rbelanec commited on
Commit
fed276c
·
verified ·
1 Parent(s): e40c786

Training in progress, step 1924

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
4
+ "inference_mode": true,
5
+ "modules_to_save": null,
6
+ "num_attention_heads": 32,
7
+ "num_layers": 32,
8
+ "num_transformer_submodules": 1,
9
+ "num_virtual_tokens": 100,
10
+ "peft_type": "PROMPT_TUNING",
11
+ "prompt_tuning_init": "RANDOM",
12
+ "prompt_tuning_init_text": null,
13
+ "revision": null,
14
+ "task_type": "CAUSAL_LM",
15
+ "token_dim": 4096,
16
+ "tokenizer_kwargs": null,
17
+ "tokenizer_name_or_path": null
18
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b03e4f69e07485b37ade3da5c0e482a9760259f59deb60e0b67a78324aa9f51
3
+ size 819328
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c1dcab308e7cf5970ea38815e0a62887d705c5b436f869ca27a5dcdd40c36a6
3
+ size 17210148
tokenizer_config.json ADDED
@@ -0,0 +1,2077 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|eom_id|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "<|eom_id|>"
2062
+ ],
2063
+ "bos_token": "<|begin_of_text|>",
2064
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2065
+ "clean_up_tokenization_spaces": true,
2066
+ "eos_token": "<|eot_id|>",
2067
+ "extra_special_tokens": {},
2068
+ "model_input_names": [
2069
+ "input_ids",
2070
+ "attention_mask"
2071
+ ],
2072
+ "model_max_length": 1000000000000000019884624838656,
2073
+ "pad_token": "<|eot_id|>",
2074
+ "padding_side": "right",
2075
+ "split_special_tokens": false,
2076
+ "tokenizer_class": "PreTrainedTokenizer"
2077
+ }
train.yaml ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ seed: 456
2
+
3
+ ### model
4
+ model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
5
+ trust_remote_code: true
6
+ flash_attn: auto
7
+ use_cache: false
8
+
9
+ ### method
10
+ stage: sft
11
+ do_train: true
12
+ finetuning_type: prompt-tuning
13
+ task_type: CAUSAL_LM
14
+ num_virtual_tokens: 100
15
+
16
+ ### dataset
17
+ dataset: cola
18
+ template: llama3
19
+ cutoff_len: 2048
20
+ overwrite_cache: true
21
+ preprocessing_num_workers: 8
22
+ dataloader_num_workers: 2
23
+ packing: false
24
+
25
+ ### output
26
+ output_dir: saves_multiple/prompt-tuning/llama-3-8b-instruct/train_cola_456_1760637816
27
+ logging_steps: 5
28
+ save_steps: 0.05
29
+ overwrite_output_dir: true
30
+ save_only_model: false
31
+ plot_loss: true
32
+ include_num_input_tokens_seen: true
33
+ push_to_hub: true
34
+ push_to_hub_organization: rbelanec
35
+ load_best_model_at_end: true
36
+ save_total_limit: 1
37
+
38
+ ### train
39
+ per_device_train_batch_size: 4
40
+ learning_rate: 3.0e-2
41
+ num_train_epochs: 20
42
+ weight_decay: 1.0e-5
43
+ lr_scheduler_type: cosine
44
+ bf16: true
45
+ ddp_timeout: 180000000
46
+ resume_from_checkpoint: null
47
+ warmup_ratio: 0.1
48
+ optim: adamw_torch
49
+ report_to:
50
+ - wandb
51
+ run_name: prompt-tuning_llama-3-8b-instruct_train_cola_456_1760637816
52
+
53
+ ### eval
54
+ per_device_eval_batch_size: 4
55
+ eval_strategy: steps
56
+ eval_steps: 0.05
57
+ val_size: 0.1
trainer_log.jsonl ADDED
@@ -0,0 +1,400 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 38480, "loss": 1.6191, "lr": 3.118503118503119e-05, "epoch": 0.002598752598752599, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "2:16:47", "throughput": 900.04, "total_tokens": 960}
2
+ {"current_steps": 10, "total_steps": 38480, "loss": 0.8357, "lr": 7.016632016632016e-05, "epoch": 0.005197505197505198, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:51:19", "throughput": 1124.22, "total_tokens": 1952}
3
+ {"current_steps": 15, "total_steps": 38480, "loss": 0.5563, "lr": 0.00010914760914760915, "epoch": 0.007796257796257797, "percentage": 0.04, "elapsed_time": "0:00:02", "remaining_time": "1:42:54", "throughput": 1236.02, "total_tokens": 2976}
4
+ {"current_steps": 20, "total_steps": 38480, "loss": 0.6886, "lr": 0.00014812889812889813, "epoch": 0.010395010395010396, "percentage": 0.05, "elapsed_time": "0:00:03", "remaining_time": "1:38:41", "throughput": 1288.64, "total_tokens": 3968}
5
+ {"current_steps": 25, "total_steps": 38480, "loss": 0.4828, "lr": 0.00018711018711018712, "epoch": 0.012993762993762994, "percentage": 0.06, "elapsed_time": "0:00:03", "remaining_time": "1:35:58", "throughput": 1299.28, "total_tokens": 4864}
6
+ {"current_steps": 30, "total_steps": 38480, "loss": 0.1926, "lr": 0.0002260914760914761, "epoch": 0.015592515592515593, "percentage": 0.08, "elapsed_time": "0:00:04", "remaining_time": "1:34:13", "throughput": 1313.15, "total_tokens": 5792}
7
+ {"current_steps": 35, "total_steps": 38480, "loss": 0.3334, "lr": 0.00026507276507276505, "epoch": 0.018191268191268192, "percentage": 0.09, "elapsed_time": "0:00:05", "remaining_time": "1:33:01", "throughput": 1334.96, "total_tokens": 6784}
8
+ {"current_steps": 40, "total_steps": 38480, "loss": 0.1662, "lr": 0.00030405405405405404, "epoch": 0.02079002079002079, "percentage": 0.1, "elapsed_time": "0:00:05", "remaining_time": "1:32:21", "throughput": 1348.54, "total_tokens": 7776}
9
+ {"current_steps": 45, "total_steps": 38480, "loss": 0.1755, "lr": 0.000343035343035343, "epoch": 0.02338877338877339, "percentage": 0.12, "elapsed_time": "0:00:06", "remaining_time": "1:31:35", "throughput": 1357.72, "total_tokens": 8736}
10
+ {"current_steps": 50, "total_steps": 38480, "loss": 0.381, "lr": 0.000382016632016632, "epoch": 0.02598752598752599, "percentage": 0.13, "elapsed_time": "0:00:07", "remaining_time": "1:30:58", "throughput": 1360.79, "total_tokens": 9664}
11
+ {"current_steps": 55, "total_steps": 38480, "loss": 0.3162, "lr": 0.000420997920997921, "epoch": 0.028586278586278588, "percentage": 0.14, "elapsed_time": "0:00:07", "remaining_time": "1:30:30", "throughput": 1370.8, "total_tokens": 10656}
12
+ {"current_steps": 60, "total_steps": 38480, "loss": 0.2817, "lr": 0.00045997920997920997, "epoch": 0.031185031185031187, "percentage": 0.16, "elapsed_time": "0:00:08", "remaining_time": "1:30:03", "throughput": 1372.66, "total_tokens": 11584}
13
+ {"current_steps": 65, "total_steps": 38480, "loss": 0.2317, "lr": 0.000498960498960499, "epoch": 0.033783783783783786, "percentage": 0.17, "elapsed_time": "0:00:09", "remaining_time": "1:29:39", "throughput": 1370.98, "total_tokens": 12480}
14
+ {"current_steps": 70, "total_steps": 38480, "loss": 0.1814, "lr": 0.000537941787941788, "epoch": 0.036382536382536385, "percentage": 0.18, "elapsed_time": "0:00:09", "remaining_time": "1:29:19", "throughput": 1369.39, "total_tokens": 13376}
15
+ {"current_steps": 75, "total_steps": 38480, "loss": 0.2537, "lr": 0.000576923076923077, "epoch": 0.03898128898128898, "percentage": 0.19, "elapsed_time": "0:00:10", "remaining_time": "1:29:02", "throughput": 1367.95, "total_tokens": 14272}
16
+ {"current_steps": 80, "total_steps": 38480, "loss": 0.369, "lr": 0.000615904365904366, "epoch": 0.04158004158004158, "percentage": 0.21, "elapsed_time": "0:00:11", "remaining_time": "1:28:48", "throughput": 1369.33, "total_tokens": 15200}
17
+ {"current_steps": 85, "total_steps": 38480, "loss": 0.8154, "lr": 0.0006548856548856549, "epoch": 0.04417879417879418, "percentage": 0.22, "elapsed_time": "0:00:11", "remaining_time": "1:28:35", "throughput": 1370.5, "total_tokens": 16128}
18
+ {"current_steps": 90, "total_steps": 38480, "loss": 0.2604, "lr": 0.0006938669438669439, "epoch": 0.04677754677754678, "percentage": 0.23, "elapsed_time": "0:00:12", "remaining_time": "1:28:24", "throughput": 1374.07, "total_tokens": 17088}
19
+ {"current_steps": 95, "total_steps": 38480, "loss": 0.2351, "lr": 0.0007328482328482329, "epoch": 0.04937629937629938, "percentage": 0.25, "elapsed_time": "0:00:13", "remaining_time": "1:28:14", "throughput": 1374.95, "total_tokens": 18016}
20
+ {"current_steps": 100, "total_steps": 38480, "loss": 0.2478, "lr": 0.0007718295218295219, "epoch": 0.05197505197505198, "percentage": 0.26, "elapsed_time": "0:00:13", "remaining_time": "1:28:05", "throughput": 1377.85, "total_tokens": 18976}
21
+ {"current_steps": 105, "total_steps": 38480, "loss": 0.1882, "lr": 0.0008108108108108109, "epoch": 0.05457380457380458, "percentage": 0.27, "elapsed_time": "0:00:14", "remaining_time": "1:27:57", "throughput": 1380.48, "total_tokens": 19936}
22
+ {"current_steps": 110, "total_steps": 38480, "loss": 1.4402, "lr": 0.0008497920997920999, "epoch": 0.057172557172557176, "percentage": 0.29, "elapsed_time": "0:00:15", "remaining_time": "1:27:51", "throughput": 1386.87, "total_tokens": 20960}
23
+ {"current_steps": 115, "total_steps": 38480, "loss": 1.1043, "lr": 0.0008887733887733887, "epoch": 0.059771309771309775, "percentage": 0.3, "elapsed_time": "0:00:15", "remaining_time": "1:27:46", "throughput": 1390.69, "total_tokens": 21952}
24
+ {"current_steps": 120, "total_steps": 38480, "loss": 2.996, "lr": 0.0009277546777546777, "epoch": 0.062370062370062374, "percentage": 0.31, "elapsed_time": "0:00:16", "remaining_time": "1:27:45", "throughput": 1394.92, "total_tokens": 22976}
25
+ {"current_steps": 125, "total_steps": 38480, "loss": 0.6608, "lr": 0.0009667359667359667, "epoch": 0.06496881496881497, "percentage": 0.32, "elapsed_time": "0:00:17", "remaining_time": "1:27:38", "throughput": 1396.58, "total_tokens": 23936}
26
+ {"current_steps": 130, "total_steps": 38480, "loss": 0.3449, "lr": 0.0010057172557172557, "epoch": 0.06756756756756757, "percentage": 0.34, "elapsed_time": "0:00:17", "remaining_time": "1:27:33", "throughput": 1398.1, "total_tokens": 24896}
27
+ {"current_steps": 135, "total_steps": 38480, "loss": 0.5803, "lr": 0.0010446985446985447, "epoch": 0.07016632016632017, "percentage": 0.35, "elapsed_time": "0:00:18", "remaining_time": "1:27:27", "throughput": 1397.86, "total_tokens": 25824}
28
+ {"current_steps": 140, "total_steps": 38480, "loss": 0.5772, "lr": 0.0010836798336798337, "epoch": 0.07276507276507277, "percentage": 0.36, "elapsed_time": "0:00:19", "remaining_time": "1:27:21", "throughput": 1396.07, "total_tokens": 26720}
29
+ {"current_steps": 145, "total_steps": 38480, "loss": 0.3451, "lr": 0.0011226611226611226, "epoch": 0.07536382536382537, "percentage": 0.38, "elapsed_time": "0:00:19", "remaining_time": "1:27:15", "throughput": 1393.0, "total_tokens": 27584}
30
+ {"current_steps": 150, "total_steps": 38480, "loss": 0.8536, "lr": 0.0011616424116424116, "epoch": 0.07796257796257797, "percentage": 0.39, "elapsed_time": "0:00:20", "remaining_time": "1:27:11", "throughput": 1395.9, "total_tokens": 28576}
31
+ {"current_steps": 155, "total_steps": 38480, "loss": 0.4389, "lr": 0.0012006237006237006, "epoch": 0.08056133056133057, "percentage": 0.4, "elapsed_time": "0:00:21", "remaining_time": "1:27:07", "throughput": 1397.16, "total_tokens": 29536}
32
+ {"current_steps": 160, "total_steps": 38480, "loss": 0.537, "lr": 0.0012396049896049896, "epoch": 0.08316008316008316, "percentage": 0.42, "elapsed_time": "0:00:21", "remaining_time": "1:27:02", "throughput": 1395.62, "total_tokens": 30432}
33
+ {"current_steps": 165, "total_steps": 38480, "loss": 0.7026, "lr": 0.0012785862785862786, "epoch": 0.08575883575883576, "percentage": 0.43, "elapsed_time": "0:00:22", "remaining_time": "1:26:58", "throughput": 1395.5, "total_tokens": 31360}
34
+ {"current_steps": 170, "total_steps": 38480, "loss": 0.2963, "lr": 0.0013175675675675676, "epoch": 0.08835758835758836, "percentage": 0.44, "elapsed_time": "0:00:23", "remaining_time": "1:26:54", "throughput": 1394.12, "total_tokens": 32256}
35
+ {"current_steps": 175, "total_steps": 38480, "loss": 0.5182, "lr": 0.0013565488565488565, "epoch": 0.09095634095634096, "percentage": 0.45, "elapsed_time": "0:00:23", "remaining_time": "1:26:48", "throughput": 1391.74, "total_tokens": 33120}
36
+ {"current_steps": 180, "total_steps": 38480, "loss": 0.6989, "lr": 0.0013955301455301455, "epoch": 0.09355509355509356, "percentage": 0.47, "elapsed_time": "0:00:24", "remaining_time": "1:26:45", "throughput": 1391.76, "total_tokens": 34048}
37
+ {"current_steps": 185, "total_steps": 38480, "loss": 0.7271, "lr": 0.0014345114345114345, "epoch": 0.09615384615384616, "percentage": 0.48, "elapsed_time": "0:00:25", "remaining_time": "1:26:41", "throughput": 1391.78, "total_tokens": 34976}
38
+ {"current_steps": 190, "total_steps": 38480, "loss": 0.4156, "lr": 0.0014734927234927235, "epoch": 0.09875259875259876, "percentage": 0.49, "elapsed_time": "0:00:25", "remaining_time": "1:26:39", "throughput": 1394.17, "total_tokens": 35968}
39
+ {"current_steps": 195, "total_steps": 38480, "loss": 0.6335, "lr": 0.0015124740124740125, "epoch": 0.10135135135135136, "percentage": 0.51, "elapsed_time": "0:00:26", "remaining_time": "1:26:36", "throughput": 1396.36, "total_tokens": 36960}
40
+ {"current_steps": 200, "total_steps": 38480, "loss": 0.4673, "lr": 0.0015514553014553015, "epoch": 0.10395010395010396, "percentage": 0.52, "elapsed_time": "0:00:27", "remaining_time": "1:26:33", "throughput": 1396.32, "total_tokens": 37888}
41
+ {"current_steps": 205, "total_steps": 38480, "loss": 0.3669, "lr": 0.0015904365904365904, "epoch": 0.10654885654885655, "percentage": 0.53, "elapsed_time": "0:00:27", "remaining_time": "1:26:31", "throughput": 1398.39, "total_tokens": 38880}
42
+ {"current_steps": 210, "total_steps": 38480, "loss": 0.3005, "lr": 0.0016294178794178794, "epoch": 0.10914760914760915, "percentage": 0.55, "elapsed_time": "0:00:28", "remaining_time": "1:26:29", "throughput": 1399.07, "total_tokens": 39840}
43
+ {"current_steps": 215, "total_steps": 38480, "loss": 0.3239, "lr": 0.0016683991683991684, "epoch": 0.11174636174636175, "percentage": 0.56, "elapsed_time": "0:00:29", "remaining_time": "1:26:26", "throughput": 1397.89, "total_tokens": 40736}
44
+ {"current_steps": 220, "total_steps": 38480, "loss": 0.4084, "lr": 0.0017073804573804574, "epoch": 0.11434511434511435, "percentage": 0.57, "elapsed_time": "0:00:29", "remaining_time": "1:26:25", "throughput": 1399.56, "total_tokens": 41728}
45
+ {"current_steps": 225, "total_steps": 38480, "loss": 0.4402, "lr": 0.0017463617463617464, "epoch": 0.11694386694386695, "percentage": 0.58, "elapsed_time": "0:00:30", "remaining_time": "1:26:23", "throughput": 1399.27, "total_tokens": 42656}
46
+ {"current_steps": 230, "total_steps": 38480, "loss": 0.5, "lr": 0.0017853430353430354, "epoch": 0.11954261954261955, "percentage": 0.6, "elapsed_time": "0:00:31", "remaining_time": "1:26:20", "throughput": 1400.08, "total_tokens": 43616}
47
+ {"current_steps": 235, "total_steps": 38480, "loss": 0.4304, "lr": 0.0018243243243243243, "epoch": 0.12214137214137215, "percentage": 0.61, "elapsed_time": "0:00:31", "remaining_time": "1:26:18", "throughput": 1399.91, "total_tokens": 44544}
48
+ {"current_steps": 240, "total_steps": 38480, "loss": 0.435, "lr": 0.0018633056133056133, "epoch": 0.12474012474012475, "percentage": 0.62, "elapsed_time": "0:00:32", "remaining_time": "1:26:15", "throughput": 1398.79, "total_tokens": 45440}
49
+ {"current_steps": 245, "total_steps": 38480, "loss": 0.5094, "lr": 0.0019022869022869023, "epoch": 0.12733887733887733, "percentage": 0.64, "elapsed_time": "0:00:33", "remaining_time": "1:26:13", "throughput": 1399.64, "total_tokens": 46400}
50
+ {"current_steps": 250, "total_steps": 38480, "loss": 0.322, "lr": 0.001941268191268191, "epoch": 0.12993762993762994, "percentage": 0.65, "elapsed_time": "0:00:33", "remaining_time": "1:26:11", "throughput": 1400.4, "total_tokens": 47360}
51
+ {"current_steps": 255, "total_steps": 38480, "loss": 0.3769, "lr": 0.0019802494802494803, "epoch": 0.13253638253638253, "percentage": 0.66, "elapsed_time": "0:00:34", "remaining_time": "1:26:09", "throughput": 1401.98, "total_tokens": 48352}
52
+ {"current_steps": 260, "total_steps": 38480, "loss": 0.3452, "lr": 0.0020192307692307693, "epoch": 0.13513513513513514, "percentage": 0.68, "elapsed_time": "0:00:35", "remaining_time": "1:26:07", "throughput": 1401.81, "total_tokens": 49280}
53
+ {"current_steps": 265, "total_steps": 38480, "loss": 0.3785, "lr": 0.0020582120582120582, "epoch": 0.13773388773388773, "percentage": 0.69, "elapsed_time": "0:00:35", "remaining_time": "1:26:05", "throughput": 1401.69, "total_tokens": 50208}
54
+ {"current_steps": 270, "total_steps": 38480, "loss": 0.2968, "lr": 0.0020971933471933472, "epoch": 0.14033264033264034, "percentage": 0.7, "elapsed_time": "0:00:36", "remaining_time": "1:26:03", "throughput": 1401.45, "total_tokens": 51136}
55
+ {"current_steps": 275, "total_steps": 38480, "loss": 0.3263, "lr": 0.002136174636174636, "epoch": 0.14293139293139293, "percentage": 0.71, "elapsed_time": "0:00:37", "remaining_time": "1:26:02", "throughput": 1401.12, "total_tokens": 52064}
56
+ {"current_steps": 280, "total_steps": 38480, "loss": 0.2634, "lr": 0.002175155925155925, "epoch": 0.14553014553014554, "percentage": 0.73, "elapsed_time": "0:00:37", "remaining_time": "1:26:00", "throughput": 1401.73, "total_tokens": 53024}
57
+ {"current_steps": 285, "total_steps": 38480, "loss": 0.2889, "lr": 0.002214137214137214, "epoch": 0.14812889812889812, "percentage": 0.74, "elapsed_time": "0:00:38", "remaining_time": "1:25:59", "throughput": 1402.21, "total_tokens": 53984}
58
+ {"current_steps": 290, "total_steps": 38480, "loss": 0.28, "lr": 0.002253118503118503, "epoch": 0.15072765072765074, "percentage": 0.75, "elapsed_time": "0:00:39", "remaining_time": "1:25:58", "throughput": 1403.47, "total_tokens": 54976}
59
+ {"current_steps": 295, "total_steps": 38480, "loss": 0.3535, "lr": 0.002292099792099792, "epoch": 0.15332640332640332, "percentage": 0.77, "elapsed_time": "0:00:39", "remaining_time": "1:25:56", "throughput": 1403.23, "total_tokens": 55904}
60
+ {"current_steps": 300, "total_steps": 38480, "loss": 0.2127, "lr": 0.002331081081081081, "epoch": 0.15592515592515593, "percentage": 0.78, "elapsed_time": "0:00:40", "remaining_time": "1:25:55", "throughput": 1403.74, "total_tokens": 56864}
61
+ {"current_steps": 305, "total_steps": 38480, "loss": 0.3159, "lr": 0.00237006237006237, "epoch": 0.15852390852390852, "percentage": 0.79, "elapsed_time": "0:00:41", "remaining_time": "1:25:53", "throughput": 1402.84, "total_tokens": 57760}
62
+ {"current_steps": 310, "total_steps": 38480, "loss": 0.3835, "lr": 0.002409043659043659, "epoch": 0.16112266112266113, "percentage": 0.81, "elapsed_time": "0:00:41", "remaining_time": "1:25:52", "throughput": 1403.3, "total_tokens": 58720}
63
+ {"current_steps": 315, "total_steps": 38480, "loss": 0.4242, "lr": 0.002448024948024948, "epoch": 0.16372141372141372, "percentage": 0.82, "elapsed_time": "0:00:42", "remaining_time": "1:25:50", "throughput": 1403.79, "total_tokens": 59680}
64
+ {"current_steps": 320, "total_steps": 38480, "loss": 0.3357, "lr": 0.002487006237006237, "epoch": 0.16632016632016633, "percentage": 0.83, "elapsed_time": "0:00:43", "remaining_time": "1:25:49", "throughput": 1405.0, "total_tokens": 60672}
65
+ {"current_steps": 325, "total_steps": 38480, "loss": 0.3035, "lr": 0.002525987525987526, "epoch": 0.16891891891891891, "percentage": 0.84, "elapsed_time": "0:00:43", "remaining_time": "1:25:47", "throughput": 1404.82, "total_tokens": 61600}
66
+ {"current_steps": 330, "total_steps": 38480, "loss": 0.3055, "lr": 0.002564968814968815, "epoch": 0.17151767151767153, "percentage": 0.86, "elapsed_time": "0:00:44", "remaining_time": "1:25:46", "throughput": 1404.63, "total_tokens": 62528}
67
+ {"current_steps": 335, "total_steps": 38480, "loss": 0.3057, "lr": 0.002603950103950104, "epoch": 0.1741164241164241, "percentage": 0.87, "elapsed_time": "0:00:45", "remaining_time": "1:25:44", "throughput": 1403.72, "total_tokens": 63424}
68
+ {"current_steps": 340, "total_steps": 38480, "loss": 0.2424, "lr": 0.0026429313929313926, "epoch": 0.17671517671517672, "percentage": 0.88, "elapsed_time": "0:00:45", "remaining_time": "1:25:43", "throughput": 1404.17, "total_tokens": 64384}
69
+ {"current_steps": 345, "total_steps": 38480, "loss": 0.3878, "lr": 0.002681912681912682, "epoch": 0.1793139293139293, "percentage": 0.9, "elapsed_time": "0:00:46", "remaining_time": "1:25:42", "throughput": 1405.23, "total_tokens": 65376}
70
+ {"current_steps": 350, "total_steps": 38480, "loss": 0.3039, "lr": 0.0027208939708939705, "epoch": 0.18191268191268192, "percentage": 0.91, "elapsed_time": "0:00:47", "remaining_time": "1:25:41", "throughput": 1405.03, "total_tokens": 66304}
71
+ {"current_steps": 355, "total_steps": 38480, "loss": 0.316, "lr": 0.00275987525987526, "epoch": 0.1845114345114345, "percentage": 0.92, "elapsed_time": "0:00:47", "remaining_time": "1:25:39", "throughput": 1404.88, "total_tokens": 67232}
72
+ {"current_steps": 360, "total_steps": 38480, "loss": 0.2952, "lr": 0.0027988565488565485, "epoch": 0.18711018711018712, "percentage": 0.94, "elapsed_time": "0:00:48", "remaining_time": "1:25:38", "throughput": 1404.68, "total_tokens": 68160}
73
+ {"current_steps": 365, "total_steps": 38480, "loss": 0.2692, "lr": 0.002837837837837838, "epoch": 0.1897089397089397, "percentage": 0.95, "elapsed_time": "0:00:49", "remaining_time": "1:25:36", "throughput": 1403.9, "total_tokens": 69056}
74
+ {"current_steps": 370, "total_steps": 38480, "loss": 0.389, "lr": 0.0028768191268191265, "epoch": 0.19230769230769232, "percentage": 0.96, "elapsed_time": "0:00:49", "remaining_time": "1:25:35", "throughput": 1405.49, "total_tokens": 70080}
75
+ {"current_steps": 375, "total_steps": 38480, "loss": 0.2915, "lr": 0.002915800415800416, "epoch": 0.1949064449064449, "percentage": 0.97, "elapsed_time": "0:00:50", "remaining_time": "1:25:36", "throughput": 1405.47, "total_tokens": 71040}
76
+ {"current_steps": 380, "total_steps": 38480, "loss": 0.343, "lr": 0.0029547817047817044, "epoch": 0.19750519750519752, "percentage": 0.99, "elapsed_time": "0:00:51", "remaining_time": "1:25:34", "throughput": 1405.29, "total_tokens": 71968}
77
+ {"current_steps": 385, "total_steps": 38480, "loss": 0.2772, "lr": 0.002993762993762994, "epoch": 0.2001039501039501, "percentage": 1.0, "elapsed_time": "0:00:51", "remaining_time": "1:25:33", "throughput": 1405.13, "total_tokens": 72896}
78
+ {"current_steps": 390, "total_steps": 38480, "loss": 0.3701, "lr": 0.0030327442827442824, "epoch": 0.20270270270270271, "percentage": 1.01, "elapsed_time": "0:00:52", "remaining_time": "1:25:32", "throughput": 1405.53, "total_tokens": 73856}
79
+ {"current_steps": 395, "total_steps": 38480, "loss": 0.2957, "lr": 0.003071725571725572, "epoch": 0.2053014553014553, "percentage": 1.03, "elapsed_time": "0:00:53", "remaining_time": "1:25:30", "throughput": 1405.89, "total_tokens": 74816}
80
+ {"current_steps": 400, "total_steps": 38480, "loss": 0.302, "lr": 0.0031107068607068604, "epoch": 0.2079002079002079, "percentage": 1.04, "elapsed_time": "0:00:53", "remaining_time": "1:25:29", "throughput": 1406.27, "total_tokens": 75776}
81
+ {"current_steps": 405, "total_steps": 38480, "loss": 0.2757, "lr": 0.0031496881496881498, "epoch": 0.2104989604989605, "percentage": 1.05, "elapsed_time": "0:00:54", "remaining_time": "1:25:28", "throughput": 1406.11, "total_tokens": 76704}
82
+ {"current_steps": 410, "total_steps": 38480, "loss": 0.2033, "lr": 0.0031886694386694383, "epoch": 0.2130977130977131, "percentage": 1.07, "elapsed_time": "0:00:55", "remaining_time": "1:25:26", "throughput": 1404.83, "total_tokens": 77568}
83
+ {"current_steps": 415, "total_steps": 38480, "loss": 0.3129, "lr": 0.0032276507276507277, "epoch": 0.2156964656964657, "percentage": 1.08, "elapsed_time": "0:00:55", "remaining_time": "1:25:25", "throughput": 1404.65, "total_tokens": 78496}
84
+ {"current_steps": 420, "total_steps": 38480, "loss": 0.2193, "lr": 0.0032666320166320163, "epoch": 0.2182952182952183, "percentage": 1.09, "elapsed_time": "0:00:56", "remaining_time": "1:25:24", "throughput": 1405.02, "total_tokens": 79456}
85
+ {"current_steps": 425, "total_steps": 38480, "loss": 0.2947, "lr": 0.0033056133056133057, "epoch": 0.2208939708939709, "percentage": 1.1, "elapsed_time": "0:00:57", "remaining_time": "1:25:23", "throughput": 1404.88, "total_tokens": 80384}
86
+ {"current_steps": 430, "total_steps": 38480, "loss": 0.2973, "lr": 0.0033445945945945943, "epoch": 0.2234927234927235, "percentage": 1.12, "elapsed_time": "0:00:57", "remaining_time": "1:25:21", "throughput": 1404.22, "total_tokens": 81280}
87
+ {"current_steps": 435, "total_steps": 38480, "loss": 0.2819, "lr": 0.0033835758835758837, "epoch": 0.2260914760914761, "percentage": 1.13, "elapsed_time": "0:00:58", "remaining_time": "1:25:21", "throughput": 1405.06, "total_tokens": 82272}
88
+ {"current_steps": 440, "total_steps": 38480, "loss": 0.1711, "lr": 0.0034225571725571722, "epoch": 0.2286902286902287, "percentage": 1.14, "elapsed_time": "0:00:59", "remaining_time": "1:25:20", "throughput": 1405.9, "total_tokens": 83264}
89
+ {"current_steps": 445, "total_steps": 38480, "loss": 0.3385, "lr": 0.0034615384615384616, "epoch": 0.2312889812889813, "percentage": 1.16, "elapsed_time": "0:00:59", "remaining_time": "1:25:19", "throughput": 1406.11, "total_tokens": 84224}
90
+ {"current_steps": 450, "total_steps": 38480, "loss": 0.1903, "lr": 0.00350051975051975, "epoch": 0.2338877338877339, "percentage": 1.17, "elapsed_time": "0:01:00", "remaining_time": "1:25:18", "throughput": 1405.94, "total_tokens": 85152}
91
+ {"current_steps": 455, "total_steps": 38480, "loss": 0.3401, "lr": 0.0035395010395010396, "epoch": 0.23648648648648649, "percentage": 1.18, "elapsed_time": "0:01:01", "remaining_time": "1:25:17", "throughput": 1405.8, "total_tokens": 86080}
92
+ {"current_steps": 460, "total_steps": 38480, "loss": 0.2671, "lr": 0.003578482328482328, "epoch": 0.2390852390852391, "percentage": 1.2, "elapsed_time": "0:01:01", "remaining_time": "1:25:16", "throughput": 1406.15, "total_tokens": 87040}
93
+ {"current_steps": 465, "total_steps": 38480, "loss": 0.2975, "lr": 0.0036174636174636176, "epoch": 0.24168399168399168, "percentage": 1.21, "elapsed_time": "0:01:02", "remaining_time": "1:25:15", "throughput": 1405.96, "total_tokens": 87968}
94
+ {"current_steps": 470, "total_steps": 38480, "loss": 0.3454, "lr": 0.003656444906444906, "epoch": 0.2442827442827443, "percentage": 1.22, "elapsed_time": "0:01:03", "remaining_time": "1:25:15", "throughput": 1406.91, "total_tokens": 88992}
95
+ {"current_steps": 475, "total_steps": 38480, "loss": 0.338, "lr": 0.0036954261954261955, "epoch": 0.24688149688149688, "percentage": 1.23, "elapsed_time": "0:01:03", "remaining_time": "1:25:14", "throughput": 1407.66, "total_tokens": 89984}
96
+ {"current_steps": 480, "total_steps": 38480, "loss": 0.2658, "lr": 0.003734407484407484, "epoch": 0.2494802494802495, "percentage": 1.25, "elapsed_time": "0:01:04", "remaining_time": "1:25:13", "throughput": 1408.88, "total_tokens": 91008}
97
+ {"current_steps": 485, "total_steps": 38480, "loss": 0.2347, "lr": 0.0037733887733887735, "epoch": 0.2520790020790021, "percentage": 1.26, "elapsed_time": "0:01:05", "remaining_time": "1:25:12", "throughput": 1409.62, "total_tokens": 92000}
98
+ {"current_steps": 490, "total_steps": 38480, "loss": 0.2922, "lr": 0.003812370062370062, "epoch": 0.25467775467775466, "percentage": 1.27, "elapsed_time": "0:01:05", "remaining_time": "1:25:11", "throughput": 1409.45, "total_tokens": 92928}
99
+ {"current_steps": 495, "total_steps": 38480, "loss": 0.2188, "lr": 0.003851351351351351, "epoch": 0.25727650727650725, "percentage": 1.29, "elapsed_time": "0:01:06", "remaining_time": "1:25:11", "throughput": 1410.55, "total_tokens": 93952}
100
+ {"current_steps": 500, "total_steps": 38480, "loss": 0.2472, "lr": 0.0038903326403326396, "epoch": 0.2598752598752599, "percentage": 1.3, "elapsed_time": "0:01:07", "remaining_time": "1:25:10", "throughput": 1410.35, "total_tokens": 94880}
101
+ {"current_steps": 505, "total_steps": 38480, "loss": 0.1924, "lr": 0.003929313929313929, "epoch": 0.2624740124740125, "percentage": 1.31, "elapsed_time": "0:01:07", "remaining_time": "1:25:08", "throughput": 1409.31, "total_tokens": 95744}
102
+ {"current_steps": 510, "total_steps": 38480, "loss": 0.2633, "lr": 0.003968295218295218, "epoch": 0.26507276507276506, "percentage": 1.33, "elapsed_time": "0:01:08", "remaining_time": "1:25:08", "throughput": 1409.27, "total_tokens": 96704}
103
+ {"current_steps": 515, "total_steps": 38480, "loss": 0.3097, "lr": 0.004007276507276507, "epoch": 0.26767151767151764, "percentage": 1.34, "elapsed_time": "0:01:09", "remaining_time": "1:25:08", "throughput": 1410.38, "total_tokens": 97728}
104
+ {"current_steps": 520, "total_steps": 38480, "loss": 0.3325, "lr": 0.004046257796257796, "epoch": 0.2702702702702703, "percentage": 1.35, "elapsed_time": "0:01:09", "remaining_time": "1:25:07", "throughput": 1410.59, "total_tokens": 98688}
105
+ {"current_steps": 525, "total_steps": 38480, "loss": 0.2991, "lr": 0.004085239085239085, "epoch": 0.27286902286902287, "percentage": 1.36, "elapsed_time": "0:01:10", "remaining_time": "1:25:06", "throughput": 1410.8, "total_tokens": 99648}
106
+ {"current_steps": 530, "total_steps": 38480, "loss": 0.2485, "lr": 0.004124220374220374, "epoch": 0.27546777546777546, "percentage": 1.38, "elapsed_time": "0:01:11", "remaining_time": "1:25:05", "throughput": 1410.18, "total_tokens": 100544}
107
+ {"current_steps": 535, "total_steps": 38480, "loss": 0.2732, "lr": 0.004163201663201663, "epoch": 0.27806652806652804, "percentage": 1.39, "elapsed_time": "0:01:11", "remaining_time": "1:25:04", "throughput": 1410.0, "total_tokens": 101472}
108
+ {"current_steps": 540, "total_steps": 38480, "loss": 0.2028, "lr": 0.004202182952182952, "epoch": 0.2806652806652807, "percentage": 1.4, "elapsed_time": "0:01:12", "remaining_time": "1:25:03", "throughput": 1409.81, "total_tokens": 102400}
109
+ {"current_steps": 545, "total_steps": 38480, "loss": 0.3245, "lr": 0.004241164241164241, "epoch": 0.28326403326403327, "percentage": 1.42, "elapsed_time": "0:01:13", "remaining_time": "1:25:02", "throughput": 1410.83, "total_tokens": 103424}
110
+ {"current_steps": 550, "total_steps": 38480, "loss": 0.3041, "lr": 0.00428014553014553, "epoch": 0.28586278586278585, "percentage": 1.43, "elapsed_time": "0:01:13", "remaining_time": "1:25:01", "throughput": 1411.45, "total_tokens": 104416}
111
+ {"current_steps": 555, "total_steps": 38480, "loss": 0.3074, "lr": 0.004319126819126819, "epoch": 0.28846153846153844, "percentage": 1.44, "elapsed_time": "0:01:14", "remaining_time": "1:25:00", "throughput": 1410.88, "total_tokens": 105312}
112
+ {"current_steps": 560, "total_steps": 38480, "loss": 0.2401, "lr": 0.004358108108108108, "epoch": 0.2910602910602911, "percentage": 1.46, "elapsed_time": "0:01:15", "remaining_time": "1:24:59", "throughput": 1411.47, "total_tokens": 106304}
113
+ {"current_steps": 565, "total_steps": 38480, "loss": 0.2378, "lr": 0.004397089397089397, "epoch": 0.29365904365904366, "percentage": 1.47, "elapsed_time": "0:01:15", "remaining_time": "1:24:58", "throughput": 1410.93, "total_tokens": 107200}
114
+ {"current_steps": 570, "total_steps": 38480, "loss": 0.2905, "lr": 0.004436070686070686, "epoch": 0.29625779625779625, "percentage": 1.48, "elapsed_time": "0:01:16", "remaining_time": "1:24:57", "throughput": 1411.15, "total_tokens": 108160}
115
+ {"current_steps": 575, "total_steps": 38480, "loss": 0.2302, "lr": 0.004475051975051975, "epoch": 0.29885654885654883, "percentage": 1.49, "elapsed_time": "0:01:17", "remaining_time": "1:24:56", "throughput": 1411.38, "total_tokens": 109120}
116
+ {"current_steps": 580, "total_steps": 38480, "loss": 0.2939, "lr": 0.004514033264033264, "epoch": 0.30145530145530147, "percentage": 1.51, "elapsed_time": "0:01:17", "remaining_time": "1:24:55", "throughput": 1411.97, "total_tokens": 110112}
117
+ {"current_steps": 585, "total_steps": 38480, "loss": 0.2933, "lr": 0.004553014553014553, "epoch": 0.30405405405405406, "percentage": 1.52, "elapsed_time": "0:01:18", "remaining_time": "1:24:55", "throughput": 1412.16, "total_tokens": 111072}
118
+ {"current_steps": 590, "total_steps": 38480, "loss": 0.2733, "lr": 0.004591995841995842, "epoch": 0.30665280665280664, "percentage": 1.53, "elapsed_time": "0:01:19", "remaining_time": "1:24:54", "throughput": 1412.37, "total_tokens": 112032}
119
+ {"current_steps": 595, "total_steps": 38480, "loss": 0.2897, "lr": 0.004630977130977131, "epoch": 0.3092515592515592, "percentage": 1.55, "elapsed_time": "0:01:19", "remaining_time": "1:24:53", "throughput": 1412.56, "total_tokens": 112992}
120
+ {"current_steps": 600, "total_steps": 38480, "loss": 0.2733, "lr": 0.00466995841995842, "epoch": 0.31185031185031187, "percentage": 1.56, "elapsed_time": "0:01:20", "remaining_time": "1:24:52", "throughput": 1413.12, "total_tokens": 113984}
121
+ {"current_steps": 605, "total_steps": 38480, "loss": 0.2701, "lr": 0.004708939708939709, "epoch": 0.31444906444906445, "percentage": 1.57, "elapsed_time": "0:01:21", "remaining_time": "1:24:51", "throughput": 1413.67, "total_tokens": 114976}
122
+ {"current_steps": 610, "total_steps": 38480, "loss": 0.2921, "lr": 0.004747920997920998, "epoch": 0.31704781704781704, "percentage": 1.59, "elapsed_time": "0:01:22", "remaining_time": "1:24:52", "throughput": 1415.37, "total_tokens": 116096}
123
+ {"current_steps": 615, "total_steps": 38480, "loss": 0.2924, "lr": 0.004786902286902287, "epoch": 0.3196465696465696, "percentage": 1.6, "elapsed_time": "0:01:22", "remaining_time": "1:24:51", "throughput": 1415.2, "total_tokens": 117024}
124
+ {"current_steps": 620, "total_steps": 38480, "loss": 0.3052, "lr": 0.004825883575883576, "epoch": 0.32224532224532226, "percentage": 1.61, "elapsed_time": "0:01:23", "remaining_time": "1:24:50", "throughput": 1415.38, "total_tokens": 117984}
125
+ {"current_steps": 625, "total_steps": 38480, "loss": 0.2763, "lr": 0.004864864864864865, "epoch": 0.32484407484407485, "percentage": 1.62, "elapsed_time": "0:01:24", "remaining_time": "1:24:49", "throughput": 1415.2, "total_tokens": 118912}
126
+ {"current_steps": 630, "total_steps": 38480, "loss": 1.1931, "lr": 0.004903846153846154, "epoch": 0.32744282744282743, "percentage": 1.64, "elapsed_time": "0:01:24", "remaining_time": "1:24:48", "throughput": 1415.04, "total_tokens": 119840}
127
+ {"current_steps": 635, "total_steps": 38480, "loss": 0.2738, "lr": 0.004942827442827443, "epoch": 0.33004158004158, "percentage": 1.65, "elapsed_time": "0:01:25", "remaining_time": "1:24:47", "throughput": 1414.86, "total_tokens": 120768}
128
+ {"current_steps": 640, "total_steps": 38480, "loss": 0.2866, "lr": 0.0049818087318087316, "epoch": 0.33264033264033266, "percentage": 1.66, "elapsed_time": "0:01:26", "remaining_time": "1:24:47", "throughput": 1415.82, "total_tokens": 121824}
129
+ {"current_steps": 645, "total_steps": 38480, "loss": 0.249, "lr": 0.0050207900207900205, "epoch": 0.33523908523908524, "percentage": 1.68, "elapsed_time": "0:01:26", "remaining_time": "1:24:46", "throughput": 1415.3, "total_tokens": 122720}
130
+ {"current_steps": 650, "total_steps": 38480, "loss": 0.2691, "lr": 0.0050597713097713095, "epoch": 0.33783783783783783, "percentage": 1.69, "elapsed_time": "0:01:27", "remaining_time": "1:24:45", "throughput": 1415.12, "total_tokens": 123648}
131
+ {"current_steps": 655, "total_steps": 38480, "loss": 0.2129, "lr": 0.0050987525987525985, "epoch": 0.3404365904365904, "percentage": 1.7, "elapsed_time": "0:01:28", "remaining_time": "1:24:44", "throughput": 1415.62, "total_tokens": 124640}
132
+ {"current_steps": 660, "total_steps": 38480, "loss": 0.1927, "lr": 0.0051377338877338875, "epoch": 0.34303534303534305, "percentage": 1.72, "elapsed_time": "0:01:28", "remaining_time": "1:24:43", "throughput": 1415.79, "total_tokens": 125600}
133
+ {"current_steps": 665, "total_steps": 38480, "loss": 0.2187, "lr": 0.0051767151767151765, "epoch": 0.34563409563409564, "percentage": 1.73, "elapsed_time": "0:01:29", "remaining_time": "1:24:42", "throughput": 1415.62, "total_tokens": 126528}
134
+ {"current_steps": 670, "total_steps": 38480, "loss": 0.3382, "lr": 0.0052156964656964655, "epoch": 0.3482328482328482, "percentage": 1.74, "elapsed_time": "0:01:30", "remaining_time": "1:24:41", "throughput": 1416.1, "total_tokens": 127520}
135
+ {"current_steps": 675, "total_steps": 38480, "loss": 0.2708, "lr": 0.0052546777546777544, "epoch": 0.3508316008316008, "percentage": 1.75, "elapsed_time": "0:01:30", "remaining_time": "1:24:40", "throughput": 1415.57, "total_tokens": 128416}
136
+ {"current_steps": 680, "total_steps": 38480, "loss": 0.2863, "lr": 0.005293659043659043, "epoch": 0.35343035343035345, "percentage": 1.77, "elapsed_time": "0:01:31", "remaining_time": "1:24:40", "throughput": 1416.31, "total_tokens": 129440}
137
+ {"current_steps": 685, "total_steps": 38480, "loss": 0.1828, "lr": 0.005332640332640332, "epoch": 0.35602910602910603, "percentage": 1.78, "elapsed_time": "0:01:32", "remaining_time": "1:24:39", "throughput": 1416.68, "total_tokens": 130432}
138
+ {"current_steps": 690, "total_steps": 38480, "loss": 0.2801, "lr": 0.005371621621621621, "epoch": 0.3586278586278586, "percentage": 1.79, "elapsed_time": "0:01:32", "remaining_time": "1:24:39", "throughput": 1416.8, "total_tokens": 131392}
139
+ {"current_steps": 695, "total_steps": 38480, "loss": 0.2957, "lr": 0.00541060291060291, "epoch": 0.3612266112266112, "percentage": 1.81, "elapsed_time": "0:01:33", "remaining_time": "1:24:38", "throughput": 1416.62, "total_tokens": 132320}
140
+ {"current_steps": 700, "total_steps": 38480, "loss": 0.3027, "lr": 0.005449584199584199, "epoch": 0.36382536382536385, "percentage": 1.82, "elapsed_time": "0:01:34", "remaining_time": "1:24:36", "throughput": 1415.5, "total_tokens": 133152}
141
+ {"current_steps": 705, "total_steps": 38480, "loss": 0.2779, "lr": 0.005488565488565488, "epoch": 0.36642411642411643, "percentage": 1.83, "elapsed_time": "0:01:34", "remaining_time": "1:24:36", "throughput": 1415.95, "total_tokens": 134144}
142
+ {"current_steps": 710, "total_steps": 38480, "loss": 0.2489, "lr": 0.005527546777546777, "epoch": 0.369022869022869, "percentage": 1.85, "elapsed_time": "0:01:35", "remaining_time": "1:24:35", "throughput": 1415.15, "total_tokens": 135008}
143
+ {"current_steps": 715, "total_steps": 38480, "loss": 0.1911, "lr": 0.005566528066528066, "epoch": 0.3716216216216216, "percentage": 1.86, "elapsed_time": "0:01:36", "remaining_time": "1:24:34", "throughput": 1414.98, "total_tokens": 135936}
144
+ {"current_steps": 720, "total_steps": 38480, "loss": 0.3137, "lr": 0.005605509355509355, "epoch": 0.37422037422037424, "percentage": 1.87, "elapsed_time": "0:01:36", "remaining_time": "1:24:33", "throughput": 1415.43, "total_tokens": 136928}
145
+ {"current_steps": 725, "total_steps": 38480, "loss": 0.2402, "lr": 0.005644490644490644, "epoch": 0.3768191268191268, "percentage": 1.88, "elapsed_time": "0:01:37", "remaining_time": "1:24:32", "throughput": 1415.58, "total_tokens": 137888}
146
+ {"current_steps": 730, "total_steps": 38480, "loss": 0.2124, "lr": 0.005683471933471933, "epoch": 0.3794178794178794, "percentage": 1.9, "elapsed_time": "0:01:38", "remaining_time": "1:24:31", "throughput": 1416.01, "total_tokens": 138880}
147
+ {"current_steps": 735, "total_steps": 38480, "loss": 0.2515, "lr": 0.005722453222453222, "epoch": 0.382016632016632, "percentage": 1.91, "elapsed_time": "0:01:38", "remaining_time": "1:24:31", "throughput": 1416.45, "total_tokens": 139872}
148
+ {"current_steps": 740, "total_steps": 38480, "loss": 0.2248, "lr": 0.005761434511434511, "epoch": 0.38461538461538464, "percentage": 1.92, "elapsed_time": "0:01:39", "remaining_time": "1:24:30", "throughput": 1415.96, "total_tokens": 140768}
149
+ {"current_steps": 745, "total_steps": 38480, "loss": 0.2872, "lr": 0.0058004158004158, "epoch": 0.3872141372141372, "percentage": 1.94, "elapsed_time": "0:01:40", "remaining_time": "1:24:29", "throughput": 1416.39, "total_tokens": 141760}
150
+ {"current_steps": 750, "total_steps": 38480, "loss": 0.286, "lr": 0.005839397089397089, "epoch": 0.3898128898128898, "percentage": 1.95, "elapsed_time": "0:01:40", "remaining_time": "1:24:28", "throughput": 1416.23, "total_tokens": 142688}
151
+ {"current_steps": 755, "total_steps": 38480, "loss": 0.7241, "lr": 0.005878378378378378, "epoch": 0.3924116424116424, "percentage": 1.96, "elapsed_time": "0:01:41", "remaining_time": "1:24:27", "throughput": 1416.64, "total_tokens": 143680}
152
+ {"current_steps": 760, "total_steps": 38480, "loss": 0.2459, "lr": 0.005917359667359667, "epoch": 0.39501039501039503, "percentage": 1.98, "elapsed_time": "0:01:42", "remaining_time": "1:24:27", "throughput": 1417.06, "total_tokens": 144672}
153
+ {"current_steps": 765, "total_steps": 38480, "loss": 0.2752, "lr": 0.005956340956340956, "epoch": 0.3976091476091476, "percentage": 1.99, "elapsed_time": "0:01:42", "remaining_time": "1:24:25", "throughput": 1416.31, "total_tokens": 145536}
154
+ {"current_steps": 770, "total_steps": 38480, "loss": 0.2658, "lr": 0.005995322245322245, "epoch": 0.4002079002079002, "percentage": 2.0, "elapsed_time": "0:01:43", "remaining_time": "1:24:25", "throughput": 1416.16, "total_tokens": 146464}
155
+ {"current_steps": 775, "total_steps": 38480, "loss": 0.3761, "lr": 0.006034303534303534, "epoch": 0.4028066528066528, "percentage": 2.01, "elapsed_time": "0:01:44", "remaining_time": "1:24:26", "throughput": 1416.71, "total_tokens": 147520}
156
+ {"current_steps": 780, "total_steps": 38480, "loss": 0.3304, "lr": 0.006073284823284823, "epoch": 0.40540540540540543, "percentage": 2.03, "elapsed_time": "0:01:44", "remaining_time": "1:24:25", "throughput": 1416.8, "total_tokens": 148480}
157
+ {"current_steps": 785, "total_steps": 38480, "loss": 0.3127, "lr": 0.006112266112266112, "epoch": 0.408004158004158, "percentage": 2.04, "elapsed_time": "0:01:45", "remaining_time": "1:24:24", "throughput": 1416.92, "total_tokens": 149440}
158
+ {"current_steps": 790, "total_steps": 38480, "loss": 0.295, "lr": 0.006151247401247401, "epoch": 0.4106029106029106, "percentage": 2.05, "elapsed_time": "0:01:46", "remaining_time": "1:24:23", "throughput": 1416.47, "total_tokens": 150336}
159
+ {"current_steps": 795, "total_steps": 38480, "loss": 0.2617, "lr": 0.00619022869022869, "epoch": 0.4132016632016632, "percentage": 2.07, "elapsed_time": "0:01:46", "remaining_time": "1:24:22", "throughput": 1416.04, "total_tokens": 151232}
160
+ {"current_steps": 800, "total_steps": 38480, "loss": 0.2545, "lr": 0.006229209979209979, "epoch": 0.4158004158004158, "percentage": 2.08, "elapsed_time": "0:01:47", "remaining_time": "1:24:21", "throughput": 1415.89, "total_tokens": 152160}
161
+ {"current_steps": 805, "total_steps": 38480, "loss": 0.2577, "lr": 0.006268191268191268, "epoch": 0.4183991683991684, "percentage": 2.09, "elapsed_time": "0:01:48", "remaining_time": "1:24:20", "throughput": 1416.0, "total_tokens": 153120}
162
+ {"current_steps": 810, "total_steps": 38480, "loss": 0.2703, "lr": 0.006307172557172557, "epoch": 0.420997920997921, "percentage": 2.1, "elapsed_time": "0:01:48", "remaining_time": "1:24:20", "throughput": 1416.39, "total_tokens": 154112}
163
+ {"current_steps": 815, "total_steps": 38480, "loss": 0.2316, "lr": 0.006346153846153846, "epoch": 0.4235966735966736, "percentage": 2.12, "elapsed_time": "0:01:49", "remaining_time": "1:24:19", "throughput": 1415.97, "total_tokens": 155008}
164
+ {"current_steps": 820, "total_steps": 38480, "loss": 0.2914, "lr": 0.006385135135135135, "epoch": 0.4261954261954262, "percentage": 2.13, "elapsed_time": "0:01:50", "remaining_time": "1:24:18", "throughput": 1416.35, "total_tokens": 156000}
165
+ {"current_steps": 825, "total_steps": 38480, "loss": 0.208, "lr": 0.006424116424116424, "epoch": 0.4287941787941788, "percentage": 2.14, "elapsed_time": "0:01:50", "remaining_time": "1:24:17", "throughput": 1416.2, "total_tokens": 156928}
166
+ {"current_steps": 830, "total_steps": 38480, "loss": 0.272, "lr": 0.006463097713097713, "epoch": 0.4313929313929314, "percentage": 2.16, "elapsed_time": "0:01:51", "remaining_time": "1:24:16", "throughput": 1416.32, "total_tokens": 157888}
167
+ {"current_steps": 835, "total_steps": 38480, "loss": 0.2477, "lr": 0.006502079002079002, "epoch": 0.433991683991684, "percentage": 2.17, "elapsed_time": "0:01:52", "remaining_time": "1:24:15", "throughput": 1416.44, "total_tokens": 158848}
168
+ {"current_steps": 840, "total_steps": 38480, "loss": 0.3256, "lr": 0.006541060291060291, "epoch": 0.4365904365904366, "percentage": 2.18, "elapsed_time": "0:01:52", "remaining_time": "1:24:15", "throughput": 1416.3, "total_tokens": 159776}
169
+ {"current_steps": 845, "total_steps": 38480, "loss": 2.3466, "lr": 0.00658004158004158, "epoch": 0.4391891891891892, "percentage": 2.2, "elapsed_time": "0:01:53", "remaining_time": "1:24:15", "throughput": 1416.73, "total_tokens": 160800}
170
+ {"current_steps": 850, "total_steps": 38480, "loss": 0.3165, "lr": 0.006619022869022869, "epoch": 0.4417879417879418, "percentage": 2.21, "elapsed_time": "0:01:54", "remaining_time": "1:24:14", "throughput": 1417.09, "total_tokens": 161792}
171
+ {"current_steps": 855, "total_steps": 38480, "loss": 0.2626, "lr": 0.006658004158004158, "epoch": 0.44438669438669437, "percentage": 2.22, "elapsed_time": "0:01:54", "remaining_time": "1:24:13", "throughput": 1416.92, "total_tokens": 162720}
172
+ {"current_steps": 860, "total_steps": 38480, "loss": 0.2511, "lr": 0.006696985446985447, "epoch": 0.446985446985447, "percentage": 2.23, "elapsed_time": "0:01:55", "remaining_time": "1:24:12", "throughput": 1417.03, "total_tokens": 163680}
173
+ {"current_steps": 865, "total_steps": 38480, "loss": 0.3811, "lr": 0.006735966735966736, "epoch": 0.4495841995841996, "percentage": 2.25, "elapsed_time": "0:01:56", "remaining_time": "1:24:12", "throughput": 1417.39, "total_tokens": 164672}
174
+ {"current_steps": 870, "total_steps": 38480, "loss": 0.308, "lr": 0.006774948024948025, "epoch": 0.4521829521829522, "percentage": 2.26, "elapsed_time": "0:01:56", "remaining_time": "1:24:11", "throughput": 1417.01, "total_tokens": 165568}
175
+ {"current_steps": 875, "total_steps": 38480, "loss": 0.2922, "lr": 0.006813929313929314, "epoch": 0.45478170478170477, "percentage": 2.27, "elapsed_time": "0:01:57", "remaining_time": "1:24:10", "throughput": 1416.87, "total_tokens": 166496}
176
+ {"current_steps": 880, "total_steps": 38480, "loss": 0.3053, "lr": 0.006852910602910603, "epoch": 0.4573804573804574, "percentage": 2.29, "elapsed_time": "0:01:58", "remaining_time": "1:24:09", "throughput": 1416.98, "total_tokens": 167456}
177
+ {"current_steps": 885, "total_steps": 38480, "loss": 0.25, "lr": 0.006891891891891892, "epoch": 0.45997920997921, "percentage": 2.3, "elapsed_time": "0:01:58", "remaining_time": "1:24:08", "throughput": 1417.08, "total_tokens": 168416}
178
+ {"current_steps": 890, "total_steps": 38480, "loss": 0.2847, "lr": 0.006930873180873181, "epoch": 0.4625779625779626, "percentage": 2.31, "elapsed_time": "0:01:59", "remaining_time": "1:24:07", "throughput": 1416.68, "total_tokens": 169312}
179
+ {"current_steps": 895, "total_steps": 38480, "loss": 0.2092, "lr": 0.00696985446985447, "epoch": 0.46517671517671516, "percentage": 2.33, "elapsed_time": "0:02:00", "remaining_time": "1:24:06", "throughput": 1416.8, "total_tokens": 170272}
180
+ {"current_steps": 900, "total_steps": 38480, "loss": 0.2934, "lr": 0.007008835758835759, "epoch": 0.4677754677754678, "percentage": 2.34, "elapsed_time": "0:02:00", "remaining_time": "1:24:05", "throughput": 1416.17, "total_tokens": 171136}
181
+ {"current_steps": 905, "total_steps": 38480, "loss": 0.3012, "lr": 0.007047817047817048, "epoch": 0.4703742203742204, "percentage": 2.35, "elapsed_time": "0:02:01", "remaining_time": "1:24:05", "throughput": 1415.76, "total_tokens": 172032}
182
+ {"current_steps": 910, "total_steps": 38480, "loss": 0.2703, "lr": 0.007086798336798337, "epoch": 0.47297297297297297, "percentage": 2.36, "elapsed_time": "0:02:02", "remaining_time": "1:24:04", "throughput": 1415.81, "total_tokens": 172992}
183
+ {"current_steps": 915, "total_steps": 38480, "loss": 0.2779, "lr": 0.007125779625779626, "epoch": 0.47557172557172556, "percentage": 2.38, "elapsed_time": "0:02:02", "remaining_time": "1:24:03", "throughput": 1415.89, "total_tokens": 173952}
184
+ {"current_steps": 920, "total_steps": 38480, "loss": 0.3164, "lr": 0.007164760914760915, "epoch": 0.4781704781704782, "percentage": 2.39, "elapsed_time": "0:02:03", "remaining_time": "1:24:02", "throughput": 1415.52, "total_tokens": 174848}
185
+ {"current_steps": 925, "total_steps": 38480, "loss": 0.2957, "lr": 0.007203742203742204, "epoch": 0.4807692307692308, "percentage": 2.4, "elapsed_time": "0:02:04", "remaining_time": "1:24:02", "throughput": 1415.38, "total_tokens": 175776}
186
+ {"current_steps": 930, "total_steps": 38480, "loss": 0.2593, "lr": 0.007242723492723493, "epoch": 0.48336798336798337, "percentage": 2.42, "elapsed_time": "0:02:04", "remaining_time": "1:24:02", "throughput": 1416.26, "total_tokens": 176864}
187
+ {"current_steps": 935, "total_steps": 38480, "loss": 0.3458, "lr": 0.007281704781704782, "epoch": 0.48596673596673595, "percentage": 2.43, "elapsed_time": "0:02:05", "remaining_time": "1:24:01", "throughput": 1416.6, "total_tokens": 177856}
188
+ {"current_steps": 940, "total_steps": 38480, "loss": 0.27, "lr": 0.007320686070686071, "epoch": 0.4885654885654886, "percentage": 2.44, "elapsed_time": "0:02:06", "remaining_time": "1:24:01", "throughput": 1416.84, "total_tokens": 178848}
189
+ {"current_steps": 945, "total_steps": 38480, "loss": 0.2873, "lr": 0.0073596673596673596, "epoch": 0.4911642411642412, "percentage": 2.46, "elapsed_time": "0:02:06", "remaining_time": "1:24:00", "throughput": 1417.38, "total_tokens": 179872}
190
+ {"current_steps": 950, "total_steps": 38480, "loss": 0.2874, "lr": 0.0073986486486486485, "epoch": 0.49376299376299376, "percentage": 2.47, "elapsed_time": "0:02:07", "remaining_time": "1:23:59", "throughput": 1416.56, "total_tokens": 180704}
191
+ {"current_steps": 955, "total_steps": 38480, "loss": 0.2513, "lr": 0.0074376299376299375, "epoch": 0.49636174636174635, "percentage": 2.48, "elapsed_time": "0:02:08", "remaining_time": "1:23:58", "throughput": 1415.98, "total_tokens": 181568}
192
+ {"current_steps": 960, "total_steps": 38480, "loss": 0.3091, "lr": 0.0074766112266112265, "epoch": 0.498960498960499, "percentage": 2.49, "elapsed_time": "0:02:08", "remaining_time": "1:23:57", "throughput": 1416.53, "total_tokens": 182592}
193
+ {"current_steps": 965, "total_steps": 38480, "loss": 0.2519, "lr": 0.007515592515592515, "epoch": 0.5015592515592515, "percentage": 2.51, "elapsed_time": "0:02:09", "remaining_time": "1:23:57", "throughput": 1417.03, "total_tokens": 183616}
194
+ {"current_steps": 970, "total_steps": 38480, "loss": 0.2246, "lr": 0.0075545738045738045, "epoch": 0.5041580041580042, "percentage": 2.52, "elapsed_time": "0:02:10", "remaining_time": "1:23:56", "throughput": 1417.36, "total_tokens": 184608}
195
+ {"current_steps": 975, "total_steps": 38480, "loss": 0.2795, "lr": 0.007593555093555093, "epoch": 0.5067567567567568, "percentage": 2.53, "elapsed_time": "0:02:10", "remaining_time": "1:23:55", "throughput": 1417.23, "total_tokens": 185536}
196
+ {"current_steps": 980, "total_steps": 38480, "loss": 0.3575, "lr": 0.0076325363825363824, "epoch": 0.5093555093555093, "percentage": 2.55, "elapsed_time": "0:02:11", "remaining_time": "1:23:55", "throughput": 1417.77, "total_tokens": 186560}
197
+ {"current_steps": 985, "total_steps": 38480, "loss": 0.3378, "lr": 0.007671517671517671, "epoch": 0.511954261954262, "percentage": 2.56, "elapsed_time": "0:02:12", "remaining_time": "1:23:54", "throughput": 1418.08, "total_tokens": 187552}
198
+ {"current_steps": 990, "total_steps": 38480, "loss": 0.332, "lr": 0.0077104989604989595, "epoch": 0.5145530145530145, "percentage": 2.57, "elapsed_time": "0:02:12", "remaining_time": "1:23:53", "throughput": 1418.62, "total_tokens": 188576}
199
+ {"current_steps": 995, "total_steps": 38480, "loss": 0.2819, "lr": 0.007749480249480249, "epoch": 0.5171517671517671, "percentage": 2.59, "elapsed_time": "0:02:13", "remaining_time": "1:23:52", "throughput": 1418.27, "total_tokens": 189472}
200
+ {"current_steps": 1000, "total_steps": 38480, "loss": 0.2974, "lr": 0.007788461538461539, "epoch": 0.5197505197505198, "percentage": 2.6, "elapsed_time": "0:02:14", "remaining_time": "1:23:52", "throughput": 1417.92, "total_tokens": 190368}
201
+ {"current_steps": 1005, "total_steps": 38480, "loss": 0.293, "lr": 0.007827442827442826, "epoch": 0.5223492723492723, "percentage": 2.61, "elapsed_time": "0:02:14", "remaining_time": "1:23:51", "throughput": 1417.76, "total_tokens": 191296}
202
+ {"current_steps": 1010, "total_steps": 38480, "loss": 0.271, "lr": 0.007866424116424117, "epoch": 0.524948024948025, "percentage": 2.62, "elapsed_time": "0:02:15", "remaining_time": "1:23:50", "throughput": 1417.43, "total_tokens": 192192}
203
+ {"current_steps": 1015, "total_steps": 38480, "loss": 0.2837, "lr": 0.007905405405405404, "epoch": 0.5275467775467776, "percentage": 2.64, "elapsed_time": "0:02:16", "remaining_time": "1:23:49", "throughput": 1417.51, "total_tokens": 193152}
204
+ {"current_steps": 1020, "total_steps": 38480, "loss": 0.277, "lr": 0.007944386694386693, "epoch": 0.5301455301455301, "percentage": 2.65, "elapsed_time": "0:02:16", "remaining_time": "1:23:48", "throughput": 1417.6, "total_tokens": 194112}
205
+ {"current_steps": 1025, "total_steps": 38480, "loss": 0.2329, "lr": 0.007983367983367984, "epoch": 0.5327442827442828, "percentage": 2.66, "elapsed_time": "0:02:17", "remaining_time": "1:23:48", "throughput": 1417.69, "total_tokens": 195072}
206
+ {"current_steps": 1030, "total_steps": 38480, "loss": 0.2897, "lr": 0.008022349272349271, "epoch": 0.5353430353430353, "percentage": 2.68, "elapsed_time": "0:02:18", "remaining_time": "1:23:47", "throughput": 1417.15, "total_tokens": 195936}
207
+ {"current_steps": 1035, "total_steps": 38480, "loss": 0.2327, "lr": 0.00806133056133056, "epoch": 0.5379417879417879, "percentage": 2.69, "elapsed_time": "0:02:18", "remaining_time": "1:23:46", "throughput": 1417.04, "total_tokens": 196864}
208
+ {"current_steps": 1040, "total_steps": 38480, "loss": 0.21, "lr": 0.008100311850311851, "epoch": 0.5405405405405406, "percentage": 2.7, "elapsed_time": "0:02:19", "remaining_time": "1:23:45", "throughput": 1417.55, "total_tokens": 197888}
209
+ {"current_steps": 1045, "total_steps": 38480, "loss": 0.2697, "lr": 0.008139293139293138, "epoch": 0.5431392931392931, "percentage": 2.72, "elapsed_time": "0:02:20", "remaining_time": "1:23:44", "throughput": 1417.41, "total_tokens": 198816}
210
+ {"current_steps": 1050, "total_steps": 38480, "loss": 0.3516, "lr": 0.008178274428274429, "epoch": 0.5457380457380457, "percentage": 2.73, "elapsed_time": "0:02:20", "remaining_time": "1:23:43", "throughput": 1417.29, "total_tokens": 199744}
211
+ {"current_steps": 1055, "total_steps": 38480, "loss": 0.2735, "lr": 0.008217255717255716, "epoch": 0.5483367983367984, "percentage": 2.74, "elapsed_time": "0:02:21", "remaining_time": "1:23:43", "throughput": 1417.38, "total_tokens": 200704}
212
+ {"current_steps": 1060, "total_steps": 38480, "loss": 0.2806, "lr": 0.008256237006237005, "epoch": 0.5509355509355509, "percentage": 2.75, "elapsed_time": "0:02:22", "remaining_time": "1:23:42", "throughput": 1417.49, "total_tokens": 201664}
213
+ {"current_steps": 1065, "total_steps": 38480, "loss": 0.2676, "lr": 0.008295218295218296, "epoch": 0.5535343035343036, "percentage": 2.77, "elapsed_time": "0:02:22", "remaining_time": "1:23:41", "throughput": 1417.59, "total_tokens": 202624}
214
+ {"current_steps": 1070, "total_steps": 38480, "loss": 0.2108, "lr": 0.008334199584199583, "epoch": 0.5561330561330561, "percentage": 2.78, "elapsed_time": "0:02:23", "remaining_time": "1:23:40", "throughput": 1417.28, "total_tokens": 203520}
215
+ {"current_steps": 1075, "total_steps": 38480, "loss": 0.3126, "lr": 0.008373180873180872, "epoch": 0.5587318087318087, "percentage": 2.79, "elapsed_time": "0:02:24", "remaining_time": "1:23:39", "throughput": 1417.56, "total_tokens": 204512}
216
+ {"current_steps": 1080, "total_steps": 38480, "loss": 0.2467, "lr": 0.008412162162162163, "epoch": 0.5613305613305614, "percentage": 2.81, "elapsed_time": "0:02:24", "remaining_time": "1:23:39", "throughput": 1417.63, "total_tokens": 205472}
217
+ {"current_steps": 1085, "total_steps": 38480, "loss": 0.199, "lr": 0.00845114345114345, "epoch": 0.5639293139293139, "percentage": 2.82, "elapsed_time": "0:02:25", "remaining_time": "1:23:38", "throughput": 1418.32, "total_tokens": 206528}
218
+ {"current_steps": 1090, "total_steps": 38480, "loss": 0.2983, "lr": 0.00849012474012474, "epoch": 0.5665280665280665, "percentage": 2.83, "elapsed_time": "0:02:26", "remaining_time": "1:23:37", "throughput": 1418.0, "total_tokens": 207424}
219
+ {"current_steps": 1095, "total_steps": 38480, "loss": 0.2302, "lr": 0.008529106029106028, "epoch": 0.5691268191268192, "percentage": 2.85, "elapsed_time": "0:02:26", "remaining_time": "1:23:37", "throughput": 1418.26, "total_tokens": 208416}
220
+ {"current_steps": 1100, "total_steps": 38480, "loss": 0.2684, "lr": 0.008568087318087317, "epoch": 0.5717255717255717, "percentage": 2.86, "elapsed_time": "0:02:27", "remaining_time": "1:23:36", "throughput": 1418.56, "total_tokens": 209408}
221
+ {"current_steps": 1105, "total_steps": 38480, "loss": 0.2251, "lr": 0.008607068607068608, "epoch": 0.5743243243243243, "percentage": 2.87, "elapsed_time": "0:02:28", "remaining_time": "1:23:35", "throughput": 1419.03, "total_tokens": 210432}
222
+ {"current_steps": 1110, "total_steps": 38480, "loss": 0.1932, "lr": 0.008646049896049895, "epoch": 0.5769230769230769, "percentage": 2.88, "elapsed_time": "0:02:28", "remaining_time": "1:23:34", "throughput": 1418.91, "total_tokens": 211360}
223
+ {"current_steps": 1115, "total_steps": 38480, "loss": 0.3096, "lr": 0.008685031185031184, "epoch": 0.5795218295218295, "percentage": 2.9, "elapsed_time": "0:02:29", "remaining_time": "1:23:34", "throughput": 1418.8, "total_tokens": 212288}
224
+ {"current_steps": 1120, "total_steps": 38480, "loss": 0.2988, "lr": 0.008724012474012475, "epoch": 0.5821205821205822, "percentage": 2.91, "elapsed_time": "0:02:30", "remaining_time": "1:23:33", "throughput": 1418.69, "total_tokens": 213216}
225
+ {"current_steps": 1125, "total_steps": 38480, "loss": 0.2193, "lr": 0.008762993762993762, "epoch": 0.5847193347193347, "percentage": 2.92, "elapsed_time": "0:02:30", "remaining_time": "1:23:32", "throughput": 1418.96, "total_tokens": 214208}
226
+ {"current_steps": 1130, "total_steps": 38480, "loss": 0.2267, "lr": 0.008801975051975051, "epoch": 0.5873180873180873, "percentage": 2.94, "elapsed_time": "0:02:31", "remaining_time": "1:23:31", "throughput": 1419.43, "total_tokens": 215232}
227
+ {"current_steps": 1135, "total_steps": 38480, "loss": 0.1448, "lr": 0.00884095634095634, "epoch": 0.58991683991684, "percentage": 2.95, "elapsed_time": "0:02:32", "remaining_time": "1:23:31", "throughput": 1418.92, "total_tokens": 216096}
228
+ {"current_steps": 1140, "total_steps": 38480, "loss": 0.2991, "lr": 0.008879937629937629, "epoch": 0.5925155925155925, "percentage": 2.96, "elapsed_time": "0:02:32", "remaining_time": "1:23:30", "throughput": 1418.8, "total_tokens": 217024}
229
+ {"current_steps": 1145, "total_steps": 38480, "loss": 0.1907, "lr": 0.00891891891891892, "epoch": 0.5951143451143451, "percentage": 2.98, "elapsed_time": "0:02:33", "remaining_time": "1:23:29", "throughput": 1418.45, "total_tokens": 217920}
230
+ {"current_steps": 1150, "total_steps": 38480, "loss": 0.232, "lr": 0.008957900207900207, "epoch": 0.5977130977130977, "percentage": 2.99, "elapsed_time": "0:02:34", "remaining_time": "1:23:28", "throughput": 1418.14, "total_tokens": 218816}
231
+ {"current_steps": 1155, "total_steps": 38480, "loss": 0.3241, "lr": 0.008996881496881496, "epoch": 0.6003118503118503, "percentage": 3.0, "elapsed_time": "0:02:34", "remaining_time": "1:23:27", "throughput": 1418.22, "total_tokens": 219776}
232
+ {"current_steps": 1160, "total_steps": 38480, "loss": 0.3285, "lr": 0.009035862785862787, "epoch": 0.6029106029106029, "percentage": 3.01, "elapsed_time": "0:02:35", "remaining_time": "1:23:27", "throughput": 1418.08, "total_tokens": 220704}
233
+ {"current_steps": 1165, "total_steps": 38480, "loss": 0.2573, "lr": 0.009074844074844074, "epoch": 0.6055093555093555, "percentage": 3.03, "elapsed_time": "0:02:36", "remaining_time": "1:23:27", "throughput": 1418.78, "total_tokens": 221792}
234
+ {"current_steps": 1170, "total_steps": 38480, "loss": 0.3078, "lr": 0.009113825363825363, "epoch": 0.6081081081081081, "percentage": 3.04, "elapsed_time": "0:02:36", "remaining_time": "1:23:26", "throughput": 1419.03, "total_tokens": 222784}
235
+ {"current_steps": 1175, "total_steps": 38480, "loss": 0.3172, "lr": 0.009152806652806652, "epoch": 0.6107068607068608, "percentage": 3.05, "elapsed_time": "0:02:37", "remaining_time": "1:23:25", "throughput": 1419.1, "total_tokens": 223744}
236
+ {"current_steps": 1180, "total_steps": 38480, "loss": 0.287, "lr": 0.009191787941787941, "epoch": 0.6133056133056133, "percentage": 3.07, "elapsed_time": "0:02:38", "remaining_time": "1:23:25", "throughput": 1419.34, "total_tokens": 224736}
237
+ {"current_steps": 1185, "total_steps": 38480, "loss": 0.2081, "lr": 0.009230769230769232, "epoch": 0.6159043659043659, "percentage": 3.08, "elapsed_time": "0:02:39", "remaining_time": "1:23:24", "throughput": 1419.4, "total_tokens": 225696}
238
+ {"current_steps": 1190, "total_steps": 38480, "loss": 0.2841, "lr": 0.009269750519750519, "epoch": 0.6185031185031185, "percentage": 3.09, "elapsed_time": "0:02:39", "remaining_time": "1:23:23", "throughput": 1419.67, "total_tokens": 226688}
239
+ {"current_steps": 1195, "total_steps": 38480, "loss": 0.2338, "lr": 0.009308731808731808, "epoch": 0.6211018711018711, "percentage": 3.11, "elapsed_time": "0:02:40", "remaining_time": "1:23:22", "throughput": 1419.92, "total_tokens": 227680}
240
+ {"current_steps": 1200, "total_steps": 38480, "loss": 0.3064, "lr": 0.009347713097713099, "epoch": 0.6237006237006237, "percentage": 3.12, "elapsed_time": "0:02:41", "remaining_time": "1:23:22", "throughput": 1419.6, "total_tokens": 228576}
241
+ {"current_steps": 1205, "total_steps": 38480, "loss": 0.2575, "lr": 0.009386694386694386, "epoch": 0.6262993762993763, "percentage": 3.13, "elapsed_time": "0:02:41", "remaining_time": "1:23:21", "throughput": 1419.48, "total_tokens": 229504}
242
+ {"current_steps": 1210, "total_steps": 38480, "loss": 0.1562, "lr": 0.009425675675675675, "epoch": 0.6288981288981289, "percentage": 3.14, "elapsed_time": "0:02:42", "remaining_time": "1:23:20", "throughput": 1419.54, "total_tokens": 230464}
243
+ {"current_steps": 1215, "total_steps": 38480, "loss": 0.1991, "lr": 0.009464656964656964, "epoch": 0.6314968814968815, "percentage": 3.16, "elapsed_time": "0:02:43", "remaining_time": "1:23:19", "throughput": 1419.79, "total_tokens": 231456}
244
+ {"current_steps": 1220, "total_steps": 38480, "loss": 0.3199, "lr": 0.009503638253638253, "epoch": 0.6340956340956341, "percentage": 3.17, "elapsed_time": "0:02:43", "remaining_time": "1:23:19", "throughput": 1419.32, "total_tokens": 232320}
245
+ {"current_steps": 1225, "total_steps": 38480, "loss": 0.2845, "lr": 0.009542619542619543, "epoch": 0.6366943866943867, "percentage": 3.18, "elapsed_time": "0:02:44", "remaining_time": "1:23:18", "throughput": 1418.85, "total_tokens": 233184}
246
+ {"current_steps": 1230, "total_steps": 38480, "loss": 0.2771, "lr": 0.00958160083160083, "epoch": 0.6392931392931392, "percentage": 3.2, "elapsed_time": "0:02:45", "remaining_time": "1:23:17", "throughput": 1418.75, "total_tokens": 234112}
247
+ {"current_steps": 1235, "total_steps": 38480, "loss": 0.2672, "lr": 0.00962058212058212, "epoch": 0.6418918918918919, "percentage": 3.21, "elapsed_time": "0:02:45", "remaining_time": "1:23:16", "throughput": 1418.64, "total_tokens": 235040}
248
+ {"current_steps": 1240, "total_steps": 38480, "loss": 0.2768, "lr": 0.00965956340956341, "epoch": 0.6444906444906445, "percentage": 3.22, "elapsed_time": "0:02:46", "remaining_time": "1:23:15", "throughput": 1418.88, "total_tokens": 236032}
249
+ {"current_steps": 1245, "total_steps": 38480, "loss": 0.2766, "lr": 0.009698544698544698, "epoch": 0.6470893970893971, "percentage": 3.24, "elapsed_time": "0:02:47", "remaining_time": "1:23:15", "throughput": 1418.96, "total_tokens": 236992}
250
+ {"current_steps": 1250, "total_steps": 38480, "loss": 0.2781, "lr": 0.009737525987525987, "epoch": 0.6496881496881497, "percentage": 3.25, "elapsed_time": "0:02:47", "remaining_time": "1:23:14", "throughput": 1419.37, "total_tokens": 238016}
251
+ {"current_steps": 1255, "total_steps": 38480, "loss": 0.2769, "lr": 0.009776507276507276, "epoch": 0.6522869022869023, "percentage": 3.26, "elapsed_time": "0:02:48", "remaining_time": "1:23:13", "throughput": 1419.25, "total_tokens": 238944}
252
+ {"current_steps": 1260, "total_steps": 38480, "loss": 0.2606, "lr": 0.009815488565488565, "epoch": 0.6548856548856549, "percentage": 3.27, "elapsed_time": "0:02:49", "remaining_time": "1:23:13", "throughput": 1419.3, "total_tokens": 239904}
253
+ {"current_steps": 1265, "total_steps": 38480, "loss": 0.2923, "lr": 0.009854469854469855, "epoch": 0.6574844074844075, "percentage": 3.29, "elapsed_time": "0:02:49", "remaining_time": "1:23:12", "throughput": 1419.2, "total_tokens": 240832}
254
+ {"current_steps": 1270, "total_steps": 38480, "loss": 0.2791, "lr": 0.009893451143451143, "epoch": 0.66008316008316, "percentage": 3.3, "elapsed_time": "0:02:50", "remaining_time": "1:23:11", "throughput": 1419.44, "total_tokens": 241824}
255
+ {"current_steps": 1275, "total_steps": 38480, "loss": 0.2649, "lr": 0.009932432432432432, "epoch": 0.6626819126819127, "percentage": 3.31, "elapsed_time": "0:02:51", "remaining_time": "1:23:10", "throughput": 1419.67, "total_tokens": 242816}
256
+ {"current_steps": 1280, "total_steps": 38480, "loss": 0.2219, "lr": 0.009971413721413722, "epoch": 0.6652806652806653, "percentage": 3.33, "elapsed_time": "0:02:51", "remaining_time": "1:23:10", "throughput": 1419.78, "total_tokens": 243808}
257
+ {"current_steps": 1285, "total_steps": 38480, "loss": 0.267, "lr": 0.01001039501039501, "epoch": 0.6678794178794178, "percentage": 3.34, "elapsed_time": "0:02:52", "remaining_time": "1:23:09", "throughput": 1419.67, "total_tokens": 244736}
258
+ {"current_steps": 1290, "total_steps": 38480, "loss": 0.3221, "lr": 0.010049376299376299, "epoch": 0.6704781704781705, "percentage": 3.35, "elapsed_time": "0:02:53", "remaining_time": "1:23:09", "throughput": 1419.73, "total_tokens": 245696}
259
+ {"current_steps": 1295, "total_steps": 38480, "loss": 0.3043, "lr": 0.010088357588357588, "epoch": 0.6730769230769231, "percentage": 3.37, "elapsed_time": "0:02:53", "remaining_time": "1:23:08", "throughput": 1420.13, "total_tokens": 246720}
260
+ {"current_steps": 1300, "total_steps": 38480, "loss": 0.2781, "lr": 0.010127338877338877, "epoch": 0.6756756756756757, "percentage": 3.38, "elapsed_time": "0:02:54", "remaining_time": "1:23:08", "throughput": 1420.4, "total_tokens": 247744}
261
+ {"current_steps": 1305, "total_steps": 38480, "loss": 0.2656, "lr": 0.010166320166320167, "epoch": 0.6782744282744283, "percentage": 3.39, "elapsed_time": "0:02:55", "remaining_time": "1:23:07", "throughput": 1420.62, "total_tokens": 248736}
262
+ {"current_steps": 1310, "total_steps": 38480, "loss": 0.2929, "lr": 0.010205301455301454, "epoch": 0.6808731808731808, "percentage": 3.4, "elapsed_time": "0:02:55", "remaining_time": "1:23:07", "throughput": 1420.84, "total_tokens": 249728}
263
+ {"current_steps": 1315, "total_steps": 38480, "loss": 0.2928, "lr": 0.010244282744282743, "epoch": 0.6834719334719335, "percentage": 3.42, "elapsed_time": "0:02:56", "remaining_time": "1:23:06", "throughput": 1420.57, "total_tokens": 250624}
264
+ {"current_steps": 1320, "total_steps": 38480, "loss": 0.2957, "lr": 0.010283264033264034, "epoch": 0.6860706860706861, "percentage": 3.43, "elapsed_time": "0:02:57", "remaining_time": "1:23:05", "throughput": 1420.79, "total_tokens": 251616}
265
+ {"current_steps": 1325, "total_steps": 38480, "loss": 0.2812, "lr": 0.010322245322245321, "epoch": 0.6886694386694386, "percentage": 3.44, "elapsed_time": "0:02:57", "remaining_time": "1:23:04", "throughput": 1420.35, "total_tokens": 252480}
266
+ {"current_steps": 1330, "total_steps": 38480, "loss": 0.2516, "lr": 0.01036122661122661, "epoch": 0.6912681912681913, "percentage": 3.46, "elapsed_time": "0:02:58", "remaining_time": "1:23:03", "throughput": 1420.42, "total_tokens": 253440}
267
+ {"current_steps": 1335, "total_steps": 38480, "loss": 0.3159, "lr": 0.0104002079002079, "epoch": 0.6938669438669439, "percentage": 3.47, "elapsed_time": "0:02:59", "remaining_time": "1:23:03", "throughput": 1420.47, "total_tokens": 254400}
268
+ {"current_steps": 1340, "total_steps": 38480, "loss": 0.2668, "lr": 0.010439189189189188, "epoch": 0.6964656964656964, "percentage": 3.48, "elapsed_time": "0:02:59", "remaining_time": "1:23:02", "throughput": 1420.85, "total_tokens": 255424}
269
+ {"current_steps": 1345, "total_steps": 38480, "loss": 0.2328, "lr": 0.010478170478170479, "epoch": 0.6990644490644491, "percentage": 3.5, "elapsed_time": "0:03:00", "remaining_time": "1:23:01", "throughput": 1420.58, "total_tokens": 256320}
270
+ {"current_steps": 1350, "total_steps": 38480, "loss": 0.2514, "lr": 0.010517151767151766, "epoch": 0.7016632016632016, "percentage": 3.51, "elapsed_time": "0:03:01", "remaining_time": "1:23:00", "throughput": 1420.31, "total_tokens": 257216}
271
+ {"current_steps": 1355, "total_steps": 38480, "loss": 0.2251, "lr": 0.010556133056133055, "epoch": 0.7042619542619543, "percentage": 3.52, "elapsed_time": "0:03:01", "remaining_time": "1:23:00", "throughput": 1419.87, "total_tokens": 258080}
272
+ {"current_steps": 1360, "total_steps": 38480, "loss": 0.2693, "lr": 0.010595114345114346, "epoch": 0.7068607068607069, "percentage": 3.53, "elapsed_time": "0:03:02", "remaining_time": "1:22:59", "throughput": 1419.77, "total_tokens": 259008}
273
+ {"current_steps": 1365, "total_steps": 38480, "loss": 0.3196, "lr": 0.010634095634095633, "epoch": 0.7094594594594594, "percentage": 3.55, "elapsed_time": "0:03:03", "remaining_time": "1:22:58", "throughput": 1419.81, "total_tokens": 259968}
274
+ {"current_steps": 1370, "total_steps": 38480, "loss": 0.1942, "lr": 0.010673076923076922, "epoch": 0.7120582120582121, "percentage": 3.56, "elapsed_time": "0:03:03", "remaining_time": "1:22:57", "throughput": 1420.02, "total_tokens": 260960}
275
+ {"current_steps": 1375, "total_steps": 38480, "loss": 0.2788, "lr": 0.010712058212058211, "epoch": 0.7146569646569647, "percentage": 3.57, "elapsed_time": "0:03:04", "remaining_time": "1:22:57", "throughput": 1420.08, "total_tokens": 261920}
276
+ {"current_steps": 1380, "total_steps": 38480, "loss": 0.2655, "lr": 0.0107510395010395, "epoch": 0.7172557172557172, "percentage": 3.59, "elapsed_time": "0:03:05", "remaining_time": "1:22:56", "throughput": 1419.81, "total_tokens": 262816}
277
+ {"current_steps": 1385, "total_steps": 38480, "loss": 0.3056, "lr": 0.010790020790020791, "epoch": 0.7198544698544699, "percentage": 3.6, "elapsed_time": "0:03:05", "remaining_time": "1:22:55", "throughput": 1419.99, "total_tokens": 263808}
278
+ {"current_steps": 1390, "total_steps": 38480, "loss": 0.2561, "lr": 0.010829002079002078, "epoch": 0.7224532224532224, "percentage": 3.61, "elapsed_time": "0:03:06", "remaining_time": "1:22:55", "throughput": 1419.87, "total_tokens": 264736}
279
+ {"current_steps": 1395, "total_steps": 38480, "loss": 0.2448, "lr": 0.010867983367983367, "epoch": 0.725051975051975, "percentage": 3.63, "elapsed_time": "0:03:07", "remaining_time": "1:22:54", "throughput": 1419.91, "total_tokens": 265696}
280
+ {"current_steps": 1400, "total_steps": 38480, "loss": 0.2789, "lr": 0.010906964656964658, "epoch": 0.7276507276507277, "percentage": 3.64, "elapsed_time": "0:03:07", "remaining_time": "1:22:53", "throughput": 1419.82, "total_tokens": 266624}
281
+ {"current_steps": 1405, "total_steps": 38480, "loss": 0.2038, "lr": 0.010945945945945945, "epoch": 0.7302494802494802, "percentage": 3.65, "elapsed_time": "0:03:08", "remaining_time": "1:22:52", "throughput": 1419.89, "total_tokens": 267584}
282
+ {"current_steps": 1410, "total_steps": 38480, "loss": 0.2724, "lr": 0.010984927234927234, "epoch": 0.7328482328482329, "percentage": 3.66, "elapsed_time": "0:03:09", "remaining_time": "1:22:52", "throughput": 1419.94, "total_tokens": 268544}
283
+ {"current_steps": 1415, "total_steps": 38480, "loss": 0.1938, "lr": 0.011023908523908523, "epoch": 0.7354469854469855, "percentage": 3.68, "elapsed_time": "0:03:09", "remaining_time": "1:22:51", "throughput": 1419.84, "total_tokens": 269472}
284
+ {"current_steps": 1420, "total_steps": 38480, "loss": 0.2763, "lr": 0.011062889812889812, "epoch": 0.738045738045738, "percentage": 3.69, "elapsed_time": "0:03:10", "remaining_time": "1:22:50", "throughput": 1419.59, "total_tokens": 270368}
285
+ {"current_steps": 1425, "total_steps": 38480, "loss": 0.33, "lr": 0.011101871101871103, "epoch": 0.7406444906444907, "percentage": 3.7, "elapsed_time": "0:03:11", "remaining_time": "1:22:49", "throughput": 1419.95, "total_tokens": 271392}
286
+ {"current_steps": 1430, "total_steps": 38480, "loss": 0.2298, "lr": 0.01114085239085239, "epoch": 0.7432432432432432, "percentage": 3.72, "elapsed_time": "0:03:11", "remaining_time": "1:22:49", "throughput": 1420.16, "total_tokens": 272384}
287
+ {"current_steps": 1435, "total_steps": 38480, "loss": 0.2535, "lr": 0.011179833679833679, "epoch": 0.7458419958419958, "percentage": 3.73, "elapsed_time": "0:03:12", "remaining_time": "1:22:48", "throughput": 1419.91, "total_tokens": 273280}
288
+ {"current_steps": 1440, "total_steps": 38480, "loss": 0.2301, "lr": 0.01121881496881497, "epoch": 0.7484407484407485, "percentage": 3.74, "elapsed_time": "0:03:13", "remaining_time": "1:22:47", "throughput": 1419.66, "total_tokens": 274176}
289
+ {"current_steps": 1445, "total_steps": 38480, "loss": 0.2719, "lr": 0.011257796257796257, "epoch": 0.751039501039501, "percentage": 3.76, "elapsed_time": "0:03:13", "remaining_time": "1:22:46", "throughput": 1419.71, "total_tokens": 275136}
290
+ {"current_steps": 1450, "total_steps": 38480, "loss": 0.2936, "lr": 0.011296777546777546, "epoch": 0.7536382536382537, "percentage": 3.77, "elapsed_time": "0:03:14", "remaining_time": "1:22:46", "throughput": 1419.92, "total_tokens": 276128}
291
+ {"current_steps": 1455, "total_steps": 38480, "loss": 0.2275, "lr": 0.011335758835758835, "epoch": 0.7562370062370062, "percentage": 3.78, "elapsed_time": "0:03:15", "remaining_time": "1:22:45", "throughput": 1419.67, "total_tokens": 277024}
292
+ {"current_steps": 1460, "total_steps": 38480, "loss": 0.264, "lr": 0.011374740124740124, "epoch": 0.7588357588357588, "percentage": 3.79, "elapsed_time": "0:03:15", "remaining_time": "1:22:45", "throughput": 1419.91, "total_tokens": 278048}
293
+ {"current_steps": 1465, "total_steps": 38480, "loss": 0.3208, "lr": 0.011413721413721415, "epoch": 0.7614345114345115, "percentage": 3.81, "elapsed_time": "0:03:16", "remaining_time": "1:22:44", "throughput": 1420.11, "total_tokens": 279040}
294
+ {"current_steps": 1470, "total_steps": 38480, "loss": 0.2612, "lr": 0.011452702702702702, "epoch": 0.764033264033264, "percentage": 3.82, "elapsed_time": "0:03:17", "remaining_time": "1:22:43", "throughput": 1420.16, "total_tokens": 280000}
295
+ {"current_steps": 1475, "total_steps": 38480, "loss": 0.2588, "lr": 0.011491683991683991, "epoch": 0.7666320166320166, "percentage": 3.83, "elapsed_time": "0:03:17", "remaining_time": "1:22:43", "throughput": 1420.21, "total_tokens": 280960}
296
+ {"current_steps": 1480, "total_steps": 38480, "loss": 0.2414, "lr": 0.01153066528066528, "epoch": 0.7692307692307693, "percentage": 3.85, "elapsed_time": "0:03:18", "remaining_time": "1:22:42", "throughput": 1420.27, "total_tokens": 281920}
297
+ {"current_steps": 1485, "total_steps": 38480, "loss": 0.2246, "lr": 0.011569646569646569, "epoch": 0.7718295218295218, "percentage": 3.86, "elapsed_time": "0:03:19", "remaining_time": "1:22:41", "throughput": 1420.62, "total_tokens": 282944}
298
+ {"current_steps": 1490, "total_steps": 38480, "loss": 0.1204, "lr": 0.011608627858627858, "epoch": 0.7744282744282744, "percentage": 3.87, "elapsed_time": "0:03:19", "remaining_time": "1:22:41", "throughput": 1420.51, "total_tokens": 283872}
299
+ {"current_steps": 1495, "total_steps": 38480, "loss": 0.3974, "lr": 0.011647609147609147, "epoch": 0.777027027027027, "percentage": 3.89, "elapsed_time": "0:03:20", "remaining_time": "1:22:40", "throughput": 1420.41, "total_tokens": 284800}
300
+ {"current_steps": 1500, "total_steps": 38480, "loss": 0.3467, "lr": 0.011686590436590436, "epoch": 0.7796257796257796, "percentage": 3.9, "elapsed_time": "0:03:21", "remaining_time": "1:22:39", "throughput": 1420.02, "total_tokens": 285664}
301
+ {"current_steps": 1505, "total_steps": 38480, "loss": 0.1981, "lr": 0.011725571725571727, "epoch": 0.7822245322245323, "percentage": 3.91, "elapsed_time": "0:03:21", "remaining_time": "1:22:38", "throughput": 1420.07, "total_tokens": 286624}
302
+ {"current_steps": 1510, "total_steps": 38480, "loss": 0.2655, "lr": 0.011764553014553014, "epoch": 0.7848232848232848, "percentage": 3.92, "elapsed_time": "0:03:22", "remaining_time": "1:22:37", "throughput": 1419.85, "total_tokens": 287520}
303
+ {"current_steps": 1515, "total_steps": 38480, "loss": 0.2574, "lr": 0.011803534303534303, "epoch": 0.7874220374220374, "percentage": 3.94, "elapsed_time": "0:03:23", "remaining_time": "1:22:37", "throughput": 1420.05, "total_tokens": 288512}
304
+ {"current_steps": 1520, "total_steps": 38480, "loss": 0.251, "lr": 0.011842515592515592, "epoch": 0.7900207900207901, "percentage": 3.95, "elapsed_time": "0:03:23", "remaining_time": "1:22:36", "throughput": 1420.1, "total_tokens": 289472}
305
+ {"current_steps": 1525, "total_steps": 38480, "loss": 0.2526, "lr": 0.01188149688149688, "epoch": 0.7926195426195426, "percentage": 3.96, "elapsed_time": "0:03:24", "remaining_time": "1:22:35", "throughput": 1419.99, "total_tokens": 290400}
306
+ {"current_steps": 1530, "total_steps": 38480, "loss": 0.3051, "lr": 0.01192047817047817, "epoch": 0.7952182952182952, "percentage": 3.98, "elapsed_time": "0:03:25", "remaining_time": "1:22:35", "throughput": 1420.04, "total_tokens": 291360}
307
+ {"current_steps": 1535, "total_steps": 38480, "loss": 0.2782, "lr": 0.011959459459459459, "epoch": 0.7978170478170478, "percentage": 3.99, "elapsed_time": "0:03:25", "remaining_time": "1:22:34", "throughput": 1420.37, "total_tokens": 292384}
308
+ {"current_steps": 1540, "total_steps": 38480, "loss": 0.2667, "lr": 0.011998440748440748, "epoch": 0.8004158004158004, "percentage": 4.0, "elapsed_time": "0:03:26", "remaining_time": "1:22:34", "throughput": 1420.88, "total_tokens": 293472}
309
+ {"current_steps": 1545, "total_steps": 38480, "loss": 0.2904, "lr": 0.012037422037422038, "epoch": 0.803014553014553, "percentage": 4.02, "elapsed_time": "0:03:27", "remaining_time": "1:22:33", "throughput": 1420.93, "total_tokens": 294432}
310
+ {"current_steps": 1550, "total_steps": 38480, "loss": 0.2705, "lr": 0.012076403326403326, "epoch": 0.8056133056133056, "percentage": 4.03, "elapsed_time": "0:03:27", "remaining_time": "1:22:33", "throughput": 1421.25, "total_tokens": 295456}
311
+ {"current_steps": 1555, "total_steps": 38480, "loss": 0.2539, "lr": 0.012115384615384615, "epoch": 0.8082120582120582, "percentage": 4.04, "elapsed_time": "0:03:28", "remaining_time": "1:22:32", "throughput": 1421.45, "total_tokens": 296448}
312
+ {"current_steps": 1560, "total_steps": 38480, "loss": 0.2384, "lr": 0.012154365904365904, "epoch": 0.8108108108108109, "percentage": 4.05, "elapsed_time": "0:03:29", "remaining_time": "1:22:31", "throughput": 1421.35, "total_tokens": 297376}
313
+ {"current_steps": 1565, "total_steps": 38480, "loss": 0.2508, "lr": 0.012193347193347193, "epoch": 0.8134095634095634, "percentage": 4.07, "elapsed_time": "0:03:29", "remaining_time": "1:22:30", "throughput": 1421.42, "total_tokens": 298336}
314
+ {"current_steps": 1570, "total_steps": 38480, "loss": 0.2517, "lr": 0.012232328482328482, "epoch": 0.816008316008316, "percentage": 4.08, "elapsed_time": "0:03:30", "remaining_time": "1:22:29", "throughput": 1421.33, "total_tokens": 299264}
315
+ {"current_steps": 1575, "total_steps": 38480, "loss": 0.194, "lr": 0.01227130977130977, "epoch": 0.8186070686070686, "percentage": 4.09, "elapsed_time": "0:03:31", "remaining_time": "1:22:29", "throughput": 1421.51, "total_tokens": 300256}
316
+ {"current_steps": 1580, "total_steps": 38480, "loss": 0.2517, "lr": 0.01231029106029106, "epoch": 0.8212058212058212, "percentage": 4.11, "elapsed_time": "0:03:31", "remaining_time": "1:22:28", "throughput": 1421.41, "total_tokens": 301184}
317
+ {"current_steps": 1585, "total_steps": 38480, "loss": 0.2709, "lr": 0.01234927234927235, "epoch": 0.8238045738045738, "percentage": 4.12, "elapsed_time": "0:03:32", "remaining_time": "1:22:27", "throughput": 1421.45, "total_tokens": 302144}
318
+ {"current_steps": 1590, "total_steps": 38480, "loss": 0.2999, "lr": 0.012388253638253638, "epoch": 0.8264033264033264, "percentage": 4.13, "elapsed_time": "0:03:33", "remaining_time": "1:22:27", "throughput": 1421.63, "total_tokens": 303136}
319
+ {"current_steps": 1595, "total_steps": 38480, "loss": 0.2538, "lr": 0.012427234927234927, "epoch": 0.829002079002079, "percentage": 4.15, "elapsed_time": "0:03:33", "remaining_time": "1:22:26", "throughput": 1421.68, "total_tokens": 304096}
320
+ {"current_steps": 1600, "total_steps": 38480, "loss": 0.231, "lr": 0.012466216216216216, "epoch": 0.8316008316008316, "percentage": 4.16, "elapsed_time": "0:03:34", "remaining_time": "1:22:25", "throughput": 1421.46, "total_tokens": 304992}
321
+ {"current_steps": 1605, "total_steps": 38480, "loss": 0.2457, "lr": 0.012505197505197505, "epoch": 0.8341995841995842, "percentage": 4.17, "elapsed_time": "0:03:35", "remaining_time": "1:22:25", "throughput": 1421.64, "total_tokens": 305984}
322
+ {"current_steps": 1610, "total_steps": 38480, "loss": 0.2124, "lr": 0.012544178794178793, "epoch": 0.8367983367983368, "percentage": 4.18, "elapsed_time": "0:03:35", "remaining_time": "1:22:24", "throughput": 1421.87, "total_tokens": 307008}
323
+ {"current_steps": 1615, "total_steps": 38480, "loss": 0.2186, "lr": 0.012583160083160082, "epoch": 0.8393970893970893, "percentage": 4.2, "elapsed_time": "0:03:36", "remaining_time": "1:22:23", "throughput": 1421.78, "total_tokens": 307936}
324
+ {"current_steps": 1620, "total_steps": 38480, "loss": 0.2275, "lr": 0.012622141372141371, "epoch": 0.841995841995842, "percentage": 4.21, "elapsed_time": "0:03:37", "remaining_time": "1:22:23", "throughput": 1421.8, "total_tokens": 308896}
325
+ {"current_steps": 1625, "total_steps": 38480, "loss": 0.2273, "lr": 0.012661122661122662, "epoch": 0.8445945945945946, "percentage": 4.22, "elapsed_time": "0:03:37", "remaining_time": "1:22:22", "throughput": 1421.71, "total_tokens": 309824}
326
+ {"current_steps": 1630, "total_steps": 38480, "loss": 0.1659, "lr": 0.01270010395010395, "epoch": 0.8471933471933472, "percentage": 4.24, "elapsed_time": "0:03:38", "remaining_time": "1:22:21", "throughput": 1422.16, "total_tokens": 310880}
327
+ {"current_steps": 1635, "total_steps": 38480, "loss": 0.2981, "lr": 0.012739085239085238, "epoch": 0.8497920997920998, "percentage": 4.25, "elapsed_time": "0:03:39", "remaining_time": "1:22:21", "throughput": 1422.19, "total_tokens": 311840}
328
+ {"current_steps": 1640, "total_steps": 38480, "loss": 0.2889, "lr": 0.012778066528066527, "epoch": 0.8523908523908524, "percentage": 4.26, "elapsed_time": "0:03:39", "remaining_time": "1:22:20", "throughput": 1422.23, "total_tokens": 312800}
329
+ {"current_steps": 1645, "total_steps": 38480, "loss": 0.2605, "lr": 0.012817047817047816, "epoch": 0.854989604989605, "percentage": 4.27, "elapsed_time": "0:03:40", "remaining_time": "1:22:19", "throughput": 1422.4, "total_tokens": 313792}
330
+ {"current_steps": 1650, "total_steps": 38480, "loss": 0.2521, "lr": 0.012856029106029105, "epoch": 0.8575883575883576, "percentage": 4.29, "elapsed_time": "0:03:41", "remaining_time": "1:22:19", "throughput": 1422.31, "total_tokens": 314720}
331
+ {"current_steps": 1655, "total_steps": 38480, "loss": 0.2668, "lr": 0.012895010395010394, "epoch": 0.8601871101871101, "percentage": 4.3, "elapsed_time": "0:03:41", "remaining_time": "1:22:18", "throughput": 1422.21, "total_tokens": 315648}
332
+ {"current_steps": 1660, "total_steps": 38480, "loss": 0.2482, "lr": 0.012933991683991683, "epoch": 0.8627858627858628, "percentage": 4.31, "elapsed_time": "0:03:42", "remaining_time": "1:22:17", "throughput": 1422.25, "total_tokens": 316608}
333
+ {"current_steps": 1665, "total_steps": 38480, "loss": 0.2049, "lr": 0.012972972972972974, "epoch": 0.8653846153846154, "percentage": 4.33, "elapsed_time": "0:03:43", "remaining_time": "1:22:16", "throughput": 1422.42, "total_tokens": 317600}
334
+ {"current_steps": 1670, "total_steps": 38480, "loss": 0.2776, "lr": 0.013011954261954261, "epoch": 0.867983367983368, "percentage": 4.34, "elapsed_time": "0:03:43", "remaining_time": "1:22:16", "throughput": 1422.45, "total_tokens": 318560}
335
+ {"current_steps": 1675, "total_steps": 38480, "loss": 0.2251, "lr": 0.01305093555093555, "epoch": 0.8705821205821206, "percentage": 4.35, "elapsed_time": "0:03:44", "remaining_time": "1:22:15", "throughput": 1422.22, "total_tokens": 319456}
336
+ {"current_steps": 1680, "total_steps": 38480, "loss": 0.2604, "lr": 0.01308991683991684, "epoch": 0.8731808731808732, "percentage": 4.37, "elapsed_time": "0:03:45", "remaining_time": "1:22:14", "throughput": 1422.12, "total_tokens": 320384}
337
+ {"current_steps": 1685, "total_steps": 38480, "loss": 0.2479, "lr": 0.013128898128898128, "epoch": 0.8757796257796258, "percentage": 4.38, "elapsed_time": "0:03:45", "remaining_time": "1:22:14", "throughput": 1422.15, "total_tokens": 321344}
338
+ {"current_steps": 1690, "total_steps": 38480, "loss": 0.2909, "lr": 0.013167879417879417, "epoch": 0.8783783783783784, "percentage": 4.39, "elapsed_time": "0:03:46", "remaining_time": "1:22:13", "throughput": 1422.32, "total_tokens": 322336}
339
+ {"current_steps": 1695, "total_steps": 38480, "loss": 0.2337, "lr": 0.013206860706860706, "epoch": 0.8809771309771309, "percentage": 4.4, "elapsed_time": "0:03:47", "remaining_time": "1:22:12", "throughput": 1422.62, "total_tokens": 323360}
340
+ {"current_steps": 1700, "total_steps": 38480, "loss": 0.2468, "lr": 0.013245841995841995, "epoch": 0.8835758835758836, "percentage": 4.42, "elapsed_time": "0:03:47", "remaining_time": "1:22:12", "throughput": 1422.39, "total_tokens": 324256}
341
+ {"current_steps": 1705, "total_steps": 38480, "loss": 0.2589, "lr": 0.013284823284823286, "epoch": 0.8861746361746362, "percentage": 4.43, "elapsed_time": "0:03:48", "remaining_time": "1:22:11", "throughput": 1422.17, "total_tokens": 325152}
342
+ {"current_steps": 1710, "total_steps": 38480, "loss": 0.2285, "lr": 0.013323804573804573, "epoch": 0.8887733887733887, "percentage": 4.44, "elapsed_time": "0:03:49", "remaining_time": "1:22:10", "throughput": 1421.95, "total_tokens": 326048}
343
+ {"current_steps": 1715, "total_steps": 38480, "loss": 0.2368, "lr": 0.013362785862785862, "epoch": 0.8913721413721414, "percentage": 4.46, "elapsed_time": "0:03:49", "remaining_time": "1:22:09", "throughput": 1421.99, "total_tokens": 327008}
344
+ {"current_steps": 1720, "total_steps": 38480, "loss": 0.2299, "lr": 0.013401767151767151, "epoch": 0.893970893970894, "percentage": 4.47, "elapsed_time": "0:03:50", "remaining_time": "1:22:09", "throughput": 1421.9, "total_tokens": 327936}
345
+ {"current_steps": 1725, "total_steps": 38480, "loss": 0.328, "lr": 0.01344074844074844, "epoch": 0.8965696465696466, "percentage": 4.48, "elapsed_time": "0:03:51", "remaining_time": "1:22:08", "throughput": 1421.94, "total_tokens": 328896}
346
+ {"current_steps": 1730, "total_steps": 38480, "loss": 0.2241, "lr": 0.013479729729729729, "epoch": 0.8991683991683992, "percentage": 4.5, "elapsed_time": "0:03:51", "remaining_time": "1:22:08", "throughput": 1422.01, "total_tokens": 329888}
347
+ {"current_steps": 1735, "total_steps": 38480, "loss": 0.273, "lr": 0.013518711018711018, "epoch": 0.9017671517671517, "percentage": 4.51, "elapsed_time": "0:03:52", "remaining_time": "1:22:07", "throughput": 1422.05, "total_tokens": 330848}
348
+ {"current_steps": 1740, "total_steps": 38480, "loss": 0.2359, "lr": 0.013557692307692307, "epoch": 0.9043659043659044, "percentage": 4.52, "elapsed_time": "0:03:53", "remaining_time": "1:22:06", "throughput": 1421.83, "total_tokens": 331744}
349
+ {"current_steps": 1745, "total_steps": 38480, "loss": 0.2906, "lr": 0.013596673596673598, "epoch": 0.906964656964657, "percentage": 4.53, "elapsed_time": "0:03:53", "remaining_time": "1:22:05", "throughput": 1421.99, "total_tokens": 332736}
350
+ {"current_steps": 1750, "total_steps": 38480, "loss": 0.2425, "lr": 0.013635654885654885, "epoch": 0.9095634095634095, "percentage": 4.55, "elapsed_time": "0:03:54", "remaining_time": "1:22:05", "throughput": 1422.15, "total_tokens": 333728}
351
+ {"current_steps": 1755, "total_steps": 38480, "loss": 0.2651, "lr": 0.013674636174636174, "epoch": 0.9121621621621622, "percentage": 4.56, "elapsed_time": "0:03:55", "remaining_time": "1:22:04", "throughput": 1421.95, "total_tokens": 334624}
352
+ {"current_steps": 1760, "total_steps": 38480, "loss": 0.2666, "lr": 0.013713617463617463, "epoch": 0.9147609147609148, "percentage": 4.57, "elapsed_time": "0:03:56", "remaining_time": "1:22:04", "throughput": 1422.02, "total_tokens": 335616}
353
+ {"current_steps": 1765, "total_steps": 38480, "loss": 0.311, "lr": 0.013752598752598752, "epoch": 0.9173596673596673, "percentage": 4.59, "elapsed_time": "0:03:56", "remaining_time": "1:22:03", "throughput": 1421.93, "total_tokens": 336544}
354
+ {"current_steps": 1770, "total_steps": 38480, "loss": 0.2821, "lr": 0.013791580041580041, "epoch": 0.91995841995842, "percentage": 4.6, "elapsed_time": "0:03:57", "remaining_time": "1:22:02", "throughput": 1421.84, "total_tokens": 337472}
355
+ {"current_steps": 1775, "total_steps": 38480, "loss": 0.2792, "lr": 0.01383056133056133, "epoch": 0.9225571725571725, "percentage": 4.61, "elapsed_time": "0:03:58", "remaining_time": "1:22:01", "throughput": 1421.76, "total_tokens": 338400}
356
+ {"current_steps": 1780, "total_steps": 38480, "loss": 0.2726, "lr": 0.013869542619542619, "epoch": 0.9251559251559252, "percentage": 4.63, "elapsed_time": "0:03:58", "remaining_time": "1:22:01", "throughput": 1421.81, "total_tokens": 339360}
357
+ {"current_steps": 1785, "total_steps": 38480, "loss": 0.3003, "lr": 0.01390852390852391, "epoch": 0.9277546777546778, "percentage": 4.64, "elapsed_time": "0:03:59", "remaining_time": "1:22:00", "throughput": 1421.72, "total_tokens": 340288}
358
+ {"current_steps": 1790, "total_steps": 38480, "loss": 0.2475, "lr": 0.013947505197505197, "epoch": 0.9303534303534303, "percentage": 4.65, "elapsed_time": "0:04:00", "remaining_time": "1:21:59", "throughput": 1422.0, "total_tokens": 341312}
359
+ {"current_steps": 1795, "total_steps": 38480, "loss": 0.2551, "lr": 0.013986486486486486, "epoch": 0.932952182952183, "percentage": 4.66, "elapsed_time": "0:04:00", "remaining_time": "1:21:59", "throughput": 1422.03, "total_tokens": 342272}
360
+ {"current_steps": 1800, "total_steps": 38480, "loss": 0.2867, "lr": 0.014025467775467775, "epoch": 0.9355509355509356, "percentage": 4.68, "elapsed_time": "0:04:01", "remaining_time": "1:21:58", "throughput": 1421.71, "total_tokens": 343136}
361
+ {"current_steps": 1805, "total_steps": 38480, "loss": 0.2794, "lr": 0.014064449064449064, "epoch": 0.9381496881496881, "percentage": 4.69, "elapsed_time": "0:04:02", "remaining_time": "1:21:57", "throughput": 1421.62, "total_tokens": 344064}
362
+ {"current_steps": 1810, "total_steps": 38480, "loss": 0.2745, "lr": 0.014103430353430353, "epoch": 0.9407484407484408, "percentage": 4.7, "elapsed_time": "0:04:02", "remaining_time": "1:21:56", "throughput": 1421.66, "total_tokens": 345024}
363
+ {"current_steps": 1815, "total_steps": 38480, "loss": 0.228, "lr": 0.014142411642411642, "epoch": 0.9433471933471933, "percentage": 4.72, "elapsed_time": "0:04:03", "remaining_time": "1:21:56", "throughput": 1421.81, "total_tokens": 346016}
364
+ {"current_steps": 1820, "total_steps": 38480, "loss": 0.3096, "lr": 0.01418139293139293, "epoch": 0.9459459459459459, "percentage": 4.73, "elapsed_time": "0:04:04", "remaining_time": "1:21:55", "throughput": 1421.96, "total_tokens": 347008}
365
+ {"current_steps": 1825, "total_steps": 38480, "loss": 0.2611, "lr": 0.01422037422037422, "epoch": 0.9485446985446986, "percentage": 4.74, "elapsed_time": "0:04:04", "remaining_time": "1:21:54", "throughput": 1421.89, "total_tokens": 347936}
366
+ {"current_steps": 1830, "total_steps": 38480, "loss": 0.247, "lr": 0.014259355509355509, "epoch": 0.9511434511434511, "percentage": 4.76, "elapsed_time": "0:04:05", "remaining_time": "1:21:54", "throughput": 1421.93, "total_tokens": 348896}
367
+ {"current_steps": 1835, "total_steps": 38480, "loss": 0.2652, "lr": 0.014298336798336798, "epoch": 0.9537422037422038, "percentage": 4.77, "elapsed_time": "0:04:06", "remaining_time": "1:21:53", "throughput": 1421.85, "total_tokens": 349824}
368
+ {"current_steps": 1840, "total_steps": 38480, "loss": 0.2651, "lr": 0.014337318087318087, "epoch": 0.9563409563409564, "percentage": 4.78, "elapsed_time": "0:04:06", "remaining_time": "1:21:52", "throughput": 1421.77, "total_tokens": 350752}
369
+ {"current_steps": 1845, "total_steps": 38480, "loss": 0.2945, "lr": 0.014376299376299376, "epoch": 0.9589397089397089, "percentage": 4.79, "elapsed_time": "0:04:07", "remaining_time": "1:21:51", "throughput": 1421.57, "total_tokens": 351648}
370
+ {"current_steps": 1850, "total_steps": 38480, "loss": 0.274, "lr": 0.014415280665280665, "epoch": 0.9615384615384616, "percentage": 4.81, "elapsed_time": "0:04:08", "remaining_time": "1:21:51", "throughput": 1421.61, "total_tokens": 352608}
371
+ {"current_steps": 1855, "total_steps": 38480, "loss": 0.2753, "lr": 0.014454261954261954, "epoch": 0.9641372141372141, "percentage": 4.82, "elapsed_time": "0:04:08", "remaining_time": "1:21:50", "throughput": 1421.8, "total_tokens": 353632}
372
+ {"current_steps": 1860, "total_steps": 38480, "loss": 0.259, "lr": 0.014493243243243243, "epoch": 0.9667359667359667, "percentage": 4.83, "elapsed_time": "0:04:09", "remaining_time": "1:21:50", "throughput": 1421.83, "total_tokens": 354592}
373
+ {"current_steps": 1865, "total_steps": 38480, "loss": 0.2431, "lr": 0.014532224532224532, "epoch": 0.9693347193347194, "percentage": 4.85, "elapsed_time": "0:04:10", "remaining_time": "1:21:49", "throughput": 1421.51, "total_tokens": 355456}
374
+ {"current_steps": 1870, "total_steps": 38480, "loss": 0.242, "lr": 0.01457120582120582, "epoch": 0.9719334719334719, "percentage": 4.86, "elapsed_time": "0:04:10", "remaining_time": "1:21:48", "throughput": 1421.66, "total_tokens": 356448}
375
+ {"current_steps": 1875, "total_steps": 38480, "loss": 0.1629, "lr": 0.01461018711018711, "epoch": 0.9745322245322245, "percentage": 4.87, "elapsed_time": "0:04:11", "remaining_time": "1:21:47", "throughput": 1421.69, "total_tokens": 357408}
376
+ {"current_steps": 1880, "total_steps": 38480, "loss": 0.2617, "lr": 0.014649168399168399, "epoch": 0.9771309771309772, "percentage": 4.89, "elapsed_time": "0:04:12", "remaining_time": "1:21:47", "throughput": 1421.73, "total_tokens": 358368}
377
+ {"current_steps": 1885, "total_steps": 38480, "loss": 0.3222, "lr": 0.014688149688149688, "epoch": 0.9797297297297297, "percentage": 4.9, "elapsed_time": "0:04:12", "remaining_time": "1:21:46", "throughput": 1421.65, "total_tokens": 359296}
378
+ {"current_steps": 1890, "total_steps": 38480, "loss": 0.2914, "lr": 0.014727130977130977, "epoch": 0.9823284823284824, "percentage": 4.91, "elapsed_time": "0:04:13", "remaining_time": "1:21:45", "throughput": 1421.68, "total_tokens": 360256}
379
+ {"current_steps": 1895, "total_steps": 38480, "loss": 0.2628, "lr": 0.014766112266112266, "epoch": 0.9849272349272349, "percentage": 4.92, "elapsed_time": "0:04:14", "remaining_time": "1:21:45", "throughput": 1421.72, "total_tokens": 361216}
380
+ {"current_steps": 1900, "total_steps": 38480, "loss": 0.2409, "lr": 0.014805093555093555, "epoch": 0.9875259875259875, "percentage": 4.94, "elapsed_time": "0:04:14", "remaining_time": "1:21:44", "throughput": 1421.75, "total_tokens": 362176}
381
+ {"current_steps": 1905, "total_steps": 38480, "loss": 0.3017, "lr": 0.014844074844074844, "epoch": 0.9901247401247402, "percentage": 4.95, "elapsed_time": "0:04:15", "remaining_time": "1:21:43", "throughput": 1422.0, "total_tokens": 363200}
382
+ {"current_steps": 1910, "total_steps": 38480, "loss": 0.2129, "lr": 0.014883056133056132, "epoch": 0.9927234927234927, "percentage": 4.96, "elapsed_time": "0:04:16", "remaining_time": "1:21:43", "throughput": 1422.03, "total_tokens": 364160}
383
+ {"current_steps": 1915, "total_steps": 38480, "loss": 0.2449, "lr": 0.014922037422037421, "epoch": 0.9953222453222453, "percentage": 4.98, "elapsed_time": "0:04:16", "remaining_time": "1:21:42", "throughput": 1421.73, "total_tokens": 365024}
384
+ {"current_steps": 1920, "total_steps": 38480, "loss": 0.2719, "lr": 0.01496101871101871, "epoch": 0.997920997920998, "percentage": 4.99, "elapsed_time": "0:04:17", "remaining_time": "1:21:41", "throughput": 1421.88, "total_tokens": 366016}
385
+ {"current_steps": 1924, "total_steps": 38480, "eval_loss": 0.26113998889923096, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:04:31", "remaining_time": "1:25:51", "throughput": 1352.43, "total_tokens": 366712}
386
+ {"current_steps": 1925, "total_steps": 38480, "loss": 0.2587, "lr": 0.015, "epoch": 1.0005197505197505, "percentage": 5.0, "elapsed_time": "0:04:32", "remaining_time": "1:26:14", "throughput": 1346.48, "total_tokens": 366904}
387
+ {"current_steps": 1930, "total_steps": 38480, "loss": 0.3068, "lr": 0.015038981288981287, "epoch": 1.003118503118503, "percentage": 5.02, "elapsed_time": "0:04:33", "remaining_time": "1:26:14", "throughput": 1346.2, "total_tokens": 367832}
388
+ {"current_steps": 1935, "total_steps": 38480, "loss": 0.2854, "lr": 0.01507796257796258, "epoch": 1.0057172557172558, "percentage": 5.03, "elapsed_time": "0:04:33", "remaining_time": "1:26:13", "throughput": 1346.5, "total_tokens": 368824}
389
+ {"current_steps": 1940, "total_steps": 38480, "loss": 0.275, "lr": 0.015116943866943866, "epoch": 1.0083160083160083, "percentage": 5.04, "elapsed_time": "0:04:34", "remaining_time": "1:26:11", "throughput": 1346.81, "total_tokens": 369816}
390
+ {"current_steps": 1945, "total_steps": 38480, "loss": 0.2915, "lr": 0.015155925155925155, "epoch": 1.0109147609147608, "percentage": 5.05, "elapsed_time": "0:04:35", "remaining_time": "1:26:10", "throughput": 1347.03, "total_tokens": 370776}
391
+ {"current_steps": 1950, "total_steps": 38480, "loss": 0.2943, "lr": 0.015194906444906446, "epoch": 1.0135135135135136, "percentage": 5.07, "elapsed_time": "0:04:35", "remaining_time": "1:26:08", "throughput": 1347.12, "total_tokens": 371704}
392
+ {"current_steps": 1955, "total_steps": 38480, "loss": 0.2769, "lr": 0.015233887733887733, "epoch": 1.0161122661122661, "percentage": 5.08, "elapsed_time": "0:04:36", "remaining_time": "1:26:07", "throughput": 1347.32, "total_tokens": 372664}
393
+ {"current_steps": 1960, "total_steps": 38480, "loss": 0.2615, "lr": 0.015272869022869022, "epoch": 1.0187110187110187, "percentage": 5.09, "elapsed_time": "0:04:37", "remaining_time": "1:26:06", "throughput": 1347.42, "total_tokens": 373592}
394
+ {"current_steps": 1965, "total_steps": 38480, "loss": 0.2921, "lr": 0.01531185031185031, "epoch": 1.0213097713097714, "percentage": 5.11, "elapsed_time": "0:04:37", "remaining_time": "1:26:04", "throughput": 1347.41, "total_tokens": 374488}
395
+ {"current_steps": 1970, "total_steps": 38480, "loss": 0.2536, "lr": 0.0153508316008316, "epoch": 1.023908523908524, "percentage": 5.12, "elapsed_time": "0:04:38", "remaining_time": "1:26:03", "throughput": 1347.5, "total_tokens": 375416}
396
+ {"current_steps": 1975, "total_steps": 38480, "loss": 0.2782, "lr": 0.01538981288981289, "epoch": 1.0265072765072765, "percentage": 5.13, "elapsed_time": "0:04:39", "remaining_time": "1:26:01", "throughput": 1347.47, "total_tokens": 376312}
397
+ {"current_steps": 1980, "total_steps": 38480, "loss": 0.2944, "lr": 0.015428794178794177, "epoch": 1.0291060291060292, "percentage": 5.15, "elapsed_time": "0:04:39", "remaining_time": "1:26:00", "throughput": 1347.32, "total_tokens": 377176}
398
+ {"current_steps": 1985, "total_steps": 38480, "loss": 0.273, "lr": 0.015467775467775467, "epoch": 1.0317047817047817, "percentage": 5.16, "elapsed_time": "0:04:40", "remaining_time": "1:25:59", "throughput": 1347.55, "total_tokens": 378168}
399
+ {"current_steps": 1990, "total_steps": 38480, "loss": 0.2774, "lr": 0.015506756756756756, "epoch": 1.0343035343035343, "percentage": 5.17, "elapsed_time": "0:04:41", "remaining_time": "1:25:58", "throughput": 1347.84, "total_tokens": 379160}
400
+ {"current_steps": 1995, "total_steps": 38480, "loss": 0.2705, "lr": 0.015545738045738043, "epoch": 1.0369022869022868, "percentage": 5.18, "elapsed_time": "0:04:41", "remaining_time": "1:25:56", "throughput": 1348.04, "total_tokens": 380120}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca0420034040df1035b943479e066c4c04a9b72e21edaabce502b8ee11e0e26
3
+ size 6289