{"eval_library":{"additional_details":{"dataset":"squad-it","few_shot":"true","languages":"[\"it\"]","litellm_version":null,"raw_results":"[{\"f1\": 64.13130373173226, \"em\": 48.333333333333336}, {\"f1\": 65.12451846453435, \"em\": 47.53601213040182}, {\"f1\": 63.94111438957976, \"em\": 47.63014763014763}, {\"f1\": 64.47268478455419, \"em\": 46.57534246575342}, {\"f1\": 65.19102615940504, \"em\": 47.64841942945258}, {\"f1\": 66.6500759997794, \"em\": 50.0763358778626}, {\"f1\": 65.51084198273418, \"em\": 48.28393135725429}, {\"f1\": 63.972897872926104, \"em\": 44.418238993710695}, {\"f1\": 65.90785285273036, \"em\": 51.0061919504644}, {\"f1\": 62.862120683406786, \"em\": 44.21296296296296}]","task":"reading-comprehension","torch_version":"2.7.0","transformers_version":"4.51.3","validation_split":"false","vllm_version":"0.9.1","xgrammar_version":"0.2.0"},"name":"euroeval","version":"15.10.0"},"evaluation_id":"squad-it/CohereForAI/aya-23-8B/1781766557","evaluation_results":[{"evaluation_name":"test_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":64.77644369213826,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":64.08688978019646,"method":"bootstrap","upper":65.46599760408006},"num_samples":10}},"source_data":{"dataset_name":"squad-it","source_type":"hf_dataset"}},{"evaluation_name":"test_em","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":47.572091613134376,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":46.242995332044885,"method":"bootstrap","upper":48.90118789422387},"num_samples":10}},"source_data":{"dataset_name":"squad-it","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:17.050948+00:00","model_info":{"additional_details":{"commercially_licensed":false,"generative":"true","generative_type":"instruction_tuned","max_sequence_length":"8192","merge":"false","model_url":"https://hf.co/CohereForAI/aya-23-8B","num_model_parameters":"8028033024","open":true,"release_date":"2024-05-23","trained_from_scratch":false,"vocabulary_size":"256000"},"id":"CohereForAI/aya-23-8B","inference_engine":{"name":"vllm","version":"0.9.1"},"name":"CohereForAI/aya-23-8B"},"retrieved_timestamp":"1781766557","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"}}
