| {"result": {"arc": 0.7295}, "time": "20240619-110533"} | |
| {"result": {"gsm8k": 0.4943}, "time": "20240619-110618"} | |
| {"result": {"ceval": 0.5594}, "time": "20240619-111828"} | |
| {"result": {"bbh": 0.1474}, "time": "20240619-111950"} | |
| {"result": {"mmlu": 0.3756}, "time": "20240619-112007"} | |
| {"result": {"arc": 0.7295}, "time": "20240619-112022"} | |
| {"result": {"gsm8k": 0.4943}, "time": "20240619-112058"} | |
| {"result": {"mmlu": 0.3758}, "time": "20240619-112312"} | |
| {"result": {"ceval": 0.5594}, "time": "20240619-112625"} | |
| {"result": {"bbh": 0.1474}, "time": "20240619-112729"} | |
| {"result": {"EvalFormatSingleChoiceExam95207": 0.7644}, "time": "20240619-115821"} | |
| {"result": {"EvalFormatSingleChoiceExam95207": 0.5335}, "time": "20240619-121837"} | |
| {"result": {"EvalFormatSingleChoiceExam2579": 0.4618}, "time": "20240624-154539"} | |
| {"result": {"EvalFormatSingleChoiceExam2579": 0.3563}, "time": "20240627-183455"} | |