1 line
3.5 KiB
JSON
1 line
3.5 KiB
JSON
{"repo": "chusi-truth/grid-visual-cot", "files": {"eval/2026-04-02_api_baseline_gemini3flash_reachable100_tok2048/metadata.json": {"47d7e79a8eebd5c1b990cff731a5f5363dd56aad": {"t": 1785768973.7569158, "n": 455, "h": "70e9aec60e6dc5d1", "c": "{\n \"timestamp\": \"2026-04-02T23:31:16.767872+08:00\",\n \"api_mode\": \"chat\",\n \"model\": \"gemini-3-flash-preview\",\n \"api_base_url\": \"https://aihubmix.com/v1\",\n \"dataset_path\": \"eval/2026-03-30_reachable_holdout100_bfs/grid_cot_test_reachable_100.json\",\n \"max_output_tokens\": 2048,\n \"temperature\": 0.0,\n \"max_retries\": 3,\n \"retry_sleep\": 2.0,\n \"request_timeout\": 180.0,\n \"prompt_mode\": \"text_only\",\n \"note\": \"API baseline eval on provided dataset.\"\n}"}}, "eval/2026-03-30_api_baseline_gemini31pro_reachable100_smoke1/metadata.json": {"47d7e79a8eebd5c1b990cff731a5f5363dd56aad": {"t": 1785768973.8255167, "n": 451, "h": "16b983e890568163", "c": "{\n \"timestamp\": \"2026-03-30T14:55:03.990790+08:00\",\n \"api_mode\": \"chat\",\n \"model\": \"gemini-3.1-pro-preview\",\n \"api_base_url\": \"https://aihubmix.com/v1\",\n \"dataset_path\": \"eval/2026-03-27_reachable_holdout100/grid_cot_test_reachable_100.json\",\n \"max_output_tokens\": 1024,\n \"temperature\": 0.0,\n \"max_retries\": 3,\n \"retry_sleep\": 2.0,\n \"request_timeout\": 180.0,\n \"prompt_mode\": \"text_only\",\n \"note\": \"API baseline eval on provided dataset.\"\n}"}}, "eval/2026-03-30_api_baseline_gemini31pro_reachable100_smoke1_tok4096/metadata.json": {"47d7e79a8eebd5c1b990cff731a5f5363dd56aad": {"t": 1785768974.488105, "n": 451, "h": "999e215582df2447", "c": "{\n \"timestamp\": \"2026-03-30T14:59:12.043872+08:00\",\n \"api_mode\": \"chat\",\n \"model\": \"gemini-3.1-pro-preview\",\n \"api_base_url\": \"https://aihubmix.com/v1\",\n \"dataset_path\": \"eval/2026-03-27_reachable_holdout100/grid_cot_test_reachable_100.json\",\n \"max_output_tokens\": 4096,\n \"temperature\": 0.0,\n \"max_retries\": 3,\n \"retry_sleep\": 2.0,\n \"request_timeout\": 180.0,\n \"prompt_mode\": \"text_only\",\n \"note\": \"API baseline eval on provided dataset.\"\n}"}}, "eval/2026-03-30_api_baseline_gemini31pro_reachable100_first50_tok4096/metadata.json": {"47d7e79a8eebd5c1b990cff731a5f5363dd56aad": {"t": 1785768974.9703596, "n": 451, "h": "1583630b101bd5f8", "c": "{\n \"timestamp\": \"2026-03-30T15:43:38.305904+08:00\",\n \"api_mode\": \"chat\",\n \"model\": \"gemini-3.1-pro-preview\",\n \"api_base_url\": \"https://aihubmix.com/v1\",\n \"dataset_path\": \"eval/2026-03-27_reachable_holdout100/grid_cot_test_reachable_100.json\",\n \"max_output_tokens\": 4096,\n \"temperature\": 0.0,\n \"max_retries\": 3,\n \"retry_sleep\": 2.0,\n \"request_timeout\": 180.0,\n \"prompt_mode\": \"text_only\",\n \"note\": \"API baseline eval on provided dataset.\"\n}"}}, "eval/2026-03-30_api_baseline_gemini31pro_reachable100_smoke3_tok4096/metadata.json": {"47d7e79a8eebd5c1b990cff731a5f5363dd56aad": {"t": 1785768976.2816515, "n": 451, "h": "8659aa85a991a693", "c": "{\n \"timestamp\": \"2026-03-30T15:07:42.263956+08:00\",\n \"api_mode\": \"chat\",\n \"model\": \"gemini-3.1-pro-preview\",\n \"api_base_url\": \"https://aihubmix.com/v1\",\n \"dataset_path\": \"eval/2026-03-27_reachable_holdout100/grid_cot_test_reachable_100.json\",\n \"max_output_tokens\": 4096,\n \"temperature\": 0.0,\n \"max_retries\": 3,\n \"retry_sleep\": 2.0,\n \"request_timeout\": 180.0,\n \"prompt_mode\": \"text_only\",\n \"note\": \"API baseline eval on provided dataset.\"\n}"}}}} |