Add files using upload-large-folder tool

.gitattributes

@@ -47,3 +47,7 @@ global_step_115/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -
 global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 global_step_55/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_95/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_100/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text

eval_results/global_step_0/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": 20,
+    "acc": 75.7,
+    "pass_acc": 75.7,
+    "pass@k": {
+        "1": 75.7
+    },
+    "time_use_in_second": 125.95953345298767,
+    "time_use_in_minite": "2:05"
+}

eval_results/global_step_0/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": 1,
+    "empty_samples": 9,
+    "acc": 52.2,
+    "pass_acc": 52.2,
+    "pass@k": {
+        "1": 52.2
+    },
+    "time_use_in_second": 94.54320168495178,
+    "time_use_in_minite": "1:34"
+}

eval_results/global_step_0/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": 18,
+    "acc": 20.6,
+    "pass_acc": 20.6,
+    "pass@k": {
+        "1": 20.6
+    },
+    "time_use_in_second": 200.8112862110138,
+    "time_use_in_minite": "3:20"
+}

eval_results/global_step_15/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": 34.98631310462952,
+    "time_use_in_minite": "0:34"
+}

eval_results/global_step_15/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": 52.5,
+    "pass_acc": 52.5,
+    "pass@k": {
+        "1": 52.5
+    },
+    "time_use_in_second": 68.07727694511414,
+    "time_use_in_minite": "1:08"
+}

eval_results/global_step_15/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": 90.2,
+    "pass_acc": 90.2,
+    "pass@k": {
+        "1": 90.2
+    },
+    "time_use_in_second": 63.200294494628906,
+    "time_use_in_minite": "1:03"
+}

eval_results/global_step_15/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": 1,
+    "empty_samples": 1,
+    "acc": 72.4,
+    "pass_acc": 72.4,
+    "pass@k": {
+        "1": 72.4
+    },
+    "time_use_in_second": 57.943002700805664,
+    "time_use_in_minite": "0:57"
+}

eval_results/global_step_15/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": 35.7,
+    "pass_acc": 35.7,
+    "pass@k": {
+        "1": 35.7
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 64.6,
+        "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)": 28.3,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 21.6,
+        "Physical Chemistry (5.61 Fall 2017)": 9.1,
+        "Principles of Microeconomics (14.01 Fall 2011)": 55.6,
+        "Relativity (8.033 Fall 2006)": 36.4
+    },
+    "time_use_in_second": 84.02002787590027,
+    "time_use_in_minite": "1:24"
+}

eval_results/global_step_15/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": 36.3,
+    "pass_acc": 36.3,
+    "pass@k": {
+        "1": 36.3
+    },
+    "time_use_in_second": 138.21381092071533,
+    "time_use_in_minite": "2:18"
+}

eval_results/global_step_25/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": 68.03684830665588,
+    "time_use_in_minite": "1:08"
+}

eval_results/global_step_25/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": 52.5,
+    "pass_acc": 52.5,
+    "pass@k": {
+        "1": 52.5
+    },
+    "time_use_in_second": 30.228216886520386,
+    "time_use_in_minite": "0:30"
+}

eval_results/global_step_25/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": 91.3,
+    "pass_acc": 91.3,
+    "pass@k": {
+        "1": 91.3
+    },
+    "time_use_in_second": 61.750991344451904,
+    "time_use_in_minite": "1:01"
+}

eval_results/global_step_25/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": 73.4,
+    "pass_acc": 73.4,
+    "pass@k": {
+        "1": 73.4
+    },
+    "time_use_in_second": 102.64481163024902,
+    "time_use_in_minite": "1:42"
+}

eval_results/global_step_25/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": 32.7,
+    "pass_acc": 32.7,
+    "pass@k": {
+        "1": 32.7
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 58.3,
+        "Dynamics and Control (2.003 Spring 2005)": 53.8,
+        "Ecology I (1.018J Fall 2009)": 40.0,
+        "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)": 23.7,
+        "Physical Chemistry (5.61 Fall 2017)": 9.1,
+        "Principles of Microeconomics (14.01 Fall 2011)": 55.6,
+        "Relativity (8.033 Fall 2006)": 27.3
+    },
+    "time_use_in_second": 36.20563268661499,
+    "time_use_in_minite": "0:36"
+}

eval_results/global_step_25/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": 38.5,
+    "pass_acc": 38.5,
+    "pass@k": {
+        "1": 38.5
+    },
+    "time_use_in_second": 137.9393606185913,
+    "time_use_in_minite": "2:17"
+}

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": 16.7,
+    "pass_acc": 16.7,
+    "pass@k": {
+        "1": 16.7
+    },
+    "time_use_in_second": 67.79033923149109,
+    "time_use_in_minite": "1:07"
+}

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": 52.5,
+    "pass_acc": 52.5,
+    "pass@k": {
+        "1": 52.5
+    },
+    "time_use_in_second": 22.189570665359497,
+    "time_use_in_minite": "0:22"
+}

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": 89.9,
+    "pass_acc": 89.9,
+    "pass@k": {
+        "1": 89.9
+    },
+    "time_use_in_second": 110.01273012161255,
+    "time_use_in_minite": "1:50"
+}

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": 76.0,
+    "pass_acc": 76.0,
+    "pass@k": {
+        "1": 76.0
+    },
+    "time_use_in_second": 101.99508786201477,
+    "time_use_in_minite": "1:41"
+}

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": 0,
+    "acc": 33.8,
+    "pass_acc": 33.8,
+    "pass@k": {
+        "1": 33.8
+    },
+    "type_acc": {
+        "Differential Equations (18.03 Spring 2010)": 62.5,
+        "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)": 20.8,
+        "Introduction to Solid State Chemistry (3.091 Fall 2010)": 22.7,
+        "Physical Chemistry (5.61 Fall 2017)": 9.1,
+        "Principles of Microeconomics (14.01 Fall 2011)": 50.0,
+        "Relativity (8.033 Fall 2006)": 36.4
+    },
+    "time_use_in_second": 36.29343605041504,
+    "time_use_in_minite": "0:36"
+}

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": 36.6,
+    "pass_acc": 36.6,
+    "pass@k": {
+        "1": 36.6
+    },
+    "time_use_in_second": 140.6587872505188,
+    "time_use_in_minite": "2:20"
+}

eval_results/global_step_35/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": 66.62974858283997,
+    "time_use_in_minite": "1:06"
+}

eval_results/global_step_35/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": 55.0,
+    "pass_acc": 55.0,
+    "pass@k": {
+        "1": 55.0
+    },
+    "time_use_in_second": 19.278455018997192,
+    "time_use_in_minite": "0:19"
+}

eval_results/global_step_35/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": 91.3,
+    "pass_acc": 91.3,
+    "pass@k": {
+        "1": 91.3
+    },
+    "time_use_in_second": 64.08755540847778,
+    "time_use_in_minite": "1:04"
+}