Optimizer comparison script (5 runs on Model B)
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 38/100
- Issue type
- Feature
- Clarity
- Mostly clear
- Activity status
- Active
- Tech stack
- python
- Domain
- machine-learning
Research direction
Work goes in scripts/compare_optimizers.py. Model B and its setup come from the blocking issues #20, #21 and #22, which are not in this payload, so read those first. Done means five history files, results/opt_<name>.json, one per optimizer configuration, each from a 30-epoch run that starts from the same saved initial state_dict.
Written by the indexing model from the issue text.
Description
Fair comparison: every run starts from the same initial weights.
Files: scripts/compare_optimizers.py
Tasks
- Create ModelB once, save its initial
state_dict, load it before every run - Runs: Adam lr=1e-3; SGD lr=0.01; SGD+momentum 0.5, 0.9, 0.99 (lr=0.01)
- 30 epochs each; save each history to
results/opt_<name>.json
Done when
Five history files exist in results/.
Depends on
#20 #21 #22
Close with a commit or PR message containing Closes #<this issue>.
- Dominant language
- Jupyter Notebook
- Stars
- 0
- Forks
- 0
- Avg merge
- 1m
- Merged PRs (30d)
- 3
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from VisionForgeCSE/CNN-For-Image-Classification
-
evaluation
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
-
evaluation good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
-
evaluation
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
training
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Optimizer factoryOpentraining
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
All issues in VisionForgeCSE/CNN-For-Image-Classification
Similar issues
-
Kumo-Tabular weights unreachable behind restrictive egress proxies (Xet + plain HTTP both fail)Open
Difficulty 2/5 1-3 hours Newbie friendliness 67/100
NVIDIA/structured-data-models#1091 ·
Maintainers usually reply within 1 day
-
BUG: kmeans raises a weight-shape error on duplicate background rowsPossibly taken @guptaishaan claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 5 days
-
bot-triaged module: docs triaged
Difficulty 1/5 1-3 hours Newbie friendliness 88/100
Maintainers usually reply within 1 day
-
CSV additive steering fails because SAE decoder bias is always includedPossibly taken @sdivyanshu90 claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
EleutherAI/lm-evaluation-harness#4364 ·
Maintainers usually reply within 1 day
-
[Bug]: CPU without Triton: slot-mapping fallback has a stale signature after #57169, V1 inference fails on the first forward stepPossibly taken A pull request linked to this issue is open or already merged. Open
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
vllm-project/vllm#61131 ·
Maintainers usually reply within 1 day