rbelanec commited on
Commit
72e5e9e
·
verified ·
1 Parent(s): 76c61ca

Training in progress, step 1061

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
4
+ "exclude_modules": null,
5
+ "inference_mode": true,
6
+ "modules_to_save": null,
7
+ "peft_type": "LN_TUNING",
8
+ "revision": null,
9
+ "target_modules": [
10
+ "input_layernorm",
11
+ "norm",
12
+ "post_attention_layernorm"
13
+ ],
14
+ "task_type": "CAUSAL_LM"
15
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bb6497d379852ab381682617c79087c68cbd4c544104233d34c92abe71bd2ba
3
+ size 1074144
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c1dcab308e7cf5970ea38815e0a62887d705c5b436f869ca27a5dcdd40c36a6
3
+ size 17210148
tokenizer_config.json ADDED
@@ -0,0 +1,2077 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|eom_id|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "<|eom_id|>"
2062
+ ],
2063
+ "bos_token": "<|begin_of_text|>",
2064
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2065
+ "clean_up_tokenization_spaces": true,
2066
+ "eos_token": "<|eot_id|>",
2067
+ "extra_special_tokens": {},
2068
+ "model_input_names": [
2069
+ "input_ids",
2070
+ "attention_mask"
2071
+ ],
2072
+ "model_max_length": 1000000000000000019884624838656,
2073
+ "pad_token": "<|eot_id|>",
2074
+ "padding_side": "right",
2075
+ "split_special_tokens": false,
2076
+ "tokenizer_class": "PreTrainedTokenizer"
2077
+ }
train.yaml ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ seed: 123
2
+
3
+ ### model
4
+ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
5
+ trust_remote_code: true
6
+ flash_attn: auto
7
+ use_cache: false
8
+
9
+ ### method
10
+ stage: sft
11
+ do_train: true
12
+ finetuning_type: lntuning
13
+ task_type: CAUSAL_LM
14
+
15
+ ### dataset
16
+ dataset: boolq
17
+ template: llama3
18
+ cutoff_len: 2048
19
+ overwrite_cache: true
20
+ preprocessing_num_workers: 16
21
+ dataloader_num_workers: 4
22
+ packing: false
23
+
24
+ ### output
25
+ output_dir: saves/lntuning/llama-3-8b-instruct/train_boolq_1753094167
26
+ logging_steps: 5
27
+ save_steps: 0.05
28
+ overwrite_output_dir: true
29
+ save_only_model: false
30
+ plot_loss: true
31
+ include_num_input_tokens_seen: true
32
+ push_to_hub: true
33
+ push_to_hub_organization: rbelanec
34
+ load_best_model_at_end: true
35
+ save_total_limit: 1
36
+
37
+ ### train
38
+ per_device_train_batch_size: 4
39
+ learning_rate: 5.0e-5
40
+ num_train_epochs: 10.0
41
+ weight_decay: 1.0e-5
42
+ lr_scheduler_type: cosine
43
+ bf16: true
44
+ ddp_timeout: 180000000
45
+ resume_from_checkpoint: null
46
+ warmup_ratio: 0.1
47
+ optim: adamw_torch
48
+ report_to:
49
+ - wandb
50
+
51
+ ### eval
52
+ per_device_eval_batch_size: 4
53
+ eval_strategy: steps
54
+ eval_steps: 0.05
55
+ val_size: 0.1
trainer_log.jsonl ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 21210, "loss": 0.6186, "lr": 9.42951438000943e-08, "epoch": 0.0023573785950023575, "percentage": 0.02, "elapsed_time": "0:00:02", "remaining_time": "2:33:29", "throughput": 2387.21, "total_tokens": 5184}
2
+ {"current_steps": 10, "total_steps": 21210, "loss": 0.5783, "lr": 2.1216407355021216e-07, "epoch": 0.004714757190004715, "percentage": 0.05, "elapsed_time": "0:00:03", "remaining_time": "2:07:54", "throughput": 2651.81, "total_tokens": 9600}
3
+ {"current_steps": 15, "total_steps": 21210, "loss": 0.3488, "lr": 3.300330033003301e-07, "epoch": 0.007072135785007072, "percentage": 0.07, "elapsed_time": "0:00:05", "remaining_time": "2:00:03", "throughput": 2812.18, "total_tokens": 14336}
4
+ {"current_steps": 20, "total_steps": 21210, "loss": 0.3136, "lr": 4.479019330504479e-07, "epoch": 0.00942951438000943, "percentage": 0.09, "elapsed_time": "0:00:06", "remaining_time": "1:59:04", "throughput": 2918.32, "total_tokens": 19680}
5
+ {"current_steps": 25, "total_steps": 21210, "loss": 0.9414, "lr": 5.657708628005658e-07, "epoch": 0.011786892975011787, "percentage": 0.12, "elapsed_time": "0:00:08", "remaining_time": "1:56:43", "throughput": 2973.56, "total_tokens": 24576}
6
+ {"current_steps": 30, "total_steps": 21210, "loss": 0.3306, "lr": 6.836397925506837e-07, "epoch": 0.014144271570014143, "percentage": 0.14, "elapsed_time": "0:00:09", "remaining_time": "1:54:34", "throughput": 3000.49, "total_tokens": 29216}
7
+ {"current_steps": 35, "total_steps": 21210, "loss": 0.1144, "lr": 8.015087223008016e-07, "epoch": 0.0165016501650165, "percentage": 0.17, "elapsed_time": "0:00:11", "remaining_time": "1:51:35", "throughput": 3021.64, "total_tokens": 33440}
8
+ {"current_steps": 40, "total_steps": 21210, "loss": 0.5296, "lr": 9.193776520509195e-07, "epoch": 0.01885902876001886, "percentage": 0.19, "elapsed_time": "0:00:12", "remaining_time": "1:50:58", "throughput": 3039.5, "total_tokens": 38240}
9
+ {"current_steps": 45, "total_steps": 21210, "loss": 0.3058, "lr": 1.0372465818010372e-06, "epoch": 0.021216407355021217, "percentage": 0.21, "elapsed_time": "0:00:14", "remaining_time": "1:51:10", "throughput": 3052.77, "total_tokens": 43296}
10
+ {"current_steps": 50, "total_steps": 21210, "loss": 0.1705, "lr": 1.155115511551155e-06, "epoch": 0.023573785950023574, "percentage": 0.24, "elapsed_time": "0:00:15", "remaining_time": "1:50:13", "throughput": 3057.09, "total_tokens": 47776}
11
+ {"current_steps": 55, "total_steps": 21210, "loss": 0.6337, "lr": 1.272984441301273e-06, "epoch": 0.02593116454502593, "percentage": 0.26, "elapsed_time": "0:00:17", "remaining_time": "1:49:46", "throughput": 3068.44, "total_tokens": 52544}
12
+ {"current_steps": 60, "total_steps": 21210, "loss": 0.3866, "lr": 1.390853371051391e-06, "epoch": 0.028288543140028287, "percentage": 0.28, "elapsed_time": "0:00:18", "remaining_time": "1:50:43", "throughput": 3086.93, "total_tokens": 58176}
13
+ {"current_steps": 65, "total_steps": 21210, "loss": 0.7549, "lr": 1.5087223008015088e-06, "epoch": 0.030645921735030647, "percentage": 0.31, "elapsed_time": "0:00:20", "remaining_time": "1:50:28", "throughput": 3087.74, "total_tokens": 62912}
14
+ {"current_steps": 70, "total_steps": 21210, "loss": 0.6266, "lr": 1.6265912305516266e-06, "epoch": 0.033003300330033, "percentage": 0.33, "elapsed_time": "0:00:22", "remaining_time": "1:51:51", "throughput": 3104.34, "total_tokens": 68992}
15
+ {"current_steps": 75, "total_steps": 21210, "loss": 0.8035, "lr": 1.7444601603017446e-06, "epoch": 0.03536067892503536, "percentage": 0.35, "elapsed_time": "0:00:23", "remaining_time": "1:51:01", "throughput": 3101.14, "total_tokens": 73312}
16
+ {"current_steps": 80, "total_steps": 21210, "loss": 0.6382, "lr": 1.8623290900518624e-06, "epoch": 0.03771805752003772, "percentage": 0.38, "elapsed_time": "0:00:25", "remaining_time": "1:51:45", "throughput": 3110.81, "total_tokens": 78976}
17
+ {"current_steps": 85, "total_steps": 21210, "loss": 0.4382, "lr": 1.9801980198019803e-06, "epoch": 0.040075436115040074, "percentage": 0.4, "elapsed_time": "0:00:26", "remaining_time": "1:51:15", "throughput": 3116.78, "total_tokens": 83712}
18
+ {"current_steps": 90, "total_steps": 21210, "loss": 0.3434, "lr": 2.0980669495520983e-06, "epoch": 0.042432814710042434, "percentage": 0.42, "elapsed_time": "0:00:28", "remaining_time": "1:50:15", "throughput": 3119.31, "total_tokens": 87936}
19
+ {"current_steps": 95, "total_steps": 21210, "loss": 0.2014, "lr": 2.215935879302216e-06, "epoch": 0.04479019330504479, "percentage": 0.45, "elapsed_time": "0:00:29", "remaining_time": "1:49:52", "throughput": 3125.29, "total_tokens": 92704}
20
+ {"current_steps": 100, "total_steps": 21210, "loss": 0.1679, "lr": 2.333804809052334e-06, "epoch": 0.04714757190004715, "percentage": 0.47, "elapsed_time": "0:00:31", "remaining_time": "1:49:54", "throughput": 3126.43, "total_tokens": 97664}
21
+ {"current_steps": 105, "total_steps": 21210, "loss": 0.1832, "lr": 2.4516737388024515e-06, "epoch": 0.04950495049504951, "percentage": 0.5, "elapsed_time": "0:00:32", "remaining_time": "1:49:30", "throughput": 3127.57, "total_tokens": 102240}
22
+ {"current_steps": 110, "total_steps": 21210, "loss": 0.191, "lr": 2.56954266855257e-06, "epoch": 0.05186232909005186, "percentage": 0.52, "elapsed_time": "0:00:34", "remaining_time": "1:49:39", "throughput": 3128.29, "total_tokens": 107296}
23
+ {"current_steps": 115, "total_steps": 21210, "loss": 0.2683, "lr": 2.687411598302688e-06, "epoch": 0.05421970768505422, "percentage": 0.54, "elapsed_time": "0:00:36", "remaining_time": "1:50:22", "throughput": 3129.77, "total_tokens": 112992}
24
+ {"current_steps": 120, "total_steps": 21210, "loss": 0.3142, "lr": 2.8052805280528055e-06, "epoch": 0.056577086280056574, "percentage": 0.57, "elapsed_time": "0:00:37", "remaining_time": "1:50:42", "throughput": 3134.22, "total_tokens": 118464}
25
+ {"current_steps": 125, "total_steps": 21210, "loss": 0.3899, "lr": 2.9231494578029235e-06, "epoch": 0.058934464875058934, "percentage": 0.59, "elapsed_time": "0:00:39", "remaining_time": "1:51:40", "throughput": 3136.89, "total_tokens": 124608}
26
+ {"current_steps": 130, "total_steps": 21210, "loss": 0.4313, "lr": 3.041018387553041e-06, "epoch": 0.061291843470061294, "percentage": 0.61, "elapsed_time": "0:00:41", "remaining_time": "1:53:05", "throughput": 3130.65, "total_tokens": 131008}
27
+ {"current_steps": 135, "total_steps": 21210, "loss": 0.2092, "lr": 3.1588873173031586e-06, "epoch": 0.06364922206506365, "percentage": 0.64, "elapsed_time": "0:00:43", "remaining_time": "1:53:14", "throughput": 3135.82, "total_tokens": 136480}
28
+ {"current_steps": 140, "total_steps": 21210, "loss": 0.6368, "lr": 3.2767562470532766e-06, "epoch": 0.066006600660066, "percentage": 0.66, "elapsed_time": "0:00:45", "remaining_time": "1:53:01", "throughput": 3135.31, "total_tokens": 141280}
29
+ {"current_steps": 145, "total_steps": 21210, "loss": 0.618, "lr": 3.3946251768033946e-06, "epoch": 0.06836397925506836, "percentage": 0.68, "elapsed_time": "0:00:46", "remaining_time": "1:52:58", "throughput": 3137.52, "total_tokens": 146400}
30
+ {"current_steps": 150, "total_steps": 21210, "loss": 0.344, "lr": 3.5124941065535126e-06, "epoch": 0.07072135785007072, "percentage": 0.71, "elapsed_time": "0:00:48", "remaining_time": "1:52:54", "throughput": 3137.76, "total_tokens": 151392}
31
+ {"current_steps": 155, "total_steps": 21210, "loss": 0.3959, "lr": 3.6303630363036306e-06, "epoch": 0.07307873644507308, "percentage": 0.73, "elapsed_time": "0:00:49", "remaining_time": "1:52:58", "throughput": 3141.38, "total_tokens": 156768}
32
+ {"current_steps": 160, "total_steps": 21210, "loss": 0.1549, "lr": 3.748231966053748e-06, "epoch": 0.07543611504007544, "percentage": 0.75, "elapsed_time": "0:00:51", "remaining_time": "1:52:33", "throughput": 3140.41, "total_tokens": 161216}
33
+ {"current_steps": 165, "total_steps": 21210, "loss": 0.2558, "lr": 3.866100895803866e-06, "epoch": 0.07779349363507779, "percentage": 0.78, "elapsed_time": "0:00:53", "remaining_time": "1:52:40", "throughput": 3141.75, "total_tokens": 166528}
34
+ {"current_steps": 170, "total_steps": 21210, "loss": 0.3007, "lr": 3.983969825553984e-06, "epoch": 0.08015087223008015, "percentage": 0.8, "elapsed_time": "0:00:54", "remaining_time": "1:52:53", "throughput": 3143.81, "total_tokens": 172064}
35
+ {"current_steps": 175, "total_steps": 21210, "loss": 0.3396, "lr": 4.101838755304102e-06, "epoch": 0.08250825082508251, "percentage": 0.83, "elapsed_time": "0:00:56", "remaining_time": "1:52:57", "throughput": 3144.04, "total_tokens": 177280}
36
+ {"current_steps": 180, "total_steps": 21210, "loss": 0.4503, "lr": 4.2197076850542205e-06, "epoch": 0.08486562942008487, "percentage": 0.85, "elapsed_time": "0:00:57", "remaining_time": "1:52:24", "throughput": 3142.89, "total_tokens": 181440}
37
+ {"current_steps": 185, "total_steps": 21210, "loss": 0.4446, "lr": 4.337576614804337e-06, "epoch": 0.08722300801508723, "percentage": 0.87, "elapsed_time": "0:00:59", "remaining_time": "1:52:22", "throughput": 3143.36, "total_tokens": 186496}
38
+ {"current_steps": 190, "total_steps": 21210, "loss": 0.1676, "lr": 4.455445544554456e-06, "epoch": 0.08958038661008957, "percentage": 0.9, "elapsed_time": "0:01:00", "remaining_time": "1:51:52", "throughput": 3142.59, "total_tokens": 190688}
39
+ {"current_steps": 195, "total_steps": 21210, "loss": 0.3249, "lr": 4.573314474304573e-06, "epoch": 0.09193776520509193, "percentage": 0.92, "elapsed_time": "0:01:02", "remaining_time": "1:51:47", "throughput": 3143.55, "total_tokens": 195648}
40
+ {"current_steps": 200, "total_steps": 21210, "loss": 0.2724, "lr": 4.691183404054692e-06, "epoch": 0.0942951438000943, "percentage": 0.94, "elapsed_time": "0:01:03", "remaining_time": "1:51:37", "throughput": 3144.79, "total_tokens": 200512}
41
+ {"current_steps": 205, "total_steps": 21210, "loss": 0.6804, "lr": 4.809052333804809e-06, "epoch": 0.09665252239509665, "percentage": 0.97, "elapsed_time": "0:01:05", "remaining_time": "1:51:47", "throughput": 3144.67, "total_tokens": 205856}
42
+ {"current_steps": 210, "total_steps": 21210, "loss": 0.5254, "lr": 4.926921263554928e-06, "epoch": 0.09900990099009901, "percentage": 0.99, "elapsed_time": "0:01:07", "remaining_time": "1:51:41", "throughput": 3145.51, "total_tokens": 210784}
43
+ {"current_steps": 215, "total_steps": 21210, "loss": 0.4397, "lr": 5.044790193305045e-06, "epoch": 0.10136727958510136, "percentage": 1.01, "elapsed_time": "0:01:08", "remaining_time": "1:51:29", "throughput": 3143.54, "total_tokens": 215360}
44
+ {"current_steps": 220, "total_steps": 21210, "loss": 0.574, "lr": 5.162659123055163e-06, "epoch": 0.10372465818010372, "percentage": 1.04, "elapsed_time": "0:01:10", "remaining_time": "1:51:18", "throughput": 3143.77, "total_tokens": 220064}
45
+ {"current_steps": 225, "total_steps": 21210, "loss": 0.396, "lr": 5.280528052805281e-06, "epoch": 0.10608203677510608, "percentage": 1.06, "elapsed_time": "0:01:11", "remaining_time": "1:50:58", "throughput": 3142.56, "total_tokens": 224352}
46
+ {"current_steps": 230, "total_steps": 21210, "loss": 0.3436, "lr": 5.398396982555399e-06, "epoch": 0.10843941537010844, "percentage": 1.08, "elapsed_time": "0:01:12", "remaining_time": "1:50:47", "throughput": 3143.61, "total_tokens": 229088}
47
+ {"current_steps": 235, "total_steps": 21210, "loss": 0.1962, "lr": 5.516265912305517e-06, "epoch": 0.1107967939651108, "percentage": 1.11, "elapsed_time": "0:01:14", "remaining_time": "1:50:35", "throughput": 3145.3, "total_tokens": 233824}
48
+ {"current_steps": 240, "total_steps": 21210, "loss": 0.5238, "lr": 5.634134842055634e-06, "epoch": 0.11315417256011315, "percentage": 1.13, "elapsed_time": "0:01:15", "remaining_time": "1:50:31", "throughput": 3146.78, "total_tokens": 238816}
49
+ {"current_steps": 245, "total_steps": 21210, "loss": 0.5431, "lr": 5.752003771805752e-06, "epoch": 0.11551155115511551, "percentage": 1.16, "elapsed_time": "0:01:17", "remaining_time": "1:50:16", "throughput": 3146.95, "total_tokens": 243328}
50
+ {"current_steps": 250, "total_steps": 21210, "loss": 0.2214, "lr": 5.86987270155587e-06, "epoch": 0.11786892975011787, "percentage": 1.18, "elapsed_time": "0:01:19", "remaining_time": "1:50:26", "throughput": 3148.87, "total_tokens": 248896}
51
+ {"current_steps": 255, "total_steps": 21210, "loss": 0.249, "lr": 5.987741631305988e-06, "epoch": 0.12022630834512023, "percentage": 1.2, "elapsed_time": "0:01:20", "remaining_time": "1:50:14", "throughput": 3148.62, "total_tokens": 253440}
52
+ {"current_steps": 260, "total_steps": 21210, "loss": 0.3677, "lr": 6.105610561056106e-06, "epoch": 0.12258368694012259, "percentage": 1.23, "elapsed_time": "0:01:22", "remaining_time": "1:50:07", "throughput": 3148.74, "total_tokens": 258208}
53
+ {"current_steps": 265, "total_steps": 21210, "loss": 0.0409, "lr": 6.2234794908062235e-06, "epoch": 0.12494106553512493, "percentage": 1.25, "elapsed_time": "0:01:23", "remaining_time": "1:49:50", "throughput": 3149.19, "total_tokens": 262592}
54
+ {"current_steps": 270, "total_steps": 21210, "loss": 0.3933, "lr": 6.341348420556342e-06, "epoch": 0.1272984441301273, "percentage": 1.27, "elapsed_time": "0:01:24", "remaining_time": "1:49:52", "throughput": 3148.83, "total_tokens": 267648}
55
+ {"current_steps": 275, "total_steps": 21210, "loss": 0.642, "lr": 6.4592173503064595e-06, "epoch": 0.12965582272512965, "percentage": 1.3, "elapsed_time": "0:01:26", "remaining_time": "1:49:45", "throughput": 3148.8, "total_tokens": 272384}
56
+ {"current_steps": 280, "total_steps": 21210, "loss": 0.2568, "lr": 6.577086280056577e-06, "epoch": 0.132013201320132, "percentage": 1.32, "elapsed_time": "0:01:28", "remaining_time": "1:50:05", "throughput": 3151.1, "total_tokens": 278464}
57
+ {"current_steps": 285, "total_steps": 21210, "loss": 0.1598, "lr": 6.6949552098066954e-06, "epoch": 0.13437057991513437, "percentage": 1.34, "elapsed_time": "0:01:29", "remaining_time": "1:49:41", "throughput": 3150.52, "total_tokens": 282432}
58
+ {"current_steps": 290, "total_steps": 21210, "loss": 0.4028, "lr": 6.812824139556813e-06, "epoch": 0.13672795851013672, "percentage": 1.37, "elapsed_time": "0:01:31", "remaining_time": "1:49:47", "throughput": 3151.09, "total_tokens": 287744}
59
+ {"current_steps": 295, "total_steps": 21210, "loss": 0.2817, "lr": 6.9306930693069314e-06, "epoch": 0.1390853371051391, "percentage": 1.39, "elapsed_time": "0:01:32", "remaining_time": "1:49:29", "throughput": 3149.76, "total_tokens": 291840}
60
+ {"current_steps": 300, "total_steps": 21210, "loss": 0.4345, "lr": 7.048561999057049e-06, "epoch": 0.14144271570014144, "percentage": 1.41, "elapsed_time": "0:01:34", "remaining_time": "1:49:29", "throughput": 3150.51, "total_tokens": 296928}
61
+ {"current_steps": 305, "total_steps": 21210, "loss": 0.1777, "lr": 7.1664309288071666e-06, "epoch": 0.1438000942951438, "percentage": 1.44, "elapsed_time": "0:01:35", "remaining_time": "1:49:36", "throughput": 3150.55, "total_tokens": 302272}
62
+ {"current_steps": 310, "total_steps": 21210, "loss": 0.4476, "lr": 7.284299858557285e-06, "epoch": 0.14615747289014616, "percentage": 1.46, "elapsed_time": "0:01:37", "remaining_time": "1:49:24", "throughput": 3149.6, "total_tokens": 306688}
63
+ {"current_steps": 315, "total_steps": 21210, "loss": 0.5639, "lr": 7.4021687883074026e-06, "epoch": 0.1485148514851485, "percentage": 1.49, "elapsed_time": "0:01:38", "remaining_time": "1:49:02", "throughput": 3148.34, "total_tokens": 310528}
64
+ {"current_steps": 320, "total_steps": 21210, "loss": 0.2435, "lr": 7.520037718057521e-06, "epoch": 0.15087223008015088, "percentage": 1.51, "elapsed_time": "0:01:40", "remaining_time": "1:48:51", "throughput": 3147.55, "total_tokens": 314912}
65
+ {"current_steps": 325, "total_steps": 21210, "loss": 0.1655, "lr": 7.637906647807639e-06, "epoch": 0.15322960867515323, "percentage": 1.53, "elapsed_time": "0:01:41", "remaining_time": "1:48:46", "throughput": 3148.03, "total_tokens": 319712}
66
+ {"current_steps": 330, "total_steps": 21210, "loss": 0.5502, "lr": 7.755775577557756e-06, "epoch": 0.15558698727015557, "percentage": 1.56, "elapsed_time": "0:01:43", "remaining_time": "1:48:46", "throughput": 3147.91, "total_tokens": 324704}
67
+ {"current_steps": 335, "total_steps": 21210, "loss": 0.3191, "lr": 7.873644507307874e-06, "epoch": 0.15794436586515795, "percentage": 1.58, "elapsed_time": "0:01:44", "remaining_time": "1:48:53", "throughput": 3148.43, "total_tokens": 330112}
68
+ {"current_steps": 340, "total_steps": 21210, "loss": 0.2473, "lr": 7.991513437057991e-06, "epoch": 0.1603017444601603, "percentage": 1.6, "elapsed_time": "0:01:47", "remaining_time": "1:49:40", "throughput": 3152.74, "total_tokens": 337984}
69
+ {"current_steps": 345, "total_steps": 21210, "loss": 0.3606, "lr": 8.10938236680811e-06, "epoch": 0.16265912305516267, "percentage": 1.63, "elapsed_time": "0:01:48", "remaining_time": "1:49:41", "throughput": 3153.1, "total_tokens": 343136}
70
+ {"current_steps": 350, "total_steps": 21210, "loss": 0.2061, "lr": 8.227251296558228e-06, "epoch": 0.16501650165016502, "percentage": 1.65, "elapsed_time": "0:01:50", "remaining_time": "1:49:55", "throughput": 3153.55, "total_tokens": 348992}
71
+ {"current_steps": 355, "total_steps": 21210, "loss": 0.3679, "lr": 8.345120226308346e-06, "epoch": 0.16737388024516736, "percentage": 1.67, "elapsed_time": "0:01:52", "remaining_time": "1:49:45", "throughput": 3153.49, "total_tokens": 353504}
72
+ {"current_steps": 360, "total_steps": 21210, "loss": 0.2449, "lr": 8.462989156058463e-06, "epoch": 0.16973125884016974, "percentage": 1.7, "elapsed_time": "0:01:53", "remaining_time": "1:49:52", "throughput": 3154.73, "total_tokens": 359104}
73
+ {"current_steps": 365, "total_steps": 21210, "loss": 0.1667, "lr": 8.58085808580858e-06, "epoch": 0.17208863743517208, "percentage": 1.72, "elapsed_time": "0:01:55", "remaining_time": "1:49:44", "throughput": 3154.68, "total_tokens": 363744}
74
+ {"current_steps": 370, "total_steps": 21210, "loss": 0.3993, "lr": 8.6987270155587e-06, "epoch": 0.17444601603017446, "percentage": 1.74, "elapsed_time": "0:01:56", "remaining_time": "1:49:44", "throughput": 3155.13, "total_tokens": 368864}
75
+ {"current_steps": 375, "total_steps": 21210, "loss": 0.2897, "lr": 8.816595945308818e-06, "epoch": 0.1768033946251768, "percentage": 1.77, "elapsed_time": "0:01:58", "remaining_time": "1:49:40", "throughput": 3156.22, "total_tokens": 373824}
76
+ {"current_steps": 380, "total_steps": 21210, "loss": 0.3777, "lr": 8.934464875058935e-06, "epoch": 0.17916077322017915, "percentage": 1.79, "elapsed_time": "0:01:59", "remaining_time": "1:49:31", "throughput": 3156.54, "total_tokens": 378432}
77
+ {"current_steps": 385, "total_steps": 21210, "loss": 0.256, "lr": 9.052333804809053e-06, "epoch": 0.18151815181518152, "percentage": 1.82, "elapsed_time": "0:02:01", "remaining_time": "1:49:31", "throughput": 3157.22, "total_tokens": 383552}
78
+ {"current_steps": 390, "total_steps": 21210, "loss": 0.2934, "lr": 9.17020273455917e-06, "epoch": 0.18387553041018387, "percentage": 1.84, "elapsed_time": "0:02:03", "remaining_time": "1:49:31", "throughput": 3158.04, "total_tokens": 388768}
79
+ {"current_steps": 395, "total_steps": 21210, "loss": 0.0891, "lr": 9.28807166430929e-06, "epoch": 0.18623290900518624, "percentage": 1.86, "elapsed_time": "0:02:04", "remaining_time": "1:49:19", "throughput": 3158.0, "total_tokens": 393120}
80
+ {"current_steps": 400, "total_steps": 21210, "loss": 0.1325, "lr": 9.405940594059407e-06, "epoch": 0.1885902876001886, "percentage": 1.89, "elapsed_time": "0:02:06", "remaining_time": "1:49:15", "throughput": 3157.43, "total_tokens": 397856}
81
+ {"current_steps": 405, "total_steps": 21210, "loss": 0.2957, "lr": 9.523809523809523e-06, "epoch": 0.19094766619519093, "percentage": 1.91, "elapsed_time": "0:02:07", "remaining_time": "1:49:12", "throughput": 3158.29, "total_tokens": 402848}
82
+ {"current_steps": 410, "total_steps": 21210, "loss": 0.3105, "lr": 9.641678453559642e-06, "epoch": 0.1933050447901933, "percentage": 1.93, "elapsed_time": "0:02:09", "remaining_time": "1:49:10", "throughput": 3159.14, "total_tokens": 407936}
83
+ {"current_steps": 415, "total_steps": 21210, "loss": 0.3259, "lr": 9.75954738330976e-06, "epoch": 0.19566242338519566, "percentage": 1.96, "elapsed_time": "0:02:10", "remaining_time": "1:49:09", "throughput": 3159.7, "total_tokens": 413024}
84
+ {"current_steps": 420, "total_steps": 21210, "loss": 0.3267, "lr": 9.87741631305988e-06, "epoch": 0.19801980198019803, "percentage": 1.98, "elapsed_time": "0:02:12", "remaining_time": "1:49:16", "throughput": 3161.43, "total_tokens": 418720}
85
+ {"current_steps": 425, "total_steps": 21210, "loss": 0.1132, "lr": 9.995285242809995e-06, "epoch": 0.20037718057520038, "percentage": 2.0, "elapsed_time": "0:02:14", "remaining_time": "1:49:36", "throughput": 3163.57, "total_tokens": 425440}
86
+ {"current_steps": 430, "total_steps": 21210, "loss": 0.4139, "lr": 1.0113154172560113e-05, "epoch": 0.20273455917020272, "percentage": 2.03, "elapsed_time": "0:02:16", "remaining_time": "1:49:35", "throughput": 3163.78, "total_tokens": 430464}
87
+ {"current_steps": 435, "total_steps": 21210, "loss": 0.1413, "lr": 1.0231023102310232e-05, "epoch": 0.2050919377652051, "percentage": 2.05, "elapsed_time": "0:02:17", "remaining_time": "1:49:37", "throughput": 3163.92, "total_tokens": 435776}
88
+ {"current_steps": 440, "total_steps": 21210, "loss": 0.3757, "lr": 1.034889203206035e-05, "epoch": 0.20744931636020744, "percentage": 2.07, "elapsed_time": "0:02:19", "remaining_time": "1:49:30", "throughput": 3163.42, "total_tokens": 440352}
89
+ {"current_steps": 445, "total_steps": 21210, "loss": 0.128, "lr": 1.0466760961810467e-05, "epoch": 0.20980669495520982, "percentage": 2.1, "elapsed_time": "0:02:20", "remaining_time": "1:49:22", "throughput": 3162.65, "total_tokens": 444768}
90
+ {"current_steps": 450, "total_steps": 21210, "loss": 0.4375, "lr": 1.0584629891560585e-05, "epoch": 0.21216407355021216, "percentage": 2.12, "elapsed_time": "0:02:22", "remaining_time": "1:49:29", "throughput": 3163.62, "total_tokens": 450528}
91
+ {"current_steps": 455, "total_steps": 21210, "loss": 0.6733, "lr": 1.0702498821310702e-05, "epoch": 0.2145214521452145, "percentage": 2.15, "elapsed_time": "0:02:23", "remaining_time": "1:49:20", "throughput": 3163.39, "total_tokens": 454976}
92
+ {"current_steps": 460, "total_steps": 21210, "loss": 0.7582, "lr": 1.0820367751060821e-05, "epoch": 0.21687883074021688, "percentage": 2.17, "elapsed_time": "0:02:25", "remaining_time": "1:49:08", "throughput": 3162.46, "total_tokens": 459072}
93
+ {"current_steps": 465, "total_steps": 21210, "loss": 0.1904, "lr": 1.0938236680810939e-05, "epoch": 0.21923620933521923, "percentage": 2.19, "elapsed_time": "0:02:26", "remaining_time": "1:49:10", "throughput": 3162.11, "total_tokens": 464320}
94
+ {"current_steps": 470, "total_steps": 21210, "loss": 0.0705, "lr": 1.1056105610561057e-05, "epoch": 0.2215935879302216, "percentage": 2.22, "elapsed_time": "0:02:28", "remaining_time": "1:49:05", "throughput": 3162.67, "total_tokens": 469120}
95
+ {"current_steps": 475, "total_steps": 21210, "loss": 0.3262, "lr": 1.1173974540311174e-05, "epoch": 0.22395096652522395, "percentage": 2.24, "elapsed_time": "0:02:29", "remaining_time": "1:49:00", "throughput": 3162.85, "total_tokens": 473920}
96
+ {"current_steps": 480, "total_steps": 21210, "loss": 0.4997, "lr": 1.1291843470061292e-05, "epoch": 0.2263083451202263, "percentage": 2.26, "elapsed_time": "0:02:31", "remaining_time": "1:48:46", "throughput": 3162.35, "total_tokens": 477920}
97
+ {"current_steps": 485, "total_steps": 21210, "loss": 0.4178, "lr": 1.1409712399811411e-05, "epoch": 0.22866572371522867, "percentage": 2.29, "elapsed_time": "0:02:32", "remaining_time": "1:48:46", "throughput": 3162.54, "total_tokens": 483040}
98
+ {"current_steps": 490, "total_steps": 21210, "loss": 0.3223, "lr": 1.1527581329561529e-05, "epoch": 0.23102310231023102, "percentage": 2.31, "elapsed_time": "0:02:34", "remaining_time": "1:48:44", "throughput": 3161.98, "total_tokens": 487872}
99
+ {"current_steps": 495, "total_steps": 21210, "loss": 0.1633, "lr": 1.1645450259311646e-05, "epoch": 0.2333804809052334, "percentage": 2.33, "elapsed_time": "0:02:35", "remaining_time": "1:48:44", "throughput": 3162.08, "total_tokens": 492960}
100
+ {"current_steps": 500, "total_steps": 21210, "loss": 0.1123, "lr": 1.1763319189061764e-05, "epoch": 0.23573785950023574, "percentage": 2.36, "elapsed_time": "0:02:37", "remaining_time": "1:48:46", "throughput": 3163.2, "total_tokens": 498400}
101
+ {"current_steps": 505, "total_steps": 21210, "loss": 0.2401, "lr": 1.1881188118811881e-05, "epoch": 0.23809523809523808, "percentage": 2.38, "elapsed_time": "0:02:39", "remaining_time": "1:48:39", "throughput": 3161.98, "total_tokens": 502784}
102
+ {"current_steps": 510, "total_steps": 21210, "loss": 0.2126, "lr": 1.1999057048562e-05, "epoch": 0.24045261669024046, "percentage": 2.4, "elapsed_time": "0:02:40", "remaining_time": "1:48:36", "throughput": 3162.66, "total_tokens": 507776}
103
+ {"current_steps": 515, "total_steps": 21210, "loss": 0.0517, "lr": 1.2116925978312118e-05, "epoch": 0.2428099952852428, "percentage": 2.43, "elapsed_time": "0:02:42", "remaining_time": "1:48:33", "throughput": 3161.8, "total_tokens": 512480}
104
+ {"current_steps": 520, "total_steps": 21210, "loss": 0.2541, "lr": 1.2234794908062236e-05, "epoch": 0.24516737388024518, "percentage": 2.45, "elapsed_time": "0:02:43", "remaining_time": "1:48:29", "throughput": 3163.54, "total_tokens": 517600}
105
+ {"current_steps": 525, "total_steps": 21210, "loss": 0.3024, "lr": 1.2352663837812353e-05, "epoch": 0.24752475247524752, "percentage": 2.48, "elapsed_time": "0:02:45", "remaining_time": "1:48:39", "throughput": 3164.04, "total_tokens": 523520}
106
+ {"current_steps": 530, "total_steps": 21210, "loss": 0.3081, "lr": 1.247053276756247e-05, "epoch": 0.24988213107024987, "percentage": 2.5, "elapsed_time": "0:02:46", "remaining_time": "1:48:29", "throughput": 3162.65, "total_tokens": 527584}
107
+ {"current_steps": 535, "total_steps": 21210, "loss": 0.2706, "lr": 1.2588401697312588e-05, "epoch": 0.2522395096652522, "percentage": 2.52, "elapsed_time": "0:02:48", "remaining_time": "1:48:26", "throughput": 3163.95, "total_tokens": 532736}
108
+ {"current_steps": 540, "total_steps": 21210, "loss": 0.4416, "lr": 1.2706270627062708e-05, "epoch": 0.2545968882602546, "percentage": 2.55, "elapsed_time": "0:02:49", "remaining_time": "1:48:22", "throughput": 3163.68, "total_tokens": 537440}
109
+ {"current_steps": 545, "total_steps": 21210, "loss": 0.1643, "lr": 1.2824139556812825e-05, "epoch": 0.25695426685525696, "percentage": 2.57, "elapsed_time": "0:02:51", "remaining_time": "1:48:26", "throughput": 3164.45, "total_tokens": 543040}
110
+ {"current_steps": 550, "total_steps": 21210, "loss": 0.3817, "lr": 1.2942008486562943e-05, "epoch": 0.2593116454502593, "percentage": 2.59, "elapsed_time": "0:02:53", "remaining_time": "1:48:19", "throughput": 3164.25, "total_tokens": 547520}
111
+ {"current_steps": 555, "total_steps": 21210, "loss": 0.1746, "lr": 1.305987741631306e-05, "epoch": 0.26166902404526166, "percentage": 2.62, "elapsed_time": "0:02:54", "remaining_time": "1:48:19", "throughput": 3165.26, "total_tokens": 552800}
112
+ {"current_steps": 560, "total_steps": 21210, "loss": 0.0639, "lr": 1.3177746346063178e-05, "epoch": 0.264026402640264, "percentage": 2.64, "elapsed_time": "0:02:56", "remaining_time": "1:48:14", "throughput": 3164.82, "total_tokens": 557376}
113
+ {"current_steps": 565, "total_steps": 21210, "loss": 0.0617, "lr": 1.3295615275813297e-05, "epoch": 0.2663837812352664, "percentage": 2.66, "elapsed_time": "0:02:58", "remaining_time": "1:48:25", "throughput": 3166.55, "total_tokens": 563776}
114
+ {"current_steps": 570, "total_steps": 21210, "loss": 0.4295, "lr": 1.3413484205563415e-05, "epoch": 0.26874115983026875, "percentage": 2.69, "elapsed_time": "0:02:59", "remaining_time": "1:48:12", "throughput": 3166.18, "total_tokens": 567712}
115
+ {"current_steps": 575, "total_steps": 21210, "loss": 0.1494, "lr": 1.3531353135313532e-05, "epoch": 0.2710985384252711, "percentage": 2.71, "elapsed_time": "0:03:00", "remaining_time": "1:48:13", "throughput": 3166.82, "total_tokens": 572992}
116
+ {"current_steps": 580, "total_steps": 21210, "loss": 0.2063, "lr": 1.364922206506365e-05, "epoch": 0.27345591702027344, "percentage": 2.73, "elapsed_time": "0:03:02", "remaining_time": "1:48:18", "throughput": 3167.89, "total_tokens": 578816}
117
+ {"current_steps": 585, "total_steps": 21210, "loss": 0.3087, "lr": 1.3767090994813767e-05, "epoch": 0.2758132956152758, "percentage": 2.76, "elapsed_time": "0:03:04", "remaining_time": "1:48:15", "throughput": 3167.25, "total_tokens": 583552}
118
+ {"current_steps": 590, "total_steps": 21210, "loss": 0.1562, "lr": 1.3884959924563887e-05, "epoch": 0.2781706742102782, "percentage": 2.78, "elapsed_time": "0:03:05", "remaining_time": "1:48:16", "throughput": 3167.91, "total_tokens": 588864}
119
+ {"current_steps": 595, "total_steps": 21210, "loss": 0.1357, "lr": 1.4002828854314004e-05, "epoch": 0.28052805280528054, "percentage": 2.81, "elapsed_time": "0:03:07", "remaining_time": "1:48:09", "throughput": 3167.28, "total_tokens": 593248}
120
+ {"current_steps": 600, "total_steps": 21210, "loss": 0.3908, "lr": 1.4120697784064122e-05, "epoch": 0.2828854314002829, "percentage": 2.83, "elapsed_time": "0:03:09", "remaining_time": "1:48:19", "throughput": 3167.79, "total_tokens": 599360}
121
+ {"current_steps": 605, "total_steps": 21210, "loss": 0.302, "lr": 1.423856671381424e-05, "epoch": 0.28524280999528523, "percentage": 2.85, "elapsed_time": "0:03:10", "remaining_time": "1:48:16", "throughput": 3168.16, "total_tokens": 604352}
122
+ {"current_steps": 610, "total_steps": 21210, "loss": 0.1452, "lr": 1.4356435643564355e-05, "epoch": 0.2876001885902876, "percentage": 2.88, "elapsed_time": "0:03:12", "remaining_time": "1:48:20", "throughput": 3168.53, "total_tokens": 609952}
123
+ {"current_steps": 615, "total_steps": 21210, "loss": 0.0962, "lr": 1.4474304573314476e-05, "epoch": 0.28995756718529, "percentage": 2.9, "elapsed_time": "0:03:13", "remaining_time": "1:48:14", "throughput": 3168.2, "total_tokens": 614400}
124
+ {"current_steps": 620, "total_steps": 21210, "loss": 0.3459, "lr": 1.4592173503064594e-05, "epoch": 0.2923149457802923, "percentage": 2.92, "elapsed_time": "0:03:15", "remaining_time": "1:48:14", "throughput": 3167.95, "total_tokens": 619552}
125
+ {"current_steps": 625, "total_steps": 21210, "loss": 0.2729, "lr": 1.4710042432814711e-05, "epoch": 0.29467232437529467, "percentage": 2.95, "elapsed_time": "0:03:17", "remaining_time": "1:48:17", "throughput": 3168.15, "total_tokens": 624960}
126
+ {"current_steps": 630, "total_steps": 21210, "loss": 0.2094, "lr": 1.4827911362564827e-05, "epoch": 0.297029702970297, "percentage": 2.97, "elapsed_time": "0:03:19", "remaining_time": "1:48:28", "throughput": 3169.73, "total_tokens": 631520}
127
+ {"current_steps": 635, "total_steps": 21210, "loss": 0.2703, "lr": 1.4945780292314945e-05, "epoch": 0.29938708156529936, "percentage": 2.99, "elapsed_time": "0:03:21", "remaining_time": "1:48:35", "throughput": 3170.7, "total_tokens": 637568}
128
+ {"current_steps": 640, "total_steps": 21210, "loss": 0.2673, "lr": 1.5063649222065066e-05, "epoch": 0.30174446016030176, "percentage": 3.02, "elapsed_time": "0:03:22", "remaining_time": "1:48:34", "throughput": 3170.87, "total_tokens": 642688}
129
+ {"current_steps": 645, "total_steps": 21210, "loss": 0.2028, "lr": 1.5181518151815183e-05, "epoch": 0.3041018387553041, "percentage": 3.04, "elapsed_time": "0:03:24", "remaining_time": "1:48:31", "throughput": 3170.11, "total_tokens": 647392}
130
+ {"current_steps": 650, "total_steps": 21210, "loss": 0.2163, "lr": 1.52993870815653e-05, "epoch": 0.30645921735030646, "percentage": 3.06, "elapsed_time": "0:03:25", "remaining_time": "1:48:33", "throughput": 3170.33, "total_tokens": 652800}
131
+ {"current_steps": 655, "total_steps": 21210, "loss": 0.1059, "lr": 1.5417256011315417e-05, "epoch": 0.3088165959453088, "percentage": 3.09, "elapsed_time": "0:03:27", "remaining_time": "1:48:44", "throughput": 3171.16, "total_tokens": 659328}
132
+ {"current_steps": 660, "total_steps": 21210, "loss": 0.0759, "lr": 1.5535124941065536e-05, "epoch": 0.31117397454031115, "percentage": 3.11, "elapsed_time": "0:03:29", "remaining_time": "1:48:36", "throughput": 3170.12, "total_tokens": 663488}
133
+ {"current_steps": 665, "total_steps": 21210, "loss": 0.1421, "lr": 1.5652993870815655e-05, "epoch": 0.31353135313531355, "percentage": 3.14, "elapsed_time": "0:03:30", "remaining_time": "1:48:31", "throughput": 3170.34, "total_tokens": 668192}
134
+ {"current_steps": 670, "total_steps": 21210, "loss": 0.5979, "lr": 1.577086280056577e-05, "epoch": 0.3158887317303159, "percentage": 3.16, "elapsed_time": "0:03:32", "remaining_time": "1:48:32", "throughput": 3170.79, "total_tokens": 673568}
135
+ {"current_steps": 675, "total_steps": 21210, "loss": 0.1972, "lr": 1.588873173031589e-05, "epoch": 0.31824611032531824, "percentage": 3.18, "elapsed_time": "0:03:34", "remaining_time": "1:48:53", "throughput": 3171.35, "total_tokens": 681056}
136
+ {"current_steps": 680, "total_steps": 21210, "loss": 0.0861, "lr": 1.6006600660066006e-05, "epoch": 0.3206034889203206, "percentage": 3.21, "elapsed_time": "0:03:36", "remaining_time": "1:48:49", "throughput": 3171.45, "total_tokens": 685920}
137
+ {"current_steps": 685, "total_steps": 21210, "loss": 0.2072, "lr": 1.6124469589816126e-05, "epoch": 0.32296086751532294, "percentage": 3.23, "elapsed_time": "0:03:37", "remaining_time": "1:48:46", "throughput": 3171.73, "total_tokens": 690816}
138
+ {"current_steps": 690, "total_steps": 21210, "loss": 0.1425, "lr": 1.6242338519566245e-05, "epoch": 0.32531824611032534, "percentage": 3.25, "elapsed_time": "0:03:39", "remaining_time": "1:48:43", "throughput": 3171.38, "total_tokens": 695648}
139
+ {"current_steps": 695, "total_steps": 21210, "loss": 0.1239, "lr": 1.636020744931636e-05, "epoch": 0.3276756247053277, "percentage": 3.28, "elapsed_time": "0:03:41", "remaining_time": "1:48:43", "throughput": 3171.65, "total_tokens": 700960}
140
+ {"current_steps": 700, "total_steps": 21210, "loss": 0.1696, "lr": 1.647807637906648e-05, "epoch": 0.33003300330033003, "percentage": 3.3, "elapsed_time": "0:03:42", "remaining_time": "1:48:41", "throughput": 3171.34, "total_tokens": 705856}
141
+ {"current_steps": 705, "total_steps": 21210, "loss": 0.3662, "lr": 1.6595945308816596e-05, "epoch": 0.3323903818953324, "percentage": 3.32, "elapsed_time": "0:03:44", "remaining_time": "1:48:35", "throughput": 3170.52, "total_tokens": 710272}
142
+ {"current_steps": 710, "total_steps": 21210, "loss": 0.329, "lr": 1.6713814238566712e-05, "epoch": 0.3347477604903347, "percentage": 3.35, "elapsed_time": "0:03:45", "remaining_time": "1:48:29", "throughput": 3170.38, "total_tokens": 714816}
143
+ {"current_steps": 715, "total_steps": 21210, "loss": 0.8206, "lr": 1.6831683168316834e-05, "epoch": 0.3371051390853371, "percentage": 3.37, "elapsed_time": "0:03:47", "remaining_time": "1:48:35", "throughput": 3170.96, "total_tokens": 720736}
144
+ {"current_steps": 720, "total_steps": 21210, "loss": 0.2018, "lr": 1.694955209806695e-05, "epoch": 0.33946251768033947, "percentage": 3.39, "elapsed_time": "0:03:49", "remaining_time": "1:48:40", "throughput": 3172.2, "total_tokens": 726848}
145
+ {"current_steps": 725, "total_steps": 21210, "loss": 0.4315, "lr": 1.706742102781707e-05, "epoch": 0.3418198962753418, "percentage": 3.42, "elapsed_time": "0:03:50", "remaining_time": "1:48:43", "throughput": 3172.93, "total_tokens": 732512}
146
+ {"current_steps": 730, "total_steps": 21210, "loss": 0.1915, "lr": 1.7185289957567185e-05, "epoch": 0.34417727487034416, "percentage": 3.44, "elapsed_time": "0:03:52", "remaining_time": "1:48:43", "throughput": 3173.57, "total_tokens": 737952}
147
+ {"current_steps": 735, "total_steps": 21210, "loss": 0.1208, "lr": 1.73031588873173e-05, "epoch": 0.3465346534653465, "percentage": 3.47, "elapsed_time": "0:03:54", "remaining_time": "1:48:40", "throughput": 3173.19, "total_tokens": 742752}
148
+ {"current_steps": 740, "total_steps": 21210, "loss": 0.5414, "lr": 1.7421027817067424e-05, "epoch": 0.3488920320603489, "percentage": 3.49, "elapsed_time": "0:03:55", "remaining_time": "1:48:40", "throughput": 3173.22, "total_tokens": 747968}
149
+ {"current_steps": 745, "total_steps": 21210, "loss": 0.2476, "lr": 1.753889674681754e-05, "epoch": 0.35124941065535126, "percentage": 3.51, "elapsed_time": "0:03:57", "remaining_time": "1:48:43", "throughput": 3173.68, "total_tokens": 753632}
150
+ {"current_steps": 750, "total_steps": 21210, "loss": 0.3497, "lr": 1.765676567656766e-05, "epoch": 0.3536067892503536, "percentage": 3.54, "elapsed_time": "0:03:59", "remaining_time": "1:48:50", "throughput": 3174.17, "total_tokens": 759904}
151
+ {"current_steps": 755, "total_steps": 21210, "loss": 0.5964, "lr": 1.7774634606317775e-05, "epoch": 0.35596416784535595, "percentage": 3.56, "elapsed_time": "0:04:00", "remaining_time": "1:48:48", "throughput": 3174.56, "total_tokens": 764960}
152
+ {"current_steps": 760, "total_steps": 21210, "loss": 0.2109, "lr": 1.789250353606789e-05, "epoch": 0.3583215464403583, "percentage": 3.58, "elapsed_time": "0:04:02", "remaining_time": "1:48:40", "throughput": 3174.02, "total_tokens": 769184}
153
+ {"current_steps": 765, "total_steps": 21210, "loss": 0.1323, "lr": 1.8010372465818014e-05, "epoch": 0.3606789250353607, "percentage": 3.61, "elapsed_time": "0:04:04", "remaining_time": "1:48:45", "throughput": 3174.47, "total_tokens": 775104}
154
+ {"current_steps": 770, "total_steps": 21210, "loss": 0.1665, "lr": 1.812824139556813e-05, "epoch": 0.36303630363036304, "percentage": 3.63, "elapsed_time": "0:04:05", "remaining_time": "1:48:40", "throughput": 3174.58, "total_tokens": 779744}
155
+ {"current_steps": 775, "total_steps": 21210, "loss": 0.068, "lr": 1.8246110325318245e-05, "epoch": 0.3653936822253654, "percentage": 3.65, "elapsed_time": "0:04:07", "remaining_time": "1:48:39", "throughput": 3174.4, "total_tokens": 784832}
156
+ {"current_steps": 780, "total_steps": 21210, "loss": 0.1474, "lr": 1.8363979255068365e-05, "epoch": 0.36775106082036774, "percentage": 3.68, "elapsed_time": "0:04:08", "remaining_time": "1:48:37", "throughput": 3174.61, "total_tokens": 789920}
157
+ {"current_steps": 785, "total_steps": 21210, "loss": 0.1002, "lr": 1.848184818481848e-05, "epoch": 0.3701084394153701, "percentage": 3.7, "elapsed_time": "0:04:10", "remaining_time": "1:48:36", "throughput": 3174.78, "total_tokens": 795168}
158
+ {"current_steps": 790, "total_steps": 21210, "loss": 0.3149, "lr": 1.8599717114568603e-05, "epoch": 0.3724658180103725, "percentage": 3.72, "elapsed_time": "0:04:12", "remaining_time": "1:48:34", "throughput": 3174.65, "total_tokens": 800096}
159
+ {"current_steps": 795, "total_steps": 21210, "loss": 0.1795, "lr": 1.871758604431872e-05, "epoch": 0.37482319660537483, "percentage": 3.75, "elapsed_time": "0:04:13", "remaining_time": "1:48:35", "throughput": 3174.97, "total_tokens": 805632}
160
+ {"current_steps": 800, "total_steps": 21210, "loss": 0.3072, "lr": 1.8835454974068835e-05, "epoch": 0.3771805752003772, "percentage": 3.77, "elapsed_time": "0:04:15", "remaining_time": "1:48:35", "throughput": 3174.47, "total_tokens": 810688}
161
+ {"current_steps": 805, "total_steps": 21210, "loss": 0.2722, "lr": 1.8953323903818954e-05, "epoch": 0.3795379537953795, "percentage": 3.8, "elapsed_time": "0:04:16", "remaining_time": "1:48:28", "throughput": 3174.91, "total_tokens": 815264}
162
+ {"current_steps": 810, "total_steps": 21210, "loss": 0.2517, "lr": 1.907119283356907e-05, "epoch": 0.38189533239038187, "percentage": 3.82, "elapsed_time": "0:04:18", "remaining_time": "1:48:26", "throughput": 3175.37, "total_tokens": 820320}
163
+ {"current_steps": 815, "total_steps": 21210, "loss": 0.4604, "lr": 1.9189061763319193e-05, "epoch": 0.38425271098538427, "percentage": 3.84, "elapsed_time": "0:04:19", "remaining_time": "1:48:14", "throughput": 3175.15, "total_tokens": 824064}
164
+ {"current_steps": 820, "total_steps": 21210, "loss": 0.1154, "lr": 1.930693069306931e-05, "epoch": 0.3866100895803866, "percentage": 3.87, "elapsed_time": "0:04:21", "remaining_time": "1:48:12", "throughput": 3175.35, "total_tokens": 829120}
165
+ {"current_steps": 825, "total_steps": 21210, "loss": 0.189, "lr": 1.9424799622819424e-05, "epoch": 0.38896746817538896, "percentage": 3.89, "elapsed_time": "0:04:22", "remaining_time": "1:48:17", "throughput": 3174.8, "total_tokens": 834816}
166
+ {"current_steps": 830, "total_steps": 21210, "loss": 0.1241, "lr": 1.9542668552569544e-05, "epoch": 0.3913248467703913, "percentage": 3.91, "elapsed_time": "0:04:24", "remaining_time": "1:48:17", "throughput": 3175.21, "total_tokens": 840256}
167
+ {"current_steps": 835, "total_steps": 21210, "loss": 0.1061, "lr": 1.966053748231966e-05, "epoch": 0.39368222536539366, "percentage": 3.94, "elapsed_time": "0:04:26", "remaining_time": "1:48:13", "throughput": 3174.82, "total_tokens": 844864}
168
+ {"current_steps": 840, "total_steps": 21210, "loss": 0.2223, "lr": 1.977840641206978e-05, "epoch": 0.39603960396039606, "percentage": 3.96, "elapsed_time": "0:04:27", "remaining_time": "1:48:14", "throughput": 3175.09, "total_tokens": 850304}
169
+ {"current_steps": 845, "total_steps": 21210, "loss": 0.1223, "lr": 1.9896275341819898e-05, "epoch": 0.3983969825553984, "percentage": 3.98, "elapsed_time": "0:04:29", "remaining_time": "1:48:11", "throughput": 3174.94, "total_tokens": 855232}
170
+ {"current_steps": 850, "total_steps": 21210, "loss": 0.4665, "lr": 2.0014144271570014e-05, "epoch": 0.40075436115040075, "percentage": 4.01, "elapsed_time": "0:04:30", "remaining_time": "1:48:08", "throughput": 3175.12, "total_tokens": 860128}
171
+ {"current_steps": 855, "total_steps": 21210, "loss": 0.3571, "lr": 2.0132013201320133e-05, "epoch": 0.4031117397454031, "percentage": 4.03, "elapsed_time": "0:04:32", "remaining_time": "1:48:05", "throughput": 3174.68, "total_tokens": 864896}
172
+ {"current_steps": 860, "total_steps": 21210, "loss": 0.2638, "lr": 2.024988213107025e-05, "epoch": 0.40546911834040544, "percentage": 4.05, "elapsed_time": "0:04:33", "remaining_time": "1:48:01", "throughput": 3174.09, "total_tokens": 869408}
173
+ {"current_steps": 865, "total_steps": 21210, "loss": 0.1763, "lr": 2.036775106082037e-05, "epoch": 0.40782649693540785, "percentage": 4.08, "elapsed_time": "0:04:35", "remaining_time": "1:47:58", "throughput": 3173.81, "total_tokens": 874144}
174
+ {"current_steps": 870, "total_steps": 21210, "loss": 0.3704, "lr": 2.0485619990570488e-05, "epoch": 0.4101838755304102, "percentage": 4.1, "elapsed_time": "0:04:36", "remaining_time": "1:47:55", "throughput": 3173.76, "total_tokens": 879040}
175
+ {"current_steps": 875, "total_steps": 21210, "loss": 0.23, "lr": 2.0603488920320603e-05, "epoch": 0.41254125412541254, "percentage": 4.13, "elapsed_time": "0:04:38", "remaining_time": "1:47:50", "throughput": 3173.96, "total_tokens": 883712}
176
+ {"current_steps": 880, "total_steps": 21210, "loss": 0.1763, "lr": 2.0721357850070723e-05, "epoch": 0.4148986327204149, "percentage": 4.15, "elapsed_time": "0:04:39", "remaining_time": "1:47:44", "throughput": 3173.75, "total_tokens": 888128}
177
+ {"current_steps": 885, "total_steps": 21210, "loss": 0.1873, "lr": 2.083922677982084e-05, "epoch": 0.41725601131541723, "percentage": 4.17, "elapsed_time": "0:04:41", "remaining_time": "1:47:50", "throughput": 3174.18, "total_tokens": 894240}
178
+ {"current_steps": 890, "total_steps": 21210, "loss": 0.1787, "lr": 2.0957095709570958e-05, "epoch": 0.41961338991041963, "percentage": 4.2, "elapsed_time": "0:04:43", "remaining_time": "1:47:48", "throughput": 3174.64, "total_tokens": 899456}
179
+ {"current_steps": 895, "total_steps": 21210, "loss": 0.1412, "lr": 2.1074964639321077e-05, "epoch": 0.421970768505422, "percentage": 4.22, "elapsed_time": "0:04:45", "remaining_time": "1:47:49", "throughput": 3174.16, "total_tokens": 904672}
180
+ {"current_steps": 900, "total_steps": 21210, "loss": 0.2004, "lr": 2.1192833569071193e-05, "epoch": 0.4243281471004243, "percentage": 4.24, "elapsed_time": "0:04:47", "remaining_time": "1:48:10", "throughput": 3175.23, "total_tokens": 913216}
181
+ {"current_steps": 905, "total_steps": 21210, "loss": 0.4027, "lr": 2.1310702498821312e-05, "epoch": 0.42668552569542667, "percentage": 4.27, "elapsed_time": "0:04:49", "remaining_time": "1:48:05", "throughput": 3174.7, "total_tokens": 917664}
182
+ {"current_steps": 910, "total_steps": 21210, "loss": 0.1375, "lr": 2.1428571428571428e-05, "epoch": 0.429042904290429, "percentage": 4.29, "elapsed_time": "0:04:50", "remaining_time": "1:48:07", "throughput": 3175.0, "total_tokens": 923360}
183
+ {"current_steps": 915, "total_steps": 21210, "loss": 0.1583, "lr": 2.1546440358321547e-05, "epoch": 0.4314002828854314, "percentage": 4.31, "elapsed_time": "0:04:52", "remaining_time": "1:48:06", "throughput": 3175.24, "total_tokens": 928608}
184
+ {"current_steps": 920, "total_steps": 21210, "loss": 0.1373, "lr": 2.1664309288071667e-05, "epoch": 0.43375766148043376, "percentage": 4.34, "elapsed_time": "0:04:53", "remaining_time": "1:48:02", "throughput": 3175.47, "total_tokens": 933312}
185
+ {"current_steps": 925, "total_steps": 21210, "loss": 0.3189, "lr": 2.1782178217821783e-05, "epoch": 0.4361150400754361, "percentage": 4.36, "elapsed_time": "0:04:55", "remaining_time": "1:47:56", "throughput": 3175.37, "total_tokens": 937824}
186
+ {"current_steps": 930, "total_steps": 21210, "loss": 0.3496, "lr": 2.1900047147571902e-05, "epoch": 0.43847241867043846, "percentage": 4.38, "elapsed_time": "0:04:56", "remaining_time": "1:47:50", "throughput": 3174.93, "total_tokens": 942016}
187
+ {"current_steps": 935, "total_steps": 21210, "loss": 0.3136, "lr": 2.2017916077322018e-05, "epoch": 0.4408297972654408, "percentage": 4.41, "elapsed_time": "0:04:58", "remaining_time": "1:47:43", "throughput": 3174.15, "total_tokens": 946080}
188
+ {"current_steps": 940, "total_steps": 21210, "loss": 0.0724, "lr": 2.2135785007072137e-05, "epoch": 0.4431871758604432, "percentage": 4.43, "elapsed_time": "0:04:59", "remaining_time": "1:47:41", "throughput": 3174.3, "total_tokens": 951168}
189
+ {"current_steps": 945, "total_steps": 21210, "loss": 0.1784, "lr": 2.2253653936822256e-05, "epoch": 0.44554455445544555, "percentage": 4.46, "elapsed_time": "0:05:01", "remaining_time": "1:47:43", "throughput": 3174.89, "total_tokens": 956992}
190
+ {"current_steps": 950, "total_steps": 21210, "loss": 0.1649, "lr": 2.2371522866572372e-05, "epoch": 0.4479019330504479, "percentage": 4.48, "elapsed_time": "0:05:02", "remaining_time": "1:47:37", "throughput": 3174.36, "total_tokens": 961248}
191
+ {"current_steps": 955, "total_steps": 21210, "loss": 0.2852, "lr": 2.248939179632249e-05, "epoch": 0.45025931164545024, "percentage": 4.5, "elapsed_time": "0:05:04", "remaining_time": "1:47:31", "throughput": 3173.7, "total_tokens": 965376}
192
+ {"current_steps": 960, "total_steps": 21210, "loss": 0.3548, "lr": 2.2607260726072607e-05, "epoch": 0.4526166902404526, "percentage": 4.53, "elapsed_time": "0:05:05", "remaining_time": "1:47:25", "throughput": 3173.27, "total_tokens": 969664}
193
+ {"current_steps": 965, "total_steps": 21210, "loss": 0.1377, "lr": 2.2725129655822727e-05, "epoch": 0.454974068835455, "percentage": 4.55, "elapsed_time": "0:05:06", "remaining_time": "1:47:19", "throughput": 3173.18, "total_tokens": 974016}
194
+ {"current_steps": 970, "total_steps": 21210, "loss": 0.3587, "lr": 2.2842998585572846e-05, "epoch": 0.45733144743045734, "percentage": 4.57, "elapsed_time": "0:05:08", "remaining_time": "1:47:18", "throughput": 3173.21, "total_tokens": 979072}
195
+ {"current_steps": 975, "total_steps": 21210, "loss": 0.3017, "lr": 2.296086751532296e-05, "epoch": 0.4596888260254597, "percentage": 4.6, "elapsed_time": "0:05:10", "remaining_time": "1:47:15", "throughput": 3173.39, "total_tokens": 984032}
196
+ {"current_steps": 980, "total_steps": 21210, "loss": 0.0502, "lr": 2.3078736445073078e-05, "epoch": 0.46204620462046203, "percentage": 4.62, "elapsed_time": "0:05:11", "remaining_time": "1:47:11", "throughput": 3172.88, "total_tokens": 988544}
197
+ {"current_steps": 985, "total_steps": 21210, "loss": 0.3651, "lr": 2.3196605374823197e-05, "epoch": 0.4644035832154644, "percentage": 4.64, "elapsed_time": "0:05:13", "remaining_time": "1:47:08", "throughput": 3173.08, "total_tokens": 993504}
198
+ {"current_steps": 990, "total_steps": 21210, "loss": 0.2169, "lr": 2.3314474304573316e-05, "epoch": 0.4667609618104668, "percentage": 4.67, "elapsed_time": "0:05:14", "remaining_time": "1:47:11", "throughput": 3172.82, "total_tokens": 999104}
199
+ {"current_steps": 995, "total_steps": 21210, "loss": 0.1685, "lr": 2.3432343234323435e-05, "epoch": 0.4691183404054691, "percentage": 4.69, "elapsed_time": "0:05:16", "remaining_time": "1:47:13", "throughput": 3173.49, "total_tokens": 1004864}
200
+ {"current_steps": 1000, "total_steps": 21210, "loss": 0.1179, "lr": 2.355021216407355e-05, "epoch": 0.47147571900047147, "percentage": 4.71, "elapsed_time": "0:05:18", "remaining_time": "1:47:09", "throughput": 3173.33, "total_tokens": 1009472}
201
+ {"current_steps": 1005, "total_steps": 21210, "loss": 0.1602, "lr": 2.3668081093823667e-05, "epoch": 0.4738330975954738, "percentage": 4.74, "elapsed_time": "0:05:19", "remaining_time": "1:47:02", "throughput": 3172.82, "total_tokens": 1013536}
202
+ {"current_steps": 1010, "total_steps": 21210, "loss": 0.1298, "lr": 2.3785950023573786e-05, "epoch": 0.47619047619047616, "percentage": 4.76, "elapsed_time": "0:05:20", "remaining_time": "1:46:58", "throughput": 3172.57, "total_tokens": 1018144}
203
+ {"current_steps": 1015, "total_steps": 21210, "loss": 0.391, "lr": 2.3903818953323906e-05, "epoch": 0.47854785478547857, "percentage": 4.79, "elapsed_time": "0:05:22", "remaining_time": "1:46:54", "throughput": 3172.6, "total_tokens": 1022848}
204
+ {"current_steps": 1020, "total_steps": 21210, "loss": 0.2078, "lr": 2.4021687883074025e-05, "epoch": 0.4809052333804809, "percentage": 4.81, "elapsed_time": "0:05:23", "remaining_time": "1:46:50", "throughput": 3172.56, "total_tokens": 1027424}
205
+ {"current_steps": 1025, "total_steps": 21210, "loss": 0.326, "lr": 2.413955681282414e-05, "epoch": 0.48326261197548326, "percentage": 4.83, "elapsed_time": "0:05:25", "remaining_time": "1:46:50", "throughput": 3172.51, "total_tokens": 1032768}
206
+ {"current_steps": 1030, "total_steps": 21210, "loss": 0.057, "lr": 2.4257425742574257e-05, "epoch": 0.4856199905704856, "percentage": 4.86, "elapsed_time": "0:05:27", "remaining_time": "1:46:47", "throughput": 3172.22, "total_tokens": 1037440}
207
+ {"current_steps": 1035, "total_steps": 21210, "loss": 0.1232, "lr": 2.4375294672324376e-05, "epoch": 0.48797736916548795, "percentage": 4.88, "elapsed_time": "0:05:28", "remaining_time": "1:46:44", "throughput": 3172.54, "total_tokens": 1042400}
208
+ {"current_steps": 1040, "total_steps": 21210, "loss": 0.1843, "lr": 2.4493163602074495e-05, "epoch": 0.49033474776049035, "percentage": 4.9, "elapsed_time": "0:05:30", "remaining_time": "1:46:46", "throughput": 3172.8, "total_tokens": 1048032}
209
+ {"current_steps": 1045, "total_steps": 21210, "loss": 0.1646, "lr": 2.461103253182461e-05, "epoch": 0.4926921263554927, "percentage": 4.93, "elapsed_time": "0:05:31", "remaining_time": "1:46:45", "throughput": 3173.33, "total_tokens": 1053408}
210
+ {"current_steps": 1050, "total_steps": 21210, "loss": 0.1685, "lr": 2.472890146157473e-05, "epoch": 0.49504950495049505, "percentage": 4.95, "elapsed_time": "0:05:33", "remaining_time": "1:46:47", "throughput": 3173.44, "total_tokens": 1059008}
211
+ {"current_steps": 1055, "total_steps": 21210, "loss": 0.1896, "lr": 2.4846770391324846e-05, "epoch": 0.4974068835454974, "percentage": 4.97, "elapsed_time": "0:05:35", "remaining_time": "1:46:44", "throughput": 3172.96, "total_tokens": 1063712}
212
+ {"current_steps": 1060, "total_steps": 21210, "loss": 0.7593, "lr": 2.4964639321074965e-05, "epoch": 0.49976426214049974, "percentage": 5.0, "elapsed_time": "0:05:36", "remaining_time": "1:46:40", "throughput": 3172.85, "total_tokens": 1068320}
213
+ {"current_steps": 1061, "total_steps": 21210, "eval_loss": 0.22503285109996796, "epoch": 0.5002357378595003, "percentage": 5.0, "elapsed_time": "0:06:00", "remaining_time": "1:53:58", "throughput": 2970.11, "total_tokens": 1069568}
214
+ {"current_steps": 1065, "total_steps": 21210, "loss": 0.1379, "lr": 2.508250825082508e-05, "epoch": 0.5021216407355021, "percentage": 5.02, "elapsed_time": "0:06:02", "remaining_time": "1:54:07", "throughput": 2964.72, "total_tokens": 1073280}
215
+ {"current_steps": 1070, "total_steps": 21210, "loss": 0.213, "lr": 2.52003771805752e-05, "epoch": 0.5044790193305044, "percentage": 5.04, "elapsed_time": "0:06:03", "remaining_time": "1:53:58", "throughput": 2965.06, "total_tokens": 1077184}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f60669290c79ecbdbdb6f039f7ac92bcd1cbba230e8146834769f296338b623f
3
+ size 6225