Delete math_eval

math_eval/aime24/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 30,
-    "num_scores": 30,
-    "timeout_samples": 0,
-    "empty_samples": 0,
-    "acc": 30.0,
-    "time_use_in_second": 35.265536069869995,
-    "time_use_in_minite": "0:35"
-}

math_eval/aime24/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 30,
-    "num_scores": 30,
-    "timeout_samples": 0,
-    "empty_samples": 0,
-    "acc": 13.3,
-    "time_use_in_second": 34.18890905380249,
-    "time_use_in_minite": "0:34"
-}

math_eval/amc23/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 40,
-    "num_scores": 40,
-    "timeout_samples": 0,
-    "empty_samples": 0,
-    "acc": 70.0,
-    "time_use_in_second": 32.98717260360718,
-    "time_use_in_minite": "0:32"
-}

math_eval/amc23/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 40,
-    "num_scores": 40,
-    "timeout_samples": 0,
-    "empty_samples": 0,
-    "acc": 62.5,
-    "time_use_in_second": 30.84848642349243,
-    "time_use_in_minite": "0:30"
-}

math_eval/gsm8k/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 1319,
-    "num_scores": 1319,
-    "timeout_samples": 0,
-    "empty_samples": 1,
-    "acc": 92.2,
-    "time_use_in_second": 149.93445825576782,
-    "time_use_in_minite": "2:29"
-}

math_eval/gsm8k/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 1319,
-    "num_scores": 1319,
-    "timeout_samples": 0,
-    "empty_samples": 0,
-    "acc": 91.0,
-    "time_use_in_second": 164.76103806495667,
-    "time_use_in_minite": "2:44"
-}

math_eval/math500/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 500,
-    "num_scores": 500,
-    "timeout_samples": 0,
-    "empty_samples": 1,
-    "acc": 83.8,
-    "time_use_in_second": 98.43564033508301,
-    "time_use_in_minite": "1:38"
-}

math_eval/math500/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 500,
-    "num_scores": 500,
-    "timeout_samples": 0,
-    "empty_samples": 1,
-    "acc": 83.2,
-    "time_use_in_second": 106.62742972373962,
-    "time_use_in_minite": "1:46"
-}

math_eval/minerva_math/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json

@@ -1,20 +0,0 @@
-{
-    "num_samples": 272,
-    "num_scores": 272,
-    "timeout_samples": 2,
-    "empty_samples": 1,
-    "acc": 39.0,
-    "type_acc": {
-        "Differential Equations (18.03 Spring 2010)": 56.2,
-        "Dynamics and Control (2.003 Spring 2005)": 53.8,
-        "Ecology I (1.018J Fall 2009)": 40.0,
-        "Information and Entropy (6.050J Spring 2008)": 33.3,
-        "Introduction to Astronomy (8.282J Spring 2006)": 37.7,
-        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 28.9,
-        "Physical Chemistry (5.61 Fall 2017)": 36.4,
-        "Principles of Microeconomics (14.01 Fall 2011)": 38.9,
-        "Relativity (8.033 Fall 2006)": 27.3
-    },
-    "time_use_in_second": 66.03826689720154,
-    "time_use_in_minite": "1:06"
-}

math_eval/minerva_math/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json

@@ -1,20 +0,0 @@
-{
-    "num_samples": 272,
-    "num_scores": 272,
-    "timeout_samples": 1,
-    "empty_samples": 0,
-    "acc": 30.9,
-    "type_acc": {
-        "Differential Equations (18.03 Spring 2010)": 33.3,
-        "Dynamics and Control (2.003 Spring 2005)": 46.2,
-        "Ecology I (1.018J Fall 2009)": 40.0,
-        "Information and Entropy (6.050J Spring 2008)": 33.3,
-        "Introduction to Astronomy (8.282J Spring 2006)": 26.4,
-        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 26.8,
-        "Physical Chemistry (5.61 Fall 2017)": 36.4,
-        "Principles of Microeconomics (14.01 Fall 2011)": 33.3,
-        "Relativity (8.033 Fall 2006)": 27.3
-    },
-    "time_use_in_second": 68.34114909172058,
-    "time_use_in_minite": "1:08"
-}

math_eval/olympiadbench/test_o1_cot_-1_seed0_t0.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 675,
-    "num_scores": 675,
-    "timeout_samples": 2,
-    "empty_samples": 0,
-    "acc": 46.4,
-    "time_use_in_second": 245.80863761901855,
-    "time_use_in_minite": "4:05"
-}

math_eval/olympiadbench/test_o1_cot_-1_seed0_t1.0_s0_e-1_o1_cot_metrics.json

@@ -1,9 +0,0 @@
-{
-    "num_samples": 675,
-    "num_scores": 675,
-    "timeout_samples": 0,
-    "empty_samples": 0,
-    "acc": 47.0,
-    "time_use_in_second": 252.64844059944153,
-    "time_use_in_minite": "4:12"
-}