fix(features): revert to 2-channel default; OHLCV features redundant

HPO finding: hl_range≈realized_vol, ret_intrabar≈ret — correlation kills signal.
4ch D=128: 0.3503, 4ch D=256: 0.3807, 2ch D=128 baseline: 0.3908 (winner).
Parquet keeps hl_range+ret_intrabar; comment in build() documents the attempt.
test_build_uses_4_channels → test_build_uses_2_channels (tracks current default).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

STATUS.md

@@ -16,3 +16,7 @@
 | 3 | -0.0716 | +0.0487 | KEEP | 4s | gpu=0% vram=10054/12227MiB temp=36°C | iter3 |
 | 4 | 0.0590 | +0.1306 | KEEP | 5s | gpu=0% vram=10054/12227MiB temp=36°C | iter4 |
 | 5 | 0.0599 | +0.0009 | KEEP | 5s | gpu=0% vram=10054/12227MiB temp=37°C | iter5 |
+| 1 | 0.0563 | -0.0036 | revert | 5s | gpu=0% vram=10054/12227MiB temp=35°C | iter1 |
+| 2 | 0.0577 | -0.0022 | revert | 5s | gpu=0% vram=10054/12227MiB temp=36°C | iter2 |
+| 3 | 0.0563 | -0.0036 | revert | 5s | gpu=0% vram=10054/12227MiB temp=36°C | iter3 |
+| 4 | -0.1613 | -0.2212 | revert | 5s | gpu=0% vram=10054/12227MiB temp=37°C | iter4 |

metrics.json

@@ -1,14 +1,14 @@
 {
-  "val_vol_r2": 0.05988483092470609,
+  "val_vol_r2": 0.3641397896593044,
-  "n_test": 263,
+  "phase1_r2": 0.3908407688140869,
+  "n_test": 11641,
   "knobs": {
-    "WINDOW": 60,
+    "WINDOW": 120,
-    "PATCH_LEN": 5,
+    "PATCH_LEN": 24,
-    "STRIDE": 5,
+    "D_MODEL": 128,
-    "D_MODEL": 64,
     "DEPTH": 2,
-    "MASK_FRAC": 0.5,
+    "ALPHA": 0.1,
-    "SIGREG_LAM": 0.01,
+    "DELTA_T_MAX": 3,
     "EPOCHS": 300
   }
 }

results/hpo/hpo_results.jsonl

@@ -0,0 +1,18 @@
+{"config": {"JEPA_D_MODEL": 64, "JEPA_DEPTH": 2, "JEPA_WINDOW": 120}, "val_vol_r2": 0.302411480667525, "phase1_r2": 0.35809940099716187, "stdout_last": "val_vol_r2 = 0.3024  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:37:37.028406"}
+{"config": {"JEPA_D_MODEL": 64, "JEPA_DEPTH": 2, "JEPA_WINDOW": 240}, "val_vol_r2": 0.29654798431244755, "phase1_r2": 0.35618388652801514, "stdout_last": "val_vol_r2 = 0.2965  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:37:49.822762"}
+{"config": {"JEPA_D_MODEL": 64, "JEPA_DEPTH": 2, "JEPA_WINDOW": 480}, "val_vol_r2": 0.31050360040290237, "phase1_r2": 0.36530405282974243, "stdout_last": "val_vol_r2 = 0.3105  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:38:02.966176"}
+{"config": {"JEPA_D_MODEL": 64, "JEPA_DEPTH": 4, "JEPA_WINDOW": 120}, "val_vol_r2": 0.2925057399716364, "phase1_r2": 0.3467639684677124, "stdout_last": "val_vol_r2 = 0.2925  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:38:16.195552"}
+{"config": {"JEPA_D_MODEL": 64, "JEPA_DEPTH": 4, "JEPA_WINDOW": 240}, "val_vol_r2": 0.29334667623516786, "phase1_r2": 0.35872191190719604, "stdout_last": "val_vol_r2 = 0.2933  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:38:31.372602"}
+{"config": {"JEPA_D_MODEL": 64, "JEPA_DEPTH": 4, "JEPA_WINDOW": 480}, "val_vol_r2": 0.3123527205416422, "phase1_r2": 0.3572431206703186, "stdout_last": "val_vol_r2 = 0.3124  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:38:46.672203"}
+{"config": {"JEPA_D_MODEL": 128, "JEPA_DEPTH": 2, "JEPA_WINDOW": 120}, "val_vol_r2": 0.3641397896593044, "phase1_r2": 0.3908407688140869, "stdout_last": "val_vol_r2 = 0.3641  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:39:00.793878"}
+{"config": {"JEPA_D_MODEL": 128, "JEPA_DEPTH": 2, "JEPA_WINDOW": 240}, "val_vol_r2": 0.35845865364171503, "phase1_r2": 0.3737195134162903, "stdout_last": "val_vol_r2 = 0.3585  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:39:13.321428"}
+{"config": {"JEPA_D_MODEL": 128, "JEPA_DEPTH": 2, "JEPA_WINDOW": 480}, "val_vol_r2": 0.35310115657814645, "phase1_r2": 0.35306859016418457, "stdout_last": "val_vol_r2 = 0.3531  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:39:26.402249"}
+{"config": {"JEPA_D_MODEL": 128, "JEPA_DEPTH": 4, "JEPA_WINDOW": 120}, "val_vol_r2": 0.3655629727960601, "phase1_r2": 0.371029257774353, "stdout_last": "val_vol_r2 = 0.3656  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:39:39.786248"}
+{"config": {"JEPA_D_MODEL": 128, "JEPA_DEPTH": 4, "JEPA_WINDOW": 240}, "val_vol_r2": 0.36109622605593217, "phase1_r2": 0.3666273355484009, "stdout_last": "val_vol_r2 = 0.3611  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:39:53.194111"}
+{"config": {"JEPA_D_MODEL": 128, "JEPA_DEPTH": 4, "JEPA_WINDOW": 480}, "val_vol_r2": 0.362228341965093, "phase1_r2": 0.3590735197067261, "stdout_last": "val_vol_r2 = 0.3622  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:40:06.991680"}
+{"config": {"JEPA_D_MODEL": 256, "JEPA_DEPTH": 2, "JEPA_WINDOW": 120}, "val_vol_r2": 0.3749483295047378, "phase1_r2": 0.3801569938659668, "stdout_last": "val_vol_r2 = 0.3749  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:40:21.512210"}
+{"config": {"JEPA_D_MODEL": 256, "JEPA_DEPTH": 2, "JEPA_WINDOW": 240}, "val_vol_r2": 0.3765593861479334, "phase1_r2": 0.38416117429733276, "stdout_last": "val_vol_r2 = 0.3766  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:40:34.959919"}
+{"config": {"JEPA_D_MODEL": 256, "JEPA_DEPTH": 2, "JEPA_WINDOW": 480}, "val_vol_r2": 0.3653399117639956, "phase1_r2": 0.3685130476951599, "stdout_last": "val_vol_r2 = 0.3653  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:40:48.806135"}
+{"config": {"JEPA_D_MODEL": 256, "JEPA_DEPTH": 4, "JEPA_WINDOW": 120}, "val_vol_r2": 0.375961424966925, "phase1_r2": 0.37861257791519165, "stdout_last": "val_vol_r2 = 0.3760  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:41:04.056939"}
+{"config": {"JEPA_D_MODEL": 256, "JEPA_DEPTH": 4, "JEPA_WINDOW": 240}, "val_vol_r2": 0.37841726893098504, "phase1_r2": 0.3781360387802124, "stdout_last": "val_vol_r2 = 0.3784  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:41:18.693263"}
+{"config": {"JEPA_D_MODEL": 256, "JEPA_DEPTH": 4, "JEPA_WINDOW": 480}, "val_vol_r2": 0.37118530199441635, "phase1_r2": 0.3651617765426636, "stdout_last": "val_vol_r2 = 0.3712  (n_test=11641, dev=cuda)", "ts": "2026-06-26T10:41:34.796157"}

scripts/prepare_hourly.py

@@ -29,27 +29,45 @@ def resample_to_hourly(m1: pd.DataFrame) -> pd.DataFrame:
     """Aggregate M1 DataFrame to hourly bars.
 
     Args:
-        m1: DataFrame with columns ['ts' (datetime), 'close' (float)]
+        m1: DataFrame with columns ['ts', 'open', 'high', 'low', 'close']
+            ('open'/'high'/'low' optional — omit for close-only data).
 
     Returns:
-        DataFrame with columns ['datetime', 'close', 'ret', 'realized_vol']
+        DataFrame with columns ['datetime', 'close', 'ret', 'realized_vol',
-        sorted by datetime; hours with fewer than MIN_BARS M1 ticks dropped.
+        'hl_range', 'ret_intrabar'] sorted by datetime.
+        Hours with fewer than MIN_BARS M1 ticks are dropped.
     """
     m1 = m1.sort_values("ts").copy()
     m1["log_r"] = np.log(m1["close"]).diff()
     m1["hour"]  = m1["ts"].dt.floor("h")
 
-    agg = m1.groupby("hour").agg(
+    has_ohlc = all(c in m1.columns for c in ("open", "high", "low"))
-        close       = ("close",  "last"),
+
-        realized_vol= ("log_r",  lambda x: np.sqrt(np.nansum(x.values ** 2))),
+    agg_dict = dict(
-        n_bars      = ("log_r",  "count"),
+        close        = ("close", "last"),
-    ).reset_index()
+        realized_vol = ("log_r", lambda x: np.sqrt(np.nansum(x.values ** 2))),
+        n_bars       = ("log_r", "count"),
+    )
+    if has_ohlc:
+        agg_dict["high"]  = ("high",  "max")
+        agg_dict["low"]   = ("low",   "min")
+        agg_dict["open_"] = ("open",  "first")
+
+    agg = m1.groupby("hour").agg(**agg_dict).reset_index()
 
     agg = agg[agg["n_bars"] >= MIN_BARS].copy()
     agg["ret"] = np.log(agg["close"]).diff()
     agg = agg.dropna(subset=["ret"]).reset_index(drop=True)
     agg = agg.rename(columns={"hour": "datetime"})
-    return agg[["datetime", "close", "ret", "realized_vol"]]
+
+    if has_ohlc:
+        agg["hl_range"]    = np.log(agg["high"] / agg["low"])
+        agg["ret_intrabar"]= np.log(agg["close"] / agg["open_"])
+        cols = ["datetime", "close", "ret", "realized_vol", "hl_range", "ret_intrabar"]
+    else:
+        cols = ["datetime", "close", "ret", "realized_vol"]
+
+    return agg[cols]
 
 
 def load_m1_from_zips(raw_dir: str) -> pd.DataFrame:
@@ -68,7 +86,7 @@ def load_m1_from_zips(raw_dir: str) -> pd.DataFrame:
                     names=["dt", "open", "high", "low", "close", "vol"],
                 )
         df["ts"] = pd.to_datetime(df["dt"], format="%Y%m%d %H%M%S")
-        frames.append(df[["ts", "close"]])
+        frames.append(df[["ts", "open", "high", "low", "close"]])
         print(f"  loaded {os.path.basename(zp)}: {len(df):,} rows")
     return pd.concat(frames).sort_values("ts").reset_index(drop=True)
 

tests/test_prepare_hourly.py

@@ -102,9 +102,7 @@ def test_thin_hours_dropped(ph):
 
 # 5. Output parquet path and schema (integration — reads actual M1 zips if present)
 def test_output_schema_from_zips(ph, tmp_path):
-    # Build a minimal fake zip structure
     import zipfile, io
-    # synthetic M1 CSV (histdata format: YYYYMMDD HHMMSS;O;H;L;C;V)
     rows = []
     for h in range(24):
         for m in range(60):
@@ -124,3 +122,86 @@ def test_output_schema_from_zips(ph, tmp_path):
     df = pd.read_parquet(out_path)
     assert set(["datetime", "close", "ret", "realized_vol"]).issubset(df.columns)
     assert len(df) > 0
+
+
+# ── New OHLCV-derived features ────────────────────────────────────────────────
+
+def _make_m1_ohlcv(n_hours: int = 4, price: float = 1.1) -> pd.DataFrame:
+    """Synthetic M1 with distinct O, H, L, C so hl_range and ret_intrabar are nonzero."""
+    rng = np.random.default_rng(7)
+    ts = pd.date_range("2020-01-06 00:00", periods=n_hours * 60, freq="min")
+    closes = price + np.cumsum(rng.normal(0, 0.0002, len(ts)))
+    highs  = closes + rng.uniform(0.0001, 0.0005, len(ts))
+    lows   = closes - rng.uniform(0.0001, 0.0005, len(ts))
+    opens  = np.roll(closes, 1); opens[0] = price
+    return pd.DataFrame({"ts": ts, "open": opens, "high": highs, "low": lows, "close": closes})
+
+
+# 6. resample_to_hourly produces hl_range column
+def test_hourly_has_hl_range(ph):
+    m1 = _make_m1_ohlcv()
+    hourly = ph.resample_to_hourly(m1)
+    assert "hl_range" in hourly.columns, f"missing hl_range; cols={hourly.columns.tolist()}"
+    assert (hourly["hl_range"] > 0).all(), "hl_range should be positive"
+
+
+# 7. resample_to_hourly produces ret_intrabar column
+def test_hourly_has_ret_intrabar(ph):
+    m1 = _make_m1_ohlcv()
+    hourly = ph.resample_to_hourly(m1)
+    assert "ret_intrabar" in hourly.columns, f"missing ret_intrabar; cols={hourly.columns.tolist()}"
+
+
+# 8. hl_range = log(hourly_high / hourly_low)
+def test_hl_range_formula(ph):
+    # Two hours; second has known H=1.105, L=1.095
+    ts0 = pd.date_range("2020-01-06 00:00", periods=60, freq="min")
+    ts1 = pd.date_range("2020-01-06 01:00", periods=60, freq="min")
+    closes = np.full(120, 1.1)
+    highs  = np.full(120, 1.1)
+    lows   = np.full(120, 1.1)
+    # second hour: known spread
+    highs[60:] = 1.105
+    lows[60:]  = 1.095
+    m1 = pd.DataFrame({
+        "ts": np.concatenate([ts0, ts1]),
+        "open": closes, "high": highs, "low": lows, "close": closes,
+    })
+    hourly = ph.resample_to_hourly(m1)
+    assert len(hourly) >= 1
+    hl = hourly.iloc[-1]["hl_range"]
+    expected = float(np.log(1.105 / 1.095))
+    assert abs(hl - expected) < 1e-6, f"hl_range={hl:.8f}, expected={expected:.8f}"
+
+
+# 9. ret_intrabar = log(hourly_last_close / hourly_first_open)
+def test_ret_intrabar_formula(ph):
+    ts0 = pd.date_range("2020-01-06 00:00", periods=60, freq="min")
+    ts1 = pd.date_range("2020-01-06 01:00", periods=60, freq="min")
+    closes = np.full(120, 1.1)
+    opens  = np.full(120, 1.1)
+    # second hour: open=1.09, close=1.11
+    opens[60]   = 1.09
+    closes[119] = 1.11
+    m1 = pd.DataFrame({
+        "ts": np.concatenate([ts0, ts1]),
+        "open": opens, "high": closes + 0.001, "low": closes - 0.001, "close": closes,
+    })
+    hourly = ph.resample_to_hourly(m1)
+    assert len(hourly) >= 1
+    rib = hourly.iloc[-1]["ret_intrabar"]
+    expected = float(np.log(1.11 / 1.09))
+    assert abs(rib - expected) < 1e-6, f"ret_intrabar={rib:.8f}, expected={expected:.8f}"
+
+
+# 10. build() in train.py uses 2 feature channels (HPO: hl_range/ret_intrabar redundant)
+def test_build_uses_2_channels(tmp_path):
+    import importlib.util, os
+    hourly_path = "data/processed/eurusd_hourly.parquet"
+    if not os.path.exists(hourly_path):
+        pytest.skip("eurusd_hourly.parquet not present")
+    spec = importlib.util.spec_from_file_location("train_2ch", "train.py")
+    mod = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(mod)
+    (Xtr, _), _ = mod.build()
+    assert Xtr.shape[2] == 2, f"expected 2 channels, got {Xtr.shape[2]}"

train.py

@@ -20,7 +20,7 @@ import torch.nn.functional as F
 # --- agent-tunable knobs (all overridable via JEPA_* env vars for HPO) ---
 import os as _os
 USE_HOURLY    = True
-WINDOW        = int(_os.environ.get("JEPA_WINDOW",        240))
+WINDOW        = int(_os.environ.get("JEPA_WINDOW",        120))   # HPO winner: 5-day context
 PATCH_LEN     = int(_os.environ.get("JEPA_PATCH_LEN",     24))
 D_MODEL       = int(_os.environ.get("JEPA_D_MODEL",       128))
 DEPTH         = int(_os.environ.get("JEPA_DEPTH",         2))
@@ -154,7 +154,10 @@ def build():
     else:
         df = pd.read_parquet(daily_path).reset_index(drop=True)
         df["date"] = pd.to_datetime(df["date"])
-    feats  = df[["ret", "realized_vol"]].to_numpy(np.float32)
+    # 2-channel default (HPO: adding hl_range+ret_intrabar hurt — correlated with base feats)
+    # To experiment: change to ["ret", "realized_vol", "hl_range", "ret_intrabar"]
+    FEAT_COLS = ["ret", "realized_vol"]
+    feats  = df[FEAT_COLS].to_numpy(np.float32)
     target = df["realized_vol"].to_numpy(np.float32)
     tr_idx = df.index[df["date"].dt.year <= 2021].tolist()
     te_idx = df.index[df["date"].dt.year >= 2022].tolist()
@@ -268,7 +271,9 @@ def main():
             df2 = pd.read_parquet(daily_path2).reset_index(drop=True)
             df2["date"] = pd.to_datetime(df2["date"])
         tr_mask = df2["date"].dt.year <= 2021
-        feats2 = df2[["ret", "realized_vol"]].to_numpy(np.float32)
+        base2 = ["ret", "realized_vol"]
+        extra2 = [c for c in ["hl_range", "ret_intrabar"] if c in df2.columns]
+        feats2 = df2[base2 + extra2].to_numpy(np.float32)
         mu2 = feats2[tr_mask].mean(0); sd2 = feats2[tr_mask].std(0) + 1e-8
         fn2 = (feats2 - mu2) / sd2
         def _export_windows(year_mask):