20221011_211002 | kimsehun725 Workspace – Weights & Biases

Skip to main content

Kimsehun725's group workspace

Group: 20221011_211002

1

1

1

1-3

of 3

Tags

Notes

Author

State

Crashed

Start time

October 11th, 2022 1:06:34 PM

Runtime

21m 43s

Tracked hours

21m 43s

Run path

kimsehun725/my_vae/3m9bgnib

OS

Linux-3.10.0-1062.9.1.el7.x86_64-x86_64-with-glibc2.29

Python version

3.8.10

Command

src/train.py

System Hardware

CPU count	40
GPU count	4
GPU type	Tesla V100-SXM2-32GB

W&B CLI Version

0.13.4

Group

20221011_211002

Job Type

step3_tset02

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 14 keys
- args/baseline:
  false
- args/baseline_epochs:
  192
- args/baseline_lr:
  0.005
- args/bins_per_octave:
  24
- args/down_sampling_rate:
  22,050
- args/estimator_feature_type:
  "cqt"
- args/hop_length:
  512
- args/lr:
  0.005
- args/n_bins:
  192
- args/pretrain_feature_type:
  "cqt"
- args/pretrain_lr:
  0.001
- args/step2_epochs:
  64
- args/step3_epochs:
  192
- args/train_ratio:
  0.9

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 9 keys
- epoch:
  147
- lr-RAdam:
  0.0003125
- train/loss:
  0.03880560025572777
- trainer/global_step:
  1,183
- val/f1:
  0.7781568188328429
- val/loss:
  0.03137755021452904
- val/precision:
  0.7800866704954837
- val/recall:
  0.7762364921030757
- val/TDR:
  0.9548185071574642

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

run-3m9bgnib-history:v0

Loading...