Add files using upload-large-folder tool

eval_results/global_step_20/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": 61.8,
+    "pass_acc": 61.8,
+    "pass@k": {
+        "1": 61.8
+    },
+    "time_use_in_second": 209.1798279285431,
+    "time_use_in_minite": "3:29"
+}

eval_results/global_step_20/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": 1,
+    "acc": 23.2,
+    "pass_acc": 23.2,
+    "pass@k": {
+        "1": 23.2
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 47.9,
+        "Dynamics and Control (2.003 Spring 2005)": 38.5,
+        "Ecology I (1.018J Fall 2009)": 0.0,
+        "Information and Entropy (6.050J Spring 2008)": 33.3,
+        "Introduction to Astronomy (8.282J Spring 2006)": 15.1,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 11.3,
+        "Physical Chemistry (5.61 Fall 2017)": 0.0,
+        "Principles of Microeconomics (14.01 Fall 2011)": 44.4,
+        "Relativity (8.033 Fall 2006)": 18.2
+    },
+    "time_use_in_second": 163.57887530326843,
+    "time_use_in_minite": "2:43"
+}

eval_results/global_step_20/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": 7,
+    "acc": 46.5,
+    "pass_acc": 46.5,
+    "pass@k": {
+        "1": 46.5
+    },
+    "type_acc": {
+        "abstract_algebra": 31.0,
+        "astronomy": 53.9,
+        "college_biology": 57.6,
+        "college_chemistry": 41.0,
+        "college_computer_science": 43.0,
+        "college_mathematics": 32.0,
+        "college_physics": 36.3,
+        "computer_security": 50.0,
+        "conceptual_physics": 56.6,
+        "electrical_engineering": 57.9,
+        "elementary_mathematics": 41.8,
+        "high_school_biology": 66.8,
+        "high_school_chemistry": 47.8,
+        "high_school_computer_science": 50.0,
+        "high_school_mathematics": 20.4,
+        "high_school_physics": 41.7,
+        "high_school_statistics": 48.1,
+        "machine_learning": 46.4
+    },
+    "time_use_in_second": 424.80005264282227,
+    "time_use_in_minite": "7:04"
+}

eval_results/global_step_20/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": 22.2,
+    "pass_acc": 22.2,
+    "pass@k": {
+        "1": 22.2
+    },
+    "time_use_in_second": 370.25228238105774,
+    "time_use_in_minite": "6:10"
+}

eval_results/global_step_30/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": 3.3,
+    "pass_acc": 3.3,
+    "pass@k": {
+        "1": 3.3
+    },
+    "time_use_in_second": 39.19697904586792,
+    "time_use_in_minite": "0:39"
+}

eval_results/global_step_30/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": 145.47153449058533,
+    "time_use_in_minite": "2:25"
+}

eval_results/global_step_30/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": 32.5,
+    "pass_acc": 32.5,
+    "pass@k": {
+        "1": 32.5
+    },
+    "time_use_in_second": 146.0725929737091,
+    "time_use_in_minite": "2:26"
+}

eval_results/global_step_30/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": 79.9,
+    "pass_acc": 79.9,
+    "pass@k": {
+        "1": 79.9
+    },
+    "time_use_in_second": 211.3379385471344,
+    "time_use_in_minite": "3:31"
+}

eval_results/global_step_30/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": 62.2,
+    "pass_acc": 62.2,
+    "pass@k": {
+        "1": 62.2
+    },
+    "time_use_in_second": 205.48666501045227,
+    "time_use_in_minite": "3:25"
+}

eval_results/global_step_30/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": 3,
+    "acc": 22.4,
+    "pass_acc": 22.4,
+    "pass@k": {
+        "1": 22.4
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 43.8,
+        "Dynamics and Control (2.003 Spring 2005)": 42.3,
+        "Ecology I (1.018J Fall 2009)": 40.0,
+        "Information and Entropy (6.050J Spring 2008)": 66.7,
+        "Introduction to Astronomy (8.282J Spring 2006)": 7.5,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 11.3,
+        "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": 169.33431148529053,
+    "time_use_in_minite": "2:49"
+}

eval_results/global_step_30/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": 4,
+    "empty_samples": 8,
+    "acc": 48.5,
+    "pass_acc": 48.5,
+    "pass@k": {
+        "1": 48.5
+    },
+    "type_acc": {
+        "abstract_algebra": 33.0,
+        "astronomy": 59.2,
+        "college_biology": 60.4,
+        "college_chemistry": 41.0,
+        "college_computer_science": 48.0,
+        "college_mathematics": 37.0,
+        "college_physics": 41.2,
+        "computer_security": 53.0,
+        "conceptual_physics": 61.7,
+        "electrical_engineering": 54.5,
+        "elementary_mathematics": 49.7,
+        "high_school_biology": 63.2,
+        "high_school_chemistry": 47.3,
+        "high_school_computer_science": 58.0,
+        "high_school_mathematics": 17.4,
+        "high_school_physics": 41.7,
+        "high_school_statistics": 50.5,
+        "machine_learning": 45.5
+    },
+    "time_use_in_second": 467.60332226753235,
+    "time_use_in_minite": "7:47"
+}

eval_results/global_step_30/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": 24.9,
+    "pass_acc": 24.9,
+    "pass@k": {
+        "1": 24.9
+    },
+    "time_use_in_second": 352.9934434890747,
+    "time_use_in_minite": "5:52"
+}

eval_results/global_step_40/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": 149.70813250541687,
+    "time_use_in_minite": "2:29"
+}

eval_results/global_step_40/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": 3.3,
+    "pass_acc": 3.3,
+    "pass@k": {
+        "1": 3.3
+    },
+    "time_use_in_second": 146.4937720298767,
+    "time_use_in_minite": "2:26"
+}

eval_results/global_step_40/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": 27.5,
+    "pass_acc": 27.5,
+    "pass@k": {
+        "1": 27.5
+    },
+    "time_use_in_second": 153.41063284873962,
+    "time_use_in_minite": "2:33"
+}

eval_results/global_step_40/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": 80.2,
+    "pass_acc": 80.2,
+    "pass@k": {
+        "1": 80.2
+    },
+    "time_use_in_second": 194.10877060890198,
+    "time_use_in_minite": "3:14"
+}

eval_results/global_step_40/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": 62.8,
+    "pass_acc": 62.8,
+    "pass@k": {
+        "1": 62.8
+    },
+    "time_use_in_second": 194.2277638912201,
+    "time_use_in_minite": "3:14"
+}

eval_results/global_step_40/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": 27.9,
+    "pass_acc": 27.9,
+    "pass@k": {
+        "1": 27.9
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 54.2,
+        "Dynamics and Control (2.003 Spring 2005)": 46.2,
+        "Ecology I (1.018J Fall 2009)": 60.0,
+        "Information and Entropy (6.050J Spring 2008)": 0.0,
+        "Introduction to Astronomy (8.282J Spring 2006)": 15.1,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 16.5,
+        "Physical Chemistry (5.61 Fall 2017)": 9.1,
+        "Principles of Microeconomics (14.01 Fall 2011)": 44.4,
+        "Relativity (8.033 Fall 2006)": 18.2
+    },
+    "time_use_in_second": 174.37697458267212,
+    "time_use_in_minite": "2:54"
+}

eval_results/global_step_40/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": 2,
+    "empty_samples": 5,
+    "acc": 52.0,
+    "pass_acc": 52.0,
+    "pass@k": {
+        "1": 52.0
+    },
+    "type_acc": {
+        "abstract_algebra": 34.0,
+        "astronomy": 65.1,
+        "college_biology": 63.9,
+        "college_chemistry": 46.0,
+        "college_computer_science": 48.0,
+        "college_mathematics": 38.0,
+        "college_physics": 50.0,
+        "computer_security": 46.0,
+        "conceptual_physics": 60.9,
+        "electrical_engineering": 55.2,
+        "elementary_mathematics": 53.4,
+        "high_school_biology": 67.4,
+        "high_school_chemistry": 56.7,
+        "high_school_computer_science": 67.0,
+        "high_school_mathematics": 21.9,
+        "high_school_physics": 48.3,
+        "high_school_statistics": 50.9,
+        "machine_learning": 50.0
+    },
+    "time_use_in_second": 409.8589496612549,
+    "time_use_in_minite": "6:49"
+}

eval_results/global_step_40/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": 1,
+    "empty_samples": 0,
+    "acc": 25.3,
+    "pass_acc": 25.3,
+    "pass@k": {
+        "1": 25.3
+    },
+    "time_use_in_second": 418.00734639167786,
+    "time_use_in_minite": "6:58"
+}

eval_results/global_step_50/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": 152.48893404006958,
+    "time_use_in_minite": "2:32"
+}