OmniOpt2

Experiment overview

Setting	Value
Model for non-random steps	BOTORCH_MODULAR
Max. nr. evaluations	5
Number random steps	2
Nr. of workers (parameter)	5

Best RESULT, min (total: 5)

x	y	RESULT
218	4344.089648204856	2184344.089648205

Job Summary per Generation Node

Generation Node	Total	COMPLETED
SOBOL	5	5

Experiment parameters

Name	Type	Lower bound	Upper bound	Type	Log Scale?
x	range	123	1000	int	No
y	range	1234	5431	float	No

Number of evaluations

Failed	Succeeded	Running	Total
0	5	0	5

Result names and types

name	min/max
RESULT	min

Last progressbar status

2026-10-30 14:55:37 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, best RESULT: 2184344.089648205, ▆▁▃█▇, finishing jobs, finished 5 jobs

Git-Version

Commit: 62893ae80f6fd2c5fdcce1c4d576e2a43605f0bd

[INFO 10-30 14:55:17] ax.storage.sqa_store.with_db_settings_base: Ax SQL storage initialized with SQLAlchemy 2.1.6
Run-UUID: 21647bce-663a-458d-ad80-37cdb27ab5d6
  _________________________________________________
 /                                                 \
| OmniOpt2 - A small tweak, a big effect – the butt |
| erfly principle of tuning.                        |
 \                                                 /
  =================================================
                                                 \
                                                  \
                                                    ^__^
                                                    (oo)\_______
                                                    (__)\       )\/\
                                                        ||----w |
                                                        ||     ||
./omniopt --partition=alpha --live_share --debug --verbose --experiment_name=pip_test_experiment --mem_gb=1 --time=60 --worker_timeout=60 --max_eval=5 --num_parallel_jobs=5 --gpus=1 --num_random_steps=2 --follow --send_anonymized_usage_stats --result_names RESULT=min --run_program=ZWNobyAiUkVTVUxUOiAlKHgpJSh5KSI= --cpus_per_task=1 --nodes_per_job=1 --generate_all_jobs_at_once --model=BOTORCH_MODULAR --run_mode=local --occ_type=euclid --main_process_gb=8 --max_nr_of_zero_results=50 --slurm_signal_delay_s=0 --parameter x range 123 1000 int false --parameter y range 5431 1234 float false
⠋ Creating folder /home/runner/work/OmniOpt/OmniOpt/runs/pip_test_experiment/0...
Run-folder: /home/runner/work/OmniOpt/OmniOpt/runs/pip_test_experiment/0
Lower bound (5431.0) was larger than upper bound (1234.0) for parameter 'y'. Switched them.
[WARNING 10-30 14:55:18] ax.service.ax_client: Selecting a GenerationStrategy when using BatchTrials is in beta. Double check the recommended strategy matches your expectations.
See https://imageseg.scads.de/omniax/share?user_id=defaultuser&experiment_name=pip_test_experiment&run_nr=688 for live-results.


You have 4 CPUs available for the main process. No CUDA devices found.
Generation strategy: SOBOL for 2 steps and then BOTORCH_MODULAR for 3 steps.
Run-Program: echo "RESULT: %(x)%(y)"
Experiment parameters
┏━━━━━━┳━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━┓
┃ Name ┃ Type  ┃ Lower bound ┃ Upper bound ┃ Type  ┃ Log Scale? ┃
┡━━━━━━╇━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━┩
│ x    │ range │ 123         │ 1000        │ int   │ No         │
│ y    │ range │ 1234        │ 5431        │ float │ No         │
└──────┴───────┴─────────────┴─────────────┴───────┴────────────┘
Result-Names
┏━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓
┃ Result-Name ┃ Min or max? ┃
┡━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩
│ RESULT      │         min │
└─────────────┴─────────────┘
SOBOL, started new job                    :   0%|░░░░░░░░░░| 0/5 [00:01Best RESULT, min (total: 5)
┏━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓
┃ x   ┃ y                 ┃ RESULT            ┃
┡━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩
│ 218 │ 4344.089648204856 │ 2184344.089648205 │
└─────┴───────────────────┴───────────────────┘
Runtime Infos
┏━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┓
┃ Number of evaluations ┃ Min time  ┃ Max time  ┃ Average time ┃ Median time ┃
┡━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━━━╇━━━━━━━━━━━━━┩
│           5           │ 0.00 sec  │ 6.00 sec  │   1.20 sec   │  0.00 sec   │
└───────────────────────┴───────────┴───────────┴──────────────┴─────────────┘

╭─────────────────────────────────────────────────────────────── OmniOpt2 Run Summary ───────────────────────────────────────────────────────────────╮
│                                                                                                                                                    │
│  ✅  Optimization complete!                                                                                                                        │
│                                                                                                                                                    │
│    📊 Trials: 5 succeeded / 0 failed / 5 done / 5 submitted                                                                                        │
│    ⏱️  Duration: 28s                                                                                                                               │
│    🏆 Best RESULT: 2184344.089648205                                                                                                               │
│    📁 Results: /home/runner/work/OmniOpt/OmniOpt/runs/pip_test_experiment/0/results.csv                                                            │
│    🤖 Model: SOBOL                                                                                                                                 │
│                                                                                                                                                    │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, Started OmniOpt2 run...
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, getting new HP set #1/5 (no sbatch)
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, getting new HP set #2/5 (no sbatch)
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, getting new HP set #3/5 (no sbatch)
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, getting new HP set #4/5 (no sbatch)
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, getting new HP set #5/5 (no sbatch)
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, requested 5 jobs, got 5, 0.02 s/job
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, eval #1/5 start                    
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, eval #2/5 start                    
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, eval #3/5 start                    
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, eval #4/5 start                    
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, eval #5/5 start                    
2026-10-30 14:55:20 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, starting new job                   
2026-10-30 14:55:21 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, started new job                    
2026-10-30 14:55:29 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, new result: RESULT: 9754840.096120 
2026-10-30 14:55:30 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, best RESULT: 9754840.096120173, new result: RESULT: 2184344.089648
2026-10-30 14:55:30 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, best RESULT: 9754840.096120173, new result: RESULT: 3482518.379163
2026-10-30 14:55:30 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, best RESULT: 9754840.096120173, new result: RESULT: 6811890.896435
2026-10-30 14:55:35 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, best RESULT: 2184344.089648205, ▆▁▃█, new result: RESULT: 2871448.819864
2026-10-30 14:55:37 (0b21d388-619c-4e73-b515-5d3290b69e97): SOBOL, best RESULT: 2184344.089648205, ▆▁▃█▇, finishing jobs, finished 5 jobs

         Job submission durations          
┏━━━━━━━━━┳━━━━━━━━━┳━━━━━━┳━━━━━━━━━━━━━━┓
┃   Batch ┃ Seconds ┃ Jobs ┃ Time per job ┃
┡━━━━━━━━━╇━━━━━━━━━╇━━━━━━╇━━━━━━━━━━━━━━┩
│       1 │   1.197 │    5 │        0.239 │
├─────────┼─────────┼──────┼──────────────┤
│ Average │   1.197 │      │              │
│  Median │   1.197 │      │              │
│   Total │   1.197 │      │              │
│     Max │   1.197 │      │              │
│     Min │   1.197 │      │              │
└─────────┴─────────┴──────┴──────────────┘

           Model generation times            
┏━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━┳━━━━━━━━━━━━━━┓
┃ Iteration ┃ Seconds ┃ Jobs ┃ Time per job ┃
┡━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━╇━━━━━━━━━━━━━━┩
│         1 │   0.092 │    5 │        0.018 │
├───────────┼─────────┼──────┼──────────────┤
│   Average │   0.092 │      │              │
│    Median │   0.092 │      │              │
│     Total │   0.092 │      │              │
│       Max │   0.092 │      │              │
│       Min │   0.092 │      │              │
└───────────┴─────────┴──────┴──────────────┘

Arguments Overview

Key	Value
install	False
config_yaml	None
config_toml	None
config_json	None
num_random_steps	2
max_eval	5
run_program	[['ZWNobyAiUkVTVUxUOiAlKHgpJSh5KSI=']]
experiment_name	pip_test_experiment
mem_gb	1
parameter	[['x', 'range', '123', '1000', 'int', 'false'], ['y', 'range', '5431', '1234', 'float', 'false']]
continue_previous_job	None
experiment_constraints	None
run_dir	runs
modules
venv
seed	None
verbose_tqdm	False
model	BOTORCH_MODULAR
gridsearch	False
occ	False
show_sixel_scatter	False
show_sixel_general	False
show_sixel_trial_index_result	False
follow	True
wait_until_ended	False
send_anonymized_usage_stats	True
ui_url	None
root_venv_dir	/home/runner
exclude	None
main_process_gb	8
max_nr_of_zero_results	50
abbreviate_job_names	False
orchestrator_file	None
checkout_to_latest_tested_version	False
live_share	True
disable_tqdm	False
local_cpu_monitor	False
disable_previous_job_constraint	False
workdir
occ_type	euclid
result_names	['RESULT=min']
minkowski_p	2
signed_weighted_euclidean_weights
generation_strategy	None
generate_all_jobs_at_once	True
revert_to_random_when_seemingly_exhausted	False
load_data_from_existing_jobs	[]
n_estimators_randomforest	100
max_attempts_for_generation	20
external_generator	None
optuna_sampler	None
optuna_pruner	none
optuna_n_startup_trials	10
optuna_multivariate	False
optuna_group	False
optuna_constraints	False
optuna_n_ei_candidates	0
optuna_storage	None
optuna_study_name	omniopt_study
optuna_no_load_if_exists	False
optuna_extra_iters	1
username	None
max_failed_jobs	None
num_cpus_main_job	None
calculate_pareto_front_of_job	[]
show_generate_time_table	False
force_choice_for_ranges	False
max_abandoned_retrial	20
share_password	None
dryrun	False
db_url	None
run_program_once	None
worker_generator_path	None
save_to_database	False
range_max_difference	1000000
skip_search	False
nr_evals_per_arm	1
dump_config	None
formula	None
formula_mode	auto
formula_python_path	/home/runner/omniopt_via_pip_omniopt/bin/python3
dont_warm_start_refitting	False
refit_on_cv	False
fit_out_of_design	False
fit_abandoned	False
dont_jit_compile	False
num_restarts	20
raw_samples	1024
max_num_of_parallel_sruns	16
no_transform_inputs	False
no_normalize_y	False
transforms	[]
number_of_generators	1
num_parallel_jobs	5
worker_timeout	60
slurm_use_srun	False
time	60
partition	alpha
reservation	None
force_local_execution	False
slurm_signal_delay_s	0
nodes_per_job	1
cpus_per_task	1
account	None
gpus	1
dependency	None
run_mode	local
verbose	True
verbose_break_run_search_table	False
debug	True
flame_graph	False
memray	False
no_sleep	False
tests	False
show_worker_percentage_table_at_end	False
auto_exclude_defective_hosts	False
run_tests_that_fail_on_taurus	False
raise_in_eval	False
show_ram_every_n_seconds	0
show_generation_and_submission_sixel	False
just_return_defaults	False
prettyprint	False
runtime_debug	False
debug_stack_regex
debug_stack_trace_regex	None
show_func_name	False
beartype	False

This logs the CPU and RAM usage of the main worker process.

timestamp,ram_usage_mb,cpu_usage_percent
1793372118,927.93359375,27

`RESULT` (goal: minimize)

Best value: 2184344.0896482
Achieved at:
- x = 218 (r=1, strong positive correlation)
- run_time = 0 (r=-0.377, weak negative correlation)
- y = 4344.0896482049 (r=0.364, weak positive correlation)

Top-5 Best Results

Parameter Sensitivity Ranking

Parameters ranked by absolute Pearson correlation with each result. Stronger correlations (|r| ≥ 0.7) suggest the parameter has more influence on the outcome.

Convergence Analysis

Parameter statistics

Parameter	Min	Max	Mean	Std Dev	Count
run_time	0	6	1.2	2.4	5
RESULT	2184344.0896	9754840.0961	5021008.4562	2851338.1064	5
x	218	975	501.8	285.0848	5
y	1448.8199	4840.0961	3008.4562	1346.1354	5

Some single-run logs were not shared

By default only logs from failed or interrupted jobs are shared. Successful logs and logs above the upload cap were left out.

single_runs/6719 — successful job (logs are skipped by default)
single_runs/6721 — successful job (logs are skipped by default)
single_runs/6726 — successful job (logs are skipped by default)
single_runs/6730 — successful job (logs are skipped by default)
single_runs/6732 — successful job (logs are skipped by default)

To see these logs here as well, run one of these commands on the machine that has the run folder:

send_all_failed_logs

omniopt_share /home/runner/work/OmniOpt/OmniOpt/runs/pip_test_experiment/0 --update --username=defaultuser --send_all_failed_logs

send_all_single_runs

omniopt_share /home/runner/work/OmniOpt/OmniOpt/runs/pip_test_experiment/0 --update --username=defaultuser --send_all_single_runs

To view an omitted log locally instead, open it on the machine that has the run folder, e.g.:

less '/home/runner/work/OmniOpt/OmniOpt/runs/pip_test_experiment/0/single_runs/<job-id>/<job-id>_0_log.out'