Machine Learning for the Common Engineer with Google’s Tensorflow

After taking an online class from Stanford University on machine learning I’ve been playing with Google’s TensorFlow library. In the last five years graphic processors have increased in speed by a factor over 500; thus, machine learning algorithms once too complex for computers to execute in real-time are now commonplace.

In a nutshell machine learning and AI are using basic Calculus methods that have been understood well for decades. A machine learning neural network takes an n dimensional vector of inputs and outputs a y dimensional vector of outputs. The mapping of inputs to outputs can be described by a linear mapping, and then using some linear algebra to deduce derivatives and roots the coefficients of this mapping are found. In machine learning lingo a loss function, neural network weights, and epochs all correspond to common linear algebra and calculus I math terms. Any engineering college graduate should be able to understand basic machine learning models! Companies such as Google open-source their prediction models which can be downloaded for free off of Github.

As a proof of concept I decided to use TensorFlow to create a chatbot model. I found an article on Chatbots magazine to get me started. Get in touch if you have any ideas for applying machine learning at your company for my next project.

Here’s the conversational model. It’s basic and stateless.


{
"intents": [
{
"tag": "greeting",
"patterns": ["Hi", "How are you", "Is anyone there?", "Hello", "Good day"],
"responses": ["Would you like to watch a movie or tv show?"]
},
{
"tag": "goodbye",
"patterns": ["Bye", "See you later", "Goodbye"],
"responses": ["See you later, thanks for visiting", "Have a nice day", "Bye! Come back again soon."]
},
{
"tag": "thanks",
"patterns": ["Thanks", "Thank you", "That's helpful"],
"responses": ["Happy to help!", "Any time!", "My pleasure"]
},
{
"tag": "movies",
"patterns": ["Which movies do you have?", "What kinds of movies are there?", "Movies?", "Movie.", "I want to watch a movie.", "Watch movie." ],
"responses": ["Here's the movies list. We have Moana, Tarzan, and Frozen."]
},
{
"tag": "shows",
"patterns": ["Which shows do you have?", "What kinds of shows are there?", "Shows?", "Show.", "I want to watch a show.", "Watch show." ],
"responses": ["Here's the shows list. We have Sesame Street, Mickey Mouse Playhouse, and Puppy Dog pals."]
},
{
"tag": "play",
"patterns": ["Play movie", "Watch movie", "Play show", "Watch show" ],
"responses": ["Playing."]
},
{
"tag": "stop",
"patterns": ["Stop movie", "Stop show" ],
"responses": ["Stopping."]
}
]
}

Here’s the Python script to train the TensorFlow model. We use a four layer network with the two interior layers having 8 nodes fully connected. There are many variations on interior layers – this is what determines how accurate your machine learning model can predict outcomes. The common engineer doesn’t need to know these details – just download an open-sourced model from Google that has been designed by PhD level engineers.


# things we need for NLP
import nltk
from nltk.stem.lancaster import LancasterStemmer
stemmer = LancasterStemm()

# things we need for Tensorflow
import numpy as np
import tflearn
import tensorflow as tf
import random

# import our chat-bot intents file
import json
with open('intents.json') as json_data:
intents = json.load(json_data)

words = []
classes = []
documents = []
ignore_words = ['?']

# loop through each sentence in our intents patterns
for intent in intents['intents']:
for pattern in intent['patterns']:
# tokenize each word in the sentence
w = nltk.word_tokenize(pattern)
# add to our words list
words.extend(w)
# add to documents in our corpus
documents.append((w, intent['tag']))
# add to our classes list
if intent['tag'] not in classes:
classes.append(intent['tag'])

# stem and lower each word and remove duplicates
words = [stemmer.stem(w.lower()) for w in words if w not in ignore_words]
words = sorted(list(set(words)))

# remove duplicates
classes = sorted(list(set(classes)))

print (len(documents), "documents")
print (len(classes), "classes", classes)
print (len(words), "unique stemmed words", words)

# create our training data
training = []
output = []
# create an empty array for our output
output_empty = [0] * len(classes)

# training set, bag of words for each sentence
for doc in documents:
# initialize our bag of words
bag = []
# list of tokenized words for the pattern
pattern_words = doc[0]
# stem each word
pattern_words = [stemmer.stem(word.lower()) for word in pattern_words]
# create our bag of words array
for w in words:
bag.append(1) if w in pattern_words else bag.append(0)

# output is a '0' for each tag and '1' for current tag
output_row = list(output_empty)
output_row[classes.index(doc[1])] = 1

training.append([bag, output_row])

# shuffle our features and turn into np.array
random.shuffle(training)
training = np.array(training)

# create train and test lists
train_x = list(training[:,0])
train_y = list(training[:,1])

# reset underlying graph data
tf.reset_default_graph()

# Build neural network
net = tflearn.input_data(shape=[None, len(train_x[0])])
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, len(train_y[0]), activation='softmax')
net = tflearn.regression(net)

# Define model and setup tensorboard
model = tflearn.DNN(net, tensorboard_dir='tflearn_logs')

# Start training (apply gradient descent algorithm)
model.fit(train_x, train_y, n_epoch=1000, batch_size=8, show_metric=True)
model.save('model.tflearn')

# save all of our data structures
import pickle
pickle.dump( {'words':words, 'classes':classes, 'train_x':train_x, 'train_y':train_y}, open( "training_data", "wb" ) )

The output of the training script is a TensorFlow model that represents the weights of the network. Here’s the output of the training script:


(29, 'documents')
(7, 'classes', [u'goodbye', u'greeting', u'movies', u'play', u'shows', u'stop', u'thanks'])
(34, 'unique stemmed words', [u"'s", u'.', u'a', u'anyon', u'ar', u'bye', u'day', u'do', u'good', u'goodby', u'hav', u'hello', u'help', u'hi', u'how', u'i', u'is', u'kind', u'lat', u'movy', u'of', u'play', u'see', u'show', u'stop', u'thank', u'that', u'ther', u'to', u'want', u'watch', u'what', u'which', u'you'])
---------------------------------
Run id: R2VMXY
Log directory: tflearn_logs/
[?25l---------------------------------
Training samples: 29
Validation samples: 0
--
Training Step: 1 | time: 0.043s
[2K
| Adam | epoch: 001 | loss: 0.00000 - acc: 0.0000 -- iter: 08/29
[A[ATraining Step: 2 | total loss: [1m[32m1.75134[0m[0m | time: 0.046s
[2K
| Adam | epoch: 001 | loss: 1.75134 - acc: 0.0000 -- iter: 16/29
[A[ATraining Step: 3 | total loss: [1m[32m1.91036[0m[0m | time: 0.049s
[2K
| Adam | epoch: 001 | loss: 1.91036 - acc: 0.3068 -- iter: 24/29
[A[ATraining Step: 4 | total loss: [1m[32m1.93647[0m[0m | time: 0.052s
[2K
| Adam | epoch: 001 | loss: 1.93647 - acc: 0.2642 -- iter: 29/29
--
Training Step: 5 | total loss: [1m[32m1.94295[0m[0m | time: 0.003s
[2K
| Adam | epoch: 002 | loss: 1.94295 - acc: 0.2198 -- iter: 08/29
[A[ATraining Step: 6 | total loss: [1m[32m1.94457[0m[0m | time: 0.005s
[2K
| Adam | epoch: 002 | loss: 1.94457 - acc: 0.2071 -- iter: 16/29
[A[ATraining Step: 7 | total loss: [1m[32m1.94534[0m[0m | time: 0.007s
[2K
| Adam | epoch: 002 | loss: 1.94534 - acc: 0.1578 -- iter: 24/29
[A[ATraining Step: 8 | total loss: [1m[32m1.94527[0m[0m | time: 0.009s
[2K
| Adam | epoch: 002 | loss: 1.94527 - acc: 0.2097 -- iter: 29/29
--
Training Step: 9 | total loss: [1m[32m1.94467[0m[0m | time: 0.003s
[2K
| Adam | epoch: 003 | loss: 1.94467 - acc: 0.2310 -- iter: 08/29
[A[ATraining Step: 10 | total loss: [1m[32m1.94431[0m[0m | time: 0.006s
[2K
| Adam | epoch: 003 | loss: 1.94431 - acc: 0.2155 -- iter: 16/29
[A[ATraining Step: 11 | total loss: [1m[32m1.94389[0m[0m | time: 0.010s
[2K
| Adam | epoch: 003 | loss: 1.94389 - acc: 0.2082 -- iter: 24/29
[A[ATraining Step: 12 | total loss: [1m[32m1.94586[0m[0m | time: 0.012s
[2K
| Adam | epoch: 003 | loss: 1.94586 - acc: 0.1707 -- iter: 29/29
--
Training Step: 13 | total loss: [1m[32m1.94322[0m[0m | time: 0.004s
[2K
| Adam | epoch: 004 | loss: 1.94322 - acc: 0.2583 -- iter: 08/29
[A[ATraining Step: 14 | total loss: [1m[32m1.94433[0m[0m | time: 0.007s
[2K
| Adam | epoch: 004 | loss: 1.94433 - acc: 0.2038 -- iter: 16/29
[A[ATraining Step: 15 | total loss: [1m[32m1.94503[0m[0m | time: 0.011s
[2K
| Adam | epoch: 004 | loss: 1.94503 - acc: 0.2023 -- iter: 24/29
[A[ATraining Step: 16 | total loss: [1m[32m1.94544[0m[0m | time: 0.015s
[2K
| Adam | epoch: 004 | loss: 1.94544 - acc: 0.2014 -- iter: 29/29
--
Training Step: 17 | total loss: [1m[32m1.94432[0m[0m | time: 0.005s
[2K
| Adam | epoch: 005 | loss: 1.94432 - acc: 0.1739 -- iter: 08/29
[A[ATraining Step: 18 | total loss: [1m[32m1.94286[0m[0m | time: 0.009s
[2K
| Adam | epoch: 005 | loss: 1.94286 - acc: 0.2435 -- iter: 16/29
[A[ATraining Step: 19 | total loss: [1m[32m1.94371[0m[0m | time: 0.013s
[2K
| Adam | epoch: 005 | loss: 1.94371 - acc: 0.2040 -- iter: 24/29
[A[ATraining Step: 20 | total loss: [1m[32m1.94448[0m[0m | time: 0.015s
[2K
| Adam | epoch: 005 | loss: 1.94448 - acc: 0.2027 -- iter: 29/29
--
Training Step: 21 | total loss: [1m[32m1.94498[0m[0m | time: 0.003s
[2K
| Adam | epoch: 006 | loss: 1.94498 - acc: 0.2019 -- iter: 08/29
[A[ATraining Step: 22 | total loss: [1m[32m1.94384[0m[0m | time: 0.005s
[2K
| Adam | epoch: 006 | loss: 1.94384 - acc: 0.1788 -- iter: 16/29
[A[ATraining Step: 23 | total loss: [1m[32m1.94230[0m[0m | time: 0.007s
[2K
| Adam | epoch: 006 | loss: 1.94230 - acc: 0.2358 -- iter: 24/29
[A[ATraining Step: 24 | total loss: [1m[32m1.94306[0m[0m | time: 0.010s
[2K
| Adam | epoch: 006 | loss: 1.94306 - acc: 0.2046 -- iter: 29/29
--
Training Step: 25 | total loss: [1m[32m1.94383[0m[0m | time: 0.003s
[2K
| Adam | epoch: 007 | loss: 1.94383 - acc: 0.2034 -- iter: 08/29
[A[ATraining Step: 26 | total loss: [1m[32m1.94434[0m[0m | time: 0.006s
[2K
| Adam | epoch: 007 | loss: 1.94434 - acc: 0.2025 -- iter: 16/29
[A[ATraining Step: 27 | total loss: [1m[32m1.94324[0m[0m | time: 0.008s
[2K
| Adam | epoch: 007 | loss: 1.94324 - acc: 0.1825 -- iter: 24/29
[A[ATraining Step: 28 | total loss: [1m[32m1.94157[0m[0m | time: 0.012s
[2K
| Adam | epoch: 007 | loss: 1.94157 - acc: 0.2307 -- iter: 29/29
--
Training Step: 29 | total loss: [1m[32m1.94230[0m[0m | time: 0.005s
[2K
| Adam | epoch: 008 | loss: 1.94230 - acc: 0.2050 -- iter: 08/29
[A[ATraining Step: 30 | total loss: [1m[32m1.94303[0m[0m | time: 0.008s
[2K
| Adam | epoch: 008 | loss: 1.94303 - acc: 0.2038 -- iter: 16/29
[A[ATraining Step: 31 | total loss: [1m[32m1.94354[0m[0m | time: 0.012s
[2K
| Adam | epoch: 008 | loss: 1.94354 - acc: 0.2029 -- iter: 24/29
[A[ATraining Step: 32 | total loss: [1m[32m1.94243[0m[0m | time: 0.015s
[2K
| Adam | epoch: 008 | loss: 1.94243 - acc: 0.1854 -- iter: 29/29
--
Training Step: 33 | total loss: [1m[32m1.94059[0m[0m | time: 0.005s
[2K
| Adam | epoch: 009 | loss: 1.94059 - acc: 0.2270 -- iter: 08/29
[A[ATraining Step: 34 | total loss: [1m[32m1.94132[0m[0m | time: 0.009s
[2K
| Adam | epoch: 009 | loss: 1.94132 - acc: 0.2051 -- iter: 16/29
[A[ATraining Step: 35 | total loss: [1m[32m1.94201[0m[0m | time: 0.012s
[2K
| Adam | epoch: 009 | loss: 1.94201 - acc: 0.2041 -- iter: 24/29
[A[ATraining Step: 36 | total loss: [1m[32m1.94060[0m[0m | time: 0.014s
[2K
| Adam | epoch: 009 | loss: 1.94060 - acc: 0.2441 -- iter: 29/29
--
Training Step: 37 | total loss: [1m[32m1.93992[0m[0m | time: 0.002s
[2K
| Adam | epoch: 010 | loss: 1.93992 - acc: 0.2203 -- iter: 08/29
[A[ATraining Step: 38 | total loss: [1m[32m1.94212[0m[0m | time: 0.005s
[2K
| Adam | epoch: 010 | loss: 1.94212 - acc: 0.1772 -- iter: 16/29
[A[ATraining Step: 39 | total loss: [1m[32m1.93864[0m[0m | time: 0.008s
[2K
| Adam | epoch: 010 | loss: 1.93864 - acc: 0.2390 -- iter: 24/29
[A[ATraining Step: 40 | total loss: [1m[32m1.94264[0m[0m | time: 0.010s
[2K
| Adam | epoch: 010 | loss: 1.94264 - acc: 0.1942 -- iter: 29/29
--
Training Step: 41 | total loss: [1m[32m1.94581[0m[0m | time: 0.002s
[2K
| Adam | epoch: 011 | loss: 1.94581 - acc: 0.1585 -- iter: 08/29
[A[ATraining Step: 42 | total loss: [1m[32m1.94349[0m[0m | time: 0.005s
[2K
| Adam | epoch: 011 | loss: 1.94349 - acc: 0.1750 -- iter: 16/29
[A[ATraining Step: 43 | total loss: [1m[32m1.94285[0m[0m | time: 0.007s
[2K
| Adam | epoch: 011 | loss: 1.94285 - acc: 0.1441 -- iter: 24/29
[A[ATraining Step: 44 | total loss: [1m[32m1.94207[0m[0m | time: 0.010s
[2K
| Adam | epoch: 011 | loss: 1.94207 - acc: 0.1408 -- iter: 29/29
--
Training Step: 45 | total loss: [1m[32m1.94333[0m[0m | time: 0.003s
[2K
| Adam | epoch: 012 | loss: 1.94333 - acc: 0.1169 -- iter: 08/29
[A[ATraining Step: 46 | total loss: [1m[32m1.94428[0m[0m | time: 0.007s
[2K
| Adam | epoch: 012 | loss: 1.94428 - acc: 0.0974 -- iter: 16/29
[A[ATraining Step: 47 | total loss: [1m[32m1.94074[0m[0m | time: 0.010s
[2K
| Adam | epoch: 012 | loss: 1.94074 - acc: 0.1428 -- iter: 24/29
[A[ATraining Step: 48 | total loss: [1m[32m1.93932[0m[0m | time: 0.013s
[2K
| Adam | epoch: 012 | loss: 1.93932 - acc: 0.1601 -- iter: 29/29
--
Training Step: 49 | total loss: [1m[32m1.93838[0m[0m | time: 0.004s
[2K
| Adam | epoch: 013 | loss: 1.93838 - acc: 0.1743 -- iter: 08/29
[A[ATraining Step: 50 | total loss: [1m[32m1.93453[0m[0m | time: 0.008s
[2K
| Adam | epoch: 013 | loss: 1.93453 - acc: 0.2093 -- iter: 16/29
[A[ATraining Step: 51 | total loss: [1m[32m1.93103[0m[0m | time: 0.011s
[2K
| Adam | epoch: 013 | loss: 1.93103 - acc: 0.2384 -- iter: 24/29
[A[ATraining Step: 52 | total loss: [1m[32m1.93264[0m[0m | time: 0.013s
[2K
| Adam | epoch: 013 | loss: 1.93264 - acc: 0.2214 -- iter: 29/29
--
Training Step: 53 | total loss: [1m[32m1.93184[0m[0m | time: 0.002s
[2K
| Adam | epoch: 014 | loss: 1.93184 - acc: 0.2072 -- iter: 08/29
[A[ATraining Step: 54 | total loss: [1m[32m1.93205[0m[0m | time: 0.006s
[2K
| Adam | epoch: 014 | loss: 1.93205 - acc: 0.1952 -- iter: 16/29
[A[ATraining Step: 55 | total loss: [1m[32m1.93254[0m[0m | time: 0.009s
[2K
| Adam | epoch: 014 | loss: 1.93254 - acc: 0.1959 -- iter: 24/29
[A[ATraining Step: 56 | total loss: [1m[32m1.93282[0m[0m | time: 0.013s
[2K
| Adam | epoch: 014 | loss: 1.93282 - acc: 0.1965 -- iter: 29/29
--
Training Step: 57 | total loss: [1m[32m1.92793[0m[0m | time: 0.003s
[2K
| Adam | epoch: 015 | loss: 1.92793 - acc: 0.2212 -- iter: 08/29
[A[ATraining Step: 58 | total loss: [1m[32m1.92878[0m[0m | time: 0.006s
[2K
| Adam | epoch: 015 | loss: 1.92878 - acc: 0.2081 -- iter: 16/29
[A[ATraining Step: 59 | total loss: [1m[32m1.92673[0m[0m | time: 0.009s
[2K
| Adam | epoch: 015 | loss: 1.92673 - acc: 0.2137 -- iter: 24/29
[A[ATraining Step: 60 | total loss: [1m[32m1.92648[0m[0m | time: 0.011s
[2K
| Adam | epoch: 015 | loss: 1.92648 - acc: 0.2119 -- iter: 29/29
--
Training Step: 61 | total loss: [1m[32m1.92611[0m[0m | time: 0.002s
[2K
| Adam | epoch: 016 | loss: 1.92611 - acc: 0.2103 -- iter: 08/29
[A[ATraining Step: 62 | total loss: [1m[32m1.92520[0m[0m | time: 0.005s
[2K
| Adam | epoch: 016 | loss: 1.92520 - acc: 0.1994 -- iter: 16/29
[A[ATraining Step: 63 | total loss: [1m[32m1.92388[0m[0m | time: 0.008s
[2K
| Adam | epoch: 016 | loss: 1.92388 - acc: 0.2058 -- iter: 24/29
[A[ATraining Step: 64 | total loss: [1m[32m1.92055[0m[0m | time: 0.011s
[2K
| Adam | epoch: 016 | loss: 1.92055 - acc: 0.2269 -- iter: 29/29
--
Training Step: 65 | total loss: [1m[32m1.92175[0m[0m | time: 0.003s
[2K
| Adam | epoch: 017 | loss: 1.92175 - acc: 0.1990 -- iter: 08/29
[A[ATraining Step: 66 | total loss: [1m[32m1.92262[0m[0m | time: 0.005s
[2K
| Adam | epoch: 017 | loss: 1.92262 - acc: 0.1748 -- iter: 16/29
[A[ATraining Step: 67 | total loss: [1m[32m1.92213[0m[0m | time: 0.009s
[2K
| Adam | epoch: 017 | loss: 1.92213 - acc: 0.1688 -- iter: 24/29
[A[ATraining Step: 68 | total loss: [1m[32m1.91849[0m[0m | time: 0.011s
[2K
| Adam | epoch: 017 | loss: 1.91849 - acc: 0.1784 -- iter: 29/29
--
Training Step: 69 | total loss: [1m[32m1.91463[0m[0m | time: 0.002s
[2K
| Adam | epoch: 018 | loss: 1.91463 - acc: 0.1722 -- iter: 08/29
[A[ATraining Step: 70 | total loss: [1m[32m1.91716[0m[0m | time: 0.003s
[2K
| Adam | epoch: 018 | loss: 1.91716 - acc: 0.1754 -- iter: 16/29
[A[ATraining Step: 71 | total loss: [1m[32m1.91929[0m[0m | time: 0.005s
[2K
| Adam | epoch: 018 | loss: 1.91929 - acc: 0.1782 -- iter: 24/29
[A[ATraining Step: 72 | total loss: [1m[32m1.91629[0m[0m | time: 0.006s
[2K
| Adam | epoch: 018 | loss: 1.91629 - acc: 0.1722 -- iter: 29/29
--
Training Step: 73 | total loss: [1m[32m1.91257[0m[0m | time: 0.001s
[2K
| Adam | epoch: 019 | loss: 1.91257 - acc: 0.1947 -- iter: 08/29
[A[ATraining Step: 74 | total loss: [1m[32m1.91254[0m[0m | time: 0.003s
[2K
| Adam | epoch: 019 | loss: 1.91254 - acc: 0.1734 -- iter: 16/29
[A[ATraining Step: 75 | total loss: [1m[32m1.91452[0m[0m | time: 0.004s
[2K
| Adam | epoch: 019 | loss: 1.91452 - acc: 0.1762 -- iter: 24/29
[A[ATraining Step: 76 | total loss: [1m[32m1.91616[0m[0m | time: 0.007s
[2K
| Adam | epoch: 019 | loss: 1.91616 - acc: 0.1788 -- iter: 29/29
--
Training Step: 77 | total loss: [1m[32m1.91173[0m[0m | time: 0.004s
[2K
| Adam | epoch: 020 | loss: 1.91173 - acc: 0.1731 -- iter: 08/29
[A[ATraining Step: 78 | total loss: [1m[32m1.90241[0m[0m | time: 0.007s
[2K
| Adam | epoch: 020 | loss: 1.90241 - acc: 0.2073 -- iter: 16/29
[A[ATraining Step: 79 | total loss: [1m[32m1.89913[0m[0m | time: 0.011s
[2K
| Adam | epoch: 020 | loss: 1.89913 - acc: 0.2117 -- iter: 24/29
[A[ATraining Step: 80 | total loss: [1m[32m1.90080[0m[0m | time: 0.014s
[2K
| Adam | epoch: 020 | loss: 1.90080 - acc: 0.2105 -- iter: 29/29
--
Training Step: 81 | total loss: [1m[32m1.90211[0m[0m | time: 0.004s
[2K
| Adam | epoch: 021 | loss: 1.90211 - acc: 0.2095 -- iter: 08/29
[A[ATraining Step: 82 | total loss: [1m[32m1.89812[0m[0m | time: 0.008s
[2K
| Adam | epoch: 021 | loss: 1.89812 - acc: 0.2135 -- iter: 16/29
[A[ATraining Step: 83 | total loss: [1m[32m1.89164[0m[0m | time: 0.011s
[2K
| Adam | epoch: 021 | loss: 1.89164 - acc: 0.2047 -- iter: 24/29
[A[ATraining Step: 84 | total loss: [1m[32m1.89205[0m[0m | time: 0.015s
[2K
| Adam | epoch: 021 | loss: 1.89205 - acc: 0.2092 -- iter: 29/29
--
Training Step: 85 | total loss: [1m[32m1.88655[0m[0m | time: 0.003s
[2K
| Adam | epoch: 022 | loss: 1.88655 - acc: 0.2283 -- iter: 08/29
[A[ATraining Step: 86 | total loss: [1m[32m1.88106[0m[0m | time: 0.006s
[2K
| Adam | epoch: 022 | loss: 1.88106 - acc: 0.2454 -- iter: 16/29
[A[ATraining Step: 87 | total loss: [1m[32m1.87374[0m[0m | time: 0.009s
[2K
| Adam | epoch: 022 | loss: 1.87374 - acc: 0.2584 -- iter: 24/29
[A[ATraining Step: 88 | total loss: [1m[32m1.87099[0m[0m | time: 0.012s
[2K
| Adam | epoch: 022 | loss: 1.87099 - acc: 0.2326 -- iter: 29/29
--
Training Step: 89 | total loss: [1m[32m1.86359[0m[0m | time: 0.003s
[2K
| Adam | epoch: 023 | loss: 1.86359 - acc: 0.2468 -- iter: 08/29
[A[ATraining Step: 90 | total loss: [1m[32m1.86616[0m[0m | time: 0.006s
[2K
| Adam | epoch: 023 | loss: 1.86616 - acc: 0.2621 -- iter: 16/29
[A[ATraining Step: 91 | total loss: [1m[32m1.86818[0m[0m | time: 0.009s
[2K
| Adam | epoch: 023 | loss: 1.86818 - acc: 0.2759 -- iter: 24/29
[A[ATraining Step: 92 | total loss: [1m[32m1.87408[0m[0m | time: 0.012s
[2K
| Adam | epoch: 023 | loss: 1.87408 - acc: 0.2483 -- iter: 29/29
--
Training Step: 93 | total loss: [1m[32m1.85791[0m[0m | time: 0.003s
[2K
| Adam | epoch: 024 | loss: 1.85791 - acc: 0.2485 -- iter: 08/29
[A[ATraining Step: 94 | total loss: [1m[32m1.84726[0m[0m | time: 0.005s
[2K
| Adam | epoch: 024 | loss: 1.84726 - acc: 0.2486 -- iter: 16/29
[A[ATraining Step: 95 | total loss: [1m[32m1.85894[0m[0m | time: 0.008s
[2K
| Adam | epoch: 024 | loss: 1.85894 - acc: 0.2438 -- iter: 24/29
[A[ATraining Step: 96 | total loss: [1m[32m1.86941[0m[0m | time: 0.010s
[2K
| Adam | epoch: 024 | loss: 1.86941 - acc: 0.2394 -- iter: 29/29
--
Training Step: 97 | total loss: [1m[32m1.86061[0m[0m | time: 0.004s
[2K
| Adam | epoch: 025 | loss: 1.86061 - acc: 0.2405 -- iter: 08/29
[A[ATraining Step: 98 | total loss: [1m[32m1.85211[0m[0m | time: 0.006s
[2K
| Adam | epoch: 025 | loss: 1.85211 - acc: 0.2414 -- iter: 16/29
[A[ATraining Step: 99 | total loss: [1m[32m1.84625[0m[0m | time: 0.009s
[2K
| Adam | epoch: 025 | loss: 1.84625 - acc: 0.2298 -- iter: 24/29
[A[ATraining Step: 100 | total loss: [1m[32m1.81933[0m[0m | time: 0.022s
[2K
| Adam | epoch: 025 | loss: 1.81933 - acc: 0.2668 -- iter: 29/29
--
Training Step: 101 | total loss: [1m[32m1.79388[0m[0m | time: 0.003s
[2K
| Adam | epoch: 026 | loss: 1.79388 - acc: 0.3001 -- iter: 08/29
[A[ATraining Step: 102 | total loss: [1m[32m1.80373[0m[0m | time: 0.006s
[2K
| Adam | epoch: 026 | loss: 1.80373 - acc: 0.2826 -- iter: 16/29
[A[ATraining Step: 103 | total loss: [1m[32m1.80203[0m[0m | time: 0.009s
[2K
| Adam | epoch: 026 | loss: 1.80203 - acc: 0.2793 -- iter: 24/29
[A[ATraining Step: 104 | total loss: [1m[32m1.79236[0m[0m | time: 0.012s
[2K
| Adam | epoch: 026 | loss: 1.79236 - acc: 0.2764 -- iter: 29/29
--
Training Step: 105 | total loss: [1m[32m1.79094[0m[0m | time: 0.002s
[2K
| Adam | epoch: 027 | loss: 1.79094 - acc: 0.2688 -- iter: 08/29
[A[ATraining Step: 106 | total loss: [1m[32m1.78914[0m[0m | time: 0.005s
[2K
| Adam | epoch: 027 | loss: 1.78914 - acc: 0.2619 -- iter: 16/29
[A[ATraining Step: 107 | total loss: [1m[32m1.78310[0m[0m | time: 0.007s
[2K
| Adam | epoch: 027 | loss: 1.78310 - acc: 0.2607 -- iter: 24/29
[A[ATraining Step: 108 | total loss: [1m[32m1.78600[0m[0m | time: 0.010s
[2K
| Adam | epoch: 027 | loss: 1.78600 - acc: 0.2721 -- iter: 29/29
--
Training Step: 109 | total loss: [1m[32m1.78108[0m[0m | time: 0.003s
[2K
| Adam | epoch: 028 | loss: 1.78108 - acc: 0.2824 -- iter: 08/29
[A[ATraining Step: 110 | total loss: [1m[32m1.76966[0m[0m | time: 0.005s
[2K
| Adam | epoch: 028 | loss: 1.76966 - acc: 0.2742 -- iter: 16/29
[A[ATraining Step: 111 | total loss: [1m[32m1.75867[0m[0m | time: 0.008s
[2K
| Adam | epoch: 028 | loss: 1.75867 - acc: 0.2668 -- iter: 24/29
[A[ATraining Step: 112 | total loss: [1m[32m1.75513[0m[0m | time: 0.011s
[2K
| Adam | epoch: 028 | loss: 1.75513 - acc: 0.2526 -- iter: 29/29
--
Training Step: 113 | total loss: [1m[32m1.75498[0m[0m | time: 0.003s
[2K
| Adam | epoch: 029 | loss: 1.75498 - acc: 0.2648 -- iter: 08/29
[A[ATraining Step: 114 | total loss: [1m[32m1.74605[0m[0m | time: 0.007s
[2K
| Adam | epoch: 029 | loss: 1.74605 - acc: 0.2508 -- iter: 16/29
[A[ATraining Step: 115 | total loss: [1m[32m1.74852[0m[0m | time: 0.010s
[2K
| Adam | epoch: 029 | loss: 1.74852 - acc: 0.2458 -- iter: 24/29
[A[ATraining Step: 116 | total loss: [1m[32m1.75034[0m[0m | time: 0.013s
[2K
| Adam | epoch: 029 | loss: 1.75034 - acc: 0.2412 -- iter: 29/29
--
Training Step: 117 | total loss: [1m[32m1.75133[0m[0m | time: 0.003s
[2K
| Adam | epoch: 030 | loss: 1.75133 - acc: 0.2546 -- iter: 08/29
[A[ATraining Step: 118 | total loss: [1m[32m1.73893[0m[0m | time: 0.008s
[2K
| Adam | epoch: 030 | loss: 1.73893 - acc: 0.2666 -- iter: 16/29
[A[ATraining Step: 119 | total loss: [1m[32m1.73175[0m[0m | time: 0.011s
[2K
| Adam | epoch: 030 | loss: 1.73175 - acc: 0.2649 -- iter: 24/29
[A[ATraining Step: 120 | total loss: [1m[32m1.72076[0m[0m | time: 0.015s
[2K
| Adam | epoch: 030 | loss: 1.72076 - acc: 0.2585 -- iter: 29/29
--
Training Step: 121 | total loss: [1m[32m1.72076[0m[0m | time: 0.004s
[2K
| Adam | epoch: 031 | loss: 1.72076 - acc: 0.2526 -- iter: 08/29
[A[ATraining Step: 122 | total loss: [1m[32m1.73120[0m[0m | time: 0.007s
[2K
| Adam | epoch: 031 | loss: 1.73120 - acc: 0.2523 -- iter: 16/29
[A[ATraining Step: 123 | total loss: [1m[32m1.71077[0m[0m | time: 0.010s
[2K
| Adam | epoch: 031 | loss: 1.71077 - acc: 0.2646 -- iter: 24/29
[A[ATraining Step: 124 | total loss: [1m[32m1.68690[0m[0m | time: 0.022s
[2K
| Adam | epoch: 031 | loss: 1.68690 - acc: 0.2757 -- iter: 29/29
--
Training Step: 125 | total loss: [1m[32m1.67434[0m[0m | time: 0.003s
[2K
| Adam | epoch: 032 | loss: 1.67434 - acc: 0.2681 -- iter: 08/29
[A[ATraining Step: 126 | total loss: [1m[32m1.66227[0m[0m | time: 0.005s
[2K
| Adam | epoch: 032 | loss: 1.66227 - acc: 0.2613 -- iter: 16/29
[A[ATraining Step: 127 | total loss: [1m[32m1.67363[0m[0m | time: 0.009s
[2K
| Adam | epoch: 032 | loss: 1.67363 - acc: 0.2601 -- iter: 24/29
[A[ATraining Step: 128 | total loss: [1m[32m1.68338[0m[0m | time: 0.012s
[2K
| Adam | epoch: 032 | loss: 1.68338 - acc: 0.2591 -- iter: 29/29
--
Training Step: 129 | total loss: [1m[32m1.66671[0m[0m | time: 0.003s
[2K
| Adam | epoch: 033 | loss: 1.66671 - acc: 0.2582 -- iter: 08/29
[A[ATraining Step: 130 | total loss: [1m[32m1.65812[0m[0m | time: 0.006s
[2K
| Adam | epoch: 033 | loss: 1.65812 - acc: 0.2724 -- iter: 16/29
[A[ATraining Step: 131 | total loss: [1m[32m1.64991[0m[0m | time: 0.008s
[2K
| Adam | epoch: 033 | loss: 1.64991 - acc: 0.2852 -- iter: 24/29
[A[ATraining Step: 132 | total loss: [1m[32m1.65012[0m[0m | time: 0.011s
[2K
| Adam | epoch: 033 | loss: 1.65012 - acc: 0.2691 -- iter: 29/29
--
Training Step: 133 | total loss: [1m[32m1.65952[0m[0m | time: 0.003s
[2K
| Adam | epoch: 034 | loss: 1.65952 - acc: 0.2922 -- iter: 08/29
[A[ATraining Step: 134 | total loss: [1m[32m1.66788[0m[0m | time: 0.005s
[2K
| Adam | epoch: 034 | loss: 1.66788 - acc: 0.2880 -- iter: 16/29
[A[ATraining Step: 135 | total loss: [1m[32m1.68099[0m[0m | time: 0.008s
[2K
| Adam | epoch: 034 | loss: 1.68099 - acc: 0.2592 -- iter: 24/29
[A[ATraining Step: 136 | total loss: [1m[32m1.69246[0m[0m | time: 0.011s
[2K
| Adam | epoch: 034 | loss: 1.69246 - acc: 0.2333 -- iter: 29/29
--
Training Step: 137 | total loss: [1m[32m1.68566[0m[0m | time: 0.002s
[2K
| Adam | epoch: 035 | loss: 1.68566 - acc: 0.2225 -- iter: 08/29
[A[ATraining Step: 138 | total loss: [1m[32m1.64971[0m[0m | time: 0.005s
[2K
| Adam | epoch: 035 | loss: 1.64971 - acc: 0.2627 -- iter: 16/29
[A[ATraining Step: 139 | total loss: [1m[32m1.64407[0m[0m | time: 0.007s
[2K
| Adam | epoch: 035 | loss: 1.64407 - acc: 0.2739 -- iter: 24/29
[A[ATraining Step: 140 | total loss: [1m[32m1.65908[0m[0m | time: 0.010s
[2K
| Adam | epoch: 035 | loss: 1.65908 - acc: 0.2465 -- iter: 29/29
--
Training Step: 141 | total loss: [1m[32m1.67234[0m[0m | time: 0.002s
[2K
| Adam | epoch: 036 | loss: 1.67234 - acc: 0.2219 -- iter: 08/29
[A[ATraining Step: 142 | total loss: [1m[32m1.67136[0m[0m | time: 0.005s
[2K
| Adam | epoch: 036 | loss: 1.67136 - acc: 0.2372 -- iter: 16/29
[A[ATraining Step: 143 | total loss: [1m[32m1.64125[0m[0m | time: 0.008s
[2K
| Adam | epoch: 036 | loss: 1.64125 - acc: 0.2510 -- iter: 24/29
[A[ATraining Step: 144 | total loss: [1m[32m1.64122[0m[0m | time: 0.010s
[2K
| Adam | epoch: 036 | loss: 1.64122 - acc: 0.2384 -- iter: 29/29
--
Training Step: 145 | total loss: [1m[32m1.62684[0m[0m | time: 0.003s
[2K
| Adam | epoch: 037 | loss: 1.62684 - acc: 0.2545 -- iter: 08/29
[A[ATraining Step: 146 | total loss: [1m[32m1.61338[0m[0m | time: 0.005s
[2K
| Adam | epoch: 037 | loss: 1.61338 - acc: 0.2691 -- iter: 16/29
[A[ATraining Step: 147 | total loss: [1m[32m1.59857[0m[0m | time: 0.008s
[2K
| Adam | epoch: 037 | loss: 1.59857 - acc: 0.2797 -- iter: 24/29
[A[ATraining Step: 148 | total loss: [1m[32m1.60227[0m[0m | time: 0.010s
[2K
| Adam | epoch: 037 | loss: 1.60227 - acc: 0.2767 -- iter: 29/29
--
Training Step: 149 | total loss: [1m[32m1.60780[0m[0m | time: 0.003s
[2K
| Adam | epoch: 038 | loss: 1.60780 - acc: 0.2865 -- iter: 08/29
[A[ATraining Step: 150 | total loss: [1m[32m1.59567[0m[0m | time: 0.005s
[2K
| Adam | epoch: 038 | loss: 1.59567 - acc: 0.2579 -- iter: 16/29
[A[ATraining Step: 151 | total loss: [1m[32m1.58403[0m[0m | time: 0.008s
[2K
| Adam | epoch: 038 | loss: 1.58403 - acc: 0.2321 -- iter: 24/29
[A[ATraining Step: 152 | total loss: [1m[32m1.58954[0m[0m | time: 0.010s
[2K
| Adam | epoch: 038 | loss: 1.58954 - acc: 0.2589 -- iter: 29/29
--
Training Step: 153 | total loss: [1m[32m1.56935[0m[0m | time: 0.003s
[2K
| Adam | epoch: 039 | loss: 1.56935 - acc: 0.2580 -- iter: 08/29
[A[ATraining Step: 154 | total loss: [1m[32m1.55330[0m[0m | time: 0.008s
[2K
| Adam | epoch: 039 | loss: 1.55330 - acc: 0.2697 -- iter: 16/29
[A[ATraining Step: 155 | total loss: [1m[32m1.56306[0m[0m | time: 0.011s
[2K
| Adam | epoch: 039 | loss: 1.56306 - acc: 0.2827 -- iter: 24/29
[A[ATraining Step: 156 | total loss: [1m[32m1.57116[0m[0m | time: 0.013s
[2K
| Adam | epoch: 039 | loss: 1.57116 - acc: 0.2945 -- iter: 29/29
--
Training Step: 157 | total loss: [1m[32m1.57694[0m[0m | time: 0.003s
[2K
| Adam | epoch: 040 | loss: 1.57694 - acc: 0.2900 -- iter: 08/29
[A[ATraining Step: 158 | total loss: [1m[32m1.56635[0m[0m | time: 0.006s
[2K
| Adam | epoch: 040 | loss: 1.56635 - acc: 0.2860 -- iter: 16/29
[A[ATraining Step: 159 | total loss: [1m[32m1.56713[0m[0m | time: 0.010s
[2K
| Adam | epoch: 040 | loss: 1.56713 - acc: 0.2824 -- iter: 24/29
[A[ATraining Step: 160 | total loss: [1m[32m1.53632[0m[0m | time: 0.013s
[2K
| Adam | epoch: 040 | loss: 1.53632 - acc: 0.3142 -- iter: 29/29
--
Training Step: 161 | total loss: [1m[32m1.50818[0m[0m | time: 0.003s
[2K
| Adam | epoch: 041 | loss: 1.50818 - acc: 0.3228 -- iter: 08/29
[A[ATraining Step: 162 | total loss: [1m[32m1.51395[0m[0m | time: 0.007s
[2K
| Adam | epoch: 041 | loss: 1.51395 - acc: 0.3280 -- iter: 16/29
[A[ATraining Step: 163 | total loss: [1m[32m1.51668[0m[0m | time: 0.011s
[2K
| Adam | epoch: 041 | loss: 1.51668 - acc: 0.3077 -- iter: 24/29
[A[ATraining Step: 164 | total loss: [1m[32m1.53522[0m[0m | time: 0.014s
[2K
| Adam | epoch: 041 | loss: 1.53522 - acc: 0.3019 -- iter: 29/29
--
Training Step: 165 | total loss: [1m[32m1.54491[0m[0m | time: 0.003s
[2K
| Adam | epoch: 042 | loss: 1.54491 - acc: 0.2917 -- iter: 08/29
[A[ATraining Step: 166 | total loss: [1m[32m1.55311[0m[0m | time: 0.007s
[2K
| Adam | epoch: 042 | loss: 1.55311 - acc: 0.2825 -- iter: 16/29
[A[ATraining Step: 167 | total loss: [1m[32m1.52345[0m[0m | time: 0.010s
[2K
| Adam | epoch: 042 | loss: 1.52345 - acc: 0.2918 -- iter: 24/29
[A[ATraining Step: 168 | total loss: [1m[32m1.51292[0m[0m | time: 0.013s
[2K
| Adam | epoch: 042 | loss: 1.51292 - acc: 0.3126 -- iter: 29/29
--
Training Step: 169 | total loss: [1m[32m1.51416[0m[0m | time: 0.003s
[2K
| Adam | epoch: 043 | loss: 1.51416 - acc: 0.3189 -- iter: 08/29
[A[ATraining Step: 170 | total loss: [1m[32m1.50007[0m[0m | time: 0.007s
[2K
| Adam | epoch: 043 | loss: 1.50007 - acc: 0.3270 -- iter: 16/29
[A[ATraining Step: 171 | total loss: [1m[32m1.48701[0m[0m | time: 0.011s
[2K
| Adam | epoch: 043 | loss: 1.48701 - acc: 0.3343 -- iter: 24/29
[A[ATraining Step: 172 | total loss: [1m[32m1.50017[0m[0m | time: 0.014s
[2K
| Adam | epoch: 043 | loss: 1.50017 - acc: 0.3133 -- iter: 29/29
--
Training Step: 173 | total loss: [1m[32m1.48315[0m[0m | time: 0.003s
[2K
| Adam | epoch: 044 | loss: 1.48315 - acc: 0.3195 -- iter: 08/29
[A[ATraining Step: 174 | total loss: [1m[32m1.49202[0m[0m | time: 0.007s
[2K
| Adam | epoch: 044 | loss: 1.49202 - acc: 0.3126 -- iter: 16/29
[A[ATraining Step: 175 | total loss: [1m[32m1.50333[0m[0m | time: 0.010s
[2K
| Adam | epoch: 044 | loss: 1.50333 - acc: 0.3013 -- iter: 24/29
[A[ATraining Step: 176 | total loss: [1m[32m1.51324[0m[0m | time: 0.013s
[2K
| Adam | epoch: 044 | loss: 1.51324 - acc: 0.2912 -- iter: 29/29
--
Training Step: 177 | total loss: [1m[32m1.49359[0m[0m | time: 0.003s
[2K
| Adam | epoch: 045 | loss: 1.49359 - acc: 0.3121 -- iter: 08/29
[A[ATraining Step: 178 | total loss: [1m[32m1.48213[0m[0m | time: 0.007s
[2K
| Adam | epoch: 045 | loss: 1.48213 - acc: 0.3183 -- iter: 16/29
[A[ATraining Step: 179 | total loss: [1m[32m1.47550[0m[0m | time: 0.010s
[2K
| Adam | epoch: 045 | loss: 1.47550 - acc: 0.3240 -- iter: 24/29
[A[ATraining Step: 180 | total loss: [1m[32m1.50013[0m[0m | time: 0.013s
[2K
| Adam | epoch: 045 | loss: 1.50013 - acc: 0.3116 -- iter: 29/29
--
Training Step: 181 | total loss: [1m[32m1.52188[0m[0m | time: 0.004s
[2K
| Adam | epoch: 046 | loss: 1.52188 - acc: 0.3005 -- iter: 08/29
[A[ATraining Step: 182 | total loss: [1m[32m1.52118[0m[0m | time: 0.007s
[2K
| Adam | epoch: 046 | loss: 1.52118 - acc: 0.3079 -- iter: 16/29
[A[ATraining Step: 183 | total loss: [1m[32m1.49006[0m[0m | time: 0.010s
[2K
| Adam | epoch: 046 | loss: 1.49006 - acc: 0.3271 -- iter: 24/29
[A[ATraining Step: 184 | total loss: [1m[32m1.49203[0m[0m | time: 0.014s
[2K
| Adam | epoch: 046 | loss: 1.49203 - acc: 0.3194 -- iter: 29/29
--
Training Step: 185 | total loss: [1m[32m1.49000[0m[0m | time: 0.003s
[2K
| Adam | epoch: 047 | loss: 1.49000 - acc: 0.3275 -- iter: 08/29
[A[ATraining Step: 186 | total loss: [1m[32m1.48757[0m[0m | time: 0.007s
[2K
| Adam | epoch: 047 | loss: 1.48757 - acc: 0.3147 -- iter: 16/29
[A[ATraining Step: 187 | total loss: [1m[32m1.47570[0m[0m | time: 0.010s
[2K
| Adam | epoch: 047 | loss: 1.47570 - acc: 0.2957 -- iter: 24/29
[A[ATraining Step: 188 | total loss: [1m[32m1.46400[0m[0m | time: 0.013s
[2K
| Adam | epoch: 047 | loss: 1.46400 - acc: 0.3162 -- iter: 29/29
--
Training Step: 189 | total loss: [1m[32m1.45298[0m[0m | time: 0.003s
[2K
| Adam | epoch: 048 | loss: 1.45298 - acc: 0.3221 -- iter: 08/29
[A[ATraining Step: 190 | total loss: [1m[32m1.48292[0m[0m | time: 0.007s
[2K
| Adam | epoch: 048 | loss: 1.48292 - acc: 0.2898 -- iter: 16/29
[A[ATraining Step: 191 | total loss: [1m[32m1.50966[0m[0m | time: 0.011s
[2K
| Adam | epoch: 048 | loss: 1.50966 - acc: 0.2609 -- iter: 24/29
[A[ATraining Step: 192 | total loss: [1m[32m1.51982[0m[0m | time: 0.020s
[2K
| Adam | epoch: 048 | loss: 1.51982 - acc: 0.2723 -- iter: 29/29
--
Training Step: 193 | total loss: [1m[32m1.47224[0m[0m | time: 0.003s
[2K
| Adam | epoch: 049 | loss: 1.47224 - acc: 0.2825 -- iter: 08/29
[A[ATraining Step: 194 | total loss: [1m[32m1.43775[0m[0m | time: 0.008s
[2K
| Adam | epoch: 049 | loss: 1.43775 - acc: 0.2793 -- iter: 16/29
[A[ATraining Step: 195 | total loss: [1m[32m1.45065[0m[0m | time: 0.011s
[2K
| Adam | epoch: 049 | loss: 1.45065 - acc: 0.2714 -- iter: 24/29
[A[ATraining Step: 196 | total loss: [1m[32m1.46182[0m[0m | time: 0.015s
[2K
| Adam | epoch: 049 | loss: 1.46182 - acc: 0.2642 -- iter: 29/29
--
Training Step: 197 | total loss: [1m[32m1.46429[0m[0m | time: 0.004s
[2K
| Adam | epoch: 050 | loss: 1.46429 - acc: 0.2878 -- iter: 08/29
[A[ATraining Step: 198 | total loss: [1m[32m1.46332[0m[0m | time: 0.008s
[2K
| Adam | epoch: 050 | loss: 1.46332 - acc: 0.2840 -- iter: 16/29
[A[ATraining Step: 199 | total loss: [1m[32m1.45049[0m[0m | time: 0.012s
[2K
| Adam | epoch: 050 | loss: 1.45049 - acc: 0.2681 -- iter: 24/29
[A[ATraining Step: 200 | total loss: [1m[32m1.44178[0m[0m | time: 0.016s
[2K
| Adam | epoch: 050 | loss: 1.44178 - acc: 0.2813 -- iter: 29/29
--
Training Step: 201 | total loss: [1m[32m1.43377[0m[0m | time: 0.004s
[2K
| Adam | epoch: 051 | loss: 1.43377 - acc: 0.2932 -- iter: 08/29
[A[ATraining Step: 202 | total loss: [1m[32m1.43648[0m[0m | time: 0.008s
[2K
| Adam | epoch: 051 | loss: 1.43648 - acc: 0.2889 -- iter: 16/29
[A[ATraining Step: 203 | total loss: [1m[32m1.42764[0m[0m | time: 0.012s
[2K
| Adam | epoch: 051 | loss: 1.42764 - acc: 0.3100 -- iter: 24/29
[A[ATraining Step: 204 | total loss: [1m[32m1.43606[0m[0m | time: 0.015s
[2K
| Adam | epoch: 051 | loss: 1.43606 - acc: 0.2915 -- iter: 29/29
--
Training Step: 205 | total loss: [1m[32m1.43134[0m[0m | time: 0.004s
[2K
| Adam | epoch: 052 | loss: 1.43134 - acc: 0.2823 -- iter: 08/29
[A[ATraining Step: 206 | total loss: [1m[32m1.42678[0m[0m | time: 0.008s
[2K
| Adam | epoch: 052 | loss: 1.42678 - acc: 0.2741 -- iter: 16/29
[A[ATraining Step: 207 | total loss: [1m[32m1.42487[0m[0m | time: 0.011s
[2K
| Adam | epoch: 052 | loss: 1.42487 - acc: 0.2967 -- iter: 24/29
[A[ATraining Step: 208 | total loss: [1m[32m1.39823[0m[0m | time: 0.015s
[2K
| Adam | epoch: 052 | loss: 1.39823 - acc: 0.3045 -- iter: 29/29
--
Training Step: 209 | total loss: [1m[32m1.40423[0m[0m | time: 0.004s
[2K
| Adam | epoch: 053 | loss: 1.40423 - acc: 0.3116 -- iter: 08/29
[A[ATraining Step: 210 | total loss: [1m[32m1.39158[0m[0m | time: 0.008s
[2K
| Adam | epoch: 053 | loss: 1.39158 - acc: 0.3204 -- iter: 16/29
[A[ATraining Step: 211 | total loss: [1m[32m1.37986[0m[0m | time: 0.012s
[2K
| Adam | epoch: 053 | loss: 1.37986 - acc: 0.3284 -- iter: 24/29
[A[ATraining Step: 212 | total loss: [1m[32m1.38867[0m[0m | time: 0.015s
[2K
| Adam | epoch: 053 | loss: 1.38867 - acc: 0.3205 -- iter: 29/29
--
Training Step: 213 | total loss: [1m[32m1.36749[0m[0m | time: 0.004s
[2K
| Adam | epoch: 054 | loss: 1.36749 - acc: 0.3135 -- iter: 08/29
[A[ATraining Step: 214 | total loss: [1m[32m1.37297[0m[0m | time: 0.030s
[2K
| Adam | epoch: 054 | loss: 1.37297 - acc: 0.3071 -- iter: 16/29
[A[ATraining Step: 215 | total loss: [1m[32m1.35225[0m[0m | time: 0.033s
[2K
| Adam | epoch: 054 | loss: 1.35225 - acc: 0.2964 -- iter: 24/29
[A[ATraining Step: 216 | total loss: [1m[32m1.33311[0m[0m | time: 0.037s
[2K
| Adam | epoch: 054 | loss: 1.33311 - acc: 0.2868 -- iter: 29/29
--
Training Step: 217 | total loss: [1m[32m1.31248[0m[0m | time: 0.003s
[2K
| Adam | epoch: 055 | loss: 1.31248 - acc: 0.3081 -- iter: 08/29
[A[ATraining Step: 218 | total loss: [1m[32m1.33941[0m[0m | time: 0.007s
[2K
| Adam | epoch: 055 | loss: 1.33941 - acc: 0.3023 -- iter: 16/29
[A[ATraining Step: 219 | total loss: [1m[32m1.32959[0m[0m | time: 0.012s
[2K
| Adam | epoch: 055 | loss: 1.32959 - acc: 0.3096 -- iter: 24/29
[A[ATraining Step: 220 | total loss: [1m[32m1.33994[0m[0m | time: 0.015s
[2K
| Adam | epoch: 055 | loss: 1.33994 - acc: 0.3186 -- iter: 29/29
--
Training Step: 221 | total loss: [1m[32m1.34890[0m[0m | time: 0.003s
[2K
| Adam | epoch: 056 | loss: 1.34890 - acc: 0.3267 -- iter: 08/29
[A[ATraining Step: 222 | total loss: [1m[32m1.33449[0m[0m | time: 0.007s
[2K
| Adam | epoch: 056 | loss: 1.33449 - acc: 0.3191 -- iter: 16/29
[A[ATraining Step: 223 | total loss: [1m[32m1.34826[0m[0m | time: 0.011s
[2K
| Adam | epoch: 056 | loss: 1.34826 - acc: 0.3122 -- iter: 24/29
[A[ATraining Step: 224 | total loss: [1m[32m1.36567[0m[0m | time: 0.014s
[2K
| Adam | epoch: 056 | loss: 1.36567 - acc: 0.2934 -- iter: 29/29
--
Training Step: 225 | total loss: [1m[32m1.34279[0m[0m | time: 0.004s
[2K
| Adam | epoch: 057 | loss: 1.34279 - acc: 0.3041 -- iter: 08/29
[A[ATraining Step: 226 | total loss: [1m[32m1.32182[0m[0m | time: 0.007s
[2K
| Adam | epoch: 057 | loss: 1.32182 - acc: 0.3337 -- iter: 16/29
[A[ATraining Step: 227 | total loss: [1m[32m1.30899[0m[0m | time: 0.010s
[2K
| Adam | epoch: 057 | loss: 1.30899 - acc: 0.3253 -- iter: 24/29
[A[ATraining Step: 228 | total loss: [1m[32m1.31285[0m[0m | time: 0.014s
[2K
| Adam | epoch: 057 | loss: 1.31285 - acc: 0.3178 -- iter: 29/29
--
Training Step: 229 | total loss: [1m[32m1.28622[0m[0m | time: 0.004s
[2K
| Adam | epoch: 058 | loss: 1.28622 - acc: 0.3235 -- iter: 08/29
[A[ATraining Step: 230 | total loss: [1m[32m1.28901[0m[0m | time: 0.008s
[2K
| Adam | epoch: 058 | loss: 1.28901 - acc: 0.3112 -- iter: 16/29
[A[ATraining Step: 231 | total loss: [1m[32m1.29120[0m[0m | time: 0.011s
[2K
| Adam | epoch: 058 | loss: 1.29120 - acc: 0.3000 -- iter: 24/29
[A[ATraining Step: 232 | total loss: [1m[32m1.29917[0m[0m | time: 0.014s
[2K
| Adam | epoch: 058 | loss: 1.29917 - acc: 0.2950 -- iter: 29/29
--
Training Step: 233 | total loss: [1m[32m1.31843[0m[0m | time: 0.003s
[2K
| Adam | epoch: 059 | loss: 1.31843 - acc: 0.2655 -- iter: 08/29
[A[ATraining Step: 234 | total loss: [1m[32m1.30232[0m[0m | time: 0.007s
[2K
| Adam | epoch: 059 | loss: 1.30232 - acc: 0.2765 -- iter: 16/29
[A[ATraining Step: 235 | total loss: [1m[32m1.30514[0m[0m | time: 0.011s
[2K
| Adam | epoch: 059 | loss: 1.30514 - acc: 0.2688 -- iter: 24/29
[A[ATraining Step: 236 | total loss: [1m[32m1.30721[0m[0m | time: 0.014s
[2K
| Adam | epoch: 059 | loss: 1.30721 - acc: 0.2820 -- iter: 29/29
--
Training Step: 237 | total loss: [1m[32m1.31967[0m[0m | time: 0.004s
[2K
| Adam | epoch: 060 | loss: 1.31967 - acc: 0.2663 -- iter: 08/29
[A[ATraining Step: 238 | total loss: [1m[32m1.31516[0m[0m | time: 0.024s
[2K
| Adam | epoch: 060 | loss: 1.31516 - acc: 0.2646 -- iter: 16/29
[A[ATraining Step: 239 | total loss: [1m[32m1.30490[0m[0m | time: 0.027s
[2K
| Adam | epoch: 060 | loss: 1.30490 - acc: 0.2882 -- iter: 24/29
[A[ATraining Step: 240 | total loss: [1m[32m1.32477[0m[0m | time: 0.030s
[2K
| Adam | epoch: 060 | loss: 1.32477 - acc: 0.2994 -- iter: 29/29
--
Training Step: 241 | total loss: [1m[32m1.34232[0m[0m | time: 0.003s
[2K
| Adam | epoch: 061 | loss: 1.34232 - acc: 0.3094 -- iter: 08/29
[A[ATraining Step: 242 | total loss: [1m[32m1.32787[0m[0m | time: 0.006s
[2K
| Adam | epoch: 061 | loss: 1.32787 - acc: 0.2910 -- iter: 16/29
[A[ATraining Step: 243 | total loss: [1m[32m1.32538[0m[0m | time: 0.010s
[2K
| Adam | epoch: 061 | loss: 1.32538 - acc: 0.2869 -- iter: 24/29
[A[ATraining Step: 244 | total loss: [1m[32m1.31446[0m[0m | time: 0.013s
[2K
| Adam | epoch: 061 | loss: 1.31446 - acc: 0.2957 -- iter: 29/29
--
Training Step: 245 | total loss: [1m[32m1.30114[0m[0m | time: 0.003s
[2K
| Adam | epoch: 062 | loss: 1.30114 - acc: 0.3061 -- iter: 08/29
[A[ATraining Step: 246 | total loss: [1m[32m1.28878[0m[0m | time: 0.007s
[2K
| Adam | epoch: 062 | loss: 1.28878 - acc: 0.3155 -- iter: 16/29
[A[ATraining Step: 247 | total loss: [1m[32m1.28660[0m[0m | time: 0.011s
[2K
| Adam | epoch: 062 | loss: 1.28660 - acc: 0.3090 -- iter: 24/29
[A[ATraining Step: 248 | total loss: [1m[32m1.29767[0m[0m | time: 0.014s
[2K
| Adam | epoch: 062 | loss: 1.29767 - acc: 0.3031 -- iter: 29/29
--
Training Step: 249 | total loss: [1m[32m1.29373[0m[0m | time: 0.004s
[2K
| Adam | epoch: 063 | loss: 1.29373 - acc: 0.2853 -- iter: 08/29
[A[ATraining Step: 250 | total loss: [1m[32m1.30059[0m[0m | time: 0.007s
[2K
| Adam | epoch: 063 | loss: 1.30059 - acc: 0.2967 -- iter: 16/29
[A[ATraining Step: 251 | total loss: [1m[32m1.30672[0m[0m | time: 0.009s
[2K
| Adam | epoch: 063 | loss: 1.30672 - acc: 0.2871 -- iter: 24/29
[A[ATraining Step: 252 | total loss: [1m[32m1.31155[0m[0m | time: 0.013s
[2K
| Adam | epoch: 063 | loss: 1.31155 - acc: 0.2834 -- iter: 29/29
--
Training Step: 253 | total loss: [1m[32m1.29246[0m[0m | time: 0.002s
[2K
| Adam | epoch: 064 | loss: 1.29246 - acc: 0.2925 -- iter: 08/29
[A[ATraining Step: 254 | total loss: [1m[32m1.26433[0m[0m | time: 0.005s
[2K
| Adam | epoch: 064 | loss: 1.26433 - acc: 0.3008 -- iter: 16/29
[A[ATraining Step: 255 | total loss: [1m[32m1.30034[0m[0m | time: 0.008s
[2K
| Adam | epoch: 064 | loss: 1.30034 - acc: 0.2707 -- iter: 24/29
[A[ATraining Step: 256 | total loss: [1m[32m1.33253[0m[0m | time: 0.010s
[2K
| Adam | epoch: 064 | loss: 1.33253 - acc: 0.2436 -- iter: 29/29
--
Training Step: 257 | total loss: [1m[32m1.33207[0m[0m | time: 0.003s
[2K
| Adam | epoch: 065 | loss: 1.33207 - acc: 0.2568 -- iter: 08/29
[A[ATraining Step: 258 | total loss: [1m[32m1.31879[0m[0m | time: 0.005s
[2K
| Adam | epoch: 065 | loss: 1.31879 - acc: 0.2686 -- iter: 16/29
[A[ATraining Step: 259 | total loss: [1m[32m1.29609[0m[0m | time: 0.008s
[2K
| Adam | epoch: 065 | loss: 1.29609 - acc: 0.2667 -- iter: 24/29
[A[ATraining Step: 260 | total loss: [1m[32m1.29155[0m[0m | time: 0.010s
[2K
| Adam | epoch: 065 | loss: 1.29155 - acc: 0.2601 -- iter: 29/29
--
Training Step: 261 | total loss: [1m[32m1.28729[0m[0m | time: 0.002s
[2K
| Adam | epoch: 066 | loss: 1.28729 - acc: 0.2540 -- iter: 08/29
[A[ATraining Step: 262 | total loss: [1m[32m1.29305[0m[0m | time: 0.005s
[2K
| Adam | epoch: 066 | loss: 1.29305 - acc: 0.2661 -- iter: 16/29
[A[ATraining Step: 263 | total loss: [1m[32m1.29437[0m[0m | time: 0.008s
[2K
| Adam | epoch: 066 | loss: 1.29437 - acc: 0.2770 -- iter: 24/29
[A[ATraining Step: 264 | total loss: [1m[32m1.30692[0m[0m | time: 0.011s
[2K
| Adam | epoch: 066 | loss: 1.30692 - acc: 0.2618 -- iter: 29/29
--
Training Step: 265 | total loss: [1m[32m1.29840[0m[0m | time: 0.003s
[2K
| Adam | epoch: 067 | loss: 1.29840 - acc: 0.2756 -- iter: 08/29
[A[ATraining Step: 266 | total loss: [1m[32m1.29039[0m[0m | time: 0.005s
[2K
| Adam | epoch: 067 | loss: 1.29039 - acc: 0.2881 -- iter: 16/29
[A[ATraining Step: 267 | total loss: [1m[32m1.26806[0m[0m | time: 0.007s
[2K
| Adam | epoch: 067 | loss: 1.26806 - acc: 0.3093 -- iter: 24/29
[A[ATraining Step: 268 | total loss: [1m[32m1.26668[0m[0m | time: 0.010s
[2K
| Adam | epoch: 067 | loss: 1.26668 - acc: 0.3033 -- iter: 29/29
--
Training Step: 269 | total loss: [1m[32m1.26184[0m[0m | time: 0.003s
[2K
| Adam | epoch: 068 | loss: 1.26184 - acc: 0.3230 -- iter: 08/29
[A[ATraining Step: 270 | total loss: [1m[32m1.23668[0m[0m | time: 0.005s
[2K
| Adam | epoch: 068 | loss: 1.23668 - acc: 0.3307 -- iter: 16/29
[A[ATraining Step: 271 | total loss: [1m[32m1.21400[0m[0m | time: 0.007s
[2K
| Adam | epoch: 068 | loss: 1.21400 - acc: 0.3376 -- iter: 24/29
[A[ATraining Step: 272 | total loss: [1m[32m1.23405[0m[0m | time: 0.010s
[2K
| Adam | epoch: 068 | loss: 1.23405 - acc: 0.3164 -- iter: 29/29
--
Training Step: 273 | total loss: [1m[32m1.23193[0m[0m | time: 0.002s
[2K
| Adam | epoch: 069 | loss: 1.23193 - acc: 0.3097 -- iter: 08/29
[A[ATraining Step: 274 | total loss: [1m[32m1.23324[0m[0m | time: 0.005s
[2K
| Adam | epoch: 069 | loss: 1.23324 - acc: 0.2913 -- iter: 16/29
[A[ATraining Step: 275 | total loss: [1m[32m1.24291[0m[0m | time: 0.008s
[2K
| Adam | epoch: 069 | loss: 1.24291 - acc: 0.2821 -- iter: 24/29
[A[ATraining Step: 276 | total loss: [1m[32m1.25143[0m[0m | time: 0.010s
[2K
| Adam | epoch: 069 | loss: 1.25143 - acc: 0.2739 -- iter: 29/29
--
Training Step: 277 | total loss: [1m[32m1.25970[0m[0m | time: 0.002s
[2K
| Adam | epoch: 070 | loss: 1.25970 - acc: 0.2715 -- iter: 08/29
[A[ATraining Step: 278 | total loss: [1m[32m1.23830[0m[0m | time: 0.005s
[2K
| Adam | epoch: 070 | loss: 1.23830 - acc: 0.3069 -- iter: 16/29
[A[ATraining Step: 279 | total loss: [1m[32m1.25817[0m[0m | time: 0.007s
[2K
| Adam | epoch: 070 | loss: 1.25817 - acc: 0.3012 -- iter: 24/29
[A[ATraining Step: 280 | total loss: [1m[32m1.25841[0m[0m | time: 0.010s
[2K
| Adam | epoch: 070 | loss: 1.25841 - acc: 0.2911 -- iter: 29/29
--
Training Step: 281 | total loss: [1m[32m1.25824[0m[0m | time: 0.002s
[2K
| Adam | epoch: 071 | loss: 1.25824 - acc: 0.2820 -- iter: 08/29
[A[ATraining Step: 282 | total loss: [1m[32m1.25063[0m[0m | time: 0.005s
[2K
| Adam | epoch: 071 | loss: 1.25063 - acc: 0.2788 -- iter: 16/29
[A[ATraining Step: 283 | total loss: [1m[32m1.22827[0m[0m | time: 0.007s
[2K
| Adam | epoch: 071 | loss: 1.22827 - acc: 0.3009 -- iter: 24/29
[A[ATraining Step: 284 | total loss: [1m[32m1.24323[0m[0m | time: 0.010s
[2K
| Adam | epoch: 071 | loss: 1.24323 - acc: 0.2833 -- iter: 29/29
--
Training Step: 285 | total loss: [1m[32m1.22907[0m[0m | time: 0.003s
[2K
| Adam | epoch: 072 | loss: 1.22907 - acc: 0.2950 -- iter: 08/29
[A[ATraining Step: 286 | total loss: [1m[32m1.21602[0m[0m | time: 0.005s
[2K
| Adam | epoch: 072 | loss: 1.21602 - acc: 0.3055 -- iter: 16/29
[A[ATraining Step: 287 | total loss: [1m[32m1.20401[0m[0m | time: 0.007s
[2K
| Adam | epoch: 072 | loss: 1.20401 - acc: 0.3249 -- iter: 24/29
[A[ATraining Step: 288 | total loss: [1m[32m1.20805[0m[0m | time: 0.010s
[2K
| Adam | epoch: 072 | loss: 1.20805 - acc: 0.3174 -- iter: 29/29
--
Training Step: 289 | total loss: [1m[32m1.22337[0m[0m | time: 0.002s
[2K
| Adam | epoch: 073 | loss: 1.22337 - acc: 0.3107 -- iter: 08/29
[A[ATraining Step: 290 | total loss: [1m[32m1.20237[0m[0m | time: 0.005s
[2K
| Adam | epoch: 073 | loss: 1.20237 - acc: 0.2996 -- iter: 16/29
[A[ATraining Step: 291 | total loss: [1m[32m1.18288[0m[0m | time: 0.007s
[2K
| Adam | epoch: 073 | loss: 1.18288 - acc: 0.2897 -- iter: 24/29
[A[ATraining Step: 292 | total loss: [1m[32m1.18172[0m[0m | time: 0.010s
[2K
| Adam | epoch: 073 | loss: 1.18172 - acc: 0.2982 -- iter: 29/29
--
Training Step: 293 | total loss: [1m[32m1.18649[0m[0m | time: 0.002s
[2K
| Adam | epoch: 074 | loss: 1.18649 - acc: 0.3059 -- iter: 08/29
[A[ATraining Step: 294 | total loss: [1m[32m1.18474[0m[0m | time: 0.005s
[2K
| Adam | epoch: 074 | loss: 1.18474 - acc: 0.3378 -- iter: 16/29
[A[ATraining Step: 295 | total loss: [1m[32m1.19468[0m[0m | time: 0.007s
[2K
| Adam | epoch: 074 | loss: 1.19468 - acc: 0.3440 -- iter: 24/29
[A[ATraining Step: 296 | total loss: [1m[32m1.20329[0m[0m | time: 0.010s
[2K
| Adam | epoch: 074 | loss: 1.20329 - acc: 0.3496 -- iter: 29/29
--
Training Step: 297 | total loss: [1m[32m1.20420[0m[0m | time: 0.002s
[2K
| Adam | epoch: 075 | loss: 1.20420 - acc: 0.3396 -- iter: 08/29
[A[ATraining Step: 298 | total loss: [1m[32m1.20121[0m[0m | time: 0.005s
[2K
| Adam | epoch: 075 | loss: 1.20121 - acc: 0.3307 -- iter: 16/29
[A[ATraining Step: 299 | total loss: [1m[32m1.20860[0m[0m | time: 0.007s
[2K
| Adam | epoch: 075 | loss: 1.20860 - acc: 0.3351 -- iter: 24/29
[A[ATraining Step: 300 | total loss: [1m[32m1.22281[0m[0m | time: 0.010s
[2K
| Adam | epoch: 075 | loss: 1.22281 - acc: 0.3016 -- iter: 29/29
--
Training Step: 301 | total loss: [1m[32m1.23542[0m[0m | time: 0.002s
[2K
| Adam | epoch: 076 | loss: 1.23542 - acc: 0.2714 -- iter: 08/29
[A[ATraining Step: 302 | total loss: [1m[32m1.22342[0m[0m | time: 0.005s
[2K
| Adam | epoch: 076 | loss: 1.22342 - acc: 0.2693 -- iter: 16/29
[A[ATraining Step: 303 | total loss: [1m[32m1.21244[0m[0m | time: 0.007s
[2K
| Adam | epoch: 076 | loss: 1.21244 - acc: 0.2924 -- iter: 24/29
[A[ATraining Step: 304 | total loss: [1m[32m1.20454[0m[0m | time: 0.010s
[2K
| Adam | epoch: 076 | loss: 1.20454 - acc: 0.3006 -- iter: 29/29
--
Training Step: 305 | total loss: [1m[32m1.19232[0m[0m | time: 0.002s
[2K
| Adam | epoch: 077 | loss: 1.19232 - acc: 0.3306 -- iter: 08/29
[A[ATraining Step: 306 | total loss: [1m[32m1.18084[0m[0m | time: 0.005s
[2K
| Adam | epoch: 077 | loss: 1.18084 - acc: 0.3575 -- iter: 16/29
[A[ATraining Step: 307 | total loss: [1m[32m1.18054[0m[0m | time: 0.019s
[2K
| Adam | epoch: 077 | loss: 1.18054 - acc: 0.3593 -- iter: 24/29
[A[ATraining Step: 308 | total loss: [1m[32m1.19721[0m[0m | time: 0.022s
[2K
| Adam | epoch: 077 | loss: 1.19721 - acc: 0.3233 -- iter: 29/29
--
Training Step: 309 | total loss: [1m[32m1.18016[0m[0m | time: 0.002s
[2K
| Adam | epoch: 078 | loss: 1.18016 - acc: 0.3410 -- iter: 08/29
[A[ATraining Step: 310 | total loss: [1m[32m1.20859[0m[0m | time: 0.006s
[2K
| Adam | epoch: 078 | loss: 1.20859 - acc: 0.3069 -- iter: 16/29
[A[ATraining Step: 311 | total loss: [1m[32m1.23408[0m[0m | time: 0.009s
[2K
| Adam | epoch: 078 | loss: 1.23408 - acc: 0.2762 -- iter: 24/29
[A[ATraining Step: 312 | total loss: [1m[32m1.22328[0m[0m | time: 0.012s
[2K
| Adam | epoch: 078 | loss: 1.22328 - acc: 0.3111 -- iter: 29/29
--
Training Step: 313 | total loss: [1m[32m1.22644[0m[0m | time: 0.003s
[2K
| Adam | epoch: 079 | loss: 1.22644 - acc: 0.2800 -- iter: 08/29
[A[ATraining Step: 314 | total loss: [1m[32m1.22017[0m[0m | time: 0.006s
[2K
| Adam | epoch: 079 | loss: 1.22017 - acc: 0.3020 -- iter: 16/29
[A[ATraining Step: 315 | total loss: [1m[32m1.22866[0m[0m | time: 0.008s
[2K
| Adam | epoch: 079 | loss: 1.22866 - acc: 0.2918 -- iter: 24/29
[A[ATraining Step: 316 | total loss: [1m[32m1.23603[0m[0m | time: 0.011s
[2K
| Adam | epoch: 079 | loss: 1.23603 - acc: 0.2826 -- iter: 29/29
--
Training Step: 317 | total loss: [1m[32m1.22927[0m[0m | time: 0.002s
[2K
| Adam | epoch: 080 | loss: 1.22927 - acc: 0.2793 -- iter: 08/29
[A[ATraining Step: 318 | total loss: [1m[32m1.37479[0m[0m | time: 0.005s
[2K
| Adam | epoch: 080 | loss: 1.37479 - acc: 0.2639 -- iter: 16/29
[A[ATraining Step: 319 | total loss: [1m[32m1.35507[0m[0m | time: 0.008s
[2K
| Adam | epoch: 080 | loss: 1.35507 - acc: 0.2750 -- iter: 24/29
[A[ATraining Step: 320 | total loss: [1m[32m1.33450[0m[0m | time: 0.010s
[2K
| Adam | epoch: 080 | loss: 1.33450 - acc: 0.2675 -- iter: 29/29
--
Training Step: 321 | total loss: [1m[32m1.31575[0m[0m | time: 0.003s
[2K
| Adam | epoch: 081 | loss: 1.31575 - acc: 0.2608 -- iter: 08/29
[A[ATraining Step: 322 | total loss: [1m[32m1.29892[0m[0m | time: 0.006s
[2K
| Adam | epoch: 081 | loss: 1.29892 - acc: 0.2722 -- iter: 16/29
[A[ATraining Step: 323 | total loss: [1m[32m1.29395[0m[0m | time: 0.009s
[2K
| Adam | epoch: 081 | loss: 1.29395 - acc: 0.2700 -- iter: 24/29
[A[ATraining Step: 324 | total loss: [1m[32m1.28503[0m[0m | time: 0.012s
[2K
| Adam | epoch: 081 | loss: 1.28503 - acc: 0.2805 -- iter: 29/29
--
Training Step: 325 | total loss: [1m[32m1.25508[0m[0m | time: 0.002s
[2K
| Adam | epoch: 082 | loss: 1.25508 - acc: 0.2924 -- iter: 08/29
[A[ATraining Step: 326 | total loss: [1m[32m1.22794[0m[0m | time: 0.005s
[2K
| Adam | epoch: 082 | loss: 1.22794 - acc: 0.3032 -- iter: 16/29
[A[ATraining Step: 327 | total loss: [1m[32m1.22240[0m[0m | time: 0.009s
[2K
| Adam | epoch: 082 | loss: 1.22240 - acc: 0.3104 -- iter: 24/29
[A[ATraining Step: 328 | total loss: [1m[32m1.49522[0m[0m | time: 0.011s
[2K
| Adam | epoch: 082 | loss: 1.49522 - acc: 0.2918 -- iter: 29/29
--
Training Step: 329 | total loss: [1m[32m1.47543[0m[0m | time: 0.003s
[2K
| Adam | epoch: 083 | loss: 1.47543 - acc: 0.2876 -- iter: 08/29
[A[ATraining Step: 330 | total loss: [1m[32m1.44110[0m[0m | time: 0.007s
[2K
| Adam | epoch: 083 | loss: 1.44110 - acc: 0.2989 -- iter: 16/29
[A[ATraining Step: 331 | total loss: [1m[32m1.41039[0m[0m | time: 0.009s
[2K
| Adam | epoch: 083 | loss: 1.41039 - acc: 0.3090 -- iter: 24/29
[A[ATraining Step: 332 | total loss: [1m[32m1.38807[0m[0m | time: 0.012s
[2K
| Adam | epoch: 083 | loss: 1.38807 - acc: 0.3156 -- iter: 29/29
--
Training Step: 333 | total loss: [1m[32m1.35755[0m[0m | time: 0.003s
[2K
| Adam | epoch: 084 | loss: 1.35755 - acc: 0.3090 -- iter: 08/29
[A[ATraining Step: 334 | total loss: [1m[32m1.35152[0m[0m | time: 0.030s
[2K
| Adam | epoch: 084 | loss: 1.35152 - acc: 0.2906 -- iter: 16/29
[A[ATraining Step: 335 | total loss: [1m[32m1.31941[0m[0m | time: 0.032s
[2K
| Adam | epoch: 084 | loss: 1.31941 - acc: 0.2816 -- iter: 24/29
[A[ATraining Step: 336 | total loss: [1m[32m1.29030[0m[0m | time: 0.035s
[2K
| Adam | epoch: 084 | loss: 1.29030 - acc: 0.2734 -- iter: 29/29
--
Training Step: 337 | total loss: [1m[32m1.26103[0m[0m | time: 0.002s
[2K
| Adam | epoch: 085 | loss: 1.26103 - acc: 0.2961 -- iter: 08/29
[A[ATraining Step: 338 | total loss: [1m[32m1.26885[0m[0m | time: 0.006s
[2K
| Adam | epoch: 085 | loss: 1.26885 - acc: 0.3040 -- iter: 16/29
[A[ATraining Step: 339 | total loss: [1m[32m1.27471[0m[0m | time: 0.008s
[2K
| Adam | epoch: 085 | loss: 1.27471 - acc: 0.2986 -- iter: 24/29
[A[ATraining Step: 340 | total loss: [1m[32m1.25174[0m[0m | time: 0.011s
[2K
| Adam | epoch: 085 | loss: 1.25174 - acc: 0.3087 -- iter: 29/29
--
Training Step: 341 | total loss: [1m[32m1.23049[0m[0m | time: 0.003s
[2K
| Adam | epoch: 086 | loss: 1.23049 - acc: 0.3178 -- iter: 08/29
[A[ATraining Step: 342 | total loss: [1m[32m1.23359[0m[0m | time: 0.007s
[2K
| Adam | epoch: 086 | loss: 1.23359 - acc: 0.3111 -- iter: 16/29
[A[ATraining Step: 343 | total loss: [1m[32m1.21317[0m[0m | time: 0.010s
[2K
| Adam | epoch: 086 | loss: 1.21317 - acc: 0.3299 -- iter: 24/29
[A[ATraining Step: 344 | total loss: [1m[32m1.23197[0m[0m | time: 0.015s
[2K
| Adam | epoch: 086 | loss: 1.23197 - acc: 0.3095 -- iter: 29/29
--
Training Step: 345 | total loss: [1m[32m1.20577[0m[0m | time: 0.003s
[2K
| Adam | epoch: 087 | loss: 1.20577 - acc: 0.2785 -- iter: 08/29
[A[ATraining Step: 346 | total loss: [1m[32m1.18210[0m[0m | time: 0.006s
[2K
| Adam | epoch: 087 | loss: 1.18210 - acc: 0.2507 -- iter: 16/29
[A[ATraining Step: 347 | total loss: [1m[32m1.17602[0m[0m | time: 0.009s
[2K
| Adam | epoch: 087 | loss: 1.17602 - acc: 0.2381 -- iter: 24/29
[A[ATraining Step: 348 | total loss: [1m[32m1.17171[0m[0m | time: 0.012s
[2K
| Adam | epoch: 087 | loss: 1.17171 - acc: 0.2518 -- iter: 29/29
--
Training Step: 349 | total loss: [1m[32m1.17627[0m[0m | time: 0.002s
[2K
| Adam | epoch: 088 | loss: 1.17627 - acc: 0.2641 -- iter: 08/29
[A[ATraining Step: 350 | total loss: [1m[32m1.17789[0m[0m | time: 0.006s
[2K
| Adam | epoch: 088 | loss: 1.17789 - acc: 0.2577 -- iter: 16/29
[A[ATraining Step: 351 | total loss: [1m[32m1.17924[0m[0m | time: 0.009s
[2K
| Adam | epoch: 088 | loss: 1.17924 - acc: 0.2519 -- iter: 24/29
[A[ATraining Step: 352 | total loss: [1m[32m1.17167[0m[0m | time: 0.012s
[2K
| Adam | epoch: 088 | loss: 1.17167 - acc: 0.2642 -- iter: 29/29
--
Training Step: 353 | total loss: [1m[32m1.17231[0m[0m | time: 0.003s
[2K
| Adam | epoch: 089 | loss: 1.17231 - acc: 0.2628 -- iter: 08/29
[A[ATraining Step: 354 | total loss: [1m[32m1.17461[0m[0m | time: 0.005s
[2K
| Adam | epoch: 089 | loss: 1.17461 - acc: 0.2490 -- iter: 16/29
[A[ATraining Step: 355 | total loss: [1m[32m1.17879[0m[0m | time: 0.008s
[2K
| Adam | epoch: 089 | loss: 1.17879 - acc: 0.2841 -- iter: 24/29
[A[ATraining Step: 356 | total loss: [1m[32m1.18225[0m[0m | time: 0.012s
[2K
| Adam | epoch: 089 | loss: 1.18225 - acc: 0.3157 -- iter: 29/29
--
Training Step: 357 | total loss: [1m[32m1.16117[0m[0m | time: 0.003s
[2K
| Adam | epoch: 090 | loss: 1.16117 - acc: 0.3341 -- iter: 08/29
[A[ATraining Step: 358 | total loss: [1m[32m1.17609[0m[0m | time: 0.007s
[2K
| Adam | epoch: 090 | loss: 1.17609 - acc: 0.3132 -- iter: 16/29
[A[ATraining Step: 359 | total loss: [1m[32m1.17482[0m[0m | time: 0.010s
[2K
| Adam | epoch: 090 | loss: 1.17482 - acc: 0.3319 -- iter: 24/29
[A[ATraining Step: 360 | total loss: [1m[32m1.17867[0m[0m | time: 0.014s
[2K
| Adam | epoch: 090 | loss: 1.17867 - acc: 0.3387 -- iter: 29/29
--
Training Step: 361 | total loss: [1m[32m1.18200[0m[0m | time: 0.003s
[2K
| Adam | epoch: 091 | loss: 1.18200 - acc: 0.3448 -- iter: 08/29
[A[ATraining Step: 362 | total loss: [1m[32m1.17710[0m[0m | time: 0.007s
[2K
| Adam | epoch: 091 | loss: 1.17710 - acc: 0.3354 -- iter: 16/29
[A[ATraining Step: 363 | total loss: [1m[32m1.17695[0m[0m | time: 0.010s
[2K
| Adam | epoch: 091 | loss: 1.17695 - acc: 0.3143 -- iter: 24/29
[A[ATraining Step: 364 | total loss: [1m[32m1.17075[0m[0m | time: 0.012s
[2K
| Adam | epoch: 091 | loss: 1.17075 - acc: 0.3329 -- iter: 29/29
--
Training Step: 365 | total loss: [1m[32m1.17790[0m[0m | time: 0.003s
[2K
| Adam | epoch: 092 | loss: 1.17790 - acc: 0.3396 -- iter: 08/29
[A[ATraining Step: 366 | total loss: [1m[32m1.18401[0m[0m | time: 0.007s
[2K
| Adam | epoch: 092 | loss: 1.18401 - acc: 0.3456 -- iter: 16/29
[A[ATraining Step: 367 | total loss: [1m[32m1.18089[0m[0m | time: 0.010s
[2K
| Adam | epoch: 092 | loss: 1.18089 - acc: 0.3236 -- iter: 24/29
[A[ATraining Step: 368 | total loss: [1m[32m1.18074[0m[0m | time: 0.012s
[2K
| Adam | epoch: 092 | loss: 1.18074 - acc: 0.3162 -- iter: 29/29
--
Training Step: 369 | total loss: [1m[32m1.18609[0m[0m | time: 0.003s
[2K
| Adam | epoch: 093 | loss: 1.18609 - acc: 0.3221 -- iter: 08/29
[A[ATraining Step: 370 | total loss: [1m[32m1.16295[0m[0m | time: 0.007s
[2K
| Adam | epoch: 093 | loss: 1.16295 - acc: 0.3499 -- iter: 16/29
[A[ATraining Step: 371 | total loss: [1m[32m1.14180[0m[0m | time: 0.009s
[2K
| Adam | epoch: 093 | loss: 1.14180 - acc: 0.3749 -- iter: 24/29
[A[ATraining Step: 372 | total loss: [1m[32m1.15176[0m[0m | time: 0.012s
[2K
| Adam | epoch: 093 | loss: 1.15176 - acc: 0.3624 -- iter: 29/29
--
Training Step: 373 | total loss: [1m[32m1.15063[0m[0m | time: 0.003s
[2K
| Adam | epoch: 094 | loss: 1.15063 - acc: 0.3387 -- iter: 08/29
[A[ATraining Step: 374 | total loss: [1m[32m1.14530[0m[0m | time: 0.006s
[2K
| Adam | epoch: 094 | loss: 1.14530 - acc: 0.3423 -- iter: 16/29
[A[ATraining Step: 375 | total loss: [1m[32m1.13272[0m[0m | time: 0.009s
[2K
| Adam | epoch: 094 | loss: 1.13272 - acc: 0.3681 -- iter: 24/29
[A[ATraining Step: 376 | total loss: [1m[32m1.12108[0m[0m | time: 0.012s
[2K
| Adam | epoch: 094 | loss: 1.12108 - acc: 0.3913 -- iter: 29/29
--
Training Step: 377 | total loss: [1m[32m1.13253[0m[0m | time: 0.002s
[2K
| Adam | epoch: 095 | loss: 1.13253 - acc: 0.3771 -- iter: 08/29
[A[ATraining Step: 378 | total loss: [1m[32m1.14281[0m[0m | time: 0.006s
[2K
| Adam | epoch: 095 | loss: 1.14281 - acc: 0.3519 -- iter: 16/29
[A[ATraining Step: 379 | total loss: [1m[32m1.13541[0m[0m | time: 0.008s
[2K
| Adam | epoch: 095 | loss: 1.13541 - acc: 0.3542 -- iter: 24/29
[A[ATraining Step: 380 | total loss: [1m[32m1.13241[0m[0m | time: 0.011s
[2K
| Adam | epoch: 095 | loss: 1.13241 - acc: 0.3588 -- iter: 29/29
--
Training Step: 381 | total loss: [1m[32m1.12952[0m[0m | time: 0.003s
[2K
| Adam | epoch: 096 | loss: 1.12952 - acc: 0.3629 -- iter: 08/29
[A[ATraining Step: 382 | total loss: [1m[32m1.13453[0m[0m | time: 0.006s
[2K
| Adam | epoch: 096 | loss: 1.13453 - acc: 0.3516 -- iter: 16/29
[A[ATraining Step: 383 | total loss: [1m[32m1.14666[0m[0m | time: 0.009s
[2K
| Adam | epoch: 096 | loss: 1.14666 - acc: 0.3415 -- iter: 24/29
[A[ATraining Step: 384 | total loss: [1m[32m1.13689[0m[0m | time: 0.012s
[2K
| Adam | epoch: 096 | loss: 1.13689 - acc: 0.3573 -- iter: 29/29
--
Training Step: 385 | total loss: [1m[32m1.14749[0m[0m | time: 0.005s
[2K
| Adam | epoch: 097 | loss: 1.14749 - acc: 0.3416 -- iter: 08/29
[A[ATraining Step: 386 | total loss: [1m[32m1.15683[0m[0m | time: 0.009s
[2K
| Adam | epoch: 097 | loss: 1.15683 - acc: 0.3274 -- iter: 16/29
[A[ATraining Step: 387 | total loss: [1m[32m1.16218[0m[0m | time: 0.012s
[2K
| Adam | epoch: 097 | loss: 1.16218 - acc: 0.3072 -- iter: 24/29
[A[ATraining Step: 388 | total loss: [1m[32m1.16178[0m[0m | time: 0.016s
[2K
| Adam | epoch: 097 | loss: 1.16178 - acc: 0.3140 -- iter: 29/29
--
Training Step: 389 | total loss: [1m[32m1.16034[0m[0m | time: 0.003s
[2K
| Adam | epoch: 098 | loss: 1.16034 - acc: 0.3076 -- iter: 08/29
[A[ATraining Step: 390 | total loss: [1m[32m1.15428[0m[0m | time: 0.006s
[2K
| Adam | epoch: 098 | loss: 1.15428 - acc: 0.3168 -- iter: 16/29
[A[ATraining Step: 391 | total loss: [1m[32m1.14878[0m[0m | time: 0.008s
[2K
| Adam | epoch: 098 | loss: 1.14878 - acc: 0.3251 -- iter: 24/29
[A[ATraining Step: 392 | total loss: [1m[32m1.15444[0m[0m | time: 0.011s
[2K
| Adam | epoch: 098 | loss: 1.15444 - acc: 0.3176 -- iter: 29/29
--
Training Step: 393 | total loss: [1m[32m1.15321[0m[0m | time: 0.004s
[2K
| Adam | epoch: 099 | loss: 1.15321 - acc: 0.3234 -- iter: 08/29
[A[ATraining Step: 394 | total loss: [1m[32m1.15497[0m[0m | time: 0.007s
[2K
| Adam | epoch: 099 | loss: 1.15497 - acc: 0.3160 -- iter: 16/29
[A[ATraining Step: 395 | total loss: [1m[32m1.13533[0m[0m | time: 0.021s
[2K
| Adam | epoch: 099 | loss: 1.13533 - acc: 0.3444 -- iter: 24/29
[A[ATraining Step: 396 | total loss: [1m[32m1.11767[0m[0m | time: 0.024s
[2K
| Adam | epoch: 099 | loss: 1.11767 - acc: 0.3700 -- iter: 29/29
--
Training Step: 397 | total loss: [1m[32m1.11186[0m[0m | time: 0.003s
[2K
| Adam | epoch: 100 | loss: 1.11186 - acc: 0.3705 -- iter: 08/29
[A[ATraining Step: 398 | total loss: [1m[32m1.13484[0m[0m | time: 0.005s
[2K
| Adam | epoch: 100 | loss: 1.13484 - acc: 0.3709 -- iter: 16/29
[A[ATraining Step: 399 | total loss: [1m[32m1.11997[0m[0m | time: 0.008s
[2K
| Adam | epoch: 100 | loss: 1.11997 - acc: 0.3713 -- iter: 24/29
[A[ATraining Step: 400 | total loss: [1m[32m1.15083[0m[0m | time: 0.011s
[2K
| Adam | epoch: 100 | loss: 1.15083 - acc: 0.3542 -- iter: 29/29
--
Training Step: 401 | total loss: [1m[32m1.17841[0m[0m | time: 0.003s
[2K
| Adam | epoch: 101 | loss: 1.17841 - acc: 0.3388 -- iter: 08/29
[A[ATraining Step: 402 | total loss: [1m[32m1.18577[0m[0m | time: 0.006s
[2K
| Adam | epoch: 101 | loss: 1.18577 - acc: 0.3299 -- iter: 16/29
[A[ATraining Step: 403 | total loss: [1m[32m1.17052[0m[0m | time: 0.008s
[2K
| Adam | epoch: 101 | loss: 1.17052 - acc: 0.3594 -- iter: 24/29
[A[ATraining Step: 404 | total loss: [1m[32m1.18482[0m[0m | time: 0.011s
[2K
| Adam | epoch: 101 | loss: 1.18482 - acc: 0.3360 -- iter: 29/29
--
Training Step: 405 | total loss: [1m[32m1.15523[0m[0m | time: 0.002s
[2K
| Adam | epoch: 102 | loss: 1.15523 - acc: 0.3624 -- iter: 08/29
[A[ATraining Step: 406 | total loss: [1m[32m1.12857[0m[0m | time: 0.005s
[2K
| Adam | epoch: 102 | loss: 1.12857 - acc: 0.3861 -- iter: 16/29
[A[ATraining Step: 407 | total loss: [1m[32m1.14565[0m[0m | time: 0.008s
[2K
| Adam | epoch: 102 | loss: 1.14565 - acc: 0.3725 -- iter: 24/29
[A[ATraining Step: 408 | total loss: [1m[32m1.12988[0m[0m | time: 0.010s
[2K
| Adam | epoch: 102 | loss: 1.12988 - acc: 0.3853 -- iter: 29/29
--
Training Step: 409 | total loss: [1m[32m1.12775[0m[0m | time: 0.003s
[2K
| Adam | epoch: 103 | loss: 1.12775 - acc: 0.3842 -- iter: 08/29
[A[ATraining Step: 410 | total loss: [1m[32m1.14601[0m[0m | time: 0.006s
[2K
| Adam | epoch: 103 | loss: 1.14601 - acc: 0.3858 -- iter: 16/29
[A[ATraining Step: 411 | total loss: [1m[32m1.16229[0m[0m | time: 0.009s
[2K
| Adam | epoch: 103 | loss: 1.16229 - acc: 0.3872 -- iter: 24/29
[A[ATraining Step: 412 | total loss: [1m[32m1.16176[0m[0m | time: 0.012s
[2K
| Adam | epoch: 103 | loss: 1.16176 - acc: 0.3610 -- iter: 29/29
--
Training Step: 413 | total loss: [1m[32m1.15207[0m[0m | time: 0.002s
[2K
| Adam | epoch: 104 | loss: 1.15207 - acc: 0.3624 -- iter: 08/29
[A[ATraining Step: 414 | total loss: [1m[32m1.14882[0m[0m | time: 0.005s
[2K
| Adam | epoch: 104 | loss: 1.14882 - acc: 0.3512 -- iter: 16/29
[A[ATraining Step: 415 | total loss: [1m[32m1.15946[0m[0m | time: 0.008s
[2K
| Adam | epoch: 104 | loss: 1.15946 - acc: 0.3561 -- iter: 24/29
[A[ATraining Step: 416 | total loss: [1m[32m1.16891[0m[0m | time: 0.010s
[2K
| Adam | epoch: 104 | loss: 1.16891 - acc: 0.3604 -- iter: 29/29
--
Training Step: 417 | total loss: [1m[32m1.17004[0m[0m | time: 0.002s
[2K
| Adam | epoch: 105 | loss: 1.17004 - acc: 0.3619 -- iter: 08/29
[A[ATraining Step: 418 | total loss: [1m[32m1.15875[0m[0m | time: 0.005s
[2K
| Adam | epoch: 105 | loss: 1.15875 - acc: 0.3507 -- iter: 16/29
[A[ATraining Step: 419 | total loss: [1m[32m1.15693[0m[0m | time: 0.007s
[2K
| Adam | epoch: 105 | loss: 1.15693 - acc: 0.3406 -- iter: 24/29
[A[ATraining Step: 420 | total loss: [1m[32m1.14636[0m[0m | time: 0.009s
[2K
| Adam | epoch: 105 | loss: 1.14636 - acc: 0.3666 -- iter: 29/29
--
Training Step: 421 | total loss: [1m[32m1.13659[0m[0m | time: 0.002s
[2K
| Adam | epoch: 106 | loss: 1.13659 - acc: 0.3899 -- iter: 08/29
[A[ATraining Step: 422 | total loss: [1m[32m1.13908[0m[0m | time: 0.005s
[2K
| Adam | epoch: 106 | loss: 1.13908 - acc: 0.3759 -- iter: 16/29
[A[ATraining Step: 423 | total loss: [1m[32m1.14281[0m[0m | time: 0.007s
[2K
| Adam | epoch: 106 | loss: 1.14281 - acc: 0.3633 -- iter: 24/29
[A[ATraining Step: 424 | total loss: [1m[32m1.14062[0m[0m | time: 0.009s
[2K
| Adam | epoch: 106 | loss: 1.14062 - acc: 0.3770 -- iter: 29/29
--
Training Step: 425 | total loss: [1m[32m1.14134[0m[0m | time: 0.023s
[2K
| Adam | epoch: 107 | loss: 1.14134 - acc: 0.3793 -- iter: 08/29
[A[ATraining Step: 426 | total loss: [1m[32m1.14197[0m[0m | time: 0.026s
[2K
| Adam | epoch: 107 | loss: 1.14197 - acc: 0.3814 -- iter: 16/29
[A[ATraining Step: 427 | total loss: [1m[32m1.15537[0m[0m | time: 0.028s
[2K
| Adam | epoch: 107 | loss: 1.15537 - acc: 0.3557 -- iter: 24/29
[A[ATraining Step: 428 | total loss: [1m[32m1.14080[0m[0m | time: 0.030s
[2K
| Adam | epoch: 107 | loss: 1.14080 - acc: 0.3452 -- iter: 29/29
--
Training Step: 429 | total loss: [1m[32m1.15199[0m[0m | time: 0.002s
[2K
| Adam | epoch: 108 | loss: 1.15199 - acc: 0.3356 -- iter: 08/29
[A[ATraining Step: 430 | total loss: [1m[32m1.12444[0m[0m | time: 0.005s
[2K
| Adam | epoch: 108 | loss: 1.12444 - acc: 0.3421 -- iter: 16/29
[A[ATraining Step: 431 | total loss: [1m[32m1.09952[0m[0m | time: 0.007s
[2K
| Adam | epoch: 108 | loss: 1.09952 - acc: 0.3479 -- iter: 24/29
[A[ATraining Step: 432 | total loss: [1m[32m1.11211[0m[0m | time: 0.010s
[2K
| Adam | epoch: 108 | loss: 1.11211 - acc: 0.3256 -- iter: 29/29
--
Training Step: 433 | total loss: [1m[32m1.10993[0m[0m | time: 0.003s
[2K
| Adam | epoch: 109 | loss: 1.10993 - acc: 0.3430 -- iter: 08/29
[A[ATraining Step: 434 | total loss: [1m[32m1.11787[0m[0m | time: 0.005s
[2K
| Adam | epoch: 109 | loss: 1.11787 - acc: 0.3587 -- iter: 16/29
[A[ATraining Step: 435 | total loss: [1m[32m1.12826[0m[0m | time: 0.007s
[2K
| Adam | epoch: 109 | loss: 1.12826 - acc: 0.3429 -- iter: 24/29
[A[ATraining Step: 436 | total loss: [1m[32m1.13747[0m[0m | time: 0.010s
[2K
| Adam | epoch: 109 | loss: 1.13747 - acc: 0.3286 -- iter: 29/29
--
Training Step: 437 | total loss: [1m[32m1.12571[0m[0m | time: 0.002s
[2K
| Adam | epoch: 110 | loss: 1.12571 - acc: 0.3207 -- iter: 08/29
[A[ATraining Step: 438 | total loss: [1m[32m1.43375[0m[0m | time: 0.005s
[2K
| Adam | epoch: 110 | loss: 1.43375 - acc: 0.3136 -- iter: 16/29
[A[ATraining Step: 439 | total loss: [1m[32m1.40301[0m[0m | time: 0.007s
[2K
| Adam | epoch: 110 | loss: 1.40301 - acc: 0.3198 -- iter: 24/29
[A[ATraining Step: 440 | total loss: [1m[32m1.37784[0m[0m | time: 0.010s
[2K
| Adam | epoch: 110 | loss: 1.37784 - acc: 0.2878 -- iter: 29/29
--
Training Step: 441 | total loss: [1m[32m1.35475[0m[0m | time: 0.002s
[2K
| Adam | epoch: 111 | loss: 1.35475 - acc: 0.2590 -- iter: 08/29
[A[ATraining Step: 442 | total loss: [1m[32m1.33682[0m[0m | time: 0.005s
[2K
| Adam | epoch: 111 | loss: 1.33682 - acc: 0.2581 -- iter: 16/29
[A[ATraining Step: 443 | total loss: [1m[32m1.31235[0m[0m | time: 0.007s
[2K
| Adam | epoch: 111 | loss: 1.31235 - acc: 0.2823 -- iter: 24/29
[A[ATraining Step: 444 | total loss: [1m[32m1.29408[0m[0m | time: 0.010s
[2K
| Adam | epoch: 111 | loss: 1.29408 - acc: 0.2791 -- iter: 29/29
--
Training Step: 445 | total loss: [1m[32m1.25104[0m[0m | time: 0.002s
[2K
| Adam | epoch: 112 | loss: 1.25104 - acc: 0.3312 -- iter: 08/29
[A[ATraining Step: 446 | total loss: [1m[32m1.21239[0m[0m | time: 0.005s
[2K
| Adam | epoch: 112 | loss: 1.21239 - acc: 0.3780 -- iter: 16/29
[A[ATraining Step: 447 | total loss: [1m[32m1.20911[0m[0m | time: 0.007s
[2K
| Adam | epoch: 112 | loss: 1.20911 - acc: 0.3902 -- iter: 24/29
[A[ATraining Step: 448 | total loss: [1m[32m1.21318[0m[0m | time: 0.010s
[2K
| Adam | epoch: 112 | loss: 1.21318 - acc: 0.3887 -- iter: 29/29
--
Training Step: 449 | total loss: [1m[32m1.20721[0m[0m | time: 0.003s
[2K
| Adam | epoch: 113 | loss: 1.20721 - acc: 0.3873 -- iter: 08/29
[A[ATraining Step: 450 | total loss: [1m[32m1.18042[0m[0m | time: 0.005s
[2K
| Adam | epoch: 113 | loss: 1.18042 - acc: 0.4286 -- iter: 16/29
[A[ATraining Step: 451 | total loss: [1m[32m1.15609[0m[0m | time: 0.007s
[2K
| Adam | epoch: 113 | loss: 1.15609 - acc: 0.4658 -- iter: 24/29
[A[ATraining Step: 452 | total loss: [1m[32m1.16299[0m[0m | time: 0.010s
[2K
| Adam | epoch: 113 | loss: 1.16299 - acc: 0.4567 -- iter: 29/29
--
Training Step: 453 | total loss: [1m[32m1.15993[0m[0m | time: 0.002s
[2K
| Adam | epoch: 114 | loss: 1.15993 - acc: 0.4485 -- iter: 08/29
[A[ATraining Step: 454 | total loss: [1m[32m1.15695[0m[0m | time: 0.005s
[2K
| Adam | epoch: 114 | loss: 1.15695 - acc: 0.4662 -- iter: 16/29
[A[ATraining Step: 455 | total loss: [1m[32m1.14278[0m[0m | time: 0.007s
[2K
| Adam | epoch: 114 | loss: 1.14278 - acc: 0.4595 -- iter: 24/29
[A[ATraining Step: 456 | total loss: [1m[32m1.12998[0m[0m | time: 0.010s
[2K
| Adam | epoch: 114 | loss: 1.12998 - acc: 0.4536 -- iter: 29/29
--
Training Step: 457 | total loss: [1m[32m1.14842[0m[0m | time: 0.003s
[2K
| Adam | epoch: 115 | loss: 1.14842 - acc: 0.4207 -- iter: 08/29
[A[ATraining Step: 458 | total loss: [1m[32m1.13472[0m[0m | time: 0.005s
[2K
| Adam | epoch: 115 | loss: 1.13472 - acc: 0.4287 -- iter: 16/29
[A[ATraining Step: 459 | total loss: [1m[32m1.12840[0m[0m | time: 0.007s
[2K
| Adam | epoch: 115 | loss: 1.12840 - acc: 0.4358 -- iter: 24/29
[A[ATraining Step: 460 | total loss: [1m[32m1.13551[0m[0m | time: 0.022s
[2K
| Adam | epoch: 115 | loss: 1.13551 - acc: 0.4522 -- iter: 29/29
--
Training Step: 461 | total loss: [1m[32m1.14160[0m[0m | time: 0.003s
[2K
| Adam | epoch: 116 | loss: 1.14160 - acc: 0.4670 -- iter: 08/29
[A[ATraining Step: 462 | total loss: [1m[32m1.13967[0m[0m | time: 0.006s
[2K
| Adam | epoch: 116 | loss: 1.13967 - acc: 0.4453 -- iter: 16/29
[A[ATraining Step: 463 | total loss: [1m[32m1.13998[0m[0m | time: 0.009s
[2K
| Adam | epoch: 116 | loss: 1.13998 - acc: 0.4508 -- iter: 24/29
[A[ATraining Step: 464 | total loss: [1m[32m1.12561[0m[0m | time: 0.011s
[2K
| Adam | epoch: 116 | loss: 1.12561 - acc: 0.4682 -- iter: 29/29
--
Training Step: 465 | total loss: [1m[32m1.13827[0m[0m | time: 0.003s
[2K
| Adam | epoch: 117 | loss: 1.13827 - acc: 0.4614 -- iter: 08/29
[A[ATraining Step: 466 | total loss: [1m[32m1.14948[0m[0m | time: 0.006s
[2K
| Adam | epoch: 117 | loss: 1.14948 - acc: 0.4552 -- iter: 16/29
[A[ATraining Step: 467 | total loss: [1m[32m1.14121[0m[0m | time: 0.010s
[2K
| Adam | epoch: 117 | loss: 1.14121 - acc: 0.4347 -- iter: 24/29
[A[ATraining Step: 468 | total loss: [1m[32m1.15026[0m[0m | time: 0.012s
[2K
| Adam | epoch: 117 | loss: 1.15026 - acc: 0.4287 -- iter: 29/29
--
Training Step: 469 | total loss: [1m[32m1.15827[0m[0m | time: 0.003s
[2K
| Adam | epoch: 118 | loss: 1.15827 - acc: 0.4234 -- iter: 08/29
[A[ATraining Step: 470 | total loss: [1m[32m1.15494[0m[0m | time: 0.005s
[2K
| Adam | epoch: 118 | loss: 1.15494 - acc: 0.4210 -- iter: 16/29
[A[ATraining Step: 471 | total loss: [1m[32m1.15189[0m[0m | time: 0.008s
[2K
| Adam | epoch: 118 | loss: 1.15189 - acc: 0.4189 -- iter: 24/29
[A[ATraining Step: 472 | total loss: [1m[32m1.14909[0m[0m | time: 0.012s
[2K
| Adam | epoch: 118 | loss: 1.14909 - acc: 0.4395 -- iter: 29/29
--
Training Step: 473 | total loss: [1m[32m1.13508[0m[0m | time: 0.003s
[2K
| Adam | epoch: 119 | loss: 1.13508 - acc: 0.4206 -- iter: 08/29
[A[ATraining Step: 474 | total loss: [1m[32m1.12562[0m[0m | time: 0.006s
[2K
| Adam | epoch: 119 | loss: 1.12562 - acc: 0.4160 -- iter: 16/29
[A[ATraining Step: 475 | total loss: [1m[32m1.13557[0m[0m | time: 0.010s
[2K
| Adam | epoch: 119 | loss: 1.13557 - acc: 0.3944 -- iter: 24/29
[A[ATraining Step: 476 | total loss: [1m[32m1.14448[0m[0m | time: 0.014s
[2K
| Adam | epoch: 119 | loss: 1.14448 - acc: 0.3750 -- iter: 29/29
--
Training Step: 477 | total loss: [1m[32m1.13712[0m[0m | time: 0.003s
[2K
| Adam | epoch: 120 | loss: 1.13712 - acc: 0.4125 -- iter: 08/29
[A[ATraining Step: 478 | total loss: [1m[32m1.14198[0m[0m | time: 0.007s
[2K
| Adam | epoch: 120 | loss: 1.14198 - acc: 0.3962 -- iter: 16/29
[A[ATraining Step: 479 | total loss: [1m[32m1.11819[0m[0m | time: 0.010s
[2K
| Adam | epoch: 120 | loss: 1.11819 - acc: 0.4066 -- iter: 24/29
[A[ATraining Step: 480 | total loss: [1m[32m1.11937[0m[0m | time: 0.017s
[2K
| Adam | epoch: 120 | loss: 1.11937 - acc: 0.3859 -- iter: 29/29
--
Training Step: 481 | total loss: [1m[32m1.12011[0m[0m | time: 0.003s
[2K
| Adam | epoch: 121 | loss: 1.12011 - acc: 0.3674 -- iter: 08/29
[A[ATraining Step: 482 | total loss: [1m[32m1.14177[0m[0m | time: 0.006s
[2K
| Adam | epoch: 121 | loss: 1.14177 - acc: 0.3556 -- iter: 16/29
[A[ATraining Step: 483 | total loss: [1m[32m1.13846[0m[0m | time: 0.008s
[2K
| Adam | epoch: 121 | loss: 1.13846 - acc: 0.3826 -- iter: 24/29
[A[ATraining Step: 484 | total loss: [1m[32m1.14750[0m[0m | time: 0.012s
[2K
| Adam | epoch: 121 | loss: 1.14750 - acc: 0.3568 -- iter: 29/29
--
Training Step: 485 | total loss: [1m[32m1.14208[0m[0m | time: 0.003s
[2K
| Adam | epoch: 122 | loss: 1.14208 - acc: 0.3811 -- iter: 08/29
[A[ATraining Step: 486 | total loss: [1m[32m1.13704[0m[0m | time: 0.006s
[2K
| Adam | epoch: 122 | loss: 1.13704 - acc: 0.4030 -- iter: 16/29
[A[ATraining Step: 487 | total loss: [1m[32m1.12872[0m[0m | time: 0.009s
[2K
| Adam | epoch: 122 | loss: 1.12872 - acc: 0.4002 -- iter: 24/29
[A[ATraining Step: 488 | total loss: [1m[32m1.12443[0m[0m | time: 0.011s
[2K
| Adam | epoch: 122 | loss: 1.12443 - acc: 0.4352 -- iter: 29/29
--
Training Step: 489 | total loss: [1m[32m1.11191[0m[0m | time: 0.003s
[2K
| Adam | epoch: 123 | loss: 1.11191 - acc: 0.4417 -- iter: 08/29
[A[ATraining Step: 490 | total loss: [1m[32m1.11685[0m[0m | time: 0.006s
[2K
| Adam | epoch: 123 | loss: 1.11685 - acc: 0.4175 -- iter: 16/29
[A[ATraining Step: 491 | total loss: [1m[32m1.12103[0m[0m | time: 0.008s
[2K
| Adam | epoch: 123 | loss: 1.12103 - acc: 0.4358 -- iter: 24/29
[A[ATraining Step: 492 | total loss: [1m[32m1.13089[0m[0m | time: 0.011s
[2K
| Adam | epoch: 123 | loss: 1.13089 - acc: 0.4422 -- iter: 29/29
--
Training Step: 493 | total loss: [1m[32m1.12831[0m[0m | time: 0.003s
[2K
| Adam | epoch: 124 | loss: 1.12831 - acc: 0.4230 -- iter: 08/29
[A[ATraining Step: 494 | total loss: [1m[32m1.11213[0m[0m | time: 0.006s
[2K
| Adam | epoch: 124 | loss: 1.11213 - acc: 0.4557 -- iter: 16/29
[A[ATraining Step: 495 | total loss: [1m[32m1.12732[0m[0m | time: 0.009s
[2K
| Adam | epoch: 124 | loss: 1.12732 - acc: 0.4301 -- iter: 24/29
[A[ATraining Step: 496 | total loss: [1m[32m1.14107[0m[0m | time: 0.011s
[2K
| Adam | epoch: 124 | loss: 1.14107 - acc: 0.4071 -- iter: 29/29
--
Training Step: 497 | total loss: [1m[32m1.12846[0m[0m | time: 0.003s
[2K
| Adam | epoch: 125 | loss: 1.12846 - acc: 0.4164 -- iter: 08/29
[A[ATraining Step: 498 | total loss: [1m[32m1.14251[0m[0m | time: 0.005s
[2K
| Adam | epoch: 125 | loss: 1.14251 - acc: 0.4122 -- iter: 16/29
[A[ATraining Step: 499 | total loss: [1m[32m1.14074[0m[0m | time: 0.008s
[2K
| Adam | epoch: 125 | loss: 1.14074 - acc: 0.4085 -- iter: 24/29
[A[ATraining Step: 500 | total loss: [1m[32m1.14184[0m[0m | time: 0.010s
[2K
| Adam | epoch: 125 | loss: 1.14184 - acc: 0.4077 -- iter: 29/29
--
Training Step: 501 | total loss: [1m[32m1.14252[0m[0m | time: 0.003s
[2K
| Adam | epoch: 126 | loss: 1.14252 - acc: 0.4069 -- iter: 08/29
[A[ATraining Step: 502 | total loss: [1m[32m1.13590[0m[0m | time: 0.005s
[2K
| Adam | epoch: 126 | loss: 1.13590 - acc: 0.4537 -- iter: 16/29
[A[ATraining Step: 503 | total loss: [1m[32m1.13402[0m[0m | time: 0.008s
[2K
| Adam | epoch: 126 | loss: 1.13402 - acc: 0.4458 -- iter: 24/29
[A[ATraining Step: 504 | total loss: [1m[32m1.12091[0m[0m | time: 0.011s
[2K
| Adam | epoch: 126 | loss: 1.12091 - acc: 0.4638 -- iter: 29/29
--
Training Step: 505 | total loss: [1m[32m1.15201[0m[0m | time: 0.003s
[2K
| Adam | epoch: 127 | loss: 1.15201 - acc: 0.4174 -- iter: 08/29
[A[ATraining Step: 506 | total loss: [1m[32m1.17994[0m[0m | time: 0.005s
[2K
| Adam | epoch: 127 | loss: 1.17994 - acc: 0.3756 -- iter: 16/29
[A[ATraining Step: 507 | total loss: [1m[32m1.18527[0m[0m | time: 0.008s
[2K
| Adam | epoch: 127 | loss: 1.18527 - acc: 0.3631 -- iter: 24/29
[A[ATraining Step: 508 | total loss: [1m[32m1.15681[0m[0m | time: 0.011s
[2K
| Adam | epoch: 127 | loss: 1.15681 - acc: 0.4018 -- iter: 29/29
--
Training Step: 509 | total loss: [1m[32m1.15309[0m[0m | time: 0.003s
[2K
| Adam | epoch: 128 | loss: 1.15309 - acc: 0.4241 -- iter: 08/29
[A[ATraining Step: 510 | total loss: [1m[32m1.17546[0m[0m | time: 0.005s
[2K
| Adam | epoch: 128 | loss: 1.17546 - acc: 0.4217 -- iter: 16/29
[A[ATraining Step: 511 | total loss: [1m[32m1.19531[0m[0m | time: 0.008s
[2K
| Adam | epoch: 128 | loss: 1.19531 - acc: 0.4195 -- iter: 24/29
[A[ATraining Step: 512 | total loss: [1m[32m1.18245[0m[0m | time: 0.025s
[2K
| Adam | epoch: 128 | loss: 1.18245 - acc: 0.4151 -- iter: 29/29
--
Training Step: 513 | total loss: [1m[32m1.16210[0m[0m | time: 0.003s
[2K
| Adam | epoch: 129 | loss: 1.16210 - acc: 0.4236 -- iter: 08/29
[A[ATraining Step: 514 | total loss: [1m[32m1.15974[0m[0m | time: 0.005s
[2K
| Adam | epoch: 129 | loss: 1.15974 - acc: 0.4437 -- iter: 16/29
[A[ATraining Step: 515 | total loss: [1m[32m1.15942[0m[0m | time: 0.008s
[2K
| Adam | epoch: 129 | loss: 1.15942 - acc: 0.4393 -- iter: 24/29
[A[ATraining Step: 516 | total loss: [1m[32m1.15895[0m[0m | time: 0.011s
[2K
| Adam | epoch: 129 | loss: 1.15895 - acc: 0.4354 -- iter: 29/29
--
Training Step: 517 | total loss: [1m[32m1.14977[0m[0m | time: 0.003s
[2K
| Adam | epoch: 130 | loss: 1.14977 - acc: 0.4419 -- iter: 08/29
[A[ATraining Step: 518 | total loss: [1m[32m1.14430[0m[0m | time: 0.005s
[2K
| Adam | epoch: 130 | loss: 1.14430 - acc: 0.4352 -- iter: 16/29
[A[ATraining Step: 519 | total loss: [1m[32m1.13489[0m[0m | time: 0.008s
[2K
| Adam | epoch: 130 | loss: 1.13489 - acc: 0.4542 -- iter: 24/29
[A[ATraining Step: 520 | total loss: [1m[32m1.15099[0m[0m | time: 0.011s
[2K
| Adam | epoch: 130 | loss: 1.15099 - acc: 0.4487 -- iter: 29/29
--
Training Step: 521 | total loss: [1m[32m1.16527[0m[0m | time: 0.002s
[2K
| Adam | epoch: 131 | loss: 1.16527 - acc: 0.4439 -- iter: 08/29
[A[ATraining Step: 522 | total loss: [1m[32m1.15205[0m[0m | time: 0.005s
[2K
| Adam | epoch: 131 | loss: 1.15205 - acc: 0.4370 -- iter: 16/29
[A[ATraining Step: 523 | total loss: [1m[32m1.14924[0m[0m | time: 0.008s
[2K
| Adam | epoch: 131 | loss: 1.14924 - acc: 0.4308 -- iter: 24/29
[A[ATraining Step: 524 | total loss: [1m[32m1.14258[0m[0m | time: 0.011s
[2K
| Adam | epoch: 131 | loss: 1.14258 - acc: 0.4127 -- iter: 29/29
--
Training Step: 525 | total loss: [1m[32m1.12738[0m[0m | time: 0.003s
[2K
| Adam | epoch: 132 | loss: 1.12738 - acc: 0.4514 -- iter: 08/29
[A[ATraining Step: 526 | total loss: [1m[32m1.11364[0m[0m | time: 0.006s
[2K
| Adam | epoch: 132 | loss: 1.11364 - acc: 0.4863 -- iter: 16/29
[A[ATraining Step: 527 | total loss: [1m[32m1.11657[0m[0m | time: 0.008s
[2K
| Adam | epoch: 132 | loss: 1.11657 - acc: 0.4877 -- iter: 24/29
[A[ATraining Step: 528 | total loss: [1m[32m1.12136[0m[0m | time: 0.011s
[2K
| Adam | epoch: 132 | loss: 1.12136 - acc: 0.4764 -- iter: 29/29
--
Training Step: 529 | total loss: [1m[32m1.11491[0m[0m | time: 0.003s
[2K
| Adam | epoch: 133 | loss: 1.11491 - acc: 0.4788 -- iter: 08/29
[A[ATraining Step: 530 | total loss: [1m[32m1.11092[0m[0m | time: 0.006s
[2K
| Adam | epoch: 133 | loss: 1.11092 - acc: 0.4309 -- iter: 16/29
[A[ATraining Step: 531 | total loss: [1m[32m1.10679[0m[0m | time: 0.008s
[2K
| Adam | epoch: 133 | loss: 1.10679 - acc: 0.3878 -- iter: 24/29
[A[ATraining Step: 532 | total loss: [1m[32m1.10595[0m[0m | time: 0.011s
[2K
| Adam | epoch: 133 | loss: 1.10595 - acc: 0.3990 -- iter: 29/29
--
Training Step: 533 | total loss: [1m[32m1.11425[0m[0m | time: 0.026s
[2K
| Adam | epoch: 134 | loss: 1.11425 - acc: 0.4216 -- iter: 08/29
[A[ATraining Step: 534 | total loss: [1m[32m1.10349[0m[0m | time: 0.029s
[2K
| Adam | epoch: 134 | loss: 1.10349 - acc: 0.4170 -- iter: 16/29
[A[ATraining Step: 535 | total loss: [1m[32m1.09882[0m[0m | time: 0.031s
[2K
| Adam | epoch: 134 | loss: 1.09882 - acc: 0.3953 -- iter: 24/29
[A[ATraining Step: 536 | total loss: [1m[32m1.09405[0m[0m | time: 0.034s
[2K
| Adam | epoch: 134 | loss: 1.09405 - acc: 0.3757 -- iter: 29/29
--
Training Step: 537 | total loss: [1m[32m1.10456[0m[0m | time: 0.003s
[2K
| Adam | epoch: 135 | loss: 1.10456 - acc: 0.4007 -- iter: 08/29
[A[ATraining Step: 538 | total loss: [1m[32m1.10881[0m[0m | time: 0.006s
[2K
| Adam | epoch: 135 | loss: 1.10881 - acc: 0.4106 -- iter: 16/29
[A[ATraining Step: 539 | total loss: [1m[32m1.10182[0m[0m | time: 0.009s
[2K
| Adam | epoch: 135 | loss: 1.10182 - acc: 0.4195 -- iter: 24/29
[A[ATraining Step: 540 | total loss: [1m[32m1.09961[0m[0m | time: 0.012s
[2K
| Adam | epoch: 135 | loss: 1.09961 - acc: 0.3976 -- iter: 29/29
--
Training Step: 541 | total loss: [1m[32m1.09721[0m[0m | time: 0.003s
[2K
| Adam | epoch: 136 | loss: 1.09721 - acc: 0.3778 -- iter: 08/29
[A[ATraining Step: 542 | total loss: [1m[32m1.09137[0m[0m | time: 0.006s
[2K
| Adam | epoch: 136 | loss: 1.09137 - acc: 0.3900 -- iter: 16/29
[A[ATraining Step: 543 | total loss: [1m[32m1.10659[0m[0m | time: 0.009s
[2K
| Adam | epoch: 136 | loss: 1.10659 - acc: 0.3760 -- iter: 24/29
[A[ATraining Step: 544 | total loss: [1m[32m1.09786[0m[0m | time: 0.012s
[2K
| Adam | epoch: 136 | loss: 1.09786 - acc: 0.4009 -- iter: 29/29
--
Training Step: 545 | total loss: [1m[32m1.08896[0m[0m | time: 0.003s
[2K
| Adam | epoch: 137 | loss: 1.08896 - acc: 0.4408 -- iter: 08/29
[A[ATraining Step: 546 | total loss: [1m[32m1.08073[0m[0m | time: 0.006s
[2K
| Adam | epoch: 137 | loss: 1.08073 - acc: 0.4768 -- iter: 16/29
[A[ATraining Step: 547 | total loss: [1m[32m1.07318[0m[0m | time: 0.009s
[2K
| Adam | epoch: 137 | loss: 1.07318 - acc: 0.4666 -- iter: 24/29
[A[ATraining Step: 548 | total loss: [1m[32m1.10020[0m[0m | time: 0.012s
[2K
| Adam | epoch: 137 | loss: 1.10020 - acc: 0.4449 -- iter: 29/29
--
Training Step: 549 | total loss: [1m[32m1.10385[0m[0m | time: 0.003s
[2K
| Adam | epoch: 138 | loss: 1.10385 - acc: 0.4504 -- iter: 08/29
[A[ATraining Step: 550 | total loss: [1m[32m1.10969[0m[0m | time: 0.006s
[2K
| Adam | epoch: 138 | loss: 1.10969 - acc: 0.4454 -- iter: 16/29
[A[ATraining Step: 551 | total loss: [1m[32m1.11479[0m[0m | time: 0.009s
[2K
| Adam | epoch: 138 | loss: 1.11479 - acc: 0.4408 -- iter: 24/29
[A[ATraining Step: 552 | total loss: [1m[32m1.11837[0m[0m | time: 0.011s
[2K
| Adam | epoch: 138 | loss: 1.11837 - acc: 0.4343 -- iter: 29/29
--
Training Step: 553 | total loss: [1m[32m1.10439[0m[0m | time: 0.003s
[2K
| Adam | epoch: 139 | loss: 1.10439 - acc: 0.4408 -- iter: 08/29
[A[ATraining Step: 554 | total loss: [1m[32m1.09829[0m[0m | time: 0.006s
[2K
| Adam | epoch: 139 | loss: 1.09829 - acc: 0.4593 -- iter: 16/29
[A[ATraining Step: 555 | total loss: [1m[32m1.08772[0m[0m | time: 0.009s
[2K
| Adam | epoch: 139 | loss: 1.08772 - acc: 0.4533 -- iter: 24/29
[A[ATraining Step: 556 | total loss: [1m[32m1.07808[0m[0m | time: 0.011s
[2K
| Adam | epoch: 139 | loss: 1.07808 - acc: 0.4480 -- iter: 29/29
--
Training Step: 557 | total loss: [1m[32m1.10704[0m[0m | time: 0.003s
[2K
| Adam | epoch: 140 | loss: 1.10704 - acc: 0.4282 -- iter: 08/29
[A[ATraining Step: 558 | total loss: [1m[32m1.09255[0m[0m | time: 0.006s
[2K
| Adam | epoch: 140 | loss: 1.09255 - acc: 0.4104 -- iter: 16/29
[A[ATraining Step: 559 | total loss: [1m[32m1.07371[0m[0m | time: 0.009s
[2K
| Adam | epoch: 140 | loss: 1.07371 - acc: 0.4318 -- iter: 24/29
[A[ATraining Step: 560 | total loss: [1m[32m1.06843[0m[0m | time: 0.012s
[2K
| Adam | epoch: 140 | loss: 1.06843 - acc: 0.4087 -- iter: 29/29
--
Training Step: 561 | total loss: [1m[32m1.06370[0m[0m | time: 0.003s
[2K
| Adam | epoch: 141 | loss: 1.06370 - acc: 0.3878 -- iter: 08/29
[A[ATraining Step: 562 | total loss: [1m[32m1.09153[0m[0m | time: 0.006s
[2K
| Adam | epoch: 141 | loss: 1.09153 - acc: 0.3740 -- iter: 16/29
[A[ATraining Step: 563 | total loss: [1m[32m1.09236[0m[0m | time: 0.009s
[2K
| Adam | epoch: 141 | loss: 1.09236 - acc: 0.3741 -- iter: 24/29
[A[ATraining Step: 564 | total loss: [1m[32m1.08808[0m[0m | time: 0.011s
[2K
| Adam | epoch: 141 | loss: 1.08808 - acc: 0.3867 -- iter: 29/29
--
Training Step: 565 | total loss: [1m[32m1.09022[0m[0m | time: 0.003s
[2K
| Adam | epoch: 142 | loss: 1.09022 - acc: 0.3880 -- iter: 08/29
[A[ATraining Step: 566 | total loss: [1m[32m1.09194[0m[0m | time: 0.006s
[2K
| Adam | epoch: 142 | loss: 1.09194 - acc: 0.3892 -- iter: 16/29
[A[ATraining Step: 567 | total loss: [1m[32m1.08503[0m[0m | time: 0.009s
[2K
| Adam | epoch: 142 | loss: 1.08503 - acc: 0.3628 -- iter: 24/29
[A[ATraining Step: 568 | total loss: [1m[32m1.09824[0m[0m | time: 0.012s
[2K
| Adam | epoch: 142 | loss: 1.09824 - acc: 0.3765 -- iter: 29/29
--
Training Step: 569 | total loss: [1m[32m1.12005[0m[0m | time: 0.003s
[2K
| Adam | epoch: 143 | loss: 1.12005 - acc: 0.3639 -- iter: 08/29
[A[ATraining Step: 570 | total loss: [1m[32m1.12761[0m[0m | time: 0.006s
[2K
| Adam | epoch: 143 | loss: 1.12761 - acc: 0.3275 -- iter: 16/29
[A[ATraining Step: 571 | total loss: [1m[32m1.13421[0m[0m | time: 0.009s
[2K
| Adam | epoch: 143 | loss: 1.13421 - acc: 0.2947 -- iter: 24/29
[A[ATraining Step: 572 | total loss: [1m[32m1.11109[0m[0m | time: 0.012s
[2K
| Adam | epoch: 143 | loss: 1.11109 - acc: 0.3153 -- iter: 29/29
--
Training Step: 573 | total loss: [1m[32m1.09998[0m[0m | time: 0.003s
[2K
| Adam | epoch: 144 | loss: 1.09998 - acc: 0.3337 -- iter: 08/29
[A[ATraining Step: 574 | total loss: [1m[32m1.10767[0m[0m | time: 0.006s
[2K
| Adam | epoch: 144 | loss: 1.10767 - acc: 0.3379 -- iter: 16/29
[A[ATraining Step: 575 | total loss: [1m[32m1.13337[0m[0m | time: 0.009s
[2K
| Adam | epoch: 144 | loss: 1.13337 - acc: 0.3241 -- iter: 24/29
[A[ATraining Step: 576 | total loss: [1m[32m1.15644[0m[0m | time: 0.012s
[2K
| Adam | epoch: 144 | loss: 1.15644 - acc: 0.3117 -- iter: 29/29
--
Training Step: 577 | total loss: [1m[32m1.14427[0m[0m | time: 0.003s
[2K
| Adam | epoch: 145 | loss: 1.14427 - acc: 0.3430 -- iter: 08/29
[A[ATraining Step: 578 | total loss: [1m[32m1.11953[0m[0m | time: 0.006s
[2K
| Adam | epoch: 145 | loss: 1.11953 - acc: 0.3587 -- iter: 16/29
[A[ATraining Step: 579 | total loss: [1m[32m1.11494[0m[0m | time: 0.009s
[2K
| Adam | epoch: 145 | loss: 1.11494 - acc: 0.3728 -- iter: 24/29
[A[ATraining Step: 580 | total loss: [1m[32m1.10696[0m[0m | time: 0.011s
[2K
| Adam | epoch: 145 | loss: 1.10696 - acc: 0.3955 -- iter: 29/29
--
Training Step: 581 | total loss: [1m[32m1.09965[0m[0m | time: 0.003s
[2K
| Adam | epoch: 146 | loss: 1.09965 - acc: 0.4160 -- iter: 08/29
[A[ATraining Step: 582 | total loss: [1m[32m1.09470[0m[0m | time: 0.006s
[2K
| Adam | epoch: 146 | loss: 1.09470 - acc: 0.4369 -- iter: 16/29
[A[ATraining Step: 583 | total loss: [1m[32m1.10378[0m[0m | time: 0.009s
[2K
| Adam | epoch: 146 | loss: 1.10378 - acc: 0.4182 -- iter: 24/29
[A[ATraining Step: 584 | total loss: [1m[32m1.08746[0m[0m | time: 0.012s
[2K
| Adam | epoch: 146 | loss: 1.08746 - acc: 0.4764 -- iter: 29/29
--
Training Step: 585 | total loss: [1m[32m1.11725[0m[0m | time: 0.003s
[2K
| Adam | epoch: 147 | loss: 1.11725 - acc: 0.4287 -- iter: 08/29
[A[ATraining Step: 586 | total loss: [1m[32m1.14411[0m[0m | time: 0.006s
[2K
| Adam | epoch: 147 | loss: 1.14411 - acc: 0.3859 -- iter: 16/29
[A[ATraining Step: 587 | total loss: [1m[32m1.14529[0m[0m | time: 0.009s
[2K
| Adam | epoch: 147 | loss: 1.14529 - acc: 0.3598 -- iter: 24/29
[A[ATraining Step: 588 | total loss: [1m[32m1.13000[0m[0m | time: 0.011s
[2K
| Adam | epoch: 147 | loss: 1.13000 - acc: 0.3863 -- iter: 29/29
--
Training Step: 589 | total loss: [1m[32m1.13228[0m[0m | time: 0.003s
[2K
| Adam | epoch: 148 | loss: 1.13228 - acc: 0.3977 -- iter: 08/29
[A[ATraining Step: 590 | total loss: [1m[32m1.10883[0m[0m | time: 0.006s
[2K
| Adam | epoch: 148 | loss: 1.10883 - acc: 0.4179 -- iter: 16/29
[A[ATraining Step: 591 | total loss: [1m[32m1.08730[0m[0m | time: 0.009s
[2K
| Adam | epoch: 148 | loss: 1.08730 - acc: 0.4361 -- iter: 24/29
[A[ATraining Step: 592 | total loss: [1m[32m1.07770[0m[0m | time: 0.011s
[2K
| Adam | epoch: 148 | loss: 1.07770 - acc: 0.4425 -- iter: 29/29
--
Training Step: 593 | total loss: [1m[32m1.09356[0m[0m | time: 0.003s
[2K
| Adam | epoch: 149 | loss: 1.09356 - acc: 0.4358 -- iter: 08/29
[A[ATraining Step: 594 | total loss: [1m[32m1.08669[0m[0m | time: 0.006s
[2K
| Adam | epoch: 149 | loss: 1.08669 - acc: 0.4547 -- iter: 16/29
[A[ATraining Step: 595 | total loss: [1m[32m1.06226[0m[0m | time: 0.008s
[2K
| Adam | epoch: 149 | loss: 1.06226 - acc: 0.4492 -- iter: 24/29
[A[ATraining Step: 596 | total loss: [1m[32m1.04047[0m[0m | time: 0.011s
[2K
| Adam | epoch: 149 | loss: 1.04047 - acc: 0.4443 -- iter: 29/29
--
Training Step: 597 | total loss: [1m[32m1.06632[0m[0m | time: 0.003s
[2K
| Adam | epoch: 150 | loss: 1.06632 - acc: 0.4124 -- iter: 08/29
[A[ATraining Step: 598 | total loss: [1m[32m1.06882[0m[0m | time: 0.005s
[2K
| Adam | epoch: 150 | loss: 1.06882 - acc: 0.4211 -- iter: 16/29
[A[ATraining Step: 599 | total loss: [1m[32m1.06935[0m[0m | time: 0.008s
[2K
| Adam | epoch: 150 | loss: 1.06935 - acc: 0.4290 -- iter: 24/29
[A[ATraining Step: 600 | total loss: [1m[32m1.05260[0m[0m | time: 0.010s
[2K
| Adam | epoch: 150 | loss: 1.05260 - acc: 0.4261 -- iter: 29/29
--
Training Step: 601 | total loss: [1m[32m1.03749[0m[0m | time: 0.003s
[2K
| Adam | epoch: 151 | loss: 1.03749 - acc: 0.4235 -- iter: 08/29
[A[ATraining Step: 602 | total loss: [1m[32m1.04921[0m[0m | time: 0.005s
[2K
| Adam | epoch: 151 | loss: 1.04921 - acc: 0.4062 -- iter: 16/29
[A[ATraining Step: 603 | total loss: [1m[32m1.05864[0m[0m | time: 0.008s
[2K
| Adam | epoch: 151 | loss: 1.05864 - acc: 0.4030 -- iter: 24/29
[A[ATraining Step: 604 | total loss: [1m[32m1.05899[0m[0m | time: 0.011s
[2K
| Adam | epoch: 151 | loss: 1.05899 - acc: 0.3877 -- iter: 29/29
--
Training Step: 605 | total loss: [1m[32m1.05620[0m[0m | time: 0.004s
[2K
| Adam | epoch: 152 | loss: 1.05620 - acc: 0.3690 -- iter: 08/29
[A[ATraining Step: 606 | total loss: [1m[32m1.05346[0m[0m | time: 0.006s
[2K
| Adam | epoch: 152 | loss: 1.05346 - acc: 0.3521 -- iter: 16/29
[A[ATraining Step: 607 | total loss: [1m[32m1.06276[0m[0m | time: 0.009s
[2K
| Adam | epoch: 152 | loss: 1.06276 - acc: 0.3669 -- iter: 24/29
[A[ATraining Step: 608 | total loss: [1m[32m1.06415[0m[0m | time: 0.012s
[2K
| Adam | epoch: 152 | loss: 1.06415 - acc: 0.3427 -- iter: 29/29
--
Training Step: 609 | total loss: [1m[32m1.05985[0m[0m | time: 0.003s
[2K
| Adam | epoch: 153 | loss: 1.05985 - acc: 0.3459 -- iter: 08/29
[A[ATraining Step: 610 | total loss: [1m[32m1.05688[0m[0m | time: 0.005s
[2K
| Adam | epoch: 153 | loss: 1.05688 - acc: 0.3313 -- iter: 16/29
[A[ATraining Step: 611 | total loss: [1m[32m1.05410[0m[0m | time: 0.008s
[2K
| Adam | epoch: 153 | loss: 1.05410 - acc: 0.3182 -- iter: 24/29
[A[ATraining Step: 612 | total loss: [1m[32m1.04615[0m[0m | time: 0.010s
[2K
| Adam | epoch: 153 | loss: 1.04615 - acc: 0.3364 -- iter: 29/29
--
Training Step: 613 | total loss: [1m[32m1.06951[0m[0m | time: 0.003s
[2K
| Adam | epoch: 154 | loss: 1.06951 - acc: 0.3402 -- iter: 08/29
[A[ATraining Step: 614 | total loss: [1m[32m1.05609[0m[0m | time: 0.005s
[2K
| Adam | epoch: 154 | loss: 1.05609 - acc: 0.3437 -- iter: 16/29
[A[ATraining Step: 615 | total loss: [1m[32m1.05924[0m[0m | time: 0.008s
[2K
| Adam | epoch: 154 | loss: 1.05924 - acc: 0.3493 -- iter: 24/29
[A[ATraining Step: 616 | total loss: [1m[32m1.06195[0m[0m | time: 0.010s
[2K
| Adam | epoch: 154 | loss: 1.06195 - acc: 0.3544 -- iter: 29/29
--
Training Step: 617 | total loss: [1m[32m1.07291[0m[0m | time: 0.003s
[2K
| Adam | epoch: 155 | loss: 1.07291 - acc: 0.3315 -- iter: 08/29
[A[ATraining Step: 618 | total loss: [1m[32m1.07843[0m[0m | time: 0.005s
[2K
| Adam | epoch: 155 | loss: 1.07843 - acc: 0.3358 -- iter: 16/29
[A[ATraining Step: 619 | total loss: [1m[32m1.10273[0m[0m | time: 0.008s
[2K
| Adam | epoch: 155 | loss: 1.10273 - acc: 0.3147 -- iter: 24/29
[A[ATraining Step: 620 | total loss: [1m[32m1.08472[0m[0m | time: 0.010s
[2K
| Adam | epoch: 155 | loss: 1.08472 - acc: 0.3433 -- iter: 29/29
--
Training Step: 621 | total loss: [1m[32m1.06832[0m[0m | time: 0.003s
[2K
| Adam | epoch: 156 | loss: 1.06832 - acc: 0.3689 -- iter: 08/29
[A[ATraining Step: 622 | total loss: [1m[32m1.06345[0m[0m | time: 0.006s
[2K
| Adam | epoch: 156 | loss: 1.06345 - acc: 0.3570 -- iter: 16/29
[A[ATraining Step: 623 | total loss: [1m[32m1.05635[0m[0m | time: 0.009s
[2K
| Adam | epoch: 156 | loss: 1.05635 - acc: 0.3588 -- iter: 24/29
[A[ATraining Step: 624 | total loss: [1m[32m1.06793[0m[0m | time: 0.012s
[2K
| Adam | epoch: 156 | loss: 1.06793 - acc: 0.3355 -- iter: 29/29
--
Training Step: 625 | total loss: [1m[32m1.06387[0m[0m | time: 0.003s
[2K
| Adam | epoch: 157 | loss: 1.06387 - acc: 0.3419 -- iter: 08/29
[A[ATraining Step: 626 | total loss: [1m[32m1.06004[0m[0m | time: 0.006s
[2K
| Adam | epoch: 157 | loss: 1.06004 - acc: 0.3477 -- iter: 16/29
[A[ATraining Step: 627 | total loss: [1m[32m1.05499[0m[0m | time: 0.008s
[2K
| Adam | epoch: 157 | loss: 1.05499 - acc: 0.3379 -- iter: 24/29
[A[ATraining Step: 628 | total loss: [1m[32m1.05760[0m[0m | time: 0.011s
[2K
| Adam | epoch: 157 | loss: 1.05760 - acc: 0.3542 -- iter: 29/29
--
Training Step: 629 | total loss: [1m[32m1.06157[0m[0m | time: 0.003s
[2K
| Adam | epoch: 158 | loss: 1.06157 - acc: 0.3687 -- iter: 08/29
[A[ATraining Step: 630 | total loss: [1m[32m1.08619[0m[0m | time: 0.006s
[2K
| Adam | epoch: 158 | loss: 1.08619 - acc: 0.3519 -- iter: 16/29
[A[ATraining Step: 631 | total loss: [1m[32m1.10822[0m[0m | time: 0.009s
[2K
| Adam | epoch: 158 | loss: 1.10822 - acc: 0.3367 -- iter: 24/29
[A[ATraining Step: 632 | total loss: [1m[32m1.09394[0m[0m | time: 0.011s
[2K
| Adam | epoch: 158 | loss: 1.09394 - acc: 0.3530 -- iter: 29/29
--
Training Step: 633 | total loss: [1m[32m1.08884[0m[0m | time: 0.003s
[2K
| Adam | epoch: 159 | loss: 1.08884 - acc: 0.3177 -- iter: 08/29
[A[ATraining Step: 634 | total loss: [1m[32m1.07371[0m[0m | time: 0.005s
[2K
| Adam | epoch: 159 | loss: 1.07371 - acc: 0.3234 -- iter: 16/29
[A[ATraining Step: 635 | total loss: [1m[32m1.11312[0m[0m | time: 0.008s
[2K
| Adam | epoch: 159 | loss: 1.11312 - acc: 0.2911 -- iter: 24/29
[A[ATraining Step: 636 | total loss: [1m[32m1.14846[0m[0m | time: 0.010s
[2K
| Adam | epoch: 159 | loss: 1.14846 - acc: 0.2620 -- iter: 29/29
--
Training Step: 637 | total loss: [1m[32m1.13753[0m[0m | time: 0.003s
[2K
| Adam | epoch: 160 | loss: 1.13753 - acc: 0.2733 -- iter: 08/29
[A[ATraining Step: 638 | total loss: [1m[32m1.12449[0m[0m | time: 0.005s
[2K
| Adam | epoch: 160 | loss: 1.12449 - acc: 0.2835 -- iter: 16/29
[A[ATraining Step: 639 | total loss: [1m[32m1.12102[0m[0m | time: 0.009s
[2K
| Adam | epoch: 160 | loss: 1.12102 - acc: 0.2801 -- iter: 24/29
[A[ATraining Step: 640 | total loss: [1m[32m1.11852[0m[0m | time: 0.012s
[2K
| Adam | epoch: 160 | loss: 1.11852 - acc: 0.2921 -- iter: 29/29
--
Training Step: 641 | total loss: [1m[32m1.11620[0m[0m | time: 0.003s
[2K
| Adam | epoch: 161 | loss: 1.11620 - acc: 0.3029 -- iter: 08/29
[A[ATraining Step: 642 | total loss: [1m[32m1.12263[0m[0m | time: 0.006s
[2K
| Adam | epoch: 161 | loss: 1.12263 - acc: 0.2976 -- iter: 16/29
[A[ATraining Step: 643 | total loss: [1m[32m1.10434[0m[0m | time: 0.009s
[2K
| Adam | epoch: 161 | loss: 1.10434 - acc: 0.3178 -- iter: 24/29
[A[ATraining Step: 644 | total loss: [1m[32m1.07202[0m[0m | time: 0.012s
[2K
| Adam | epoch: 161 | loss: 1.07202 - acc: 0.3486 -- iter: 29/29
--
Training Step: 645 | total loss: [1m[32m1.06515[0m[0m | time: 0.003s
[2K
| Adam | epoch: 162 | loss: 1.06515 - acc: 0.3337 -- iter: 08/29
[A[ATraining Step: 646 | total loss: [1m[32m1.05868[0m[0m | time: 0.005s
[2K
| Adam | epoch: 162 | loss: 1.05868 - acc: 0.3203 -- iter: 16/29
[A[ATraining Step: 647 | total loss: [1m[32m1.08697[0m[0m | time: 0.008s
[2K
| Adam | epoch: 162 | loss: 1.08697 - acc: 0.3133 -- iter: 24/29
[A[ATraining Step: 648 | total loss: [1m[32m1.09254[0m[0m | time: 0.011s
[2K
| Adam | epoch: 162 | loss: 1.09254 - acc: 0.3195 -- iter: 29/29
--
Training Step: 649 | total loss: [1m[32m1.09205[0m[0m | time: 0.003s
[2K
| Adam | epoch: 163 | loss: 1.09205 - acc: 0.3375 -- iter: 08/29
[A[ATraining Step: 650 | total loss: [1m[32m1.09680[0m[0m | time: 0.005s
[2K
| Adam | epoch: 163 | loss: 1.09680 - acc: 0.3638 -- iter: 16/29
[A[ATraining Step: 651 | total loss: [1m[32m1.10080[0m[0m | time: 0.008s
[2K
| Adam | epoch: 163 | loss: 1.10080 - acc: 0.3874 -- iter: 24/29
[A[ATraining Step: 652 | total loss: [1m[32m1.08788[0m[0m | time: 0.011s
[2K
| Adam | epoch: 163 | loss: 1.08788 - acc: 0.3862 -- iter: 29/29
--
Training Step: 653 | total loss: [1m[32m1.09037[0m[0m | time: 0.003s
[2K
| Adam | epoch: 164 | loss: 1.09037 - acc: 0.3975 -- iter: 08/29
[A[ATraining Step: 654 | total loss: [1m[32m1.08788[0m[0m | time: 0.005s
[2K
| Adam | epoch: 164 | loss: 1.08788 - acc: 0.4203 -- iter: 16/29
[A[ATraining Step: 655 | total loss: [1m[32m1.08374[0m[0m | time: 0.008s
[2K
| Adam | epoch: 164 | loss: 1.08374 - acc: 0.4183 -- iter: 24/29
[A[ATraining Step: 656 | total loss: [1m[32m1.07987[0m[0m | time: 0.011s
[2K
| Adam | epoch: 164 | loss: 1.07987 - acc: 0.4164 -- iter: 29/29
--
Training Step: 657 | total loss: [1m[32m1.08227[0m[0m | time: 0.003s
[2K
| Adam | epoch: 165 | loss: 1.08227 - acc: 0.4248 -- iter: 08/29
[A[ATraining Step: 658 | total loss: [1m[32m1.07896[0m[0m | time: 0.006s
[2K
| Adam | epoch: 165 | loss: 1.07896 - acc: 0.4198 -- iter: 16/29
[A[ATraining Step: 659 | total loss: [1m[32m1.08352[0m[0m | time: 0.008s
[2K
| Adam | epoch: 165 | loss: 1.08352 - acc: 0.4153 -- iter: 24/29
[A[ATraining Step: 660 | total loss: [1m[32m1.07933[0m[0m | time: 0.012s
[2K
| Adam | epoch: 165 | loss: 1.07933 - acc: 0.4138 -- iter: 29/29
--
Training Step: 661 | total loss: [1m[32m1.07531[0m[0m | time: 0.020s
[2K
| Adam | epoch: 166 | loss: 1.07531 - acc: 0.4124 -- iter: 08/29
[A[ATraining Step: 662 | total loss: [1m[32m1.07363[0m[0m | time: 0.023s
[2K
| Adam | epoch: 166 | loss: 1.07363 - acc: 0.4337 -- iter: 16/29
[A[ATraining Step: 663 | total loss: [1m[32m1.07034[0m[0m | time: 0.025s
[2K
| Adam | epoch: 166 | loss: 1.07034 - acc: 0.4403 -- iter: 24/29
[A[ATraining Step: 664 | total loss: [1m[32m1.08309[0m[0m | time: 0.028s
[2K
| Adam | epoch: 166 | loss: 1.08309 - acc: 0.4213 -- iter: 29/29
--
Training Step: 665 | total loss: [1m[32m1.07443[0m[0m | time: 0.003s
[2K
| Adam | epoch: 167 | loss: 1.07443 - acc: 0.4391 -- iter: 08/29
[A[ATraining Step: 666 | total loss: [1m[32m1.06591[0m[0m | time: 0.006s
[2K
| Adam | epoch: 167 | loss: 1.06591 - acc: 0.4752 -- iter: 16/29
[A[ATraining Step: 667 | total loss: [1m[32m1.07572[0m[0m | time: 0.010s
[2K
| Adam | epoch: 167 | loss: 1.07572 - acc: 0.4527 -- iter: 24/29
[A[ATraining Step: 668 | total loss: [1m[32m1.05787[0m[0m | time: 0.012s
[2K
| Adam | epoch: 167 | loss: 1.05787 - acc: 0.4699 -- iter: 29/29
--
Training Step: 669 | total loss: [1m[32m1.07526[0m[0m | time: 0.003s
[2K
| Adam | epoch: 168 | loss: 1.07526 - acc: 0.4479 -- iter: 08/29
[A[ATraining Step: 670 | total loss: [1m[32m1.06821[0m[0m | time: 0.005s
[2K
| Adam | epoch: 168 | loss: 1.06821 - acc: 0.4832 -- iter: 16/29
[A[ATraining Step: 671 | total loss: [1m[32m1.06131[0m[0m | time: 0.008s
[2K
| Adam | epoch: 168 | loss: 1.06131 - acc: 0.5148 -- iter: 24/29
[A[ATraining Step: 672 | total loss: [1m[32m1.05325[0m[0m | time: 0.011s
[2K
| Adam | epoch: 168 | loss: 1.05325 - acc: 0.5259 -- iter: 29/29
--
Training Step: 673 | total loss: [1m[32m1.05143[0m[0m | time: 0.003s
[2K
| Adam | epoch: 169 | loss: 1.05143 - acc: 0.4983 -- iter: 08/29
[A[ATraining Step: 674 | total loss: [1m[32m1.04343[0m[0m | time: 0.005s
[2K
| Adam | epoch: 169 | loss: 1.04343 - acc: 0.5109 -- iter: 16/29
[A[ATraining Step: 675 | total loss: [1m[32m1.05524[0m[0m | time: 0.007s
[2K
| Adam | epoch: 169 | loss: 1.05524 - acc: 0.5198 -- iter: 24/29
[A[ATraining Step: 676 | total loss: [1m[32m1.06548[0m[0m | time: 0.010s
[2K
| Adam | epoch: 169 | loss: 1.06548 - acc: 0.5279 -- iter: 29/29
--
Training Step: 677 | total loss: [1m[32m1.07537[0m[0m | time: 0.002s
[2K
| Adam | epoch: 170 | loss: 1.07537 - acc: 0.4876 -- iter: 08/29
[A[ATraining Step: 678 | total loss: [1m[32m1.06949[0m[0m | time: 0.005s
[2K
| Adam | epoch: 170 | loss: 1.06949 - acc: 0.4888 -- iter: 16/29
[A[ATraining Step: 679 | total loss: [1m[32m1.06754[0m[0m | time: 0.007s
[2K
| Adam | epoch: 170 | loss: 1.06754 - acc: 0.4774 -- iter: 24/29
[A[ATraining Step: 680 | total loss: [1m[32m1.08208[0m[0m | time: 0.010s
[2K
| Adam | epoch: 170 | loss: 1.08208 - acc: 0.4497 -- iter: 29/29
--
Training Step: 681 | total loss: [1m[32m1.09504[0m[0m | time: 0.002s
[2K
| Adam | epoch: 171 | loss: 1.09504 - acc: 0.4247 -- iter: 08/29
[A[ATraining Step: 682 | total loss: [1m[32m1.10076[0m[0m | time: 0.005s
[2K
| Adam | epoch: 171 | loss: 1.10076 - acc: 0.4198 -- iter: 16/29
[A[ATraining Step: 683 | total loss: [1m[32m1.08119[0m[0m | time: 0.007s
[2K
| Adam | epoch: 171 | loss: 1.08119 - acc: 0.4403 -- iter: 24/29
[A[ATraining Step: 684 | total loss: [1m[32m1.08367[0m[0m | time: 0.010s
[2K
| Adam | epoch: 171 | loss: 1.08367 - acc: 0.4212 -- iter: 29/29
--
Training Step: 685 | total loss: [1m[32m1.07224[0m[0m | time: 0.002s
[2K
| Adam | epoch: 172 | loss: 1.07224 - acc: 0.4191 -- iter: 08/29
[A[ATraining Step: 686 | total loss: [1m[32m1.06150[0m[0m | time: 0.005s
[2K
| Adam | epoch: 172 | loss: 1.06150 - acc: 0.4372 -- iter: 16/29
[A[ATraining Step: 687 | total loss: [1m[32m1.06978[0m[0m | time: 0.008s
[2K
| Adam | epoch: 172 | loss: 1.06978 - acc: 0.4310 -- iter: 24/29
[A[ATraining Step: 688 | total loss: [1m[32m1.06387[0m[0m | time: 0.011s
[2K
| Adam | epoch: 172 | loss: 1.06387 - acc: 0.4504 -- iter: 29/29
--
Training Step: 689 | total loss: [1m[32m1.04831[0m[0m | time: 0.002s
[2K
| Adam | epoch: 173 | loss: 1.04831 - acc: 0.4554 -- iter: 08/29
[A[ATraining Step: 690 | total loss: [1m[32m1.05901[0m[0m | time: 0.005s
[2K
| Adam | epoch: 173 | loss: 1.05901 - acc: 0.4298 -- iter: 16/29
[A[ATraining Step: 691 | total loss: [1m[32m1.06847[0m[0m | time: 0.007s
[2K
| Adam | epoch: 173 | loss: 1.06847 - acc: 0.4068 -- iter: 24/29
[A[ATraining Step: 692 | total loss: [1m[32m1.07213[0m[0m | time: 0.010s
[2K
| Adam | epoch: 173 | loss: 1.07213 - acc: 0.4287 -- iter: 29/29
--
Training Step: 693 | total loss: [1m[32m1.07589[0m[0m | time: 0.002s
[2K
| Adam | epoch: 174 | loss: 1.07589 - acc: 0.4358 -- iter: 08/29
[A[ATraining Step: 694 | total loss: [1m[32m1.05914[0m[0m | time: 0.005s
[2K
| Adam | epoch: 174 | loss: 1.05914 - acc: 0.4297 -- iter: 16/29
[A[ATraining Step: 695 | total loss: [1m[32m1.06709[0m[0m | time: 0.007s
[2K
| Adam | epoch: 174 | loss: 1.06709 - acc: 0.4267 -- iter: 24/29
[A[ATraining Step: 696 | total loss: [1m[32m1.07397[0m[0m | time: 0.009s
[2K
| Adam | epoch: 174 | loss: 1.07397 - acc: 0.4241 -- iter: 29/29
--
Training Step: 697 | total loss: [1m[32m1.07263[0m[0m | time: 0.002s
[2K
| Adam | epoch: 175 | loss: 1.07263 - acc: 0.4442 -- iter: 08/29
[A[ATraining Step: 698 | total loss: [1m[32m1.08134[0m[0m | time: 0.005s
[2K
| Adam | epoch: 175 | loss: 1.08134 - acc: 0.4497 -- iter: 16/29
[A[ATraining Step: 699 | total loss: [1m[32m1.08057[0m[0m | time: 0.007s
[2K
| Adam | epoch: 175 | loss: 1.08057 - acc: 0.4673 -- iter: 24/29
[A[ATraining Step: 700 | total loss: [1m[32m1.07426[0m[0m | time: 0.009s
[2K
| Adam | epoch: 175 | loss: 1.07426 - acc: 0.4805 -- iter: 29/29
--
Training Step: 701 | total loss: [1m[32m1.06802[0m[0m | time: 0.003s
[2K
| Adam | epoch: 176 | loss: 1.06802 - acc: 0.4925 -- iter: 08/29
[A[ATraining Step: 702 | total loss: [1m[32m1.06389[0m[0m | time: 0.005s
[2K
| Adam | epoch: 176 | loss: 1.06389 - acc: 0.4807 -- iter: 16/29
[A[ATraining Step: 703 | total loss: [1m[32m1.06817[0m[0m | time: 0.007s
[2K
| Adam | epoch: 176 | loss: 1.06817 - acc: 0.4702 -- iter: 24/29
[A[ATraining Step: 704 | total loss: [1m[32m1.05162[0m[0m | time: 0.009s
[2K
| Adam | epoch: 176 | loss: 1.05162 - acc: 0.4856 -- iter: 29/29
--
Training Step: 705 | total loss: [1m[32m1.07089[0m[0m | time: 0.003s
[2K
| Adam | epoch: 177 | loss: 1.07089 - acc: 0.4571 -- iter: 08/29
[A[ATraining Step: 706 | total loss: [1m[32m1.08813[0m[0m | time: 0.005s
[2K
| Adam | epoch: 177 | loss: 1.08813 - acc: 0.4314 -- iter: 16/29
[A[ATraining Step: 707 | total loss: [1m[32m1.07698[0m[0m | time: 0.007s
[2K
| Adam | epoch: 177 | loss: 1.07698 - acc: 0.4382 -- iter: 24/29
[A[ATraining Step: 708 | total loss: [1m[32m1.08675[0m[0m | time: 0.010s
[2K
| Adam | epoch: 177 | loss: 1.08675 - acc: 0.4319 -- iter: 29/29
--
Training Step: 709 | total loss: [1m[32m1.10061[0m[0m | time: 0.002s
[2K
| Adam | epoch: 178 | loss: 1.10061 - acc: 0.4137 -- iter: 08/29
[A[ATraining Step: 710 | total loss: [1m[32m1.09033[0m[0m | time: 0.005s
[2K
| Adam | epoch: 178 | loss: 1.09033 - acc: 0.4323 -- iter: 16/29
[A[ATraining Step: 711 | total loss: [1m[32m1.08104[0m[0m | time: 0.007s
[2K
| Adam | epoch: 178 | loss: 1.08104 - acc: 0.4491 -- iter: 24/29
[A[ATraining Step: 712 | total loss: [1m[32m1.07397[0m[0m | time: 0.010s
[2K
| Adam | epoch: 178 | loss: 1.07397 - acc: 0.4292 -- iter: 29/29
--
Training Step: 713 | total loss: [1m[32m1.06296[0m[0m | time: 0.002s
[2K
| Adam | epoch: 179 | loss: 1.06296 - acc: 0.4488 -- iter: 08/29
[A[ATraining Step: 714 | total loss: [1m[32m1.04063[0m[0m | time: 0.005s
[2K
| Adam | epoch: 179 | loss: 1.04063 - acc: 0.4414 -- iter: 16/29
[A[ATraining Step: 715 | total loss: [1m[32m1.04414[0m[0m | time: 0.007s
[2K
| Adam | epoch: 179 | loss: 1.04414 - acc: 0.4173 -- iter: 24/29
[A[ATraining Step: 716 | total loss: [1m[32m1.04726[0m[0m | time: 0.009s
[2K
| Adam | epoch: 179 | loss: 1.04726 - acc: 0.3955 -- iter: 29/29
--
Training Step: 717 | total loss: [1m[32m1.05395[0m[0m | time: 0.002s
[2K
| Adam | epoch: 180 | loss: 1.05395 - acc: 0.4060 -- iter: 08/29
[A[ATraining Step: 718 | total loss: [1m[32m1.06735[0m[0m | time: 0.004s
[2K
| Adam | epoch: 180 | loss: 1.06735 - acc: 0.4029 -- iter: 16/29
[A[ATraining Step: 719 | total loss: [1m[32m1.07778[0m[0m | time: 0.007s
[2K
| Adam | epoch: 180 | loss: 1.07778 - acc: 0.3876 -- iter: 24/29
[A[ATraining Step: 720 | total loss: [1m[32m1.07631[0m[0m | time: 0.009s
[2K
| Adam | epoch: 180 | loss: 1.07631 - acc: 0.4088 -- iter: 29/29
--
Training Step: 721 | total loss: [1m[32m1.07452[0m[0m | time: 0.002s
[2K
| Adam | epoch: 181 | loss: 1.07452 - acc: 0.4280 -- iter: 08/29
[A[ATraining Step: 722 | total loss: [1m[32m1.07758[0m[0m | time: 0.005s
[2K
| Adam | epoch: 181 | loss: 1.07758 - acc: 0.4227 -- iter: 16/29
[A[ATraining Step: 723 | total loss: [1m[32m1.05721[0m[0m | time: 0.008s
[2K
| Adam | epoch: 181 | loss: 1.05721 - acc: 0.4429 -- iter: 24/29
[A[ATraining Step: 724 | total loss: [1m[32m1.06045[0m[0m | time: 0.010s
[2K
| Adam | epoch: 181 | loss: 1.06045 - acc: 0.4361 -- iter: 29/29
--
Training Step: 725 | total loss: [1m[32m1.05096[0m[0m | time: 0.020s
[2K
| Adam | epoch: 182 | loss: 1.05096 - acc: 0.4325 -- iter: 08/29
[A[ATraining Step: 726 | total loss: [1m[32m1.04176[0m[0m | time: 0.023s
[2K
| Adam | epoch: 182 | loss: 1.04176 - acc: 0.4292 -- iter: 16/29
[A[ATraining Step: 727 | total loss: [1m[32m1.02586[0m[0m | time: 0.025s
[2K
| Adam | epoch: 182 | loss: 1.02586 - acc: 0.4613 -- iter: 24/29
[A[ATraining Step: 728 | total loss: [1m[32m1.04657[0m[0m | time: 0.028s
[2K
| Adam | epoch: 182 | loss: 1.04657 - acc: 0.4527 -- iter: 29/29
--
Training Step: 729 | total loss: [1m[32m1.03946[0m[0m | time: 0.003s
[2K
| Adam | epoch: 183 | loss: 1.03946 - acc: 0.4449 -- iter: 08/29
[A[ATraining Step: 730 | total loss: [1m[32m1.04634[0m[0m | time: 0.005s
[2K
| Adam | epoch: 183 | loss: 1.04634 - acc: 0.4404 -- iter: 16/29
[A[ATraining Step: 731 | total loss: [1m[32m1.05262[0m[0m | time: 0.008s
[2K
| Adam | epoch: 183 | loss: 1.05262 - acc: 0.4364 -- iter: 24/29
[A[ATraining Step: 732 | total loss: [1m[32m1.05457[0m[0m | time: 0.010s
[2K
| Adam | epoch: 183 | loss: 1.05457 - acc: 0.4427 -- iter: 29/29
--
Training Step: 733 | total loss: [1m[32m1.05440[0m[0m | time: 0.002s
[2K
| Adam | epoch: 184 | loss: 1.05440 - acc: 0.4485 -- iter: 08/29
[A[ATraining Step: 734 | total loss: [1m[32m1.03072[0m[0m | time: 0.005s
[2K
| Adam | epoch: 184 | loss: 1.03072 - acc: 0.4786 -- iter: 16/29
[A[ATraining Step: 735 | total loss: [1m[32m1.04280[0m[0m | time: 0.007s
[2K
| Adam | epoch: 184 | loss: 1.04280 - acc: 0.4508 -- iter: 24/29
[A[ATraining Step: 736 | total loss: [1m[32m1.05333[0m[0m | time: 0.010s
[2K
| Adam | epoch: 184 | loss: 1.05333 - acc: 0.4257 -- iter: 29/29
--
Training Step: 737 | total loss: [1m[32m1.05943[0m[0m | time: 0.002s
[2K
| Adam | epoch: 185 | loss: 1.05943 - acc: 0.4206 -- iter: 08/29
[A[ATraining Step: 738 | total loss: [1m[32m1.06749[0m[0m | time: 0.005s
[2K
| Adam | epoch: 185 | loss: 1.06749 - acc: 0.4286 -- iter: 16/29
[A[ATraining Step: 739 | total loss: [1m[32m1.07076[0m[0m | time: 0.008s
[2K
| Adam | epoch: 185 | loss: 1.07076 - acc: 0.4482 -- iter: 24/29
[A[ATraining Step: 740 | total loss: [1m[32m1.05569[0m[0m | time: 0.011s
[2K
| Adam | epoch: 185 | loss: 1.05569 - acc: 0.4834 -- iter: 29/29
--
Training Step: 741 | total loss: [1m[32m1.04191[0m[0m | time: 0.002s
[2K
| Adam | epoch: 186 | loss: 1.04191 - acc: 0.5150 -- iter: 08/29
[A[ATraining Step: 742 | total loss: [1m[32m1.03588[0m[0m | time: 0.005s
[2K
| Adam | epoch: 186 | loss: 1.03588 - acc: 0.5010 -- iter: 16/29
[A[ATraining Step: 743 | total loss: [1m[32m1.04485[0m[0m | time: 0.007s
[2K
| Adam | epoch: 186 | loss: 1.04485 - acc: 0.4759 -- iter: 24/29
[A[ATraining Step: 744 | total loss: [1m[32m1.03893[0m[0m | time: 0.010s
[2K
| Adam | epoch: 186 | loss: 1.03893 - acc: 0.4783 -- iter: 29/29
--
Training Step: 745 | total loss: [1m[32m1.03764[0m[0m | time: 0.002s
[2K
| Adam | epoch: 187 | loss: 1.03764 - acc: 0.4505 -- iter: 08/29
[A[ATraining Step: 746 | total loss: [1m[32m1.03647[0m[0m | time: 0.005s
[2K
| Adam | epoch: 187 | loss: 1.03647 - acc: 0.4255 -- iter: 16/29
[A[ATraining Step: 747 | total loss: [1m[32m1.02967[0m[0m | time: 0.009s
[2K
| Adam | epoch: 187 | loss: 1.02967 - acc: 0.4454 -- iter: 24/29
[A[ATraining Step: 748 | total loss: [1m[32m1.04489[0m[0m | time: 0.012s
[2K
| Adam | epoch: 187 | loss: 1.04489 - acc: 0.4509 -- iter: 29/29
--
Training Step: 749 | total loss: [1m[32m1.03019[0m[0m | time: 0.003s
[2K
| Adam | epoch: 188 | loss: 1.03019 - acc: 0.4808 -- iter: 08/29
[A[ATraining Step: 750 | total loss: [1m[32m1.02344[0m[0m | time: 0.006s
[2K
| Adam | epoch: 188 | loss: 1.02344 - acc: 0.4527 -- iter: 16/29
[A[ATraining Step: 751 | total loss: [1m[32m1.01685[0m[0m | time: 0.008s
[2K
| Adam | epoch: 188 | loss: 1.01685 - acc: 0.4274 -- iter: 24/29
[A[ATraining Step: 752 | total loss: [1m[32m1.02444[0m[0m | time: 0.011s
[2K
| Adam | epoch: 188 | loss: 1.02444 - acc: 0.4472 -- iter: 29/29
--
Training Step: 753 | total loss: [1m[32m1.03905[0m[0m | time: 0.003s
[2K
| Adam | epoch: 189 | loss: 1.03905 - acc: 0.4275 -- iter: 08/29
[A[ATraining Step: 754 | total loss: [1m[32m1.03495[0m[0m | time: 0.006s
[2K
| Adam | epoch: 189 | loss: 1.03495 - acc: 0.4347 -- iter: 16/29
[A[ATraining Step: 755 | total loss: [1m[32m1.02308[0m[0m | time: 0.008s
[2K
| Adam | epoch: 189 | loss: 1.02308 - acc: 0.4513 -- iter: 24/29
[A[ATraining Step: 756 | total loss: [1m[32m1.01241[0m[0m | time: 0.011s
[2K
| Adam | epoch: 189 | loss: 1.01241 - acc: 0.4661 -- iter: 29/29
--
Training Step: 757 | total loss: [1m[32m1.02162[0m[0m | time: 0.003s
[2K
| Adam | epoch: 190 | loss: 1.02162 - acc: 0.4820 -- iter: 08/29
[A[ATraining Step: 758 | total loss: [1m[32m1.02809[0m[0m | time: 0.006s
[2K
| Adam | epoch: 190 | loss: 1.02809 - acc: 0.4588 -- iter: 16/29
[A[ATraining Step: 759 | total loss: [1m[32m1.02654[0m[0m | time: 0.009s
[2K
| Adam | epoch: 190 | loss: 1.02654 - acc: 0.4379 -- iter: 24/29
[A[ATraining Step: 760 | total loss: [1m[32m1.03213[0m[0m | time: 0.012s
[2K
| Adam | epoch: 190 | loss: 1.03213 - acc: 0.4541 -- iter: 29/29
--
Training Step: 761 | total loss: [1m[32m1.03703[0m[0m | time: 0.003s
[2K
| Adam | epoch: 191 | loss: 1.03703 - acc: 0.4687 -- iter: 08/29
[A[ATraining Step: 762 | total loss: [1m[32m1.03842[0m[0m | time: 0.006s
[2K
| Adam | epoch: 191 | loss: 1.03842 - acc: 0.4594 -- iter: 16/29
[A[ATraining Step: 763 | total loss: [1m[32m1.03598[0m[0m | time: 0.009s
[2K
| Adam | epoch: 191 | loss: 1.03598 - acc: 0.4884 -- iter: 24/29
[A[ATraining Step: 764 | total loss: [1m[32m1.02683[0m[0m | time: 0.012s
[2K
| Adam | epoch: 191 | loss: 1.02683 - acc: 0.5021 -- iter: 29/29
--
Training Step: 765 | total loss: [1m[32m1.05194[0m[0m | time: 0.002s
[2K
| Adam | epoch: 192 | loss: 1.05194 - acc: 0.4519 -- iter: 08/29
[A[ATraining Step: 766 | total loss: [1m[32m1.07442[0m[0m | time: 0.009s
[2K
| Adam | epoch: 192 | loss: 1.07442 - acc: 0.4067 -- iter: 16/29
[A[ATraining Step: 767 | total loss: [1m[32m1.08071[0m[0m | time: 0.013s
[2K
| Adam | epoch: 192 | loss: 1.08071 - acc: 0.4160 -- iter: 24/29
[A[ATraining Step: 768 | total loss: [1m[32m1.05977[0m[0m | time: 0.015s
[2K
| Adam | epoch: 192 | loss: 1.05977 - acc: 0.4369 -- iter: 29/29
--
Training Step: 769 | total loss: [1m[32m1.04005[0m[0m | time: 0.003s
[2K
| Adam | epoch: 193 | loss: 1.04005 - acc: 0.4432 -- iter: 08/29
[A[ATraining Step: 770 | total loss: [1m[32m1.03910[0m[0m | time: 0.005s
[2K
| Adam | epoch: 193 | loss: 1.03910 - acc: 0.4389 -- iter: 16/29
[A[ATraining Step: 771 | total loss: [1m[32m1.03802[0m[0m | time: 0.008s
[2K
| Adam | epoch: 193 | loss: 1.03802 - acc: 0.4350 -- iter: 24/29
[A[ATraining Step: 772 | total loss: [1m[32m1.05873[0m[0m | time: 0.011s
[2K
| Adam | epoch: 193 | loss: 1.05873 - acc: 0.4165 -- iter: 29/29
--
Training Step: 773 | total loss: [1m[32m1.05256[0m[0m | time: 0.003s
[2K
| Adam | epoch: 194 | loss: 1.05256 - acc: 0.4499 -- iter: 08/29
[A[ATraining Step: 774 | total loss: [1m[32m1.04803[0m[0m | time: 0.006s
[2K
| Adam | epoch: 194 | loss: 1.04803 - acc: 0.4674 -- iter: 16/29
[A[ATraining Step: 775 | total loss: [1m[32m1.02930[0m[0m | time: 0.008s
[2K
| Adam | epoch: 194 | loss: 1.02930 - acc: 0.4606 -- iter: 24/29
[A[ATraining Step: 776 | total loss: [1m[32m1.01212[0m[0m | time: 0.011s
[2K
| Adam | epoch: 194 | loss: 1.01212 - acc: 0.4746 -- iter: 29/29
--
Training Step: 777 | total loss: [1m[32m1.02543[0m[0m | time: 0.003s
[2K
| Adam | epoch: 195 | loss: 1.02543 - acc: 0.4646 -- iter: 08/29
[A[ATraining Step: 778 | total loss: [1m[32m1.02858[0m[0m | time: 0.006s
[2K
| Adam | epoch: 195 | loss: 1.02858 - acc: 0.4682 -- iter: 16/29
[A[ATraining Step: 779 | total loss: [1m[32m1.01488[0m[0m | time: 0.008s
[2K
| Adam | epoch: 195 | loss: 1.01488 - acc: 0.5088 -- iter: 24/29
[A[ATraining Step: 780 | total loss: [1m[32m1.02697[0m[0m | time: 0.011s
[2K
| Adam | epoch: 195 | loss: 1.02697 - acc: 0.4780 -- iter: 29/29
--
Training Step: 781 | total loss: [1m[32m1.03792[0m[0m | time: 0.003s
[2K
| Adam | epoch: 196 | loss: 1.03792 - acc: 0.4502 -- iter: 08/29
[A[ATraining Step: 782 | total loss: [1m[32m1.04102[0m[0m | time: 0.005s
[2K
| Adam | epoch: 196 | loss: 1.04102 - acc: 0.4676 -- iter: 16/29
[A[ATraining Step: 783 | total loss: [1m[32m1.04436[0m[0m | time: 0.007s
[2K
| Adam | epoch: 196 | loss: 1.04436 - acc: 0.4459 -- iter: 24/29
[A[ATraining Step: 784 | total loss: [1m[32m1.04114[0m[0m | time: 0.010s
[2K
| Adam | epoch: 196 | loss: 1.04114 - acc: 0.4388 -- iter: 29/29
--
Training Step: 785 | total loss: [1m[32m1.05638[0m[0m | time: 0.003s
[2K
| Adam | epoch: 197 | loss: 1.05638 - acc: 0.4549 -- iter: 08/29
[A[ATraining Step: 786 | total loss: [1m[32m1.06988[0m[0m | time: 0.005s
[2K
| Adam | epoch: 197 | loss: 1.06988 - acc: 0.4694 -- iter: 16/29
[A[ATraining Step: 787 | total loss: [1m[32m1.07467[0m[0m | time: 0.008s
[2K
| Adam | epoch: 197 | loss: 1.07467 - acc: 0.4600 -- iter: 24/29
[A[ATraining Step: 788 | total loss: [1m[32m1.05324[0m[0m | time: 0.010s
[2K
| Adam | epoch: 197 | loss: 1.05324 - acc: 0.5015 -- iter: 29/29
--
Training Step: 789 | total loss: [1m[32m1.04891[0m[0m | time: 0.003s
[2K
| Adam | epoch: 198 | loss: 1.04891 - acc: 0.5013 -- iter: 08/29
[A[ATraining Step: 790 | total loss: [1m[32m1.07155[0m[0m | time: 0.005s
[2K
| Adam | epoch: 198 | loss: 1.07155 - acc: 0.4712 -- iter: 16/29
[A[ATraining Step: 791 | total loss: [1m[32m1.09184[0m[0m | time: 0.008s
[2K
| Adam | epoch: 198 | loss: 1.09184 - acc: 0.4441 -- iter: 24/29
[A[ATraining Step: 792 | total loss: [1m[32m1.08451[0m[0m | time: 0.010s
[2K
| Adam | epoch: 198 | loss: 1.08451 - acc: 0.4497 -- iter: 29/29
--
Training Step: 793 | total loss: [1m[32m1.06589[0m[0m | time: 0.002s
[2K
| Adam | epoch: 199 | loss: 1.06589 - acc: 0.4422 -- iter: 08/29
[A[ATraining Step: 794 | total loss: [1m[32m1.07847[0m[0m | time: 0.005s
[2K
| Adam | epoch: 199 | loss: 1.07847 - acc: 0.4355 -- iter: 16/29
[A[ATraining Step: 795 | total loss: [1m[32m1.08721[0m[0m | time: 0.008s
[2K
| Adam | epoch: 199 | loss: 1.08721 - acc: 0.4519 -- iter: 24/29
[A[ATraining Step: 796 | total loss: [1m[32m1.09486[0m[0m | time: 0.010s
[2K
| Adam | epoch: 199 | loss: 1.09486 - acc: 0.4667 -- iter: 29/29
--
Training Step: 797 | total loss: [1m[32m1.07280[0m[0m | time: 0.003s
[2K
| Adam | epoch: 200 | loss: 1.07280 - acc: 0.4826 -- iter: 08/29
[A[ATraining Step: 798 | total loss: [1m[32m1.05754[0m[0m | time: 0.005s
[2K
| Adam | epoch: 200 | loss: 1.05754 - acc: 0.4968 -- iter: 16/29
[A[ATraining Step: 799 | total loss: [1m[32m1.04732[0m[0m | time: 0.008s
[2K
| Adam | epoch: 200 | loss: 1.04732 - acc: 0.5221 -- iter: 24/29
[A[ATraining Step: 800 | total loss: [1m[32m1.02268[0m[0m | time: 0.010s
[2K
| Adam | epoch: 200 | loss: 1.02268 - acc: 0.5499 -- iter: 29/29
--
Training Step: 801 | total loss: [1m[32m1.00026[0m[0m | time: 0.003s
[2K
| Adam | epoch: 201 | loss: 1.00026 - acc: 0.5749 -- iter: 08/29
[A[ATraining Step: 802 | total loss: [1m[32m1.01828[0m[0m | time: 0.005s
[2K
| Adam | epoch: 201 | loss: 1.01828 - acc: 0.5424 -- iter: 16/29
[A[ATraining Step: 803 | total loss: [1m[32m1.02421[0m[0m | time: 0.008s
[2K
| Adam | epoch: 201 | loss: 1.02421 - acc: 0.5382 -- iter: 24/29
[A[ATraining Step: 804 | total loss: [1m[32m1.03808[0m[0m | time: 0.010s
[2K
| Adam | epoch: 201 | loss: 1.03808 - acc: 0.5094 -- iter: 29/29
--
Training Step: 805 | total loss: [1m[32m1.01449[0m[0m | time: 0.003s
[2K
| Adam | epoch: 202 | loss: 1.01449 - acc: 0.4984 -- iter: 08/29
[A[ATraining Step: 806 | total loss: [1m[32m0.99246[0m[0m | time: 0.005s
[2K
| Adam | epoch: 202 | loss: 0.99246 - acc: 0.4886 -- iter: 16/29
[A[ATraining Step: 807 | total loss: [1m[32m0.97902[0m[0m | time: 0.008s
[2K
| Adam | epoch: 202 | loss: 0.97902 - acc: 0.5397 -- iter: 24/29
[A[ATraining Step: 808 | total loss: [1m[32m1.00124[0m[0m | time: 0.010s
[2K
| Adam | epoch: 202 | loss: 1.00124 - acc: 0.5358 -- iter: 29/29
--
Training Step: 809 | total loss: [1m[32m1.00485[0m[0m | time: 0.003s
[2K
| Adam | epoch: 203 | loss: 1.00485 - acc: 0.5447 -- iter: 08/29
[A[ATraining Step: 810 | total loss: [1m[32m0.99126[0m[0m | time: 0.005s
[2K
| Adam | epoch: 203 | loss: 0.99126 - acc: 0.5702 -- iter: 16/29
[A[ATraining Step: 811 | total loss: [1m[32m0.97873[0m[0m | time: 0.009s
[2K
| Adam | epoch: 203 | loss: 0.97873 - acc: 0.5932 -- iter: 24/29
[A[ATraining Step: 812 | total loss: [1m[32m0.98491[0m[0m | time: 0.017s
[2K
| Adam | epoch: 203 | loss: 0.98491 - acc: 0.5589 -- iter: 29/29
--
Training Step: 813 | total loss: [1m[32m0.99460[0m[0m | time: 0.003s
[2K
| Adam | epoch: 204 | loss: 0.99460 - acc: 0.5405 -- iter: 08/29
[A[ATraining Step: 814 | total loss: [1m[32m0.98914[0m[0m | time: 0.006s
[2K
| Adam | epoch: 204 | loss: 0.98914 - acc: 0.5364 -- iter: 16/29
[A[ATraining Step: 815 | total loss: [1m[32m0.99875[0m[0m | time: 0.009s
[2K
| Adam | epoch: 204 | loss: 0.99875 - acc: 0.5228 -- iter: 24/29
[A[ATraining Step: 816 | total loss: [1m[32m1.00723[0m[0m | time: 0.011s
[2K
| Adam | epoch: 204 | loss: 1.00723 - acc: 0.5105 -- iter: 29/29
--
Training Step: 817 | total loss: [1m[32m1.01073[0m[0m | time: 0.003s
[2K
| Adam | epoch: 205 | loss: 1.01073 - acc: 0.4845 -- iter: 08/29
[A[ATraining Step: 818 | total loss: [1m[32m1.01312[0m[0m | time: 0.005s
[2K
| Adam | epoch: 205 | loss: 1.01312 - acc: 0.4860 -- iter: 16/29
[A[ATraining Step: 819 | total loss: [1m[32m1.00330[0m[0m | time: 0.008s
[2K
| Adam | epoch: 205 | loss: 1.00330 - acc: 0.4999 -- iter: 24/29
[A[ATraining Step: 820 | total loss: [1m[32m1.02550[0m[0m | time: 0.011s
[2K
| Adam | epoch: 205 | loss: 1.02550 - acc: 0.4899 -- iter: 29/29
--
Training Step: 821 | total loss: [1m[32m1.04545[0m[0m | time: 0.003s
[2K
| Adam | epoch: 206 | loss: 1.04545 - acc: 0.4809 -- iter: 08/29
[A[ATraining Step: 822 | total loss: [1m[32m1.03144[0m[0m | time: 0.006s
[2K
| Adam | epoch: 206 | loss: 1.03144 - acc: 0.4828 -- iter: 16/29
[A[ATraining Step: 823 | total loss: [1m[32m1.03859[0m[0m | time: 0.008s
[2K
| Adam | epoch: 206 | loss: 1.03859 - acc: 0.4471 -- iter: 24/29
[A[ATraining Step: 824 | total loss: [1m[32m1.02292[0m[0m | time: 0.011s
[2K
| Adam | epoch: 206 | loss: 1.02292 - acc: 0.4523 -- iter: 29/29
--
Training Step: 825 | total loss: [1m[32m1.01910[0m[0m | time: 0.003s
[2K
| Adam | epoch: 207 | loss: 1.01910 - acc: 0.4471 -- iter: 08/29
[A[ATraining Step: 826 | total loss: [1m[32m1.01551[0m[0m | time: 0.006s
[2K
| Adam | epoch: 207 | loss: 1.01551 - acc: 0.4424 -- iter: 16/29
[A[ATraining Step: 827 | total loss: [1m[32m1.02074[0m[0m | time: 0.008s
[2K
| Adam | epoch: 207 | loss: 1.02074 - acc: 0.4357 -- iter: 24/29
[A[ATraining Step: 828 | total loss: [1m[32m1.03038[0m[0m | time: 0.011s
[2K
| Adam | epoch: 207 | loss: 1.03038 - acc: 0.4296 -- iter: 29/29
--
Training Step: 829 | total loss: [1m[32m1.02144[0m[0m | time: 0.003s
[2K
| Adam | epoch: 208 | loss: 1.02144 - acc: 0.4241 -- iter: 08/29
[A[ATraining Step: 830 | total loss: [1m[32m1.03246[0m[0m | time: 0.005s
[2K
| Adam | epoch: 208 | loss: 1.03246 - acc: 0.4217 -- iter: 16/29
[A[ATraining Step: 831 | total loss: [1m[32m1.04194[0m[0m | time: 0.008s
[2K
| Adam | epoch: 208 | loss: 1.04194 - acc: 0.4196 -- iter: 24/29
[A[ATraining Step: 832 | total loss: [1m[32m1.04578[0m[0m | time: 0.011s
[2K
| Adam | epoch: 208 | loss: 1.04578 - acc: 0.4276 -- iter: 29/29
--
Training Step: 833 | total loss: [1m[32m1.03573[0m[0m | time: 0.003s
[2K
| Adam | epoch: 209 | loss: 1.03573 - acc: 0.4348 -- iter: 08/29
[A[ATraining Step: 834 | total loss: [1m[32m1.03082[0m[0m | time: 0.005s
[2K
| Adam | epoch: 209 | loss: 1.03082 - acc: 0.4414 -- iter: 16/29
[A[ATraining Step: 835 | total loss: [1m[32m1.02942[0m[0m | time: 0.008s
[2K
| Adam | epoch: 209 | loss: 1.02942 - acc: 0.4572 -- iter: 24/29
[A[ATraining Step: 836 | total loss: [1m[32m1.02808[0m[0m | time: 0.011s
[2K
| Adam | epoch: 209 | loss: 1.02808 - acc: 0.4715 -- iter: 29/29
--
Training Step: 837 | total loss: [1m[32m1.03680[0m[0m | time: 0.003s
[2K
| Adam | epoch: 210 | loss: 1.03680 - acc: 0.4743 -- iter: 08/29
[A[ATraining Step: 838 | total loss: [1m[32m1.02503[0m[0m | time: 0.006s
[2K
| Adam | epoch: 210 | loss: 1.02503 - acc: 0.4894 -- iter: 16/29
[A[ATraining Step: 839 | total loss: [1m[32m1.02461[0m[0m | time: 0.008s
[2K
| Adam | epoch: 210 | loss: 1.02461 - acc: 0.4655 -- iter: 24/29
[A[ATraining Step: 840 | total loss: [1m[32m1.01876[0m[0m | time: 0.012s
[2K
| Adam | epoch: 210 | loss: 1.01876 - acc: 0.4989 -- iter: 29/29
--
Training Step: 841 | total loss: [1m[32m1.01335[0m[0m | time: 0.003s
[2K
| Adam | epoch: 211 | loss: 1.01335 - acc: 0.5290 -- iter: 08/29
[A[ATraining Step: 842 | total loss: [1m[32m1.00368[0m[0m | time: 0.006s
[2K
| Adam | epoch: 211 | loss: 1.00368 - acc: 0.5511 -- iter: 16/29
[A[ATraining Step: 843 | total loss: [1m[32m1.01478[0m[0m | time: 0.009s
[2K
| Adam | epoch: 211 | loss: 1.01478 - acc: 0.5460 -- iter: 24/29
[A[ATraining Step: 844 | total loss: [1m[32m1.01892[0m[0m | time: 0.013s
[2K
| Adam | epoch: 211 | loss: 1.01892 - acc: 0.5414 -- iter: 29/29
--
Training Step: 845 | total loss: [1m[32m1.01499[0m[0m | time: 0.003s
[2K
| Adam | epoch: 212 | loss: 1.01499 - acc: 0.5473 -- iter: 08/29
[A[ATraining Step: 846 | total loss: [1m[32m1.01135[0m[0m | time: 0.007s
[2K
| Adam | epoch: 212 | loss: 1.01135 - acc: 0.5525 -- iter: 16/29
[A[ATraining Step: 847 | total loss: [1m[32m1.01373[0m[0m | time: 0.010s
[2K
| Adam | epoch: 212 | loss: 1.01373 - acc: 0.5473 -- iter: 24/29
[A[ATraining Step: 848 | total loss: [1m[32m1.00614[0m[0m | time: 0.013s
[2K
| Adam | epoch: 212 | loss: 1.00614 - acc: 0.5551 -- iter: 29/29
--
Training Step: 849 | total loss: [1m[32m1.00643[0m[0m | time: 0.003s
[2K
| Adam | epoch: 213 | loss: 1.00643 - acc: 0.5246 -- iter: 08/29
[A[ATraining Step: 850 | total loss: [1m[32m0.99566[0m[0m | time: 0.007s
[2K
| Adam | epoch: 213 | loss: 0.99566 - acc: 0.4921 -- iter: 16/29
[A[ATraining Step: 851 | total loss: [1m[32m0.98546[0m[0m | time: 0.010s
[2K
| Adam | epoch: 213 | loss: 0.98546 - acc: 0.5029 -- iter: 24/29
[A[ATraining Step: 852 | total loss: [1m[32m0.99719[0m[0m | time: 0.012s
[2K
| Adam | epoch: 213 | loss: 0.99719 - acc: 0.5401 -- iter: 29/29
--
Training Step: 853 | total loss: [1m[32m0.99506[0m[0m | time: 0.002s
[2K
| Adam | epoch: 214 | loss: 0.99506 - acc: 0.5236 -- iter: 08/29
[A[ATraining Step: 854 | total loss: [1m[32m1.00691[0m[0m | time: 0.006s
[2K
| Adam | epoch: 214 | loss: 1.00691 - acc: 0.5337 -- iter: 16/29
[A[ATraining Step: 855 | total loss: [1m[32m0.99608[0m[0m | time: 0.009s
[2K
| Adam | epoch: 214 | loss: 0.99608 - acc: 0.5604 -- iter: 24/29
[A[ATraining Step: 856 | total loss: [1m[32m0.98595[0m[0m | time: 0.012s
[2K
| Adam | epoch: 214 | loss: 0.98595 - acc: 0.5843 -- iter: 29/29
--
Training Step: 857 | total loss: [1m[32m0.99082[0m[0m | time: 0.003s
[2K
| Adam | epoch: 215 | loss: 0.99082 - acc: 0.5759 -- iter: 08/29
[A[ATraining Step: 858 | total loss: [1m[32m0.98513[0m[0m | time: 0.006s
[2K
| Adam | epoch: 215 | loss: 0.98513 - acc: 0.5558 -- iter: 16/29
[A[ATraining Step: 859 | total loss: [1m[32m0.99777[0m[0m | time: 0.009s
[2K
| Adam | epoch: 215 | loss: 0.99777 - acc: 0.5377 -- iter: 24/29
[A[ATraining Step: 860 | total loss: [1m[32m0.96673[0m[0m | time: 0.012s
[2K
| Adam | epoch: 215 | loss: 0.96673 - acc: 0.5639 -- iter: 29/29
--
Training Step: 861 | total loss: [1m[32m0.93860[0m[0m | time: 0.003s
[2K
| Adam | epoch: 216 | loss: 0.93860 - acc: 0.5876 -- iter: 08/29
[A[ATraining Step: 862 | total loss: [1m[32m0.95704[0m[0m | time: 0.006s
[2K
| Adam | epoch: 216 | loss: 0.95704 - acc: 0.5663 -- iter: 16/29
[A[ATraining Step: 863 | total loss: [1m[32m0.95764[0m[0m | time: 0.009s
[2K
| Adam | epoch: 216 | loss: 0.95764 - acc: 0.5847 -- iter: 24/29
[A[ATraining Step: 864 | total loss: [1m[32m0.95598[0m[0m | time: 0.012s
[2K
| Adam | epoch: 216 | loss: 0.95598 - acc: 0.6012 -- iter: 29/29
--
Training Step: 865 | total loss: [1m[32m0.98446[0m[0m | time: 0.003s
[2K
| Adam | epoch: 217 | loss: 0.98446 - acc: 0.6011 -- iter: 08/29
[A[ATraining Step: 866 | total loss: [1m[32m1.00971[0m[0m | time: 0.005s
[2K
| Adam | epoch: 217 | loss: 1.00971 - acc: 0.6010 -- iter: 16/29
[A[ATraining Step: 867 | total loss: [1m[32m1.00626[0m[0m | time: 0.008s
[2K
| Adam | epoch: 217 | loss: 1.00626 - acc: 0.5659 -- iter: 24/29
[A[ATraining Step: 868 | total loss: [1m[32m0.99914[0m[0m | time: 0.011s
[2K
| Adam | epoch: 217 | loss: 0.99914 - acc: 0.5718 -- iter: 29/29
--
Training Step: 869 | total loss: [1m[32m0.98423[0m[0m | time: 0.003s
[2K
| Adam | epoch: 218 | loss: 0.98423 - acc: 0.5896 -- iter: 08/29
[A[ATraining Step: 870 | total loss: [1m[32m1.01003[0m[0m | time: 0.006s
[2K
| Adam | epoch: 218 | loss: 1.01003 - acc: 0.5706 -- iter: 16/29
[A[ATraining Step: 871 | total loss: [1m[32m1.03317[0m[0m | time: 0.009s
[2K
| Adam | epoch: 218 | loss: 1.03317 - acc: 0.5536 -- iter: 24/29
[A[ATraining Step: 872 | total loss: [1m[32m1.01263[0m[0m | time: 0.012s
[2K
| Adam | epoch: 218 | loss: 1.01263 - acc: 0.5732 -- iter: 29/29
--
Training Step: 873 | total loss: [1m[32m1.02734[0m[0m | time: 0.003s
[2K
| Adam | epoch: 219 | loss: 1.02734 - acc: 0.5409 -- iter: 08/29
[A[ATraining Step: 874 | total loss: [1m[32m1.02344[0m[0m | time: 0.006s
[2K
| Adam | epoch: 219 | loss: 1.02344 - acc: 0.5493 -- iter: 16/29
[A[ATraining Step: 875 | total loss: [1m[32m0.99499[0m[0m | time: 0.008s
[2K
| Adam | epoch: 219 | loss: 0.99499 - acc: 0.5544 -- iter: 24/29
[A[ATraining Step: 876 | total loss: [1m[32m0.96931[0m[0m | time: 0.011s
[2K
| Adam | epoch: 219 | loss: 0.96931 - acc: 0.5589 -- iter: 29/29
--
Training Step: 877 | total loss: [1m[32m0.99048[0m[0m | time: 0.002s
[2K
| Adam | epoch: 220 | loss: 0.99048 - acc: 0.5530 -- iter: 08/29
[A[ATraining Step: 878 | total loss: [1m[32m0.98818[0m[0m | time: 0.005s
[2K
| Adam | epoch: 220 | loss: 0.98818 - acc: 0.5477 -- iter: 16/29
[A[ATraining Step: 879 | total loss: [1m[32m0.98178[0m[0m | time: 0.007s
[2K
| Adam | epoch: 220 | loss: 0.98178 - acc: 0.5555 -- iter: 24/29
[A[ATraining Step: 880 | total loss: [1m[32m0.97393[0m[0m | time: 0.010s
[2K
| Adam | epoch: 220 | loss: 0.97393 - acc: 0.5599 -- iter: 29/29
--
Training Step: 881 | total loss: [1m[32m0.96609[0m[0m | time: 0.002s
[2K
| Adam | epoch: 221 | loss: 0.96609 - acc: 0.5639 -- iter: 08/29
[A[ATraining Step: 882 | total loss: [1m[32m0.97214[0m[0m | time: 0.005s
[2K
| Adam | epoch: 221 | loss: 0.97214 - acc: 0.5700 -- iter: 16/29
[A[ATraining Step: 883 | total loss: [1m[32m0.98310[0m[0m | time: 0.007s
[2K
| Adam | epoch: 221 | loss: 0.98310 - acc: 0.5505 -- iter: 24/29
[A[ATraining Step: 884 | total loss: [1m[32m0.96127[0m[0m | time: 0.010s
[2K
| Adam | epoch: 221 | loss: 0.96127 - acc: 0.5580 -- iter: 29/29
--
Training Step: 885 | total loss: [1m[32m0.98166[0m[0m | time: 0.002s
[2K
| Adam | epoch: 222 | loss: 0.98166 - acc: 0.5422 -- iter: 08/29
[A[ATraining Step: 886 | total loss: [1m[32m0.99987[0m[0m | time: 0.005s
[2K
| Adam | epoch: 222 | loss: 0.99987 - acc: 0.5280 -- iter: 16/29
[A[ATraining Step: 887 | total loss: [1m[32m1.00418[0m[0m | time: 0.008s
[2K
| Adam | epoch: 222 | loss: 1.00418 - acc: 0.5377 -- iter: 24/29
[A[ATraining Step: 888 | total loss: [1m[32m1.00742[0m[0m | time: 0.010s
[2K
| Adam | epoch: 222 | loss: 1.00742 - acc: 0.5339 -- iter: 29/29
--
Training Step: 889 | total loss: [1m[32m0.99986[0m[0m | time: 0.002s
[2K
| Adam | epoch: 223 | loss: 0.99986 - acc: 0.5430 -- iter: 08/29
[A[ATraining Step: 890 | total loss: [1m[32m0.99903[0m[0m | time: 0.005s
[2K
| Adam | epoch: 223 | loss: 0.99903 - acc: 0.5487 -- iter: 16/29
[A[ATraining Step: 891 | total loss: [1m[32m0.99831[0m[0m | time: 0.008s
[2K
| Adam | epoch: 223 | loss: 0.99831 - acc: 0.5538 -- iter: 24/29
[A[ATraining Step: 892 | total loss: [1m[32m1.01631[0m[0m | time: 0.011s
[2K
| Adam | epoch: 223 | loss: 1.01631 - acc: 0.5485 -- iter: 29/29
--
Training Step: 893 | total loss: [1m[32m1.00008[0m[0m | time: 0.002s
[2K
| Adam | epoch: 224 | loss: 1.00008 - acc: 0.5436 -- iter: 08/29
[A[ATraining Step: 894 | total loss: [1m[32m0.99717[0m[0m | time: 0.005s
[2K
| Adam | epoch: 224 | loss: 0.99717 - acc: 0.5392 -- iter: 16/29
[A[ATraining Step: 895 | total loss: [1m[32m0.99586[0m[0m | time: 0.007s
[2K
| Adam | epoch: 224 | loss: 0.99586 - acc: 0.5653 -- iter: 24/29
[A[ATraining Step: 896 | total loss: [1m[32m0.99453[0m[0m | time: 0.010s
[2K
| Adam | epoch: 224 | loss: 0.99453 - acc: 0.5888 -- iter: 29/29
--
Training Step: 897 | total loss: [1m[32m0.97566[0m[0m | time: 0.002s
[2K
| Adam | epoch: 225 | loss: 0.97566 - acc: 0.5799 -- iter: 08/29
[A[ATraining Step: 898 | total loss: [1m[32m0.99585[0m[0m | time: 0.005s
[2K
| Adam | epoch: 225 | loss: 0.99585 - acc: 0.5719 -- iter: 16/29
[A[ATraining Step: 899 | total loss: [1m[32m0.98210[0m[0m | time: 0.007s
[2K
| Adam | epoch: 225 | loss: 0.98210 - acc: 0.5772 -- iter: 24/29
[A[ATraining Step: 900 | total loss: [1m[32m0.96746[0m[0m | time: 0.010s
[2K
| Adam | epoch: 225 | loss: 0.96746 - acc: 0.5995 -- iter: 29/29
--
Training Step: 901 | total loss: [1m[32m0.95423[0m[0m | time: 0.002s
[2K
| Adam | epoch: 226 | loss: 0.95423 - acc: 0.6196 -- iter: 08/29
[A[ATraining Step: 902 | total loss: [1m[32m0.96402[0m[0m | time: 0.005s
[2K
| Adam | epoch: 226 | loss: 0.96402 - acc: 0.6076 -- iter: 16/29
[A[ATraining Step: 903 | total loss: [1m[32m0.98030[0m[0m | time: 0.007s
[2K
| Adam | epoch: 226 | loss: 0.98030 - acc: 0.5843 -- iter: 24/29
[A[ATraining Step: 904 | total loss: [1m[32m0.96772[0m[0m | time: 0.010s
[2K
| Adam | epoch: 226 | loss: 0.96772 - acc: 0.5509 -- iter: 29/29
--
Training Step: 905 | total loss: [1m[32m0.99020[0m[0m | time: 0.002s
[2K
| Adam | epoch: 227 | loss: 0.99020 - acc: 0.5358 -- iter: 08/29
[A[ATraining Step: 906 | total loss: [1m[32m1.01051[0m[0m | time: 0.005s
[2K
| Adam | epoch: 227 | loss: 1.01051 - acc: 0.5222 -- iter: 16/29
[A[ATraining Step: 907 | total loss: [1m[32m1.01303[0m[0m | time: 0.008s
[2K
| Adam | epoch: 227 | loss: 1.01303 - acc: 0.5450 -- iter: 24/29
[A[ATraining Step: 908 | total loss: [1m[32m1.00352[0m[0m | time: 0.011s
[2K
| Adam | epoch: 227 | loss: 1.00352 - acc: 0.5655 -- iter: 29/29
--
Training Step: 909 | total loss: [1m[32m0.99472[0m[0m | time: 0.002s
[2K
| Adam | epoch: 228 | loss: 0.99472 - acc: 0.5590 -- iter: 08/29
[A[ATraining Step: 910 | total loss: [1m[32m0.99496[0m[0m | time: 0.005s
[2K
| Adam | epoch: 228 | loss: 0.99496 - acc: 0.5631 -- iter: 16/29
[A[ATraining Step: 911 | total loss: [1m[32m0.99494[0m[0m | time: 0.007s
[2K
| Adam | epoch: 228 | loss: 0.99494 - acc: 0.5668 -- iter: 24/29
[A[ATraining Step: 912 | total loss: [1m[32m1.00758[0m[0m | time: 0.009s
[2K
| Adam | epoch: 228 | loss: 1.00758 - acc: 0.5601 -- iter: 29/29
--
Training Step: 913 | total loss: [1m[32m0.99525[0m[0m | time: 0.002s
[2K
| Adam | epoch: 229 | loss: 0.99525 - acc: 0.5666 -- iter: 08/29
[A[ATraining Step: 914 | total loss: [1m[32m1.00265[0m[0m | time: 0.005s
[2K
| Adam | epoch: 229 | loss: 1.00265 - acc: 0.5724 -- iter: 16/29
[A[ATraining Step: 915 | total loss: [1m[32m0.99420[0m[0m | time: 0.024s
[2K
| Adam | epoch: 229 | loss: 0.99420 - acc: 0.5752 -- iter: 24/29
[A[ATraining Step: 916 | total loss: [1m[32m0.98662[0m[0m | time: 0.027s
[2K
| Adam | epoch: 229 | loss: 0.98662 - acc: 0.5777 -- iter: 29/29
--
Training Step: 917 | total loss: [1m[32m0.97975[0m[0m | time: 0.002s
[2K
| Adam | epoch: 230 | loss: 0.97975 - acc: 0.5699 -- iter: 08/29
[A[ATraining Step: 918 | total loss: [1m[32m0.97988[0m[0m | time: 0.005s
[2K
| Adam | epoch: 230 | loss: 0.97988 - acc: 0.5629 -- iter: 16/29
[A[ATraining Step: 919 | total loss: [1m[32m0.97236[0m[0m | time: 0.007s
[2K
| Adam | epoch: 230 | loss: 0.97236 - acc: 0.5816 -- iter: 24/29
[A[ATraining Step: 920 | total loss: [1m[32m0.97707[0m[0m | time: 0.010s
[2K
| Adam | epoch: 230 | loss: 0.97707 - acc: 0.5635 -- iter: 29/29
--
Training Step: 921 | total loss: [1m[32m0.98121[0m[0m | time: 0.002s
[2K
| Adam | epoch: 231 | loss: 0.98121 - acc: 0.5471 -- iter: 08/29
[A[ATraining Step: 922 | total loss: [1m[32m0.96871[0m[0m | time: 0.005s
[2K
| Adam | epoch: 231 | loss: 0.96871 - acc: 0.5549 -- iter: 16/29
[A[ATraining Step: 923 | total loss: [1m[32m0.98443[0m[0m | time: 0.007s
[2K
| Adam | epoch: 231 | loss: 0.98443 - acc: 0.5369 -- iter: 24/29
[A[ATraining Step: 924 | total loss: [1m[32m0.96907[0m[0m | time: 0.010s
[2K
| Adam | epoch: 231 | loss: 0.96907 - acc: 0.5582 -- iter: 29/29
--
Training Step: 925 | total loss: [1m[32m0.96248[0m[0m | time: 0.003s
[2K
| Adam | epoch: 232 | loss: 0.96248 - acc: 0.5424 -- iter: 08/29
[A[ATraining Step: 926 | total loss: [1m[32m0.95632[0m[0m | time: 0.006s
[2K
| Adam | epoch: 232 | loss: 0.95632 - acc: 0.5282 -- iter: 16/29
[A[ATraining Step: 927 | total loss: [1m[32m0.97615[0m[0m | time: 0.010s
[2K
| Adam | epoch: 232 | loss: 0.97615 - acc: 0.5253 -- iter: 24/29
[A[ATraining Step: 928 | total loss: [1m[32m0.97495[0m[0m | time: 0.013s
[2K
| Adam | epoch: 232 | loss: 0.97495 - acc: 0.5228 -- iter: 29/29
--
Training Step: 929 | total loss: [1m[32m0.97424[0m[0m | time: 0.002s
[2K
| Adam | epoch: 233 | loss: 0.97424 - acc: 0.5205 -- iter: 08/29
[A[ATraining Step: 930 | total loss: [1m[32m0.95977[0m[0m | time: 0.006s
[2K
| Adam | epoch: 233 | loss: 0.95977 - acc: 0.5685 -- iter: 16/29
[A[ATraining Step: 931 | total loss: [1m[32m0.94673[0m[0m | time: 0.008s
[2K
| Adam | epoch: 233 | loss: 0.94673 - acc: 0.6116 -- iter: 24/29
[A[ATraining Step: 932 | total loss: [1m[32m0.96654[0m[0m | time: 0.011s
[2K
| Adam | epoch: 233 | loss: 0.96654 - acc: 0.5755 -- iter: 29/29
--
Training Step: 933 | total loss: [1m[32m0.95671[0m[0m | time: 0.003s
[2K
| Adam | epoch: 234 | loss: 0.95671 - acc: 0.5804 -- iter: 08/29
[A[ATraining Step: 934 | total loss: [1m[32m0.97125[0m[0m | time: 0.007s
[2K
| Adam | epoch: 234 | loss: 0.97125 - acc: 0.5724 -- iter: 16/29
[A[ATraining Step: 935 | total loss: [1m[32m0.96841[0m[0m | time: 0.010s
[2K
| Adam | epoch: 234 | loss: 0.96841 - acc: 0.6151 -- iter: 24/29
[A[ATraining Step: 936 | total loss: [1m[32m0.96569[0m[0m | time: 0.013s
[2K
| Adam | epoch: 234 | loss: 0.96569 - acc: 0.6536 -- iter: 29/29
--
Training Step: 937 | total loss: [1m[32m0.95490[0m[0m | time: 0.003s
[2K
| Adam | epoch: 235 | loss: 0.95490 - acc: 0.6383 -- iter: 08/29
[A[ATraining Step: 938 | total loss: [1m[32m0.95437[0m[0m | time: 0.006s
[2K
| Adam | epoch: 235 | loss: 0.95437 - acc: 0.6119 -- iter: 16/29
[A[ATraining Step: 939 | total loss: [1m[32m0.95612[0m[0m | time: 0.010s
[2K
| Adam | epoch: 235 | loss: 0.95612 - acc: 0.6257 -- iter: 24/29
[A[ATraining Step: 940 | total loss: [1m[32m0.95149[0m[0m | time: 0.013s
[2K
| Adam | epoch: 235 | loss: 0.95149 - acc: 0.6432 -- iter: 29/29
--
Training Step: 941 | total loss: [1m[32m0.94701[0m[0m | time: 0.003s
[2K
| Adam | epoch: 236 | loss: 0.94701 - acc: 0.6589 -- iter: 08/29
[A[ATraining Step: 942 | total loss: [1m[32m0.94507[0m[0m | time: 0.006s
[2K
| Adam | epoch: 236 | loss: 0.94507 - acc: 0.6305 -- iter: 16/29
[A[ATraining Step: 943 | total loss: [1m[32m0.95224[0m[0m | time: 0.009s
[2K
| Adam | epoch: 236 | loss: 0.95224 - acc: 0.6049 -- iter: 24/29
[A[ATraining Step: 944 | total loss: [1m[32m0.93179[0m[0m | time: 0.012s
[2K
| Adam | epoch: 236 | loss: 0.93179 - acc: 0.6319 -- iter: 29/29
--
Training Step: 945 | total loss: [1m[32m0.91522[0m[0m | time: 0.003s
[2K
| Adam | epoch: 237 | loss: 0.91522 - acc: 0.6087 -- iter: 08/29
[A[ATraining Step: 946 | total loss: [1m[32m0.89964[0m[0m | time: 0.006s
[2K
| Adam | epoch: 237 | loss: 0.89964 - acc: 0.5879 -- iter: 16/29
[A[ATraining Step: 947 | total loss: [1m[32m0.91588[0m[0m | time: 0.009s
[2K
| Adam | epoch: 237 | loss: 0.91588 - acc: 0.5666 -- iter: 24/29
[A[ATraining Step: 948 | total loss: [1m[32m0.94200[0m[0m | time: 0.013s
[2K
| Adam | epoch: 237 | loss: 0.94200 - acc: 0.5599 -- iter: 29/29
--
Training Step: 949 | total loss: [1m[32m0.93697[0m[0m | time: 0.004s
[2K
| Adam | epoch: 238 | loss: 0.93697 - acc: 0.5789 -- iter: 08/29
[A[ATraining Step: 950 | total loss: [1m[32m0.94526[0m[0m | time: 0.007s
[2K
| Adam | epoch: 238 | loss: 0.94526 - acc: 0.5810 -- iter: 16/29
[A[ATraining Step: 951 | total loss: [1m[32m0.95276[0m[0m | time: 0.009s
[2K
| Adam | epoch: 238 | loss: 0.95276 - acc: 0.5829 -- iter: 24/29
[A[ATraining Step: 952 | total loss: [1m[32m0.96543[0m[0m | time: 0.012s
[2K
| Adam | epoch: 238 | loss: 0.96543 - acc: 0.5621 -- iter: 29/29
--
Training Step: 953 | total loss: [1m[32m0.95533[0m[0m | time: 0.003s
[2K
| Adam | epoch: 239 | loss: 0.95533 - acc: 0.5559 -- iter: 08/29
[A[ATraining Step: 954 | total loss: [1m[32m0.94858[0m[0m | time: 0.006s
[2K
| Adam | epoch: 239 | loss: 0.94858 - acc: 0.5753 -- iter: 16/29
[A[ATraining Step: 955 | total loss: [1m[32m0.93309[0m[0m | time: 0.010s
[2K
| Adam | epoch: 239 | loss: 0.93309 - acc: 0.5778 -- iter: 24/29
[A[ATraining Step: 956 | total loss: [1m[32m0.91904[0m[0m | time: 0.013s
[2K
| Adam | epoch: 239 | loss: 0.91904 - acc: 0.5800 -- iter: 29/29
--
Training Step: 957 | total loss: [1m[32m0.94148[0m[0m | time: 0.004s
[2K
| Adam | epoch: 240 | loss: 0.94148 - acc: 0.5345 -- iter: 08/29
[A[ATraining Step: 958 | total loss: [1m[32m0.94152[0m[0m | time: 0.006s
[2K
| Adam | epoch: 240 | loss: 0.94152 - acc: 0.5561 -- iter: 16/29
[A[ATraining Step: 959 | total loss: [1m[32m0.93808[0m[0m | time: 0.008s
[2K
| Adam | epoch: 240 | loss: 0.93808 - acc: 0.5505 -- iter: 24/29
[A[ATraining Step: 960 | total loss: [1m[32m0.93512[0m[0m | time: 0.011s
[2K
| Adam | epoch: 240 | loss: 0.93512 - acc: 0.5354 -- iter: 29/29
--
Training Step: 961 | total loss: [1m[32m0.93204[0m[0m | time: 0.003s
[2K
| Adam | epoch: 241 | loss: 0.93204 - acc: 0.5219 -- iter: 08/29
[A[ATraining Step: 962 | total loss: [1m[32m0.95116[0m[0m | time: 0.005s
[2K
| Adam | epoch: 241 | loss: 0.95116 - acc: 0.5197 -- iter: 16/29
[A[ATraining Step: 963 | total loss: [1m[32m0.94236[0m[0m | time: 0.008s
[2K
| Adam | epoch: 241 | loss: 0.94236 - acc: 0.5427 -- iter: 24/29
[A[ATraining Step: 964 | total loss: [1m[32m0.94156[0m[0m | time: 0.011s
[2K
| Adam | epoch: 241 | loss: 0.94156 - acc: 0.5509 -- iter: 29/29
--
Training Step: 965 | total loss: [1m[32m0.94014[0m[0m | time: 0.003s
[2K
| Adam | epoch: 242 | loss: 0.94014 - acc: 0.5358 -- iter: 08/29
[A[ATraining Step: 966 | total loss: [1m[32m0.93846[0m[0m | time: 0.005s
[2K
| Adam | epoch: 242 | loss: 0.93846 - acc: 0.5223 -- iter: 16/29
[A[ATraining Step: 967 | total loss: [1m[32m0.94941[0m[0m | time: 0.008s
[2K
| Adam | epoch: 242 | loss: 0.94941 - acc: 0.5075 -- iter: 24/29
[A[ATraining Step: 968 | total loss: [1m[32m0.94185[0m[0m | time: 0.011s
[2K
| Adam | epoch: 242 | loss: 0.94185 - acc: 0.5318 -- iter: 29/29
--
Training Step: 969 | total loss: [1m[32m0.93319[0m[0m | time: 0.003s
[2K
| Adam | epoch: 243 | loss: 0.93319 - acc: 0.5536 -- iter: 08/29
[A[ATraining Step: 970 | total loss: [1m[32m0.96387[0m[0m | time: 0.014s
[2K
| Adam | epoch: 243 | loss: 0.96387 - acc: 0.5182 -- iter: 16/29
[A[ATraining Step: 971 | total loss: [1m[32m0.99127[0m[0m | time: 0.016s
[2K
| Adam | epoch: 243 | loss: 0.99127 - acc: 0.4864 -- iter: 24/29
[A[ATraining Step: 972 | total loss: [1m[32m0.99056[0m[0m | time: 0.030s
[2K
| Adam | epoch: 243 | loss: 0.99056 - acc: 0.4878 -- iter: 29/29
--
Training Step: 973 | total loss: [1m[32m0.97150[0m[0m | time: 0.002s
[2K
| Adam | epoch: 244 | loss: 0.97150 - acc: 0.5140 -- iter: 08/29
[A[ATraining Step: 974 | total loss: [1m[32m0.99100[0m[0m | time: 0.004s
[2K
| Adam | epoch: 244 | loss: 0.99100 - acc: 0.5251 -- iter: 16/29
[A[ATraining Step: 975 | total loss: [1m[32m0.95322[0m[0m | time: 0.007s
[2K
| Adam | epoch: 244 | loss: 0.95322 - acc: 0.5526 -- iter: 24/29
[A[ATraining Step: 976 | total loss: [1m[32m0.91878[0m[0m | time: 0.010s
[2K
| Adam | epoch: 244 | loss: 0.91878 - acc: 0.5773 -- iter: 29/29
--
Training Step: 977 | total loss: [1m[32m0.92040[0m[0m | time: 0.003s
[2K
| Adam | epoch: 245 | loss: 0.92040 - acc: 0.5696 -- iter: 08/29
[A[ATraining Step: 978 | total loss: [1m[32m0.92309[0m[0m | time: 0.005s
[2K
| Adam | epoch: 245 | loss: 0.92309 - acc: 0.5501 -- iter: 16/29
[A[ATraining Step: 979 | total loss: [1m[32m0.91396[0m[0m | time: 0.008s
[2K
| Adam | epoch: 245 | loss: 0.91396 - acc: 0.5701 -- iter: 24/29
[A[ATraining Step: 980 | total loss: [1m[32m0.92095[0m[0m | time: 0.011s
[2K
| Adam | epoch: 245 | loss: 0.92095 - acc: 0.5531 -- iter: 29/29
--
Training Step: 981 | total loss: [1m[32m0.92701[0m[0m | time: 0.003s
[2K
| Adam | epoch: 246 | loss: 0.92701 - acc: 0.5378 -- iter: 08/29
[A[ATraining Step: 982 | total loss: [1m[32m0.94657[0m[0m | time: 0.006s
[2K
| Adam | epoch: 246 | loss: 0.94657 - acc: 0.5090 -- iter: 16/29
[A[ATraining Step: 983 | total loss: [1m[32m0.93632[0m[0m | time: 0.009s
[2K
| Adam | epoch: 246 | loss: 0.93632 - acc: 0.5331 -- iter: 24/29
[A[ATraining Step: 984 | total loss: [1m[32m0.93762[0m[0m | time: 0.011s
[2K
| Adam | epoch: 246 | loss: 0.93762 - acc: 0.5423 -- iter: 29/29
--
Training Step: 985 | total loss: [1m[32m0.93999[0m[0m | time: 0.003s
[2K
| Adam | epoch: 247 | loss: 0.93999 - acc: 0.5481 -- iter: 08/29
[A[ATraining Step: 986 | total loss: [1m[32m0.94184[0m[0m | time: 0.005s
[2K
| Adam | epoch: 247 | loss: 0.94184 - acc: 0.5733 -- iter: 16/29
[A[ATraining Step: 987 | total loss: [1m[32m0.94195[0m[0m | time: 0.008s
[2K
| Adam | epoch: 247 | loss: 0.94195 - acc: 0.5659 -- iter: 24/29
[A[ATraining Step: 988 | total loss: [1m[32m0.93792[0m[0m | time: 0.011s
[2K
| Adam | epoch: 247 | loss: 0.93792 - acc: 0.5718 -- iter: 29/29
--
Training Step: 989 | total loss: [1m[32m0.93069[0m[0m | time: 0.003s
[2K
| Adam | epoch: 248 | loss: 0.93069 - acc: 0.5772 -- iter: 08/29
[A[ATraining Step: 990 | total loss: [1m[32m0.94641[0m[0m | time: 0.006s
[2K
| Adam | epoch: 248 | loss: 0.94641 - acc: 0.5794 -- iter: 16/29
[A[ATraining Step: 991 | total loss: [1m[32m0.96048[0m[0m | time: 0.009s
[2K
| Adam | epoch: 248 | loss: 0.96048 - acc: 0.5815 -- iter: 24/29
[A[ATraining Step: 992 | total loss: [1m[32m0.95746[0m[0m | time: 0.012s
[2K
| Adam | epoch: 248 | loss: 0.95746 - acc: 0.5984 -- iter: 29/29
--
Training Step: 993 | total loss: [1m[32m0.95123[0m[0m | time: 0.003s
[2K
| Adam | epoch: 249 | loss: 0.95123 - acc: 0.5885 -- iter: 08/29
[A[ATraining Step: 994 | total loss: [1m[32m0.94211[0m[0m | time: 0.007s
[2K
| Adam | epoch: 249 | loss: 0.94211 - acc: 0.5797 -- iter: 16/29
[A[ATraining Step: 995 | total loss: [1m[32m0.95769[0m[0m | time: 0.011s
[2K
| Adam | epoch: 249 | loss: 0.95769 - acc: 0.5417 -- iter: 24/29
[A[ATraining Step: 996 | total loss: [1m[32m0.97177[0m[0m | time: 0.017s
[2K
| Adam | epoch: 249 | loss: 0.97177 - acc: 0.5075 -- iter: 29/29
--
Training Step: 997 | total loss: [1m[32m0.97048[0m[0m | time: 0.003s
[2K
| Adam | epoch: 250 | loss: 0.97048 - acc: 0.5193 -- iter: 08/29
[A[ATraining Step: 998 | total loss: [1m[32m0.95957[0m[0m | time: 0.006s
[2K
| Adam | epoch: 250 | loss: 0.95957 - acc: 0.5423 -- iter: 16/29
[A[ATraining Step: 999 | total loss: [1m[32m0.96125[0m[0m | time: 0.008s
[2K
| Adam | epoch: 250 | loss: 0.96125 - acc: 0.5506 -- iter: 24/29
[A[ATraining Step: 1000 | total loss: [1m[32m0.97606[0m[0m | time: 0.011s
[2K
| Adam | epoch: 250 | loss: 0.97606 - acc: 0.5556 -- iter: 29/29
--
Training Step: 1001 | total loss: [1m[32m0.98905[0m[0m | time: 0.002s
[2K
| Adam | epoch: 251 | loss: 0.98905 - acc: 0.5600 -- iter: 08/29
[A[ATraining Step: 1002 | total loss: [1m[32m0.97601[0m[0m | time: 0.004s
[2K
| Adam | epoch: 251 | loss: 0.97601 - acc: 0.5790 -- iter: 16/29
[A[ATraining Step: 1003 | total loss: [1m[32m0.96133[0m[0m | time: 0.007s
[2K
| Adam | epoch: 251 | loss: 0.96133 - acc: 0.5836 -- iter: 24/29
[A[ATraining Step: 1004 | total loss: [1m[32m0.97208[0m[0m | time: 0.009s
[2K
| Adam | epoch: 251 | loss: 0.97208 - acc: 0.5627 -- iter: 29/29
--
Training Step: 1005 | total loss: [1m[32m0.95444[0m[0m | time: 0.002s
[2K
| Adam | epoch: 252 | loss: 0.95444 - acc: 0.5865 -- iter: 08/29
[A[ATraining Step: 1006 | total loss: [1m[32m0.93842[0m[0m | time: 0.015s
[2K
| Adam | epoch: 252 | loss: 0.93842 - acc: 0.6078 -- iter: 16/29
[A[ATraining Step: 1007 | total loss: [1m[32m0.94136[0m[0m | time: 0.019s
[2K
| Adam | epoch: 252 | loss: 0.94136 - acc: 0.6095 -- iter: 24/29
[A[ATraining Step: 1008 | total loss: [1m[32m0.92753[0m[0m | time: 0.021s
[2K
| Adam | epoch: 252 | loss: 0.92753 - acc: 0.6236 -- iter: 29/29
--
Training Step: 1009 | total loss: [1m[32m0.90945[0m[0m | time: 0.002s
[2K
| Adam | epoch: 253 | loss: 0.90945 - acc: 0.6112 -- iter: 08/29
[A[ATraining Step: 1010 | total loss: [1m[32m0.90908[0m[0m | time: 0.005s
[2K
| Adam | epoch: 253 | loss: 0.90908 - acc: 0.6301 -- iter: 16/29
[A[ATraining Step: 1011 | total loss: [1m[32m0.90828[0m[0m | time: 0.007s
[2K
| Adam | epoch: 253 | loss: 0.90828 - acc: 0.6471 -- iter: 24/29
[A[ATraining Step: 1012 | total loss: [1m[32m0.91953[0m[0m | time: 0.010s
[2K
| Adam | epoch: 253 | loss: 0.91953 - acc: 0.6449 -- iter: 29/29
--
Training Step: 1013 | total loss: [1m[32m1.35077[0m[0m | time: 0.003s
[2K
| Adam | epoch: 254 | loss: 1.35077 - acc: 0.5929 -- iter: 08/29
[A[ATraining Step: 1014 | total loss: [1m[32m1.30953[0m[0m | time: 0.005s
[2K
| Adam | epoch: 254 | loss: 1.30953 - acc: 0.5836 -- iter: 16/29
[A[ATraining Step: 1015 | total loss: [1m[32m1.26763[0m[0m | time: 0.007s
[2K
| Adam | epoch: 254 | loss: 1.26763 - acc: 0.6252 -- iter: 24/29
[A[ATraining Step: 1016 | total loss: [1m[32m1.22966[0m[0m | time: 0.010s
[2K
| Adam | epoch: 254 | loss: 1.22966 - acc: 0.6627 -- iter: 29/29
--
Training Step: 1017 | total loss: [1m[32m1.20749[0m[0m | time: 0.002s
[2K
| Adam | epoch: 255 | loss: 1.20749 - acc: 0.6464 -- iter: 08/29
[A[ATraining Step: 1018 | total loss: [1m[32m1.16865[0m[0m | time: 0.005s
[2K
| Adam | epoch: 255 | loss: 1.16865 - acc: 0.6443 -- iter: 16/29
[A[ATraining Step: 1019 | total loss: [1m[32m1.14752[0m[0m | time: 0.007s
[2K
| Adam | epoch: 255 | loss: 1.14752 - acc: 0.6424 -- iter: 24/29
[A[ATraining Step: 1020 | total loss: [1m[32m1.14868[0m[0m | time: 0.010s
[2K
| Adam | epoch: 255 | loss: 1.14868 - acc: 0.6181 -- iter: 29/29
--
Training Step: 1021 | total loss: [1m[32m1.14950[0m[0m | time: 0.002s
[2K
| Adam | epoch: 256 | loss: 1.14950 - acc: 0.5963 -- iter: 08/29
[A[ATraining Step: 1022 | total loss: [1m[32m1.12467[0m[0m | time: 0.005s
[2K
| Adam | epoch: 256 | loss: 1.12467 - acc: 0.6117 -- iter: 16/29
[A[ATraining Step: 1023 | total loss: [1m[32m1.08617[0m[0m | time: 0.007s
[2K
| Adam | epoch: 256 | loss: 1.08617 - acc: 0.6130 -- iter: 24/29
[A[ATraining Step: 1024 | total loss: [1m[32m1.06480[0m[0m | time: 0.010s
[2K
| Adam | epoch: 256 | loss: 1.06480 - acc: 0.5892 -- iter: 29/29
--
Training Step: 1025 | total loss: [1m[32m1.05937[0m[0m | time: 0.003s
[2K
| Adam | epoch: 257 | loss: 1.05937 - acc: 0.6103 -- iter: 08/29
[A[ATraining Step: 1026 | total loss: [1m[32m1.05455[0m[0m | time: 0.005s
[2K
| Adam | epoch: 257 | loss: 1.05455 - acc: 0.6293 -- iter: 16/29
[A[ATraining Step: 1027 | total loss: [1m[32m1.02462[0m[0m | time: 0.007s
[2K
| Adam | epoch: 257 | loss: 1.02462 - acc: 0.6413 -- iter: 24/29
[A[ATraining Step: 1028 | total loss: [1m[32m1.02710[0m[0m | time: 0.010s
[2K
| Adam | epoch: 257 | loss: 1.02710 - acc: 0.6397 -- iter: 29/29
--
Training Step: 1029 | total loss: [1m[32m1.03601[0m[0m | time: 0.002s
[2K
| Adam | epoch: 258 | loss: 1.03601 - acc: 0.6257 -- iter: 08/29
[A[ATraining Step: 1030 | total loss: [1m[32m0.98632[0m[0m | time: 0.005s
[2K
| Adam | epoch: 258 | loss: 0.98632 - acc: 0.6632 -- iter: 16/29
[A[ATraining Step: 1031 | total loss: [1m[32m0.94135[0m[0m | time: 0.008s
[2K
| Adam | epoch: 258 | loss: 0.94135 - acc: 0.6968 -- iter: 24/29
[A[ATraining Step: 1032 | total loss: [1m[32m0.92177[0m[0m | time: 0.010s
[2K
| Adam | epoch: 258 | loss: 0.92177 - acc: 0.7147 -- iter: 29/29
--
Training Step: 1033 | total loss: [1m[32m0.94066[0m[0m | time: 0.003s
[2K
| Adam | epoch: 259 | loss: 0.94066 - acc: 0.6682 -- iter: 08/29
[A[ATraining Step: 1034 | total loss: [1m[32m0.93694[0m[0m | time: 0.005s
[2K
| Adam | epoch: 259 | loss: 0.93694 - acc: 0.6639 -- iter: 16/29
[A[ATraining Step: 1035 | total loss: [1m[32m0.93389[0m[0m | time: 0.008s
[2K
| Adam | epoch: 259 | loss: 0.93389 - acc: 0.6175 -- iter: 24/29
[A[ATraining Step: 1036 | total loss: [1m[32m0.93000[0m[0m | time: 0.010s
[2K
| Adam | epoch: 259 | loss: 0.93000 - acc: 0.5757 -- iter: 29/29
--
Training Step: 1037 | total loss: [1m[32m0.92578[0m[0m | time: 0.002s
[2K
| Adam | epoch: 260 | loss: 0.92578 - acc: 0.6057 -- iter: 08/29
[A[ATraining Step: 1038 | total loss: [1m[32m0.92727[0m[0m | time: 0.004s
[2K
| Adam | epoch: 260 | loss: 0.92727 - acc: 0.6076 -- iter: 16/29
[A[ATraining Step: 1039 | total loss: [1m[32m0.92435[0m[0m | time: 0.005s
[2K
| Adam | epoch: 260 | loss: 0.92435 - acc: 0.6093 -- iter: 24/29
[A[ATraining Step: 1040 | total loss: [1m[32m0.91588[0m[0m | time: 0.007s
[2K
| Adam | epoch: 260 | loss: 0.91588 - acc: 0.5684 -- iter: 29/29
--
Training Step: 1041 | total loss: [1m[32m0.90661[0m[0m | time: 0.002s
[2K
| Adam | epoch: 261 | loss: 0.90661 - acc: 0.5916 -- iter: 08/29
[A[ATraining Step: 1042 | total loss: [1m[32m0.91142[0m[0m | time: 0.004s
[2K
| Adam | epoch: 261 | loss: 0.91142 - acc: 0.5949 -- iter: 16/29
[A[ATraining Step: 1043 | total loss: [1m[32m0.92159[0m[0m | time: 0.012s
[2K
| Adam | epoch: 261 | loss: 0.92159 - acc: 0.5604 -- iter: 24/29
[A[ATraining Step: 1044 | total loss: [1m[32m0.92020[0m[0m | time: 0.015s
[2K
| Adam | epoch: 261 | loss: 0.92020 - acc: 0.5669 -- iter: 29/29
--
Training Step: 1045 | total loss: [1m[32m0.94806[0m[0m | time: 0.002s
[2K
| Adam | epoch: 262 | loss: 0.94806 - acc: 0.5502 -- iter: 08/29
[A[ATraining Step: 1046 | total loss: [1m[32m0.97294[0m[0m | time: 0.006s
[2K
| Adam | epoch: 262 | loss: 0.97294 - acc: 0.5352 -- iter: 16/29
[A[ATraining Step: 1047 | total loss: [1m[32m0.95378[0m[0m | time: 0.008s
[2K
| Adam | epoch: 262 | loss: 0.95378 - acc: 0.5442 -- iter: 24/29
[A[ATraining Step: 1048 | total loss: [1m[32m0.93810[0m[0m | time: 0.011s
[2K
| Adam | epoch: 262 | loss: 0.93810 - acc: 0.5522 -- iter: 29/29
--
Training Step: 1049 | total loss: [1m[32m0.92419[0m[0m | time: 0.003s
[2K
| Adam | epoch: 263 | loss: 0.92419 - acc: 0.5595 -- iter: 08/29
[A[ATraining Step: 1050 | total loss: [1m[32m0.91867[0m[0m | time: 0.006s
[2K
| Adam | epoch: 263 | loss: 0.91867 - acc: 0.5636 -- iter: 16/29
[A[ATraining Step: 1051 | total loss: [1m[32m0.91370[0m[0m | time: 0.009s
[2K
| Adam | epoch: 263 | loss: 0.91370 - acc: 0.5672 -- iter: 24/29
[A[ATraining Step: 1052 | total loss: [1m[32m0.90384[0m[0m | time: 0.012s
[2K
| Adam | epoch: 263 | loss: 0.90384 - acc: 0.5730 -- iter: 29/29
--
Training Step: 1053 | total loss: [1m[32m0.91883[0m[0m | time: 0.002s
[2K
| Adam | epoch: 264 | loss: 0.91883 - acc: 0.5782 -- iter: 08/29
[A[ATraining Step: 1054 | total loss: [1m[32m0.89252[0m[0m | time: 0.005s
[2K
| Adam | epoch: 264 | loss: 0.89252 - acc: 0.5954 -- iter: 16/29
[A[ATraining Step: 1055 | total loss: [1m[32m0.89470[0m[0m | time: 0.008s
[2K
| Adam | epoch: 264 | loss: 0.89470 - acc: 0.5758 -- iter: 24/29
[A[ATraining Step: 1056 | total loss: [1m[32m0.89661[0m[0m | time: 0.010s
[2K
| Adam | epoch: 264 | loss: 0.89661 - acc: 0.5582 -- iter: 29/29
--
Training Step: 1057 | total loss: [1m[32m0.91312[0m[0m | time: 0.002s
[2K
| Adam | epoch: 265 | loss: 0.91312 - acc: 0.5399 -- iter: 08/29
[A[ATraining Step: 1058 | total loss: [1m[32m0.91313[0m[0m | time: 0.005s
[2K
| Adam | epoch: 265 | loss: 0.91313 - acc: 0.5734 -- iter: 16/29
[A[ATraining Step: 1059 | total loss: [1m[32m0.92431[0m[0m | time: 0.008s
[2K
| Adam | epoch: 265 | loss: 0.92431 - acc: 0.5786 -- iter: 24/29
[A[ATraining Step: 1060 | total loss: [1m[32m0.92252[0m[0m | time: 0.012s
[2K
| Adam | epoch: 265 | loss: 0.92252 - acc: 0.5807 -- iter: 29/29
--
Training Step: 1061 | total loss: [1m[32m0.92072[0m[0m | time: 0.002s
[2K
| Adam | epoch: 266 | loss: 0.92072 - acc: 0.5827 -- iter: 08/29
[A[ATraining Step: 1062 | total loss: [1m[32m0.90912[0m[0m | time: 0.005s
[2K
| Adam | epoch: 266 | loss: 0.90912 - acc: 0.5744 -- iter: 16/29
[A[ATraining Step: 1063 | total loss: [1m[32m0.89675[0m[0m | time: 0.007s
[2K
| Adam | epoch: 266 | loss: 0.89675 - acc: 0.5920 -- iter: 24/29
[A[ATraining Step: 1064 | total loss: [1m[32m0.87800[0m[0m | time: 0.009s
[2K
| Adam | epoch: 266 | loss: 0.87800 - acc: 0.6328 -- iter: 29/29
--
Training Step: 1065 | total loss: [1m[32m0.88622[0m[0m | time: 0.002s
[2K
| Adam | epoch: 267 | loss: 0.88622 - acc: 0.6295 -- iter: 08/29
[A[ATraining Step: 1066 | total loss: [1m[32m0.89304[0m[0m | time: 0.005s
[2K
| Adam | epoch: 267 | loss: 0.89304 - acc: 0.6265 -- iter: 16/29
[A[ATraining Step: 1067 | total loss: [1m[32m0.91066[0m[0m | time: 0.028s
[2K
| Adam | epoch: 267 | loss: 0.91066 - acc: 0.6139 -- iter: 24/29
[A[ATraining Step: 1068 | total loss: [1m[32m0.89957[0m[0m | time: 0.030s
[2K
| Adam | epoch: 267 | loss: 0.89957 - acc: 0.5900 -- iter: 29/29
--
Training Step: 1069 | total loss: [1m[32m0.89409[0m[0m | time: 0.002s
[2K
| Adam | epoch: 268 | loss: 0.89409 - acc: 0.6060 -- iter: 08/29
[A[ATraining Step: 1070 | total loss: [1m[32m0.89296[0m[0m | time: 0.004s
[2K
| Adam | epoch: 268 | loss: 0.89296 - acc: 0.5854 -- iter: 16/29
[A[ATraining Step: 1071 | total loss: [1m[32m0.89171[0m[0m | time: 0.007s
[2K
| Adam | epoch: 268 | loss: 0.89171 - acc: 0.5669 -- iter: 24/29
[A[ATraining Step: 1072 | total loss: [1m[32m0.88560[0m[0m | time: 0.009s
[2K
| Adam | epoch: 268 | loss: 0.88560 - acc: 0.5727 -- iter: 29/29
--
Training Step: 1073 | total loss: [1m[32m0.88918[0m[0m | time: 0.002s
[2K
| Adam | epoch: 269 | loss: 0.88918 - acc: 0.5779 -- iter: 08/29
[A[ATraining Step: 1074 | total loss: [1m[32m0.88452[0m[0m | time: 0.005s
[2K
| Adam | epoch: 269 | loss: 0.88452 - acc: 0.5951 -- iter: 16/29
[A[ATraining Step: 1075 | total loss: [1m[32m0.88265[0m[0m | time: 0.007s
[2K
| Adam | epoch: 269 | loss: 0.88265 - acc: 0.5756 -- iter: 24/29
[A[ATraining Step: 1076 | total loss: [1m[32m0.88057[0m[0m | time: 0.010s
[2K
| Adam | epoch: 269 | loss: 0.88057 - acc: 0.5580 -- iter: 29/29
--
Training Step: 1077 | total loss: [1m[32m0.87276[0m[0m | time: 0.002s
[2K
| Adam | epoch: 270 | loss: 0.87276 - acc: 0.5897 -- iter: 08/29
[A[ATraining Step: 1078 | total loss: [1m[32m0.87591[0m[0m | time: 0.005s
[2K
| Adam | epoch: 270 | loss: 0.87591 - acc: 0.5683 -- iter: 16/29
[A[ATraining Step: 1079 | total loss: [1m[32m0.89526[0m[0m | time: 0.007s
[2K
| Adam | epoch: 270 | loss: 0.89526 - acc: 0.5489 -- iter: 24/29
[A[ATraining Step: 1080 | total loss: [1m[32m0.88332[0m[0m | time: 0.010s
[2K
| Adam | epoch: 270 | loss: 0.88332 - acc: 0.5740 -- iter: 29/29
--
Training Step: 1081 | total loss: [1m[32m0.87255[0m[0m | time: 0.003s
[2K
| Adam | epoch: 271 | loss: 0.87255 - acc: 0.5966 -- iter: 08/29
[A[ATraining Step: 1082 | total loss: [1m[32m0.85097[0m[0m | time: 0.005s
[2K
| Adam | epoch: 271 | loss: 0.85097 - acc: 0.5995 -- iter: 16/29
[A[ATraining Step: 1083 | total loss: [1m[32m0.85576[0m[0m | time: 0.009s
[2K
| Adam | epoch: 271 | loss: 0.85576 - acc: 0.6145 -- iter: 24/29
[A[ATraining Step: 1084 | total loss: [1m[32m0.84703[0m[0m | time: 0.011s
[2K
| Adam | epoch: 271 | loss: 0.84703 - acc: 0.6281 -- iter: 29/29
--
Training Step: 1085 | total loss: [1m[32m0.84419[0m[0m | time: 0.003s
[2K
| Adam | epoch: 272 | loss: 0.84419 - acc: 0.6053 -- iter: 08/29
[A[ATraining Step: 1086 | total loss: [1m[32m0.84113[0m[0m | time: 0.005s
[2K
| Adam | epoch: 272 | loss: 0.84113 - acc: 0.6047 -- iter: 16/29
[A[ATraining Step: 1087 | total loss: [1m[32m0.84651[0m[0m | time: 0.008s
[2K
| Adam | epoch: 272 | loss: 0.84651 - acc: 0.6068 -- iter: 24/29
[A[ATraining Step: 1088 | total loss: [1m[32m0.85422[0m[0m | time: 0.011s
[2K
| Adam | epoch: 272 | loss: 0.85422 - acc: 0.5836 -- iter: 29/29
--
Training Step: 1089 | total loss: [1m[32m0.85575[0m[0m | time: 0.003s
[2K
| Adam | epoch: 273 | loss: 0.85575 - acc: 0.6002 -- iter: 08/29
[A[ATraining Step: 1090 | total loss: [1m[32m0.89196[0m[0m | time: 0.005s
[2K
| Adam | epoch: 273 | loss: 0.89196 - acc: 0.5602 -- iter: 16/29
[A[ATraining Step: 1091 | total loss: [1m[32m0.92434[0m[0m | time: 0.008s
[2K
| Adam | epoch: 273 | loss: 0.92434 - acc: 0.5242 -- iter: 24/29
[A[ATraining Step: 1092 | total loss: [1m[32m0.89763[0m[0m | time: 0.010s
[2K
| Adam | epoch: 273 | loss: 0.89763 - acc: 0.5343 -- iter: 29/29
--
Training Step: 1093 | total loss: [1m[32m1.46087[0m[0m | time: 0.002s
[2K
| Adam | epoch: 274 | loss: 1.46087 - acc: 0.4933 -- iter: 08/29
[A[ATraining Step: 1094 | total loss: [1m[32m1.39709[0m[0m | time: 0.005s
[2K
| Adam | epoch: 274 | loss: 1.39709 - acc: 0.5190 -- iter: 16/29
[A[ATraining Step: 1095 | total loss: [1m[32m1.35578[0m[0m | time: 0.007s
[2K
| Adam | epoch: 274 | loss: 1.35578 - acc: 0.5071 -- iter: 24/29
[A[ATraining Step: 1096 | total loss: [1m[32m1.31813[0m[0m | time: 0.010s
[2K
| Adam | epoch: 274 | loss: 1.31813 - acc: 0.4964 -- iter: 29/29
--
Training Step: 1097 | total loss: [1m[32m1.25914[0m[0m | time: 0.003s
[2K
| Adam | epoch: 275 | loss: 1.25914 - acc: 0.5218 -- iter: 08/29
[A[ATraining Step: 1098 | total loss: [1m[32m1.22287[0m[0m | time: 0.005s
[2K
| Adam | epoch: 275 | loss: 1.22287 - acc: 0.5196 -- iter: 16/29
[A[ATraining Step: 1099 | total loss: [1m[32m1.19309[0m[0m | time: 0.007s
[2K
| Adam | epoch: 275 | loss: 1.19309 - acc: 0.5426 -- iter: 24/29
[A[ATraining Step: 1100 | total loss: [1m[32m1.16844[0m[0m | time: 0.010s
[2K
| Adam | epoch: 275 | loss: 1.16844 - acc: 0.5284 -- iter: 29/29
--
Training Step: 1101 | total loss: [1m[32m1.14631[0m[0m | time: 0.026s
[2K
| Adam | epoch: 276 | loss: 1.14631 - acc: 0.5155 -- iter: 08/29
[A[ATraining Step: 1102 | total loss: [1m[32m1.10110[0m[0m | time: 0.029s
[2K
| Adam | epoch: 276 | loss: 1.10110 - acc: 0.5390 -- iter: 16/29
[A[ATraining Step: 1103 | total loss: [1m[32m1.07444[0m[0m | time: 0.031s
[2K
| Adam | epoch: 276 | loss: 1.07444 - acc: 0.5351 -- iter: 24/29
[A[ATraining Step: 1104 | total loss: [1m[32m1.04498[0m[0m | time: 0.034s
[2K
| Adam | epoch: 276 | loss: 1.04498 - acc: 0.5566 -- iter: 29/29
--
Training Step: 1105 | total loss: [1m[32m1.04443[0m[0m | time: 0.002s
[2K
| Adam | epoch: 277 | loss: 1.04443 - acc: 0.5609 -- iter: 08/29
[A[ATraining Step: 1106 | total loss: [1m[32m1.04375[0m[0m | time: 0.005s
[2K
| Adam | epoch: 277 | loss: 1.04375 - acc: 0.5648 -- iter: 16/29
[A[ATraining Step: 1107 | total loss: [1m[32m1.00522[0m[0m | time: 0.008s
[2K
| Adam | epoch: 277 | loss: 1.00522 - acc: 0.5708 -- iter: 24/29
[A[ATraining Step: 1108 | total loss: [1m[32m0.99898[0m[0m | time: 0.010s
[2K
| Adam | epoch: 277 | loss: 0.99898 - acc: 0.5888 -- iter: 29/29
--
Training Step: 1109 | total loss: [1m[32m0.98749[0m[0m | time: 0.002s
[2K
| Adam | epoch: 278 | loss: 0.98749 - acc: 0.5799 -- iter: 08/29
[A[ATraining Step: 1110 | total loss: [1m[32m0.98914[0m[0m | time: 0.006s
[2K
| Adam | epoch: 278 | loss: 0.98914 - acc: 0.5819 -- iter: 16/29
[A[ATraining Step: 1111 | total loss: [1m[32m0.99060[0m[0m | time: 0.008s
[2K
| Adam | epoch: 278 | loss: 0.99060 - acc: 0.5837 -- iter: 24/29
[A[ATraining Step: 1112 | total loss: [1m[32m0.96317[0m[0m | time: 0.011s
[2K
| Adam | epoch: 278 | loss: 0.96317 - acc: 0.5878 -- iter: 29/29
--
Training Step: 1113 | total loss: [1m[32m0.94578[0m[0m | time: 0.002s
[2K
| Adam | epoch: 279 | loss: 0.94578 - acc: 0.6165 -- iter: 08/29
[A[ATraining Step: 1114 | total loss: [1m[32m0.93030[0m[0m | time: 0.005s
[2K
| Adam | epoch: 279 | loss: 0.93030 - acc: 0.6299 -- iter: 16/29
[A[ATraining Step: 1115 | total loss: [1m[32m0.89317[0m[0m | time: 0.007s
[2K
| Adam | epoch: 279 | loss: 0.89317 - acc: 0.6469 -- iter: 24/29
[A[ATraining Step: 1116 | total loss: [1m[32m0.85884[0m[0m | time: 0.009s
[2K
| Adam | epoch: 279 | loss: 0.85884 - acc: 0.6622 -- iter: 29/29
--
Training Step: 1117 | total loss: [1m[32m0.87375[0m[0m | time: 0.002s
[2K
| Adam | epoch: 280 | loss: 0.87375 - acc: 0.6210 -- iter: 08/29
[A[ATraining Step: 1118 | total loss: [1m[32m0.87276[0m[0m | time: 0.005s
[2K
| Adam | epoch: 280 | loss: 0.87276 - acc: 0.6214 -- iter: 16/29
[A[ATraining Step: 1119 | total loss: [1m[32m0.86839[0m[0m | time: 0.008s
[2K
| Adam | epoch: 280 | loss: 0.86839 - acc: 0.6343 -- iter: 24/29
[A[ATraining Step: 1120 | total loss: [1m[32m0.85992[0m[0m | time: 0.011s
[2K
| Adam | epoch: 280 | loss: 0.85992 - acc: 0.6308 -- iter: 29/29
--
Training Step: 1121 | total loss: [1m[32m0.85218[0m[0m | time: 0.003s
[2K
| Adam | epoch: 281 | loss: 0.85218 - acc: 0.6277 -- iter: 08/29
[A[ATraining Step: 1122 | total loss: [1m[32m0.85863[0m[0m | time: 0.006s
[2K
| Adam | epoch: 281 | loss: 0.85863 - acc: 0.6400 -- iter: 16/29
[A[ATraining Step: 1123 | total loss: [1m[32m0.84578[0m[0m | time: 0.008s
[2K
| Adam | epoch: 281 | loss: 0.84578 - acc: 0.6260 -- iter: 24/29
[A[ATraining Step: 1124 | total loss: [1m[32m0.81823[0m[0m | time: 0.011s
[2K
| Adam | epoch: 281 | loss: 0.81823 - acc: 0.6509 -- iter: 29/29
--
Training Step: 1125 | total loss: [1m[32m0.84516[0m[0m | time: 0.003s
[2K
| Adam | epoch: 282 | loss: 0.84516 - acc: 0.6258 -- iter: 08/29
[A[ATraining Step: 1126 | total loss: [1m[32m0.86905[0m[0m | time: 0.006s
[2K
| Adam | epoch: 282 | loss: 0.86905 - acc: 0.6032 -- iter: 16/29
[A[ATraining Step: 1127 | total loss: [1m[32m0.86662[0m[0m | time: 0.009s
[2K
| Adam | epoch: 282 | loss: 0.86662 - acc: 0.6054 -- iter: 24/29
[A[ATraining Step: 1128 | total loss: [1m[32m0.86487[0m[0m | time: 0.012s
[2K
| Adam | epoch: 282 | loss: 0.86487 - acc: 0.6074 -- iter: 29/29
--
Training Step: 1129 | total loss: [1m[32m0.85590[0m[0m | time: 0.002s
[2K
| Adam | epoch: 283 | loss: 0.85590 - acc: 0.6216 -- iter: 08/29
[A[ATraining Step: 1130 | total loss: [1m[32m0.86190[0m[0m | time: 0.006s
[2K
| Adam | epoch: 283 | loss: 0.86190 - acc: 0.6195 -- iter: 16/29
[A[ATraining Step: 1131 | total loss: [1m[32m0.86690[0m[0m | time: 0.009s
[2K
| Adam | epoch: 283 | loss: 0.86690 - acc: 0.6175 -- iter: 24/29
[A[ATraining Step: 1132 | total loss: [1m[32m0.85091[0m[0m | time: 0.013s
[2K
| Adam | epoch: 283 | loss: 0.85091 - acc: 0.6308 -- iter: 29/29
--
Training Step: 1133 | total loss: [1m[32m0.85188[0m[0m | time: 0.003s
[2K
| Adam | epoch: 284 | loss: 0.85188 - acc: 0.6177 -- iter: 08/29
[A[ATraining Step: 1134 | total loss: [1m[32m0.84570[0m[0m | time: 0.007s
[2K
| Adam | epoch: 284 | loss: 0.84570 - acc: 0.6309 -- iter: 16/29
[A[ATraining Step: 1135 | total loss: [1m[32m0.84914[0m[0m | time: 0.010s
[2K
| Adam | epoch: 284 | loss: 0.84914 - acc: 0.6278 -- iter: 24/29
[A[ATraining Step: 1136 | total loss: [1m[32m0.85215[0m[0m | time: 0.013s
[2K
| Adam | epoch: 284 | loss: 0.85215 - acc: 0.6250 -- iter: 29/29
--
Training Step: 1137 | total loss: [1m[32m0.85716[0m[0m | time: 0.003s
[2K
| Adam | epoch: 285 | loss: 0.85716 - acc: 0.5750 -- iter: 08/29
[A[ATraining Step: 1138 | total loss: [1m[32m0.83645[0m[0m | time: 0.011s
[2K
| Adam | epoch: 285 | loss: 0.83645 - acc: 0.6050 -- iter: 16/29
[A[ATraining Step: 1139 | total loss: [1m[32m0.82535[0m[0m | time: 0.014s
[2K
| Adam | epoch: 285 | loss: 0.82535 - acc: 0.6195 -- iter: 24/29
[A[ATraining Step: 1140 | total loss: [1m[32m0.81455[0m[0m | time: 0.017s
[2K
| Adam | epoch: 285 | loss: 0.81455 - acc: 0.6376 -- iter: 29/29
--
Training Step: 1141 | total loss: [1m[32m0.80468[0m[0m | time: 0.002s
[2K
| Adam | epoch: 286 | loss: 0.80468 - acc: 0.6538 -- iter: 08/29
[A[ATraining Step: 1142 | total loss: [1m[32m0.80789[0m[0m | time: 0.005s
[2K
| Adam | epoch: 286 | loss: 0.80789 - acc: 0.6509 -- iter: 16/29
[A[ATraining Step: 1143 | total loss: [1m[32m0.81241[0m[0m | time: 0.008s
[2K
| Adam | epoch: 286 | loss: 0.81241 - acc: 0.6358 -- iter: 24/29
[A[ATraining Step: 1144 | total loss: [1m[32m0.81153[0m[0m | time: 0.010s
[2K
| Adam | epoch: 286 | loss: 0.81153 - acc: 0.6473 -- iter: 29/29
--
Training Step: 1145 | total loss: [1m[32m0.78936[0m[0m | time: 0.003s
[2K
| Adam | epoch: 287 | loss: 0.78936 - acc: 0.6625 -- iter: 08/29
[A[ATraining Step: 1146 | total loss: [1m[32m0.76903[0m[0m | time: 0.005s
[2K
| Adam | epoch: 287 | loss: 0.76903 - acc: 0.6763 -- iter: 16/29
[A[ATraining Step: 1147 | total loss: [1m[32m0.78049[0m[0m | time: 0.007s
[2K
| Adam | epoch: 287 | loss: 0.78049 - acc: 0.6587 -- iter: 24/29
[A[ATraining Step: 1148 | total loss: [1m[32m0.78078[0m[0m | time: 0.010s
[2K
| Adam | epoch: 287 | loss: 0.78078 - acc: 0.6553 -- iter: 29/29
--
Training Step: 1149 | total loss: [1m[32m0.78657[0m[0m | time: 0.003s
[2K
| Adam | epoch: 288 | loss: 0.78657 - acc: 0.6523 -- iter: 08/29
[A[ATraining Step: 1150 | total loss: [1m[32m0.76772[0m[0m | time: 0.005s
[2K
| Adam | epoch: 288 | loss: 0.76772 - acc: 0.6670 -- iter: 16/29
[A[ATraining Step: 1151 | total loss: [1m[32m0.75054[0m[0m | time: 0.008s
[2K
| Adam | epoch: 288 | loss: 0.75054 - acc: 0.6803 -- iter: 24/29
[A[ATraining Step: 1152 | total loss: [1m[32m0.74901[0m[0m | time: 0.010s
[2K
| Adam | epoch: 288 | loss: 0.74901 - acc: 0.6748 -- iter: 29/29
--
Training Step: 1153 | total loss: [1m[32m0.76035[0m[0m | time: 0.003s
[2K
| Adam | epoch: 289 | loss: 0.76035 - acc: 0.6573 -- iter: 08/29
[A[ATraining Step: 1154 | total loss: [1m[32m0.77304[0m[0m | time: 0.005s
[2K
| Adam | epoch: 289 | loss: 0.77304 - acc: 0.6541 -- iter: 16/29
[A[ATraining Step: 1155 | total loss: [1m[32m0.73379[0m[0m | time: 0.008s
[2K
| Adam | epoch: 289 | loss: 0.73379 - acc: 0.6887 -- iter: 24/29
[A[ATraining Step: 1156 | total loss: [1m[32m0.69798[0m[0m | time: 0.010s
[2K
| Adam | epoch: 289 | loss: 0.69798 - acc: 0.7198 -- iter: 29/29
--
Training Step: 1157 | total loss: [1m[32m0.70979[0m[0m | time: 0.003s
[2K
| Adam | epoch: 290 | loss: 0.70979 - acc: 0.6978 -- iter: 08/29
[A[ATraining Step: 1158 | total loss: [1m[32m0.72401[0m[0m | time: 0.005s
[2K
| Adam | epoch: 290 | loss: 0.72401 - acc: 0.6780 -- iter: 16/29
[A[ATraining Step: 1159 | total loss: [1m[32m0.73294[0m[0m | time: 0.008s
[2K
| Adam | epoch: 290 | loss: 0.73294 - acc: 0.6602 -- iter: 24/29
[A[ATraining Step: 1160 | total loss: [1m[32m0.74877[0m[0m | time: 0.010s
[2K
| Adam | epoch: 290 | loss: 0.74877 - acc: 0.6342 -- iter: 29/29
--
Training Step: 1161 | total loss: [1m[32m0.76270[0m[0m | time: 0.002s
[2K
| Adam | epoch: 291 | loss: 0.76270 - acc: 0.6108 -- iter: 08/29
[A[ATraining Step: 1162 | total loss: [1m[32m0.75846[0m[0m | time: 0.006s
[2K
| Adam | epoch: 291 | loss: 0.75846 - acc: 0.6247 -- iter: 16/29
[A[ATraining Step: 1163 | total loss: [1m[32m0.75070[0m[0m | time: 0.008s
[2K
| Adam | epoch: 291 | loss: 0.75070 - acc: 0.6372 -- iter: 24/29
[A[ATraining Step: 1164 | total loss: [1m[32m0.74595[0m[0m | time: 0.011s
[2K
| Adam | epoch: 291 | loss: 0.74595 - acc: 0.6360 -- iter: 29/29
--
Training Step: 1165 | total loss: [1m[32m0.76237[0m[0m | time: 0.002s
[2K
| Adam | epoch: 292 | loss: 0.76237 - acc: 0.6324 -- iter: 08/29
[A[ATraining Step: 1166 | total loss: [1m[32m0.77687[0m[0m | time: 0.005s
[2K
| Adam | epoch: 292 | loss: 0.77687 - acc: 0.6292 -- iter: 16/29
[A[ATraining Step: 1167 | total loss: [1m[32m0.76508[0m[0m | time: 0.007s
[2K
| Adam | epoch: 292 | loss: 0.76508 - acc: 0.6413 -- iter: 24/29
[A[ATraining Step: 1168 | total loss: [1m[32m0.77001[0m[0m | time: 0.010s
[2K
| Adam | epoch: 292 | loss: 0.77001 - acc: 0.6271 -- iter: 29/29
--
Training Step: 1169 | total loss: [1m[32m0.76015[0m[0m | time: 0.003s
[2K
| Adam | epoch: 293 | loss: 0.76015 - acc: 0.6394 -- iter: 08/29
[A[ATraining Step: 1170 | total loss: [1m[32m0.77325[0m[0m | time: 0.005s
[2K
| Adam | epoch: 293 | loss: 0.77325 - acc: 0.5955 -- iter: 16/29
[A[ATraining Step: 1171 | total loss: [1m[32m0.78510[0m[0m | time: 0.008s
[2K
| Adam | epoch: 293 | loss: 0.78510 - acc: 0.5559 -- iter: 24/29
[A[ATraining Step: 1172 | total loss: [1m[32m0.78861[0m[0m | time: 0.010s
[2K
| Adam | epoch: 293 | loss: 0.78861 - acc: 0.5753 -- iter: 29/29
--
Training Step: 1173 | total loss: [1m[32m0.77756[0m[0m | time: 0.003s
[2K
| Adam | epoch: 294 | loss: 0.77756 - acc: 0.5803 -- iter: 08/29
[A[ATraining Step: 1174 | total loss: [1m[32m0.77250[0m[0m | time: 0.005s
[2K
| Adam | epoch: 294 | loss: 0.77250 - acc: 0.5973 -- iter: 16/29
[A[ATraining Step: 1175 | total loss: [1m[32m0.76857[0m[0m | time: 0.008s
[2K
| Adam | epoch: 294 | loss: 0.76857 - acc: 0.5775 -- iter: 24/29
[A[ATraining Step: 1176 | total loss: [1m[32m0.76446[0m[0m | time: 0.010s
[2K
| Adam | epoch: 294 | loss: 0.76446 - acc: 0.5598 -- iter: 29/29
--
Training Step: 1177 | total loss: [1m[32m0.77281[0m[0m | time: 0.002s
[2K
| Adam | epoch: 295 | loss: 0.77281 - acc: 0.5788 -- iter: 08/29
[A[ATraining Step: 1178 | total loss: [1m[32m0.76120[0m[0m | time: 0.005s
[2K
| Adam | epoch: 295 | loss: 0.76120 - acc: 0.5709 -- iter: 16/29
[A[ATraining Step: 1179 | total loss: [1m[32m0.74631[0m[0m | time: 0.007s
[2K
| Adam | epoch: 295 | loss: 0.74631 - acc: 0.5888 -- iter: 24/29
[A[ATraining Step: 1180 | total loss: [1m[32m0.73381[0m[0m | time: 0.010s
[2K
| Adam | epoch: 295 | loss: 0.73381 - acc: 0.5900 -- iter: 29/29
--
Training Step: 1181 | total loss: [1m[32m0.72260[0m[0m | time: 0.003s
[2K
| Adam | epoch: 296 | loss: 0.72260 - acc: 0.5910 -- iter: 08/29
[A[ATraining Step: 1182 | total loss: [1m[32m0.73364[0m[0m | time: 0.005s
[2K
| Adam | epoch: 296 | loss: 0.73364 - acc: 0.5819 -- iter: 16/29
[A[ATraining Step: 1183 | total loss: [1m[32m0.74339[0m[0m | time: 0.008s
[2K
| Adam | epoch: 296 | loss: 0.74339 - acc: 0.6112 -- iter: 24/29
[A[ATraining Step: 1184 | total loss: [1m[32m0.74419[0m[0m | time: 0.010s
[2K
| Adam | epoch: 296 | loss: 0.74419 - acc: 0.6126 -- iter: 29/29
--
Training Step: 1185 | total loss: [1m[32m0.76004[0m[0m | time: 0.002s
[2K
| Adam | epoch: 297 | loss: 0.76004 - acc: 0.6113 -- iter: 08/29
[A[ATraining Step: 1186 | total loss: [1m[32m0.77317[0m[0m | time: 0.005s
[2K
| Adam | epoch: 297 | loss: 0.77317 - acc: 0.6102 -- iter: 16/29
[A[ATraining Step: 1187 | total loss: [1m[32m0.75428[0m[0m | time: 0.007s
[2K
| Adam | epoch: 297 | loss: 0.75428 - acc: 0.6242 -- iter: 24/29
[A[ATraining Step: 1188 | total loss: [1m[32m0.75601[0m[0m | time: 0.010s
[2K
| Adam | epoch: 297 | loss: 0.75601 - acc: 0.6117 -- iter: 29/29
--
Training Step: 1189 | total loss: [1m[32m0.72893[0m[0m | time: 0.003s
[2K
| Adam | epoch: 298 | loss: 0.72893 - acc: 0.6381 -- iter: 08/29
[A[ATraining Step: 1190 | total loss: [1m[32m0.71608[0m[0m | time: 0.005s
[2K
| Adam | epoch: 298 | loss: 0.71608 - acc: 0.6343 -- iter: 16/29
[A[ATraining Step: 1191 | total loss: [1m[32m0.70446[0m[0m | time: 0.008s
[2K
| Adam | epoch: 298 | loss: 0.70446 - acc: 0.6308 -- iter: 24/29
[A[ATraining Step: 1192 | total loss: [1m[32m0.71764[0m[0m | time: 0.010s
[2K
| Adam | epoch: 298 | loss: 0.71764 - acc: 0.6177 -- iter: 29/29
--
Training Step: 1193 | total loss: [1m[32m0.73969[0m[0m | time: 0.003s
[2K
| Adam | epoch: 299 | loss: 0.73969 - acc: 0.6060 -- iter: 08/29
[A[ATraining Step: 1194 | total loss: [1m[32m0.72131[0m[0m | time: 0.005s
[2K
| Adam | epoch: 299 | loss: 0.72131 - acc: 0.6204 -- iter: 16/29
[A[ATraining Step: 1195 | total loss: [1m[32m0.73286[0m[0m | time: 0.008s
[2K
| Adam | epoch: 299 | loss: 0.73286 - acc: 0.6183 -- iter: 24/29
[A[ATraining Step: 1196 | total loss: [1m[32m0.74296[0m[0m | time: 0.011s
[2K
| Adam | epoch: 299 | loss: 0.74296 - acc: 0.6165 -- iter: 29/29
--
Training Step: 1197 | total loss: [1m[32m0.74136[0m[0m | time: 0.003s
[2K
| Adam | epoch: 300 | loss: 0.74136 - acc: 0.6049 -- iter: 08/29
[A[ATraining Step: 1198 | total loss: [1m[32m0.74822[0m[0m | time: 0.005s
[2K
| Adam | epoch: 300 | loss: 0.74822 - acc: 0.6069 -- iter: 16/29
[A[ATraining Step: 1199 | total loss: [1m[32m0.74138[0m[0m | time: 0.008s
[2K
| Adam | epoch: 300 | loss: 0.74138 - acc: 0.6212 -- iter: 24/29
[A[ATraining Step: 1200 | total loss: [1m[32m0.75352[0m[0m | time: 0.010s
[2K
| Adam | epoch: 300 | loss: 0.75352 - acc: 0.6191 -- iter: 29/29
--
Training Step: 1201 | total loss: [1m[32m0.76383[0m[0m | time: 0.003s
[2K
| Adam | epoch: 301 | loss: 0.76383 - acc: 0.6172 -- iter: 08/29
[A[ATraining Step: 1202 | total loss: [1m[32m0.75972[0m[0m | time: 0.005s
[2K
| Adam | epoch: 301 | loss: 0.75972 - acc: 0.6179 -- iter: 16/29
[A[ATraining Step: 1203 | total loss: [1m[32m0.75049[0m[0m | time: 0.008s
[2K
| Adam | epoch: 301 | loss: 0.75049 - acc: 0.6061 -- iter: 24/29
[A[ATraining Step: 1204 | total loss: [1m[32m0.74183[0m[0m | time: 0.010s
[2K
| Adam | epoch: 301 | loss: 0.74183 - acc: 0.6205 -- iter: 29/29
--
Training Step: 1205 | total loss: [1m[32m0.74556[0m[0m | time: 0.002s
[2K
| Adam | epoch: 302 | loss: 0.74556 - acc: 0.5985 -- iter: 08/29
[A[ATraining Step: 1206 | total loss: [1m[32m0.74826[0m[0m | time: 0.005s
[2K
| Adam | epoch: 302 | loss: 0.74826 - acc: 0.5786 -- iter: 16/29
[A[ATraining Step: 1207 | total loss: [1m[32m0.72994[0m[0m | time: 0.008s
[2K
| Adam | epoch: 302 | loss: 0.72994 - acc: 0.6083 -- iter: 24/29
[A[ATraining Step: 1208 | total loss: [1m[32m0.74241[0m[0m | time: 0.010s
[2K
| Adam | epoch: 302 | loss: 0.74241 - acc: 0.5849 -- iter: 29/29
--
Training Step: 1209 | total loss: [1m[32m0.74827[0m[0m | time: 0.003s
[2K
| Adam | epoch: 303 | loss: 0.74827 - acc: 0.5889 -- iter: 08/29
[A[ATraining Step: 1210 | total loss: [1m[32m0.71812[0m[0m | time: 0.005s
[2K
| Adam | epoch: 303 | loss: 0.71812 - acc: 0.6301 -- iter: 16/29
[A[ATraining Step: 1211 | total loss: [1m[32m0.69101[0m[0m | time: 0.007s
[2K
| Adam | epoch: 303 | loss: 0.69101 - acc: 0.6670 -- iter: 24/29
[A[ATraining Step: 1212 | total loss: [1m[32m0.69168[0m[0m | time: 0.010s
[2K
| Adam | epoch: 303 | loss: 0.69168 - acc: 0.6628 -- iter: 29/29
--
Training Step: 1213 | total loss: [1m[32m0.69740[0m[0m | time: 0.003s
[2K
| Adam | epoch: 304 | loss: 0.69740 - acc: 0.6591 -- iter: 08/29
[A[ATraining Step: 1214 | total loss: [1m[32m0.69275[0m[0m | time: 0.005s
[2K
| Adam | epoch: 304 | loss: 0.69275 - acc: 0.6807 -- iter: 16/29
[A[ATraining Step: 1215 | total loss: [1m[32m0.67700[0m[0m | time: 0.008s
[2K
| Adam | epoch: 304 | loss: 0.67700 - acc: 0.6726 -- iter: 24/29
[A[ATraining Step: 1216 | total loss: [1m[32m0.66194[0m[0m | time: 0.010s
[2K
| Adam | epoch: 304 | loss: 0.66194 - acc: 0.6653 -- iter: 29/29
--
Training Step: 1217 | total loss: [1m[32m0.67378[0m[0m | time: 0.003s
[2K
| Adam | epoch: 305 | loss: 0.67378 - acc: 0.6613 -- iter: 08/29
[A[ATraining Step: 1218 | total loss: [1m[32m0.68095[0m[0m | time: 0.005s
[2K
| Adam | epoch: 305 | loss: 0.68095 - acc: 0.6577 -- iter: 16/29
[A[ATraining Step: 1219 | total loss: [1m[32m0.67066[0m[0m | time: 0.008s
[2K
| Adam | epoch: 305 | loss: 0.67066 - acc: 0.6544 -- iter: 24/29
[A[ATraining Step: 1220 | total loss: [1m[32m0.66842[0m[0m | time: 0.010s
[2K
| Adam | epoch: 305 | loss: 0.66842 - acc: 0.6690 -- iter: 29/29
--
Training Step: 1221 | total loss: [1m[32m0.66595[0m[0m | time: 0.003s
[2K
| Adam | epoch: 306 | loss: 0.66595 - acc: 0.6821 -- iter: 08/29
[A[ATraining Step: 1222 | total loss: [1m[32m0.67126[0m[0m | time: 0.005s
[2K
| Adam | epoch: 306 | loss: 0.67126 - acc: 0.6639 -- iter: 16/29
[A[ATraining Step: 1223 | total loss: [1m[32m0.68309[0m[0m | time: 0.008s
[2K
| Adam | epoch: 306 | loss: 0.68309 - acc: 0.6475 -- iter: 24/29
[A[ATraining Step: 1224 | total loss: [1m[32m0.69522[0m[0m | time: 0.010s
[2K
| Adam | epoch: 306 | loss: 0.69522 - acc: 0.6327 -- iter: 29/29
--
Training Step: 1225 | total loss: [1m[32m0.69756[0m[0m | time: 0.002s
[2K
| Adam | epoch: 307 | loss: 0.69756 - acc: 0.6095 -- iter: 08/29
[A[ATraining Step: 1226 | total loss: [1m[32m0.69947[0m[0m | time: 0.005s
[2K
| Adam | epoch: 307 | loss: 0.69947 - acc: 0.5885 -- iter: 16/29
[A[ATraining Step: 1227 | total loss: [1m[32m0.68458[0m[0m | time: 0.008s
[2K
| Adam | epoch: 307 | loss: 0.68458 - acc: 0.6047 -- iter: 24/29
[A[ATraining Step: 1228 | total loss: [1m[32m0.68268[0m[0m | time: 0.010s
[2K
| Adam | epoch: 307 | loss: 0.68268 - acc: 0.6192 -- iter: 29/29
--
Training Step: 1229 | total loss: [1m[32m0.67179[0m[0m | time: 0.003s
[2K
| Adam | epoch: 308 | loss: 0.67179 - acc: 0.6323 -- iter: 08/29
[A[ATraining Step: 1230 | total loss: [1m[32m0.66187[0m[0m | time: 0.005s
[2K
| Adam | epoch: 308 | loss: 0.66187 - acc: 0.6490 -- iter: 16/29
[A[ATraining Step: 1231 | total loss: [1m[32m0.65262[0m[0m | time: 0.008s
[2K
| Adam | epoch: 308 | loss: 0.65262 - acc: 0.6641 -- iter: 24/29
[A[ATraining Step: 1232 | total loss: [1m[32m0.66282[0m[0m | time: 0.010s
[2K
| Adam | epoch: 308 | loss: 0.66282 - acc: 0.6602 -- iter: 29/29
--
Training Step: 1233 | total loss: [1m[32m0.67165[0m[0m | time: 0.003s
[2K
| Adam | epoch: 309 | loss: 0.67165 - acc: 0.6442 -- iter: 08/29
[A[ATraining Step: 1234 | total loss: [1m[32m0.66265[0m[0m | time: 0.006s
[2K
| Adam | epoch: 309 | loss: 0.66265 - acc: 0.6423 -- iter: 16/29
[A[ATraining Step: 1235 | total loss: [1m[32m0.65583[0m[0m | time: 0.008s
[2K
| Adam | epoch: 309 | loss: 0.65583 - acc: 0.6381 -- iter: 24/29
[A[ATraining Step: 1236 | total loss: [1m[32m0.64937[0m[0m | time: 0.011s
[2K
| Adam | epoch: 309 | loss: 0.64937 - acc: 0.6342 -- iter: 29/29
--
Training Step: 1237 | total loss: [1m[32m0.65830[0m[0m | time: 0.003s
[2K
| Adam | epoch: 310 | loss: 0.65830 - acc: 0.6208 -- iter: 08/29
[A[ATraining Step: 1238 | total loss: [1m[32m0.66589[0m[0m | time: 0.005s
[2K
| Adam | epoch: 310 | loss: 0.66589 - acc: 0.6337 -- iter: 16/29
[A[ATraining Step: 1239 | total loss: [1m[32m0.68188[0m[0m | time: 0.008s
[2K
| Adam | epoch: 310 | loss: 0.68188 - acc: 0.6079 -- iter: 24/29
[A[ATraining Step: 1240 | total loss: [1m[32m0.67326[0m[0m | time: 0.011s
[2K
| Adam | epoch: 310 | loss: 0.67326 - acc: 0.6271 -- iter: 29/29
--
Training Step: 1241 | total loss: [1m[32m0.66492[0m[0m | time: 0.003s
[2K
| Adam | epoch: 311 | loss: 0.66492 - acc: 0.6444 -- iter: 08/29
[A[ATraining Step: 1242 | total loss: [1m[32m0.67423[0m[0m | time: 0.006s
[2K
| Adam | epoch: 311 | loss: 0.67423 - acc: 0.6299 -- iter: 16/29
[A[ATraining Step: 1243 | total loss: [1m[32m0.65184[0m[0m | time: 0.008s
[2K
| Adam | epoch: 311 | loss: 0.65184 - acc: 0.6669 -- iter: 24/29
[A[ATraining Step: 1244 | total loss: [1m[32m0.66047[0m[0m | time: 0.011s
[2K
| Adam | epoch: 311 | loss: 0.66047 - acc: 0.6752 -- iter: 29/29
--
Training Step: 1245 | total loss: [1m[32m0.63223[0m[0m | time: 0.003s
[2K
| Adam | epoch: 312 | loss: 0.63223 - acc: 0.7077 -- iter: 08/29
[A[ATraining Step: 1246 | total loss: [1m[32m0.60655[0m[0m | time: 0.006s
[2K
| Adam | epoch: 312 | loss: 0.60655 - acc: 0.7370 -- iter: 16/29
[A[ATraining Step: 1247 | total loss: [1m[32m0.61884[0m[0m | time: 0.009s
[2K
| Adam | epoch: 312 | loss: 0.61884 - acc: 0.7133 -- iter: 24/29
[A[ATraining Step: 1248 | total loss: [1m[32m0.62573[0m[0m | time: 0.011s
[2K
| Adam | epoch: 312 | loss: 0.62573 - acc: 0.6919 -- iter: 29/29
--
Training Step: 1249 | total loss: [1m[32m0.63915[0m[0m | time: 0.003s
[2K
| Adam | epoch: 313 | loss: 0.63915 - acc: 0.6977 -- iter: 08/29
[A[ATraining Step: 1250 | total loss: [1m[32m0.65094[0m[0m | time: 0.005s
[2K
| Adam | epoch: 313 | loss: 0.65094 - acc: 0.6880 -- iter: 16/29
[A[ATraining Step: 1251 | total loss: [1m[32m0.66117[0m[0m | time: 0.008s
[2K
| Adam | epoch: 313 | loss: 0.66117 - acc: 0.6792 -- iter: 24/29
[A[ATraining Step: 1252 | total loss: [1m[32m0.66378[0m[0m | time: 0.011s
[2K
| Adam | epoch: 313 | loss: 0.66378 - acc: 0.6613 -- iter: 29/29
--
Training Step: 1253 | total loss: [1m[32m0.64325[0m[0m | time: 0.003s
[2K
| Adam | epoch: 314 | loss: 0.64325 - acc: 0.6701 -- iter: 08/29
[A[ATraining Step: 1254 | total loss: [1m[32m0.65506[0m[0m | time: 0.005s
[2K
| Adam | epoch: 314 | loss: 0.65506 - acc: 0.6406 -- iter: 16/29
[A[ATraining Step: 1255 | total loss: [1m[32m0.64772[0m[0m | time: 0.008s
[2K
| Adam | epoch: 314 | loss: 0.64772 - acc: 0.6566 -- iter: 24/29
[A[ATraining Step: 1256 | total loss: [1m[32m0.64039[0m[0m | time: 0.011s
[2K
| Adam | epoch: 314 | loss: 0.64039 - acc: 0.6709 -- iter: 29/29
--
Training Step: 1257 | total loss: [1m[32m0.63446[0m[0m | time: 0.003s
[2K
| Adam | epoch: 315 | loss: 0.63446 - acc: 0.6788 -- iter: 08/29
[A[ATraining Step: 1258 | total loss: [1m[32m0.63609[0m[0m | time: 0.006s
[2K
| Adam | epoch: 315 | loss: 0.63609 - acc: 0.6859 -- iter: 16/29
[A[ATraining Step: 1259 | total loss: [1m[32m0.63642[0m[0m | time: 0.008s
[2K
| Adam | epoch: 315 | loss: 0.63642 - acc: 0.6923 -- iter: 24/29
[A[ATraining Step: 1260 | total loss: [1m[32m0.64223[0m[0m | time: 0.010s
[2K
| Adam | epoch: 315 | loss: 0.64223 - acc: 0.6831 -- iter: 29/29
--
Training Step: 1261 | total loss: [1m[32m0.64713[0m[0m | time: 0.003s
[2K
| Adam | epoch: 316 | loss: 0.64713 - acc: 0.6548 -- iter: 08/29
[A[ATraining Step: 1262 | total loss: [1m[32m0.64588[0m[0m | time: 0.007s
[2K
| Adam | epoch: 316 | loss: 0.64588 - acc: 0.6518 -- iter: 16/29
[A[ATraining Step: 1263 | total loss: [1m[32m0.64144[0m[0m | time: 0.011s
[2K
| Adam | epoch: 316 | loss: 0.64144 - acc: 0.6616 -- iter: 24/29
[A[ATraining Step: 1264 | total loss: [1m[32m0.64426[0m[0m | time: 0.030s
[2K
| Adam | epoch: 316 | loss: 0.64426 - acc: 0.6955 -- iter: 29/29
--
Training Step: 1265 | total loss: [1m[32m0.64770[0m[0m | time: 0.002s
[2K
| Adam | epoch: 317 | loss: 0.64770 - acc: 0.7059 -- iter: 08/29
[A[ATraining Step: 1266 | total loss: [1m[32m0.65060[0m[0m | time: 0.005s
[2K
| Adam | epoch: 317 | loss: 0.65060 - acc: 0.7153 -- iter: 16/29
[A[ATraining Step: 1267 | total loss: [1m[32m0.64396[0m[0m | time: 0.008s
[2K
| Adam | epoch: 317 | loss: 0.64396 - acc: 0.7063 -- iter: 24/29
[A[ATraining Step: 1268 | total loss: [1m[32m0.64021[0m[0m | time: 0.010s
[2K
| Adam | epoch: 317 | loss: 0.64021 - acc: 0.7232 -- iter: 29/29
--
Training Step: 1269 | total loss: [1m[32m0.64366[0m[0m | time: 0.003s
[2K
| Adam | epoch: 318 | loss: 0.64366 - acc: 0.7258 -- iter: 08/29
[A[ATraining Step: 1270 | total loss: [1m[32m0.63428[0m[0m | time: 0.005s
[2K
| Adam | epoch: 318 | loss: 0.63428 - acc: 0.7533 -- iter: 16/29
[A[ATraining Step: 1271 | total loss: [1m[32m0.62552[0m[0m | time: 0.008s
[2K
| Adam | epoch: 318 | loss: 0.62552 - acc: 0.7779 -- iter: 24/29
[A[ATraining Step: 1272 | total loss: [1m[32m0.62549[0m[0m | time: 0.010s
[2K
| Adam | epoch: 318 | loss: 0.62549 - acc: 0.7626 -- iter: 29/29
--
Training Step: 1273 | total loss: [1m[32m0.62460[0m[0m | time: 0.002s
[2K
| Adam | epoch: 319 | loss: 0.62460 - acc: 0.7739 -- iter: 08/29
[A[ATraining Step: 1274 | total loss: [1m[32m0.60593[0m[0m | time: 0.005s
[2K
| Adam | epoch: 319 | loss: 0.60593 - acc: 0.7965 -- iter: 16/29
[A[ATraining Step: 1275 | total loss: [1m[32m0.60231[0m[0m | time: 0.008s
[2K
| Adam | epoch: 319 | loss: 0.60231 - acc: 0.8168 -- iter: 24/29
[A[ATraining Step: 1276 | total loss: [1m[32m0.59882[0m[0m | time: 0.010s
[2K
| Adam | epoch: 319 | loss: 0.59882 - acc: 0.8352 -- iter: 29/29
--
Training Step: 1277 | total loss: [1m[32m0.61212[0m[0m | time: 0.003s
[2K
| Adam | epoch: 320 | loss: 0.61212 - acc: 0.8016 -- iter: 08/29
[A[ATraining Step: 1278 | total loss: [1m[32m0.62238[0m[0m | time: 0.005s
[2K
| Adam | epoch: 320 | loss: 0.62238 - acc: 0.7840 -- iter: 16/29
[A[ATraining Step: 1279 | total loss: [1m[32m0.61380[0m[0m | time: 0.008s
[2K
| Adam | epoch: 320 | loss: 0.61380 - acc: 0.7806 -- iter: 24/29
[A[ATraining Step: 1280 | total loss: [1m[32m0.62663[0m[0m | time: 0.011s
[2K
| Adam | epoch: 320 | loss: 0.62663 - acc: 0.7625 -- iter: 29/29
--
Training Step: 1281 | total loss: [1m[32m0.63798[0m[0m | time: 0.002s
[2K
| Adam | epoch: 321 | loss: 0.63798 - acc: 0.7463 -- iter: 08/29
[A[ATraining Step: 1282 | total loss: [1m[32m0.63455[0m[0m | time: 0.005s
[2K
| Adam | epoch: 321 | loss: 0.63455 - acc: 0.7466 -- iter: 16/29
[A[ATraining Step: 1283 | total loss: [1m[32m0.63238[0m[0m | time: 0.007s
[2K
| Adam | epoch: 321 | loss: 0.63238 - acc: 0.7720 -- iter: 24/29
[A[ATraining Step: 1284 | total loss: [1m[32m0.63712[0m[0m | time: 0.010s
[2K
| Adam | epoch: 321 | loss: 0.63712 - acc: 0.7698 -- iter: 29/29
--
Training Step: 1285 | total loss: [1m[32m0.62252[0m[0m | time: 0.003s
[2K
| Adam | epoch: 322 | loss: 0.62252 - acc: 0.7728 -- iter: 08/29
[A[ATraining Step: 1286 | total loss: [1m[32m0.60900[0m[0m | time: 0.005s
[2K
| Adam | epoch: 322 | loss: 0.60900 - acc: 0.7755 -- iter: 16/29
[A[ATraining Step: 1287 | total loss: [1m[32m0.61261[0m[0m | time: 0.008s
[2K
| Adam | epoch: 322 | loss: 0.61261 - acc: 0.7855 -- iter: 24/29
[A[ATraining Step: 1288 | total loss: [1m[32m0.60850[0m[0m | time: 0.010s
[2K
| Adam | epoch: 322 | loss: 0.60850 - acc: 0.7694 -- iter: 29/29
--
Training Step: 1289 | total loss: [1m[32m0.61197[0m[0m | time: 0.003s
[2K
| Adam | epoch: 323 | loss: 0.61197 - acc: 0.7675 -- iter: 08/29
[A[ATraining Step: 1290 | total loss: [1m[32m0.58333[0m[0m | time: 0.005s
[2K
| Adam | epoch: 323 | loss: 0.58333 - acc: 0.7707 -- iter: 16/29
[A[ATraining Step: 1291 | total loss: [1m[32m0.55736[0m[0m | time: 0.008s
[2K
| Adam | epoch: 323 | loss: 0.55736 - acc: 0.7737 -- iter: 24/29
[A[ATraining Step: 1292 | total loss: [1m[32m0.57075[0m[0m | time: 0.010s
[2K
| Adam | epoch: 323 | loss: 0.57075 - acc: 0.7588 -- iter: 29/29
--
Training Step: 1293 | total loss: [1m[32m0.57772[0m[0m | time: 0.003s
[2K
| Adam | epoch: 324 | loss: 0.57772 - acc: 0.7579 -- iter: 08/29
[A[ATraining Step: 1294 | total loss: [1m[32m0.56823[0m[0m | time: 0.006s
[2K
| Adam | epoch: 324 | loss: 0.56823 - acc: 0.7696 -- iter: 16/29
[A[ATraining Step: 1295 | total loss: [1m[32m0.57921[0m[0m | time: 0.008s
[2K
| Adam | epoch: 324 | loss: 0.57921 - acc: 0.7527 -- iter: 24/29
[A[ATraining Step: 1296 | total loss: [1m[32m0.58863[0m[0m | time: 0.011s
[2K
| Adam | epoch: 324 | loss: 0.58863 - acc: 0.7574 -- iter: 29/29
--
Training Step: 1297 | total loss: [1m[32m0.60048[0m[0m | time: 0.003s
[2K
| Adam | epoch: 325 | loss: 0.60048 - acc: 0.7442 -- iter: 08/29
[A[ATraining Step: 1298 | total loss: [1m[32m0.59563[0m[0m | time: 0.005s
[2K
| Adam | epoch: 325 | loss: 0.59563 - acc: 0.7447 -- iter: 16/29
[A[ATraining Step: 1299 | total loss: [1m[32m0.61026[0m[0m | time: 0.008s
[2K
| Adam | epoch: 325 | loss: 0.61026 - acc: 0.7453 -- iter: 24/29
[A[ATraining Step: 1300 | total loss: [1m[32m0.61464[0m[0m | time: 0.010s
[2K
| Adam | epoch: 325 | loss: 0.61464 - acc: 0.7507 -- iter: 29/29
--
Training Step: 1301 | total loss: [1m[32m0.61830[0m[0m | time: 0.002s
[2K
| Adam | epoch: 326 | loss: 0.61830 - acc: 0.7557 -- iter: 08/29
[A[ATraining Step: 1302 | total loss: [1m[32m0.59999[0m[0m | time: 0.005s
[2K
| Adam | epoch: 326 | loss: 0.59999 - acc: 0.7551 -- iter: 16/29
[A[ATraining Step: 1303 | total loss: [1m[32m0.59645[0m[0m | time: 0.007s
[2K
| Adam | epoch: 326 | loss: 0.59645 - acc: 0.7671 -- iter: 24/29
[A[ATraining Step: 1304 | total loss: [1m[32m0.60110[0m[0m | time: 0.010s
[2K
| Adam | epoch: 326 | loss: 0.60110 - acc: 0.7779 -- iter: 29/29
--
Training Step: 1305 | total loss: [1m[32m0.57657[0m[0m | time: 0.002s
[2K
| Adam | epoch: 327 | loss: 0.57657 - acc: 0.8001 -- iter: 08/29
[A[ATraining Step: 1306 | total loss: [1m[32m0.55400[0m[0m | time: 0.005s
[2K
| Adam | epoch: 327 | loss: 0.55400 - acc: 0.8201 -- iter: 16/29
[A[ATraining Step: 1307 | total loss: [1m[32m0.56554[0m[0m | time: 0.007s
[2K
| Adam | epoch: 327 | loss: 0.56554 - acc: 0.7756 -- iter: 24/29
[A[ATraining Step: 1308 | total loss: [1m[32m0.56882[0m[0m | time: 0.010s
[2K
| Adam | epoch: 327 | loss: 0.56882 - acc: 0.7855 -- iter: 29/29
--
Training Step: 1309 | total loss: [1m[32m0.58366[0m[0m | time: 0.003s
[2K
| Adam | epoch: 328 | loss: 0.58366 - acc: 0.7820 -- iter: 08/29
[A[ATraining Step: 1310 | total loss: [1m[32m0.57848[0m[0m | time: 0.005s
[2K
| Adam | epoch: 328 | loss: 0.57848 - acc: 0.7838 -- iter: 16/29
[A[ATraining Step: 1311 | total loss: [1m[32m0.57355[0m[0m | time: 0.008s
[2K
| Adam | epoch: 328 | loss: 0.57355 - acc: 0.7854 -- iter: 24/29
[A[ATraining Step: 1312 | total loss: [1m[32m0.57581[0m[0m | time: 0.011s
[2K
| Adam | epoch: 328 | loss: 0.57581 - acc: 0.7944 -- iter: 29/29
--
Training Step: 1313 | total loss: [1m[32m0.56630[0m[0m | time: 0.003s
[2K
| Adam | epoch: 329 | loss: 0.56630 - acc: 0.7984 -- iter: 08/29
[A[ATraining Step: 1314 | total loss: [1m[32m0.56630[0m[0m | time: 0.006s
[2K
| Adam | epoch: 329 | loss: 0.56630 - acc: 0.7984 -- iter: 16/29
[A[ATraining Step: 1315 | total loss: [1m[32m0.59655[0m[0m | time: 0.008s
[2K
| Adam | epoch: 329 | loss: 0.59655 - acc: 0.7786 -- iter: 24/29
[A[ATraining Step: 1316 | total loss: [1m[32m0.62363[0m[0m | time: 0.011s
[2K
| Adam | epoch: 329 | loss: 0.62363 - acc: 0.7607 -- iter: 29/29
--
Training Step: 1317 | total loss: [1m[32m0.61669[0m[0m | time: 0.003s
[2K
| Adam | epoch: 330 | loss: 0.61669 - acc: 0.7597 -- iter: 08/29
[A[ATraining Step: 1318 | total loss: [1m[32m0.59655[0m[0m | time: 0.005s
[2K
| Adam | epoch: 330 | loss: 0.59655 - acc: 0.7837 -- iter: 16/29
[A[ATraining Step: 1319 | total loss: [1m[32m0.58848[0m[0m | time: 0.008s
[2K
| Adam | epoch: 330 | loss: 0.58848 - acc: 0.7928 -- iter: 24/29
[A[ATraining Step: 1320 | total loss: [1m[32m0.58794[0m[0m | time: 0.011s
[2K
| Adam | epoch: 330 | loss: 0.58794 - acc: 0.7935 -- iter: 29/29
--
Training Step: 1321 | total loss: [1m[32m0.58702[0m[0m | time: 0.003s
[2K
| Adam | epoch: 331 | loss: 0.58702 - acc: 0.7942 -- iter: 08/29
[A[ATraining Step: 1322 | total loss: [1m[32m0.58538[0m[0m | time: 0.006s
[2K
| Adam | epoch: 331 | loss: 0.58538 - acc: 0.7898 -- iter: 16/29
[A[ATraining Step: 1323 | total loss: [1m[32m0.58913[0m[0m | time: 0.009s
[2K
| Adam | epoch: 331 | loss: 0.58913 - acc: 0.8108 -- iter: 24/29
[A[ATraining Step: 1324 | total loss: [1m[32m0.58570[0m[0m | time: 0.011s
[2K
| Adam | epoch: 331 | loss: 0.58570 - acc: 0.8172 -- iter: 29/29
--
Training Step: 1325 | total loss: [1m[32m0.58908[0m[0m | time: 0.003s
[2K
| Adam | epoch: 332 | loss: 0.58908 - acc: 0.8355 -- iter: 08/29
[A[ATraining Step: 1326 | total loss: [1m[32m0.59203[0m[0m | time: 0.005s
[2K
| Adam | epoch: 332 | loss: 0.59203 - acc: 0.8519 -- iter: 16/29
[A[ATraining Step: 1327 | total loss: [1m[32m0.57810[0m[0m | time: 0.008s
[2K
| Adam | epoch: 332 | loss: 0.57810 - acc: 0.8667 -- iter: 24/29
[A[ATraining Step: 1328 | total loss: [1m[32m0.58550[0m[0m | time: 0.011s
[2K
| Adam | epoch: 332 | loss: 0.58550 - acc: 0.8426 -- iter: 29/29
--
Training Step: 1329 | total loss: [1m[32m0.59502[0m[0m | time: 0.003s
[2K
| Adam | epoch: 333 | loss: 0.59502 - acc: 0.8333 -- iter: 08/29
[A[ATraining Step: 1330 | total loss: [1m[32m0.61191[0m[0m | time: 0.005s
[2K
| Adam | epoch: 333 | loss: 0.61191 - acc: 0.8100 -- iter: 16/29
[A[ATraining Step: 1331 | total loss: [1m[32m0.62664[0m[0m | time: 0.008s
[2K
| Adam | epoch: 333 | loss: 0.62664 - acc: 0.7890 -- iter: 24/29
[A[ATraining Step: 1332 | total loss: [1m[32m0.59916[0m[0m | time: 0.011s
[2K
| Adam | epoch: 333 | loss: 0.59916 - acc: 0.8101 -- iter: 29/29
--
Training Step: 1333 | total loss: [1m[32m0.59108[0m[0m | time: 0.003s
[2K
| Adam | epoch: 334 | loss: 0.59108 - acc: 0.8291 -- iter: 08/29
[A[ATraining Step: 1334 | total loss: [1m[32m0.60377[0m[0m | time: 0.006s
[2K
| Adam | epoch: 334 | loss: 0.60377 - acc: 0.7962 -- iter: 16/29
[A[ATraining Step: 1335 | total loss: [1m[32m0.58221[0m[0m | time: 0.008s
[2K
| Adam | epoch: 334 | loss: 0.58221 - acc: 0.7966 -- iter: 24/29
[A[ATraining Step: 1336 | total loss: [1m[32m0.56310[0m[0m | time: 0.011s
[2K
| Adam | epoch: 334 | loss: 0.56310 - acc: 0.7969 -- iter: 29/29
--
Training Step: 1337 | total loss: [1m[32m0.56833[0m[0m | time: 0.003s
[2K
| Adam | epoch: 335 | loss: 0.56833 - acc: 0.7922 -- iter: 08/29
[A[ATraining Step: 1338 | total loss: [1m[32m0.55579[0m[0m | time: 0.005s
[2K
| Adam | epoch: 335 | loss: 0.55579 - acc: 0.8130 -- iter: 16/29
[A[ATraining Step: 1339 | total loss: [1m[32m0.55041[0m[0m | time: 0.008s
[2K
| Adam | epoch: 335 | loss: 0.55041 - acc: 0.8067 -- iter: 24/29
[A[ATraining Step: 1340 | total loss: [1m[32m0.56221[0m[0m | time: 0.032s
[2K
| Adam | epoch: 335 | loss: 0.56221 - acc: 0.8060 -- iter: 29/29
--
Training Step: 1341 | total loss: [1m[32m0.57263[0m[0m | time: 0.003s
[2K
| Adam | epoch: 336 | loss: 0.57263 - acc: 0.8054 -- iter: 08/29
[A[ATraining Step: 1342 | total loss: [1m[32m0.58570[0m[0m | time: 0.005s
[2K
| Adam | epoch: 336 | loss: 0.58570 - acc: 0.7874 -- iter: 16/29
[A[ATraining Step: 1343 | total loss: [1m[32m0.56497[0m[0m | time: 0.008s
[2K
| Adam | epoch: 336 | loss: 0.56497 - acc: 0.7961 -- iter: 24/29
[A[ATraining Step: 1344 | total loss: [1m[32m0.57437[0m[0m | time: 0.011s
[2K
| Adam | epoch: 336 | loss: 0.57437 - acc: 0.7665 -- iter: 29/29
--
Training Step: 1345 | total loss: [1m[32m0.54529[0m[0m | time: 0.002s
[2K
| Adam | epoch: 337 | loss: 0.54529 - acc: 0.7899 -- iter: 08/29
[A[ATraining Step: 1346 | total loss: [1m[32m0.51868[0m[0m | time: 0.005s
[2K
| Adam | epoch: 337 | loss: 0.51868 - acc: 0.8109 -- iter: 16/29
[A[ATraining Step: 1347 | total loss: [1m[32m0.51786[0m[0m | time: 0.007s
[2K
| Adam | epoch: 337 | loss: 0.51786 - acc: 0.8298 -- iter: 24/29
[A[ATraining Step: 1348 | total loss: [1m[32m0.53071[0m[0m | time: 0.010s
[2K
| Adam | epoch: 337 | loss: 0.53071 - acc: 0.8093 -- iter: 29/29
--
Training Step: 1349 | total loss: [1m[32m0.52721[0m[0m | time: 0.002s
[2K
| Adam | epoch: 338 | loss: 0.52721 - acc: 0.8284 -- iter: 08/29
[A[ATraining Step: 1350 | total loss: [1m[32m0.53307[0m[0m | time: 0.005s
[2K
| Adam | epoch: 338 | loss: 0.53307 - acc: 0.8255 -- iter: 16/29
[A[ATraining Step: 1351 | total loss: [1m[32m0.53829[0m[0m | time: 0.008s
[2K
| Adam | epoch: 338 | loss: 0.53829 - acc: 0.8230 -- iter: 24/29
[A[ATraining Step: 1352 | total loss: [1m[32m0.53641[0m[0m | time: 0.010s
[2K
| Adam | epoch: 338 | loss: 0.53641 - acc: 0.8032 -- iter: 29/29
--
Training Step: 1353 | total loss: [1m[32m0.54116[0m[0m | time: 0.002s
[2K
| Adam | epoch: 339 | loss: 0.54116 - acc: 0.8104 -- iter: 08/29
[A[ATraining Step: 1354 | total loss: [1m[32m0.55467[0m[0m | time: 0.005s
[2K
| Adam | epoch: 339 | loss: 0.55467 - acc: 0.8168 -- iter: 16/29
[A[ATraining Step: 1355 | total loss: [1m[32m0.53580[0m[0m | time: 0.007s
[2K
| Adam | epoch: 339 | loss: 0.53580 - acc: 0.8352 -- iter: 24/29
[A[ATraining Step: 1356 | total loss: [1m[32m0.51869[0m[0m | time: 0.010s
[2K
| Adam | epoch: 339 | loss: 0.51869 - acc: 0.8516 -- iter: 29/29
--
Training Step: 1357 | total loss: [1m[32m0.52087[0m[0m | time: 0.002s
[2K
| Adam | epoch: 340 | loss: 0.52087 - acc: 0.8415 -- iter: 08/29
[A[ATraining Step: 1358 | total loss: [1m[32m0.51939[0m[0m | time: 0.005s
[2K
| Adam | epoch: 340 | loss: 0.51939 - acc: 0.8448 -- iter: 16/29
[A[ATraining Step: 1359 | total loss: [1m[32m0.50699[0m[0m | time: 0.008s
[2K
| Adam | epoch: 340 | loss: 0.50699 - acc: 0.8478 -- iter: 24/29
[A[ATraining Step: 1360 | total loss: [1m[32m0.50679[0m[0m | time: 0.010s
[2K
| Adam | epoch: 340 | loss: 0.50679 - acc: 0.8631 -- iter: 29/29
--
Training Step: 1361 | total loss: [1m[32m0.50615[0m[0m | time: 0.002s
[2K
| Adam | epoch: 341 | loss: 0.50615 - acc: 0.8768 -- iter: 08/29
[A[ATraining Step: 1362 | total loss: [1m[32m0.52225[0m[0m | time: 0.005s
[2K
| Adam | epoch: 341 | loss: 0.52225 - acc: 0.8766 -- iter: 16/29
[A[ATraining Step: 1363 | total loss: [1m[32m0.52661[0m[0m | time: 0.008s
[2K
| Adam | epoch: 341 | loss: 0.52661 - acc: 0.8514 -- iter: 24/29
[A[ATraining Step: 1364 | total loss: [1m[32m0.51628[0m[0m | time: 0.010s
[2K
| Adam | epoch: 341 | loss: 0.51628 - acc: 0.8538 -- iter: 29/29
--
Training Step: 1365 | total loss: [1m[32m0.51802[0m[0m | time: 0.002s
[2K
| Adam | epoch: 342 | loss: 0.51802 - acc: 0.8684 -- iter: 08/29
[A[ATraining Step: 1366 | total loss: [1m[32m0.51905[0m[0m | time: 0.005s
[2K
| Adam | epoch: 342 | loss: 0.51905 - acc: 0.8816 -- iter: 16/29
[A[ATraining Step: 1367 | total loss: [1m[32m0.52629[0m[0m | time: 0.007s
[2K
| Adam | epoch: 342 | loss: 0.52629 - acc: 0.8434 -- iter: 24/29
[A[ATraining Step: 1368 | total loss: [1m[32m0.53146[0m[0m | time: 0.010s
[2K
| Adam | epoch: 342 | loss: 0.53146 - acc: 0.8341 -- iter: 29/29
--
Training Step: 1369 | total loss: [1m[32m0.53146[0m[0m | time: 0.003s
[2K
| Adam | epoch: 343 | loss: 0.53146 - acc: 0.8382 -- iter: 08/29
[A[ATraining Step: 1370 | total loss: [1m[32m0.53213[0m[0m | time: 0.005s
[2K
| Adam | epoch: 343 | loss: 0.53213 - acc: 0.8343 -- iter: 16/29
[A[ATraining Step: 1371 | total loss: [1m[32m0.53204[0m[0m | time: 0.008s
[2K
| Adam | epoch: 343 | loss: 0.53204 - acc: 0.8509 -- iter: 24/29
[A[ATraining Step: 1372 | total loss: [1m[32m0.52930[0m[0m | time: 0.010s
[2K
| Adam | epoch: 343 | loss: 0.52930 - acc: 0.8408 -- iter: 29/29
--
Training Step: 1373 | total loss: [1m[32m0.53298[0m[0m | time: 0.003s
[2K
| Adam | epoch: 344 | loss: 0.53298 - acc: 0.8192 -- iter: 08/29
[A[ATraining Step: 1374 | total loss: [1m[32m0.53287[0m[0m | time: 0.005s
[2K
| Adam | epoch: 344 | loss: 0.53287 - acc: 0.7998 -- iter: 16/29
[A[ATraining Step: 1375 | total loss: [1m[32m0.52877[0m[0m | time: 0.008s
[2K
| Adam | epoch: 344 | loss: 0.52877 - acc: 0.8198 -- iter: 24/29
[A[ATraining Step: 1376 | total loss: [1m[32m0.52466[0m[0m | time: 0.011s
[2K
| Adam | epoch: 344 | loss: 0.52466 - acc: 0.8378 -- iter: 29/29
--
Training Step: 1377 | total loss: [1m[32m0.52048[0m[0m | time: 0.003s
[2K
| Adam | epoch: 345 | loss: 0.52048 - acc: 0.8291 -- iter: 08/29
[A[ATraining Step: 1378 | total loss: [1m[32m0.52773[0m[0m | time: 0.005s
[2K
| Adam | epoch: 345 | loss: 0.52773 - acc: 0.8212 -- iter: 16/29
[A[ATraining Step: 1379 | total loss: [1m[32m0.53073[0m[0m | time: 0.008s
[2K
| Adam | epoch: 345 | loss: 0.53073 - acc: 0.8140 -- iter: 24/29
[A[ATraining Step: 1380 | total loss: [1m[32m0.53829[0m[0m | time: 0.011s
[2K
| Adam | epoch: 345 | loss: 0.53829 - acc: 0.8126 -- iter: 29/29
--
Training Step: 1381 | total loss: [1m[32m0.54492[0m[0m | time: 0.003s
[2K
| Adam | epoch: 346 | loss: 0.54492 - acc: 0.8114 -- iter: 08/29
[A[ATraining Step: 1382 | total loss: [1m[32m0.53369[0m[0m | time: 0.006s
[2K
| Adam | epoch: 346 | loss: 0.53369 - acc: 0.8052 -- iter: 16/29
[A[ATraining Step: 1383 | total loss: [1m[32m0.53441[0m[0m | time: 0.008s
[2K
| Adam | epoch: 346 | loss: 0.53441 - acc: 0.7997 -- iter: 24/29
[A[ATraining Step: 1384 | total loss: [1m[32m0.52776[0m[0m | time: 0.011s
[2K
| Adam | epoch: 346 | loss: 0.52776 - acc: 0.8072 -- iter: 29/29
--
Training Step: 1385 | total loss: [1m[32m0.52018[0m[0m | time: 0.003s
[2K
| Adam | epoch: 347 | loss: 0.52018 - acc: 0.8265 -- iter: 08/29
[A[ATraining Step: 1386 | total loss: [1m[32m0.51309[0m[0m | time: 0.006s
[2K
| Adam | epoch: 347 | loss: 0.51309 - acc: 0.8439 -- iter: 16/29
[A[ATraining Step: 1387 | total loss: [1m[32m0.53482[0m[0m | time: 0.009s
[2K
| Adam | epoch: 347 | loss: 0.53482 - acc: 0.8095 -- iter: 24/29
[A[ATraining Step: 1388 | total loss: [1m[32m0.52360[0m[0m | time: 0.011s
[2K
| Adam | epoch: 347 | loss: 0.52360 - acc: 0.8035 -- iter: 29/29
--
Training Step: 1389 | total loss: [1m[32m0.52185[0m[0m | time: 0.023s
[2K
| Adam | epoch: 348 | loss: 0.52185 - acc: 0.8107 -- iter: 08/29
[A[ATraining Step: 1390 | total loss: [1m[32m0.53766[0m[0m | time: 0.026s
[2K
| Adam | epoch: 348 | loss: 0.53766 - acc: 0.7896 -- iter: 16/29
[A[ATraining Step: 1391 | total loss: [1m[32m0.55109[0m[0m | time: 0.028s
[2K
| Adam | epoch: 348 | loss: 0.55109 - acc: 0.7706 -- iter: 24/29
[A[ATraining Step: 1392 | total loss: [1m[32m0.54168[0m[0m | time: 0.031s
[2K
| Adam | epoch: 348 | loss: 0.54168 - acc: 0.7686 -- iter: 29/29
--
Training Step: 1393 | total loss: [1m[32m0.53683[0m[0m | time: 0.003s
[2K
| Adam | epoch: 349 | loss: 0.53683 - acc: 0.7667 -- iter: 08/29
[A[ATraining Step: 1394 | total loss: [1m[32m0.52799[0m[0m | time: 0.006s
[2K
| Adam | epoch: 349 | loss: 0.52799 - acc: 0.7901 -- iter: 16/29
[A[ATraining Step: 1395 | total loss: [1m[32m0.52726[0m[0m | time: 0.008s
[2K
| Adam | epoch: 349 | loss: 0.52726 - acc: 0.7910 -- iter: 24/29
[A[ATraining Step: 1396 | total loss: [1m[32m0.52614[0m[0m | time: 0.011s
[2K
| Adam | epoch: 349 | loss: 0.52614 - acc: 0.7919 -- iter: 29/29
--
Training Step: 1397 | total loss: [1m[32m0.53707[0m[0m | time: 0.003s
[2K
| Adam | epoch: 350 | loss: 0.53707 - acc: 0.7752 -- iter: 08/29
[A[ATraining Step: 1398 | total loss: [1m[32m0.52462[0m[0m | time: 0.006s
[2K
| Adam | epoch: 350 | loss: 0.52462 - acc: 0.7727 -- iter: 16/29
[A[ATraining Step: 1399 | total loss: [1m[32m0.53691[0m[0m | time: 0.008s
[2K
| Adam | epoch: 350 | loss: 0.53691 - acc: 0.7580 -- iter: 24/29
[A[ATraining Step: 1400 | total loss: [1m[32m0.52158[0m[0m | time: 0.011s
[2K
| Adam | epoch: 350 | loss: 0.52158 - acc: 0.7822 -- iter: 29/29
--
Training Step: 1401 | total loss: [1m[32m0.50695[0m[0m | time: 0.003s
[2K
| Adam | epoch: 351 | loss: 0.50695 - acc: 0.8039 -- iter: 08/29
[A[ATraining Step: 1402 | total loss: [1m[32m0.49705[0m[0m | time: 0.005s
[2K
| Adam | epoch: 351 | loss: 0.49705 - acc: 0.8110 -- iter: 16/29
[A[ATraining Step: 1403 | total loss: [1m[32m0.50796[0m[0m | time: 0.008s
[2K
| Adam | epoch: 351 | loss: 0.50796 - acc: 0.8049 -- iter: 24/29
[A[ATraining Step: 1404 | total loss: [1m[32m0.52065[0m[0m | time: 0.011s
[2K
| Adam | epoch: 351 | loss: 0.52065 - acc: 0.7869 -- iter: 29/29
--
Training Step: 1405 | total loss: [1m[32m0.51986[0m[0m | time: 0.003s
[2K
| Adam | epoch: 352 | loss: 0.51986 - acc: 0.7883 -- iter: 08/29
[A[ATraining Step: 1406 | total loss: [1m[32m0.51906[0m[0m | time: 0.005s
[2K
| Adam | epoch: 352 | loss: 0.51906 - acc: 0.7894 -- iter: 16/29
[A[ATraining Step: 1407 | total loss: [1m[32m0.50230[0m[0m | time: 0.008s
[2K
| Adam | epoch: 352 | loss: 0.50230 - acc: 0.7980 -- iter: 24/29
[A[ATraining Step: 1408 | total loss: [1m[32m0.50218[0m[0m | time: 0.011s
[2K
| Adam | epoch: 352 | loss: 0.50218 - acc: 0.8057 -- iter: 29/29
--
Training Step: 1409 | total loss: [1m[32m0.51088[0m[0m | time: 0.003s
[2K
| Adam | epoch: 353 | loss: 0.51088 - acc: 0.7876 -- iter: 08/29
[A[ATraining Step: 1410 | total loss: [1m[32m0.50392[0m[0m | time: 0.005s
[2K
| Adam | epoch: 353 | loss: 0.50392 - acc: 0.8089 -- iter: 16/29
[A[ATraining Step: 1411 | total loss: [1m[32m0.49732[0m[0m | time: 0.008s
[2K
| Adam | epoch: 353 | loss: 0.49732 - acc: 0.8280 -- iter: 24/29
[A[ATraining Step: 1412 | total loss: [1m[32m0.49252[0m[0m | time: 0.011s
[2K
| Adam | epoch: 353 | loss: 0.49252 - acc: 0.8202 -- iter: 29/29
--
Training Step: 1413 | total loss: [1m[32m0.49191[0m[0m | time: 0.003s
[2K
| Adam | epoch: 354 | loss: 0.49191 - acc: 0.8257 -- iter: 08/29
[A[ATraining Step: 1414 | total loss: [1m[32m0.49678[0m[0m | time: 0.005s
[2K
| Adam | epoch: 354 | loss: 0.49678 - acc: 0.8181 -- iter: 16/29
[A[ATraining Step: 1415 | total loss: [1m[32m0.48127[0m[0m | time: 0.008s
[2K
| Adam | epoch: 354 | loss: 0.48127 - acc: 0.8363 -- iter: 24/29
[A[ATraining Step: 1416 | total loss: [1m[32m0.46707[0m[0m | time: 0.011s
[2K
| Adam | epoch: 354 | loss: 0.46707 - acc: 0.8527 -- iter: 29/29
--
Training Step: 1417 | total loss: [1m[32m0.46994[0m[0m | time: 0.003s
[2K
| Adam | epoch: 355 | loss: 0.46994 - acc: 0.8424 -- iter: 08/29
[A[ATraining Step: 1418 | total loss: [1m[32m0.47702[0m[0m | time: 0.005s
[2K
| Adam | epoch: 355 | loss: 0.47702 - acc: 0.8331 -- iter: 16/29
[A[ATraining Step: 1419 | total loss: [1m[32m0.46029[0m[0m | time: 0.008s
[2K
| Adam | epoch: 355 | loss: 0.46029 - acc: 0.8498 -- iter: 24/29
[A[ATraining Step: 1420 | total loss: [1m[32m0.45325[0m[0m | time: 0.027s
[2K
| Adam | epoch: 355 | loss: 0.45325 - acc: 0.8249 -- iter: 29/29
--
Training Step: 1421 | total loss: [1m[32m0.44669[0m[0m | time: 0.003s
[2K
| Adam | epoch: 356 | loss: 0.44669 - acc: 0.8024 -- iter: 08/29
[A[ATraining Step: 1422 | total loss: [1m[32m0.46363[0m[0m | time: 0.005s
[2K
| Adam | epoch: 356 | loss: 0.46363 - acc: 0.7971 -- iter: 16/29
[A[ATraining Step: 1423 | total loss: [1m[32m0.47758[0m[0m | time: 0.009s
[2K
| Adam | epoch: 356 | loss: 0.47758 - acc: 0.7799 -- iter: 24/29
[A[ATraining Step: 1424 | total loss: [1m[32m0.49220[0m[0m | time: 0.011s
[2K
| Adam | epoch: 356 | loss: 0.49220 - acc: 0.7519 -- iter: 29/29
--
Training Step: 1425 | total loss: [1m[32m0.46511[0m[0m | time: 0.002s
[2K
| Adam | epoch: 357 | loss: 0.46511 - acc: 0.7767 -- iter: 08/29
[A[ATraining Step: 1426 | total loss: [1m[32m0.44064[0m[0m | time: 0.005s
[2K
| Adam | epoch: 357 | loss: 0.44064 - acc: 0.7991 -- iter: 16/29
[A[ATraining Step: 1427 | total loss: [1m[32m0.45310[0m[0m | time: 0.007s
[2K
| Adam | epoch: 357 | loss: 0.45310 - acc: 0.8067 -- iter: 24/29
[A[ATraining Step: 1428 | total loss: [1m[32m0.45071[0m[0m | time: 0.009s
[2K
| Adam | epoch: 357 | loss: 0.45071 - acc: 0.8135 -- iter: 29/29
--
Training Step: 1429 | total loss: [1m[32m0.45118[0m[0m | time: 0.003s
[2K
| Adam | epoch: 358 | loss: 0.45118 - acc: 0.8321 -- iter: 08/29
[A[ATraining Step: 1430 | total loss: [1m[32m0.47352[0m[0m | time: 0.005s
[2K
| Adam | epoch: 358 | loss: 0.47352 - acc: 0.8289 -- iter: 16/29
[A[ATraining Step: 1431 | total loss: [1m[32m0.49355[0m[0m | time: 0.007s
[2K
| Adam | epoch: 358 | loss: 0.49355 - acc: 0.8260 -- iter: 24/29
[A[ATraining Step: 1432 | total loss: [1m[32m0.47863[0m[0m | time: 0.010s
[2K
| Adam | epoch: 358 | loss: 0.47863 - acc: 0.8309 -- iter: 29/29
--
Training Step: 1433 | total loss: [1m[32m0.83232[0m[0m | time: 0.002s
[2K
| Adam | epoch: 359 | loss: 0.83232 - acc: 0.7978 -- iter: 08/29
[A[ATraining Step: 1434 | total loss: [1m[32m0.80447[0m[0m | time: 0.005s
[2K
| Adam | epoch: 359 | loss: 0.80447 - acc: 0.8056 -- iter: 16/29
[A[ATraining Step: 1435 | total loss: [1m[32m0.74611[0m[0m | time: 0.007s
[2K
| Adam | epoch: 359 | loss: 0.74611 - acc: 0.8250 -- iter: 24/29
[A[ATraining Step: 1436 | total loss: [1m[32m0.69345[0m[0m | time: 0.009s
[2K
| Adam | epoch: 359 | loss: 0.69345 - acc: 0.8425 -- iter: 29/29
--
Training Step: 1437 | total loss: [1m[32m0.67857[0m[0m | time: 0.003s
[2K
| Adam | epoch: 360 | loss: 0.67857 - acc: 0.8332 -- iter: 08/29
[A[ATraining Step: 1438 | total loss: [1m[32m0.65924[0m[0m | time: 0.005s
[2K
| Adam | epoch: 360 | loss: 0.65924 - acc: 0.8249 -- iter: 16/29
[A[ATraining Step: 1439 | total loss: [1m[32m0.65181[0m[0m | time: 0.007s
[2K
| Adam | epoch: 360 | loss: 0.65181 - acc: 0.8174 -- iter: 24/29
[A[ATraining Step: 1440 | total loss: [1m[32m0.63140[0m[0m | time: 0.010s
[2K
| Adam | epoch: 360 | loss: 0.63140 - acc: 0.8157 -- iter: 29/29
--
Training Step: 1441 | total loss: [1m[32m0.61269[0m[0m | time: 0.003s
[2K
| Adam | epoch: 361 | loss: 0.61269 - acc: 0.8141 -- iter: 08/29
[A[ATraining Step: 1442 | total loss: [1m[32m0.59947[0m[0m | time: 0.005s
[2K
| Adam | epoch: 361 | loss: 0.59947 - acc: 0.8202 -- iter: 16/29
[A[ATraining Step: 1443 | total loss: [1m[32m0.57605[0m[0m | time: 0.007s
[2K
| Adam | epoch: 361 | loss: 0.57605 - acc: 0.8257 -- iter: 24/29
[A[ATraining Step: 1444 | total loss: [1m[32m0.56489[0m[0m | time: 0.010s
[2K
| Adam | epoch: 361 | loss: 0.56489 - acc: 0.8431 -- iter: 29/29
--
Training Step: 1445 | total loss: [1m[32m0.56839[0m[0m | time: 0.002s
[2K
| Adam | epoch: 362 | loss: 0.56839 - acc: 0.8388 -- iter: 08/29
[A[ATraining Step: 1446 | total loss: [1m[32m0.57133[0m[0m | time: 0.005s
[2K
| Adam | epoch: 362 | loss: 0.57133 - acc: 0.8349 -- iter: 16/29
[A[ATraining Step: 1447 | total loss: [1m[32m0.55357[0m[0m | time: 0.007s
[2K
| Adam | epoch: 362 | loss: 0.55357 - acc: 0.8264 -- iter: 24/29
[A[ATraining Step: 1448 | total loss: [1m[32m0.54480[0m[0m | time: 0.009s
[2K
| Adam | epoch: 362 | loss: 0.54480 - acc: 0.8188 -- iter: 29/29
--
Training Step: 1449 | total loss: [1m[32m0.53252[0m[0m | time: 0.002s
[2K
| Adam | epoch: 363 | loss: 0.53252 - acc: 0.8119 -- iter: 08/29
[A[ATraining Step: 1450 | total loss: [1m[32m0.52184[0m[0m | time: 0.005s
[2K
| Adam | epoch: 363 | loss: 0.52184 - acc: 0.8107 -- iter: 16/29
[A[ATraining Step: 1451 | total loss: [1m[32m0.51193[0m[0m | time: 0.007s
[2K
| Adam | epoch: 363 | loss: 0.51193 - acc: 0.8096 -- iter: 24/29
[A[ATraining Step: 1452 | total loss: [1m[32m0.50473[0m[0m | time: 0.009s
[2K
| Adam | epoch: 363 | loss: 0.50473 - acc: 0.8287 -- iter: 29/29
--
Training Step: 1453 | total loss: [1m[32m0.51116[0m[0m | time: 0.002s
[2K
| Adam | epoch: 364 | loss: 0.51116 - acc: 0.8208 -- iter: 08/29
[A[ATraining Step: 1454 | total loss: [1m[32m0.50010[0m[0m | time: 0.005s
[2K
| Adam | epoch: 364 | loss: 0.50010 - acc: 0.8387 -- iter: 16/29
[A[ATraining Step: 1455 | total loss: [1m[32m0.47185[0m[0m | time: 0.007s
[2K
| Adam | epoch: 364 | loss: 0.47185 - acc: 0.8549 -- iter: 24/29
[A[ATraining Step: 1456 | total loss: [1m[32m0.44631[0m[0m | time: 0.020s
[2K
| Adam | epoch: 364 | loss: 0.44631 - acc: 0.8694 -- iter: 29/29
--
Training Step: 1457 | total loss: [1m[32m0.45050[0m[0m | time: 0.002s
[2K
| Adam | epoch: 365 | loss: 0.45050 - acc: 0.8574 -- iter: 08/29
[A[ATraining Step: 1458 | total loss: [1m[32m0.47168[0m[0m | time: 0.005s
[2K
| Adam | epoch: 365 | loss: 0.47168 - acc: 0.8467 -- iter: 16/29
[A[ATraining Step: 1459 | total loss: [1m[32m0.44992[0m[0m | time: 0.007s
[2K
| Adam | epoch: 365 | loss: 0.44992 - acc: 0.8620 -- iter: 24/29
[A[ATraining Step: 1460 | total loss: [1m[32m0.46662[0m[0m | time: 0.010s
[2K
| Adam | epoch: 365 | loss: 0.46662 - acc: 0.8558 -- iter: 29/29
--
Training Step: 1461 | total loss: [1m[32m0.48141[0m[0m | time: 0.002s
[2K
| Adam | epoch: 366 | loss: 0.48141 - acc: 0.8502 -- iter: 08/29
[A[ATraining Step: 1462 | total loss: [1m[32m0.48443[0m[0m | time: 0.005s
[2K
| Adam | epoch: 366 | loss: 0.48443 - acc: 0.8402 -- iter: 16/29
[A[ATraining Step: 1463 | total loss: [1m[32m1.82803[0m[0m | time: 0.007s
[2K
| Adam | epoch: 366 | loss: 1.82803 - acc: 0.7687 -- iter: 24/29
[A[ATraining Step: 1464 | total loss: [1m[32m1.67874[0m[0m | time: 0.010s
[2K
| Adam | epoch: 366 | loss: 1.67874 - acc: 0.7918 -- iter: 29/29
--
Training Step: 1465 | total loss: [1m[32m1.53608[0m[0m | time: 0.003s
[2K
| Adam | epoch: 367 | loss: 1.53608 - acc: 0.7926 -- iter: 08/29
[A[ATraining Step: 1466 | total loss: [1m[32m1.40760[0m[0m | time: 0.005s
[2K
| Adam | epoch: 367 | loss: 1.40760 - acc: 0.7934 -- iter: 16/29
[A[ATraining Step: 1467 | total loss: [1m[32m1.32587[0m[0m | time: 0.007s
[2K
| Adam | epoch: 367 | loss: 1.32587 - acc: 0.7765 -- iter: 24/29
[A[ATraining Step: 1468 | total loss: [1m[32m1.60767[0m[0m | time: 0.010s
[2K
| Adam | epoch: 367 | loss: 1.60767 - acc: 0.7239 -- iter: 29/29
--
Training Step: 1469 | total loss: [1m[32m1.48962[0m[0m | time: 0.002s
[2K
| Adam | epoch: 368 | loss: 1.48962 - acc: 0.7515 -- iter: 08/29
[A[ATraining Step: 1470 | total loss: [1m[32m1.39213[0m[0m | time: 0.005s
[2K
| Adam | epoch: 368 | loss: 1.39213 - acc: 0.7563 -- iter: 16/29
[A[ATraining Step: 1471 | total loss: [1m[32m1.30401[0m[0m | time: 0.007s
[2K
| Adam | epoch: 368 | loss: 1.30401 - acc: 0.7607 -- iter: 24/29
[A[ATraining Step: 1472 | total loss: [1m[32m1.20564[0m[0m | time: 0.009s
[2K
| Adam | epoch: 368 | loss: 1.20564 - acc: 0.7721 -- iter: 29/29
--
Training Step: 1473 | total loss: [1m[32m1.14603[0m[0m | time: 0.002s
[2K
| Adam | epoch: 369 | loss: 1.14603 - acc: 0.7574 -- iter: 08/29
[A[ATraining Step: 1474 | total loss: [1m[32m1.06755[0m[0m | time: 0.005s
[2K
| Adam | epoch: 369 | loss: 1.06755 - acc: 0.7692 -- iter: 16/29
[A[ATraining Step: 1475 | total loss: [1m[32m1.00916[0m[0m | time: 0.007s
[2K
| Adam | epoch: 369 | loss: 1.00916 - acc: 0.7723 -- iter: 24/29
[A[ATraining Step: 1476 | total loss: [1m[32m0.95648[0m[0m | time: 0.010s
[2K
| Adam | epoch: 369 | loss: 0.95648 - acc: 0.7750 -- iter: 29/29
--
Training Step: 1477 | total loss: [1m[32m0.90568[0m[0m | time: 0.002s
[2K
| Adam | epoch: 370 | loss: 0.90568 - acc: 0.7850 -- iter: 08/29
[A[ATraining Step: 1478 | total loss: [1m[32m0.87070[0m[0m | time: 0.005s
[2K
| Adam | epoch: 370 | loss: 0.87070 - acc: 0.7815 -- iter: 16/29
[A[ATraining Step: 1479 | total loss: [1m[32m0.83962[0m[0m | time: 0.007s
[2K
| Adam | epoch: 370 | loss: 0.83962 - acc: 0.7909 -- iter: 24/29
[A[ATraining Step: 1480 | total loss: [1m[32m0.81296[0m[0m | time: 0.010s
[2K
| Adam | epoch: 370 | loss: 0.81296 - acc: 0.7718 -- iter: 29/29
--
Training Step: 1481 | total loss: [1m[32m0.78890[0m[0m | time: 0.002s
[2K
| Adam | epoch: 371 | loss: 0.78890 - acc: 0.7546 -- iter: 08/29
[A[ATraining Step: 1482 | total loss: [1m[32m0.75913[0m[0m | time: 0.005s
[2K
| Adam | epoch: 371 | loss: 0.75913 - acc: 0.7542 -- iter: 16/29
[A[ATraining Step: 1483 | total loss: [1m[32m0.70818[0m[0m | time: 0.007s
[2K
| Adam | epoch: 371 | loss: 0.70818 - acc: 0.7662 -- iter: 24/29
[A[ATraining Step: 1484 | total loss: [1m[32m0.68764[0m[0m | time: 0.009s
[2K
| Adam | epoch: 371 | loss: 0.68764 - acc: 0.7646 -- iter: 29/29
--
Training Step: 1485 | total loss: [1m[32m0.65813[0m[0m | time: 0.002s
[2K
| Adam | epoch: 372 | loss: 0.65813 - acc: 0.7682 -- iter: 08/29
[A[ATraining Step: 1486 | total loss: [1m[32m0.63151[0m[0m | time: 0.005s
[2K
| Adam | epoch: 372 | loss: 0.63151 - acc: 0.7713 -- iter: 16/29
[A[ATraining Step: 1487 | total loss: [1m[32m0.61289[0m[0m | time: 0.007s
[2K
| Adam | epoch: 372 | loss: 0.61289 - acc: 0.7817 -- iter: 24/29
[A[ATraining Step: 1488 | total loss: [1m[32m0.59789[0m[0m | time: 0.010s
[2K
| Adam | epoch: 372 | loss: 0.59789 - acc: 0.7785 -- iter: 29/29
--
Training Step: 1489 | total loss: [1m[32m0.58420[0m[0m | time: 0.002s
[2K
| Adam | epoch: 373 | loss: 0.58420 - acc: 0.7882 -- iter: 08/29
[A[ATraining Step: 1490 | total loss: [1m[32m0.58084[0m[0m | time: 0.026s
[2K
| Adam | epoch: 373 | loss: 0.58084 - acc: 0.7494 -- iter: 16/29
[A[ATraining Step: 1491 | total loss: [1m[32m0.57769[0m[0m | time: 0.029s
[2K
| Adam | epoch: 373 | loss: 0.57769 - acc: 0.7144 -- iter: 24/29
[A[ATraining Step: 1492 | total loss: [1m[32m0.56089[0m[0m | time: 0.032s
[2K
| Adam | epoch: 373 | loss: 0.56089 - acc: 0.7430 -- iter: 29/29
--
Training Step: 1493 | total loss: [1m[32m0.54759[0m[0m | time: 0.003s
[2K
| Adam | epoch: 374 | loss: 0.54759 - acc: 0.7562 -- iter: 08/29
[A[ATraining Step: 1494 | total loss: [1m[32m0.54220[0m[0m | time: 0.005s
[2K
| Adam | epoch: 374 | loss: 0.54220 - acc: 0.7556 -- iter: 16/29
[A[ATraining Step: 1495 | total loss: [1m[32m0.54677[0m[0m | time: 0.007s
[2K
| Adam | epoch: 374 | loss: 0.54677 - acc: 0.7600 -- iter: 24/29
[A[ATraining Step: 1496 | total loss: [1m[32m0.55078[0m[0m | time: 0.010s
[2K
| Adam | epoch: 374 | loss: 0.55078 - acc: 0.7640 -- iter: 29/29
--
Training Step: 1497 | total loss: [1m[32m0.52627[0m[0m | time: 0.002s
[2K
| Adam | epoch: 375 | loss: 0.52627 - acc: 0.7751 -- iter: 08/29
[A[ATraining Step: 1498 | total loss: [1m[32m0.52052[0m[0m | time: 0.004s
[2K
| Adam | epoch: 375 | loss: 0.52052 - acc: 0.7851 -- iter: 16/29
[A[ATraining Step: 1499 | total loss: [1m[32m0.51621[0m[0m | time: 0.007s
[2K
| Adam | epoch: 375 | loss: 0.51621 - acc: 0.8066 -- iter: 24/29
[A[ATraining Step: 1500 | total loss: [1m[32m0.48904[0m[0m | time: 0.009s
[2K
| Adam | epoch: 375 | loss: 0.48904 - acc: 0.8259 -- iter: 29/29
--
Training Step: 1501 | total loss: [1m[32m0.46430[0m[0m | time: 0.002s
[2K
| Adam | epoch: 376 | loss: 0.46430 - acc: 0.8433 -- iter: 08/29
[A[ATraining Step: 1502 | total loss: [1m[32m0.46155[0m[0m | time: 0.005s
[2K
| Adam | epoch: 376 | loss: 0.46155 - acc: 0.8465 -- iter: 16/29
[A[ATraining Step: 1503 | total loss: [1m[32m0.47120[0m[0m | time: 0.008s
[2K
| Adam | epoch: 376 | loss: 0.47120 - acc: 0.8119 -- iter: 24/29
[A[ATraining Step: 1504 | total loss: [1m[32m0.46609[0m[0m | time: 0.010s
[2K
| Adam | epoch: 376 | loss: 0.46609 - acc: 0.8057 -- iter: 29/29
--
Training Step: 1505 | total loss: [1m[32m0.45635[0m[0m | time: 0.003s
[2K
| Adam | epoch: 377 | loss: 0.45635 - acc: 0.8251 -- iter: 08/29
[A[ATraining Step: 1506 | total loss: [1m[32m0.44763[0m[0m | time: 0.006s
[2K
| Adam | epoch: 377 | loss: 0.44763 - acc: 0.8426 -- iter: 16/29
[A[ATraining Step: 1507 | total loss: [1m[32m0.44797[0m[0m | time: 0.008s
[2K
| Adam | epoch: 377 | loss: 0.44797 - acc: 0.8458 -- iter: 24/29
[A[ATraining Step: 1508 | total loss: [1m[32m1.67880[0m[0m | time: 0.010s
[2K
| Adam | epoch: 377 | loss: 1.67880 - acc: 0.7737 -- iter: 29/29
--
Training Step: 1509 | total loss: [1m[32m1.57022[0m[0m | time: 0.003s
[2K
| Adam | epoch: 378 | loss: 1.57022 - acc: 0.7714 -- iter: 08/29
[A[ATraining Step: 1510 | total loss: [1m[32m1.43792[0m[0m | time: 0.006s
[2K
| Adam | epoch: 378 | loss: 1.43792 - acc: 0.7942 -- iter: 16/29
[A[ATraining Step: 1511 | total loss: [1m[32m1.31881[0m[0m | time: 0.009s
[2K
| Adam | epoch: 378 | loss: 1.31881 - acc: 0.8148 -- iter: 24/29
[A[ATraining Step: 1512 | total loss: [1m[32m1.23102[0m[0m | time: 0.011s
[2K
| Adam | epoch: 378 | loss: 1.23102 - acc: 0.8208 -- iter: 29/29
--
Training Step: 1513 | total loss: [1m[32m1.57806[0m[0m | time: 0.002s
[2K
| Adam | epoch: 379 | loss: 1.57806 - acc: 0.7762 -- iter: 08/29
[A[ATraining Step: 1514 | total loss: [1m[32m1.46887[0m[0m | time: 0.006s
[2K
| Adam | epoch: 379 | loss: 1.46887 - acc: 0.7861 -- iter: 16/29
[A[ATraining Step: 1515 | total loss: [1m[32m1.38393[0m[0m | time: 0.008s
[2K
| Adam | epoch: 379 | loss: 1.38393 - acc: 0.7675 -- iter: 24/29
[A[ATraining Step: 1516 | total loss: [1m[32m1.30759[0m[0m | time: 0.011s
[2K
| Adam | epoch: 379 | loss: 1.30759 - acc: 0.7508 -- iter: 29/29
--
Training Step: 1517 | total loss: [1m[32m1.22271[0m[0m | time: 0.003s
[2K
| Adam | epoch: 380 | loss: 1.22271 - acc: 0.7632 -- iter: 08/29
[A[ATraining Step: 1518 | total loss: [1m[32m1.12793[0m[0m | time: 0.006s
[2K
| Adam | epoch: 380 | loss: 1.12793 - acc: 0.7869 -- iter: 16/29
[A[ATraining Step: 1519 | total loss: [1m[32m1.06167[0m[0m | time: 0.009s
[2K
| Adam | epoch: 380 | loss: 1.06167 - acc: 0.7957 -- iter: 24/29
[A[ATraining Step: 1520 | total loss: [1m[32m1.00568[0m[0m | time: 0.012s
[2K
| Adam | epoch: 380 | loss: 1.00568 - acc: 0.7961 -- iter: 29/29
--
Training Step: 1521 | total loss: [1m[32m0.95445[0m[0m | time: 0.019s
[2K
| Adam | epoch: 381 | loss: 0.95445 - acc: 0.8165 -- iter: 08/29
[A[ATraining Step: 1522 | total loss: [1m[32m0.90443[0m[0m | time: 0.022s
[2K
| Adam | epoch: 381 | loss: 0.90443 - acc: 0.8348 -- iter: 16/29
[A[ATraining Step: 1523 | total loss: [1m[32m1.52296[0m[0m | time: 0.024s
[2K
| Adam | epoch: 381 | loss: 1.52296 - acc: 0.7889 -- iter: 24/29
[A[ATraining Step: 1524 | total loss: [1m[32m1.40520[0m[0m | time: 0.028s
[2K
| Adam | epoch: 381 | loss: 1.40520 - acc: 0.7975 -- iter: 29/29
--
Training Step: 1525 | total loss: [1m[32m1.29316[0m[0m | time: 0.003s
[2K
| Adam | epoch: 382 | loss: 1.29316 - acc: 0.8177 -- iter: 08/29
[A[ATraining Step: 1526 | total loss: [1m[32m1.19216[0m[0m | time: 0.008s
[2K
| Adam | epoch: 382 | loss: 1.19216 - acc: 0.8360 -- iter: 16/29
[A[ATraining Step: 1527 | total loss: [1m[32m1.11661[0m[0m | time: 0.010s
[2K
| Adam | epoch: 382 | loss: 1.11661 - acc: 0.8399 -- iter: 24/29
[A[ATraining Step: 1528 | total loss: [1m[32m1.07338[0m[0m | time: 0.013s
[2K
| Adam | epoch: 382 | loss: 1.07338 - acc: 0.8184 -- iter: 29/29
--
Training Step: 1529 | total loss: [1m[32m1.01805[0m[0m | time: 0.004s
[2K
| Adam | epoch: 383 | loss: 1.01805 - acc: 0.8115 -- iter: 08/29
[A[ATraining Step: 1530 | total loss: [1m[32m0.96021[0m[0m | time: 0.007s
[2K
| Adam | epoch: 383 | loss: 0.96021 - acc: 0.8104 -- iter: 16/29
[A[ATraining Step: 1531 | total loss: [1m[32m0.90805[0m[0m | time: 0.010s
[2K
| Adam | epoch: 383 | loss: 0.90805 - acc: 0.8093 -- iter: 24/29
[A[ATraining Step: 1532 | total loss: [1m[32m0.86974[0m[0m | time: 0.013s
[2K
| Adam | epoch: 383 | loss: 0.86974 - acc: 0.8159 -- iter: 29/29
--
Training Step: 1533 | total loss: [1m[32m0.81527[0m[0m | time: 0.003s
[2K
| Adam | epoch: 384 | loss: 0.81527 - acc: 0.8218 -- iter: 08/29
[A[ATraining Step: 1534 | total loss: [1m[32m0.76903[0m[0m | time: 0.007s
[2K
| Adam | epoch: 384 | loss: 0.76903 - acc: 0.8396 -- iter: 16/29
[A[ATraining Step: 1535 | total loss: [1m[32m0.75012[0m[0m | time: 0.010s
[2K
| Adam | epoch: 384 | loss: 0.75012 - acc: 0.8157 -- iter: 24/29
[A[ATraining Step: 1536 | total loss: [1m[32m0.73296[0m[0m | time: 0.014s
[2K
| Adam | epoch: 384 | loss: 0.73296 - acc: 0.7941 -- iter: 29/29
--
Training Step: 1537 | total loss: [1m[32m0.70154[0m[0m | time: 0.003s
[2K
| Adam | epoch: 385 | loss: 0.70154 - acc: 0.8022 -- iter: 08/29
[A[ATraining Step: 1538 | total loss: [1m[32m0.67981[0m[0m | time: 0.007s
[2K
| Adam | epoch: 385 | loss: 0.67981 - acc: 0.7970 -- iter: 16/29
[A[ATraining Step: 1539 | total loss: [1m[32m0.64842[0m[0m | time: 0.010s
[2K
| Adam | epoch: 385 | loss: 0.64842 - acc: 0.8173 -- iter: 24/29
[A[ATraining Step: 1540 | total loss: [1m[32m0.62866[0m[0m | time: 0.014s
[2K
| Adam | epoch: 385 | loss: 0.62866 - acc: 0.8356 -- iter: 29/29
--
Training Step: 1541 | total loss: [1m[32m0.61095[0m[0m | time: 0.003s
[2K
| Adam | epoch: 386 | loss: 0.61095 - acc: 0.8520 -- iter: 08/29
[A[ATraining Step: 1542 | total loss: [1m[32m0.59202[0m[0m | time: 0.007s
[2K
| Adam | epoch: 386 | loss: 0.59202 - acc: 0.8543 -- iter: 16/29
[A[ATraining Step: 1543 | total loss: [1m[32m0.58580[0m[0m | time: 0.009s
[2K
| Adam | epoch: 386 | loss: 0.58580 - acc: 0.8439 -- iter: 24/29
[A[ATraining Step: 1544 | total loss: [1m[32m0.57376[0m[0m | time: 0.012s
[2K
| Adam | epoch: 386 | loss: 0.57376 - acc: 0.8470 -- iter: 29/29
--
Training Step: 1545 | total loss: [1m[32m0.54708[0m[0m | time: 0.003s
[2K
| Adam | epoch: 387 | loss: 0.54708 - acc: 0.8623 -- iter: 08/29
[A[ATraining Step: 1546 | total loss: [1m[32m0.52309[0m[0m | time: 0.007s
[2K
| Adam | epoch: 387 | loss: 0.52309 - acc: 0.8761 -- iter: 16/29
[A[ATraining Step: 1547 | total loss: [1m[32m0.52967[0m[0m | time: 0.009s
[2K
| Adam | epoch: 387 | loss: 0.52967 - acc: 0.8509 -- iter: 24/29
[A[ATraining Step: 1548 | total loss: [1m[32m0.51083[0m[0m | time: 0.013s
[2K
| Adam | epoch: 387 | loss: 0.51083 - acc: 0.8659 -- iter: 29/29
--
Training Step: 1549 | total loss: [1m[32m0.50163[0m[0m | time: 0.004s
[2K
| Adam | epoch: 388 | loss: 0.50163 - acc: 0.8668 -- iter: 08/29
[A[ATraining Step: 1550 | total loss: [1m[32m0.48405[0m[0m | time: 0.006s
[2K
| Adam | epoch: 388 | loss: 0.48405 - acc: 0.8801 -- iter: 16/29
[A[ATraining Step: 1551 | total loss: [1m[32m0.46731[0m[0m | time: 0.009s
[2K
| Adam | epoch: 388 | loss: 0.46731 - acc: 0.8921 -- iter: 24/29
[A[ATraining Step: 1552 | total loss: [1m[32m0.46224[0m[0m | time: 0.013s
[2K
| Adam | epoch: 388 | loss: 0.46224 - acc: 0.9029 -- iter: 29/29
--
Training Step: 1553 | total loss: [1m[32m0.47157[0m[0m | time: 0.002s
[2K
| Adam | epoch: 389 | loss: 0.47157 - acc: 0.8876 -- iter: 08/29
[A[ATraining Step: 1554 | total loss: [1m[32m0.46063[0m[0m | time: 0.005s
[2K
| Adam | epoch: 389 | loss: 0.46063 - acc: 0.8863 -- iter: 16/29
[A[ATraining Step: 1555 | total loss: [1m[32m0.46936[0m[0m | time: 0.008s
[2K
| Adam | epoch: 389 | loss: 0.46936 - acc: 0.8577 -- iter: 24/29
[A[ATraining Step: 1556 | total loss: [1m[32m0.47701[0m[0m | time: 0.011s
[2K
| Adam | epoch: 389 | loss: 0.47701 - acc: 0.8319 -- iter: 29/29
--
Training Step: 1557 | total loss: [1m[32m0.47995[0m[0m | time: 0.004s
[2K
| Adam | epoch: 390 | loss: 0.47995 - acc: 0.8362 -- iter: 08/29
[A[ATraining Step: 1558 | total loss: [1m[32m0.46623[0m[0m | time: 0.007s
[2K
| Adam | epoch: 390 | loss: 0.46623 - acc: 0.8401 -- iter: 16/29
[A[ATraining Step: 1559 | total loss: [1m[32m0.44644[0m[0m | time: 0.011s
[2K
| Adam | epoch: 390 | loss: 0.44644 - acc: 0.8561 -- iter: 24/29
[A[ATraining Step: 1560 | total loss: [1m[32m0.44363[0m[0m | time: 0.014s
[2K
| Adam | epoch: 390 | loss: 0.44363 - acc: 0.8505 -- iter: 29/29
--
Training Step: 1561 | total loss: [1m[32m0.44057[0m[0m | time: 0.002s
[2K
| Adam | epoch: 391 | loss: 0.44057 - acc: 0.8454 -- iter: 08/29
[A[ATraining Step: 1562 | total loss: [1m[32m0.44141[0m[0m | time: 0.005s
[2K
| Adam | epoch: 391 | loss: 0.44141 - acc: 0.8484 -- iter: 16/29
[A[ATraining Step: 1563 | total loss: [1m[32m0.45587[0m[0m | time: 0.007s
[2K
| Adam | epoch: 391 | loss: 0.45587 - acc: 0.8386 -- iter: 24/29
[A[ATraining Step: 1564 | total loss: [1m[32m0.45270[0m[0m | time: 0.010s
[2K
| Adam | epoch: 391 | loss: 0.45270 - acc: 0.8297 -- iter: 29/29
--
Training Step: 1565 | total loss: [1m[32m0.44832[0m[0m | time: 0.002s
[2K
| Adam | epoch: 392 | loss: 0.44832 - acc: 0.8467 -- iter: 08/29
[A[ATraining Step: 1566 | total loss: [1m[32m0.44360[0m[0m | time: 0.005s
[2K
| Adam | epoch: 392 | loss: 0.44360 - acc: 0.8621 -- iter: 16/29
[A[ATraining Step: 1567 | total loss: [1m[32m0.44852[0m[0m | time: 0.007s
[2K
| Adam | epoch: 392 | loss: 0.44852 - acc: 0.8509 -- iter: 24/29
[A[ATraining Step: 1568 | total loss: [1m[32m0.44289[0m[0m | time: 0.009s
[2K
| Adam | epoch: 392 | loss: 0.44289 - acc: 0.8533 -- iter: 29/29
--
Training Step: 1569 | total loss: [1m[32m0.44969[0m[0m | time: 0.003s
[2K
| Adam | epoch: 393 | loss: 0.44969 - acc: 0.8429 -- iter: 08/29
[A[ATraining Step: 1570 | total loss: [1m[32m0.44361[0m[0m | time: 0.007s
[2K
| Adam | epoch: 393 | loss: 0.44361 - acc: 0.8386 -- iter: 16/29
[A[ATraining Step: 1571 | total loss: [1m[32m0.43801[0m[0m | time: 0.010s
[2K
| Adam | epoch: 393 | loss: 0.43801 - acc: 0.8348 -- iter: 24/29
[A[ATraining Step: 1572 | total loss: [1m[32m0.41882[0m[0m | time: 0.012s
[2K
| Adam | epoch: 393 | loss: 0.41882 - acc: 0.8513 -- iter: 29/29
--
Training Step: 1573 | total loss: [1m[32m0.43211[0m[0m | time: 0.002s
[2K
| Adam | epoch: 394 | loss: 0.43211 - acc: 0.8412 -- iter: 08/29
[A[ATraining Step: 1574 | total loss: [1m[32m0.42967[0m[0m | time: 0.005s
[2K
| Adam | epoch: 394 | loss: 0.42967 - acc: 0.8446 -- iter: 16/29
[A[ATraining Step: 1575 | total loss: [1m[32m0.44296[0m[0m | time: 0.008s
[2K
| Adam | epoch: 394 | loss: 0.44296 - acc: 0.8201 -- iter: 24/29
[A[ATraining Step: 1576 | total loss: [1m[32m0.45470[0m[0m | time: 0.011s
[2K
| Adam | epoch: 394 | loss: 0.45470 - acc: 0.7981 -- iter: 29/29
--
Training Step: 1577 | total loss: [1m[32m0.44400[0m[0m | time: 0.003s
[2K
| Adam | epoch: 395 | loss: 0.44400 - acc: 0.8058 -- iter: 08/29
[A[ATraining Step: 1578 | total loss: [1m[32m0.44128[0m[0m | time: 0.006s
[2K
| Adam | epoch: 395 | loss: 0.44128 - acc: 0.8252 -- iter: 16/29
[A[ATraining Step: 1579 | total loss: [1m[32m0.43334[0m[0m | time: 0.010s
[2K
| Adam | epoch: 395 | loss: 0.43334 - acc: 0.8427 -- iter: 24/29
[A[ATraining Step: 1580 | total loss: [1m[32m0.45030[0m[0m | time: 0.013s
[2K
| Adam | epoch: 395 | loss: 0.45030 - acc: 0.8184 -- iter: 29/29
--
Training Step: 1581 | total loss: [1m[32m0.46544[0m[0m | time: 0.003s
[2K
| Adam | epoch: 396 | loss: 0.46544 - acc: 0.7966 -- iter: 08/29
[A[ATraining Step: 1582 | total loss: [1m[32m0.46840[0m[0m | time: 0.007s
[2K
| Adam | epoch: 396 | loss: 0.46840 - acc: 0.7919 -- iter: 16/29
[A[ATraining Step: 1583 | total loss: [1m[32m0.44863[0m[0m | time: 0.010s
[2K
| Adam | epoch: 396 | loss: 0.44863 - acc: 0.8127 -- iter: 24/29
[A[ATraining Step: 1584 | total loss: [1m[32m0.44348[0m[0m | time: 0.013s
[2K
| Adam | epoch: 396 | loss: 0.44348 - acc: 0.8315 -- iter: 29/29
--
Training Step: 1585 | total loss: [1m[32m0.42338[0m[0m | time: 0.003s
[2K
| Adam | epoch: 397 | loss: 0.42338 - acc: 0.8483 -- iter: 08/29
[A[ATraining Step: 1586 | total loss: [1m[32m0.40533[0m[0m | time: 0.007s
[2K
| Adam | epoch: 397 | loss: 0.40533 - acc: 0.8635 -- iter: 16/29
[A[ATraining Step: 1587 | total loss: [1m[32m0.41435[0m[0m | time: 0.009s
[2K
| Adam | epoch: 397 | loss: 0.41435 - acc: 0.8646 -- iter: 24/29
[A[ATraining Step: 1588 | total loss: [1m[32m0.41794[0m[0m | time: 0.011s
[2K
| Adam | epoch: 397 | loss: 0.41794 - acc: 0.8532 -- iter: 29/29
--
Training Step: 1589 | total loss: [1m[32m0.42542[0m[0m | time: 0.003s
[2K
| Adam | epoch: 398 | loss: 0.42542 - acc: 0.8553 -- iter: 08/29
[A[ATraining Step: 1590 | total loss: [1m[32m0.41930[0m[0m | time: 0.006s
[2K
| Adam | epoch: 398 | loss: 0.41930 - acc: 0.8498 -- iter: 16/29
[A[ATraining Step: 1591 | total loss: [1m[32m0.41368[0m[0m | time: 0.009s
[2K
| Adam | epoch: 398 | loss: 0.41368 - acc: 0.8448 -- iter: 24/29
[A[ATraining Step: 1592 | total loss: [1m[32m0.40447[0m[0m | time: 0.012s
[2K
| Adam | epoch: 398 | loss: 0.40447 - acc: 0.8603 -- iter: 29/29
--
Training Step: 1593 | total loss: [1m[32m0.40802[0m[0m | time: 0.003s
[2K
| Adam | epoch: 399 | loss: 0.40802 - acc: 0.8618 -- iter: 08/29
[A[ATraining Step: 1594 | total loss: [1m[32m0.42508[0m[0m | time: 0.005s
[2K
| Adam | epoch: 399 | loss: 0.42508 - acc: 0.8756 -- iter: 16/29
[A[ATraining Step: 1595 | total loss: [1m[32m0.41760[0m[0m | time: 0.009s
[2K
| Adam | epoch: 399 | loss: 0.41760 - acc: 0.8881 -- iter: 24/29
[A[ATraining Step: 1596 | total loss: [1m[32m0.41078[0m[0m | time: 0.011s
[2K
| Adam | epoch: 399 | loss: 0.41078 - acc: 0.8993 -- iter: 29/29
--
Training Step: 1597 | total loss: [1m[32m0.39798[0m[0m | time: 0.002s
[2K
| Adam | epoch: 400 | loss: 0.39798 - acc: 0.8968 -- iter: 08/29
[A[ATraining Step: 1598 | total loss: [1m[32m0.39754[0m[0m | time: 0.005s
[2K
| Adam | epoch: 400 | loss: 0.39754 - acc: 0.8822 -- iter: 16/29
[A[ATraining Step: 1599 | total loss: [1m[32m0.39823[0m[0m | time: 0.009s
[2K
| Adam | epoch: 400 | loss: 0.39823 - acc: 0.8814 -- iter: 24/29
[A[ATraining Step: 1600 | total loss: [1m[32m0.40187[0m[0m | time: 0.011s
[2K
| Adam | epoch: 400 | loss: 0.40187 - acc: 0.8933 -- iter: 29/29
--
Training Step: 1601 | total loss: [1m[32m0.40503[0m[0m | time: 0.003s
[2K
| Adam | epoch: 401 | loss: 0.40503 - acc: 0.9040 -- iter: 08/29
[A[ATraining Step: 1602 | total loss: [1m[32m0.40138[0m[0m | time: 0.005s
[2K
| Adam | epoch: 401 | loss: 0.40138 - acc: 0.9011 -- iter: 16/29
[A[ATraining Step: 1603 | total loss: [1m[32m0.40243[0m[0m | time: 0.008s
[2K
| Adam | epoch: 401 | loss: 0.40243 - acc: 0.9110 -- iter: 24/29
[A[ATraining Step: 1604 | total loss: [1m[32m0.40621[0m[0m | time: 0.011s
[2K
| Adam | epoch: 401 | loss: 0.40621 - acc: 0.9199 -- iter: 29/29
--
Training Step: 1605 | total loss: [1m[32m0.40065[0m[0m | time: 0.003s
[2K
| Adam | epoch: 402 | loss: 0.40065 - acc: 0.9279 -- iter: 08/29
[A[ATraining Step: 1606 | total loss: [1m[32m0.39549[0m[0m | time: 0.005s
[2K
| Adam | epoch: 402 | loss: 0.39549 - acc: 0.9351 -- iter: 16/29
[A[ATraining Step: 1607 | total loss: [1m[32m0.40047[0m[0m | time: 0.008s
[2K
| Adam | epoch: 402 | loss: 0.40047 - acc: 0.9291 -- iter: 24/29
[A[ATraining Step: 1608 | total loss: [1m[32m0.39446[0m[0m | time: 0.011s
[2K
| Adam | epoch: 402 | loss: 0.39446 - acc: 0.9362 -- iter: 29/29
--
Training Step: 1609 | total loss: [1m[32m0.39603[0m[0m | time: 0.002s
[2K
| Adam | epoch: 403 | loss: 0.39603 - acc: 0.9301 -- iter: 08/29
[A[ATraining Step: 1610 | total loss: [1m[32m0.41169[0m[0m | time: 0.005s
[2K
| Adam | epoch: 403 | loss: 0.41169 - acc: 0.9371 -- iter: 16/29
[A[ATraining Step: 1611 | total loss: [1m[32m0.42567[0m[0m | time: 0.007s
[2K
| Adam | epoch: 403 | loss: 0.42567 - acc: 0.9433 -- iter: 24/29
[A[ATraining Step: 1612 | total loss: [1m[32m0.41993[0m[0m | time: 0.010s
[2K
| Adam | epoch: 403 | loss: 0.41993 - acc: 0.9490 -- iter: 29/29
--
Training Step: 1613 | total loss: [1m[32m0.40928[0m[0m | time: 0.002s
[2K
| Adam | epoch: 404 | loss: 0.40928 - acc: 0.9541 -- iter: 08/29
[A[ATraining Step: 1614 | total loss: [1m[32m0.40679[0m[0m | time: 0.005s
[2K
| Adam | epoch: 404 | loss: 0.40679 - acc: 0.9587 -- iter: 16/29
[A[ATraining Step: 1615 | total loss: [1m[32m0.40904[0m[0m | time: 0.007s
[2K
| Adam | epoch: 404 | loss: 0.40904 - acc: 0.9428 -- iter: 24/29
[A[ATraining Step: 1616 | total loss: [1m[32m0.41054[0m[0m | time: 0.009s
[2K
| Adam | epoch: 404 | loss: 0.41054 - acc: 0.9285 -- iter: 29/29
--
Training Step: 1617 | total loss: [1m[32m0.40883[0m[0m | time: 0.002s
[2K
| Adam | epoch: 405 | loss: 0.40883 - acc: 0.9357 -- iter: 08/29
[A[ATraining Step: 1618 | total loss: [1m[32m0.40611[0m[0m | time: 0.005s
[2K
| Adam | epoch: 405 | loss: 0.40611 - acc: 0.9421 -- iter: 16/29
[A[ATraining Step: 1619 | total loss: [1m[32m0.40105[0m[0m | time: 0.019s
[2K
| Adam | epoch: 405 | loss: 0.40105 - acc: 0.9354 -- iter: 24/29
[A[ATraining Step: 1620 | total loss: [1m[32m0.41037[0m[0m | time: 0.021s
[2K
| Adam | epoch: 405 | loss: 0.41037 - acc: 0.9219 -- iter: 29/29
--
Training Step: 1621 | total loss: [1m[32m0.41815[0m[0m | time: 0.002s
[2K
| Adam | epoch: 406 | loss: 0.41815 - acc: 0.9297 -- iter: 08/29
[A[ATraining Step: 1622 | total loss: [1m[32m0.40089[0m[0m | time: 0.004s
[2K
| Adam | epoch: 406 | loss: 0.40089 - acc: 0.9367 -- iter: 16/29
[A[ATraining Step: 1623 | total loss: [1m[32m0.41014[0m[0m | time: 0.006s
[2K
| Adam | epoch: 406 | loss: 0.41014 - acc: 0.9430 -- iter: 24/29
[A[ATraining Step: 1624 | total loss: [1m[32m0.40826[0m[0m | time: 0.009s
[2K
| Adam | epoch: 406 | loss: 0.40826 - acc: 0.9362 -- iter: 29/29
--
Training Step: 1625 | total loss: [1m[32m0.39175[0m[0m | time: 0.002s
[2K
| Adam | epoch: 407 | loss: 0.39175 - acc: 0.9426 -- iter: 08/29
[A[ATraining Step: 1626 | total loss: [1m[32m0.37689[0m[0m | time: 0.004s
[2K
| Adam | epoch: 407 | loss: 0.37689 - acc: 0.9484 -- iter: 16/29
[A[ATraining Step: 1627 | total loss: [1m[32m0.38120[0m[0m | time: 0.007s
[2K
| Adam | epoch: 407 | loss: 0.38120 - acc: 0.9535 -- iter: 24/29
[A[ATraining Step: 1628 | total loss: [1m[32m0.38629[0m[0m | time: 0.009s
[2K
| Adam | epoch: 407 | loss: 0.38629 - acc: 0.9457 -- iter: 29/29
--
Training Step: 1629 | total loss: [1m[32m0.39054[0m[0m | time: 0.002s
[2K
| Adam | epoch: 408 | loss: 0.39054 - acc: 0.9386 -- iter: 08/29
[A[ATraining Step: 1630 | total loss: [1m[32m0.38677[0m[0m | time: 0.005s
[2K
| Adam | epoch: 408 | loss: 0.38677 - acc: 0.9247 -- iter: 16/29
[A[ATraining Step: 1631 | total loss: [1m[32m0.38333[0m[0m | time: 0.008s
[2K
| Adam | epoch: 408 | loss: 0.38333 - acc: 0.9123 -- iter: 24/29
[A[ATraining Step: 1632 | total loss: [1m[32m0.37378[0m[0m | time: 0.010s
[2K
| Adam | epoch: 408 | loss: 0.37378 - acc: 0.9210 -- iter: 29/29
--
Training Step: 1633 | total loss: [1m[32m0.38158[0m[0m | time: 0.002s
[2K
| Adam | epoch: 409 | loss: 0.38158 - acc: 0.9289 -- iter: 08/29
[A[ATraining Step: 1634 | total loss: [1m[32m0.36574[0m[0m | time: 0.005s
[2K
| Adam | epoch: 409 | loss: 0.36574 - acc: 0.9360 -- iter: 16/29
[A[ATraining Step: 1635 | total loss: [1m[32m0.37757[0m[0m | time: 0.008s
[2K
| Adam | epoch: 409 | loss: 0.37757 - acc: 0.9224 -- iter: 24/29
[A[ATraining Step: 1636 | total loss: [1m[32m0.38825[0m[0m | time: 0.012s
[2K
| Adam | epoch: 409 | loss: 0.38825 - acc: 0.9102 -- iter: 29/29
--
Training Step: 1637 | total loss: [1m[32m0.38559[0m[0m | time: 0.003s
[2K
| Adam | epoch: 410 | loss: 0.38559 - acc: 0.9067 -- iter: 08/29
[A[ATraining Step: 1638 | total loss: [1m[32m0.39712[0m[0m | time: 0.006s
[2K
| Adam | epoch: 410 | loss: 0.39712 - acc: 0.9035 -- iter: 16/29
[A[ATraining Step: 1639 | total loss: [1m[32m0.39435[0m[0m | time: 0.009s
[2K
| Adam | epoch: 410 | loss: 0.39435 - acc: 0.9132 -- iter: 24/29
[A[ATraining Step: 1640 | total loss: [1m[32m0.40832[0m[0m | time: 0.012s
[2K
| Adam | epoch: 410 | loss: 0.40832 - acc: 0.8818 -- iter: 29/29
--
Training Step: 1641 | total loss: [1m[32m0.42074[0m[0m | time: 0.003s
[2K
| Adam | epoch: 411 | loss: 0.42074 - acc: 0.8537 -- iter: 08/29
[A[ATraining Step: 1642 | total loss: [1m[32m0.42090[0m[0m | time: 0.006s
[2K
| Adam | epoch: 411 | loss: 0.42090 - acc: 0.8558 -- iter: 16/29
[A[ATraining Step: 1643 | total loss: [1m[32m0.40307[0m[0m | time: 0.009s
[2K
| Adam | epoch: 411 | loss: 0.40307 - acc: 0.8702 -- iter: 24/29
[A[ATraining Step: 1644 | total loss: [1m[32m0.40455[0m[0m | time: 0.013s
[2K
| Adam | epoch: 411 | loss: 0.40455 - acc: 0.8832 -- iter: 29/29
--
Training Step: 1645 | total loss: [1m[32m0.39067[0m[0m | time: 0.003s
[2K
| Adam | epoch: 412 | loss: 0.39067 - acc: 0.8949 -- iter: 08/29
[A[ATraining Step: 1646 | total loss: [1m[32m0.37807[0m[0m | time: 0.006s
[2K
| Adam | epoch: 412 | loss: 0.37807 - acc: 0.9054 -- iter: 16/29
[A[ATraining Step: 1647 | total loss: [1m[32m0.37975[0m[0m | time: 0.024s
[2K
| Adam | epoch: 412 | loss: 0.37975 - acc: 0.8898 -- iter: 24/29
[A[ATraining Step: 1648 | total loss: [1m[32m0.37902[0m[0m | time: 0.031s
[2K
| Adam | epoch: 412 | loss: 0.37902 - acc: 0.9009 -- iter: 29/29
--
Training Step: 1649 | total loss: [1m[32m0.37235[0m[0m | time: 0.003s
[2K
| Adam | epoch: 413 | loss: 0.37235 - acc: 0.9108 -- iter: 08/29
[A[ATraining Step: 1650 | total loss: [1m[32m0.37357[0m[0m | time: 0.005s
[2K
| Adam | epoch: 413 | loss: 0.37357 - acc: 0.9197 -- iter: 16/29
[A[ATraining Step: 1651 | total loss: [1m[32m0.37384[0m[0m | time: 0.008s
[2K
| Adam | epoch: 413 | loss: 0.37384 - acc: 0.9277 -- iter: 24/29
[A[ATraining Step: 1652 | total loss: [1m[32m0.38430[0m[0m | time: 0.010s
[2K
| Adam | epoch: 413 | loss: 0.38430 - acc: 0.9225 -- iter: 29/29
--
Training Step: 1653 | total loss: [1m[32m0.37795[0m[0m | time: 0.003s
[2K
| Adam | epoch: 414 | loss: 0.37795 - acc: 0.9302 -- iter: 08/29
[A[ATraining Step: 1654 | total loss: [1m[32m0.37687[0m[0m | time: 0.005s
[2K
| Adam | epoch: 414 | loss: 0.37687 - acc: 0.9372 -- iter: 16/29
[A[ATraining Step: 1655 | total loss: [1m[32m0.36299[0m[0m | time: 0.007s
[2K
| Adam | epoch: 414 | loss: 0.36299 - acc: 0.9435 -- iter: 24/29
[A[ATraining Step: 1656 | total loss: [1m[32m0.35047[0m[0m | time: 0.010s
[2K
| Adam | epoch: 414 | loss: 0.35047 - acc: 0.9491 -- iter: 29/29
--
Training Step: 1657 | total loss: [1m[32m0.35018[0m[0m | time: 0.003s
[2K
| Adam | epoch: 415 | loss: 0.35018 - acc: 0.9542 -- iter: 08/29
[A[ATraining Step: 1658 | total loss: [1m[32m0.36334[0m[0m | time: 0.005s
[2K
| Adam | epoch: 415 | loss: 0.36334 - acc: 0.9463 -- iter: 16/29
[A[ATraining Step: 1659 | total loss: [1m[32m0.36556[0m[0m | time: 0.008s
[2K
| Adam | epoch: 415 | loss: 0.36556 - acc: 0.9392 -- iter: 24/29
[A[ATraining Step: 1660 | total loss: [1m[32m0.36682[0m[0m | time: 0.010s
[2K
| Adam | epoch: 415 | loss: 0.36682 - acc: 0.9252 -- iter: 29/29
--
Training Step: 1661 | total loss: [1m[32m0.36775[0m[0m | time: 0.002s
[2K
| Adam | epoch: 416 | loss: 0.36775 - acc: 0.9127 -- iter: 08/29
[A[ATraining Step: 1662 | total loss: [1m[32m0.35988[0m[0m | time: 0.005s
[2K
| Adam | epoch: 416 | loss: 0.35988 - acc: 0.9089 -- iter: 16/29
[A[ATraining Step: 1663 | total loss: [1m[32m0.36573[0m[0m | time: 0.007s
[2K
| Adam | epoch: 416 | loss: 0.36573 - acc: 0.9181 -- iter: 24/29
[A[ATraining Step: 1664 | total loss: [1m[32m0.36262[0m[0m | time: 0.010s
[2K
| Adam | epoch: 416 | loss: 0.36262 - acc: 0.9262 -- iter: 29/29
--
Training Step: 1665 | total loss: [1m[32m0.35253[0m[0m | time: 0.002s
[2K
| Adam | epoch: 417 | loss: 0.35253 - acc: 0.9336 -- iter: 08/29
[A[ATraining Step: 1666 | total loss: [1m[32m0.34291[0m[0m | time: 0.005s
[2K
| Adam | epoch: 417 | loss: 0.34291 - acc: 0.9403 -- iter: 16/29
[A[ATraining Step: 1667 | total loss: [1m[32m0.34853[0m[0m | time: 0.007s
[2K
| Adam | epoch: 417 | loss: 0.34853 - acc: 0.9462 -- iter: 24/29
[A[ATraining Step: 1668 | total loss: [1m[32m0.35589[0m[0m | time: 0.010s
[2K
| Adam | epoch: 417 | loss: 0.35589 - acc: 0.9391 -- iter: 29/29
--
Training Step: 1669 | total loss: [1m[32m0.36693[0m[0m | time: 0.003s
[2K
| Adam | epoch: 418 | loss: 0.36693 - acc: 0.9327 -- iter: 08/29
[A[ATraining Step: 1670 | total loss: [1m[32m0.35604[0m[0m | time: 0.005s
[2K
| Adam | epoch: 418 | loss: 0.35604 - acc: 0.9394 -- iter: 16/29
[A[ATraining Step: 1671 | total loss: [1m[32m0.34616[0m[0m | time: 0.007s
[2K
| Adam | epoch: 418 | loss: 0.34616 - acc: 0.9455 -- iter: 24/29
[A[ATraining Step: 1672 | total loss: [1m[32m0.34374[0m[0m | time: 0.022s
[2K
| Adam | epoch: 418 | loss: 0.34374 - acc: 0.9509 -- iter: 29/29
--
Training Step: 1673 | total loss: [1m[32m0.34372[0m[0m | time: 0.003s
[2K
| Adam | epoch: 419 | loss: 0.34372 - acc: 0.9433 -- iter: 08/29
[A[ATraining Step: 1674 | total loss: [1m[32m0.34576[0m[0m | time: 0.005s
[2K
| Adam | epoch: 419 | loss: 0.34576 - acc: 0.9365 -- iter: 16/29
[A[ATraining Step: 1675 | total loss: [1m[32m0.36288[0m[0m | time: 0.007s
[2K
| Adam | epoch: 419 | loss: 0.36288 - acc: 0.9229 -- iter: 24/29
[A[ATraining Step: 1676 | total loss: [1m[32m0.37839[0m[0m | time: 0.010s
[2K
| Adam | epoch: 419 | loss: 0.37839 - acc: 0.9106 -- iter: 29/29
--
Training Step: 1677 | total loss: [1m[32m0.37386[0m[0m | time: 0.003s
[2K
| Adam | epoch: 420 | loss: 0.37386 - acc: 0.9195 -- iter: 08/29
[A[ATraining Step: 1678 | total loss: [1m[32m0.36374[0m[0m | time: 0.005s
[2K
| Adam | epoch: 420 | loss: 0.36374 - acc: 0.9276 -- iter: 16/29
[A[ATraining Step: 1679 | total loss: [1m[32m0.35641[0m[0m | time: 0.008s
[2K
| Adam | epoch: 420 | loss: 0.35641 - acc: 0.9348 -- iter: 24/29
[A[ATraining Step: 1680 | total loss: [1m[32m0.36511[0m[0m | time: 0.010s
[2K
| Adam | epoch: 420 | loss: 0.36511 - acc: 0.9413 -- iter: 29/29
--
Training Step: 1681 | total loss: [1m[32m0.37280[0m[0m | time: 0.002s
[2K
| Adam | epoch: 421 | loss: 0.37280 - acc: 0.9472 -- iter: 08/29
[A[ATraining Step: 1682 | total loss: [1m[32m0.35864[0m[0m | time: 0.005s
[2K
| Adam | epoch: 421 | loss: 0.35864 - acc: 0.9400 -- iter: 16/29
[A[ATraining Step: 1683 | total loss: [1m[32m0.36997[0m[0m | time: 0.008s
[2K
| Adam | epoch: 421 | loss: 0.36997 - acc: 0.9335 -- iter: 24/29
[A[ATraining Step: 1684 | total loss: [1m[32m0.37621[0m[0m | time: 0.010s
[2K
| Adam | epoch: 421 | loss: 0.37621 - acc: 0.9401 -- iter: 29/29
--
Training Step: 1685 | total loss: [1m[32m0.37147[0m[0m | time: 0.002s
[2K
| Adam | epoch: 422 | loss: 0.37147 - acc: 0.9461 -- iter: 08/29
[A[ATraining Step: 1686 | total loss: [1m[32m0.36729[0m[0m | time: 0.005s
[2K
| Adam | epoch: 422 | loss: 0.36729 - acc: 0.9515 -- iter: 16/29
[A[ATraining Step: 1687 | total loss: [1m[32m0.37852[0m[0m | time: 0.007s
[2K
| Adam | epoch: 422 | loss: 0.37852 - acc: 0.9439 -- iter: 24/29
[A[ATraining Step: 1688 | total loss: [1m[32m0.35596[0m[0m | time: 0.010s
[2K
| Adam | epoch: 422 | loss: 0.35596 - acc: 0.9495 -- iter: 29/29
--
Training Step: 1689 | total loss: [1m[32m0.36043[0m[0m | time: 0.002s
[2K
| Adam | epoch: 423 | loss: 0.36043 - acc: 0.9545 -- iter: 08/29
[A[ATraining Step: 1690 | total loss: [1m[32m0.35664[0m[0m | time: 0.005s
[2K
| Adam | epoch: 423 | loss: 0.35664 - acc: 0.9591 -- iter: 16/29
[A[ATraining Step: 1691 | total loss: [1m[32m0.35323[0m[0m | time: 0.007s
[2K
| Adam | epoch: 423 | loss: 0.35323 - acc: 0.9632 -- iter: 24/29
[A[ATraining Step: 1692 | total loss: [1m[32m0.34949[0m[0m | time: 0.010s
[2K
| Adam | epoch: 423 | loss: 0.34949 - acc: 0.9668 -- iter: 29/29
--
Training Step: 1693 | total loss: [1m[32m0.34771[0m[0m | time: 0.002s
[2K
| Adam | epoch: 424 | loss: 0.34771 - acc: 0.9577 -- iter: 08/29
[A[ATraining Step: 1694 | total loss: [1m[32m0.35361[0m[0m | time: 0.005s
[2K
| Adam | epoch: 424 | loss: 0.35361 - acc: 0.9494 -- iter: 16/29
[A[ATraining Step: 1695 | total loss: [1m[32m0.35349[0m[0m | time: 0.008s
[2K
| Adam | epoch: 424 | loss: 0.35349 - acc: 0.9545 -- iter: 24/29
[A[ATraining Step: 1696 | total loss: [1m[32m0.35317[0m[0m | time: 0.010s
[2K
| Adam | epoch: 424 | loss: 0.35317 - acc: 0.9590 -- iter: 29/29
--
Training Step: 1697 | total loss: [1m[32m0.34324[0m[0m | time: 0.002s
[2K
| Adam | epoch: 425 | loss: 0.34324 - acc: 0.9631 -- iter: 08/29
[A[ATraining Step: 1698 | total loss: [1m[32m0.34541[0m[0m | time: 0.005s
[2K
| Adam | epoch: 425 | loss: 0.34541 - acc: 0.9668 -- iter: 16/29
[A[ATraining Step: 1699 | total loss: [1m[32m0.34365[0m[0m | time: 0.007s
[2K
| Adam | epoch: 425 | loss: 0.34365 - acc: 0.9576 -- iter: 24/29
[A[ATraining Step: 1700 | total loss: [1m[32m0.34965[0m[0m | time: 0.011s
[2K
| Adam | epoch: 425 | loss: 0.34965 - acc: 0.9619 -- iter: 29/29
--
Training Step: 1701 | total loss: [1m[32m0.35466[0m[0m | time: 0.003s
[2K
| Adam | epoch: 426 | loss: 0.35466 - acc: 0.9657 -- iter: 08/29
[A[ATraining Step: 1702 | total loss: [1m[32m0.35775[0m[0m | time: 0.006s
[2K
| Adam | epoch: 426 | loss: 0.35775 - acc: 0.9566 -- iter: 16/29
[A[ATraining Step: 1703 | total loss: [1m[32m0.34926[0m[0m | time: 0.008s
[2K
| Adam | epoch: 426 | loss: 0.34926 - acc: 0.9609 -- iter: 24/29
[A[ATraining Step: 1704 | total loss: [1m[32m0.34054[0m[0m | time: 0.011s
[2K
| Adam | epoch: 426 | loss: 0.34054 - acc: 0.9648 -- iter: 29/29
--
Training Step: 1705 | total loss: [1m[32m0.35120[0m[0m | time: 0.002s
[2K
| Adam | epoch: 427 | loss: 0.35120 - acc: 0.9484 -- iter: 08/29
[A[ATraining Step: 1706 | total loss: [1m[32m0.36064[0m[0m | time: 0.005s
[2K
| Adam | epoch: 427 | loss: 0.36064 - acc: 0.9335 -- iter: 16/29
[A[ATraining Step: 1707 | total loss: [1m[32m0.36776[0m[0m | time: 0.007s
[2K
| Adam | epoch: 427 | loss: 0.36776 - acc: 0.9277 -- iter: 24/29
[A[ATraining Step: 1708 | total loss: [1m[32m0.35487[0m[0m | time: 0.010s
[2K
| Adam | epoch: 427 | loss: 0.35487 - acc: 0.9349 -- iter: 29/29
--
Training Step: 1709 | total loss: [1m[32m0.35020[0m[0m | time: 0.003s
[2K
| Adam | epoch: 428 | loss: 0.35020 - acc: 0.9414 -- iter: 08/29
[A[ATraining Step: 1710 | total loss: [1m[32m0.35379[0m[0m | time: 0.005s
[2K
| Adam | epoch: 428 | loss: 0.35379 - acc: 0.9273 -- iter: 16/29
[A[ATraining Step: 1711 | total loss: [1m[32m0.35685[0m[0m | time: 0.008s
[2K
| Adam | epoch: 428 | loss: 0.35685 - acc: 0.9145 -- iter: 24/29
[A[ATraining Step: 1712 | total loss: [1m[32m0.35649[0m[0m | time: 0.011s
[2K
| Adam | epoch: 428 | loss: 0.35649 - acc: 0.9231 -- iter: 29/29
--
Training Step: 1713 | total loss: [1m[32m0.35054[0m[0m | time: 0.003s
[2K
| Adam | epoch: 429 | loss: 0.35054 - acc: 0.9308 -- iter: 08/29
[A[ATraining Step: 1714 | total loss: [1m[32m0.34357[0m[0m | time: 0.006s
[2K
| Adam | epoch: 429 | loss: 0.34357 - acc: 0.9377 -- iter: 16/29
[A[ATraining Step: 1715 | total loss: [1m[32m0.35073[0m[0m | time: 0.009s
[2K
| Adam | epoch: 429 | loss: 0.35073 - acc: 0.9439 -- iter: 24/29
[A[ATraining Step: 1716 | total loss: [1m[32m0.35685[0m[0m | time: 0.011s
[2K
| Adam | epoch: 429 | loss: 0.35685 - acc: 0.9495 -- iter: 29/29
--
Training Step: 1717 | total loss: [1m[32m0.35604[0m[0m | time: 0.003s
[2K
| Adam | epoch: 430 | loss: 0.35604 - acc: 0.9546 -- iter: 08/29
[A[ATraining Step: 1718 | total loss: [1m[32m0.35103[0m[0m | time: 0.005s
[2K
| Adam | epoch: 430 | loss: 0.35103 - acc: 0.9591 -- iter: 16/29
[A[ATraining Step: 1719 | total loss: [1m[32m0.33629[0m[0m | time: 0.008s
[2K
| Adam | epoch: 430 | loss: 0.33629 - acc: 0.9632 -- iter: 24/29
[A[ATraining Step: 1720 | total loss: [1m[32m0.34615[0m[0m | time: 0.011s
[2K
| Adam | epoch: 430 | loss: 0.34615 - acc: 0.9669 -- iter: 29/29
--
Training Step: 1721 | total loss: [1m[32m0.35469[0m[0m | time: 0.003s
[2K
| Adam | epoch: 431 | loss: 0.35469 - acc: 0.9702 -- iter: 08/29
[A[ATraining Step: 1722 | total loss: [1m[32m0.36069[0m[0m | time: 0.006s
[2K
| Adam | epoch: 431 | loss: 0.36069 - acc: 0.9732 -- iter: 16/29
[A[ATraining Step: 1723 | total loss: [1m[32m0.35307[0m[0m | time: 0.008s
[2K
| Adam | epoch: 431 | loss: 0.35307 - acc: 0.9759 -- iter: 24/29
[A[ATraining Step: 1724 | total loss: [1m[32m0.35213[0m[0m | time: 0.011s
[2K
| Adam | epoch: 431 | loss: 0.35213 - acc: 0.9783 -- iter: 29/29
--
Training Step: 1725 | total loss: [1m[32m0.33794[0m[0m | time: 0.003s
[2K
| Adam | epoch: 432 | loss: 0.33794 - acc: 0.9805 -- iter: 08/29
[A[ATraining Step: 1726 | total loss: [1m[32m0.32510[0m[0m | time: 0.005s
[2K
| Adam | epoch: 432 | loss: 0.32510 - acc: 0.9824 -- iter: 16/29
[A[ATraining Step: 1727 | total loss: [1m[32m0.32241[0m[0m | time: 0.008s
[2K
| Adam | epoch: 432 | loss: 0.32241 - acc: 0.9842 -- iter: 24/29
[A[ATraining Step: 1728 | total loss: [1m[32m0.32990[0m[0m | time: 0.011s
[2K
| Adam | epoch: 432 | loss: 0.32990 - acc: 0.9857 -- iter: 29/29
--
Training Step: 1729 | total loss: [1m[32m0.33075[0m[0m | time: 0.003s
[2K
| Adam | epoch: 433 | loss: 0.33075 - acc: 0.9872 -- iter: 08/29
[A[ATraining Step: 1730 | total loss: [1m[32m0.31867[0m[0m | time: 0.005s
[2K
| Adam | epoch: 433 | loss: 0.31867 - acc: 0.9885 -- iter: 16/29
[A[ATraining Step: 1731 | total loss: [1m[32m0.30740[0m[0m | time: 0.008s
[2K
| Adam | epoch: 433 | loss: 0.30740 - acc: 0.9896 -- iter: 24/29
[A[ATraining Step: 1732 | total loss: [1m[32m0.31307[0m[0m | time: 0.011s
[2K
| Adam | epoch: 433 | loss: 0.31307 - acc: 0.9906 -- iter: 29/29
--
Training Step: 1733 | total loss: [1m[32m0.31403[0m[0m | time: 0.003s
[2K
| Adam | epoch: 434 | loss: 0.31403 - acc: 0.9916 -- iter: 08/29
[A[ATraining Step: 1734 | total loss: [1m[32m0.31663[0m[0m | time: 0.005s
[2K
| Adam | epoch: 434 | loss: 0.31663 - acc: 0.9924 -- iter: 16/29
[A[ATraining Step: 1735 | total loss: [1m[32m0.30427[0m[0m | time: 0.008s
[2K
| Adam | epoch: 434 | loss: 0.30427 - acc: 0.9932 -- iter: 24/29
[A[ATraining Step: 1736 | total loss: [1m[32m0.29303[0m[0m | time: 0.011s
[2K
| Adam | epoch: 434 | loss: 0.29303 - acc: 0.9939 -- iter: 29/29
--
Training Step: 1737 | total loss: [1m[32m0.30076[0m[0m | time: 0.003s
[2K
| Adam | epoch: 435 | loss: 0.30076 - acc: 0.9945 -- iter: 08/29
[A[ATraining Step: 1738 | total loss: [1m[32m0.30166[0m[0m | time: 0.005s
[2K
| Adam | epoch: 435 | loss: 0.30166 - acc: 0.9950 -- iter: 16/29
[A[ATraining Step: 1739 | total loss: [1m[32m0.30334[0m[0m | time: 0.008s
[2K
| Adam | epoch: 435 | loss: 0.30334 - acc: 0.9955 -- iter: 24/29
[A[ATraining Step: 1740 | total loss: [1m[32m0.30528[0m[0m | time: 0.011s
[2K
| Adam | epoch: 435 | loss: 0.30528 - acc: 0.9960 -- iter: 29/29
--
Training Step: 1741 | total loss: [1m[32m0.30687[0m[0m | time: 0.003s
[2K
| Adam | epoch: 436 | loss: 0.30687 - acc: 0.9964 -- iter: 08/29
[A[ATraining Step: 1742 | total loss: [1m[32m0.31053[0m[0m | time: 0.005s
[2K
| Adam | epoch: 436 | loss: 0.31053 - acc: 0.9967 -- iter: 16/29
[A[ATraining Step: 1743 | total loss: [1m[32m0.30669[0m[0m | time: 0.008s
[2K
| Adam | epoch: 436 | loss: 0.30669 - acc: 0.9971 -- iter: 24/29
[A[ATraining Step: 1744 | total loss: [1m[32m0.31312[0m[0m | time: 0.011s
[2K
| Adam | epoch: 436 | loss: 0.31312 - acc: 0.9974 -- iter: 29/29
--
Training Step: 1745 | total loss: [1m[32m0.31447[0m[0m | time: 0.003s
[2K
| Adam | epoch: 437 | loss: 0.31447 - acc: 0.9976 -- iter: 08/29
[A[ATraining Step: 1746 | total loss: [1m[32m0.31554[0m[0m | time: 0.006s
[2K
| Adam | epoch: 437 | loss: 0.31554 - acc: 0.9979 -- iter: 16/29
[A[ATraining Step: 1747 | total loss: [1m[32m0.31793[0m[0m | time: 0.008s
[2K
| Adam | epoch: 437 | loss: 0.31793 - acc: 0.9981 -- iter: 24/29
[A[ATraining Step: 1748 | total loss: [1m[32m0.30758[0m[0m | time: 0.011s
[2K
| Adam | epoch: 437 | loss: 0.30758 - acc: 0.9983 -- iter: 29/29
--
Training Step: 1749 | total loss: [1m[32m0.30464[0m[0m | time: 0.003s
[2K
| Adam | epoch: 438 | loss: 0.30464 - acc: 0.9984 -- iter: 08/29
[A[ATraining Step: 1750 | total loss: [1m[32m0.30369[0m[0m | time: 0.005s
[2K
| Adam | epoch: 438 | loss: 0.30369 - acc: 0.9986 -- iter: 16/29
[A[ATraining Step: 1751 | total loss: [1m[32m0.30276[0m[0m | time: 0.008s
[2K
| Adam | epoch: 438 | loss: 0.30276 - acc: 0.9987 -- iter: 24/29
[A[ATraining Step: 1752 | total loss: [1m[32m0.30841[0m[0m | time: 0.011s
[2K
| Adam | epoch: 438 | loss: 0.30841 - acc: 0.9989 -- iter: 29/29
--
Training Step: 1753 | total loss: [1m[32m0.30686[0m[0m | time: 0.003s
[2K
| Adam | epoch: 439 | loss: 0.30686 - acc: 0.9990 -- iter: 08/29
[A[ATraining Step: 1754 | total loss: [1m[32m0.30536[0m[0m | time: 0.006s
[2K
| Adam | epoch: 439 | loss: 0.30536 - acc: 0.9991 -- iter: 16/29
[A[ATraining Step: 1755 | total loss: [1m[32m0.31111[0m[0m | time: 0.008s
[2K
| Adam | epoch: 439 | loss: 0.31111 - acc: 0.9992 -- iter: 24/29
[A[ATraining Step: 1756 | total loss: [1m[32m0.31603[0m[0m | time: 0.011s
[2K
| Adam | epoch: 439 | loss: 0.31603 - acc: 0.9993 -- iter: 29/29
--
Training Step: 1757 | total loss: [1m[32m0.31586[0m[0m | time: 0.003s
[2K
| Adam | epoch: 440 | loss: 0.31586 - acc: 0.9993 -- iter: 08/29
[A[ATraining Step: 1758 | total loss: [1m[32m0.31161[0m[0m | time: 0.005s
[2K
| Adam | epoch: 440 | loss: 0.31161 - acc: 0.9994 -- iter: 16/29
[A[ATraining Step: 1759 | total loss: [1m[32m0.30093[0m[0m | time: 0.008s
[2K
| Adam | epoch: 440 | loss: 0.30093 - acc: 0.9995 -- iter: 24/29
[A[ATraining Step: 1760 | total loss: [1m[32m0.30203[0m[0m | time: 0.011s
[2K
| Adam | epoch: 440 | loss: 0.30203 - acc: 0.9995 -- iter: 29/29
--
Training Step: 1761 | total loss: [1m[32m0.30277[0m[0m | time: 0.002s
[2K
| Adam | epoch: 441 | loss: 0.30277 - acc: 0.9996 -- iter: 08/29
[A[ATraining Step: 1762 | total loss: [1m[32m0.30476[0m[0m | time: 0.005s
[2K
| Adam | epoch: 441 | loss: 0.30476 - acc: 0.9996 -- iter: 16/29
[A[ATraining Step: 1763 | total loss: [1m[32m0.31091[0m[0m | time: 0.007s
[2K
| Adam | epoch: 441 | loss: 0.31091 - acc: 0.9996 -- iter: 24/29
[A[ATraining Step: 1764 | total loss: [1m[32m0.32273[0m[0m | time: 0.010s
[2K
| Adam | epoch: 441 | loss: 0.32273 - acc: 0.9997 -- iter: 29/29
--
Training Step: 1765 | total loss: [1m[32m0.31176[0m[0m | time: 0.002s
[2K
| Adam | epoch: 442 | loss: 0.31176 - acc: 0.9997 -- iter: 08/29
[A[ATraining Step: 1766 | total loss: [1m[32m0.30174[0m[0m | time: 0.005s
[2K
| Adam | epoch: 442 | loss: 0.30174 - acc: 0.9997 -- iter: 16/29
[A[ATraining Step: 1767 | total loss: [1m[32m0.29637[0m[0m | time: 0.007s
[2K
| Adam | epoch: 442 | loss: 0.29637 - acc: 0.9998 -- iter: 24/29
[A[ATraining Step: 1768 | total loss: [1m[32m0.29317[0m[0m | time: 0.010s
[2K
| Adam | epoch: 442 | loss: 0.29317 - acc: 0.9998 -- iter: 29/29
--
Training Step: 1769 | total loss: [1m[32m0.29815[0m[0m | time: 0.003s
[2K
| Adam | epoch: 443 | loss: 0.29815 - acc: 0.9998 -- iter: 08/29
[A[ATraining Step: 1770 | total loss: [1m[32m0.29538[0m[0m | time: 0.005s
[2K
| Adam | epoch: 443 | loss: 0.29538 - acc: 0.9998 -- iter: 16/29
[A[ATraining Step: 1771 | total loss: [1m[32m0.29280[0m[0m | time: 0.008s
[2K
| Adam | epoch: 443 | loss: 0.29280 - acc: 0.9998 -- iter: 24/29
[A[ATraining Step: 1772 | total loss: [1m[32m0.29274[0m[0m | time: 0.010s
[2K
| Adam | epoch: 443 | loss: 0.29274 - acc: 0.9999 -- iter: 29/29
--
Training Step: 1773 | total loss: [1m[32m0.28947[0m[0m | time: 0.003s
[2K
| Adam | epoch: 444 | loss: 0.28947 - acc: 0.9999 -- iter: 08/29
[A[ATraining Step: 1774 | total loss: [1m[32m0.28826[0m[0m | time: 0.006s
[2K
| Adam | epoch: 444 | loss: 0.28826 - acc: 0.9999 -- iter: 16/29
[A[ATraining Step: 1775 | total loss: [1m[32m0.28098[0m[0m | time: 0.008s
[2K
| Adam | epoch: 444 | loss: 0.28098 - acc: 0.9999 -- iter: 24/29
[A[ATraining Step: 1776 | total loss: [1m[32m0.27436[0m[0m | time: 0.027s
[2K
| Adam | epoch: 444 | loss: 0.27436 - acc: 0.9999 -- iter: 29/29
--
Training Step: 1777 | total loss: [1m[32m0.28389[0m[0m | time: 0.003s
[2K
| Adam | epoch: 445 | loss: 0.28389 - acc: 0.9999 -- iter: 08/29
[A[ATraining Step: 1778 | total loss: [1m[32m0.28217[0m[0m | time: 0.005s
[2K
| Adam | epoch: 445 | loss: 0.28217 - acc: 0.9999 -- iter: 16/29
[A[ATraining Step: 1779 | total loss: [1m[32m0.27575[0m[0m | time: 0.008s
[2K
| Adam | epoch: 445 | loss: 0.27575 - acc: 0.9999 -- iter: 24/29
[A[ATraining Step: 1780 | total loss: [1m[32m0.28503[0m[0m | time: 0.011s
[2K
| Adam | epoch: 445 | loss: 0.28503 - acc: 0.9999 -- iter: 29/29
--
Training Step: 1781 | total loss: [1m[32m0.29307[0m[0m | time: 0.003s
[2K
| Adam | epoch: 446 | loss: 0.29307 - acc: 0.9999 -- iter: 08/29
[A[ATraining Step: 1782 | total loss: [1m[32m0.29145[0m[0m | time: 0.005s
[2K
| Adam | epoch: 446 | loss: 0.29145 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1783 | total loss: [1m[32m0.29347[0m[0m | time: 0.008s
[2K
| Adam | epoch: 446 | loss: 0.29347 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1784 | total loss: [1m[32m0.28223[0m[0m | time: 0.011s
[2K
| Adam | epoch: 446 | loss: 0.28223 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1785 | total loss: [1m[32m0.27807[0m[0m | time: 0.003s
[2K
| Adam | epoch: 447 | loss: 0.27807 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1786 | total loss: [1m[32m0.27413[0m[0m | time: 0.005s
[2K
| Adam | epoch: 447 | loss: 0.27413 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1787 | total loss: [1m[32m0.26845[0m[0m | time: 0.008s
[2K
| Adam | epoch: 447 | loss: 0.26845 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1788 | total loss: [1m[32m0.28962[0m[0m | time: 0.011s
[2K
| Adam | epoch: 447 | loss: 0.28962 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1789 | total loss: [1m[32m0.29499[0m[0m | time: 0.003s
[2K
| Adam | epoch: 448 | loss: 0.29499 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1790 | total loss: [1m[32m0.28867[0m[0m | time: 0.006s
[2K
| Adam | epoch: 448 | loss: 0.28867 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1791 | total loss: [1m[32m0.28284[0m[0m | time: 0.009s
[2K
| Adam | epoch: 448 | loss: 0.28284 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1792 | total loss: [1m[32m0.28075[0m[0m | time: 0.011s
[2K
| Adam | epoch: 448 | loss: 0.28075 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1793 | total loss: [1m[32m0.27919[0m[0m | time: 0.003s
[2K
| Adam | epoch: 449 | loss: 0.27919 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1794 | total loss: [1m[32m0.28264[0m[0m | time: 0.006s
[2K
| Adam | epoch: 449 | loss: 0.28264 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1795 | total loss: [1m[32m0.28382[0m[0m | time: 0.008s
[2K
| Adam | epoch: 449 | loss: 0.28382 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1796 | total loss: [1m[32m0.28480[0m[0m | time: 0.011s
[2K
| Adam | epoch: 449 | loss: 0.28480 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1797 | total loss: [1m[32m0.29213[0m[0m | time: 0.003s
[2K
| Adam | epoch: 450 | loss: 0.29213 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1798 | total loss: [1m[32m0.27763[0m[0m | time: 0.006s
[2K
| Adam | epoch: 450 | loss: 0.27763 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1799 | total loss: [1m[32m0.27940[0m[0m | time: 0.009s
[2K
| Adam | epoch: 450 | loss: 0.27940 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1800 | total loss: [1m[32m0.29831[0m[0m | time: 0.011s
[2K
| Adam | epoch: 450 | loss: 0.29831 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1801 | total loss: [1m[32m0.31490[0m[0m | time: 0.003s
[2K
| Adam | epoch: 451 | loss: 0.31490 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1802 | total loss: [1m[32m0.30613[0m[0m | time: 0.005s
[2K
| Adam | epoch: 451 | loss: 0.30613 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1803 | total loss: [1m[32m0.29450[0m[0m | time: 0.008s
[2K
| Adam | epoch: 451 | loss: 0.29450 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1804 | total loss: [1m[32m0.29690[0m[0m | time: 0.010s
[2K
| Adam | epoch: 451 | loss: 0.29690 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1805 | total loss: [1m[32m0.29133[0m[0m | time: 0.003s
[2K
| Adam | epoch: 452 | loss: 0.29133 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1806 | total loss: [1m[32m0.28584[0m[0m | time: 0.005s
[2K
| Adam | epoch: 452 | loss: 0.28584 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1807 | total loss: [1m[32m0.28302[0m[0m | time: 0.008s
[2K
| Adam | epoch: 452 | loss: 0.28302 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1808 | total loss: [1m[32m0.28141[0m[0m | time: 0.011s
[2K
| Adam | epoch: 452 | loss: 0.28141 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1809 | total loss: [1m[32m0.27700[0m[0m | time: 0.003s
[2K
| Adam | epoch: 453 | loss: 0.27700 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1810 | total loss: [1m[32m0.27760[0m[0m | time: 0.006s
[2K
| Adam | epoch: 453 | loss: 0.27760 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1811 | total loss: [1m[32m0.27804[0m[0m | time: 0.009s
[2K
| Adam | epoch: 453 | loss: 0.27804 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1812 | total loss: [1m[32m0.28378[0m[0m | time: 0.013s
[2K
| Adam | epoch: 453 | loss: 0.28378 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1813 | total loss: [1m[32m0.27762[0m[0m | time: 0.002s
[2K
| Adam | epoch: 454 | loss: 0.27762 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1814 | total loss: [1m[32m0.27604[0m[0m | time: 0.006s
[2K
| Adam | epoch: 454 | loss: 0.27604 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1815 | total loss: [1m[32m0.26262[0m[0m | time: 0.009s
[2K
| Adam | epoch: 454 | loss: 0.26262 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1816 | total loss: [1m[32m0.25038[0m[0m | time: 0.012s
[2K
| Adam | epoch: 454 | loss: 0.25038 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1817 | total loss: [1m[32m0.25232[0m[0m | time: 0.003s
[2K
| Adam | epoch: 455 | loss: 0.25232 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1818 | total loss: [1m[32m0.26049[0m[0m | time: 0.007s
[2K
| Adam | epoch: 455 | loss: 0.26049 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1819 | total loss: [1m[32m0.25388[0m[0m | time: 0.009s
[2K
| Adam | epoch: 455 | loss: 0.25388 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1820 | total loss: [1m[32m0.24630[0m[0m | time: 0.012s
[2K
| Adam | epoch: 455 | loss: 0.24630 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1821 | total loss: [1m[32m0.23939[0m[0m | time: 0.003s
[2K
| Adam | epoch: 456 | loss: 0.23939 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1822 | total loss: [1m[32m0.24235[0m[0m | time: 0.007s
[2K
| Adam | epoch: 456 | loss: 0.24235 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1823 | total loss: [1m[32m0.25480[0m[0m | time: 0.010s
[2K
| Adam | epoch: 456 | loss: 0.25480 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1824 | total loss: [1m[32m0.24349[0m[0m | time: 0.013s
[2K
| Adam | epoch: 456 | loss: 0.24349 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1825 | total loss: [1m[32m0.25114[0m[0m | time: 0.003s
[2K
| Adam | epoch: 457 | loss: 0.25114 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1826 | total loss: [1m[32m0.25788[0m[0m | time: 0.007s
[2K
| Adam | epoch: 457 | loss: 0.25788 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1827 | total loss: [1m[32m0.26447[0m[0m | time: 0.010s
[2K
| Adam | epoch: 457 | loss: 0.26447 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1828 | total loss: [1m[32m0.26452[0m[0m | time: 0.013s
[2K
| Adam | epoch: 457 | loss: 0.26452 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1829 | total loss: [1m[32m0.25997[0m[0m | time: 0.003s
[2K
| Adam | epoch: 458 | loss: 0.25997 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1830 | total loss: [1m[32m0.25110[0m[0m | time: 0.006s
[2K
| Adam | epoch: 458 | loss: 0.25110 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1831 | total loss: [1m[32m0.24310[0m[0m | time: 0.014s
[2K
| Adam | epoch: 458 | loss: 0.24310 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1832 | total loss: [1m[32m0.25409[0m[0m | time: 0.019s
[2K
| Adam | epoch: 458 | loss: 0.25409 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1833 | total loss: [1m[32m0.25310[0m[0m | time: 0.002s
[2K
| Adam | epoch: 459 | loss: 0.25310 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1834 | total loss: [1m[32m0.25380[0m[0m | time: 0.005s
[2K
| Adam | epoch: 459 | loss: 0.25380 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1835 | total loss: [1m[32m0.25815[0m[0m | time: 0.007s
[2K
| Adam | epoch: 459 | loss: 0.25815 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1836 | total loss: [1m[32m0.26191[0m[0m | time: 0.010s
[2K
| Adam | epoch: 459 | loss: 0.26191 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1837 | total loss: [1m[32m0.26876[0m[0m | time: 0.003s
[2K
| Adam | epoch: 460 | loss: 0.26876 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1838 | total loss: [1m[32m0.25565[0m[0m | time: 0.005s
[2K
| Adam | epoch: 460 | loss: 0.25565 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1839 | total loss: [1m[32m0.25353[0m[0m | time: 0.007s
[2K
| Adam | epoch: 460 | loss: 0.25353 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1840 | total loss: [1m[32m0.25494[0m[0m | time: 0.010s
[2K
| Adam | epoch: 460 | loss: 0.25494 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1841 | total loss: [1m[32m0.25609[0m[0m | time: 0.003s
[2K
| Adam | epoch: 461 | loss: 0.25609 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1842 | total loss: [1m[32m0.25037[0m[0m | time: 0.005s
[2K
| Adam | epoch: 461 | loss: 0.25037 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1843 | total loss: [1m[32m0.25533[0m[0m | time: 0.008s
[2K
| Adam | epoch: 461 | loss: 0.25533 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1844 | total loss: [1m[32m0.24254[0m[0m | time: 0.010s
[2K
| Adam | epoch: 461 | loss: 0.24254 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1845 | total loss: [1m[32m0.24738[0m[0m | time: 0.002s
[2K
| Adam | epoch: 462 | loss: 0.24738 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1846 | total loss: [1m[32m0.25165[0m[0m | time: 0.005s
[2K
| Adam | epoch: 462 | loss: 0.25165 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1847 | total loss: [1m[32m0.24553[0m[0m | time: 0.007s
[2K
| Adam | epoch: 462 | loss: 0.24553 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1848 | total loss: [1m[32m0.26016[0m[0m | time: 0.010s
[2K
| Adam | epoch: 462 | loss: 0.26016 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1849 | total loss: [1m[32m0.26944[0m[0m | time: 0.003s
[2K
| Adam | epoch: 463 | loss: 0.26944 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1850 | total loss: [1m[32m0.25443[0m[0m | time: 0.005s
[2K
| Adam | epoch: 463 | loss: 0.25443 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1851 | total loss: [1m[32m0.24093[0m[0m | time: 0.008s
[2K
| Adam | epoch: 463 | loss: 0.24093 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1852 | total loss: [1m[32m0.23866[0m[0m | time: 0.011s
[2K
| Adam | epoch: 463 | loss: 0.23866 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1853 | total loss: [1m[32m0.23823[0m[0m | time: 0.003s
[2K
| Adam | epoch: 464 | loss: 0.23823 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1854 | total loss: [1m[32m0.24300[0m[0m | time: 0.005s
[2K
| Adam | epoch: 464 | loss: 0.24300 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1855 | total loss: [1m[32m0.25397[0m[0m | time: 0.007s
[2K
| Adam | epoch: 464 | loss: 0.25397 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1856 | total loss: [1m[32m0.26370[0m[0m | time: 0.010s
[2K
| Adam | epoch: 464 | loss: 0.26370 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1857 | total loss: [1m[32m0.25658[0m[0m | time: 0.003s
[2K
| Adam | epoch: 465 | loss: 0.25658 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1858 | total loss: [1m[32m0.24788[0m[0m | time: 0.005s
[2K
| Adam | epoch: 465 | loss: 0.24788 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1859 | total loss: [1m[32m0.25162[0m[0m | time: 0.008s
[2K
| Adam | epoch: 465 | loss: 0.25162 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1860 | total loss: [1m[32m0.24625[0m[0m | time: 0.010s
[2K
| Adam | epoch: 465 | loss: 0.24625 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1861 | total loss: [1m[32m0.24103[0m[0m | time: 0.002s
[2K
| Adam | epoch: 466 | loss: 0.24103 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1862 | total loss: [1m[32m0.23995[0m[0m | time: 0.005s
[2K
| Adam | epoch: 466 | loss: 0.23995 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1863 | total loss: [1m[32m0.23832[0m[0m | time: 0.008s
[2K
| Adam | epoch: 466 | loss: 0.23832 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1864 | total loss: [1m[32m0.23926[0m[0m | time: 0.018s
[2K
| Adam | epoch: 466 | loss: 0.23926 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1865 | total loss: [1m[32m0.23124[0m[0m | time: 0.002s
[2K
| Adam | epoch: 467 | loss: 0.23124 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1866 | total loss: [1m[32m0.22355[0m[0m | time: 0.004s
[2K
| Adam | epoch: 467 | loss: 0.22355 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1867 | total loss: [1m[32m0.23232[0m[0m | time: 0.007s
[2K
| Adam | epoch: 467 | loss: 0.23232 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1868 | total loss: [1m[32m0.22910[0m[0m | time: 0.010s
[2K
| Adam | epoch: 467 | loss: 0.22910 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1869 | total loss: [1m[32m0.22759[0m[0m | time: 0.003s
[2K
| Adam | epoch: 468 | loss: 0.22759 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1870 | total loss: [1m[32m0.23025[0m[0m | time: 0.006s
[2K
| Adam | epoch: 468 | loss: 0.23025 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1871 | total loss: [1m[32m0.23226[0m[0m | time: 0.009s
[2K
| Adam | epoch: 468 | loss: 0.23226 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1872 | total loss: [1m[32m0.23035[0m[0m | time: 0.012s
[2K
| Adam | epoch: 468 | loss: 0.23035 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1873 | total loss: [1m[32m0.23437[0m[0m | time: 0.003s
[2K
| Adam | epoch: 469 | loss: 0.23437 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1874 | total loss: [1m[32m0.22768[0m[0m | time: 0.007s
[2K
| Adam | epoch: 469 | loss: 0.22768 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1875 | total loss: [1m[32m0.23326[0m[0m | time: 0.010s
[2K
| Adam | epoch: 469 | loss: 0.23326 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1876 | total loss: [1m[32m0.23817[0m[0m | time: 0.013s
[2K
| Adam | epoch: 469 | loss: 0.23817 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1877 | total loss: [1m[32m0.23403[0m[0m | time: 0.003s
[2K
| Adam | epoch: 470 | loss: 0.23403 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1878 | total loss: [1m[32m0.24167[0m[0m | time: 0.007s
[2K
| Adam | epoch: 470 | loss: 0.24167 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1879 | total loss: [1m[32m0.24743[0m[0m | time: 0.011s
[2K
| Adam | epoch: 470 | loss: 0.24743 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1880 | total loss: [1m[32m0.24017[0m[0m | time: 0.014s
[2K
| Adam | epoch: 470 | loss: 0.24017 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1881 | total loss: [1m[32m0.23326[0m[0m | time: 0.004s
[2K
| Adam | epoch: 471 | loss: 0.23326 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1882 | total loss: [1m[32m0.23593[0m[0m | time: 0.007s
[2K
| Adam | epoch: 471 | loss: 0.23593 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1883 | total loss: [1m[32m0.22993[0m[0m | time: 0.011s
[2K
| Adam | epoch: 471 | loss: 0.22993 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1884 | total loss: [1m[32m0.22343[0m[0m | time: 0.014s
[2K
| Adam | epoch: 471 | loss: 0.22343 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1885 | total loss: [1m[32m0.22460[0m[0m | time: 0.003s
[2K
| Adam | epoch: 472 | loss: 0.22460 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1886 | total loss: [1m[32m0.22559[0m[0m | time: 0.007s
[2K
| Adam | epoch: 472 | loss: 0.22559 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1887 | total loss: [1m[32m0.22074[0m[0m | time: 0.010s
[2K
| Adam | epoch: 472 | loss: 0.22074 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1888 | total loss: [1m[32m0.23277[0m[0m | time: 0.013s
[2K
| Adam | epoch: 472 | loss: 0.23277 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1889 | total loss: [1m[32m0.23683[0m[0m | time: 0.003s
[2K
| Adam | epoch: 473 | loss: 0.23683 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1890 | total loss: [1m[32m0.23592[0m[0m | time: 0.007s
[2K
| Adam | epoch: 473 | loss: 0.23592 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1891 | total loss: [1m[32m0.23496[0m[0m | time: 0.010s
[2K
| Adam | epoch: 473 | loss: 0.23496 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1892 | total loss: [1m[32m0.23124[0m[0m | time: 0.013s
[2K
| Adam | epoch: 473 | loss: 0.23124 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1893 | total loss: [1m[32m0.22720[0m[0m | time: 0.003s
[2K
| Adam | epoch: 474 | loss: 0.22720 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1894 | total loss: [1m[32m0.22165[0m[0m | time: 0.007s
[2K
| Adam | epoch: 474 | loss: 0.22165 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1895 | total loss: [1m[32m0.21607[0m[0m | time: 0.010s
[2K
| Adam | epoch: 474 | loss: 0.21607 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1896 | total loss: [1m[32m0.21097[0m[0m | time: 0.013s
[2K
| Adam | epoch: 474 | loss: 0.21097 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1897 | total loss: [1m[32m0.20876[0m[0m | time: 0.003s
[2K
| Adam | epoch: 475 | loss: 0.20876 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1898 | total loss: [1m[32m0.22156[0m[0m | time: 0.007s
[2K
| Adam | epoch: 475 | loss: 0.22156 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1899 | total loss: [1m[32m0.21953[0m[0m | time: 0.010s
[2K
| Adam | epoch: 475 | loss: 0.21953 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1900 | total loss: [1m[32m0.21060[0m[0m | time: 0.014s
[2K
| Adam | epoch: 475 | loss: 0.21060 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1901 | total loss: [1m[32m0.20246[0m[0m | time: 0.004s
[2K
| Adam | epoch: 476 | loss: 0.20246 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1902 | total loss: [1m[32m0.20962[0m[0m | time: 0.008s
[2K
| Adam | epoch: 476 | loss: 0.20962 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1903 | total loss: [1m[32m0.21156[0m[0m | time: 0.011s
[2K
| Adam | epoch: 476 | loss: 0.21156 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1904 | total loss: [1m[32m0.21701[0m[0m | time: 0.015s
[2K
| Adam | epoch: 476 | loss: 0.21701 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1905 | total loss: [1m[32m0.21148[0m[0m | time: 0.004s
[2K
| Adam | epoch: 477 | loss: 0.21148 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1906 | total loss: [1m[32m0.20623[0m[0m | time: 0.008s
[2K
| Adam | epoch: 477 | loss: 0.20623 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1907 | total loss: [1m[32m0.20672[0m[0m | time: 0.011s
[2K
| Adam | epoch: 477 | loss: 0.20672 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1908 | total loss: [1m[32m0.20628[0m[0m | time: 0.015s
[2K
| Adam | epoch: 477 | loss: 0.20628 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1909 | total loss: [1m[32m0.20133[0m[0m | time: 0.004s
[2K
| Adam | epoch: 478 | loss: 0.20133 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1910 | total loss: [1m[32m0.19318[0m[0m | time: 0.008s
[2K
| Adam | epoch: 478 | loss: 0.19318 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1911 | total loss: [1m[32m0.18587[0m[0m | time: 0.011s
[2K
| Adam | epoch: 478 | loss: 0.18587 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1912 | total loss: [1m[32m0.19712[0m[0m | time: 0.015s
[2K
| Adam | epoch: 478 | loss: 0.19712 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1913 | total loss: [1m[32m0.20141[0m[0m | time: 0.003s
[2K
| Adam | epoch: 479 | loss: 0.20141 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1914 | total loss: [1m[32m0.20133[0m[0m | time: 0.007s
[2K
| Adam | epoch: 479 | loss: 0.20133 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1915 | total loss: [1m[32m0.19444[0m[0m | time: 0.010s
[2K
| Adam | epoch: 479 | loss: 0.19444 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1916 | total loss: [1m[32m0.18822[0m[0m | time: 0.014s
[2K
| Adam | epoch: 479 | loss: 0.18822 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1917 | total loss: [1m[32m0.20074[0m[0m | time: 0.003s
[2K
| Adam | epoch: 480 | loss: 0.20074 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1918 | total loss: [1m[32m0.19716[0m[0m | time: 0.007s
[2K
| Adam | epoch: 480 | loss: 0.19716 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1919 | total loss: [1m[32m0.19344[0m[0m | time: 0.010s
[2K
| Adam | epoch: 480 | loss: 0.19344 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1920 | total loss: [1m[32m0.19442[0m[0m | time: 0.013s
[2K
| Adam | epoch: 480 | loss: 0.19442 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1921 | total loss: [1m[32m0.19521[0m[0m | time: 0.003s
[2K
| Adam | epoch: 481 | loss: 0.19521 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1922 | total loss: [1m[32m0.19850[0m[0m | time: 0.007s
[2K
| Adam | epoch: 481 | loss: 0.19850 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1923 | total loss: [1m[32m0.20249[0m[0m | time: 0.010s
[2K
| Adam | epoch: 481 | loss: 0.20249 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1924 | total loss: [1m[32m0.20561[0m[0m | time: 0.013s
[2K
| Adam | epoch: 481 | loss: 0.20561 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1925 | total loss: [1m[32m0.20323[0m[0m | time: 0.003s
[2K
| Adam | epoch: 482 | loss: 0.20323 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1926 | total loss: [1m[32m0.20095[0m[0m | time: 0.006s
[2K
| Adam | epoch: 482 | loss: 0.20095 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1927 | total loss: [1m[32m0.20304[0m[0m | time: 0.011s
[2K
| Adam | epoch: 482 | loss: 0.20304 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1928 | total loss: [1m[32m0.20024[0m[0m | time: 0.015s
[2K
| Adam | epoch: 482 | loss: 0.20024 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1929 | total loss: [1m[32m0.20326[0m[0m | time: 0.004s
[2K
| Adam | epoch: 483 | loss: 0.20326 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1930 | total loss: [1m[32m0.21096[0m[0m | time: 0.007s
[2K
| Adam | epoch: 483 | loss: 0.21096 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1931 | total loss: [1m[32m0.21781[0m[0m | time: 0.011s
[2K
| Adam | epoch: 483 | loss: 0.21781 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1932 | total loss: [1m[32m0.21246[0m[0m | time: 0.014s
[2K
| Adam | epoch: 483 | loss: 0.21246 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1933 | total loss: [1m[32m0.20762[0m[0m | time: 0.004s
[2K
| Adam | epoch: 484 | loss: 0.20762 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1934 | total loss: [1m[32m0.20619[0m[0m | time: 0.007s
[2K
| Adam | epoch: 484 | loss: 0.20619 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1935 | total loss: [1m[32m0.21429[0m[0m | time: 0.011s
[2K
| Adam | epoch: 484 | loss: 0.21429 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1936 | total loss: [1m[32m0.22137[0m[0m | time: 0.014s
[2K
| Adam | epoch: 484 | loss: 0.22137 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1937 | total loss: [1m[32m0.21505[0m[0m | time: 0.004s
[2K
| Adam | epoch: 485 | loss: 0.21505 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1938 | total loss: [1m[32m0.21312[0m[0m | time: 0.007s
[2K
| Adam | epoch: 485 | loss: 0.21312 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1939 | total loss: [1m[32m0.21440[0m[0m | time: 0.011s
[2K
| Adam | epoch: 485 | loss: 0.21440 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1940 | total loss: [1m[32m0.21334[0m[0m | time: 0.015s
[2K
| Adam | epoch: 485 | loss: 0.21334 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1941 | total loss: [1m[32m0.21231[0m[0m | time: 0.004s
[2K
| Adam | epoch: 486 | loss: 0.21231 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1942 | total loss: [1m[32m0.20729[0m[0m | time: 0.007s
[2K
| Adam | epoch: 486 | loss: 0.20729 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1943 | total loss: [1m[32m0.20700[0m[0m | time: 0.011s
[2K
| Adam | epoch: 486 | loss: 0.20700 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1944 | total loss: [1m[32m0.21786[0m[0m | time: 0.015s
[2K
| Adam | epoch: 486 | loss: 0.21786 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1945 | total loss: [1m[32m0.21547[0m[0m | time: 0.003s
[2K
| Adam | epoch: 487 | loss: 0.21547 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1946 | total loss: [1m[32m0.21319[0m[0m | time: 0.007s
[2K
| Adam | epoch: 487 | loss: 0.21319 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1947 | total loss: [1m[32m0.20871[0m[0m | time: 0.010s
[2K
| Adam | epoch: 487 | loss: 0.20871 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1948 | total loss: [1m[32m0.19898[0m[0m | time: 0.014s
[2K
| Adam | epoch: 487 | loss: 0.19898 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1949 | total loss: [1m[32m0.19641[0m[0m | time: 0.004s
[2K
| Adam | epoch: 488 | loss: 0.19641 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1950 | total loss: [1m[32m0.19832[0m[0m | time: 0.007s
[2K
| Adam | epoch: 488 | loss: 0.19832 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1951 | total loss: [1m[32m0.19991[0m[0m | time: 0.011s
[2K
| Adam | epoch: 488 | loss: 0.19991 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1952 | total loss: [1m[32m0.19770[0m[0m | time: 0.015s
[2K
| Adam | epoch: 488 | loss: 0.19770 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1953 | total loss: [1m[32m0.20009[0m[0m | time: 0.004s
[2K
| Adam | epoch: 489 | loss: 0.20009 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1954 | total loss: [1m[32m0.20049[0m[0m | time: 0.007s
[2K
| Adam | epoch: 489 | loss: 0.20049 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1955 | total loss: [1m[32m0.20292[0m[0m | time: 0.012s
[2K
| Adam | epoch: 489 | loss: 0.20292 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1956 | total loss: [1m[32m0.20494[0m[0m | time: 0.015s
[2K
| Adam | epoch: 489 | loss: 0.20494 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1957 | total loss: [1m[32m0.21232[0m[0m | time: 0.003s
[2K
| Adam | epoch: 490 | loss: 0.21232 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1958 | total loss: [1m[32m0.19860[0m[0m | time: 0.007s
[2K
| Adam | epoch: 490 | loss: 0.19860 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1959 | total loss: [1m[32m0.19251[0m[0m | time: 0.011s
[2K
| Adam | epoch: 490 | loss: 0.19251 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1960 | total loss: [1m[32m0.17941[0m[0m | time: 0.014s
[2K
| Adam | epoch: 490 | loss: 0.17941 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1961 | total loss: [1m[32m0.16750[0m[0m | time: 0.003s
[2K
| Adam | epoch: 491 | loss: 0.16750 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1962 | total loss: [1m[32m0.17859[0m[0m | time: 0.007s
[2K
| Adam | epoch: 491 | loss: 0.17859 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1963 | total loss: [1m[32m0.18430[0m[0m | time: 0.010s
[2K
| Adam | epoch: 491 | loss: 0.18430 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1964 | total loss: [1m[32m0.17772[0m[0m | time: 0.014s
[2K
| Adam | epoch: 491 | loss: 0.17772 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1965 | total loss: [1m[32m0.18290[0m[0m | time: 0.004s
[2K
| Adam | epoch: 492 | loss: 0.18290 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1966 | total loss: [1m[32m0.18744[0m[0m | time: 0.007s
[2K
| Adam | epoch: 492 | loss: 0.18744 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1967 | total loss: [1m[32m0.18468[0m[0m | time: 0.011s
[2K
| Adam | epoch: 492 | loss: 0.18468 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1968 | total loss: [1m[32m0.19258[0m[0m | time: 0.015s
[2K
| Adam | epoch: 492 | loss: 0.19258 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1969 | total loss: [1m[32m0.19137[0m[0m | time: 0.004s
[2K
| Adam | epoch: 493 | loss: 0.19137 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1970 | total loss: [1m[32m0.19021[0m[0m | time: 0.007s
[2K
| Adam | epoch: 493 | loss: 0.19021 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1971 | total loss: [1m[32m0.18904[0m[0m | time: 0.011s
[2K
| Adam | epoch: 493 | loss: 0.18904 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1972 | total loss: [1m[32m0.18401[0m[0m | time: 0.015s
[2K
| Adam | epoch: 493 | loss: 0.18401 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1973 | total loss: [1m[32m0.19015[0m[0m | time: 0.004s
[2K
| Adam | epoch: 494 | loss: 0.19015 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1974 | total loss: [1m[32m0.18530[0m[0m | time: 0.007s
[2K
| Adam | epoch: 494 | loss: 0.18530 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1975 | total loss: [1m[32m0.19668[0m[0m | time: 0.029s
[2K
| Adam | epoch: 494 | loss: 0.19668 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1976 | total loss: [1m[32m0.20681[0m[0m | time: 0.033s
[2K
| Adam | epoch: 494 | loss: 0.20681 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1977 | total loss: [1m[32m0.20864[0m[0m | time: 0.004s
[2K
| Adam | epoch: 495 | loss: 0.20864 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1978 | total loss: [1m[32m0.19952[0m[0m | time: 0.007s
[2K
| Adam | epoch: 495 | loss: 0.19952 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1979 | total loss: [1m[32m0.18665[0m[0m | time: 0.011s
[2K
| Adam | epoch: 495 | loss: 0.18665 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1980 | total loss: [1m[32m0.19778[0m[0m | time: 0.015s
[2K
| Adam | epoch: 495 | loss: 0.19778 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1981 | total loss: [1m[32m0.20765[0m[0m | time: 0.004s
[2K
| Adam | epoch: 496 | loss: 0.20765 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1982 | total loss: [1m[32m0.21220[0m[0m | time: 0.008s
[2K
| Adam | epoch: 496 | loss: 0.21220 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1983 | total loss: [1m[32m0.20616[0m[0m | time: 0.012s
[2K
| Adam | epoch: 496 | loss: 0.20616 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1984 | total loss: [1m[32m0.20785[0m[0m | time: 0.016s
[2K
| Adam | epoch: 496 | loss: 0.20785 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1985 | total loss: [1m[32m0.21726[0m[0m | time: 0.004s
[2K
| Adam | epoch: 497 | loss: 0.21726 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1986 | total loss: [1m[32m0.22563[0m[0m | time: 0.008s
[2K
| Adam | epoch: 497 | loss: 0.22563 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1987 | total loss: [1m[32m0.21453[0m[0m | time: 0.012s
[2K
| Adam | epoch: 497 | loss: 0.21453 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1988 | total loss: [1m[32m0.20572[0m[0m | time: 0.016s
[2K
| Adam | epoch: 497 | loss: 0.20572 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1989 | total loss: [1m[32m0.20359[0m[0m | time: 0.004s
[2K
| Adam | epoch: 498 | loss: 0.20359 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1990 | total loss: [1m[32m0.20402[0m[0m | time: 0.008s
[2K
| Adam | epoch: 498 | loss: 0.20402 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1991 | total loss: [1m[32m0.20429[0m[0m | time: 0.011s
[2K
| Adam | epoch: 498 | loss: 0.20429 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1992 | total loss: [1m[32m0.20347[0m[0m | time: 0.015s
[2K
| Adam | epoch: 498 | loss: 0.20347 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1993 | total loss: [1m[32m0.19654[0m[0m | time: 0.004s
[2K
| Adam | epoch: 499 | loss: 0.19654 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1994 | total loss: [1m[32m0.19629[0m[0m | time: 0.008s
[2K
| Adam | epoch: 499 | loss: 0.19629 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1995 | total loss: [1m[32m0.19761[0m[0m | time: 0.011s
[2K
| Adam | epoch: 499 | loss: 0.19761 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 1996 | total loss: [1m[32m0.19883[0m[0m | time: 0.015s
[2K
| Adam | epoch: 499 | loss: 0.19883 - acc: 1.0000 -- iter: 29/29
--
Training Step: 1997 | total loss: [1m[32m0.19829[0m[0m | time: 0.004s
[2K
| Adam | epoch: 500 | loss: 0.19829 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 1998 | total loss: [1m[32m0.19076[0m[0m | time: 0.008s
[2K
| Adam | epoch: 500 | loss: 0.19076 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 1999 | total loss: [1m[32m0.19930[0m[0m | time: 0.011s
[2K
| Adam | epoch: 500 | loss: 0.19930 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2000 | total loss: [1m[32m0.20247[0m[0m | time: 0.015s
[2K
| Adam | epoch: 500 | loss: 0.20247 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2001 | total loss: [1m[32m0.20522[0m[0m | time: 0.004s
[2K
| Adam | epoch: 501 | loss: 0.20522 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2002 | total loss: [1m[32m0.19848[0m[0m | time: 0.008s
[2K
| Adam | epoch: 501 | loss: 0.19848 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2003 | total loss: [1m[32m0.18622[0m[0m | time: 0.011s
[2K
| Adam | epoch: 501 | loss: 0.18622 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2004 | total loss: [1m[32m0.18620[0m[0m | time: 0.015s
[2K
| Adam | epoch: 501 | loss: 0.18620 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2005 | total loss: [1m[32m0.18050[0m[0m | time: 0.004s
[2K
| Adam | epoch: 502 | loss: 0.18050 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2006 | total loss: [1m[32m0.17525[0m[0m | time: 0.008s
[2K
| Adam | epoch: 502 | loss: 0.17525 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2007 | total loss: [1m[32m0.18310[0m[0m | time: 0.011s
[2K
| Adam | epoch: 502 | loss: 0.18310 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2008 | total loss: [1m[32m0.17570[0m[0m | time: 0.015s
[2K
| Adam | epoch: 502 | loss: 0.17570 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2009 | total loss: [1m[32m0.17534[0m[0m | time: 0.004s
[2K
| Adam | epoch: 503 | loss: 0.17534 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2010 | total loss: [1m[32m0.17262[0m[0m | time: 0.008s
[2K
| Adam | epoch: 503 | loss: 0.17262 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2011 | total loss: [1m[32m0.16995[0m[0m | time: 0.012s
[2K
| Adam | epoch: 503 | loss: 0.16995 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2012 | total loss: [1m[32m0.16553[0m[0m | time: 0.015s
[2K
| Adam | epoch: 503 | loss: 0.16553 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2013 | total loss: [1m[32m0.17220[0m[0m | time: 0.004s
[2K
| Adam | epoch: 504 | loss: 0.17220 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2014 | total loss: [1m[32m0.18469[0m[0m | time: 0.008s
[2K
| Adam | epoch: 504 | loss: 0.18469 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2015 | total loss: [1m[32m0.17977[0m[0m | time: 0.012s
[2K
| Adam | epoch: 504 | loss: 0.17977 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2016 | total loss: [1m[32m0.17531[0m[0m | time: 0.016s
[2K
| Adam | epoch: 504 | loss: 0.17531 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2017 | total loss: [1m[32m0.16654[0m[0m | time: 0.004s
[2K
| Adam | epoch: 505 | loss: 0.16654 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2018 | total loss: [1m[32m0.16388[0m[0m | time: 0.008s
[2K
| Adam | epoch: 505 | loss: 0.16388 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2019 | total loss: [1m[32m0.16751[0m[0m | time: 0.011s
[2K
| Adam | epoch: 505 | loss: 0.16751 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2020 | total loss: [1m[32m0.15800[0m[0m | time: 0.015s
[2K
| Adam | epoch: 505 | loss: 0.15800 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2021 | total loss: [1m[32m0.14939[0m[0m | time: 0.004s
[2K
| Adam | epoch: 506 | loss: 0.14939 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2022 | total loss: [1m[32m0.14825[0m[0m | time: 0.008s
[2K
| Adam | epoch: 506 | loss: 0.14825 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2023 | total loss: [1m[32m0.15550[0m[0m | time: 0.012s
[2K
| Adam | epoch: 506 | loss: 0.15550 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2024 | total loss: [1m[32m0.15881[0m[0m | time: 0.015s
[2K
| Adam | epoch: 506 | loss: 0.15881 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2025 | total loss: [1m[32m0.15527[0m[0m | time: 0.004s
[2K
| Adam | epoch: 507 | loss: 0.15527 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2026 | total loss: [1m[32m0.15198[0m[0m | time: 0.007s
[2K
| Adam | epoch: 507 | loss: 0.15198 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2027 | total loss: [1m[32m0.15264[0m[0m | time: 0.011s
[2K
| Adam | epoch: 507 | loss: 0.15264 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2028 | total loss: [1m[32m0.15512[0m[0m | time: 0.015s
[2K
| Adam | epoch: 507 | loss: 0.15512 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2029 | total loss: [1m[32m0.16661[0m[0m | time: 0.003s
[2K
| Adam | epoch: 508 | loss: 0.16661 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2030 | total loss: [1m[32m0.16859[0m[0m | time: 0.007s
[2K
| Adam | epoch: 508 | loss: 0.16859 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2031 | total loss: [1m[32m0.17030[0m[0m | time: 0.010s
[2K
| Adam | epoch: 508 | loss: 0.17030 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2032 | total loss: [1m[32m0.16280[0m[0m | time: 0.013s
[2K
| Adam | epoch: 508 | loss: 0.16280 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2033 | total loss: [1m[32m0.15785[0m[0m | time: 0.003s
[2K
| Adam | epoch: 509 | loss: 0.15785 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2034 | total loss: [1m[32m0.15038[0m[0m | time: 0.007s
[2K
| Adam | epoch: 509 | loss: 0.15038 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2035 | total loss: [1m[32m0.15309[0m[0m | time: 0.010s
[2K
| Adam | epoch: 509 | loss: 0.15309 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2036 | total loss: [1m[32m0.15538[0m[0m | time: 0.013s
[2K
| Adam | epoch: 509 | loss: 0.15538 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2037 | total loss: [1m[32m0.14969[0m[0m | time: 0.003s
[2K
| Adam | epoch: 510 | loss: 0.14969 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2038 | total loss: [1m[32m0.16461[0m[0m | time: 0.007s
[2K
| Adam | epoch: 510 | loss: 0.16461 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2039 | total loss: [1m[32m0.17157[0m[0m | time: 0.010s
[2K
| Adam | epoch: 510 | loss: 0.17157 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2040 | total loss: [1m[32m0.16279[0m[0m | time: 0.013s
[2K
| Adam | epoch: 510 | loss: 0.16279 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2041 | total loss: [1m[32m0.15482[0m[0m | time: 0.003s
[2K
| Adam | epoch: 511 | loss: 0.15482 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2042 | total loss: [1m[32m0.15520[0m[0m | time: 0.007s
[2K
| Adam | epoch: 511 | loss: 0.15520 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2043 | total loss: [1m[32m0.15332[0m[0m | time: 0.012s
[2K
| Adam | epoch: 511 | loss: 0.15332 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2044 | total loss: [1m[32m0.15942[0m[0m | time: 0.015s
[2K
| Adam | epoch: 511 | loss: 0.15942 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2045 | total loss: [1m[32m0.16795[0m[0m | time: 0.003s
[2K
| Adam | epoch: 512 | loss: 0.16795 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2046 | total loss: [1m[32m0.17556[0m[0m | time: 0.007s
[2K
| Adam | epoch: 512 | loss: 0.17556 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2047 | total loss: [1m[32m0.16916[0m[0m | time: 0.010s
[2K
| Adam | epoch: 512 | loss: 0.16916 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2048 | total loss: [1m[32m0.16225[0m[0m | time: 0.038s
[2K
| Adam | epoch: 512 | loss: 0.16225 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2049 | total loss: [1m[32m0.15451[0m[0m | time: 0.003s
[2K
| Adam | epoch: 513 | loss: 0.15451 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2050 | total loss: [1m[32m0.15066[0m[0m | time: 0.007s
[2K
| Adam | epoch: 513 | loss: 0.15066 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2051 | total loss: [1m[32m0.14714[0m[0m | time: 0.010s
[2K
| Adam | epoch: 513 | loss: 0.14714 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2052 | total loss: [1m[32m0.15073[0m[0m | time: 0.013s
[2K
| Adam | epoch: 513 | loss: 0.15073 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2053 | total loss: [1m[32m0.15897[0m[0m | time: 0.003s
[2K
| Adam | epoch: 514 | loss: 0.15897 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2054 | total loss: [1m[32m0.15996[0m[0m | time: 0.007s
[2K
| Adam | epoch: 514 | loss: 0.15996 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2055 | total loss: [1m[32m0.16072[0m[0m | time: 0.011s
[2K
| Adam | epoch: 514 | loss: 0.16072 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2056 | total loss: [1m[32m0.16131[0m[0m | time: 0.014s
[2K
| Adam | epoch: 514 | loss: 0.16131 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2057 | total loss: [1m[32m0.15378[0m[0m | time: 0.004s
[2K
| Adam | epoch: 515 | loss: 0.15378 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2058 | total loss: [1m[32m0.15950[0m[0m | time: 0.007s
[2K
| Adam | epoch: 515 | loss: 0.15950 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2059 | total loss: [1m[32m0.15193[0m[0m | time: 0.011s
[2K
| Adam | epoch: 515 | loss: 0.15193 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2060 | total loss: [1m[32m0.15001[0m[0m | time: 0.014s
[2K
| Adam | epoch: 515 | loss: 0.15001 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2061 | total loss: [1m[32m0.14814[0m[0m | time: 0.004s
[2K
| Adam | epoch: 516 | loss: 0.14814 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2062 | total loss: [1m[32m0.15578[0m[0m | time: 0.007s
[2K
| Adam | epoch: 516 | loss: 0.15578 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2063 | total loss: [1m[32m0.15763[0m[0m | time: 0.011s
[2K
| Adam | epoch: 516 | loss: 0.15763 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2064 | total loss: [1m[32m0.16868[0m[0m | time: 0.014s
[2K
| Adam | epoch: 516 | loss: 0.16868 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2065 | total loss: [1m[32m0.16303[0m[0m | time: 0.004s
[2K
| Adam | epoch: 517 | loss: 0.16303 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2066 | total loss: [1m[32m0.15788[0m[0m | time: 0.007s
[2K
| Adam | epoch: 517 | loss: 0.15788 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2067 | total loss: [1m[32m0.15505[0m[0m | time: 0.010s
[2K
| Adam | epoch: 517 | loss: 0.15505 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2068 | total loss: [1m[32m0.14854[0m[0m | time: 0.014s
[2K
| Adam | epoch: 517 | loss: 0.14854 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2069 | total loss: [1m[32m0.14701[0m[0m | time: 0.004s
[2K
| Adam | epoch: 518 | loss: 0.14701 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2070 | total loss: [1m[32m0.13835[0m[0m | time: 0.007s
[2K
| Adam | epoch: 518 | loss: 0.13835 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2071 | total loss: [1m[32m0.13048[0m[0m | time: 0.028s
[2K
| Adam | epoch: 518 | loss: 0.13048 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2072 | total loss: [1m[32m0.14150[0m[0m | time: 0.032s
[2K
| Adam | epoch: 518 | loss: 0.14150 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2073 | total loss: [1m[32m0.14135[0m[0m | time: 0.003s
[2K
| Adam | epoch: 519 | loss: 0.14135 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2074 | total loss: [1m[32m0.13721[0m[0m | time: 0.006s
[2K
| Adam | epoch: 519 | loss: 0.13721 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2075 | total loss: [1m[32m0.13765[0m[0m | time: 0.009s
[2K
| Adam | epoch: 519 | loss: 0.13765 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2076 | total loss: [1m[32m0.13794[0m[0m | time: 0.011s
[2K
| Adam | epoch: 519 | loss: 0.13794 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2077 | total loss: [1m[32m0.14398[0m[0m | time: 0.003s
[2K
| Adam | epoch: 520 | loss: 0.14398 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2078 | total loss: [1m[32m0.14567[0m[0m | time: 0.005s
[2K
| Adam | epoch: 520 | loss: 0.14567 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2079 | total loss: [1m[32m0.14555[0m[0m | time: 0.009s
[2K
| Adam | epoch: 520 | loss: 0.14555 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2080 | total loss: [1m[32m0.13456[0m[0m | time: 0.011s
[2K
| Adam | epoch: 520 | loss: 0.13456 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2081 | total loss: [1m[32m0.12464[0m[0m | time: 0.003s
[2K
| Adam | epoch: 521 | loss: 0.12464 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2082 | total loss: [1m[32m0.12477[0m[0m | time: 0.005s
[2K
| Adam | epoch: 521 | loss: 0.12477 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2083 | total loss: [1m[32m0.13708[0m[0m | time: 0.008s
[2K
| Adam | epoch: 521 | loss: 0.13708 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2084 | total loss: [1m[32m0.13080[0m[0m | time: 0.011s
[2K
| Adam | epoch: 521 | loss: 0.13080 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2085 | total loss: [1m[32m0.14857[0m[0m | time: 0.003s
[2K
| Adam | epoch: 522 | loss: 0.14857 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2086 | total loss: [1m[32m0.16443[0m[0m | time: 0.005s
[2K
| Adam | epoch: 522 | loss: 0.16443 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2087 | total loss: [1m[32m0.16023[0m[0m | time: 0.008s
[2K
| Adam | epoch: 522 | loss: 0.16023 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2088 | total loss: [1m[32m0.15908[0m[0m | time: 0.011s
[2K
| Adam | epoch: 522 | loss: 0.15908 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2089 | total loss: [1m[32m0.15910[0m[0m | time: 0.003s
[2K
| Adam | epoch: 523 | loss: 0.15910 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2090 | total loss: [1m[32m0.15842[0m[0m | time: 0.005s
[2K
| Adam | epoch: 523 | loss: 0.15842 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2091 | total loss: [1m[32m0.15768[0m[0m | time: 0.009s
[2K
| Adam | epoch: 523 | loss: 0.15768 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2092 | total loss: [1m[32m0.15830[0m[0m | time: 0.012s
[2K
| Adam | epoch: 523 | loss: 0.15830 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2093 | total loss: [1m[32m0.15426[0m[0m | time: 0.002s
[2K
| Adam | epoch: 524 | loss: 0.15426 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2094 | total loss: [1m[32m0.14984[0m[0m | time: 0.005s
[2K
| Adam | epoch: 524 | loss: 0.14984 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2095 | total loss: [1m[32m0.13933[0m[0m | time: 0.007s
[2K
| Adam | epoch: 524 | loss: 0.13933 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2096 | total loss: [1m[32m0.12980[0m[0m | time: 0.010s
[2K
| Adam | epoch: 524 | loss: 0.12980 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2097 | total loss: [1m[32m0.13782[0m[0m | time: 0.002s
[2K
| Adam | epoch: 525 | loss: 0.13782 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2098 | total loss: [1m[32m0.14212[0m[0m | time: 0.005s
[2K
| Adam | epoch: 525 | loss: 0.14212 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2099 | total loss: [1m[32m0.14885[0m[0m | time: 0.007s
[2K
| Adam | epoch: 525 | loss: 0.14885 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2100 | total loss: [1m[32m0.15214[0m[0m | time: 0.009s
[2K
| Adam | epoch: 525 | loss: 0.15214 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2101 | total loss: [1m[32m0.15500[0m[0m | time: 0.002s
[2K
| Adam | epoch: 526 | loss: 0.15500 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2102 | total loss: [1m[32m0.14575[0m[0m | time: 0.005s
[2K
| Adam | epoch: 526 | loss: 0.14575 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2103 | total loss: [1m[32m0.14492[0m[0m | time: 0.007s
[2K
| Adam | epoch: 526 | loss: 0.14492 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2104 | total loss: [1m[32m0.14291[0m[0m | time: 0.010s
[2K
| Adam | epoch: 526 | loss: 0.14291 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2105 | total loss: [1m[32m0.13819[0m[0m | time: 0.002s
[2K
| Adam | epoch: 527 | loss: 0.13819 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2106 | total loss: [1m[32m0.13389[0m[0m | time: 0.005s
[2K
| Adam | epoch: 527 | loss: 0.13389 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2107 | total loss: [1m[32m0.14302[0m[0m | time: 0.007s
[2K
| Adam | epoch: 527 | loss: 0.14302 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2108 | total loss: [1m[32m0.13938[0m[0m | time: 0.010s
[2K
| Adam | epoch: 527 | loss: 0.13938 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2109 | total loss: [1m[32m0.13891[0m[0m | time: 0.002s
[2K
| Adam | epoch: 528 | loss: 0.13891 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2110 | total loss: [1m[32m0.13126[0m[0m | time: 0.005s
[2K
| Adam | epoch: 528 | loss: 0.13126 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2111 | total loss: [1m[32m0.12428[0m[0m | time: 0.007s
[2K
| Adam | epoch: 528 | loss: 0.12428 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2112 | total loss: [1m[32m0.12239[0m[0m | time: 0.010s
[2K
| Adam | epoch: 528 | loss: 0.12239 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2113 | total loss: [1m[32m0.13377[0m[0m | time: 0.003s
[2K
| Adam | epoch: 529 | loss: 0.13377 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2114 | total loss: [1m[32m0.14610[0m[0m | time: 0.005s
[2K
| Adam | epoch: 529 | loss: 0.14610 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2115 | total loss: [1m[32m0.13806[0m[0m | time: 0.007s
[2K
| Adam | epoch: 529 | loss: 0.13806 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2116 | total loss: [1m[32m0.13074[0m[0m | time: 0.010s
[2K
| Adam | epoch: 529 | loss: 0.13074 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2117 | total loss: [1m[32m0.12729[0m[0m | time: 0.002s
[2K
| Adam | epoch: 530 | loss: 0.12729 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2118 | total loss: [1m[32m0.12635[0m[0m | time: 0.005s
[2K
| Adam | epoch: 530 | loss: 0.12635 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2119 | total loss: [1m[32m0.12920[0m[0m | time: 0.007s
[2K
| Adam | epoch: 530 | loss: 0.12920 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2120 | total loss: [1m[32m0.13991[0m[0m | time: 0.010s
[2K
| Adam | epoch: 530 | loss: 0.13991 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2121 | total loss: [1m[32m0.14940[0m[0m | time: 0.002s
[2K
| Adam | epoch: 531 | loss: 0.14940 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2122 | total loss: [1m[32m0.14778[0m[0m | time: 0.005s
[2K
| Adam | epoch: 531 | loss: 0.14778 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2123 | total loss: [1m[32m0.14017[0m[0m | time: 0.007s
[2K
| Adam | epoch: 531 | loss: 0.14017 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2124 | total loss: [1m[32m0.14014[0m[0m | time: 0.010s
[2K
| Adam | epoch: 531 | loss: 0.14014 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2125 | total loss: [1m[32m0.13076[0m[0m | time: 0.002s
[2K
| Adam | epoch: 532 | loss: 0.13076 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2126 | total loss: [1m[32m0.12224[0m[0m | time: 0.005s
[2K
| Adam | epoch: 532 | loss: 0.12224 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2127 | total loss: [1m[32m0.12268[0m[0m | time: 0.007s
[2K
| Adam | epoch: 532 | loss: 0.12268 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2128 | total loss: [1m[32m0.13137[0m[0m | time: 0.010s
[2K
| Adam | epoch: 532 | loss: 0.13137 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2129 | total loss: [1m[32m0.13772[0m[0m | time: 0.002s
[2K
| Adam | epoch: 533 | loss: 0.13772 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2130 | total loss: [1m[32m0.13229[0m[0m | time: 0.005s
[2K
| Adam | epoch: 533 | loss: 0.13229 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2131 | total loss: [1m[32m0.12737[0m[0m | time: 0.007s
[2K
| Adam | epoch: 533 | loss: 0.12737 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2132 | total loss: [1m[32m0.12989[0m[0m | time: 0.009s
[2K
| Adam | epoch: 533 | loss: 0.12989 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2133 | total loss: [1m[32m0.12656[0m[0m | time: 0.002s
[2K
| Adam | epoch: 534 | loss: 0.12656 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2134 | total loss: [1m[32m0.13043[0m[0m | time: 0.005s
[2K
| Adam | epoch: 534 | loss: 0.13043 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2135 | total loss: [1m[32m0.12123[0m[0m | time: 0.007s
[2K
| Adam | epoch: 534 | loss: 0.12123 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2136 | total loss: [1m[32m0.11293[0m[0m | time: 0.010s
[2K
| Adam | epoch: 534 | loss: 0.11293 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2137 | total loss: [1m[32m0.11397[0m[0m | time: 0.003s
[2K
| Adam | epoch: 535 | loss: 0.11397 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2138 | total loss: [1m[32m0.12061[0m[0m | time: 0.006s
[2K
| Adam | epoch: 535 | loss: 0.12061 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2139 | total loss: [1m[32m0.11771[0m[0m | time: 0.009s
[2K
| Adam | epoch: 535 | loss: 0.11771 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2140 | total loss: [1m[32m0.12687[0m[0m | time: 0.011s
[2K
| Adam | epoch: 535 | loss: 0.12687 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2141 | total loss: [1m[32m0.13496[0m[0m | time: 0.014s
[2K
| Adam | epoch: 536 | loss: 0.13496 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2142 | total loss: [1m[32m0.13281[0m[0m | time: 0.017s
[2K
| Adam | epoch: 536 | loss: 0.13281 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2143 | total loss: [1m[32m0.13479[0m[0m | time: 0.020s
[2K
| Adam | epoch: 536 | loss: 0.13479 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2144 | total loss: [1m[32m0.13263[0m[0m | time: 0.023s
[2K
| Adam | epoch: 536 | loss: 0.13263 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2145 | total loss: [1m[32m0.14448[0m[0m | time: 0.003s
[2K
| Adam | epoch: 537 | loss: 0.14448 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2146 | total loss: [1m[32m0.15503[0m[0m | time: 0.006s
[2K
| Adam | epoch: 537 | loss: 0.15503 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2147 | total loss: [1m[32m0.15011[0m[0m | time: 0.010s
[2K
| Adam | epoch: 537 | loss: 0.15011 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2148 | total loss: [1m[32m0.14598[0m[0m | time: 0.013s
[2K
| Adam | epoch: 537 | loss: 0.14598 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2149 | total loss: [1m[32m0.14391[0m[0m | time: 0.003s
[2K
| Adam | epoch: 538 | loss: 0.14391 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2150 | total loss: [1m[32m0.14518[0m[0m | time: 0.005s
[2K
| Adam | epoch: 538 | loss: 0.14518 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2151 | total loss: [1m[32m0.14616[0m[0m | time: 0.007s
[2K
| Adam | epoch: 538 | loss: 0.14616 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2152 | total loss: [1m[32m0.14120[0m[0m | time: 0.010s
[2K
| Adam | epoch: 538 | loss: 0.14120 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2153 | total loss: [1m[32m0.14349[0m[0m | time: 0.003s
[2K
| Adam | epoch: 539 | loss: 0.14349 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2154 | total loss: [1m[32m0.14377[0m[0m | time: 0.007s
[2K
| Adam | epoch: 539 | loss: 0.14377 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2155 | total loss: [1m[32m0.14258[0m[0m | time: 0.010s
[2K
| Adam | epoch: 539 | loss: 0.14258 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2156 | total loss: [1m[32m0.14144[0m[0m | time: 0.013s
[2K
| Adam | epoch: 539 | loss: 0.14144 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2157 | total loss: [1m[32m0.13775[0m[0m | time: 0.003s
[2K
| Adam | epoch: 540 | loss: 0.13775 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2158 | total loss: [1m[32m0.13807[0m[0m | time: 0.007s
[2K
| Adam | epoch: 540 | loss: 0.13807 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2159 | total loss: [1m[32m0.13666[0m[0m | time: 0.010s
[2K
| Adam | epoch: 540 | loss: 0.13666 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2160 | total loss: [1m[32m0.14268[0m[0m | time: 0.013s
[2K
| Adam | epoch: 540 | loss: 0.14268 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2161 | total loss: [1m[32m0.14793[0m[0m | time: 0.003s
[2K
| Adam | epoch: 541 | loss: 0.14793 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2162 | total loss: [1m[32m0.14509[0m[0m | time: 0.005s
[2K
| Adam | epoch: 541 | loss: 0.14509 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2163 | total loss: [1m[32m0.14109[0m[0m | time: 0.009s
[2K
| Adam | epoch: 541 | loss: 0.14109 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2164 | total loss: [1m[32m0.14591[0m[0m | time: 0.012s
[2K
| Adam | epoch: 541 | loss: 0.14591 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2165 | total loss: [1m[32m0.14729[0m[0m | time: 0.003s
[2K
| Adam | epoch: 542 | loss: 0.14729 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2166 | total loss: [1m[32m0.14839[0m[0m | time: 0.006s
[2K
| Adam | epoch: 542 | loss: 0.14839 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2167 | total loss: [1m[32m0.14107[0m[0m | time: 0.010s
[2K
| Adam | epoch: 542 | loss: 0.14107 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2168 | total loss: [1m[32m0.13747[0m[0m | time: 0.013s
[2K
| Adam | epoch: 542 | loss: 0.13747 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2169 | total loss: [1m[32m0.13271[0m[0m | time: 0.002s
[2K
| Adam | epoch: 543 | loss: 0.13271 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2170 | total loss: [1m[32m0.12949[0m[0m | time: 0.005s
[2K
| Adam | epoch: 543 | loss: 0.12949 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2171 | total loss: [1m[32m0.12648[0m[0m | time: 0.008s
[2K
| Adam | epoch: 543 | loss: 0.12648 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2172 | total loss: [1m[32m0.13169[0m[0m | time: 0.016s
[2K
| Adam | epoch: 543 | loss: 0.13169 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2173 | total loss: [1m[32m0.13188[0m[0m | time: 0.003s
[2K
| Adam | epoch: 544 | loss: 0.13188 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2174 | total loss: [1m[32m0.13183[0m[0m | time: 0.007s
[2K
| Adam | epoch: 544 | loss: 0.13183 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2175 | total loss: [1m[32m0.12683[0m[0m | time: 0.010s
[2K
| Adam | epoch: 544 | loss: 0.12683 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2176 | total loss: [1m[32m0.12232[0m[0m | time: 0.013s
[2K
| Adam | epoch: 544 | loss: 0.12232 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2177 | total loss: [1m[32m0.12929[0m[0m | time: 0.002s
[2K
| Adam | epoch: 545 | loss: 0.12929 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2178 | total loss: [1m[32m0.12485[0m[0m | time: 0.005s
[2K
| Adam | epoch: 545 | loss: 0.12485 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2179 | total loss: [1m[32m0.12140[0m[0m | time: 0.008s
[2K
| Adam | epoch: 545 | loss: 0.12140 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2180 | total loss: [1m[32m0.11703[0m[0m | time: 0.010s
[2K
| Adam | epoch: 545 | loss: 0.11703 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2181 | total loss: [1m[32m0.11300[0m[0m | time: 0.003s
[2K
| Adam | epoch: 546 | loss: 0.11300 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2182 | total loss: [1m[32m0.10948[0m[0m | time: 0.007s
[2K
| Adam | epoch: 546 | loss: 0.10948 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2183 | total loss: [1m[32m0.12246[0m[0m | time: 0.009s
[2K
| Adam | epoch: 546 | loss: 0.12246 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2184 | total loss: [1m[32m0.12205[0m[0m | time: 0.012s
[2K
| Adam | epoch: 546 | loss: 0.12205 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2185 | total loss: [1m[32m0.13075[0m[0m | time: 0.003s
[2K
| Adam | epoch: 547 | loss: 0.13075 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2186 | total loss: [1m[32m0.13852[0m[0m | time: 0.006s
[2K
| Adam | epoch: 547 | loss: 0.13852 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2187 | total loss: [1m[32m0.13641[0m[0m | time: 0.009s
[2K
| Adam | epoch: 547 | loss: 0.13641 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2188 | total loss: [1m[32m0.13138[0m[0m | time: 0.013s
[2K
| Adam | epoch: 547 | loss: 0.13138 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2189 | total loss: [1m[32m0.13605[0m[0m | time: 0.003s
[2K
| Adam | epoch: 548 | loss: 0.13605 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2190 | total loss: [1m[32m0.13415[0m[0m | time: 0.006s
[2K
| Adam | epoch: 548 | loss: 0.13415 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2191 | total loss: [1m[32m0.13237[0m[0m | time: 0.008s
[2K
| Adam | epoch: 548 | loss: 0.13237 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2192 | total loss: [1m[32m0.12597[0m[0m | time: 0.011s
[2K
| Adam | epoch: 548 | loss: 0.12597 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2193 | total loss: [1m[32m0.12627[0m[0m | time: 0.003s
[2K
| Adam | epoch: 549 | loss: 0.12627 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2194 | total loss: [1m[32m0.12857[0m[0m | time: 0.006s
[2K
| Adam | epoch: 549 | loss: 0.12857 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2195 | total loss: [1m[32m0.13096[0m[0m | time: 0.010s
[2K
| Adam | epoch: 549 | loss: 0.13096 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2196 | total loss: [1m[32m0.13288[0m[0m | time: 0.013s
[2K
| Adam | epoch: 549 | loss: 0.13288 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2197 | total loss: [1m[32m0.13085[0m[0m | time: 0.003s
[2K
| Adam | epoch: 550 | loss: 0.13085 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2198 | total loss: [1m[32m0.12653[0m[0m | time: 0.007s
[2K
| Adam | epoch: 550 | loss: 0.12653 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2199 | total loss: [1m[32m0.11940[0m[0m | time: 0.010s
[2K
| Adam | epoch: 550 | loss: 0.11940 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2200 | total loss: [1m[32m0.13000[0m[0m | time: 0.013s
[2K
| Adam | epoch: 550 | loss: 0.13000 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2201 | total loss: [1m[32m0.13948[0m[0m | time: 0.003s
[2K
| Adam | epoch: 551 | loss: 0.13948 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2202 | total loss: [1m[32m0.13985[0m[0m | time: 0.006s
[2K
| Adam | epoch: 551 | loss: 0.13985 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2203 | total loss: [1m[32m0.13581[0m[0m | time: 0.008s
[2K
| Adam | epoch: 551 | loss: 0.13581 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2204 | total loss: [1m[32m0.13343[0m[0m | time: 0.012s
[2K
| Adam | epoch: 551 | loss: 0.13343 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2205 | total loss: [1m[32m0.12511[0m[0m | time: 0.003s
[2K
| Adam | epoch: 552 | loss: 0.12511 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2206 | total loss: [1m[32m0.11758[0m[0m | time: 0.006s
[2K
| Adam | epoch: 552 | loss: 0.11758 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2207 | total loss: [1m[32m0.12530[0m[0m | time: 0.010s
[2K
| Adam | epoch: 552 | loss: 0.12530 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2208 | total loss: [1m[32m0.12339[0m[0m | time: 0.013s
[2K
| Adam | epoch: 552 | loss: 0.12339 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2209 | total loss: [1m[32m0.11921[0m[0m | time: 0.002s
[2K
| Adam | epoch: 553 | loss: 0.11921 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2210 | total loss: [1m[32m0.11962[0m[0m | time: 0.005s
[2K
| Adam | epoch: 553 | loss: 0.11962 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2211 | total loss: [1m[32m0.11995[0m[0m | time: 0.007s
[2K
| Adam | epoch: 553 | loss: 0.11995 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2212 | total loss: [1m[32m0.12475[0m[0m | time: 0.010s
[2K
| Adam | epoch: 553 | loss: 0.12475 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2213 | total loss: [1m[32m0.12285[0m[0m | time: 0.002s
[2K
| Adam | epoch: 554 | loss: 0.12285 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2214 | total loss: [1m[32m0.12253[0m[0m | time: 0.005s
[2K
| Adam | epoch: 554 | loss: 0.12253 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2215 | total loss: [1m[32m0.12225[0m[0m | time: 0.008s
[2K
| Adam | epoch: 554 | loss: 0.12225 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2216 | total loss: [1m[32m0.12195[0m[0m | time: 0.010s
[2K
| Adam | epoch: 554 | loss: 0.12195 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2217 | total loss: [1m[32m0.12359[0m[0m | time: 0.003s
[2K
| Adam | epoch: 555 | loss: 0.12359 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2218 | total loss: [1m[32m0.12088[0m[0m | time: 0.005s
[2K
| Adam | epoch: 555 | loss: 0.12088 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2219 | total loss: [1m[32m0.12106[0m[0m | time: 0.008s
[2K
| Adam | epoch: 555 | loss: 0.12106 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2220 | total loss: [1m[32m0.11493[0m[0m | time: 0.010s
[2K
| Adam | epoch: 555 | loss: 0.11493 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2221 | total loss: [1m[32m0.10935[0m[0m | time: 0.003s
[2K
| Adam | epoch: 556 | loss: 0.10935 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2222 | total loss: [1m[32m0.11766[0m[0m | time: 0.005s
[2K
| Adam | epoch: 556 | loss: 0.11766 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2223 | total loss: [1m[32m0.11303[0m[0m | time: 0.008s
[2K
| Adam | epoch: 556 | loss: 0.11303 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2224 | total loss: [1m[32m0.12265[0m[0m | time: 0.010s
[2K
| Adam | epoch: 556 | loss: 0.12265 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2225 | total loss: [1m[32m0.11840[0m[0m | time: 0.003s
[2K
| Adam | epoch: 557 | loss: 0.11840 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2226 | total loss: [1m[32m0.11452[0m[0m | time: 0.006s
[2K
| Adam | epoch: 557 | loss: 0.11452 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2227 | total loss: [1m[32m0.10921[0m[0m | time: 0.009s
[2K
| Adam | epoch: 557 | loss: 0.10921 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2228 | total loss: [1m[32m0.10827[0m[0m | time: 0.012s
[2K
| Adam | epoch: 557 | loss: 0.10827 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2229 | total loss: [1m[32m0.11199[0m[0m | time: 0.003s
[2K
| Adam | epoch: 558 | loss: 0.11199 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2230 | total loss: [1m[32m0.11771[0m[0m | time: 0.006s
[2K
| Adam | epoch: 558 | loss: 0.11771 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2231 | total loss: [1m[32m0.12277[0m[0m | time: 0.009s
[2K
| Adam | epoch: 558 | loss: 0.12277 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2232 | total loss: [1m[32m0.11726[0m[0m | time: 0.011s
[2K
| Adam | epoch: 558 | loss: 0.11726 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2233 | total loss: [1m[32m0.11543[0m[0m | time: 0.003s
[2K
| Adam | epoch: 559 | loss: 0.11543 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2234 | total loss: [1m[32m0.11172[0m[0m | time: 0.005s
[2K
| Adam | epoch: 559 | loss: 0.11172 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2235 | total loss: [1m[32m0.12638[0m[0m | time: 0.009s
[2K
| Adam | epoch: 559 | loss: 0.12638 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2236 | total loss: [1m[32m0.13950[0m[0m | time: 0.012s
[2K
| Adam | epoch: 559 | loss: 0.13950 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2237 | total loss: [1m[32m0.13407[0m[0m | time: 0.002s
[2K
| Adam | epoch: 560 | loss: 0.13407 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2238 | total loss: [1m[32m0.12976[0m[0m | time: 0.010s
[2K
| Adam | epoch: 560 | loss: 0.12976 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2239 | total loss: [1m[32m0.12589[0m[0m | time: 0.014s
[2K
| Adam | epoch: 560 | loss: 0.12589 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2240 | total loss: [1m[32m0.12158[0m[0m | time: 0.016s
[2K
| Adam | epoch: 560 | loss: 0.12158 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2241 | total loss: [1m[32m0.11767[0m[0m | time: 0.002s
[2K
| Adam | epoch: 561 | loss: 0.11767 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2242 | total loss: [1m[32m0.12396[0m[0m | time: 0.005s
[2K
| Adam | epoch: 561 | loss: 0.12396 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2243 | total loss: [1m[32m0.12057[0m[0m | time: 0.008s
[2K
| Adam | epoch: 561 | loss: 0.12057 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2244 | total loss: [1m[32m0.12303[0m[0m | time: 0.010s
[2K
| Adam | epoch: 561 | loss: 0.12303 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2245 | total loss: [1m[32m0.11829[0m[0m | time: 0.002s
[2K
| Adam | epoch: 562 | loss: 0.11829 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2246 | total loss: [1m[32m0.11400[0m[0m | time: 0.005s
[2K
| Adam | epoch: 562 | loss: 0.11400 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2247 | total loss: [1m[32m0.11728[0m[0m | time: 0.008s
[2K
| Adam | epoch: 562 | loss: 0.11728 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2248 | total loss: [1m[32m0.11269[0m[0m | time: 0.010s
[2K
| Adam | epoch: 562 | loss: 0.11269 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2249 | total loss: [1m[32m0.10939[0m[0m | time: 0.003s
[2K
| Adam | epoch: 563 | loss: 0.10939 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2250 | total loss: [1m[32m0.10683[0m[0m | time: 0.005s
[2K
| Adam | epoch: 563 | loss: 0.10683 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2251 | total loss: [1m[32m0.10447[0m[0m | time: 0.008s
[2K
| Adam | epoch: 563 | loss: 0.10447 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2252 | total loss: [1m[32m0.10577[0m[0m | time: 0.010s
[2K
| Adam | epoch: 563 | loss: 0.10577 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2253 | total loss: [1m[32m0.11096[0m[0m | time: 0.002s
[2K
| Adam | epoch: 564 | loss: 0.11096 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2254 | total loss: [1m[32m0.10955[0m[0m | time: 0.005s
[2K
| Adam | epoch: 564 | loss: 0.10955 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2255 | total loss: [1m[32m0.11252[0m[0m | time: 0.008s
[2K
| Adam | epoch: 564 | loss: 0.11252 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2256 | total loss: [1m[32m0.11515[0m[0m | time: 0.010s
[2K
| Adam | epoch: 564 | loss: 0.11515 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2257 | total loss: [1m[32m0.11487[0m[0m | time: 0.002s
[2K
| Adam | epoch: 565 | loss: 0.11487 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2258 | total loss: [1m[32m0.11414[0m[0m | time: 0.005s
[2K
| Adam | epoch: 565 | loss: 0.11414 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2259 | total loss: [1m[32m0.11404[0m[0m | time: 0.007s
[2K
| Adam | epoch: 565 | loss: 0.11404 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2260 | total loss: [1m[32m0.10625[0m[0m | time: 0.009s
[2K
| Adam | epoch: 565 | loss: 0.10625 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2261 | total loss: [1m[32m0.09924[0m[0m | time: 0.003s
[2K
| Adam | epoch: 566 | loss: 0.09924 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2262 | total loss: [1m[32m0.10147[0m[0m | time: 0.005s
[2K
| Adam | epoch: 566 | loss: 0.10147 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2263 | total loss: [1m[32m0.10563[0m[0m | time: 0.008s
[2K
| Adam | epoch: 566 | loss: 0.10563 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2264 | total loss: [1m[32m0.11353[0m[0m | time: 0.011s
[2K
| Adam | epoch: 566 | loss: 0.11353 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2265 | total loss: [1m[32m0.10755[0m[0m | time: 0.003s
[2K
| Adam | epoch: 567 | loss: 0.10755 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2266 | total loss: [1m[32m0.10213[0m[0m | time: 0.007s
[2K
| Adam | epoch: 567 | loss: 0.10213 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2267 | total loss: [1m[32m0.10449[0m[0m | time: 0.011s
[2K
| Adam | epoch: 567 | loss: 0.10449 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2268 | total loss: [1m[32m0.09934[0m[0m | time: 0.014s
[2K
| Adam | epoch: 567 | loss: 0.09934 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2269 | total loss: [1m[32m0.09835[0m[0m | time: 0.020s
[2K
| Adam | epoch: 568 | loss: 0.09835 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2270 | total loss: [1m[32m0.09501[0m[0m | time: 0.022s
[2K
| Adam | epoch: 568 | loss: 0.09501 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2271 | total loss: [1m[32m0.09197[0m[0m | time: 0.024s
[2K
| Adam | epoch: 568 | loss: 0.09197 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2272 | total loss: [1m[32m0.09149[0m[0m | time: 0.027s
[2K
| Adam | epoch: 568 | loss: 0.09149 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2273 | total loss: [1m[32m0.10000[0m[0m | time: 0.002s
[2K
| Adam | epoch: 569 | loss: 0.10000 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2274 | total loss: [1m[32m0.10121[0m[0m | time: 0.005s
[2K
| Adam | epoch: 569 | loss: 0.10121 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2275 | total loss: [1m[32m0.09616[0m[0m | time: 0.008s
[2K
| Adam | epoch: 569 | loss: 0.09616 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2276 | total loss: [1m[32m0.09158[0m[0m | time: 0.011s
[2K
| Adam | epoch: 569 | loss: 0.09158 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2277 | total loss: [1m[32m0.09390[0m[0m | time: 0.003s
[2K
| Adam | epoch: 570 | loss: 0.09390 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2278 | total loss: [1m[32m0.09772[0m[0m | time: 0.006s
[2K
| Adam | epoch: 570 | loss: 0.09772 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2279 | total loss: [1m[32m0.09814[0m[0m | time: 0.009s
[2K
| Adam | epoch: 570 | loss: 0.09814 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2280 | total loss: [1m[32m0.09353[0m[0m | time: 0.011s
[2K
| Adam | epoch: 570 | loss: 0.09353 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2281 | total loss: [1m[32m0.08935[0m[0m | time: 0.002s
[2K
| Adam | epoch: 571 | loss: 0.08935 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2282 | total loss: [1m[32m0.09720[0m[0m | time: 0.005s
[2K
| Adam | epoch: 571 | loss: 0.09720 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2283 | total loss: [1m[32m0.09607[0m[0m | time: 0.007s
[2K
| Adam | epoch: 571 | loss: 0.09607 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2284 | total loss: [1m[32m0.09007[0m[0m | time: 0.010s
[2K
| Adam | epoch: 571 | loss: 0.09007 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2285 | total loss: [1m[32m0.10104[0m[0m | time: 0.002s
[2K
| Adam | epoch: 572 | loss: 0.10104 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2286 | total loss: [1m[32m0.11078[0m[0m | time: 0.006s
[2K
| Adam | epoch: 572 | loss: 0.11078 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2287 | total loss: [1m[32m0.10415[0m[0m | time: 0.009s
[2K
| Adam | epoch: 572 | loss: 0.10415 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2288 | total loss: [1m[32m0.11192[0m[0m | time: 0.012s
[2K
| Adam | epoch: 572 | loss: 0.11192 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2289 | total loss: [1m[32m0.11280[0m[0m | time: 0.003s
[2K
| Adam | epoch: 573 | loss: 0.11280 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2290 | total loss: [1m[32m0.11074[0m[0m | time: 0.005s
[2K
| Adam | epoch: 573 | loss: 0.11074 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2291 | total loss: [1m[32m0.10885[0m[0m | time: 0.009s
[2K
| Adam | epoch: 573 | loss: 0.10885 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2292 | total loss: [1m[32m0.10241[0m[0m | time: 0.011s
[2K
| Adam | epoch: 573 | loss: 0.10241 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2293 | total loss: [1m[32m0.10811[0m[0m | time: 0.003s
[2K
| Adam | epoch: 574 | loss: 0.10811 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2294 | total loss: [1m[32m0.11044[0m[0m | time: 0.007s
[2K
| Adam | epoch: 574 | loss: 0.11044 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2295 | total loss: [1m[32m0.11228[0m[0m | time: 0.009s
[2K
| Adam | epoch: 574 | loss: 0.11228 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2296 | total loss: [1m[32m0.11378[0m[0m | time: 0.011s
[2K
| Adam | epoch: 574 | loss: 0.11378 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2297 | total loss: [1m[32m0.11463[0m[0m | time: 0.003s
[2K
| Adam | epoch: 575 | loss: 0.11463 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2298 | total loss: [1m[32m0.10792[0m[0m | time: 0.006s
[2K
| Adam | epoch: 575 | loss: 0.10792 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2299 | total loss: [1m[32m0.10218[0m[0m | time: 0.009s
[2K
| Adam | epoch: 575 | loss: 0.10218 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2300 | total loss: [1m[32m0.10520[0m[0m | time: 0.012s
[2K
| Adam | epoch: 575 | loss: 0.10520 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2301 | total loss: [1m[32m0.10784[0m[0m | time: 0.003s
[2K
| Adam | epoch: 576 | loss: 0.10784 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2302 | total loss: [1m[32m0.10604[0m[0m | time: 0.017s
[2K
| Adam | epoch: 576 | loss: 0.10604 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2303 | total loss: [1m[32m0.11101[0m[0m | time: 0.020s
[2K
| Adam | epoch: 576 | loss: 0.11101 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2304 | total loss: [1m[32m0.11273[0m[0m | time: 0.023s
[2K
| Adam | epoch: 576 | loss: 0.11273 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2305 | total loss: [1m[32m0.10601[0m[0m | time: 0.003s
[2K
| Adam | epoch: 577 | loss: 0.10601 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2306 | total loss: [1m[32m0.09996[0m[0m | time: 0.006s
[2K
| Adam | epoch: 577 | loss: 0.09996 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2307 | total loss: [1m[32m0.10481[0m[0m | time: 0.009s
[2K
| Adam | epoch: 577 | loss: 0.10481 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2308 | total loss: [1m[32m0.10139[0m[0m | time: 0.012s
[2K
| Adam | epoch: 577 | loss: 0.10139 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2309 | total loss: [1m[32m0.09363[0m[0m | time: 0.003s
[2K
| Adam | epoch: 578 | loss: 0.09363 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2310 | total loss: [1m[32m0.10138[0m[0m | time: 0.007s
[2K
| Adam | epoch: 578 | loss: 0.10138 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2311 | total loss: [1m[32m0.10829[0m[0m | time: 0.010s
[2K
| Adam | epoch: 578 | loss: 0.10829 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2312 | total loss: [1m[32m0.11201[0m[0m | time: 0.013s
[2K
| Adam | epoch: 578 | loss: 0.11201 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2313 | total loss: [1m[32m0.11047[0m[0m | time: 0.003s
[2K
| Adam | epoch: 579 | loss: 0.11047 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2314 | total loss: [1m[32m0.10781[0m[0m | time: 0.006s
[2K
| Adam | epoch: 579 | loss: 0.10781 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2315 | total loss: [1m[32m0.11793[0m[0m | time: 0.009s
[2K
| Adam | epoch: 579 | loss: 0.11793 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2316 | total loss: [1m[32m0.12698[0m[0m | time: 0.012s
[2K
| Adam | epoch: 579 | loss: 0.12698 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2317 | total loss: [1m[32m0.11944[0m[0m | time: 0.002s
[2K
| Adam | epoch: 580 | loss: 0.11944 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2318 | total loss: [1m[32m0.11800[0m[0m | time: 0.005s
[2K
| Adam | epoch: 580 | loss: 0.11800 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2319 | total loss: [1m[32m0.11506[0m[0m | time: 0.008s
[2K
| Adam | epoch: 580 | loss: 0.11506 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2320 | total loss: [1m[32m0.11197[0m[0m | time: 0.011s
[2K
| Adam | epoch: 580 | loss: 0.11197 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2321 | total loss: [1m[32m0.10910[0m[0m | time: 0.003s
[2K
| Adam | epoch: 581 | loss: 0.10910 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2322 | total loss: [1m[32m0.11129[0m[0m | time: 0.006s
[2K
| Adam | epoch: 581 | loss: 0.11129 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2323 | total loss: [1m[32m0.10969[0m[0m | time: 0.009s
[2K
| Adam | epoch: 581 | loss: 0.10969 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2324 | total loss: [1m[32m0.10977[0m[0m | time: 0.012s
[2K
| Adam | epoch: 581 | loss: 0.10977 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2325 | total loss: [1m[32m0.11163[0m[0m | time: 0.003s
[2K
| Adam | epoch: 582 | loss: 0.11163 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2326 | total loss: [1m[32m0.11325[0m[0m | time: 0.007s
[2K
| Adam | epoch: 582 | loss: 0.11325 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2327 | total loss: [1m[32m0.10889[0m[0m | time: 0.009s
[2K
| Adam | epoch: 582 | loss: 0.10889 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2328 | total loss: [1m[32m0.10850[0m[0m | time: 0.033s
[2K
| Adam | epoch: 582 | loss: 0.10850 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2329 | total loss: [1m[32m0.10940[0m[0m | time: 0.002s
[2K
| Adam | epoch: 583 | loss: 0.10940 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2330 | total loss: [1m[32m0.11047[0m[0m | time: 0.004s
[2K
| Adam | epoch: 583 | loss: 0.11047 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2331 | total loss: [1m[32m0.11135[0m[0m | time: 0.006s
[2K
| Adam | epoch: 583 | loss: 0.11135 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2332 | total loss: [1m[32m0.10798[0m[0m | time: 0.008s
[2K
| Adam | epoch: 583 | loss: 0.10798 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2333 | total loss: [1m[32m0.10638[0m[0m | time: 0.002s
[2K
| Adam | epoch: 584 | loss: 0.10638 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2334 | total loss: [1m[32m0.10536[0m[0m | time: 0.005s
[2K
| Adam | epoch: 584 | loss: 0.10536 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2335 | total loss: [1m[32m0.10419[0m[0m | time: 0.007s
[2K
| Adam | epoch: 584 | loss: 0.10419 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2336 | total loss: [1m[32m0.10301[0m[0m | time: 0.010s
[2K
| Adam | epoch: 584 | loss: 0.10301 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2337 | total loss: [1m[32m0.10041[0m[0m | time: 0.002s
[2K
| Adam | epoch: 585 | loss: 0.10041 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2338 | total loss: [1m[32m0.09596[0m[0m | time: 0.006s
[2K
| Adam | epoch: 585 | loss: 0.09596 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2339 | total loss: [1m[32m0.09661[0m[0m | time: 0.009s
[2K
| Adam | epoch: 585 | loss: 0.09661 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2340 | total loss: [1m[32m0.10474[0m[0m | time: 0.012s
[2K
| Adam | epoch: 585 | loss: 0.10474 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2341 | total loss: [1m[32m0.11208[0m[0m | time: 0.003s
[2K
| Adam | epoch: 586 | loss: 0.11208 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2342 | total loss: [1m[32m0.10922[0m[0m | time: 0.005s
[2K
| Adam | epoch: 586 | loss: 0.10922 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2343 | total loss: [1m[32m0.10403[0m[0m | time: 0.008s
[2K
| Adam | epoch: 586 | loss: 0.10403 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2344 | total loss: [1m[32m0.10191[0m[0m | time: 0.011s
[2K
| Adam | epoch: 586 | loss: 0.10191 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2345 | total loss: [1m[32m0.10320[0m[0m | time: 0.003s
[2K
| Adam | epoch: 587 | loss: 0.10320 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2346 | total loss: [1m[32m0.10429[0m[0m | time: 0.006s
[2K
| Adam | epoch: 587 | loss: 0.10429 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2347 | total loss: [1m[32m0.10448[0m[0m | time: 0.009s
[2K
| Adam | epoch: 587 | loss: 0.10448 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2348 | total loss: [1m[32m0.10310[0m[0m | time: 0.012s
[2K
| Adam | epoch: 587 | loss: 0.10310 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2349 | total loss: [1m[32m0.10280[0m[0m | time: 0.003s
[2K
| Adam | epoch: 588 | loss: 0.10280 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2350 | total loss: [1m[32m0.10119[0m[0m | time: 0.006s
[2K
| Adam | epoch: 588 | loss: 0.10119 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2351 | total loss: [1m[32m0.09970[0m[0m | time: 0.009s
[2K
| Adam | epoch: 588 | loss: 0.09970 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2352 | total loss: [1m[32m0.09750[0m[0m | time: 0.012s
[2K
| Adam | epoch: 588 | loss: 0.09750 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2353 | total loss: [1m[32m0.09929[0m[0m | time: 0.003s
[2K
| Adam | epoch: 589 | loss: 0.09929 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2354 | total loss: [1m[32m0.09739[0m[0m | time: 0.006s
[2K
| Adam | epoch: 589 | loss: 0.09739 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2355 | total loss: [1m[32m0.09449[0m[0m | time: 0.009s
[2K
| Adam | epoch: 589 | loss: 0.09449 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2356 | total loss: [1m[32m0.09184[0m[0m | time: 0.012s
[2K
| Adam | epoch: 589 | loss: 0.09184 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2357 | total loss: [1m[32m0.09846[0m[0m | time: 0.003s
[2K
| Adam | epoch: 590 | loss: 0.09846 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2358 | total loss: [1m[32m0.09508[0m[0m | time: 0.022s
[2K
| Adam | epoch: 590 | loss: 0.09508 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2359 | total loss: [1m[32m0.09093[0m[0m | time: 0.024s
[2K
| Adam | epoch: 590 | loss: 0.09093 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2360 | total loss: [1m[32m0.09207[0m[0m | time: 0.027s
[2K
| Adam | epoch: 590 | loss: 0.09207 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2361 | total loss: [1m[32m0.09301[0m[0m | time: 0.003s
[2K
| Adam | epoch: 591 | loss: 0.09301 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2362 | total loss: [1m[32m0.09146[0m[0m | time: 0.005s
[2K
| Adam | epoch: 591 | loss: 0.09146 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2363 | total loss: [1m[32m0.09701[0m[0m | time: 0.008s
[2K
| Adam | epoch: 591 | loss: 0.09701 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2364 | total loss: [1m[32m0.09892[0m[0m | time: 0.011s
[2K
| Adam | epoch: 591 | loss: 0.09892 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2365 | total loss: [1m[32m0.10629[0m[0m | time: 0.003s
[2K
| Adam | epoch: 592 | loss: 0.10629 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2366 | total loss: [1m[32m0.11290[0m[0m | time: 0.005s
[2K
| Adam | epoch: 592 | loss: 0.11290 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2367 | total loss: [1m[32m0.10743[0m[0m | time: 0.008s
[2K
| Adam | epoch: 592 | loss: 0.10743 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2368 | total loss: [1m[32m0.10236[0m[0m | time: 0.011s
[2K
| Adam | epoch: 592 | loss: 0.10236 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2369 | total loss: [1m[32m0.10224[0m[0m | time: 0.003s
[2K
| Adam | epoch: 593 | loss: 0.10224 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2370 | total loss: [1m[32m0.09628[0m[0m | time: 0.005s
[2K
| Adam | epoch: 593 | loss: 0.09628 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2371 | total loss: [1m[32m0.09089[0m[0m | time: 0.008s
[2K
| Adam | epoch: 593 | loss: 0.09089 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2372 | total loss: [1m[32m0.09397[0m[0m | time: 0.011s
[2K
| Adam | epoch: 593 | loss: 0.09397 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2373 | total loss: [1m[32m0.09338[0m[0m | time: 0.003s
[2K
| Adam | epoch: 594 | loss: 0.09338 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2374 | total loss: [1m[32m0.08835[0m[0m | time: 0.006s
[2K
| Adam | epoch: 594 | loss: 0.08835 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2375 | total loss: [1m[32m0.08960[0m[0m | time: 0.009s
[2K
| Adam | epoch: 594 | loss: 0.08960 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2376 | total loss: [1m[32m0.09069[0m[0m | time: 0.014s
[2K
| Adam | epoch: 594 | loss: 0.09069 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2377 | total loss: [1m[32m0.09763[0m[0m | time: 0.003s
[2K
| Adam | epoch: 595 | loss: 0.09763 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2378 | total loss: [1m[32m0.09472[0m[0m | time: 0.005s
[2K
| Adam | epoch: 595 | loss: 0.09472 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2379 | total loss: [1m[32m0.09354[0m[0m | time: 0.007s
[2K
| Adam | epoch: 595 | loss: 0.09354 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2380 | total loss: [1m[32m0.09969[0m[0m | time: 0.009s
[2K
| Adam | epoch: 595 | loss: 0.09969 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2381 | total loss: [1m[32m0.10516[0m[0m | time: 0.003s
[2K
| Adam | epoch: 596 | loss: 0.10516 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2382 | total loss: [1m[32m0.10371[0m[0m | time: 0.006s
[2K
| Adam | epoch: 596 | loss: 0.10371 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2383 | total loss: [1m[32m0.09963[0m[0m | time: 0.009s
[2K
| Adam | epoch: 596 | loss: 0.09963 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2384 | total loss: [1m[32m0.09825[0m[0m | time: 0.011s
[2K
| Adam | epoch: 596 | loss: 0.09825 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2385 | total loss: [1m[32m0.09462[0m[0m | time: 0.015s
[2K
| Adam | epoch: 597 | loss: 0.09462 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2386 | total loss: [1m[32m0.09133[0m[0m | time: 0.017s
[2K
| Adam | epoch: 597 | loss: 0.09133 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2387 | total loss: [1m[32m0.08817[0m[0m | time: 0.020s
[2K
| Adam | epoch: 597 | loss: 0.08817 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2388 | total loss: [1m[32m0.09388[0m[0m | time: 0.028s
[2K
| Adam | epoch: 597 | loss: 0.09388 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2389 | total loss: [1m[32m0.09620[0m[0m | time: 0.003s
[2K
| Adam | epoch: 598 | loss: 0.09620 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2390 | total loss: [1m[32m0.09447[0m[0m | time: 0.007s
[2K
| Adam | epoch: 598 | loss: 0.09447 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2391 | total loss: [1m[32m0.09287[0m[0m | time: 0.011s
[2K
| Adam | epoch: 598 | loss: 0.09287 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2392 | total loss: [1m[32m0.08694[0m[0m | time: 0.015s
[2K
| Adam | epoch: 598 | loss: 0.08694 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2393 | total loss: [1m[32m0.09103[0m[0m | time: 0.004s
[2K
| Adam | epoch: 599 | loss: 0.09103 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2394 | total loss: [1m[32m0.09445[0m[0m | time: 0.007s
[2K
| Adam | epoch: 599 | loss: 0.09445 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2395 | total loss: [1m[32m0.08925[0m[0m | time: 0.012s
[2K
| Adam | epoch: 599 | loss: 0.08925 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2396 | total loss: [1m[32m0.08451[0m[0m | time: 0.016s
[2K
| Adam | epoch: 599 | loss: 0.08451 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2397 | total loss: [1m[32m0.08473[0m[0m | time: 0.004s
[2K
| Adam | epoch: 600 | loss: 0.08473 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2398 | total loss: [1m[32m0.08493[0m[0m | time: 0.008s
[2K
| Adam | epoch: 600 | loss: 0.08493 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2399 | total loss: [1m[32m0.08804[0m[0m | time: 0.012s
[2K
| Adam | epoch: 600 | loss: 0.08804 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2400 | total loss: [1m[32m0.08444[0m[0m | time: 0.016s
[2K
| Adam | epoch: 600 | loss: 0.08444 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2401 | total loss: [1m[32m0.08115[0m[0m | time: 0.004s
[2K
| Adam | epoch: 601 | loss: 0.08115 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2402 | total loss: [1m[32m0.07922[0m[0m | time: 0.007s
[2K
| Adam | epoch: 601 | loss: 0.07922 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2403 | total loss: [1m[32m0.08272[0m[0m | time: 0.012s
[2K
| Adam | epoch: 601 | loss: 0.08272 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2404 | total loss: [1m[32m0.08516[0m[0m | time: 0.017s
[2K
| Adam | epoch: 601 | loss: 0.08516 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2405 | total loss: [1m[32m0.08260[0m[0m | time: 0.026s
[2K
| Adam | epoch: 602 | loss: 0.08260 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2406 | total loss: [1m[32m0.08028[0m[0m | time: 0.028s
[2K
| Adam | epoch: 602 | loss: 0.08028 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2407 | total loss: [1m[32m0.07728[0m[0m | time: 0.031s
[2K
| Adam | epoch: 602 | loss: 0.07728 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2408 | total loss: [1m[32m0.08216[0m[0m | time: 0.033s
[2K
| Adam | epoch: 602 | loss: 0.08216 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2409 | total loss: [1m[32m0.07703[0m[0m | time: 0.003s
[2K
| Adam | epoch: 603 | loss: 0.07703 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2410 | total loss: [1m[32m0.08043[0m[0m | time: 0.005s
[2K
| Adam | epoch: 603 | loss: 0.08043 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2411 | total loss: [1m[32m0.08337[0m[0m | time: 0.007s
[2K
| Adam | epoch: 603 | loss: 0.08337 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2412 | total loss: [1m[32m0.08830[0m[0m | time: 0.014s
[2K
| Adam | epoch: 603 | loss: 0.08830 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2413 | total loss: [1m[32m0.08818[0m[0m | time: 0.002s
[2K
| Adam | epoch: 604 | loss: 0.08818 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2414 | total loss: [1m[32m0.08479[0m[0m | time: 0.005s
[2K
| Adam | epoch: 604 | loss: 0.08479 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2415 | total loss: [1m[32m0.08563[0m[0m | time: 0.007s
[2K
| Adam | epoch: 604 | loss: 0.08563 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2416 | total loss: [1m[32m0.08626[0m[0m | time: 0.010s
[2K
| Adam | epoch: 604 | loss: 0.08626 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2417 | total loss: [1m[32m0.09327[0m[0m | time: 0.002s
[2K
| Adam | epoch: 605 | loss: 0.09327 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2418 | total loss: [1m[32m0.08883[0m[0m | time: 0.005s
[2K
| Adam | epoch: 605 | loss: 0.08883 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2419 | total loss: [1m[32m0.09165[0m[0m | time: 0.008s
[2K
| Adam | epoch: 605 | loss: 0.09165 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2420 | total loss: [1m[32m0.09733[0m[0m | time: 0.011s
[2K
| Adam | epoch: 605 | loss: 0.09733 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2421 | total loss: [1m[32m0.10229[0m[0m | time: 0.003s
[2K
| Adam | epoch: 606 | loss: 0.10229 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2422 | total loss: [1m[32m0.09649[0m[0m | time: 0.005s
[2K
| Adam | epoch: 606 | loss: 0.09649 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2423 | total loss: [1m[32m0.09288[0m[0m | time: 0.007s
[2K
| Adam | epoch: 606 | loss: 0.09288 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2424 | total loss: [1m[32m0.09019[0m[0m | time: 0.010s
[2K
| Adam | epoch: 606 | loss: 0.09019 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2425 | total loss: [1m[32m0.08670[0m[0m | time: 0.002s
[2K
| Adam | epoch: 607 | loss: 0.08670 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2426 | total loss: [1m[32m0.08354[0m[0m | time: 0.005s
[2K
| Adam | epoch: 607 | loss: 0.08354 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2427 | total loss: [1m[32m0.08565[0m[0m | time: 0.007s
[2K
| Adam | epoch: 607 | loss: 0.08565 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2428 | total loss: [1m[32m0.08752[0m[0m | time: 0.010s
[2K
| Adam | epoch: 607 | loss: 0.08752 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2429 | total loss: [1m[32m0.08315[0m[0m | time: 0.002s
[2K
| Adam | epoch: 608 | loss: 0.08315 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2430 | total loss: [1m[32m0.08122[0m[0m | time: 0.005s
[2K
| Adam | epoch: 608 | loss: 0.08122 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2431 | total loss: [1m[32m0.07946[0m[0m | time: 0.007s
[2K
| Adam | epoch: 608 | loss: 0.07946 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2432 | total loss: [1m[32m0.08437[0m[0m | time: 0.010s
[2K
| Adam | epoch: 608 | loss: 0.08437 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2433 | total loss: [1m[32m0.08548[0m[0m | time: 0.002s
[2K
| Adam | epoch: 609 | loss: 0.08548 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2434 | total loss: [1m[32m0.08268[0m[0m | time: 0.005s
[2K
| Adam | epoch: 609 | loss: 0.08268 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2435 | total loss: [1m[32m0.07943[0m[0m | time: 0.008s
[2K
| Adam | epoch: 609 | loss: 0.07943 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2436 | total loss: [1m[32m0.07650[0m[0m | time: 0.010s
[2K
| Adam | epoch: 609 | loss: 0.07650 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2437 | total loss: [1m[32m0.08443[0m[0m | time: 0.020s
[2K
| Adam | epoch: 610 | loss: 0.08443 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2438 | total loss: [1m[32m0.08209[0m[0m | time: 0.022s
[2K
| Adam | epoch: 610 | loss: 0.08209 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2439 | total loss: [1m[32m0.08039[0m[0m | time: 0.025s
[2K
| Adam | epoch: 610 | loss: 0.08039 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2440 | total loss: [1m[32m0.08374[0m[0m | time: 0.027s
[2K
| Adam | epoch: 610 | loss: 0.08374 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2441 | total loss: [1m[32m0.08670[0m[0m | time: 0.003s
[2K
| Adam | epoch: 611 | loss: 0.08670 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2442 | total loss: [1m[32m0.08976[0m[0m | time: 0.007s
[2K
| Adam | epoch: 611 | loss: 0.08976 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2443 | total loss: [1m[32m0.08587[0m[0m | time: 0.009s
[2K
| Adam | epoch: 611 | loss: 0.08587 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2444 | total loss: [1m[32m0.08592[0m[0m | time: 0.012s
[2K
| Adam | epoch: 611 | loss: 0.08592 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2445 | total loss: [1m[32m0.08473[0m[0m | time: 0.003s
[2K
| Adam | epoch: 612 | loss: 0.08473 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2446 | total loss: [1m[32m0.08361[0m[0m | time: 0.005s
[2K
| Adam | epoch: 612 | loss: 0.08361 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2447 | total loss: [1m[32m0.07777[0m[0m | time: 0.008s
[2K
| Adam | epoch: 612 | loss: 0.07777 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2448 | total loss: [1m[32m0.08454[0m[0m | time: 0.011s
[2K
| Adam | epoch: 612 | loss: 0.08454 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2449 | total loss: [1m[32m0.08512[0m[0m | time: 0.003s
[2K
| Adam | epoch: 613 | loss: 0.08512 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2450 | total loss: [1m[32m0.08178[0m[0m | time: 0.007s
[2K
| Adam | epoch: 613 | loss: 0.08178 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2451 | total loss: [1m[32m0.07874[0m[0m | time: 0.010s
[2K
| Adam | epoch: 613 | loss: 0.07874 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2452 | total loss: [1m[32m0.07853[0m[0m | time: 0.013s
[2K
| Adam | epoch: 613 | loss: 0.07853 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2453 | total loss: [1m[32m0.08083[0m[0m | time: 0.003s
[2K
| Adam | epoch: 614 | loss: 0.08083 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2454 | total loss: [1m[32m0.08109[0m[0m | time: 0.007s
[2K
| Adam | epoch: 614 | loss: 0.08109 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2455 | total loss: [1m[32m0.07630[0m[0m | time: 0.010s
[2K
| Adam | epoch: 614 | loss: 0.07630 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2456 | total loss: [1m[32m0.07198[0m[0m | time: 0.013s
[2K
| Adam | epoch: 614 | loss: 0.07198 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2457 | total loss: [1m[32m0.07076[0m[0m | time: 0.003s
[2K
| Adam | epoch: 615 | loss: 0.07076 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2458 | total loss: [1m[32m0.07711[0m[0m | time: 0.006s
[2K
| Adam | epoch: 615 | loss: 0.07711 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2459 | total loss: [1m[32m0.07899[0m[0m | time: 0.011s
[2K
| Adam | epoch: 615 | loss: 0.07899 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2460 | total loss: [1m[32m0.07606[0m[0m | time: 0.013s
[2K
| Adam | epoch: 615 | loss: 0.07606 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2461 | total loss: [1m[32m0.07341[0m[0m | time: 0.003s
[2K
| Adam | epoch: 616 | loss: 0.07341 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2462 | total loss: [1m[32m0.07518[0m[0m | time: 0.007s
[2K
| Adam | epoch: 616 | loss: 0.07518 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2463 | total loss: [1m[32m0.07554[0m[0m | time: 0.010s
[2K
| Adam | epoch: 616 | loss: 0.07554 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2464 | total loss: [1m[32m0.07867[0m[0m | time: 0.013s
[2K
| Adam | epoch: 616 | loss: 0.07867 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2465 | total loss: [1m[32m0.07218[0m[0m | time: 0.003s
[2K
| Adam | epoch: 617 | loss: 0.07218 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2466 | total loss: [1m[32m0.06633[0m[0m | time: 0.016s
[2K
| Adam | epoch: 617 | loss: 0.06633 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2467 | total loss: [1m[32m0.06841[0m[0m | time: 0.019s
[2K
| Adam | epoch: 617 | loss: 0.06841 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2468 | total loss: [1m[32m0.07074[0m[0m | time: 0.022s
[2K
| Adam | epoch: 617 | loss: 0.07074 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2469 | total loss: [1m[32m0.06888[0m[0m | time: 0.003s
[2K
| Adam | epoch: 618 | loss: 0.06888 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2470 | total loss: [1m[32m0.07314[0m[0m | time: 0.006s
[2K
| Adam | epoch: 618 | loss: 0.07314 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2471 | total loss: [1m[32m0.07691[0m[0m | time: 0.009s
[2K
| Adam | epoch: 618 | loss: 0.07691 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2472 | total loss: [1m[32m0.07445[0m[0m | time: 0.012s
[2K
| Adam | epoch: 618 | loss: 0.07445 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2473 | total loss: [1m[32m0.07893[0m[0m | time: 0.003s
[2K
| Adam | epoch: 619 | loss: 0.07893 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2474 | total loss: [1m[32m0.07381[0m[0m | time: 0.006s
[2K
| Adam | epoch: 619 | loss: 0.07381 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2475 | total loss: [1m[32m0.07392[0m[0m | time: 0.010s
[2K
| Adam | epoch: 619 | loss: 0.07392 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2476 | total loss: [1m[32m0.07397[0m[0m | time: 0.013s
[2K
| Adam | epoch: 619 | loss: 0.07397 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2477 | total loss: [1m[32m0.07643[0m[0m | time: 0.003s
[2K
| Adam | epoch: 620 | loss: 0.07643 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2478 | total loss: [1m[32m0.08057[0m[0m | time: 0.007s
[2K
| Adam | epoch: 620 | loss: 0.08057 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2479 | total loss: [1m[32m0.07691[0m[0m | time: 0.010s
[2K
| Adam | epoch: 620 | loss: 0.07691 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2480 | total loss: [1m[32m0.07481[0m[0m | time: 0.013s
[2K
| Adam | epoch: 620 | loss: 0.07481 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2481 | total loss: [1m[32m0.07288[0m[0m | time: 0.004s
[2K
| Adam | epoch: 621 | loss: 0.07288 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2482 | total loss: [1m[32m0.07336[0m[0m | time: 0.007s
[2K
| Adam | epoch: 621 | loss: 0.07336 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2483 | total loss: [1m[32m0.07936[0m[0m | time: 0.010s
[2K
| Adam | epoch: 621 | loss: 0.07936 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2484 | total loss: [1m[32m0.07693[0m[0m | time: 0.013s
[2K
| Adam | epoch: 621 | loss: 0.07693 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2485 | total loss: [1m[32m0.08755[0m[0m | time: 0.003s
[2K
| Adam | epoch: 622 | loss: 0.08755 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2486 | total loss: [1m[32m0.09699[0m[0m | time: 0.006s
[2K
| Adam | epoch: 622 | loss: 0.09699 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2487 | total loss: [1m[32m0.09470[0m[0m | time: 0.010s
[2K
| Adam | epoch: 622 | loss: 0.09470 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2488 | total loss: [1m[32m0.08975[0m[0m | time: 0.013s
[2K
| Adam | epoch: 622 | loss: 0.08975 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2489 | total loss: [1m[32m0.08446[0m[0m | time: 0.002s
[2K
| Adam | epoch: 623 | loss: 0.08446 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2490 | total loss: [1m[32m0.08393[0m[0m | time: 0.006s
[2K
| Adam | epoch: 623 | loss: 0.08393 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2491 | total loss: [1m[32m0.08340[0m[0m | time: 0.009s
[2K
| Adam | epoch: 623 | loss: 0.08340 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2492 | total loss: [1m[32m0.07831[0m[0m | time: 0.012s
[2K
| Adam | epoch: 623 | loss: 0.07831 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2493 | total loss: [1m[32m0.08702[0m[0m | time: 0.003s
[2K
| Adam | epoch: 624 | loss: 0.08702 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2494 | total loss: [1m[32m0.08686[0m[0m | time: 0.006s
[2K
| Adam | epoch: 624 | loss: 0.08686 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2495 | total loss: [1m[32m0.08162[0m[0m | time: 0.009s
[2K
| Adam | epoch: 624 | loss: 0.08162 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2496 | total loss: [1m[32m0.07690[0m[0m | time: 0.012s
[2K
| Adam | epoch: 624 | loss: 0.07690 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2497 | total loss: [1m[32m0.07990[0m[0m | time: 0.003s
[2K
| Adam | epoch: 625 | loss: 0.07990 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2498 | total loss: [1m[32m0.07870[0m[0m | time: 0.007s
[2K
| Adam | epoch: 625 | loss: 0.07870 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2499 | total loss: [1m[32m0.07992[0m[0m | time: 0.009s
[2K
| Adam | epoch: 625 | loss: 0.07992 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2500 | total loss: [1m[32m0.08031[0m[0m | time: 0.012s
[2K
| Adam | epoch: 625 | loss: 0.08031 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2501 | total loss: [1m[32m0.08064[0m[0m | time: 0.003s
[2K
| Adam | epoch: 626 | loss: 0.08064 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2502 | total loss: [1m[32m0.08227[0m[0m | time: 0.006s
[2K
| Adam | epoch: 626 | loss: 0.08227 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2503 | total loss: [1m[32m0.07802[0m[0m | time: 0.008s
[2K
| Adam | epoch: 626 | loss: 0.07802 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2504 | total loss: [1m[32m0.08107[0m[0m | time: 0.012s
[2K
| Adam | epoch: 626 | loss: 0.08107 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2505 | total loss: [1m[32m0.07983[0m[0m | time: 0.003s
[2K
| Adam | epoch: 627 | loss: 0.07983 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2506 | total loss: [1m[32m0.07869[0m[0m | time: 0.007s
[2K
| Adam | epoch: 627 | loss: 0.07869 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2507 | total loss: [1m[32m0.07476[0m[0m | time: 0.009s
[2K
| Adam | epoch: 627 | loss: 0.07476 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2508 | total loss: [1m[32m0.07607[0m[0m | time: 0.012s
[2K
| Adam | epoch: 627 | loss: 0.07607 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2509 | total loss: [1m[32m0.08039[0m[0m | time: 0.003s
[2K
| Adam | epoch: 628 | loss: 0.08039 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2510 | total loss: [1m[32m0.07966[0m[0m | time: 0.007s
[2K
| Adam | epoch: 628 | loss: 0.07966 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2511 | total loss: [1m[32m0.07896[0m[0m | time: 0.010s
[2K
| Adam | epoch: 628 | loss: 0.07896 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2512 | total loss: [1m[32m0.07558[0m[0m | time: 0.014s
[2K
| Adam | epoch: 628 | loss: 0.07558 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2513 | total loss: [1m[32m0.07462[0m[0m | time: 0.004s
[2K
| Adam | epoch: 629 | loss: 0.07462 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2514 | total loss: [1m[32m0.07442[0m[0m | time: 0.007s
[2K
| Adam | epoch: 629 | loss: 0.07442 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2515 | total loss: [1m[32m0.07959[0m[0m | time: 0.009s
[2K
| Adam | epoch: 629 | loss: 0.07959 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2516 | total loss: [1m[32m0.08420[0m[0m | time: 0.012s
[2K
| Adam | epoch: 629 | loss: 0.08420 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2517 | total loss: [1m[32m0.08337[0m[0m | time: 0.004s
[2K
| Adam | epoch: 630 | loss: 0.08337 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2518 | total loss: [1m[32m0.07978[0m[0m | time: 0.007s
[2K
| Adam | epoch: 630 | loss: 0.07978 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2519 | total loss: [1m[32m0.08057[0m[0m | time: 0.010s
[2K
| Adam | epoch: 630 | loss: 0.08057 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2520 | total loss: [1m[32m0.07892[0m[0m | time: 0.013s
[2K
| Adam | epoch: 630 | loss: 0.07892 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2521 | total loss: [1m[32m0.07740[0m[0m | time: 0.003s
[2K
| Adam | epoch: 631 | loss: 0.07740 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2522 | total loss: [1m[32m0.07494[0m[0m | time: 0.007s
[2K
| Adam | epoch: 631 | loss: 0.07494 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2523 | total loss: [1m[32m0.07678[0m[0m | time: 0.009s
[2K
| Adam | epoch: 631 | loss: 0.07678 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2524 | total loss: [1m[32m0.07900[0m[0m | time: 0.012s
[2K
| Adam | epoch: 631 | loss: 0.07900 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2525 | total loss: [1m[32m0.07436[0m[0m | time: 0.013s
[2K
| Adam | epoch: 632 | loss: 0.07436 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2526 | total loss: [1m[32m0.07016[0m[0m | time: 0.015s
[2K
| Adam | epoch: 632 | loss: 0.07016 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2527 | total loss: [1m[32m0.06749[0m[0m | time: 0.017s
[2K
| Adam | epoch: 632 | loss: 0.06749 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2528 | total loss: [1m[32m0.07166[0m[0m | time: 0.020s
[2K
| Adam | epoch: 632 | loss: 0.07166 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2529 | total loss: [1m[32m0.06877[0m[0m | time: 0.002s
[2K
| Adam | epoch: 633 | loss: 0.06877 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2530 | total loss: [1m[32m0.07144[0m[0m | time: 0.005s
[2K
| Adam | epoch: 633 | loss: 0.07144 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2531 | total loss: [1m[32m0.07381[0m[0m | time: 0.007s
[2K
| Adam | epoch: 633 | loss: 0.07381 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2532 | total loss: [1m[32m0.07511[0m[0m | time: 0.010s
[2K
| Adam | epoch: 633 | loss: 0.07511 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2533 | total loss: [1m[32m0.07571[0m[0m | time: 0.002s
[2K
| Adam | epoch: 634 | loss: 0.07571 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2534 | total loss: [1m[32m0.07491[0m[0m | time: 0.006s
[2K
| Adam | epoch: 634 | loss: 0.07491 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2535 | total loss: [1m[32m0.07919[0m[0m | time: 0.009s
[2K
| Adam | epoch: 634 | loss: 0.07919 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2536 | total loss: [1m[32m0.08291[0m[0m | time: 0.012s
[2K
| Adam | epoch: 634 | loss: 0.08291 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2537 | total loss: [1m[32m0.08416[0m[0m | time: 0.003s
[2K
| Adam | epoch: 635 | loss: 0.08416 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2538 | total loss: [1m[32m0.07906[0m[0m | time: 0.006s
[2K
| Adam | epoch: 635 | loss: 0.07906 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2539 | total loss: [1m[32m0.07654[0m[0m | time: 0.008s
[2K
| Adam | epoch: 635 | loss: 0.07654 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2540 | total loss: [1m[32m0.07071[0m[0m | time: 0.011s
[2K
| Adam | epoch: 635 | loss: 0.07071 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2541 | total loss: [1m[32m0.06545[0m[0m | time: 0.003s
[2K
| Adam | epoch: 636 | loss: 0.06545 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2542 | total loss: [1m[32m0.07011[0m[0m | time: 0.005s
[2K
| Adam | epoch: 636 | loss: 0.07011 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2543 | total loss: [1m[32m0.07178[0m[0m | time: 0.008s
[2K
| Adam | epoch: 636 | loss: 0.07178 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2544 | total loss: [1m[32m0.07036[0m[0m | time: 0.010s
[2K
| Adam | epoch: 636 | loss: 0.07036 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2545 | total loss: [1m[32m0.07390[0m[0m | time: 0.002s
[2K
| Adam | epoch: 637 | loss: 0.07390 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2546 | total loss: [1m[32m0.07692[0m[0m | time: 0.005s
[2K
| Adam | epoch: 637 | loss: 0.07692 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2547 | total loss: [1m[32m0.07275[0m[0m | time: 0.008s
[2K
| Adam | epoch: 637 | loss: 0.07275 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2548 | total loss: [1m[32m0.07613[0m[0m | time: 0.011s
[2K
| Adam | epoch: 637 | loss: 0.07613 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2549 | total loss: [1m[32m0.07846[0m[0m | time: 0.003s
[2K
| Adam | epoch: 638 | loss: 0.07846 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2550 | total loss: [1m[32m0.08491[0m[0m | time: 0.006s
[2K
| Adam | epoch: 638 | loss: 0.08491 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2551 | total loss: [1m[32m0.09071[0m[0m | time: 0.009s
[2K
| Adam | epoch: 638 | loss: 0.09071 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2552 | total loss: [1m[32m0.08384[0m[0m | time: 0.011s
[2K
| Adam | epoch: 638 | loss: 0.08384 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2553 | total loss: [1m[32m0.08065[0m[0m | time: 0.003s
[2K
| Adam | epoch: 639 | loss: 0.08065 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2554 | total loss: [1m[32m0.08364[0m[0m | time: 0.006s
[2K
| Adam | epoch: 639 | loss: 0.08364 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2555 | total loss: [1m[32m0.08129[0m[0m | time: 0.030s
[2K
| Adam | epoch: 639 | loss: 0.08129 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2556 | total loss: [1m[32m0.07915[0m[0m | time: 0.032s
[2K
| Adam | epoch: 639 | loss: 0.07915 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2557 | total loss: [1m[32m0.07953[0m[0m | time: 0.003s
[2K
| Adam | epoch: 640 | loss: 0.07953 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2558 | total loss: [1m[32m0.07452[0m[0m | time: 0.005s
[2K
| Adam | epoch: 640 | loss: 0.07452 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2559 | total loss: [1m[32m0.07637[0m[0m | time: 0.007s
[2K
| Adam | epoch: 640 | loss: 0.07637 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2560 | total loss: [1m[32m0.07680[0m[0m | time: 0.010s
[2K
| Adam | epoch: 640 | loss: 0.07680 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2561 | total loss: [1m[32m0.07711[0m[0m | time: 0.002s
[2K
| Adam | epoch: 641 | loss: 0.07711 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2562 | total loss: [1m[32m0.07750[0m[0m | time: 0.005s
[2K
| Adam | epoch: 641 | loss: 0.07750 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2563 | total loss: [1m[32m0.07325[0m[0m | time: 0.007s
[2K
| Adam | epoch: 641 | loss: 0.07325 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2564 | total loss: [1m[32m0.06904[0m[0m | time: 0.010s
[2K
| Adam | epoch: 641 | loss: 0.06904 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2565 | total loss: [1m[32m0.06982[0m[0m | time: 0.002s
[2K
| Adam | epoch: 642 | loss: 0.06982 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2566 | total loss: [1m[32m0.07050[0m[0m | time: 0.005s
[2K
| Adam | epoch: 642 | loss: 0.07050 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2567 | total loss: [1m[32m0.07336[0m[0m | time: 0.007s
[2K
| Adam | epoch: 642 | loss: 0.07336 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2568 | total loss: [1m[32m0.07383[0m[0m | time: 0.010s
[2K
| Adam | epoch: 642 | loss: 0.07383 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2569 | total loss: [1m[32m0.06972[0m[0m | time: 0.002s
[2K
| Adam | epoch: 643 | loss: 0.06972 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2570 | total loss: [1m[32m0.06704[0m[0m | time: 0.005s
[2K
| Adam | epoch: 643 | loss: 0.06704 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2571 | total loss: [1m[32m0.06459[0m[0m | time: 0.008s
[2K
| Adam | epoch: 643 | loss: 0.06459 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2572 | total loss: [1m[32m0.05961[0m[0m | time: 0.010s
[2K
| Adam | epoch: 643 | loss: 0.05961 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2573 | total loss: [1m[32m0.07160[0m[0m | time: 0.003s
[2K
| Adam | epoch: 644 | loss: 0.07160 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2574 | total loss: [1m[32m0.07388[0m[0m | time: 0.005s
[2K
| Adam | epoch: 644 | loss: 0.07388 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2575 | total loss: [1m[32m0.06918[0m[0m | time: 0.008s
[2K
| Adam | epoch: 644 | loss: 0.06918 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2576 | total loss: [1m[32m0.06494[0m[0m | time: 0.011s
[2K
| Adam | epoch: 644 | loss: 0.06494 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2577 | total loss: [1m[32m0.06617[0m[0m | time: 0.002s
[2K
| Adam | epoch: 645 | loss: 0.06617 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2578 | total loss: [1m[32m0.06598[0m[0m | time: 0.005s
[2K
| Adam | epoch: 645 | loss: 0.06598 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2579 | total loss: [1m[32m0.06344[0m[0m | time: 0.007s
[2K
| Adam | epoch: 645 | loss: 0.06344 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2580 | total loss: [1m[32m0.05790[0m[0m | time: 0.026s
[2K
| Adam | epoch: 645 | loss: 0.05790 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2581 | total loss: [1m[32m0.05291[0m[0m | time: 0.003s
[2K
| Adam | epoch: 646 | loss: 0.05291 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2582 | total loss: [1m[32m0.05623[0m[0m | time: 0.005s
[2K
| Adam | epoch: 646 | loss: 0.05623 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2583 | total loss: [1m[32m0.06244[0m[0m | time: 0.008s
[2K
| Adam | epoch: 646 | loss: 0.06244 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2584 | total loss: [1m[32m0.06120[0m[0m | time: 0.010s
[2K
| Adam | epoch: 646 | loss: 0.06120 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2585 | total loss: [1m[32m0.07066[0m[0m | time: 0.003s
[2K
| Adam | epoch: 647 | loss: 0.07066 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2586 | total loss: [1m[32m0.07909[0m[0m | time: 0.006s
[2K
| Adam | epoch: 647 | loss: 0.07909 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2587 | total loss: [1m[32m0.07386[0m[0m | time: 0.008s
[2K
| Adam | epoch: 647 | loss: 0.07386 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2588 | total loss: [1m[32m0.07407[0m[0m | time: 0.011s
[2K
| Adam | epoch: 647 | loss: 0.07407 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2589 | total loss: [1m[32m0.07487[0m[0m | time: 0.003s
[2K
| Adam | epoch: 648 | loss: 0.07487 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2590 | total loss: [1m[32m0.07227[0m[0m | time: 0.005s
[2K
| Adam | epoch: 648 | loss: 0.07227 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2591 | total loss: [1m[32m0.06991[0m[0m | time: 0.007s
[2K
| Adam | epoch: 648 | loss: 0.06991 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2592 | total loss: [1m[32m0.07191[0m[0m | time: 0.010s
[2K
| Adam | epoch: 648 | loss: 0.07191 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2593 | total loss: [1m[32m0.06920[0m[0m | time: 0.002s
[2K
| Adam | epoch: 649 | loss: 0.06920 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2594 | total loss: [1m[32m0.06961[0m[0m | time: 0.005s
[2K
| Adam | epoch: 649 | loss: 0.06961 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2595 | total loss: [1m[32m0.07126[0m[0m | time: 0.007s
[2K
| Adam | epoch: 649 | loss: 0.07126 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2596 | total loss: [1m[32m0.07270[0m[0m | time: 0.010s
[2K
| Adam | epoch: 649 | loss: 0.07270 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2597 | total loss: [1m[32m0.06975[0m[0m | time: 0.003s
[2K
| Adam | epoch: 650 | loss: 0.06975 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2598 | total loss: [1m[32m0.07026[0m[0m | time: 0.005s
[2K
| Adam | epoch: 650 | loss: 0.07026 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2599 | total loss: [1m[32m0.06673[0m[0m | time: 0.007s
[2K
| Adam | epoch: 650 | loss: 0.06673 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2600 | total loss: [1m[32m0.06719[0m[0m | time: 0.010s
[2K
| Adam | epoch: 650 | loss: 0.06719 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2601 | total loss: [1m[32m0.06753[0m[0m | time: 0.002s
[2K
| Adam | epoch: 651 | loss: 0.06753 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2602 | total loss: [1m[32m0.06293[0m[0m | time: 0.005s
[2K
| Adam | epoch: 651 | loss: 0.06293 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2603 | total loss: [1m[32m0.07113[0m[0m | time: 0.007s
[2K
| Adam | epoch: 651 | loss: 0.07113 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2604 | total loss: [1m[32m0.07516[0m[0m | time: 0.009s
[2K
| Adam | epoch: 651 | loss: 0.07516 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2605 | total loss: [1m[32m0.07375[0m[0m | time: 0.003s
[2K
| Adam | epoch: 652 | loss: 0.07375 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2606 | total loss: [1m[32m0.07245[0m[0m | time: 0.005s
[2K
| Adam | epoch: 652 | loss: 0.07245 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2607 | total loss: [1m[32m0.07245[0m[0m | time: 0.008s
[2K
| Adam | epoch: 652 | loss: 0.07245 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2608 | total loss: [1m[32m0.06751[0m[0m | time: 0.010s
[2K
| Adam | epoch: 652 | loss: 0.06751 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2609 | total loss: [1m[32m0.07119[0m[0m | time: 0.003s
[2K
| Adam | epoch: 653 | loss: 0.07119 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2610 | total loss: [1m[32m0.07013[0m[0m | time: 0.005s
[2K
| Adam | epoch: 653 | loss: 0.07013 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2611 | total loss: [1m[32m0.06907[0m[0m | time: 0.007s
[2K
| Adam | epoch: 653 | loss: 0.06907 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2612 | total loss: [1m[32m0.06485[0m[0m | time: 0.010s
[2K
| Adam | epoch: 653 | loss: 0.06485 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2613 | total loss: [1m[32m0.06572[0m[0m | time: 0.002s
[2K
| Adam | epoch: 654 | loss: 0.06572 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2614 | total loss: [1m[32m0.06964[0m[0m | time: 0.005s
[2K
| Adam | epoch: 654 | loss: 0.06964 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2615 | total loss: [1m[32m0.06638[0m[0m | time: 0.017s
[2K
| Adam | epoch: 654 | loss: 0.06638 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2616 | total loss: [1m[32m0.06342[0m[0m | time: 0.020s
[2K
| Adam | epoch: 654 | loss: 0.06342 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2617 | total loss: [1m[32m0.06297[0m[0m | time: 0.002s
[2K
| Adam | epoch: 655 | loss: 0.06297 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2618 | total loss: [1m[32m0.06207[0m[0m | time: 0.005s
[2K
| Adam | epoch: 655 | loss: 0.06207 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2619 | total loss: [1m[32m0.05832[0m[0m | time: 0.008s
[2K
| Adam | epoch: 655 | loss: 0.05832 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2620 | total loss: [1m[32m0.06089[0m[0m | time: 0.011s
[2K
| Adam | epoch: 655 | loss: 0.06089 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2621 | total loss: [1m[32m0.06305[0m[0m | time: 0.003s
[2K
| Adam | epoch: 656 | loss: 0.06305 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2622 | total loss: [1m[32m0.06182[0m[0m | time: 0.007s
[2K
| Adam | epoch: 656 | loss: 0.06182 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2623 | total loss: [1m[32m0.06682[0m[0m | time: 0.009s
[2K
| Adam | epoch: 656 | loss: 0.06682 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2624 | total loss: [1m[32m0.06743[0m[0m | time: 0.012s
[2K
| Adam | epoch: 656 | loss: 0.06743 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2625 | total loss: [1m[32m0.07435[0m[0m | time: 0.003s
[2K
| Adam | epoch: 657 | loss: 0.07435 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2626 | total loss: [1m[32m0.08059[0m[0m | time: 0.005s
[2K
| Adam | epoch: 657 | loss: 0.08059 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2627 | total loss: [1m[32m0.07565[0m[0m | time: 0.009s
[2K
| Adam | epoch: 657 | loss: 0.07565 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2628 | total loss: [1m[32m0.07295[0m[0m | time: 0.012s
[2K
| Adam | epoch: 657 | loss: 0.07295 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2629 | total loss: [1m[32m0.07649[0m[0m | time: 0.003s
[2K
| Adam | epoch: 658 | loss: 0.07649 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2630 | total loss: [1m[32m0.07156[0m[0m | time: 0.005s
[2K
| Adam | epoch: 658 | loss: 0.07156 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2631 | total loss: [1m[32m0.06710[0m[0m | time: 0.008s
[2K
| Adam | epoch: 658 | loss: 0.06710 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2632 | total loss: [1m[32m0.06520[0m[0m | time: 0.012s
[2K
| Adam | epoch: 658 | loss: 0.06520 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2633 | total loss: [1m[32m0.06492[0m[0m | time: 0.005s
[2K
| Adam | epoch: 659 | loss: 0.06492 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2634 | total loss: [1m[32m0.07100[0m[0m | time: 0.007s
[2K
| Adam | epoch: 659 | loss: 0.07100 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2635 | total loss: [1m[32m0.06799[0m[0m | time: 0.010s
[2K
| Adam | epoch: 659 | loss: 0.06799 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2636 | total loss: [1m[32m0.06527[0m[0m | time: 0.014s
[2K
| Adam | epoch: 659 | loss: 0.06527 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2637 | total loss: [1m[32m0.06361[0m[0m | time: 0.002s
[2K
| Adam | epoch: 660 | loss: 0.06361 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2638 | total loss: [1m[32m0.06055[0m[0m | time: 0.005s
[2K
| Adam | epoch: 660 | loss: 0.06055 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2639 | total loss: [1m[32m0.05733[0m[0m | time: 0.007s
[2K
| Adam | epoch: 660 | loss: 0.05733 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2640 | total loss: [1m[32m0.06320[0m[0m | time: 0.009s
[2K
| Adam | epoch: 660 | loss: 0.06320 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2641 | total loss: [1m[32m0.06843[0m[0m | time: 0.002s
[2K
| Adam | epoch: 661 | loss: 0.06843 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2642 | total loss: [1m[32m0.06818[0m[0m | time: 0.005s
[2K
| Adam | epoch: 661 | loss: 0.06818 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2643 | total loss: [1m[32m0.06789[0m[0m | time: 0.007s
[2K
| Adam | epoch: 661 | loss: 0.06789 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2644 | total loss: [1m[32m0.06443[0m[0m | time: 0.010s
[2K
| Adam | epoch: 661 | loss: 0.06443 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2645 | total loss: [1m[32m0.06882[0m[0m | time: 0.002s
[2K
| Adam | epoch: 662 | loss: 0.06882 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2646 | total loss: [1m[32m0.07270[0m[0m | time: 0.005s
[2K
| Adam | epoch: 662 | loss: 0.07270 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2647 | total loss: [1m[32m0.06980[0m[0m | time: 0.007s
[2K
| Adam | epoch: 662 | loss: 0.06980 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2648 | total loss: [1m[32m0.07138[0m[0m | time: 0.010s
[2K
| Adam | epoch: 662 | loss: 0.07138 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2649 | total loss: [1m[32m0.07160[0m[0m | time: 0.008s
[2K
| Adam | epoch: 663 | loss: 0.07160 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2650 | total loss: [1m[32m0.06956[0m[0m | time: 0.010s
[2K
| Adam | epoch: 663 | loss: 0.06956 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2651 | total loss: [1m[32m0.06770[0m[0m | time: 0.012s
[2K
| Adam | epoch: 663 | loss: 0.06770 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2652 | total loss: [1m[32m0.06580[0m[0m | time: 0.014s
[2K
| Adam | epoch: 663 | loss: 0.06580 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2653 | total loss: [1m[32m0.06658[0m[0m | time: 0.002s
[2K
| Adam | epoch: 664 | loss: 0.06658 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2654 | total loss: [1m[32m0.07204[0m[0m | time: 0.005s
[2K
| Adam | epoch: 664 | loss: 0.07204 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2655 | total loss: [1m[32m0.06879[0m[0m | time: 0.007s
[2K
| Adam | epoch: 664 | loss: 0.06879 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2656 | total loss: [1m[32m0.06584[0m[0m | time: 0.009s
[2K
| Adam | epoch: 664 | loss: 0.06584 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2657 | total loss: [1m[32m0.06410[0m[0m | time: 0.003s
[2K
| Adam | epoch: 665 | loss: 0.06410 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2658 | total loss: [1m[32m0.06091[0m[0m | time: 0.005s
[2K
| Adam | epoch: 665 | loss: 0.06091 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2659 | total loss: [1m[32m0.06344[0m[0m | time: 0.008s
[2K
| Adam | epoch: 665 | loss: 0.06344 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2660 | total loss: [1m[32m0.06603[0m[0m | time: 0.011s
[2K
| Adam | epoch: 665 | loss: 0.06603 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2661 | total loss: [1m[32m0.06831[0m[0m | time: 0.002s
[2K
| Adam | epoch: 666 | loss: 0.06831 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2662 | total loss: [1m[32m0.06452[0m[0m | time: 0.005s
[2K
| Adam | epoch: 666 | loss: 0.06452 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2663 | total loss: [1m[32m0.06342[0m[0m | time: 0.007s
[2K
| Adam | epoch: 666 | loss: 0.06342 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2664 | total loss: [1m[32m0.06125[0m[0m | time: 0.009s
[2K
| Adam | epoch: 666 | loss: 0.06125 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2665 | total loss: [1m[32m0.05588[0m[0m | time: 0.002s
[2K
| Adam | epoch: 667 | loss: 0.05588 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2666 | total loss: [1m[32m0.05104[0m[0m | time: 0.005s
[2K
| Adam | epoch: 667 | loss: 0.05104 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2667 | total loss: [1m[32m0.05470[0m[0m | time: 0.007s
[2K
| Adam | epoch: 667 | loss: 0.05470 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2668 | total loss: [1m[32m0.05812[0m[0m | time: 0.011s
[2K
| Adam | epoch: 667 | loss: 0.05812 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2669 | total loss: [1m[32m0.05929[0m[0m | time: 0.004s
[2K
| Adam | epoch: 668 | loss: 0.05929 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2670 | total loss: [1m[32m0.05893[0m[0m | time: 0.007s
[2K
| Adam | epoch: 668 | loss: 0.05893 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2671 | total loss: [1m[32m0.05859[0m[0m | time: 0.010s
[2K
| Adam | epoch: 668 | loss: 0.05859 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2672 | total loss: [1m[32m0.06268[0m[0m | time: 0.012s
[2K
| Adam | epoch: 668 | loss: 0.06268 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2673 | total loss: [1m[32m0.05824[0m[0m | time: 0.003s
[2K
| Adam | epoch: 669 | loss: 0.05824 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2674 | total loss: [1m[32m0.06440[0m[0m | time: 0.006s
[2K
| Adam | epoch: 669 | loss: 0.06440 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2675 | total loss: [1m[32m0.06057[0m[0m | time: 0.009s
[2K
| Adam | epoch: 669 | loss: 0.06057 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2676 | total loss: [1m[32m0.05711[0m[0m | time: 0.011s
[2K
| Adam | epoch: 669 | loss: 0.05711 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2677 | total loss: [1m[32m0.05522[0m[0m | time: 0.003s
[2K
| Adam | epoch: 670 | loss: 0.05522 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2678 | total loss: [1m[32m0.05434[0m[0m | time: 0.005s
[2K
| Adam | epoch: 670 | loss: 0.05434 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2679 | total loss: [1m[32m0.05696[0m[0m | time: 0.008s
[2K
| Adam | epoch: 670 | loss: 0.05696 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2680 | total loss: [1m[32m0.05510[0m[0m | time: 0.010s
[2K
| Adam | epoch: 670 | loss: 0.05510 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2681 | total loss: [1m[32m0.05342[0m[0m | time: 0.002s
[2K
| Adam | epoch: 671 | loss: 0.05342 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2682 | total loss: [1m[32m0.05589[0m[0m | time: 0.021s
[2K
| Adam | epoch: 671 | loss: 0.05589 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2683 | total loss: [1m[32m0.05399[0m[0m | time: 0.023s
[2K
| Adam | epoch: 671 | loss: 0.05399 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2684 | total loss: [1m[32m0.05260[0m[0m | time: 0.025s
[2K
| Adam | epoch: 671 | loss: 0.05260 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2685 | total loss: [1m[32m0.04992[0m[0m | time: 0.003s
[2K
| Adam | epoch: 672 | loss: 0.04992 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2686 | total loss: [1m[32m0.04749[0m[0m | time: 0.006s
[2K
| Adam | epoch: 672 | loss: 0.04749 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2687 | total loss: [1m[32m0.04972[0m[0m | time: 0.009s
[2K
| Adam | epoch: 672 | loss: 0.04972 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2688 | total loss: [1m[32m0.05393[0m[0m | time: 0.013s
[2K
| Adam | epoch: 672 | loss: 0.05393 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2689 | total loss: [1m[32m0.05329[0m[0m | time: 0.003s
[2K
| Adam | epoch: 673 | loss: 0.05329 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2690 | total loss: [1m[32m0.05236[0m[0m | time: 0.006s
[2K
| Adam | epoch: 673 | loss: 0.05236 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2691 | total loss: [1m[32m0.05150[0m[0m | time: 0.008s
[2K
| Adam | epoch: 673 | loss: 0.05150 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2692 | total loss: [1m[32m0.05653[0m[0m | time: 0.010s
[2K
| Adam | epoch: 673 | loss: 0.05653 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2693 | total loss: [1m[32m0.05484[0m[0m | time: 0.003s
[2K
| Adam | epoch: 674 | loss: 0.05484 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2694 | total loss: [1m[32m0.05300[0m[0m | time: 0.006s
[2K
| Adam | epoch: 674 | loss: 0.05300 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2695 | total loss: [1m[32m0.04874[0m[0m | time: 0.009s
[2K
| Adam | epoch: 674 | loss: 0.04874 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2696 | total loss: [1m[32m0.04490[0m[0m | time: 0.012s
[2K
| Adam | epoch: 674 | loss: 0.04490 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2697 | total loss: [1m[32m0.05040[0m[0m | time: 0.002s
[2K
| Adam | epoch: 675 | loss: 0.05040 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2698 | total loss: [1m[32m0.05264[0m[0m | time: 0.005s
[2K
| Adam | epoch: 675 | loss: 0.05264 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2699 | total loss: [1m[32m0.05197[0m[0m | time: 0.008s
[2K
| Adam | epoch: 675 | loss: 0.05197 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2700 | total loss: [1m[32m0.04845[0m[0m | time: 0.010s
[2K
| Adam | epoch: 675 | loss: 0.04845 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2701 | total loss: [1m[32m0.04526[0m[0m | time: 0.002s
[2K
| Adam | epoch: 676 | loss: 0.04526 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2702 | total loss: [1m[32m0.05247[0m[0m | time: 0.005s
[2K
| Adam | epoch: 676 | loss: 0.05247 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2703 | total loss: [1m[32m0.05127[0m[0m | time: 0.008s
[2K
| Adam | epoch: 676 | loss: 0.05127 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2704 | total loss: [1m[32m0.05182[0m[0m | time: 0.011s
[2K
| Adam | epoch: 676 | loss: 0.05182 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2705 | total loss: [1m[32m0.05146[0m[0m | time: 0.003s
[2K
| Adam | epoch: 677 | loss: 0.05146 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2706 | total loss: [1m[32m0.05107[0m[0m | time: 0.006s
[2K
| Adam | epoch: 677 | loss: 0.05107 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2707 | total loss: [1m[32m0.04868[0m[0m | time: 0.009s
[2K
| Adam | epoch: 677 | loss: 0.04868 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2708 | total loss: [1m[32m0.05383[0m[0m | time: 0.011s
[2K
| Adam | epoch: 677 | loss: 0.05383 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2709 | total loss: [1m[32m0.05169[0m[0m | time: 0.029s
[2K
| Adam | epoch: 678 | loss: 0.05169 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2710 | total loss: [1m[32m0.04808[0m[0m | time: 0.031s
[2K
| Adam | epoch: 678 | loss: 0.04808 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2711 | total loss: [1m[32m0.04482[0m[0m | time: 0.034s
[2K
| Adam | epoch: 678 | loss: 0.04482 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2712 | total loss: [1m[32m0.04724[0m[0m | time: 0.036s
[2K
| Adam | epoch: 678 | loss: 0.04724 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2713 | total loss: [1m[32m0.05252[0m[0m | time: 0.002s
[2K
| Adam | epoch: 679 | loss: 0.05252 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2714 | total loss: [1m[32m0.05025[0m[0m | time: 0.005s
[2K
| Adam | epoch: 679 | loss: 0.05025 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2715 | total loss: [1m[32m0.05225[0m[0m | time: 0.008s
[2K
| Adam | epoch: 679 | loss: 0.05225 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2716 | total loss: [1m[32m0.05398[0m[0m | time: 0.010s
[2K
| Adam | epoch: 679 | loss: 0.05398 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2717 | total loss: [1m[32m0.05703[0m[0m | time: 0.002s
[2K
| Adam | epoch: 680 | loss: 0.05703 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2718 | total loss: [1m[32m0.05668[0m[0m | time: 0.005s
[2K
| Adam | epoch: 680 | loss: 0.05668 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2719 | total loss: [1m[32m0.05470[0m[0m | time: 0.008s
[2K
| Adam | epoch: 680 | loss: 0.05470 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2720 | total loss: [1m[32m0.06198[0m[0m | time: 0.011s
[2K
| Adam | epoch: 680 | loss: 0.06198 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2721 | total loss: [1m[32m0.06852[0m[0m | time: 0.002s
[2K
| Adam | epoch: 681 | loss: 0.06852 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2722 | total loss: [1m[32m0.06428[0m[0m | time: 0.005s
[2K
| Adam | epoch: 681 | loss: 0.06428 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2723 | total loss: [1m[32m0.06448[0m[0m | time: 0.007s
[2K
| Adam | epoch: 681 | loss: 0.06448 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2724 | total loss: [1m[32m0.06079[0m[0m | time: 0.010s
[2K
| Adam | epoch: 681 | loss: 0.06079 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2725 | total loss: [1m[32m0.05768[0m[0m | time: 0.002s
[2K
| Adam | epoch: 682 | loss: 0.05768 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2726 | total loss: [1m[32m0.05486[0m[0m | time: 0.005s
[2K
| Adam | epoch: 682 | loss: 0.05486 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2727 | total loss: [1m[32m0.05518[0m[0m | time: 0.007s
[2K
| Adam | epoch: 682 | loss: 0.05518 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2728 | total loss: [1m[32m0.06000[0m[0m | time: 0.010s
[2K
| Adam | epoch: 682 | loss: 0.06000 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2729 | total loss: [1m[32m0.05916[0m[0m | time: 0.002s
[2K
| Adam | epoch: 683 | loss: 0.05916 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2730 | total loss: [1m[32m0.05655[0m[0m | time: 0.005s
[2K
| Adam | epoch: 683 | loss: 0.05655 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2731 | total loss: [1m[32m0.05417[0m[0m | time: 0.007s
[2K
| Adam | epoch: 683 | loss: 0.05417 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2732 | total loss: [1m[32m0.05185[0m[0m | time: 0.009s
[2K
| Adam | epoch: 683 | loss: 0.05185 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2733 | total loss: [1m[32m0.05705[0m[0m | time: 0.003s
[2K
| Adam | epoch: 684 | loss: 0.05705 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2734 | total loss: [1m[32m0.05656[0m[0m | time: 0.005s
[2K
| Adam | epoch: 684 | loss: 0.05656 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2735 | total loss: [1m[32m0.06271[0m[0m | time: 0.008s
[2K
| Adam | epoch: 684 | loss: 0.06271 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2736 | total loss: [1m[32m0.06821[0m[0m | time: 0.011s
[2K
| Adam | epoch: 684 | loss: 0.06821 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2737 | total loss: [1m[32m0.06537[0m[0m | time: 0.002s
[2K
| Adam | epoch: 685 | loss: 0.06537 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2738 | total loss: [1m[32m0.06282[0m[0m | time: 0.005s
[2K
| Adam | epoch: 685 | loss: 0.06282 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2739 | total loss: [1m[32m0.06659[0m[0m | time: 0.007s
[2K
| Adam | epoch: 685 | loss: 0.06659 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2740 | total loss: [1m[32m0.06530[0m[0m | time: 0.009s
[2K
| Adam | epoch: 685 | loss: 0.06530 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2741 | total loss: [1m[32m0.06412[0m[0m | time: 0.003s
[2K
| Adam | epoch: 686 | loss: 0.06412 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2742 | total loss: [1m[32m0.06172[0m[0m | time: 0.005s
[2K
| Adam | epoch: 686 | loss: 0.06172 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2743 | total loss: [1m[32m0.05857[0m[0m | time: 0.008s
[2K
| Adam | epoch: 686 | loss: 0.05857 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2744 | total loss: [1m[32m0.05632[0m[0m | time: 0.010s
[2K
| Adam | epoch: 686 | loss: 0.05632 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2745 | total loss: [1m[32m0.05401[0m[0m | time: 0.002s
[2K
| Adam | epoch: 687 | loss: 0.05401 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2746 | total loss: [1m[32m0.05190[0m[0m | time: 0.005s
[2K
| Adam | epoch: 687 | loss: 0.05190 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2747 | total loss: [1m[32m0.05103[0m[0m | time: 0.008s
[2K
| Adam | epoch: 687 | loss: 0.05103 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2748 | total loss: [1m[32m0.05620[0m[0m | time: 0.010s
[2K
| Adam | epoch: 687 | loss: 0.05620 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2749 | total loss: [1m[32m0.05357[0m[0m | time: 0.002s
[2K
| Adam | epoch: 688 | loss: 0.05357 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2750 | total loss: [1m[32m0.06369[0m[0m | time: 0.004s
[2K
| Adam | epoch: 688 | loss: 0.06369 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2751 | total loss: [1m[32m0.07275[0m[0m | time: 0.006s
[2K
| Adam | epoch: 688 | loss: 0.07275 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2752 | total loss: [1m[32m0.06793[0m[0m | time: 0.009s
[2K
| Adam | epoch: 688 | loss: 0.06793 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2753 | total loss: [1m[32m0.06621[0m[0m | time: 0.003s
[2K
| Adam | epoch: 689 | loss: 0.06621 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2754 | total loss: [1m[32m0.06439[0m[0m | time: 0.005s
[2K
| Adam | epoch: 689 | loss: 0.06439 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2755 | total loss: [1m[32m0.06321[0m[0m | time: 0.007s
[2K
| Adam | epoch: 689 | loss: 0.06321 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2756 | total loss: [1m[32m0.06213[0m[0m | time: 0.010s
[2K
| Adam | epoch: 689 | loss: 0.06213 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2757 | total loss: [1m[32m0.05771[0m[0m | time: 0.002s
[2K
| Adam | epoch: 690 | loss: 0.05771 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2758 | total loss: [1m[32m0.06212[0m[0m | time: 0.005s
[2K
| Adam | epoch: 690 | loss: 0.06212 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2759 | total loss: [1m[32m0.06204[0m[0m | time: 0.008s
[2K
| Adam | epoch: 690 | loss: 0.06204 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2760 | total loss: [1m[32m0.05942[0m[0m | time: 0.011s
[2K
| Adam | epoch: 690 | loss: 0.05942 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2761 | total loss: [1m[32m0.05703[0m[0m | time: 0.003s
[2K
| Adam | epoch: 691 | loss: 0.05703 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2762 | total loss: [1m[32m0.05413[0m[0m | time: 0.005s
[2K
| Adam | epoch: 691 | loss: 0.05413 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2763 | total loss: [1m[32m0.05748[0m[0m | time: 0.008s
[2K
| Adam | epoch: 691 | loss: 0.05748 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2764 | total loss: [1m[32m0.05602[0m[0m | time: 0.010s
[2K
| Adam | epoch: 691 | loss: 0.05602 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2765 | total loss: [1m[32m0.05205[0m[0m | time: 0.002s
[2K
| Adam | epoch: 692 | loss: 0.05205 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2766 | total loss: [1m[32m0.04847[0m[0m | time: 0.005s
[2K
| Adam | epoch: 692 | loss: 0.04847 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2767 | total loss: [1m[32m0.05331[0m[0m | time: 0.007s
[2K
| Adam | epoch: 692 | loss: 0.05331 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2768 | total loss: [1m[32m0.05270[0m[0m | time: 0.009s
[2K
| Adam | epoch: 692 | loss: 0.05270 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2769 | total loss: [1m[32m0.05259[0m[0m | time: 0.003s
[2K
| Adam | epoch: 693 | loss: 0.05259 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2770 | total loss: [1m[32m0.04794[0m[0m | time: 0.005s
[2K
| Adam | epoch: 693 | loss: 0.04794 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2771 | total loss: [1m[32m0.04376[0m[0m | time: 0.008s
[2K
| Adam | epoch: 693 | loss: 0.04376 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2772 | total loss: [1m[32m0.04850[0m[0m | time: 0.010s
[2K
| Adam | epoch: 693 | loss: 0.04850 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2773 | total loss: [1m[32m0.04861[0m[0m | time: 0.003s
[2K
| Adam | epoch: 694 | loss: 0.04861 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2774 | total loss: [1m[32m0.04591[0m[0m | time: 0.005s
[2K
| Adam | epoch: 694 | loss: 0.04591 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2775 | total loss: [1m[32m0.04766[0m[0m | time: 0.008s
[2K
| Adam | epoch: 694 | loss: 0.04766 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2776 | total loss: [1m[32m0.04922[0m[0m | time: 0.010s
[2K
| Adam | epoch: 694 | loss: 0.04922 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2777 | total loss: [1m[32m0.05497[0m[0m | time: 0.002s
[2K
| Adam | epoch: 695 | loss: 0.05497 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2778 | total loss: [1m[32m0.05220[0m[0m | time: 0.005s
[2K
| Adam | epoch: 695 | loss: 0.05220 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2779 | total loss: [1m[32m0.05428[0m[0m | time: 0.008s
[2K
| Adam | epoch: 695 | loss: 0.05428 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2780 | total loss: [1m[32m0.05522[0m[0m | time: 0.011s
[2K
| Adam | epoch: 695 | loss: 0.05522 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2781 | total loss: [1m[32m0.05604[0m[0m | time: 0.002s
[2K
| Adam | epoch: 696 | loss: 0.05604 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2782 | total loss: [1m[32m0.05424[0m[0m | time: 0.005s
[2K
| Adam | epoch: 696 | loss: 0.05424 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2783 | total loss: [1m[32m0.05314[0m[0m | time: 0.007s
[2K
| Adam | epoch: 696 | loss: 0.05314 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2784 | total loss: [1m[32m0.05305[0m[0m | time: 0.010s
[2K
| Adam | epoch: 696 | loss: 0.05305 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2785 | total loss: [1m[32m0.05256[0m[0m | time: 0.002s
[2K
| Adam | epoch: 697 | loss: 0.05256 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2786 | total loss: [1m[32m0.05212[0m[0m | time: 0.005s
[2K
| Adam | epoch: 697 | loss: 0.05212 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2787 | total loss: [1m[32m0.04933[0m[0m | time: 0.007s
[2K
| Adam | epoch: 697 | loss: 0.04933 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2788 | total loss: [1m[32m0.05305[0m[0m | time: 0.009s
[2K
| Adam | epoch: 697 | loss: 0.05305 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2789 | total loss: [1m[32m0.05921[0m[0m | time: 0.003s
[2K
| Adam | epoch: 698 | loss: 0.05921 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2790 | total loss: [1m[32m0.05654[0m[0m | time: 0.005s
[2K
| Adam | epoch: 698 | loss: 0.05654 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2791 | total loss: [1m[32m0.05412[0m[0m | time: 0.008s
[2K
| Adam | epoch: 698 | loss: 0.05412 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2792 | total loss: [1m[32m0.05302[0m[0m | time: 0.010s
[2K
| Adam | epoch: 698 | loss: 0.05302 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2793 | total loss: [1m[32m0.04907[0m[0m | time: 0.002s
[2K
| Adam | epoch: 699 | loss: 0.04907 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2794 | total loss: [1m[32m0.05228[0m[0m | time: 0.005s
[2K
| Adam | epoch: 699 | loss: 0.05228 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2795 | total loss: [1m[32m0.05269[0m[0m | time: 0.007s
[2K
| Adam | epoch: 699 | loss: 0.05269 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2796 | total loss: [1m[32m0.05302[0m[0m | time: 0.010s
[2K
| Adam | epoch: 699 | loss: 0.05302 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2797 | total loss: [1m[32m0.04999[0m[0m | time: 0.002s
[2K
| Adam | epoch: 700 | loss: 0.04999 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2798 | total loss: [1m[32m0.05017[0m[0m | time: 0.005s
[2K
| Adam | epoch: 700 | loss: 0.05017 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2799 | total loss: [1m[32m0.04816[0m[0m | time: 0.007s
[2K
| Adam | epoch: 700 | loss: 0.04816 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2800 | total loss: [1m[32m0.05496[0m[0m | time: 0.009s
[2K
| Adam | epoch: 700 | loss: 0.05496 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2801 | total loss: [1m[32m0.06107[0m[0m | time: 0.002s
[2K
| Adam | epoch: 701 | loss: 0.06107 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2802 | total loss: [1m[32m0.06060[0m[0m | time: 0.005s
[2K
| Adam | epoch: 701 | loss: 0.06060 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2803 | total loss: [1m[32m0.05756[0m[0m | time: 0.007s
[2K
| Adam | epoch: 701 | loss: 0.05756 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2804 | total loss: [1m[32m0.06048[0m[0m | time: 0.010s
[2K
| Adam | epoch: 701 | loss: 0.06048 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2805 | total loss: [1m[32m0.05628[0m[0m | time: 0.002s
[2K
| Adam | epoch: 702 | loss: 0.05628 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2806 | total loss: [1m[32m0.05249[0m[0m | time: 0.005s
[2K
| Adam | epoch: 702 | loss: 0.05249 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2807 | total loss: [1m[32m0.04974[0m[0m | time: 0.007s
[2K
| Adam | epoch: 702 | loss: 0.04974 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2808 | total loss: [1m[32m0.05134[0m[0m | time: 0.009s
[2K
| Adam | epoch: 702 | loss: 0.05134 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2809 | total loss: [1m[32m0.05505[0m[0m | time: 0.003s
[2K
| Adam | epoch: 703 | loss: 0.05505 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2810 | total loss: [1m[32m0.05313[0m[0m | time: 0.005s
[2K
| Adam | epoch: 703 | loss: 0.05313 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2811 | total loss: [1m[32m0.05138[0m[0m | time: 0.008s
[2K
| Adam | epoch: 703 | loss: 0.05138 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2812 | total loss: [1m[32m0.05021[0m[0m | time: 0.010s
[2K
| Adam | epoch: 703 | loss: 0.05021 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2813 | total loss: [1m[32m0.04888[0m[0m | time: 0.002s
[2K
| Adam | epoch: 704 | loss: 0.04888 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2814 | total loss: [1m[32m0.05100[0m[0m | time: 0.005s
[2K
| Adam | epoch: 704 | loss: 0.05100 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2815 | total loss: [1m[32m0.04976[0m[0m | time: 0.008s
[2K
| Adam | epoch: 704 | loss: 0.04976 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2816 | total loss: [1m[32m0.04860[0m[0m | time: 0.010s
[2K
| Adam | epoch: 704 | loss: 0.04860 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2817 | total loss: [1m[32m0.04875[0m[0m | time: 0.002s
[2K
| Adam | epoch: 705 | loss: 0.04875 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2818 | total loss: [1m[32m0.04804[0m[0m | time: 0.005s
[2K
| Adam | epoch: 705 | loss: 0.04804 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2819 | total loss: [1m[32m0.04660[0m[0m | time: 0.008s
[2K
| Adam | epoch: 705 | loss: 0.04660 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2820 | total loss: [1m[32m0.05031[0m[0m | time: 0.010s
[2K
| Adam | epoch: 705 | loss: 0.05031 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2821 | total loss: [1m[32m0.05361[0m[0m | time: 0.019s
[2K
| Adam | epoch: 706 | loss: 0.05361 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2822 | total loss: [1m[32m0.05600[0m[0m | time: 0.022s
[2K
| Adam | epoch: 706 | loss: 0.05600 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2823 | total loss: [1m[32m0.05251[0m[0m | time: 0.024s
[2K
| Adam | epoch: 706 | loss: 0.05251 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2824 | total loss: [1m[32m0.04927[0m[0m | time: 0.027s
[2K
| Adam | epoch: 706 | loss: 0.04927 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2825 | total loss: [1m[32m0.04992[0m[0m | time: 0.002s
[2K
| Adam | epoch: 707 | loss: 0.04992 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2826 | total loss: [1m[32m0.05048[0m[0m | time: 0.005s
[2K
| Adam | epoch: 707 | loss: 0.05048 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2827 | total loss: [1m[32m0.05086[0m[0m | time: 0.008s
[2K
| Adam | epoch: 707 | loss: 0.05086 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2828 | total loss: [1m[32m0.05319[0m[0m | time: 0.011s
[2K
| Adam | epoch: 707 | loss: 0.05319 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2829 | total loss: [1m[32m0.05008[0m[0m | time: 0.003s
[2K
| Adam | epoch: 708 | loss: 0.05008 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2830 | total loss: [1m[32m0.04757[0m[0m | time: 0.006s
[2K
| Adam | epoch: 708 | loss: 0.04757 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2831 | total loss: [1m[32m0.04530[0m[0m | time: 0.009s
[2K
| Adam | epoch: 708 | loss: 0.04530 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2832 | total loss: [1m[32m0.04570[0m[0m | time: 0.011s
[2K
| Adam | epoch: 708 | loss: 0.04570 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2833 | total loss: [1m[32m0.05065[0m[0m | time: 0.002s
[2K
| Adam | epoch: 709 | loss: 0.05065 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2834 | total loss: [1m[32m0.05378[0m[0m | time: 0.006s
[2K
| Adam | epoch: 709 | loss: 0.05378 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2835 | total loss: [1m[32m0.05030[0m[0m | time: 0.009s
[2K
| Adam | epoch: 709 | loss: 0.05030 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2836 | total loss: [1m[32m0.04715[0m[0m | time: 0.011s
[2K
| Adam | epoch: 709 | loss: 0.04715 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2837 | total loss: [1m[32m0.04674[0m[0m | time: 0.003s
[2K
| Adam | epoch: 710 | loss: 0.04674 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2838 | total loss: [1m[32m0.04652[0m[0m | time: 0.005s
[2K
| Adam | epoch: 710 | loss: 0.04652 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2839 | total loss: [1m[32m0.04616[0m[0m | time: 0.008s
[2K
| Adam | epoch: 710 | loss: 0.04616 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2840 | total loss: [1m[32m0.04679[0m[0m | time: 0.011s
[2K
| Adam | epoch: 710 | loss: 0.04679 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2841 | total loss: [1m[32m0.04733[0m[0m | time: 0.002s
[2K
| Adam | epoch: 711 | loss: 0.04733 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2842 | total loss: [1m[32m0.04997[0m[0m | time: 0.006s
[2K
| Adam | epoch: 711 | loss: 0.04997 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2843 | total loss: [1m[32m0.04806[0m[0m | time: 0.008s
[2K
| Adam | epoch: 711 | loss: 0.04806 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2844 | total loss: [1m[32m0.04761[0m[0m | time: 0.011s
[2K
| Adam | epoch: 711 | loss: 0.04761 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2845 | total loss: [1m[32m0.04537[0m[0m | time: 0.003s
[2K
| Adam | epoch: 712 | loss: 0.04537 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2846 | total loss: [1m[32m0.04334[0m[0m | time: 0.006s
[2K
| Adam | epoch: 712 | loss: 0.04334 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2847 | total loss: [1m[32m0.04945[0m[0m | time: 0.010s
[2K
| Adam | epoch: 712 | loss: 0.04945 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2848 | total loss: [1m[32m0.04607[0m[0m | time: 0.013s
[2K
| Adam | epoch: 712 | loss: 0.04607 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2849 | total loss: [1m[32m0.04524[0m[0m | time: 0.003s
[2K
| Adam | epoch: 713 | loss: 0.04524 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2850 | total loss: [1m[32m0.04481[0m[0m | time: 0.006s
[2K
| Adam | epoch: 713 | loss: 0.04481 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2851 | total loss: [1m[32m0.04439[0m[0m | time: 0.009s
[2K
| Adam | epoch: 713 | loss: 0.04439 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2852 | total loss: [1m[32m0.04320[0m[0m | time: 0.013s
[2K
| Adam | epoch: 713 | loss: 0.04320 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2853 | total loss: [1m[32m0.04712[0m[0m | time: 0.019s
[2K
| Adam | epoch: 714 | loss: 0.04712 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2854 | total loss: [1m[32m0.04480[0m[0m | time: 0.022s
[2K
| Adam | epoch: 714 | loss: 0.04480 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2855 | total loss: [1m[32m0.04330[0m[0m | time: 0.025s
[2K
| Adam | epoch: 714 | loss: 0.04330 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2856 | total loss: [1m[32m0.04192[0m[0m | time: 0.027s
[2K
| Adam | epoch: 714 | loss: 0.04192 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2857 | total loss: [1m[32m0.04535[0m[0m | time: 0.003s
[2K
| Adam | epoch: 715 | loss: 0.04535 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2858 | total loss: [1m[32m0.04682[0m[0m | time: 0.005s
[2K
| Adam | epoch: 715 | loss: 0.04682 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2859 | total loss: [1m[32m0.05047[0m[0m | time: 0.008s
[2K
| Adam | epoch: 715 | loss: 0.05047 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2860 | total loss: [1m[32m0.04785[0m[0m | time: 0.011s
[2K
| Adam | epoch: 715 | loss: 0.04785 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2861 | total loss: [1m[32m0.04549[0m[0m | time: 0.003s
[2K
| Adam | epoch: 716 | loss: 0.04549 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2862 | total loss: [1m[32m0.04409[0m[0m | time: 0.005s
[2K
| Adam | epoch: 716 | loss: 0.04409 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2863 | total loss: [1m[32m0.04440[0m[0m | time: 0.008s
[2K
| Adam | epoch: 716 | loss: 0.04440 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2864 | total loss: [1m[32m0.04537[0m[0m | time: 0.011s
[2K
| Adam | epoch: 716 | loss: 0.04537 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2865 | total loss: [1m[32m0.04384[0m[0m | time: 0.003s
[2K
| Adam | epoch: 717 | loss: 0.04384 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2866 | total loss: [1m[32m0.04243[0m[0m | time: 0.005s
[2K
| Adam | epoch: 717 | loss: 0.04243 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2867 | total loss: [1m[32m0.03918[0m[0m | time: 0.008s
[2K
| Adam | epoch: 717 | loss: 0.03918 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2868 | total loss: [1m[32m0.04462[0m[0m | time: 0.011s
[2K
| Adam | epoch: 717 | loss: 0.04462 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2869 | total loss: [1m[32m0.04339[0m[0m | time: 0.003s
[2K
| Adam | epoch: 718 | loss: 0.04339 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2870 | total loss: [1m[32m0.05266[0m[0m | time: 0.005s
[2K
| Adam | epoch: 718 | loss: 0.05266 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2871 | total loss: [1m[32m0.06095[0m[0m | time: 0.008s
[2K
| Adam | epoch: 718 | loss: 0.06095 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2872 | total loss: [1m[32m0.05874[0m[0m | time: 0.011s
[2K
| Adam | epoch: 718 | loss: 0.05874 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2873 | total loss: [1m[32m0.05478[0m[0m | time: 0.003s
[2K
| Adam | epoch: 719 | loss: 0.05478 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2874 | total loss: [1m[32m0.05146[0m[0m | time: 0.005s
[2K
| Adam | epoch: 719 | loss: 0.05146 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2875 | total loss: [1m[32m0.05046[0m[0m | time: 0.008s
[2K
| Adam | epoch: 719 | loss: 0.05046 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2876 | total loss: [1m[32m0.04953[0m[0m | time: 0.010s
[2K
| Adam | epoch: 719 | loss: 0.04953 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2877 | total loss: [1m[32m0.05428[0m[0m | time: 0.003s
[2K
| Adam | epoch: 720 | loss: 0.05428 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2878 | total loss: [1m[32m0.05174[0m[0m | time: 0.005s
[2K
| Adam | epoch: 720 | loss: 0.05174 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2879 | total loss: [1m[32m0.05188[0m[0m | time: 0.008s
[2K
| Adam | epoch: 720 | loss: 0.05188 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2880 | total loss: [1m[32m0.05040[0m[0m | time: 0.011s
[2K
| Adam | epoch: 720 | loss: 0.05040 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2881 | total loss: [1m[32m0.04907[0m[0m | time: 0.004s
[2K
| Adam | epoch: 721 | loss: 0.04907 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2882 | total loss: [1m[32m0.04628[0m[0m | time: 0.006s
[2K
| Adam | epoch: 721 | loss: 0.04628 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2883 | total loss: [1m[32m0.04910[0m[0m | time: 0.009s
[2K
| Adam | epoch: 721 | loss: 0.04910 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2884 | total loss: [1m[32m0.05066[0m[0m | time: 0.012s
[2K
| Adam | epoch: 721 | loss: 0.05066 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2885 | total loss: [1m[32m0.05258[0m[0m | time: 0.003s
[2K
| Adam | epoch: 722 | loss: 0.05258 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2886 | total loss: [1m[32m0.05423[0m[0m | time: 0.016s
[2K
| Adam | epoch: 722 | loss: 0.05423 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2887 | total loss: [1m[32m0.05297[0m[0m | time: 0.023s
[2K
| Adam | epoch: 722 | loss: 0.05297 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2888 | total loss: [1m[32m0.04988[0m[0m | time: 0.026s
[2K
| Adam | epoch: 722 | loss: 0.04988 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2889 | total loss: [1m[32m0.05009[0m[0m | time: 0.003s
[2K
| Adam | epoch: 723 | loss: 0.05009 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2890 | total loss: [1m[32m0.04740[0m[0m | time: 0.006s
[2K
| Adam | epoch: 723 | loss: 0.04740 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2891 | total loss: [1m[32m0.04497[0m[0m | time: 0.009s
[2K
| Adam | epoch: 723 | loss: 0.04497 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2892 | total loss: [1m[32m0.04779[0m[0m | time: 0.012s
[2K
| Adam | epoch: 723 | loss: 0.04779 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2893 | total loss: [1m[32m0.04602[0m[0m | time: 0.003s
[2K
| Adam | epoch: 724 | loss: 0.04602 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2894 | total loss: [1m[32m0.04315[0m[0m | time: 0.006s
[2K
| Adam | epoch: 724 | loss: 0.04315 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2895 | total loss: [1m[32m0.04277[0m[0m | time: 0.009s
[2K
| Adam | epoch: 724 | loss: 0.04277 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2896 | total loss: [1m[32m0.04240[0m[0m | time: 0.013s
[2K
| Adam | epoch: 724 | loss: 0.04240 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2897 | total loss: [1m[32m0.04219[0m[0m | time: 0.003s
[2K
| Adam | epoch: 725 | loss: 0.04219 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2898 | total loss: [1m[32m0.04659[0m[0m | time: 0.005s
[2K
| Adam | epoch: 725 | loss: 0.04659 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2899 | total loss: [1m[32m0.04392[0m[0m | time: 0.009s
[2K
| Adam | epoch: 725 | loss: 0.04392 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2900 | total loss: [1m[32m0.04105[0m[0m | time: 0.011s
[2K
| Adam | epoch: 725 | loss: 0.04105 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2901 | total loss: [1m[32m0.03847[0m[0m | time: 0.002s
[2K
| Adam | epoch: 726 | loss: 0.03847 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2902 | total loss: [1m[32m0.03927[0m[0m | time: 0.005s
[2K
| Adam | epoch: 726 | loss: 0.03927 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2903 | total loss: [1m[32m0.04449[0m[0m | time: 0.007s
[2K
| Adam | epoch: 726 | loss: 0.04449 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2904 | total loss: [1m[32m0.04648[0m[0m | time: 0.009s
[2K
| Adam | epoch: 726 | loss: 0.04648 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2905 | total loss: [1m[32m0.04260[0m[0m | time: 0.002s
[2K
| Adam | epoch: 727 | loss: 0.04260 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2906 | total loss: [1m[32m0.03911[0m[0m | time: 0.005s
[2K
| Adam | epoch: 727 | loss: 0.03911 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2907 | total loss: [1m[32m0.03774[0m[0m | time: 0.007s
[2K
| Adam | epoch: 727 | loss: 0.03774 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2908 | total loss: [1m[32m0.04117[0m[0m | time: 0.009s
[2K
| Adam | epoch: 727 | loss: 0.04117 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2909 | total loss: [1m[32m0.03986[0m[0m | time: 0.002s
[2K
| Adam | epoch: 728 | loss: 0.03986 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2910 | total loss: [1m[32m0.03739[0m[0m | time: 0.005s
[2K
| Adam | epoch: 728 | loss: 0.03739 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2911 | total loss: [1m[32m0.03517[0m[0m | time: 0.009s
[2K
| Adam | epoch: 728 | loss: 0.03517 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2912 | total loss: [1m[32m0.03736[0m[0m | time: 0.011s
[2K
| Adam | epoch: 728 | loss: 0.03736 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2913 | total loss: [1m[32m0.04071[0m[0m | time: 0.002s
[2K
| Adam | epoch: 729 | loss: 0.04071 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2914 | total loss: [1m[32m0.04171[0m[0m | time: 0.005s
[2K
| Adam | epoch: 729 | loss: 0.04171 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2915 | total loss: [1m[32m0.04183[0m[0m | time: 0.007s
[2K
| Adam | epoch: 729 | loss: 0.04183 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2916 | total loss: [1m[32m0.04189[0m[0m | time: 0.015s
[2K
| Adam | epoch: 729 | loss: 0.04189 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2917 | total loss: [1m[32m0.03894[0m[0m | time: 0.002s
[2K
| Adam | epoch: 730 | loss: 0.03894 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2918 | total loss: [1m[32m0.04258[0m[0m | time: 0.004s
[2K
| Adam | epoch: 730 | loss: 0.04258 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2919 | total loss: [1m[32m0.04237[0m[0m | time: 0.007s
[2K
| Adam | epoch: 730 | loss: 0.04237 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2920 | total loss: [1m[32m0.03978[0m[0m | time: 0.010s
[2K
| Adam | epoch: 730 | loss: 0.03978 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2921 | total loss: [1m[32m0.03745[0m[0m | time: 0.002s
[2K
| Adam | epoch: 731 | loss: 0.03745 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2922 | total loss: [1m[32m0.04287[0m[0m | time: 0.005s
[2K
| Adam | epoch: 731 | loss: 0.04287 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2923 | total loss: [1m[32m0.04071[0m[0m | time: 0.007s
[2K
| Adam | epoch: 731 | loss: 0.04071 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2924 | total loss: [1m[32m0.04029[0m[0m | time: 0.010s
[2K
| Adam | epoch: 731 | loss: 0.04029 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2925 | total loss: [1m[32m0.03869[0m[0m | time: 0.002s
[2K
| Adam | epoch: 732 | loss: 0.03869 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2926 | total loss: [1m[32m0.03725[0m[0m | time: 0.005s
[2K
| Adam | epoch: 732 | loss: 0.03725 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2927 | total loss: [1m[32m0.04149[0m[0m | time: 0.007s
[2K
| Adam | epoch: 732 | loss: 0.04149 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2928 | total loss: [1m[32m0.04049[0m[0m | time: 0.010s
[2K
| Adam | epoch: 732 | loss: 0.04049 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2929 | total loss: [1m[32m0.03794[0m[0m | time: 0.002s
[2K
| Adam | epoch: 733 | loss: 0.03794 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2930 | total loss: [1m[32m0.03589[0m[0m | time: 0.005s
[2K
| Adam | epoch: 733 | loss: 0.03589 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2931 | total loss: [1m[32m0.03403[0m[0m | time: 0.007s
[2K
| Adam | epoch: 733 | loss: 0.03403 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2932 | total loss: [1m[32m0.03637[0m[0m | time: 0.010s
[2K
| Adam | epoch: 733 | loss: 0.03637 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2933 | total loss: [1m[32m0.04060[0m[0m | time: 0.002s
[2K
| Adam | epoch: 734 | loss: 0.04060 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2934 | total loss: [1m[32m0.03917[0m[0m | time: 0.005s
[2K
| Adam | epoch: 734 | loss: 0.03917 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2935 | total loss: [1m[32m0.04588[0m[0m | time: 0.007s
[2K
| Adam | epoch: 734 | loss: 0.04588 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2936 | total loss: [1m[32m0.05189[0m[0m | time: 0.010s
[2K
| Adam | epoch: 734 | loss: 0.05189 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2937 | total loss: [1m[32m0.05144[0m[0m | time: 0.002s
[2K
| Adam | epoch: 735 | loss: 0.05144 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2938 | total loss: [1m[32m0.04847[0m[0m | time: 0.005s
[2K
| Adam | epoch: 735 | loss: 0.04847 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2939 | total loss: [1m[32m0.04892[0m[0m | time: 0.007s
[2K
| Adam | epoch: 735 | loss: 0.04892 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2940 | total loss: [1m[32m0.04568[0m[0m | time: 0.009s
[2K
| Adam | epoch: 735 | loss: 0.04568 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2941 | total loss: [1m[32m0.04276[0m[0m | time: 0.002s
[2K
| Adam | epoch: 736 | loss: 0.04276 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2942 | total loss: [1m[32m0.04648[0m[0m | time: 0.005s
[2K
| Adam | epoch: 736 | loss: 0.04648 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2943 | total loss: [1m[32m0.04354[0m[0m | time: 0.007s
[2K
| Adam | epoch: 736 | loss: 0.04354 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2944 | total loss: [1m[32m0.04101[0m[0m | time: 0.010s
[2K
| Adam | epoch: 736 | loss: 0.04101 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2945 | total loss: [1m[32m0.04122[0m[0m | time: 0.002s
[2K
| Adam | epoch: 737 | loss: 0.04122 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2946 | total loss: [1m[32m0.04138[0m[0m | time: 0.005s
[2K
| Adam | epoch: 737 | loss: 0.04138 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2947 | total loss: [1m[32m0.04446[0m[0m | time: 0.007s
[2K
| Adam | epoch: 737 | loss: 0.04446 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2948 | total loss: [1m[32m0.04430[0m[0m | time: 0.009s
[2K
| Adam | epoch: 737 | loss: 0.04430 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2949 | total loss: [1m[32m0.04208[0m[0m | time: 0.002s
[2K
| Adam | epoch: 738 | loss: 0.04208 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2950 | total loss: [1m[32m0.04127[0m[0m | time: 0.005s
[2K
| Adam | epoch: 738 | loss: 0.04127 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2951 | total loss: [1m[32m0.04051[0m[0m | time: 0.018s
[2K
| Adam | epoch: 738 | loss: 0.04051 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2952 | total loss: [1m[32m0.04502[0m[0m | time: 0.021s
[2K
| Adam | epoch: 738 | loss: 0.04502 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2953 | total loss: [1m[32m0.04354[0m[0m | time: 0.002s
[2K
| Adam | epoch: 739 | loss: 0.04354 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2954 | total loss: [1m[32m0.04423[0m[0m | time: 0.005s
[2K
| Adam | epoch: 739 | loss: 0.04423 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 2955 | total loss: [1m[32m0.04783[0m[0m | time: 0.007s
[2K
| Adam | epoch: 739 | loss: 0.04783 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 2956 | total loss: [1m[32m0.05104[0m[0m | time: 0.010s
[2K
| Adam | epoch: 739 | loss: 0.05104 - acc: 1.0000 -- iter: 29/29
--
Training Step: 2957 | total loss: [1m[32m0.04757[0m[0m | time: 0.003s
[2K
| Adam | epoch: 740 | loss: 0.04757 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 2958 | total loss: [1m[32m1.27767[0m[0m | time: 0.006s
[2K
| Adam | epoch: 740 | loss: 1.27767 - acc: 0.9000 -- iter: 16/29
[A[ATraining Step: 2959 | total loss: [1m[32m1.15295[0m[0m | time: 0.008s
[2K
| Adam | epoch: 740 | loss: 1.15295 - acc: 0.9100 -- iter: 24/29
[A[ATraining Step: 2960 | total loss: [1m[32m1.03833[0m[0m | time: 0.010s
[2K
| Adam | epoch: 740 | loss: 1.03833 - acc: 0.9190 -- iter: 29/29
--
Training Step: 2961 | total loss: [1m[32m0.93517[0m[0m | time: 0.002s
[2K
| Adam | epoch: 741 | loss: 0.93517 - acc: 0.9271 -- iter: 08/29
[A[ATraining Step: 2962 | total loss: [1m[32m0.85043[0m[0m | time: 0.005s
[2K
| Adam | epoch: 741 | loss: 0.85043 - acc: 0.9344 -- iter: 16/29
[A[ATraining Step: 2963 | total loss: [1m[32m0.76915[0m[0m | time: 0.008s
[2K
| Adam | epoch: 741 | loss: 0.76915 - acc: 0.9410 -- iter: 24/29
[A[ATraining Step: 2964 | total loss: [1m[32m0.69483[0m[0m | time: 0.010s
[2K
| Adam | epoch: 741 | loss: 0.69483 - acc: 0.9469 -- iter: 29/29
--
Training Step: 2965 | total loss: [1m[32m0.63109[0m[0m | time: 0.002s
[2K
| Adam | epoch: 742 | loss: 0.63109 - acc: 0.9522 -- iter: 08/29
[A[ATraining Step: 2966 | total loss: [1m[32m0.57371[0m[0m | time: 0.005s
[2K
| Adam | epoch: 742 | loss: 0.57371 - acc: 0.9570 -- iter: 16/29
[A[ATraining Step: 2967 | total loss: [1m[32m0.51772[0m[0m | time: 0.008s
[2K
| Adam | epoch: 742 | loss: 0.51772 - acc: 0.9613 -- iter: 24/29
[A[ATraining Step: 2968 | total loss: [1m[32m0.47476[0m[0m | time: 0.011s
[2K
| Adam | epoch: 742 | loss: 0.47476 - acc: 0.9651 -- iter: 29/29
--
Training Step: 2969 | total loss: [1m[32m0.43013[0m[0m | time: 0.002s
[2K
| Adam | epoch: 743 | loss: 0.43013 - acc: 0.9686 -- iter: 08/29
[A[ATraining Step: 2970 | total loss: [1m[32m0.39597[0m[0m | time: 0.005s
[2K
| Adam | epoch: 743 | loss: 0.39597 - acc: 0.9718 -- iter: 16/29
[A[ATraining Step: 2971 | total loss: [1m[32m0.36523[0m[0m | time: 0.007s
[2K
| Adam | epoch: 743 | loss: 0.36523 - acc: 0.9746 -- iter: 24/29
[A[ATraining Step: 2972 | total loss: [1m[32m0.33191[0m[0m | time: 0.011s
[2K
| Adam | epoch: 743 | loss: 0.33191 - acc: 0.9771 -- iter: 29/29
--
Training Step: 2973 | total loss: [1m[32m1.22742[0m[0m | time: 0.002s
[2K
| Adam | epoch: 744 | loss: 1.22742 - acc: 0.9044 -- iter: 08/29
[A[ATraining Step: 2974 | total loss: [1m[32m1.10707[0m[0m | time: 0.005s
[2K
| Adam | epoch: 744 | loss: 1.10707 - acc: 0.9140 -- iter: 16/29
[A[ATraining Step: 2975 | total loss: [1m[32m1.00092[0m[0m | time: 0.008s
[2K
| Adam | epoch: 744 | loss: 1.00092 - acc: 0.9226 -- iter: 24/29
[A[ATraining Step: 2976 | total loss: [1m[32m0.90537[0m[0m | time: 0.010s
[2K
| Adam | epoch: 744 | loss: 0.90537 - acc: 0.9303 -- iter: 29/29
--
Training Step: 2977 | total loss: [1m[32m0.81793[0m[0m | time: 0.003s
[2K
| Adam | epoch: 745 | loss: 0.81793 - acc: 0.9373 -- iter: 08/29
[A[ATraining Step: 2978 | total loss: [1m[32m1.39572[0m[0m | time: 0.005s
[2K
| Adam | epoch: 745 | loss: 1.39572 - acc: 0.8686 -- iter: 16/29
[A[ATraining Step: 2979 | total loss: [1m[32m1.26286[0m[0m | time: 0.008s
[2K
| Adam | epoch: 745 | loss: 1.26286 - acc: 0.8817 -- iter: 24/29
[A[ATraining Step: 2980 | total loss: [1m[32m1.14203[0m[0m | time: 0.010s
[2K
| Adam | epoch: 745 | loss: 1.14203 - acc: 0.8935 -- iter: 29/29
--
Training Step: 2981 | total loss: [1m[32m1.03332[0m[0m | time: 0.002s
[2K
| Adam | epoch: 746 | loss: 1.03332 - acc: 0.9042 -- iter: 08/29
[A[ATraining Step: 2982 | total loss: [1m[32m0.93268[0m[0m | time: 0.027s
[2K
| Adam | epoch: 746 | loss: 0.93268 - acc: 0.9138 -- iter: 16/29
[A[ATraining Step: 2983 | total loss: [1m[32m0.84375[0m[0m | time: 0.030s
[2K
| Adam | epoch: 746 | loss: 0.84375 - acc: 0.9224 -- iter: 24/29
[A[ATraining Step: 2984 | total loss: [1m[32m0.76104[0m[0m | time: 0.032s
[2K
| Adam | epoch: 746 | loss: 0.76104 - acc: 0.9301 -- iter: 29/29
--
Training Step: 2985 | total loss: [1m[32m0.69590[0m[0m | time: 0.002s
[2K
| Adam | epoch: 747 | loss: 0.69590 - acc: 0.9371 -- iter: 08/29
[A[ATraining Step: 2986 | total loss: [1m[32m0.63736[0m[0m | time: 0.004s
[2K
| Adam | epoch: 747 | loss: 0.63736 - acc: 0.9434 -- iter: 16/29
[A[ATraining Step: 2987 | total loss: [1m[32m0.57968[0m[0m | time: 0.007s
[2K
| Adam | epoch: 747 | loss: 0.57968 - acc: 0.9491 -- iter: 24/29
[A[ATraining Step: 2988 | total loss: [1m[32m0.52468[0m[0m | time: 0.009s
[2K
| Adam | epoch: 747 | loss: 0.52468 - acc: 0.9542 -- iter: 29/29
--
Training Step: 2989 | total loss: [1m[32m0.47382[0m[0m | time: 0.002s
[2K
| Adam | epoch: 748 | loss: 0.47382 - acc: 0.9588 -- iter: 08/29
[A[ATraining Step: 2990 | total loss: [1m[32m0.42861[0m[0m | time: 0.005s
[2K
| Adam | epoch: 748 | loss: 0.42861 - acc: 0.9629 -- iter: 16/29
[A[ATraining Step: 2991 | total loss: [1m[32m0.38791[0m[0m | time: 0.007s
[2K
| Adam | epoch: 748 | loss: 0.38791 - acc: 0.9666 -- iter: 24/29
[A[ATraining Step: 2992 | total loss: [1m[32m0.35947[0m[0m | time: 0.009s
[2K
| Adam | epoch: 748 | loss: 0.35947 - acc: 0.9699 -- iter: 29/29
--
Training Step: 2993 | total loss: [1m[32m0.32796[0m[0m | time: 0.002s
[2K
| Adam | epoch: 749 | loss: 0.32796 - acc: 0.9729 -- iter: 08/29
[A[ATraining Step: 2994 | total loss: [1m[32m0.29929[0m[0m | time: 0.004s
[2K
| Adam | epoch: 749 | loss: 0.29929 - acc: 0.9756 -- iter: 16/29
[A[ATraining Step: 2995 | total loss: [1m[32m0.28057[0m[0m | time: 0.007s
[2K
| Adam | epoch: 749 | loss: 0.28057 - acc: 0.9781 -- iter: 24/29
[A[ATraining Step: 2996 | total loss: [1m[32m0.26365[0m[0m | time: 0.009s
[2K
| Adam | epoch: 749 | loss: 0.26365 - acc: 0.9803 -- iter: 29/29
--
Training Step: 2997 | total loss: [1m[32m0.23901[0m[0m | time: 0.002s
[2K
| Adam | epoch: 750 | loss: 0.23901 - acc: 0.9822 -- iter: 08/29
[A[ATraining Step: 2998 | total loss: [1m[32m0.21999[0m[0m | time: 0.005s
[2K
| Adam | epoch: 750 | loss: 0.21999 - acc: 0.9840 -- iter: 16/29
[A[ATraining Step: 2999 | total loss: [1m[32m0.19976[0m[0m | time: 0.007s
[2K
| Adam | epoch: 750 | loss: 0.19976 - acc: 0.9856 -- iter: 24/29
[A[ATraining Step: 3000 | total loss: [1m[32m0.18208[0m[0m | time: 0.010s
[2K
| Adam | epoch: 750 | loss: 0.18208 - acc: 0.9871 -- iter: 29/29
--
Training Step: 3001 | total loss: [1m[32m0.16613[0m[0m | time: 0.002s
[2K
| Adam | epoch: 751 | loss: 0.16613 - acc: 0.9884 -- iter: 08/29
[A[ATraining Step: 3002 | total loss: [1m[32m0.15792[0m[0m | time: 0.005s
[2K
| Adam | epoch: 751 | loss: 0.15792 - acc: 0.9895 -- iter: 16/29
[A[ATraining Step: 3003 | total loss: [1m[32m0.14792[0m[0m | time: 0.007s
[2K
| Adam | epoch: 751 | loss: 0.14792 - acc: 0.9906 -- iter: 24/29
[A[ATraining Step: 3004 | total loss: [1m[32m0.13542[0m[0m | time: 0.010s
[2K
| Adam | epoch: 751 | loss: 0.13542 - acc: 0.9915 -- iter: 29/29
--
Training Step: 3005 | total loss: [1m[32m0.13251[0m[0m | time: 0.002s
[2K
| Adam | epoch: 752 | loss: 0.13251 - acc: 0.9924 -- iter: 08/29
[A[ATraining Step: 3006 | total loss: [1m[32m0.12987[0m[0m | time: 0.005s
[2K
| Adam | epoch: 752 | loss: 0.12987 - acc: 0.9931 -- iter: 16/29
[A[ATraining Step: 3007 | total loss: [1m[32m0.12353[0m[0m | time: 0.007s
[2K
| Adam | epoch: 752 | loss: 0.12353 - acc: 0.9938 -- iter: 24/29
[A[ATraining Step: 3008 | total loss: [1m[32m0.11286[0m[0m | time: 0.027s
[2K
| Adam | epoch: 752 | loss: 0.11286 - acc: 0.9944 -- iter: 29/29
--
Training Step: 3009 | total loss: [1m[32m0.10576[0m[0m | time: 0.002s
[2K
| Adam | epoch: 753 | loss: 0.10576 - acc: 0.9950 -- iter: 08/29
[A[ATraining Step: 3010 | total loss: [1m[32m0.10660[0m[0m | time: 0.005s
[2K
| Adam | epoch: 753 | loss: 0.10660 - acc: 0.9955 -- iter: 16/29
[A[ATraining Step: 3011 | total loss: [1m[32m0.10729[0m[0m | time: 0.007s
[2K
| Adam | epoch: 753 | loss: 0.10729 - acc: 0.9959 -- iter: 24/29
[A[ATraining Step: 3012 | total loss: [1m[32m0.09948[0m[0m | time: 0.010s
[2K
| Adam | epoch: 753 | loss: 0.09948 - acc: 0.9963 -- iter: 29/29
--
Training Step: 3013 | total loss: [1m[32m0.09242[0m[0m | time: 0.003s
[2K
| Adam | epoch: 754 | loss: 0.09242 - acc: 0.9967 -- iter: 08/29
[A[ATraining Step: 3014 | total loss: [1m[32m0.09163[0m[0m | time: 0.005s
[2K
| Adam | epoch: 754 | loss: 0.09163 - acc: 0.9970 -- iter: 16/29
[A[ATraining Step: 3015 | total loss: [1m[32m0.08536[0m[0m | time: 0.008s
[2K
| Adam | epoch: 754 | loss: 0.08536 - acc: 0.9973 -- iter: 24/29
[A[ATraining Step: 3016 | total loss: [1m[32m0.07970[0m[0m | time: 0.011s
[2K
| Adam | epoch: 754 | loss: 0.07970 - acc: 0.9976 -- iter: 29/29
--
Training Step: 3017 | total loss: [1m[32m0.07542[0m[0m | time: 0.003s
[2K
| Adam | epoch: 755 | loss: 0.07542 - acc: 0.9978 -- iter: 08/29
[A[ATraining Step: 3018 | total loss: [1m[32m0.07082[0m[0m | time: 0.005s
[2K
| Adam | epoch: 755 | loss: 0.07082 - acc: 0.9981 -- iter: 16/29
[A[ATraining Step: 3019 | total loss: [1m[32m0.06605[0m[0m | time: 0.008s
[2K
| Adam | epoch: 755 | loss: 0.06605 - acc: 0.9983 -- iter: 24/29
[A[ATraining Step: 3020 | total loss: [1m[32m0.06216[0m[0m | time: 0.011s
[2K
| Adam | epoch: 755 | loss: 0.06216 - acc: 0.9984 -- iter: 29/29
--
Training Step: 3021 | total loss: [1m[32m0.05866[0m[0m | time: 0.003s
[2K
| Adam | epoch: 756 | loss: 0.05866 - acc: 0.9986 -- iter: 08/29
[A[ATraining Step: 3022 | total loss: [1m[32m0.05890[0m[0m | time: 0.005s
[2K
| Adam | epoch: 756 | loss: 0.05890 - acc: 0.9987 -- iter: 16/29
[A[ATraining Step: 3023 | total loss: [1m[32m0.05970[0m[0m | time: 0.008s
[2K
| Adam | epoch: 756 | loss: 0.05970 - acc: 0.9989 -- iter: 24/29
[A[ATraining Step: 3024 | total loss: [1m[32m0.05838[0m[0m | time: 0.010s
[2K
| Adam | epoch: 756 | loss: 0.05838 - acc: 0.9990 -- iter: 29/29
--
Training Step: 3025 | total loss: [1m[32m0.05697[0m[0m | time: 0.003s
[2K
| Adam | epoch: 757 | loss: 0.05697 - acc: 0.9991 -- iter: 08/29
[A[ATraining Step: 3026 | total loss: [1m[32m0.05569[0m[0m | time: 0.005s
[2K
| Adam | epoch: 757 | loss: 0.05569 - acc: 0.9992 -- iter: 16/29
[A[ATraining Step: 3027 | total loss: [1m[32m0.05136[0m[0m | time: 0.008s
[2K
| Adam | epoch: 757 | loss: 0.05136 - acc: 0.9992 -- iter: 24/29
[A[ATraining Step: 3028 | total loss: [1m[32m0.05425[0m[0m | time: 0.011s
[2K
| Adam | epoch: 757 | loss: 0.05425 - acc: 0.9993 -- iter: 29/29
--
Training Step: 3029 | total loss: [1m[32m0.05295[0m[0m | time: 0.003s
[2K
| Adam | epoch: 758 | loss: 0.05295 - acc: 0.9994 -- iter: 08/29
[A[ATraining Step: 3030 | total loss: [1m[32m0.05684[0m[0m | time: 0.005s
[2K
| Adam | epoch: 758 | loss: 0.05684 - acc: 0.9995 -- iter: 16/29
[A[ATraining Step: 3031 | total loss: [1m[32m0.06033[0m[0m | time: 0.008s
[2K
| Adam | epoch: 758 | loss: 0.06033 - acc: 0.9995 -- iter: 24/29
[A[ATraining Step: 3032 | total loss: [1m[32m0.05685[0m[0m | time: 0.011s
[2K
| Adam | epoch: 758 | loss: 0.05685 - acc: 0.9996 -- iter: 29/29
--
Training Step: 3033 | total loss: [1m[32m0.05534[0m[0m | time: 0.003s
[2K
| Adam | epoch: 759 | loss: 0.05534 - acc: 0.9996 -- iter: 08/29
[A[ATraining Step: 3034 | total loss: [1m[32m0.05166[0m[0m | time: 0.006s
[2K
| Adam | epoch: 759 | loss: 0.05166 - acc: 0.9996 -- iter: 16/29
[A[ATraining Step: 3035 | total loss: [1m[32m0.05539[0m[0m | time: 0.008s
[2K
| Adam | epoch: 759 | loss: 0.05539 - acc: 0.9997 -- iter: 24/29
[A[ATraining Step: 3036 | total loss: [1m[32m0.05871[0m[0m | time: 0.011s
[2K
| Adam | epoch: 759 | loss: 0.05871 - acc: 0.9997 -- iter: 29/29
--
Training Step: 3037 | total loss: [1m[32m0.05568[0m[0m | time: 0.003s
[2K
| Adam | epoch: 760 | loss: 0.05568 - acc: 0.9997 -- iter: 08/29
[A[ATraining Step: 3038 | total loss: [1m[32m1.22583[0m[0m | time: 0.005s
[2K
| Adam | epoch: 760 | loss: 1.22583 - acc: 0.9123 -- iter: 16/29
[A[ATraining Step: 3039 | total loss: [1m[32m1.10631[0m[0m | time: 0.008s
[2K
| Adam | epoch: 760 | loss: 1.10631 - acc: 0.9210 -- iter: 24/29
[A[ATraining Step: 3040 | total loss: [1m[32m0.99964[0m[0m | time: 0.010s
[2K
| Adam | epoch: 760 | loss: 0.99964 - acc: 0.9289 -- iter: 29/29
--
Training Step: 3041 | total loss: [1m[32m0.90369[0m[0m | time: 0.014s
[2K
| Adam | epoch: 761 | loss: 0.90369 - acc: 0.9360 -- iter: 08/29
[A[ATraining Step: 3042 | total loss: [1m[32m0.82066[0m[0m | time: 0.017s
[2K
| Adam | epoch: 761 | loss: 0.82066 - acc: 0.9424 -- iter: 16/29
[A[ATraining Step: 3043 | total loss: [1m[32m0.74199[0m[0m | time: 0.019s
[2K
| Adam | epoch: 761 | loss: 0.74199 - acc: 0.9482 -- iter: 24/29
[A[ATraining Step: 3044 | total loss: [1m[32m0.67086[0m[0m | time: 0.022s
[2K
| Adam | epoch: 761 | loss: 0.67086 - acc: 0.9534 -- iter: 29/29
--
Training Step: 3045 | total loss: [1m[32m0.60562[0m[0m | time: 0.003s
[2K
| Adam | epoch: 762 | loss: 0.60562 - acc: 0.9580 -- iter: 08/29
[A[ATraining Step: 3046 | total loss: [1m[32m0.54694[0m[0m | time: 0.005s
[2K
| Adam | epoch: 762 | loss: 0.54694 - acc: 0.9622 -- iter: 16/29
[A[ATraining Step: 3047 | total loss: [1m[32m0.49745[0m[0m | time: 0.008s
[2K
| Adam | epoch: 762 | loss: 0.49745 - acc: 0.9660 -- iter: 24/29
[A[ATraining Step: 3048 | total loss: [1m[32m0.45506[0m[0m | time: 0.011s
[2K
| Adam | epoch: 762 | loss: 0.45506 - acc: 0.9694 -- iter: 29/29
--
Training Step: 3049 | total loss: [1m[32m0.41728[0m[0m | time: 0.003s
[2K
| Adam | epoch: 763 | loss: 0.41728 - acc: 0.9725 -- iter: 08/29
[A[ATraining Step: 3050 | total loss: [1m[32m0.37825[0m[0m | time: 0.006s
[2K
| Adam | epoch: 763 | loss: 0.37825 - acc: 0.9752 -- iter: 16/29
[A[ATraining Step: 3051 | total loss: [1m[32m0.34312[0m[0m | time: 0.009s
[2K
| Adam | epoch: 763 | loss: 0.34312 - acc: 0.9777 -- iter: 24/29
[A[ATraining Step: 3052 | total loss: [1m[32m0.31263[0m[0m | time: 0.011s
[2K
| Adam | epoch: 763 | loss: 0.31263 - acc: 0.9799 -- iter: 29/29
--
Training Step: 3053 | total loss: [1m[32m0.28489[0m[0m | time: 0.003s
[2K
| Adam | epoch: 764 | loss: 0.28489 - acc: 0.9819 -- iter: 08/29
[A[ATraining Step: 3054 | total loss: [1m[32m0.26056[0m[0m | time: 0.006s
[2K
| Adam | epoch: 764 | loss: 0.26056 - acc: 0.9837 -- iter: 16/29
[A[ATraining Step: 3055 | total loss: [1m[32m0.23947[0m[0m | time: 0.009s
[2K
| Adam | epoch: 764 | loss: 0.23947 - acc: 0.9854 -- iter: 24/29
[A[ATraining Step: 3056 | total loss: [1m[32m0.22045[0m[0m | time: 0.012s
[2K
| Adam | epoch: 764 | loss: 0.22045 - acc: 0.9868 -- iter: 29/29
--
Training Step: 3057 | total loss: [1m[32m0.20149[0m[0m | time: 0.003s
[2K
| Adam | epoch: 765 | loss: 0.20149 - acc: 0.9881 -- iter: 08/29
[A[ATraining Step: 3058 | total loss: [1m[32m0.18780[0m[0m | time: 0.006s
[2K
| Adam | epoch: 765 | loss: 0.18780 - acc: 0.9893 -- iter: 16/29
[A[ATraining Step: 3059 | total loss: [1m[32m0.17360[0m[0m | time: 0.009s
[2K
| Adam | epoch: 765 | loss: 0.17360 - acc: 0.9904 -- iter: 24/29
[A[ATraining Step: 3060 | total loss: [1m[32m0.16188[0m[0m | time: 0.011s
[2K
| Adam | epoch: 765 | loss: 0.16188 - acc: 0.9914 -- iter: 29/29
--
Training Step: 3061 | total loss: [1m[32m0.15131[0m[0m | time: 0.003s
[2K
| Adam | epoch: 766 | loss: 0.15131 - acc: 0.9922 -- iter: 08/29
[A[ATraining Step: 3062 | total loss: [1m[32m0.13822[0m[0m | time: 0.005s
[2K
| Adam | epoch: 766 | loss: 0.13822 - acc: 0.9930 -- iter: 16/29
[A[ATraining Step: 3063 | total loss: [1m[32m0.13102[0m[0m | time: 0.008s
[2K
| Adam | epoch: 766 | loss: 0.13102 - acc: 0.9937 -- iter: 24/29
[A[ATraining Step: 3064 | total loss: [1m[32m0.12415[0m[0m | time: 0.011s
[2K
| Adam | epoch: 766 | loss: 0.12415 - acc: 0.9943 -- iter: 29/29
--
Training Step: 3065 | total loss: [1m[32m0.11389[0m[0m | time: 0.003s
[2K
| Adam | epoch: 767 | loss: 0.11389 - acc: 0.9949 -- iter: 08/29
[A[ATraining Step: 3066 | total loss: [1m[32m0.10466[0m[0m | time: 0.005s
[2K
| Adam | epoch: 767 | loss: 0.10466 - acc: 0.9954 -- iter: 16/29
[A[ATraining Step: 3067 | total loss: [1m[32m0.09645[0m[0m | time: 0.009s
[2K
| Adam | epoch: 767 | loss: 0.09645 - acc: 0.9959 -- iter: 24/29
[A[ATraining Step: 3068 | total loss: [1m[32m0.09370[0m[0m | time: 0.012s
[2K
| Adam | epoch: 767 | loss: 0.09370 - acc: 0.9963 -- iter: 29/29
--
Training Step: 3069 | total loss: [1m[32m0.09197[0m[0m | time: 0.003s
[2K
| Adam | epoch: 768 | loss: 0.09197 - acc: 0.9967 -- iter: 08/29
[A[ATraining Step: 3070 | total loss: [1m[32m0.08513[0m[0m | time: 0.006s
[2K
| Adam | epoch: 768 | loss: 0.08513 - acc: 0.9970 -- iter: 16/29
[A[ATraining Step: 3071 | total loss: [1m[32m0.07897[0m[0m | time: 0.008s
[2K
| Adam | epoch: 768 | loss: 0.07897 - acc: 0.9973 -- iter: 24/29
[A[ATraining Step: 3072 | total loss: [1m[32m0.07634[0m[0m | time: 0.011s
[2K
| Adam | epoch: 768 | loss: 0.07634 - acc: 0.9976 -- iter: 29/29
--
Training Step: 3073 | total loss: [1m[32m0.07096[0m[0m | time: 0.003s
[2K
| Adam | epoch: 769 | loss: 0.07096 - acc: 0.9978 -- iter: 08/29
[A[ATraining Step: 3074 | total loss: [1m[32m0.06731[0m[0m | time: 0.006s
[2K
| Adam | epoch: 769 | loss: 0.06731 - acc: 0.9980 -- iter: 16/29
[A[ATraining Step: 3075 | total loss: [1m[32m0.06378[0m[0m | time: 0.008s
[2K
| Adam | epoch: 769 | loss: 0.06378 - acc: 0.9982 -- iter: 24/29
[A[ATraining Step: 3076 | total loss: [1m[32m0.06060[0m[0m | time: 0.011s
[2K
| Adam | epoch: 769 | loss: 0.06060 - acc: 0.9984 -- iter: 29/29
--
Training Step: 3077 | total loss: [1m[32m0.05647[0m[0m | time: 0.003s
[2K
| Adam | epoch: 770 | loss: 0.05647 - acc: 0.9986 -- iter: 08/29
[A[ATraining Step: 3078 | total loss: [1m[32m0.06001[0m[0m | time: 0.006s
[2K
| Adam | epoch: 770 | loss: 0.06001 - acc: 0.9987 -- iter: 16/29
[A[ATraining Step: 3079 | total loss: [1m[32m0.05948[0m[0m | time: 0.009s
[2K
| Adam | epoch: 770 | loss: 0.05948 - acc: 0.9988 -- iter: 24/29
[A[ATraining Step: 3080 | total loss: [1m[32m0.05537[0m[0m | time: 0.011s
[2K
| Adam | epoch: 770 | loss: 0.05537 - acc: 0.9989 -- iter: 29/29
--
Training Step: 3081 | total loss: [1m[32m0.05165[0m[0m | time: 0.003s
[2K
| Adam | epoch: 771 | loss: 0.05165 - acc: 0.9991 -- iter: 08/29
[A[ATraining Step: 3082 | total loss: [1m[32m0.04951[0m[0m | time: 0.005s
[2K
| Adam | epoch: 771 | loss: 0.04951 - acc: 0.9991 -- iter: 16/29
[A[ATraining Step: 3083 | total loss: [1m[32m0.05131[0m[0m | time: 0.008s
[2K
| Adam | epoch: 771 | loss: 0.05131 - acc: 0.9992 -- iter: 24/29
[A[ATraining Step: 3084 | total loss: [1m[32m0.05056[0m[0m | time: 0.010s
[2K
| Adam | epoch: 771 | loss: 0.05056 - acc: 0.9993 -- iter: 29/29
--
Training Step: 3085 | total loss: [1m[32m0.04718[0m[0m | time: 0.002s
[2K
| Adam | epoch: 772 | loss: 0.04718 - acc: 0.9994 -- iter: 08/29
[A[ATraining Step: 3086 | total loss: [1m[32m0.04414[0m[0m | time: 0.005s
[2K
| Adam | epoch: 772 | loss: 0.04414 - acc: 0.9994 -- iter: 16/29
[A[ATraining Step: 3087 | total loss: [1m[32m0.04231[0m[0m | time: 0.008s
[2K
| Adam | epoch: 772 | loss: 0.04231 - acc: 0.9995 -- iter: 24/29
[A[ATraining Step: 3088 | total loss: [1m[32m0.04639[0m[0m | time: 0.010s
[2K
| Adam | epoch: 772 | loss: 0.04639 - acc: 0.9995 -- iter: 29/29
--
Training Step: 3089 | total loss: [1m[32m0.04615[0m[0m | time: 0.003s
[2K
| Adam | epoch: 773 | loss: 0.04615 - acc: 0.9996 -- iter: 08/29
[A[ATraining Step: 3090 | total loss: [1m[32m0.05222[0m[0m | time: 0.005s
[2K
| Adam | epoch: 773 | loss: 0.05222 - acc: 0.9996 -- iter: 16/29
[A[ATraining Step: 3091 | total loss: [1m[32m0.05764[0m[0m | time: 0.008s
[2K
| Adam | epoch: 773 | loss: 0.05764 - acc: 0.9997 -- iter: 24/29
[A[ATraining Step: 3092 | total loss: [1m[32m0.05468[0m[0m | time: 0.010s
[2K
| Adam | epoch: 773 | loss: 0.05468 - acc: 0.9997 -- iter: 29/29
--
Training Step: 3093 | total loss: [1m[32m0.05156[0m[0m | time: 0.003s
[2K
| Adam | epoch: 774 | loss: 0.05156 - acc: 0.9997 -- iter: 08/29
[A[ATraining Step: 3094 | total loss: [1m[32m0.05358[0m[0m | time: 0.005s
[2K
| Adam | epoch: 774 | loss: 0.05358 - acc: 0.9998 -- iter: 16/29
[A[ATraining Step: 3095 | total loss: [1m[32m0.05031[0m[0m | time: 0.008s
[2K
| Adam | epoch: 774 | loss: 0.05031 - acc: 0.9998 -- iter: 24/29
[A[ATraining Step: 3096 | total loss: [1m[32m0.04733[0m[0m | time: 0.010s
[2K
| Adam | epoch: 774 | loss: 0.04733 - acc: 0.9998 -- iter: 29/29
--
Training Step: 3097 | total loss: [1m[32m0.04532[0m[0m | time: 0.003s
[2K
| Adam | epoch: 775 | loss: 0.04532 - acc: 0.9998 -- iter: 08/29
[A[ATraining Step: 3098 | total loss: [1m[32m0.04567[0m[0m | time: 0.005s
[2K
| Adam | epoch: 775 | loss: 0.04567 - acc: 0.9998 -- iter: 16/29
[A[ATraining Step: 3099 | total loss: [1m[32m0.04284[0m[0m | time: 0.008s
[2K
| Adam | epoch: 775 | loss: 0.04284 - acc: 0.9999 -- iter: 24/29
[A[ATraining Step: 3100 | total loss: [1m[32m0.04576[0m[0m | time: 0.010s
[2K
| Adam | epoch: 775 | loss: 0.04576 - acc: 0.9999 -- iter: 29/29
--
Training Step: 3101 | total loss: [1m[32m0.04836[0m[0m | time: 0.003s
[2K
| Adam | epoch: 776 | loss: 0.04836 - acc: 0.9999 -- iter: 08/29
[A[ATraining Step: 3102 | total loss: [1m[32m0.05014[0m[0m | time: 0.005s
[2K
| Adam | epoch: 776 | loss: 0.05014 - acc: 0.9999 -- iter: 16/29
[A[ATraining Step: 3103 | total loss: [1m[32m0.04830[0m[0m | time: 0.008s
[2K
| Adam | epoch: 776 | loss: 0.04830 - acc: 0.9999 -- iter: 24/29
[A[ATraining Step: 3104 | total loss: [1m[32m0.04433[0m[0m | time: 0.010s
[2K
| Adam | epoch: 776 | loss: 0.04433 - acc: 0.9999 -- iter: 29/29
--
Training Step: 3105 | total loss: [1m[32m0.04278[0m[0m | time: 0.002s
[2K
| Adam | epoch: 777 | loss: 0.04278 - acc: 0.9999 -- iter: 08/29
[A[ATraining Step: 3106 | total loss: [1m[32m0.04138[0m[0m | time: 0.005s
[2K
| Adam | epoch: 777 | loss: 0.04138 - acc: 0.9999 -- iter: 16/29
[A[ATraining Step: 3107 | total loss: [1m[32m0.04794[0m[0m | time: 0.008s
[2K
| Adam | epoch: 777 | loss: 0.04794 - acc: 0.9999 -- iter: 24/29
[A[ATraining Step: 3108 | total loss: [1m[32m0.04565[0m[0m | time: 0.010s
[2K
| Adam | epoch: 777 | loss: 0.04565 - acc: 0.9999 -- iter: 29/29
--
Training Step: 3109 | total loss: [1m[32m0.04609[0m[0m | time: 0.003s
[2K
| Adam | epoch: 778 | loss: 0.04609 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3110 | total loss: [1m[32m0.05048[0m[0m | time: 0.006s
[2K
| Adam | epoch: 778 | loss: 0.05048 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3111 | total loss: [1m[32m0.05442[0m[0m | time: 0.008s
[2K
| Adam | epoch: 778 | loss: 0.05442 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3112 | total loss: [1m[32m0.05124[0m[0m | time: 0.011s
[2K
| Adam | epoch: 778 | loss: 0.05124 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3113 | total loss: [1m[32m0.04906[0m[0m | time: 0.003s
[2K
| Adam | epoch: 779 | loss: 0.04906 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3114 | total loss: [1m[32m0.05360[0m[0m | time: 0.005s
[2K
| Adam | epoch: 779 | loss: 0.05360 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3115 | total loss: [1m[32m0.05054[0m[0m | time: 0.032s
[2K
| Adam | epoch: 779 | loss: 0.05054 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3116 | total loss: [1m[32m0.04778[0m[0m | time: 0.034s
[2K
| Adam | epoch: 779 | loss: 0.04778 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3117 | total loss: [1m[32m0.04500[0m[0m | time: 0.002s
[2K
| Adam | epoch: 780 | loss: 0.04500 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3118 | total loss: [1m[32m0.04341[0m[0m | time: 0.005s
[2K
| Adam | epoch: 780 | loss: 0.04341 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3119 | total loss: [1m[32m0.04473[0m[0m | time: 0.008s
[2K
| Adam | epoch: 780 | loss: 0.04473 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3120 | total loss: [1m[32m0.04170[0m[0m | time: 0.010s
[2K
| Adam | epoch: 780 | loss: 0.04170 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3121 | total loss: [1m[32m0.03895[0m[0m | time: 0.003s
[2K
| Adam | epoch: 781 | loss: 0.03895 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3122 | total loss: [1m[32m0.03778[0m[0m | time: 0.005s
[2K
| Adam | epoch: 781 | loss: 0.03778 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3123 | total loss: [1m[32m0.04040[0m[0m | time: 0.008s
[2K
| Adam | epoch: 781 | loss: 0.04040 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3124 | total loss: [1m[32m0.04075[0m[0m | time: 0.010s
[2K
| Adam | epoch: 781 | loss: 0.04075 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3125 | total loss: [1m[32m0.03923[0m[0m | time: 0.003s
[2K
| Adam | epoch: 782 | loss: 0.03923 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3126 | total loss: [1m[32m0.03785[0m[0m | time: 0.005s
[2K
| Adam | epoch: 782 | loss: 0.03785 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3127 | total loss: [1m[32m0.03920[0m[0m | time: 0.008s
[2K
| Adam | epoch: 782 | loss: 0.03920 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3128 | total loss: [1m[32m0.03978[0m[0m | time: 0.010s
[2K
| Adam | epoch: 782 | loss: 0.03978 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3129 | total loss: [1m[32m0.04204[0m[0m | time: 0.003s
[2K
| Adam | epoch: 783 | loss: 0.04204 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3130 | total loss: [1m[32m0.03928[0m[0m | time: 0.005s
[2K
| Adam | epoch: 783 | loss: 0.03928 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3131 | total loss: [1m[32m0.03679[0m[0m | time: 0.008s
[2K
| Adam | epoch: 783 | loss: 0.03679 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3132 | total loss: [1m[32m0.03491[0m[0m | time: 0.010s
[2K
| Adam | epoch: 783 | loss: 0.03491 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3133 | total loss: [1m[32m0.03799[0m[0m | time: 0.003s
[2K
| Adam | epoch: 784 | loss: 0.03799 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3134 | total loss: [1m[32m0.04067[0m[0m | time: 0.005s
[2K
| Adam | epoch: 784 | loss: 0.04067 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3135 | total loss: [1m[32m0.03949[0m[0m | time: 0.008s
[2K
| Adam | epoch: 784 | loss: 0.03949 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3136 | total loss: [1m[32m0.03842[0m[0m | time: 0.010s
[2K
| Adam | epoch: 784 | loss: 0.03842 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3137 | total loss: [1m[32m0.03730[0m[0m | time: 0.003s
[2K
| Adam | epoch: 785 | loss: 0.03730 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3138 | total loss: [1m[32m0.03801[0m[0m | time: 0.005s
[2K
| Adam | epoch: 785 | loss: 0.03801 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3139 | total loss: [1m[32m0.03518[0m[0m | time: 0.008s
[2K
| Adam | epoch: 785 | loss: 0.03518 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3140 | total loss: [1m[32m0.03682[0m[0m | time: 0.010s
[2K
| Adam | epoch: 785 | loss: 0.03682 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3141 | total loss: [1m[32m0.03823[0m[0m | time: 0.003s
[2K
| Adam | epoch: 786 | loss: 0.03823 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3142 | total loss: [1m[32m0.03820[0m[0m | time: 0.005s
[2K
| Adam | epoch: 786 | loss: 0.03820 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3143 | total loss: [1m[32m0.04182[0m[0m | time: 0.008s
[2K
| Adam | epoch: 786 | loss: 0.04182 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3144 | total loss: [1m[32m0.04304[0m[0m | time: 0.011s
[2K
| Adam | epoch: 786 | loss: 0.04304 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3145 | total loss: [1m[32m0.04269[0m[0m | time: 0.003s
[2K
| Adam | epoch: 787 | loss: 0.04269 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3146 | total loss: [1m[32m0.04239[0m[0m | time: 0.005s
[2K
| Adam | epoch: 787 | loss: 0.04239 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3147 | total loss: [1m[32m0.03862[0m[0m | time: 0.008s
[2K
| Adam | epoch: 787 | loss: 0.03862 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3148 | total loss: [1m[32m0.04173[0m[0m | time: 0.010s
[2K
| Adam | epoch: 787 | loss: 0.04173 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3149 | total loss: [1m[32m0.04251[0m[0m | time: 0.003s
[2K
| Adam | epoch: 788 | loss: 0.04251 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3150 | total loss: [1m[32m0.04051[0m[0m | time: 0.005s
[2K
| Adam | epoch: 788 | loss: 0.04051 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3151 | total loss: [1m[32m0.03870[0m[0m | time: 0.008s
[2K
| Adam | epoch: 788 | loss: 0.03870 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3152 | total loss: [1m[32m0.03766[0m[0m | time: 0.010s
[2K
| Adam | epoch: 788 | loss: 0.03766 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3153 | total loss: [1m[32m0.03995[0m[0m | time: 0.003s
[2K
| Adam | epoch: 789 | loss: 0.03995 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3154 | total loss: [1m[32m0.03898[0m[0m | time: 0.005s
[2K
| Adam | epoch: 789 | loss: 0.03898 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3155 | total loss: [1m[32m0.03735[0m[0m | time: 0.008s
[2K
| Adam | epoch: 789 | loss: 0.03735 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3156 | total loss: [1m[32m0.03588[0m[0m | time: 0.011s
[2K
| Adam | epoch: 789 | loss: 0.03588 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3157 | total loss: [1m[32m0.03536[0m[0m | time: 0.003s
[2K
| Adam | epoch: 790 | loss: 0.03536 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3158 | total loss: [1m[32m0.03941[0m[0m | time: 0.005s
[2K
| Adam | epoch: 790 | loss: 0.03941 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3159 | total loss: [1m[32m0.03837[0m[0m | time: 0.008s
[2K
| Adam | epoch: 790 | loss: 0.03837 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3160 | total loss: [1m[32m0.04300[0m[0m | time: 0.011s
[2K
| Adam | epoch: 790 | loss: 0.04300 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3161 | total loss: [1m[32m0.04715[0m[0m | time: 0.003s
[2K
| Adam | epoch: 791 | loss: 0.04715 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3162 | total loss: [1m[32m0.04607[0m[0m | time: 0.005s
[2K
| Adam | epoch: 791 | loss: 0.04607 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3163 | total loss: [1m[32m0.04471[0m[0m | time: 0.008s
[2K
| Adam | epoch: 791 | loss: 0.04471 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3164 | total loss: [1m[32m0.04447[0m[0m | time: 0.010s
[2K
| Adam | epoch: 791 | loss: 0.04447 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3165 | total loss: [1m[32m0.04365[0m[0m | time: 0.003s
[2K
| Adam | epoch: 792 | loss: 0.04365 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3166 | total loss: [1m[32m0.04290[0m[0m | time: 0.005s
[2K
| Adam | epoch: 792 | loss: 0.04290 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3167 | total loss: [1m[32m0.04042[0m[0m | time: 0.008s
[2K
| Adam | epoch: 792 | loss: 0.04042 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3168 | total loss: [1m[32m0.04302[0m[0m | time: 0.010s
[2K
| Adam | epoch: 792 | loss: 0.04302 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3169 | total loss: [1m[32m0.04247[0m[0m | time: 0.003s
[2K
| Adam | epoch: 793 | loss: 0.04247 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3170 | total loss: [1m[32m0.04583[0m[0m | time: 0.006s
[2K
| Adam | epoch: 793 | loss: 0.04583 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3171 | total loss: [1m[32m0.04882[0m[0m | time: 0.008s
[2K
| Adam | epoch: 793 | loss: 0.04882 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3172 | total loss: [1m[32m0.04769[0m[0m | time: 0.011s
[2K
| Adam | epoch: 793 | loss: 0.04769 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3173 | total loss: [1m[32m0.04555[0m[0m | time: 0.003s
[2K
| Adam | epoch: 794 | loss: 0.04555 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3174 | total loss: [1m[32m0.04612[0m[0m | time: 0.006s
[2K
| Adam | epoch: 794 | loss: 0.04612 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3175 | total loss: [1m[32m0.04450[0m[0m | time: 0.009s
[2K
| Adam | epoch: 794 | loss: 0.04450 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3176 | total loss: [1m[32m0.04302[0m[0m | time: 0.012s
[2K
| Adam | epoch: 794 | loss: 0.04302 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3177 | total loss: [1m[32m0.04257[0m[0m | time: 0.003s
[2K
| Adam | epoch: 795 | loss: 0.04257 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3178 | total loss: [1m[32m0.04241[0m[0m | time: 0.006s
[2K
| Adam | epoch: 795 | loss: 0.04241 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3179 | total loss: [1m[32m0.04494[0m[0m | time: 0.009s
[2K
| Adam | epoch: 795 | loss: 0.04494 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3180 | total loss: [1m[32m0.04238[0m[0m | time: 0.012s
[2K
| Adam | epoch: 795 | loss: 0.04238 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3181 | total loss: [1m[32m0.04008[0m[0m | time: 0.003s
[2K
| Adam | epoch: 796 | loss: 0.04008 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3182 | total loss: [1m[32m0.03780[0m[0m | time: 0.006s
[2K
| Adam | epoch: 796 | loss: 0.03780 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3183 | total loss: [1m[32m0.03914[0m[0m | time: 0.009s
[2K
| Adam | epoch: 796 | loss: 0.03914 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3184 | total loss: [1m[32m0.03780[0m[0m | time: 0.012s
[2K
| Adam | epoch: 796 | loss: 0.03780 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3185 | total loss: [1m[32m0.03537[0m[0m | time: 0.003s
[2K
| Adam | epoch: 797 | loss: 0.03537 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3186 | total loss: [1m[32m0.03317[0m[0m | time: 0.006s
[2K
| Adam | epoch: 797 | loss: 0.03317 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3187 | total loss: [1m[32m0.03751[0m[0m | time: 0.008s
[2K
| Adam | epoch: 797 | loss: 0.03751 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3188 | total loss: [1m[32m0.03744[0m[0m | time: 0.012s
[2K
| Adam | epoch: 797 | loss: 0.03744 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3189 | total loss: [1m[32m0.03523[0m[0m | time: 0.003s
[2K
| Adam | epoch: 798 | loss: 0.03523 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3190 | total loss: [1m[32m0.04375[0m[0m | time: 0.006s
[2K
| Adam | epoch: 798 | loss: 0.04375 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3191 | total loss: [1m[32m0.05138[0m[0m | time: 0.008s
[2K
| Adam | epoch: 798 | loss: 0.05138 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3192 | total loss: [1m[32m0.04874[0m[0m | time: 0.011s
[2K
| Adam | epoch: 798 | loss: 0.04874 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3193 | total loss: [1m[32m0.04702[0m[0m | time: 0.003s
[2K
| Adam | epoch: 799 | loss: 0.04702 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3194 | total loss: [1m[32m0.04626[0m[0m | time: 0.006s
[2K
| Adam | epoch: 799 | loss: 0.04626 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3195 | total loss: [1m[32m0.05151[0m[0m | time: 0.009s
[2K
| Adam | epoch: 799 | loss: 0.05151 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3196 | total loss: [1m[32m0.05622[0m[0m | time: 0.012s
[2K
| Adam | epoch: 799 | loss: 0.05622 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3197 | total loss: [1m[32m0.05185[0m[0m | time: 0.003s
[2K
| Adam | epoch: 800 | loss: 0.05185 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3198 | total loss: [1m[32m0.04988[0m[0m | time: 0.006s
[2K
| Adam | epoch: 800 | loss: 0.04988 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3199 | total loss: [1m[32m0.04636[0m[0m | time: 0.009s
[2K
| Adam | epoch: 800 | loss: 0.04636 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3200 | total loss: [1m[32m0.04404[0m[0m | time: 0.012s
[2K
| Adam | epoch: 800 | loss: 0.04404 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3201 | total loss: [1m[32m0.04194[0m[0m | time: 0.003s
[2K
| Adam | epoch: 801 | loss: 0.04194 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3202 | total loss: [1m[32m0.04295[0m[0m | time: 0.006s
[2K
| Adam | epoch: 801 | loss: 0.04295 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3203 | total loss: [1m[32m0.04497[0m[0m | time: 0.008s
[2K
| Adam | epoch: 801 | loss: 0.04497 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3204 | total loss: [1m[32m0.04636[0m[0m | time: 0.011s
[2K
| Adam | epoch: 801 | loss: 0.04636 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3205 | total loss: [1m[32m0.04305[0m[0m | time: 0.003s
[2K
| Adam | epoch: 802 | loss: 0.04305 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3206 | total loss: [1m[32m0.04007[0m[0m | time: 0.006s
[2K
| Adam | epoch: 802 | loss: 0.04007 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3207 | total loss: [1m[32m0.04276[0m[0m | time: 0.009s
[2K
| Adam | epoch: 802 | loss: 0.04276 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3208 | total loss: [1m[32m0.03942[0m[0m | time: 0.012s
[2K
| Adam | epoch: 802 | loss: 0.03942 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3209 | total loss: [1m[32m0.03852[0m[0m | time: 0.003s
[2K
| Adam | epoch: 803 | loss: 0.03852 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3210 | total loss: [1m[32m0.03582[0m[0m | time: 0.006s
[2K
| Adam | epoch: 803 | loss: 0.03582 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3211 | total loss: [1m[32m0.03340[0m[0m | time: 0.009s
[2K
| Adam | epoch: 803 | loss: 0.03340 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3212 | total loss: [1m[32m0.03648[0m[0m | time: 0.011s
[2K
| Adam | epoch: 803 | loss: 0.03648 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3213 | total loss: [1m[32m0.03692[0m[0m | time: 0.003s
[2K
| Adam | epoch: 804 | loss: 0.03692 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3214 | total loss: [1m[32m0.03983[0m[0m | time: 0.006s
[2K
| Adam | epoch: 804 | loss: 0.03983 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3215 | total loss: [1m[32m0.03868[0m[0m | time: 0.008s
[2K
| Adam | epoch: 804 | loss: 0.03868 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3216 | total loss: [1m[32m0.03764[0m[0m | time: 0.011s
[2K
| Adam | epoch: 804 | loss: 0.03764 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3217 | total loss: [1m[32m0.03517[0m[0m | time: 0.003s
[2K
| Adam | epoch: 805 | loss: 0.03517 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3218 | total loss: [1m[32m0.03620[0m[0m | time: 0.006s
[2K
| Adam | epoch: 805 | loss: 0.03620 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3219 | total loss: [1m[32m0.03764[0m[0m | time: 0.009s
[2K
| Adam | epoch: 805 | loss: 0.03764 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3220 | total loss: [1m[32m0.03714[0m[0m | time: 0.012s
[2K
| Adam | epoch: 805 | loss: 0.03714 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3221 | total loss: [1m[32m0.03669[0m[0m | time: 0.003s
[2K
| Adam | epoch: 806 | loss: 0.03669 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3222 | total loss: [1m[32m0.03471[0m[0m | time: 0.006s
[2K
| Adam | epoch: 806 | loss: 0.03471 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3223 | total loss: [1m[32m0.03663[0m[0m | time: 0.009s
[2K
| Adam | epoch: 806 | loss: 0.03663 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3224 | total loss: [1m[32m0.03870[0m[0m | time: 0.012s
[2K
| Adam | epoch: 806 | loss: 0.03870 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3225 | total loss: [1m[32m0.03626[0m[0m | time: 0.003s
[2K
| Adam | epoch: 807 | loss: 0.03626 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3226 | total loss: [1m[32m0.03407[0m[0m | time: 0.006s
[2K
| Adam | epoch: 807 | loss: 0.03407 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3227 | total loss: [1m[32m0.03226[0m[0m | time: 0.009s
[2K
| Adam | epoch: 807 | loss: 0.03226 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3228 | total loss: [1m[32m0.03490[0m[0m | time: 0.012s
[2K
| Adam | epoch: 807 | loss: 0.03490 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3229 | total loss: [1m[32m0.03329[0m[0m | time: 0.003s
[2K
| Adam | epoch: 808 | loss: 0.03329 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3230 | total loss: [1m[32m0.03960[0m[0m | time: 0.006s
[2K
| Adam | epoch: 808 | loss: 0.03960 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3231 | total loss: [1m[32m0.04524[0m[0m | time: 0.009s
[2K
| Adam | epoch: 808 | loss: 0.04524 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3232 | total loss: [1m[32m0.04426[0m[0m | time: 0.012s
[2K
| Adam | epoch: 808 | loss: 0.04426 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3233 | total loss: [1m[32m0.04238[0m[0m | time: 0.003s
[2K
| Adam | epoch: 809 | loss: 0.04238 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3234 | total loss: [1m[32m0.03895[0m[0m | time: 0.006s
[2K
| Adam | epoch: 809 | loss: 0.03895 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3235 | total loss: [1m[32m0.04252[0m[0m | time: 0.008s
[2K
| Adam | epoch: 809 | loss: 0.04252 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3236 | total loss: [1m[32m0.04571[0m[0m | time: 0.011s
[2K
| Adam | epoch: 809 | loss: 0.04571 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3237 | total loss: [1m[32m0.04635[0m[0m | time: 0.003s
[2K
| Adam | epoch: 810 | loss: 0.04635 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3238 | total loss: [1m[32m0.04496[0m[0m | time: 0.006s
[2K
| Adam | epoch: 810 | loss: 0.04496 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3239 | total loss: [1m[32m0.04820[0m[0m | time: 0.009s
[2K
| Adam | epoch: 810 | loss: 0.04820 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3240 | total loss: [1m[32m0.04788[0m[0m | time: 0.012s
[2K
| Adam | epoch: 810 | loss: 0.04788 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3241 | total loss: [1m[32m0.04759[0m[0m | time: 0.003s
[2K
| Adam | epoch: 811 | loss: 0.04759 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3242 | total loss: [1m[32m0.04539[0m[0m | time: 0.007s
[2K
| Adam | epoch: 811 | loss: 0.04539 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3243 | total loss: [1m[32m0.04167[0m[0m | time: 0.010s
[2K
| Adam | epoch: 811 | loss: 0.04167 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3244 | total loss: [1m[32m0.04496[0m[0m | time: 0.013s
[2K
| Adam | epoch: 811 | loss: 0.04496 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3245 | total loss: [1m[32m0.04189[0m[0m | time: 0.003s
[2K
| Adam | epoch: 812 | loss: 0.04189 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3246 | total loss: [1m[32m0.03913[0m[0m | time: 0.006s
[2K
| Adam | epoch: 812 | loss: 0.03913 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3247 | total loss: [1m[32m0.03810[0m[0m | time: 0.008s
[2K
| Adam | epoch: 812 | loss: 0.03810 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3248 | total loss: [1m[32m0.03681[0m[0m | time: 0.011s
[2K
| Adam | epoch: 812 | loss: 0.03681 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3249 | total loss: [1m[32m0.03649[0m[0m | time: 0.003s
[2K
| Adam | epoch: 813 | loss: 0.03649 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3250 | total loss: [1m[32m0.03464[0m[0m | time: 0.005s
[2K
| Adam | epoch: 813 | loss: 0.03464 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3251 | total loss: [1m[32m0.03297[0m[0m | time: 0.008s
[2K
| Adam | epoch: 813 | loss: 0.03297 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3252 | total loss: [1m[32m0.03626[0m[0m | time: 0.011s
[2K
| Adam | epoch: 813 | loss: 0.03626 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3253 | total loss: [1m[32m0.03531[0m[0m | time: 0.003s
[2K
| Adam | epoch: 814 | loss: 0.03531 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3254 | total loss: [1m[32m0.03876[0m[0m | time: 0.006s
[2K
| Adam | epoch: 814 | loss: 0.03876 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3255 | total loss: [1m[32m0.03600[0m[0m | time: 0.008s
[2K
| Adam | epoch: 814 | loss: 0.03600 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3256 | total loss: [1m[32m0.03351[0m[0m | time: 0.011s
[2K
| Adam | epoch: 814 | loss: 0.03351 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3257 | total loss: [1m[32m0.03314[0m[0m | time: 0.003s
[2K
| Adam | epoch: 815 | loss: 0.03314 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3258 | total loss: [1m[32m0.03281[0m[0m | time: 0.005s
[2K
| Adam | epoch: 815 | loss: 0.03281 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3259 | total loss: [1m[32m0.03301[0m[0m | time: 0.008s
[2K
| Adam | epoch: 815 | loss: 0.03301 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3260 | total loss: [1m[32m0.03123[0m[0m | time: 0.011s
[2K
| Adam | epoch: 815 | loss: 0.03123 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3261 | total loss: [1m[32m0.02963[0m[0m | time: 0.003s
[2K
| Adam | epoch: 816 | loss: 0.02963 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3262 | total loss: [1m[32m0.03271[0m[0m | time: 0.005s
[2K
| Adam | epoch: 816 | loss: 0.03271 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3263 | total loss: [1m[32m0.03254[0m[0m | time: 0.008s
[2K
| Adam | epoch: 816 | loss: 0.03254 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3264 | total loss: [1m[32m0.03190[0m[0m | time: 0.010s
[2K
| Adam | epoch: 816 | loss: 0.03190 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3265 | total loss: [1m[32m0.03631[0m[0m | time: 0.003s
[2K
| Adam | epoch: 817 | loss: 0.03631 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3266 | total loss: [1m[32m0.04027[0m[0m | time: 0.005s
[2K
| Adam | epoch: 817 | loss: 0.04027 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3267 | total loss: [1m[32m0.03870[0m[0m | time: 0.008s
[2K
| Adam | epoch: 817 | loss: 0.03870 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3268 | total loss: [1m[32m0.03850[0m[0m | time: 0.011s
[2K
| Adam | epoch: 817 | loss: 0.03850 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3269 | total loss: [1m[32m0.03857[0m[0m | time: 0.003s
[2K
| Adam | epoch: 818 | loss: 0.03857 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3270 | total loss: [1m[32m0.03531[0m[0m | time: 0.005s
[2K
| Adam | epoch: 818 | loss: 0.03531 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3271 | total loss: [1m[32m0.03237[0m[0m | time: 0.008s
[2K
| Adam | epoch: 818 | loss: 0.03237 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3272 | total loss: [1m[32m0.03533[0m[0m | time: 0.011s
[2K
| Adam | epoch: 818 | loss: 0.03533 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3273 | total loss: [1m[32m0.03475[0m[0m | time: 0.003s
[2K
| Adam | epoch: 819 | loss: 0.03475 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3274 | total loss: [1m[32m0.03470[0m[0m | time: 0.005s
[2K
| Adam | epoch: 819 | loss: 0.03470 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3275 | total loss: [1m[32m0.03846[0m[0m | time: 0.008s
[2K
| Adam | epoch: 819 | loss: 0.03846 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3276 | total loss: [1m[32m0.04184[0m[0m | time: 0.011s
[2K
| Adam | epoch: 819 | loss: 0.04184 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3277 | total loss: [1m[32m0.04137[0m[0m | time: 0.003s
[2K
| Adam | epoch: 820 | loss: 0.04137 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3278 | total loss: [1m[32m0.03897[0m[0m | time: 0.005s
[2K
| Adam | epoch: 820 | loss: 0.03897 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3279 | total loss: [1m[32m0.04274[0m[0m | time: 0.009s
[2K
| Adam | epoch: 820 | loss: 0.04274 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3280 | total loss: [1m[32m0.04201[0m[0m | time: 0.011s
[2K
| Adam | epoch: 820 | loss: 0.04201 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3281 | total loss: [1m[32m0.04133[0m[0m | time: 0.003s
[2K
| Adam | epoch: 821 | loss: 0.04133 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3282 | total loss: [1m[32m0.03996[0m[0m | time: 0.005s
[2K
| Adam | epoch: 821 | loss: 0.03996 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3283 | total loss: [1m[32m0.03664[0m[0m | time: 0.008s
[2K
| Adam | epoch: 821 | loss: 0.03664 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3284 | total loss: [1m[32m0.03461[0m[0m | time: 0.011s
[2K
| Adam | epoch: 821 | loss: 0.03461 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3285 | total loss: [1m[32m0.03347[0m[0m | time: 0.003s
[2K
| Adam | epoch: 822 | loss: 0.03347 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3286 | total loss: [1m[32m0.03243[0m[0m | time: 0.005s
[2K
| Adam | epoch: 822 | loss: 0.03243 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3287 | total loss: [1m[32m0.03117[0m[0m | time: 0.008s
[2K
| Adam | epoch: 822 | loss: 0.03117 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3288 | total loss: [1m[32m0.03624[0m[0m | time: 0.010s
[2K
| Adam | epoch: 822 | loss: 0.03624 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3289 | total loss: [1m[32m0.03493[0m[0m | time: 0.003s
[2K
| Adam | epoch: 823 | loss: 0.03493 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3290 | total loss: [1m[32m0.03860[0m[0m | time: 0.005s
[2K
| Adam | epoch: 823 | loss: 0.03860 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3291 | total loss: [1m[32m0.04189[0m[0m | time: 0.008s
[2K
| Adam | epoch: 823 | loss: 0.04189 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3292 | total loss: [1m[32m0.04239[0m[0m | time: 0.011s
[2K
| Adam | epoch: 823 | loss: 0.04239 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3293 | total loss: [1m[32m0.03987[0m[0m | time: 0.003s
[2K
| Adam | epoch: 824 | loss: 0.03987 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3294 | total loss: [1m[32m0.03840[0m[0m | time: 0.005s
[2K
| Adam | epoch: 824 | loss: 0.03840 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3295 | total loss: [1m[32m0.03608[0m[0m | time: 0.008s
[2K
| Adam | epoch: 824 | loss: 0.03608 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3296 | total loss: [1m[32m0.03399[0m[0m | time: 0.026s
[2K
| Adam | epoch: 824 | loss: 0.03399 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3297 | total loss: [1m[32m0.03413[0m[0m | time: 0.003s
[2K
| Adam | epoch: 825 | loss: 0.03413 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3298 | total loss: [1m[32m0.03683[0m[0m | time: 0.006s
[2K
| Adam | epoch: 825 | loss: 0.03683 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3299 | total loss: [1m[32m0.03972[0m[0m | time: 0.009s
[2K
| Adam | epoch: 825 | loss: 0.03972 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3300 | total loss: [1m[32m0.03868[0m[0m | time: 0.012s
[2K
| Adam | epoch: 825 | loss: 0.03868 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3301 | total loss: [1m[32m0.03772[0m[0m | time: 0.004s
[2K
| Adam | epoch: 826 | loss: 0.03772 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3302 | total loss: [1m[32m0.03648[0m[0m | time: 0.007s
[2K
| Adam | epoch: 826 | loss: 0.03648 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3303 | total loss: [1m[32m0.03498[0m[0m | time: 0.010s
[2K
| Adam | epoch: 826 | loss: 0.03498 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3304 | total loss: [1m[32m0.03752[0m[0m | time: 0.013s
[2K
| Adam | epoch: 826 | loss: 0.03752 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3305 | total loss: [1m[32m0.03720[0m[0m | time: 0.008s
[2K
| Adam | epoch: 827 | loss: 0.03720 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3306 | total loss: [1m[32m0.03687[0m[0m | time: 0.010s
[2K
| Adam | epoch: 827 | loss: 0.03687 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3307 | total loss: [1m[32m0.03401[0m[0m | time: 0.012s
[2K
| Adam | epoch: 827 | loss: 0.03401 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3308 | total loss: [1m[32m0.03465[0m[0m | time: 0.014s
[2K
| Adam | epoch: 827 | loss: 0.03465 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3309 | total loss: [1m[32m0.03372[0m[0m | time: 0.002s
[2K
| Adam | epoch: 828 | loss: 0.03372 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3310 | total loss: [1m[32m0.04123[0m[0m | time: 0.004s
[2K
| Adam | epoch: 828 | loss: 0.04123 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3311 | total loss: [1m[32m0.04797[0m[0m | time: 0.006s
[2K
| Adam | epoch: 828 | loss: 0.04797 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3312 | total loss: [1m[32m0.04433[0m[0m | time: 0.009s
[2K
| Adam | epoch: 828 | loss: 0.04433 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3313 | total loss: [1m[32m0.04240[0m[0m | time: 0.002s
[2K
| Adam | epoch: 829 | loss: 0.04240 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3314 | total loss: [1m[32m0.04491[0m[0m | time: 0.005s
[2K
| Adam | epoch: 829 | loss: 0.04491 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3315 | total loss: [1m[32m0.04503[0m[0m | time: 0.007s
[2K
| Adam | epoch: 829 | loss: 0.04503 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3316 | total loss: [1m[32m0.04510[0m[0m | time: 0.009s
[2K
| Adam | epoch: 829 | loss: 0.04510 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3317 | total loss: [1m[32m0.04236[0m[0m | time: 0.002s
[2K
| Adam | epoch: 830 | loss: 0.04236 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3318 | total loss: [1m[32m0.03968[0m[0m | time: 0.004s
[2K
| Adam | epoch: 830 | loss: 0.03968 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3319 | total loss: [1m[32m0.04081[0m[0m | time: 0.007s
[2K
| Adam | epoch: 830 | loss: 0.04081 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3320 | total loss: [1m[32m0.03773[0m[0m | time: 0.009s
[2K
| Adam | epoch: 830 | loss: 0.03773 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3321 | total loss: [1m[32m0.03496[0m[0m | time: 0.002s
[2K
| Adam | epoch: 831 | loss: 0.03496 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3322 | total loss: [1m[32m0.03697[0m[0m | time: 0.004s
[2K
| Adam | epoch: 831 | loss: 0.03697 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3323 | total loss: [1m[32m0.03481[0m[0m | time: 0.006s
[2K
| Adam | epoch: 831 | loss: 0.03481 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3324 | total loss: [1m[32m0.03353[0m[0m | time: 0.009s
[2K
| Adam | epoch: 831 | loss: 0.03353 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3325 | total loss: [1m[32m0.03352[0m[0m | time: 0.002s
[2K
| Adam | epoch: 832 | loss: 0.03352 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3326 | total loss: [1m[32m0.03344[0m[0m | time: 0.004s
[2K
| Adam | epoch: 832 | loss: 0.03344 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3327 | total loss: [1m[32m0.03277[0m[0m | time: 0.007s
[2K
| Adam | epoch: 832 | loss: 0.03277 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3328 | total loss: [1m[32m0.03533[0m[0m | time: 0.009s
[2K
| Adam | epoch: 832 | loss: 0.03533 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3329 | total loss: [1m[32m0.03352[0m[0m | time: 0.002s
[2K
| Adam | epoch: 833 | loss: 0.03352 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3330 | total loss: [1m[32m0.03928[0m[0m | time: 0.005s
[2K
| Adam | epoch: 833 | loss: 0.03928 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3331 | total loss: [1m[32m0.04445[0m[0m | time: 0.007s
[2K
| Adam | epoch: 833 | loss: 0.04445 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3332 | total loss: [1m[32m0.04375[0m[0m | time: 0.021s
[2K
| Adam | epoch: 833 | loss: 0.04375 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3333 | total loss: [1m[32m0.04086[0m[0m | time: 0.002s
[2K
| Adam | epoch: 834 | loss: 0.04086 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3334 | total loss: [1m[32m0.04195[0m[0m | time: 0.004s
[2K
| Adam | epoch: 834 | loss: 0.04195 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3335 | total loss: [1m[32m0.03980[0m[0m | time: 0.006s
[2K
| Adam | epoch: 834 | loss: 0.03980 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3336 | total loss: [1m[32m0.03785[0m[0m | time: 0.009s
[2K
| Adam | epoch: 834 | loss: 0.03785 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3337 | total loss: [1m[32m0.03445[0m[0m | time: 0.002s
[2K
| Adam | epoch: 835 | loss: 0.03445 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3338 | total loss: [1m[32m0.03674[0m[0m | time: 0.004s
[2K
| Adam | epoch: 835 | loss: 0.03674 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3339 | total loss: [1m[32m0.03875[0m[0m | time: 0.006s
[2K
| Adam | epoch: 835 | loss: 0.03875 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3340 | total loss: [1m[32m0.03767[0m[0m | time: 0.008s
[2K
| Adam | epoch: 835 | loss: 0.03767 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3341 | total loss: [1m[32m0.03670[0m[0m | time: 0.003s
[2K
| Adam | epoch: 836 | loss: 0.03670 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3342 | total loss: [1m[32m0.03489[0m[0m | time: 0.005s
[2K
| Adam | epoch: 836 | loss: 0.03489 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3343 | total loss: [1m[32m0.03466[0m[0m | time: 0.007s
[2K
| Adam | epoch: 836 | loss: 0.03466 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3344 | total loss: [1m[32m0.03287[0m[0m | time: 0.010s
[2K
| Adam | epoch: 836 | loss: 0.03287 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3345 | total loss: [1m[32m0.03119[0m[0m | time: 0.002s
[2K
| Adam | epoch: 837 | loss: 0.03119 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3346 | total loss: [1m[32m0.02967[0m[0m | time: 0.005s
[2K
| Adam | epoch: 837 | loss: 0.02967 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3347 | total loss: [1m[32m0.03420[0m[0m | time: 0.007s
[2K
| Adam | epoch: 837 | loss: 0.03420 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3348 | total loss: [1m[32m0.03302[0m[0m | time: 0.009s
[2K
| Adam | epoch: 837 | loss: 0.03302 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3349 | total loss: [1m[32m0.03103[0m[0m | time: 0.003s
[2K
| Adam | epoch: 838 | loss: 0.03103 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3350 | total loss: [1m[32m0.02930[0m[0m | time: 0.005s
[2K
| Adam | epoch: 838 | loss: 0.02930 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3351 | total loss: [1m[32m0.02774[0m[0m | time: 0.007s
[2K
| Adam | epoch: 838 | loss: 0.02774 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3352 | total loss: [1m[32m0.03028[0m[0m | time: 0.010s
[2K
| Adam | epoch: 838 | loss: 0.03028 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3353 | total loss: [1m[32m0.03214[0m[0m | time: 0.003s
[2K
| Adam | epoch: 839 | loss: 0.03214 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3354 | total loss: [1m[32m0.03064[0m[0m | time: 0.005s
[2K
| Adam | epoch: 839 | loss: 0.03064 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3355 | total loss: [1m[32m0.02969[0m[0m | time: 0.007s
[2K
| Adam | epoch: 839 | loss: 0.02969 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3356 | total loss: [1m[32m0.02883[0m[0m | time: 0.009s
[2K
| Adam | epoch: 839 | loss: 0.02883 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3357 | total loss: [1m[32m0.02842[0m[0m | time: 0.002s
[2K
| Adam | epoch: 840 | loss: 0.02842 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3358 | total loss: [1m[32m0.03238[0m[0m | time: 0.009s
[2K
| Adam | epoch: 840 | loss: 0.03238 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3359 | total loss: [1m[32m0.03252[0m[0m | time: 0.012s
[2K
| Adam | epoch: 840 | loss: 0.03252 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3360 | total loss: [1m[32m0.02956[0m[0m | time: 0.014s
[2K
| Adam | epoch: 840 | loss: 0.02956 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3361 | total loss: [1m[32m0.02689[0m[0m | time: 0.002s
[2K
| Adam | epoch: 841 | loss: 0.02689 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3362 | total loss: [1m[32m0.02723[0m[0m | time: 0.005s
[2K
| Adam | epoch: 841 | loss: 0.02723 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3363 | total loss: [1m[32m0.03018[0m[0m | time: 0.007s
[2K
| Adam | epoch: 841 | loss: 0.03018 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3364 | total loss: [1m[32m0.02998[0m[0m | time: 0.025s
[2K
| Adam | epoch: 841 | loss: 0.02998 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3365 | total loss: [1m[32m0.02970[0m[0m | time: 0.002s
[2K
| Adam | epoch: 842 | loss: 0.02970 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3366 | total loss: [1m[32m0.02945[0m[0m | time: 0.003s
[2K
| Adam | epoch: 842 | loss: 0.02945 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3367 | total loss: [1m[32m0.02812[0m[0m | time: 0.005s
[2K
| Adam | epoch: 842 | loss: 0.02812 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3368 | total loss: [1m[32m0.03138[0m[0m | time: 0.008s
[2K
| Adam | epoch: 842 | loss: 0.03138 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3369 | total loss: [1m[32m0.03191[0m[0m | time: 0.003s
[2K
| Adam | epoch: 843 | loss: 0.03191 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3370 | total loss: [1m[32m0.03010[0m[0m | time: 0.005s
[2K
| Adam | epoch: 843 | loss: 0.03010 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3371 | total loss: [1m[32m0.02847[0m[0m | time: 0.007s
[2K
| Adam | epoch: 843 | loss: 0.02847 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3372 | total loss: [1m[32m0.03138[0m[0m | time: 0.010s
[2K
| Adam | epoch: 843 | loss: 0.03138 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3373 | total loss: [1m[32m0.03008[0m[0m | time: 0.002s
[2K
| Adam | epoch: 844 | loss: 0.03008 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3374 | total loss: [1m[32m0.02953[0m[0m | time: 0.005s
[2K
| Adam | epoch: 844 | loss: 0.02953 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3375 | total loss: [1m[32m0.02994[0m[0m | time: 0.008s
[2K
| Adam | epoch: 844 | loss: 0.02994 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3376 | total loss: [1m[32m0.03029[0m[0m | time: 0.011s
[2K
| Adam | epoch: 844 | loss: 0.03029 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3377 | total loss: [1m[32m0.03307[0m[0m | time: 0.003s
[2K
| Adam | epoch: 845 | loss: 0.03307 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3378 | total loss: [1m[32m0.03150[0m[0m | time: 0.006s
[2K
| Adam | epoch: 845 | loss: 0.03150 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3379 | total loss: [1m[32m0.03054[0m[0m | time: 0.009s
[2K
| Adam | epoch: 845 | loss: 0.03054 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3380 | total loss: [1m[32m0.03685[0m[0m | time: 0.011s
[2K
| Adam | epoch: 845 | loss: 0.03685 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3381 | total loss: [1m[32m0.04252[0m[0m | time: 0.003s
[2K
| Adam | epoch: 846 | loss: 0.04252 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3382 | total loss: [1m[32m0.04069[0m[0m | time: 0.005s
[2K
| Adam | epoch: 846 | loss: 0.04069 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3383 | total loss: [1m[32m0.03818[0m[0m | time: 0.008s
[2K
| Adam | epoch: 846 | loss: 0.03818 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3384 | total loss: [1m[32m0.03634[0m[0m | time: 0.011s
[2K
| Adam | epoch: 846 | loss: 0.03634 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3385 | total loss: [1m[32m0.03695[0m[0m | time: 0.003s
[2K
| Adam | epoch: 847 | loss: 0.03695 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3386 | total loss: [1m[32m0.03748[0m[0m | time: 0.005s
[2K
| Adam | epoch: 847 | loss: 0.03748 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3387 | total loss: [1m[32m0.03996[0m[0m | time: 0.008s
[2K
| Adam | epoch: 847 | loss: 0.03996 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3388 | total loss: [1m[32m0.03709[0m[0m | time: 0.010s
[2K
| Adam | epoch: 847 | loss: 0.03709 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3389 | total loss: [1m[32m0.03985[0m[0m | time: 0.002s
[2K
| Adam | epoch: 848 | loss: 0.03985 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3390 | total loss: [1m[32m0.03735[0m[0m | time: 0.005s
[2K
| Adam | epoch: 848 | loss: 0.03735 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3391 | total loss: [1m[32m0.03511[0m[0m | time: 0.008s
[2K
| Adam | epoch: 848 | loss: 0.03511 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3392 | total loss: [1m[32m0.03344[0m[0m | time: 0.011s
[2K
| Adam | epoch: 848 | loss: 0.03344 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3393 | total loss: [1m[32m0.03273[0m[0m | time: 0.003s
[2K
| Adam | epoch: 849 | loss: 0.03273 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3394 | total loss: [1m[32m0.03722[0m[0m | time: 0.005s
[2K
| Adam | epoch: 849 | loss: 0.03722 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3395 | total loss: [1m[32m0.03512[0m[0m | time: 0.008s
[2K
| Adam | epoch: 849 | loss: 0.03512 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3396 | total loss: [1m[32m0.03322[0m[0m | time: 0.011s
[2K
| Adam | epoch: 849 | loss: 0.03322 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3397 | total loss: [1m[32m0.03149[0m[0m | time: 0.002s
[2K
| Adam | epoch: 850 | loss: 0.03149 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3398 | total loss: [1m[32m0.02981[0m[0m | time: 0.005s
[2K
| Adam | epoch: 850 | loss: 0.02981 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3399 | total loss: [1m[32m0.02964[0m[0m | time: 0.018s
[2K
| Adam | epoch: 850 | loss: 0.02964 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3400 | total loss: [1m[32m0.03503[0m[0m | time: 0.021s
[2K
| Adam | epoch: 850 | loss: 0.03503 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3401 | total loss: [1m[32m0.03986[0m[0m | time: 0.002s
[2K
| Adam | epoch: 851 | loss: 0.03986 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3402 | total loss: [1m[32m0.03727[0m[0m | time: 0.005s
[2K
| Adam | epoch: 851 | loss: 0.03727 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3403 | total loss: [1m[32m0.03596[0m[0m | time: 0.007s
[2K
| Adam | epoch: 851 | loss: 0.03596 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3404 | total loss: [1m[32m0.03507[0m[0m | time: 0.010s
[2K
| Adam | epoch: 851 | loss: 0.03507 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3405 | total loss: [1m[32m0.03987[0m[0m | time: 0.002s
[2K
| Adam | epoch: 852 | loss: 0.03987 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3406 | total loss: [1m[32m0.04416[0m[0m | time: 0.005s
[2K
| Adam | epoch: 852 | loss: 0.04416 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3407 | total loss: [1m[32m0.04117[0m[0m | time: 0.007s
[2K
| Adam | epoch: 852 | loss: 0.04117 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3408 | total loss: [1m[32m0.03948[0m[0m | time: 0.009s
[2K
| Adam | epoch: 852 | loss: 0.03948 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3409 | total loss: [1m[32m0.04089[0m[0m | time: 0.002s
[2K
| Adam | epoch: 853 | loss: 0.04089 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3410 | total loss: [1m[32m0.03841[0m[0m | time: 0.005s
[2K
| Adam | epoch: 853 | loss: 0.03841 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3411 | total loss: [1m[32m0.03617[0m[0m | time: 0.007s
[2K
| Adam | epoch: 853 | loss: 0.03617 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3412 | total loss: [1m[32m0.03604[0m[0m | time: 0.010s
[2K
| Adam | epoch: 853 | loss: 0.03604 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3413 | total loss: [1m[32m0.03428[0m[0m | time: 0.003s
[2K
| Adam | epoch: 854 | loss: 0.03428 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3414 | total loss: [1m[32m0.03286[0m[0m | time: 0.005s
[2K
| Adam | epoch: 854 | loss: 0.03286 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3415 | total loss: [1m[32m0.03388[0m[0m | time: 0.008s
[2K
| Adam | epoch: 854 | loss: 0.03388 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3416 | total loss: [1m[32m0.03478[0m[0m | time: 0.011s
[2K
| Adam | epoch: 854 | loss: 0.03478 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3417 | total loss: [1m[32m0.03589[0m[0m | time: 0.002s
[2K
| Adam | epoch: 855 | loss: 0.03589 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3418 | total loss: [1m[32m0.03461[0m[0m | time: 0.005s
[2K
| Adam | epoch: 855 | loss: 0.03461 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3419 | total loss: [1m[32m0.03652[0m[0m | time: 0.007s
[2K
| Adam | epoch: 855 | loss: 0.03652 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3420 | total loss: [1m[32m0.03514[0m[0m | time: 0.010s
[2K
| Adam | epoch: 855 | loss: 0.03514 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3421 | total loss: [1m[32m0.03389[0m[0m | time: 0.002s
[2K
| Adam | epoch: 856 | loss: 0.03389 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3422 | total loss: [1m[32m0.03234[0m[0m | time: 0.005s
[2K
| Adam | epoch: 856 | loss: 0.03234 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3423 | total loss: [1m[32m0.03205[0m[0m | time: 0.007s
[2K
| Adam | epoch: 856 | loss: 0.03205 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3424 | total loss: [1m[32m0.03111[0m[0m | time: 0.010s
[2K
| Adam | epoch: 856 | loss: 0.03111 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3425 | total loss: [1m[32m0.03121[0m[0m | time: 0.002s
[2K
| Adam | epoch: 857 | loss: 0.03121 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3426 | total loss: [1m[32m0.03127[0m[0m | time: 0.004s
[2K
| Adam | epoch: 857 | loss: 0.03127 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3427 | total loss: [1m[32m0.03231[0m[0m | time: 0.006s
[2K
| Adam | epoch: 857 | loss: 0.03231 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3428 | total loss: [1m[32m0.03216[0m[0m | time: 0.010s
[2K
| Adam | epoch: 857 | loss: 0.03216 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3429 | total loss: [1m[32m0.03156[0m[0m | time: 0.003s
[2K
| Adam | epoch: 858 | loss: 0.03156 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3430 | total loss: [1m[32m0.03603[0m[0m | time: 0.027s
[2K
| Adam | epoch: 858 | loss: 0.03603 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3431 | total loss: [1m[32m0.04003[0m[0m | time: 0.030s
[2K
| Adam | epoch: 858 | loss: 0.04003 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3432 | total loss: [1m[32m0.03919[0m[0m | time: 0.033s
[2K
| Adam | epoch: 858 | loss: 0.03919 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3433 | total loss: [1m[32m0.03620[0m[0m | time: 0.003s
[2K
| Adam | epoch: 859 | loss: 0.03620 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3434 | total loss: [1m[32m0.03642[0m[0m | time: 0.007s
[2K
| Adam | epoch: 859 | loss: 0.03642 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3435 | total loss: [1m[32m0.03338[0m[0m | time: 0.010s
[2K
| Adam | epoch: 859 | loss: 0.03338 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3436 | total loss: [1m[32m0.03064[0m[0m | time: 0.013s
[2K
| Adam | epoch: 859 | loss: 0.03064 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3437 | total loss: [1m[32m0.02977[0m[0m | time: 0.003s
[2K
| Adam | epoch: 860 | loss: 0.02977 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3438 | total loss: [1m[32m0.03176[0m[0m | time: 0.007s
[2K
| Adam | epoch: 860 | loss: 0.03176 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3439 | total loss: [1m[32m0.03130[0m[0m | time: 0.009s
[2K
| Adam | epoch: 860 | loss: 0.03130 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3440 | total loss: [1m[32m0.03102[0m[0m | time: 0.012s
[2K
| Adam | epoch: 860 | loss: 0.03102 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3441 | total loss: [1m[32m0.03074[0m[0m | time: 0.003s
[2K
| Adam | epoch: 861 | loss: 0.03074 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3442 | total loss: [1m[32m0.02945[0m[0m | time: 0.006s
[2K
| Adam | epoch: 861 | loss: 0.02945 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3443 | total loss: [1m[32m0.03159[0m[0m | time: 0.008s
[2K
| Adam | epoch: 861 | loss: 0.03159 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3444 | total loss: [1m[32m0.03130[0m[0m | time: 0.011s
[2K
| Adam | epoch: 861 | loss: 0.03130 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3445 | total loss: [1m[32m0.03107[0m[0m | time: 0.003s
[2K
| Adam | epoch: 862 | loss: 0.03107 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3446 | total loss: [1m[32m0.03084[0m[0m | time: 0.005s
[2K
| Adam | epoch: 862 | loss: 0.03084 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3447 | total loss: [1m[32m0.03283[0m[0m | time: 0.008s
[2K
| Adam | epoch: 862 | loss: 0.03283 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3448 | total loss: [1m[32m0.03113[0m[0m | time: 0.010s
[2K
| Adam | epoch: 862 | loss: 0.03113 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3449 | total loss: [1m[32m0.02980[0m[0m | time: 0.003s
[2K
| Adam | epoch: 863 | loss: 0.02980 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3450 | total loss: [1m[32m0.03631[0m[0m | time: 0.005s
[2K
| Adam | epoch: 863 | loss: 0.03631 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3451 | total loss: [1m[32m0.04214[0m[0m | time: 0.007s
[2K
| Adam | epoch: 863 | loss: 0.04214 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3452 | total loss: [1m[32m0.03962[0m[0m | time: 0.010s
[2K
| Adam | epoch: 863 | loss: 0.03962 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3453 | total loss: [1m[32m0.03750[0m[0m | time: 0.002s
[2K
| Adam | epoch: 864 | loss: 0.03750 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3454 | total loss: [1m[32m0.03752[0m[0m | time: 0.005s
[2K
| Adam | epoch: 864 | loss: 0.03752 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3455 | total loss: [1m[32m0.03439[0m[0m | time: 0.024s
[2K
| Adam | epoch: 864 | loss: 0.03439 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3456 | total loss: [1m[32m0.03158[0m[0m | time: 0.032s
[2K
| Adam | epoch: 864 | loss: 0.03158 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3457 | total loss: [1m[32m0.03475[0m[0m | time: 0.004s
[2K
| Adam | epoch: 865 | loss: 0.03475 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3458 | total loss: [1m[32m0.03192[0m[0m | time: 0.007s
[2K
| Adam | epoch: 865 | loss: 0.03192 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3459 | total loss: [1m[32m0.03036[0m[0m | time: 0.011s
[2K
| Adam | epoch: 865 | loss: 0.03036 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3460 | total loss: [1m[32m0.02833[0m[0m | time: 0.015s
[2K
| Adam | epoch: 865 | loss: 0.02833 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3461 | total loss: [1m[32m0.02651[0m[0m | time: 0.004s
[2K
| Adam | epoch: 866 | loss: 0.02651 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3462 | total loss: [1m[32m0.02579[0m[0m | time: 0.007s
[2K
| Adam | epoch: 866 | loss: 0.02579 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3463 | total loss: [1m[32m0.03012[0m[0m | time: 0.011s
[2K
| Adam | epoch: 866 | loss: 0.03012 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3464 | total loss: [1m[32m0.03011[0m[0m | time: 0.015s
[2K
| Adam | epoch: 866 | loss: 0.03011 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3465 | total loss: [1m[32m0.02960[0m[0m | time: 0.004s
[2K
| Adam | epoch: 867 | loss: 0.02960 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3466 | total loss: [1m[32m0.02914[0m[0m | time: 0.007s
[2K
| Adam | epoch: 867 | loss: 0.02914 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3467 | total loss: [1m[32m0.02813[0m[0m | time: 0.011s
[2K
| Adam | epoch: 867 | loss: 0.02813 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3468 | total loss: [1m[32m0.02989[0m[0m | time: 0.014s
[2K
| Adam | epoch: 867 | loss: 0.02989 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3469 | total loss: [1m[32m0.02775[0m[0m | time: 0.004s
[2K
| Adam | epoch: 868 | loss: 0.02775 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3470 | total loss: [1m[32m0.02619[0m[0m | time: 0.007s
[2K
| Adam | epoch: 868 | loss: 0.02619 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3471 | total loss: [1m[32m0.02478[0m[0m | time: 0.011s
[2K
| Adam | epoch: 868 | loss: 0.02478 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3472 | total loss: [1m[32m0.02866[0m[0m | time: 0.015s
[2K
| Adam | epoch: 868 | loss: 0.02866 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3473 | total loss: [1m[32m0.02881[0m[0m | time: 0.004s
[2K
| Adam | epoch: 869 | loss: 0.02881 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3474 | total loss: [1m[32m0.03201[0m[0m | time: 0.008s
[2K
| Adam | epoch: 869 | loss: 0.03201 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3475 | total loss: [1m[32m0.02914[0m[0m | time: 0.012s
[2K
| Adam | epoch: 869 | loss: 0.02914 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3476 | total loss: [1m[32m0.02656[0m[0m | time: 0.015s
[2K
| Adam | epoch: 869 | loss: 0.02656 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3477 | total loss: [1m[32m0.02711[0m[0m | time: 0.004s
[2K
| Adam | epoch: 870 | loss: 0.02711 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3478 | total loss: [1m[32m0.02587[0m[0m | time: 0.008s
[2K
| Adam | epoch: 870 | loss: 0.02587 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3479 | total loss: [1m[32m0.02894[0m[0m | time: 0.016s
[2K
| Adam | epoch: 870 | loss: 0.02894 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3480 | total loss: [1m[32m0.03037[0m[0m | time: 0.019s
[2K
| Adam | epoch: 870 | loss: 0.03037 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3481 | total loss: [1m[32m0.03164[0m[0m | time: 0.005s
[2K
| Adam | epoch: 871 | loss: 0.03164 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3482 | total loss: [1m[32m0.03001[0m[0m | time: 0.008s
[2K
| Adam | epoch: 871 | loss: 0.03001 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3483 | total loss: [1m[32m0.02801[0m[0m | time: 0.011s
[2K
| Adam | epoch: 871 | loss: 0.02801 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3484 | total loss: [1m[32m0.02671[0m[0m | time: 0.013s
[2K
| Adam | epoch: 871 | loss: 0.02671 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3485 | total loss: [1m[32m0.02739[0m[0m | time: 0.003s
[2K
| Adam | epoch: 872 | loss: 0.02739 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3486 | total loss: [1m[32m0.02800[0m[0m | time: 0.006s
[2K
| Adam | epoch: 872 | loss: 0.02800 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3487 | total loss: [1m[32m0.02675[0m[0m | time: 0.009s
[2K
| Adam | epoch: 872 | loss: 0.02675 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3488 | total loss: [1m[32m0.02975[0m[0m | time: 0.011s
[2K
| Adam | epoch: 872 | loss: 0.02975 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3489 | total loss: [1m[32m0.03017[0m[0m | time: 0.003s
[2K
| Adam | epoch: 873 | loss: 0.03017 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3490 | total loss: [1m[32m0.02885[0m[0m | time: 0.005s
[2K
| Adam | epoch: 873 | loss: 0.02885 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3491 | total loss: [1m[32m0.02765[0m[0m | time: 0.007s
[2K
| Adam | epoch: 873 | loss: 0.02765 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3492 | total loss: [1m[32m0.02596[0m[0m | time: 0.010s
[2K
| Adam | epoch: 873 | loss: 0.02596 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3493 | total loss: [1m[32m0.02865[0m[0m | time: 0.002s
[2K
| Adam | epoch: 874 | loss: 0.02865 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3494 | total loss: [1m[32m0.02700[0m[0m | time: 0.005s
[2K
| Adam | epoch: 874 | loss: 0.02700 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3495 | total loss: [1m[32m0.02553[0m[0m | time: 0.007s
[2K
| Adam | epoch: 874 | loss: 0.02553 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3496 | total loss: [1m[32m0.02420[0m[0m | time: 0.009s
[2K
| Adam | epoch: 874 | loss: 0.02420 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3497 | total loss: [1m[32m0.02422[0m[0m | time: 0.003s
[2K
| Adam | epoch: 875 | loss: 0.02422 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3498 | total loss: [1m[32m0.02813[0m[0m | time: 0.005s
[2K
| Adam | epoch: 875 | loss: 0.02813 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3499 | total loss: [1m[32m0.02757[0m[0m | time: 0.007s
[2K
| Adam | epoch: 875 | loss: 0.02757 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3500 | total loss: [1m[32m0.02513[0m[0m | time: 0.010s
[2K
| Adam | epoch: 875 | loss: 0.02513 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3501 | total loss: [1m[32m0.02293[0m[0m | time: 0.002s
[2K
| Adam | epoch: 876 | loss: 0.02293 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3502 | total loss: [1m[32m0.02174[0m[0m | time: 0.005s
[2K
| Adam | epoch: 876 | loss: 0.02174 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3503 | total loss: [1m[32m0.02220[0m[0m | time: 0.007s
[2K
| Adam | epoch: 876 | loss: 0.02220 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3504 | total loss: [1m[32m0.02255[0m[0m | time: 0.010s
[2K
| Adam | epoch: 876 | loss: 0.02255 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3505 | total loss: [1m[32m0.02152[0m[0m | time: 0.003s
[2K
| Adam | epoch: 877 | loss: 0.02152 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3506 | total loss: [1m[32m0.02058[0m[0m | time: 0.005s
[2K
| Adam | epoch: 877 | loss: 0.02058 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3507 | total loss: [1m[32m0.02321[0m[0m | time: 0.008s
[2K
| Adam | epoch: 877 | loss: 0.02321 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3508 | total loss: [1m[32m0.02352[0m[0m | time: 0.010s
[2K
| Adam | epoch: 877 | loss: 0.02352 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3509 | total loss: [1m[32m0.02308[0m[0m | time: 0.003s
[2K
| Adam | epoch: 878 | loss: 0.02308 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3510 | total loss: [1m[32m0.02194[0m[0m | time: 0.005s
[2K
| Adam | epoch: 878 | loss: 0.02194 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3511 | total loss: [1m[32m0.02091[0m[0m | time: 0.023s
[2K
| Adam | epoch: 878 | loss: 0.02091 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3512 | total loss: [1m[32m0.01999[0m[0m | time: 0.026s
[2K
| Adam | epoch: 878 | loss: 0.01999 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3513 | total loss: [1m[32m0.02479[0m[0m | time: 0.003s
[2K
| Adam | epoch: 879 | loss: 0.02479 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3514 | total loss: [1m[32m0.02459[0m[0m | time: 0.006s
[2K
| Adam | epoch: 879 | loss: 0.02459 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3515 | total loss: [1m[32m0.02281[0m[0m | time: 0.008s
[2K
| Adam | epoch: 879 | loss: 0.02281 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3516 | total loss: [1m[32m0.02119[0m[0m | time: 0.010s
[2K
| Adam | epoch: 879 | loss: 0.02119 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3517 | total loss: [1m[32m0.02394[0m[0m | time: 0.003s
[2K
| Adam | epoch: 880 | loss: 0.02394 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3518 | total loss: [1m[32m0.02453[0m[0m | time: 0.007s
[2K
| Adam | epoch: 880 | loss: 0.02453 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3519 | total loss: [1m[32m0.02341[0m[0m | time: 0.010s
[2K
| Adam | epoch: 880 | loss: 0.02341 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3520 | total loss: [1m[32m0.02216[0m[0m | time: 0.012s
[2K
| Adam | epoch: 880 | loss: 0.02216 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3521 | total loss: [1m[32m0.02104[0m[0m | time: 0.002s
[2K
| Adam | epoch: 881 | loss: 0.02104 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3522 | total loss: [1m[32m0.02167[0m[0m | time: 0.006s
[2K
| Adam | epoch: 881 | loss: 0.02167 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3523 | total loss: [1m[32m0.02527[0m[0m | time: 0.009s
[2K
| Adam | epoch: 881 | loss: 0.02527 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3524 | total loss: [1m[32m0.02767[0m[0m | time: 0.012s
[2K
| Adam | epoch: 881 | loss: 0.02767 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3525 | total loss: [1m[32m0.02678[0m[0m | time: 0.004s
[2K
| Adam | epoch: 882 | loss: 0.02678 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3526 | total loss: [1m[32m0.02597[0m[0m | time: 0.007s
[2K
| Adam | epoch: 882 | loss: 0.02597 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3527 | total loss: [1m[32m0.02535[0m[0m | time: 0.010s
[2K
| Adam | epoch: 882 | loss: 0.02535 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3528 | total loss: [1m[32m0.02521[0m[0m | time: 0.013s
[2K
| Adam | epoch: 882 | loss: 0.02521 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3529 | total loss: [1m[32m0.02373[0m[0m | time: 0.003s
[2K
| Adam | epoch: 883 | loss: 0.02373 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3530 | total loss: [1m[32m0.02348[0m[0m | time: 0.007s
[2K
| Adam | epoch: 883 | loss: 0.02348 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3531 | total loss: [1m[32m0.02324[0m[0m | time: 0.011s
[2K
| Adam | epoch: 883 | loss: 0.02324 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3532 | total loss: [1m[32m0.02312[0m[0m | time: 0.014s
[2K
| Adam | epoch: 883 | loss: 0.02312 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3533 | total loss: [1m[32m0.02666[0m[0m | time: 0.003s
[2K
| Adam | epoch: 884 | loss: 0.02666 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3534 | total loss: [1m[32m0.03015[0m[0m | time: 0.007s
[2K
| Adam | epoch: 884 | loss: 0.03015 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3535 | total loss: [1m[32m0.02813[0m[0m | time: 0.010s
[2K
| Adam | epoch: 884 | loss: 0.02813 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3536 | total loss: [1m[32m0.02630[0m[0m | time: 0.013s
[2K
| Adam | epoch: 884 | loss: 0.02630 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3537 | total loss: [1m[32m0.02502[0m[0m | time: 0.003s
[2K
| Adam | epoch: 885 | loss: 0.02502 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3538 | total loss: [1m[32m0.02481[0m[0m | time: 0.007s
[2K
| Adam | epoch: 885 | loss: 0.02481 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3539 | total loss: [1m[32m0.02400[0m[0m | time: 0.010s
[2K
| Adam | epoch: 885 | loss: 0.02400 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3540 | total loss: [1m[32m0.02254[0m[0m | time: 0.013s
[2K
| Adam | epoch: 885 | loss: 0.02254 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3541 | total loss: [1m[32m0.02122[0m[0m | time: 0.003s
[2K
| Adam | epoch: 886 | loss: 0.02122 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3542 | total loss: [1m[32m0.02494[0m[0m | time: 0.005s
[2K
| Adam | epoch: 886 | loss: 0.02494 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3543 | total loss: [1m[32m0.02469[0m[0m | time: 0.008s
[2K
| Adam | epoch: 886 | loss: 0.02469 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3544 | total loss: [1m[32m0.02469[0m[0m | time: 0.011s
[2K
| Adam | epoch: 886 | loss: 0.02469 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3545 | total loss: [1m[32m0.02464[0m[0m | time: 0.002s
[2K
| Adam | epoch: 887 | loss: 0.02464 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3546 | total loss: [1m[32m0.02457[0m[0m | time: 0.006s
[2K
| Adam | epoch: 887 | loss: 0.02457 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3547 | total loss: [1m[32m0.02630[0m[0m | time: 0.009s
[2K
| Adam | epoch: 887 | loss: 0.02630 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3548 | total loss: [1m[32m0.02582[0m[0m | time: 0.012s
[2K
| Adam | epoch: 887 | loss: 0.02582 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3549 | total loss: [1m[32m0.02441[0m[0m | time: 0.003s
[2K
| Adam | epoch: 888 | loss: 0.02441 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3550 | total loss: [1m[32m0.02358[0m[0m | time: 0.007s
[2K
| Adam | epoch: 888 | loss: 0.02358 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3551 | total loss: [1m[32m0.02283[0m[0m | time: 0.009s
[2K
| Adam | epoch: 888 | loss: 0.02283 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3552 | total loss: [1m[32m0.02167[0m[0m | time: 0.012s
[2K
| Adam | epoch: 888 | loss: 0.02167 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3553 | total loss: [1m[32m0.02645[0m[0m | time: 0.003s
[2K
| Adam | epoch: 889 | loss: 0.02645 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3554 | total loss: [1m[32m0.02448[0m[0m | time: 0.007s
[2K
| Adam | epoch: 889 | loss: 0.02448 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3555 | total loss: [1m[32m0.02288[0m[0m | time: 0.010s
[2K
| Adam | epoch: 889 | loss: 0.02288 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3556 | total loss: [1m[32m0.02143[0m[0m | time: 0.012s
[2K
| Adam | epoch: 889 | loss: 0.02143 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3557 | total loss: [1m[32m0.02187[0m[0m | time: 0.002s
[2K
| Adam | epoch: 890 | loss: 0.02187 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3558 | total loss: [1m[32m0.02611[0m[0m | time: 0.006s
[2K
| Adam | epoch: 890 | loss: 0.02611 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3559 | total loss: [1m[32m0.02859[0m[0m | time: 0.009s
[2K
| Adam | epoch: 890 | loss: 0.02859 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3560 | total loss: [1m[32m0.02706[0m[0m | time: 0.012s
[2K
| Adam | epoch: 890 | loss: 0.02706 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3561 | total loss: [1m[32m0.02568[0m[0m | time: 0.002s
[2K
| Adam | epoch: 891 | loss: 0.02568 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3562 | total loss: [1m[32m0.02598[0m[0m | time: 0.006s
[2K
| Adam | epoch: 891 | loss: 0.02598 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3563 | total loss: [1m[32m0.02477[0m[0m | time: 0.009s
[2K
| Adam | epoch: 891 | loss: 0.02477 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3564 | total loss: [1m[32m0.02347[0m[0m | time: 0.011s
[2K
| Adam | epoch: 891 | loss: 0.02347 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3565 | total loss: [1m[32m0.02531[0m[0m | time: 0.002s
[2K
| Adam | epoch: 892 | loss: 0.02531 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3566 | total loss: [1m[32m0.02695[0m[0m | time: 0.006s
[2K
| Adam | epoch: 892 | loss: 0.02695 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3567 | total loss: [1m[32m0.02984[0m[0m | time: 0.009s
[2K
| Adam | epoch: 892 | loss: 0.02984 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3568 | total loss: [1m[32m0.02763[0m[0m | time: 0.012s
[2K
| Adam | epoch: 892 | loss: 0.02763 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3569 | total loss: [1m[32m0.02947[0m[0m | time: 0.002s
[2K
| Adam | epoch: 893 | loss: 0.02947 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3570 | total loss: [1m[32m0.02942[0m[0m | time: 0.005s
[2K
| Adam | epoch: 893 | loss: 0.02942 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3571 | total loss: [1m[32m0.02934[0m[0m | time: 0.008s
[2K
| Adam | epoch: 893 | loss: 0.02934 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3572 | total loss: [1m[32m0.02979[0m[0m | time: 0.011s
[2K
| Adam | epoch: 893 | loss: 0.02979 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3573 | total loss: [1m[32m0.02715[0m[0m | time: 0.003s
[2K
| Adam | epoch: 894 | loss: 0.02715 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3574 | total loss: [1m[32m0.02505[0m[0m | time: 0.005s
[2K
| Adam | epoch: 894 | loss: 0.02505 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3575 | total loss: [1m[32m0.02885[0m[0m | time: 0.009s
[2K
| Adam | epoch: 894 | loss: 0.02885 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3576 | total loss: [1m[32m0.03224[0m[0m | time: 0.011s
[2K
| Adam | epoch: 894 | loss: 0.03224 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3577 | total loss: [1m[32m0.03294[0m[0m | time: 0.002s
[2K
| Adam | epoch: 895 | loss: 0.03294 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3578 | total loss: [1m[32m0.03123[0m[0m | time: 0.006s
[2K
| Adam | epoch: 895 | loss: 0.03123 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3579 | total loss: [1m[32m0.03388[0m[0m | time: 0.008s
[2K
| Adam | epoch: 895 | loss: 0.03388 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3580 | total loss: [1m[32m0.03089[0m[0m | time: 0.010s
[2K
| Adam | epoch: 895 | loss: 0.03089 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3581 | total loss: [1m[32m0.02820[0m[0m | time: 0.003s
[2K
| Adam | epoch: 896 | loss: 0.02820 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3582 | total loss: [1m[32m0.02679[0m[0m | time: 0.006s
[2K
| Adam | epoch: 896 | loss: 0.02679 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3583 | total loss: [1m[32m0.02667[0m[0m | time: 0.009s
[2K
| Adam | epoch: 896 | loss: 0.02667 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3584 | total loss: [1m[32m0.02459[0m[0m | time: 0.012s
[2K
| Adam | epoch: 896 | loss: 0.02459 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3585 | total loss: [1m[32m0.02853[0m[0m | time: 0.003s
[2K
| Adam | epoch: 897 | loss: 0.02853 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3586 | total loss: [1m[32m0.03205[0m[0m | time: 0.006s
[2K
| Adam | epoch: 897 | loss: 0.03205 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3587 | total loss: [1m[32m0.03050[0m[0m | time: 0.009s
[2K
| Adam | epoch: 897 | loss: 0.03050 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3588 | total loss: [1m[32m0.03120[0m[0m | time: 0.012s
[2K
| Adam | epoch: 897 | loss: 0.03120 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3589 | total loss: [1m[32m0.02920[0m[0m | time: 0.003s
[2K
| Adam | epoch: 898 | loss: 0.02920 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3590 | total loss: [1m[32m0.03396[0m[0m | time: 0.005s
[2K
| Adam | epoch: 898 | loss: 0.03396 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3591 | total loss: [1m[32m0.03819[0m[0m | time: 0.008s
[2K
| Adam | epoch: 898 | loss: 0.03819 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3592 | total loss: [1m[32m0.03714[0m[0m | time: 0.012s
[2K
| Adam | epoch: 898 | loss: 0.03714 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3593 | total loss: [1m[32m0.03470[0m[0m | time: 0.003s
[2K
| Adam | epoch: 899 | loss: 0.03470 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3594 | total loss: [1m[32m0.03189[0m[0m | time: 0.006s
[2K
| Adam | epoch: 899 | loss: 0.03189 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3595 | total loss: [1m[32m0.03700[0m[0m | time: 0.009s
[2K
| Adam | epoch: 899 | loss: 0.03700 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3596 | total loss: [1m[32m0.04152[0m[0m | time: 0.011s
[2K
| Adam | epoch: 899 | loss: 0.04152 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3597 | total loss: [1m[32m0.03982[0m[0m | time: 0.003s
[2K
| Adam | epoch: 900 | loss: 0.03982 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3598 | total loss: [1m[32m0.03754[0m[0m | time: 0.006s
[2K
| Adam | epoch: 900 | loss: 0.03754 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3599 | total loss: [1m[32m0.03501[0m[0m | time: 0.010s
[2K
| Adam | epoch: 900 | loss: 0.03501 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3600 | total loss: [1m[32m0.03922[0m[0m | time: 0.015s
[2K
| Adam | epoch: 900 | loss: 0.03922 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3601 | total loss: [1m[32m0.04297[0m[0m | time: 0.003s
[2K
| Adam | epoch: 901 | loss: 0.04297 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3602 | total loss: [1m[32m0.04128[0m[0m | time: 0.006s
[2K
| Adam | epoch: 901 | loss: 0.04128 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3603 | total loss: [1m[32m0.03841[0m[0m | time: 0.008s
[2K
| Adam | epoch: 901 | loss: 0.03841 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3604 | total loss: [1m[32m0.03601[0m[0m | time: 0.010s
[2K
| Adam | epoch: 901 | loss: 0.03601 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3605 | total loss: [1m[32m0.03474[0m[0m | time: 0.015s
[2K
| Adam | epoch: 902 | loss: 0.03474 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3606 | total loss: [1m[32m0.03358[0m[0m | time: 0.018s
[2K
| Adam | epoch: 902 | loss: 0.03358 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3607 | total loss: [1m[32m0.03479[0m[0m | time: 0.021s
[2K
| Adam | epoch: 902 | loss: 0.03479 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3608 | total loss: [1m[32m0.03371[0m[0m | time: 0.023s
[2K
| Adam | epoch: 902 | loss: 0.03371 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3609 | total loss: [1m[32m0.03476[0m[0m | time: 0.002s
[2K
| Adam | epoch: 903 | loss: 0.03476 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3610 | total loss: [1m[32m0.03341[0m[0m | time: 0.005s
[2K
| Adam | epoch: 903 | loss: 0.03341 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3611 | total loss: [1m[32m0.03216[0m[0m | time: 0.007s
[2K
| Adam | epoch: 903 | loss: 0.03216 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3612 | total loss: [1m[32m0.03121[0m[0m | time: 0.010s
[2K
| Adam | epoch: 903 | loss: 0.03121 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3613 | total loss: [1m[32m0.02994[0m[0m | time: 0.002s
[2K
| Adam | epoch: 904 | loss: 0.02994 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3614 | total loss: [1m[32m0.02904[0m[0m | time: 0.005s
[2K
| Adam | epoch: 904 | loss: 0.02904 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3615 | total loss: [1m[32m0.02995[0m[0m | time: 0.007s
[2K
| Adam | epoch: 904 | loss: 0.02995 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3616 | total loss: [1m[32m0.03069[0m[0m | time: 0.011s
[2K
| Adam | epoch: 904 | loss: 0.03069 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3617 | total loss: [1m[32m0.02860[0m[0m | time: 0.004s
[2K
| Adam | epoch: 905 | loss: 0.02860 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3618 | total loss: [1m[32m0.03012[0m[0m | time: 0.007s
[2K
| Adam | epoch: 905 | loss: 0.03012 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3619 | total loss: [1m[32m0.02784[0m[0m | time: 0.010s
[2K
| Adam | epoch: 905 | loss: 0.02784 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3620 | total loss: [1m[32m0.02786[0m[0m | time: 0.012s
[2K
| Adam | epoch: 905 | loss: 0.02786 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3621 | total loss: [1m[32m0.02781[0m[0m | time: 0.002s
[2K
| Adam | epoch: 906 | loss: 0.02781 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3622 | total loss: [1m[32m0.03002[0m[0m | time: 0.006s
[2K
| Adam | epoch: 906 | loss: 0.03002 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3623 | total loss: [1m[32m0.02918[0m[0m | time: 0.008s
[2K
| Adam | epoch: 906 | loss: 0.02918 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3624 | total loss: [1m[32m0.02867[0m[0m | time: 0.012s
[2K
| Adam | epoch: 906 | loss: 0.02867 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3625 | total loss: [1m[32m0.02700[0m[0m | time: 0.003s
[2K
| Adam | epoch: 907 | loss: 0.02700 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3626 | total loss: [1m[32m0.02548[0m[0m | time: 0.007s
[2K
| Adam | epoch: 907 | loss: 0.02548 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3627 | total loss: [1m[32m0.02878[0m[0m | time: 0.010s
[2K
| Adam | epoch: 907 | loss: 0.02878 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3628 | total loss: [1m[32m0.02637[0m[0m | time: 0.012s
[2K
| Adam | epoch: 907 | loss: 0.02637 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3629 | total loss: [1m[32m0.02525[0m[0m | time: 0.003s
[2K
| Adam | epoch: 908 | loss: 0.02525 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3630 | total loss: [1m[32m0.02450[0m[0m | time: 0.006s
[2K
| Adam | epoch: 908 | loss: 0.02450 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3631 | total loss: [1m[32m0.02382[0m[0m | time: 0.008s
[2K
| Adam | epoch: 908 | loss: 0.02382 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3632 | total loss: [1m[32m0.02742[0m[0m | time: 0.010s
[2K
| Adam | epoch: 908 | loss: 0.02742 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3633 | total loss: [1m[32m0.02555[0m[0m | time: 0.002s
[2K
| Adam | epoch: 909 | loss: 0.02555 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3634 | total loss: [1m[32m0.02375[0m[0m | time: 0.005s
[2K
| Adam | epoch: 909 | loss: 0.02375 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3635 | total loss: [1m[32m0.02425[0m[0m | time: 0.008s
[2K
| Adam | epoch: 909 | loss: 0.02425 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3636 | total loss: [1m[32m0.02469[0m[0m | time: 0.011s
[2K
| Adam | epoch: 909 | loss: 0.02469 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3637 | total loss: [1m[32m0.02741[0m[0m | time: 0.003s
[2K
| Adam | epoch: 910 | loss: 0.02741 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3638 | total loss: [1m[32m0.02634[0m[0m | time: 0.007s
[2K
| Adam | epoch: 910 | loss: 0.02634 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3639 | total loss: [1m[32m0.02852[0m[0m | time: 0.015s
[2K
| Adam | epoch: 910 | loss: 0.02852 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3640 | total loss: [1m[32m0.02681[0m[0m | time: 0.017s
[2K
| Adam | epoch: 910 | loss: 0.02681 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3641 | total loss: [1m[32m0.02526[0m[0m | time: 0.002s
[2K
| Adam | epoch: 911 | loss: 0.02526 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3642 | total loss: [1m[32m0.02479[0m[0m | time: 0.005s
[2K
| Adam | epoch: 911 | loss: 0.02479 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3643 | total loss: [1m[32m0.02411[0m[0m | time: 0.007s
[2K
| Adam | epoch: 911 | loss: 0.02411 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3644 | total loss: [1m[32m0.02364[0m[0m | time: 0.010s
[2K
| Adam | epoch: 911 | loss: 0.02364 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3645 | total loss: [1m[32m0.02184[0m[0m | time: 0.003s
[2K
| Adam | epoch: 912 | loss: 0.02184 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3646 | total loss: [1m[32m0.02021[0m[0m | time: 0.008s
[2K
| Adam | epoch: 912 | loss: 0.02021 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3647 | total loss: [1m[32m0.02221[0m[0m | time: 0.012s
[2K
| Adam | epoch: 912 | loss: 0.02221 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3648 | total loss: [1m[32m0.02300[0m[0m | time: 0.017s
[2K
| Adam | epoch: 912 | loss: 0.02300 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3649 | total loss: [1m[32m0.02205[0m[0m | time: 0.005s
[2K
| Adam | epoch: 913 | loss: 0.02205 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3650 | total loss: [1m[32m0.02089[0m[0m | time: 0.009s
[2K
| Adam | epoch: 913 | loss: 0.02089 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3651 | total loss: [1m[32m0.01984[0m[0m | time: 0.012s
[2K
| Adam | epoch: 913 | loss: 0.01984 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3652 | total loss: [1m[32m0.01920[0m[0m | time: 0.015s
[2K
| Adam | epoch: 913 | loss: 0.01920 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3653 | total loss: [1m[32m0.02320[0m[0m | time: 0.003s
[2K
| Adam | epoch: 914 | loss: 0.02320 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3654 | total loss: [1m[32m0.02236[0m[0m | time: 0.007s
[2K
| Adam | epoch: 914 | loss: 0.02236 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3655 | total loss: [1m[32m0.02160[0m[0m | time: 0.010s
[2K
| Adam | epoch: 914 | loss: 0.02160 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3656 | total loss: [1m[32m0.02092[0m[0m | time: 0.013s
[2K
| Adam | epoch: 914 | loss: 0.02092 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3657 | total loss: [1m[32m0.02403[0m[0m | time: 0.003s
[2K
| Adam | epoch: 915 | loss: 0.02403 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3658 | total loss: [1m[32m0.02326[0m[0m | time: 0.007s
[2K
| Adam | epoch: 915 | loss: 0.02326 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3659 | total loss: [1m[32m0.02674[0m[0m | time: 0.010s
[2K
| Adam | epoch: 915 | loss: 0.02674 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3660 | total loss: [1m[32m0.02562[0m[0m | time: 0.013s
[2K
| Adam | epoch: 915 | loss: 0.02562 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3661 | total loss: [1m[32m0.02462[0m[0m | time: 0.003s
[2K
| Adam | epoch: 916 | loss: 0.02462 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3662 | total loss: [1m[32m0.02339[0m[0m | time: 0.007s
[2K
| Adam | epoch: 916 | loss: 0.02339 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3663 | total loss: [1m[32m0.02223[0m[0m | time: 0.010s
[2K
| Adam | epoch: 916 | loss: 0.02223 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3664 | total loss: [1m[32m0.02478[0m[0m | time: 0.013s
[2K
| Adam | epoch: 916 | loss: 0.02478 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3665 | total loss: [1m[32m0.02567[0m[0m | time: 0.002s
[2K
| Adam | epoch: 917 | loss: 0.02567 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3666 | total loss: [1m[32m0.02647[0m[0m | time: 0.005s
[2K
| Adam | epoch: 917 | loss: 0.02647 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3667 | total loss: [1m[32m0.02483[0m[0m | time: 0.008s
[2K
| Adam | epoch: 917 | loss: 0.02483 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3668 | total loss: [1m[32m0.02361[0m[0m | time: 0.010s
[2K
| Adam | epoch: 917 | loss: 0.02361 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3669 | total loss: [1m[32m0.02399[0m[0m | time: 0.003s
[2K
| Adam | epoch: 918 | loss: 0.02399 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3670 | total loss: [1m[32m0.02251[0m[0m | time: 0.005s
[2K
| Adam | epoch: 918 | loss: 0.02251 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3671 | total loss: [1m[32m0.02116[0m[0m | time: 0.008s
[2K
| Adam | epoch: 918 | loss: 0.02116 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3672 | total loss: [1m[32m0.02039[0m[0m | time: 0.010s
[2K
| Adam | epoch: 918 | loss: 0.02039 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3673 | total loss: [1m[32m0.02283[0m[0m | time: 0.002s
[2K
| Adam | epoch: 919 | loss: 0.02283 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3674 | total loss: [1m[32m0.02180[0m[0m | time: 0.005s
[2K
| Adam | epoch: 919 | loss: 0.02180 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3675 | total loss: [1m[32m0.02592[0m[0m | time: 0.007s
[2K
| Adam | epoch: 919 | loss: 0.02592 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3676 | total loss: [1m[32m0.02962[0m[0m | time: 0.010s
[2K
| Adam | epoch: 919 | loss: 0.02962 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3677 | total loss: [1m[32m0.02861[0m[0m | time: 0.004s
[2K
| Adam | epoch: 920 | loss: 0.02861 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3678 | total loss: [1m[32m0.02767[0m[0m | time: 0.008s
[2K
| Adam | epoch: 920 | loss: 0.02767 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3679 | total loss: [1m[32m0.02798[0m[0m | time: 0.010s
[2K
| Adam | epoch: 920 | loss: 0.02798 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3680 | total loss: [1m[32m0.03131[0m[0m | time: 0.013s
[2K
| Adam | epoch: 920 | loss: 0.03131 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3681 | total loss: [1m[32m0.03427[0m[0m | time: 0.002s
[2K
| Adam | epoch: 921 | loss: 0.03427 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3682 | total loss: [1m[32m0.03238[0m[0m | time: 0.005s
[2K
| Adam | epoch: 921 | loss: 0.03238 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3683 | total loss: [1m[32m0.02972[0m[0m | time: 0.008s
[2K
| Adam | epoch: 921 | loss: 0.02972 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3684 | total loss: [1m[32m0.02902[0m[0m | time: 0.010s
[2K
| Adam | epoch: 921 | loss: 0.02902 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3685 | total loss: [1m[32m0.02786[0m[0m | time: 0.003s
[2K
| Adam | epoch: 922 | loss: 0.02786 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3686 | total loss: [1m[32m0.02681[0m[0m | time: 0.005s
[2K
| Adam | epoch: 922 | loss: 0.02681 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3687 | total loss: [1m[32m0.02755[0m[0m | time: 0.007s
[2K
| Adam | epoch: 922 | loss: 0.02755 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3688 | total loss: [1m[32m0.02701[0m[0m | time: 0.010s
[2K
| Adam | epoch: 922 | loss: 0.02701 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3689 | total loss: [1m[32m0.02535[0m[0m | time: 0.002s
[2K
| Adam | epoch: 923 | loss: 0.02535 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3690 | total loss: [1m[32m0.02850[0m[0m | time: 0.005s
[2K
| Adam | epoch: 923 | loss: 0.02850 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3691 | total loss: [1m[32m0.03130[0m[0m | time: 0.007s
[2K
| Adam | epoch: 923 | loss: 0.03130 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3692 | total loss: [1m[32m0.03037[0m[0m | time: 0.009s
[2K
| Adam | epoch: 923 | loss: 0.03037 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3693 | total loss: [1m[32m0.02953[0m[0m | time: 0.002s
[2K
| Adam | epoch: 924 | loss: 0.02953 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3694 | total loss: [1m[32m0.02768[0m[0m | time: 0.005s
[2K
| Adam | epoch: 924 | loss: 0.02768 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3695 | total loss: [1m[32m0.02596[0m[0m | time: 0.007s
[2K
| Adam | epoch: 924 | loss: 0.02596 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3696 | total loss: [1m[32m0.02441[0m[0m | time: 0.010s
[2K
| Adam | epoch: 924 | loss: 0.02441 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3697 | total loss: [1m[32m0.02318[0m[0m | time: 0.002s
[2K
| Adam | epoch: 925 | loss: 0.02318 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3698 | total loss: [1m[32m0.02680[0m[0m | time: 0.005s
[2K
| Adam | epoch: 925 | loss: 0.02680 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3699 | total loss: [1m[32m0.02906[0m[0m | time: 0.007s
[2K
| Adam | epoch: 925 | loss: 0.02906 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3700 | total loss: [1m[32m0.02724[0m[0m | time: 0.009s
[2K
| Adam | epoch: 925 | loss: 0.02724 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3701 | total loss: [1m[32m0.02559[0m[0m | time: 0.002s
[2K
| Adam | epoch: 926 | loss: 0.02559 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3702 | total loss: [1m[32m0.02452[0m[0m | time: 0.004s
[2K
| Adam | epoch: 926 | loss: 0.02452 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3703 | total loss: [1m[32m0.02388[0m[0m | time: 0.006s
[2K
| Adam | epoch: 926 | loss: 0.02388 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3704 | total loss: [1m[32m0.02167[0m[0m | time: 0.009s
[2K
| Adam | epoch: 926 | loss: 0.02167 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3705 | total loss: [1m[32m0.02125[0m[0m | time: 0.002s
[2K
| Adam | epoch: 927 | loss: 0.02125 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3706 | total loss: [1m[32m0.02086[0m[0m | time: 0.005s
[2K
| Adam | epoch: 927 | loss: 0.02086 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3707 | total loss: [1m[32m0.02471[0m[0m | time: 0.007s
[2K
| Adam | epoch: 927 | loss: 0.02471 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3708 | total loss: [1m[32m0.02387[0m[0m | time: 0.009s
[2K
| Adam | epoch: 927 | loss: 0.02387 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3709 | total loss: [1m[32m0.02199[0m[0m | time: 0.003s
[2K
| Adam | epoch: 928 | loss: 0.02199 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3710 | total loss: [1m[32m0.02228[0m[0m | time: 0.005s
[2K
| Adam | epoch: 928 | loss: 0.02228 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3711 | total loss: [1m[32m0.02253[0m[0m | time: 0.007s
[2K
| Adam | epoch: 928 | loss: 0.02253 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3712 | total loss: [1m[32m0.02499[0m[0m | time: 0.009s
[2K
| Adam | epoch: 928 | loss: 0.02499 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3713 | total loss: [1m[32m0.02451[0m[0m | time: 0.003s
[2K
| Adam | epoch: 929 | loss: 0.02451 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3714 | total loss: [1m[32m0.02632[0m[0m | time: 0.005s
[2K
| Adam | epoch: 929 | loss: 0.02632 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3715 | total loss: [1m[32m0.02518[0m[0m | time: 0.007s
[2K
| Adam | epoch: 929 | loss: 0.02518 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3716 | total loss: [1m[32m0.02413[0m[0m | time: 0.010s
[2K
| Adam | epoch: 929 | loss: 0.02413 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3717 | total loss: [1m[32m0.02384[0m[0m | time: 0.002s
[2K
| Adam | epoch: 930 | loss: 0.02384 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3718 | total loss: [1m[32m0.02290[0m[0m | time: 0.005s
[2K
| Adam | epoch: 930 | loss: 0.02290 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3719 | total loss: [1m[32m0.02189[0m[0m | time: 0.007s
[2K
| Adam | epoch: 930 | loss: 0.02189 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3720 | total loss: [1m[32m0.02220[0m[0m | time: 0.010s
[2K
| Adam | epoch: 930 | loss: 0.02220 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3721 | total loss: [1m[32m0.02245[0m[0m | time: 0.002s
[2K
| Adam | epoch: 931 | loss: 0.02245 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3722 | total loss: [1m[32m0.02157[0m[0m | time: 0.005s
[2K
| Adam | epoch: 931 | loss: 0.02157 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3723 | total loss: [1m[32m0.02396[0m[0m | time: 0.007s
[2K
| Adam | epoch: 931 | loss: 0.02396 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3724 | total loss: [1m[32m0.02272[0m[0m | time: 0.009s
[2K
| Adam | epoch: 931 | loss: 0.02272 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3725 | total loss: [1m[32m0.02201[0m[0m | time: 0.003s
[2K
| Adam | epoch: 932 | loss: 0.02201 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3726 | total loss: [1m[32m0.02136[0m[0m | time: 0.005s
[2K
| Adam | epoch: 932 | loss: 0.02136 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3727 | total loss: [1m[32m0.02042[0m[0m | time: 0.007s
[2K
| Adam | epoch: 932 | loss: 0.02042 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3728 | total loss: [1m[32m0.02370[0m[0m | time: 0.010s
[2K
| Adam | epoch: 932 | loss: 0.02370 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3729 | total loss: [1m[32m0.02283[0m[0m | time: 0.002s
[2K
| Adam | epoch: 933 | loss: 0.02283 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3730 | total loss: [1m[32m0.02120[0m[0m | time: 0.005s
[2K
| Adam | epoch: 933 | loss: 0.02120 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3731 | total loss: [1m[32m0.01973[0m[0m | time: 0.007s
[2K
| Adam | epoch: 933 | loss: 0.01973 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3732 | total loss: [1m[32m0.02370[0m[0m | time: 0.009s
[2K
| Adam | epoch: 933 | loss: 0.02370 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3733 | total loss: [1m[32m0.02207[0m[0m | time: 0.003s
[2K
| Adam | epoch: 934 | loss: 0.02207 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3734 | total loss: [1m[32m0.02398[0m[0m | time: 0.005s
[2K
| Adam | epoch: 934 | loss: 0.02398 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3735 | total loss: [1m[32m0.02292[0m[0m | time: 0.007s
[2K
| Adam | epoch: 934 | loss: 0.02292 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3736 | total loss: [1m[32m0.02195[0m[0m | time: 0.010s
[2K
| Adam | epoch: 934 | loss: 0.02195 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3737 | total loss: [1m[32m0.02238[0m[0m | time: 0.003s
[2K
| Adam | epoch: 935 | loss: 0.02238 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3738 | total loss: [1m[32m0.02115[0m[0m | time: 0.020s
[2K
| Adam | epoch: 935 | loss: 0.02115 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3739 | total loss: [1m[32m0.02017[0m[0m | time: 0.023s
[2K
| Adam | epoch: 935 | loss: 0.02017 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3740 | total loss: [1m[32m0.02035[0m[0m | time: 0.025s
[2K
| Adam | epoch: 935 | loss: 0.02035 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3741 | total loss: [1m[32m0.02051[0m[0m | time: 0.002s
[2K
| Adam | epoch: 936 | loss: 0.02051 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3742 | total loss: [1m[32m0.02217[0m[0m | time: 0.005s
[2K
| Adam | epoch: 936 | loss: 0.02217 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3743 | total loss: [1m[32m0.02230[0m[0m | time: 0.008s
[2K
| Adam | epoch: 936 | loss: 0.02230 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3744 | total loss: [1m[32m0.02119[0m[0m | time: 0.011s
[2K
| Adam | epoch: 936 | loss: 0.02119 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3745 | total loss: [1m[32m0.02282[0m[0m | time: 0.002s
[2K
| Adam | epoch: 937 | loss: 0.02282 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3746 | total loss: [1m[32m0.02428[0m[0m | time: 0.005s
[2K
| Adam | epoch: 937 | loss: 0.02428 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3747 | total loss: [1m[32m0.02272[0m[0m | time: 0.007s
[2K
| Adam | epoch: 937 | loss: 0.02272 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3748 | total loss: [1m[32m0.02465[0m[0m | time: 0.009s
[2K
| Adam | epoch: 937 | loss: 0.02465 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3749 | total loss: [1m[32m0.02302[0m[0m | time: 0.002s
[2K
| Adam | epoch: 938 | loss: 0.02302 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3750 | total loss: [1m[32m0.02128[0m[0m | time: 0.005s
[2K
| Adam | epoch: 938 | loss: 0.02128 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3751 | total loss: [1m[32m0.01971[0m[0m | time: 0.007s
[2K
| Adam | epoch: 938 | loss: 0.01971 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3752 | total loss: [1m[32m0.02245[0m[0m | time: 0.010s
[2K
| Adam | epoch: 938 | loss: 0.02245 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3753 | total loss: [1m[32m0.02278[0m[0m | time: 0.002s
[2K
| Adam | epoch: 939 | loss: 0.02278 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3754 | total loss: [1m[32m0.02276[0m[0m | time: 0.005s
[2K
| Adam | epoch: 939 | loss: 0.02276 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3755 | total loss: [1m[32m0.02133[0m[0m | time: 0.007s
[2K
| Adam | epoch: 939 | loss: 0.02133 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3756 | total loss: [1m[32m0.02004[0m[0m | time: 0.009s
[2K
| Adam | epoch: 939 | loss: 0.02004 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3757 | total loss: [1m[32m0.01855[0m[0m | time: 0.003s
[2K
| Adam | epoch: 940 | loss: 0.01855 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3758 | total loss: [1m[32m0.02188[0m[0m | time: 0.005s
[2K
| Adam | epoch: 940 | loss: 0.02188 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3759 | total loss: [1m[32m0.02474[0m[0m | time: 0.008s
[2K
| Adam | epoch: 940 | loss: 0.02474 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3760 | total loss: [1m[32m0.02276[0m[0m | time: 0.010s
[2K
| Adam | epoch: 940 | loss: 0.02276 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3761 | total loss: [1m[32m0.02097[0m[0m | time: 0.002s
[2K
| Adam | epoch: 941 | loss: 0.02097 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3762 | total loss: [1m[32m0.02115[0m[0m | time: 0.005s
[2K
| Adam | epoch: 941 | loss: 0.02115 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3763 | total loss: [1m[32m0.01984[0m[0m | time: 0.007s
[2K
| Adam | epoch: 941 | loss: 0.01984 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3764 | total loss: [1m[32m0.01888[0m[0m | time: 0.009s
[2K
| Adam | epoch: 941 | loss: 0.01888 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3765 | total loss: [1m[32m0.01787[0m[0m | time: 0.002s
[2K
| Adam | epoch: 942 | loss: 0.01787 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3766 | total loss: [1m[32m0.01697[0m[0m | time: 0.005s
[2K
| Adam | epoch: 942 | loss: 0.01697 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3767 | total loss: [1m[32m0.02058[0m[0m | time: 0.007s
[2K
| Adam | epoch: 942 | loss: 0.02058 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3768 | total loss: [1m[32m0.02001[0m[0m | time: 0.010s
[2K
| Adam | epoch: 942 | loss: 0.02001 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3769 | total loss: [1m[32m0.02183[0m[0m | time: 0.002s
[2K
| Adam | epoch: 943 | loss: 0.02183 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3770 | total loss: [1m[32m0.02209[0m[0m | time: 0.005s
[2K
| Adam | epoch: 943 | loss: 0.02209 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3771 | total loss: [1m[32m0.02232[0m[0m | time: 0.007s
[2K
| Adam | epoch: 943 | loss: 0.02232 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3772 | total loss: [1m[32m0.02135[0m[0m | time: 0.009s
[2K
| Adam | epoch: 943 | loss: 0.02135 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3773 | total loss: [1m[32m0.02095[0m[0m | time: 0.002s
[2K
| Adam | epoch: 944 | loss: 0.02095 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3774 | total loss: [1m[32m0.01994[0m[0m | time: 0.005s
[2K
| Adam | epoch: 944 | loss: 0.01994 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3775 | total loss: [1m[32m0.01887[0m[0m | time: 0.018s
[2K
| Adam | epoch: 944 | loss: 0.01887 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3776 | total loss: [1m[32m0.01790[0m[0m | time: 0.021s
[2K
| Adam | epoch: 944 | loss: 0.01790 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3777 | total loss: [1m[32m0.02093[0m[0m | time: 0.003s
[2K
| Adam | epoch: 945 | loss: 0.02093 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3778 | total loss: [1m[32m0.02066[0m[0m | time: 0.005s
[2K
| Adam | epoch: 945 | loss: 0.02066 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3779 | total loss: [1m[32m0.01975[0m[0m | time: 0.008s
[2K
| Adam | epoch: 945 | loss: 0.01975 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3780 | total loss: [1m[32m0.01824[0m[0m | time: 0.011s
[2K
| Adam | epoch: 945 | loss: 0.01824 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3781 | total loss: [1m[32m0.01689[0m[0m | time: 0.003s
[2K
| Adam | epoch: 946 | loss: 0.01689 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3782 | total loss: [1m[32m0.01711[0m[0m | time: 0.006s
[2K
| Adam | epoch: 946 | loss: 0.01711 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3783 | total loss: [1m[32m0.02034[0m[0m | time: 0.009s
[2K
| Adam | epoch: 946 | loss: 0.02034 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3784 | total loss: [1m[32m0.02079[0m[0m | time: 0.012s
[2K
| Adam | epoch: 946 | loss: 0.02079 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3785 | total loss: [1m[32m0.02030[0m[0m | time: 0.003s
[2K
| Adam | epoch: 947 | loss: 0.02030 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3786 | total loss: [1m[32m0.01983[0m[0m | time: 0.006s
[2K
| Adam | epoch: 947 | loss: 0.01983 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3787 | total loss: [1m[32m0.02210[0m[0m | time: 0.009s
[2K
| Adam | epoch: 947 | loss: 0.02210 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3788 | total loss: [1m[32m0.02043[0m[0m | time: 0.012s
[2K
| Adam | epoch: 947 | loss: 0.02043 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3789 | total loss: [1m[32m0.02289[0m[0m | time: 0.003s
[2K
| Adam | epoch: 948 | loss: 0.02289 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3790 | total loss: [1m[32m0.02083[0m[0m | time: 0.005s
[2K
| Adam | epoch: 948 | loss: 0.02083 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3791 | total loss: [1m[32m0.01898[0m[0m | time: 0.007s
[2K
| Adam | epoch: 948 | loss: 0.01898 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3792 | total loss: [1m[32m0.01928[0m[0m | time: 0.011s
[2K
| Adam | epoch: 948 | loss: 0.01928 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3793 | total loss: [1m[32m0.01870[0m[0m | time: 0.003s
[2K
| Adam | epoch: 949 | loss: 0.01870 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3794 | total loss: [1m[32m0.01774[0m[0m | time: 0.007s
[2K
| Adam | epoch: 949 | loss: 0.01774 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3795 | total loss: [1m[32m0.01705[0m[0m | time: 0.009s
[2K
| Adam | epoch: 949 | loss: 0.01705 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3796 | total loss: [1m[32m0.01643[0m[0m | time: 0.013s
[2K
| Adam | epoch: 949 | loss: 0.01643 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3797 | total loss: [1m[32m0.01988[0m[0m | time: 0.002s
[2K
| Adam | epoch: 950 | loss: 0.01988 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3798 | total loss: [1m[32m1.73345[0m[0m | time: 0.005s
[2K
| Adam | epoch: 950 | loss: 1.73345 - acc: 0.9000 -- iter: 16/29
[A[ATraining Step: 3799 | total loss: [1m[32m1.56028[0m[0m | time: 0.008s
[2K
| Adam | epoch: 950 | loss: 1.56028 - acc: 0.9100 -- iter: 24/29
[A[ATraining Step: 3800 | total loss: [1m[32m1.40599[0m[0m | time: 0.012s
[2K
| Adam | epoch: 950 | loss: 1.40599 - acc: 0.9190 -- iter: 29/29
--
Training Step: 3801 | total loss: [1m[32m1.26711[0m[0m | time: 0.003s
[2K
| Adam | epoch: 951 | loss: 1.26711 - acc: 0.9271 -- iter: 08/29
[A[ATraining Step: 3802 | total loss: [1m[32m1.14240[0m[0m | time: 0.006s
[2K
| Adam | epoch: 951 | loss: 1.14240 - acc: 0.9344 -- iter: 16/29
[A[ATraining Step: 3803 | total loss: [1m[32m1.03325[0m[0m | time: 0.010s
[2K
| Adam | epoch: 951 | loss: 1.03325 - acc: 0.9410 -- iter: 24/29
[A[ATraining Step: 3804 | total loss: [1m[32m0.93040[0m[0m | time: 0.012s
[2K
| Adam | epoch: 951 | loss: 0.93040 - acc: 0.9469 -- iter: 29/29
--
Training Step: 3805 | total loss: [1m[32m0.83774[0m[0m | time: 0.002s
[2K
| Adam | epoch: 952 | loss: 0.83774 - acc: 0.9522 -- iter: 08/29
[A[ATraining Step: 3806 | total loss: [1m[32m0.75434[0m[0m | time: 0.005s
[2K
| Adam | epoch: 952 | loss: 0.75434 - acc: 0.9570 -- iter: 16/29
[A[ATraining Step: 3807 | total loss: [1m[32m0.68075[0m[0m | time: 0.008s
[2K
| Adam | epoch: 952 | loss: 0.68075 - acc: 0.9613 -- iter: 24/29
[A[ATraining Step: 3808 | total loss: [1m[32m0.61859[0m[0m | time: 0.015s
[2K
| Adam | epoch: 952 | loss: 0.61859 - acc: 0.9651 -- iter: 29/29
--
Training Step: 3809 | total loss: [1m[32m0.55802[0m[0m | time: 0.003s
[2K
| Adam | epoch: 953 | loss: 0.55802 - acc: 0.9686 -- iter: 08/29
[A[ATraining Step: 3810 | total loss: [1m[32m0.50319[0m[0m | time: 0.005s
[2K
| Adam | epoch: 953 | loss: 0.50319 - acc: 0.9718 -- iter: 16/29
[A[ATraining Step: 3811 | total loss: [1m[32m0.45385[0m[0m | time: 0.008s
[2K
| Adam | epoch: 953 | loss: 0.45385 - acc: 0.9746 -- iter: 24/29
[A[ATraining Step: 3812 | total loss: [1m[32m0.41316[0m[0m | time: 0.011s
[2K
| Adam | epoch: 953 | loss: 0.41316 - acc: 0.9771 -- iter: 29/29
--
Training Step: 3813 | total loss: [1m[32m0.37381[0m[0m | time: 0.002s
[2K
| Adam | epoch: 954 | loss: 0.37381 - acc: 0.9794 -- iter: 08/29
[A[ATraining Step: 3814 | total loss: [1m[32m0.33720[0m[0m | time: 0.006s
[2K
| Adam | epoch: 954 | loss: 0.33720 - acc: 0.9815 -- iter: 16/29
[A[ATraining Step: 3815 | total loss: [1m[32m0.30529[0m[0m | time: 0.009s
[2K
| Adam | epoch: 954 | loss: 0.30529 - acc: 0.9833 -- iter: 24/29
[A[ATraining Step: 3816 | total loss: [1m[32m0.27657[0m[0m | time: 0.012s
[2K
| Adam | epoch: 954 | loss: 0.27657 - acc: 0.9850 -- iter: 29/29
--
Training Step: 3817 | total loss: [1m[32m0.25413[0m[0m | time: 0.003s
[2K
| Adam | epoch: 955 | loss: 0.25413 - acc: 0.9865 -- iter: 08/29
[A[ATraining Step: 3818 | total loss: [1m[32m0.23024[0m[0m | time: 0.005s
[2K
| Adam | epoch: 955 | loss: 0.23024 - acc: 0.9878 -- iter: 16/29
[A[ATraining Step: 3819 | total loss: [1m[32m0.20768[0m[0m | time: 0.008s
[2K
| Adam | epoch: 955 | loss: 0.20768 - acc: 0.9891 -- iter: 24/29
[A[ATraining Step: 3820 | total loss: [1m[32m0.18909[0m[0m | time: 0.011s
[2K
| Adam | epoch: 955 | loss: 0.18909 - acc: 0.9902 -- iter: 29/29
--
Training Step: 3821 | total loss: [1m[32m0.17236[0m[0m | time: 0.004s
[2K
| Adam | epoch: 956 | loss: 0.17236 - acc: 0.9911 -- iter: 08/29
[A[ATraining Step: 3822 | total loss: [1m[32m0.15683[0m[0m | time: 0.007s
[2K
| Adam | epoch: 956 | loss: 0.15683 - acc: 0.9920 -- iter: 16/29
[A[ATraining Step: 3823 | total loss: [1m[32m0.14623[0m[0m | time: 0.010s
[2K
| Adam | epoch: 956 | loss: 0.14623 - acc: 0.9928 -- iter: 24/29
[A[ATraining Step: 3824 | total loss: [1m[32m0.13297[0m[0m | time: 0.016s
[2K
| Adam | epoch: 956 | loss: 0.13297 - acc: 0.9935 -- iter: 29/29
--
Training Step: 3825 | total loss: [1m[32m0.12068[0m[0m | time: 0.002s
[2K
| Adam | epoch: 957 | loss: 0.12068 - acc: 0.9942 -- iter: 08/29
[A[ATraining Step: 3826 | total loss: [1m[32m0.10961[0m[0m | time: 0.005s
[2K
| Adam | epoch: 957 | loss: 0.10961 - acc: 0.9948 -- iter: 16/29
[A[ATraining Step: 3827 | total loss: [1m[32m0.10002[0m[0m | time: 0.007s
[2K
| Adam | epoch: 957 | loss: 0.10002 - acc: 0.9953 -- iter: 24/29
[A[ATraining Step: 3828 | total loss: [1m[32m0.96999[0m[0m | time: 0.010s
[2K
| Adam | epoch: 957 | loss: 0.96999 - acc: 0.9208 -- iter: 29/29
--
Training Step: 3829 | total loss: [1m[32m0.87725[0m[0m | time: 0.003s
[2K
| Adam | epoch: 958 | loss: 0.87725 - acc: 0.9287 -- iter: 08/29
[A[ATraining Step: 3830 | total loss: [1m[32m0.79141[0m[0m | time: 0.005s
[2K
| Adam | epoch: 958 | loss: 0.79141 - acc: 0.9358 -- iter: 16/29
[A[ATraining Step: 3831 | total loss: [1m[32m0.71409[0m[0m | time: 0.007s
[2K
| Adam | epoch: 958 | loss: 0.71409 - acc: 0.9422 -- iter: 24/29
[A[ATraining Step: 3832 | total loss: [1m[32m0.64404[0m[0m | time: 0.010s
[2K
| Adam | epoch: 958 | loss: 0.64404 - acc: 0.9480 -- iter: 29/29
--
Training Step: 3833 | total loss: [1m[32m0.58134[0m[0m | time: 0.002s
[2K
| Adam | epoch: 959 | loss: 0.58134 - acc: 0.9532 -- iter: 08/29
[A[ATraining Step: 3834 | total loss: [1m[32m0.52399[0m[0m | time: 0.005s
[2K
| Adam | epoch: 959 | loss: 0.52399 - acc: 0.9579 -- iter: 16/29
[A[ATraining Step: 3835 | total loss: [1m[32m0.47801[0m[0m | time: 0.007s
[2K
| Adam | epoch: 959 | loss: 0.47801 - acc: 0.9621 -- iter: 24/29
[A[ATraining Step: 3836 | total loss: [1m[32m0.43667[0m[0m | time: 0.010s
[2K
| Adam | epoch: 959 | loss: 0.43667 - acc: 0.9659 -- iter: 29/29
--
Training Step: 3837 | total loss: [1m[32m0.39548[0m[0m | time: 0.002s
[2K
| Adam | epoch: 960 | loss: 0.39548 - acc: 0.9693 -- iter: 08/29
[A[ATraining Step: 3838 | total loss: [1m[32m0.35732[0m[0m | time: 0.004s
[2K
| Adam | epoch: 960 | loss: 0.35732 - acc: 0.9724 -- iter: 16/29
[A[ATraining Step: 3839 | total loss: [1m[32m0.32698[0m[0m | time: 0.006s
[2K
| Adam | epoch: 960 | loss: 0.32698 - acc: 0.9751 -- iter: 24/29
[A[ATraining Step: 3840 | total loss: [1m[32m0.29535[0m[0m | time: 0.008s
[2K
| Adam | epoch: 960 | loss: 0.29535 - acc: 0.9776 -- iter: 29/29
--
Training Step: 3841 | total loss: [1m[32m0.26685[0m[0m | time: 0.002s
[2K
| Adam | epoch: 961 | loss: 0.26685 - acc: 0.9799 -- iter: 08/29
[A[ATraining Step: 3842 | total loss: [1m[32m0.24133[0m[0m | time: 0.004s
[2K
| Adam | epoch: 961 | loss: 0.24133 - acc: 0.9819 -- iter: 16/29
[A[ATraining Step: 3843 | total loss: [1m[32m0.21891[0m[0m | time: 0.005s
[2K
| Adam | epoch: 961 | loss: 0.21891 - acc: 0.9837 -- iter: 24/29
[A[ATraining Step: 3844 | total loss: [1m[32m0.19860[0m[0m | time: 0.007s
[2K
| Adam | epoch: 961 | loss: 0.19860 - acc: 0.9853 -- iter: 29/29
--
Training Step: 3845 | total loss: [1m[32m0.17963[0m[0m | time: 0.003s
[2K
| Adam | epoch: 962 | loss: 0.17963 - acc: 0.9868 -- iter: 08/29
[A[ATraining Step: 3846 | total loss: [1m[32m0.16255[0m[0m | time: 0.005s
[2K
| Adam | epoch: 962 | loss: 0.16255 - acc: 0.9881 -- iter: 16/29
[A[ATraining Step: 3847 | total loss: [1m[32m0.14777[0m[0m | time: 0.007s
[2K
| Adam | epoch: 962 | loss: 0.14777 - acc: 0.9893 -- iter: 24/29
[A[ATraining Step: 3848 | total loss: [1m[32m0.13836[0m[0m | time: 0.010s
[2K
| Adam | epoch: 962 | loss: 0.13836 - acc: 0.9904 -- iter: 29/29
--
Training Step: 3849 | total loss: [1m[32m0.12891[0m[0m | time: 0.003s
[2K
| Adam | epoch: 963 | loss: 0.12891 - acc: 0.9913 -- iter: 08/29
[A[ATraining Step: 3850 | total loss: [1m[32m0.11678[0m[0m | time: 0.006s
[2K
| Adam | epoch: 963 | loss: 0.11678 - acc: 0.9922 -- iter: 16/29
[A[ATraining Step: 3851 | total loss: [1m[32m0.10586[0m[0m | time: 0.009s
[2K
| Adam | epoch: 963 | loss: 0.10586 - acc: 0.9930 -- iter: 24/29
[A[ATraining Step: 3852 | total loss: [1m[32m0.09686[0m[0m | time: 0.011s
[2K
| Adam | epoch: 963 | loss: 0.09686 - acc: 0.9937 -- iter: 29/29
--
Training Step: 3853 | total loss: [1m[32m0.08973[0m[0m | time: 0.002s
[2K
| Adam | epoch: 964 | loss: 0.08973 - acc: 0.9943 -- iter: 08/29
[A[ATraining Step: 3854 | total loss: [1m[32m0.08563[0m[0m | time: 0.005s
[2K
| Adam | epoch: 964 | loss: 0.08563 - acc: 0.9949 -- iter: 16/29
[A[ATraining Step: 3855 | total loss: [1m[32m0.07967[0m[0m | time: 0.007s
[2K
| Adam | epoch: 964 | loss: 0.07967 - acc: 0.9954 -- iter: 24/29
[A[ATraining Step: 3856 | total loss: [1m[32m0.07427[0m[0m | time: 0.009s
[2K
| Adam | epoch: 964 | loss: 0.07427 - acc: 0.9959 -- iter: 29/29
--
Training Step: 3857 | total loss: [1m[32m0.06834[0m[0m | time: 0.002s
[2K
| Adam | epoch: 965 | loss: 0.06834 - acc: 0.9963 -- iter: 08/29
[A[ATraining Step: 3858 | total loss: [1m[32m0.06249[0m[0m | time: 0.005s
[2K
| Adam | epoch: 965 | loss: 0.06249 - acc: 0.9966 -- iter: 16/29
[A[ATraining Step: 3859 | total loss: [1m[32m0.05668[0m[0m | time: 0.008s
[2K
| Adam | epoch: 965 | loss: 0.05668 - acc: 0.9970 -- iter: 24/29
[A[ATraining Step: 3860 | total loss: [1m[32m0.05335[0m[0m | time: 0.010s
[2K
| Adam | epoch: 965 | loss: 0.05335 - acc: 0.9973 -- iter: 29/29
--
Training Step: 3861 | total loss: [1m[32m0.05034[0m[0m | time: 0.003s
[2K
| Adam | epoch: 966 | loss: 0.05034 - acc: 0.9976 -- iter: 08/29
[A[ATraining Step: 3862 | total loss: [1m[32m0.05057[0m[0m | time: 0.005s
[2K
| Adam | epoch: 966 | loss: 0.05057 - acc: 0.9978 -- iter: 16/29
[A[ATraining Step: 3863 | total loss: [1m[32m0.04711[0m[0m | time: 0.007s
[2K
| Adam | epoch: 966 | loss: 0.04711 - acc: 0.9980 -- iter: 24/29
[A[ATraining Step: 3864 | total loss: [1m[32m0.04342[0m[0m | time: 0.010s
[2K
| Adam | epoch: 966 | loss: 0.04342 - acc: 0.9982 -- iter: 29/29
--
Training Step: 3865 | total loss: [1m[32m0.04780[0m[0m | time: 0.002s
[2K
| Adam | epoch: 967 | loss: 0.04780 - acc: 0.9984 -- iter: 08/29
[A[ATraining Step: 3866 | total loss: [1m[32m0.05168[0m[0m | time: 0.005s
[2K
| Adam | epoch: 967 | loss: 0.05168 - acc: 0.9986 -- iter: 16/29
[A[ATraining Step: 3867 | total loss: [1m[32m0.04789[0m[0m | time: 0.007s
[2K
| Adam | epoch: 967 | loss: 0.04789 - acc: 0.9987 -- iter: 24/29
[A[ATraining Step: 3868 | total loss: [1m[32m0.04396[0m[0m | time: 0.009s
[2K
| Adam | epoch: 967 | loss: 0.04396 - acc: 0.9988 -- iter: 29/29
--
Training Step: 3869 | total loss: [1m[32m0.04153[0m[0m | time: 0.002s
[2K
| Adam | epoch: 968 | loss: 0.04153 - acc: 0.9989 -- iter: 08/29
[A[ATraining Step: 3870 | total loss: [1m[32m0.04043[0m[0m | time: 0.005s
[2K
| Adam | epoch: 968 | loss: 0.04043 - acc: 0.9991 -- iter: 16/29
[A[ATraining Step: 3871 | total loss: [1m[32m0.03943[0m[0m | time: 0.007s
[2K
| Adam | epoch: 968 | loss: 0.03943 - acc: 0.9991 -- iter: 24/29
[A[ATraining Step: 3872 | total loss: [1m[32m0.03929[0m[0m | time: 0.009s
[2K
| Adam | epoch: 968 | loss: 0.03929 - acc: 0.9992 -- iter: 29/29
--
Training Step: 3873 | total loss: [1m[32m0.03621[0m[0m | time: 0.002s
[2K
| Adam | epoch: 969 | loss: 0.03621 - acc: 0.9993 -- iter: 08/29
[A[ATraining Step: 3874 | total loss: [1m[32m0.03450[0m[0m | time: 0.005s
[2K
| Adam | epoch: 969 | loss: 0.03450 - acc: 0.9994 -- iter: 16/29
[A[ATraining Step: 3875 | total loss: [1m[32m0.03404[0m[0m | time: 0.007s
[2K
| Adam | epoch: 969 | loss: 0.03404 - acc: 0.9994 -- iter: 24/29
[A[ATraining Step: 3876 | total loss: [1m[32m1.34248[0m[0m | time: 0.030s
[2K
| Adam | epoch: 969 | loss: 1.34248 - acc: 0.8995 -- iter: 29/29
--
Training Step: 3877 | total loss: [1m[32m1.21263[0m[0m | time: 0.002s
[2K
| Adam | epoch: 970 | loss: 1.21263 - acc: 0.9095 -- iter: 08/29
[A[ATraining Step: 3878 | total loss: [1m[32m1.09341[0m[0m | time: 0.005s
[2K
| Adam | epoch: 970 | loss: 1.09341 - acc: 0.9186 -- iter: 16/29
[A[ATraining Step: 3879 | total loss: [1m[32m0.98520[0m[0m | time: 0.007s
[2K
| Adam | epoch: 970 | loss: 0.98520 - acc: 0.9267 -- iter: 24/29
[A[ATraining Step: 3880 | total loss: [1m[32m0.88854[0m[0m | time: 0.010s
[2K
| Adam | epoch: 970 | loss: 0.88854 - acc: 0.9341 -- iter: 29/29
--
Training Step: 3881 | total loss: [1m[32m0.80151[0m[0m | time: 0.002s
[2K
| Adam | epoch: 971 | loss: 0.80151 - acc: 0.9407 -- iter: 08/29
[A[ATraining Step: 3882 | total loss: [1m[32m0.72694[0m[0m | time: 0.005s
[2K
| Adam | epoch: 971 | loss: 0.72694 - acc: 0.9466 -- iter: 16/29
[A[ATraining Step: 3883 | total loss: [1m[32m0.65572[0m[0m | time: 0.007s
[2K
| Adam | epoch: 971 | loss: 0.65572 - acc: 0.9519 -- iter: 24/29
[A[ATraining Step: 3884 | total loss: [1m[32m0.59513[0m[0m | time: 0.010s
[2K
| Adam | epoch: 971 | loss: 0.59513 - acc: 0.9567 -- iter: 29/29
--
Training Step: 3885 | total loss: [1m[32m0.53725[0m[0m | time: 0.002s
[2K
| Adam | epoch: 972 | loss: 0.53725 - acc: 0.9611 -- iter: 08/29
[A[ATraining Step: 3886 | total loss: [1m[32m0.48514[0m[0m | time: 0.005s
[2K
| Adam | epoch: 972 | loss: 0.48514 - acc: 0.9650 -- iter: 16/29
[A[ATraining Step: 3887 | total loss: [1m[32m0.43871[0m[0m | time: 0.008s
[2K
| Adam | epoch: 972 | loss: 0.43871 - acc: 0.9685 -- iter: 24/29
[A[ATraining Step: 3888 | total loss: [1m[32m0.39563[0m[0m | time: 0.011s
[2K
| Adam | epoch: 972 | loss: 0.39563 - acc: 0.9716 -- iter: 29/29
--
Training Step: 3889 | total loss: [1m[32m0.36136[0m[0m | time: 0.003s
[2K
| Adam | epoch: 973 | loss: 0.36136 - acc: 0.9745 -- iter: 08/29
[A[ATraining Step: 3890 | total loss: [1m[32m0.32666[0m[0m | time: 0.006s
[2K
| Adam | epoch: 973 | loss: 0.32666 - acc: 0.9770 -- iter: 16/29
[A[ATraining Step: 3891 | total loss: [1m[32m0.29542[0m[0m | time: 0.009s
[2K
| Adam | epoch: 973 | loss: 0.29542 - acc: 0.9793 -- iter: 24/29
[A[ATraining Step: 3892 | total loss: [1m[32m0.26716[0m[0m | time: 0.012s
[2K
| Adam | epoch: 973 | loss: 0.26716 - acc: 0.9814 -- iter: 29/29
--
Training Step: 3893 | total loss: [1m[32m0.24196[0m[0m | time: 0.003s
[2K
| Adam | epoch: 974 | loss: 0.24196 - acc: 0.9832 -- iter: 08/29
[A[ATraining Step: 3894 | total loss: [1m[32m0.21914[0m[0m | time: 0.006s
[2K
| Adam | epoch: 974 | loss: 0.21914 - acc: 0.9849 -- iter: 16/29
[A[ATraining Step: 3895 | total loss: [1m[32m0.20386[0m[0m | time: 0.009s
[2K
| Adam | epoch: 974 | loss: 0.20386 - acc: 0.9864 -- iter: 24/29
[A[ATraining Step: 3896 | total loss: [1m[32m0.19010[0m[0m | time: 0.012s
[2K
| Adam | epoch: 974 | loss: 0.19010 - acc: 0.9878 -- iter: 29/29
--
Training Step: 3897 | total loss: [1m[32m0.17332[0m[0m | time: 0.003s
[2K
| Adam | epoch: 975 | loss: 0.17332 - acc: 0.9890 -- iter: 08/29
[A[ATraining Step: 3898 | total loss: [1m[32m0.15726[0m[0m | time: 0.006s
[2K
| Adam | epoch: 975 | loss: 0.15726 - acc: 0.9901 -- iter: 16/29
[A[ATraining Step: 3899 | total loss: [1m[32m0.14275[0m[0m | time: 0.008s
[2K
| Adam | epoch: 975 | loss: 0.14275 - acc: 0.9911 -- iter: 24/29
[A[ATraining Step: 3900 | total loss: [1m[32m0.13462[0m[0m | time: 0.011s
[2K
| Adam | epoch: 975 | loss: 0.13462 - acc: 0.9920 -- iter: 29/29
--
Training Step: 3901 | total loss: [1m[32m0.12728[0m[0m | time: 0.003s
[2K
| Adam | epoch: 976 | loss: 0.12728 - acc: 0.9928 -- iter: 08/29
[A[ATraining Step: 3902 | total loss: [1m[32m0.11597[0m[0m | time: 0.006s
[2K
| Adam | epoch: 976 | loss: 0.11597 - acc: 0.9935 -- iter: 16/29
[A[ATraining Step: 3903 | total loss: [1m[32m0.10684[0m[0m | time: 0.008s
[2K
| Adam | epoch: 976 | loss: 0.10684 - acc: 0.9942 -- iter: 24/29
[A[ATraining Step: 3904 | total loss: [1m[32m0.09671[0m[0m | time: 0.011s
[2K
| Adam | epoch: 976 | loss: 0.09671 - acc: 0.9947 -- iter: 29/29
--
Training Step: 3905 | total loss: [1m[32m0.08851[0m[0m | time: 0.003s
[2K
| Adam | epoch: 977 | loss: 0.08851 - acc: 0.9953 -- iter: 08/29
[A[ATraining Step: 3906 | total loss: [1m[32m0.08113[0m[0m | time: 0.006s
[2K
| Adam | epoch: 977 | loss: 0.08113 - acc: 0.9957 -- iter: 16/29
[A[ATraining Step: 3907 | total loss: [1m[32m0.07508[0m[0m | time: 0.025s
[2K
| Adam | epoch: 977 | loss: 0.07508 - acc: 0.9962 -- iter: 24/29
[A[ATraining Step: 3908 | total loss: [1m[32m0.07280[0m[0m | time: 0.027s
[2K
| Adam | epoch: 977 | loss: 0.07280 - acc: 0.9965 -- iter: 29/29
--
Training Step: 3909 | total loss: [1m[32m0.07057[0m[0m | time: 0.002s
[2K
| Adam | epoch: 978 | loss: 0.07057 - acc: 0.9969 -- iter: 08/29
[A[ATraining Step: 3910 | total loss: [1m[32m0.06488[0m[0m | time: 0.004s
[2K
| Adam | epoch: 978 | loss: 0.06488 - acc: 0.9972 -- iter: 16/29
[A[ATraining Step: 3911 | total loss: [1m[32m0.05974[0m[0m | time: 0.007s
[2K
| Adam | epoch: 978 | loss: 0.05974 - acc: 0.9975 -- iter: 24/29
[A[ATraining Step: 3912 | total loss: [1m[32m0.05424[0m[0m | time: 0.010s
[2K
| Adam | epoch: 978 | loss: 0.05424 - acc: 0.9977 -- iter: 29/29
--
Training Step: 3913 | total loss: [1m[32m0.05118[0m[0m | time: 0.003s
[2K
| Adam | epoch: 979 | loss: 0.05118 - acc: 0.9980 -- iter: 08/29
[A[ATraining Step: 3914 | total loss: [1m[32m0.04738[0m[0m | time: 0.006s
[2K
| Adam | epoch: 979 | loss: 0.04738 - acc: 0.9982 -- iter: 16/29
[A[ATraining Step: 3915 | total loss: [1m[32m0.04418[0m[0m | time: 0.009s
[2K
| Adam | epoch: 979 | loss: 0.04418 - acc: 0.9983 -- iter: 24/29
[A[ATraining Step: 3916 | total loss: [1m[32m0.04129[0m[0m | time: 0.013s
[2K
| Adam | epoch: 979 | loss: 0.04129 - acc: 0.9985 -- iter: 29/29
--
Training Step: 3917 | total loss: [1m[32m0.04173[0m[0m | time: 0.003s
[2K
| Adam | epoch: 980 | loss: 0.04173 - acc: 0.9987 -- iter: 08/29
[A[ATraining Step: 3918 | total loss: [1m[32m0.03935[0m[0m | time: 0.007s
[2K
| Adam | epoch: 980 | loss: 0.03935 - acc: 0.9988 -- iter: 16/29
[A[ATraining Step: 3919 | total loss: [1m[32m0.03706[0m[0m | time: 0.010s
[2K
| Adam | epoch: 980 | loss: 0.03706 - acc: 0.9989 -- iter: 24/29
[A[ATraining Step: 3920 | total loss: [1m[32m0.03528[0m[0m | time: 0.013s
[2K
| Adam | epoch: 980 | loss: 0.03528 - acc: 0.9990 -- iter: 29/29
--
Training Step: 3921 | total loss: [1m[32m0.03367[0m[0m | time: 0.003s
[2K
| Adam | epoch: 981 | loss: 0.03367 - acc: 0.9991 -- iter: 08/29
[A[ATraining Step: 3922 | total loss: [1m[32m0.03444[0m[0m | time: 0.006s
[2K
| Adam | epoch: 981 | loss: 0.03444 - acc: 0.9992 -- iter: 16/29
[A[ATraining Step: 3923 | total loss: [1m[32m0.03251[0m[0m | time: 0.010s
[2K
| Adam | epoch: 981 | loss: 0.03251 - acc: 0.9993 -- iter: 24/29
[A[ATraining Step: 3924 | total loss: [1m[32m0.03115[0m[0m | time: 0.013s
[2K
| Adam | epoch: 981 | loss: 0.03115 - acc: 0.9994 -- iter: 29/29
--
Training Step: 3925 | total loss: [1m[32m0.02844[0m[0m | time: 0.004s
[2K
| Adam | epoch: 982 | loss: 0.02844 - acc: 0.9994 -- iter: 08/29
[A[ATraining Step: 3926 | total loss: [1m[32m0.02601[0m[0m | time: 0.007s
[2K
| Adam | epoch: 982 | loss: 0.02601 - acc: 0.9995 -- iter: 16/29
[A[ATraining Step: 3927 | total loss: [1m[32m0.02876[0m[0m | time: 0.010s
[2K
| Adam | epoch: 982 | loss: 0.02876 - acc: 0.9995 -- iter: 24/29
[A[ATraining Step: 3928 | total loss: [1m[32m0.02687[0m[0m | time: 0.013s
[2K
| Adam | epoch: 982 | loss: 0.02687 - acc: 0.9996 -- iter: 29/29
--
Training Step: 3929 | total loss: [1m[32m0.02494[0m[0m | time: 0.003s
[2K
| Adam | epoch: 983 | loss: 0.02494 - acc: 0.9996 -- iter: 08/29
[A[ATraining Step: 3930 | total loss: [1m[32m0.02856[0m[0m | time: 0.007s
[2K
| Adam | epoch: 983 | loss: 0.02856 - acc: 0.9997 -- iter: 16/29
[A[ATraining Step: 3931 | total loss: [1m[32m0.03180[0m[0m | time: 0.010s
[2K
| Adam | epoch: 983 | loss: 0.03180 - acc: 0.9997 -- iter: 24/29
[A[ATraining Step: 3932 | total loss: [1m[32m0.03054[0m[0m | time: 0.014s
[2K
| Adam | epoch: 983 | loss: 0.03054 - acc: 0.9997 -- iter: 29/29
--
Training Step: 3933 | total loss: [1m[32m0.02942[0m[0m | time: 0.004s
[2K
| Adam | epoch: 984 | loss: 0.02942 - acc: 0.9998 -- iter: 08/29
[A[ATraining Step: 3934 | total loss: [1m[32m0.02791[0m[0m | time: 0.007s
[2K
| Adam | epoch: 984 | loss: 0.02791 - acc: 0.9998 -- iter: 16/29
[A[ATraining Step: 3935 | total loss: [1m[32m0.02597[0m[0m | time: 0.010s
[2K
| Adam | epoch: 984 | loss: 0.02597 - acc: 0.9998 -- iter: 24/29
[A[ATraining Step: 3936 | total loss: [1m[32m0.02424[0m[0m | time: 0.025s
[2K
| Adam | epoch: 984 | loss: 0.02424 - acc: 0.9998 -- iter: 29/29
--
Training Step: 3937 | total loss: [1m[32m0.02649[0m[0m | time: 0.002s
[2K
| Adam | epoch: 985 | loss: 0.02649 - acc: 0.9998 -- iter: 08/29
[A[ATraining Step: 3938 | total loss: [1m[32m0.02551[0m[0m | time: 0.005s
[2K
| Adam | epoch: 985 | loss: 0.02551 - acc: 0.9999 -- iter: 16/29
[A[ATraining Step: 3939 | total loss: [1m[32m0.02814[0m[0m | time: 0.007s
[2K
| Adam | epoch: 985 | loss: 0.02814 - acc: 0.9999 -- iter: 24/29
[A[ATraining Step: 3940 | total loss: [1m[32m0.02681[0m[0m | time: 0.010s
[2K
| Adam | epoch: 985 | loss: 0.02681 - acc: 0.9999 -- iter: 29/29
--
Training Step: 3941 | total loss: [1m[32m0.02561[0m[0m | time: 0.003s
[2K
| Adam | epoch: 986 | loss: 0.02561 - acc: 0.9999 -- iter: 08/29
[A[ATraining Step: 3942 | total loss: [1m[32m0.02465[0m[0m | time: 0.005s
[2K
| Adam | epoch: 986 | loss: 0.02465 - acc: 0.9999 -- iter: 16/29
[A[ATraining Step: 3943 | total loss: [1m[32m0.02272[0m[0m | time: 0.007s
[2K
| Adam | epoch: 986 | loss: 0.02272 - acc: 0.9999 -- iter: 24/29
[A[ATraining Step: 3944 | total loss: [1m[32m0.02104[0m[0m | time: 0.010s
[2K
| Adam | epoch: 986 | loss: 0.02104 - acc: 0.9999 -- iter: 29/29
--
Training Step: 3945 | total loss: [1m[32m0.02607[0m[0m | time: 0.002s
[2K
| Adam | epoch: 987 | loss: 0.02607 - acc: 0.9999 -- iter: 08/29
[A[ATraining Step: 3946 | total loss: [1m[32m0.03057[0m[0m | time: 0.005s
[2K
| Adam | epoch: 987 | loss: 0.03057 - acc: 0.9999 -- iter: 16/29
[A[ATraining Step: 3947 | total loss: [1m[32m0.02879[0m[0m | time: 0.007s
[2K
| Adam | epoch: 987 | loss: 0.02879 - acc: 0.9999 -- iter: 24/29
[A[ATraining Step: 3948 | total loss: [1m[32m0.02778[0m[0m | time: 0.010s
[2K
| Adam | epoch: 987 | loss: 0.02778 - acc: 0.9999 -- iter: 29/29
--
Training Step: 3949 | total loss: [1m[32m0.02694[0m[0m | time: 0.003s
[2K
| Adam | epoch: 988 | loss: 0.02694 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3950 | total loss: [1m[32m0.02967[0m[0m | time: 0.005s
[2K
| Adam | epoch: 988 | loss: 0.02967 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3951 | total loss: [1m[32m0.03211[0m[0m | time: 0.007s
[2K
| Adam | epoch: 988 | loss: 0.03211 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3952 | total loss: [1m[32m0.03123[0m[0m | time: 0.010s
[2K
| Adam | epoch: 988 | loss: 0.03123 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3953 | total loss: [1m[32m0.02860[0m[0m | time: 0.002s
[2K
| Adam | epoch: 989 | loss: 0.02860 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3954 | total loss: [1m[32m0.02981[0m[0m | time: 0.005s
[2K
| Adam | epoch: 989 | loss: 0.02981 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3955 | total loss: [1m[32m0.03023[0m[0m | time: 0.007s
[2K
| Adam | epoch: 989 | loss: 0.03023 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3956 | total loss: [1m[32m0.03060[0m[0m | time: 0.010s
[2K
| Adam | epoch: 989 | loss: 0.03060 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3957 | total loss: [1m[32m0.02915[0m[0m | time: 0.002s
[2K
| Adam | epoch: 990 | loss: 0.02915 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3958 | total loss: [1m[32m0.02650[0m[0m | time: 0.005s
[2K
| Adam | epoch: 990 | loss: 0.02650 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3959 | total loss: [1m[32m0.02555[0m[0m | time: 0.007s
[2K
| Adam | epoch: 990 | loss: 0.02555 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3960 | total loss: [1m[32m0.02974[0m[0m | time: 0.010s
[2K
| Adam | epoch: 990 | loss: 0.02974 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3961 | total loss: [1m[32m0.03350[0m[0m | time: 0.002s
[2K
| Adam | epoch: 991 | loss: 0.03350 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3962 | total loss: [1m[32m0.03119[0m[0m | time: 0.005s
[2K
| Adam | epoch: 991 | loss: 0.03119 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3963 | total loss: [1m[32m0.02911[0m[0m | time: 0.008s
[2K
| Adam | epoch: 991 | loss: 0.02911 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3964 | total loss: [1m[32m0.02725[0m[0m | time: 0.010s
[2K
| Adam | epoch: 991 | loss: 0.02725 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3965 | total loss: [1m[32m0.02746[0m[0m | time: 0.003s
[2K
| Adam | epoch: 992 | loss: 0.02746 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3966 | total loss: [1m[32m0.02763[0m[0m | time: 0.005s
[2K
| Adam | epoch: 992 | loss: 0.02763 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3967 | total loss: [1m[32m0.02626[0m[0m | time: 0.031s
[2K
| Adam | epoch: 992 | loss: 0.02626 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3968 | total loss: [1m[32m0.02731[0m[0m | time: 0.034s
[2K
| Adam | epoch: 992 | loss: 0.02731 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3969 | total loss: [1m[32m0.02654[0m[0m | time: 0.003s
[2K
| Adam | epoch: 993 | loss: 0.02654 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3970 | total loss: [1m[32m0.02479[0m[0m | time: 0.005s
[2K
| Adam | epoch: 993 | loss: 0.02479 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3971 | total loss: [1m[32m0.02321[0m[0m | time: 0.008s
[2K
| Adam | epoch: 993 | loss: 0.02321 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3972 | total loss: [1m[32m0.02133[0m[0m | time: 0.012s
[2K
| Adam | epoch: 993 | loss: 0.02133 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3973 | total loss: [1m[32m0.02408[0m[0m | time: 0.004s
[2K
| Adam | epoch: 994 | loss: 0.02408 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3974 | total loss: [1m[32m0.02233[0m[0m | time: 0.006s
[2K
| Adam | epoch: 994 | loss: 0.02233 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3975 | total loss: [1m[32m0.02084[0m[0m | time: 0.009s
[2K
| Adam | epoch: 994 | loss: 0.02084 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3976 | total loss: [1m[32m0.01949[0m[0m | time: 0.012s
[2K
| Adam | epoch: 994 | loss: 0.01949 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3977 | total loss: [1m[32m0.01984[0m[0m | time: 0.003s
[2K
| Adam | epoch: 995 | loss: 0.01984 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3978 | total loss: [1m[32m0.02226[0m[0m | time: 0.005s
[2K
| Adam | epoch: 995 | loss: 0.02226 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3979 | total loss: [1m[32m0.02256[0m[0m | time: 0.008s
[2K
| Adam | epoch: 995 | loss: 0.02256 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3980 | total loss: [1m[32m0.02065[0m[0m | time: 0.010s
[2K
| Adam | epoch: 995 | loss: 0.02065 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3981 | total loss: [1m[32m0.01893[0m[0m | time: 0.003s
[2K
| Adam | epoch: 996 | loss: 0.01893 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3982 | total loss: [1m[32m0.01835[0m[0m | time: 0.005s
[2K
| Adam | epoch: 996 | loss: 0.01835 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3983 | total loss: [1m[32m0.02025[0m[0m | time: 0.008s
[2K
| Adam | epoch: 996 | loss: 0.02025 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3984 | total loss: [1m[32m0.02225[0m[0m | time: 0.010s
[2K
| Adam | epoch: 996 | loss: 0.02225 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3985 | total loss: [1m[32m0.02154[0m[0m | time: 0.003s
[2K
| Adam | epoch: 997 | loss: 0.02154 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3986 | total loss: [1m[32m0.02089[0m[0m | time: 0.006s
[2K
| Adam | epoch: 997 | loss: 0.02089 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3987 | total loss: [1m[32m0.02103[0m[0m | time: 0.010s
[2K
| Adam | epoch: 997 | loss: 0.02103 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3988 | total loss: [1m[32m0.01950[0m[0m | time: 0.012s
[2K
| Adam | epoch: 997 | loss: 0.01950 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3989 | total loss: [1m[32m0.01828[0m[0m | time: 0.003s
[2K
| Adam | epoch: 998 | loss: 0.01828 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3990 | total loss: [1m[32m0.01764[0m[0m | time: 0.006s
[2K
| Adam | epoch: 998 | loss: 0.01764 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3991 | total loss: [1m[32m0.01706[0m[0m | time: 0.008s
[2K
| Adam | epoch: 998 | loss: 0.01706 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3992 | total loss: [1m[32m0.01970[0m[0m | time: 0.011s
[2K
| Adam | epoch: 998 | loss: 0.01970 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3993 | total loss: [1m[32m0.01963[0m[0m | time: 0.002s
[2K
| Adam | epoch: 999 | loss: 0.01963 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3994 | total loss: [1m[32m0.02153[0m[0m | time: 0.005s
[2K
| Adam | epoch: 999 | loss: 0.02153 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3995 | total loss: [1m[32m0.02010[0m[0m | time: 0.007s
[2K
| Adam | epoch: 999 | loss: 0.02010 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 3996 | total loss: [1m[32m0.01880[0m[0m | time: 0.009s
[2K
| Adam | epoch: 999 | loss: 0.01880 - acc: 1.0000 -- iter: 29/29
--
Training Step: 3997 | total loss: [1m[32m0.01876[0m[0m | time: 0.002s
[2K
| Adam | epoch: 1000 | loss: 0.01876 - acc: 1.0000 -- iter: 08/29
[A[ATraining Step: 3998 | total loss: [1m[32m0.01842[0m[0m | time: 0.005s
[2K
| Adam | epoch: 1000 | loss: 0.01842 - acc: 1.0000 -- iter: 16/29
[A[ATraining Step: 3999 | total loss: [1m[32m0.02068[0m[0m | time: 0.007s
[2K
| Adam | epoch: 1000 | loss: 0.02068 - acc: 1.0000 -- iter: 24/29
[A[ATraining Step: 4000 | total loss: [1m[32m0.02171[0m[0m | time: 0.010s
[2K
| Adam | epoch: 1000 | loss: 0.02171 - acc: 1.0000 -- iter: 29/29
--
[B[B[B[?12;25h

Here’s the application to load the model and respond to chatbot requets.


# network INPUT: word vector
# network OUTPUT: intent classifier

import nltk
from nltk.stem.lancaster import LancasterStemmer
stemmer = LancasterStemmer()

import pickle
import numpy as np
import tflearn
import tensorflow as tf
import random

# restore all of our data structures
data = pickle.load( open( "training_data", "rb" ) )
words = data['words']
classes = data['classes']
train_x = data['train_x']
train_y = data['train_y']

# import our chat-bot intents file
import json
with open('intents.json') as json_data:
intents = json.load(json_data)

# load our saved model
net = tflearn.input_data(shape=[None, len(train_x[0])])
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, 8)
net = tflearn.fully_connected(net, len(train_y[0]), activation='softmax')
model = tflearn.DNN(net, tensorboard_dir='tflearn_logs')
model.load('./model.tflearn')

def clean_up_sentence(sentence):
# tokenize the pattern
sentence_words = nltk.word_tokenize(sentence)
# stem each word
sentence_words = [stemmer.stem(word.lower()) for word in sentence_words]
return sentence_words

# return bag of words array: 0 or 1 for each word in the bag that exists in the sentence
def bow(sentence, words, show_details=False):
# tokenize the pattern
sentence_words = clean_up_sentence(sentence)
# bag of words
bag = [0]*len(words)
for s in sentence_words:
for i,w in enumerate(words):
if w == s:
bag[i] = 1
if show_details:
print ("found in bag: %s" % w)

return (np.array(bag))

ERROR_THRESHOLD = 0.75

def classify(sentence):
# generate probabilities from the model
results = model.predict([bow(sentence, words)])[0]
print results
# filter out predictions below a threshold
results = [[i,r] for i,r in enumerate(results) if r > ERROR_THRESHOLD]
# sort by strength of probability
results.sort(key=lambda x: x[1], reverse=True)
return_list = []
for r in results:
return_list.append((classes[r[0]], r[1]))
# return tuple of intent and probability
print return_list
return return_list

def response(sentence, userID='123', show_details=False):
results = classify(sentence)
# if we have a classification then find the matching intent tag
if results:
# loop as long as there are matches to process
while results:
for node in intents['intents']:
# find a tag matching the first result
if node['tag'] == results[0][0]:
# a random response from the intent
response = random.choice( node['responses'] )
print response
return response

results.pop(0)
return "Unknown Command"

And finally here’s the model predicting responses to inputs:


randall@randall-VirtualBox3:~/machinelearning$ python
Python 2.7.12+ (default, Sep 17 2016, 12:08:02)
[GCC 6.2.0 20160914] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> from app import *
>>> response('hello')
[4.6882556e-06 9.9047524e-01 1.3915565e-06 1.9635949e-07 6.2862798e-03
1.1722450e-08 3.2322633e-03]
[(u'greeting', 0.99047524)]
Would you like to watch a movie or tv show?
u'Would you like to watch a movie or tv show?'
>>> response('bye')
[9.8856843e-01 9.0067388e-08 5.4130946e-13 4.1699337e-08 1.6880620e-14
7.1965023e-03 4.2349650e-03]
[(u'goodbye', 0.9885684)]
See you later, thanks for visiting
u'See you later, thanks for visiting'
>>> response('thanks!')
[7.4308193e-03 2.5330344e-04 3.4046589e-19 1.9528095e-15 6.1316281e-16
1.4109991e-09 9.9231589e-01]
[(u'thanks', 0.9923159)]
Any time!
u'Any time!'
>>> response('which movies you have?')
[3.7415457e-20 6.2959171e-17 9.9830151e-01 5.1191595e-04 1.1865206e-03
2.0078308e-12 3.1797434e-23]
[(u'movies', 0.9983015)]
Here's the movies list. We have Moana, Tarzan, and Frozen.
u"Here's the movies list. We have Moana, Tarzan, and Frozen."
>>> response('which shows do you have?')
[4.6719631e-23 2.7403475e-11 2.0165250e-03 1.9235664e-09 9.9798346e-01
2.4630931e-19 1.0165740e-20]
[(u'shows', 0.99798346)]
Here's the shows list. We have Sesame Street, Mickey Mouse Playhouse, and Puppy Dog pals.
u"Here's the shows list. We have Sesame Street, Mickey Mouse Playhouse, and Puppy Dog pals."
>>> response('Play movie')
[5.5635421e-14 1.9603365e-24 4.3229596e-03 9.9451643e-01 6.9768643e-13
1.1605433e-03 7.7749910e-24]
[(u'play', 0.99451643)]
Playing.
u'Playing.'
>>> response('Play any movie')
[5.5635421e-14 1.9603365e-24 4.3229596e-03 9.9451643e-01 6.9768643e-13
1.1605433e-03 7.7749910e-24]
[(u'play', 0.99451643)]
Playing.
u'Playing.'
>>> response('Play movie tarzan')
[5.5635421e-14 1.9603365e-24 4.3229596e-03 9.9451643e-01 6.9768643e-13
1.1605433e-03 7.7749910e-24]
[(u'play', 0.99451643)]
Playing.
u'Playing.'
>>> response('Hop on one foot')
[0.11652738 0.16857924 0.0711435 0.38504073 0.09938802 0.12485332
0.03446784]
[]
'Unknown Command'
>>> response('Stop movie')
[4.9643923e-08 3.0365553e-22 1.6420231e-07 2.3848217e-02 4.2257686e-17
9.7615153e-01 6.6083926e-18]
[(u'stop', 0.9761515)]
Stopping.
u'Stopping.'
>>>

Leave a Reply

Your email address will not be published. Required fields are marked *