{"eval_library":{"additional_details":{"dataset":"hellaswag-fi","few_shot":"true","languages":"[\"fi\"]","litellm_version":null,"raw_results":"[{\"mcc\": 0.2874152145939662, \"accuracy\": 0.4609375, \"failed_instances\": []}, {\"mcc\": 0.3689394985583499, \"accuracy\": 0.51953125, \"failed_instances\": []}, {\"mcc\": 0.24015172175585892, \"accuracy\": 0.4140625, \"failed_instances\": []}, {\"mcc\": 0.26782014772882934, \"accuracy\": 0.453125, \"failed_instances\": []}, {\"mcc\": 0.2725681620485708, \"accuracy\": 0.45703125, \"failed_instances\": []}, {\"mcc\": 0.26324913333612415, \"accuracy\": 0.44921875, \"failed_instances\": []}, {\"mcc\": 0.2595302901098087, \"accuracy\": 0.43359375, \"failed_instances\": []}, {\"mcc\": 0.2416411472060516, \"accuracy\": 0.42578125, \"failed_instances\": []}, {\"mcc\": 0.18153354438766947, \"accuracy\": 0.37890625, \"failed_instances\": []}, {\"mcc\": 0.38098552714576495, \"accuracy\": 0.5234375, \"failed_instances\": []}]","task":"common-sense-reasoning","torch_version":"2.10.0","transformers_version":"4.57.6","validation_split":"true","vllm_version":"0.16.1rc1.dev281+g612e7729c","xgrammar_version":"0.1.29"},"name":"euroeval","version":"16.16.1.dev0"},"evaluation_id":"hellaswag-fi/CohereLabs/tiny-aya-water/1781766559","evaluation_results":[{"evaluation_name":"test_mcc","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":27.638343868709942,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":23.96044202684137,"method":"bootstrap","upper":31.316245710578514},"num_samples":10}},"source_data":{"dataset_name":"hellaswag-fi","source_type":"hf_dataset"}},{"evaluation_name":"test_accuracy","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":45.15625,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":42.41659121618474,"method":"bootstrap","upper":47.89590878381526},"num_samples":10}},"source_data":{"dataset_name":"hellaswag-fi","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:19.821249+00:00","model_info":{"additional_details":{"commercially_licensed":false,"generative":"true","generative_type":"instruction_tuned","max_sequence_length":"500000","merge":"false","model_url":"https://hf.co/CohereLabs/tiny-aya-water","num_model_parameters":"3349227520","open":true,"release_date":"2026-02-13","trained_from_scratch":true,"vocabulary_size":"262144"},"id":"CohereLabs/tiny-aya-water","inference_engine":{"name":"vllm","version":"0.16.1rc1.dev281+g612e7729c"},"name":"CohereLabs/tiny-aya-water"},"retrieved_timestamp":"1781766559","schema_version":"0.2.1","source_metadata":{"evaluator_relationship":"third_party","source_name":"EuroEval","source_organization_name":"EuroEval","source_organization_url":"https://euroeval.com","source_type":"evaluation_run"}}
