imagining syntax

Text set in serif type with a dotted bar in the margin was drafted by an LLM (claude-fable-5) and sometimes reviewed by the author. The rest is the author's own. How to read this site

scaling → model-scale

model-scale

investigation

Intent

Intent: How model size gates agreement generalization \@{model-scale-intent}

This investigation asks how a model's size gates its ability to learn subject-verb number agreement well enough to generalize to unseen pairings. Size has two axes here, embedding width (n_embd) and depth (n_layer), and the member experiments vary each against the full α sweep: first the width ladder, then depth, then longer-budget continuations of both to separate what is a property of the architecture from what is a sign of undertraining at the paper's budget.

Referenced by (1 direct)

Direct references:

Conclusions

Conclusion: Width and depth are different axes, and bigger is not better \@{model-scale-conclusion}

The paper's configuration, 256 wide and two layers, sits near the top of the size range this task rewards, and the two ways of making the model bigger fail in different ways.

Conclusion: The two size axes come apart \@{model-scale-axes}

Width sets which solution the model can represent, following a capacity ladder from agreeing with the nearest noun through memorization to the general rule (the solution ladder), and past the paper's width the wide model splits by seed rather than improving (the 512 split). Depth is not capacity in the same sense: one layer already suffices for the rule (depth_v1), and added layers delay and degrade acquisition (delays and degrades) rather than failing to represent it.

Referenced by (1 direct)

Direct references:

The continuations settle what the paper's budget left ambiguous. The depth penalty at 1200 steps looked like it might be undertraining, and for the onset it partly is: given four times the budget the deeper arms' onset recovers (depth_long), but the recovery splits by seed (the effect splits) and longer training then erodes the peak (peak erosion), leaving a stopping window rather than a clean win. The width split does not recover at all: four times the budget leaves the 512-wide cohort split, so the split is width-intrinsic (msize_long), and it persists across every waypoint measured (the split persists). The 256-wide model, by contrast, has already peaked near the paper's budget and slips with more training (the budget optimum), the same post-peak erosion the training-dynamics work sees at fixed size. Read together the axes dissociate (msize_long): more width changes which basin a seed lands in, more depth changes how long it takes to get there.

What would change this reading. The width ladder tops out at 512 and the depth ladder at four layers, both at the default vocabulary; the vocabulary-scaling result already shows the capacity story bends with vocabulary size, so a wider grid over width × vocabulary is the natural next probe, and the seed-level mechanics of the 512 split belong to the bimodality thread, bimodality.

Experiments

Referenced by

model-scale-axes: Summer Summary
model-scale-conclusion: The intermediate peak is real but it is a slice of a moving target, The peak is universal, capacity caps it, and the holdout fraction is second order
model-scale-intent: How the result scales