platform-demo-scripts/experiments/sweep_basicphase_ae.yaml

name: BasicPhaseAE
method: bayes
metric:
  goal: minimize
  name: val_loss
parameters:
  model_name:
    value:
      - BasicPhaseAE
  batch_size:
    values: [64, 128, 256]
  max_epochs:
    value:
      - 30
  learning_rate:
    values: [0.01, 0.005, 0.001]
fixed PhaseNet normalization, added reducing lr on plateau 2024-07-14 10:32:37 +02:00			`name: BasicPhaseAE`
Added logging MAE for the best runs, option to run a pipeline on a specific dataset, template bash scripts, GPLv3 license. Modified behavior of generating eval targets, it is skipped if targets already exist. 2023-10-12 14:27:53 +02:00			`method: bayes`
			`metric:`
			`goal: minimize`
			`name: val_loss`
			`parameters:`
			`model_name:`
			`value:`
			`- BasicPhaseAE`
			`batch_size:`
fixed PhaseNet normalization, added reducing lr on plateau 2024-07-14 10:32:37 +02:00			`values: [64, 128, 256]`
Added logging MAE for the best runs, option to run a pipeline on a specific dataset, template bash scripts, GPLv3 license. Modified behavior of generating eval targets, it is skipped if targets already exist. 2023-10-12 14:27:53 +02:00			`max_epochs:`
			`value:`
fixed PhaseNet normalization, added reducing lr on plateau 2024-07-14 10:32:37 +02:00			`- 30`
Added logging MAE for the best runs, option to run a pipeline on a specific dataset, template bash scripts, GPLv3 license. Modified behavior of generating eval targets, it is skipped if targets already exist. 2023-10-12 14:27:53 +02:00			`learning_rate:`
fixed PhaseNet normalization, added reducing lr on plateau 2024-07-14 10:32:37 +02:00			`values: [0.01, 0.005, 0.001]`