Transformers
undfined commited on
Commit
52d70fc
·
verified ·
1 Parent(s): 6afefab

Upload meta.json

Browse files
Files changed (1) hide show
  1. meta.json +675 -0
meta.json ADDED
@@ -0,0 +1,675 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_bytes": 10000000000,
3
+ "train_files": [
4
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000116.txt",
5
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000060.txt",
6
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000046.txt",
7
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000052.txt",
8
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000015.txt",
9
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000003.txt",
10
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000012.txt",
11
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000036.txt",
12
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000035.txt",
13
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000000.txt",
14
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000032.txt",
15
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000039.txt",
16
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000033.txt",
17
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000054.txt",
18
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000077.txt",
19
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000110.txt",
20
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000016.txt",
21
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000016.txt",
22
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000088.txt",
23
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000025.txt",
24
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000005.txt",
25
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000078.txt",
26
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000097.txt",
27
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000116.txt",
28
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000041.txt",
29
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000027.txt",
30
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000060.txt",
31
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000106.txt",
32
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000105.txt",
33
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000005.txt",
34
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000031.txt",
35
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000052.txt",
36
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000111.txt",
37
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000124.txt",
38
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000040.txt",
39
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000032.txt",
40
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000078.txt",
41
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000017.txt",
42
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000085.txt",
43
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000092.txt",
44
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000132.txt",
45
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000129.txt",
46
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000029.txt",
47
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000014.txt",
48
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000002.txt",
49
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000009.txt",
50
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000089.txt",
51
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000043.txt",
52
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000026.txt",
53
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000061.txt",
54
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000025.txt",
55
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000004.txt",
56
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000023.txt",
57
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000080.txt",
58
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000070.txt",
59
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000067.txt",
60
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000109.txt",
61
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000029.txt",
62
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000093.txt",
63
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000014.txt",
64
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000043.txt",
65
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000106.txt",
66
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000011.txt",
67
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000021.txt",
68
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000075.txt",
69
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000050.txt",
70
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000048.txt",
71
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000112.txt",
72
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000012.txt",
73
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000072.txt",
74
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000025.txt",
75
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000064.txt",
76
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000118.txt",
77
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000121.txt",
78
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000124.txt",
79
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000090.txt",
80
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000096.txt",
81
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000084.txt",
82
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000010.txt",
83
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000049.txt",
84
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000014.txt",
85
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000030.txt",
86
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000090.txt",
87
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000054.txt",
88
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000066.txt",
89
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000011.txt",
90
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000121.txt",
91
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000009.txt",
92
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000030.txt",
93
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000092.txt",
94
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000074.txt",
95
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000020.txt",
96
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000007.txt",
97
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000107.txt",
98
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000081.txt",
99
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000110.txt",
100
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000053.txt",
101
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000007.txt",
102
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000082.txt",
103
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000046.txt",
104
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000074.txt",
105
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000119.txt",
106
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000028.txt",
107
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000037.txt",
108
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000040.txt",
109
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000083.txt",
110
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000062.txt",
111
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000018.txt",
112
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000007.txt",
113
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000120.txt",
114
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000063.txt",
115
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000052.txt",
116
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000014.txt",
117
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000015.txt",
118
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000081.txt",
119
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000035.txt",
120
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000059.txt",
121
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000063.txt",
122
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000122.txt",
123
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000067.txt",
124
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000079.txt",
125
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000048.txt",
126
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000034.txt",
127
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000020.txt",
128
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000007.txt",
129
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000045.txt",
130
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000111.txt",
131
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000114.txt",
132
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000058.txt",
133
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000133.txt",
134
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000079.txt",
135
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000123.txt",
136
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000086.txt",
137
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000004.txt",
138
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000018.txt",
139
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000038.txt",
140
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000056.txt",
141
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000059.txt",
142
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000110.txt",
143
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000075.txt",
144
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000104.txt",
145
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000112.txt",
146
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000069.txt",
147
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000120.txt",
148
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000004.txt",
149
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000104.txt",
150
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000112.txt",
151
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000061.txt",
152
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000005.txt",
153
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000034.txt",
154
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000061.txt",
155
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000041.txt",
156
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000006.txt",
157
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000128.txt",
158
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000032.txt",
159
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000036.txt",
160
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000035.txt",
161
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000020.txt",
162
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000071.txt",
163
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000070.txt",
164
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000026.txt",
165
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000063.txt",
166
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000003.txt",
167
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000078.txt",
168
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000130.txt",
169
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000107.txt",
170
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000083.txt",
171
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000110.txt",
172
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000021.txt",
173
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000002.txt",
174
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000026.txt",
175
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000062.txt",
176
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000038.txt",
177
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000020.txt",
178
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000105.txt",
179
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000109.txt",
180
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000119.txt",
181
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000016.txt",
182
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000028.txt",
183
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000037.txt",
184
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000108.txt",
185
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000067.txt",
186
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000011.txt",
187
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000042.txt",
188
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000062.txt",
189
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000071.txt",
190
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000064.txt",
191
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000120.txt",
192
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000032.txt",
193
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000002.txt",
194
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000037.txt",
195
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000108.txt",
196
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000013.txt",
197
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000075.txt",
198
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000099.txt",
199
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000114.txt",
200
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000058.txt",
201
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000055.txt",
202
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000047.txt",
203
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000115.txt",
204
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000116.txt",
205
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000019.txt",
206
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000081.txt",
207
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000016.txt",
208
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000080.txt",
209
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000122.txt",
210
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000057.txt",
211
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000111.txt",
212
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000002.txt",
213
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000041.txt",
214
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000127.txt",
215
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000100.txt",
216
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000092.txt",
217
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000004.txt",
218
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000061.txt",
219
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000058.txt",
220
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000051.txt",
221
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000098.txt",
222
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000105.txt",
223
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000105.txt",
224
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000001.txt",
225
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000009.txt",
226
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000015.txt",
227
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000060.txt",
228
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000089.txt",
229
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000001.txt",
230
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000107.txt",
231
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000066.txt",
232
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000098.txt",
233
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000021.txt",
234
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000041.txt",
235
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000006.txt",
236
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000008.txt",
237
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000019.txt",
238
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000038.txt",
239
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000089.txt",
240
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000115.txt",
241
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000079.txt",
242
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000096.txt",
243
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000071.txt",
244
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000027.txt",
245
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000083.txt",
246
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000086.txt",
247
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000008.txt",
248
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000031.txt",
249
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000076.txt",
250
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000077.txt",
251
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000062.txt",
252
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000022.txt",
253
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000097.txt",
254
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000087.txt",
255
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000097.txt",
256
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000085.txt",
257
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000071.txt",
258
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000103.txt",
259
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000010.txt",
260
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000121.txt",
261
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000018.txt",
262
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000055.txt",
263
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000061.txt",
264
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000083.txt",
265
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000044.txt",
266
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000048.txt",
267
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000076.txt",
268
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000063.txt",
269
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000081.txt",
270
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000108.txt",
271
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000036.txt",
272
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000024.txt",
273
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000004.txt",
274
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000107.txt",
275
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000011.txt",
276
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000085.txt",
277
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000095.txt",
278
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000086.txt",
279
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000064.txt",
280
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000025.txt",
281
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000051.txt",
282
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000096.txt",
283
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000102.txt",
284
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000042.txt",
285
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000023.txt",
286
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000053.txt",
287
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000050.txt",
288
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000055.txt",
289
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000047.txt",
290
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000044.txt",
291
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000018.txt",
292
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000082.txt",
293
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000048.txt",
294
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000006.txt",
295
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000009.txt",
296
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000069.txt",
297
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000106.txt",
298
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000051.txt",
299
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000017.txt",
300
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000066.txt",
301
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000100.txt",
302
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000058.txt",
303
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000091.txt",
304
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000078.txt",
305
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000121.txt",
306
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000057.txt",
307
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000011.txt",
308
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000028.txt",
309
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000094.txt",
310
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000099.txt",
311
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000094.txt",
312
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000022.txt",
313
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000010.txt",
314
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000091.txt",
315
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000049.txt",
316
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000064.txt",
317
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000059.txt",
318
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000045.txt",
319
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000073.txt",
320
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000008.txt",
321
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000126.txt",
322
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000098.txt",
323
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000014.txt",
324
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000040.txt",
325
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000119.txt",
326
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000076.txt",
327
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000079.txt",
328
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000120.txt",
329
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000096.txt",
330
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000060.txt",
331
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000054.txt",
332
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000086.txt",
333
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000077.txt",
334
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000058.txt",
335
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000049.txt",
336
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000082.txt",
337
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000056.txt",
338
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000060.txt",
339
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000103.txt",
340
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000099.txt",
341
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000022.txt",
342
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000110.txt",
343
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000113.txt",
344
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000040.txt",
345
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000089.txt",
346
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000091.txt",
347
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000007.txt",
348
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000066.txt",
349
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000044.txt",
350
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000043.txt",
351
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000023.txt",
352
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000001.txt",
353
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000104.txt",
354
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000026.txt",
355
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000098.txt",
356
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000034.txt",
357
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000045.txt",
358
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000131.txt",
359
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000019.txt",
360
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000117.txt",
361
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000056.txt",
362
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000048.txt",
363
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000105.txt",
364
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000013.txt",
365
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000039.txt",
366
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000053.txt",
367
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000093.txt",
368
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000010.txt",
369
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000030.txt",
370
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000108.txt",
371
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000027.txt",
372
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000024.txt",
373
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000023.txt",
374
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000082.txt",
375
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000101.txt",
376
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000117.txt",
377
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000121.txt",
378
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000084.txt",
379
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000019.txt",
380
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000013.txt",
381
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000035.txt",
382
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000065.txt",
383
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000115.txt",
384
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000052.txt",
385
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000111.txt",
386
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000073.txt",
387
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000114.txt",
388
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000050.txt",
389
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000079.txt",
390
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000045.txt",
391
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000073.txt",
392
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000104.txt",
393
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000046.txt",
394
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000000.txt",
395
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000099.txt",
396
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000109.txt",
397
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000090.txt",
398
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000003.txt",
399
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000115.txt",
400
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000037.txt",
401
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000090.txt",
402
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000075.txt",
403
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000108.txt",
404
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000049.txt",
405
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000045.txt",
406
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000104.txt",
407
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000072.txt",
408
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000024.txt",
409
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000050.txt",
410
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000050.txt",
411
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000125.txt",
412
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000033.txt",
413
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000001.txt",
414
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000076.txt",
415
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000088.txt",
416
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000106.txt",
417
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000023.txt",
418
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000092.txt",
419
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000054.txt",
420
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000046.txt",
421
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000001.txt",
422
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000113.txt",
423
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000032.txt",
424
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000114.txt",
425
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000030.txt",
426
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000080.txt",
427
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000047.txt",
428
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000074.txt",
429
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000078.txt",
430
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000056.txt",
431
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000028.txt",
432
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000039.txt",
433
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000003.txt",
434
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000085.txt",
435
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000123.txt",
436
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000106.txt",
437
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000038.txt",
438
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000005.txt",
439
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000084.txt",
440
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000012.txt",
441
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000091.txt",
442
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000074.txt",
443
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000065.txt",
444
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000005.txt",
445
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000012.txt",
446
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000051.txt",
447
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000042.txt",
448
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000068.txt",
449
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000052.txt",
450
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000101.txt",
451
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000038.txt",
452
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000029.txt",
453
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000012.txt",
454
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000098.txt",
455
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000109.txt",
456
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000095.txt",
457
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000086.txt",
458
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000033.txt",
459
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000039.txt",
460
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000118.txt",
461
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000100.txt",
462
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000067.txt",
463
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000101.txt",
464
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000103.txt",
465
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000093.txt",
466
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000118.txt",
467
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000112.txt",
468
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000047.txt",
469
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000020.txt",
470
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000117.txt",
471
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000000.txt",
472
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000113.txt",
473
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000088.txt",
474
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000087.txt",
475
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000049.txt",
476
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000031.txt",
477
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000071.txt",
478
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000036.txt",
479
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000113.txt",
480
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000035.txt",
481
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000046.txt",
482
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000070.txt",
483
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000057.txt",
484
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000080.txt",
485
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000087.txt",
486
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000021.txt",
487
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000125.txt",
488
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000087.txt",
489
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000103.txt",
490
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000031.txt",
491
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000044.txt",
492
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000119.txt",
493
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000107.txt",
494
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000122.txt",
495
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000003.txt",
496
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000116.txt",
497
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000091.txt",
498
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000118.txt",
499
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000094.txt",
500
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000008.txt",
501
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000000.txt",
502
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000018.txt",
503
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000067.txt",
504
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000030.txt",
505
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000065.txt",
506
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000006.txt",
507
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000070.txt",
508
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000068.txt",
509
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000065.txt",
510
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000066.txt",
511
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000094.txt",
512
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000093.txt",
513
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000068.txt",
514
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000015.txt",
515
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000025.txt",
516
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000034.txt",
517
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000040.txt",
518
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000099.txt",
519
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000027.txt",
520
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000029.txt",
521
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000118.txt",
522
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000043.txt",
523
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000072.txt",
524
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000055.txt",
525
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000000.txt",
526
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000094.txt",
527
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000117.txt",
528
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000019.txt",
529
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000013.txt",
530
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000124.txt",
531
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000073.txt",
532
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000088.txt",
533
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000027.txt",
534
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000116.txt",
535
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000069.txt",
536
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000055.txt",
537
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000090.txt",
538
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000075.txt",
539
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000095.txt",
540
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000024.txt",
541
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000041.txt",
542
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000096.txt",
543
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000119.txt",
544
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000036.txt",
545
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000026.txt",
546
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000033.txt",
547
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000017.txt",
548
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000102.txt",
549
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000039.txt",
550
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000028.txt",
551
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000033.txt",
552
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000089.txt",
553
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000077.txt",
554
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000109.txt",
555
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000120.txt",
556
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000034.txt",
557
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000072.txt",
558
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000074.txt",
559
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000068.txt",
560
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000043.txt",
561
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000126.txt",
562
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000065.txt",
563
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000101.txt",
564
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000103.txt",
565
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000088.txt",
566
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000037.txt",
567
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000059.txt",
568
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000083.txt",
569
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000053.txt",
570
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000097.txt",
571
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000062.txt",
572
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000006.txt",
573
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000044.txt",
574
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000063.txt",
575
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000057.txt",
576
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000112.txt",
577
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000082.txt",
578
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000013.txt",
579
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000072.txt",
580
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000095.txt",
581
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000092.txt",
582
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000087.txt",
583
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000057.txt",
584
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000022.txt",
585
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000123.txt",
586
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000095.txt",
587
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000073.txt",
588
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000080.txt",
589
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000070.txt",
590
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000077.txt",
591
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000127.txt",
592
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000084.txt",
593
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000114.txt",
594
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000002.txt",
595
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000056.txt",
596
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000097.txt",
597
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000017.txt",
598
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000064.txt",
599
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000069.txt",
600
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000009.txt",
601
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000024.txt",
602
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000069.txt",
603
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000093.txt",
604
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000068.txt",
605
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000085.txt",
606
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000059.txt",
607
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000076.txt",
608
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000111.txt",
609
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000101.txt",
610
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000084.txt",
611
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000100.txt",
612
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000102.txt",
613
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000081.txt",
614
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000100.txt",
615
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000051.txt",
616
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000029.txt",
617
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000047.txt",
618
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000134.txt",
619
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000102.txt",
620
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000021.txt",
621
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000031.txt",
622
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000016.txt",
623
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000010.txt",
624
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000102.txt",
625
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000115.txt",
626
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000113.txt",
627
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000117.txt",
628
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000054.txt",
629
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000022.txt",
630
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000053.txt",
631
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000017.txt",
632
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000008.txt",
633
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000042.txt",
634
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000042.txt",
635
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000015.txt",
636
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000116.txt",
637
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000060.txt",
638
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000046.txt",
639
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000052.txt",
640
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000015.txt",
641
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000003.txt",
642
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000012.txt",
643
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000036.txt",
644
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000035.txt",
645
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000000.txt",
646
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000032.txt",
647
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000039.txt",
648
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000033.txt",
649
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000054.txt",
650
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000077.txt",
651
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000110.txt",
652
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000016.txt",
653
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000016.txt",
654
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000088.txt",
655
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000025.txt",
656
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000005.txt",
657
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000078.txt",
658
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000097.txt",
659
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000116.txt",
660
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000041.txt",
661
+ "/mnt/raid0/data/superbpe/preprocessed/code_shard_00000027.txt",
662
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000060.txt",
663
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000106.txt",
664
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000105.txt",
665
+ "/mnt/raid0/data/superbpe/preprocessed/olmocr_shard_00000005.txt",
666
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000031.txt",
667
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000052.txt",
668
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000111.txt",
669
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000124.txt",
670
+ "/mnt/raid0/data/superbpe/preprocessed/math_shard_00000040.txt",
671
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000032.txt",
672
+ "/mnt/raid0/data/superbpe/preprocessed/fineweb-2_shard_00000078.txt",
673
+ "/mnt/raid0/data/superbpe/preprocessed/dclm_shard_00000017_truncated_9972064.txt"
674
+ ]
675
+ }