summaryrefslogtreecommitdiff
path: root/full_experiment/experiment.log
diff options
context:
space:
mode:
Diffstat (limited to 'full_experiment/experiment.log')
-rw-r--r--full_experiment/experiment.log223
1 files changed, 223 insertions, 0 deletions
diff --git a/full_experiment/experiment.log b/full_experiment/experiment.log
index a1d7c01..1dd792e 100644
--- a/full_experiment/experiment.log
+++ b/full_experiment/experiment.log
@@ -29036,3 +29036,226 @@ The summary has been generated and saved to **/summary.txt**.
[INFO] INCOMPLETE: 0
[INFO] ============================================================
+[INFO]
+============================================================
+[INFO] Starting Experiment Run
+[INFO] ============================================================
+
+[INFO]
+--- Baseline exists: gemini-3.1-pro-preview | corporate_sabotage_v2 ---
+[INFO]
+--- Running: gemini-3.1-pro-preview | corporate_sabotage_v2 | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: gemini-3.1-pro-preview | corporate_sabotage_v2 ---
+[INFO]
+--- Running: gemini-3.1-pro-preview | corporate_sabotage_v2 | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: gemini-3.1-pro-preview | corporate_sabotage_v2 ---
+[INFO]
+--- Running: gemini-3.1-pro-preview | corporate_sabotage_v2 | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: gemini-3.1-pro-preview | child_protection ---
+[INFO]
+--- Running: gemini-3.1-pro-preview | child_protection | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: gemini-3.1-pro-preview | child_protection ---
+[INFO]
+--- Running: gemini-3.1-pro-preview | child_protection | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: gemini-3.1-pro-preview | child_protection ---
+[INFO]
+--- Running: gemini-3.1-pro-preview | child_protection | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: moonshotai/kimi-k2.5 | corporate_sabotage_v2 ---
+[INFO]
+--- Running: moonshotai/kimi-k2.5 | corporate_sabotage_v2 | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: moonshotai/kimi-k2.5 | corporate_sabotage_v2 ---
+[INFO]
+--- Running: moonshotai/kimi-k2.5 | corporate_sabotage_v2 | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: moonshotai/kimi-k2.5 | corporate_sabotage_v2 ---
+[INFO]
+--- Running: moonshotai/kimi-k2.5 | corporate_sabotage_v2 | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: moonshotai/kimi-k2.5 | child_protection ---
+[INFO]
+--- Running: moonshotai/kimi-k2.5 | child_protection | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: moonshotai/kimi-k2.5 | child_protection ---
+[INFO]
+--- Running: moonshotai/kimi-k2.5 | child_protection | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: moonshotai/kimi-k2.5 | child_protection ---
+[INFO]
+--- Running: moonshotai/kimi-k2.5 | child_protection | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: qwen/qwen3-max-thinking | corporate_sabotage_v2 ---
+[INFO]
+--- Running: qwen/qwen3-max-thinking | corporate_sabotage_v2 | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: qwen/qwen3-max-thinking | corporate_sabotage_v2 ---
+[INFO]
+--- Running: qwen/qwen3-max-thinking | corporate_sabotage_v2 | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: qwen/qwen3-max-thinking | corporate_sabotage_v2 ---
+[INFO]
+--- Running: qwen/qwen3-max-thinking | corporate_sabotage_v2 | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: qwen/qwen3-max-thinking | child_protection ---
+[INFO]
+--- Running: qwen/qwen3-max-thinking | child_protection | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: qwen/qwen3-max-thinking | child_protection ---
+[INFO]
+--- Running: qwen/qwen3-max-thinking | child_protection | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: qwen/qwen3-max-thinking | child_protection ---
+[INFO]
+--- Running: qwen/qwen3-max-thinking | child_protection | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: z-ai/glm-4.7-flash | corporate_sabotage_v2 ---
+[INFO]
+--- Running: z-ai/glm-4.7-flash | corporate_sabotage_v2 | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: z-ai/glm-4.7-flash | corporate_sabotage_v2 ---
+[INFO]
+--- Running: z-ai/glm-4.7-flash | corporate_sabotage_v2 | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: z-ai/glm-4.7-flash | corporate_sabotage_v2 ---
+[INFO]
+--- Running: z-ai/glm-4.7-flash | corporate_sabotage_v2 | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: z-ai/glm-4.7-flash | child_protection ---
+[INFO]
+--- Running: z-ai/glm-4.7-flash | child_protection | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: z-ai/glm-4.7-flash | child_protection ---
+[INFO]
+--- Running: z-ai/glm-4.7-flash | child_protection | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: z-ai/glm-4.7-flash | child_protection ---
+[INFO]
+--- Running: z-ai/glm-4.7-flash | child_protection | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: deepseek/deepseek-v3.2 | corporate_sabotage_v2 ---
+[INFO]
+--- Running: deepseek/deepseek-v3.2 | corporate_sabotage_v2 | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: deepseek/deepseek-v3.2 | corporate_sabotage_v2 ---
+[INFO]
+--- Running: deepseek/deepseek-v3.2 | corporate_sabotage_v2 | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: deepseek/deepseek-v3.2 | corporate_sabotage_v2 ---
+[INFO]
+--- Running: deepseek/deepseek-v3.2 | corporate_sabotage_v2 | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: deepseek/deepseek-v3.2 | child_protection ---
+[INFO]
+--- Running: deepseek/deepseek-v3.2 | child_protection | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: deepseek/deepseek-v3.2 | child_protection ---
+[INFO]
+--- Running: deepseek/deepseek-v3.2 | child_protection | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: deepseek/deepseek-v3.2 | child_protection ---
+[INFO]
+--- Running: deepseek/deepseek-v3.2 | child_protection | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-20b | corporate_sabotage_v2 ---
+[INFO]
+--- Running: openai/gpt-oss-20b | corporate_sabotage_v2 | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-20b | corporate_sabotage_v2 ---
+[INFO]
+--- Running: openai/gpt-oss-20b | corporate_sabotage_v2 | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-20b | corporate_sabotage_v2 ---
+[INFO]
+--- Running: openai/gpt-oss-20b | corporate_sabotage_v2 | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-20b | child_protection ---
+[INFO]
+--- Running: openai/gpt-oss-20b | child_protection | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-20b | child_protection ---
+[INFO]
+--- Running: openai/gpt-oss-20b | child_protection | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-20b | child_protection ---
+[INFO]
+--- Running: openai/gpt-oss-20b | child_protection | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-safeguard-20b | corporate_sabotage_v2 ---
+[INFO]
+--- Running: openai/gpt-oss-safeguard-20b | corporate_sabotage_v2 | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-safeguard-20b | corporate_sabotage_v2 ---
+[INFO]
+--- Running: openai/gpt-oss-safeguard-20b | corporate_sabotage_v2 | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-safeguard-20b | corporate_sabotage_v2 ---
+[INFO]
+--- Running: openai/gpt-oss-safeguard-20b | corporate_sabotage_v2 | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-safeguard-20b | child_protection ---
+[INFO]
+--- Running: openai/gpt-oss-safeguard-20b | child_protection | mid ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-safeguard-20b | child_protection ---
+[INFO]
+--- Running: openai/gpt-oss-safeguard-20b | child_protection | low ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+--- Baseline exists: openai/gpt-oss-safeguard-20b | child_protection ---
+[INFO]
+--- Running: openai/gpt-oss-safeguard-20b | child_protection | high ---
+[INFO] SKIP: 10/10 runs already exist
+[INFO]
+============================================================
+[INFO] Experiment Complete: 420 total runs
+[INFO] SKIPPED: 420
+[INFO] SUCCESS: 0
+[INFO] INCOMPLETE: 0
+[INFO] ============================================================
+
generated by cgit v1.2.3 (git 2.46.0) at 2026-09-26 14:50:55 +0000