bensondccnqwc commited on
Commit
4041846
·
verified ·
1 Parent(s): 47dd5aa

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_50/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  2. eval_results/global_step_60/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  3. eval_results/global_step_60/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  4. eval_results/global_step_60/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  5. eval_results/global_step_60/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  6. eval_results/global_step_70/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  7. eval_results/global_step_70/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  8. eval_results/global_step_70/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  9. eval_results/global_step_70/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  10. eval_results/global_step_70/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  11. eval_results/global_step_70/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  12. eval_results/global_step_70/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  13. eval_results/global_step_70/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  14. eval_results/global_step_70/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  15. eval_results/global_step_70/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  16. eval_results/global_step_70/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  17. eval_results/global_step_70/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +24 -0
  18. eval_results/global_step_70/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  19. eval_results/global_step_70/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +33 -0
  20. eval_results/global_step_70/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  21. eval_results/global_step_70/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  22. eval_results/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  23. eval_results/global_step_80/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  24. eval_results/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  25. eval_results/global_step_80/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  26. eval_results/global_step_80/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  27. eval_results/global_step_80/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  28. eval_results/global_step_80/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  29. eval_results/global_step_80/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  30. eval_results/global_step_80/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  31. eval_results/global_step_80/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  32. eval_results/global_step_80/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  33. eval_results/global_step_80/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +24 -0
  34. eval_results/global_step_80/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  35. eval_results/global_step_80/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +33 -0
  36. eval_results/global_step_80/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  37. eval_results/global_step_80/olympiadbench/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  38. eval_results/global_step_90/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  39. eval_results/global_step_90/aime24/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  40. eval_results/global_step_90/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  41. eval_results/global_step_90/aime25/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  42. eval_results/global_step_90/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  43. eval_results/global_step_90/amc23/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  44. eval_results/global_step_90/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  45. eval_results/global_step_90/gsm8k/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  46. eval_results/global_step_90/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  47. eval_results/global_step_90/math500/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +13 -0
  48. eval_results/global_step_90/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
  49. eval_results/global_step_90/minerva_math/test_qwen-boxed_-1_seed0_t1.0_s0_e-1_metrics.json +24 -0
  50. eval_results/global_step_90/mmlu_stem/test_qwen-boxed_-1_seed0_t1.0_s0_e-1.jsonl +0 -0
eval_results/global_step_50/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_60/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_60/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_60/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_60/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_70/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_70/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": 132.74381375312805,
12
+ "time_use_in_minite": "2:12"
13
+ }
eval_results/global_step_70/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_70/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": 148.28162598609924,
12
+ "time_use_in_minite": "2:28"
13
+ }
eval_results/global_step_70/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_70/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": 40.0,
7
+ "pass_acc": 40.0,
8
+ "pass@k": {
9
+ "1": 40.0
10
+ },
11
+ "time_use_in_second": 19.03610849380493,
12
+ "time_use_in_minite": "0:19"
13
+ }
eval_results/global_step_70/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_70/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": 81.0,
7
+ "pass_acc": 81.0,
8
+ "pass@k": {
9
+ "1": 81.0
10
+ },
11
+ "time_use_in_second": 210.9955632686615,
12
+ "time_use_in_minite": "3:30"
13
+ }
eval_results/global_step_70/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_70/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": 63.8,
7
+ "pass_acc": 63.8,
8
+ "pass@k": {
9
+ "1": 63.8
10
+ },
11
+ "time_use_in_second": 217.75754499435425,
12
+ "time_use_in_minite": "3:37"
13
+ }
eval_results/global_step_70/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_70/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": 28.7,
7
+ "pass_acc": 28.7,
8
+ "pass@k": {
9
+ "1": 28.7
10
+ },
11
+ "type_acc": {
12
+ "Differential Equations (18.03 Spring 2010)": 45.8,
13
+ "Dynamics and Control (2.003 Spring 2005)": 50.0,
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)": 19.6,
18
+ "Physical Chemistry (5.61 Fall 2017)": 18.2,
19
+ "Principles of Microeconomics (14.01 Fall 2011)": 55.6,
20
+ "Relativity (8.033 Fall 2006)": 18.2
21
+ },
22
+ "time_use_in_second": 66.88714957237244,
23
+ "time_use_in_minite": "1:06"
24
+ }
eval_results/global_step_70/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_70/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": 1,
6
+ "acc": 57.0,
7
+ "pass_acc": 57.0,
8
+ "pass@k": {
9
+ "1": 57.0
10
+ },
11
+ "type_acc": {
12
+ "abstract_algebra": 47.0,
13
+ "astronomy": 63.8,
14
+ "college_biology": 64.6,
15
+ "college_chemistry": 48.0,
16
+ "college_computer_science": 53.0,
17
+ "college_mathematics": 42.0,
18
+ "college_physics": 50.0,
19
+ "computer_security": 54.0,
20
+ "conceptual_physics": 63.4,
21
+ "electrical_engineering": 60.7,
22
+ "elementary_mathematics": 69.3,
23
+ "high_school_biology": 65.8,
24
+ "high_school_chemistry": 55.2,
25
+ "high_school_computer_science": 72.0,
26
+ "high_school_mathematics": 34.4,
27
+ "high_school_physics": 56.3,
28
+ "high_school_statistics": 51.4,
29
+ "machine_learning": 51.8
30
+ },
31
+ "time_use_in_second": 400.7698700428009,
32
+ "time_use_in_minite": "6:40"
33
+ }
eval_results/global_step_70/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_70/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": 28.3,
7
+ "pass_acc": 28.3,
8
+ "pass@k": {
9
+ "1": 28.3
10
+ },
11
+ "time_use_in_second": 370.0450277328491,
12
+ "time_use_in_minite": "6:10"
13
+ }
eval_results/global_step_80/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_80/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": 161.716717004776,
12
+ "time_use_in_minite": "2:41"
13
+ }
eval_results/global_step_80/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_80/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": 41.25397300720215,
12
+ "time_use_in_minite": "0:41"
13
+ }
eval_results/global_step_80/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_80/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": 14.606422662734985,
12
+ "time_use_in_minite": "0:14"
13
+ }
eval_results/global_step_80/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_80/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": 81.9,
7
+ "pass_acc": 81.9,
8
+ "pass@k": {
9
+ "1": 81.9
10
+ },
11
+ "time_use_in_second": 211.34290099143982,
12
+ "time_use_in_minite": "3:31"
13
+ }
eval_results/global_step_80/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_80/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": 64.4,
7
+ "pass_acc": 64.4,
8
+ "pass@k": {
9
+ "1": 64.4
10
+ },
11
+ "time_use_in_second": 190.35562467575073,
12
+ "time_use_in_minite": "3:10"
13
+ }
eval_results/global_step_80/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_80/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": 28.3,
7
+ "pass_acc": 28.3,
8
+ "pass@k": {
9
+ "1": 28.3
10
+ },
11
+ "type_acc": {
12
+ "Differential Equations (18.03 Spring 2010)": 56.2,
13
+ "Dynamics and Control (2.003 Spring 2005)": 50.0,
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)": 17.5,
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)": 18.2
21
+ },
22
+ "time_use_in_second": 107.61190485954285,
23
+ "time_use_in_minite": "1:47"
24
+ }
eval_results/global_step_80/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_80/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": 1,
6
+ "acc": 59.0,
7
+ "pass_acc": 59.0,
8
+ "pass@k": {
9
+ "1": 59.0
10
+ },
11
+ "type_acc": {
12
+ "abstract_algebra": 47.0,
13
+ "astronomy": 63.8,
14
+ "college_biology": 62.5,
15
+ "college_chemistry": 45.0,
16
+ "college_computer_science": 60.0,
17
+ "college_mathematics": 43.0,
18
+ "college_physics": 52.9,
19
+ "computer_security": 59.0,
20
+ "conceptual_physics": 64.3,
21
+ "electrical_engineering": 55.2,
22
+ "elementary_mathematics": 72.8,
23
+ "high_school_biology": 70.6,
24
+ "high_school_chemistry": 59.6,
25
+ "high_school_computer_science": 71.0,
26
+ "high_school_mathematics": 37.8,
27
+ "high_school_physics": 55.6,
28
+ "high_school_statistics": 58.8,
29
+ "machine_learning": 50.9
30
+ },
31
+ "time_use_in_second": 376.31753158569336,
32
+ "time_use_in_minite": "6:16"
33
+ }
eval_results/global_step_80/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_80/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": 28.9,
7
+ "pass_acc": 28.9,
8
+ "pass@k": {
9
+ "1": 28.9
10
+ },
11
+ "time_use_in_second": 333.0325434207916,
12
+ "time_use_in_minite": "5:33"
13
+ }
eval_results/global_step_90/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_90/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": 149.4713592529297,
12
+ "time_use_in_minite": "2:29"
13
+ }
eval_results/global_step_90/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_90/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": 135.20457649230957,
12
+ "time_use_in_minite": "2:15"
13
+ }
eval_results/global_step_90/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_90/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": 37.5,
7
+ "pass_acc": 37.5,
8
+ "pass@k": {
9
+ "1": 37.5
10
+ },
11
+ "time_use_in_second": 18.216927528381348,
12
+ "time_use_in_minite": "0:18"
13
+ }
eval_results/global_step_90/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_90/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": 81.4,
7
+ "pass_acc": 81.4,
8
+ "pass@k": {
9
+ "1": 81.4
10
+ },
11
+ "time_use_in_second": 189.12426161766052,
12
+ "time_use_in_minite": "3:09"
13
+ }
eval_results/global_step_90/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_90/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": 66.4,
7
+ "pass_acc": 66.4,
8
+ "pass@k": {
9
+ "1": 66.4
10
+ },
11
+ "time_use_in_second": 198.44291973114014,
12
+ "time_use_in_minite": "3:18"
13
+ }
eval_results/global_step_90/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_90/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": 28.7,
7
+ "pass_acc": 28.7,
8
+ "pass@k": {
9
+ "1": 28.7
10
+ },
11
+ "type_acc": {
12
+ "Differential Equations (18.03 Spring 2010)": 56.2,
13
+ "Dynamics and Control (2.003 Spring 2005)": 42.3,
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)": 11.3,
17
+ "Introduction to Solid State Chemistry (3.091 Fall 2010)": 20.6,
18
+ "Physical Chemistry (5.61 Fall 2017)": 0.0,
19
+ "Principles of Microeconomics (14.01 Fall 2011)": 55.6,
20
+ "Relativity (8.033 Fall 2006)": 9.1
21
+ },
22
+ "time_use_in_second": 153.03648972511292,
23
+ "time_use_in_minite": "2:33"
24
+ }
eval_results/global_step_90/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