AiLab-IMCS-UL_lvbert.jsonl

{"schema_version": "0.2.1", "evaluation_id": "atsiliepimai/AiLab-IMCS-UL/lvbert/1781766556", "evaluation_timestamp": "2026-06-18T07:09:16.547163+00:00", "retrieved_timestamp": "1781766556", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "atsiliepimai", "languages": "[\"lt\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 1.0003571510314941, \"test_mcc\": 0.05294702308274401, \"test_macro_f1\": 0.2752973511071375, \"test_runtime\": 1.1876, \"test_samples_per_second\": 865.6, \"test_steps_per_second\": 27.787, \"epoch\": 5.625}, {\"test_loss\": 0.9476094841957092, \"test_mcc\": 0.1633660274743694, \"test_macro_f1\": 0.40513646294722666, \"test_runtime\": 1.1618, \"test_samples_per_second\": 884.868, \"test_steps_per_second\": 28.405, \"epoch\": 7.5}, {\"test_loss\": 0.9968119263648987, \"test_mcc\": 0.03894765466633349, \"test_macro_f1\": 0.23877198983401193, \"test_runtime\": 1.157, \"test_samples_per_second\": 888.476, \"test_steps_per_second\": 28.521, \"epoch\": 5.625}, {\"test_loss\": 1.0457241535186768, \"test_mcc\": 0.18499974657594992, \"test_macro_f1\": 0.49289958759752217, \"test_runtime\": 1.1566, \"test_samples_per_second\": 888.801, \"test_steps_per_second\": 28.532, \"epoch\": 9.375}, {\"test_loss\": 0.9910893440246582, \"test_mcc\": -0.03274893280344485, \"test_macro_f1\": 0.222582172553908, \"test_runtime\": 1.1676, \"test_samples_per_second\": 880.432, \"test_steps_per_second\": 28.263, \"epoch\": 5.625}, {\"test_loss\": 1.0065908432006836, \"test_mcc\": 0.0993042251090968, \"test_macro_f1\": 0.32607335793268943, \"test_runtime\": 1.1765, \"test_samples_per_second\": 873.79, \"test_steps_per_second\": 28.05, \"epoch\": 7.5}, {\"test_loss\": 0.9802825450897217, \"test_mcc\": 0.05710309678679003, \"test_macro_f1\": 0.2660952161643311, \"test_runtime\": 1.1971, \"test_samples_per_second\": 858.754, \"test_steps_per_second\": 27.567, \"epoch\": 5.625}, {\"test_loss\": 0.9992856383323669, \"test_mcc\": 0.018047493327913226, \"test_macro_f1\": 0.24714619005957586, \"test_runtime\": 1.1674, \"test_samples_per_second\": 880.626, \"test_steps_per_second\": 28.269, \"epoch\": 5.625}, {\"test_loss\": 1.0041152238845825, \"test_mcc\": 0.02830445605787282, \"test_macro_f1\": 0.3001353239043129, \"test_runtime\": 1.1601, \"test_samples_per_second\": 886.164, \"test_steps_per_second\": 28.447, \"epoch\": 5.625}, {\"test_loss\": 1.0177586078643799, \"test_mcc\": 0.09994962805406198, \"test_macro_f1\": 0.4291496463976177, \"test_runtime\": 1.188, \"test_samples_per_second\": 865.307, \"test_steps_per_second\": 27.777, \"epoch\": 7.5}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "atsiliepimai", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 7.102204183316868, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 2.964806836650535, "upper": 11.2396015299832, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "atsiliepimai", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 32.032872984983335, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 26.345251017995935, "upper": 37.720494951970736, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "atsiliepimai/AiLab-IMCS-UL/lvbert/1782214648", "evaluation_timestamp": "2026-06-23T11:37:28.669976+00:00", "retrieved_timestamp": "1782214648", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.5.0.dev0", "additional_details": {"dataset": "atsiliepimai", "languages": "[\"lt\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "true", "use_bits_per_character": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 1.0136566162109375, \"test_mcc\": 0.034636442941310595, \"test_macro_f1\": 0.3078062070599384, \"test_runtime\": 1.1726, \"test_samples_per_second\": 218.315, \"test_steps_per_second\": 6.822, \"epoch\": 5.625}, {\"test_loss\": 1.02978515625, \"test_mcc\": 0.0813627181771454, \"test_macro_f1\": 0.3657411526137935, \"test_runtime\": 1.1704, \"test_samples_per_second\": 218.731, \"test_steps_per_second\": 6.835, \"epoch\": 7.5}, {\"test_loss\": 1.01953125, \"test_mcc\": 0.028806419780164676, \"test_macro_f1\": 0.25339778618467146, \"test_runtime\": 1.1738, \"test_samples_per_second\": 218.088, \"test_steps_per_second\": 6.815, \"epoch\": 5.625}, {\"test_loss\": 0.972930908203125, \"test_mcc\": 0.1444452142026832, \"test_macro_f1\": 0.42306449941796326, \"test_runtime\": 1.1896, \"test_samples_per_second\": 215.205, \"test_steps_per_second\": 6.725, \"epoch\": 7.5}, {\"test_loss\": 0.9939422607421875, \"test_mcc\": 0.14434544546710915, \"test_macro_f1\": 0.25599546684214375, \"test_runtime\": 1.1591, \"test_samples_per_second\": 220.853, \"test_steps_per_second\": 6.902, \"epoch\": 5.625}, {\"test_loss\": 0.9552993774414062, \"test_mcc\": -0.05605216843763488, \"test_macro_f1\": 0.2655505020543581, \"test_runtime\": 1.1699, \"test_samples_per_second\": 218.823, \"test_steps_per_second\": 6.838, \"epoch\": 7.5}, {\"test_loss\": 0.9451408386230469, \"test_mcc\": 0.16320403600645572, \"test_macro_f1\": 0.45717363020285323, \"test_runtime\": 1.1747, \"test_samples_per_second\": 217.927, \"test_steps_per_second\": 6.81, \"epoch\": 7.5}, {\"test_loss\": 1.0360107421875, \"test_mcc\": 0.048476921083504564, \"test_macro_f1\": 0.2950490072882634, \"test_runtime\": 1.1655, \"test_samples_per_second\": 219.639, \"test_steps_per_second\": 6.864, \"epoch\": 5.625}, {\"test_loss\": 1.018707275390625, \"test_mcc\": -0.005750162267354156, \"test_macro_f1\": 0.29890560875513, \"test_runtime\": 1.0093, \"test_samples_per_second\": 253.65, \"test_steps_per_second\": 7.927, \"epoch\": 5.625}, {\"test_loss\": 0.9454498291015625, \"test_mcc\": 0.06449686478154465, \"test_macro_f1\": 0.2782106782106782, \"test_runtime\": 1.1737, \"test_samples_per_second\": 218.106, \"test_steps_per_second\": 6.816, \"epoch\": 5.625}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "atsiliepimai", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 6.47971731734929, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 2.11248814909829, "upper": 10.84694648560029, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "atsiliepimai", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 32.00894538629793, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 27.578265627117297, "upper": 36.439625145478566, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "fullstack-ner-lv/AiLab-IMCS-UL/lvbert/1781785699", "evaluation_timestamp": "2026-06-18T12:28:19.752867+00:00", "retrieved_timestamp": "1781785699", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "fullstack-ner-lv", "languages": "[\"lv\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.13627281785011292, \"test_micro_f1_no_misc\": 0.7905366416618582, \"test_micro_f1\": 0.7313080434440421, \"test_runtime\": 4.5546, \"test_samples_per_second\": 449.653, \"test_steps_per_second\": 14.052, \"epoch\": 5.625}, {\"test_loss\": 0.10943156480789185, \"test_micro_f1_no_misc\": 0.7964740450538689, \"test_micro_f1\": 0.7471992206527034, \"test_runtime\": 4.4666, \"test_samples_per_second\": 458.511, \"test_steps_per_second\": 14.328, \"epoch\": 5.625}, {\"test_loss\": 0.12279541045427322, \"test_micro_f1_no_misc\": 0.792044111855061, \"test_micro_f1\": 0.7493755203996669, \"test_runtime\": 3.6576, \"test_samples_per_second\": 559.925, \"test_steps_per_second\": 17.498, \"epoch\": 6.5625}, {\"test_loss\": 0.12428943067789078, \"test_micro_f1_no_misc\": 0.8034066713981547, \"test_micro_f1\": 0.7539589442815249, \"test_runtime\": 4.0959, \"test_samples_per_second\": 500.014, \"test_steps_per_second\": 15.625, \"epoch\": 6.5625}, {\"test_loss\": 0.13076692819595337, \"test_micro_f1_no_misc\": 0.7192228656827948, \"test_micro_f1\": 0.6959208899876391, \"test_runtime\": 4.0198, \"test_samples_per_second\": 509.484, \"test_steps_per_second\": 15.921, \"epoch\": 4.6875}, {\"test_loss\": 0.1616959273815155, \"test_micro_f1_no_misc\": 0.7231023102310231, \"test_micro_f1\": 0.6849842011265285, \"test_runtime\": 3.1743, \"test_samples_per_second\": 645.19, \"test_steps_per_second\": 20.162, \"epoch\": 4.6875}, {\"test_loss\": 0.1414448767900467, \"test_micro_f1_no_misc\": 0.7466816227332211, \"test_micro_f1\": 0.6729368932038835, \"test_runtime\": 2.8042, \"test_samples_per_second\": 730.328, \"test_steps_per_second\": 22.823, \"epoch\": 4.6875}, {\"test_loss\": 0.11556355655193329, \"test_micro_f1_no_misc\": 0.8144813355843182, \"test_micro_f1\": 0.7627383557361677, \"test_runtime\": 3.1895, \"test_samples_per_second\": 642.112, \"test_steps_per_second\": 20.066, \"epoch\": 6.5625}, {\"test_loss\": 0.12134446948766708, \"test_micro_f1_no_misc\": 0.816057293629853, \"test_micro_f1\": 0.749221183800623, \"test_runtime\": 4.5214, \"test_samples_per_second\": 452.961, \"test_steps_per_second\": 14.155, \"epoch\": 5.625}, {\"test_loss\": 0.12275354564189911, \"test_micro_f1_no_misc\": 0.8276241069793001, \"test_micro_f1\": 0.7735244776574653, \"test_runtime\": 2.7933, \"test_samples_per_second\": 733.175, \"test_steps_per_second\": 22.912, \"epoch\": 7.5}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "fullstack-ner-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 78.29631004809453, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 75.8705144256601, "upper": 80.72210567052895, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "fullstack-ner-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 73.21167730290246, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 71.04660922563562, "upper": 75.3767453801693, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "fullstack-ner-lv/AiLab-IMCS-UL/lvbert/1782218995", "evaluation_timestamp": "2026-06-23T12:49:55.535337+00:00", "retrieved_timestamp": "1782218995", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.5.0.dev0", "additional_details": {"dataset": "fullstack-ner-lv", "languages": "[\"lv\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "true", "use_bits_per_character": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.18393352627754211, \"test_micro_f1_no_misc\": 0.7859649122807018, \"test_micro_f1\": 0.6867305061559508, \"test_runtime\": 0.2824, \"test_samples_per_second\": 906.551, \"test_steps_per_second\": 28.33, \"epoch\": 5.625}, {\"test_loss\": 0.11086928844451904, \"test_micro_f1_no_misc\": 0.7766323024054983, \"test_micro_f1\": 0.7280108254397833, \"test_runtime\": 0.2756, \"test_samples_per_second\": 928.809, \"test_steps_per_second\": 29.025, \"epoch\": 5.625}, {\"test_loss\": 0.09955459833145142, \"test_micro_f1_no_misc\": 0.8139963167587477, \"test_micro_f1\": 0.7599410898379971, \"test_runtime\": 0.2852, \"test_samples_per_second\": 897.476, \"test_steps_per_second\": 28.046, \"epoch\": 6.5625}, {\"test_loss\": 0.21045637130737305, \"test_micro_f1_no_misc\": 0.720136518771331, \"test_micro_f1\": 0.6522911051212938, \"test_runtime\": 0.287, \"test_samples_per_second\": 892.04, \"test_steps_per_second\": 27.876, \"epoch\": 6.5625}, {\"test_loss\": 0.15171152353286743, \"test_micro_f1_no_misc\": 0.693815987933635, \"test_micro_f1\": 0.6785714285714286, \"test_runtime\": 0.2935, \"test_samples_per_second\": 872.114, \"test_steps_per_second\": 27.254, \"epoch\": 4.6875}, {\"test_loss\": 0.1240561380982399, \"test_micro_f1_no_misc\": 0.7384615384615385, \"test_micro_f1\": 0.7173637515842839, \"test_runtime\": 0.2844, \"test_samples_per_second\": 899.988, \"test_steps_per_second\": 28.125, \"epoch\": 4.6875}, {\"test_loss\": 0.175827294588089, \"test_micro_f1_no_misc\": 0.721915285451197, \"test_micro_f1\": 0.6534653465346535, \"test_runtime\": 0.2842, \"test_samples_per_second\": 900.846, \"test_steps_per_second\": 28.151, \"epoch\": 4.6875}, {\"test_loss\": 0.12039299309253693, \"test_micro_f1_no_misc\": 0.719640179910045, \"test_micro_f1\": 0.7231352718078381, \"test_runtime\": 0.277, \"test_samples_per_second\": 924.257, \"test_steps_per_second\": 28.883, \"epoch\": 6.5625}, {\"test_loss\": 0.13185033202171326, \"test_micro_f1_no_misc\": 0.7514619883040935, \"test_micro_f1\": 0.7031963470319634, \"test_runtime\": 0.2862, \"test_samples_per_second\": 894.616, \"test_steps_per_second\": 27.957, \"epoch\": 5.625}, {\"test_loss\": 0.13558733463287354, \"test_micro_f1_no_misc\": 0.8892617449664431, \"test_micro_f1\": 0.8, \"test_runtime\": 0.2711, \"test_samples_per_second\": 944.234, \"test_steps_per_second\": 29.507, \"epoch\": 7.5}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "fullstack-ner-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 76.11286775243231, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 72.52560627906772, "upper": 79.7001292257969, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "fullstack-ner-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 71.02705672085192, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 68.16082685962505, "upper": 73.89328658207879, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "latvian-twitter-sentiment/AiLab-IMCS-UL/lvbert/1781784012", "evaluation_timestamp": "2026-06-18T12:00:12.185362+00:00", "retrieved_timestamp": "1781784012", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "latvian-twitter-sentiment", "languages": "[\"lv\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.941655158996582, \"test_mcc\": 0.282973577575063, \"test_macro_f1\": 0.4641001340082059, \"test_runtime\": 2.5802, \"test_samples_per_second\": 793.723, \"test_steps_per_second\": 24.804, \"epoch\": 3.75}, {\"test_loss\": 0.8414952754974365, \"test_mcc\": 0.44742895638693897, \"test_macro_f1\": 0.6313909229426296, \"test_runtime\": 2.6052, \"test_samples_per_second\": 786.129, \"test_steps_per_second\": 24.567, \"epoch\": 4.6875}, {\"test_loss\": 0.8184407949447632, \"test_mcc\": 0.42848585742417894, \"test_macro_f1\": 0.6106692707256339, \"test_runtime\": 2.5071, \"test_samples_per_second\": 816.89, \"test_steps_per_second\": 25.528, \"epoch\": 4.6875}, {\"test_loss\": 0.9270024299621582, \"test_mcc\": 0.3023884011998631, \"test_macro_f1\": 0.5161815047015619, \"test_runtime\": 2.4428, \"test_samples_per_second\": 838.382, \"test_steps_per_second\": 26.199, \"epoch\": 3.75}, {\"test_loss\": 0.8499133586883545, \"test_mcc\": 0.4103403858941045, \"test_macro_f1\": 0.5879021366505185, \"test_runtime\": 2.5546, \"test_samples_per_second\": 801.678, \"test_steps_per_second\": 25.052, \"epoch\": 4.6875}, {\"test_loss\": 0.9491977691650391, \"test_mcc\": 0.288504691994753, \"test_macro_f1\": 0.5073404136519892, \"test_runtime\": 2.542, \"test_samples_per_second\": 805.668, \"test_steps_per_second\": 25.177, \"epoch\": 3.75}, {\"test_loss\": 0.8721460103988647, \"test_mcc\": 0.4001840565327343, \"test_macro_f1\": 0.5652355762004203, \"test_runtime\": 2.5658, \"test_samples_per_second\": 798.176, \"test_steps_per_second\": 24.943, \"epoch\": 4.6875}, {\"test_loss\": 0.8570451736450195, \"test_mcc\": 0.3804980477093266, \"test_macro_f1\": 0.5851280496511321, \"test_runtime\": 2.4773, \"test_samples_per_second\": 826.717, \"test_steps_per_second\": 25.835, \"epoch\": 4.6875}, {\"test_loss\": 0.8441863059997559, \"test_mcc\": 0.45402550943511083, \"test_macro_f1\": 0.6352903346921533, \"test_runtime\": 2.5617, \"test_samples_per_second\": 799.454, \"test_steps_per_second\": 24.983, \"epoch\": 4.6875}, {\"test_loss\": 0.950739860534668, \"test_mcc\": 0.3179413185464749, \"test_macro_f1\": 0.5162058959815444, \"test_runtime\": 2.5053, \"test_samples_per_second\": 817.482, \"test_steps_per_second\": 25.546, \"epoch\": 3.75}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "latvian-twitter-sentiment", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 37.127708026985474, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 32.96453562225314, "upper": 41.29088043171781, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "latvian-twitter-sentiment", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 56.194442392057894, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 52.58392440507024, "upper": 59.804960379045546, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "latvian-twitter-sentiment/AiLab-IMCS-UL/lvbert/1782217364", "evaluation_timestamp": "2026-06-23T12:22:44.038141+00:00", "retrieved_timestamp": "1782217364", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.5.0.dev0", "additional_details": {"dataset": "latvian-twitter-sentiment", "languages": "[\"lv\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "true", "use_bits_per_character": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.8937034606933594, \"test_mcc\": 0.3839473968123387, \"test_macro_f1\": 0.5241141700140426, \"test_runtime\": 0.4348, \"test_samples_per_second\": 588.817, \"test_steps_per_second\": 18.401, \"epoch\": 3.75}, {\"test_loss\": 0.963470458984375, \"test_mcc\": 0.28803843017132486, \"test_macro_f1\": 0.5260844901606226, \"test_runtime\": 0.4336, \"test_samples_per_second\": 590.446, \"test_steps_per_second\": 18.451, \"epoch\": 4.6875}, {\"test_loss\": 0.9115705490112305, \"test_mcc\": 0.31835815500751363, \"test_macro_f1\": 0.5239444356166051, \"test_runtime\": 0.4339, \"test_samples_per_second\": 590.003, \"test_steps_per_second\": 18.438, \"epoch\": 4.6875}, {\"test_loss\": 0.9392547607421875, \"test_mcc\": 0.2816126842703217, \"test_macro_f1\": 0.5078827676388652, \"test_runtime\": 0.4344, \"test_samples_per_second\": 589.305, \"test_steps_per_second\": 18.416, \"epoch\": 3.75}, {\"test_loss\": 0.8967170715332031, \"test_mcc\": 0.33289779843113365, \"test_macro_f1\": 0.48485697039844183, \"test_runtime\": 0.298, \"test_samples_per_second\": 859.153, \"test_steps_per_second\": 26.849, \"epoch\": 4.6875}, {\"test_loss\": 0.9640655517578125, \"test_mcc\": 0.34232231062309204, \"test_macro_f1\": 0.5326465042712183, \"test_runtime\": 0.2968, \"test_samples_per_second\": 862.436, \"test_steps_per_second\": 26.951, \"epoch\": 3.75}, {\"test_loss\": 0.8189058303833008, \"test_mcc\": 0.38102467970669207, \"test_macro_f1\": 0.5465063526374908, \"test_runtime\": 0.4297, \"test_samples_per_second\": 595.733, \"test_steps_per_second\": 18.617, \"epoch\": 4.6875}, {\"test_loss\": 0.7974491119384766, \"test_mcc\": 0.4090237873723464, \"test_macro_f1\": 0.6067745605343315, \"test_runtime\": 0.4325, \"test_samples_per_second\": 591.841, \"test_steps_per_second\": 18.495, \"epoch\": 4.6875}, {\"test_loss\": 0.9646949768066406, \"test_mcc\": 0.3243670543459236, \"test_macro_f1\": 0.5440741443397485, \"test_runtime\": 0.431, \"test_samples_per_second\": 593.966, \"test_steps_per_second\": 18.561, \"epoch\": 4.6875}, {\"test_loss\": 0.9371566772460938, \"test_mcc\": 0.19586349311424975, \"test_macro_f1\": 0.4193512159125928, \"test_runtime\": 0.3236, \"test_samples_per_second\": 791.103, \"test_steps_per_second\": 24.722, \"epoch\": 3.75}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "latvian-twitter-sentiment", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 32.574557898549365, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 28.76501359049841, "upper": 36.384102206600325, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "latvian-twitter-sentiment", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 52.16235611523958, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 49.20230951342481, "upper": 55.12240271705436, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "multi-wiki-qa-lt/AiLab-IMCS-UL/lvbert/1781766556", "evaluation_timestamp": "2026-06-18T07:09:16.547324+00:00", "retrieved_timestamp": "1781766556", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "multi-wiki-qa-lt", "languages": "[\"lt\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_f1\": 0.48373190863862503, \"test_em\": 0.1865671641791045, \"epoch\": 2.1875}, {\"test_f1\": 2.3894817679733884, \"test_em\": 0.931098696461825, \"epoch\": 2.1875}, {\"test_f1\": 0.0, \"test_em\": 0.0, \"epoch\": 1.8556701030927836}, {\"test_f1\": 0.0, \"test_em\": 0.0, \"epoch\": 2.1875}, {\"test_f1\": 0.0, \"test_em\": 0.0, \"epoch\": 2.142857142857143}, {\"test_f1\": 0.8636271812441403, \"test_em\": 0.0, \"epoch\": 2.1649484536082473}, {\"test_f1\": 2.6247181653836, \"test_em\": 1.478743068391867, \"epoch\": 1.836734693877551}, {\"test_f1\": 0.0, \"test_em\": 0.0, \"epoch\": 1.875}, {\"test_f1\": 1.5061530230069555, \"test_em\": 0.5617977528089888, \"epoch\": 2.526315789473684}, {\"test_f1\": 1.2266372516372517, \"test_em\": 0.5454545454545454, \"epoch\": 2.2105263157894735}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "multi-wiki-qa-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 0.909434929788396, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 0.28684446160290267, "upper": 1.5320253979738894, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "multi-wiki-qa-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 0.3703661227296331, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 0.05501112502671701, "upper": 0.6857211204325492, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "multi-wiki-qa-lt/AiLab-IMCS-UL/lvbert/1782216813", "evaluation_timestamp": "2026-06-23T12:13:33.216954+00:00", "retrieved_timestamp": "1782216813", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.5.0.dev0", "additional_details": {"dataset": "multi-wiki-qa-lt", "languages": "[\"lt\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "true", "use_bits_per_character": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_f1\": 0.8802816901408451, \"test_em\": 0.704225352112676, \"epoch\": 2.1875}, {\"test_f1\": 0.5728314238952538, \"test_em\": 0.0, \"epoch\": 2.5}, {\"test_f1\": 0.8928571428571429, \"test_em\": 0.6944444444444444, \"epoch\": 2.1649484536082473}, {\"test_f1\": 0.0, \"test_em\": 0.0, \"epoch\": 2.1875}, {\"test_f1\": 0.0, \"test_em\": 0.0, \"epoch\": 2.142857142857143}, {\"test_f1\": 0.5855986119144014, \"test_em\": 0.0, \"epoch\": 2.1649484536082473}, {\"test_f1\": 3.1060385692738635, \"test_em\": 1.4285714285714286, \"epoch\": 2.142857142857143}, {\"test_f1\": 0.0, \"test_em\": 0.0, \"epoch\": 1.875}, {\"test_f1\": 1.6326530612244896, \"test_em\": 1.4285714285714286, \"epoch\": 2.2105263157894735}, {\"test_f1\": 0.0, \"test_em\": 0.0, \"epoch\": 2.526315789473684}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "multi-wiki-qa-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 0.7670260499305996, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 0.15858736569942744, "upper": 1.3754647341617718, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "multi-wiki-qa-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 0.42558126536999774, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 0.05320275998646862, "upper": 0.7979597707535269, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "multi-wiki-qa-lv/AiLab-IMCS-UL/lvbert/1781786808", "evaluation_timestamp": "2026-06-18T12:46:48.970466+00:00", "retrieved_timestamp": "1781786808", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "multi-wiki-qa-lv", "languages": "[\"lv\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_f1\": 3.019351674405929, \"test_em\": 1.3592233009708738, \"epoch\": 2.7272727272727275}, {\"test_f1\": 5.387916577102778, \"test_em\": 2.5096525096525095, \"epoch\": 2.2727272727272725}, {\"test_f1\": 4.759392344167431, \"test_em\": 2.7450980392156863, \"epoch\": 2.2727272727272725}, {\"test_f1\": 2.2281469689795093, \"test_em\": 1.1673151750972763, \"epoch\": 2.2727272727272725}, {\"test_f1\": 4.657114928664067, \"test_em\": 1.761252446183953, \"epoch\": 2.2727272727272725}, {\"test_f1\": 4.240135880876809, \"test_em\": 1.5841584158415842, \"epoch\": 2.2727272727272725}, {\"test_f1\": 3.2684290164669973, \"test_em\": 1.3888888888888888, \"epoch\": 2.8125}, {\"test_f1\": 1.897390308802778, \"test_em\": 1.1976047904191616, \"epoch\": 2.769230769230769}, {\"test_f1\": 5.188303338138179, \"test_em\": 2.1653543307086616, \"epoch\": 2.34375}, {\"test_f1\": 3.0195687561553686, \"test_em\": 1.5533980582524272, \"epoch\": 2.7272727272727275}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "multi-wiki-qa-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 3.766574979375984, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 2.996910871951078, "upper": 4.53623908680089, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "multi-wiki-qa-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 1.7431945955231023, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 1.4016193175751184, "upper": 2.084769873471086, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "multi-wiki-qa-lv/AiLab-IMCS-UL/lvbert/1782219932", "evaluation_timestamp": "2026-06-23T13:05:32.007699+00:00", "retrieved_timestamp": "1782219932", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.5.0.dev0", "additional_details": {"dataset": "multi-wiki-qa-lv", "languages": "[\"lv\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "true", "use_bits_per_character": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_f1\": 2.3255662370331462, \"test_em\": 0.684931506849315, \"epoch\": 2.7272727272727275}, {\"test_f1\": 1.7379356050755645, \"test_em\": 0.0, \"epoch\": 2.2727272727272725}, {\"test_f1\": 2.29995604995605, \"test_em\": 0.6756756756756757, \"epoch\": 2.2727272727272725}, {\"test_f1\": 0.7437007437007438, \"test_em\": 0.0, \"epoch\": 2.2727272727272725}, {\"test_f1\": 4.4633016271266825, \"test_em\": 1.408450704225352, \"epoch\": 2.2727272727272725}, {\"test_f1\": 1.7320392502874253, \"test_em\": 0.7299270072992701, \"epoch\": 2.2727272727272725}, {\"test_f1\": 1.6381697442012464, \"test_em\": 0.0, \"epoch\": 2.8125}, {\"test_f1\": 1.7730496453900708, \"test_em\": 1.4184397163120568, \"epoch\": 2.769230769230769}, {\"test_f1\": 3.3229201846223124, \"test_em\": 0.7092198581560284, \"epoch\": 2.34375}, {\"test_f1\": 0.696748506967485, \"test_em\": 0.0, \"epoch\": 2.7272727272727275}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "multi-wiki-qa-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 2.0733387594360724, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 1.3708971155938923, "upper": 2.7757804032782527, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "multi-wiki-qa-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 0.5626644468517698, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 0.21749373396409666, "upper": 0.9078351597394428, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "scala-lt/AiLab-IMCS-UL/lvbert/1781766556", "evaluation_timestamp": "2026-06-18T07:09:16.547399+00:00", "retrieved_timestamp": "1781766556", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "scala-lt", "languages": "[\"lt\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.6940183639526367, \"test_mcc\": 0.004495625204991601, \"test_macro_f1\": 0.5021326654106935, \"test_runtime\": 1.7843, \"test_samples_per_second\": 1147.776, \"test_steps_per_second\": 35.868, \"epoch\": 2.8125}, {\"test_loss\": 0.7156352996826172, \"test_mcc\": 0.03120772987186554, \"test_macro_f1\": 0.4939271255060729, \"test_runtime\": 1.7708, \"test_samples_per_second\": 1156.572, \"test_steps_per_second\": 36.143, \"epoch\": 4.6875}, {\"test_loss\": 0.7073907852172852, \"test_mcc\": 0.011364750249947582, \"test_macro_f1\": 0.3827008988643092, \"test_runtime\": 1.771, \"test_samples_per_second\": 1156.394, \"test_steps_per_second\": 36.137, \"epoch\": 2.8125}, {\"test_loss\": 0.7415480613708496, \"test_mcc\": -0.006908161535804158, \"test_macro_f1\": 0.4931177493645242, \"test_runtime\": 1.6531, \"test_samples_per_second\": 1238.889, \"test_steps_per_second\": 38.715, \"epoch\": 4.6875}, {\"test_loss\": 0.6991100311279297, \"test_mcc\": 0.0019834058649062275, \"test_macro_f1\": 0.38253210834935786, \"test_runtime\": 1.8694, \"test_samples_per_second\": 1095.522, \"test_steps_per_second\": 34.235, \"epoch\": 2.8125}, {\"test_loss\": 0.6982955932617188, \"test_mcc\": -0.010450906034608083, \"test_macro_f1\": 0.4941285640851041, \"test_runtime\": 1.9163, \"test_samples_per_second\": 1068.723, \"test_steps_per_second\": 33.398, \"epoch\": 2.8125}, {\"test_loss\": 0.6957054138183594, \"test_mcc\": 0.019850303860371666, \"test_macro_f1\": 0.49157461380157563, \"test_runtime\": 1.8924, \"test_samples_per_second\": 1082.211, \"test_steps_per_second\": 33.819, \"epoch\": 2.8125}, {\"test_loss\": 0.7167215347290039, \"test_mcc\": 0.014009361932872812, \"test_macro_f1\": 0.35479887241021685, \"test_runtime\": 1.8908, \"test_samples_per_second\": 1083.159, \"test_steps_per_second\": 33.849, \"epoch\": 3.75}, {\"test_loss\": 0.6940793991088867, \"test_mcc\": 0.0035031712281383695, \"test_macro_f1\": 0.49897106016779635, \"test_runtime\": 1.7725, \"test_samples_per_second\": 1155.449, \"test_steps_per_second\": 36.108, \"epoch\": 2.8125}, {\"test_loss\": 0.6994638442993164, \"test_mcc\": -0.005626276790467264, \"test_macro_f1\": 0.49663827366475893, \"test_runtime\": 1.6459, \"test_samples_per_second\": 1244.299, \"test_steps_per_second\": 38.884, \"epoch\": 3.75}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 0.6342900385221429, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": -0.1701510892041057, "upper": 1.4387311662483917, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 45.90521931624409, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 42.20475998933141, "upper": 49.60567864315678, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "scala-lt/AiLab-IMCS-UL/lvbert/1782215160", "evaluation_timestamp": "2026-06-23T11:46:00.695308+00:00", "retrieved_timestamp": "1782215160", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.5.0.dev0", "additional_details": {"dataset": "scala-lt", "languages": "[\"lt\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "true", "use_bits_per_character": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.69482421875, \"test_mcc\": -0.03973147828078671, \"test_macro_f1\": 0.4714714714714715, \"test_runtime\": 0.5463, \"test_samples_per_second\": 468.637, \"test_steps_per_second\": 14.645, \"epoch\": 2.8125}, {\"test_loss\": 0.7119140625, \"test_mcc\": -0.015298702501687867, \"test_macro_f1\": 0.40904278399722294, \"test_runtime\": 0.5391, \"test_samples_per_second\": 474.901, \"test_steps_per_second\": 14.841, \"epoch\": 2.8125}, {\"test_loss\": 0.6915817260742188, \"test_mcc\": 0.1278268377029522, \"test_macro_f1\": 0.5513742851872347, \"test_runtime\": 0.4725, \"test_samples_per_second\": 541.766, \"test_steps_per_second\": 16.93, \"epoch\": 4.6875}, {\"test_loss\": 0.7028121948242188, \"test_mcc\": -0.056365532041843726, \"test_macro_f1\": 0.464808362369338, \"test_runtime\": 0.5453, \"test_samples_per_second\": 469.487, \"test_steps_per_second\": 14.671, \"epoch\": 2.8125}, {\"test_loss\": 0.714385986328125, \"test_mcc\": -0.12445008856737837, \"test_macro_f1\": 0.36588818117480537, \"test_runtime\": 0.5422, \"test_samples_per_second\": 472.141, \"test_steps_per_second\": 14.754, \"epoch\": 2.8125}, {\"test_loss\": 0.7066726684570312, \"test_mcc\": -0.001685933780474737, \"test_macro_f1\": 0.49394613293797873, \"test_runtime\": 0.541, \"test_samples_per_second\": 473.239, \"test_steps_per_second\": 14.789, \"epoch\": 2.8125}, {\"test_loss\": 0.6951217651367188, \"test_mcc\": 0.051809417251998856, \"test_macro_f1\": 0.5220079583715947, \"test_runtime\": 0.5434, \"test_samples_per_second\": 471.106, \"test_steps_per_second\": 14.722, \"epoch\": 2.8125}, {\"test_loss\": 0.702880859375, \"test_mcc\": 0.04033376328443046, \"test_macro_f1\": 0.44279874714657325, \"test_runtime\": 0.5426, \"test_samples_per_second\": 471.815, \"test_steps_per_second\": 14.744, \"epoch\": 2.8125}, {\"test_loss\": 0.6943511962890625, \"test_mcc\": 0.041919300341805424, \"test_macro_f1\": 0.5100365941418751, \"test_runtime\": 0.4785, \"test_samples_per_second\": 535.026, \"test_steps_per_second\": 16.72, \"epoch\": 2.8125}, {\"test_loss\": 0.707275390625, \"test_mcc\": -0.054133318988259654, \"test_macro_f1\": 0.4697353279631761, \"test_runtime\": 0.5427, \"test_samples_per_second\": 471.75, \"test_steps_per_second\": 14.742, \"epoch\": 3.75}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": -0.2977573557924411, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": -4.71586062914721, "upper": 4.120345917562329, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 47.011098447612696, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 43.62717394431233, "upper": 50.39502295091306, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "scala-lv/AiLab-IMCS-UL/lvbert/1781785212", "evaluation_timestamp": "2026-06-18T12:20:12.418245+00:00", "retrieved_timestamp": "1781785212", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "scala-lv", "languages": "[\"lv\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.6820721626281738, \"test_mcc\": 0.11247669288422031, \"test_macro_f1\": 0.5551142005958292, \"test_runtime\": 3.835, \"test_samples_per_second\": 534.028, \"test_steps_per_second\": 16.688, \"epoch\": 3.75}, {\"test_loss\": 0.6932239532470703, \"test_mcc\": 0.05651845084659053, \"test_macro_f1\": 0.5272123465632634, \"test_runtime\": 5.4791, \"test_samples_per_second\": 373.783, \"test_steps_per_second\": 11.681, \"epoch\": 3.75}, {\"test_loss\": 0.6955685615539551, \"test_mcc\": 0.3716556782577395, \"test_macro_f1\": 0.6776510793964043, \"test_runtime\": 3.8849, \"test_samples_per_second\": 527.163, \"test_steps_per_second\": 16.474, \"epoch\": 6.5625}, {\"test_loss\": 0.677833080291748, \"test_mcc\": 0.19614888250069262, \"test_macro_f1\": 0.5953558161110878, \"test_runtime\": 2.1594, \"test_samples_per_second\": 948.399, \"test_steps_per_second\": 29.637, \"epoch\": 4.6875}, {\"test_loss\": 0.6746664047241211, \"test_mcc\": 0.17782349033816688, \"test_macro_f1\": 0.5755915317559153, \"test_runtime\": 4.1618, \"test_samples_per_second\": 492.089, \"test_steps_per_second\": 15.378, \"epoch\": 4.6875}, {\"test_loss\": 0.7040035724639893, \"test_mcc\": 0.23358956353163038, \"test_macro_f1\": 0.5895796629090538, \"test_runtime\": 5.4848, \"test_samples_per_second\": 373.399, \"test_steps_per_second\": 11.669, \"epoch\": 5.625}, {\"test_loss\": 0.716991126537323, \"test_mcc\": 0.44087666230478323, \"test_macro_f1\": 0.7198391187293177, \"test_runtime\": 3.9972, \"test_samples_per_second\": 512.356, \"test_steps_per_second\": 16.011, \"epoch\": 7.5}, {\"test_loss\": 0.6694254875183105, \"test_mcc\": 0.31415851716586385, \"test_macro_f1\": 0.6490533705536055, \"test_runtime\": 5.5294, \"test_samples_per_second\": 370.382, \"test_steps_per_second\": 11.574, \"epoch\": 6.5625}, {\"test_loss\": 0.6728925704956055, \"test_mcc\": 0.16994660232914274, \"test_macro_f1\": 0.5849593542455835, \"test_runtime\": 2.1126, \"test_samples_per_second\": 969.416, \"test_steps_per_second\": 30.294, \"epoch\": 4.6875}, {\"test_loss\": 0.6289611458778381, \"test_mcc\": 0.4036470439561756, \"test_macro_f1\": 0.688081662126746, \"test_runtime\": 5.4989, \"test_samples_per_second\": 372.437, \"test_steps_per_second\": 11.639, \"epoch\": 6.5625}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 24.768415841150055, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 16.76570619469919, "upper": 32.77112548760092, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 61.624381429868066, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.694483646037334, "upper": 65.5542792136988, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "scala-lv/AiLab-IMCS-UL/lvbert/1782218537", "evaluation_timestamp": "2026-06-23T12:42:17.331971+00:00", "retrieved_timestamp": "1782218537", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.5.0.dev0", "additional_details": {"dataset": "scala-lv", "languages": "[\"lv\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "true", "use_bits_per_character": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.6884841918945312, \"test_mcc\": 0.09435114503816794, \"test_macro_f1\": 0.546875, \"test_runtime\": 0.1914, \"test_samples_per_second\": 1337.513, \"test_steps_per_second\": 41.797, \"epoch\": 3.75}, {\"test_loss\": 0.6837539672851562, \"test_mcc\": 0.12135047163362946, \"test_macro_f1\": 0.5598133136821419, \"test_runtime\": 0.1904, \"test_samples_per_second\": 1344.375, \"test_steps_per_second\": 42.012, \"epoch\": 3.75}, {\"test_loss\": 0.6673276424407959, \"test_mcc\": 0.3953094702270846, \"test_macro_f1\": 0.6928015958358658, \"test_runtime\": 0.1912, \"test_samples_per_second\": 1339.213, \"test_steps_per_second\": 41.85, \"epoch\": 6.5625}, {\"test_loss\": 0.6797027587890625, \"test_mcc\": 0.19531846073733983, \"test_macro_f1\": 0.5976501106279087, \"test_runtime\": 0.192, \"test_samples_per_second\": 1333.617, \"test_steps_per_second\": 41.676, \"epoch\": 4.6875}, {\"test_loss\": 0.6884536743164062, \"test_mcc\": 0.08600131635675316, \"test_macro_f1\": 0.5421271159374002, \"test_runtime\": 0.1939, \"test_samples_per_second\": 1320.295, \"test_steps_per_second\": 41.259, \"epoch\": 4.6875}, {\"test_loss\": 0.6515998840332031, \"test_mcc\": 0.2848096143429841, \"test_macro_f1\": 0.6226557109703318, \"test_runtime\": 0.1939, \"test_samples_per_second\": 1320.318, \"test_steps_per_second\": 41.26, \"epoch\": 5.625}, {\"test_loss\": 0.6278476715087891, \"test_mcc\": 0.5306273151925697, \"test_macro_f1\": 0.7652668256005868, \"test_runtime\": 0.2021, \"test_samples_per_second\": 1266.665, \"test_steps_per_second\": 39.583, \"epoch\": 7.5}, {\"test_loss\": 0.6298236846923828, \"test_mcc\": 0.28280698047644315, \"test_macro_f1\": 0.6374384236453201, \"test_runtime\": 0.1933, \"test_samples_per_second\": 1324.193, \"test_steps_per_second\": 41.381, \"epoch\": 6.5625}, {\"test_loss\": 0.6566848754882812, \"test_mcc\": 0.23246443322102903, \"test_macro_f1\": 0.6154548974061169, \"test_runtime\": 0.1924, \"test_samples_per_second\": 1330.852, \"test_steps_per_second\": 41.589, \"epoch\": 4.6875}, {\"test_loss\": 0.6881799697875977, \"test_mcc\": 0.38912862004157134, \"test_macro_f1\": 0.6760759197063189, \"test_runtime\": 0.1957, \"test_samples_per_second\": 1307.87, \"test_steps_per_second\": 40.871, \"epoch\": 6.5625}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 26.12167827267572, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 17.087149452532266, "upper": 35.15620709281917, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-lv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 62.56158913411991, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 58.1741814273004, "upper": 66.94899684093943, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "wikiann-lt/AiLab-IMCS-UL/lvbert/1781766556", "evaluation_timestamp": "2026-06-18T07:09:16.547508+00:00", "retrieved_timestamp": "1781766556", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "wikiann-lt", "languages": "[\"lt\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.49074000120162964, \"test_micro_f1_no_misc\": 0.5657351727390638, \"test_micro_f1\": 0.5657351727390638, \"test_runtime\": 1.5077, \"test_samples_per_second\": 1358.395, \"test_steps_per_second\": 42.45, \"epoch\": 5.625}, {\"test_loss\": 0.46496933698654175, \"test_micro_f1_no_misc\": 0.5976154992548435, \"test_micro_f1\": 0.5976154992548435, \"test_runtime\": 1.4471, \"test_samples_per_second\": 1415.212, \"test_steps_per_second\": 44.225, \"epoch\": 5.625}, {\"test_loss\": 0.48648035526275635, \"test_micro_f1_no_misc\": 0.5924819517052526, \"test_micro_f1\": 0.5924819517052526, \"test_runtime\": 1.481, \"test_samples_per_second\": 1382.831, \"test_steps_per_second\": 43.213, \"epoch\": 5.625}, {\"test_loss\": 0.5473958253860474, \"test_micro_f1_no_misc\": 0.5749397590361446, \"test_micro_f1\": 0.5749397590361446, \"test_runtime\": 1.4795, \"test_samples_per_second\": 1384.234, \"test_steps_per_second\": 43.257, \"epoch\": 6.5625}, {\"test_loss\": 0.5467627644538879, \"test_micro_f1_no_misc\": 0.5952292670868867, \"test_micro_f1\": 0.5952292670868867, \"test_runtime\": 1.5127, \"test_samples_per_second\": 1353.857, \"test_steps_per_second\": 42.308, \"epoch\": 6.5625}, {\"test_loss\": 0.49450069665908813, \"test_micro_f1_no_misc\": 0.5777507598784194, \"test_micro_f1\": 0.5777507598784194, \"test_runtime\": 1.478, \"test_samples_per_second\": 1385.683, \"test_steps_per_second\": 43.303, \"epoch\": 5.625}, {\"test_loss\": 0.5425136089324951, \"test_micro_f1_no_misc\": 0.5592361192974183, \"test_micro_f1\": 0.5592361192974183, \"test_runtime\": 1.4792, \"test_samples_per_second\": 1384.527, \"test_steps_per_second\": 43.266, \"epoch\": 5.625}, {\"test_loss\": 0.520317792892456, \"test_micro_f1_no_misc\": 0.5818002222496604, \"test_micro_f1\": 0.5818002222496604, \"test_runtime\": 1.4749, \"test_samples_per_second\": 1388.573, \"test_steps_per_second\": 43.393, \"epoch\": 5.625}, {\"test_loss\": 0.47174620628356934, \"test_micro_f1_no_misc\": 0.6187085093542547, \"test_micro_f1\": 0.6187085093542547, \"test_runtime\": 1.4504, \"test_samples_per_second\": 1412.026, \"test_steps_per_second\": 44.126, \"epoch\": 6.5625}, {\"test_loss\": 0.5078248977661133, \"test_micro_f1_no_misc\": 0.627054060490593, \"test_micro_f1\": 0.627054060490593, \"test_runtime\": 1.4997, \"test_samples_per_second\": 1365.583, \"test_steps_per_second\": 42.674, \"epoch\": 7.5}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "wikiann-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 58.90551321092536, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.557199625448035, "upper": 60.25382679640269, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "wikiann-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 58.90551321092536, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.557199625448035, "upper": 60.25382679640269, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "wikiann-lt/AiLab-IMCS-UL/lvbert/1782215565", "evaluation_timestamp": "2026-06-23T11:52:45.651149+00:00", "retrieved_timestamp": "1782215565", "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": "AiLab-IMCS-UL/lvbert", "id": "AiLab-IMCS-UL/lvbert", "additional_details": {"num_model_parameters": "110620416", "max_sequence_length": "512", "vocabulary_size": "32004", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": true, "model_url": "https://hf.co/AiLab-IMCS-UL/lvbert"}, "inference_engine": {"name": "transformers", "version": "5.10.2"}}, "eval_library": {"name": "euroeval", "version": "17.5.0.dev0", "additional_details": {"dataset": "wikiann-lt", "languages": "[\"lt\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "true", "use_bits_per_character": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": null, "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.5214793682098389, \"test_micro_f1_no_misc\": 0.5350877192982456, \"test_micro_f1\": 0.5350877192982456, \"test_runtime\": 0.3107, \"test_samples_per_second\": 823.874, \"test_steps_per_second\": 25.746, \"epoch\": 5.625}, {\"test_loss\": 0.4537166357040405, \"test_micro_f1_no_misc\": 0.5865800865800865, \"test_micro_f1\": 0.5865800865800865, \"test_runtime\": 0.3119, \"test_samples_per_second\": 820.879, \"test_steps_per_second\": 25.652, \"epoch\": 4.6875}, {\"test_loss\": 0.43446657061576843, \"test_micro_f1_no_misc\": 0.653191489361702, \"test_micro_f1\": 0.653191489361702, \"test_runtime\": 0.233, \"test_samples_per_second\": 1098.86, \"test_steps_per_second\": 34.339, \"epoch\": 5.625}, {\"test_loss\": 0.49868345260620117, \"test_micro_f1_no_misc\": 0.542336548767417, \"test_micro_f1\": 0.542336548767417, \"test_runtime\": 0.2286, \"test_samples_per_second\": 1119.999, \"test_steps_per_second\": 35.0, \"epoch\": 5.625}, {\"test_loss\": 0.4583035111427307, \"test_micro_f1_no_misc\": 0.5891783567134269, \"test_micro_f1\": 0.5891783567134269, \"test_runtime\": 0.2315, \"test_samples_per_second\": 1105.907, \"test_steps_per_second\": 34.56, \"epoch\": 5.625}, {\"test_loss\": 0.37699151039123535, \"test_micro_f1_no_misc\": 0.6442687747035573, \"test_micro_f1\": 0.6442687747035573, \"test_runtime\": 0.3178, \"test_samples_per_second\": 805.63, \"test_steps_per_second\": 25.176, \"epoch\": 5.625}, {\"test_loss\": 0.5031620860099792, \"test_micro_f1_no_misc\": 0.5714285714285714, \"test_micro_f1\": 0.5714285714285714, \"test_runtime\": 0.2308, \"test_samples_per_second\": 1109.192, \"test_steps_per_second\": 34.662, \"epoch\": 5.625}, {\"test_loss\": 0.43877720832824707, \"test_micro_f1_no_misc\": 0.6261585993820803, \"test_micro_f1\": 0.6261585993820803, \"test_runtime\": 0.3134, \"test_samples_per_second\": 816.76, \"test_steps_per_second\": 25.524, \"epoch\": 5.625}, {\"test_loss\": 0.502036452293396, \"test_micro_f1_no_misc\": 0.6076502732240436, \"test_micro_f1\": 0.6076502732240436, \"test_runtime\": 0.3109, \"test_samples_per_second\": 823.342, \"test_steps_per_second\": 25.729, \"epoch\": 5.625}, {\"test_loss\": 0.49953359365463257, \"test_micro_f1_no_misc\": 0.5892857142857143, \"test_micro_f1\": 0.5892857142857143, \"test_runtime\": 0.2307, \"test_samples_per_second\": 1109.472, \"test_steps_per_second\": 34.671, \"epoch\": 5.625}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "wikiann-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 59.451661337448456, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.00727031344714, "upper": 61.896052361449776, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "wikiann-lt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 59.451661337448456, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.00727031344714, "upper": 61.896052361449776, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}