rbelanec commited on
Commit
8cbb8ca
·
verified ·
1 Parent(s): 196379d

Training in progress, step 826

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 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
4
+ "exclude_modules": null,
5
+ "fan_in_fan_out": false,
6
+ "feedforward_modules": "down_proj",
7
+ "inference_mode": true,
8
+ "init_ia3_weights": true,
9
+ "modules_to_save": null,
10
+ "peft_type": "IA3",
11
+ "revision": null,
12
+ "target_modules": [
13
+ "v_proj",
14
+ "k_proj",
15
+ "down_proj"
16
+ ],
17
+ "task_type": "CAUSAL_LM"
18
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff31bc75524ca32d3d048b2f464ec3998b1a2059a458f6af924fdcfa143cbdd
3
+ size 798032
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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ seed: 456
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: ia3
13
+ task_type: CAUSAL_LM
14
+ target_modules:
15
+ - k_proj
16
+ - v_proj
17
+ - down_proj
18
+ feedforward_modules: down_proj
19
+
20
+ ### dataset
21
+ dataset: mrpc
22
+ template: llama3
23
+ cutoff_len: 2048
24
+ overwrite_cache: true
25
+ preprocessing_num_workers: 8
26
+ dataloader_num_workers: 2
27
+ packing: false
28
+
29
+ ### output
30
+ output_dir: saves_multiple/ia3/llama-3-8b-instruct/train_mrpc_456_1760637795
31
+ logging_steps: 5
32
+ save_steps: 0.05
33
+ overwrite_output_dir: true
34
+ save_only_model: false
35
+ plot_loss: true
36
+ include_num_input_tokens_seen: true
37
+ push_to_hub: true
38
+ push_to_hub_organization: rbelanec
39
+ load_best_model_at_end: true
40
+ save_total_limit: 1
41
+
42
+ ### train
43
+ per_device_train_batch_size: 4
44
+ learning_rate: 5.0e-5
45
+ num_train_epochs: 20
46
+ weight_decay: 1.0e-5
47
+ lr_scheduler_type: cosine
48
+ bf16: true
49
+ ddp_timeout: 180000000
50
+ resume_from_checkpoint: null
51
+ warmup_ratio: 0.1
52
+ optim: adamw_torch
53
+ report_to:
54
+ - wandb
55
+ run_name: ia3_llama-3-8b-instruct_train_mrpc_456_1760637795
56
+
57
+ ### eval
58
+ per_device_eval_batch_size: 4
59
+ eval_strategy: steps
60
+ eval_steps: 0.05
61
+ val_size: 0.1
trainer_log.jsonl ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 16520, "loss": 0.2115, "lr": 1.2106537530266344e-07, "epoch": 0.006053268765133172, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:09:49", "throughput": 1639.95, "total_tokens": 2080}
2
+ {"current_steps": 10, "total_steps": 16520, "loss": 0.2785, "lr": 2.7239709443099273e-07, "epoch": 0.012106537530266344, "percentage": 0.06, "elapsed_time": "0:00:02", "remaining_time": "0:56:23", "throughput": 1998.39, "total_tokens": 4096}
3
+ {"current_steps": 15, "total_steps": 16520, "loss": 0.2869, "lr": 4.2372881355932204e-07, "epoch": 0.018159806295399514, "percentage": 0.09, "elapsed_time": "0:00:02", "remaining_time": "0:51:58", "throughput": 2156.45, "total_tokens": 6112}
4
+ {"current_steps": 20, "total_steps": 16520, "loss": 0.1891, "lr": 5.750605326876514e-07, "epoch": 0.024213075060532687, "percentage": 0.12, "elapsed_time": "0:00:03", "remaining_time": "0:50:41", "throughput": 2248.3, "total_tokens": 8288}
5
+ {"current_steps": 25, "total_steps": 16520, "loss": 0.2838, "lr": 7.263922518159807e-07, "epoch": 0.03026634382566586, "percentage": 0.15, "elapsed_time": "0:00:04", "remaining_time": "0:48:46", "throughput": 2315.54, "total_tokens": 10272}
6
+ {"current_steps": 30, "total_steps": 16520, "loss": 0.3742, "lr": 8.777239709443099e-07, "epoch": 0.03631961259079903, "percentage": 0.18, "elapsed_time": "0:00:05", "remaining_time": "0:48:09", "throughput": 2362.01, "total_tokens": 12416}
7
+ {"current_steps": 35, "total_steps": 16520, "loss": 0.1887, "lr": 1.0290556900726392e-06, "epoch": 0.0423728813559322, "percentage": 0.21, "elapsed_time": "0:00:06", "remaining_time": "0:47:09", "throughput": 2402.66, "total_tokens": 14432}
8
+ {"current_steps": 40, "total_steps": 16520, "loss": 0.2379, "lr": 1.1803874092009686e-06, "epoch": 0.048426150121065374, "percentage": 0.24, "elapsed_time": "0:00:06", "remaining_time": "0:46:09", "throughput": 2423.29, "total_tokens": 16288}
9
+ {"current_steps": 45, "total_steps": 16520, "loss": 0.1968, "lr": 1.3317191283292979e-06, "epoch": 0.05447941888619855, "percentage": 0.27, "elapsed_time": "0:00:07", "remaining_time": "0:45:45", "throughput": 2440.4, "total_tokens": 18304}
10
+ {"current_steps": 50, "total_steps": 16520, "loss": 0.1854, "lr": 1.4830508474576273e-06, "epoch": 0.06053268765133172, "percentage": 0.3, "elapsed_time": "0:00:08", "remaining_time": "0:45:51", "throughput": 2455.4, "total_tokens": 20512}
11
+ {"current_steps": 55, "total_steps": 16520, "loss": 0.1824, "lr": 1.6343825665859565e-06, "epoch": 0.06658595641646489, "percentage": 0.33, "elapsed_time": "0:00:09", "remaining_time": "0:45:43", "throughput": 2461.41, "total_tokens": 22560}
12
+ {"current_steps": 60, "total_steps": 16520, "loss": 0.1982, "lr": 1.7857142857142857e-06, "epoch": 0.07263922518159806, "percentage": 0.36, "elapsed_time": "0:00:10", "remaining_time": "0:45:48", "throughput": 2469.37, "total_tokens": 24736}
13
+ {"current_steps": 65, "total_steps": 16520, "loss": 0.1534, "lr": 1.937046004842615e-06, "epoch": 0.07869249394673124, "percentage": 0.39, "elapsed_time": "0:00:10", "remaining_time": "0:45:43", "throughput": 2474.4, "total_tokens": 26816}
14
+ {"current_steps": 70, "total_steps": 16520, "loss": 0.2148, "lr": 2.0883777239709445e-06, "epoch": 0.0847457627118644, "percentage": 0.42, "elapsed_time": "0:00:11", "remaining_time": "0:45:46", "throughput": 2478.18, "total_tokens": 28960}
15
+ {"current_steps": 75, "total_steps": 16520, "loss": 0.2215, "lr": 2.239709443099274e-06, "epoch": 0.09079903147699758, "percentage": 0.45, "elapsed_time": "0:00:12", "remaining_time": "0:45:33", "throughput": 2484.35, "total_tokens": 30976}
16
+ {"current_steps": 80, "total_steps": 16520, "loss": 0.2426, "lr": 2.391041162227603e-06, "epoch": 0.09685230024213075, "percentage": 0.48, "elapsed_time": "0:00:13", "remaining_time": "0:45:23", "throughput": 2494.02, "total_tokens": 33056}
17
+ {"current_steps": 85, "total_steps": 16520, "loss": 0.3335, "lr": 2.5423728813559323e-06, "epoch": 0.10290556900726393, "percentage": 0.51, "elapsed_time": "0:00:14", "remaining_time": "0:45:19", "throughput": 2495.85, "total_tokens": 35104}
18
+ {"current_steps": 90, "total_steps": 16520, "loss": 0.2504, "lr": 2.6937046004842618e-06, "epoch": 0.1089588377723971, "percentage": 0.54, "elapsed_time": "0:00:14", "remaining_time": "0:45:10", "throughput": 2500.34, "total_tokens": 37120}
19
+ {"current_steps": 95, "total_steps": 16520, "loss": 0.097, "lr": 2.8450363196125907e-06, "epoch": 0.11501210653753027, "percentage": 0.58, "elapsed_time": "0:00:15", "remaining_time": "0:45:07", "throughput": 2500.96, "total_tokens": 39168}
20
+ {"current_steps": 100, "total_steps": 16520, "loss": 0.2305, "lr": 2.99636803874092e-06, "epoch": 0.12106537530266344, "percentage": 0.61, "elapsed_time": "0:00:16", "remaining_time": "0:45:00", "throughput": 2506.11, "total_tokens": 41216}
21
+ {"current_steps": 105, "total_steps": 16520, "loss": 0.3135, "lr": 3.1476997578692496e-06, "epoch": 0.1271186440677966, "percentage": 0.64, "elapsed_time": "0:00:17", "remaining_time": "0:44:53", "throughput": 2510.77, "total_tokens": 43264}
22
+ {"current_steps": 110, "total_steps": 16520, "loss": 0.3231, "lr": 3.2990314769975786e-06, "epoch": 0.13317191283292978, "percentage": 0.67, "elapsed_time": "0:00:18", "remaining_time": "0:44:48", "throughput": 2513.92, "total_tokens": 45312}
23
+ {"current_steps": 115, "total_steps": 16520, "loss": 0.2264, "lr": 3.450363196125908e-06, "epoch": 0.13922518159806296, "percentage": 0.7, "elapsed_time": "0:00:18", "remaining_time": "0:44:38", "throughput": 2520.34, "total_tokens": 47328}
24
+ {"current_steps": 120, "total_steps": 16520, "loss": 0.1965, "lr": 3.6016949152542374e-06, "epoch": 0.14527845036319612, "percentage": 0.73, "elapsed_time": "0:00:19", "remaining_time": "0:44:24", "throughput": 2527.82, "total_tokens": 49280}
25
+ {"current_steps": 125, "total_steps": 16520, "loss": 0.2165, "lr": 3.7530266343825673e-06, "epoch": 0.1513317191283293, "percentage": 0.76, "elapsed_time": "0:00:20", "remaining_time": "0:44:16", "throughput": 2531.48, "total_tokens": 51264}
26
+ {"current_steps": 130, "total_steps": 16520, "loss": 0.3403, "lr": 3.904358353510896e-06, "epoch": 0.15738498789346247, "percentage": 0.79, "elapsed_time": "0:00:21", "remaining_time": "0:44:12", "throughput": 2534.29, "total_tokens": 53312}
27
+ {"current_steps": 135, "total_steps": 16520, "loss": 0.1652, "lr": 4.055690072639226e-06, "epoch": 0.16343825665859565, "percentage": 0.82, "elapsed_time": "0:00:21", "remaining_time": "0:44:05", "throughput": 2542.64, "total_tokens": 55424}
28
+ {"current_steps": 140, "total_steps": 16520, "loss": 0.2709, "lr": 4.207021791767555e-06, "epoch": 0.1694915254237288, "percentage": 0.85, "elapsed_time": "0:00:22", "remaining_time": "0:44:02", "throughput": 2546.32, "total_tokens": 57504}
29
+ {"current_steps": 145, "total_steps": 16520, "loss": 0.2777, "lr": 4.358353510895884e-06, "epoch": 0.17554479418886199, "percentage": 0.88, "elapsed_time": "0:00:23", "remaining_time": "0:44:03", "throughput": 2550.8, "total_tokens": 59712}
30
+ {"current_steps": 150, "total_steps": 16520, "loss": 0.228, "lr": 4.5096852300242135e-06, "epoch": 0.18159806295399517, "percentage": 0.91, "elapsed_time": "0:00:24", "remaining_time": "0:44:00", "throughput": 2552.84, "total_tokens": 61760}
31
+ {"current_steps": 155, "total_steps": 16520, "loss": 0.2292, "lr": 4.6610169491525425e-06, "epoch": 0.18765133171912832, "percentage": 0.94, "elapsed_time": "0:00:24", "remaining_time": "0:43:53", "throughput": 2556.78, "total_tokens": 63776}
32
+ {"current_steps": 160, "total_steps": 16520, "loss": 0.1386, "lr": 4.812348668280872e-06, "epoch": 0.1937046004842615, "percentage": 0.97, "elapsed_time": "0:00:25", "remaining_time": "0:43:57", "throughput": 2557.7, "total_tokens": 65984}
33
+ {"current_steps": 165, "total_steps": 16520, "loss": 0.1434, "lr": 4.963680387409201e-06, "epoch": 0.19975786924939468, "percentage": 1.0, "elapsed_time": "0:00:26", "remaining_time": "0:43:58", "throughput": 2558.63, "total_tokens": 68096}
34
+ {"current_steps": 170, "total_steps": 16520, "loss": 0.3021, "lr": 5.11501210653753e-06, "epoch": 0.20581113801452786, "percentage": 1.03, "elapsed_time": "0:00:27", "remaining_time": "0:43:54", "throughput": 2560.39, "total_tokens": 70144}
35
+ {"current_steps": 175, "total_steps": 16520, "loss": 0.2367, "lr": 5.26634382566586e-06, "epoch": 0.211864406779661, "percentage": 1.06, "elapsed_time": "0:00:28", "remaining_time": "0:43:53", "throughput": 2564.43, "total_tokens": 72320}
36
+ {"current_steps": 180, "total_steps": 16520, "loss": 0.2039, "lr": 5.417675544794189e-06, "epoch": 0.2179176755447942, "percentage": 1.09, "elapsed_time": "0:00:29", "remaining_time": "0:43:53", "throughput": 2563.22, "total_tokens": 74368}
37
+ {"current_steps": 185, "total_steps": 16520, "loss": 0.2762, "lr": 5.569007263922518e-06, "epoch": 0.22397094430992737, "percentage": 1.12, "elapsed_time": "0:00:29", "remaining_time": "0:43:48", "throughput": 2568.01, "total_tokens": 76448}
38
+ {"current_steps": 190, "total_steps": 16520, "loss": 0.2169, "lr": 5.720338983050848e-06, "epoch": 0.23002421307506055, "percentage": 1.15, "elapsed_time": "0:00:30", "remaining_time": "0:43:45", "throughput": 2567.12, "total_tokens": 78432}
39
+ {"current_steps": 195, "total_steps": 16520, "loss": 0.1502, "lr": 5.871670702179177e-06, "epoch": 0.2360774818401937, "percentage": 1.18, "elapsed_time": "0:00:31", "remaining_time": "0:43:43", "throughput": 2568.95, "total_tokens": 80512}
40
+ {"current_steps": 200, "total_steps": 16520, "loss": 0.2852, "lr": 6.023002421307506e-06, "epoch": 0.24213075060532688, "percentage": 1.21, "elapsed_time": "0:00:32", "remaining_time": "0:43:43", "throughput": 2568.75, "total_tokens": 82592}
41
+ {"current_steps": 205, "total_steps": 16520, "loss": 0.1813, "lr": 6.174334140435836e-06, "epoch": 0.24818401937046006, "percentage": 1.24, "elapsed_time": "0:00:32", "remaining_time": "0:43:38", "throughput": 2572.2, "total_tokens": 84640}
42
+ {"current_steps": 210, "total_steps": 16520, "loss": 0.2474, "lr": 6.325665859564164e-06, "epoch": 0.2542372881355932, "percentage": 1.27, "elapsed_time": "0:00:33", "remaining_time": "0:43:36", "throughput": 2572.63, "total_tokens": 86656}
43
+ {"current_steps": 215, "total_steps": 16520, "loss": 0.1722, "lr": 6.476997578692494e-06, "epoch": 0.2602905569007264, "percentage": 1.3, "elapsed_time": "0:00:34", "remaining_time": "0:43:33", "throughput": 2573.79, "total_tokens": 88704}
44
+ {"current_steps": 220, "total_steps": 16520, "loss": 0.1599, "lr": 6.628329297820824e-06, "epoch": 0.26634382566585957, "percentage": 1.33, "elapsed_time": "0:00:35", "remaining_time": "0:43:31", "throughput": 2573.99, "total_tokens": 90720}
45
+ {"current_steps": 225, "total_steps": 16520, "loss": 0.3355, "lr": 6.779661016949153e-06, "epoch": 0.27239709443099275, "percentage": 1.36, "elapsed_time": "0:00:35", "remaining_time": "0:43:26", "throughput": 2575.81, "total_tokens": 92704}
46
+ {"current_steps": 230, "total_steps": 16520, "loss": 0.2717, "lr": 6.9309927360774825e-06, "epoch": 0.2784503631961259, "percentage": 1.39, "elapsed_time": "0:00:36", "remaining_time": "0:43:19", "throughput": 2576.29, "total_tokens": 94560}
47
+ {"current_steps": 235, "total_steps": 16520, "loss": 0.3503, "lr": 7.0823244552058115e-06, "epoch": 0.2845036319612591, "percentage": 1.42, "elapsed_time": "0:00:37", "remaining_time": "0:43:13", "throughput": 2578.71, "total_tokens": 96512}
48
+ {"current_steps": 240, "total_steps": 16520, "loss": 0.2625, "lr": 7.233656174334141e-06, "epoch": 0.29055690072639223, "percentage": 1.45, "elapsed_time": "0:00:38", "remaining_time": "0:43:11", "throughput": 2580.34, "total_tokens": 98592}
49
+ {"current_steps": 245, "total_steps": 16520, "loss": 0.2905, "lr": 7.3849878934624694e-06, "epoch": 0.2966101694915254, "percentage": 1.48, "elapsed_time": "0:00:38", "remaining_time": "0:43:10", "throughput": 2581.09, "total_tokens": 100640}
50
+ {"current_steps": 250, "total_steps": 16520, "loss": 0.1742, "lr": 7.536319612590799e-06, "epoch": 0.3026634382566586, "percentage": 1.51, "elapsed_time": "0:00:39", "remaining_time": "0:43:08", "throughput": 2582.28, "total_tokens": 102720}
51
+ {"current_steps": 255, "total_steps": 16520, "loss": 0.2308, "lr": 7.687651331719129e-06, "epoch": 0.30871670702179177, "percentage": 1.54, "elapsed_time": "0:00:40", "remaining_time": "0:43:05", "throughput": 2583.2, "total_tokens": 104704}
52
+ {"current_steps": 260, "total_steps": 16520, "loss": 0.2484, "lr": 7.838983050847458e-06, "epoch": 0.31476997578692495, "percentage": 1.57, "elapsed_time": "0:00:41", "remaining_time": "0:43:05", "throughput": 2582.71, "total_tokens": 106784}
53
+ {"current_steps": 265, "total_steps": 16520, "loss": 0.1425, "lr": 7.990314769975787e-06, "epoch": 0.32082324455205813, "percentage": 1.6, "elapsed_time": "0:00:42", "remaining_time": "0:43:08", "throughput": 2582.84, "total_tokens": 108992}
54
+ {"current_steps": 270, "total_steps": 16520, "loss": 0.2462, "lr": 8.141646489104116e-06, "epoch": 0.3268765133171913, "percentage": 1.63, "elapsed_time": "0:00:43", "remaining_time": "0:43:10", "throughput": 2581.24, "total_tokens": 111104}
55
+ {"current_steps": 275, "total_steps": 16520, "loss": 0.4431, "lr": 8.292978208232447e-06, "epoch": 0.33292978208232443, "percentage": 1.66, "elapsed_time": "0:00:43", "remaining_time": "0:43:06", "throughput": 2583.06, "total_tokens": 113120}
56
+ {"current_steps": 280, "total_steps": 16520, "loss": 0.2022, "lr": 8.444309927360774e-06, "epoch": 0.3389830508474576, "percentage": 1.69, "elapsed_time": "0:00:44", "remaining_time": "0:43:07", "throughput": 2582.63, "total_tokens": 115200}
57
+ {"current_steps": 285, "total_steps": 16520, "loss": 0.2192, "lr": 8.595641646489105e-06, "epoch": 0.3450363196125908, "percentage": 1.73, "elapsed_time": "0:00:45", "remaining_time": "0:43:05", "throughput": 2583.53, "total_tokens": 117280}
58
+ {"current_steps": 290, "total_steps": 16520, "loss": 0.227, "lr": 8.746973365617434e-06, "epoch": 0.35108958837772397, "percentage": 1.76, "elapsed_time": "0:00:46", "remaining_time": "0:43:02", "throughput": 2585.35, "total_tokens": 119296}
59
+ {"current_steps": 295, "total_steps": 16520, "loss": 0.1656, "lr": 8.898305084745763e-06, "epoch": 0.35714285714285715, "percentage": 1.79, "elapsed_time": "0:00:46", "remaining_time": "0:43:00", "throughput": 2585.98, "total_tokens": 121344}
60
+ {"current_steps": 300, "total_steps": 16520, "loss": 0.2076, "lr": 9.049636803874092e-06, "epoch": 0.36319612590799033, "percentage": 1.82, "elapsed_time": "0:00:47", "remaining_time": "0:43:01", "throughput": 2588.12, "total_tokens": 123584}
61
+ {"current_steps": 305, "total_steps": 16520, "loss": 0.1718, "lr": 9.200968523002422e-06, "epoch": 0.3692493946731235, "percentage": 1.85, "elapsed_time": "0:00:48", "remaining_time": "0:42:58", "throughput": 2587.9, "total_tokens": 125504}
62
+ {"current_steps": 310, "total_steps": 16520, "loss": 0.3896, "lr": 9.352300242130751e-06, "epoch": 0.37530266343825663, "percentage": 1.88, "elapsed_time": "0:00:49", "remaining_time": "0:42:58", "throughput": 2587.46, "total_tokens": 127584}
63
+ {"current_steps": 315, "total_steps": 16520, "loss": 0.2959, "lr": 9.50363196125908e-06, "epoch": 0.3813559322033898, "percentage": 1.91, "elapsed_time": "0:00:50", "remaining_time": "0:42:56", "throughput": 2588.52, "total_tokens": 129664}
64
+ {"current_steps": 320, "total_steps": 16520, "loss": 0.2738, "lr": 9.65496368038741e-06, "epoch": 0.387409200968523, "percentage": 1.94, "elapsed_time": "0:00:50", "remaining_time": "0:42:55", "throughput": 2588.83, "total_tokens": 131712}
65
+ {"current_steps": 325, "total_steps": 16520, "loss": 0.3155, "lr": 9.806295399515738e-06, "epoch": 0.3934624697336562, "percentage": 1.97, "elapsed_time": "0:00:51", "remaining_time": "0:42:56", "throughput": 2589.26, "total_tokens": 133856}
66
+ {"current_steps": 330, "total_steps": 16520, "loss": 0.209, "lr": 9.957627118644067e-06, "epoch": 0.39951573849878935, "percentage": 2.0, "elapsed_time": "0:00:52", "remaining_time": "0:42:57", "throughput": 2588.33, "total_tokens": 136000}
67
+ {"current_steps": 335, "total_steps": 16520, "loss": 0.2466, "lr": 1.0108958837772398e-05, "epoch": 0.40556900726392253, "percentage": 2.03, "elapsed_time": "0:00:53", "remaining_time": "0:42:56", "throughput": 2589.24, "total_tokens": 138080}
68
+ {"current_steps": 340, "total_steps": 16520, "loss": 0.2488, "lr": 1.0260290556900727e-05, "epoch": 0.4116222760290557, "percentage": 2.06, "elapsed_time": "0:00:54", "remaining_time": "0:42:56", "throughput": 2589.19, "total_tokens": 140192}
69
+ {"current_steps": 345, "total_steps": 16520, "loss": 0.2268, "lr": 1.0411622276029056e-05, "epoch": 0.41767554479418884, "percentage": 2.09, "elapsed_time": "0:00:54", "remaining_time": "0:42:55", "throughput": 2590.2, "total_tokens": 142272}
70
+ {"current_steps": 350, "total_steps": 16520, "loss": 0.3712, "lr": 1.0562953995157387e-05, "epoch": 0.423728813559322, "percentage": 2.12, "elapsed_time": "0:00:55", "remaining_time": "0:42:52", "throughput": 2591.66, "total_tokens": 144288}
71
+ {"current_steps": 355, "total_steps": 16520, "loss": 0.1469, "lr": 1.0714285714285714e-05, "epoch": 0.4297820823244552, "percentage": 2.15, "elapsed_time": "0:00:56", "remaining_time": "0:42:52", "throughput": 2591.69, "total_tokens": 146400}
72
+ {"current_steps": 360, "total_steps": 16520, "loss": 0.2912, "lr": 1.0865617433414043e-05, "epoch": 0.4358353510895884, "percentage": 2.18, "elapsed_time": "0:00:57", "remaining_time": "0:42:50", "throughput": 2592.21, "total_tokens": 148448}
73
+ {"current_steps": 365, "total_steps": 16520, "loss": 0.2695, "lr": 1.1016949152542374e-05, "epoch": 0.44188861985472155, "percentage": 2.21, "elapsed_time": "0:00:57", "remaining_time": "0:42:46", "throughput": 2592.31, "total_tokens": 150304}
74
+ {"current_steps": 370, "total_steps": 16520, "loss": 0.1827, "lr": 1.1168280871670703e-05, "epoch": 0.44794188861985473, "percentage": 2.24, "elapsed_time": "0:00:58", "remaining_time": "0:42:43", "throughput": 2593.94, "total_tokens": 152352}
75
+ {"current_steps": 375, "total_steps": 16520, "loss": 0.2616, "lr": 1.1319612590799032e-05, "epoch": 0.4539951573849879, "percentage": 2.27, "elapsed_time": "0:00:59", "remaining_time": "0:42:45", "throughput": 2593.05, "total_tokens": 154496}
76
+ {"current_steps": 380, "total_steps": 16520, "loss": 0.2822, "lr": 1.1470944309927362e-05, "epoch": 0.4600484261501211, "percentage": 2.3, "elapsed_time": "0:01:00", "remaining_time": "0:42:42", "throughput": 2593.68, "total_tokens": 156480}
77
+ {"current_steps": 385, "total_steps": 16520, "loss": 0.3087, "lr": 1.1622276029055691e-05, "epoch": 0.4661016949152542, "percentage": 2.33, "elapsed_time": "0:01:01", "remaining_time": "0:42:41", "throughput": 2594.53, "total_tokens": 158560}
78
+ {"current_steps": 390, "total_steps": 16520, "loss": 0.2605, "lr": 1.1773607748184019e-05, "epoch": 0.4721549636803874, "percentage": 2.36, "elapsed_time": "0:01:01", "remaining_time": "0:42:41", "throughput": 2594.83, "total_tokens": 160704}
79
+ {"current_steps": 395, "total_steps": 16520, "loss": 0.2248, "lr": 1.192493946731235e-05, "epoch": 0.4782082324455206, "percentage": 2.39, "elapsed_time": "0:01:02", "remaining_time": "0:42:37", "throughput": 2596.21, "total_tokens": 162656}
80
+ {"current_steps": 400, "total_steps": 16520, "loss": 0.1414, "lr": 1.2076271186440678e-05, "epoch": 0.48426150121065376, "percentage": 2.42, "elapsed_time": "0:01:03", "remaining_time": "0:42:33", "throughput": 2595.67, "total_tokens": 164480}
81
+ {"current_steps": 405, "total_steps": 16520, "loss": 0.2633, "lr": 1.2227602905569007e-05, "epoch": 0.49031476997578693, "percentage": 2.45, "elapsed_time": "0:01:04", "remaining_time": "0:42:32", "throughput": 2595.89, "total_tokens": 166528}
82
+ {"current_steps": 410, "total_steps": 16520, "loss": 0.3061, "lr": 1.2378934624697338e-05, "epoch": 0.4963680387409201, "percentage": 2.48, "elapsed_time": "0:01:04", "remaining_time": "0:42:31", "throughput": 2595.22, "total_tokens": 168512}
83
+ {"current_steps": 415, "total_steps": 16520, "loss": 0.2267, "lr": 1.2530266343825667e-05, "epoch": 0.5024213075060533, "percentage": 2.51, "elapsed_time": "0:01:05", "remaining_time": "0:42:31", "throughput": 2595.53, "total_tokens": 170656}
84
+ {"current_steps": 420, "total_steps": 16520, "loss": 0.3836, "lr": 1.2681598062953994e-05, "epoch": 0.5084745762711864, "percentage": 2.54, "elapsed_time": "0:01:06", "remaining_time": "0:42:30", "throughput": 2595.72, "total_tokens": 172704}
85
+ {"current_steps": 425, "total_steps": 16520, "loss": 0.201, "lr": 1.2832929782082325e-05, "epoch": 0.5145278450363197, "percentage": 2.57, "elapsed_time": "0:01:07", "remaining_time": "0:42:27", "throughput": 2597.59, "total_tokens": 174752}
86
+ {"current_steps": 430, "total_steps": 16520, "loss": 0.1328, "lr": 1.2984261501210654e-05, "epoch": 0.5205811138014528, "percentage": 2.6, "elapsed_time": "0:01:07", "remaining_time": "0:42:24", "throughput": 2598.41, "total_tokens": 176672}
87
+ {"current_steps": 435, "total_steps": 16520, "loss": 0.1487, "lr": 1.3135593220338985e-05, "epoch": 0.5266343825665859, "percentage": 2.63, "elapsed_time": "0:01:08", "remaining_time": "0:42:20", "throughput": 2599.96, "total_tokens": 178624}
88
+ {"current_steps": 440, "total_steps": 16520, "loss": 0.1349, "lr": 1.3286924939467312e-05, "epoch": 0.5326876513317191, "percentage": 2.66, "elapsed_time": "0:01:09", "remaining_time": "0:42:19", "throughput": 2599.46, "total_tokens": 180608}
89
+ {"current_steps": 445, "total_steps": 16520, "loss": 0.2015, "lr": 1.3438256658595641e-05, "epoch": 0.5387409200968523, "percentage": 2.69, "elapsed_time": "0:01:10", "remaining_time": "0:42:19", "throughput": 2598.89, "total_tokens": 182688}
90
+ {"current_steps": 450, "total_steps": 16520, "loss": 0.2505, "lr": 1.3589588377723972e-05, "epoch": 0.5447941888619855, "percentage": 2.72, "elapsed_time": "0:01:11", "remaining_time": "0:42:18", "throughput": 2598.76, "total_tokens": 184704}
91
+ {"current_steps": 455, "total_steps": 16520, "loss": 0.1654, "lr": 1.37409200968523e-05, "epoch": 0.5508474576271186, "percentage": 2.75, "elapsed_time": "0:01:11", "remaining_time": "0:42:18", "throughput": 2600.84, "total_tokens": 187008}
92
+ {"current_steps": 460, "total_steps": 16520, "loss": 0.338, "lr": 1.3892251815980631e-05, "epoch": 0.5569007263922519, "percentage": 2.78, "elapsed_time": "0:01:12", "remaining_time": "0:42:18", "throughput": 2600.33, "total_tokens": 189088}
93
+ {"current_steps": 465, "total_steps": 16520, "loss": 0.2775, "lr": 1.4043583535108959e-05, "epoch": 0.562953995157385, "percentage": 2.81, "elapsed_time": "0:01:13", "remaining_time": "0:42:17", "throughput": 2601.57, "total_tokens": 191232}
94
+ {"current_steps": 470, "total_steps": 16520, "loss": 0.1171, "lr": 1.419491525423729e-05, "epoch": 0.5690072639225182, "percentage": 2.85, "elapsed_time": "0:01:14", "remaining_time": "0:42:18", "throughput": 2602.85, "total_tokens": 193472}
95
+ {"current_steps": 475, "total_steps": 16520, "loss": 0.2417, "lr": 1.4346246973365618e-05, "epoch": 0.5750605326876513, "percentage": 2.88, "elapsed_time": "0:01:15", "remaining_time": "0:42:17", "throughput": 2603.05, "total_tokens": 195520}
96
+ {"current_steps": 480, "total_steps": 16520, "loss": 0.2471, "lr": 1.4497578692493946e-05, "epoch": 0.5811138014527845, "percentage": 2.91, "elapsed_time": "0:01:15", "remaining_time": "0:42:14", "throughput": 2603.55, "total_tokens": 197504}
97
+ {"current_steps": 485, "total_steps": 16520, "loss": 0.2255, "lr": 1.4648910411622276e-05, "epoch": 0.5871670702179177, "percentage": 2.94, "elapsed_time": "0:01:16", "remaining_time": "0:42:12", "throughput": 2603.94, "total_tokens": 199488}
98
+ {"current_steps": 490, "total_steps": 16520, "loss": 0.2621, "lr": 1.4800242130750605e-05, "epoch": 0.5932203389830508, "percentage": 2.97, "elapsed_time": "0:01:17", "remaining_time": "0:42:10", "throughput": 2604.79, "total_tokens": 201504}
99
+ {"current_steps": 495, "total_steps": 16520, "loss": 0.2636, "lr": 1.4951573849878936e-05, "epoch": 0.5992736077481841, "percentage": 3.0, "elapsed_time": "0:01:18", "remaining_time": "0:42:08", "throughput": 2604.47, "total_tokens": 203424}
100
+ {"current_steps": 500, "total_steps": 16520, "loss": 0.2464, "lr": 1.5102905569007263e-05, "epoch": 0.6053268765133172, "percentage": 3.03, "elapsed_time": "0:01:18", "remaining_time": "0:42:09", "throughput": 2604.31, "total_tokens": 205632}
101
+ {"current_steps": 505, "total_steps": 16520, "loss": 0.2105, "lr": 1.5254237288135596e-05, "epoch": 0.6113801452784504, "percentage": 3.06, "elapsed_time": "0:01:19", "remaining_time": "0:42:11", "throughput": 2604.0, "total_tokens": 207840}
102
+ {"current_steps": 510, "total_steps": 16520, "loss": 0.186, "lr": 1.5405569007263923e-05, "epoch": 0.6174334140435835, "percentage": 3.09, "elapsed_time": "0:01:20", "remaining_time": "0:42:09", "throughput": 2603.96, "total_tokens": 209792}
103
+ {"current_steps": 515, "total_steps": 16520, "loss": 0.3136, "lr": 1.5556900726392254e-05, "epoch": 0.6234866828087167, "percentage": 3.12, "elapsed_time": "0:01:21", "remaining_time": "0:42:08", "throughput": 2604.15, "total_tokens": 211840}
104
+ {"current_steps": 520, "total_steps": 16520, "loss": 0.1874, "lr": 1.570823244552058e-05, "epoch": 0.6295399515738499, "percentage": 3.15, "elapsed_time": "0:01:22", "remaining_time": "0:42:07", "throughput": 2604.34, "total_tokens": 213888}
105
+ {"current_steps": 525, "total_steps": 16520, "loss": 0.225, "lr": 1.5859564164648912e-05, "epoch": 0.635593220338983, "percentage": 3.18, "elapsed_time": "0:01:22", "remaining_time": "0:42:06", "throughput": 2603.12, "total_tokens": 215904}
106
+ {"current_steps": 530, "total_steps": 16520, "loss": 0.2313, "lr": 1.6010895883777242e-05, "epoch": 0.6416464891041163, "percentage": 3.21, "elapsed_time": "0:01:23", "remaining_time": "0:42:05", "throughput": 2602.62, "total_tokens": 217888}
107
+ {"current_steps": 535, "total_steps": 16520, "loss": 0.2918, "lr": 1.616222760290557e-05, "epoch": 0.6476997578692494, "percentage": 3.24, "elapsed_time": "0:01:24", "remaining_time": "0:42:03", "throughput": 2603.74, "total_tokens": 219936}
108
+ {"current_steps": 540, "total_steps": 16520, "loss": 0.2479, "lr": 1.63135593220339e-05, "epoch": 0.6537530266343826, "percentage": 3.27, "elapsed_time": "0:01:25", "remaining_time": "0:42:02", "throughput": 2603.96, "total_tokens": 221984}
109
+ {"current_steps": 545, "total_steps": 16520, "loss": 0.2475, "lr": 1.6464891041162228e-05, "epoch": 0.6598062953995157, "percentage": 3.3, "elapsed_time": "0:01:25", "remaining_time": "0:42:00", "throughput": 2604.48, "total_tokens": 223968}
110
+ {"current_steps": 550, "total_steps": 16520, "loss": 0.228, "lr": 1.661622276029056e-05, "epoch": 0.6658595641646489, "percentage": 3.33, "elapsed_time": "0:01:26", "remaining_time": "0:41:58", "throughput": 2605.14, "total_tokens": 225984}
111
+ {"current_steps": 555, "total_steps": 16520, "loss": 0.2638, "lr": 1.6767554479418886e-05, "epoch": 0.6719128329297821, "percentage": 3.36, "elapsed_time": "0:01:27", "remaining_time": "0:41:55", "throughput": 2605.55, "total_tokens": 227872}
112
+ {"current_steps": 560, "total_steps": 16520, "loss": 0.209, "lr": 1.6918886198547216e-05, "epoch": 0.6779661016949152, "percentage": 3.39, "elapsed_time": "0:01:28", "remaining_time": "0:41:54", "throughput": 2606.34, "total_tokens": 229984}
113
+ {"current_steps": 565, "total_steps": 16520, "loss": 0.3089, "lr": 1.7070217917675547e-05, "epoch": 0.6840193704600485, "percentage": 3.42, "elapsed_time": "0:01:29", "remaining_time": "0:41:54", "throughput": 2607.02, "total_tokens": 232096}
114
+ {"current_steps": 570, "total_steps": 16520, "loss": 0.1835, "lr": 1.7221549636803874e-05, "epoch": 0.6900726392251816, "percentage": 3.45, "elapsed_time": "0:01:29", "remaining_time": "0:41:53", "throughput": 2607.04, "total_tokens": 234144}
115
+ {"current_steps": 575, "total_steps": 16520, "loss": 0.2042, "lr": 1.7372881355932205e-05, "epoch": 0.6961259079903148, "percentage": 3.48, "elapsed_time": "0:01:30", "remaining_time": "0:41:51", "throughput": 2607.38, "total_tokens": 236128}
116
+ {"current_steps": 580, "total_steps": 16520, "loss": 0.2091, "lr": 1.7524213075060532e-05, "epoch": 0.7021791767554479, "percentage": 3.51, "elapsed_time": "0:01:31", "remaining_time": "0:41:51", "throughput": 2606.53, "total_tokens": 238176}
117
+ {"current_steps": 585, "total_steps": 16520, "loss": 0.1935, "lr": 1.7675544794188863e-05, "epoch": 0.7082324455205811, "percentage": 3.54, "elapsed_time": "0:01:32", "remaining_time": "0:41:50", "throughput": 2607.53, "total_tokens": 240320}
118
+ {"current_steps": 590, "total_steps": 16520, "loss": 0.245, "lr": 1.7826876513317194e-05, "epoch": 0.7142857142857143, "percentage": 3.57, "elapsed_time": "0:01:32", "remaining_time": "0:41:50", "throughput": 2607.13, "total_tokens": 242400}
119
+ {"current_steps": 595, "total_steps": 16520, "loss": 0.2027, "lr": 1.797820823244552e-05, "epoch": 0.7203389830508474, "percentage": 3.6, "elapsed_time": "0:01:33", "remaining_time": "0:41:50", "throughput": 2606.32, "total_tokens": 244448}
120
+ {"current_steps": 600, "total_steps": 16520, "loss": 0.1068, "lr": 1.812953995157385e-05, "epoch": 0.7263922518159807, "percentage": 3.63, "elapsed_time": "0:01:34", "remaining_time": "0:41:50", "throughput": 2606.12, "total_tokens": 246560}
121
+ {"current_steps": 605, "total_steps": 16520, "loss": 0.1968, "lr": 1.828087167070218e-05, "epoch": 0.7324455205811138, "percentage": 3.66, "elapsed_time": "0:01:35", "remaining_time": "0:41:51", "throughput": 2605.72, "total_tokens": 248736}
122
+ {"current_steps": 610, "total_steps": 16520, "loss": 0.1501, "lr": 1.843220338983051e-05, "epoch": 0.738498789346247, "percentage": 3.69, "elapsed_time": "0:01:36", "remaining_time": "0:41:50", "throughput": 2605.34, "total_tokens": 250816}
123
+ {"current_steps": 615, "total_steps": 16520, "loss": 0.2392, "lr": 1.8583535108958837e-05, "epoch": 0.7445520581113801, "percentage": 3.72, "elapsed_time": "0:01:37", "remaining_time": "0:41:50", "throughput": 2605.17, "total_tokens": 252928}
124
+ {"current_steps": 620, "total_steps": 16520, "loss": 0.292, "lr": 1.8734866828087168e-05, "epoch": 0.7506053268765133, "percentage": 3.75, "elapsed_time": "0:01:37", "remaining_time": "0:41:49", "throughput": 2604.92, "total_tokens": 254944}
125
+ {"current_steps": 625, "total_steps": 16520, "loss": 0.18, "lr": 1.88861985472155e-05, "epoch": 0.7566585956416465, "percentage": 3.78, "elapsed_time": "0:01:38", "remaining_time": "0:41:48", "throughput": 2605.57, "total_tokens": 256960}
126
+ {"current_steps": 630, "total_steps": 16520, "loss": 0.1771, "lr": 1.9037530266343826e-05, "epoch": 0.7627118644067796, "percentage": 3.81, "elapsed_time": "0:01:39", "remaining_time": "0:41:46", "throughput": 2605.87, "total_tokens": 258944}
127
+ {"current_steps": 635, "total_steps": 16520, "loss": 0.1884, "lr": 1.9188861985472156e-05, "epoch": 0.7687651331719129, "percentage": 3.84, "elapsed_time": "0:01:40", "remaining_time": "0:41:44", "throughput": 2606.26, "total_tokens": 260928}
128
+ {"current_steps": 640, "total_steps": 16520, "loss": 0.2775, "lr": 1.9340193704600484e-05, "epoch": 0.774818401937046, "percentage": 3.87, "elapsed_time": "0:01:40", "remaining_time": "0:41:43", "throughput": 2606.93, "total_tokens": 263040}
129
+ {"current_steps": 645, "total_steps": 16520, "loss": 0.2366, "lr": 1.9491525423728814e-05, "epoch": 0.7808716707021792, "percentage": 3.9, "elapsed_time": "0:01:41", "remaining_time": "0:41:41", "throughput": 2608.09, "total_tokens": 265024}
130
+ {"current_steps": 650, "total_steps": 16520, "loss": 0.1396, "lr": 1.9642857142857145e-05, "epoch": 0.7869249394673123, "percentage": 3.93, "elapsed_time": "0:01:42", "remaining_time": "0:41:40", "throughput": 2607.2, "total_tokens": 266976}
131
+ {"current_steps": 655, "total_steps": 16520, "loss": 0.0892, "lr": 1.9794188861985476e-05, "epoch": 0.7929782082324455, "percentage": 3.96, "elapsed_time": "0:01:43", "remaining_time": "0:41:39", "throughput": 2607.82, "total_tokens": 269088}
132
+ {"current_steps": 660, "total_steps": 16520, "loss": 0.1326, "lr": 1.9945520581113803e-05, "epoch": 0.7990314769975787, "percentage": 4.0, "elapsed_time": "0:01:43", "remaining_time": "0:41:37", "throughput": 2608.25, "total_tokens": 271072}
133
+ {"current_steps": 665, "total_steps": 16520, "loss": 0.1605, "lr": 2.009685230024213e-05, "epoch": 0.8050847457627118, "percentage": 4.03, "elapsed_time": "0:01:44", "remaining_time": "0:41:36", "throughput": 2608.65, "total_tokens": 273152}
134
+ {"current_steps": 670, "total_steps": 16520, "loss": 0.2463, "lr": 2.024818401937046e-05, "epoch": 0.8111380145278451, "percentage": 4.06, "elapsed_time": "0:01:45", "remaining_time": "0:41:36", "throughput": 2608.38, "total_tokens": 275264}
135
+ {"current_steps": 675, "total_steps": 16520, "loss": 0.2235, "lr": 2.0399515738498788e-05, "epoch": 0.8171912832929782, "percentage": 4.09, "elapsed_time": "0:01:46", "remaining_time": "0:41:36", "throughput": 2607.95, "total_tokens": 277344}
136
+ {"current_steps": 680, "total_steps": 16520, "loss": 0.2217, "lr": 2.055084745762712e-05, "epoch": 0.8232445520581114, "percentage": 4.12, "elapsed_time": "0:01:47", "remaining_time": "0:41:35", "throughput": 2607.87, "total_tokens": 279360}
137
+ {"current_steps": 685, "total_steps": 16520, "loss": 0.1806, "lr": 2.070217917675545e-05, "epoch": 0.8292978208232445, "percentage": 4.15, "elapsed_time": "0:01:47", "remaining_time": "0:41:33", "throughput": 2609.21, "total_tokens": 281472}
138
+ {"current_steps": 690, "total_steps": 16520, "loss": 0.2098, "lr": 2.085351089588378e-05, "epoch": 0.8353510895883777, "percentage": 4.18, "elapsed_time": "0:01:48", "remaining_time": "0:41:34", "throughput": 2608.16, "total_tokens": 283552}
139
+ {"current_steps": 695, "total_steps": 16520, "loss": 0.1952, "lr": 2.1004842615012108e-05, "epoch": 0.8414043583535109, "percentage": 4.21, "elapsed_time": "0:01:49", "remaining_time": "0:41:32", "throughput": 2608.4, "total_tokens": 285536}
140
+ {"current_steps": 700, "total_steps": 16520, "loss": 0.1662, "lr": 2.1156174334140435e-05, "epoch": 0.847457627118644, "percentage": 4.24, "elapsed_time": "0:01:50", "remaining_time": "0:41:30", "throughput": 2608.22, "total_tokens": 287456}
141
+ {"current_steps": 705, "total_steps": 16520, "loss": 0.2437, "lr": 2.1307506053268766e-05, "epoch": 0.8535108958837773, "percentage": 4.27, "elapsed_time": "0:01:50", "remaining_time": "0:41:28", "throughput": 2608.72, "total_tokens": 289376}
142
+ {"current_steps": 710, "total_steps": 16520, "loss": 0.1688, "lr": 2.1458837772397093e-05, "epoch": 0.8595641646489104, "percentage": 4.3, "elapsed_time": "0:01:51", "remaining_time": "0:41:27", "throughput": 2608.59, "total_tokens": 291392}
143
+ {"current_steps": 715, "total_steps": 16520, "loss": 0.3024, "lr": 2.1610169491525427e-05, "epoch": 0.8656174334140436, "percentage": 4.33, "elapsed_time": "0:01:52", "remaining_time": "0:41:26", "throughput": 2609.39, "total_tokens": 293536}
144
+ {"current_steps": 720, "total_steps": 16520, "loss": 0.1876, "lr": 2.1761501210653754e-05, "epoch": 0.8716707021791767, "percentage": 4.36, "elapsed_time": "0:01:53", "remaining_time": "0:41:25", "throughput": 2609.28, "total_tokens": 295552}
145
+ {"current_steps": 725, "total_steps": 16520, "loss": 0.1068, "lr": 2.1912832929782085e-05, "epoch": 0.8777239709443099, "percentage": 4.39, "elapsed_time": "0:01:54", "remaining_time": "0:41:23", "throughput": 2609.35, "total_tokens": 297504}
146
+ {"current_steps": 730, "total_steps": 16520, "loss": 0.1672, "lr": 2.2064164648910412e-05, "epoch": 0.8837772397094431, "percentage": 4.42, "elapsed_time": "0:01:54", "remaining_time": "0:41:23", "throughput": 2609.2, "total_tokens": 299616}
147
+ {"current_steps": 735, "total_steps": 16520, "loss": 0.1825, "lr": 2.221549636803874e-05, "epoch": 0.8898305084745762, "percentage": 4.45, "elapsed_time": "0:01:55", "remaining_time": "0:41:22", "throughput": 2609.22, "total_tokens": 301664}
148
+ {"current_steps": 740, "total_steps": 16520, "loss": 0.2193, "lr": 2.236682808716707e-05, "epoch": 0.8958837772397095, "percentage": 4.48, "elapsed_time": "0:01:56", "remaining_time": "0:41:21", "throughput": 2608.86, "total_tokens": 303648}
149
+ {"current_steps": 745, "total_steps": 16520, "loss": 0.1539, "lr": 2.25181598062954e-05, "epoch": 0.9019370460048426, "percentage": 4.51, "elapsed_time": "0:01:57", "remaining_time": "0:41:22", "throughput": 2608.53, "total_tokens": 305824}
150
+ {"current_steps": 750, "total_steps": 16520, "loss": 0.1869, "lr": 2.266949152542373e-05, "epoch": 0.9079903147699758, "percentage": 4.54, "elapsed_time": "0:01:57", "remaining_time": "0:41:20", "throughput": 2608.9, "total_tokens": 307808}
151
+ {"current_steps": 755, "total_steps": 16520, "loss": 0.1989, "lr": 2.282082324455206e-05, "epoch": 0.914043583535109, "percentage": 4.57, "elapsed_time": "0:01:58", "remaining_time": "0:41:20", "throughput": 2608.58, "total_tokens": 309888}
152
+ {"current_steps": 760, "total_steps": 16520, "loss": 0.211, "lr": 2.297215496368039e-05, "epoch": 0.9200968523002422, "percentage": 4.6, "elapsed_time": "0:01:59", "remaining_time": "0:41:21", "throughput": 2608.68, "total_tokens": 312128}
153
+ {"current_steps": 765, "total_steps": 16520, "loss": 0.2296, "lr": 2.3123486682808717e-05, "epoch": 0.9261501210653753, "percentage": 4.63, "elapsed_time": "0:02:00", "remaining_time": "0:41:19", "throughput": 2609.52, "total_tokens": 314208}
154
+ {"current_steps": 770, "total_steps": 16520, "loss": 0.1516, "lr": 2.3274818401937044e-05, "epoch": 0.9322033898305084, "percentage": 4.66, "elapsed_time": "0:02:01", "remaining_time": "0:41:18", "throughput": 2609.64, "total_tokens": 316256}
155
+ {"current_steps": 775, "total_steps": 16520, "loss": 0.2006, "lr": 2.342615012106538e-05, "epoch": 0.9382566585956417, "percentage": 4.69, "elapsed_time": "0:02:02", "remaining_time": "0:41:18", "throughput": 2609.05, "total_tokens": 318304}
156
+ {"current_steps": 780, "total_steps": 16520, "loss": 0.1673, "lr": 2.3577481840193706e-05, "epoch": 0.9443099273607748, "percentage": 4.72, "elapsed_time": "0:02:02", "remaining_time": "0:41:18", "throughput": 2609.03, "total_tokens": 320480}
157
+ {"current_steps": 785, "total_steps": 16520, "loss": 0.2101, "lr": 2.3728813559322036e-05, "epoch": 0.950363196125908, "percentage": 4.75, "elapsed_time": "0:02:03", "remaining_time": "0:41:17", "throughput": 2609.11, "total_tokens": 322528}
158
+ {"current_steps": 790, "total_steps": 16520, "loss": 0.1828, "lr": 2.3880145278450364e-05, "epoch": 0.9564164648910412, "percentage": 4.78, "elapsed_time": "0:02:04", "remaining_time": "0:41:16", "throughput": 2609.41, "total_tokens": 324608}
159
+ {"current_steps": 795, "total_steps": 16520, "loss": 0.1945, "lr": 2.4031476997578694e-05, "epoch": 0.9624697336561744, "percentage": 4.81, "elapsed_time": "0:02:05", "remaining_time": "0:41:15", "throughput": 2609.31, "total_tokens": 326624}
160
+ {"current_steps": 800, "total_steps": 16520, "loss": 0.1425, "lr": 2.418280871670702e-05, "epoch": 0.9685230024213075, "percentage": 4.84, "elapsed_time": "0:02:05", "remaining_time": "0:41:15", "throughput": 2609.62, "total_tokens": 328704}
161
+ {"current_steps": 805, "total_steps": 16520, "loss": 0.2567, "lr": 2.4334140435835352e-05, "epoch": 0.9745762711864406, "percentage": 4.87, "elapsed_time": "0:02:06", "remaining_time": "0:41:13", "throughput": 2610.14, "total_tokens": 330720}
162
+ {"current_steps": 810, "total_steps": 16520, "loss": 0.1975, "lr": 2.4485472154963683e-05, "epoch": 0.9806295399515739, "percentage": 4.9, "elapsed_time": "0:02:07", "remaining_time": "0:41:12", "throughput": 2609.99, "total_tokens": 332736}
163
+ {"current_steps": 815, "total_steps": 16520, "loss": 0.1438, "lr": 2.463680387409201e-05, "epoch": 0.986682808716707, "percentage": 4.93, "elapsed_time": "0:02:08", "remaining_time": "0:41:12", "throughput": 2609.44, "total_tokens": 334784}
164
+ {"current_steps": 820, "total_steps": 16520, "loss": 0.2619, "lr": 2.478813559322034e-05, "epoch": 0.9927360774818402, "percentage": 4.96, "elapsed_time": "0:02:09", "remaining_time": "0:41:11", "throughput": 2609.54, "total_tokens": 336832}
165
+ {"current_steps": 825, "total_steps": 16520, "loss": 0.2116, "lr": 2.4939467312348668e-05, "epoch": 0.9987893462469734, "percentage": 4.99, "elapsed_time": "0:02:09", "remaining_time": "0:41:09", "throughput": 2610.41, "total_tokens": 338784}
166
+ {"current_steps": 826, "total_steps": 16520, "eval_loss": 0.18920761346817017, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:02:14", "remaining_time": "0:42:39", "throughput": 2515.76, "total_tokens": 338864}
167
+ {"current_steps": 830, "total_steps": 16520, "loss": 0.202, "lr": 2.5090799031476996e-05, "epoch": 1.0048426150121066, "percentage": 5.02, "elapsed_time": "0:02:16", "remaining_time": "0:42:54", "throughput": 2500.58, "total_tokens": 340592}
168
+ {"current_steps": 835, "total_steps": 16520, "loss": 0.1596, "lr": 2.524213075060533e-05, "epoch": 1.0108958837772397, "percentage": 5.05, "elapsed_time": "0:02:17", "remaining_time": "0:42:54", "throughput": 2500.08, "total_tokens": 342704}
169
+ {"current_steps": 840, "total_steps": 16520, "loss": 0.233, "lr": 2.539346246973366e-05, "epoch": 1.0169491525423728, "percentage": 5.08, "elapsed_time": "0:02:17", "remaining_time": "0:42:54", "throughput": 2498.25, "total_tokens": 344592}
170
+ {"current_steps": 845, "total_steps": 16520, "loss": 0.1698, "lr": 2.5544794188861988e-05, "epoch": 1.023002421307506, "percentage": 5.12, "elapsed_time": "0:02:18", "remaining_time": "0:42:54", "throughput": 2498.58, "total_tokens": 346800}
171
+ {"current_steps": 850, "total_steps": 16520, "loss": 0.16, "lr": 2.5696125907990315e-05, "epoch": 1.0290556900726393, "percentage": 5.15, "elapsed_time": "0:02:19", "remaining_time": "0:42:56", "throughput": 2494.5, "total_tokens": 348688}
172
+ {"current_steps": 855, "total_steps": 16520, "loss": 0.1787, "lr": 2.5847457627118642e-05, "epoch": 1.0351089588377724, "percentage": 5.18, "elapsed_time": "0:02:20", "remaining_time": "0:42:54", "throughput": 2495.3, "total_tokens": 350672}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827d8705f4ebf6793c87e036a584de42c20c87176b3e207b7e24a18ad420ec16
3
+ size 6289