lillian039 commited on
Commit
c8063ab
·
verified ·
1 Parent(s): ca4c581

Training in progress, step 100

Browse files
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_vl",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.51.3",
34
+ "use_cache": false,
35
+ "use_sliding_window": false,
36
+ "video_token_id": 151656,
37
+ "vision_config": {
38
+ "depth": 32,
39
+ "embed_dim": 1280,
40
+ "hidden_act": "quick_gelu",
41
+ "hidden_size": 1536,
42
+ "in_channels": 3,
43
+ "in_chans": 3,
44
+ "mlp_ratio": 4,
45
+ "model_type": "qwen2_vl",
46
+ "num_heads": 16,
47
+ "patch_size": 14,
48
+ "spatial_merge_size": 2,
49
+ "spatial_patch_size": 14,
50
+ "temporal_patch_size": 2,
51
+ "torch_dtype": "float32"
52
+ },
53
+ "vision_end_token_id": 151653,
54
+ "vision_start_token_id": 151652,
55
+ "vision_token_id": 151654,
56
+ "vocab_size": 151936
57
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99bffadbd1babbbe93a1c88875cec4152705091b8a89afa55f98bc91a4abb79d
3
+ size 4418050848
special_tokens_map.json CHANGED
@@ -1,36 +1,28 @@
1
  {
2
  "additional_special_tokens": [
3
- {
4
- "content": "<|eot_id|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<|eom_id|>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
  ],
18
- "bos_token": {
19
- "content": "<|begin_of_text|>",
20
- "lstrip": false,
21
- "normalized": false,
22
- "rstrip": false,
23
- "single_word": false
24
- },
25
  "eos_token": {
26
- "content": "<|eot_id|>",
27
  "lstrip": false,
28
  "normalized": false,
29
  "rstrip": false,
30
  "single_word": false
31
  },
32
  "pad_token": {
33
- "content": "<|finetune_right_pad_id|>",
34
  "lstrip": false,
35
  "normalized": false,
36
  "rstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
 
16
  ],
 
 
 
 
 
 
 
17
  "eos_token": {
18
+ "content": "<|im_end|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  },
24
  "pad_token": {
25
+ "content": "<|endoftext|>",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9816d43bd5347d64bccc66b7710947fb18e9818cc660215b1462061d4a44e449
3
- size 17210088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json CHANGED
@@ -1,2055 +1,112 @@
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": "<|finetune_right_pad_id|>",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  },
43
- "128005": {
44
- "content": "<|step_id|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
  "lstrip": false,
86
  "normalized": false,
87
  "rstrip": false,
88
  "single_word": false,
89
  "special": true
90
  },
91
- "128011": {
92
- "content": "<|reserved_special_token_2|>",
93
  "lstrip": false,
94
  "normalized": false,
95
  "rstrip": false,
96
  "single_word": false,
97
  "special": true
98
  },
99
- "128012": {
100
- "content": "<|reserved_special_token_3|>",
101
  "lstrip": false,
102
  "normalized": false,
103
  "rstrip": false,
104
  "single_word": false,
105
  "special": true
106
  },
107
- "128013": {
108
- "content": "<|reserved_special_token_4|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_5|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_6|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_7|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_8|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_9|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_10|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_11|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_12|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_13|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_14|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_15|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_16|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_17|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_18|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_19|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_20|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_21|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_22|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_23|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_24|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_25|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_26|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_27|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_28|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_29|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_30|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_31|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_32|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_33|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_34|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_35|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_36|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_37|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_38|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_39|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_40|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_41|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_42|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_43|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_44|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_45|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_46|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_47|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_48|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_49|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_50|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_51|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_52|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_53|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_54|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_55|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_56|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_57|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_58|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_59|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_60|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_61|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_62|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_63|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_64|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_65|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_66|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_67|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_68|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_69|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_70|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_71|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_72|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_73|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_74|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_75|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_76|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_77|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_78|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_79|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_80|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_81|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_82|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_83|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_84|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_85|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_86|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_87|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_88|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_89|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_90|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_91|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_92|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_93|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_94|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_95|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_96|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_97|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_98|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_99|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_100|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_101|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_102|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_103|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_104|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_105|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_106|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_107|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_108|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_109|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_110|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_111|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_112|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_113|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_114|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_115|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_116|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_117|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_118|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_119|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_120|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_121|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_122|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_123|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_124|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_125|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_126|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_127|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_128|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_129|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_130|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_131|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_132|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_133|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_134|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_135|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_136|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_137|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_138|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_139|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_140|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_141|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_142|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_143|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_144|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_145|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_146|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_147|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_148|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_149|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_150|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_151|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_152|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_153|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_154|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_155|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_156|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_157|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_158|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_159|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_160|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_161|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_162|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_163|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_164|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_165|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_166|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_167|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_168|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_169|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_170|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_171|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_172|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_173|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_174|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_175|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_176|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_177|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_178|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_179|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_180|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_181|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_182|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_183|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_184|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_185|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_186|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_187|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_188|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_189|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_190|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_191|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_192|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_193|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_194|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_195|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_196|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_197|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_198|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_199|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_200|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_201|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_202|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_203|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_204|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_205|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_206|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_207|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_208|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_209|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_210|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_211|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_212|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_213|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_214|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_215|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_216|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_217|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_218|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_219|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_220|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_221|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_222|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_223|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_224|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_225|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_226|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_227|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_228|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_229|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_230|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_231|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_232|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_233|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_234|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_235|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_236|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_237|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_238|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_239|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_240|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_241|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_242|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_243|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_244|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_245|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_246|>",
2045
- "lstrip": false,
2046
- "normalized": false,
2047
- "rstrip": false,
2048
- "single_word": false,
2049
- "special": true
2050
- },
2051
- "128256": {
2052
- "content": "<|image|>",
2053
  "lstrip": false,
2054
  "normalized": false,
2055
  "rstrip": false,
@@ -2058,21 +115,30 @@
2058
  }
2059
  },
2060
  "additional_special_tokens": [
2061
- "<|eot_id|>",
2062
- "<|eom_id|>"
2063
- ],
2064
- "bos_token": "<|begin_of_text|>",
2065
- "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- set user_supplied_system_message = true %}\n{%- else %}\n {%- set system_message = \"\" %}\n {%- set user_supplied_system_message = false %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %} \n{%- for message in messages %}\n {%- for content in message['content'] %}\n {%- if content['type'] == 'image' %}\n {%- set image_ns.has_images = true %}\n {%- endif %}\n {%- endfor %}\n{%- endfor %}\n\n{#- System message if there are no images, or if the user supplied one #}\n{%- if user_supplied_system_message or not image_ns.has_images %}\n {{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n {%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n {%- endif %}\n {{- \"Cutting Knowledge Date: December 2023\\n\" }}\n {{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n {%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {%- endif %}\n {{- system_message }}\n {{- \"<|eot_id|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n {%- if message['content'] is string %}\n {{- message['content'] }}\n {%- else %}\n {%- for content in message['content'] %}\n {%- if content['type'] == 'image' %}\n {{- '<|image|>' }}\n {%- elif content['type'] == 'text' %}\n {{- content['text'] }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2066
- "clean_up_tokenization_spaces": true,
2067
- "eos_token": "<|eot_id|>",
2068
- "model_input_names": [
2069
- "input_ids",
2070
- "attention_mask"
 
 
 
2071
  ],
2072
- "model_max_length": 131072,
2073
- "pad_token": "<|finetune_right_pad_id|>",
 
 
 
 
 
 
2074
  "padding_side": "right",
2075
- "processor_class": "MllamaProcessor",
2076
  "split_special_tokens": false,
2077
- "tokenizer_class": "PreTrainedTokenizerFast"
 
2078
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
  "lstrip": false,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
49
  "single_word": false,
50
  "special": true
51
  },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
  "lstrip": false,
55
  "normalized": false,
56
  "rstrip": false,
57
  "single_word": false,
58
  "special": true
59
  },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
  "lstrip": false,
63
  "normalized": false,
64
  "rstrip": false,
65
  "single_word": false,
66
  "special": true
67
  },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
  "lstrip": false,
71
  "normalized": false,
72
  "rstrip": false,
73
  "single_word": false,
74
  "special": true
75
  },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
  "lstrip": false,
79
  "normalized": false,
80
  "rstrip": false,
81
  "single_word": false,
82
  "special": true
83
  },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
  "lstrip": false,
87
  "normalized": false,
88
  "rstrip": false,
89
  "single_word": false,
90
  "special": true
91
  },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
  "lstrip": false,
95
  "normalized": false,
96
  "rstrip": false,
97
  "single_word": false,
98
  "special": true
99
  },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
  "lstrip": false,
103
  "normalized": false,
104
  "rstrip": false,
105
  "single_word": false,
106
  "special": true
107
  },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
110
  "lstrip": false,
111
  "normalized": false,
112
  "rstrip": false,
 
115
  }
116
  },
117
  "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
  ],
132
+ "bos_token": null,
133
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "extra_special_tokens": {},
138
+ "model_max_length": 32768,
139
+ "pad_token": "<|endoftext|>",
140
  "padding_side": "right",
 
141
  "split_special_tokens": false,
142
+ "tokenizer_class": "Qwen2Tokenizer",
143
+ "unk_token": null
144
  }
trainer_log.jsonl CHANGED
@@ -1,352 +1,11 @@
1
- {"current_steps": 10, "total_steps": 3453, "loss": 0.9018, "lr": 2.8901734104046244e-06, "epoch": 0.008688097306689836, "percentage": 0.29, "elapsed_time": "0:03:44", "remaining_time": "21:28:49"}
2
- {"current_steps": 20, "total_steps": 3453, "loss": 0.7737, "lr": 5.780346820809249e-06, "epoch": 0.01737619461337967, "percentage": 0.58, "elapsed_time": "0:07:19", "remaining_time": "20:58:36"}
3
- {"current_steps": 30, "total_steps": 3453, "loss": 0.3131, "lr": 8.670520231213873e-06, "epoch": 0.026064291920069503, "percentage": 0.87, "elapsed_time": "0:10:55", "remaining_time": "20:46:28"}
4
- {"current_steps": 40, "total_steps": 3453, "loss": 0.0834, "lr": 1.1560693641618498e-05, "epoch": 0.03475238922675934, "percentage": 1.16, "elapsed_time": "0:14:30", "remaining_time": "20:38:22"}
5
- {"current_steps": 50, "total_steps": 3453, "loss": 0.0815, "lr": 1.4450867052023123e-05, "epoch": 0.043440486533449174, "percentage": 1.45, "elapsed_time": "0:18:06", "remaining_time": "20:32:06"}
6
- {"current_steps": 60, "total_steps": 3453, "loss": 0.0784, "lr": 1.7341040462427746e-05, "epoch": 0.052128583840139006, "percentage": 1.74, "elapsed_time": "0:21:41", "remaining_time": "20:26:33"}
7
- {"current_steps": 70, "total_steps": 3453, "loss": 0.079, "lr": 2.023121387283237e-05, "epoch": 0.060816681146828845, "percentage": 2.03, "elapsed_time": "0:25:16", "remaining_time": "20:21:51"}
8
- {"current_steps": 80, "total_steps": 3453, "loss": 0.0785, "lr": 2.3121387283236996e-05, "epoch": 0.06950477845351868, "percentage": 2.32, "elapsed_time": "0:28:52", "remaining_time": "20:17:19"}
9
- {"current_steps": 90, "total_steps": 3453, "loss": 0.0774, "lr": 2.6011560693641617e-05, "epoch": 0.07819287576020852, "percentage": 2.61, "elapsed_time": "0:32:27", "remaining_time": "20:13:00"}
10
- {"current_steps": 100, "total_steps": 3453, "loss": 0.077, "lr": 2.8901734104046245e-05, "epoch": 0.08688097306689835, "percentage": 2.9, "elapsed_time": "0:36:03", "remaining_time": "20:08:50"}
11
- {"current_steps": 110, "total_steps": 3453, "loss": 0.077, "lr": 3.179190751445087e-05, "epoch": 0.09556907037358818, "percentage": 3.19, "elapsed_time": "0:39:38", "remaining_time": "20:04:47"}
12
- {"current_steps": 120, "total_steps": 3453, "loss": 0.0764, "lr": 3.468208092485549e-05, "epoch": 0.10425716768027801, "percentage": 3.48, "elapsed_time": "0:43:13", "remaining_time": "20:00:47"}
13
- {"current_steps": 130, "total_steps": 3453, "loss": 0.0776, "lr": 3.757225433526011e-05, "epoch": 0.11294526498696786, "percentage": 3.76, "elapsed_time": "0:46:49", "remaining_time": "19:56:52"}
14
- {"current_steps": 140, "total_steps": 3453, "loss": 0.0782, "lr": 4.046242774566474e-05, "epoch": 0.12163336229365769, "percentage": 4.05, "elapsed_time": "0:50:24", "remaining_time": "19:52:58"}
15
- {"current_steps": 150, "total_steps": 3453, "loss": 0.0766, "lr": 4.335260115606937e-05, "epoch": 0.13032145960034752, "percentage": 4.34, "elapsed_time": "0:54:00", "remaining_time": "19:49:10"}
16
- {"current_steps": 160, "total_steps": 3453, "loss": 0.0778, "lr": 4.624277456647399e-05, "epoch": 0.13900955690703737, "percentage": 4.63, "elapsed_time": "0:57:35", "remaining_time": "19:45:21"}
17
- {"current_steps": 170, "total_steps": 3453, "loss": 0.0769, "lr": 4.913294797687861e-05, "epoch": 0.1476976542137272, "percentage": 4.92, "elapsed_time": "1:01:11", "remaining_time": "19:41:35"}
18
- {"current_steps": 180, "total_steps": 3453, "loss": 0.0751, "lr": 5.2023121387283234e-05, "epoch": 0.15638575152041703, "percentage": 5.21, "elapsed_time": "1:04:46", "remaining_time": "19:37:49"}
19
- {"current_steps": 190, "total_steps": 3453, "loss": 0.0783, "lr": 5.491329479768786e-05, "epoch": 0.16507384882710685, "percentage": 5.5, "elapsed_time": "1:08:21", "remaining_time": "19:34:04"}
20
- {"current_steps": 200, "total_steps": 3453, "loss": 0.0754, "lr": 5.780346820809249e-05, "epoch": 0.1737619461337967, "percentage": 5.79, "elapsed_time": "1:11:57", "remaining_time": "19:30:21"}
21
- {"current_steps": 210, "total_steps": 3453, "loss": 0.0744, "lr": 6.069364161849711e-05, "epoch": 0.18245004344048654, "percentage": 6.08, "elapsed_time": "1:15:32", "remaining_time": "19:26:40"}
22
- {"current_steps": 220, "total_steps": 3453, "loss": 0.0772, "lr": 6.358381502890174e-05, "epoch": 0.19113814074717636, "percentage": 6.37, "elapsed_time": "1:19:08", "remaining_time": "19:22:58"}
23
- {"current_steps": 230, "total_steps": 3453, "loss": 0.0758, "lr": 6.647398843930635e-05, "epoch": 0.1998262380538662, "percentage": 6.66, "elapsed_time": "1:22:43", "remaining_time": "19:19:14"}
24
- {"current_steps": 240, "total_steps": 3453, "loss": 0.0782, "lr": 6.936416184971098e-05, "epoch": 0.20851433536055602, "percentage": 6.95, "elapsed_time": "1:26:19", "remaining_time": "19:15:34"}
25
- {"current_steps": 250, "total_steps": 3453, "loss": 0.0768, "lr": 7.225433526011561e-05, "epoch": 0.21720243266724587, "percentage": 7.24, "elapsed_time": "1:29:54", "remaining_time": "19:11:52"}
26
- {"current_steps": 260, "total_steps": 3453, "loss": 0.0797, "lr": 7.514450867052023e-05, "epoch": 0.22589052997393572, "percentage": 7.53, "elapsed_time": "1:33:29", "remaining_time": "19:08:11"}
27
- {"current_steps": 270, "total_steps": 3453, "loss": 0.0788, "lr": 7.803468208092485e-05, "epoch": 0.23457862728062553, "percentage": 7.82, "elapsed_time": "1:37:05", "remaining_time": "19:04:31"}
28
- {"current_steps": 280, "total_steps": 3453, "loss": 0.0781, "lr": 8.092485549132948e-05, "epoch": 0.24326672458731538, "percentage": 8.11, "elapsed_time": "1:40:40", "remaining_time": "19:00:52"}
29
- {"current_steps": 290, "total_steps": 3453, "loss": 0.0795, "lr": 8.381502890173411e-05, "epoch": 0.2519548218940052, "percentage": 8.4, "elapsed_time": "1:44:16", "remaining_time": "18:57:14"}
30
- {"current_steps": 300, "total_steps": 3453, "loss": 0.0765, "lr": 8.670520231213874e-05, "epoch": 0.26064291920069504, "percentage": 8.69, "elapsed_time": "1:47:51", "remaining_time": "18:53:35"}
31
- {"current_steps": 310, "total_steps": 3453, "loss": 0.0718, "lr": 8.959537572254337e-05, "epoch": 0.2693310165073849, "percentage": 8.98, "elapsed_time": "1:51:26", "remaining_time": "18:49:57"}
32
- {"current_steps": 320, "total_steps": 3453, "loss": 0.0761, "lr": 9.248554913294798e-05, "epoch": 0.27801911381407474, "percentage": 9.27, "elapsed_time": "1:55:02", "remaining_time": "18:46:17"}
33
- {"current_steps": 330, "total_steps": 3453, "loss": 0.0702, "lr": 9.537572254335261e-05, "epoch": 0.2867072111207645, "percentage": 9.56, "elapsed_time": "1:58:37", "remaining_time": "18:42:38"}
34
- {"current_steps": 340, "total_steps": 3453, "loss": 0.0711, "lr": 9.826589595375723e-05, "epoch": 0.2953953084274544, "percentage": 9.85, "elapsed_time": "2:02:12", "remaining_time": "18:38:58"}
35
- {"current_steps": 350, "total_steps": 3453, "loss": 0.0679, "lr": 9.999959104394929e-05, "epoch": 0.3040834057341442, "percentage": 10.14, "elapsed_time": "2:05:48", "remaining_time": "18:35:20"}
36
- {"current_steps": 360, "total_steps": 3453, "loss": 0.074, "lr": 9.999499036520664e-05, "epoch": 0.31277150304083406, "percentage": 10.43, "elapsed_time": "2:09:23", "remaining_time": "18:31:43"}
37
- {"current_steps": 370, "total_steps": 3453, "loss": 0.0699, "lr": 9.998527828459135e-05, "epoch": 0.3214596003475239, "percentage": 10.72, "elapsed_time": "2:12:59", "remaining_time": "18:28:05"}
38
- {"current_steps": 380, "total_steps": 3453, "loss": 0.073, "lr": 9.997045579504985e-05, "epoch": 0.3301476976542137, "percentage": 11.0, "elapsed_time": "2:16:34", "remaining_time": "18:24:28"}
39
- {"current_steps": 390, "total_steps": 3453, "loss": 0.0666, "lr": 9.995052441200799e-05, "epoch": 0.33883579496090355, "percentage": 11.29, "elapsed_time": "2:20:10", "remaining_time": "18:20:51"}
40
- {"current_steps": 400, "total_steps": 3453, "loss": 0.0735, "lr": 9.992548617321612e-05, "epoch": 0.3475238922675934, "percentage": 11.58, "elapsed_time": "2:23:45", "remaining_time": "18:17:13"}
41
- {"current_steps": 410, "total_steps": 3453, "loss": 0.0707, "lr": 9.989534363854072e-05, "epoch": 0.35621198957428324, "percentage": 11.87, "elapsed_time": "2:27:20", "remaining_time": "18:13:36"}
42
- {"current_steps": 420, "total_steps": 3453, "loss": 0.0768, "lr": 9.986009988970273e-05, "epoch": 0.3649000868809731, "percentage": 12.16, "elapsed_time": "2:30:56", "remaining_time": "18:09:58"}
43
- {"current_steps": 430, "total_steps": 3453, "loss": 0.074, "lr": 9.981975852996243e-05, "epoch": 0.3735881841876629, "percentage": 12.45, "elapsed_time": "2:34:31", "remaining_time": "18:06:21"}
44
- {"current_steps": 440, "total_steps": 3453, "loss": 0.0729, "lr": 9.977432368375113e-05, "epoch": 0.3822762814943527, "percentage": 12.74, "elapsed_time": "2:38:07", "remaining_time": "18:02:44"}
45
- {"current_steps": 450, "total_steps": 3453, "loss": 0.0678, "lr": 9.972379999624936e-05, "epoch": 0.39096437880104257, "percentage": 13.03, "elapsed_time": "2:41:42", "remaining_time": "17:59:07"}
46
- {"current_steps": 460, "total_steps": 3453, "loss": 0.0707, "lr": 9.96681926329121e-05, "epoch": 0.3996524761077324, "percentage": 13.32, "elapsed_time": "2:45:17", "remaining_time": "17:55:29"}
47
- {"current_steps": 470, "total_steps": 3453, "loss": 0.0732, "lr": 9.960750727894057e-05, "epoch": 0.40834057341442226, "percentage": 13.61, "elapsed_time": "2:48:53", "remaining_time": "17:51:52"}
48
- {"current_steps": 480, "total_steps": 3453, "loss": 0.0686, "lr": 9.954175013870108e-05, "epoch": 0.41702867072111205, "percentage": 13.9, "elapsed_time": "2:52:28", "remaining_time": "17:48:15"}
49
- {"current_steps": 490, "total_steps": 3453, "loss": 0.0709, "lr": 9.947092793509056e-05, "epoch": 0.4257167680278019, "percentage": 14.19, "elapsed_time": "2:56:03", "remaining_time": "17:44:38"}
50
- {"current_steps": 500, "total_steps": 3453, "loss": 0.072, "lr": 9.939504790884939e-05, "epoch": 0.43440486533449174, "percentage": 14.48, "elapsed_time": "2:59:39", "remaining_time": "17:41:01"}
51
- {"current_steps": 500, "total_steps": 3453, "eval_loss": 0.06750335544347763, "epoch": 0.43440486533449174, "percentage": 14.48, "elapsed_time": "3:02:03", "remaining_time": "17:55:16"}
52
- {"current_steps": 510, "total_steps": 3453, "loss": 0.0728, "lr": 9.931411781782103e-05, "epoch": 0.4430929626411816, "percentage": 14.77, "elapsed_time": "3:05:38", "remaining_time": "17:51:15"}
53
- {"current_steps": 520, "total_steps": 3453, "loss": 0.0711, "lr": 9.922814593615883e-05, "epoch": 0.45178105994787143, "percentage": 15.06, "elapsed_time": "3:09:13", "remaining_time": "17:47:19"}
54
- {"current_steps": 530, "total_steps": 3453, "loss": 0.0674, "lr": 9.913714105348023e-05, "epoch": 0.4604691572545613, "percentage": 15.35, "elapsed_time": "3:12:49", "remaining_time": "17:43:24"}
55
- {"current_steps": 540, "total_steps": 3453, "loss": 0.0652, "lr": 9.904111247396793e-05, "epoch": 0.46915725456125107, "percentage": 15.64, "elapsed_time": "3:16:24", "remaining_time": "17:39:29"}
56
- {"current_steps": 550, "total_steps": 3453, "loss": 0.0705, "lr": 9.894007001541888e-05, "epoch": 0.4778453518679409, "percentage": 15.93, "elapsed_time": "3:19:59", "remaining_time": "17:35:36"}
57
- {"current_steps": 560, "total_steps": 3453, "loss": 0.0752, "lr": 9.883402400824032e-05, "epoch": 0.48653344917463076, "percentage": 16.22, "elapsed_time": "3:23:35", "remaining_time": "17:31:43"}
58
- {"current_steps": 570, "total_steps": 3453, "loss": 0.0726, "lr": 9.872298529439374e-05, "epoch": 0.4952215464813206, "percentage": 16.51, "elapsed_time": "3:27:10", "remaining_time": "17:27:51"}
59
- {"current_steps": 580, "total_steps": 3453, "loss": 0.0685, "lr": 9.860696522628639e-05, "epoch": 0.5039096437880104, "percentage": 16.8, "elapsed_time": "3:30:45", "remaining_time": "17:24:00"}
60
- {"current_steps": 590, "total_steps": 3453, "loss": 0.0694, "lr": 9.848597566561054e-05, "epoch": 0.5125977410947002, "percentage": 17.09, "elapsed_time": "3:34:21", "remaining_time": "17:20:09"}
61
- {"current_steps": 600, "total_steps": 3453, "loss": 0.0691, "lr": 9.836002898213093e-05, "epoch": 0.5212858384013901, "percentage": 17.38, "elapsed_time": "3:37:56", "remaining_time": "17:16:19"}
62
- {"current_steps": 610, "total_steps": 3453, "loss": 0.069, "lr": 9.822913805241996e-05, "epoch": 0.5299739357080799, "percentage": 17.67, "elapsed_time": "3:41:31", "remaining_time": "17:12:28"}
63
- {"current_steps": 620, "total_steps": 3453, "loss": 0.0675, "lr": 9.809331625854128e-05, "epoch": 0.5386620330147698, "percentage": 17.96, "elapsed_time": "3:45:07", "remaining_time": "17:08:39"}
64
- {"current_steps": 630, "total_steps": 3453, "loss": 0.0719, "lr": 9.795257748668163e-05, "epoch": 0.5473501303214596, "percentage": 18.25, "elapsed_time": "3:48:42", "remaining_time": "17:04:49"}
65
- {"current_steps": 640, "total_steps": 3453, "loss": 0.067, "lr": 9.780693612573108e-05, "epoch": 0.5560382276281495, "percentage": 18.53, "elapsed_time": "3:52:17", "remaining_time": "17:01:01"}
66
- {"current_steps": 650, "total_steps": 3453, "loss": 0.0688, "lr": 9.765640706581205e-05, "epoch": 0.5647263249348393, "percentage": 18.82, "elapsed_time": "3:55:53", "remaining_time": "16:57:14"}
67
- {"current_steps": 660, "total_steps": 3453, "loss": 0.0683, "lr": 9.750100569675684e-05, "epoch": 0.573414422241529, "percentage": 19.11, "elapsed_time": "3:59:28", "remaining_time": "16:53:26"}
68
- {"current_steps": 670, "total_steps": 3453, "loss": 0.0652, "lr": 9.734074790653428e-05, "epoch": 0.5821025195482189, "percentage": 19.4, "elapsed_time": "4:03:04", "remaining_time": "16:49:38"}
69
- {"current_steps": 680, "total_steps": 3453, "loss": 0.0655, "lr": 9.71756500796254e-05, "epoch": 0.5907906168549087, "percentage": 19.69, "elapsed_time": "4:06:39", "remaining_time": "16:45:51"}
70
- {"current_steps": 690, "total_steps": 3453, "loss": 0.0567, "lr": 9.700572909534818e-05, "epoch": 0.5994787141615986, "percentage": 19.98, "elapsed_time": "4:10:14", "remaining_time": "16:42:04"}
71
- {"current_steps": 700, "total_steps": 3453, "loss": 0.0842, "lr": 9.683100232613193e-05, "epoch": 0.6081668114682884, "percentage": 20.27, "elapsed_time": "4:13:50", "remaining_time": "16:38:17"}
72
- {"current_steps": 710, "total_steps": 3453, "loss": 0.0682, "lr": 9.665148763574123e-05, "epoch": 0.6168549087749783, "percentage": 20.56, "elapsed_time": "4:17:25", "remaining_time": "16:34:31"}
73
- {"current_steps": 720, "total_steps": 3453, "loss": 0.0694, "lr": 9.646720337744941e-05, "epoch": 0.6255430060816681, "percentage": 20.85, "elapsed_time": "4:21:00", "remaining_time": "16:30:45"}
74
- {"current_steps": 730, "total_steps": 3453, "loss": 0.0708, "lr": 9.627816839216226e-05, "epoch": 0.634231103388358, "percentage": 21.14, "elapsed_time": "4:24:36", "remaining_time": "16:27:00"}
75
- {"current_steps": 740, "total_steps": 3453, "loss": 0.0703, "lr": 9.60844020064917e-05, "epoch": 0.6429192006950478, "percentage": 21.43, "elapsed_time": "4:28:11", "remaining_time": "16:23:15"}
76
- {"current_steps": 750, "total_steps": 3453, "loss": 0.0685, "lr": 9.588592403077993e-05, "epoch": 0.6516072980017377, "percentage": 21.72, "elapsed_time": "4:31:46", "remaining_time": "16:19:29"}
77
- {"current_steps": 760, "total_steps": 3453, "loss": 0.0631, "lr": 9.568275475707402e-05, "epoch": 0.6602953953084274, "percentage": 22.01, "elapsed_time": "4:35:22", "remaining_time": "16:15:44"}
78
- {"current_steps": 770, "total_steps": 3453, "loss": 0.0683, "lr": 9.54749149570512e-05, "epoch": 0.6689834926151172, "percentage": 22.3, "elapsed_time": "4:38:57", "remaining_time": "16:12:00"}
79
- {"current_steps": 780, "total_steps": 3453, "loss": 0.0587, "lr": 9.526242587989542e-05, "epoch": 0.6776715899218071, "percentage": 22.59, "elapsed_time": "4:42:32", "remaining_time": "16:08:16"}
80
- {"current_steps": 790, "total_steps": 3453, "loss": 0.0681, "lr": 9.504530925012461e-05, "epoch": 0.6863596872284969, "percentage": 22.88, "elapsed_time": "4:46:08", "remaining_time": "16:04:31"}
81
- {"current_steps": 800, "total_steps": 3453, "loss": 0.0689, "lr": 9.482358726536975e-05, "epoch": 0.6950477845351868, "percentage": 23.17, "elapsed_time": "4:49:43", "remaining_time": "16:00:48"}
82
- {"current_steps": 810, "total_steps": 3453, "loss": 0.0632, "lr": 9.459728259410547e-05, "epoch": 0.7037358818418766, "percentage": 23.46, "elapsed_time": "4:53:18", "remaining_time": "15:57:04"}
83
- {"current_steps": 820, "total_steps": 3453, "loss": 0.0756, "lr": 9.436641837333231e-05, "epoch": 0.7124239791485665, "percentage": 23.75, "elapsed_time": "4:56:54", "remaining_time": "15:53:21"}
84
- {"current_steps": 830, "total_steps": 3453, "loss": 0.0653, "lr": 9.413101820621136e-05, "epoch": 0.7211120764552563, "percentage": 24.04, "elapsed_time": "5:00:29", "remaining_time": "15:49:38"}
85
- {"current_steps": 840, "total_steps": 3453, "loss": 0.07, "lr": 9.389110615965102e-05, "epoch": 0.7298001737619462, "percentage": 24.33, "elapsed_time": "5:04:05", "remaining_time": "15:45:55"}
86
- {"current_steps": 850, "total_steps": 3453, "loss": 0.061, "lr": 9.364670676184652e-05, "epoch": 0.738488271068636, "percentage": 24.62, "elapsed_time": "5:07:40", "remaining_time": "15:42:12"}
87
- {"current_steps": 860, "total_steps": 3453, "loss": 0.0611, "lr": 9.33978449997722e-05, "epoch": 0.7471763683753258, "percentage": 24.91, "elapsed_time": "5:11:15", "remaining_time": "15:38:30"}
88
- {"current_steps": 870, "total_steps": 3453, "loss": 0.0742, "lr": 9.314454631662679e-05, "epoch": 0.7558644656820156, "percentage": 25.2, "elapsed_time": "5:14:51", "remaining_time": "15:34:47"}
89
- {"current_steps": 880, "total_steps": 3453, "loss": 0.0633, "lr": 9.288683660923223e-05, "epoch": 0.7645525629887054, "percentage": 25.49, "elapsed_time": "5:18:26", "remaining_time": "15:31:05"}
90
- {"current_steps": 890, "total_steps": 3453, "loss": 0.0634, "lr": 9.2624742225386e-05, "epoch": 0.7732406602953953, "percentage": 25.77, "elapsed_time": "5:22:02", "remaining_time": "15:27:23"}
91
- {"current_steps": 900, "total_steps": 3453, "loss": 0.0672, "lr": 9.235828996116735e-05, "epoch": 0.7819287576020851, "percentage": 26.06, "elapsed_time": "5:25:37", "remaining_time": "15:23:41"}
92
- {"current_steps": 910, "total_steps": 3453, "loss": 0.0637, "lr": 9.208750705819776e-05, "epoch": 0.790616854908775, "percentage": 26.35, "elapsed_time": "5:29:12", "remaining_time": "15:19:59"}
93
- {"current_steps": 920, "total_steps": 3453, "loss": 0.0671, "lr": 9.181242120085571e-05, "epoch": 0.7993049522154648, "percentage": 26.64, "elapsed_time": "5:32:48", "remaining_time": "15:16:17"}
94
- {"current_steps": 930, "total_steps": 3453, "loss": 0.0651, "lr": 9.153306051344643e-05, "epoch": 0.8079930495221547, "percentage": 26.93, "elapsed_time": "5:36:23", "remaining_time": "15:12:35"}
95
- {"current_steps": 940, "total_steps": 3453, "loss": 0.0709, "lr": 9.124945355732635e-05, "epoch": 0.8166811468288445, "percentage": 27.22, "elapsed_time": "5:39:58", "remaining_time": "15:08:54"}
96
- {"current_steps": 950, "total_steps": 3453, "loss": 0.0688, "lr": 9.096162932798312e-05, "epoch": 0.8253692441355344, "percentage": 27.51, "elapsed_time": "5:43:34", "remaining_time": "15:05:12"}
97
- {"current_steps": 960, "total_steps": 3453, "loss": 0.0668, "lr": 9.066961725207119e-05, "epoch": 0.8340573414422241, "percentage": 27.8, "elapsed_time": "5:47:09", "remaining_time": "15:01:31"}
98
- {"current_steps": 970, "total_steps": 3453, "loss": 0.0696, "lr": 9.037344718440322e-05, "epoch": 0.8427454387489139, "percentage": 28.09, "elapsed_time": "5:50:44", "remaining_time": "14:57:50"}
99
- {"current_steps": 980, "total_steps": 3453, "loss": 0.0668, "lr": 9.007314940489781e-05, "epoch": 0.8514335360556038, "percentage": 28.38, "elapsed_time": "5:54:20", "remaining_time": "14:54:09"}
100
- {"current_steps": 990, "total_steps": 3453, "loss": 0.0623, "lr": 8.976875461548373e-05, "epoch": 0.8601216333622936, "percentage": 28.67, "elapsed_time": "5:57:55", "remaining_time": "14:50:28"}
101
- {"current_steps": 1000, "total_steps": 3453, "loss": 0.0695, "lr": 8.946029393696098e-05, "epoch": 0.8688097306689835, "percentage": 28.96, "elapsed_time": "6:01:30", "remaining_time": "14:46:47"}
102
- {"current_steps": 1000, "total_steps": 3453, "eval_loss": 0.06514425575733185, "epoch": 0.8688097306689835, "percentage": 28.96, "elapsed_time": "6:03:55", "remaining_time": "14:52:42"}
103
- {"current_steps": 1010, "total_steps": 3453, "loss": 0.0609, "lr": 8.91477989058191e-05, "epoch": 0.8774978279756733, "percentage": 29.25, "elapsed_time": "6:07:30", "remaining_time": "14:48:55"}
104
- {"current_steps": 1020, "total_steps": 3453, "loss": 0.0686, "lr": 8.883130147101284e-05, "epoch": 0.8861859252823632, "percentage": 29.54, "elapsed_time": "6:11:05", "remaining_time": "14:45:09"}
105
- {"current_steps": 1030, "total_steps": 3453, "loss": 0.0713, "lr": 8.851083399069591e-05, "epoch": 0.894874022589053, "percentage": 29.83, "elapsed_time": "6:14:40", "remaining_time": "14:41:24"}
106
- {"current_steps": 1040, "total_steps": 3453, "loss": 0.0703, "lr": 8.818642922891261e-05, "epoch": 0.9035621198957429, "percentage": 30.12, "elapsed_time": "6:18:16", "remaining_time": "14:37:39"}
107
- {"current_steps": 1050, "total_steps": 3453, "loss": 0.0577, "lr": 8.785812035224812e-05, "epoch": 0.9122502172024327, "percentage": 30.41, "elapsed_time": "6:21:51", "remaining_time": "14:33:54"}
108
- {"current_steps": 1060, "total_steps": 3453, "loss": 0.0645, "lr": 8.752594092643761e-05, "epoch": 0.9209383145091226, "percentage": 30.7, "elapsed_time": "6:25:26", "remaining_time": "14:30:09"}
109
- {"current_steps": 1070, "total_steps": 3453, "loss": 0.0672, "lr": 8.718992491293457e-05, "epoch": 0.9296264118158123, "percentage": 30.99, "elapsed_time": "6:29:01", "remaining_time": "14:26:25"}
110
- {"current_steps": 1080, "total_steps": 3453, "loss": 0.0697, "lr": 8.685010666543858e-05, "epoch": 0.9383145091225021, "percentage": 31.28, "elapsed_time": "6:32:37", "remaining_time": "14:22:40"}
111
- {"current_steps": 1090, "total_steps": 3453, "loss": 0.0692, "lr": 8.650652092638314e-05, "epoch": 0.947002606429192, "percentage": 31.57, "elapsed_time": "6:36:12", "remaining_time": "14:18:56"}
112
- {"current_steps": 1100, "total_steps": 3453, "loss": 0.0653, "lr": 8.615920282338355e-05, "epoch": 0.9556907037358818, "percentage": 31.86, "elapsed_time": "6:39:47", "remaining_time": "14:15:12"}
113
- {"current_steps": 1110, "total_steps": 3453, "loss": 0.0607, "lr": 8.580818786564562e-05, "epoch": 0.9643788010425717, "percentage": 32.15, "elapsed_time": "6:43:23", "remaining_time": "14:11:28"}
114
- {"current_steps": 1120, "total_steps": 3453, "loss": 0.0627, "lr": 8.545351194033527e-05, "epoch": 0.9730668983492615, "percentage": 32.44, "elapsed_time": "6:46:58", "remaining_time": "14:07:45"}
115
- {"current_steps": 1130, "total_steps": 3453, "loss": 0.0669, "lr": 8.509521130890935e-05, "epoch": 0.9817549956559514, "percentage": 32.73, "elapsed_time": "6:50:34", "remaining_time": "14:04:01"}
116
- {"current_steps": 1140, "total_steps": 3453, "loss": 0.068, "lr": 8.473332260340852e-05, "epoch": 0.9904430929626412, "percentage": 33.01, "elapsed_time": "6:54:09", "remaining_time": "14:00:18"}
117
- {"current_steps": 1150, "total_steps": 3453, "loss": 0.0715, "lr": 8.436788282271195e-05, "epoch": 0.9991311902693311, "percentage": 33.3, "elapsed_time": "6:57:44", "remaining_time": "13:56:35"}
118
- {"current_steps": 1160, "total_steps": 3453, "loss": 0.0683, "lr": 8.39989293287546e-05, "epoch": 1.0078192875760208, "percentage": 33.59, "elapsed_time": "7:01:20", "remaining_time": "13:52:51"}
119
- {"current_steps": 1170, "total_steps": 3453, "loss": 0.0597, "lr": 8.362649984270746e-05, "epoch": 1.0165073848827106, "percentage": 33.88, "elapsed_time": "7:04:55", "remaining_time": "13:49:08"}
120
- {"current_steps": 1180, "total_steps": 3453, "loss": 0.0591, "lr": 8.325063244112095e-05, "epoch": 1.0251954821894005, "percentage": 34.17, "elapsed_time": "7:08:30", "remaining_time": "13:45:26"}
121
- {"current_steps": 1190, "total_steps": 3453, "loss": 0.0613, "lr": 8.287136555203213e-05, "epoch": 1.0338835794960903, "percentage": 34.46, "elapsed_time": "7:12:06", "remaining_time": "13:41:43"}
122
- {"current_steps": 1200, "total_steps": 3453, "loss": 0.0638, "lr": 8.248873795103573e-05, "epoch": 1.0425716768027802, "percentage": 34.75, "elapsed_time": "7:15:41", "remaining_time": "13:38:00"}
123
- {"current_steps": 1210, "total_steps": 3453, "loss": 0.072, "lr": 8.210278875731998e-05, "epoch": 1.05125977410947, "percentage": 35.04, "elapsed_time": "7:19:16", "remaining_time": "13:34:17"}
124
- {"current_steps": 1220, "total_steps": 3453, "loss": 0.0578, "lr": 8.171355742966693e-05, "epoch": 1.0599478714161599, "percentage": 35.33, "elapsed_time": "7:22:52", "remaining_time": "13:30:35"}
125
- {"current_steps": 1230, "total_steps": 3453, "loss": 0.0624, "lr": 8.132108376241849e-05, "epoch": 1.0686359687228497, "percentage": 35.62, "elapsed_time": "7:26:27", "remaining_time": "13:26:53"}
126
- {"current_steps": 1240, "total_steps": 3453, "loss": 0.0604, "lr": 8.092540788140767e-05, "epoch": 1.0773240660295396, "percentage": 35.91, "elapsed_time": "7:30:02", "remaining_time": "13:23:11"}
127
- {"current_steps": 1250, "total_steps": 3453, "loss": 0.0683, "lr": 8.052657023985641e-05, "epoch": 1.0860121633362294, "percentage": 36.2, "elapsed_time": "7:33:38", "remaining_time": "13:19:29"}
128
- {"current_steps": 1260, "total_steps": 3453, "loss": 0.0603, "lr": 8.012461161423957e-05, "epoch": 1.0947002606429193, "percentage": 36.49, "elapsed_time": "7:37:13", "remaining_time": "13:15:47"}
129
- {"current_steps": 1270, "total_steps": 3453, "loss": 0.0688, "lr": 7.971957310011604e-05, "epoch": 1.103388357949609, "percentage": 36.78, "elapsed_time": "7:40:48", "remaining_time": "13:12:05"}
130
- {"current_steps": 1280, "total_steps": 3453, "loss": 0.058, "lr": 7.931149610792724e-05, "epoch": 1.112076455256299, "percentage": 37.07, "elapsed_time": "7:44:23", "remaining_time": "13:08:23"}
131
- {"current_steps": 1290, "total_steps": 3453, "loss": 0.0613, "lr": 7.890042235876335e-05, "epoch": 1.1207645525629888, "percentage": 37.36, "elapsed_time": "7:47:59", "remaining_time": "13:04:41"}
132
- {"current_steps": 1300, "total_steps": 3453, "loss": 0.0669, "lr": 7.848639388009788e-05, "epoch": 1.1294526498696786, "percentage": 37.65, "elapsed_time": "7:51:34", "remaining_time": "13:01:00"}
133
- {"current_steps": 1310, "total_steps": 3453, "loss": 0.0671, "lr": 7.806945300149073e-05, "epoch": 1.1381407471763683, "percentage": 37.94, "elapsed_time": "7:55:09", "remaining_time": "12:57:18"}
134
- {"current_steps": 1320, "total_steps": 3453, "loss": 0.0673, "lr": 7.764964235026062e-05, "epoch": 1.1468288444830583, "percentage": 38.23, "elapsed_time": "7:58:45", "remaining_time": "12:53:37"}
135
- {"current_steps": 1330, "total_steps": 3453, "loss": 0.0637, "lr": 7.722700484712686e-05, "epoch": 1.155516941789748, "percentage": 38.52, "elapsed_time": "8:02:20", "remaining_time": "12:49:55"}
136
- {"current_steps": 1340, "total_steps": 3453, "loss": 0.0614, "lr": 7.680158370182125e-05, "epoch": 1.1642050390964378, "percentage": 38.81, "elapsed_time": "8:05:55", "remaining_time": "12:46:14"}
137
- {"current_steps": 1350, "total_steps": 3453, "loss": 0.0611, "lr": 7.637342240867037e-05, "epoch": 1.1728931364031276, "percentage": 39.1, "elapsed_time": "8:09:31", "remaining_time": "12:42:33"}
138
- {"current_steps": 1360, "total_steps": 3453, "loss": 0.0595, "lr": 7.594256474214882e-05, "epoch": 1.1815812337098175, "percentage": 39.39, "elapsed_time": "8:13:06", "remaining_time": "12:38:52"}
139
- {"current_steps": 1370, "total_steps": 3453, "loss": 0.0575, "lr": 7.55090547524038e-05, "epoch": 1.1902693310165073, "percentage": 39.68, "elapsed_time": "8:16:41", "remaining_time": "12:35:11"}
140
- {"current_steps": 1380, "total_steps": 3453, "loss": 0.0671, "lr": 7.50729367607514e-05, "epoch": 1.1989574283231972, "percentage": 39.97, "elapsed_time": "8:20:17", "remaining_time": "12:31:30"}
141
- {"current_steps": 1390, "total_steps": 3453, "loss": 0.0565, "lr": 7.463425535514544e-05, "epoch": 1.207645525629887, "percentage": 40.25, "elapsed_time": "8:23:52", "remaining_time": "12:27:50"}
142
- {"current_steps": 1400, "total_steps": 3453, "loss": 0.0609, "lr": 7.41930553856187e-05, "epoch": 1.2163336229365769, "percentage": 40.54, "elapsed_time": "8:27:27", "remaining_time": "12:24:09"}
143
- {"current_steps": 1410, "total_steps": 3453, "loss": 0.0641, "lr": 7.374938195969762e-05, "epoch": 1.2250217202432667, "percentage": 40.83, "elapsed_time": "8:31:02", "remaining_time": "12:20:28"}
144
- {"current_steps": 1420, "total_steps": 3453, "loss": 0.0651, "lr": 7.330328043779064e-05, "epoch": 1.2337098175499566, "percentage": 41.12, "elapsed_time": "8:34:38", "remaining_time": "12:16:48"}
145
- {"current_steps": 1430, "total_steps": 3453, "loss": 0.0654, "lr": 7.285479642855043e-05, "epoch": 1.2423979148566464, "percentage": 41.41, "elapsed_time": "8:38:13", "remaining_time": "12:13:07"}
146
- {"current_steps": 1440, "total_steps": 3453, "loss": 0.0724, "lr": 7.240397578421118e-05, "epoch": 1.2510860121633363, "percentage": 41.7, "elapsed_time": "8:41:48", "remaining_time": "12:09:27"}
147
- {"current_steps": 1450, "total_steps": 3453, "loss": 0.0625, "lr": 7.195086459590064e-05, "epoch": 1.259774109470026, "percentage": 41.99, "elapsed_time": "8:45:24", "remaining_time": "12:05:47"}
148
- {"current_steps": 1460, "total_steps": 3453, "loss": 0.061, "lr": 7.149550918892771e-05, "epoch": 1.268462206776716, "percentage": 42.28, "elapsed_time": "8:48:59", "remaining_time": "12:02:06"}
149
- {"current_steps": 1470, "total_steps": 3453, "loss": 0.0659, "lr": 7.103795611804649e-05, "epoch": 1.2771503040834058, "percentage": 42.57, "elapsed_time": "8:52:35", "remaining_time": "11:58:26"}
150
- {"current_steps": 1480, "total_steps": 3453, "loss": 0.0673, "lr": 7.05782521626964e-05, "epoch": 1.2858384013900956, "percentage": 42.86, "elapsed_time": "8:56:10", "remaining_time": "11:54:46"}
151
- {"current_steps": 1490, "total_steps": 3453, "loss": 0.0599, "lr": 7.011644432221958e-05, "epoch": 1.2945264986967855, "percentage": 43.15, "elapsed_time": "8:59:45", "remaining_time": "11:51:06"}
152
- {"current_steps": 1500, "total_steps": 3453, "loss": 0.0627, "lr": 6.965257981105579e-05, "epoch": 1.3032145960034751, "percentage": 43.44, "elapsed_time": "9:03:21", "remaining_time": "11:47:26"}
153
- {"current_steps": 1500, "total_steps": 3453, "eval_loss": 0.061920732259750366, "epoch": 1.3032145960034751, "percentage": 43.44, "elapsed_time": "9:05:45", "remaining_time": "11:50:35"}
154
- {"current_steps": 1510, "total_steps": 3453, "loss": 0.0614, "lr": 6.918670605391526e-05, "epoch": 1.3119026933101652, "percentage": 43.73, "elapsed_time": "9:09:20", "remaining_time": "11:46:51"}
155
- {"current_steps": 1520, "total_steps": 3453, "loss": 0.0623, "lr": 6.871887068093009e-05, "epoch": 1.3205907906168548, "percentage": 44.02, "elapsed_time": "9:12:55", "remaining_time": "11:43:09"}
156
- {"current_steps": 1530, "total_steps": 3453, "loss": 0.0573, "lr": 6.824912152278458e-05, "epoch": 1.3292788879235449, "percentage": 44.31, "elapsed_time": "9:16:30", "remaining_time": "11:39:27"}
157
- {"current_steps": 1540, "total_steps": 3453, "loss": 0.0615, "lr": 6.777750660582516e-05, "epoch": 1.3379669852302345, "percentage": 44.6, "elapsed_time": "9:20:06", "remaining_time": "11:35:46"}
158
- {"current_steps": 1550, "total_steps": 3453, "loss": 0.0636, "lr": 6.73040741471502e-05, "epoch": 1.3466550825369243, "percentage": 44.89, "elapsed_time": "9:23:41", "remaining_time": "11:32:04"}
159
- {"current_steps": 1560, "total_steps": 3453, "loss": 0.0635, "lr": 6.682887254968048e-05, "epoch": 1.3553431798436142, "percentage": 45.18, "elapsed_time": "9:27:16", "remaining_time": "11:28:22"}
160
- {"current_steps": 1570, "total_steps": 3453, "loss": 0.0572, "lr": 6.635195039721041e-05, "epoch": 1.364031277150304, "percentage": 45.47, "elapsed_time": "9:30:52", "remaining_time": "11:24:41"}
161
- {"current_steps": 1580, "total_steps": 3453, "loss": 0.0685, "lr": 6.587335644944102e-05, "epoch": 1.3727193744569939, "percentage": 45.76, "elapsed_time": "9:34:27", "remaining_time": "11:20:59"}
162
- {"current_steps": 1590, "total_steps": 3453, "loss": 0.0639, "lr": 6.539313963699484e-05, "epoch": 1.3814074717636837, "percentage": 46.05, "elapsed_time": "9:38:03", "remaining_time": "11:17:18"}
163
- {"current_steps": 1600, "total_steps": 3453, "loss": 0.0613, "lr": 6.491134905641325e-05, "epoch": 1.3900955690703736, "percentage": 46.34, "elapsed_time": "9:41:38", "remaining_time": "11:13:36"}
164
- {"current_steps": 1610, "total_steps": 3453, "loss": 0.0647, "lr": 6.442803396513703e-05, "epoch": 1.3987836663770634, "percentage": 46.63, "elapsed_time": "9:45:13", "remaining_time": "11:09:55"}
165
- {"current_steps": 1620, "total_steps": 3453, "loss": 0.0689, "lr": 6.394324377647028e-05, "epoch": 1.4074717636837533, "percentage": 46.92, "elapsed_time": "9:48:48", "remaining_time": "11:06:13"}
166
- {"current_steps": 1630, "total_steps": 3453, "loss": 0.0608, "lr": 6.34570280545285e-05, "epoch": 1.416159860990443, "percentage": 47.21, "elapsed_time": "9:52:24", "remaining_time": "11:02:32"}
167
- {"current_steps": 1640, "total_steps": 3453, "loss": 0.0593, "lr": 6.296943650917128e-05, "epoch": 1.424847958297133, "percentage": 47.49, "elapsed_time": "9:55:59", "remaining_time": "10:58:51"}
168
- {"current_steps": 1650, "total_steps": 3453, "loss": 0.0647, "lr": 6.248051899092009e-05, "epoch": 1.4335360556038228, "percentage": 47.78, "elapsed_time": "9:59:34", "remaining_time": "10:55:10"}
169
- {"current_steps": 1660, "total_steps": 3453, "loss": 0.0585, "lr": 6.199032548586151e-05, "epoch": 1.4422241529105126, "percentage": 48.07, "elapsed_time": "10:03:10", "remaining_time": "10:51:29"}
170
- {"current_steps": 1670, "total_steps": 3453, "loss": 0.062, "lr": 6.149890611053685e-05, "epoch": 1.4509122502172025, "percentage": 48.36, "elapsed_time": "10:06:45", "remaining_time": "10:47:48"}
171
- {"current_steps": 1680, "total_steps": 3453, "loss": 0.0586, "lr": 6.100631110681826e-05, "epoch": 1.4596003475238923, "percentage": 48.65, "elapsed_time": "10:10:20", "remaining_time": "10:44:07"}
172
- {"current_steps": 1690, "total_steps": 3453, "loss": 0.0704, "lr": 6.0512590836772166e-05, "epoch": 1.4682884448305822, "percentage": 48.94, "elapsed_time": "10:13:55", "remaining_time": "10:40:26"}
173
- {"current_steps": 1700, "total_steps": 3453, "loss": 0.0603, "lr": 6.001779577751026e-05, "epoch": 1.476976542137272, "percentage": 49.23, "elapsed_time": "10:17:31", "remaining_time": "10:36:46"}
174
- {"current_steps": 1710, "total_steps": 3453, "loss": 0.0605, "lr": 5.952197651602882e-05, "epoch": 1.4856646394439617, "percentage": 49.52, "elapsed_time": "10:21:06", "remaining_time": "10:33:05"}
175
- {"current_steps": 1720, "total_steps": 3453, "loss": 0.0612, "lr": 5.902518374403685e-05, "epoch": 1.4943527367506517, "percentage": 49.81, "elapsed_time": "10:24:41", "remaining_time": "10:29:25"}
176
- {"current_steps": 1730, "total_steps": 3453, "loss": 0.0657, "lr": 5.852746825277333e-05, "epoch": 1.5030408340573413, "percentage": 50.1, "elapsed_time": "10:28:16", "remaining_time": "10:25:44"}
177
- {"current_steps": 1740, "total_steps": 3453, "loss": 0.0606, "lr": 5.802888092781454e-05, "epoch": 1.5117289313640314, "percentage": 50.39, "elapsed_time": "10:31:52", "remaining_time": "10:22:04"}
178
- {"current_steps": 1750, "total_steps": 3453, "loss": 0.0595, "lr": 5.752947274387147e-05, "epoch": 1.520417028670721, "percentage": 50.68, "elapsed_time": "10:35:27", "remaining_time": "10:18:23"}
179
- {"current_steps": 1760, "total_steps": 3453, "loss": 0.0593, "lr": 5.702929475957838e-05, "epoch": 1.529105125977411, "percentage": 50.97, "elapsed_time": "10:39:03", "remaining_time": "10:14:43"}
180
- {"current_steps": 1770, "total_steps": 3453, "loss": 0.0508, "lr": 5.652839811227255e-05, "epoch": 1.5377932232841007, "percentage": 51.26, "elapsed_time": "10:42:38", "remaining_time": "10:11:03"}
181
- {"current_steps": 1780, "total_steps": 3453, "loss": 0.0678, "lr": 5.602683401276615e-05, "epoch": 1.5464813205907906, "percentage": 51.55, "elapsed_time": "10:46:13", "remaining_time": "10:07:22"}
182
- {"current_steps": 1790, "total_steps": 3453, "loss": 0.0649, "lr": 5.552465374011055e-05, "epoch": 1.5551694178974804, "percentage": 51.84, "elapsed_time": "10:49:48", "remaining_time": "10:03:42"}
183
- {"current_steps": 1800, "total_steps": 3453, "loss": 0.0619, "lr": 5.5021908636353516e-05, "epoch": 1.5638575152041703, "percentage": 52.13, "elapsed_time": "10:53:24", "remaining_time": "10:00:02"}
184
- {"current_steps": 1810, "total_steps": 3453, "loss": 0.0692, "lr": 5.451865010129026e-05, "epoch": 1.5725456125108601, "percentage": 52.42, "elapsed_time": "10:56:59", "remaining_time": "9:56:22"}
185
- {"current_steps": 1820, "total_steps": 3453, "loss": 0.062, "lr": 5.4014929587208284e-05, "epoch": 1.58123370981755, "percentage": 52.71, "elapsed_time": "11:00:34", "remaining_time": "9:52:42"}
186
- {"current_steps": 1830, "total_steps": 3453, "loss": 0.0601, "lr": 5.3510798593627067e-05, "epoch": 1.5899218071242398, "percentage": 53.0, "elapsed_time": "11:04:10", "remaining_time": "9:49:02"}
187
- {"current_steps": 1840, "total_steps": 3453, "loss": 0.0628, "lr": 5.300630866203274e-05, "epoch": 1.5986099044309297, "percentage": 53.29, "elapsed_time": "11:07:45", "remaining_time": "9:45:22"}
188
- {"current_steps": 1850, "total_steps": 3453, "loss": 0.0538, "lr": 5.250151137060874e-05, "epoch": 1.6072980017376195, "percentage": 53.58, "elapsed_time": "11:11:20", "remaining_time": "9:41:42"}
189
- {"current_steps": 1860, "total_steps": 3453, "loss": 0.0693, "lr": 5.1996458328962316e-05, "epoch": 1.6159860990443093, "percentage": 53.87, "elapsed_time": "11:14:56", "remaining_time": "9:38:03"}
190
- {"current_steps": 1870, "total_steps": 3453, "loss": 0.0638, "lr": 5.14912011728483e-05, "epoch": 1.6246741963509992, "percentage": 54.16, "elapsed_time": "11:18:31", "remaining_time": "9:34:23"}
191
- {"current_steps": 1880, "total_steps": 3453, "loss": 0.0632, "lr": 5.0985791558889785e-05, "epoch": 1.6333622936576888, "percentage": 54.45, "elapsed_time": "11:22:07", "remaining_time": "9:30:43"}
192
- {"current_steps": 1890, "total_steps": 3453, "loss": 0.0649, "lr": 5.048028115929687e-05, "epoch": 1.6420503909643789, "percentage": 54.74, "elapsed_time": "11:25:42", "remaining_time": "9:27:04"}
193
- {"current_steps": 1900, "total_steps": 3453, "loss": 0.0605, "lr": 4.9974721656583856e-05, "epoch": 1.6507384882710685, "percentage": 55.02, "elapsed_time": "11:29:17", "remaining_time": "9:23:24"}
194
- {"current_steps": 1910, "total_steps": 3453, "loss": 0.0675, "lr": 4.9469164738285205e-05, "epoch": 1.6594265855777586, "percentage": 55.31, "elapsed_time": "11:32:53", "remaining_time": "9:19:44"}
195
- {"current_steps": 1920, "total_steps": 3453, "loss": 0.0628, "lr": 4.896366209167121e-05, "epoch": 1.6681146828844482, "percentage": 55.6, "elapsed_time": "11:36:28", "remaining_time": "9:16:05"}
196
- {"current_steps": 1930, "total_steps": 3453, "loss": 0.0609, "lr": 4.845826539846346e-05, "epoch": 1.6768027801911383, "percentage": 55.89, "elapsed_time": "11:40:03", "remaining_time": "9:12:25"}
197
- {"current_steps": 1940, "total_steps": 3453, "loss": 0.0595, "lr": 4.795302632955112e-05, "epoch": 1.6854908774978279, "percentage": 56.18, "elapsed_time": "11:43:39", "remaining_time": "9:08:46"}
198
- {"current_steps": 1950, "total_steps": 3453, "loss": 0.0619, "lr": 4.744799653970804e-05, "epoch": 1.694178974804518, "percentage": 56.47, "elapsed_time": "11:47:14", "remaining_time": "9:05:07"}
199
- {"current_steps": 1960, "total_steps": 3453, "loss": 0.0631, "lr": 4.694322766231183e-05, "epoch": 1.7028670721112076, "percentage": 56.76, "elapsed_time": "11:50:49", "remaining_time": "9:01:27"}
200
- {"current_steps": 1970, "total_steps": 3453, "loss": 0.0613, "lr": 4.6438771304064744e-05, "epoch": 1.7115551694178974, "percentage": 57.05, "elapsed_time": "11:54:24", "remaining_time": "8:57:48"}
201
- {"current_steps": 1980, "total_steps": 3453, "loss": 0.0613, "lr": 4.593467903971773e-05, "epoch": 1.7202432667245873, "percentage": 57.34, "elapsed_time": "11:58:00", "remaining_time": "8:54:09"}
202
- {"current_steps": 1990, "total_steps": 3453, "loss": 0.0641, "lr": 4.543100240679735e-05, "epoch": 1.7289313640312771, "percentage": 57.63, "elapsed_time": "12:01:35", "remaining_time": "8:50:29"}
203
- {"current_steps": 2000, "total_steps": 3453, "loss": 0.0619, "lr": 4.492779290033668e-05, "epoch": 1.737619461337967, "percentage": 57.92, "elapsed_time": "12:05:11", "remaining_time": "8:46:50"}
204
- {"current_steps": 2000, "total_steps": 3453, "eval_loss": 0.05979836359620094, "epoch": 1.737619461337967, "percentage": 57.92, "elapsed_time": "12:07:35", "remaining_time": "8:48:36"}
205
- {"current_steps": 2010, "total_steps": 3453, "loss": 0.0679, "lr": 4.4425101967610674e-05, "epoch": 1.7463075586446568, "percentage": 58.21, "elapsed_time": "12:11:10", "remaining_time": "8:44:55"}
206
- {"current_steps": 2020, "total_steps": 3453, "loss": 0.0647, "lr": 4.3922981002876145e-05, "epoch": 1.7549956559513467, "percentage": 58.5, "elapsed_time": "12:14:45", "remaining_time": "8:41:14"}
207
- {"current_steps": 2030, "total_steps": 3453, "loss": 0.0634, "lr": 4.3421481342117386e-05, "epoch": 1.7636837532580365, "percentage": 58.79, "elapsed_time": "12:18:21", "remaining_time": "8:37:34"}
208
- {"current_steps": 2040, "total_steps": 3453, "loss": 0.0646, "lr": 4.29206542577976e-05, "epoch": 1.7723718505647263, "percentage": 59.08, "elapsed_time": "12:21:56", "remaining_time": "8:33:54"}
209
- {"current_steps": 2050, "total_steps": 3453, "loss": 0.0592, "lr": 4.242055095361698e-05, "epoch": 1.7810599478714162, "percentage": 59.37, "elapsed_time": "12:25:32", "remaining_time": "8:30:14"}
210
- {"current_steps": 2060, "total_steps": 3453, "loss": 0.068, "lr": 4.192122255927765e-05, "epoch": 1.789748045178106, "percentage": 59.66, "elapsed_time": "12:29:07", "remaining_time": "8:26:34"}
211
- {"current_steps": 2070, "total_steps": 3453, "loss": 0.065, "lr": 4.14227201252563e-05, "epoch": 1.7984361424847957, "percentage": 59.95, "elapsed_time": "12:32:42", "remaining_time": "8:22:54"}
212
- {"current_steps": 2080, "total_steps": 3453, "loss": 0.0579, "lr": 4.0925094617584816e-05, "epoch": 1.8071242397914857, "percentage": 60.24, "elapsed_time": "12:36:18", "remaining_time": "8:19:14"}
213
- {"current_steps": 2090, "total_steps": 3453, "loss": 0.0668, "lr": 4.0428396912639725e-05, "epoch": 1.8158123370981754, "percentage": 60.53, "elapsed_time": "12:39:53", "remaining_time": "8:15:34"}
214
- {"current_steps": 2100, "total_steps": 3453, "loss": 0.0671, "lr": 3.993267779194052e-05, "epoch": 1.8245004344048654, "percentage": 60.82, "elapsed_time": "12:43:29", "remaining_time": "8:11:54"}
215
- {"current_steps": 2110, "total_steps": 3453, "loss": 0.0664, "lr": 3.943798793695795e-05, "epoch": 1.833188531711555, "percentage": 61.11, "elapsed_time": "12:47:04", "remaining_time": "8:08:14"}
216
- {"current_steps": 2120, "total_steps": 3453, "loss": 0.0644, "lr": 3.8944377923932415e-05, "epoch": 1.8418766290182451, "percentage": 61.4, "elapsed_time": "12:50:39", "remaining_time": "8:04:34"}
217
- {"current_steps": 2130, "total_steps": 3453, "loss": 0.0645, "lr": 3.845189821870314e-05, "epoch": 1.8505647263249347, "percentage": 61.69, "elapsed_time": "12:54:15", "remaining_time": "8:00:54"}
218
- {"current_steps": 2140, "total_steps": 3453, "loss": 0.06, "lr": 3.7960599171548574e-05, "epoch": 1.8592528236316248, "percentage": 61.98, "elapsed_time": "12:57:50", "remaining_time": "7:57:14"}
219
- {"current_steps": 2150, "total_steps": 3453, "loss": 0.0656, "lr": 3.747053101203875e-05, "epoch": 1.8679409209383144, "percentage": 62.26, "elapsed_time": "13:01:25", "remaining_time": "7:53:35"}
220
- {"current_steps": 2160, "total_steps": 3453, "loss": 0.059, "lr": 3.698174384389988e-05, "epoch": 1.8766290182450045, "percentage": 62.55, "elapsed_time": "13:05:01", "remaining_time": "7:49:55"}
221
- {"current_steps": 2170, "total_steps": 3453, "loss": 0.0642, "lr": 3.649428763989178e-05, "epoch": 1.8853171155516941, "percentage": 62.84, "elapsed_time": "13:08:36", "remaining_time": "7:46:15"}
222
- {"current_steps": 2180, "total_steps": 3453, "loss": 0.0584, "lr": 3.6008212236698815e-05, "epoch": 1.894005212858384, "percentage": 63.13, "elapsed_time": "13:12:11", "remaining_time": "7:42:35"}
223
- {"current_steps": 2190, "total_steps": 3453, "loss": 0.0598, "lr": 3.552356732983462e-05, "epoch": 1.9026933101650738, "percentage": 63.42, "elapsed_time": "13:15:47", "remaining_time": "7:38:56"}
224
- {"current_steps": 2200, "total_steps": 3453, "loss": 0.0637, "lr": 3.5040402468561384e-05, "epoch": 1.9113814074717637, "percentage": 63.71, "elapsed_time": "13:19:22", "remaining_time": "7:35:16"}
225
- {"current_steps": 2210, "total_steps": 3453, "loss": 0.0629, "lr": 3.455876705082392e-05, "epoch": 1.9200695047784535, "percentage": 64.0, "elapsed_time": "13:22:57", "remaining_time": "7:31:37"}
226
- {"current_steps": 2220, "total_steps": 3453, "loss": 0.0694, "lr": 3.407871031819944e-05, "epoch": 1.9287576020851434, "percentage": 64.29, "elapsed_time": "13:26:32", "remaining_time": "7:27:57"}
227
- {"current_steps": 2230, "total_steps": 3453, "loss": 0.0641, "lr": 3.360028135086303e-05, "epoch": 1.9374456993918332, "percentage": 64.58, "elapsed_time": "13:30:08", "remaining_time": "7:24:18"}
228
- {"current_steps": 2240, "total_steps": 3453, "loss": 0.0563, "lr": 3.312352906256989e-05, "epoch": 1.946133796698523, "percentage": 64.87, "elapsed_time": "13:33:43", "remaining_time": "7:20:38"}
229
- {"current_steps": 2250, "total_steps": 3453, "loss": 0.0661, "lr": 3.264850219565443e-05, "epoch": 1.954821894005213, "percentage": 65.16, "elapsed_time": "13:37:18", "remaining_time": "7:16:59"}
230
- {"current_steps": 2260, "total_steps": 3453, "loss": 0.0582, "lr": 3.217524931604695e-05, "epoch": 1.9635099913119027, "percentage": 65.45, "elapsed_time": "13:40:54", "remaining_time": "7:13:20"}
231
- {"current_steps": 2270, "total_steps": 3453, "loss": 0.0611, "lr": 3.1703818808308324e-05, "epoch": 1.9721980886185926, "percentage": 65.74, "elapsed_time": "13:44:29", "remaining_time": "7:09:40"}
232
- {"current_steps": 2280, "total_steps": 3453, "loss": 0.0636, "lr": 3.1234258870683264e-05, "epoch": 1.9808861859252822, "percentage": 66.03, "elapsed_time": "13:48:04", "remaining_time": "7:06:01"}
233
- {"current_steps": 2290, "total_steps": 3453, "loss": 0.0644, "lr": 3.076661751017261e-05, "epoch": 1.9895742832319723, "percentage": 66.32, "elapsed_time": "13:51:40", "remaining_time": "7:02:22"}
234
- {"current_steps": 2300, "total_steps": 3453, "loss": 0.0648, "lr": 3.0300942537625172e-05, "epoch": 1.998262380538662, "percentage": 66.61, "elapsed_time": "13:55:15", "remaining_time": "6:58:43"}
235
- {"current_steps": 2310, "total_steps": 3453, "loss": 0.0594, "lr": 2.983728156284967e-05, "epoch": 2.006950477845352, "percentage": 66.9, "elapsed_time": "13:58:50", "remaining_time": "6:55:03"}
236
- {"current_steps": 2320, "total_steps": 3453, "loss": 0.0589, "lr": 2.9375681989747074e-05, "epoch": 2.0156385751520416, "percentage": 67.19, "elapsed_time": "14:02:26", "remaining_time": "6:51:24"}
237
- {"current_steps": 2330, "total_steps": 3453, "loss": 0.0624, "lr": 2.8916191011464287e-05, "epoch": 2.0243266724587317, "percentage": 67.48, "elapsed_time": "14:06:01", "remaining_time": "6:47:45"}
238
- {"current_steps": 2340, "total_steps": 3453, "loss": 0.0565, "lr": 2.8458855605569e-05, "epoch": 2.0330147697654213, "percentage": 67.77, "elapsed_time": "14:09:36", "remaining_time": "6:44:06"}
239
- {"current_steps": 2350, "total_steps": 3453, "loss": 0.0595, "lr": 2.8003722529247024e-05, "epoch": 2.0417028670721113, "percentage": 68.06, "elapsed_time": "14:13:11", "remaining_time": "6:40:27"}
240
- {"current_steps": 2360, "total_steps": 3453, "loss": 0.0551, "lr": 2.755083831452162e-05, "epoch": 2.050390964378801, "percentage": 68.35, "elapsed_time": "14:16:47", "remaining_time": "6:36:48"}
241
- {"current_steps": 2370, "total_steps": 3453, "loss": 0.0564, "lr": 2.710024926349643e-05, "epoch": 2.059079061685491, "percentage": 68.64, "elapsed_time": "14:20:22", "remaining_time": "6:33:09"}
242
- {"current_steps": 2380, "total_steps": 3453, "loss": 0.058, "lr": 2.6652001443621445e-05, "epoch": 2.0677671589921807, "percentage": 68.93, "elapsed_time": "14:23:57", "remaining_time": "6:29:30"}
243
- {"current_steps": 2390, "total_steps": 3453, "loss": 0.0631, "lr": 2.6206140682983247e-05, "epoch": 2.0764552562988707, "percentage": 69.22, "elapsed_time": "14:27:33", "remaining_time": "6:25:51"}
244
- {"current_steps": 2400, "total_steps": 3453, "loss": 0.0592, "lr": 2.5762712565619528e-05, "epoch": 2.0851433536055604, "percentage": 69.5, "elapsed_time": "14:31:08", "remaining_time": "6:22:12"}
245
- {"current_steps": 2410, "total_steps": 3453, "loss": 0.0595, "lr": 2.5321762426858752e-05, "epoch": 2.0938314509122504, "percentage": 69.79, "elapsed_time": "14:34:43", "remaining_time": "6:18:33"}
246
- {"current_steps": 2420, "total_steps": 3453, "loss": 0.0597, "lr": 2.4883335348685133e-05, "epoch": 2.10251954821894, "percentage": 70.08, "elapsed_time": "14:38:19", "remaining_time": "6:14:55"}
247
- {"current_steps": 2430, "total_steps": 3453, "loss": 0.0675, "lr": 2.4447476155129433e-05, "epoch": 2.1112076455256297, "percentage": 70.37, "elapsed_time": "14:41:54", "remaining_time": "6:11:16"}
248
- {"current_steps": 2440, "total_steps": 3453, "loss": 0.056, "lr": 2.4014229407686384e-05, "epoch": 2.1198957428323197, "percentage": 70.66, "elapsed_time": "14:45:29", "remaining_time": "6:07:37"}
249
- {"current_steps": 2450, "total_steps": 3453, "loss": 0.0589, "lr": 2.3583639400758673e-05, "epoch": 2.1285838401390094, "percentage": 70.95, "elapsed_time": "14:49:05", "remaining_time": "6:03:58"}
250
- {"current_steps": 2460, "total_steps": 3453, "loss": 0.0583, "lr": 2.3155750157128443e-05, "epoch": 2.1372719374456994, "percentage": 71.24, "elapsed_time": "14:52:40", "remaining_time": "6:00:20"}
251
- {"current_steps": 2470, "total_steps": 3453, "loss": 0.0596, "lr": 2.2730605423456354e-05, "epoch": 2.145960034752389, "percentage": 71.53, "elapsed_time": "14:56:15", "remaining_time": "5:56:41"}
252
- {"current_steps": 2480, "total_steps": 3453, "loss": 0.0573, "lr": 2.230824866580921e-05, "epoch": 2.154648132059079, "percentage": 71.82, "elapsed_time": "14:59:50", "remaining_time": "5:53:02"}
253
- {"current_steps": 2490, "total_steps": 3453, "loss": 0.0597, "lr": 2.1888723065215837e-05, "epoch": 2.1633362293657687, "percentage": 72.11, "elapsed_time": "15:03:26", "remaining_time": "5:49:24"}
254
- {"current_steps": 2500, "total_steps": 3453, "loss": 0.0641, "lr": 2.1472071513252477e-05, "epoch": 2.172024326672459, "percentage": 72.4, "elapsed_time": "15:07:01", "remaining_time": "5:45:45"}
255
- {"current_steps": 2500, "total_steps": 3453, "eval_loss": 0.06191257759928703, "epoch": 2.172024326672459, "percentage": 72.4, "elapsed_time": "15:09:26", "remaining_time": "5:46:40"}
256
- {"current_steps": 2510, "total_steps": 3453, "loss": 0.0628, "lr": 2.105833660765757e-05, "epoch": 2.1807124239791484, "percentage": 72.69, "elapsed_time": "15:13:01", "remaining_time": "5:43:01"}
257
- {"current_steps": 2520, "total_steps": 3453, "loss": 0.0621, "lr": 2.064756064797666e-05, "epoch": 2.1894005212858385, "percentage": 72.98, "elapsed_time": "15:16:36", "remaining_time": "5:39:21"}
258
- {"current_steps": 2530, "total_steps": 3453, "loss": 0.0603, "lr": 2.0239785631237705e-05, "epoch": 2.198088618592528, "percentage": 73.27, "elapsed_time": "15:20:12", "remaining_time": "5:35:42"}
259
- {"current_steps": 2540, "total_steps": 3453, "loss": 0.0574, "lr": 1.983505324765746e-05, "epoch": 2.206776715899218, "percentage": 73.56, "elapsed_time": "15:23:47", "remaining_time": "5:32:03"}
260
- {"current_steps": 2550, "total_steps": 3453, "loss": 0.0568, "lr": 1.9433404876379092e-05, "epoch": 2.215464813205908, "percentage": 73.85, "elapsed_time": "15:27:22", "remaining_time": "5:28:24"}
261
- {"current_steps": 2560, "total_steps": 3453, "loss": 0.0628, "lr": 1.9034881581241616e-05, "epoch": 2.224152910512598, "percentage": 74.14, "elapsed_time": "15:30:58", "remaining_time": "5:24:44"}
262
- {"current_steps": 2570, "total_steps": 3453, "loss": 0.0696, "lr": 1.8639524106581663e-05, "epoch": 2.2328410078192875, "percentage": 74.43, "elapsed_time": "15:34:33", "remaining_time": "5:21:05"}
263
- {"current_steps": 2580, "total_steps": 3453, "loss": 0.056, "lr": 1.824737287306782e-05, "epoch": 2.2415291051259776, "percentage": 74.72, "elapsed_time": "15:38:09", "remaining_time": "5:17:26"}
264
- {"current_steps": 2590, "total_steps": 3453, "loss": 0.0618, "lr": 1.7858467973568104e-05, "epoch": 2.250217202432667, "percentage": 75.01, "elapsed_time": "15:41:44", "remaining_time": "5:13:47"}
265
- {"current_steps": 2600, "total_steps": 3453, "loss": 0.0661, "lr": 1.7472849169050853e-05, "epoch": 2.2589052997393573, "percentage": 75.3, "elapsed_time": "15:45:19", "remaining_time": "5:10:08"}
266
- {"current_steps": 2610, "total_steps": 3453, "loss": 0.0583, "lr": 1.7090555884519833e-05, "epoch": 2.267593397046047, "percentage": 75.59, "elapsed_time": "15:48:55", "remaining_time": "5:06:29"}
267
- {"current_steps": 2620, "total_steps": 3453, "loss": 0.0608, "lr": 1.6711627204983215e-05, "epoch": 2.2762814943527365, "percentage": 75.88, "elapsed_time": "15:52:30", "remaining_time": "5:02:50"}
268
- {"current_steps": 2630, "total_steps": 3453, "loss": 0.0599, "lr": 1.6336101871457844e-05, "epoch": 2.2849695916594266, "percentage": 76.17, "elapsed_time": "15:56:05", "remaining_time": "4:59:11"}
269
- {"current_steps": 2640, "total_steps": 3453, "loss": 0.0637, "lr": 1.5964018277008276e-05, "epoch": 2.2936576889661167, "percentage": 76.46, "elapsed_time": "15:59:41", "remaining_time": "4:55:32"}
270
- {"current_steps": 2650, "total_steps": 3453, "loss": 0.0559, "lr": 1.5595414462821606e-05, "epoch": 2.3023457862728063, "percentage": 76.74, "elapsed_time": "16:03:16", "remaining_time": "4:51:53"}
271
- {"current_steps": 2660, "total_steps": 3453, "loss": 0.0622, "lr": 1.5230328114318127e-05, "epoch": 2.311033883579496, "percentage": 77.03, "elapsed_time": "16:06:52", "remaining_time": "4:48:14"}
272
- {"current_steps": 2670, "total_steps": 3453, "loss": 0.0634, "lr": 1.4868796557298543e-05, "epoch": 2.319721980886186, "percentage": 77.32, "elapsed_time": "16:10:27", "remaining_time": "4:44:35"}
273
- {"current_steps": 2680, "total_steps": 3453, "loss": 0.0611, "lr": 1.4510856754127771e-05, "epoch": 2.3284100781928756, "percentage": 77.61, "elapsed_time": "16:14:02", "remaining_time": "4:40:56"}
274
- {"current_steps": 2690, "total_steps": 3453, "loss": 0.0548, "lr": 1.4156545299955936e-05, "epoch": 2.3370981754995657, "percentage": 77.9, "elapsed_time": "16:17:38", "remaining_time": "4:37:18"}
275
- {"current_steps": 2700, "total_steps": 3453, "loss": 0.0621, "lr": 1.3805898418977115e-05, "epoch": 2.3457862728062553, "percentage": 78.19, "elapsed_time": "16:21:13", "remaining_time": "4:33:39"}
276
- {"current_steps": 2710, "total_steps": 3453, "loss": 0.0593, "lr": 1.3458951960725591e-05, "epoch": 2.3544743701129454, "percentage": 78.48, "elapsed_time": "16:24:48", "remaining_time": "4:30:00"}
277
- {"current_steps": 2720, "total_steps": 3453, "loss": 0.0609, "lr": 1.311574139641088e-05, "epoch": 2.363162467419635, "percentage": 78.77, "elapsed_time": "16:28:24", "remaining_time": "4:26:21"}
278
- {"current_steps": 2730, "total_steps": 3453, "loss": 0.0606, "lr": 1.2776301815291081e-05, "epoch": 2.371850564726325, "percentage": 79.06, "elapsed_time": "16:31:59", "remaining_time": "4:22:42"}
279
- {"current_steps": 2740, "total_steps": 3453, "loss": 0.0634, "lr": 1.2440667921085481e-05, "epoch": 2.3805386620330147, "percentage": 79.35, "elapsed_time": "16:35:35", "remaining_time": "4:19:04"}
280
- {"current_steps": 2750, "total_steps": 3453, "loss": 0.0541, "lr": 1.2108874028426437e-05, "epoch": 2.3892267593397047, "percentage": 79.64, "elapsed_time": "16:39:10", "remaining_time": "4:15:25"}
281
- {"current_steps": 2760, "total_steps": 3453, "loss": 0.0559, "lr": 1.1780954059351184e-05, "epoch": 2.3979148566463944, "percentage": 79.93, "elapsed_time": "16:42:45", "remaining_time": "4:11:46"}
282
- {"current_steps": 2770, "total_steps": 3453, "loss": 0.0642, "lr": 1.1456941539833666e-05, "epoch": 2.4066029539530844, "percentage": 80.22, "elapsed_time": "16:46:21", "remaining_time": "4:08:08"}
283
- {"current_steps": 2780, "total_steps": 3453, "loss": 0.0518, "lr": 1.1136869596356908e-05, "epoch": 2.415291051259774, "percentage": 80.51, "elapsed_time": "16:49:56", "remaining_time": "4:04:29"}
284
- {"current_steps": 2790, "total_steps": 3453, "loss": 0.0569, "lr": 1.0820770952526155e-05, "epoch": 2.423979148566464, "percentage": 80.8, "elapsed_time": "16:53:32", "remaining_time": "4:00:51"}
285
- {"current_steps": 2800, "total_steps": 3453, "loss": 0.0567, "lr": 1.0508677925723432e-05, "epoch": 2.4326672458731537, "percentage": 81.09, "elapsed_time": "16:57:07", "remaining_time": "3:57:12"}
286
- {"current_steps": 2810, "total_steps": 3453, "loss": 0.0631, "lr": 1.0200622423803274e-05, "epoch": 2.4413553431798434, "percentage": 81.38, "elapsed_time": "17:00:42", "remaining_time": "3:53:33"}
287
- {"current_steps": 2820, "total_steps": 3453, "loss": 0.0591, "lr": 9.896635941830623e-06, "epoch": 2.4500434404865334, "percentage": 81.67, "elapsed_time": "17:04:18", "remaining_time": "3:49:55"}
288
- {"current_steps": 2830, "total_steps": 3453, "loss": 0.054, "lr": 9.59674955886089e-06, "epoch": 2.4587315377932235, "percentage": 81.96, "elapsed_time": "17:07:53", "remaining_time": "3:46:16"}
289
- {"current_steps": 2840, "total_steps": 3453, "loss": 0.0587, "lr": 9.300993934762315e-06, "epoch": 2.467419635099913, "percentage": 82.25, "elapsed_time": "17:11:29", "remaining_time": "3:42:38"}
290
- {"current_steps": 2850, "total_steps": 3453, "loss": 0.0615, "lr": 9.009399307081518e-06, "epoch": 2.4761077324066028, "percentage": 82.54, "elapsed_time": "17:15:04", "remaining_time": "3:39:00"}
291
- {"current_steps": 2860, "total_steps": 3453, "loss": 0.0529, "lr": 8.721995487951968e-06, "epoch": 2.484795829713293, "percentage": 82.83, "elapsed_time": "17:18:39", "remaining_time": "3:35:21"}
292
- {"current_steps": 2870, "total_steps": 3453, "loss": 0.0609, "lr": 8.438811861046097e-06, "epoch": 2.4934839270199824, "percentage": 83.12, "elapsed_time": "17:22:15", "remaining_time": "3:31:43"}
293
- {"current_steps": 2880, "total_steps": 3453, "loss": 0.0617, "lr": 8.159877378571096e-06, "epoch": 2.5021720243266725, "percentage": 83.41, "elapsed_time": "17:25:50", "remaining_time": "3:28:04"}
294
- {"current_steps": 2890, "total_steps": 3453, "loss": 0.0565, "lr": 7.885220558308975e-06, "epoch": 2.510860121633362, "percentage": 83.7, "elapsed_time": "17:29:26", "remaining_time": "3:24:26"}
295
- {"current_steps": 2900, "total_steps": 3453, "loss": 0.066, "lr": 7.614869480700898e-06, "epoch": 2.519548218940052, "percentage": 83.98, "elapsed_time": "17:33:01", "remaining_time": "3:20:48"}
296
- {"current_steps": 2910, "total_steps": 3453, "loss": 0.0566, "lr": 7.348851785976302e-06, "epoch": 2.528236316246742, "percentage": 84.27, "elapsed_time": "17:36:36", "remaining_time": "3:17:09"}
297
- {"current_steps": 2920, "total_steps": 3453, "loss": 0.0612, "lr": 7.0871946713269856e-06, "epoch": 2.536924413553432, "percentage": 84.56, "elapsed_time": "17:40:12", "remaining_time": "3:13:31"}
298
- {"current_steps": 2930, "total_steps": 3453, "loss": 0.0582, "lr": 6.8299248881265985e-06, "epoch": 2.5456125108601215, "percentage": 84.85, "elapsed_time": "17:43:47", "remaining_time": "3:09:53"}
299
- {"current_steps": 2940, "total_steps": 3453, "loss": 0.0559, "lr": 6.577068739195496e-06, "epoch": 2.5543006081668116, "percentage": 85.14, "elapsed_time": "17:47:23", "remaining_time": "3:06:14"}
300
- {"current_steps": 2950, "total_steps": 3453, "loss": 0.0627, "lr": 6.328652076111663e-06, "epoch": 2.562988705473501, "percentage": 85.43, "elapsed_time": "17:50:58", "remaining_time": "3:02:36"}
301
- {"current_steps": 2960, "total_steps": 3453, "loss": 0.062, "lr": 6.0847002965677465e-06, "epoch": 2.5716768027801913, "percentage": 85.72, "elapsed_time": "17:54:33", "remaining_time": "2:58:58"}
302
- {"current_steps": 2970, "total_steps": 3453, "loss": 0.0556, "lr": 5.845238341774289e-06, "epoch": 2.580364900086881, "percentage": 86.01, "elapsed_time": "17:58:09", "remaining_time": "2:55:20"}
303
- {"current_steps": 2980, "total_steps": 3453, "loss": 0.0538, "lr": 5.6102906939099255e-06, "epoch": 2.589052997393571, "percentage": 86.3, "elapsed_time": "18:01:44", "remaining_time": "2:51:41"}
304
- {"current_steps": 2990, "total_steps": 3453, "loss": 0.0593, "lr": 5.379881373618295e-06, "epoch": 2.5977410947002606, "percentage": 86.59, "elapsed_time": "18:05:20", "remaining_time": "2:48:03"}
305
- {"current_steps": 3000, "total_steps": 3453, "loss": 0.0541, "lr": 5.154033937552238e-06, "epoch": 2.6064291920069502, "percentage": 86.88, "elapsed_time": "18:08:55", "remaining_time": "2:44:25"}
306
- {"current_steps": 3000, "total_steps": 3453, "eval_loss": 0.058555811643600464, "epoch": 2.6064291920069502, "percentage": 86.88, "elapsed_time": "18:11:20", "remaining_time": "2:44:47"}
307
- {"current_steps": 3010, "total_steps": 3453, "loss": 0.0555, "lr": 4.932771475965342e-06, "epoch": 2.6151172893136403, "percentage": 87.17, "elapsed_time": "18:15:24", "remaining_time": "2:41:13"}
308
- {"current_steps": 3020, "total_steps": 3453, "loss": 0.0625, "lr": 4.7161166103513784e-06, "epoch": 2.6238053866203304, "percentage": 87.46, "elapsed_time": "18:18:59", "remaining_time": "2:37:34"}
309
- {"current_steps": 3030, "total_steps": 3453, "loss": 0.0655, "lr": 4.5040914911313345e-06, "epoch": 2.63249348392702, "percentage": 87.75, "elapsed_time": "18:22:35", "remaining_time": "2:33:55"}
310
- {"current_steps": 3040, "total_steps": 3453, "loss": 0.0647, "lr": 4.296717795388938e-06, "epoch": 2.6411815812337096, "percentage": 88.04, "elapsed_time": "18:26:10", "remaining_time": "2:30:16"}
311
- {"current_steps": 3050, "total_steps": 3453, "loss": 0.0498, "lr": 4.094016724654359e-06, "epoch": 2.6498696785403997, "percentage": 88.33, "elapsed_time": "18:29:46", "remaining_time": "2:26:38"}
312
- {"current_steps": 3060, "total_steps": 3453, "loss": 0.0601, "lr": 3.896009002736639e-06, "epoch": 2.6585577758470897, "percentage": 88.62, "elapsed_time": "18:33:21", "remaining_time": "2:22:59"}
313
- {"current_steps": 3070, "total_steps": 3453, "loss": 0.0668, "lr": 3.702714873604862e-06, "epoch": 2.6672458731537794, "percentage": 88.91, "elapsed_time": "18:36:57", "remaining_time": "2:19:20"}
314
- {"current_steps": 3080, "total_steps": 3453, "loss": 0.0595, "lr": 3.5141540993185286e-06, "epoch": 2.675933970460469, "percentage": 89.2, "elapsed_time": "18:40:32", "remaining_time": "2:15:42"}
315
- {"current_steps": 3090, "total_steps": 3453, "loss": 0.0541, "lr": 3.3303459580070695e-06, "epoch": 2.684622067767159, "percentage": 89.49, "elapsed_time": "18:44:07", "remaining_time": "2:12:03"}
316
- {"current_steps": 3100, "total_steps": 3453, "loss": 0.0579, "lr": 3.1513092418988643e-06, "epoch": 2.6933101650738487, "percentage": 89.78, "elapsed_time": "18:47:43", "remaining_time": "2:08:24"}
317
- {"current_steps": 3110, "total_steps": 3453, "loss": 0.0611, "lr": 2.9770622554000094e-06, "epoch": 2.7019982623805388, "percentage": 90.07, "elapsed_time": "18:51:18", "remaining_time": "2:04:46"}
318
- {"current_steps": 3120, "total_steps": 3453, "loss": 0.0592, "lr": 2.807622813222871e-06, "epoch": 2.7106863596872284, "percentage": 90.36, "elapsed_time": "18:54:54", "remaining_time": "2:01:07"}
319
- {"current_steps": 3130, "total_steps": 3453, "loss": 0.0553, "lr": 2.643008238564759e-06, "epoch": 2.7193744569939184, "percentage": 90.65, "elapsed_time": "18:58:29", "remaining_time": "1:57:29"}
320
- {"current_steps": 3140, "total_steps": 3453, "loss": 0.0559, "lr": 2.4832353613367833e-06, "epoch": 2.728062554300608, "percentage": 90.94, "elapsed_time": "19:02:04", "remaining_time": "1:53:50"}
321
- {"current_steps": 3150, "total_steps": 3453, "loss": 0.0555, "lr": 2.3283205164432884e-06, "epoch": 2.736750651607298, "percentage": 91.23, "elapsed_time": "19:05:40", "remaining_time": "1:50:12"}
322
- {"current_steps": 3160, "total_steps": 3453, "loss": 0.0617, "lr": 2.1782795421116996e-06, "epoch": 2.7454387489139878, "percentage": 91.51, "elapsed_time": "19:09:15", "remaining_time": "1:46:33"}
323
- {"current_steps": 3170, "total_steps": 3453, "loss": 0.0547, "lr": 2.033127778273308e-06, "epoch": 2.754126846220678, "percentage": 91.8, "elapsed_time": "19:12:50", "remaining_time": "1:42:55"}
324
- {"current_steps": 3180, "total_steps": 3453, "loss": 0.0606, "lr": 1.892880064994934e-06, "epoch": 2.7628149435273675, "percentage": 92.09, "elapsed_time": "19:16:26", "remaining_time": "1:39:16"}
325
- {"current_steps": 3190, "total_steps": 3453, "loss": 0.0569, "lr": 1.7575507409617053e-06, "epoch": 2.771503040834057, "percentage": 92.38, "elapsed_time": "19:20:01", "remaining_time": "1:35:38"}
326
- {"current_steps": 3200, "total_steps": 3453, "loss": 0.06, "lr": 1.627153642011059e-06, "epoch": 2.780191138140747, "percentage": 92.67, "elapsed_time": "19:23:37", "remaining_time": "1:31:59"}
327
- {"current_steps": 3210, "total_steps": 3453, "loss": 0.0572, "lr": 1.501702099718244e-06, "epoch": 2.788879235447437, "percentage": 92.96, "elapsed_time": "19:27:12", "remaining_time": "1:28:21"}
328
- {"current_steps": 3220, "total_steps": 3453, "loss": 0.0568, "lr": 1.381208940033296e-06, "epoch": 2.797567332754127, "percentage": 93.25, "elapsed_time": "19:30:47", "remaining_time": "1:24:43"}
329
- {"current_steps": 3230, "total_steps": 3453, "loss": 0.0605, "lr": 1.2656864819697189e-06, "epoch": 2.8062554300608165, "percentage": 93.54, "elapsed_time": "19:34:23", "remaining_time": "1:21:04"}
330
- {"current_steps": 3240, "total_steps": 3453, "loss": 0.0609, "lr": 1.155146536345053e-06, "epoch": 2.8149435273675065, "percentage": 93.83, "elapsed_time": "19:37:58", "remaining_time": "1:17:26"}
331
- {"current_steps": 3250, "total_steps": 3453, "loss": 0.0622, "lr": 1.0496004045733143e-06, "epoch": 2.8236316246741966, "percentage": 94.12, "elapsed_time": "19:41:33", "remaining_time": "1:13:48"}
332
- {"current_steps": 3260, "total_steps": 3453, "loss": 0.0572, "lr": 9.490588775095733e-07, "epoch": 2.832319721980886, "percentage": 94.41, "elapsed_time": "19:45:09", "remaining_time": "1:10:09"}
333
- {"current_steps": 3270, "total_steps": 3453, "loss": 0.0613, "lr": 8.535322343467322e-07, "epoch": 2.841007819287576, "percentage": 94.7, "elapsed_time": "19:48:44", "remaining_time": "1:06:31"}
334
- {"current_steps": 3280, "total_steps": 3453, "loss": 0.054, "lr": 7.630302415645774e-07, "epoch": 2.849695916594266, "percentage": 94.99, "elapsed_time": "19:52:19", "remaining_time": "1:02:53"}
335
- {"current_steps": 3290, "total_steps": 3453, "loss": 0.0558, "lr": 6.775621519312713e-07, "epoch": 2.8583840139009555, "percentage": 95.28, "elapsed_time": "19:55:55", "remaining_time": "0:59:15"}
336
- {"current_steps": 3300, "total_steps": 3453, "loss": 0.0611, "lr": 5.971367035573771e-07, "epoch": 2.8670721112076456, "percentage": 95.57, "elapsed_time": "19:59:30", "remaining_time": "0:55:36"}
337
- {"current_steps": 3310, "total_steps": 3453, "loss": 0.0592, "lr": 5.217621190024779e-07, "epoch": 2.8757602085143352, "percentage": 95.86, "elapsed_time": "20:03:05", "remaining_time": "0:51:58"}
338
- {"current_steps": 3320, "total_steps": 3453, "loss": 0.0496, "lr": 4.5144610443454414e-07, "epoch": 2.8844483058210253, "percentage": 96.15, "elapsed_time": "20:06:41", "remaining_time": "0:48:20"}
339
- {"current_steps": 3330, "total_steps": 3453, "loss": 0.058, "lr": 3.8619584884201367e-07, "epoch": 2.893136403127715, "percentage": 96.44, "elapsed_time": "20:10:16", "remaining_time": "0:44:42"}
340
- {"current_steps": 3340, "total_steps": 3453, "loss": 0.061, "lr": 3.2601802329886857e-07, "epoch": 2.901824500434405, "percentage": 96.73, "elapsed_time": "20:13:52", "remaining_time": "0:41:04"}
341
- {"current_steps": 3350, "total_steps": 3453, "loss": 0.0575, "lr": 2.709187802825364e-07, "epoch": 2.9105125977410946, "percentage": 97.02, "elapsed_time": "20:17:27", "remaining_time": "0:37:25"}
342
- {"current_steps": 3360, "total_steps": 3453, "loss": 0.0583, "lr": 2.2090375304489874e-07, "epoch": 2.9192006950477847, "percentage": 97.31, "elapsed_time": "20:21:03", "remaining_time": "0:33:47"}
343
- {"current_steps": 3370, "total_steps": 3453, "loss": 0.0611, "lr": 1.7597805503637432e-07, "epoch": 2.9278887923544743, "percentage": 97.6, "elapsed_time": "20:24:38", "remaining_time": "0:30:09"}
344
- {"current_steps": 3380, "total_steps": 3453, "loss": 0.0566, "lr": 1.3614627938309809e-07, "epoch": 2.9365768896611644, "percentage": 97.89, "elapsed_time": "20:28:13", "remaining_time": "0:26:31"}
345
- {"current_steps": 3390, "total_steps": 3453, "loss": 0.0597, "lr": 1.0141249841734146e-07, "epoch": 2.945264986967854, "percentage": 98.18, "elapsed_time": "20:31:48", "remaining_time": "0:22:53"}
346
- {"current_steps": 3400, "total_steps": 3453, "loss": 0.0607, "lr": 7.178026326115639e-08, "epoch": 2.953953084274544, "percentage": 98.47, "elapsed_time": "20:35:24", "remaining_time": "0:19:15"}
347
- {"current_steps": 3410, "total_steps": 3453, "loss": 0.0592, "lr": 4.725260346333804e-08, "epoch": 2.9626411815812337, "percentage": 98.75, "elapsed_time": "20:38:59", "remaining_time": "0:15:37"}
348
- {"current_steps": 3420, "total_steps": 3453, "loss": 0.0592, "lr": 2.7832026689650347e-08, "epoch": 2.9713292788879233, "percentage": 99.04, "elapsed_time": "20:42:35", "remaining_time": "0:11:59"}
349
- {"current_steps": 3430, "total_steps": 3453, "loss": 0.0588, "lr": 1.3520518466481058e-08, "epoch": 2.9800173761946134, "percentage": 99.33, "elapsed_time": "20:46:10", "remaining_time": "0:08:21"}
350
- {"current_steps": 3440, "total_steps": 3453, "loss": 0.0578, "lr": 4.319541977831909e-09, "epoch": 2.9887054735013034, "percentage": 99.62, "elapsed_time": "20:49:45", "remaining_time": "0:04:43"}
351
- {"current_steps": 3450, "total_steps": 3453, "loss": 0.0581, "lr": 2.300379157160748e-10, "epoch": 2.997393570807993, "percentage": 99.91, "elapsed_time": "20:53:21", "remaining_time": "0:01:05"}
352
- {"current_steps": 3453, "total_steps": 3453, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "20:54:54", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 10, "total_steps": 1266, "loss": 2.5618, "lr": 7.086614173228346e-07, "epoch": 0.023696682464454975, "percentage": 0.79, "elapsed_time": "0:07:59", "remaining_time": "16:43:36"}
2
+ {"current_steps": 20, "total_steps": 1266, "loss": 2.0072, "lr": 1.4960629921259845e-06, "epoch": 0.04739336492890995, "percentage": 1.58, "elapsed_time": "0:15:50", "remaining_time": "16:26:57"}
3
+ {"current_steps": 30, "total_steps": 1266, "loss": 0.5321, "lr": 2.283464566929134e-06, "epoch": 0.07109004739336493, "percentage": 2.37, "elapsed_time": "0:23:42", "remaining_time": "16:16:59"}
4
+ {"current_steps": 40, "total_steps": 1266, "loss": 0.0718, "lr": 3.0708661417322837e-06, "epoch": 0.0947867298578199, "percentage": 3.16, "elapsed_time": "0:31:34", "remaining_time": "16:07:35"}
5
+ {"current_steps": 50, "total_steps": 1266, "loss": 0.0486, "lr": 3.858267716535433e-06, "epoch": 0.11848341232227488, "percentage": 3.95, "elapsed_time": "0:39:24", "remaining_time": "15:58:28"}
6
+ {"current_steps": 60, "total_steps": 1266, "loss": 0.0393, "lr": 4.645669291338583e-06, "epoch": 0.14218009478672985, "percentage": 4.74, "elapsed_time": "0:47:13", "remaining_time": "15:49:14"}
7
+ {"current_steps": 70, "total_steps": 1266, "loss": 0.0312, "lr": 5.433070866141733e-06, "epoch": 0.16587677725118483, "percentage": 5.53, "elapsed_time": "0:55:05", "remaining_time": "15:41:15"}
8
+ {"current_steps": 80, "total_steps": 1266, "loss": 0.0285, "lr": 6.220472440944882e-06, "epoch": 0.1895734597156398, "percentage": 6.32, "elapsed_time": "1:02:56", "remaining_time": "15:33:07"}
9
+ {"current_steps": 90, "total_steps": 1266, "loss": 0.0255, "lr": 7.0078740157480315e-06, "epoch": 0.2132701421800948, "percentage": 7.11, "elapsed_time": "1:10:47", "remaining_time": "15:24:59"}
10
+ {"current_steps": 100, "total_steps": 1266, "loss": 0.0243, "lr": 7.79527559055118e-06, "epoch": 0.23696682464454977, "percentage": 7.9, "elapsed_time": "1:18:36", "remaining_time": "15:16:36"}
11
+ {"current_steps": 100, "total_steps": 1266, "eval_loss": 0.02421322837471962, "epoch": 0.23696682464454977, "percentage": 7.9, "elapsed_time": "1:52:52", "remaining_time": "21:56:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f6638594d58e72a7db9fac816368034862d538faab741fa773c990ee887ed88
3
- size 7352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a91ec8dc544a474e1418f3430bd13c7b085f181ea7d0e1ed35bf2015958d17d
3
+ size 7480
vocab.json ADDED
The diff for this file is too large to render. See raw diff