rbelanec commited on
Commit
e95604c
·
verified ·
1 Parent(s): 23d81e9

Training in progress, step 1116

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
4
+ "exclude_modules": null,
5
+ "inference_mode": true,
6
+ "modules_to_save": null,
7
+ "peft_type": "LN_TUNING",
8
+ "revision": null,
9
+ "target_modules": [
10
+ "norm",
11
+ "input_layernorm",
12
+ "post_attention_layernorm"
13
+ ],
14
+ "task_type": "CAUSAL_LM"
15
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd52d6e57ed7f167342bd66e21dd0ad281618b2d10b6128b6a3f9d2575614130
3
+ size 541712
chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ 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|>
4
+
5
+ ' }}{% endif %}
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 +1,2076 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
2065
+ "eos_token": "<|eot_id|>",
2066
+ "extra_special_tokens": {},
2067
+ "model_input_names": [
2068
+ "input_ids",
2069
+ "attention_mask"
2070
+ ],
2071
+ "model_max_length": 1000000000000000019884624838656,
2072
+ "pad_token": "<|eot_id|>",
2073
+ "padding_side": "right",
2074
+ "split_special_tokens": false,
2075
+ "tokenizer_class": "PreTrainedTokenizerFast"
2076
+ }
train.yaml ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ seed: 42
2
+
3
+ ### model
4
+ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
5
+ trust_remote_code: true
6
+ flash_attn: auto
7
+ use_cache: false
8
+
9
+ ### method
10
+ stage: sft
11
+ do_train: true
12
+ finetuning_type: lntuning
13
+ task_type: CAUSAL_LM
14
+
15
+ ### dataset
16
+ dataset: openbookqa
17
+ template: llama3
18
+ cutoff_len: 2048
19
+ overwrite_cache: true
20
+ preprocessing_num_workers: 8
21
+ dataloader_num_workers: 2
22
+ packing: false
23
+
24
+ ### output
25
+ output_dir: saves_multiple/lntuning/llama-3-8b-instruct/train_openbookqa_42_1760623657
26
+ logging_steps: 5
27
+ save_steps: 0.05
28
+ overwrite_output_dir: true
29
+ save_only_model: false
30
+ plot_loss: true
31
+ include_num_input_tokens_seen: true
32
+ push_to_hub: true
33
+ push_to_hub_organization: rbelanec
34
+ load_best_model_at_end: true
35
+ save_total_limit: 1
36
+
37
+ ### train
38
+ per_device_train_batch_size: 4
39
+ learning_rate: 5.0e-5
40
+ num_train_epochs: 20
41
+ weight_decay: 1.0e-5
42
+ lr_scheduler_type: cosine
43
+ bf16: true
44
+ ddp_timeout: 180000000
45
+ resume_from_checkpoint: null
46
+ warmup_ratio: 0.1
47
+ optim: adamw_torch
48
+ report_to:
49
+ - wandb
50
+ run_name: lntuning_llama-3-8b-instruct_train_openbookqa_42_1760623657
51
+
52
+ ### eval
53
+ per_device_eval_batch_size: 4
54
+ eval_strategy: steps
55
+ eval_steps: 0.05
56
+ val_size: 0.1
trainer_log.jsonl ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 22320, "loss": 0.0972, "lr": 8.960573476702509e-08, "epoch": 0.004480286738351254, "percentage": 0.02, "elapsed_time": "0:00:01", "remaining_time": "1:56:42", "throughput": 1121.65, "total_tokens": 1760}
2
+ {"current_steps": 10, "total_steps": 22320, "loss": 0.1497, "lr": 2.0161290322580645e-07, "epoch": 0.008960573476702509, "percentage": 0.04, "elapsed_time": "0:00:02", "remaining_time": "1:34:26", "throughput": 1474.0, "total_tokens": 3744}
3
+ {"current_steps": 15, "total_steps": 22320, "loss": 0.5413, "lr": 3.136200716845878e-07, "epoch": 0.013440860215053764, "percentage": 0.07, "elapsed_time": "0:00:03", "remaining_time": "1:27:02", "throughput": 1585.24, "total_tokens": 5568}
4
+ {"current_steps": 20, "total_steps": 22320, "loss": 0.4864, "lr": 4.2562724014336925e-07, "epoch": 0.017921146953405017, "percentage": 0.09, "elapsed_time": "0:00:04", "remaining_time": "1:22:30", "throughput": 1643.22, "total_tokens": 7296}
5
+ {"current_steps": 25, "total_steps": 22320, "loss": 0.8454, "lr": 5.376344086021506e-07, "epoch": 0.022401433691756272, "percentage": 0.11, "elapsed_time": "0:00:05", "remaining_time": "1:16:29", "throughput": 1803.38, "total_tokens": 9280}
6
+ {"current_steps": 30, "total_steps": 22320, "loss": 0.5996, "lr": 6.496415770609319e-07, "epoch": 0.026881720430107527, "percentage": 0.13, "elapsed_time": "0:00:05", "remaining_time": "1:12:09", "throughput": 1916.52, "total_tokens": 11168}
7
+ {"current_steps": 35, "total_steps": 22320, "loss": 0.6479, "lr": 7.616487455197133e-07, "epoch": 0.03136200716845878, "percentage": 0.16, "elapsed_time": "0:00:06", "remaining_time": "1:08:42", "throughput": 2001.89, "total_tokens": 12960}
8
+ {"current_steps": 40, "total_steps": 22320, "loss": 0.192, "lr": 8.736559139784946e-07, "epoch": 0.035842293906810034, "percentage": 0.18, "elapsed_time": "0:00:07", "remaining_time": "1:06:06", "throughput": 2076.04, "total_tokens": 14784}
9
+ {"current_steps": 45, "total_steps": 22320, "loss": 0.3537, "lr": 9.85663082437276e-07, "epoch": 0.04032258064516129, "percentage": 0.2, "elapsed_time": "0:00:07", "remaining_time": "1:04:39", "throughput": 2135.6, "total_tokens": 16736}
10
+ {"current_steps": 50, "total_steps": 22320, "loss": 0.3496, "lr": 1.0976702508960573e-06, "epoch": 0.044802867383512544, "percentage": 0.22, "elapsed_time": "0:00:08", "remaining_time": "1:03:46", "throughput": 2186.48, "total_tokens": 18784}
11
+ {"current_steps": 55, "total_steps": 22320, "loss": 0.5974, "lr": 1.2096774193548388e-06, "epoch": 0.0492831541218638, "percentage": 0.25, "elapsed_time": "0:00:09", "remaining_time": "1:02:48", "throughput": 2227.75, "total_tokens": 20736}
12
+ {"current_steps": 60, "total_steps": 22320, "loss": 1.1371, "lr": 1.3216845878136201e-06, "epoch": 0.053763440860215055, "percentage": 0.27, "elapsed_time": "0:00:09", "remaining_time": "1:01:33", "throughput": 2263.09, "total_tokens": 22528}
13
+ {"current_steps": 65, "total_steps": 22320, "loss": 0.8351, "lr": 1.4336917562724014e-06, "epoch": 0.05824372759856631, "percentage": 0.29, "elapsed_time": "0:00:10", "remaining_time": "1:00:41", "throughput": 2295.5, "total_tokens": 24416}
14
+ {"current_steps": 70, "total_steps": 22320, "loss": 0.1825, "lr": 1.545698924731183e-06, "epoch": 0.06272401433691756, "percentage": 0.31, "elapsed_time": "0:00:11", "remaining_time": "1:00:18", "throughput": 2318.93, "total_tokens": 26400}
15
+ {"current_steps": 75, "total_steps": 22320, "loss": 0.4391, "lr": 1.6577060931899643e-06, "epoch": 0.06720430107526881, "percentage": 0.34, "elapsed_time": "0:00:12", "remaining_time": "0:59:28", "throughput": 2343.52, "total_tokens": 28192}
16
+ {"current_steps": 80, "total_steps": 22320, "loss": 0.2905, "lr": 1.7697132616487456e-06, "epoch": 0.07168458781362007, "percentage": 0.36, "elapsed_time": "0:00:12", "remaining_time": "0:59:19", "throughput": 2369.16, "total_tokens": 30336}
17
+ {"current_steps": 85, "total_steps": 22320, "loss": 0.2991, "lr": 1.881720430107527e-06, "epoch": 0.07616487455197132, "percentage": 0.38, "elapsed_time": "0:00:13", "remaining_time": "0:58:47", "throughput": 2384.85, "total_tokens": 32160}
18
+ {"current_steps": 90, "total_steps": 22320, "loss": 0.6053, "lr": 1.9937275985663085e-06, "epoch": 0.08064516129032258, "percentage": 0.4, "elapsed_time": "0:00:14", "remaining_time": "0:58:20", "throughput": 2411.39, "total_tokens": 34176}
19
+ {"current_steps": 95, "total_steps": 22320, "loss": 0.397, "lr": 2.10573476702509e-06, "epoch": 0.08512544802867383, "percentage": 0.43, "elapsed_time": "0:00:14", "remaining_time": "0:57:55", "throughput": 2425.41, "total_tokens": 36032}
20
+ {"current_steps": 100, "total_steps": 22320, "loss": 0.6181, "lr": 2.217741935483871e-06, "epoch": 0.08960573476702509, "percentage": 0.45, "elapsed_time": "0:00:15", "remaining_time": "0:57:43", "throughput": 2443.19, "total_tokens": 38080}
21
+ {"current_steps": 105, "total_steps": 22320, "loss": 0.6656, "lr": 2.3297491039426526e-06, "epoch": 0.09408602150537634, "percentage": 0.47, "elapsed_time": "0:00:16", "remaining_time": "0:57:13", "throughput": 2456.69, "total_tokens": 39872}
22
+ {"current_steps": 110, "total_steps": 22320, "loss": 0.1816, "lr": 2.441756272401434e-06, "epoch": 0.0985663082437276, "percentage": 0.49, "elapsed_time": "0:00:17", "remaining_time": "0:57:15", "throughput": 2465.72, "total_tokens": 41952}
23
+ {"current_steps": 115, "total_steps": 22320, "loss": 0.0985, "lr": 2.5537634408602153e-06, "epoch": 0.10304659498207885, "percentage": 0.52, "elapsed_time": "0:00:17", "remaining_time": "0:56:56", "throughput": 2475.74, "total_tokens": 43808}
24
+ {"current_steps": 120, "total_steps": 22320, "loss": 0.5658, "lr": 2.6657706093189964e-06, "epoch": 0.10752688172043011, "percentage": 0.54, "elapsed_time": "0:00:18", "remaining_time": "0:56:39", "throughput": 2485.08, "total_tokens": 45664}
25
+ {"current_steps": 125, "total_steps": 22320, "loss": 1.2658, "lr": 2.777777777777778e-06, "epoch": 0.11200716845878136, "percentage": 0.56, "elapsed_time": "0:00:19", "remaining_time": "0:56:23", "throughput": 2495.4, "total_tokens": 47552}
26
+ {"current_steps": 130, "total_steps": 22320, "loss": 0.8597, "lr": 2.889784946236559e-06, "epoch": 0.11648745519713262, "percentage": 0.58, "elapsed_time": "0:00:19", "remaining_time": "0:56:15", "throughput": 2504.97, "total_tokens": 49536}
27
+ {"current_steps": 135, "total_steps": 22320, "loss": 0.3641, "lr": 3.0017921146953406e-06, "epoch": 0.12096774193548387, "percentage": 0.6, "elapsed_time": "0:00:20", "remaining_time": "0:56:01", "throughput": 2510.98, "total_tokens": 51360}
28
+ {"current_steps": 140, "total_steps": 22320, "loss": 0.4041, "lr": 3.113799283154122e-06, "epoch": 0.12544802867383512, "percentage": 0.63, "elapsed_time": "0:00:21", "remaining_time": "0:55:59", "throughput": 2516.97, "total_tokens": 53376}
29
+ {"current_steps": 145, "total_steps": 22320, "loss": 0.6046, "lr": 3.225806451612903e-06, "epoch": 0.12992831541218638, "percentage": 0.65, "elapsed_time": "0:00:21", "remaining_time": "0:56:02", "throughput": 2521.86, "total_tokens": 55456}
30
+ {"current_steps": 150, "total_steps": 22320, "loss": 1.2544, "lr": 3.337813620071685e-06, "epoch": 0.13440860215053763, "percentage": 0.67, "elapsed_time": "0:00:22", "remaining_time": "0:55:44", "throughput": 2530.94, "total_tokens": 57280}
31
+ {"current_steps": 155, "total_steps": 22320, "loss": 0.5747, "lr": 3.4498207885304663e-06, "epoch": 0.1388888888888889, "percentage": 0.69, "elapsed_time": "0:00:23", "remaining_time": "0:55:42", "throughput": 2538.49, "total_tokens": 59328}
32
+ {"current_steps": 160, "total_steps": 22320, "loss": 0.121, "lr": 3.5618279569892478e-06, "epoch": 0.14336917562724014, "percentage": 0.72, "elapsed_time": "0:00:24", "remaining_time": "0:55:30", "throughput": 2544.0, "total_tokens": 61184}
33
+ {"current_steps": 165, "total_steps": 22320, "loss": 0.0765, "lr": 3.673835125448029e-06, "epoch": 0.1478494623655914, "percentage": 0.74, "elapsed_time": "0:00:24", "remaining_time": "0:55:28", "throughput": 2550.92, "total_tokens": 63232}
34
+ {"current_steps": 170, "total_steps": 22320, "loss": 0.077, "lr": 3.7858422939068104e-06, "epoch": 0.15232974910394265, "percentage": 0.76, "elapsed_time": "0:00:25", "remaining_time": "0:55:21", "throughput": 2560.48, "total_tokens": 65280}
35
+ {"current_steps": 175, "total_steps": 22320, "loss": 0.4861, "lr": 3.8978494623655915e-06, "epoch": 0.15681003584229392, "percentage": 0.78, "elapsed_time": "0:00:26", "remaining_time": "0:55:15", "throughput": 2568.42, "total_tokens": 67296}
36
+ {"current_steps": 180, "total_steps": 22320, "loss": 0.7762, "lr": 4.009856630824372e-06, "epoch": 0.16129032258064516, "percentage": 0.81, "elapsed_time": "0:00:26", "remaining_time": "0:55:02", "throughput": 2575.7, "total_tokens": 69152}
37
+ {"current_steps": 185, "total_steps": 22320, "loss": 0.3872, "lr": 4.121863799283155e-06, "epoch": 0.16577060931899643, "percentage": 0.83, "elapsed_time": "0:00:27", "remaining_time": "0:54:53", "throughput": 2577.57, "total_tokens": 70944}
38
+ {"current_steps": 190, "total_steps": 22320, "loss": 0.7982, "lr": 4.233870967741935e-06, "epoch": 0.17025089605734767, "percentage": 0.85, "elapsed_time": "0:00:28", "remaining_time": "0:54:49", "throughput": 2580.29, "total_tokens": 72864}
39
+ {"current_steps": 195, "total_steps": 22320, "loss": 0.4576, "lr": 4.345878136200717e-06, "epoch": 0.17473118279569894, "percentage": 0.87, "elapsed_time": "0:00:28", "remaining_time": "0:54:48", "throughput": 2586.89, "total_tokens": 74976}
40
+ {"current_steps": 200, "total_steps": 22320, "loss": 0.706, "lr": 4.457885304659498e-06, "epoch": 0.17921146953405018, "percentage": 0.9, "elapsed_time": "0:00:29", "remaining_time": "0:54:52", "throughput": 2589.4, "total_tokens": 77088}
41
+ {"current_steps": 205, "total_steps": 22320, "loss": 0.613, "lr": 4.56989247311828e-06, "epoch": 0.18369175627240145, "percentage": 0.92, "elapsed_time": "0:00:30", "remaining_time": "0:54:48", "throughput": 2591.61, "total_tokens": 79008}
42
+ {"current_steps": 210, "total_steps": 22320, "loss": 1.199, "lr": 4.6818996415770606e-06, "epoch": 0.1881720430107527, "percentage": 0.94, "elapsed_time": "0:00:31", "remaining_time": "0:54:45", "throughput": 2595.64, "total_tokens": 80992}
43
+ {"current_steps": 215, "total_steps": 22320, "loss": 0.4297, "lr": 4.793906810035843e-06, "epoch": 0.19265232974910393, "percentage": 0.96, "elapsed_time": "0:00:31", "remaining_time": "0:54:42", "throughput": 2598.82, "total_tokens": 82976}
44
+ {"current_steps": 220, "total_steps": 22320, "loss": 0.739, "lr": 4.905913978494624e-06, "epoch": 0.1971326164874552, "percentage": 0.99, "elapsed_time": "0:00:32", "remaining_time": "0:54:31", "throughput": 2600.66, "total_tokens": 84704}
45
+ {"current_steps": 225, "total_steps": 22320, "loss": 0.3477, "lr": 5.017921146953405e-06, "epoch": 0.20161290322580644, "percentage": 1.01, "elapsed_time": "0:00:33", "remaining_time": "0:54:21", "throughput": 2605.85, "total_tokens": 86560}
46
+ {"current_steps": 230, "total_steps": 22320, "loss": 0.3037, "lr": 5.129928315412187e-06, "epoch": 0.2060931899641577, "percentage": 1.03, "elapsed_time": "0:00:33", "remaining_time": "0:54:12", "throughput": 2610.23, "total_tokens": 88384}
47
+ {"current_steps": 235, "total_steps": 22320, "loss": 0.322, "lr": 5.241935483870968e-06, "epoch": 0.21057347670250895, "percentage": 1.05, "elapsed_time": "0:00:34", "remaining_time": "0:54:09", "throughput": 2611.98, "total_tokens": 90304}
48
+ {"current_steps": 240, "total_steps": 22320, "loss": 1.1322, "lr": 5.353942652329749e-06, "epoch": 0.21505376344086022, "percentage": 1.08, "elapsed_time": "0:00:35", "remaining_time": "0:54:06", "throughput": 2615.27, "total_tokens": 92288}
49
+ {"current_steps": 245, "total_steps": 22320, "loss": 0.5944, "lr": 5.465949820788531e-06, "epoch": 0.21953405017921146, "percentage": 1.1, "elapsed_time": "0:00:35", "remaining_time": "0:54:00", "throughput": 2616.97, "total_tokens": 94112}
50
+ {"current_steps": 250, "total_steps": 22320, "loss": 0.4822, "lr": 5.577956989247312e-06, "epoch": 0.22401433691756273, "percentage": 1.12, "elapsed_time": "0:00:36", "remaining_time": "0:53:54", "throughput": 2618.37, "total_tokens": 95936}
51
+ {"current_steps": 255, "total_steps": 22320, "loss": 0.3735, "lr": 5.6899641577060935e-06, "epoch": 0.22849462365591397, "percentage": 1.14, "elapsed_time": "0:00:37", "remaining_time": "0:53:45", "throughput": 2621.33, "total_tokens": 97728}
52
+ {"current_steps": 260, "total_steps": 22320, "loss": 0.2575, "lr": 5.801971326164875e-06, "epoch": 0.23297491039426524, "percentage": 1.16, "elapsed_time": "0:00:37", "remaining_time": "0:53:40", "throughput": 2623.33, "total_tokens": 99584}
53
+ {"current_steps": 265, "total_steps": 22320, "loss": 1.0801, "lr": 5.9139784946236566e-06, "epoch": 0.23745519713261648, "percentage": 1.19, "elapsed_time": "0:00:38", "remaining_time": "0:53:42", "throughput": 2626.7, "total_tokens": 101696}
54
+ {"current_steps": 270, "total_steps": 22320, "loss": 0.5527, "lr": 6.025985663082437e-06, "epoch": 0.24193548387096775, "percentage": 1.21, "elapsed_time": "0:00:39", "remaining_time": "0:53:37", "throughput": 2632.05, "total_tokens": 103712}
55
+ {"current_steps": 275, "total_steps": 22320, "loss": 0.1222, "lr": 6.13799283154122e-06, "epoch": 0.246415770609319, "percentage": 1.23, "elapsed_time": "0:00:40", "remaining_time": "0:53:39", "throughput": 2633.68, "total_tokens": 105760}
56
+ {"current_steps": 280, "total_steps": 22320, "loss": 0.6007, "lr": 6.25e-06, "epoch": 0.25089605734767023, "percentage": 1.25, "elapsed_time": "0:00:40", "remaining_time": "0:53:31", "throughput": 2636.79, "total_tokens": 107584}
57
+ {"current_steps": 285, "total_steps": 22320, "loss": 0.3354, "lr": 6.362007168458782e-06, "epoch": 0.2553763440860215, "percentage": 1.28, "elapsed_time": "0:00:41", "remaining_time": "0:53:30", "throughput": 2639.52, "total_tokens": 109600}
58
+ {"current_steps": 290, "total_steps": 22320, "loss": 0.8933, "lr": 6.4740143369175625e-06, "epoch": 0.25985663082437277, "percentage": 1.3, "elapsed_time": "0:00:42", "remaining_time": "0:53:26", "throughput": 2643.17, "total_tokens": 111552}
59
+ {"current_steps": 295, "total_steps": 22320, "loss": 0.4712, "lr": 6.586021505376344e-06, "epoch": 0.26433691756272404, "percentage": 1.32, "elapsed_time": "0:00:42", "remaining_time": "0:53:29", "throughput": 2643.38, "total_tokens": 113632}
60
+ {"current_steps": 300, "total_steps": 22320, "loss": 0.3626, "lr": 6.698028673835126e-06, "epoch": 0.26881720430107525, "percentage": 1.34, "elapsed_time": "0:00:43", "remaining_time": "0:53:27", "throughput": 2646.3, "total_tokens": 115648}
61
+ {"current_steps": 305, "total_steps": 22320, "loss": 0.3794, "lr": 6.810035842293908e-06, "epoch": 0.2732974910394265, "percentage": 1.37, "elapsed_time": "0:00:44", "remaining_time": "0:53:20", "throughput": 2648.97, "total_tokens": 117472}
62
+ {"current_steps": 310, "total_steps": 22320, "loss": 0.3793, "lr": 6.922043010752688e-06, "epoch": 0.2777777777777778, "percentage": 1.39, "elapsed_time": "0:00:45", "remaining_time": "0:53:16", "throughput": 2649.42, "total_tokens": 119296}
63
+ {"current_steps": 315, "total_steps": 22320, "loss": 0.2559, "lr": 7.034050179211469e-06, "epoch": 0.28225806451612906, "percentage": 1.41, "elapsed_time": "0:00:45", "remaining_time": "0:53:12", "throughput": 2649.46, "total_tokens": 121088}
64
+ {"current_steps": 320, "total_steps": 22320, "loss": 0.2121, "lr": 7.146057347670252e-06, "epoch": 0.2867383512544803, "percentage": 1.43, "elapsed_time": "0:00:46", "remaining_time": "0:53:11", "throughput": 2649.49, "total_tokens": 122976}
65
+ {"current_steps": 325, "total_steps": 22320, "loss": 0.6545, "lr": 7.258064516129033e-06, "epoch": 0.29121863799283154, "percentage": 1.46, "elapsed_time": "0:00:47", "remaining_time": "0:53:09", "throughput": 2650.01, "total_tokens": 124896}
66
+ {"current_steps": 330, "total_steps": 22320, "loss": 0.9049, "lr": 7.370071684587813e-06, "epoch": 0.2956989247311828, "percentage": 1.48, "elapsed_time": "0:00:47", "remaining_time": "0:53:05", "throughput": 2650.07, "total_tokens": 126688}
67
+ {"current_steps": 335, "total_steps": 22320, "loss": 0.8112, "lr": 7.4820788530465954e-06, "epoch": 0.300179211469534, "percentage": 1.5, "elapsed_time": "0:00:48", "remaining_time": "0:52:59", "throughput": 2651.97, "total_tokens": 128480}
68
+ {"current_steps": 340, "total_steps": 22320, "loss": 0.4131, "lr": 7.594086021505377e-06, "epoch": 0.3046594982078853, "percentage": 1.52, "elapsed_time": "0:00:49", "remaining_time": "0:52:53", "throughput": 2654.92, "total_tokens": 130336}
69
+ {"current_steps": 345, "total_steps": 22320, "loss": 0.9123, "lr": 7.706093189964159e-06, "epoch": 0.30913978494623656, "percentage": 1.55, "elapsed_time": "0:00:49", "remaining_time": "0:52:50", "throughput": 2656.55, "total_tokens": 132224}
70
+ {"current_steps": 350, "total_steps": 22320, "loss": 0.6805, "lr": 7.81810035842294e-06, "epoch": 0.31362007168458783, "percentage": 1.57, "elapsed_time": "0:00:50", "remaining_time": "0:52:49", "throughput": 2657.96, "total_tokens": 134208}
71
+ {"current_steps": 355, "total_steps": 22320, "loss": 0.8838, "lr": 7.93010752688172e-06, "epoch": 0.31810035842293904, "percentage": 1.59, "elapsed_time": "0:00:51", "remaining_time": "0:52:45", "throughput": 2658.52, "total_tokens": 136032}
72
+ {"current_steps": 360, "total_steps": 22320, "loss": 1.1213, "lr": 8.042114695340502e-06, "epoch": 0.3225806451612903, "percentage": 1.61, "elapsed_time": "0:00:51", "remaining_time": "0:52:44", "throughput": 2659.59, "total_tokens": 137984}
73
+ {"current_steps": 365, "total_steps": 22320, "loss": 0.8657, "lr": 8.154121863799285e-06, "epoch": 0.3270609318996416, "percentage": 1.64, "elapsed_time": "0:00:52", "remaining_time": "0:52:41", "throughput": 2659.71, "total_tokens": 139776}
74
+ {"current_steps": 370, "total_steps": 22320, "loss": 0.4244, "lr": 8.266129032258065e-06, "epoch": 0.33154121863799285, "percentage": 1.66, "elapsed_time": "0:00:53", "remaining_time": "0:52:38", "throughput": 2661.17, "total_tokens": 141664}
75
+ {"current_steps": 375, "total_steps": 22320, "loss": 1.0161, "lr": 8.378136200716846e-06, "epoch": 0.33602150537634407, "percentage": 1.68, "elapsed_time": "0:00:53", "remaining_time": "0:52:32", "throughput": 2661.98, "total_tokens": 143424}
76
+ {"current_steps": 380, "total_steps": 22320, "loss": 0.219, "lr": 8.490143369175628e-06, "epoch": 0.34050179211469533, "percentage": 1.7, "elapsed_time": "0:00:54", "remaining_time": "0:52:36", "throughput": 2661.07, "total_tokens": 145472}
77
+ {"current_steps": 385, "total_steps": 22320, "loss": 0.9806, "lr": 8.602150537634409e-06, "epoch": 0.3449820788530466, "percentage": 1.72, "elapsed_time": "0:00:55", "remaining_time": "0:52:35", "throughput": 2662.21, "total_tokens": 147456}
78
+ {"current_steps": 390, "total_steps": 22320, "loss": 0.4166, "lr": 8.71415770609319e-06, "epoch": 0.34946236559139787, "percentage": 1.75, "elapsed_time": "0:00:56", "remaining_time": "0:52:34", "throughput": 2662.62, "total_tokens": 149376}
79
+ {"current_steps": 395, "total_steps": 22320, "loss": 0.7766, "lr": 8.826164874551972e-06, "epoch": 0.3539426523297491, "percentage": 1.77, "elapsed_time": "0:00:56", "remaining_time": "0:52:31", "throughput": 2663.24, "total_tokens": 151232}
80
+ {"current_steps": 400, "total_steps": 22320, "loss": 0.6488, "lr": 8.938172043010753e-06, "epoch": 0.35842293906810035, "percentage": 1.79, "elapsed_time": "0:00:57", "remaining_time": "0:52:31", "throughput": 2664.82, "total_tokens": 153248}
81
+ {"current_steps": 405, "total_steps": 22320, "loss": 0.7861, "lr": 9.050179211469534e-06, "epoch": 0.3629032258064516, "percentage": 1.81, "elapsed_time": "0:00:58", "remaining_time": "0:52:30", "throughput": 2665.27, "total_tokens": 155168}
82
+ {"current_steps": 410, "total_steps": 22320, "loss": 0.3136, "lr": 9.162186379928316e-06, "epoch": 0.3673835125448029, "percentage": 1.84, "elapsed_time": "0:00:58", "remaining_time": "0:52:27", "throughput": 2666.73, "total_tokens": 157056}
83
+ {"current_steps": 415, "total_steps": 22320, "loss": 0.5188, "lr": 9.274193548387097e-06, "epoch": 0.3718637992831541, "percentage": 1.86, "elapsed_time": "0:00:59", "remaining_time": "0:52:24", "throughput": 2668.43, "total_tokens": 158976}
84
+ {"current_steps": 420, "total_steps": 22320, "loss": 0.1776, "lr": 9.386200716845879e-06, "epoch": 0.3763440860215054, "percentage": 1.88, "elapsed_time": "0:01:00", "remaining_time": "0:52:23", "throughput": 2669.05, "total_tokens": 160928}
85
+ {"current_steps": 425, "total_steps": 22320, "loss": 0.5347, "lr": 9.49820788530466e-06, "epoch": 0.38082437275985664, "percentage": 1.9, "elapsed_time": "0:01:01", "remaining_time": "0:52:26", "throughput": 2669.7, "total_tokens": 163072}
86
+ {"current_steps": 430, "total_steps": 22320, "loss": 0.6804, "lr": 9.61021505376344e-06, "epoch": 0.38530465949820786, "percentage": 1.93, "elapsed_time": "0:01:01", "remaining_time": "0:52:27", "throughput": 2670.2, "total_tokens": 165120}
87
+ {"current_steps": 435, "total_steps": 22320, "loss": 0.2984, "lr": 9.722222222222223e-06, "epoch": 0.3897849462365591, "percentage": 1.95, "elapsed_time": "0:01:02", "remaining_time": "0:52:25", "throughput": 2671.3, "total_tokens": 167008}
88
+ {"current_steps": 440, "total_steps": 22320, "loss": 0.2737, "lr": 9.834229390681005e-06, "epoch": 0.3942652329749104, "percentage": 1.97, "elapsed_time": "0:01:03", "remaining_time": "0:52:22", "throughput": 2673.34, "total_tokens": 168960}
89
+ {"current_steps": 445, "total_steps": 22320, "loss": 0.3621, "lr": 9.946236559139786e-06, "epoch": 0.39874551971326166, "percentage": 1.99, "elapsed_time": "0:01:03", "remaining_time": "0:52:21", "throughput": 2673.97, "total_tokens": 170912}
90
+ {"current_steps": 450, "total_steps": 22320, "loss": 0.3349, "lr": 1.0058243727598566e-05, "epoch": 0.4032258064516129, "percentage": 2.02, "elapsed_time": "0:01:04", "remaining_time": "0:52:17", "throughput": 2676.01, "total_tokens": 172768}
91
+ {"current_steps": 455, "total_steps": 22320, "loss": 0.5243, "lr": 1.0170250896057349e-05, "epoch": 0.40770609318996415, "percentage": 2.04, "elapsed_time": "0:01:05", "remaining_time": "0:52:17", "throughput": 2677.47, "total_tokens": 174784}
92
+ {"current_steps": 460, "total_steps": 22320, "loss": 0.9593, "lr": 1.028225806451613e-05, "epoch": 0.4121863799283154, "percentage": 2.06, "elapsed_time": "0:01:05", "remaining_time": "0:52:14", "throughput": 2677.74, "total_tokens": 176608}
93
+ {"current_steps": 465, "total_steps": 22320, "loss": 0.455, "lr": 1.039426523297491e-05, "epoch": 0.4166666666666667, "percentage": 2.08, "elapsed_time": "0:01:06", "remaining_time": "0:52:12", "throughput": 2679.5, "total_tokens": 178560}
94
+ {"current_steps": 470, "total_steps": 22320, "loss": 0.6845, "lr": 1.0506272401433693e-05, "epoch": 0.4211469534050179, "percentage": 2.11, "elapsed_time": "0:01:07", "remaining_time": "0:52:08", "throughput": 2681.4, "total_tokens": 180448}
95
+ {"current_steps": 475, "total_steps": 22320, "loss": 0.5128, "lr": 1.0618279569892473e-05, "epoch": 0.42562724014336917, "percentage": 2.13, "elapsed_time": "0:01:07", "remaining_time": "0:52:06", "throughput": 2682.04, "total_tokens": 182336}
96
+ {"current_steps": 480, "total_steps": 22320, "loss": 0.4941, "lr": 1.0730286738351256e-05, "epoch": 0.43010752688172044, "percentage": 2.15, "elapsed_time": "0:01:08", "remaining_time": "0:52:06", "throughput": 2684.29, "total_tokens": 184448}
97
+ {"current_steps": 485, "total_steps": 22320, "loss": 0.3189, "lr": 1.0842293906810036e-05, "epoch": 0.4345878136200717, "percentage": 2.17, "elapsed_time": "0:01:09", "remaining_time": "0:52:08", "throughput": 2684.16, "total_tokens": 186528}
98
+ {"current_steps": 490, "total_steps": 22320, "loss": 0.4637, "lr": 1.0954301075268817e-05, "epoch": 0.4390681003584229, "percentage": 2.2, "elapsed_time": "0:01:10", "remaining_time": "0:52:06", "throughput": 2683.77, "total_tokens": 188320}
99
+ {"current_steps": 495, "total_steps": 22320, "loss": 0.396, "lr": 1.10663082437276e-05, "epoch": 0.4435483870967742, "percentage": 2.22, "elapsed_time": "0:01:10", "remaining_time": "0:52:02", "throughput": 2685.37, "total_tokens": 190176}
100
+ {"current_steps": 500, "total_steps": 22320, "loss": 0.2008, "lr": 1.117831541218638e-05, "epoch": 0.44802867383512546, "percentage": 2.24, "elapsed_time": "0:01:11", "remaining_time": "0:52:00", "throughput": 2686.15, "total_tokens": 192064}
101
+ {"current_steps": 505, "total_steps": 22320, "loss": 0.5649, "lr": 1.129032258064516e-05, "epoch": 0.4525089605734767, "percentage": 2.26, "elapsed_time": "0:01:12", "remaining_time": "0:52:01", "throughput": 2685.38, "total_tokens": 194016}
102
+ {"current_steps": 510, "total_steps": 22320, "loss": 0.9924, "lr": 1.1402329749103943e-05, "epoch": 0.45698924731182794, "percentage": 2.28, "elapsed_time": "0:01:12", "remaining_time": "0:51:58", "throughput": 2685.86, "total_tokens": 195872}
103
+ {"current_steps": 515, "total_steps": 22320, "loss": 0.651, "lr": 1.1514336917562725e-05, "epoch": 0.4614695340501792, "percentage": 2.31, "elapsed_time": "0:01:13", "remaining_time": "0:51:59", "throughput": 2685.16, "total_tokens": 197824}
104
+ {"current_steps": 520, "total_steps": 22320, "loss": 0.3407, "lr": 1.1626344086021504e-05, "epoch": 0.4659498207885305, "percentage": 2.33, "elapsed_time": "0:01:14", "remaining_time": "0:51:57", "throughput": 2686.06, "total_tokens": 199744}
105
+ {"current_steps": 525, "total_steps": 22320, "loss": 0.5132, "lr": 1.1738351254480287e-05, "epoch": 0.47043010752688175, "percentage": 2.35, "elapsed_time": "0:01:15", "remaining_time": "0:51:58", "throughput": 2686.27, "total_tokens": 201792}
106
+ {"current_steps": 530, "total_steps": 22320, "loss": 0.6351, "lr": 1.185035842293907e-05, "epoch": 0.47491039426523296, "percentage": 2.37, "elapsed_time": "0:01:15", "remaining_time": "0:51:56", "throughput": 2685.85, "total_tokens": 203584}
107
+ {"current_steps": 535, "total_steps": 22320, "loss": 0.3927, "lr": 1.196236559139785e-05, "epoch": 0.47939068100358423, "percentage": 2.4, "elapsed_time": "0:01:16", "remaining_time": "0:51:54", "throughput": 2686.23, "total_tokens": 205440}
108
+ {"current_steps": 540, "total_steps": 22320, "loss": 0.0351, "lr": 1.207437275985663e-05, "epoch": 0.4838709677419355, "percentage": 2.42, "elapsed_time": "0:01:17", "remaining_time": "0:51:53", "throughput": 2686.6, "total_tokens": 207392}
109
+ {"current_steps": 545, "total_steps": 22320, "loss": 0.4408, "lr": 1.2186379928315413e-05, "epoch": 0.4883512544802867, "percentage": 2.44, "elapsed_time": "0:01:17", "remaining_time": "0:51:50", "throughput": 2687.25, "total_tokens": 209184}
110
+ {"current_steps": 550, "total_steps": 22320, "loss": 0.2941, "lr": 1.2298387096774194e-05, "epoch": 0.492831541218638, "percentage": 2.46, "elapsed_time": "0:01:18", "remaining_time": "0:51:49", "throughput": 2687.84, "total_tokens": 211168}
111
+ {"current_steps": 555, "total_steps": 22320, "loss": 0.018, "lr": 1.2410394265232976e-05, "epoch": 0.49731182795698925, "percentage": 2.49, "elapsed_time": "0:01:19", "remaining_time": "0:51:49", "throughput": 2689.43, "total_tokens": 213248}
112
+ {"current_steps": 560, "total_steps": 22320, "loss": 0.2407, "lr": 1.2522401433691758e-05, "epoch": 0.5017921146953405, "percentage": 2.51, "elapsed_time": "0:01:20", "remaining_time": "0:51:49", "throughput": 2689.99, "total_tokens": 215232}
113
+ {"current_steps": 565, "total_steps": 22320, "loss": 0.1319, "lr": 1.2634408602150537e-05, "epoch": 0.5062724014336918, "percentage": 2.53, "elapsed_time": "0:01:20", "remaining_time": "0:51:45", "throughput": 2691.72, "total_tokens": 217120}
114
+ {"current_steps": 570, "total_steps": 22320, "loss": 0.6092, "lr": 1.2746415770609318e-05, "epoch": 0.510752688172043, "percentage": 2.55, "elapsed_time": "0:01:21", "remaining_time": "0:51:45", "throughput": 2692.06, "total_tokens": 219072}
115
+ {"current_steps": 575, "total_steps": 22320, "loss": 0.2269, "lr": 1.2858422939068102e-05, "epoch": 0.5152329749103942, "percentage": 2.58, "elapsed_time": "0:01:22", "remaining_time": "0:51:48", "throughput": 2691.61, "total_tokens": 221248}
116
+ {"current_steps": 580, "total_steps": 22320, "loss": 0.6802, "lr": 1.2970430107526881e-05, "epoch": 0.5197132616487455, "percentage": 2.6, "elapsed_time": "0:01:22", "remaining_time": "0:51:46", "throughput": 2692.62, "total_tokens": 223168}
117
+ {"current_steps": 585, "total_steps": 22320, "loss": 0.6734, "lr": 1.3082437275985665e-05, "epoch": 0.5241935483870968, "percentage": 2.62, "elapsed_time": "0:01:23", "remaining_time": "0:51:44", "throughput": 2693.27, "total_tokens": 225056}
118
+ {"current_steps": 590, "total_steps": 22320, "loss": 0.5133, "lr": 1.3194444444444446e-05, "epoch": 0.5286738351254481, "percentage": 2.64, "elapsed_time": "0:01:24", "remaining_time": "0:51:41", "throughput": 2692.89, "total_tokens": 226752}
119
+ {"current_steps": 595, "total_steps": 22320, "loss": 0.6177, "lr": 1.3306451612903225e-05, "epoch": 0.5331541218637993, "percentage": 2.67, "elapsed_time": "0:01:24", "remaining_time": "0:51:39", "throughput": 2693.03, "total_tokens": 228608}
120
+ {"current_steps": 600, "total_steps": 22320, "loss": 0.3267, "lr": 1.3418458781362009e-05, "epoch": 0.5376344086021505, "percentage": 2.69, "elapsed_time": "0:01:25", "remaining_time": "0:51:36", "throughput": 2694.66, "total_tokens": 230496}
121
+ {"current_steps": 605, "total_steps": 22320, "loss": 0.4914, "lr": 1.353046594982079e-05, "epoch": 0.5421146953405018, "percentage": 2.71, "elapsed_time": "0:01:26", "remaining_time": "0:51:34", "throughput": 2695.27, "total_tokens": 232384}
122
+ {"current_steps": 610, "total_steps": 22320, "loss": 0.7597, "lr": 1.364247311827957e-05, "epoch": 0.546594982078853, "percentage": 2.73, "elapsed_time": "0:01:26", "remaining_time": "0:51:35", "throughput": 2695.77, "total_tokens": 234464}
123
+ {"current_steps": 615, "total_steps": 22320, "loss": 0.5514, "lr": 1.3754480286738353e-05, "epoch": 0.5510752688172043, "percentage": 2.76, "elapsed_time": "0:01:27", "remaining_time": "0:51:32", "throughput": 2696.26, "total_tokens": 236256}
124
+ {"current_steps": 620, "total_steps": 22320, "loss": 0.9979, "lr": 1.3866487455197133e-05, "epoch": 0.5555555555555556, "percentage": 2.78, "elapsed_time": "0:01:28", "remaining_time": "0:51:29", "throughput": 2695.97, "total_tokens": 237952}
125
+ {"current_steps": 625, "total_steps": 22320, "loss": 0.7025, "lr": 1.3978494623655914e-05, "epoch": 0.5600358422939068, "percentage": 2.8, "elapsed_time": "0:01:28", "remaining_time": "0:51:27", "throughput": 2696.28, "total_tokens": 239808}
126
+ {"current_steps": 630, "total_steps": 22320, "loss": 0.7179, "lr": 1.4090501792114696e-05, "epoch": 0.5645161290322581, "percentage": 2.82, "elapsed_time": "0:01:29", "remaining_time": "0:51:26", "throughput": 2696.2, "total_tokens": 241728}
127
+ {"current_steps": 635, "total_steps": 22320, "loss": 1.0102, "lr": 1.4202508960573477e-05, "epoch": 0.5689964157706093, "percentage": 2.84, "elapsed_time": "0:01:30", "remaining_time": "0:51:26", "throughput": 2695.46, "total_tokens": 243584}
128
+ {"current_steps": 640, "total_steps": 22320, "loss": 0.919, "lr": 1.431451612903226e-05, "epoch": 0.5734767025089605, "percentage": 2.87, "elapsed_time": "0:01:31", "remaining_time": "0:51:25", "throughput": 2695.29, "total_tokens": 245504}
129
+ {"current_steps": 645, "total_steps": 22320, "loss": 0.1854, "lr": 1.442652329749104e-05, "epoch": 0.5779569892473119, "percentage": 2.89, "elapsed_time": "0:01:31", "remaining_time": "0:51:24", "throughput": 2696.38, "total_tokens": 247488}
130
+ {"current_steps": 650, "total_steps": 22320, "loss": 0.7057, "lr": 1.4538530465949821e-05, "epoch": 0.5824372759856631, "percentage": 2.91, "elapsed_time": "0:01:32", "remaining_time": "0:51:22", "throughput": 2696.1, "total_tokens": 249312}
131
+ {"current_steps": 655, "total_steps": 22320, "loss": 0.6207, "lr": 1.4650537634408603e-05, "epoch": 0.5869175627240143, "percentage": 2.93, "elapsed_time": "0:01:33", "remaining_time": "0:51:20", "throughput": 2697.16, "total_tokens": 251168}
132
+ {"current_steps": 660, "total_steps": 22320, "loss": 0.6484, "lr": 1.4762544802867384e-05, "epoch": 0.5913978494623656, "percentage": 2.96, "elapsed_time": "0:01:33", "remaining_time": "0:51:18", "throughput": 2697.45, "total_tokens": 253024}
133
+ {"current_steps": 665, "total_steps": 22320, "loss": 0.1609, "lr": 1.4874551971326165e-05, "epoch": 0.5958781362007168, "percentage": 2.98, "elapsed_time": "0:01:34", "remaining_time": "0:51:17", "throughput": 2697.31, "total_tokens": 254944}
134
+ {"current_steps": 670, "total_steps": 22320, "loss": 0.5327, "lr": 1.4986559139784947e-05, "epoch": 0.600358422939068, "percentage": 3.0, "elapsed_time": "0:01:35", "remaining_time": "0:51:16", "throughput": 2696.87, "total_tokens": 256736}
135
+ {"current_steps": 675, "total_steps": 22320, "loss": 0.74, "lr": 1.5098566308243728e-05, "epoch": 0.6048387096774194, "percentage": 3.02, "elapsed_time": "0:01:35", "remaining_time": "0:51:14", "throughput": 2696.45, "total_tokens": 258528}
136
+ {"current_steps": 680, "total_steps": 22320, "loss": 0.6724, "lr": 1.5210573476702512e-05, "epoch": 0.6093189964157706, "percentage": 3.05, "elapsed_time": "0:01:36", "remaining_time": "0:51:12", "throughput": 2696.14, "total_tokens": 260320}
137
+ {"current_steps": 685, "total_steps": 22320, "loss": 0.8154, "lr": 1.5322580645161292e-05, "epoch": 0.6137992831541219, "percentage": 3.07, "elapsed_time": "0:01:37", "remaining_time": "0:51:11", "throughput": 2696.61, "total_tokens": 262208}
138
+ {"current_steps": 690, "total_steps": 22320, "loss": 0.5859, "lr": 1.5434587813620073e-05, "epoch": 0.6182795698924731, "percentage": 3.09, "elapsed_time": "0:01:37", "remaining_time": "0:51:10", "throughput": 2697.3, "total_tokens": 264224}
139
+ {"current_steps": 695, "total_steps": 22320, "loss": 0.311, "lr": 1.5546594982078854e-05, "epoch": 0.6227598566308243, "percentage": 3.11, "elapsed_time": "0:01:38", "remaining_time": "0:51:10", "throughput": 2696.91, "total_tokens": 266112}
140
+ {"current_steps": 700, "total_steps": 22320, "loss": 0.7888, "lr": 1.5658602150537635e-05, "epoch": 0.6272401433691757, "percentage": 3.14, "elapsed_time": "0:01:39", "remaining_time": "0:51:08", "throughput": 2697.91, "total_tokens": 268064}
141
+ {"current_steps": 705, "total_steps": 22320, "loss": 1.0873, "lr": 1.5770609318996415e-05, "epoch": 0.6317204301075269, "percentage": 3.16, "elapsed_time": "0:01:40", "remaining_time": "0:51:07", "throughput": 2698.94, "total_tokens": 270016}
142
+ {"current_steps": 710, "total_steps": 22320, "loss": 0.3965, "lr": 1.58826164874552e-05, "epoch": 0.6362007168458781, "percentage": 3.18, "elapsed_time": "0:01:40", "remaining_time": "0:51:07", "throughput": 2698.88, "total_tokens": 271968}
143
+ {"current_steps": 715, "total_steps": 22320, "loss": 0.6491, "lr": 1.599462365591398e-05, "epoch": 0.6406810035842294, "percentage": 3.2, "elapsed_time": "0:01:41", "remaining_time": "0:51:08", "throughput": 2699.03, "total_tokens": 274080}
144
+ {"current_steps": 720, "total_steps": 22320, "loss": 0.86, "lr": 1.610663082437276e-05, "epoch": 0.6451612903225806, "percentage": 3.23, "elapsed_time": "0:01:42", "remaining_time": "0:51:08", "throughput": 2698.69, "total_tokens": 276064}
145
+ {"current_steps": 725, "total_steps": 22320, "loss": 0.245, "lr": 1.621863799283154e-05, "epoch": 0.649641577060932, "percentage": 3.25, "elapsed_time": "0:01:42", "remaining_time": "0:51:06", "throughput": 2699.78, "total_tokens": 277920}
146
+ {"current_steps": 730, "total_steps": 22320, "loss": 0.6997, "lr": 1.6330645161290322e-05, "epoch": 0.6541218637992832, "percentage": 3.27, "elapsed_time": "0:01:43", "remaining_time": "0:51:05", "throughput": 2699.21, "total_tokens": 279776}
147
+ {"current_steps": 735, "total_steps": 22320, "loss": 0.5005, "lr": 1.6442652329749106e-05, "epoch": 0.6586021505376344, "percentage": 3.29, "elapsed_time": "0:01:44", "remaining_time": "0:51:04", "throughput": 2700.42, "total_tokens": 281760}
148
+ {"current_steps": 740, "total_steps": 22320, "loss": 0.5388, "lr": 1.6554659498207887e-05, "epoch": 0.6630824372759857, "percentage": 3.32, "elapsed_time": "0:01:45", "remaining_time": "0:51:02", "throughput": 2700.48, "total_tokens": 283616}
149
+ {"current_steps": 745, "total_steps": 22320, "loss": 0.5167, "lr": 1.6666666666666667e-05, "epoch": 0.6675627240143369, "percentage": 3.34, "elapsed_time": "0:01:45", "remaining_time": "0:51:02", "throughput": 2700.87, "total_tokens": 285600}
150
+ {"current_steps": 750, "total_steps": 22320, "loss": 0.9435, "lr": 1.6778673835125448e-05, "epoch": 0.6720430107526881, "percentage": 3.36, "elapsed_time": "0:01:46", "remaining_time": "0:51:00", "throughput": 2701.39, "total_tokens": 287488}
151
+ {"current_steps": 755, "total_steps": 22320, "loss": 0.3714, "lr": 1.689068100358423e-05, "epoch": 0.6765232974910395, "percentage": 3.38, "elapsed_time": "0:01:47", "remaining_time": "0:50:58", "throughput": 2701.15, "total_tokens": 289280}
152
+ {"current_steps": 760, "total_steps": 22320, "loss": 0.6141, "lr": 1.700268817204301e-05, "epoch": 0.6810035842293907, "percentage": 3.41, "elapsed_time": "0:01:47", "remaining_time": "0:50:56", "throughput": 2701.87, "total_tokens": 291104}
153
+ {"current_steps": 765, "total_steps": 22320, "loss": 0.288, "lr": 1.7114695340501794e-05, "epoch": 0.6854838709677419, "percentage": 3.43, "elapsed_time": "0:01:48", "remaining_time": "0:50:56", "throughput": 2701.9, "total_tokens": 293056}
154
+ {"current_steps": 770, "total_steps": 22320, "loss": 0.0204, "lr": 1.7226702508960574e-05, "epoch": 0.6899641577060932, "percentage": 3.45, "elapsed_time": "0:01:49", "remaining_time": "0:50:55", "throughput": 2702.19, "total_tokens": 295040}
155
+ {"current_steps": 775, "total_steps": 22320, "loss": 0.4715, "lr": 1.733870967741936e-05, "epoch": 0.6944444444444444, "percentage": 3.47, "elapsed_time": "0:01:49", "remaining_time": "0:50:55", "throughput": 2702.25, "total_tokens": 296992}
156
+ {"current_steps": 780, "total_steps": 22320, "loss": 1.0656, "lr": 1.7450716845878136e-05, "epoch": 0.6989247311827957, "percentage": 3.49, "elapsed_time": "0:01:50", "remaining_time": "0:50:53", "throughput": 2701.56, "total_tokens": 298752}
157
+ {"current_steps": 785, "total_steps": 22320, "loss": 0.0364, "lr": 1.7562724014336916e-05, "epoch": 0.703405017921147, "percentage": 3.52, "elapsed_time": "0:01:51", "remaining_time": "0:50:53", "throughput": 2701.44, "total_tokens": 300672}
158
+ {"current_steps": 790, "total_steps": 22320, "loss": 0.8115, "lr": 1.76747311827957e-05, "epoch": 0.7078853046594982, "percentage": 3.54, "elapsed_time": "0:01:51", "remaining_time": "0:50:50", "throughput": 2701.64, "total_tokens": 302432}
159
+ {"current_steps": 795, "total_steps": 22320, "loss": 0.46, "lr": 1.778673835125448e-05, "epoch": 0.7123655913978495, "percentage": 3.56, "elapsed_time": "0:01:52", "remaining_time": "0:50:50", "throughput": 2701.53, "total_tokens": 304352}
160
+ {"current_steps": 800, "total_steps": 22320, "loss": 0.5221, "lr": 1.7898745519713262e-05, "epoch": 0.7168458781362007, "percentage": 3.58, "elapsed_time": "0:01:53", "remaining_time": "0:50:48", "throughput": 2701.49, "total_tokens": 306176}
161
+ {"current_steps": 805, "total_steps": 22320, "loss": 1.1312, "lr": 1.8010752688172046e-05, "epoch": 0.7213261648745519, "percentage": 3.61, "elapsed_time": "0:01:54", "remaining_time": "0:50:49", "throughput": 2702.66, "total_tokens": 308384}
162
+ {"current_steps": 810, "total_steps": 22320, "loss": 0.4251, "lr": 1.8122759856630827e-05, "epoch": 0.7258064516129032, "percentage": 3.63, "elapsed_time": "0:01:54", "remaining_time": "0:50:50", "throughput": 2702.53, "total_tokens": 310400}
163
+ {"current_steps": 815, "total_steps": 22320, "loss": 0.4217, "lr": 1.8234767025089607e-05, "epoch": 0.7302867383512545, "percentage": 3.65, "elapsed_time": "0:01:55", "remaining_time": "0:50:49", "throughput": 2702.51, "total_tokens": 312352}
164
+ {"current_steps": 820, "total_steps": 22320, "loss": 0.4723, "lr": 1.8346774193548388e-05, "epoch": 0.7347670250896058, "percentage": 3.67, "elapsed_time": "0:01:56", "remaining_time": "0:50:49", "throughput": 2702.47, "total_tokens": 314272}
165
+ {"current_steps": 825, "total_steps": 22320, "loss": 0.3469, "lr": 1.845878136200717e-05, "epoch": 0.739247311827957, "percentage": 3.7, "elapsed_time": "0:01:56", "remaining_time": "0:50:46", "throughput": 2701.85, "total_tokens": 315936}
166
+ {"current_steps": 830, "total_steps": 22320, "loss": 0.2082, "lr": 1.8570788530465953e-05, "epoch": 0.7437275985663082, "percentage": 3.72, "elapsed_time": "0:01:57", "remaining_time": "0:50:47", "throughput": 2702.63, "total_tokens": 318144}
167
+ {"current_steps": 835, "total_steps": 22320, "loss": 0.704, "lr": 1.8682795698924733e-05, "epoch": 0.7482078853046595, "percentage": 3.74, "elapsed_time": "0:01:58", "remaining_time": "0:50:46", "throughput": 2702.81, "total_tokens": 320000}
168
+ {"current_steps": 840, "total_steps": 22320, "loss": 0.517, "lr": 1.8794802867383514e-05, "epoch": 0.7526881720430108, "percentage": 3.76, "elapsed_time": "0:01:59", "remaining_time": "0:50:45", "throughput": 2702.63, "total_tokens": 321920}
169
+ {"current_steps": 845, "total_steps": 22320, "loss": 0.393, "lr": 1.8906810035842295e-05, "epoch": 0.757168458781362, "percentage": 3.79, "elapsed_time": "0:01:59", "remaining_time": "0:50:43", "throughput": 2702.58, "total_tokens": 323648}
170
+ {"current_steps": 850, "total_steps": 22320, "loss": 0.9965, "lr": 1.9018817204301075e-05, "epoch": 0.7616487455197133, "percentage": 3.81, "elapsed_time": "0:02:00", "remaining_time": "0:50:43", "throughput": 2703.57, "total_tokens": 325792}
171
+ {"current_steps": 855, "total_steps": 22320, "loss": 0.1825, "lr": 1.9130824372759856e-05, "epoch": 0.7661290322580645, "percentage": 3.83, "elapsed_time": "0:02:01", "remaining_time": "0:50:42", "throughput": 2703.81, "total_tokens": 327648}
172
+ {"current_steps": 860, "total_steps": 22320, "loss": 0.2139, "lr": 1.924283154121864e-05, "epoch": 0.7706093189964157, "percentage": 3.85, "elapsed_time": "0:02:01", "remaining_time": "0:50:39", "throughput": 2703.48, "total_tokens": 329344}
173
+ {"current_steps": 865, "total_steps": 22320, "loss": 0.7226, "lr": 1.935483870967742e-05, "epoch": 0.775089605734767, "percentage": 3.88, "elapsed_time": "0:02:02", "remaining_time": "0:50:38", "throughput": 2704.11, "total_tokens": 331264}
174
+ {"current_steps": 870, "total_steps": 22320, "loss": 0.689, "lr": 1.94668458781362e-05, "epoch": 0.7795698924731183, "percentage": 3.9, "elapsed_time": "0:02:03", "remaining_time": "0:50:39", "throughput": 2704.13, "total_tokens": 333312}
175
+ {"current_steps": 875, "total_steps": 22320, "loss": 0.3166, "lr": 1.9578853046594982e-05, "epoch": 0.7840501792114696, "percentage": 3.92, "elapsed_time": "0:02:03", "remaining_time": "0:50:37", "throughput": 2704.29, "total_tokens": 335168}
176
+ {"current_steps": 880, "total_steps": 22320, "loss": 0.8267, "lr": 1.9690860215053763e-05, "epoch": 0.7885304659498208, "percentage": 3.94, "elapsed_time": "0:02:04", "remaining_time": "0:50:36", "throughput": 2703.74, "total_tokens": 337024}
177
+ {"current_steps": 885, "total_steps": 22320, "loss": 0.5392, "lr": 1.9802867383512547e-05, "epoch": 0.793010752688172, "percentage": 3.97, "elapsed_time": "0:02:05", "remaining_time": "0:50:36", "throughput": 2703.65, "total_tokens": 338944}
178
+ {"current_steps": 890, "total_steps": 22320, "loss": 0.6543, "lr": 1.9914874551971328e-05, "epoch": 0.7974910394265233, "percentage": 3.99, "elapsed_time": "0:02:06", "remaining_time": "0:50:34", "throughput": 2703.8, "total_tokens": 340704}
179
+ {"current_steps": 895, "total_steps": 22320, "loss": 0.8707, "lr": 2.002688172043011e-05, "epoch": 0.8019713261648745, "percentage": 4.01, "elapsed_time": "0:02:06", "remaining_time": "0:50:33", "throughput": 2703.42, "total_tokens": 342592}
180
+ {"current_steps": 900, "total_steps": 22320, "loss": 0.9575, "lr": 2.013888888888889e-05, "epoch": 0.8064516129032258, "percentage": 4.03, "elapsed_time": "0:02:07", "remaining_time": "0:50:32", "throughput": 2703.71, "total_tokens": 344480}
181
+ {"current_steps": 905, "total_steps": 22320, "loss": 0.2066, "lr": 2.025089605734767e-05, "epoch": 0.8109318996415771, "percentage": 4.05, "elapsed_time": "0:02:08", "remaining_time": "0:50:31", "throughput": 2704.32, "total_tokens": 346400}
182
+ {"current_steps": 910, "total_steps": 22320, "loss": 0.7631, "lr": 2.0362903225806454e-05, "epoch": 0.8154121863799283, "percentage": 4.08, "elapsed_time": "0:02:08", "remaining_time": "0:50:30", "throughput": 2704.75, "total_tokens": 348384}
183
+ {"current_steps": 915, "total_steps": 22320, "loss": 0.7422, "lr": 2.0474910394265234e-05, "epoch": 0.8198924731182796, "percentage": 4.1, "elapsed_time": "0:02:09", "remaining_time": "0:50:29", "throughput": 2704.67, "total_tokens": 350208}
184
+ {"current_steps": 920, "total_steps": 22320, "loss": 0.4186, "lr": 2.0586917562724015e-05, "epoch": 0.8243727598566308, "percentage": 4.12, "elapsed_time": "0:02:10", "remaining_time": "0:50:27", "throughput": 2705.02, "total_tokens": 352096}
185
+ {"current_steps": 925, "total_steps": 22320, "loss": 0.1824, "lr": 2.06989247311828e-05, "epoch": 0.828853046594982, "percentage": 4.14, "elapsed_time": "0:02:10", "remaining_time": "0:50:26", "throughput": 2705.22, "total_tokens": 353952}
186
+ {"current_steps": 930, "total_steps": 22320, "loss": 0.3514, "lr": 2.0810931899641577e-05, "epoch": 0.8333333333333334, "percentage": 4.17, "elapsed_time": "0:02:11", "remaining_time": "0:50:25", "throughput": 2705.61, "total_tokens": 355936}
187
+ {"current_steps": 935, "total_steps": 22320, "loss": 0.4387, "lr": 2.0922939068100357e-05, "epoch": 0.8378136200716846, "percentage": 4.19, "elapsed_time": "0:02:12", "remaining_time": "0:50:25", "throughput": 2705.97, "total_tokens": 357920}
188
+ {"current_steps": 940, "total_steps": 22320, "loss": 0.6719, "lr": 2.103494623655914e-05, "epoch": 0.8422939068100358, "percentage": 4.21, "elapsed_time": "0:02:12", "remaining_time": "0:50:23", "throughput": 2705.9, "total_tokens": 359648}
189
+ {"current_steps": 945, "total_steps": 22320, "loss": 0.7939, "lr": 2.1146953405017922e-05, "epoch": 0.8467741935483871, "percentage": 4.23, "elapsed_time": "0:02:13", "remaining_time": "0:50:21", "throughput": 2705.99, "total_tokens": 361504}
190
+ {"current_steps": 950, "total_steps": 22320, "loss": 0.8633, "lr": 2.1258960573476703e-05, "epoch": 0.8512544802867383, "percentage": 4.26, "elapsed_time": "0:02:14", "remaining_time": "0:50:22", "throughput": 2705.75, "total_tokens": 363520}
191
+ {"current_steps": 955, "total_steps": 22320, "loss": 0.438, "lr": 2.1370967741935487e-05, "epoch": 0.8557347670250897, "percentage": 4.28, "elapsed_time": "0:02:15", "remaining_time": "0:50:20", "throughput": 2705.31, "total_tokens": 365312}
192
+ {"current_steps": 960, "total_steps": 22320, "loss": 0.6055, "lr": 2.1482974910394264e-05, "epoch": 0.8602150537634409, "percentage": 4.3, "elapsed_time": "0:02:15", "remaining_time": "0:50:19", "throughput": 2705.47, "total_tokens": 367200}
193
+ {"current_steps": 965, "total_steps": 22320, "loss": 0.4399, "lr": 2.1594982078853048e-05, "epoch": 0.8646953405017921, "percentage": 4.32, "elapsed_time": "0:02:16", "remaining_time": "0:50:20", "throughput": 2705.23, "total_tokens": 369216}
194
+ {"current_steps": 970, "total_steps": 22320, "loss": 0.4845, "lr": 2.170698924731183e-05, "epoch": 0.8691756272401434, "percentage": 4.35, "elapsed_time": "0:02:17", "remaining_time": "0:50:19", "throughput": 2704.84, "total_tokens": 371104}
195
+ {"current_steps": 975, "total_steps": 22320, "loss": 0.4469, "lr": 2.181899641577061e-05, "epoch": 0.8736559139784946, "percentage": 4.37, "elapsed_time": "0:02:17", "remaining_time": "0:50:17", "throughput": 2704.65, "total_tokens": 372832}
196
+ {"current_steps": 980, "total_steps": 22320, "loss": 0.7461, "lr": 2.1931003584229394e-05, "epoch": 0.8781362007168458, "percentage": 4.39, "elapsed_time": "0:02:18", "remaining_time": "0:50:16", "throughput": 2704.27, "total_tokens": 374624}
197
+ {"current_steps": 985, "total_steps": 22320, "loss": 0.874, "lr": 2.2043010752688174e-05, "epoch": 0.8826164874551972, "percentage": 4.41, "elapsed_time": "0:02:19", "remaining_time": "0:50:14", "throughput": 2704.13, "total_tokens": 376352}
198
+ {"current_steps": 990, "total_steps": 22320, "loss": 0.5172, "lr": 2.2155017921146955e-05, "epoch": 0.8870967741935484, "percentage": 4.44, "elapsed_time": "0:02:19", "remaining_time": "0:50:13", "throughput": 2704.44, "total_tokens": 378240}
199
+ {"current_steps": 995, "total_steps": 22320, "loss": 0.8491, "lr": 2.2267025089605736e-05, "epoch": 0.8915770609318996, "percentage": 4.46, "elapsed_time": "0:02:20", "remaining_time": "0:50:12", "throughput": 2704.45, "total_tokens": 380192}
200
+ {"current_steps": 1000, "total_steps": 22320, "loss": 0.3806, "lr": 2.2379032258064516e-05, "epoch": 0.8960573476702509, "percentage": 4.48, "elapsed_time": "0:02:21", "remaining_time": "0:50:11", "throughput": 2704.49, "total_tokens": 382048}
201
+ {"current_steps": 1005, "total_steps": 22320, "loss": 0.4773, "lr": 2.24910394265233e-05, "epoch": 0.9005376344086021, "percentage": 4.5, "elapsed_time": "0:02:21", "remaining_time": "0:50:10", "throughput": 2704.75, "total_tokens": 383936}
202
+ {"current_steps": 1010, "total_steps": 22320, "loss": 0.5688, "lr": 2.260304659498208e-05, "epoch": 0.9050179211469535, "percentage": 4.53, "elapsed_time": "0:02:22", "remaining_time": "0:50:09", "throughput": 2705.22, "total_tokens": 385856}
203
+ {"current_steps": 1015, "total_steps": 22320, "loss": 0.1703, "lr": 2.271505376344086e-05, "epoch": 0.9094982078853047, "percentage": 4.55, "elapsed_time": "0:02:23", "remaining_time": "0:50:09", "throughput": 2705.42, "total_tokens": 387840}
204
+ {"current_steps": 1020, "total_steps": 22320, "loss": 0.2451, "lr": 2.2827060931899642e-05, "epoch": 0.9139784946236559, "percentage": 4.57, "elapsed_time": "0:02:24", "remaining_time": "0:50:08", "throughput": 2705.32, "total_tokens": 389696}
205
+ {"current_steps": 1025, "total_steps": 22320, "loss": 0.504, "lr": 2.2939068100358423e-05, "epoch": 0.9184587813620072, "percentage": 4.59, "elapsed_time": "0:02:24", "remaining_time": "0:50:07", "throughput": 2705.31, "total_tokens": 391648}
206
+ {"current_steps": 1030, "total_steps": 22320, "loss": 0.4998, "lr": 2.3051075268817204e-05, "epoch": 0.9229390681003584, "percentage": 4.61, "elapsed_time": "0:02:25", "remaining_time": "0:50:06", "throughput": 2706.06, "total_tokens": 393632}
207
+ {"current_steps": 1035, "total_steps": 22320, "loss": 0.3624, "lr": 2.3163082437275988e-05, "epoch": 0.9274193548387096, "percentage": 4.64, "elapsed_time": "0:02:26", "remaining_time": "0:50:04", "throughput": 2706.81, "total_tokens": 395488}
208
+ {"current_steps": 1040, "total_steps": 22320, "loss": 0.2735, "lr": 2.327508960573477e-05, "epoch": 0.931899641577061, "percentage": 4.66, "elapsed_time": "0:02:26", "remaining_time": "0:50:04", "throughput": 2707.35, "total_tokens": 397504}
209
+ {"current_steps": 1045, "total_steps": 22320, "loss": 0.5871, "lr": 2.338709677419355e-05, "epoch": 0.9363799283154122, "percentage": 4.68, "elapsed_time": "0:02:27", "remaining_time": "0:50:02", "throughput": 2707.26, "total_tokens": 399328}
210
+ {"current_steps": 1050, "total_steps": 22320, "loss": 0.3203, "lr": 2.349910394265233e-05, "epoch": 0.9408602150537635, "percentage": 4.7, "elapsed_time": "0:02:28", "remaining_time": "0:50:01", "throughput": 2707.36, "total_tokens": 401184}
211
+ {"current_steps": 1055, "total_steps": 22320, "loss": 0.7475, "lr": 2.361111111111111e-05, "epoch": 0.9453405017921147, "percentage": 4.73, "elapsed_time": "0:02:28", "remaining_time": "0:49:59", "throughput": 2707.69, "total_tokens": 402976}
212
+ {"current_steps": 1060, "total_steps": 22320, "loss": 0.841, "lr": 2.3723118279569895e-05, "epoch": 0.9498207885304659, "percentage": 4.75, "elapsed_time": "0:02:29", "remaining_time": "0:49:58", "throughput": 2707.63, "total_tokens": 404800}
213
+ {"current_steps": 1065, "total_steps": 22320, "loss": 0.8663, "lr": 2.3835125448028675e-05, "epoch": 0.9543010752688172, "percentage": 4.77, "elapsed_time": "0:02:30", "remaining_time": "0:49:58", "throughput": 2708.2, "total_tokens": 406848}
214
+ {"current_steps": 1070, "total_steps": 22320, "loss": 0.3776, "lr": 2.3947132616487456e-05, "epoch": 0.9587813620071685, "percentage": 4.79, "elapsed_time": "0:02:30", "remaining_time": "0:49:56", "throughput": 2708.56, "total_tokens": 408672}
215
+ {"current_steps": 1075, "total_steps": 22320, "loss": 0.2185, "lr": 2.405913978494624e-05, "epoch": 0.9632616487455197, "percentage": 4.82, "elapsed_time": "0:02:31", "remaining_time": "0:49:55", "throughput": 2708.54, "total_tokens": 410528}
216
+ {"current_steps": 1080, "total_steps": 22320, "loss": 0.0626, "lr": 2.4171146953405017e-05, "epoch": 0.967741935483871, "percentage": 4.84, "elapsed_time": "0:02:32", "remaining_time": "0:49:55", "throughput": 2708.68, "total_tokens": 412608}
217
+ {"current_steps": 1085, "total_steps": 22320, "loss": 0.3936, "lr": 2.4283154121863798e-05, "epoch": 0.9722222222222222, "percentage": 4.86, "elapsed_time": "0:02:33", "remaining_time": "0:49:55", "throughput": 2708.87, "total_tokens": 414592}
218
+ {"current_steps": 1090, "total_steps": 22320, "loss": 0.4166, "lr": 2.4395161290322582e-05, "epoch": 0.9767025089605734, "percentage": 4.88, "elapsed_time": "0:02:33", "remaining_time": "0:49:54", "throughput": 2708.56, "total_tokens": 416384}
219
+ {"current_steps": 1095, "total_steps": 22320, "loss": 0.5508, "lr": 2.4507168458781363e-05, "epoch": 0.9811827956989247, "percentage": 4.91, "elapsed_time": "0:02:34", "remaining_time": "0:49:53", "throughput": 2709.36, "total_tokens": 418464}
220
+ {"current_steps": 1100, "total_steps": 22320, "loss": 0.312, "lr": 2.4619175627240147e-05, "epoch": 0.985663082437276, "percentage": 4.93, "elapsed_time": "0:02:35", "remaining_time": "0:49:53", "throughput": 2708.91, "total_tokens": 420320}
221
+ {"current_steps": 1105, "total_steps": 22320, "loss": 0.4404, "lr": 2.4731182795698928e-05, "epoch": 0.9901433691756273, "percentage": 4.95, "elapsed_time": "0:02:35", "remaining_time": "0:49:51", "throughput": 2709.14, "total_tokens": 422112}
222
+ {"current_steps": 1110, "total_steps": 22320, "loss": 0.2663, "lr": 2.4843189964157705e-05, "epoch": 0.9946236559139785, "percentage": 4.97, "elapsed_time": "0:02:36", "remaining_time": "0:49:49", "throughput": 2708.47, "total_tokens": 423744}
223
+ {"current_steps": 1115, "total_steps": 22320, "loss": 0.4076, "lr": 2.495519713261649e-05, "epoch": 0.9991039426523297, "percentage": 5.0, "elapsed_time": "0:02:37", "remaining_time": "0:49:48", "throughput": 2708.31, "total_tokens": 425536}
224
+ {"current_steps": 1116, "total_steps": 22320, "eval_loss": 0.5515770316123962, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:02:42", "remaining_time": "0:51:33", "throughput": 2613.92, "total_tokens": 425624}
225
+ {"current_steps": 1120, "total_steps": 22320, "loss": 0.7785, "lr": 2.506720430107527e-05, "epoch": 1.003584229390681, "percentage": 5.02, "elapsed_time": "0:02:44", "remaining_time": "0:51:48", "throughput": 2601.02, "total_tokens": 427096}
226
+ {"current_steps": 1125, "total_steps": 22320, "loss": 0.6219, "lr": 2.5179211469534054e-05, "epoch": 1.0080645161290323, "percentage": 5.04, "elapsed_time": "0:02:44", "remaining_time": "0:51:46", "throughput": 2601.34, "total_tokens": 428952}
227
+ {"current_steps": 1130, "total_steps": 22320, "loss": 0.8549, "lr": 2.529121863799283e-05, "epoch": 1.0125448028673836, "percentage": 5.06, "elapsed_time": "0:02:45", "remaining_time": "0:51:46", "throughput": 2601.94, "total_tokens": 431096}
228
+ {"current_steps": 1135, "total_steps": 22320, "loss": 0.3929, "lr": 2.5403225806451615e-05, "epoch": 1.0170250896057347, "percentage": 5.09, "elapsed_time": "0:02:46", "remaining_time": "0:51:45", "throughput": 2601.68, "total_tokens": 432824}
229
+ {"current_steps": 1140, "total_steps": 22320, "loss": 0.2541, "lr": 2.5515232974910396e-05, "epoch": 1.021505376344086, "percentage": 5.11, "elapsed_time": "0:02:47", "remaining_time": "0:51:43", "throughput": 2602.38, "total_tokens": 434744}
230
+ {"current_steps": 1145, "total_steps": 22320, "loss": 0.8254, "lr": 2.5627240143369173e-05, "epoch": 1.0259856630824373, "percentage": 5.13, "elapsed_time": "0:02:47", "remaining_time": "0:51:42", "throughput": 2602.9, "total_tokens": 436728}
231
+ {"current_steps": 1150, "total_steps": 22320, "loss": 0.3765, "lr": 2.5739247311827957e-05, "epoch": 1.0304659498207884, "percentage": 5.15, "elapsed_time": "0:02:48", "remaining_time": "0:51:42", "throughput": 2602.88, "total_tokens": 438616}
232
+ {"current_steps": 1155, "total_steps": 22320, "loss": 0.3124, "lr": 2.585125448028674e-05, "epoch": 1.0349462365591398, "percentage": 5.17, "elapsed_time": "0:02:49", "remaining_time": "0:51:40", "throughput": 2603.27, "total_tokens": 440536}
233
+ {"current_steps": 1160, "total_steps": 22320, "loss": 0.2793, "lr": 2.596326164874552e-05, "epoch": 1.039426523297491, "percentage": 5.2, "elapsed_time": "0:02:49", "remaining_time": "0:51:38", "throughput": 2603.95, "total_tokens": 442360}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ab567fd1190c431180c1f5c15e3c6a411afa5832e7e4f8b6ee5778c9fa6976
3
+ size 6417