Skip to content

Script that generates step size comparison for schedule free adamw ac… #45

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wyfEmma wants to merge 8 commits into
base: a100_scoring
Choose a base branch
from
Open

Script that generates step size comparison for schedule free adamw ac… #45

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
9628ec9
Logs for a100 scoring
aahladc Apr 3, 2026
3aae62f
Logs for a100 scoring
aahladc Apr 3, 2026
d3f92e5
Logs for a100 scoring
aahladc Apr 3, 2026
1fa23a7
add plotting script and plots for the schedule free adamw training curve
wyfEmma Jun 4, 2026
83a7554
revise the script for:
wyfEmma Jun 4, 2026
f83c0b6
the script now supports all algorithms and have the option to choose …
wyfEmma Jun 10, 2026
a6cbad4
Logs for a100 scoring
aahladc Jun 12, 2026
873d8cf
Script that generates step size comparison for schedule free adamw ac…
wyfEmma Jun 14, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
272 changes: 272 additions & 0 deletions configs/ademamix.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,272 @@
{
"0": {
"framework": "pytorch",
"workload": "imagenet_resnet",
"dataset": "imagenet",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_0",
"rng_seed": -297801539,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"1": {
"framework": "pytorch",
"workload": "imagenet_resnet",
"dataset": "imagenet",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_1",
"rng_seed": 1533933257,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"2": {
"framework": "pytorch",
"workload": "imagenet_resnet",
"dataset": "imagenet",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_2",
"rng_seed": 1726799996,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"3": {
"framework": "pytorch",
"workload": "imagenet_vit",
"dataset": "imagenet",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_0",
"rng_seed": -1402490634,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"4": {
"framework": "pytorch",
"workload": "imagenet_vit",
"dataset": "imagenet",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_1",
"rng_seed": -1500662809,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"5": {
"framework": "pytorch",
"workload": "imagenet_vit",
"dataset": "imagenet",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_2",
"rng_seed": 1332992545,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"6": {
"framework": "pytorch",
"workload": "fastmri",
"dataset": "fastmri",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_0",
"rng_seed": -1778082179,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"7": {
"framework": "pytorch",
"workload": "fastmri",
"dataset": "fastmri",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_1",
"rng_seed": -1306213645,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"8": {
"framework": "pytorch",
"workload": "fastmri",
"dataset": "fastmri",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_2",
"rng_seed": -1690267914,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"9": {
"framework": "pytorch",
"workload": "ogbg",
"dataset": "ogbg",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_0",
"rng_seed": 1781005226,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"10": {
"framework": "pytorch",
"workload": "ogbg",
"dataset": "ogbg",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_1",
"rng_seed": -2106912870,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"11": {
"framework": "pytorch",
"workload": "ogbg",
"dataset": "ogbg",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_2",
"rng_seed": 1081817396,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"12": {
"framework": "pytorch",
"workload": "wmt",
"dataset": "wmt",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_0",
"rng_seed": -1925775617,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"13": {
"framework": "pytorch",
"workload": "wmt",
"dataset": "wmt",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_1",
"rng_seed": 447881411,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"14": {
"framework": "pytorch",
"workload": "wmt",
"dataset": "wmt",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_2",
"rng_seed": -950757498,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"15": {
"framework": "pytorch",
"workload": "librispeech_deepspeech",
"dataset": "librispeech",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_0",
"rng_seed": -2040292039,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"16": {
"framework": "pytorch",
"workload": "librispeech_deepspeech",
"dataset": "librispeech",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_1",
"rng_seed": -343731362,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"17": {
"framework": "pytorch",
"workload": "librispeech_deepspeech",
"dataset": "librispeech",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_2",
"rng_seed": -1409407453,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"18": {
"framework": "pytorch",
"workload": "criteo1tb",
"dataset": "criteo1tb",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_0",
"rng_seed": -1283159881,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"19": {
"framework": "pytorch",
"workload": "criteo1tb",
"dataset": "criteo1tb",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_1",
"rng_seed": 670969102,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"20": {
"framework": "pytorch",
"workload": "criteo1tb",
"dataset": "criteo1tb",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_2",
"rng_seed": 432436421,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"21": {
"framework": "pytorch",
"workload": "librispeech_conformer",
"dataset": "librispeech",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_0",
"rng_seed": -1269082835,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"22": {
"framework": "pytorch",
"workload": "librispeech_conformer",
"dataset": "librispeech",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_1",
"rng_seed": -275718753,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"23": {
"framework": "pytorch",
"workload": "librispeech_conformer",
"dataset": "librispeech",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_2",
"rng_seed": 889690628,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"24": {
"framework": "pytorch",
"workload": "finewebedu_lm",
"dataset": "fineweb_edu_10B",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_0",
"rng_seed": -211830631,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"25": {
"framework": "pytorch",
"workload": "finewebedu_lm",
"dataset": "fineweb_edu_10B",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_1",
"rng_seed": 2074116566,
"tuning_ruleset": "self",
"num_tuning_trials": 1
},
"26": {
"framework": "pytorch",
"workload": "finewebedu_lm",
"dataset": "fineweb_edu_10B",
"submission_path": "submissions_algorithms/submissions/self_tuning/ademamix/submission.py",
"experiment_dir": "submissions_a100/ademamix/study_2",
"rng_seed": 1058885013,
"tuning_ruleset": "self",
"num_tuning_trials": 1
}
}
Loading
Loading