clean

results.json

@@ -5785,43 +5785,6 @@
     "accuracy": 0.5723270440251572
    }
   },
-  "data/ifeval_best_of_k/Qwen2.5-7B-RM-09192024.json": {
-   "all": {
-    "accuracy": 0.5726562500000001,
-    "area_under_curve": 0.5536947485942088,
-    "loss": 0.1320898115634918,
-    "mean_max_score": 0.58177734375,
-    "mean_end_score": 0.565234375
-   },
-   "gemma-2-9b-it": {
-    "accuracy": 0.5796875,
-    "area_under_curve": 0.5556161705870118,
-    "loss": 0.11947629928588867,
-    "mean_max_score": 0.62125,
-    "mean_end_score": 0.58953125
-   },
-   "gpt-4o-mini-2024-07-18": {
-    "accuracy": 0.61875,
-    "area_under_curve": 0.5427620686093066,
-    "loss": 0.1205466079711914,
-    "mean_max_score": 0.631328125,
-    "mean_end_score": 0.605390625
-   },
-   "Meta-Llama-3-8B-Instruct": {
-    "accuracy": 0.58125,
-    "area_under_curve": 0.5553819052297072,
-    "loss": 0.14538890838623048,
-    "mean_max_score": 0.60421875,
-    "mean_end_score": 0.55078125
-   },
-   "claude-3-haiku-20240307": {
-    "accuracy": 0.5109375,
-    "area_under_curve": 0.5500825653737205,
-    "loss": 0.15359460830688476,
-    "mean_max_score": 0.54703125,
-    "mean_end_score": 0.515625
-   }
-  },
   "data/ifeval_best_of_k/internlm2-1_8b-reward.json": {
    "all": {
     "accuracy": 0.5386718749999999,
@@ -6189,43 +6152,6 @@
     "mean_end_score": 0.606015625
    }
   },
-  "data/ifeval_best_of_k/Qwen2.5-72B-RM-09242024.json": {
-   "all": {
-    "accuracy": 0.591796875,
-    "area_under_curve": 0.5682828198209156,
-    "loss": 0.11081918239593506,
-    "mean_max_score": 0.61642578125,
-    "mean_end_score": 0.61126953125
-   },
-   "gemma-2-9b-it": {
-    "accuracy": 0.615625,
-    "area_under_curve": 0.5724099728839697,
-    "loss": 0.08845264434814454,
-    "mean_max_score": 0.667265625,
-    "mean_end_score": 0.6484375
-   },
-   "gpt-4o-mini-2024-07-18": {
-    "accuracy": 0.6046875,
-    "area_under_curve": 0.5579399685462639,
-    "loss": 0.1147395133972168,
-    "mean_max_score": 0.644296875,
-    "mean_end_score": 0.6171875
-   },
-   "Meta-Llama-3-8B-Instruct": {
-    "accuracy": 0.6140625,
-    "area_under_curve": 0.576997247648311,
-    "loss": 0.11122642517089844,
-    "mean_max_score": 0.64453125,
-    "mean_end_score": 0.636640625
-   },
-   "claude-3-haiku-20240307": {
-    "accuracy": 0.5328125,
-    "area_under_curve": 0.5592622087343524,
-    "loss": 0.13447074890136718,
-    "mean_max_score": 0.5696875,
-    "mean_end_score": 0.543359375
-   }
-  },
   "data/ifeval_best_of_k/nemotron-4-340b-reward.json": {
    "all": {
     "accuracy": 0.6265624999999999,
@@ -6300,43 +6226,6 @@
     "mean_end_score": 0.578125
    }
   },
-  "data/ifeval_best_of_k/Llama-3.1-8B-Instruct-RM-Test.json": {
-   "all": {
-    "accuracy": 0.5953124999999999,
-    "area_under_curve": 0.5659010925349728,
-    "loss": 0.11261327266693115,
-    "mean_max_score": 0.61439453125,
-    "mean_end_score": 0.60623046875
-   },
-   "gemma-2-9b-it": {
-    "accuracy": 0.6,
-    "area_under_curve": 0.5742011950437376,
-    "loss": 0.08687259674072266,
-    "mean_max_score": 0.67890625,
-    "mean_end_score": 0.6640625
-   },
-   "gpt-4o-mini-2024-07-18": {
-    "accuracy": 0.5984375,
-    "area_under_curve": 0.5628933527191842,
-    "loss": 0.10282745361328124,
-    "mean_max_score": 0.655625,
-    "mean_end_score": 0.644375
-   },
-   "Meta-Llama-3-8B-Instruct": {
-    "accuracy": 0.603125,
-    "area_under_curve": 0.5555893773327166,
-    "loss": 0.12582313537597656,
-    "mean_max_score": 0.618515625,
-    "mean_end_score": 0.578125
-   },
-   "claude-3-haiku-20240307": {
-    "accuracy": 0.5796874999999999,
-    "area_under_curve": 0.5637145211028964,
-    "loss": 0.13854501724243165,
-    "mean_max_score": 0.564296875,
-    "mean_end_score": 0.5390625
-   }
-  },
   "data/ifeval_best_of_k/Starling-RM-7B-alpha.json": {
    "all": {
     "accuracy": 0.5406249999999999,
@@ -6411,43 +6300,6 @@
     "mean_end_score": 0.484375
    }
   },
-  "data/ifeval_best_of_k/Llama-3.1-70B-RM-09172024.json": {
-   "all": {
-    "accuracy": 0.630078125,
-    "area_under_curve": 0.5902905300669057,
-    "loss": 0.09440629482269287,
-    "mean_max_score": 0.64310546875,
-    "mean_end_score": 0.62984375
-   },
-   "gemma-2-9b-it": {
-    "accuracy": 0.6375,
-    "area_under_curve": 0.6064561485832756,
-    "loss": 0.07111602783203125,
-    "mean_max_score": 0.709375,
-    "mean_end_score": 0.6953125
-   },
-   "gpt-4o-mini-2024-07-18": {
-    "accuracy": 0.6359374999999999,
-    "area_under_curve": 0.5804507982664724,
-    "loss": 0.08310569763183594,
-    "mean_max_score": 0.693203125,
-    "mean_end_score": 0.6759375
-   },
-   "Meta-Llama-3-8B-Instruct": {
-    "accuracy": 0.6468750000000001,
-    "area_under_curve": 0.5893750619966321,
-    "loss": 0.10088687896728515,
-    "mean_max_score": 0.653359375,
-    "mean_end_score": 0.6171875
-   },
-   "claude-3-haiku-20240307": {
-    "accuracy": 0.6000000000000001,
-    "area_under_curve": 0.585711467200442,
-    "loss": 0.12550268173217774,
-    "mean_max_score": 0.588984375,
-    "mean_end_score": 0.53125
-   }
-  },
   "data/ifeval_best_of_k/Skywork-Reward-Gemma-2-27B.json": {
    "all": {
     "accuracy": 0.537890625,