"validation_pretraining: 0.0330676168743166 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/ar/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_ar_text_document, 0.011242051312222764 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/ca/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_ca_text_document, 0.13027200903379185 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/code/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_code_text_document, 0.22171164529099704 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/en/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_en_text_document, 0.10667815627928671 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/es/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_es_text_document, 0.0015595123898173287 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/eu/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_eu_text_document, 0.13054018439603915 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/fr/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_fr_text_document, 0.01091803753667153 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/id/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_id_text_document, 0.00011021422347108609 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-as/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-as_text_document, 0.005492381453597748 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-bn/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-bn_text_document, 0.0004021215011318779 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-gu/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-gu_text_document, 0.007470068593492175 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-hi/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-hi_text_document, 0.0006190467776576425 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-kn/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-kn_text_document, 0.0010335296343329384 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-ml/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-ml_text_document, 0.0005012010684646179 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-mr/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-mr_text_document, 0.0006672772956128299 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-ne/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-ne_text_document, 0.00035928138344705506 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-or/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-or_text_document, 0.0005084433130291778 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-pa/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-pa_text_document, 0.0021137328219915496 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-ta/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-ta_text_document, 0.0009129946225980253 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-te/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-te_text_document, 0.0012454301613725426 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/indic-ur/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_indic-ur_text_document, 0.00031588689199263235 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/nigercongo-all/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_nigercongo-all_text_document, 0.08137213783015229 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/oscar-en/meg_ds_bigscience_tokenizer_text_document, 0.055293935695898196 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/oscar-zh/meg_ds_bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_text_document, 0.04954150576361177 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/pt/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_pt_text_document, 0.02461641286531197 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/vi/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_vi_text_document, 0.12091748245519074 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/zhs/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_zhs_text_document, 0.0005177025345001541 0.950:1.0 /gpfsdsstore/projects/rech/six/commun/merged-meg-ds_v3_pii/zht/bigscience-catalogue-data-dev_byte-level-bpe-tokenizer-no-norm-250k-whitespace-and-eos-regex-alpha-v3-dedup-lines-articles_zht_text_document" "validation: 0.3924620202 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_en, 0.0797519865 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_es, 0.0645613968 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_pt, 0.0592991658 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_code, 0.0584218969 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_fr, 0.0492644683 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ar, 0.0485168956 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_id, 0.048344327 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_zh, 0.0462777165 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_hi, 0.0326663657 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_vi, 0.0202046859 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ur, 0.0140392334 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_te, 0.0097374884 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ta, 0.0087708344 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_bn, 0.0070173416 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_mr, 0.0059077793 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_sw, 0.0059055884 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_gu, 0.0055112422 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_pa, 0.0041465344 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ne, 0.0037157869 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_yo, 0.0034255885 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ig, 0.0028662571 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ny, 0.0027776135 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_zu, 0.0026823974 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_xh, 0.0026594781 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_sn, 0.0026358847 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ts, 0.0026264474 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_rw, 0.0024850557 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_lg, 0.0024808426 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_tn, 0.0024194999 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_nso, 0.0020327371 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_rn, 0.0018436532 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ml, 0.0017427072 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_kn, 0.0017007448 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_or, 0.0016458059 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_as, 0.0013303289 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ln, 0.0012908943 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_wo, 0.0012221364 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_tum, 0.001211688 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ki, 0.0012015765 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_st, 0.0011909595 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_fon, 0.0011650068 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ca, 0.001138717 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_eu, 0.0011385485 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_ak, 0.0011275944 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_bm, 0.0011195053 0.950:1 /gpfswork/rech/six/commun/bigscience-training/xp3cappedmixednewcodelong/xp3_tw"