| { |
| "results": { |
| "assin2_rte": { |
| "f1_macro,all": 0.577927165258549, |
| "f1_macro_stderr,all": 0.0071561886831375205, |
| "acc,all": 0.6004901960784313, |
| "acc_stderr,all": 0.006996270367086327, |
| "alias": "assin2_rte" |
| }, |
| "assin2_sts": { |
| "pearson,all": 0.01994583242718194, |
| "pearson_stderr,all": 0.014030097851152527, |
| "mse,all": 2.0782883986928105, |
| "mse_stderr,all": "N/A", |
| "alias": "assin2_sts" |
| }, |
| "bluex": { |
| "acc,all": 0.24756606397774686, |
| "acc_stderr,all": 0.009256090690166377, |
| "acc,exam_id__USP_2020": 0.23214285714285715, |
| "acc_stderr,exam_id__USP_2020": 0.03265301549767108, |
| "acc,exam_id__UNICAMP_2022": 0.3076923076923077, |
| "acc_stderr,exam_id__UNICAMP_2022": 0.04284625323101336, |
| "acc,exam_id__USP_2019": 0.15, |
| "acc_stderr,exam_id__USP_2019": 0.032604803052830006, |
| "acc,exam_id__UNICAMP_2019": 0.26, |
| "acc_stderr,exam_id__UNICAMP_2019": 0.035805342426308485, |
| "acc,exam_id__UNICAMP_2023": 0.3488372093023256, |
| "acc_stderr,exam_id__UNICAMP_2023": 0.041919014018416384, |
| "acc,exam_id__UNICAMP_2021_2": 0.3137254901960784, |
| "acc_stderr,exam_id__UNICAMP_2021_2": 0.037486879456641045, |
| "acc,exam_id__USP_2023": 0.18181818181818182, |
| "acc_stderr,exam_id__USP_2023": 0.03349033495084427, |
| "acc,exam_id__USP_2021": 0.23076923076923078, |
| "acc_stderr,exam_id__USP_2021": 0.03381852906171476, |
| "acc,exam_id__UNICAMP_2021_1": 0.2391304347826087, |
| "acc_stderr,exam_id__UNICAMP_2021_1": 0.03638828981438008, |
| "acc,exam_id__UNICAMP_2020": 0.32727272727272727, |
| "acc_stderr,exam_id__UNICAMP_2020": 0.03653884692218891, |
| "acc,exam_id__USP_2022": 0.16326530612244897, |
| "acc_stderr,exam_id__USP_2022": 0.03041886398004624, |
| "acc,exam_id__USP_2024": 0.1951219512195122, |
| "acc_stderr,exam_id__USP_2024": 0.03573567350069458, |
| "acc,exam_id__UNICAMP_2024": 0.28888888888888886, |
| "acc_stderr,exam_id__UNICAMP_2024": 0.038994404039252965, |
| "acc,exam_id__USP_2018": 0.16666666666666666, |
| "acc_stderr,exam_id__USP_2018": 0.029375798861409928, |
| "acc,exam_id__UNICAMP_2018": 0.2962962962962963, |
| "acc_stderr,exam_id__UNICAMP_2018": 0.035803514128866995, |
| "alias": "bluex" |
| }, |
| "enem_challenge": { |
| "alias": "enem", |
| "acc,all": 0.19174247725682295, |
| "acc_stderr,all": 0.006016154421005065, |
| "acc,exam_id__2014": 0.14678899082568808, |
| "acc_stderr,exam_id__2014": 0.019587599223040625, |
| "acc,exam_id__2017": 0.1896551724137931, |
| "acc_stderr,exam_id__2017": 0.02093347844131792, |
| "acc,exam_id__2016_2": 0.21951219512195122, |
| "acc_stderr,exam_id__2016_2": 0.021542806426202234, |
| "acc,exam_id__2016": 0.23140495867768596, |
| "acc_stderr,exam_id__2016": 0.022131076893750434, |
| "acc,exam_id__2012": 0.1724137931034483, |
| "acc_stderr,exam_id__2012": 0.020164330045300043, |
| "acc,exam_id__2010": 0.2222222222222222, |
| "acc_stderr,exam_id__2010": 0.02213114984638704, |
| "acc,exam_id__2022": 0.16541353383458646, |
| "acc_stderr,exam_id__2022": 0.018647718361639067, |
| "acc,exam_id__2015": 0.23529411764705882, |
| "acc_stderr,exam_id__2015": 0.02241173308841978, |
| "acc,exam_id__2011": 0.18803418803418803, |
| "acc_stderr,exam_id__2011": 0.020817448020547174, |
| "acc,exam_id__2013": 0.23148148148148148, |
| "acc_stderr,exam_id__2013": 0.02345320376483438, |
| "acc,exam_id__2009": 0.13043478260869565, |
| "acc_stderr,exam_id__2009": 0.018075482087183004, |
| "acc,exam_id__2023": 0.17037037037037037, |
| "acc_stderr,exam_id__2023": 0.018694761764683765 |
| }, |
| "faquad_nli": { |
| "f1_macro,all": 0.4396551724137931, |
| "f1_macro_stderr,all": 0.0035796984729087084, |
| "acc,all": 0.7846153846153846, |
| "acc_stderr,all": 0.011396120309131327, |
| "alias": "faquad_nli" |
| }, |
| "hatebr_offensive": { |
| "alias": "hatebr_offensive_binary", |
| "f1_macro,all": 0.5373169584712172, |
| "f1_macro_stderr,all": 0.009509765977605292, |
| "acc,all": 0.5642857142857143, |
| "acc_stderr,all": 0.009363640166058677 |
| }, |
| "oab_exams": { |
| "acc,all": 0.2528473804100228, |
| "acc_stderr,all": 0.005369584144606133, |
| "acc,exam_id__2012-06a": 0.2875, |
| "acc_stderr,exam_id__2012-06a": 0.029268820937911468, |
| "acc,exam_id__2012-09": 0.2857142857142857, |
| "acc_stderr,exam_id__2012-09": 0.02981338225884132, |
| "acc,exam_id__2013-10": 0.1375, |
| "acc_stderr,exam_id__2013-10": 0.022269660648017626, |
| "acc,exam_id__2011-04": 0.2625, |
| "acc_stderr,exam_id__2011-04": 0.02838995857974862, |
| "acc,exam_id__2018-25": 0.2, |
| "acc_stderr,exam_id__2018-25": 0.02584730185242964, |
| "acc,exam_id__2011-05": 0.2625, |
| "acc_stderr,exam_id__2011-05": 0.028394014157416495, |
| "acc,exam_id__2012-07": 0.275, |
| "acc_stderr,exam_id__2012-07": 0.028825122025371252, |
| "acc,exam_id__2014-13": 0.2375, |
| "acc_stderr,exam_id__2014-13": 0.027472596578792648, |
| "acc,exam_id__2012-06": 0.2375, |
| "acc_stderr,exam_id__2012-06": 0.027444121032139803, |
| "acc,exam_id__2015-16": 0.3125, |
| "acc_stderr,exam_id__2015-16": 0.03003339727126325, |
| "acc,exam_id__2017-22": 0.25, |
| "acc_stderr,exam_id__2017-22": 0.027997530519651585, |
| "acc,exam_id__2017-24": 0.275, |
| "acc_stderr,exam_id__2017-24": 0.028929264616280162, |
| "acc,exam_id__2014-14": 0.2125, |
| "acc_stderr,exam_id__2014-14": 0.02645590211050805, |
| "acc,exam_id__2011-03": 0.25252525252525254, |
| "acc_stderr,exam_id__2011-03": 0.02522016343392691, |
| "acc,exam_id__2014-15": 0.2564102564102564, |
| "acc_stderr,exam_id__2014-15": 0.02850809134358431, |
| "acc,exam_id__2016-19": 0.2948717948717949, |
| "acc_stderr,exam_id__2016-19": 0.029792524691902637, |
| "acc,exam_id__2012-08": 0.2375, |
| "acc_stderr,exam_id__2012-08": 0.02756426923964389, |
| "acc,exam_id__2015-17": 0.24358974358974358, |
| "acc_stderr,exam_id__2015-17": 0.028007851240875885, |
| "acc,exam_id__2015-18": 0.2875, |
| "acc_stderr,exam_id__2015-18": 0.02920616482631226, |
| "acc,exam_id__2010-01": 0.25882352941176473, |
| "acc_stderr,exam_id__2010-01": 0.027343286705705846, |
| "acc,exam_id__2016-20a": 0.2125, |
| "acc_stderr,exam_id__2016-20a": 0.026410470748996454, |
| "acc,exam_id__2016-21": 0.2625, |
| "acc_stderr,exam_id__2016-21": 0.028563711821251347, |
| "acc,exam_id__2016-20": 0.225, |
| "acc_stderr,exam_id__2016-20": 0.02689442014065515, |
| "acc,exam_id__2017-23": 0.275, |
| "acc_stderr,exam_id__2017-23": 0.028728458302479908, |
| "acc,exam_id__2013-12": 0.2875, |
| "acc_stderr,exam_id__2013-12": 0.02914378722659053, |
| "acc,exam_id__2010-02": 0.27, |
| "acc_stderr,exam_id__2010-02": 0.02563525101778004, |
| "acc,exam_id__2013-11": 0.225, |
| "acc_stderr,exam_id__2013-11": 0.027058590192888813, |
| "alias": "oab_exams" |
| }, |
| "portuguese_hate_speech": { |
| "alias": "portuguese_hate_speech_binary", |
| "f1_macro,all": 0.300060277449729, |
| "f1_macro_stderr,all": 0.010227555978721074, |
| "acc,all": 0.33137485311398357, |
| "acc_stderr,all": 0.011379474523059378 |
| }, |
| "tweetsentbr": { |
| "f1_macro,all": 0.2072905953605302, |
| "f1_macro_stderr,all": 0.0024889383614545776, |
| "acc,all": 0.45124378109452734, |
| "acc_stderr,all": 0.007861876742012653, |
| "alias": "tweetsentbr" |
| } |
| }, |
| "configs": { |
| "assin2_rte": { |
| "task": "assin2_rte", |
| "group": [ |
| "pt_benchmark", |
| "assin2" |
| ], |
| "dataset_path": "assin2", |
| "test_split": "test", |
| "fewshot_split": "train", |
| "doc_to_text": "Premissa: {{premise}}\nHipótese: {{hypothesis}}\nPergunta: A hipótese pode ser inferida pela premissa? Sim ou Não?\nResposta:", |
| "doc_to_target": "{{['Não', 'Sim'][entailment_judgment]}}", |
| "description": "Abaixo estão pares de premissa e hipótese. Para cada par, indique se a hipótese pode ser inferida a partir da premissa, responda apenas com \"Sim\" ou \"Não\".\n\n", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "id_sampler", |
| "sampler_config": { |
| "id_list": [ |
| 1, |
| 3251, |
| 2, |
| 3252, |
| 3, |
| 4, |
| 5, |
| 6, |
| 3253, |
| 7, |
| 3254, |
| 3255, |
| 3256, |
| 8, |
| 9, |
| 10, |
| 3257, |
| 11, |
| 3258, |
| 12, |
| 13, |
| 14, |
| 15, |
| 3259, |
| 3260, |
| 3261, |
| 3262, |
| 3263, |
| 16, |
| 17, |
| 3264, |
| 18, |
| 3265, |
| 3266, |
| 3267, |
| 19, |
| 20, |
| 3268, |
| 3269, |
| 21, |
| 3270, |
| 3271, |
| 22, |
| 3272, |
| 3273, |
| 23, |
| 3274, |
| 24, |
| 25, |
| 3275 |
| ], |
| "id_column": "sentence_pair_id" |
| } |
| }, |
| "num_fewshot": 15, |
| "metric_list": [ |
| { |
| "metric": "f1_macro", |
| "aggregation": "f1_macro", |
| "higher_is_better": true |
| }, |
| { |
| "metric": "acc", |
| "aggregation": "acc", |
| "higher_is_better": true |
| } |
| ], |
| "output_type": "generate_until", |
| "generation_kwargs": { |
| "max_gen_toks": 32, |
| "do_sample": false, |
| "temperature": 0.0, |
| "top_k": null, |
| "top_p": null, |
| "until": [ |
| "\n\n" |
| ] |
| }, |
| "repeats": 1, |
| "filter_list": [ |
| { |
| "name": "all", |
| "filter": [ |
| { |
| "function": "find_similar_label", |
| "labels": [ |
| "Sim", |
| "Não" |
| ] |
| }, |
| { |
| "function": "take_first" |
| } |
| ] |
| } |
| ], |
| "should_decontaminate": false, |
| "metadata": { |
| "version": 1.1 |
| } |
| }, |
| "assin2_sts": { |
| "task": "assin2_sts", |
| "group": [ |
| "pt_benchmark", |
| "assin2" |
| ], |
| "dataset_path": "assin2", |
| "test_split": "test", |
| "fewshot_split": "train", |
| "doc_to_text": "Frase 1: {{premise}}\nFrase 2: {{hypothesis}}\nPergunta: Quão similares são as duas frases? Dê uma pontuação entre 1,0 a 5,0.\nResposta:", |
| "doc_to_target": "<function assin2_float_to_pt_str at 0x14879d55b600>", |
| "description": "Abaixo estão pares de frases que você deve avaliar o grau de similaridade. Dê uma pontuação entre 1,0 e 5,0, sendo 1,0 pouco similar e 5,0 muito similar.\n\n", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "id_sampler", |
| "sampler_config": { |
| "id_list": [ |
| 1, |
| 3251, |
| 2, |
| 3252, |
| 3, |
| 4, |
| 5, |
| 6, |
| 3253, |
| 7, |
| 3254, |
| 3255, |
| 3256, |
| 8, |
| 9, |
| 10, |
| 3257, |
| 11, |
| 3258, |
| 12, |
| 13, |
| 14, |
| 15, |
| 3259, |
| 3260, |
| 3261, |
| 3262, |
| 3263, |
| 16, |
| 17, |
| 3264, |
| 18, |
| 3265, |
| 3266, |
| 3267, |
| 19, |
| 20, |
| 3268, |
| 3269, |
| 21, |
| 3270, |
| 3271, |
| 22, |
| 3272, |
| 3273, |
| 23, |
| 3274, |
| 24, |
| 25, |
| 3275 |
| ], |
| "id_column": "sentence_pair_id" |
| } |
| }, |
| "num_fewshot": 10, |
| "metric_list": [ |
| { |
| "metric": "pearson", |
| "aggregation": "pearsonr", |
| "higher_is_better": true |
| }, |
| { |
| "metric": "mse", |
| "aggregation": "mean_squared_error", |
| "higher_is_better": false |
| } |
| ], |
| "output_type": "generate_until", |
| "generation_kwargs": { |
| "max_gen_toks": 32, |
| "do_sample": false, |
| "temperature": 0.0, |
| "top_k": null, |
| "top_p": null, |
| "until": [ |
| "\n\n" |
| ] |
| }, |
| "repeats": 1, |
| "filter_list": [ |
| { |
| "name": "all", |
| "filter": [ |
| { |
| "function": "number_filter", |
| "type": "float", |
| "range_min": 1.0, |
| "range_max": 5.0, |
| "on_outside_range": "clip", |
| "fallback": 5.0 |
| }, |
| { |
| "function": "take_first" |
| } |
| ] |
| } |
| ], |
| "should_decontaminate": false, |
| "metadata": { |
| "version": 1.1 |
| } |
| }, |
| "bluex": { |
| "task": "bluex", |
| "group": [ |
| "pt_benchmark", |
| "vestibular" |
| ], |
| "dataset_path": "eduagarcia-temp/BLUEX_without_images", |
| "test_split": "train", |
| "fewshot_split": "train", |
| "doc_to_text": "<function enem_doc_to_text at 0x14879d55ab60>", |
| "doc_to_target": "{{answerKey}}", |
| "description": "As perguntas a seguir são questões de múltipla escolha de provas de vestibular de universidades brasileiras, selecione a única alternativa correta e responda apenas com as letras \"A\", \"B\", \"C\", \"D\" ou \"E\".\n\n", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "id_sampler", |
| "sampler_config": { |
| "id_list": [ |
| "USP_2018_3", |
| "UNICAMP_2018_2", |
| "USP_2018_35", |
| "UNICAMP_2018_16", |
| "USP_2018_89" |
| ], |
| "id_column": "id", |
| "exclude_from_task": true |
| } |
| }, |
| "num_fewshot": 3, |
| "metric_list": [ |
| { |
| "metric": "acc", |
| "aggregation": "acc", |
| "higher_is_better": true |
| } |
| ], |
| "output_type": "generate_until", |
| "generation_kwargs": { |
| "max_gen_toks": 32, |
| "do_sample": false, |
| "temperature": 0.0, |
| "top_k": null, |
| "top_p": null, |
| "until": [ |
| "\n\n" |
| ] |
| }, |
| "repeats": 1, |
| "filter_list": [ |
| { |
| "name": "all", |
| "filter": [ |
| { |
| "function": "normalize_spaces" |
| }, |
| { |
| "function": "remove_accents" |
| }, |
| { |
| "function": "find_choices", |
| "choices": [ |
| "A", |
| "B", |
| "C", |
| "D", |
| "E" |
| ], |
| "regex_patterns": [ |
| "(?:[Ll]etra|[Aa]lternativa|[Rr]esposta|[Rr]esposta [Cc]orreta|[Rr]esposta [Cc]orreta e|[Oo]pcao):? ([ABCDE])\\b", |
| "\\b([ABCDE])\\.", |
| "\\b([ABCDE]) ?[.):-]", |
| "\\b([ABCDE])$", |
| "\\b([ABCDE])\\b" |
| ] |
| }, |
| { |
| "function": "take_first" |
| } |
| ], |
| "group_by": { |
| "column": "exam_id" |
| } |
| } |
| ], |
| "should_decontaminate": true, |
| "doc_to_decontamination_query": "<function enem_doc_to_text at 0x14879d55ae80>", |
| "metadata": { |
| "version": 1.1 |
| } |
| }, |
| "enem_challenge": { |
| "task": "enem_challenge", |
| "task_alias": "enem", |
| "group": [ |
| "pt_benchmark", |
| "vestibular" |
| ], |
| "dataset_path": "eduagarcia/enem_challenge", |
| "test_split": "train", |
| "fewshot_split": "train", |
| "doc_to_text": "<function enem_doc_to_text at 0x14879d55b060>", |
| "doc_to_target": "{{answerKey}}", |
| "description": "As perguntas a seguir são questões de múltipla escolha do Exame Nacional do Ensino Médio (ENEM), selecione a única alternativa correta e responda apenas com as letras \"A\", \"B\", \"C\", \"D\" ou \"E\".\n\n", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "id_sampler", |
| "sampler_config": { |
| "id_list": [ |
| "2022_21", |
| "2022_88", |
| "2022_143" |
| ], |
| "id_column": "id", |
| "exclude_from_task": true |
| } |
| }, |
| "num_fewshot": 3, |
| "metric_list": [ |
| { |
| "metric": "acc", |
| "aggregation": "acc", |
| "higher_is_better": true |
| } |
| ], |
| "output_type": "generate_until", |
| "generation_kwargs": { |
| "max_gen_toks": 32, |
| "do_sample": false, |
| "temperature": 0.0, |
| "top_k": null, |
| "top_p": null, |
| "until": [ |
| "\n\n" |
| ] |
| }, |
| "repeats": 1, |
| "filter_list": [ |
| { |
| "name": "all", |
| "filter": [ |
| { |
| "function": "normalize_spaces" |
| }, |
| { |
| "function": "remove_accents" |
| }, |
| { |
| "function": "find_choices", |
| "choices": [ |
| "A", |
| "B", |
| "C", |
| "D", |
| "E" |
| ], |
| "regex_patterns": [ |
| "(?:[Ll]etra|[Aa]lternativa|[Rr]esposta|[Rr]esposta [Cc]orreta|[Rr]esposta [Cc]orreta e|[Oo]pcao):? ([ABCDE])\\b", |
| "\\b([ABCDE])\\.", |
| "\\b([ABCDE]) ?[.):-]", |
| "\\b([ABCDE])$", |
| "\\b([ABCDE])\\b" |
| ] |
| }, |
| { |
| "function": "take_first" |
| } |
| ], |
| "group_by": { |
| "column": "exam_id" |
| } |
| } |
| ], |
| "should_decontaminate": true, |
| "doc_to_decontamination_query": "<function enem_doc_to_text at 0x14879d55b240>", |
| "metadata": { |
| "version": 1.1 |
| } |
| }, |
| "faquad_nli": { |
| "task": "faquad_nli", |
| "group": [ |
| "pt_benchmark" |
| ], |
| "dataset_path": "ruanchaves/faquad-nli", |
| "test_split": "test", |
| "fewshot_split": "train", |
| "doc_to_text": "Pergunta: {{question}}\nResposta: {{answer}}\nA resposta dada satisfaz à pergunta? Sim ou Não?", |
| "doc_to_target": "{{['Não', 'Sim'][label]}}", |
| "description": "Abaixo estão pares de pergunta e resposta. Para cada par, você deve julgar se a resposta responde à pergunta de maneira satisfatória e aparenta estar correta. Escreva apenas \"Sim\" ou \"Não\".\n\n", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "first_n", |
| "sampler_config": { |
| "fewshot_indices": [ |
| 1893, |
| 949, |
| 663, |
| 105, |
| 1169, |
| 2910, |
| 2227, |
| 2813, |
| 974, |
| 558, |
| 1503, |
| 1958, |
| 2918, |
| 601, |
| 1560, |
| 984, |
| 2388, |
| 995, |
| 2233, |
| 1982, |
| 165, |
| 2788, |
| 1312, |
| 2285, |
| 522, |
| 1113, |
| 1670, |
| 323, |
| 236, |
| 1263, |
| 1562, |
| 2519, |
| 1049, |
| 432, |
| 1167, |
| 1394, |
| 2022, |
| 2551, |
| 2194, |
| 2187, |
| 2282, |
| 2816, |
| 108, |
| 301, |
| 1185, |
| 1315, |
| 1420, |
| 2436, |
| 2322, |
| 766 |
| ] |
| } |
| }, |
| "num_fewshot": 15, |
| "metric_list": [ |
| { |
| "metric": "f1_macro", |
| "aggregation": "f1_macro", |
| "higher_is_better": true |
| }, |
| { |
| "metric": "acc", |
| "aggregation": "acc", |
| "higher_is_better": true |
| } |
| ], |
| "output_type": "generate_until", |
| "generation_kwargs": { |
| "max_gen_toks": 32, |
| "do_sample": false, |
| "temperature": 0.0, |
| "top_k": null, |
| "top_p": null, |
| "until": [ |
| "\n\n" |
| ] |
| }, |
| "repeats": 1, |
| "filter_list": [ |
| { |
| "name": "all", |
| "filter": [ |
| { |
| "function": "find_similar_label", |
| "labels": [ |
| "Sim", |
| "Não" |
| ] |
| }, |
| { |
| "function": "take_first" |
| } |
| ] |
| } |
| ], |
| "should_decontaminate": false, |
| "metadata": { |
| "version": 1.1 |
| } |
| }, |
| "hatebr_offensive": { |
| "task": "hatebr_offensive", |
| "task_alias": "hatebr_offensive_binary", |
| "group": [ |
| "pt_benchmark" |
| ], |
| "dataset_path": "eduagarcia/portuguese_benchmark", |
| "dataset_name": "HateBR_offensive_binary", |
| "test_split": "test", |
| "fewshot_split": "train", |
| "doc_to_text": "Texto: {{sentence}}\nPergunta: O texto é ofensivo?\nResposta:", |
| "doc_to_target": "{{'Sim' if label == 1 else 'Não'}}", |
| "description": "Abaixo contém o texto de comentários de usuários do Instagram em português, sua tarefa é classificar se o texto é ofensivo ou não. Responda apenas com \"Sim\" ou \"Não\".\n\n", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "id_sampler", |
| "sampler_config": { |
| "id_list": [ |
| 48, |
| 44, |
| 36, |
| 20, |
| 3511, |
| 88, |
| 3555, |
| 16, |
| 56, |
| 3535, |
| 60, |
| 40, |
| 3527, |
| 4, |
| 76, |
| 3579, |
| 3523, |
| 3551, |
| 68, |
| 3503, |
| 84, |
| 3539, |
| 64, |
| 3599, |
| 80, |
| 3563, |
| 3559, |
| 3543, |
| 3547, |
| 3587, |
| 3595, |
| 3575, |
| 3567, |
| 3591, |
| 24, |
| 96, |
| 92, |
| 3507, |
| 52, |
| 72, |
| 8, |
| 3571, |
| 3515, |
| 3519, |
| 3531, |
| 28, |
| 32, |
| 0, |
| 12, |
| 3583 |
| ], |
| "id_column": "idx" |
| } |
| }, |
| "num_fewshot": 25, |
| "metric_list": [ |
| { |
| "metric": "f1_macro", |
| "aggregation": "f1_macro", |
| "higher_is_better": true |
| }, |
| { |
| "metric": "acc", |
| "aggregation": "acc", |
| "higher_is_better": true |
| } |
| ], |
| "output_type": "generate_until", |
| "generation_kwargs": { |
| "max_gen_toks": 32, |
| "do_sample": false, |
| "temperature": 0.0, |
| "top_k": null, |
| "top_p": null, |
| "until": [ |
| "\n\n" |
| ] |
| }, |
| "repeats": 1, |
| "filter_list": [ |
| { |
| "name": "all", |
| "filter": [ |
| { |
| "function": "find_similar_label", |
| "labels": [ |
| "Sim", |
| "Não" |
| ] |
| }, |
| { |
| "function": "take_first" |
| } |
| ] |
| } |
| ], |
| "should_decontaminate": false, |
| "metadata": { |
| "version": 1.0 |
| } |
| }, |
| "oab_exams": { |
| "task": "oab_exams", |
| "group": [ |
| "legal_benchmark", |
| "pt_benchmark" |
| ], |
| "dataset_path": "eduagarcia/oab_exams", |
| "test_split": "train", |
| "fewshot_split": "train", |
| "doc_to_text": "<function doc_to_text at 0x14879d55bd80>", |
| "doc_to_target": "{{answerKey}}", |
| "description": "As perguntas a seguir são questões de múltipla escolha do Exame de Ordem da Ordem dos Advogados do Brasil (OAB), selecione a única alternativa correta e responda apenas com as letras \"A\", \"B\", \"C\" ou \"D\".\n\n", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "id_sampler", |
| "sampler_config": { |
| "id_list": [ |
| "2010-01_1", |
| "2010-01_11", |
| "2010-01_13", |
| "2010-01_23", |
| "2010-01_26", |
| "2010-01_28", |
| "2010-01_38", |
| "2010-01_48", |
| "2010-01_58", |
| "2010-01_68", |
| "2010-01_76", |
| "2010-01_83", |
| "2010-01_85", |
| "2010-01_91", |
| "2010-01_99" |
| ], |
| "id_column": "id", |
| "exclude_from_task": true |
| } |
| }, |
| "num_fewshot": 3, |
| "metric_list": [ |
| { |
| "metric": "acc", |
| "aggregation": "acc", |
| "higher_is_better": true |
| } |
| ], |
| "output_type": "generate_until", |
| "generation_kwargs": { |
| "max_gen_toks": 32, |
| "do_sample": false, |
| "temperature": 0.0, |
| "top_k": null, |
| "top_p": null, |
| "until": [ |
| "\n\n" |
| ] |
| }, |
| "repeats": 1, |
| "filter_list": [ |
| { |
| "name": "all", |
| "filter": [ |
| { |
| "function": "normalize_spaces" |
| }, |
| { |
| "function": "remove_accents" |
| }, |
| { |
| "function": "find_choices", |
| "choices": [ |
| "A", |
| "B", |
| "C", |
| "D" |
| ], |
| "regex_patterns": [ |
| "(?:[Ll]etra|[Aa]lternativa|[Rr]esposta|[Rr]esposta [Cc]orreta|[Rr]esposta [Cc]orreta e|[Oo]pcao):? ([ABCD])\\b", |
| "\\b([ABCD])\\.", |
| "\\b([ABCD]) ?[.):-]", |
| "\\b([ABCD])$", |
| "\\b([ABCD])\\b" |
| ] |
| }, |
| { |
| "function": "take_first" |
| } |
| ], |
| "group_by": { |
| "column": "exam_id" |
| } |
| } |
| ], |
| "should_decontaminate": true, |
| "doc_to_decontamination_query": "<function doc_to_text at 0x14879d3ac040>", |
| "metadata": { |
| "version": 1.5 |
| } |
| }, |
| "portuguese_hate_speech": { |
| "task": "portuguese_hate_speech", |
| "task_alias": "portuguese_hate_speech_binary", |
| "group": [ |
| "pt_benchmark" |
| ], |
| "dataset_path": "eduagarcia/portuguese_benchmark", |
| "dataset_name": "Portuguese_Hate_Speech_binary", |
| "test_split": "test", |
| "fewshot_split": "train", |
| "doc_to_text": "Texto: {{sentence}}\nPergunta: O texto contém discurso de ódio?\nResposta:", |
| "doc_to_target": "{{'Sim' if label == 1 else 'Não'}}", |
| "description": "Abaixo contém o texto de tweets de usuários do Twitter em português, sua tarefa é classificar se o texto contém discurso de ódio ou não. Responda apenas com \"Sim\" ou \"Não\".\n\n", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "id_sampler", |
| "sampler_config": { |
| "id_list": [ |
| 52, |
| 50, |
| 39, |
| 28, |
| 3, |
| 105, |
| 22, |
| 25, |
| 60, |
| 11, |
| 66, |
| 41, |
| 9, |
| 4, |
| 91, |
| 42, |
| 7, |
| 20, |
| 76, |
| 1, |
| 104, |
| 13, |
| 67, |
| 54, |
| 97, |
| 27, |
| 24, |
| 14, |
| 16, |
| 48, |
| 53, |
| 40, |
| 34, |
| 49, |
| 32, |
| 119, |
| 114, |
| 2, |
| 58, |
| 83, |
| 18, |
| 36, |
| 5, |
| 6, |
| 10, |
| 35, |
| 38, |
| 0, |
| 21, |
| 46 |
| ], |
| "id_column": "idx" |
| } |
| }, |
| "num_fewshot": 25, |
| "metric_list": [ |
| { |
| "metric": "f1_macro", |
| "aggregation": "f1_macro", |
| "higher_is_better": true |
| }, |
| { |
| "metric": "acc", |
| "aggregation": "acc", |
| "higher_is_better": true |
| } |
| ], |
| "output_type": "generate_until", |
| "generation_kwargs": { |
| "max_gen_toks": 32, |
| "do_sample": false, |
| "temperature": 0.0, |
| "top_k": null, |
| "top_p": null, |
| "until": [ |
| "\n\n" |
| ] |
| }, |
| "repeats": 1, |
| "filter_list": [ |
| { |
| "name": "all", |
| "filter": [ |
| { |
| "function": "find_similar_label", |
| "labels": [ |
| "Sim", |
| "Não" |
| ] |
| }, |
| { |
| "function": "take_first" |
| } |
| ] |
| } |
| ], |
| "should_decontaminate": false, |
| "metadata": { |
| "version": 1.0 |
| } |
| }, |
| "tweetsentbr": { |
| "task": "tweetsentbr", |
| "group": [ |
| "pt_benchmark" |
| ], |
| "dataset_path": "eduagarcia/tweetsentbr_fewshot", |
| "test_split": "test", |
| "fewshot_split": "train", |
| "doc_to_text": "Texto: {{sentence}}\nPergunta: O sentimento do texto é Positivo, Neutro ou Negativo?\nResposta:", |
| "doc_to_target": "{{'Positivo' if label == 'Positive' else ('Negativo' if label == 'Negative' else 'Neutro')}}", |
| "description": "Abaixo contém o texto de tweets de usuários do Twitter em português, sua tarefa é classificar se o sentimento do texto é Positivo, Neutro ou Negativo. Responda apenas com uma das opções.\n\n", |
| "target_delimiter": " ", |
| "fewshot_delimiter": "\n\n", |
| "fewshot_config": { |
| "sampler": "first_n" |
| }, |
| "num_fewshot": 25, |
| "metric_list": [ |
| { |
| "metric": "f1_macro", |
| "aggregation": "f1_macro", |
| "higher_is_better": true |
| }, |
| { |
| "metric": "acc", |
| "aggregation": "acc", |
| "higher_is_better": true |
| } |
| ], |
| "output_type": "generate_until", |
| "generation_kwargs": { |
| "max_gen_toks": 32, |
| "do_sample": false, |
| "temperature": 0.0, |
| "top_k": null, |
| "top_p": null, |
| "until": [ |
| "\n\n" |
| ] |
| }, |
| "repeats": 1, |
| "filter_list": [ |
| { |
| "name": "all", |
| "filter": [ |
| { |
| "function": "find_similar_label", |
| "labels": [ |
| "Positivo", |
| "Neutro", |
| "Negativo" |
| ] |
| }, |
| { |
| "function": "take_first" |
| } |
| ] |
| } |
| ], |
| "should_decontaminate": false, |
| "metadata": { |
| "version": 1.0 |
| } |
| } |
| }, |
| "versions": { |
| "assin2_rte": 1.1, |
| "assin2_sts": 1.1, |
| "bluex": 1.1, |
| "enem_challenge": 1.1, |
| "faquad_nli": 1.1, |
| "hatebr_offensive": 1.0, |
| "oab_exams": 1.5, |
| "portuguese_hate_speech": 1.0, |
| "tweetsentbr": 1.0 |
| }, |
| "n-shot": { |
| "assin2_rte": 15, |
| "assin2_sts": 10, |
| "bluex": 3, |
| "enem_challenge": 3, |
| "faquad_nli": 15, |
| "hatebr_offensive": 25, |
| "oab_exams": 3, |
| "portuguese_hate_speech": 25, |
| "tweetsentbr": 25 |
| }, |
| "model_meta": { |
| "truncated": 2, |
| "non_truncated": 14148, |
| "padded": 0, |
| "non_padded": 14150, |
| "fewshots_truncated": 4, |
| "has_chat_template": false, |
| "chat_type": null, |
| "n_gpus": 1, |
| "accelerate_num_process": null, |
| "model_sha": "None", |
| "model_dtype": "torch.bfloat16", |
| "model_memory_footprint": 1260510976, |
| "model_num_parameters": 630253568, |
| "model_is_loaded_in_4bit": null, |
| "model_is_loaded_in_8bit": null, |
| "model_is_quantized": null, |
| "model_device": "cuda:0", |
| "batch_size": 64, |
| "max_length": 2048, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32 |
| }, |
| "task_model_meta": { |
| "assin2_rte": { |
| "sample_size": 2448, |
| "truncated": 0, |
| "non_truncated": 2448, |
| "padded": 0, |
| "non_padded": 2448, |
| "fewshots_truncated": 0, |
| "mean_seq_length": 924.4232026143791, |
| "min_seq_length": 909, |
| "max_seq_length": 963, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32, |
| "mean_original_fewshots_size": 15.0, |
| "mean_effective_fewshot_size": 15.0 |
| }, |
| "assin2_sts": { |
| "sample_size": 2448, |
| "truncated": 0, |
| "non_truncated": 2448, |
| "padded": 0, |
| "non_padded": 2448, |
| "fewshots_truncated": 0, |
| "mean_seq_length": 659.4232026143791, |
| "min_seq_length": 644, |
| "max_seq_length": 698, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32, |
| "mean_original_fewshots_size": 10.0, |
| "mean_effective_fewshot_size": 10.0 |
| }, |
| "bluex": { |
| "sample_size": 719, |
| "truncated": 0, |
| "non_truncated": 719, |
| "padded": 0, |
| "non_padded": 719, |
| "fewshots_truncated": 0, |
| "mean_seq_length": 1170.817802503477, |
| "min_seq_length": 904, |
| "max_seq_length": 1801, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32, |
| "mean_original_fewshots_size": 3.0, |
| "mean_effective_fewshot_size": 3.0 |
| }, |
| "enem_challenge": { |
| "sample_size": 1429, |
| "truncated": 2, |
| "non_truncated": 1427, |
| "padded": 0, |
| "non_padded": 1429, |
| "fewshots_truncated": 4, |
| "mean_seq_length": 1007.4177746675997, |
| "min_seq_length": 829, |
| "max_seq_length": 2484, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32, |
| "mean_original_fewshots_size": 3.0, |
| "mean_effective_fewshot_size": 2.9972008397480754 |
| }, |
| "faquad_nli": { |
| "sample_size": 650, |
| "truncated": 0, |
| "non_truncated": 650, |
| "padded": 0, |
| "non_padded": 650, |
| "fewshots_truncated": 0, |
| "mean_seq_length": 968.1338461538462, |
| "min_seq_length": 936, |
| "max_seq_length": 1034, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32, |
| "mean_original_fewshots_size": 15.0, |
| "mean_effective_fewshot_size": 15.0 |
| }, |
| "hatebr_offensive": { |
| "sample_size": 1400, |
| "truncated": 0, |
| "non_truncated": 1400, |
| "padded": 0, |
| "non_padded": 1400, |
| "fewshots_truncated": 0, |
| "mean_seq_length": 867.4407142857143, |
| "min_seq_length": 852, |
| "max_seq_length": 1061, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32, |
| "mean_original_fewshots_size": 25.0, |
| "mean_effective_fewshot_size": 25.0 |
| }, |
| "oab_exams": { |
| "sample_size": 2195, |
| "truncated": 0, |
| "non_truncated": 2195, |
| "padded": 0, |
| "non_padded": 2195, |
| "fewshots_truncated": 0, |
| "mean_seq_length": 832.024145785877, |
| "min_seq_length": 659, |
| "max_seq_length": 1108, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32, |
| "mean_original_fewshots_size": 3.0, |
| "mean_effective_fewshot_size": 3.0 |
| }, |
| "portuguese_hate_speech": { |
| "sample_size": 851, |
| "truncated": 0, |
| "non_truncated": 851, |
| "padded": 0, |
| "non_padded": 851, |
| "fewshots_truncated": 0, |
| "mean_seq_length": 1219.021151586369, |
| "min_seq_length": 1192, |
| "max_seq_length": 1255, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32, |
| "mean_original_fewshots_size": 25.0, |
| "mean_effective_fewshot_size": 25.0 |
| }, |
| "tweetsentbr": { |
| "sample_size": 2010, |
| "truncated": 0, |
| "non_truncated": 2010, |
| "padded": 0, |
| "non_padded": 2010, |
| "fewshots_truncated": 0, |
| "mean_seq_length": 1154.4194029850746, |
| "min_seq_length": 1137, |
| "max_seq_length": 1211, |
| "max_ctx_length": 2016, |
| "max_gen_toks": 32, |
| "mean_original_fewshots_size": 25.0, |
| "mean_effective_fewshot_size": 25.0 |
| } |
| }, |
| "config": { |
| "model": "huggingface", |
| "model_args": "pretrained=/lustre/mlnvme/data/asen_hpc-mula/checkpoints-llama/slurm_job_17032104/step_400000", |
| "batch_size": "auto", |
| "batch_sizes": [], |
| "device": "cuda:0", |
| "use_cache": null, |
| "limit": null, |
| "bootstrap_iters": 100000, |
| "gen_kwargs": null |
| }, |
| "git_hash": null |
| } |
