Scribd Logo
Upload

Welcome to Scribd!

  • 6 views

    Filename

    Uploaded by

    Animesh Basak
    This document shows the loss, validation loss, accuracy, and validation accuracy metrics over 110 epochs of training a neural network model. The metrics improve over the epochs, with loss and validation loss decreasing while accuracy and validation accuracy increase, indicating the model is learning from the training. By epoch 14, the model reaches perfect accuracy of 1 on the training data.

    Copyright:

    © All Rights Reserved
    Download as XLSX, PDF, TXT or read online from Scribd

    Filename

    Uploaded by

    Animesh Basak
    6 views3 pages
    This document shows the loss, validation loss, accuracy, and validation accuracy metrics over 110 epochs of training a neural network model. The metrics improve over the epochs, with loss and validation loss decreasing while accuracy and validation accuracy increase, indicating the model is learning from the training. By epoch 14, the model reaches perfect accuracy of 1 on the training data.

    Original Title

    filename (1)

    Copyright

    © © All Rights Reserved

    Available Formats

    XLSX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document shows the loss, validation loss, accuracy, and validation accuracy metrics over 110 epochs of training a neural network model. The metrics improve over the epochs, with loss and validation loss decreasing while accuracy and validation accuracy increase, indicating the model is learning from the training. By epoch 14, the model reaches perfect accuracy of 1 on the training data.

    Copyright:

    © All Rights Reserved
    Download as XLSX, PDF, TXT or read online from Scribd
    Download as xlsx, pdf, or txt
    6 views3 pages

    Filename

    Uploaded by

    Animesh Basak
    This document shows the loss, validation loss, accuracy, and validation accuracy metrics over 110 epochs of training a neural network model. The metrics improve over the epochs, with loss and validation loss decreasing while accuracy and validation accuracy increase, indicating the model is learning from the training. By epoch 14, the model reaches perfect accuracy of 1 on the training data.

    Copyright:

    © All Rights Reserved
    Download as XLSX, PDF, TXT or read online from Scribd
    Download as xlsx, pdf, or txt
    You are on page 1of 3

    loss val_loss accuracy

    val_accuracy
    0 0.711605 0.578333 0.595 0.665323
    1 0.569539 0.710241 0.7025 0.604839
    2 0.518422 0.528762 0.755784 0.733871
    3 0.441742 0.438595 0.795 0.798387
    4 0.41096 0.461855 0.791774 0.770161
    5 0.207657 0.38083 0.9475 0.830645
    6 0.205101 0.382911 0.9275 0.842742
    7 0.152365 0.360074 0.948586 0.850806
    8 0.124519 0.426439 0.9675 0.790323
    9 0.123067 0.367954 0.976864 0.854839
    10 0.099628 0.314042 0.9825 0.883065
    11 0.081387 0.316658 0.995 0.862903
    12 0.069201 0.309681 0.994859 0.887097
    13 0.060392 0.296351 0.9975 0.899194
    14 0.059458 0.296531 1 0.883065
    15 0.042729 0.297199 1 0.887097
    16 0.047369 0.337892 0.9975 0.887097
    17 0.043231 0.289504 0.997429 0.887097
    18 0.033618 0.294392 1 0.899194
    19 0.040744 0.294515 0.997429 0.903226
    20 0.031089 0.293313 1 0.895161
    21 0.02722 0.290917 1 0.899194
    22 0.031386 0.282895 0.994859 0.879032
    23 0.023708 0.287509 0.9975 0.891129
    24 0.032515 0.313853 0.997429 0.891129
    25 0.019381 0.291081 1 0.887097
    26 0.026664 0.285176 0.9975 0.899194
    27 0.019871 0.278201 1 0.907258
    28 0.017048 0.281106 1 0.895161
    29 0.022135 0.297482 0.997429 0.91129
    30 0.015163 0.292936 1 0.895161
    31 0.014808 0.300478 1 0.875
    32 0.020699 0.293131 0.997429 0.903226
    33 0.019461 0.332119 0.9975 0.887097
    34 0.014155 0.295779 1 0.891129
    35 0.015507 0.307059 0.9975 0.907258
    36 0.02584 0.43658 0.9975 0.854839
    37 0.008404 0.369552 1 0.870968
    38 0.020185 0.314633 0.9975 0.891129
    39 0.010494 0.306026 1 0.91129
    40 0.006232 0.337039 1 0.91129
    41 0.003139 0.335568 1 0.907258
    42 0.012828 0.312537 0.997429 0.907258
    43 0.003415 0.314777 1 0.907258
    44 0.012092 0.324094 0.997429 0.903226
    45 0.002747 0.330168 1 0.895161
    46 0.010904 0.36237 0.9975 0.875
    47 0.003136 0.308965 1 0.91129
    48 0.015828 0.494932 0.9975 0.834677
    49 0.00435 0.354823 1 0.883065
    50 0.001713 0.346383 1 0.903226
    51 0.01188 0.382161 0.9975 0.891129
    52 0.002819 0.317826 1 0.903226
    53 0.001806 0.307543 1 0.899194
    54 0.011954 0.440637 0.997429 0.875
    55 0.040213 0.954541 0.9875 0.762097
    56 0.072203 0.397924 0.99 0.895161
    57 0.007899 0.483858 1 0.895161
    58 0.0044 0.391405 1 0.891129
    59 0.015987 0.436685 0.994859 0.879032
    60 0.009608 0.383249 0.9975 0.899194
    61 0.001936 0.348032 1 0.891129
    62 0.001897 0.342921 1 0.91129
    63 0.012173 0.374954 0.9975 0.899194
    64 0.001396 0.391079 1 0.907258
    65 0.015961 0.458928 0.9975 0.870968
    66 0.008637 0.39574 0.9975 0.903226
    67 0.001319 0.439117 1 0.903226
    68 0.021513 0.469271 0.995 0.875
    69 0.003393 0.404266 1 0.899194
    70 0.011687 0.45813 0.9975 0.879032
    71 0.014536 0.373427 0.9975 0.899194
    72 0.001419 0.403855 1 0.891129
    73 0.012523 0.396983 0.9975 0.895161
    74 0.01073 0.409797 0.997429 0.903226
    75 0.001024 0.398144 1 0.91129
    76 0.013371 0.409956 0.9975 0.891129
    77 0.001156 0.361151 1 0.907258
    78 0.000722 0.365005 1 0.91129
    79 0.012503 0.499584 0.997429 0.858871
    80 0.002807 0.402307 1 0.891129
    81 0.000547 0.399027 1 0.915323
    82 0.000968 0.394892 1 0.915323
    83 0.000494 0.393523 1 0.907258
    84 0.011205 0.361404 0.997429 0.91129
    85 0.017731 0.537452 0.9975 0.846774
    86 0.010737 0.389827 0.9975 0.899194
    87 0.006291 0.560147 1 0.850806
    88 0.00285 0.415134 1 0.907258
    89 0.020176 0.521086 0.994859 0.883065
    90 0.019228 0.427199 0.9975 0.903226
    91 0.001178 0.388562 1 0.895161
    92 0.015442 0.554423 0.997429 0.854839
    93 0.022271 0.511092 0.9975 0.854839
    94 0.001329 0.407582 1 0.895161
    95 0.011411 0.448932 0.9975 0.895161
    96 0.000663 0.465244 1 0.891129
    97 0.020554 0.431366 0.997429 0.907258
    98 0.011051 0.455195 0.9975 0.907258
    99 0.014683 0.449522 0.997429 0.895161
    100 0.001035 0.394399 1 0.903226
    101 0.000447 0.379098 1 0.899194
    102 0.01537 0.444933 0.997429 0.895161
    103 0.004016 0.483381 1 0.891129
    104 0.021867 0.676693 0.997429 0.870968
    105 0.002318 0.398074 1 0.915323
    106 0.000665 0.389755 1 0.919355
    107 0.045087 0.416708 0.994859 0.903226
    108 0.014566 1.053394 0.9975 0.75
    109 0.050188 0.488451 0.979434 0.899194
    110 0.007109 0.666249 1 0.866935

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy