E1 evaluation progress 500/500

evaluation/progress.json

@@ -1,9 +1,9 @@
 {
   "checkpoint_step": 30,
-  "correct": 317,
-  "evaluation_seconds": 6557.741287099,
+  "correct": 321,
+  "evaluation_seconds": 6657.714269455001,
   "heldout_n": 500,
-  "next_index": 496,
+  "next_index": 500,
   "schema_version": "e1-evaluation-progress-v1",
   "trace": [
     {
@@ -3477,8 +3477,36 @@
       "index": 495,
       "prediction": 200,
       "target": 200
+    },
+    {
+      "completion_sha256": "0bac0c818c93f62d84411c5851e0509ed7c7def6d2ca4b1baec7e2d588e3beca",
+      "correct": true,
+      "index": 496,
+      "prediction": 38,
+      "target": 38
+    },
+    {
+      "completion_sha256": "23db433923fbab2ffb92255c579131e478d3ceea87efc73e4668dabd530c1085",
+      "correct": true,
+      "index": 497,
+      "prediction": 112,
+      "target": 112
+    },
+    {
+      "completion_sha256": "c23aa32891b238d32f7c2763a0d023ce8f5066baf05afa15cd8e29546b64b57c",
+      "correct": true,
+      "index": 498,
+      "prediction": 40,
+      "target": 40
+    },
+    {
+      "completion_sha256": "84ddaee0a564c41781b76f35fde00ac98da75fda089168afc804815b146d5c17",
+      "correct": true,
+      "index": 499,
+      "prediction": 10,
+      "target": 10
     }
   ],
   "unit_fingerprint": "60e5b791330c4f442831c701fb1d7fc61f84a0d1eb741fb3fc2ec3a9cb3f7544",
-  "updated_at": "2026-07-18T17:41:13+00:00"
+  "updated_at": "2026-07-18T17:42:54+00:00"
 }