Initial commit

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+math_eval/college_math/test_qwen-boxed_-1_seed0_t0.0_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
+math_eval/math/test_qwen-boxed_-1_seed0_t0.0_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text
+math_eval/olympiadbench/test_qwen-boxed_-1_seed0_t0.0_s0_e-1.jsonl filter=lfs diff=lfs merge=lfs -text

math_eval/aime24/test_qwen-boxed_-1_seed0_t0.0_s0_e-1_qwen-boxed_metrics.json

@@ -0,0 +1,9 @@
+{
+    "num_samples": 30,
+    "num_scores": 30,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 13.3,
+    "time_use_in_second": 43.51688075065613,
+    "time_use_in_minite": "0:43"
+}

math_eval/amc23/test_qwen-boxed_-1_seed0_t0.0_s0_e-1_qwen-boxed_metrics.json

@@ -0,0 +1,9 @@
+{
+    "num_samples": 40,
+    "num_scores": 40,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 40.0,
+    "time_use_in_second": 45.59167838096619,
+    "time_use_in_minite": "0:45"
+}

math_eval/college_math/test_qwen-boxed_-1_seed0_t0.0_s0_e-1.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368a2ac394e55fcd050fa1140f4ecf28d6a0cbd2ceebd6c2eb86fcba012b7527
+size 18199361

math_eval/college_math/test_qwen-boxed_-1_seed0_t0.0_s0_e-1_qwen-boxed_metrics.json

@@ -0,0 +1,9 @@
+{
+    "num_samples": 2818,
+    "num_scores": 2818,
+    "timeout_samples": 13,
+    "empty_samples": 21,
+    "acc": 42.8,
+    "time_use_in_second": 783.5445840358734,
+    "time_use_in_minite": "13:03"
+}

math_eval/gaokao2023en/test_qwen-boxed_-1_seed0_t0.0_s0_e-1_qwen-boxed_metrics.json

@@ -0,0 +1,9 @@
+{
+    "num_samples": 385,
+    "num_scores": 385,
+    "timeout_samples": 0,
+    "empty_samples": 3,
+    "acc": 54.3,
+    "time_use_in_second": 130.78554272651672,
+    "time_use_in_minite": "2:10"
+}

math_eval/gsm8k/test_qwen-boxed_-1_seed0_t0.0_s0_e-1_qwen-boxed_metrics.json

@@ -0,0 +1,9 @@
+{
+    "num_samples": 1319,
+    "num_scores": 1319,
+    "timeout_samples": 0,
+    "empty_samples": 1,
+    "acc": 80.0,
+    "time_use_in_second": 240.4810688495636,
+    "time_use_in_minite": "4:00"
+}

math_eval/math/test_qwen-boxed_-1_seed0_t0.0_s0_e-1.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4503235d1b51251d8c5cb7311d3a60e67278013556e3881800dfae7a648cbf
+size 50309114

math_eval/math/test_qwen-boxed_-1_seed0_t0.0_s0_e-1_qwen-boxed_metrics.json

@@ -0,0 +1,9 @@
+{
+    "num_samples": 5000,
+    "num_scores": 5000,
+    "timeout_samples": 1,
+    "empty_samples": 46,
+    "acc": 61.8,
+    "time_use_in_second": 2204.3763966560364,
+    "time_use_in_minite": "36:44"
+}

math_eval/minerva_math/test_qwen-boxed_-1_seed0_t0.0_s0_e-1_qwen-boxed_metrics.json

@@ -0,0 +1,20 @@
+{
+    "num_samples": 272,
+    "num_scores": 272,
+    "timeout_samples": 0,
+    "empty_samples": 4,
+    "acc": 23.9,
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 54.2,
+        "Dynamics and Control (2.003 Spring 2005)": 50.0,
+        "Ecology I (1.018J Fall 2009)": 40.0,
+        "Information and Entropy (6.050J Spring 2008)": 33.3,
+        "Introduction to Astronomy (8.282J Spring 2006)": 9.4,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 9.3,
+        "Physical Chemistry (5.61 Fall 2017)": 0.0,
+        "Principles of Microeconomics (14.01 Fall 2011)": 50.0,
+        "Relativity (8.033 Fall 2006)": 0.0
+    },
+    "time_use_in_second": 116.57392597198486,
+    "time_use_in_minite": "1:56"
+}

math_eval/olympiadbench/test_qwen-boxed_-1_seed0_t0.0_s0_e-1.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:102cedef8e54800640a93e6a2842e221d78c6e39eb1c785c74baf7c82de8a84e
+size 11002333

math_eval/olympiadbench/test_qwen-boxed_-1_seed0_t0.0_s0_e-1_qwen-boxed_metrics.json

@@ -0,0 +1,9 @@
+{
+    "num_samples": 675,
+    "num_scores": 675,
+    "timeout_samples": 0,
+    "empty_samples": 8,
+    "acc": 28.9,
+    "time_use_in_second": 445.92377376556396,
+    "time_use_in_minite": "7:25"
+}