johndoe123345 commited on
Commit
fb24969
·
verified ·
1 Parent(s): 274ea97

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. eval_results/global_step_0/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  2. eval_results/global_step_0/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  3. eval_results/global_step_0/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  4. eval_results/global_step_0/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  5. eval_results/global_step_0/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  6. eval_results/global_step_0/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  7. eval_results/global_step_0/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  8. eval_results/global_step_0/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  9. eval_results/global_step_0/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  10. eval_results/global_step_0/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  11. eval_results/global_step_0/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  12. eval_results/global_step_0/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +24 -0
  13. eval_results/global_step_0/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  14. eval_results/global_step_0/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +33 -0
  15. eval_results/global_step_0/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  16. eval_results/global_step_0/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  17. eval_results/global_step_10/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  18. eval_results/global_step_10/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  19. eval_results/global_step_10/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  20. eval_results/global_step_10/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  21. eval_results/global_step_10/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  22. eval_results/global_step_10/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  23. eval_results/global_step_10/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  24. eval_results/global_step_10/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  25. eval_results/global_step_10/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  26. eval_results/global_step_10/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  27. eval_results/global_step_10/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +33 -0
  28. eval_results/global_step_10/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  29. eval_results/global_step_10/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  30. eval_results/global_step_100/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  31. eval_results/global_step_100/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  32. eval_results/global_step_100/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  33. eval_results/global_step_100/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  34. eval_results/global_step_100/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  35. eval_results/global_step_100/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  36. eval_results/global_step_100/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  37. eval_results/global_step_100/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  38. eval_results/global_step_100/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  39. eval_results/global_step_100/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  40. eval_results/global_step_100/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  41. eval_results/global_step_100/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +24 -0
  42. eval_results/global_step_100/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +33 -0
  43. eval_results/global_step_100/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  44. eval_results/global_step_100/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  45. eval_results/global_step_20/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  46. eval_results/global_step_20/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  47. eval_results/global_step_20/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  48. eval_results/global_step_20/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  49. eval_results/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  50. eval_results/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
eval_results/global_step_0/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_0/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 6.7,
7
+ "pass_acc": 6.7,
8
+ "pass@k": {
9
+ "1": 6.7
10
+ },
11
+ "time_use_in_second": 218.54596161842346,
12
+ "time_use_in_minite": "3:38"
13
+ }
eval_results/global_step_0/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_0/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 13.3,
7
+ "pass_acc": 13.3,
8
+ "pass@k": {
9
+ "1": 13.3
10
+ },
11
+ "time_use_in_second": 210.55786085128784,
12
+ "time_use_in_minite": "3:30"
13
+ }
eval_results/global_step_0/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_0/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 40,
3
+ "num_scores": 40,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 45.0,
7
+ "pass_acc": 45.0,
8
+ "pass@k": {
9
+ "1": 45.0
10
+ },
11
+ "time_use_in_second": 56.58969306945801,
12
+ "time_use_in_minite": "0:56"
13
+ }
eval_results/global_step_0/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_0/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 1319,
3
+ "num_scores": 1319,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 15,
6
+ "acc": 84.3,
7
+ "pass_acc": 84.3,
8
+ "pass@k": {
9
+ "1": 84.3
10
+ },
11
+ "time_use_in_second": 335.95774841308594,
12
+ "time_use_in_minite": "5:35"
13
+ }
eval_results/global_step_0/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_0/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 500,
3
+ "num_scores": 500,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 9,
6
+ "acc": 65.4,
7
+ "pass_acc": 65.4,
8
+ "pass@k": {
9
+ "1": 65.4
10
+ },
11
+ "time_use_in_second": 380.1704812049866,
12
+ "time_use_in_minite": "6:20"
13
+ }
eval_results/global_step_0/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_0/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 272,
3
+ "num_scores": 272,
4
+ "timeout_samples": 1,
5
+ "empty_samples": 14,
6
+ "acc": 26.1,
7
+ "pass_acc": 26.1,
8
+ "pass@k": {
9
+ "1": 26.1
10
+ },
11
+ "type_acc": {
12
+ "Differential Equations (18.03 Spring 2010)": 35.4,
13
+ "Dynamics and Control (2.003 Spring 2005)": 38.5,
14
+ "Ecology I (1.018J Fall 2009)": 40.0,
15
+ "Information and Entropy (6.050J Spring 2008)": 66.7,
16
+ "Introduction to Astronomy (8.282J Spring 2006)": 20.8,
17
+ "Introduction to Solid State Chemistry (3.091 Fall 2010)": 16.5,
18
+ "Physical Chemistry (5.61 Fall 2017)": 18.2,
19
+ "Principles of Microeconomics (14.01 Fall 2011)": 44.4,
20
+ "Relativity (8.033 Fall 2006)": 27.3
21
+ },
22
+ "time_use_in_second": 243.3234167098999,
23
+ "time_use_in_minite": "4:03"
24
+ }
eval_results/global_step_0/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_0/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 3018,
3
+ "num_scores": 3018,
4
+ "timeout_samples": 8,
5
+ "empty_samples": 11,
6
+ "acc": 60.7,
7
+ "pass_acc": 60.7,
8
+ "pass@k": {
9
+ "1": 60.7
10
+ },
11
+ "type_acc": {
12
+ "abstract_algebra": 53.0,
13
+ "astronomy": 78.9,
14
+ "college_biology": 80.6,
15
+ "college_chemistry": 49.0,
16
+ "college_computer_science": 52.0,
17
+ "college_mathematics": 43.0,
18
+ "college_physics": 56.9,
19
+ "computer_security": 65.0,
20
+ "conceptual_physics": 74.5,
21
+ "electrical_engineering": 64.1,
22
+ "elementary_mathematics": 52.1,
23
+ "high_school_biology": 75.8,
24
+ "high_school_chemistry": 63.5,
25
+ "high_school_computer_science": 75.0,
26
+ "high_school_mathematics": 29.3,
27
+ "high_school_physics": 55.6,
28
+ "high_school_statistics": 63.0,
29
+ "machine_learning": 66.1
30
+ },
31
+ "time_use_in_second": 614.4746489524841,
32
+ "time_use_in_minite": "10:14"
33
+ }
eval_results/global_step_0/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_0/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 675,
3
+ "num_scores": 675,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 9,
6
+ "acc": 31.1,
7
+ "pass_acc": 31.1,
8
+ "pass@k": {
9
+ "1": 31.1
10
+ },
11
+ "time_use_in_second": 503.0589566230774,
12
+ "time_use_in_minite": "8:23"
13
+ }
eval_results/global_step_10/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_10/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 16.7,
7
+ "pass_acc": 16.7,
8
+ "pass@k": {
9
+ "1": 16.7
10
+ },
11
+ "time_use_in_second": 241.16228032112122,
12
+ "time_use_in_minite": "4:01"
13
+ }
eval_results/global_step_10/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_10/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 16.7,
7
+ "pass_acc": 16.7,
8
+ "pass@k": {
9
+ "1": 16.7
10
+ },
11
+ "time_use_in_second": 229.15140557289124,
12
+ "time_use_in_minite": "3:49"
13
+ }
eval_results/global_step_10/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_10/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_10/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 1319,
3
+ "num_scores": 1319,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 1,
6
+ "acc": 91.8,
7
+ "pass_acc": 91.8,
8
+ "pass@k": {
9
+ "1": 91.8
10
+ },
11
+ "time_use_in_second": 273.5060772895813,
12
+ "time_use_in_minite": "4:33"
13
+ }
eval_results/global_step_10/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_10/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 500,
3
+ "num_scores": 500,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 1,
6
+ "acc": 79.2,
7
+ "pass_acc": 79.2,
8
+ "pass@k": {
9
+ "1": 79.2
10
+ },
11
+ "time_use_in_second": 349.78808665275574,
12
+ "time_use_in_minite": "5:49"
13
+ }
eval_results/global_step_10/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_10/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 3018,
3
+ "num_scores": 3018,
4
+ "timeout_samples": 2,
5
+ "empty_samples": 2,
6
+ "acc": 64.5,
7
+ "pass_acc": 64.5,
8
+ "pass@k": {
9
+ "1": 64.5
10
+ },
11
+ "type_acc": {
12
+ "abstract_algebra": 63.0,
13
+ "astronomy": 81.6,
14
+ "college_biology": 81.9,
15
+ "college_chemistry": 58.0,
16
+ "college_computer_science": 64.0,
17
+ "college_mathematics": 53.0,
18
+ "college_physics": 51.0,
19
+ "computer_security": 57.0,
20
+ "conceptual_physics": 76.2,
21
+ "electrical_engineering": 67.6,
22
+ "elementary_mathematics": 53.7,
23
+ "high_school_biology": 86.5,
24
+ "high_school_chemistry": 72.4,
25
+ "high_school_computer_science": 68.0,
26
+ "high_school_mathematics": 30.0,
27
+ "high_school_physics": 64.2,
28
+ "high_school_statistics": 67.1,
29
+ "machine_learning": 65.2
30
+ },
31
+ "time_use_in_second": 605.1673429012299,
32
+ "time_use_in_minite": "10:05"
33
+ }
eval_results/global_step_10/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_10/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 675,
3
+ "num_scores": 675,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 1,
6
+ "acc": 43.6,
7
+ "pass_acc": 43.6,
8
+ "pass@k": {
9
+ "1": 43.6
10
+ },
11
+ "time_use_in_second": 614.8699924945831,
12
+ "time_use_in_minite": "10:14"
13
+ }
eval_results/global_step_100/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_100/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 13.3,
7
+ "pass_acc": 13.3,
8
+ "pass@k": {
9
+ "1": 13.3
10
+ },
11
+ "time_use_in_second": 299.66179943084717,
12
+ "time_use_in_minite": "4:59"
13
+ }
eval_results/global_step_100/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_100/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 26.7,
7
+ "pass_acc": 26.7,
8
+ "pass@k": {
9
+ "1": 26.7
10
+ },
11
+ "time_use_in_second": 270.207879781723,
12
+ "time_use_in_minite": "4:30"
13
+ }
eval_results/global_step_100/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_100/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 40,
3
+ "num_scores": 40,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 67.5,
7
+ "pass_acc": 67.5,
8
+ "pass@k": {
9
+ "1": 67.5
10
+ },
11
+ "time_use_in_second": 255.5747799873352,
12
+ "time_use_in_minite": "4:15"
13
+ }
eval_results/global_step_100/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_100/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 1319,
3
+ "num_scores": 1319,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 1,
6
+ "acc": 93.6,
7
+ "pass_acc": 93.6,
8
+ "pass@k": {
9
+ "1": 93.6
10
+ },
11
+ "time_use_in_second": 295.32457733154297,
12
+ "time_use_in_minite": "4:55"
13
+ }
eval_results/global_step_100/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_100/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 500,
3
+ "num_scores": 500,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 86.0,
7
+ "pass_acc": 86.0,
8
+ "pass@k": {
9
+ "1": 86.0
10
+ },
11
+ "time_use_in_second": 437.3554677963257,
12
+ "time_use_in_minite": "7:17"
13
+ }
eval_results/global_step_100/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_100/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 272,
3
+ "num_scores": 272,
4
+ "timeout_samples": 1,
5
+ "empty_samples": 0,
6
+ "acc": 37.9,
7
+ "pass_acc": 37.9,
8
+ "pass@k": {
9
+ "1": 37.9
10
+ },
11
+ "type_acc": {
12
+ "Differential Equations (18.03 Spring 2010)": 62.5,
13
+ "Dynamics and Control (2.003 Spring 2005)": 46.2,
14
+ "Ecology I (1.018J Fall 2009)": 40.0,
15
+ "Information and Entropy (6.050J Spring 2008)": 33.3,
16
+ "Introduction to Astronomy (8.282J Spring 2006)": 32.1,
17
+ "Introduction to Solid State Chemistry (3.091 Fall 2010)": 22.7,
18
+ "Physical Chemistry (5.61 Fall 2017)": 18.2,
19
+ "Principles of Microeconomics (14.01 Fall 2011)": 61.1,
20
+ "Relativity (8.033 Fall 2006)": 54.5
21
+ },
22
+ "time_use_in_second": 277.40999937057495,
23
+ "time_use_in_minite": "4:37"
24
+ }
eval_results/global_step_100/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 3018,
3
+ "num_scores": 3018,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 77.6,
7
+ "pass_acc": 77.6,
8
+ "pass@k": {
9
+ "1": 77.6
10
+ },
11
+ "type_acc": {
12
+ "abstract_algebra": 78.0,
13
+ "astronomy": 80.3,
14
+ "college_biology": 88.2,
15
+ "college_chemistry": 60.0,
16
+ "college_computer_science": 77.0,
17
+ "college_mathematics": 74.0,
18
+ "college_physics": 72.5,
19
+ "computer_security": 58.0,
20
+ "conceptual_physics": 83.0,
21
+ "electrical_engineering": 70.3,
22
+ "elementary_mathematics": 82.5,
23
+ "high_school_biology": 88.7,
24
+ "high_school_chemistry": 79.8,
25
+ "high_school_computer_science": 75.0,
26
+ "high_school_mathematics": 74.8,
27
+ "high_school_physics": 75.5,
28
+ "high_school_statistics": 75.0,
29
+ "machine_learning": 65.2
30
+ },
31
+ "time_use_in_second": 930.7638278007507,
32
+ "time_use_in_minite": "15:30"
33
+ }
eval_results/global_step_100/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_100/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 675,
3
+ "num_scores": 675,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 1,
6
+ "acc": 50.4,
7
+ "pass_acc": 50.4,
8
+ "pass@k": {
9
+ "1": 50.4
10
+ },
11
+ "time_use_in_second": 1464.0274574756622,
12
+ "time_use_in_minite": "24:24"
13
+ }
eval_results/global_step_20/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_20/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 13.3,
7
+ "pass_acc": 13.3,
8
+ "pass@k": {
9
+ "1": 13.3
10
+ },
11
+ "time_use_in_second": 313.1780161857605,
12
+ "time_use_in_minite": "5:13"
13
+ }
eval_results/global_step_20/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_20/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 30,
3
+ "num_scores": 30,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 23.3,
7
+ "pass_acc": 23.3,
8
+ "pass@k": {
9
+ "1": 23.3
10
+ },
11
+ "time_use_in_second": 267.39144802093506,
12
+ "time_use_in_minite": "4:27"
13
+ }
eval_results/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
eval_results/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "num_samples": 40,
3
+ "num_scores": 40,
4
+ "timeout_samples": 0,
5
+ "empty_samples": 0,
6
+ "acc": 62.5,
7
+ "pass_acc": 62.5,
8
+ "pass@k": {
9
+ "1": 62.5
10
+ },
11
+ "time_use_in_second": 253.86100006103516,
12
+ "time_use_in_minite": "4:13"
13
+ }