huanz

Huanz's group workspace

Group: composer_id-ASAP-perfmidi-sequence-MIDILike-bpe4

1-8

of 8

Tags

Notes

Author

huanz

State

Finished

Start time

March 7th, 2023 2:13:29 AM

Runtime

1h 7m 40s

Tracked hours

1h 7m 29s

Run path

huanz/symrep/ikswovsm

Linux-3.10.0-1160.53.1.el7.x86_64-x86_64-with-glibc2.17

Python version

3.9.7

Git repository

git clone https://github.com/anusfoil/SymRep.git

Git state

git checkout -b "composer_id-ASAP-perfmidi-sequence-fold7" 144f4e334be3f9d2702df061feb6415c5f4a7011

Command

/homes/hz009/Research/SymRep/experiments/train.py experiment.fold_idx=7 experiment.grouped=1 experiment.dataset=ASAP experiment.symrep=sequence experiment.lr=1e-5 experiment.device=[2] experiment.batch_size=6 sequence.BPE=4 sequence.max_seq_len=1000

System Hardware

CPU count	48
Logical CPU count	96
GPU count	8
GPU type	NVIDIA RTX A5000

W&B CLI Version

0.13.10

Group

composer_id-ASAP-perfmidi-sequence-MIDILike-bpe4

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 68 keys
- cfg/dataset/ASAP/dataset_dir:
  "/homes/hz009/Research/Datasets/asap-dataset/"
- cfg/dataset/ASAP/metadata_file:
  "/homes/hz009/Research/Datasets/asap-dataset/metadata-v1.3.csv"
- cfg/dataset/ATEPP/dataset_dir:
  "/homes/hz009/Research/Datasets/ATEPP-1.1/"
- cfg/dataset/ATEPP/metadata_file:
  "/homes/hz009/Research/Datasets/ATEPP-1.1/ATEPP-metadata-1.5.csv"
- cfg/dataset/PD/dataset_dir:
  "/homes/hz009/Research/Datasets/piano_difficulty/"
- cfg/dataset/PD/metadata_file:
  "/homes/hz009/Research/Datasets/piano_difficulty/labels.csv"
- cfg/experiment/artifact_dir:
  "'huanz/symrep/model-35lc0sy2:v9'"
- cfg/experiment/batch_size:
  6
- cfg/experiment/checkpoint_dir:
  "checkpoints/composer_id-ASAP-perfmidi-sequence-fold7"
- cfg/experiment/checkpoint_file:
  "checkpoints/composer_id-ASAP-perfmidi-sequence-fold7/epoch=49-step=1850.ckpt"
- cfg/experiment/data_save_dir:
  "/import/c4dm-datasets-ext/symrep_assets/sequence/ASAP/perfmidi"
- cfg/experiment/dataset:
  "ASAP"
- ▶
  cfg/experiment/device:[] 1 item
  - 0:
    2
- cfg/experiment/emb_dim:
  32
- cfg/experiment/epoch:
  300
- cfg/experiment/es_patience:
  60
- cfg/experiment/es_threshold:
  0.005
- cfg/experiment/exp_name:
  "composer_id-ASAP-perfmidi-sequence-fold7"
- cfg/experiment/feat_level:
  0
- cfg/experiment/fold_idx:
  7
- cfg/experiment/group_name:
  "composer_id-ASAP-perfmidi-sequence-MIDILike-bpe4"
- cfg/experiment/grouped:
  1
- cfg/experiment/input_format:
  "perfmidi"
- cfg/experiment/load_data:
  true
- cfg/experiment/load_model:
  false
- cfg/experiment/lr:
  0.00001
- cfg/experiment/lr_gamma:
  0.99
- cfg/experiment/random_seed:
  13
- cfg/experiment/restore_training:
  false
- cfg/experiment/symrep:
  "sequence"
- cfg/experiment/task:
  "composer_id"
- ▶
  cfg/graph/basic_edges:[] 7 items
- cfg/graph/bi_dir:
  true
- cfg/graph/conv_type:
  "SAGEConv"
- cfg/graph/hid_dim:
  256
- cfg/graph/homo:
  0
- cfg/graph/mid_window:
  0.03
- cfg/graph/n_layers:
  2
- cfg/matrix/bins:
  131
- cfg/matrix/n_channels:
  2
- ▶
  cfg/matrix/res_layers:[] 4 items
  - 0:
    1
  - 1:
    1
  - 2:
    1
  - 3:
    1
- cfg/matrix/resolution:
  600
- cfg/matrix/save_dir:
  "fix_time-(4|300|60|180)-600-0"
- cfg/segmentation/seg_beat:
  180
- cfg/segmentation/seg_num:
  4
- cfg/segmentation/seg_size:
  300
- model_backend:
  null
- model_frontend:
  null
- ▶
  segmentation:{} 5 keys
- ▶
  sequence:{} 12 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 19 keys
- epoch:
  128
- ▶
  graph_0:{} 4 keys
  - _type:
    "graph-file"
  - path:
    "media/graph/graph_0_summary_8685d30be079dc429e33.graph.json"
  - sha256:
    "8685d30be079dc429e33c8f6cccda33940c92ab1b090d9b07a49c176cbcba7a8"
  - size:
    7,282
- lr-Adam:
  0.00000279042088585059
- test_acc:
  0.8878504633903503
- test_auroc:
  0.8989617824554443
- test_fscore:
  0.728327751159668
- train_acc_epoch:
  1
- train_acc_step:
  1
- train_auroc_epoch:
  0.9090909361839294
- train_auroc_step:
  0.3636363744735718
- train_fscore_epoch:
  0.9090909361839294
- train_fscore_step:
  0.3636363744735718
- train_loss_epoch:
  0.06548554450273514
- train_loss_step:
  0.151602104306221
- trainer/global_step:
  11,264
- val_acc:
  0.9333333373069764
- val_auroc:
  0.895148754119873
- val_fscore:
  0.7471634149551392
- val_loss:
  0.29206714034080505

This run consumed these artifacts as inputs. Learn more

job

job-https___github.com_anusfoil_SymRep.git_experiments_train.py:v72

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

model

model-ikswovsm:v16

wandb-history

run-ikswovsm-history:v0