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": 60.6,
+    "pass_acc": 60.6,
+    "pass@k": {
+        "1": 60.6
+    },
+    "time_use_in_second": 224.34149503707886,
+    "time_use_in_minite": "3:44"
+}

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": 1,
+    "empty_samples": 1,
+    "acc": 26.5,
+    "pass_acc": 26.5,
+    "pass@k": {
+        "1": 26.5
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 52.1,
+        "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)": 15.1,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 14.4,
+        "Physical Chemistry (5.61 Fall 2017)": 9.1,
+        "Principles of Microeconomics (14.01 Fall 2011)": 50.0,
+        "Relativity (8.033 Fall 2006)": 0.0
+    },
+    "time_use_in_second": 196.60941886901855,
+    "time_use_in_minite": "3:16"
+}

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": 6,
+    "empty_samples": 1,
+    "acc": 46.2,
+    "pass_acc": 46.2,
+    "pass@k": {
+        "1": 46.2
+    },
+    "type_acc": {
+        "abstract_algebra": 37.0,
+        "astronomy": 59.2,
+        "college_biology": 59.7,
+        "college_chemistry": 42.0,
+        "college_computer_science": 42.0,
+        "college_mathematics": 29.0,
+        "college_physics": 40.2,
+        "computer_security": 55.0,
+        "conceptual_physics": 58.3,
+        "electrical_engineering": 47.6,
+        "elementary_mathematics": 38.1,
+        "high_school_biology": 62.6,
+        "high_school_chemistry": 49.3,
+        "high_school_computer_science": 53.0,
+        "high_school_mathematics": 18.5,
+        "high_school_physics": 43.7,
+        "high_school_statistics": 50.9,
+        "machine_learning": 42.9
+    },
+    "time_use_in_second": 427.97210025787354,
+    "time_use_in_minite": "7:07"
+}

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": 1,
+    "acc": 25.5,
+    "pass_acc": 25.5,
+    "pass@k": {
+        "1": 25.5
+    },
+    "time_use_in_second": 360.7439937591553,
+    "time_use_in_minite": "6:00"
+}

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": 150.81112670898438,
+    "time_use_in_minite": "2:30"
+}

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": 3.3,
+    "pass_acc": 3.3,
+    "pass@k": {
+        "1": 3.3
+    },
+    "time_use_in_second": 138.79038548469543,
+    "time_use_in_minite": "2:18"
+}

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": 140.12043976783752,
+    "time_use_in_minite": "2:20"
+}

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": 1,
+    "acc": 79.6,
+    "pass_acc": 79.6,
+    "pass@k": {
+        "1": 79.6
+    },
+    "time_use_in_second": 200.72886109352112,
+    "time_use_in_minite": "3:20"
+}

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": 60.8,
+    "pass_acc": 60.8,
+    "pass@k": {
+        "1": 60.8
+    },
+    "time_use_in_second": 206.27783274650574,
+    "time_use_in_minite": "3:26"
+}

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": 1,
+    "empty_samples": 2,
+    "acc": 26.8,
+    "pass_acc": 26.8,
+    "pass@k": {
+        "1": 26.8
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 52.1,
+        "Dynamics and Control (2.003 Spring 2005)": 38.5,
+        "Ecology I (1.018J Fall 2009)": 40.0,
+        "Information and Entropy (6.050J Spring 2008)": 0.0,
+        "Introduction to Astronomy (8.282J Spring 2006)": 13.2,
+        "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)": 18.2
+    },
+    "time_use_in_second": 166.70260381698608,
+    "time_use_in_minite": "2:46"
+}

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": 5,
+    "empty_samples": 0,
+    "acc": 49.5,
+    "pass_acc": 49.5,
+    "pass@k": {
+        "1": 49.5
+    },
+    "type_acc": {
+        "abstract_algebra": 33.0,
+        "astronomy": 61.8,
+        "college_biology": 57.6,
+        "college_chemistry": 43.0,
+        "college_computer_science": 46.0,
+        "college_mathematics": 37.0,
+        "college_physics": 48.0,
+        "computer_security": 55.0,
+        "conceptual_physics": 62.6,
+        "electrical_engineering": 50.3,
+        "elementary_mathematics": 47.9,
+        "high_school_biology": 64.2,
+        "high_school_chemistry": 50.7,
+        "high_school_computer_science": 59.0,
+        "high_school_mathematics": 21.5,
+        "high_school_physics": 50.3,
+        "high_school_statistics": 48.6,
+        "machine_learning": 46.4
+    },
+    "time_use_in_second": 450.33214259147644,
+    "time_use_in_minite": "7:30"
+}

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": 27.0,
+    "pass_acc": 27.0,
+    "pass@k": {
+        "1": 27.0
+    },
+    "time_use_in_second": 368.3768582344055,
+    "time_use_in_minite": "6:08"
+}

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": 13.3,
+    "pass_acc": 13.3,
+    "pass@k": {
+        "1": 13.3
+    },
+    "time_use_in_second": 140.23443508148193,
+    "time_use_in_minite": "2:20"
+}

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": 6.7,
+    "pass_acc": 6.7,
+    "pass@k": {
+        "1": 6.7
+    },
+    "time_use_in_second": 136.14000034332275,
+    "time_use_in_minite": "2:16"
+}

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": 32.5,
+    "pass_acc": 32.5,
+    "pass@k": {
+        "1": 32.5
+    },
+    "time_use_in_second": 142.76098036766052,
+    "time_use_in_minite": "2:22"
+}

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": 80.3,
+    "pass_acc": 80.3,
+    "pass@k": {
+        "1": 80.3
+    },
+    "time_use_in_second": 221.4554967880249,
+    "time_use_in_minite": "3:41"
+}

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": 61.8,
+    "pass_acc": 61.8,
+    "pass@k": {
+        "1": 61.8
+    },
+    "time_use_in_second": 207.39032745361328,
+    "time_use_in_minite": "3:27"
+}

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": 28.3,
+    "pass_acc": 28.3,
+    "pass@k": {
+        "1": 28.3
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 52.1,
+        "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)": 15.1,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 17.5,
+        "Physical Chemistry (5.61 Fall 2017)": 9.1,
+        "Principles of Microeconomics (14.01 Fall 2011)": 61.1,
+        "Relativity (8.033 Fall 2006)": 0.0
+    },
+    "time_use_in_second": 30.424518585205078,
+    "time_use_in_minite": "0:30"
+}

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": 1,
+    "empty_samples": 2,
+    "acc": 51.8,
+    "pass_acc": 51.8,
+    "pass@k": {
+        "1": 51.8
+    },
+    "type_acc": {
+        "abstract_algebra": 37.0,
+        "astronomy": 58.6,
+        "college_biology": 64.6,
+        "college_chemistry": 38.0,
+        "college_computer_science": 50.0,
+        "college_mathematics": 34.0,
+        "college_physics": 50.0,
+        "computer_security": 56.0,
+        "conceptual_physics": 62.1,
+        "electrical_engineering": 53.1,
+        "elementary_mathematics": 52.4,
+        "high_school_biology": 63.9,
+        "high_school_chemistry": 54.7,
+        "high_school_computer_science": 68.0,
+        "high_school_mathematics": 29.6,
+        "high_school_physics": 45.0,
+        "high_school_statistics": 54.2,
+        "machine_learning": 46.4
+    },
+    "time_use_in_second": 374.854798078537,
+    "time_use_in_minite": "6:14"
+}

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": 0,
+    "empty_samples": 0,
+    "acc": 26.4,
+    "pass_acc": 26.4,
+    "pass@k": {
+        "1": 26.4
+    },
+    "time_use_in_second": 354.25014901161194,
+    "time_use_in_minite": "5:54"
+}

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": 53.92802691459656,
+    "time_use_in_minite": "0:53"
+}