Add a narrative 'development chronicle' to the report notebook, drawn from
the project's commit history: six instructive episodes (BAR-token removal,
key normalization, the shared-bias aliasing bug, --bars vs early EOS,
fail-loud on empty bars, fine-tune lr/epoch search) plus three short notes
(open style tags, corpus hygiene, the 'time' name-shadowing trap). Each
episode ends with a generalizable lesson. Renumber the conclusions section
from 7 to 8 accordingly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Runnable end-to-end report combining narrative, code, and inline figures:
data and .chord format, transformer working principle, two-stage training
curves, perplexity (3.58 -> 2.15), distribution-shift plot with a reading
legend, qualitative examples, and a generation demo. Written in a
first-person student voice.
- CLAUDE.md: report is now a Jupyter notebook; GOST formatting dropped
- requirements.txt: add nbconvert + ipykernel (optional, for the notebook)
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
make_colab_zip.py now accepts --mode pretrain|finetune (default: pretrain).
Finetune mode bundles scripts/train.py + data/processed/user/{train,val}/*.pt
plus an optional --include-checkpoint flag for pretrained.pt.
notebooks/colab_finetune.ipynb covers the full Colab fine-tuning workflow:
upload zip → upload pretrained.pt → verify data → train → inspect → download.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
scripts/make_colab_zip.py packages src/, scripts/pretrain.py,
requirements.txt, and processed .pt files into hamori_colab.zip,
remapping data/processed/{train,val}/ -> data/processed/mcgill/{train,val}/
so pretrain.py finds the data without modification.
notebooks/colab_pretrain.ipynb guides through upload, extraction,
dependency install, training run, report display, and results download.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
H1K0