Commit
•
77c5c17
1
Parent(s):
a61dd96
Upload data_budget_hours_24.json with huggingface_hub
Browse files- data_budget_hours_24.json +67 -0
data_budget_hours_24.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"sources": {
|
| 3 |
+
"the_pile": {
|
| 4 |
+
"provider": "local",
|
| 5 |
+
"file_type": "json",
|
| 6 |
+
"files": [
|
| 7 |
+
"/fs/cml-datasets/Pile/train/00.jsonl.zst",
|
| 8 |
+
"/fs/cml-datasets/Pile/train/01.jsonl.zst",
|
| 9 |
+
"/fs/cml-datasets/Pile/train/02.jsonl.zst",
|
| 10 |
+
"/fs/cml-datasets/Pile/train/03.jsonl.zst",
|
| 11 |
+
"/fs/cml-datasets/Pile/train/04.jsonl.zst",
|
| 12 |
+
"/fs/cml-datasets/Pile/train/05.jsonl.zst",
|
| 13 |
+
"/fs/cml-datasets/Pile/train/06.jsonl.zst",
|
| 14 |
+
"/fs/cml-datasets/Pile/train/07.jsonl.zst",
|
| 15 |
+
"/fs/cml-datasets/Pile/train/08.jsonl.zst",
|
| 16 |
+
"/fs/cml-datasets/Pile/train/09.jsonl.zst",
|
| 17 |
+
"/fs/cml-datasets/Pile/train/10.jsonl.zst",
|
| 18 |
+
"/fs/cml-datasets/Pile/train/11.jsonl.zst",
|
| 19 |
+
"/fs/cml-datasets/Pile/train/12.jsonl.zst",
|
| 20 |
+
"/fs/cml-datasets/Pile/train/13.jsonl.zst",
|
| 21 |
+
"/fs/cml-datasets/Pile/train/14.jsonl.zst",
|
| 22 |
+
"/fs/cml-datasets/Pile/train/15.jsonl.zst",
|
| 23 |
+
"/fs/cml-datasets/Pile/train/16.jsonl.zst",
|
| 24 |
+
"/fs/cml-datasets/Pile/train/17.jsonl.zst",
|
| 25 |
+
"/fs/cml-datasets/Pile/train/18.jsonl.zst",
|
| 26 |
+
"/fs/cml-datasets/Pile/train/19.jsonl.zst",
|
| 27 |
+
"/fs/cml-datasets/Pile/train/20.jsonl.zst",
|
| 28 |
+
"/fs/cml-datasets/Pile/train/21.jsonl.zst",
|
| 29 |
+
"/fs/cml-datasets/Pile/train/22.jsonl.zst",
|
| 30 |
+
"/fs/cml-datasets/Pile/train/23.jsonl.zst",
|
| 31 |
+
"/fs/cml-datasets/Pile/train/24.jsonl.zst",
|
| 32 |
+
"/fs/cml-datasets/Pile/train/25.jsonl.zst",
|
| 33 |
+
"/fs/cml-datasets/Pile/train/26.jsonl.zst",
|
| 34 |
+
"/fs/cml-datasets/Pile/train/27.jsonl.zst",
|
| 35 |
+
"/fs/cml-datasets/Pile/train/28.jsonl.zst",
|
| 36 |
+
"/fs/cml-datasets/Pile/train/29.jsonl.zst"
|
| 37 |
+
],
|
| 38 |
+
"filter": null,
|
| 39 |
+
"split": "train",
|
| 40 |
+
"streaming": true,
|
| 41 |
+
"remove_columns": null,
|
| 42 |
+
"concatenate_successive_entries": 0
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"name": "the_pile",
|
| 46 |
+
"normalizer": {
|
| 47 |
+
"force_lowercase": true,
|
| 48 |
+
"strip_accents": true,
|
| 49 |
+
"force_english_keyboard": true,
|
| 50 |
+
"whitespace_escape": false
|
| 51 |
+
},
|
| 52 |
+
"tokenizer": "WordPiece",
|
| 53 |
+
"vocab_size": 32768,
|
| 54 |
+
"seq_length": 128,
|
| 55 |
+
"include_cls_token_in_corpus": false,
|
| 56 |
+
"include_sep_token_in_corpus": true,
|
| 57 |
+
"use_type_ids": false,
|
| 58 |
+
"max_entries_in_raw_dataset": 8000000.0,
|
| 59 |
+
"max_seq_in_tokenized_dataset": 85000000.0,
|
| 60 |
+
"named_entity_simplification": false,
|
| 61 |
+
"remove_whitespaces": false,
|
| 62 |
+
"remove_trash": true,
|
| 63 |
+
"trash_cutoff": 0.25,
|
| 64 |
+
"deduplicate_entries": false,
|
| 65 |
+
"deduplication_threshold": 75,
|
| 66 |
+
"ordering": "sentence-length-curriculum"
|
| 67 |
+
}
|