##---- This script was made for educational purposes ----##
##---- Data was taken after request from a published ----##
##---- Research Article N.Karagianni et al.(2019) ----##
##---- https://doi.org/10.1371/journal.pcbi.1006933 ----##
::opts_chunk$set(message = FALSE, warning = FALSE)
knitroptions(warn = -1)
suppressPackageStartupMessages({
library(preprocessCore)
library(umap)
library(ggplot2)
library(multcomp)
library(gplots)
library(factoextra)
library(dplyr)
library(kableExtra)
library(gprofiler2)
library(randomForest)
library(caret)
library(cowplot)
library(RColorBrewer)
library(plotly)
})
1 Part 1 - Introduction
Advancements in high-throughput sequencing technologies have revolutionized our understanding of gene expression, providing a comprehensive view of cellular processes. Differential gene expression analysis plays a pivotal role in identifying genes that are significantly altered between different experimental conditions, shedding light on biological mechanisms underlying diverse phenotypes.
This notebook serves as a practical guide to conduct a differential analysis of gene expression using R, a powerful programming language for statistical computing and graphics. Focused on employing Analysis of Variance (ANOVA), a robust statistical technique, the notebook will walk you through the step-by-step process of comparing gene expression levels across multiple conditions. ANOVA allows for the simultaneous assessment of variations within and between groups, enabling the identification of genes with expression patterns that are significantly different across experimental conditions.
In the last part of the workshop, an attempt will be made to use machine learning algorithms for treatment prediction, based on gene expression data, for research purposes.
1.1 Microarrays
A microarray is a laboratory tool used to detect the expression of thousands of genes at the same time. DNA microarrays are microscope slides that are printed with thousands of tiny spots in defined positions, with each spot containing a known DNA sequence or gene. Often, these slides are referred to as gene chips or DNA chips. The DNA molecules attached to each slide act as probes to detect gene expression, which is also known as the transcriptome or the set of messenger RNA (mRNA) transcripts expressed by a group of genes.
To perform a microarray analysis, mRNA molecules are typically collected from both an experimental sample and a reference sample. For example, the reference sample could be collected from a healthy individual, and the experimental sample could be collected from an individual with a disease like cancer. The two mRNA samples are then converted into complementary DNA (cDNA), and each sample is labeled with a fluorescent probe of a different color. For instance, the experimental cDNA sample may be labeled with a red fluorescent dye, whereas the reference cDNA may be labeled with a green fluorescent dye. The two samples are then mixed together and allowed to bind to the microarray slide. The process in which the cDNA molecules bind to the DNA probes on the slide is called hybridization. Following hybridization, the microarray is scanned to measure the expression of each gene printed on the slide. If the expression of a particular gene is higher in the experimental sample than in the reference sample, then the corresponding spot on the microarray appears red. In contrast, if the expression in the experimental sample is lower than in the reference sample, then the spot appears green. Finally, if there is equal expression in the two samples, then the spot appears yellow. The data gathered through microarrays can be used to create gene expression profiles, which show simultaneous changes in the expression of many genes in response to a particular condition or treatment. (“Microarray | Learn Science at Scitable” 2024)
(Afzal, Manzoor, and Kuipers 2015)
Microarray Data is stored in a matrix of specific format like the one represented in the table:
Gene id | Sample 1 | Sample 2 | Sample 3 | Sample 4 |
---|---|---|---|---|
Gene 1 | 1,1 | 1,2 | 1,3 | 1,4 |
Gene 2 | 2,1 | 2,2 | 2,3 | 2,4 |
Gene 3 | 3,1 | 3,2 | 3,3 | 3,4 |
1.2 Anti-TNF agents
A number of anti-TNF drugs are being used in the treatment of inflammatory autoimmune diseases, such as Rheumatoid Arthritis and Crohn’s Disease. Despite their wide use there has been, to date, no detailed analysis of their effect on the affected tissues at a transcriptome level. Four different anti-TNF drugs were applied on an established mouse model of inflammatory polyarthritis and they collected a large number of independent biological replicates from the synovial tissue of healthy, diseased and treated animals. (Karagianni et al. 2019)
1.3 Format of Data
Every data analysis process starts with understanding the format of the data and what it contains, in order to understand the problem and how to analyze it. Our data include information about genes and different experimental conditions in hTNFTg mouse model of inflammatory polyarthritis (Karagianni et al. 2019). Here’s a breakdown of the dataset column names:
Gene: This column contains the gene names.
A_Wt, A_Wt.1, A_Wt.2, …, A_Wt.9: These columns represent samples under wild type condition (A_Wt), which is the initial state, without the administration of any drug. Numbers indicate different replicates.
B_Tg, B_Tg.1, B_Tg.2, …, B_Tg.11: Similar to the A_Wt conditions, these columns represent samples under transgenic condition, with different replicates.
C_Proph_Ther_Rem, C_Proph_Ther_Rem.1, C_Proph_Ther_Rem.2: The Proph_Ther_Rem condition is the intervention of infliximab at a prophylactic stage, starting from 3 weeks of age of mice.
D_Ther_Rem, D_Ther_Rem.1, D_Ther_Rem.2, …, D_Ther_Rem.9: Samples under infliximab (Remicade) condition.
E_Ther_Hum, E_Ther_Hum.1, E_Ther_Hum.2, …, E_Ther_Hum.9: Samples under adalimumab (Humira) condition.
F_Ther_Enb, F_Ther_Enb.1, F_Ther_Enb.2, …, F_Ther_Enb.9: Samples under etanercept (Enbrel) condition.
G_Ther_Cim, G_Ther_Cim.1, G_Ther_Cim.2, …, G_Ther_Cim.9: Samples under certolizumab pegol (Cimzia) condition.
Each condition has multiple replicates denoted by the numbers following the condition abbreviation. This dataset structure is typical for differential gene expression analysis, where each column represents a different sample or replicate, and each row represents a gene with corresponding expression values across different conditions.
1.4 Analysis Pipeline
2 Methodology
Firstly, we load some necessary R packages, that will facilitate our analysis. These packages concern some visualization libraries, such as ggplot2
, factoextra
and kableExtra
, various machine learning algorithm packages, such as caret
or randomForest
and data analysis packages, such as dplyr
.
2.1 Exploratory Data Analysis (EDA)
Exploratory Data Analysis is an approach to analyzing data sets to summarize their main characteristics and it involves a comprehensive examination of the underlying structure and characteristics of a dataset. It is performed to understand the biological/biomedical data, the context about them, understand the variables and their interrelationships, and formulate hypotheses that could be useful in building predictive models and for further analysis.
# Set Working Directory
# path to working directory for Windows users
# setwd("C:\\Users\\USER\\Desktop\\")
# path to working directory for Linux/Mac users
# setwd("~")
# read file
= read.delim(# insert file name
genes_data file = "Supplement/Raw_common18704genes_antiTNF.tsv",
# try "T" or "F"
header = T,
# try "1" or "0"
row.names = 1,
# try "\t" or ","
sep = "\t")
# plot a boxplot
boxplot(genes_data,
# try "T" or "F"
horizontal= T,
# try "0" or "1"
las= 1,
# try "0.2" or "0.5"
cex.axis= 0.5)
# Number of rows
= nrow(genes_data)
n
# Dataset Dimensions
dim(genes_data)
[1] 18703 66
# Show head of the data frame
kable(head(genes_data)) |>
kable_styling(bootstrap_options = c("striped")) |>
scroll_box(width = "100%", height = "100%") |>
kable_classic()
Exp1Wt_1 | Exp1Wt_2 | Exp1Wt_3 | Exp2Wt_1 | Exp2Wt_2 | Exp2Wt_3 | Exp2Wt_4 | Exp3Wt_1 | Exp3Wt_2 | Exp3Wt_3 | Exp1Tg_1 | Exp1Tg_2 | Exp1Tg_3 | Exp2Tg_1 | Exp2Tg_2 | Exp2Tg_3 | Exp2Tg_4 | Exp3Tg_1 | Exp3Tg_2 | Exp3Tg_3 | Exp4Tg_1 | Exp4Tg_2 | Exp4Tg_3 | Exp1Rem3_1 | Exp1Rem3_2 | Exp1Rem3_3 | Exp1Rem6_1 | Exp1Rem6_2 | Exp1Rem6_3 | Exp2Rem6_1 | Exp2Rem6_2 | Exp2Rem6_3 | Exp2Rem6_4 | Exp3Rem6_1 | Exp3Rem6_2 | Exp3Rem6_3 | Exp2Hum6_1 | Exp2Hum6_2 | Exp2Hum6_3 | Exp2Hum6_4 | Exp3Hum6_1 | Exp3Hum6_2 | Exp3Hum6_3 | Exp4Hum6_1 | Exp4Hum6_2 | Exp4Hum6_3 | Exp2Enb6_1 | Exp2Enb6_2 | Exp2Enb6_3 | Exp2Enb6_4 | Exp4Enb6_1 | Exp4Enb6_2 | Exp4Enb6_3 | Exp4Enb6_4 | Exp4Enb6_5 | Exp4Enb6_6 | Exp2Cim6_1 | Exp2Cim6_2 | Exp2Cim6_3 | Exp2Cim6_4 | Exp4Cim6_1 | Exp4Cim6_2 | Exp4Cim6_3 | Exp4Cim6_4 | Exp4Cim6_5 | Exp4Cim6_6 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
A1bg | 3.78911 | 3.90081 | 3.72526 | 4.23290 | 4.14451 | 4.17460 | 4.19904 | 4.37631 | 4.35622 | 4.35167 | 3.78454 | 4.07887 | 4.13286 | 4.05313 | 4.20157 | 4.18684 | 4.27081 | 4.50461 | 4.29096 | 4.36422 | 3.74793 | 3.74200 | 3.79036 | 3.59538 | 3.96438 | 3.79821 | 3.55839 | 3.72886 | 3.73221 | 4.00460 | 4.06560 | 4.10832 | 4.14768 | 4.45705 | 4.40942 | 4.29107 | 4.23619 | 4.11532 | 4.04981 | 4.05459 | 4.38727 | 4.36555 | 4.49019 | 3.55204 | 3.45422 | 3.75162 | 4.11680 | 4.11782 | 4.09583 | 4.05194 | 3.70226 | 3.75635 | 3.82224 | 3.39433 | 3.74648 | 3.48890 | 4.11928 | 4.14522 | 4.10418 | 4.10931 | 3.61480 | 3.37258 | 3.58425 | 3.88982 | 3.28356 | 4.04937 |
A1cf | 4.21654 | 4.17014 | 4.05211 | 4.60213 | 4.62320 | 4.65975 | 4.57693 | 4.15842 | 4.21211 | 4.18009 | 3.98771 | 4.11709 | 4.10684 | 4.68407 | 4.63325 | 4.73126 | 4.67542 | 4.09641 | 3.97244 | 4.10268 | 3.30531 | 3.29409 | 3.06133 | 4.29460 | 4.22492 | 4.08466 | 4.08205 | 4.13011 | 4.09484 | 4.62164 | 4.66620 | 4.61722 | 4.55999 | 4.38385 | 4.06813 | 4.13370 | 4.53864 | 4.75150 | 4.64363 | 4.68842 | 4.03449 | 4.62612 | 4.24503 | 3.39752 | 3.35704 | 3.31550 | 4.61107 | 4.71722 | 4.65451 | 4.68732 | 3.34686 | 3.26266 | 3.04503 | 3.16430 | 3.13805 | 3.10227 | 4.65152 | 4.67835 | 4.67399 | 4.61035 | 2.90180 | 3.27259 | 3.02554 | 3.12053 | 3.08666 | 3.24268 |
A2ld1 | 5.32714 | 5.62827 | 5.66799 | 8.32861 | 8.27225 | 8.27447 | 8.42341 | 8.22626 | 8.39943 | 8.57076 | 5.23156 | 5.29504 | 5.28384 | 7.90894 | 7.85233 | 8.14223 | 7.79835 | 7.90913 | 8.08984 | 7.95827 | 6.55196 | 6.51255 | 6.43711 | 6.01249 | 5.46742 | 5.54192 | 5.56968 | 5.70214 | 5.46825 | 8.26541 | 8.30650 | 8.22540 | 8.09633 | 8.30025 | 7.86106 | 7.86827 | 8.19100 | 8.37507 | 8.20061 | 8.27231 | 8.39751 | 8.30546 | 8.49839 | 6.69627 | 6.52055 | 6.64086 | 8.00233 | 8.18752 | 8.25757 | 8.03628 | 6.43991 | 6.62674 | 6.80411 | 6.40195 | 6.77547 | 6.49056 | 8.09591 | 8.09534 | 8.08303 | 8.07122 | 6.51077 | 6.56018 | 6.40339 | 6.71310 | 6.35072 | 6.61334 |
A2m | 5.28545 | 6.49319 | 5.19705 | 6.34696 | 5.68818 | 7.02162 | 6.30722 | 7.24319 | 6.80225 | 6.69186 | 4.71382 | 5.03411 | 5.41249 | 6.57654 | 6.10905 | 6.11674 | 5.67339 | 6.93047 | 6.70562 | 6.65830 | 5.29271 | 5.47738 | 6.79552 | 6.19873 | 5.40119 | 6.48264 | 5.78780 | 5.32115 | 5.44562 | 6.88086 | 5.34267 | 6.33201 | 6.39798 | 6.45636 | 6.43533 | 6.19721 | 6.10152 | 6.31918 | 5.95871 | 6.76260 | 6.76862 | 6.14994 | 5.71077 | 5.23411 | 5.38092 | 5.36692 | 5.98963 | 5.63186 | 5.84172 | 5.34126 | 5.51386 | 5.58334 | 5.51965 | 5.63152 | 5.64672 | 6.46401 | 5.42400 | 6.97807 | 6.39452 | 5.24073 | 4.64791 | 4.64806 | 6.10691 | 5.04173 | 4.90970 | 4.32605 |
A3galt2 | 4.59905 | 4.59698 | 4.52439 | 4.85959 | 5.07224 | 5.01061 | 5.07838 | 5.62244 | 5.79039 | 5.66514 | 4.73714 | 4.90568 | 5.18567 | 4.95670 | 4.65065 | 4.95141 | 4.96971 | 5.23615 | 5.38050 | 5.49452 | 4.72958 | 4.78397 | 4.66467 | 4.41278 | 4.82166 | 4.49756 | 4.54898 | 4.53977 | 4.85098 | 4.89872 | 4.96186 | 5.01156 | 5.02533 | 5.50526 | 5.51928 | 5.52995 | 5.12319 | 5.15686 | 5.02892 | 4.91145 | 5.58904 | 5.62234 | 5.64090 | 4.49644 | 4.98682 | 4.62059 | 4.94060 | 5.10253 | 4.92040 | 4.80770 | 4.63297 | 4.79730 | 4.73491 | 4.63326 | 4.78748 | 4.69899 | 4.96660 | 5.02830 | 4.96265 | 5.03972 | 4.70114 | 4.64965 | 4.50466 | 4.70696 | 4.55098 | 4.64297 |
A4galt | 7.73303 | 7.65939 | 7.93984 | 8.55175 | 8.48415 | 8.47890 | 8.22892 | 8.72356 | 8.71276 | 8.58030 | 7.22117 | 7.00438 | 6.80762 | 8.65125 | 8.49504 | 8.61091 | 8.60534 | 8.90632 | 8.84868 | 8.88411 | 8.87908 | 8.68815 | 8.59815 | 7.98948 | 7.60469 | 7.47936 | 7.60934 | 7.44681 | 7.36165 | 8.70350 | 8.61929 | 8.80555 | 8.47461 | 8.76373 | 9.06743 | 9.36881 | 8.55062 | 8.73755 | 8.65360 | 8.69017 | 9.22244 | 9.12786 | 9.25526 | 8.76674 | 8.93546 | 8.86313 | 8.66064 | 8.60910 | 8.63829 | 8.86686 | 8.73614 | 8.96106 | 8.77789 | 8.77312 | 8.97563 | 8.70684 | 8.83717 | 8.88996 | 8.98343 | 8.75343 | 8.80162 | 8.76917 | 8.70345 | 8.80999 | 8.86269 | 8.62107 |
# Keep gene and sample names
= rownames(genes_data)
Gene = colnames(genes_data) Sample
2.1.1 Missing Values
Then, we check for missing values in the data. If there are any, we will need to decide how to handle them, probably by removing the genes with missing values.
# Check genes_data for missing values
colSums(is.na(genes_data))
Exp1Wt_1 Exp1Wt_2 Exp1Wt_3 Exp2Wt_1 Exp2Wt_2 Exp2Wt_3 Exp2Wt_4
0 0 0 0 0 0 0
Exp3Wt_1 Exp3Wt_2 Exp3Wt_3 Exp1Tg_1 Exp1Tg_2 Exp1Tg_3 Exp2Tg_1
0 0 0 0 0 0 0
Exp2Tg_2 Exp2Tg_3 Exp2Tg_4 Exp3Tg_1 Exp3Tg_2 Exp3Tg_3 Exp4Tg_1
0 0 0 0 0 0 0
Exp4Tg_2 Exp4Tg_3 Exp1Rem3_1 Exp1Rem3_2 Exp1Rem3_3 Exp1Rem6_1 Exp1Rem6_2
0 0 0 0 0 0 0
Exp1Rem6_3 Exp2Rem6_1 Exp2Rem6_2 Exp2Rem6_3 Exp2Rem6_4 Exp3Rem6_1 Exp3Rem6_2
0 0 0 0 0 0 0
Exp3Rem6_3 Exp2Hum6_1 Exp2Hum6_2 Exp2Hum6_3 Exp2Hum6_4 Exp3Hum6_1 Exp3Hum6_2
0 0 0 0 0 0 0
Exp3Hum6_3 Exp4Hum6_1 Exp4Hum6_2 Exp4Hum6_3 Exp2Enb6_1 Exp2Enb6_2 Exp2Enb6_3
0 0 0 0 0 0 0
Exp2Enb6_4 Exp4Enb6_1 Exp4Enb6_2 Exp4Enb6_3 Exp4Enb6_4 Exp4Enb6_5 Exp4Enb6_6
0 0 0 0 0 0 0
Exp2Cim6_1 Exp2Cim6_2 Exp2Cim6_3 Exp2Cim6_4 Exp4Cim6_1 Exp4Cim6_2 Exp4Cim6_3
0 0 0 0 0 0 0
Exp4Cim6_4 Exp4Cim6_5 Exp4Cim6_6
0 0 0
# Alternative method for total sum of missing values
# apply takes as input a dataframe and a function to apply to each row (1) or column (2)
sum(apply(genes_data, 2, function(x) any(is.na(x))))
[1] 0
2.1.2 Data Distribution
Understanding the distribution of the data is a fundamental aspect of EDA. Examining data distribution provides insights into the central tendencies, variabilities, and patterns within the dataset. A thorough exploration of data distribution aids in making informed decisions about appropriate statistical analyses and understanding the inherent variability, which is crucial for formulating hypotheses and guiding subsequent modeling or inferential procedures. As such, a detailed assessment of data distribution is a foundational step in unraveling the complexities of any dataset during the EDA process.
# Adjust the layout and margins as needed
par(mfrow = c(8, 9), mar = c(1, 1, 2.5, 1))
for (col in colnames(genes_data)) {
plot(density(genes_data[[col]]),
main = col,
xlab = col, col = "#009AEF", lwd = 2)
}
%>%
genes_data select_if(is.numeric) %>%
apply(2, function(x) round(summary(x), 3)) %>%
kbl() %>%
kable_styling(bootstrap_options = c("striped", "bordered")) %>%
kable_classic() %>%
scroll_box(width = "100%", height = "100%")
Exp1Wt_1 | Exp1Wt_2 | Exp1Wt_3 | Exp2Wt_1 | Exp2Wt_2 | Exp2Wt_3 | Exp2Wt_4 | Exp3Wt_1 | Exp3Wt_2 | Exp3Wt_3 | Exp1Tg_1 | Exp1Tg_2 | Exp1Tg_3 | Exp2Tg_1 | Exp2Tg_2 | Exp2Tg_3 | Exp2Tg_4 | Exp3Tg_1 | Exp3Tg_2 | Exp3Tg_3 | Exp4Tg_1 | Exp4Tg_2 | Exp4Tg_3 | Exp1Rem3_1 | Exp1Rem3_2 | Exp1Rem3_3 | Exp1Rem6_1 | Exp1Rem6_2 | Exp1Rem6_3 | Exp2Rem6_1 | Exp2Rem6_2 | Exp2Rem6_3 | Exp2Rem6_4 | Exp3Rem6_1 | Exp3Rem6_2 | Exp3Rem6_3 | Exp2Hum6_1 | Exp2Hum6_2 | Exp2Hum6_3 | Exp2Hum6_4 | Exp3Hum6_1 | Exp3Hum6_2 | Exp3Hum6_3 | Exp4Hum6_1 | Exp4Hum6_2 | Exp4Hum6_3 | Exp2Enb6_1 | Exp2Enb6_2 | Exp2Enb6_3 | Exp2Enb6_4 | Exp4Enb6_1 | Exp4Enb6_2 | Exp4Enb6_3 | Exp4Enb6_4 | Exp4Enb6_5 | Exp4Enb6_6 | Exp2Cim6_1 | Exp2Cim6_2 | Exp2Cim6_3 | Exp2Cim6_4 | Exp4Cim6_1 | Exp4Cim6_2 | Exp4Cim6_3 | Exp4Cim6_4 | Exp4Cim6_5 | Exp4Cim6_6 | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Min. | 3.376 | 3.144 | 3.338 | 3.726 | 3.615 | 3.586 | 3.555 | 1.029 | 0.978 | 0.806 | 3.349 | 3.261 | 3.282 | 3.607 | 3.728 | 3.754 | 3.605 | 0.751 | 1.088 | 1.023 | 1.177 | 1.101 | 1.058 | 3.407 | 3.372 | 3.283 | 3.390 | 3.329 | 3.305 | 3.682 | 3.624 | 3.589 | 3.662 | 0.978 | 1.015 | 1.059 | 3.626 | 3.578 | 3.658 | 3.689 | 1.100 | 0.953 | 1.021 | 1.084 | 1.144 | 1.114 | 3.733 | 3.609 | 3.716 | 3.787 | 1.210 | 1.096 | 1.147 | 1.376 | 1.283 | 1.318 | 3.632 | 3.676 | 3.691 | 3.685 | 1.233 | 1.147 | 1.014 | 1.377 | 1.201 | 1.128 |
1st Qu. | 4.550 | 4.524 | 4.441 | 5.039 | 4.981 | 4.993 | 5.038 | 5.169 | 5.199 | 5.276 | 4.596 | 4.719 | 4.808 | 4.973 | 4.938 | 4.987 | 5.027 | 5.155 | 5.186 | 5.172 | 4.358 | 4.395 | 4.352 | 4.565 | 4.675 | 4.493 | 4.525 | 4.500 | 4.705 | 4.952 | 4.956 | 4.982 | 5.004 | 5.269 | 5.199 | 5.177 | 4.976 | 4.975 | 4.952 | 4.968 | 5.170 | 5.201 | 5.208 | 4.376 | 4.365 | 4.368 | 5.027 | 5.018 | 4.979 | 4.960 | 4.366 | 4.379 | 4.305 | 4.365 | 4.314 | 4.378 | 4.973 | 4.994 | 4.962 | 4.976 | 4.323 | 4.316 | 4.282 | 4.319 | 4.344 | 4.301 |
Median | 6.030 | 6.070 | 6.107 | 6.790 | 6.841 | 6.833 | 6.752 | 6.727 | 6.706 | 6.665 | 6.042 | 5.997 | 6.029 | 6.831 | 6.840 | 6.852 | 6.781 | 6.734 | 6.730 | 6.745 | 5.806 | 5.761 | 5.783 | 6.126 | 6.066 | 6.057 | 6.040 | 6.026 | 6.016 | 6.813 | 6.812 | 6.810 | 6.849 | 6.691 | 6.757 | 6.714 | 6.837 | 6.804 | 6.827 | 6.839 | 6.744 | 6.726 | 6.708 | 5.806 | 5.805 | 5.789 | 6.811 | 6.808 | 6.825 | 6.864 | 5.765 | 5.780 | 5.798 | 5.773 | 5.778 | 5.792 | 6.834 | 6.798 | 6.847 | 6.815 | 5.786 | 5.805 | 5.799 | 5.788 | 5.806 | 5.762 |
Mean | 6.260 | 6.285 | 6.286 | 6.960 | 6.952 | 6.944 | 6.934 | 6.623 | 6.619 | 6.616 | 6.270 | 6.221 | 6.233 | 6.966 | 6.952 | 6.981 | 6.943 | 6.616 | 6.624 | 6.626 | 5.743 | 5.726 | 5.730 | 6.341 | 6.296 | 6.266 | 6.265 | 6.240 | 6.245 | 6.948 | 6.952 | 6.952 | 6.952 | 6.624 | 6.637 | 6.623 | 6.958 | 6.958 | 6.953 | 6.969 | 6.624 | 6.635 | 6.630 | 5.756 | 5.737 | 5.732 | 6.957 | 6.960 | 6.950 | 6.972 | 5.730 | 5.750 | 5.738 | 5.736 | 5.732 | 5.744 | 6.953 | 6.942 | 6.957 | 6.952 | 5.738 | 5.740 | 5.731 | 5.740 | 5.747 | 5.728 |
3rd Qu. | 7.679 | 7.745 | 7.797 | 8.523 | 8.536 | 8.526 | 8.487 | 8.123 | 8.092 | 8.028 | 7.649 | 7.452 | 7.389 | 8.601 | 8.594 | 8.599 | 8.522 | 8.147 | 8.126 | 8.138 | 7.113 | 7.046 | 7.091 | 7.826 | 7.637 | 7.727 | 7.704 | 7.679 | 7.513 | 8.556 | 8.576 | 8.538 | 8.524 | 8.056 | 8.135 | 8.133 | 8.560 | 8.570 | 8.568 | 8.581 | 8.127 | 8.131 | 8.109 | 7.134 | 7.091 | 7.101 | 8.525 | 8.532 | 8.542 | 8.612 | 7.068 | 7.099 | 7.134 | 7.094 | 7.120 | 7.099 | 8.555 | 8.523 | 8.573 | 8.558 | 7.133 | 7.147 | 7.140 | 7.137 | 7.126 | 7.129 |
Max. | 13.482 | 13.700 | 13.650 | 13.684 | 13.776 | 13.726 | 13.653 | 12.926 | 12.912 | 12.887 | 13.204 | 13.218 | 13.116 | 13.725 | 13.781 | 13.700 | 13.700 | 13.081 | 12.927 | 13.040 | 12.801 | 12.838 | 13.148 | 13.711 | 13.501 | 13.562 | 13.473 | 13.644 | 13.453 | 13.711 | 13.700 | 13.694 | 13.726 | 12.937 | 13.001 | 12.999 | 13.694 | 13.699 | 13.718 | 13.704 | 13.073 | 12.970 | 12.947 | 12.823 | 12.837 | 12.995 | 13.695 | 13.696 | 13.734 | 13.767 | 12.731 | 12.831 | 12.784 | 12.752 | 12.816 | 12.797 | 13.712 | 13.791 | 13.753 | 13.733 | 12.815 | 12.854 | 12.995 | 12.851 | 12.833 | 12.759 |
= function(data.frame) {
calculate_metrics <- apply(data.frame, 2, max)
max <- apply(data.frame, 2, min)
min <- (max + min) / 2
mean
= data.frame(name = colnames(data.frame),
dt_matrix min = as.numeric(as.character(min)),
max = as.numeric(as.character(max)),
mean = as.numeric(as.character(mean)))
return(dt_matrix)
}
# Calculate metrics for each condition
= calculate_metrics(genes_data)
c_metrics c_metrics
name min max mean
1 Exp1Wt_1 3.37556 13.4822 8.428880
2 Exp1Wt_2 3.14427 13.7005 8.422385
3 Exp1Wt_3 3.33822 13.6498 8.494010
4 Exp2Wt_1 3.72646 13.6836 8.705030
5 Exp2Wt_2 3.61474 13.7756 8.695170
6 Exp2Wt_3 3.58591 13.7262 8.656055
7 Exp2Wt_4 3.55539 13.6532 8.604295
8 Exp3Wt_1 1.02914 12.9258 6.977470
9 Exp3Wt_2 0.97795 12.9121 6.945025
10 Exp3Wt_3 0.80624 12.8875 6.846870
11 Exp1Tg_1 3.34917 13.2042 8.276685
12 Exp1Tg_2 3.26118 13.2179 8.239540
13 Exp1Tg_3 3.28197 13.1161 8.199035
14 Exp2Tg_1 3.60711 13.7250 8.666055
15 Exp2Tg_2 3.72809 13.7809 8.754495
16 Exp2Tg_3 3.75376 13.6998 8.726780
17 Exp2Tg_4 3.60466 13.6999 8.652280
18 Exp3Tg_1 0.75115 13.0814 6.916275
19 Exp3Tg_2 1.08764 12.9265 7.007070
20 Exp3Tg_3 1.02303 13.0399 7.031465
21 Exp4Tg_1 1.17688 12.8012 6.989040
22 Exp4Tg_2 1.10078 12.8384 6.969590
23 Exp4Tg_3 1.05794 13.1482 7.103070
24 Exp1Rem3_1 3.40727 13.7114 8.559335
25 Exp1Rem3_2 3.37224 13.5005 8.436370
26 Exp1Rem3_3 3.28277 13.5621 8.422435
27 Exp1Rem6_1 3.38981 13.4728 8.431305
28 Exp1Rem6_2 3.32883 13.6436 8.486215
29 Exp1Rem6_3 3.30500 13.4533 8.379150
30 Exp2Rem6_1 3.68185 13.7110 8.696425
31 Exp2Rem6_2 3.62371 13.7001 8.661905
32 Exp2Rem6_3 3.58858 13.6942 8.641390
33 Exp2Rem6_4 3.66171 13.7255 8.693605
34 Exp3Rem6_1 0.97805 12.9367 6.957375
35 Exp3Rem6_2 1.01526 13.0005 7.007880
36 Exp3Rem6_3 1.05879 12.9986 7.028695
37 Exp2Hum6_1 3.62648 13.6944 8.660440
38 Exp2Hum6_2 3.57819 13.6989 8.638545
39 Exp2Hum6_3 3.65832 13.7184 8.688360
40 Exp2Hum6_4 3.68866 13.7042 8.696430
41 Exp3Hum6_1 1.09956 13.0734 7.086480
42 Exp3Hum6_2 0.95331 12.9700 6.961655
43 Exp3Hum6_3 1.02125 12.9465 6.983875
44 Exp4Hum6_1 1.08401 12.8233 6.953655
45 Exp4Hum6_2 1.14380 12.8366 6.990200
46 Exp4Hum6_3 1.11394 12.9948 7.054370
47 Exp2Enb6_1 3.73300 13.6948 8.713900
48 Exp2Enb6_2 3.60938 13.6959 8.652640
49 Exp2Enb6_3 3.71600 13.7344 8.725200
50 Exp2Enb6_4 3.78704 13.7671 8.777070
51 Exp4Enb6_1 1.21022 12.7314 6.970810
52 Exp4Enb6_2 1.09627 12.8306 6.963435
53 Exp4Enb6_3 1.14697 12.7839 6.965435
54 Exp4Enb6_4 1.37550 12.7517 7.063600
55 Exp4Enb6_5 1.28300 12.8161 7.049550
56 Exp4Enb6_6 1.31791 12.7969 7.057405
57 Exp2Cim6_1 3.63227 13.7120 8.672135
58 Exp2Cim6_2 3.67638 13.7910 8.733690
59 Exp2Cim6_3 3.69146 13.7532 8.722330
60 Exp2Cim6_4 3.68540 13.7332 8.709300
61 Exp4Cim6_1 1.23322 12.8151 7.024160
62 Exp4Cim6_2 1.14684 12.8535 7.000170
63 Exp4Cim6_3 1.01430 12.9947 7.004500
64 Exp4Cim6_4 1.37744 12.8509 7.114170
65 Exp4Cim6_5 1.20130 12.8331 7.017200
66 Exp4Cim6_6 1.12756 12.7590 6.943280
2.2 Data Normalization
Before running UMAP, we execute quantile normalization in the data. Quantile normalization is a preprocessing step commonly used when comparing multiple samples or conditions. It is necessary because ANOVA assumes normally distributed residuals and homogeneity of variances, meaning that the variance is roughly the same across all groups.
# Normalization
# convert dataframe to matrix
# try "as.matrix" or "as.data.frame"
= as.matrix(genes_data)
genes_data
# normalize data
= normalize.quantiles(genes_data , copy=TRUE)
genes_data
# convert matrix to dataframe
# try "data.frame" or "matrix"
= data.frame(genes_data)
genes_data
# add column names to dataframe
# try "colnames" or "rownames" [1] and "Sample" or "Gene" [2]
colnames(genes_data) = Sample
# add row names to dataframe
# try "colnames" or "rownames" [1] and "Sample" or "Gene" [2]
rownames(genes_data) = Gene
# Boxplot visualization after normalization
boxplot( genes_data, horizontal=T , las=1 , cex.axis=0.5 )
# Adjust the layout and margins as needed
par(mfrow = c(8, 9), mar = c(1, 1, 2.5, 1))
for (col in colnames(genes_data)) {
plot(density(genes_data[[col]]),
main = col,
xlab = col, col = "#009AEF", lwd = 2)
}
# Write normalized data to file for future use in part 2
# Setting the Condition Strings in the first column
= factor(c(
group "Gene",
paste0("A_Wt.", 1:10),
paste0("B_Tg.", 1:13),
paste0("C_Proph_Ther_Rem.", 1:3),
paste0("D_Ther_Rem.", 1:10),
paste0("E_Ther_Hum.", 1:10),
paste0("F_Ther_Enb.", 1:10),
paste0("G_Ther_Cim.", 1:10)
))
write.table(data.frame(rownames(genes_data), genes_data),
file = "Supplement/Raw_common18704genes_antiTNF_normalized.tsv",
sep = "\t",
quote = F,
row.names = F,
col.names = group)
2.3 Principal Components Analysis (PCA) & Uniform Manifold Approximation and Projection (UMAP)
In this section, the PCA and UMAP techniques are used to increase the interpretability and reduce the dimensionality of the data, keeping only the components that contain enough information.
UMAP is a dimensionality reduction technique commonly used for visualizing high-dimensional data in a lower-dimensional space. This algorithm is particularly valuable for visualizing complex datasets such as genomics, single-cell RNA sequencing, and other high-dimensional biological applications. Its flexibility, speed, and ability to retain meaningful structures make UMAP a powerful tool for exploratory data analysis and gaining insights into the inherent structures of diverse datasets.
Firstly, we preprocess the data to keep only WT and TG conditions for simplicity and we plot the first two UMAP components. This UMAP plot captures the essential structure of the data in a lower-dimensional space, effectively highlighting the distinct patterns and relationships between wild-type (WT) and transgenic (TG) conditions.
# We prepare dataframe for UMAP dimension reduction
# We check if samples are separated in 2 dimensions
# Keep only WT and TG samples
= genes_data[, 1:23]
wt_tg_df
# After dataframe transposition columns must represent genes
= t(wt_tg_df) wt_tg_df
# UMAP dimension reduction for wt and tg samples
<- umap(wt_tg_df, n_components=2, random_state=15)
wt_tg_df.umap
# Keep the numeric dimensions
<- wt_tg_df.umap[["layout"]]
wt_tg_df.umap
# Create vector with groups
= c(rep("A_Wt", 10), rep("B_Tg", 13))
group
# Create final dataframe with dimensions and group for plotting
<- cbind(wt_tg_df.umap, group)
wt_tg_df.umap <- data.frame(wt_tg_df.umap)
wt_tg_df.umap
# Plot UMAP results
ggplotly(
ggplot(wt_tg_df.umap, aes(x = V1, y = V2, color = group)) +
geom_point() +
labs(
x = "UMAP1",
y = "UMAP2",
title = "UMAP plot",
subtitle = "A UMAP Visualization of WT and TG samples") +
theme(
axis.text.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks = element_blank()
) )
Principal Component Analysis (PCA) is a widely used dimensionality reduction technique that transforms high-dimensional data into a new coordinate system, revealing its underlying structure. In PCA, the first principal component captures the maximum variance in the data, with subsequent components capturing decreasing amounts of variance. This reduction not only simplifies the dataset but also allows for the identification of the most significant features driving variability.
The table below shows the standard deviation and variance of each PCA component. It turns out that only the first 3 components represent more than 84% of the variability of the data, which facilitates the selection of the main features from the total components. The next step is to graphically represent the contribution of each component to the overall information.
# PCA dimension reduction
<- prcomp(wt_tg_df, scale. = FALSE)
wt_tg_df.pca
summary(wt_tg_df.pca)
Importance of components:
PC1 PC2 PC3 PC4 PC5 PC6 PC7
Standard deviation 64.2329 34.1273 30.6454 20.32780 13.6953 8.9139 7.93867
Proportion of Variance 0.5608 0.1583 0.1277 0.05617 0.0255 0.0108 0.00857
Cumulative Proportion 0.5608 0.7191 0.8468 0.90298 0.9285 0.9393 0.94785
PC8 PC9 PC10 PC11 PC12 PC13 PC14
Standard deviation 6.80061 6.34603 6.13851 5.80207 5.57370 5.31339 5.10862
Proportion of Variance 0.00629 0.00547 0.00512 0.00458 0.00422 0.00384 0.00355
Cumulative Proportion 0.95413 0.95961 0.96473 0.96930 0.97353 0.97737 0.98091
PC15 PC16 PC17 PC18 PC19 PC20 PC21
Standard deviation 4.95260 4.73197 4.56130 4.14881 3.95569 3.74775 3.64909
Proportion of Variance 0.00333 0.00304 0.00283 0.00234 0.00213 0.00191 0.00181
Cumulative Proportion 0.98425 0.98729 0.99012 0.99246 0.99459 0.99649 0.99830
PC22 PC23
Standard deviation 3.5312 8.294e-14
Proportion of Variance 0.0017 0.000e+00
Cumulative Proportion 1.0000 1.000e+00
plot_grid(fviz_pca_ind(wt_tg_df.pca, repel = TRUE, # Avoid text overlapping
habillage = group,
label = "none",
axes = c(1, 2), # choose PCs to plot
addEllipses = TRUE,
ellipse.level = 0.95,
title = "Biplot: PC1 vs PC2") +
scale_color_manual(values = c('#33cc00','#009AEF95')) +
scale_fill_manual(values = c('#33cc00','#009AEF95')),
fviz_pca_ind(wt_tg_df.pca, repel = TRUE, # Avoid text overlapping
habillage = group,
label = "none",
axes = c(1, 3), # choose PCs to plot
addEllipses = TRUE,
ellipse.level = 0.95,
title = "Biplot: PC1 vs PC3") +
scale_color_manual(values = c('#33cc00','#009AEF95')) +
scale_fill_manual(values = c('#33cc00','#009AEF95')),
fviz_pca_ind(wt_tg_df.pca, repel = TRUE, # Avoid text overlapping
habillage = group,
label = "none",
axes = c(2, 3), # choose PCs to plot
addEllipses = TRUE,
ellipse.level = 0.95,
title = "Biplot: PC2 vs PC3") +
scale_color_manual(values = c('#33cc00','#009AEF95')) +
scale_fill_manual(values = c('#33cc00','#009AEF95')),
# Visualize eigenvalues/variances
fviz_screeplot(wt_tg_df.pca,
addlabels = TRUE,
title = "Principal Components Contribution",
ylim = c(0, 65),
barcolor = "#009AEF95",
barfill = "#009AEF95"),
# Contributions of features to PC1
fviz_contrib(wt_tg_df.pca,
choice = "var",
axes = 1,
top = 14,
color = "#009AEF95",
fill = "#009AEF95"),
# Contributions of features to PC2
fviz_contrib(wt_tg_df.pca,
choice = "var",
axes = 2,
top = 14,
color = "#009AEF95",
fill = "#009AEF95"),
labels = c("A", "B", "C", "D", "E", "F")
)
<- data.frame("PC1" = wt_tg_df.pca$x[,1],
wt_tg_df.pca "PC2" = wt_tg_df.pca$x[,2],
"group" = group)
# Plot PCA results
# insert dataframe [1] , variables [2]-[3] and color groyp [4]
ggplot( wt_tg_df.pca, aes(x= PC1 , y= PC2 , color= group ))+
# try "geom_point" or "geom_line"
geom_point()+
# try "ggtitle" or "ggname"
ggtitle("Two First Components of PCA") +
theme(axis.text.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks = element_blank())
ggplotly()
2.4 Statistical Analysis
2.4.1 Group Treatments in dataframe
The following code performs an Analysis of Variance (ANOVA) on the gene expression levels of the first gene in the dataset (matrixdata
) across different experimental groups (group
). It then summarizes the results and calculates the mean expression value for each group.
# Create Matrix by Excluding rownames and colnames
= as.matrix(genes_data)
matrixdata
# Create Groups
= factor(c(
group rep("A_Wt", 10),
rep("B_Tg", 13),
rep("C_Proph_Ther_Rem", 3),
rep("D_Ther_Rem", 10),
rep("E_Ther_Hum", 10),
rep("F_Ther_Enb", 10),
rep("G_Ther_Cim", 10)
))
# apply ANOVA on the first gene
# create dataframe for gene1
# try "data.frame" or "as.data.frame" [1] and insert first matrix row [2]
= data.frame("gene_expression" = matrixdata[ 1 , ], "group" = group)
gene1
# ANOVA function on the first gene
# try "aov" or "anova" [1] , insert gene1 data [2] and groups [3]
= aov( gene_expression ~ group , data = gene1)
gene_aov
# summary anova results
summary(gene_aov)
Df Sum Sq Mean Sq F value Pr(>F)
group 6 2.706 0.4509 1.123 0.36
Residuals 59 23.689 0.4015
# Calculate Mean Expression value / group
<- aggregate(gene1$gene_expression,
group_mean_values list(gene1$group),
FUN=mean)
group_mean_values
Group.1 x
1 A_Wt 3.440906
2 B_Tg 3.752887
3 C_Proph_Ther_Rem 3.120895
4 D_Ther_Rem 3.295889
5 E_Ther_Hum 3.719382
6 F_Ther_Enb 3.719076
7 G_Ther_Cim 3.758434
2.4.2 ANOVA
The Analysis of Variance (ANOVA) test is a statistical method frequently employed in gene expression studies to assess the significance of expression differences across multiple experimental conditions. ANOVA determines whether there are statistically significant variations in the means of gene expression levels between different groups or conditions. In the context of gene expression data, ANOVA is particularly useful when comparing more than two groups, providing insights into whether any observed differences are likely due to actual biological effects (for example, the administration of a drug) rather than random variability. The test generates an F-statistic and a p-value, where a low p-value suggests that at least one group significantly differs from the others. Post-hoc tests, such as Tukey’s HSD (honestly significant difference), can be applied following ANOVA to identify specific groups with significantly different expression levels, offering a comprehensive approach to understanding the nuances of gene expression patterns across diverse experimental conditions.
In general:
ANOVA (Analysis of Variance):
Advantages: ANOVA is useful when you have more than two groups, allowing you to assess whether there are any significant differences in gene expression across multiple conditions simultaneously.
Considerations: ANOVA only informs you that there are differences between groups but does not identify which specific groups are different. If ANOVA indicates significance, post-hoc tests like Tukey’s HSD can be subsequently applied to pinpoint pairwise differences.
Tukey’s HSD (Honest Significant Difference) Test:
Advantages: Tukey’s HSD post-hoc test is a valuable follow-up of ANOVA. It is advantageous for identifying specific pairs of conditions that exhibit significant differences in gene expression, providing a detailed understanding of the groups that contribute to the observed variability.
Considerations: Tukey’s HSD makes assumptions of normality and homogeneity of variances.
For the purposes of the present analysis, we will focus only on the analysis of variance and Tukey’s HSD post hoc test, for simplicity and speed of calculations reasons.
# Tukey's HSD post-hoc on the first (1st) gene
<- TukeyHSD(gene_aov, conf.level = 0.95)
tukey
# ------- Metrics -------
# diff: The estimated difference in means between two different conditions.
# lwr: The lower limit of the confidence interval for the difference.
# upr: The upper limit of the confidence interval for the difference.
# p adj: The adjusted p-value for the test.
tukey
Tukey multiple comparisons of means
95% family-wise confidence level
Fit: aov(formula = gene_expression ~ group, data = gene1)
$group
diff lwr upr p adj
B_Tg-A_Wt 0.3119807821 -0.5015454 1.1255070 0.9023145
C_Proph_Ther_Rem-A_Wt -0.3200114091 -1.5931930 0.9531702 0.9871894
D_Ther_Rem-A_Wt -0.1450164545 -1.0099730 0.7199401 0.9985912
E_Ther_Hum-A_Wt 0.2784761364 -0.5864805 1.1434327 0.9558296
F_Ther_Enb-A_Wt 0.2781700152 -0.5867866 1.1431266 0.9560601
G_Ther_Cim-A_Wt 0.3175276970 -0.5474289 1.1824843 0.9192663
C_Proph_Ther_Rem-B_Tg -0.6319921911 -1.8708087 0.6068244 0.7093658
D_Ther_Rem-B_Tg -0.4569972366 -1.2705235 0.3565290 0.6092227
E_Ther_Hum-B_Tg -0.0335046457 -0.8470309 0.7800216 0.9999996
F_Ther_Enb-B_Tg -0.0338107669 -0.8473370 0.7797155 0.9999996
G_Ther_Cim-B_Tg 0.0055469149 -0.8079793 0.8190731 1.0000000
D_Ther_Rem-C_Proph_Ther_Rem 0.1749949545 -1.0981867 1.4481766 0.9995461
E_Ther_Hum-C_Proph_Ther_Rem 0.5984875455 -0.6746941 1.8716692 0.7808077
F_Ther_Enb-C_Proph_Ther_Rem 0.5981814242 -0.6750002 1.8713630 0.7812123
G_Ther_Cim-C_Proph_Ther_Rem 0.6375391061 -0.6356425 1.9107207 0.7267893
E_Ther_Hum-D_Ther_Rem 0.4234925909 -0.4414640 1.2884492 0.7469193
F_Ther_Enb-D_Ther_Rem 0.4231864697 -0.4417701 1.2881431 0.7475501
G_Ther_Cim-D_Ther_Rem 0.4625441515 -0.4024124 1.3275007 0.6623957
F_Ther_Enb-E_Ther_Hum -0.0003061212 -0.8652627 0.8646505 1.0000000
G_Ther_Cim-E_Ther_Hum 0.0390515606 -0.8259050 0.9040081 0.9999994
G_Ther_Cim-F_Ther_Enb 0.0393576818 -0.8255989 0.9043143 0.9999993
# Access all metrics from Tukey's post-hoc test for TG and WT conditions
$group["B_Tg-A_Wt", ] tukey
diff lwr upr p adj
0.3119808 -0.5015454 1.1255070 0.9023145
# Access the estimated difference in means between two different conditions
$group["B_Tg-A_Wt", 1] tukey
[1] 0.3119808
# Access the adjusted p-value for the test
$group["B_Tg-A_Wt", 4] tukey
[1] 0.9023145
<- c(tukey$group["B_Tg-A_Wt", 1], tukey$group["B_Tg-A_Wt", 4],
tukey_data $group["C_Proph_Ther_Rem-A_Wt", 1], tukey$group["C_Proph_Ther_Rem-A_Wt", 4],
tukey$group["D_Ther_Rem-A_Wt", 1], tukey$group["D_Ther_Rem-A_Wt", 4],
tukey$group["E_Ther_Hum-A_Wt", 1], tukey$group["E_Ther_Hum-A_Wt", 4],
tukey$group["F_Ther_Enb-A_Wt", 1], tukey$group["F_Ther_Enb-A_Wt", 4],
tukey$group["G_Ther_Cim-A_Wt", 1], tukey$group["G_Ther_Cim-A_Wt", 4])
tukey tukey_data
[1] 0.3119808 0.9023145 -0.3200114 0.9871894 -0.1450165 0.9985912
[7] 0.2784761 0.9558296 0.2781700 0.9560601 0.3175277 0.9192663
In summary, the Tukey’s HSD test results indicate that there is no statistically significant difference in the mean gene expression levels between the TG and WT conditions. The estimated difference is -0.03668, and the confidence interval (-0.40742 to 0.33406) includes zero. The adjusted p-value of 0.99993 is higher than the commonly used significance level (e.g., 0.05), suggesting that we do not have sufficient evidence to reject the null hypothesis of no difference between these two conditions.
Note: If zero is included in the confidence interval, it implies that the estimated effect or difference is not statistically significant at the chosen level of confidence. In other words, there is a level of uncertainty, and the data do not provide enough evidence to reject the null hypothesis of no effect or difference.
Below, we conducting Dunnett’s post-hoc test on the results of the ANOVA model for gene expression data. Dunnett’s test is a post-hoc test that compares each treatment group to a single control group, helping identify which treatment groups differ significantly from the control. In this context:
Hypotheses:
Null Hypothesis: The mean of the control group is equal to the means of all other groups.
Alternative Hypothesis: The mean of the control group is not equal to the means of one or more other groups.
Output:
The coefficients represent the estimated differences between the means of each treatment group and the control group.
The p-values indicate the statistical significance of each comparison.
The provided code allows you to examine the estimated differences and associated p-values for each group compared to the control in the context of Dunnett’s post-hoc test.
# Dunnett's post-hoc on the first (1st) gene
<- glht(gene_aov, linfct = mcp(group = "Dunnett"))
dunnett
<- summary(dunnett)
modgene modgene
Simultaneous Tests for General Linear Hypotheses
Multiple Comparisons of Means: Dunnett Contrasts
Fit: aov(formula = gene_expression ~ group, data = gene1)
Linear Hypotheses:
Estimate Std. Error t value Pr(>|t|)
B_Tg - A_Wt == 0 0.3120 0.2665 1.171 0.721
C_Proph_Ther_Rem - A_Wt == 0 -0.3200 0.4171 -0.767 0.940
D_Ther_Rem - A_Wt == 0 -0.1450 0.2834 -0.512 0.991
E_Ther_Hum - A_Wt == 0 0.2785 0.2834 0.983 0.841
F_Ther_Enb - A_Wt == 0 0.2782 0.2834 0.982 0.842
G_Ther_Cim - A_Wt == 0 0.3175 0.2834 1.121 0.755
(Adjusted p values reported -- single-step method)
10]]$coefficients modgene[[
B_Tg - A_Wt C_Proph_Ther_Rem - A_Wt D_Ther_Rem - A_Wt
0.3119808 -0.3200114 -0.1450165
E_Ther_Hum - A_Wt F_Ther_Enb - A_Wt G_Ther_Cim - A_Wt
0.2784761 0.2781700 0.3175277
10]]$pvalues modgene[[
[1] 0.7205765 0.9398139 0.9912297 0.8409861 0.8416245 0.7547572
attr(,"error")
[1] 0.0001767197
In the final step of statistical analysis, we perform analysis of variance and Tukey’s post hoc tests on all genes and we store them in a new dataframe. This analysis is similar to above, but repeated for the total number of genes.
# Apply ANOVA on all genes
# create empty dataframe
= data.frame()
anova_table
# recursive parse all genes
# try "length" or "len" [1] and insert matrix first column [2]
for( i in 1:length( matrixdata[ , 1 ] ) ) {
# create dataframe for each gene
# insert gene row data
= data.frame("gene_expression" = matrixdata[ i , ],
df "group" = group)
# apply ANOVA for gene i
# insert anova function [1] and gene i data [2] and groups [3]
= aov( gene_expression ~ group , data = df)
gene_aov
# apply tukey's post-hoc test on ANOVA results
# try "Tukey" or "TukeyHSD" [1] and insert anova output [2]
= TukeyHSD( gene_aov , conf.level = 0.99)
tukey
# vector calling Tukey's values
= c(tukey$group["B_Tg-A_Wt", 1],
tukey_data $group["B_Tg-A_Wt", 4],
tukey$group["C_Proph_Ther_Rem-A_Wt", 1],
tukey$group["C_Proph_Ther_Rem-A_Wt", 4],
tukey$group["D_Ther_Rem-A_Wt", 1],
tukey$group["D_Ther_Rem-A_Wt", 4],
tukey$group["E_Ther_Hum-A_Wt", 1],
tukey$group["E_Ther_Hum-A_Wt", 4],
tukey$group["F_Ther_Enb-A_Wt", 1],
tukey$group["F_Ther_Enb-A_Wt", 4],
tukey$group["G_Ther_Cim-A_Wt", 1],
tukey$group["G_Ther_Cim-A_Wt", 4],
tukey
$group["C_Proph_Ther_Rem-B_Tg", 1],
tukey$group["C_Proph_Ther_Rem-B_Tg", 4],
tukey$group["D_Ther_Rem-B_Tg", 1],
tukey$group["D_Ther_Rem-B_Tg", 4],
tukey$group["E_Ther_Hum-B_Tg", 1],
tukey$group["E_Ther_Hum-B_Tg", 4],
tukey$group["F_Ther_Enb-B_Tg", 1],
tukey$group["F_Ther_Enb-B_Tg", 4],
tukey$group["G_Ther_Cim-B_Tg", 1],
tukey$group["G_Ther_Cim-B_Tg", 4])
tukey
# append Tukey's data to dataframe
# try "rbind" or "cbind"
= rbind( anova_table , tukey_data)
anova_table
}
colnames(anova_table) <- c("Wt_Tg_diff", "Wt_Tg_padj",
"Wt_Rem_P_diff", "Wt_Rem_P_padj",
"Wt_Rem_diff", "Wt_Rem_padj",
"Wt_Hum_diff", "Wt_Hum_padj",
"Wt_Enb_diff", "Wt_Enb_padj",
"Wt_Cim_diff", "Wt_Cim_padj",
"Tg_Rem_P_diff", "Tg_Rem_P_padj",
"Tg_Rem_diff", "Tg_Rem_padj",
"Tg_Hum_diff", "Tg_Hum_padj",
"Tg_Enb_diff", "Tg_Enb_padj",
"Tg_Cim_diff", "Tg_Cim_padj")
# Add rownames with gene names
rownames(anova_table) = Gene
2.5 Volcano Plot
Volcano plots are graphical representations commonly used to visualize the results of statistical tests, particularly in the context of differential expression analysis. In a volcano plot, each data point represents a gene, with the x-axis indicating the effect size (log-fold change or difference between two conditions) and the y-axis representing the statistical significance (p-value) of the difference between experimental conditions. Genes that exhibit substantial changes and high statistical significance appear as points located towards the extremes of the plot, resembling the shape of a volcano. This visualization helps to identify and prioritize genes that are most relevant to the conditions being compared, making it a powerful tool for exploring and interpreting high-throughput data.
# Volcano plot preparation
# set variable to "0"
= 0
upWT = 0
downWT = 0
nochangeWT
# Filter Differential Expressed Genes
# insert dataframe column id [1] , try "&" or "|" [2]
# and insert dataframe column id [3]
= which(anova_table[ , 1 ] < -1.0 & anova_table[ , 2 ] < 0.05)
upWT
# insert dataframe column id [1] , try "&" or "|" [2]
# and insert dataframe column id [3]
= which(anova_table[ , 1 ] > 1.0 & anova_table[ , 2 ] < 0.05)
downWT
# try ">" or "<" [1] , try "&" or "|" [2] and try "&" or "|" [3]
= which(anova_table[ , 2 ] > 0.05 |
nochangeWT # try "<" or ">" [1] , try "&" or "|" [2] , try "<" or ">" [3]
1 ] > -1.0 & anova_table[ , 1 ] < 1.0 ) )
(anova_table[ ,
# Create vector to store states for each gene
<- vector(mode="character", length=length(anova_table[,1]))
state <- "up_WT"
state[upWT] <- "down_WT"
state[downWT] <- "nochange_WT"
state[nochangeWT]
# Identify names of genes differentially expressed between wt and tg
<- c(rownames(anova_table)[upWT])
genes_up_WT <- c(rownames(anova_table)[downWT])
genes_down_WT
# Union of DEGs between wt and tg
<- c(genes_up_WT, genes_down_WT)
deg_wt_tg
# Subset dataframe based on specific degs
<- subset( genes_data , Gene %in% deg_wt_tg)
deg_wt_tg_df
## Dataframe for volcano plot
<- data.frame("padj" = anova_table[,2],
volcano_data "DisWt" = anova_table[,1],
state=state)
# Volcano plot
# insert data [1] , insert variables [2]-[3] and insert color group [4]
ggplot( volcano_data , aes(x = DisWt , y = -log10(padj) , colour = state )) +
geom_point() +
labs(x = "mean(Difference)",
y = "-log10(p-value)",
title = "Volcano Plot",
subtitle = "Differentially Expressed Genes (WT vs TG)") +
# insert line to show cutoff
# try "-2" or "-1" [1] and try "2" or "1" [2]
geom_vline(xintercept = c( -1 , 1 ),
linetype = "dashed",
color = "black") +
# insert line to show cutoff
geom_hline(yintercept = -log10(0.05),
linetype = "dashed",
color = "black")
2.6 Principal Components Analysis (PCA) & Uniform Manifold Approximation and Projection (UMAP) after identifying Differential Expressed Genes
First subset the original genes data based on the Differential Expressed Genes
# Subset dataframe based on specific degs
= subset( genes_data , Gene %in% deg_wt_tg)
deg_wt_tg_df
= deg_wt_tg_df[,1:23]
deg_wt_tg_df
# After dataframe transposition columns must represent genes
= t(deg_wt_tg_df) deg_wt_tg_df
# UMAP dimension reduction for wt and tg samples
= umap(deg_wt_tg_df, n_components=2, random_state=15)
deg_wt_tg_df.umap
# Keep the numeric dimensions
= deg_wt_tg_df.umap[["layout"]]
deg_wt_tg_df.umap
# Create vector with groups
= c(rep("A_Wt", 10), rep("B_Tg", 13) )
group
# Create final dataframe with dimensions and group for plotting
= cbind(deg_wt_tg_df.umap, group)
deg_wt_tg_df.umap = data.frame(deg_wt_tg_df.umap)
deg_wt_tg_df.umap
# Plot UMAP results
ggplotly(
ggplot(deg_wt_tg_df.umap, aes(x = V1, y = V2, color = group)) +
geom_point() +
labs(x = "UMAP1", y = "UMAP2",
title = "UMAP plot",
subtitle = "A UMAP Visualization of WT and TG samples (DEGs subset)") +
theme(axis.text.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks = element_blank())
)
# group wt and tg as character and not factor
= c(rep("A_Wt", 10), rep("B_Tg", 13) )
group
# dimension reduction with PCA for wt and tg dataframe
= prcomp(deg_wt_tg_df , scale. = FALSE)
deg_wt_tg_df.pca
= data.frame("PC1" = deg_wt_tg_df.pca$x[,1] ,
deg_wt_tg_df.pca "PC2" = deg_wt_tg_df.pca$x[,2] ,
"group" = group)
# plot PCA results
ggplotly(
ggplot(deg_wt_tg_df.pca , aes(x=PC1,y=PC2,color=group))+
geom_point()+
labs(x = "PC1", y = "PC2",
title = "PCA plot",
subtitle = "A PCA Visualization of WT and TG samples (DEGs subset)") +
theme(axis.text.x = element_blank(),
axis.text.y = element_blank(),
axis.ticks = element_blank())
)
We now identify Differential Expressed Genes between transgenic animals and at least one therapy
# Volcano plot dataframe preparation for DEGs from TG vs therapies
= 0
upTHER = 0
downTHER = 0
nochangeTHER
# Filter genes based on mean diff and p_value between TG and therapies
= which((anova_table[,13] < -1.0 & anova_table[,14] < 0.05) |
upTHER 15] < -1.0 & anova_table[,16] < 0.05) |
(anova_table[,17] < -1.0 & anova_table[,18] < 0.05) |
(anova_table[,19] < -1.0 & anova_table[,20] < 0.05) |
(anova_table[,21] < -1.0 & anova_table[,22] < 0.05) )
(anova_table[,
= which((anova_table[,13] > 1.0 & anova_table[,14] < 0.05) |
downTHER 15] > 1.0 & anova_table[,16] < 0.05) |
(anova_table[,17] > 1.0 & anova_table[,18] < 0.05) |
(anova_table[,19] > 1.0 & anova_table[,20] < 0.05) |
(anova_table[,21] > 1.0 & anova_table[,22] < 0.05) )
(anova_table[,
= which( ( (anova_table[,13] > -1.0 & anova_table[,13] < 1.0) |
nochangeTHER 14] > 0.05) |
anova_table[,
15] > -1.0 & anova_table[,15] < 1.0) |
( (anova_table[,16] > 0.05) |
anova_table[,
17] > -1.0 & anova_table[,17] < 1.0) |
( (anova_table[,18] > 0.05) |
anova_table[,
19] > -1.0 & anova_table[,19] < 1.0) |
( (anova_table[,20] > 0.05) |
anova_table[,
21] > -1.0 & anova_table[,21] < 1.0) |
( (anova_table[,22] > 0.05) )
anova_table[,
# Create vector to store states for each gene
= vector(mode = "character", length = length(anova_table[,1]))
state = "up_THER"
state[upTHER] = "down_THER"
state[downTHER] = "nochange_THER"
state[nochangeTHER]
# Identify names of genes differentially expressed between tg and therapies
= c(rownames(anova_table)[upTHER])
genes_up_THER = c(rownames(anova_table)[downTHER])
genes_down_THER
= c(genes_up_THER, genes_down_THER)
deg_tg_ther
# Combine DEGs from TG and ther
= c(deg_tg_ther, deg_wt_tg)
DEGs
# Data frame with all DEGs for clustering
= anova_table[rownames(anova_table) %in% DEGs, ]
DEGsFrame = as.matrix(DEGsFrame) DEGsFrame
2.7 Hierarchical Clustering
The code performs k-means clustering on a gene expression dataset (DEGsFrame) to partition genes into six distinct clusters based on their expression profiles. After clustering, it extracts genes belonging to each cluster and presents them in a tabular format. This analysis provides insights into the underlying patterns and relationships within the gene expression data, facilitating the identification of co-expressed genes and potential regulatory networks.
# k-means clustering
# ------------------
= kmeans(DEGsFrame[, c(1,3,5,7,9,11) ], centers = 6)
kmeans ggplotly(fviz_cluster(kmeans, data = (DEGsFrame[, c(1,3,5,7,9,11)]), geom = "point", show.clust.cent = TRUE))
# Extract genes from clusters
= data.frame(kmeans$cluster)
clusters colnames(clusters) = ("ClusterNo")
# Extract specific cluster
= rownames(subset(clusters, ClusterNo==1))
cluster1
# Output data as table (group by cluster number)
kable(clusters, col.names="Cluster Number",
caption ="Clusters and associated genes.") |>
kable_styling(font_size = 16) |>
scroll_box(height = "400px")
Cluster Number | |
---|---|
Abca5 | 1 |
Abca6 | 2 |
Abca8a | 2 |
Abca8b | 2 |
Abcb4 | 5 |
Abhd14b | 1 |
Ablim1 | 1 |
Abra | 4 |
Acaca | 1 |
Acacb | 5 |
Acan | 5 |
Ache | 4 |
Acp2 | 6 |
Acp5 | 3 |
Acpp | 3 |
Acsl6 | 5 |
Acss3 | 1 |
Acta1 | 5 |
Actc1 | 5 |
Actg2 | 1 |
Actn2 | 4 |
Actn3 | 5 |
Acvr1c | 2 |
Acvr2a | 1 |
Acyp2 | 4 |
Adam8 | 3 |
Adamts13 | 6 |
Adamts15 | 6 |
Adamts4 | 3 |
Adamts5 | 1 |
Adamts7 | 6 |
Adcy5 | 1 |
Adig | 2 |
Adipoq | 2 |
Adk | 1 |
Adprhl1 | 4 |
Adrbk2 | 3 |
Aff2 | 5 |
Agbl1 | 4 |
Agpat9 | 1 |
Aif1 | 6 |
Aim1 | 3 |
Akna | 6 |
Akt2 | 1 |
Alas2 | 5 |
Alcam | 3 |
Aldh1a1 | 5 |
Aldh1a3 | 2 |
Aldh1a7 | 1 |
Aldh3a1 | 1 |
Aldh6a1 | 2 |
Aldob | 6 |
Aldoc | 3 |
Alg3 | 6 |
Alox12 | 5 |
Alpk3 | 4 |
Amacr | 6 |
Amot | 4 |
Ampd1 | 4 |
Amy1 | 2 |
Angptl4 | 6 |
Angptl7 | 5 |
Ank2 | 1 |
Ank3 | 5 |
Ankrd1 | 4 |
Ankrd2 | 4 |
Ankrd23 | 4 |
Ankrd55 | 6 |
Ano5 | 5 |
Anpep | 6 |
Anxa8 | 1 |
Aoah | 3 |
Aox1 | 5 |
Aox3 | 1 |
Ap4s1 | 1 |
Apbb1ip | 6 |
Apobec1 | 3 |
Apobec2 | 4 |
Apobec3 | 6 |
Aprt | 6 |
Aqp7 | 5 |
Ar | 4 |
Arg1 | 3 |
Arg2 | 6 |
Arhgap19 | 1 |
Arhgap20 | 4 |
Arhgap28 | 1 |
Arhgap30 | 3 |
Arhgap4 | 6 |
Arhgef10 | 1 |
Arhgef9 | 5 |
Arid3c | 6 |
Arpc1b | 6 |
Arpc2 | 6 |
Arpc3 | 6 |
Arrdc4 | 6 |
Art3 | 5 |
Asb11 | 4 |
Asb12 | 2 |
Asb14 | 4 |
Asb15 | 4 |
Asb2 | 5 |
Asb5 | 4 |
Asf1b | 6 |
Aspa | 5 |
Aspm | 6 |
Asrgl1 | 1 |
Atf3 | 6 |
Atn1 | 6 |
Atp1a2 | 5 |
Atp1a3 | 6 |
Atp1b1 | 4 |
Atp1b2 | 4 |
Atp1b4 | 4 |
Atp2a1 | 5 |
Atp6v0a4 | 1 |
Atp6v0d2 | 3 |
Atp6v1a | 6 |
Atp6v1b1 | 6 |
Atp8b4 | 3 |
Atp9a | 5 |
Atpbd4 | 6 |
Aurkb | 6 |
B3galt2 | 2 |
B3gnt5 | 6 |
B4galnt1 | 6 |
B4galt5 | 6 |
B4galt6 | 6 |
Baiap2 | 3 |
Bak1 | 6 |
Bank1 | 6 |
Basp1 | 6 |
Bax | 3 |
Bbox1 | 5 |
Bccip | 1 |
Bche | 2 |
Bcl10 | 6 |
Bcl11b | 6 |
Bcl2a1a | 6 |
Bcl2a1b | 6 |
Bcl2a1d | 6 |
Bcl2l1 | 1 |
Bcl3 | 3 |
Bdh2 | 1 |
Bdkrb1 | 3 |
Bend4 | 6 |
Best3 | 4 |
Bid | 6 |
Bin1 | 5 |
Birc3 | 3 |
Blk | 6 |
Blnk | 6 |
Blvrb | 6 |
Bmper | 1 |
Bod1 | 2 |
Brms1l | 1 |
Bst1 | 3 |
Btg1 | 1 |
Btg2 | 6 |
Btk | 3 |
Btla | 6 |
Bub1 | 6 |
Bub1b | 3 |
Bves | 4 |
C1qb | 6 |
C1qtnf3 | 3 |
C1rl | 6 |
C3 | 3 |
C4a | 1 |
C4b | 1 |
C7 | 2 |
C77370 | 1 |
C87977 | 1 |
Cacna1i | 6 |
Cacna1s | 4 |
Cacna2d1 | 5 |
Cacnb1 | 4 |
Cacng1 | 5 |
Cadm3 | 5 |
Calcr | 6 |
Camk2a | 6 |
Camk2b | 5 |
Camkk1 | 5 |
Cand2 | 4 |
Cap2 | 5 |
Capn3 | 5 |
Capn6 | 6 |
Car12 | 3 |
Car3 | 2 |
Car5b | 1 |
Car8 | 2 |
Casc5 | 6 |
Casp1 | 3 |
Casp4 | 3 |
Casp7 | 6 |
Casp8 | 6 |
Casq1 | 4 |
Casq2 | 5 |
Casr | 1 |
Cav3 | 5 |
Cbr2 | 5 |
Ccbp2 | 1 |
Ccdc23 | 6 |
Ccdc3 | 5 |
Ccdc62 | 1 |
Ccdc67 | 6 |
Ccl11 | 4 |
Ccl17 | 3 |
Ccl19 | 3 |
Ccl2 | 3 |
Ccl20 | 6 |
Ccl21a | 3 |
Ccl22 | 3 |
Ccl24 | 5 |
Ccl28 | 6 |
Ccl3 | 6 |
Ccl5 | 3 |
Ccl7 | 3 |
Ccl8 | 6 |
Ccl9 | 3 |
Ccna2 | 6 |
Ccnb1 | 3 |
Ccnb2 | 6 |
Ccnd1 | 6 |
Ccne2 | 6 |
Ccr2 | 3 |
Ccr3 | 6 |
Ccr6 | 6 |
Ccr7 | 6 |
Ccr8 | 6 |
Ccrl2 | 6 |
Cd101 | 6 |
Cd14 | 3 |
Cd163 | 1 |
Cd177 | 1 |
Cd19 | 6 |
Cd22 | 6 |
Cd248 | 5 |
Cd27 | 6 |
Cd274 | 6 |
Cd300lb | 6 |
Cd33 | 6 |
Cd37 | 3 |
Cd38 | 6 |
Cd3d | 6 |
Cd3e | 6 |
Cd3g | 3 |
Cd4 | 3 |
Cd44 | 3 |
Cd46 | 1 |
Cd48 | 6 |
Cd5 | 6 |
Cd52 | 3 |
Cd53 | 3 |
Cd55 | 5 |
Cd59a | 4 |
Cd63 | 6 |
Cd68 | 3 |
Cd69 | 6 |
Cd72 | 3 |
Cd74 | 3 |
Cd79a | 3 |
Cd79b | 6 |
Cd80 | 3 |
Cd84 | 3 |
Cdadc1 | 1 |
Cdc25c | 6 |
Cdh19 | 2 |
Cdh22 | 6 |
Cdh5 | 6 |
Cdhr1 | 6 |
Cdk18 | 6 |
Cdk2ap2 | 6 |
Cdk6 | 3 |
Cdkl1 | 6 |
Cdkn1c | 1 |
Cdo1 | 1 |
Cdon | 5 |
Ceacam1 | 3 |
Ceacam16 | 6 |
Ceacam19 | 3 |
Ceacam2 | 6 |
Cenpe | 3 |
Cenpf | 6 |
Cenpm | 6 |
Cenpn | 6 |
Cep55 | 6 |
Cetn4 | 1 |
Cfb | 3 |
Cfd | 1 |
Cfp | 6 |
Ch25h | 1 |
Chad | 2 |
Chd2 | 1 |
Chi3l1 | 3 |
Chl1 | 3 |
Chodl | 2 |
Chpt1 | 5 |
Chrna1 | 4 |
Chrnb1 | 4 |
Chst2 | 5 |
Cidec | 5 |
Ciita | 3 |
Cilp | 1 |
Cilp2 | 5 |
Cirbp | 1 |
Ckap2 | 6 |
Ckap2l | 6 |
Ckb | 6 |
Ckmt2 | 4 |
Clcn1 | 4 |
Cldn20 | 1 |
Clec12a | 3 |
Clec2d | 6 |
Clec3a | 2 |
Clec3b | 4 |
Clec4a1 | 3 |
Clec4a2 | 3 |
Clec4a3 | 3 |
Clec4d | 3 |
Clec4e | 3 |
Clec4n | 3 |
Clec5a | 3 |
Clec7a | 3 |
Clic5 | 2 |
Cln5 | 6 |
Cln6 | 6 |
Clnk | 6 |
Clu | 1 |
Cmbl | 2 |
Cmya5 | 5 |
Cnksr1 | 4 |
Cnn2 | 6 |
Cnn3 | 6 |
Cnr2 | 6 |
Cobll1 | 1 |
Coch | 4 |
Col10a1 | 2 |
Col12a1 | 3 |
Col22a1 | 1 |
Col28a1 | 1 |
Comp | 5 |
Coro1a | 6 |
Coro2a | 6 |
Coro6 | 4 |
Cotl1 | 6 |
Cox6a2 | 4 |
Cox7a1 | 4 |
Cox8a | 6 |
Cox8b | 4 |
Cpa3 | 4 |
Cpa6 | 6 |
Cpe | 1 |
Cpeb3 | 5 |
Cpm | 2 |
Cpne8 | 1 |
Cpxm1 | 3 |
Cr2 | 6 |
Crb3 | 6 |
Creb5 | 4 |
Crebl2 | 1 |
Creg1 | 6 |
Crispld1 | 2 |
Cry2 | 5 |
Cryaa | 6 |
Cryab | 2 |
Cryba2 | 6 |
Csf1r | 6 |
Csf2ra | 3 |
Csf2rb | 3 |
Csf2rb2 | 3 |
Csf3r | 6 |
Csgalnact2 | 1 |
Csmd1 | 3 |
Csrp3 | 4 |
Cst7 | 6 |
Cstb | 6 |
Cth | 1 |
Cthrc1 | 3 |
Ctla2b | 6 |
Ctnnal1 | 5 |
Cts3 | 1 |
Ctsc | 6 |
Ctsk | 3 |
Ctss | 3 |
Ctsz | 3 |
Cttnbp2 | 1 |
Ctxn1 | 6 |
Ctxn3 | 5 |
Cubn | 6 |
Cx3cl1 | 3 |
Cx3cr1 | 1 |
Cxcl1 | 3 |
Cxcl10 | 6 |
Cxcl13 | 3 |
Cxcl16 | 3 |
Cxcl2 | 3 |
Cxcl3 | 3 |
Cxcl5 | 3 |
Cxcl9 | 6 |
Cxcr2 | 6 |
Cxcr4 | 3 |
Cyba | 6 |
Cybb | 3 |
Cyp2e1 | 2 |
Cyp2f2 | 2 |
Cyp2s1 | 3 |
Cyp3a13 | 1 |
Cyp4f18 | 6 |
Cyp4v3 | 3 |
Cyp7b1 | 3 |
Cypt4 | 6 |
Cyth4 | 3 |
Cytip | 3 |
Cytl1 | 2 |
Daam2 | 5 |
Dad1 | 6 |
Dapp1 | 6 |
Dcbld2 | 1 |
Ddit4l | 2 |
Ddrgk1 | 1 |
Ddx60 | 1 |
Des | 4 |
Dgat2 | 5 |
Dgkb | 5 |
Dhrs7c | 5 |
Diap3 | 3 |
Dixdc1 | 1 |
Dkk2 | 5 |
Dmd | 5 |
Dmp1 | 3 |
Dmpk | 5 |
Dmxl2 | 3 |
Dna2 | 6 |
Dnaja4 | 5 |
Dnajc21 | 1 |
Dnajc22 | 6 |
Dock10 | 3 |
Dock2 | 3 |
Dock5 | 3 |
Dok3 | 3 |
Dok6 | 6 |
Dpep2 | 3 |
Dpf3 | 6 |
Dpm1 | 1 |
Dram1 | 3 |
Drp2 | 5 |
Dsg1b | 6 |
Dsg2 | 6 |
Dstyk | 1 |
Dtl | 6 |
Dtna | 4 |
Dtx3l | 6 |
Dusp10 | 4 |
Dusp13 | 4 |
Dusp14 | 5 |
Dusp27 | 4 |
Dusp5 | 6 |
Dync2h1 | 1 |
E2f1 | 6 |
E2f4 | 6 |
E2f8 | 6 |
Ear2 | 6 |
Ebf2 | 5 |
Ebi3 | 6 |
Ebna1bp2 | 1 |
Ecscr | 3 |
Ect2 | 3 |
Eda2r | 5 |
Edil3 | 3 |
Ednrb | 5 |
Eef1a2 | 5 |
Efcab2 | 5 |
Efha2 | 1 |
Efhd1 | 2 |
Efhd2 | 3 |
Egf | 1 |
Egln3 | 4 |
Egr2 | 6 |
Ehbp1 | 1 |
Ehd4 | 1 |
Eif3k | 6 |
Eln | 1 |
Eme1 | 6 |
Emilin1 | 3 |
Emr1 | 3 |
Emr4 | 3 |
Emx2 | 6 |
Eng | 6 |
Eno3 | 5 |
Enpep | 5 |
Entpd7 | 6 |
Epb4.1l4a | 4 |
Epb4.1l4b | 1 |
Epha3 | 6 |
Epm2a | 4 |
Eps8l2 | 1 |
Epsti1 | 6 |
Espl1 | 6 |
Etv6 | 6 |
Evc | 1 |
Evi2a | 6 |
Evi5 | 1 |
Exo1 | 6 |
Exosc1 | 6 |
Ext1 | 3 |
Eya4 | 5 |
F10 | 3 |
F13a1 | 1 |
F2r | 6 |
F2rl1 | 6 |
F2rl2 | 6 |
F7 | 3 |
Fabp4 | 5 |
Fabp7 | 3 |
Fabp9 | 1 |
Fads3 | 6 |
Faim3 | 6 |
Fam105a | 3 |
Fam108c | 6 |
Fam114a2 | 1 |
Fam124b | 6 |
Fam126a | 1 |
Fam126b | 1 |
Fam129a | 1 |
Fam13a | 5 |
Fam160a1 | 5 |
Fam35a | 1 |
Fam64a | 6 |
Fam83f | 6 |
Fancc | 1 |
Fas | 3 |
Fasn | 5 |
Fbl | 6 |
Fbn2 | 1 |
Fbp2 | 6 |
Fbxo30 | 1 |
Fbxo40 | 4 |
Fcer1g | 3 |
Fcer2a | 6 |
Fcf1 | 1 |
Fcgr2b | 3 |
Fcgr3 | 3 |
Fcgr4 | 6 |
Fcrl1 | 6 |
Fcrla | 6 |
Fcrlb | 6 |
Fermt2 | 2 |
Fermt3 | 3 |
Fez1 | 5 |
Fgf13 | 5 |
Fgf2 | 2 |
Fgf23 | 6 |
Fgf9 | 2 |
Fgfr3 | 1 |
Fgl2 | 2 |
Fgr | 3 |
Fhl1 | 2 |
Fhl3 | 4 |
Fhod3 | 4 |
Figf | 1 |
Filip1 | 5 |
Fitm1 | 4 |
Fkbp2 | 1 |
Flnc | 4 |
Flt3 | 3 |
Fmnl1 | 6 |
Fmo2 | 5 |
Fndc5 | 4 |
Folr2 | 4 |
Fos | 6 |
Fosl2 | 6 |
Foxp3 | 6 |
Fpr1 | 6 |
Fras1 | 4 |
Frmd3 | 2 |
Frmd7 | 2 |
Frrs1 | 3 |
Frzb | 2 |
Fscn1 | 3 |
Fsd1l | 2 |
Fsd2 | 5 |
Fv1 | 1 |
Fxyd1 | 4 |
Fxyd2 | 6 |
Fyb | 3 |
Fyco1 | 4 |
G0s2 | 1 |
Gabra4 | 1 |
Gabrb3 | 6 |
Galnt6 | 3 |
Galntl2 | 2 |
Gbe1 | 2 |
Gbgt1 | 3 |
Gbp2 | 3 |
Gbp5 | 6 |
Gclm | 6 |
Gdap1 | 4 |
Gdf10 | 2 |
Gdpd1 | 6 |
Gfpt2 | 2 |
Gfra2 | 6 |
Gimap4 | 1 |
Gimap5 | 6 |
Gjb3 | 3 |
Gjc3 | 5 |
Gk5 | 1 |
Gla | 3 |
Glb1l2 | 2 |
Gldn | 2 |
Gli1 | 1 |
Glrx | 6 |
Gls | 1 |
Glt25d2 | 2 |
Glt28d2 | 5 |
Glycam1 | 6 |
Gm10228 | 3 |
Gm10229 | 3 |
Gm11559 | 6 |
Gm14492 | 4 |
Gm1679 | 6 |
Gm2a | 6 |
Gm3893 | 1 |
Gm4792 | 6 |
Gm5150 | 3 |
Gm527 | 1 |
Gm5465 | 6 |
Gm5563 | 6 |
Gm6026 | 6 |
Gm614 | 3 |
Gm7609 | 3 |
Gm885 | 3 |
Gm889 | 5 |
Gm9733 | 6 |
Gm9766 | 5 |
Gmpr | 4 |
Gna15 | 6 |
Gnai1 | 2 |
Gngt2 | 6 |
Gnpnat1 | 2 |
Gnptab | 3 |
Gp49a | 3 |
Gpam | 5 |
Gpc3 | 2 |
Gpc4 | 1 |
Gpd1 | 2 |
Gphb5 | 6 |
Gpr1 | 2 |
Gpr114 | 6 |
Gpr132 | 3 |
Gpr137b | 3 |
Gpr141 | 6 |
Gpr161 | 1 |
Gpr162 | 6 |
Gpr165 | 2 |
Gpr176 | 3 |
Gpr18 | 6 |
Gpr35 | 6 |
Gpr64 | 5 |
Gpr65 | 3 |
Gpr68 | 6 |
Gpr84 | 3 |
Gpr97 | 6 |
Gprc5a | 5 |
Gpt2 | 4 |
Grap2 | 6 |
Grb14 | 2 |
Gria2 | 1 |
Grid2 | 2 |
Grina | 6 |
Gsn | 5 |
Gsta3 | 1 |
Gsta4 | 2 |
Gstk1 | 4 |
Gusb | 3 |
Gxylt2 | 3 |
Gyg | 4 |
Gypa | 6 |
Gys1 | 4 |
Gzmc | 6 |
H19 | 5 |
Hacl1 | 1 |
Hal | 6 |
Hapln1 | 1 |
Has1 | 1 |
Has2 | 2 |
Havcr2 | 3 |
Hbegf | 2 |
Hck | 3 |
Hcls1 | 3 |
Hcn1 | 1 |
Hectd2 | 5 |
Hemgn | 6 |
Hexa | 6 |
Hfe2 | 4 |
Hhatl | 4 |
Hhip | 2 |
Hibch | 1 |
Higd1a | 1 |
Hist1h2ab | 3 |
Hist1h2bb | 6 |
Hist2h2bb | 6 |
Hmcn1 | 3 |
Hmgb2 | 1 |
Hmha1 | 6 |
Hmox1 | 3 |
Hn1 | 6 |
Hn1l | 6 |
Hnrnpm | 1 |
Homer2 | 5 |
Hoxa11 | 1 |
Hoxa13 | 4 |
Hoxc10 | 5 |
Hoxd13 | 4 |
Hp | 3 |
Hpse2 | 4 |
Hrc | 5 |
Hspa12a | 1 |
Hspb1 | 5 |
Hspb3 | 4 |
Hspb6 | 4 |
Hspb7 | 4 |
Hspb8 | 5 |
Htatsf1 | 1 |
Htra2 | 6 |
Htra4 | 2 |
Hvcn1 | 3 |
Icam1 | 3 |
Id4 | 1 |
Idua | 6 |
Ifi205 | 6 |
Ifi27l2a | 5 |
Ifi30 | 3 |
Ifitm3 | 6 |
Ifitm6 | 1 |
Ifnar1 | 3 |
Ifnar2 | 6 |
Ifngr2 | 6 |
Igf2 | 5 |
Igfbp3 | 6 |
Igfbp6 | 5 |
Igfbp7 | 6 |
Igj | 6 |
Igsf10 | 3 |
Igsf6 | 3 |
Ikbke | 3 |
Ikzf3 | 6 |
Ikzf5 | 1 |
Il10ra | 3 |
Il12rb2 | 6 |
Il13ra1 | 3 |
Il16 | 1 |
Il1a | 3 |
Il1b | 3 |
Il1f9 | 6 |
Il1rn | 3 |
Il20ra | 6 |
Il23r | 6 |
Il28ra | 6 |
Il2ra | 6 |
Il2rg | 3 |
Il6 | 3 |
Il7r | 3 |
Inmt | 2 |
Insig2 | 1 |
Insl6 | 6 |
Ipp | 1 |
Iqgap3 | 6 |
Irak2 | 6 |
Irg1 | 3 |
Itga2 | 6 |
Itga4 | 3 |
Itga5 | 3 |
Itga6 | 1 |
Itga7 | 2 |
Itga8 | 5 |
Itgae | 6 |
Itgal | 3 |
Itgam | 3 |
Itgax | 3 |
Itgb1bp2 | 4 |
Itgb2 | 3 |
Itgb3 | 3 |
Itgb6 | 5 |
Itgb8 | 1 |
Itih2 | 5 |
Itih5 | 1 |
Jdp2 | 3 |
Jph1 | 4 |
Jph2 | 5 |
Jup | 4 |
Kank1 | 1 |
Kbtbd10 | 5 |
Kbtbd5 | 4 |
Kcna1 | 4 |
Kcna3 | 3 |
Kcna6 | 1 |
Kcnc1 | 4 |
Kcnc2 | 2 |
Kcne1 | 6 |
Kcng3 | 6 |
Kcnj2 | 5 |
Kcnn4 | 3 |
Kcnq5 | 2 |
Kcnt2 | 2 |
Kctd2 | 1 |
Kdm5a | 1 |
Kif11 | 6 |
Kif13b | 1 |
Kif1b | 1 |
Kif20a | 3 |
Kif21a | 5 |
Kif26b | 6 |
Klf12 | 5 |
Klf4 | 6 |
Klhl13 | 2 |
Klhl31 | 4 |
Klra17 | 6 |
Klra2 | 6 |
Klrb1f | 6 |
Klrc1 | 6 |
Klrd1 | 6 |
Kmo | 6 |
Kng2 | 3 |
Krt31 | 6 |
Krt6a | 6 |
Krtap1-5 | 3 |
Krtap3-2 | 6 |
Krtap4-1 | 6 |
Krtdap | 4 |
Ky | 5 |
Kynu | 6 |
Lair1 | 3 |
Lama2 | 2 |
Lamb2 | 1 |
Lass6 | 3 |
Lat2 | 3 |
Layn | 6 |
Lcp1 | 3 |
Lcp2 | 3 |
Ldb3 | 4 |
Lef1 | 6 |
Lep | 5 |
Lgals12 | 5 |
Lgi1 | 2 |
Lgi4 | 1 |
Lif | 3 |
Lilra6 | 3 |
Lilrb3 | 6 |
Lilrb4 | 3 |
Limch1 | 5 |
Lims2 | 5 |
Lipa | 3 |
Lipn | 3 |
Lmcd1 | 4 |
Lmo2 | 1 |
Lmod2 | 4 |
Lmod3 | 4 |
Lpar1 | 1 |
Lpcat2 | 3 |
Lpin1 | 4 |
Lpl | 2 |
Lrdd | 6 |
Lrrc15 | 3 |
Lrrc2 | 4 |
Lrrc25 | 6 |
Lrrc39 | 5 |
Lrrc55 | 6 |
Lrrc61 | 6 |
Lrrn1 | 4 |
Lrrn4cl | 4 |
Lrtm1 | 5 |
Ltb | 3 |
Ltbp2 | 3 |
Luc7l3 | 1 |
Lxn | 3 |
Ly6g5c | 6 |
Ly6i | 1 |
Ly86 | 3 |
Ly9 | 3 |
Ly96 | 6 |
Lyn | 6 |
Lynx1 | 4 |
Lyve1 | 5 |
Lyz1 | 3 |
Lyz2 | 3 |
Maff | 6 |
Mageh1 | 1 |
Malt1 | 3 |
Mamdc2 | 1 |
Manea | 6 |
Map1lc3a | 5 |
Map4k1 | 6 |
Mapk11 | 6 |
Mapk12 | 5 |
Mapk3 | 6 |
Mapkapk3 | 6 |
Mapt | 4 |
Marcksl1 | 1 |
Marco | 3 |
Matn2 | 1 |
Mb | 4 |
Mccc1 | 1 |
Mcm5 | 6 |
Mcoln2 | 3 |
Mcpt4 | 2 |
Mdga2 | 2 |
Med29 | 6 |
Mef2c | 2 |
Mefv | 3 |
Meg3 | 2 |
Megf10 | 1 |
Meox1 | 6 |
Mfap4 | 6 |
Mfi2 | 2 |
Mfn2 | 5 |
Mfsd4 | 6 |
Mgll | 5 |
Mgst3 | 4 |
Micall2 | 6 |
Mif | 6 |
Mir100 | 1 |
Mir125b-1 | 1 |
Mir133a-1 | 4 |
Mir133a-2 | 4 |
Mir133b | 2 |
Mir142 | 3 |
Mir194-2 | 1 |
Mir23b | 1 |
Mir29b-2 | 1 |
Mir300 | 1 |
Mir376b | 1 |
Mir380 | 1 |
Mir382 | 1 |
Mir487b | 1 |
Mir543 | 1 |
Mirlet7a-2 | 1 |
Mirlet7c-1 | 2 |
Mirlet7c-2 | 1 |
Mki67 | 3 |
Mlf1 | 4 |
Mlxip | 6 |
Mlxipl | 4 |
Mme | 6 |
Mmp12 | 3 |
Mmp13 | 3 |
Mmp14 | 3 |
Mmp19 | 3 |
Mmp25 | 6 |
Mmp3 | 3 |
Mmp9 | 3 |
Mn1 | 5 |
Mobp | 6 |
Mocs1 | 6 |
Mpdz | 1 |
Mpeg1 | 3 |
Mpp3 | 5 |
Mpp7 | 1 |
Mpz | 5 |
Mpzl3 | 3 |
Mreg | 4 |
Mrgprb1 | 2 |
Mrgprb2 | 5 |
Mrpl22 | 6 |
Mrpl34 | 6 |
Mrpl54 | 6 |
Mrps24 | 6 |
Ms4a1 | 6 |
Ms4a14 | 3 |
Ms4a6d | 3 |
Ms4a7 | 3 |
Msc | 6 |
Msr1 | 3 |
Mstn | 4 |
Mt2 | 6 |
Mtap1b | 5 |
Mtmr11 | 1 |
Murc | 5 |
Musk | 4 |
Mustn1 | 4 |
Myadml2 | 5 |
Mybpc1 | 5 |
Mybpc2 | 4 |
Mybph | 4 |
Myc | 6 |
Myf6 | 4 |
Myh1 | 5 |
Myh10 | 2 |
Myh11 | 1 |
Myh2 | 5 |
Myh3 | 5 |
Myh4 | 5 |
Myh7 | 4 |
Myh8 | 1 |
Myl1 | 4 |
Myl2 | 2 |
Myl3 | 4 |
Myl6b | 4 |
Mylk2 | 4 |
Mylk4 | 2 |
Mylpf | 5 |
Myo18b | 5 |
Myo1f | 3 |
Myom1 | 5 |
Myom2 | 5 |
Myom3 | 5 |
Myot | 4 |
Myoz1 | 4 |
Myoz2 | 4 |
Myoz3 | 2 |
Mypn | 4 |
N4bp1 | 6 |
Nagpa | 6 |
Naip2 | 3 |
Naip5 | 3 |
Naip6 | 3 |
Napsa | 3 |
Nat14 | 1 |
Ncf1 | 3 |
Ncf2 | 3 |
Ncf4 | 3 |
Nckap1l | 3 |
Ncr1 | 6 |
Ndc80 | 3 |
Ndrg2 | 5 |
Ndufb9 | 6 |
Ndufs8 | 4 |
Neb | 5 |
Necab1 | 2 |
Neil3 | 6 |
Nes | 5 |
Neurl3 | 3 |
Nexn | 2 |
Nfam1 | 3 |
Nfatc1 | 6 |
Nfe2 | 6 |
Nfe2l2 | 6 |
Nfkb2 | 3 |
Nfkbia | 3 |
Nfkbid | 3 |
Nfkbie | 3 |
Ngf | 6 |
Nhedc2 | 3 |
Ninl | 6 |
Nkg7 | 6 |
Nlrc4 | 3 |
Nlrp3 | 3 |
Nmral1 | 6 |
Nnat | 2 |
Nop10 | 6 |
Nos2 | 3 |
Nov | 5 |
Nova1 | 5 |
Npr1 | 1 |
Npr2 | 1 |
Npr3 | 2 |
Npy | 2 |
Nr1d1 | 5 |
Nr2f2 | 1 |
Nr3c2 | 2 |
Nr4a3 | 6 |
Nr5a2 | 6 |
Nrap | 5 |
Nrbf2 | 6 |
Nrg4 | 1 |
Nrn1 | 1 |
Nrn1l | 4 |
Nrp2 | 3 |
Nt5dc2 | 3 |
Ntn1 | 1 |
Ntn4 | 5 |
Ntng1 | 1 |
Ntrk2 | 5 |
Ntrk3 | 5 |
Nudt10 | 1 |
Nuf2 | 3 |
Nupl1 | 6 |
Nxph1 | 6 |
Obp1a | 1 |
Obscn | 2 |
Ociad2 | 5 |
Olfr1020 | 1 |
Olfr1130 | 1 |
Olfr1249 | 1 |
Olfr1252 | 1 |
Olfr1307 | 1 |
Olfr133 | 1 |
Olfr1413 | 1 |
Olfr1474 | 1 |
Olfr172 | 1 |
Olfr179 | 6 |
Olfr444 | 1 |
Olfr605 | 6 |
Olfr684 | 1 |
Olfr732 | 1 |
Olfr781 | 1 |
Olfr866 | 1 |
Olfr888 | 1 |
Olfr889 | 1 |
Olfr921 | 1 |
Olfr963 | 4 |
Olr1 | 3 |
Omd | 4 |
Osbpl1a | 1 |
Osbpl6 | 5 |
Oscar | 3 |
Osm | 6 |
Ostn | 2 |
Otud1 | 4 |
Ovgp1 | 1 |
Oxsr1 | 1 |
P2rx1 | 1 |
P2rx4 | 3 |
P2ry10 | 6 |
P2ry6 | 6 |
P4ha3 | 3 |
Pacsin3 | 1 |
Palmd | 5 |
Panx1 | 6 |
Panx3 | 3 |
Pcbp4 | 6 |
Pcdh11x | 5 |
Pcdh9 | 2 |
Pck1 | 5 |
Pcolce2 | 2 |
Pcp4l1 | 4 |
Pcsk6 | 2 |
Pcx | 2 |
Pdcd1lg2 | 6 |
Pde1a | 1 |
Pde4dip | 4 |
Pdha1 | 1 |
Pdk2 | 4 |
Pdk4 | 6 |
Pdlim3 | 4 |
Pdlim4 | 6 |
Pdpn | 3 |
Peg3 | 2 |
Penk | 2 |
Pfkfb1 | 5 |
Pfkfb3 | 1 |
Pfkm | 5 |
Pfn2 | 5 |
Pgam2 | 2 |
Pgm2 | 5 |
Pgm3 | 1 |
Phka1 | 4 |
Phkg1 | 4 |
Phtf2 | 5 |
Pi15 | 2 |
Pi16 | 6 |
Pid1 | 6 |
Pik3ap1 | 3 |
Pik3cg | 3 |
Pik3r5 | 3 |
Pilra | 6 |
Pilrb1 | 6 |
Pion | 3 |
Pkia | 5 |
Pla1a | 2 |
Pla2g16 | 2 |
Pla2g2a | 2 |
Pla2g2d | 3 |
Pla2g4e | 4 |
Pla2g7 | 3 |
Plac8 | 6 |
Plaur | 3 |
Plbd1 | 3 |
Plcb2 | 3 |
Plcg2 | 6 |
Pld3 | 3 |
Pld4 | 3 |
Plek | 3 |
Plek2 | 3 |
Plin1 | 2 |
Plin4 | 4 |
Plk1 | 6 |
Plk3 | 6 |
Plp1 | 5 |
Pls3 | 1 |
Plscr1 | 1 |
Plxnb2 | 3 |
Plxnc1 | 6 |
Pmp2 | 2 |
Pmp22 | 1 |
Pnn | 1 |
Pnpla3 | 2 |
Podn | 4 |
Podnl1 | 3 |
Pold4 | 6 |
Popdc2 | 5 |
Popdc3 | 4 |
Postn | 3 |
Pot1b | 6 |
Pou2af1 | 6 |
Pou2f2 | 6 |
Pparg | 2 |
Ppargc1a | 4 |
Ppfibp2 | 1 |
Ppic | 3 |
Ppip5k1 | 5 |
Ppl | 5 |
Ppp1r14c | 5 |
Ppp1r3a | 4 |
Ppp1r3c | 4 |
Ppp2r3a | 5 |
Ppp4r4 | 1 |
Prc1 | 3 |
Prcp | 3 |
Prdm1 | 3 |
Prdm13 | 6 |
Prelid1 | 6 |
Prkaa2 | 4 |
Prkar2a | 4 |
Prkcd | 3 |
Prkcq | 4 |
Prkd1 | 1 |
Prkg1 | 5 |
Prl2c5 | 6 |
Prnp | 1 |
Prokr1 | 6 |
Prps1 | 1 |
Prr11 | 6 |
Prr23a | 6 |
Prss46 | 6 |
Prss50 | 6 |
Prune2 | 4 |
Psd4 | 3 |
Psmb10 | 6 |
Psmb8 | 6 |
Psmd10 | 6 |
Pstpip1 | 3 |
Ptafr | 3 |
Ptbp1 | 6 |
Ptch1 | 2 |
Ptger2 | 6 |
Ptger3 | 1 |
Ptger4 | 3 |
Ptgs1 | 5 |
Ptgs2 | 6 |
Ptk2b | 3 |
Ptpla | 6 |
Ptplad2 | 6 |
Ptpn22 | 3 |
Ptpn3 | 5 |
Ptpn6 | 3 |
Ptpn7 | 6 |
Ptprc | 3 |
Ptpre | 3 |
Ptprv | 3 |
Ptrf | 5 |
Ptx4 | 4 |
Pvalb | 5 |
Pvrl1 | 3 |
Pycard | 6 |
Pygm | 5 |
Qpct | 5 |
Rab11fip1 | 6 |
Rab32 | 3 |
Rab37 | 2 |
Rab38 | 3 |
Rabgap1l | 1 |
Rac2 | 3 |
Racgap1 | 3 |
Rai14 | 3 |
Rasd1 | 2 |
Rasgrp1 | 3 |
Rassf2 | 6 |
Rassf4 | 3 |
Rassf6 | 1 |
Raver2 | 2 |
Rbm24 | 4 |
Rbm7 | 6 |
Rbp1 | 3 |
Rcan2 | 5 |
Rcn2 | 1 |
Reck | 1 |
Rel | 6 |
Relb | 3 |
Rep15 | 1 |
Retn | 4 |
Retnla | 2 |
Rgs1 | 3 |
Rgs19 | 3 |
Rgs5 | 1 |
Rhag | 6 |
Rhbdf2 | 6 |
Rhog | 6 |
Rilpl2 | 6 |
Rin3 | 6 |
Rinl | 6 |
Rnaset2a | 6 |
Rnf122 | 6 |
Rnf125 | 6 |
Rnf128 | 3 |
Rnf146 | 1 |
Rnf149 | 3 |
Rnf157 | 6 |
Rnf19b | 3 |
Rnu3a | 6 |
Rnu73b | 6 |
Rny1 | 3 |
Rora | 1 |
Rorc | 5 |
Rp2h | 6 |
Rpa3 | 6 |
Rpl28 | 6 |
Rpl34 | 6 |
Rpl3l | 4 |
Rps19 | 6 |
Rragb | 1 |
Rragd | 4 |
Rrs1 | 1 |
Rsu1 | 6 |
Rtn2 | 5 |
Rtn4rl1 | 2 |
Ruvbl1 | 1 |
Rxrg | 4 |
Ryr1 | 5 |
S100a8 | 6 |
S100b | 1 |
Saa3 | 3 |
Samsn1 | 6 |
Sash3 | 6 |
Satb1 | 2 |
Sbk2 | 5 |
Sbsn | 1 |
Scd1 | 5 |
Scg3 | 2 |
Scg5 | 1 |
Scn4a | 5 |
Scn4b | 4 |
Scrg1 | 2 |
Sdf2l1 | 6 |
Sectm1b | 1 |
Sel1l3 | 4 |
Sele | 3 |
Sell | 6 |
Selp | 3 |
Selplg | 3 |
Sema3a | 2 |
Sema3c | 5 |
Sema3d | 2 |
Sema3e | 2 |
Sema4a | 3 |
Sema4d | 6 |
Sema6c | 5 |
Serpina3c | 5 |
Serpina3f | 3 |
Serpinb9 | 6 |
Serpine1 | 3 |
Serpine2 | 1 |
Sestd1 | 1 |
Sf3b5 | 6 |
Sfpi1 | 6 |
Sfrp4 | 1 |
Sfrp5 | 5 |
Sgca | 4 |
Sgcd | 5 |
Sgcg | 4 |
Sgsh | 6 |
Sgsm2 | 1 |
Sh2d1b1 | 6 |
Sh3bgrl3 | 6 |
Sh3bp1 | 6 |
Sh3bp2 | 6 |
Sh3kbp1 | 6 |
Sh3rf2 | 4 |
Siglece | 6 |
Siglecg | 6 |
Sipa1 | 6 |
Sirpb1a | 3 |
Sirpb1b | 3 |
Sirt6 | 6 |
Sla | 6 |
Slain1 | 6 |
Slamf1 | 6 |
Slamf7 | 6 |
Slamf8 | 3 |
Slc10a6 | 3 |
Slc11a1 | 3 |
Slc13a3 | 6 |
Slc14a1 | 6 |
Slc15a3 | 3 |
Slc16a10 | 6 |
Slc16a6 | 6 |
Slc18a1 | 6 |
Slc19a3 | 6 |
Slc20a1 | 1 |
Slc22a3 | 2 |
Slc25a37 | 6 |
Slc25a4 | 5 |
Slc25a5 | 6 |
Slc2a4 | 4 |
Slc2a6 | 3 |
Slc31a2 | 6 |
Slc33a1 | 1 |
Slc36a1 | 6 |
Slc37a2 | 3 |
Slc38a3 | 4 |
Slc38a4 | 5 |
Slc39a4 | 6 |
Slc47a1 | 5 |
Slc48a1 | 6 |
Slc7a2 | 3 |
Slc7a9 | 1 |
Slc8a1 | 6 |
Slco2b1 | 1 |
Slfn2 | 3 |
Slfn9 | 6 |
Slpi | 3 |
Slurp1 | 5 |
Smarca1 | 1 |
Smpdl3b | 3 |
Smpx | 5 |
Smtn | 1 |
Smtnl1 | 4 |
Smtnl2 | 4 |
Smyd1 | 2 |
Snai2 | 6 |
Snap25 | 6 |
Sncg | 5 |
Sned1 | 1 |
Snora23 | 6 |
Snora44 | 6 |
Snora74a | 6 |
Snord104 | 6 |
Snord118 | 6 |
Snord57 | 6 |
Snord82 | 6 |
Snrpn | 4 |
Snx10 | 3 |
Snx13 | 1 |
Snx18 | 6 |
Snx20 | 6 |
Soat1 | 3 |
Socs5 | 1 |
Sod3 | 6 |
Sorbs1 | 4 |
Sox5 | 1 |
Sox6 | 5 |
Sox9 | 5 |
Spag5 | 6 |
Sparcl1 | 5 |
Speer6-ps1 | 1 |
Spg20 | 1 |
Spib | 6 |
Spn | 3 |
Spna1 | 6 |
Spnb1 | 4 |
Spock2 | 2 |
Spp1 | 3 |
Sprr1b | 6 |
Sprr2e | 6 |
Src | 6 |
Srfbp1 | 1 |
Srl | 5 |
Srsy | 1 |
Ssty1 | 1 |
Ssty2 | 1 |
St18 | 6 |
St3gal5 | 5 |
St3gal6 | 5 |
St6galnac4 | 6 |
St8sia4 | 6 |
St8sia6 | 3 |
Stac3 | 5 |
Stap1 | 6 |
Stc1 | 6 |
Stc2 | 1 |
Stk32b | 2 |
Stk38l | 1 |
Stox1 | 6 |
Stra6 | 6 |
Stx4a | 1 |
Stxbp2 | 6 |
Sucla2 | 5 |
Sult1e1 | 2 |
Susd2 | 3 |
Susd3 | 6 |
Sv2b | 4 |
Sv2c | 1 |
Syde2 | 1 |
Syn1 | 6 |
Syne2 | 1 |
Synpo2l | 4 |
Sypl2 | 4 |
Tacc2 | 5 |
Taf10 | 6 |
Tagap | 3 |
Tagln | 1 |
Tarm1 | 6 |
Tarsl2 | 5 |
Tbc1d20 | 6 |
Tbc1d2b | 6 |
Tbc1d8b | 1 |
Tc2n | 3 |
Tcap | 4 |
Tcea3 | 4 |
Tchh | 1 |
Tcirg1 | 6 |
Tctex1d2 | 6 |
Tenc1 | 5 |
Tff1 | 6 |
Tgfbr3 | 5 |
Thbd | 1 |
Thrb | 5 |
Thrsp | 5 |
Tiaf2 | 1 |
Tifab | 6 |
Tigd4 | 4 |
Timp1 | 3 |
Timp4 | 2 |
Tk1 | 6 |
Tlcd1 | 6 |
Tln2 | 1 |
Tlr1 | 6 |
Tlr13 | 3 |
Tlr2 | 3 |
Tlr8 | 3 |
Tlr9 | 6 |
Tm4sf19 | 3 |
Tm6sf1 | 6 |
Tmeff2 | 4 |
Tmem100 | 5 |
Tmem117 | 5 |
Tmem121 | 6 |
Tmem123 | 6 |
Tmem134 | 6 |
Tmem141 | 6 |
Tmem173 | 3 |
Tmem176a | 3 |
Tmem176b | 6 |
Tmem179b | 6 |
Tmem182 | 4 |
Tmem196 | 2 |
Tmem45b | 2 |
Tmem56 | 4 |
Tmem97 | 6 |
Tmod4 | 4 |
Tnf | 3 |
Tnfaip2 | 3 |
Tnfaip3 | 3 |
Tnfaip6 | 3 |
Tnfrsf11a | 3 |
Tnfrsf11b | 1 |
Tnfrsf13c | 6 |
Tnfrsf14 | 3 |
Tnfrsf1b | 3 |
Tnfrsf26 | 6 |
Tnfrsf9 | 3 |
Tnfsf10 | 6 |
Tnfsf15 | 6 |
Tnfsf9 | 6 |
Tnik | 5 |
Tnip1 | 3 |
Tnip3 | 3 |
Tnn | 3 |
Tnnc1 | 5 |
Tnnc2 | 5 |
Tnni1 | 4 |
Tnni2 | 5 |
Tnnt1 | 5 |
Tnnt2 | 4 |
Tnnt3 | 5 |
Tns3 | 6 |
Tnxb | 2 |
Tomm6 | 6 |
Tor2a | 6 |
Tpm1 | 1 |
Tpm2 | 5 |
Tpsab1 | 2 |
Tpsb2 | 5 |
Tpx2 | 3 |
Traf1 | 3 |
Traf3ip3 | 6 |
Tram2 | 6 |
Trappc2l | 6 |
Trdn | 4 |
Trem1 | 3 |
Trem2 | 3 |
Trem3 | 6 |
Treml4 | 3 |
Trf | 1 |
Trhde | 2 |
Trim54 | 5 |
Trim55 | 4 |
Trim63 | 4 |
Trim65 | 6 |
Trim72 | 5 |
Trpc3 | 1 |
Trpc4 | 6 |
Tshr | 5 |
Tshz2 | 1 |
Tspan15 | 2 |
Tspan17 | 6 |
Tspan2 | 1 |
Tspan3 | 1 |
Tspan6 | 6 |
Tspan8 | 5 |
Ttc9 | 4 |
Ttll7 | 5 |
Ttyh3 | 6 |
Tuft1 | 1 |
Txlnb | 4 |
Txnrd3 | 1 |
Tyms | 6 |
Tyrobp | 6 |
Uaca | 5 |
Uap1 | 1 |
Ube2c | 6 |
Ube2q1 | 6 |
Ube2ql1 | 6 |
Ucma | 2 |
Ucp2 | 3 |
Ucp3 | 6 |
Ufsp1 | 4 |
Ugcg | 6 |
Ugdh | 1 |
Ugp2 | 4 |
Ugt8a | 5 |
Unc13d | 6 |
Unc93b1 | 3 |
Upp1 | 6 |
Usmg5 | 4 |
Usp13 | 5 |
Usp2 | 4 |
Usp53 | 1 |
Utrn | 1 |
Uxs1 | 1 |
Vash2 | 6 |
Vasp | 3 |
Vat1l | 2 |
Vav1 | 3 |
Vcam1 | 3 |
Vcan | 1 |
Vgll2 | 4 |
Vgll3 | 6 |
Vit | 2 |
Vkorc1 | 6 |
Vldlr | 2 |
Vmn1r219 | 1 |
Vmn1r220 | 1 |
Vmn2r15 | 1 |
Vmn2r75 | 1 |
Vps37a | 6 |
Vsig4 | 2 |
Vwa1 | 1 |
Was | 6 |
Wbscr25 | 6 |
Wdfy4 | 3 |
Wfdc1 | 4 |
Wif1 | 1 |
Wipf2 | 6 |
Wisp1 | 3 |
Xcl1 | 6 |
Xirp1 | 4 |
Xirp2 | 2 |
Xkr7 | 6 |
Xpr1 | 6 |
Yipf7 | 4 |
Zadh2 | 1 |
Zbp1 | 3 |
Zbtb10 | 1 |
Zbtb16 | 5 |
Zbtb41 | 1 |
Zc3h12a | 6 |
Zfp106 | 2 |
Zfp212 | 1 |
Zfp330 | 1 |
Zfp36 | 6 |
Zfp365 | 1 |
Zfp36l2 | 6 |
Zfp385b | 2 |
Zfp511 | 6 |
Zfp628 | 6 |
Zfp800 | 6 |
Zfp870 | 1 |
Zfpm2 | 6 |
Zfyve9 | 1 |
Zmiz2 | 6 |
Zmynd15 | 3 |
Zmynd17 | 4 |
Znhit6 | 1 |
# Extract other cluster
= rownames(subset(clusters, ClusterNo==2))
cluster2 = rownames(subset(clusters, ClusterNo==3))
cluster3 = rownames(subset(clusters, ClusterNo==4))
cluster4 = rownames(subset(clusters, ClusterNo==5))
cluster5 = rownames(subset(clusters, ClusterNo==6))
cluster6
# Prepare data for heatmap
# Function to perform hierarchical clustering using the "ward.D2" method
= function(x)
hclustfunc hclust(x, method="ward.D2")
# Function to calculate pairwise Euclidean distances between data points
= function(x)
distfunc dist(x, method="euclidean")
# Perform clustering on rows and columns
= hclustfunc(distfunc(DEGsFrame[, c(1,3,5,7,9,11)]))
cl.row
# Extract cluster assignments of rows
= cutree(cl.row, k=6)
gr.row
# Apply a set of color palette
= brewer.pal(5, "Set3")
colors
<- heatmap.2(
heatmap c(1,3,5,7,9,11)],
DEGsFrame[, col = bluered(100), # blue-red color palette
tracecol="black",
density.info = "none",
labCol = c("TG", "REM_P", "REM", "HUM", "ENB","CIM"),
scale="none",
labRow="",
vline = 0,
mar=c(6,2),
RowSideColors = colors[gr.row],
hclustfun = function(x) hclust(x, method = 'ward.D2')
)
2.8 Functional analysis of Differentially Expressed Genes (DEGs)
Functional analysis of Differentially Expressed Genes (DEGs) is a critical component in understanding the molecular mechanisms underlying various biological processes, such as disease progression, developmental pathways, or responses to external stimuli. DEGs are genes that exhibit significant changes in expression levels between different experimental conditions, such as diseased versus healthy tissues or treated versus untreated samples.
Once DEGs are identified, they need to be annotated to determine their biological functions, cellular localization, molecular interactions, and involvement in various biological pathways. This is often achieved by comparing DEGs to databases of known gene annotations, such as Gene Ontology (GO) or Kyoto Encyclopedia of Genes and Genomes (KEGG).
Pathway analysis focuses on identifying interconnected networks of genes that collaborate to carry out specific biological functions or participate in common signaling pathways. This involves mapping DEGs onto existing biological pathways and identifying key regulatory nodes or hub genes within these pathways. Pathway analysis provides insights into the underlying molecular mechanisms driving the observed gene expression changes.
The code below performs hierarchical clustering analysis on a gene expression dataset and then further analyzes the clusters to identify enriched biological terms using the databases: Gene Ontology (GO), with three Sub-Ontologies (Biological Process (BP), Cellular Component (CC), Molecular Function (MF)) transcription factors (TF), and Kyoto Encyclopedia of Genes and Genomes (KEGG) databases.
The gost
function in the gProfileR
package performs the Gene Ontology (GO) semantic similarity analysis. It calculates the semantic similarity between terms in the Gene Ontology hierarchy based on the information content of the terms and the relationship between them.
# Get the cluster assignments
<- as.hclust(heatmap$rowDendrogram)
mt
# Cut the tree into 8 clusters
<- cutree(mt, k = 8)
tgcluster <- rownames(DEGsFrame)
tgdegnames <- as.numeric(names(table(tgcluster)))
cl
<- 0
totalresults <- 0
totalcols <-c("firebrick4", "red", "dark orange", "gold","dark green", "dodgerblue", "blue", "magenta", "darkorchid4")
pcols
for (i in c(6, 5, 4, 3, 2, 7, 1)) {
<- gost(query = as.character(tgdegnames[which(tgcluster == cl[i])]), organism = "mmusculus", significant = T, sources = "GO:BP")$result
gobp <- gost(query = as.character(tgdegnames[which(tgcluster == cl[i])]), organism = "mmusculus", significant = T, sources = "GO:MF")$result
gomf <- gost(query = as.character(tgdegnames[which(tgcluster == cl[i])]), organism = "mmusculus", significant = T, sources = "GO:CC")$result
gocc <- gost(query = as.character(tgdegnames[which(tgcluster == cl[i])]), organism = "mmusculus", significant = T, sources = "TF")$result
tf <- gost(query = as.character(tgdegnames[which(tgcluster == cl[i])]), organism = "mmusculus", significant = T, sources = "KEGG")$result
kegg
<- rbind(kegg, tf, gobp, gomf, gocc)
results
# Filter the results based on different sources
<- grep("TF:", results$term_id)
tf <- grep("GO:", results$term_id)
go <-grep("KEGG:", results$term_id)
kegg
# Get enriched terms/pathways, their associated p-values, and other relevant information obtained from the enrichment analysis.
<- results[kegg, ]
kegg<- results[tf, ]
tf <- results[go, ]
go
# Order the results based on p-values
<- kegg[order(kegg$p_value), ]
kegg<- go[order(go$p_value), ]
go <- tf[order(tf$p_value), ]
tf
# Split the term_id and term_name
<- strsplit(as.character(tf$term_name), ": ")
ll <- sapply(ll, "[[", 2)
ll <- strsplit(as.character(ll), ";")
ll $term_name <- sapply(ll, "[[", 1)
tf
# Remove duplicates
if (length(tf$term_id) > 0) {
<- unique(tf$term_name)
uniqtf <- 0
tfout for (ik in 1:length(uniqtf)) {
<- which(as.character(tf$term_name) == as.character(uniqtf[ik]))
nn <- tf[nn, ]
tfn <- which(tfn$p_value == min(tfn$p_value))
inn <- rbind(tfout, head(tfn[inn, ], 1))
tfout
}<- tfout[2:length(tfout[, 1]), ]
tf
}<- rbind(head(kegg, 10), head(go, 10), head(tf, 10))
results <- rbind(totalresults, results)
totalresults <- length(results$term_id)
n <- c(totalcols, rep(pcols[i], n))
totalcols
}
<- totalresults[2:length(totalresults[, 1]), ]
totalresults <- totalcols[2:length(totalcols)]
totalcols par(mar = c(5, 15, 1, 2))
# Visualization of Enriched Terms
barplot(
rev(-log10(totalresults$p_value[75:126])),
xlab = "-log10(p-value)",
ylab = "",
cex.main = 1.3,
cex.lab = 0.9,
cex.axis = 0.9,
main = "Under-Expressed Clusters",
col = rev(totalcols[75:126]),
horiz = T,
names = rev(totalresults$term_name[75:126]),
las = 1,
cex.names = 0.6
)
par(mar = c(5, 15, 1, 2))
barplot(
rev(-log10(totalresults$p_value[1:74])),
xlab = "-log10(p-value)",
ylab = "",
cex.main = 1.3,
cex.lab = 0.9,
cex.axis = 0.9,
main = "Over-Expressed Clusters",
col = rev(totalcols[1:74]),
horiz = T,
names = rev(totalresults$term_name[1:74]),
las = 1,
cex.names = 0.6
)
In addition, we perform functional enrichment analysis using the same function from the gprofiler2
package to identify enriched biological terms associated with the genes in each cluster. The gost
function compares the input gene list to a reference gene set and identifies statistically significant over-represented biological terms, such as Gene Ontology (GO) terms and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways. The results of the functional enrichment analysis are then filtered to include only statistically significant terms (p-value <= 0.01) and terms with a maximum size of 200 genes. The final enriched genes are then stored in a single dataframe for further analysis.
<- gost(query=as.character(cluster1), organism="mmusculus")
funcenr1 <- gost(query=as.character(cluster2), organism="mmusculus")
funcenr2 <- gost(query=as.character(cluster3), organism="mmusculus")
funcenr3 <- gost(query=as.character(cluster4), organism="mmusculus")
funcenr4 <- gost(query=as.character(cluster5), organism="mmusculus")
funcenr5 <- gost(query=as.character(cluster6), organism="mmusculus")
funcenr6
# Extract statistical significant genes, based on Functional Enrichment
<- subset(funcenr1$result[c("term_name","p_value")], funcenr1$result$term_size<=200 & funcenr1$result$p_value<=0.01)
filtered1 <- filtered1[order(filtered1$p_value),]
filtered1
<- subset(funcenr2$result[c("term_name","p_value")], funcenr2$result$term_size<=200 & funcenr2$result$p_value<=0.01)
filtered2 <- filtered2[order(filtered2$p_value),]
filtered2
<- subset(funcenr3$result[c("term_name","p_value")], funcenr3$result$term_size<=200 & funcenr3$result$p_value<=0.01)
filtered3 <- filtered3[order(filtered3$p_value),]
filtered3
<- subset(funcenr4$result[c("term_name","p_value")], funcenr4$result$term_size<=200 & funcenr4$result$p_value<=0.01)
filtered4 <- filtered4[order(filtered4$p_value),]
filtered4
<- subset(funcenr5$result[c("term_name","p_value")], funcenr5$result$term_size<=200 & funcenr5$result$p_value<=0.01)
filtered5 <- filtered5[order(filtered5$p_value),]
filtered5
<- subset(funcenr6$result[c("term_name","p_value")], funcenr6$result$term_size<=200 & funcenr6$result$p_value<=0.01)
filtered6 <- filtered6[order(filtered6$p_value),]
filtered6
# Final Enriched genes
<- rbind(filtered1, filtered2, filtered3, filtered4, filtered5, filtered6)
finalEnrichedDEGs
# Output data as table
kable(finalEnrichedDEGs, col.names = c("Enriched Term", "p-value"), caption = "Enriched Biological Terms") |>
kable_styling(font_size = 16) |>
scroll_box(height = "400px")
Enriched Term | p-value | |
---|---|---|
12 | myelination | 0.0000030 |
13 | ensheathment of neurons | 0.0000037 |
14 | axon ensheathment | 0.0000037 |
84 | extracellular matrix structural constituent | 0.0001949 |
102 | Complement and coagulation cascades | 0.0026797 |
57 | heparin binding | 0.0000638 |
65 | Adipogenesis genes | 0.0009603 |
66 | Endochondral ossification | 0.0090117 |
69 | positive regulation of leukocyte migration | 0.0000000 |
96 | neutrophil migration | 0.0000000 |
118 | granulocyte migration | 0.0000000 |
123 | neutrophil chemotaxis | 0.0000000 |
127 | T cell activation involved in immune response | 0.0000000 |
134 | tissue remodeling | 0.0000000 |
136 | granulocyte chemotaxis | 0.0000000 |
151 | positive regulation of inflammatory response | 0.0000000 |
156 | lymphocyte migration | 0.0000000 |
1136 | Chemokine signaling pathway | 0.0000000 |
175 | cellular extravasation | 0.0000000 |
1137 | TNF signaling pathway | 0.0000000 |
1138 | Viral protein interaction with cytokine and cytokine receptor | 0.0000000 |
872 | chemokine activity | 0.0000000 |
1139 | Rheumatoid arthritis | 0.0000000 |
186 | mononuclear cell migration | 0.0000000 |
187 | acute inflammatory response | 0.0000000 |
188 | interleukin-1 production | 0.0000000 |
189 | regulation of interleukin-1 production | 0.0000000 |
1140 | Legionellosis | 0.0000000 |
932 | Skin rash | 0.0000000 |
208 | chemokine-mediated signaling pathway | 0.0000000 |
1142 | Osteoclast differentiation | 0.0000000 |
874 | chemokine receptor binding | 0.0000000 |
226 | response to chemokine | 0.0000000 |
227 | cellular response to chemokine | 0.0000000 |
228 | regulation of leukocyte chemotaxis | 0.0000000 |
1262 | Tyrobp causal network in microglia | 0.0000000 |
231 | cell adhesion mediated by integrin | 0.0000000 |
234 | lymphocyte chemotaxis | 0.0000000 |
235 | bone remodeling | 0.0000000 |
1143 | NF-kappa B signaling pathway | 0.0000000 |
241 | antigen processing and presentation | 0.0000000 |
242 | positive regulation of chemotaxis | 0.0000000 |
243 | positive regulation of leukocyte proliferation | 0.0000000 |
247 | bone resorption | 0.0000000 |
249 | positive regulation of leukocyte chemotaxis | 0.0000000 |
1263 | Microglia pathogen phagocytosis pathway | 0.0000000 |
262 | response to interleukin-1 | 0.0000000 |
268 | regulation of phagocytosis | 0.0000000 |
272 | T cell differentiation involved in immune response | 0.0000000 |
274 | positive regulation of interleukin-1 production | 0.0000000 |
275 | response to type II interferon | 0.0000000 |
277 | positive regulation of phagocytosis | 0.0000000 |
1145 | Leishmaniasis | 0.0000000 |
1264 | Chemokine signaling pathway | 0.0000000 |
282 | interleukin-6 production | 0.0000000 |
283 | regulation of interleukin-6 production | 0.0000000 |
1146 | C-type lectin receptor signaling pathway | 0.0000000 |
285 | positive regulation of endocytosis | 0.0000000 |
289 | macrophage migration | 0.0000000 |
1147 | Tuberculosis | 0.0000000 |
292 | CD4-positive, alpha-beta T cell differentiation | 0.0000000 |
294 | myeloid cell activation involved in immune response | 0.0000000 |
295 | interleukin-8 production | 0.0000000 |
296 | regulation of interleukin-8 production | 0.0000000 |
297 | interleukin-1 beta production | 0.0000000 |
298 | regulation of interleukin-1 beta production | 0.0000000 |
300 | T cell differentiation in thymus | 0.0000000 |
302 | T cell migration | 0.0000000 |
304 | leukocyte adhesion to vascular endothelial cell | 0.0000000 |
306 | pyroptosis | 0.0000000 |
307 | T cell mediated immunity | 0.0000000 |
308 | myeloid leukocyte mediated immunity | 0.0000000 |
309 | positive regulation of peptidyl-tyrosine phosphorylation | 0.0000000 |
311 | positive regulation of mononuclear cell migration | 0.0000000 |
312 | CD4-positive, alpha-beta T cell activation | 0.0000000 |
828 | plasma membrane signaling receptor complex | 0.0000000 |
313 | cellular response to interleukin-1 | 0.0000000 |
315 | integrin-mediated signaling pathway | 0.0000000 |
316 | regulation of acute inflammatory response | 0.0000000 |
317 | positive regulation of lymphocyte migration | 0.0000000 |
319 | positive regulation of interleukin-1 beta production | 0.0000000 |
320 | response to fungus | 0.0000000 |
321 | regulation of mononuclear cell migration | 0.0000000 |
322 | alpha-beta T cell differentiation | 0.0000000 |
324 | regulation of macrophage migration | 0.0000000 |
1148 | Yersinia infection | 0.0000000 |
942 | Erosion of oral mucosa | 0.0000000 |
325 | regulation of granulocyte chemotaxis | 0.0000000 |
831 | canonical inflammasome complex | 0.0000000 |
327 | heterotypic cell-cell adhesion | 0.0000000 |
1149 | IL-17 signaling pathway | 0.0000000 |
1150 | Hematopoietic cell lineage | 0.0000000 |
329 | regulation of response to cytokine stimulus | 0.0000000 |
879 | cytokine binding | 0.0000000 |
330 | cytoplasmic pattern recognition receptor signaling pathway | 0.0000000 |
334 | non-canonical NF-kappaB signal transduction | 0.0000000 |
335 | killing of cells of another organism | 0.0000000 |
336 | disruption of cell in another organism | 0.0000000 |
337 | positive regulation of lymphocyte proliferation | 0.0000000 |
947 | Hemolytic anemia | 0.0000000 |
948 | Anemia due to reduced life span of red cells | 0.0000000 |
342 | positive regulation of mononuclear cell proliferation | 0.0000000 |
343 | leukocyte tethering or rolling | 0.0000000 |
344 | regulation of neutrophil migration | 0.0000000 |
949 | Sinusitis | 0.0000000 |
347 | regulation of myeloid leukocyte differentiation | 0.0000000 |
950 | Abnormal paranasal sinus morphology | 0.0000000 |
348 | positive regulation of T cell proliferation | 0.0000000 |
880 | immune receptor activity | 0.0000001 |
352 | regulation of cytokine-mediated signaling pathway | 0.0000001 |
881 | cytokine receptor activity | 0.0000001 |
355 | positive regulation of leukocyte mediated immunity | 0.0000001 |
357 | leukocyte degranulation | 0.0000001 |
358 | regulation of myeloid leukocyte mediated immunity | 0.0000001 |
359 | antigen receptor-mediated signaling pathway | 0.0000001 |
361 | cellular response to type II interferon | 0.0000001 |
362 | positive regulation of angiogenesis | 0.0000001 |
363 | positive regulation of adaptive immune response | 0.0000001 |
364 | positive regulation of vasculature development | 0.0000001 |
365 | T-helper cell differentiation | 0.0000001 |
1189 | Chemokine receptors bind chemokines | 0.0000001 |
367 | CD4-positive, alpha-beta T cell differentiation involved in immune response | 0.0000001 |
369 | alpha-beta T cell differentiation involved in immune response | 0.0000001 |
370 | positive regulation of tumor necrosis factor superfamily cytokine production | 0.0000002 |
371 | negative regulation of leukocyte activation | 0.0000002 |
955 | Abnormal T cell morphology | 0.0000002 |
956 | Mediastinal lymphadenopathy | 0.0000002 |
372 | alpha-beta T cell activation involved in immune response | 0.0000002 |
883 | integrin binding | 0.0000002 |
374 | production of molecular mediator involved in inflammatory response | 0.0000002 |
961 | Abscess | 0.0000002 |
376 | inflammatory response to antigenic stimulus | 0.0000002 |
377 | regulation of cellular extravasation | 0.0000002 |
378 | positive regulation of interleukin-8 production | 0.0000002 |
965 | Unusual CNS infection | 0.0000003 |
381 | leukocyte apoptotic process | 0.0000003 |
382 | dendritic cell antigen processing and presentation | 0.0000003 |
386 | cytokine production involved in immune response | 0.0000004 |
387 | regulation of cytokine production involved in immune response | 0.0000004 |
388 | B cell differentiation | 0.0000004 |
389 | disruption of anatomical structure in another organism | 0.0000004 |
1151 | Leukocyte transendothelial migration | 0.0000004 |
392 | positive regulation of adaptive immune response based on somatic recombination of immune receptors built from immunoglobulin superfamily domains | 0.0000005 |
832 | IPAF inflammasome complex | 0.0000005 |
833 | protein complex involved in cell adhesion | 0.0000005 |
393 | regulation of leukocyte adhesion to vascular endothelial cell | 0.0000005 |
394 | positive regulation of T cell migration | 0.0000005 |
1152 | Phagosome | 0.0000006 |
967 | Abnormal T cell count | 0.0000006 |
395 | positive regulation of acute inflammatory response | 0.0000006 |
396 | regulation of lymphocyte migration | 0.0000006 |
397 | monocyte chemotaxis | 0.0000006 |
398 | positive regulation of leukocyte adhesion to vascular endothelial cell | 0.0000006 |
968 | Unusual infection by anatomical site | 0.0000008 |
400 | blood coagulation | 0.0000008 |
888 | CCR chemokine receptor binding | 0.0000008 |
401 | negative regulation of tumor necrosis factor production | 0.0000008 |
1153 | Pertussis | 0.0000009 |
402 | eosinophil migration | 0.0000009 |
972 | Recurrent fungal infections | 0.0000009 |
1265 | IL 5 signaling pathway | 0.0000009 |
404 | regulation of chemokine production | 0.0000009 |
405 | chemokine production | 0.0000009 |
406 | coagulation | 0.0000010 |
407 | leukocyte homeostasis | 0.0000010 |
408 | hemostasis | 0.0000011 |
409 | leukocyte mediated cytotoxicity | 0.0000011 |
410 | regulation of leukocyte degranulation | 0.0000011 |
974 | Elevated circulating C-reactive protein concentration | 0.0000011 |
411 | negative regulation of tumor necrosis factor superfamily cytokine production | 0.0000011 |
412 | detection of biotic stimulus | 0.0000012 |
415 | negative regulation of immune effector process | 0.0000013 |
975 | Unusual fungal infection | 0.0000013 |
417 | regulation of T cell mediated immunity | 0.0000013 |
418 | positive regulation of lymphocyte differentiation | 0.0000014 |
419 | positive regulation of tumor necrosis factor production | 0.0000014 |
421 | negative regulation of lymphocyte activation | 0.0000015 |
977 | Abnormal circulating C-reactive protein concentration | 0.0000017 |
423 | respiratory burst | 0.0000017 |
424 | detection of external biotic stimulus | 0.0000017 |
426 | negative regulation of inflammatory response | 0.0000018 |
978 | Meningitis | 0.0000019 |
427 | positive regulation of neutrophil migration | 0.0000019 |
1154 | Malaria | 0.0000019 |
428 | negative regulation of leukocyte mediated immunity | 0.0000022 |
429 | negative regulation of adaptive immune response | 0.0000023 |
891 | CXCR chemokine receptor binding | 0.0000027 |
431 | defense response to Gram-positive bacterium | 0.0000028 |
432 | superoxide anion generation | 0.0000030 |
1266 | Spinal cord injury | 0.0000030 |
433 | positive regulation of macrophage migration | 0.0000031 |
434 | positive regulation of T cell differentiation | 0.0000032 |
436 | defense response to fungus | 0.0000033 |
437 | positive regulation of type II interferon production | 0.0000033 |
980 | Lymphopenia | 0.0000034 |
981 | T lymphocytopenia | 0.0000036 |
1155 | Chagas disease | 0.0000041 |
441 | negative regulation of cell-cell adhesion | 0.0000042 |
983 | Abnormal B cell morphology | 0.0000050 |
985 | Abnormal circulating IgG level | 0.0000057 |
986 | Recurrent skin infections | 0.0000057 |
987 | Discoid lupus rash | 0.0000058 |
1156 | African trypanosomiasis | 0.0000064 |
444 | positive regulation of CD4-positive, alpha-beta T cell differentiation | 0.0000072 |
445 | regulation of T cell differentiation | 0.0000072 |
893 | fibronectin binding | 0.0000073 |
446 | osteoclast differentiation | 0.0000079 |
447 | fever generation | 0.0000081 |
448 | homotypic cell-cell adhesion | 0.0000085 |
1267 | Macrophage markers | 0.0000090 |
449 | T-helper 1 type immune response | 0.0000103 |
450 | regulation of T cell migration | 0.0000103 |
451 | acute-phase response | 0.0000103 |
452 | tumor necrosis factor-mediated signaling pathway | 0.0000110 |
1158 | B cell receptor signaling pathway | 0.0000110 |
454 | superoxide metabolic process | 0.0000119 |
991 | Increased B cell count | 0.0000122 |
456 | mast cell activation | 0.0000124 |
457 | endolysosomal toll-like receptor signaling pathway | 0.0000125 |
458 | positive regulation of interleukin-6 production | 0.0000126 |
460 | regulation of cell adhesion mediated by integrin | 0.0000150 |
461 | regulation of alpha-beta T cell activation | 0.0000151 |
462 | regulation of leukocyte apoptotic process | 0.0000155 |
992 | Hepatosplenomegaly | 0.0000158 |
464 | nitric oxide metabolic process | 0.0000179 |
465 | cellular response to virus | 0.0000179 |
466 | negative regulation of adaptive immune response based on somatic recombination of immune receptors built from immunoglobulin superfamily domains | 0.0000179 |
993 | Abnormal B cell count | 0.0000194 |
994 | Colitis | 0.0000199 |
467 | collagen metabolic process | 0.0000210 |
468 | B cell receptor signaling pathway | 0.0000214 |
469 | reactive nitrogen species metabolic process | 0.0000226 |
470 | negative regulation of T cell mediated immunity | 0.0000233 |
995 | Abnormality of the thoracic cavity | 0.0000238 |
1159 | AGE-RAGE signaling pathway in diabetic complications | 0.0000241 |
472 | positive regulation of myeloid leukocyte differentiation | 0.0000243 |
474 | receptor signaling pathway via JAK-STAT | 0.0000285 |
998 | Antineutrophil antibody positivity | 0.0000292 |
475 | regulation of neutrophil chemotaxis | 0.0000299 |
476 | T cell selection | 0.0000301 |
1160 | Toll-like receptor signaling pathway | 0.0000304 |
477 | positive regulation of cell adhesion mediated by integrin | 0.0000316 |
839 | integrin complex | 0.0000321 |
478 | negative regulation of leukocyte cell-cell adhesion | 0.0000332 |
479 | positive regulation of alpha-beta T cell activation | 0.0000356 |
1000 | Abnormal mediastinum morphology | 0.0000362 |
481 | type II interferon production | 0.0000377 |
1001 | Decreased circulating IgG level | 0.0000383 |
485 | lymph node development | 0.0000423 |
1002 | Recurrent gram-negative bacterial infections | 0.0000457 |
487 | negative regulation of cytokine-mediated signaling pathway | 0.0000473 |
1161 | Amoebiasis | 0.0000477 |
488 | platelet aggregation | 0.0000489 |
489 | lipopolysaccharide-mediated signaling pathway | 0.0000489 |
490 | platelet activation | 0.0000493 |
492 | positive regulation of JNK cascade | 0.0000549 |
493 | negative regulation of interleukin-1 production | 0.0000556 |
494 | inflammatory response to wounding | 0.0000558 |
1005 | Systemic lupus erythematosus | 0.0000591 |
1192 | ROS and RNS production in phagocytes | 0.0000679 |
500 | negative regulation of response to cytokine stimulus | 0.0000777 |
502 | positive regulation of CD4-positive, alpha-beta T cell activation | 0.0000818 |
1010 | Antiphospholipid antibody positivity | 0.0000834 |
1162 | Influenza A | 0.0000918 |
505 | nitric oxide biosynthetic process | 0.0000986 |
507 | regulation of dendritic cell antigen processing and presentation | 0.0001059 |
1012 | Bronchiectasis | 0.0001074 |
1268 | Lung fibrosis | 0.0001084 |
1269 | Matrix metalloproteinases | 0.0001085 |
510 | animal organ regeneration | 0.0001108 |
1270 | Osteoclast signaling | 0.0001159 |
512 | detection of other organism | 0.0001211 |
513 | positive regulation of lymphocyte chemotaxis | 0.0001211 |
518 | positive regulation of canonical NF-kappaB signal transduction | 0.0001456 |
519 | positive regulation of production of molecular mediator of immune response | 0.0001456 |
1163 | Natural killer cell mediated cytotoxicity | 0.0001486 |
520 | mast cell activation involved in immune response | 0.0001564 |
521 | defense response to Gram-negative bacterium | 0.0001635 |
1015 | Impaired antigen-specific response | 0.0001641 |
1016 | Decreased circulating complement C3 concentration | 0.0001647 |
522 | granulocyte activation | 0.0001672 |
523 | regulation of platelet activation | 0.0001672 |
524 | regulation of bone resorption | 0.0001672 |
525 | antifungal innate immune response | 0.0001713 |
526 | regulation of cell killing | 0.0001804 |
527 | positive regulation of cytosolic calcium ion concentration | 0.0001819 |
1018 | Inflammation of the large intestine | 0.0001875 |
897 | pattern recognition receptor activity | 0.0001915 |
528 | regulation of osteoclast differentiation | 0.0001938 |
1019 | Abnormal proportion of CD8-positive T cells | 0.0001959 |
529 | positive regulation of myeloid cell differentiation | 0.0001968 |
532 | positive regulation of response to cytokine stimulus | 0.0002041 |
1020 | Recurrent pneumonia | 0.0002062 |
533 | hematopoietic or lymphoid organ development | 0.0002156 |
1021 | Recurrent upper respiratory tract infections | 0.0002228 |
534 | regulation of antigen processing and presentation | 0.0002374 |
535 | positive regulation of cellular extravasation | 0.0002374 |
536 | positive regulation of T-helper cell differentiation | 0.0002374 |
1022 | Antinuclear antibody positivity | 0.0002511 |
1023 | Autoimmune hemolytic anemia | 0.0002625 |
1024 | Recurrent staphylococcal infections | 0.0002625 |
1166 | Measles | 0.0002655 |
539 | positive regulation of alpha-beta T cell differentiation | 0.0002737 |
1025 | Decreased circulating total IgM | 0.0002941 |
541 | regulation of alpha-beta T cell differentiation | 0.0002991 |
543 | eosinophil chemotaxis | 0.0003232 |
544 | positive regulation of antigen processing and presentation | 0.0003264 |
545 | toll-like receptor 7 signaling pathway | 0.0003264 |
1026 | Abnormal lymphocyte proliferation | 0.0003280 |
1027 | Abnormal cell proliferation | 0.0003280 |
546 | regulation of type II interferon production | 0.0003354 |
1028 | Complement deficiency | 0.0003489 |
547 | collagen catabolic process | 0.0003631 |
1271 | Fibrin complement receptor 3 signaling pathway | 0.0003689 |
548 | regulation of CD4-positive, alpha-beta T cell differentiation | 0.0003733 |
550 | regulation of leukocyte mediated cytotoxicity | 0.0003978 |
1029 | Chronic pulmonary obstruction | 0.0004072 |
551 | regulation of leukocyte tethering or rolling | 0.0004330 |
552 | regulation of lymphocyte chemotaxis | 0.0004330 |
553 | positive regulation of bone resorption | 0.0004330 |
554 | regulation of T cell cytokine production | 0.0004434 |
555 | T cell cytokine production | 0.0004434 |
1167 | Complement and coagulation cascades | 0.0004817 |
556 | positive regulation of lymphocyte mediated immunity | 0.0004849 |
1030 | Sepsis | 0.0004957 |
557 | regulation of wound healing | 0.0005109 |
558 | positive regulation of chemokine (C-X-C motif) ligand 2 production | 0.0005253 |
559 | negative regulation of leukocyte degranulation | 0.0005253 |
560 | T cell extravasation | 0.0005253 |
562 | regulation of non-canonical NF-kappaB signal transduction | 0.0005356 |
563 | regulation of homotypic cell-cell adhesion | 0.0005381 |
564 | neutrophil mediated immunity | 0.0005381 |
1031 | Oral ulcer | 0.0005387 |
565 | regulation of CD4-positive, alpha-beta T cell activation | 0.0005436 |
566 | antigen processing and presentation of peptide antigen | 0.0005436 |
1032 | Autoimmune antibody positivity | 0.0005454 |
1194 | GPVI-mediated activation cascade | 0.0005456 |
567 | negative regulation of T cell mediated cytotoxicity | 0.0005623 |
1033 | Decreased circulating complement C4 concentration | 0.0005799 |
1034 | Abnormal nasopharynx morphology | 0.0005958 |
571 | neutrophil activation | 0.0006492 |
572 | response to protozoan | 0.0006492 |
573 | positive T cell selection | 0.0006492 |
574 | negative regulation of T cell activation | 0.0006514 |
575 | regulation of bone remodeling | 0.0006684 |
1168 | Lysosome | 0.0006757 |
1036 | Abnormality of complement system | 0.0006963 |
1037 | Abnormal T cell subset distribution | 0.0007181 |
580 | antigen processing and presentation of peptide antigen via MHC class II | 0.0007449 |
1039 | Acute phase response | 0.0007521 |
1272 | Cytokines and inflammatory response | 0.0007599 |
582 | positive regulation of chemokine production | 0.0007616 |
583 | innate immune response activating cell surface receptor signaling pathway | 0.0007616 |
584 | lymphocyte apoptotic process | 0.0007784 |
585 | vascular endothelial growth factor production | 0.0007791 |
586 | negative thymic T cell selection | 0.0008094 |
587 | positive regulation of leukocyte tethering or rolling | 0.0008094 |
1040 | Lymphocytosis | 0.0008131 |
589 | mature B cell differentiation | 0.0009302 |
591 | thymic T cell selection | 0.0009589 |
1169 | Primary immunodeficiency | 0.0009685 |
592 | calcium ion transmembrane import into cytosol | 0.0009757 |
593 | epithelial cell apoptotic process | 0.0010376 |
594 | negative regulation of lymphocyte mediated immunity | 0.0010517 |
1043 | Increased circulating IgG level | 0.0011090 |
596 | lipid storage | 0.0011126 |
597 | release of sequestered calcium ion into cytosol | 0.0011197 |
598 | positive regulation of cytokine-mediated signaling pathway | 0.0011438 |
599 | neutrophil-mediated killing of symbiont cell | 0.0012024 |
600 | negative T cell selection | 0.0012024 |
602 | negative regulation of sequestering of calcium ion | 0.0012065 |
603 | antigen processing and presentation of peptide or polysaccharide antigen via MHC class II | 0.0012208 |
604 | leukocyte migration involved in inflammatory response | 0.0012208 |
606 | positive regulation of cell-substrate adhesion | 0.0012991 |
607 | positive regulation of dendritic cell antigen processing and presentation | 0.0013000 |
608 | T cell apoptotic process | 0.0013001 |
609 | mast cell degranulation | 0.0013001 |
610 | macrophage chemotaxis | 0.0013068 |
1045 | Uveitis | 0.0013287 |
1046 | Recurrent aphthous stomatitis | 0.0013287 |
611 | regulation of response to wounding | 0.0013477 |
612 | regulation of sequestering of calcium ion | 0.0013980 |
613 | T cell receptor signaling pathway | 0.0013980 |
614 | JNK cascade | 0.0014371 |
1195 | Peptide ligand-binding receptors | 0.0014442 |
900 | phospholipase activity | 0.0014489 |
615 | cell surface toll-like receptor signaling pathway | 0.0014742 |
1047 | Recurrent Staphylococcus aureus infections | 0.0014987 |
616 | regulation of B cell activation | 0.0015035 |
617 | response to ethanol | 0.0015316 |
619 | integrin activation | 0.0015385 |
1170 | Fluid shear stress and atherosclerosis | 0.0015884 |
621 | sequestering of calcium ion | 0.0016159 |
623 | mast cell mediated immunity | 0.0016678 |
1048 | Rectal abscess | 0.0016886 |
1049 | Elevated proportion of CD4-negative, CD8-negative, alpha-beta regulatory T cells | 0.0016968 |
1235 | Factor: NF-kappaB; motif: NGGGANTTYCCMNNNN; match class: 1 | 0.0017107 |
624 | positive regulation of homotypic cell-cell adhesion | 0.0017323 |
625 | regulation of JNK cascade | 0.0017356 |
626 | negative regulation of lymphocyte proliferation | 0.0017491 |
845 | podosome | 0.0017575 |
1050 | Decreased proportion of CD4-positive T cells | 0.0018639 |
627 | regulation of antigen receptor-mediated signaling pathway | 0.0018827 |
628 | heat generation | 0.0019209 |
846 | lamellipodium membrane | 0.0019284 |
629 | negative regulation of mononuclear cell proliferation | 0.0019285 |
1052 | Abnormal pharynx morphology | 0.0019567 |
902 | lipase activity | 0.0020628 |
631 | regulation of humoral immune response | 0.0021065 |
632 | heterophilic cell-cell adhesion via plasma membrane cell adhesion molecules | 0.0021065 |
1055 | Polyarticular arthritis | 0.0023005 |
1056 | Non-Hodgkin lymphoma | 0.0023024 |
1196 | Signal regulatory protein family interactions | 0.0023686 |
1172 | Cell adhesion molecules | 0.0023768 |
633 | cell surface pattern recognition receptor signaling pathway | 0.0023841 |
634 | detection of bacterium | 0.0024306 |
635 | toll-like receptor 9 signaling pathway | 0.0024306 |
636 | neutrophil mediated cytotoxicity | 0.0024306 |
637 | inflammasome-mediated signaling pathway | 0.0024505 |
638 | antigen processing and presentation of exogenous peptide antigen via MHC class I | 0.0025759 |
639 | positive regulation of fever generation | 0.0025759 |
905 | protease binding | 0.0026600 |
641 | B cell proliferation | 0.0027558 |
643 | positive regulation of myeloid leukocyte mediated immunity | 0.0028403 |
908 | lipopolysaccharide binding | 0.0028877 |
645 | regulation of macrophage chemotaxis | 0.0029193 |
646 | positive regulation of neutrophil chemotaxis | 0.0029193 |
1059 | Elevated erythrocyte sedimentation rate | 0.0031376 |
849 | microvillus | 0.0032063 |
1060 | Leukocytosis | 0.0032551 |
850 | NADPH oxidase complex | 0.0033137 |
649 | cell-cell adhesion mediated by integrin | 0.0033332 |
1061 | Recurrent Burkholderia cepacia infections | 0.0033486 |
1062 | Pyuria | 0.0033486 |
1063 | Anti-La/SS-B antibody positivity | 0.0033486 |
1197 | Degradation of the extracellular matrix | 0.0034051 |
1273 | Focal adhesion | 0.0034171 |
851 | phagocytic vesicle | 0.0034470 |
1065 | Vasculitis | 0.0035906 |
650 | regulation of pattern recognition receptor signaling pathway | 0.0036685 |
1066 | Cellulitis | 0.0036832 |
1067 | Opportunistic infection | 0.0036832 |
651 | negative regulation of leukocyte proliferation | 0.0036925 |
652 | regulation of nitric oxide biosynthetic process | 0.0037346 |
653 | regulation of cell-matrix adhesion | 0.0040297 |
1274 | Comprehensive IL 17A signaling | 0.0040887 |
1198 | Cell surface interactions at the vascular wall | 0.0042484 |
1068 | Recurrent bacterial skin infections | 0.0042891 |
1069 | Decreased lymphocyte proliferation in response to mitogen | 0.0042891 |
1070 | Anti-Sm antibody positivity | 0.0042891 |
1071 | Lupus nephritis | 0.0042891 |
1072 | Anti-U1 ribonucleoprotein antibody positivity | 0.0042891 |
656 | positive regulation of granulocyte chemotaxis | 0.0043059 |
1073 | Chronic mucocutaneous candidiasis | 0.0043087 |
1074 | Abnormal erythrocyte sedimentation rate | 0.0043087 |
657 | acute inflammatory response to antigenic stimulus | 0.0043341 |
658 | humoral immune response mediated by circulating immunoglobulin | 0.0043341 |
659 | antigen processing and presentation of exogenous peptide antigen | 0.0043341 |
660 | negative regulation of interleukin-6 production | 0.0043341 |
1199 | Cross-presentation of particulate exogenous antigens (phagosomes) | 0.0045432 |
1075 | B-cell lymphoma | 0.0046338 |
1076 | Polyarticular arthropathy | 0.0046338 |
1077 | Stomatitis | 0.0046779 |
665 | phagocytosis, engulfment | 0.0049585 |
1078 | Abnormal proportion of double-negative alpha-beta regulatory T cell | 0.0050041 |
1079 | Cheilitis | 0.0050235 |
1080 | Abnormal proportion of CD4-positive T cells | 0.0050439 |
666 | negative regulation of leukocyte apoptotic process | 0.0051324 |
667 | negative regulation of T cell proliferation | 0.0051324 |
853 | ruffle | 0.0051473 |
910 | Toll-like receptor binding | 0.0051647 |
668 | extracellular matrix disassembly | 0.0051775 |
1082 | Recurrent Aspergillus infections | 0.0054404 |
1083 | Malaise | 0.0054404 |
1084 | Extractable nuclear antigen positivity | 0.0054404 |
669 | regulation of protein kinase activity | 0.0055975 |
670 | regulation of tissue remodeling | 0.0056874 |
671 | regulation of lymphocyte apoptotic process | 0.0056874 |
672 | regulation of nitric oxide metabolic process | 0.0056874 |
855 | granulocyte macrophage colony-stimulating factor receptor complex | 0.0058975 |
1174 | Staphylococcus aureus infection | 0.0059319 |
1085 | Decreased circulating level of specific antibody | 0.0060531 |
1086 | Abnormal macrophage morphology | 0.0060531 |
1200 | RHO GTPases Activate NADPH Oxidases | 0.0060673 |
1275 | Circulating monocytes and cardiac macrophages in diastolic dysfunction | 0.0061643 |
912 | coreceptor activity | 0.0061820 |
673 | regulation of B cell differentiation | 0.0061876 |
674 | liver morphogenesis | 0.0061876 |
675 | defense response to protozoan | 0.0061876 |
1175 | T cell receptor signaling pathway | 0.0063974 |
676 | response to gamma radiation | 0.0064340 |
678 | regulation of reactive oxygen species metabolic process | 0.0064567 |
856 | immunological synapse | 0.0064596 |
1176 | Cytosolic DNA-sensing pathway | 0.0064681 |
680 | regulation of cytoplasmic pattern recognition receptor signaling pathway | 0.0067015 |
1087 | Cutaneous photosensitivity | 0.0069518 |
684 | regulation of vascular endothelial growth factor production | 0.0073524 |
1178 | Platelet activation | 0.0074231 |
685 | regulation of fever generation | 0.0075860 |
686 | marginal zone B cell differentiation | 0.0075860 |
687 | wound healing involved in inflammatory response | 0.0075860 |
689 | antigen processing and presentation of exogenous peptide antigen via MHC class II | 0.0076917 |
1276 | Apoptosis | 0.0079350 |
1091 | T-cell lymphoma | 0.0081798 |
691 | regulation of inflammatory response to antigenic stimulus | 0.0082589 |
1092 | Elevated sweat chloride | 0.0085234 |
1093 | Abnormal urine cytology | 0.0085283 |
1094 | Hematuria | 0.0085283 |
694 | positive regulation of osteoclast differentiation | 0.0086897 |
1201 | Interleukin-1 processing | 0.0089043 |
1202 | Dectin-2 family | 0.0089043 |
1095 | Abnormality on pulmonary function testing | 0.0091486 |
696 | positive regulation of cytokine production involved in immune response | 0.0092242 |
697 | antigen processing and presentation of exogenous antigen | 0.0093215 |
698 | positive regulation of humoral immune response | 0.0098588 |
699 | modulation of process of another organism | 0.0098588 |
1203 | RAC2 GTPase cycle | 0.0099342 |
115 | I band | 0.0000000 |
11 | myofibril assembly | 0.0000000 |
133 | striated muscle cell development | 0.0000000 |
18 | sarcomere organization | 0.0000000 |
1181 | Z disc | 0.0000000 |
20 | cellular component assembly involved in morphogenesis | 0.0000000 |
121 | sarcolemma | 0.0000000 |
1751 | Orthopnea | 0.0000000 |
23 | striated muscle contraction | 0.0000000 |
3021 | Muscle contraction | 0.0000000 |
176 | Left ventricular systolic dysfunction | 0.0000000 |
179 | Type 1 muscle fiber predominance | 0.0000000 |
181 | Abnormal left ventricular function | 0.0000000 |
2921 | Cardiac muscle contraction | 0.0000000 |
303 | Striated Muscle Contraction | 0.0000000 |
33 | skeletal muscle adaptation | 0.0000000 |
184 | Abnormal muscle fiber-type distribution | 0.0000000 |
185 | Abnormal cardiac ventricular function | 0.0000000 |
1231 | striated muscle thin filament | 0.0000000 |
1861 | Heart block | 0.0000000 |
158 | titin binding | 0.0000000 |
1871 | Limb-girdle muscle weakness | 0.0000000 |
125 | myofilament | 0.0000000 |
41 | muscle adaptation | 0.0000001 |
42 | striated muscle adaptation | 0.0000001 |
1881 | Exertional dyspnea | 0.0000001 |
190 | Cardiac conduction abnormality | 0.0000003 |
191 | Increased variability in muscle fiber diameter | 0.0000003 |
192 | Thromboembolic stroke | 0.0000003 |
193 | Neck flexor weakness | 0.0000003 |
194 | Sudden death | 0.0000003 |
195 | Neck muscle weakness | 0.0000003 |
199 | Cardiac arrest | 0.0000005 |
200 | Left atrial enlargement | 0.0000005 |
201 | Abnormality of skeletal muscle fiber size | 0.0000005 |
202 | Sudden cardiac death | 0.0000005 |
293 | Adrenergic signaling in cardiomyocytes | 0.0000006 |
2941 | Hypertrophic cardiomyopathy | 0.0000009 |
159 | FATZ binding | 0.0000009 |
203 | Thromboembolism | 0.0000010 |
45 | cardiac muscle contraction | 0.0000010 |
204 | Abnormal left atrium morphology | 0.0000012 |
3041 | Glycogen metabolism | 0.0000013 |
205 | Abnormal cardiomyocyte morphology | 0.0000015 |
206 | Supraventricular arrhythmia | 0.0000017 |
207 | EMG: myopathic abnormalities | 0.0000017 |
160 | structural constituent of muscle | 0.0000018 |
126 | sarcoplasm | 0.0000025 |
2081 | Reduced left ventricular ejection fraction | 0.0000025 |
209 | Abnormal left ventricular ejection fraction | 0.0000025 |
211 | Atrial arrhythmia | 0.0000036 |
46 | muscle organ morphogenesis | 0.0000077 |
215 | Lipoatrophy | 0.0000091 |
216 | Dilated cardiomyopathy | 0.0000092 |
48 | regulation of muscle contraction | 0.0000106 |
161 | tropomyosin binding | 0.0000111 |
218 | Reduced systolic function | 0.0000147 |
2951 | Dilated cardiomyopathy | 0.0000164 |
305 | Glycogen synthesis | 0.0000189 |
219 | Atrial fibrillation | 0.0000211 |
2961 | Insulin signaling pathway | 0.0000234 |
53 | skeletal muscle contraction | 0.0000271 |
220 | Ventricular hypertrophy | 0.0000289 |
54 | glycogen biosynthetic process | 0.0000315 |
55 | glucan biosynthetic process | 0.0000315 |
2971 | Insulin resistance | 0.0000317 |
221 | Hand muscle weakness | 0.0000320 |
222 | Muscle fiber inclusion bodies | 0.0000333 |
576 | glycogen metabolic process | 0.0000459 |
223 | Muscle hypertrophy of the lower extremities | 0.0000464 |
2981 | Arrhythmogenic right ventricular cardiomyopathy | 0.0000489 |
60 | glucan metabolic process | 0.0000563 |
61 | muscle tissue morphogenesis | 0.0000687 |
224 | Reduced vital capacity | 0.0001050 |
2261 | Fatigable weakness | 0.0001612 |
654 | musculoskeletal movement | 0.0001748 |
2271 | Abnormal synaptic transmission | 0.0001768 |
2281 | Abnormal synaptic transmission at the neuromuscular junction | 0.0001768 |
229 | Abnormal peripheral nervous system synaptic transmission | 0.0001768 |
130 | sodium:potassium-exchanging ATPase complex | 0.0001828 |
230 | Fatigable weakness of skeletal muscles | 0.0001873 |
2311 | Interstitial cardiac fibrosis | 0.0002016 |
233 | Abnormal left ventricle morphology | 0.0002120 |
2341 | Abnormality of the musculature of the lower limbs | 0.0002205 |
2351 | Pelvic girdle muscle weakness | 0.0002263 |
661 | energy reserve metabolic process | 0.0002413 |
67 | multicellular organismal movement | 0.0002450 |
238 | Abnormal morphology of myocardial trabeculae | 0.0003735 |
68 | polysaccharide biosynthetic process | 0.0003746 |
692 | cardiac muscle tissue morphogenesis | 0.0003746 |
70 | regulation of myotube differentiation | 0.0003894 |
239 | Weakness of muscles of respiration | 0.0004017 |
71 | polysaccharide metabolic process | 0.0004198 |
72 | response to muscle stretch | 0.0004590 |
240 | Calf muscle hypertrophy | 0.0004604 |
1 | Sarcoglycan-sarcospan-syntrophin-dystrobrevin complex | 0.0004651 |
2411 | Abnormal calf musculature morphology | 0.0004754 |
73 | muscle filament sliding | 0.0005062 |
131 | intercalated disc | 0.0005519 |
2421 | Shoulder girdle muscle weakness | 0.0006402 |
132 | cation-transporting ATPase complex | 0.0006595 |
2431 | Abnormality of the shoulder girdle musculature | 0.0006923 |
244 | Foot dorsiflexor weakness | 0.0007492 |
78 | actin-myosin filament sliding | 0.0007917 |
3191 | Glycogen metabolism | 0.0009601 |
245 | Ventricular septal hypertrophy | 0.0009955 |
1341 | T-tubule | 0.0010508 |
135 | ATPase dependent transmembrane transport complex | 0.0010985 |
2471 | Lipodystrophy | 0.0011928 |
248 | Abnormality of the musculature of the hand | 0.0014120 |
80 | positive regulation of sodium ion export across plasma membrane | 0.0016330 |
137 | sarcoplasmic reticulum | 0.0017266 |
250 | Left ventricular hypertrophy | 0.0017538 |
251 | Abnormal cell morphology | 0.0019015 |
82 | tissue regeneration | 0.0020470 |
253 | Muscle fiber necrosis | 0.0022715 |
254 | Hip flexor weakness | 0.0022715 |
841 | regulation of striated muscle contraction | 0.0027776 |
162 | telethonin binding | 0.0028321 |
299 | Proximal tubule bicarbonate reclamation | 0.0028822 |
255 | Proximal muscle weakness in upper limbs | 0.0030966 |
163 | actinin binding | 0.0031857 |
138 | cell-cell contact zone | 0.0036059 |
85 | myotube differentiation | 0.0037738 |
86 | regulation of sodium ion export across plasma membrane | 0.0040641 |
139 | myosin II complex | 0.0043950 |
259 | Muscle fiber cytoplasmatic inclusion bodies | 0.0051092 |
260 | Abnormality of jaw muscles | 0.0051092 |
89 | actin-mediated cell contraction | 0.0052442 |
140 | cardiac myofibril | 0.0053234 |
261 | Ventricular tachycardia | 0.0057041 |
263 | Myocardial fibrosis | 0.0062675 |
264 | Proximal muscle weakness in lower limbs | 0.0064039 |
265 | Abnormal muscle tissue metabolite concentration | 0.0068551 |
266 | Atrioventricular block | 0.0068962 |
90 | cardiac muscle cell development | 0.0072670 |
91 | regulation of heart contraction | 0.0072891 |
141 | contractile actin filament bundle | 0.0077510 |
142 | stress fiber | 0.0077510 |
92 | cardiac muscle cell differentiation | 0.0078382 |
164 | glycogen binding | 0.0078541 |
267 | Centrally nucleated skeletal muscle fibers | 0.0079069 |
2681 | Left ventricular noncompaction | 0.0084114 |
269 | Abnormal morphology of left ventricular trabeculae | 0.0084114 |
144 | neuromuscular junction | 0.0092310 |
270 | Respiratory insufficiency due to muscle weakness | 0.0099220 |
3 | striated muscle contraction | 0.0000000 |
2262 | I band | 0.0000000 |
8 | skeletal muscle contraction | 0.0000000 |
9 | musculoskeletal movement | 0.0000000 |
112 | multicellular organismal movement | 0.0000000 |
2282 | sarcoplasmic reticulum | 0.0000000 |
2291 | Z disc | 0.0000000 |
2301 | sarcoplasm | 0.0000000 |
146 | regulation of muscle contraction | 0.0000000 |
232 | sarcolemma | 0.0000000 |
390 | Striated Muscle Contraction | 0.0000000 |
391 | Muscle contraction | 0.0000000 |
19 | neuromuscular process | 0.0000000 |
2342 | striated muscle thin filament | 0.0000000 |
24 | actin-mediated cell contraction | 0.0000000 |
2352 | myofilament | 0.0000000 |
236 | T-tubule | 0.0000000 |
3310 | actin filament-based movement | 0.0000000 |
34 | cardiac muscle contraction | 0.0000000 |
2381 | sarcoplasmic reticulum membrane | 0.0000000 |
2391 | A band | 0.0000000 |
37 | regulation of striated muscle contraction | 0.0000000 |
38 | striated muscle cell development | 0.0000000 |
413 | regulation of skeletal muscle contraction | 0.0000000 |
43 | myofibril assembly | 0.0000001 |
453 | cardiac muscle cell contraction | 0.0000003 |
2432 | troponin complex | 0.0000004 |
49 | regulation of heart contraction | 0.0000005 |
3811 | Motor proteins | 0.0000012 |
3821 | Hypertrophic cardiomyopathy | 0.0000022 |
383 | Dilated cardiomyopathy | 0.0000030 |
2441 | myosin filament | 0.0000031 |
2451 | M band | 0.0000031 |
58 | cellular component assembly involved in morphogenesis | 0.0000045 |
618 | adaptive thermogenesis | 0.0000049 |
62 | regulation of actin filament-based movement | 0.0000050 |
63 | regulation of calcium ion transmembrane transport | 0.0000057 |
3042 | Abnormality of skeletal muscle fiber size | 0.0000060 |
2472 | myosin II complex | 0.0000072 |
662 | sarcoplasmic reticulum calcium ion transport | 0.0000091 |
711 | relaxation of muscle | 0.0000113 |
721 | cardiac muscle cell development | 0.0000113 |
75 | regulation of cold-induced thermogenesis | 0.0000150 |
781 | cold-induced thermogenesis | 0.0000175 |
81 | cardiac cell development | 0.0000231 |
842 | triglyceride metabolic process | 0.0000252 |
861 | acylglycerol metabolic process | 0.0000289 |
87 | cardiac muscle cell differentiation | 0.0000310 |
3111 | Increased variability in muscle fiber diameter | 0.0000322 |
88 | cardiocyte differentiation | 0.0000326 |
892 | temperature homeostasis | 0.0000326 |
901 | neutral lipid metabolic process | 0.0000332 |
911 | regulation of cardiac muscle cell contraction | 0.0000362 |
93 | action potential | 0.0000407 |
3121 | Scapular winging | 0.0000596 |
3131 | Difficulty climbing stairs | 0.0000614 |
2491 | myosin complex | 0.0000636 |
384 | Arrhythmogenic right ventricular cardiomyopathy | 0.0000647 |
97 | sarcomere organization | 0.0000713 |
385 | Cardiac muscle contraction | 0.0000875 |
314 | Upper limb amyotrophy | 0.0000900 |
3151 | Abnormality of the shoulder girdle musculature | 0.0000915 |
2501 | intercalated disc | 0.0001023 |
3161 | Shoulder contracture | 0.0001084 |
3171 | Shoulder flexion contracture | 0.0001084 |
318 | Exercise-induced muscle stiffness | 0.0001084 |
3192 | Calf muscle hypertrophy | 0.0001228 |
106 | muscle adaptation | 0.0001275 |
108 | regulation of cardiac muscle contraction | 0.0001417 |
111 | regulation of muscle adaptation | 0.0001800 |
3211 | Abnormal calf musculature morphology | 0.0001872 |
113 | regulation of heart rate | 0.0002117 |
3221 | Muscle hypertrophy of the lower extremities | 0.0002137 |
3861 | Adrenergic signaling in cardiomyocytes | 0.0002361 |
3241 | Weakness of muscles of respiration | 0.0002925 |
3251 | Nemaline bodies | 0.0003454 |
326 | Exercise-induced muscle cramps | 0.0003454 |
3871 | Regulation of lipolysis in adipocytes | 0.0004619 |
328 | Facial diplegia | 0.0004901 |
1251 | cardiac muscle cell action potential | 0.0005525 |
332 | Respiratory insufficiency due to muscle weakness | 0.0006397 |
333 | Muscle fiber cytoplasmatic inclusion bodies | 0.0007646 |
3341 | Foot joint contracture | 0.0008108 |
129 | response to activity | 0.0008492 |
1301 | positive regulation of ion transmembrane transporter activity | 0.0008619 |
3351 | Exertional dyspnea | 0.0008809 |
1311 | positive regulation of cation transmembrane transport | 0.0009082 |
2531 | cell-cell contact zone | 0.0009209 |
1411 | myotube differentiation | 0.0015153 |
339 | Myotonia | 0.0015392 |
1421 | positive regulation of transporter activity | 0.0015464 |
2931 | troponin T binding | 0.0015562 |
143 | positive regulation of monoatomic ion transmembrane transport | 0.0016115 |
340 | Muscle spasm | 0.0016562 |
3441 | Muscle fiber inclusion bodies | 0.0023568 |
345 | Proximal muscle weakness in lower limbs | 0.0024040 |
150 | release of sequestered calcium ion into cytosol by sarcoplasmic reticulum | 0.0027055 |
1511 | relaxation of skeletal muscle | 0.0028622 |
3471 | Facial palsy | 0.0032522 |
153 | release of sequestered calcium ion into cytosol by endoplasmic reticulum | 0.0032738 |
154 | negative regulation of muscle contraction | 0.0032738 |
3481 | Abnormal seventh cranial physiology | 0.0034703 |
350 | Gowers sign | 0.0050211 |
2601 | cell-substrate junction | 0.0055704 |
351 | Malignant hyperthermia | 0.0056802 |
3521 | Abnormal scapula morphology | 0.0056872 |
166 | striated muscle adaptation | 0.0059344 |
2972 | microfilament motor activity | 0.0063703 |
354 | Waddling gait | 0.0081302 |
3551 | Myalgia | 0.0084495 |
356 | Abnormal muscle fiber-type distribution | 0.0087981 |
3571 | EMG: myopathic abnormalities | 0.0088126 |
3581 | Muscle stiffness | 0.0097921 |
2621 | junctional membrane complex | 0.0099015 |
5211 | immune receptor activity | 0.0000000 |
116 | regulation of type II interferon production | 0.0000000 |
117 | type II interferon production | 0.0000000 |
5221 | cytokine receptor activity | 0.0000000 |
5521 | Abnormal circulating IgA level | 0.0000000 |
124 | leukocyte apoptotic process | 0.0000000 |
1342 | lymphocyte apoptotic process | 0.0000000 |
1412 | positive regulation of leukocyte proliferation | 0.0000001 |
6061 | Hematopoietic cell lineage | 0.0000001 |
145 | regulation of leukocyte apoptotic process | 0.0000001 |
148 | response to chemokine | 0.0000001 |
149 | cellular response to chemokine | 0.0000001 |
1531 | leukocyte homeostasis | 0.0000001 |
1561 | regulation of leukocyte chemotaxis | 0.0000002 |
1581 | chemokine-mediated signaling pathway | 0.0000002 |
1601 | regulation of B cell activation | 0.0000003 |
6071 | B cell receptor signaling pathway | 0.0000005 |
165 | lymphocyte homeostasis | 0.0000005 |
6081 | Viral protein interaction with cytokine and cytokine receptor | 0.0000006 |
167 | positive regulation of lymphocyte proliferation | 0.0000007 |
168 | regulation of lymphocyte apoptotic process | 0.0000007 |
170 | granulocyte chemotaxis | 0.0000007 |
172 | positive regulation of mononuclear cell proliferation | 0.0000009 |
183 | positive regulation of cytosolic calcium ion concentration | 0.0000018 |
5251 | cytokine binding | 0.0000027 |
2021 | interleukin-10 production | 0.0000122 |
2031 | regulation of interleukin-10 production | 0.0000122 |
2061 | granulocyte migration | 0.0000131 |
214 | leukocyte mediated cytotoxicity | 0.0000174 |
2151 | antigen receptor-mediated signaling pathway | 0.0000174 |
225 | B cell proliferation | 0.0000232 |
6321 | Chemokine receptors bind chemokines | 0.0000249 |
5581 | Decreased circulating IgA level | 0.0000253 |
2343 | B cell receptor signaling pathway | 0.0000329 |
2353 | B cell homeostasis | 0.0000342 |
2361 | regulation of interleukin-6 production | 0.0000389 |
237 | interleukin-6 production | 0.0000389 |
5631 | Abnormal circulating IgM level | 0.0000394 |
2382 | CD4-positive, alpha-beta T cell activation | 0.0000398 |
2412 | positive regulation of leukocyte migration | 0.0000424 |
246 | positive regulation of T cell proliferation | 0.0000491 |
5641 | Antinuclear antibody positivity | 0.0000745 |
2591 | response to interleukin-1 | 0.0000897 |
5291 | chemokine receptor activity | 0.0000964 |
530 | G protein-coupled chemoattractant receptor activity | 0.0000964 |
531 | C-C chemokine binding | 0.0000964 |
2641 | regulation of CD4-positive, alpha-beta T cell activation | 0.0001120 |
6101 | Natural killer cell mediated cytotoxicity | 0.0001236 |
2682 | microglial cell activation | 0.0001263 |
2691 | positive regulation of type II interferon production | 0.0001288 |
2701 | plasma membrane invagination | 0.0001353 |
2741 | neuroinflammatory response | 0.0001477 |
2751 | thymocyte migration | 0.0001521 |
2771 | T cell apoptotic process | 0.0001590 |
281 | negative regulation of leukocyte activation | 0.0001953 |
5651 | Unusual CNS infection | 0.0002032 |
2821 | regulation of CD4-positive, alpha-beta T cell proliferation | 0.0002036 |
2831 | leukocyte activation involved in inflammatory response | 0.0002255 |
287 | ganglioside metabolic process | 0.0002787 |
2891 | regulation of B cell proliferation | 0.0002942 |
290 | neutrophil chemotaxis | 0.0003253 |
291 | calcium ion transmembrane import into cytosol | 0.0003267 |
2952 | regulation of myeloid leukocyte differentiation | 0.0003529 |
2973 | CD4-positive, alpha-beta T cell proliferation | 0.0003760 |
2982 | cellular response to interleukin-1 | 0.0004030 |
3001 | B cell differentiation | 0.0004123 |
301 | positive regulation of calcium ion transport | 0.0004174 |
569 | Unusual infection by anatomical site | 0.0004249 |
3031 | membrane invagination | 0.0004537 |
6121 | Osteoclast differentiation | 0.0004682 |
3051 | positive regulation of leukocyte chemotaxis | 0.0004969 |
3061 | osteoclast differentiation | 0.0005024 |
3071 | glial cell activation | 0.0005427 |
310 | regulation of mononuclear cell migration | 0.0006025 |
3112 | positive regulation of interleukin-6 production | 0.0006099 |
6131 | Chemokine signaling pathway | 0.0007419 |
5711 | Abnormal T cell morphology | 0.0007583 |
5321 | phosphotyrosine residue binding | 0.0007959 |
5721 | Decreased specific antibody response to polysaccharide vaccine | 0.0008319 |
3181 | negative regulation of leukocyte apoptotic process | 0.0008908 |
5341 | sialic acid binding | 0.0009717 |
3222 | positive regulation of lymphocyte migration | 0.0010634 |
323 | macrophage chemotaxis | 0.0010634 |
3252 | response to type II interferon | 0.0010936 |
3261 | negative regulation of lymphocyte activation | 0.0010936 |
3271 | interleukin-1 production | 0.0010980 |
3281 | regulation of interleukin-1 production | 0.0010980 |
3291 | interleukin-1 beta production | 0.0011540 |
3301 | regulation of interleukin-1 beta production | 0.0011540 |
5351 | chemokine binding | 0.0011558 |
5361 | C-C chemokine receptor activity | 0.0011716 |
331 | positive regulation of chemotaxis | 0.0011800 |
3342 | apoptotic mitochondrial changes | 0.0014531 |
3352 | mononuclear cell migration | 0.0015035 |
3371 | macrophage migration | 0.0015983 |
338 | innate immune response activating cell surface receptor signaling pathway | 0.0016602 |
3391 | killing of cells of another organism | 0.0017562 |
3401 | disruption of cell in another organism | 0.0017562 |
3421 | negative regulation of CD4-positive, alpha-beta T cell proliferation | 0.0020366 |
579 | Abnormal circulating IgG level | 0.0021845 |
346 | regulation of cytokine production involved in immune response | 0.0023034 |
3472 | cytokine production involved in immune response | 0.0023034 |
3552 | neutrophil migration | 0.0029456 |
3561 | positive regulation of mononuclear cell migration | 0.0029570 |
3572 | regulation of T cell migration | 0.0030334 |
3611 | regulation of lymphocyte migration | 0.0031721 |
3621 | T cell migration | 0.0031721 |
3631 | macrophage activation | 0.0031775 |
6521 | Microglia pathogen phagocytosis pathway | 0.0033083 |
366 | positive regulation of cytokine production involved in immune response | 0.0034936 |
368 | glycosphingolipid metabolic process | 0.0035596 |
3691 | negative regulation of lymphocyte apoptotic process | 0.0035596 |
3701 | release of cytochrome c from mitochondria | 0.0036114 |
3711 | response to leptin | 0.0036684 |
3771 | positive regulation of interleukin-1 production | 0.0041022 |
3781 | positive regulation of T cell migration | 0.0041391 |
379 | intrinsic apoptotic signaling pathway in response to DNA damage | 0.0042097 |
3862 | phagocytosis, engulfment | 0.0048479 |
3872 | negative regulation of alpha-beta T cell proliferation | 0.0050096 |
3881 | positive regulation of small GTPase mediated signal transduction | 0.0050615 |
3931 | positive regulation of tumor necrosis factor production | 0.0056625 |
5851 | Decreased circulating total IgM | 0.0058855 |
3941 | positive regulation of Rho protein signal transduction | 0.0060823 |
5861 | Autoimmune antibody positivity | 0.0062389 |
5871 | Decreased circulating level of specific antibody | 0.0064637 |
3971 | myeloid cell activation involved in immune response | 0.0065906 |
3981 | positive regulation of tumor necrosis factor superfamily cytokine production | 0.0066177 |
540 | chemokine activity | 0.0066863 |
4001 | regulation of calcium ion transmembrane transport | 0.0069278 |
511 | phagocytic vesicle | 0.0074162 |
5411 | protein phosphorylated amino acid binding | 0.0076369 |
4051 | positive regulation of production of molecular mediator of immune response | 0.0079456 |
4071 | regulation of phagocytosis | 0.0085261 |
588 | Decreased circulating IgG level | 0.0091945 |
4101 | regulation of release of sequestered calcium ion into cytosol | 0.0094442 |
4121 | positive regulation of interleukin-1 beta production | 0.0099061 |
3 Results
We have performed a comprehensive analysis of the gene expression data, including statistical analysis, differential expression analysis, hierarchical clustering, and functional enrichment analysis. The results of the analysis provide valuable insights into the underlying biological processes and molecular mechanisms associated with the observed gene expression changes. The identified differentially expressed genes (DEGs) and enriched biological terms can serve as a basis for further investigation and hypothesis generation, leading to a deeper understanding of the biological context and potential regulatory networks involved in the experimental conditions under study.
In the next section, we will integrate machine learning algorithms to predict the response to different treatments based on the gene expression data. We will explore various classification models and evaluate their performance in predicting the treatment response, providing a practical application of the gene expression data in a predictive modeling context. The results of the machine learning analysis will complement the findings of the statistical and functional analyses, contributing to a comprehensive understanding of the biological and clinical implications of the gene expression data.
4 Part 2 - Integrating Machine Learning Algorithms
import pandas as pd
import numpy as np
from collections import OrderedDict
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import LinearRegression, Ridge, Lasso, RidgeCV, LassoCV
from sklearn.neural_network import MLPClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report
from sklearn.metrics import f1_score
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from random import shuffle
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from tqdm import tqdm
import time
from hyperopt import fmin, tpe, hp
import tensorflow as tf
from tensorflow.keras.models import Sequential
import tensorflow as tf
from tensorflow.keras.layers import Input, Dense
from tensorflow.keras.models import Model
The initial data look like this:
= 'Supplement/Raw_common18704genes_antiTNF_normalized.tsv'
tsv_file = pd.read_csv(tsv_file, sep='\t')
df 10) df.head(
Gene A_Wt.1 A_Wt.2 ... G_Ther_Cim.8 G_Ther_Cim.9 G_Ther_Cim.10
0 A1bg 3.070662 3.439500 ... 4.451450 4.063431 4.587729
1 A1cf 4.203059 4.163411 ... 3.973460 3.937325 4.045415
2 A2ld1 5.688889 5.985790 ... 7.456668 7.041198 7.357232
3 A2m 5.643947 6.761445 ... 5.473457 5.297770 4.798315
4 A3galt2 4.848963 4.872971 ... 5.122402 4.950228 5.096405
5 A4galt 7.968874 7.840223 ... 9.638612 9.709996 9.446098
6 A4gnt 4.766360 4.508001 ... 4.477549 4.569458 4.802614
7 Aaas 6.955212 7.195978 ... 7.037981 6.915920 7.014394
8 Aacs 7.917138 8.385624 ... 7.166091 7.118318 6.723467
9 Aadac 3.028571 2.869241 ... 3.054603 3.126782 3.038146
[10 rows x 67 columns]
The final dataset looks like this:
= df['Gene'].values
genes = df.columns.tolist()
classes = classes[1:]
classes for i in range(0, len(classes)):
if '.' in classes[i]:
= classes[i].split('.')
parts = parts[0]
classes[i] = pd.DataFrame(columns=genes)
final_df for i in range(1, len(classes)+1):
= df.iloc[:, i].tolist()
values = {column: [value] for column, value in zip(genes, values)}
new_data = final_df._append(pd.DataFrame(new_data), ignore_index=True)
final_df 'label']=classes
final_df['label'] = pd.factorize(final_df['label'])[0]
final_df[= list(final_df.index)
rows
shuffle(rows)= final_df.loc[rows].reset_index(drop=True)
final_df 20) final_df.head(
A1bg A1cf A2ld1 A2m ... Zyx Zzef1 Zzz3 label
0 2.826464 4.314649 7.576914 5.678596 ... 8.163634 7.971203 8.854346 4
1 4.122122 3.971787 7.145736 6.196697 ... 8.554566 8.318015 8.197171 5
2 4.221542 4.014900 8.189553 6.411558 ... 8.792674 8.044391 8.235345 4
3 2.995979 4.244164 7.666683 5.427408 ... 8.274243 8.046331 8.786375 0
4 4.356665 3.985330 7.536229 6.223930 ... 8.557591 8.334049 8.121923 5
5 4.284299 3.929056 7.100726 6.735612 ... 8.637847 8.259391 8.243332 6
6 3.086808 4.161198 6.092865 5.717453 ... 7.934088 8.623265 9.006445 3
7 3.009204 4.073736 7.518545 5.986411 ... 8.580009 7.951099 8.688412 3
8 4.211045 4.059337 7.724071 6.278023 ... 8.882459 8.194287 8.222634 1
9 4.353070 4.080114 7.399227 5.857244 ... 8.764438 8.316751 8.146425 4
10 2.889848 4.108383 7.437147 5.692869 ... 8.513486 8.164049 8.742647 5
11 3.792425 3.738919 5.378959 5.544028 ... 8.213836 8.389922 8.990674 1
12 3.794275 3.880379 5.515330 5.159042 ... 8.346689 8.567041 9.050696 1
13 2.916708 4.191340 7.623201 5.968024 ... 8.392303 7.957400 8.714572 3
14 2.918813 4.202757 7.468092 5.074160 ... 8.352705 8.005533 8.713686 6
15 3.156002 4.090821 6.008787 5.575969 ... 8.051423 8.702022 9.122607 0
16 4.128573 4.033241 8.461913 6.410486 ... 8.777754 8.098338 8.330377 0
17 4.211936 4.163802 8.161904 6.092865 ... 9.180087 8.035402 8.269289 3
18 4.310112 4.058462 7.664548 6.591627 ... 8.959582 8.241116 8.230142 1
19 3.439500 4.163411 5.985790 6.761445 ... 8.141234 8.565268 9.012988 0
[20 rows x 18704 columns]
Let’s split the dataset into training and testing data:
=final_df['label']
y'label'], axis=1, inplace=True)
final_df.drop([=final_df
x= train_test_split(x, y, test_size=0.3, random_state=10) x_train, x_val, y_train, y_val
How do the training data look like?
10) x_train.head(
A1bg A1cf A2ld1 ... Zyx Zzef1 Zzz3
53 4.222589 4.130838 7.427760 ... 8.617622 8.246039 8.127647
10 2.889848 4.108383 7.437147 ... 8.513486 8.164049 8.742647
46 3.090952 4.063431 7.747365 ... 8.187328 7.843144 8.637428
44 2.788430 4.277230 7.646996 ... 8.190990 7.869362 8.726987
35 3.082066 4.304573 7.691302 ... 8.188497 7.973546 8.600527
18 4.310112 4.058462 7.664548 ... 8.959582 8.241116 8.230142
4 4.356665 3.985330 7.536229 ... 8.557591 8.334049 8.121923
31 4.211936 4.075409 8.027757 ... 8.687422 8.010624 8.232478
1 4.122122 3.971787 7.145736 ... 8.554566 8.318015 8.197171
12 3.794275 3.880379 5.515330 ... 8.346689 8.567041 9.050696
[10 rows x 18703 columns]
We will train various classifiers:
4.1 1. Gaussian Naive Bayes (GaussianNB)
The Gaussian Naive Bayes classifier is based on applying Bayes’ theorem with the “naive” assumption of independence between every pair of features. Given a class variable \(y\) and a dependent feature vector \(x_1\) through \(x_n\), Bayes’ theorem states the following relationship:
\[ P(y|x_1, \dots, x_n) = \frac{P(x_1, \dots, x_n|y) P(y)}{P(x_1, \dots, x_n)} \]
However, calculating \(P(x_1, \dots, x_n|y)\) directly is often infeasible, so Naive Bayes assumes that each feature \(x_i\) is conditionally independent of every other feature. This simplifies the calculation to:
\[ P(x_i|y) \approx \frac{1}{\sqrt{2\pi\sigma_y^2}} e^{-\frac{(x_i - \mu_y)^2}{2\sigma_y^2}} \]
where \(\mu_y\) and \(\sigma_y^2\) are the mean and variance of feature \(x_i\) for class \(y\). The parameters \(\mu_y\) and \(\sigma_y^2\) are estimated from the training data.
4.2 2. Support Vector Machine (SVC)
The Support Vector Machine (SVC for Support Vector Classification) aims to find the hyperplane in an N-dimensional space that distinctly classifies the data points. To separate two classes, the SVM finds the hyperplane with the maximum margin, which is the maximum distance between data points of both classes. Mathematically, if the training data set is given by \((x_i, y_i)\) where \(x_i\) is the feature vector and \(y_i \in \{-1, 1\}\) is the class label, the problem can be formulated as:
\[ \min_{w, b} \frac{1}{2}||w||^2 \]
subject to the constraint:
\[ y_i(w \cdot x_i + b) \geq 1, \forall i \]
Here, \(w\) is the normal vector to the hyperplane, and \(b\) is the bias term. This formulation is often solved using Lagrange multipliers and kernel tricks for non-linearly separable data.
4.3 3. Decision Tree Classifier
A Decision Tree Classifier uses a decision tree to go from observations about an item to conclusions about the item’s target value. It’s a simple flowchart-like structure where each internal node represents a “test” on an attribute, each branch represents the outcome of the test, and each leaf node represents a class label. The paths from root to leaf represent classification rules.
In a simplified mathematical description, the decision at each node is made based on maximizing some criterion, typically the Information Gain, defined as:
\[ \text{Information Gain} = \text{Entropy}(parent) - \sum_{j} \frac{N_j}{N} \text{Entropy}(child_j) \]
where Entropy is a measure of the impurity or randomness in the dataset and is given by:
\[ \text{Entropy}(S) = - \sum_{i} p_i \log_2 p_i \]
with \(p_i\) being the proportion of the samples that belong to class \(i\).
4.4 4. Random Forest Classifier
A Random Forest Classifier builds multiple decision trees and merges them together to get a more accurate and stable prediction. The fundamental idea behind a random forest is to combine the predictions of several trees to decide on the final classification. This is often more accurate than the prediction of any individual tree because the forest corrects for the overfitting of individual trees to their training set.
Mathematically, the prediction of the random forest for classification tasks is the mode of the classes predicted by individual trees. If you have a random forest with \(N\) trees and \(C_i\) is the class predicted by the \(i^{th}\) tree, the final prediction (\(C_{\text{final}}\)) can be expressed as:
\[ C_{\text{final}} = \text{mode} \{C_1, C_2, \ldots, C_N\} \]
This model reduces overfitting by averaging multiple trees, each trained on random subsets of the training data (both samples and features), leading to higher robustness and accuracy.
We will now train the models!
= GaussianNB()
nbc nbc.fit(x_train,y_train)
GaussianNB()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
GaussianNB()
= SVC()
svc svc.fit(x_train, y_train)
SVC()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
SVC()
= DecisionTreeClassifier()
tree tree.fit(x_train, y_train)
DecisionTreeClassifier()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
DecisionTreeClassifier()
= RandomForestClassifier()
rf rf.fit(x_train, y_train)
RandomForestClassifier()In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
RandomForestClassifier()
Then, using the trained models, we make our predictions:
= nbc.predict(x_val)
y_pred_nbc = svc.predict(x_val)
y_pred_svc = tree.predict(x_val)
y_pred_tree = rf.predict(x_val) y_pred_rf
We will now evaluate these predictions so that we can decide which model is the best fit for our dataset.
='micro'
parameter=f1_score(y_val, y_pred_nbc, average=parameter)
s1= accuracy_score(y_val, y_pred_nbc)
accuracy print("\nGaussianNB f1 score:")
GaussianNB f1 score:
print(s1)
0.4000000000000001
print("GaussianNB accuracy:")
GaussianNB accuracy:
print(accuracy)
0.4
=f1_score(y_val, y_pred_svc, average=parameter)
s5= accuracy_score(y_val, y_pred_svc)
accuracy print("\nSVC f1 score:")
SVC f1 score:
print(s5)
0.05000000000000001
print("SVC accuracy:")
SVC accuracy:
print(accuracy)
0.05
=f1_score(y_val, y_pred_tree, average=parameter)
s6= accuracy_score(y_val, y_pred_tree)
accuracy print("\nDecision Tree f1 score:")
Decision Tree f1 score:
print(s6)
0.4000000000000001
print("Tree accuracy:")
Tree accuracy:
print(accuracy)
0.4
=f1_score(y_val, y_pred_rf, average=parameter)
s7= accuracy_score(y_val, y_pred_rf)
accuracy print("\nRandom Forest f1 score:")
Random Forest f1 score:
print(s7)
0.55
print("Random Forest accuracy:")
Random Forest accuracy:
print(accuracy)
0.55
= confusion_matrix(y_val, y_pred_rf) cnf_matrix
However, because of the small amount of data that we have, if we execute again hthe above cells, we may get slightly different results. As a result, we will run these experiments multiple time so that we get the average results:
def average_trainer(trials):
=1
min1=1
min5=1
min6=1
min7=0
max1=0
max5=0
max6=0
max7=0
avg1=0
avg5=0
avg6=0
avg7for i in tqdm(range(trials), desc="Processing", unit="iteration"):
= train_test_split(x, y, test_size=0.3, random_state=10)
x_train, x_val, y_train, y_val
= GaussianNB()
nbc
nbc.fit(x_train,y_train)= SVC()
svc
svc.fit(x_train, y_train)= DecisionTreeClassifier()
tree
tree.fit(x_train, y_train)= RandomForestClassifier()
rf
rf.fit(x_train, y_train)
= nbc.predict(x_val)
y_pred_nbc = svc.predict(x_val)
y_pred_svc = tree.predict(x_val)
y_pred_tree = rf.predict(x_val)
y_pred_rf
='micro'
parameter=f1_score(y_val, y_pred_nbc, average=parameter)
s1if(s1<min1):
=s1
min1if(s1>max1):
=s1
max1=avg1+s1
avg1=f1_score(y_val, y_pred_svc, average=parameter)
s5if(s5<min5):
=s5
min5if(s5>max5):
=s5
max5=avg5+s5
avg5=f1_score(y_val, y_pred_tree, average=parameter)
s6if(s6<min6):
=s6
min6if(s6>max6):
=s6
max6=avg6+s6
avg6=f1_score(y_val, y_pred_rf, average=parameter)
s7if(s7<min7):
=s7
min7if(s7>max7):
=s7
max7=avg7+s7
avg7=avg1/trials
avg1=avg5/trials
avg5=avg6/trials
avg6=avg7/trials
avg7print('\nNBC: max: '+str(max1)+ ' min: '+ str(min1) + ' average: '+ str(avg1))
print('SVC: max: '+str(max5)+ ' min: '+ str(min5) + ' average: '+ str(avg5))
print('TREE: max: '+str(max6)+ ' min: '+ str(min6) + ' average: '+ str(avg6))
print('RFOREST: max: '+str(max7)+ ' min: '+ str(min7) + ' average: '+ str(avg7))
50) average_trainer(
NBC: max: 0.4000000000000001 min: 0.4000000000000001 average: 0.3999999999999999
SVC: max: 0.05000000000000001 min: 0.05000000000000001 average: 0.04999999999999999
TREE: max: 0.65 min: 0.3 average: 0.457
RFOREST: max: 0.75 min: 0.4000000000000001 average: 0.599
Processing: 0%| | 0/50 [00:00<?, ?iteration/s]
Processing: 2%|2 | 1/50 [00:02<01:44, 2.14s/iteration]
Processing: 4%|4 | 2/50 [00:04<01:42, 2.15s/iteration]
Processing: 6%|6 | 3/50 [00:06<01:40, 2.14s/iteration]
Processing: 8%|8 | 4/50 [00:08<01:39, 2.16s/iteration]
Processing: 10%|# | 5/50 [00:10<01:40, 2.22s/iteration]
Processing: 12%|#2 | 6/50 [00:13<01:36, 2.20s/iteration]
Processing: 14%|#4 | 7/50 [00:15<01:35, 2.22s/iteration]
Processing: 16%|#6 | 8/50 [00:17<01:37, 2.33s/iteration]
Processing: 18%|#8 | 9/50 [00:20<01:35, 2.32s/iteration]
Processing: 20%|## | 10/50 [00:22<01:32, 2.31s/iteration]
Processing: 22%|##2 | 11/50 [00:25<01:32, 2.37s/iteration]
Processing: 24%|##4 | 12/50 [00:27<01:28, 2.32s/iteration]
Processing: 26%|##6 | 13/50 [00:29<01:24, 2.28s/iteration]
Processing: 28%|##8 | 14/50 [00:31<01:21, 2.25s/iteration]
Processing: 30%|### | 15/50 [00:33<01:18, 2.23s/iteration]
Processing: 32%|###2 | 16/50 [00:36<01:16, 2.24s/iteration]
Processing: 34%|###4 | 17/50 [00:38<01:13, 2.22s/iteration]
Processing: 36%|###6 | 18/50 [00:40<01:10, 2.21s/iteration]
Processing: 38%|###8 | 19/50 [00:42<01:08, 2.20s/iteration]
Processing: 40%|#### | 20/50 [00:44<01:05, 2.19s/iteration]
Processing: 42%|####2 | 21/50 [00:46<01:03, 2.18s/iteration]
Processing: 44%|####4 | 22/50 [00:49<01:01, 2.18s/iteration]
Processing: 46%|####6 | 23/50 [00:51<00:58, 2.18s/iteration]
Processing: 48%|####8 | 24/50 [00:53<00:56, 2.17s/iteration]
Processing: 50%|##### | 25/50 [00:55<00:54, 2.17s/iteration]
Processing: 52%|#####2 | 26/50 [00:57<00:51, 2.16s/iteration]
Processing: 54%|#####4 | 27/50 [00:59<00:49, 2.16s/iteration]
Processing: 56%|#####6 | 28/50 [01:02<00:47, 2.16s/iteration]
Processing: 58%|#####8 | 29/50 [01:04<00:46, 2.19s/iteration]
Processing: 60%|###### | 30/50 [01:06<00:43, 2.20s/iteration]
Processing: 62%|######2 | 31/50 [01:08<00:41, 2.19s/iteration]
Processing: 64%|######4 | 32/50 [01:10<00:39, 2.19s/iteration]
Processing: 66%|######6 | 33/50 [01:13<00:36, 2.18s/iteration]
Processing: 68%|######8 | 34/50 [01:15<00:34, 2.17s/iteration]
Processing: 70%|####### | 35/50 [01:17<00:32, 2.17s/iteration]
Processing: 72%|#######2 | 36/50 [01:19<00:30, 2.16s/iteration]
Processing: 74%|#######4 | 37/50 [01:21<00:27, 2.15s/iteration]
Processing: 76%|#######6 | 38/50 [01:23<00:25, 2.16s/iteration]
Processing: 78%|#######8 | 39/50 [01:25<00:23, 2.15s/iteration]
Processing: 80%|######## | 40/50 [01:28<00:21, 2.15s/iteration]
Processing: 82%|########2 | 41/50 [01:30<00:19, 2.15s/iteration]
Processing: 84%|########4 | 42/50 [01:32<00:17, 2.15s/iteration]
Processing: 86%|########6 | 43/50 [01:34<00:15, 2.16s/iteration]
Processing: 88%|########8 | 44/50 [01:36<00:12, 2.16s/iteration]
Processing: 90%|######### | 45/50 [01:38<00:10, 2.17s/iteration]
Processing: 92%|#########2| 46/50 [01:41<00:08, 2.17s/iteration]
Processing: 94%|#########3| 47/50 [01:43<00:06, 2.16s/iteration]
Processing: 96%|#########6| 48/50 [01:45<00:04, 2.16s/iteration]
Processing: 98%|#########8| 49/50 [01:47<00:02, 2.18s/iteration]
Processing: 100%|##########| 50/50 [01:49<00:00, 2.19s/iteration]
Processing: 100%|##########| 50/50 [01:49<00:00, 2.20s/iteration]
We will now check how different model parameters change our results, so that we select the best possible random forest classifier:
def objective(params):
= params['n_estimators']
n_estimators = params['max_depth']
max_depth = params['min_samples_split']
min_samples_split = params['min_samples_leaf']
min_samples_leaf
= RandomForestClassifier(
clf =n_estimators,
n_estimators=max_depth,
max_depth=min_samples_split,
min_samples_split=min_samples_leaf,
min_samples_leaf=42
random_state
)=0
final_scorefor i in range(0,20):
= train_test_split(x, y, test_size=0.3, random_state=10)
x_train, x_val, y_train, y_val
clf.fit(x_train, y_train)= clf.predict(x_val)
y_pred ='micro'
parameter=f1_score(y_val, y_pred, average=parameter)
score=final_score+score
final_score=final_score/20
final_score
return -final_score
= {
space 'n_estimators': hp.choice('n_estimators', range(10, 101)),
'max_depth': hp.choice('max_depth', range(1, 21)),
'min_samples_split': hp.choice('min_samples_split', range(2, 11)),
'min_samples_leaf': hp.choice('min_samples_leaf', range(1, 11))
}
= fmin(fn=objective, space=space, algo=tpe.suggest, max_evals=100) best
0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
1%|1 | 1/100 [00:10<17:35, 10.66s/trial, best loss: -0.6500000000000001]
2%|2 | 2/100 [00:20<16:18, 9.98s/trial, best loss: -0.6500000000000001]
3%|3 | 3/100 [00:28<15:04, 9.32s/trial, best loss: -0.6500000000000001]
4%|4 | 4/100 [00:39<15:46, 9.86s/trial, best loss: -0.6500000000000001]
5%|5 | 5/100 [00:49<15:36, 9.86s/trial, best loss: -0.6500000000000001]
6%|6 | 6/100 [00:59<15:51, 10.12s/trial, best loss: -0.6500000000000001]
7%|7 | 7/100 [01:09<15:37, 10.09s/trial, best loss: -0.6500000000000001]
8%|8 | 8/100 [01:19<15:20, 10.01s/trial, best loss: -0.6500000000000001]
9%|9 | 9/100 [01:28<14:36, 9.63s/trial, best loss: -0.6500000000000001]
10%|# | 10/100 [01:37<14:06, 9.41s/trial, best loss: -0.6500000000000001]
11%|#1 | 11/100 [01:46<13:41, 9.23s/trial, best loss: -0.6500000000000001]
12%|#2 | 12/100 [01:58<14:52, 10.14s/trial, best loss: -0.75]
13%|#3 | 13/100 [02:08<14:39, 10.11s/trial, best loss: -0.75]
14%|#4 | 14/100 [02:20<15:10, 10.58s/trial, best loss: -0.75]
15%|#5 | 15/100 [02:29<14:18, 10.10s/trial, best loss: -0.75]
16%|#6 | 16/100 [02:41<15:12, 10.87s/trial, best loss: -0.75]
17%|#7 | 17/100 [02:51<14:23, 10.41s/trial, best loss: -0.75]
18%|#8 | 18/100 [03:00<13:41, 10.02s/trial, best loss: -0.75]
19%|#9 | 19/100 [03:10<13:39, 10.12s/trial, best loss: -0.75]
20%|## | 20/100 [03:21<13:54, 10.43s/trial, best loss: -0.75]
21%|##1 | 21/100 [03:34<14:46, 11.22s/trial, best loss: -0.75]
22%|##2 | 22/100 [03:48<15:20, 11.80s/trial, best loss: -0.75]
23%|##3 | 23/100 [03:57<14:16, 11.13s/trial, best loss: -0.75]
24%|##4 | 24/100 [04:08<13:58, 11.03s/trial, best loss: -0.75]
25%|##5 | 25/100 [04:19<13:58, 11.17s/trial, best loss: -0.75]
26%|##6 | 26/100 [04:32<14:23, 11.67s/trial, best loss: -0.75]
27%|##7 | 27/100 [04:40<12:47, 10.52s/trial, best loss: -0.75]
28%|##8 | 28/100 [04:51<12:45, 10.63s/trial, best loss: -0.75]
29%|##9 | 29/100 [05:03<13:05, 11.06s/trial, best loss: -0.75]
30%|### | 30/100 [05:12<12:01, 10.30s/trial, best loss: -0.75]
31%|###1 | 31/100 [05:24<12:27, 10.84s/trial, best loss: -0.75]
32%|###2 | 32/100 [05:34<11:59, 10.59s/trial, best loss: -0.75]
33%|###3 | 33/100 [05:45<12:13, 10.95s/trial, best loss: -0.75]
34%|###4 | 34/100 [05:54<11:16, 10.26s/trial, best loss: -0.75]
35%|###5 | 35/100 [06:08<12:09, 11.23s/trial, best loss: -0.75]
36%|###6 | 36/100 [06:16<10:55, 10.25s/trial, best loss: -0.75]
37%|###7 | 37/100 [06:25<10:35, 10.09s/trial, best loss: -0.75]
38%|###8 | 38/100 [06:38<11:15, 10.89s/trial, best loss: -0.75]
39%|###9 | 39/100 [06:50<11:17, 11.10s/trial, best loss: -0.75]
40%|#### | 40/100 [07:01<11:07, 11.12s/trial, best loss: -0.75]
41%|####1 | 41/100 [07:11<10:35, 10.77s/trial, best loss: -0.75]
42%|####2 | 42/100 [07:22<10:38, 11.01s/trial, best loss: -0.75]
43%|####3 | 43/100 [07:33<10:20, 10.89s/trial, best loss: -0.75]
44%|####4 | 44/100 [07:43<10:03, 10.78s/trial, best loss: -0.75]
45%|####5 | 45/100 [07:55<10:06, 11.03s/trial, best loss: -0.75]
46%|####6 | 46/100 [08:04<09:22, 10.41s/trial, best loss: -0.75]
47%|####6 | 47/100 [08:15<09:15, 10.49s/trial, best loss: -0.75]
48%|####8 | 48/100 [08:27<09:37, 11.10s/trial, best loss: -0.75]
49%|####9 | 49/100 [08:39<09:30, 11.18s/trial, best loss: -0.75]
50%|##### | 50/100 [08:49<09:07, 10.95s/trial, best loss: -0.75]
51%|#####1 | 51/100 [08:59<08:39, 10.61s/trial, best loss: -0.75]
52%|#####2 | 52/100 [09:10<08:33, 10.70s/trial, best loss: -0.75]
53%|#####3 | 53/100 [09:18<07:49, 10.00s/trial, best loss: -0.75]
54%|#####4 | 54/100 [09:29<07:47, 10.17s/trial, best loss: -0.75]
55%|#####5 | 55/100 [09:38<07:24, 9.88s/trial, best loss: -0.75]
56%|#####6 | 56/100 [09:48<07:22, 10.05s/trial, best loss: -0.75]
57%|#####6 | 57/100 [09:58<07:02, 9.83s/trial, best loss: -0.75]
58%|#####8 | 58/100 [10:06<06:33, 9.37s/trial, best loss: -0.75]
59%|#####8 | 59/100 [10:14<06:09, 9.01s/trial, best loss: -0.75]
60%|###### | 60/100 [10:23<05:57, 8.93s/trial, best loss: -0.75]
61%|######1 | 61/100 [10:31<05:44, 8.84s/trial, best loss: -0.75]
62%|######2 | 62/100 [10:41<05:49, 9.20s/trial, best loss: -0.75]
63%|######3 | 63/100 [10:52<05:52, 9.54s/trial, best loss: -0.75]
64%|######4 | 64/100 [11:01<05:35, 9.31s/trial, best loss: -0.75]
65%|######5 | 65/100 [11:11<05:41, 9.76s/trial, best loss: -0.75]
66%|######6 | 66/100 [11:24<06:02, 10.66s/trial, best loss: -0.75]
67%|######7 | 67/100 [11:37<06:09, 11.19s/trial, best loss: -0.75]
68%|######8 | 68/100 [11:47<05:53, 11.04s/trial, best loss: -0.75]
69%|######9 | 69/100 [12:00<05:58, 11.55s/trial, best loss: -0.75]
70%|####### | 70/100 [12:13<05:57, 11.91s/trial, best loss: -0.75]
71%|#######1 | 71/100 [12:25<05:49, 12.07s/trial, best loss: -0.75]
72%|#######2 | 72/100 [12:36<05:25, 11.64s/trial, best loss: -0.75]
73%|#######3 | 73/100 [12:46<04:58, 11.05s/trial, best loss: -0.75]
74%|#######4 | 74/100 [12:54<04:28, 10.32s/trial, best loss: -0.75]
75%|#######5 | 75/100 [13:07<04:33, 10.94s/trial, best loss: -0.75]
76%|#######6 | 76/100 [13:17<04:19, 10.80s/trial, best loss: -0.75]
77%|#######7 | 77/100 [13:27<04:02, 10.55s/trial, best loss: -0.75]
78%|#######8 | 78/100 [13:40<04:11, 11.44s/trial, best loss: -0.75]
79%|#######9 | 79/100 [13:50<03:46, 10.77s/trial, best loss: -0.75]
80%|######## | 80/100 [13:59<03:28, 10.43s/trial, best loss: -0.75]
81%|########1 | 81/100 [14:11<03:25, 10.79s/trial, best loss: -0.75]
82%|########2 | 82/100 [14:20<03:04, 10.27s/trial, best loss: -0.75]
83%|########2 | 83/100 [14:28<02:45, 9.74s/trial, best loss: -0.75]
84%|########4 | 84/100 [14:39<02:39, 9.99s/trial, best loss: -0.75]
85%|########5 | 85/100 [14:48<02:23, 9.60s/trial, best loss: -0.75]
86%|########6 | 86/100 [14:57<02:11, 9.37s/trial, best loss: -0.75]
87%|########7 | 87/100 [15:06<02:03, 9.47s/trial, best loss: -0.75]
88%|########8 | 88/100 [15:15<01:52, 9.37s/trial, best loss: -0.75]
89%|########9 | 89/100 [15:27<01:48, 9.88s/trial, best loss: -0.75]
90%|######### | 90/100 [15:38<01:44, 10.40s/trial, best loss: -0.75]
91%|#########1| 91/100 [15:46<01:27, 9.69s/trial, best loss: -0.75]
92%|#########2| 92/100 [15:58<01:22, 10.36s/trial, best loss: -0.75]
93%|#########3| 93/100 [16:09<01:13, 10.47s/trial, best loss: -0.75]
94%|#########3| 94/100 [16:18<01:01, 10.21s/trial, best loss: -0.75]
95%|#########5| 95/100 [16:30<00:52, 10.48s/trial, best loss: -0.75]
96%|#########6| 96/100 [16:40<00:41, 10.44s/trial, best loss: -0.75]
97%|#########7| 97/100 [16:51<00:31, 10.63s/trial, best loss: -0.75]
98%|#########8| 98/100 [17:04<00:22, 11.26s/trial, best loss: -0.75]
99%|#########9| 99/100 [17:15<00:11, 11.33s/trial, best loss: -0.75]
100%|##########| 100/100 [17:27<00:00, 11.58s/trial, best loss: -0.75]
100%|##########| 100/100 [17:27<00:00, 10.48s/trial, best loss: -0.75]
print("Best hyperparameters:", best)
Best hyperparameters: {'max_depth': 11, 'min_samples_leaf': 1, 'min_samples_split': 0, 'n_estimators': 64}
4.5 Principal Component Analysis (PCA)
Principal Component Analysis (PCA) is a technique used to emphasize variation and bring out strong patterns in a dataset. It’s often used to make data easy to explore and visualize. PCA can also be used for dimensionality reduction by identifying a smaller number of uncorrelated variables, known as principal components, from a large set of data.
The goal of PCA is to identify the axes (principal components) that maximize the variance in the data. Here’s how PCA works mathematically:
Standardization: The first step is to standardize the range of the continuous initial variables so that each one of them contributes equally to the analysis.
Covariance Matrix Computation: The next step is to compute the covariance matrix of the data. The covariance matrix expresses the correlation between the different variables in the dataset. For a dataset with \(n\) variables, the covariance matrix is a \(n \times n\) matrix given by:
\[ \Sigma = \begin{bmatrix} \sigma^2_1 & \sigma_{12} & \cdots & \sigma_{1n} \\ \sigma_{21} & \sigma^2_2 & \cdots & \sigma_{2n} \\ \vdots & \vdots & \ddots & \vdots \\ \sigma_{n1} & \sigma_{n2} & \cdots & \sigma^2_n \end{bmatrix} \]
where \(\sigma^2_i\) is the variance of the \(i^{th}\) variable and \(\sigma_{ij}\) is the covariance between the \(i^{th}\) and \(j^{th}\) variables.
Eigenvalue Decomposition: The covariance matrix is then decomposed into its eigenvectors and eigenvalues. The eigenvectors represent the directions or components for the reduced subspace of the feature space, while the eigenvalues represent the magnitude of those directions. In PCA, the eigenvectors are called principal components.
Selecting Principal Components: The eigenvectors are sorted by their eigenvalues in decreasing order to rank the corresponding eigenvalues by their explained variance. The idea is to select the top \(k\) eigenvectors that capture the most variance in the data, where \(k\) is the number of dimensions that we want to keep.
Projection Onto the New Feature Space: The final step is to project the original data onto the new subspace of dimension \(k\) that we chose. This is done by multiplying the original data matrix by the matrix containing the top \(k\) eigenvectors.
The mathematical representation of the projection is given by:
\[ Y = X \times P \]
where \(X\) is the original data matrix with \(n\) columns (features), and \(P\) is the matrix with the top \(k\) eigenvectors (principal components) as its columns. \(Y\) is the matrix of the transformed data with respect to the principal components.
In our case, we will use PCA for dimensionality reduction.
def pca_objective(params):
= params['n_components']
n_components = params['n_estimators']
n_estimators = params['max_depth']
max_depth = params['min_samples_split']
min_samples_split = params['min_samples_leaf']
min_samples_leaf
= RandomForestClassifier(
clf =n_estimators,
n_estimators=max_depth,
max_depth=min_samples_split,
min_samples_split=min_samples_leaf,
min_samples_leaf=42
random_state
)=0
final_scorefor i in range(0,20):
= train_test_split(x, y, test_size=0.3, random_state=10)
x_train, x_val, y_train, y_val = StandardScaler()
scaler = scaler.fit_transform(x_train)
x_train_scaled = scaler.transform(x_val)
x_val_scaled
= PCA(n_components=n_components)
pca = pca.fit_transform(x_train_scaled)
x_train_pca = pca.transform(x_val_scaled)
x_val_pca
clf.fit(x_train_pca, y_train)= clf.predict(x_val_pca)
y_pred ='micro'
parameter=f1_score(y_val, y_pred, average=parameter)
score=final_score+score
final_score=final_score/20
final_score
return -final_score
# Define the search space for hyperparameters
= {
space 'n_components': hp.choice('n_components', range(2, 101)),
'n_estimators': hp.choice('n_estimators', range(10, 101)),
'max_depth': hp.choice('max_depth', range(1, 21)),
'min_samples_split': hp.choice('min_samples_split', range(2, 11)),
'min_samples_leaf': hp.choice('min_samples_leaf', range(1, 11))
}
# Use Tree-structured Parzen Estimator (TPE) as the optimization algorithm
= fmin(fn=objective, space=space, algo=tpe.suggest, max_evals=100) best
0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
1%|1 | 1/100 [00:10<17:04, 10.34s/trial, best loss: -0.4000000000000002]
2%|2 | 2/100 [00:20<16:56, 10.37s/trial, best loss: -0.5]
3%|3 | 3/100 [00:32<17:36, 10.89s/trial, best loss: -0.5999999999999999]
4%|4 | 4/100 [00:44<18:22, 11.49s/trial, best loss: -0.75]
5%|5 | 5/100 [00:55<17:45, 11.22s/trial, best loss: -0.75]
6%|6 | 6/100 [01:04<16:17, 10.40s/trial, best loss: -0.75]
7%|7 | 7/100 [01:14<16:01, 10.34s/trial, best loss: -0.75]
8%|8 | 8/100 [01:22<14:43, 9.61s/trial, best loss: -0.75]
9%|9 | 9/100 [01:30<14:04, 9.28s/trial, best loss: -0.75]
10%|# | 10/100 [01:43<15:15, 10.17s/trial, best loss: -0.75]
11%|#1 | 11/100 [01:53<15:21, 10.35s/trial, best loss: -0.75]
12%|#2 | 12/100 [02:04<15:15, 10.41s/trial, best loss: -0.75]
13%|#3 | 13/100 [02:15<15:10, 10.46s/trial, best loss: -0.75]
14%|#4 | 14/100 [02:24<14:29, 10.11s/trial, best loss: -0.75]
15%|#5 | 15/100 [02:35<14:51, 10.49s/trial, best loss: -0.75]
16%|#6 | 16/100 [02:46<14:41, 10.49s/trial, best loss: -0.75]
17%|#7 | 17/100 [02:54<13:34, 9.81s/trial, best loss: -0.75]
18%|#8 | 18/100 [03:04<13:18, 9.74s/trial, best loss: -0.75]
19%|#9 | 19/100 [03:12<12:29, 9.25s/trial, best loss: -0.75]
20%|## | 20/100 [03:20<12:01, 9.02s/trial, best loss: -0.75]
21%|##1 | 21/100 [03:32<13:08, 9.98s/trial, best loss: -0.75]
22%|##2 | 22/100 [03:45<13:55, 10.71s/trial, best loss: -0.75]
23%|##3 | 23/100 [03:53<12:51, 10.01s/trial, best loss: -0.75]
24%|##4 | 24/100 [04:06<13:51, 10.94s/trial, best loss: -0.75]
25%|##5 | 25/100 [04:21<14:59, 12.00s/trial, best loss: -0.75]
26%|##6 | 26/100 [04:29<13:30, 10.95s/trial, best loss: -0.75]
27%|##7 | 27/100 [04:41<13:31, 11.12s/trial, best loss: -0.75]
28%|##8 | 28/100 [04:54<14:10, 11.81s/trial, best loss: -0.75]
29%|##9 | 29/100 [05:04<13:13, 11.18s/trial, best loss: -0.75]
30%|### | 30/100 [05:15<13:07, 11.25s/trial, best loss: -0.75]
31%|###1 | 31/100 [05:29<13:46, 11.97s/trial, best loss: -0.75]
32%|###2 | 32/100 [05:42<13:52, 12.25s/trial, best loss: -0.75]
33%|###3 | 33/100 [05:52<12:57, 11.61s/trial, best loss: -0.75]
34%|###4 | 34/100 [06:00<11:33, 10.50s/trial, best loss: -0.75]
35%|###5 | 35/100 [06:12<12:04, 11.15s/trial, best loss: -0.75]
36%|###6 | 36/100 [06:24<11:54, 11.16s/trial, best loss: -0.75]
37%|###7 | 37/100 [06:32<10:57, 10.44s/trial, best loss: -0.75]
38%|###8 | 38/100 [06:41<10:08, 9.81s/trial, best loss: -0.75]
39%|###9 | 39/100 [06:50<09:49, 9.67s/trial, best loss: -0.75]
40%|#### | 40/100 [07:00<09:42, 9.70s/trial, best loss: -0.75]
41%|####1 | 41/100 [07:10<09:31, 9.68s/trial, best loss: -0.75]
42%|####2 | 42/100 [07:18<09:03, 9.37s/trial, best loss: -0.75]
43%|####3 | 43/100 [07:29<09:11, 9.67s/trial, best loss: -0.75]
44%|####4 | 44/100 [07:40<09:32, 10.22s/trial, best loss: -0.75]
45%|####5 | 45/100 [07:50<09:21, 10.21s/trial, best loss: -0.75]
46%|####6 | 46/100 [07:59<08:46, 9.75s/trial, best loss: -0.75]
47%|####6 | 47/100 [08:08<08:22, 9.49s/trial, best loss: -0.75]
48%|####8 | 48/100 [08:16<07:55, 9.14s/trial, best loss: -0.75]
49%|####9 | 49/100 [08:28<08:25, 9.92s/trial, best loss: -0.75]
50%|##### | 50/100 [08:37<07:58, 9.58s/trial, best loss: -0.75]
51%|#####1 | 51/100 [08:50<08:41, 10.65s/trial, best loss: -0.75]
52%|#####2 | 52/100 [09:00<08:23, 10.50s/trial, best loss: -0.75]
53%|#####3 | 53/100 [09:10<08:09, 10.41s/trial, best loss: -0.75]
54%|#####4 | 54/100 [09:21<08:01, 10.47s/trial, best loss: -0.75]
55%|#####5 | 55/100 [09:29<07:17, 9.72s/trial, best loss: -0.75]
56%|#####6 | 56/100 [09:41<07:41, 10.49s/trial, best loss: -0.75]
57%|#####6 | 57/100 [09:51<07:21, 10.28s/trial, best loss: -0.75]
58%|#####8 | 58/100 [10:01<07:06, 10.16s/trial, best loss: -0.75]
59%|#####8 | 59/100 [10:13<07:23, 10.81s/trial, best loss: -0.75]
60%|###### | 60/100 [10:22<06:53, 10.33s/trial, best loss: -0.75]
61%|######1 | 61/100 [10:36<07:28, 11.50s/trial, best loss: -0.75]
62%|######2 | 62/100 [10:48<07:15, 11.46s/trial, best loss: -0.75]
63%|######3 | 63/100 [10:58<06:53, 11.18s/trial, best loss: -0.75]
64%|######4 | 64/100 [11:11<06:58, 11.64s/trial, best loss: -0.75]
65%|######5 | 65/100 [11:20<06:23, 10.94s/trial, best loss: -0.75]
66%|######6 | 66/100 [11:33<06:31, 11.50s/trial, best loss: -0.75]
67%|######7 | 67/100 [11:43<06:06, 11.11s/trial, best loss: -0.75]
68%|######8 | 68/100 [11:55<06:01, 11.31s/trial, best loss: -0.75]
69%|######9 | 69/100 [12:08<06:09, 11.92s/trial, best loss: -0.75]
70%|####### | 70/100 [12:22<06:12, 12.42s/trial, best loss: -0.75]
71%|#######1 | 71/100 [12:33<05:44, 11.89s/trial, best loss: -0.75]
72%|#######2 | 72/100 [12:43<05:18, 11.39s/trial, best loss: -0.75]
73%|#######3 | 73/100 [12:53<04:58, 11.05s/trial, best loss: -0.75]
74%|#######4 | 74/100 [13:03<04:33, 10.53s/trial, best loss: -0.75]
75%|#######5 | 75/100 [13:10<04:04, 9.76s/trial, best loss: -0.75]
76%|#######6 | 76/100 [13:24<04:19, 10.83s/trial, best loss: -0.75]
77%|#######7 | 77/100 [13:36<04:21, 11.39s/trial, best loss: -0.75]
78%|#######8 | 78/100 [13:51<04:30, 12.32s/trial, best loss: -0.75]
79%|#######9 | 79/100 [14:03<04:16, 12.20s/trial, best loss: -0.75]
80%|######## | 80/100 [14:15<04:03, 12.15s/trial, best loss: -0.75]
81%|########1 | 81/100 [14:26<03:45, 11.85s/trial, best loss: -0.75]
82%|########2 | 82/100 [14:37<03:26, 11.49s/trial, best loss: -0.75]
83%|########2 | 83/100 [14:48<03:14, 11.46s/trial, best loss: -0.75]
84%|########4 | 84/100 [15:01<03:09, 11.82s/trial, best loss: -0.75]
85%|########5 | 85/100 [15:15<03:06, 12.41s/trial, best loss: -0.75]
86%|########6 | 86/100 [15:28<02:58, 12.77s/trial, best loss: -0.75]
87%|########7 | 87/100 [15:37<02:30, 11.55s/trial, best loss: -0.75]
88%|########8 | 88/100 [15:46<02:09, 10.77s/trial, best loss: -0.75]
89%|########9 | 89/100 [15:57<01:59, 10.84s/trial, best loss: -0.75]
90%|######### | 90/100 [16:06<01:43, 10.35s/trial, best loss: -0.75]
91%|#########1| 91/100 [16:15<01:30, 10.08s/trial, best loss: -0.75]
92%|#########2| 92/100 [16:31<01:34, 11.76s/trial, best loss: -0.75]
93%|#########3| 93/100 [16:42<01:21, 11.62s/trial, best loss: -0.75]
94%|#########3| 94/100 [16:52<01:06, 11.08s/trial, best loss: -0.75]
95%|#########5| 95/100 [17:06<00:59, 11.93s/trial, best loss: -0.75]
96%|#########6| 96/100 [17:24<00:54, 13.64s/trial, best loss: -0.75]
97%|#########7| 97/100 [17:37<00:40, 13.57s/trial, best loss: -0.75]
98%|#########8| 98/100 [17:51<00:27, 13.56s/trial, best loss: -0.75]
99%|#########9| 99/100 [18:00<00:12, 12.25s/trial, best loss: -0.75]
100%|##########| 100/100 [18:11<00:00, 11.87s/trial, best loss: -0.75]
100%|##########| 100/100 [18:11<00:00, 10.91s/trial, best loss: -0.75]
print("Best hyperparameters:", best)
Best hyperparameters: {'max_depth': 6, 'min_samples_leaf': 1, 'min_samples_split': 2, 'n_components': 41, 'n_estimators': 70}
As it is obvious, we do not get any better results with the use of PCA.
4.6 Neural Networks
Neural Networks are computational models inspired by the human brain’s structure and function. They are composed of nodes, or “neurons,” organized in layers: an input layer, one or more hidden layers, and an output layer. Neural networks are particularly powerful in capturing complex patterns and relationships in data, making them highly effective for a wide range of machine learning tasks, including classification, regression, and feature learning.
The mathematical operation in each neuron involves weighted inputs, a bias term, and an activation function. For a given neuron, the process can be described as follows:
Calculate weighted sum of inputs: The input values \(x_i\) are multiplied by their corresponding weights \(w_i\) and summed up along with a bias term \(b\):
\[ z = \sum_{i}(w_i \cdot x_i) + b \]
Apply an activation function: The activation function \(\phi\) is applied to the weighted sum to introduce non-linearity, allowing the network to learn complex patterns:
\[ a = \phi(z) \]
Common activation functions include Sigmoid, ReLU (Rectified Linear Unit), and Tanh.
The network learns by adjusting the weights and biases to minimize the difference between the actual output and the predicted output. This process is known as backpropagation, where the error is propagated back through the network, allowing the weights to be updated via gradient descent or other optimization algorithms.
In mathematical terms, the objective is to minimize the loss function, which measures the difference between the actual and predicted outputs. For a set of training examples, the goal is to find the set of weights and biases that minimize this loss function.
= train_test_split(x, y, test_size=0.3, random_state=10)
x_train, x_test, y_train, y_test = train_test_split(x_train, y_train, test_size=0.3, random_state=10)
x_train, x_val, y_train, y_val # Define the model
= Sequential([
model 64, activation='relu', input_shape=(18703,)),
Dense(32, activation='relu'),
Dense(7, activation='softmax')
Dense(
])
# Compile the model
compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.
# Train the model
=100, batch_size=2, validation_data=(x_val, y_val), verbose=2) model.fit(x_train, y_train, epochs
Epoch 1/100
16/16 - 1s - 62ms/step - accuracy: 0.2812 - loss: 30.5104 - val_accuracy: 0.2143 - val_loss: 20.8323
Epoch 2/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 16.6631 - val_accuracy: 0.2143 - val_loss: 22.1152
Epoch 3/100
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 18.3124 - val_accuracy: 0.0714 - val_loss: 18.1703
Epoch 4/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 8.4460 - val_accuracy: 0.2143 - val_loss: 8.4616
Epoch 5/100
16/16 - 0s - 12ms/step - accuracy: 0.0625 - loss: 5.9877 - val_accuracy: 0.1429 - val_loss: 4.5860
Epoch 6/100
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 4.4411 - val_accuracy: 0.2143 - val_loss: 4.0520
Epoch 7/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 3.7566 - val_accuracy: 0.2143 - val_loss: 5.5674
Epoch 8/100
16/16 - 0s - 12ms/step - accuracy: 0.0938 - loss: 6.1763 - val_accuracy: 0.2143 - val_loss: 4.2611
Epoch 9/100
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 3.2876 - val_accuracy: 0.1429 - val_loss: 2.9167
Epoch 10/100
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 6.9382 - val_accuracy: 0.1429 - val_loss: 6.2733
Epoch 11/100
16/16 - 0s - 12ms/step - accuracy: 0.0938 - loss: 5.9460 - val_accuracy: 0.2143 - val_loss: 6.4630
Epoch 12/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 3.4044 - val_accuracy: 0.0714 - val_loss: 4.5348
Epoch 13/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 4.3773 - val_accuracy: 0.2143 - val_loss: 5.5014
Epoch 14/100
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 4.7496 - val_accuracy: 0.0714 - val_loss: 4.5597
Epoch 15/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 3.3272 - val_accuracy: 0.2857 - val_loss: 2.6075
Epoch 16/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 3.1101 - val_accuracy: 0.1429 - val_loss: 4.4122
Epoch 17/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 3.7322 - val_accuracy: 0.2857 - val_loss: 7.3007
Epoch 18/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 3.7460 - val_accuracy: 0.0714 - val_loss: 3.0032
Epoch 19/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 2.6649 - val_accuracy: 0.1429 - val_loss: 4.0252
Epoch 20/100
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 2.3026 - val_accuracy: 0.2143 - val_loss: 2.2899
Epoch 21/100
16/16 - 0s - 13ms/step - accuracy: 0.2812 - loss: 1.8681 - val_accuracy: 0.0714 - val_loss: 2.7269
Epoch 22/100
16/16 - 0s - 13ms/step - accuracy: 0.1562 - loss: 3.0049 - val_accuracy: 0.0714 - val_loss: 3.1133
Epoch 23/100
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 2.3959 - val_accuracy: 0.1429 - val_loss: 2.8942
Epoch 24/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 2.7899 - val_accuracy: 0.2143 - val_loss: 2.5015
Epoch 25/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 2.9483 - val_accuracy: 0.1429 - val_loss: 4.3454
Epoch 26/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.5096 - val_accuracy: 0.0714 - val_loss: 2.6469
Epoch 27/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 2.6279 - val_accuracy: 0.1429 - val_loss: 2.4766
Epoch 28/100
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 3.4286 - val_accuracy: 0.0714 - val_loss: 5.5225
Epoch 29/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 4.5089 - val_accuracy: 0.2143 - val_loss: 3.9817
Epoch 30/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 3.8311 - val_accuracy: 0.1429 - val_loss: 4.1533
Epoch 31/100
16/16 - 0s - 13ms/step - accuracy: 0.1875 - loss: 2.9810 - val_accuracy: 0.2143 - val_loss: 4.3358
Epoch 32/100
16/16 - 0s - 13ms/step - accuracy: 0.1562 - loss: 3.8415 - val_accuracy: 0.1429 - val_loss: 4.3705
Epoch 33/100
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 3.8863 - val_accuracy: 0.1429 - val_loss: 5.6584
Epoch 34/100
16/16 - 0s - 13ms/step - accuracy: 0.1562 - loss: 5.2758 - val_accuracy: 0.0000e+00 - val_loss: 4.5720
Epoch 35/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 3.4978 - val_accuracy: 0.2143 - val_loss: 5.5483
Epoch 36/100
16/16 - 0s - 13ms/step - accuracy: 0.1250 - loss: 3.7669 - val_accuracy: 0.2857 - val_loss: 2.9863
Epoch 37/100
16/16 - 0s - 12ms/step - accuracy: 0.0938 - loss: 3.0114 - val_accuracy: 0.1429 - val_loss: 2.7275
Epoch 38/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 2.2240 - val_accuracy: 0.1429 - val_loss: 3.1875
Epoch 39/100
16/16 - 0s - 13ms/step - accuracy: 0.0938 - loss: 5.4158 - val_accuracy: 0.0714 - val_loss: 3.0482
Epoch 40/100
16/16 - 0s - 13ms/step - accuracy: 0.1875 - loss: 3.1231 - val_accuracy: 0.1429 - val_loss: 3.0160
Epoch 41/100
16/16 - 0s - 12ms/step - accuracy: 0.3125 - loss: 2.7868 - val_accuracy: 0.1429 - val_loss: 3.5932
Epoch 42/100
16/16 - 0s - 12ms/step - accuracy: 0.2812 - loss: 2.4301 - val_accuracy: 0.3571 - val_loss: 3.4156
Epoch 43/100
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 3.9719 - val_accuracy: 0.0714 - val_loss: 4.7721
Epoch 44/100
16/16 - 0s - 12ms/step - accuracy: 0.0625 - loss: 2.8362 - val_accuracy: 0.0714 - val_loss: 2.9436
Epoch 45/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.5141 - val_accuracy: 0.0714 - val_loss: 2.6107
Epoch 46/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 2.5626 - val_accuracy: 0.0714 - val_loss: 2.2856
Epoch 47/100
16/16 - 0s - 12ms/step - accuracy: 0.0625 - loss: 2.1904 - val_accuracy: 0.0714 - val_loss: 2.5728
Epoch 48/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.1047 - val_accuracy: 0.1429 - val_loss: 3.2741
Epoch 49/100
16/16 - 0s - 12ms/step - accuracy: 0.2812 - loss: 2.5018 - val_accuracy: 0.0000e+00 - val_loss: 2.5913
Epoch 50/100
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 1.9502 - val_accuracy: 0.1429 - val_loss: 2.8934
Epoch 51/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.1751 - val_accuracy: 0.1429 - val_loss: 2.6396
Epoch 52/100
16/16 - 0s - 12ms/step - accuracy: 0.0312 - loss: 2.2535 - val_accuracy: 0.2143 - val_loss: 2.0851
Epoch 53/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 1.8592 - val_accuracy: 0.0714 - val_loss: 3.0087
Epoch 54/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 2.0935 - val_accuracy: 0.1429 - val_loss: 2.3191
Epoch 55/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.0420 - val_accuracy: 0.2143 - val_loss: 2.5693
Epoch 56/100
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 2.5006 - val_accuracy: 0.0714 - val_loss: 2.4221
Epoch 57/100
16/16 - 0s - 12ms/step - accuracy: 0.0938 - loss: 3.3605 - val_accuracy: 0.1429 - val_loss: 3.2608
Epoch 58/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 4.1793 - val_accuracy: 0.0714 - val_loss: 3.2394
Epoch 59/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 2.4653 - val_accuracy: 0.1429 - val_loss: 2.9773
Epoch 60/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 3.1853 - val_accuracy: 0.1429 - val_loss: 3.2672
Epoch 61/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 2.3919 - val_accuracy: 0.0714 - val_loss: 2.1506
Epoch 62/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 2.3205 - val_accuracy: 0.1429 - val_loss: 3.0445
Epoch 63/100
16/16 - 0s - 14ms/step - accuracy: 0.1562 - loss: 3.1270 - val_accuracy: 0.0714 - val_loss: 2.3981
Epoch 64/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.6032 - val_accuracy: 0.2143 - val_loss: 3.1998
Epoch 65/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.1248 - val_accuracy: 0.2143 - val_loss: 3.5750
Epoch 66/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 2.5400 - val_accuracy: 0.2143 - val_loss: 2.0263
Epoch 67/100
16/16 - 0s - 13ms/step - accuracy: 0.1250 - loss: 2.0001 - val_accuracy: 0.4286 - val_loss: 1.9162
Epoch 68/100
16/16 - 0s - 13ms/step - accuracy: 0.1562 - loss: 1.9779 - val_accuracy: 0.1429 - val_loss: 2.6477
Epoch 69/100
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 2.1042 - val_accuracy: 0.0714 - val_loss: 1.9579
Epoch 70/100
16/16 - 0s - 13ms/step - accuracy: 0.1562 - loss: 1.8411 - val_accuracy: 0.3571 - val_loss: 1.9934
Epoch 71/100
16/16 - 0s - 13ms/step - accuracy: 0.2812 - loss: 2.2580 - val_accuracy: 0.2143 - val_loss: 2.8935
Epoch 72/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.1594 - val_accuracy: 0.1429 - val_loss: 2.2144
Epoch 73/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 2.6267 - val_accuracy: 0.2857 - val_loss: 2.7360
Epoch 74/100
16/16 - 0s - 13ms/step - accuracy: 0.3125 - loss: 2.8441 - val_accuracy: 0.0714 - val_loss: 4.1842
Epoch 75/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 3.1956 - val_accuracy: 0.0714 - val_loss: 6.9344
Epoch 76/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 4.4892 - val_accuracy: 0.1429 - val_loss: 5.3279
Epoch 77/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.9246 - val_accuracy: 0.2143 - val_loss: 2.5269
Epoch 78/100
16/16 - 0s - 12ms/step - accuracy: 0.0625 - loss: 3.1195 - val_accuracy: 0.2143 - val_loss: 2.3887
Epoch 79/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 3.8073 - val_accuracy: 0.1429 - val_loss: 2.7933
Epoch 80/100
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 2.8774 - val_accuracy: 0.1429 - val_loss: 4.9416
Epoch 81/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 4.1803 - val_accuracy: 0.0714 - val_loss: 3.1901
Epoch 82/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 3.7331 - val_accuracy: 0.2143 - val_loss: 5.6679
Epoch 83/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 3.5474 - val_accuracy: 0.2857 - val_loss: 2.6773
Epoch 84/100
16/16 - 0s - 13ms/step - accuracy: 0.1875 - loss: 2.1530 - val_accuracy: 0.1429 - val_loss: 2.0150
Epoch 85/100
16/16 - 0s - 12ms/step - accuracy: 0.2812 - loss: 1.8546 - val_accuracy: 0.1429 - val_loss: 2.6262
Epoch 86/100
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 3.1075 - val_accuracy: 0.2143 - val_loss: 3.4946
Epoch 87/100
16/16 - 0s - 12ms/step - accuracy: 0.2812 - loss: 3.1822 - val_accuracy: 0.1429 - val_loss: 2.8123
Epoch 88/100
16/16 - 0s - 14ms/step - accuracy: 0.1562 - loss: 2.3661 - val_accuracy: 0.2143 - val_loss: 2.8486
Epoch 89/100
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 2.2189 - val_accuracy: 0.2143 - val_loss: 1.9729
Epoch 90/100
16/16 - 0s - 12ms/step - accuracy: 0.2812 - loss: 2.0743 - val_accuracy: 0.1429 - val_loss: 2.5119
Epoch 91/100
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 2.3694 - val_accuracy: 0.1429 - val_loss: 1.7529
Epoch 92/100
16/16 - 0s - 12ms/step - accuracy: 0.3125 - loss: 1.6802 - val_accuracy: 0.1429 - val_loss: 1.7654
Epoch 93/100
16/16 - 0s - 12ms/step - accuracy: 0.1875 - loss: 2.2315 - val_accuracy: 0.2143 - val_loss: 1.9735
Epoch 94/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 1.8710 - val_accuracy: 0.2143 - val_loss: 2.8180
Epoch 95/100
16/16 - 0s - 12ms/step - accuracy: 0.3125 - loss: 2.1987 - val_accuracy: 0.1429 - val_loss: 2.1128
Epoch 96/100
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 1.7576 - val_accuracy: 0.5000 - val_loss: 1.7119
Epoch 97/100
16/16 - 0s - 12ms/step - accuracy: 0.1562 - loss: 2.1599 - val_accuracy: 0.2857 - val_loss: 2.7114
Epoch 98/100
16/16 - 0s - 12ms/step - accuracy: 0.3125 - loss: 2.1273 - val_accuracy: 0.2857 - val_loss: 2.2308
Epoch 99/100
16/16 - 0s - 12ms/step - accuracy: 0.2812 - loss: 3.5008 - val_accuracy: 0.2143 - val_loss: 3.7997
Epoch 100/100
16/16 - 0s - 13ms/step - accuracy: 0.0625 - loss: 3.9816 - val_accuracy: 0.1429 - val_loss: 2.9731
<keras.src.callbacks.history.History object at 0x00000274C3D0A9B0>
# Evaluate the model on the test set
= model.evaluate(x_test, y_test) test_loss, test_accuracy
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 118ms/step - accuracy: 0.2500 - loss: 2.7441
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 120ms/step - accuracy: 0.2500 - loss: 2.7441
print(f'Test Accuracy: {test_accuracy * 100:.2f}%')
Test Accuracy: 25.00%
x.head()
A1bg A1cf A2ld1 ... Zyx Zzef1 Zzz3
0 2.826464 4.314649 7.576914 ... 8.163634 7.971203 8.854346
1 4.122122 3.971787 7.145736 ... 8.554566 8.318015 8.197171
2 4.221542 4.014900 8.189553 ... 8.792674 8.044391 8.235345
3 2.995979 4.244164 7.666683 ... 8.274243 8.046331 8.786375
4 4.356665 3.985330 7.536229 ... 8.557591 8.334049 8.121923
[5 rows x 18703 columns]
def neural_network(input_size, n_hidden, hidden_size):
= Input(shape=(input_size,))
input_layer = input_layer
hidden_layer for _ in range(0, n_hidden):
= Dense(hidden_size, activation='relu')(hidden_layer)
hidden_layer = Dense(7, activation='softmax')(hidden_layer)
output_layer
= Model(inputs=input_layer, outputs=output_layer)
model return model
def neural_pca_objective(params):
= params['n_components']
n_components = params['n_hidden']
n_hidden = params['hidden_size']
hidden_size
= train_test_split(x, y, test_size=0.3, random_state=10)
x_train, x_test, y_train, y_test = train_test_split(x_train, y_train, test_size=0.3, random_state=10)
x_train, x_val, y_train, y_val = StandardScaler()
scaler = scaler.fit_transform(x_train)
x_train_scaled = scaler.transform(x_val)
x_val_scaled = scaler.transform(x_test)
x_test_scaled
= PCA(n_components=n_components)
pca = pca.fit_transform(x_train_scaled)
x_train_pca = pca.transform(x_val_scaled)
x_val_pca
=neural_network(n_components, n_hidden, hidden_size)
clfcompile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.=20, batch_size=2, validation_data=(x_val, y_val), verbose=2)
model.fit(x_train, y_train, epochs= model.evaluate(x_test, y_test)
test_loss, test_accuracy
return -test_accuracy
# Define the search space for hyperparameters
= {
space 'n_components': hp.choice('n_components', range(2, 32)),
'n_hidden': hp.choice('n_hidden', range(1, 10)),
'hidden_size': hp.choice('hidden_size', [32, 64, 128, 256, 512, 1024]),
}
# Use Tree-structured Parzen Estimator (TPE) as the optimization algorithm
= fmin(fn=neural_pca_objective, space=space, algo=tpe.suggest, max_evals=100) best
0%| | 0/100 [00:00<?, ?trial/s, best loss=?]
Epoch 1/20
0%| | 0/100 [00:01<?, ?trial/s, best loss=?]
16/16 - 1s - 64ms/step - accuracy: 0.1562 - loss: 3.0255 - val_accuracy: 0.0000e+00 - val_loss: 3.0671
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
Epoch 2/20
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
16/16 - 0s - 13ms/step - accuracy: 0.1875 - loss: 2.5048 - val_accuracy: 0.2143 - val_loss: 2.1047
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
Epoch 3/20
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
16/16 - 0s - 13ms/step - accuracy: 0.2188 - loss: 2.1853 - val_accuracy: 0.1429 - val_loss: 2.2218
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
Epoch 4/20
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
16/16 - 0s - 13ms/step - accuracy: 0.1562 - loss: 3.2800 - val_accuracy: 0.2143 - val_loss: 1.9384
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
Epoch 5/20
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 1.9452 - val_accuracy: 0.2143 - val_loss: 1.9375
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
Epoch 6/20
0%| | 0/100 [00:02<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 1.9404 - val_accuracy: 0.2143 - val_loss: 1.9360
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
Epoch 7/20
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.1250 - loss: 1.9368 - val_accuracy: 0.2143 - val_loss: 1.9344
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
Epoch 8/20
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.2188 - loss: 1.9328 - val_accuracy: 0.1429 - val_loss: 1.9330
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
Epoch 9/20
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.9295 - val_accuracy: 0.1429 - val_loss: 1.9319
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
Epoch 10/20
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.9262 - val_accuracy: 0.1429 - val_loss: 1.9313
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
Epoch 11/20
0%| | 0/100 [00:03<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.9237 - val_accuracy: 0.1429 - val_loss: 1.9306
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
Epoch 12/20
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.9205 - val_accuracy: 0.1429 - val_loss: 1.9298
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
Epoch 13/20
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.9173 - val_accuracy: 0.1429 - val_loss: 1.9292
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
Epoch 14/20
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.9145 - val_accuracy: 0.1429 - val_loss: 1.9282
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
Epoch 15/20
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.9117 - val_accuracy: 0.1429 - val_loss: 1.9278
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
Epoch 16/20
0%| | 0/100 [00:04<?, ?trial/s, best loss=?]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.9088 - val_accuracy: 0.1429 - val_loss: 1.9273
0%| | 0/100 [00:05<?, ?trial/s, best loss=?]
Epoch 17/20
0%| | 0/100 [00:05<?, ?trial/s, best loss=?]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.9063 - val_accuracy: 0.1429 - val_loss: 1.9268
0%| | 0/100 [00:05<?, ?trial/s, best loss=?]
Epoch 18/20
0%| | 0/100 [00:05<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.9036 - val_accuracy: 0.1429 - val_loss: 1.9267
0%| | 0/100 [00:05<?, ?trial/s, best loss=?]
Epoch 19/20
0%| | 0/100 [00:05<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.9012 - val_accuracy: 0.1429 - val_loss: 1.9263
0%| | 0/100 [00:05<?, ?trial/s, best loss=?]
Epoch 20/20
0%| | 0/100 [00:05<?, ?trial/s, best loss=?]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8987 - val_accuracy: 0.1429 - val_loss: 1.9262
0%| | 0/100 [00:05<?, ?trial/s, best loss=?]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 1.9451
0%| | 0/100 [00:06<?, ?trial/s, best loss=?]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 114ms/step - accuracy: 0.1500 - loss: 1.9451
0%| | 0/100 [00:06<?, ?trial/s, best loss=?]
1%|1 | 1/100 [00:06<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 1/20
1%|1 | 1/100 [00:06<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8966 - val_accuracy: 0.1429 - val_loss: 1.9257
1%|1 | 1/100 [00:07<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 2/20
1%|1 | 1/100 [00:07<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8930 - val_accuracy: 0.1429 - val_loss: 1.9255
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 3/20
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8913 - val_accuracy: 0.1429 - val_loss: 1.9259
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 4/20
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8887 - val_accuracy: 0.1429 - val_loss: 1.9259
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 5/20
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8864 - val_accuracy: 0.1429 - val_loss: 1.9258
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 6/20
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8847 - val_accuracy: 0.1429 - val_loss: 1.9258
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 7/20
1%|1 | 1/100 [00:08<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8824 - val_accuracy: 0.1429 - val_loss: 1.9261
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 8/20
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8803 - val_accuracy: 0.1429 - val_loss: 1.9261
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 9/20
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8788 - val_accuracy: 0.1429 - val_loss: 1.9265
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 10/20
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8767 - val_accuracy: 0.1429 - val_loss: 1.9267
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 11/20
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8754 - val_accuracy: 0.1429 - val_loss: 1.9268
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 12/20
1%|1 | 1/100 [00:09<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8730 - val_accuracy: 0.1429 - val_loss: 1.9275
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 13/20
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8714 - val_accuracy: 0.1429 - val_loss: 1.9277
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 14/20
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8699 - val_accuracy: 0.1429 - val_loss: 1.9281
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 15/20
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8684 - val_accuracy: 0.1429 - val_loss: 1.9289
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 16/20
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8664 - val_accuracy: 0.1429 - val_loss: 1.9294
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 17/20
1%|1 | 1/100 [00:10<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8652 - val_accuracy: 0.1429 - val_loss: 1.9295
1%|1 | 1/100 [00:11<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 18/20
1%|1 | 1/100 [00:11<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8631 - val_accuracy: 0.1429 - val_loss: 1.9301
1%|1 | 1/100 [00:11<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 19/20
1%|1 | 1/100 [00:11<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8619 - val_accuracy: 0.1429 - val_loss: 1.9309
1%|1 | 1/100 [00:11<10:01, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 20/20
1%|1 | 1/100 [00:11<10:01, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8609 - val_accuracy: 0.1429 - val_loss: 1.9317
1%|1 | 1/100 [00:11<10:01, 6.08s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 121ms/step - accuracy: 0.1500 - loss: 1.9601
1%|1 | 1/100 [00:11<10:01, 6.08s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 125ms/step - accuracy: 0.1500 - loss: 1.9601
1%|1 | 1/100 [00:11<10:01, 6.08s/trial, best loss: -0.15000000596046448]
2%|2 | 2/100 [00:11<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 1/20
2%|2 | 2/100 [00:12<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 76ms/step - accuracy: 0.2500 - loss: 1.8600 - val_accuracy: 0.1429 - val_loss: 1.9336
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 2/20
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8576 - val_accuracy: 0.1429 - val_loss: 1.9340
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 3/20
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8571 - val_accuracy: 0.1429 - val_loss: 1.9340
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 4/20
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8555 - val_accuracy: 0.1429 - val_loss: 1.9354
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 5/20
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8542 - val_accuracy: 0.1429 - val_loss: 1.9358
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 6/20
2%|2 | 2/100 [00:14<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8532 - val_accuracy: 0.1429 - val_loss: 1.9364
2%|2 | 2/100 [00:15<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 7/20
2%|2 | 2/100 [00:15<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8527 - val_accuracy: 0.1429 - val_loss: 1.9371
2%|2 | 2/100 [00:15<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 8/20
2%|2 | 2/100 [00:15<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8511 - val_accuracy: 0.1429 - val_loss: 1.9381
2%|2 | 2/100 [00:15<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 9/20
2%|2 | 2/100 [00:15<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8503 - val_accuracy: 0.1429 - val_loss: 1.9390
2%|2 | 2/100 [00:15<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 10/20
2%|2 | 2/100 [00:15<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8490 - val_accuracy: 0.1429 - val_loss: 1.9399
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 11/20
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8484 - val_accuracy: 0.1429 - val_loss: 1.9407
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 12/20
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8474 - val_accuracy: 0.1429 - val_loss: 1.9407
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 13/20
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8464 - val_accuracy: 0.1429 - val_loss: 1.9417
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 14/20
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8458 - val_accuracy: 0.1429 - val_loss: 1.9431
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 15/20
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8452 - val_accuracy: 0.1429 - val_loss: 1.9443
2%|2 | 2/100 [00:16<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 16/20
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8441 - val_accuracy: 0.1429 - val_loss: 1.9446
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 17/20
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8436 - val_accuracy: 0.1429 - val_loss: 1.9456
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 18/20
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8429 - val_accuracy: 0.1429 - val_loss: 1.9468
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 19/20
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8421 - val_accuracy: 0.1429 - val_loss: 1.9472
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
Epoch 20/20
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8414 - val_accuracy: 0.1429 - val_loss: 1.9481
2%|2 | 2/100 [00:17<09:37, 5.90s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 1.9807
2%|2 | 2/100 [00:18<09:37, 5.90s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 1.9807
2%|2 | 2/100 [00:18<09:37, 5.90s/trial, best loss: -0.15000000596046448]
3%|3 | 3/100 [00:18<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 1/20
3%|3 | 3/100 [00:19<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 68ms/step - accuracy: 0.2500 - loss: 1.8417 - val_accuracy: 0.1429 - val_loss: 1.9488
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 2/20
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8408 - val_accuracy: 0.1429 - val_loss: 1.9498
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 3/20
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8402 - val_accuracy: 0.1429 - val_loss: 1.9510
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 4/20
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8395 - val_accuracy: 0.1429 - val_loss: 1.9512
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 5/20
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8389 - val_accuracy: 0.1429 - val_loss: 1.9516
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 6/20
3%|3 | 3/100 [00:20<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8388 - val_accuracy: 0.1429 - val_loss: 1.9531
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 7/20
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8378 - val_accuracy: 0.1429 - val_loss: 1.9537
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 8/20
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8376 - val_accuracy: 0.1429 - val_loss: 1.9549
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 9/20
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8369 - val_accuracy: 0.1429 - val_loss: 1.9556
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 10/20
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8367 - val_accuracy: 0.1429 - val_loss: 1.9559
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 11/20
3%|3 | 3/100 [00:21<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8365 - val_accuracy: 0.1429 - val_loss: 1.9570
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 12/20
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8357 - val_accuracy: 0.1429 - val_loss: 1.9573
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 13/20
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8356 - val_accuracy: 0.1429 - val_loss: 1.9584
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 14/20
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8353 - val_accuracy: 0.1429 - val_loss: 1.9592
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 15/20
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8346 - val_accuracy: 0.1429 - val_loss: 1.9596
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 16/20
3%|3 | 3/100 [00:22<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8347 - val_accuracy: 0.1429 - val_loss: 1.9609
3%|3 | 3/100 [00:23<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 17/20
3%|3 | 3/100 [00:23<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8341 - val_accuracy: 0.1429 - val_loss: 1.9609
3%|3 | 3/100 [00:23<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 18/20
3%|3 | 3/100 [00:23<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8337 - val_accuracy: 0.1429 - val_loss: 1.9620
3%|3 | 3/100 [00:23<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 19/20
3%|3 | 3/100 [00:23<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8337 - val_accuracy: 0.1429 - val_loss: 1.9628
3%|3 | 3/100 [00:23<09:49, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 20/20
3%|3 | 3/100 [00:23<09:49, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8333 - val_accuracy: 0.1429 - val_loss: 1.9635
3%|3 | 3/100 [00:23<09:49, 6.08s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 1.9993
3%|3 | 3/100 [00:24<09:49, 6.08s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 114ms/step - accuracy: 0.1500 - loss: 1.9993
3%|3 | 3/100 [00:24<09:49, 6.08s/trial, best loss: -0.15000000596046448]
4%|4 | 4/100 [00:24<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 1/20
4%|4 | 4/100 [00:24<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8345 - val_accuracy: 0.1429 - val_loss: 1.9658
4%|4 | 4/100 [00:25<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 2/20
4%|4 | 4/100 [00:25<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8325 - val_accuracy: 0.1429 - val_loss: 1.9662
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 3/20
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8323 - val_accuracy: 0.1429 - val_loss: 1.9666
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 4/20
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8323 - val_accuracy: 0.1429 - val_loss: 1.9674
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 5/20
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8319 - val_accuracy: 0.1429 - val_loss: 1.9678
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 6/20
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8320 - val_accuracy: 0.1429 - val_loss: 1.9680
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 7/20
4%|4 | 4/100 [00:26<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8316 - val_accuracy: 0.1429 - val_loss: 1.9688
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 8/20
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8314 - val_accuracy: 0.1429 - val_loss: 1.9694
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 9/20
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8309 - val_accuracy: 0.1429 - val_loss: 1.9701
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 10/20
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8310 - val_accuracy: 0.1429 - val_loss: 1.9701
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 11/20
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8308 - val_accuracy: 0.1429 - val_loss: 1.9709
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 12/20
4%|4 | 4/100 [00:27<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8309 - val_accuracy: 0.1429 - val_loss: 1.9724
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 13/20
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8308 - val_accuracy: 0.1429 - val_loss: 1.9724
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 14/20
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8304 - val_accuracy: 0.1429 - val_loss: 1.9725
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 15/20
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8302 - val_accuracy: 0.1429 - val_loss: 1.9737
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 16/20
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8298 - val_accuracy: 0.1429 - val_loss: 1.9745
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 17/20
4%|4 | 4/100 [00:28<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8301 - val_accuracy: 0.1429 - val_loss: 1.9752
4%|4 | 4/100 [00:29<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 18/20
4%|4 | 4/100 [00:29<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8300 - val_accuracy: 0.1429 - val_loss: 1.9760
4%|4 | 4/100 [00:29<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 19/20
4%|4 | 4/100 [00:29<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8294 - val_accuracy: 0.1429 - val_loss: 1.9765
4%|4 | 4/100 [00:29<09:35, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 20/20
4%|4 | 4/100 [00:29<09:35, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8292 - val_accuracy: 0.1429 - val_loss: 1.9768
4%|4 | 4/100 [00:29<09:35, 6.00s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0132
4%|4 | 4/100 [00:29<09:35, 6.00s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 110ms/step - accuracy: 0.1500 - loss: 2.0132
4%|4 | 4/100 [00:29<09:35, 6.00s/trial, best loss: -0.15000000596046448]
5%|5 | 5/100 [00:29<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 1/20
5%|5 | 5/100 [00:30<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 71ms/step - accuracy: 0.2500 - loss: 1.8305 - val_accuracy: 0.1429 - val_loss: 1.9786
5%|5 | 5/100 [00:31<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 2/20
5%|5 | 5/100 [00:31<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8292 - val_accuracy: 0.1429 - val_loss: 1.9788
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 3/20
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8289 - val_accuracy: 0.1429 - val_loss: 1.9791
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 4/20
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8286 - val_accuracy: 0.1429 - val_loss: 1.9793
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 5/20
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8287 - val_accuracy: 0.1429 - val_loss: 1.9798
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 6/20
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8285 - val_accuracy: 0.1429 - val_loss: 1.9805
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 7/20
5%|5 | 5/100 [00:32<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8284 - val_accuracy: 0.1429 - val_loss: 1.9811
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 8/20
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8281 - val_accuracy: 0.1429 - val_loss: 1.9817
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 9/20
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8280 - val_accuracy: 0.1429 - val_loss: 1.9816
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 10/20
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8279 - val_accuracy: 0.1429 - val_loss: 1.9821
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 11/20
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8283 - val_accuracy: 0.1429 - val_loss: 1.9828
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 12/20
5%|5 | 5/100 [00:33<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8279 - val_accuracy: 0.1429 - val_loss: 1.9826
5%|5 | 5/100 [00:34<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 13/20
5%|5 | 5/100 [00:34<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8279 - val_accuracy: 0.1429 - val_loss: 1.9833
5%|5 | 5/100 [00:34<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 14/20
5%|5 | 5/100 [00:34<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8278 - val_accuracy: 0.1429 - val_loss: 1.9832
5%|5 | 5/100 [00:34<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 15/20
5%|5 | 5/100 [00:34<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8281 - val_accuracy: 0.1429 - val_loss: 1.9847
5%|5 | 5/100 [00:34<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 16/20
5%|5 | 5/100 [00:34<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8277 - val_accuracy: 0.1429 - val_loss: 1.9854
5%|5 | 5/100 [00:35<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 17/20
5%|5 | 5/100 [00:35<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 18ms/step - accuracy: 0.2500 - loss: 1.8277 - val_accuracy: 0.1429 - val_loss: 1.9848
5%|5 | 5/100 [00:35<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 18/20
5%|5 | 5/100 [00:35<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 23ms/step - accuracy: 0.2500 - loss: 1.8276 - val_accuracy: 0.1429 - val_loss: 1.9846
5%|5 | 5/100 [00:35<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 19/20
5%|5 | 5/100 [00:35<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8277 - val_accuracy: 0.1429 - val_loss: 1.9855
5%|5 | 5/100 [00:36<09:24, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 20/20
5%|5 | 5/100 [00:36<09:24, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8281 - val_accuracy: 0.1429 - val_loss: 1.9862
5%|5 | 5/100 [00:36<09:24, 5.94s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 145ms/step - accuracy: 0.1500 - loss: 2.0231
5%|5 | 5/100 [00:36<09:24, 5.94s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 148ms/step - accuracy: 0.1500 - loss: 2.0231
5%|5 | 5/100 [00:36<09:24, 5.94s/trial, best loss: -0.15000000596046448]
6%|6 | 6/100 [00:36<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 1/20
6%|6 | 6/100 [00:37<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 69ms/step - accuracy: 0.2500 - loss: 1.8286 - val_accuracy: 0.1429 - val_loss: 1.9864
6%|6 | 6/100 [00:38<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 2/20
6%|6 | 6/100 [00:38<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8275 - val_accuracy: 0.1429 - val_loss: 1.9865
6%|6 | 6/100 [00:38<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 3/20
6%|6 | 6/100 [00:38<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8269 - val_accuracy: 0.1429 - val_loss: 1.9870
6%|6 | 6/100 [00:38<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 4/20
6%|6 | 6/100 [00:38<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8273 - val_accuracy: 0.1429 - val_loss: 1.9884
6%|6 | 6/100 [00:39<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 5/20
6%|6 | 6/100 [00:39<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8272 - val_accuracy: 0.1429 - val_loss: 1.9884
6%|6 | 6/100 [00:39<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 6/20
6%|6 | 6/100 [00:39<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8269 - val_accuracy: 0.1429 - val_loss: 1.9885
6%|6 | 6/100 [00:39<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 7/20
6%|6 | 6/100 [00:39<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8268 - val_accuracy: 0.1429 - val_loss: 1.9887
6%|6 | 6/100 [00:39<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 8/20
6%|6 | 6/100 [00:39<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8269 - val_accuracy: 0.1429 - val_loss: 1.9882
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 9/20
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8266 - val_accuracy: 0.1429 - val_loss: 1.9882
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 10/20
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8267 - val_accuracy: 0.1429 - val_loss: 1.9887
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 11/20
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8267 - val_accuracy: 0.1429 - val_loss: 1.9896
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 12/20
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8267 - val_accuracy: 0.1429 - val_loss: 1.9898
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 13/20
6%|6 | 6/100 [00:40<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8267 - val_accuracy: 0.1429 - val_loss: 1.9903
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 14/20
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8266 - val_accuracy: 0.1429 - val_loss: 1.9905
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 15/20
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8268 - val_accuracy: 0.1429 - val_loss: 1.9907
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 16/20
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8267 - val_accuracy: 0.1429 - val_loss: 1.9899
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 17/20
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8267 - val_accuracy: 0.1429 - val_loss: 1.9915
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 18/20
6%|6 | 6/100 [00:41<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 1.9910
6%|6 | 6/100 [00:42<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 19/20
6%|6 | 6/100 [00:42<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 1.9914
6%|6 | 6/100 [00:42<09:40, 6.17s/trial, best loss: -0.15000000596046448]
Epoch 20/20
6%|6 | 6/100 [00:42<09:40, 6.17s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 1.9915
6%|6 | 6/100 [00:42<09:40, 6.17s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0279
6%|6 | 6/100 [00:42<09:40, 6.17s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0279
6%|6 | 6/100 [00:42<09:40, 6.17s/trial, best loss: -0.15000000596046448]
7%|7 | 7/100 [00:42<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 1/20
7%|7 | 7/100 [00:43<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8280 - val_accuracy: 0.1429 - val_loss: 1.9905
7%|7 | 7/100 [00:44<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 2/20
7%|7 | 7/100 [00:44<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8262 - val_accuracy: 0.1429 - val_loss: 1.9912
7%|7 | 7/100 [00:44<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 3/20
7%|7 | 7/100 [00:44<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8268 - val_accuracy: 0.1429 - val_loss: 1.9923
7%|7 | 7/100 [00:44<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 4/20
7%|7 | 7/100 [00:44<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 1.9920
7%|7 | 7/100 [00:44<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 5/20
7%|7 | 7/100 [00:44<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 1.9917
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 6/20
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 1.9925
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 7/20
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8262 - val_accuracy: 0.1429 - val_loss: 1.9933
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 8/20
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 1.9922
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 9/20
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8262 - val_accuracy: 0.1429 - val_loss: 1.9930
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 10/20
7%|7 | 7/100 [00:45<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 1.9926
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 11/20
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 1.9929
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 12/20
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8262 - val_accuracy: 0.1429 - val_loss: 1.9935
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 13/20
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 1.9935
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 14/20
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 1.9933
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 15/20
7%|7 | 7/100 [00:46<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 1.9947
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 16/20
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 1.9945
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 17/20
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 1.9937
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 18/20
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 1.9942
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 19/20
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 1.9947
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 20/20
7%|7 | 7/100 [00:47<09:31, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 1.9960
7%|7 | 7/100 [00:48<09:31, 6.15s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 102ms/step - accuracy: 0.1500 - loss: 2.0334
7%|7 | 7/100 [00:48<09:31, 6.15s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0334
7%|7 | 7/100 [00:48<09:31, 6.15s/trial, best loss: -0.15000000596046448]
8%|8 | 8/100 [00:48<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 1/20
8%|8 | 8/100 [00:49<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 65ms/step - accuracy: 0.2500 - loss: 1.8266 - val_accuracy: 0.1429 - val_loss: 1.9950
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 2/20
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 1.9956
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 3/20
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 1.9955
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 4/20
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 1.9952
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 5/20
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 1.9961
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 6/20
8%|8 | 8/100 [00:50<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 1.9967
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 7/20
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 1.9956
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 8/20
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 1.9962
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 9/20
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 1.9966
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 10/20
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 1.9969
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 11/20
8%|8 | 8/100 [00:51<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 1.9970
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 12/20
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 1.9970
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 13/20
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 1.9978
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 14/20
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 1.9972
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 15/20
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 1.9976
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 16/20
8%|8 | 8/100 [00:52<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 1.9979
8%|8 | 8/100 [00:53<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 17/20
8%|8 | 8/100 [00:53<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 1.9982
8%|8 | 8/100 [00:53<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 18/20
8%|8 | 8/100 [00:53<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 1.9970
8%|8 | 8/100 [00:53<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 19/20
8%|8 | 8/100 [00:53<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 1.9987
8%|8 | 8/100 [00:53<09:12, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 20/20
8%|8 | 8/100 [00:53<09:12, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 1.9989
8%|8 | 8/100 [00:53<09:12, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0347
8%|8 | 8/100 [00:54<09:12, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0347
8%|8 | 8/100 [00:54<09:12, 6.01s/trial, best loss: -0.15000000596046448]
9%|9 | 9/100 [00:54<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 1/20
9%|9 | 9/100 [00:55<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 74ms/step - accuracy: 0.2500 - loss: 1.8265 - val_accuracy: 0.1429 - val_loss: 1.9999
9%|9 | 9/100 [00:56<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 2/20
9%|9 | 9/100 [00:56<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0003
9%|9 | 9/100 [00:56<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 3/20
9%|9 | 9/100 [00:56<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0005
9%|9 | 9/100 [00:56<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 4/20
9%|9 | 9/100 [00:56<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0005
9%|9 | 9/100 [00:56<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 5/20
9%|9 | 9/100 [00:56<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0002
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 6/20
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0003
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 7/20
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0002
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 8/20
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0007
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 9/20
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0002
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 10/20
9%|9 | 9/100 [00:57<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0008
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 11/20
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0008
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 12/20
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0007
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 13/20
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0010
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 14/20
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0004
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 15/20
9%|9 | 9/100 [00:58<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0008
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 16/20
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 1.9998
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 17/20
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0003
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 18/20
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0012
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 19/20
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0005
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 20/20
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0011
9%|9 | 9/100 [00:59<08:59, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0355
9%|9 | 9/100 [01:00<08:59, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 109ms/step - accuracy: 0.1500 - loss: 2.0355
9%|9 | 9/100 [01:00<08:59, 5.93s/trial, best loss: -0.15000000596046448]
10%|# | 10/100 [01:00<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 1/20
10%|# | 10/100 [01:01<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 2.0026
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 2/20
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0015
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 3/20
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0022
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 4/20
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0016
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 5/20
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0016
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 6/20
10%|# | 10/100 [01:02<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0022
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 7/20
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0021
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 8/20
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0028
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 9/20
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0028
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 10/20
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0015
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 11/20
10%|# | 10/100 [01:03<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0021
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 12/20
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0022
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 13/20
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0023
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 14/20
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0022
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 15/20
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0027
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 16/20
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0024
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 17/20
10%|# | 10/100 [01:04<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0025
10%|# | 10/100 [01:05<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 18/20
10%|# | 10/100 [01:05<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0024
10%|# | 10/100 [01:05<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 19/20
10%|# | 10/100 [01:05<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0021
10%|# | 10/100 [01:05<08:58, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 20/20
10%|# | 10/100 [01:05<08:58, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0032
10%|# | 10/100 [01:05<08:58, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0367
10%|# | 10/100 [01:05<08:58, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0367
10%|# | 10/100 [01:05<08:58, 5.99s/trial, best loss: -0.15000000596046448]
11%|#1 | 11/100 [01:05<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 1/20
11%|#1 | 11/100 [01:06<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 2.0057
11%|#1 | 11/100 [01:07<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 2/20
11%|#1 | 11/100 [01:07<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0054
11%|#1 | 11/100 [01:07<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 3/20
11%|#1 | 11/100 [01:07<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0058
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 4/20
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0055
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 5/20
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0051
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 6/20
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0047
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 7/20
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0060
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 8/20
11%|#1 | 11/100 [01:08<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0052
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 9/20
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0054
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 10/20
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0052
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 11/20
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0048
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 12/20
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0050
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 13/20
11%|#1 | 11/100 [01:09<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0052
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 14/20
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0044
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 15/20
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0047
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 16/20
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0050
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 17/20
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 17ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0047
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 18/20
11%|#1 | 11/100 [01:10<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0053
11%|#1 | 11/100 [01:11<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 19/20
11%|#1 | 11/100 [01:11<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0056
11%|#1 | 11/100 [01:11<08:46, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 20/20
11%|#1 | 11/100 [01:11<08:46, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0052
11%|#1 | 11/100 [01:11<08:46, 5.92s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 148ms/step - accuracy: 0.1500 - loss: 2.0371
11%|#1 | 11/100 [01:11<08:46, 5.92s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 150ms/step - accuracy: 0.1500 - loss: 2.0371
11%|#1 | 11/100 [01:11<08:46, 5.92s/trial, best loss: -0.15000000596046448]
12%|#2 | 12/100 [01:11<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 1/20
12%|#2 | 12/100 [01:13<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 82ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 2.0072
12%|#2 | 12/100 [01:14<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 2/20
12%|#2 | 12/100 [01:14<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0072
12%|#2 | 12/100 [01:14<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 3/20
12%|#2 | 12/100 [01:14<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
12%|#2 | 12/100 [01:14<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 4/20
12%|#2 | 12/100 [01:14<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0072
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 5/20
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0068
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 6/20
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 7/20
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0066
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 8/20
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0071
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 9/20
12%|#2 | 12/100 [01:15<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 10/20
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0070
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 11/20
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 12/20
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 13/20
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 14/20
12%|#2 | 12/100 [01:16<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0060
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 15/20
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0054
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 16/20
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0058
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 17/20
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 18/20
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0058
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 19/20
12%|#2 | 12/100 [01:17<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0064
12%|#2 | 12/100 [01:18<08:41, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 20/20
12%|#2 | 12/100 [01:18<08:41, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
12%|#2 | 12/100 [01:18<08:41, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 116ms/step - accuracy: 0.1500 - loss: 2.0379
12%|#2 | 12/100 [01:18<08:41, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 118ms/step - accuracy: 0.1500 - loss: 2.0379
12%|#2 | 12/100 [01:18<08:41, 5.93s/trial, best loss: -0.15000000596046448]
13%|#3 | 13/100 [01:18<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 1/20
13%|#3 | 13/100 [01:19<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 64ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0058
13%|#3 | 13/100 [01:20<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 2/20
13%|#3 | 13/100 [01:20<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0056
13%|#3 | 13/100 [01:20<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 3/20
13%|#3 | 13/100 [01:20<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0063
13%|#3 | 13/100 [01:20<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 4/20
13%|#3 | 13/100 [01:20<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 5/20
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0061
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 6/20
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0072
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 7/20
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 8/20
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0054
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 9/20
13%|#3 | 13/100 [01:21<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0056
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 10/20
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0057
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 11/20
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0057
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 12/20
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 13/20
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0049
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 14/20
13%|#3 | 13/100 [01:22<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0054
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 15/20
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0063
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 16/20
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 17/20
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0056
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 18/20
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0053
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 19/20
13%|#3 | 13/100 [01:23<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0054
13%|#3 | 13/100 [01:24<08:55, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 20/20
13%|#3 | 13/100 [01:24<08:55, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0062
13%|#3 | 13/100 [01:24<08:55, 6.15s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 121ms/step - accuracy: 0.1500 - loss: 2.0375
13%|#3 | 13/100 [01:24<08:55, 6.15s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 124ms/step - accuracy: 0.1500 - loss: 2.0375
13%|#3 | 13/100 [01:24<08:55, 6.15s/trial, best loss: -0.15000000596046448]
14%|#4 | 14/100 [01:24<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 1/20
14%|#4 | 14/100 [01:25<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 70ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 2.0089
14%|#4 | 14/100 [01:26<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 2/20
14%|#4 | 14/100 [01:26<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0088
14%|#4 | 14/100 [01:26<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 3/20
14%|#4 | 14/100 [01:26<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0086
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 4/20
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 5/20
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0078
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 6/20
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0079
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 7/20
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0080
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 8/20
14%|#4 | 14/100 [01:27<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0076
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 9/20
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0075
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 10/20
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0078
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 11/20
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0067
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 12/20
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 13/20
14%|#4 | 14/100 [01:28<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 19ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
14%|#4 | 14/100 [01:29<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 14/20
14%|#4 | 14/100 [01:29<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0081
14%|#4 | 14/100 [01:29<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 15/20
14%|#4 | 14/100 [01:29<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0074
14%|#4 | 14/100 [01:29<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 16/20
14%|#4 | 14/100 [01:29<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
14%|#4 | 14/100 [01:29<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 17/20
14%|#4 | 14/100 [01:29<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
14%|#4 | 14/100 [01:30<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 18/20
14%|#4 | 14/100 [01:30<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0061
14%|#4 | 14/100 [01:30<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 19/20
14%|#4 | 14/100 [01:30<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0070
14%|#4 | 14/100 [01:30<08:43, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 20/20
14%|#4 | 14/100 [01:30<08:43, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0060
14%|#4 | 14/100 [01:30<08:43, 6.09s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 2.0373
14%|#4 | 14/100 [01:30<08:43, 6.09s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 114ms/step - accuracy: 0.1500 - loss: 2.0373
14%|#4 | 14/100 [01:30<08:43, 6.09s/trial, best loss: -0.15000000596046448]
15%|#5 | 15/100 [01:30<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 1/20
15%|#5 | 15/100 [01:31<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 66ms/step - accuracy: 0.2500 - loss: 1.8270 - val_accuracy: 0.1429 - val_loss: 2.0094
15%|#5 | 15/100 [01:32<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 2/20
15%|#5 | 15/100 [01:32<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0077
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 3/20
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0085
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 4/20
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0084
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 5/20
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 6/20
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 7/20
15%|#5 | 15/100 [01:33<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0080
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 8/20
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0078
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 9/20
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 10/20
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 11/20
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0075
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 12/20
15%|#5 | 15/100 [01:34<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0069
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 13/20
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 14/20
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 15/20
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0078
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 16/20
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0066
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 17/20
15%|#5 | 15/100 [01:35<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
15%|#5 | 15/100 [01:36<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 18/20
15%|#5 | 15/100 [01:36<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0065
15%|#5 | 15/100 [01:36<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 19/20
15%|#5 | 15/100 [01:36<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
15%|#5 | 15/100 [01:36<08:45, 6.18s/trial, best loss: -0.15000000596046448]
Epoch 20/20
15%|#5 | 15/100 [01:36<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
15%|#5 | 15/100 [01:36<08:45, 6.18s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 160ms/step - accuracy: 0.1500 - loss: 2.0385
15%|#5 | 15/100 [01:36<08:45, 6.18s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 164ms/step - accuracy: 0.1500 - loss: 2.0385
15%|#5 | 15/100 [01:36<08:45, 6.18s/trial, best loss: -0.15000000596046448]
16%|#6 | 16/100 [01:36<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 1/20
16%|#6 | 16/100 [01:37<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 91ms/step - accuracy: 0.2500 - loss: 1.8269 - val_accuracy: 0.1429 - val_loss: 2.0068
16%|#6 | 16/100 [01:39<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 2/20
16%|#6 | 16/100 [01:39<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0075
16%|#6 | 16/100 [01:39<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 3/20
16%|#6 | 16/100 [01:39<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 20ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
16%|#6 | 16/100 [01:39<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 4/20
16%|#6 | 16/100 [01:39<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 5/20
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0079
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 6/20
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0061
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 7/20
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0070
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 8/20
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 9/20
16%|#6 | 16/100 [01:40<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 10/20
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 11/20
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 12/20
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0066
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 13/20
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0065
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 14/20
16%|#6 | 16/100 [01:41<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0069
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 15/20
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 16/20
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0070
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 17/20
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0063
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 18/20
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0055
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 19/20
16%|#6 | 16/100 [01:42<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
16%|#6 | 16/100 [01:43<08:36, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 20/20
16%|#6 | 16/100 [01:43<08:36, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0066
16%|#6 | 16/100 [01:43<08:36, 6.15s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 152ms/step - accuracy: 0.1500 - loss: 2.0369
16%|#6 | 16/100 [01:43<08:36, 6.15s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 156ms/step - accuracy: 0.1500 - loss: 2.0369
16%|#6 | 16/100 [01:43<08:36, 6.15s/trial, best loss: -0.15000000596046448]
17%|#7 | 17/100 [01:43<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 1/20
17%|#7 | 17/100 [01:44<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 67ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 2.0072
17%|#7 | 17/100 [01:45<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 2/20
17%|#7 | 17/100 [01:45<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
17%|#7 | 17/100 [01:45<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 3/20
17%|#7 | 17/100 [01:45<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 4/20
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 5/20
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0062
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 6/20
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0079
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 7/20
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 8/20
17%|#7 | 17/100 [01:46<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 9/20
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 10/20
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 11/20
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0073
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 12/20
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0074
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 13/20
17%|#7 | 17/100 [01:47<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0061
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 14/20
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0074
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 15/20
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 16/20
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 17/20
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 18/20
17%|#7 | 17/100 [01:48<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0067
17%|#7 | 17/100 [01:49<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 19/20
17%|#7 | 17/100 [01:49<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0058
17%|#7 | 17/100 [01:49<08:44, 6.31s/trial, best loss: -0.15000000596046448]
Epoch 20/20
17%|#7 | 17/100 [01:49<08:44, 6.31s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0055
17%|#7 | 17/100 [01:49<08:44, 6.31s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 131ms/step - accuracy: 0.1500 - loss: 2.0353
17%|#7 | 17/100 [01:49<08:44, 6.31s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 133ms/step - accuracy: 0.1500 - loss: 2.0353
17%|#7 | 17/100 [01:49<08:44, 6.31s/trial, best loss: -0.15000000596046448]
18%|#8 | 18/100 [01:49<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 1/20
18%|#8 | 18/100 [01:50<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0069
18%|#8 | 18/100 [01:51<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 2/20
18%|#8 | 18/100 [01:51<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0076
18%|#8 | 18/100 [01:51<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 3/20
18%|#8 | 18/100 [01:51<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0073
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 4/20
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0069
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 5/20
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0063
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 6/20
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 7/20
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 8/20
18%|#8 | 18/100 [01:52<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0063
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 9/20
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0067
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 10/20
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 11/20
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 12/20
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0060
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 13/20
18%|#8 | 18/100 [01:53<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 14/20
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0071
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 15/20
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 16/20
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 17/20
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 18/20
18%|#8 | 18/100 [01:54<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0067
18%|#8 | 18/100 [01:55<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 19/20
18%|#8 | 18/100 [01:55<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0067
18%|#8 | 18/100 [01:55<08:33, 6.26s/trial, best loss: -0.15000000596046448]
Epoch 20/20
18%|#8 | 18/100 [01:55<08:33, 6.26s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0061
18%|#8 | 18/100 [01:55<08:33, 6.26s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0362
18%|#8 | 18/100 [01:55<08:33, 6.26s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0362
18%|#8 | 18/100 [01:55<08:33, 6.26s/trial, best loss: -0.15000000596046448]
19%|#9 | 19/100 [01:55<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 1/20
19%|#9 | 19/100 [01:56<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0090
19%|#9 | 19/100 [01:57<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 2/20
19%|#9 | 19/100 [01:57<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0092
19%|#9 | 19/100 [01:57<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 3/20
19%|#9 | 19/100 [01:57<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0086
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 4/20
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0085
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 5/20
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0088
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 6/20
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0075
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 7/20
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0078
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 8/20
19%|#9 | 19/100 [01:58<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0077
19%|#9 | 19/100 [01:59<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 9/20
19%|#9 | 19/100 [01:59<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 22ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
19%|#9 | 19/100 [01:59<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 10/20
19%|#9 | 19/100 [01:59<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0078
19%|#9 | 19/100 [01:59<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 11/20
19%|#9 | 19/100 [01:59<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0076
19%|#9 | 19/100 [01:59<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 12/20
19%|#9 | 19/100 [01:59<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
19%|#9 | 19/100 [01:59<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 13/20
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0079
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 14/20
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0077
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 15/20
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0080
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 16/20
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0075
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 17/20
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 18/20
19%|#9 | 19/100 [02:00<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0084
19%|#9 | 19/100 [02:01<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 19/20
19%|#9 | 19/100 [02:01<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0078
19%|#9 | 19/100 [02:01<08:17, 6.14s/trial, best loss: -0.15000000596046448]
Epoch 20/20
19%|#9 | 19/100 [02:01<08:17, 6.14s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0066
19%|#9 | 19/100 [02:01<08:17, 6.14s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 121ms/step - accuracy: 0.1500 - loss: 2.0366
19%|#9 | 19/100 [02:01<08:17, 6.14s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 123ms/step - accuracy: 0.1500 - loss: 2.0366
19%|#9 | 19/100 [02:01<08:17, 6.14s/trial, best loss: -0.15000000596046448]
20%|## | 20/100 [02:01<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 1/20
20%|## | 20/100 [02:02<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 67ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0092
20%|## | 20/100 [02:03<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 2/20
20%|## | 20/100 [02:03<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0094
20%|## | 20/100 [02:04<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 3/20
20%|## | 20/100 [02:04<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0084
20%|## | 20/100 [02:04<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 4/20
20%|## | 20/100 [02:04<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0081
20%|## | 20/100 [02:04<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 5/20
20%|## | 20/100 [02:04<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0084
20%|## | 20/100 [02:04<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 6/20
20%|## | 20/100 [02:04<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0083
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 7/20
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0090
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 8/20
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0084
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 9/20
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0084
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 10/20
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0077
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 11/20
20%|## | 20/100 [02:05<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0080
20%|## | 20/100 [02:06<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 12/20
20%|## | 20/100 [02:06<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0081
20%|## | 20/100 [02:06<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 13/20
20%|## | 20/100 [02:06<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0075
20%|## | 20/100 [02:06<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 14/20
20%|## | 20/100 [02:06<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0082
20%|## | 20/100 [02:06<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 15/20
20%|## | 20/100 [02:06<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0075
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 16/20
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 17/20
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 18/20
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0079
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 19/20
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
Epoch 20/20
20%|## | 20/100 [02:07<08:11, 6.15s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
20%|## | 20/100 [02:08<08:11, 6.15s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 137ms/step - accuracy: 0.1500 - loss: 2.0372
20%|## | 20/100 [02:08<08:11, 6.15s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 139ms/step - accuracy: 0.1500 - loss: 2.0372
20%|## | 20/100 [02:08<08:11, 6.15s/trial, best loss: -0.15000000596046448]
21%|##1 | 21/100 [02:08<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 1/20
21%|##1 | 21/100 [02:09<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 65ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0082
21%|##1 | 21/100 [02:10<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 2/20
21%|##1 | 21/100 [02:10<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0075
21%|##1 | 21/100 [02:10<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 3/20
21%|##1 | 21/100 [02:10<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0073
21%|##1 | 21/100 [02:10<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 4/20
21%|##1 | 21/100 [02:10<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0084
21%|##1 | 21/100 [02:10<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 5/20
21%|##1 | 21/100 [02:10<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0079
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 6/20
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0077
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 7/20
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0071
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 8/20
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0070
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 9/20
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 10/20
21%|##1 | 21/100 [02:11<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 11/20
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 12/20
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0073
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 13/20
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 14/20
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 15/20
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0067
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 16/20
21%|##1 | 21/100 [02:12<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0072
21%|##1 | 21/100 [02:13<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 17/20
21%|##1 | 21/100 [02:13<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
21%|##1 | 21/100 [02:13<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 18/20
21%|##1 | 21/100 [02:13<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
21%|##1 | 21/100 [02:13<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 19/20
21%|##1 | 21/100 [02:13<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
21%|##1 | 21/100 [02:13<08:12, 6.24s/trial, best loss: -0.15000000596046448]
Epoch 20/20
21%|##1 | 21/100 [02:13<08:12, 6.24s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0074
21%|##1 | 21/100 [02:13<08:12, 6.24s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 121ms/step - accuracy: 0.1500 - loss: 2.0381
21%|##1 | 21/100 [02:14<08:12, 6.24s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 123ms/step - accuracy: 0.1500 - loss: 2.0381
21%|##1 | 21/100 [02:14<08:12, 6.24s/trial, best loss: -0.15000000596046448]
22%|##2 | 22/100 [02:14<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 1/20
22%|##2 | 22/100 [02:15<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 63ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0106
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 2/20
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0104
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 3/20
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0105
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 4/20
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0101
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 5/20
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0089
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 6/20
22%|##2 | 22/100 [02:16<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0095
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 7/20
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0095
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 8/20
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0097
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 9/20
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0091
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 10/20
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0088
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 11/20
22%|##2 | 22/100 [02:17<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0090
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 12/20
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0090
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 13/20
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0081
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 14/20
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0079
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 15/20
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0075
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 16/20
22%|##2 | 22/100 [02:18<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0088
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 17/20
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0084
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 18/20
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0082
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 19/20
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0083
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 20/20
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0085
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0381
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0381
22%|##2 | 22/100 [02:19<07:58, 6.13s/trial, best loss: -0.15000000596046448]
23%|##3 | 23/100 [02:19<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 1/20
23%|##3 | 23/100 [02:20<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 77ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0090
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 2/20
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0085
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 3/20
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0087
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 4/20
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0090
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 5/20
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0083
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 6/20
23%|##3 | 23/100 [02:22<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0092
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 7/20
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0086
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 8/20
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0092
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 9/20
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0082
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 10/20
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0083
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 11/20
23%|##3 | 23/100 [02:23<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0091
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 12/20
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0092
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 13/20
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0082
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 14/20
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0080
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 15/20
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 16/20
23%|##3 | 23/100 [02:24<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
23%|##3 | 23/100 [02:25<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 17/20
23%|##3 | 23/100 [02:25<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0084
23%|##3 | 23/100 [02:25<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 18/20
23%|##3 | 23/100 [02:25<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0080
23%|##3 | 23/100 [02:25<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 19/20
23%|##3 | 23/100 [02:25<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0079
23%|##3 | 23/100 [02:25<07:45, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 20/20
23%|##3 | 23/100 [02:25<07:45, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0083
23%|##3 | 23/100 [02:25<07:45, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 128ms/step - accuracy: 0.1500 - loss: 2.0370
23%|##3 | 23/100 [02:26<07:45, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 131ms/step - accuracy: 0.1500 - loss: 2.0370
23%|##3 | 23/100 [02:26<07:45, 6.04s/trial, best loss: -0.15000000596046448]
24%|##4 | 24/100 [02:26<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 1/20
24%|##4 | 24/100 [02:26<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 63ms/step - accuracy: 0.2500 - loss: 1.8268 - val_accuracy: 0.1429 - val_loss: 2.0087
24%|##4 | 24/100 [02:27<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 2/20
24%|##4 | 24/100 [02:27<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0082
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 3/20
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0084
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 4/20
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0079
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 5/20
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0079
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 6/20
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0082
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 7/20
24%|##4 | 24/100 [02:28<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0078
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 8/20
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 9/20
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 10/20
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0066
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 11/20
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0069
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 12/20
24%|##4 | 24/100 [02:29<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0077
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 13/20
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 14/20
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0086
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 15/20
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0078
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 16/20
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0078
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 17/20
24%|##4 | 24/100 [02:30<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0062
24%|##4 | 24/100 [02:31<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 18/20
24%|##4 | 24/100 [02:31<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
24%|##4 | 24/100 [02:31<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 19/20
24%|##4 | 24/100 [02:31<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0066
24%|##4 | 24/100 [02:31<07:41, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 20/20
24%|##4 | 24/100 [02:31<07:41, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
24%|##4 | 24/100 [02:31<07:41, 6.07s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0347
24%|##4 | 24/100 [02:31<07:41, 6.07s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0347
24%|##4 | 24/100 [02:31<07:41, 6.07s/trial, best loss: -0.15000000596046448]
25%|##5 | 25/100 [02:31<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 1/20
25%|##5 | 25/100 [02:32<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0061
25%|##5 | 25/100 [02:33<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 2/20
25%|##5 | 25/100 [02:33<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0081
25%|##5 | 25/100 [02:33<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 3/20
25%|##5 | 25/100 [02:33<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0073
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 4/20
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 5/20
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 6/20
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0070
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 7/20
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0065
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 8/20
25%|##5 | 25/100 [02:34<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 9/20
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0067
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 10/20
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0057
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 11/20
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0067
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 12/20
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 13/20
25%|##5 | 25/100 [02:35<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 14/20
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 15/20
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 16/20
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 17/20
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 18/20
25%|##5 | 25/100 [02:36<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
25%|##5 | 25/100 [02:37<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 19/20
25%|##5 | 25/100 [02:37<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
25%|##5 | 25/100 [02:37<07:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 20/20
25%|##5 | 25/100 [02:37<07:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
25%|##5 | 25/100 [02:37<07:29, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 109ms/step - accuracy: 0.1500 - loss: 2.0351
25%|##5 | 25/100 [02:37<07:29, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 111ms/step - accuracy: 0.1500 - loss: 2.0351
25%|##5 | 25/100 [02:37<07:29, 5.99s/trial, best loss: -0.15000000596046448]
26%|##6 | 26/100 [02:37<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 1/20
26%|##6 | 26/100 [02:38<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 64ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 2.0061
26%|##6 | 26/100 [02:39<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 2/20
26%|##6 | 26/100 [02:39<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0062
26%|##6 | 26/100 [02:39<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 3/20
26%|##6 | 26/100 [02:39<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 4/20
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0060
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 5/20
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0073
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 6/20
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0059
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 7/20
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0061
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 8/20
26%|##6 | 26/100 [02:40<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0060
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 9/20
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0052
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 10/20
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0056
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 11/20
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0070
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 12/20
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0052
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 13/20
26%|##6 | 26/100 [02:41<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0051
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 14/20
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0060
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 15/20
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0055
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 16/20
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0054
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 17/20
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 18/20
26%|##6 | 26/100 [02:42<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0051
26%|##6 | 26/100 [02:43<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 19/20
26%|##6 | 26/100 [02:43<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0067
26%|##6 | 26/100 [02:43<07:18, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 20/20
26%|##6 | 26/100 [02:43<07:18, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0060
26%|##6 | 26/100 [02:43<07:18, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0342
26%|##6 | 26/100 [02:43<07:18, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 110ms/step - accuracy: 0.1500 - loss: 2.0342
26%|##6 | 26/100 [02:43<07:18, 5.93s/trial, best loss: -0.15000000596046448]
27%|##7 | 27/100 [02:43<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 1/20
27%|##7 | 27/100 [02:44<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 2.0044
27%|##7 | 27/100 [02:45<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 2/20
27%|##7 | 27/100 [02:45<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0051
27%|##7 | 27/100 [02:45<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 3/20
27%|##7 | 27/100 [02:45<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0046
27%|##7 | 27/100 [02:45<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 4/20
27%|##7 | 27/100 [02:45<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0052
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 5/20
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0060
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 6/20
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 7/20
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0051
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 8/20
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0052
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 9/20
27%|##7 | 27/100 [02:46<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0055
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 10/20
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0051
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 11/20
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0051
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 12/20
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0051
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 13/20
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0047
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 14/20
27%|##7 | 27/100 [02:47<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0055
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 15/20
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0049
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 16/20
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0055
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 17/20
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0053
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 18/20
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0053
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 19/20
27%|##7 | 27/100 [02:48<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0048
27%|##7 | 27/100 [02:49<07:11, 5.91s/trial, best loss: -0.15000000596046448]
Epoch 20/20
27%|##7 | 27/100 [02:49<07:11, 5.91s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0046
27%|##7 | 27/100 [02:49<07:11, 5.91s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 119ms/step - accuracy: 0.1500 - loss: 2.0332
27%|##7 | 27/100 [02:49<07:11, 5.91s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 121ms/step - accuracy: 0.1500 - loss: 2.0332
27%|##7 | 27/100 [02:49<07:11, 5.91s/trial, best loss: -0.15000000596046448]
28%|##8 | 28/100 [02:49<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 1/20
28%|##8 | 28/100 [02:50<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8269 - val_accuracy: 0.1429 - val_loss: 2.0066
28%|##8 | 28/100 [02:51<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 2/20
28%|##8 | 28/100 [02:51<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
28%|##8 | 28/100 [02:51<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 3/20
28%|##8 | 28/100 [02:51<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0055
28%|##8 | 28/100 [02:51<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 4/20
28%|##8 | 28/100 [02:51<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0056
28%|##8 | 28/100 [02:51<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 5/20
28%|##8 | 28/100 [02:51<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0065
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 6/20
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0057
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 7/20
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0054
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 8/20
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0049
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 9/20
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0059
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 10/20
28%|##8 | 28/100 [02:52<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0052
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 11/20
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0059
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 12/20
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0057
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 13/20
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0059
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 14/20
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0063
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 15/20
28%|##8 | 28/100 [02:53<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0057
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 16/20
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0051
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 17/20
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0055
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 18/20
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0056
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 19/20
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0047
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 20/20
28%|##8 | 28/100 [02:54<07:04, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0054
28%|##8 | 28/100 [02:55<07:04, 5.89s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 102ms/step - accuracy: 0.1500 - loss: 2.0363
28%|##8 | 28/100 [02:55<07:04, 5.89s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0363
28%|##8 | 28/100 [02:55<07:04, 5.89s/trial, best loss: -0.15000000596046448]
29%|##9 | 29/100 [02:55<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 1/20
29%|##9 | 29/100 [02:56<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0065
29%|##9 | 29/100 [02:56<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 2/20
29%|##9 | 29/100 [02:56<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0059
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 3/20
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 4/20
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0060
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 5/20
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 6/20
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0061
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 7/20
29%|##9 | 29/100 [02:57<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0069
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 8/20
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 9/20
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0063
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 10/20
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 11/20
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0057
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 12/20
29%|##9 | 29/100 [02:58<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0052
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 13/20
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 14/20
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 15/20
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 16/20
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0065
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 17/20
29%|##9 | 29/100 [02:59<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0057
29%|##9 | 29/100 [03:00<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 18/20
29%|##9 | 29/100 [03:00<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
29%|##9 | 29/100 [03:00<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 19/20
29%|##9 | 29/100 [03:00<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0055
29%|##9 | 29/100 [03:00<06:55, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 20/20
29%|##9 | 29/100 [03:00<06:55, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0057
29%|##9 | 29/100 [03:00<06:55, 5.85s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0367
29%|##9 | 29/100 [03:00<06:55, 5.85s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0367
29%|##9 | 29/100 [03:00<06:55, 5.85s/trial, best loss: -0.15000000596046448]
30%|### | 30/100 [03:00<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 1/20
30%|### | 30/100 [03:01<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 2.0066
30%|### | 30/100 [03:02<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 2/20
30%|### | 30/100 [03:02<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
30%|### | 30/100 [03:02<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 3/20
30%|### | 30/100 [03:02<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0062
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 4/20
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0070
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 5/20
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0066
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 6/20
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 7/20
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 8/20
30%|### | 30/100 [03:03<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 9/20
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0056
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 10/20
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0071
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 11/20
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 12/20
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0062
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 13/20
30%|### | 30/100 [03:04<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0058
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 14/20
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 15/20
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 16/20
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0058
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 17/20
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0051
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 18/20
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0064
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 19/20
30%|### | 30/100 [03:05<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0055
30%|### | 30/100 [03:06<06:45, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 20/20
30%|### | 30/100 [03:06<06:45, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0053
30%|### | 30/100 [03:06<06:45, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0375
30%|### | 30/100 [03:06<06:45, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0375
30%|### | 30/100 [03:06<06:45, 5.79s/trial, best loss: -0.15000000596046448]
31%|###1 | 31/100 [03:06<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 1/20
31%|###1 | 31/100 [03:07<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 59ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0040
31%|###1 | 31/100 [03:08<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 2/20
31%|###1 | 31/100 [03:08<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0049
31%|###1 | 31/100 [03:08<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 3/20
31%|###1 | 31/100 [03:08<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0049
31%|###1 | 31/100 [03:08<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 4/20
31%|###1 | 31/100 [03:08<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0041
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 5/20
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0049
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 6/20
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0052
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 7/20
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0058
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 8/20
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0047
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 9/20
31%|###1 | 31/100 [03:09<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0046
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 10/20
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0052
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 11/20
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0040
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 12/20
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0042
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 13/20
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0041
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 14/20
31%|###1 | 31/100 [03:10<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0047
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 15/20
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0054
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 16/20
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0045
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 17/20
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0045
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 18/20
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0041
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 19/20
31%|###1 | 31/100 [03:11<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0039
31%|###1 | 31/100 [03:12<06:37, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 20/20
31%|###1 | 31/100 [03:12<06:37, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0043
31%|###1 | 31/100 [03:12<06:37, 5.77s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0364
31%|###1 | 31/100 [03:12<06:37, 5.77s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0364
31%|###1 | 31/100 [03:12<06:37, 5.77s/trial, best loss: -0.15000000596046448]
32%|###2 | 32/100 [03:12<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 1/20
32%|###2 | 32/100 [03:13<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 2.0040
32%|###2 | 32/100 [03:14<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 2/20
32%|###2 | 32/100 [03:14<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0044
32%|###2 | 32/100 [03:14<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 3/20
32%|###2 | 32/100 [03:14<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0046
32%|###2 | 32/100 [03:14<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 4/20
32%|###2 | 32/100 [03:14<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0044
32%|###2 | 32/100 [03:14<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 5/20
32%|###2 | 32/100 [03:14<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0041
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 6/20
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0051
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 7/20
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0044
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 8/20
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0043
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 9/20
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0044
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 10/20
32%|###2 | 32/100 [03:15<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0051
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 11/20
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0049
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 12/20
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0050
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 13/20
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0056
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 14/20
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0042
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 15/20
32%|###2 | 32/100 [03:16<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0040
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 16/20
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0044
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 17/20
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0043
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 18/20
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0045
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 19/20
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0050
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
Epoch 20/20
32%|###2 | 32/100 [03:17<06:34, 5.81s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0051
32%|###2 | 32/100 [03:18<06:34, 5.81s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0364
32%|###2 | 32/100 [03:18<06:34, 5.81s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0364
32%|###2 | 32/100 [03:18<06:34, 5.81s/trial, best loss: -0.15000000596046448]
33%|###3 | 33/100 [03:18<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 1/20
33%|###3 | 33/100 [03:19<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0052
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 2/20
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0050
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 3/20
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0057
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 4/20
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0057
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 5/20
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0046
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 6/20
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0046
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 7/20
33%|###3 | 33/100 [03:20<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0040
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 8/20
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0049
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 9/20
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0053
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 10/20
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0050
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 11/20
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0048
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 12/20
33%|###3 | 33/100 [03:21<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0058
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 13/20
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0055
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 14/20
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0050
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 15/20
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0043
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 16/20
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0046
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 17/20
33%|###3 | 33/100 [03:22<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0052
33%|###3 | 33/100 [03:23<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 18/20
33%|###3 | 33/100 [03:23<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0058
33%|###3 | 33/100 [03:23<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 19/20
33%|###3 | 33/100 [03:23<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0049
33%|###3 | 33/100 [03:23<06:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 20/20
33%|###3 | 33/100 [03:23<06:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0057
33%|###3 | 33/100 [03:23<06:28, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 102ms/step - accuracy: 0.1500 - loss: 2.0367
33%|###3 | 33/100 [03:23<06:28, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0367
33%|###3 | 33/100 [03:23<06:28, 5.79s/trial, best loss: -0.15000000596046448]
34%|###4 | 34/100 [03:23<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 1/20
34%|###4 | 34/100 [03:24<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 59ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 2.0076
34%|###4 | 34/100 [03:25<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 2/20
34%|###4 | 34/100 [03:25<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0064
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 3/20
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 4/20
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 5/20
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 6/20
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0064
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 7/20
34%|###4 | 34/100 [03:26<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 8/20
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 9/20
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0074
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 10/20
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0062
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 11/20
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 12/20
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0060
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 13/20
34%|###4 | 34/100 [03:27<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0057
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 14/20
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0057
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 15/20
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 16/20
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0058
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 17/20
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0059
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 18/20
34%|###4 | 34/100 [03:28<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
34%|###4 | 34/100 [03:29<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 19/20
34%|###4 | 34/100 [03:29<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0056
34%|###4 | 34/100 [03:29<06:20, 5.76s/trial, best loss: -0.15000000596046448]
Epoch 20/20
34%|###4 | 34/100 [03:29<06:20, 5.76s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0064
34%|###4 | 34/100 [03:29<06:20, 5.76s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 102ms/step - accuracy: 0.1500 - loss: 2.0372
34%|###4 | 34/100 [03:29<06:20, 5.76s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0372
34%|###4 | 34/100 [03:29<06:20, 5.76s/trial, best loss: -0.15000000596046448]
35%|###5 | 35/100 [03:29<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 1/20
35%|###5 | 35/100 [03:30<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0072
35%|###5 | 35/100 [03:31<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 2/20
35%|###5 | 35/100 [03:31<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0071
35%|###5 | 35/100 [03:31<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 3/20
35%|###5 | 35/100 [03:31<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
35%|###5 | 35/100 [03:31<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 4/20
35%|###5 | 35/100 [03:31<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 5/20
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 6/20
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 7/20
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 8/20
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0053
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 9/20
35%|###5 | 35/100 [03:32<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0055
35%|###5 | 35/100 [03:33<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 10/20
35%|###5 | 35/100 [03:33<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0059
35%|###5 | 35/100 [03:33<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 11/20
35%|###5 | 35/100 [03:33<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
35%|###5 | 35/100 [03:33<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 12/20
35%|###5 | 35/100 [03:33<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0062
35%|###5 | 35/100 [03:33<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 13/20
35%|###5 | 35/100 [03:33<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0056
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 14/20
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 17ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0076
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 15/20
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 16/20
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 17/20
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0057
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 18/20
35%|###5 | 35/100 [03:34<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0059
35%|###5 | 35/100 [03:35<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 19/20
35%|###5 | 35/100 [03:35<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 21ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0059
35%|###5 | 35/100 [03:35<06:15, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 20/20
35%|###5 | 35/100 [03:35<06:15, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0055
35%|###5 | 35/100 [03:35<06:15, 5.78s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 119ms/step - accuracy: 0.1500 - loss: 2.0349
35%|###5 | 35/100 [03:35<06:15, 5.78s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 122ms/step - accuracy: 0.1500 - loss: 2.0349
35%|###5 | 35/100 [03:35<06:15, 5.78s/trial, best loss: -0.15000000596046448]
36%|###6 | 36/100 [03:35<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 1/20
36%|###6 | 36/100 [03:36<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0073
36%|###6 | 36/100 [03:37<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 2/20
36%|###6 | 36/100 [03:37<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0075
36%|###6 | 36/100 [03:37<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 3/20
36%|###6 | 36/100 [03:37<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 4/20
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0067
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 5/20
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 6/20
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0078
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 7/20
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 8/20
36%|###6 | 36/100 [03:38<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0076
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 9/20
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0082
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 10/20
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0080
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 11/20
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0069
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 12/20
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 13/20
36%|###6 | 36/100 [03:39<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 17ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 14/20
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 15/20
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 16/20
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 17/20
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0073
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 18/20
36%|###6 | 36/100 [03:40<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
36%|###6 | 36/100 [03:41<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 19/20
36%|###6 | 36/100 [03:41<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
36%|###6 | 36/100 [03:41<06:16, 5.88s/trial, best loss: -0.15000000596046448]
Epoch 20/20
36%|###6 | 36/100 [03:41<06:16, 5.88s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
36%|###6 | 36/100 [03:41<06:16, 5.88s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 102ms/step - accuracy: 0.1500 - loss: 2.0363
36%|###6 | 36/100 [03:41<06:16, 5.88s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0363
36%|###6 | 36/100 [03:41<06:16, 5.88s/trial, best loss: -0.15000000596046448]
37%|###7 | 37/100 [03:41<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 1/20
37%|###7 | 37/100 [03:42<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0064
37%|###7 | 37/100 [03:43<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 2/20
37%|###7 | 37/100 [03:43<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0061
37%|###7 | 37/100 [03:43<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 3/20
37%|###7 | 37/100 [03:43<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0067
37%|###7 | 37/100 [03:43<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 4/20
37%|###7 | 37/100 [03:43<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0056
37%|###7 | 37/100 [03:44<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 5/20
37%|###7 | 37/100 [03:44<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0063
37%|###7 | 37/100 [03:44<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 6/20
37%|###7 | 37/100 [03:44<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0066
37%|###7 | 37/100 [03:44<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 7/20
37%|###7 | 37/100 [03:44<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
37%|###7 | 37/100 [03:44<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 8/20
37%|###7 | 37/100 [03:44<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 9/20
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0064
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 10/20
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 11/20
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 12/20
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 13/20
37%|###7 | 37/100 [03:45<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 14/20
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0055
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 15/20
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0060
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 16/20
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0054
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 17/20
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 18/20
37%|###7 | 37/100 [03:46<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
37%|###7 | 37/100 [03:47<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 19/20
37%|###7 | 37/100 [03:47<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0057
37%|###7 | 37/100 [03:47<06:10, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 20/20
37%|###7 | 37/100 [03:47<06:10, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
37%|###7 | 37/100 [03:47<06:10, 5.89s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 102ms/step - accuracy: 0.1500 - loss: 2.0373
37%|###7 | 37/100 [03:47<06:10, 5.89s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0373
37%|###7 | 37/100 [03:47<06:10, 5.89s/trial, best loss: -0.15000000596046448]
38%|###8 | 38/100 [03:47<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 1/20
38%|###8 | 38/100 [03:48<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 68ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 2.0072
38%|###8 | 38/100 [03:49<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 2/20
38%|###8 | 38/100 [03:49<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
38%|###8 | 38/100 [03:49<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 3/20
38%|###8 | 38/100 [03:49<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0070
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 4/20
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0061
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 5/20
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 6/20
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 7/20
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0069
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 8/20
38%|###8 | 38/100 [03:50<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0066
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 9/20
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0057
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 10/20
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 11/20
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 12/20
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0065
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 13/20
38%|###8 | 38/100 [03:51<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 14/20
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0061
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 15/20
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0065
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 16/20
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0061
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 17/20
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0065
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 18/20
38%|###8 | 38/100 [03:52<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
38%|###8 | 38/100 [03:53<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 19/20
38%|###8 | 38/100 [03:53<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
38%|###8 | 38/100 [03:53<06:07, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 20/20
38%|###8 | 38/100 [03:53<06:07, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0058
38%|###8 | 38/100 [03:53<06:07, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 111ms/step - accuracy: 0.1500 - loss: 2.0357
38%|###8 | 38/100 [03:53<06:07, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 113ms/step - accuracy: 0.1500 - loss: 2.0357
38%|###8 | 38/100 [03:53<06:07, 5.93s/trial, best loss: -0.15000000596046448]
39%|###9 | 39/100 [03:53<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 1/20
39%|###9 | 39/100 [03:54<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 64ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0057
39%|###9 | 39/100 [03:55<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 2/20
39%|###9 | 39/100 [03:55<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0060
39%|###9 | 39/100 [03:55<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 3/20
39%|###9 | 39/100 [03:55<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0062
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 4/20
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 5/20
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0067
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 6/20
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0065
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 7/20
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0058
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 8/20
39%|###9 | 39/100 [03:56<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 9/20
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 10/20
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0058
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 11/20
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 12/20
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0062
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 13/20
39%|###9 | 39/100 [03:57<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 14/20
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0056
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 15/20
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0061
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 16/20
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0061
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 17/20
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 18/20
39%|###9 | 39/100 [03:58<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0056
39%|###9 | 39/100 [03:59<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 19/20
39%|###9 | 39/100 [03:59<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0053
39%|###9 | 39/100 [03:59<06:01, 5.93s/trial, best loss: -0.15000000596046448]
Epoch 20/20
39%|###9 | 39/100 [03:59<06:01, 5.93s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0051
39%|###9 | 39/100 [03:59<06:01, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 125ms/step - accuracy: 0.1500 - loss: 2.0354
39%|###9 | 39/100 [03:59<06:01, 5.93s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 127ms/step - accuracy: 0.1500 - loss: 2.0354
39%|###9 | 39/100 [03:59<06:01, 5.93s/trial, best loss: -0.15000000596046448]
40%|#### | 40/100 [03:59<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 1/20
40%|#### | 40/100 [04:00<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 64ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0066
40%|#### | 40/100 [04:01<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 2/20
40%|#### | 40/100 [04:01<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0074
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 3/20
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 4/20
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 5/20
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0069
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 6/20
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 7/20
40%|#### | 40/100 [04:02<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0058
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 8/20
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0056
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 9/20
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0071
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 10/20
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 11/20
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 12/20
40%|#### | 40/100 [04:03<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 13/20
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 14/20
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 15/20
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 16/20
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 17/20
40%|#### | 40/100 [04:04<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0062
40%|#### | 40/100 [04:05<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 18/20
40%|#### | 40/100 [04:05<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0052
40%|#### | 40/100 [04:05<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 19/20
40%|#### | 40/100 [04:05<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0056
40%|#### | 40/100 [04:05<05:59, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 20/20
40%|#### | 40/100 [04:05<05:59, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0059
40%|#### | 40/100 [04:05<05:59, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 102ms/step - accuracy: 0.1500 - loss: 2.0352
40%|#### | 40/100 [04:05<05:59, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0352
40%|#### | 40/100 [04:05<05:59, 5.99s/trial, best loss: -0.15000000596046448]
41%|####1 | 41/100 [04:05<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 1/20
41%|####1 | 41/100 [04:06<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 2.0067
41%|####1 | 41/100 [04:07<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 2/20
41%|####1 | 41/100 [04:07<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0070
41%|####1 | 41/100 [04:07<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 3/20
41%|####1 | 41/100 [04:07<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0063
41%|####1 | 41/100 [04:08<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 4/20
41%|####1 | 41/100 [04:08<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
41%|####1 | 41/100 [04:08<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 5/20
41%|####1 | 41/100 [04:08<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0065
41%|####1 | 41/100 [04:08<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 6/20
41%|####1 | 41/100 [04:08<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0062
41%|####1 | 41/100 [04:08<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 7/20
41%|####1 | 41/100 [04:08<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0062
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 8/20
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0063
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 9/20
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 17ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 10/20
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 11/20
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0054
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 12/20
41%|####1 | 41/100 [04:09<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0054
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 13/20
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0050
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 14/20
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 15/20
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 16/20
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0055
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 17/20
41%|####1 | 41/100 [04:10<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
41%|####1 | 41/100 [04:11<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 18/20
41%|####1 | 41/100 [04:11<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0056
41%|####1 | 41/100 [04:11<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 19/20
41%|####1 | 41/100 [04:11<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
41%|####1 | 41/100 [04:11<05:55, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 20/20
41%|####1 | 41/100 [04:11<05:55, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
41%|####1 | 41/100 [04:11<05:55, 6.02s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0363
41%|####1 | 41/100 [04:11<05:55, 6.02s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0363
41%|####1 | 41/100 [04:11<05:55, 6.02s/trial, best loss: -0.15000000596046448]
42%|####2 | 42/100 [04:11<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 1/20
42%|####2 | 42/100 [04:12<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 63ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0068
42%|####2 | 42/100 [04:13<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 2/20
42%|####2 | 42/100 [04:13<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
42%|####2 | 42/100 [04:13<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 3/20
42%|####2 | 42/100 [04:13<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0065
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 4/20
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0071
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 5/20
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 6/20
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0065
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 7/20
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0065
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 8/20
42%|####2 | 42/100 [04:14<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0061
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 9/20
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 10/20
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 11/20
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0057
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 12/20
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0057
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 13/20
42%|####2 | 42/100 [04:15<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
42%|####2 | 42/100 [04:16<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 14/20
42%|####2 | 42/100 [04:16<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
42%|####2 | 42/100 [04:16<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 15/20
42%|####2 | 42/100 [04:16<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0066
42%|####2 | 42/100 [04:16<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 16/20
42%|####2 | 42/100 [04:16<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
42%|####2 | 42/100 [04:16<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 17/20
42%|####2 | 42/100 [04:16<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
42%|####2 | 42/100 [04:17<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 18/20
42%|####2 | 42/100 [04:17<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0060
42%|####2 | 42/100 [04:17<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 19/20
42%|####2 | 42/100 [04:17<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0056
42%|####2 | 42/100 [04:17<05:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 20/20
42%|####2 | 42/100 [04:17<05:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
42%|####2 | 42/100 [04:17<05:48, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 116ms/step - accuracy: 0.1500 - loss: 2.0355
42%|####2 | 42/100 [04:17<05:48, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 118ms/step - accuracy: 0.1500 - loss: 2.0355
42%|####2 | 42/100 [04:17<05:48, 6.01s/trial, best loss: -0.15000000596046448]
43%|####3 | 43/100 [04:17<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 1/20
43%|####3 | 43/100 [04:18<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 2.0032
43%|####3 | 43/100 [04:19<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 2/20
43%|####3 | 43/100 [04:19<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0035
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 3/20
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0046
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 4/20
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0042
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 5/20
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0045
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 6/20
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0046
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 7/20
43%|####3 | 43/100 [04:20<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0042
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 8/20
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0044
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 9/20
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0041
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 10/20
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0048
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 11/20
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0047
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 12/20
43%|####3 | 43/100 [04:21<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0042
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 13/20
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0034
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 14/20
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0046
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 15/20
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0042
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 16/20
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0052
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 17/20
43%|####3 | 43/100 [04:22<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0043
43%|####3 | 43/100 [04:23<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 18/20
43%|####3 | 43/100 [04:23<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0047
43%|####3 | 43/100 [04:23<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 19/20
43%|####3 | 43/100 [04:23<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0045
43%|####3 | 43/100 [04:23<05:44, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 20/20
43%|####3 | 43/100 [04:23<05:44, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0052
43%|####3 | 43/100 [04:23<05:44, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 118ms/step - accuracy: 0.1500 - loss: 2.0342
43%|####3 | 43/100 [04:23<05:44, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 120ms/step - accuracy: 0.1500 - loss: 2.0342
43%|####3 | 43/100 [04:23<05:44, 6.04s/trial, best loss: -0.15000000596046448]
44%|####4 | 44/100 [04:23<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 1/20
44%|####4 | 44/100 [04:24<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 73ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0080
44%|####4 | 44/100 [04:25<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 2/20
44%|####4 | 44/100 [04:25<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0070
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 3/20
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0065
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 4/20
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0067
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 5/20
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0065
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 6/20
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0074
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 7/20
44%|####4 | 44/100 [04:26<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 2.0058
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 8/20
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0064
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 9/20
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0073
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 10/20
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0065
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 11/20
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0065
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 12/20
44%|####4 | 44/100 [04:27<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0071
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 13/20
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 14/20
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 15/20
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0080
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 16/20
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0067
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 17/20
44%|####4 | 44/100 [04:28<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0061
44%|####4 | 44/100 [04:29<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 18/20
44%|####4 | 44/100 [04:29<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0068
44%|####4 | 44/100 [04:29<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 19/20
44%|####4 | 44/100 [04:29<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0072
44%|####4 | 44/100 [04:29<05:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 20/20
44%|####4 | 44/100 [04:29<05:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
44%|####4 | 44/100 [04:29<05:36, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 111ms/step - accuracy: 0.1500 - loss: 2.0358
44%|####4 | 44/100 [04:29<05:36, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 113ms/step - accuracy: 0.1500 - loss: 2.0358
44%|####4 | 44/100 [04:29<05:36, 6.01s/trial, best loss: -0.15000000596046448]
45%|####5 | 45/100 [04:29<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 1/20
45%|####5 | 45/100 [04:30<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 75ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0073
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 2/20
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0080
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 3/20
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0076
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 4/20
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 5/20
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 6/20
45%|####5 | 45/100 [04:32<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0059
45%|####5 | 45/100 [04:33<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 7/20
45%|####5 | 45/100 [04:33<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0068
45%|####5 | 45/100 [04:33<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 8/20
45%|####5 | 45/100 [04:33<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
45%|####5 | 45/100 [04:33<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 9/20
45%|####5 | 45/100 [04:33<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
45%|####5 | 45/100 [04:33<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 10/20
45%|####5 | 45/100 [04:33<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 11/20
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0066
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 12/20
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 13/20
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0066
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 14/20
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0064
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 15/20
45%|####5 | 45/100 [04:34<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 16/20
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0060
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 17/20
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0066
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 18/20
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0054
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 19/20
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0058
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 20/20
45%|####5 | 45/100 [04:35<05:30, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0062
45%|####5 | 45/100 [04:36<05:30, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 126ms/step - accuracy: 0.1500 - loss: 2.0371
45%|####5 | 45/100 [04:36<05:30, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 128ms/step - accuracy: 0.1500 - loss: 2.0371
45%|####5 | 45/100 [04:36<05:30, 6.01s/trial, best loss: -0.15000000596046448]
46%|####6 | 46/100 [04:36<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 1/20
46%|####6 | 46/100 [04:37<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 71ms/step - accuracy: 0.2500 - loss: 1.8268 - val_accuracy: 0.1429 - val_loss: 2.0087
46%|####6 | 46/100 [04:38<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 2/20
46%|####6 | 46/100 [04:38<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0076
46%|####6 | 46/100 [04:38<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 3/20
46%|####6 | 46/100 [04:38<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
46%|####6 | 46/100 [04:38<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 4/20
46%|####6 | 46/100 [04:38<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0078
46%|####6 | 46/100 [04:38<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 5/20
46%|####6 | 46/100 [04:38<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0080
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 6/20
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0083
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 7/20
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0077
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 8/20
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0076
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 9/20
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 10/20
46%|####6 | 46/100 [04:39<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0078
46%|####6 | 46/100 [04:40<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 11/20
46%|####6 | 46/100 [04:40<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0076
46%|####6 | 46/100 [04:40<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 12/20
46%|####6 | 46/100 [04:40<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
46%|####6 | 46/100 [04:40<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 13/20
46%|####6 | 46/100 [04:40<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0075
46%|####6 | 46/100 [04:40<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 14/20
46%|####6 | 46/100 [04:40<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 15/20
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0071
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 16/20
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 17/20
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 18/20
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0062
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 19/20
46%|####6 | 46/100 [04:41<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
46%|####6 | 46/100 [04:42<05:28, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 20/20
46%|####6 | 46/100 [04:42<05:28, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0069
46%|####6 | 46/100 [04:42<05:28, 6.09s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 102ms/step - accuracy: 0.1500 - loss: 2.0377
46%|####6 | 46/100 [04:42<05:28, 6.09s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0377
46%|####6 | 46/100 [04:42<05:28, 6.09s/trial, best loss: -0.15000000596046448]
47%|####6 | 47/100 [04:42<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 1/20
47%|####6 | 47/100 [04:43<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 66ms/step - accuracy: 0.2500 - loss: 1.8265 - val_accuracy: 0.1429 - val_loss: 2.0086
47%|####6 | 47/100 [04:44<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 2/20
47%|####6 | 47/100 [04:44<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0083
47%|####6 | 47/100 [04:44<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 3/20
47%|####6 | 47/100 [04:44<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0075
47%|####6 | 47/100 [04:44<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 4/20
47%|####6 | 47/100 [04:44<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0083
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 5/20
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0081
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 6/20
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0083
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 7/20
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0081
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 8/20
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0083
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 9/20
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 10/20
47%|####6 | 47/100 [04:45<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0076
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 11/20
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0081
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 12/20
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0081
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 13/20
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0066
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 14/20
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 15/20
47%|####6 | 47/100 [04:46<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 16/20
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 17/20
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0065
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 18/20
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 19/20
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0081
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
Epoch 20/20
47%|####6 | 47/100 [04:47<05:24, 6.12s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0067
47%|####6 | 47/100 [04:48<05:24, 6.12s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0365
47%|####6 | 47/100 [04:48<05:24, 6.12s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 110ms/step - accuracy: 0.1500 - loss: 2.0365
47%|####6 | 47/100 [04:48<05:24, 6.12s/trial, best loss: -0.15000000596046448]
48%|####8 | 48/100 [04:48<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 1/20
48%|####8 | 48/100 [04:49<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0081
48%|####8 | 48/100 [04:50<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 2/20
48%|####8 | 48/100 [04:50<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0072
48%|####8 | 48/100 [04:50<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 3/20
48%|####8 | 48/100 [04:50<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0082
48%|####8 | 48/100 [04:50<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 4/20
48%|####8 | 48/100 [04:50<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0076
48%|####8 | 48/100 [04:50<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 5/20
48%|####8 | 48/100 [04:50<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0077
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 6/20
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 7/20
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0077
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 8/20
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0083
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 9/20
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0077
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 10/20
48%|####8 | 48/100 [04:51<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0081
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 11/20
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0064
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 12/20
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 13/20
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0065
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 14/20
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 15/20
48%|####8 | 48/100 [04:52<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0074
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 16/20
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 17/20
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0075
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 18/20
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 19/20
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 17ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0073
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 20/20
48%|####8 | 48/100 [04:53<05:14, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0064
48%|####8 | 48/100 [04:54<05:14, 6.05s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 137ms/step - accuracy: 0.1500 - loss: 2.0367
48%|####8 | 48/100 [04:54<05:14, 6.05s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 139ms/step - accuracy: 0.1500 - loss: 2.0367
48%|####8 | 48/100 [04:54<05:14, 6.05s/trial, best loss: -0.15000000596046448]
49%|####9 | 49/100 [04:54<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 1/20
49%|####9 | 49/100 [04:55<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 66ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0066
49%|####9 | 49/100 [04:56<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 2/20
49%|####9 | 49/100 [04:56<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
49%|####9 | 49/100 [04:56<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 3/20
49%|####9 | 49/100 [04:56<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0062
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 4/20
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0064
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 5/20
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 6/20
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0072
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 7/20
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 2.0060
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 8/20
49%|####9 | 49/100 [04:57<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0069
49%|####9 | 49/100 [04:58<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 9/20
49%|####9 | 49/100 [04:58<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 17ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
49%|####9 | 49/100 [04:58<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 10/20
49%|####9 | 49/100 [04:58<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
49%|####9 | 49/100 [04:58<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 11/20
49%|####9 | 49/100 [04:58<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
49%|####9 | 49/100 [04:58<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 12/20
49%|####9 | 49/100 [04:58<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0059
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 13/20
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0060
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 14/20
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0064
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 15/20
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0072
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 16/20
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0061
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 17/20
49%|####9 | 49/100 [04:59<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0065
49%|####9 | 49/100 [05:00<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 18/20
49%|####9 | 49/100 [05:00<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
49%|####9 | 49/100 [05:00<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 19/20
49%|####9 | 49/100 [05:00<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0060
49%|####9 | 49/100 [05:00<05:08, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 20/20
49%|####9 | 49/100 [05:00<05:08, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0049
49%|####9 | 49/100 [05:00<05:08, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0353
49%|####9 | 49/100 [05:00<05:08, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0353
49%|####9 | 49/100 [05:00<05:08, 6.04s/trial, best loss: -0.15000000596046448]
50%|##### | 50/100 [05:00<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 1/20
50%|##### | 50/100 [05:01<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 65ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0062
50%|##### | 50/100 [05:02<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 2/20
50%|##### | 50/100 [05:02<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0059
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 3/20
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 4/20
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 5/20
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0066
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 6/20
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0057
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 7/20
50%|##### | 50/100 [05:03<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0057
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 8/20
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 9/20
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0070
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 10/20
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0060
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 11/20
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0054
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 12/20
50%|##### | 50/100 [05:04<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0060
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 13/20
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0056
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 14/20
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0057
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 15/20
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0061
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 16/20
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 17/20
50%|##### | 50/100 [05:05<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0054
50%|##### | 50/100 [05:06<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 18/20
50%|##### | 50/100 [05:06<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0056
50%|##### | 50/100 [05:06<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 19/20
50%|##### | 50/100 [05:06<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0054
50%|##### | 50/100 [05:06<05:11, 6.23s/trial, best loss: -0.15000000596046448]
Epoch 20/20
50%|##### | 50/100 [05:06<05:11, 6.23s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0048
50%|##### | 50/100 [05:06<05:11, 6.23s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0344
50%|##### | 50/100 [05:06<05:11, 6.23s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0344
50%|##### | 50/100 [05:06<05:11, 6.23s/trial, best loss: -0.15000000596046448]
51%|#####1 | 51/100 [05:06<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 1/20
51%|#####1 | 51/100 [05:07<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 2.0031
51%|#####1 | 51/100 [05:08<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 2/20
51%|#####1 | 51/100 [05:08<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0033
51%|#####1 | 51/100 [05:08<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 3/20
51%|#####1 | 51/100 [05:08<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0039
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 4/20
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0043
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 5/20
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0039
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 6/20
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0027
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 7/20
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0033
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 8/20
51%|#####1 | 51/100 [05:09<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0033
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 9/20
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0032
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 10/20
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0045
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 11/20
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0047
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 12/20
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0046
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 13/20
51%|#####1 | 51/100 [05:10<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0039
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 14/20
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0034
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 15/20
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0046
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 16/20
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0033
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 17/20
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0034
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 18/20
51%|#####1 | 51/100 [05:11<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0044
51%|#####1 | 51/100 [05:12<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 19/20
51%|#####1 | 51/100 [05:12<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0046
51%|#####1 | 51/100 [05:12<05:00, 6.13s/trial, best loss: -0.15000000596046448]
Epoch 20/20
51%|#####1 | 51/100 [05:12<05:00, 6.13s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0035
51%|#####1 | 51/100 [05:12<05:00, 6.13s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0334
51%|#####1 | 51/100 [05:12<05:00, 6.13s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0334
51%|#####1 | 51/100 [05:12<05:00, 6.13s/trial, best loss: -0.15000000596046448]
52%|#####2 | 52/100 [05:12<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 1/20
52%|#####2 | 52/100 [05:13<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 65ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0046
52%|#####2 | 52/100 [05:14<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 2/20
52%|#####2 | 52/100 [05:14<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0053
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 3/20
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 4/20
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0055
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 5/20
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0048
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 6/20
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0048
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 7/20
52%|#####2 | 52/100 [05:15<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0056
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 8/20
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0060
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 9/20
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0054
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 10/20
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0055
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 11/20
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0051
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 12/20
52%|#####2 | 52/100 [05:16<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0048
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 13/20
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0046
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 14/20
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0046
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 15/20
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0047
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 16/20
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0050
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 17/20
52%|#####2 | 52/100 [05:17<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0050
52%|#####2 | 52/100 [05:18<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 18/20
52%|#####2 | 52/100 [05:18<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0057
52%|#####2 | 52/100 [05:18<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 19/20
52%|#####2 | 52/100 [05:18<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0059
52%|#####2 | 52/100 [05:18<04:48, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 20/20
52%|#####2 | 52/100 [05:18<04:48, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0046
52%|#####2 | 52/100 [05:18<04:48, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0338
52%|#####2 | 52/100 [05:18<04:48, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 110ms/step - accuracy: 0.1500 - loss: 2.0338
52%|#####2 | 52/100 [05:18<04:48, 6.01s/trial, best loss: -0.15000000596046448]
53%|#####3 | 53/100 [05:18<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 1/20
53%|#####3 | 53/100 [05:19<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0053
53%|#####3 | 53/100 [05:20<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 2/20
53%|#####3 | 53/100 [05:20<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0049
53%|#####3 | 53/100 [05:20<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 3/20
53%|#####3 | 53/100 [05:20<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0045
53%|#####3 | 53/100 [05:21<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 4/20
53%|#####3 | 53/100 [05:21<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0060
53%|#####3 | 53/100 [05:21<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 5/20
53%|#####3 | 53/100 [05:21<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0049
53%|#####3 | 53/100 [05:21<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 6/20
53%|#####3 | 53/100 [05:21<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0047
53%|#####3 | 53/100 [05:21<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 7/20
53%|#####3 | 53/100 [05:21<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0044
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 8/20
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0049
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 9/20
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0041
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 10/20
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0048
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 11/20
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0048
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 12/20
53%|#####3 | 53/100 [05:22<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0049
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 13/20
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0053
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 14/20
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0042
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 15/20
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0050
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 16/20
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0046
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 17/20
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0052
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 18/20
53%|#####3 | 53/100 [05:23<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0046
53%|#####3 | 53/100 [05:24<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 19/20
53%|#####3 | 53/100 [05:24<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0049
53%|#####3 | 53/100 [05:24<04:45, 6.08s/trial, best loss: -0.15000000596046448]
Epoch 20/20
53%|#####3 | 53/100 [05:24<04:45, 6.08s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0059
53%|#####3 | 53/100 [05:24<04:45, 6.08s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 113ms/step - accuracy: 0.1500 - loss: 2.0364
53%|#####3 | 53/100 [05:24<04:45, 6.08s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 115ms/step - accuracy: 0.1500 - loss: 2.0364
53%|#####3 | 53/100 [05:24<04:45, 6.08s/trial, best loss: -0.15000000596046448]
54%|#####4 | 54/100 [05:24<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 1/20
54%|#####4 | 54/100 [05:25<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 67ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 2.0089
54%|#####4 | 54/100 [05:26<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 2/20
54%|#####4 | 54/100 [05:26<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0088
54%|#####4 | 54/100 [05:26<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 3/20
54%|#####4 | 54/100 [05:26<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0087
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 4/20
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0086
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 5/20
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0080
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 6/20
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0072
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 7/20
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0077
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 8/20
54%|#####4 | 54/100 [05:27<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0078
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 9/20
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0078
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 10/20
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0080
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 11/20
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0080
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 12/20
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0076
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 13/20
54%|#####4 | 54/100 [05:28<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
54%|#####4 | 54/100 [05:29<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 14/20
54%|#####4 | 54/100 [05:29<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0073
54%|#####4 | 54/100 [05:29<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 15/20
54%|#####4 | 54/100 [05:29<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
54%|#####4 | 54/100 [05:29<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 16/20
54%|#####4 | 54/100 [05:29<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0078
54%|#####4 | 54/100 [05:29<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 17/20
54%|#####4 | 54/100 [05:29<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
54%|#####4 | 54/100 [05:30<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 18/20
54%|#####4 | 54/100 [05:30<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
54%|#####4 | 54/100 [05:30<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 19/20
54%|#####4 | 54/100 [05:30<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
54%|#####4 | 54/100 [05:30<04:36, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 20/20
54%|#####4 | 54/100 [05:30<04:36, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0070
54%|#####4 | 54/100 [05:30<04:36, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 109ms/step - accuracy: 0.1500 - loss: 2.0382
54%|#####4 | 54/100 [05:30<04:36, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 111ms/step - accuracy: 0.1500 - loss: 2.0382
54%|#####4 | 54/100 [05:30<04:36, 6.01s/trial, best loss: -0.15000000596046448]
55%|#####5 | 55/100 [05:30<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 1/20
55%|#####5 | 55/100 [05:31<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0075
55%|#####5 | 55/100 [05:32<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 2/20
55%|#####5 | 55/100 [05:32<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0076
55%|#####5 | 55/100 [05:32<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 3/20
55%|#####5 | 55/100 [05:32<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 4/20
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 5/20
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 6/20
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0065
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 7/20
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0066
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 8/20
55%|#####5 | 55/100 [05:33<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 9/20
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0064
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 10/20
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0060
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 11/20
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0070
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 12/20
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0068
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 13/20
55%|#####5 | 55/100 [05:34<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0058
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 14/20
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 15/20
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0067
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 16/20
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 17/20
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 18/20
55%|#####5 | 55/100 [05:35<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0064
55%|#####5 | 55/100 [05:36<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 19/20
55%|#####5 | 55/100 [05:36<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
55%|#####5 | 55/100 [05:36<04:31, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 20/20
55%|#####5 | 55/100 [05:36<04:31, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0057
55%|#####5 | 55/100 [05:36<04:31, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0365
55%|#####5 | 55/100 [05:36<04:31, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0365
55%|#####5 | 55/100 [05:36<04:31, 6.04s/trial, best loss: -0.15000000596046448]
56%|#####6 | 56/100 [05:36<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 1/20
56%|#####6 | 56/100 [05:37<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 65ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0076
56%|#####6 | 56/100 [05:38<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 2/20
56%|#####6 | 56/100 [05:38<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0077
56%|#####6 | 56/100 [05:38<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 3/20
56%|#####6 | 56/100 [05:38<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 4/20
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0080
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 5/20
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0065
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 6/20
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 7/20
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 8/20
56%|#####6 | 56/100 [05:39<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 9/20
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 10/20
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0073
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 11/20
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0085
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 12/20
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0066
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 13/20
56%|#####6 | 56/100 [05:40<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 14/20
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 15/20
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 16/20
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0064
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 17/20
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0067
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 18/20
56%|#####6 | 56/100 [05:41<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0066
56%|#####6 | 56/100 [05:42<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 19/20
56%|#####6 | 56/100 [05:42<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
56%|#####6 | 56/100 [05:42<04:23, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 20/20
56%|#####6 | 56/100 [05:42<04:23, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0066
56%|#####6 | 56/100 [05:42<04:23, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 118ms/step - accuracy: 0.1500 - loss: 2.0366
56%|#####6 | 56/100 [05:42<04:23, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 119ms/step - accuracy: 0.1500 - loss: 2.0366
56%|#####6 | 56/100 [05:42<04:23, 5.99s/trial, best loss: -0.15000000596046448]
57%|#####6 | 57/100 [05:42<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 1/20
57%|#####6 | 57/100 [05:43<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0086
57%|#####6 | 57/100 [05:44<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 2/20
57%|#####6 | 57/100 [05:44<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0086
57%|#####6 | 57/100 [05:44<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 3/20
57%|#####6 | 57/100 [05:44<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0079
57%|#####6 | 57/100 [05:44<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 4/20
57%|#####6 | 57/100 [05:44<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0084
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 5/20
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0085
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 6/20
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0090
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 7/20
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0083
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 8/20
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0079
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 9/20
57%|#####6 | 57/100 [05:45<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0073
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 10/20
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 11/20
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0079
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 12/20
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0082
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 13/20
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 14/20
57%|#####6 | 57/100 [05:46<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 15/20
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0081
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 16/20
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0079
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 17/20
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 18/20
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 19/20
57%|#####6 | 57/100 [05:47<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0069
57%|#####6 | 57/100 [05:48<04:17, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 20/20
57%|#####6 | 57/100 [05:48<04:17, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
57%|#####6 | 57/100 [05:48<04:17, 6.00s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0377
57%|#####6 | 57/100 [05:48<04:17, 6.00s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0377
57%|#####6 | 57/100 [05:48<04:17, 6.00s/trial, best loss: -0.15000000596046448]
58%|#####8 | 58/100 [05:48<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 1/20
58%|#####8 | 58/100 [05:49<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 89ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0066
58%|#####8 | 58/100 [05:50<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 2/20
58%|#####8 | 58/100 [05:50<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0068
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 3/20
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 4/20
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0075
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 5/20
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0066
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 6/20
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 7/20
58%|#####8 | 58/100 [05:51<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0065
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 8/20
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 9/20
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 10/20
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 11/20
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 12/20
58%|#####8 | 58/100 [05:52<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 13/20
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 14/20
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0063
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 15/20
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0063
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 16/20
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0062
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 17/20
58%|#####8 | 58/100 [05:53<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0060
58%|#####8 | 58/100 [05:54<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 18/20
58%|#####8 | 58/100 [05:54<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
58%|#####8 | 58/100 [05:54<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 19/20
58%|#####8 | 58/100 [05:54<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0057
58%|#####8 | 58/100 [05:54<04:08, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 20/20
58%|#####8 | 58/100 [05:54<04:08, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0055
58%|#####8 | 58/100 [05:54<04:08, 5.92s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 109ms/step - accuracy: 0.1500 - loss: 2.0378
58%|#####8 | 58/100 [05:54<04:08, 5.92s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 2.0378
58%|#####8 | 58/100 [05:54<04:08, 5.92s/trial, best loss: -0.15000000596046448]
59%|#####8 | 59/100 [05:54<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 1/20
59%|#####8 | 59/100 [05:55<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 63ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0061
59%|#####8 | 59/100 [05:56<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 2/20
59%|#####8 | 59/100 [05:56<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0066
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 3/20
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 4/20
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0072
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 5/20
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 6/20
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0065
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 7/20
59%|#####8 | 59/100 [05:57<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 8/20
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0057
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 9/20
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 10/20
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 11/20
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 12/20
59%|#####8 | 59/100 [05:58<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0057
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 13/20
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0061
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 14/20
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 15/20
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0059
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 16/20
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0058
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 17/20
59%|#####8 | 59/100 [05:59<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0066
59%|#####8 | 59/100 [06:00<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 18/20
59%|#####8 | 59/100 [06:00<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0066
59%|#####8 | 59/100 [06:00<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 19/20
59%|#####8 | 59/100 [06:00<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0061
59%|#####8 | 59/100 [06:00<04:07, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 20/20
59%|#####8 | 59/100 [06:00<04:07, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0054
59%|#####8 | 59/100 [06:00<04:07, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 113ms/step - accuracy: 0.1500 - loss: 2.0358
59%|#####8 | 59/100 [06:00<04:07, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 116ms/step - accuracy: 0.1500 - loss: 2.0358
59%|#####8 | 59/100 [06:00<04:07, 6.04s/trial, best loss: -0.15000000596046448]
60%|###### | 60/100 [06:00<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 1/20
60%|###### | 60/100 [06:01<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 64ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0048
60%|###### | 60/100 [06:02<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 2/20
60%|###### | 60/100 [06:02<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0053
60%|###### | 60/100 [06:03<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 3/20
60%|###### | 60/100 [06:03<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0043
60%|###### | 60/100 [06:03<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 4/20
60%|###### | 60/100 [06:03<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0042
60%|###### | 60/100 [06:03<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 5/20
60%|###### | 60/100 [06:03<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0043
60%|###### | 60/100 [06:03<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 6/20
60%|###### | 60/100 [06:03<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0050
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 7/20
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0040
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 8/20
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0050
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 9/20
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0046
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 10/20
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0048
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 11/20
60%|###### | 60/100 [06:04<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0051
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 12/20
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0049
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 13/20
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0048
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 14/20
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0044
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 15/20
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0047
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 16/20
60%|###### | 60/100 [06:05<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0052
60%|###### | 60/100 [06:06<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 17/20
60%|###### | 60/100 [06:06<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0049
60%|###### | 60/100 [06:06<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 18/20
60%|###### | 60/100 [06:06<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0039
60%|###### | 60/100 [06:06<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 19/20
60%|###### | 60/100 [06:06<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0044
60%|###### | 60/100 [06:06<04:02, 6.06s/trial, best loss: -0.15000000596046448]
Epoch 20/20
60%|###### | 60/100 [06:06<04:02, 6.06s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0051
60%|###### | 60/100 [06:06<04:02, 6.06s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 114ms/step - accuracy: 0.1500 - loss: 2.0360
60%|###### | 60/100 [06:07<04:02, 6.06s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 117ms/step - accuracy: 0.1500 - loss: 2.0360
60%|###### | 60/100 [06:07<04:02, 6.06s/trial, best loss: -0.15000000596046448]
61%|######1 | 61/100 [06:07<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 1/20
61%|######1 | 61/100 [06:07<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0083
61%|######1 | 61/100 [06:08<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 2/20
61%|######1 | 61/100 [06:08<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0079
61%|######1 | 61/100 [06:09<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 3/20
61%|######1 | 61/100 [06:09<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0079
61%|######1 | 61/100 [06:09<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 4/20
61%|######1 | 61/100 [06:09<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 21ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0073
61%|######1 | 61/100 [06:09<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 5/20
61%|######1 | 61/100 [06:09<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
61%|######1 | 61/100 [06:09<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 6/20
61%|######1 | 61/100 [06:09<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
61%|######1 | 61/100 [06:10<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 7/20
61%|######1 | 61/100 [06:10<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
61%|######1 | 61/100 [06:10<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 8/20
61%|######1 | 61/100 [06:10<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
61%|######1 | 61/100 [06:10<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 9/20
61%|######1 | 61/100 [06:10<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
61%|######1 | 61/100 [06:10<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 10/20
61%|######1 | 61/100 [06:10<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0081
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 11/20
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 12/20
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 13/20
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0069
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 14/20
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0072
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 15/20
61%|######1 | 61/100 [06:11<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 16/20
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0067
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 17/20
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 18/20
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0060
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 19/20
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0076
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
Epoch 20/20
61%|######1 | 61/100 [06:12<03:57, 6.09s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0059
61%|######1 | 61/100 [06:13<03:57, 6.09s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 109ms/step - accuracy: 0.1500 - loss: 2.0373
61%|######1 | 61/100 [06:13<03:57, 6.09s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 111ms/step - accuracy: 0.1500 - loss: 2.0373
61%|######1 | 61/100 [06:13<03:57, 6.09s/trial, best loss: -0.15000000596046448]
62%|######2 | 62/100 [06:13<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 1/20
62%|######2 | 62/100 [06:14<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 66ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 2.0044
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 2/20
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0042
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 3/20
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0049
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 4/20
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0044
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 5/20
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0046
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 6/20
62%|######2 | 62/100 [06:15<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0046
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 7/20
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0053
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 8/20
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0048
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 9/20
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0053
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 10/20
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0051
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 11/20
62%|######2 | 62/100 [06:16<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0050
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 12/20
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0046
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 13/20
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0052
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 14/20
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0050
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 15/20
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0052
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 16/20
62%|######2 | 62/100 [06:17<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0049
62%|######2 | 62/100 [06:18<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 17/20
62%|######2 | 62/100 [06:18<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0050
62%|######2 | 62/100 [06:18<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 18/20
62%|######2 | 62/100 [06:18<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0052
62%|######2 | 62/100 [06:18<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 19/20
62%|######2 | 62/100 [06:18<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0047
62%|######2 | 62/100 [06:18<03:52, 6.11s/trial, best loss: -0.15000000596046448]
Epoch 20/20
62%|######2 | 62/100 [06:18<03:52, 6.11s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0040
62%|######2 | 62/100 [06:19<03:52, 6.11s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0347
62%|######2 | 62/100 [06:19<03:52, 6.11s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0347
62%|######2 | 62/100 [06:19<03:52, 6.11s/trial, best loss: -0.15000000596046448]
63%|######3 | 63/100 [06:19<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 1/20
63%|######3 | 63/100 [06:20<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0069
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 2/20
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 3/20
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 4/20
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 5/20
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 6/20
63%|######3 | 63/100 [06:21<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0066
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 7/20
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 8/20
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0062
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 9/20
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0066
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 10/20
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0051
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 11/20
63%|######3 | 63/100 [06:22<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0062
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 12/20
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0064
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 13/20
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0059
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 14/20
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0068
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 15/20
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0055
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 16/20
63%|######3 | 63/100 [06:23<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 17/20
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0061
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 18/20
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0054
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 19/20
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0056
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
Epoch 20/20
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0061
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0367
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0367
63%|######3 | 63/100 [06:24<03:44, 6.07s/trial, best loss: -0.15000000596046448]
64%|######4 | 64/100 [06:24<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 1/20
64%|######4 | 64/100 [06:25<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 67ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0058
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 2/20
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0068
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 3/20
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 4/20
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 5/20
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0058
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 6/20
64%|######4 | 64/100 [06:27<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0060
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 7/20
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0066
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 8/20
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 9/20
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0057
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 10/20
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0056
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 11/20
64%|######4 | 64/100 [06:28<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0060
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 12/20
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 13/20
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0065
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 14/20
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0051
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 15/20
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0050
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 16/20
64%|######4 | 64/100 [06:29<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0057
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 17/20
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0052
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 18/20
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0045
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 19/20
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0051
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 20/20
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0057
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0352
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0352
64%|######4 | 64/100 [06:30<03:35, 5.98s/trial, best loss: -0.15000000596046448]
65%|######5 | 65/100 [06:30<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 1/20
65%|######5 | 65/100 [06:31<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 74ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 2.0088
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 2/20
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0070
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 3/20
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 4/20
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0079
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 5/20
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0079
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 6/20
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0077
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 7/20
65%|######5 | 65/100 [06:33<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 8/20
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 9/20
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0073
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 10/20
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0075
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 11/20
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0079
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 12/20
65%|######5 | 65/100 [06:34<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0072
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 13/20
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0075
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 14/20
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0075
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 15/20
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 16/20
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0067
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 17/20
65%|######5 | 65/100 [06:35<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
65%|######5 | 65/100 [06:36<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 18/20
65%|######5 | 65/100 [06:36<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
65%|######5 | 65/100 [06:36<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 19/20
65%|######5 | 65/100 [06:36<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0072
65%|######5 | 65/100 [06:36<03:29, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 20/20
65%|######5 | 65/100 [06:36<03:29, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
65%|######5 | 65/100 [06:36<03:29, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 111ms/step - accuracy: 0.1500 - loss: 2.0363
65%|######5 | 65/100 [06:36<03:29, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 2.0363
65%|######5 | 65/100 [06:36<03:29, 5.99s/trial, best loss: -0.15000000596046448]
66%|######6 | 66/100 [06:36<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 1/20
66%|######6 | 66/100 [06:37<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 64ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0096
66%|######6 | 66/100 [06:38<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 2/20
66%|######6 | 66/100 [06:38<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0088
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 3/20
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0087
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 4/20
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0085
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 5/20
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0088
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 6/20
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0089
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 7/20
66%|######6 | 66/100 [06:39<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0081
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 8/20
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0085
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 9/20
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0089
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 10/20
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0081
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 11/20
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0097
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 12/20
66%|######6 | 66/100 [06:40<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0086
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 13/20
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0080
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 14/20
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0077
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 15/20
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0084
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 16/20
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0081
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 17/20
66%|######6 | 66/100 [06:41<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0080
66%|######6 | 66/100 [06:42<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 18/20
66%|######6 | 66/100 [06:42<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
66%|######6 | 66/100 [06:42<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 19/20
66%|######6 | 66/100 [06:42<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0077
66%|######6 | 66/100 [06:42<03:23, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 20/20
66%|######6 | 66/100 [06:42<03:23, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0083
66%|######6 | 66/100 [06:42<03:23, 5.98s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0385
66%|######6 | 66/100 [06:42<03:23, 5.98s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0385
66%|######6 | 66/100 [06:42<03:23, 5.98s/trial, best loss: -0.15000000596046448]
67%|######7 | 67/100 [06:42<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 1/20
67%|######7 | 67/100 [06:43<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 63ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0097
67%|######7 | 67/100 [06:44<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 2/20
67%|######7 | 67/100 [06:44<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0100
67%|######7 | 67/100 [06:44<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 3/20
67%|######7 | 67/100 [06:44<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0101
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 4/20
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0098
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 5/20
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0090
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 6/20
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0094
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 7/20
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0089
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 8/20
67%|######7 | 67/100 [06:45<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0092
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 9/20
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0095
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 10/20
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0094
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 11/20
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0100
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 12/20
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0091
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 13/20
67%|######7 | 67/100 [06:46<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0084
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 14/20
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0082
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 15/20
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0070
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 16/20
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0073
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 17/20
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0077
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 18/20
67%|######7 | 67/100 [06:47<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0084
67%|######7 | 67/100 [06:48<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 19/20
67%|######7 | 67/100 [06:48<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0085
67%|######7 | 67/100 [06:48<03:16, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 20/20
67%|######7 | 67/100 [06:48<03:16, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
67%|######7 | 67/100 [06:48<03:16, 5.96s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 120ms/step - accuracy: 0.1500 - loss: 2.0380
67%|######7 | 67/100 [06:48<03:16, 5.96s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 123ms/step - accuracy: 0.1500 - loss: 2.0380
67%|######7 | 67/100 [06:48<03:16, 5.96s/trial, best loss: -0.15000000596046448]
68%|######8 | 68/100 [06:48<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 1/20
68%|######8 | 68/100 [06:49<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 66ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0091
68%|######8 | 68/100 [06:50<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 2/20
68%|######8 | 68/100 [06:50<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0095
68%|######8 | 68/100 [06:50<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 3/20
68%|######8 | 68/100 [06:50<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0092
68%|######8 | 68/100 [06:51<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 4/20
68%|######8 | 68/100 [06:51<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0073
68%|######8 | 68/100 [06:51<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 5/20
68%|######8 | 68/100 [06:51<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0092
68%|######8 | 68/100 [06:51<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 6/20
68%|######8 | 68/100 [06:51<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0079
68%|######8 | 68/100 [06:51<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 7/20
68%|######8 | 68/100 [06:51<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0080
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 8/20
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0082
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 9/20
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 10/20
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0084
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 11/20
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0079
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 12/20
68%|######8 | 68/100 [06:52<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0081
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 13/20
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0080
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 14/20
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0082
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 15/20
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0075
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 16/20
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0077
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 17/20
68%|######8 | 68/100 [06:53<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0079
68%|######8 | 68/100 [06:54<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 18/20
68%|######8 | 68/100 [06:54<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0080
68%|######8 | 68/100 [06:54<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 19/20
68%|######8 | 68/100 [06:54<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0079
68%|######8 | 68/100 [06:54<03:09, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 20/20
68%|######8 | 68/100 [06:54<03:09, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0081
68%|######8 | 68/100 [06:54<03:09, 5.94s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 125ms/step - accuracy: 0.1500 - loss: 2.0383
68%|######8 | 68/100 [06:54<03:09, 5.94s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 126ms/step - accuracy: 0.1500 - loss: 2.0383
68%|######8 | 68/100 [06:54<03:09, 5.94s/trial, best loss: -0.15000000596046448]
69%|######9 | 69/100 [06:54<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 1/20
69%|######9 | 69/100 [06:55<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 69ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0067
69%|######9 | 69/100 [06:56<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 2/20
69%|######9 | 69/100 [06:56<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0071
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 3/20
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 4/20
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0071
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 5/20
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0077
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 6/20
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 7/20
69%|######9 | 69/100 [06:57<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0061
69%|######9 | 69/100 [06:58<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 8/20
69%|######9 | 69/100 [06:58<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
69%|######9 | 69/100 [06:58<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 9/20
69%|######9 | 69/100 [06:58<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
69%|######9 | 69/100 [06:58<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 10/20
69%|######9 | 69/100 [06:58<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0076
69%|######9 | 69/100 [06:58<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 11/20
69%|######9 | 69/100 [06:58<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 12/20
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0073
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 13/20
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 14/20
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0072
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 15/20
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 16/20
69%|######9 | 69/100 [06:59<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0064
69%|######9 | 69/100 [07:00<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 17/20
69%|######9 | 69/100 [07:00<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
69%|######9 | 69/100 [07:00<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 18/20
69%|######9 | 69/100 [07:00<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
69%|######9 | 69/100 [07:00<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 19/20
69%|######9 | 69/100 [07:00<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
69%|######9 | 69/100 [07:00<03:06, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 20/20
69%|######9 | 69/100 [07:00<03:06, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
69%|######9 | 69/100 [07:00<03:06, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 114ms/step - accuracy: 0.1500 - loss: 2.0375
69%|######9 | 69/100 [07:01<03:06, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 117ms/step - accuracy: 0.1500 - loss: 2.0375
69%|######9 | 69/100 [07:01<03:06, 6.01s/trial, best loss: -0.15000000596046448]
70%|####### | 70/100 [07:01<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 1/20
70%|####### | 70/100 [07:01<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 64ms/step - accuracy: 0.2500 - loss: 1.8267 - val_accuracy: 0.1429 - val_loss: 2.0090
70%|####### | 70/100 [07:02<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 2/20
70%|####### | 70/100 [07:02<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0071
70%|####### | 70/100 [07:03<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 3/20
70%|####### | 70/100 [07:03<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0076
70%|####### | 70/100 [07:03<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 4/20
70%|####### | 70/100 [07:03<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
70%|####### | 70/100 [07:03<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 5/20
70%|####### | 70/100 [07:03<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0081
70%|####### | 70/100 [07:03<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 6/20
70%|####### | 70/100 [07:03<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0077
70%|####### | 70/100 [07:03<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 7/20
70%|####### | 70/100 [07:04<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0081
70%|####### | 70/100 [07:04<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 8/20
70%|####### | 70/100 [07:04<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0078
70%|####### | 70/100 [07:04<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 9/20
70%|####### | 70/100 [07:04<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0077
70%|####### | 70/100 [07:04<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 10/20
70%|####### | 70/100 [07:04<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0083
70%|####### | 70/100 [07:04<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 11/20
70%|####### | 70/100 [07:04<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0078
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 12/20
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0078
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 13/20
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0077
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 14/20
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0075
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 15/20
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 16/20
70%|####### | 70/100 [07:05<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
70%|####### | 70/100 [07:06<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 17/20
70%|####### | 70/100 [07:06<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0067
70%|####### | 70/100 [07:06<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 18/20
70%|####### | 70/100 [07:06<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0061
70%|####### | 70/100 [07:06<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 19/20
70%|####### | 70/100 [07:06<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0066
70%|####### | 70/100 [07:06<03:01, 6.05s/trial, best loss: -0.15000000596046448]
Epoch 20/20
70%|####### | 70/100 [07:06<03:01, 6.05s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
70%|####### | 70/100 [07:06<03:01, 6.05s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 134ms/step - accuracy: 0.1500 - loss: 2.0377
70%|####### | 70/100 [07:07<03:01, 6.05s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 136ms/step - accuracy: 0.1500 - loss: 2.0377
70%|####### | 70/100 [07:07<03:01, 6.05s/trial, best loss: -0.15000000596046448]
71%|#######1 | 71/100 [07:07<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 1/20
71%|#######1 | 71/100 [07:07<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0071
71%|#######1 | 71/100 [07:08<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 2/20
71%|#######1 | 71/100 [07:08<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0085
71%|#######1 | 71/100 [07:09<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 3/20
71%|#######1 | 71/100 [07:09<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
71%|#######1 | 71/100 [07:09<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 4/20
71%|#######1 | 71/100 [07:09<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0080
71%|#######1 | 71/100 [07:09<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 5/20
71%|#######1 | 71/100 [07:09<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0073
71%|#######1 | 71/100 [07:09<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 6/20
71%|#######1 | 71/100 [07:09<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0076
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 7/20
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0076
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 8/20
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0078
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 9/20
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0080
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 10/20
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0071
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 11/20
71%|#######1 | 71/100 [07:10<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 12/20
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0075
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 13/20
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0083
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 14/20
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0074
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 15/20
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0070
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 16/20
71%|#######1 | 71/100 [07:11<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0061
71%|#######1 | 71/100 [07:12<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 17/20
71%|#######1 | 71/100 [07:12<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
71%|#######1 | 71/100 [07:12<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 18/20
71%|#######1 | 71/100 [07:12<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0067
71%|#######1 | 71/100 [07:12<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 19/20
71%|#######1 | 71/100 [07:12<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0070
71%|#######1 | 71/100 [07:12<02:55, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 20/20
71%|#######1 | 71/100 [07:12<02:55, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
71%|#######1 | 71/100 [07:12<02:55, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0371
71%|#######1 | 71/100 [07:13<02:55, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 110ms/step - accuracy: 0.1500 - loss: 2.0371
71%|#######1 | 71/100 [07:13<02:55, 6.04s/trial, best loss: -0.15000000596046448]
72%|#######2 | 72/100 [07:13<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 1/20
72%|#######2 | 72/100 [07:14<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 67ms/step - accuracy: 0.2500 - loss: 1.8259 - val_accuracy: 0.1429 - val_loss: 2.0073
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 2/20
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0068
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 3/20
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 4/20
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0074
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 5/20
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 6/20
72%|#######2 | 72/100 [07:15<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 7/20
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 8/20
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0063
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 9/20
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0064
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 10/20
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 11/20
72%|#######2 | 72/100 [07:16<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 12/20
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 13/20
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0063
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 14/20
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 15/20
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 16/20
72%|#######2 | 72/100 [07:17<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
72%|#######2 | 72/100 [07:18<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 17/20
72%|#######2 | 72/100 [07:18<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
72%|#######2 | 72/100 [07:18<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 18/20
72%|#######2 | 72/100 [07:18<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0066
72%|#######2 | 72/100 [07:18<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 19/20
72%|#######2 | 72/100 [07:18<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0059
72%|#######2 | 72/100 [07:18<02:49, 6.04s/trial, best loss: -0.15000000596046448]
Epoch 20/20
72%|#######2 | 72/100 [07:18<02:49, 6.04s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
72%|#######2 | 72/100 [07:18<02:49, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 111ms/step - accuracy: 0.1500 - loss: 2.0377
72%|#######2 | 72/100 [07:19<02:49, 6.04s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 113ms/step - accuracy: 0.1500 - loss: 2.0377
72%|#######2 | 72/100 [07:19<02:49, 6.04s/trial, best loss: -0.15000000596046448]
73%|#######3 | 73/100 [07:19<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 1/20
73%|#######3 | 73/100 [07:20<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 2.0074
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 2/20
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0074
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 3/20
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 4/20
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0082
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 5/20
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 6/20
73%|#######3 | 73/100 [07:21<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 7/20
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 8/20
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0069
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 9/20
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 10/20
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0078
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 11/20
73%|#######3 | 73/100 [07:22<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 12/20
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 13/20
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0063
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 14/20
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0065
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 15/20
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0067
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 16/20
73%|#######3 | 73/100 [07:23<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
73%|#######3 | 73/100 [07:24<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 17/20
73%|#######3 | 73/100 [07:24<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
73%|#######3 | 73/100 [07:24<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 18/20
73%|#######3 | 73/100 [07:24<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0064
73%|#######3 | 73/100 [07:24<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 19/20
73%|#######3 | 73/100 [07:24<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0066
73%|#######3 | 73/100 [07:24<02:42, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 20/20
73%|#######3 | 73/100 [07:24<02:42, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 15ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
73%|#######3 | 73/100 [07:24<02:42, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 2.0381
73%|#######3 | 73/100 [07:25<02:42, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 114ms/step - accuracy: 0.1500 - loss: 2.0381
73%|#######3 | 73/100 [07:25<02:42, 6.01s/trial, best loss: -0.15000000596046448]
74%|#######4 | 74/100 [07:25<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 1/20
74%|#######4 | 74/100 [07:26<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8267 - val_accuracy: 0.1429 - val_loss: 2.0089
74%|#######4 | 74/100 [07:26<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 2/20
74%|#######4 | 74/100 [07:26<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0082
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 3/20
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0080
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 4/20
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0078
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 5/20
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 6/20
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0081
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 7/20
74%|#######4 | 74/100 [07:27<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0078
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 8/20
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0083
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 9/20
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0072
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 10/20
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0077
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 11/20
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0080
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 12/20
74%|#######4 | 74/100 [07:28<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0078
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 13/20
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 14/20
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0065
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 15/20
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 16/20
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0068
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 17/20
74%|#######4 | 74/100 [07:29<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
74%|#######4 | 74/100 [07:30<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 18/20
74%|#######4 | 74/100 [07:30<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
74%|#######4 | 74/100 [07:30<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 19/20
74%|#######4 | 74/100 [07:30<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
74%|#######4 | 74/100 [07:30<02:36, 6.02s/trial, best loss: -0.15000000596046448]
Epoch 20/20
74%|#######4 | 74/100 [07:30<02:36, 6.02s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0057
74%|#######4 | 74/100 [07:30<02:36, 6.02s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 110ms/step - accuracy: 0.1500 - loss: 2.0378
74%|#######4 | 74/100 [07:30<02:36, 6.02s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 2.0378
74%|#######4 | 74/100 [07:30<02:36, 6.02s/trial, best loss: -0.15000000596046448]
75%|#######5 | 75/100 [07:30<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 1/20
75%|#######5 | 75/100 [07:31<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 63ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 2.0059
75%|#######5 | 75/100 [07:32<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 2/20
75%|#######5 | 75/100 [07:32<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0052
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 3/20
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0066
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 4/20
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 5/20
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 6/20
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0060
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 7/20
75%|#######5 | 75/100 [07:33<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0053
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 8/20
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0065
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 9/20
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 10/20
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0054
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 11/20
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0057
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 12/20
75%|#######5 | 75/100 [07:34<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0065
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 13/20
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0059
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 14/20
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0062
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 15/20
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0061
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 16/20
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0067
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 17/20
75%|#######5 | 75/100 [07:35<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
75%|#######5 | 75/100 [07:36<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 18/20
75%|#######5 | 75/100 [07:36<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
75%|#######5 | 75/100 [07:36<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 19/20
75%|#######5 | 75/100 [07:36<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0061
75%|#######5 | 75/100 [07:36<02:29, 5.96s/trial, best loss: -0.15000000596046448]
Epoch 20/20
75%|#######5 | 75/100 [07:36<02:29, 5.96s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
75%|#######5 | 75/100 [07:36<02:29, 5.96s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 114ms/step - accuracy: 0.1500 - loss: 2.0390
75%|#######5 | 75/100 [07:36<02:29, 5.96s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 117ms/step - accuracy: 0.1500 - loss: 2.0390
75%|#######5 | 75/100 [07:36<02:29, 5.96s/trial, best loss: -0.15000000596046448]
76%|#######6 | 76/100 [07:36<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 1/20
76%|#######6 | 76/100 [07:37<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 65ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 2.0064
76%|#######6 | 76/100 [07:38<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 2/20
76%|#######6 | 76/100 [07:38<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0064
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 3/20
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 4/20
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0074
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 5/20
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0059
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 6/20
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 7/20
76%|#######6 | 76/100 [07:39<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 8/20
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 9/20
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0066
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 10/20
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 11/20
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0063
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 12/20
76%|#######6 | 76/100 [07:40<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0065
76%|#######6 | 76/100 [07:41<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 13/20
76%|#######6 | 76/100 [07:41<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 16ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0054
76%|#######6 | 76/100 [07:41<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 14/20
76%|#######6 | 76/100 [07:41<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
76%|#######6 | 76/100 [07:41<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 15/20
76%|#######6 | 76/100 [07:41<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
76%|#######6 | 76/100 [07:41<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 16/20
76%|#######6 | 76/100 [07:41<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
76%|#######6 | 76/100 [07:41<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 17/20
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0059
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 18/20
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 19/20
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0062
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
Epoch 20/20
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 113ms/step - accuracy: 0.1500 - loss: 2.0373
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 115ms/step - accuracy: 0.1500 - loss: 2.0373
76%|#######6 | 76/100 [07:42<02:23, 5.97s/trial, best loss: -0.15000000596046448]
77%|#######7 | 77/100 [07:42<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 1/20
77%|#######7 | 77/100 [07:43<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 66ms/step - accuracy: 0.2500 - loss: 1.8270 - val_accuracy: 0.1429 - val_loss: 2.0082
77%|#######7 | 77/100 [07:44<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 2/20
77%|#######7 | 77/100 [07:44<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 3/20
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 4/20
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0072
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 5/20
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0075
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 6/20
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0086
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 7/20
77%|#######7 | 77/100 [07:45<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 8/20
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 9/20
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0075
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 10/20
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 11/20
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0082
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 12/20
77%|#######7 | 77/100 [07:46<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 13/20
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0065
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 14/20
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 15/20
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 16/20
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 17/20
77%|#######7 | 77/100 [07:47<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0066
77%|#######7 | 77/100 [07:48<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 18/20
77%|#######7 | 77/100 [07:48<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
77%|#######7 | 77/100 [07:48<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 19/20
77%|#######7 | 77/100 [07:48<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0063
77%|#######7 | 77/100 [07:48<02:18, 6.01s/trial, best loss: -0.15000000596046448]
Epoch 20/20
77%|#######7 | 77/100 [07:48<02:18, 6.01s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0057
77%|#######7 | 77/100 [07:48<02:18, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 123ms/step - accuracy: 0.1500 - loss: 2.0363
77%|#######7 | 77/100 [07:48<02:18, 6.01s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 126ms/step - accuracy: 0.1500 - loss: 2.0363
77%|#######7 | 77/100 [07:48<02:18, 6.01s/trial, best loss: -0.15000000596046448]
78%|#######8 | 78/100 [07:48<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 1/20
78%|#######8 | 78/100 [07:49<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 67ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0059
78%|#######8 | 78/100 [07:50<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 2/20
78%|#######8 | 78/100 [07:50<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 3/20
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 4/20
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 5/20
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 6/20
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 7/20
78%|#######8 | 78/100 [07:51<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0066
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 8/20
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0063
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 9/20
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0057
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 10/20
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0057
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 11/20
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0055
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 12/20
78%|#######8 | 78/100 [07:52<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0050
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 13/20
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0056
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 14/20
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 15/20
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0054
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 16/20
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0060
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 17/20
78%|#######8 | 78/100 [07:53<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0061
78%|#######8 | 78/100 [07:54<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 18/20
78%|#######8 | 78/100 [07:54<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0062
78%|#######8 | 78/100 [07:54<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 19/20
78%|#######8 | 78/100 [07:54<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0063
78%|#######8 | 78/100 [07:54<02:11, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 20/20
78%|#######8 | 78/100 [07:54<02:11, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0055
78%|#######8 | 78/100 [07:54<02:11, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0358
78%|#######8 | 78/100 [07:54<02:11, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0358
78%|#######8 | 78/100 [07:54<02:11, 5.99s/trial, best loss: -0.15000000596046448]
79%|#######9 | 79/100 [07:54<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 1/20
79%|#######9 | 79/100 [07:55<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 64ms/step - accuracy: 0.2500 - loss: 1.8266 - val_accuracy: 0.1429 - val_loss: 2.0077
79%|#######9 | 79/100 [07:56<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 2/20
79%|#######9 | 79/100 [07:56<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0065
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 3/20
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0073
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 4/20
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 5/20
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0063
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 6/20
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 7/20
79%|#######9 | 79/100 [07:57<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0067
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 8/20
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0058
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 9/20
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 10/20
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0058
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 11/20
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 12/20
79%|#######9 | 79/100 [07:58<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0066
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 13/20
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 14/20
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 15/20
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 16/20
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 17/20
79%|#######9 | 79/100 [07:59<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
79%|#######9 | 79/100 [08:00<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 18/20
79%|#######9 | 79/100 [08:00<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0067
79%|#######9 | 79/100 [08:00<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 19/20
79%|#######9 | 79/100 [08:00<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
79%|#######9 | 79/100 [08:00<02:05, 5.99s/trial, best loss: -0.15000000596046448]
Epoch 20/20
79%|#######9 | 79/100 [08:00<02:05, 5.99s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0060
79%|#######9 | 79/100 [08:00<02:05, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 124ms/step - accuracy: 0.1500 - loss: 2.0365
79%|#######9 | 79/100 [08:00<02:05, 5.99s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 125ms/step - accuracy: 0.1500 - loss: 2.0365
79%|#######9 | 79/100 [08:00<02:05, 5.99s/trial, best loss: -0.15000000596046448]
80%|######## | 80/100 [08:00<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 1/20
80%|######## | 80/100 [08:01<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 78ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0065
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 2/20
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0062
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 3/20
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 4/20
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0068
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 5/20
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 6/20
80%|######## | 80/100 [08:03<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 7/20
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0077
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 8/20
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0067
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 9/20
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 10/20
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0060
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 11/20
80%|######## | 80/100 [08:04<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0055
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 12/20
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0064
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 13/20
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0071
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 14/20
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0063
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 15/20
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0062
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 16/20
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0061
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 17/20
80%|######## | 80/100 [08:05<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
80%|######## | 80/100 [08:06<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 18/20
80%|######## | 80/100 [08:06<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
80%|######## | 80/100 [08:06<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 19/20
80%|######## | 80/100 [08:06<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0054
80%|######## | 80/100 [08:06<01:59, 5.98s/trial, best loss: -0.15000000596046448]
Epoch 20/20
80%|######## | 80/100 [08:06<01:59, 5.98s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
80%|######## | 80/100 [08:06<01:59, 5.98s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0362
80%|######## | 80/100 [08:06<01:59, 5.98s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0362
80%|######## | 80/100 [08:06<01:59, 5.98s/trial, best loss: -0.15000000596046448]
81%|########1 | 81/100 [08:06<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 1/20
81%|########1 | 81/100 [08:07<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 62ms/step - accuracy: 0.2500 - loss: 1.8262 - val_accuracy: 0.1429 - val_loss: 2.0085
81%|########1 | 81/100 [08:08<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 2/20
81%|########1 | 81/100 [08:08<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0084
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 3/20
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0078
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 4/20
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 5/20
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0086
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 6/20
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0085
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 7/20
81%|########1 | 81/100 [08:09<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0079
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 8/20
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0086
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 9/20
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0073
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 10/20
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0075
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 11/20
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 12/20
81%|########1 | 81/100 [08:10<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 13/20
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0063
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 14/20
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0075
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 15/20
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 16/20
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0071
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 17/20
81%|########1 | 81/100 [08:11<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
81%|########1 | 81/100 [08:12<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 18/20
81%|########1 | 81/100 [08:12<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
81%|########1 | 81/100 [08:12<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 19/20
81%|########1 | 81/100 [08:12<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0065
81%|########1 | 81/100 [08:12<01:54, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 20/20
81%|########1 | 81/100 [08:12<01:54, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
81%|########1 | 81/100 [08:12<01:54, 6.00s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0377
81%|########1 | 81/100 [08:12<01:54, 6.00s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0377
81%|########1 | 81/100 [08:12<01:54, 6.00s/trial, best loss: -0.15000000596046448]
82%|########2 | 82/100 [08:12<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 1/20
82%|########2 | 82/100 [08:13<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8268 - val_accuracy: 0.1429 - val_loss: 2.0112
82%|########2 | 82/100 [08:14<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 2/20
82%|########2 | 82/100 [08:14<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0102
82%|########2 | 82/100 [08:14<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 3/20
82%|########2 | 82/100 [08:14<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0109
82%|########2 | 82/100 [08:14<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 4/20
82%|########2 | 82/100 [08:14<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0102
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 5/20
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0098
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 6/20
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0094
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 7/20
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0091
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 8/20
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0101
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 9/20
82%|########2 | 82/100 [08:15<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0095
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 10/20
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0097
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 11/20
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0090
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 12/20
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0084
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 13/20
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0099
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 14/20
82%|########2 | 82/100 [08:16<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0082
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 15/20
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0086
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 16/20
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0086
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 17/20
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0092
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 18/20
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0093
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 19/20
82%|########2 | 82/100 [08:17<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0092
82%|########2 | 82/100 [08:18<01:46, 5.94s/trial, best loss: -0.15000000596046448]
Epoch 20/20
82%|########2 | 82/100 [08:18<01:46, 5.94s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0080
82%|########2 | 82/100 [08:18<01:46, 5.94s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 110ms/step - accuracy: 0.1500 - loss: 2.0379
82%|########2 | 82/100 [08:18<01:46, 5.94s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 2.0379
82%|########2 | 82/100 [08:18<01:46, 5.94s/trial, best loss: -0.15000000596046448]
83%|########2 | 83/100 [08:18<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 1/20
83%|########2 | 83/100 [08:19<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 79ms/step - accuracy: 0.2500 - loss: 1.8262 - val_accuracy: 0.1429 - val_loss: 2.0096
83%|########2 | 83/100 [08:20<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 2/20
83%|########2 | 83/100 [08:20<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0097
83%|########2 | 83/100 [08:20<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 3/20
83%|########2 | 83/100 [08:20<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0093
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 4/20
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0091
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 5/20
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0093
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 6/20
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0100
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 7/20
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0103
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 8/20
83%|########2 | 83/100 [08:21<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0091
83%|########2 | 83/100 [08:22<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 9/20
83%|########2 | 83/100 [08:22<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0093
83%|########2 | 83/100 [08:22<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 10/20
83%|########2 | 83/100 [08:22<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0092
83%|########2 | 83/100 [08:22<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 11/20
83%|########2 | 83/100 [08:22<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0085
83%|########2 | 83/100 [08:22<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 12/20
83%|########2 | 83/100 [08:22<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 14ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0090
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 13/20
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0084
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 14/20
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0086
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 15/20
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0074
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 16/20
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0075
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 17/20
83%|########2 | 83/100 [08:23<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
83%|########2 | 83/100 [08:24<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 18/20
83%|########2 | 83/100 [08:24<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0077
83%|########2 | 83/100 [08:24<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 19/20
83%|########2 | 83/100 [08:24<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0087
83%|########2 | 83/100 [08:24<01:40, 5.89s/trial, best loss: -0.15000000596046448]
Epoch 20/20
83%|########2 | 83/100 [08:24<01:40, 5.89s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0089
83%|########2 | 83/100 [08:24<01:40, 5.89s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 109ms/step - accuracy: 0.1500 - loss: 2.0380
83%|########2 | 83/100 [08:24<01:40, 5.89s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 111ms/step - accuracy: 0.1500 - loss: 2.0380
83%|########2 | 83/100 [08:24<01:40, 5.89s/trial, best loss: -0.15000000596046448]
84%|########4 | 84/100 [08:24<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 1/20
84%|########4 | 84/100 [08:25<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 66ms/step - accuracy: 0.2500 - loss: 1.8262 - val_accuracy: 0.1429 - val_loss: 2.0111
84%|########4 | 84/100 [08:26<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 2/20
84%|########4 | 84/100 [08:26<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0103
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 3/20
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0103
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 4/20
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0106
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 5/20
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0103
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 6/20
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0099
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 7/20
84%|########4 | 84/100 [08:27<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0098
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 8/20
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0095
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 9/20
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0105
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 10/20
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0097
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 11/20
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0096
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 12/20
84%|########4 | 84/100 [08:28<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0100
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 13/20
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0088
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 14/20
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0095
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 15/20
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0093
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 16/20
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0088
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 17/20
84%|########4 | 84/100 [08:29<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8256 - val_accuracy: 0.1429 - val_loss: 2.0090
84%|########4 | 84/100 [08:30<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 18/20
84%|########4 | 84/100 [08:30<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0084
84%|########4 | 84/100 [08:30<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 19/20
84%|########4 | 84/100 [08:30<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0086
84%|########4 | 84/100 [08:30<01:36, 6.03s/trial, best loss: -0.15000000596046448]
Epoch 20/20
84%|########4 | 84/100 [08:30<01:36, 6.03s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0088
84%|########4 | 84/100 [08:30<01:36, 6.03s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0369
84%|########4 | 84/100 [08:30<01:36, 6.03s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0369
84%|########4 | 84/100 [08:30<01:36, 6.03s/trial, best loss: -0.15000000596046448]
85%|########5 | 85/100 [08:30<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 1/20
85%|########5 | 85/100 [08:31<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0101
85%|########5 | 85/100 [08:32<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 2/20
85%|########5 | 85/100 [08:32<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0094
85%|########5 | 85/100 [08:32<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 3/20
85%|########5 | 85/100 [08:32<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0102
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 4/20
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0091
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 5/20
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0105
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 6/20
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0107
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 7/20
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0090
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 8/20
85%|########5 | 85/100 [08:33<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0098
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 9/20
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0092
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 10/20
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0091
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 11/20
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0087
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 12/20
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0090
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 13/20
85%|########5 | 85/100 [08:34<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0086
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 14/20
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0088
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 15/20
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0080
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 16/20
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0089
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 17/20
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0088
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 18/20
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0093
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 19/20
85%|########5 | 85/100 [08:35<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0082
85%|########5 | 85/100 [08:36<01:29, 6.00s/trial, best loss: -0.15000000596046448]
Epoch 20/20
85%|########5 | 85/100 [08:36<01:29, 6.00s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0078
85%|########5 | 85/100 [08:36<01:29, 6.00s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0371
85%|########5 | 85/100 [08:36<01:29, 6.00s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0371
85%|########5 | 85/100 [08:36<01:29, 6.00s/trial, best loss: -0.15000000596046448]
86%|########6 | 86/100 [08:36<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 1/20
86%|########6 | 86/100 [08:37<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8263 - val_accuracy: 0.1429 - val_loss: 2.0107
86%|########6 | 86/100 [08:38<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 2/20
86%|########6 | 86/100 [08:38<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0101
86%|########6 | 86/100 [08:38<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 3/20
86%|########6 | 86/100 [08:38<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0101
86%|########6 | 86/100 [08:38<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 4/20
86%|########6 | 86/100 [08:38<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0087
86%|########6 | 86/100 [08:38<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 5/20
86%|########6 | 86/100 [08:38<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0096
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 6/20
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0089
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 7/20
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0100
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 8/20
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0095
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 9/20
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0093
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 10/20
86%|########6 | 86/100 [08:39<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0090
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 11/20
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0097
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 12/20
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0087
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 13/20
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0097
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 14/20
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0089
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 15/20
86%|########6 | 86/100 [08:40<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0085
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 16/20
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0081
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 17/20
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0092
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 18/20
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0092
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 19/20
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0093
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
Epoch 20/20
86%|########6 | 86/100 [08:41<01:22, 5.92s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0084
86%|########6 | 86/100 [08:42<01:22, 5.92s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0374
86%|########6 | 86/100 [08:42<01:22, 5.92s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0374
86%|########6 | 86/100 [08:42<01:22, 5.92s/trial, best loss: -0.15000000596046448]
87%|########7 | 87/100 [08:42<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 1/20
87%|########7 | 87/100 [08:43<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 75ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0075
87%|########7 | 87/100 [08:44<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 2/20
87%|########7 | 87/100 [08:44<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0082
87%|########7 | 87/100 [08:44<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 3/20
87%|########7 | 87/100 [08:44<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0079
87%|########7 | 87/100 [08:44<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 4/20
87%|########7 | 87/100 [08:44<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0074
87%|########7 | 87/100 [08:44<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 5/20
87%|########7 | 87/100 [08:44<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0077
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 6/20
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0081
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 7/20
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 8/20
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0082
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 9/20
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0083
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 10/20
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 11ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0077
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 11/20
87%|########7 | 87/100 [08:45<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0078
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 12/20
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 13/20
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 14/20
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 15/20
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 16/20
87%|########7 | 87/100 [08:46<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0076
87%|########7 | 87/100 [08:47<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 17/20
87%|########7 | 87/100 [08:47<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0079
87%|########7 | 87/100 [08:47<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 18/20
87%|########7 | 87/100 [08:47<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
87%|########7 | 87/100 [08:47<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 19/20
87%|########7 | 87/100 [08:47<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0071
87%|########7 | 87/100 [08:47<01:16, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 20/20
87%|########7 | 87/100 [08:47<01:16, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
87%|########7 | 87/100 [08:47<01:16, 5.85s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0358
87%|########7 | 87/100 [08:48<01:16, 5.85s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 109ms/step - accuracy: 0.1500 - loss: 2.0358
87%|########7 | 87/100 [08:48<01:16, 5.85s/trial, best loss: -0.15000000596046448]
88%|########8 | 88/100 [08:48<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 1/20
88%|########8 | 88/100 [08:48<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0080
88%|########8 | 88/100 [08:49<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 2/20
88%|########8 | 88/100 [08:49<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0075
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 3/20
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 4/20
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0069
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 5/20
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 6/20
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0084
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 7/20
88%|########8 | 88/100 [08:50<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 8/20
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0077
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 9/20
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0072
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 10/20
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 11/20
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0080
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 12/20
88%|########8 | 88/100 [08:51<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8246 - val_accuracy: 0.1429 - val_loss: 2.0074
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 13/20
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0070
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 14/20
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0073
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 15/20
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 16/20
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0069
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 17/20
88%|########8 | 88/100 [08:52<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
88%|########8 | 88/100 [08:53<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 18/20
88%|########8 | 88/100 [08:53<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
88%|########8 | 88/100 [08:53<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 19/20
88%|########8 | 88/100 [08:53<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
88%|########8 | 88/100 [08:53<01:10, 5.85s/trial, best loss: -0.15000000596046448]
Epoch 20/20
88%|########8 | 88/100 [08:53<01:10, 5.85s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0064
88%|########8 | 88/100 [08:53<01:10, 5.85s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0371
88%|########8 | 88/100 [08:53<01:10, 5.85s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0371
88%|########8 | 88/100 [08:53<01:10, 5.85s/trial, best loss: -0.15000000596046448]
89%|########9 | 89/100 [08:53<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 1/20
89%|########9 | 89/100 [08:54<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0082
89%|########9 | 89/100 [08:55<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 2/20
89%|########9 | 89/100 [08:55<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0083
89%|########9 | 89/100 [08:55<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 3/20
89%|########9 | 89/100 [08:55<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0083
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 4/20
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0069
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 5/20
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 6/20
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0073
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 7/20
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 8/20
89%|########9 | 89/100 [08:56<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0070
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 9/20
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 10/20
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 11/20
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 12/20
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 13/20
89%|########9 | 89/100 [08:57<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 14/20
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 15/20
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 16/20
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0071
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 17/20
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 18/20
89%|########9 | 89/100 [08:58<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
89%|########9 | 89/100 [08:59<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 19/20
89%|########9 | 89/100 [08:59<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0067
89%|########9 | 89/100 [08:59<01:04, 5.82s/trial, best loss: -0.15000000596046448]
Epoch 20/20
89%|########9 | 89/100 [08:59<01:04, 5.82s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0076
89%|########9 | 89/100 [08:59<01:04, 5.82s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 102ms/step - accuracy: 0.1500 - loss: 2.0386
89%|########9 | 89/100 [08:59<01:04, 5.82s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0386
89%|########9 | 89/100 [08:59<01:04, 5.82s/trial, best loss: -0.15000000596046448]
90%|######### | 90/100 [08:59<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 1/20
90%|######### | 90/100 [09:00<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 63ms/step - accuracy: 0.2500 - loss: 1.8264 - val_accuracy: 0.1429 - val_loss: 2.0071
90%|######### | 90/100 [09:01<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 2/20
90%|######### | 90/100 [09:01<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0078
90%|######### | 90/100 [09:01<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 3/20
90%|######### | 90/100 [09:01<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0079
90%|######### | 90/100 [09:01<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 4/20
90%|######### | 90/100 [09:01<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 5/20
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0074
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 6/20
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0076
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 7/20
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0079
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 8/20
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 9/20
90%|######### | 90/100 [09:02<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0074
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 10/20
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0075
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 11/20
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 12/20
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0072
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 13/20
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0066
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 14/20
90%|######### | 90/100 [09:03<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 15/20
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0067
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 16/20
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 17/20
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 18/20
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 19/20
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 20/20
90%|######### | 90/100 [09:04<00:57, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0071
90%|######### | 90/100 [09:05<00:57, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0380
90%|######### | 90/100 [09:05<00:57, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0380
90%|######### | 90/100 [09:05<00:57, 5.79s/trial, best loss: -0.15000000596046448]
91%|#########1| 91/100 [09:05<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 1/20
91%|#########1| 91/100 [09:06<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8260 - val_accuracy: 0.1429 - val_loss: 2.0095
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 2/20
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0093
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 3/20
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0087
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 4/20
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0083
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 5/20
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0090
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 6/20
91%|#########1| 91/100 [09:07<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0093
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 7/20
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0090
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 8/20
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0098
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 9/20
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0083
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 10/20
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0082
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 11/20
91%|#########1| 91/100 [09:08<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0090
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 12/20
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0085
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 13/20
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0071
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 14/20
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0090
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 15/20
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0082
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 16/20
91%|#########1| 91/100 [09:09<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
91%|#########1| 91/100 [09:10<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 17/20
91%|#########1| 91/100 [09:10<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0082
91%|#########1| 91/100 [09:10<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 18/20
91%|#########1| 91/100 [09:10<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0081
91%|#########1| 91/100 [09:10<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 19/20
91%|#########1| 91/100 [09:10<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0077
91%|#########1| 91/100 [09:10<00:52, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 20/20
91%|#########1| 91/100 [09:10<00:52, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
91%|#########1| 91/100 [09:10<00:52, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 2.0396
91%|#########1| 91/100 [09:11<00:52, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 114ms/step - accuracy: 0.1500 - loss: 2.0396
91%|#########1| 91/100 [09:11<00:52, 5.79s/trial, best loss: -0.15000000596046448]
92%|#########2| 92/100 [09:11<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 1/20
92%|#########2| 92/100 [09:11<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0071
92%|#########2| 92/100 [09:12<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 2/20
92%|#########2| 92/100 [09:12<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0075
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 3/20
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 4/20
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0079
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 5/20
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0079
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 6/20
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0073
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 7/20
92%|#########2| 92/100 [09:13<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0071
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 8/20
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 9/20
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 10/20
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0066
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 11/20
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0067
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 12/20
92%|#########2| 92/100 [09:14<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 13/20
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 14/20
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0076
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 15/20
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0073
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 16/20
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 17/20
92%|#########2| 92/100 [09:15<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0067
92%|#########2| 92/100 [09:16<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 18/20
92%|#########2| 92/100 [09:16<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0074
92%|#########2| 92/100 [09:16<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 19/20
92%|#########2| 92/100 [09:16<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0072
92%|#########2| 92/100 [09:16<00:46, 5.77s/trial, best loss: -0.15000000596046448]
Epoch 20/20
92%|#########2| 92/100 [09:16<00:46, 5.77s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
92%|#########2| 92/100 [09:16<00:46, 5.77s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0381
92%|#########2| 92/100 [09:16<00:46, 5.77s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0381
92%|#########2| 92/100 [09:16<00:46, 5.77s/trial, best loss: -0.15000000596046448]
93%|#########3| 93/100 [09:16<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 1/20
93%|#########3| 93/100 [09:17<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0056
93%|#########3| 93/100 [09:18<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 2/20
93%|#########3| 93/100 [09:18<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0058
93%|#########3| 93/100 [09:18<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 3/20
93%|#########3| 93/100 [09:18<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0061
93%|#########3| 93/100 [09:18<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 4/20
93%|#########3| 93/100 [09:18<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 5/20
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0055
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 6/20
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0056
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 7/20
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0059
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 8/20
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0060
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 9/20
93%|#########3| 93/100 [09:19<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0046
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 10/20
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0058
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 11/20
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0055
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 12/20
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0065
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 13/20
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0053
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 14/20
93%|#########3| 93/100 [09:20<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0057
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 15/20
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 16/20
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0059
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 17/20
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0061
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 18/20
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 19/20
93%|#########3| 93/100 [09:21<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0056
93%|#########3| 93/100 [09:22<00:40, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 20/20
93%|#########3| 93/100 [09:22<00:40, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
93%|#########3| 93/100 [09:22<00:40, 5.75s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0371
93%|#########3| 93/100 [09:22<00:40, 5.75s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0371
93%|#########3| 93/100 [09:22<00:40, 5.75s/trial, best loss: -0.15000000596046448]
94%|#########3| 94/100 [09:22<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 1/20
94%|#########3| 94/100 [09:23<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8257 - val_accuracy: 0.1429 - val_loss: 2.0074
94%|#########3| 94/100 [09:24<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 2/20
94%|#########3| 94/100 [09:24<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0082
94%|#########3| 94/100 [09:24<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 3/20
94%|#########3| 94/100 [09:24<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0083
94%|#########3| 94/100 [09:24<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 4/20
94%|#########3| 94/100 [09:24<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0072
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 5/20
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0069
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 6/20
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0084
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 7/20
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0081
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 8/20
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 9/20
94%|#########3| 94/100 [09:25<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0072
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 10/20
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0077
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 11/20
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0083
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 12/20
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 13/20
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0075
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 14/20
94%|#########3| 94/100 [09:26<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 15/20
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 16/20
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0072
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 17/20
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 18/20
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0076
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 19/20
94%|#########3| 94/100 [09:27<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0064
94%|#########3| 94/100 [09:28<00:34, 5.73s/trial, best loss: -0.15000000596046448]
Epoch 20/20
94%|#########3| 94/100 [09:28<00:34, 5.73s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
94%|#########3| 94/100 [09:28<00:34, 5.73s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 104ms/step - accuracy: 0.1500 - loss: 2.0371
94%|#########3| 94/100 [09:28<00:34, 5.73s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0371
94%|#########3| 94/100 [09:28<00:34, 5.73s/trial, best loss: -0.15000000596046448]
95%|#########5| 95/100 [09:28<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 1/20
95%|#########5| 95/100 [09:29<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0079
95%|#########5| 95/100 [09:30<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 2/20
95%|#########5| 95/100 [09:30<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0064
95%|#########5| 95/100 [09:30<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 3/20
95%|#########5| 95/100 [09:30<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
95%|#########5| 95/100 [09:30<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 4/20
95%|#########5| 95/100 [09:30<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0075
95%|#########5| 95/100 [09:30<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 5/20
95%|#########5| 95/100 [09:30<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0075
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 6/20
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 7/20
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 8/20
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0067
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 9/20
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0071
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 10/20
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0061
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 11/20
95%|#########5| 95/100 [09:31<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0066
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 12/20
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0063
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 13/20
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 14/20
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 15/20
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0065
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 16/20
95%|#########5| 95/100 [09:32<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0075
95%|#########5| 95/100 [09:33<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 17/20
95%|#########5| 95/100 [09:33<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0069
95%|#########5| 95/100 [09:33<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 18/20
95%|#########5| 95/100 [09:33<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0062
95%|#########5| 95/100 [09:33<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 19/20
95%|#########5| 95/100 [09:33<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0059
95%|#########5| 95/100 [09:33<00:28, 5.79s/trial, best loss: -0.15000000596046448]
Epoch 20/20
95%|#########5| 95/100 [09:33<00:28, 5.79s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
95%|#########5| 95/100 [09:33<00:28, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 112ms/step - accuracy: 0.1500 - loss: 2.0363
95%|#########5| 95/100 [09:34<00:28, 5.79s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 113ms/step - accuracy: 0.1500 - loss: 2.0363
95%|#########5| 95/100 [09:34<00:28, 5.79s/trial, best loss: -0.15000000596046448]
96%|#########6| 96/100 [09:34<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 1/20
96%|#########6| 96/100 [09:34<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8258 - val_accuracy: 0.1429 - val_loss: 2.0072
96%|#########6| 96/100 [09:35<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 2/20
96%|#########6| 96/100 [09:35<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 3/20
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0076
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 4/20
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0073
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 5/20
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0077
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 6/20
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0074
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 7/20
96%|#########6| 96/100 [09:36<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0082
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 8/20
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 9/20
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0073
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 10/20
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0074
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 11/20
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0062
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 12/20
96%|#########6| 96/100 [09:37<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0072
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 13/20
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0062
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 14/20
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0064
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 15/20
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0071
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 16/20
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0067
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 17/20
96%|#########6| 96/100 [09:38<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 13ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
96%|#########6| 96/100 [09:39<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 18/20
96%|#########6| 96/100 [09:39<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0064
96%|#########6| 96/100 [09:39<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 19/20
96%|#########6| 96/100 [09:39<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0060
96%|#########6| 96/100 [09:39<00:23, 5.78s/trial, best loss: -0.15000000596046448]
Epoch 20/20
96%|#########6| 96/100 [09:39<00:23, 5.78s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0064
96%|#########6| 96/100 [09:39<00:23, 5.78s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 106ms/step - accuracy: 0.1500 - loss: 2.0368
96%|#########6| 96/100 [09:39<00:23, 5.78s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 108ms/step - accuracy: 0.1500 - loss: 2.0368
96%|#########6| 96/100 [09:39<00:23, 5.78s/trial, best loss: -0.15000000596046448]
97%|#########7| 97/100 [09:39<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 1/20
97%|#########7| 97/100 [09:40<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0060
97%|#########7| 97/100 [09:41<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 2/20
97%|#########7| 97/100 [09:41<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0058
97%|#########7| 97/100 [09:41<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 3/20
97%|#########7| 97/100 [09:41<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0061
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 4/20
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0054
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 5/20
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0059
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 6/20
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0064
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 7/20
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0070
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 8/20
97%|#########7| 97/100 [09:42<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 9/20
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0066
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 10/20
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0065
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 11/20
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0055
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 12/20
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0061
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 13/20
97%|#########7| 97/100 [09:43<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0058
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 14/20
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0068
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 15/20
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 16/20
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0057
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 17/20
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0054
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 18/20
97%|#########7| 97/100 [09:44<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0057
97%|#########7| 97/100 [09:45<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 19/20
97%|#########7| 97/100 [09:45<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0054
97%|#########7| 97/100 [09:45<00:17, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 20/20
97%|#########7| 97/100 [09:45<00:17, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0061
97%|#########7| 97/100 [09:45<00:17, 5.75s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 103ms/step - accuracy: 0.1500 - loss: 2.0364
97%|#########7| 97/100 [09:45<00:17, 5.75s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0364
97%|#########7| 97/100 [09:45<00:17, 5.75s/trial, best loss: -0.15000000596046448]
98%|#########8| 98/100 [09:45<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 1/20
98%|#########8| 98/100 [09:46<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 61ms/step - accuracy: 0.2500 - loss: 1.8261 - val_accuracy: 0.1429 - val_loss: 2.0067
98%|#########8| 98/100 [09:47<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 2/20
98%|#########8| 98/100 [09:47<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0074
98%|#########8| 98/100 [09:47<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 3/20
98%|#########8| 98/100 [09:47<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
98%|#########8| 98/100 [09:47<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 4/20
98%|#########8| 98/100 [09:47<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0057
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 5/20
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0069
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 6/20
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0069
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 7/20
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0058
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 8/20
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0062
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 9/20
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8247 - val_accuracy: 0.1429 - val_loss: 2.0065
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 10/20
98%|#########8| 98/100 [09:48<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0068
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 11/20
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0070
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 12/20
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8254 - val_accuracy: 0.1429 - val_loss: 2.0062
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 13/20
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0060
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 14/20
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 15/20
98%|#########8| 98/100 [09:49<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0062
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 16/20
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0068
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 17/20
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 18/20
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0062
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 19/20
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0061
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
Epoch 20/20
98%|#########8| 98/100 [09:50<00:11, 5.75s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0057
98%|#########8| 98/100 [09:51<00:11, 5.75s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 114ms/step - accuracy: 0.1500 - loss: 2.0359
98%|#########8| 98/100 [09:51<00:11, 5.75s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 116ms/step - accuracy: 0.1500 - loss: 2.0359
98%|#########8| 98/100 [09:51<00:11, 5.75s/trial, best loss: -0.15000000596046448]
99%|#########9| 99/100 [09:51<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 1/20
99%|#########9| 99/100 [09:52<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 1s - 60ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0054
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 2/20
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8253 - val_accuracy: 0.1429 - val_loss: 2.0058
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 3/20
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0054
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 4/20
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0063
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 5/20
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 6/20
99%|#########9| 99/100 [09:53<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8255 - val_accuracy: 0.1429 - val_loss: 2.0052
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 7/20
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0052
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 8/20
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0053
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 9/20
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0060
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 10/20
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0056
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 11/20
99%|#########9| 99/100 [09:54<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0060
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 12/20
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0054
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 13/20
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8250 - val_accuracy: 0.1429 - val_loss: 2.0064
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 14/20
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0058
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 15/20
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8251 - val_accuracy: 0.1429 - val_loss: 2.0065
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 16/20
99%|#########9| 99/100 [09:55<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0063
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 17/20
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0057
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 18/20
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8249 - val_accuracy: 0.1429 - val_loss: 2.0061
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 19/20
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8248 - val_accuracy: 0.1429 - val_loss: 2.0053
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
Epoch 20/20
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
16/16 - 0s - 12ms/step - accuracy: 0.2500 - loss: 1.8252 - val_accuracy: 0.1429 - val_loss: 2.0058
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 105ms/step - accuracy: 0.1500 - loss: 2.0364
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
[1m1/1[0m [32m━━━━━━━━━━━━━━━━━━━━[0m[37m[0m [1m0s[0m 107ms/step - accuracy: 0.1500 - loss: 2.0364
99%|#########9| 99/100 [09:56<00:05, 5.74s/trial, best loss: -0.15000000596046448]
100%|##########| 100/100 [09:56<00:00, 5.72s/trial, best loss: -0.15000000596046448]
100%|##########| 100/100 [09:56<00:00, 5.97s/trial, best loss: -0.15000000596046448]
print("Best hyperparameters:", best)
Best hyperparameters: {'hidden_size': 5, 'n_components': 15, 'n_hidden': 3}