{ "counts": { "duplicate_pairs_removed": 101879, "groups_with_multiple_responses": 133562, "invalid_or_empty_rows": 283, "prompt_groups": 2339573, "retained_rows": 3492041, "source_rows": 3594203 }, "files": { "dataset_info.json": { "bytes": 560, "sha256": "049ff7f6702cdf4e49f0afb491bb2aad4552e96c96565f191564665fe8c74d1d" }, "eval.jsonl": { "bytes": 475745, "rows": 1000, "sha256": "154ebcf5f73f1711865d389b3a7d483ca1006098ff5d25881bbabb5cfcb8a1e0" }, "eval.metadata.jsonl": { "bytes": 416790, "rows": 1000, "sha256": "7864cb71daf35d56ea3caebb496108839d7d4e36653effd0741507e21a8e1e47" }, "test.jsonl": { "bytes": 449384, "rows": 1000, "sha256": "9e6df865c825979b5b3d458a8a832406ce5a859e8f9aaa9e567b7377e41c1324" }, "test.metadata.jsonl": { "bytes": 414881, "rows": 1000, "sha256": "a5a46723acc22f20c99a29e3b338d6986201c943c6b937f7402e2f04f671c8f3" }, "train.jsonl": { "bytes": 1636857404, "rows": 3490041, "sha256": "39acf85df1401f9748f665d29754bd57234f45bca37195eb891f3ce696e5a1ab" }, "train.metadata.jsonl": { "bytes": 1464274344, "rows": 3490041, "sha256": "2d8ce0a5394487463ea8292b6e9bf376a11dd4f79700292cf8a65fe9ca3a66a3" } }, "format_version": 1, "preparation_script_sha256": "5b126cdcfcaf0e38a38ff45f98fde9409b69eb10a925d6444990a90f99830b9b", "prepared_at_utc": "2026-11-08T03:52:39.903856+00:00", "requested_holdout_max_rows": { "eval": 1000, "test": 1000 }, "seed": 42, "source": { "bytes": 931479534, "kind": "local_parquet", "path": "/mnt/project/perun26012578/raw/slovak_train.parquet", "revision": null, "sha256": "6a21c52b80549cbb8f9d13de981a2d8f65c273a17f651fd09c1efcc952821e82" }, "source_breakdown": [ { "dataset_name": "Adversarial QA (T)", "prompt_groups": 4, "rows": 4, "split": "eval", "task_type": "question-answering" }, { "dataset_name": "CNN-Daily-Mail (T)", "prompt_groups": 29, "rows": 29, "split": "eval", "task_type": "summarization" }, { "dataset_name": "Dolly-v2 (T)", "prompt_groups": 6, "rows": 6, "split": "eval", "task_type": "generation" }, { "dataset_name": "Flan-CoT-submix (T)", "prompt_groups": 30, "rows": 30, "split": "eval", "task_type": "generation" }, { "dataset_name": "Flan-Coqa (T)", "prompt_groups": 1, "rows": 1, "split": "eval", "task_type": "question-answering" }, { "dataset_name": "Flan-GEM-wiki-lingua (T)", "prompt_groups": 9, "rows": 9, "split": "eval", "task_type": "summarization" }, { "dataset_name": "Flan-lambada (T)", "prompt_groups": 2, "rows": 2, "split": "eval", "task_type": "generation" }, { "dataset_name": "Flan-unified-QA (T)", "prompt_groups": 2, "rows": 2, "split": "eval", "task_type": "question-answering" }, { "dataset_name": "HotpotQA (T)", "prompt_groups": 80, "rows": 80, "split": "eval", "task_type": "question-answering" }, { "dataset_name": "NQ-Open (T)", "prompt_groups": 60, "rows": 60, "split": "eval", "task_type": "question-answering" }, { "dataset_name": "PAWS-Wiki (T)", "prompt_groups": 7, "rows": 7, "split": "eval", "task_type": "paraphrase-identification" }, { "dataset_name": "PIQA (T)", "prompt_groups": 7, "rows": 7, "split": "eval", "task_type": "question-answering" }, { "dataset_name": "SODA-inst (T)", "prompt_groups": 34, "rows": 267, "split": "eval", "task_type": "dialogue" }, { "dataset_name": "UNER-LLM-inst", "prompt_groups": 2, "rows": 2, "split": "eval", "task_type": "named-entity-recognition" }, { "dataset_name": "Wiki-split-inst (T)", "prompt_groups": 329, "rows": 334, "split": "eval", "task_type": "text-simplification" }, { "dataset_name": "Xlel_wd-inst", "prompt_groups": 4, "rows": 4, "split": "eval", "task_type": "event-linking" }, { "dataset_name": "Xlel_wd-inst (T)", "prompt_groups": 156, "rows": 156, "split": "eval", "task_type": "event-linking" }, { "dataset_name": "Adversarial QA (T)", "prompt_groups": 3, "rows": 3, "split": "test", "task_type": "question-answering" }, { "dataset_name": "CNN-Daily-Mail (T)", "prompt_groups": 19, "rows": 19, "split": "test", "task_type": "summarization" }, { "dataset_name": "Dolly-v2 (T)", "prompt_groups": 3, "rows": 3, "split": "test", "task_type": "generation" }, { "dataset_name": "Flan-CoT-submix (T)", "prompt_groups": 28, "rows": 28, "split": "test", "task_type": "generation" }, { "dataset_name": "Flan-Coqa (T)", "prompt_groups": 3, "rows": 3, "split": "test", "task_type": "question-answering" }, { "dataset_name": "Flan-GEM-wiki-lingua (T)", "prompt_groups": 8, "rows": 8, "split": "test", "task_type": "summarization" }, { "dataset_name": "HotpotQA (T)", "prompt_groups": 67, "rows": 67, "split": "test", "task_type": "question-answering" }, { "dataset_name": "Joke-explaination-inst (T)", "prompt_groups": 1, "rows": 1, "split": "test", "task_type": "generation" }, { "dataset_name": "NQ-Open (T)", "prompt_groups": 49, "rows": 51, "split": "test", "task_type": "question-answering" }, { "dataset_name": "PAWS-Wiki (T)", "prompt_groups": 15, "rows": 15, "split": "test", "task_type": "paraphrase-identification" }, { "dataset_name": "PIQA (T)", "prompt_groups": 7, "rows": 7, "split": "test", "task_type": "question-answering" }, { "dataset_name": "SODA-inst (T)", "prompt_groups": 37, "rows": 379, "split": "test", "task_type": "dialogue" }, { "dataset_name": "UNER-LLM-inst", "prompt_groups": 4, "rows": 4, "split": "test", "task_type": "named-entity-recognition" }, { "dataset_name": "Wiki-split-inst (T)", "prompt_groups": 273, "rows": 277, "split": "test", "task_type": "text-simplification" }, { "dataset_name": "Xlel_wd-inst", "prompt_groups": 4, "rows": 4, "split": "test", "task_type": "event-linking" }, { "dataset_name": "Xlel_wd-inst (T)", "prompt_groups": 131, "rows": 131, "split": "test", "task_type": "event-linking" }, { "dataset_name": "Adversarial QA (T)", "prompt_groups": 9686, "rows": 9984, "split": "train", "task_type": "question-answering" }, { "dataset_name": "CNN-Daily-Mail (T)", "prompt_groups": 98366, "rows": 98381, "split": "train", "task_type": "summarization" }, { "dataset_name": "Dolly-v2 (T)", "prompt_groups": 14559, "rows": 14783, "split": "train", "task_type": "generation" }, { "dataset_name": "Flan-CoT-submix (T)", "prompt_groups": 88084, "rows": 91852, "split": "train", "task_type": "generation" }, { "dataset_name": "Flan-Coqa (T)", "prompt_groups": 6405, "rows": 6405, "split": "train", "task_type": "question-answering" }, { "dataset_name": "Flan-GEM-wiki-lingua (T)", "prompt_groups": 27128, "rows": 27130, "split": "train", "task_type": "summarization" }, { "dataset_name": "Flan-lambada (T)", "prompt_groups": 4277, "rows": 4277, "split": "train", "task_type": "generation" }, { "dataset_name": "Flan-unified-QA (T)", "prompt_groups": 538, "rows": 538, "split": "train", "task_type": "question-answering" }, { "dataset_name": "HotpotQA (T)", "prompt_groups": 264664, "rows": 266105, "split": "train", "task_type": "question-answering" }, { "dataset_name": "Joke-explaination-inst (T)", "prompt_groups": 724, "rows": 733, "split": "train", "task_type": "generation" }, { "dataset_name": "Mintaka-inst (T)", "prompt_groups": 8, "rows": 13834, "split": "train", "task_type": "question-answering" }, { "dataset_name": "NQ-Open (T)", "prompt_groups": 170153, "rows": 172361, "split": "train", "task_type": "question-answering" }, { "dataset_name": "PAWS-Wiki (T)", "prompt_groups": 46682, "rows": 46746, "split": "train", "task_type": "paraphrase-identification" }, { "dataset_name": "PIQA (T)", "prompt_groups": 16092, "rows": 16093, "split": "train", "task_type": "question-answering" }, { "dataset_name": "SODA-inst (T)", "prompt_groups": 116604, "rows": 1190936, "split": "train", "task_type": "dialogue" }, { "dataset_name": "UNER-LLM-inst", "prompt_groups": 8195, "rows": 8197, "split": "train", "task_type": "named-entity-recognition" }, { "dataset_name": "WIKI QA (T)", "prompt_groups": 1030, "rows": 1039, "split": "train", "task_type": "question-answering" }, { "dataset_name": "Wiki-split-inst (T)", "prompt_groups": 970135, "rows": 988524, "split": "train", "task_type": "text-simplification" }, { "dataset_name": "Xlel_wd-inst", "prompt_groups": 12433, "rows": 13268, "split": "train", "task_type": "event-linking" }, { "dataset_name": "Xlel_wd-inst (T)", "prompt_groups": 482400, "rows": 518855, "split": "train", "task_type": "event-linking" } ], "splits": { "eval": { "prompt_groups": 762, "rows": 1000 }, "test": { "prompt_groups": 652, "rows": 1000 }, "train": { "prompt_groups": 2338159, "rows": 3490041 } } }