Add files using upload-large-folder tool

eval_results/global_step_70/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": 39.98672890663147,
+    "time_use_in_minite": "0:39"
+}

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": 42.5,
+    "pass_acc": 42.5,
+    "pass@k": {
+        "1": 42.5
+    },
+    "time_use_in_second": 10.751169919967651,
+    "time_use_in_minite": "0:10"
+}

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": 226.53313755989075,
+    "time_use_in_minite": "3:46"
+}

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": 61.8,
+    "pass_acc": 61.8,
+    "pass@k": {
+        "1": 61.8
+    },
+    "time_use_in_second": 215.82098245620728,
+    "time_use_in_minite": "3:35"
+}

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": 1,
+    "empty_samples": 0,
+    "acc": 26.5,
+    "pass_acc": 26.5,
+    "pass@k": {
+        "1": 26.5
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 47.9,
+        "Dynamics and Control (2.003 Spring 2005)": 46.2,
+        "Ecology I (1.018J Fall 2009)": 20.0,
+        "Information and Entropy (6.050J Spring 2008)": 33.3,
+        "Introduction to Astronomy (8.282J Spring 2006)": 17.0,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 16.5,
+        "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": 171.99901270866394,
+    "time_use_in_minite": "2:51"
+}

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": 1,
+    "empty_samples": 2,
+    "acc": 55.5,
+    "pass_acc": 55.5,
+    "pass@k": {
+        "1": 55.5
+    },
+    "type_acc": {
+        "abstract_algebra": 47.0,
+        "astronomy": 61.2,
+        "college_biology": 60.4,
+        "college_chemistry": 44.0,
+        "college_computer_science": 45.0,
+        "college_mathematics": 38.0,
+        "college_physics": 49.0,
+        "computer_security": 56.0,
+        "conceptual_physics": 59.1,
+        "electrical_engineering": 56.6,
+        "elementary_mathematics": 67.7,
+        "high_school_biology": 62.6,
+        "high_school_chemistry": 60.6,
+        "high_school_computer_science": 64.0,
+        "high_school_mathematics": 35.2,
+        "high_school_physics": 56.3,
+        "high_school_statistics": 53.7,
+        "machine_learning": 53.6
+    },
+    "time_use_in_second": 434.28683280944824,
+    "time_use_in_minite": "7:14"
+}

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": 28.1,
+    "pass_acc": 28.1,
+    "pass@k": {
+        "1": 28.1
+    },
+    "time_use_in_second": 391.85224533081055,
+    "time_use_in_minite": "6:31"
+}

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": 168.11040616035461,
+    "time_use_in_minite": "2:48"
+}

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": 1,
+    "empty_samples": 0,
+    "acc": 3.3,
+    "pass_acc": 3.3,
+    "pass@k": {
+        "1": 3.3
+    },
+    "time_use_in_second": 153.61491012573242,
+    "time_use_in_minite": "2:33"
+}

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": 25.0,
+    "pass_acc": 25.0,
+    "pass@k": {
+        "1": 25.0
+    },
+    "time_use_in_second": 157.09997868537903,
+    "time_use_in_minite": "2:37"
+}

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": 82.0,
+    "pass_acc": 82.0,
+    "pass@k": {
+        "1": 82.0
+    },
+    "time_use_in_second": 202.64411163330078,
+    "time_use_in_minite": "3:22"
+}

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": 1,
+    "acc": 64.4,
+    "pass_acc": 64.4,
+    "pass@k": {
+        "1": 64.4
+    },
+    "time_use_in_second": 207.95617079734802,
+    "time_use_in_minite": "3:27"
+}

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": 24.3,
+    "pass_acc": 24.3,
+    "pass@k": {
+        "1": 24.3
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 45.8,
+        "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)": 13.2,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 17.5,
+        "Physical Chemistry (5.61 Fall 2017)": 18.2,
+        "Principles of Microeconomics (14.01 Fall 2011)": 38.9,
+        "Relativity (8.033 Fall 2006)": 0.0
+    },
+    "time_use_in_second": 182.77215790748596,
+    "time_use_in_minite": "3:02"
+}

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": 4,
+    "empty_samples": 0,
+    "acc": 59.4,
+    "pass_acc": 59.4,
+    "pass@k": {
+        "1": 59.4
+    },
+    "type_acc": {
+        "abstract_algebra": 44.0,
+        "astronomy": 63.2,
+        "college_biology": 66.0,
+        "college_chemistry": 49.0,
+        "college_computer_science": 51.0,
+        "college_mathematics": 55.0,
+        "college_physics": 54.9,
+        "computer_security": 59.0,
+        "conceptual_physics": 67.2,
+        "electrical_engineering": 57.9,
+        "elementary_mathematics": 73.5,
+        "high_school_biology": 70.0,
+        "high_school_chemistry": 56.7,
+        "high_school_computer_science": 70.0,
+        "high_school_mathematics": 39.6,
+        "high_school_physics": 56.3,
+        "high_school_statistics": 55.1,
+        "machine_learning": 50.0
+    },
+    "time_use_in_second": 436.29017210006714,
+    "time_use_in_minite": "7:16"
+}

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": 26.4,
+    "pass_acc": 26.4,
+    "pass@k": {
+        "1": 26.4
+    },
+    "time_use_in_second": 408.1657428741455,
+    "time_use_in_minite": "6:48"
+}

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": 159.29473733901978,
+    "time_use_in_minite": "2:39"
+}

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": 10.0,
+    "pass_acc": 10.0,
+    "pass@k": {
+        "1": 10.0
+    },
+    "time_use_in_second": 133.72769832611084,
+    "time_use_in_minite": "2:13"
+}

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": 42.5,
+    "pass_acc": 42.5,
+    "pass@k": {
+        "1": 42.5
+    },
+    "time_use_in_second": 153.2292251586914,
+    "time_use_in_minite": "2:33"
+}

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": 82.6,
+    "pass_acc": 82.6,
+    "pass@k": {
+        "1": 82.6
+    },
+    "time_use_in_second": 195.806147813797,
+    "time_use_in_minite": "3:15"
+}

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": 64.4,
+    "pass_acc": 64.4,
+    "pass@k": {
+        "1": 64.4
+    },
+    "time_use_in_second": 252.0947515964508,
+    "time_use_in_minite": "4:12"
+}

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": 3,
+    "empty_samples": 0,
+    "acc": 26.5,
+    "pass_acc": 26.5,
+    "pass@k": {
+        "1": 26.5
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 54.2,
+        "Dynamics and Control (2.003 Spring 2005)": 34.6,
+        "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)": 15.5,
+        "Physical Chemistry (5.61 Fall 2017)": 0.0,
+        "Principles of Microeconomics (14.01 Fall 2011)": 44.4,
+        "Relativity (8.033 Fall 2006)": 27.3
+    },
+    "time_use_in_second": 177.2519736289978,
+    "time_use_in_minite": "2:57"
+}

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": 0,
+    "empty_samples": 1,
+    "acc": 60.7,
+    "pass_acc": 60.7,
+    "pass@k": {
+        "1": 60.7
+    },
+    "type_acc": {
+        "abstract_algebra": 48.0,
+        "astronomy": 61.8,
+        "college_biology": 68.8,
+        "college_chemistry": 53.0,
+        "college_computer_science": 57.0,
+        "college_mathematics": 47.0,
+        "college_physics": 55.9,
+        "computer_security": 60.0,
+        "conceptual_physics": 64.7,
+        "electrical_engineering": 53.8,
+        "elementary_mathematics": 79.6,
+        "high_school_biology": 68.7,
+        "high_school_chemistry": 62.6,
+        "high_school_computer_science": 69.0,
+        "high_school_mathematics": 41.9,
+        "high_school_physics": 57.0,
+        "high_school_statistics": 55.1,
+        "machine_learning": 52.7
+    },
+    "time_use_in_second": 415.04196524620056,
+    "time_use_in_minite": "6:55"
+}