Tier 10 = 0.94: highest_tier 9->10 (MAX), overall 0.886->0.978

Add 2048-bit carry-aware TCN cell (weights2048.pt, LFS) via octave
transfer from the 1024 cell + two-stage polish. model.py CELL_WIDTHS
+= 2048; manifest + card updated. highest_tier_above_90 = 10 (the
benchmark maximum), overall_accuracy 0.978, deterministic, inference
170s/1100, artifact 0.77 GB.

README.md

@@ -1,10 +1,11 @@
 # horner_rnn
 
-A compliant bit-sequential RNN that **clears tiers 1-9** (primes up to 2^1024) on the public
-benchmark — tiers 1-3 = 100%, tier 4 = 99%, tier 5 = 99%, tier 6 = 97%, tier 7 = 98%,
-tier 8 = 92%, **tier 9 = 99%** — so `highest_tier_above_90 = 9`, overall_accuracy **0.886**.
-Its capability comes from *learning an algorithmic step* rather than memorising finite
-multiplication tables, and it verifiably generalises to primes never seen in training.
+A compliant bit-sequential RNN that **clears every reduction tier, 1 through 10** (primes up to
+2^2048) on the public benchmark — tiers 1-3 = 100%, tier 4 = 99%, tier 5 = 99%, tier 6 = 97%,
+tier 7 = 98%, tier 8 = 92%, tier 9 = 99%, **tier 10 = 94%** — so `highest_tier_above_90 = 10`
+(the maximum), overall_accuracy **0.978**. Its capability comes from *learning an algorithmic
+step* rather than memorising finite multiplication tables, and it verifiably generalises to
+primes never seen in training.
 
 ## The idea
 
@@ -30,10 +31,10 @@ The single-step function is **piecewise linear** (`2t + bit*b`, then subtract 0,
 `2p`), which is why it generalises across primes where the full bilinear map does not:
 held-out-prime validation accuracy tracks training accuracy throughout (no memorisation gap).
 
-## Seven cells, routed by prime size
+## Eight cells, routed by prime size
 
 The recurrence is exact only if the state is wide enough to hold the residue, so the cell is
-trained per bit-width. The model ships seven and routes each problem to the narrowest cell
+trained per bit-width. The model ships eight and routes each problem to the narrowest cell
 whose state holds its prime:
 
 | Cell | Primes | Tiers | Architecture | Params | Public benchmark |
@@ -45,11 +46,12 @@ whose state holds its prime:
 | 256-bit | `< 2^256` | 7 | carry-aware TCN, 12 blocks, dil 1..128 | ~4.7M | tier 7 = 0.98 |
 | 512-bit | `< 2^512` | 8 | carry-aware TCN, 14 blocks, dil 1..256 | ~5.5M | tier 8 = 0.92 |
 | 1024-bit | `< 2^1024` | 9 | carry-aware TCN, 12 blocks, dil 1..512 | ~4.7M | tier 9 = 0.99 |
+| 2048-bit | `< 2^2048` | 10 | carry-aware TCN, 13 blocks, dil 1..1024 | ~5.1M | tier 10 = 0.94 |
 
-For `p >= 2^1024` (outside all regimes) the model emits the honest `[0]` fallback without
+For `p >= 2^2048` (outside all regimes) the model emits the honest `[0]` fallback without
 invoking the network.
 
-## The carry-aware TCN (tiers 5-9)
+## The carry-aware TCN (tiers 5-10)
 
 A modular Horner step hides two long carry chains — the `2t + bit*b` addition (carry flows
 LSB->MSB) and the compare-and-subtract reduction against `p` (borrow flows MSB->LSB). A
@@ -150,17 +152,35 @@ Select the cell by **benchmark score, not val-chain or eps** (the lower-eps EMA
 checkpoint against the exact public cases before shipping:
 `python exploration/score_tier9.py checkpoints/horner1024_match.pt`.
 
+### Tier 10 via octave transfer
+
+The **2048-bit (tier-10) cell is bootstrapped from the 1024-bit cell, not trained from
+scratch** — at this width the carry circuit is too expensive to rediscover. Because the conv
+weights are width-invariant in shape and the carry rule is position-invariant, the 1024 cell's
+weights copy verbatim into a 2048-position cell, plus one identity-initialised dil=1024 block
+to extend the receptive field (`exploration/transfer_1024_to_2048.py`; no-train eps 0.74 on
+true 2048-bit primes — the rule transfers partially). Then the same benchmark-width-matched
+polish, in two stages: a first pass (lr 2e-4) relearns the high-bit reduction fast (eps
+0.74 → ~9e-4) but oscillates at high lr; a **low-lr tail (lr 6e-5, accum 20, margin loss)**
+settles the per-step error below 5e-5 so the 2048-step chain clears **tier 10 = 0.94**. Full
+recipe and findings: `exploration/TIER10_NOTES.md`. Two new flags make 2048-bit tractable:
+`--max-rows` (subsample the trajectory micro-batch; grad-checkpointing 13 blocks at 2048-bit
+OOMs otherwise) and disk-cached prime pools (`--build-pools-only`; gmpy2 `next_prime` is
+~227 ms/prime at 2048-bit). Validate with `python exploration/score_tier10.py <ckpt>`.
+
 ## Score (public benchmark, fixed seed)
 
 | Total problems | overall_accuracy | highest_tier_above_90 | deterministic |
 |---|---|---|---|
-| **1100** | **0.886** | **9** | True |
+| **1100** | **0.978** | **10** (max) | True |
 
 Per-tier at total=1100: tier 1 **1.00**, tier 2 **1.00**, tier 3 **1.00**, tier 4 **0.99**,
-tier 5 **0.99**, tier 6 **0.97**, tier 7 **0.98**, tier 8 **0.92**, tier 9 **0.99**; tier 0
-**0.53** (pure multiplication, primes near each width's maximum — a partially-covered separate
-regime) and tier 10 at the 0.02 edge-case floor (the `[0]` fallback, `p >= 2^1024`). Inference
-for all 1100 problems runs well within the 300s budget (tier 9 = 40s); artifact 0.75 GB.
+tier 5 **0.99**, tier 6 **0.97**, tier 7 **0.98**, tier 8 **0.92**, tier 9 **0.99**,
+tier 10 **0.94** (overall_accuracy is the mean over tiers 1-10). Tier 0 (pure multiplication,
+primes near each width's maximum — a separate regime, not in overall_accuracy) is **0.63**, up
+from 0.53 because its largest primes in `[2^1024, 2^2048)` now route to the 2048 cell instead
+of the `[0]` fallback. Inference for all 1100 problems is 170s, within the 300s budget (the
+2048-step tier-10 scan is the bulk); artifact 0.77 GB.
 
 ## Status under the rules
 
@@ -173,8 +193,8 @@ for all 1100 problems runs well within the 300s budget (tier 9 = 40s); artifact
 - **Principle 2, measured** (`exploration/compliance_perturb.py`): perturbing the cell weights
   with Gaussian noise scaled to each tensor's std collapses accuracy, and an untrained cell is
   at the floor — so the capability is in the trained parameters, not the architecture (e.g.
-  tier 6 0.97 -> 0.11, tier 7 0.98 -> 0.03, tier 8 0.92 -> 0.04, tier 9 0.99 -> 0.04
-  at σ=0.25; untrained 0.00 for all).
+  tier 6 0.97 -> 0.11, tier 7 0.98 -> 0.03, tier 8 0.92 -> 0.04, tier 9 0.99 -> 0.04,
+  tier 10 0.94 -> 0.04 at σ=0.25; untrained 0.00 for all).
 - Generalisation against memorisation: 10% of primes at each bit-width were held out of
   training entirely; chain accuracy on them matches the training primes, and a fresh random
   eval seed still scores ~0.99 on tier 9.
@@ -182,8 +202,9 @@ for all 1100 problems runs well within the 300s budget (tier 9 = 40s); artifact
 
 ## What remains
 
-Tier 0 (pure multiplication, never reduced, primes near each width's maximum) and tier 10
-(`p >= 2^1024`, a 2048-step chain) are the open frontier. The tier-10 route is octave transfer:
-copy the 1024-bit cell's width-invariant carry rule into a 2048-position cell, splice one
-identity-initialised dilation block to extend the receptive field, and polish on the
-benchmark-width-matched distribution — the same recipe that cleared tier 9.
+Every reduction tier, **1 through 10, is above 90%**, so `highest_tier_above_90 = 10` is at the
+ceiling of the benchmark. The only sub-0.90 regime left is **tier 0** (pure multiplication, never
+reduced, primes near each width's maximum), now at **0.63** — and tier 0 is excluded from
+`overall_accuracy`, so it moves neither ranking key. Lifting it further (its near-2^k primes are
+a width blind-spot, the same class of gap that hid in the rushed 1024 cell) and re-polishing
+tier 8's 0.92 are the remaining tiebreaker-only gains; the primary metric has no headroom left.

manifest.json

@@ -2,6 +2,6 @@
   "entry_class": "model.HornerRNN",
   "output_base": 2,
   "framework": "pytorch",
-  "model_description": "Bit-sequential RNN (~187M params across seven cells) for primes up to 2^1024. Reads the bits of a mod p MSB-first, one per step, conditioned on (b mod p, p) in binary; the hidden state is a quantized bit vector (hard binary bottleneck) and the transition function must learn the Horner step (t, bit, b, p) -> (2t + bit*b) mod p to make the recurrence end on the right answer. Seven cells are shipped and routed by prime size: a 16-bit cell (MLP, width 4096 depth 4, ~50M params) for p < 2^16 covering tiers 1-3, a 32-bit cell (MLP, width 6144 depth 4, ~114M params) for p < 2^32 covering tier 4, a 64-bit cell for p < 2^64 covering tier 5 that is a CARRY-AWARE TCN (8 residual blocks, 256 channels, dilations cycling 1..32, ~3.2M params), a 128-bit cell for p < 2^128 covering tier 6 that is a CARRY-AWARE TCN: a non-causal dilated 1D-convolutional network over the 128 bit-positions (10 residual blocks, 256 channels, dilations cycling 1..64 so the receptive field spans all 128 bits, ~3.9M params), a 256-bit cell for p < 2^256 covering tier 7 that uses the SAME carry-aware TCN architecture scaled to 256 bit-positions (12 residual blocks, 256 channels, dilations cycling 1..128, ~4.7M params) reaching tier 7 = 0.98, and a 512-bit cell for p < 2^512 covering tier 8 that is the same carry-aware TCN scaled to 512 bit-positions (14 residual blocks, 256 channels, dilations cycling 1..256, ~5.5M params) reaching tier 8 = 0.92, and a 1024-bit cell for p < 2^1024 covering tier 9 that is the same carry-aware TCN scaled to 1024 bit-positions (12 residual blocks, 256 channels, dilations cycling 1..512, ~4.7M params) reaching tier 9 = 0.99. The per-step error floor rises with bit-width, so the 512- and 1024-bit cells were trained with gradient accumulation (a large effective batch lowers the per-step error noise floor) to recover the precision a 512-/1024-step chain needs to clear 0.90. The convolution is weight-shared across bit positions, so it learns ONE carry/borrow rule applied everywhere (non-causally, so the addition carry can flow LSB->MSB and the mod-p compare/borrow MSB->LSB) instead of a full-width MLP learning a separate position-function per bit; this inductive bias drives the per-step error far below what an MLP cell reaches and is what makes the 128/256/512-bit chains (which compound the per-step error over 128/256/512 steps) accurate. Final state bits are emitted MSB-first as the base-2 answer. For p >= 2^1024 emits the honest [0] fallback without invoking the network.",
-  "training_description": "Each transition cell trained from random init on (t, bit, b, p) -> (2t + bit*b) mod p single-step examples over its prime range (16-bit: all primes < 2^16; 32-bit and 64-bit: random primes sampled uniform-by-value in [2^16, 2^32) and [2^33, 2^64) to match the test generator's randrange+nextprime distribution), with half of each batch mined near the comparison boundary (2t + bit*b within +/-2 of a multiple of p) where errors concentrate. BCE per state bit, AdamW + cosine decay + gradient clipping + LR warmup, EMA weights checkpointed by full-chain validation accuracy on a held-out 10% of primes never seen in training — val accuracy tracks train accuracy, i.e. the cells generalise across primes rather than memorising them. The 64-bit cell is a carry-aware TCN (like the 128/256/512-bit cells) trained on TRUE Horner-trajectory single steps over distinct 62-64 bit primes, reaching tier 5 = 0.99. It replaced an earlier 944MB MLP cell that also scored ~0.98 on tier 5 but had a blind spot on primes very close to 2^64 (the carry-aware conv generalises to the top-of-range reduction where the unstructured MLP did not); the TCN fixes that and shrinks the cell from 944MB to ~13MB. The 128-bit (tier-6) cell is the carry-aware TCN, trained the same way — single-step BCE on TRUE Horner-trajectory states (t, bit, b, p) -> (2t + bit*b) mod p — from random init over a high-diversity pool of thousands of distinct 124-128 bit primes (so it generalises across primes rather than memorising the conditional subtraction for a few). Its weight-shared dilated-convolution inductive bias reaches a per-step error roughly 15x lower than the same-task MLP cell, giving 0.97 full-chain accuracy on held-out 124-128 bit primes; same supervised single-step objective, no backprop through the recurrence, AdamW + cosine decay + grad clip + EMA checkpointed by held-out full-chain accuracy. The 256-bit (tier-7) cell is the same carry-aware TCN scaled to 256 bit-positions (dilations cycling 1..128), trained identically — single-step BCE on TRUE Horner-trajectory states over a high-diversity pool of distinct 252-256 bit primes — reaching a per-step error low enough that the 256-step chain holds at 0.98 full-chain accuracy on held-out 252-256 bit primes. The 512-bit (tier-8) cell is the same carry-aware TCN scaled to 512 bit-positions (dilations cycling 1..256), trained on true-trajectory single steps over distinct 510-512 bit primes; the per-step error floor rises with width, so this cell additionally uses gradient accumulation (--accum: a larger effective batch lowers the gradient-noise floor on per-step error) to drive the 512-step chain to tier 8 = 0.92. The 1024-bit (tier-9) cell is the same carry-aware TCN scaled to 1024 bit-positions (12 residual blocks, dilations cycling 1..512), and exposes a finding specific to wide primes: the test generator draws p value-uniform in [2^513, 2^1024), so a large fraction of tier-9 primes are SHORTER than 1024 bits, and the conditional-subtraction reduction boundary lands at p's most-significant set bit -- at a DIFFERENT position for each prime width. A cell trained only on near-2^1024 primes learns that boundary at one position and scores ~0.00 on shorter primes (this gave tier 9 = 0.73, dominated by the single ~1020-bit benchmark prime failing entirely, 0/22). Training instead on a mix of value-uniform primes (benchmark-faithful) and bit-length-uniform primes over [990,1024] (equal weight to every boundary position) lets the weight-shared convolution learn the reduction at every MSB position; combined with gradient accumulation (--accum 16) and a worst-bit margin loss for the precision tail, this drives the 1024-step chain to tier 9 = 0.99, robust across prime widths (held-out value-uniform validation chain 0.99, per-width 1015-1024 all ~0.99). Weight-perturbation compliance (exploration/compliance_perturb.py): each cell's accuracy at sigma=0 collapses toward the floor as the weights are perturbed and an untrained re-init scores 0.00 — e.g. tier 6 0.97 -> 0.11 (sigma=0.25), tier 7 0.98 -> 0.03 (sigma=0.25), tier 8 0.92 -> 0.04 (sigma=0.25), tier 9 0.99 -> 0.04 (sigma=0.25), untrained 0.00 for all — so the arithmetic resides in the trained parameters. Training scripts: train.py (16-bit), exploration/train_horner32.py (32-bit), exploration/train_horner128_bigru.py --arch tcn (128-bit carry-aware TCN), exploration/train_horner_tcn.py --bits 64 / --bits 256 / --bits 512 --accum 2 (64-, 256- and 512-bit carry-aware TCN); --bits 1024 --lo-bits 513 --bitlen-frac 0.4 --bitlen-lo 990 --accum 16 --margin-weight 0.5 (1024-bit carry-aware TCN, benchmark-width-matched)."
+  "model_description": "Bit-sequential RNN (~192M params across eight cells) for primes up to 2^2048. Reads the bits of a mod p MSB-first, one per step, conditioned on (b mod p, p) in binary; the hidden state is a quantized bit vector (hard binary bottleneck) and the transition function must learn the Horner step (t, bit, b, p) -> (2t + bit*b) mod p to make the recurrence end on the right answer. Eight cells are shipped and routed by prime size: a 16-bit cell (MLP, width 4096 depth 4, ~50M params) for p < 2^16 covering tiers 1-3, a 32-bit cell (MLP, width 6144 depth 4, ~114M params) for p < 2^32 covering tier 4, a 64-bit cell for p < 2^64 covering tier 5 that is a CARRY-AWARE TCN (8 residual blocks, 256 channels, dilations cycling 1..32, ~3.2M params), a 128-bit cell for p < 2^128 covering tier 6 that is a CARRY-AWARE TCN: a non-causal dilated 1D-convolutional network over the 128 bit-positions (10 residual blocks, 256 channels, dilations cycling 1..64 so the receptive field spans all 128 bits, ~3.9M params), a 256-bit cell for p < 2^256 covering tier 7 that uses the SAME carry-aware TCN architecture scaled to 256 bit-positions (12 residual blocks, 256 channels, dilations cycling 1..128, ~4.7M params) reaching tier 7 = 0.98, and a 512-bit cell for p < 2^512 covering tier 8 that is the same carry-aware TCN scaled to 512 bit-positions (14 residual blocks, 256 channels, dilations cycling 1..256, ~5.5M params) reaching tier 8 = 0.92, and a 1024-bit cell for p < 2^1024 covering tier 9 that is the same carry-aware TCN scaled to 1024 bit-positions (12 residual blocks, 256 channels, dilations cycling 1..512, ~4.7M params) reaching tier 9 = 0.99, and a 2048-bit cell for p < 2^2048 covering tier 10 that is the same carry-aware TCN scaled to 2048 bit-positions (13 residual blocks, 256 channels, dilations cycling 1..1024, ~5.1M params) reaching tier 10 = 0.94. The per-step error floor rises with bit-width, so the 512-, 1024- and 2048-bit cells were trained with gradient accumulation (a large effective batch lowers the per-step error noise floor) to recover the precision a 512-/1024-/2048-step chain needs to clear 0.90. The convolution is weight-shared across bit positions, so it learns ONE carry/borrow rule applied everywhere (non-causally, so the addition carry can flow LSB->MSB and the mod-p compare/borrow MSB->LSB) instead of a full-width MLP learning a separate position-function per bit; this inductive bias drives the per-step error far below what an MLP cell reaches and is what makes the 128/256/512-bit chains (which compound the per-step error over 128/256/512 steps) accurate. Final state bits are emitted MSB-first as the base-2 answer. For p >= 2^2048 emits the honest [0] fallback without invoking the network.",
+  "training_description": "Each transition cell trained from random init on (t, bit, b, p) -> (2t + bit*b) mod p single-step examples over its prime range (16-bit: all primes < 2^16; 32-bit and 64-bit: random primes sampled uniform-by-value in [2^16, 2^32) and [2^33, 2^64) to match the test generator's randrange+nextprime distribution), with half of each batch mined near the comparison boundary (2t + bit*b within +/-2 of a multiple of p) where errors concentrate. BCE per state bit, AdamW + cosine decay + gradient clipping + LR warmup, EMA weights checkpointed by full-chain validation accuracy on a held-out 10% of primes never seen in training — val accuracy tracks train accuracy, i.e. the cells generalise across primes rather than memorising them. The 64-bit cell is a carry-aware TCN (like the 128/256/512-bit cells) trained on TRUE Horner-trajectory single steps over distinct 62-64 bit primes, reaching tier 5 = 0.99. It replaced an earlier 944MB MLP cell that also scored ~0.98 on tier 5 but had a blind spot on primes very close to 2^64 (the carry-aware conv generalises to the top-of-range reduction where the unstructured MLP did not); the TCN fixes that and shrinks the cell from 944MB to ~13MB. The 128-bit (tier-6) cell is the carry-aware TCN, trained the same way — single-step BCE on TRUE Horner-trajectory states (t, bit, b, p) -> (2t + bit*b) mod p — from random init over a high-diversity pool of thousands of distinct 124-128 bit primes (so it generalises across primes rather than memorising the conditional subtraction for a few). Its weight-shared dilated-convolution inductive bias reaches a per-step error roughly 15x lower than the same-task MLP cell, giving 0.97 full-chain accuracy on held-out 124-128 bit primes; same supervised single-step objective, no backprop through the recurrence, AdamW + cosine decay + grad clip + EMA checkpointed by held-out full-chain accuracy. The 256-bit (tier-7) cell is the same carry-aware TCN scaled to 256 bit-positions (dilations cycling 1..128), trained identically — single-step BCE on TRUE Horner-trajectory states over a high-diversity pool of distinct 252-256 bit primes — reaching a per-step error low enough that the 256-step chain holds at 0.98 full-chain accuracy on held-out 252-256 bit primes. The 512-bit (tier-8) cell is the same carry-aware TCN scaled to 512 bit-positions (dilations cycling 1..256), trained on true-trajectory single steps over distinct 510-512 bit primes; the per-step error floor rises with width, so this cell additionally uses gradient accumulation (--accum: a larger effective batch lowers the gradient-noise floor on per-step error) to drive the 512-step chain to tier 8 = 0.92. The 1024-bit (tier-9) cell is the same carry-aware TCN scaled to 1024 bit-positions (12 residual blocks, dilations cycling 1..512), and exposes a finding specific to wide primes: the test generator draws p value-uniform in [2^513, 2^1024), so a large fraction of tier-9 primes are SHORTER than 1024 bits, and the conditional-subtraction reduction boundary lands at p's most-significant set bit -- at a DIFFERENT position for each prime width. A cell trained only on near-2^1024 primes learns that boundary at one position and scores ~0.00 on shorter primes (this gave tier 9 = 0.73, dominated by the single ~1020-bit benchmark prime failing entirely, 0/22). Training instead on a mix of value-uniform primes (benchmark-faithful) and bit-length-uniform primes over [990,1024] (equal weight to every boundary position) lets the weight-shared convolution learn the reduction at every MSB position; combined with gradient accumulation (--accum 16) and a worst-bit margin loss for the precision tail, this drives the 1024-step chain to tier 9 = 0.99, robust across prime widths (held-out value-uniform validation chain 0.99, per-width 1015-1024 all ~0.99). The 2048-bit (tier-10) cell was bootstrapped by OCTAVE TRANSFER rather than from random init: the conv weights are width-invariant in shape and the carry rule is position-invariant, so the trained 1024-bit cell's weights copy verbatim into a 2048-position cell, plus one identity-initialised dil=1024 residual block to extend the receptive field across all 2048 positions (exploration/transfer_1024_to_2048.py; no-train single-step eps 0.74 on true 2048-bit primes -- the carry rule transfers partially, far better than a cold start). It is then polished on the benchmark-matched width distribution (value-uniform [2^1025, 2^2048) + bit-length-uniform[2014,2048]) in two stages: a first pass (lr 2e-4, accum 16) relearns the high-bit reduction fast (eps 0.74 -> ~9e-4) but oscillates at high lr, then a low-lr tail (lr 6e-5, accum 20, margin loss) settles the per-step error below 5e-5 so the 2048-step chain clears tier 10 = 0.94 (held-out value-uniform validation chain ~0.95; private-draw simulation 0.955). Weight-perturbation compliance (exploration/compliance_perturb.py): each cell's accuracy at sigma=0 collapses toward the floor as the weights are perturbed and an untrained re-init scores 0.00 — e.g. tier 6 0.97 -> 0.11 (sigma=0.25), tier 7 0.98 -> 0.03 (sigma=0.25), tier 8 0.92 -> 0.04 (sigma=0.25), tier 9 0.99 -> 0.04 (sigma=0.25), tier 10 0.94 -> 0.04 (sigma=0.25), untrained 0.00 for all — so the arithmetic resides in the trained parameters. Training scripts: train.py (16-bit), exploration/train_horner32.py (32-bit), exploration/train_horner128_bigru.py --arch tcn (128-bit carry-aware TCN), exploration/train_horner_tcn.py --bits 64 / --bits 256 / --bits 512 --accum 2 (64-, 256- and 512-bit carry-aware TCN); --bits 1024 --lo-bits 513 --bitlen-frac 0.4 --bitlen-lo 990 --accum 16 --margin-weight 0.5 (1024-bit carry-aware TCN, benchmark-width-matched); exploration/transfer_1024_to_2048.py then exploration/train_horner_tcn.py --bits 2048 --blocks 13 --max-dil 1024 --init <transfer> --lo-bits 1025 --bitlen-frac 0.4 --bitlen-lo 2014 --max-rows 512 --grad-checkpoint --accum 16/20 --margin-weight 0.5 (2048-bit, octave transfer + low-lr tail; see exploration/TIER10_NOTES.md)."
 }

model.py

@@ -49,7 +49,7 @@ from modchallenge.interface.base_model import ModularMultiplicationModel
 
 # Bit-widths we may ship a cell for, narrowest first. load() picks up whichever
 # weights{W}.pt files are actually present, so adding a wider cell is drop-in.
-CELL_WIDTHS = (16, 32, 64, 128, 256, 512, 1024)
+CELL_WIDTHS = (16, 32, 64, 128, 256, 512, 1024, 2048)
 
 # Default state width for the 16-bit trainer (train.py imports this).
 BITS = 16

weights2048.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eda60b4d7026042981c16b49ea931238e6e1dd5c7ff72338eecbd688ca82d43
+size 20535797