Upload folder using huggingface_hub
Browse files- data-00000-of-00038.arrow +3 -0
- data-00001-of-00038.arrow +3 -0
- data-00002-of-00038.arrow +3 -0
- data-00003-of-00038.arrow +3 -0
- data-00004-of-00038.arrow +3 -0
- data-00005-of-00038.arrow +3 -0
- data-00006-of-00038.arrow +3 -0
- data-00007-of-00038.arrow +3 -0
- data-00008-of-00038.arrow +3 -0
- data-00009-of-00038.arrow +3 -0
- data-00010-of-00038.arrow +3 -0
- data-00011-of-00038.arrow +3 -0
- data-00012-of-00038.arrow +3 -0
- data-00013-of-00038.arrow +3 -0
- data-00014-of-00038.arrow +3 -0
- data-00015-of-00038.arrow +3 -0
- data-00016-of-00038.arrow +3 -0
- data-00017-of-00038.arrow +3 -0
- data-00018-of-00038.arrow +3 -0
- data-00019-of-00038.arrow +3 -0
- data-00020-of-00038.arrow +3 -0
- data-00021-of-00038.arrow +3 -0
- data-00022-of-00038.arrow +3 -0
- data-00023-of-00038.arrow +3 -0
- data-00024-of-00038.arrow +3 -0
- data-00025-of-00038.arrow +3 -0
- data-00026-of-00038.arrow +3 -0
- data-00027-of-00038.arrow +3 -0
- data-00028-of-00038.arrow +3 -0
- data-00029-of-00038.arrow +3 -0
- data-00030-of-00038.arrow +3 -0
- data-00031-of-00038.arrow +3 -0
- data-00032-of-00038.arrow +3 -0
- data-00033-of-00038.arrow +3 -0
- data-00034-of-00038.arrow +3 -0
- data-00035-of-00038.arrow +3 -0
- data-00036-of-00038.arrow +3 -0
- data-00037-of-00038.arrow +3 -0
- dataset_info.json +214 -0
- state.json +124 -0
data-00000-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9494f3ab54ec3ab4073f8186bd72a117034832971700ab75a48ebc398711867
|
| 3 |
+
size 487501080
|
data-00001-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86e8e6dc4e25ea5015d0523dccc0b4377df24cc2e962cd698eca05683cf12551
|
| 3 |
+
size 491954016
|
data-00002-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6f5463a8b3bd66da446d6953d9c0bc7042c30f5d2adb7c845c20583cb2ecf86
|
| 3 |
+
size 479718848
|
data-00003-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dfa986bb31341f679a4b223f8ba09b2470318e7033c9c887a280dc266f1455b
|
| 3 |
+
size 488730624
|
data-00004-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74720da1ba0c956d8c10101e326c331a94210127d690a39488fbbbe5d6e6226a
|
| 3 |
+
size 490776048
|
data-00005-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f164adf618798d144cb5db51d0d9474a13bd0587ee14f07ba01958e264564e65
|
| 3 |
+
size 495879000
|
data-00006-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12612ae4e0b3221cbc37119d8f92ae32a41839d45ca359876e6222f5d4e5d843
|
| 3 |
+
size 487081136
|
data-00007-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3109bd1058ee41368881adbee7be84156456b0ea5fb5eba133756414faee522
|
| 3 |
+
size 485015744
|
data-00008-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8512c339916d3fc25217e7f12e97b8fee7364932b3735a6d37a46937e0bef695
|
| 3 |
+
size 499956656
|
data-00009-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53660cc0c72ab77b5760510081227eff5799516ec78bb2654cbf30a088688372
|
| 3 |
+
size 480309376
|
data-00010-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7540c54c9984695a09ce3bb9351d1af05fe051cd089446415d7dfc8797fe643c
|
| 3 |
+
size 482949432
|
data-00011-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e3e393a3e64e40f7c813316c31d0fadf0dd1fbc4fde962df4cbca6ba3a2d44d
|
| 3 |
+
size 492876712
|
data-00012-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7727132a3b48e2723b0f6251eabf5eda77875215a7500be5688e74007d5ed239
|
| 3 |
+
size 487963840
|
data-00013-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecfcd0304f9b5d3c8f3170da9f4d88412c6e3ac2fe357d90c7bca12044be6515
|
| 3 |
+
size 496644072
|
data-00014-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8ff3e47d98214b244aeca9158b6131a0475f4f782d81c5335f5c376a01b40c5
|
| 3 |
+
size 489826848
|
data-00015-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7b708c94f0d15735e2400249e3e774094582676fb4baa9a5fa700164d22f58c
|
| 3 |
+
size 483721248
|
data-00016-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:553cabac0c61ef753f99013378ede2794cd80ece74936484f9d57af02d0836b5
|
| 3 |
+
size 500170848
|
data-00017-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:faf37d9ad1ebf507dfa613a478a78705222b80b1fa971796a3f97dff0eef7d61
|
| 3 |
+
size 491021784
|
data-00018-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10530dadd7af93b23c311ca84b2112cbf2794423032323c7b035189c968b2299
|
| 3 |
+
size 482726944
|
data-00019-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e24597f9724fe8131ae24de02e3087ae0581ee55bb798d20b0f989e352ed457
|
| 3 |
+
size 483869648
|
data-00020-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee739c54957f158dc95e962c2216feb972638768c714e4cf33c0634da169b42b
|
| 3 |
+
size 478443832
|
data-00021-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fca3f3cff7699a2a6d07e9b06d8031ac49294369a4c731db7b173d38398dce66
|
| 3 |
+
size 487069888
|
data-00022-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fcd4611aed6b6f9842425dd38dc2f4b4bc1f915e661af6756db5eb263821ac0
|
| 3 |
+
size 485343920
|
data-00023-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0ef08f2a9e5618ec6e2907d5733fb17ffc378078b898a5f55a54675f892c3a3
|
| 3 |
+
size 490252128
|
data-00024-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76bfe20c2a4d8c53eb146cecae0d7ca65fdc23cdc0d4103fd7648b33e877d43b
|
| 3 |
+
size 480027440
|
data-00025-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ff28cfd9eba3e64713a4b1647253d009325e1b446dd1a8d0d3a1f3945536927
|
| 3 |
+
size 481756280
|
data-00026-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a27e850c0d07ad4b216c392f5963afb2052a1c37f200940b38485672677ef956
|
| 3 |
+
size 488331808
|
data-00027-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50ae107960dbbe17f880d23e0985e8bfc186a8930b9151d66384db7f171c5af4
|
| 3 |
+
size 480714496
|
data-00028-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d42c5b0ce4ef2d98fc2c13dc8c869d06042cca7ed702160231ceb7814b11c58
|
| 3 |
+
size 492508480
|
data-00029-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18b594f561cfd6099c3e2754ddfed327e27bc381d3930a2f63cca602abab9356
|
| 3 |
+
size 486451752
|
data-00030-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce90a7363d9b1b222c2abc24c6e90288b049696dfa9b3743e5c55431b441fb5c
|
| 3 |
+
size 490103480
|
data-00031-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:474818cd24f727fdea41d27beffac3d6029f00632c01224d2aca79c26784c4d8
|
| 3 |
+
size 490307728
|
data-00032-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55d55c1bc7058af741eca5c7ee94ff9a0f809319a4283c17e0c967599ca0c527
|
| 3 |
+
size 487202952
|
data-00033-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:659abd246dfae6a8c470c440ee6987970ec9b654d0433e8edc5996452e3a9387
|
| 3 |
+
size 479283872
|
data-00034-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84de7a91e50547003d3f3422e141a10753e6a06f7d25eb2bc37bbacfe764776c
|
| 3 |
+
size 482694400
|
data-00035-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:029a99f01cde258173cd32a8244c457bdaab6d83622e126b84749e4f8d2f9c73
|
| 3 |
+
size 482945152
|
data-00036-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34210465230c08c8bc00f1392fb85e508d68dd7e4cb8b772b342384069cf4713
|
| 3 |
+
size 483156824
|
data-00037-of-00038.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffcda05d94d87dd2d93bf689e62ba9bd6544cb0449b1b39407ded3ba0f75c8c0
|
| 3 |
+
size 484386208
|
dataset_info.json
ADDED
|
@@ -0,0 +1,214 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"builder_name": "openwebtext",
|
| 3 |
+
"citation": "@misc{Gokaslan2019OpenWeb,\n title={OpenWebText Corpus},\n author={Aaron Gokaslan*, Vanya Cohen*, Ellie Pavlick, Stefanie Tellex},\n howpublished{\\url{http://Skylion007.github.io/OpenWebTextCorpus}},\n year={2019}\n}\n",
|
| 4 |
+
"config_name": "plain_text",
|
| 5 |
+
"dataset_name": "openwebtext",
|
| 6 |
+
"dataset_size": 39769491688,
|
| 7 |
+
"description": "An open-source replication of the WebText dataset from OpenAI.\n",
|
| 8 |
+
"download_checksums": {
|
| 9 |
+
"subsets/urlsf_subset00.tar": {
|
| 10 |
+
"num_bytes": 633047040,
|
| 11 |
+
"checksum": null
|
| 12 |
+
},
|
| 13 |
+
"subsets/urlsf_subset01.tar": {
|
| 14 |
+
"num_bytes": 628838400,
|
| 15 |
+
"checksum": null
|
| 16 |
+
},
|
| 17 |
+
"subsets/urlsf_subset02.tar": {
|
| 18 |
+
"num_bytes": 629125120,
|
| 19 |
+
"checksum": null
|
| 20 |
+
},
|
| 21 |
+
"subsets/urlsf_subset03.tar": {
|
| 22 |
+
"num_bytes": 627578880,
|
| 23 |
+
"checksum": null
|
| 24 |
+
},
|
| 25 |
+
"subsets/urlsf_subset04.tar": {
|
| 26 |
+
"num_bytes": 627189760,
|
| 27 |
+
"checksum": null
|
| 28 |
+
},
|
| 29 |
+
"subsets/urlsf_subset05.tar": {
|
| 30 |
+
"num_bytes": 630200320,
|
| 31 |
+
"checksum": null
|
| 32 |
+
},
|
| 33 |
+
"subsets/urlsf_subset06.tar": {
|
| 34 |
+
"num_bytes": 625612800,
|
| 35 |
+
"checksum": null
|
| 36 |
+
},
|
| 37 |
+
"subsets/urlsf_subset07.tar": {
|
| 38 |
+
"num_bytes": 625356800,
|
| 39 |
+
"checksum": null
|
| 40 |
+
},
|
| 41 |
+
"subsets/urlsf_subset08.tar": {
|
| 42 |
+
"num_bytes": 624629760,
|
| 43 |
+
"checksum": null
|
| 44 |
+
},
|
| 45 |
+
"subsets/urlsf_subset09.tar": {
|
| 46 |
+
"num_bytes": 625807360,
|
| 47 |
+
"checksum": null
|
| 48 |
+
},
|
| 49 |
+
"subsets/urlsf_subset10.tar": {
|
| 50 |
+
"num_bytes": 625172480,
|
| 51 |
+
"checksum": null
|
| 52 |
+
},
|
| 53 |
+
"subsets/urlsf_subset11.tar": {
|
| 54 |
+
"num_bytes": 625264640,
|
| 55 |
+
"checksum": null
|
| 56 |
+
},
|
| 57 |
+
"subsets/urlsf_subset12.tar": {
|
| 58 |
+
"num_bytes": 624445440,
|
| 59 |
+
"checksum": null
|
| 60 |
+
},
|
| 61 |
+
"subsets/urlsf_subset13.tar": {
|
| 62 |
+
"num_bytes": 628961280,
|
| 63 |
+
"checksum": null
|
| 64 |
+
},
|
| 65 |
+
"subsets/urlsf_subset14.tar": {
|
| 66 |
+
"num_bytes": 626708480,
|
| 67 |
+
"checksum": null
|
| 68 |
+
},
|
| 69 |
+
"subsets/urlsf_subset15.tar": {
|
| 70 |
+
"num_bytes": 620666880,
|
| 71 |
+
"checksum": null
|
| 72 |
+
},
|
| 73 |
+
"subsets/urlsf_subset16.tar": {
|
| 74 |
+
"num_bytes": 618752000,
|
| 75 |
+
"checksum": null
|
| 76 |
+
},
|
| 77 |
+
"subsets/urlsf_subset17.tar": {
|
| 78 |
+
"num_bytes": 619141120,
|
| 79 |
+
"checksum": null
|
| 80 |
+
},
|
| 81 |
+
"subsets/urlsf_subset18.tar": {
|
| 82 |
+
"num_bytes": 617789440,
|
| 83 |
+
"checksum": null
|
| 84 |
+
},
|
| 85 |
+
"subsets/urlsf_subset19.tar": {
|
| 86 |
+
"num_bytes": 619192320,
|
| 87 |
+
"checksum": null
|
| 88 |
+
},
|
| 89 |
+
"subsets/urlsf_subset20.tar": {
|
| 90 |
+
"num_bytes": 376709120,
|
| 91 |
+
"checksum": null
|
| 92 |
+
}
|
| 93 |
+
},
|
| 94 |
+
"download_size": 12880189440,
|
| 95 |
+
"features": {
|
| 96 |
+
"text": {
|
| 97 |
+
"dtype": "string",
|
| 98 |
+
"_type": "Value"
|
| 99 |
+
},
|
| 100 |
+
"token_ids": {
|
| 101 |
+
"feature": {
|
| 102 |
+
"dtype": "int64",
|
| 103 |
+
"_type": "Value"
|
| 104 |
+
},
|
| 105 |
+
"_type": "Sequence"
|
| 106 |
+
},
|
| 107 |
+
"counterfactual_ids": {
|
| 108 |
+
"feature": {
|
| 109 |
+
"dtype": "int64",
|
| 110 |
+
"_type": "Value"
|
| 111 |
+
},
|
| 112 |
+
"_type": "Sequence"
|
| 113 |
+
}
|
| 114 |
+
},
|
| 115 |
+
"homepage": "https://skylion007.github.io/OpenWebTextCorpus/",
|
| 116 |
+
"license": "",
|
| 117 |
+
"size_in_bytes": 52649681128,
|
| 118 |
+
"splits": {
|
| 119 |
+
"train": {
|
| 120 |
+
"name": "train",
|
| 121 |
+
"num_bytes": 39769491688,
|
| 122 |
+
"num_examples": 8013769,
|
| 123 |
+
"shard_lengths": [
|
| 124 |
+
101000,
|
| 125 |
+
100000,
|
| 126 |
+
101000,
|
| 127 |
+
101000,
|
| 128 |
+
102000,
|
| 129 |
+
102000,
|
| 130 |
+
101000,
|
| 131 |
+
102000,
|
| 132 |
+
101000,
|
| 133 |
+
101000,
|
| 134 |
+
101000,
|
| 135 |
+
101000,
|
| 136 |
+
101000,
|
| 137 |
+
102000,
|
| 138 |
+
101000,
|
| 139 |
+
101000,
|
| 140 |
+
101000,
|
| 141 |
+
101000,
|
| 142 |
+
102000,
|
| 143 |
+
102000,
|
| 144 |
+
100000,
|
| 145 |
+
101000,
|
| 146 |
+
100000,
|
| 147 |
+
101000,
|
| 148 |
+
102000,
|
| 149 |
+
101000,
|
| 150 |
+
102000,
|
| 151 |
+
101000,
|
| 152 |
+
102000,
|
| 153 |
+
102000,
|
| 154 |
+
102000,
|
| 155 |
+
101000,
|
| 156 |
+
101000,
|
| 157 |
+
101000,
|
| 158 |
+
101000,
|
| 159 |
+
102000,
|
| 160 |
+
101000,
|
| 161 |
+
102000,
|
| 162 |
+
101000,
|
| 163 |
+
101000,
|
| 164 |
+
100000,
|
| 165 |
+
101000,
|
| 166 |
+
101000,
|
| 167 |
+
101000,
|
| 168 |
+
101000,
|
| 169 |
+
101000,
|
| 170 |
+
101000,
|
| 171 |
+
101000,
|
| 172 |
+
101000,
|
| 173 |
+
101000,
|
| 174 |
+
101000,
|
| 175 |
+
100000,
|
| 176 |
+
101000,
|
| 177 |
+
102000,
|
| 178 |
+
101000,
|
| 179 |
+
101000,
|
| 180 |
+
101000,
|
| 181 |
+
101000,
|
| 182 |
+
101000,
|
| 183 |
+
102000,
|
| 184 |
+
102000,
|
| 185 |
+
101000,
|
| 186 |
+
102000,
|
| 187 |
+
101000,
|
| 188 |
+
102000,
|
| 189 |
+
102000,
|
| 190 |
+
101000,
|
| 191 |
+
101000,
|
| 192 |
+
102000,
|
| 193 |
+
102000,
|
| 194 |
+
102000,
|
| 195 |
+
101000,
|
| 196 |
+
102000,
|
| 197 |
+
102000,
|
| 198 |
+
102000,
|
| 199 |
+
101000,
|
| 200 |
+
101000,
|
| 201 |
+
102000,
|
| 202 |
+
101000,
|
| 203 |
+
13769
|
| 204 |
+
],
|
| 205 |
+
"dataset_name": "openwebtext"
|
| 206 |
+
}
|
| 207 |
+
},
|
| 208 |
+
"version": {
|
| 209 |
+
"version_str": "1.0.0",
|
| 210 |
+
"major": 1,
|
| 211 |
+
"minor": 0,
|
| 212 |
+
"patch": 0
|
| 213 |
+
}
|
| 214 |
+
}
|
state.json
ADDED
|
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00038.arrow"
|
| 5 |
+
},
|
| 6 |
+
{
|
| 7 |
+
"filename": "data-00001-of-00038.arrow"
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"filename": "data-00002-of-00038.arrow"
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"filename": "data-00003-of-00038.arrow"
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"filename": "data-00004-of-00038.arrow"
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"filename": "data-00005-of-00038.arrow"
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"filename": "data-00006-of-00038.arrow"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"filename": "data-00007-of-00038.arrow"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"filename": "data-00008-of-00038.arrow"
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"filename": "data-00009-of-00038.arrow"
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"filename": "data-00010-of-00038.arrow"
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"filename": "data-00011-of-00038.arrow"
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"filename": "data-00012-of-00038.arrow"
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"filename": "data-00013-of-00038.arrow"
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"filename": "data-00014-of-00038.arrow"
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"filename": "data-00015-of-00038.arrow"
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"filename": "data-00016-of-00038.arrow"
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"filename": "data-00017-of-00038.arrow"
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"filename": "data-00018-of-00038.arrow"
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"filename": "data-00019-of-00038.arrow"
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"filename": "data-00020-of-00038.arrow"
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"filename": "data-00021-of-00038.arrow"
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"filename": "data-00022-of-00038.arrow"
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"filename": "data-00023-of-00038.arrow"
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"filename": "data-00024-of-00038.arrow"
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"filename": "data-00025-of-00038.arrow"
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"filename": "data-00026-of-00038.arrow"
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"filename": "data-00027-of-00038.arrow"
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"filename": "data-00028-of-00038.arrow"
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"filename": "data-00029-of-00038.arrow"
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"filename": "data-00030-of-00038.arrow"
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"filename": "data-00031-of-00038.arrow"
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"filename": "data-00032-of-00038.arrow"
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"filename": "data-00033-of-00038.arrow"
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"filename": "data-00034-of-00038.arrow"
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"filename": "data-00035-of-00038.arrow"
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"filename": "data-00036-of-00038.arrow"
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"filename": "data-00037-of-00038.arrow"
|
| 116 |
+
}
|
| 117 |
+
],
|
| 118 |
+
"_fingerprint": "74d0c30dce8b356d",
|
| 119 |
+
"_format_columns": null,
|
| 120 |
+
"_format_kwargs": {},
|
| 121 |
+
"_format_type": null,
|
| 122 |
+
"_output_all_columns": false,
|
| 123 |
+
"_split": null
|
| 124 |
+
}
|