Add files using upload-large-folder tool

eval_results_avg4/global_step_20/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 3.3,
+    "pass_acc": 10.0,
+    "pass@k": {
+        "1": 3.3,
+        "2": 6.1,
+        "4": 10.0
+    },
+    "time_use_in_second": 181.98684406280518,
+    "time_use_in_minite": "3:01"
+}

eval_results_avg4/global_step_20/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 2.5,
+    "pass_acc": 6.7,
+    "pass@k": {
+        "1": 2.5,
+        "2": 4.4,
+        "4": 6.7
+    },
+    "time_use_in_second": 176.9613161087036,
+    "time_use_in_minite": "2:56"
+}

eval_results_avg4/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 40,
+    "num_scores": 160,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 31.9,
+    "pass_acc": 57.5,
+    "pass@k": {
+        "1": 31.9,
+        "2": 44.6,
+        "4": 57.5
+    },
+    "time_use_in_second": 177.31663274765015,
+    "time_use_in_minite": "2:57"
+}

eval_results_avg4/global_step_30/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 8.3,
+    "pass_acc": 16.7,
+    "pass@k": {
+        "1": 8.3,
+        "2": 12.8,
+        "4": 16.7
+    },
+    "time_use_in_second": 171.64313411712646,
+    "time_use_in_minite": "2:51"
+}

eval_results_avg4/global_step_30/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 4.2,
+    "pass_acc": 10.0,
+    "pass@k": {
+        "1": 4.2,
+        "2": 6.7,
+        "4": 10.0
+    },
+    "time_use_in_second": 158.31116390228271,
+    "time_use_in_minite": "2:38"
+}

eval_results_avg4/global_step_30/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 40,
+    "num_scores": 160,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 33.8,
+    "pass_acc": 50.0,
+    "pass@k": {
+        "1": 33.8,
+        "2": 42.9,
+        "4": 50.0
+    },
+    "time_use_in_second": 166.854505777359,
+    "time_use_in_minite": "2:46"
+}

eval_results_avg4/global_step_40/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 4.2,
+    "pass_acc": 6.7,
+    "pass@k": {
+        "1": 4.2,
+        "2": 5.0,
+        "4": 6.7
+    },
+    "time_use_in_second": 168.94713473320007,
+    "time_use_in_minite": "2:48"
+}

eval_results_avg4/global_step_40/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 2.5,
+    "pass_acc": 6.7,
+    "pass@k": {
+        "1": 2.5,
+        "2": 4.4,
+        "4": 6.7
+    },
+    "time_use_in_second": 141.42398166656494,
+    "time_use_in_minite": "2:21"
+}

eval_results_avg4/global_step_40/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 40,
+    "num_scores": 160,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 31.2,
+    "pass_acc": 55.0,
+    "pass@k": {
+        "1": 31.2,
+        "2": 42.5,
+        "4": 55.0
+    },
+    "time_use_in_second": 158.56345629692078,
+    "time_use_in_minite": "2:38"
+}

eval_results_avg4/global_step_50/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 8.3,
+    "pass_acc": 20.0,
+    "pass@k": {
+        "1": 8.3,
+        "2": 12.8,
+        "4": 20.0
+    },
+    "time_use_in_second": 182.78652429580688,
+    "time_use_in_minite": "3:02"
+}

eval_results_avg4/global_step_50/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 0.8,
+    "pass_acc": 3.3,
+    "pass@k": {
+        "1": 0.8,
+        "2": 1.7,
+        "4": 3.3
+    },
+    "time_use_in_second": 166.4728286266327,
+    "time_use_in_minite": "2:46"
+}

eval_results_avg4/global_step_50/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 40,
+    "num_scores": 160,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 35.0,
+    "pass_acc": 52.5,
+    "pass@k": {
+        "1": 35.0,
+        "2": 44.6,
+        "4": 52.5
+    },
+    "time_use_in_second": 152.36885404586792,
+    "time_use_in_minite": "2:32"
+}

eval_results_avg4/global_step_60/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 10.0,
+    "pass_acc": 20.0,
+    "pass@k": {
+        "1": 10.0,
+        "2": 14.4,
+        "4": 20.0
+    },
+    "time_use_in_second": 161.36754608154297,
+    "time_use_in_minite": "2:41"
+}

eval_results_avg4/global_step_60/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 2.5,
+    "pass_acc": 6.7,
+    "pass@k": {
+        "1": 2.5,
+        "2": 4.4,
+        "4": 6.7
+    },
+    "time_use_in_second": 159.51917576789856,
+    "time_use_in_minite": "2:39"
+}

eval_results_avg4/global_step_60/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 40,
+    "num_scores": 160,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 30.0,
+    "pass_acc": 45.0,
+    "pass@k": {
+        "1": 30.0,
+        "2": 38.3,
+        "4": 45.0
+    },
+    "time_use_in_second": 164.06099128723145,
+    "time_use_in_minite": "2:44"
+}

eval_results_avg4/global_step_70/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 10.8,
+    "pass_acc": 20.0,
+    "pass@k": {
+        "1": 10.8,
+        "2": 15.6,
+        "4": 20.0
+    },
+    "time_use_in_second": 161.0793993473053,
+    "time_use_in_minite": "2:41"
+}

eval_results_avg4/global_step_70/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 1.7,
+    "pass_acc": 6.7,
+    "pass@k": {
+        "1": 1.7,
+        "2": 3.3,
+        "4": 6.7
+    },
+    "time_use_in_second": 164.75507164001465,
+    "time_use_in_minite": "2:44"
+}

eval_results_avg4/global_step_70/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 40,
+    "num_scores": 160,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 35.0,
+    "pass_acc": 47.5,
+    "pass@k": {
+        "1": 35.0,
+        "2": 41.2,
+        "4": 47.5
+    },
+    "time_use_in_second": 160.2115559577942,
+    "time_use_in_minite": "2:40"
+}

eval_results_avg4/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 6.7,
+    "pass_acc": 13.3,
+    "pass@k": {
+        "1": 6.7,
+        "2": 10.0,
+        "4": 13.3
+    },
+    "time_use_in_second": 176.63634634017944,
+    "time_use_in_minite": "2:56"
+}

eval_results_avg4/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 0.8,
+    "pass_acc": 3.3,
+    "pass@k": {
+        "1": 0.8,
+        "2": 1.7,
+        "4": 3.3
+    },
+    "time_use_in_second": 183.75958013534546,
+    "time_use_in_minite": "3:03"
+}

eval_results_avg4/global_step_80/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 40,
+    "num_scores": 160,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 35.0,
+    "pass_acc": 50.0,
+    "pass@k": {
+        "1": 35.0,
+        "2": 42.5,
+        "4": 50.0
+    },
+    "time_use_in_second": 80.48573231697083,
+    "time_use_in_minite": "1:20"
+}

eval_results_avg4/global_step_90/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 12.5,
+    "pass_acc": 23.3,
+    "pass@k": {
+        "1": 12.5,
+        "2": 18.3,
+        "4": 23.3
+    },
+    "time_use_in_second": 164.63086247444153,
+    "time_use_in_minite": "2:44"
+}

eval_results_avg4/global_step_90/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 30,
+    "num_scores": 120,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 2.5,
+    "pass_acc": 6.7,
+    "pass@k": {
+        "1": 2.5,
+        "2": 4.4,
+        "4": 6.7
+    },
+    "time_use_in_second": 187.7517955303192,
+    "time_use_in_minite": "3:07"
+}

eval_results_avg4/global_step_90/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json

@@ -0,0 +1,15 @@
+{
+    "num_samples": 40,
+    "num_scores": 160,
+    "timeout_samples": 0,
+    "empty_samples": 0,
+    "acc": 29.4,
+    "pass_acc": 50.0,
+    "pass@k": {
+        "1": 29.4,
+        "2": 39.6,
+        "4": 50.0
+    },
+    "time_use_in_second": 176.775892496109,
+    "time_use_in_minite": "2:56"
+}

eval_results_merged/merged.csv

@@ -0,0 +1,12 @@
+global_step,aime24_acc_avg4,aime25_acc_avg4,amc23_acc_avg4,aime24_acc,aime25_acc,amc23_acc,gsm8k_acc,math500_acc,minerva_math_acc,olympiadbench_acc,mmlu_stem_acc,prompt_level_strict_acc_ood,gpqa_pass@1:1_samples_ood
+0,5.80,1.70,25.60,0.00,0.00,25.00,59.60,46.00,15.10,16.70,40.00,17.7,0.24
+10,3.30,3.30,30.00,13.30,3.30,22.50,75.40,56.40,21.00,23.10,43.40,19.8,0.27
+20,3.30,2.50,31.90,0.00,0.00,32.50,79.00,60.00,28.70,25.80,47.00,23.7,0.26
+30,8.30,4.20,33.80,6.70,3.30,35.00,79.60,63.20,26.10,25.00,49.10,27.0,0.25
+40,4.20,2.50,31.20,3.30,0.00,45.00,81.20,62.80,26.80,27.90,51.90,27.9,0.31
+50,8.30,0.80,35.00,6.70,0.00,37.50,81.30,63.40,25.70,27.40,52.40,29.0,0.27
+60,10.00,2.50,30.00,6.70,3.30,27.50,82.80,65.80,27.60,28.30,52.60,27.0,0.30
+70,10.80,1.70,35.00,3.30,3.30,32.50,83.20,63.00,27.20,25.20,53.30,29.2,0.26
+80,6.70,0.80,35.00,3.30,3.30,30.00,84.20,64.40,29.00,27.10,55.10,29.2,0.32
+90,12.50,2.50,29.40,3.30,3.30,35.00,83.50,64.20,29.40,28.60,56.70,28.1,0.27
+100,10.00,2.50,28.70,3.30,3.30,37.50,83.30,64.60,26.50,27.90,57.70,30.9,0.29

eval_results_merged_v3/merged.csv

@@ -0,0 +1,12 @@
+global_step,aime24_acc_avg16,aime25_acc_avg16,amc23_acc_avg16,aime24_acc_avg32,aime25_acc_avg32,amc23_acc_avg32,aime24_acc,aime25_acc,amc23_acc,gsm8k_acc,math500_acc,minerva_math_acc,olympiadbench_acc,mmlu_stem_acc,prompt_level_strict_acc_ood,gpqa_pass@1:1_samples_ood
+0,,,,,,,0.00,0.00,25.00,59.60,46.00,15.10,16.70,40.00,17.7,0.24
+10,,,,,,,13.30,3.30,22.50,75.40,56.40,21.00,23.10,43.40,19.8,0.27
+20,,,,,,,0.00,0.00,32.50,79.00,60.00,28.70,25.80,47.00,23.7,0.26
+30,,,,,,,6.70,3.30,35.00,79.60,63.20,26.10,25.00,49.10,27.0,0.25
+40,,,,,,,3.30,0.00,45.00,81.20,62.80,26.80,27.90,51.90,27.9,0.31
+50,,,,,,,6.70,0.00,37.50,81.30,63.40,25.70,27.40,52.40,29.0,0.27
+60,,,,,,,6.70,3.30,27.50,82.80,65.80,27.60,28.30,52.60,27.0,0.30
+70,,,,,,,3.30,3.30,32.50,83.20,63.00,27.20,25.20,53.30,29.2,0.26
+80,,,,,,,3.30,3.30,30.00,84.20,64.40,29.00,27.10,55.10,29.2,0.32
+90,,,,,,,3.30,3.30,35.00,83.50,64.20,29.40,28.60,56.70,28.1,0.27
+100,,,,,,,3.30,3.30,37.50,83.30,64.60,26.50,27.90,57.70,30.9,0.29

eval_results_merged_v3/missing.txt

@@ -0,0 +1,11 @@
+step 0: missing avg16, avg32
+step 10: missing avg16, avg32
+step 20: missing avg16, avg32
+step 30: missing avg16, avg32
+step 40: missing avg16, avg32
+step 50: missing avg16, avg32
+step 60: missing avg16, avg32
+step 70: missing avg16, avg32
+step 80: missing avg16, avg32
+step 90: missing avg16, avg32
+step 100: missing avg16, avg32