ChocoLlama_ChocoLlama-2-7B-base.jsonl

{"schema_version": "0.2.1", "evaluation_id": "conll-nl/ChocoLlama/ChocoLlama-2-7B-base/1781766559", "evaluation_timestamp": "2026-06-18T07:09:19.322682+00:00", "retrieved_timestamp": "1781766559", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-base", "id": "ChocoLlama/ChocoLlama-2-7B-base", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-base"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "conll-nl", "languages": "[\"nl\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.3661344225770516, \"micro_f1\": 0.4052032520325203}, {\"micro_f1_no_misc\": 0.23040304665185657, \"micro_f1\": 0.2708333333333333}, {\"micro_f1_no_misc\": 0.27770700636942675, \"micro_f1\": 0.28991596638655465}, {\"micro_f1_no_misc\": 0.2585119798234552, \"micro_f1\": 0.22624815673056667}, {\"micro_f1_no_misc\": 0.2765826674861709, \"micro_f1\": 0.2921102921102921}, {\"micro_f1_no_misc\": 0.3427146419665123, \"micro_f1\": 0.3216630196936543}, {\"micro_f1_no_misc\": 0.29519071310116085, \"micro_f1\": 0.28519195612431447}, {\"micro_f1_no_misc\": 0.23471882640586797, \"micro_f1\": 0.25266030013642565}, {\"micro_f1_no_misc\": 0.2622601279317698, \"micro_f1\": 0.1883656509695291}, {\"micro_f1_no_misc\": 0.2603990530943524, \"micro_f1\": 0.2931498653903679}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "conll-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 28.046224854076247, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 25.331257350764144, "upper": 30.76119235738835, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "conll-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 28.253417929075585, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 24.6803413720208, "upper": 31.826494486130372, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "dbrd/ChocoLlama/ChocoLlama-2-7B-base/1781766559", "evaluation_timestamp": "2026-06-18T07:09:19.322719+00:00", "retrieved_timestamp": "1781766559", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-base", "id": "ChocoLlama/ChocoLlama-2-7B-base", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": "base", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-base"}, "inference_engine": {"name": "vllm", "version": "0.8.3"}}, "eval_library": {"name": "euroeval", "version": "15.7.1.dev0", "additional_details": {"dataset": "dbrd", "languages": "[\"nl\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.2", "torch_version": "2.6.0", "vllm_version": "0.8.3", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.8547207619978787, \"macro_f1\": 0.922620140801959}, {\"mcc\": 0.8492599617984316, \"macro_f1\": 0.9191606602932005}, {\"mcc\": 0.8564321945435739, \"macro_f1\": 0.9231454491782982}, {\"mcc\": 0.8132730888289299, \"macro_f1\": 0.8981292334676839}, {\"mcc\": 0.8929543739626086, \"macro_f1\": 0.9443078411559787}, {\"mcc\": 0.8076151049987809, \"macro_f1\": 0.8940360801628091}, {\"mcc\": 0.7483725602012397, \"macro_f1\": 0.8571072790437382}, {\"mcc\": 0.8170070236570004, \"macro_f1\": 0.9001429288462917}, {\"mcc\": 0.8276218070384522, \"macro_f1\": 0.9072237670067109}, {\"mcc\": 0.8098725820787439, \"macro_f1\": 0.8962830154941359}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "dbrd", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 82.7712945910564, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 80.36057706956865, "upper": 85.18201211254416, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "dbrd", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 90.62156395450806, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 89.17001234380822, "upper": 92.0731155652079, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "dutch-social/ChocoLlama/ChocoLlama-2-7B-base/1781766559", "evaluation_timestamp": "2026-06-18T07:09:19.322752+00:00", "retrieved_timestamp": "1781766559", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-base", "id": "ChocoLlama/ChocoLlama-2-7B-base", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-base"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "dutch-social", "languages": "[\"nl\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.08632494361048654, \"macro_f1\": 0.349763919009567}, {\"mcc\": 0.07492249547222496, \"macro_f1\": 0.33841881835713566}, {\"mcc\": 0.04870814856085148, \"macro_f1\": 0.36668811643972804}, {\"mcc\": 0.11455317831883098, \"macro_f1\": 0.4007717219015186}, {\"mcc\": 0.07841966578009998, \"macro_f1\": 0.37151087100651337}, {\"mcc\": 0.055217921203838734, \"macro_f1\": 0.3803809764432123}, {\"mcc\": 0.01487596169481396, \"macro_f1\": 0.3435085581733519}, {\"mcc\": 0.09935872267296374, \"macro_f1\": 0.3983271164153915}, {\"mcc\": -0.063335069452819, \"macro_f1\": 0.31342616365253256}, {\"mcc\": 0.1319412117211712, \"macro_f1\": 0.4339174739095808}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "dutch-social", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 6.409871795824626, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 2.941307878374637, "upper": 9.878435713274614, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "dutch-social", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 36.96713735308531, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 34.77443063840263, "upper": 39.159844067768, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "hellaswag-nl/ChocoLlama/ChocoLlama-2-7B-base/1781766559", "evaluation_timestamp": "2026-06-18T07:09:19.322784+00:00", "retrieved_timestamp": "1781766559", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-base", "id": "ChocoLlama/ChocoLlama-2-7B-base", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-base"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "hellaswag-nl", "languages": "[\"nl\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.03883053300602004, \"accuracy\": 0.275390625}, {\"mcc\": -0.0016080282615326261, \"accuracy\": 0.24755859375}, {\"mcc\": 0.018594055393654354, \"accuracy\": 0.2529296875}, {\"mcc\": 0.04002997351906259, \"accuracy\": 0.25048828125}, {\"mcc\": 0.04492757572386442, \"accuracy\": 0.27294921875}, {\"mcc\": 0.020040142133200253, \"accuracy\": 0.24267578125}, {\"mcc\": 0.04162782495078157, \"accuracy\": 0.27490234375}, {\"mcc\": 0.041903249658160634, \"accuracy\": 0.25634765625}, {\"mcc\": 0.043670124318373506, \"accuracy\": 0.27880859375}, {\"mcc\": 0.016138217843667476, \"accuracy\": 0.26025390625}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 3.0415366828525228, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 2.0541680717186193, "upper": 4.028905293986426, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 26.123046875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 25.303370110349427, "upper": 26.942723639650573, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "mmlu-nl/ChocoLlama/ChocoLlama-2-7B-base/1781766559", "evaluation_timestamp": "2026-06-18T07:09:19.322815+00:00", "retrieved_timestamp": "1781766559", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-base", "id": "ChocoLlama/ChocoLlama-2-7B-base", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-base"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "mmlu-nl", "languages": "[\"nl\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.06898887985495544, \"accuracy\": 0.30419921875}, {\"mcc\": 0.11017537277067622, \"accuracy\": 0.3232421875}, {\"mcc\": 0.1066180913584559, \"accuracy\": 0.30615234375}, {\"mcc\": 0.07150122741409028, \"accuracy\": 0.2783203125}, {\"mcc\": 0.08169156517197082, \"accuracy\": 0.29052734375}, {\"mcc\": 0.08697068507711422, \"accuracy\": 0.29541015625}, {\"mcc\": 0.09051062244283763, \"accuracy\": 0.2890625}, {\"mcc\": 0.06539145392678453, \"accuracy\": 0.271484375}, {\"mcc\": 0.06399590821144166, \"accuracy\": 0.27978515625}, {\"mcc\": 0.07781898484595225, \"accuracy\": 0.296875}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 8.23662791074279, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 7.22601194822251, "upper": 9.24724387326307, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 29.3505859375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 28.402480753546406, "upper": 30.298691121453594, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "scala-nl/ChocoLlama/ChocoLlama-2-7B-base/1781766559", "evaluation_timestamp": "2026-06-18T07:09:19.322846+00:00", "retrieved_timestamp": "1781766559", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-base", "id": "ChocoLlama/ChocoLlama-2-7B-base", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-base"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "scala-nl", "languages": "[\"nl\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.15413274541417468, \"macro_f1\": 0.4376984529960598}, {\"mcc\": 0.16611273385271413, \"macro_f1\": 0.5548872029317061}, {\"mcc\": 0.10981055511052823, \"macro_f1\": 0.4528075845722904}, {\"mcc\": 0.14885611684634925, \"macro_f1\": 0.4761839179963405}, {\"mcc\": 0.18500131554382093, \"macro_f1\": 0.5629430184088234}, {\"mcc\": 0.15452828828503345, \"macro_f1\": 0.407668675952412}, {\"mcc\": 0.1567902350072, \"macro_f1\": 0.4308577212372684}, {\"mcc\": 0.18990689581810707, \"macro_f1\": 0.583876509725956}, {\"mcc\": 0.10717969023131996, \"macro_f1\": 0.44061650640472205}, {\"mcc\": 0.10684482468031632, \"macro_f1\": 0.3681733802416582}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 14.791634007895643, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 12.894716195342994, "upper": 16.688551820448293, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 47.15712970467237, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 42.68697435451978, "upper": 51.62728505482496, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "speed/ChocoLlama/ChocoLlama-2-7B-base/1781766559", "evaluation_timestamp": "2026-06-18T07:09:19.322885+00:00", "retrieved_timestamp": "1781766559", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-base", "id": "ChocoLlama/ChocoLlama-2-7B-base", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-base"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "speed", "languages": "[\"ab\", \"aa\", \"af\", \"sq\", \"am\", \"ar\", \"an\", \"hy\", \"as\", \"av\", \"ae\", \"ay\", \"az\", \"bm\", \"ba\", \"eu\", \"be\", \"bn\", \"bi\", \"bs\", \"br\", \"bg\", \"my\", \"ca\", \"ch\", \"ce\", \"ny\", \"zh\", \"cu\", \"cv\", \"kw\", \"co\", \"cr\", \"hr\", \"cs\", \"da\", \"dv\", \"nl\", \"dz\", \"en\", \"eo\", \"et\", \"ee\", \"fo\", \"fj\", \"fi\", \"fr\", \"fy\", \"ff\", \"gd\", \"gl\", \"lg\", \"ka\", \"de\", \"el\", \"kl\", \"gn\", \"gu\", \"ht\", \"ha\", \"he\", \"hz\", \"hi\", \"ho\", \"hu\", \"is\", \"io\", \"ig\", \"id\", \"ia\", \"ie\", \"iu\", \"ik\", \"ga\", \"it\", \"ja\", \"kn\", \"kr\", \"ks\", \"kk\", \"km\", \"ki\", \"rw\", \"ky\", \"kv\", \"kg\", \"ko\", \"kj\", \"ku\", \"lo\", \"la\", \"lv\", \"li\", \"ln\", \"lt\", \"lu\", \"lb\", \"mk\", \"mg\", \"ms\", \"ml\", \"mt\", \"gv\", \"mi\", \"mr\", \"mh\", \"mn\", \"na\", \"nv\", \"nd\", \"nr\", \"ng\", \"ne\", \"no\", \"nb\", \"nn\", \"ii\", \"oc\", \"oj\", \"or\", \"om\", \"os\", \"pi\", \"ps\", \"fa\", \"pl\", \"pt\", \"pa\", \"qu\", \"ro\", \"rm\", \"rn\", \"ru\", \"se\", \"sm\", \"sg\", \"sa\", \"sc\", \"sr\", \"sn\", \"sd\", \"si\", \"sk\", \"sl\", \"so\", \"st\", \"es\", \"su\", \"sw\", \"ss\", \"sv\", \"tl\", \"ty\", \"tg\", \"ta\", \"tt\", \"te\", \"th\", \"bo\", \"ti\", \"to\", \"ts\", \"tn\", \"tr\", \"tk\", \"tw\", \"ug\", \"uk\", \"ur\", \"uz\", \"ve\", \"vi\", \"vo\", \"wa\", \"cy\", \"wo\", \"xh\", \"yi\", \"yo\", \"za\", \"zu\"]", "task": "speed", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_speed\": 856.97, \"test_speed_short\": 98.96}, {\"test_speed\": 1625.73, \"test_speed_short\": 184.5}, {\"test_speed\": 2122.6600000000003, \"test_speed_short\": 353.79999999999995}, {\"test_speed\": 2784.71, \"test_speed_short\": 438.12}, {\"test_speed\": 3162.5099999999998, \"test_speed_short\": 521.16}, {\"test_speed\": 3502.7200000000003, \"test_speed_short\": 690.27}, {\"test_speed\": 3903.4500000000003, \"test_speed_short\": 773.12}, {\"test_speed\": 4151.400000000001, \"test_speed_short\": 857.68}, {\"test_speed\": 4385.45, \"test_speed_short\": 938.3399999999999}, {\"test_speed\": 4542.4800000000005, \"test_speed_short\": 1015.7499999999999}]"}}, "evaluation_results": [{"evaluation_name": "test_speed", "source_data": {"dataset_name": "speed", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false}, "score_details": {"score": 3103.808, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 2333.2815327536373, "upper": 3874.3344672463627, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_speed_short", "source_data": {"dataset_name": "speed", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false}, "score_details": {"score": 587.17, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 390.4189329248577, "upper": 783.9210670751422, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "squad-nl/ChocoLlama/ChocoLlama-2-7B-base/1781766559", "evaluation_timestamp": "2026-06-18T07:09:19.322926+00:00", "retrieved_timestamp": "1781766559", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-base", "id": "ChocoLlama/ChocoLlama-2-7B-base", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-base"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "squad-nl", "languages": "[\"nl\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 74.271537261787, \"em\": 60.75757575757576}, {\"f1\": 73.78845010335733, \"em\": 61.25852918877938}, {\"f1\": 65.76149583718447, \"em\": 54.07925407925408}, {\"f1\": 68.44203972235618, \"em\": 57.534246575342465}, {\"f1\": 72.69377451002514, \"em\": 61.141094834232845}, {\"f1\": 74.2768986615711, \"em\": 59.847328244274806}, {\"f1\": 70.23724292318683, \"em\": 58.11232449297972}, {\"f1\": 70.46153777290218, \"em\": 59.43396226415094}, {\"f1\": 69.83320252493739, \"em\": 60.139318885448915}, {\"f1\": 71.60988011734432, \"em\": 57.407407407407405}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "squad-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 71.1376059434652, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 69.42784135181606, "upper": 72.84737053511435, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "squad-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 58.97110417294463, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.59047012418889, "upper": 60.351738221700366, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}