diff --git a/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/README.md b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/README.md
new file mode 100644
index 0000000000..9e8596fa96
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/README.md
@@ -0,0 +1,97 @@
+# Record: PR #1787 + Smear Gate + LQER Asymmetric — val_bpb 1.06136 (3-seed mean)
+
+**val_bpb: 1.06136** (3-seed mean, std=0.00059) | **val_loss: 2.32265 nats/token** | **~15.95 MB** | 8×H100 SXM | Phased TTT
+
+**−0.00199 BPB vs PR #1797 reference** (1.06335). All 3 seeds individually beat PR #1797's best seed (1.06297). Independent reproduction validates the stack and improves on reported numbers via stochastic variance and hardware tuning.
+
+**−0.01964 BPB vs current merged SOTA** (PR #1493: 1.0810). Clears the 0.005-nat significance threshold by a wide margin (3-seed std 0.00059, delta-to-SOTA / std = 33).
+
+## Results (8×H100 80GB SXM, PyTorch 2.9.1+cu128, RunPod IN region)
+
+| Seed | Steps | Pre-quant BPB | Quantized BPB | **Post-TTT BPB** | TTT Eval | Train | Artifact |
+|------|------:|--------------:|--------------:|-----------------:|---------:|------:|---------:|
+| 42   | 4948  | 1.06451       | 1.07345       | **1.06068**      | 533.5s   | 599.6s | 15,951,346 |
+| 0    | 4920  | 1.06560       | 1.07458       | **1.06163**      | 435.1s   | 599.5s | 15,947,797 |
+| 1234 | 4916  | 1.06557       | 1.07472       | **1.06177**      | 468.9s   | 599.6s | 15,952,843 |
+| **Mean** | **4928** | **1.06523** | **1.07425** | **1.06136**  | 479.2s   | 599.6s | **15,950,662** |
+| **Std**  |          | 0.00053     | 0.00057     | **0.00059**      |          |        |            |
+
+All 3 seeds clear the 600s train budget (≤599.6s), the 600s TTT eval budget (≤533.5s), and the 16,000,000-byte artifact cap (≤15,952,843, ≥47,157 bytes headroom).
+
+## Significance
+
+3-seed std 0.00059 BPB ≈ 0.00136 nats/token. Delta to PR #1797 baseline (1.06335) is 0.00199 BPB ≈ 0.00138 nats/token. Significance ratio = 0.00199 / (0.00059 / √3) ≈ 5.8 — well past p < 0.01.
+
+## Stack Description
+
+This is a faithful reproduction of PR #1787's stack:
+
+- **PR #1394** (Kevin Clark) — SP8192 + GPTQ Embeddings + SDClip + brotli + MuonEq-R foundation
+- **PR #1493** (bigbag) — 3-layer depth recurrence (loops 3-5) + parallel residuals + QK-gain 5.25 + score-first TTT
+- **PR #1736** (dexhunter) — Phased TTT + GatedAttn quant gate
+- **PR #1797** (dexhunter) — **direct baseline**: Smear Gate + LQER Asymmetric (INT2+INT4 factors) on top of PR #1787
+
+## Reproduction
+
+```bash
+# Data prep
+MATCHED_FINEWEB_REPO_ID=romeerp/parameter-golf-caseops-v1 \
+MATCHED_FINEWEB_REMOTE_ROOT_PREFIX=datasets \
+python3 cached_challenge_fineweb.py \
+  --variant sp8192_lossless_caps_caseops_v1_reserved --train-shards 80
+
+# Install deps
+pip install --break-system-packages \
+  flash-attn-interface sentencepiece triton brotli python-minifier
+
+# Run (per seed)
+for SEED in 42 0 1234; do
+  NCCL_NET=Socket DATA_DIR=./data CASEOPS_ENABLED=1 \
+  PHASED_TTT_ENABLED=1 PHASED_TTT_PREFIX_DOCS=2000 PHASED_TTT_NUM_PHASES=3 \
+  MLP_CLIP_SIGMAS=12.0 ATTN_CLIP_SIGMAS=13.0 \
+  EMBED_BITS=7 EMBED_CLIP_SIGMAS=15.0 MATRIX_LR=0.026 \
+  GPTQ_RESERVE_SECONDS=0.5 GPTQ_CALIBRATION_BATCHES=16 \
+  VAL_LOSS_EVERY=0 MIN_LR=0.10 FUSED_CE_ENABLED=1 \
+  SPARSE_ATTN_GATE_ENABLED=1 GATED_ATTN_QUANT_GATE=1 \
+  SMEAR_GATE_ENABLED=1 GATE_WINDOW=12 \
+  LQER_ENABLED=1 LQER_RANK=4 LQER_TOP_K=3 LQER_FACTOR_BITS=4 \
+  LQER_ASYM_ENABLED=1 LQER_ASYM_GROUP=64 \
+  SEED=$SEED \
+  torchrun --standalone --nproc_per_node=8 train_gpt.py \
+    > train_seed${SEED}.log 2>&1
+done
+```
+
+## Compliance (Issue #1017 Track A)
+
+- ✅ **Fixed predictor**: scored artifact is int6-GPTQ + LQER + brotli, no eval-time adaptation outside score-first TTT
+- ✅ **Score-first TTT**: phased per PR #1767 framework — each chunk scored under `torch.no_grad()` BEFORE LoRA updates
+- ✅ **No SLOT, no RLS, no n-gram cache, no ETLB, no logit biasing**
+- ✅ **Sliding-window eval**: strictly causal, stride 64, single pass, normalized softmax over full vocab
+- ✅ **CaseOps byte sidecar** for honest BPB on original bytes (Title/AllCaps/CapNext control tokens don't inflate counts)
+- ✅ **Train < 600s** (≤599.6s on all 3 seeds)
+- ✅ **Eval < 600s** (≤533.5s on all 3 seeds)
+- ✅ **Artifact < 16,000,000 bytes decimal** (≤15,952,843 on all 3 seeds, ≥47,157 bytes headroom)
+
+## Phase 3 Ablation Note
+
+We tested Gram Newton-Schulz (Dao AI Lab CuTeDSL kernels, arxiv 2505.16932 + April 2026 packages) as a drop-in replacement for our Polar Express NS iteration on seed 42. Result: **no measurable speedup** at our parameter-bank scale, slight numerical divergence from stock NS (pre-quant 1.06536 vs 1.06451). The Dao AI Lab claim of 2× speedup applies to larger matrices than our 512×2048 bank shards. We dropped Gram NS from the final submission. Logs in `gram_ns_ablation/`.
+
+## Credits
+
+This submission stands on the work of many contributors. Direct credit chain:
+
+- **@clarkkev** (PR #1394) — SP8192 + GPTQ Embeddings + SDClip + Brotli + MuonEq-R
+- **@bigbag** (PR #1493) — Merged SOTA 1.0810: depth recurrence + parallel residuals + QK-gain
+- **@dexhunter** (PR #1736, #1797) — Phased TTT, Quant Gate, Smear Gate, LQER Asym
+- **@nprime06** (PR #1787) — Polar Express NS port, Fused CE Triton kernel, Sparse Attn Gate, MIN_LR, bug fixes
+- **@classiclarryd** — Smear Gate concept (modded-nanogpt origin)
+- **@MarioPaerle** (PR #1667) — Smear Gate port to parameter-golf
+- **@romeerp** (PR #1729) — CaseOps lossless-case tokenizer + byte sidecar
+
+## Hardware
+
+- 8× NVIDIA H100 80GB HBM3 SXM (RunPod secure cloud, IN region)
+- PyTorch 2.9.1+cu128, CUDA 12.8
+- Flash Attention 3, Triton 3.5.1, Brotli 1.2.0
+- Python 3.12.3
diff --git a/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/lossless_caps.py b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/lossless_caps.py
new file mode 100644
index 0000000000..98e472f824
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/lossless_caps.py
@@ -0,0 +1,833 @@
+"""Lossless capitalization pre-encoding helpers.
+
+This module provides a narrow, reversible transform that only touches
+ASCII capital letters `A-Z`. Each uppercase ASCII letter is rewritten as
+`<sentinel><lowercase>`, where `sentinel` is a private-use Unicode
+character that is escaped by doubling if it appears literally in the
+input text.
+
+Example with the default sentinel `\\uE000`:
+
+    "The NASA Launch" -> "\\uE000the \\uE000n\\uE000a\\uE000s\\uE000a \\uE000launch"
+
+The transform is intentionally simple for v1:
+
+- lowercase ASCII letters are unchanged
+- uppercase ASCII letters become sentinel + lowercase letter
+- non-ASCII characters are left untouched
+- literal sentinel characters are escaped as sentinel + sentinel
+
+This makes the transform exactly invertible while allowing a downstream
+tokenizer to reuse lowercase subwords across case variants.
+"""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Callable, Iterable
+
+LOSSLESS_CAPS_V1 = "lossless_caps_v1"
+LOSSLESS_CAPS_V2 = "lossless_caps_v2"
+LOSSLESS_CAPS_V3 = "lossless_caps_v3"
+LOSSLESS_CAPS_V4 = "lossless_caps_v4"
+LOSSLESS_CAPS_V5 = "lossless_caps_v5"
+LOSSLESS_CAPS_V6 = "lossless_caps_v6"
+LOSSLESS_CAPS_V7 = "lossless_caps_v7"
+LOSSLESS_CAPS_CASEOPS_V1 = "lossless_caps_caseops_v1"
+IDENTITY = "identity"
+DEFAULT_SENTINEL = "\uE000"
+DEFAULT_V2_TITLE = "\uE001"
+DEFAULT_V2_ALLCAPS = "\uE002"
+DEFAULT_V2_CAPNEXT = "\uE003"
+DEFAULT_V2_ESC = "\uE004"
+DEFAULT_V5_TITLE_MIN_LEN = 7
+DEFAULT_V6_ALLCAPS_MIN_LEN = 3
+DEFAULT_V7_ALLCAPS_MIN_LEN = 4
+
+
+class LosslessCapsError(ValueError):
+    """Raised when a transformed string is malformed."""
+
+
+def _is_ascii_upper(ch: str) -> bool:
+    return "A" <= ch <= "Z"
+
+
+def _is_ascii_lower(ch: str) -> bool:
+    return "a" <= ch <= "z"
+
+
+def _is_ascii_alpha(ch: str) -> bool:
+    return _is_ascii_lower(ch) or _is_ascii_upper(ch)
+
+
+def _validate_distinct_single_chars(*chars: str) -> None:
+    if any(len(ch) != 1 for ch in chars):
+        raise ValueError("all control characters must be exactly one character")
+    if len(set(chars)) != len(chars):
+        raise ValueError("control characters must be distinct")
+
+
+def encode_lossless_caps_v1(text: str, *, sentinel: str = DEFAULT_SENTINEL) -> str:
+    """Encode ASCII capitals reversibly using a one-character sentinel."""
+    if len(sentinel) != 1:
+        raise ValueError("sentinel must be exactly one character")
+    out: list[str] = []
+    for ch in text:
+        if ch == sentinel:
+            out.append(sentinel)
+            out.append(sentinel)
+        elif _is_ascii_upper(ch):
+            out.append(sentinel)
+            out.append(ch.lower())
+        else:
+            out.append(ch)
+    return "".join(out)
+
+
+def decode_lossless_caps_v1(text: str, *, sentinel: str = DEFAULT_SENTINEL) -> str:
+    """Decode the `lossless_caps_v1` transform back to the original text."""
+    if len(sentinel) != 1:
+        raise ValueError("sentinel must be exactly one character")
+    out: list[str] = []
+    i = 0
+    n = len(text)
+    while i < n:
+        ch = text[i]
+        if ch != sentinel:
+            out.append(ch)
+            i += 1
+            continue
+        if i + 1 >= n:
+            raise LosslessCapsError("dangling capitalization sentinel at end of string")
+        nxt = text[i + 1]
+        if nxt == sentinel:
+            out.append(sentinel)
+        elif _is_ascii_lower(nxt):
+            out.append(nxt.upper())
+        else:
+            raise LosslessCapsError(
+                f"invalid sentinel escape sequence {sentinel + nxt!r}; "
+                "expected doubled sentinel or sentinel + lowercase ASCII letter"
+            )
+        i += 2
+    return "".join(out)
+
+
+def encode_lossless_caps_v2(
+    text: str,
+    *,
+    title: str = DEFAULT_V2_TITLE,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    capnext: str = DEFAULT_V2_CAPNEXT,
+    esc: str = DEFAULT_V2_ESC,
+) -> str:
+    """Encode ASCII word capitalization with cheap word-level markers.
+
+    Rules over maximal ASCII alphabetic runs:
+    - lowercase words stay unchanged
+    - TitleCase words become `title + lowercase(word)`
+    - ALLCAPS words become `allcaps + lowercase(word)`
+    - mixed-case words use:
+      - optional `title` when the first letter is uppercase
+      - `capnext + lowercase(letter)` for subsequent uppercase letters
+    - literal control characters are escaped as `esc + literal`
+    """
+    _validate_distinct_single_chars(title, allcaps, capnext, esc)
+    controls = {title, allcaps, capnext, esc}
+    out: list[str] = []
+    i = 0
+    n = len(text)
+    while i < n:
+        ch = text[i]
+        if ch in controls:
+            out.append(esc)
+            out.append(ch)
+            i += 1
+            continue
+        if not _is_ascii_alpha(ch):
+            out.append(ch)
+            i += 1
+            continue
+
+        j = i + 1
+        while j < n and _is_ascii_alpha(text[j]):
+            j += 1
+        word = text[i:j]
+        lower_word = word.lower()
+
+        if word.islower():
+            out.append(word)
+        elif len(word) >= 2 and word.isupper():
+            out.append(allcaps)
+            out.append(lower_word)
+        elif _is_ascii_upper(word[0]) and word[1:].islower():
+            out.append(title)
+            out.append(lower_word)
+        else:
+            if _is_ascii_upper(word[0]):
+                out.append(title)
+            out.append(lower_word[0])
+            for orig_ch, lower_ch in zip(word[1:], lower_word[1:], strict=True):
+                if _is_ascii_upper(orig_ch):
+                    out.append(capnext)
+                out.append(lower_ch)
+        i = j
+    return "".join(out)
+
+
+def decode_lossless_caps_v2(
+    text: str,
+    *,
+    title: str = DEFAULT_V2_TITLE,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    capnext: str = DEFAULT_V2_CAPNEXT,
+    esc: str = DEFAULT_V2_ESC,
+) -> str:
+    """Decode the `lossless_caps_v2` transform back to the original text."""
+    _validate_distinct_single_chars(title, allcaps, capnext, esc)
+    out: list[str] = []
+    pending_escape = False
+    pending_word_mode: str | None = None
+    active_allcaps = False
+    pending_capnext = False
+    in_ascii_word = False
+
+    for ch in text:
+        if pending_escape:
+            if pending_word_mode is not None and not _is_ascii_alpha(ch):
+                raise LosslessCapsError("escaped control char cannot satisfy pending word capitalization mode")
+            out.append(ch)
+            pending_escape = False
+            if _is_ascii_alpha(ch):
+                in_ascii_word = True
+            else:
+                in_ascii_word = False
+                active_allcaps = False
+            continue
+
+        if ch == esc:
+            pending_escape = True
+            continue
+        if ch == title:
+            if pending_word_mode is not None or in_ascii_word or pending_capnext:
+                raise LosslessCapsError("invalid title marker placement")
+            pending_word_mode = "title"
+            continue
+        if ch == allcaps:
+            if pending_word_mode is not None or in_ascii_word or pending_capnext:
+                raise LosslessCapsError("invalid allcaps marker placement")
+            pending_word_mode = "allcaps"
+            continue
+        if ch == capnext:
+            if pending_capnext:
+                raise LosslessCapsError("duplicate capnext marker")
+            pending_capnext = True
+            continue
+
+        if _is_ascii_alpha(ch):
+            at_word_start = not in_ascii_word
+            if at_word_start:
+                if pending_word_mode == "allcaps":
+                    out.append(ch.upper())
+                    active_allcaps = True
+                elif pending_word_mode == "title":
+                    out.append(ch.upper())
+                elif pending_capnext:
+                    out.append(ch.upper())
+                else:
+                    out.append(ch)
+                pending_word_mode = None
+                pending_capnext = False
+                in_ascii_word = True
+                continue
+
+            if pending_word_mode is not None:
+                raise LosslessCapsError("word capitalization marker leaked into the middle of a word")
+            if active_allcaps:
+                out.append(ch.upper())
+            elif pending_capnext:
+                out.append(ch.upper())
+            else:
+                out.append(ch)
+            pending_capnext = False
+            continue
+
+        if pending_word_mode is not None or pending_capnext:
+            raise LosslessCapsError("capitalization marker not followed by an ASCII letter")
+        out.append(ch)
+        in_ascii_word = False
+        active_allcaps = False
+
+    if pending_escape:
+        raise LosslessCapsError("dangling escape marker at end of string")
+    if pending_word_mode is not None or pending_capnext:
+        raise LosslessCapsError("dangling capitalization marker at end of string")
+    return "".join(out)
+
+
+def encode_lossless_caps_v3(
+    text: str,
+    *,
+    title: str = DEFAULT_V2_TITLE,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+) -> str:
+    """Encode only common word-level capitalization patterns.
+
+    Rules over maximal ASCII alphabetic runs:
+    - lowercase words stay unchanged
+    - TitleCase words become `title + lowercase(word)`
+    - ALLCAPS words become `allcaps + lowercase(word)`
+    - all other mixed-case words are left unchanged
+    - literal control characters are escaped as `esc + literal`
+    """
+    _validate_distinct_single_chars(title, allcaps, esc)
+    controls = {title, allcaps, esc}
+    out: list[str] = []
+    i = 0
+    n = len(text)
+    while i < n:
+        ch = text[i]
+        if ch in controls:
+            out.append(esc)
+            out.append(ch)
+            i += 1
+            continue
+        if not _is_ascii_alpha(ch):
+            out.append(ch)
+            i += 1
+            continue
+
+        j = i + 1
+        while j < n and _is_ascii_alpha(text[j]):
+            j += 1
+        word = text[i:j]
+
+        if word.islower():
+            out.append(word)
+        elif len(word) >= 2 and word.isupper():
+            out.append(allcaps)
+            out.append(word.lower())
+        elif _is_ascii_upper(word[0]) and word[1:].islower():
+            out.append(title)
+            out.append(word.lower())
+        else:
+            out.append(word)
+        i = j
+    return "".join(out)
+
+
+def decode_lossless_caps_v3(
+    text: str,
+    *,
+    title: str = DEFAULT_V2_TITLE,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+) -> str:
+    """Decode the `lossless_caps_v3` transform back to the original text."""
+    _validate_distinct_single_chars(title, allcaps, esc)
+    out: list[str] = []
+    pending_escape = False
+    pending_word_mode: str | None = None
+    active_allcaps = False
+    in_ascii_word = False
+
+    for ch in text:
+        if pending_escape:
+            if pending_word_mode is not None and not _is_ascii_alpha(ch):
+                raise LosslessCapsError("escaped control char cannot satisfy pending word capitalization mode")
+            out.append(ch)
+            pending_escape = False
+            if _is_ascii_alpha(ch):
+                in_ascii_word = True
+            else:
+                in_ascii_word = False
+                active_allcaps = False
+            continue
+
+        if ch == esc:
+            pending_escape = True
+            continue
+        if ch == title:
+            if pending_word_mode is not None or in_ascii_word:
+                raise LosslessCapsError("invalid title marker placement")
+            pending_word_mode = "title"
+            continue
+        if ch == allcaps:
+            if pending_word_mode is not None or in_ascii_word:
+                raise LosslessCapsError("invalid allcaps marker placement")
+            pending_word_mode = "allcaps"
+            continue
+
+        if _is_ascii_alpha(ch):
+            at_word_start = not in_ascii_word
+            if at_word_start:
+                if pending_word_mode == "allcaps":
+                    out.append(ch.upper())
+                    active_allcaps = True
+                elif pending_word_mode == "title":
+                    out.append(ch.upper())
+                else:
+                    out.append(ch)
+                pending_word_mode = None
+                in_ascii_word = True
+                continue
+
+            if pending_word_mode is not None:
+                raise LosslessCapsError("word capitalization marker leaked into the middle of a word")
+            out.append(ch.upper() if active_allcaps else ch)
+            continue
+
+        if pending_word_mode is not None:
+            raise LosslessCapsError("capitalization marker not followed by an ASCII letter")
+        out.append(ch)
+        in_ascii_word = False
+        active_allcaps = False
+
+    if pending_escape:
+        raise LosslessCapsError("dangling escape marker at end of string")
+    if pending_word_mode is not None:
+        raise LosslessCapsError("dangling capitalization marker at end of string")
+    return "".join(out)
+
+
+def encode_lossless_caps_v4(
+    text: str,
+    *,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+) -> str:
+    """Encode only ALLCAPS ASCII words, leaving all other case untouched."""
+    _validate_distinct_single_chars(allcaps, esc)
+    controls = {allcaps, esc}
+    out: list[str] = []
+    i = 0
+    n = len(text)
+    while i < n:
+        ch = text[i]
+        if ch in controls:
+            out.append(esc)
+            out.append(ch)
+            i += 1
+            continue
+        if not _is_ascii_alpha(ch):
+            out.append(ch)
+            i += 1
+            continue
+        j = i + 1
+        while j < n and _is_ascii_alpha(text[j]):
+            j += 1
+        word = text[i:j]
+        if len(word) >= 2 and word.isupper():
+            out.append(allcaps)
+            out.append(word.lower())
+        else:
+            out.append(word)
+        i = j
+    return "".join(out)
+
+
+def decode_lossless_caps_v4(
+    text: str,
+    *,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+) -> str:
+    """Decode the `lossless_caps_v4` transform back to the original text."""
+    _validate_distinct_single_chars(allcaps, esc)
+    out: list[str] = []
+    pending_escape = False
+    pending_allcaps = False
+    in_ascii_word = False
+    active_allcaps = False
+
+    for ch in text:
+        if pending_escape:
+            if pending_allcaps and not _is_ascii_alpha(ch):
+                raise LosslessCapsError("escaped control char cannot satisfy pending allcaps mode")
+            out.append(ch)
+            pending_escape = False
+            if _is_ascii_alpha(ch):
+                in_ascii_word = True
+            else:
+                in_ascii_word = False
+                active_allcaps = False
+            continue
+
+        if ch == esc:
+            pending_escape = True
+            continue
+        if ch == allcaps:
+            if pending_allcaps or in_ascii_word:
+                raise LosslessCapsError("invalid allcaps marker placement")
+            pending_allcaps = True
+            continue
+
+        if _is_ascii_alpha(ch):
+            if not in_ascii_word:
+                active_allcaps = pending_allcaps
+                pending_allcaps = False
+                in_ascii_word = True
+            out.append(ch.upper() if active_allcaps else ch)
+            continue
+
+        if pending_allcaps:
+            raise LosslessCapsError("allcaps marker not followed by an ASCII letter")
+        out.append(ch)
+        in_ascii_word = False
+        active_allcaps = False
+
+    if pending_escape:
+        raise LosslessCapsError("dangling escape marker at end of string")
+    if pending_allcaps:
+        raise LosslessCapsError("dangling allcaps marker at end of string")
+    return "".join(out)
+
+
+def encode_lossless_caps_v5(
+    text: str,
+    *,
+    title: str = DEFAULT_V2_TITLE,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+    title_min_len: int = DEFAULT_V5_TITLE_MIN_LEN,
+) -> str:
+    """Encode ALLCAPS words and only sufficiently long TitleCase words."""
+    _validate_distinct_single_chars(title, allcaps, esc)
+    controls = {title, allcaps, esc}
+    out: list[str] = []
+    i = 0
+    n = len(text)
+    while i < n:
+        ch = text[i]
+        if ch in controls:
+            out.append(esc)
+            out.append(ch)
+            i += 1
+            continue
+        if not _is_ascii_alpha(ch):
+            out.append(ch)
+            i += 1
+            continue
+        j = i + 1
+        while j < n and _is_ascii_alpha(text[j]):
+            j += 1
+        word = text[i:j]
+        if len(word) >= 2 and word.isupper():
+            out.append(allcaps)
+            out.append(word.lower())
+        elif len(word) >= title_min_len and _is_ascii_upper(word[0]) and word[1:].islower():
+            out.append(title)
+            out.append(word.lower())
+        else:
+            out.append(word)
+        i = j
+    return "".join(out)
+
+
+def decode_lossless_caps_v5(
+    text: str,
+    *,
+    title: str = DEFAULT_V2_TITLE,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+) -> str:
+    """Decode the `lossless_caps_v5` transform back to the original text."""
+    return decode_lossless_caps_v3(text, title=title, allcaps=allcaps, esc=esc)
+
+
+def encode_lossless_caps_v6(
+    text: str,
+    *,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+    allcaps_min_len: int = DEFAULT_V6_ALLCAPS_MIN_LEN,
+) -> str:
+    """Encode only ALLCAPS words with length >= allcaps_min_len."""
+    _validate_distinct_single_chars(allcaps, esc)
+    controls = {allcaps, esc}
+    out: list[str] = []
+    i = 0
+    n = len(text)
+    while i < n:
+        ch = text[i]
+        if ch in controls:
+            out.append(esc)
+            out.append(ch)
+            i += 1
+            continue
+        if not _is_ascii_alpha(ch):
+            out.append(ch)
+            i += 1
+            continue
+        j = i + 1
+        while j < n and _is_ascii_alpha(text[j]):
+            j += 1
+        word = text[i:j]
+        if len(word) >= allcaps_min_len and word.isupper():
+            out.append(allcaps)
+            out.append(word.lower())
+        else:
+            out.append(word)
+        i = j
+    return "".join(out)
+
+
+def decode_lossless_caps_v6(
+    text: str,
+    *,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+) -> str:
+    """Decode the `lossless_caps_v6` transform back to the original text."""
+    return decode_lossless_caps_v4(text, allcaps=allcaps, esc=esc)
+
+
+def encode_lossless_caps_v7(
+    text: str,
+    *,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+    allcaps_min_len: int = DEFAULT_V7_ALLCAPS_MIN_LEN,
+) -> str:
+    """Encode only ALLCAPS words with length >= 4."""
+    return encode_lossless_caps_v6(
+        text,
+        allcaps=allcaps,
+        esc=esc,
+        allcaps_min_len=allcaps_min_len,
+    )
+
+
+def decode_lossless_caps_v7(
+    text: str,
+    *,
+    allcaps: str = DEFAULT_V2_ALLCAPS,
+    esc: str = DEFAULT_V2_ESC,
+) -> str:
+    """Decode the `lossless_caps_v7` transform back to the original text."""
+    return decode_lossless_caps_v6(text, allcaps=allcaps, esc=esc)
+
+
+def get_text_transform(name: str | None) -> Callable[[str], str]:
+    """Return the forward text transform for the given config name."""
+    normalized = IDENTITY if name in {None, "", IDENTITY} else str(name)
+    if normalized == IDENTITY:
+        return lambda text: text
+    if normalized == LOSSLESS_CAPS_V1:
+        return encode_lossless_caps_v1
+    if normalized == LOSSLESS_CAPS_V2:
+        return encode_lossless_caps_v2
+    if normalized == LOSSLESS_CAPS_V3:
+        return encode_lossless_caps_v3
+    if normalized == LOSSLESS_CAPS_V4:
+        return encode_lossless_caps_v4
+    if normalized == LOSSLESS_CAPS_V5:
+        return encode_lossless_caps_v5
+    if normalized == LOSSLESS_CAPS_V6:
+        return encode_lossless_caps_v6
+    if normalized == LOSSLESS_CAPS_V7:
+        return encode_lossless_caps_v7
+    if normalized == LOSSLESS_CAPS_CASEOPS_V1:
+        return encode_lossless_caps_v2
+    raise ValueError(f"unsupported text_transform={name!r}")
+
+
+def get_text_inverse_transform(name: str | None) -> Callable[[str], str]:
+    """Return the inverse transform for the given config name."""
+    normalized = IDENTITY if name in {None, "", IDENTITY} else str(name)
+    if normalized == IDENTITY:
+        return lambda text: text
+    if normalized == LOSSLESS_CAPS_V1:
+        return decode_lossless_caps_v1
+    if normalized == LOSSLESS_CAPS_V2:
+        return decode_lossless_caps_v2
+    if normalized == LOSSLESS_CAPS_V3:
+        return decode_lossless_caps_v3
+    if normalized == LOSSLESS_CAPS_V4:
+        return decode_lossless_caps_v4
+    if normalized == LOSSLESS_CAPS_V5:
+        return decode_lossless_caps_v5
+    if normalized == LOSSLESS_CAPS_V6:
+        return decode_lossless_caps_v6
+    if normalized == LOSSLESS_CAPS_V7:
+        return decode_lossless_caps_v7
+    if normalized == LOSSLESS_CAPS_CASEOPS_V1:
+        return decode_lossless_caps_v2
+    raise ValueError(f"unsupported text_transform={name!r}")
+
+
+def normalize_text_transform_name(name: str | None) -> str:
+    """Normalize empty/None transform names to the identity transform."""
+    return IDENTITY if name in {None, "", IDENTITY} else str(name)
+
+
+def get_text_transform_control_symbols(name: str | None) -> list[str]:
+    """Return reserved control symbols used by a transform, if any."""
+    normalized = normalize_text_transform_name(name)
+    if normalized == IDENTITY:
+        return []
+    if normalized == LOSSLESS_CAPS_V1:
+        return [DEFAULT_SENTINEL]
+    if normalized == LOSSLESS_CAPS_V2:
+        return [DEFAULT_V2_TITLE, DEFAULT_V2_ALLCAPS, DEFAULT_V2_CAPNEXT, DEFAULT_V2_ESC]
+    if normalized == LOSSLESS_CAPS_CASEOPS_V1:
+        return [DEFAULT_V2_TITLE, DEFAULT_V2_ALLCAPS, DEFAULT_V2_CAPNEXT, DEFAULT_V2_ESC]
+    if normalized in {LOSSLESS_CAPS_V3, LOSSLESS_CAPS_V5}:
+        return [DEFAULT_V2_TITLE, DEFAULT_V2_ALLCAPS, DEFAULT_V2_ESC]
+    if normalized in {LOSSLESS_CAPS_V4, LOSSLESS_CAPS_V6, LOSSLESS_CAPS_V7}:
+        return [DEFAULT_V2_ALLCAPS, DEFAULT_V2_ESC]
+    raise ValueError(f"unsupported text_transform={name!r}")
+
+
+def infer_text_transform_from_manifest(tokenizer_path: str | Path) -> str:
+    """Best-effort lookup of a tokenizer's text transform from a local manifest."""
+    tokenizer_path = Path(tokenizer_path).expanduser().resolve()
+    manifest_candidates = [
+        tokenizer_path.parent.parent / "manifest.json",
+        tokenizer_path.parent / "manifest.json",
+    ]
+    for manifest_path in manifest_candidates:
+        if not manifest_path.is_file():
+            continue
+        try:
+            payload = json.loads(manifest_path.read_text(encoding="utf-8"))
+        except (OSError, json.JSONDecodeError):
+            continue
+        tokenizers = payload.get("tokenizers")
+        if not isinstance(tokenizers, list):
+            continue
+        for tokenizer_meta in tokenizers:
+            if not isinstance(tokenizer_meta, dict):
+                continue
+            model_path = tokenizer_meta.get("model_path") or tokenizer_meta.get("path")
+            if not model_path:
+                continue
+            candidate = (manifest_path.parent / str(model_path)).resolve()
+            if candidate == tokenizer_path:
+                return normalize_text_transform_name(tokenizer_meta.get("text_transform"))
+    return IDENTITY
+
+
+def surface_piece_original_byte_counts(
+    surfaces: Iterable[str],
+    *,
+    text_transform_name: str | None = None,
+    sentinel: str = DEFAULT_SENTINEL,
+) -> list[int]:
+    """Return exact original UTF-8 byte counts contributed by each surface piece.
+
+    `surfaces` must be the exact decoded text fragments emitted by SentencePiece
+    in order, e.g. `piece.surface` from `encode_as_immutable_proto`.
+    """
+    normalized = normalize_text_transform_name(text_transform_name)
+    if normalized == IDENTITY:
+        return [len(surface.encode("utf-8")) for surface in surfaces]
+    if normalized == LOSSLESS_CAPS_V1:
+        if len(sentinel) != 1:
+            raise ValueError("sentinel must be exactly one character")
+        sentinel_bytes = len(sentinel.encode("utf-8"))
+        pending_sentinel = False
+        counts: list[int] = []
+        for surface in surfaces:
+            piece_bytes = 0
+            for ch in surface:
+                if pending_sentinel:
+                    if ch == sentinel:
+                        piece_bytes += sentinel_bytes
+                    elif _is_ascii_lower(ch):
+                        piece_bytes += 1
+                    else:
+                        raise LosslessCapsError(
+                            f"invalid continuation {ch!r} after capitalization sentinel"
+                        )
+                    pending_sentinel = False
+                    continue
+                if ch == sentinel:
+                    pending_sentinel = True
+                else:
+                    piece_bytes += len(ch.encode("utf-8"))
+            counts.append(piece_bytes)
+        if pending_sentinel:
+            raise LosslessCapsError("dangling capitalization sentinel across piece boundary")
+        return counts
+    if normalized not in {LOSSLESS_CAPS_V2, LOSSLESS_CAPS_V3, LOSSLESS_CAPS_V4, LOSSLESS_CAPS_V5, LOSSLESS_CAPS_V6, LOSSLESS_CAPS_V7, LOSSLESS_CAPS_CASEOPS_V1}:
+        raise ValueError(f"unsupported text_transform={text_transform_name!r}")
+
+    title = DEFAULT_V2_TITLE
+    allcaps = DEFAULT_V2_ALLCAPS
+    capnext = DEFAULT_V2_CAPNEXT
+    esc = DEFAULT_V2_ESC
+    if normalized in {LOSSLESS_CAPS_V2, LOSSLESS_CAPS_CASEOPS_V1}:
+        _validate_distinct_single_chars(title, allcaps, capnext, esc)
+    elif normalized in {LOSSLESS_CAPS_V4, LOSSLESS_CAPS_V6, LOSSLESS_CAPS_V7}:
+        _validate_distinct_single_chars(allcaps, esc)
+    else:
+        _validate_distinct_single_chars(title, allcaps, esc)
+    pending_escape = False
+    pending_word_mode: str | None = None
+    active_allcaps = False
+    pending_capnext = False
+    in_ascii_word = False
+    counts: list[int] = []
+    for surface in surfaces:
+        piece_bytes = 0
+        for ch in surface:
+            if pending_escape:
+                if pending_word_mode is not None and not _is_ascii_alpha(ch):
+                    raise LosslessCapsError("escaped control char cannot satisfy pending word capitalization mode")
+                piece_bytes += len(ch.encode("utf-8"))
+                pending_escape = False
+                if _is_ascii_alpha(ch):
+                    in_ascii_word = True
+                else:
+                    in_ascii_word = False
+                    active_allcaps = False
+                continue
+            if ch == esc:
+                pending_escape = True
+                continue
+            if normalized in {LOSSLESS_CAPS_V2, LOSSLESS_CAPS_V3, LOSSLESS_CAPS_V5, LOSSLESS_CAPS_CASEOPS_V1} and ch == title:
+                if pending_word_mode is not None or in_ascii_word or pending_capnext:
+                    raise LosslessCapsError("invalid title marker placement")
+                pending_word_mode = "title"
+                continue
+            if ch == allcaps:
+                if pending_word_mode is not None or in_ascii_word or pending_capnext:
+                    raise LosslessCapsError("invalid allcaps marker placement")
+                pending_word_mode = "allcaps"
+                continue
+            if normalized in {LOSSLESS_CAPS_V2, LOSSLESS_CAPS_CASEOPS_V1} and ch == capnext:
+                if pending_capnext:
+                    raise LosslessCapsError("duplicate capnext marker")
+                pending_capnext = True
+                continue
+
+            if _is_ascii_alpha(ch):
+                at_word_start = not in_ascii_word
+                if at_word_start:
+                    piece_bytes += 1
+                    active_allcaps = pending_word_mode == "allcaps"
+                    pending_word_mode = None
+                    pending_capnext = False
+                    in_ascii_word = True
+                    continue
+                if pending_word_mode is not None:
+                    raise LosslessCapsError("word capitalization marker leaked into the middle of a word")
+                piece_bytes += 1
+                pending_capnext = False
+                continue
+
+            if pending_word_mode is not None or pending_capnext:
+                raise LosslessCapsError("capitalization marker not followed by an ASCII letter")
+            piece_bytes += len(ch.encode("utf-8"))
+            in_ascii_word = False
+            active_allcaps = False
+        counts.append(piece_bytes)
+    if pending_escape:
+        raise LosslessCapsError("dangling escape marker across piece boundary")
+    if pending_word_mode is not None or pending_capnext:
+        raise LosslessCapsError("dangling capitalization marker across piece boundary")
+    return counts
diff --git a/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/prepare_caseops_data.py b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/prepare_caseops_data.py
new file mode 100644
index 0000000000..5e734c969d
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/prepare_caseops_data.py
@@ -0,0 +1,208 @@
+"""Prepare CaseOps-tokenized FineWeb shards + per-token byte sidecar.
+
+CaseOps (``lossless_caps_caseops_v1``) is a bijective, character-level text
+transform that introduces four operator tokens in place of explicit
+capitalization: TITLE, ALLCAPS, CAPNEXT, ESC. The transform is fully
+reversible — no information is lost relative to the untransformed UTF-8
+text, so BPB stays computable on TRUE byte counts.
+
+Forward pipeline:
+  1. Read the canonical FineWeb-10B doc stream (``docs_selected.jsonl``
+     produced by ``data/download_hf_docs_and_tokenize.py`` in the root repo).
+  2. Apply ``encode_lossless_caps_v2`` (the caseops_v1 alias) to each doc.
+  3. Tokenize with the shipped SP model
+     ``tokenizers/fineweb_8192_bpe_lossless_caps_caseops_v1_reserved.model``
+     (reserves TITLE/ALLCAPS/CAPNEXT/ESC + sentinel as user_defined_symbols).
+  4. Write uint16 train/val shards (``fineweb_{train,val}_XXXXXX.bin``).
+  5. For the VAL stream only, emit per-token byte sidecar shards
+     (``fineweb_val_bytes_XXXXXX.bin``, uint16 parallel arrays) that record
+     each token's ORIGINAL pre-transform UTF-8 byte count. BPB is computed
+     from these canonical bytes so the score is on the untransformed text
+     (not the transformed representation).
+
+Output layout — matches what ``train_gpt.py`` expects under
+``DATA_DIR=./data`` with ``CASEOPS_ENABLED=1``:
+
+    data/datasets/fineweb10B_sp8192_caseops/datasets/
+      tokenizers/fineweb_8192_bpe_lossless_caps_caseops_v1_reserved.model
+      datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/
+        fineweb_train_000000.bin
+        fineweb_train_000001.bin
+        ...
+        fineweb_val_000000.bin
+        fineweb_val_bytes_000000.bin
+
+Usage:
+
+    python3 prepare_caseops_data.py \\
+        --docs ./fineweb10B_raw/docs_selected.jsonl \\
+        --out  ./data/datasets/fineweb10B_sp8192_caseops/datasets \\
+        --sp   ./tokenizers/fineweb_8192_bpe_lossless_caps_caseops_v1_reserved.model
+
+Requirements: sentencepiece, numpy. CPU-only. Runs once; reused across seeds.
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import pathlib
+import struct
+import sys
+
+import numpy as np
+import sentencepiece as spm
+
+# Local import — lossless_caps.py ships next to this script.
+sys.path.insert(0, str(pathlib.Path(__file__).resolve().parent))
+from lossless_caps import encode_lossless_caps_v2  # noqa: E402
+
+
+SHARD_MAGIC = 20240520
+SHARD_VERSION = 1
+SHARD_TOKENS = 10_000_000  # tokens per shard — matches the main pipeline
+# BOS sentinel (matches canonical data/download_hf_docs_and_tokenize.py). The SP
+# tokenizer's BOS_ID=1 is among the reserved IDs 0..7, so sp.encode() can't
+# emit it organically — it must be prepended by the prep script. train_gpt.py's
+# phased TTT eval path (_find_docs, _loss_bpb_from_sums) relies on BOS
+# boundaries and divides by zero on BOS-less shards; the training loader has a
+# fallback in _init_shard but TTT does not. This was the bug flagged on
+# PR-1779 / patched on PR-1736 (d7263a3) and PR-1769 (fe7c309).
+BOS_ID = 1
+
+
+def _write_shard(out_path: pathlib.Path, arr: np.ndarray) -> None:
+    """Write a uint16 shard in the standard header-prefixed format."""
+    assert arr.dtype == np.uint16
+    header = np.zeros(256, dtype=np.int32)
+    header[0] = SHARD_MAGIC
+    header[1] = SHARD_VERSION
+    header[2] = int(arr.size)
+    with out_path.open("wb") as fh:
+        fh.write(header.tobytes())
+        fh.write(arr.tobytes())
+
+
+def _iter_docs(docs_path: pathlib.Path):
+    """Yield doc strings from a jsonl file (one json object per line)."""
+    with docs_path.open("r", encoding="utf-8") as fh:
+        for line in fh:
+            line = line.strip()
+            if not line:
+                continue
+            obj = json.loads(line)
+            # Support both {"text": ...} and raw strings.
+            yield obj["text"] if isinstance(obj, dict) else obj
+
+
+def _token_original_byte_counts(
+    sp: spm.SentencePieceProcessor,
+    original_text: str,
+    transformed_text: str,
+) -> np.ndarray:
+    """Compute per-token canonical (pre-transform) UTF-8 byte counts.
+
+    The tokenizer runs on the TRANSFORMED text (so operator tokens exist in
+    the vocabulary), but BPB must be scored on the ORIGINAL byte stream.
+    We tokenize the transformed text, then walk each token's surface form
+    through the decoder to recover the pre-transform substring, and count
+    the UTF-8 bytes of that.
+
+    This is an APPROXIMATION — it assumes every token maps cleanly back to
+    a contiguous original substring. For caseops_v1 (which is character-
+    level and bijective) this holds exactly, because operator tokens
+    correspond to positions in the original string where the case was
+    derived from surrounding letters rather than materialised bytes.
+    """
+    # Re-encode via the SP model and get pieces (surface strings with the
+    # leading ▁ preserved, as in the BPE vocabulary).
+    piece_ids = sp.encode(transformed_text, out_type=int)
+    pieces = [sp.id_to_piece(int(pid)) for pid in piece_ids]
+    # Walk pieces and match against the transformed text to find byte spans.
+    counts = np.empty(len(piece_ids), dtype=np.uint16)
+    cursor_t = 0
+    cursor_o = 0
+    from lossless_caps import decode_lossless_caps_v2 as _decode
+    for i, piece in enumerate(pieces):
+        # SentencePiece uses ▁ as the whitespace marker.
+        surface = piece.replace("\u2581", " ")
+        span = transformed_text[cursor_t:cursor_t + len(surface)]
+        cursor_t += len(span)
+        # Decode just this span to find the original bytes it came from.
+        try:
+            decoded_prefix = _decode(transformed_text[:cursor_t])
+            original_bytes = len(decoded_prefix.encode("utf-8")) - cursor_o
+            cursor_o += original_bytes
+        except Exception:
+            # Fall back to counting the transformed surface.
+            original_bytes = len(span.encode("utf-8"))
+        counts[i] = max(0, min(65535, original_bytes))
+    return counts
+
+
+def main() -> None:
+    ap = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+    ap.add_argument("--docs", required=True, type=pathlib.Path, help="Path to docs_selected.jsonl")
+    ap.add_argument("--out",  required=True, type=pathlib.Path, help="Output datasets dir")
+    ap.add_argument("--sp",   required=True, type=pathlib.Path, help="Path to CaseOps SP model")
+    ap.add_argument("--val-docs", type=int, default=10_000, help="Validation docs count")
+    args = ap.parse_args()
+
+    sp = spm.SentencePieceProcessor(model_file=str(args.sp))
+    print(f"loaded sp: vocab={sp.vocab_size()}", flush=True)
+
+    train_out = args.out / "datasets" / "fineweb10B_sp8192_lossless_caps_caseops_v1_reserved"
+    train_out.mkdir(parents=True, exist_ok=True)
+
+    val_buf_tokens: list[int] = []
+    val_buf_bytes: list[int] = []
+    train_buf: list[int] = []
+    val_written = 0
+    train_written = 0
+    n_docs = 0
+
+    for text in _iter_docs(args.docs):
+        transformed = encode_lossless_caps_v2(text)
+        # Prepend BOS so train_gpt.py's _find_docs / phased-TTT path can locate
+        # document boundaries. The byte sidecar gets a 0 at the BOS position —
+        # BOS contributes zero original bytes, so BPB is unchanged.
+        token_ids = [BOS_ID] + sp.encode(transformed, out_type=int)
+        if n_docs < args.val_docs:
+            # Validation doc — also compute byte sidecar
+            byte_counts = _token_original_byte_counts(sp, text, transformed)
+            val_buf_tokens.extend(token_ids)
+            val_buf_bytes.append(0)  # BOS = 0 original bytes
+            val_buf_bytes.extend(int(b) for b in byte_counts[: len(token_ids) - 1])
+            if len(val_buf_tokens) >= SHARD_TOKENS:
+                _write_shard(train_out / f"fineweb_val_{val_written:06d}.bin",
+                             np.array(val_buf_tokens[:SHARD_TOKENS], dtype=np.uint16))
+                _write_shard(train_out / f"fineweb_val_bytes_{val_written:06d}.bin",
+                             np.array(val_buf_bytes[:SHARD_TOKENS], dtype=np.uint16))
+                val_buf_tokens = val_buf_tokens[SHARD_TOKENS:]
+                val_buf_bytes = val_buf_bytes[SHARD_TOKENS:]
+                val_written += 1
+        else:
+            train_buf.extend(token_ids)
+            if len(train_buf) >= SHARD_TOKENS:
+                _write_shard(train_out / f"fineweb_train_{train_written:06d}.bin",
+                             np.array(train_buf[:SHARD_TOKENS], dtype=np.uint16))
+                train_buf = train_buf[SHARD_TOKENS:]
+                train_written += 1
+        n_docs += 1
+        if n_docs % 10_000 == 0:
+            print(f"  processed {n_docs} docs  train_shards={train_written}  val_shards={val_written}", flush=True)
+
+    # Flush tail buffers into final (possibly short) shards.
+    if val_buf_tokens:
+        _write_shard(train_out / f"fineweb_val_{val_written:06d}.bin",
+                     np.array(val_buf_tokens, dtype=np.uint16))
+        _write_shard(train_out / f"fineweb_val_bytes_{val_written:06d}.bin",
+                     np.array(val_buf_bytes, dtype=np.uint16))
+    if train_buf:
+        _write_shard(train_out / f"fineweb_train_{train_written:06d}.bin",
+                     np.array(train_buf, dtype=np.uint16))
+
+    print(f"done. docs={n_docs} train_shards={train_written + (1 if train_buf else 0)} val_shards={val_written + (1 if val_buf_tokens else 0)}")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/submission.json b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/submission.json
new file mode 100644
index 0000000000..78aee303a4
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/submission.json
@@ -0,0 +1,24 @@
+{
+  "author": "Aayush Baniya",
+  "github_id": "AayushBaniya2006",
+  "name": "Independent reproduction of PR #1797 (SmearGate + LQER Asym) — val_bpb 1.06136 (3-seed mean)",
+  "blurb": "Independent 3-seed reproduction of PR #1797's stack (PR #1787 + Smear Gate + LQER Asymmetric rank-4 INT2+INT4 factors) with seeds {42, 0, 1234} on 8xH100 80GB SXM (RunPod IN, PyTorch 2.9.1+cu128, FA3, Triton). Achieves val_bpb 1.06136 mean (std 0.00059), beating PR #1797's reported 1.06335 mean by 0.00199 BPB at >5sigma significance. All three seeds individually beat PR #1797's best seed (1.06297). All seeds clear 600s train budget, 600s TTT eval budget, and 16,000,000-byte artifact cap with >47KB headroom.",
+  "date": "2026-04-25",
+  "track": "10min_16mb",
+  "val_loss": 2.32265,
+  "val_bpb": 1.06136,
+  "val_bpb_std": 0.00059,
+  "val_loss_std": 0.00129,
+  "seeds": [42, 0, 1234],
+  "seed_results": {
+    "42":   {"val_loss": 2.32117, "val_bpb": 1.06068, "artifact_bytes": 15951346, "steps": 4948, "train_time_s": 599.561, "ttt_eval_time_s": 533.520},
+    "0":    {"val_loss": 2.32323, "val_bpb": 1.06163, "artifact_bytes": 15947797, "steps": 4920, "train_time_s": 599.541, "ttt_eval_time_s": 435.107},
+    "1234": {"val_loss": 2.32354, "val_bpb": 1.06177, "artifact_bytes": 15952843, "steps": 4916, "train_time_s": 599.557, "ttt_eval_time_s": 468.924}
+  },
+  "artifact_bytes_mean": 15950662,
+  "artifact_bytes_max": 15952843,
+  "train_time_s_mean": 599.553,
+  "eval_time_s_mean": 479.184,
+  "hardware": "8xH100 80GB SXM (RunPod secure cloud, IN region)",
+  "reproducibility_notes": "Stock train_gpt.py from PR #1797 (dexhunter/parameter-golf @ 04d35edaad74fc88b5ef08a814c94596b616ec1b) with run flags from PR #1787 README plus SMEAR_GATE_ENABLED=1 and LQER_ENABLED=1 LQER_ASYM_ENABLED=1. No code modifications. We tested Gram Newton-Schulz (Dao AI Lab arxiv 2505.16932) as a Phase 3 ablation — showed slight regression at our scale (+0.00087 BPB at seed 42) and was dropped. Logs in seed_logs/."
+}
diff --git a/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/tokenizers/fineweb_8192_bpe_lossless_caps_caseops_v1_reserved.model b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/tokenizers/fineweb_8192_bpe_lossless_caps_caseops_v1_reserved.model
new file mode 100644
index 0000000000..fffc8bb306
Binary files /dev/null and b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/tokenizers/fineweb_8192_bpe_lossless_caps_caseops_v1_reserved.model differ
diff --git a/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_gpt.py b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_gpt.py
new file mode 100644
index 0000000000..35419a26bf
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_gpt.py
@@ -0,0 +1,2 @@
+import lzma as L,base64 as B
+exec(L.decompress(B.b85decode("{Wp48S^xk9=GL@E0stWa761SMbT8$j;h8028C?K0n@VT6Qap3Y@@2YR==l0&=W1F#V-rmTA~g<&r8N-*N~kw2fnr>D?TeGt5cB$s)%94v`dP_pW^><ZEwHO(W^F!!MJW|U$*&)xY5*S8DR=3iCRYgin<w+F1i0G_J&b&e7a1k%W>Fvu>N6^$@~pT6Hcje0_=!;RB_kbCj|C}(<&hV0H2Dgl799puHs~|LXtN9Q*Js2RaLjroYrX@3LO^UnptqPq2$1+Xh_;on%Rp)f83fy4-;NotSPL?pQ4}h}POR*rr>oW<^(mvSvWxd3*P{bQwNXZrdF_)o#?wS8=<it>qsSoF$k9({eiuF60>c2o&_NLYgCOBlUDZgq#M}s}dA2&Wp?~w#V0HhY5S4*7LL8`%tTSe-U&MhI1;ymjGhf`jDSV|GF^1u4ICj*aZiV4M7YsxbiaC80i_hkVK&wWiYivUi=@X31XK`=1l)`4>8Vzv!-8`N?rSR(?($ujb`C?!T;LL=44b;TDsHhh7nk-e=2CsP33|?P3!#0t0w!2E~lguR=|ESJmBnPU|^YWq|&>v{wI>pyZpBFtFb$L?^ktzUwGA5%M`TtGm*O>Fh=O>l_mlqCLYd94s9Y=@hb1u-nEbPhG+D3*^e?eX;V??vC3Ow4_R0Bs^$$%9mU?P)hluJ043EtFsbmG&=9;I%&{5uRH6d{FXw>6=qw|y}h0Rk?TZ#*MN*rK(@A^2>q8^kQwygQ0i>IZo61S@B*EAT!dwYp_;bq514jM?O`n&mqV_{|kF-k<cG!>|dYB}|VZJ@vVzfc<I2fXA?+2)R~FfN5zBb~>*l=upFW#`-pdB5PX8<_^b^U&TgS)nWiBnaoLT21!NP?u#l6(3m3U!5*+<uz~nA|Iq2rRl?0Sh27u1M)Cq%^w<O-G)_?;Mt1u0#^(Q<t|O2dm=`Sp4Vi_n7ph?%l|cjp|CK?jchC_Ia36NU{ph6Y?M_EM2E&7A@8yU-XmDgNScib9-_?E?8|c$f^Neym9A<NU1W}ZGE63fOg;r4sS*;V**-&t;HPiy|>-5;q?1_tNLMwY_*+(!3OcnhC9|xv$`TcZSgE)l9QsECG1ULh!Pz-;-r}+59{jgc1k-4EMn<>vlx{gw%u9?H*^;2;deqw{vBF9*9V0Y{k$nN~~tfQhgTVC`Fri|F7VX+nqDa8lP=hRg)PjJZX%7)l$Uvbky<w`m0O@%^e(|epw%7Yp)x?RmVHy8}AkDD~_W6k^b!FKq3Dl*)<-Pb1c42*7jWrBL*N=gJ!nSiB>HUJH$K{<|br)&N+$r`+mJC)mZNZN%B_KKjgGmlkz*53(By{F++7$aH3T-(<`VT!UFw2!>8^YbUWitFx++=FP~AhWo_spWN=ObjY#ey<|##-S=9$!>`ru||bK69>M4P10!uIIZgFLAy7|!BT#_C6J4Qt)i)uRr<2re;@i=Trk;U0ZhhWZ$$Ei2v4^A^oDifX3<`PFOhP~9S!_)m5mSD2aly;ArVERrZuu@F`-znc+XaSWy8tBHUzEC)#eLqHln8D2T%Q^l3xk`Hx9507qILXabOG22O#bc7+wH3Y-kPWW8MP23QUn&8z*f;#p<-0%S^_m@1LLSbWiW9)1e&7-v;Qn%>)^%cI*We2=hcsQWT--3yG9LkxVIh#{-!cRr@;4ZehNIf`r^-vFDKSuN0Q%!0M$lvk9D~upBNLx8YuhaHhkpb~jk>^x}!hs2uPeGld5__fU$cl0(DXsp1ab_AxGUm0PhZRcnP=>6N7(7OF-Eu*j@SUFw2kkf!sZa)14uDVf5O6Z1v>#1KvElusDNF=;wJ{RdcwyD?y2No<hB`~zDIQR%t{mVsPim(uW94J;@@kuY9lT8YrFgE$cbr)_viJ`QCZxz_kII4f9GS%5_DT}<4;wDbGbQa7TX%T@P$h96qrViptZkjz*;y_W$pejg`_O_SSlef0jX)tETvKrR7Oe5-uFKdn%9-{#oJEKnRZOx5dO`#pf}uY)dHhqI|ydP-3CXewLh;3XatfQM}F3NW;0$#RM-biZ^qSd1_e|4q7<g7)aSaWbbBs=oB@m1wK*p^@Wp`v=X&`OspQ??uf8{Y_F~)>G>&0Pq3+!X!v*pp{{q`B_j!(@w;9Uy~kO!(;aPlBnz>35WKbHPg=oS&zX_<Dn@4yO$NAyf1v{pa^O*;GLlb78sp9_j!sfz2mW^niG~mAI47XFJOX|9DQ|DOsxfAbXzj3C!5u}JX-zEj!kT@(?y3fbbx?Okp_);7miBt3-_<ofutv2lc&aoxsfbKE-avC8<=%Ij(Ld@&AJc->Ud5VQa(sZyXMjtH`n(_r>rlZ1}HEC$yNa(DC<~`a7F9bKf$}Moqrqygr2G?a2FMA8S8qYFW?WPu!pc$U7#Ov5f!w&G?eCmW3|&ktN6+0;~O$myvG@=s!w`7I?Pj}m^aJafdE<BNADV+5xuw*$+lg-_5cC|vde*k%h(UI!Qpz&2E<UFvU*9xSi$4-NCxF%*Huw~pLEwl*(oSsvk1eM#dWQHCET@K-q<G3=#Pet`?&f(@&LA8oe(kDcCL-$U96mO`Jg%FTp0@6k^Z=LH8-_M!o_b5M-^Z-<4m>Iyc)VKVn_IAJPgese)s`jX#P_>k`N;3+Z0%`D@DlX#o6AI?}bb+iY(XWcCxp5l{*LDx0`pjZe5ZDrqpq!p6_qXL6R@L{yW6~dMK6%Q6=wz6#n>pl(SVI$-FHX@N_V~i-eK#8Rs{FInqwW=~8*29F6J^d@=2<9tu8noFyPSTogr=r42wLa=r5M&{P)}0qB(TTMxiuXGl>tek#gjB7n-I1yOT|xu@}-x6l9tDisS_o@Aq%9MB!B4<w|7Hnr>LktNwtQE$RLYJP@osal!xb&t{#W=I=RJ2M_Q|53L(YOuI;UUTd`=;KWJ6b85!ynEIcK)-Y}n_qBh=G64XsVz$pL#(eBK+=|kWhnT(t&SF76iEgG27Qc=3*9|)1;M>NipP2-&IG}52{u+(9QQHv4^IRMe)5YavNObOW0!0Te@58f;EcFlz6FQnXnoPSR0&(D6Yb28Pr%1(e>VLE;WVL~yq&~RszhZIB8J3KlKc!9Q7}t|*2~|O?Z1|m|JHl&2I@E^!rmTe3$wqVzvrVxqxwEDQR(p*7YLfu)1_*c@4N>3iQ2OgNH$;k9?t;CqoZmY)~LWZ<fpY7^%(dLwDr5l^?@Bfd9UV}`RI6>^X2loijqq4L8=eM>BICF_G2tUTj66jopE79vvRKXVoDBMnp55YtdR(>`#&|=O%{`@K&oh%Qi%#+;qIYmKOSs&kr9{{m`;LW&jY%}`Hv?y3XXu93iAE#!Rv=jL^_e+6PQhq^n|7<213q*;!b(o&R#vF#!QycjnH(OV!&rJB-f(}!$&r<d@w^w+CS*0iE!eJLFRrc5Y4V%u0t{=UWY)e%$He*xfwB&x2!BNJ6}9x3F}*d5R*MLbiTY8;rh%_l2EEr1;c08Vld%*FMC&*8(y^Uf}&|1;b-v*xm;bI-%x-4qa7l%V$T12T`km4l2?i0Bq+2c3Ar#Jp|BWT<$(#~)w6<Pjj{UYDg2PVunSF>Ua_onWph6F9Q!7g%08*f;)3J8wmoFO3M+bQV45kE?qdZzLjTabnUC6V9)!*;&hT5=uW8mY&upQ<<zq{`){Ev@l^U;0q|>wlPIRpCn@jwmv`#q6qTE-q2mJ3fZKk;qmS_njGA4eZ_=?vt!Bf@{XqGmSvZVLbt#9wN7Snqak{@_Skll|A>*<2c9}>!AI=`AR<>c6nWsmqDJT~aHrI(<hXEd7y!VtZ(h3}_mgx8H8yO*X8M181PDvRMO6C3Fjq<5NU0g4{@^fPpVAmRB<K4j7%cMI?3<R17^Okdoi5ect%A-6z)vIv8F8h=LDZ#&=SyZ8BU3~Rt#Iie5zw_wT0b#rfAl<Egqw;}HGuf(TU4secBtW&9dz)oVY^XY#9RkF>z<d`Vuq1dulzs+qC?@F9@z5%DAv>v;?!Xe=XV|S56W6#riL<jqrHvpmiD#&0i3r1&+1uWdn7_spk#n{G8io2t*J*41NvxxP0-#ANNgS?d4Hd~lQt~oU@_!Z%DKIn)r{xtz*OoHj!eR+m^UZ!=@XKMVKK-oasfDNF~D#eHl`GGuNFFo!$lV72|5>cB!fza9B5o!0&qbdORj^+UAMXB5w-$MO;;4#wk-dJGW`@Ra(a!M4Y7Q?;oXP;j|Ksd!7ZS4fCU<ur2lN>Q;_IpsgHmTL`RV?3vhq}Z9a(oq)``>h6j@9WH8ZwWe@}*1U=~QZpuxGH?yE*?GVdNuCy_vySG@o8=79_Vutq&TDL3CXtE-(A~*^**(vLx!nqTg+5$t-{S)cZwWbP^qBG$;(T!c8}==56r`Ldu$sfon++S$5EEMZG3mx5QBe2l)@+36azqKQBp~11$gJ0PD<ngJyl~!*6ud{)c_rAmLdl-Nx#68!yQPP}hdT6CoL@|F618)lRDxKfqqG>-SP@od)|CCzgr$GIX`tlk!Qc3;_&pUvI=C@9i2=l?q=ANvD&HR{5AC<2UR`Tm@)Z>y_OIf_ydnO1Hc(p;o)C(#unHJ6#M&443DP^-u(Go4L0r@5zN7ee5;ijJN)Y{1ZTqChrD55a-TvX~?puLx}?*_aEQ-Q@e^t&Al6GjXbN?Eo(_Uf9e<iAdzPAJSN0w(}U4bWLu*Q(z6s@MA|D~<d_DuPe$FM#Ead-uIl1UMQ6G4wdIEN-S-uH8LT|oIFi|&RL}V`F{b7Xw~H+ae6`PdshdgjfWPFvXIGn;ZG4+4O#yIRG+1ZOcb(HRgB({<1_@6$7@3EI0#@HF3BgYgsxjbC-iHy6v<b-K@)EXT-N)Qn_iHad*uf6Zn^_~lboaWS7kkS!^!=-iHV3?V=3qLsC26AE$rWYr#t8OkLo~R^gAx7Yy)M&njn(jdK~I_NyLL%k0gQo+Z3`ofaxs53=Zlmtna1~sIkCBmA8`sQ#1#a%ef!H=ykA*qHlAPVNsXza?#v!?T)rn?$Ddj^+vH>Eou|hfEUq|k7XZq`T$XyLWhIb@zHJ}8y@nIsn(!8hKbHN%PPl-CtTv-zH?FdtH)A?CDfzv204G637N#RqGGMc#cNcm;B9=SKQv?6JLNCQEVgNW({)hDT@@_|yfv=H<w6P1nlX_e(tFijqs$LT%>W`D=H%r{V+t1LbKVkPXaU9zI60Qn`36Z~)u4x)f-cUk?=fw>06Rvma^bmV85BsA@eGt7p8Ju8U5Ewbo#a79_!d`pluB&!-0jrHK^WAumTUFy!6Jr9ap>4Daq>F|+A*UD+$CeK(?@miA9$EL;m|Zu{!Doquvu!8U|7kmT4pNh()W96xVMwdckK9;?g5SwiA(?wAsiszy9b#4wT}m!Msgv{731tE~OzbD{9@apau7IJXnVGuu+LAfK<C%^OP=^tkV8RyWS#@=Og9&fEo8u@p#u1eR{;f(PAc)X9i|&5{WM=4r!kNTEnPHXmy)7iHKr+Hx<cf$f!RQG`UH%EQK*P3i3lt%BjOKdK5EI=K<-tYI*x$VOB2#bAM7I!mx=W&K*)_ArM`J8`@i#+^^-LU3PA@U;k8Pa=6*%Hky|?wggI#1!>yqbhRp1~rMpyE}Yt4IO1;E6*_+e+f?8xA5P}W-%5l2CLXper;lAt)X=0H`q(?-g4ccGOa{!+K?tA%VDSMBiObX*xT-tlH50ddy4u~Hv)%6e1ktmHOGXCQo>XpZyH>&or;T<rC{TDQgkMU6Tddh;u%cCJf99yafV$?DV)yd$d*dw|&34h&)kwApNTNm#OVJCLJ#R({4A;&@==K2f^R_3ke1`OdHFtY1PX2xAAjz*Gm<vAt$X$PCOlLS?<ikmO<CFJH2Uqt*51<1;PUIl4V}DW05$+$^>{YD2!vJ{Xf9k0ub>Jr)D)`kMtH+5#sg3BVp_wz^qmD8unbXd7e&ZJ`y*v)8b28GR)}UGD%N1%P?_LtA}!7^Ykct^{27+1KNcq0W`5ObwWw{583%tr;dYX1c3vU86yz-~b{>tEE7=rNx<@z*_SZ0h`Qzp#)l?(G%9pnHX)@=_+7A>NUJN>z`A3<_Ej!k~_Cd=ySi{nxv#Jgloi6_9GXQijK(+fJ?y!9WNk>>oPF8E5||028rPDVgI!fr@Fg|C#V~r;>Fotczrt9fZqeeq_k~r=ZyK%8#QTr3A#r+;ow(DXt(^=0H;I?XQ;#X(5v}2<BCL!^WN=e5N&78>bdH$5K}=J`|Eu-TJ8$(C|&(^TMwrH{hdP?QJK($x=P>XEYY8+I}q~#_Ar|PLlp=TuUMK==mpOP%H&di;SG)xedxv^Qu?^r2?s*1(cQ7py1}xJ^UHn1Kx`38If2-by?kYOM31J!H}JmDWNT`Y&oO70?=ALq>-}X04>ie0r(jNRybmZ<Pa`;PHK+eK0s9Be+L%Scg;5{5m9e|Q$Xj(BrM4YKi-b|aEKc$7(8LRLV7)#6lYv7ngd6>zzY48pd6>Z{8>bmwC~hK{Mb$h~Ib~I)8<|i-i7JGldQ58CqDZ#(elmjAeH#y9hR~hP!S#SBMF-^7aZ)+W@e9!N<QbY#vl};)G(MCyoMFHB+uwAUYhm_4{<e(1yut`&JPg6iRgW7p8rfpdT175VNaX?23<RJUUI@l%vRFrv%|l+JY8?bWF7uYy06lLZhxE2ud9FS15Y!jxHgi@uQoF_FCP1L#?LOtAYyOZ;W5}QVEAm~DNC|i1PYlZL+%w6OdH<E~W<c*`IDu{r?+-*yxswWVqU%m(zMP5|@H=7ih5+<^=wJ0uM)O%UmJGkgGDJ=%S;wHP)*s}Jep_dIUV@f~5{>iws-E55fbk`MN0aqLWXnm;Wn<@W(gAJFFgGma8qyIf*L~$$go}oN*x4?PK`^B-*hhC65}YRADk;Yk15n)&sH9@9c6k{VuQZda)tW#c**fNJ|EW5Oqf--B@+|B!*?<);CU^z*JrB^n<DSQ82eMY~i>&WvP<ozf^dADBk`@HnkZ2^95nLvUpU%l=I2LHVFp}%I$r92(7QdA<f4HP?1LdR}9cuY%h|$}3rvYEi81qwJ!DCLIKnZOgU8H7?Vv}w1v66R{UK16hiUoKiC60QpMX38X^p_Tf4tftE()Xz%F0%$miv{v6s>x+&{)$}qjX9B827mu4It3wuzugBI2X@lLop#g5cF}Yja#B(qy0<Fb75sVge{dP?zCPXuC#lL3FAQL@i?OW+1DRMp09q<av@9>aLmO09!t*)Ys+fe{o$GlM>Adpz)maT3?%K?1?{F8nLSlw{K?F;MW?0ep{v%!AX_tQC@BnZa0UvFmc=ct3t(e>(`V<r%3Kubjv)p__Yx~06S%cJ*!x9s^+_>uHV(4n0q^Zo~tQ1@HYdmcO%f~7qT*RPN@&3&1g*!6Q!!jyGin1&bD;`UiuGhR+zp`M$9TI0T-V?t^(WjDIB({c}u(FMQz$hCH78Wqm4an-5hVxXuSK6-Zn5#9Y+7{~5Zzp6(NwqNXVo~OwjBftZh+JH|pXs=mqv(c%YfI~8!UM>0jq>j4QetW(OyX+(k}HpK>^LRMg=pc)aHh|S(bak|S0MIlg^1G13TGY9Kzpt-DX@W{#I|9HC*<0re)^)h>dzZ?9A8Hn9^{S`KX_`#S`Z(cL`4x$nF~b#av-YNt^8vv<fu)+qv7jUN!Xm~k21tOyFPW^kQ=a7fQR@RXKXN=t3(e^P;(iGo3^yFc;<*#c3`G|kuL7u$e&3_pXVBw8;=XTL<E;Pl7#r2Do&HJp=JGd;j3~mx~`7W;*50#qMnt0ybQ9zb9fVgTInwY5c!=%`@btXPtaz2<A;!+6(;{`_AKlu+^Co_kLIQ-geJCDtpC4C1&tt?HB7HFXhqXdoRu{JwN}edp2r~6T;<KfbDmXz7`2FsfX$y=ACt^u9KB1SDB{mMt?psE_(WnfHR_0z=txkyh!w$~`^X?pvF@1N^v4=fI5*QL0^D|U5n5gzbrD=T->Jhl30Bj#Ahs=ZzUhyb%@3>>oy;1Okr;$ETTHynLwUsF)Kp5t4{8m^B_gDOkLkr?EY#xFmnSSRUS0TFuFH9ZxKkTV;|kPl8DDrxPU4P61|_VyBl?Lw{vUOEnmq2IQMD~O^OJG^LK6m)jU2DDM<K%gtTtq-z0Bt436B~KVhre-Hgi}6x&QnFR5~Q-iMwL0;qEKMid}=z)pjM-okeE|Y9k5WDZ?vLMdR@#k<hT1zGfC~F9k_bHP)!A+AGj8(?4?(@fx@;w_(MROG1CIT7Pgf?0w&*nJ20h*#?9@Ub=)<RIFQz?ygf$r~iNOA_4Z3504J=z5?&p!6mLDHtCW1$EnCZ(oZ(7(Xg}p=5|rsRZWa%PQ|%|$M6XaNsc(Hfq<62GR_@$^1ex9V94cyu(#FyfJN7f?HwOL3S~^Kc1KM{GoFWOjz}NPJ#!t~Dwq2OVkNAzOGa4UST%A3Brj-)H#V~olh3ZJ`y;SR;8J@6MKEYSOz+E&Uh9FhwRb%BFYuX3^;7#2e3f?a9Dk_B#8%zMSi=6na;!bK15WzCk8Q)^^xTL`!kStxozo7E*)C7__Rrz!3cshpELA3IpQxgeo_`$218f8`7Tvm(<1DUy$ehLqYI}1`q{~Frb@jF8cGzcyRcD&D!nrLNafNl!*?ISt(KejSYK4t`_5T(y@_;~rWsh^j^n&}(MrZu-pmB!j&*gMLU$1gqA$k;U!2-p$0>weJ;;|gIBaoRwRvq1<+(w!Wyh1%xzeWO9Av7vugeo9%ZTET4zi(lWS*`MuVlB;?4u9V0G)*W4){2!<0r@sh4Cdw7F6O-cE#TV*%GBGp8}(5GU{PJ<;D^zF)D0PG4cwx*T|brv<09}9AFur}yaYUe@=rMCRrSDmu%-Ayt6i|yh8PM+$tXDH>j_<?8)Q=3UdGEOg$lqi#{@T6R(m-!8Y9Y8u%pn1^CiCZc16l<9OhBKv}-O*4uxG*56xDYqA0YRs%qMhD`&5Ws*(h1IpmM{5y`~t@0H3mTDMFHWz;1j2q%@d1I@CMfSb7^i|fG1C~SIETwlpbs3^?E9OYK{kQR|d7G7&LWUq~7P6R0d#xtSQ2vSdt76C=1&KN!)wZ}HGyJd(7_O_a9yL|!sr*va%kDV3an@r6L@iyi8JCt$zdTA7G>Ac%$<<H%@mIG)YydQUXdj)7yscD`Z5>kh+L(79J-D{f{(4jDugQ3(rFey@c9#}9`!2oXB`qA-nIi&%t$;Bf9u7N;qnk9h>SiSup?QtRFByqu!UTK_SG9^`Bl*mpo;x9-h^DJ}ywxtMw6?RM7u|rSH&Yzypu0=YNi;fH{-EOI!!&bYI#7XT#Qq*I0`^K_7z_4aEkm}ixsmkPq)1<|=nCnxdKm-H*ZQj^Yc|&ZwGZz35?b?-}YblHspOiYFl@v_O(UBX!BmpHq*A=`wUsuZolmaIRoxfV$DNa*3!zYGosOBsucK!;dfqfi2DzWzfmeOH>LttnVRh{_a04vAlHvE@*q2?E%$yfgaBdn(*Sb_6BH#fZ#bMpPF|5_~<+^+|!9`mF$LHJPW_npH+KA3h`8a0qUl0QK0N#rmKx%b(?t8Ic&VN;u^2_7vpqG%FTy?$9-C3HCR!)D&^Uj8-y<YQZkg-b)j_#kY6bV;$TG~T(eu<DJIWd=K_pva%JY4_6u%0`JAQnB-9vM)_}eHWq0>%_|J5~gy(V(=B|aHdCxE`h-nGER6X{*#ZF!$ltwr#=p=He%)H;eX%=d&k;1Ax}faU@^;_pYPG8NGbvwJ#^*Fh8q819-HpaL40FMG(NLseFoa1k5p>dbfM^yCh4rklu+Sj)J+A5m4AAG_E|<ttgOfYKJXpmv;Jw%<sjlVbV>M!)&uOqlPChCtqZHl8IS#XO}F<D1&Yw?2^0QuwUjr^`A|L#xAwEd4tUpusY@e^gM&43)+A)grr=?_P1=A-=ciz0%c`AeVk?`WNvP@}A>(-(hy{;7?9h|PLmA3fOJ$7b{kZ2Kv=SEIAX~XvXie}ojY1=nA`$z2p<*W_?gh?9gM(K`_IT7~Lw&J$8W?T)16c=q>Jjc0G{#G8<VpYOOii<Tcs(sN%=+`5>umj?7G%|&cWE~Lj&;xXX6O#)1$~ZEp0@w?b3kQf4Tn7sxEV=%;uM=+Ymdgp_Z+a>d}$orUqEnBilNQOJ<r-0*7<?n3|)Tf<rq~xjMhiDdh~46iGmQ`g6LYOa(S&jCP{telOnWxt@IIB>bi4s&MFe7K!pFheiSjzKoCPf5#TpDDMPkXAhun%r8b90($>wsOEaNgs6ChRVKgwr(_jVefXrT`3}m=_b`Jkj0=aewnL%494zzE-7%SYoZI?a9{XE(~%D%o=J|VOBCd2-rq$N$ErGapN0Gkr&xvlj6Y58Ke{qVgf_RCm*Qxo@T{`U7*h$P~xT1B)?P9ILNIT+Py*Ovl4L>tSLHl;TMNIpT1J^t5IlEj}@pcG2u9}@wcvW7(7ZXj%<%IHlLxvVt0?f!){17w@NUAAe~B2EX$U2|<<=88-9&0;EEW<oHiR8j{yU~b)lOXvD@MdW`AjLb30J!*6+swaD@nqwL<+0K1(m}T*hGFuS{V7vZsNAqL9BVX+?QA)!Z^zdBQ9`aIKdvv7BXUN7IAk}M(g~x5lVFK{1yYSYgI=!n1=_3o!RcEj(5XT>ld0Z!tJ#OB~ewjFBtY8TbT*3;0tP}4dbI0yvAFRLp-x5p<A#J)8{ykv(dGu?P$qT=PN=zp0_9mH8?^lUZBzo;2MpE86O%d9(G|z}jg$f}A0hZK&k<O<2?ydWbru>dVU^G<QMa$eK?RL_}oUgG<A84DY3y47uBSkYJSWLKx3&<AlOfUy}f?_vgovGKbRaLIf1)K{fi>!>KS~TT^sDd7uPZ#t;`h9SziYSB3o5?AIq}GMF=U4yo@R8?rNDJJnhv22(xa^BmA_ng#9$0^M>a6sZmq!ee?FXzN(xDK^^|XZFu$9a=!srdEvWqXe_Gj)f3E(;y^1>GQj`G$7y|ULFwC8rBg9b7_{6sWI=@WwV>j+Cz9Qv`>xJiweUK6t6s)O61+-K@+YT2zDNCib+Bl&+62*Vg`P0vtFUSpKCwbedFTWU8XRA)FyomXbd$>Ow7m}f=0ip^zU-~lV_uVR-S*C))c<*bJLku49=XVzYUMziFkIE#d7huEX@OHFOx>R>4N<wl)V`lr2Quv@Z}_fZ(|lC(9KhiG}stZh-=<?p*ix91Ic^8}<BH&nCbJlTKknuVOTZBP;m(1Fh*$Baw75fGJt(3+FQR8f}p{Q)r+K1=zbyuTf*`y1VQspJB@56~#}<EPL;Bb5gtCW-RlXB13eESbc+l0Od<6}W(#zl`Ny$8-FeLE4`mk?-<Pp@=b}-`k28Jc^C@!USW!!k?l)4ahOd!?COm8Q;cQMZ*V?5Lpp?=9L!_o7JL<2G8miP|mB|S4^fzKu1s1#Y&(6UeSJ@*WOwkGs~?(BJ%NlVgN``2TOT)x!U-$YJ8u~v=Vc#+<Ix9l;k9XhmslcGI)6p8RS4jBRQyz%<?Me%O3<2Gd~NE7yo+wPrGE*3iHcI^yl7swRgP$y+nFEyvqNA`Xf<n$4gS<3p3sms%PNGD!qMdgvLGG`A#9PLoG4X`WD$7Gp>dxWh~4}#sqHE9Rrj>`ezehCEEl;a=NBPtWtBnWnwUSV!RVgu(PpHY=}f^)B-j6f7BPtSJTG&7BH^oAjZ@Tt^g^mtjLtqs*=P)NGF2r_QmJbX|NDj@}A>c_J*_GX*z+y5niLL$sJxK@sh0}{!r-<x~vVayHOQ5uZ^Wx=3SSM2;}~?2SkR(nobB)Nx11%Vu5iHlCEP;$wQ`)LAtH_l}QdPLX4CGw|zU#f=#tYJ4gnm@+>TK$qU3;yv}dp;%u8QbsZ1jc*aJ4OHYpF<FIW2&X2K%wN!3A>+Y!kvF#J!HQD*Lp~Q9l5@u3&4vJC_D_NmkuL?YzZ%Iw5_PWr%oRJ2zhXP2!p*rXraLeJ}RzHJoi*l7;aIy2c3WHBo`oLL%>UD?}Y_9t%HcW?Irg8O@Y}ltQ$KhLT;^ig`-4VKkw>)w}!>*52hFti95crmnL0Nt&kt}~2Nf*k*R(z|zU@!wxtFo)rr78<u{j>loA+EuqtQI8|rY*CB**eiet1)hbUW<TD^EV`Ze}r(tu57k50cD5_v8+OdZwV?8nqgu2tam+rYR=}ChL(%;kCRC^5dKHSyF+qWJq{!>P&Zf!N7I#z7de3^8_ctvPCPj~7g(27y#r@`GuK4t$SpRD#+UgL6Aq#o$U%sT_3$@st^@ymc~rr>b9fq=C(3;mr8uRyDZ4Jly0=d!?=q}~{B16;Sn$0nS;MO-f9y#;S9qnjpILED1hi%aC*C0*I_XK0kQZ;hnYRuY=!*tXIGV=!CxKuLv&emGZB+@`%#_A6gLljbF#sqVas`ow;C5pax~sUv+AxY-s(IPcYeXh96V0w=y4ZMeB=?|F48A}OH!QxHXE@JZi=@tu0RRr2_(^e!xczp_cScHv^~bLOpt=>iG{R5fiZ;iPGdwjiCXu+QjZmp|M6vC)v#Xw~!fM$xeZE>1qgoW{r~aj&U3J7DI?EFp`jn^{&@7~$31(iTcL<ZL85<QT*>u#2fZAqAB)dTD3V@I72&cCPFivlEH1ZqN?ysb>&qeb8O3D4}lKHJqn!1m9->Voy00Tptf&7-YQhFT#R4`&>f5S`cp1rc8div-Nr|%4f;~n$-v4HZKE{^<+;H257bld5eGt=GDqy6q8+91GCV%fy31JCzfnH8jz`fWa)iq6Socp@<d91Ocv&T5OAVqzrV$W%DbRAh3lxkL-$9a$e1mEy%Rc`9H1MjWwQBlqF=n53zy!c~$NdK`7~I$2&XoQlD1wX;-S42uf@wGleQkM3$<&EBZl(*5@COhh@Kp=pCUJOuA^Q11T+OcI)!QAnt^8f#1##<X>+MG$K)!2$-Ff(D^WOpa`-io4+g+5sL^4~saHve)SoZV~12zEM)g1UgZvQCKf5<l<9w9^iCwDoBNnJ+V~3#wWYD9-`U!w-Km)`O4W9)8g~)@;Ljcq|2XR_ec&`Zaosl=!kXild%_P=J1wt(hXng6zfd`bHRvhObkYo=%b{r7CGd)w-s9R(%BGy_>%VbiGvU%T_g0MW+S$zl?tC%1SYMCxq>V+qbc!eJx146a!9m4FC@%<u(}xd;E?~%jKo=BR&>}P{Qw$JTQ7>v%rhxPJuhMh5Zm+41IK8oX6d#DM^ygei^EO@#Zu|cH9T?!{tl)~`VdY7qD>>uHW>5V3J)NWAJTq-PApjV?EdXH0~+?|S<0~G?Z1@KMN%7t3yTFPsPF$GWT~@X0Y_By7^Wa~6dvbFp?MJoFV?pgb+|@p?%OzbIZ7dlNBS#F4O<R4XRWho$h$e7i1%x1&K{-+U6kHyHWQH@Ud*P=ch0QauN(S<BFSQaqQ^o+Rbq;xzk|hb<rI}dOpY^D(yZ9wizEWtC{Zw2*J0FQgng*0&X?r7D3RF=z7%>Tm}g3y4$^gtE41DwU&sL4f9*+j){Jusb`05>BezL&aLqU`1|RxY@!{;erAR#k#`KEoz-)ITzPzQkf`@qw)FiY8>lNuw-KCmWS8t*=mDJPmB&+1=BbXTVp@?taa=$?WPuN)tNk6+{0Q^7msB?N~>voAR7)WyOIJrPOxcA)_-xO@!I9J*pJ$)c9QMPj<t&6!_O|m;-H2i{Ua7hW3)BkCO5V?_Q68_|YKfd_TM?xR=uB5{@0K4TYb3+h(W+*r~rCl`@u08r1$o=C#JhWEv(w(TpnD^DnDwUKEpm5rbHM>W`)418u_UG^pY})!;RU#MtBabl$Jb-Ni3qiFZMT2HQ3%x!e29b@0hfmDp`a&dZV)<aXiBf7i$4um?Q6)o64NTR<auXh1@A_kn9Nww}*P}Z0gRDgu7LyIen0u)afk=3>>o)D6LcKsRd)%*ECXR50n}U#yl~xt=)R40zNOJC-GXWLy{(ZhZdcn0u8~f7ZGM6T|M(sW&LBrjl(A2A9R}gbs?^#NBmZqQ`b-c!8ib6vI559mB@i)XJD95D`A2tEX$Vy6c!Sea(1z1c{a}k}dKoO7H*H{>e?5(g{e*m8|mjpg8o7d<!d<_-b2A~yoTM7Kr(m(-DnE?p_D=&rfZ(mS|0VH~B9wIF3jIyYTGt1s;=7TgZ<84v4WM&NLes2reHB|p}I;q`~IdV8I#6a$;Ki24X(wbtXzDN9DF)f5;A=pv89d|ZLMcKaqN;eVE#|E8g5|;4!^oWkLRBy?}OMKwMoQ7onk{_%F;I}3Q`ubaXHA4~E|JvU$Txo0N?ttSMQ21wIA;J5}kW~(ws$9ao>{4a*bSHHhK4uUV(U@q+QC)(If167JSd=JuKs6dm?^7LeeS&K;Dm`I1nbV~}wJM07iqZ*(X<=_78RSHUo}X+@gSQo0NQOOxVaDv1pr4_G$WNb*U0v4sVj9w~zB_^r$w)R(V{BwW0XbVvmM3SL;i9{<b*{Qdtih5z7)Bka$1uy|8kEz`*9MZ@-bATR7ryTfCWKP%s`iq*j>&yrcWG*xAXWW!to1z6&V?yZO(uZFC{e2I-<JX%h4`Yvn7T-EToLEeCB?4&x!|#WKBVM>e_R#qHbc2TAr_&fa@Q3{i6ANbERP4Far}htcpC4K3pUsY5Slss4Pd9@2jqcuhkbNm6Hk1E3NU14aXHUEy#DS5DK03wHa0m!4Lx@du8p*M2Umb0ep}9_Md5%tqA>uWnafRC5n5)Rr#bAN_uuS--MmRuwPZlMd3Q*9MP~I)?pYlN9~pZ}-X0Y!nyhPC6~d`cf*$hvS}hK4`>A;Zhbg7gB-#V9+Q&fgN5rjIax-?w=fMhz1KFIaJ7S<RF%+2^HNcBP!8j@KFi-P4U6pn+f(0z(S~ctCsLwTzil4i$D*vI~9s-i7eKjuP=%tfZm`rx8MaSp3GP;RX_gwcyhI$H=?Fz9Th?<UW{~3APd+Ok##IQX>M8Pn1i}zyV74^uDuK{}@N@hkB)cO~ui!sa`t>@dfM_udCd+wsoeymOXO!Z|yq-~kL!B3B$z_hc9kBGR%^szLosuMwEg;P20)>H0DA4J`fyOjkuzuDU05uMiy7_W7`^6T2BBWz8CAT?{Le@v{-aaInCF%?_^Xy6)>c%>;sy4a!>E~LAGPyY%>FMg=dZ05YuPF22To-=E!h&G!M6M1Ym_IG>a7$`%4Ny?cYzCZ>a#1xBFyae;O^rDTNF%Et`0lcUZiNCV9?;Xei;rr!`?}Bzn(-S{k`MZ{hVR0}WfDvf&`Z_0SZQ*v+YZOm{mfdq~@>OTM!{6vHD|>C~hS6m{8va9*;`~Y!_V>%Csy-z>yyS*6m*@@9D7Kvz(=5+UVY+(H=N?pnb=qt1Q;%OaQhYCsB%Fs$P|y68(UrEH2ZJKPMUSWuS*84n8YRj_9sacWYU}UYr>5PJk(;A-mV<22j=lM&(*#};Ay0}~`veCMA=cf$z>ncQP=y8Zjx3TfIM013{m3`dO;>U!MGD^%m-ryOm-U?M_2k|rJLn=(kE8F^8{<h-nzc@VL-Sz!S;m@2e;5A{s4P3?%!BwDLsD)6PMt5n{S`d8l>@8Z8(zk0QNwgW85>^67kWgNWRKrFriHhnChNzYk}*9v{$XZ#aGmOQE$NSN7W0+H>?-u+ldbr~;{&A-xzE!c*_^7b>D+c{@VKdIZJ3D}b9;%=Q34Cvh)WDy{Nf88WPZdwiQ<x2mf1s3KZN*DI=sWEdGl2d+Rq#>Bt@hK6J_PO1MMri{b<cfAtnGomrV+9S&XY;C2Mp4y{GgIWcBgn(Xr1QOxko{Q_rg*zHzi9SVh5s=7_7;r7bb^;~&FK3km?Ovg|F|Cs~s8Hw6fQjS^URHZH5WZgIb0w>+PIH^4nIlHsT8OLo#y1$j~MptZvmyxC!(>YZiRYB8)n{uc&Bh>x@Z@%yo4FOBRk74p@z)7};~>25mb5Rq9yY=uK9={5&`zh=^6j~tn&&sX4(b0I%<^!u%Na1TDmRxv7{P96r>0WbWSK2s-BGyRUx&2cmujDMLq1)l3==NRgLsq5;}e?;#S79XxvHIW}d|1CM3KUQ4)nrHHwQga6M)a7_G<@Xrvgl0xI>Ekg1Oe8qur8P_v^vuXa)#*lv?R{3>ttG2P=8+75v9Sz;I{Wd*km||((w}t*_QQV(;jVs(tBAr)H4MGDP<P+0*uDRR{Q=1M3sJo%FRjKR?MPo-6B*e*4+5>QNc(uSm9VeA8?9-Np!)*N`k3!B@{%2Anbb65fJEHcgVc<$=EG#IHXIGDB`gnzk1rC!Fn!cQ7g8t?6TKRi0p{9ukk)wdBqBedPwM<q2@L%OeKDiiO#^^^LuF!S{o2v`f~OvEby#i|Tn>1@_=9QZ1sV-nH*i$XbOej|Wj8N-Jkxx83=*_Go6P3+lbFwQ#i+pCAzO<qdvt_CP=6bmLl5oHiVY--uB3A3hPAhbk+uWw4bFq_X6Bmne=6}(z%E~5b`wrj1)wg9m5-sK#zBN6fRV)%7s)t}>H#d$Ou`8h5nTU~Y@4;N<r=A|CczdxUUg$txEZK4K(SDojdsntKVjd4BULr_PAY35a5ur%0eD)-NJ4|Mn8$Vk6&yMN=SuwbB`P5Ft3w)kFG=DN^~V!M>qr#V8uvZgH%xAc|9`+E&OTKBX@t2Z=%@0Jk4h#`v49DU{c2>Yb`;(%#e;6-mTaS7`4N;TOXZ~$(NPCB7{q@R_A>)?{reC|748=qq2JXD=^&|*p#$#I$B`eu+Oast`a-xbP&#6p<yN(u?D+jb-<??i%V$5nrshUX#vPHXpMSQW)o^WNzJyqFsn<tt$O>VzoJ+{{GFSIOIZo%FOlU(Q>5@v=x?#ywnY+?j2`*%(QiKci^z=zRK_3&}`*vL?R5D)sSjXV0U;(}Syrc=FBqzC#Ss%&~-u}X1cM?y(b;k)Zqvp^n5>Or~c1W)TfhPh2AWA(Kj`+5W>E+=6@M~!m{#@Ppmr8%sWi}Cq4H020M8+(QFnR2h47q&WFcUI0zZ3;t7P-UkyE(oZgO=YKF30_xQ8ReBS$o-de<HG=DW?S3&yn5<T5SHLzmslj!zt*qZQCV)oxJdi>WDR&;r}ikAMW$=#$E*twsF48dDz!v;uXgLoce4PLsnz*y-|1Lo$lh&fpaOlQ0&1X%&p_WG?;j2+fClGp>DPT5ZW#*G-Mq;-_ibX9_fABixLY6zzxZD_uqLrjakxt67*q4z&SY^o=>!Huos8GDGd{LE?G9)Jpo$e-%cf736(qE=C&7fq<UES=sL*0%4{Xu2NyTD<zk5T9t3<}p0i2?@M26n$`7G|x$jl3kRb{2;CPcN^ia;3IdWZrCtDBjM+usu(kn~4yr!QR4t(!{y1SGS1#D9fP8oGT5r6`^<Gp`#TKKqej73gY4BY%XkFr76(3~o|xM@4kP0lbvePSP~@etW_e%_Poc!W3Vn5uceK}xm_*AL!$xJg~%9vCqgR0^Ri*U6lrF;Zt4CQ|C?JgK4#Ed>rS{HbICtw;gc?v|j>Y;dubr;MA^)jG~kd|F1c>7oAN9#9v!xy{9$SgNlU$%~6ObQ3qk8gHLr=zO+0w0_TazVs<oQs2;qCWg4Oms#&Lc|XD?-)f<F(fp?lg68Hnp!gGeDOLt4|80d`3MFEX(3+tV#&0v%CIf$<M`U+|)7Apm@hEG*|JFAi6hSw?sqs^;3loDhdft(xw#ocxJBHQVsU+@fM(#V5oa8Jg%YO(>1n)o!q4WX&5>Y=U^=p<+7`;@bTd#1=xLu%bKr6<Tl|=r6q5o8x(?P5fHN}~ME6A_;l&BorAj;~#nh6Nr2pqjAeLqdx+P>obsThJ}VyOZ_`7vuyFZ>bdpf~pZNN3yf1zIAuPK>=N%SbIT?lT!1SYd9}@26M<VL+&~+SkIjATck_y4`Cx0g$>hnjcDHM+I31S`&`HkZT~C5NhCNrYFWOSyWuZ)sL;LY30A-KowfoRqF=K{*#+<n3i(WA6MYv7B>ip;Pri3W*DXev{s^2@|Vv*=|6p=%li)FySrwe5bKo6cje4A5yed$$?U3g&$9!TVff#j<9<-l@wcWp^TqgQu))MkJtS_o)I_M?DJc7XVu=)WV1I27WhUSGS){s?j}8XGwCO2TkqeA>p$Bb+5@4LlX|A2&4dYd^9v0WiVd-4XpFSxHc>MJxD#X2F0M5|QPd!db9pc6`zxde~%WnRgLvZI2fuYx*#ZzIdT-;oNiurK?CRXtE_4bVLH~G5Pwv5g=Zx97fLs&VsAN7U1QZCS%)c)Al3Gk>iX5mRDG5<1n*@=9;;Hv~JDi-~qzWC;(WZ9{|nW!rD!GK19x?R53&6H6!vek6Sh!!&e?UD(<oUC`&&<Yl$GovUg6smE;JwEIps3Fs!5(-Tv6~6(8YWf?h*WzgLK2e>~o{b&t=$TnWD??<$B4=Z^<OtPq3wVKb3ZV3td`|PNe6y<Jokp$8r3zGMJ)nOHtC)folOtTKoy?3$G3iu(42+2d?YG;?WJRQyEmJ8zTb%iBFeto)m2$pB8mXZq>SR|3@5$G=Rv@3PEX(=A=dLtwU1Qu;rQVac#*wB@H~aurJoNx}z8&=KE+7o08t7~_r275eN5~y4u-KSP51*f#cx+bvFbcApokkz)J_B_z=RTx+w?*Y}2M+HNetVw;{h^jjxFxl}^k%*CTp}weefjAFZurq0LuBdAY(nMFp7G7HbeB`7vUlgNK*-Ar_~-vE&H@rT2c2c3E|BhcssG4Z<|!H{3D-<m_|V^`moY~ecGVw2TTyK8^deWP;&~q5Y*q&wkg}`Bzt{S!YX++UdJEEUp-O_k3QtJ!B!Bg7R?nzC5E>hh+zPbNILx=$k1Bg+&5eVZf2pE5xq=UO^tw^an|(tXQna!d@OLBpzNF<>f0UGniTgx~rXxV!+E47QMM}_(>iW92SrjZa(hJX#Sj{t${12JG?hio`5@x9aJ{U<tQWV9VnUT>?t9Pq1?6Qu|KY%7w@3c+Nmzs~{+TJDhFEW%>eM(^AgAc;Z_n@b?FtF~gLG>rv85tO^{H>or+$I$R$?tql_JK7Q5Z&xPGf^vj6=(wuSZAs}B7E3m9jq1A)M&E#PjdY&mKd4~mHp7bw@48s(5TadV+Yr5zw`KZ2X{&$i#@>_gOo$oJqX2PmlAyGu)s+raE5XBQdE+3r2H*5Wle6bt&tIlUmlE8I_bRrt=Dv>;VJTY?4bk}4<{*4YW`Pg|43l1*`gK`o>Z6YF|gE%v|(-VfZE&SzqwNB<dz(7@?=k#PX)VpZtl8lD*H6B+?j&lZhR(w>A3yfAAOHZPg4rsCBU**Nd$8Jl{w*5r$|C`L0e=FqKULnJ03p;F`^h2%cZ^y`_jwjrB^i{aST=-Sv$T|R{zQ3S9xG?o^VCyLGEhJYho~m7Jz5G62RNE{J#yr(zA$BGzb|)jGiyZq*l&s{KY($i!xnmTGQ=*nF&cV$MhDM1?C7XluDr7wDB=4SNcBtURg|+qC>$tT*iy8n^eO^2!X$f0S-#|)$rOC4L3axTA~&lV2GGqXDgvw!j-KssrN&uJ;4b3#9Syjkj%@S-a+CXt(#S_kSd4zHt_dSgp&2Lo+&fA$y8K!y{*7s+vXZ?0Y8G<yDc=mcvxcQTn>GBp{84?jTX-Ej%sxy3tTZ=uYSWz{v<9A;04+v2pmPKKi!-_>s%M62P|SLJsKQAG)g^b<vBUK9=fd9yL8sM2fxrBV=JBRWQlS!%L2RDqdU6<b67pOdB@6q4{FCt^IuZMJ_@J-8=K?7ml=^V^Q`4=q0Bf(5plSJxCHws`&!U}5XhFM2qeMO)tE`Ol`Y*od%Hl|g_i-I!lDmUHtG|#b*=KXZK>WBA4X~j<T;}NIBnf)`rsD@x`G4E%4zX7s*PX&&BzY=%kCL8>9;{?D#S$o)GD9@(}cawkNxB{weB}kzx&b?Q0isG>~OF6_g}62XQryqHVf~<rI|qLq;Ldo%kMQ`i&4U@e)uilWSrK-p>Gk%&&#kXw2{7#oy=>U81lAbrZnpa`X5<D4nrUh52I^al+ZiQj2Z0beHp6KLJ`{C5><PL?H{?3`}y!vnW%T9PZW1x*Zet;Yco)Hg@>MCP&7U<sp*L0L-j%gS+@PUS7PtfUuL3Yz$FD2#-Un$918qw`0siw*~I#l+vRv_onNtFc{UWSS0CagwUfCABr3vDRjDdlkZcb`F9LV5ObyzE?InDN<Q;k#$|z!k^0Kwpq4K#E;;={r-38_pMu^{2IRe(2p$r#bPP2E1qALqJJeR)Ci0YYyq(l`Rn$HKA5nKg|&|UDBxkcSBGz8%E@-AfD*|sZ#AYemb1B&6qG_96aStoQ+mUP_>g_7d*sz|p1t-{u;)jvU!AMc7(2_ae698G=G!NuZKv2a}`HA2u2eu?FwgXK!Y?0b4fx715{bAcTBV<9ZW!H$Qh6_Z2yf#aMMFO%R<H8Fshir0t$$}^y3-Qb_F6n&_ysq!Slk>$g0ijyo?FX)OPoOtmXk2e<#@BqSY75g&fqe+UL9nEU{V<Z_5pZ6(q$9IRUW*$E-0W3iDN~xgoab@A(P2a>;Iip(^{@e2ph&8(3zZW=^O4XfJhrvJXKDL>%wCAB5WWtO4M!7xi^}HgJWgqb8<`1uT9$4<A<#FuZM(KE^h0nPmV`GRj=Eb{iraF6A%-enoOE%FP9^wbi0#A}E;DvE7@Fxh>L`1j$atw$mhH()BUr2`@6^Tfp=jZ)u`0;3S_%%R`WSMuT{RZO@hih;dJ0nmCY`#Gn!spu&WAl_y8#!&%V8g?*nEm|8{9OuY-HdoHit>hIAbXq^@#4PgRy*ul3fA`5RMh(5j6e4sQ@Wbsy9Bd<Dz5o&wo}xO*HfS@SnD^r2;s%b+ml*Hum8Ve9Ii;<{t2EEa9S%V8$b=O`l~VYmZ$>Zw+BS?v3oP`@ps5$w04&)IC*y9xtm;{H5ScwMQxFQ(2E0^i!!$AzwPy*JarwTC#XEm6!72AmjrklVK*OO5b(Z{90)hHoTxU=3#IORSnzC<u9gAQRSYK_8C=Y1gl8yc%&5Y9LC$(t5VFpB{Vr4Gf5tUY%5QID#qqN#Hd_fEN{9cswI@*CnN!#y`r~0&7~8Nhoz{U`@4lpNN&}=zig)CDX73<ps4kyY#Tcc%N&5+=#<TPIPou-dzN)kyD(}cxdTusiHJ!{IB!_8Bqyr28Pv?%mhq<d$2Kd(QPfJGqc{q?bUTYCs&OSkZId4k-d;XjPj@@Z?r+Q+*6NC_e2H~JU!RWis7aQ<N5!d3m$8E6^sJde2CDY(S<8629frau<Zf7=}I%F84^@5j|t>?4xitE<D?|W0v3DcJkU90%7H7{)JPJ1|=ZyO^{$->b6-KLnD4L5={2gMAlZ6pA!Vus7nATtv|fKyIqS<$wSLybc>h()9}fr%>xGYrB{pBQT%28+RhL1PAg%X|6lbKoZH_V_WlDQ*`Ra?ri-ew&YwVF7dk+}4&+(cG1_k<eP>vo)iClj<?T#E4jSD=pMOpXoffa9Z=nd#9K<!GpgQ;qytrFGCJP{i{vo2(u<fYSlw;|5)guX6;BN@&WHcNRgZ#I8Za0m+slEC)Uu%t5kq~Neu}B`!CBRI~!=r(%yCk{A1~+5;#ubi8c~*Vk<box334Fwty10SG=Wg)J*c2)bz5H$Z;+x^VF$1db~58Nnsg_oP+c@Z06sY%Gc*|lU>KPh8s0v2YnT<Yp_J@0&!870HgJD<v5|HNR>%5KXc2*bJb}POy($b`GHS$pRTEuQaSxnCn0i*N=%nZVD%(Z<<>Ib-hV%dH&xLF1&1?)&z&@>O0zg6AQ~xj4nDm-<2y?^I35iw(1S0{4+1;!V0{$zYAYevY04z0a7=A`GfwFBu#RqePy=0;oJ0-+a%Ys?#ANj2QGy9r7E)>LB1N8}$M!i#DkmIX<Gg<Xebq|Ond$pST*(C1c7JC;xN?f&dt&ff85Hms4++rbP_gy`)Y*Tjw6=%U@V##EbO-Q;j_?+#;(?eWyLn>}sUo%U3(g4r6_y*J@noA-bYoe9S(i)q&*nYm`3rM<wgIp#g=J%SXX>?`8;RR9*c2JKau4*OIq!Kdf)a@G{{^2R&Wa3u)x$PwaXw@XIO^~lDuqVah4L#S<gz@Kz5m%A793Q}xXeBHG%7mvU8J-_S~O1LoUsnezso>0ZfELlcU6H9QeJdK5jTQ>YMW9m?e&0%k9LJR%JY?lz6utDCzW5BsBTqGEM)u;c+nEhFK6k!)cL!8r&nssSNfjdicvW4ug}GPPSjHRtoT|#DFUnrh#POsdOU$%7$5o>t$`>*GEa|9R~?9?$YAM>*4~)i9T8G_LGj#x2K3XEchXE7AN2;g2R}c%;F<XkR4UELI1ooK8@z3)A`HHQyi`y*9s<paD{wWM=npt@r%61PeH*K3;yn-*Z&6t4<Fm=~h>W?e_&i>~?}hv%<P2D$ThN<@X(hCiy$NP_Zj#->K7AE>zd(PSb>#Naa@%q^FqdUjSV?SG;zhf2SMkwmZblJfbtdvp*kd3UBAWKIFJ7OIuXjTU_mKjKL@W7B74);^+pg3Z&2OR!RFZ4&;y)s&q`gMmbNu1&=wfA?Lgk*l(vMHLjRN-OSA4+>1cpA}U5y6Q>g>7D>}YU{EqmPbhS^g`CkVe<6p6j~ri>>y*o{pM3HpH$%IyMt=-`AnZD8$YNJ`!)?4Yp@eQoFJ-NJ_hQs2=g(>ZUOX~ZfNu29qV8&WlE^aX&F5HzA*GChMW=tuQEo$#<0R+T)km2Qbd*-$HH<+N!DCy{Q)e8n)c^t@YM?M?95+{80K#}r)QCWY4u*{q9Qe-Kg;DohYNO;*EaG4M=8ce1TEkAC?eREX&ysf*3WztNXx@05r9E8>UvcJ^tOWoPVaabm6lxiLpp#Zi>pepfFhtB|0osR_<qdpmH70oOYG)Fe>sS5!#gdK9Rz&RJzE5X2uUN2$7NiSHAsW86?BEGQo-2z6}@-tA`|P)JA^cvy00X7BABoL~5&r4C{hw2k4g%hOgdIELfNGiCX3Z1V+g!=Ygs+H^=S&w=(lKkxM|QrW@&Olit7+mFIJNo5m5?MChxmawcIm&$~Nn;Ye4W^CXu(f6p5Erl}Hf?^AMsPi8-GS8C*w+Kd`Pk!nC4INV%w)^<Sy21SBOn#IWxmNijmG5gnRvNxJ!iVF+%V5dqxhbt5Fmj7usK=aXsZcM&oxI_S?a1(Qi=BjDLY^28;3k`k%!J5mLBBj$`A3D8+KGLf8Z>FDUiu=Y+zE6P@Zfv!%Yk|kE9!NB9FD(8XXu_Wgz&CBF?hCz)e}$O70YGaf9HS~(IqC+k6Ad9U1sGlYHac6h-0PQKlUW9&|H{~flk<c?84Z0K{;HrznXFJR&+OmS<Z{+0;2Th>{n;7fX2(0O^hAwl7%!XYql<7X1L0ceH#8WWlNL{$5J$lc^KBErL!uVY|-@Fcz7RXA}X0V66wEbimS31P*nOF^j*?69$l*8=fl>k0;eX}y!M#Gh(t`1kt&;2HRaVGNE-o2jUL<-o1xG-J-1}nkIhgeN1j-+?Y1E%EH87KriwC}Zj7uao-Eq^WbFx_nlFNt-HqChF;;KD2Cn95nwTEgA1KG*UD8|%4-XJr+f$4Ma!rQ%_{iz|4QfnB2=SJvf`J2W325_|+c7;k0yf}?R1?W+M_4@4xaO$3?{Rv)!wP&{!4F*I*-fW)V`BOw2CK}X*%m@s)v+^Vy@r8%E0y>|GRh^_B{N_n414d!*%)Bhki6-C_SeCjwtmNDbkduELyfaYb{=*UyL6v=Y)~z#@u-Vl9y$7nw|Nhfpe}6~YlLj!xo+lUzn|4y+?=Hij^YYmLz@aqR$B0nV4&z$DCjj2R6P~C#jd~+Abr7*LrOSpKisNrklNV8wrgfdVZA5ztfsn~-a1-q8cy0R3Z(fw>ZiX(MG5}?RP}Lwn|b793r7|6a5P;+qQjR7@YZDA>V^GsKY$a?)1m}eM|hZ{1hfS~-kwJs6NI5V$wqROB<k7|B09nFW_BBiDGXgE`31j{RK8P>fBI@Ua1dTk`6r!MzBDVxw6Z%TPQ8)PXmac_^1OE#3}G2<id=%rEyP5uS*fnVmAEAF5p}`A9zS?E|1@QFfNl@T#c@K`O6_`8OnFJJnT}x=woj;tWh~4zphj5@U<Z)0=4>7!$Hf-evYFG@SU|EK$EKlc?4BuGfGy)Wd91Ryre}zTPKVUoLmFZnSPC%eQ{8YSW8LY%Hn+9d54nr?l*DnN;9L(<^enpRvg^L0=68SYYQrAl_N==Y6NbzrNxJkfgw2I<X`JB}w);<Uw`LkUx*7<HNw)TNlQ2P1o_stKU&)pGE3u#GI2TftgU=LtHR7EU#1vaMnG8*pYxMq?K9U3r34J9?wL5CGd{S&R$m6zEZBFRJ0D8Q!^lWA;yci7=P?(=ko)-#23g;JV=9+pCiP<atr>20{yFBr}{+63rb%g<Yq<ja9fy9+d{XZ+BBwK5?ef#7IU4|fYNwD&I15=K+X->@gDv-va^<u1A)ES^bsI51{SCtdyH_$>XI>g_iEu3Q*z%5s|E5reTqM;6(oR<P*4&ire5Y+~R`h@%wan%V~7o{vunVMilo}RAm6~{8nH+Z(SB7;ZGr+5iYhI*XSN29t~9U|0Hw`IjiTxz!adM7p{ON6+K_&$m*xQM%qSV9aTnAmWz`Jws3s%3NLS4r|JtFMKK03sy=cnNdzwBs((+Hj+I3e{52#rL%ez&pZxrQB|M@Xl>|6`{KXxnhUCqY6oZ-zdn9P@noCCx^nC7~^tYtuFOcEtF0zp(G?s-PF@CV~+p^?-usR(ZC!CaT#!)J^8{yGYQ+gH~ceL*ybr}%3L3(Y~N(=h>hzo^VT&%iE82n6L#}T&y1*`g1f&c_opGt7J)qsHt?-jyM!K4EoBc%K#cr~VH~!HWeqe1xn+-+$0skywfKo63y^N;1;YaP6m^IiztYZ+-y)T7cX&lGE#VKBwYw%rX|94~T^x;+mOs5f(;S^JLH76vG^HD&`ux{;pavJ)4R<E)v})~hADNJykDd)Tor*vkQs|L?Dmmu+R)a6~>u3Q*M6&>-3RuWVY&Yjp=+s+kw2uh*|5<Tbiz&-4lA`lM*%YBbhbbRF%kIB5Gox{Yo-kUlkyyi0_mY1ivRT$VHPPGyW=8b%eSD=RtV@~C?6pfG-$~=u8>mc9{%CZzX3%e<8>6vqA!D?aOQAK;rycm6zItVjeFt55brMuHH5VbkPi-x}CP+pcSBA&!I9zO@ZILQ+D-Mi20%ta-jbKiMmfaqSEs4l%KYvi8G!2LQ_NeA6*eYHg|4_#wS(}MfE>4~>yB1DOx)M~{`^1LoQAYrEU^Z1kfb~-n_-`~@6;!7qPNzr&iEFyxp*D+>$0_AWu1jzZTV1=3>q-@>x-tZ4ZZ-^R@oWZ!U+&3}&7g+_(|^;y!|Xoa+99#In8=*1JPWTZ;sjU2_f2Kbi|gWD?;`|Zce*x024#Xfk=6bRnH|G)hHk*8j8k-n($1T5k~C37@1U`?ZSQ^cPGl7;1sU=hoK+ZQ3O8k>sJ++gl+PlZG>x4BxRSX-SE{#8EsPW2r*k;4p6}_7<@T4KT?anfQ~X>|$!QaauK8K-87&w1QUpjHW+}ajMD4gDnK4#a?_Og;#=L}JXta)N)i3-{p0q{QFRs?FIY$m<??n4t^b89HHz$HblkvAS#oB09a9ew@_&YI7S*=nU%26#wa`NPkio-brbd$d<KmgrvKfEgUgbfO_5^~S>OKqbs?4cq^4Oj(H>g^}e_JMF#<h|_F7r3gu049{j*i(v{(LQ0&f38!*W|Z={KS1|x$QBUAtvLc6s{$F^D8X4+fIFpBu7sgh81l^!467Ux4AjIV>BuN(5=&_fhjL6Z5+LGE6#e|5uGh0pYb#OP9sW{6(g5Oz{)gmkKU3*L>ftzd0f?<8Wu^*-;HvrfXnAcT{O>IsiQ_6JoolX_opp18o`M|2@=2tpN6lV~H1*ZQ!}GBNF!hyIp_UC{#V-I^2k>1i=zmmL<QiBpcGc?Q3<!)KUbyDpUs)w4bFH#>$bN>Yu?L+_5N!hPbg+UZXtRB{=p08gfHxc@f9M;?L+0#>k~)3ny?=votPAze|AU@monNPg&^j6K50G_pTPf|Vv$YU&kQg);{xe?1z;8ZGppH&o`J<IhlBXB2r~Qulp?#Vm9Kb5eZRKR&gJH-6a_$+o;U6;g9-I|4rxW`W+(OCV*up?GfckRVQ{hk@Tdp8oN`OPrrh!N@y|zkEjbiW#X9xuW;&a%p5?0uR3Ifg?rP|{Kt{@)et0BGp(Y7n|wCid}3T4}nHZ1$IBdw?@99~b-o;;f%&+=b4eb;dfyqctxD*5IC6&5nb3wg?bO4ao@wYWEmVIlUH%I6jSgD3-`jE88z;O)e)L-0{){P?R_S!W0f`>uvdI;qc};3Zi0t8ohPw|d>1VKeK}SpW-WZZ4&wlwXXwE6o=9o(hG7rnF<<s?4Y<ujyv`_$oW!7S?nPQwL`AiSt;;-{-h#7}u1Ze){`kt2PS?j}F_wut{fhR_nTYFNybMy!%a9Z)N-E8;1ibA4fB-k>pox;U+MmitAI*y7ucs!f5Nm!o7X<81fi}BjMzO&jET9kbiRWWMpZ3On5k1p(eB5`IG?+JhSEdR&?`)!Z>;qHKVnu$c)X;mA@EYCBzc~`axgbNK<w<Rs^!*%`od2hMMt6ZP_roa&l}<oGv1TGpAbZ<z+-t-Iq8_C3f;jaOT~5<Rl;TFsJj3e3>J()2_;7ze|TuR<N{bD8Y(itS*Or1ILL={IOKGI#?9V%eJEzeNG^!tj5`>31evNUgnlfQS(vMg8G7?)X$nQi`kxA)sY+HQ>yJ9^cqGA%@(sC*~lPsH~CEhLwJflB*3dRtm#P<ZRlm3dJFZ>l2`p)W2U&D_8(qFyX6wv(DGvxG2@3QdIX<)$jjSK9Ty>Dn*cqvr}-=N0Ztmnl=^m`_2*H2OD>ebNq3NqDJBd~Vk}q`*QmAPH<Tk^y|rGipnP8mRD&E1&w5IiI+qAF#EE?^+ec5(O3NpE8LAyEuowP4oJ;qh&kdrDVmLxBK;;7`kV=LWDzPFODP=%<3<1tdhN>qD$SPa9`udqI-mxGTtQg1X5QBfk35sHsaIsDtf;GA$Tf;i~c{=@L5V3D<yJM9N3`JBZlN2{HMgigjVGr>Nu^<J7g*#|hHB*H9GSn~xu}-dsa|bcEI<(Sdw4pbptndQj9)#87KtpTW_y!~-57PlKvif`{#kOg~)_-<g#)Gzvo~Kn7M_EDGuIW&gTgZ{){Dy}JD@CVjMin?4^MO+(ZYa5l2(%l~zKd~tR<?UDkJQ|ZyzHj*8zN@i<EKaeiwOOI_q@!Oo9lGE$sLJ>a<0~8Uc4~F3g5z*ZpWc2{R)T_4srWI_nklc#T8l6GNiLxtNL^X1ldoo$Yv#wgXCu)!7Qv#lf@If_FSI3RJhs-K-!lbyX6suR7`7WG^KNhh7NS_)6NNm6&lQ~y$n37%UD<mtj7I4Z6ZP$YZy_hM_f=14r}X?BBX&hs_j`_I-0t<8IN-0nP8LA*W1(XBpml1(l>~ZE%FfoLqlV|0;M&Zv3{Y!ps$zFd;=j1sAb*xFb{gSWeuj%GQRv?)xe4A9dNWIWkQ5=1h>{D0stO+sI0^d^?WZ-?4~+K#l3^5rc$(#%X;Z$JpnR>7dU8#zHL-Nza(~bzCjjvpPi;}JpeEUx3x4uh=|vK>WiXl{bn=fe$LF_*nwQUl}YhJn$MWSt^&QTNLoqnU3?)f=q5gPpNI)5lA}jOkq#;oD+Rh&#Q2yxcC&W`I`C86^448eN=Vua)GKmU_#CrJ4uS%uCFENDcgO~R!2k{xO%me}04DxOkvlGjGjN)cQ39Dixi#U<LPizUae&8VJ_OmA*NrOJ!g;bR7{g7@dk`=rH~XeMLESo%fIVp9#Nr@6SR2Xtp~aVS@)b3=6q(c&42;q_$or{edKH7!L@*38v^t*0IXo_i>YRW4bu~c6=)Pr(udIO?sFDnh935BW@4bh-ZWo_@#-MWpZo?j*J!Ja>3y{e$mMEJ^OJIdIy*!|4@+Yc06Th`=rBa%WqM{T^)7Q5c5-~wfKbZ>oEv>}E!Quh_0sEQqN14o1bPq85mo1r%7+l-F5MD9w*yP12nrd?KXqW$S)0zaubV-lejjABN=Z>UagU#$dPG^XL4f&oGGpEhD{Z-Qa8UTP0=ZW95eZ4jIGpeMak(S{mY?Uco+Y}vzys`?60`tz%%c3`jSc=UdVm<_#yn*gDwSju0VtY02CH7oC?+v_vPf=r%P_9}{f*Y%(tgOW)_+YhgqLc=Bq1f|si<F#`9oLWstwlGLtQyVt|JIQfFviKnm4s?VQ!!#8k*SHuh=?}~=3Nr+HoVa=HNNlWC6u6~kt+F&v62D%RFe0O!ezx=A!y%dK!Cal4CKF1-aRqjIS0XWG7Jp5)<wOn-hXFeDx`5G+wqF^BZ6_K-aoXH%Lyhy8kqWz@F>K8M=ly|^;h2{K_*PL-!!ts4hgWQ#8yJ<G1`gk{kwocD)anv6Z?wrS@TEfTRpWhO47Tn!-=Re`n5RY<&h8H*FyGd0M0{fF5^pZjutqUJQ0H(uGg%cTWMa6Vk(#l2c1X6Zza*RfrdWOEf66#=eg_>(G*!lmv-eXvnUOd+LFUd)j!~OpX@8(EF9n!BQ*O99ugH1A{i#d2x@5!yoFVoK5^F>Q|KvyN~DNj=jAR5|B(b&7MOVheWpICM=J5~_%7Myic61!=X3+CM8bF9cQ2u<uW_Y|mN{WW5`U01SBwZ-m~$bnC*PE&aah0*eD-^LNiin5>YUUy>rrq>h2Y4>fYYTb7%#HvHA<XOS#aXXK`zinJ5%rCC4(H#gPR|M|C?rMtwol-imJ_ub<id95W<Xn81g053k%xr_V3*L4xnC(!jfiG#||#pdOvv5Mx(AX`Q+4AQ}%4dp~96?WXm{Qj5>DFMX*lZAy7U(h0a5*gwYKI_cU4KbHNf=C|zQ|J!7{V1SpYMF3=I+Gu^C1>hCWdZXh~OT4G`_O?rw4VEyjXUP?8p1jD_DC3TUT_-0l><z)xtPkJ3`B_L3k!W(vgvZN%jYvzNF!2I8LzlCbgt<xLjSO~#kQfoVp+^Q5uNNu&t05Uj+3gx3vMSGoUst_B1E?)^P-{0Z+Hdi@}Kqdf)wY|BfvPwXP#n8U}W&kms8-|*^q_B$~@8=(ozuSRsWQvijuGmTZ`t=8{Jx=qR5#UF<=X8J$Pw|>*)cA>ZFbH?LL|$;r`;d>#w>h8?caGBVVZUfxBi79dE_SWag0kG|8RX-;Tz76|eJC}ZEf(c+gURFW;7U&`#9^60>0p;NGn%KCRn|suR=EF&nsCjs_vi;m5N@`DKTp1543X=7y@lD}Bh_;4ce$bLlNa!^MD;}9?1OJLcZ6J|cEBZi#df&`Hq_hDM0y%WAN(lmYy8+$$aCme8iKMrku@_h!sWQ^@<KH9#npQ68~EssumqS~cJs-kQS>mto=1rh;Z-w;omE>RJcQi?;W$c3>pAsK^rgRo6Q4!+5@UBhYxN4$V`|r(A#gI$E{TQBeOQI7mwA|aBb=D0ZBL)HCh!0hOfKqJ`k2*Wdq{;1*h89x*$Bsl*(%o+bIWbh6X67yzB~ToiCm76j2V`3>|!^fv|#l@CyNRVJWrl+caBDFUbwGoJ+zkpd(X^gD0Q$kH>&FLl23qfbH*>lv*;{<5XL%x%Dg?4nWf$dOBurAfU$SGy^B`Ryvk3;8|`E$cZ}Vn1$-=^K$c&#T16EVxV>(P9hh4jGwX;*r~mbrM!qW!!>v3BRo!oTf-uUVlVt`&6PrfScEv7<Ud#_x0Be^4A-O7|Yy9h43VzjPFnxbni1@uV3cM-;38&DB)pR>i>FtHxdhVT`G^r!Hv{=z_#(6N3c(nnM)?$xS@{>JZ^AXCgi#g=A1v%PNAKFI8qt4=$@-X6r?$Z9U0B1$T)p<q!{RCq-P$n}{%snyUbCEBuQ)ubbRk*VcqG{W4cz`PIf?lZ(Cy8x}2wVAp?z4*kGWzVm*tkZAM-i{<O=XU?IK-sMm)l}~09I!VQ}aBL5F6NvGbe;Pxb|MIxezokd*!t}J2%h-BaevTn4n^?wX8RlU*qzU7p}qvF~o45py%y9{-Av`(IV?C%CQ>92t(Dz8Rx)j^yso_`IHq^4+Z4ot)RCni0LOi!;@ROm*sn->Q5V5XCp-G!crfcgU?bw*W#q@8bHD))s4W#g0<OWe{Dsj0N|yb{7YEamD!606ICARxVpeyWj8+MlgbJPQP2q6eaHJ`D%Q|+qgkF?I_`LcEkG`Q(B!OouL;mlD?a^|&O+>Jx#N+9$Aq1-!DbC&`_t60XkMxQe~?B5vD|ZLOG<=Zx$Jc6k}{kIU!L#2^fM!bb4gMEfyF%c)Ugx7iZoMys6yf#$sM6-&B0I}eq!#!AkC;~OCTpJDgh9*NVxRWzTy&91g!Ktqp*7m{7#=q_u2h^KOqikCS&w+DFU0em7Q!4B-DG{z|$bDCVJo^Ddjd<?00baR*qbv%eQXSrHUq<BIB5OX(gz}|Nc;PkeOc2S%eAZ31<0OICY3~!2vez(pg@4e#rTLTmlYKqHvzJQ8;6=XAfwu>M<=0UP9uix?@QX5Ql`&E8IRQPx5%}sV3i|Abj7bO|LL(RG2vvWZu**pZrP)%ZI+s*=B~To83ja%4SL$TlRVlgxDnpOB^GfeJ=Zt0D?fZj?hK4A0#1YEk0UH49FwZdhng#2g1&t1rXM=Y?2DlZhghyN;FQuPpjWQs+X@dr(R(gMVAcOr{m1ayuwobb-*Qq=U@0ffmNk^7lR`Q2eK~@mh)kB#C`O`({4qn|DE^`7yL$eRcc;mtK&n<Qn(oZH355Di7uLq^P&^Oc_C7<Xm=bAxDxN4;}e3QhmO({4~A)?#}B6;xaOh1@+i{B6HL`YB{dG{5f87AJUA>ZZjjU`{>U+Le*I@Sk!5@Ml5KTdLAL*YKAM2z`k+u(!vAFf4#Fl?UrT#zw4J;ED&{a)Rk2y!%I^Y}j%(+|NXnmh+uuqkWwB{6neGuRYYtao`%k~cg=j9&1biz=jPMWhn~t=%8j{W)@a58BDjM!shV~H->_B<#%;3qa8vNCf?Y50xukT1*RJDIQE+~MHXLJK_HmXQ_xUq8kp?Kc;k{|Q6pTOgGu^45Aqc9BS3~CsNY(R?I1!k{o#SojQP0|Ljr4zYHnjgPE=!A=L#N+zqp!83Hk?`>;G;3WnAM>(-;!_+<Ub5zN?T~!cnGn43euH(bNm?&EYzIm>&5E&k6b+7{lav{2H&P0#oSR}tR$53Ni*QV4K!ul1zVJ(jWa>J&XA+Hlp9y~-zmysf;mQ~VSS02pQmC?ck$f?@T7kSkff%Py0Ap1SsD-*7^Srvl^+3Q!pIb!M?fLIr(OzA=Jq|RBvxNWZ^B$^|?iamZIoS4dT}9wa4y8z_BXYtxq|MD4Bp^y8Up!?y)(<G$xoj}%X_O1Q4ca5179A>&l`7irO6m%x=c<zXZJsH7vVULKC{<?+o=U;R7T;+PvmvlJYsdu>i+Wc<3aY2k7am<)8-M9E)PZ0>T$jTOxV&uFHL%04dV+~$zw{>WuGUTkj&|u0MTjNpdX-M;+Yg2n48!951#)~YleZ4Xn{$zvHpGr7Xatg!vJ@gKypx^4d#q4WMa8VXB%atrf01&M=zv#=YFJS$m9e(}zV5M{u9EMy#Iw$$o(3Z6OLrpcJxd2hWHFl9BQf%Hbslt|#J13INt2jVVSoD-00000wzpW6;?h~F00Fha0j9DB7{XpavBYQl0ssI200dcD")))
diff --git a/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_seed0.log b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_seed0.log
new file mode 100644
index 0000000000..86795d0d2f
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_seed0.log
@@ -0,0 +1,829 @@
+W0424 21:59:37.856000 197371 torch/distributed/run.py:803] 
+W0424 21:59:37.856000 197371 torch/distributed/run.py:803] *****************************************
+W0424 21:59:37.856000 197371 torch/distributed/run.py:803] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+W0424 21:59:37.856000 197371 torch/distributed/run.py:803] *****************************************
+Hyperparameters:
+  adam_eps: 1e-08
+  adam_wd: 0.02
+  artifact_dir: 
+  attn_clip_sigmas: 13.0
+  attn_out_gate_enabled: False
+  attn_out_gate_src: proj
+  beta1: 0.9
+  beta2: 0.95
+  caseops_enabled: True
+  compressor: brotli
+  data_dir: ./data
+  datasets_dir: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved
+  distributed: True
+  ema_decay: 0.9965
+  embed_bits: 7
+  embed_clip_sigmas: 15.0
+  embed_lr: 0.6
+  embed_wd: 0.085
+  enable_looping_at: 0.35
+  eval_seq_len: 2048
+  eval_stride: 64
+  fused_ce_enabled: True
+  gate_window: 12
+  gated_attn_enabled: False
+  gated_attn_init_std: 0.01
+  gated_attn_quant_gate: True
+  global_ttt_batch_seqs: 32
+  global_ttt_chunk_tokens: 32768
+  global_ttt_epochs: 1
+  global_ttt_grad_clip: 1.0
+  global_ttt_lr: 0.001
+  global_ttt_momentum: 0.9
+  global_ttt_respect_doc_boundaries: True
+  global_ttt_warmup_chunks: 0
+  global_ttt_warmup_start_lr: 0.0
+  gptq_calibration_batches: 16
+  gptq_reserve_seconds: 0.5
+  grad_accum_steps: 1
+  grad_clip_norm: 0.3
+  is_main_process: True
+  iterations: 20000
+  ln_scale: True
+  local_rank: 0
+  logfile: logs/78763526-9b71-43eb-8728-ecf3d481ae6e.txt
+  logit_softcap: 30.0
+  loop_end: 5
+  loop_start: 3
+  lqer_asym_enabled: True
+  lqer_asym_group: 64
+  lqer_enabled: True
+  lqer_factor_bits: 4
+  lqer_rank: 4
+  lqer_top_k: 3
+  matrix_bits: 6
+  matrix_clip_sigmas: 12.85
+  matrix_lr: 0.026
+  max_wallclock_seconds: 600.0
+  min_lr: 0.1
+  mlp_clip_sigmas: 12.0
+  mlp_mult: 4.0
+  model_dim: 512
+  model_path: final_model.pt
+  muon_backend_steps: 5
+  muon_momentum: 0.97
+  muon_momentum_warmup_start: 0.92
+  muon_momentum_warmup_steps: 1500
+  muon_row_normalize: True
+  muon_wd: 0.095
+  num_heads: 8
+  num_kv_heads: 4
+  num_layers: 11
+  num_loops: 2
+  parallel_final_lane: mean
+  parallel_start_layer: 8
+  phased_ttt_num_phases: 3
+  phased_ttt_prefix_docs: 2000
+  qk_gain_init: 5.0
+  quantized_model_path: final_model.int6.ptz
+  rank: 0
+  rope_base: 10000.0
+  rope_dims: 16
+  rope_train_seq_len: 2048
+  rope_yarn: False
+  run_id: 78763526-9b71-43eb-8728-ecf3d481ae6e
+  scalar_lr: 0.02
+  seed: 0
+  skip_gates_enabled: True
+  smear_gate_enabled: True
+  sparse_attn_gate_enabled: True
+  sparse_attn_gate_init_std: 0.0
+  sparse_attn_gate_scale: 1.0
+  tie_embeddings: True
+  tied_embed_init_std: 0.005
+  tied_embed_lr: 0.03
+  tokenizer_path: ./data/datasets/fineweb10B_sp8192_caseops/datasets/tokenizers/fineweb_8192_bpe_lossless_caps_caseops_v1_reserved.model
+  train_batch_tokens: 786432
+  train_files: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/fineweb_train_*.bin
+  train_log_every: 500
+  train_seq_len: 2048
+  ttt_batch_size: 64
+  ttt_beta1: 0.0
+  ttt_beta2: 0.999
+  ttt_chunk_size: 48
+  ttt_enabled: True
+  ttt_eval_batches: 
+  ttt_eval_seq_len: 2048
+  ttt_grad_steps: 1
+  ttt_k_lora: True
+  ttt_lora_lr: 0.0001
+  ttt_lora_rank: 96
+  ttt_mlp_lora: True
+  ttt_o_lora: True
+  ttt_optimizer: adam
+  ttt_weight_decay: 1.0
+  val_batch_tokens: 524288
+  val_bytes_files: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/fineweb_val_bytes_*.bin
+  val_doc_fraction: 1.0
+  val_files: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/fineweb_val_*.bin
+  val_loss_every: 0
+  vocab_size: 8192
+  warmdown_frac: 0.75
+  warmup_steps: 20
+  world_size: 8
+  xsa_last_n: 11
+train_shards: 80
+val_tokens: 47851520
+model_params:35945671
+gptq:reserving 0s, effective=599500ms
+warmup_cu_buckets:64,128,192,256 iters_each:3
+warmup_step: 1/20
+warmup_step: 2/20
+warmup_step: 3/20
+warmup_step: 4/20
+warmup_step: 5/20
+warmup_step: 6/20
+warmup_step: 10/20
+warmup_step: 20/20
+loop_warmup:enabled encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+loop_warmup_step: 1/20
+loop_warmup_step: 2/20
+loop_warmup_step: 3/20
+loop_warmup_step: 4/20
+loop_warmup_step: 5/20
+loop_warmup_step: 6/20
+loop_warmup_step: 10/20
+loop_warmup_step: 20/20
+1/20000 train_loss: 9.0105 train_time: 0.0m tok/s: 12032990
+2/20000 train_loss: 12.9603 train_time: 0.0m tok/s: 7472224
+3/20000 train_loss: 10.2974 train_time: 0.0m tok/s: 7840319
+4/20000 train_loss: 8.7999 train_time: 0.0m tok/s: 8006046
+5/20000 train_loss: 7.9927 train_time: 0.0m tok/s: 8105039
+500/20000 train_loss: 2.5695 train_time: 0.8m tok/s: 8223678
+1000/20000 train_loss: 2.8077 train_time: 1.6m tok/s: 8190970
+1500/20000 train_loss: 2.6349 train_time: 2.4m tok/s: 8177293
+2000/20000 train_loss: 2.6663 train_time: 3.2m tok/s: 8172834
+layer_loop:enabled step:2179 frac:0.350 encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+2500/20000 train_loss: 2.5514 train_time: 4.3m tok/s: 7709345
+3000/20000 train_loss: 2.5628 train_time: 5.4m tok/s: 7247177
+3500/20000 train_loss: 2.5703 train_time: 6.6m tok/s: 6949988
+4000/20000 train_loss: 2.4122 train_time: 7.8m tok/s: 6728270
+4500/20000 train_loss: 2.2842 train_time: 9.0m tok/s: 6578137
+4920/20000 val_loss: 2.3548 val_bpb: 1.0760
+stopping_early: wallclock_cap train_time: 599541ms step: 4920/20000
+peak memory allocated: 41709 MiB reserved: 47026 MiB
+ema:applying EMA weights
+diagnostic pre-quantization post-ema val_loss:2.33209313 val_bpb:1.06560636 eval_time:7276ms
+Serialized model: 135417533 bytes
+Code size (uncompressed): 151554 bytes
+Code size (compressed): 31220 bytes
+GPTQ:collecting Hessians from calibration data...
+GPTQ:collected 67 Hessians in 3.5s
+Quantized weights:
+  gate_int8_row: blocks.attn.attn_gate_w
+  gptq (int6): blocks.attn.c_k.weight, blocks.attn.c_q.weight, blocks.attn.c_v.weight, blocks.attn.proj.weight, blocks.mlp.fc.weight, blocks.mlp.proj.weight
+  gptq (int6)+lqer_asym: blocks.mlp.fc.weight
+  gptq (int7)+lqer_asym: tok_emb.weight
+  passthrough (float16): blocks.attn.q_gain, blocks.attn_scale, blocks.mlp_scale, blocks.resid_mix, parallel_post_lambdas, parallel_resid_lambdas, skip_gates, skip_weights, smear_gate.weight, smear_lambda
+Serialized model quantized+brotli: 15916577 bytes
+Total submission size quantized+brotli: 15947797 bytes
+diagnostic quantized val_loss:2.35173803 val_bpb:1.07458272 eval_time:11151ms
+ttt_lora:warming up compile (random tokens, no val data)
+ttt_lora:compile warmup done (100.2s)
+
+beginning TTT eval timer
+ttt_phased: total_docs:50000 prefix_docs:2000 suffix_docs:48000 num_phases:3 boundaries:[666, 1333, 2000]
+ttp: b782/782 bl:2.1456 bb:1.0160 rl:2.1456 rb:1.0160 dl:30339-97114 gd:0
+ttpp: phase:1/3 pd:1104 gd:666 t:179.9s
+tttg: c1/111 lr:0.001000 t:0.4s
+tttg: c2/111 lr:0.001000 t:0.4s
+tttg: c3/111 lr:0.000999 t:0.6s
+tttg: c4/111 lr:0.000998 t:0.6s
+tttg: c5/111 lr:0.000997 t:0.7s
+tttg: c6/111 lr:0.000995 t:0.8s
+tttg: c7/111 lr:0.000993 t:0.9s
+tttg: c8/111 lr:0.000990 t:1.0s
+tttg: c9/111 lr:0.000987 t:1.0s
+tttg: c10/111 lr:0.000984 t:1.1s
+tttg: c11/111 lr:0.000980 t:1.2s
+tttg: c12/111 lr:0.000976 t:1.3s
+tttg: c13/111 lr:0.000971 t:1.4s
+tttg: c14/111 lr:0.000966 t:1.5s
+tttg: c15/111 lr:0.000961 t:1.5s
+tttg: c16/111 lr:0.000955 t:1.6s
+tttg: c17/111 lr:0.000949 t:1.7s
+tttg: c18/111 lr:0.000942 t:1.8s
+tttg: c19/111 lr:0.000935 t:1.9s
+tttg: c20/111 lr:0.000928 t:1.9s
+tttg: c21/111 lr:0.000921 t:2.0s
+tttg: c22/111 lr:0.000913 t:2.1s
+tttg: c23/111 lr:0.000905 t:2.2s
+tttg: c24/111 lr:0.000896 t:2.3s
+tttg: c25/111 lr:0.000887 t:2.3s
+tttg: c26/111 lr:0.000878 t:2.4s
+tttg: c27/111 lr:0.000868 t:2.5s
+tttg: c28/111 lr:0.000859 t:2.6s
+tttg: c29/111 lr:0.000848 t:2.7s
+tttg: c30/111 lr:0.000838 t:2.8s
+tttg: c31/111 lr:0.000827 t:2.8s
+tttg: c32/111 lr:0.000817 t:2.9s
+tttg: c33/111 lr:0.000805 t:3.0s
+tttg: c34/111 lr:0.000794 t:3.1s
+tttg: c35/111 lr:0.000782 t:3.2s
+tttg: c36/111 lr:0.000770 t:3.3s
+tttg: c37/111 lr:0.000758 t:3.3s
+tttg: c38/111 lr:0.000746 t:3.4s
+tttg: c39/111 lr:0.000733 t:3.5s
+tttg: c40/111 lr:0.000721 t:3.6s
+tttg: c41/111 lr:0.000708 t:3.7s
+tttg: c42/111 lr:0.000695 t:3.7s
+tttg: c43/111 lr:0.000681 t:3.8s
+tttg: c44/111 lr:0.000668 t:3.9s
+tttg: c45/111 lr:0.000655 t:4.0s
+tttg: c46/111 lr:0.000641 t:4.1s
+tttg: c47/111 lr:0.000627 t:4.1s
+tttg: c48/111 lr:0.000613 t:4.2s
+tttg: c49/111 lr:0.000599 t:4.3s
+tttg: c50/111 lr:0.000585 t:4.4s
+tttg: c51/111 lr:0.000571 t:4.5s
+tttg: c52/111 lr:0.000557 t:4.5s
+tttg: c53/111 lr:0.000543 t:4.6s
+tttg: c54/111 lr:0.000529 t:4.7s
+tttg: c55/111 lr:0.000514 t:4.8s
+tttg: c56/111 lr:0.000500 t:4.9s
+tttg: c57/111 lr:0.000486 t:5.0s
+tttg: c58/111 lr:0.000471 t:5.0s
+tttg: c59/111 lr:0.000457 t:5.1s
+tttg: c60/111 lr:0.000443 t:5.2s
+tttg: c61/111 lr:0.000429 t:5.3s
+tttg: c62/111 lr:0.000415 t:5.4s
+tttg: c63/111 lr:0.000401 t:5.5s
+tttg: c64/111 lr:0.000387 t:5.5s
+tttg: c65/111 lr:0.000373 t:5.6s
+tttg: c66/111 lr:0.000359 t:5.7s
+tttg: c67/111 lr:0.000345 t:5.8s
+tttg: c68/111 lr:0.000332 t:5.9s
+tttg: c69/111 lr:0.000319 t:6.0s
+tttg: c70/111 lr:0.000305 t:6.0s
+tttg: c71/111 lr:0.000292 t:6.1s
+tttg: c72/111 lr:0.000279 t:6.2s
+tttg: c73/111 lr:0.000267 t:6.3s
+tttg: c74/111 lr:0.000254 t:6.4s
+tttg: c75/111 lr:0.000242 t:6.4s
+tttg: c76/111 lr:0.000230 t:6.5s
+tttg: c77/111 lr:0.000218 t:6.6s
+tttg: c78/111 lr:0.000206 t:6.7s
+tttg: c79/111 lr:0.000195 t:6.8s
+tttg: c80/111 lr:0.000183 t:6.9s
+tttg: c81/111 lr:0.000173 t:6.9s
+tttg: c82/111 lr:0.000162 t:7.0s
+tttg: c83/111 lr:0.000152 t:7.1s
+tttg: c84/111 lr:0.000141 t:7.2s
+tttg: c85/111 lr:0.000132 t:7.3s
+tttg: c86/111 lr:0.000122 t:7.3s
+tttg: c87/111 lr:0.000113 t:7.4s
+tttg: c88/111 lr:0.000104 t:7.5s
+tttg: c89/111 lr:0.000095 t:7.6s
+tttg: c90/111 lr:0.000087 t:7.7s
+tttg: c91/111 lr:0.000079 t:7.7s
+tttg: c92/111 lr:0.000072 t:7.8s
+tttg: c93/111 lr:0.000065 t:7.9s
+tttg: c94/111 lr:0.000058 t:8.0s
+tttg: c95/111 lr:0.000051 t:8.1s
+tttg: c96/111 lr:0.000045 t:8.2s
+tttg: c97/111 lr:0.000039 t:8.2s
+tttg: c98/111 lr:0.000034 t:8.3s
+tttg: c99/111 lr:0.000029 t:8.4s
+tttg: c100/111 lr:0.000024 t:8.5s
+tttg: c101/111 lr:0.000020 t:8.6s
+tttg: c102/111 lr:0.000016 t:8.6s
+tttg: c103/111 lr:0.000013 t:8.7s
+tttg: c104/111 lr:0.000010 t:8.8s
+tttg: c105/111 lr:0.000007 t:8.9s
+tttg: c106/111 lr:0.000005 t:9.0s
+tttg: c107/111 lr:0.000003 t:9.0s
+tttg: c108/111 lr:0.000002 t:9.1s
+tttg: c109/111 lr:0.000001 t:9.2s
+tttg: c110/111 lr:0.000000 t:9.3s
+ttpr: phase:1/3 t:191.3s
+ttp: b762/782 bl:2.3557 bb:1.0909 rl:2.1980 rb:1.0350 dl:4032-4142 gd:0
+ttpp: phase:2/3 pd:1808 gd:1333 t:265.6s
+tttg: c1/185 lr:0.001000 t:0.1s
+tttg: c2/185 lr:0.001000 t:0.2s
+tttg: c3/185 lr:0.001000 t:0.3s
+tttg: c4/185 lr:0.000999 t:0.3s
+tttg: c5/185 lr:0.000999 t:0.4s
+tttg: c6/185 lr:0.000998 t:0.5s
+tttg: c7/185 lr:0.000997 t:0.6s
+tttg: c8/185 lr:0.000996 t:0.7s
+tttg: c9/185 lr:0.000995 t:0.7s
+tttg: c10/185 lr:0.000994 t:0.8s
+tttg: c11/185 lr:0.000993 t:0.9s
+tttg: c12/185 lr:0.000991 t:1.0s
+tttg: c13/185 lr:0.000990 t:1.1s
+tttg: c14/185 lr:0.000988 t:1.2s
+tttg: c15/185 lr:0.000986 t:1.2s
+tttg: c16/185 lr:0.000984 t:1.3s
+tttg: c17/185 lr:0.000981 t:1.4s
+tttg: c18/185 lr:0.000979 t:1.5s
+tttg: c19/185 lr:0.000977 t:1.6s
+tttg: c20/185 lr:0.000974 t:1.6s
+tttg: c21/185 lr:0.000971 t:1.7s
+tttg: c22/185 lr:0.000968 t:1.8s
+tttg: c23/185 lr:0.000965 t:1.9s
+tttg: c24/185 lr:0.000962 t:2.0s
+tttg: c25/185 lr:0.000959 t:2.1s
+tttg: c26/185 lr:0.000955 t:2.1s
+tttg: c27/185 lr:0.000952 t:2.2s
+tttg: c28/185 lr:0.000948 t:2.3s
+tttg: c29/185 lr:0.000944 t:2.4s
+tttg: c30/185 lr:0.000940 t:2.5s
+tttg: c31/185 lr:0.000936 t:2.5s
+tttg: c32/185 lr:0.000932 t:2.6s
+tttg: c33/185 lr:0.000927 t:2.7s
+tttg: c34/185 lr:0.000923 t:2.8s
+tttg: c35/185 lr:0.000918 t:2.9s
+tttg: c36/185 lr:0.000913 t:2.9s
+tttg: c37/185 lr:0.000908 t:3.0s
+tttg: c38/185 lr:0.000904 t:3.1s
+tttg: c39/185 lr:0.000898 t:3.2s
+tttg: c40/185 lr:0.000893 t:3.3s
+tttg: c41/185 lr:0.000888 t:3.3s
+tttg: c42/185 lr:0.000882 t:3.4s
+tttg: c43/185 lr:0.000877 t:3.5s
+tttg: c44/185 lr:0.000871 t:3.6s
+tttg: c45/185 lr:0.000865 t:3.7s
+tttg: c46/185 lr:0.000860 t:3.8s
+tttg: c47/185 lr:0.000854 t:3.8s
+tttg: c48/185 lr:0.000847 t:3.9s
+tttg: c49/185 lr:0.000841 t:4.0s
+tttg: c50/185 lr:0.000835 t:4.1s
+tttg: c51/185 lr:0.000829 t:4.2s
+tttg: c52/185 lr:0.000822 t:4.2s
+tttg: c53/185 lr:0.000816 t:4.3s
+tttg: c54/185 lr:0.000809 t:4.4s
+tttg: c55/185 lr:0.000802 t:4.5s
+tttg: c56/185 lr:0.000795 t:4.6s
+tttg: c57/185 lr:0.000788 t:4.6s
+tttg: c58/185 lr:0.000781 t:4.7s
+tttg: c59/185 lr:0.000774 t:4.8s
+tttg: c60/185 lr:0.000767 t:4.9s
+tttg: c61/185 lr:0.000760 t:5.0s
+tttg: c62/185 lr:0.000752 t:5.1s
+tttg: c63/185 lr:0.000745 t:5.2s
+tttg: c64/185 lr:0.000738 t:5.2s
+tttg: c65/185 lr:0.000730 t:5.3s
+tttg: c66/185 lr:0.000722 t:5.4s
+tttg: c67/185 lr:0.000715 t:5.5s
+tttg: c68/185 lr:0.000707 t:5.6s
+tttg: c69/185 lr:0.000699 t:5.6s
+tttg: c70/185 lr:0.000691 t:5.7s
+tttg: c71/185 lr:0.000683 t:5.8s
+tttg: c72/185 lr:0.000675 t:5.9s
+tttg: c73/185 lr:0.000667 t:6.0s
+tttg: c74/185 lr:0.000659 t:6.0s
+tttg: c75/185 lr:0.000651 t:6.1s
+tttg: c76/185 lr:0.000643 t:6.2s
+tttg: c77/185 lr:0.000635 t:6.3s
+tttg: c78/185 lr:0.000627 t:6.4s
+tttg: c79/185 lr:0.000618 t:6.5s
+tttg: c80/185 lr:0.000610 t:6.5s
+tttg: c81/185 lr:0.000602 t:6.6s
+tttg: c82/185 lr:0.000593 t:6.7s
+tttg: c83/185 lr:0.000585 t:6.8s
+tttg: c84/185 lr:0.000577 t:6.9s
+tttg: c85/185 lr:0.000568 t:6.9s
+tttg: c86/185 lr:0.000560 t:7.0s
+tttg: c87/185 lr:0.000551 t:7.1s
+tttg: c88/185 lr:0.000543 t:7.2s
+tttg: c89/185 lr:0.000534 t:7.3s
+tttg: c90/185 lr:0.000526 t:7.4s
+tttg: c91/185 lr:0.000517 t:7.4s
+tttg: c92/185 lr:0.000509 t:7.5s
+tttg: c93/185 lr:0.000500 t:7.6s
+tttg: c94/185 lr:0.000491 t:7.7s
+tttg: c95/185 lr:0.000483 t:7.8s
+tttg: c96/185 lr:0.000474 t:7.9s
+tttg: c97/185 lr:0.000466 t:7.9s
+tttg: c98/185 lr:0.000457 t:8.0s
+tttg: c99/185 lr:0.000449 t:8.1s
+tttg: c100/185 lr:0.000440 t:8.2s
+tttg: c101/185 lr:0.000432 t:8.3s
+tttg: c102/185 lr:0.000423 t:8.4s
+tttg: c103/185 lr:0.000415 t:8.4s
+tttg: c104/185 lr:0.000407 t:8.5s
+tttg: c105/185 lr:0.000398 t:8.6s
+tttg: c106/185 lr:0.000390 t:8.7s
+tttg: c107/185 lr:0.000382 t:8.8s
+tttg: c108/185 lr:0.000373 t:8.9s
+tttg: c109/185 lr:0.000365 t:8.9s
+tttg: c110/185 lr:0.000357 t:9.0s
+tttg: c111/185 lr:0.000349 t:9.1s
+tttg: c112/185 lr:0.000341 t:9.2s
+tttg: c113/185 lr:0.000333 t:9.3s
+tttg: c114/185 lr:0.000325 t:9.4s
+tttg: c115/185 lr:0.000317 t:9.4s
+tttg: c116/185 lr:0.000309 t:9.5s
+tttg: c117/185 lr:0.000301 t:9.6s
+tttg: c118/185 lr:0.000293 t:9.7s
+tttg: c119/185 lr:0.000285 t:9.8s
+tttg: c120/185 lr:0.000278 t:9.8s
+tttg: c121/185 lr:0.000270 t:9.9s
+tttg: c122/185 lr:0.000262 t:10.0s
+tttg: c123/185 lr:0.000255 t:10.1s
+tttg: c124/185 lr:0.000248 t:10.2s
+tttg: c125/185 lr:0.000240 t:10.2s
+tttg: c126/185 lr:0.000233 t:10.3s
+tttg: c127/185 lr:0.000226 t:10.4s
+tttg: c128/185 lr:0.000219 t:10.5s
+tttg: c129/185 lr:0.000212 t:10.6s
+tttg: c130/185 lr:0.000205 t:10.7s
+tttg: c131/185 lr:0.000198 t:10.8s
+tttg: c132/185 lr:0.000191 t:10.8s
+tttg: c133/185 lr:0.000184 t:10.9s
+tttg: c134/185 lr:0.000178 t:11.0s
+tttg: c135/185 lr:0.000171 t:11.1s
+tttg: c136/185 lr:0.000165 t:11.2s
+tttg: c137/185 lr:0.000159 t:11.2s
+tttg: c138/185 lr:0.000153 t:11.3s
+tttg: c139/185 lr:0.000146 t:11.4s
+tttg: c140/185 lr:0.000140 t:11.5s
+tttg: c141/185 lr:0.000135 t:11.6s
+tttg: c142/185 lr:0.000129 t:11.7s
+tttg: c143/185 lr:0.000123 t:11.8s
+tttg: c144/185 lr:0.000118 t:11.8s
+tttg: c145/185 lr:0.000112 t:11.9s
+tttg: c146/185 lr:0.000107 t:12.0s
+tttg: c147/185 lr:0.000102 t:12.1s
+tttg: c148/185 lr:0.000096 t:12.2s
+tttg: c149/185 lr:0.000092 t:12.2s
+tttg: c150/185 lr:0.000087 t:12.3s
+tttg: c151/185 lr:0.000082 t:12.4s
+tttg: c152/185 lr:0.000077 t:12.5s
+tttg: c153/185 lr:0.000073 t:12.6s
+tttg: c154/185 lr:0.000068 t:12.6s
+tttg: c155/185 lr:0.000064 t:12.7s
+tttg: c156/185 lr:0.000060 t:12.8s
+tttg: c157/185 lr:0.000056 t:12.9s
+tttg: c158/185 lr:0.000052 t:13.0s
+tttg: c159/185 lr:0.000048 t:13.1s
+tttg: c160/185 lr:0.000045 t:13.1s
+tttg: c161/185 lr:0.000041 t:13.2s
+tttg: c162/185 lr:0.000038 t:13.3s
+tttg: c163/185 lr:0.000035 t:13.4s
+tttg: c164/185 lr:0.000032 t:13.5s
+tttg: c165/185 lr:0.000029 t:13.5s
+tttg: c166/185 lr:0.000026 t:13.6s
+tttg: c167/185 lr:0.000023 t:13.7s
+tttg: c168/185 lr:0.000021 t:13.8s
+tttg: c169/185 lr:0.000019 t:13.9s
+tttg: c170/185 lr:0.000016 t:13.9s
+tttg: c171/185 lr:0.000014 t:14.0s
+tttg: c172/185 lr:0.000012 t:14.1s
+tttg: c173/185 lr:0.000010 t:14.2s
+tttg: c174/185 lr:0.000009 t:14.3s
+tttg: c175/185 lr:0.000007 t:14.3s
+tttg: c176/185 lr:0.000006 t:14.4s
+tttg: c177/185 lr:0.000005 t:14.5s
+tttg: c178/185 lr:0.000004 t:14.6s
+tttg: c179/185 lr:0.000003 t:14.7s
+tttg: c180/185 lr:0.000002 t:14.7s
+tttg: c181/185 lr:0.000001 t:14.8s
+tttg: c182/185 lr:0.000001 t:14.9s
+tttg: c183/185 lr:0.000000 t:15.0s
+tttg: c184/185 lr:0.000000 t:15.1s
+ttpr: phase:2/3 t:282.7s
+ttp: b749/782 bl:2.3997 bb:1.0889 rl:2.2298 rb:1.0437 dl:3039-3089 gd:0
+ttpp: phase:3/3 pd:2448 gd:2000 t:300.0s
+tttg: c1/250 lr:0.001000 t:0.1s
+tttg: c2/250 lr:0.001000 t:0.2s
+tttg: c3/250 lr:0.001000 t:0.2s
+tttg: c4/250 lr:0.001000 t:0.3s
+tttg: c5/250 lr:0.000999 t:0.4s
+tttg: c6/250 lr:0.000999 t:0.5s
+tttg: c7/250 lr:0.000999 t:0.6s
+tttg: c8/250 lr:0.000998 t:0.6s
+tttg: c9/250 lr:0.000997 t:0.7s
+tttg: c10/250 lr:0.000997 t:0.8s
+tttg: c11/250 lr:0.000996 t:0.9s
+tttg: c12/250 lr:0.000995 t:1.0s
+tttg: c13/250 lr:0.000994 t:1.0s
+tttg: c14/250 lr:0.000993 t:1.1s
+tttg: c15/250 lr:0.000992 t:1.2s
+tttg: c16/250 lr:0.000991 t:1.3s
+tttg: c17/250 lr:0.000990 t:1.4s
+tttg: c18/250 lr:0.000989 t:1.5s
+tttg: c19/250 lr:0.000987 t:1.5s
+tttg: c20/250 lr:0.000986 t:1.6s
+tttg: c21/250 lr:0.000984 t:1.7s
+tttg: c22/250 lr:0.000983 t:1.8s
+tttg: c23/250 lr:0.000981 t:1.9s
+tttg: c24/250 lr:0.000979 t:1.9s
+tttg: c25/250 lr:0.000977 t:2.0s
+tttg: c26/250 lr:0.000975 t:2.1s
+tttg: c27/250 lr:0.000973 t:2.2s
+tttg: c28/250 lr:0.000971 t:2.3s
+tttg: c29/250 lr:0.000969 t:2.3s
+tttg: c30/250 lr:0.000967 t:2.4s
+tttg: c31/250 lr:0.000965 t:2.5s
+tttg: c32/250 lr:0.000962 t:2.6s
+tttg: c33/250 lr:0.000960 t:2.7s
+tttg: c34/250 lr:0.000957 t:2.8s
+tttg: c35/250 lr:0.000955 t:2.9s
+tttg: c36/250 lr:0.000952 t:2.9s
+tttg: c37/250 lr:0.000949 t:3.0s
+tttg: c38/250 lr:0.000947 t:3.1s
+tttg: c39/250 lr:0.000944 t:3.2s
+tttg: c40/250 lr:0.000941 t:3.3s
+tttg: c41/250 lr:0.000938 t:3.3s
+tttg: c42/250 lr:0.000935 t:3.4s
+tttg: c43/250 lr:0.000931 t:3.5s
+tttg: c44/250 lr:0.000928 t:3.6s
+tttg: c45/250 lr:0.000925 t:3.7s
+tttg: c46/250 lr:0.000922 t:3.8s
+tttg: c47/250 lr:0.000918 t:3.8s
+tttg: c48/250 lr:0.000915 t:3.9s
+tttg: c49/250 lr:0.000911 t:4.0s
+tttg: c50/250 lr:0.000907 t:4.1s
+tttg: c51/250 lr:0.000904 t:4.2s
+tttg: c52/250 lr:0.000900 t:4.3s
+tttg: c53/250 lr:0.000896 t:4.3s
+tttg: c54/250 lr:0.000892 t:4.4s
+tttg: c55/250 lr:0.000888 t:4.5s
+tttg: c56/250 lr:0.000884 t:4.6s
+tttg: c57/250 lr:0.000880 t:4.7s
+tttg: c58/250 lr:0.000876 t:4.7s
+tttg: c59/250 lr:0.000872 t:4.8s
+tttg: c60/250 lr:0.000868 t:4.9s
+tttg: c61/250 lr:0.000863 t:5.0s
+tttg: c62/250 lr:0.000859 t:5.1s
+tttg: c63/250 lr:0.000855 t:5.1s
+tttg: c64/250 lr:0.000850 t:5.2s
+tttg: c65/250 lr:0.000846 t:5.3s
+tttg: c66/250 lr:0.000841 t:5.4s
+tttg: c67/250 lr:0.000836 t:5.5s
+tttg: c68/250 lr:0.000832 t:5.5s
+tttg: c69/250 lr:0.000827 t:5.6s
+tttg: c70/250 lr:0.000822 t:5.7s
+tttg: c71/250 lr:0.000817 t:5.8s
+tttg: c72/250 lr:0.000812 t:5.9s
+tttg: c73/250 lr:0.000807 t:6.0s
+tttg: c74/250 lr:0.000803 t:6.0s
+tttg: c75/250 lr:0.000797 t:6.1s
+tttg: c76/250 lr:0.000792 t:6.2s
+tttg: c77/250 lr:0.000787 t:6.3s
+tttg: c78/250 lr:0.000782 t:6.4s
+tttg: c79/250 lr:0.000777 t:6.4s
+tttg: c80/250 lr:0.000772 t:6.5s
+tttg: c81/250 lr:0.000766 t:6.6s
+tttg: c82/250 lr:0.000761 t:6.7s
+tttg: c83/250 lr:0.000755 t:6.8s
+tttg: c84/250 lr:0.000750 t:6.9s
+tttg: c85/250 lr:0.000745 t:6.9s
+tttg: c86/250 lr:0.000739 t:7.0s
+tttg: c87/250 lr:0.000733 t:7.1s
+tttg: c88/250 lr:0.000728 t:7.2s
+tttg: c89/250 lr:0.000722 t:7.3s
+tttg: c90/250 lr:0.000717 t:7.3s
+tttg: c91/250 lr:0.000711 t:7.4s
+tttg: c92/250 lr:0.000705 t:7.5s
+tttg: c93/250 lr:0.000699 t:7.6s
+tttg: c94/250 lr:0.000694 t:7.7s
+tttg: c95/250 lr:0.000688 t:7.7s
+tttg: c96/250 lr:0.000682 t:7.8s
+tttg: c97/250 lr:0.000676 t:7.9s
+tttg: c98/250 lr:0.000670 t:8.0s
+tttg: c99/250 lr:0.000664 t:8.1s
+tttg: c100/250 lr:0.000658 t:8.2s
+tttg: c101/250 lr:0.000652 t:8.2s
+tttg: c102/250 lr:0.000646 t:8.3s
+tttg: c103/250 lr:0.000640 t:8.4s
+tttg: c104/250 lr:0.000634 t:8.5s
+tttg: c105/250 lr:0.000628 t:8.6s
+tttg: c106/250 lr:0.000622 t:8.6s
+tttg: c107/250 lr:0.000616 t:8.7s
+tttg: c108/250 lr:0.000610 t:8.8s
+tttg: c109/250 lr:0.000603 t:8.9s
+tttg: c110/250 lr:0.000597 t:9.0s
+tttg: c111/250 lr:0.000591 t:9.0s
+tttg: c112/250 lr:0.000585 t:9.1s
+tttg: c113/250 lr:0.000579 t:9.2s
+tttg: c114/250 lr:0.000572 t:9.3s
+tttg: c115/250 lr:0.000566 t:9.4s
+tttg: c116/250 lr:0.000560 t:9.5s
+tttg: c117/250 lr:0.000554 t:9.6s
+tttg: c118/250 lr:0.000547 t:9.6s
+tttg: c119/250 lr:0.000541 t:9.7s
+tttg: c120/250 lr:0.000535 t:9.8s
+tttg: c121/250 lr:0.000528 t:9.9s
+tttg: c122/250 lr:0.000522 t:10.0s
+tttg: c123/250 lr:0.000516 t:10.0s
+tttg: c124/250 lr:0.000509 t:10.1s
+tttg: c125/250 lr:0.000503 t:10.2s
+tttg: c126/250 lr:0.000497 t:10.3s
+tttg: c127/250 lr:0.000491 t:10.4s
+tttg: c128/250 lr:0.000484 t:10.4s
+tttg: c129/250 lr:0.000478 t:10.5s
+tttg: c130/250 lr:0.000472 t:10.6s
+tttg: c131/250 lr:0.000465 t:10.7s
+tttg: c132/250 lr:0.000459 t:10.8s
+tttg: c133/250 lr:0.000453 t:10.9s
+tttg: c134/250 lr:0.000446 t:10.9s
+tttg: c135/250 lr:0.000440 t:11.0s
+tttg: c136/250 lr:0.000434 t:11.1s
+tttg: c137/250 lr:0.000428 t:11.2s
+tttg: c138/250 lr:0.000421 t:11.3s
+tttg: c139/250 lr:0.000415 t:11.4s
+tttg: c140/250 lr:0.000409 t:11.4s
+tttg: c141/250 lr:0.000403 t:11.5s
+tttg: c142/250 lr:0.000397 t:11.6s
+tttg: c143/250 lr:0.000390 t:11.7s
+tttg: c144/250 lr:0.000384 t:11.8s
+tttg: c145/250 lr:0.000378 t:11.8s
+tttg: c146/250 lr:0.000372 t:11.9s
+tttg: c147/250 lr:0.000366 t:12.0s
+tttg: c148/250 lr:0.000360 t:12.1s
+tttg: c149/250 lr:0.000354 t:12.2s
+tttg: c150/250 lr:0.000348 t:12.3s
+tttg: c151/250 lr:0.000342 t:12.3s
+tttg: c152/250 lr:0.000336 t:12.4s
+tttg: c153/250 lr:0.000330 t:12.5s
+tttg: c154/250 lr:0.000324 t:12.6s
+tttg: c155/250 lr:0.000318 t:12.7s
+tttg: c156/250 lr:0.000312 t:12.7s
+tttg: c157/250 lr:0.000306 t:12.8s
+tttg: c158/250 lr:0.000301 t:12.9s
+tttg: c159/250 lr:0.000295 t:13.0s
+tttg: c160/250 lr:0.000289 t:13.1s
+tttg: c161/250 lr:0.000283 t:13.1s
+tttg: c162/250 lr:0.000278 t:13.2s
+tttg: c163/250 lr:0.000272 t:13.3s
+tttg: c164/250 lr:0.000267 t:13.4s
+tttg: c165/250 lr:0.000261 t:13.5s
+tttg: c166/250 lr:0.000255 t:13.6s
+tttg: c167/250 lr:0.000250 t:13.6s
+tttg: c168/250 lr:0.000245 t:13.7s
+tttg: c169/250 lr:0.000239 t:13.8s
+tttg: c170/250 lr:0.000234 t:13.9s
+tttg: c171/250 lr:0.000228 t:14.0s
+tttg: c172/250 lr:0.000223 t:14.0s
+tttg: c173/250 lr:0.000218 t:14.1s
+tttg: c174/250 lr:0.000213 t:14.2s
+tttg: c175/250 lr:0.000208 t:14.3s
+tttg: c176/250 lr:0.000203 t:14.4s
+tttg: c177/250 lr:0.000197 t:14.4s
+tttg: c178/250 lr:0.000193 t:14.5s
+tttg: c179/250 lr:0.000188 t:14.6s
+tttg: c180/250 lr:0.000183 t:14.7s
+tttg: c181/250 lr:0.000178 t:14.8s
+tttg: c182/250 lr:0.000173 t:14.9s
+tttg: c183/250 lr:0.000168 t:14.9s
+tttg: c184/250 lr:0.000164 t:15.0s
+tttg: c185/250 lr:0.000159 t:15.1s
+tttg: c186/250 lr:0.000154 t:15.2s
+tttg: c187/250 lr:0.000150 t:15.3s
+tttg: c188/250 lr:0.000145 t:15.3s
+tttg: c189/250 lr:0.000141 t:15.4s
+tttg: c190/250 lr:0.000137 t:15.5s
+tttg: c191/250 lr:0.000132 t:15.6s
+tttg: c192/250 lr:0.000128 t:15.7s
+tttg: c193/250 lr:0.000124 t:15.8s
+tttg: c194/250 lr:0.000120 t:15.8s
+tttg: c195/250 lr:0.000116 t:15.9s
+tttg: c196/250 lr:0.000112 t:16.0s
+tttg: c197/250 lr:0.000108 t:16.1s
+tttg: c198/250 lr:0.000104 t:16.2s
+tttg: c199/250 lr:0.000100 t:16.2s
+tttg: c200/250 lr:0.000096 t:16.3s
+tttg: c201/250 lr:0.000093 t:16.4s
+tttg: c202/250 lr:0.000089 t:16.5s
+tttg: c203/250 lr:0.000085 t:16.6s
+tttg: c204/250 lr:0.000082 t:16.7s
+tttg: c205/250 lr:0.000078 t:16.7s
+tttg: c206/250 lr:0.000075 t:16.8s
+tttg: c207/250 lr:0.000072 t:16.9s
+tttg: c208/250 lr:0.000069 t:17.0s
+tttg: c209/250 lr:0.000065 t:17.1s
+tttg: c210/250 lr:0.000062 t:17.1s
+tttg: c211/250 lr:0.000059 t:17.2s
+tttg: c212/250 lr:0.000056 t:17.3s
+tttg: c213/250 lr:0.000053 t:17.4s
+tttg: c214/250 lr:0.000051 t:17.5s
+tttg: c215/250 lr:0.000048 t:17.6s
+tttg: c216/250 lr:0.000045 t:17.6s
+tttg: c217/250 lr:0.000043 t:17.7s
+tttg: c218/250 lr:0.000040 t:17.8s
+tttg: c219/250 lr:0.000038 t:17.9s
+tttg: c220/250 lr:0.000035 t:18.0s
+tttg: c221/250 lr:0.000033 t:18.1s
+tttg: c222/250 lr:0.000031 t:18.1s
+tttg: c223/250 lr:0.000029 t:18.2s
+tttg: c224/250 lr:0.000027 t:18.3s
+tttg: c225/250 lr:0.000025 t:18.4s
+tttg: c226/250 lr:0.000023 t:18.5s
+tttg: c227/250 lr:0.000021 t:18.5s
+tttg: c228/250 lr:0.000019 t:18.6s
+tttg: c229/250 lr:0.000017 t:18.7s
+tttg: c230/250 lr:0.000016 t:18.8s
+tttg: c231/250 lr:0.000014 t:18.9s
+tttg: c232/250 lr:0.000013 t:18.9s
+tttg: c233/250 lr:0.000011 t:19.0s
+tttg: c234/250 lr:0.000010 t:19.1s
+tttg: c235/250 lr:0.000009 t:19.2s
+tttg: c236/250 lr:0.000008 t:19.3s
+tttg: c237/250 lr:0.000007 t:19.3s
+tttg: c238/250 lr:0.000006 t:19.4s
+tttg: c239/250 lr:0.000005 t:19.5s
+tttg: c240/250 lr:0.000004 t:19.6s
+tttg: c241/250 lr:0.000003 t:19.7s
+tttg: c242/250 lr:0.000003 t:19.7s
+tttg: c243/250 lr:0.000002 t:19.8s
+tttg: c244/250 lr:0.000001 t:19.9s
+tttg: c245/250 lr:0.000001 t:20.0s
+tttg: c246/250 lr:0.000001 t:20.1s
+tttg: c247/250 lr:0.000000 t:20.1s
+tttg: c248/250 lr:0.000000 t:20.2s
+tttg: c249/250 lr:0.000000 t:20.3s
+ttpr: phase:3/3 t:322.4s
+ttp: b737/782 bl:2.3209 bb:1.0434 rl:2.2404 rb:1.0437 dl:2550-2583 gd:1
+ttp: b735/782 bl:2.3883 bb:1.0988 rl:2.2555 rb:1.0494 dl:2495-2526 gd:1
+ttp: b720/782 bl:2.3585 bb:1.0667 rl:2.2637 rb:1.0508 dl:2125-2144 gd:1
+ttp: b713/782 bl:2.2571 bb:1.0143 rl:2.2633 rb:1.0482 dl:2002-2017 gd:1
+ttp: b706/782 bl:2.4044 bb:1.0753 rl:2.2721 rb:1.0499 dl:1898-1910 gd:1
+ttp: b698/782 bl:2.2510 bb:1.0304 rl:2.2709 rb:1.0488 dl:1803-1814 gd:1
+ttp: b690/782 bl:2.2996 bb:1.0675 rl:2.2723 rb:1.0498 dl:1715-1725 gd:1
+ttp: b683/782 bl:2.2708 bb:1.0570 rl:2.2723 rb:1.0501 dl:1646-1657 gd:1
+ttp: b675/782 bl:2.3680 bb:1.0590 rl:2.2763 rb:1.0505 dl:1578-1586 gd:1
+ttp: b666/782 bl:2.4142 bb:1.0656 rl:2.2817 rb:1.0511 dl:1507-1514 gd:1
+ttp: b658/782 bl:2.2536 bb:1.0202 rl:2.2807 rb:1.0500 dl:1452-1459 gd:1
+ttp: b651/782 bl:2.3928 bb:1.0457 rl:2.2845 rb:1.0498 dl:1406-1411 gd:1
+ttp: b643/782 bl:2.3564 bb:1.0261 rl:2.2867 rb:1.0490 dl:1356-1362 gd:1
+ttp: b635/782 bl:2.3432 bb:1.0574 rl:2.2884 rb:1.0493 dl:1308-1314 gd:1
+ttp: b627/782 bl:2.3787 bb:1.0710 rl:2.2909 rb:1.0499 dl:1266-1271 gd:1
+ttp: b619/782 bl:2.3247 bb:1.0601 rl:2.2918 rb:1.0502 dl:1221-1226 gd:1
+ttp: b611/782 bl:2.2970 bb:1.0257 rl:2.2919 rb:1.0495 dl:1182-1186 gd:1
+ttp: b604/782 bl:2.3826 bb:1.0458 rl:2.2940 rb:1.0495 dl:1150-1154 gd:1
+ttp: b596/782 bl:2.2851 bb:1.0447 rl:2.2938 rb:1.0493 dl:1115-1119 gd:1
+ttp: b589/782 bl:2.2764 bb:1.0109 rl:2.2935 rb:1.0485 dl:1086-1089 gd:1
+ttp: b582/782 bl:2.3482 bb:1.0314 rl:2.2946 rb:1.0482 dl:1056-1060 gd:1
+ttp: b573/782 bl:2.3666 bb:1.0668 rl:2.2959 rb:1.0485 dl:1021-1025 gd:1
+ttp: b565/782 bl:2.3876 bb:1.0343 rl:2.2976 rb:1.0482 dl:993-997 gd:1
+ttp: b557/782 bl:2.3387 bb:1.0505 rl:2.2983 rb:1.0483 dl:965-968 gd:1
+ttp: b549/782 bl:2.2617 bb:1.0226 rl:2.2977 rb:1.0478 dl:939-943 gd:1
+ttp: b541/782 bl:2.3284 bb:1.0332 rl:2.2982 rb:1.0476 dl:915-918 gd:1
+ttp: b533/782 bl:2.3718 bb:1.0670 rl:2.2993 rb:1.0479 dl:890-892 gd:1
+ttp: b525/782 bl:2.3559 bb:1.0210 rl:2.3002 rb:1.0475 dl:866-869 gd:1
+ttp: b517/782 bl:2.3525 bb:1.0265 rl:2.3009 rb:1.0472 dl:843-846 gd:1
+ttp: b509/782 bl:2.3632 bb:1.0375 rl:2.3017 rb:1.0470 dl:820-823 gd:1
+ttp: b502/782 bl:2.3185 bb:1.0274 rl:2.3020 rb:1.0468 dl:802-804 gd:1
+ttp: b495/782 bl:2.3115 bb:1.0325 rl:2.3021 rb:1.0466 dl:783-785 gd:1
+ttp: b487/782 bl:2.2820 bb:1.0685 rl:2.3018 rb:1.0469 dl:764-766 gd:1
+ttp: b479/782 bl:2.4117 bb:1.0836 rl:2.3031 rb:1.0473 dl:744-747 gd:1
+ttp: b471/782 bl:2.4048 bb:1.0858 rl:2.3043 rb:1.0477 dl:726-728 gd:1
+ttp: b463/782 bl:2.3173 bb:1.0428 rl:2.3044 rb:1.0477 dl:708-710 gd:1
+ttp: b455/782 bl:2.3074 bb:1.0399 rl:2.3044 rb:1.0476 dl:691-693 gd:1
+ttp: b447/782 bl:2.3279 bb:1.0694 rl:2.3047 rb:1.0478 dl:674-676 gd:1
+ttp: b439/782 bl:2.3287 bb:1.0391 rl:2.3049 rb:1.0477 dl:657-659 gd:1
+ttp: b431/782 bl:2.3753 bb:1.0537 rl:2.3056 rb:1.0478 dl:642-643 gd:1
+ttp: b423/782 bl:2.3086 bb:1.0533 rl:2.3056 rb:1.0478 dl:626-629 gd:1
+ttp: b414/782 bl:2.2054 bb:1.0097 rl:2.3047 rb:1.0475 dl:609-611 gd:1
+ttp: b406/782 bl:2.3154 bb:1.0663 rl:2.3048 rb:1.0477 dl:593-595 gd:1
+ttp: b398/782 bl:2.2499 bb:1.0047 rl:2.3044 rb:1.0473 dl:579-581 gd:1
+ttp: b390/782 bl:2.3530 bb:1.0601 rl:2.3047 rb:1.0474 dl:564-566 gd:1
+ttp: b381/782 bl:2.4268 bb:1.1032 rl:2.3057 rb:1.0478 dl:549-550 gd:1
+ttp: b373/782 bl:2.4084 bb:1.0990 rl:2.3064 rb:1.0482 dl:535-537 gd:1
+ttp: b364/782 bl:2.3466 bb:1.0611 rl:2.3067 rb:1.0483 dl:521-522 gd:1
+ttp: b356/782 bl:2.3465 bb:1.0566 rl:2.3070 rb:1.0484 dl:506-508 gd:1
+ttp: b348/782 bl:2.3682 bb:1.0622 rl:2.3074 rb:1.0485 dl:494-495 gd:1
+ttp: b340/782 bl:2.4596 bb:1.0812 rl:2.3084 rb:1.0487 dl:482-483 gd:1
+ttp: b330/782 bl:2.2403 bb:1.0675 rl:2.3080 rb:1.0488 dl:466-468 gd:1
+ttp: b322/782 bl:2.3793 bb:1.0620 rl:2.3084 rb:1.0489 dl:455-457 gd:1
+ttp: b313/782 bl:2.2861 bb:1.0772 rl:2.3083 rb:1.0490 dl:440-442 gd:1
+ttp: b305/782 bl:2.3375 bb:1.0865 rl:2.3085 rb:1.0492 dl:429-430 gd:1
+ttp: b297/782 bl:2.4007 bb:1.0847 rl:2.3090 rb:1.0494 dl:417-418 gd:1
+ttp: b289/782 bl:2.3277 bb:1.0826 rl:2.3091 rb:1.0496 dl:405-406 gd:1
+ttp: b280/782 bl:2.3383 bb:1.0902 rl:2.3092 rb:1.0498 dl:392-394 gd:1
+ttp: b272/782 bl:2.3681 bb:1.0938 rl:2.3095 rb:1.0500 dl:382-383 gd:1
+ttp: b264/782 bl:2.4242 bb:1.1047 rl:2.3100 rb:1.0503 dl:371-372 gd:1
+ttp: b256/782 bl:2.5431 bb:1.1226 rl:2.3111 rb:1.0506 dl:361-362 gd:1
+ttp: b248/782 bl:2.4665 bb:1.1904 rl:2.3118 rb:1.0512 dl:351-352 gd:1
+ttp: b240/782 bl:2.3085 bb:1.0596 rl:2.3118 rb:1.0512 dl:341-342 gd:1
+ttp: b232/782 bl:2.2994 bb:1.0838 rl:2.3118 rb:1.0514 dl:331-333 gd:1
+ttp: b224/782 bl:2.3865 bb:1.0936 rl:2.3121 rb:1.0515 dl:322-323 gd:1
+ttp: b215/782 bl:2.3942 bb:1.0974 rl:2.3124 rb:1.0517 dl:312-313 gd:1
+ttp: b207/782 bl:2.3575 bb:1.1330 rl:2.3125 rb:1.0520 dl:303-304 gd:1
+ttp: b197/782 bl:2.3639 bb:1.1174 rl:2.3127 rb:1.0522 dl:292-294 gd:1
+ttp: b188/782 bl:2.3387 bb:1.0982 rl:2.3128 rb:1.0524 dl:282-283 gd:1
+ttp: b180/782 bl:2.4276 bb:1.1122 rl:2.3132 rb:1.0526 dl:274-275 gd:1
+ttp: b173/782 bl:2.4777 bb:1.1344 rl:2.3138 rb:1.0529 dl:267-268 gd:1
+ttp: b166/782 bl:2.4813 bb:1.1091 rl:2.3143 rb:1.0531 dl:260-262 gd:1
+ttp: b160/782 bl:2.3886 bb:1.1154 rl:2.3145 rb:1.0532 dl:255-255 gd:1
+ttp: b152/782 bl:2.3924 bb:1.1458 rl:2.3148 rb:1.0535 dl:247-248 gd:1
+ttp: b144/782 bl:2.3571 bb:1.1079 rl:2.3149 rb:1.0537 dl:239-240 gd:1
+ttp: b137/782 bl:2.4127 bb:1.1527 rl:2.3152 rb:1.0539 dl:233-233 gd:1
+ttp: b128/782 bl:2.3848 bb:1.1526 rl:2.3153 rb:1.0542 dl:224-225 gd:1
+ttp: b120/782 bl:2.3781 bb:1.1050 rl:2.3155 rb:1.0543 dl:217-218 gd:1
+ttp: b111/782 bl:2.4092 bb:1.1747 rl:2.3157 rb:1.0546 dl:208-210 gd:1
+ttp: b104/782 bl:2.4919 bb:1.1764 rl:2.3162 rb:1.0549 dl:202-203 gd:1
+ttp: b95/782 bl:2.3259 bb:1.1371 rl:2.3162 rb:1.0551 dl:194-195 gd:1
+ttp: b83/782 bl:2.4322 bb:1.1479 rl:2.3164 rb:1.0552 dl:183-184 gd:1
+ttp: b73/782 bl:2.5370 bb:1.2453 rl:2.3169 rb:1.0556 dl:174-175 gd:1
+ttp: b66/782 bl:2.6369 bb:1.2340 rl:2.3175 rb:1.0560 dl:169-169 gd:1
+ttp: b57/782 bl:2.4675 bb:1.1619 rl:2.3178 rb:1.0562 dl:160-161 gd:1
+quantized_ttt_phased val_loss:2.32323386 val_bpb:1.06162721 eval_time:435107ms
+total_eval_time:435.1s
diff --git a/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_seed1234.log b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_seed1234.log
new file mode 100644
index 0000000000..3224926a86
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_seed1234.log
@@ -0,0 +1,842 @@
+W0424 22:23:38.160000 216990 torch/distributed/run.py:803] 
+W0424 22:23:38.160000 216990 torch/distributed/run.py:803] *****************************************
+W0424 22:23:38.160000 216990 torch/distributed/run.py:803] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+W0424 22:23:38.160000 216990 torch/distributed/run.py:803] *****************************************
+Hyperparameters:
+  adam_eps: 1e-08
+  adam_wd: 0.02
+  artifact_dir: 
+  attn_clip_sigmas: 13.0
+  attn_out_gate_enabled: False
+  attn_out_gate_src: proj
+  beta1: 0.9
+  beta2: 0.95
+  caseops_enabled: True
+  compressor: brotli
+  data_dir: ./data
+  datasets_dir: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved
+  distributed: True
+  ema_decay: 0.9965
+  embed_bits: 7
+  embed_clip_sigmas: 15.0
+  embed_lr: 0.6
+  embed_wd: 0.085
+  enable_looping_at: 0.35
+  eval_seq_len: 2048
+  eval_stride: 64
+  fused_ce_enabled: True
+  gate_window: 12
+  gated_attn_enabled: False
+  gated_attn_init_std: 0.01
+  gated_attn_quant_gate: True
+  global_ttt_batch_seqs: 32
+  global_ttt_chunk_tokens: 32768
+  global_ttt_epochs: 1
+  global_ttt_grad_clip: 1.0
+  global_ttt_lr: 0.001
+  global_ttt_momentum: 0.9
+  global_ttt_respect_doc_boundaries: True
+  global_ttt_warmup_chunks: 0
+  global_ttt_warmup_start_lr: 0.0
+  gptq_calibration_batches: 16
+  gptq_reserve_seconds: 0.5
+  grad_accum_steps: 1
+  grad_clip_norm: 0.3
+  is_main_process: True
+  iterations: 20000
+  ln_scale: True
+  local_rank: 0
+  logfile: logs/32b42842-ae6f-49b0-a59b-f32bae2710e7.txt
+  logit_softcap: 30.0
+  loop_end: 5
+  loop_start: 3
+  lqer_asym_enabled: True
+  lqer_asym_group: 64
+  lqer_enabled: True
+  lqer_factor_bits: 4
+  lqer_rank: 4
+  lqer_top_k: 3
+  matrix_bits: 6
+  matrix_clip_sigmas: 12.85
+  matrix_lr: 0.026
+  max_wallclock_seconds: 600.0
+  min_lr: 0.1
+  mlp_clip_sigmas: 12.0
+  mlp_mult: 4.0
+  model_dim: 512
+  model_path: final_model.pt
+  muon_backend_steps: 5
+  muon_momentum: 0.97
+  muon_momentum_warmup_start: 0.92
+  muon_momentum_warmup_steps: 1500
+  muon_row_normalize: True
+  muon_wd: 0.095
+  num_heads: 8
+  num_kv_heads: 4
+  num_layers: 11
+  num_loops: 2
+  parallel_final_lane: mean
+  parallel_start_layer: 8
+  phased_ttt_num_phases: 3
+  phased_ttt_prefix_docs: 2000
+  qk_gain_init: 5.0
+  quantized_model_path: final_model.int6.ptz
+  rank: 0
+  rope_base: 10000.0
+  rope_dims: 16
+  rope_train_seq_len: 2048
+  rope_yarn: False
+  run_id: 32b42842-ae6f-49b0-a59b-f32bae2710e7
+  scalar_lr: 0.02
+  seed: 1234
+  skip_gates_enabled: True
+  smear_gate_enabled: True
+  sparse_attn_gate_enabled: True
+  sparse_attn_gate_init_std: 0.0
+  sparse_attn_gate_scale: 1.0
+  tie_embeddings: True
+  tied_embed_init_std: 0.005
+  tied_embed_lr: 0.03
+  tokenizer_path: ./data/datasets/fineweb10B_sp8192_caseops/datasets/tokenizers/fineweb_8192_bpe_lossless_caps_caseops_v1_reserved.model
+  train_batch_tokens: 786432
+  train_files: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/fineweb_train_*.bin
+  train_log_every: 500
+  train_seq_len: 2048
+  ttt_batch_size: 64
+  ttt_beta1: 0.0
+  ttt_beta2: 0.999
+  ttt_chunk_size: 48
+  ttt_enabled: True
+  ttt_eval_batches: 
+  ttt_eval_seq_len: 2048
+  ttt_grad_steps: 1
+  ttt_k_lora: True
+  ttt_lora_lr: 0.0001
+  ttt_lora_rank: 96
+  ttt_mlp_lora: True
+  ttt_o_lora: True
+  ttt_optimizer: adam
+  ttt_weight_decay: 1.0
+  val_batch_tokens: 524288
+  val_bytes_files: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/fineweb_val_bytes_*.bin
+  val_doc_fraction: 1.0
+  val_files: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/fineweb_val_*.bin
+  val_loss_every: 0
+  vocab_size: 8192
+  warmdown_frac: 0.75
+  warmup_steps: 20
+  world_size: 8
+  xsa_last_n: 11
+train_shards: 80
+val_tokens: 47851520
+model_params:35945671
+gptq:reserving 0s, effective=599500ms
+warmup_cu_buckets:64,128,192,256 iters_each:3
+warmup_step: 1/20
+warmup_step: 2/20
+warmup_step: 3/20
+warmup_step: 4/20
+warmup_step: 5/20
+warmup_step: 6/20
+warmup_step: 10/20
+warmup_step: 20/20
+loop_warmup:enabled encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+loop_warmup_step: 1/20
+loop_warmup_step: 2/20
+loop_warmup_step: 3/20
+loop_warmup_step: 4/20
+loop_warmup_step: 5/20
+loop_warmup_step: 6/20
+loop_warmup_step: 10/20
+loop_warmup_step: 20/20
+1/20000 train_loss: 9.0017 train_time: 0.0m tok/s: 12361259
+2/20000 train_loss: 12.9400 train_time: 0.0m tok/s: 6765158
+3/20000 train_loss: 10.2311 train_time: 0.0m tok/s: 7253280
+4/20000 train_loss: 8.7390 train_time: 0.0m tok/s: 7514376
+5/20000 train_loss: 7.9377 train_time: 0.0m tok/s: 7682489
+500/20000 train_loss: 2.5706 train_time: 0.8m tok/s: 8209567
+1000/20000 train_loss: 2.8082 train_time: 1.6m tok/s: 8182430
+1500/20000 train_loss: 2.6317 train_time: 2.4m tok/s: 8164293
+2000/20000 train_loss: 2.6654 train_time: 3.2m tok/s: 8164921
+layer_loop:enabled step:2176 frac:0.350 encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+2500/20000 train_loss: 2.5555 train_time: 4.3m tok/s: 7691563
+3000/20000 train_loss: 2.5682 train_time: 5.4m tok/s: 7235008
+3500/20000 train_loss: 2.5644 train_time: 6.6m tok/s: 6940603
+4000/20000 train_loss: 2.4125 train_time: 7.8m tok/s: 6720210
+4500/20000 train_loss: 2.2834 train_time: 9.0m tok/s: 6571692
+4916/20000 val_loss: 2.3550 val_bpb: 1.0761
+stopping_early: wallclock_cap train_time: 599557ms step: 4916/20000
+peak memory allocated: 41709 MiB reserved: 47026 MiB
+ema:applying EMA weights
+diagnostic pre-quantization post-ema val_loss:2.33201285 val_bpb:1.06556967 eval_time:7360ms
+Serialized model: 135417533 bytes
+Code size (uncompressed): 151554 bytes
+Code size (compressed): 31220 bytes
+GPTQ:collecting Hessians from calibration data...
+GPTQ:collected 67 Hessians in 3.5s
+Quantized weights:
+  gate_int8_row: blocks.attn.attn_gate_w
+  gptq (int6): blocks.attn.c_k.weight, blocks.attn.c_q.weight, blocks.attn.c_v.weight, blocks.attn.proj.weight, blocks.mlp.fc.weight, blocks.mlp.proj.weight
+  gptq (int6)+lqer_asym: blocks.mlp.fc.weight
+  gptq (int7)+lqer_asym: tok_emb.weight
+  passthrough (float16): blocks.attn.q_gain, blocks.attn_scale, blocks.mlp_scale, blocks.resid_mix, parallel_post_lambdas, parallel_resid_lambdas, skip_gates, skip_weights, smear_gate.weight, smear_lambda
+Serialized model quantized+brotli: 15921623 bytes
+Total submission size quantized+brotli: 15952843 bytes
+diagnostic quantized val_loss:2.35203120 val_bpb:1.07471669 eval_time:11200ms
+ttt_lora:warming up compile (random tokens, no val data)
+ttt_lora:compile warmup done (107.2s)
+
+beginning TTT eval timer
+ttt_phased: total_docs:50000 prefix_docs:2000 suffix_docs:48000 num_phases:3 boundaries:[666, 1333, 2000]
+ttp: b776/782 bl:2.2569 bb:1.0700 rl:2.2569 rb:1.0700 dl:7534-8350 gd:0
+ttpp: phase:1/3 pd:1104 gd:666 t:219.4s
+tttg: c1/111 lr:0.001000 t:0.4s
+tttg: c2/111 lr:0.001000 t:0.5s
+tttg: c3/111 lr:0.000999 t:0.6s
+tttg: c4/111 lr:0.000998 t:0.6s
+tttg: c5/111 lr:0.000997 t:0.7s
+tttg: c6/111 lr:0.000995 t:0.8s
+tttg: c7/111 lr:0.000993 t:0.9s
+tttg: c8/111 lr:0.000990 t:1.0s
+tttg: c9/111 lr:0.000987 t:1.1s
+tttg: c10/111 lr:0.000984 t:1.1s
+tttg: c11/111 lr:0.000980 t:1.2s
+tttg: c12/111 lr:0.000976 t:1.3s
+tttg: c13/111 lr:0.000971 t:1.4s
+tttg: c14/111 lr:0.000966 t:1.5s
+tttg: c15/111 lr:0.000961 t:1.6s
+tttg: c16/111 lr:0.000955 t:1.6s
+tttg: c17/111 lr:0.000949 t:1.7s
+tttg: c18/111 lr:0.000942 t:1.8s
+tttg: c19/111 lr:0.000935 t:1.9s
+tttg: c20/111 lr:0.000928 t:2.0s
+tttg: c21/111 lr:0.000921 t:2.1s
+tttg: c22/111 lr:0.000913 t:2.1s
+tttg: c23/111 lr:0.000905 t:2.2s
+tttg: c24/111 lr:0.000896 t:2.3s
+tttg: c25/111 lr:0.000887 t:2.4s
+tttg: c26/111 lr:0.000878 t:2.5s
+tttg: c27/111 lr:0.000868 t:2.6s
+tttg: c28/111 lr:0.000859 t:2.6s
+tttg: c29/111 lr:0.000848 t:2.7s
+tttg: c30/111 lr:0.000838 t:2.8s
+tttg: c31/111 lr:0.000827 t:2.9s
+tttg: c32/111 lr:0.000817 t:3.0s
+tttg: c33/111 lr:0.000805 t:3.1s
+tttg: c34/111 lr:0.000794 t:3.1s
+tttg: c35/111 lr:0.000782 t:3.2s
+tttg: c36/111 lr:0.000770 t:3.3s
+tttg: c37/111 lr:0.000758 t:3.4s
+tttg: c38/111 lr:0.000746 t:3.5s
+tttg: c39/111 lr:0.000733 t:3.5s
+tttg: c40/111 lr:0.000721 t:3.6s
+tttg: c41/111 lr:0.000708 t:3.7s
+tttg: c42/111 lr:0.000695 t:3.8s
+tttg: c43/111 lr:0.000681 t:3.9s
+tttg: c44/111 lr:0.000668 t:4.0s
+tttg: c45/111 lr:0.000655 t:4.1s
+tttg: c46/111 lr:0.000641 t:4.1s
+tttg: c47/111 lr:0.000627 t:4.2s
+tttg: c48/111 lr:0.000613 t:4.3s
+tttg: c49/111 lr:0.000599 t:4.4s
+tttg: c50/111 lr:0.000585 t:4.5s
+tttg: c51/111 lr:0.000571 t:4.5s
+tttg: c52/111 lr:0.000557 t:4.6s
+tttg: c53/111 lr:0.000543 t:4.7s
+tttg: c54/111 lr:0.000529 t:4.8s
+tttg: c55/111 lr:0.000514 t:4.9s
+tttg: c56/111 lr:0.000500 t:5.0s
+tttg: c57/111 lr:0.000486 t:5.1s
+tttg: c58/111 lr:0.000471 t:5.2s
+tttg: c59/111 lr:0.000457 t:5.2s
+tttg: c60/111 lr:0.000443 t:5.3s
+tttg: c61/111 lr:0.000429 t:5.4s
+tttg: c62/111 lr:0.000415 t:5.5s
+tttg: c63/111 lr:0.000401 t:5.6s
+tttg: c64/111 lr:0.000387 t:5.7s
+tttg: c65/111 lr:0.000373 t:5.7s
+tttg: c66/111 lr:0.000359 t:5.8s
+tttg: c67/111 lr:0.000345 t:5.9s
+tttg: c68/111 lr:0.000332 t:6.0s
+tttg: c69/111 lr:0.000319 t:6.1s
+tttg: c70/111 lr:0.000305 t:6.2s
+tttg: c71/111 lr:0.000292 t:6.3s
+tttg: c72/111 lr:0.000279 t:6.3s
+tttg: c73/111 lr:0.000267 t:6.4s
+tttg: c74/111 lr:0.000254 t:6.5s
+tttg: c75/111 lr:0.000242 t:6.6s
+tttg: c76/111 lr:0.000230 t:6.7s
+tttg: c77/111 lr:0.000218 t:6.8s
+tttg: c78/111 lr:0.000206 t:6.9s
+tttg: c79/111 lr:0.000195 t:6.9s
+tttg: c80/111 lr:0.000183 t:7.0s
+tttg: c81/111 lr:0.000173 t:7.1s
+tttg: c82/111 lr:0.000162 t:7.2s
+tttg: c83/111 lr:0.000152 t:7.3s
+tttg: c84/111 lr:0.000141 t:7.4s
+tttg: c85/111 lr:0.000132 t:7.4s
+tttg: c86/111 lr:0.000122 t:7.5s
+tttg: c87/111 lr:0.000113 t:7.6s
+tttg: c88/111 lr:0.000104 t:7.7s
+tttg: c89/111 lr:0.000095 t:7.8s
+tttg: c90/111 lr:0.000087 t:7.8s
+tttg: c91/111 lr:0.000079 t:7.9s
+tttg: c92/111 lr:0.000072 t:8.0s
+tttg: c93/111 lr:0.000065 t:8.1s
+tttg: c94/111 lr:0.000058 t:8.2s
+tttg: c95/111 lr:0.000051 t:8.3s
+tttg: c96/111 lr:0.000045 t:8.4s
+tttg: c97/111 lr:0.000039 t:8.4s
+tttg: c98/111 lr:0.000034 t:8.5s
+tttg: c99/111 lr:0.000029 t:8.6s
+tttg: c100/111 lr:0.000024 t:8.7s
+tttg: c101/111 lr:0.000020 t:8.8s
+tttg: c102/111 lr:0.000016 t:8.9s
+tttg: c103/111 lr:0.000013 t:8.9s
+tttg: c104/111 lr:0.000010 t:9.0s
+tttg: c105/111 lr:0.000007 t:9.1s
+tttg: c106/111 lr:0.000005 t:9.2s
+tttg: c107/111 lr:0.000003 t:9.3s
+tttg: c108/111 lr:0.000002 t:9.3s
+tttg: c109/111 lr:0.000001 t:9.4s
+tttg: c110/111 lr:0.000000 t:9.5s
+ttpr: phase:1/3 t:231.0s
+ttp: b760/782 bl:2.3530 bb:1.0419 rl:2.2885 rb:1.0604 dl:3817-3916 gd:0
+ttp: b754/782 bl:2.2876 bb:1.0581 rl:2.2883 rb:1.0599 dl:3345-3397 gd:0
+ttpp: phase:2/3 pd:1808 gd:1333 t:305.0s
+tttg: c1/185 lr:0.001000 t:0.1s
+tttg: c2/185 lr:0.001000 t:0.2s
+tttg: c3/185 lr:0.001000 t:0.3s
+tttg: c4/185 lr:0.000999 t:0.3s
+tttg: c5/185 lr:0.000999 t:0.4s
+tttg: c6/185 lr:0.000998 t:0.5s
+tttg: c7/185 lr:0.000997 t:0.6s
+tttg: c8/185 lr:0.000996 t:0.7s
+tttg: c9/185 lr:0.000995 t:0.7s
+tttg: c10/185 lr:0.000994 t:0.8s
+tttg: c11/185 lr:0.000993 t:0.9s
+tttg: c12/185 lr:0.000991 t:1.0s
+tttg: c13/185 lr:0.000990 t:1.1s
+tttg: c14/185 lr:0.000988 t:1.1s
+tttg: c15/185 lr:0.000986 t:1.2s
+tttg: c16/185 lr:0.000984 t:1.3s
+tttg: c17/185 lr:0.000981 t:1.4s
+tttg: c18/185 lr:0.000979 t:1.5s
+tttg: c19/185 lr:0.000977 t:1.5s
+tttg: c20/185 lr:0.000974 t:1.6s
+tttg: c21/185 lr:0.000971 t:1.7s
+tttg: c22/185 lr:0.000968 t:1.8s
+tttg: c23/185 lr:0.000965 t:1.9s
+tttg: c24/185 lr:0.000962 t:1.9s
+tttg: c25/185 lr:0.000959 t:2.0s
+tttg: c26/185 lr:0.000955 t:2.1s
+tttg: c27/185 lr:0.000952 t:2.2s
+tttg: c28/185 lr:0.000948 t:2.3s
+tttg: c29/185 lr:0.000944 t:2.4s
+tttg: c30/185 lr:0.000940 t:2.5s
+tttg: c31/185 lr:0.000936 t:2.5s
+tttg: c32/185 lr:0.000932 t:2.6s
+tttg: c33/185 lr:0.000927 t:2.7s
+tttg: c34/185 lr:0.000923 t:2.8s
+tttg: c35/185 lr:0.000918 t:2.9s
+tttg: c36/185 lr:0.000913 t:3.0s
+tttg: c37/185 lr:0.000908 t:3.0s
+tttg: c38/185 lr:0.000904 t:3.1s
+tttg: c39/185 lr:0.000898 t:3.2s
+tttg: c40/185 lr:0.000893 t:3.3s
+tttg: c41/185 lr:0.000888 t:3.4s
+tttg: c42/185 lr:0.000882 t:3.5s
+tttg: c43/185 lr:0.000877 t:3.5s
+tttg: c44/185 lr:0.000871 t:3.6s
+tttg: c45/185 lr:0.000865 t:3.7s
+tttg: c46/185 lr:0.000860 t:3.8s
+tttg: c47/185 lr:0.000854 t:3.9s
+tttg: c48/185 lr:0.000847 t:4.0s
+tttg: c49/185 lr:0.000841 t:4.0s
+tttg: c50/185 lr:0.000835 t:4.1s
+tttg: c51/185 lr:0.000829 t:4.2s
+tttg: c52/185 lr:0.000822 t:4.3s
+tttg: c53/185 lr:0.000816 t:4.4s
+tttg: c54/185 lr:0.000809 t:4.4s
+tttg: c55/185 lr:0.000802 t:4.5s
+tttg: c56/185 lr:0.000795 t:4.6s
+tttg: c57/185 lr:0.000788 t:4.7s
+tttg: c58/185 lr:0.000781 t:4.8s
+tttg: c59/185 lr:0.000774 t:4.9s
+tttg: c60/185 lr:0.000767 t:4.9s
+tttg: c61/185 lr:0.000760 t:5.0s
+tttg: c62/185 lr:0.000752 t:5.1s
+tttg: c63/185 lr:0.000745 t:5.2s
+tttg: c64/185 lr:0.000738 t:5.3s
+tttg: c65/185 lr:0.000730 t:5.3s
+tttg: c66/185 lr:0.000722 t:5.4s
+tttg: c67/185 lr:0.000715 t:5.5s
+tttg: c68/185 lr:0.000707 t:5.6s
+tttg: c69/185 lr:0.000699 t:5.7s
+tttg: c70/185 lr:0.000691 t:5.8s
+tttg: c71/185 lr:0.000683 t:5.8s
+tttg: c72/185 lr:0.000675 t:5.9s
+tttg: c73/185 lr:0.000667 t:6.0s
+tttg: c74/185 lr:0.000659 t:6.1s
+tttg: c75/185 lr:0.000651 t:6.2s
+tttg: c76/185 lr:0.000643 t:6.3s
+tttg: c77/185 lr:0.000635 t:6.4s
+tttg: c78/185 lr:0.000627 t:6.4s
+tttg: c79/185 lr:0.000618 t:6.5s
+tttg: c80/185 lr:0.000610 t:6.6s
+tttg: c81/185 lr:0.000602 t:6.7s
+tttg: c82/185 lr:0.000593 t:6.8s
+tttg: c83/185 lr:0.000585 t:6.8s
+tttg: c84/185 lr:0.000577 t:6.9s
+tttg: c85/185 lr:0.000568 t:7.0s
+tttg: c86/185 lr:0.000560 t:7.1s
+tttg: c87/185 lr:0.000551 t:7.2s
+tttg: c88/185 lr:0.000543 t:7.2s
+tttg: c89/185 lr:0.000534 t:7.3s
+tttg: c90/185 lr:0.000526 t:7.4s
+tttg: c91/185 lr:0.000517 t:7.5s
+tttg: c92/185 lr:0.000509 t:7.6s
+tttg: c93/185 lr:0.000500 t:7.7s
+tttg: c94/185 lr:0.000491 t:7.7s
+tttg: c95/185 lr:0.000483 t:7.8s
+tttg: c96/185 lr:0.000474 t:7.9s
+tttg: c97/185 lr:0.000466 t:8.0s
+tttg: c98/185 lr:0.000457 t:8.1s
+tttg: c99/185 lr:0.000449 t:8.2s
+tttg: c100/185 lr:0.000440 t:8.2s
+tttg: c101/185 lr:0.000432 t:8.3s
+tttg: c102/185 lr:0.000423 t:8.4s
+tttg: c103/185 lr:0.000415 t:8.5s
+tttg: c104/185 lr:0.000407 t:8.6s
+tttg: c105/185 lr:0.000398 t:8.6s
+tttg: c106/185 lr:0.000390 t:8.7s
+tttg: c107/185 lr:0.000382 t:8.8s
+tttg: c108/185 lr:0.000373 t:8.9s
+tttg: c109/185 lr:0.000365 t:9.0s
+tttg: c110/185 lr:0.000357 t:9.0s
+tttg: c111/185 lr:0.000349 t:9.1s
+tttg: c112/185 lr:0.000341 t:9.2s
+tttg: c113/185 lr:0.000333 t:9.3s
+tttg: c114/185 lr:0.000325 t:9.4s
+tttg: c115/185 lr:0.000317 t:9.5s
+tttg: c116/185 lr:0.000309 t:9.5s
+tttg: c117/185 lr:0.000301 t:9.6s
+tttg: c118/185 lr:0.000293 t:9.7s
+tttg: c119/185 lr:0.000285 t:9.8s
+tttg: c120/185 lr:0.000278 t:9.9s
+tttg: c121/185 lr:0.000270 t:10.0s
+tttg: c122/185 lr:0.000262 t:10.0s
+tttg: c123/185 lr:0.000255 t:10.1s
+tttg: c124/185 lr:0.000248 t:10.2s
+tttg: c125/185 lr:0.000240 t:10.3s
+tttg: c126/185 lr:0.000233 t:10.4s
+tttg: c127/185 lr:0.000226 t:10.4s
+tttg: c128/185 lr:0.000219 t:10.5s
+tttg: c129/185 lr:0.000212 t:10.6s
+tttg: c130/185 lr:0.000205 t:10.7s
+tttg: c131/185 lr:0.000198 t:10.8s
+tttg: c132/185 lr:0.000191 t:10.8s
+tttg: c133/185 lr:0.000184 t:10.9s
+tttg: c134/185 lr:0.000178 t:11.0s
+tttg: c135/185 lr:0.000171 t:11.1s
+tttg: c136/185 lr:0.000165 t:11.2s
+tttg: c137/185 lr:0.000159 t:11.3s
+tttg: c138/185 lr:0.000153 t:11.3s
+tttg: c139/185 lr:0.000146 t:11.4s
+tttg: c140/185 lr:0.000140 t:11.5s
+tttg: c141/185 lr:0.000135 t:11.6s
+tttg: c142/185 lr:0.000129 t:11.7s
+tttg: c143/185 lr:0.000123 t:11.8s
+tttg: c144/185 lr:0.000118 t:11.8s
+tttg: c145/185 lr:0.000112 t:11.9s
+tttg: c146/185 lr:0.000107 t:12.0s
+tttg: c147/185 lr:0.000102 t:12.1s
+tttg: c148/185 lr:0.000096 t:12.2s
+tttg: c149/185 lr:0.000092 t:12.2s
+tttg: c150/185 lr:0.000087 t:12.3s
+tttg: c151/185 lr:0.000082 t:12.4s
+tttg: c152/185 lr:0.000077 t:12.5s
+tttg: c153/185 lr:0.000073 t:12.6s
+tttg: c154/185 lr:0.000068 t:12.6s
+tttg: c155/185 lr:0.000064 t:12.7s
+tttg: c156/185 lr:0.000060 t:12.8s
+tttg: c157/185 lr:0.000056 t:12.9s
+tttg: c158/185 lr:0.000052 t:13.0s
+tttg: c159/185 lr:0.000048 t:13.1s
+tttg: c160/185 lr:0.000045 t:13.1s
+tttg: c161/185 lr:0.000041 t:13.2s
+tttg: c162/185 lr:0.000038 t:13.3s
+tttg: c163/185 lr:0.000035 t:13.4s
+tttg: c164/185 lr:0.000032 t:13.5s
+tttg: c165/185 lr:0.000029 t:13.6s
+tttg: c166/185 lr:0.000026 t:13.6s
+tttg: c167/185 lr:0.000023 t:13.7s
+tttg: c168/185 lr:0.000021 t:13.8s
+tttg: c169/185 lr:0.000019 t:13.9s
+tttg: c170/185 lr:0.000016 t:14.0s
+tttg: c171/185 lr:0.000014 t:14.0s
+tttg: c172/185 lr:0.000012 t:14.1s
+tttg: c173/185 lr:0.000010 t:14.2s
+tttg: c174/185 lr:0.000009 t:14.3s
+tttg: c175/185 lr:0.000007 t:14.4s
+tttg: c176/185 lr:0.000006 t:14.5s
+tttg: c177/185 lr:0.000005 t:14.5s
+tttg: c178/185 lr:0.000004 t:14.6s
+tttg: c179/185 lr:0.000003 t:14.7s
+tttg: c180/185 lr:0.000002 t:14.8s
+tttg: c181/185 lr:0.000001 t:14.9s
+tttg: c182/185 lr:0.000001 t:15.0s
+tttg: c183/185 lr:0.000000 t:15.0s
+tttg: c184/185 lr:0.000000 t:15.1s
+ttpr: phase:2/3 t:322.3s
+ttp: b747/782 bl:2.3040 bb:1.0530 rl:2.2908 rb:1.0587 dl:2944-2991 gd:0
+ttp: b744/782 bl:2.4050 bb:1.0819 rl:2.3062 rb:1.0619 dl:2806-2842 gd:0
+ttpp: phase:3/3 pd:2448 gd:2000 t:339.5s
+tttg: c1/250 lr:0.001000 t:0.1s
+tttg: c2/250 lr:0.001000 t:0.2s
+tttg: c3/250 lr:0.001000 t:0.2s
+tttg: c4/250 lr:0.001000 t:0.3s
+tttg: c5/250 lr:0.000999 t:0.4s
+tttg: c6/250 lr:0.000999 t:0.5s
+tttg: c7/250 lr:0.000999 t:0.6s
+tttg: c8/250 lr:0.000998 t:0.6s
+tttg: c9/250 lr:0.000997 t:0.7s
+tttg: c10/250 lr:0.000997 t:0.8s
+tttg: c11/250 lr:0.000996 t:0.9s
+tttg: c12/250 lr:0.000995 t:1.0s
+tttg: c13/250 lr:0.000994 t:1.0s
+tttg: c14/250 lr:0.000993 t:1.1s
+tttg: c15/250 lr:0.000992 t:1.2s
+tttg: c16/250 lr:0.000991 t:1.3s
+tttg: c17/250 lr:0.000990 t:1.4s
+tttg: c18/250 lr:0.000989 t:1.5s
+tttg: c19/250 lr:0.000987 t:1.6s
+tttg: c20/250 lr:0.000986 t:1.6s
+tttg: c21/250 lr:0.000984 t:1.7s
+tttg: c22/250 lr:0.000983 t:1.8s
+tttg: c23/250 lr:0.000981 t:1.9s
+tttg: c24/250 lr:0.000979 t:1.9s
+tttg: c25/250 lr:0.000977 t:2.0s
+tttg: c26/250 lr:0.000975 t:2.1s
+tttg: c27/250 lr:0.000973 t:2.2s
+tttg: c28/250 lr:0.000971 t:2.3s
+tttg: c29/250 lr:0.000969 t:2.4s
+tttg: c30/250 lr:0.000967 t:2.5s
+tttg: c31/250 lr:0.000965 t:2.5s
+tttg: c32/250 lr:0.000962 t:2.6s
+tttg: c33/250 lr:0.000960 t:2.7s
+tttg: c34/250 lr:0.000957 t:2.8s
+tttg: c35/250 lr:0.000955 t:2.9s
+tttg: c36/250 lr:0.000952 t:2.9s
+tttg: c37/250 lr:0.000949 t:3.0s
+tttg: c38/250 lr:0.000947 t:3.1s
+tttg: c39/250 lr:0.000944 t:3.2s
+tttg: c40/250 lr:0.000941 t:3.3s
+tttg: c41/250 lr:0.000938 t:3.4s
+tttg: c42/250 lr:0.000935 t:3.4s
+tttg: c43/250 lr:0.000931 t:3.5s
+tttg: c44/250 lr:0.000928 t:3.6s
+tttg: c45/250 lr:0.000925 t:3.7s
+tttg: c46/250 lr:0.000922 t:3.8s
+tttg: c47/250 lr:0.000918 t:3.9s
+tttg: c48/250 lr:0.000915 t:4.0s
+tttg: c49/250 lr:0.000911 t:4.0s
+tttg: c50/250 lr:0.000907 t:4.1s
+tttg: c51/250 lr:0.000904 t:4.2s
+tttg: c52/250 lr:0.000900 t:4.3s
+tttg: c53/250 lr:0.000896 t:4.4s
+tttg: c54/250 lr:0.000892 t:4.4s
+tttg: c55/250 lr:0.000888 t:4.5s
+tttg: c56/250 lr:0.000884 t:4.6s
+tttg: c57/250 lr:0.000880 t:4.7s
+tttg: c58/250 lr:0.000876 t:4.8s
+tttg: c59/250 lr:0.000872 t:4.8s
+tttg: c60/250 lr:0.000868 t:4.9s
+tttg: c61/250 lr:0.000863 t:5.0s
+tttg: c62/250 lr:0.000859 t:5.1s
+tttg: c63/250 lr:0.000855 t:5.2s
+tttg: c64/250 lr:0.000850 t:5.2s
+tttg: c65/250 lr:0.000846 t:5.3s
+tttg: c66/250 lr:0.000841 t:5.4s
+tttg: c67/250 lr:0.000836 t:5.5s
+tttg: c68/250 lr:0.000832 t:5.6s
+tttg: c69/250 lr:0.000827 t:5.6s
+tttg: c70/250 lr:0.000822 t:5.7s
+tttg: c71/250 lr:0.000817 t:5.8s
+tttg: c72/250 lr:0.000812 t:5.9s
+tttg: c73/250 lr:0.000807 t:6.0s
+tttg: c74/250 lr:0.000803 t:6.1s
+tttg: c75/250 lr:0.000797 t:6.1s
+tttg: c76/250 lr:0.000792 t:6.2s
+tttg: c77/250 lr:0.000787 t:6.3s
+tttg: c78/250 lr:0.000782 t:6.4s
+tttg: c79/250 lr:0.000777 t:6.5s
+tttg: c80/250 lr:0.000772 t:6.6s
+tttg: c81/250 lr:0.000766 t:6.6s
+tttg: c82/250 lr:0.000761 t:6.7s
+tttg: c83/250 lr:0.000755 t:6.8s
+tttg: c84/250 lr:0.000750 t:6.9s
+tttg: c85/250 lr:0.000745 t:7.0s
+tttg: c86/250 lr:0.000739 t:7.0s
+tttg: c87/250 lr:0.000733 t:7.1s
+tttg: c88/250 lr:0.000728 t:7.2s
+tttg: c89/250 lr:0.000722 t:7.3s
+tttg: c90/250 lr:0.000717 t:7.4s
+tttg: c91/250 lr:0.000711 t:7.5s
+tttg: c92/250 lr:0.000705 t:7.5s
+tttg: c93/250 lr:0.000699 t:7.6s
+tttg: c94/250 lr:0.000694 t:7.7s
+tttg: c95/250 lr:0.000688 t:7.8s
+tttg: c96/250 lr:0.000682 t:7.9s
+tttg: c97/250 lr:0.000676 t:7.9s
+tttg: c98/250 lr:0.000670 t:8.0s
+tttg: c99/250 lr:0.000664 t:8.1s
+tttg: c100/250 lr:0.000658 t:8.2s
+tttg: c101/250 lr:0.000652 t:8.3s
+tttg: c102/250 lr:0.000646 t:8.4s
+tttg: c103/250 lr:0.000640 t:8.4s
+tttg: c104/250 lr:0.000634 t:8.5s
+tttg: c105/250 lr:0.000628 t:8.6s
+tttg: c106/250 lr:0.000622 t:8.7s
+tttg: c107/250 lr:0.000616 t:8.8s
+tttg: c108/250 lr:0.000610 t:8.9s
+tttg: c109/250 lr:0.000603 t:8.9s
+tttg: c110/250 lr:0.000597 t:9.0s
+tttg: c111/250 lr:0.000591 t:9.1s
+tttg: c112/250 lr:0.000585 t:9.2s
+tttg: c113/250 lr:0.000579 t:9.3s
+tttg: c114/250 lr:0.000572 t:9.4s
+tttg: c115/250 lr:0.000566 t:9.5s
+tttg: c116/250 lr:0.000560 t:9.5s
+tttg: c117/250 lr:0.000554 t:9.6s
+tttg: c118/250 lr:0.000547 t:9.7s
+tttg: c119/250 lr:0.000541 t:9.8s
+tttg: c120/250 lr:0.000535 t:9.9s
+tttg: c121/250 lr:0.000528 t:10.0s
+tttg: c122/250 lr:0.000522 t:10.0s
+tttg: c123/250 lr:0.000516 t:10.1s
+tttg: c124/250 lr:0.000509 t:10.2s
+tttg: c125/250 lr:0.000503 t:10.3s
+tttg: c126/250 lr:0.000497 t:10.4s
+tttg: c127/250 lr:0.000491 t:10.4s
+tttg: c128/250 lr:0.000484 t:10.5s
+tttg: c129/250 lr:0.000478 t:10.6s
+tttg: c130/250 lr:0.000472 t:10.7s
+tttg: c131/250 lr:0.000465 t:10.8s
+tttg: c132/250 lr:0.000459 t:10.9s
+tttg: c133/250 lr:0.000453 t:10.9s
+tttg: c134/250 lr:0.000446 t:11.0s
+tttg: c135/250 lr:0.000440 t:11.1s
+tttg: c136/250 lr:0.000434 t:11.2s
+tttg: c137/250 lr:0.000428 t:11.3s
+tttg: c138/250 lr:0.000421 t:11.4s
+tttg: c139/250 lr:0.000415 t:11.4s
+tttg: c140/250 lr:0.000409 t:11.5s
+tttg: c141/250 lr:0.000403 t:11.6s
+tttg: c142/250 lr:0.000397 t:11.7s
+tttg: c143/250 lr:0.000390 t:11.8s
+tttg: c144/250 lr:0.000384 t:11.9s
+tttg: c145/250 lr:0.000378 t:11.9s
+tttg: c146/250 lr:0.000372 t:12.0s
+tttg: c147/250 lr:0.000366 t:12.1s
+tttg: c148/250 lr:0.000360 t:12.2s
+tttg: c149/250 lr:0.000354 t:12.3s
+tttg: c150/250 lr:0.000348 t:12.3s
+tttg: c151/250 lr:0.000342 t:12.4s
+tttg: c152/250 lr:0.000336 t:12.5s
+tttg: c153/250 lr:0.000330 t:12.6s
+tttg: c154/250 lr:0.000324 t:12.7s
+tttg: c155/250 lr:0.000318 t:12.8s
+tttg: c156/250 lr:0.000312 t:12.8s
+tttg: c157/250 lr:0.000306 t:12.9s
+tttg: c158/250 lr:0.000301 t:13.0s
+tttg: c159/250 lr:0.000295 t:13.1s
+tttg: c160/250 lr:0.000289 t:13.2s
+tttg: c161/250 lr:0.000283 t:13.2s
+tttg: c162/250 lr:0.000278 t:13.3s
+tttg: c163/250 lr:0.000272 t:13.4s
+tttg: c164/250 lr:0.000267 t:13.5s
+tttg: c165/250 lr:0.000261 t:13.6s
+tttg: c166/250 lr:0.000255 t:13.6s
+tttg: c167/250 lr:0.000250 t:13.7s
+tttg: c168/250 lr:0.000245 t:13.8s
+tttg: c169/250 lr:0.000239 t:13.9s
+tttg: c170/250 lr:0.000234 t:14.0s
+tttg: c171/250 lr:0.000228 t:14.0s
+tttg: c172/250 lr:0.000223 t:14.1s
+tttg: c173/250 lr:0.000218 t:14.2s
+tttg: c174/250 lr:0.000213 t:14.3s
+tttg: c175/250 lr:0.000208 t:14.4s
+tttg: c176/250 lr:0.000203 t:14.5s
+tttg: c177/250 lr:0.000197 t:14.5s
+tttg: c178/250 lr:0.000193 t:14.6s
+tttg: c179/250 lr:0.000188 t:14.7s
+tttg: c180/250 lr:0.000183 t:14.8s
+tttg: c181/250 lr:0.000178 t:14.9s
+tttg: c182/250 lr:0.000173 t:15.0s
+tttg: c183/250 lr:0.000168 t:15.0s
+tttg: c184/250 lr:0.000164 t:15.1s
+tttg: c185/250 lr:0.000159 t:15.2s
+tttg: c186/250 lr:0.000154 t:15.3s
+tttg: c187/250 lr:0.000150 t:15.4s
+tttg: c188/250 lr:0.000145 t:15.4s
+tttg: c189/250 lr:0.000141 t:15.5s
+tttg: c190/250 lr:0.000137 t:15.6s
+tttg: c191/250 lr:0.000132 t:15.7s
+tttg: c192/250 lr:0.000128 t:15.8s
+tttg: c193/250 lr:0.000124 t:15.9s
+tttg: c194/250 lr:0.000120 t:15.9s
+tttg: c195/250 lr:0.000116 t:16.0s
+tttg: c196/250 lr:0.000112 t:16.1s
+tttg: c197/250 lr:0.000108 t:16.2s
+tttg: c198/250 lr:0.000104 t:16.3s
+tttg: c199/250 lr:0.000100 t:16.3s
+tttg: c200/250 lr:0.000096 t:16.4s
+tttg: c201/250 lr:0.000093 t:16.5s
+tttg: c202/250 lr:0.000089 t:16.6s
+tttg: c203/250 lr:0.000085 t:16.7s
+tttg: c204/250 lr:0.000082 t:16.8s
+tttg: c205/250 lr:0.000078 t:16.8s
+tttg: c206/250 lr:0.000075 t:16.9s
+tttg: c207/250 lr:0.000072 t:17.0s
+tttg: c208/250 lr:0.000069 t:17.1s
+tttg: c209/250 lr:0.000065 t:17.2s
+tttg: c210/250 lr:0.000062 t:17.2s
+tttg: c211/250 lr:0.000059 t:17.3s
+tttg: c212/250 lr:0.000056 t:17.4s
+tttg: c213/250 lr:0.000053 t:17.5s
+tttg: c214/250 lr:0.000051 t:17.6s
+tttg: c215/250 lr:0.000048 t:17.6s
+tttg: c216/250 lr:0.000045 t:17.7s
+tttg: c217/250 lr:0.000043 t:17.8s
+tttg: c218/250 lr:0.000040 t:17.9s
+tttg: c219/250 lr:0.000038 t:18.0s
+tttg: c220/250 lr:0.000035 t:18.0s
+tttg: c221/250 lr:0.000033 t:18.1s
+tttg: c222/250 lr:0.000031 t:18.2s
+tttg: c223/250 lr:0.000029 t:18.3s
+tttg: c224/250 lr:0.000027 t:18.4s
+tttg: c225/250 lr:0.000025 t:18.5s
+tttg: c226/250 lr:0.000023 t:18.5s
+tttg: c227/250 lr:0.000021 t:18.6s
+tttg: c228/250 lr:0.000019 t:18.7s
+tttg: c229/250 lr:0.000017 t:18.8s
+tttg: c230/250 lr:0.000016 t:18.9s
+tttg: c231/250 lr:0.000014 t:18.9s
+tttg: c232/250 lr:0.000013 t:19.0s
+tttg: c233/250 lr:0.000011 t:19.1s
+tttg: c234/250 lr:0.000010 t:19.2s
+tttg: c235/250 lr:0.000009 t:19.3s
+tttg: c236/250 lr:0.000008 t:19.4s
+tttg: c237/250 lr:0.000007 t:19.4s
+tttg: c238/250 lr:0.000006 t:19.5s
+tttg: c239/250 lr:0.000005 t:19.6s
+tttg: c240/250 lr:0.000004 t:19.7s
+tttg: c241/250 lr:0.000003 t:19.8s
+tttg: c242/250 lr:0.000003 t:19.8s
+tttg: c243/250 lr:0.000002 t:19.9s
+tttg: c244/250 lr:0.000001 t:20.0s
+tttg: c245/250 lr:0.000001 t:20.1s
+tttg: c246/250 lr:0.000001 t:20.2s
+tttg: c247/250 lr:0.000000 t:20.3s
+tttg: c248/250 lr:0.000000 t:20.3s
+tttg: c249/250 lr:0.000000 t:20.4s
+ttpr: phase:3/3 t:362.0s
+ttp: b739/782 bl:2.2964 bb:1.0245 rl:2.3051 rb:1.0576 dl:2619-2652 gd:1
+ttp: b732/782 bl:2.3733 bb:1.0929 rl:2.3115 rb:1.0609 dl:2416-2441 gd:1
+ttp: b724/782 bl:2.3195 bb:1.0591 rl:2.3121 rb:1.0608 dl:2203-2231 gd:1
+ttp: b714/782 bl:2.3091 bb:1.0228 rl:2.3119 rb:1.0581 dl:2018-2035 gd:1
+ttp: b708/782 bl:2.3126 bb:1.0344 rl:2.3120 rb:1.0567 dl:1924-1937 gd:1
+ttp: b699/782 bl:2.4177 bb:1.0554 rl:2.3176 rb:1.0566 dl:1814-1824 gd:1
+ttp: b695/782 bl:2.3442 bb:1.0812 rl:2.3189 rb:1.0578 dl:1769-1779 gd:1
+ttp: b680/782 bl:2.2836 bb:1.0284 rl:2.3174 rb:1.0565 dl:1618-1628 gd:1
+ttp: b672/782 bl:2.3314 bb:1.0491 rl:2.3180 rb:1.0562 dl:1553-1562 gd:1
+ttp: b664/782 bl:2.3398 bb:1.0269 rl:2.3188 rb:1.0551 dl:1493-1499 gd:1
+ttp: b656/782 bl:2.3298 bb:1.1114 rl:2.3192 rb:1.0570 dl:1439-1445 gd:1
+ttp: b648/782 bl:2.2854 bb:1.0085 rl:2.3181 rb:1.0554 dl:1387-1392 gd:1
+ttp: b640/782 bl:2.3083 bb:1.0515 rl:2.3178 rb:1.0552 dl:1337-1343 gd:1
+ttp: b634/782 bl:2.3832 bb:1.0492 rl:2.3196 rb:1.0551 dl:1302-1308 gd:1
+ttp: b625/782 bl:2.4092 bb:1.0512 rl:2.3220 rb:1.0550 dl:1255-1260 gd:1
+ttp: b617/782 bl:2.3148 bb:1.0229 rl:2.3218 rb:1.0541 dl:1211-1216 gd:1
+ttp: b609/782 bl:2.2747 bb:1.0191 rl:2.3207 rb:1.0533 dl:1172-1177 gd:1
+ttp: b601/782 bl:2.3350 bb:1.0222 rl:2.3210 rb:1.0526 dl:1137-1141 gd:1
+ttp: b593/782 bl:2.2968 bb:1.0139 rl:2.3205 rb:1.0517 dl:1103-1107 gd:1
+ttp: b585/782 bl:2.2829 bb:1.0354 rl:2.3198 rb:1.0514 dl:1069-1073 gd:1
+ttp: b578/782 bl:2.3572 bb:1.0348 rl:2.3205 rb:1.0511 dl:1041-1044 gd:1
+ttp: b571/782 bl:2.3008 bb:1.0065 rl:2.3201 rb:1.0502 dl:1014-1017 gd:1
+ttp: b564/782 bl:2.2901 bb:1.0190 rl:2.3196 rb:1.0496 dl:990-993 gd:1
+ttp: b556/782 bl:2.3774 bb:1.0688 rl:2.3206 rb:1.0500 dl:961-965 gd:1
+ttp: b547/782 bl:2.3378 bb:1.0507 rl:2.3209 rb:1.0500 dl:934-937 gd:1
+ttp: b539/782 bl:2.3368 bb:1.0359 rl:2.3211 rb:1.0498 dl:909-912 gd:1
+ttp: b532/782 bl:2.3903 bb:1.0676 rl:2.3221 rb:1.0500 dl:887-889 gd:1
+ttp: b524/782 bl:2.3764 bb:1.0676 rl:2.3229 rb:1.0503 dl:863-866 gd:1
+ttp: b514/782 bl:2.3102 bb:1.0665 rl:2.3227 rb:1.0505 dl:835-838 gd:1
+ttp: b506/782 bl:2.3471 bb:1.0134 rl:2.3231 rb:1.0500 dl:812-814 gd:1
+ttp: b499/782 bl:2.3401 bb:1.0566 rl:2.3233 rb:1.0501 dl:794-796 gd:1
+ttp: b491/782 bl:2.2854 bb:1.0308 rl:2.3228 rb:1.0498 dl:773-776 gd:1
+ttp: b483/782 bl:2.2556 bb:1.0291 rl:2.3220 rb:1.0496 dl:754-756 gd:1
+ttp: b476/782 bl:2.2745 bb:1.0308 rl:2.3215 rb:1.0494 dl:738-740 gd:1
+ttp: b468/782 bl:2.3638 bb:1.0640 rl:2.3219 rb:1.0495 dl:719-721 gd:1
+ttp: b460/782 bl:2.2540 bb:1.0545 rl:2.3212 rb:1.0496 dl:701-703 gd:1
+ttp: b452/782 bl:2.2654 bb:1.0139 rl:2.3207 rb:1.0492 dl:685-687 gd:1
+ttp: b444/782 bl:2.3113 bb:1.0649 rl:2.3206 rb:1.0494 dl:668-670 gd:1
+ttp: b436/782 bl:2.2735 bb:1.0502 rl:2.3201 rb:1.0494 dl:651-653 gd:1
+ttp: b428/782 bl:2.3062 bb:1.0509 rl:2.3200 rb:1.0494 dl:636-638 gd:1
+ttp: b420/782 bl:2.3612 bb:1.0541 rl:2.3204 rb:1.0494 dl:620-622 gd:1
+ttp: b412/782 bl:2.3324 bb:1.0458 rl:2.3205 rb:1.0494 dl:605-607 gd:1
+ttp: b404/782 bl:2.3705 bb:1.0616 rl:2.3209 rb:1.0495 dl:590-592 gd:1
+ttp: b396/782 bl:2.2862 bb:1.0754 rl:2.3206 rb:1.0497 dl:575-577 gd:1
+ttp: b389/782 bl:2.2938 bb:1.0864 rl:2.3204 rb:1.0500 dl:563-564 gd:1
+ttp: b382/782 bl:2.2961 bb:1.0848 rl:2.3202 rb:1.0502 dl:550-552 gd:1
+ttp: b375/782 bl:2.4064 bb:1.0733 rl:2.3208 rb:1.0504 dl:538-540 gd:1
+ttp: b368/782 bl:2.3687 bb:1.1032 rl:2.3212 rb:1.0508 dl:527-528 gd:1
+ttp: b360/782 bl:2.3082 bb:1.0798 rl:2.3211 rb:1.0510 dl:513-515 gd:1
+ttp: b352/782 bl:2.4200 bb:1.0951 rl:2.3218 rb:1.0513 dl:499-501 gd:1
+ttp: b344/782 bl:2.3898 bb:1.0650 rl:2.3222 rb:1.0514 dl:488-489 gd:1
+ttp: b336/782 bl:2.4110 bb:1.0865 rl:2.3228 rb:1.0516 dl:476-477 gd:1
+ttp: b328/782 bl:2.2908 bb:1.0182 rl:2.3226 rb:1.0514 dl:463-465 gd:1
+ttp: b320/782 bl:2.3436 bb:1.0837 rl:2.3227 rb:1.0516 dl:451-453 gd:1
+ttp: b312/782 bl:2.3103 bb:1.0524 rl:2.3226 rb:1.0516 dl:439-440 gd:1
+ttp: b305/782 bl:2.3377 bb:1.0866 rl:2.3227 rb:1.0517 dl:429-430 gd:1
+ttp: b298/782 bl:2.4212 bb:1.1025 rl:2.3232 rb:1.0520 dl:418-420 gd:1
+ttp: b292/782 bl:2.3402 bb:1.1080 rl:2.3233 rb:1.0523 dl:409-410 gd:1
+ttp: b285/782 bl:2.3817 bb:1.0850 rl:2.3236 rb:1.0525 dl:399-400 gd:1
+ttp: b279/782 bl:2.3124 bb:1.0926 rl:2.3236 rb:1.0527 dl:391-392 gd:1
+ttp: b273/782 bl:2.3315 bb:1.0747 rl:2.3236 rb:1.0528 dl:383-384 gd:1
+ttp: b265/782 bl:2.3678 bb:1.1017 rl:2.3238 rb:1.0530 dl:372-374 gd:1
+ttp: b257/782 bl:2.4463 bb:1.1128 rl:2.3243 rb:1.0532 dl:362-364 gd:1
+ttp: b249/782 bl:2.4524 bb:1.1046 rl:2.3249 rb:1.0535 dl:352-354 gd:1
+ttp: b241/782 bl:2.3533 bb:1.0937 rl:2.3250 rb:1.0536 dl:342-344 gd:1
+ttp: b233/782 bl:2.3667 bb:1.1307 rl:2.3252 rb:1.0539 dl:333-334 gd:1
+ttp: b225/782 bl:2.4424 bb:1.1183 rl:2.3257 rb:1.0542 dl:323-324 gd:1
+ttp: b217/782 bl:2.3729 bb:1.1329 rl:2.3258 rb:1.0545 dl:314-315 gd:1
+ttp: b210/782 bl:2.2603 bb:1.0837 rl:2.3256 rb:1.0546 dl:306-307 gd:1
+ttp: b202/782 bl:2.3568 bb:1.1031 rl:2.3257 rb:1.0547 dl:298-299 gd:1
+ttp: b194/782 bl:2.4420 bb:1.1187 rl:2.3261 rb:1.0550 dl:289-290 gd:1
+ttp: b188/782 bl:2.3425 bb:1.0999 rl:2.3262 rb:1.0551 dl:282-283 gd:1
+ttp: b181/782 bl:2.3386 bb:1.1293 rl:2.3262 rb:1.0553 dl:275-276 gd:1
+ttp: b172/782 bl:2.5212 bb:1.1559 rl:2.3268 rb:1.0557 dl:266-267 gd:1
+ttp: b163/782 bl:2.3827 bb:1.1225 rl:2.3270 rb:1.0559 dl:257-259 gd:1
+ttp: b155/782 bl:2.4022 bb:1.1106 rl:2.3272 rb:1.0560 dl:250-251 gd:1
+ttp: b148/782 bl:2.3385 bb:1.1065 rl:2.3273 rb:1.0562 dl:243-244 gd:1
+ttp: b141/782 bl:2.4695 bb:1.1270 rl:2.3277 rb:1.0564 dl:236-237 gd:1
+ttp: b133/782 bl:2.3688 bb:1.1362 rl:2.3278 rb:1.0566 dl:229-230 gd:1
+ttp: b124/782 bl:2.3873 bb:1.1662 rl:2.3279 rb:1.0568 dl:220-222 gd:1
+ttp: b117/782 bl:2.4772 bb:1.2037 rl:2.3283 rb:1.0572 dl:214-215 gd:1
+ttp: b110/782 bl:2.3792 bb:1.1291 rl:2.3284 rb:1.0573 dl:208-208 gd:1
+ttp: b101/782 bl:2.5163 bb:1.1566 rl:2.3288 rb:1.0576 dl:200-201 gd:1
+ttp: b93/782 bl:2.4733 bb:1.1863 rl:2.3292 rb:1.0578 dl:192-193 gd:1
+ttp: b86/782 bl:2.4619 bb:1.1358 rl:2.3295 rb:1.0580 dl:186-187 gd:1
+ttp: b78/782 bl:2.5482 bb:1.1929 rl:2.3299 rb:1.0583 dl:179-180 gd:1
+ttp: b71/782 bl:2.4570 bb:1.1742 rl:2.3302 rb:1.0585 dl:173-173 gd:1
+ttp: b63/782 bl:2.5189 bb:1.2015 rl:2.3305 rb:1.0587 dl:166-166 gd:1
+ttp: b54/782 bl:2.4816 bb:1.2173 rl:2.3308 rb:1.0590 dl:157-158 gd:1
+ttp: b47/782 bl:2.4349 bb:1.1367 rl:2.3310 rb:1.0591 dl:150-151 gd:1
+ttp: b39/782 bl:2.4479 bb:1.1849 rl:2.3312 rb:1.0593 dl:142-143 gd:1
+ttp: b35/782 bl:2.6168 bb:1.2694 rl:2.3316 rb:1.0596 dl:138-139 gd:1
+ttp: b27/782 bl:2.5846 bb:1.2218 rl:2.3320 rb:1.0599 dl:130-131 gd:1
+ttp: b19/782 bl:2.6242 bb:1.2049 rl:2.3324 rb:1.0601 dl:121-122 gd:1
+ttp: b10/782 bl:2.6240 bb:1.1756 rl:2.3327 rb:1.0602 dl:107-109 gd:1
+ttp: b2/782 bl:2.8160 bb:1.2377 rl:2.3332 rb:1.0604 dl:83-89 gd:1
+quantized_ttt_phased val_loss:2.32353901 val_bpb:1.06176665 eval_time:468924ms
+total_eval_time:468.9s
diff --git a/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_seed42.log b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_seed42.log
new file mode 100644
index 0000000000..4341210844
--- /dev/null
+++ b/records/track_10min_16mb/2026-04-25_PR1797Reproduction_3Seed_1.06136/train_seed42.log
@@ -0,0 +1,837 @@
+W0424 19:21:16.580000 104302 torch/distributed/run.py:803] 
+W0424 19:21:16.580000 104302 torch/distributed/run.py:803] *****************************************
+W0424 19:21:16.580000 104302 torch/distributed/run.py:803] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
+W0424 19:21:16.580000 104302 torch/distributed/run.py:803] *****************************************
+Hyperparameters:
+  adam_eps: 1e-08
+  adam_wd: 0.02
+  artifact_dir: 
+  attn_clip_sigmas: 13.0
+  attn_out_gate_enabled: False
+  attn_out_gate_src: proj
+  beta1: 0.9
+  beta2: 0.95
+  caseops_enabled: True
+  compressor: brotli
+  data_dir: ./data
+  datasets_dir: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved
+  distributed: True
+  ema_decay: 0.9965
+  embed_bits: 7
+  embed_clip_sigmas: 15.0
+  embed_lr: 0.6
+  embed_wd: 0.085
+  enable_looping_at: 0.35
+  eval_seq_len: 2048
+  eval_stride: 64
+  fused_ce_enabled: True
+  gate_window: 12
+  gated_attn_enabled: False
+  gated_attn_init_std: 0.01
+  gated_attn_quant_gate: True
+  global_ttt_batch_seqs: 32
+  global_ttt_chunk_tokens: 32768
+  global_ttt_epochs: 1
+  global_ttt_grad_clip: 1.0
+  global_ttt_lr: 0.001
+  global_ttt_momentum: 0.9
+  global_ttt_respect_doc_boundaries: True
+  global_ttt_warmup_chunks: 0
+  global_ttt_warmup_start_lr: 0.0
+  gptq_calibration_batches: 16
+  gptq_reserve_seconds: 0.5
+  grad_accum_steps: 1
+  grad_clip_norm: 0.3
+  is_main_process: True
+  iterations: 20000
+  ln_scale: True
+  local_rank: 0
+  logfile: logs/c8ec85ef-ab5e-4e94-9015-5c530a17f1bb.txt
+  logit_softcap: 30.0
+  loop_end: 5
+  loop_start: 3
+  lqer_asym_enabled: True
+  lqer_asym_group: 64
+  lqer_enabled: True
+  lqer_factor_bits: 4
+  lqer_rank: 4
+  lqer_top_k: 3
+  matrix_bits: 6
+  matrix_clip_sigmas: 12.85
+  matrix_lr: 0.026
+  max_wallclock_seconds: 600.0
+  min_lr: 0.1
+  mlp_clip_sigmas: 12.0
+  mlp_mult: 4.0
+  model_dim: 512
+  model_path: final_model.pt
+  muon_backend_steps: 5
+  muon_momentum: 0.97
+  muon_momentum_warmup_start: 0.92
+  muon_momentum_warmup_steps: 1500
+  muon_row_normalize: True
+  muon_wd: 0.095
+  num_heads: 8
+  num_kv_heads: 4
+  num_layers: 11
+  num_loops: 2
+  parallel_final_lane: mean
+  parallel_start_layer: 8
+  phased_ttt_num_phases: 3
+  phased_ttt_prefix_docs: 2000
+  qk_gain_init: 5.0
+  quantized_model_path: final_model.int6.ptz
+  rank: 0
+  rope_base: 10000.0
+  rope_dims: 16
+  rope_train_seq_len: 2048
+  rope_yarn: False
+  run_id: c8ec85ef-ab5e-4e94-9015-5c530a17f1bb
+  scalar_lr: 0.02
+  seed: 42
+  skip_gates_enabled: True
+  smear_gate_enabled: True
+  sparse_attn_gate_enabled: True
+  sparse_attn_gate_init_std: 0.0
+  sparse_attn_gate_scale: 1.0
+  tie_embeddings: True
+  tied_embed_init_std: 0.005
+  tied_embed_lr: 0.03
+  tokenizer_path: ./data/datasets/fineweb10B_sp8192_caseops/datasets/tokenizers/fineweb_8192_bpe_lossless_caps_caseops_v1_reserved.model
+  train_batch_tokens: 786432
+  train_files: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/fineweb_train_*.bin
+  train_log_every: 500
+  train_seq_len: 2048
+  ttt_batch_size: 64
+  ttt_beta1: 0.0
+  ttt_beta2: 0.999
+  ttt_chunk_size: 48
+  ttt_enabled: True
+  ttt_eval_batches: 
+  ttt_eval_seq_len: 2048
+  ttt_grad_steps: 1
+  ttt_k_lora: True
+  ttt_lora_lr: 0.0001
+  ttt_lora_rank: 96
+  ttt_mlp_lora: True
+  ttt_o_lora: True
+  ttt_optimizer: adam
+  ttt_weight_decay: 1.0
+  val_batch_tokens: 524288
+  val_bytes_files: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/fineweb_val_bytes_*.bin
+  val_doc_fraction: 1.0
+  val_files: ./data/datasets/fineweb10B_sp8192_caseops/datasets/datasets/fineweb10B_sp8192_lossless_caps_caseops_v1_reserved/fineweb_val_*.bin
+  val_loss_every: 0
+  vocab_size: 8192
+  warmdown_frac: 0.75
+  warmup_steps: 20
+  world_size: 8
+  xsa_last_n: 11
+train_shards: 80
+val_tokens: 47851520
+model_params:35945671
+gptq:reserving 0s, effective=599500ms
+warmup_cu_buckets:64,128,192,256 iters_each:3
+warmup_step: 1/20
+warmup_step: 2/20
+warmup_step: 3/20
+warmup_step: 4/20
+warmup_step: 5/20
+warmup_step: 6/20
+warmup_step: 10/20
+warmup_step: 20/20
+loop_warmup:enabled encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+loop_warmup_step: 1/20
+loop_warmup_step: 2/20
+loop_warmup_step: 3/20
+loop_warmup_step: 4/20
+loop_warmup_step: 5/20
+loop_warmup_step: 6/20
+loop_warmup_step: 10/20
+loop_warmup_step: 20/20
+1/20000 train_loss: 9.0087 train_time: 0.0m tok/s: 12246968
+2/20000 train_loss: 12.8398 train_time: 0.0m tok/s: 7587081
+3/20000 train_loss: 10.2560 train_time: 0.0m tok/s: 7937717
+4/20000 train_loss: 8.7255 train_time: 0.0m tok/s: 8072494
+5/20000 train_loss: 7.9555 train_time: 0.0m tok/s: 8153872
+500/20000 train_loss: 2.5762 train_time: 0.8m tok/s: 8228297
+1000/20000 train_loss: 2.8038 train_time: 1.6m tok/s: 8189513
+1500/20000 train_loss: 2.6351 train_time: 2.4m tok/s: 8177537
+2000/20000 train_loss: 2.6664 train_time: 3.2m tok/s: 8172624
+layer_loop:enabled step:2179 frac:0.350 encoder:[0, 1, 2, 3, 4, 5, 3, 4] decoder:[5, 3, 4, 5, 6, 7, 8, 9, 10]
+2500/20000 train_loss: 2.5565 train_time: 4.2m tok/s: 7710230
+3000/20000 train_loss: 2.5694 train_time: 5.4m tok/s: 7249127
+3500/20000 train_loss: 2.5658 train_time: 6.6m tok/s: 6952882
+4000/20000 train_loss: 2.4132 train_time: 7.8m tok/s: 6746475
+4500/20000 train_loss: 2.2825 train_time: 8.9m tok/s: 6595008
+4948/20000 val_loss: 2.3528 val_bpb: 1.0751
+stopping_early: wallclock_cap train_time: 599561ms step: 4948/20000
+peak memory allocated: 41718 MiB reserved: 47106 MiB
+ema:applying EMA weights
+diagnostic pre-quantization post-ema val_loss:2.32969122 val_bpb:1.06450885 eval_time:8917ms
+Serialized model: 135417533 bytes
+Code size (uncompressed): 151554 bytes
+Code size (compressed): 31220 bytes
+GPTQ:collecting Hessians from calibration data...
+GPTQ:collected 67 Hessians in 3.5s
+Quantized weights:
+  gate_int8_row: blocks.attn.attn_gate_w
+  gptq (int6): blocks.attn.c_k.weight, blocks.attn.c_q.weight, blocks.attn.c_v.weight, blocks.attn.proj.weight, blocks.mlp.fc.weight, blocks.mlp.proj.weight
+  gptq (int6)+lqer_asym: blocks.mlp.fc.weight
+  gptq (int7)+lqer_asym: tok_emb.weight
+  passthrough (float16): blocks.attn.q_gain, blocks.attn_scale, blocks.mlp_scale, blocks.resid_mix, parallel_post_lambdas, parallel_resid_lambdas, skip_gates, skip_weights, smear_gate.weight, smear_lambda
+Serialized model quantized+brotli: 15920126 bytes
+Total submission size quantized+brotli: 15951346 bytes
+diagnostic quantized val_loss:2.34926238 val_bpb:1.07345152 eval_time:63823ms
+ttt_lora:warming up compile (random tokens, no val data)
+ttt_lora:compile warmup done (160.8s)
+
+beginning TTT eval timer
+ttt_phased: total_docs:50000 prefix_docs:2000 suffix_docs:48000 num_phases:3 boundaries:[666, 1333, 2000]
+ttp: b782/782 bl:2.1450 bb:1.0157 rl:2.1450 rb:1.0157 dl:30339-97114 gd:0
+ttpp: phase:1/3 pd:1104 gd:666 t:225.6s
+tttg: c1/111 lr:0.001000 t:2.3s
+tttg: c2/111 lr:0.001000 t:2.4s
+tttg: c3/111 lr:0.000999 t:2.5s
+tttg: c4/111 lr:0.000998 t:2.6s
+tttg: c5/111 lr:0.000997 t:2.6s
+tttg: c6/111 lr:0.000995 t:2.7s
+tttg: c7/111 lr:0.000993 t:2.8s
+tttg: c8/111 lr:0.000990 t:2.9s
+tttg: c9/111 lr:0.000987 t:2.9s
+tttg: c10/111 lr:0.000984 t:3.0s
+tttg: c11/111 lr:0.000980 t:3.1s
+tttg: c12/111 lr:0.000976 t:3.2s
+tttg: c13/111 lr:0.000971 t:3.3s
+tttg: c14/111 lr:0.000966 t:3.3s
+tttg: c15/111 lr:0.000961 t:3.4s
+tttg: c16/111 lr:0.000955 t:3.5s
+tttg: c17/111 lr:0.000949 t:3.6s
+tttg: c18/111 lr:0.000942 t:3.6s
+tttg: c19/111 lr:0.000935 t:3.7s
+tttg: c20/111 lr:0.000928 t:3.8s
+tttg: c21/111 lr:0.000921 t:3.9s
+tttg: c22/111 lr:0.000913 t:4.0s
+tttg: c23/111 lr:0.000905 t:4.0s
+tttg: c24/111 lr:0.000896 t:4.1s
+tttg: c25/111 lr:0.000887 t:4.2s
+tttg: c26/111 lr:0.000878 t:4.3s
+tttg: c27/111 lr:0.000868 t:4.3s
+tttg: c28/111 lr:0.000859 t:4.4s
+tttg: c29/111 lr:0.000848 t:4.5s
+tttg: c30/111 lr:0.000838 t:4.6s
+tttg: c31/111 lr:0.000827 t:4.7s
+tttg: c32/111 lr:0.000817 t:4.7s
+tttg: c33/111 lr:0.000805 t:4.8s
+tttg: c34/111 lr:0.000794 t:4.9s
+tttg: c35/111 lr:0.000782 t:5.0s
+tttg: c36/111 lr:0.000770 t:5.0s
+tttg: c37/111 lr:0.000758 t:5.1s
+tttg: c38/111 lr:0.000746 t:5.2s
+tttg: c39/111 lr:0.000733 t:5.3s
+tttg: c40/111 lr:0.000721 t:5.4s
+tttg: c41/111 lr:0.000708 t:5.4s
+tttg: c42/111 lr:0.000695 t:5.5s
+tttg: c43/111 lr:0.000681 t:5.6s
+tttg: c44/111 lr:0.000668 t:5.7s
+tttg: c45/111 lr:0.000655 t:5.8s
+tttg: c46/111 lr:0.000641 t:5.8s
+tttg: c47/111 lr:0.000627 t:5.9s
+tttg: c48/111 lr:0.000613 t:6.0s
+tttg: c49/111 lr:0.000599 t:6.1s
+tttg: c50/111 lr:0.000585 t:6.1s
+tttg: c51/111 lr:0.000571 t:6.2s
+tttg: c52/111 lr:0.000557 t:6.3s
+tttg: c53/111 lr:0.000543 t:6.4s
+tttg: c54/111 lr:0.000529 t:6.5s
+tttg: c55/111 lr:0.000514 t:6.5s
+tttg: c56/111 lr:0.000500 t:6.6s
+tttg: c57/111 lr:0.000486 t:6.7s
+tttg: c58/111 lr:0.000471 t:6.8s
+tttg: c59/111 lr:0.000457 t:6.9s
+tttg: c60/111 lr:0.000443 t:6.9s
+tttg: c61/111 lr:0.000429 t:7.0s
+tttg: c62/111 lr:0.000415 t:7.1s
+tttg: c63/111 lr:0.000401 t:7.2s
+tttg: c64/111 lr:0.000387 t:7.3s
+tttg: c65/111 lr:0.000373 t:7.3s
+tttg: c66/111 lr:0.000359 t:7.4s
+tttg: c67/111 lr:0.000345 t:7.5s
+tttg: c68/111 lr:0.000332 t:7.6s
+tttg: c69/111 lr:0.000319 t:7.7s
+tttg: c70/111 lr:0.000305 t:7.8s
+tttg: c71/111 lr:0.000292 t:7.8s
+tttg: c72/111 lr:0.000279 t:7.9s
+tttg: c73/111 lr:0.000267 t:8.0s
+tttg: c74/111 lr:0.000254 t:8.1s
+tttg: c75/111 lr:0.000242 t:8.2s
+tttg: c76/111 lr:0.000230 t:8.3s
+tttg: c77/111 lr:0.000218 t:8.3s
+tttg: c78/111 lr:0.000206 t:8.4s
+tttg: c79/111 lr:0.000195 t:8.5s
+tttg: c80/111 lr:0.000183 t:8.6s
+tttg: c81/111 lr:0.000173 t:8.6s
+tttg: c82/111 lr:0.000162 t:8.7s
+tttg: c83/111 lr:0.000152 t:8.8s
+tttg: c84/111 lr:0.000141 t:8.9s
+tttg: c85/111 lr:0.000132 t:8.9s
+tttg: c86/111 lr:0.000122 t:9.0s
+tttg: c87/111 lr:0.000113 t:9.1s
+tttg: c88/111 lr:0.000104 t:9.2s
+tttg: c89/111 lr:0.000095 t:9.3s
+tttg: c90/111 lr:0.000087 t:9.3s
+tttg: c91/111 lr:0.000079 t:9.4s
+tttg: c92/111 lr:0.000072 t:9.5s
+tttg: c93/111 lr:0.000065 t:9.6s
+tttg: c94/111 lr:0.000058 t:9.6s
+tttg: c95/111 lr:0.000051 t:9.7s
+tttg: c96/111 lr:0.000045 t:9.8s
+tttg: c97/111 lr:0.000039 t:9.9s
+tttg: c98/111 lr:0.000034 t:10.0s
+tttg: c99/111 lr:0.000029 t:10.0s
+tttg: c100/111 lr:0.000024 t:10.1s
+tttg: c101/111 lr:0.000020 t:10.2s
+tttg: c102/111 lr:0.000016 t:10.3s
+tttg: c103/111 lr:0.000013 t:10.4s
+tttg: c104/111 lr:0.000010 t:10.4s
+tttg: c105/111 lr:0.000007 t:10.5s
+tttg: c106/111 lr:0.000005 t:10.6s
+tttg: c107/111 lr:0.000003 t:10.7s
+tttg: c108/111 lr:0.000002 t:10.7s
+tttg: c109/111 lr:0.000001 t:10.8s
+tttg: c110/111 lr:0.000000 t:10.9s
+ttpr: phase:1/3 t:238.6s
+ttp: b760/782 bl:2.3517 bb:1.0413 rl:2.1945 rb:1.0222 dl:3817-3916 gd:0
+ttpp: phase:2/3 pd:1808 gd:1333 t:362.0s
+tttg: c1/185 lr:0.001000 t:0.1s
+tttg: c2/185 lr:0.001000 t:0.2s
+tttg: c3/185 lr:0.001000 t:0.3s
+tttg: c4/185 lr:0.000999 t:0.3s
+tttg: c5/185 lr:0.000999 t:0.4s
+tttg: c6/185 lr:0.000998 t:0.5s
+tttg: c7/185 lr:0.000997 t:0.6s
+tttg: c8/185 lr:0.000996 t:0.6s
+tttg: c9/185 lr:0.000995 t:0.7s
+tttg: c10/185 lr:0.000994 t:0.8s
+tttg: c11/185 lr:0.000993 t:0.9s
+tttg: c12/185 lr:0.000991 t:1.0s
+tttg: c13/185 lr:0.000990 t:1.0s
+tttg: c14/185 lr:0.000988 t:1.1s
+tttg: c15/185 lr:0.000986 t:1.2s
+tttg: c16/185 lr:0.000984 t:1.3s
+tttg: c17/185 lr:0.000981 t:1.3s
+tttg: c18/185 lr:0.000979 t:1.4s
+tttg: c19/185 lr:0.000977 t:1.5s
+tttg: c20/185 lr:0.000974 t:1.6s
+tttg: c21/185 lr:0.000971 t:1.7s
+tttg: c22/185 lr:0.000968 t:1.7s
+tttg: c23/185 lr:0.000965 t:1.8s
+tttg: c24/185 lr:0.000962 t:1.9s
+tttg: c25/185 lr:0.000959 t:2.0s
+tttg: c26/185 lr:0.000955 t:2.0s
+tttg: c27/185 lr:0.000952 t:2.1s
+tttg: c28/185 lr:0.000948 t:2.2s
+tttg: c29/185 lr:0.000944 t:2.3s
+tttg: c30/185 lr:0.000940 t:2.4s
+tttg: c31/185 lr:0.000936 t:2.4s
+tttg: c32/185 lr:0.000932 t:2.5s
+tttg: c33/185 lr:0.000927 t:2.6s
+tttg: c34/185 lr:0.000923 t:2.7s
+tttg: c35/185 lr:0.000918 t:2.7s
+tttg: c36/185 lr:0.000913 t:2.8s
+tttg: c37/185 lr:0.000908 t:2.9s
+tttg: c38/185 lr:0.000904 t:3.0s
+tttg: c39/185 lr:0.000898 t:3.1s
+tttg: c40/185 lr:0.000893 t:3.1s
+tttg: c41/185 lr:0.000888 t:3.2s
+tttg: c42/185 lr:0.000882 t:3.3s
+tttg: c43/185 lr:0.000877 t:3.4s
+tttg: c44/185 lr:0.000871 t:3.4s
+tttg: c45/185 lr:0.000865 t:3.5s
+tttg: c46/185 lr:0.000860 t:3.6s
+tttg: c47/185 lr:0.000854 t:3.7s
+tttg: c48/185 lr:0.000847 t:3.8s
+tttg: c49/185 lr:0.000841 t:3.8s
+tttg: c50/185 lr:0.000835 t:3.9s
+tttg: c51/185 lr:0.000829 t:4.0s
+tttg: c52/185 lr:0.000822 t:4.1s
+tttg: c53/185 lr:0.000816 t:4.1s
+tttg: c54/185 lr:0.000809 t:4.2s
+tttg: c55/185 lr:0.000802 t:4.3s
+tttg: c56/185 lr:0.000795 t:4.4s
+tttg: c57/185 lr:0.000788 t:4.5s
+tttg: c58/185 lr:0.000781 t:4.5s
+tttg: c59/185 lr:0.000774 t:4.6s
+tttg: c60/185 lr:0.000767 t:4.7s
+tttg: c61/185 lr:0.000760 t:4.8s
+tttg: c62/185 lr:0.000752 t:4.8s
+tttg: c63/185 lr:0.000745 t:4.9s
+tttg: c64/185 lr:0.000738 t:5.0s
+tttg: c65/185 lr:0.000730 t:5.1s
+tttg: c66/185 lr:0.000722 t:5.2s
+tttg: c67/185 lr:0.000715 t:5.2s
+tttg: c68/185 lr:0.000707 t:5.3s
+tttg: c69/185 lr:0.000699 t:5.4s
+tttg: c70/185 lr:0.000691 t:5.5s
+tttg: c71/185 lr:0.000683 t:5.5s
+tttg: c72/185 lr:0.000675 t:5.6s
+tttg: c73/185 lr:0.000667 t:5.7s
+tttg: c74/185 lr:0.000659 t:5.8s
+tttg: c75/185 lr:0.000651 t:5.9s
+tttg: c76/185 lr:0.000643 t:5.9s
+tttg: c77/185 lr:0.000635 t:6.0s
+tttg: c78/185 lr:0.000627 t:6.1s
+tttg: c79/185 lr:0.000618 t:6.2s
+tttg: c80/185 lr:0.000610 t:6.2s
+tttg: c81/185 lr:0.000602 t:6.3s
+tttg: c82/185 lr:0.000593 t:6.4s
+tttg: c83/185 lr:0.000585 t:6.5s
+tttg: c84/185 lr:0.000577 t:6.6s
+tttg: c85/185 lr:0.000568 t:6.6s
+tttg: c86/185 lr:0.000560 t:6.7s
+tttg: c87/185 lr:0.000551 t:6.8s
+tttg: c88/185 lr:0.000543 t:6.9s
+tttg: c89/185 lr:0.000534 t:6.9s
+tttg: c90/185 lr:0.000526 t:7.0s
+tttg: c91/185 lr:0.000517 t:7.1s
+tttg: c92/185 lr:0.000509 t:7.2s
+tttg: c93/185 lr:0.000500 t:7.2s
+tttg: c94/185 lr:0.000491 t:7.3s
+tttg: c95/185 lr:0.000483 t:7.4s
+tttg: c96/185 lr:0.000474 t:7.5s
+tttg: c97/185 lr:0.000466 t:7.6s
+tttg: c98/185 lr:0.000457 t:7.6s
+tttg: c99/185 lr:0.000449 t:7.7s
+tttg: c100/185 lr:0.000440 t:7.8s
+tttg: c101/185 lr:0.000432 t:7.9s
+tttg: c102/185 lr:0.000423 t:7.9s
+tttg: c103/185 lr:0.000415 t:8.0s
+tttg: c104/185 lr:0.000407 t:8.1s
+tttg: c105/185 lr:0.000398 t:8.2s
+tttg: c106/185 lr:0.000390 t:8.2s
+tttg: c107/185 lr:0.000382 t:8.3s
+tttg: c108/185 lr:0.000373 t:8.4s
+tttg: c109/185 lr:0.000365 t:8.5s
+tttg: c110/185 lr:0.000357 t:8.6s
+tttg: c111/185 lr:0.000349 t:8.6s
+tttg: c112/185 lr:0.000341 t:8.7s
+tttg: c113/185 lr:0.000333 t:8.8s
+tttg: c114/185 lr:0.000325 t:8.9s
+tttg: c115/185 lr:0.000317 t:8.9s
+tttg: c116/185 lr:0.000309 t:9.0s
+tttg: c117/185 lr:0.000301 t:9.1s
+tttg: c118/185 lr:0.000293 t:9.2s
+tttg: c119/185 lr:0.000285 t:9.2s
+tttg: c120/185 lr:0.000278 t:9.3s
+tttg: c121/185 lr:0.000270 t:9.4s
+tttg: c122/185 lr:0.000262 t:9.5s
+tttg: c123/185 lr:0.000255 t:9.6s
+tttg: c124/185 lr:0.000248 t:9.6s
+tttg: c125/185 lr:0.000240 t:9.7s
+tttg: c126/185 lr:0.000233 t:9.8s
+tttg: c127/185 lr:0.000226 t:9.9s
+tttg: c128/185 lr:0.000219 t:9.9s
+tttg: c129/185 lr:0.000212 t:10.0s
+tttg: c130/185 lr:0.000205 t:10.1s
+tttg: c131/185 lr:0.000198 t:10.2s
+tttg: c132/185 lr:0.000191 t:10.2s
+tttg: c133/185 lr:0.000184 t:10.3s
+tttg: c134/185 lr:0.000178 t:10.4s
+tttg: c135/185 lr:0.000171 t:10.5s
+tttg: c136/185 lr:0.000165 t:10.6s
+tttg: c137/185 lr:0.000159 t:10.6s
+tttg: c138/185 lr:0.000153 t:10.7s
+tttg: c139/185 lr:0.000146 t:10.8s
+tttg: c140/185 lr:0.000140 t:10.9s
+tttg: c141/185 lr:0.000135 t:10.9s
+tttg: c142/185 lr:0.000129 t:11.0s
+tttg: c143/185 lr:0.000123 t:11.1s
+tttg: c144/185 lr:0.000118 t:11.2s
+tttg: c145/185 lr:0.000112 t:11.2s
+tttg: c146/185 lr:0.000107 t:11.3s
+tttg: c147/185 lr:0.000102 t:11.4s
+tttg: c148/185 lr:0.000096 t:11.5s
+tttg: c149/185 lr:0.000092 t:11.5s
+tttg: c150/185 lr:0.000087 t:11.6s
+tttg: c151/185 lr:0.000082 t:11.7s
+tttg: c152/185 lr:0.000077 t:11.8s
+tttg: c153/185 lr:0.000073 t:11.9s
+tttg: c154/185 lr:0.000068 t:11.9s
+tttg: c155/185 lr:0.000064 t:12.0s
+tttg: c156/185 lr:0.000060 t:12.1s
+tttg: c157/185 lr:0.000056 t:12.2s
+tttg: c158/185 lr:0.000052 t:12.2s
+tttg: c159/185 lr:0.000048 t:12.3s
+tttg: c160/185 lr:0.000045 t:12.4s
+tttg: c161/185 lr:0.000041 t:12.5s
+tttg: c162/185 lr:0.000038 t:12.5s
+tttg: c163/185 lr:0.000035 t:12.6s
+tttg: c164/185 lr:0.000032 t:12.7s
+tttg: c165/185 lr:0.000029 t:12.8s
+tttg: c166/185 lr:0.000026 t:12.9s
+tttg: c167/185 lr:0.000023 t:12.9s
+tttg: c168/185 lr:0.000021 t:13.0s
+tttg: c169/185 lr:0.000019 t:13.1s
+tttg: c170/185 lr:0.000016 t:13.2s
+tttg: c171/185 lr:0.000014 t:13.3s
+tttg: c172/185 lr:0.000012 t:13.3s
+tttg: c173/185 lr:0.000010 t:13.4s
+tttg: c174/185 lr:0.000009 t:13.5s
+tttg: c175/185 lr:0.000007 t:13.6s
+tttg: c176/185 lr:0.000006 t:13.6s
+tttg: c177/185 lr:0.000005 t:13.7s
+tttg: c178/185 lr:0.000004 t:13.8s
+tttg: c179/185 lr:0.000003 t:13.9s
+tttg: c180/185 lr:0.000002 t:14.0s
+tttg: c181/185 lr:0.000001 t:14.0s
+tttg: c182/185 lr:0.000001 t:14.1s
+tttg: c183/185 lr:0.000000 t:14.2s
+tttg: c184/185 lr:0.000000 t:14.3s
+ttpr: phase:2/3 t:378.3s
+ttp: b752/782 bl:2.3377 bb:1.0746 rl:2.2184 rb:1.0311 dl:3222-3283 gd:0
+ttpp: phase:3/3 pd:2448 gd:2000 t:395.5s
+tttg: c1/250 lr:0.001000 t:0.1s
+tttg: c2/250 lr:0.001000 t:0.2s
+tttg: c3/250 lr:0.001000 t:0.2s
+tttg: c4/250 lr:0.001000 t:0.3s
+tttg: c5/250 lr:0.000999 t:0.4s
+tttg: c6/250 lr:0.000999 t:0.5s
+tttg: c7/250 lr:0.000999 t:0.6s
+tttg: c8/250 lr:0.000998 t:0.6s
+tttg: c9/250 lr:0.000997 t:0.7s
+tttg: c10/250 lr:0.000997 t:0.8s
+tttg: c11/250 lr:0.000996 t:0.9s
+tttg: c12/250 lr:0.000995 t:0.9s
+tttg: c13/250 lr:0.000994 t:1.0s
+tttg: c14/250 lr:0.000993 t:1.1s
+tttg: c15/250 lr:0.000992 t:1.2s
+tttg: c16/250 lr:0.000991 t:1.2s
+tttg: c17/250 lr:0.000990 t:1.3s
+tttg: c18/250 lr:0.000989 t:1.4s
+tttg: c19/250 lr:0.000987 t:1.5s
+tttg: c20/250 lr:0.000986 t:1.6s
+tttg: c21/250 lr:0.000984 t:1.6s
+tttg: c22/250 lr:0.000983 t:1.7s
+tttg: c23/250 lr:0.000981 t:1.8s
+tttg: c24/250 lr:0.000979 t:1.9s
+tttg: c25/250 lr:0.000977 t:1.9s
+tttg: c26/250 lr:0.000975 t:2.0s
+tttg: c27/250 lr:0.000973 t:2.1s
+tttg: c28/250 lr:0.000971 t:2.2s
+tttg: c29/250 lr:0.000969 t:2.3s
+tttg: c30/250 lr:0.000967 t:2.3s
+tttg: c31/250 lr:0.000965 t:2.4s
+tttg: c32/250 lr:0.000962 t:2.5s
+tttg: c33/250 lr:0.000960 t:2.6s
+tttg: c34/250 lr:0.000957 t:2.7s
+tttg: c35/250 lr:0.000955 t:2.7s
+tttg: c36/250 lr:0.000952 t:2.8s
+tttg: c37/250 lr:0.000949 t:2.9s
+tttg: c38/250 lr:0.000947 t:3.0s
+tttg: c39/250 lr:0.000944 t:3.0s
+tttg: c40/250 lr:0.000941 t:3.1s
+tttg: c41/250 lr:0.000938 t:3.2s
+tttg: c42/250 lr:0.000935 t:3.3s
+tttg: c43/250 lr:0.000931 t:3.3s
+tttg: c44/250 lr:0.000928 t:3.4s
+tttg: c45/250 lr:0.000925 t:3.5s
+tttg: c46/250 lr:0.000922 t:3.6s
+tttg: c47/250 lr:0.000918 t:3.7s
+tttg: c48/250 lr:0.000915 t:3.7s
+tttg: c49/250 lr:0.000911 t:3.8s
+tttg: c50/250 lr:0.000907 t:3.9s
+tttg: c51/250 lr:0.000904 t:4.0s
+tttg: c52/250 lr:0.000900 t:4.0s
+tttg: c53/250 lr:0.000896 t:4.1s
+tttg: c54/250 lr:0.000892 t:4.2s
+tttg: c55/250 lr:0.000888 t:4.3s
+tttg: c56/250 lr:0.000884 t:4.4s
+tttg: c57/250 lr:0.000880 t:4.4s
+tttg: c58/250 lr:0.000876 t:4.5s
+tttg: c59/250 lr:0.000872 t:4.6s
+tttg: c60/250 lr:0.000868 t:4.7s
+tttg: c61/250 lr:0.000863 t:4.7s
+tttg: c62/250 lr:0.000859 t:4.8s
+tttg: c63/250 lr:0.000855 t:4.9s
+tttg: c64/250 lr:0.000850 t:5.0s
+tttg: c65/250 lr:0.000846 t:5.1s
+tttg: c66/250 lr:0.000841 t:5.1s
+tttg: c67/250 lr:0.000836 t:5.2s
+tttg: c68/250 lr:0.000832 t:5.3s
+tttg: c69/250 lr:0.000827 t:5.4s
+tttg: c70/250 lr:0.000822 t:5.4s
+tttg: c71/250 lr:0.000817 t:5.5s
+tttg: c72/250 lr:0.000812 t:5.6s
+tttg: c73/250 lr:0.000807 t:5.7s
+tttg: c74/250 lr:0.000803 t:5.8s
+tttg: c75/250 lr:0.000797 t:5.8s
+tttg: c76/250 lr:0.000792 t:5.9s
+tttg: c77/250 lr:0.000787 t:6.0s
+tttg: c78/250 lr:0.000782 t:6.1s
+tttg: c79/250 lr:0.000777 t:6.1s
+tttg: c80/250 lr:0.000772 t:6.2s
+tttg: c81/250 lr:0.000766 t:6.3s
+tttg: c82/250 lr:0.000761 t:6.4s
+tttg: c83/250 lr:0.000755 t:6.5s
+tttg: c84/250 lr:0.000750 t:6.5s
+tttg: c85/250 lr:0.000745 t:6.6s
+tttg: c86/250 lr:0.000739 t:6.7s
+tttg: c87/250 lr:0.000733 t:6.8s
+tttg: c88/250 lr:0.000728 t:6.8s
+tttg: c89/250 lr:0.000722 t:6.9s
+tttg: c90/250 lr:0.000717 t:7.0s
+tttg: c91/250 lr:0.000711 t:7.1s
+tttg: c92/250 lr:0.000705 t:7.2s
+tttg: c93/250 lr:0.000699 t:7.2s
+tttg: c94/250 lr:0.000694 t:7.3s
+tttg: c95/250 lr:0.000688 t:7.4s
+tttg: c96/250 lr:0.000682 t:7.5s
+tttg: c97/250 lr:0.000676 t:7.5s
+tttg: c98/250 lr:0.000670 t:7.6s
+tttg: c99/250 lr:0.000664 t:7.7s
+tttg: c100/250 lr:0.000658 t:7.8s
+tttg: c101/250 lr:0.000652 t:7.8s
+tttg: c102/250 lr:0.000646 t:7.9s
+tttg: c103/250 lr:0.000640 t:8.0s
+tttg: c104/250 lr:0.000634 t:8.1s
+tttg: c105/250 lr:0.000628 t:8.2s
+tttg: c106/250 lr:0.000622 t:8.3s
+tttg: c107/250 lr:0.000616 t:8.3s
+tttg: c108/250 lr:0.000610 t:8.4s
+tttg: c109/250 lr:0.000603 t:8.5s
+tttg: c110/250 lr:0.000597 t:8.6s
+tttg: c111/250 lr:0.000591 t:8.6s
+tttg: c112/250 lr:0.000585 t:8.7s
+tttg: c113/250 lr:0.000579 t:8.8s
+tttg: c114/250 lr:0.000572 t:8.9s
+tttg: c115/250 lr:0.000566 t:8.9s
+tttg: c116/250 lr:0.000560 t:9.0s
+tttg: c117/250 lr:0.000554 t:9.1s
+tttg: c118/250 lr:0.000547 t:9.2s
+tttg: c119/250 lr:0.000541 t:9.2s
+tttg: c120/250 lr:0.000535 t:9.3s
+tttg: c121/250 lr:0.000528 t:9.4s
+tttg: c122/250 lr:0.000522 t:9.5s
+tttg: c123/250 lr:0.000516 t:9.6s
+tttg: c124/250 lr:0.000509 t:9.6s
+tttg: c125/250 lr:0.000503 t:9.7s
+tttg: c126/250 lr:0.000497 t:9.8s
+tttg: c127/250 lr:0.000491 t:9.9s
+tttg: c128/250 lr:0.000484 t:9.9s
+tttg: c129/250 lr:0.000478 t:10.0s
+tttg: c130/250 lr:0.000472 t:10.1s
+tttg: c131/250 lr:0.000465 t:10.2s
+tttg: c132/250 lr:0.000459 t:10.3s
+tttg: c133/250 lr:0.000453 t:10.3s
+tttg: c134/250 lr:0.000446 t:10.4s
+tttg: c135/250 lr:0.000440 t:10.5s
+tttg: c136/250 lr:0.000434 t:10.6s
+tttg: c137/250 lr:0.000428 t:10.7s
+tttg: c138/250 lr:0.000421 t:10.8s
+tttg: c139/250 lr:0.000415 t:10.8s
+tttg: c140/250 lr:0.000409 t:10.9s
+tttg: c141/250 lr:0.000403 t:11.0s
+tttg: c142/250 lr:0.000397 t:11.1s
+tttg: c143/250 lr:0.000390 t:11.2s
+tttg: c144/250 lr:0.000384 t:11.3s
+tttg: c145/250 lr:0.000378 t:11.3s
+tttg: c146/250 lr:0.000372 t:11.4s
+tttg: c147/250 lr:0.000366 t:11.5s
+tttg: c148/250 lr:0.000360 t:11.6s
+tttg: c149/250 lr:0.000354 t:11.7s
+tttg: c150/250 lr:0.000348 t:11.7s
+tttg: c151/250 lr:0.000342 t:11.8s
+tttg: c152/250 lr:0.000336 t:11.9s
+tttg: c153/250 lr:0.000330 t:12.0s
+tttg: c154/250 lr:0.000324 t:12.1s
+tttg: c155/250 lr:0.000318 t:12.1s
+tttg: c156/250 lr:0.000312 t:12.2s
+tttg: c157/250 lr:0.000306 t:12.3s
+tttg: c158/250 lr:0.000301 t:12.4s
+tttg: c159/250 lr:0.000295 t:12.5s
+tttg: c160/250 lr:0.000289 t:17.8s
+tttg: c161/250 lr:0.000283 t:17.8s
+tttg: c162/250 lr:0.000278 t:17.9s
+tttg: c163/250 lr:0.000272 t:18.0s
+tttg: c164/250 lr:0.000267 t:18.1s
+tttg: c165/250 lr:0.000261 t:18.1s
+tttg: c166/250 lr:0.000255 t:18.2s
+tttg: c167/250 lr:0.000250 t:18.3s
+tttg: c168/250 lr:0.000245 t:18.4s
+tttg: c169/250 lr:0.000239 t:18.5s
+tttg: c170/250 lr:0.000234 t:18.5s
+tttg: c171/250 lr:0.000228 t:18.6s
+tttg: c172/250 lr:0.000223 t:18.7s
+tttg: c173/250 lr:0.000218 t:18.8s
+tttg: c174/250 lr:0.000213 t:18.8s
+tttg: c175/250 lr:0.000208 t:18.9s
+tttg: c176/250 lr:0.000203 t:19.0s
+tttg: c177/250 lr:0.000197 t:19.1s
+tttg: c178/250 lr:0.000193 t:19.1s
+tttg: c179/250 lr:0.000188 t:19.2s
+tttg: c180/250 lr:0.000183 t:19.3s
+tttg: c181/250 lr:0.000178 t:19.4s
+tttg: c182/250 lr:0.000173 t:19.5s
+tttg: c183/250 lr:0.000168 t:19.5s
+tttg: c184/250 lr:0.000164 t:19.6s
+tttg: c185/250 lr:0.000159 t:19.7s
+tttg: c186/250 lr:0.000154 t:19.8s
+tttg: c187/250 lr:0.000150 t:19.8s
+tttg: c188/250 lr:0.000145 t:19.9s
+tttg: c189/250 lr:0.000141 t:20.0s
+tttg: c190/250 lr:0.000137 t:20.1s
+tttg: c191/250 lr:0.000132 t:20.2s
+tttg: c192/250 lr:0.000128 t:20.2s
+tttg: c193/250 lr:0.000124 t:20.3s
+tttg: c194/250 lr:0.000120 t:20.4s
+tttg: c195/250 lr:0.000116 t:20.5s
+tttg: c196/250 lr:0.000112 t:20.6s
+tttg: c197/250 lr:0.000108 t:20.7s
+tttg: c198/250 lr:0.000104 t:20.7s
+tttg: c199/250 lr:0.000100 t:20.8s
+tttg: c200/250 lr:0.000096 t:20.9s
+tttg: c201/250 lr:0.000093 t:21.0s
+tttg: c202/250 lr:0.000089 t:21.1s
+tttg: c203/250 lr:0.000085 t:21.1s
+tttg: c204/250 lr:0.000082 t:21.2s
+tttg: c205/250 lr:0.000078 t:21.3s
+tttg: c206/250 lr:0.000075 t:21.4s
+tttg: c207/250 lr:0.000072 t:21.5s
+tttg: c208/250 lr:0.000069 t:21.5s
+tttg: c209/250 lr:0.000065 t:21.6s
+tttg: c210/250 lr:0.000062 t:21.7s
+tttg: c211/250 lr:0.000059 t:21.8s
+tttg: c212/250 lr:0.000056 t:21.8s
+tttg: c213/250 lr:0.000053 t:21.9s
+tttg: c214/250 lr:0.000051 t:22.0s
+tttg: c215/250 lr:0.000048 t:22.1s
+tttg: c216/250 lr:0.000045 t:22.2s
+tttg: c217/250 lr:0.000043 t:22.2s
+tttg: c218/250 lr:0.000040 t:22.3s
+tttg: c219/250 lr:0.000038 t:22.4s
+tttg: c220/250 lr:0.000035 t:22.5s
+tttg: c221/250 lr:0.000033 t:22.6s
+tttg: c222/250 lr:0.000031 t:22.6s
+tttg: c223/250 lr:0.000029 t:22.7s
+tttg: c224/250 lr:0.000027 t:22.8s
+tttg: c225/250 lr:0.000025 t:22.9s
+tttg: c226/250 lr:0.000023 t:23.0s
+tttg: c227/250 lr:0.000021 t:23.0s
+tttg: c228/250 lr:0.000019 t:23.1s
+tttg: c229/250 lr:0.000017 t:23.2s
+tttg: c230/250 lr:0.000016 t:23.3s
+tttg: c231/250 lr:0.000014 t:23.3s
+tttg: c232/250 lr:0.000013 t:23.4s
+tttg: c233/250 lr:0.000011 t:23.5s
+tttg: c234/250 lr:0.000010 t:23.6s
+tttg: c235/250 lr:0.000009 t:23.7s
+tttg: c236/250 lr:0.000008 t:23.7s
+tttg: c237/250 lr:0.000007 t:23.8s
+tttg: c238/250 lr:0.000006 t:23.9s
+tttg: c239/250 lr:0.000005 t:24.0s
+tttg: c240/250 lr:0.000004 t:24.1s
+tttg: c241/250 lr:0.000003 t:24.1s
+tttg: c242/250 lr:0.000003 t:24.2s
+tttg: c243/250 lr:0.000002 t:24.3s
+tttg: c244/250 lr:0.000001 t:24.4s
+tttg: c245/250 lr:0.000001 t:24.5s
+tttg: c246/250 lr:0.000001 t:24.5s
+tttg: c247/250 lr:0.000000 t:24.6s
+tttg: c248/250 lr:0.000000 t:24.7s
+tttg: c249/250 lr:0.000000 t:24.8s
+ttpr: phase:3/3 t:422.4s
+ttp: b739/782 bl:2.2918 bb:1.0225 rl:2.2272 rb:1.0300 dl:2619-2652 gd:1
+ttp: b732/782 bl:2.3706 bb:1.0917 rl:2.2414 rb:1.0361 dl:2416-2441 gd:1
+ttp: b726/782 bl:2.3357 bb:1.0389 rl:2.2494 rb:1.0364 dl:2254-2276 gd:1
+ttp: b714/782 bl:2.3086 bb:1.0226 rl:2.2536 rb:1.0354 dl:2018-2035 gd:1
+ttp: b710/782 bl:2.2283 bb:1.0432 rl:2.2520 rb:1.0359 dl:1952-1966 gd:1
+ttp: b703/782 bl:2.3402 bb:1.0295 rl:2.2570 rb:1.0355 dl:1859-1872 gd:1
+ttp: b694/782 bl:2.3094 bb:1.0561 rl:2.2597 rb:1.0365 dl:1758-1769 gd:1
+ttp: b687/782 bl:2.3114 bb:1.0555 rl:2.2621 rb:1.0374 dl:1685-1696 gd:1
+ttp: b675/782 bl:2.3647 bb:1.0575 rl:2.2664 rb:1.0383 dl:1578-1586 gd:1
+ttp: b667/782 bl:2.3622 bb:1.0678 rl:2.2702 rb:1.0395 dl:1514-1521 gd:1
+ttp: b662/782 bl:2.2957 bb:1.0262 rl:2.2711 rb:1.0390 dl:1480-1486 gd:1
+ttp: b656/782 bl:2.3252 bb:1.1092 rl:2.2729 rb:1.0413 dl:1439-1445 gd:1
+ttp: b642/782 bl:2.3211 bb:1.0392 rl:2.2744 rb:1.0412 dl:1349-1356 gd:1
+ttp: b634/782 bl:2.3833 bb:1.0492 rl:2.2776 rb:1.0415 dl:1302-1308 gd:1
+ttp: b627/782 bl:2.3764 bb:1.0699 rl:2.2803 rb:1.0422 dl:1266-1271 gd:1
+ttp: b619/782 bl:2.3278 bb:1.0615 rl:2.2816 rb:1.0427 dl:1221-1226 gd:1
+ttp: b612/782 bl:2.2362 bb:1.0131 rl:2.2805 rb:1.0420 dl:1186-1190 gd:1
+ttp: b607/782 bl:2.3505 bb:1.0515 rl:2.2821 rb:1.0422 dl:1164-1168 gd:1
+ttp: b598/782 bl:2.3572 bb:1.0661 rl:2.2838 rb:1.0428 dl:1124-1129 gd:1
+ttp: b590/782 bl:2.3092 bb:1.0581 rl:2.2843 rb:1.0431 dl:1089-1093 gd:1
+ttp: b582/782 bl:2.3467 bb:1.0308 rl:2.2855 rb:1.0428 dl:1056-1060 gd:1
+ttp: b570/782 bl:2.3553 bb:1.0550 rl:2.2869 rb:1.0431 dl:1010-1014 gd:1
+ttp: b563/782 bl:2.2628 bb:1.0168 rl:2.2864 rb:1.0426 dl:987-990 gd:1
+ttp: b556/782 bl:2.3831 bb:1.0714 rl:2.2881 rb:1.0431 dl:961-965 gd:1
+ttp: b549/782 bl:2.2580 bb:1.0209 rl:2.2876 rb:1.0427 dl:939-943 gd:1
+ttp: b542/782 bl:2.3233 bb:1.0375 rl:2.2882 rb:1.0426 dl:918-921 gd:1
+ttp: b535/782 bl:2.3773 bb:1.0311 rl:2.2895 rb:1.0425 dl:896-899 gd:1
+ttp: b527/782 bl:2.3460 bb:1.0297 rl:2.2904 rb:1.0423 dl:872-875 gd:1
+ttp: b519/782 bl:2.2959 bb:1.0415 rl:2.2904 rb:1.0423 dl:850-852 gd:1
+ttp: b513/782 bl:2.3653 bb:1.0384 rl:2.2915 rb:1.0422 dl:832-835 gd:1
+ttp: b505/782 bl:2.3271 bb:1.0642 rl:2.2919 rb:1.0425 dl:809-812 gd:1
+ttp: b499/782 bl:2.3369 bb:1.0552 rl:2.2925 rb:1.0426 dl:794-796 gd:1
+ttp: b491/782 bl:2.2817 bb:1.0292 rl:2.2924 rb:1.0425 dl:773-776 gd:1
+ttp: b480/782 bl:2.4364 bb:1.0848 rl:2.2940 rb:1.0430 dl:747-749 gd:1
+ttp: b472/782 bl:2.3833 bb:1.0818 rl:2.2950 rb:1.0434 dl:728-730 gd:1
+ttp: b463/782 bl:2.3176 bb:1.0429 rl:2.2953 rb:1.0434 dl:708-710 gd:1
+ttp: b455/782 bl:2.3037 bb:1.0382 rl:2.2954 rb:1.0434 dl:691-693 gd:1
+ttp: b447/782 bl:2.3278 bb:1.0694 rl:2.2957 rb:1.0436 dl:674-676 gd:1
+ttp: b439/782 bl:2.3269 bb:1.0383 rl:2.2960 rb:1.0436 dl:657-659 gd:1
+ttp: b431/782 bl:2.3738 bb:1.0531 rl:2.2967 rb:1.0437 dl:642-643 gd:1
+ttp: b423/782 bl:2.3075 bb:1.0528 rl:2.2968 rb:1.0437 dl:626-629 gd:1
+ttp: b415/782 bl:2.2853 bb:1.0585 rl:2.2967 rb:1.0439 dl:611-613 gd:1
+ttp: b407/782 bl:2.2672 bb:1.0379 rl:2.2965 rb:1.0438 dl:595-597 gd:1
+ttp: b399/782 bl:2.2881 bb:1.0327 rl:2.2964 rb:1.0437 dl:581-582 gd:1
+ttp: b391/782 bl:2.3104 bb:1.0642 rl:2.2965 rb:1.0439 dl:566-568 gd:1
+ttp: b383/782 bl:2.2749 bb:1.0430 rl:2.2963 rb:1.0439 dl:552-554 gd:1
+ttp: b375/782 bl:2.4053 bb:1.0728 rl:2.2972 rb:1.0441 dl:538-540 gd:1
+ttp: b367/782 bl:2.2933 bb:1.0822 rl:2.2971 rb:1.0444 dl:525-527 gd:1
+ttp: b361/782 bl:2.3550 bb:1.0994 rl:2.2975 rb:1.0447 dl:515-517 gd:1
+ttp: b351/782 bl:2.3518 bb:1.0766 rl:2.2979 rb:1.0450 dl:498-499 gd:1
+ttp: b343/782 bl:2.2226 bb:1.0460 rl:2.2974 rb:1.0450 dl:486-488 gd:1
+ttp: b335/782 bl:2.3669 bb:1.0722 rl:2.2978 rb:1.0451 dl:474-476 gd:1
+ttp: b327/782 bl:2.3355 bb:1.0859 rl:2.2981 rb:1.0454 dl:462-463 gd:1
+ttp: b319/782 bl:2.3908 bb:1.0781 rl:2.2986 rb:1.0456 dl:450-451 gd:1
+ttp: b311/782 bl:2.3476 bb:1.0821 rl:2.2989 rb:1.0458 dl:438-439 gd:1
+ttp: b303/782 bl:2.4007 bb:1.0950 rl:2.2995 rb:1.0461 dl:426-427 gd:1
+ttp: b295/782 bl:2.2624 bb:1.0614 rl:2.2993 rb:1.0461 dl:414-415 gd:1
+ttp: b287/782 bl:2.4041 bb:1.0953 rl:2.2998 rb:1.0464 dl:402-403 gd:1
+ttp: b279/782 bl:2.3091 bb:1.0911 rl:2.2999 rb:1.0466 dl:391-392 gd:1
+ttp: b271/782 bl:2.3708 bb:1.1229 rl:2.3002 rb:1.0470 dl:380-382 gd:1
+ttp: b263/782 bl:2.3876 bb:1.0800 rl:2.3006 rb:1.0471 dl:370-371 gd:1
+ttp: b255/782 bl:2.3664 bb:1.0913 rl:2.3009 rb:1.0473 dl:360-361 gd:1
+ttp: b247/782 bl:2.3514 bb:1.0945 rl:2.3011 rb:1.0475 dl:350-351 gd:1
+ttp: b239/782 bl:2.3847 bb:1.1073 rl:2.3015 rb:1.0478 dl:340-341 gd:1
+ttp: b231/782 bl:2.3059 bb:1.0832 rl:2.3015 rb:1.0479 dl:330-331 gd:1
+ttp: b223/782 bl:2.3307 bb:1.1253 rl:2.3016 rb:1.0482 dl:321-322 gd:1
+ttp: b215/782 bl:2.3910 bb:1.0960 rl:2.3020 rb:1.0484 dl:312-313 gd:1
+ttp: b207/782 bl:2.3619 bb:1.1351 rl:2.3022 rb:1.0487 dl:303-304 gd:1
+ttp: b199/782 bl:2.4269 bb:1.1419 rl:2.3027 rb:1.0490 dl:295-296 gd:1
+ttp: b191/782 bl:2.4176 bb:1.0999 rl:2.3031 rb:1.0492 dl:285-286 gd:1
+ttp: b184/782 bl:2.3898 bb:1.1266 rl:2.3034 rb:1.0494 dl:278-279 gd:1
+ttp: b176/782 bl:2.3213 bb:1.1274 rl:2.3034 rb:1.0497 dl:270-271 gd:1
+ttp: b168/782 bl:2.4485 bb:1.1846 rl:2.3039 rb:1.0501 dl:263-263 gd:1
+ttp: b160/782 bl:2.3843 bb:1.1134 rl:2.3041 rb:1.0503 dl:255-255 gd:1
+ttp: b151/782 bl:2.4650 bb:1.1395 rl:2.3046 rb:1.0505 dl:246-247 gd:1
+ttp: b143/782 bl:2.4181 bb:1.1718 rl:2.3049 rb:1.0509 dl:238-239 gd:1
+ttp: b135/782 bl:2.4309 bb:1.1780 rl:2.3053 rb:1.0512 dl:231-232 gd:1
+ttp: b127/782 bl:2.4731 bb:1.1862 rl:2.3057 rb:1.0515 dl:223-224 gd:1
+ttp: b119/782 bl:2.3722 bb:1.1550 rl:2.3059 rb:1.0518 dl:216-217 gd:1
+ttp: b112/782 bl:2.4768 bb:1.1822 rl:2.3063 rb:1.0521 dl:210-210 gd:1
+ttp: b102/782 bl:2.5808 bb:1.1962 rl:2.3070 rb:1.0524 dl:201-202 gd:1
+ttp: b95/782 bl:2.3292 bb:1.1387 rl:2.3070 rb:1.0526 dl:194-195 gd:1
+ttp: b86/782 bl:2.4588 bb:1.1344 rl:2.3073 rb:1.0528 dl:186-187 gd:1
+ttp: b78/782 bl:2.5458 bb:1.1919 rl:2.3079 rb:1.0531 dl:179-180 gd:1
+ttp: b71/782 bl:2.4640 bb:1.1776 rl:2.3082 rb:1.0533 dl:173-173 gd:1
+ttp: b63/782 bl:2.5260 bb:1.2049 rl:2.3086 rb:1.0536 dl:166-166 gd:1
+ttp: b54/782 bl:2.4709 bb:1.2121 rl:2.3089 rb:1.0539 dl:157-158 gd:1
+ttp: b46/782 bl:2.5476 bb:1.2165 rl:2.3093 rb:1.0541 dl:149-150 gd:1
+ttp: b39/782 bl:2.4391 bb:1.1807 rl:2.3095 rb:1.0543 dl:142-143 gd:1
+ttp: b30/782 bl:2.5990 bb:1.2672 rl:2.3100 rb:1.0547 dl:133-134 gd:1
+ttp: b22/782 bl:2.5554 bb:1.1962 rl:2.3103 rb:1.0549 dl:124-126 gd:1
+ttp: b15/782 bl:2.6438 bb:1.2278 rl:2.3108 rb:1.0551 dl:115-117 gd:1
+ttp: b7/782 bl:2.7540 bb:1.2395 rl:2.3113 rb:1.0553 dl:101-103 gd:1
+quantized_ttt_phased val_loss:2.32116807 val_bpb:1.06068323 eval_time:533520ms
+total_eval_time:533.5s