bensondccnqwc commited on
Commit
1cfb291
·
verified ·
1 Parent(s): 4bafbec

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_10/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  2. eval_results/global_step_10/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  3. eval_results/global_step_100/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  4. eval_results/global_step_100/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  5. eval_results/global_step_20/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  6. eval_results/global_step_20/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  7. eval_results/global_step_20/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  8. eval_results/global_step_20/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  9. eval_results/global_step_20/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  10. eval_results/global_step_20/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  11. eval_results/global_step_20/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +24 -0
  12. eval_results/global_step_20/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  13. eval_results/global_step_20/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +33 -0
  14. eval_results/global_step_20/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  15. eval_results/global_step_20/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  16. eval_results/global_step_30/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  17. eval_results/global_step_30/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  18. eval_results/global_step_30/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  19. eval_results/global_step_30/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  20. eval_results/global_step_30/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  21. eval_results/global_step_30/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  22. eval_results/global_step_30/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  23. eval_results/global_step_30/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  24. eval_results/global_step_30/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  25. eval_results/global_step_30/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  26. eval_results/global_step_30/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  27. eval_results/global_step_30/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +24 -0
  28. eval_results/global_step_30/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  29. eval_results/global_step_30/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +33 -0
  30. eval_results/global_step_30/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  31. eval_results/global_step_30/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  32. eval_results/global_step_40/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  33. eval_results/global_step_40/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  34. eval_results/global_step_40/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  35. eval_results/global_step_40/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  36. eval_results/global_step_40/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  37. eval_results/global_step_40/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  38. eval_results/global_step_40/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  39. eval_results/global_step_40/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  40. eval_results/global_step_40/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  41. eval_results/global_step_40/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  42. eval_results/global_step_40/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  43. eval_results/global_step_40/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +24 -0
  44. eval_results/global_step_40/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +33 -0
  45. eval_results/global_step_40/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  46. eval_results/global_step_40/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  47. eval_results/global_step_50/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  48. eval_results/global_step_50/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  49. eval_results/global_step_50/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  50. eval_results/global_step_50/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
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/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/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_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_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/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_20/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": 0,
6
+ "acc": 79.8,
7
+ "pass_acc": 79.8,
8
+ "pass@k": {
9
+ "1": 79.8
10
+ },
11
+ "time_use_in_second": 68.8884105682373,
12
+ "time_use_in_minite": "1:08"
13
+ }
eval_results/global_step_20/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_20/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": 57.4,
7
+ "pass_acc": 57.4,
8
+ "pass@k": {
9
+ "1": 57.4
10
+ },
11
+ "time_use_in_second": 188.7331085205078,
12
+ "time_use_in_minite": "3:08"
13
+ }
eval_results/global_step_20/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_20/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": 0,
5
+ "empty_samples": 0,
6
+ "acc": 24.6,
7
+ "pass_acc": 24.6,
8
+ "pass@k": {
9
+ "1": 24.6
10
+ },
11
+ "type_acc": {
12
+ "Differential Equations (18.03 Spring 2010)": 45.8,
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)": 13.2,
17
+ "Introduction to Solid State Chemistry (3.091 Fall 2010)": 15.5,
18
+ "Physical Chemistry (5.61 Fall 2017)": 9.1,
19
+ "Principles of Microeconomics (14.01 Fall 2011)": 38.9,
20
+ "Relativity (8.033 Fall 2006)": 0.0
21
+ },
22
+ "time_use_in_second": 168.47852659225464,
23
+ "time_use_in_minite": "2:48"
24
+ }
eval_results/global_step_20/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_20/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": 5,
5
+ "empty_samples": 3,
6
+ "acc": 45.9,
7
+ "pass_acc": 45.9,
8
+ "pass@k": {
9
+ "1": 45.9
10
+ },
11
+ "type_acc": {
12
+ "abstract_algebra": 25.0,
13
+ "astronomy": 56.6,
14
+ "college_biology": 64.6,
15
+ "college_chemistry": 49.0,
16
+ "college_computer_science": 39.0,
17
+ "college_mathematics": 29.0,
18
+ "college_physics": 41.2,
19
+ "computer_security": 52.0,
20
+ "conceptual_physics": 56.6,
21
+ "electrical_engineering": 46.9,
22
+ "elementary_mathematics": 41.3,
23
+ "high_school_biology": 64.2,
24
+ "high_school_chemistry": 52.7,
25
+ "high_school_computer_science": 52.0,
26
+ "high_school_mathematics": 14.8,
27
+ "high_school_physics": 43.7,
28
+ "high_school_statistics": 48.1,
29
+ "machine_learning": 39.3
30
+ },
31
+ "time_use_in_second": 429.1207802295685,
32
+ "time_use_in_minite": "7:09"
33
+ }
eval_results/global_step_20/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_20/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": 0,
6
+ "acc": 24.3,
7
+ "pass_acc": 24.3,
8
+ "pass@k": {
9
+ "1": 24.3
10
+ },
11
+ "time_use_in_second": 389.05578565597534,
12
+ "time_use_in_minite": "6:29"
13
+ }
eval_results/global_step_30/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_30/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": 138.837792634964,
12
+ "time_use_in_minite": "2:18"
13
+ }
eval_results/global_step_30/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_30/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": 6.7,
7
+ "pass_acc": 6.7,
8
+ "pass@k": {
9
+ "1": 6.7
10
+ },
11
+ "time_use_in_second": 32.871572732925415,
12
+ "time_use_in_minite": "0:32"
13
+ }
eval_results/global_step_30/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_30/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": 30.0,
7
+ "pass_acc": 30.0,
8
+ "pass@k": {
9
+ "1": 30.0
10
+ },
11
+ "time_use_in_second": 136.81593942642212,
12
+ "time_use_in_minite": "2:16"
13
+ }
eval_results/global_step_30/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_30/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": 0,
6
+ "acc": 80.1,
7
+ "pass_acc": 80.1,
8
+ "pass@k": {
9
+ "1": 80.1
10
+ },
11
+ "time_use_in_second": 194.5436201095581,
12
+ "time_use_in_minite": "3:14"
13
+ }
eval_results/global_step_30/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_30/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": 59.4,
7
+ "pass_acc": 59.4,
8
+ "pass@k": {
9
+ "1": 59.4
10
+ },
11
+ "time_use_in_second": 208.02852749824524,
12
+ "time_use_in_minite": "3:28"
13
+ }
eval_results/global_step_30/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_30/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": 2,
5
+ "empty_samples": 0,
6
+ "acc": 22.1,
7
+ "pass_acc": 22.1,
8
+ "pass@k": {
9
+ "1": 22.1
10
+ },
11
+ "type_acc": {
12
+ "Differential Equations (18.03 Spring 2010)": 45.8,
13
+ "Dynamics and Control (2.003 Spring 2005)": 34.6,
14
+ "Ecology I (1.018J Fall 2009)": 0.0,
15
+ "Information and Entropy (6.050J Spring 2008)": 0.0,
16
+ "Introduction to Astronomy (8.282J Spring 2006)": 11.3,
17
+ "Introduction to Solid State Chemistry (3.091 Fall 2010)": 18.6,
18
+ "Physical Chemistry (5.61 Fall 2017)": 0.0,
19
+ "Principles of Microeconomics (14.01 Fall 2011)": 27.8,
20
+ "Relativity (8.033 Fall 2006)": 0.0
21
+ },
22
+ "time_use_in_second": 167.37208485603333,
23
+ "time_use_in_minite": "2:47"
24
+ }
eval_results/global_step_30/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_30/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": 3,
5
+ "empty_samples": 5,
6
+ "acc": 51.0,
7
+ "pass_acc": 51.0,
8
+ "pass@k": {
9
+ "1": 51.0
10
+ },
11
+ "type_acc": {
12
+ "abstract_algebra": 38.0,
13
+ "astronomy": 63.8,
14
+ "college_biology": 62.5,
15
+ "college_chemistry": 44.0,
16
+ "college_computer_science": 44.0,
17
+ "college_mathematics": 31.0,
18
+ "college_physics": 50.0,
19
+ "computer_security": 46.0,
20
+ "conceptual_physics": 60.0,
21
+ "electrical_engineering": 53.8,
22
+ "elementary_mathematics": 48.9,
23
+ "high_school_biology": 66.8,
24
+ "high_school_chemistry": 53.7,
25
+ "high_school_computer_science": 61.0,
26
+ "high_school_mathematics": 26.3,
27
+ "high_school_physics": 45.7,
28
+ "high_school_statistics": 58.8,
29
+ "machine_learning": 44.6
30
+ },
31
+ "time_use_in_second": 478.0683960914612,
32
+ "time_use_in_minite": "7:58"
33
+ }
eval_results/global_step_30/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_30/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": 0,
6
+ "acc": 27.3,
7
+ "pass_acc": 27.3,
8
+ "pass@k": {
9
+ "1": 27.3
10
+ },
11
+ "time_use_in_second": 371.59140634536743,
12
+ "time_use_in_minite": "6:11"
13
+ }
eval_results/global_step_40/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_40/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": 154.73073053359985,
12
+ "time_use_in_minite": "2:34"
13
+ }
eval_results/global_step_40/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_40/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": 0.0,
7
+ "pass_acc": 0.0,
8
+ "pass@k": {
9
+ "1": 0.0
10
+ },
11
+ "time_use_in_second": 150.83997917175293,
12
+ "time_use_in_minite": "2:30"
13
+ }
eval_results/global_step_40/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_40/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": 27.5,
7
+ "pass_acc": 27.5,
8
+ "pass@k": {
9
+ "1": 27.5
10
+ },
11
+ "time_use_in_second": 152.0974292755127,
12
+ "time_use_in_minite": "2:32"
13
+ }
eval_results/global_step_40/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_40/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": 0,
6
+ "acc": 81.3,
7
+ "pass_acc": 81.3,
8
+ "pass@k": {
9
+ "1": 81.3
10
+ },
11
+ "time_use_in_second": 190.61600041389465,
12
+ "time_use_in_minite": "3:10"
13
+ }
eval_results/global_step_40/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_40/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": 64.8,
7
+ "pass_acc": 64.8,
8
+ "pass@k": {
9
+ "1": 64.8
10
+ },
11
+ "time_use_in_second": 218.48642587661743,
12
+ "time_use_in_minite": "3:38"
13
+ }
eval_results/global_step_40/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_40/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": 27.2,
7
+ "pass_acc": 27.2,
8
+ "pass@k": {
9
+ "1": 27.2
10
+ },
11
+ "type_acc": {
12
+ "Differential Equations (18.03 Spring 2010)": 54.2,
13
+ "Dynamics and Control (2.003 Spring 2005)": 46.2,
14
+ "Ecology I (1.018J Fall 2009)": 20.0,
15
+ "Information and Entropy (6.050J Spring 2008)": 0.0,
16
+ "Introduction to Astronomy (8.282J Spring 2006)": 13.2,
17
+ "Introduction to Solid State Chemistry (3.091 Fall 2010)": 17.5,
18
+ "Physical Chemistry (5.61 Fall 2017)": 9.1,
19
+ "Principles of Microeconomics (14.01 Fall 2011)": 55.6,
20
+ "Relativity (8.033 Fall 2006)": 0.0
21
+ },
22
+ "time_use_in_second": 177.72079944610596,
23
+ "time_use_in_minite": "2:57"
24
+ }
eval_results/global_step_40/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": 3,
5
+ "empty_samples": 2,
6
+ "acc": 54.8,
7
+ "pass_acc": 54.8,
8
+ "pass@k": {
9
+ "1": 54.8
10
+ },
11
+ "type_acc": {
12
+ "abstract_algebra": 44.0,
13
+ "astronomy": 67.8,
14
+ "college_biology": 61.8,
15
+ "college_chemistry": 51.0,
16
+ "college_computer_science": 53.0,
17
+ "college_mathematics": 38.0,
18
+ "college_physics": 52.9,
19
+ "computer_security": 58.0,
20
+ "conceptual_physics": 57.0,
21
+ "electrical_engineering": 61.4,
22
+ "elementary_mathematics": 56.9,
23
+ "high_school_biology": 68.7,
24
+ "high_school_chemistry": 56.7,
25
+ "high_school_computer_science": 71.0,
26
+ "high_school_mathematics": 30.4,
27
+ "high_school_physics": 51.0,
28
+ "high_school_statistics": 51.9,
29
+ "machine_learning": 49.1
30
+ },
31
+ "time_use_in_second": 406.9477262496948,
32
+ "time_use_in_minite": "6:46"
33
+ }
eval_results/global_step_40/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_40/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": 0,
6
+ "acc": 28.6,
7
+ "pass_acc": 28.6,
8
+ "pass@k": {
9
+ "1": 28.6
10
+ },
11
+ "time_use_in_second": 448.2467827796936,
12
+ "time_use_in_minite": "7:28"
13
+ }
eval_results/global_step_50/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_50/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": 3.3,
7
+ "pass_acc": 3.3,
8
+ "pass@k": {
9
+ "1": 3.3
10
+ },
11
+ "time_use_in_second": 140.95101380348206,
12
+ "time_use_in_minite": "2:20"
13
+ }
eval_results/global_step_50/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_50/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": 3.3,
7
+ "pass_acc": 3.3,
8
+ "pass@k": {
9
+ "1": 3.3
10
+ },
11
+ "time_use_in_second": 134.8092610836029,
12
+ "time_use_in_minite": "2:14"
13
+ }