diff --git "a/src/lib/leaderboard.json" "b/src/lib/leaderboard.json"
--- "a/src/lib/leaderboard.json"
+++ "b/src/lib/leaderboard.json"
@@ -702,6 +702,60 @@
       },
       "relation": "first_better"
     },
+    "gemma-3-270m__gpt2-medium-355m": {
+      "ci": [
+        4.567690555799388,
+        6.414205704409783
+      ],
+      "difference": 5.490700049071364,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "gemma-3-270m__limen-0-2b": {
+      "ci": [
+        1.346747725245972,
+        3.162401660917923
+      ],
+      "difference": 2.257917152787524,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
     "gemma-3-270m__mobilellm-r1-140m-base": {
       "ci": [
         6.7285212269252535,
@@ -1188,6 +1242,33 @@
       },
       "relation": "first_better"
     },
+    "gpt-x2-125m__gpt2-medium-355m": {
+      "ci": [
+        1.2408356393255757,
+        2.9406022879415636
+      ],
+      "difference": 2.094977644097771,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
     "gpt-x2-125m__mobilellm-r1-140m-base": {
       "ci": [
         3.4001537890801874,
@@ -1647,66 +1728,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__atom-3-4m": {
-      "ci": [
-        27.58893756755036,
-        30.042187485115143
-      ],
-      "difference": 28.789996315485123,
-      "matched_samples": {
-        "arc_challenge": 1172,
-        "arc_easy": 2376,
-        "blimp:Anaphor agreement": 2000,
-        "blimp:Argument structure": 9000,
-        "blimp:Binding": 7000,
-        "blimp:Control / raising": 5000,
-        "blimp:Determiner-noun agreement": 8000,
-        "blimp:Ellipsis": 2000,
-        "blimp:Filler-gap": 10000,
-        "blimp:Irregular forms": 2000,
-        "blimp:Island effects": 8000,
-        "blimp:NPI licensing": 7000,
-        "blimp:Quantifiers": 4000,
-        "blimp:Subject-verb agreement": 6000,
-        "commonsense_qa": 1221,
-        "hellaswag": 10042,
-        "piqa": 1838
-      },
-      "relation": "first_better"
-    },
-    "lfm2-350m__baguettotron": {
-      "ci": [
-        12.443170128806557,
-        14.63607099576427
-      ],
-      "difference": 13.526740651870819,
-      "matched_samples": {
-        "arc_challenge": 1172,
-        "arc_easy": 2376,
-        "blimp:Anaphor agreement": 2000,
-        "blimp:Argument structure": 9000,
-        "blimp:Binding": 7000,
-        "blimp:Control / raising": 5000,
-        "blimp:Determiner-noun agreement": 8000,
-        "blimp:Ellipsis": 2000,
-        "blimp:Filler-gap": 10000,
-        "blimp:Irregular forms": 2000,
-        "blimp:Island effects": 8000,
-        "blimp:NPI licensing": 7000,
-        "blimp:Quantifiers": 4000,
-        "blimp:Subject-verb agreement": 6000,
-        "commonsense_qa": 1221,
-        "hellaswag": 10042,
-        "piqa": 1838
-      },
-      "relation": "first_better"
-    },
-    "lfm2-350m__falcon-h1-tiny-r-90m": {
+    "gpt2-medium-355m__atom-3-4m": {
       "ci": [
-        21.180647286515022,
-        23.545436928921546
+        17.993914360231898,
+        20.11495959677222
       ],
-      "difference": 22.34695811824909,
+      "difference": 19.05198128734326,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1728,12 +1755,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__gemma-3-270m": {
+    "gpt2-medium-355m__baguettotron": {
       "ci": [
-        3.2295084969038235,
-        5.224620472855046
+        2.7853069505419072,
+        4.8012688019468905
       ],
-      "difference": 4.247314979070493,
+      "difference": 3.788725623728961,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1755,12 +1782,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__gpt-s-1-4m": {
+    "gpt2-medium-355m__falcon-h1-tiny-r-90m": {
       "ci": [
-        29.546430185030548,
-        32.048984499243076
+        11.59984492132836,
+        13.659119500473565
       ],
-      "difference": 30.822639445627008,
+      "difference": 12.608943090107232,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1782,12 +1809,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__gpt-s2-5m": {
+    "gpt2-medium-355m__gpt-s-1-4m": {
       "ci": [
-        22.692921220894892,
-        25.060730091228283
+        19.901446108663194,
+        22.191881707503878
       ],
-      "difference": 23.858188709910568,
+      "difference": 21.084624417485145,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1809,12 +1836,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__gpt-x2-125m": {
+    "gpt2-medium-355m__gpt-s2-5m": {
       "ci": [
-        6.543548887485459,
-        8.719161211825703
+        13.110875827961552,
+        15.153969564470772
       ],
-      "difference": 7.643037384044087,
+      "difference": 14.120173681768705,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1836,12 +1863,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__gpt2-124m": {
+    "gpt2-medium-355m__gpt2-124m": {
       "ci": [
-        14.143222563888733,
-        16.4118593800478
+        4.700135778835568,
+        6.333309904394746
       ],
-      "difference": 15.266974006372491,
+      "difference": 5.528958978230634,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1863,12 +1890,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__mobilellm-r1-140m-base": {
+    "gpt2-medium-355m__mobilellm-r1-140m-base": {
       "ci": [
-        10.873284350857205,
-        13.02640742452202
+        1.2852382146811867,
+        3.19745496440504
       ],
-      "difference": 11.955807929644676,
+      "difference": 2.217792901502818,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1890,12 +1917,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__nanowhale-100m-base": {
+    "gpt2-medium-355m__nanowhale-100m-base": {
       "ci": [
-        24.094314926003207,
-        26.46428926562647
+        14.524544922835736,
+        16.532400611219693
       ],
-      "difference": 25.269477462631208,
+      "difference": 15.531462434489349,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1917,12 +1944,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__pythia-160m": {
+    "gpt2-medium-355m__pythia-160m": {
       "ci": [
-        21.76448313300386,
-        24.12912979103644
+        12.147837559283435,
+        14.24955981177643
       ],
-      "difference": 22.920771056258122,
+      "difference": 13.182756028116266,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1944,12 +1971,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__pythia-31m": {
+    "gpt2-medium-355m__pythia-31m": {
       "ci": [
-        24.947883218281085,
-        27.411184938190967
+        15.388049395302364,
+        17.515758670665342
       ],
-      "difference": 26.185999797644175,
+      "difference": 16.44798476950232,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -1971,39 +1998,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__qwen2-5-0-5b": {
-      "ci": [
-        -0.7937443045238336,
-        1.2109056554752804
-      ],
-      "difference": 0.19496537145225148,
-      "matched_samples": {
-        "arc_challenge": 1172,
-        "arc_easy": 2376,
-        "blimp:Anaphor agreement": 2000,
-        "blimp:Argument structure": 9000,
-        "blimp:Binding": 7000,
-        "blimp:Control / raising": 5000,
-        "blimp:Determiner-noun agreement": 8000,
-        "blimp:Ellipsis": 2000,
-        "blimp:Filler-gap": 10000,
-        "blimp:Irregular forms": 2000,
-        "blimp:Island effects": 8000,
-        "blimp:NPI licensing": 7000,
-        "blimp:Quantifiers": 4000,
-        "blimp:Subject-verb agreement": 6000,
-        "commonsense_qa": 1221,
-        "hellaswag": 10042,
-        "piqa": 1838
-      },
-      "relation": "tie"
-    },
-    "lfm2-350m__slm-10m": {
+    "gpt2-medium-355m__slm-10m": {
       "ci": [
-        21.736389241473272,
-        24.094793643932555
+        12.13887142432881,
+        14.182253685153766
       ],
-      "difference": 22.887298318807428,
+      "difference": 13.149283290665572,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2025,12 +2025,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__smollm2-135m": {
+    "gpt2-medium-355m__supra-50m-base": {
       "ci": [
-        4.2639180400644365,
-        6.304742227756106
+        5.190257140204221,
+        7.02033532538955
       ],
-      "difference": 5.305004387140445,
+      "difference": 6.1165851135639056,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2052,12 +2052,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__supra-50m-base": {
+    "gpt2-medium-355m__veyra2-apricot-50m-base": {
       "ci": [
-        14.717188310254356,
-        16.936606168548764
+        6.391542401843375,
+        8.29118001567598
       ],
-      "difference": 15.854600141705763,
+      "difference": 7.336030953801166,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2079,12 +2079,12 @@
       },
       "relation": "first_better"
     },
-    "lfm2-350m__veyra2-apricot-50m-base": {
+    "lfm2-350m__atom-3-4m": {
       "ci": [
-        15.922087105664474,
-        18.21523002545234
+        27.58893756755036,
+        30.042187485115143
       ],
-      "difference": 17.074045981943023,
+      "difference": 28.789996315485123,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2106,12 +2106,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__atom-3-4m": {
+    "lfm2-350m__baguettotron": {
       "ci": [
-        15.724389468592625,
-        17.9181576661227
+        12.443170128806557,
+        14.63607099576427
       ],
-      "difference": 16.83418838584044,
+      "difference": 13.526740651870819,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2133,12 +2133,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__baguettotron": {
+    "lfm2-350m__falcon-h1-tiny-r-90m": {
       "ci": [
-        0.6028456289645157,
-        2.5682754519275246
+        21.180647286515022,
+        23.545436928921546
       ],
-      "difference": 1.5709327222261427,
+      "difference": 22.34695811824909,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2160,12 +2160,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__falcon-h1-tiny-r-90m": {
+    "lfm2-350m__gemma-3-270m": {
       "ci": [
-        9.366761121353298,
-        11.456567965416465
+        3.2295084969038235,
+        5.224620472855046
       ],
-      "difference": 10.391150188604414,
+      "difference": 4.247314979070493,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2187,12 +2187,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__gpt-s-1-4m": {
+    "lfm2-350m__gpt-s-1-4m": {
       "ci": [
-        17.72035213429454,
-        19.952356120653356
+        29.546430185030548,
+        32.048984499243076
       ],
-      "difference": 18.86683151598233,
+      "difference": 30.822639445627008,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2214,12 +2214,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__gpt-s2-5m": {
+    "lfm2-350m__gpt-s2-5m": {
       "ci": [
-        10.837860366434668,
-        12.916752286983545
+        22.692921220894892,
+        25.060730091228283
       ],
-      "difference": 11.902380780265888,
+      "difference": 23.858188709910568,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2241,12 +2241,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__gpt2-124m": {
+    "lfm2-350m__gpt-x2-125m": {
       "ci": [
-        2.3527040000432247,
-        4.2604573197727165
+        6.543548887485459,
+        8.719161211825703
       ],
-      "difference": 3.3111660767278153,
+      "difference": 7.643037384044087,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2268,39 +2268,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__nanowhale-100m-base": {
-      "ci": [
-        12.244547029232189,
-        14.383753052584806
-      ],
-      "difference": 13.313669532986532,
-      "matched_samples": {
-        "arc_challenge": 1172,
-        "arc_easy": 2376,
-        "blimp:Anaphor agreement": 2000,
-        "blimp:Argument structure": 9000,
-        "blimp:Binding": 7000,
-        "blimp:Control / raising": 5000,
-        "blimp:Determiner-noun agreement": 8000,
-        "blimp:Ellipsis": 2000,
-        "blimp:Filler-gap": 10000,
-        "blimp:Irregular forms": 2000,
-        "blimp:Island effects": 8000,
-        "blimp:NPI licensing": 7000,
-        "blimp:Quantifiers": 4000,
-        "blimp:Subject-verb agreement": 6000,
-        "commonsense_qa": 1221,
-        "hellaswag": 10042,
-        "piqa": 1838
-      },
-      "relation": "first_better"
-    },
-    "mobilellm-r1-140m-base__pythia-160m": {
+    "lfm2-350m__gpt2-124m": {
       "ci": [
-        9.850460315653072,
-        12.110903533239728
+        14.143222563888733,
+        16.4118593800478
       ],
-      "difference": 10.96496312661345,
+      "difference": 15.266974006372491,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2322,12 +2295,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__pythia-31m": {
+    "lfm2-350m__gpt2-medium-355m": {
       "ci": [
-        13.173488573335227,
-        15.260343800248487
+        8.647105187970773,
+        10.81188758495598
       ],
-      "difference": 14.230191867999498,
+      "difference": 9.738015028141858,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2349,12 +2322,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__slm-10m": {
+    "lfm2-350m__limen-0-2b": {
       "ci": [
-        9.834008908382621,
-        11.962969758352465
+        5.465900728782017,
+        7.5273454316989
       ],
-      "difference": 10.931490389162754,
+      "difference": 6.505232131858017,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2376,12 +2349,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__supra-50m-base": {
+    "lfm2-350m__mobilellm-r1-140m-base": {
       "ci": [
-        2.9471642992203297,
-        4.800180307345809
+        10.873284350857205,
+        13.02640742452202
       ],
-      "difference": 3.898792212061088,
+      "difference": 11.955807929644676,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2403,12 +2376,12 @@
       },
       "relation": "first_better"
     },
-    "mobilellm-r1-140m-base__veyra2-apricot-50m-base": {
+    "lfm2-350m__nanowhale-100m-base": {
       "ci": [
-        4.204117362859041,
-        6.037751350789785
+        24.094314926003207,
+        26.46428926562647
       ],
-      "difference": 5.118238052298348,
+      "difference": 25.269477462631208,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2430,12 +2403,12 @@
       },
       "relation": "first_better"
     },
-    "nanowhale-100m-base__atom-3-4m": {
+    "lfm2-350m__pythia-160m": {
       "ci": [
-        2.5114800270993958,
-        4.522962101886533
+        21.76448313300386,
+        24.12912979103644
       ],
-      "difference": 3.520518852853912,
+      "difference": 22.920771056258122,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2457,12 +2430,12 @@
       },
       "relation": "first_better"
     },
-    "nanowhale-100m-base__gpt-s-1-4m": {
+    "lfm2-350m__pythia-31m": {
       "ci": [
-        4.520390817955864,
-        6.571451905864101
+        24.947883218281085,
+        27.411184938190967
       ],
-      "difference": 5.553161982995798,
+      "difference": 26.185999797644175,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2484,12 +2457,12 @@
       },
       "relation": "first_better"
     },
-    "nanowhale-100m-base__pythia-31m": {
+    "lfm2-350m__qwen2-5-0-5b": {
       "ci": [
-        -0.04982526813426013,
-        1.8445162857873265
+        -0.7937443045238336,
+        1.2109056554752804
       ],
-      "difference": 0.9165223350129663,
+      "difference": 0.19496537145225148,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2511,12 +2484,12 @@
       },
       "relation": "tie"
     },
-    "pythia-160m__atom-3-4m": {
+    "lfm2-350m__slm-10m": {
       "ci": [
-        4.737172915984907,
-        7.018566565651529
+        21.736389241473272,
+        24.094793643932555
       ],
-      "difference": 5.8692252592269964,
+      "difference": 22.887298318807428,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2538,12 +2511,12 @@
       },
       "relation": "first_better"
     },
-    "pythia-160m__gpt-s-1-4m": {
+    "lfm2-350m__smollm2-135m": {
       "ci": [
-        6.721804247693422,
-        9.058153968300607
+        4.2639180400644365,
+        6.304742227756106
       ],
-      "difference": 7.901868389368882,
+      "difference": 5.305004387140445,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2565,39 +2538,12 @@
       },
       "relation": "first_better"
     },
-    "pythia-160m__gpt-s2-5m": {
-      "ci": [
-        -0.19073668035679597,
-        2.031592137727357
-      ],
-      "difference": 0.9374176536524387,
-      "matched_samples": {
-        "arc_challenge": 1172,
-        "arc_easy": 2376,
-        "blimp:Anaphor agreement": 2000,
-        "blimp:Argument structure": 9000,
-        "blimp:Binding": 7000,
-        "blimp:Control / raising": 5000,
-        "blimp:Determiner-noun agreement": 8000,
-        "blimp:Ellipsis": 2000,
-        "blimp:Filler-gap": 10000,
-        "blimp:Irregular forms": 2000,
-        "blimp:Island effects": 8000,
-        "blimp:NPI licensing": 7000,
-        "blimp:Quantifiers": 4000,
-        "blimp:Subject-verb agreement": 6000,
-        "commonsense_qa": 1221,
-        "hellaswag": 10042,
-        "piqa": 1838
-      },
-      "relation": "tie"
-    },
-    "pythia-160m__nanowhale-100m-base": {
+    "lfm2-350m__supra-50m-base": {
       "ci": [
-        1.24315052655882,
-        3.4148330794518693
+        14.717188310254356,
+        16.936606168548764
       ],
-      "difference": 2.348706406373083,
+      "difference": 15.854600141705763,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2619,12 +2565,12 @@
       },
       "relation": "first_better"
     },
-    "pythia-160m__pythia-31m": {
+    "lfm2-350m__veyra2-apricot-50m-base": {
       "ci": [
-        2.148599543800454,
-        4.357216741831833
+        15.922087105664474,
+        18.21523002545234
       ],
-      "difference": 3.2652287413860495,
+      "difference": 17.074045981943023,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2646,12 +2592,12 @@
       },
       "relation": "first_better"
     },
-    "pythia-31m__atom-3-4m": {
+    "limen-0-2b__atom-3-4m": {
       "ci": [
-        1.6057485508016338,
-        3.598754829970397
+        21.161513441941704,
+        23.390632501383145
       ],
-      "difference": 2.6039965178409457,
+      "difference": 22.2847641836271,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2673,12 +2619,12 @@
       },
       "relation": "first_better"
     },
-    "pythia-31m__gpt-s-1-4m": {
+    "limen-0-2b__baguettotron": {
       "ci": [
-        3.553404497040384,
-        5.681548302264185
+        6.060289304833157,
+        8.008273883388364
       ],
-      "difference": 4.636639647982832,
+      "difference": 7.021508520012802,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2700,12 +2646,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__atom-3-4m": {
+    "limen-0-2b__falcon-h1-tiny-r-90m": {
       "ci": [
-        27.429065503800224,
-        29.758126578860814
+        14.749412938163642,
+        16.841796663719702
       ],
-      "difference": 28.59503094403287,
+      "difference": 15.841725986391072,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2727,12 +2673,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__baguettotron": {
+    "limen-0-2b__gpt-s-1-4m": {
       "ci": [
-        12.233474837251677,
-        14.410463289394922
+        23.10948466843261,
+        25.458602842321564
       ],
-      "difference": 13.331775280418565,
+      "difference": 24.317407313768992,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2754,12 +2700,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__falcon-h1-tiny-r-90m": {
+    "limen-0-2b__gpt-s2-5m": {
       "ci": [
-        21.042544193912452,
-        23.292755794541097
+        16.30800521073441,
+        18.4279354737554
       ],
-      "difference": 22.151992746796836,
+      "difference": 17.352956578052545,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2781,12 +2727,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__gemma-3-270m": {
+    "limen-0-2b__gpt-x2-125m": {
       "ci": [
-        3.1289293385506296,
-        4.949670349757808
+        0.3224073766022845,
+        1.9122064121523048
       ],
-      "difference": 4.0523496076182415,
+      "difference": 1.1378052521860695,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2808,12 +2754,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__gpt-s-1-4m": {
+    "limen-0-2b__gpt2-124m": {
       "ci": [
-        29.358591326483403,
-        31.787910953580926
+        7.833099108366243,
+        9.65152584643135
       ],
-      "difference": 30.627674074174756,
+      "difference": 8.761741874514474,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2835,12 +2781,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__gpt-s2-5m": {
+    "limen-0-2b__gpt2-medium-355m": {
       "ci": [
-        22.484367687263422,
-        24.80643089248962
+        2.3561414181964686,
+        4.07347368481736
       ],
-      "difference": 23.663223338458312,
+      "difference": 3.2327828962838403,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2862,12 +2808,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__gpt-x2-125m": {
+    "limen-0-2b__mobilellm-r1-140m-base": {
       "ci": [
-        6.504515401914428,
-        8.401385534393647
+        4.488179280316571,
+        6.39340909504688
       ],
-      "difference": 7.448072012591836,
+      "difference": 5.450575797786659,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2889,12 +2835,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__gpt2-124m": {
+    "limen-0-2b__nanowhale-100m-base": {
       "ci": [
-        14.119663769992147,
-        16.08811450435093
+        17.773543836990466,
+        19.818671756113275
       ],
-      "difference": 15.07200863492024,
+      "difference": 18.764245330773193,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2916,12 +2862,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__mobilellm-r1-140m-base": {
+    "limen-0-2b__pythia-160m": {
       "ci": [
-        10.797843611952915,
-        12.719193410831675
+        15.347024605257046,
+        17.461363940919785
       ],
-      "difference": 11.760842558192424,
+      "difference": 16.415538924400106,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2943,12 +2889,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__nanowhale-100m-base": {
+    "limen-0-2b__pythia-31m": {
       "ci": [
-        23.99988085171323,
-        26.190262920767886
+        18.600823907513195,
+        20.77696639320947
       ],
-      "difference": 25.074512091178956,
+      "difference": 19.68076766578616,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2970,12 +2916,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__pythia-160m": {
+    "limen-0-2b__slm-10m": {
       "ci": [
-        21.56004563074552,
-        23.87905437950645
+        15.304067721870874,
+        17.457018849422926
       ],
-      "difference": 22.725805684805874,
+      "difference": 16.382066186949416,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -2997,12 +2943,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__pythia-31m": {
+    "limen-0-2b__supra-50m-base": {
       "ci": [
-        24.841628881519235,
-        27.14392774955085
+        8.485989855643487,
+        10.252743940672737
       ],
-      "difference": 25.991034426191924,
+      "difference": 9.349368009847748,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3024,12 +2970,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__slm-10m": {
+    "limen-0-2b__veyra2-apricot-50m-base": {
       "ci": [
-        21.573153354252433,
-        23.791472841951883
+        9.680541335952592,
+        11.49796980911933
       ],
-      "difference": 22.69233294735518,
+      "difference": 10.568813850085007,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3051,12 +2997,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__smollm2-135m": {
+    "mobilellm-r1-140m-base__atom-3-4m": {
       "ci": [
-        4.182377294645956,
-        6.041752403489344
+        15.724389468592625,
+        17.9181576661227
       ],
-      "difference": 5.110039015688194,
+      "difference": 16.83418838584044,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3078,12 +3024,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__supra-50m-base": {
+    "mobilellm-r1-140m-base__baguettotron": {
       "ci": [
-        14.674719371285,
-        16.64642100282309
+        0.6028456289645157,
+        2.5682754519275246
       ],
-      "difference": 15.659634770253513,
+      "difference": 1.5709327222261427,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3105,12 +3051,12 @@
       },
       "relation": "first_better"
     },
-    "qwen2-5-0-5b__veyra2-apricot-50m-base": {
+    "mobilellm-r1-140m-base__falcon-h1-tiny-r-90m": {
       "ci": [
-        15.843063351497843,
-        17.88305005638959
+        9.366761121353298,
+        11.456567965416465
       ],
-      "difference": 16.87908061049077,
+      "difference": 10.391150188604414,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3132,12 +3078,12 @@
       },
       "relation": "first_better"
     },
-    "slm-10m__atom-3-4m": {
+    "mobilellm-r1-140m-base__gpt-s-1-4m": {
       "ci": [
-        5.036334220813094,
-        6.855128264261082
+        17.72035213429454,
+        19.952356120653356
       ],
-      "difference": 5.902697996677689,
+      "difference": 18.86683151598233,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3159,12 +3105,12 @@
       },
       "relation": "first_better"
     },
-    "slm-10m__gpt-s-1-4m": {
+    "mobilellm-r1-140m-base__gpt-s2-5m": {
       "ci": [
-        6.926706396733146,
-        8.94055735587147
+        10.837860366434668,
+        12.916752286983545
       ],
-      "difference": 7.935341126819576,
+      "difference": 11.902380780265888,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3186,12 +3132,12 @@
       },
       "relation": "first_better"
     },
-    "slm-10m__gpt-s2-5m": {
+    "mobilellm-r1-140m-base__gpt2-124m": {
       "ci": [
-        0.06659882140217428,
-        1.8222234812887246
+        2.3527040000432247,
+        4.2604573197727165
       ],
-      "difference": 0.970890391103133,
+      "difference": 3.3111660767278153,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3213,12 +3159,12 @@
       },
       "relation": "first_better"
     },
-    "slm-10m__nanowhale-100m-base": {
+    "mobilellm-r1-140m-base__nanowhale-100m-base": {
       "ci": [
-        1.4914905145647108,
-        3.2592393440485696
+        12.244547029232189,
+        14.383753052584806
       ],
-      "difference": 2.382179143823778,
+      "difference": 13.313669532986532,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3240,66 +3186,12 @@
       },
       "relation": "first_better"
     },
-    "slm-10m__pythia-160m": {
-      "ci": [
-        -1.0366806397870105,
-        1.1714324189900007
-      ],
-      "difference": 0.03347273745069435,
-      "matched_samples": {
-        "arc_challenge": 1172,
-        "arc_easy": 2376,
-        "blimp:Anaphor agreement": 2000,
-        "blimp:Argument structure": 9000,
-        "blimp:Binding": 7000,
-        "blimp:Control / raising": 5000,
-        "blimp:Determiner-noun agreement": 8000,
-        "blimp:Ellipsis": 2000,
-        "blimp:Filler-gap": 10000,
-        "blimp:Irregular forms": 2000,
-        "blimp:Island effects": 8000,
-        "blimp:NPI licensing": 7000,
-        "blimp:Quantifiers": 4000,
-        "blimp:Subject-verb agreement": 6000,
-        "commonsense_qa": 1221,
-        "hellaswag": 10042,
-        "piqa": 1838
-      },
-      "relation": "tie"
-    },
-    "slm-10m__pythia-31m": {
-      "ci": [
-        2.372327463312847,
-        4.223426615282993
-      ],
-      "difference": 3.2987014788367444,
-      "matched_samples": {
-        "arc_challenge": 1172,
-        "arc_easy": 2376,
-        "blimp:Anaphor agreement": 2000,
-        "blimp:Argument structure": 9000,
-        "blimp:Binding": 7000,
-        "blimp:Control / raising": 5000,
-        "blimp:Determiner-noun agreement": 8000,
-        "blimp:Ellipsis": 2000,
-        "blimp:Filler-gap": 10000,
-        "blimp:Irregular forms": 2000,
-        "blimp:Island effects": 8000,
-        "blimp:NPI licensing": 7000,
-        "blimp:Quantifiers": 4000,
-        "blimp:Subject-verb agreement": 6000,
-        "commonsense_qa": 1221,
-        "hellaswag": 10042,
-        "piqa": 1838
-      },
-      "relation": "first_better"
-    },
-    "smollm2-135m__atom-3-4m": {
+    "mobilellm-r1-140m-base__pythia-160m": {
       "ci": [
-        22.34756564971431,
-        24.615212198542363
+        9.850460315653072,
+        12.110903533239728
       ],
-      "difference": 23.484991928344677,
+      "difference": 10.96496312661345,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3321,12 +3213,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__baguettotron": {
+    "mobilellm-r1-140m-base__pythia-31m": {
       "ci": [
-        7.21981046049257,
-        9.250291115821636
+        13.173488573335227,
+        15.260343800248487
       ],
-      "difference": 8.221736264730373,
+      "difference": 14.230191867999498,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3348,12 +3240,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__falcon-h1-tiny-r-90m": {
+    "mobilellm-r1-140m-base__slm-10m": {
       "ci": [
-        15.998703266315285,
-        18.097428607290865
+        9.834008908382621,
+        11.962969758352465
       ],
-      "difference": 17.04195373110864,
+      "difference": 10.931490389162754,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3375,12 +3267,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__gpt-s-1-4m": {
+    "mobilellm-r1-140m-base__supra-50m-base": {
       "ci": [
-        24.306597878265215,
-        26.660924664410892
+        2.9471642992203297,
+        4.800180307345809
       ],
-      "difference": 25.517635058486558,
+      "difference": 3.898792212061088,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3402,12 +3294,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__gpt-s2-5m": {
+    "mobilellm-r1-140m-base__veyra2-apricot-50m-base": {
       "ci": [
-        17.474818949264733,
-        19.65927462835377
+        4.204117362859041,
+        6.037751350789785
       ],
-      "difference": 18.553184322770118,
+      "difference": 5.118238052298348,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3429,12 +3321,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__gpt-x2-125m": {
+    "nanowhale-100m-base__atom-3-4m": {
       "ci": [
-        1.520836731078651,
-        3.1770188989552963
+        2.5114800270993958,
+        4.522962101886533
       ],
-      "difference": 2.338032996903642,
+      "difference": 3.520518852853912,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3456,12 +3348,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__gpt2-124m": {
+    "nanowhale-100m-base__gpt-s-1-4m": {
       "ci": [
-        9.01471391018264,
-        10.912959371692486
+        4.520390817955864,
+        6.571451905864101
       ],
-      "difference": 9.961969619232047,
+      "difference": 5.553161982995798,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3483,12 +3375,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__mobilellm-r1-140m-base": {
+    "nanowhale-100m-base__pythia-31m": {
       "ci": [
-        5.754466156999673,
-        7.575045374739086
+        -0.04982526813426013,
+        1.8445162857873265
       ],
-      "difference": 6.65080354250423,
+      "difference": 0.9165223350129663,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3508,14 +3400,14 @@
         "hellaswag": 10042,
         "piqa": 1838
       },
-      "relation": "first_better"
+      "relation": "tie"
     },
-    "smollm2-135m__nanowhale-100m-base": {
+    "pythia-160m__atom-3-4m": {
       "ci": [
-        18.89929834073857,
-        21.076546736195468
+        4.737172915984907,
+        7.018566565651529
       ],
-      "difference": 19.964473075490766,
+      "difference": 5.8692252592269964,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3537,12 +3429,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__pythia-160m": {
+    "pythia-160m__gpt-s-1-4m": {
       "ci": [
-        16.533556862312427,
-        18.762458693268172
+        6.721804247693422,
+        9.058153968300607
       ],
-      "difference": 17.61576666911768,
+      "difference": 7.901868389368882,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3564,12 +3456,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__pythia-31m": {
+    "pythia-160m__gpt-s2-5m": {
       "ci": [
-        19.743832355893147,
-        21.98849774424981
+        -0.19073668035679597,
+        2.031592137727357
       ],
-      "difference": 20.88099541050373,
+      "difference": 0.9374176536524387,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3589,14 +3481,14 @@
         "hellaswag": 10042,
         "piqa": 1838
       },
-      "relation": "first_better"
+      "relation": "tie"
     },
-    "smollm2-135m__slm-10m": {
+    "pythia-160m__nanowhale-100m-base": {
       "ci": [
-        16.48898449494742,
-        18.664225888028522
+        1.24315052655882,
+        3.4148330794518693
       ],
-      "difference": 17.58229393166699,
+      "difference": 2.348706406373083,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3618,12 +3510,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__supra-50m-base": {
+    "pythia-160m__pythia-31m": {
       "ci": [
-        9.632456329100759,
-        11.448445329599902
+        2.148599543800454,
+        4.357216741831833
       ],
-      "difference": 10.549595754565319,
+      "difference": 3.2652287413860495,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3645,12 +3537,12 @@
       },
       "relation": "first_better"
     },
-    "smollm2-135m__veyra2-apricot-50m-base": {
+    "pythia-31m__atom-3-4m": {
       "ci": [
-        10.828312999027693,
-        12.721441869861339
+        1.6057485508016338,
+        3.598754829970397
       ],
-      "difference": 11.769041594802578,
+      "difference": 2.6039965178409457,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3672,12 +3564,12 @@
       },
       "relation": "first_better"
     },
-    "supra-50m-base__atom-3-4m": {
+    "pythia-31m__gpt-s-1-4m": {
       "ci": [
-        11.943975471387882,
-        13.975141551589562
+        3.553404497040384,
+        5.681548302264185
       ],
-      "difference": 12.935396173779356,
+      "difference": 4.636639647982832,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3699,12 +3591,12 @@
       },
       "relation": "first_better"
     },
-    "supra-50m-base__falcon-h1-tiny-r-90m": {
+    "qwen2-5-0-5b__atom-3-4m": {
       "ci": [
-        5.4933752538658185,
-        7.494091690632844
+        27.429065503800224,
+        29.758126578860814
       ],
-      "difference": 6.4923579765433255,
+      "difference": 28.59503094403287,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3726,12 +3618,12 @@
       },
       "relation": "first_better"
     },
-    "supra-50m-base__gpt-s-1-4m": {
+    "qwen2-5-0-5b__baguettotron": {
       "ci": [
-        13.913111223226107,
-        16.026314781815554
+        12.233474837251677,
+        14.410463289394922
       ],
-      "difference": 14.968039303921243,
+      "difference": 13.331775280418565,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3753,12 +3645,12 @@
       },
       "relation": "first_better"
     },
-    "supra-50m-base__gpt-s2-5m": {
+    "qwen2-5-0-5b__falcon-h1-tiny-r-90m": {
       "ci": [
-        7.055711440473382,
-        8.973542914177806
+        21.042544193912452,
+        23.292755794541097
       ],
-      "difference": 8.0035885682048,
+      "difference": 22.151992746796836,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3780,12 +3672,12 @@
       },
       "relation": "first_better"
     },
-    "supra-50m-base__nanowhale-100m-base": {
+    "qwen2-5-0-5b__gemma-3-270m": {
       "ci": [
-        8.481265325554629,
-        10.332046076912933
+        3.1289293385506296,
+        4.949670349757808
       ],
-      "difference": 9.414877320925445,
+      "difference": 4.0523496076182415,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3807,12 +3699,12 @@
       },
       "relation": "first_better"
     },
-    "supra-50m-base__pythia-160m": {
+    "qwen2-5-0-5b__gpt-s-1-4m": {
       "ci": [
-        5.988387846530205,
-        8.160833376393306
+        29.358591326483403,
+        31.787910953580926
       ],
-      "difference": 7.0661709145523615,
+      "difference": 30.627674074174756,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3834,12 +3726,12 @@
       },
       "relation": "first_better"
     },
-    "supra-50m-base__pythia-31m": {
+    "qwen2-5-0-5b__gpt-s2-5m": {
       "ci": [
-        9.341259784482242,
-        11.317334294187644
+        22.484367687263422,
+        24.80643089248962
       ],
-      "difference": 10.33139965593841,
+      "difference": 23.663223338458312,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3861,12 +3753,12 @@
       },
       "relation": "first_better"
     },
-    "supra-50m-base__slm-10m": {
+    "qwen2-5-0-5b__gpt-x2-125m": {
       "ci": [
-        6.057935337460307,
-        8.006326905907825
+        6.504515401914428,
+        8.401385534393647
       ],
-      "difference": 7.032698177101667,
+      "difference": 7.448072012591836,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3888,12 +3780,12 @@
       },
       "relation": "first_better"
     },
-    "supra-50m-base__veyra2-apricot-50m-base": {
+    "qwen2-5-0-5b__gpt2-124m": {
       "ci": [
-        0.352626714684538,
-        2.1370426725718357
+        14.119663769992147,
+        16.08811450435093
       ],
-      "difference": 1.21944584023726,
+      "difference": 15.07200863492024,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3915,12 +3807,12 @@
       },
       "relation": "first_better"
     },
-    "veyra2-apricot-50m-base__atom-3-4m": {
+    "qwen2-5-0-5b__gpt2-medium-355m": {
       "ci": [
-        10.627668222625106,
-        12.751269936412879
+        8.580291489301949,
+        10.482138750922191
       ],
-      "difference": 11.715950333542096,
+      "difference": 9.543049656689606,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3942,12 +3834,12 @@
       },
       "relation": "first_better"
     },
-    "veyra2-apricot-50m-base__falcon-h1-tiny-r-90m": {
+    "qwen2-5-0-5b__limen-0-2b": {
       "ci": [
-        4.269879876321943,
-        6.237640792156269
+        5.395933348530456,
+        7.243893177924733
       ],
-      "difference": 5.272912136306066,
+      "difference": 6.310266760405766,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3969,12 +3861,12 @@
       },
       "relation": "first_better"
     },
-    "veyra2-apricot-50m-base__gpt-s-1-4m": {
+    "qwen2-5-0-5b__mobilellm-r1-140m-base": {
       "ci": [
-        12.499782605339313,
-        14.838887566245907
+        10.797843611952915,
+        12.719193410831675
       ],
-      "difference": 13.748593463683981,
+      "difference": 11.760842558192424,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -3996,12 +3888,12 @@
       },
       "relation": "first_better"
     },
-    "veyra2-apricot-50m-base__gpt-s2-5m": {
+    "qwen2-5-0-5b__nanowhale-100m-base": {
       "ci": [
-        5.8032698087522885,
-        7.724554386452487
+        23.99988085171323,
+        26.190262920767886
       ],
-      "difference": 6.784142727967539,
+      "difference": 25.074512091178956,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -4023,12 +3915,12 @@
       },
       "relation": "first_better"
     },
-    "veyra2-apricot-50m-base__nanowhale-100m-base": {
+    "qwen2-5-0-5b__pythia-160m": {
       "ci": [
-        7.226025832871106,
-        9.190466152028234
+        21.56004563074552,
+        23.87905437950645
       ],
-      "difference": 8.195431480688185,
+      "difference": 22.725805684805874,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -4050,12 +3942,498 @@
       },
       "relation": "first_better"
     },
-    "veyra2-apricot-50m-base__pythia-160m": {
+    "qwen2-5-0-5b__pythia-31m": {
       "ci": [
-        4.834200955167154,
-        6.909557402281555
+        24.841628881519235,
+        27.14392774955085
       ],
-      "difference": 5.846725074315101,
+      "difference": 25.991034426191924,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "qwen2-5-0-5b__slm-10m": {
+      "ci": [
+        21.573153354252433,
+        23.791472841951883
+      ],
+      "difference": 22.69233294735518,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "qwen2-5-0-5b__smollm2-135m": {
+      "ci": [
+        4.182377294645956,
+        6.041752403489344
+      ],
+      "difference": 5.110039015688194,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "qwen2-5-0-5b__supra-50m-base": {
+      "ci": [
+        14.674719371285,
+        16.64642100282309
+      ],
+      "difference": 15.659634770253513,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "qwen2-5-0-5b__veyra2-apricot-50m-base": {
+      "ci": [
+        15.843063351497843,
+        17.88305005638959
+      ],
+      "difference": 16.87908061049077,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "slm-10m__atom-3-4m": {
+      "ci": [
+        5.036334220813094,
+        6.855128264261082
+      ],
+      "difference": 5.902697996677689,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "slm-10m__gpt-s-1-4m": {
+      "ci": [
+        6.926706396733146,
+        8.94055735587147
+      ],
+      "difference": 7.935341126819576,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "slm-10m__gpt-s2-5m": {
+      "ci": [
+        0.06659882140217428,
+        1.8222234812887246
+      ],
+      "difference": 0.970890391103133,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "slm-10m__nanowhale-100m-base": {
+      "ci": [
+        1.4914905145647108,
+        3.2592393440485696
+      ],
+      "difference": 2.382179143823778,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "slm-10m__pythia-160m": {
+      "ci": [
+        -1.0366806397870105,
+        1.1714324189900007
+      ],
+      "difference": 0.03347273745069435,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "tie"
+    },
+    "slm-10m__pythia-31m": {
+      "ci": [
+        2.372327463312847,
+        4.223426615282993
+      ],
+      "difference": 3.2987014788367444,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__atom-3-4m": {
+      "ci": [
+        22.34756564971431,
+        24.615212198542363
+      ],
+      "difference": 23.484991928344677,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__baguettotron": {
+      "ci": [
+        7.21981046049257,
+        9.250291115821636
+      ],
+      "difference": 8.221736264730373,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__falcon-h1-tiny-r-90m": {
+      "ci": [
+        15.998703266315285,
+        18.097428607290865
+      ],
+      "difference": 17.04195373110864,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__gpt-s-1-4m": {
+      "ci": [
+        24.306597878265215,
+        26.660924664410892
+      ],
+      "difference": 25.517635058486558,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__gpt-s2-5m": {
+      "ci": [
+        17.474818949264733,
+        19.65927462835377
+      ],
+      "difference": 18.553184322770118,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__gpt-x2-125m": {
+      "ci": [
+        1.520836731078651,
+        3.1770188989552963
+      ],
+      "difference": 2.338032996903642,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__gpt2-124m": {
+      "ci": [
+        9.01471391018264,
+        10.912959371692486
+      ],
+      "difference": 9.961969619232047,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__gpt2-medium-355m": {
+      "ci": [
+        3.5516102335971445,
+        5.330605430074946
+      ],
+      "difference": 4.433010641001412,
       "matched_samples": {
         "arc_challenge": 1172,
         "arc_easy": 2376,
@@ -4075,181 +4453,8104 @@
         "hellaswag": 10042,
         "piqa": 1838
       },
-      "relation": "first_better"
-    },
-    "veyra2-apricot-50m-base__pythia-31m": {
-      "ci": [
-        8.142263967111687,
-        10.097664917317006
+      "relation": "first_better"
+    },
+    "smollm2-135m__limen-0-2b": {
+      "ci": [
+        0.3179865353874399,
+        2.0083468477308863
+      ],
+      "difference": 1.200227744717572,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__mobilellm-r1-140m-base": {
+      "ci": [
+        5.754466156999673,
+        7.575045374739086
+      ],
+      "difference": 6.65080354250423,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__nanowhale-100m-base": {
+      "ci": [
+        18.89929834073857,
+        21.076546736195468
+      ],
+      "difference": 19.964473075490766,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__pythia-160m": {
+      "ci": [
+        16.533556862312427,
+        18.762458693268172
+      ],
+      "difference": 17.61576666911768,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__pythia-31m": {
+      "ci": [
+        19.743832355893147,
+        21.98849774424981
+      ],
+      "difference": 20.88099541050373,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__slm-10m": {
+      "ci": [
+        16.48898449494742,
+        18.664225888028522
+      ],
+      "difference": 17.58229393166699,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__supra-50m-base": {
+      "ci": [
+        9.632456329100759,
+        11.448445329599902
+      ],
+      "difference": 10.549595754565319,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "smollm2-135m__veyra2-apricot-50m-base": {
+      "ci": [
+        10.828312999027693,
+        12.721441869861339
+      ],
+      "difference": 11.769041594802578,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "supra-50m-base__atom-3-4m": {
+      "ci": [
+        11.943975471387882,
+        13.975141551589562
+      ],
+      "difference": 12.935396173779356,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "supra-50m-base__falcon-h1-tiny-r-90m": {
+      "ci": [
+        5.4933752538658185,
+        7.494091690632844
+      ],
+      "difference": 6.4923579765433255,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "supra-50m-base__gpt-s-1-4m": {
+      "ci": [
+        13.913111223226107,
+        16.026314781815554
+      ],
+      "difference": 14.968039303921243,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "supra-50m-base__gpt-s2-5m": {
+      "ci": [
+        7.055711440473382,
+        8.973542914177806
+      ],
+      "difference": 8.0035885682048,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "supra-50m-base__nanowhale-100m-base": {
+      "ci": [
+        8.481265325554629,
+        10.332046076912933
+      ],
+      "difference": 9.414877320925445,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "supra-50m-base__pythia-160m": {
+      "ci": [
+        5.988387846530205,
+        8.160833376393306
+      ],
+      "difference": 7.0661709145523615,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "supra-50m-base__pythia-31m": {
+      "ci": [
+        9.341259784482242,
+        11.317334294187644
+      ],
+      "difference": 10.33139965593841,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "supra-50m-base__slm-10m": {
+      "ci": [
+        6.057935337460307,
+        8.006326905907825
+      ],
+      "difference": 7.032698177101667,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "supra-50m-base__veyra2-apricot-50m-base": {
+      "ci": [
+        0.352626714684538,
+        2.1370426725718357
+      ],
+      "difference": 1.21944584023726,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "veyra2-apricot-50m-base__atom-3-4m": {
+      "ci": [
+        10.627668222625106,
+        12.751269936412879
+      ],
+      "difference": 11.715950333542096,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "veyra2-apricot-50m-base__falcon-h1-tiny-r-90m": {
+      "ci": [
+        4.269879876321943,
+        6.237640792156269
+      ],
+      "difference": 5.272912136306066,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "veyra2-apricot-50m-base__gpt-s-1-4m": {
+      "ci": [
+        12.499782605339313,
+        14.838887566245907
+      ],
+      "difference": 13.748593463683981,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "veyra2-apricot-50m-base__gpt-s2-5m": {
+      "ci": [
+        5.8032698087522885,
+        7.724554386452487
+      ],
+      "difference": 6.784142727967539,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "veyra2-apricot-50m-base__nanowhale-100m-base": {
+      "ci": [
+        7.226025832871106,
+        9.190466152028234
+      ],
+      "difference": 8.195431480688185,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "veyra2-apricot-50m-base__pythia-160m": {
+      "ci": [
+        4.834200955167154,
+        6.909557402281555
+      ],
+      "difference": 5.846725074315101,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "veyra2-apricot-50m-base__pythia-31m": {
+      "ci": [
+        8.142263967111687,
+        10.097664917317006
+      ],
+      "difference": 9.11195381570115,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    },
+    "veyra2-apricot-50m-base__slm-10m": {
+      "ci": [
+        4.863643976660482,
+        6.735987982048942
+      ],
+      "difference": 5.813252336864407,
+      "matched_samples": {
+        "arc_challenge": 1172,
+        "arc_easy": 2376,
+        "blimp:Anaphor agreement": 2000,
+        "blimp:Argument structure": 9000,
+        "blimp:Binding": 7000,
+        "blimp:Control / raising": 5000,
+        "blimp:Determiner-noun agreement": 8000,
+        "blimp:Ellipsis": 2000,
+        "blimp:Filler-gap": 10000,
+        "blimp:Irregular forms": 2000,
+        "blimp:Island effects": 8000,
+        "blimp:NPI licensing": 7000,
+        "blimp:Quantifiers": 4000,
+        "blimp:Subject-verb agreement": 6000,
+        "commonsense_qa": 1221,
+        "hellaswag": 10042,
+        "piqa": 1838
+      },
+      "relation": "first_better"
+    }
+  },
+  "generated_at": "2026-07-27T17:06:56.669003+00:00",
+  "models": [
+    {
+      "artifacts": {
+        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154647Z-v1.1/results_v1.1_merged.json",
+        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154647Z-v1.1"
+      },
+      "benchmarks": {
+        "arc_challenge": {
+          "accuracy": 0.39590443686006827,
+          "chance": 0.25,
+          "ci": [
+            15.696814562002272,
+            23.321956769055745
+          ],
+          "classification": "reliably above chance",
+          "label": "ARC-Challenge",
+          "n_samples": 1172,
+          "score": 19.45392491467577
+        },
+        "arc_easy": {
+          "accuracy": 0.6641414141414141,
+          "chance": 0.25,
+          "ci": [
+            52.637485970819306,
+            57.744107744107744
+          ],
+          "classification": "reliably above chance",
+          "label": "ARC-Easy",
+          "n_samples": 2376,
+          "score": 55.21885521885522
+        },
+        "blimp": {
+          "accuracy": 0.7906593253968254,
+          "categories": {
+            "Anaphor agreement": 0.977,
+            "Argument structure": 0.7756666666666666,
+            "Binding": 0.7418571428571428,
+            "Control / raising": 0.8074,
+            "Determiner-noun agreement": 0.9377500000000001,
+            "Ellipsis": 0.8654999999999999,
+            "Filler-gap": 0.7779999999999999,
+            "Irregular forms": 0.728,
+            "Island effects": 0.739,
+            "NPI licensing": 0.5485714285714286,
+            "Quantifiers": 0.7414999999999999,
+            "Subject-verb agreement": 0.8476666666666666
+          },
+          "category_count": 12,
+          "chance": 0.5,
+          "ci": [
+            57.22199222883596,
+            58.42621676587302
+          ],
+          "classification": "reliably above chance",
+          "label": "BLiMP",
+          "n_samples": 70000,
+          "score": 58.13186507936508
+        },
+        "commonsense_qa": {
+          "accuracy": 0.45045045045045046,
+          "chance": 0.2,
+          "ci": [
+            27.927927927927925,
+            34.88943488943489
+          ],
+          "classification": "reliably above chance",
+          "label": "CommonsenseQA",
+          "n_samples": 1221,
+          "score": 31.306306306306304
+        },
+        "hellaswag": {
+          "accuracy": 0.4898426608245369,
+          "chance": 0.25,
+          "ci": [
+            30.61143198566022,
+            33.25433180641306
+          ],
+          "classification": "reliably above chance",
+          "label": "HellaSwag",
+          "n_samples": 10042,
+          "score": 31.97902144327159
+        },
+        "piqa": {
+          "accuracy": 0.6958650707290533,
+          "chance": 0.5,
+          "ci": [
+            35.03808487486397,
+            43.2018498367791
+          ],
+          "classification": "reliably above chance",
+          "label": "PIQA",
+          "n_samples": 1838,
+          "score": 39.17301414581067
+        }
+      },
+      "complete": true,
+      "composite": {
+        "ci": [
+          42.03623437890757,
+          44.21094708361269
+        ],
+        "classification": "reliably above chance",
+        "score": 43.17876224644195
+      },
+      "id": "lfm2-350m",
+      "name": "LFM2 350M",
+      "params_m": 354.484,
+      "protocol": {
+        "bootstrap_replicates": 2000,
+        "bootstrap_seed": 20260716,
+        "harness": "lm-eval==0.4.12",
+        "harness_git_hash": null,
+        "inference_config": {
+          "batch_size": "auto",
+          "batch_sizes": [
+            64
+          ],
+          "bootstrap_iters": 100000,
+          "device": "cuda:0",
+          "fewshot_seed": 1234,
+          "gen_kwargs": {},
+          "limit": null,
+          "model": "hf",
+          "model_args": {
+            "dtype": "bfloat16",
+            "pretrained": "models/lfm2-350m",
+            "tokenizer": "models/lfm2-350m",
+            "trust_remote_code": false
+          },
+          "model_dtype": "torch.bfloat16",
+          "model_num_parameters": 354483968,
+          "model_revision": "main",
+          "model_sha": "",
+          "numpy_seed": 1234,
+          "random_seed": 1234,
+          "tasks": [
+            "hellaswag",
+            "piqa",
+            "arc_easy",
+            "arc_challenge",
+            "commonsense_qa_text",
+            "blimp"
+          ],
+          "torch_seed": 1234,
+          "use_cache": null,
+          "v1_1_sources": {
+            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154341Z-v1.1/results_v1.1_merged.json",
+            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154341Z-v1.1/results_v1.1_merged.json"
+          }
+        },
+        "n_shot": {
+          "arc_easy": 0,
+          "blimp": 0,
+          "blimp_adjunct_island": 0,
+          "blimp_anaphor_gender_agreement": 0,
+          "blimp_anaphor_number_agreement": 0,
+          "blimp_animate_subject_passive": 0,
+          "blimp_animate_subject_trans": 0,
+          "blimp_causative": 0,
+          "blimp_complex_NP_island": 0,
+          "blimp_coordinate_structure_constraint_complex_left_branch": 0,
+          "blimp_coordinate_structure_constraint_object_extraction": 0,
+          "blimp_determiner_noun_agreement_1": 0,
+          "blimp_determiner_noun_agreement_2": 0,
+          "blimp_determiner_noun_agreement_irregular_1": 0,
+          "blimp_determiner_noun_agreement_irregular_2": 0,
+          "blimp_determiner_noun_agreement_with_adj_2": 0,
+          "blimp_determiner_noun_agreement_with_adj_irregular_1": 0,
+          "blimp_determiner_noun_agreement_with_adj_irregular_2": 0,
+          "blimp_determiner_noun_agreement_with_adjective_1": 0,
+          "blimp_distractor_agreement_relational_noun": 0,
+          "blimp_distractor_agreement_relative_clause": 0,
+          "blimp_drop_argument": 0,
+          "blimp_ellipsis_n_bar_1": 0,
+          "blimp_ellipsis_n_bar_2": 0,
+          "blimp_existential_there_object_raising": 0,
+          "blimp_existential_there_quantifiers_1": 0,
+          "blimp_existential_there_quantifiers_2": 0,
+          "blimp_existential_there_subject_raising": 0,
+          "blimp_expletive_it_object_raising": 0,
+          "blimp_inchoative": 0,
+          "blimp_intransitive": 0,
+          "blimp_irregular_past_participle_adjectives": 0,
+          "blimp_irregular_past_participle_verbs": 0,
+          "blimp_irregular_plural_subject_verb_agreement_1": 0,
+          "blimp_irregular_plural_subject_verb_agreement_2": 0,
+          "blimp_left_branch_island_echo_question": 0,
+          "blimp_left_branch_island_simple_question": 0,
+          "blimp_matrix_question_npi_licensor_present": 0,
+          "blimp_npi_present_1": 0,
+          "blimp_npi_present_2": 0,
+          "blimp_only_npi_licensor_present": 0,
+          "blimp_only_npi_scope": 0,
+          "blimp_passive_1": 0,
+          "blimp_passive_2": 0,
+          "blimp_principle_A_c_command": 0,
+          "blimp_principle_A_case_1": 0,
+          "blimp_principle_A_case_2": 0,
+          "blimp_principle_A_domain_1": 0,
+          "blimp_principle_A_domain_2": 0,
+          "blimp_principle_A_domain_3": 0,
+          "blimp_principle_A_reconstruction": 0,
+          "blimp_regular_plural_subject_verb_agreement_1": 0,
+          "blimp_regular_plural_subject_verb_agreement_2": 0,
+          "blimp_sentential_negation_npi_licensor_present": 0,
+          "blimp_sentential_negation_npi_scope": 0,
+          "blimp_sentential_subject_island": 0,
+          "blimp_superlative_quantifiers_1": 0,
+          "blimp_superlative_quantifiers_2": 0,
+          "blimp_tough_vs_raising_1": 0,
+          "blimp_tough_vs_raising_2": 0,
+          "blimp_transitive": 0,
+          "blimp_wh_island": 0,
+          "blimp_wh_questions_object_gap": 0,
+          "blimp_wh_questions_subject_gap": 0,
+          "blimp_wh_questions_subject_gap_long_distance": 0,
+          "blimp_wh_vs_that_no_gap": 0,
+          "blimp_wh_vs_that_no_gap_long_distance": 0,
+          "blimp_wh_vs_that_with_gap": 0,
+          "blimp_wh_vs_that_with_gap_long_distance": 0,
+          "commonsense_qa": 0,
+          "hellaswag": 0,
+          "piqa": 0
+        },
+        "suite": "slm-benchmark-v1.1",
+        "task_config": {
+          "arc_challenge": {
+            "dataset_name": "ARC-Challenge",
+            "dataset_path": "allenai/ai2_arc",
+            "description": "",
+            "doc_to_choice": "{{choices.text}}",
+            "doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
+            "doc_to_target": "{{choices.label.index(answerKey)}}",
+            "doc_to_text": "Question: {{question}}\nAnswer:",
+            "fewshot_config": {
+              "doc_to_choice": "{{choices.text}}",
+              "doc_to_target": "{{choices.label.index(answerKey)}}",
+              "doc_to_text": "Question: {{question}}\nAnswer:",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_challenge.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "arc_challenge",
+            "test_split": "test",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          },
+          "arc_easy": {
+            "dataset_name": "ARC-Easy",
+            "dataset_path": "allenai/ai2_arc",
+            "description": "",
+            "doc_to_choice": "{{choices.text}}",
+            "doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
+            "doc_to_target": "{{choices.label.index(answerKey)}}",
+            "doc_to_text": "Question: {{question}}\nAnswer:",
+            "fewshot_config": {
+              "doc_to_choice": "{{choices.text}}",
+              "doc_to_target": "{{choices.label.index(answerKey)}}",
+              "doc_to_text": "Question: {{question}}\nAnswer:",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_easy.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "arc_easy",
+            "test_split": "test",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          },
+          "blimp_adjunct_island": {
+            "dataset_name": "adjunct_island",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/adjunct_island.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_adjunct_island",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_anaphor_gender_agreement": {
+            "dataset_name": "anaphor_gender_agreement",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_gender_agreement.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_anaphor_gender_agreement",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_anaphor_number_agreement": {
+            "dataset_name": "anaphor_number_agreement",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_number_agreement.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_anaphor_number_agreement",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_animate_subject_passive": {
+            "dataset_name": "animate_subject_passive",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_passive.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_animate_subject_passive",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_animate_subject_trans": {
+            "dataset_name": "animate_subject_trans",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_trans.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_animate_subject_trans",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_causative": {
+            "dataset_name": "causative",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/causative.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_causative",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_complex_NP_island": {
+            "dataset_name": "complex_NP_island",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/complex_NP_island.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_complex_NP_island",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_coordinate_structure_constraint_complex_left_branch": {
+            "dataset_name": "coordinate_structure_constraint_complex_left_branch",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_complex_left_branch.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_coordinate_structure_constraint_complex_left_branch",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_coordinate_structure_constraint_object_extraction": {
+            "dataset_name": "coordinate_structure_constraint_object_extraction",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_object_extraction.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_coordinate_structure_constraint_object_extraction",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_1": {
+            "dataset_name": "determiner_noun_agreement_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_2": {
+            "dataset_name": "determiner_noun_agreement_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_irregular_1": {
+            "dataset_name": "determiner_noun_agreement_irregular_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_irregular_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_irregular_2": {
+            "dataset_name": "determiner_noun_agreement_irregular_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_irregular_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_with_adj_2": {
+            "dataset_name": "determiner_noun_agreement_with_adj_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_with_adj_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_with_adj_irregular_1": {
+            "dataset_name": "determiner_noun_agreement_with_adj_irregular_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_with_adj_irregular_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_with_adj_irregular_2": {
+            "dataset_name": "determiner_noun_agreement_with_adj_irregular_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_with_adj_irregular_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_with_adjective_1": {
+            "dataset_name": "determiner_noun_agreement_with_adjective_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adjective_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_with_adjective_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_distractor_agreement_relational_noun": {
+            "dataset_name": "distractor_agreement_relational_noun",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relational_noun.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_distractor_agreement_relational_noun",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_distractor_agreement_relative_clause": {
+            "dataset_name": "distractor_agreement_relative_clause",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relative_clause.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_distractor_agreement_relative_clause",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_drop_argument": {
+            "dataset_name": "drop_argument",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/drop_argument.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_drop_argument",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_ellipsis_n_bar_1": {
+            "dataset_name": "ellipsis_n_bar_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_ellipsis_n_bar_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_ellipsis_n_bar_2": {
+            "dataset_name": "ellipsis_n_bar_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_ellipsis_n_bar_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_existential_there_object_raising": {
+            "dataset_name": "existential_there_object_raising",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_object_raising.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_existential_there_object_raising",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_existential_there_quantifiers_1": {
+            "dataset_name": "existential_there_quantifiers_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_existential_there_quantifiers_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_existential_there_quantifiers_2": {
+            "dataset_name": "existential_there_quantifiers_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_existential_there_quantifiers_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_existential_there_subject_raising": {
+            "dataset_name": "existential_there_subject_raising",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_subject_raising.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_existential_there_subject_raising",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_expletive_it_object_raising": {
+            "dataset_name": "expletive_it_object_raising",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/expletive_it_object_raising.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_expletive_it_object_raising",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_inchoative": {
+            "dataset_name": "inchoative",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/inchoative.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_inchoative",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_intransitive": {
+            "dataset_name": "intransitive",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/intransitive.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_intransitive",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_irregular_past_participle_adjectives": {
+            "dataset_name": "irregular_past_participle_adjectives",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_adjectives.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_irregular_past_participle_adjectives",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_irregular_past_participle_verbs": {
+            "dataset_name": "irregular_past_participle_verbs",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_verbs.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_irregular_past_participle_verbs",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_irregular_plural_subject_verb_agreement_1": {
+            "dataset_name": "irregular_plural_subject_verb_agreement_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_irregular_plural_subject_verb_agreement_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_irregular_plural_subject_verb_agreement_2": {
+            "dataset_name": "irregular_plural_subject_verb_agreement_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_irregular_plural_subject_verb_agreement_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_left_branch_island_echo_question": {
+            "dataset_name": "left_branch_island_echo_question",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_echo_question.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_left_branch_island_echo_question",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_left_branch_island_simple_question": {
+            "dataset_name": "left_branch_island_simple_question",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_simple_question.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_left_branch_island_simple_question",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_matrix_question_npi_licensor_present": {
+            "dataset_name": "matrix_question_npi_licensor_present",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/matrix_question_npi_licensor_present.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_matrix_question_npi_licensor_present",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_npi_present_1": {
+            "dataset_name": "npi_present_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_npi_present_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_npi_present_2": {
+            "dataset_name": "npi_present_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_npi_present_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_only_npi_licensor_present": {
+            "dataset_name": "only_npi_licensor_present",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_licensor_present.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_only_npi_licensor_present",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_only_npi_scope": {
+            "dataset_name": "only_npi_scope",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_scope.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_only_npi_scope",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_passive_1": {
+            "dataset_name": "passive_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_passive_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_passive_2": {
+            "dataset_name": "passive_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_passive_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_c_command": {
+            "dataset_name": "principle_A_c_command",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_c_command.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_c_command",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_case_1": {
+            "dataset_name": "principle_A_case_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_case_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_case_2": {
+            "dataset_name": "principle_A_case_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_case_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_domain_1": {
+            "dataset_name": "principle_A_domain_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_domain_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_domain_2": {
+            "dataset_name": "principle_A_domain_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_domain_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_domain_3": {
+            "dataset_name": "principle_A_domain_3",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_3.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_domain_3",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_reconstruction": {
+            "dataset_name": "principle_A_reconstruction",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_reconstruction.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_reconstruction",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_regular_plural_subject_verb_agreement_1": {
+            "dataset_name": "regular_plural_subject_verb_agreement_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_regular_plural_subject_verb_agreement_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_regular_plural_subject_verb_agreement_2": {
+            "dataset_name": "regular_plural_subject_verb_agreement_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_regular_plural_subject_verb_agreement_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_sentential_negation_npi_licensor_present": {
+            "dataset_name": "sentential_negation_npi_licensor_present",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_licensor_present.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_sentential_negation_npi_licensor_present",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_sentential_negation_npi_scope": {
+            "dataset_name": "sentential_negation_npi_scope",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_sentential_negation_npi_scope",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_sentential_subject_island": {
+            "dataset_name": "sentential_subject_island",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_subject_island.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_sentential_subject_island",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_superlative_quantifiers_1": {
+            "dataset_name": "superlative_quantifiers_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_superlative_quantifiers_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_superlative_quantifiers_2": {
+            "dataset_name": "superlative_quantifiers_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_superlative_quantifiers_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_tough_vs_raising_1": {
+            "dataset_name": "tough_vs_raising_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_tough_vs_raising_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_tough_vs_raising_2": {
+            "dataset_name": "tough_vs_raising_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_tough_vs_raising_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_transitive": {
+            "dataset_name": "transitive",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/transitive.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_transitive",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_island": {
+            "dataset_name": "wh_island",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_island.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_island",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_questions_object_gap": {
+            "dataset_name": "wh_questions_object_gap",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_object_gap.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_questions_object_gap",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_questions_subject_gap": {
+            "dataset_name": "wh_questions_subject_gap",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_questions_subject_gap",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_questions_subject_gap_long_distance": {
+            "dataset_name": "wh_questions_subject_gap_long_distance",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_questions_subject_gap_long_distance",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_vs_that_no_gap": {
+            "dataset_name": "wh_vs_that_no_gap",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_vs_that_no_gap",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_vs_that_no_gap_long_distance": {
+            "dataset_name": "wh_vs_that_no_gap_long_distance",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_vs_that_no_gap_long_distance",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_vs_that_with_gap": {
+            "dataset_name": "wh_vs_that_with_gap",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_vs_that_with_gap",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_vs_that_with_gap_long_distance": {
+            "dataset_name": "wh_vs_that_with_gap_long_distance",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_vs_that_with_gap_long_distance",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "commonsense_qa_text": {
+            "dataset_path": "tau/commonsense_qa",
+            "description": "",
+            "doc_to_choice": "{{ choices.text }}",
+            "doc_to_target": "{{ choices.label.index(answerKey) }}",
+            "doc_to_text": "Question: {{ question.strip() }}\nAnswer:",
+            "fewshot_config": {
+              "doc_to_choice": "{{ choices.text }}",
+              "doc_to_target": "{{ choices.label.index(answerKey) }}",
+              "doc_to_text": "Question: {{ question.strip() }}\nAnswer:",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/config/tasks/commonsense_qa_text.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": false,
+            "target_delimiter": " ",
+            "task": "commonsense_qa_text",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          },
+          "hellaswag": {
+            "dataset_path": "Rowan/hellaswag",
+            "description": "",
+            "doc_to_choice": "choices",
+            "doc_to_target": "{{label}}",
+            "doc_to_text": "{{query}}",
+            "fewshot_config": {
+              "doc_to_choice": "choices",
+              "doc_to_target": "{{label}}",
+              "doc_to_text": "{{query}}",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": "<function process_docs at 0x7e746d33d940>",
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/hellaswag/hellaswag.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n    def _process_doc(doc):\n        ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n        out_doc = {\n            \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n            \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n            \"gold\": int(doc[\"label\"]),\n        }\n        return out_doc\n\n    return dataset.map(_process_doc)\n",
+            "repeats": 1,
+            "should_decontaminate": false,
+            "target_delimiter": " ",
+            "task": "hellaswag",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          },
+          "piqa": {
+            "dataset_path": "baber/piqa",
+            "description": "",
+            "doc_to_choice": "{{[sol1, sol2]}}",
+            "doc_to_decontamination_query": "goal",
+            "doc_to_target": "label",
+            "doc_to_text": "Question: {{goal}}\nAnswer:",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sol1, sol2]}}",
+              "doc_to_target": "label",
+              "doc_to_text": "Question: {{goal}}\nAnswer:",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/piqa/piqa.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/lfm2-350m",
+              "tokenizer": "models/lfm2-350m",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "piqa",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          }
+        },
+        "task_versions": {
+          "arc_challenge": 1.0,
+          "arc_easy": 1.0,
+          "blimp": "2.0",
+          "blimp_adjunct_island": 1.0,
+          "blimp_anaphor_gender_agreement": 1.0,
+          "blimp_anaphor_number_agreement": 1.0,
+          "blimp_animate_subject_passive": 1.0,
+          "blimp_animate_subject_trans": 1.0,
+          "blimp_causative": 1.0,
+          "blimp_complex_NP_island": 1.0,
+          "blimp_coordinate_structure_constraint_complex_left_branch": 1.0,
+          "blimp_coordinate_structure_constraint_object_extraction": 1.0,
+          "blimp_determiner_noun_agreement_1": 1.0,
+          "blimp_determiner_noun_agreement_2": 1.0,
+          "blimp_determiner_noun_agreement_irregular_1": 1.0,
+          "blimp_determiner_noun_agreement_irregular_2": 1.0,
+          "blimp_determiner_noun_agreement_with_adj_2": 1.0,
+          "blimp_determiner_noun_agreement_with_adj_irregular_1": 1.0,
+          "blimp_determiner_noun_agreement_with_adj_irregular_2": 1.0,
+          "blimp_determiner_noun_agreement_with_adjective_1": 1.0,
+          "blimp_distractor_agreement_relational_noun": 1.0,
+          "blimp_distractor_agreement_relative_clause": 1.0,
+          "blimp_drop_argument": 1.0,
+          "blimp_ellipsis_n_bar_1": 1.0,
+          "blimp_ellipsis_n_bar_2": 1.0,
+          "blimp_existential_there_object_raising": 1.0,
+          "blimp_existential_there_quantifiers_1": 1.0,
+          "blimp_existential_there_quantifiers_2": 1.0,
+          "blimp_existential_there_subject_raising": 1.0,
+          "blimp_expletive_it_object_raising": 1.0,
+          "blimp_inchoative": 1.0,
+          "blimp_intransitive": 1.0,
+          "blimp_irregular_past_participle_adjectives": 1.0,
+          "blimp_irregular_past_participle_verbs": 1.0,
+          "blimp_irregular_plural_subject_verb_agreement_1": 1.0,
+          "blimp_irregular_plural_subject_verb_agreement_2": 1.0,
+          "blimp_left_branch_island_echo_question": 1.0,
+          "blimp_left_branch_island_simple_question": 1.0,
+          "blimp_matrix_question_npi_licensor_present": 1.0,
+          "blimp_npi_present_1": 1.0,
+          "blimp_npi_present_2": 1.0,
+          "blimp_only_npi_licensor_present": 1.0,
+          "blimp_only_npi_scope": 1.0,
+          "blimp_passive_1": 1.0,
+          "blimp_passive_2": 1.0,
+          "blimp_principle_A_c_command": 1.0,
+          "blimp_principle_A_case_1": 1.0,
+          "blimp_principle_A_case_2": 1.0,
+          "blimp_principle_A_domain_1": 1.0,
+          "blimp_principle_A_domain_2": 1.0,
+          "blimp_principle_A_domain_3": 1.0,
+          "blimp_principle_A_reconstruction": 1.0,
+          "blimp_regular_plural_subject_verb_agreement_1": 1.0,
+          "blimp_regular_plural_subject_verb_agreement_2": 1.0,
+          "blimp_sentential_negation_npi_licensor_present": 1.0,
+          "blimp_sentential_negation_npi_scope": 1.0,
+          "blimp_sentential_subject_island": 1.0,
+          "blimp_superlative_quantifiers_1": 1.0,
+          "blimp_superlative_quantifiers_2": 1.0,
+          "blimp_tough_vs_raising_1": 1.0,
+          "blimp_tough_vs_raising_2": 1.0,
+          "blimp_transitive": 1.0,
+          "blimp_wh_island": 1.0,
+          "blimp_wh_questions_object_gap": 1.0,
+          "blimp_wh_questions_subject_gap": 1.0,
+          "blimp_wh_questions_subject_gap_long_distance": 1.0,
+          "blimp_wh_vs_that_no_gap": 1.0,
+          "blimp_wh_vs_that_no_gap_long_distance": 1.0,
+          "blimp_wh_vs_that_with_gap": 1.0,
+          "blimp_wh_vs_that_with_gap_long_distance": 1.0,
+          "commonsense_qa_text": "Yaml",
+          "hellaswag": 1.0,
+          "piqa": 1.0
+        }
+      },
+      "rank_range": [
+        1,
+        2
+      ],
+      "release_date": "2025-07-10",
+      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154647Z-v1.1",
+      "source": "LiquidAI/LFM2-350M",
+      "track": "instruction",
+      "updated_at": "2026-07-16T15:46:57.444261+00:00",
+      "vocab_size": 65536
+    },
+    {
+      "artifacts": {
+        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154647Z-v1.1/results_v1.1_merged.json",
+        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154647Z-v1.1"
+      },
+      "benchmarks": {
+        "arc_challenge": {
+          "accuracy": 0.3199658703071672,
+          "chance": 0.25,
+          "ci": [
+            5.802047781569963,
+            13.083048919226394
+          ],
+          "classification": "reliably above chance",
+          "label": "ARC-Challenge",
+          "n_samples": 1172,
+          "score": 9.328782707622297
+        },
+        "arc_easy": {
+          "accuracy": 0.5845959595959596,
+          "chance": 0.25,
+          "ci": [
+            41.86307519640854,
+            47.1955667789001
+          ],
+          "classification": "reliably above chance",
+          "label": "ARC-Easy",
+          "n_samples": 2376,
+          "score": 44.61279461279461
+        },
+        "blimp": {
+          "accuracy": 0.8435170304232805,
+          "categories": {
+            "Anaphor agreement": 0.986,
+            "Argument structure": 0.8395555555555556,
+            "Binding": 0.7834285714285715,
+            "Control / raising": 0.8469999999999999,
+            "Determiner-noun agreement": 0.95575,
+            "Ellipsis": 0.8895,
+            "Filler-gap": 0.7902857142857144,
+            "Irregular forms": 0.9515,
+            "Island effects": 0.694125,
+            "NPI licensing": 0.7531428571428572,
+            "Quantifiers": 0.7372500000000001,
+            "Subject-verb agreement": 0.8946666666666667
+          },
+          "category_count": 12,
+          "chance": 0.5,
+          "ci": [
+            67.90119460978836,
+            68.90242162698412
+          ],
+          "classification": "reliably above chance",
+          "label": "BLiMP",
+          "n_samples": 70000,
+          "score": 68.70340608465611
+        },
+        "commonsense_qa": {
+          "accuracy": 0.4095004095004095,
+          "chance": 0.2,
+          "ci": [
+            22.91154791154791,
+            29.67086404586403
+          ],
+          "classification": "reliably above chance",
+          "label": "CommonsenseQA",
+          "n_samples": 1221,
+          "score": 26.187551187551186
+        },
+        "hellaswag": {
+          "accuracy": 0.5212109141605258,
+          "chance": 0.25,
+          "ci": [
+            34.846976033990565,
+            37.50282148310429
+          ],
+          "classification": "reliably above chance",
+          "label": "HellaSwag",
+          "n_samples": 10042,
+          "score": 36.161455221403436
+        },
+        "piqa": {
+          "accuracy": 0.6942328618063112,
+          "chance": 0.5,
+          "ci": [
+            34.71164309031556,
+            42.763873775843294
+          ],
+          "classification": "reliably above chance",
+          "label": "PIQA",
+          "n_samples": 1838,
+          "score": 38.84657236126223
+        }
+      },
+      "complete": true,
+      "composite": {
+        "ci": [
+          41.86348233604306,
+          43.96668012300082
+        ],
+        "classification": "reliably above chance",
+        "score": 42.989729225325554
+      },
+      "id": "qwen2-5-0-5b",
+      "name": "Qwen2.5 0.5B",
+      "params_m": 494.0,
+      "protocol": {
+        "bootstrap_replicates": 2000,
+        "bootstrap_seed": 20260716,
+        "harness": "lm-eval==0.4.12",
+        "harness_git_hash": null,
+        "inference_config": {
+          "batch_size": "auto",
+          "batch_sizes": [
+            64
+          ],
+          "bootstrap_iters": 100000,
+          "device": "cuda:0",
+          "fewshot_seed": 1234,
+          "gen_kwargs": {},
+          "limit": null,
+          "model": "hf",
+          "model_args": {
+            "dtype": "bfloat16",
+            "pretrained": "models/qwen2.5-0.5b",
+            "tokenizer": "models/qwen2.5-0.5b",
+            "trust_remote_code": false
+          },
+          "model_dtype": "torch.bfloat16",
+          "model_num_parameters": 494032768,
+          "model_revision": "main",
+          "model_sha": "",
+          "numpy_seed": 1234,
+          "random_seed": 1234,
+          "tasks": [
+            "hellaswag",
+            "piqa",
+            "arc_easy",
+            "arc_challenge",
+            "commonsense_qa_text",
+            "blimp"
+          ],
+          "torch_seed": 1234,
+          "use_cache": null,
+          "v1_1_sources": {
+            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154341Z-v1.1/results_v1.1_merged.json",
+            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154341Z-v1.1/results_v1.1_merged.json"
+          }
+        },
+        "n_shot": {
+          "arc_easy": 0,
+          "blimp": 0,
+          "blimp_adjunct_island": 0,
+          "blimp_anaphor_gender_agreement": 0,
+          "blimp_anaphor_number_agreement": 0,
+          "blimp_animate_subject_passive": 0,
+          "blimp_animate_subject_trans": 0,
+          "blimp_causative": 0,
+          "blimp_complex_NP_island": 0,
+          "blimp_coordinate_structure_constraint_complex_left_branch": 0,
+          "blimp_coordinate_structure_constraint_object_extraction": 0,
+          "blimp_determiner_noun_agreement_1": 0,
+          "blimp_determiner_noun_agreement_2": 0,
+          "blimp_determiner_noun_agreement_irregular_1": 0,
+          "blimp_determiner_noun_agreement_irregular_2": 0,
+          "blimp_determiner_noun_agreement_with_adj_2": 0,
+          "blimp_determiner_noun_agreement_with_adj_irregular_1": 0,
+          "blimp_determiner_noun_agreement_with_adj_irregular_2": 0,
+          "blimp_determiner_noun_agreement_with_adjective_1": 0,
+          "blimp_distractor_agreement_relational_noun": 0,
+          "blimp_distractor_agreement_relative_clause": 0,
+          "blimp_drop_argument": 0,
+          "blimp_ellipsis_n_bar_1": 0,
+          "blimp_ellipsis_n_bar_2": 0,
+          "blimp_existential_there_object_raising": 0,
+          "blimp_existential_there_quantifiers_1": 0,
+          "blimp_existential_there_quantifiers_2": 0,
+          "blimp_existential_there_subject_raising": 0,
+          "blimp_expletive_it_object_raising": 0,
+          "blimp_inchoative": 0,
+          "blimp_intransitive": 0,
+          "blimp_irregular_past_participle_adjectives": 0,
+          "blimp_irregular_past_participle_verbs": 0,
+          "blimp_irregular_plural_subject_verb_agreement_1": 0,
+          "blimp_irregular_plural_subject_verb_agreement_2": 0,
+          "blimp_left_branch_island_echo_question": 0,
+          "blimp_left_branch_island_simple_question": 0,
+          "blimp_matrix_question_npi_licensor_present": 0,
+          "blimp_npi_present_1": 0,
+          "blimp_npi_present_2": 0,
+          "blimp_only_npi_licensor_present": 0,
+          "blimp_only_npi_scope": 0,
+          "blimp_passive_1": 0,
+          "blimp_passive_2": 0,
+          "blimp_principle_A_c_command": 0,
+          "blimp_principle_A_case_1": 0,
+          "blimp_principle_A_case_2": 0,
+          "blimp_principle_A_domain_1": 0,
+          "blimp_principle_A_domain_2": 0,
+          "blimp_principle_A_domain_3": 0,
+          "blimp_principle_A_reconstruction": 0,
+          "blimp_regular_plural_subject_verb_agreement_1": 0,
+          "blimp_regular_plural_subject_verb_agreement_2": 0,
+          "blimp_sentential_negation_npi_licensor_present": 0,
+          "blimp_sentential_negation_npi_scope": 0,
+          "blimp_sentential_subject_island": 0,
+          "blimp_superlative_quantifiers_1": 0,
+          "blimp_superlative_quantifiers_2": 0,
+          "blimp_tough_vs_raising_1": 0,
+          "blimp_tough_vs_raising_2": 0,
+          "blimp_transitive": 0,
+          "blimp_wh_island": 0,
+          "blimp_wh_questions_object_gap": 0,
+          "blimp_wh_questions_subject_gap": 0,
+          "blimp_wh_questions_subject_gap_long_distance": 0,
+          "blimp_wh_vs_that_no_gap": 0,
+          "blimp_wh_vs_that_no_gap_long_distance": 0,
+          "blimp_wh_vs_that_with_gap": 0,
+          "blimp_wh_vs_that_with_gap_long_distance": 0,
+          "commonsense_qa": 0,
+          "hellaswag": 0,
+          "piqa": 0
+        },
+        "suite": "slm-benchmark-v1.1",
+        "task_config": {
+          "arc_challenge": {
+            "dataset_name": "ARC-Challenge",
+            "dataset_path": "allenai/ai2_arc",
+            "description": "",
+            "doc_to_choice": "{{choices.text}}",
+            "doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
+            "doc_to_target": "{{choices.label.index(answerKey)}}",
+            "doc_to_text": "Question: {{question}}\nAnswer:",
+            "fewshot_config": {
+              "doc_to_choice": "{{choices.text}}",
+              "doc_to_target": "{{choices.label.index(answerKey)}}",
+              "doc_to_text": "Question: {{question}}\nAnswer:",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_challenge.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "arc_challenge",
+            "test_split": "test",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          },
+          "arc_easy": {
+            "dataset_name": "ARC-Easy",
+            "dataset_path": "allenai/ai2_arc",
+            "description": "",
+            "doc_to_choice": "{{choices.text}}",
+            "doc_to_decontamination_query": "Question: {{question}}\nAnswer:",
+            "doc_to_target": "{{choices.label.index(answerKey)}}",
+            "doc_to_text": "Question: {{question}}\nAnswer:",
+            "fewshot_config": {
+              "doc_to_choice": "{{choices.text}}",
+              "doc_to_target": "{{choices.label.index(answerKey)}}",
+              "doc_to_text": "Question: {{question}}\nAnswer:",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_easy.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "arc_easy",
+            "test_split": "test",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          },
+          "blimp_adjunct_island": {
+            "dataset_name": "adjunct_island",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/adjunct_island.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_adjunct_island",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_anaphor_gender_agreement": {
+            "dataset_name": "anaphor_gender_agreement",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_gender_agreement.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_anaphor_gender_agreement",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_anaphor_number_agreement": {
+            "dataset_name": "anaphor_number_agreement",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_number_agreement.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_anaphor_number_agreement",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_animate_subject_passive": {
+            "dataset_name": "animate_subject_passive",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_passive.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_animate_subject_passive",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_animate_subject_trans": {
+            "dataset_name": "animate_subject_trans",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_trans.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_animate_subject_trans",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_causative": {
+            "dataset_name": "causative",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/causative.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_causative",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_complex_NP_island": {
+            "dataset_name": "complex_NP_island",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/complex_NP_island.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_complex_NP_island",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_coordinate_structure_constraint_complex_left_branch": {
+            "dataset_name": "coordinate_structure_constraint_complex_left_branch",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_complex_left_branch.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_coordinate_structure_constraint_complex_left_branch",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_coordinate_structure_constraint_object_extraction": {
+            "dataset_name": "coordinate_structure_constraint_object_extraction",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_object_extraction.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_coordinate_structure_constraint_object_extraction",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_1": {
+            "dataset_name": "determiner_noun_agreement_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_2": {
+            "dataset_name": "determiner_noun_agreement_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_irregular_1": {
+            "dataset_name": "determiner_noun_agreement_irregular_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_irregular_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_irregular_2": {
+            "dataset_name": "determiner_noun_agreement_irregular_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_irregular_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_with_adj_2": {
+            "dataset_name": "determiner_noun_agreement_with_adj_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_with_adj_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_with_adj_irregular_1": {
+            "dataset_name": "determiner_noun_agreement_with_adj_irregular_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_with_adj_irregular_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_with_adj_irregular_2": {
+            "dataset_name": "determiner_noun_agreement_with_adj_irregular_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_with_adj_irregular_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_determiner_noun_agreement_with_adjective_1": {
+            "dataset_name": "determiner_noun_agreement_with_adjective_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adjective_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_determiner_noun_agreement_with_adjective_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_distractor_agreement_relational_noun": {
+            "dataset_name": "distractor_agreement_relational_noun",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relational_noun.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_distractor_agreement_relational_noun",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_distractor_agreement_relative_clause": {
+            "dataset_name": "distractor_agreement_relative_clause",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relative_clause.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_distractor_agreement_relative_clause",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_drop_argument": {
+            "dataset_name": "drop_argument",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/drop_argument.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_drop_argument",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_ellipsis_n_bar_1": {
+            "dataset_name": "ellipsis_n_bar_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_ellipsis_n_bar_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_ellipsis_n_bar_2": {
+            "dataset_name": "ellipsis_n_bar_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_ellipsis_n_bar_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_existential_there_object_raising": {
+            "dataset_name": "existential_there_object_raising",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_object_raising.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_existential_there_object_raising",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_existential_there_quantifiers_1": {
+            "dataset_name": "existential_there_quantifiers_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_existential_there_quantifiers_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_existential_there_quantifiers_2": {
+            "dataset_name": "existential_there_quantifiers_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_existential_there_quantifiers_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_existential_there_subject_raising": {
+            "dataset_name": "existential_there_subject_raising",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_subject_raising.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_existential_there_subject_raising",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_expletive_it_object_raising": {
+            "dataset_name": "expletive_it_object_raising",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/expletive_it_object_raising.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_expletive_it_object_raising",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_inchoative": {
+            "dataset_name": "inchoative",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/inchoative.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_inchoative",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_intransitive": {
+            "dataset_name": "intransitive",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/intransitive.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_intransitive",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_irregular_past_participle_adjectives": {
+            "dataset_name": "irregular_past_participle_adjectives",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_adjectives.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_irregular_past_participle_adjectives",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_irregular_past_participle_verbs": {
+            "dataset_name": "irregular_past_participle_verbs",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_verbs.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_irregular_past_participle_verbs",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_irregular_plural_subject_verb_agreement_1": {
+            "dataset_name": "irregular_plural_subject_verb_agreement_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_irregular_plural_subject_verb_agreement_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_irregular_plural_subject_verb_agreement_2": {
+            "dataset_name": "irregular_plural_subject_verb_agreement_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_irregular_plural_subject_verb_agreement_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_left_branch_island_echo_question": {
+            "dataset_name": "left_branch_island_echo_question",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_echo_question.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_left_branch_island_echo_question",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_left_branch_island_simple_question": {
+            "dataset_name": "left_branch_island_simple_question",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_simple_question.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_left_branch_island_simple_question",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_matrix_question_npi_licensor_present": {
+            "dataset_name": "matrix_question_npi_licensor_present",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/matrix_question_npi_licensor_present.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_matrix_question_npi_licensor_present",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_npi_present_1": {
+            "dataset_name": "npi_present_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_npi_present_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_npi_present_2": {
+            "dataset_name": "npi_present_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_npi_present_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_only_npi_licensor_present": {
+            "dataset_name": "only_npi_licensor_present",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_licensor_present.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_only_npi_licensor_present",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_only_npi_scope": {
+            "dataset_name": "only_npi_scope",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_scope.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_only_npi_scope",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_passive_1": {
+            "dataset_name": "passive_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_passive_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_passive_2": {
+            "dataset_name": "passive_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_passive_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_c_command": {
+            "dataset_name": "principle_A_c_command",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_c_command.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_c_command",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_case_1": {
+            "dataset_name": "principle_A_case_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_case_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_case_2": {
+            "dataset_name": "principle_A_case_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_case_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_domain_1": {
+            "dataset_name": "principle_A_domain_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_domain_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_domain_2": {
+            "dataset_name": "principle_A_domain_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_domain_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_domain_3": {
+            "dataset_name": "principle_A_domain_3",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_3.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_domain_3",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_principle_A_reconstruction": {
+            "dataset_name": "principle_A_reconstruction",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_reconstruction.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_principle_A_reconstruction",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_regular_plural_subject_verb_agreement_1": {
+            "dataset_name": "regular_plural_subject_verb_agreement_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_regular_plural_subject_verb_agreement_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_regular_plural_subject_verb_agreement_2": {
+            "dataset_name": "regular_plural_subject_verb_agreement_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_regular_plural_subject_verb_agreement_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_sentential_negation_npi_licensor_present": {
+            "dataset_name": "sentential_negation_npi_licensor_present",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_licensor_present.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_sentential_negation_npi_licensor_present",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_sentential_negation_npi_scope": {
+            "dataset_name": "sentential_negation_npi_scope",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_sentential_negation_npi_scope",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_sentential_subject_island": {
+            "dataset_name": "sentential_subject_island",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_subject_island.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_sentential_subject_island",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_superlative_quantifiers_1": {
+            "dataset_name": "superlative_quantifiers_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_superlative_quantifiers_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_superlative_quantifiers_2": {
+            "dataset_name": "superlative_quantifiers_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_superlative_quantifiers_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_tough_vs_raising_1": {
+            "dataset_name": "tough_vs_raising_1",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_1.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_tough_vs_raising_1",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_tough_vs_raising_2": {
+            "dataset_name": "tough_vs_raising_2",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_2.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_tough_vs_raising_2",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_transitive": {
+            "dataset_name": "transitive",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/transitive.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_transitive",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_island": {
+            "dataset_name": "wh_island",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_island.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_island",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_questions_object_gap": {
+            "dataset_name": "wh_questions_object_gap",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_object_gap.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_questions_object_gap",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_questions_subject_gap": {
+            "dataset_name": "wh_questions_subject_gap",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_questions_subject_gap",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_questions_subject_gap_long_distance": {
+            "dataset_name": "wh_questions_subject_gap_long_distance",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_questions_subject_gap_long_distance",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_vs_that_no_gap": {
+            "dataset_name": "wh_vs_that_no_gap",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_vs_that_no_gap",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_vs_that_no_gap_long_distance": {
+            "dataset_name": "wh_vs_that_no_gap_long_distance",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_vs_that_no_gap_long_distance",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_vs_that_with_gap": {
+            "dataset_name": "wh_vs_that_with_gap",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_vs_that_with_gap",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "blimp_wh_vs_that_with_gap_long_distance": {
+            "dataset_name": "wh_vs_that_with_gap_long_distance",
+            "dataset_path": "nyu-mll/blimp",
+            "description": "",
+            "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+            "doc_to_decontamination_query": "{{sentence_good}} {{sentence_bad}}",
+            "doc_to_target": 0,
+            "doc_to_text": "",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sentence_good, sentence_bad]}}",
+              "doc_to_target": 0,
+              "doc_to_text": "",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "blimp_wh_vs_that_with_gap_long_distance",
+            "unsafe_code": false,
+            "validation_split": "train"
+          },
+          "commonsense_qa_text": {
+            "dataset_path": "tau/commonsense_qa",
+            "description": "",
+            "doc_to_choice": "{{ choices.text }}",
+            "doc_to_target": "{{ choices.label.index(answerKey) }}",
+            "doc_to_text": "Question: {{ question.strip() }}\nAnswer:",
+            "fewshot_config": {
+              "doc_to_choice": "{{ choices.text }}",
+              "doc_to_target": "{{ choices.label.index(answerKey) }}",
+              "doc_to_text": "Question: {{ question.strip() }}\nAnswer:",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/config/tasks/commonsense_qa_text.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": false,
+            "target_delimiter": " ",
+            "task": "commonsense_qa_text",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          },
+          "hellaswag": {
+            "dataset_path": "Rowan/hellaswag",
+            "description": "",
+            "doc_to_choice": "choices",
+            "doc_to_target": "{{label}}",
+            "doc_to_text": "{{query}}",
+            "fewshot_config": {
+              "doc_to_choice": "choices",
+              "doc_to_target": "{{label}}",
+              "doc_to_text": "{{query}}",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": "<function process_docs at 0x72645c9311c0>",
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/hellaswag/hellaswag.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "process_docs": "def process_docs(dataset: datasets.Dataset) -> datasets.Dataset:\n    def _process_doc(doc):\n        ctx = doc[\"ctx_a\"] + \" \" + doc[\"ctx_b\"].capitalize()\n        out_doc = {\n            \"query\": preprocess(doc[\"activity_label\"] + \": \" + ctx),\n            \"choices\": [preprocess(ending) for ending in doc[\"endings\"]],\n            \"gold\": int(doc[\"label\"]),\n        }\n        return out_doc\n\n    return dataset.map(_process_doc)\n",
+            "repeats": 1,
+            "should_decontaminate": false,
+            "target_delimiter": " ",
+            "task": "hellaswag",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          },
+          "piqa": {
+            "dataset_path": "baber/piqa",
+            "description": "",
+            "doc_to_choice": "{{[sol1, sol2]}}",
+            "doc_to_decontamination_query": "goal",
+            "doc_to_target": "label",
+            "doc_to_text": "Question: {{goal}}\nAnswer:",
+            "fewshot_config": {
+              "doc_to_choice": "{{[sol1, sol2]}}",
+              "doc_to_target": "label",
+              "doc_to_text": "Question: {{goal}}\nAnswer:",
+              "fewshot_delimiter": "\n\n",
+              "fewshot_indices": null,
+              "gen_prefix": null,
+              "process_docs": null,
+              "sampler": "default",
+              "samples": null,
+              "split": null,
+              "target_delimiter": " "
+            },
+            "fewshot_delimiter": "\n\n",
+            "metadata": {
+              "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/piqa/piqa.yaml",
+              "dtype": "bfloat16",
+              "pretrained": "models/qwen2.5-0.5b",
+              "tokenizer": "models/qwen2.5-0.5b",
+              "trust_remote_code": false,
+              "version": 1.0
+            },
+            "metric_list": [
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc"
+              },
+              {
+                "aggregation": "mean",
+                "higher_is_better": true,
+                "metric": "acc_norm"
+              }
+            ],
+            "num_fewshot": 0,
+            "output_type": "multiple_choice",
+            "repeats": 1,
+            "should_decontaminate": true,
+            "target_delimiter": " ",
+            "task": "piqa",
+            "training_split": "train",
+            "unsafe_code": false,
+            "validation_split": "validation"
+          }
+        },
+        "task_versions": {
+          "arc_challenge": 1.0,
+          "arc_easy": 1.0,
+          "blimp": "2.0",
+          "blimp_adjunct_island": 1.0,
+          "blimp_anaphor_gender_agreement": 1.0,
+          "blimp_anaphor_number_agreement": 1.0,
+          "blimp_animate_subject_passive": 1.0,
+          "blimp_animate_subject_trans": 1.0,
+          "blimp_causative": 1.0,
+          "blimp_complex_NP_island": 1.0,
+          "blimp_coordinate_structure_constraint_complex_left_branch": 1.0,
+          "blimp_coordinate_structure_constraint_object_extraction": 1.0,
+          "blimp_determiner_noun_agreement_1": 1.0,
+          "blimp_determiner_noun_agreement_2": 1.0,
+          "blimp_determiner_noun_agreement_irregular_1": 1.0,
+          "blimp_determiner_noun_agreement_irregular_2": 1.0,
+          "blimp_determiner_noun_agreement_with_adj_2": 1.0,
+          "blimp_determiner_noun_agreement_with_adj_irregular_1": 1.0,
+          "blimp_determiner_noun_agreement_with_adj_irregular_2": 1.0,
+          "blimp_determiner_noun_agreement_with_adjective_1": 1.0,
+          "blimp_distractor_agreement_relational_noun": 1.0,
+          "blimp_distractor_agreement_relative_clause": 1.0,
+          "blimp_drop_argument": 1.0,
+          "blimp_ellipsis_n_bar_1": 1.0,
+          "blimp_ellipsis_n_bar_2": 1.0,
+          "blimp_existential_there_object_raising": 1.0,
+          "blimp_existential_there_quantifiers_1": 1.0,
+          "blimp_existential_there_quantifiers_2": 1.0,
+          "blimp_existential_there_subject_raising": 1.0,
+          "blimp_expletive_it_object_raising": 1.0,
+          "blimp_inchoative": 1.0,
+          "blimp_intransitive": 1.0,
+          "blimp_irregular_past_participle_adjectives": 1.0,
+          "blimp_irregular_past_participle_verbs": 1.0,
+          "blimp_irregular_plural_subject_verb_agreement_1": 1.0,
+          "blimp_irregular_plural_subject_verb_agreement_2": 1.0,
+          "blimp_left_branch_island_echo_question": 1.0,
+          "blimp_left_branch_island_simple_question": 1.0,
+          "blimp_matrix_question_npi_licensor_present": 1.0,
+          "blimp_npi_present_1": 1.0,
+          "blimp_npi_present_2": 1.0,
+          "blimp_only_npi_licensor_present": 1.0,
+          "blimp_only_npi_scope": 1.0,
+          "blimp_passive_1": 1.0,
+          "blimp_passive_2": 1.0,
+          "blimp_principle_A_c_command": 1.0,
+          "blimp_principle_A_case_1": 1.0,
+          "blimp_principle_A_case_2": 1.0,
+          "blimp_principle_A_domain_1": 1.0,
+          "blimp_principle_A_domain_2": 1.0,
+          "blimp_principle_A_domain_3": 1.0,
+          "blimp_principle_A_reconstruction": 1.0,
+          "blimp_regular_plural_subject_verb_agreement_1": 1.0,
+          "blimp_regular_plural_subject_verb_agreement_2": 1.0,
+          "blimp_sentential_negation_npi_licensor_present": 1.0,
+          "blimp_sentential_negation_npi_scope": 1.0,
+          "blimp_sentential_subject_island": 1.0,
+          "blimp_superlative_quantifiers_1": 1.0,
+          "blimp_superlative_quantifiers_2": 1.0,
+          "blimp_tough_vs_raising_1": 1.0,
+          "blimp_tough_vs_raising_2": 1.0,
+          "blimp_transitive": 1.0,
+          "blimp_wh_island": 1.0,
+          "blimp_wh_questions_object_gap": 1.0,
+          "blimp_wh_questions_subject_gap": 1.0,
+          "blimp_wh_questions_subject_gap_long_distance": 1.0,
+          "blimp_wh_vs_that_no_gap": 1.0,
+          "blimp_wh_vs_that_no_gap_long_distance": 1.0,
+          "blimp_wh_vs_that_with_gap": 1.0,
+          "blimp_wh_vs_that_with_gap_long_distance": 1.0,
+          "commonsense_qa_text": "Yaml",
+          "hellaswag": 1.0,
+          "piqa": 1.0
+        }
+      },
+      "rank_range": [
+        1,
+        2
       ],
-      "difference": 9.11195381570115,
-      "matched_samples": {
-        "arc_challenge": 1172,
-        "arc_easy": 2376,
-        "blimp:Anaphor agreement": 2000,
-        "blimp:Argument structure": 9000,
-        "blimp:Binding": 7000,
-        "blimp:Control / raising": 5000,
-        "blimp:Determiner-noun agreement": 8000,
-        "blimp:Ellipsis": 2000,
-        "blimp:Filler-gap": 10000,
-        "blimp:Irregular forms": 2000,
-        "blimp:Island effects": 8000,
-        "blimp:NPI licensing": 7000,
-        "blimp:Quantifiers": 4000,
-        "blimp:Subject-verb agreement": 6000,
-        "commonsense_qa": 1221,
-        "hellaswag": 10042,
-        "piqa": 1838
-      },
-      "relation": "first_better"
+      "release_date": "2024-09-15",
+      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154647Z-v1.1",
+      "source": "Qwen/Qwen2.5-0.5B",
+      "track": "base",
+      "updated_at": "2026-07-16T15:47:02.275688+00:00",
+      "vocab_size": 151936
     },
-    "veyra2-apricot-50m-base__slm-10m": {
-      "ci": [
-        4.863643976660482,
-        6.735987982048942
-      ],
-      "difference": 5.813252336864407,
-      "matched_samples": {
-        "arc_challenge": 1172,
-        "arc_easy": 2376,
-        "blimp:Anaphor agreement": 2000,
-        "blimp:Argument structure": 9000,
-        "blimp:Binding": 7000,
-        "blimp:Control / raising": 5000,
-        "blimp:Determiner-noun agreement": 8000,
-        "blimp:Ellipsis": 2000,
-        "blimp:Filler-gap": 10000,
-        "blimp:Irregular forms": 2000,
-        "blimp:Island effects": 8000,
-        "blimp:NPI licensing": 7000,
-        "blimp:Quantifiers": 4000,
-        "blimp:Subject-verb agreement": 6000,
-        "commonsense_qa": 1221,
-        "hellaswag": 10042,
-        "piqa": 1838
-      },
-      "relation": "first_better"
-    }
-  },
-  "generated_at": "2026-07-22T07:57:07.788524+00:00",
-  "models": [
     {
       "artifacts": {
-        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154647Z-v1.1/results_v1.1_merged.json",
-        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154647Z-v1.1"
+        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154647Z-v1.1/results_v1.1_merged.json",
+        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154647Z-v1.1"
       },
       "benchmarks": {
         "arc_challenge": {
-          "accuracy": 0.39590443686006827,
+          "accuracy": 0.27986348122866894,
           "chance": 0.25,
           "ci": [
-            15.696814562002272,
-            23.321956769055745
+            0.5688282138794095,
+            7.281001137656425
           ],
           "classification": "reliably above chance",
           "label": "ARC-Challenge",
           "n_samples": 1172,
-          "score": 19.45392491467577
+          "score": 3.9817974971558585
         },
         "arc_easy": {
-          "accuracy": 0.6641414141414141,
+          "accuracy": 0.5728114478114478,
           "chance": 0.25,
           "ci": [
-            52.637485970819306,
-            57.744107744107744
+            40.404040404040394,
+            45.62289562289561
           ],
           "classification": "reliably above chance",
           "label": "ARC-Easy",
           "n_samples": 2376,
-          "score": 55.21885521885522
+          "score": 43.0415263748597
         },
         "blimp": {
-          "accuracy": 0.7906593253968254,
+          "accuracy": 0.8213405423280423,
           "categories": {
-            "Anaphor agreement": 0.977,
-            "Argument structure": 0.7756666666666666,
-            "Binding": 0.7418571428571428,
-            "Control / raising": 0.8074,
-            "Determiner-noun agreement": 0.9377500000000001,
-            "Ellipsis": 0.8654999999999999,
-            "Filler-gap": 0.7779999999999999,
-            "Irregular forms": 0.728,
-            "Island effects": 0.739,
-            "NPI licensing": 0.5485714285714286,
-            "Quantifiers": 0.7414999999999999,
-            "Subject-verb agreement": 0.8476666666666666
+            "Anaphor agreement": 0.99,
+            "Argument structure": 0.7935555555555555,
+            "Binding": 0.7918571428571427,
+            "Control / raising": 0.8374,
+            "Determiner-noun agreement": 0.956,
+            "Ellipsis": 0.87,
+            "Filler-gap": 0.7927142857142858,
+            "Irregular forms": 0.9295,
+            "Island effects": 0.68875,
+            "NPI licensing": 0.668142857142857,
+            "Quantifiers": 0.7084999999999999,
+            "Subject-verb agreement": 0.8296666666666667
           },
           "category_count": 12,
           "chance": 0.5,
           "ci": [
-            57.22199222883596,
-            58.42621676587302
+            63.49301306216931,
+            64.53917559523809
           ],
           "classification": "reliably above chance",
           "label": "BLiMP",
           "n_samples": 70000,
-          "score": 58.13186507936508
+          "score": 64.26810846560846
         },
         "commonsense_qa": {
-          "accuracy": 0.45045045045045046,
+          "accuracy": 0.4258804258804259,
           "chance": 0.2,
           "ci": [
-            27.927927927927925,
-            34.88943488943489
+            24.754299754299755,
+            31.71580671580671
           ],
           "classification": "reliably above chance",
           "label": "CommonsenseQA",
           "n_samples": 1221,
-          "score": 31.306306306306304
+          "score": 28.235053235053236
         },
         "hellaswag": {
-          "accuracy": 0.4898426608245369,
+          "accuracy": 0.4144592710615415,
           "chance": 0.25,
           "ci": [
-            30.61143198566022,
-            33.25433180641306
+            20.65325632344155,
+            23.29582420500564
           ],
           "classification": "reliably above chance",
           "label": "HellaSwag",
           "n_samples": 10042,
-          "score": 31.97902144327159
+          "score": 21.927902808205534
         },
         "piqa": {
-          "accuracy": 0.6958650707290533,
+          "accuracy": 0.6849836779107725,
           "chance": 0.5,
           "ci": [
-            35.03808487486397,
-            43.2018498367791
+            32.86180631120783,
+            41.240478781284004
           ],
           "classification": "reliably above chance",
           "label": "PIQA",
           "n_samples": 1838,
-          "score": 39.17301414581067
+          "score": 36.99673558215451
         }
       },
       "complete": true,
       "composite": {
         "ci": [
-          42.03623437890757,
-          44.21094708361269
+          37.774028206553304,
+          39.9138118144519
         ],
         "classification": "reliably above chance",
-        "score": 43.17876224644195
+        "score": 38.912790926162764
       },
-      "id": "lfm2-350m",
-      "name": "LFM2 350M",
-      "params_m": 354.484,
+      "id": "gemma-3-270m",
+      "name": "Gemma 3 270M",
+      "params_m": 270.0,
       "protocol": {
         "bootstrap_replicates": 2000,
         "bootstrap_seed": 20260716,
         "harness": "lm-eval==0.4.12",
         "harness_git_hash": null,
         "inference_config": {
-          "batch_size": "auto",
-          "batch_sizes": [
-            64
-          ],
+          "batch_size": "32",
+          "batch_sizes": [],
           "bootstrap_iters": 100000,
           "device": "cuda:0",
           "fewshot_seed": 1234,
@@ -4258,12 +12559,12 @@
           "model": "hf",
           "model_args": {
             "dtype": "bfloat16",
-            "pretrained": "models/lfm2-350m",
-            "tokenizer": "models/lfm2-350m",
+            "pretrained": "models/gemma-3-270m",
+            "tokenizer": "models/gemma-3-270m",
             "trust_remote_code": false
           },
           "model_dtype": "torch.bfloat16",
-          "model_num_parameters": 354483968,
+          "model_num_parameters": 268098176,
           "model_revision": "main",
           "model_sha": "",
           "numpy_seed": 1234,
@@ -4279,8 +12580,8 @@
           "torch_seed": 1234,
           "use_cache": null,
           "v1_1_sources": {
-            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154341Z-v1.1/results_v1.1_merged.json",
-            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154341Z-v1.1/results_v1.1_merged.json"
+            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154341Z-v1.1/results_v1.1_merged.json",
+            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154341Z-v1.1/results_v1.1_merged.json"
           }
         },
         "n_shot": {
@@ -4384,8 +12685,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_challenge.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4437,8 +12738,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_easy.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4490,8 +12791,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/adjunct_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4536,8 +12837,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_gender_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4582,8 +12883,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_number_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4628,8 +12929,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_passive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4674,8 +12975,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_trans.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4720,8 +13021,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/causative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4766,8 +13067,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/complex_NP_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4812,8 +13113,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_complex_left_branch.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4858,8 +13159,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_object_extraction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4904,8 +13205,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4950,8 +13251,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -4996,8 +13297,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5042,8 +13343,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5088,8 +13389,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5134,8 +13435,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5180,8 +13481,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5226,8 +13527,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adjective_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5272,8 +13573,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relational_noun.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5318,8 +13619,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relative_clause.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5364,8 +13665,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/drop_argument.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5410,8 +13711,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5456,8 +13757,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5502,8 +13803,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5548,8 +13849,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5594,8 +13895,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5640,8 +13941,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_subject_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5686,8 +13987,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/expletive_it_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5732,8 +14033,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/inchoative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5778,8 +14079,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/intransitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5824,8 +14125,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_adjectives.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5870,8 +14171,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_verbs.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5916,8 +14217,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -5962,8 +14263,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6008,8 +14309,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_echo_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6054,8 +14355,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_simple_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6100,8 +14401,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/matrix_question_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6146,8 +14447,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6192,8 +14493,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6238,8 +14539,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6284,8 +14585,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6330,8 +14631,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6376,8 +14677,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6422,8 +14723,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_c_command.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6468,8 +14769,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6514,8 +14815,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6560,8 +14861,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6606,8 +14907,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6652,8 +14953,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_3.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6698,8 +14999,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_reconstruction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6744,8 +15045,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6790,8 +15091,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6836,8 +15137,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6882,8 +15183,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6928,8 +15229,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_subject_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -6974,8 +15275,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7020,8 +15321,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7066,8 +15367,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7112,8 +15413,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7158,8 +15459,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/transitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7204,8 +15505,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7250,8 +15551,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_object_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7296,8 +15597,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7342,8 +15643,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7388,8 +15689,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7434,8 +15735,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7480,8 +15781,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7526,8 +15827,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7570,8 +15871,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/config/tasks/commonsense_qa_text.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false
             },
             "metric_list": [
@@ -7609,7 +15910,7 @@
               "fewshot_delimiter": "\n\n",
               "fewshot_indices": null,
               "gen_prefix": null,
-              "process_docs": "<function process_docs at 0x7e746d33d940>",
+              "process_docs": "<function process_docs at 0x7ff024f928e0>",
               "sampler": "default",
               "samples": null,
               "split": null,
@@ -7619,8 +15920,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/hellaswag/hellaswag.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7671,8 +15972,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/piqa/piqa.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/lfm2-350m",
-              "tokenizer": "models/lfm2-350m",
+              "pretrained": "models/gemma-3-270m",
+              "tokenizer": "models/gemma-3-270m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -7776,122 +16077,122 @@
         }
       },
       "rank_range": [
-        1,
-        2
+        3,
+        3
       ],
-      "release_date": "2025-07-10",
-      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/lfm2-350m/20260716T154647Z-v1.1",
-      "source": "LiquidAI/LFM2-350M",
-      "track": "instruction",
-      "updated_at": "2026-07-16T15:46:57.444261+00:00",
-      "vocab_size": 65536
+      "release_date": "2025-08-05",
+      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154647Z-v1.1",
+      "source": "google/gemma-3-270m",
+      "track": "base",
+      "updated_at": "2026-07-16T15:46:49.790812+00:00",
+      "vocab_size": 262144
     },
     {
       "artifacts": {
-        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154647Z-v1.1/results_v1.1_merged.json",
-        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154647Z-v1.1"
+        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154647Z-v1.1/results_v1.1_merged.json",
+        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154647Z-v1.1"
       },
       "benchmarks": {
         "arc_challenge": {
-          "accuracy": 0.3199658703071672,
+          "accuracy": 0.29692832764505117,
           "chance": 0.25,
           "ci": [
-            5.802047781569963,
-            13.083048919226394
+            2.6166097838452806,
+            9.670079635949946
           ],
           "classification": "reliably above chance",
           "label": "ARC-Challenge",
           "n_samples": 1172,
-          "score": 9.328782707622297
+          "score": 6.2571103526734895
         },
         "arc_easy": {
-          "accuracy": 0.5845959595959596,
+          "accuracy": 0.5871212121212122,
           "chance": 0.25,
           "ci": [
-            41.86307519640854,
-            47.1955667789001
+            42.255892255892256,
+            47.53086419753087
           ],
           "classification": "reliably above chance",
           "label": "ARC-Easy",
           "n_samples": 2376,
-          "score": 44.61279461279461
+          "score": 44.949494949494955
         },
         "blimp": {
-          "accuracy": 0.8435170304232805,
+          "accuracy": 0.8136013227513228,
           "categories": {
-            "Anaphor agreement": 0.986,
-            "Argument structure": 0.8395555555555556,
-            "Binding": 0.7834285714285715,
-            "Control / raising": 0.8469999999999999,
-            "Determiner-noun agreement": 0.95575,
-            "Ellipsis": 0.8895,
-            "Filler-gap": 0.7902857142857144,
-            "Irregular forms": 0.9515,
-            "Island effects": 0.694125,
-            "NPI licensing": 0.7531428571428572,
-            "Quantifiers": 0.7372500000000001,
-            "Subject-verb agreement": 0.8946666666666667
+            "Anaphor agreement": 0.977,
+            "Argument structure": 0.8337777777777778,
+            "Binding": 0.7632857142857142,
+            "Control / raising": 0.8392000000000002,
+            "Determiner-noun agreement": 0.968,
+            "Ellipsis": 0.8745,
+            "Filler-gap": 0.7977142857142857,
+            "Irregular forms": 0.8380000000000001,
+            "Island effects": 0.6892499999999999,
+            "NPI licensing": 0.6485714285714286,
+            "Quantifiers": 0.67025,
+            "Subject-verb agreement": 0.8636666666666667
           },
           "category_count": 12,
           "chance": 0.5,
           "ci": [
-            67.90119460978836,
-            68.90242162698412
+            61.932142030423265,
+            63.0667154431217
           ],
           "classification": "reliably above chance",
           "label": "BLiMP",
           "n_samples": 70000,
-          "score": 68.70340608465611
+          "score": 62.72026455026456
         },
         "commonsense_qa": {
-          "accuracy": 0.4095004095004095,
+          "accuracy": 0.35544635544635544,
           "chance": 0.2,
           "ci": [
-            22.91154791154791,
-            29.67086404586403
+            16.152231777231773,
+            22.81173218673217
           ],
           "classification": "reliably above chance",
           "label": "CommonsenseQA",
           "n_samples": 1221,
-          "score": 26.187551187551186
+          "score": 19.43079443079443
         },
         "hellaswag": {
-          "accuracy": 0.5212109141605258,
+          "accuracy": 0.43218482374029077,
           "chance": 0.25,
           "ci": [
-            34.846976033990565,
-            37.50282148310429
+            23.016331408086035,
+            25.592511451902016
           ],
           "classification": "reliably above chance",
           "label": "HellaSwag",
           "n_samples": 10042,
-          "score": 36.161455221403436
+          "score": 24.291309832038767
         },
         "piqa": {
-          "accuracy": 0.6942328618063112,
+          "accuracy": 0.6817192600652884,
           "chance": 0.5,
           "ci": [
-            34.71164309031556,
-            42.763873775843294
+            32.097388465723604,
+            40.58759521218715
           ],
           "classification": "reliably above chance",
           "label": "PIQA",
           "n_samples": 1838,
-          "score": 38.84657236126223
+          "score": 36.34385201305768
         }
       },
       "complete": true,
       "composite": {
         "ci": [
-          41.86348233604306,
-          43.96668012300082
+          36.68113506339092,
+          38.849860312348774
         ],
         "classification": "reliably above chance",
-        "score": 42.989729225325554
+        "score": 37.843491883620345
       },
-      "id": "qwen2-5-0-5b",
-      "name": "Qwen2.5 0.5B",
-      "params_m": 494.0,
+      "id": "smollm2-135m",
+      "name": "SmolLM2 135M",
+      "params_m": 135.0,
       "protocol": {
         "bootstrap_replicates": 2000,
         "bootstrap_seed": 20260716,
@@ -7910,12 +16211,12 @@
           "model": "hf",
           "model_args": {
             "dtype": "bfloat16",
-            "pretrained": "models/qwen2.5-0.5b",
-            "tokenizer": "models/qwen2.5-0.5b",
+            "pretrained": "models/smollm2-135m",
+            "tokenizer": "models/smollm2-135m",
             "trust_remote_code": false
           },
           "model_dtype": "torch.bfloat16",
-          "model_num_parameters": 494032768,
+          "model_num_parameters": 134515008,
           "model_revision": "main",
           "model_sha": "",
           "numpy_seed": 1234,
@@ -7931,8 +16232,8 @@
           "torch_seed": 1234,
           "use_cache": null,
           "v1_1_sources": {
-            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154341Z-v1.1/results_v1.1_merged.json",
-            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154341Z-v1.1/results_v1.1_merged.json"
+            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154341Z-v1.1/results_v1.1_merged.json",
+            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154341Z-v1.1/results_v1.1_merged.json"
           }
         },
         "n_shot": {
@@ -8036,8 +16337,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_challenge.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8089,8 +16390,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_easy.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8142,8 +16443,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/adjunct_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8188,8 +16489,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_gender_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8234,8 +16535,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_number_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8280,8 +16581,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_passive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8326,8 +16627,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_trans.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8372,8 +16673,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/causative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8418,8 +16719,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/complex_NP_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8464,8 +16765,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_complex_left_branch.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8510,8 +16811,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_object_extraction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8556,8 +16857,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8602,8 +16903,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8648,8 +16949,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8694,8 +16995,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8740,8 +17041,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8786,8 +17087,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8832,8 +17133,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8878,8 +17179,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adjective_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8924,8 +17225,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relational_noun.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -8970,8 +17271,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relative_clause.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9016,8 +17317,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/drop_argument.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9062,8 +17363,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9108,8 +17409,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9154,8 +17455,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9200,8 +17501,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9246,8 +17547,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9292,8 +17593,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_subject_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9338,8 +17639,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/expletive_it_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9384,8 +17685,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/inchoative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9430,8 +17731,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/intransitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9476,8 +17777,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_adjectives.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9522,8 +17823,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_verbs.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9568,8 +17869,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9614,8 +17915,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9660,8 +17961,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_echo_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9706,8 +18007,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_simple_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9752,8 +18053,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/matrix_question_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9798,8 +18099,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9844,8 +18145,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9890,8 +18191,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9936,8 +18237,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -9982,8 +18283,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10028,8 +18329,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10074,8 +18375,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_c_command.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10120,8 +18421,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10166,8 +18467,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10212,8 +18513,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10258,8 +18559,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10304,8 +18605,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_3.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10350,8 +18651,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_reconstruction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10396,8 +18697,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10442,8 +18743,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10488,8 +18789,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10534,8 +18835,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10580,8 +18881,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_subject_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10626,8 +18927,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10672,8 +18973,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10718,8 +19019,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10764,8 +19065,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10810,8 +19111,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/transitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10856,8 +19157,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10902,8 +19203,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_object_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10948,8 +19249,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -10994,8 +19295,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -11040,8 +19341,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -11086,8 +19387,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -11132,8 +19433,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -11178,8 +19479,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -11222,8 +19523,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/config/tasks/commonsense_qa_text.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false
             },
             "metric_list": [
@@ -11261,7 +19562,7 @@
               "fewshot_delimiter": "\n\n",
               "fewshot_indices": null,
               "gen_prefix": null,
-              "process_docs": "<function process_docs at 0x72645c9311c0>",
+              "process_docs": "<function process_docs at 0x7162a1fca3e0>",
               "sampler": "default",
               "samples": null,
               "split": null,
@@ -11271,8 +19572,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/hellaswag/hellaswag.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -11323,8 +19624,8 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/piqa/piqa.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/qwen2.5-0.5b",
-              "tokenizer": "models/qwen2.5-0.5b",
+              "pretrained": "models/smollm2-135m",
+              "tokenizer": "models/smollm2-135m",
               "trust_remote_code": false,
               "version": 1.0
             },
@@ -11428,129 +19729,129 @@
         }
       },
       "rank_range": [
-        1,
-        2
+        4,
+        4
       ],
-      "release_date": "2024-09-15",
-      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/qwen2-5-0-5b/20260716T154647Z-v1.1",
-      "source": "Qwen/Qwen2.5-0.5B",
+      "release_date": "2024-10-31",
+      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154647Z-v1.1",
+      "source": "HuggingFaceTB/SmolLM2-135M",
       "track": "base",
-      "updated_at": "2026-07-16T15:47:02.275688+00:00",
-      "vocab_size": 151936
+      "updated_at": "2026-07-16T15:47:05.346313+00:00",
+      "vocab_size": 49152
     },
     {
       "artifacts": {
-        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154647Z-v1.1/results_v1.1_merged.json",
-        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154647Z-v1.1"
+        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/limen-0-2b/20260727T165752Z/models__limen-0-2b/results_2026-07-27T19-06-16.084476.json",
+        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/limen-0-2b/20260727T165752Z"
       },
       "benchmarks": {
         "arc_challenge": {
-          "accuracy": 0.27986348122866894,
+          "accuracy": 0.29692832764505117,
           "chance": 0.25,
           "ci": [
-            0.5688282138794095,
-            7.281001137656425
+            2.730375426621164,
+            9.897610921501705
           ],
           "classification": "reliably above chance",
           "label": "ARC-Challenge",
           "n_samples": 1172,
-          "score": 3.9817974971558585
+          "score": 6.2571103526734895
         },
         "arc_easy": {
-          "accuracy": 0.5728114478114478,
+          "accuracy": 0.5336700336700336,
           "chance": 0.25,
           "ci": [
-            40.404040404040394,
-            45.62289562289561
+            35.18518518518518,
+            40.404040404040394
           ],
           "classification": "reliably above chance",
           "label": "ARC-Easy",
           "n_samples": 2376,
-          "score": 43.0415263748597
+          "score": 37.82267115600448
         },
         "blimp": {
-          "accuracy": 0.8213405423280423,
+          "accuracy": 0.8327736772486772,
           "categories": {
-            "Anaphor agreement": 0.99,
-            "Argument structure": 0.7935555555555555,
-            "Binding": 0.7918571428571427,
-            "Control / raising": 0.8374,
-            "Determiner-noun agreement": 0.956,
-            "Ellipsis": 0.87,
-            "Filler-gap": 0.7927142857142858,
-            "Irregular forms": 0.9295,
-            "Island effects": 0.68875,
-            "NPI licensing": 0.668142857142857,
-            "Quantifiers": 0.7084999999999999,
-            "Subject-verb agreement": 0.8296666666666667
+            "Anaphor agreement": 0.993,
+            "Argument structure": 0.8152222222222222,
+            "Binding": 0.7435714285714285,
+            "Control / raising": 0.8097999999999999,
+            "Determiner-noun agreement": 0.954125,
+            "Ellipsis": 0.862,
+            "Filler-gap": 0.7794285714285715,
+            "Irregular forms": 0.905,
+            "Island effects": 0.704375,
+            "NPI licensing": 0.8164285714285714,
+            "Quantifiers": 0.722,
+            "Subject-verb agreement": 0.8883333333333332
           },
           "category_count": 12,
           "chance": 0.5,
           "ci": [
-            63.49301306216931,
-            64.53917559523809
+            65.83977000661378,
+            66.87867873677249
           ],
           "classification": "reliably above chance",
           "label": "BLiMP",
           "n_samples": 70000,
-          "score": 64.26810846560846
+          "score": 66.55473544973545
         },
         "commonsense_qa": {
-          "accuracy": 0.4258804258804259,
+          "accuracy": 0.3415233415233415,
           "chance": 0.2,
           "ci": [
-            24.754299754299755,
-            31.71580671580671
+            14.312039312039309,
+            21.068796068796065
           ],
           "classification": "reliably above chance",
           "label": "CommonsenseQA",
           "n_samples": 1221,
-          "score": 28.235053235053236
+          "score": 17.690417690417686
         },
         "hellaswag": {
-          "accuracy": 0.4144592710615415,
+          "accuracy": 0.41983668591913964,
           "chance": 0.25,
           "ci": [
-            20.65325632344155,
-            23.29582420500564
+            21.33041226847242,
+            23.9328155081989
           ],
           "classification": "reliably above chance",
           "label": "HellaSwag",
           "n_samples": 10042,
-          "score": 21.927902808205534
+          "score": 22.644891455885286
         },
         "piqa": {
-          "accuracy": 0.6849836779107725,
+          "accuracy": 0.6735582154515778,
           "chance": 0.5,
           "ci": [
-            32.86180631120783,
-            41.240478781284004
+            30.359085963003274,
+            38.84929270946679
           ],
           "classification": "reliably above chance",
           "label": "PIQA",
           "n_samples": 1838,
-          "score": 36.99673558215451
+          "score": 34.71164309031556
         }
       },
       "complete": true,
       "composite": {
         "ci": [
-          37.774028206553304,
-          39.9138118144519
+          35.46080088232033,
+          37.604706072519605
         ],
         "classification": "reliably above chance",
-        "score": 38.912790926162764
+        "score": 36.62932947399655
       },
-      "id": "gemma-3-270m",
-      "name": "Gemma 3 270M",
-      "params_m": 270.0,
+      "id": "limen-0-2b",
+      "name": "Limen0.2B",
+      "params_m": 222.51648,
       "protocol": {
         "bootstrap_replicates": 2000,
         "bootstrap_seed": 20260716,
         "harness": "lm-eval==0.4.12",
-        "harness_git_hash": null,
+        "harness_git_hash": "dc3c1cf",
         "inference_config": {
-          "batch_size": "32",
+          "batch_size": "64",
           "batch_sizes": [],
           "bootstrap_iters": 100000,
           "device": "cuda:0",
@@ -11560,32 +19861,22 @@
           "model": "hf",
           "model_args": {
             "dtype": "bfloat16",
-            "pretrained": "models/gemma-3-270m",
-            "tokenizer": "models/gemma-3-270m",
-            "trust_remote_code": false
+            "prefix_token_id": 16383,
+            "pretrained": "models/limen-0-2b",
+            "tokenizer": "models/limen-0-2b",
+            "trust_remote_code": true
           },
-          "model_dtype": "torch.bfloat16",
-          "model_num_parameters": 268098176,
+          "model_dtype": "torch.float32",
+          "model_num_parameters": 222516480,
           "model_revision": "main",
           "model_sha": "",
           "numpy_seed": 1234,
           "random_seed": 1234,
-          "tasks": [
-            "hellaswag",
-            "piqa",
-            "arc_easy",
-            "arc_challenge",
-            "commonsense_qa_text",
-            "blimp"
-          ],
           "torch_seed": 1234,
-          "use_cache": null,
-          "v1_1_sources": {
-            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154341Z-v1.1/results_v1.1_merged.json",
-            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154341Z-v1.1/results_v1.1_merged.json"
-          }
+          "use_cache": null
         },
         "n_shot": {
+          "arc_challenge": 0,
           "arc_easy": 0,
           "blimp": 0,
           "blimp_adjunct_island": 0,
@@ -11655,7 +19946,7 @@
           "blimp_wh_vs_that_no_gap_long_distance": 0,
           "blimp_wh_vs_that_with_gap": 0,
           "blimp_wh_vs_that_with_gap_long_distance": 0,
-          "commonsense_qa": 0,
+          "commonsense_qa_text": 0,
           "hellaswag": 0,
           "piqa": 0
         },
@@ -11686,9 +19977,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_challenge.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -11739,9 +20031,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_easy.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -11792,9 +20085,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/adjunct_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -11838,9 +20132,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_gender_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -11884,9 +20179,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_number_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -11930,9 +20226,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_passive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -11976,9 +20273,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_trans.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12022,9 +20320,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/causative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12068,9 +20367,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/complex_NP_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12114,9 +20414,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_complex_left_branch.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12160,9 +20461,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_object_extraction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12206,9 +20508,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12252,9 +20555,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12298,9 +20602,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12344,9 +20649,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12390,9 +20696,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12436,9 +20743,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12482,9 +20790,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12528,9 +20837,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adjective_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12574,9 +20884,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relational_noun.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12620,9 +20931,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relative_clause.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12666,9 +20978,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/drop_argument.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12712,9 +21025,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12758,9 +21072,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12804,9 +21119,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12850,9 +21166,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12896,9 +21213,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12942,9 +21260,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_subject_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -12988,9 +21307,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/expletive_it_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13034,9 +21354,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/inchoative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13080,9 +21401,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/intransitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13126,9 +21448,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_adjectives.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13172,9 +21495,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_verbs.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13218,9 +21542,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13264,9 +21589,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13310,9 +21636,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_echo_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13356,9 +21683,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_simple_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13402,9 +21730,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/matrix_question_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13448,9 +21777,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13494,9 +21824,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13540,9 +21871,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13586,9 +21918,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13632,9 +21965,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13678,9 +22012,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13724,9 +22059,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_c_command.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13770,9 +22106,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13816,9 +22153,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13862,9 +22200,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13908,9 +22247,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -13954,9 +22294,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_3.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14000,9 +22341,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_reconstruction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14046,9 +22388,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14092,9 +22435,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14138,9 +22482,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14184,9 +22529,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14230,9 +22576,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_subject_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14276,9 +22623,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14322,9 +22670,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14368,9 +22717,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14414,9 +22764,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14460,9 +22811,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/transitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14506,9 +22858,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14552,9 +22905,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_object_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14598,9 +22952,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14644,9 +22999,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14690,9 +23046,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14736,9 +23093,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14782,9 +23140,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14828,9 +23187,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14872,9 +23232,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/config/tasks/commonsense_qa_text.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true
             },
             "metric_list": [
               {
@@ -14911,7 +23272,7 @@
               "fewshot_delimiter": "\n\n",
               "fewshot_indices": null,
               "gen_prefix": null,
-              "process_docs": "<function process_docs at 0x7ff024f928e0>",
+              "process_docs": "<function process_docs at 0x7e1a5f77d120>",
               "sampler": "default",
               "samples": null,
               "split": null,
@@ -14921,9 +23282,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/hellaswag/hellaswag.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -14973,9 +23335,10 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/piqa/piqa.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gemma-3-270m",
-              "tokenizer": "models/gemma-3-270m",
-              "trust_remote_code": false,
+              "prefix_token_id": 16383,
+              "pretrained": "models/limen-0-2b",
+              "tokenizer": "models/limen-0-2b",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15078,122 +23441,122 @@
         }
       },
       "rank_range": [
-        3,
-        3
+        5,
+        5
       ],
-      "release_date": "2025-08-05",
-      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gemma-3-270m/20260716T154647Z-v1.1",
-      "source": "google/gemma-3-270m",
+      "release_date": "2026-07-24",
+      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/limen-0-2b/20260727T165752Z",
+      "source": "UniversalComputingResearch/Limen0.2B",
       "track": "base",
-      "updated_at": "2026-07-16T15:46:49.790812+00:00",
-      "vocab_size": 262144
+      "updated_at": "2026-07-27T17:06:22.066132+00:00",
+      "vocab_size": 16384
     },
     {
       "artifacts": {
-        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154647Z-v1.1/results_v1.1_merged.json",
-        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154647Z-v1.1"
+        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154647Z-v1.1/results_v1.1_merged.json",
+        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154647Z-v1.1"
       },
       "benchmarks": {
         "arc_challenge": {
-          "accuracy": 0.29692832764505117,
+          "accuracy": 0.27559726962457337,
           "chance": 0.25,
           "ci": [
-            2.6166097838452806,
-            9.670079635949946
+            -0.11376564277588337,
+            7.053469852104666
           ],
-          "classification": "reliably above chance",
+          "classification": "indistinguishable from chance",
           "label": "ARC-Challenge",
           "n_samples": 1172,
-          "score": 6.2571103526734895
+          "score": 3.4129692832764498
         },
         "arc_easy": {
-          "accuracy": 0.5871212121212122,
+          "accuracy": 0.5164141414141414,
           "chance": 0.25,
           "ci": [
-            42.255892255892256,
-            47.53086419753087
+            32.82687991021324,
+            38.21548821548822
           ],
           "classification": "reliably above chance",
           "label": "ARC-Easy",
           "n_samples": 2376,
-          "score": 44.949494949494955
+          "score": 35.52188552188553
         },
         "blimp": {
-          "accuracy": 0.8136013227513228,
+          "accuracy": 0.8291201719576721,
           "categories": {
-            "Anaphor agreement": 0.977,
-            "Argument structure": 0.8337777777777778,
-            "Binding": 0.7632857142857142,
-            "Control / raising": 0.8392000000000002,
-            "Determiner-noun agreement": 0.968,
-            "Ellipsis": 0.8745,
-            "Filler-gap": 0.7977142857142857,
-            "Irregular forms": 0.8380000000000001,
-            "Island effects": 0.6892499999999999,
-            "NPI licensing": 0.6485714285714286,
-            "Quantifiers": 0.67025,
-            "Subject-verb agreement": 0.8636666666666667
+            "Anaphor agreement": 0.9864999999999999,
+            "Argument structure": 0.826111111111111,
+            "Binding": 0.7557142857142857,
+            "Control / raising": 0.8231999999999999,
+            "Determiner-noun agreement": 0.9581249999999999,
+            "Ellipsis": 0.8534999999999999,
+            "Filler-gap": 0.7958571428571429,
+            "Irregular forms": 0.923,
+            "Island effects": 0.6868749999999999,
+            "NPI licensing": 0.7461428571428571,
+            "Quantifiers": 0.70725,
+            "Subject-verb agreement": 0.8871666666666665
           },
           "category_count": 12,
           "chance": 0.5,
           "ci": [
-            61.932142030423265,
-            63.0667154431217
+            64.96420122354498,
+            66.0613258928571
           ],
           "classification": "reliably above chance",
           "label": "BLiMP",
           "n_samples": 70000,
-          "score": 62.72026455026456
+          "score": 65.82403439153441
         },
         "commonsense_qa": {
-          "accuracy": 0.35544635544635544,
+          "accuracy": 0.3464373464373464,
           "chance": 0.2,
           "ci": [
-            16.152231777231773,
-            22.81173218673217
+            14.926289926289922,
+            21.580671580671574
           ],
           "classification": "reliably above chance",
           "label": "CommonsenseQA",
           "n_samples": 1221,
-          "score": 19.43079443079443
+          "score": 18.3046683046683
         },
         "hellaswag": {
-          "accuracy": 0.43218482374029077,
+          "accuracy": 0.4051981676956781,
           "chance": 0.25,
           "ci": [
-            23.016331408086035,
-            25.592511451902016
+            19.431388169687313,
+            21.941512314943907
           ],
           "classification": "reliably above chance",
           "label": "HellaSwag",
           "n_samples": 10042,
-          "score": 24.291309832038767
+          "score": 20.693089026090416
         },
         "piqa": {
-          "accuracy": 0.6817192600652884,
+          "accuracy": 0.6708378672470077,
           "chance": 0.5,
           "ci": [
-            32.097388465723604,
-            40.58759521218715
+            29.706202393906423,
+            38.41131664853101
           ],
           "classification": "reliably above chance",
           "label": "PIQA",
           "n_samples": 1838,
-          "score": 36.34385201305768
+          "score": 34.16757344940153
         }
       },
       "complete": true,
       "composite": {
         "ci": [
-          36.68113506339092,
-          38.849860312348774
+          34.34048401085747,
+          36.481411360993164
         ],
         "classification": "reliably above chance",
-        "score": 37.843491883620345
+        "score": 35.52389451013529
       },
-      "id": "smollm2-135m",
-      "name": "SmolLM2 135M",
-      "params_m": 135.0,
+      "id": "gpt-x2-125m",
+      "name": "GPT-X2 125M",
+      "params_m": 125.081664,
       "protocol": {
         "bootstrap_replicates": 2000,
         "bootstrap_seed": 20260716,
@@ -15212,12 +23575,12 @@
           "model": "hf",
           "model_args": {
             "dtype": "bfloat16",
-            "pretrained": "models/smollm2-135m",
-            "tokenizer": "models/smollm2-135m",
-            "trust_remote_code": false
+            "pretrained": "models/gpt-x2-125m",
+            "tokenizer": "models/gpt-x2-125m",
+            "trust_remote_code": true
           },
           "model_dtype": "torch.bfloat16",
-          "model_num_parameters": 134515008,
+          "model_num_parameters": 125081664,
           "model_revision": "main",
           "model_sha": "",
           "numpy_seed": 1234,
@@ -15233,8 +23596,8 @@
           "torch_seed": 1234,
           "use_cache": null,
           "v1_1_sources": {
-            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154341Z-v1.1/results_v1.1_merged.json",
-            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154341Z-v1.1/results_v1.1_merged.json"
+            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154341Z-v1.1/results_v1.1_merged.json",
+            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154341Z-v1.1/results_v1.1_merged.json"
           }
         },
         "n_shot": {
@@ -15338,9 +23701,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_challenge.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15391,9 +23754,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_easy.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15444,9 +23807,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/adjunct_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15490,9 +23853,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_gender_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15536,9 +23899,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_number_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15582,9 +23945,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_passive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15628,9 +23991,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_trans.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15674,9 +24037,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/causative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15720,9 +24083,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/complex_NP_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15766,9 +24129,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_complex_left_branch.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15812,9 +24175,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_object_extraction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15858,9 +24221,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15904,9 +24267,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15950,9 +24313,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -15996,9 +24359,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16042,9 +24405,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16088,9 +24451,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16134,9 +24497,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16180,9 +24543,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adjective_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16226,9 +24589,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relational_noun.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16272,9 +24635,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relative_clause.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16318,9 +24681,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/drop_argument.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16364,9 +24727,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16410,9 +24773,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16456,9 +24819,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16502,9 +24865,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16548,9 +24911,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16594,9 +24957,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_subject_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16640,9 +25003,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/expletive_it_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16686,9 +25049,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/inchoative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16732,9 +25095,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/intransitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16778,9 +25141,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_adjectives.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16824,9 +25187,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_verbs.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16870,9 +25233,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16916,9 +25279,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -16962,9 +25325,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_echo_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17008,9 +25371,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_simple_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17054,9 +25417,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/matrix_question_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17100,9 +25463,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17146,9 +25509,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17192,9 +25555,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17238,9 +25601,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17284,9 +25647,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17330,9 +25693,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17376,9 +25739,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_c_command.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17422,9 +25785,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17468,9 +25831,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17514,9 +25877,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17560,9 +25923,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17606,9 +25969,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_3.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17652,9 +26015,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_reconstruction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17698,9 +26061,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17744,9 +26107,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17790,9 +26153,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17836,9 +26199,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17882,9 +26245,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_subject_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17928,9 +26291,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -17974,9 +26337,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18020,9 +26383,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18066,9 +26429,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18112,9 +26475,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/transitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18158,9 +26521,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18204,9 +26567,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_object_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18250,9 +26613,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18296,9 +26659,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18342,9 +26705,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18388,9 +26751,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18434,9 +26797,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18480,9 +26843,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18524,9 +26887,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/config/tasks/commonsense_qa_text.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true
             },
             "metric_list": [
               {
@@ -18563,7 +26926,7 @@
               "fewshot_delimiter": "\n\n",
               "fewshot_indices": null,
               "gen_prefix": null,
-              "process_docs": "<function process_docs at 0x7162a1fca3e0>",
+              "process_docs": "<function process_docs at 0x73557ef813a0>",
               "sampler": "default",
               "samples": null,
               "split": null,
@@ -18573,9 +26936,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/hellaswag/hellaswag.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18625,9 +26988,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/piqa/piqa.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/smollm2-135m",
-              "tokenizer": "models/smollm2-135m",
-              "trust_remote_code": false,
+              "pretrained": "models/gpt-x2-125m",
+              "tokenizer": "models/gpt-x2-125m",
+              "trust_remote_code": true,
               "version": 1.0
             },
             "metric_list": [
@@ -18730,132 +27093,130 @@
         }
       },
       "rank_range": [
-        4,
-        4
+        6,
+        6
       ],
-      "release_date": "2024-10-31",
-      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/smollm2-135m/20260716T154647Z-v1.1",
-      "source": "HuggingFaceTB/SmolLM2-135M",
+      "release_date": "2026-03-25",
+      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154647Z-v1.1",
+      "source": "AxiomicLabs/GPT-X2-125M",
       "track": "base",
-      "updated_at": "2026-07-16T15:47:05.346313+00:00",
-      "vocab_size": 49152
+      "updated_at": "2026-07-16T15:46:54.567291+00:00",
+      "vocab_size": 32768
     },
     {
       "artifacts": {
-        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154647Z-v1.1/results_v1.1_merged.json",
-        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154647Z-v1.1"
+        "result_file": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt2-medium-355m/20260723T113123Z/models__gpt2-medium-355m/results_2026-07-23T13-38-50.898870.json",
+        "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt2-medium-355m/20260723T113123Z"
       },
       "benchmarks": {
         "arc_challenge": {
-          "accuracy": 0.27559726962457337,
+          "accuracy": 0.25,
           "chance": 0.25,
           "ci": [
-            -0.11376564277588337,
-            7.053469852104666
+            -3.074516496018204,
+            3.2992036405005662
           ],
           "classification": "indistinguishable from chance",
           "label": "ARC-Challenge",
           "n_samples": 1172,
-          "score": 3.4129692832764498
+          "score": 0.0
         },
         "arc_easy": {
-          "accuracy": 0.5164141414141414,
+          "accuracy": 0.43476430976430974,
           "chance": 0.25,
           "ci": [
-            32.82687991021324,
-            38.21548821548822
+            22.053872053872052,
+            27.328843995510663
           ],
           "classification": "reliably above chance",
           "label": "ARC-Easy",
           "n_samples": 2376,
-          "score": 35.52188552188553
+          "score": 24.635241301907968
         },
         "blimp": {
-          "accuracy": 0.8291201719576721,
+          "accuracy": 0.8522063492063493,
           "categories": {
-            "Anaphor agreement": 0.9864999999999999,
-            "Argument structure": 0.826111111111111,
-            "Binding": 0.7557142857142857,
-            "Control / raising": 0.8231999999999999,
-            "Determiner-noun agreement": 0.9581249999999999,
-            "Ellipsis": 0.8534999999999999,
-            "Filler-gap": 0.7958571428571429,
-            "Irregular forms": 0.923,
-            "Island effects": 0.6868749999999999,
-            "NPI licensing": 0.7461428571428571,
-            "Quantifiers": 0.70725,
-            "Subject-verb agreement": 0.8871666666666665
+            "Anaphor agreement": 0.9964999999999999,
+            "Argument structure": 0.8430000000000001,
+            "Binding": 0.7965714285714285,
+            "Control / raising": 0.8360000000000001,
+            "Determiner-noun agreement": 0.9661249999999999,
+            "Ellipsis": 0.874,
+            "Filler-gap": 0.825,
+            "Irregular forms": 0.95,
+            "Island effects": 0.719875,
+            "NPI licensing": 0.7845714285714287,
+            "Quantifiers": 0.7424999999999999,
+            "Subject-verb agreement": 0.8923333333333333
           },
           "category_count": 12,
           "chance": 0.5,
           "ci": [
-            64.96420122354498,
-            66.0613258928571
+            69.78037599206348,
+            70.79667377645502
           ],
           "classification": "reliably above chance",
           "label": "BLiMP",
           "n_samples": 70000,
-          "score": 65.82403439153441
+          "score": 70.44126984126986
         },
         "commonsense_qa": {
-          "accuracy": 0.3464373464373464,
+          "accuracy": 0.31695331695331697,
           "chance": 0.2,
           "ci": [
-            14.926289926289922,
-            21.580671580671574
+            11.545352170352167,
+            17.997542997542997
           ],
           "classification": "reliably above chance",
           "label": "CommonsenseQA",
           "n_samples": 1221,
-          "score": 18.3046683046683
+          "score": 14.61916461916462
         },
         "hellaswag": {
-          "accuracy": 0.4051981676956781,
+          "accuracy": 0.3933479386576379,
           "chance": 0.25,
           "ci": [
-            19.431388169687313,
-            21.941512314943907
+            17.86463519883157,
+            20.34820420898891
           ],
           "classification": "reliably above chance",
           "label": "HellaSwag",
           "n_samples": 10042,
-          "score": 20.693089026090416
+          "score": 19.113058487685052
         },
         "piqa": {
-          "accuracy": 0.6708378672470077,
+          "accuracy": 0.6659412404787813,
           "chance": 0.5,
           "ci": [
-            29.706202393906423,
-            38.41131664853101
+            28.944504896626768,
+            37.54080522306855
           ],
           "classification": "reliably above chance",
           "label": "PIQA",
           "n_samples": 1838,
-          "score": 34.16757344940153
+          "score": 33.188248095756265
         }
       },
       "complete": true,
       "composite": {
         "ci": [
-          34.34048401085747,
-          36.481411360993164
+          32.30209572902444,
+          34.41893633162846
         ],
         "classification": "reliably above chance",
-        "score": 35.52389451013529
+        "score": 33.3828370715262
       },
-      "id": "gpt-x2-125m",
-      "name": "GPT-X2 125M",
-      "params_m": 125.081664,
+      "id": "gpt2-medium-355m",
+      "name": "GPT-2 Medium 355M",
+      "params_m": 354.823168,
       "protocol": {
         "bootstrap_replicates": 2000,
         "bootstrap_seed": 20260716,
         "harness": "lm-eval==0.4.12",
-        "harness_git_hash": null,
+        "harness_git_hash": "dc3c1cf",
         "inference_config": {
-          "batch_size": "auto",
-          "batch_sizes": [
-            64
-          ],
+          "batch_size": "16",
+          "batch_sizes": [],
           "bootstrap_iters": 100000,
           "device": "cuda:0",
           "fewshot_seed": 1234,
@@ -18864,32 +27225,21 @@
           "model": "hf",
           "model_args": {
             "dtype": "bfloat16",
-            "pretrained": "models/gpt-x2-125m",
-            "tokenizer": "models/gpt-x2-125m",
-            "trust_remote_code": true
+            "pretrained": "models/gpt2-medium-355m",
+            "tokenizer": "models/gpt2-medium-355m",
+            "trust_remote_code": false
           },
           "model_dtype": "torch.bfloat16",
-          "model_num_parameters": 125081664,
+          "model_num_parameters": 354823168,
           "model_revision": "main",
           "model_sha": "",
           "numpy_seed": 1234,
           "random_seed": 1234,
-          "tasks": [
-            "hellaswag",
-            "piqa",
-            "arc_easy",
-            "arc_challenge",
-            "commonsense_qa_text",
-            "blimp"
-          ],
           "torch_seed": 1234,
-          "use_cache": null,
-          "v1_1_sources": {
-            "rechecked_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154341Z-v1.1/results_v1.1_merged.json",
-            "unchanged_tasks_result": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154341Z-v1.1/results_v1.1_merged.json"
-          }
+          "use_cache": null
         },
         "n_shot": {
+          "arc_challenge": 0,
           "arc_easy": 0,
           "blimp": 0,
           "blimp_adjunct_island": 0,
@@ -18959,7 +27309,7 @@
           "blimp_wh_vs_that_no_gap_long_distance": 0,
           "blimp_wh_vs_that_with_gap": 0,
           "blimp_wh_vs_that_with_gap_long_distance": 0,
-          "commonsense_qa": 0,
+          "commonsense_qa_text": 0,
           "hellaswag": 0,
           "piqa": 0
         },
@@ -18990,9 +27340,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_challenge.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19043,9 +27393,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/arc/arc_easy.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19096,9 +27446,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/adjunct_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19142,9 +27492,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_gender_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19188,9 +27538,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/anaphor_number_agreement.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19234,9 +27584,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_passive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19280,9 +27630,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/animate_subject_trans.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19326,9 +27676,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/causative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19372,9 +27722,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/complex_NP_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19418,9 +27768,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_complex_left_branch.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19464,9 +27814,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/coordinate_structure_constraint_object_extraction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19510,9 +27860,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19556,9 +27906,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19602,9 +27952,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19648,9 +27998,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19694,9 +28044,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19740,9 +28090,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19786,9 +28136,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adj_irregular_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19832,9 +28182,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/determiner_noun_agreement_with_adjective_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19878,9 +28228,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relational_noun.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19924,9 +28274,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/distractor_agreement_relative_clause.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -19970,9 +28320,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/drop_argument.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20016,9 +28366,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20062,9 +28412,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/ellipsis_n_bar_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20108,9 +28458,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20154,9 +28504,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20200,9 +28550,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20246,9 +28596,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/existential_there_subject_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20292,9 +28642,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/expletive_it_object_raising.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20338,9 +28688,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/inchoative.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20384,9 +28734,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/intransitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20430,9 +28780,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_adjectives.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20476,9 +28826,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_past_participle_verbs.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20522,9 +28872,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20568,9 +28918,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/irregular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20614,9 +28964,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_echo_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20660,9 +29010,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/left_branch_island_simple_question.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20706,9 +29056,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/matrix_question_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20752,9 +29102,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20798,9 +29148,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/npi_present_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20844,9 +29194,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20890,9 +29240,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/only_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20936,9 +29286,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -20982,9 +29332,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/passive_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21028,9 +29378,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_c_command.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21074,9 +29424,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21120,9 +29470,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_case_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21166,9 +29516,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21212,9 +29562,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21258,9 +29608,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_domain_3.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21304,9 +29654,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/principle_A_reconstruction.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21350,9 +29700,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21396,9 +29746,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21442,9 +29792,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_licensor_present.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21488,9 +29838,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21534,9 +29884,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/sentential_subject_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21580,9 +29930,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21626,9 +29976,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21672,9 +30022,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_1.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21718,9 +30068,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/tough_vs_raising_2.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21764,9 +30114,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/transitive.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21810,9 +30160,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_island.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21856,9 +30206,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_object_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21902,9 +30252,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21948,9 +30298,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -21994,9 +30344,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -22040,9 +30390,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -22086,9 +30436,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -22132,9 +30482,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -22176,9 +30526,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/config/tasks/commonsense_qa_text.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false
             },
             "metric_list": [
               {
@@ -22215,7 +30565,7 @@
               "fewshot_delimiter": "\n\n",
               "fewshot_indices": null,
               "gen_prefix": null,
-              "process_docs": "<function process_docs at 0x73557ef813a0>",
+              "process_docs": "<function process_docs at 0x7737c7db9260>",
               "sampler": "default",
               "samples": null,
               "split": null,
@@ -22225,9 +30575,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/hellaswag/hellaswag.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -22277,9 +30627,9 @@
             "metadata": {
               "config_source": "/home/max/PROJECTS/PythonProjects/mcpterm/venv/lib/python3.11/site-packages/lm_eval/tasks/piqa/piqa.yaml",
               "dtype": "bfloat16",
-              "pretrained": "models/gpt-x2-125m",
-              "tokenizer": "models/gpt-x2-125m",
-              "trust_remote_code": true,
+              "pretrained": "models/gpt2-medium-355m",
+              "tokenizer": "models/gpt2-medium-355m",
+              "trust_remote_code": false,
               "version": 1.0
             },
             "metric_list": [
@@ -22382,15 +30732,15 @@
         }
       },
       "rank_range": [
-        5,
-        5
+        7,
+        7
       ],
-      "release_date": "2026-03-25",
-      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-x2-125m/20260716T154647Z-v1.1",
-      "source": "AxiomicLabs/GPT-X2-125M",
+      "release_date": "2022-03-02",
+      "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt2-medium-355m/20260723T113123Z",
+      "source": "openai-community/gpt2-medium",
       "track": "base",
-      "updated_at": "2026-07-16T15:46:54.567291+00:00",
-      "vocab_size": 32768
+      "updated_at": "2026-07-23T11:38:57.225513+00:00",
+      "vocab_size": 50257
     },
     {
       "artifacts": {
@@ -26023,8 +34373,8 @@
         }
       },
       "rank_range": [
-        6,
-        6
+        8,
+        8
       ],
       "release_date": "2025-09-10",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/mobilellm-r1-140m-base/20260716T161918Z",
@@ -29664,8 +38014,8 @@
         }
       },
       "rank_range": [
-        7,
-        7
+        9,
+        9
       ],
       "release_date": "2025-11-10",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/baguettotron/20260719T231314Z",
@@ -33316,8 +41666,8 @@
         }
       },
       "rank_range": [
-        8,
-        9
+        10,
+        11
       ],
       "release_date": "2022-03-02",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt2-124m/20260716T154647Z-v1.1",
@@ -36968,8 +45318,8 @@
         }
       },
       "rank_range": [
-        8,
-        9
+        10,
+        11
       ],
       "release_date": "2026-05-21",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/supra-50m-base/20260716T154647Z-v1.1",
@@ -40607,8 +48957,8 @@
         }
       },
       "rank_range": [
-        10,
-        10
+        12,
+        12
       ],
       "release_date": "2026-06-14",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/veyra2-apricot-50m-base/20260716T163209Z",
@@ -44248,8 +52598,8 @@
         }
       },
       "rank_range": [
-        11,
-        13
+        13,
+        15
       ],
       "release_date": "2026-01-12",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/falcon-h1-tiny-r-90m/20260720T072155Z",
@@ -47900,8 +56250,8 @@
         }
       },
       "rank_range": [
-        11,
-        13
+        13,
+        15
       ],
       "release_date": "2026-06-13",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/slm-10m/20260716T154647Z-v1.1",
@@ -51552,8 +59902,8 @@
         }
       },
       "rank_range": [
-        11,
-        14
+        13,
+        16
       ],
       "release_date": "2023-02-08",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/pythia-160m/20260716T154647Z-v1.1",
@@ -55204,8 +63554,8 @@
         }
       },
       "rank_range": [
-        13,
-        14
+        15,
+        16
       ],
       "release_date": "2026-06-19",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-s2-5m/20260716T154647Z-v1.1",
@@ -58843,8 +67193,8 @@
         }
       },
       "rank_range": [
-        15,
-        16
+        17,
+        18
       ],
       "release_date": "2026-04-24",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/nanowhale-100m-base/20260719T232857Z",
@@ -62495,8 +70845,8 @@
         }
       },
       "rank_range": [
-        15,
-        16
+        17,
+        18
       ],
       "release_date": "2026-02-24",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/pythia-31m/20260716T154647Z-v1.1",
@@ -66147,8 +74497,8 @@
         }
       },
       "rank_range": [
-        17,
-        17
+        19,
+        19
       ],
       "release_date": "2026-06-19",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/atom-3-4m/20260716T154647Z-v1.1",
@@ -69799,8 +78149,8 @@
         }
       },
       "rank_range": [
-        18,
-        18
+        20,
+        20
       ],
       "release_date": "2026-06-01",
       "run_dir": "/home/max/PROJECTS/PythonProjects/CompactLMIndex/runs/gpt-s-1-4m/20260716T154647Z-v1.1",