krenerd77

Krenerd77's group workspace

Group: CIFAR10-AdditiveGradientNoiseExperiment

1-20

of 21

Tags

Notes

Author

krenerd77

State

Crashed

Start time

September 18th, 2022 3:28:50 PM

Runtime

1h 41m 8s

Tracked hours

1h 41m 5s

Run path

krenerd77/CIFAR10-classification/3sxh76na

Linux-5.10.133+-x86_64-with-Ubuntu-18.04-bionic

Python version

3.7.14

Git repository

git clone https://github.com/krenerd/awesome-modular-pytorch-lightning

Git state

git checkout -b "CIFAR10-Simpleinit-Var5.0-cycle_1-callbacks.GradientNoise.args.eta_0.01-Sep18_15-28-46" 886af8c2e98b3bfaeb46c08d1db1257aa0c0b1c5

Command

hyperparameter_sweep.py --name CIFAR10-Simpleinit-Var5.0 -k callbacks.GradientNoise.args.eta -t float -v 0.0 0.01 0.1 1.0 --group CIFAR10-AdditiveGradientNoiseExperiment --config configs/algorithms/initialization/simple-init.yaml configs/algorithms/gradient_noise/decaying.yaml configs/vision/classification/resnet-cifar10.yaml configs/vision/models/resnet/resnet18-custom.yaml configs/data/cifar10-kuangliu.yaml configs/device/gpu.yaml configs/utils/wandb.yaml configs/utils/train.yaml

System Hardware

CPU count	2
GPU count	1
GPU type	Tesla T4

W&B CLI Version

0.13.3

Group

CIFAR10-AdditiveGradientNoiseExperiment

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 93 keys
- callbacks/GradientNoise/args/eta:
  0.01
- callbacks/GradientNoise/args/gamma:
  0.55
- callbacks/GradientNoise/name:
  "DecayingGradientNoiseCallback"
- callbacks/Initialization/args/bias:
  false
- ▶
  callbacks/Initialization/args/layer_whitelist:[] 2 items
  - 0:
    "Conv2d"
  - 1:
    "Linear"
- callbacks/Initialization/args/mean:
  0
- callbacks/Initialization/args/mode:
  "normal"
- callbacks/Initialization/args/var:
  5
- callbacks/Initialization/name:
  "WeightInitialization"
- callbacks/LearningRateMonitor/args/args/logging_interval:
  "epoch"
- callbacks/LearningRateMonitor/args/name:
  "LearningRateMonitor"
- callbacks/LearningRateMonitor/name:
  "LightningCallback"
- callbacks/ModelCheckpoint/args/args/mode:
  "max"
- callbacks/ModelCheckpoint/args/args/monitor:
  "epoch_val/accuracy"
- callbacks/ModelCheckpoint/args/args/save_last:
  true
- callbacks/ModelCheckpoint/args/args/save_top_k:
  1
- callbacks/ModelCheckpoint/args/name:
  "ModelCheckpoint"
- callbacks/ModelCheckpoint/name:
  "LightningCallback"
- ▶
  const/label_map:[] 10 items
- ▶
  const/normalization_mean:[] 3 items
  - 0:
    0.4914
  - 1:
    0.4822
  - 2:
    0.4465
- ▶
  const/normalization_std:[] 3 items
  - 0:
    0.2023
  - 1:
    0.1994
  - 2:
    0.201
- const/num_classes:
  10
- const/task:
  "image classification"
- dataloader/base_dataloader/batch_size:
  64
- dataloader/base_dataloader/shuffle:
  true
- dataloader/trn/shuffle:
  true
- dataloader/val/drop_last:
  false
- dataloader/val/shuffle:
  false
- dataset/dataset_base_cfg/args/args/root:
  "./cifar10"
- dataset/dataset_base_cfg/args/name:
  "CIFAR10"
- dataset/dataset_base_cfg/name:
  "TorchvisionDataset"
- dataset/dataset_subset_cfg/trn/args/args/download:
  true
- dataset/dataset_subset_cfg/trn/args/args/train:
  true
- dataset/dataset_subset_cfg/val/args/args/train:
  false
- dataset/initial_transform/name:
  "TupleToClassificationData"
- DEBUG_MODE:
  false
- ▶
  debug/network_summary/input_shape:[] 3 items
  - 0:
    3
  - 1:
    32
  - 2:
    32
- ▶
  debug/view_train_augmentation/normalization_mean:[] 3 items
  - 0:
    0.4914
  - 1:
    0.4822
  - 2:
    0.4465
- ▶
  debug/view_train_augmentation/normalization_std:[] 3 items
  - 0:
    0.2023
  - 1:
    0.1994
  - 2:
    0.201
- debug/view_train_augmentation/plot_size:
  5
- ▶
  debug/view_train_augmentation/resize_to:[] 2 items
  - 0:
    256
  - 1:
    256
- debug/view_train_augmentation/save_to:
  "vis/training_samples.png"
- ▶
  debug/view_train_augmentation/subplot_dim:[] 2 items
  - 0:
    4
  - 1:
    4
- model/backbone/name:
  "ResNet18"
- model/backbone/out_features:
  512
- model/init_hook/low_res/name:
  "ResNetLowResHead"
- ▶
  transform:[] 2 items
  - ▶
    0:[] 2 items
    - 0:
      "trn"
    - ▶
      1:[] 2 items
      - ▶
        0:{} 2 keys
        ▶
        args:{} 2 keys
        ▶
        args:{} 2 keys
        padding:
        4
        size:
        32
        name:
        "RandomCrop"
        name:
        "TorchvisionTransform"
      - ▶
        1:{} 2 keys
        ▶
        args:{} 1 key
        name:
        "RandomHorizontalFlip"
        name:
        "TorchvisionTransform"
  - ▶
    1:[] 2 items
    - 0:
      "trn,val"
    - ▶
      1:[] 2 items
      - ▶
        0:{} 2 keys
        args:{} 0 keys
        name:
        "ImageToTensor"
      - ▶
        1:{} 2 keys
        ▶
        args:{} 2 keys
        ▶
        mean:[] 3 items
        0:
        0.4914
        1:
        0.4822
        2:
        0.4465
        ▶
        std:[] 3 items
        0:
        0.2023
        1:
        0.1994
        2:
        0.201
        name:
        "Normalize"
- VERBOSE:
  "DEFAULT"
- wandb/group:
  "CIFAR10-AdditiveGradientNoiseExperiment"
- wandb/project:
  "CIFAR10-classification"

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 12 keys
- epoch:
  96
- epoch_trn/accuracy:
  0.930840015411377
- ▶
  epoch_trn/confusion_matrix:{} 7 keys
- epoch_trn/loss:
  0.20586252212524417
- epoch_val/accuracy:
  0.8878999948501587
- ▶
  epoch_val/confusion_matrix:{} 7 keys
- epoch_val/loss:
  0.34038427472114563
- lr-SGD:
  0.0159418577929397
- step/main_loss:
  0.1688019037246704
- step/noise-sigma:
  0.00002072513052553404
- step/train_loss:
  0.1688019037246704
- trainer/global_step:
  75,699

This run produced these artifacts as outputs. Total: 1. Learn more

wandb-history

run-3sxh76na-history:v0