Delete reports/validation.json
Browse files- reports/validation.json +0 -48
reports/validation.json
DELETED
|
@@ -1,48 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"groups": {
|
| 3 |
-
"saudi_schoolbooks": {
|
| 4 |
-
"documents": 229,
|
| 5 |
-
"tokens": 31833,
|
| 6 |
-
"words": 18880,
|
| 7 |
-
"characters": 116742,
|
| 8 |
-
"bytes": 205534,
|
| 9 |
-
"roundtrip_failures": 0,
|
| 10 |
-
"unknown_tokens": 0,
|
| 11 |
-
"tokens_per_word": 1.6860699152542373,
|
| 12 |
-
"bytes_per_token": 6.456633053749254
|
| 13 |
-
},
|
| 14 |
-
"aramix_arabic": {
|
| 15 |
-
"documents": 5703,
|
| 16 |
-
"tokens": 3293519,
|
| 17 |
-
"words": 2454958,
|
| 18 |
-
"characters": 14302541,
|
| 19 |
-
"bytes": 25621109,
|
| 20 |
-
"roundtrip_failures": 0,
|
| 21 |
-
"unknown_tokens": 0,
|
| 22 |
-
"tokens_per_word": 1.341578552464034,
|
| 23 |
-
"bytes_per_token": 7.779250400559402
|
| 24 |
-
},
|
| 25 |
-
"fineweb2_arabic": {
|
| 26 |
-
"documents": 6024,
|
| 27 |
-
"tokens": 3770575,
|
| 28 |
-
"words": 2685728,
|
| 29 |
-
"characters": 15828573,
|
| 30 |
-
"bytes": 28416402,
|
| 31 |
-
"roundtrip_failures": 0,
|
| 32 |
-
"unknown_tokens": 0,
|
| 33 |
-
"tokens_per_word": 1.4039303309940545,
|
| 34 |
-
"bytes_per_token": 7.536357717324281
|
| 35 |
-
},
|
| 36 |
-
"fineweb_english": {
|
| 37 |
-
"documents": 3433,
|
| 38 |
-
"tokens": 1967458,
|
| 39 |
-
"words": 1398259,
|
| 40 |
-
"characters": 8333087,
|
| 41 |
-
"bytes": 8383641,
|
| 42 |
-
"roundtrip_failures": 0,
|
| 43 |
-
"unknown_tokens": 0,
|
| 44 |
-
"tokens_per_word": 1.4070769435419332,
|
| 45 |
-
"bytes_per_token": 4.261153732379547
|
| 46 |
-
}
|
| 47 |
-
}
|
| 48 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|