Merge branch 'main' into autobatchtest

# Conflicts:
#	lm_eval/models/huggingface.py

lm_eval/tasks/catalan_bench/catcola.yaml

+task: catcola
+dataset_path: nbel/CatCoLA
+output_type: multiple_choice
+training_split: train
+validation_split: validation
+test_split: null
+doc_to_text: "{{Sentence}}\nPregunta: Té sentit aquesta frase?\nResposta:"
+doc_to_target: Label
+doc_to_choice: ["no", "sí"]
+metric_list:
+  - metric: mcc
+  - metric: acc
+metadata:
+  version: 1.0

lm_eval/tasks/catalan_bench/copa_ca.yaml

+task: copa_ca
+dataset_path: projecte-aina/COPA-ca
+dataset_name: null
+output_type: multiple_choice
+training_split: train
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs_copa_ca
+doc_to_text: '{{premise[:-1].strip() + " " + {"cause": "perquè", "effect": "i per tant"}[question]}}'
+doc_to_target: '{{choice1 if label == 0 else choice2}}'
+doc_to_choice: '{{[choice1, choice2]}}'
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/catalan_bench/coqcat.yaml

+task: coqcat
+dataset_path: projecte-aina/CoQCat
+output_type: generate_until
+training_split: train
+validation_split: validation
+test_split: test
+doc_to_text: '{{story+"\n\n"}}{% for i in range(questions|length-1) %}{{"Q: "+questions[i]+"\n\n"+"A: "+answers["input_text"][i]+"\n\n"}}{% endfor %}{{"Q: "+questions[-1]+"\n\n"+"A:"}}'
+doc_to_target: '{{ answers["input_text"][questions|length - 1] }}'
+process_results: !function utils.process_results_coqcat
+should_decontaminate: true
+doc_to_decontamination_query: "{{story}} {{question.input_text|join('\n')}}"
+generation_kwargs:
+  until:
+    - "\nQ:"
+metric_list:
+  - metric: "em"
+    aggregation: mean
+    higher_is_better: true
+  - metric: "f1"
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm_eval/tasks/catalan_bench/flores_ca/_flores_common_yaml

+dataset_path: facebook/flores
+dataset_name: all
+output_type: generate_until
+training_split: dev
+validation_split: dev
+test_split: devtest
+fewshot_split: dev
+target_delimiter: ''
+generation_kwargs:
+  until:
+    - "\n"
+metric_list:
+  - metric: bleu
+    aggregation: bleu
+    higher_is_better: true
+  - metric: ter
+    aggregation: ter
+    higher_is_better: false
+  - metric: chrf
+    aggregation: chrf
+    higher_is_better: true
+metadata:
+  version: 1.0
+dataset_kwargs:
+  trust_remote_code: true

lm_eval/tasks/catalan_bench/flores_ca/create_yamls_flores_ca.py

+"""
+Script to generate task YAMLs for the FLORES-200 dataset.
+Based on `tasks/translation/utils.py`.
+"""
+
+import argparse
+
+import yaml
+from langcodes import Language
+
+
+# constants
+_LANGUAGES = [
+    "ace_Arab",
+    "bam_Latn",
+    "dzo_Tibt",
+    "hin_Deva",
+    "khm_Khmr",
+    "mag_Deva",
+    "pap_Latn",
+    "sot_Latn",
+    "tur_Latn",
+    "ace_Latn",
+    "ban_Latn",
+    "ell_Grek",
+    "hne_Deva",
+    "kik_Latn",
+    "mai_Deva",
+    "pbt_Arab",
+    "spa_Latn",
+    "twi_Latn",
+    "acm_Arab",
+    "bel_Cyrl",
+    "eng_Latn",
+    "hrv_Latn",
+    "kin_Latn",
+    "mal_Mlym",
+    "pes_Arab",
+    "srd_Latn",
+    "tzm_Tfng",
+    "acq_Arab",
+    "bem_Latn",
+    "epo_Latn",
+    "hun_Latn",
+    "kir_Cyrl",
+    "mar_Deva",
+    "plt_Latn",
+    "srp_Cyrl",
+    "uig_Arab",
+    "aeb_Arab",
+    "ben_Beng",
+    "est_Latn",
+    "hye_Armn",
+    "kmb_Latn",
+    "min_Arab",
+    "pol_Latn",
+    "ssw_Latn",
+    "ukr_Cyrl",
+    "afr_Latn",
+    "bho_Deva",
+    "eus_Latn",
+    "ibo_Latn",
+    "kmr_Latn",
+    "min_Latn",
+    "por_Latn",
+    "sun_Latn",
+    "umb_Latn",
+    "ajp_Arab",
+    "bjn_Arab",
+    "ewe_Latn",
+    "ilo_Latn",
+    "knc_Arab",
+    "mkd_Cyrl",
+    "prs_Arab",
+    "swe_Latn",
+    "urd_Arab",
+    "aka_Latn",
+    "bjn_Latn",
+    "fao_Latn",
+    "ind_Latn",
+    "knc_Latn",
+    "mlt_Latn",
+    "quy_Latn",
+    "swh_Latn",
+    "uzn_Latn",
+    "als_Latn",
+    "bod_Tibt",
+    "fij_Latn",
+    "isl_Latn",
+    "kon_Latn",
+    "mni_Beng",
+    "ron_Latn",
+    "szl_Latn",
+    "vec_Latn",
+    "amh_Ethi",
+    "bos_Latn",
+    "fin_Latn",
+    "ita_Latn",
+    "kor_Hang",
+    "mos_Latn",
+    "run_Latn",
+    "tam_Taml",
+    "vie_Latn",
+    "apc_Arab",
+    "bug_Latn",
+    "fon_Latn",
+    "jav_Latn",
+    "lao_Laoo",
+    "mri_Latn",
+    "rus_Cyrl",
+    "taq_Latn",
+    "war_Latn",
+    "arb_Arab",
+    "bul_Cyrl",
+    "fra_Latn",
+    "jpn_Jpan",
+    "lij_Latn",
+    "mya_Mymr",
+    "sag_Latn",
+    "taq_Tfng",
+    "wol_Latn",
+    "arb_Latn",
+    "cat_Latn",
+    "fur_Latn",
+    "kab_Latn",
+    "lim_Latn",
+    "nld_Latn",
+    "san_Deva",
+    "tat_Cyrl",
+    "xho_Latn",
+    "ars_Arab",
+    "ceb_Latn",
+    "fuv_Latn",
+    "kac_Latn",
+    "lin_Latn",
+    "nno_Latn",
+    "sat_Olck",
+    "tel_Telu",
+    "ydd_Hebr",
+    "ary_Arab",
+    "ces_Latn",
+    "gaz_Latn",
+    "kam_Latn",
+    "lit_Latn",
+    "nob_Latn",
+    "scn_Latn",
+    "tgk_Cyrl",
+    "yor_Latn",
+    "arz_Arab",
+    "cjk_Latn",
+    "gla_Latn",
+    "kan_Knda",
+    "lmo_Latn",
+    "npi_Deva",
+    "shn_Mymr",
+    "tgl_Latn",
+    "yue_Hant",
+    "asm_Beng",
+    "ckb_Arab",
+    "gle_Latn",
+    "kas_Arab",
+    "ltg_Latn",
+    "nso_Latn",
+    "sin_Sinh",
+    "tha_Thai",
+    "zho_Hans",
+    "ast_Latn",
+    "crh_Latn",
+    "glg_Latn",
+    "kas_Deva",
+    "ltz_Latn",
+    "nus_Latn",
+    "slk_Latn",
+    "tir_Ethi",
+    "zho_Hant",
+    "awa_Deva",
+    "cym_Latn",
+    "grn_Latn",
+    "kat_Geor",
+    "lua_Latn",
+    "nya_Latn",
+    "slv_Latn",
+    "tpi_Latn",
+    "zsm_Latn",
+    "ayr_Latn",
+    "dan_Latn",
+    "guj_Gujr",
+    "kaz_Cyrl",
+    "lug_Latn",
+    "oci_Latn",
+    "smo_Latn",
+    "tsn_Latn",
+    "zul_Latn",
+    "azb_Arab",
+    "deu_Latn",
+    "hat_Latn",
+    "kbp_Latn",
+    "luo_Latn",
+    "ory_Orya",
+    "sna_Latn",
+    "tso_Latn",
+    "azj_Latn",
+    "dik_Latn",
+    "hau_Latn",
+    "kea_Latn",
+    "lus_Latn",
+    "pag_Latn",
+    "snd_Arab",
+    "tuk_Latn",
+    "bak_Cyrl",
+    "dyu_Latn",
+    "heb_Hebr",
+    "khk_Cyrl",
+    "lvs_Latn",
+    "pan_Guru",
+    "som_Latn",
+    "tum_Latn",
+]
+LANGUAGE_PAIRS = [
+    (a, b) for idx, a in enumerate(_LANGUAGES) for b in _LANGUAGES[idx + 1 :]
+]
+
+LANGUAGES_OF_INTEREST = [
+    "cat_Latn",
+    "spa_Latn",
+    "eng_Latn",
+    "glg_Latn",
+    "eus_Latn",
+    "ita_Latn",
+    "deu_Latn",
+    "por_Latn",
+    "fra_Latn",
+]
+MAIN_LANG = "cat_Latn"
+LANGUAGE_PAIRS = [
+    (a, b)
+    for (a, b) in LANGUAGE_PAIRS
+    if a in LANGUAGES_OF_INTEREST
+    and b in LANGUAGES_OF_INTEREST
+    and "cat_Latn" in (a, b)
+]
+
+# auxiliary functions
+
+
+def code_to_language_name(code):
+    return Language.make(language=Language.get(code)["language"]).display_name()
+
+
+def code_to_short_name(code):
+    return Language.get(code)["language"]
+
+
+def jinja_var(s):
+    return "{{" + s + "}}"
+
+
+def doc_to_text(src: str, tgt: str) -> str:
+    src_name, tgt_name = map(code_to_language_name, [src, tgt])
+
+    return f"""\
+{src_name} sentence: {jinja_var('sentence_' + src)}
+{tgt_name} sentence:"""
+
+
+def doc_to_target(tgt: str) -> str:
+    return f"{jinja_var('sentence_' + tgt)}"
+
+
+# main function
+
+
+def gen_lang_yamls(output_dir: str, overwrite: bool) -> None:
+    """
+    Generate a YAML file for each translation direction.
+    """
+
+    err = []
+    for src, tgt in LANGUAGE_PAIRS:
+        # do both translation directions for each lang pair
+        for src, tgt in [(src, tgt), (tgt, src)]:
+            lang_pair_name = f"{code_to_short_name(src)}-{code_to_short_name(tgt)}"
+            yaml_file_name = f"flores_{lang_pair_name}.yaml"
+
+            try:
+                with open(
+                    f"{output_dir}/{yaml_file_name}",
+                    "w" if overwrite else "x",
+                    encoding="utf-8",
+                ) as outfile:
+                    print(f"Creating {yaml_file_name}...")
+                    outfile.write("# File generated by `create-yamls.py`\n")
+                    yaml.dump(
+                        {
+                            #                             "group": [f"{BENCH_NAME}_bench", f"{BENCH_NAME}_bench_flores"],
+                            #                            "group": "flores_ca",
+                            "include": "_flores_common_yaml",
+                            "task": f"flores_{lang_pair_name}",
+                            "doc_to_text": doc_to_text(src, tgt),
+                            "doc_to_target": doc_to_target(tgt),
+                        },
+                        outfile,
+                        sort_keys=False,
+                    )
+
+            except FileExistsError:
+                err.append(yaml_file_name)
+
+    if len(err) > 0:
+        raise FileExistsError(
+            "Files were not created because they already exist:"
+            f" {', '.join(err)}"
+            "\nUse flag --overwrite to overwrite them."
+        )
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "--overwrite",
+        default=False,
+        action="store_true",
+        help="Overwrite files if they already exist",
+    )
+    parser.add_argument(
+        "--output-dir", default=".", help="Directory to write yaml files to"
+    )
+    args = parser.parse_args()
+
+    gen_lang_yamls(output_dir=args.output_dir, overwrite=args.overwrite)
+
+
+if __name__ == "__main__":
+    main()

lm_eval/tasks/catalan_bench/flores_ca/flores_ca-de.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_ca-de
+doc_to_text: 'Catalan sentence: {{sentence_cat_Latn}}
+
+  German sentence:'
+doc_to_target: '{{sentence_deu_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_ca-en.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_ca-en
+doc_to_text: 'Catalan sentence: {{sentence_cat_Latn}}
+
+  English sentence:'
+doc_to_target: '{{sentence_eng_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_ca-es.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_ca-es
+doc_to_text: 'Catalan sentence: {{sentence_cat_Latn}}
+
+  Spanish sentence:'
+doc_to_target: '{{sentence_spa_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_ca-eu.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_ca-eu
+doc_to_text: 'Catalan sentence: {{sentence_cat_Latn}}
+
+  Basque sentence:'
+doc_to_target: '{{sentence_eus_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_ca-fr.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_ca-fr
+doc_to_text: 'Catalan sentence: {{sentence_cat_Latn}}
+
+  French sentence:'
+doc_to_target: '{{sentence_fra_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_ca-gl.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_ca-gl
+doc_to_text: 'Catalan sentence: {{sentence_cat_Latn}}
+
+  Galician sentence:'
+doc_to_target: '{{sentence_glg_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_ca-it.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_ca-it
+doc_to_text: 'Catalan sentence: {{sentence_cat_Latn}}
+
+  Italian sentence:'
+doc_to_target: '{{sentence_ita_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_ca-pt.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_ca-pt
+doc_to_text: 'Catalan sentence: {{sentence_cat_Latn}}
+
+  Portuguese sentence:'
+doc_to_target: '{{sentence_por_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_ca.yaml

+group: flores_ca
+task:
+  - flores_es-ca
+  - flores_ca-es
+  - flores_en-ca
+  - flores_ca-en
+  - flores_eu-ca
+  - flores_ca-eu
+  - flores_pt-ca
+  - flores_ca-pt
+  - flores_it-ca
+  - flores_ca-it
+  - flores_fr-ca
+  - flores_ca-fr
+  - flores_ca-gl
+  - flores_gl-ca
+  - flores_ca-de
+  - flores_de-ca
+aggregate_metric_list:
+  - metric: bleu
+    aggregation: mean
+    weight_by_size: false
+metadata:
+  version: 1.0

lm_eval/tasks/catalan_bench/flores_ca/flores_de-ca.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_de-ca
+doc_to_text: 'German sentence: {{sentence_deu_Latn}}
+
+  Catalan sentence:'
+doc_to_target: '{{sentence_cat_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_en-ca.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_en-ca
+doc_to_text: 'English sentence: {{sentence_eng_Latn}}
+
+  Catalan sentence:'
+doc_to_target: '{{sentence_cat_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_es-ca.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_es-ca
+doc_to_text: 'Spanish sentence: {{sentence_spa_Latn}}
+
+  Catalan sentence:'
+doc_to_target: '{{sentence_cat_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_eu-ca.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_eu-ca
+doc_to_text: 'Basque sentence: {{sentence_eus_Latn}}
+
+  Catalan sentence:'
+doc_to_target: '{{sentence_cat_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_fr-ca.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_fr-ca
+doc_to_text: 'French sentence: {{sentence_fra_Latn}}
+
+  Catalan sentence:'
+doc_to_target: '{{sentence_cat_Latn}}'

lm_eval/tasks/catalan_bench/flores_ca/flores_gl-ca.yaml

+# File generated by `create-yamls.py`
+include: _flores_common_yaml
+task: flores_gl-ca
+doc_to_text: 'Galician sentence: {{sentence_glg_Latn}}
+
+  Catalan sentence:'
+doc_to_target: '{{sentence_cat_Latn}}'