Add lzma6 submission (1.172 bpb, 10min_16mb)

[lee101]

Summary

• Adds lzma6 record for the 10min_16mb track
• val_bpb: 1.17217075, val_loss: 1.97916121
• 12196 steps, artifact size 15.3MB
• Author: lee101

Details

• Seed 1337 result included
• INT8 quantized model with LZMA compression

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: be1edf065b

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Point the experiment manifest at the new LZMA trainer

The manifest still tells reruns to execute records/track_10min_16mb/2026-03-19_SlidingWindow_FP16Emb_10L_MuonWD_OvertoneInit/train_gpt.py, but that script hardcodes zlib.compress(...) and logs final_int8_zlib_roundtrip_exact (.../train_gpt.py:1228-1246,1287-1291). In other words, replaying this experiment.json cannot reproduce the LZMA-6 artifact or metric recorded in records/lzma6/result.json, so the included reproduction metadata is currently wrong.

Useful? React with 👍 / 👎.

[lee101]

i do have the model for this hmm its an old run here though i may still have a better submission coming :)