Add files using upload-large-folder tool

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/global_step_60/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": 4,
+    "acc": 85.6,
+    "pass_acc": 85.6,
+    "pass@k": {
+        "1": 85.6
+    },
+    "type_acc": {
+        "abstract_algebra": 85.0,
+        "astronomy": 88.8,
+        "college_biology": 89.6,
+        "college_chemistry": 68.0,
+        "college_computer_science": 75.0,
+        "college_mathematics": 79.0,
+        "college_physics": 86.3,
+        "computer_security": 71.0,
+        "conceptual_physics": 86.8,
+        "electrical_engineering": 76.6,
+        "elementary_mathematics": 95.2,
+        "high_school_biology": 91.6,
+        "high_school_chemistry": 85.2,
+        "high_school_computer_science": 86.0,
+        "high_school_mathematics": 90.7,
+        "high_school_physics": 84.8,
+        "high_school_statistics": 81.9,
+        "machine_learning": 76.8
+    },
+    "time_use_in_second": 453.47122716903687,
+    "time_use_in_minite": "7:33"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/global_step_60/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": 49.2,
+    "pass_acc": 49.2,
+    "pass@k": {
+        "1": 49.2
+    },
+    "time_use_in_second": 739.9170608520508,
+    "time_use_in_minite": "12:19"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/eval_results/global_step_70/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": 30.0,
+    "pass_acc": 30.0,
+    "pass@k": {
+        "1": 30.0
+    },
+    "time_use_in_second": 256.68022561073303,
+    "time_use_in_minite": "4:16"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 16.7,
+    "pass_acc": 16.7,
+    "pass@k": {
+        "1": 16.7
+    },
+    "time_use_in_second": 244.1304202079773,
+    "time_use_in_minite": "4:04"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 65.0,
+    "pass_acc": 65.0,
+    "pass@k": {
+        "1": 65.0
+    },
+    "time_use_in_second": 55.264809131622314,
+    "time_use_in_minite": "0:55"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 93.5,
+    "pass_acc": 93.5,
+    "pass@k": {
+        "1": 93.5
+    },
+    "time_use_in_second": 102.33035564422607,
+    "time_use_in_minite": "1:42"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 84.0,
+    "pass_acc": 84.0,
+    "pass@k": {
+        "1": 84.0
+    },
+    "time_use_in_second": 222.14642930030823,
+    "time_use_in_minite": "3:42"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 43.4,
+    "pass_acc": 43.4,
+    "pass@k": {
+        "1": 43.4
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 72.9,
+        "Dynamics and Control (2.003 Spring 2005)": 50.0,
+        "Ecology I (1.018J Fall 2009)": 60.0,
+        "Information and Entropy (6.050J Spring 2008)": 66.7,
+        "Introduction to Astronomy (8.282J Spring 2006)": 34.0,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 26.8,
+        "Physical Chemistry (5.61 Fall 2017)": 27.3,
+        "Principles of Microeconomics (14.01 Fall 2011)": 72.2,
+        "Relativity (8.033 Fall 2006)": 45.5
+    },
+    "time_use_in_second": 236.5802080631256,
+    "time_use_in_minite": "3:56"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 3,
+    "acc": 85.6,
+    "pass_acc": 85.6,
+    "pass@k": {
+        "1": 85.6
+    },
+    "type_acc": {
+        "abstract_algebra": 82.0,
+        "astronomy": 88.8,
+        "college_biology": 86.8,
+        "college_chemistry": 67.0,
+        "college_computer_science": 80.0,
+        "college_mathematics": 79.0,
+        "college_physics": 91.2,
+        "computer_security": 67.0,
+        "conceptual_physics": 85.1,
+        "electrical_engineering": 77.2,
+        "elementary_mathematics": 95.5,
+        "high_school_biology": 90.3,
+        "high_school_chemistry": 87.7,
+        "high_school_computer_science": 92.0,
+        "high_school_mathematics": 88.9,
+        "high_school_physics": 83.4,
+        "high_school_statistics": 83.3,
+        "machine_learning": 76.8
+    },
+    "time_use_in_second": 446.51267433166504,
+    "time_use_in_minite": "7:26"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 1,
+    "empty_samples": 0,
+    "acc": 47.6,
+    "pass_acc": 47.6,
+    "pass@k": {
+        "1": 47.6
+    },
+    "time_use_in_second": 731.3076951503754,
+    "time_use_in_minite": "12:11"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 30.0,
+    "pass_acc": 30.0,
+    "pass@k": {
+        "1": 30.0
+    },
+    "time_use_in_second": 248.597638130188,
+    "time_use_in_minite": "4:08"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 16.7,
+    "pass_acc": 16.7,
+    "pass@k": {
+        "1": 16.7
+    },
+    "time_use_in_second": 104.9330325126648,
+    "time_use_in_minite": "1:44"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 70.0,
+    "pass_acc": 70.0,
+    "pass@k": {
+        "1": 70.0
+    },
+    "time_use_in_second": 135.92350673675537,
+    "time_use_in_minite": "2:15"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 94.2,
+    "pass_acc": 94.2,
+    "pass@k": {
+        "1": 94.2
+    },
+    "time_use_in_second": 92.96837067604065,
+    "time_use_in_minite": "1:32"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 85.6,
+    "pass_acc": 85.6,
+    "pass@k": {
+        "1": 85.6
+    },
+    "time_use_in_second": 355.6146864891052,
+    "time_use_in_minite": "5:55"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 44.1,
+    "pass_acc": 44.1,
+    "pass@k": {
+        "1": 44.1
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 66.7,
+        "Dynamics and Control (2.003 Spring 2005)": 53.8,
+        "Ecology I (1.018J Fall 2009)": 60.0,
+        "Information and Entropy (6.050J Spring 2008)": 66.7,
+        "Introduction to Astronomy (8.282J Spring 2006)": 37.7,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 27.8,
+        "Physical Chemistry (5.61 Fall 2017)": 27.3,
+        "Principles of Microeconomics (14.01 Fall 2011)": 77.8,
+        "Relativity (8.033 Fall 2006)": 45.5
+    },
+    "time_use_in_second": 127.21856451034546,
+    "time_use_in_minite": "2:07"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 0,
+    "empty_samples": 0,
+    "acc": 85.4,
+    "pass_acc": 85.4,
+    "pass@k": {
+        "1": 85.4
+    },
+    "type_acc": {
+        "abstract_algebra": 85.0,
+        "astronomy": 88.8,
+        "college_biology": 88.9,
+        "college_chemistry": 67.0,
+        "college_computer_science": 77.0,
+        "college_mathematics": 77.0,
+        "college_physics": 85.3,
+        "computer_security": 69.0,
+        "conceptual_physics": 86.0,
+        "electrical_engineering": 77.2,
+        "elementary_mathematics": 94.7,
+        "high_school_biology": 91.9,
+        "high_school_chemistry": 86.2,
+        "high_school_computer_science": 87.0,
+        "high_school_mathematics": 90.0,
+        "high_school_physics": 83.4,
+        "high_school_statistics": 82.4,
+        "machine_learning": 75.9
+    },
+    "time_use_in_second": 446.0400495529175,
+    "time_use_in_minite": "7:26"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 1,
+    "acc": 49.9,
+    "pass_acc": 49.9,
+    "pass@k": {
+        "1": 49.9
+    },
+    "time_use_in_second": 766.2501382827759,
+    "time_use_in_minite": "12:46"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 26.7,
+    "pass_acc": 26.7,
+    "pass@k": {
+        "1": 26.7
+    },
+    "time_use_in_second": 244.0300760269165,
+    "time_use_in_minite": "4:04"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 13.3,
+    "pass_acc": 13.3,
+    "pass@k": {
+        "1": 13.3
+    },
+    "time_use_in_second": 253.21099305152893,
+    "time_use_in_minite": "4:13"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 70.0,
+    "pass_acc": 70.0,
+    "pass@k": {
+        "1": 70.0
+    },
+    "time_use_in_second": 145.44669604301453,
+    "time_use_in_minite": "2:25"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 93.9,
+    "pass_acc": 93.9,
+    "pass@k": {
+        "1": 93.9
+    },
+    "time_use_in_second": 92.97574210166931,
+    "time_use_in_minite": "1:32"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 85.8,
+    "pass_acc": 85.8,
+    "pass@k": {
+        "1": 85.8
+    },
+    "time_use_in_second": 297.74292850494385,
+    "time_use_in_minite": "4:57"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 1,
+    "empty_samples": 0,
+    "acc": 42.6,
+    "pass_acc": 42.6,
+    "pass@k": {
+        "1": 42.6
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 66.7,
+        "Dynamics and Control (2.003 Spring 2005)": 57.7,
+        "Ecology I (1.018J Fall 2009)": 60.0,
+        "Information and Entropy (6.050J Spring 2008)": 66.7,
+        "Introduction to Astronomy (8.282J Spring 2006)": 28.3,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 27.8,
+        "Physical Chemistry (5.61 Fall 2017)": 18.2,
+        "Principles of Microeconomics (14.01 Fall 2011)": 77.8,
+        "Relativity (8.033 Fall 2006)": 54.5
+    },
+    "time_use_in_second": 58.997036933898926,
+    "time_use_in_minite": "0:58"
+}

reinforce_pp_deepmath_train_sample_6144_context_4k_Qwen3-8B-Base_max_response4096_batch1024_ppomini256_rollout8_vllm/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": 86.1,
+    "pass_acc": 86.1,
+    "pass@k": {
+        "1": 86.1
+    },
+    "type_acc": {
+        "abstract_algebra": 87.0,
+        "astronomy": 89.5,
+        "college_biology": 88.2,
+        "college_chemistry": 66.0,
+        "college_computer_science": 76.0,
+        "college_mathematics": 75.0,
+        "college_physics": 88.2,
+        "computer_security": 65.0,
+        "conceptual_physics": 88.9,
+        "electrical_engineering": 77.9,
+        "elementary_mathematics": 96.6,
+        "high_school_biology": 92.3,
+        "high_school_chemistry": 87.7,
+        "high_school_computer_science": 83.0,
+        "high_school_mathematics": 91.9,
+        "high_school_physics": 83.4,
+        "high_school_statistics": 84.3,
+        "machine_learning": 78.6
+    },
+    "time_use_in_second": 508.3278658390045,
+    "time_use_in_minite": "8:28"
+}