RYDE-WORK/autoresearch
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/autoresearch.git synced 2026-07-22 05:04:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

cleanup more references to spawn.sh

Browse Source
This commit is contained in:
Andrej Karpathy 2026-03-06 22:36:20 +00:00
parent ae81d55904
commit 69eb7f9b99
1 changed files with 5 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
program.md
View File

@ -4,24 +4,19 @@ This is an experiment to have the LLM do its own research.
## Setup ## Setup
Check your git state. There are two cases: To set up a new experiment, work with the user to:
**If launched via `spawn.sh` (multi-agent):** The branch and worktree already exist. You are already on the right branch. Skip to step 3. 1. **Agree on a run tag**: propose a tag based on today's date (e.g. `mar5`). The branch `autoresearch/<tag>` must not already exist — this is a fresh run.
**If launched manually (single agent):**
1. **Agree on a run tag** with the human: propose a tag based on today's date (e.g. `mar5`). The branch `autoresearch/<tag>` must not already exist — this is a fresh run.
2. **Create the branch**: `git checkout -b autoresearch/<tag>` from current master. 2. **Create the branch**: `git checkout -b autoresearch/<tag>` from current master.
**Then, in both cases:**
3. **Read the in-scope files**: The repo is small. Read these files for full context: 3. **Read the in-scope files**: The repo is small. Read these files for full context:
- `constants.py` — fixed constants (`MAX_SEQ_LEN`, `TIME_BUDGET`, `EVAL_TOKENS`). Do not modify. - `constants.py` — fixed constants (`MAX_SEQ_LEN`, `TIME_BUDGET`, `EVAL_TOKENS`). Do not modify.
- `prepare.py` — data prep, tokenizer, dataloader, evaluation. Do not modify. - `prepare.py` — data prep, tokenizer, dataloader, evaluation. Do not modify.
- `train.py` — the file you modify. Model architecture, optimizer, training loop. - `train.py` — the file you modify. Model architecture, optimizer, training loop.
4. **Verify data exists**: Check that `~/.cache/autoresearch/` contains data shards and a tokenizer. If not, tell the human to run `uv run prepare.py`. 4. **Verify data exists**: Check that `~/.cache/autoresearch/` contains data shards and a tokenizer. If not, tell the human to run `uv run prepare.py`.
5. **Initialize results.tsv**: Create `results.tsv` with header row and baseline entry. The baseline results are already known from the output format section below (val_bpb: 0.997900, peak_vram_mb: 45060.2). Do NOT re-run the baseline — just record it. 5. **Initialize results.tsv**: Create `results.tsv` with header row and baseline entry. The baseline results are already known from the output format section below (val_bpb: 0.997900, peak_vram_mb: 45060.2). Do NOT re-run the baseline — just record it.
6. **Confirm and go**: If a human is present, confirm setup looks good. If launched via `spawn.sh`, proceed directly into the autonomous experiment loop. 6. **Confirm and go**: Confirm setup looks good.
Once you get confirmation, kick off the experimentation.
## Experimentation ## Experimentation