{"eval_library":{"additional_details":{"dataset":"allocine","few_shot":"true","languages":"[\"fr\"]","litellm_version":null,"raw_results":"[{\"mcc\": 0.06988478507864133, \"macro_f1\": 0.2909090909090909, \"failed_instances\": []}, {\"mcc\": 0.39838472810476044, \"macro_f1\": 0.5804509462280263, \"failed_instances\": []}, {\"mcc\": 0.32763603163228283, \"macro_f1\": 0.5152802109323849, \"failed_instances\": []}, {\"mcc\": 0.3763480815415215, \"macro_f1\": 0.5601145535016923, \"failed_instances\": []}, {\"mcc\": 0.16348734079150698, \"macro_f1\": 0.3727353727353727, \"failed_instances\": []}, {\"mcc\": 0.3454282083455378, \"macro_f1\": 0.5256964497337717, \"failed_instances\": []}, {\"mcc\": 0.22735269324866683, \"macro_f1\": 0.44325412807088205, \"failed_instances\": []}, {\"mcc\": 0.0, \"macro_f1\": 0.3245382585751979, \"failed_instances\": []}, {\"mcc\": 0.058363739034294745, \"macro_f1\": 0.32542819499341236, \"failed_instances\": []}, {\"mcc\": 0.3440455593940656, \"macro_f1\": 0.5272229822161423, \"failed_instances\": []}]","task":"sentiment-classification","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":"allocine/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":23.109311671712778,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":13.914961296555198,"method":"bootstrap","upper":32.30366204687036},"num_samples":10}},"source_data":{"dataset_name":"allocine","source_type":"hf_dataset"}},{"evaluation_name":"test_macro_f1","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":44.65630187895974,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":37.88040006738084,"method":"bootstrap","upper":51.432203690538635},"num_samples":10}},"source_data":{"dataset_name":"allocine","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:19.816810+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"}}
