Add files using upload-large-folder tool

eval_results/global_step_70/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 40,
+    "num_scores": 40,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 35.0,
+    "pass_acc": 35.0,
+    "pass@k": {
+        "1": 35.0
+    },
+    "time_use_in_second": 15.2857027053833,
+    "time_use_in_minite": "0:15"
+}

eval_results/global_step_70/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 1319,
+    "num_scores": 1319,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 82.3,
+    "pass_acc": 82.3,
+    "pass@k": {
+        "1": 82.3
+    },
+    "time_use_in_second": 222.78310704231262,
+    "time_use_in_minite": "3:42"
+}

eval_results/global_step_70/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 500,
+    "num_scores": 500,
+    "timeout_samples": 0,
+    "empty_samples": 1,
+    "acc": 64.4,
+    "pass_acc": 64.4,
+    "pass@k": {
+        "1": 64.4
+    },
+    "time_use_in_second": 217.67270517349243,
+    "time_use_in_minite": "3:37"
+}

eval_results/global_step_70/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,24 @@
+{
+    "num_samples": 272,
+    "num_scores": 272,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 28.3,
+    "pass_acc": 28.3,
+    "pass@k": {
+        "1": 28.3
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 50.0,
+        "Dynamics and Control (2.003 Spring 2005)": 38.5,
+        "Ecology I (1.018J Fall 2009)": 60.0,
+        "Information and Entropy (6.050J Spring 2008)": 33.3,
+        "Introduction to Astronomy (8.282J Spring 2006)": 13.2,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 22.7,
+        "Physical Chemistry (5.61 Fall 2017)": 0.0,
+        "Principles of Microeconomics (14.01 Fall 2011)": 55.6,
+        "Relativity (8.033 Fall 2006)": 0.0
+    },
+    "time_use_in_second": 152.92707705497742,
+    "time_use_in_minite": "2:32"
+}

eval_results/global_step_70/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,33 @@
+{
+    "num_samples": 3018,
+    "num_scores": 3018,
+    "timeout_samples": 3,
+    "empty_samples": 0,
+    "acc": 60.0,
+    "pass_acc": 60.0,
+    "pass@k": {
+        "1": 60.0
+    },
+    "type_acc": {
+        "abstract_algebra": 45.0,
+        "astronomy": 61.2,
+        "college_biology": 65.3,
+        "college_chemistry": 52.0,
+        "college_computer_science": 51.0,
+        "college_mathematics": 41.0,
+        "college_physics": 60.8,
+        "computer_security": 65.0,
+        "conceptual_physics": 63.8,
+        "electrical_engineering": 62.1,
+        "elementary_mathematics": 73.3,
+        "high_school_biology": 67.4,
+        "high_school_chemistry": 61.1,
+        "high_school_computer_science": 70.0,
+        "high_school_mathematics": 37.4,
+        "high_school_physics": 59.6,
+        "high_school_statistics": 61.6,
+        "machine_learning": 58.0
+    },
+    "time_use_in_second": 446.1949541568756,
+    "time_use_in_minite": "7:26"
+}

eval_results/global_step_70/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 675,
+    "num_scores": 675,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 27.1,
+    "pass_acc": 27.1,
+    "pass@k": {
+        "1": 27.1
+    },
+    "time_use_in_second": 378.41182827949524,
+    "time_use_in_minite": "6:18"
+}

eval_results/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 30,
+    "num_scores": 30,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 6.7,
+    "pass_acc": 6.7,
+    "pass@k": {
+        "1": 6.7
+    },
+    "time_use_in_second": 160.06483268737793,
+    "time_use_in_minite": "2:40"
+}

eval_results/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 30,
+    "num_scores": 30,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 0.0,
+    "pass_acc": 0.0,
+    "pass@k": {
+        "1": 0.0
+    },
+    "time_use_in_second": 15.96849012374878,
+    "time_use_in_minite": "0:15"
+}

eval_results/global_step_80/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 40,
+    "num_scores": 40,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 40.0,
+    "pass_acc": 40.0,
+    "pass@k": {
+        "1": 40.0
+    },
+    "time_use_in_second": 13.520498752593994,
+    "time_use_in_minite": "0:13"
+}

eval_results/global_step_80/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 1319,
+    "num_scores": 1319,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 81.6,
+    "pass_acc": 81.6,
+    "pass@k": {
+        "1": 81.6
+    },
+    "time_use_in_second": 194.54892826080322,
+    "time_use_in_minite": "3:14"
+}

eval_results/global_step_80/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 500,
+    "num_scores": 500,
+    "timeout_samples": 0,
+    "empty_samples": 2,
+    "acc": 65.8,
+    "pass_acc": 65.8,
+    "pass@k": {
+        "1": 65.8
+    },
+    "time_use_in_second": 228.69391536712646,
+    "time_use_in_minite": "3:48"
+}

eval_results/global_step_80/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,24 @@
+{
+    "num_samples": 272,
+    "num_scores": 272,
+    "timeout_samples": 1,
+    "empty_samples": 0,
+    "acc": 28.3,
+    "pass_acc": 28.3,
+    "pass@k": {
+        "1": 28.3
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 60.4,
+        "Dynamics and Control (2.003 Spring 2005)": 42.3,
+        "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)": 17.5,
+        "Physical Chemistry (5.61 Fall 2017)": 0.0,
+        "Principles of Microeconomics (14.01 Fall 2011)": 55.6,
+        "Relativity (8.033 Fall 2006)": 18.2
+    },
+    "time_use_in_second": 152.58683347702026,
+    "time_use_in_minite": "2:32"
+}

eval_results/global_step_80/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,33 @@
+{
+    "num_samples": 3018,
+    "num_scores": 3018,
+    "timeout_samples": 3,
+    "empty_samples": 0,
+    "acc": 60.2,
+    "pass_acc": 60.2,
+    "pass@k": {
+        "1": 60.2
+    },
+    "type_acc": {
+        "abstract_algebra": 46.0,
+        "astronomy": 66.4,
+        "college_biology": 64.6,
+        "college_chemistry": 43.0,
+        "college_computer_science": 51.0,
+        "college_mathematics": 49.0,
+        "college_physics": 60.8,
+        "computer_security": 48.0,
+        "conceptual_physics": 61.7,
+        "electrical_engineering": 53.8,
+        "elementary_mathematics": 77.0,
+        "high_school_biology": 70.3,
+        "high_school_chemistry": 62.1,
+        "high_school_computer_science": 68.0,
+        "high_school_mathematics": 47.8,
+        "high_school_physics": 54.3,
+        "high_school_statistics": 60.2,
+        "machine_learning": 50.0
+    },
+    "time_use_in_second": 472.4004137516022,
+    "time_use_in_minite": "7:52"
+}

eval_results/global_step_80/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 675,
+    "num_scores": 675,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 29.2,
+    "pass_acc": 29.2,
+    "pass@k": {
+        "1": 29.2
+    },
+    "time_use_in_second": 336.4007785320282,
+    "time_use_in_minite": "5:36"
+}

eval_results/global_step_90/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 30,
+    "num_scores": 30,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 10.0,
+    "pass_acc": 10.0,
+    "pass@k": {
+        "1": 10.0
+    },
+    "time_use_in_second": 150.63824343681335,
+    "time_use_in_minite": "2:30"
+}

eval_results/global_step_90/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 30,
+    "num_scores": 30,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 6.7,
+    "pass_acc": 6.7,
+    "pass@k": {
+        "1": 6.7
+    },
+    "time_use_in_second": 46.11515021324158,
+    "time_use_in_minite": "0:46"
+}

eval_results/global_step_90/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 40,
+    "num_scores": 40,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 40.0,
+    "pass_acc": 40.0,
+    "pass@k": {
+        "1": 40.0
+    },
+    "time_use_in_second": 155.80011105537415,
+    "time_use_in_minite": "2:35"
+}

eval_results/global_step_90/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 1319,
+    "num_scores": 1319,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 82.9,
+    "pass_acc": 82.9,
+    "pass@k": {
+        "1": 82.9
+    },
+    "time_use_in_second": 199.40842032432556,
+    "time_use_in_minite": "3:19"
+}

eval_results/global_step_90/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,13 @@
+{
+    "num_samples": 500,
+    "num_scores": 500,
+    "timeout_samples": 0,
+    "empty_samples": 1,
+    "acc": 66.0,
+    "pass_acc": 66.0,
+    "pass@k": {
+        "1": 66.0
+    },
+    "time_use_in_second": 203.9113118648529,
+    "time_use_in_minite": "3:23"
+}

eval_results/global_step_90/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,24 @@
+{
+    "num_samples": 272,
+    "num_scores": 272,
+    "timeout_samples": 2,
+    "empty_samples": 0,
+    "acc": 29.0,
+    "pass_acc": 29.0,
+    "pass@k": {
+        "1": 29.0
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 58.3,
+        "Dynamics and Control (2.003 Spring 2005)": 42.3,
+        "Ecology I (1.018J Fall 2009)": 40.0,
+        "Information and Entropy (6.050J Spring 2008)": 0.0,
+        "Introduction to Astronomy (8.282J Spring 2006)": 18.9,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 18.6,
+        "Physical Chemistry (5.61 Fall 2017)": 0.0,
+        "Principles of Microeconomics (14.01 Fall 2011)": 50.0,
+        "Relativity (8.033 Fall 2006)": 9.1
+    },
+    "time_use_in_second": 173.75322580337524,
+    "time_use_in_minite": "2:53"
+}

eval_results/global_step_90/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,33 @@
+{
+    "num_samples": 3018,
+    "num_scores": 3018,
+    "timeout_samples": 3,
+    "empty_samples": 0,
+    "acc": 61.1,
+    "pass_acc": 61.1,
+    "pass@k": {
+        "1": 61.1
+    },
+    "type_acc": {
+        "abstract_algebra": 44.0,
+        "astronomy": 65.8,
+        "college_biology": 67.4,
+        "college_chemistry": 47.0,
+        "college_computer_science": 55.0,
+        "college_mathematics": 48.0,
+        "college_physics": 66.7,
+        "computer_security": 56.0,
+        "conceptual_physics": 63.4,
+        "electrical_engineering": 53.8,
+        "elementary_mathematics": 78.0,
+        "high_school_biology": 68.1,
+        "high_school_chemistry": 66.0,
+        "high_school_computer_science": 65.0,
+        "high_school_mathematics": 40.7,
+        "high_school_physics": 63.6,
+        "high_school_statistics": 63.4,
+        "machine_learning": 47.3
+    },
+    "time_use_in_second": 391.68414282798767,
+    "time_use_in_minite": "6:31"
+}