Initial upload of multiple checkpoints
Browse files- data-00000-of-00012.arrow +3 -0
- data-00001-of-00012.arrow +3 -0
- data-00002-of-00012.arrow +3 -0
- data-00003-of-00012.arrow +3 -0
- data-00004-of-00012.arrow +3 -0
- data-00005-of-00012.arrow +3 -0
- data-00006-of-00012.arrow +3 -0
- data-00007-of-00012.arrow +3 -0
- data-00008-of-00012.arrow +3 -0
- data-00009-of-00012.arrow +3 -0
- data-00010-of-00012.arrow +3 -0
- data-00011-of-00012.arrow +3 -0
- dataset_info.json +73 -0
- state.json +46 -0
data-00000-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76e03caeb716d0d247d81b584c438076ddf7093f242771c521a1324a04194758
|
| 3 |
+
size 507442744
|
data-00001-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:789533d3c22f7f9697b5b4d34ab453f43bab5649bcd2c5c5f3e49a8a88c148c4
|
| 3 |
+
size 488601488
|
data-00002-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c1e7c275dfc8708e193e5f5c148970c66e331564afa8975b7a84e5e231894e7
|
| 3 |
+
size 563781856
|
data-00003-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b30b9cdbe24527cca4a3a02aacebe30edc02d3284f33de163ff20dea7488a63a
|
| 3 |
+
size 504856544
|
data-00004-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b5c25b71c5d6ac284222fc9486ac644e101dc7ed13d6508f4f404714dc6bce3
|
| 3 |
+
size 481932344
|
data-00005-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c4d1084624d2711d655de53383c0e6f51ba04ef5644cea6a44b487c2c6240da
|
| 3 |
+
size 516141848
|
data-00006-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac4e50171f3ebdc698b0ec967595b3b6380aa569c3e2958b839e9b65e2beee54
|
| 3 |
+
size 356910272
|
data-00007-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e761bdd5e7e1118200076a607f0ec30451f84c1a5d710e81ea68d162479830e
|
| 3 |
+
size 416740984
|
data-00008-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4199aa8ab8e59036ce6c16fcf1039adcd84e6b78465662ab78409fb8e06a61b
|
| 3 |
+
size 472785008
|
data-00009-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:110ad5a5ad78d1eb18451ac3e39f4a022c774cac6f4057e64c2c921887acef2b
|
| 3 |
+
size 475780072
|
data-00010-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f60d52d6a8a2b46a6ed0d701a7cfb1eff46d484ca36e913e542a53909213d97d
|
| 3 |
+
size 362354496
|
data-00011-of-00012.arrow
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64f80e7bf81a7869247fa03fcb58d90c3419af59aa14c9408f7a2ab4c619ac8f
|
| 3 |
+
size 515327800
|
dataset_info.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"builder_name": "csv",
|
| 3 |
+
"citation": "",
|
| 4 |
+
"config_name": "default",
|
| 5 |
+
"dataset_name": "csv",
|
| 6 |
+
"dataset_size": 11489580992,
|
| 7 |
+
"description": "",
|
| 8 |
+
"download_checksums": {
|
| 9 |
+
"/l/users/daniil.orel/kaz_news/kazakhNews.csv": {
|
| 10 |
+
"num_bytes": 11469139176,
|
| 11 |
+
"checksum": null
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"download_size": 11469139176,
|
| 15 |
+
"features": {
|
| 16 |
+
"input_ids": {
|
| 17 |
+
"feature": {
|
| 18 |
+
"dtype": "int32",
|
| 19 |
+
"_type": "Value"
|
| 20 |
+
},
|
| 21 |
+
"_type": "Sequence"
|
| 22 |
+
},
|
| 23 |
+
"attention_mask": {
|
| 24 |
+
"feature": {
|
| 25 |
+
"dtype": "int8",
|
| 26 |
+
"_type": "Value"
|
| 27 |
+
},
|
| 28 |
+
"_type": "Sequence"
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"homepage": "",
|
| 32 |
+
"license": "",
|
| 33 |
+
"size_in_bytes": 22958720168,
|
| 34 |
+
"splits": {
|
| 35 |
+
"train": {
|
| 36 |
+
"name": "train",
|
| 37 |
+
"num_bytes": 11489580992,
|
| 38 |
+
"num_examples": 3264273,
|
| 39 |
+
"shard_lengths": [
|
| 40 |
+
160000,
|
| 41 |
+
130000,
|
| 42 |
+
170000,
|
| 43 |
+
150000,
|
| 44 |
+
150000,
|
| 45 |
+
90000,
|
| 46 |
+
130000,
|
| 47 |
+
180000,
|
| 48 |
+
120000,
|
| 49 |
+
130000,
|
| 50 |
+
160000,
|
| 51 |
+
140000,
|
| 52 |
+
300000,
|
| 53 |
+
140000,
|
| 54 |
+
150000,
|
| 55 |
+
160000,
|
| 56 |
+
130000,
|
| 57 |
+
120000,
|
| 58 |
+
120000,
|
| 59 |
+
200000,
|
| 60 |
+
120000,
|
| 61 |
+
100000,
|
| 62 |
+
14273
|
| 63 |
+
],
|
| 64 |
+
"dataset_name": "csv"
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"version": {
|
| 68 |
+
"version_str": "0.0.0",
|
| 69 |
+
"major": 0,
|
| 70 |
+
"minor": 0,
|
| 71 |
+
"patch": 0
|
| 72 |
+
}
|
| 73 |
+
}
|
state.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_data_files": [
|
| 3 |
+
{
|
| 4 |
+
"filename": "data-00000-of-00012.arrow"
|
| 5 |
+
},
|
| 6 |
+
{
|
| 7 |
+
"filename": "data-00001-of-00012.arrow"
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"filename": "data-00002-of-00012.arrow"
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"filename": "data-00003-of-00012.arrow"
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"filename": "data-00004-of-00012.arrow"
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"filename": "data-00005-of-00012.arrow"
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"filename": "data-00006-of-00012.arrow"
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"filename": "data-00007-of-00012.arrow"
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"filename": "data-00008-of-00012.arrow"
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"filename": "data-00009-of-00012.arrow"
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"filename": "data-00010-of-00012.arrow"
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"filename": "data-00011-of-00012.arrow"
|
| 38 |
+
}
|
| 39 |
+
],
|
| 40 |
+
"_fingerprint": "6dc398ab2c75630b",
|
| 41 |
+
"_format_columns": null,
|
| 42 |
+
"_format_kwargs": {},
|
| 43 |
+
"_format_type": null,
|
| 44 |
+
"_output_all_columns": false,
|
| 45 |
+
"_split": null
|
| 46 |
+
}
|