vocsep

Fosfrancesco's group workspace

Group: Composer Classification

test_f1

0.56807

0.47859

0.45297

0.4943

0.52523

0.5107

0.50472

0.32673

0.38419

0.51308

0.43444

0.36128

0.5331

0.40416

0.41589

0.50067

0.37007

0.39478

0.54893

0.53205

1-20

of 98

Tags

Notes

Author

melkisedeath

State

Finished

Start time

January 16th, 2024 2:29:22 PM

Runtime

18m 2s

Tracked hours

17m 57s

Run path

vocsep/MusGConv/f8o8gm3w

Linux-4.15.0-213-generic-x86_64-with-glibc2.27

Python version

3.9.18

Git repository

git clone git@github.com:manoskary/MusGConv.git

Git state

git checkout -b "MusGConv-2x64-lr=0.001-wd=0.0005-dr=0.5-jk=False" 24696d3a9746ad8ccd25692e58824162fc9b5aa1

Command

/share/hel/home/manos/codes/MusGConv/experiments/composer_classification.py --gpus 0 --use_wandb --wandb_entity vocsep --model MusGConv --use_reledge --seed 11 --mixed_features

System Hardware

CPU count	20
Logical CPU count	40
GPU count	4
GPU type	GeForce GTX 1080 Ti

W&B CLI Version

0.15.11

Group

Composer Classification

Job Type

MusGConv-woPE-wEF-woSEF-woEE+Mixed

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 34 keys
- activation:
  "relu"
- aggregation:
  "cat"
- batch_size:
  1,000
- conv_block:
  "MusGConv"
- dropout:
  0.5
- force_reload:
  false
- gpus:
  "0"
- hidden_features:
  64
- homogeneous:
  false
- input_features:
  23
- load_from_checkpoint:
  false
- lr:
  0.001
- metrical:
  false
- mixed_features:
  true
- model:
  "MusGConv"
- n_epochs:
  100
- n_hidden:
  64
- n_layers:
  2
- num_layers:
  2
- num_workers:
  20
- output_features:
  10
- pitch_embedding:
  null
- reg_loss_type:
  "la"
- return_edge_emb:
  false
- seed:
  11
- stack_convs:
  false
- tags:
  ""
- use_jk:
  false
- use_metrical:
  false
- use_reledge:
  true
- use_signed_features:
  false
- use_wandb:
  true
- wandb_entity:
  "vocsep"
- weight_decay:
  0.0005

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 10 keys
- epoch:
  100
- test_acc:
  0.8037634491920471
- test_f1:
  0.5680674314498901
- test_loss:
  0.9573708772659302
- train_acc:
  0.8403534889221191
- train_loss:
  0.4879223704338074
- trainer/global_step:
  600
- val_acc:
  0.5561403632164001
- val_f1:
  0.32416272163391113
- val_loss:
  1.9009090662002563

This run consumed these artifacts as inputs. Learn more

job

job-git_github.com_manoskary_MusGConv.git_experiments_composer_classification.py:v11

This run produced these artifacts as outputs. Total: 2. Learn more

model

model-f8o8gm3w:v0

wandb-history

run-f8o8gm3w-history:v0