%; Average loss: 6.8359 Iteration: 9; Percent complete: 0.2%; Average loss: 6.9067 Iteration: 10; Percent complete: 0.2%; Average loss: 6.5912 Iteration: 11; Percent complete: 0.3%; Average loss: 6.1867 Iteration: 12; Percent complete: 0.3%; Average loss: 5.9758 Iteration: 13; Percent complete: 0.3%; Average loss: 5.7458 Iteration: 14; Percent complete: 0.4%; Average loss: 5.6528 Iteration: 15; Percent complete: 0.4%; Average loss: 5.6514 Iteration: 16; Percent complete: 0.4%; Average loss: 5.5781 Iteration: 17; Percent complete: 0.4%; Average loss: 5.2218 Iteration: 18; Percent complete: 0.4%; Average loss: 5.1461 Iteration: 19; Percent complete: 0.5%; Average loss: 5.1936 Iteration: 20; Percent complete: 0.5%; Average loss: 4.7800 Iteration: 21; Percent complete: 0.5%; Average loss: 5.1136 Iteration: 22; Percent complete: 0.5%; Average loss: 4.8743 Iteration: 23; Percent complete: 0.6%; Average loss: 5.1095 Iteration: 24; Percent complete: 0.6%; Average loss: 4.9185 Iteration: 25; Percent complete: 0.6%; Average loss: 5.0219 Iteration: 26; Percent complete: 0.7%; Average loss: 4.7137 Iteration: 27; Percent complete: 0.7%; Average loss: 4.8904 Iteration: 28; Percent complete: 0.7%; Average loss: 4.8820 Iteration: 29; Percent complete: 0.7%; Average loss: 4.7673 Iteration: 30; Percent complete: 0.8%; Average loss: 4.9658 Iteration: 31; Percent complete: 0.8%; Average loss: 4.6614 Iteration: 32; Percent complete: 0.8%; Average loss: 4.8095 Iteration: 33; Percent complete: 0.8%; Average loss: 4.7338 Iteration: 34; Percent complete: 0.9%; Average loss: 4.7562 Iteration: 35; Percent complete: 0.9%; Average loss: 4.7819 Iteration: 36; Percent complete: 0.9%; Average loss: 4.8076 Iteration: 37; Percent complete: 0.9%; Average loss: 4.8190 Iteration: 38; Percent complete: 0.9%; Average loss: 4.7370 Iteration: 39; Percent complete: 1.0%; Average loss: 5.0267 Iteration: 40; Percent complete: 1.0%; Average loss: 4.7106 Iteration: 41; Percent complete: 1.0%; Average loss: 4.6497 Iteration: 42; Percent complete: 1.1%; Average loss: 4.8935 Iteration: 43; Percent complete: 1.1%; Average loss: 4.7271 Iteration: 44; Percent complete: 1.1%; Average loss: 4.7653 Iteration: 45; Percent complete: 1.1%; Average loss: 4.7483 Iteration: 46; Percent complete: 1.1%; Average loss: 4.7889 Iteration: 47; Percent complete: 1.2%; Average loss: 4.7812 Iteration: 48; Percent complete: 1.2%; Average loss: 4.5309 Iteration: 49; Percent complete: 1.2%; Average loss: 4.4495 Iteration: 50; Percent complete: 1.2%; Average loss: 4.6171 Iteration: 51; Percent complete: 1.3%; Average loss: 4.6777 Iteration: 52; Percent complete: 1.3%; Average loss: 4.7583 Iteration: 53; Percent complete: 1.3%; Average loss: 4.6302 Iteration: 54; Percent complete: 1.4%; Average loss: 4.8279 Iteration: 55; Percent complete: 1.4%; Average loss: 4.7301 Iteration: 56; Percent complete: 1.4%; Average loss: 4.5886 Iteration: 57; Percent complete: 1.4%; Average loss: 4.6465 Iteration: 58; Percent complete: 1.5%; Average loss: 4.5468 Iteration: 59; Percent complete: 1.5%; Average loss: 4.8872 Iteration: 60; Percent complete: 1.5%; Average loss: 4.5926 Iteration: 61; Percent complete: 1.5%; Average loss: 4.5934 Iteration: 62; Percent complete: 1.6%; Average loss: 4.5745 Iteration: 63; Percent complete: 1.6%; Average loss: 4.6842 Iteration: 64; Percent complete: 1.6%; Average loss: 4.5969 Iteration: 65; Percent complete: 1.6%; Average loss: 4.4704 Iteration: 66; Percent complete: 1.7%; Average loss: 4.7207 Iteration: 67; Percent complete: 1.7%; Average loss: 4.4352 Iteration: 68; Percent complete: 1.7%; Average loss: 4.3765 Iteration: 69; Percent complete: 1.7%; Average loss: 4.6770 Iteration: 70; Percent complete: 1.8%; Average loss: 4.5426 Iteration: 71; Percent complete: 1.8%; Average loss: 4.4794 Iteration: 72; Percent complete: 1.8%; Average loss: 4.5821 Iteration: 73; Percent complete: 1.8%; Average loss: 4.5298 Iteration: 74; Percent complete: 1.8%; Average loss: 4.3629 Iteration: 75; Percent complete: 1.9%; Average loss: 4.5660 Iteration: 76; Percent complete: 1.9%; Average loss: 4.3732 Iteration: 77; Percent complete: 1.9%; Average loss: 4.6122 Iteration: 78; Percent complete: 1.9%; Average loss: 4.3864 Iteration: 79; Percent complete: 2.0%; Average loss: 4.6285 Iteration: 80; Percent complete: 2.0%; Average loss: 4.6040 Iteration: 81; Percent complete: 2.0%; Average loss: 4.3618 Iteration: 82; Percent complete: 2.1%; Average loss: 4.3494 Iteration: 83; Percent complete: 2.1%; Average loss: 4.5388 Iteration: 84; Percent complete: 2.1%; Average loss: 4.6473 Iteration: 85; Percent complete: 2.1%; Average loss: 4.4755 Iteration: 86; Percent complete: 2.1%; Average loss: 4.7000 Iteration: 87; Percent complete: 2.2%; Average loss: 4.0924 Iteration: 88; Percent complete: 2.2%; Average loss: 4.2748 Iteration: 89; Percent complete: 2.2%; Average loss: 4.4305 Iteration: 90; Percent complete: 2.2%; Average loss: 4.5600 Iteration: 91; Percent complete: 2.3%; Average loss: 4.3567 Iteration: 92; Percent complete: 2.3%; Average loss: 4.4309 Iteration: 93; Percent complete: 2.3%; Average loss: 4.1718 Iteration: 94; Percent complete: 2.4%; Average loss: 4.4969 Iteration: 95; Percent complete: 2.4%; Average loss: 4.3200 Iteration: 96; Percent complete: 2.4%; Average loss: 4.5377 Iteration: 97; Percent complete: 2.4%; Average loss: 4.3732 Iteration: 98; Percent complete: 2.5%; Average loss: 4.4786 Iteration: 99; Percent complete: 2.5%; Average loss: 4.4567 Iteration: 100; Percent complete: 2.5%; Average loss: 4.3800 Iteration: 101; Percent complete: 2.5%; Average loss: 4.1223 Iteration: 102; Percent complete: 2.5%; Average loss: 4.1655 Iteration: 103; Percent complete: 2.6%; Average loss: 4.4471 Iteration: 104; Percent complete: 2.6%; Average loss: 4.6099 Iteration: 105; Percent complete: 2.6%; Average loss: 4.4651 Iteration: 106; Percent complete: 2.6%; Average loss: 4.4795 Iteration: 107; Percent complete: 2.7%; Average loss: 4.3684 Iteration: 108; Percent complete: 2.7%; Average loss: 4.5205 Iteration: 109; Percent complete: 2.7%; Average loss: 4.3959 Iteration: 110; Percent complete: 2.8%; Average loss: 4.1490 Iteration: 111; Percent complete: 2.8%; Average loss: 4.3062 Iteration: 112; Percent complete: 2.8%; Average loss: 4.4504 Iteration: 113; Percent complete: 2.8%; Average loss: 4.2488 Iteration: 114; Percent complete: 2.9%; Average loss: 4.4712 Iteration: 115; Percent complete: 2.9%; Average loss: 4.2890 Iteration: 116; Percent complete: 2.9%; Average loss: 4.3356 Iteration: 117; Percent complete: 2.9%; Average loss: 4.4046 Iteration: 118; Percent complete: 2.9%; Average loss: 4.5150 Iteration: 119; Percent complete: 3.0%; Average loss: 4.0587 Iteration: 120; Percent complete: 3.0%; Average loss: 4.0377 Iteration: 121; Percent complete: 3.0%; Average loss: 4.2357 Iteration: 122; Percent complete: 3.0%; Average loss: 4.2774 Iteration: 123; Percent complete: 3.1%; Average loss: 4.3476 Iteration: 124; Percent complete: 3.1%; Average loss: 4.5789 Iteration: 125; Percent complete: 3.1%; Average loss: 4.3132 Iteration: 126; Percent complete: 3.1%; Average loss: 4.3818 Iteration: 127; Percent complete: 3.2%; Average loss: 4.4732 Iteration: 128; Percent complete: 3.2%; Average loss: 4.4561 Iteration: 129; Percent complete: 3.2%; Average loss: 4.2981 Iteration: 130; Percent complete: 3.2%; Average loss: 4.1577 Iteration: 131; Percent complete: 3.3%; Average loss: 4.1074 Iteration: 132; Percent complete: 3.3%; Average loss: 4.4824 Iteration: 133; Percent complete: 3.3%; Average loss: 4.2938 Iteration: 134; Percent complete: 3.4%; Average loss: 4.5122 Iteration: 135; Percent complete: 3.4%; Average loss: 4.1860 Iteration: 136; Percent complete: 3.4%; Average loss: 4.2620 Iteration: 137; Percent complete: 3.4%; Average loss: 4.4110 Iteration: 138; Percent complete: 3.5%; Average loss: 4.3452 Iteration: 139; Percent complete: 3.5%; Average loss: 4.1146 Iteration: 140; Percent complete: 3.5%; Average loss: 3.8306 Iteration: 141; Percent complete: 3.5%; Average loss: 4.1964 Iteration: 142; Percent complete: 3.5%; Average loss: 4.0733 Iteration: 143; Percent complete: 3.6%; Average loss: 4.3898 Iteration: 144; Percent complete: 3.6%; Average loss: 4.2930 Iteration: 145; Percent complete: 3.6%; Average loss: 4.1015 Iteration: 146; Percent complete: 3.6%; Average loss: 4.1348 Iteration: 147; Percent complete: 3.7%; Average loss: 4.1631 Iteration: 148; Percent complete: 3.7%; Average loss: 4.2620 Iteration: 149; Percent complete: 3.7%; Average loss: 4.1695 Iteration: 150; Percent complete: 3.8%; Average loss: 4.1711 Iteration: 151; Percent complete: 3.8%; Average loss: 4.1968 Iteration: 152; Percent complete: 3.8%; Average loss: 4.1347 Iteration: 153; Percent complete: 3.8%; Average loss: 4.1283 Iteration: 154; Percent complete: 3.9%; Average loss: 4.2636 Iteration: 155; Percent complete: 3.9%; Average loss: 4.2029 Iteration: 156; Percent complete: 3.9%; Average loss: 4.3961 Iteration: 157; Percent complete: 3.9%; Average loss: 3.9807 Iteration: 158; Percent complete: 4.0%; Average loss: 4.1868 Iteration: 159; Percent complete: 4.0%; Average loss: 4.1840 Iteration: 160; Percent complete: 4.0%; Average loss: 4.0592 Iteration: 161; Percent complete: 4.0%; Average loss: 4.3990 Iteration: 162; Percent complete: 4.0%; Average loss: 4.4004 Iteration: 163; Percent complete: 4.1%; Average loss: 4.3456 Iteration: 164; Percent complete: 4.1%; Average loss: 4.3676 Iteration: 165; Percent complete: 4.1%; Average loss: 4.0251 Iteration: 166; Percent complete: 4.2%; Average loss: 4.2526 Iteration: 167; Percent complete: 4.2%; Average loss: 4.4405 Iteration: 168; Percent complete: 4.2%; Average loss: 4.1813 Iteration: 169; Percent complete: 4.2%; Average loss: 4.2581 Iteration: 170; Percent complete: 4.2%; Average loss: 4.0595 Iteration: 171; Percent complete: 4.3%; Average loss: 4.2434 Iteration: 172; Percent complete: 4.3%; Average loss: 4.1835 Iteration: 173; Percent complete: 4.3%; Average loss: 4.1225 Iteration: 174; Percent complete: 4.3%; Average loss: 4.4362 Iteration: 175; Percent complete: 4.4%; Average loss: 4.0959 Iteration: 176; Percent complete: 4.4%; Average loss: 4.1757 Iteration: 177; Percent complete: 4.4%; Average loss: 4.6338 Iteration: 178; Percent complete: 4.5%; Average loss: 4.0817 Iteration: 179; Percent complete: 4.5%; Average loss: 4.1752 Iteration: 180; Percent complete: 4.5%; Average loss: 4.1337 Iteration: 181; Percent complete: 4.5%; Average loss: 4.1216 Iteration: 182; Percent complete: 4.5%; Average loss: 4.1502 Iteration: 183; Percent complete: 4.6%; Average loss: 4.1655 Iteration: 184; Percent complete: 4.6%; Average loss: 4.2771 Iteration: 185; Percent complete: 4.6%; Average loss: 4.1689 Iteration: 186; Percent complete: 4.7%; Average loss: 3.9378 Iteration: 187; Percent complete: 4.7%; Average loss: 4.1988 Iteration: 188; Percent complete: 4.7%; Average loss: 4.2666 Iteration: 189; Percent complete: 4.7%; Average loss: 4.2148 Iteration: 190; Percent complete: 4.8%; Average loss: 3.9353 Iteration: 191; Percent complete: 4.8%; Average loss: 4.1107 Iteration: 192; Percent complete: 4.8%; Average loss: 4.1333 Iteration: 193; Percent complete: 4.8%; Average loss: 4.0493 Iteration: 194; Percent complete: 4.9%; Average loss: 4.2000 Iteration: 195; Percent complete: 4.9%; Average loss: 4.1483 Iteration: 196; Percent complete: 4.9%; Average loss: 4.1174 Iteration: 197; Percent complete: 4.9%; Average loss: 4.2877 Iteration: 198; Percent complete: 5.0%; Average loss: 3.8941 Iteration: 199; Percent complete: 5.0%; Average loss: 4.1067 Iteration: 200; Percent complete: 5.0%; Average loss: 4.1840 Iteration: 201; Percent complete: 5.0%; Average loss: 4.2756 Iteration: 202; Percent complete: 5.1%; Average loss: 4.2228 Iteration: 203; Percent complete: 5.1%; Average loss: 4.1570 Iteration: 204; Percent complete: 5.1%; Average loss: 3.9869 Iteration: 205; Percent complete: 5.1%; Average loss: 4.2767 Iteration: 206; Percent complete: 5.1%; Average loss: 4.0019 Iteration: 207; Percent complete: 5.2%; Average loss: 4.2531 Iteration: 208; Percent complete: 5.2%; Average loss: 3.8180 Iteration: 209; Percent complete: 5.2%; Average loss: 3.8654 Iteration: 210; Percent complete: 5.2%; Average loss: 4.2586 Iteration: 211; Percent complete: 5.3%; Average loss: 4.1570 Iteration: 212; Percent complete: 5.3%; Average loss: 4.0894 Iteration: 213; Percent complete: 5.3%; Average loss: 4.1214 Iteration: 214; Percent complete: 5.3%; Average loss: 4.3031 Iteration: 215; Percent complete: 5.4%; Average loss: 4.1882 Iteration: 216; Percent complete: 5.4%; Average loss: 4.2501 Iteration: 217; Percent complete: 5.4%; Average loss: 4.1832 Iteration: 218; Percent complete: 5.5%; Average loss: 4.0178 Iteration: 219; Percent complete: 5.5%; Average loss: 4.0602 Iteration: 220; Percent complete: 5.5%; Average loss: 4.0852 Iteration: 221; Percent complete: 5.5%; Average loss: 3.9369 Iteration: 222; Percent complete: 5.5%; Average loss: 4.2817 Iteration: 223; Percent complete: 5.6%; Average loss: 4.1273 Iteration: 224; Percent complete: 5.6%; Average loss: 4.0299 Iteration: 225; Percent complete: 5.6%; Average loss: 3.9908 Iteration: 226; Percent complete: 5.7%; Average loss: 4.2145 Iteration: 227; Percent complete: 5.7%; Average loss: 3.7170 Iteration: 228; Percent complete: 5.7%; Average loss: 4.2233 Iteration: 229; Percent complete: 5.7%; Average loss: 3.9509 Iteration: 230; Percent complete: 5.8%; Average loss: 4.3340 Iteration: 231; Percent complete: 5.8%; Average loss: 3.8341 Iteration: 232; Percent complete: 5.8%; Average loss: 4.0113 Iteration: 233; Percent complete: 5.8%; Average loss: 3.6913 Iteration: 234; Percent complete: 5.9%; Average loss: 3.7380 Iteration: 235; Percent complete: 5.9%; Average loss: 3.8695 Iteration: 236; Percent complete: 5.9%; Average loss: 4.1501 Iteration: 237; Percent complete: 5.9%; Average loss: 4.1089 Iteration: 238; Percent complete: 5.9%; Average loss: 3.6484 Iteration: 239; Percent complete: 6.0%; Average loss: 3.4312 Iteration: 240; Percent complete: 6.0%; Average loss: 3.7948 Iteration: 241; Percent complete: 6.0%; Average loss: 4.1554 Iteration: 242; Percent complete: 6.0%; Average loss: 4.0801 Iteration: 243; Percent complete: 6.1%; Average loss: 4.2534 Iteration: 244; Percent complete: 6.1%; Average loss: 4.0417 Iteration: 245; Percent complete: 6.1%; Average loss: 4.1263 Iteration: 246; Percent complete: 6.2%; Average loss: 4.0104 Iteration: 247; Percent complete: 6.2%; Average loss: 3.8729 Iteration: 248; Percent complete: 6.2%; Average loss: 4.0947 Iteration: 249; Percent complete: 6.2%; Average loss: 4.1025 Iteration: 250; Percent complete: 6.2%; Average loss: 4.1210 Iteration: 251; Percent complete: 6.3%; Average loss: 3.7926 Iteration: 252; Percent complete: 6.3%; Average loss: 3.8577 Iteration: 253; Percent complete: 6.3%; Average loss: 4.0715 Iteration: 254; Percent complete: 6.3%; Average loss: 3.8229 Iteration: 255; Percent complete: 6.4%; Average loss: 3.9067 Iteration: 256; Percent complete: 6.4%; Average loss: 3.9665 Iteration: 257; Percent complete: 6.4%; Average loss: 4.0981 Iteration: 258; Percent complete: 6.5%; Average loss: 4.0436 Iteration: 259; Percent complete: 6.5%; Average loss: 3.8282 Iteration: 260; Percent complete: 6.5%; Average loss: 4.0790 Iteration: 261; Percent complete: 6.5%; Average loss: 3.6914 Iteration: 262; Percent complete: 6.6%; Average loss: 4.2762 Iteration: 263; Percent complete: 6.6%; Average loss: 4.0146 Iteration: 264; Percent complete: 6.6%; Average loss: 4.1632 Iteration: 265; Percent complete: 6.6%; Average loss: 3.9937 Iteration: 266; Percent complete: 6.7%; Average loss: 4.0931 Iteration: 267; Percent complete: 6.7%; Average loss: 4.0049 Iteration: 268; Percent complete: 6.7%; Average loss: 3.9685 Iteration: 269; Percent complete: 6.7%; Average loss: 4.1224 Iteration: 270; Percent complete: 6.8%; Average loss: 3.8407 Iteration: 271; Percent complete: 6.8%; Average loss: 3.9879 Iteration: 272; Percent complete: 6.8%; Average loss: 4.0518 Iteration: 273; Percent complete: 6.8%; Average loss: 4.2381 Iteration: 274; Percent complete: 6.9%; Average loss: 4.0945 Iteration: 275; Percent complete: 6.9%; Average loss: 3.9848 Iteration: 276; Percent complete: 6.9%; Average loss: 3.9972 Iteration: 277; Percent complete: 6.9%; Average loss: 3.9867 Iteration: 278; Percent complete: 7.0%; Average loss: 3.8162 Iteration: 279; Percent complete: 7.0%; Average loss: 3.8720 Iteration: 280; Percent complete: 7.0%; Average loss: 3.8497 Iteration: 281; Percent complete: 7.0%; Average loss: 3.8569 Iteration: 282; Percent complete: 7.0%; Average loss: 3.8674 Iteration: 283; Percent complete: 7.1%; Average loss: 3.9777 Iteration: 284; Percent complete: 7.1%; Average loss: 3.8317 Iteration: 285; Percent complete: 7.1%; Average loss: 4.1731 Iteration: 286; Percent complete: 7.1%; Average loss: 3.8641 Iteration: 287; Percent complete: 7.2%; Average loss: 4.2366 Iteration: 288; Percent complete: 7.2%; Average loss: 3.9066 Iteration: 289; Percent complete: 7.2%; Average loss: 3.6921 Iteration: 290; Percent complete: 7.2%; Average loss: 3.6458 Iteration: 291; Percent complete: 7.3%; Average loss: 3.6761 Iteration: 292; Percent complete: 7.3%; Average loss: 3.9698 Iteration: 293; Percent complete: 7.3%; Average loss: 3.8070 Iteration: 294; Percent complete: 7.3%; Average loss: 3.7149 Iteration: 295; Percent complete: 7.4%; Average loss: 3.8142 Iteration: 296; Percent complete: 7.4%; Average loss: 3.7971 Iteration: 297; Percent complete: 7.4%; Average loss: 3.6566 Iteration: 298; Percent complete: 7.4%; Average loss: 3.7541 Iteration: 299; Percent complete: 7.5%; Average loss: 3.7535 Iteration: 300; Percent complete: 7.5%; Average loss: 3.9134 Iteration: 301; Percent complete: 7.5%; Average loss: 3.9584 Iteration: 302; Percent complete: 7.5%; Average loss: 4.0147 Iteration: 303; Percent complete: 7.6%; Average loss: 3.7487 Iteration: 304; Percent complete: 7.6%; Average loss: 3.7744 Iteration: 305; Percent complete: 7.6%; Average loss: 3.8985 Iteration: 306; Percent complete: 7.6%; Average loss: 3.9881 Iteration: 307; Percent complete: 7.7%; Average loss: 4.1234 Iteration: 308; Percent complete: 7.7%; Average loss: 4.1167 Iteration: 309; Percent complete: 7.7%; Average loss: 4.0259 Iteration: 310; Percent complete: 7.8%; Average loss: 3.7172 Iteration: 311; Percent complete: 7.8%; Average loss: 3.8312 Iteration: 312; Percent complete: 7.8%; Average loss: 3.7123 Iteration: 313; Percent complete: 7.8%; Average loss: 3.7671 Iteration: 314; Percent complete: 7.8%; Average loss: 3.7575 Iteration: 315; Percent complete: 7.9%; Average loss: 3.8204 Iteration: 316; Percent complete: 7.9%; Average loss: 3.9143 Iteration: 317; Percent complete: 7.9%; Average loss: 3.7469 Iteration: 318; Percent complete: 8.0%; Average loss: 3.8910 Iteration: 319; Percent complete: 8.0%; Average loss: 4.0528 Iteration: 320; Percent complete: 8.0%; Average loss: 3.7145 Iteration: 321; Percent complete: 8.0%; Average loss: 3.7265 Iteration: 322; Percent complete: 8.1%; Average loss: 3.4666 Iteration: 323; Percent complete: 8.1%; Average loss: 3.7086 Iteration: 324; Percent complete: 8.1%; Average loss: 3.7396 Iteration: 325; Percent complete: 8.1%; Average loss: 3.8440 Iteration: 326; Percent complete: 8.2%; Average loss: 3.8278 Iteration: 327; Percent complete: 8.2%; Average loss: 3.7452 Iteration: 328; Percent complete: 8.2%; Average loss: 4.0670 Iteration: 329; Percent complete: 8.2%; Average loss: 3.6928 Iteration: 330; Percent complete: 8.2%; Average loss: 4.0523 Iteration: 331; Percent complete: 8.3%; Average loss: 3.7819 Iteration: 332; Percent complete: 8.3%; Average loss: 3.8812 Iteration: 333; Percent complete: 8.3%; Average loss: 3.9175 Iteration: 334; Percent complete: 8.3%; Average loss: 3.6585 Iteration: 335; Percent complete: 8.4%; Average loss: 3.9351 Iteration: 336; Percent complete: 8.4%; Average loss: 4.0586 Iteration: 337; Percent complete: 8.4%; Average loss: 3.8923 Iteration: 338; Percent complete: 8.5%; Average loss: 3.7746 Iteration: 339; Percent complete: 8.5%; Average loss: 3.9010 Iteration: 340; Percent complete: 8.5%; Average loss: 3.7905 Iteration: 341; Percent complete: 8.5%; Average loss: 3.9016 Iteration: 342; Percent complete: 8.6%; Average loss: 3.9732 Iteration: 343; Percent complete: 8.6%; Average loss: 4.0932 Iteration: 344; Percent complete: 8.6%; Average loss: 3.8265 Iteration: 345; Percent complete: 8.6%; Average loss: 3.9091 Iteration: 346; Percent complete: 8.6%; Average loss: 3.9337 Iteration: 347; Percent complete: 8.7%; Average loss: 3.7264 Iteration: 348; Percent complete: 8.7%; Average loss: 3.9740 Iteration: 349; Percent complete: 8.7%; Average loss: 3.9883 Iteration: 350; Percent complete: 8.8%; Average loss: 3.9159 Iteration: 351; Percent complete: 8.8%; Average loss: 3.8024 Iteration: 352; Percent complete: 8.8%; Average loss: 3.7455 Iteration: 353; Percent complete: 8.8%; Average loss: 3.7468 Iteration: 354; Percent complete: 8.8%; Average loss: 3.8783 Iteration: 355; Percent complete: 8.9%; Average loss: 3.5521 Iteration: 356; Percent complete: 8.9%; Average loss: 3.9728 Iteration: 357; Percent complete: 8.9%; Average loss: 3.7995 Iteration: 358; Percent complete: 8.9%; Average loss: 3.8172 Iteration: 359; Percent complete: 9.0%; Average loss: 3.8613 Iteration: 360; Percent complete: 9.0%; Average loss: 3.7835 Iteration: 361; Percent complete: 9.0%; Average loss: 3.8016 Iteration: 362; Percent complete: 9.0%; Average loss: 3.8009 Iteration: 363; Percent complete: 9.1%; Average loss: 3.8441 Iteration: 364; Percent complete: 9.1%; Average loss: 3.7485 Iteration: 365; Percent complete: 9.1%; Average loss: 3.7446 Iteration: 366; Percent complete: 9.2%; Average loss: 3.8230 Iteration: 367; Percent complete: 9.2%; Average loss: 3.6738 Iteration: 368; Percent complete: 9.2%; Average loss: 4.0543 Iteration: 369; Percent complete: 9.2%; Average loss: 3.8046 Iteration: 370; Percent complete: 9.2%; Average loss: 3.9057 Iteration: 371; Percent complete: 9.3%; Average loss: 4.0574 Iteration: 372; Percent complete: 9.3%; Average loss: 4.0534 Iteration: 373; Percent complete: 9.3%; Average loss: 3.8358 Iteration: 374; Percent complete: 9.3%; Average loss: 3.7453 Iteration: 375; Percent complete: 9.4%; Average loss: 3.6387 Iteration: 376; Percent complete: 9.4%; Average loss: 3.6681 Iteration: 377; Percent complete: 9.4%; Average loss: 3.8265 Iteration: 378; Percent complete: 9.4%; Average loss: 3.4165 Iteration: 379; Percent complete: 9.5%; Average loss: 3.5960 Iteration: 380; Percent complete: 9.5%; Average loss: 3.9769 Iteration: 381; Percent complete: 9.5%; Average loss: 3.9443 Iteration: 382; Percent complete: 9.6%; Average loss: 3.9426 Iteration: 383; Percent complete: 9.6%; Average loss: 3.9131 Iteration: 384; Percent complete: 9.6%; Average loss: 3.8024 Iteration: 385; Percent complete: 9.6%; Average loss: 3.8597 Iteration: 386; Percent complete: 9.7%; Average loss: 3.8691 Iteration: 387; Percent complete: 9.7%; Average loss: 3.6374 Iteration: 388; Percent complete: 9.7%; Average loss: 3.8478 Iteration: 389; Percent complete: 9.7%; Average loss: 3.8218 Iteration: 390; Percent complete: 9.8%; Average loss: 3.8917 Iteration: 391; Percent complete: 9.8%; Average loss: 3.8123 Iteration: 392; Percent complete: 9.8%; Average loss: 3.9453 Iteration: 393; Percent complete: 9.8%; Average loss: 3.9331 Iteration: 394; Percent complete: 9.8%; Average loss: 4.2270 Iteration: 395; Percent complete: 9.9%; Average loss: 3.9430 Iteration: 396; Percent complete: 9.9%; Average loss: 3.8370 Iteration: 397; Percent complete: 9.9%; Average loss: 3.8744 Iteration: 398; Percent complete: 10.0%; Average loss: 3.6739 Iteration: 399; Percent complete: 10.0%; Average loss: 3.6270 Iteration: 400; Percent complete: 10.0%; Average loss: 3.9071 Iteration: 401; Percent complete: 10.0%; Average loss: 3.7005 Iteration: 402; Percent complete: 10.1%; Average loss: 3.7749 Iteration: 403; Percent complete: 10.1%; Average loss: 3.8736 Iteration: 404; Percent complete: 10.1%; Average loss: 3.7603 Iteration: 405; Percent complete: 10.1%; Average loss: 3.8011 Iteration: 406; Percent complete: 10.2%; Average loss: 3.7235 Iteration: 407; Percent complete: 10.2%; Average loss: 3.8097 Iteration: 408; Percent complete: 10.2%; Average loss: 3.9003 Iteration: 409; Percent complete: 10.2%; Average loss: 3.6257 Iteration: 410; Percent complete: 10.2%; Average loss: 3.6350 Iteration: 411; Percent complete: 10.3%; Average loss: 3.6961 Iteration: 412; Percent complete: 10.3%; Average loss: 3.8720 Iteration: 413; Percent complete: 10.3%; Average loss: 3.9186 Iteration: 414; Percent complete: 10.3%; Average loss: 3.9477 Iteration: 415; Percent complete: 10.4%; Average loss: 3.8339 Iteration: 416; Percent complete: 10.4%; Average loss: 3.3875 Iteration: 417; Percent complete: 10.4%; Average loss: 3.8229 Iteration: 418; Percent complete: 10.4%; Average loss: 3.7367 Iteration: 419; Percent complete: 10.5%; Average loss: 3.5100 Iteration: 420; Percent complete: 10.5%; Average loss: 3.8490 Iteration: 421; Percent complete: 10.5%; Average loss: 3.6847 Iteration: 422; Percent complete: 10.5%; Average loss: 3.5401 Iteration: 423; Percent complete: 10.6%; Average loss: 3.7410 Iteration: 424; Percent complete: 10.6%; Average loss: 3.9216 Iteration: 425; Percent complete: 10.6%; Average loss: 4.0085 Iteration: 426; Percent complete: 10.7%; Average loss: 3.9630 Iteration: 427; Percent complete: 10.7%; Average loss: 3.7315 Iteration: 428; Percent complete: 10.7%; Average loss: 3.8792 Iteration: 429; Percent complete: 10.7%; Average loss: 3.7179 Iteration: 430; Percent complete: 10.8%; Average loss: 3.9187 Iteration: 431; Percent complete: 10.8%; Average loss: 3.9548 Iteration: 432; Percent complete: 10.8%; Average loss: 4.1301 Iteration: 433; Percent complete: 10.8%; Average loss: 3.8412 Iteration: 434; Percent complete: 10.8%; Average loss: 3.8828 Iteration: 435; Percent complete: 10.9%; Average loss: 3.8534 Iteration: 436; Percent complete: 10.9%; Average loss: 3.7988 Iteration: 437; Percent complete: 10.9%; Average loss: 3.5906 Iteration: 438; Percent complete: 10.9%; Average loss: 3.5844 Iteration: 439; Percent complete: 11.0%; Average loss: 3.7842 Iteration: 440; Percent complete: 11.0%; Average loss: 3.8500 Iteration: 441; Percent complete: 11.0%; Average loss: 3.8632 Iteration: 442; Percent complete: 11.1%; Average loss: 3.7985 Iteration: 443; Percent complete: 11.1%; Average loss: 3.4788 Iteration: 444; Percent complete: 11.1%; Average loss: 3.8406 Iteration: 445; Percent complete: 11.1%; Average loss: 4.0159 Iteration: 446; Percent complete: 11.2%; Average loss: 3.8815 Iteration: 447; Percent complete: 11.2%; Average loss: 3.8677 Iteration: 448; Percent complete: 11.2%; Average loss: 3.9927 Iteration: 449; Percent complete: 11.2%; Average loss: 3.9073 Iteration: 450; Percent complete: 11.2%; Average loss: 3.6929 Iteration: 451; Percent complete: 11.3%; Average loss: 3.9500 Iteration: 452; Percent complete: 11.3%; Average loss: 3.6809 Iteration: 453; Percent complete: 11.3%; Average loss: 3.5997 Iteration: 454; Percent complete: 11.3%; Average loss: 3.7570 Iteration: 455; Percent complete: 11.4%; Average loss: 3.6326 Iteration: 456; Percent complete: 11.4%; Average loss: 3.8147 Iteration: 457; Percent complete: 11.4%; Average loss: 3.6579 Iteration: 458; Percent complete: 11.5%; Average loss: 4.0057 Iteration: 459; Percent complete: 11.5%; Average loss: 3.8790 Iteration: 460; Percent complete: 11.5%; Average loss: 3.7212 Iteration: 461; Percent complete: 11.5%; Average loss: 3.8343 Iteration: 462; Percent complete: 11.6%; Average loss: 3.7305 Iteration: 463; Percent complete: 11.6%; Average loss: 3.5277 Iteration: 464; Percent complete: 11.6%; Average loss: 3.7842 Iteration: 465; Percent complete: 11.6%; Average loss: 3.8054 Iteration: 466; Percent complete: 11.7%; Average loss: 3.6037 Iteration: 467; Percent complete: 11.7%; Average loss: 3.5950 Iteration: 468; Percent complete: 11.7%; Average loss: 4.0011 Iteration: 469; Percent complete: 11.7%; Average loss: 3.8815 Iteration: 470; Percent complete: 11.8%; Average loss: 3.6975 Iteration: 471; Percent complete: 11.8%; Average loss: 3.7235 Iteration: 472; Percent complete: 11.8%; Average loss: 3.7252 Iteration: 473; Percent complete: 11.8%; Average loss: 3.3677 Iteration: 474; Percent complete: 11.8%; Average loss: 3.7972 Iteration: 475; Percent complete: 11.9%; Average loss: 3.8338 Iteration: 476; Percent complete: 11.9%; Average loss: 3.7517 Iteration: 477; Percent complete: 11.9%; Average loss: 3.8373 Iteration: 478; Percent complete: 11.9%; Average loss: 3.8766 Iteration: 479; Percent complete: 12.0%; Average loss: 3.7268 Iteration: 480; Percent complete: 12.0%; Average loss: 3.6228 Iteration: 481; Percent complete: 12.0%; Average loss: 3.7208 Iteration: 482; Percent complete: 12.0%; Average loss: 3.7277 Iteration: 483; Percent complete: 12.1%; Average loss: 3.8022 Iteration: 484; Percent complete: 12.1%; Average loss: 3.8443 Iteration: 485; Percent complete: 12.1%; Average loss: 3.7321 Iteration: 486; Percent complete: 12.2%; Average loss: 4.0171 Iteration: 487; Percent complete: 12.2%; Average loss: 4.0877 Iteration: 488; Percent complete: 12.2%; Average loss: 3.7467 Iteration: 489; Percent complete: 12.2%; Average loss: 3.9557 Iteration: 490; Percent complete: 12.2%; Average loss: 3.4506 Iteration: 491; Percent complete: 12.3%; Average loss: 4.0426 Iteration: 492; Percent complete: 12.3%; Average loss: 3.6859 Iteration: 493; Percent complete: 12.3%; Average loss: 3.6495 Iteration: 494; Percent complete: 12.3%; Average loss: 3.7113 Iteration: 495; Percent complete: 12.4%; Average loss: 3.7489 Iteration: 496; Percent complete: 12.4%; Average loss: 3.8658 Iteration: 497; Percent complete: 12.4%; Average loss: 3.7115 Iteration: 498; Percent complete: 12.4%; Average loss: 3.4833 Iteration: 499; Percent complete: 12.5%; Average loss: 3.9535 Iteration: 500; Percent complete: 12.5%; Average loss: 3.6378 Iteration: 501; Percent complete: 12.5%; Average loss: 3.9160 Iteration: 502; Percent complete: 12.6%; Average loss: 3.6221 Iteration: 503; Percent complete: 12.6%; Average loss: 3.9835 Iteration: 504; Percent complete: 12.6%; Average loss: 3.9040 Iteration: 505; Percent complete: 12.6%; Average loss: 3.8058 Iteration: 506; Percent complete: 12.7%; Average loss: 3.8010 Iteration: 507; Percent complete: 12.7%; Average loss: 3.6834 Iteration: 508; Percent complete: 12.7%; Average loss: 3.8133 Iteration: 509; Percent complete: 12.7%; Average loss: 3.7315 Iteration: 510; Percent complete: 12.8%; Average loss: 3.9426 Iteration: 511; Percent complete: 12.8%; Average loss: 3.6938 Iteration: 512; Percent complete: 12.8%; Average loss: 3.5216 Iteration: 513; Percent complete: 12.8%; Average loss: 4.0600 Iteration: 514; Percent complete: 12.8%; Average loss: 3.7644 Iteration: 515; Percent complete: 12.9%; Average loss: 3.8841 Iteration: 516; Percent complete: 12.9%; Average loss: 3.7674 Iteration: 517; Percent complete: 12.9%; Average loss: 3.8615 Iteration: 518; Percent complete: 13.0%; Average loss: 3.6034 Iteration: 519; Percent complete: 13.0%; Average loss: 3.9064 Iteration: 520; Percent complete: 13.0%; Average loss: 3.8650 Iteration: 521; Percent complete: 13.0%; Average loss: 3.7300 Iteration: 522; Percent complete: 13.1%; Average loss: 3.5175 Iteration: 523; Percent complete: 13.1%; Average loss: 3.6775 Iteration: 524; Percent complete: 13.1%; Average loss: 3.6062 Iteration: 525; Percent complete: 13.1%; Average loss: 3.7345 Iteration: 526; Percent complete: 13.2%; Average loss: 3.5766 Iteration: 527; Percent complete: 13.2%; Average loss: 3.7572 Iteration: 528; Percent complete: 13.2%; Average loss: 3.7561 Iteration: 529; Percent complete: 13.2%; Average loss: 3.7658 Iteration: 530; Percent complete: 13.2%; Average loss: 3.7251 Iteration: 531; Percent complete: 13.3%; Average loss: 3.7484 Iteration: 532; Percent complete: 13.3%; Average loss: 3.6960 Iteration: 533; Percent complete: 13.3%; Average loss: 3.7007 Iteration: 534; Percent complete: 13.4%; Average loss: 3.6827 Iteration: 535; Percent complete: 13.4%; Average loss: 3.7515 Iteration: 536; Percent complete: 13.4%; Average loss: 3.9892 Iteration: 537; Percent complete: 13.4%; Average loss: 3.6554 Iteration: 538; Percent complete: 13.5%; Average loss: 3.6784 Iteration: 539; Percent complete: 13.5%; Average loss: 3.9004 Iteration: 540; Percent complete: 13.5%; Average loss: 3.7029 Iteration: 541; Percent complete: 13.5%; Average loss: 3.6588 Iteration: 542; Percent complete: 13.6%; Average loss: 3.4758 Iteration: 543; Percent complete: 13.6%; Average loss: 3.6862 Iteration: 544; Percent complete: 13.6%; Average loss: 3.6165 Iteration: 545; Percent complete: 13.6%; Average loss: 3.7184 Iteration: 546; Percent complete: 13.7%; Average loss: 3.7494 Iteration: 547; Percent complete: 13.7%; Average loss: 3.6793 Iteration: 548; Percent complete: 13.7%; Average loss: 3.7853 Iteration: 549; Percent complete: 13.7%; Average loss: 3.8128 Iteration: 550; Percent complete: 13.8%; Average loss: 3.8737 Iteration: 551; Percent complete: 13.8%; Average loss: 3.6005 Iteration: 552; Percent complete: 13.8%; Average loss: 3.5577 Iteration: 553; Percent complete: 13.8%; Average loss: 4.0173 Iteration: 554; Percent complete: 13.9%; Average loss: 3.8951 Iteration: 555; Percent complete: 13.9%; Average loss: 3.5867 Iteration: 556; Percent complete: 13.9%; Average loss: 3.7899 Iteration: 557; Percent complete: 13.9%; Average loss: 3.9546 Iteration: 558; Percent complete: 14.0%; Average loss: 3.8706 Iteration: 559; Percent complete: 14.0%; Average loss: 3.8335 Iteration: 560; Percent complete: 14.0%; Average loss: 3.4553 Iteration: 561; Percent complete: 14.0%; Average loss: 3.6189 Iteration: 562; Percent complete: 14.1%; Average loss: 3.5142 Iteration: 563; Percent complete: 14.1%; Average loss: 3.8603 Iteration: 564; Percent complete: 14.1%; Average loss: 3.7313 Iteration: 565; Percent complete: 14.1%; Average loss: 3.7744 Iteration: 566; Percent complete: 14.1%; Average loss: 3.5629 Iteration: 567; Percent complete: 14.2%; Average loss: 3.8631 Iteration: 568; Percent complete: 14.2%; Average loss: 3.8204 Iteration: 569; Percent complete: 14.2%; Average loss: 3.5985 Iteration: 570; Percent complete: 14.2%; Average loss: 3.7693 Iteration: 571; Percent complete: 14.3%; Average loss: 3.6897 Iteration: 572; Percent complete: 14.3%; Average loss: 3.5227 Iteration: 573; Percent complete: 14.3%; Average loss: 3.5399 Iteration: 574; Percent complete: 14.3%; Average loss: 3.7187 Iteration: 575; Percent complete: 14.4%; Average loss: 3.5697 Iteration: 576; Percent complete: 14.4%; Average loss: 3.5280 Iteration: 577; Percent complete: 14.4%; Average loss: 3.5168 Iteration: 578; Percent complete: 14.4%; Average loss: 3.9495 Iteration: 579; Percent complete: 14.5%; Average loss: 3.7273 Iteration: 580; Percent complete: 14.5%; Average loss: 3.7166 Iteration: 581; Percent complete: 14.5%; Average loss: 3.8751 Iteration: 582; Percent complete: 14.5%; Average loss: 3.5214 Iteration: 583; Percent complete: 14.6%; Average loss: 3.6004 Iteration: 584; Percent complete: 14.6%; Average loss: 3.6483 Iteration: 585; Percent complete: 14.6%; Average loss: 3.6591 Iteration: 586; Percent complete: 14.6%; Average loss: 3.6764 Iteration: 587; Percent complete: 14.7%; Average loss: 3.6546 Iteration: 588; Percent complete: 14.7%; Average loss: 3.7109 Iteration: 589; Percent complete: 14.7%; Average loss: 3.7925 Iteration: 590; Percent complete: 14.8%; Average loss: 3.5920 Iteration: 591; Percent complete: 14.8%; Average loss: 3.7937 Iteration: 592; Percent complete: 14.8%; Average loss: 3.5959 Iteration: 593; Percent complete: 14.8%; Average loss: 3.8230 Iteration: 594; Percent complete: 14.8%; Average loss: 3.3767 Iteration: 595; Percent complete: 14.9%; Average loss: 3.7708 Iteration: 596; Percent complete: 14.9%; Average loss: 3.7534 Iteration: 597; Percent complete: 14.9%; Average loss: 3.4622 Iteration: 598; Percent complete: 14.9%; Average loss: 3.6922 Iteration: 599; Percent complete: 15.0%; Average loss: 3.7130 Iteration: 600; Percent complete: 15.0%; Average loss: 3.4693 Iteration: 601; Percent complete: 15.0%; Average loss: 3.6567 Iteration: 602; Percent complete: 15.0%; Average loss: 3.7524 Iteration: 603; Percent complete: 15.1%; Average loss: 3.7098 Iteration: 604; Percent complete: 15.1%; Average loss: 3.2016 Iteration: 605; Percent complete: 15.1%; Average loss: 3.5936 Iteration: 606; Percent complete: 15.2%; Average loss: 3.3464 Iteration: 607; Percent complete: 15.2%; Average loss: 3.6801 Iteration: 608; Percent complete: 15.2%; Average loss: 3.5281 Iteration: 609; Percent complete: 15.2%; Average loss: 3.8112 Iteration: 610; Percent complete: 15.2%; Average loss: 3.6066 Iteration: 611; Percent complete: 15.3%; Average loss: 3.7661 Iteration: 612; Percent complete: 15.3%; Average loss: 3.7468 Iteration: 613; Percent complete: 15.3%; Average loss: 3.8694 Iteration: 614; Percent complete: 15.3%; Average loss: 3.7171 Iteration: 615; Percent complete: 15.4%; Average loss: 3.5649 Iteration: 616; Percent complete: 15.4%; Average loss: 3.7099 Iteration: 617; Percent complete: 15.4%; Average loss: 3.7501 Iteration: 618; Percent complete: 15.4%; Average loss: 3.7276 Iteration: 619; Percent complete: 15.5%; Average loss: 3.5047 Iteration: 620; Percent complete: 15.5%; Average loss: 3.6745 Iteration: 621; Percent complete: 15.5%; Average loss: 3.5764 Iteration: 622; Percent complete: 15.6%; Average loss: 3.5327 Iteration: 623; Percent complete: 15.6%; Average loss: 3.6056 Iteration: 624; Percent complete: 15.6%; Average loss: 3.6391 Iteration: 625; Percent complete: 15.6%; Average loss: 3.5071 Iteration: 626; Percent complete: 15.7%; Average loss: 3.6052 Iteration: 627; Percent complete: 15.7%; Average loss: 3.4532 Iteration: 628; Percent complete: 15.7%; Average loss: 3.9024 Iteration: 629; Percent complete: 15.7%; Average loss: 3.6641 Iteration: 630; Percent complete: 15.8%; Average loss: 3.6032 Iteration: 631; Percent complete: 15.8%; Average loss: 3.6324 Iteration: 632; Percent complete: 15.8%; Average loss: 3.4973 Iteration: 633; Percent complete: 15.8%; Average loss: 3.4555 Iteration: 634; Percent complete: 15.8%; Average loss: 3.7865 Iteration: 635; Percent complete: 15.9%; Average loss: 3.5574 Iteration: 636; Percent complete: 15.9%; Average loss: 3.4455 Iteration: 637; Percent complete: 15.9%; Average loss: 3.4501 Iteration: 638; Percent complete: 16.0%; Average loss: 3.6886 Iteration: 639; Percent complete: 16.0%; Average loss: 3.6609 Iteration: 640; Percent complete: 16.0%; Average loss: 3.4877 Iteration: 641; Percent complete: 16.0%; Average loss: 3.7034 Iteration: 642; Percent complete: 16.1%; Average loss: 3.6957 Iteration: 643; Percent complete: 16.1%; Average loss: 3.6035 Iteration: 644; Percent complete: 16.1%; Average loss: 3.7237 Iteration: 645; Percent complete: 16.1%; Average loss: 3.7442 Iteration: 646; Percent complete: 16.2%; Average loss: 3.6350 Iteration: 647; Percent complete: 16.2%; Average loss: 3.8434 Iteration: 648; Percent complete: 16.2%; Average loss: 3.4888 Iteration: 649; Percent complete: 16.2%; Average loss: 4.0369 Iteration: 650; Percent complete: 16.2%; Average loss: 3.7598 Iteration: 651; Percent complete: 16.3%; Average loss: 3.7341 Iteration: 652; Percent complete: 16.3%; Average loss: 3.6495 Iteration: 653; Percent complete: 16.3%; Average loss: 3.4404 Iteration: 654; Percent complete: 16.4%; Average loss: 3.5015 Iteration: 655; Percent complete: 16.4%; Average loss: 3.5511 Iteration: 656; Percent complete: 16.4%; Average loss: 3.4211 Iteration: 657; Percent complete: 16.4%; Average loss: 3.5290 Iteration: 658; Percent complete: 16.4%; Average loss: 3.6582 Iteration: 659; Percent complete: 16.5%; Average loss: 4.0355 Iteration: 660; Percent complete: 16.5%; Average loss: 3.6969 Iteration: 661; Percent complete: 16.5%; Average loss: 3.5901 Iteration: 662; Percent complete: 16.6%; Average loss: 3.6491 Iteration: 663; Percent complete: 16.6%; Average loss: 3.5773 Iteration: 664; Percent complete: 16.6%; Average loss: 3.5285 Iteration: 665; Percent complete: 16.6%; Average loss: 3.6456 Iteration: 666; Percent complete: 16.7%; Average loss: 3.7512 Iteration: 667; Percent complete: 16.7%; Average loss: 3.7115 Iteration: 668; Percent complete: 16.7%; Average loss: 3.4373 Iteration: 669; Percent complete: 16.7%; Average loss: 3.6150 Iteration: 670; Percent complete: 16.8%; Average loss: 3.7668 Iteration: 671; Percent complete: 16.8%; Average loss: 3.4801 Iteration: 672; Percent complete: 16.8%; Average loss: 3.5567 Iteration: 673; Percent complete: 16.8%; Average loss: 3.7417 Iteration: 674; Percent complete: 16.9%; Average loss: 3.5684 Iteration: 675; Percent complete: 16.9%; Average loss: 3.8948 Iteration: 676; Percent complete: 16.9%; Average loss: 3.5138 Iteration: 677; Percent complete: 16.9%; Average loss: 3.5588 Iteration: 678; Percent complete: 17.0%; Average loss: 3.8463 Iteration: 679; Percent complete: 17.0%; Average loss: 3.7210 Iteration: 680; Percent complete: 17.0%; Average loss: 3.5384 Iteration: 681; Percent complete: 17.0%; Average loss: 3.6103 Iteration: 682; Percent complete: 17.1%; Average loss: 3.7068 Iteration: 683; Percent complete: 17.1%; Average loss: 3.6307 Iteration: 684; Percent complete: 17.1%; Average loss: 3.3692 Iteration: 685; Percent complete: 17.1%; Average loss: 3.5162 Iteration: 686; Percent complete: 17.2%; Average loss: 3.6775 Iteration: 687; Percent complete: 17.2%; Average loss: 3.9015 Iteration: 688; Percent complete: 17.2%; Average loss: 3.3498 Iteration: 689; Percent complete: 17.2%; Average loss: 3.6023 Iteration: 690; Percent complete: 17.2%; Average loss: 3.5819 Iteration: 691; Percent complete: 17.3%; Average loss: 3.5788 Iteration: 692; Percent complete: 17.3%; Average loss: 3.6692 Iteration: 693; Percent complete: 17.3%; Average loss: 3.6891 Iteration: 694; Percent complete: 17.3%; Average loss: 3.6537 Iteration: 695; Percent complete: 17.4%; Average loss: 3.7697 Iteration: 696; Percent complete: 17.4%; Average loss: 3.4102 Iteration: 697; Percent complete: 17.4%; Average loss: 3.5535 Iteration: 698; Percent complete: 17.4%; Average loss: 3.8169 Iteration: 699; Percent complete: 17.5%; Average loss: 3.3914 Iteration: 700; Percent complete: 17.5%; Average loss: 4.0585 Iteration: 701; Percent complete: 17.5%; Average loss: 3.4453 Iteration: 702; Percent complete: 17.5%; Average loss: 3.9283 Iteration: 703; Percent complete: 17.6%; Average loss: 3.7141 Iteration: 704; Percent complete: 17.6%; Average loss: 3.5471 Iteration: 705; Percent complete: 17.6%; Average loss: 3.7991 Iteration: 706; Percent complete: 17.6%; Average loss: 3.6785 Iteration: 707; Percent complete: 17.7%; Average loss: 3.6736 Iteration: 708; Percent complete: 17.7%; Average loss: 3.4598 Iteration: 709; Percent complete: 17.7%; Average loss: 3.5478 Iteration: 710; Percent complete: 17.8%; Average loss: 3.5446 Iteration: 711; Percent complete: 17.8%; Average loss: 3.6895 Iteration: 712; Percent complete: 17.8%; Average loss: 3.8355 Iteration: 713; Percent complete: 17.8%; Average loss: 3.5265 Iteration: 714; Percent complete: 17.8%; Average loss: 3.7500 Iteration: 715; Percent complete: 17.9%; Average loss: 3.5666 Iteration: 716; Percent complete: 17.9%; Average loss: 3.5981 Iteration: 717; Percent complete: 17.9%; Average loss: 3.6574 Iteration: 718; Percent complete: 17.9%; Average loss: 3.8789 Iteration: 719; Percent complete: 18.0%; Average loss: 3.6112 Iteration: 720; Percent complete: 18.0%; Average loss: 3.7686 Iteration: 721; Percent complete: 18.0%; Average loss: 3.6448 Iteration: 722; Percent complete: 18.1%; Average loss: 3.2403 Iteration: 723; Percent complete: 18.1%; Average loss: 3.8176 Iteration: 724; Percent complete: 18.1%; Average loss: 3.4604 Iteration: 725; Percent complete: 18.1%; Average loss: 4.0421 Iteration: 726; Percent complete: 18.1%; Average loss: 3.7189 Iteration: 727; Percent complete: 18.2%; Average loss: 3.7609 Iteration: 728; Percent complete: 18.2%; Average loss: 3.3972 Iteration: 729; Percent complete: 18.2%; Average loss: 3.7267 Iteration: 730; Percent complete: 18.2%; Average loss: 3.4458 Iteration: 731; Percent complete: 18.3%; Average loss: 3.5687 Iteration: 732; Percent complete: 18.3%; Average loss: 3.6197 Iteration: 733; Percent complete: 18.3%; Average loss: 3.8144 Iteration: 734; Percent complete: 18.4%; Average loss: 3.6975 Iteration: 735; Percent complete: 18.4%; Average loss: 3.6059 Iteration: 736; Percent complete: 18.4%; Average loss: 3.4335 Iteration: 737; Percent complete: 18.4%; Average loss: 3.4884 Iteration: 738; Percent complete: 18.4%; Average loss: 3.7238 Iteration: 739; Percent complete: 18.5%; Average loss: 3.7177 Iteration: 740; Percent complete: 18.5%; Average loss: 3.8108 Iteration: 741; Percent complete: 18.5%; Average loss: 3.4599 Iteration: 742; Percent complete: 18.6%; Average loss: 3.6039 Iteration: 743; Percent complete: 18.6%; Average loss: 3.6901 Iteration: 744; Percent complete: 18.6%; Average loss: 3.6071 Iteration: 745; Percent complete: 18.6%; Average loss: 3.4928 Iteration: 746; Percent complete: 18.6%; Average loss: 3.4580 Iteration: 747; Percent complete: 18.7%; Average loss: 3.5328 Iteration: 748; Percent complete: 18.7%; Average loss: 3.5437 Iteration: 749; Percent complete: 18.7%; Average loss: 3.6509 Iteration: 750; Percent complete: 18.8%; Average loss: 3.5360 Iteration: 751; Percent complete: 18.8%; Average loss: 3.5073 Iteration: 752; Percent complete: 18.8%; Average loss: 3.6168 Iteration: 753; Percent complete: 18.8%; Average loss: 3.7231 Iteration: 754; Percent complete: 18.9%; Average loss: 3.6571 Iteration: 755; Percent complete: 18.9%; Average loss: 3.6777 Iteration: 756; Percent complete: 18.9%; Average loss: 3.4329 Iteration: 757; Percent complete: 18.9%; Average loss: 3.6043 Iteration: 758; Percent complete: 18.9%; Average loss: 3.4039 Iteration: 759; Percent complete: 19.0%; Average loss: 3.2907 Iteration: 760; Percent complete: 19.0%; Average loss: 3.6318 Iteration: 761; Percent complete: 19.0%; Average loss: 3.7274 Iteration: 762; Percent complete: 19.1%; Average loss: 3.6796 Iteration: 763; Percent complete: 19.1%; Average loss: 3.3866 Iteration: 764; Percent complete: 19.1%; Average loss: 3.6012 Iteration: 765; Percent complete: 19.1%; Average loss: 3.4232 Iteration: 766; Percent complete: 19.1%; Average loss: 3.7472 Iteration: 767; Percent complete: 19.2%; Average loss: 3.5249 Iteration: 768; Percent complete: 19.2%; Average loss: 3.3999 Iteration: 769; Percent complete: 19.2%; Average loss: 3.7207 Iteration: 770; Percent complete: 19.2%; Average loss: 3.7767 Iteration: 771; Percent complete: 19.3%; Average loss: 3.7148 Iteration: 772; Percent complete: 19.3%; Average loss: 3.6814 Iteration: 773; Percent complete: 19.3%; Average loss: 3.6072 Iteration: 774; Percent complete: 19.4%; Average loss: 3.8256 Iteration: 775; Percent complete: 19.4%; Average loss: 3.4776 Iteration: 776; Percent complete: 19.4%; Average loss: 3.7539 Iteration: 777; Percent complete: 19.4%; Average loss: 3.4912 Iteration: 778; Percent complete: 19.4%; Average loss: 3.5462 Iteration: 779; Percent complete: 19.5%; Average loss: 3.7244 Iteration: 780; Percent complete: 19.5%; Average loss: 3.4170 Iteration: 781; Percent complete: 19.5%; Average loss: 3.5676 Iteration: 782; Percent complete: 19.6%; Average loss: 3.3839 Iteration: 783; Percent complete: 19.6%; Average loss: 3.6389 Iteration: 784; Percent complete: 19.6%; Average loss: 3.6606 Iteration: 785; Percent complete: 19.6%; Average loss: 3.4910 Iteration: 786; Percent complete: 19.7%; Average loss: 3.5063 Iteration: 787; Percent complete: 19.7%; Average loss: 3.5234 Iteration: 788; Percent complete: 19.7%; Average loss: 3.6695 Iteration: 789; Percent complete: 19.7%; Average loss: 3.5038 Iteration: 790; Percent complete: 19.8%; Average loss: 3.5968 Iteration: 791; Percent complete: 19.8%; Average loss: 3.6817 Iteration: 792; Percent complete: 19.8%; Average loss: 3.7135 Iteration: 793; Percent complete: 19.8%; Average loss: 3.3524 Iteration: 794; Percent complete: 19.9%; Average loss: 3.1859 Iteration: 795; Percent complete: 19.9%; Average loss: 3.2480 Iteration: 796; Percent complete: 19.9%; Average loss: 3.3627 Iteration: 797; Percent complete: 19.9%; Average loss: 3.7313 Iteration: 798; Percent complete: 20.0%; Average loss: 3.7514 Iteration: 799; Percent complete: 20.0%; Average loss: 3.6394 Iteration: 800; Percent complete: 20.0%; Average loss: 3.4716 Iteration: 801; Percent complete: 20.0%; Average loss: 3.7387 Iteration: 802; Percent complete: 20.1%; Average loss: 3.7363 Iteration: 803; Percent complete: 20.1%; Average loss: 3.2854 Iteration: 804; Percent complete: 20.1%; Average loss: 3.6841 Iteration: 805; Percent complete: 20.1%; Average loss: 3.6283 Iteration: 806; Percent complete: 20.2%; Average loss: 3.7519 Iteration: 807; Percent complete: 20.2%; Average loss: 3.8107 Iteration: 808; Percent complete: 20.2%; Average loss: 3.5295 Iteration: 809; Percent complete: 20.2%; Average loss: 3.7516 Iteration: 810; Percent complete: 20.2%; Average loss: 3.3987 Iteration: 811; Percent complete: 20.3%; Average loss: 3.4302 Iteration: 812; Percent complete: 20.3%; Average loss: 3.6803 Iteration: 813; Percent complete: 20.3%; Average loss: 3.7482 Iteration: 814; Percent complete: 20.3%; Average loss: 3.2650 Iteration: 815; Percent complete: 20.4%; Average loss: 3.3059 Iteration: 816; Percent complete: 20.4%; Average loss: 3.5659 Iteration: 817; Percent complete: 20.4%; Average loss: 3.3079 Iteration: 818; Percent complete: 20.4%; Average loss: 3.6516 Iteration: 819; Percent complete: 20.5%; Average loss: 3.3066 Iteration: 820; Percent complete: 20.5%; Average loss: 3.6482 Iteration: 821; Percent complete: 20.5%; Average loss: 3.3684 Iteration: 822; Percent complete: 20.5%; Average loss: 3.5800 Iteration: 823; Percent complete: 20.6%; Average loss: 3.7340 Iteration: 824; Percent complete: 20.6%; Average loss: 3.6185 Iteration: 825; Percent complete: 20.6%; Average loss: 3.3914 Iteration: 826; Percent complete: 20.6%; Average loss: 3.6667 Iteration: 827; Percent complete: 20.7%; Average loss: 3.5500 Iteration: 828; Percent complete: 20.7%; Average loss: 3.3266 Iteration: 829; Percent complete: 20.7%; Average loss: 3.7449 Iteration: 830; Percent complete: 20.8%; Average loss: 3.5292 Iteration: 831; Percent complete: 20.8%; Average loss: 3.3897 Iteration: 832; Percent complete: 20.8%; Average loss: 3.0412 Iteration: 833; Percent complete: 20.8%; Average loss: 3.4952 Iteration: 834; Percent complete: 20.8%; Average loss: 3.7136 Iteration: 835; Percent complete: 20.9%; Average loss: 3.7280 Iteration: 836; Percent complete: 20.9%; Average loss: 3.7350 Iteration: 837; Percent complete: 20.9%; Average loss: 3.6793 Iteration: 838; Percent complete: 20.9%; Average loss: 3.8289 Iteration: 839; Percent complete: 21.0%; Average loss: 3.6341 Iteration: 840; Percent complete: 21.0%; Average loss: 3.4519 Iteration: 841; Percent complete: 21.0%; Average loss: 3.8600 Iteration: 842; Percent complete: 21.1%; Average loss: 3.6469 Iteration: 843; Percent complete: 21.1%; Average loss: 3.4329 Iteration: 844; Percent complete: 21.1%; Average loss: 3.4779 Iteration: 845; Percent complete: 21.1%; Average loss: 3.5559 Iteration: 846; Percent complete: 21.1%; Average loss: 3.5672 Iteration: 847; Percent complete: 21.2%; Average loss: 3.5676 Iteration: 848; Percent complete: 21.2%; Average loss: 3.4539 Iteration: 849; Percent complete: 21.2%; Average loss: 3.3791 Iteration: 850; Percent complete: 21.2%; Average loss: 3.3969 Iteration: 851; Percent complete: 21.3%; Average loss: 3.3837 Iteration: 852; Percent complete: 21.3%; Average loss: 3.6185 Iteration: 853; Percent complete: 21.3%; Average loss: 3.6694 Iteration: 854; Percent complete: 21.3%; Average loss: 3.5222 Iteration: 855; Percent complete: 21.4%; Average loss: 3.5786 Iteration: 856; Percent complete: 21.4%; Average loss: 3.3268 Iteration: 857; Percent complete: 21.4%; Average loss: 3.3918 Iteration: 858; Percent complete: 21.4%; Average loss: 3.8086 Iteration: 859; Percent complete: 21.5%; Average loss: 3.5997 Iteration: 860; Percent complete: 21.5%; Average loss: 3.5508 Iteration: 861; Percent complete: 21.5%; Average loss: 3.4994 Iteration: 862; Percent complete: 21.6%; Average loss: 3.6349 Iteration: 863; Percent complete: 21.6%; Average loss: 3.6527 Iteration: 864; Percent complete: 21.6%; Average loss: 3.5222 Iteration: 865; Percent complete: 21.6%; Average loss: 3.7328 Iteration: 866; Percent complete: 21.6%; Average loss: 3.2870 Iteration: 867; Percent complete: 21.7%; Average loss: 3.5389 Iteration: 868; Percent complete: 21.7%; Average loss: 3.1759 Iteration: 869; Percent complete: 21.7%; Average loss: 3.6047 Iteration: 870; Percent complete: 21.8%; Average loss: 3.2560 Iteration: 871; Percent complete: 21.8%; Average loss: 3.6376 Iteration: 872; Percent complete: 21.8%; Average loss: 3.4438 Iteration: 873; Percent complete: 21.8%; Average loss: 3.6804 Iteration: 874; Percent complete: 21.9%; Average loss: 3.5714 Iteration: 875; Percent complete: 21.9%; Average loss: 3.5962 Iteration: 876; Percent complete: 21.9%; Average loss: 3.4885 Iteration: 877; Percent complete: 21.9%; Average loss: 3.4258 Iteration: 878; Percent complete: 21.9%; Average loss: 3.7824 Iteration: 879; Percent complete: 22.0%; Average loss: 3.5903 Iteration: 880; Percent complete: 22.0%; Average loss: 3.4604 Iteration: 881; Percent complete: 22.0%; Average loss: 3.6968 Iteration: 882; Percent complete: 22.1%; Average loss: 3.4886 Iteration: 883; Percent complete: 22.1%; Average loss: 3.2925 Iteration: 884; Percent complete: 22.1%; Average loss: 3.5721 Iteration: 885; Percent complete: 22.1%; Average loss: 3.6917 Iteration: 886; Percent complete: 22.1%; Average loss: 3.4908 Iteration: 887; Percent complete: 22.2%; Average loss: 3.3382 Iteration: 888; Percent complete: 22.2%; Average loss: 3.4447 Iteration: 889; Percent complete: 22.2%; Average loss: 3.7334 Iteration: 890; Percent complete: 22.2%; Average loss: 3.2581 Iteration: 891; Percent complete: 22.3%; Average loss: 3.4281 Iteration: 892; Percent complete: 22.3%; Average loss: 3.8356 Iteration: 893; Percent complete: 22.3%; Average loss: 3.5299 Iteration: 894; Percent complete: 22.4%; Average loss: 3.5971 Iteration: 895; Percent complete: 22.4%; Average loss: 3.7434 Iteration: 896; Percent complete: 22.4%; Average loss: 3.6625 Iteration: 897; Percent complete: 22.4%; Average loss: 3.4300 Iteration: 898; Percent complete: 22.4%; Average loss: 3.7416 Iteration: 899; Percent complete: 22.5%; Average loss: 3.6472 Iteration: 900; Percent complete: 22.5%; Average loss: 3.3974 Iteration: 901; Percent complete: 22.5%; Average loss: 3.3092 Iteration: 902; Percent complete: 22.6%; Average loss: 3.3859 Iteration: 903; Percent complete: 22.6%; Average loss: 3.5108 Iteration: 904; Percent complete: 22.6%; Average loss: 3.4020 Iteration: 905; Percent complete: 22.6%; Average loss: 3.5062 Iteration: 906; Percent complete: 22.7%; Average loss: 3.6086 Iteration: 907; Percent complete: 22.7%; Average loss: 3.3917 Iteration: 908; Percent complete: 22.7%; Average loss: 3.3340 Iteration: 909; Percent complete: 22.7%; Average loss: 3.4454 Iteration: 910; Percent complete: 22.8%; Average loss: 3.6127 Iteration: 911; Percent complete: 22.8%; Average loss: 3.5597 Iteration: 912; Percent complete: 22.8%; Average loss: 3.5330 Iteration: 913; Percent complete: 22.8%; Average loss: 3.3913 Iteration: 914; Percent complete: 22.9%; Average loss: 3.5077 Iteration: 915; Percent complete: 22.9%; Average loss: 3.4181 Iteration: 916; Percent complete: 22.9%; Average loss: 3.5063 Iteration: 917; Percent complete: 22.9%; Average loss: 3.5189 Iteration: 918; Percent complete: 22.9%; Average loss: 3.4923 Iteration: 919; Percent complete: 23.0%; Average loss: 3.4814 Iteration: 920; Percent complete: 23.0%; Average loss: 3.3413 Iteration: 921; Percent complete: 23.0%; Average loss: 3.4142 Iteration: 922; Percent complete: 23.1%; Average loss: 3.3171 Iteration: 923; Percent complete: 23.1%; Average loss: 3.5123 Iteration: 924; Percent complete: 23.1%; Average loss: 3.4350 Iteration: 925; Percent complete: 23.1%; Average loss: 3.7331 Iteration: 926; Percent complete: 23.2%; Average loss: 3.4948 Iteration: 927; Percent complete: 23.2%; Average loss: 3.4705 Iteration: 928; Percent complete: 23.2%; Average loss: 3.5541 Iteration: 929; Percent complete: 23.2%; Average loss: 3.2701 Iteration: 930; Percent complete: 23.2%; Average loss: 3.6191 Iteration: 931; Percent complete: 23.3%; Average loss: 3.2687 Iteration: 932; Percent complete: 23.3%; Average loss: 3.5127 Iteration: 933; Percent complete: 23.3%; Average loss: 3.6577 Iteration: 934; Percent complete: 23.4%; Average loss: 3.4153 Iteration: 935; Percent complete: 23.4%; Average loss: 3.6011 Iteration: 936; Percent complete: 23.4%; Average loss: 3.3562 Iteration: 937; Percent complete: 23.4%; Average loss: 3.2175 Iteration: 938; Percent complete: 23.4%; Average loss: 3.5056 Iteration: 939; Percent complete: 23.5%; Average loss: 3.5648 Iteration: 940; Percent complete: 23.5%; Average loss: 3.3697 Iteration: 941; Percent complete: 23.5%; Average loss: 3.7658 Iteration: 942; Percent complete: 23.5%; Average loss: 3.5257 Iteration: 943; Percent complete: 23.6%; Average loss: 3.4436 Iteration: 944; Percent complete: 23.6%; Average loss: 3.4974 Iteration: 945; Percent complete: 23.6%; Average loss: 3.2295 Iteration: 946; Percent complete: 23.6%; Average loss: 3.6355 Iteration: 947; Percent complete: 23.7%; Average loss: 3.3571 Iteration: 948; Percent complete: 23.7%; Average loss: 3.5191 Iteration: 949; Percent complete: 23.7%; Average loss: 3.7119 Iteration: 950; Percent complete: 23.8%; Average loss: 3.2768 Iteration: 951; Percent complete: 23.8%; Average loss: 3.4776 Iteration: 952; Percent complete: 23.8%; Average loss: 3.2682 Iteration: 953; Percent complete: 23.8%; Average loss: 3.4787 Iteration: 954; Percent complete: 23.8%; Average loss: 3.4087 Iteration: 955; Percent complete: 23.9%; Average loss: 3.4209 Iteration: 956; Percent complete: 23.9%; Average loss: 3.4645 Iteration: 957; Percent complete: 23.9%; Average loss: 3.5612 Iteration: 958; Percent complete: 23.9%; Average loss: 3.4188 Iteration: 959; Percent complete: 24.0%; Average loss: 3.5346 Iteration: 960; Percent complete: 24.0%; Average loss: 3.4142 Iteration: 961; Percent complete: 24.0%; Average loss: 3.2537 Iteration: 962; Percent complete: 24.1%; Average loss: 3.4231 Iteration: 963; Percent complete: 24.1%; Average loss: 3.6446 Iteration: 964; Percent complete: 24.1%; Average loss: 3.4076 Iteration: 965; Percent complete: 24.1%; Average loss: 3.2817 Iteration: 966; Percent complete: 24.1%; Average loss: 3.4516 Iteration: 967; Percent complete: 24.2%; Average loss: 3.4942 Iteration: 968; Percent complete: 24.2%; Average loss: 3.2995 Iteration: 969; Percent complete: 24.2%; Average loss: 3.6060 Iteration: 970; Percent complete: 24.2%; Average loss: 3.7089 Iteration: 971; Percent complete: 24.3%; Average loss: 3.3577 Iteration: 972; Percent complete: 24.3%; Average loss: 3.3670 Iteration: 973; Percent complete: 24.3%; Average loss: 3.2918 Iteration: 974; Percent complete: 24.3%; Average loss: 3.4636 Iteration: 975; Percent complete: 24.4%; Average loss: 3.6155 Iteration: 976; Percent complete: 24.4%; Average loss: 3.3776 Iteration: 977; Percent complete: 24.4%; Average loss: 3.3909 Iteration: 978; Percent complete: 24.4%; Average loss: 3.2839 Iteration: 979; Percent complete: 24.5%; Average loss: 3.6619 Iteration: 980; Percent complete: 24.5%; Average loss: 3.5954 Iteration: 981; Percent complete: 24.5%; Average loss: 3.4895 Iteration: 982; Percent complete: 24.6%; Average loss: 3.4897 Iteration: 983; Percent complete: 24.6%; Average loss: 3.5542 Iteration: 984; Percent complete: 24.6%; Average loss: 3.2633 Iteration: 985; Percent complete: 24.6%; Average loss: 3.4085 Iteration: 986; Percent complete: 24.6%; Average loss: 3.7056 Iteration: 987; Percent complete: 24.7%; Average loss: 3.3413 Iteration: 988; Percent complete: 24.7%; Average loss: 3.5320 Iteration: 989; Percent complete: 24.7%; Average loss: 3.6930 Iteration: 990; Percent complete: 24.8%; Average loss: 3.2434 Iteration: 991; Percent complete: 24.8%; Average loss: 3.3358 Iteration: 992; Percent complete: 24.8%; Average loss: 3.5073 Iteration: 993; Percent complete: 24.8%; Average loss: 3.5233 Iteration: 994; Percent complete: 24.9%; Average loss: 3.5269 Iteration: 995; Percent complete: 24.9%; Average loss: 3.1489 Iteration: 996; Percent complete: 24.9%; Average loss: 3.3043 Iteration: 997; Percent complete: 24.9%; Average loss: 3.4207 Iteration: 998; Percent complete: 24.9%; Average loss: 3.2435 Iteration: 999; Percent complete: 25.0%; Average loss: 3.4865 Iteration: 1000; Percent complete: 25.0%; Average loss: 3.6380 Iteration: 1001; Percent complete: 25.0%; Average loss: 3.1771 Iteration: 1002; Percent complete: 25.1%; Average loss: 3.3559 Iteration: 1003; Percent complete: 25.1%; Average loss: 3.6952 Iteration: 1004; Percent complete: 25.1%; Average loss: 3.2310 Iteration: 1005; Percent complete: 25.1%; Average loss: 3.6138 Iteration: 1006; Percent complete: 25.1%; Average loss: 3.5824 Iteration: 1007; Percent complete: 25.2%; Average loss: 3.4058 Iteration: 1008; Percent complete: 25.2%; Average loss: 3.2312 Iteration: 1009; Percent complete: 25.2%; Average loss: 3.2858 Iteration: 1010; Percent complete: 25.2%; Average loss: 3.3956 Iteration: 1011; Percent complete: 25.3%; Average loss: 3.5197 Iteration: 1012; Percent complete: 25.3%; Average loss: 3.6270 Iteration: 1013; Percent complete: 25.3%; Average loss: 3.4288 Iteration: 1014; Percent complete: 25.4%; Average loss: 3.4374 Iteration: 1015; Percent complete: 25.4%; Average loss: 3.5147 Iteration: 1016; Percent complete: 25.4%; Average loss: 3.2789 Iteration: 1017; Percent complete: 25.4%; Average loss: 3.4532 Iteration: 1018; Percent complete: 25.4%; Average loss: 3.5277 Iteration: 1019; Percent complete: 25.5%; Average loss: 3.4648 Iteration: 1020; Percent complete: 25.5%; Average loss: 3.3900 Iteration: 1021; Percent complete: 25.5%; Average loss: 3.5176 Iteration: 1022; Percent complete: 25.6%; Average loss: 3.7292 Iteration: 1023; Percent complete: 25.6%; Average loss: 3.5338 Iteration: 1024; Percent complete: 25.6%; Average loss: 3.1601 Iteration: 1025; Percent complete: 25.6%; Average loss: 3.5410 Iteration: 1026; Percent complete: 25.7%; Average loss: 3.5743 Iteration: 1027; Percent complete: 25.7%; Average loss: 3.4632 Iteration: 1028; Percent complete: 25.7%; Average loss: 3.5518 Iteration: 1029; Percent complete: 25.7%; Average loss: 3.5062 Iteration: 1030; Percent complete: 25.8%; Average loss: 3.5108 Iteration: 1031; Percent complete: 25.8%; Average loss: 3.4114 Iteration: 1032; Percent complete: 25.8%; Average loss: 3.5395 Iteration: 1033; Percent complete: 25.8%; Average loss: 3.2386 Iteration: 1034; Percent complete: 25.9%; Average loss: 3.6287 Iteration: 1035; Percent complete: 25.9%; Average loss: 3.6047 Iteration: 1036; Percent complete: 25.9%; Average loss: 3.4071 Iteration: 1037; Percent complete: 25.9%; Average loss: 3.3066 Iteration: 1038; Percent complete: 25.9%; Average loss: 3.5398 Iteration: 1039; Percent complete: 26.0%; Average loss: 3.6242 Iteration: 1040; Percent complete: 26.0%; Average loss: 3.2621 Iteration: 1041; Percent complete: 26.0%; Average loss: 3.1681 Iteration: 1042; Percent complete: 26.1%; Average loss: 3.6318 Iteration: 1043; Percent complete: 26.1%; Average loss: 3.5914 Iteration: 1044; Percent complete: 26.1%; Average loss: 3.4431 Iteration: 1045; Percent complete: 26.1%; Average loss: 3.5515 Iteration: 1046; Percent complete: 26.2%; Average loss: 3.2954 Iteration: 1047; Percent complete: 26.2%; Average loss: 3.5509 Iteration: 1048; Percent complete: 26.2%; Average loss: 3.7634 Iteration: 1049; Percent complete: 26.2%; Average loss: 3.3134 Iteration: 1050; Percent complete: 26.2%; Average loss: 3.5684 Iteration: 1051; Percent complete: 26.3%; Average loss: 3.2606 Iteration: 1052; Percent complete: 26.3%; Average loss: 3.3438 Iteration: 1053; Percent complete: 26.3%; Average loss: 3.4629 Iteration: 1054; Percent complete: 26.4%; Average loss: 3.3210 Iteration: 1055; Percent complete: 26.4%; Average loss: 3.6567 Iteration: 1056; Percent complete: 26.4%; Average loss: 3.3527 Iteration: 1057; Percent complete: 26.4%; Average loss: 3.4250 Iteration: 1058; Percent complete: 26.5%; Average loss: 3.4923 Iteration: 1059; Percent complete: 26.5%; Average loss: 3.3620 Iteration: 1060; Percent complete: 26.5%; Average loss: 3.4448 Iteration: 1061; Percent complete: 26.5%; Average loss: 3.6230 Iteration: 1062; Percent complete: 26.6%; Average loss: 3.3798 Iteration: 1063; Percent complete: 26.6%; Average loss: 3.7109 Iteration: 1064; Percent complete: 26.6%; Average loss: 3.4052 Iteration: 1065; Percent complete: 26.6%; Average loss: 3.5061 Iteration: 1066; Percent complete: 26.7%; Average loss: 3.5263 Iteration: 1067; Percent complete: 26.7%; Average loss: 3.2264 Iteration: 1068; Percent complete: 26.7%; Average loss: 3.3214 Iteration: 1069; Percent complete: 26.7%; Average loss: 3.2114 Iteration: 1070; Percent complete: 26.8%; Average loss: 3.4190 Iteration: 1071; Percent complete: 26.8%; Average loss: 3.3312 Iteration: 1072; Percent complete: 26.8%; Average loss: 3.2649 Iteration: 1073; Percent complete: 26.8%; Average loss: 3.3737 Iteration: 1074; Percent complete: 26.9%; Average loss: 3.3305 Iteration: 1075; Percent complete: 26.9%; Average loss: 3.4773 Iteration: 1076; Percent complete: 26.9%; Average loss: 3.3947 Iteration: 1077; Percent complete: 26.9%; Average loss: 3.4275 Iteration: 1078; Percent complete: 27.0%; Average loss: 3.3687 Iteration: 1079; Percent complete: 27.0%; Average loss: 3.2761 Iteration: 1080; Percent complete: 27.0%; Average loss: 3.4990 Iteration: 1081; Percent complete: 27.0%; Average loss: 3.2868 Iteration: 1082; Percent complete: 27.1%; Average loss: 3.3947 Iteration: 1083; Percent complete: 27.1%; Average loss: 3.5048 Iteration: 1084; Percent complete: 27.1%; Average loss: 3.1729 Iteration: 1085; Percent complete: 27.1%; Average loss: 3.4101 Iteration: 1086; Percent complete: 27.2%; Average loss: 3.4037 Iteration: 1087; Percent complete: 27.2%; Average loss: 3.2637 Iteration: 1088; Percent complete: 27.2%; Average loss: 3.2435 Iteration: 1089; Percent complete: 27.2%; Average loss: 3.5543 Iteration: 1090; Percent complete: 27.3%; Average loss: 3.5018 Iteration: 1091; Percent complete: 27.3%; Average loss: 3.2695 Iteration: 1092; Percent complete: 27.3%; Average loss: 3.3470 Iteration: 1093; Percent complete: 27.3%; Average loss: 3.3502 Iteration: 1094; Percent complete: 27.4%; Average loss: 3.3129 Iteration: 1095; Percent complete: 27.4%; Average loss: 3.6373 Iteration: 1096; Percent complete: 27.4%; Average loss: 3.5312 Iteration: 1097; Percent complete: 27.4%; Average loss: 3.5110 Iteration: 1098; Percent complete: 27.5%; Average loss: 3.6372 Iteration: 1099; Percent complete: 27.5%; Average loss: 3.2521 Iteration: 1100; Percent complete: 27.5%; Average loss: 3.4913 Iteration: 1101; Percent complete: 27.5%; Average loss: 3.3364 Iteration: 1102; Percent complete: 27.6%; Average loss: 3.3348 Iteration: 1103; Percent complete: 27.6%; Average loss: 3.3653 Iteration: 1104; Percent complete: 27.6%; Average loss: 3.4475 Iteration: 1105; Percent complete: 27.6%; Average loss: 3.3798 Iteration: 1106; Percent complete: 27.7%; Average loss: 3.6265 Iteration: 1107; Percent complete: 27.7%; Average loss: 3.2817 Iteration: 1108; Percent complete: 27.7%; Average loss: 3.3001 Iteration: 1109; Percent complete: 27.7%; Average loss: 3.4603 Iteration: 1110; Percent complete: 27.8%; Average loss: 3.3554 Iteration: 1111; Percent complete: 27.8%; Average loss: 3.4489 Iteration: 1112; Percent complete: 27.8%; Average loss: 3.4950 Iteration: 1113; Percent complete: 27.8%; Average loss: 3.3836 Iteration: 1114; Percent complete: 27.9%; Average loss: 3.3554 Iteration: 1115; Percent complete: 27.9%; Average loss: 3.5752 Iteration: 1116; Percent complete: 27.9%; Average loss: 3.4512 Iteration: 1117; Percent complete: 27.9%; Average loss: 3.5871 Iteration: 1118; Percent complete: 28.0%; Average loss: 3.5400 Iteration: 1119; Percent complete: 28.0%; Average loss: 3.7064 Iteration: 1120; Percent complete: 28.0%; Average loss: 3.5427 Iteration: 1121; Percent complete: 28.0%; Average loss: 3.6916 Iteration: 1122; Percent complete: 28.1%; Average loss: 3.1973 Iteration: 1123; Percent complete: 28.1%; Average loss: 3.5991 Iteration: 1124; Percent complete: 28.1%; Average loss: 3.4284 Iteration: 1125; Percent complete: 28.1%; Average loss: 3.6911 Iteration: 1126; Percent complete: 28.1%; Average loss: 3.4041 Iteration: 1127; Percent complete: 28.2%; Average loss: 3.5628 Iteration: 1128; Percent complete: 28.2%; Average loss: 3.2447 Iteration: 1129; Percent complete: 28.2%; Average loss: 3.1401 Iteration: 1130; Percent complete: 28.2%; Average loss: 3.4196 Iteration: 1131; Percent complete: 28.3%; Average loss: 3.4738 Iteration: 1132; Percent complete: 28.3%; Average loss: 3.7065 Iteration: 1133; Percent complete: 28.3%; Average loss: 3.3450 Iteration: 1134; Percent complete: 28.3%; Average loss: 3.2179 Iteration: 1135; Percent complete: 28.4%; Average loss: 3.2650 Iteration: 1136; Percent complete: 28.4%; Average loss: 3.2385 Iteration: 1137; Percent complete: 28.4%; Average loss: 3.3323 Iteration: 1138; Percent complete: 28.4%; Average loss: 3.6113 Iteration: 1139; Percent complete: 28.5%; Average loss: 3.3966 Iteration: 1140; Percent complete: 28.5%; Average loss: 3.5650 Iteration: 1141; Percent complete: 28.5%; Average loss: 3.2610 Iteration: 1142; Percent complete: 28.5%; Average loss: 3.3568 Iteration: 1143; Percent complete: 28.6%; Average loss: 3.3413 Iteration: 1144; Percent complete: 28.6%; Average loss: 3.3043 Iteration: 1145; Percent complete: 28.6%; Average loss: 3.4846 Iteration: 1146; Percent complete: 28.6%; Average loss: 3.4469 Iteration: 1147; Percent complete: 28.7%; Average loss: 3.4536 Iteration: 1148; Percent complete: 28.7%; Average loss: 3.4909 Iteration: 1149; Percent complete: 28.7%; Average loss: 3.4958 Iteration: 1150; Percent complete: 28.7%; Average loss: 3.3711 Iteration: 1151; Percent complete: 28.8%; Average loss: 3.4634 Iteration: 1152; Percent complete: 28.8%; Average loss: 3.3261 Iteration: 1153; Percent complete: 28.8%; Average loss: 3.3324 Iteration: 1154; Percent complete: 28.8%; Average loss: 3.2560 Iteration: 1155; Percent complete: 28.9%; Average loss: 3.7982 Iteration: 1156; Percent complete: 28.9%; Average loss: 3.6138 Iteration: 1157; Percent complete: 28.9%; Average loss: 3.2879 Iteration: 1158; Percent complete: 28.9%; Average loss: 3.3117 Iteration: 1159; Percent complete: 29.0%; Average loss: 3.3557 Iteration: 1160; Percent complete: 29.0%; Average loss: 3.2420 Iteration: 1161; Percent complete: 29.0%; Average loss: 3.4565 Iteration: 1162; Percent complete: 29.0%; Average loss: 3.5760 Iteration: 1163; Percent complete: 29.1%; Average loss: 3.1347 Iteration: 1164; Percent complete: 29.1%; Average loss: 3.5229 Iteration: 1165; Percent complete: 29.1%; Average loss: 3.2211 Iteration: 1166; Percent complete: 29.1%; Average loss: 3.1457 Iteration: 1167; Percent complete: 29.2%; Average loss: 3.4732 Iteration: 1168; Percent complete: 29.2%; Average loss: 3.2120 Iteration: 1169; Percent complete: 29.2%; Average loss: 3.3620 Iteration: 1170; Percent complete: 29.2%; Average loss: 3.3952 Iteration: 1171; Percent complete: 29.3%; Average loss: 3.4275 Iteration: 1172; Percent complete: 29.3%; Average loss: 3.2737 Iteration: 1173; Percent complete: 29.3%; Average loss: 3.3697 Iteration: 1174; Percent complete: 29.3%; Average loss: 3.5523 Iteration: 1175; Percent complete: 29.4%; Average loss: 3.5064 Iteration: 1176; Percent complete: 29.4%; Average loss: 3.5193 Iteration: 1177; Percent complete: 29.4%; Average loss: 3.3721 Iteration: 1178; Percent complete: 29.4%; Average loss: 3.5386 Iteration: 1179; Percent complete: 29.5%; Average loss: 3.2706 Iteration: 1180; Percent complete: 29.5%; Average loss: 3.4461 Iteration: 1181; Percent complete: 29.5%; Average loss: 3.3196 Iteration: 1182; Percent complete: 29.5%; Average loss: 3.6356 Iteration: 1183; Percent complete: 29.6%; Average loss: 3.4740 Iteration: 1184; Percent complete: 29.6%; Average loss: 3.4576 Iteration: 1185; Percent complete: 29.6%; Average loss: 3.3766 Iteration: 1186; Percent complete: 29.6%; Average loss: 3.4774 Iteration: 1187; Percent complete: 29.7%; Average loss: 3.5381 Iteration: 1188; Percent complete: 29.7%; Average loss: 3.5715 Iteration: 1189; Percent complete: 29.7%; Average loss: 3.3465 Iteration: 1190; Percent complete: 29.8%; Average loss: 3.3293 Iteration: 1191; Percent complete: 29.8%; Average loss: 3.4845 Iteration: 1192; Percent complete: 29.8%; Average loss: 3.3276 Iteration: 1193; Percent complete: 29.8%; Average loss: 3.2444 Iteration: 1194; Percent complete: 29.8%; Average loss: 3.5055 Iteration: 1195; Percent complete: 29.9%; Average loss: 3.4485 Iteration: 1196; Percent complete: 29.9%; Average loss: 3.2521 Iteration: 1197; Percent complete: 29.9%; Average loss: 3.3677 Iteration: 1198; Percent complete: 29.9%; Average loss: 3.2800 Iteration: 1199; Percent complete: 30.0%; Average loss: 3.5647 Iteration: 1200; Percent complete: 30.0%; Average loss: 3.4025 Iteration: 1201; Percent complete: 30.0%; Average loss: 3.3022 Iteration: 1202; Percent complete: 30.0%; Average loss: 3.4424 Iteration: 1203; Percent complete: 30.1%; Average loss: 3.1870 Iteration: 1204; Percent complete: 30.1%; Average loss: 3.3799 Iteration: 1205; Percent complete: 30.1%; Average loss: 3.4375 Iteration: 1206; Percent complete: 30.1%; Average loss: 3.4670 Iteration: 1207; Percent complete: 30.2%; Average loss: 3.3683 Iteration: 1208; Percent complete: 30.2%; Average loss: 3.3011 Iteration: 1209; Percent complete: 30.2%; Average loss: 3.3266 Iteration: 1210; Percent complete: 30.2%; Average loss: 3.4367 Iteration: 1211; Percent complete: 30.3%; Average loss: 3.2613 Iteration: 1212; Percent complete: 30.3%; Average loss: 3.4044 Iteration: 1213; Percent complete: 30.3%; Average loss: 3.5511 Iteration: 1214; Percent complete: 30.3%; Average loss: 3.4162 Iteration: 1215; Percent complete: 30.4%; Average loss: 3.3554 Iteration: 1216; Percent complete: 30.4%; Average loss: 3.4276 Iteration: 1217; Percent complete: 30.4%; Average loss: 3.3299 Iteration: 1218; Percent complete: 30.4%; Average loss: 3.4952 Iteration: 1219; Percent complete: 30.5%; Average loss: 3.6491 Iteration: 1220; Percent complete: 30.5%; Average loss: 3.5216 Iteration: 1221; Percent complete: 30.5%; Average loss: 3.5551 Iteration: 1222; Percent complete: 30.6%; Average loss: 3.5374 Iteration: 1223; Percent complete: 30.6%; Average loss: 3.4199 Iteration: 1224; Percent complete: 30.6%; Average loss: 3.4176 Iteration: 1225; Percent complete: 30.6%; Average loss: 3.5352 Iteration: 1226; Percent complete: 30.6%; Average loss: 3.1036 Iteration: 1227; Percent complete: 30.7%; Average loss: 3.4255 Iteration: 1228; Percent complete: 30.7%; Average loss: 3.6622 Iteration: 1229; Percent complete: 30.7%; Average loss: 3.4640 Iteration: 1230; Percent complete: 30.8%; Average loss: 3.5379 Iteration: 1231; Percent complete: 30.8%; Average loss: 3.4400 Iteration: 1232; Percent complete: 30.8%; Average loss: 3.6238 Iteration: 1233; Percent complete: 30.8%; Average loss: 3.2298 Iteration: 1234; Percent complete: 30.9%; Average loss: 3.4146 Iteration: 1235; Percent complete: 30.9%; Average loss: 3.1394 Iteration: 1236; Percent complete: 30.9%; Average loss: 3.3005 Iteration: 1237; Percent complete: 30.9%; Average loss: 3.3208 Iteration: 1238; Percent complete: 30.9%; Average loss: 3.4141 Iteration: 1239; Percent complete: 31.0%; Average loss: 3.2506 Iteration: 1240; Percent complete: 31.0%; Average loss: 3.2783 Iteration: 1241; Percent complete: 31.0%; Average loss: 3.2986 Iteration: 1242; Percent complete: 31.1%; Average loss: 3.1474 Iteration: 1243; Percent complete: 31.1%; Average loss: 3.2518 Iteration: 1244; Percent complete: 31.1%; Average loss: 3.5062 Iteration: 1245; Percent complete: 31.1%; Average loss: 3.5079 Iteration: 1246; Percent complete: 31.1%; Average loss: 3.4375 Iteration: 1247; Percent complete: 31.2%; Average loss: 3.3457 Iteration: 1248; Percent complete: 31.2%; Average loss: 3.0779 Iteration: 1249; Percent complete: 31.2%; Average loss: 3.4054 Iteration: 1250; Percent complete: 31.2%; Average loss: 3.4689 Iteration: 1251; Percent complete: 31.3%; Average loss: 3.4579 Iteration: 1252; Percent complete: 31.3%; Average loss: 3.2517 Iteration: 1253; Percent complete: 31.3%; Average loss: 3.5716 Iteration: 1254; Percent complete: 31.4%; Average loss: 3.3345 Iteration: 1255; Percent complete: 31.4%; Average loss: 3.2550 Iteration: 1256; Percent complete: 31.4%; Average loss: 3.1825 Iteration: 1257; Percent complete: 31.4%; Average loss: 3.3646 Iteration: 1258; Percent complete: 31.4%; Average loss: 3.3923 Iteration: 1259; Percent complete: 31.5%; Average loss: 3.4186 Iteration: 1260; Percent complete: 31.5%; Average loss: 3.3822 Iteration: 1261; Percent complete: 31.5%; Average loss: 3.3103 Iteration: 1262; Percent complete: 31.6%; Average loss: 3.3522 Iteration: 1263; Percent complete: 31.6%; Average loss: 3.6204 Iteration: 1264; Percent complete: 31.6%; Average loss: 3.5546 Iteration: 1265; Percent complete: 31.6%; Average loss: 3.4284 Iteration: 1266; Percent complete: 31.6%; Average loss: 3.3355 Iteration: 1267; Percent complete: 31.7%; Average loss: 3.5998 Iteration: 1268; Percent complete: 31.7%; Average loss: 3.4123 Iteration: 1269; Percent complete: 31.7%; Average loss: 3.0445 Iteration: 1270; Percent complete: 31.8%; Average loss: 3.4419 Iteration: 1271; Percent complete: 31.8%; Average loss: 3.2919 Iteration: 1272; Percent complete: 31.8%; Average loss: 3.2838 Iteration: 1273; Percent complete: 31.8%; Average loss: 3.2764 Iteration: 1274; Percent complete: 31.9%; Average loss: 3.3561 Iteration: 1275; Percent complete: 31.9%; Average loss: 3.2957 Iteration: 1276; Percent complete: 31.9%; Average loss: 3.6267 Iteration: 1277; Percent complete: 31.9%; Average loss: 3.4304 Iteration: 1278; Percent complete: 31.9%; Average loss: 3.1026 Iteration: 1279; Percent complete: 32.0%; Average loss: 3.2520 Iteration: 1280; Percent complete: 32.0%; Average loss: 3.3364 Iteration: 1281; Percent complete: 32.0%; Average loss: 3.5839 Iteration: 1282; Percent complete: 32.0%; Average loss: 3.2975 Iteration: 1283; Percent complete: 32.1%; Average loss: 3.4749 Iteration: 1284; Percent complete: 32.1%; Average loss: 3.2254 Iteration: 1285; Percent complete: 32.1%; Average loss: 3.4485 Iteration: 1286; Percent complete: 32.1%; Average loss: 3.1847 Iteration: 1287; Percent complete: 32.2%; Average loss: 3.2621 Iteration: 1288; Percent complete: 32.2%; Average loss: 3.3854 Iteration: 1289; Percent complete: 32.2%; Average loss: 3.5837 Iteration: 1290; Percent complete: 32.2%; Average loss: 3.5156 Iteration: 1291; Percent complete: 32.3%; Average loss: 3.1838 Iteration: 1292; Percent complete: 32.3%; Average loss: 3.2913 Iteration: 1293; Percent complete: 32.3%; Average loss: 3.6002 Iteration: 1294; Percent complete: 32.4%; Average loss: 3.4072 Iteration: 1295; Percent complete: 32.4%; Average loss: 3.4546 Iteration: 1296; Percent complete: 32.4%; Average loss: 3.2129 Iteration: 1297; Percent complete: 32.4%; Average loss: 3.2767 Iteration: 1298; Percent complete: 32.5%; Average loss: 3.1505 Iteration: 1299; Percent complete: 32.5%; Average loss: 3.5019 Iteration: 1300; Percent complete: 32.5%; Average loss: 3.5274 Iteration: 1301; Percent complete: 32.5%; Average loss: 3.1926 Iteration: 1302; Percent complete: 32.6%; Average loss: 3.5543 Iteration: 1303; Percent complete: 32.6%; Average loss: 3.3128 Iteration: 1304; Percent complete: 32.6%; Average loss: 3.2091 Iteration: 1305; Percent complete: 32.6%; Average loss: 3.2406 Iteration: 1306; Percent complete: 32.6%; Average loss: 3.3959 Iteration: 1307; Percent complete: 32.7%; Average loss: 3.3779 Iteration: 1308; Percent complete: 32.7%; Average loss: 3.5011 Iteration: 1309; Percent complete: 32.7%; Average loss: 3.3349 Iteration: 1310; Percent complete: 32.8%; Average loss: 3.3823 Iteration: 1311; Percent complete: 32.8%; Average loss: 3.3805 Iteration: 1312; Percent complete: 32.8%; Average loss: 3.4599 Iteration: 1313; Percent complete: 32.8%; Average loss: 3.4224 Iteration: 1314; Percent complete: 32.9%; Average loss: 3.3458 Iteration: 1315; Percent complete: 32.9%; Average loss: 3.3223 Iteration: 1316; Percent complete: 32.9%; Average loss: 3.3913 Iteration: 1317; Percent complete: 32.9%; Average loss: 3.3072 Iteration: 1318; Percent complete: 33.0%; Average loss: 3.5176 Iteration: 1319; Percent complete: 33.0%; Average loss: 3.2167 Iteration: 1320; Percent complete: 33.0%; Average loss: 3.1628 Iteration: 1321; Percent complete: 33.0%; Average loss: 3.5155 Iteration: 1322; Percent complete: 33.1%; Average loss: 3.2235 Iteration: 1323; Percent complete: 33.1%; Average loss: 3.4907 Iteration: 1324; Percent complete: 33.1%; Average loss: 3.2155 Iteration: 1325; Percent complete: 33.1%; Average loss: 3.3531 Iteration: 1326; Percent complete: 33.1%; Average loss: 3.1962 Iteration: 1327; Percent complete: 33.2%; Average loss: 3.5032 Iteration: 1328; Percent complete: 33.2%; Average loss: 3.3445 Iteration: 1329; Percent complete: 33.2%; Average loss: 3.1819 Iteration: 1330; Percent complete: 33.2%; Average loss: 3.5182 Iteration: 1331; Percent complete: 33.3%; Average loss: 3.1457 Iteration: 1332; Percent complete: 33.3%; Average loss: 3.4491 Iteration: 1333; Percent complete: 33.3%; Average loss: 3.2044 Iteration: 1334; Percent complete: 33.4%; Average loss: 3.2068 Iteration: 1335; Percent complete: 33.4%; Average loss: 3.1670 Iteration: 1336; Percent complete: 33.4%; Average loss: 3.5315 Iteration: 1337; Percent complete: 33.4%; Average loss: 3.5064 Iteration: 1338; Percent complete: 33.5%; Average loss: 3.1431 Iteration: 1339; Percent complete: 33.5%; Average loss: 3.4497 Iteration: 1340; Percent complete: 33.5%; Average loss: 3.5665 Iteration: 1341; Percent complete: 33.5%; Average loss: 3.1809 Iteration: 1342; Percent complete: 33.6%; Average loss: 3.2101 Iteration: 1343; Percent complete: 33.6%; Average loss: 3.4630 Iteration: 1344; Percent complete: 33.6%; Average loss: 3.3102 Iteration: 1345; Percent complete: 33.6%; Average loss: 3.3596 Iteration: 1346; Percent complete: 33.7%; Average loss: 3.2921 Iteration: 1347; Percent complete: 33.7%; Average loss: 3.5573 Iteration: 1348; Percent complete: 33.7%; Average loss: 3.1611 Iteration: 1349; Percent complete: 33.7%; Average loss: 3.2893 Iteration: 1350; Percent complete: 33.8%; Average loss: 3.3609 Iteration: 1351; Percent complete: 33.8%; Average loss: 3.3578 Iteration: 1352; Percent complete: 33.8%; Average loss: 3.4436 Iteration: 1353; Percent complete: 33.8%; Average loss: 3.2843 Iteration: 1354; Percent complete: 33.9%; Average loss: 3.5502 Iteration: 1355; Percent complete: 33.9%; Average loss: 3.2917 Iteration: 1356; Percent complete: 33.9%; Average loss: 3.4310 Iteration: 1357; Percent complete: 33.9%; Average loss: 3.3869 Iteration: 1358; Percent complete: 34.0%; Average loss: 3.2598 Iteration: 1359; Percent complete: 34.0%; Average loss: 3.5456 Iteration: 1360; Percent complete: 34.0%; Average loss: 3.5503 Iteration: 1361; Percent complete: 34.0%; Average loss: 3.6583 Iteration: 1362; Percent complete: 34.1%; Average loss: 3.5265 Iteration: 1363; Percent complete: 34.1%; Average loss: 3.2209 Iteration: 1364; Percent complete: 34.1%; Average loss: 3.2740 Iteration: 1365; Percent complete: 34.1%; Average loss: 3.2581 Iteration: 1366; Percent complete: 34.2%; Average loss: 3.2406 Iteration: 1367; Percent complete: 34.2%; Average loss: 3.3757 Iteration: 1368; Percent complete: 34.2%; Average loss: 3.2966 Iteration: 1369; Percent complete: 34.2%; Average loss: 3.4324 Iteration: 1370; Percent complete: 34.2%; Average loss: 3.2637 Iteration: 1371; Percent complete: 34.3%; Average loss: 3.5320 Iteration: 1372; Percent complete: 34.3%; Average loss: 3.2456 Iteration: 1373; Percent complete: 34.3%; Average loss: 3.4451 Iteration: 1374; Percent complete: 34.4%; Average loss: 3.4623 Iteration: 1375; Percent complete: 34.4%; Average loss: 3.3462 Iteration: 1376; Percent complete: 34.4%; Average loss: 3.3746 Iteration: 1377; Percent complete: 34.4%; Average loss: 3.5230 Iteration: 1378; Percent complete: 34.4%; Average loss: 3.1501 Iteration: 1379; Percent complete: 34.5%; Average loss: 3.2750 Iteration: 1380; Percent complete: 34.5%; Average loss: 3.0087 Iteration: 1381; Percent complete: 34.5%; Average loss: 3.2717 Iteration: 1382; Percent complete: 34.5%; Average loss: 3.5653 Iteration: 1383; Percent complete: 34.6%; Average loss: 3.2093 Iteration: 1384; Percent complete: 34.6%; Average loss: 3.4081 Iteration: 1385; Percent complete: 34.6%; Average loss: 3.3027 Iteration: 1386; Percent complete: 34.6%; Average loss: 3.3704 Iteration: 1387; Percent complete: 34.7%; Average loss: 3.2488 Iteration: 1388; Percent complete: 34.7%; Average loss: 3.1777 Iteration: 1389; Percent complete: 34.7%; Average loss: 3.3354 Iteration: 1390; Percent complete: 34.8%; Average loss: 3.2649 Iteration: 1391; Percent complete: 34.8%; Average loss: 3.2487 Iteration: 1392; Percent complete: 34.8%; Average loss: 3.4196 Iteration: 1393; Percent complete: 34.8%; Average loss: 3.1587 Iteration: 1394; Percent complete: 34.8%; Average loss: 3.3583 Iteration: 1395; Percent complete: 34.9%; Average loss: 3.3293 Iteration: 1396; Percent complete: 34.9%; Average loss: 3.5176 Iteration: 1397; Percent complete: 34.9%; Average loss: 3.1734 Iteration: 1398; Percent complete: 34.9%; Average loss: 3.4213 Iteration: 1399; Percent complete: 35.0%; Average loss: 3.3473 Iteration: 1400; Percent complete: 35.0%; Average loss: 3.4739 Iteration: 1401; Percent complete: 35.0%; Average loss: 3.4255 Iteration: 1402; Percent complete: 35.0%; Average loss: 3.3054 Iteration: 1403; Percent complete: 35.1%; Average loss: 3.3715 Iteration: 1404; Percent complete: 35.1%; Average loss: 3.2991 Iteration: 1405; Percent complete: 35.1%; Average loss: 3.3329 Iteration: 1406; Percent complete: 35.1%; Average loss: 3.5185 Iteration: 1407; Percent complete: 35.2%; Average loss: 3.0385 Iteration: 1408; Percent complete: 35.2%; Average loss: 3.2536 Iteration: 1409; Percent complete: 35.2%; Average loss: 3.3810 Iteration: 1410; Percent complete: 35.2%; Average loss: 3.4168 Iteration: 1411; Percent complete: 35.3%; Average loss: 3.3700 Iteration: 1412; Percent complete: 35.3%; Average loss: 3.5540 Iteration: 1413; Percent complete: 35.3%; Average loss: 3.2354 Iteration: 1414; Percent complete: 35.4%; Average loss: 3.2373 Iteration: 1415; Percent complete: 35.4%; Average loss: 3.2477 Iteration: 1416; Percent complete: 35.4%; Average loss: 3.2120 Iteration: 1417; Percent complete: 35.4%; Average loss: 3.3904 Iteration: 1418; Percent complete: 35.4%; Average loss: 3.3980 Iteration: 1419; Percent complete: 35.5%; Average loss: 3.3394 Iteration: 1420; Percent complete: 35.5%; Average loss: 3.7073 Iteration: 1421; Percent complete: 35.5%; Average loss: 3.3537 Iteration: 1422; Percent complete: 35.5%; Average loss: 3.6298 Iteration: 1423; Percent complete: 35.6%; Average loss: 3.1478 Iteration: 1424; Percent complete: 35.6%; Average loss: 3.0290 Iteration: 1425; Percent complete: 35.6%; Average loss: 3.0911 Iteration: 1426; Percent complete: 35.6%; Average loss: 3.3006 Iteration: 1427; Percent complete: 35.7%; Average loss: 3.3966 Iteration: 1428; Percent complete: 35.7%; Average loss: 3.2620 Iteration: 1429; Percent complete: 35.7%; Average loss: 3.3553 Iteration: 1430; Percent complete: 35.8%; Average loss: 3.5475 Iteration: 1431; Percent complete: 35.8%; Average loss: 3.3376 Iteration: 1432; Percent complete: 35.8%; Average loss: 3.2526 Iteration: 1433; Percent complete: 35.8%; Average loss: 2.9664 Iteration: 1434; Percent complete: 35.9%; Average loss: 3.3397 Iteration: 1435; Percent complete: 35.9%; Average loss: 3.0309 Iteration: 1436; Percent complete: 35.9%; Average loss: 3.4391 Iteration: 1437; Percent complete: 35.9%; Average loss: 3.2923 Iteration: 1438; Percent complete: 35.9%; Average loss: 3.2330 Iteration: 1439; Percent complete: 36.0%; Average loss: 3.1384 Iteration: 1440; Percent complete: 36.0%; Average loss: 3.5330 Iteration: 1441; Percent complete: 36.0%; Average loss: 3.3591 Iteration: 1442; Percent complete: 36.0%; Average loss: 3.2571 Iteration: 1443; Percent complete: 36.1%; Average loss: 3.3372 Iteration: 1444; Percent complete: 36.1%; Average loss: 3.2706 Iteration: 1445; Percent complete: 36.1%; Average loss: 3.2446 Iteration: 1446; Percent complete: 36.1%; Average loss: 3.3739 Iteration: 1447; Percent complete: 36.2%; Average loss: 3.3612 Iteration: 1448; Percent complete: 36.2%; Average loss: 3.4190 Iteration: 1449; Percent complete: 36.2%; Average loss: 3.4435 Iteration: 1450; Percent complete: 36.2%; Average loss: 3.2652 Iteration: 1451; Percent complete: 36.3%; Average loss: 3.0131 Iteration: 1452; Percent complete: 36.3%; Average loss: 3.2680 Iteration: 1453; Percent complete: 36.3%; Average loss: 3.4722 Iteration: 1454; Percent complete: 36.4%; Average loss: 3.4427 Iteration: 1455; Percent complete: 36.4%; Average loss: 3.3853 Iteration: 1456; Percent complete: 36.4%; Average loss: 3.3408 Iteration: 1457; Percent complete: 36.4%; Average loss: 3.3051 Iteration: 1458; Percent complete: 36.4%; Average loss: 3.5230 Iteration: 1459; Percent complete: 36.5%; Average loss: 3.3252 Iteration: 1460; Percent complete: 36.5%; Average loss: 3.2645 Iteration: 1461; Percent complete: 36.5%; Average loss: 3.4739 Iteration: 1462; Percent complete: 36.5%; Average loss: 3.2905 Iteration: 1463; Percent complete: 36.6%; Average loss: 3.2476 Iteration: 1464; Percent complete: 36.6%; Average loss: 3.4456 Iteration: 1465; Percent complete: 36.6%; Average loss: 3.6101 Iteration: 1466; Percent complete: 36.6%; Average loss: 3.3848 Iteration: 1467; Percent complete: 36.7%; Average loss: 3.2775 Iteration: 1468; Percent complete: 36.7%; Average loss: 3.6134 Iteration: 1469; Percent complete: 36.7%; Average loss: 3.1998 Iteration: 1470; Percent complete: 36.8%; Average loss: 3.0050 Iteration: 1471; Percent complete: 36.8%; Average loss: 3.2560 Iteration: 1472; Percent complete: 36.8%; Average loss: 3.2060 Iteration: 1473; Percent complete: 36.8%; Average loss: 3.2328 Iteration: 1474; Percent complete: 36.9%; Average loss: 3.5163 Iteration: 1475; Percent complete: 36.9%; Average loss: 3.1436 Iteration: 1476; Percent complete: 36.9%; Average loss: 3.1547 Iteration: 1477; Percent complete: 36.9%; Average loss: 3.2153 Iteration: 1478; Percent complete: 37.0%; Average loss: 3.3703 Iteration: 1479; Percent complete: 37.0%; Average loss: 3.3158 Iteration: 1480; Percent complete: 37.0%; Average loss: 3.4528 Iteration: 1481; Percent complete: 37.0%; Average loss: 3.2204 Iteration: 1482; Percent complete: 37.0%; Average loss: 3.2598 Iteration: 1483; Percent complete: 37.1%; Average loss: 3.3692 Iteration: 1484; Percent complete: 37.1%; Average loss: 3.4041 Iteration: 1485; Percent complete: 37.1%; Average loss: 3.1944 Iteration: 1486; Percent complete: 37.1%; Average loss: 3.3173 Iteration: 1487; Percent complete: 37.2%; Average loss: 3.3155 Iteration: 1488; Percent complete: 37.2%; Average loss: 3.0936 Iteration: 1489; Percent complete: 37.2%; Average loss: 3.2821 Iteration: 1490; Percent complete: 37.2%; Average loss: 3.1537 Iteration: 1491; Percent complete: 37.3%; Average loss: 3.3232 Iteration: 1492; Percent complete: 37.3%; Average loss: 3.4606 Iteration: 1493; Percent complete: 37.3%; Average loss: 3.3567 Iteration: 1494; Percent complete: 37.4%; Average loss: 3.1843 Iteration: 1495; Percent complete: 37.4%; Average loss: 3.3527 Iteration: 1496; Percent complete: 37.4%; Average loss: 3.5133 Iteration: 1497; Percent complete: 37.4%; Average loss: 3.3920 Iteration: 1498; Percent complete: 37.5%; Average loss: 3.3238 Iteration: 1499; Percent complete: 37.5%; Average loss: 3.0865 Iteration: 1500; Percent complete: 37.5%; Average loss: 3.3105 Iteration: 1501; Percent complete: 37.5%; Average loss: 3.0631 Iteration: 1502; Percent complete: 37.5%; Average loss: 3.1845 Iteration: 1503; Percent complete: 37.6%; Average loss: 3.5027 Iteration: 1504; Percent complete: 37.6%; Average loss: 3.0667 Iteration: 1505; Percent complete: 37.6%; Average loss: 3.1771 Iteration: 1506; Percent complete: 37.6%; Average loss: 3.3534 Iteration: 1507; Percent complete: 37.7%; Average loss: 3.3328 Iteration: 1508; Percent complete: 37.7%; Average loss: 3.2488 Iteration: 1509; Percent complete: 37.7%; Average loss: 3.2745 Iteration: 1510; Percent complete: 37.8%; Average loss: 3.3587 Iteration: 1511; Percent complete: 37.8%; Average loss: 3.2825 Iteration: 1512; Percent complete: 37.8%; Average loss: 3.3011 Iteration: 1513; Percent complete: 37.8%; Average loss: 3.1831 Iteration: 1514; Percent complete: 37.9%; Average loss: 3.2179 Iteration: 1515; Percent complete: 37.9%; Average loss: 3.3102 Iteration: 1516; Percent complete: 37.9%; Average loss: 3.1896 Iteration: 1517; Percent complete: 37.9%; Average loss: 3.3132 Iteration: 1518; Percent complete: 38.0%; Average loss: 3.4629 Iteration: 1519; Percent complete: 38.0%; Average loss: 3.3050 Iteration: 1520; Percent complete: 38.0%; Average loss: 3.2683 Iteration: 1521; Percent complete: 38.0%; Average loss: 3.3089 Iteration: 1522; Percent complete: 38.0%; Average loss: 3.2898 Iteration: 1523; Percent complete: 38.1%; Average loss: 3.3054 Iteration: 1524; Percent complete: 38.1%; Average loss: 3.5515 Iteration: 1525; Percent complete: 38.1%; Average loss: 3.3273 Iteration: 1526; Percent complete: 38.1%; Average loss: 3.3951 Iteration: 1527; Percent complete: 38.2%; Average loss: 3.3680 Iteration: 1528; Percent complete: 38.2%; Average loss: 3.5396 Iteration: 1529; Percent complete: 38.2%; Average loss: 3.2970 Iteration: 1530; Percent complete: 38.2%; Average loss: 3.3205 Iteration: 1531; Percent complete: 38.3%; Average loss: 3.3641 Iteration: 1532; Percent complete: 38.3%; Average loss: 3.3597 Iteration: 1533; Percent complete: 38.3%; Average loss: 3.3507 Iteration: 1534; Percent complete: 38.4%; Average loss: 3.1989 Iteration: 1535; Percent complete: 38.4%; Average loss: 3.0055 Iteration: 1536; Percent complete: 38.4%; Average loss: 3.4222 Iteration: 1537; Percent complete: 38.4%; Average loss: 3.4173 Iteration: 1538; Percent complete: 38.5%; Average loss: 3.1627 Iteration: 1539; Percent complete: 38.5%; Average loss: 3.4179 Iteration: 1540; Percent complete: 38.5%; Average loss: 3.3573 Iteration: 1541; Percent complete: 38.5%; Average loss: 3.3509 Iteration: 1542; Percent complete: 38.6%; Average loss: 3.2410 Iteration: 1543; Percent complete: 38.6%; Average loss: 3.1262 Iteration: 1544; Percent complete: 38.6%; Average loss: 3.3719 Iteration: 1545; Percent complete: 38.6%; Average loss: 3.3058 Iteration: 1546; Percent complete: 38.6%; Average loss: 3.1397 Iteration: 1547; Percent complete: 38.7%; Average loss: 3.3000 Iteration: 1548; Percent complete: 38.7%; Average loss: 3.4228 Iteration: 1549; Percent complete: 38.7%; Average loss: 3.0139 Iteration: 1550; Percent complete: 38.8%; Average loss: 3.2163 Iteration: 1551; Percent complete: 38.8%; Average loss: 3.0389 Iteration: 1552; Percent complete: 38.8%; Average loss: 3.3767 Iteration: 1553; Percent complete: 38.8%; Average loss: 3.0668 Iteration: 1554; Percent complete: 38.9%; Average loss: 3.4387 Iteration: 1555; Percent complete: 38.9%; Average loss: 3.2410 Iteration: 1556; Percent complete: 38.9%; Average loss: 3.0967 Iteration: 1557; Percent complete: 38.9%; Average loss: 3.2336 Iteration: 1558; Percent complete: 39.0%; Average loss: 3.3705 Iteration: 1559; Percent complete: 39.0%; Average loss: 3.4761 Iteration: 1560; Percent complete: 39.0%; Average loss: 2.9517 Iteration: 1561; Percent complete: 39.0%; Average loss: 3.6442 Iteration: 1562; Percent complete: 39.1%; Average loss: 3.3509 Iteration: 1563; Percent complete: 39.1%; Average loss: 3.2605 Iteration: 1564; Percent complete: 39.1%; Average loss: 3.4990 Iteration: 1565; Percent complete: 39.1%; Average loss: 3.3310 Iteration: 1566; Percent complete: 39.1%; Average loss: 3.2944 Iteration: 1567; Percent complete: 39.2%; Average loss: 3.0552 Iteration: 1568; Percent complete: 39.2%; Average loss: 3.1716 Iteration: 1569; Percent complete: 39.2%; Average loss: 3.2499 Iteration: 1570; Percent complete: 39.2%; Average loss: 3.1406 Iteration: 1571; Percent complete: 39.3%; Average loss: 3.0204 Iteration: 1572; Percent complete: 39.3%; Average loss: 3.2494 Iteration: 1573; Percent complete: 39.3%; Average loss: 3.4423 Iteration: 1574; Percent complete: 39.4%; Average loss: 3.1752 Iteration: 1575; Percent complete: 39.4%; Average loss: 3.5528 Iteration: 1576; Percent complete: 39.4%; Average loss: 3.2452 Iteration: 1577; Percent complete: 39.4%; Average loss: 3.2668 Iteration: 1578; Percent complete: 39.5%; Average loss: 3.1068 Iteration: 1579; Percent complete: 39.5%; Average loss: 3.3184 Iteration: 1580; Percent complete: 39.5%; Average loss: 3.0748 Iteration: 1581; Percent complete: 39.5%; Average loss: 3.1879 Iteration: 1582; Percent complete: 39.6%; Average loss: 3.2851 Iteration: 1583; Percent complete: 39.6%; Average loss: 3.4248 Iteration: 1584; Percent complete: 39.6%; Average loss: 2.9970 Iteration: 1585; Percent complete: 39.6%; Average loss: 3.4324 Iteration: 1586; Percent complete: 39.6%; Average loss: 3.1261 Iteration: 1587; Percent complete: 39.7%; Average loss: 3.2883 Iteration: 1588; Percent complete: 39.7%; Average loss: 3.3539 Iteration: 1589; Percent complete: 39.7%; Average loss: 3.4146 Iteration: 1590; Percent complete: 39.8%; Average loss: 3.1644 Iteration: 1591; Percent complete: 39.8%; Average loss: 3.2466 Iteration: 1592; Percent complete: 39.8%; Average loss: 3.3265 Iteration: 1593; Percent complete: 39.8%; Average loss: 3.3376 Iteration: 1594; Percent complete: 39.9%; Average loss: 3.2076 Iteration: 1595; Percent complete: 39.9%; Average loss: 3.5753 Iteration: 1596; Percent complete: 39.9%; Average loss: 3.2547 Iteration: 1597; Percent complete: 39.9%; Average loss: 3.4595 Iteration: 1598; Percent complete: 40.0%; Average loss: 3.3422 Iteration: 1599; Percent complete: 40.0%; Average loss: 2.9297 Iteration: 1600; Percent complete: 40.0%; Average loss: 3.0884 Iteration: 1601; Percent complete: 40.0%; Average loss: 3.1667 Iteration: 1602; Percent complete: 40.1%; Average loss: 3.3583 Iteration: 1603; Percent complete: 40.1%; Average loss: 3.1853 Iteration: 1604; Percent complete: 40.1%; Average loss: 3.2462 Iteration: 1605; Percent complete: 40.1%; Average loss: 3.3503 Iteration: 1606; Percent complete: 40.2%; Average loss: 3.2797 Iteration: 1607; Percent complete: 40.2%; Average loss: 3.2673 Iteration: 1608; Percent complete: 40.2%; Average loss: 3.1713 Iteration: 1609; Percent complete: 40.2%; Average loss: 3.5728 Iteration: 1610; Percent complete: 40.2%; Average loss: 3.1173 Iteration: 1611; Percent complete: 40.3%; Average loss: 3.2607 Iteration: 1612; Percent complete: 40.3%; Average loss: 3.0841 Iteration: 1613; Percent complete: 40.3%; Average loss: 3.0977 Iteration: 1614; Percent complete: 40.4%; Average loss: 2.9855 Iteration: 1615; Percent complete: 40.4%; Average loss: 3.0462 Iteration: 1616; Percent complete: 40.4%; Average loss: 3.4105 Iteration: 1617; Percent complete: 40.4%; Average loss: 3.1495 Iteration: 1618; Percent complete: 40.5%; Average loss: 3.3060 Iteration: 1619; Percent complete: 40.5%; Average loss: 3.4936 Iteration: 1620; Percent complete: 40.5%; Average loss: 3.1452 Iteration: 1621; Percent complete: 40.5%; Average loss: 3.4832 Iteration: 1622; Percent complete: 40.6%; Average loss: 3.3346 Iteration: 1623; Percent complete: 40.6%; Average loss: 3.3653 Iteration: 1624; Percent complete: 40.6%; Average loss: 3.3612 Iteration: 1625; Percent complete: 40.6%; Average loss: 3.4054 Iteration: 1626; Percent complete: 40.6%; Average loss: 2.9665 Iteration: 1627; Percent complete: 40.7%; Average loss: 3.2513 Iteration: 1628; Percent complete: 40.7%; Average loss: 3.2043 Iteration: 1629; Percent complete: 40.7%; Average loss: 3.3621 Iteration: 1630; Percent complete: 40.8%; Average loss: 3.3932 Iteration: 1631; Percent complete: 40.8%; Average loss: 3.2017 Iteration: 1632; Percent complete: 40.8%; Average loss: 3.2485 Iteration: 1633; Percent complete: 40.8%; Average loss: 3.5062 Iteration: 1634; Percent complete: 40.8%; Average loss: 3.0950 Iteration: 1635; Percent complete: 40.9%; Average loss: 3.2928 Iteration: 1636; Percent complete: 40.9%; Average loss: 3.5320 Iteration: 1637; Percent complete: 40.9%; Average loss: 3.3227 Iteration: 1638; Percent complete: 40.9%; Average loss: 3.3175 Iteration: 1639; Percent complete: 41.0%; Average loss: 3.2078 Iteration: 1640; Percent complete: 41.0%; Average loss: 3.1912 Iteration: 1641; Percent complete: 41.0%; Average loss: 3.3639 Iteration: 1642; Percent complete: 41.0%; Average loss: 3.1155 Iteration: 1643; Percent complete: 41.1%; Average loss: 3.3933 Iteration: 1644; Percent complete: 41.1%; Average loss: 3.3455 Iteration: 1645; Percent complete: 41.1%; Average loss: 3.3423 Iteration: 1646; Percent complete: 41.1%; Average loss: 3.2855 Iteration: 1647; Percent complete: 41.2%; Average loss: 3.5216 Iteration: 1648; Percent complete: 41.2%; Average loss: 3.3172 Iteration: 1649; Percent complete: 41.2%; Average loss: 3.1998 Iteration: 1650; Percent complete: 41.2%; Average loss: 3.3009 Iteration: 1651; Percent complete: 41.3%; Average loss: 3.1540 Iteration: 1652; Percent complete: 41.3%; Average loss: 3.2450 Iteration: 1653; Percent complete: 41.3%; Average loss: 3.4056 Iteration: 1654; Percent complete: 41.3%; Average loss: 3.5479 Iteration: 1655; Percent complete: 41.4%; Average loss: 2.9632 Iteration: 1656; Percent complete: 41.4%; Average loss: 3.2166 Iteration: 1657; Percent complete: 41.4%; Average loss: 3.3261 Iteration: 1658; Percent complete: 41.4%; Average loss: 3.5242 Iteration: 1659; Percent complete: 41.5%; Average loss: 3.5843 Iteration: 1660; Percent complete: 41.5%; Average loss: 3.2045 Iteration: 1661; Percent complete: 41.5%; Average loss: 3.2379 Iteration: 1662; Percent complete: 41.5%; Average loss: 3.2424 Iteration: 1663; Percent complete: 41.6%; Average loss: 3.5204 Iteration: 1664; Percent complete: 41.6%; Average loss: 3.2398 Iteration: 1665; Percent complete: 41.6%; Average loss: 3.1524 Iteration: 1666; Percent complete: 41.6%; Average loss: 3.1533 Iteration: 1667; Percent complete: 41.7%; Average loss: 3.2421 Iteration: 1668; Percent complete: 41.7%; Average loss: 3.5251 Iteration: 1669; Percent complete: 41.7%; Average loss: 3.2302 Iteration: 1670; Percent complete: 41.8%; Average loss: 3.1977 Iteration: 1671; Percent complete: 41.8%; Average loss: 3.0297 Iteration: 1672; Percent complete: 41.8%; Average loss: 2.9194 Iteration: 1673; Percent complete: 41.8%; Average loss: 3.5056 Iteration: 1674; Percent complete: 41.9%; Average loss: 3.1253 Iteration: 1675; Percent complete: 41.9%; Average loss: 2.9404 Iteration: 1676; Percent complete: 41.9%; Average loss: 3.4172 Iteration: 1677; Percent complete: 41.9%; Average loss: 3.1471 Iteration: 1678; Percent complete: 41.9%; Average loss: 3.5478 Iteration: 1679; Percent complete: 42.0%; Average loss: 3.2259 Iteration: 1680; Percent complete: 42.0%; Average loss: 3.1885 Iteration: 1681; Percent complete: 42.0%; Average loss: 3.3304 Iteration: 1682; Percent complete: 42.0%; Average loss: 3.1763 Iteration: 1683; Percent complete: 42.1%; Average loss: 3.0354 Iteration: 1684; Percent complete: 42.1%; Average loss: 3.4043 Iteration: 1685; Percent complete: 42.1%; Average loss: 3.1929 Iteration: 1686; Percent complete: 42.1%; Average loss: 3.2152 Iteration: 1687; Percent complete: 42.2%; Average loss: 3.2578 Iteration: 1688; Percent complete: 42.2%; Average loss: 3.1043 Iteration: 1689; Percent complete: 42.2%; Average loss: 3.2315 Iteration: 1690; Percent complete: 42.2%; Average loss: 3.3456 Iteration: 1691; Percent complete: 42.3%; Average loss: 3.1367 Iteration: 1692; Percent complete: 42.3%; Average loss: 3.2382 Iteration: 1693; Percent complete: 42.3%; Average loss: 3.4375 Iteration: 1694; Percent complete: 42.4%; Average loss: 3.2973 Iteration: 1695; Percent complete: 42.4%; Average loss: 3.2115 Iteration: 1696; Percent complete: 42.4%; Average loss: 3.2702 Iteration: 1697; Percent complete: 42.4%; Average loss: 3.4212 Iteration: 1698; Percent complete: 42.4%; Average loss: 3.2305 Iteration: 1699; Percent complete: 42.5%; Average loss: 3.2455 Iteration: 1700; Percent complete: 42.5%; Average loss: 3.1984 Iteration: 1701; Percent complete: 42.5%; Average loss: 3.0964 Iteration: 1702; Percent complete: 42.5%; Average loss: 3.2192 Iteration: 1703; Percent complete: 42.6%; Average loss: 3.0919 Iteration: 1704; Percent complete: 42.6%; Average loss: 3.4110 Iteration: 1705; Percent complete: 42.6%; Average loss: 3.0484 Iteration: 1706; Percent complete: 42.6%; Average loss: 3.3129 Iteration: 1707; Percent complete: 42.7%; Average loss: 3.0650 Iteration: 1708; Percent complete: 42.7%; Average loss: 3.1714 Iteration: 1709; Percent complete: 42.7%; Average loss: 3.2032 Iteration: 1710; Percent complete: 42.8%; Average loss: 3.3200 Iteration: 1711; Percent complete: 42.8%; Average loss: 3.4995 Iteration: 1712; Percent complete: 42.8%; Average loss: 3.4465 Iteration: 1713; Percent complete: 42.8%; Average loss: 3.0240 Iteration: 1714; Percent complete: 42.9%; Average loss: 3.3218 Iteration: 1715; Percent complete: 42.9%; Average loss: 3.2801 Iteration: 1716; Percent complete: 42.9%; Average loss: 2.9936 Iteration: 1717; Percent complete: 42.9%; Average loss: 3.2905 Iteration: 1718; Percent complete: 43.0%; Average loss: 3.4809 Iteration: 1719; Percent complete: 43.0%; Average loss: 3.3738 Iteration: 1720; Percent complete: 43.0%; Average loss: 3.3233 Iteration: 1721; Percent complete: 43.0%; Average loss: 3.5028 Iteration: 1722; Percent complete: 43.0%; Average loss: 3.3046 Iteration: 1723; Percent complete: 43.1%; Average loss: 3.1096 Iteration: 1724; Percent complete: 43.1%; Average loss: 3.4155 Iteration: 1725; Percent complete: 43.1%; Average loss: 3.1472 Iteration: 1726; Percent complete: 43.1%; Average loss: 3.3424 Iteration: 1727; Percent complete: 43.2%; Average loss: 3.3402 Iteration: 1728; Percent complete: 43.2%; Average loss: 3.2006 Iteration: 1729; Percent complete: 43.2%; Average loss: 3.3966 Iteration: 1730; Percent complete: 43.2%; Average loss: 3.2453 Iteration: 1731; Percent complete: 43.3%; Average loss: 3.1100 Iteration: 1732; Percent complete: 43.3%; Average loss: 3.2543 Iteration: 1733; Percent complete: 43.3%; Average loss: 3.2207 Iteration: 1734; Percent complete: 43.4%; Average loss: 3.3408 Iteration: 1735; Percent complete: 43.4%; Average loss: 2.9089 Iteration: 1736; Percent complete: 43.4%; Average loss: 3.2861 Iteration: 1737; Percent complete: 43.4%; Average loss: 3.2323 Iteration: 1738; Percent complete: 43.5%; Average loss: 2.9445 Iteration: 1739; Percent complete: 43.5%; Average loss: 3.3679 Iteration: 1740; Percent complete: 43.5%; Average loss: 3.3260 Iteration: 1741; Percent complete: 43.5%; Average loss: 3.1415 Iteration: 1742; Percent complete: 43.5%; Average loss: 3.2040 Iteration: 1743; Percent complete: 43.6%; Average loss: 3.0227 Iteration: 1744; Percent complete: 43.6%; Average loss: 3.3311 Iteration: 1745; Percent complete: 43.6%; Average loss: 3.5572 Iteration: 1746; Percent complete: 43.6%; Average loss: 3.0916 Iteration: 1747; Percent complete: 43.7%; Average loss: 3.2038 Iteration: 1748; Percent complete: 43.7%; Average loss: 3.2582 Iteration: 1749; Percent complete: 43.7%; Average loss: 3.2748 Iteration: 1750; Percent complete: 43.8%; Average loss: 3.3156 Iteration: 1751; Percent complete: 43.8%; Average loss: 3.1625 Iteration: 1752; Percent complete: 43.8%; Average loss: 3.2222 Iteration: 1753; Percent complete: 43.8%; Average loss: 3.2293 Iteration: 1754; Percent complete: 43.9%; Average loss: 3.0900 Iteration: 1755; Percent complete: 43.9%; Average loss: 3.1335 Iteration: 1756; Percent complete: 43.9%; Average loss: 3.2294 Iteration: 1757; Percent complete: 43.9%; Average loss: 3.2230 Iteration: 1758; Percent complete: 44.0%; Average loss: 3.1295 Iteration: 1759; Percent complete: 44.0%; Average loss: 3.2705 Iteration: 1760; Percent complete: 44.0%; Average loss: 3.2648 Iteration: 1761; Percent complete: 44.0%; Average loss: 3.1001 Iteration: 1762; Percent complete: 44.0%; Average loss: 3.1261 Iteration: 1763; Percent complete: 44.1%; Average loss: 3.3586 Iteration: 1764; Percent complete: 44.1%; Average loss: 3.0322 Iteration: 1765; Percent complete: 44.1%; Average loss: 3.2023 Iteration: 1766; Percent complete: 44.1%; Average loss: 3.1830 Iteration: 1767; Percent complete: 44.2%; Average loss: 3.1401 Iteration: 1768; Percent complete: 44.2%; Average loss: 3.3967 Iteration: 1769; Percent complete: 44.2%; Average loss: 3.4335 Iteration: 1770; Percent complete: 44.2%; Average loss: 2.9232 Iteration: 1771; Percent complete: 44.3%; Average loss: 3.1998 Iteration: 1772; Percent complete: 44.3%; Average loss: 3.3832 Iteration: 1773; Percent complete: 44.3%; Average loss: 2.9628 Iteration: 1774; Percent complete: 44.4%; Average loss: 3.0752 Iteration: 1775; Percent complete: 44.4%; Average loss: 3.0887 Iteration: 1776; Percent complete: 44.4%; Average loss: 3.2821 Iteration: 1777; Percent complete: 44.4%; Average loss: 3.1431 Iteration: 1778; Percent complete: 44.5%; Average loss: 3.3365 Iteration: 1779; Percent complete: 44.5%; Average loss: 3.2694 Iteration: 1780; Percent complete: 44.5%; Average loss: 3.2546 Iteration: 1781; Percent complete: 44.5%; Average loss: 3.1721 Iteration: 1782; Percent complete: 44.5%; Average loss: 3.0153 Iteration: 1783; Percent complete: 44.6%; Average loss: 3.0705 Iteration: 1784; Percent complete: 44.6%; Average loss: 3.2800 Iteration: 1785; Percent complete: 44.6%; Average loss: 3.2317 Iteration: 1786; Percent complete: 44.6%; Average loss: 3.0543 Iteration: 1787; Percent complete: 44.7%; Average loss: 3.2180 Iteration: 1788; Percent complete: 44.7%; Average loss: 3.4846 Iteration: 1789; Percent complete: 44.7%; Average loss: 3.0931 Iteration: 1790; Percent complete: 44.8%; Average loss: 3.2535 Iteration: 1791; Percent complete: 44.8%; Average loss: 3.4005 Iteration: 1792; Percent complete: 44.8%; Average loss: 3.2500 Iteration: 1793; Percent complete: 44.8%; Average loss: 3.2439 Iteration: 1794; Percent complete: 44.9%; Average loss: 3.2661 Iteration: 1795; Percent complete: 44.9%; Average loss: 3.0657 Iteration: 1796; Percent complete: 44.9%; Average loss: 3.2324 Iteration: 1797; Percent complete: 44.9%; Average loss: 3.1760 Iteration: 1798; Percent complete: 45.0%; Average loss: 3.0484 Iteration: 1799; Percent complete: 45.0%; Average loss: 2.8386 Iteration: 1800; Percent complete: 45.0%; Average loss: 3.3372 Iteration: 1801; Percent complete: 45.0%; Average loss: 3.2206 Iteration: 1802; Percent complete: 45.1%; Average loss: 3.2211 Iteration: 1803; Percent complete: 45.1%; Average loss: 3.1074 Iteration: 1804; Percent complete: 45.1%; Average loss: 3.3390 Iteration: 1805; Percent complete: 45.1%; Average loss: 3.3266 Iteration: 1806; Percent complete: 45.1%; Average loss: 3.1016 Iteration: 1807; Percent complete: 45.2%; Average loss: 3.6167 Iteration: 1808; Percent complete: 45.2%; Average loss: 2.9625 Iteration: 1809; Percent complete: 45.2%; Average loss: 3.2261 Iteration: 1810; Percent complete: 45.2%; Average loss: 3.1793 Iteration: 1811; Percent complete: 45.3%; Average loss: 3.0557 Iteration: 1812; Percent complete: 45.3%; Average loss: 2.9483 Iteration: 1813; Percent complete: 45.3%; Average loss: 3.0182 Iteration: 1814; Percent complete: 45.4%; Average loss: 3.2683 Iteration: 1815; Percent complete: 45.4%; Average loss: 3.4402 Iteration: 1816; Percent complete: 45.4%; Average loss: 3.0263 Iteration: 1817; Percent complete: 45.4%; Average loss: 3.1384 Iteration: 1818; Percent complete: 45.5%; Average loss: 3.1087 Iteration: 1819; Percent complete: 45.5%; Average loss: 3.0767 Iteration: 1820; Percent complete: 45.5%; Average loss: 3.3280 Iteration: 1821; Percent complete: 45.5%; Average loss: 3.1998 Iteration: 1822; Percent complete: 45.6%; Average loss: 3.1304 Iteration: 1823; Percent complete: 45.6%; Average loss: 2.9595 Iteration: 1824; Percent complete: 45.6%; Average loss: 3.4010 Iteration: 1825; Percent complete: 45.6%; Average loss: 3.1832 Iteration: 1826; Percent complete: 45.6%; Average loss: 3.0422 Iteration: 1827; Percent complete: 45.7%; Average loss: 3.2856 Iteration: 1828; Percent complete: 45.7%; Average loss: 3.2279 Iteration: 1829; Percent complete: 45.7%; Average loss: 2.9226 Iteration: 1830; Percent complete: 45.8%; Average loss: 3.2936 Iteration: 1831; Percent complete: 45.8%; Average loss: 3.1139 Iteration: 1832; Percent complete: 45.8%; Average loss: 3.3371 Iteration: 1833; Percent complete: 45.8%; Average loss: 2.9700 Iteration: 1834; Percent complete: 45.9%; Average loss: 3.2174 Iteration: 1835; Percent complete: 45.9%; Average loss: 3.2905 Iteration: 1836; Percent complete: 45.9%; Average loss: 3.1390 Iteration: 1837; Percent complete: 45.9%; Average loss: 3.1589 Iteration: 1838; Percent complete: 46.0%; Average loss: 3.3519 Iteration: 1839; Percent complete: 46.0%; Average loss: 3.2096 Iteration: 1840; Percent complete: 46.0%; Average loss: 3.4934 Iteration: 1841; Percent complete: 46.0%; Average loss: 3.3693 Iteration: 1842; Percent complete: 46.1%; Average loss: 3.4312 Iteration: 1843; Percent complete: 46.1%; Average loss: 3.3258 Iteration: 1844; Percent complete: 46.1%; Average loss: 3.3311 Iteration: 1845; Percent complete: 46.1%; Average loss: 3.1433 Iteration: 1846; Percent complete: 46.2%; Average loss: 2.9580 Iteration: 1847; Percent complete: 46.2%; Average loss: 3.2697 Iteration: 1848; Percent complete: 46.2%; Average loss: 3.0016 Iteration: 1849; Percent complete: 46.2%; Average loss: 3.0875 Iteration: 1850; Percent complete: 46.2%; Average loss: 3.2538 Iteration: 1851; Percent complete: 46.3%; Average loss: 3.3177 Iteration: 1852; Percent complete: 46.3%; Average loss: 3.1679 Iteration: 1853; Percent complete: 46.3%; Average loss: 3.0986 Iteration: 1854; Percent complete: 46.4%; Average loss: 3.1053 Iteration: 1855; Percent complete: 46.4%; Average loss: 3.4248 Iteration: 1856; Percent complete: 46.4%; Average loss: 3.1982 Iteration: 1857; Percent complete: 46.4%; Average loss: 3.2125 Iteration: 1858; Percent complete: 46.5%; Average loss: 3.2110 Iteration: 1859; Percent complete: 46.5%; Average loss: 3.2993 Iteration: 1860; Percent complete: 46.5%; Average loss: 3.2370 Iteration: 1861; Percent complete: 46.5%; Average loss: 3.0034 Iteration: 1862; Percent complete: 46.6%; Average loss: 3.1501 Iteration: 1863; Percent complete: 46.6%; Average loss: 3.1100 Iteration: 1864; Percent complete: 46.6%; Average loss: 3.3210 Iteration: 1865; Percent complete: 46.6%; Average loss: 3.0766 Iteration: 1866; Percent complete: 46.7%; Average loss: 3.2235 Iteration: 1867; Percent complete: 46.7%; Average loss: 3.0587 Iteration: 1868; Percent complete: 46.7%; Average loss: 3.1618 Iteration: 1869; Percent complete: 46.7%; Average loss: 3.3469 Iteration: 1870; Percent complete: 46.8%; Average loss: 3.1676 Iteration: 1871; Percent complete: 46.8%; Average loss: 3.1110 Iteration: 1872; Percent complete: 46.8%; Average loss: 3.4601 Iteration: 1873; Percent complete: 46.8%; Average loss: 3.2294 Iteration: 1874; Percent complete: 46.9%; Average loss: 3.2103 Iteration: 1875; Percent complete: 46.9%; Average loss: 3.0912 Iteration: 1876; Percent complete: 46.9%; Average loss: 3.0485 Iteration: 1877; Percent complete: 46.9%; Average loss: 3.1727 Iteration: 1878; Percent complete: 46.9%; Average loss: 3.3715 Iteration: 1879; Percent complete: 47.0%; Average loss: 3.1510 Iteration: 1880; Percent complete: 47.0%; Average loss: 3.1361 Iteration: 1881; Percent complete: 47.0%; Average loss: 3.1514 Iteration: 1882; Percent complete: 47.0%; Average loss: 3.3698 Iteration: 1883; Percent complete: 47.1%; Average loss: 2.9892 Iteration: 1884; Percent complete: 47.1%; Average loss: 3.0473 Iteration: 1885; Percent complete: 47.1%; Average loss: 3.1865 Iteration: 1886; Percent complete: 47.1%; Average loss: 3.1233 Iteration: 1887; Percent complete: 47.2%; Average loss: 2.9021 Iteration: 1888; Percent complete: 47.2%; Average loss: 3.2303 Iteration: 1889; Percent complete: 47.2%; Average loss: 3.3805 Iteration: 1890; Percent complete: 47.2%; Average loss: 3.4560 Iteration: 1891; Percent complete: 47.3%; Average loss: 3.2141 Iteration: 1892; Percent complete: 47.3%; Average loss: 3.0710 Iteration: 1893; Percent complete: 47.3%; Average loss: 3.3438 Iteration: 1894; Percent complete: 47.3%; Average loss: 3.3393 Iteration: 1895; Percent complete: 47.4%; Average loss: 3.1752 Iteration: 1896; Percent complete: 47.4%; Average loss: 3.2241 Iteration: 1897; Percent complete: 47.4%; Average loss: 3.3147 Iteration: 1898; Percent complete: 47.4%; Average loss: 3.2009 Iteration: 1899; Percent complete: 47.5%; Average loss: 3.2969 Iteration: 1900; Percent complete: 47.5%; Average loss: 3.1904 Iteration: 1901; Percent complete: 47.5%; Average loss: 3.3238 Iteration: 1902; Percent complete: 47.5%; Average loss: 3.0111 Iteration: 1903; Percent complete: 47.6%; Average loss: 3.2076 Iteration: 1904; Percent complete: 47.6%; Average loss: 3.0563 Iteration: 1905; Percent complete: 47.6%; Average loss: 3.0702 Iteration: 1906; Percent complete: 47.6%; Average loss: 3.1373 Iteration: 1907; Percent complete: 47.7%; Average loss: 3.3443 Iteration: 1908; Percent complete: 47.7%; Average loss: 3.3115 Iteration: 1909; Percent complete: 47.7%; Average loss: 3.0262 Iteration: 1910; Percent complete: 47.8%; Average loss: 3.0268 Iteration: 1911; Percent complete: 47.8%; Average loss: 3.3628 Iteration: 1912; Percent complete: 47.8%; Average loss: 3.1087 Iteration: 1913; Percent complete: 47.8%; Average loss: 3.2108 Iteration: 1914; Percent complete: 47.9%; Average loss: 3.2005 Iteration: 1915; Percent complete: 47.9%; Average loss: 3.0133 Iteration: 1916; Percent complete: 47.9%; Average loss: 3.0813 Iteration: 1917; Percent complete: 47.9%; Average loss: 2.9121 Iteration: 1918; Percent complete: 47.9%; Average loss: 3.2187 Iteration: 1919; Percent complete: 48.0%; Average loss: 3.1581 Iteration: 1920; Percent complete: 48.0%; Average loss: 3.1181 Iteration: 1921; Percent complete: 48.0%; Average loss: 3.0659 Iteration: 1922; Percent complete: 48.0%; Average loss: 3.2061 Iteration: 1923; Percent complete: 48.1%; Average loss: 3.2597 Iteration: 1924; Percent complete: 48.1%; Average loss: 3.1535 Iteration: 1925; Percent complete: 48.1%; Average loss: 3.1334 Iteration: 1926; Percent complete: 48.1%; Average loss: 3.1596 Iteration: 1927; Percent complete: 48.2%; Average loss: 3.0238 Iteration: 1928; Percent complete: 48.2%; Average loss: 3.1859 Iteration: 1929; Percent complete: 48.2%; Average loss: 3.1206 Iteration: 1930; Percent complete: 48.2%; Average loss: 2.8868 Iteration: 1931; Percent complete: 48.3%; Average loss: 3.2410 Iteration: 1932; Percent complete: 48.3%; Average loss: 3.0013 Iteration: 1933; Percent complete: 48.3%; Average loss: 3.3067 Iteration: 1934; Percent complete: 48.4%; Average loss: 3.0804 Iteration: 1935; Percent complete: 48.4%; Average loss: 3.3156 Iteration: 1936; Percent complete: 48.4%; Average loss: 3.1444 Iteration: 1937; Percent complete: 48.4%; Average loss: 3.0530 Iteration: 1938; Percent complete: 48.4%; Average loss: 3.2447 Iteration: 1939; Percent complete: 48.5%; Average loss: 3.0594 Iteration: 1940; Percent complete: 48.5%; Average loss: 3.2126 Iteration: 1941; Percent complete: 48.5%; Average loss: 3.0503 Iteration: 1942; Percent complete: 48.5%; Average loss: 3.2449 Iteration: 1943; Percent complete: 48.6%; Average loss: 3.1148 Iteration: 1944; Percent complete: 48.6%; Average loss: 2.9914 Iteration: 1945; Percent complete: 48.6%; Average loss: 3.1128 Iteration: 1946; Percent complete: 48.6%; Average loss: 3.3171 Iteration: 1947; Percent complete: 48.7%; Average loss: 3.2491 Iteration: 1948; Percent complete: 48.7%; Average loss: 3.1829 Iteration: 1949; Percent complete: 48.7%; Average loss: 3.3291 Iteration: 1950; Percent complete: 48.8%; Average loss: 3.2305 Iteration: 1951; Percent complete: 48.8%; Average loss: 3.0523 Iteration: 1952; Percent complete: 48.8%; Average loss: 3.2682 Iteration: 1953; Percent complete: 48.8%; Average loss: 3.1249 Iteration: 1954; Percent complete: 48.9%; Average loss: 3.0757 Iteration: 1955; Percent complete: 48.9%; Average loss: 2.9147 Iteration: 1956; Percent complete: 48.9%; Average loss: 3.1402 Iteration: 1957; Percent complete: 48.9%; Average loss: 2.9203 Iteration: 1958; Percent complete: 48.9%; Average loss: 3.3850 Iteration: 1959; Percent complete: 49.0%; Average loss: 3.2709 Iteration: 1960; Percent complete: 49.0%; Average loss: 3.3953 Iteration: 1961; Percent complete: 49.0%; Average loss: 2.9023 Iteration: 1962; Percent complete: 49.0%; Average loss: 3.1508 Iteration: 1963; Percent complete: 49.1%; Average loss: 3.3039 Iteration: 1964; Percent complete: 49.1%; Average loss: 3.0012 Iteration: 1965; Percent complete: 49.1%; Average loss: 3.0501 Iteration: 1966; Percent complete: 49.1%; Average loss: 2.9183 Iteration: 1967; Percent complete: 49.2%; Average loss: 3.2355 Iteration: 1968; Percent complete: 49.2%; Average loss: 2.6765 Iteration: 1969; Percent complete: 49.2%; Average loss: 2.7911 Iteration: 1970; Percent complete: 49.2%; Average loss: 3.1373 Iteration: 1971; Percent complete: 49.3%; Average loss: 3.2078 Iteration: 1972; Percent complete: 49.3%; Average loss: 2.8246 Iteration: 1973; Percent complete: 49.3%; Average loss: 2.9807 Iteration: 1974; Percent complete: 49.4%; Average loss: 3.3305 Iteration: 1975; Percent complete: 49.4%; Average loss: 2.8084 Iteration: 1976; Percent complete: 49.4%; Average loss: 3.3077 Iteration: 1977; Percent complete: 49.4%; Average loss: 2.9969 Iteration: 1978; Percent complete: 49.5%; Average loss: 2.9809 Iteration: 1979; Percent complete: 49.5%; Average loss: 3.1690 Iteration: 1980; Percent complete: 49.5%; Average loss: 3.1645 Iteration: 1981; Percent complete: 49.5%; Average loss: 3.3002 Iteration: 1982; Percent complete: 49.5%; Average loss: 3.2052 Iteration: 1983; Percent complete: 49.6%; Average loss: 3.3550 Iteration: 1984; Percent complete: 49.6%; Average loss: 3.0970 Iteration: 1985; Percent complete: 49.6%; Average loss: 3.2243 Iteration: 1986; Percent complete: 49.6%; Average loss: 3.3862 Iteration: 1987; Percent complete: 49.7%; Average loss: 3.0583 Iteration: 1988; Percent complete: 49.7%; Average loss: 3.3518 Iteration: 1989; Percent complete: 49.7%; Average loss: 3.1325 Iteration: 1990; Percent complete: 49.8%; Average loss: 3.1231 Iteration: 1991; Percent complete: 49.8%; Average loss: 3.2490 Iteration: 1992; Percent complete: 49.8%; Average loss: 3.0738 Iteration: 1993; Percent complete: 49.8%; Average loss: 3.3225 Iteration: 1994; Percent complete: 49.9%; Average loss: 3.2903 Iteration: 1995; Percent complete: 49.9%; Average loss: 3.1316 Iteration: 1996; Percent complete: 49.9%; Average loss: 2.9411 Iteration: 1997; Percent complete: 49.9%; Average loss: 3.2565 Iteration: 1998; Percent complete: 50.0%; Average loss: 2.9941 Iteration: 1999; Percent complete: 50.0%; Average loss: 2.9547 Iteration: 2000; Percent complete: 50.0%; Average loss: 3.2050 Iteration: 2001; Percent complete: 50.0%; Average loss: 3.1220 Iteration: 2002; Percent complete: 50.0%; Average loss: 3.2148 Iteration: 2003; Percent complete: 50.1%; Average loss: 3.1028 Iteration: 2004; Percent complete: 50.1%; Average loss: 3.1398 Iteration: 2005; Percent complete: 50.1%; Average loss: 2.8681 Iteration: 2006; Percent complete: 50.1%; Average loss: 2.9920 Iteration: 2007; Percent complete: 50.2%; Average loss: 3.1613 Iteration: 2008; Percent complete: 50.2%; Average loss: 3.2713 Iteration: 2009; Percent complete: 50.2%; Average loss: 3.0881 Iteration: 2010; Percent complete: 50.2%; Average loss: 2.8820 Iteration: 2011; Percent complete: 50.3%; Average loss: 2.9539 Iteration: 2012; Percent complete: 50.3%; Average loss: 3.3017 Iteration: 2013; Percent complete: 50.3%; Average loss: 3.0075 Iteration: 2014; Percent complete: 50.3%; Average loss: 3.1440 Iteration: 2015; Percent complete: 50.4%; Average loss: 3.0451 Iteration: 2016; Percent complete: 50.4%; Average loss: 3.2156 Iteration: 2017; Percent complete: 50.4%; Average loss: 3.2827 Iteration: 2018; Percent complete: 50.4%; Average loss: 3.0738 Iteration: 2019; Percent complete: 50.5%; Average loss: 3.2786 Iteration: 2020; Percent complete: 50.5%; Average loss: 3.0971 Iteration: 2021; Percent complete: 50.5%; Average loss: 3.1644 Iteration: 2022; Percent complete: 50.5%; Average loss: 3.1274 Iteration: 2023; Percent complete: 50.6%; Average loss: 3.0747 Iteration: 2024; Percent complete: 50.6%; Average loss: 3.2808 Iteration: 2025; Percent complete: 50.6%; Average loss: 2.9597 Iteration: 2026; Percent complete: 50.6%; Average loss: 3.2533 Iteration: 2027; Percent complete: 50.7%; Average loss: 2.9248 Iteration: 2028; Percent complete: 50.7%; Average loss: 3.2251 Iteration: 2029; Percent complete: 50.7%; Average loss: 3.3952 Iteration: 2030; Percent complete: 50.7%; Average loss: 3.5306 Iteration: 2031; Percent complete: 50.8%; Average loss: 3.0520 Iteration: 2032; Percent complete: 50.8%; Average loss: 3.4348 Iteration: 2033; Percent complete: 50.8%; Average loss: 3.1870 Iteration: 2034; Percent complete: 50.8%; Average loss: 2.9692 Iteration: 2035; Percent complete: 50.9%; Average loss: 3.2315 Iteration: 2036; Percent complete: 50.9%; Average loss: 3.3439 Iteration: 2037; Percent complete: 50.9%; Average loss: 3.1642 Iteration: 2038; Percent complete: 50.9%; Average loss: 3.8122 Iteration: 2039; Percent complete: 51.0%; Average loss: 3.1173 Iteration: 2040; Percent complete: 51.0%; Average loss: 3.2174 Iteration: 2041; Percent complete: 51.0%; Average loss: 2.9998 Iteration: 2042; Percent complete: 51.0%; Average loss: 3.2791 Iteration: 2043; Percent complete: 51.1%; Average loss: 3.3198 Iteration: 2044; Percent complete: 51.1%; Average loss: 3.1315 Iteration: 2045; Percent complete: 51.1%; Average loss: 3.1268 Iteration: 2046; Percent complete: 51.1%; Average loss: 3.3421 Iteration: 2047; Percent complete: 51.2%; Average loss: 3.1476 Iteration: 2048; Percent complete: 51.2%; Average loss: 3.0307 Iteration: 2049; Percent complete: 51.2%; Average loss: 3.1706 Iteration: 2050; Percent complete: 51.2%; Average loss: 3.6805 Iteration: 2051; Percent complete: 51.3%; Average loss: 3.1899 Iteration: 2052; Percent complete: 51.3%; Average loss: 2.8288 Iteration: 2053; Percent complete: 51.3%; Average loss: 3.1877 Iteration: 2054; Percent complete: 51.3%; Average loss: 3.2439 Iteration: 2055; Percent complete: 51.4%; Average loss: 3.2039 Iteration: 2056; Percent complete: 51.4%; Average loss: 3.2958 Iteration: 2057; Percent complete: 51.4%; Average loss: 2.8138 Iteration: 2058; Percent complete: 51.4%; Average loss: 3.0092 Iteration: 2059; Percent complete: 51.5%; Average loss: 3.2780 Iteration: 2060; Percent complete: 51.5%; Average loss: 3.1062 Iteration: 2061; Percent complete: 51.5%; Average loss: 3.1710 Iteration: 2062; Percent complete: 51.5%; Average loss: 3.0315 Iteration: 2063; Percent complete: 51.6%; Average loss: 3.2914 Iteration: 2064; Percent complete: 51.6%; Average loss: 3.0573 Iteration: 2065; Percent complete: 51.6%; Average loss: 3.0758 Iteration: 2066; Percent complete: 51.6%; Average loss: 3.1120 Iteration: 2067; Percent complete: 51.7%; Average loss: 3.2179 Iteration: 2068; Percent complete: 51.7%; Average loss: 3.4420 Iteration: 2069; Percent complete: 51.7%; Average loss: 3.0375 Iteration: 2070; Percent complete: 51.7%; Average loss: 3.0351 Iteration: 2071; Percent complete: 51.8%; Average loss: 3.0943 Iteration: 2072; Percent complete: 51.8%; Average loss: 3.1973 Iteration: 2073; Percent complete: 51.8%; Average loss: 3.0584 Iteration: 2074; Percent complete: 51.8%; Average loss: 3.3704 Iteration: 2075; Percent complete: 51.9%; Average loss: 3.4169 Iteration: 2076; Percent complete: 51.9%; Average loss: 3.1850 Iteration: 2077; Percent complete: 51.9%; Average loss: 3.1341 Iteration: 2078; Percent complete: 51.9%; Average loss: 3.2229 Iteration: 2079; Percent complete: 52.0%; Average loss: 3.0053 Iteration: 2080; Percent complete: 52.0%; Average loss: 3.5050 Iteration: 2081; Percent complete: 52.0%; Average loss: 3.2849 Iteration: 2082; Percent complete: 52.0%; Average loss: 3.0233 Iteration: 2083; Percent complete: 52.1%; Average loss: 3.1191 Iteration: 2084; Percent complete: 52.1%; Average loss: 3.0870 Iteration: 2085; Percent complete: 52.1%; Average loss: 3.1829 Iteration: 2086; Percent complete: 52.1%; Average loss: 3.0635 Iteration: 2087; Percent complete: 52.2%; Average loss: 3.1791 Iteration: 2088; Percent complete: 52.2%; Average loss: 3.0271 Iteration: 2089; Percent complete: 52.2%; Average loss: 3.0115 Iteration: 2090; Percent complete: 52.2%; Average loss: 3.0537 Iteration: 2091; Percent complete: 52.3%; Average loss: 3.1242 Iteration: 2092; Percent complete: 52.3%; Average loss: 3.3818 Iteration: 2093; Percent complete: 52.3%; Average loss: 3.0642 Iteration: 2094; Percent complete: 52.3%; Average loss: 3.0156 Iteration: 2095; Percent complete: 52.4%; Average loss: 3.1104 Iteration: 2096; Percent complete: 52.4%; Average loss: 3.2099 Iteration: 2097; Percent complete: 52.4%; Average loss: 3.0529 Iteration: 2098; Percent complete: 52.4%; Average loss: 3.1401 Iteration: 2099; Percent complete: 52.5%; Average loss: 3.2115 Iteration: 2100; Percent complete: 52.5%; Average loss: 3.1442 Iteration: 2101; Percent complete: 52.5%; Average loss: 3.1309 Iteration: 2102; Percent complete: 52.5%; Average loss: 3.3911 Iteration: 2103; Percent complete: 52.6%; Average loss: 3.1025 Iteration: 2104; Percent complete: 52.6%; Average loss: 3.0971 Iteration: 2105; Percent complete: 52.6%; Average loss: 3.1303 Iteration: 2106; Percent complete: 52.6%; Average loss: 2.9175 Iteration: 2107; Percent complete: 52.7%; Average loss: 3.1597 Iteration: 2108; Percent complete: 52.7%; Average loss: 3.1260 Iteration: 2109; Percent complete: 52.7%; Average loss: 3.2018 Iteration: 2110; Percent complete: 52.8%; Average loss: 3.1795 Iteration: 2111; Percent complete: 52.8%; Average loss: 3.0150 Iteration: 2112; Percent complete: 52.8%; Average loss: 3.1272 Iteration: 2113; Percent complete: 52.8%; Average loss: 2.8334 Iteration: 2114; Percent complete: 52.8%; Average loss: 3.1090 Iteration: 2115; Percent complete: 52.9%; Average loss: 3.3560 Iteration: 2116; Percent complete: 52.9%; Average loss: 3.0045 Iteration: 2117; Percent complete: 52.9%; Average loss: 3.0784 Iteration: 2118; Percent complete: 52.9%; Average loss: 3.0342 Iteration: 2119; Percent complete: 53.0%; Average loss: 3.3143 Iteration: 2120; Percent complete: 53.0%; Average loss: 2.9348 Iteration: 2121; Percent complete: 53.0%; Average loss: 3.0964 Iteration: 2122; Percent complete: 53.0%; Average loss: 3.0448 Iteration: 2123; Percent complete: 53.1%; Average loss: 3.1987 Iteration: 2124; Percent complete: 53.1%; Average loss: 3.0161 Iteration: 2125; Percent complete: 53.1%; Average loss: 3.1386 Iteration: 2126; Percent complete: 53.1%; Average loss: 3.1287 Iteration: 2127; Percent complete: 53.2%; Average loss: 3.1042 Iteration: 2128; Percent complete: 53.2%; Average loss: 3.0072 Iteration: 2129; Percent complete: 53.2%; Average loss: 3.0868 Iteration: 2130; Percent complete: 53.2%; Average loss: 3.1732 Iteration: 2131; Percent complete: 53.3%; Average loss: 3.1291 Iteration: 2132; Percent complete: 53.3%; Average loss: 3.1058 Iteration: 2133; Percent complete: 53.3%; Average loss: 3.3029 Iteration: 2134; Percent complete: 53.3%; Average loss: 3.1003 Iteration: 2135; Percent complete: 53.4%; Average loss: 3.1334 Iteration: 2136; Percent complete: 53.4%; Average loss: 2.9098 Iteration: 2137; Percent complete: 53.4%; Average loss: 2.9286 Iteration: 2138; Percent complete: 53.4%; Average loss: 3.0234 Iteration: 2139; Percent complete: 53.5%; Average loss: 3.0347 Iteration: 2140; Percent complete: 53.5%; Average loss: 2.9344 Iteration: 2141; Percent complete: 53.5%; Average loss: 3.2577 Iteration: 2142; Percent complete: 53.5%; Average loss: 3.1194 Iteration: 2143; Percent complete: 53.6%; Average loss: 3.3176 Iteration: 2144; Percent complete: 53.6%; Average loss: 2.9911 Iteration: 2145; Percent complete: 53.6%; Average loss: 3.0549 Iteration: 2146; Percent complete: 53.6%; Average loss: 3.0807 Iteration: 2147; Percent complete: 53.7%; Average loss: 3.2789 Iteration: 2148; Percent complete: 53.7%; Average loss: 3.3476 Iteration: 2149; Percent complete: 53.7%; Average loss: 3.2186 Iteration: 2150; Percent complete: 53.8%; Average loss: 2.7736 Iteration: 2151; Percent complete: 53.8%; Average loss: 3.0894 Iteration: 2152; Percent complete: 53.8%; Average loss: 2.9813 Iteration: 2153; Percent complete: 53.8%; Average loss: 3.0777 Iteration: 2154; Percent complete: 53.8%; Average loss: 2.8545 Iteration: 2155; Percent complete: 53.9%; Average loss: 3.2971 Iteration: 2156; Percent complete: 53.9%; Average loss: 3.2127 Iteration: 2157; Percent complete: 53.9%; Average loss: 3.0932 Iteration: 2158; Percent complete: 53.9%; Average loss: 3.4698 Iteration: 2159; Percent complete: 54.0%; Average loss: 3.0915 Iteration: 2160; Percent complete: 54.0%; Average loss: 2.9651 Iteration: 2161; Percent complete: 54.0%; Average loss: 3.3126 Iteration: 2162; Percent complete: 54.0%; Average loss: 3.1693 Iteration: 2163; Percent complete: 54.1%; Average loss: 3.0134 Iteration: 2164; Percent complete: 54.1%; Average loss: 2.8968 Iteration: 2165; Percent complete: 54.1%; Average loss: 3.0285 Iteration: 2166; Percent complete: 54.1%; Average loss: 3.3426 Iteration: 2167; Percent complete: 54.2%; Average loss: 3.1184 Iteration: 2168; Percent complete: 54.2%; Average loss: 3.0999 Iteration: 2169; Percent complete: 54.2%; Average loss: 2.9527 Iteration: 2170; Percent complete: 54.2%; Average loss: 3.0716 Iteration: 2171; Percent complete: 54.3%; Average loss: 3.3020 Iteration: 2172; Percent complete: 54.3%; Average loss: 3.1737 Iteration: 2173; Percent complete: 54.3%; Average loss: 3.1312 Iteration: 2174; Percent complete: 54.4%; Average loss: 3.1873 Iteration: 2175; Percent complete: 54.4%; Average loss: 2.8976 Iteration: 2176; Percent complete: 54.4%; Average loss: 3.0015 Iteration: 2177; Percent complete: 54.4%; Average loss: 3.3148 Iteration: 2178; Percent complete: 54.4%; Average loss: 3.0653 Iteration: 2179; Percent complete: 54.5%; Average loss: 3.2087 Iteration: 2180; Percent complete: 54.5%; Average loss: 3.0357 Iteration: 2181; Percent complete: 54.5%; Average loss: 3.2595 Iteration: 2182; Percent complete: 54.5%; Average loss: 3.1117 Iteration: 2183; Percent complete: 54.6%; Average loss: 3.1168 Iteration: 2184; Percent complete: 54.6%; Average loss: 3.2596 Iteration: 2185; Percent complete: 54.6%; Average loss: 3.2766 Iteration: 2186; Percent complete: 54.6%; Average loss: 3.1199 Iteration: 2187; Percent complete: 54.7%; Average loss: 2.9820 Iteration: 2188; Percent complete: 54.7%; Average loss: 2.9330 Iteration: 2189; Percent complete: 54.7%; Average loss: 3.3362 Iteration: 2190; Percent complete: 54.8%; Average loss: 3.0809 Iteration: 2191; Percent complete: 54.8%; Average loss: 3.2771 Iteration: 2192; Percent complete: 54.8%; Average loss: 3.0776 Iteration: 2193; Percent complete: 54.8%; Average loss: 3.1039 Iteration: 2194; Percent complete: 54.9%; Average loss: 3.3314 Iteration: 2195; Percent complete: 54.9%; Average loss: 3.0769 Iteration: 2196; Percent complete: 54.9%; Average loss: 2.9924 Iteration: 2197; Percent complete: 54.9%; Average loss: 3.1182 Iteration: 2198; Percent complete: 54.9%; Average loss: 2.8760 Iteration: 2199; Percent complete: 55.0%; Average loss: 3.1414 Iteration: 2200; Percent complete: 55.0%; Average loss: 2.9853 Iteration: 2201; Percent complete: 55.0%; Average loss: 3.2970 Iteration: 2202; Percent complete: 55.0%; Average loss: 3.1970 Iteration: 2203; Percent complete: 55.1%; Average loss: 3.1897 Iteration: 2204; Percent complete: 55.1%; Average loss: 3.1190 Iteration: 2205; Percent complete: 55.1%; Average loss: 3.1261 Iteration: 2206; Percent complete: 55.1%; Average loss: 3.3225 Iteration: 2207; Percent complete: 55.2%; Average loss: 3.1963 Iteration: 2208; Percent complete: 55.2%; Average loss: 3.0725 Iteration: 2209; Percent complete: 55.2%; Average loss: 3.1786 Iteration: 2210; Percent complete: 55.2%; Average loss: 3.4157 Iteration: 2211; Percent complete: 55.3%; Average loss: 3.2420 Iteration: 2212; Percent complete: 55.3%; Average loss: 2.9719 Iteration: 2213; Percent complete: 55.3%; Average loss: 3.1023 Iteration: 2214; Percent complete: 55.4%; Average loss: 3.2108 Iteration: 2215; Percent complete: 55.4%; Average loss: 3.3364 Iteration: 2216; Percent complete: 55.4%; Average loss: 3.1127 Iteration: 2217; Percent complete: 55.4%; Average loss: 3.2705 Iteration: 2218; Percent complete: 55.5%; Average loss: 3.3505 Iteration: 2219; Percent complete: 55.5%; Average loss: 3.3872 Iteration: 2220; Percent complete: 55.5%; Average loss: 3.0498 Iteration: 2221; Percent complete: 55.5%; Average loss: 3.2546 Iteration: 2222; Percent complete: 55.5%; Average loss: 3.2073 Iteration: 2223; Percent complete: 55.6%; Average loss: 3.1363 Iteration: 2224; Percent complete: 55.6%; Average loss: 2.9946 Iteration: 2225; Percent complete: 55.6%; Average loss: 2.8915 Iteration: 2226; Percent complete: 55.6%; Average loss: 3.0293 Iteration: 2227; Percent complete: 55.7%; Average loss: 3.2835 Iteration: 2228; Percent complete: 55.7%; Average loss: 3.3445 Iteration: 2229; Percent complete: 55.7%; Average loss: 3.2012 Iteration: 2230; Percent complete: 55.8%; Average loss: 3.1993 Iteration: 2231; Percent complete: 55.8%; Average loss: 2.9709 Iteration: 2232; Percent complete: 55.8%; Average loss: 3.0296 Iteration: 2233; Percent complete: 55.8%; Average loss: 3.2953 Iteration: 2234; Percent complete: 55.9%; Average loss: 3.1630 Iteration: 2235; Percent complete: 55.9%; Average loss: 2.9506 Iteration: 2236; Percent complete: 55.9%; Average loss: 3.0341 Iteration: 2237; Percent complete: 55.9%; Average loss: 3.0442 Iteration: 2238; Percent complete: 56.0%; Average loss: 2.9930 Iteration: 2239; Percent complete: 56.0%; Average loss: 2.9833 Iteration: 2240; Percent complete: 56.0%; Average loss: 2.9867 Iteration: 2241; Percent complete: 56.0%; Average loss: 3.0773 Iteration: 2242; Percent complete: 56.0%; Average loss: 3.0334 Iteration: 2243; Percent complete: 56.1%; Average loss: 3.0079 Iteration: 2244; Percent complete: 56.1%; Average loss: 3.0967 Iteration: 2245; Percent complete: 56.1%; Average loss: 3.2643 Iteration: 2246; Percent complete: 56.1%; Average loss: 3.0794 Iteration: 2247; Percent complete: 56.2%; Average loss: 3.4839 Iteration: 2248; Percent complete: 56.2%; Average loss: 3.0216 Iteration: 2249; Percent complete: 56.2%; Average loss: 3.1439 Iteration: 2250; Percent complete: 56.2%; Average loss: 2.9332 Iteration: 2251; Percent complete: 56.3%; Average loss: 3.1694 Iteration: 2252; Percent complete: 56.3%; Average loss: 3.0943 Iteration: 2253; Percent complete: 56.3%; Average loss: 3.0856 Iteration: 2254; Percent complete: 56.4%; Average loss: 3.1710 Iteration: 2255; Percent complete: 56.4%; Average loss: 2.9592 Iteration: 2256; Percent complete: 56.4%; Average loss: 3.3418 Iteration: 2257; Percent complete: 56.4%; Average loss: 2.9973 Iteration: 2258; Percent complete: 56.5%; Average loss: 3.3154 Iteration: 2259; Percent complete: 56.5%; Average loss: 3.1771 Iteration: 2260; Percent complete: 56.5%; Average loss: 2.9380 Iteration: 2261; Percent complete: 56.5%; Average loss: 3.0814 Iteration: 2262; Percent complete: 56.5%; Average loss: 3.0033 Iteration: 2263; Percent complete: 56.6%; Average loss: 2.8198 Iteration: 2264; Percent complete: 56.6%; Average loss: 2.8776 Iteration: 2265; Percent complete: 56.6%; Average loss: 2.7840 Iteration: 2266; Percent complete: 56.6%; Average loss: 3.1524 Iteration: 2267; Percent complete: 56.7%; Average loss: 3.0536 Iteration: 2268; Percent complete: 56.7%; Average loss: 2.8683 Iteration: 2269; Percent complete: 56.7%; Average loss: 3.1298 Iteration: 2270; Percent complete: 56.8%; Average loss: 2.7638 Iteration: 2271; Percent complete: 56.8%; Average loss: 3.2516 Iteration: 2272; Percent complete: 56.8%; Average loss: 2.9215 Iteration: 2273; Percent complete: 56.8%; Average loss: 3.0926 Iteration: 2274; Percent complete: 56.9%; Average loss: 2.9187 Iteration: 2275; Percent complete: 56.9%; Average loss: 3.0571 Iteration: 2276; Percent complete: 56.9%; Average loss: 3.1107 Iteration: 2277; Percent complete: 56.9%; Average loss: 3.0010 Iteration: 2278; Percent complete: 57.0%; Average loss: 3.1321 Iteration: 2279; Percent complete: 57.0%; Average loss: 3.2357 Iteration: 2280; Percent complete: 57.0%; Average loss: 3.1262 Iteration: 2281; Percent complete: 57.0%; Average loss: 3.0446 Iteration: 2282; Percent complete: 57.0%; Average loss: 3.2927 Iteration: 2283; Percent complete: 57.1%; Average loss: 3.1757 Iteration: 2284; Percent complete: 57.1%; Average loss: 3.2276 Iteration: 2285; Percent complete: 57.1%; Average loss: 3.0504 Iteration: 2286; Percent complete: 57.1%; Average loss: 3.1023 Iteration: 2287; Percent complete: 57.2%; Average loss: 3.0208 Iteration: 2288; Percent complete: 57.2%; Average loss: 2.9687 Iteration: 2289; Percent complete: 57.2%; Average loss: 2.9497 Iteration: 2290; Percent complete: 57.2%; Average loss: 2.9993 Iteration: 2291; Percent complete: 57.3%; Average loss: 2.8280 Iteration: 2292; Percent complete: 57.3%; Average loss: 3.0283 Iteration: 2293; Percent complete: 57.3%; Average loss: 3.0965 Iteration: 2294; Percent complete: 57.4%; Average loss: 3.0884 Iteration: 2295; Percent complete: 57.4%; Average loss: 2.9668 Iteration: 2296; Percent complete: 57.4%; Average loss: 3.0393 Iteration: 2297; Percent complete: 57.4%; Average loss: 2.9863 Iteration: 2298; Percent complete: 57.5%; Average loss: 3.1158 Iteration: 2299; Percent complete: 57.5%; Average loss: 2.8022 Iteration: 2300; Percent complete: 57.5%; Average loss: 2.8674 Iteration: 2301; Percent complete: 57.5%; Average loss: 3.1625 Iteration: 2302; Percent complete: 57.6%; Average loss: 3.0815 Iteration: 2303; Percent complete: 57.6%; Average loss: 3.5918 Iteration: 2304; Percent complete: 57.6%; Average loss: 3.1200 Iteration: 2305; Percent complete: 57.6%; Average loss: 3.0869 Iteration: 2306; Percent complete: 57.6%; Average loss: 3.3112 Iteration: 2307; Percent complete: 57.7%; Average loss: 2.8601 Iteration: 2308; Percent complete: 57.7%; Average loss: 3.1145 Iteration: 2309; Percent complete: 57.7%; Average loss: 2.9767 Iteration: 2310; Percent complete: 57.8%; Average loss: 3.0672 Iteration: 2311; Percent complete: 57.8%; Average loss: 3.0643 Iteration: 2312; Percent complete: 57.8%; Average loss: 3.0974 Iteration: 2313; Percent complete: 57.8%; Average loss: 2.9734 Iteration: 2314; Percent complete: 57.9%; Average loss: 2.8460 Iteration: 2315; Percent complete: 57.9%; Average loss: 3.0868 Iteration: 2316; Percent complete: 57.9%; Average loss: 3.0283 Iteration: 2317; Percent complete: 57.9%; Average loss: 3.3072 Iteration: 2318; Percent complete: 58.0%; Average loss: 3.0635 Iteration: 2319; Percent complete: 58.0%; Average loss: 3.0174 Iteration: 2320; Percent complete: 58.0%; Average loss: 3.0065 Iteration: 2321; Percent complete: 58.0%; Average loss: 3.1648 Iteration: 2322; Percent complete: 58.1%; Average loss: 3.0269 Iteration: 2323; Percent complete: 58.1%; Average loss: 3.2151 Iteration: 2324; Percent complete: 58.1%; Average loss: 2.9599 Iteration: 2325; Percent complete: 58.1%; Average loss: 3.1293 Iteration: 2326; Percent complete: 58.1%; Average loss: 3.0035 Iteration: 2327; Percent complete: 58.2%; Average loss: 3.0349 Iteration: 2328; Percent complete: 58.2%; Average loss: 3.0289 Iteration: 2329; Percent complete: 58.2%; Average loss: 2.9084 Iteration: 2330; Percent complete: 58.2%; Average loss: 3.0724 Iteration: 2331; Percent complete: 58.3%; Average loss: 3.3233 Iteration: 2332; Percent complete: 58.3%; Average loss: 3.1491 Iteration: 2333; Percent complete: 58.3%; Average loss: 3.0652 Iteration: 2334; Percent complete: 58.4%; Average loss: 2.8556 Iteration: 2335; Percent complete: 58.4%; Average loss: 3.1396 Iteration: 2336; Percent complete: 58.4%; Average loss: 3.1199 Iteration: 2337; Percent complete: 58.4%; Average loss: 3.0737 Iteration: 2338; Percent complete: 58.5%; Average loss: 3.0121 Iteration: 2339; Percent complete: 58.5%; Average loss: 3.1651 Iteration: 2340; Percent complete: 58.5%; Average loss: 3.0271 Iteration: 2341; Percent complete: 58.5%; Average loss: 3.0024 Iteration: 2342; Percent complete: 58.6%; Average loss: 3.1509 Iteration: 2343; Percent complete: 58.6%; Average loss: 3.1131 Iteration: 2344; Percent complete: 58.6%; Average loss: 2.9229 Iteration: 2345; Percent complete: 58.6%; Average loss: 3.0783 Iteration: 2346; Percent complete: 58.7%; Average loss: 3.2676 Iteration: 2347; Percent complete: 58.7%; Average loss: 3.0802 Iteration: 2348; Percent complete: 58.7%; Average loss: 2.9503 Iteration: 2349; Percent complete: 58.7%; Average loss: 3.0161 Iteration: 2350; Percent complete: 58.8%; Average loss: 3.2102 Iteration: 2351; Percent complete: 58.8%; Average loss: 2.9143 Iteration: 2352; Percent complete: 58.8%; Average loss: 2.9980 Iteration: 2353; Percent complete: 58.8%; Average loss: 2.9619 Iteration: 2354; Percent complete: 58.9%; Average loss: 3.0666 Iteration: 2355; Percent complete: 58.9%; Average loss: 3.1465 Iteration: 2356; Percent complete: 58.9%; Average loss: 3.1123 Iteration: 2357; Percent complete: 58.9%; Average loss: 3.0513 Iteration: 2358; Percent complete: 59.0%; Average loss: 3.3397 Iteration: 2359; Percent complete: 59.0%; Average loss: 3.1479 Iteration: 2360; Percent complete: 59.0%; Average loss: 2.8586 Iteration: 2361; Percent complete: 59.0%; Average loss: 2.9561 Iteration: 2362; Percent complete: 59.1%; Average loss: 3.3488 Iteration: 2363; Percent complete: 59.1%; Average loss: 3.0482 Iteration: 2364; Percent complete: 59.1%; Average loss: 3.2510 Iteration: 2365; Percent complete: 59.1%; Average loss: 3.2665 Iteration: 2366; Percent complete: 59.2%; Average loss: 3.2543 Iteration: 2367; Percent complete: 59.2%; Average loss: 3.0365 Iteration: 2368; Percent complete: 59.2%; Average loss: 3.0304 Iteration: 2369; Percent complete: 59.2%; Average loss: 3.1243 Iteration: 2370; Percent complete: 59.2%; Average loss: 3.0438 Iteration: 2371; Percent complete: 59.3%; Average loss: 3.0941 Iteration: 2372; Percent complete: 59.3%; Average loss: 2.9181 Iteration: 2373; Percent complete: 59.3%; Average loss: 2.9559 Iteration: 2374; Percent complete: 59.4%; Average loss: 2.9610 Iteration: 2375; Percent complete: 59.4%; Average loss: 3.1460 Iteration: 2376; Percent complete: 59.4%; Average loss: 2.9601 Iteration: 2377; Percent complete: 59.4%; Average loss: 3.1229 Iteration: 2378; Percent complete: 59.5%; Average loss: 3.0564 Iteration: 2379; Percent complete: 59.5%; Average loss: 2.9406 Iteration: 2380; Percent complete: 59.5%; Average loss: 3.1179 Iteration: 2381; Percent complete: 59.5%; Average loss: 3.1028 Iteration: 2382; Percent complete: 59.6%; Average loss: 3.3896 Iteration: 2383; Percent complete: 59.6%; Average loss: 3.1369 Iteration: 2384; Percent complete: 59.6%; Average loss: 2.8653 Iteration: 2385; Percent complete: 59.6%; Average loss: 3.2399 Iteration: 2386; Percent complete: 59.7%; Average loss: 3.1899 Iteration: 2387; Percent complete: 59.7%; Average loss: 2.8797 Iteration: 2388; Percent complete: 59.7%; Average loss: 2.9621 Iteration: 2389; Percent complete: 59.7%; Average loss: 2.8515 Iteration: 2390; Percent complete: 59.8%; Average loss: 2.9659 Iteration: 2391; Percent complete: 59.8%; Average loss: 3.2610 Iteration: 2392; Percent complete: 59.8%; Average loss: 3.1137 Iteration: 2393; Percent complete: 59.8%; Average loss: 3.2475 Iteration: 2394; Percent complete: 59.9%; Average loss: 2.9315 Iteration: 2395; Percent complete: 59.9%; Average loss: 3.0743 Iteration: 2396; Percent complete: 59.9%; Average loss: 3.1087 Iteration: 2397; Percent complete: 59.9%; Average loss: 2.8460 Iteration: 2398; Percent complete: 60.0%; Average loss: 3.1938 Iteration: 2399; Percent complete: 60.0%; Average loss: 2.8384 Iteration: 2400; Percent complete: 60.0%; Average loss: 2.6512 Iteration: 2401; Percent complete: 60.0%; Average loss: 2.9405 Iteration: 2402; Percent complete: 60.1%; Average loss: 2.9099 Iteration: 2403; Percent complete: 60.1%; Average loss: 2.7917 Iteration: 2404; Percent complete: 60.1%; Average loss: 2.7661 Iteration: 2405; Percent complete: 60.1%; Average loss: 3.2068 Iteration: 2406; Percent complete: 60.2%; Average loss: 3.1744 Iteration: 2407; Percent complete: 60.2%; Average loss: 3.1008 Iteration: 2408; Percent complete: 60.2%; Average loss: 3.0129 Iteration: 2409; Percent complete: 60.2%; Average loss: 3.1564 Iteration: 2410; Percent complete: 60.2%; Average loss: 3.0074 Iteration: 2411; Percent complete: 60.3%; Average loss: 2.9896 Iteration: 2412; Percent complete: 60.3%; Average loss: 3.2040 Iteration: 2413; Percent complete: 60.3%; Average loss: 3.2846 Iteration: 2414; Percent complete: 60.4%; Average loss: 3.3163 Iteration: 2415; Percent complete: 60.4%; Average loss: 3.1789 Iteration: 2416; Percent complete: 60.4%; Average loss: 3.1687 Iteration: 2417; Percent complete: 60.4%; Average loss: 3.1238 Iteration: 2418; Percent complete: 60.5%; Average loss: 3.1842 Iteration: 2419; Percent complete: 60.5%; Average loss: 3.1937 Iteration: 2420; Percent complete: 60.5%; Average loss: 3.1693 Iteration: 2421; Percent complete: 60.5%; Average loss: 3.1783 Iteration: 2422; Percent complete: 60.6%; Average loss: 2.9708 Iteration: 2423; Percent complete: 60.6%; Average loss: 3.0848 Iteration: 2424; Percent complete: 60.6%; Average loss: 2.8048 Iteration: 2425; Percent complete: 60.6%; Average loss: 2.9275 Iteration: 2426; Percent complete: 60.7%; Average loss: 3.0026 Iteration: 2427; Percent complete: 60.7%; Average loss: 2.9433 Iteration: 2428; Percent complete: 60.7%; Average loss: 2.8574 Iteration: 2429; Percent complete: 60.7%; Average loss: 3.1838 Iteration: 2430; Percent complete: 60.8%; Average loss: 3.0820 Iteration: 2431; Percent complete: 60.8%; Average loss: 2.9067 Iteration: 2432; Percent complete: 60.8%; Average loss: 3.0638 Iteration: 2433; Percent complete: 60.8%; Average loss: 2.9357 Iteration: 2434; Percent complete: 60.9%; Average loss: 3.0468 Iteration: 2435; Percent complete: 60.9%; Average loss: 3.0584 Iteration: 2436; Percent complete: 60.9%; Average loss: 2.9635 Iteration: 2437; Percent complete: 60.9%; Average loss: 3.1432 Iteration: 2438; Percent complete: 61.0%; Average loss: 2.8078 Iteration: 2439; Percent complete: 61.0%; Average loss: 2.8879 Iteration: 2440; Percent complete: 61.0%; Average loss: 2.8880 Iteration: 2441; Percent complete: 61.0%; Average loss: 2.8697 Iteration: 2442; Percent complete: 61.1%; Average loss: 2.9377 Iteration: 2443; Percent complete: 61.1%; Average loss: 2.9938 Iteration: 2444; Percent complete: 61.1%; Average loss: 3.0607 Iteration: 2445; Percent complete: 61.1%; Average loss: 2.8979 Iteration: 2446; Percent complete: 61.2%; Average loss: 3.0755 Iteration: 2447; Percent complete: 61.2%; Average loss: 3.0194 Iteration: 2448; Percent complete: 61.2%; Average loss: 2.8316 Iteration: 2449; Percent complete: 61.2%; Average loss: 2.8150 Iteration: 2450; Percent complete: 61.3%; Average loss: 2.9788 Iteration: 2451; Percent complete: 61.3%; Average loss: 2.8770 Iteration: 2452; Percent complete: 61.3%; Average loss: 2.9984 Iteration: 2453; Percent complete: 61.3%; Average loss: 3.0891 Iteration: 2454; Percent complete: 61.4%; Average loss: 3.2077 Iteration: 2455; Percent complete: 61.4%; Average loss: 2.9969 Iteration: 2456; Percent complete: 61.4%; Average loss: 2.9951 Iteration: 2457; Percent complete: 61.4%; Average loss: 3.0445 Iteration: 2458; Percent complete: 61.5%; Average loss: 3.2225 Iteration: 2459; Percent complete: 61.5%; Average loss: 3.1977 Iteration: 2460; Percent complete: 61.5%; Average loss: 3.0972 Iteration: 2461; Percent complete: 61.5%; Average loss: 3.0707 Iteration: 2462; Percent complete: 61.6%; Average loss: 2.9228 Iteration: 2463; Percent complete: 61.6%; Average loss: 2.9764 Iteration: 2464; Percent complete: 61.6%; Average loss: 2.8566 Iteration: 2465; Percent complete: 61.6%; Average loss: 2.9622 Iteration: 2466; Percent complete: 61.7%; Average loss: 3.1637 Iteration: 2467; Percent complete: 61.7%; Average loss: 2.7864 Iteration: 2468; Percent complete: 61.7%; Average loss: 2.9329 Iteration: 2469; Percent complete: 61.7%; Average loss: 2.9633 Iteration: 2470; Percent complete: 61.8%; Average loss: 2.8461 Iteration: 2471; Percent complete: 61.8%; Average loss: 3.1908 Iteration: 2472; Percent complete: 61.8%; Average loss: 2.9507 Iteration: 2473; Percent complete: 61.8%; Average loss: 3.2058 Iteration: 2474; Percent complete: 61.9%; Average loss: 3.0392 Iteration: 2475; Percent complete: 61.9%; Average loss: 2.8038 Iteration: 2476; Percent complete: 61.9%; Average loss: 3.3357 Iteration: 2477; Percent complete: 61.9%; Average loss: 2.7371 Iteration: 2478; Percent complete: 62.0%; Average loss: 3.0883 Iteration: 2479; Percent complete: 62.0%; Average loss: 3.2906 Iteration: 2480; Percent complete: 62.0%; Average loss: 3.0799 Iteration: 2481; Percent complete: 62.0%; Average loss: 3.2883 Iteration: 2482; Percent complete: 62.1%; Average loss: 3.1772 Iteration: 2483; Percent complete: 62.1%; Average loss: 2.9369 Iteration: 2484; Percent complete: 62.1%; Average loss: 3.0250 Iteration: 2485; Percent complete: 62.1%; Average loss: 3.0485 Iteration: 2486; Percent complete: 62.2%; Average loss: 2.9617 Iteration: 2487; Percent complete: 62.2%; Average loss: 3.1313 Iteration: 2488; Percent complete: 62.2%; Average loss: 2.7583 Iteration: 2489; Percent complete: 62.2%; Average loss: 2.9449 Iteration: 2490; Percent complete: 62.3%; Average loss: 3.0297 Iteration: 2491; Percent complete: 62.3%; Average loss: 3.0629 Iteration: 2492; Percent complete: 62.3%; Average loss: 3.1535 Iteration: 2493; Percent complete: 62.3%; Average loss: 2.9892 Iteration: 2494; Percent complete: 62.4%; Average loss: 3.3946 Iteration: 2495; Percent complete: 62.4%; Average loss: 3.2047 Iteration: 2496; Percent complete: 62.4%; Average loss: 2.9783 Iteration: 2497; Percent complete: 62.4%; Average loss: 3.1134 Iteration: 2498; Percent complete: 62.5%; Average loss: 2.9570 Iteration: 2499; Percent complete: 62.5%; Average loss: 3.0620 Iteration: 2500; Percent complete: 62.5%; Average loss: 3.1146 Iteration: 2501; Percent complete: 62.5%; Average loss: 2.9250 Iteration: 2502; Percent complete: 62.5%; Average loss: 2.9992 Iteration: 2503; Percent complete: 62.6%; Average loss: 3.0986 Iteration: 2504; Percent complete: 62.6%; Average loss: 2.9101 Iteration: 2505; Percent complete: 62.6%; Average loss: 3.0783 Iteration: 2506; Percent complete: 62.6%; Average loss: 2.9315 Iteration: 2507; Percent complete: 62.7%; Average loss: 3.1201 Iteration: 2508; Percent complete: 62.7%; Average loss: 3.0437 Iteration: 2509; Percent complete: 62.7%; Average loss: 2.8964 Iteration: 2510; Percent complete: 62.7%; Average loss: 2.8975 Iteration: 2511; Percent complete: 62.8%; Average loss: 2.8955 Iteration: 2512; Percent complete: 62.8%; Average loss: 3.0504 Iteration: 2513; Percent complete: 62.8%; Average loss: 3.1182 Iteration: 2514; Percent complete: 62.8%; Average loss: 2.8083 Iteration: 2515; Percent complete: 62.9%; Average loss: 2.8548 Iteration: 2516; Percent complete: 62.9%; Average loss: 3.0094 Iteration: 2517; Percent complete: 62.9%; Average loss: 3.2335 Iteration: 2518; Percent complete: 62.9%; Average loss: 2.9452 Iteration: 2519; Percent complete: 63.0%; Average loss: 3.2650 Iteration: 2520; Percent complete: 63.0%; Average loss: 2.7587 Iteration: 2521; Percent complete: 63.0%; Average loss: 3.1644 Iteration: 2522; Percent complete: 63.0%; Average loss: 2.9131 Iteration: 2523; Percent complete: 63.1%; Average loss: 3.0869 Iteration: 2524; Percent complete: 63.1%; Average loss: 2.8780 Iteration: 2525; Percent complete: 63.1%; Average loss: 3.0629 Iteration: 2526; Percent complete: 63.1%; Average loss: 2.9245 Iteration: 2527; Percent complete: 63.2%; Average loss: 3.2116 Iteration: 2528; Percent complete: 63.2%; Average loss: 2.9157 Iteration: 2529; Percent complete: 63.2%; Average loss: 3.0659 Iteration: 2530; Percent complete: 63.2%; Average loss: 3.1319 Iteration: 2531; Percent complete: 63.3%; Average loss: 2.9887 Iteration: 2532; Percent complete: 63.3%; Average loss: 2.9735 Iteration: 2533; Percent complete: 63.3%; Average loss: 3.1593 Iteration: 2534; Percent complete: 63.3%; Average loss: 2.8837 Iteration: 2535; Percent complete: 63.4%; Average loss: 3.1090 Iteration: 2536; Percent complete: 63.4%; Average loss: 3.0141 Iteration: 2537; Percent complete: 63.4%; Average loss: 2.7488 Iteration: 2538; Percent complete: 63.4%; Average loss: 3.1394 Iteration: 2539; Percent complete: 63.5%; Average loss: 3.1971 Iteration: 2540; Percent complete: 63.5%; Average loss: 3.0522 Iteration: 2541; Percent complete: 63.5%; Average loss: 3.0760 Iteration: 2542; Percent complete: 63.5%; Average loss: 2.9533 Iteration: 2543; Percent complete: 63.6%; Average loss: 3.1255 Iteration: 2544; Percent complete: 63.6%; Average loss: 2.9635 Iteration: 2545; Percent complete: 63.6%; Average loss: 3.0568 Iteration: 2546; Percent complete: 63.6%; Average loss: 2.8300 Iteration: 2547; Percent complete: 63.7%; Average loss: 3.1488 Iteration: 2548; Percent complete: 63.7%; Average loss: 3.3210 Iteration: 2549; Percent complete: 63.7%; Average loss: 3.0972 Iteration: 2550; Percent complete: 63.7%; Average loss: 2.7379 Iteration: 2551; Percent complete: 63.8%; Average loss: 2.8499 Iteration: 2552; Percent complete: 63.8%; Average loss: 2.7978 Iteration: 2553; Percent complete: 63.8%; Average loss: 2.9639 Iteration: 2554; Percent complete: 63.8%; Average loss: 2.9213 Iteration: 2555; Percent complete: 63.9%; Average loss: 3.1152 Iteration: 2556; Percent complete: 63.9%; Average loss: 3.0673 Iteration: 2557; Percent complete: 63.9%; Average loss: 3.0902 Iteration: 2558; Percent complete: 63.9%; Average loss: 3.0133 Iteration: 2559; Percent complete: 64.0%; Average loss: 2.9550 Iteration: 2560; Percent complete: 64.0%; Average loss: 2.9594 Iteration: 2561; Percent complete: 64.0%; Average loss: 3.0293 Iteration: 2562; Percent complete: 64.0%; Average loss: 3.1464 Iteration: 2563; Percent complete: 64.1%; Average loss: 2.8881 Iteration: 2564; Percent complete: 64.1%; Average loss: 3.0484 Iteration: 2565; Percent complete: 64.1%; Average loss: 2.9312 Iteration: 2566; Percent complete: 64.1%; Average loss: 2.8531 Iteration: 2567; Percent complete: 64.2%; Average loss: 3.0559 Iteration: 2568; Percent complete: 64.2%; Average loss: 3.1100 Iteration: 2569; Percent complete: 64.2%; Average loss: 3.0419 Iteration: 2570; Percent complete: 64.2%; Average loss: 3.0740 Iteration: 2571; Percent complete: 64.3%; Average loss: 2.9646 Iteration: 2572; Percent complete: 64.3%; Average loss: 3.0419 Iteration: 2573; Percent complete: 64.3%; Average loss: 2.9262 Iteration: 2574; Percent complete: 64.3%; Average loss: 3.0376 Iteration: 2575; Percent complete: 64.4%; Average loss: 2.8689 Iteration: 2576; Percent complete: 64.4%; Average loss: 2.8755 Iteration: 2577; Percent complete: 64.4%; Average loss: 2.8421 Iteration: 2578; Percent complete: 64.5%; Average loss: 2.9200 Iteration: 2579; Percent complete: 64.5%; Average loss: 2.9726 Iteration: 2580; Percent complete: 64.5%; Average loss: 3.1085 Iteration: 2581; Percent complete: 64.5%; Average loss: 3.0842 Iteration: 2582; Percent complete: 64.5%; Average loss: 3.0097 Iteration: 2583; Percent complete: 64.6%; Average loss: 2.9718 Iteration: 2584; Percent complete: 64.6%; Average loss: 3.0146 Iteration: 2585; Percent complete: 64.6%; Average loss: 2.9782 Iteration: 2586; Percent complete: 64.6%; Average loss: 3.0159 Iteration: 2587; Percent complete: 64.7%; Average loss: 3.2278 Iteration: 2588; Percent complete: 64.7%; Average loss: 3.0316 Iteration: 2589; Percent complete: 64.7%; Average loss: 2.7904 Iteration: 2590; Percent complete: 64.8%; Average loss: 3.0489 Iteration: 2591; Percent complete: 64.8%; Average loss: 3.1692 Iteration: 2592; Percent complete: 64.8%; Average loss: 3.0924 Iteration: 2593; Percent complete: 64.8%; Average loss: 2.9901 Iteration: 2594; Percent complete: 64.8%; Average loss: 3.1880 Iteration: 2595; Percent complete: 64.9%; Average loss: 3.0427 Iteration: 2596; Percent complete: 64.9%; Average loss: 2.9152 Iteration: 2597; Percent complete: 64.9%; Average loss: 3.0160 Iteration: 2598; Percent complete: 65.0%; Average loss: 2.8660 Iteration: 2599; Percent complete: 65.0%; Average loss: 2.9540 Iteration: 2600; Percent complete: 65.0%; Average loss: 3.1155 Iteration: 2601; Percent complete: 65.0%; Average loss: 2.7858 Iteration: 2602; Percent complete: 65.0%; Average loss: 2.7531 Iteration: 2603; Percent complete: 65.1%; Average loss: 2.6747 Iteration: 2604; Percent complete: 65.1%; Average loss: 2.9158 Iteration: 2605; Percent complete: 65.1%; Average loss: 3.0294 Iteration: 2606; Percent complete: 65.1%; Average loss: 2.8659 Iteration: 2607; Percent complete: 65.2%; Average loss: 2.9980 Iteration: 2608; Percent complete: 65.2%; Average loss: 3.0357 Iteration: 2609; Percent complete: 65.2%; Average loss: 2.9570 Iteration: 2610; Percent complete: 65.2%; Average loss: 2.9752 Iteration: 2611; Percent complete: 65.3%; Average loss: 2.9969 Iteration: 2612; Percent complete: 65.3%; Average loss: 3.2120 Iteration: 2613; Percent complete: 65.3%; Average loss: 2.9238 Iteration: 2614; Percent complete: 65.3%; Average loss: 2.9322 Iteration: 2615; Percent complete: 65.4%; Average loss: 2.9886 Iteration: 2616; Percent complete: 65.4%; Average loss: 2.9466 Iteration: 2617; Percent complete: 65.4%; Average loss: 2.9858 Iteration: 2618; Percent complete: 65.5%; Average loss: 3.0451 Iteration: 2619; Percent complete: 65.5%; Average loss: 2.9521 Iteration: 2620; Percent complete: 65.5%; Average loss: 3.2242 Iteration: 2621; Percent complete: 65.5%; Average loss: 2.8692 Iteration: 2622; Percent complete: 65.5%; Average loss: 2.8062 Iteration: 2623; Percent complete: 65.6%; Average loss: 2.9348 Iteration: 2624; Percent complete: 65.6%; Average loss: 2.8612 Iteration: 2625; Percent complete: 65.6%; Average loss: 3.0593 Iteration: 2626; Percent complete: 65.6%; Average loss: 2.9806 Iteration: 2627; Percent complete: 65.7%; Average loss: 2.9712 Iteration: 2628; Percent complete: 65.7%; Average loss: 3.0113 Iteration: 2629; Percent complete: 65.7%; Average loss: 2.7373 Iteration: 2630; Percent complete: 65.8%; Average loss: 2.9619 Iteration: 2631; Percent complete: 65.8%; Average loss: 3.2055 Iteration: 2632; Percent complete: 65.8%; Average loss: 2.8622 Iteration: 2633; Percent complete: 65.8%; Average loss: 2.9695 Iteration: 2634; Percent complete: 65.8%; Average loss: 2.9234 Iteration: 2635; Percent complete: 65.9%; Average loss: 3.1051 Iteration: 2636; Percent complete: 65.9%; Average loss: 2.8558 Iteration: 2637; Percent complete: 65.9%; Average loss: 2.9527 Iteration: 2638; Percent complete: 66.0%; Average loss: 2.8019 Iteration: 2639; Percent complete: 66.0%; Average loss: 2.8330 Iteration: 2640; Percent complete: 66.0%; Average loss: 2.8716 Iteration: 2641; Percent complete: 66.0%; Average loss: 2.9125 Iteration: 2642; Percent complete: 66.0%; Average loss: 3.0816 Iteration: 2643; Percent complete: 66.1%; Average loss: 3.0544 Iteration: 2644; Percent complete: 66.1%; Average loss: 2.8857 Iteration: 2645; Percent complete: 66.1%; Average loss: 3.0679 Iteration: 2646; Percent complete: 66.1%; Average loss: 3.3293 Iteration: 2647; Percent complete: 66.2%; Average loss: 2.9652 Iteration: 2648; Percent complete: 66.2%; Average loss: 2.8954 Iteration: 2649; Percent complete: 66.2%; Average loss: 2.8712 Iteration: 2650; Percent complete: 66.2%; Average loss: 2.8401 Iteration: 2651; Percent complete: 66.3%; Average loss: 2.9045 Iteration: 2652; Percent complete: 66.3%; Average loss: 3.0938 Iteration: 2653; Percent complete: 66.3%; Average loss: 2.9098 Iteration: 2654; Percent complete: 66.3%; Average loss: 2.7088 Iteration: 2655; Percent complete: 66.4%; Average loss: 2.9374 Iteration: 2656; Percent complete: 66.4%; Average loss: 3.1646 Iteration: 2657; Percent complete: 66.4%; Average loss: 2.8668 Iteration: 2658; Percent complete: 66.5%; Average loss: 2.7656 Iteration: 2659; Percent complete: 66.5%; Average loss: 3.2328 Iteration: 2660; Percent complete: 66.5%; Average loss: 3.0251 Iteration: 2661; Percent complete: 66.5%; Average loss: 2.9928 Iteration: 2662; Percent complete: 66.5%; Average loss: 2.8460 Iteration: 2663; Percent complete: 66.6%; Average loss: 3.2613 Iteration: 2664; Percent complete: 66.6%; Average loss: 2.9308 Iteration: 2665; Percent complete: 66.6%; Average loss: 3.0504 Iteration: 2666; Percent complete: 66.6%; Average loss: 2.8435 Iteration: 2667; Percent complete: 66.7%; Average loss: 3.0076 Iteration: 2668; Percent complete: 66.7%; Average loss: 2.9069 Iteration: 2669; Percent complete: 66.7%; Average loss: 3.1698 Iteration: 2670; Percent complete: 66.8%; Average loss: 3.1505 Iteration: 2671; Percent complete: 66.8%; Average loss: 2.9058 Iteration: 2672; Percent complete: 66.8%; Average loss: 3.0981 Iteration: 2673; Percent complete: 66.8%; Average loss: 3.1156 Iteration: 2674; Percent complete: 66.8%; Average loss: 2.8263 Iteration: 2675; Percent complete: 66.9%; Average loss: 2.9627 Iteration: 2676; Percent complete: 66.9%; Average loss: 2.9352 Iteration: 2677; Percent complete: 66.9%; Average loss: 2.9258 Iteration: 2678; Percent complete: 67.0%; Average loss: 2.9149 Iteration: 2679; Percent complete: 67.0%; Average loss: 2.7973 Iteration: 2680; Percent complete: 67.0%; Average loss: 3.0766 Iteration: 2681; Percent complete: 67.0%; Average loss: 2.7609 Iteration: 2682; Percent complete: 67.0%; Average loss: 2.9654 Iteration: 2683; Percent complete: 67.1%; Average loss: 2.8781 Iteration: 2684; Percent complete: 67.1%; Average loss: 2.9246 Iteration: 2685; Percent complete: 67.1%; Average loss: 2.8440 Iteration: 2686; Percent complete: 67.2%; Average loss: 2.8951 Iteration: 2687; Percent complete: 67.2%; Average loss: 3.0603 Iteration: 2688; Percent complete: 67.2%; Average loss: 2.8689 Iteration: 2689; Percent complete: 67.2%; Average loss: 2.8604 Iteration: 2690; Percent complete: 67.2%; Average loss: 3.0475 Iteration: 2691; Percent complete: 67.3%; Average loss: 2.7013 Iteration: 2692; Percent complete: 67.3%; Average loss: 3.0582 Iteration: 2693; Percent complete: 67.3%; Average loss: 3.3412 Iteration: 2694; Percent complete: 67.3%; Average loss: 3.0789 Iteration: 2695; Percent complete: 67.4%; Average loss: 3.0815 Iteration: 2696; Percent complete: 67.4%; Average loss: 2.8957 Iteration: 2697; Percent complete: 67.4%; Average loss: 2.9346 Iteration: 2698; Percent complete: 67.5%; Average loss: 3.1164 Iteration: 2699; Percent complete: 67.5%; Average loss: 2.7369 Iteration: 2700; Percent complete: 67.5%; Average loss: 2.8962 Iteration: 2701; Percent complete: 67.5%; Average loss: 3.0448 Iteration: 2702; Percent complete: 67.5%; Average loss: 2.8527 Iteration: 2703; Percent complete: 67.6%; Average loss: 2.8255 Iteration: 2704; Percent complete: 67.6%; Average loss: 3.2980 Iteration: 2705; Percent complete: 67.6%; Average loss: 2.7549 Iteration: 2706; Percent complete: 67.7%; Average loss: 2.7777 Iteration: 2707; Percent complete: 67.7%; Average loss: 2.7427 Iteration: 2708; Percent complete: 67.7%; Average loss: 2.9312 Iteration: 2709; Percent complete: 67.7%; Average loss: 3.1434 Iteration: 2710; Percent complete: 67.8%; Average loss: 2.9104 Iteration: 2711; Percent complete: 67.8%; Average loss: 2.9743 Iteration: 2712; Percent complete: 67.8%; Average loss: 3.0661 Iteration: 2713; Percent complete: 67.8%; Average loss: 3.0371 Iteration: 2714; Percent complete: 67.8%; Average loss: 3.0686 Iteration: 2715; Percent complete: 67.9%; Average loss: 3.0135 Iteration: 2716; Percent complete: 67.9%; Average loss: 2.8945 Iteration: 2717; Percent complete: 67.9%; Average loss: 2.6755 Iteration: 2718; Percent complete: 68.0%; Average loss: 2.7947 Iteration: 2719; Percent complete: 68.0%; Average loss: 2.8932 Iteration: 2720; Percent complete: 68.0%; Average loss: 2.8895 Iteration: 2721; Percent complete: 68.0%; Average loss: 2.9466 Iteration: 2722; Percent complete: 68.0%; Average loss: 2.9643 Iteration: 2723; Percent complete: 68.1%; Average loss: 3.1052 Iteration: 2724; Percent complete: 68.1%; Average loss: 3.0719 Iteration: 2725; Percent complete: 68.1%; Average loss: 3.1570 Iteration: 2726; Percent complete: 68.2%; Average loss: 2.7766 Iteration: 2727; Percent complete: 68.2%; Average loss: 3.1077 Iteration: 2728; Percent complete: 68.2%; Average loss: 2.8224 Iteration: 2729; Percent complete: 68.2%; Average loss: 2.7998 Iteration: 2730; Percent complete: 68.2%; Average loss: 3.0373 Iteration: 2731; Percent complete: 68.3%; Average loss: 2.8941 Iteration: 2732; Percent complete: 68.3%; Average loss: 3.1043 Iteration: 2733; Percent complete: 68.3%; Average loss: 2.9309 Iteration: 2734; Percent complete: 68.3%; Average loss: 3.1356 Iteration: 2735; Percent complete: 68.4%; Average loss: 2.8281 Iteration: 2736; Percent complete: 68.4%; Average loss: 3.0699 Iteration: 2737; Percent complete: 68.4%; Average loss: 2.9093 Iteration: 2738; Percent complete: 68.5%; Average loss: 2.8947 Iteration: 2739; Percent complete: 68.5%; Average loss: 2.9510 Iteration: 2740; Percent complete: 68.5%; Average loss: 3.0641 Iteration: 2741; Percent complete: 68.5%; Average loss: 2.6815 Iteration: 2742; Percent complete: 68.5%; Average loss: 3.1404 Iteration: 2743; Percent complete: 68.6%; Average loss: 2.8262 Iteration: 2744; Percent complete: 68.6%; Average loss: 3.0630 Iteration: 2745; Percent complete: 68.6%; Average loss: 3.1901 Iteration: 2746; Percent complete: 68.7%; Average loss: 2.7947 Iteration: 2747; Percent complete: 68.7%; Average loss: 2.6146 Iteration: 2748; Percent complete: 68.7%; Average loss: 2.6632 Iteration: 2749; Percent complete: 68.7%; Average loss: 2.9547 Iteration: 2750; Percent complete: 68.8%; Average loss: 2.9155 Iteration: 2751; Percent complete: 68.8%; Average loss: 2.8673 Iteration: 2752; Percent complete: 68.8%; Average loss: 3.0056 Iteration: 2753; Percent complete: 68.8%; Average loss: 2.9271 Iteration: 2754; Percent complete: 68.8%; Average loss: 2.8739 Iteration: 2755; Percent complete: 68.9%; Average loss: 3.1382 Iteration: 2756; Percent complete: 68.9%; Average loss: 2.8126 Iteration: 2757; Percent complete: 68.9%; Average loss: 3.0221 Iteration: 2758; Percent complete: 69.0%; Average loss: 3.2198 Iteration: 2759; Percent complete: 69.0%; Average loss: 2.7688 Iteration: 2760; Percent complete: 69.0%; Average loss: 2.9101 Iteration: 2761; Percent complete: 69.0%; Average loss: 2.9292 Iteration: 2762; Percent complete: 69.0%; Average loss: 2.8109 Iteration: 2763; Percent complete: 69.1%; Average loss: 2.9545 Iteration: 2764; Percent complete: 69.1%; Average loss: 2.9192 Iteration: 2765; Percent complete: 69.1%; Average loss: 2.8895 Iteration: 2766; Percent complete: 69.2%; Average loss: 3.0225 Iteration: 2767; Percent complete: 69.2%; Average loss: 2.9308 Iteration: 2768; Percent complete: 69.2%; Average loss: 2.8284 Iteration: 2769; Percent complete: 69.2%; Average loss: 3.1988 Iteration: 2770; Percent complete: 69.2%; Average loss: 3.0126 Iteration: 2771; Percent complete: 69.3%; Average loss: 2.9437 Iteration: 2772; Percent complete: 69.3%; Average loss: 3.0478 Iteration: 2773; Percent complete: 69.3%; Average loss: 2.7585 Iteration: 2774; Percent complete: 69.3%; Average loss: 3.0595 Iteration: 2775; Percent complete: 69.4%; Average loss: 2.8397 Iteration: 2776; Percent complete: 69.4%; Average loss: 3.0137 Iteration: 2777; Percent complete: 69.4%; Average loss: 3.2597 Iteration: 2778; Percent complete: 69.5%; Average loss: 2.8684 Iteration: 2779; Percent complete: 69.5%; Average loss: 2.9990 Iteration: 2780; Percent complete: 69.5%; Average loss: 3.0643 Iteration: 2781; Percent complete: 69.5%; Average loss: 2.8879 Iteration: 2782; Percent complete: 69.5%; Average loss: 3.0612 Iteration: 2783; Percent complete: 69.6%; Average loss: 2.8988 Iteration: 2784; Percent complete: 69.6%; Average loss: 2.6450 Iteration: 2785; Percent complete: 69.6%; Average loss: 2.9163 Iteration: 2786; Percent complete: 69.7%; Average loss: 3.0658 Iteration: 2787; Percent complete: 69.7%; Average loss: 3.0169 Iteration: 2788; Percent complete: 69.7%; Average loss: 2.8609 Iteration: 2789; Percent complete: 69.7%; Average loss: 2.9718 Iteration: 2790; Percent complete: 69.8%; Average loss: 2.9413 Iteration: 2791; Percent complete: 69.8%; Average loss: 2.9809 Iteration: 2792; Percent complete: 69.8%; Average loss: 3.0567 Iteration: 2793; Percent complete: 69.8%; Average loss: 2.9318 Iteration: 2794; Percent complete: 69.8%; Average loss: 2.9730 Iteration: 2795; Percent complete: 69.9%; Average loss: 2.8751 Iteration: 2796; Percent complete: 69.9%; Average loss: 2.9379 Iteration: 2797; Percent complete: 69.9%; Average loss: 3.1825 Iteration: 2798; Percent complete: 70.0%; Average loss: 2.7833 Iteration: 2799; Percent complete: 70.0%; Average loss: 3.0531 Iteration: 2800; Percent complete: 70.0%; Average loss: 3.1108 Iteration: 2801; Percent complete: 70.0%; Average loss: 2.9743 Iteration: 2802; Percent complete: 70.0%; Average loss: 2.9520 Iteration: 2803; Percent complete: 70.1%; Average loss: 2.8053 Iteration: 2804; Percent complete: 70.1%; Average loss: 2.7220 Iteration: 2805; Percent complete: 70.1%; Average loss: 2.8060 Iteration: 2806; Percent complete: 70.2%; Average loss: 2.9875 Iteration: 2807; Percent complete: 70.2%; Average loss: 2.9351 Iteration: 2808; Percent complete: 70.2%; Average loss: 3.0858 Iteration: 2809; Percent complete: 70.2%; Average loss: 2.8735 Iteration: 2810; Percent complete: 70.2%; Average loss: 2.7674 Iteration: 2811; Percent complete: 70.3%; Average loss: 3.2374 Iteration: 2812; Percent complete: 70.3%; Average loss: 2.6323 Iteration: 2813; Percent complete: 70.3%; Average loss: 2.7799 Iteration: 2814; Percent complete: 70.3%; Average loss: 2.8485 Iteration: 2815; Percent complete: 70.4%; Average loss: 2.9964 Iteration: 2816; Percent complete: 70.4%; Average loss: 2.9729 Iteration: 2817; Percent complete: 70.4%; Average loss: 3.0811 Iteration: 2818; Percent complete: 70.5%; Average loss: 2.9527 Iteration: 2819; Percent complete: 70.5%; Average loss: 2.8169 Iteration: 2820; Percent complete: 70.5%; Average loss: 2.9205 Iteration: 2821; Percent complete: 70.5%; Average loss: 2.7928 Iteration: 2822; Percent complete: 70.5%; Average loss: 2.9551 Iteration: 2823; Percent complete: 70.6%; Average loss: 3.0601 Iteration: 2824; Percent complete: 70.6%; Average loss: 3.0469 Iteration: 2825; Percent complete: 70.6%; Average loss: 2.7225 Iteration: 2826; Percent complete: 70.7%; Average loss: 2.9559 Iteration: 2827; Percent complete: 70.7%; Average loss: 2.7962 Iteration: 2828; Percent complete: 70.7%; Average loss: 2.8479 Iteration: 2829; Percent complete: 70.7%; Average loss: 2.7867 Iteration: 2830; Percent complete: 70.8%; Average loss: 2.7810 Iteration: 2831; Percent complete: 70.8%; Average loss: 2.6793 Iteration: 2832; Percent complete: 70.8%; Average loss: 2.6110 Iteration: 2833; Percent complete: 70.8%; Average loss: 2.9886 Iteration: 2834; Percent complete: 70.9%; Average loss: 2.9781 Iteration: 2835; Percent complete: 70.9%; Average loss: 2.8387 Iteration: 2836; Percent complete: 70.9%; Average loss: 3.1029 Iteration: 2837; Percent complete: 70.9%; Average loss: 2.7861 Iteration: 2838; Percent complete: 71.0%; Average loss: 2.7411 Iteration: 2839; Percent complete: 71.0%; Average loss: 2.8820 Iteration: 2840; Percent complete: 71.0%; Average loss: 2.8688 Iteration: 2841; Percent complete: 71.0%; Average loss: 2.8614 Iteration: 2842; Percent complete: 71.0%; Average loss: 2.8331 Iteration: 2843; Percent complete: 71.1%; Average loss: 2.9088 Iteration: 2844; Percent complete: 71.1%; Average loss: 3.1663 Iteration: 2845; Percent complete: 71.1%; Average loss: 2.9079 Iteration: 2846; Percent complete: 71.2%; Average loss: 2.9131 Iteration: 2847; Percent complete: 71.2%; Average loss: 3.0382 Iteration: 2848; Percent complete: 71.2%; Average loss: 3.3103 Iteration: 2849; Percent complete: 71.2%; Average loss: 3.0905 Iteration: 2850; Percent complete: 71.2%; Average loss: 2.8652 Iteration: 2851; Percent complete: 71.3%; Average loss: 3.1070 Iteration: 2852; Percent complete: 71.3%; Average loss: 2.8627 Iteration: 2853; Percent complete: 71.3%; Average loss: 2.9911 Iteration: 2854; Percent complete: 71.4%; Average loss: 2.9712 Iteration: 2855; Percent complete: 71.4%; Average loss: 2.8979 Iteration: 2856; Percent complete: 71.4%; Average loss: 2.7016 Iteration: 2857; Percent complete: 71.4%; Average loss: 3.1126 Iteration: 2858; Percent complete: 71.5%; Average loss: 2.9222 Iteration: 2859; Percent complete: 71.5%; Average loss: 3.1138 Iteration: 2860; Percent complete: 71.5%; Average loss: 3.0079 Iteration: 2861; Percent complete: 71.5%; Average loss: 2.8253 Iteration: 2862; Percent complete: 71.5%; Average loss: 2.9950 Iteration: 2863; Percent complete: 71.6%; Average loss: 2.6510 Iteration: 2864; Percent complete: 71.6%; Average loss: 2.9798 Iteration: 2865; Percent complete: 71.6%; Average loss: 2.9327 Iteration: 2866; Percent complete: 71.7%; Average loss: 3.1896 Iteration: 2867; Percent complete: 71.7%; Average loss: 2.6548 Iteration: 2868; Percent complete: 71.7%; Average loss: 3.0053 Iteration: 2869; Percent complete: 71.7%; Average loss: 2.7066 Iteration: 2870; Percent complete: 71.8%; Average loss: 2.8737 Iteration: 2871; Percent complete: 71.8%; Average loss: 2.8449 Iteration: 2872; Percent complete: 71.8%; Average loss: 2.6466 Iteration: 2873; Percent complete: 71.8%; Average loss: 2.9246 Iteration: 2874; Percent complete: 71.9%; Average loss: 2.9757 Iteration: 2875; Percent complete: 71.9%; Average loss: 2.8799 Iteration: 2876; Percent complete: 71.9%; Average loss: 2.9836 Iteration: 2877; Percent complete: 71.9%; Average loss: 2.7711 Iteration: 2878; Percent complete: 72.0%; Average loss: 3.1649 Iteration: 2879; Percent complete: 72.0%; Average loss: 2.9261 Iteration: 2880; Percent complete: 72.0%; Average loss: 3.0311 Iteration: 2881; Percent complete: 72.0%; Average loss: 2.7534 Iteration: 2882; Percent complete: 72.0%; Average loss: 2.8596 Iteration: 2883; Percent complete: 72.1%; Average loss: 2.9214 Iteration: 2884; Percent complete: 72.1%; Average loss: 2.7179 Iteration: 2885; Percent complete: 72.1%; Average loss: 2.9790 Iteration: 2886; Percent complete: 72.2%; Average loss: 3.2031 Iteration: 2887; Percent complete: 72.2%; Average loss: 2.7247 Iteration: 2888; Percent complete: 72.2%; Average loss: 2.6779 Iteration: 2889; Percent complete: 72.2%; Average loss: 3.0260 Iteration: 2890; Percent complete: 72.2%; Average loss: 2.8155 Iteration: 2891; Percent complete: 72.3%; Average loss: 2.9193 Iteration: 2892; Percent complete: 72.3%; Average loss: 2.7993 Iteration: 2893; Percent complete: 72.3%; Average loss: 3.0493 Iteration: 2894; Percent complete: 72.4%; Average loss: 2.9882 Iteration: 2895; Percent complete: 72.4%; Average loss: 3.0542 Iteration: 2896; Percent complete: 72.4%; Average loss: 3.0318 Iteration: 2897; Percent complete: 72.4%; Average loss: 3.0603 Iteration: 2898; Percent complete: 72.5%; Average loss: 2.9083 Iteration: 2899; Percent complete: 72.5%; Average loss: 2.8821 Iteration: 2900; Percent complete: 72.5%; Average loss: 2.6394 Iteration: 2901; Percent complete: 72.5%; Average loss: 2.9563 Iteration: 2902; Percent complete: 72.5%; Average loss: 2.8772 Iteration: 2903; Percent complete: 72.6%; Average loss: 3.0744 Iteration: 2904; Percent complete: 72.6%; Average loss: 2.8555 Iteration: 2905; Percent complete: 72.6%; Average loss: 2.8057 Iteration: 2906; Percent complete: 72.7%; Average loss: 2.8860 Iteration: 2907; Percent complete: 72.7%; Average loss: 2.8756 Iteration: 2908; Percent complete: 72.7%; Average loss: 2.7260 Iteration: 2909; Percent complete: 72.7%; Average loss: 2.9964 Iteration: 2910; Percent complete: 72.8%; Average loss: 3.0194 Iteration: 2911; Percent complete: 72.8%; Average loss: 2.9294 Iteration: 2912; Percent complete: 72.8%; Average loss: 2.7714 Iteration: 2913; Percent complete: 72.8%; Average loss: 3.0106 Iteration: 2914; Percent complete: 72.9%; Average loss: 2.9071 Iteration: 2915; Percent complete: 72.9%; Average loss: 2.9167 Iteration: 2916; Percent complete: 72.9%; Average loss: 2.7747 Iteration: 2917; Percent complete: 72.9%; Average loss: 2.7075 Iteration: 2918; Percent complete: 73.0%; Average loss: 2.8588 Iteration: 2919; Percent complete: 73.0%; Average loss: 2.9034 Iteration: 2920; Percent complete: 73.0%; Average loss: 2.9105 Iteration: 2921; Percent complete: 73.0%; Average loss: 2.6998 Iteration: 2922; Percent complete: 73.0%; Average loss: 2.6112 Iteration: 2923; Percent complete: 73.1%; Average loss: 3.0574 Iteration: 2924; Percent complete: 73.1%; Average loss: 2.8712 Iteration: 2925; Percent complete: 73.1%; Average loss: 3.0870 Iteration: 2926; Percent complete: 73.2%; Average loss: 2.9632 Iteration: 2927; Percent complete: 73.2%; Average loss: 2.9527 Iteration: 2928; Percent complete: 73.2%; Average loss: 2.9880 Iteration: 2929; Percent complete: 73.2%; Average loss: 2.9034 Iteration: 2930; Percent complete: 73.2%; Average loss: 2.7490 Iteration: 2931; Percent complete: 73.3%; Average loss: 2.9261 Iteration: 2932; Percent complete: 73.3%; Average loss: 2.7053 Iteration: 2933; Percent complete: 73.3%; Average loss: 2.7947 Iteration: 2934; Percent complete: 73.4%; Average loss: 2.9404 Iteration: 2935; Percent complete: 73.4%; Average loss: 2.9599 Iteration: 2936; Percent complete: 73.4%; Average loss: 2.7999 Iteration: 2937; Percent complete: 73.4%; Average loss: 2.8021 Iteration: 2938; Percent complete: 73.5%; Average loss: 2.9160 Iteration: 2939; Percent complete: 73.5%; Average loss: 2.9433 Iteration: 2940; Percent complete: 73.5%; Average loss: 2.8256 Iteration: 2941; Percent complete: 73.5%; Average loss: 2.7776 Iteration: 2942; Percent complete: 73.6%; Average loss: 2.7083 Iteration: 2943; Percent complete: 73.6%; Average loss: 2.9078 Iteration: 2944; Percent complete: 73.6%; Average loss: 2.8112 Iteration: 2945; Percent complete: 73.6%; Average loss: 2.6741 Iteration: 2946; Percent complete: 73.7%; Average loss: 2.8937 Iteration: 2947; Percent complete: 73.7%; Average loss: 2.8719 Iteration: 2948; Percent complete: 73.7%; Average loss: 3.0538 Iteration: 2949; Percent complete: 73.7%; Average loss: 2.8464 Iteration: 2950; Percent complete: 73.8%; Average loss: 2.8333 Iteration: 2951; Percent complete: 73.8%; Average loss: 2.8239 Iteration: 2952; Percent complete: 73.8%; Average loss: 2.9011 Iteration: 2953; Percent complete: 73.8%; Average loss: 2.8617 Iteration: 2954; Percent complete: 73.9%; Average loss: 2.7233 Iteration: 2955; Percent complete: 73.9%; Average loss: 2.8497 Iteration: 2956; Percent complete: 73.9%; Average loss: 2.9532 Iteration: 2957; Percent complete: 73.9%; Average loss: 2.8631 Iteration: 2958; Percent complete: 74.0%; Average loss: 2.7187 Iteration: 2959; Percent complete: 74.0%; Average loss: 2.7775 Iteration: 2960; Percent complete: 74.0%; Average loss: 3.0193 Iteration: 2961; Percent complete: 74.0%; Average loss: 2.7526 Iteration: 2962; Percent complete: 74.1%; Average loss: 2.8415 Iteration: 2963; Percent complete: 74.1%; Average loss: 2.8825 Iteration: 2964; Percent complete: 74.1%; Average loss: 2.8838 Iteration: 2965; Percent complete: 74.1%; Average loss: 2.9200 Iteration: 2966; Percent complete: 74.2%; Average loss: 2.9882 Iteration: 2967; Percent complete: 74.2%; Average loss: 2.9577 Iteration: 2968; Percent complete: 74.2%; Average loss: 2.8805 Iteration: 2969; Percent complete: 74.2%; Average loss: 2.7365 Iteration: 2970; Percent complete: 74.2%; Average loss: 2.7621 Iteration: 2971; Percent complete: 74.3%; Average loss: 2.6986 Iteration: 2972; Percent complete: 74.3%; Average loss: 2.7607 Iteration: 2973; Percent complete: 74.3%; Average loss: 2.7038 Iteration: 2974; Percent complete: 74.4%; Average loss: 2.9121 Iteration: 2975; Percent complete: 74.4%; Average loss: 2.7866 Iteration: 2976; Percent complete: 74.4%; Average loss: 3.0203 Iteration: 2977; Percent complete: 74.4%; Average loss: 2.7698 Iteration: 2978; Percent complete: 74.5%; Average loss: 2.7950 Iteration: 2979; Percent complete: 74.5%; Average loss: 2.9532 Iteration: 2980; Percent complete: 74.5%; Average loss: 2.9360 Iteration: 2981; Percent complete: 74.5%; Average loss: 2.6624 Iteration: 2982; Percent complete: 74.6%; Average loss: 2.9808 Iteration: 2983; Percent complete: 74.6%; Average loss: 2.9869 Iteration: 2984; Percent complete: 74.6%; Average loss: 2.9784 Iteration: 2985; Percent complete: 74.6%; Average loss: 2.7912 Iteration: 2986; Percent complete: 74.7%; Average loss: 2.8613 Iteration: 2987; Percent complete: 74.7%; Average loss: 2.7530 Iteration: 2988; Percent complete: 74.7%; Average loss: 2.7823 Iteration: 2989; Percent complete: 74.7%; Average loss: 2.7746 Iteration: 2990; Percent complete: 74.8%; Average loss: 3.1274 Iteration: 2991; Percent complete: 74.8%; Average loss: 3.0962 Iteration: 2992; Percent complete: 74.8%; Average loss: 2.6728 Iteration: 2993; Percent complete: 74.8%; Average loss: 2.9400 Iteration: 2994; Percent complete: 74.9%; Average loss: 2.9310 Iteration: 2995; Percent complete: 74.9%; Average loss: 2.7889 Iteration: 2996; Percent complete: 74.9%; Average loss: 3.0163 Iteration: 2997; Percent complete: 74.9%; Average loss: 2.8007 Iteration: 2998; Percent complete: 75.0%; Average loss: 2.9177 Iteration: 2999; Percent complete: 75.0%; Average loss: 2.9792 Iteration: 3000; Percent complete: 75.0%; Average loss: 2.8084 Iteration: 3001; Percent complete: 75.0%; Average loss: 3.1195 Iteration: 3002; Percent complete: 75.0%; Average loss: 2.8852 Iteration: 3003; Percent complete: 75.1%; Average loss: 2.8523 Iteration: 3004; Percent complete: 75.1%; Average loss: 2.9273 Iteration: 3005; Percent complete: 75.1%; Average loss: 3.0341 Iteration: 3006; Percent complete: 75.1%; Average loss: 3.1004 Iteration: 3007; Percent complete: 75.2%; Average loss: 2.7801 Iteration: 3008; Percent complete: 75.2%; Average loss: 2.7940 Iteration: 3009; Percent complete: 75.2%; Average loss: 2.9840 Iteration: 3010; Percent complete: 75.2%; Average loss: 2.6465 Iteration: 3011; Percent complete: 75.3%; Average loss: 2.9202 Iteration: 3012; Percent complete: 75.3%; Average loss: 3.0069 Iteration: 3013; Percent complete: 75.3%; Average loss: 2.7846 Iteration: 3014; Percent complete: 75.3%; Average loss: 2.8769 Iteration: 3015; Percent complete: 75.4%; Average loss: 2.9122 Iteration: 3016; Percent complete: 75.4%; Average loss: 2.9252 Iteration: 3017; Percent complete: 75.4%; Average loss: 2.9572 Iteration: 3018; Percent complete: 75.4%; Average loss: 3.1521 Iteration: 3019; Percent complete: 75.5%; Average loss: 2.7108 Iteration: 3020; Percent complete: 75.5%; Average loss: 2.7019 Iteration: 3021; Percent complete: 75.5%; Average loss: 2.9674 Iteration: 3022; Percent complete: 75.5%; Average loss: 2.8107 Iteration: 3023; Percent complete: 75.6%; Average loss: 2.9836 Iteration: 3024; Percent complete: 75.6%; Average loss: 3.0708 Iteration: 3025; Percent complete: 75.6%; Average loss: 2.8371 Iteration: 3026; Percent complete: 75.6%; Average loss: 2.9662 Iteration: 3027; Percent complete: 75.7%; Average loss: 2.9287 Iteration: 3028; Percent complete: 75.7%; Average loss: 2.7730 Iteration: 3029; Percent complete: 75.7%; Average loss: 2.8538 Iteration: 3030; Percent complete: 75.8%; Average loss: 2.7173 Iteration: 3031; Percent complete: 75.8%; Average loss: 2.7624 Iteration: 3032; Percent complete: 75.8%; Average loss: 2.9839 Iteration: 3033; Percent complete: 75.8%; Average loss: 2.7535 Iteration: 3034; Percent complete: 75.8%; Average loss: 2.9550 Iteration: 3035; Percent complete: 75.9%; Average loss: 2.6840 Iteration: 3036; Percent complete: 75.9%; Average loss: 2.6255 Iteration: 3037; Percent complete: 75.9%; Average loss: 2.9777 Iteration: 3038; Percent complete: 75.9%; Average loss: 2.5536 Iteration: 3039; Percent complete: 76.0%; Average loss: 2.9595 Iteration: 3040; Percent complete: 76.0%; Average loss: 2.7319 Iteration: 3041; Percent complete: 76.0%; Average loss: 2.8941 Iteration: 3042; Percent complete: 76.0%; Average loss: 2.7285 Iteration: 3043; Percent complete: 76.1%; Average loss: 2.7806 Iteration: 3044; Percent complete: 76.1%; Average loss: 3.1105 Iteration: 3045; Percent complete: 76.1%; Average loss: 3.0182 Iteration: 3046; Percent complete: 76.1%; Average loss: 3.0777 Iteration: 3047; Percent complete: 76.2%; Average loss: 2.8069 Iteration: 3048; Percent complete: 76.2%; Average loss: 2.5526 Iteration: 3049; Percent complete: 76.2%; Average loss: 3.1003 Iteration: 3050; Percent complete: 76.2%; Average loss: 3.0570 Iteration: 3051; Percent complete: 76.3%; Average loss: 3.1241 Iteration: 3052; Percent complete: 76.3%; Average loss: 2.7884 Iteration: 3053; Percent complete: 76.3%; Average loss: 2.9619 Iteration: 3054; Percent complete: 76.3%; Average loss: 2.8847 Iteration: 3055; Percent complete: 76.4%; Average loss: 2.7627 Iteration: 3056; Percent complete: 76.4%; Average loss: 3.0893 Iteration: 3057; Percent complete: 76.4%; Average loss: 2.9351 Iteration: 3058; Percent complete: 76.4%; Average loss: 2.8549 Iteration: 3059; Percent complete: 76.5%; Average loss: 2.8132 Iteration: 3060; Percent complete: 76.5%; Average loss: 2.6562 Iteration: 3061; Percent complete: 76.5%; Average loss: 3.0449 Iteration: 3062; Percent complete: 76.5%; Average loss: 2.8249 Iteration: 3063; Percent complete: 76.6%; Average loss: 2.8997 Iteration: 3064; Percent complete: 76.6%; Average loss: 2.7898 Iteration: 3065; Percent complete: 76.6%; Average loss: 2.8252 Iteration: 3066; Percent complete: 76.6%; Average loss: 2.8972 Iteration: 3067; Percent complete: 76.7%; Average loss: 2.8495 Iteration: 3068; Percent complete: 76.7%; Average loss: 2.8347 Iteration: 3069; Percent complete: 76.7%; Average loss: 2.7709 Iteration: 3070; Percent complete: 76.8%; Average loss: 2.8590 Iteration: 3071; Percent complete: 76.8%; Average loss: 2.7985 Iteration: 3072; Percent complete: 76.8%; Average loss: 3.0723 Iteration: 3073; Percent complete: 76.8%; Average loss: 2.9717 Iteration: 3074; Percent complete: 76.8%; Average loss: 2.7962 Iteration: 3075; Percent complete: 76.9%; Average loss: 2.9156 Iteration: 3076; Percent complete: 76.9%; Average loss: 2.7797 Iteration: 3077; Percent complete: 76.9%; Average loss: 2.8095 Iteration: 3078; Percent complete: 77.0%; Average loss: 2.9072 Iteration: 3079; Percent complete: 77.0%; Average loss: 2.9742 Iteration: 3080; Percent complete: 77.0%; Average loss: 2.8425 Iteration: 3081; Percent complete: 77.0%; Average loss: 2.9594 Iteration: 3082; Percent complete: 77.0%; Average loss: 2.5834 Iteration: 3083; Percent complete: 77.1%; Average loss: 2.9668 Iteration: 3084; Percent complete: 77.1%; Average loss: 2.9858 Iteration: 3085; Percent complete: 77.1%; Average loss: 2.9059 Iteration: 3086; Percent complete: 77.1%; Average loss: 2.8634 Iteration: 3087; Percent complete: 77.2%; Average loss: 2.8576 Iteration: 3088; Percent complete: 77.2%; Average loss: 2.8791 Iteration: 3089; Percent complete: 77.2%; Average loss: 2.6906 Iteration: 3090; Percent complete: 77.2%; Average loss: 2.8207 Iteration: 3091; Percent complete: 77.3%; Average loss: 2.7964 Iteration: 3092; Percent complete: 77.3%; Average loss: 2.6594 Iteration: 3093; Percent complete: 77.3%; Average loss: 2.9094 Iteration: 3094; Percent complete: 77.3%; Average loss: 2.6527 Iteration: 3095; Percent complete: 77.4%; Average loss: 2.7977 Iteration: 3096; Percent complete: 77.4%; Average loss: 2.7865 Iteration: 3097; Percent complete: 77.4%; Average loss: 2.7671 Iteration: 3098; Percent complete: 77.5%; Average loss: 2.8958 Iteration: 3099; Percent complete: 77.5%; Average loss: 2.6669 Iteration: 3100; Percent complete: 77.5%; Average loss: 2.9882 Iteration: 3101; Percent complete: 77.5%; Average loss: 2.6648 Iteration: 3102; Percent complete: 77.5%; Average loss: 2.7968 Iteration: 3103; Percent complete: 77.6%; Average loss: 2.8021 Iteration: 3104; Percent complete: 77.6%; Average loss: 2.8449 Iteration: 3105; Percent complete: 77.6%; Average loss: 3.0175 Iteration: 3106; Percent complete: 77.6%; Average loss: 3.0847 Iteration: 3107; Percent complete: 77.7%; Average loss: 2.7879 Iteration: 3108; Percent complete: 77.7%; Average loss: 2.7424 Iteration: 3109; Percent complete: 77.7%; Average loss: 3.1044 Iteration: 3110; Percent complete: 77.8%; Average loss: 2.7274 Iteration: 3111; Percent complete: 77.8%; Average loss: 2.7919 Iteration: 3112; Percent complete: 77.8%; Average loss: 3.0667 Iteration: 3113; Percent complete: 77.8%; Average loss: 3.0090 Iteration: 3114; Percent complete: 77.8%; Average loss: 2.8893 Iteration: 3115; Percent complete: 77.9%; Average loss: 2.9459 Iteration: 3116; Percent complete: 77.9%; Average loss: 2.8765 Iteration: 3117; Percent complete: 77.9%; Average loss: 2.9244 Iteration: 3118; Percent complete: 78.0%; Average loss: 2.7831 Iteration: 3119; Percent complete: 78.0%; Average loss: 2.8006 Iteration: 3120; Percent complete: 78.0%; Average loss: 3.1132 Iteration: 3121; Percent complete: 78.0%; Average loss: 2.9093 Iteration: 3122; Percent complete: 78.0%; Average loss: 2.9172 Iteration: 3123; Percent complete: 78.1%; Average loss: 2.6305 Iteration: 3124; Percent complete: 78.1%; Average loss: 2.9937 Iteration: 3125; Percent complete: 78.1%; Average loss: 2.9462 Iteration: 3126; Percent complete: 78.1%; Average loss: 2.9689 Iteration: 3127; Percent complete: 78.2%; Average loss: 2.5974 Iteration: 3128; Percent complete: 78.2%; Average loss: 2.9425 Iteration: 3129; Percent complete: 78.2%; Average loss: 2.7610 Iteration: 3130; Percent complete: 78.2%; Average loss: 2.9803 Iteration: 3131; Percent complete: 78.3%; Average loss: 2.8329 Iteration: 3132; Percent complete: 78.3%; Average loss: 2.7207 Iteration: 3133; Percent complete: 78.3%; Average loss: 2.6801 Iteration: 3134; Percent complete: 78.3%; Average loss: 2.9613 Iteration: 3135; Percent complete: 78.4%; Average loss: 2.7247 Iteration: 3136; Percent complete: 78.4%; Average loss: 2.5690 Iteration: 3137; Percent complete: 78.4%; Average loss: 2.8778 Iteration: 3138; Percent complete: 78.5%; Average loss: 2.9186 Iteration: 3139; Percent complete: 78.5%; Average loss: 2.7980 Iteration: 3140; Percent complete: 78.5%; Average loss: 2.8901 Iteration: 3141; Percent complete: 78.5%; Average loss: 2.6961 Iteration: 3142; Percent complete: 78.5%; Average loss: 2.7142 Iteration: 3143; Percent complete: 78.6%; Average loss: 2.7147 Iteration: 3144; Percent complete: 78.6%; Average loss: 2.9426 Iteration: 3145; Percent complete: 78.6%; Average loss: 2.8646 Iteration: 3146; Percent complete: 78.6%; Average loss: 3.0517 Iteration: 3147; Percent complete: 78.7%; Average loss: 2.8530 Iteration: 3148; Percent complete: 78.7%; Average loss: 2.8700 Iteration: 3149; Percent complete: 78.7%; Average loss: 2.7282 Iteration: 3150; Percent complete: 78.8%; Average loss: 2.8792 Iteration: 3151; Percent complete: 78.8%; Average loss: 2.9027 Iteration: 3152; Percent complete: 78.8%; Average loss: 2.9666 Iteration: 3153; Percent complete: 78.8%; Average loss: 2.8192 Iteration: 3154; Percent complete: 78.8%; Average loss: 3.0086 Iteration: 3155; Percent complete: 78.9%; Average loss: 2.7139 Iteration: 3156; Percent complete: 78.9%; Average loss: 2.7552 Iteration: 3157; Percent complete: 78.9%; Average loss: 3.1187 Iteration: 3158; Percent complete: 79.0%; Average loss: 2.5589 Iteration: 3159; Percent complete: 79.0%; Average loss: 2.9392 Iteration: 3160; Percent complete: 79.0%; Average loss: 2.7345 Iteration: 3161; Percent complete: 79.0%; Average loss: 2.8231 Iteration: 3162; Percent complete: 79.0%; Average loss: 3.2983 Iteration: 3163; Percent complete: 79.1%; Average loss: 2.9044 Iteration: 3164; Percent complete: 79.1%; Average loss: 2.7272 Iteration: 3165; Percent complete: 79.1%; Average loss: 2.7271 Iteration: 3166; Percent complete: 79.1%; Average loss: 2.8992 Iteration: 3167; Percent complete: 79.2%; Average loss: 2.7188 Iteration: 3168; Percent complete: 79.2%; Average loss: 2.5820 Iteration: 3169; Percent complete: 79.2%; Average loss: 2.8076 Iteration: 3170; Percent complete: 79.2%; Average loss: 2.8566 Iteration: 3171; Percent complete: 79.3%; Average loss: 2.8620 Iteration: 3172; Percent complete: 79.3%; Average loss: 2.8054 Iteration: 3173; Percent complete: 79.3%; Average loss: 2.7425 Iteration: 3174; Percent complete: 79.3%; Average loss: 2.5676 Iteration: 3175; Percent complete: 79.4%; Average loss: 2.7794 Iteration: 3176; Percent complete: 79.4%; Average loss: 2.9740 Iteration: 3177; Percent complete: 79.4%; Average loss: 2.8178 Iteration: 3178; Percent complete: 79.5%; Average loss: 2.8901 Iteration: 3179; Percent complete: 79.5%; Average loss: 2.7495 Iteration: 3180; Percent complete: 79.5%; Average loss: 2.9546 Iteration: 3181; Percent complete: 79.5%; Average loss: 2.7088 Iteration: 3182; Percent complete: 79.5%; Average loss: 2.9240 Iteration: 3183; Percent complete: 79.6%; Average loss: 2.9997 Iteration: 3184; Percent complete: 79.6%; Average loss: 2.7208 Iteration: 3185; Percent complete: 79.6%; Average loss: 2.8693 Iteration: 3186; Percent complete: 79.7%; Average loss: 3.0361 Iteration: 3187; Percent complete: 79.7%; Average loss: 2.8959 Iteration: 3188; Percent complete: 79.7%; Average loss: 2.7621 Iteration: 3189; Percent complete: 79.7%; Average loss: 2.9440 Iteration: 3190; Percent complete: 79.8%; Average loss: 2.8994 Iteration: 3191; Percent complete: 79.8%; Average loss: 2.7217 Iteration: 3192; Percent complete: 79.8%; Average loss: 2.9201 Iteration: 3193; Percent complete: 79.8%; Average loss: 2.6607 Iteration: 3194; Percent complete: 79.8%; Average loss: 2.8065 Iteration: 3195; Percent complete: 79.9%; Average loss: 2.8388 Iteration: 3196; Percent complete: 79.9%; Average loss: 2.8739 Iteration: 3197; Percent complete: 79.9%; Average loss: 3.0021 Iteration: 3198; Percent complete: 80.0%; Average loss: 2.8182 Iteration: 3199; Percent complete: 80.0%; Average loss: 2.6366 Iteration: 3200; Percent complete: 80.0%; Average loss: 2.6378 Iteration: 3201; Percent complete: 80.0%; Average loss: 2.9557 Iteration: 3202; Percent complete: 80.0%; Average loss: 2.9569 Iteration: 3203; Percent complete: 80.1%; Average loss: 2.7753 Iteration: 3204; Percent complete: 80.1%; Average loss: 3.1457 Iteration: 3205; Percent complete: 80.1%; Average loss: 2.7751 Iteration: 3206; Percent complete: 80.2%; Average loss: 2.8938 Iteration: 3207; Percent complete: 80.2%; Average loss: 2.8733 Iteration: 3208; Percent complete: 80.2%; Average loss: 2.6591 Iteration: 3209; Percent complete: 80.2%; Average loss: 2.8695 Iteration: 3210; Percent complete: 80.2%; Average loss: 2.7468 Iteration: 3211; Percent complete: 80.3%; Average loss: 2.8448 Iteration: 3212; Percent complete: 80.3%; Average loss: 2.5705 Iteration: 3213; Percent complete: 80.3%; Average loss: 2.9362 Iteration: 3214; Percent complete: 80.3%; Average loss: 2.5364 Iteration: 3215; Percent complete: 80.4%; Average loss: 2.9067 Iteration: 3216; Percent complete: 80.4%; Average loss: 2.7456 Iteration: 3217; Percent complete: 80.4%; Average loss: 2.6071 Iteration: 3218; Percent complete: 80.5%; Average loss: 2.8226 Iteration: 3219; Percent complete: 80.5%; Average loss: 2.8397 Iteration: 3220; Percent complete: 80.5%; Average loss: 2.4819 Iteration: 3221; Percent complete: 80.5%; Average loss: 2.7157 Iteration: 3222; Percent complete: 80.5%; Average loss: 2.9914 Iteration: 3223; Percent complete: 80.6%; Average loss: 2.7301 Iteration: 3224; Percent complete: 80.6%; Average loss: 2.7304 Iteration: 3225; Percent complete: 80.6%; Average loss: 2.5472 Iteration: 3226; Percent complete: 80.7%; Average loss: 2.7291 Iteration: 3227; Percent complete: 80.7%; Average loss: 2.6346 Iteration: 3228; Percent complete: 80.7%; Average loss: 2.9844 Iteration: 3229; Percent complete: 80.7%; Average loss: 2.6887 Iteration: 3230; Percent complete: 80.8%; Average loss: 2.8315 Iteration: 3231; Percent complete: 80.8%; Average loss: 2.8054 Iteration: 3232; Percent complete: 80.8%; Average loss: 2.9746 Iteration: 3233; Percent complete: 80.8%; Average loss: 3.0810 Iteration: 3234; Percent complete: 80.8%; Average loss: 2.8427 Iteration: 3235; Percent complete: 80.9%; Average loss: 3.1354 Iteration: 3236; Percent complete: 80.9%; Average loss: 2.8278 Iteration: 3237; Percent complete: 80.9%; Average loss: 2.8025 Iteration: 3238; Percent complete: 81.0%; Average loss: 2.9510 Iteration: 3239; Percent complete: 81.0%; Average loss: 2.9139 Iteration: 3240; Percent complete: 81.0%; Average loss: 2.8099 Iteration: 3241; Percent complete: 81.0%; Average loss: 2.8103 Iteration: 3242; Percent complete: 81.0%; Average loss: 2.8998 Iteration: 3243; Percent complete: 81.1%; Average loss: 2.8841 Iteration: 3244; Percent complete: 81.1%; Average loss: 2.7871 Iteration: 3245; Percent complete: 81.1%; Average loss: 2.6965 Iteration: 3246; Percent complete: 81.2%; Average loss: 2.6558 Iteration: 3247; Percent complete: 81.2%; Average loss: 2.9868 Iteration: 3248; Percent complete: 81.2%; Average loss: 2.7197 Iteration: 3249; Percent complete: 81.2%; Average loss: 2.8245 Iteration: 3250; Percent complete: 81.2%; Average loss: 2.8504 Iteration: 3251; Percent complete: 81.3%; Average loss: 2.4894 Iteration: 3252; Percent complete: 81.3%; Average loss: 2.7469 Iteration: 3253; Percent complete: 81.3%; Average loss: 2.9555 Iteration: 3254; Percent complete: 81.3%; Average loss: 2.9092 Iteration: 3255; Percent complete: 81.4%; Average loss: 2.7153 Iteration: 3256; Percent complete: 81.4%; Average loss: 2.6894 Iteration: 3257; Percent complete: 81.4%; Average loss: 2.7365 Iteration: 3258; Percent complete: 81.5%; Average loss: 2.9024 Iteration: 3259; Percent complete: 81.5%; Average loss: 2.9313 Iteration: 3260; Percent complete: 81.5%; Average loss: 2.6930 Iteration: 3261; Percent complete: 81.5%; Average loss: 2.6987 Iteration: 3262; Percent complete: 81.5%; Average loss: 3.1009 Iteration: 3263; Percent complete: 81.6%; Average loss: 2.7768 Iteration: 3264; Percent complete: 81.6%; Average loss: 2.7979 Iteration: 3265; Percent complete: 81.6%; Average loss: 2.9035 Iteration: 3266; Percent complete: 81.7%; Average loss: 2.7804 Iteration: 3267; Percent complete: 81.7%; Average loss: 2.7046 Iteration: 3268; Percent complete: 81.7%; Average loss: 2.6413 Iteration: 3269; Percent complete: 81.7%; Average loss: 2.8144 Iteration: 3270; Percent complete: 81.8%; Average loss: 2.9124 Iteration: 3271; Percent complete: 81.8%; Average loss: 3.0752 Iteration: 3272; Percent complete: 81.8%; Average loss: 2.6936 Iteration: 3273; Percent complete: 81.8%; Average loss: 2.7399 Iteration: 3274; Percent complete: 81.8%; Average loss: 2.7877 Iteration: 3275; Percent complete: 81.9%; Average loss: 2.7430 Iteration: 3276; Percent complete: 81.9%; Average loss: 2.8248 Iteration: 3277; Percent complete: 81.9%; Average loss: 2.7876 Iteration: 3278; Percent complete: 82.0%; Average loss: 2.8327 Iteration: 3279; Percent complete: 82.0%; Average loss: 3.0944 Iteration: 3280; Percent complete: 82.0%; Average loss: 2.8529 Iteration: 3281; Percent complete: 82.0%; Average loss: 2.7695 Iteration: 3282; Percent complete: 82.0%; Average loss: 2.7043 Iteration: 3283; Percent complete: 82.1%; Average loss: 2.6940 Iteration: 3284; Percent complete: 82.1%; Average loss: 2.6865 Iteration: 3285; Percent complete: 82.1%; Average loss: 2.8005 Iteration: 3286; Percent complete: 82.2%; Average loss: 2.7794 Iteration: 3287; Percent complete: 82.2%; Average loss: 3.0264 Iteration: 3288; Percent complete: 82.2%; Average loss: 2.8955 Iteration: 3289; Percent complete: 82.2%; Average loss: 2.8888 Iteration: 3290; Percent complete: 82.2%; Average loss: 2.6937 Iteration: 3291; Percent complete: 82.3%; Average loss: 2.7154 Iteration: 3292; Percent complete: 82.3%; Average loss: 2.7504 Iteration: 3293; Percent complete: 82.3%; Average loss: 2.8377 Iteration: 3294; Percent complete: 82.3%; Average loss: 2.7677 Iteration: 3295; Percent complete: 82.4%; Average loss: 2.6208 Iteration: 3296; Percent complete: 82.4%; Average loss: 2.6250 Iteration: 3297; Percent complete: 82.4%; Average loss: 2.7482 Iteration: 3298; Percent complete: 82.5%; Average loss: 2.8682 Iteration: 3299; Percent complete: 82.5%; Average loss: 2.7431 Iteration: 3300; Percent complete: 82.5%; Average loss: 2.7730 Iteration: 3301; Percent complete: 82.5%; Average loss: 2.6172 Iteration: 3302; Percent complete: 82.5%; Average loss: 2.9220 Iteration: 3303; Percent complete: 82.6%; Average loss: 2.5694 Iteration: 3304; Percent complete: 82.6%; Average loss: 2.9588 Iteration: 3305; Percent complete: 82.6%; Average loss: 3.0438 Iteration: 3306; Percent complete: 82.7%; Average loss: 2.9374 Iteration: 3307; Percent complete: 82.7%; Average loss: 2.8580 Iteration: 3308; Percent complete: 82.7%; Average loss: 2.6264 Iteration: 3309; Percent complete: 82.7%; Average loss: 2.9111 Iteration: 3310; Percent complete: 82.8%; Average loss: 2.6075 Iteration: 3311; Percent complete: 82.8%; Average loss: 2.7633 Iteration: 3312; Percent complete: 82.8%; Average loss: 2.8521 Iteration: 3313; Percent complete: 82.8%; Average loss: 2.8456 Iteration: 3314; Percent complete: 82.8%; Average loss: 2.8167 Iteration: 3315; Percent complete: 82.9%; Average loss: 2.7716 Iteration: 3316; Percent complete: 82.9%; Average loss: 2.8787 Iteration: 3317; Percent complete: 82.9%; Average loss: 2.7337 Iteration: 3318; Percent complete: 83.0%; Average loss: 2.8541 Iteration: 3319; Percent complete: 83.0%; Average loss: 2.6045 Iteration: 3320; Percent complete: 83.0%; Average loss: 2.5889 Iteration: 3321; Percent complete: 83.0%; Average loss: 3.0120 Iteration: 3322; Percent complete: 83.0%; Average loss: 2.8932 Iteration: 3323; Percent complete: 83.1%; Average loss: 2.9955 Iteration: 3324; Percent complete: 83.1%; Average loss: 2.8088 Iteration: 3325; Percent complete: 83.1%; Average loss: 2.6639 Iteration: 3326; Percent complete: 83.2%; Average loss: 2.7510 Iteration: 3327; Percent complete: 83.2%; Average loss: 2.7598 Iteration: 3328; Percent complete: 83.2%; Average loss: 2.7517 Iteration: 3329; Percent complete: 83.2%; Average loss: 2.6644 Iteration: 3330; Percent complete: 83.2%; Average loss: 2.9953 Iteration: 3331; Percent complete: 83.3%; Average loss: 2.9275 Iteration: 3332; Percent complete: 83.3%; Average loss: 2.7729 Iteration: 3333; Percent complete: 83.3%; Average loss: 2.9132 Iteration: 3334; Percent complete: 83.4%; Average loss: 2.9719 Iteration: 3335; Percent complete: 83.4%; Average loss: 2.5709 Iteration: 3336; Percent complete: 83.4%; Average loss: 2.7188 Iteration: 3337; Percent complete: 83.4%; Average loss: 3.0410 Iteration: 3338; Percent complete: 83.5%; Average loss: 3.0086 Iteration: 3339; Percent complete: 83.5%; Average loss: 2.9660 Iteration: 3340; Percent complete: 83.5%; Average loss: 2.5728 Iteration: 3341; Percent complete: 83.5%; Average loss: 2.6418 Iteration: 3342; Percent complete: 83.5%; Average loss: 2.8296 Iteration: 3343; Percent complete: 83.6%; Average loss: 2.8919 Iteration: 3344; Percent complete: 83.6%; Average loss: 2.7103 Iteration: 3345; Percent complete: 83.6%; Average loss: 2.4793 Iteration: 3346; Percent complete: 83.7%; Average loss: 2.6698 Iteration: 3347; Percent complete: 83.7%; Average loss: 2.8554 Iteration: 3348; Percent complete: 83.7%; Average loss: 2.8463 Iteration: 3349; Percent complete: 83.7%; Average loss: 2.7017 Iteration: 3350; Percent complete: 83.8%; Average loss: 2.7556 Iteration: 3351; Percent complete: 83.8%; Average loss: 2.8779 Iteration: 3352; Percent complete: 83.8%; Average loss: 2.6651 Iteration: 3353; Percent complete: 83.8%; Average loss: 2.9170 Iteration: 3354; Percent complete: 83.9%; Average loss: 2.8580 Iteration: 3355; Percent complete: 83.9%; Average loss: 3.0085 Iteration: 3356; Percent complete: 83.9%; Average loss: 2.7239 Iteration: 3357; Percent complete: 83.9%; Average loss: 2.6047 Iteration: 3358; Percent complete: 84.0%; Average loss: 2.4785 Iteration: 3359; Percent complete: 84.0%; Average loss: 2.7826 Iteration: 3360; Percent complete: 84.0%; Average loss: 2.6786 Iteration: 3361; Percent complete: 84.0%; Average loss: 2.9561 Iteration: 3362; Percent complete: 84.0%; Average loss: 2.6993 Iteration: 3363; Percent complete: 84.1%; Average loss: 2.9437 Iteration: 3364; Percent complete: 84.1%; Average loss: 2.9327 Iteration: 3365; Percent complete: 84.1%; Average loss: 2.6804 Iteration: 3366; Percent complete: 84.2%; Average loss: 2.5455 Iteration: 3367; Percent complete: 84.2%; Average loss: 2.8453 Iteration: 3368; Percent complete: 84.2%; Average loss: 2.6679 Iteration: 3369; Percent complete: 84.2%; Average loss: 2.8039 Iteration: 3370; Percent complete: 84.2%; Average loss: 2.8262 Iteration: 3371; Percent complete: 84.3%; Average loss: 2.8003 Iteration: 3372; Percent complete: 84.3%; Average loss: 2.5765 Iteration: 3373; Percent complete: 84.3%; Average loss: 2.4919 Iteration: 3374; Percent complete: 84.4%; Average loss: 3.0013 Iteration: 3375; Percent complete: 84.4%; Average loss: 2.9478 Iteration: 3376; Percent complete: 84.4%; Average loss: 2.7432 Iteration: 3377; Percent complete: 84.4%; Average loss: 2.8397 Iteration: 3378; Percent complete: 84.5%; Average loss: 2.9068 Iteration: 3379; Percent complete: 84.5%; Average loss: 3.0353 Iteration: 3380; Percent complete: 84.5%; Average loss: 2.9022 Iteration: 3381; Percent complete: 84.5%; Average loss: 2.6919 Iteration: 3382; Percent complete: 84.5%; Average loss: 2.6851 Iteration: 3383; Percent complete: 84.6%; Average loss: 2.6156 Iteration: 3384; Percent complete: 84.6%; Average loss: 2.6867 Iteration: 3385; Percent complete: 84.6%; Average loss: 2.7933 Iteration: 3386; Percent complete: 84.7%; Average loss: 2.7175 Iteration: 3387; Percent complete: 84.7%; Average loss: 2.8209 Iteration: 3388; Percent complete: 84.7%; Average loss: 2.8118 Iteration: 3389; Percent complete: 84.7%; Average loss: 2.7409 Iteration: 3390; Percent complete: 84.8%; Average loss: 2.7524 Iteration: 3391; Percent complete: 84.8%; Average loss: 2.8035 Iteration: 3392; Percent complete: 84.8%; Average loss: 2.7692 Iteration: 3393; Percent complete: 84.8%; Average loss: 2.7139 Iteration: 3394; Percent complete: 84.9%; Average loss: 2.8296 Iteration: 3395; Percent complete: 84.9%; Average loss: 2.6793 Iteration: 3396; Percent complete: 84.9%; Average loss: 2.7268 Iteration: 3397; Percent complete: 84.9%; Average loss: 2.8404 Iteration: 3398; Percent complete: 85.0%; Average loss: 2.8266 Iteration: 3399; Percent complete: 85.0%; Average loss: 2.9853 Iteration: 3400; Percent complete: 85.0%; Average loss: 2.6445 Iteration: 3401; Percent complete: 85.0%; Average loss: 2.7802 Iteration: 3402; Percent complete: 85.0%; Average loss: 2.7942 Iteration: 3403; Percent complete: 85.1%; Average loss: 2.6372 Iteration: 3404; Percent complete: 85.1%; Average loss: 3.0356 Iteration: 3405; Percent complete: 85.1%; Average loss: 2.7139 Iteration: 3406; Percent complete: 85.2%; Average loss: 2.7637 Iteration: 3407; Percent complete: 85.2%; Average loss: 2.7668 Iteration: 3408; Percent complete: 85.2%; Average loss: 2.6046 Iteration: 3409; Percent complete: 85.2%; Average loss: 2.9080 Iteration: 3410; Percent complete: 85.2%; Average loss: 2.9664 Iteration: 3411; Percent complete: 85.3%; Average loss: 2.8296 Iteration: 3412; Percent complete: 85.3%; Average loss: 2.8440 Iteration: 3413; Percent complete: 85.3%; Average loss: 2.7324 Iteration: 3414; Percent complete: 85.4%; Average loss: 2.8752 Iteration: 3415; Percent complete: 85.4%; Average loss: 2.7309 Iteration: 3416; Percent complete: 85.4%; Average loss: 2.9169 Iteration: 3417; Percent complete: 85.4%; Average loss: 2.5707 Iteration: 3418; Percent complete: 85.5%; Average loss: 3.0617 Iteration: 3419; Percent complete: 85.5%; Average loss: 2.9471 Iteration: 3420; Percent complete: 85.5%; Average loss: 2.7286 Iteration: 3421; Percent complete: 85.5%; Average loss: 2.6550 Iteration: 3422; Percent complete: 85.5%; Average loss: 2.5018 Iteration: 3423; Percent complete: 85.6%; Average loss: 2.8021 Iteration: 3424; Percent complete: 85.6%; Average loss: 2.8741 Iteration: 3425; Percent complete: 85.6%; Average loss: 2.8726 Iteration: 3426; Percent complete: 85.7%; Average loss: 2.9770 Iteration: 3427; Percent complete: 85.7%; Average loss: 2.7719 Iteration: 3428; Percent complete: 85.7%; Average loss: 2.8145 Iteration: 3429; Percent complete: 85.7%; Average loss: 2.8036 Iteration: 3430; Percent complete: 85.8%; Average loss: 2.8381 Iteration: 3431; Percent complete: 85.8%; Average loss: 2.6960 Iteration: 3432; Percent complete: 85.8%; Average loss: 2.8131 Iteration: 3433; Percent complete: 85.8%; Average loss: 2.6966 Iteration: 3434; Percent complete: 85.9%; Average loss: 2.8044 Iteration: 3435; Percent complete: 85.9%; Average loss: 2.8299 Iteration: 3436; Percent complete: 85.9%; Average loss: 2.7449 Iteration: 3437; Percent complete: 85.9%; Average loss: 2.8296 Iteration: 3438; Percent complete: 86.0%; Average loss: 2.7304 Iteration: 3439; Percent complete: 86.0%; Average loss: 2.6956 Iteration: 3440; Percent complete: 86.0%; Average loss: 2.7512 Iteration: 3441; Percent complete: 86.0%; Average loss: 2.9506 Iteration: 3442; Percent complete: 86.1%; Average loss: 2.8815 Iteration: 3443; Percent complete: 86.1%; Average loss: 2.8879 Iteration: 3444; Percent complete: 86.1%; Average loss: 2.8426 Iteration: 3445; Percent complete: 86.1%; Average loss: 2.8444 Iteration: 3446; Percent complete: 86.2%; Average loss: 2.7609 Iteration: 3447; Percent complete: 86.2%; Average loss: 2.7690 Iteration: 3448; Percent complete: 86.2%; Average loss: 2.7262 Iteration: 3449; Percent complete: 86.2%; Average loss: 2.5984 Iteration: 3450; Percent complete: 86.2%; Average loss: 2.6103 Iteration: 3451; Percent complete: 86.3%; Average loss: 3.0396 Iteration: 3452; Percent complete: 86.3%; Average loss: 2.7875 Iteration: 3453; Percent complete: 86.3%; Average loss: 2.7919 Iteration: 3454; Percent complete: 86.4%; Average loss: 2.6506 Iteration: 3455; Percent complete: 86.4%; Average loss: 2.7781 Iteration: 3456; Percent complete: 86.4%; Average loss: 2.7998 Iteration: 3457; Percent complete: 86.4%; Average loss: 2.8435 Iteration: 3458; Percent complete: 86.5%; Average loss: 2.6009 Iteration: 3459; Percent complete: 86.5%; Average loss: 2.8036 Iteration: 3460; Percent complete: 86.5%; Average loss: 2.6685 Iteration: 3461; Percent complete: 86.5%; Average loss: 2.8338 Iteration: 3462; Percent complete: 86.6%; Average loss: 2.9343 Iteration: 3463; Percent complete: 86.6%; Average loss: 2.6772 Iteration: 3464; Percent complete: 86.6%; Average loss: 2.6122 Iteration: 3465; Percent complete: 86.6%; Average loss: 2.9516 Iteration: 3466; Percent complete: 86.7%; Average loss: 2.7357 Iteration: 3467; Percent complete: 86.7%; Average loss: 2.7450 Iteration: 3468; Percent complete: 86.7%; Average loss: 2.4845 Iteration: 3469; Percent complete: 86.7%; Average loss: 2.6989 Iteration: 3470; Percent complete: 86.8%; Average loss: 2.5675 Iteration: 3471; Percent complete: 86.8%; Average loss: 3.0826 Iteration: 3472; Percent complete: 86.8%; Average loss: 2.7790 Iteration: 3473; Percent complete: 86.8%; Average loss: 2.4522 Iteration: 3474; Percent complete: 86.9%; Average loss: 2.6455 Iteration: 3475; Percent complete: 86.9%; Average loss: 2.7757 Iteration: 3476; Percent complete: 86.9%; Average loss: 2.7695 Iteration: 3477; Percent complete: 86.9%; Average loss: 2.7216 Iteration: 3478; Percent complete: 87.0%; Average loss: 2.7490 Iteration: 3479; Percent complete: 87.0%; Average loss: 2.7929 Iteration: 3480; Percent complete: 87.0%; Average loss: 2.8241 Iteration: 3481; Percent complete: 87.0%; Average loss: 2.6795 Iteration: 3482; Percent complete: 87.1%; Average loss: 2.8323 Iteration: 3483; Percent complete: 87.1%; Average loss: 2.7136 Iteration: 3484; Percent complete: 87.1%; Average loss: 2.8420 Iteration: 3485; Percent complete: 87.1%; Average loss: 2.7886 Iteration: 3486; Percent complete: 87.2%; Average loss: 2.7933 Iteration: 3487; Percent complete: 87.2%; Average loss: 2.8359 Iteration: 3488; Percent complete: 87.2%; Average loss: 3.1042 Iteration: 3489; Percent complete: 87.2%; Average loss: 2.6602 Iteration: 3490; Percent complete: 87.2%; Average loss: 2.4284 Iteration: 3491; Percent complete: 87.3%; Average loss: 2.6499 Iteration: 3492; Percent complete: 87.3%; Average loss: 2.6227 Iteration: 3493; Percent complete: 87.3%; Average loss: 2.7493 Iteration: 3494; Percent complete: 87.4%; Average loss: 2.6200 Iteration: 3495; Percent complete: 87.4%; Average loss: 2.6133 Iteration: 3496; Percent complete: 87.4%; Average loss: 2.5774 Iteration: 3497; Percent complete: 87.4%; Average loss: 2.6436 Iteration: 3498; Percent complete: 87.5%; Average loss: 2.5522 Iteration: 3499; Percent complete: 87.5%; Average loss: 2.7224 Iteration: 3500; Percent complete: 87.5%; Average loss: 2.6589 Iteration: 3501; Percent complete: 87.5%; Average loss: 2.6972 Iteration: 3502; Percent complete: 87.5%; Average loss: 2.7803 Iteration: 3503; Percent complete: 87.6%; Average loss: 2.7600 Iteration: 3504; Percent complete: 87.6%; Average loss: 2.7264 Iteration: 3505; Percent complete: 87.6%; Average loss: 2.8350 Iteration: 3506; Percent complete: 87.6%; Average loss: 2.7900 Iteration: 3507; Percent complete: 87.7%; Average loss: 2.9526 Iteration: 3508; Percent complete: 87.7%; Average loss: 2.7574 Iteration: 3509; Percent complete: 87.7%; Average loss: 2.6957 Iteration: 3510; Percent complete: 87.8%; Average loss: 2.8839 Iteration: 3511; Percent complete: 87.8%; Average loss: 2.8602 Iteration: 3512; Percent complete: 87.8%; Average loss: 2.4817 Iteration: 3513; Percent complete: 87.8%; Average loss: 2.8014 Iteration: 3514; Percent complete: 87.8%; Average loss: 2.6752 Iteration: 3515; Percent complete: 87.9%; Average loss: 2.6295 Iteration: 3516; Percent complete: 87.9%; Average loss: 2.5631 Iteration: 3517; Percent complete: 87.9%; Average loss: 2.7433 Iteration: 3518; Percent complete: 87.9%; Average loss: 2.8591 Iteration: 3519; Percent complete: 88.0%; Average loss: 2.8695 Iteration: 3520; Percent complete: 88.0%; Average loss: 2.8944 Iteration: 3521; Percent complete: 88.0%; Average loss: 2.8783 Iteration: 3522; Percent complete: 88.0%; Average loss: 3.1044 Iteration: 3523; Percent complete: 88.1%; Average loss: 2.7433 Iteration: 3524; Percent complete: 88.1%; Average loss: 2.8376 Iteration: 3525; Percent complete: 88.1%; Average loss: 2.6651 Iteration: 3526; Percent complete: 88.1%; Average loss: 2.8478 Iteration: 3527; Percent complete: 88.2%; Average loss: 2.7579 Iteration: 3528; Percent complete: 88.2%; Average loss: 2.7791 Iteration: 3529; Percent complete: 88.2%; Average loss: 2.7969 Iteration: 3530; Percent complete: 88.2%; Average loss: 2.9238 Iteration: 3531; Percent complete: 88.3%; Average loss: 2.7836 Iteration: 3532; Percent complete: 88.3%; Average loss: 2.5908 Iteration: 3533; Percent complete: 88.3%; Average loss: 2.8173 Iteration: 3534; Percent complete: 88.3%; Average loss: 2.7117 Iteration: 3535; Percent complete: 88.4%; Average loss: 2.7241 Iteration: 3536; Percent complete: 88.4%; Average loss: 2.9128 Iteration: 3537; Percent complete: 88.4%; Average loss: 2.5404 Iteration: 3538; Percent complete: 88.4%; Average loss: 2.6126 Iteration: 3539; Percent complete: 88.5%; Average loss: 2.8224 Iteration: 3540; Percent complete: 88.5%; Average loss: 2.6664 Iteration: 3541; Percent complete: 88.5%; Average loss: 2.8464 Iteration: 3542; Percent complete: 88.5%; Average loss: 2.6034 Iteration: 3543; Percent complete: 88.6%; Average loss: 2.8930 Iteration: 3544; Percent complete: 88.6%; Average loss: 2.5719 Iteration: 3545; Percent complete: 88.6%; Average loss: 2.7771 Iteration: 3546; Percent complete: 88.6%; Average loss: 2.7261 Iteration: 3547; Percent complete: 88.7%; Average loss: 2.8517 Iteration: 3548; Percent complete: 88.7%; Average loss: 2.9941 Iteration: 3549; Percent complete: 88.7%; Average loss: 2.8294 Iteration: 3550; Percent complete: 88.8%; Average loss: 2.8407 Iteration: 3551; Percent complete: 88.8%; Average loss: 2.8349 Iteration: 3552; Percent complete: 88.8%; Average loss: 2.8763 Iteration: 3553; Percent complete: 88.8%; Average loss: 2.8414 Iteration: 3554; Percent complete: 88.8%; Average loss: 2.8691 Iteration: 3555; Percent complete: 88.9%; Average loss: 2.8835 Iteration: 3556; Percent complete: 88.9%; Average loss: 2.6605 Iteration: 3557; Percent complete: 88.9%; Average loss: 2.6779 Iteration: 3558; Percent complete: 88.9%; Average loss: 2.6173 Iteration: 3559; Percent complete: 89.0%; Average loss: 3.0470 Iteration: 3560; Percent complete: 89.0%; Average loss: 2.7230 Iteration: 3561; Percent complete: 89.0%; Average loss: 2.8018 Iteration: 3562; Percent complete: 89.0%; Average loss: 2.8571 Iteration: 3563; Percent complete: 89.1%; Average loss: 2.8418 Iteration: 3564; Percent complete: 89.1%; Average loss: 2.6781 Iteration: 3565; Percent complete: 89.1%; Average loss: 2.8367 Iteration: 3566; Percent complete: 89.1%; Average loss: 2.7409 Iteration: 3567; Percent complete: 89.2%; Average loss: 2.9581 Iteration: 3568; Percent complete: 89.2%; Average loss: 2.6451 Iteration: 3569; Percent complete: 89.2%; Average loss: 2.7272 Iteration: 3570; Percent complete: 89.2%; Average loss: 2.8448 Iteration: 3571; Percent complete: 89.3%; Average loss: 2.8703 Iteration: 3572; Percent complete: 89.3%; Average loss: 2.8440 Iteration: 3573; Percent complete: 89.3%; Average loss: 3.0357 Iteration: 3574; Percent complete: 89.3%; Average loss: 2.9250 Iteration: 3575; Percent complete: 89.4%; Average loss: 2.7300 Iteration: 3576; Percent complete: 89.4%; Average loss: 2.9258 Iteration: 3577; Percent complete: 89.4%; Average loss: 2.7404 Iteration: 3578; Percent complete: 89.5%; Average loss: 2.6800 Iteration: 3579; Percent complete: 89.5%; Average loss: 2.7289 Iteration: 3580; Percent complete: 89.5%; Average loss: 3.0095 Iteration: 3581; Percent complete: 89.5%; Average loss: 2.6710 Iteration: 3582; Percent complete: 89.5%; Average loss: 2.7946 Iteration: 3583; Percent complete: 89.6%; Average loss: 2.6024 Iteration: 3584; Percent complete: 89.6%; Average loss: 2.7203 Iteration: 3585; Percent complete: 89.6%; Average loss: 2.7697 Iteration: 3586; Percent complete: 89.6%; Average loss: 2.4420 Iteration: 3587; Percent complete: 89.7%; Average loss: 2.7587 Iteration: 3588; Percent complete: 89.7%; Average loss: 2.7154 Iteration: 3589; Percent complete: 89.7%; Average loss: 2.6725 Iteration: 3590; Percent complete: 89.8%; Average loss: 2.6962 Iteration: 3591; Percent complete: 89.8%; Average loss: 2.6828 Iteration: 3592; Percent complete: 89.8%; Average loss: 2.6976 Iteration: 3593; Percent complete: 89.8%; Average loss: 2.7849 Iteration: 3594; Percent complete: 89.8%; Average loss: 2.8977 Iteration: 3595; Percent complete: 89.9%; Average loss: 2.7962 Iteration: 3596; Percent complete: 89.9%; Average loss: 3.0118 Iteration: 3597; Percent complete: 89.9%; Average loss: 2.6156 Iteration: 3598; Percent complete: 90.0%; Average loss: 2.8411 Iteration: 3599; Percent complete: 90.0%; Average loss: 2.6987 Iteration: 3600; Percent complete: 90.0%; Average loss: 2.7982 Iteration: 3601; Percent complete: 90.0%; Average loss: 2.5734 Iteration: 3602; Percent complete: 90.0%; Average loss: 2.5884 Iteration: 3603; Percent complete: 90.1%; Average loss: 2.8353 Iteration: 3604; Percent complete: 90.1%; Average loss: 2.7726 Iteration: 3605; Percent complete: 90.1%; Average loss: 2.7132 Iteration: 3606; Percent complete: 90.1%; Average loss: 2.6555 Iteration: 3607; Percent complete: 90.2%; Average loss: 2.6021 Iteration: 3608; Percent complete: 90.2%; Average loss: 2.6038 Iteration: 3609; Percent complete: 90.2%; Average loss: 2.7257 Iteration: 3610; Percent complete: 90.2%; Average loss: 2.8357 Iteration: 3611; Percent complete: 90.3%; Average loss: 2.9097 Iteration: 3612; Percent complete: 90.3%; Average loss: 2.6515 Iteration: 3613; Percent complete: 90.3%; Average loss: 2.6869 Iteration: 3614; Percent complete: 90.3%; Average loss: 2.6525 Iteration: 3615; Percent complete: 90.4%; Average loss: 2.8354 Iteration: 3616; Percent complete: 90.4%; Average loss: 2.8385 Iteration: 3617; Percent complete: 90.4%; Average loss: 2.8777 Iteration: 3618; Percent complete: 90.5%; Average loss: 2.7262 Iteration: 3619; Percent complete: 90.5%; Average loss: 2.7714 Iteration: 3620; Percent complete: 90.5%; Average loss: 2.6632 Iteration: 3621; Percent complete: 90.5%; Average loss: 2.6655 Iteration: 3622; Percent complete: 90.5%; Average loss: 2.6905 Iteration: 3623; Percent complete: 90.6%; Average loss: 2.7133 Iteration: 3624; Percent complete: 90.6%; Average loss: 2.9895 Iteration: 3625; Percent complete: 90.6%; Average loss: 2.6854 Iteration: 3626; Percent complete: 90.6%; Average loss: 2.6195 Iteration: 3627; Percent complete: 90.7%; Average loss: 2.8435 Iteration: 3628; Percent complete: 90.7%; Average loss: 2.6734 Iteration: 3629; Percent complete: 90.7%; Average loss: 2.6870 Iteration: 3630; Percent complete: 90.8%; Average loss: 2.5607 Iteration: 3631; Percent complete: 90.8%; Average loss: 2.7350 Iteration: 3632; Percent complete: 90.8%; Average loss: 2.6058 Iteration: 3633; Percent complete: 90.8%; Average loss: 2.4560 Iteration: 3634; Percent complete: 90.8%; Average loss: 2.8718 Iteration: 3635; Percent complete: 90.9%; Average loss: 2.8950 Iteration: 3636; Percent complete: 90.9%; Average loss: 2.7360 Iteration: 3637; Percent complete: 90.9%; Average loss: 2.6777 Iteration: 3638; Percent complete: 91.0%; Average loss: 2.8613 Iteration: 3639; Percent complete: 91.0%; Average loss: 2.8034 Iteration: 3640; Percent complete: 91.0%; Average loss: 2.7528 Iteration: 3641; Percent complete: 91.0%; Average loss: 2.6428 Iteration: 3642; Percent complete: 91.0%; Average loss: 2.7210 Iteration: 3643; Percent complete: 91.1%; Average loss: 2.8201 Iteration: 3644; Percent complete: 91.1%; Average loss: 2.6195 Iteration: 3645; Percent complete: 91.1%; Average loss: 2.8826 Iteration: 3646; Percent complete: 91.1%; Average loss: 2.5454 Iteration: 3647; Percent complete: 91.2%; Average loss: 2.5737 Iteration: 3648; Percent complete: 91.2%; Average loss: 2.7141 Iteration: 3649; Percent complete: 91.2%; Average loss: 2.8455 Iteration: 3650; Percent complete: 91.2%; Average loss: 2.4901 Iteration: 3651; Percent complete: 91.3%; Average loss: 2.9012 Iteration: 3652; Percent complete: 91.3%; Average loss: 2.8890 Iteration: 3653; Percent complete: 91.3%; Average loss: 2.7740 Iteration: 3654; Percent complete: 91.3%; Average loss: 2.5389 Iteration: 3655; Percent complete: 91.4%; Average loss: 2.6295 Iteration: 3656; Percent complete: 91.4%; Average loss: 2.7192 Iteration: 3657; Percent complete: 91.4%; Average loss: 2.4222 Iteration: 3658; Percent complete: 91.5%; Average loss: 2.9274 Iteration: 3659; Percent complete: 91.5%; Average loss: 2.5931 Iteration: 3660; Percent complete: 91.5%; Average loss: 2.5854 Iteration: 3661; Percent complete: 91.5%; Average loss: 2.7785 Iteration: 3662; Percent complete: 91.5%; Average loss: 2.5166 Iteration: 3663; Percent complete: 91.6%; Average loss: 2.6755 Iteration: 3664; Percent complete: 91.6%; Average loss: 2.7139 Iteration: 3665; Percent complete: 91.6%; Average loss: 2.7761 Iteration: 3666; Percent complete: 91.6%; Average loss: 2.7994 Iteration: 3667; Percent complete: 91.7%; Average loss: 2.6971 Iteration: 3668; Percent complete: 91.7%; Average loss: 2.5994 Iteration: 3669; Percent complete: 91.7%; Average loss: 2.6804 Iteration: 3670; Percent complete: 91.8%; Average loss: 2.5659 Iteration: 3671; Percent complete: 91.8%; Average loss: 2.7175 Iteration: 3672; Percent complete: 91.8%; Average loss: 2.7135 Iteration: 3673; Percent complete: 91.8%; Average loss: 2.8937 Iteration: 3674; Percent complete: 91.8%; Average loss: 2.7235 Iteration: 3675; Percent complete: 91.9%; Average loss: 2.8656 Iteration: 3676; Percent complete: 91.9%; Average loss: 2.6238 Iteration: 3677; Percent complete: 91.9%; Average loss: 2.8599 Iteration: 3678; Percent complete: 92.0%; Average loss: 2.5867 Iteration: 3679; Percent complete: 92.0%; Average loss: 2.6170 Iteration: 3680; Percent complete: 92.0%; Average loss: 2.7800 Iteration: 3681; Percent complete: 92.0%; Average loss: 2.6984 Iteration: 3682; Percent complete: 92.0%; Average loss: 2.8264 Iteration: 3683; Percent complete: 92.1%; Average loss: 2.6758 Iteration: 3684; Percent complete: 92.1%; Average loss: 2.7419 Iteration: 3685; Percent complete: 92.1%; Average loss: 2.8639 Iteration: 3686; Percent complete: 92.2%; Average loss: 2.8029 Iteration: 3687; Percent complete: 92.2%; Average loss: 2.8368 Iteration: 3688; Percent complete: 92.2%; Average loss: 2.8057 Iteration: 3689; Percent complete: 92.2%; Average loss: 2.6765 Iteration: 3690; Percent complete: 92.2%; Average loss: 2.5919 Iteration: 3691; Percent complete: 92.3%; Average loss: 2.8553 Iteration: 3692; Percent complete: 92.3%; Average loss: 2.7060 Iteration: 3693; Percent complete: 92.3%; Average loss: 2.7230 Iteration: 3694; Percent complete: 92.3%; Average loss: 2.6462 Iteration: 3695; Percent complete: 92.4%; Average loss: 2.7073 Iteration: 3696; Percent complete: 92.4%; Average loss: 2.6704 Iteration: 3697; Percent complete: 92.4%; Average loss: 2.5875 Iteration: 3698; Percent complete: 92.5%; Average loss: 2.9335 Iteration: 3699; Percent complete: 92.5%; Average loss: 2.6505 Iteration: 3700; Percent complete: 92.5%; Average loss: 2.4880 Iteration: 3701; Percent complete: 92.5%; Average loss: 2.8399 Iteration: 3702; Percent complete: 92.5%; Average loss: 2.5550 Iteration: 3703; Percent complete: 92.6%; Average loss: 2.6555 Iteration: 3704; Percent complete: 92.6%; Average loss: 2.8539 Iteration: 3705; Percent complete: 92.6%; Average loss: 2.8492 Iteration: 3706; Percent complete: 92.7%; Average loss: 2.6757 Iteration: 3707; Percent complete: 92.7%; Average loss: 2.6523 Iteration: 3708; Percent complete: 92.7%; Average loss: 2.8119 Iteration: 3709; Percent complete: 92.7%; Average loss: 2.4142 Iteration: 3710; Percent complete: 92.8%; Average loss: 2.6778 Iteration: 3711; Percent complete: 92.8%; Average loss: 2.6903 Iteration: 3712; Percent complete: 92.8%; Average loss: 2.6954 Iteration: 3713; Percent complete: 92.8%; Average loss: 2.7220 Iteration: 3714; Percent complete: 92.8%; Average loss: 2.5743 Iteration: 3715; Percent complete: 92.9%; Average loss: 2.7192 Iteration: 3716; Percent complete: 92.9%; Average loss: 2.5006 Iteration: 3717; Percent complete: 92.9%; Average loss: 2.7942 Iteration: 3718; Percent complete: 93.0%; Average loss: 2.6757 Iteration: 3719; Percent complete: 93.0%; Average loss: 2.7648 Iteration: 3720; Percent complete: 93.0%; Average loss: 2.5321 Iteration: 3721; Percent complete: 93.0%; Average loss: 2.6876 Iteration: 3722; Percent complete: 93.0%; Average loss: 2.6956 Iteration: 3723; Percent complete: 93.1%; Average loss: 2.4508 Iteration: 3724; Percent complete: 93.1%; Average loss: 2.5704 Iteration: 3725; Percent complete: 93.1%; Average loss: 2.5099 Iteration: 3726; Percent complete: 93.2%; Average loss: 2.7382 Iteration: 3727; Percent complete: 93.2%; Average loss: 2.6362 Iteration: 3728; Percent complete: 93.2%; Average loss: 2.7032 Iteration: 3729; Percent complete: 93.2%; Average loss: 2.7373 Iteration: 3730; Percent complete: 93.2%; Average loss: 2.7125 Iteration: 3731; Percent complete: 93.3%; Average loss: 2.8094 Iteration: 3732; Percent complete: 93.3%; Average loss: 2.8834 Iteration: 3733; Percent complete: 93.3%; Average loss: 2.9129 Iteration: 3734; Percent complete: 93.3%; Average loss: 2.7034 Iteration: 3735; Percent complete: 93.4%; Average loss: 2.7209 Iteration: 3736; Percent complete: 93.4%; Average loss: 2.6783 Iteration: 3737; Percent complete: 93.4%; Average loss: 2.6776 Iteration: 3738; Percent complete: 93.5%; Average loss: 2.6114 Iteration: 3739; Percent complete: 93.5%; Average loss: 2.7002 Iteration: 3740; Percent complete: 93.5%; Average loss: 2.6486 Iteration: 3741; Percent complete: 93.5%; Average loss: 2.9956 Iteration: 3742; Percent complete: 93.5%; Average loss: 2.8710 Iteration: 3743; Percent complete: 93.6%; Average loss: 2.7367 Iteration: 3744; Percent complete: 93.6%; Average loss: 2.8909 Iteration: 3745; Percent complete: 93.6%; Average loss: 2.8625 Iteration: 3746; Percent complete: 93.7%; Average loss: 3.0609 Iteration: 3747; Percent complete: 93.7%; Average loss: 2.6708 Iteration: 3748; Percent complete: 93.7%; Average loss: 2.7055 Iteration: 3749; Percent complete: 93.7%; Average loss: 2.6937 Iteration: 3750; Percent complete: 93.8%; Average loss: 2.5488 Iteration: 3751; Percent complete: 93.8%; Average loss: 2.6902 Iteration: 3752; Percent complete: 93.8%; Average loss: 2.5244 Iteration: 3753; Percent complete: 93.8%; Average loss: 2.5556 Iteration: 3754; Percent complete: 93.8%; Average loss: 2.7157 Iteration: 3755; Percent complete: 93.9%; Average loss: 2.6435 Iteration: 3756; Percent complete: 93.9%; Average loss: 2.5898 Iteration: 3757; Percent complete: 93.9%; Average loss: 2.6989 Iteration: 3758; Percent complete: 94.0%; Average loss: 2.5458 Iteration: 3759; Percent complete: 94.0%; Average loss: 2.6102 Iteration: 3760; Percent complete: 94.0%; Average loss: 2.6865 Iteration: 3761; Percent complete: 94.0%; Average loss: 2.7686 Iteration: 3762; Percent complete: 94.0%; Average loss: 2.7302 Iteration: 3763; Percent complete: 94.1%; Average loss: 2.6119 Iteration: 3764; Percent complete: 94.1%; Average loss: 2.5667 Iteration: 3765; Percent complete: 94.1%; Average loss: 2.8493 Iteration: 3766; Percent complete: 94.2%; Average loss: 2.6951 Iteration: 3767; Percent complete: 94.2%; Average loss: 2.8562 Iteration: 3768; Percent complete: 94.2%; Average loss: 2.7987 Iteration: 3769; Percent complete: 94.2%; Average loss: 2.5385 Iteration: 3770; Percent complete: 94.2%; Average loss: 2.9085 Iteration: 3771; Percent complete: 94.3%; Average loss: 2.6024 Iteration: 3772; Percent complete: 94.3%; Average loss: 2.6679 Iteration: 3773; Percent complete: 94.3%; Average loss: 2.5901 Iteration: 3774; Percent complete: 94.3%; Average loss: 2.5780 Iteration: 3775; Percent complete: 94.4%; Average loss: 2.5686 Iteration: 3776; Percent complete: 94.4%; Average loss: 2.6717 Iteration: 3777; Percent complete: 94.4%; Average loss: 2.8586 Iteration: 3778; Percent complete: 94.5%; Average loss: 2.5101 Iteration: 3779; Percent complete: 94.5%; Average loss: 2.6561 Iteration: 3780; Percent complete: 94.5%; Average loss: 2.5741 Iteration: 3781; Percent complete: 94.5%; Average loss: 2.7068 Iteration: 3782; Percent complete: 94.5%; Average loss: 2.5012 Iteration: 3783; Percent complete: 94.6%; Average loss: 2.5838 Iteration: 3784; Percent complete: 94.6%; Average loss: 2.8081 Iteration: 3785; Percent complete: 94.6%; Average loss: 2.6799 Iteration: 3786; Percent complete: 94.7%; Average loss: 2.4000 Iteration: 3787; Percent complete: 94.7%; Average loss: 2.6911 Iteration: 3788; Percent complete: 94.7%; Average loss: 2.6576 Iteration: 3789; Percent complete: 94.7%; Average loss: 2.5780 Iteration: 3790; Percent complete: 94.8%; Average loss: 2.6599 Iteration: 3791; Percent complete: 94.8%; Average loss: 2.6517 Iteration: 3792; Percent complete: 94.8%; Average loss: 2.5906 Iteration: 3793; Percent complete: 94.8%; Average loss: 2.8564 Iteration: 3794; Percent complete: 94.8%; Average loss: 2.8247 Iteration: 3795; Percent complete: 94.9%; Average loss: 2.6695 Iteration: 3796; Percent complete: 94.9%; Average loss: 2.4007 Iteration: 3797; Percent complete: 94.9%; Average loss: 2.4537 Iteration: 3798; Percent complete: 95.0%; Average loss: 2.8994 Iteration: 3799; Percent complete: 95.0%; Average loss: 2.5720 Iteration: 3800; Percent complete: 95.0%; Average loss: 2.6809 Iteration: 3801; Percent complete: 95.0%; Average loss: 2.7143 Iteration: 3802; Percent complete: 95.0%; Average loss: 2.6849 Iteration: 3803; Percent complete: 95.1%; Average loss: 2.8724 Iteration: 3804; Percent complete: 95.1%; Average loss: 2.6002 Iteration: 3805; Percent complete: 95.1%; Average loss: 2.5940 Iteration: 3806; Percent complete: 95.2%; Average loss: 2.6140 Iteration: 3807; Percent complete: 95.2%; Average loss: 2.6505 Iteration: 3808; Percent complete: 95.2%; Average loss: 2.5353 Iteration: 3809; Percent complete: 95.2%; Average loss: 2.7085 Iteration: 3810; Percent complete: 95.2%; Average loss: 2.5804 Iteration: 3811; Percent complete: 95.3%; Average loss: 2.5279 Iteration: 3812; Percent complete: 95.3%; Average loss: 2.7234 Iteration: 3813; Percent complete: 95.3%; Average loss: 2.5719 Iteration: 3814; Percent complete: 95.3%; Average loss: 2.7502 Iteration: 3815; Percent complete: 95.4%; Average loss: 2.4800 Iteration: 3816; Percent complete: 95.4%; Average loss: 2.4121 Iteration: 3817; Percent complete: 95.4%; Average loss: 2.8290 Iteration: 3818; Percent complete: 95.5%; Average loss: 2.7156 Iteration: 3819; Percent complete: 95.5%; Average loss: 2.5034 Iteration: 3820; Percent complete: 95.5%; Average loss: 2.6576 Iteration: 3821; Percent complete: 95.5%; Average loss: 2.7087 Iteration: 3822; Percent complete: 95.5%; Average loss: 2.8897 Iteration: 3823; Percent complete: 95.6%; Average loss: 2.8173 Iteration: 3824; Percent complete: 95.6%; Average loss: 2.6789 Iteration: 3825; Percent complete: 95.6%; Average loss: 2.6361 Iteration: 3826; Percent complete: 95.7%; Average loss: 2.6429 Iteration: 3827; Percent complete: 95.7%; Average loss: 2.7222 Iteration: 3828; Percent complete: 95.7%; Average loss: 2.7625 Iteration: 3829; Percent complete: 95.7%; Average loss: 2.5701 Iteration: 3830; Percent complete: 95.8%; Average loss: 2.5974 Iteration: 3831; Percent complete: 95.8%; Average loss: 2.5374 Iteration: 3832; Percent complete: 95.8%; Average loss: 2.5578 Iteration: 3833; Percent complete: 95.8%; Average loss: 2.7075 Iteration: 3834; Percent complete: 95.9%; Average loss: 2.6357 Iteration: 3835; Percent complete: 95.9%; Average loss: 2.6637 Iteration: 3836; Percent complete: 95.9%; Average loss: 2.7431 Iteration: 3837; Percent complete: 95.9%; Average loss: 2.5998 Iteration: 3838; Percent complete: 96.0%; Average loss: 2.5297 Iteration: 3839; Percent complete: 96.0%; Average loss: 2.6842 Iteration: 3840; Percent complete: 96.0%; Average loss: 2.7667 Iteration: 3841; Percent complete: 96.0%; Average loss: 2.6910 Iteration: 3842; Percent complete: 96.0%; Average loss: 2.5839 Iteration: 3843; Percent complete: 96.1%; Average loss: 2.8751 Iteration: 3844; Percent complete: 96.1%; Average loss: 2.7541 Iteration: 3845; Percent complete: 96.1%; Average loss: 2.6723 Iteration: 3846; Percent complete: 96.2%; Average loss: 2.5978 Iteration: 3847; Percent complete: 96.2%; Average loss: 2.5247 Iteration: 3848; Percent complete: 96.2%; Average loss: 2.8984 Iteration: 3849; Percent complete: 96.2%; Average loss: 2.8817 Iteration: 3850; Percent complete: 96.2%; Average loss: 2.5514 Iteration: 3851; Percent complete: 96.3%; Average loss: 2.7143 Iteration: 3852; Percent complete: 96.3%; Average loss: 2.6886 Iteration: 3853; Percent complete: 96.3%; Average loss: 2.5065 Iteration: 3854; Percent complete: 96.4%; Average loss: 2.7868 Iteration: 3855; Percent complete: 96.4%; Average loss: 2.6877 Iteration: 3856; Percent complete: 96.4%; Average loss: 2.6562 Iteration: 3857; Percent complete: 96.4%; Average loss: 2.6755 Iteration: 3858; Percent complete: 96.5%; Average loss: 2.6618 Iteration: 3859; Percent complete: 96.5%; Average loss: 2.5340 Iteration: 3860; Percent complete: 96.5%; Average loss: 2.6893 Iteration: 3861; Percent complete: 96.5%; Average loss: 2.6454 Iteration: 3862; Percent complete: 96.5%; Average loss: 2.6089 Iteration: 3863; Percent complete: 96.6%; Average loss: 2.5547 Iteration: 3864; Percent complete: 96.6%; Average loss: 2.5053 Iteration: 3865; Percent complete: 96.6%; Average loss: 2.6210 Iteration: 3866; Percent complete: 96.7%; Average loss: 2.6326 Iteration: 3867; Percent complete: 96.7%; Average loss: 2.6646 Iteration: 3868; Percent complete: 96.7%; Average loss: 2.9453 Iteration: 3869; Percent complete: 96.7%; Average loss: 2.6731 Iteration: 3870; Percent complete: 96.8%; Average loss: 2.6592 Iteration: 3871; Percent complete: 96.8%; Average loss: 2.7139 Iteration: 3872; Percent complete: 96.8%; Average loss: 2.9139 Iteration: 3873; Percent complete: 96.8%; Average loss: 2.5216 Iteration: 3874; Percent complete: 96.9%; Average loss: 2.5714 Iteration: 3875; Percent complete: 96.9%; Average loss: 2.5471 Iteration: 3876; Percent complete: 96.9%; Average loss: 2.8413 Iteration: 3877; Percent complete: 96.9%; Average loss: 2.5316 Iteration: 3878; Percent complete: 97.0%; Average loss: 2.7127 Iteration: 3879; Percent complete: 97.0%; Average loss: 2.5501 Iteration: 3880; Percent complete: 97.0%; Average loss: 2.5761 Iteration: 3881; Percent complete: 97.0%; Average loss: 2.9180 Iteration: 3882; Percent complete: 97.0%; Average loss: 2.5878 Iteration: 3883; Percent complete: 97.1%; Average loss: 2.6610 Iteration: 3884; Percent complete: 97.1%; Average loss: 2.5782 Iteration: 3885; Percent complete: 97.1%; Average loss: 2.7035 Iteration: 3886; Percent complete: 97.2%; Average loss: 2.8279 Iteration: 3887; Percent complete: 97.2%; Average loss: 2.6466 Iteration: 3888; Percent complete: 97.2%; Average loss: 2.4795 Iteration: 3889; Percent complete: 97.2%; Average loss: 2.5924 Iteration: 3890; Percent complete: 97.2%; Average loss: 2.8224 Iteration: 3891; Percent complete: 97.3%; Average loss: 2.7278 Iteration: 3892; Percent complete: 97.3%; Average loss: 2.6859 Iteration: 3893; Percent complete: 97.3%; Average loss: 2.7105 Iteration: 3894; Percent complete: 97.4%; Average loss: 2.5756 Iteration: 3895; Percent complete: 97.4%; Average loss: 2.6768 Iteration: 3896; Percent complete: 97.4%; Average loss: 2.7214 Iteration: 3897; Percent complete: 97.4%; Average loss: 2.7240 Iteration: 3898; Percent complete: 97.5%; Average loss: 2.7766 Iteration: 3899; Percent complete: 97.5%; Average loss: 2.5769 Iteration: 3900; Percent complete: 97.5%; Average loss: 2.5047 Iteration: 3901; Percent complete: 97.5%; Average loss: 2.8784 Iteration: 3902; Percent complete: 97.5%; Average loss: 2.6291 Iteration: 3903; Percent complete: 97.6%; Average loss: 2.6135 Iteration: 3904; Percent complete: 97.6%; Average loss: 2.4287 Iteration: 3905; Percent complete: 97.6%; Average loss: 2.5819 Iteration: 3906; Percent complete: 97.7%; Average loss: 2.5640 Iteration: 3907; Percent complete: 97.7%; Average loss: 2.6679 Iteration: 3908; Percent complete: 97.7%; Average loss: 2.7462 Iteration: 3909; Percent complete: 97.7%; Average loss: 2.6882 Iteration: 3910; Percent complete: 97.8%; Average loss: 2.4764 Iteration: 3911; Percent complete: 97.8%; Average loss: 2.7090 Iteration: 3912; Percent complete: 97.8%; Average loss: 2.6469 Iteration: 3913; Percent complete: 97.8%; Average loss: 2.7736 Iteration: 3914; Percent complete: 97.9%; Average loss: 2.4404 Iteration: 3915; Percent complete: 97.9%; Average loss: 2.6103 Iteration: 3916; Percent complete: 97.9%; Average loss: 2.4401 Iteration: 3917; Percent complete: 97.9%; Average loss: 2.6127 Iteration: 3918; Percent complete: 98.0%; Average loss: 2.5188 Iteration: 3919; Percent complete: 98.0%; Average loss: 2.6286 Iteration: 3920; Percent complete: 98.0%; Average loss: 2.8184 Iteration: 3921; Percent complete: 98.0%; Average loss: 2.7928 Iteration: 3922; Percent complete: 98.0%; Average loss: 2.5510 Iteration: 3923; Percent complete: 98.1%; Average loss: 2.8099 Iteration: 3924; Percent complete: 98.1%; Average loss: 2.8159 Iteration: 3925; Percent complete: 98.1%; Average loss: 2.4415 Iteration: 3926; Percent complete: 98.2%; Average loss: 2.6581 Iteration: 3927; Percent complete: 98.2%; Average loss: 2.5642 Iteration: 3928; Percent complete: 98.2%; Average loss: 2.6420 Iteration: 3929; Percent complete: 98.2%; Average loss: 2.6338 Iteration: 3930; Percent complete: 98.2%; Average loss: 2.6937 Iteration: 3931; Percent complete: 98.3%; Average loss: 2.8180 Iteration: 3932; Percent complete: 98.3%; Average loss: 2.5759 Iteration: 3933; Percent complete: 98.3%; Average loss: 2.7213 Iteration: 3934; Percent complete: 98.4%; Average loss: 3.1816 Iteration: 3935; Percent complete: 98.4%; Average loss: 2.6288 Iteration: 3936; Percent complete: 98.4%; Average loss: 2.5920 Iteration: 3937; Percent complete: 98.4%; Average loss: 2.5880 Iteration: 3938; Percent complete: 98.5%; Average loss: 2.5404 Iteration: 3939; Percent complete: 98.5%; Average loss: 2.5782 Iteration: 3940; Percent complete: 98.5%; Average loss: 2.7518 Iteration: 3941; Percent complete: 98.5%; Average loss: 2.7541 Iteration: 3942; Percent complete: 98.6%; Average loss: 2.7865 Iteration: 3943; Percent complete: 98.6%; Average loss: 2.5141 Iteration: 3944; Percent complete: 98.6%; Average loss: 2.5617 Iteration: 3945; Percent complete: 98.6%; Average loss: 2.5470 Iteration: 3946; Percent complete: 98.7%; Average loss: 2.6554 Iteration: 3947; Percent complete: 98.7%; Average loss: 2.5669 Iteration: 3948; Percent complete: 98.7%; Average loss: 2.6674 Iteration: 3949; Percent complete: 98.7%; Average loss: 2.6752 Iteration: 3950; Percent complete: 98.8%; Average loss: 2.7686 Iteration: 3951; Percent complete: 98.8%; Average loss: 2.5229 Iteration: 3952; Percent complete: 98.8%; Average loss: 2.8237 Iteration: 3953; Percent complete: 98.8%; Average loss: 2.6934 Iteration: 3954; Percent complete: 98.9%; Average loss: 2.8510 Iteration: 3955; Percent complete: 98.9%; Average loss: 2.5630 Iteration: 3956; Percent complete: 98.9%; Average loss: 2.4631 Iteration: 3957; Percent complete: 98.9%; Average loss: 2.7320 Iteration: 3958; Percent complete: 99.0%; Average loss: 2.3835 Iteration: 3959; Percent complete: 99.0%; Average loss: 2.6158 Iteration: 3960; Percent complete: 99.0%; Average loss: 2.6473 Iteration: 3961; Percent complete: 99.0%; Average loss: 2.6172 Iteration: 3962; Percent complete: 99.1%; Average loss: 2.8322 Iteration: 3963; Percent complete: 99.1%; Average loss: 2.6934 Iteration: 3964; Percent complete: 99.1%; Average loss: 2.5994 Iteration: 3965; Percent complete: 99.1%; Average loss: 2.7277 Iteration: 3966; Percent complete: 99.2%; Average loss: 2.6844 Iteration: 3967; Percent complete: 99.2%; Average loss: 2.8117 Iteration: 3968; Percent complete: 99.2%; Average loss: 2.4602 Iteration: 3969; Percent complete: 99.2%; Average loss: 2.4431 Iteration: 3970; Percent complete: 99.2%; Average loss: 2.5236 Iteration: 3971; Percent complete: 99.3%; Average loss: 2.8077 Iteration: 3972; Percent complete: 99.3%; Average loss: 2.7562 Iteration: 3973; Percent complete: 99.3%; Average loss: 2.7051 Iteration: 3974; Percent complete: 99.4%; Average loss: 2.5143 Iteration: 3975; Percent complete: 99.4%; Average loss: 2.9073 Iteration: 3976; Percent complete: 99.4%; Average loss: 2.6857 Iteration: 3977; Percent complete: 99.4%; Average loss: 2.7935 Iteration: 3978; Percent complete: 99.5%; Average loss: 2.5431 Iteration: 3979; Percent complete: 99.5%; Average loss: 2.5151 Iteration: 3980; Percent complete: 99.5%; Average loss: 2.3734 Iteration: 3981; Percent complete: 99.5%; Average loss: 2.6543 Iteration: 3982; Percent complete: 99.6%; Average loss: 2.3823 Iteration: 3983; Percent complete: 99.6%; Average loss: 2.6787 Iteration: 3984; Percent complete: 99.6%; Average loss: 2.5208 Iteration: 3985; Percent complete: 99.6%; Average loss: 2.5706 Iteration: 3986; Percent complete: 99.7%; Average loss: 2.8362 Iteration: 3987; Percent complete: 99.7%; Average loss: 2.3601 Iteration: 3988; Percent complete: 99.7%; Average loss: 2.7444 Iteration: 3989; Percent complete: 99.7%; Average loss: 2.6111 Iteration: 3990; Percent complete: 99.8%; Average loss: 2.4729 Iteration: 3991; Percent complete: 99.8%; Average loss: 2.7254 Iteration: 3992; Percent complete: 99.8%; Average loss: 2.6925 Iteration: 3993; Percent complete: 99.8%; Average loss: 2.6161 Iteration: 3994; Percent complete: 99.9%; Average loss: 2.7716 Iteration: 3995; Percent complete: 99.9%; Average loss: 2.5390 Iteration: 3996; Percent complete: 99.9%; Average loss: 2.6175 Iteration: 3997; Percent complete: 99.9%; Average loss: 2.4677 Iteration: 3998; Percent complete: 100.0%; Average loss: 2.7727 Iteration: 3999; Percent complete: 100.0%; Average loss: 2.6781 Iteration: 4000; Percent complete: 100.0%; Average loss: 2.9340 .. GENERATED FROM PYTHON SOURCE LINES 1341-1346 Run Evaluation ~~~~~~~~~~~~~~ To chat with your model, run the following block. .. GENERATED FROM PYTHON SOURCE LINES 1346-1358 .. code-block:: default # Set dropout layers to ``eval`` mode encoder.eval() decoder.eval() # Initialize search module searcher = GreedySearchDecoder(encoder, decoder) # Begin chatting (uncomment and run the following line to begin) # evaluateInput(encoder, decoder, searcher, voc) .. GENERATED FROM PYTHON SOURCE LINES 1359-1371 Conclusion ---------- That’s all for this one, folks. Congratulations, you now know the fundamentals to building a generative chatbot model! If you’re interested, you can try tailoring the chatbot’s behavior by tweaking the model and training parameters and customizing the data that you train the model on. Check out the other tutorials for more cool deep learning applications in PyTorch! .. rst-class:: sphx-glr-timing **Total running time of the script:** ( 5 minutes 51.952 seconds) .. _sphx_glr_download_beginner_chatbot_tutorial.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: chatbot_tutorial.py ` .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: chatbot_tutorial.ipynb ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_