categories rename
Browse files- logs/guardbench_20250331_202524_f070fad2.log +0 -19
- logs/guardbench_20250331_203348_6e24b81a.log +0 -19
- logs/guardbench_20250331_204307_8d77ec17.log +0 -23
- logs/guardbench_20250331_204836_3421e73f.log +0 -16
- logs/guardbench_20250331_205152_1140353b.log +0 -19
- logs/guardbench_20250331_205420_d59a424e.log +0 -61
- logs/guardbench_20250331_205853_bf4fa85f.log +0 -2
- logs/guardbench_20250331_210025_ba691e37.log +0 -2
- logs/guardbench_20250331_210109_f46123b9.log +0 -2
- logs/guardbench_20250331_210119_f0e10b9b.log +0 -2
- logs/guardbench_20250331_210208_029d8318.log +0 -2
- logs/guardbench_20250331_210459_437adc64.log +0 -2
- logs/guardbench_20250331_210550_0358568e.log +0 -2
- logs/guardbench_20250331_210641_91d1d06b.log +0 -2
- logs/guardbench_20250331_210920_cd35c4f0.log +0 -2
- logs/guardbench_20250331_211215_a8cf06a3.log +0 -2
- logs/guardbench_20250331_211255_d32ee1a4.log +0 -2
- logs/guardbench_20250331_211332_24223f1a.log +0 -2
- logs/guardbench_20250331_211545_244674df.log +0 -2
- logs/guardbench_20250331_211735_6d503239.log +0 -2
- logs/guardbench_20250331_211916_3e96de42.log +0 -2
- logs/guardbench_20250331_212027_f9d450e9.log +0 -5
- logs/guardbench_20250331_212722_655f3190.log +0 -2
- logs/guardbench_20250331_213207_74f9e2de.log +0 -5
- logs/guardbench_20250331_213331_f72d2f6a.log +0 -5
- logs/guardbench_20250331_214118_0da0491f.log +0 -50
- logs/guardbench_20250331_214511_0a5acf8b.log +0 -5
- logs/guardbench_20250331_214841_4df080f3.log +0 -5
- logs/guardbench_20250331_215007_9c98c60a.log +0 -5
- logs/guardbench_20250331_215514_ad36e4b4.log +0 -50
- logs/guardbench_20250331_220348_0cb4d8e9.log +0 -50
- logs/guardbench_20250331_220638_21aa20f2.log +0 -50
- logs/guardbench_20250331_221124_3ffa908f.log +0 -50
- logs/guardbench_20250331_221755_fc667123.log +0 -50
- logs/guardbench_20250331_222103_90a3095d.log +0 -50
- logs/guardbench_20250331_222531_b0fff871.log +0 -50
- logs/guardbench_20250331_223148_4e22eb66.log +0 -50
- logs/guardbench_20250424_132721_81730502.log +0 -2
- logs/guardbench_20250424_132735_5fe7accd.log +0 -2
- logs/guardbench_20250424_133606_bfae8d28.log +0 -2
- logs/guardbench_20250424_133744_d3ca5956.log +0 -2
- logs/guardbench_20250424_133847_cf6f7f0f.log +0 -2
- logs/guardbench_20250424_133952_920f4d61.log +0 -2
- logs/guardbench_20250424_134044_2df3fadc.log +0 -17
logs/guardbench_20250331_202524_f070fad2.log
DELETED
@@ -1,19 +0,0 @@
|
|
1 |
-
2025-03-31 20:25:27,855 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 20:25:28,116 - __main__ - INFO - Loaded leaderboard with 0 entries
|
3 |
-
2025-03-31 20:25:28,184 - __main__ - WARNING - Initializing empty leaderboard
|
4 |
-
2025-03-31 20:25:28,348 - __main__ - WARNING - Initializing empty leaderboard
|
5 |
-
2025-03-31 20:25:28,514 - __main__ - WARNING - Initializing empty leaderboard
|
6 |
-
2025-03-31 20:25:28,624 - __main__ - WARNING - Initializing empty leaderboard
|
7 |
-
2025-03-31 20:25:28,739 - __main__ - WARNING - Initializing empty leaderboard
|
8 |
-
2025-03-31 20:25:28,869 - __main__ - WARNING - Initializing empty leaderboard
|
9 |
-
2025-03-31 20:25:29,008 - __main__ - WARNING - Initializing empty leaderboard
|
10 |
-
2025-03-31 20:25:29,568 - __main__ - WARNING - Initializing empty leaderboard
|
11 |
-
2025-03-31 20:25:29,687 - __main__ - WARNING - Initializing empty leaderboard
|
12 |
-
2025-03-31 20:25:29,796 - __main__ - WARNING - Initializing empty leaderboard
|
13 |
-
2025-03-31 20:25:29,908 - __main__ - WARNING - Initializing empty leaderboard
|
14 |
-
2025-03-31 20:25:30,148 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
15 |
-
2025-03-31 20:25:30,148 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
16 |
-
2025-03-31 20:25:30,148 - apscheduler.scheduler - INFO - Scheduler started
|
17 |
-
2025-03-31 20:29:44,676 - __main__ - INFO - Received submission for model chatgpt-4o-latest (CoT): /tmp/gradio/a1f2d3a725f7b441a1fbfdac8e51dfd3bf7bbb4ab2d1c20362cfa130f4bdda6d/chatgpt-4o-latest CoT.jsonl
|
18 |
-
2025-03-31 20:29:44,708 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
19 |
-
2025-03-31 20:29:44,923 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_203348_6e24b81a.log
DELETED
@@ -1,19 +0,0 @@
|
|
1 |
-
2025-03-31 20:33:49,499 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 20:33:49,728 - __main__ - INFO - Loaded leaderboard with 0 entries
|
3 |
-
2025-03-31 20:33:49,795 - __main__ - WARNING - Initializing empty leaderboard
|
4 |
-
2025-03-31 20:33:49,946 - __main__ - WARNING - Initializing empty leaderboard
|
5 |
-
2025-03-31 20:33:50,278 - __main__ - WARNING - Initializing empty leaderboard
|
6 |
-
2025-03-31 20:33:50,398 - __main__ - WARNING - Initializing empty leaderboard
|
7 |
-
2025-03-31 20:33:50,624 - __main__ - WARNING - Initializing empty leaderboard
|
8 |
-
2025-03-31 20:33:50,735 - __main__ - WARNING - Initializing empty leaderboard
|
9 |
-
2025-03-31 20:33:50,853 - __main__ - WARNING - Initializing empty leaderboard
|
10 |
-
2025-03-31 20:33:51,000 - __main__ - WARNING - Initializing empty leaderboard
|
11 |
-
2025-03-31 20:33:51,211 - __main__ - WARNING - Initializing empty leaderboard
|
12 |
-
2025-03-31 20:33:51,471 - __main__ - WARNING - Initializing empty leaderboard
|
13 |
-
2025-03-31 20:33:51,591 - __main__ - WARNING - Initializing empty leaderboard
|
14 |
-
2025-03-31 20:33:51,921 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
15 |
-
2025-03-31 20:33:51,921 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
16 |
-
2025-03-31 20:33:51,922 - apscheduler.scheduler - INFO - Scheduler started
|
17 |
-
2025-03-31 20:37:48,565 - __main__ - INFO - Received submission for model chatgpt-4o-latest (CoT): /tmp/gradio/a1f2d3a725f7b441a1fbfdac8e51dfd3bf7bbb4ab2d1c20362cfa130f4bdda6d/chatgpt-4o-latest CoT.jsonl
|
18 |
-
2025-03-31 20:37:48,595 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
19 |
-
2025-03-31 20:37:48,765 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_204307_8d77ec17.log
DELETED
@@ -1,23 +0,0 @@
|
|
1 |
-
2025-03-31 20:43:08,422 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 20:43:08,623 - __main__ - INFO - Loaded leaderboard with 0 entries
|
3 |
-
2025-03-31 20:43:08,693 - __main__ - WARNING - Initializing empty leaderboard
|
4 |
-
2025-03-31 20:43:08,832 - __main__ - WARNING - Initializing empty leaderboard
|
5 |
-
2025-03-31 20:43:08,948 - __main__ - WARNING - Initializing empty leaderboard
|
6 |
-
2025-03-31 20:43:09,071 - __main__ - WARNING - Initializing empty leaderboard
|
7 |
-
2025-03-31 20:43:09,188 - __main__ - WARNING - Initializing empty leaderboard
|
8 |
-
2025-03-31 20:43:09,383 - __main__ - WARNING - Initializing empty leaderboard
|
9 |
-
2025-03-31 20:43:09,494 - __main__ - WARNING - Initializing empty leaderboard
|
10 |
-
2025-03-31 20:43:09,604 - __main__ - WARNING - Initializing empty leaderboard
|
11 |
-
2025-03-31 20:43:09,803 - __main__ - WARNING - Initializing empty leaderboard
|
12 |
-
2025-03-31 20:43:10,013 - __main__ - WARNING - Initializing empty leaderboard
|
13 |
-
2025-03-31 20:43:10,123 - __main__ - WARNING - Initializing empty leaderboard
|
14 |
-
2025-03-31 20:43:10,578 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
15 |
-
2025-03-31 20:43:10,579 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
16 |
-
2025-03-31 20:43:10,579 - apscheduler.scheduler - INFO - Scheduler started
|
17 |
-
2025-03-31 20:46:56,010 - __main__ - INFO - Received submission for model chatgpt-4o-latest (CoT): /tmp/gradio/a1f2d3a725f7b441a1fbfdac8e51dfd3bf7bbb4ab2d1c20362cfa130f4bdda6d/chatgpt-4o-latest CoT.jsonl
|
18 |
-
2025-03-31 20:46:56,040 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
19 |
-
2025-03-31 20:46:57,488 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
20 |
-
2025-03-31 20:46:57,488 - guardbench.evaluator - INFO - Starting evaluation for model: chatgpt-4o-latest_(CoT)
|
21 |
-
2025-03-31 20:46:57,488 - guardbench.evaluator - INFO - Using cached results for model: chatgpt-4o-latest_(CoT)
|
22 |
-
2025-03-31 20:46:57,489 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
23 |
-
2025-03-31 20:46:57,582 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_204836_3421e73f.log
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
2025-03-31 20:48:37,607 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 20:48:37,906 - __main__ - INFO - Loaded leaderboard with 0 entries
|
3 |
-
2025-03-31 20:48:37,976 - __main__ - WARNING - Initializing empty leaderboard
|
4 |
-
2025-03-31 20:48:38,156 - __main__ - WARNING - Initializing empty leaderboard
|
5 |
-
2025-03-31 20:48:38,310 - __main__ - WARNING - Initializing empty leaderboard
|
6 |
-
2025-03-31 20:48:38,484 - __main__ - WARNING - Initializing empty leaderboard
|
7 |
-
2025-03-31 20:48:38,744 - __main__ - WARNING - Initializing empty leaderboard
|
8 |
-
2025-03-31 20:48:38,898 - __main__ - WARNING - Initializing empty leaderboard
|
9 |
-
2025-03-31 20:48:39,059 - __main__ - WARNING - Initializing empty leaderboard
|
10 |
-
2025-03-31 20:48:39,327 - __main__ - WARNING - Initializing empty leaderboard
|
11 |
-
2025-03-31 20:48:39,480 - __main__ - WARNING - Initializing empty leaderboard
|
12 |
-
2025-03-31 20:48:39,670 - __main__ - WARNING - Initializing empty leaderboard
|
13 |
-
2025-03-31 20:48:39,832 - __main__ - WARNING - Initializing empty leaderboard
|
14 |
-
2025-03-31 20:48:40,214 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
15 |
-
2025-03-31 20:48:40,214 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
16 |
-
2025-03-31 20:48:40,214 - apscheduler.scheduler - INFO - Scheduler started
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_205152_1140353b.log
DELETED
@@ -1,19 +0,0 @@
|
|
1 |
-
2025-03-31 20:51:53,395 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 20:51:53,703 - __main__ - INFO - Loaded leaderboard with 0 entries
|
3 |
-
2025-03-31 20:51:53,774 - __main__ - WARNING - Initializing empty leaderboard
|
4 |
-
2025-03-31 20:51:54,056 - __main__ - WARNING - Initializing empty leaderboard
|
5 |
-
2025-03-31 20:51:54,148 - __main__ - WARNING - Initializing empty leaderboard
|
6 |
-
2025-03-31 20:51:54,235 - __main__ - WARNING - Initializing empty leaderboard
|
7 |
-
2025-03-31 20:51:54,326 - __main__ - WARNING - Initializing empty leaderboard
|
8 |
-
2025-03-31 20:51:54,417 - __main__ - WARNING - Initializing empty leaderboard
|
9 |
-
2025-03-31 20:51:54,705 - __main__ - WARNING - Initializing empty leaderboard
|
10 |
-
2025-03-31 20:51:54,797 - __main__ - WARNING - Initializing empty leaderboard
|
11 |
-
2025-03-31 20:51:54,901 - __main__ - WARNING - Initializing empty leaderboard
|
12 |
-
2025-03-31 20:51:54,993 - __main__ - WARNING - Initializing empty leaderboard
|
13 |
-
2025-03-31 20:51:55,092 - __main__ - WARNING - Initializing empty leaderboard
|
14 |
-
2025-03-31 20:51:55,407 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
15 |
-
2025-03-31 20:51:55,407 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
16 |
-
2025-03-31 20:51:55,407 - apscheduler.scheduler - INFO - Scheduler started
|
17 |
-
2025-03-31 20:53:44,802 - __main__ - INFO - Received submission for model chatgpt-4o-latest (CoT): /tmp/gradio/a1f2d3a725f7b441a1fbfdac8e51dfd3bf7bbb4ab2d1c20362cfa130f4bdda6d/chatgpt-4o-latest CoT.jsonl
|
18 |
-
2025-03-31 20:53:44,829 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
19 |
-
2025-03-31 20:53:44,996 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_205420_d59a424e.log
DELETED
@@ -1,61 +0,0 @@
|
|
1 |
-
2025-03-31 20:54:21,474 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 20:54:21,606 - __main__ - INFO - Loaded leaderboard with 0 entries
|
3 |
-
2025-03-31 20:54:21,675 - __main__ - WARNING - Initializing empty leaderboard
|
4 |
-
2025-03-31 20:54:21,785 - __main__ - WARNING - Initializing empty leaderboard
|
5 |
-
2025-03-31 20:54:21,881 - __main__ - WARNING - Initializing empty leaderboard
|
6 |
-
2025-03-31 20:54:21,977 - __main__ - WARNING - Initializing empty leaderboard
|
7 |
-
2025-03-31 20:54:22,074 - __main__ - WARNING - Initializing empty leaderboard
|
8 |
-
2025-03-31 20:54:22,169 - __main__ - WARNING - Initializing empty leaderboard
|
9 |
-
2025-03-31 20:54:22,293 - __main__ - WARNING - Initializing empty leaderboard
|
10 |
-
2025-03-31 20:54:22,394 - __main__ - WARNING - Initializing empty leaderboard
|
11 |
-
2025-03-31 20:54:22,505 - __main__ - WARNING - Initializing empty leaderboard
|
12 |
-
2025-03-31 20:54:22,594 - __main__ - WARNING - Initializing empty leaderboard
|
13 |
-
2025-03-31 20:54:22,685 - __main__ - WARNING - Initializing empty leaderboard
|
14 |
-
2025-03-31 20:54:22,997 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
15 |
-
2025-03-31 20:54:22,997 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
16 |
-
2025-03-31 20:54:22,997 - apscheduler.scheduler - INFO - Scheduler started
|
17 |
-
2025-03-31 20:55:51,877 - __main__ - INFO - Received submission for model chatgpt-4o-latest (CoT): /tmp/gradio/a1f2d3a725f7b441a1fbfdac8e51dfd3bf7bbb4ab2d1c20362cfa130f4bdda6d/chatgpt-4o-latest CoT.jsonl
|
18 |
-
2025-03-31 20:55:51,906 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
19 |
-
2025-03-31 20:55:52,929 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
20 |
-
2025-03-31 20:55:52,929 - guardbench.evaluator - INFO - Starting evaluation for model: chatgpt-4o-latest_(CoT)
|
21 |
-
2025-03-31 20:55:52,929 - guardbench.evaluator - INFO - Using cached results for model: chatgpt-4o-latest_(CoT)
|
22 |
-
2025-03-31 20:55:52,966 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
23 |
-
2025-03-31 20:55:52,970 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
24 |
-
2025-03-31 20:55:53,073 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
25 |
-
2025-03-31 20:55:53,076 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
26 |
-
2025-03-31 20:55:53,175 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
27 |
-
2025-03-31 20:55:53,178 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
28 |
-
2025-03-31 20:55:53,281 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
29 |
-
2025-03-31 20:55:53,284 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
30 |
-
2025-03-31 20:55:53,386 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
31 |
-
2025-03-31 20:55:53,390 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
32 |
-
2025-03-31 20:55:53,487 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
33 |
-
2025-03-31 20:55:53,491 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
34 |
-
2025-03-31 20:55:53,592 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
35 |
-
2025-03-31 20:55:53,596 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
36 |
-
2025-03-31 20:55:53,698 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
37 |
-
2025-03-31 20:55:53,701 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
38 |
-
2025-03-31 20:55:54,267 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
39 |
-
2025-03-31 20:55:54,271 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
40 |
-
2025-03-31 20:55:54,371 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
41 |
-
2025-03-31 20:55:54,375 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
42 |
-
2025-03-31 20:55:54,431 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
43 |
-
2025-03-31 20:55:54,434 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
44 |
-
2025-03-31 20:55:54,534 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
45 |
-
2025-03-31 20:55:54,537 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
46 |
-
2025-03-31 20:55:54,634 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
47 |
-
2025-03-31 20:55:54,638 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
48 |
-
2025-03-31 20:55:54,738 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
49 |
-
2025-03-31 20:55:54,741 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
50 |
-
2025-03-31 20:55:54,841 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
51 |
-
2025-03-31 20:55:54,844 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
52 |
-
2025-03-31 20:55:54,945 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
53 |
-
2025-03-31 20:55:54,949 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
54 |
-
2025-03-31 20:55:55,049 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
55 |
-
2025-03-31 20:55:55,052 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
56 |
-
2025-03-31 20:55:55,152 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
57 |
-
2025-03-31 20:55:55,156 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
58 |
-
2025-03-31 20:55:55,260 - guardbench.evaluator - INFO - Updated leaderboard for model: chatgpt-4o-latest_(CoT) from cached results
|
59 |
-
2025-03-31 20:55:55,262 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: chatgpt-4o-latest_(CoT)
|
60 |
-
2025-03-31 20:55:56,838 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
61 |
-
2025-03-31 20:55:57,001 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_205853_bf4fa85f.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 20:58:54,582 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 20:58:54,675 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_210025_ba691e37.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:00:26,667 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:00:26,793 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_210109_f46123b9.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:01:10,756 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:01:10,828 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_210119_f0e10b9b.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:01:20,172 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:01:20,242 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_210208_029d8318.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:02:09,399 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:02:09,500 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_210459_437adc64.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:04:59,995 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:05:00,111 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_210550_0358568e.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:05:51,686 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:05:51,759 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_210641_91d1d06b.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:06:42,594 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:06:42,717 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_210920_cd35c4f0.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:09:21,490 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:09:21,613 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_211215_a8cf06a3.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:12:16,593 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:12:16,704 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_211255_d32ee1a4.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:12:56,431 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:12:56,505 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_211332_24223f1a.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:13:33,061 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:13:33,189 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_211545_244674df.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:15:46,264 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:15:46,382 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_211735_6d503239.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:17:36,939 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:17:37,057 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_211916_3e96de42.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:19:17,112 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:19:17,224 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_212027_f9d450e9.log
DELETED
@@ -1,5 +0,0 @@
|
|
1 |
-
2025-03-31 21:20:28,558 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:20:28,829 - __main__ - INFO - Loaded leaderboard with 1 entries
|
3 |
-
2025-03-31 21:20:30,189 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 21:20:30,189 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 21:20:30,189 - apscheduler.scheduler - INFO - Scheduler started
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_212722_655f3190.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-03-31 21:27:23,630 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:27:23,765 - __main__ - INFO - Loaded leaderboard with 1 entries
|
|
|
|
|
|
logs/guardbench_20250331_213207_74f9e2de.log
DELETED
@@ -1,5 +0,0 @@
|
|
1 |
-
2025-03-31 21:32:08,256 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:32:08,412 - __main__ - INFO - Loaded leaderboard with 1 entries
|
3 |
-
2025-03-31 21:32:09,385 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 21:32:09,385 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 21:32:09,386 - apscheduler.scheduler - INFO - Scheduler started
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_213331_f72d2f6a.log
DELETED
@@ -1,5 +0,0 @@
|
|
1 |
-
2025-03-31 21:33:32,956 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:33:33,112 - __main__ - INFO - Loaded leaderboard with 1 entries
|
3 |
-
2025-03-31 21:33:34,050 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 21:33:34,050 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 21:33:34,050 - apscheduler.scheduler - INFO - Scheduler started
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_214118_0da0491f.log
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
2025-03-31 21:41:19,264 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:41:19,411 - __main__ - INFO - Loaded leaderboard with 1 entries
|
3 |
-
2025-03-31 21:41:20,492 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 21:41:20,492 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 21:41:20,492 - apscheduler.scheduler - INFO - Scheduler started
|
6 |
-
2025-03-31 21:44:25,074 - __main__ - INFO - Received submission for model gpt-4o-mini (CoT): /tmp/gradio/35fc6ab7ba3af1e1b210ed2851ec70f52004490c3534b64bfd8e4830f5cccea0/gpt-4o-mini CoT.jsonl
|
7 |
-
2025-03-31 21:44:25,100 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
8 |
-
2025-03-31 21:44:26,183 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
9 |
-
2025-03-31 21:44:26,183 - guardbench.evaluator - INFO - Starting evaluation for model: gpt-4o-mini_(CoT)
|
10 |
-
2025-03-31 21:44:26,183 - guardbench.evaluator - INFO - Using cached results for model: gpt-4o-mini_(CoT)
|
11 |
-
2025-03-31 21:44:26,214 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
12 |
-
2025-03-31 21:44:26,218 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
13 |
-
2025-03-31 21:44:26,486 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
14 |
-
2025-03-31 21:44:26,490 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
15 |
-
2025-03-31 21:44:26,594 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
16 |
-
2025-03-31 21:44:26,597 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
17 |
-
2025-03-31 21:44:26,700 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
18 |
-
2025-03-31 21:44:26,703 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
19 |
-
2025-03-31 21:44:26,806 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
20 |
-
2025-03-31 21:44:26,810 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
21 |
-
2025-03-31 21:44:26,908 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
22 |
-
2025-03-31 21:44:26,912 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
23 |
-
2025-03-31 21:44:27,015 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
24 |
-
2025-03-31 21:44:27,018 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
25 |
-
2025-03-31 21:44:27,130 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
26 |
-
2025-03-31 21:44:27,134 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
27 |
-
2025-03-31 21:44:27,201 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
28 |
-
2025-03-31 21:44:27,205 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
29 |
-
2025-03-31 21:44:27,326 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
30 |
-
2025-03-31 21:44:27,330 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
31 |
-
2025-03-31 21:44:27,962 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
32 |
-
2025-03-31 21:44:27,966 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
33 |
-
2025-03-31 21:44:28,070 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
34 |
-
2025-03-31 21:44:28,074 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
35 |
-
2025-03-31 21:44:28,175 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
36 |
-
2025-03-31 21:44:28,179 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
37 |
-
2025-03-31 21:44:28,282 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
38 |
-
2025-03-31 21:44:28,286 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
39 |
-
2025-03-31 21:44:28,386 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
40 |
-
2025-03-31 21:44:28,390 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
41 |
-
2025-03-31 21:44:28,489 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
42 |
-
2025-03-31 21:44:28,493 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
43 |
-
2025-03-31 21:44:28,594 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
44 |
-
2025-03-31 21:44:28,598 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
45 |
-
2025-03-31 21:44:28,702 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
46 |
-
2025-03-31 21:44:28,705 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
47 |
-
2025-03-31 21:44:28,813 - guardbench.evaluator - INFO - Updated leaderboard for model: gpt-4o-mini_(CoT) from cached results
|
48 |
-
2025-03-31 21:44:28,815 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: gpt-4o-mini_(CoT)
|
49 |
-
2025-03-31 21:44:30,083 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
50 |
-
2025-03-31 21:44:30,284 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_214511_0a5acf8b.log
DELETED
@@ -1,5 +0,0 @@
|
|
1 |
-
2025-03-31 21:45:12,578 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:45:12,654 - __main__ - INFO - Loaded leaderboard with 2 entries
|
3 |
-
2025-03-31 21:45:13,819 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 21:45:13,819 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 21:45:13,819 - apscheduler.scheduler - INFO - Scheduler started
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_214841_4df080f3.log
DELETED
@@ -1,5 +0,0 @@
|
|
1 |
-
2025-03-31 21:48:42,942 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:48:43,058 - __main__ - INFO - Loaded leaderboard with 2 entries
|
3 |
-
2025-03-31 21:48:43,995 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 21:48:43,995 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 21:48:43,995 - apscheduler.scheduler - INFO - Scheduler started
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_215007_9c98c60a.log
DELETED
@@ -1,5 +0,0 @@
|
|
1 |
-
2025-03-31 21:50:08,436 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:50:08,552 - __main__ - INFO - Loaded leaderboard with 2 entries
|
3 |
-
2025-03-31 21:50:09,654 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 21:50:09,654 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 21:50:09,655 - apscheduler.scheduler - INFO - Scheduler started
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_215514_ad36e4b4.log
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
2025-03-31 21:55:15,352 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 21:55:15,454 - __main__ - INFO - Loaded leaderboard with 2 entries
|
3 |
-
2025-03-31 21:55:16,351 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 21:55:16,352 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 21:55:16,352 - apscheduler.scheduler - INFO - Scheduler started
|
6 |
-
2025-03-31 21:57:09,862 - __main__ - INFO - Received submission for model gpt-4o-mini: /tmp/gradio/26f1c6837517a59736a02ffe486b3504336116347e339745a7973e9412dad4db/gpt-4o-mini-3.jsonl
|
7 |
-
2025-03-31 21:57:10,863 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
8 |
-
2025-03-31 21:57:11,927 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
9 |
-
2025-03-31 21:57:11,927 - guardbench.evaluator - INFO - Starting evaluation for model: gpt-4o-mini
|
10 |
-
2025-03-31 21:57:11,927 - guardbench.evaluator - INFO - Using cached results for model: gpt-4o-mini
|
11 |
-
2025-03-31 21:57:11,947 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
12 |
-
2025-03-31 21:57:11,951 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
13 |
-
2025-03-31 21:57:12,054 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
14 |
-
2025-03-31 21:57:12,058 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
15 |
-
2025-03-31 21:57:12,155 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
16 |
-
2025-03-31 21:57:12,158 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
17 |
-
2025-03-31 21:57:12,215 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
18 |
-
2025-03-31 21:57:12,219 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
19 |
-
2025-03-31 21:57:12,319 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
20 |
-
2025-03-31 21:57:12,322 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
21 |
-
2025-03-31 21:57:12,423 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
22 |
-
2025-03-31 21:57:12,426 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
23 |
-
2025-03-31 21:57:12,526 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
24 |
-
2025-03-31 21:57:12,530 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
25 |
-
2025-03-31 21:57:12,631 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
26 |
-
2025-03-31 21:57:12,634 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
27 |
-
2025-03-31 21:57:12,736 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
28 |
-
2025-03-31 21:57:12,740 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
29 |
-
2025-03-31 21:57:12,840 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
30 |
-
2025-03-31 21:57:12,843 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
31 |
-
2025-03-31 21:57:12,943 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
32 |
-
2025-03-31 21:57:12,946 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
33 |
-
2025-03-31 21:57:13,045 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
34 |
-
2025-03-31 21:57:13,049 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
35 |
-
2025-03-31 21:57:13,147 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
36 |
-
2025-03-31 21:57:13,151 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
37 |
-
2025-03-31 21:57:13,701 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
38 |
-
2025-03-31 21:57:13,705 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
39 |
-
2025-03-31 21:57:13,805 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
40 |
-
2025-03-31 21:57:13,809 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
41 |
-
2025-03-31 21:57:13,905 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
42 |
-
2025-03-31 21:57:13,909 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
43 |
-
2025-03-31 21:57:14,008 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
44 |
-
2025-03-31 21:57:14,011 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
45 |
-
2025-03-31 21:57:14,113 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
46 |
-
2025-03-31 21:57:14,117 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
47 |
-
2025-03-31 21:57:14,219 - guardbench.evaluator - INFO - Updated leaderboard for model: gpt-4o-mini from cached results
|
48 |
-
2025-03-31 21:57:14,220 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: gpt-4o-mini
|
49 |
-
2025-03-31 21:57:15,528 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
50 |
-
2025-03-31 21:57:15,650 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_220348_0cb4d8e9.log
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
2025-03-31 22:03:49,677 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 22:03:49,841 - __main__ - INFO - Loaded leaderboard with 3 entries
|
3 |
-
2025-03-31 22:03:51,379 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 22:03:51,379 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 22:03:51,379 - apscheduler.scheduler - INFO - Scheduler started
|
6 |
-
2025-03-31 22:04:45,096 - __main__ - INFO - Received submission for model gpt4omini-TEST: /tmp/gradio/26f1c6837517a59736a02ffe486b3504336116347e339745a7973e9412dad4db/gpt-4o-mini-3.jsonl
|
7 |
-
2025-03-31 22:04:45,574 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
8 |
-
2025-03-31 22:04:46,470 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
9 |
-
2025-03-31 22:04:46,470 - guardbench.evaluator - INFO - Starting evaluation for model: gpt4omini-TEST
|
10 |
-
2025-03-31 22:04:46,470 - guardbench.evaluator - INFO - Using cached results for model: gpt4omini-TEST
|
11 |
-
2025-03-31 22:04:46,490 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
12 |
-
2025-03-31 22:04:46,493 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
13 |
-
2025-03-31 22:04:46,595 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
14 |
-
2025-03-31 22:04:46,600 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
15 |
-
2025-03-31 22:04:46,702 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
16 |
-
2025-03-31 22:04:46,706 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
17 |
-
2025-03-31 22:04:46,804 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
18 |
-
2025-03-31 22:04:46,808 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
19 |
-
2025-03-31 22:04:46,914 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
20 |
-
2025-03-31 22:04:46,917 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
21 |
-
2025-03-31 22:04:47,019 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
22 |
-
2025-03-31 22:04:47,023 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
23 |
-
2025-03-31 22:04:47,128 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
24 |
-
2025-03-31 22:04:47,132 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
25 |
-
2025-03-31 22:04:47,237 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
26 |
-
2025-03-31 22:04:47,240 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
27 |
-
2025-03-31 22:04:47,355 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
28 |
-
2025-03-31 22:04:47,359 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
29 |
-
2025-03-31 22:04:47,462 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
30 |
-
2025-03-31 22:04:47,466 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
31 |
-
2025-03-31 22:04:47,573 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
32 |
-
2025-03-31 22:04:47,576 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
33 |
-
2025-03-31 22:04:47,694 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
34 |
-
2025-03-31 22:04:47,697 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
35 |
-
2025-03-31 22:04:47,804 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
36 |
-
2025-03-31 22:04:47,808 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
37 |
-
2025-03-31 22:04:47,913 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
38 |
-
2025-03-31 22:04:47,917 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
39 |
-
2025-03-31 22:04:48,022 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
40 |
-
2025-03-31 22:04:48,026 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
41 |
-
2025-03-31 22:04:48,605 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
42 |
-
2025-03-31 22:04:48,609 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
43 |
-
2025-03-31 22:04:48,667 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
44 |
-
2025-03-31 22:04:48,671 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
45 |
-
2025-03-31 22:04:48,771 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
46 |
-
2025-03-31 22:04:48,775 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
47 |
-
2025-03-31 22:04:48,882 - guardbench.evaluator - INFO - Updated leaderboard for model: gpt4omini-TEST from cached results
|
48 |
-
2025-03-31 22:04:48,883 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: gpt4omini-TEST
|
49 |
-
2025-03-31 22:04:50,345 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
50 |
-
2025-03-31 22:04:50,514 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_220638_21aa20f2.log
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
2025-03-31 22:06:39,559 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 22:06:39,705 - __main__ - INFO - Loaded leaderboard with 4 entries
|
3 |
-
2025-03-31 22:06:41,404 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 22:06:41,404 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 22:06:41,404 - apscheduler.scheduler - INFO - Scheduler started
|
6 |
-
2025-03-31 22:07:29,463 - __main__ - INFO - Received submission for model gpt4omini-TEST2: /tmp/gradio/26f1c6837517a59736a02ffe486b3504336116347e339745a7973e9412dad4db/gpt-4o-mini-3.jsonl
|
7 |
-
2025-03-31 22:07:30,063 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
8 |
-
2025-03-31 22:07:31,596 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
9 |
-
2025-03-31 22:07:31,597 - guardbench.evaluator - INFO - Starting evaluation for model: gpt4omini-TEST2
|
10 |
-
2025-03-31 22:07:31,597 - guardbench.evaluator - INFO - Using cached results for model: gpt4omini-TEST2
|
11 |
-
2025-03-31 22:07:31,616 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
12 |
-
2025-03-31 22:07:31,620 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
13 |
-
2025-03-31 22:07:31,723 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
14 |
-
2025-03-31 22:07:31,727 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
15 |
-
2025-03-31 22:07:31,828 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
16 |
-
2025-03-31 22:07:31,831 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
17 |
-
2025-03-31 22:07:31,934 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
18 |
-
2025-03-31 22:07:31,937 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
19 |
-
2025-03-31 22:07:32,040 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
20 |
-
2025-03-31 22:07:32,043 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
21 |
-
2025-03-31 22:07:32,144 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
22 |
-
2025-03-31 22:07:32,148 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
23 |
-
2025-03-31 22:07:32,703 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
24 |
-
2025-03-31 22:07:32,706 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
25 |
-
2025-03-31 22:07:32,808 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
26 |
-
2025-03-31 22:07:32,812 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
27 |
-
2025-03-31 22:07:32,912 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
28 |
-
2025-03-31 22:07:32,916 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
29 |
-
2025-03-31 22:07:33,018 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
30 |
-
2025-03-31 22:07:33,022 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
31 |
-
2025-03-31 22:07:33,123 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
32 |
-
2025-03-31 22:07:33,127 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
33 |
-
2025-03-31 22:07:33,231 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
34 |
-
2025-03-31 22:07:33,234 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
35 |
-
2025-03-31 22:07:33,336 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
36 |
-
2025-03-31 22:07:33,339 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
37 |
-
2025-03-31 22:07:33,438 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
38 |
-
2025-03-31 22:07:33,441 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
39 |
-
2025-03-31 22:07:33,545 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
40 |
-
2025-03-31 22:07:33,548 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
41 |
-
2025-03-31 22:07:33,647 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
42 |
-
2025-03-31 22:07:33,650 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
43 |
-
2025-03-31 22:07:33,707 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
44 |
-
2025-03-31 22:07:33,711 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
45 |
-
2025-03-31 22:07:33,807 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
46 |
-
2025-03-31 22:07:33,811 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
47 |
-
2025-03-31 22:07:33,915 - guardbench.evaluator - INFO - Updated leaderboard for model: gpt4omini-TEST2 from cached results
|
48 |
-
2025-03-31 22:07:33,917 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: gpt4omini-TEST2
|
49 |
-
2025-03-31 22:07:36,275 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
50 |
-
2025-03-31 22:07:36,423 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_221124_3ffa908f.log
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
2025-03-31 22:11:25,101 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 22:11:25,216 - __main__ - INFO - Loaded leaderboard with 5 entries
|
3 |
-
2025-03-31 22:11:26,084 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 22:11:26,084 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 22:11:26,085 - apscheduler.scheduler - INFO - Scheduler started
|
6 |
-
2025-03-31 22:12:12,091 - __main__ - INFO - Received submission for model gpt4omini-TEST5: /tmp/gradio/26f1c6837517a59736a02ffe486b3504336116347e339745a7973e9412dad4db/gpt-4o-mini-3.jsonl
|
7 |
-
2025-03-31 22:12:12,831 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
8 |
-
2025-03-31 22:12:14,244 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
9 |
-
2025-03-31 22:12:14,244 - guardbench.evaluator - INFO - Starting evaluation for model: gpt4omini-TEST5
|
10 |
-
2025-03-31 22:12:14,244 - guardbench.evaluator - INFO - Using cached results for model: gpt4omini-TEST5
|
11 |
-
2025-03-31 22:12:14,263 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
12 |
-
2025-03-31 22:12:14,267 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
13 |
-
2025-03-31 22:12:14,831 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
14 |
-
2025-03-31 22:12:14,835 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
15 |
-
2025-03-31 22:12:14,939 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
16 |
-
2025-03-31 22:12:14,942 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
17 |
-
2025-03-31 22:12:15,044 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
18 |
-
2025-03-31 22:12:15,047 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
19 |
-
2025-03-31 22:12:15,149 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
20 |
-
2025-03-31 22:12:15,152 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
21 |
-
2025-03-31 22:12:15,255 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
22 |
-
2025-03-31 22:12:15,258 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
23 |
-
2025-03-31 22:12:15,361 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
24 |
-
2025-03-31 22:12:15,364 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
25 |
-
2025-03-31 22:12:15,463 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
26 |
-
2025-03-31 22:12:15,466 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
27 |
-
2025-03-31 22:12:15,569 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
28 |
-
2025-03-31 22:12:15,573 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
29 |
-
2025-03-31 22:12:15,676 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
30 |
-
2025-03-31 22:12:15,680 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
31 |
-
2025-03-31 22:12:15,782 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
32 |
-
2025-03-31 22:12:15,785 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
33 |
-
2025-03-31 22:12:15,843 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
34 |
-
2025-03-31 22:12:15,847 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
35 |
-
2025-03-31 22:12:15,949 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
36 |
-
2025-03-31 22:12:15,953 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
37 |
-
2025-03-31 22:12:16,053 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
38 |
-
2025-03-31 22:12:16,056 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
39 |
-
2025-03-31 22:12:16,156 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
40 |
-
2025-03-31 22:12:16,160 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
41 |
-
2025-03-31 22:12:16,263 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
42 |
-
2025-03-31 22:12:16,267 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
43 |
-
2025-03-31 22:12:16,369 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
44 |
-
2025-03-31 22:12:16,373 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
45 |
-
2025-03-31 22:12:16,474 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
46 |
-
2025-03-31 22:12:16,478 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
47 |
-
2025-03-31 22:12:16,583 - guardbench.evaluator - INFO - Updated leaderboard for model: gpt4omini-TEST5 from cached results
|
48 |
-
2025-03-31 22:12:16,584 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: gpt4omini-TEST5
|
49 |
-
2025-03-31 22:12:18,047 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
50 |
-
2025-03-31 22:12:18,174 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_221755_fc667123.log
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
2025-03-31 22:17:56,280 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 22:17:56,406 - __main__ - INFO - Loaded leaderboard with 6 entries
|
3 |
-
2025-03-31 22:17:57,983 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 22:17:57,983 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 22:17:57,983 - apscheduler.scheduler - INFO - Scheduler started
|
6 |
-
2025-03-31 22:18:49,068 - __main__ - INFO - Received submission for model gpt4omini-TEST27: /tmp/gradio/26f1c6837517a59736a02ffe486b3504336116347e339745a7973e9412dad4db/gpt-4o-mini-3.jsonl
|
7 |
-
2025-03-31 22:18:49,596 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
8 |
-
2025-03-31 22:18:50,543 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
9 |
-
2025-03-31 22:18:50,543 - guardbench.evaluator - INFO - Starting evaluation for model: gpt4omini-TEST27
|
10 |
-
2025-03-31 22:18:50,543 - guardbench.evaluator - INFO - Using cached results for model: gpt4omini-TEST27
|
11 |
-
2025-03-31 22:18:50,563 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
12 |
-
2025-03-31 22:18:50,567 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
13 |
-
2025-03-31 22:18:50,668 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
14 |
-
2025-03-31 22:18:50,672 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
15 |
-
2025-03-31 22:18:50,769 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
16 |
-
2025-03-31 22:18:50,772 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
17 |
-
2025-03-31 22:18:50,873 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
18 |
-
2025-03-31 22:18:50,877 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
19 |
-
2025-03-31 22:18:50,978 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
20 |
-
2025-03-31 22:18:50,982 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
21 |
-
2025-03-31 22:18:51,085 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
22 |
-
2025-03-31 22:18:51,088 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
23 |
-
2025-03-31 22:18:51,191 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
24 |
-
2025-03-31 22:18:51,195 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
25 |
-
2025-03-31 22:18:51,297 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
26 |
-
2025-03-31 22:18:51,300 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
27 |
-
2025-03-31 22:18:51,398 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
28 |
-
2025-03-31 22:18:51,401 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
29 |
-
2025-03-31 22:18:51,503 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
30 |
-
2025-03-31 22:18:51,507 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
31 |
-
2025-03-31 22:18:51,607 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
32 |
-
2025-03-31 22:18:51,611 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
33 |
-
2025-03-31 22:18:51,712 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
34 |
-
2025-03-31 22:18:51,716 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
35 |
-
2025-03-31 22:18:51,817 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
36 |
-
2025-03-31 22:18:51,821 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
37 |
-
2025-03-31 22:18:51,923 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
38 |
-
2025-03-31 22:18:51,926 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
39 |
-
2025-03-31 22:18:52,476 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
40 |
-
2025-03-31 22:18:52,480 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
41 |
-
2025-03-31 22:18:52,582 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
42 |
-
2025-03-31 22:18:52,586 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
43 |
-
2025-03-31 22:18:52,686 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
44 |
-
2025-03-31 22:18:52,690 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
45 |
-
2025-03-31 22:18:52,747 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
46 |
-
2025-03-31 22:18:52,750 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
47 |
-
2025-03-31 22:18:52,851 - guardbench.evaluator - INFO - Updated leaderboard for model: gpt4omini-TEST27 from cached results
|
48 |
-
2025-03-31 22:18:52,852 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: gpt4omini-TEST27
|
49 |
-
2025-03-31 22:18:54,180 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
50 |
-
2025-03-31 22:18:54,298 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_222103_90a3095d.log
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
2025-03-31 22:21:04,147 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 22:21:04,266 - __main__ - INFO - Loaded leaderboard with 7 entries
|
3 |
-
2025-03-31 22:21:06,082 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 22:21:06,083 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 22:21:06,083 - apscheduler.scheduler - INFO - Scheduler started
|
6 |
-
2025-03-31 22:21:41,064 - __main__ - INFO - Received submission for model gpt-4o-mini-TEST6: /tmp/gradio/26f1c6837517a59736a02ffe486b3504336116347e339745a7973e9412dad4db/gpt-4o-mini-3.jsonl
|
7 |
-
2025-03-31 22:21:42,056 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
8 |
-
2025-03-31 22:21:42,922 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
9 |
-
2025-03-31 22:21:42,922 - guardbench.evaluator - INFO - Starting evaluation for model: gpt-4o-mini-TEST6
|
10 |
-
2025-03-31 22:21:42,922 - guardbench.evaluator - INFO - Using cached results for model: gpt-4o-mini-TEST6
|
11 |
-
2025-03-31 22:21:42,942 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
12 |
-
2025-03-31 22:21:42,945 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
13 |
-
2025-03-31 22:21:43,044 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
14 |
-
2025-03-31 22:21:43,048 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
15 |
-
2025-03-31 22:21:43,151 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
16 |
-
2025-03-31 22:21:43,155 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
17 |
-
2025-03-31 22:21:43,257 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
18 |
-
2025-03-31 22:21:43,260 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
19 |
-
2025-03-31 22:21:43,360 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
20 |
-
2025-03-31 22:21:43,363 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
21 |
-
2025-03-31 22:21:43,461 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
22 |
-
2025-03-31 22:21:43,465 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
23 |
-
2025-03-31 22:21:43,563 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
24 |
-
2025-03-31 22:21:43,567 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
25 |
-
2025-03-31 22:21:44,119 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
26 |
-
2025-03-31 22:21:44,123 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
27 |
-
2025-03-31 22:21:44,223 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
28 |
-
2025-03-31 22:21:44,226 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
29 |
-
2025-03-31 22:21:44,323 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
30 |
-
2025-03-31 22:21:44,326 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
31 |
-
2025-03-31 22:21:44,383 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
32 |
-
2025-03-31 22:21:44,387 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
33 |
-
2025-03-31 22:21:44,487 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
34 |
-
2025-03-31 22:21:44,490 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
35 |
-
2025-03-31 22:21:44,590 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
36 |
-
2025-03-31 22:21:44,593 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
37 |
-
2025-03-31 22:21:44,694 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
38 |
-
2025-03-31 22:21:44,698 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
39 |
-
2025-03-31 22:21:44,799 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
40 |
-
2025-03-31 22:21:44,802 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
41 |
-
2025-03-31 22:21:44,903 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
42 |
-
2025-03-31 22:21:44,907 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
43 |
-
2025-03-31 22:21:45,008 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
44 |
-
2025-03-31 22:21:45,011 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
45 |
-
2025-03-31 22:21:45,112 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
46 |
-
2025-03-31 22:21:45,116 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
47 |
-
2025-03-31 22:21:45,222 - guardbench.evaluator - INFO - Updated leaderboard for model: gpt-4o-mini-TEST6 from cached results
|
48 |
-
2025-03-31 22:21:45,223 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: gpt-4o-mini-TEST6
|
49 |
-
2025-03-31 22:21:47,120 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
50 |
-
2025-03-31 22:21:47,363 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_222531_b0fff871.log
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
2025-03-31 22:25:32,811 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 22:25:32,908 - __main__ - INFO - Loaded leaderboard with 8 entries
|
3 |
-
2025-03-31 22:25:34,603 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 22:25:34,603 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 22:25:34,603 - apscheduler.scheduler - INFO - Scheduler started
|
6 |
-
2025-03-31 22:26:13,775 - __main__ - INFO - Received submission for model gpt4omini-TEST7: /tmp/gradio/26f1c6837517a59736a02ffe486b3504336116347e339745a7973e9412dad4db/gpt-4o-mini-3.jsonl
|
7 |
-
2025-03-31 22:26:14,580 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
8 |
-
2025-03-31 22:26:15,600 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
9 |
-
2025-03-31 22:26:15,600 - guardbench.evaluator - INFO - Starting evaluation for model: gpt4omini-TEST7
|
10 |
-
2025-03-31 22:26:15,601 - guardbench.evaluator - INFO - Using cached results for model: gpt4omini-TEST7
|
11 |
-
2025-03-31 22:26:15,620 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
12 |
-
2025-03-31 22:26:15,624 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
13 |
-
2025-03-31 22:26:15,727 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
14 |
-
2025-03-31 22:26:15,731 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
15 |
-
2025-03-31 22:26:16,284 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
16 |
-
2025-03-31 22:26:16,287 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
17 |
-
2025-03-31 22:26:16,389 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
18 |
-
2025-03-31 22:26:16,392 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
19 |
-
2025-03-31 22:26:16,488 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
20 |
-
2025-03-31 22:26:16,491 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
21 |
-
2025-03-31 22:26:16,593 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
22 |
-
2025-03-31 22:26:16,597 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
23 |
-
2025-03-31 22:26:16,696 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
24 |
-
2025-03-31 22:26:16,700 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
25 |
-
2025-03-31 22:26:16,758 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
26 |
-
2025-03-31 22:26:16,761 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
27 |
-
2025-03-31 22:26:16,863 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
28 |
-
2025-03-31 22:26:16,866 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
29 |
-
2025-03-31 22:26:16,964 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
30 |
-
2025-03-31 22:26:16,968 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
31 |
-
2025-03-31 22:26:17,069 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
32 |
-
2025-03-31 22:26:17,073 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
33 |
-
2025-03-31 22:26:17,172 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
34 |
-
2025-03-31 22:26:17,176 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
35 |
-
2025-03-31 22:26:17,276 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
36 |
-
2025-03-31 22:26:17,279 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
37 |
-
2025-03-31 22:26:17,381 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
38 |
-
2025-03-31 22:26:17,384 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
39 |
-
2025-03-31 22:26:17,480 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
40 |
-
2025-03-31 22:26:17,484 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
41 |
-
2025-03-31 22:26:17,583 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
42 |
-
2025-03-31 22:26:17,586 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
43 |
-
2025-03-31 22:26:17,687 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
44 |
-
2025-03-31 22:26:17,691 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
45 |
-
2025-03-31 22:26:17,793 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
46 |
-
2025-03-31 22:26:17,796 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
47 |
-
2025-03-31 22:26:17,903 - guardbench.evaluator - INFO - Updated leaderboard for model: gpt4omini-TEST7 from cached results
|
48 |
-
2025-03-31 22:26:17,905 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: gpt4omini-TEST7
|
49 |
-
2025-03-31 22:26:19,582 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
50 |
-
2025-03-31 22:26:19,716 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250331_223148_4e22eb66.log
DELETED
@@ -1,50 +0,0 @@
|
|
1 |
-
2025-03-31 22:31:49,992 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-03-31 22:31:50,115 - __main__ - INFO - Loaded leaderboard with 9 entries
|
3 |
-
2025-03-31 22:31:51,543 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
4 |
-
2025-03-31 22:31:51,543 - apscheduler.scheduler - INFO - Added job "<lambda>" to job store "default"
|
5 |
-
2025-03-31 22:31:51,543 - apscheduler.scheduler - INFO - Scheduler started
|
6 |
-
2025-03-31 22:32:19,107 - __main__ - INFO - Received submission for model got-r0mini-8: /tmp/gradio/26f1c6837517a59736a02ffe486b3504336116347e339745a7973e9412dad4db/gpt-4o-mini-3.jsonl
|
7 |
-
2025-03-31 22:32:19,583 - guardbench.context - INFO - Loading dataset from: whitecircle-ai/guardbench_dataset_1k_public
|
8 |
-
2025-03-31 22:32:20,839 - guardbench.context - INFO - Successfully loaded dataset with 980 examples
|
9 |
-
2025-03-31 22:32:20,839 - guardbench.evaluator - INFO - Starting evaluation for model: got-r0mini-8
|
10 |
-
2025-03-31 22:32:20,839 - guardbench.evaluator - INFO - Using cached results for model: got-r0mini-8
|
11 |
-
2025-03-31 22:32:20,857 - guardbench.evaluator - INFO - Processing cached results for category: Political Corruption and Legal Evasion
|
12 |
-
2025-03-31 22:32:20,861 - guardbench.evaluator - INFO - Length Political Corruption and Legal Evasion - 30
|
13 |
-
2025-03-31 22:32:20,960 - guardbench.evaluator - INFO - Processing cached results for category: Creative Content Involving Illicit Themes
|
14 |
-
2025-03-31 22:32:20,963 - guardbench.evaluator - INFO - Length Creative Content Involving Illicit Themes - 30
|
15 |
-
2025-03-31 22:32:21,062 - guardbench.evaluator - INFO - Processing cached results for category: Financial Fraud and Unethical Business
|
16 |
-
2025-03-31 22:32:21,065 - guardbench.evaluator - INFO - Length Financial Fraud and Unethical Business - 30
|
17 |
-
2025-03-31 22:32:21,165 - guardbench.evaluator - INFO - Processing cached results for category: Manipulation, Deception, and Misinformation
|
18 |
-
2025-03-31 22:32:21,168 - guardbench.evaluator - INFO - Length Manipulation, Deception, and Misinformation - 30
|
19 |
-
2025-03-31 22:32:21,266 - guardbench.evaluator - INFO - Processing cached results for category: Drug– and Substance–Related Activities
|
20 |
-
2025-03-31 22:32:21,269 - guardbench.evaluator - INFO - Length Drug– and Substance–Related Activities - 30
|
21 |
-
2025-03-31 22:32:21,367 - guardbench.evaluator - INFO - Processing cached results for category: AI Manipulation and Jailbreaking
|
22 |
-
2025-03-31 22:32:21,371 - guardbench.evaluator - INFO - Length AI Manipulation and Jailbreaking - 30
|
23 |
-
2025-03-31 22:32:21,469 - guardbench.evaluator - INFO - Processing cached results for category: Sexual Content and Violence
|
24 |
-
2025-03-31 22:32:21,473 - guardbench.evaluator - INFO - Length Sexual Content and Violence - 29
|
25 |
-
2025-03-31 22:32:21,568 - guardbench.evaluator - INFO - Processing cached results for category: Cybercrime, Hacking, and Digital Exploits
|
26 |
-
2025-03-31 22:32:21,571 - guardbench.evaluator - INFO - Length Cybercrime, Hacking, and Digital Exploits - 30
|
27 |
-
2025-03-31 22:32:21,669 - guardbench.evaluator - INFO - Processing cached results for category: Safe Prompts
|
28 |
-
2025-03-31 22:32:21,673 - guardbench.evaluator - INFO - Length Safe Prompts - 490
|
29 |
-
2025-03-31 22:32:22,215 - guardbench.evaluator - INFO - Processing cached results for category: Child Exploitation and Abuse
|
30 |
-
2025-03-31 22:32:22,219 - guardbench.evaluator - INFO - Length Child Exploitation and Abuse - 30
|
31 |
-
2025-03-31 22:32:22,318 - guardbench.evaluator - INFO - Processing cached results for category: Labor Exploitation and Human Trafficking
|
32 |
-
2025-03-31 22:32:22,321 - guardbench.evaluator - INFO - Length Labor Exploitation and Human Trafficking - 30
|
33 |
-
2025-03-31 22:32:22,418 - guardbench.evaluator - INFO - Processing cached results for category: Self–Harm and Suicidal Ideation
|
34 |
-
2025-03-31 22:32:22,422 - guardbench.evaluator - INFO - Length Self–Harm and Suicidal Ideation - 13
|
35 |
-
2025-03-31 22:32:22,476 - guardbench.evaluator - INFO - Processing cached results for category: Criminal, Violent, and Terrorist Activity
|
36 |
-
2025-03-31 22:32:22,480 - guardbench.evaluator - INFO - Length Criminal, Violent, and Terrorist Activity - 30
|
37 |
-
2025-03-31 22:32:22,578 - guardbench.evaluator - INFO - Processing cached results for category: Hate Speech, Extremism, and Discrimination
|
38 |
-
2025-03-31 22:32:22,581 - guardbench.evaluator - INFO - Length Hate Speech, Extremism, and Discrimination - 29
|
39 |
-
2025-03-31 22:32:22,678 - guardbench.evaluator - INFO - Processing cached results for category: Environmental and Industrial Harm
|
40 |
-
2025-03-31 22:32:22,681 - guardbench.evaluator - INFO - Length Environmental and Industrial Harm - 30
|
41 |
-
2025-03-31 22:32:22,779 - guardbench.evaluator - INFO - Processing cached results for category: Animal Cruelty and Exploitation
|
42 |
-
2025-03-31 22:32:22,783 - guardbench.evaluator - INFO - Length Animal Cruelty and Exploitation - 30
|
43 |
-
2025-03-31 22:32:22,884 - guardbench.evaluator - INFO - Processing cached results for category: Academic Dishonesty and Cheating
|
44 |
-
2025-03-31 22:32:22,888 - guardbench.evaluator - INFO - Length Academic Dishonesty and Cheating - 29
|
45 |
-
2025-03-31 22:32:22,984 - guardbench.evaluator - INFO - Processing cached results for category: Weapon, Explosives, and Hazardous Materials
|
46 |
-
2025-03-31 22:32:22,987 - guardbench.evaluator - INFO - Length Weapon, Explosives, and Hazardous Materials - 30
|
47 |
-
2025-03-31 22:32:23,092 - guardbench.evaluator - INFO - Updated leaderboard for model: got-r0mini-8 from cached results
|
48 |
-
2025-03-31 22:32:23,093 - guardbench.evaluator - INFO - Evaluation from cached results completed for model: got-r0mini-8
|
49 |
-
2025-03-31 22:32:25,575 - __main__ - INFO - Refreshing leaderboard data after submission for version v0...
|
50 |
-
2025-03-31 22:32:25,790 - __main__ - INFO - Refreshed leaderboard data after submission
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
logs/guardbench_20250424_132721_81730502.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-04-24 13:27:22,432 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-04-24 13:27:22,600 - __main__ - INFO - Loaded leaderboard with 0 entries
|
|
|
|
|
|
logs/guardbench_20250424_132735_5fe7accd.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-04-24 13:27:35,986 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-04-24 13:27:36,096 - __main__ - INFO - Loaded leaderboard with 0 entries
|
|
|
|
|
|
logs/guardbench_20250424_133606_bfae8d28.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-04-24 13:36:07,557 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-04-24 13:36:07,754 - __main__ - INFO - Loaded leaderboard with 0 entries
|
|
|
|
|
|
logs/guardbench_20250424_133744_d3ca5956.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-04-24 13:37:44,999 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-04-24 13:37:45,167 - __main__ - INFO - Loaded leaderboard with 0 entries
|
|
|
|
|
|
logs/guardbench_20250424_133847_cf6f7f0f.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-04-24 13:38:48,713 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-04-24 13:38:48,956 - __main__ - INFO - Loaded leaderboard with 0 entries
|
|
|
|
|
|
logs/guardbench_20250424_133952_920f4d61.log
DELETED
@@ -1,2 +0,0 @@
|
|
1 |
-
2025-04-24 13:39:53,041 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-04-24 13:39:53,311 - __main__ - INFO - Loaded leaderboard with 0 entries
|
|
|
|
|
|
logs/guardbench_20250424_134044_2df3fadc.log
DELETED
@@ -1,17 +0,0 @@
|
|
1 |
-
2025-04-24 13:40:44,934 - __main__ - INFO - Initializing leaderboard data...
|
2 |
-
2025-04-24 13:40:45,088 - __main__ - INFO - Loaded leaderboard with 0 entries
|
3 |
-
2025-04-24 13:40:45,155 - __main__ - INFO - Available columns in LEADERBOARD_DF: ['model_name', 'model_type', 'guard_model_type', 'integral_score', 'macro_accuracy', 'macro_recall', 'micro_avg_error_ratio', 'micro_avg_runtime_ms', 'total_evals_count']
|
4 |
-
2025-04-24 13:40:45,158 - __main__ - WARNING - Initializing empty leaderboard
|
5 |
-
2025-04-24 13:40:45,672 - __main__ - WARNING - Initializing empty leaderboard
|
6 |
-
2025-04-24 13:40:45,758 - __main__ - WARNING - Initializing empty leaderboard
|
7 |
-
2025-04-24 13:40:45,862 - __main__ - WARNING - Initializing empty leaderboard
|
8 |
-
2025-04-24 13:40:45,950 - __main__ - WARNING - Initializing empty leaderboard
|
9 |
-
2025-04-24 13:40:46,035 - __main__ - WARNING - Initializing empty leaderboard
|
10 |
-
2025-04-24 13:40:46,122 - __main__ - WARNING - Initializing empty leaderboard
|
11 |
-
2025-04-24 13:40:46,389 - __main__ - WARNING - Initializing empty leaderboard
|
12 |
-
2025-04-24 13:40:46,473 - __main__ - WARNING - Initializing empty leaderboard
|
13 |
-
2025-04-24 13:40:46,593 - __main__ - WARNING - Initializing empty leaderboard
|
14 |
-
2025-04-24 13:40:46,686 - __main__ - WARNING - Initializing empty leaderboard
|
15 |
-
2025-04-24 13:40:46,869 - apscheduler.scheduler - INFO - Adding job tentatively -- it will be properly scheduled when the scheduler starts
|
16 |
-
2025-04-24 13:40:46,869 - apscheduler.scheduler - INFO - Added job "refresh_data" to job store "default"
|
17 |
-
2025-04-24 13:40:46,870 - apscheduler.scheduler - INFO - Scheduler started
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|