shamim

Shamim's group workspace

Group: Augment

1-11

of 11

Tags

Notes

Author

shamim

State

Finished

Start time

June 3rd, 2023 9:17:44 PM

Runtime

6m 42s

Tracked hours

6m 33s

Run path

shamim/ActionNet/

Linux-5.4.0-97-generic-x86_64-with-glibc2.31

Python version

3.10.11

Git repository

git clone https://github.com/DataRaptor/ActionNet.git

Git state

git checkout -b "BASE-HS2-TL2-(Final)" e0828406e7926201ad5086a768cd46358267d476

Command

/home/ActionNet/src/train.py --group Augment --name "BASE HS2 TL2 (Final)" --n_epochs 13 --batch_size 256 --learning_rate 0.001 --dropout 0.2 --weight_decay 0 --hidden_size 512 --train_last_nlayer 2 --augment --num_workers 7

System Hardware

CPU count	32
Logical CPU count	64
GPU count	1
GPU type	Quadro RTX 5000

W&B CLI Version

0.15.3

Group

Augment

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 12 keys
- augement:
  true
- batch_size:
  256
- dropout:
  0.2
- hidden_size:
  512
- learning_rate:
  0.001
- n_epochs:
  13
- test_size:
  0.15
- test_split_seed:
  42
- train_last_nlayer:
  2
- valid_size:
  0.15
- valid_split_seed:
  42
- weight_decay:
  0

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 12 keys
- epoch:
  13
- test_acc:
  0.8023382425308228
- train_acc:
  0.8828125
- train_acc(avg):
  0.8631591796875
- train_loss:
  1.88446044921875
- train_loss(avg):
  1.8990753889083865
- train_step:
  415
- val_acc:
  0.7649999856948853
- val_loss:
  1.9884743690490725
- val_step:
  77
- valid_acc(avg):
  0.7811458706855774
- valid_loss(avg):
  1.9834805130958555

This run consumed these artifacts as inputs. Learn more

job

job-https___github.com_DataRaptor_ActionNet.git_src_train.py:v38

This run produced these artifacts as outputs. Learn more

wandb-history

run-myivme4t-history:v0