3ebdola_Dialectal-Arabic-XLM-R-Base.jsonl

{"schema_version": "0.2.1", "evaluation_id": "dbrd/3ebdola/Dialectal-Arabic-XLM-R-Base/1781766556", "evaluation_timestamp": "2026-06-18T07:09:16.546846+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": "3ebdola/Dialectal-Arabic-XLM-R-Base", "id": "3ebdola/Dialectal-Arabic-XLM-R-Base", "additional_details": {"num_model_parameters": "278045186", "max_sequence_length": "512", "vocabulary_size": "250002", "merge": "false", "generative": "false", "generative_type": null, "commercially_licensed": true, "open": true, "trained_from_scratch": false}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "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": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_loss\": 0.7121152877807617, \"test_mcc\": 0.18203887892877846, \"test_macro_f1\": 0.5533180778032036, \"test_runtime\": 5.2964, \"test_samples_per_second\": 386.679, \"test_steps_per_second\": 12.084, \"epoch\": 9.375}, {\"test_loss\": 0.6928367614746094, \"test_mcc\": 0.019869171867153864, \"test_macro_f1\": 0.48032197876398003, \"test_runtime\": 4.9439, \"test_samples_per_second\": 414.247, \"test_steps_per_second\": 12.945, \"epoch\": 3.75}, {\"test_loss\": 0.6914272308349609, \"test_mcc\": 0.07521082125447316, \"test_macro_f1\": 0.5246352487196869, \"test_runtime\": 5.1389, \"test_samples_per_second\": 398.532, \"test_steps_per_second\": 12.454, \"epoch\": 4.6875}, {\"test_loss\": 0.6923408508300781, \"test_mcc\": 0.0355760558396187, \"test_macro_f1\": 0.5177434304466545, \"test_runtime\": 5.4727, \"test_samples_per_second\": 374.221, \"test_steps_per_second\": 11.694, \"epoch\": 4.6875}, {\"test_loss\": 0.7007665634155273, \"test_mcc\": 0.0, \"test_macro_f1\": 0.33892834086507423, \"test_runtime\": 4.9464, \"test_samples_per_second\": 414.04, \"test_steps_per_second\": 12.939, \"epoch\": 4.6875}, {\"test_loss\": 0.6864118576049805, \"test_mcc\": 0.08647686982105723, \"test_macro_f1\": 0.535107633566709, \"test_runtime\": 5.2878, \"test_samples_per_second\": 387.304, \"test_steps_per_second\": 12.103, \"epoch\": 8.4375}, {\"test_loss\": 0.6928997039794922, \"test_mcc\": 0.03592635855263112, \"test_macro_f1\": 0.4382966438108986, \"test_runtime\": 5.3128, \"test_samples_per_second\": 385.487, \"test_steps_per_second\": 12.046, \"epoch\": 3.75}, {\"test_loss\": 0.6944904327392578, \"test_mcc\": -0.043768241414737175, \"test_macro_f1\": 0.3562045863946404, \"test_runtime\": 5.3259, \"test_samples_per_second\": 384.537, \"test_steps_per_second\": 12.017, \"epoch\": 2.8125}, {\"test_loss\": 0.7117748260498047, \"test_mcc\": 0.06846785928256786, \"test_macro_f1\": 0.46256849034751446, \"test_runtime\": 5.2601, \"test_samples_per_second\": 389.349, \"test_steps_per_second\": 12.167, \"epoch\": 8.4375}, {\"test_loss\": 0.689814567565918, \"test_mcc\": 0.10446084542727761, \"test_macro_f1\": 0.549335445823431, \"test_runtime\": 5.1181, \"test_samples_per_second\": 400.152, \"test_steps_per_second\": 12.505, \"epoch\": 7.5}]"}}, "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": 5.642586195588208, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 1.7828838999612913, "upper": 9.502288491215126, "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": 47.56459876541793, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 42.77620728597638, "upper": 52.35299024485947, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}