Hugging Face's logo

Weyaxi
/
Einstein-v7-Qwen2-7B

Text Generation
Transformers
Safetensors
English
qwen2
axolotl
instruct
finetune
chatml
gpt4
synthetic data
science
physics
chemistry
biology
math
qwen
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
2
Weyaxi commited on
Commit
d5a2f24
•
1 Parent(s): b5dd2af

weird issue fix please

Browse files
Files changed (5) hide show
  1. config.json +16 -17
  2. special_tokens_map.json +4 -7
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +21 -2049
  5. trainer_state.json +3561 -0
config.json CHANGED
@@ -1,28 +1,27 @@
1
  {
2
- "_name_or_path": "meta-llama/Meta-Llama-3-8B",
3
  "architectures": [
4
- "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
  "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128256,
10
  "hidden_act": "silu",
11
- "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
15
- "model_type": "llama",
16
- "num_attention_heads": 32,
17
- "num_hidden_layers": 32,
18
- "num_key_value_heads": 8,
19
- "pretraining_tp": 1,
20
- "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
22
- "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.40.0.dev0",
26
  "use_cache": false,
27
- "vocab_size": 128258
 
28
  }
 
1
  {
2
+ "_name_or_path": "Qwen/Qwen2-7B",
3
  "architectures": [
4
+ "Qwen2ForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
 
8
  "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 28,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 4,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": 131072,
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.40.0.dev0",
24
  "use_cache": false,
25
+ "use_sliding_window": false,
26
+ "vocab_size": 152064
27
  }
special_tokens_map.json CHANGED
@@ -1,11 +1,8 @@
1
  {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
  "eos_token": {
10
  "content": "<|im_end|>",
11
  "lstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
 
 
 
6
  "eos_token": {
7
  "content": "<|im_end|>",
8
  "lstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,2054 +1,23 @@
1
  {
 
2
  "added_tokens_decoder": {
3
- "128000": {
4
- "content": "<|begin_of_text|>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "128001": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "128002": {
20
- "content": "<|reserved_special_token_0|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "128003": {
28
- "content": "<|reserved_special_token_1|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "128004": {
36
- "content": "<|reserved_special_token_2|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "128005": {
44
- "content": "<|reserved_special_token_3|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "128006": {
52
- "content": "<|start_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "128007": {
60
- "content": "<|end_header_id|>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "128008": {
68
- "content": "<|reserved_special_token_4|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "128009": {
76
- "content": "<|eot_id|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "128010": {
84
- "content": "<|reserved_special_token_5|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "128011": {
92
- "content": "<|reserved_special_token_6|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "128012": {
100
- "content": "<|reserved_special_token_7|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "128013": {
108
- "content": "<|reserved_special_token_8|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "128014": {
116
- "content": "<|reserved_special_token_9|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "128015": {
124
- "content": "<|reserved_special_token_10|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "128016": {
132
- "content": "<|reserved_special_token_11|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "128017": {
140
- "content": "<|reserved_special_token_12|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "128018": {
148
- "content": "<|reserved_special_token_13|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "128019": {
156
- "content": "<|reserved_special_token_14|>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "128020": {
164
- "content": "<|reserved_special_token_15|>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "128021": {
172
- "content": "<|reserved_special_token_16|>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "128022": {
180
- "content": "<|reserved_special_token_17|>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "128023": {
188
- "content": "<|reserved_special_token_18|>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "128024": {
196
- "content": "<|reserved_special_token_19|>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "128025": {
204
- "content": "<|reserved_special_token_20|>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "128026": {
212
- "content": "<|reserved_special_token_21|>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "128027": {
220
- "content": "<|reserved_special_token_22|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "128028": {
228
- "content": "<|reserved_special_token_23|>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "128029": {
236
- "content": "<|reserved_special_token_24|>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "128030": {
244
- "content": "<|reserved_special_token_25|>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "128031": {
252
- "content": "<|reserved_special_token_26|>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "128032": {
260
- "content": "<|reserved_special_token_27|>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "128033": {
268
- "content": "<|reserved_special_token_28|>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "128034": {
276
- "content": "<|reserved_special_token_29|>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "128035": {
284
- "content": "<|reserved_special_token_30|>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "128036": {
292
- "content": "<|reserved_special_token_31|>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "128037": {
300
- "content": "<|reserved_special_token_32|>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "128038": {
308
- "content": "<|reserved_special_token_33|>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "128039": {
316
- "content": "<|reserved_special_token_34|>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "128040": {
324
- "content": "<|reserved_special_token_35|>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "128041": {
332
- "content": "<|reserved_special_token_36|>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "128042": {
340
- "content": "<|reserved_special_token_37|>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "128043": {
348
- "content": "<|reserved_special_token_38|>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "128044": {
356
- "content": "<|reserved_special_token_39|>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "128045": {
364
- "content": "<|reserved_special_token_40|>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "128046": {
372
- "content": "<|reserved_special_token_41|>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "128047": {
380
- "content": "<|reserved_special_token_42|>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "128048": {
388
- "content": "<|reserved_special_token_43|>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "128049": {
396
- "content": "<|reserved_special_token_44|>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "128050": {
404
- "content": "<|reserved_special_token_45|>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "128051": {
412
- "content": "<|reserved_special_token_46|>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "128052": {
420
- "content": "<|reserved_special_token_47|>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "128053": {
428
- "content": "<|reserved_special_token_48|>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "128054": {
436
- "content": "<|reserved_special_token_49|>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "128055": {
444
- "content": "<|reserved_special_token_50|>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "128056": {
452
- "content": "<|reserved_special_token_51|>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "128057": {
460
- "content": "<|reserved_special_token_52|>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "128058": {
468
- "content": "<|reserved_special_token_53|>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "128059": {
476
- "content": "<|reserved_special_token_54|>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "128060": {
484
- "content": "<|reserved_special_token_55|>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "128061": {
492
- "content": "<|reserved_special_token_56|>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "128062": {
500
- "content": "<|reserved_special_token_57|>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "128063": {
508
- "content": "<|reserved_special_token_58|>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "128064": {
516
- "content": "<|reserved_special_token_59|>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "128065": {
524
- "content": "<|reserved_special_token_60|>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "128066": {
532
- "content": "<|reserved_special_token_61|>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "128067": {
540
- "content": "<|reserved_special_token_62|>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "128068": {
548
- "content": "<|reserved_special_token_63|>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "128069": {
556
- "content": "<|reserved_special_token_64|>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "128070": {
564
- "content": "<|reserved_special_token_65|>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "128071": {
572
- "content": "<|reserved_special_token_66|>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "128072": {
580
- "content": "<|reserved_special_token_67|>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "128073": {
588
- "content": "<|reserved_special_token_68|>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "128074": {
596
- "content": "<|reserved_special_token_69|>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "128075": {
604
- "content": "<|reserved_special_token_70|>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "128076": {
612
- "content": "<|reserved_special_token_71|>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "128077": {
620
- "content": "<|reserved_special_token_72|>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "128078": {
628
- "content": "<|reserved_special_token_73|>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "128079": {
636
- "content": "<|reserved_special_token_74|>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "128080": {
644
- "content": "<|reserved_special_token_75|>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "128081": {
652
- "content": "<|reserved_special_token_76|>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "128082": {
660
- "content": "<|reserved_special_token_77|>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "128083": {
668
- "content": "<|reserved_special_token_78|>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "128084": {
676
- "content": "<|reserved_special_token_79|>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "128085": {
684
- "content": "<|reserved_special_token_80|>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "128086": {
692
- "content": "<|reserved_special_token_81|>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "128087": {
700
- "content": "<|reserved_special_token_82|>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "128088": {
708
- "content": "<|reserved_special_token_83|>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "128089": {
716
- "content": "<|reserved_special_token_84|>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "128090": {
724
- "content": "<|reserved_special_token_85|>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "128091": {
732
- "content": "<|reserved_special_token_86|>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "128092": {
740
- "content": "<|reserved_special_token_87|>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "128093": {
748
- "content": "<|reserved_special_token_88|>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "128094": {
756
- "content": "<|reserved_special_token_89|>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "128095": {
764
- "content": "<|reserved_special_token_90|>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "128096": {
772
- "content": "<|reserved_special_token_91|>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "128097": {
780
- "content": "<|reserved_special_token_92|>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "128098": {
788
- "content": "<|reserved_special_token_93|>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "128099": {
796
- "content": "<|reserved_special_token_94|>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "128100": {
804
- "content": "<|reserved_special_token_95|>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "128101": {
812
- "content": "<|reserved_special_token_96|>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "128102": {
820
- "content": "<|reserved_special_token_97|>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "128103": {
828
- "content": "<|reserved_special_token_98|>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "128104": {
836
- "content": "<|reserved_special_token_99|>",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "128105": {
844
- "content": "<|reserved_special_token_100|>",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "128106": {
852
- "content": "<|reserved_special_token_101|>",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "128107": {
860
- "content": "<|reserved_special_token_102|>",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "128108": {
868
- "content": "<|reserved_special_token_103|>",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "128109": {
876
- "content": "<|reserved_special_token_104|>",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "128110": {
884
- "content": "<|reserved_special_token_105|>",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "128111": {
892
- "content": "<|reserved_special_token_106|>",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "128112": {
900
- "content": "<|reserved_special_token_107|>",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "128113": {
908
- "content": "<|reserved_special_token_108|>",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "128114": {
916
- "content": "<|reserved_special_token_109|>",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "128115": {
924
- "content": "<|reserved_special_token_110|>",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "128116": {
932
- "content": "<|reserved_special_token_111|>",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "128117": {
940
- "content": "<|reserved_special_token_112|>",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "128118": {
948
- "content": "<|reserved_special_token_113|>",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "128119": {
956
- "content": "<|reserved_special_token_114|>",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "128120": {
964
- "content": "<|reserved_special_token_115|>",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "128121": {
972
- "content": "<|reserved_special_token_116|>",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "128122": {
980
- "content": "<|reserved_special_token_117|>",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "128123": {
988
- "content": "<|reserved_special_token_118|>",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "128124": {
996
- "content": "<|reserved_special_token_119|>",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_120|>",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_121|>",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_122|>",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_123|>",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_124|>",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_125|>",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_126|>",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_127|>",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_128|>",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_129|>",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_130|>",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_131|>",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_132|>",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_133|>",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_134|>",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_135|>",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_136|>",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_137|>",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_138|>",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_139|>",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_140|>",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_141|>",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_142|>",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_143|>",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_144|>",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_145|>",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_146|>",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_147|>",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_148|>",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_149|>",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_150|>",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_151|>",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_152|>",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_153|>",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_154|>",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_155|>",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_156|>",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_157|>",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_158|>",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_159|>",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_160|>",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_161|>",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_162|>",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_163|>",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_164|>",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_165|>",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_166|>",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_167|>",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_168|>",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_169|>",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_170|>",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_171|>",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_172|>",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_173|>",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_174|>",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_175|>",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_176|>",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_177|>",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_178|>",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_179|>",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_180|>",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_181|>",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_182|>",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_183|>",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_184|>",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_185|>",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_186|>",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_187|>",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_188|>",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_189|>",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_190|>",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_191|>",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_192|>",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_193|>",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_194|>",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_195|>",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_196|>",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_197|>",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_198|>",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_199|>",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_200|>",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_201|>",
1653
- "lstrip": false,
1654
- "normalized": false,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_202|>",
1661
- "lstrip": false,
1662
- "normalized": false,
1663
- "rstrip": false,
1664
- "single_word": false,
1665
- "special": true
1666
- },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_203|>",
1669
- "lstrip": false,
1670
- "normalized": false,
1671
- "rstrip": false,
1672
- "single_word": false,
1673
- "special": true
1674
- },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_204|>",
1677
- "lstrip": false,
1678
- "normalized": false,
1679
- "rstrip": false,
1680
- "single_word": false,
1681
- "special": true
1682
- },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_205|>",
1685
- "lstrip": false,
1686
- "normalized": false,
1687
- "rstrip": false,
1688
- "single_word": false,
1689
- "special": true
1690
- },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_206|>",
1693
- "lstrip": false,
1694
- "normalized": false,
1695
- "rstrip": false,
1696
- "single_word": false,
1697
- "special": true
1698
- },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_207|>",
1701
- "lstrip": false,
1702
- "normalized": false,
1703
- "rstrip": false,
1704
- "single_word": false,
1705
- "special": true
1706
- },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_208|>",
1709
- "lstrip": false,
1710
- "normalized": false,
1711
- "rstrip": false,
1712
- "single_word": false,
1713
- "special": true
1714
- },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_209|>",
1717
- "lstrip": false,
1718
- "normalized": false,
1719
- "rstrip": false,
1720
- "single_word": false,
1721
- "special": true
1722
- },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_210|>",
1725
- "lstrip": false,
1726
- "normalized": false,
1727
- "rstrip": false,
1728
- "single_word": false,
1729
- "special": true
1730
- },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_211|>",
1733
- "lstrip": false,
1734
- "normalized": false,
1735
- "rstrip": false,
1736
- "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_212|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_213|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_214|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_215|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_216|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_217|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_218|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_219|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_220|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_221|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_222|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_223|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_224|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_225|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_226|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_227|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_228|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_229|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_230|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_231|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_232|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_233|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_234|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_235|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_236|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_237|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_238|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_239|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_240|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_241|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_242|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_243|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_244|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_245|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_246|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_247|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_248|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_249|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_250|>",
2045
  "lstrip": false,
2046
  "normalized": false,
2047
  "rstrip": false,
2048
  "single_word": false,
2049
- "special": true
2050
  },
2051
- "128256": {
2052
  "content": "<|im_end|>",
2053
  "lstrip": false,
2054
  "normalized": false,
@@ -2056,24 +25,27 @@
2056
  "single_word": false,
2057
  "special": false
2058
  },
2059
- "128257": {
2060
- "content": "<|im_start|>",
2061
  "lstrip": false,
2062
  "normalized": false,
2063
  "rstrip": false,
2064
  "single_word": false,
2065
- "special": false
2066
  }
2067
  },
2068
- "bos_token": "<|begin_of_text|>",
 
 
 
 
2069
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
2070
- "clean_up_tokenization_spaces": true,
2071
  "eos_token": "<|im_end|>",
2072
- "model_input_names": [
2073
- "input_ids",
2074
- "attention_mask"
2075
- ],
2076
- "model_max_length": 1000000000000000019884624838656,
2077
  "pad_token": "<|end_of_text|>",
2078
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
2079
  }
 
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": false
19
  },
20
+ "151645": {
21
  "content": "<|im_end|>",
22
  "lstrip": false,
23
  "normalized": false,
 
25
  "single_word": false,
26
  "special": false
27
  },
28
+ "151646": {
29
+ "content": "<|end_of_text|>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
+ "special": true
35
  }
36
  },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
  "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 32768,
 
 
 
47
  "pad_token": "<|end_of_text|>",
48
+ "split_special_tokens": false,
49
+ "tokenizer_class": "Qwen2Tokenizer",
50
+ "unk_token": null
51
  }
trainer_state.json ADDED
@@ -0,0 +1,3561 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9740777666999003,
5
+ "eval_steps": 125,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 1.8329473944625845,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 0.9189,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "eval_loss": 0.8840048313140869,
21
+ "eval_runtime": 99.9262,
22
+ "eval_samples_per_second": 17.693,
23
+ "eval_steps_per_second": 0.37,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.01,
28
+ "grad_norm": 1.7916344264608899,
29
+ "learning_rate": 2.0000000000000003e-06,
30
+ "loss": 0.8962,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "grad_norm": 1.8909931480365287,
36
+ "learning_rate": 3e-06,
37
+ "loss": 0.8805,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "grad_norm": 1.6318273112027453,
43
+ "learning_rate": 4.000000000000001e-06,
44
+ "loss": 0.913,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "grad_norm": 1.2463401136319747,
50
+ "learning_rate": 5e-06,
51
+ "loss": 0.908,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.02,
56
+ "grad_norm": 1.1463980681106876,
57
+ "learning_rate": 6e-06,
58
+ "loss": 0.8729,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.03,
63
+ "grad_norm": 0.9477573494094379,
64
+ "learning_rate": 7e-06,
65
+ "loss": 0.8411,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.03,
70
+ "grad_norm": 4.0165120162042935,
71
+ "learning_rate": 8.000000000000001e-06,
72
+ "loss": 1.0541,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.04,
77
+ "grad_norm": 1.0713771331971476,
78
+ "learning_rate": 9e-06,
79
+ "loss": 0.8495,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.04,
84
+ "grad_norm": 0.8667235558943894,
85
+ "learning_rate": 1e-05,
86
+ "loss": 0.8199,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.04,
91
+ "grad_norm": 0.7411429457268661,
92
+ "learning_rate": 9.999897234791831e-06,
93
+ "loss": 0.7964,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.05,
98
+ "grad_norm": 0.5729968036750446,
99
+ "learning_rate": 9.999588943391597e-06,
100
+ "loss": 0.8039,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.05,
105
+ "grad_norm": 0.5402964207486183,
106
+ "learning_rate": 9.99907513847195e-06,
107
+ "loss": 0.8287,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.06,
112
+ "grad_norm": 0.5633328266442124,
113
+ "learning_rate": 9.9983558411534e-06,
114
+ "loss": 0.7842,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.06,
119
+ "grad_norm": 0.5412290905686791,
120
+ "learning_rate": 9.99743108100344e-06,
121
+ "loss": 0.8345,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.06,
126
+ "grad_norm": 0.4895379189634968,
127
+ "learning_rate": 9.99630089603534e-06,
128
+ "loss": 0.7922,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.07,
133
+ "grad_norm": 0.5088260537094976,
134
+ "learning_rate": 9.994965332706574e-06,
135
+ "loss": 0.7969,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.07,
140
+ "grad_norm": 0.47075507205524136,
141
+ "learning_rate": 9.993424445916923e-06,
142
+ "loss": 0.7931,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.08,
147
+ "grad_norm": 0.3878407143429931,
148
+ "learning_rate": 9.991678299006206e-06,
149
+ "loss": 0.8041,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.08,
154
+ "grad_norm": 0.3873731682942636,
155
+ "learning_rate": 9.989726963751683e-06,
156
+ "loss": 0.8107,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.08,
161
+ "grad_norm": 0.42417629604043083,
162
+ "learning_rate": 9.987570520365105e-06,
163
+ "loss": 0.7874,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.09,
168
+ "grad_norm": 0.4324680733617199,
169
+ "learning_rate": 9.98520905748941e-06,
170
+ "loss": 0.8025,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.09,
175
+ "grad_norm": 0.34546199757993784,
176
+ "learning_rate": 9.982642672195093e-06,
177
+ "loss": 0.8048,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.1,
182
+ "grad_norm": 0.35958771648273496,
183
+ "learning_rate": 9.979871469976197e-06,
184
+ "loss": 0.831,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.1,
189
+ "grad_norm": 0.3940074197908444,
190
+ "learning_rate": 9.976895564745993e-06,
191
+ "loss": 0.7944,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.1,
196
+ "grad_norm": 0.3818406187889153,
197
+ "learning_rate": 9.973715078832288e-06,
198
+ "loss": 0.7936,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.11,
203
+ "grad_norm": 10.237346743255186,
204
+ "learning_rate": 9.970330142972403e-06,
205
+ "loss": 1.0017,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.11,
210
+ "grad_norm": 6.504690612414681,
211
+ "learning_rate": 9.966740896307791e-06,
212
+ "loss": 1.0329,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.12,
217
+ "grad_norm": 0.4028775109425473,
218
+ "learning_rate": 9.962947486378325e-06,
219
+ "loss": 0.7702,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.12,
224
+ "grad_norm": 0.39810277536967076,
225
+ "learning_rate": 9.95895006911623e-06,
226
+ "loss": 0.771,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.12,
231
+ "grad_norm": 0.29862663396811506,
232
+ "learning_rate": 9.954748808839675e-06,
233
+ "loss": 0.7767,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.13,
238
+ "grad_norm": 0.3106188272362696,
239
+ "learning_rate": 9.950343878246011e-06,
240
+ "loss": 0.7943,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.13,
245
+ "grad_norm": 0.34702364911134964,
246
+ "learning_rate": 9.945735458404681e-06,
247
+ "loss": 0.7972,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.14,
252
+ "grad_norm": 0.3216448960978253,
253
+ "learning_rate": 9.94092373874978e-06,
254
+ "loss": 0.7847,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.14,
259
+ "grad_norm": 0.31232207978504006,
260
+ "learning_rate": 9.935908917072253e-06,
261
+ "loss": 0.7738,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.14,
266
+ "grad_norm": 0.3004886604892709,
267
+ "learning_rate": 9.930691199511775e-06,
268
+ "loss": 0.7877,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.15,
273
+ "grad_norm": 0.2870013960815822,
274
+ "learning_rate": 9.925270800548285e-06,
275
+ "loss": 0.754,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.15,
280
+ "grad_norm": 0.28322113595593756,
281
+ "learning_rate": 9.91964794299315e-06,
282
+ "loss": 0.7445,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.16,
287
+ "grad_norm": 0.3065117198934518,
288
+ "learning_rate": 9.91382285798002e-06,
289
+ "loss": 0.787,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.16,
294
+ "grad_norm": 0.2727693466806482,
295
+ "learning_rate": 9.907795784955327e-06,
296
+ "loss": 0.7865,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.16,
301
+ "grad_norm": 0.2746198009076503,
302
+ "learning_rate": 9.901566971668437e-06,
303
+ "loss": 0.7755,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.17,
308
+ "grad_norm": 0.2888207750688948,
309
+ "learning_rate": 9.895136674161466e-06,
310
+ "loss": 0.7789,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.17,
315
+ "grad_norm": 0.26218141394209254,
316
+ "learning_rate": 9.888505156758758e-06,
317
+ "loss": 0.7781,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.18,
322
+ "grad_norm": 0.27028128323788914,
323
+ "learning_rate": 9.881672692056022e-06,
324
+ "loss": 0.7596,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.18,
329
+ "grad_norm": 0.301432889634355,
330
+ "learning_rate": 9.874639560909118e-06,
331
+ "loss": 0.7746,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.18,
336
+ "grad_norm": 0.27768870163187315,
337
+ "learning_rate": 9.867406052422525e-06,
338
+ "loss": 0.7751,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.19,
343
+ "grad_norm": 0.2638230079020965,
344
+ "learning_rate": 9.85997246393744e-06,
345
+ "loss": 0.8085,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.19,
350
+ "grad_norm": 0.2826098837962784,
351
+ "learning_rate": 9.852339101019574e-06,
352
+ "loss": 0.7878,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.2,
357
+ "grad_norm": 0.2673052298412088,
358
+ "learning_rate": 9.844506277446577e-06,
359
+ "loss": 0.7747,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.2,
364
+ "grad_norm": 0.2589820555015507,
365
+ "learning_rate": 9.836474315195148e-06,
366
+ "loss": 0.7491,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.2,
371
+ "grad_norm": 0.27744141325372174,
372
+ "learning_rate": 9.828243544427795e-06,
373
+ "loss": 0.771,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.21,
378
+ "grad_norm": 0.25617202776049003,
379
+ "learning_rate": 9.819814303479268e-06,
380
+ "loss": 0.789,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.21,
385
+ "grad_norm": 0.25777796417187593,
386
+ "learning_rate": 9.811186938842645e-06,
387
+ "loss": 0.7498,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.22,
392
+ "grad_norm": 0.26356120702424557,
393
+ "learning_rate": 9.802361805155097e-06,
394
+ "loss": 0.7618,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.22,
399
+ "grad_norm": 0.24594116238284844,
400
+ "learning_rate": 9.793339265183303e-06,
401
+ "loss": 0.7647,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.22,
406
+ "grad_norm": 0.2766331605712476,
407
+ "learning_rate": 9.784119689808545e-06,
408
+ "loss": 0.7757,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.23,
413
+ "grad_norm": 0.2674205732918615,
414
+ "learning_rate": 9.774703458011453e-06,
415
+ "loss": 0.7479,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.23,
420
+ "grad_norm": 0.25100414008068433,
421
+ "learning_rate": 9.765090956856437e-06,
422
+ "loss": 0.7629,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.24,
427
+ "grad_norm": 0.2558976905977626,
428
+ "learning_rate": 9.755282581475769e-06,
429
+ "loss": 0.7368,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.24,
434
+ "grad_norm": 0.2816597522453804,
435
+ "learning_rate": 9.745278735053345e-06,
436
+ "loss": 0.7675,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.24,
441
+ "grad_norm": 0.27864046582364604,
442
+ "learning_rate": 9.735079828808107e-06,
443
+ "loss": 0.7693,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.25,
448
+ "grad_norm": 0.2537495381298166,
449
+ "learning_rate": 9.724686281977146e-06,
450
+ "loss": 0.7612,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.25,
455
+ "grad_norm": 0.27161360619636454,
456
+ "learning_rate": 9.714098521798466e-06,
457
+ "loss": 0.7659,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.26,
462
+ "grad_norm": 0.257282261183055,
463
+ "learning_rate": 9.703316983493414e-06,
464
+ "loss": 0.77,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.26,
469
+ "grad_norm": 0.2598148868150837,
470
+ "learning_rate": 9.692342110248802e-06,
471
+ "loss": 0.7637,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.26,
476
+ "grad_norm": 0.25319486577746536,
477
+ "learning_rate": 9.681174353198687e-06,
478
+ "loss": 0.7529,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.27,
483
+ "grad_norm": 0.2616187230129625,
484
+ "learning_rate": 9.669814171405818e-06,
485
+ "loss": 0.7482,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.27,
490
+ "grad_norm": 0.2531735015293101,
491
+ "learning_rate": 9.658262031842772e-06,
492
+ "loss": 0.7507,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.28,
497
+ "grad_norm": 0.2540031125746497,
498
+ "learning_rate": 9.64651840937276e-06,
499
+ "loss": 0.7573,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.28,
504
+ "grad_norm": 0.26251145119756225,
505
+ "learning_rate": 9.63458378673011e-06,
506
+ "loss": 0.7617,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.28,
511
+ "grad_norm": 11.659656865913,
512
+ "learning_rate": 9.622458654500408e-06,
513
+ "loss": 0.9807,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.29,
518
+ "grad_norm": 43.33218979251603,
519
+ "learning_rate": 9.610143511100354e-06,
520
+ "loss": 1.0213,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.29,
525
+ "grad_norm": 0.29661440448786996,
526
+ "learning_rate": 9.597638862757255e-06,
527
+ "loss": 0.7597,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.3,
532
+ "grad_norm": 0.2674359864711363,
533
+ "learning_rate": 9.584945223488227e-06,
534
+ "loss": 0.7716,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.3,
539
+ "grad_norm": 0.2587397735578842,
540
+ "learning_rate": 9.572063115079063e-06,
541
+ "loss": 0.7654,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.3,
546
+ "grad_norm": 0.27326638279450294,
547
+ "learning_rate": 9.558993067062785e-06,
548
+ "loss": 0.7832,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.31,
553
+ "grad_norm": 0.26424783232216553,
554
+ "learning_rate": 9.545735616697875e-06,
555
+ "loss": 0.7509,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.31,
560
+ "grad_norm": 0.26894661215694415,
561
+ "learning_rate": 9.532291308946191e-06,
562
+ "loss": 0.7638,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.32,
567
+ "grad_norm": 12.381149099110814,
568
+ "learning_rate": 9.518660696450567e-06,
569
+ "loss": 0.9726,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.32,
574
+ "grad_norm": 63.276974873593076,
575
+ "learning_rate": 9.504844339512096e-06,
576
+ "loss": 0.961,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.32,
581
+ "grad_norm": 0.34404347007223207,
582
+ "learning_rate": 9.490842806067095e-06,
583
+ "loss": 0.7366,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.33,
588
+ "grad_norm": 0.2761892805994169,
589
+ "learning_rate": 9.476656671663766e-06,
590
+ "loss": 0.7565,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.33,
595
+ "grad_norm": 0.2938700568825168,
596
+ "learning_rate": 9.462286519438531e-06,
597
+ "loss": 0.7586,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.33,
602
+ "grad_norm": 0.30998708104141814,
603
+ "learning_rate": 9.44773294009206e-06,
604
+ "loss": 0.747,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.34,
609
+ "grad_norm": 0.2789622879446074,
610
+ "learning_rate": 9.432996531865001e-06,
611
+ "loss": 0.7381,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.34,
616
+ "grad_norm": 0.3043211841621936,
617
+ "learning_rate": 9.418077900513377e-06,
618
+ "loss": 0.7648,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.35,
623
+ "grad_norm": 0.27269347275749684,
624
+ "learning_rate": 9.40297765928369e-06,
625
+ "loss": 0.7287,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.35,
630
+ "grad_norm": 0.29165683068711035,
631
+ "learning_rate": 9.387696428887715e-06,
632
+ "loss": 0.7714,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.35,
637
+ "grad_norm": 0.29093659611546846,
638
+ "learning_rate": 9.372234837476979e-06,
639
+ "loss": 0.754,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.36,
644
+ "grad_norm": 0.2622000520062877,
645
+ "learning_rate": 9.356593520616948e-06,
646
+ "loss": 0.7604,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.36,
651
+ "grad_norm": 0.29648676556314774,
652
+ "learning_rate": 9.340773121260893e-06,
653
+ "loss": 0.7677,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.37,
658
+ "grad_norm": 0.2971691719126809,
659
+ "learning_rate": 9.324774289723469e-06,
660
+ "loss": 0.7826,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.37,
665
+ "grad_norm": 0.2695147958164756,
666
+ "learning_rate": 9.308597683653976e-06,
667
+ "loss": 0.7675,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.37,
672
+ "grad_norm": 0.2947547264550856,
673
+ "learning_rate": 9.292243968009332e-06,
674
+ "loss": 0.7611,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.38,
679
+ "grad_norm": 0.2698951119585888,
680
+ "learning_rate": 9.275713815026732e-06,
681
+ "loss": 0.7437,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.38,
686
+ "grad_norm": 0.2922871464880811,
687
+ "learning_rate": 9.259007904196023e-06,
688
+ "loss": 0.7716,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.39,
693
+ "grad_norm": 13.342043215041077,
694
+ "learning_rate": 9.242126922231763e-06,
695
+ "loss": 1.0262,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.39,
700
+ "grad_norm": 3.3348436860369577,
701
+ "learning_rate": 9.225071563045007e-06,
702
+ "loss": 0.9733,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.39,
707
+ "grad_norm": 0.30515152013617763,
708
+ "learning_rate": 9.207842527714767e-06,
709
+ "loss": 0.7491,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.4,
714
+ "grad_norm": 0.2797372956926758,
715
+ "learning_rate": 9.190440524459203e-06,
716
+ "loss": 0.7658,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.4,
721
+ "grad_norm": 0.295442681103485,
722
+ "learning_rate": 9.172866268606514e-06,
723
+ "loss": 0.7359,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.41,
728
+ "grad_norm": 0.2890934213055238,
729
+ "learning_rate": 9.15512048256552e-06,
730
+ "loss": 0.7783,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.41,
735
+ "grad_norm": 0.2698602196909741,
736
+ "learning_rate": 9.137203895795983e-06,
737
+ "loss": 0.7476,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.41,
742
+ "grad_norm": 0.30586672847809404,
743
+ "learning_rate": 9.119117244778609e-06,
744
+ "loss": 0.7494,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.42,
749
+ "grad_norm": 0.28256137853789653,
750
+ "learning_rate": 9.10086127298478e-06,
751
+ "loss": 0.7347,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.42,
756
+ "grad_norm": 0.2654565204147507,
757
+ "learning_rate": 9.082436730845993e-06,
758
+ "loss": 0.7282,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.43,
763
+ "grad_norm": 0.3110313172517606,
764
+ "learning_rate": 9.063844375723014e-06,
765
+ "loss": 0.7442,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.43,
770
+ "grad_norm": 0.30406144580285027,
771
+ "learning_rate": 9.045084971874738e-06,
772
+ "loss": 0.7365,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.43,
777
+ "grad_norm": 0.2578097986689305,
778
+ "learning_rate": 9.026159290426782e-06,
779
+ "loss": 0.7644,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.44,
784
+ "grad_norm": 0.2875228334986064,
785
+ "learning_rate": 9.007068109339783e-06,
786
+ "loss": 0.7359,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.44,
791
+ "grad_norm": 0.3007292657335934,
792
+ "learning_rate": 8.987812213377423e-06,
793
+ "loss": 0.7571,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.45,
798
+ "grad_norm": 0.2705781647990633,
799
+ "learning_rate": 8.968392394074164e-06,
800
+ "loss": 0.7321,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.45,
805
+ "grad_norm": 7.709717121399015,
806
+ "learning_rate": 8.948809449702712e-06,
807
+ "loss": 1.0663,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.45,
812
+ "grad_norm": 0.3159530858994423,
813
+ "learning_rate": 8.929064185241214e-06,
814
+ "loss": 0.7594,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.46,
819
+ "grad_norm": 0.3001925080979955,
820
+ "learning_rate": 8.90915741234015e-06,
821
+ "loss": 0.7486,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.46,
826
+ "grad_norm": 2.7719217922453914,
827
+ "learning_rate": 8.889089949288986e-06,
828
+ "loss": 1.0014,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.47,
833
+ "grad_norm": 0.2980097580186808,
834
+ "learning_rate": 8.868862620982534e-06,
835
+ "loss": 0.7302,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.47,
840
+ "grad_norm": 0.2674175783919389,
841
+ "learning_rate": 8.84847625888703e-06,
842
+ "loss": 0.7515,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.47,
847
+ "grad_norm": 0.33089914745986465,
848
+ "learning_rate": 8.827931701005974e-06,
849
+ "loss": 0.7452,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.48,
854
+ "grad_norm": 0.2657873873108844,
855
+ "learning_rate": 8.807229791845673e-06,
856
+ "loss": 0.7565,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.48,
861
+ "grad_norm": 0.26891569095038903,
862
+ "learning_rate": 8.786371382380527e-06,
863
+ "loss": 0.7525,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.49,
868
+ "grad_norm": 0.30828049821760906,
869
+ "learning_rate": 8.765357330018056e-06,
870
+ "loss": 0.7395,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.49,
875
+ "grad_norm": 0.2703956947723179,
876
+ "learning_rate": 8.74418849856364e-06,
877
+ "loss": 0.7762,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.49,
882
+ "grad_norm": 0.27665743831770573,
883
+ "learning_rate": 8.722865758185036e-06,
884
+ "loss": 0.7499,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.5,
889
+ "grad_norm": 0.31328445024397394,
890
+ "learning_rate": 8.701389985376578e-06,
891
+ "loss": 0.7368,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.5,
896
+ "eval_loss": 0.7192811369895935,
897
+ "eval_runtime": 97.0775,
898
+ "eval_samples_per_second": 18.212,
899
+ "eval_steps_per_second": 0.381,
900
+ "step": 125
901
+ },
902
+ {
903
+ "epoch": 0.5,
904
+ "grad_norm": 0.26565830658390915,
905
+ "learning_rate": 8.679762062923176e-06,
906
+ "loss": 0.7727,
907
+ "step": 126
908
+ },
909
+ {
910
+ "epoch": 0.51,
911
+ "grad_norm": 0.2768705145101062,
912
+ "learning_rate": 8.657982879864007e-06,
913
+ "loss": 0.7178,
914
+ "step": 127
915
+ },
916
+ {
917
+ "epoch": 0.51,
918
+ "grad_norm": 0.27658899618203814,
919
+ "learning_rate": 8.636053331455986e-06,
920
+ "loss": 0.7521,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 0.51,
925
+ "grad_norm": 0.2687326456666238,
926
+ "learning_rate": 8.613974319136959e-06,
927
+ "loss": 0.7411,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 0.52,
932
+ "grad_norm": 0.2618083386724651,
933
+ "learning_rate": 8.591746750488639e-06,
934
+ "loss": 0.7306,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 0.52,
939
+ "grad_norm": 0.25666246646393165,
940
+ "learning_rate": 8.569371539199316e-06,
941
+ "loss": 0.7505,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 0.53,
946
+ "grad_norm": 0.3203048983481449,
947
+ "learning_rate": 8.54684960502629e-06,
948
+ "loss": 0.7515,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 0.53,
953
+ "grad_norm": 0.2521993776332652,
954
+ "learning_rate": 8.52418187375806e-06,
955
+ "loss": 0.7505,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 0.53,
960
+ "grad_norm": 0.26591933789428035,
961
+ "learning_rate": 8.501369277176275e-06,
962
+ "loss": 0.7353,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 0.54,
967
+ "grad_norm": 0.27603393300812845,
968
+ "learning_rate": 8.478412753017433e-06,
969
+ "loss": 0.7609,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 0.54,
974
+ "grad_norm": 0.2668194745887302,
975
+ "learning_rate": 8.455313244934324e-06,
976
+ "loss": 0.7141,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 0.55,
981
+ "grad_norm": 0.2707242484249978,
982
+ "learning_rate": 8.432071702457253e-06,
983
+ "loss": 0.7223,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.55,
988
+ "grad_norm": 0.25511126409448154,
989
+ "learning_rate": 8.408689080954997e-06,
990
+ "loss": 0.7153,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.55,
995
+ "grad_norm": 15.420395873510664,
996
+ "learning_rate": 8.38516634159555e-06,
997
+ "loss": 1.0042,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.56,
1002
+ "grad_norm": 0.3012234081880187,
1003
+ "learning_rate": 8.361504451306585e-06,
1004
+ "loss": 0.7713,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.56,
1009
+ "grad_norm": 0.2598491249346932,
1010
+ "learning_rate": 8.337704382735741e-06,
1011
+ "loss": 0.7288,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.57,
1016
+ "grad_norm": 0.26256298238822373,
1017
+ "learning_rate": 8.313767114210615e-06,
1018
+ "loss": 0.7379,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.57,
1023
+ "grad_norm": 0.2945113973208366,
1024
+ "learning_rate": 8.289693629698564e-06,
1025
+ "loss": 0.7401,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.57,
1030
+ "grad_norm": 0.24981458420819586,
1031
+ "learning_rate": 8.265484918766243e-06,
1032
+ "loss": 0.7512,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.58,
1037
+ "grad_norm": 0.2678413297548206,
1038
+ "learning_rate": 8.241141976538944e-06,
1039
+ "loss": 0.7449,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.58,
1044
+ "grad_norm": 0.2623417103083203,
1045
+ "learning_rate": 8.216665803659671e-06,
1046
+ "loss": 0.7647,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.59,
1051
+ "grad_norm": 0.263785777979794,
1052
+ "learning_rate": 8.192057406248028e-06,
1053
+ "loss": 0.7725,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.59,
1058
+ "grad_norm": 0.2519540317965661,
1059
+ "learning_rate": 8.16731779585885e-06,
1060
+ "loss": 0.715,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.59,
1065
+ "grad_norm": 0.27015785362121375,
1066
+ "learning_rate": 8.142447989440618e-06,
1067
+ "loss": 0.7532,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.6,
1072
+ "grad_norm": 0.25863328277564784,
1073
+ "learning_rate": 8.117449009293668e-06,
1074
+ "loss": 0.7335,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.6,
1079
+ "grad_norm": 0.2550714525590909,
1080
+ "learning_rate": 8.092321883028157e-06,
1081
+ "loss": 0.7182,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 0.61,
1086
+ "grad_norm": 0.2752483825047847,
1087
+ "learning_rate": 8.067067643521834e-06,
1088
+ "loss": 0.772,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 0.61,
1093
+ "grad_norm": 0.2582002365542859,
1094
+ "learning_rate": 8.041687328877566e-06,
1095
+ "loss": 0.7284,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 0.61,
1100
+ "grad_norm": 0.24823845365447103,
1101
+ "learning_rate": 8.016181982380682e-06,
1102
+ "loss": 0.7467,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 0.62,
1107
+ "grad_norm": 0.25644169647568194,
1108
+ "learning_rate": 7.99055265245608e-06,
1109
+ "loss": 0.7191,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 0.62,
1114
+ "grad_norm": 0.27463144458405375,
1115
+ "learning_rate": 7.96480039262513e-06,
1116
+ "loss": 0.7375,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 0.63,
1121
+ "grad_norm": 0.2642553744129046,
1122
+ "learning_rate": 7.938926261462366e-06,
1123
+ "loss": 0.7587,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 0.63,
1128
+ "grad_norm": 0.25679436337027056,
1129
+ "learning_rate": 7.912931322551981e-06,
1130
+ "loss": 0.7312,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 0.63,
1135
+ "grad_norm": 0.2784563408983632,
1136
+ "learning_rate": 7.886816644444099e-06,
1137
+ "loss": 0.7213,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 0.64,
1142
+ "grad_norm": 0.2638439438037005,
1143
+ "learning_rate": 7.860583300610849e-06,
1144
+ "loss": 0.7286,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 0.64,
1149
+ "grad_norm": 0.2599487424469649,
1150
+ "learning_rate": 7.83423236940225e-06,
1151
+ "loss": 0.7211,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 0.65,
1156
+ "grad_norm": 0.2620169279227201,
1157
+ "learning_rate": 7.807764934001875e-06,
1158
+ "loss": 0.7243,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 0.65,
1163
+ "grad_norm": 0.3455142385888707,
1164
+ "learning_rate": 7.781182082382325e-06,
1165
+ "loss": 0.7709,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 0.65,
1170
+ "grad_norm": 0.25797958121628417,
1171
+ "learning_rate": 7.754484907260513e-06,
1172
+ "loss": 0.7371,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 0.66,
1177
+ "grad_norm": 0.26245124486082283,
1178
+ "learning_rate": 7.727674506052744e-06,
1179
+ "loss": 0.7625,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 0.66,
1184
+ "grad_norm": 0.259525851556208,
1185
+ "learning_rate": 7.700751980829601e-06,
1186
+ "loss": 0.7785,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 0.67,
1191
+ "grad_norm": 0.25578616887441574,
1192
+ "learning_rate": 7.673718438270649e-06,
1193
+ "loss": 0.7349,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 0.67,
1198
+ "grad_norm": 0.26880908011952676,
1199
+ "learning_rate": 7.646574989618938e-06,
1200
+ "loss": 0.7423,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 0.67,
1205
+ "grad_norm": 0.28268284846763475,
1206
+ "learning_rate": 7.619322750635327e-06,
1207
+ "loss": 0.8089,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 0.68,
1212
+ "grad_norm": 0.2565025440158926,
1213
+ "learning_rate": 7.591962841552627e-06,
1214
+ "loss": 0.708,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 0.68,
1219
+ "grad_norm": 0.2589330645555015,
1220
+ "learning_rate": 7.564496387029532e-06,
1221
+ "loss": 0.7276,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 0.69,
1226
+ "grad_norm": 4.072287518324262,
1227
+ "learning_rate": 7.536924516104411e-06,
1228
+ "loss": 0.963,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 0.69,
1233
+ "grad_norm": 5.236195816930884,
1234
+ "learning_rate": 7.509248362148889e-06,
1235
+ "loss": 0.9786,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 0.69,
1240
+ "grad_norm": 0.3208811366448085,
1241
+ "learning_rate": 7.481469062821252e-06,
1242
+ "loss": 0.7417,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 0.7,
1247
+ "grad_norm": 0.280850125752099,
1248
+ "learning_rate": 7.453587760019691e-06,
1249
+ "loss": 0.7249,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 0.7,
1254
+ "grad_norm": 0.26692675004354643,
1255
+ "learning_rate": 7.42560559983536e-06,
1256
+ "loss": 0.727,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 0.71,
1261
+ "grad_norm": 0.27369623001787907,
1262
+ "learning_rate": 7.39752373250527e-06,
1263
+ "loss": 0.7617,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 0.71,
1268
+ "grad_norm": 0.2784142807735342,
1269
+ "learning_rate": 7.369343312364994e-06,
1270
+ "loss": 0.7466,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 0.71,
1275
+ "grad_norm": 37.27250895412763,
1276
+ "learning_rate": 7.34106549780123e-06,
1277
+ "loss": 1.0667,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 0.72,
1282
+ "grad_norm": 0.2760061039631398,
1283
+ "learning_rate": 7.312691451204178e-06,
1284
+ "loss": 0.7244,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 0.72,
1289
+ "grad_norm": 0.25459829854169064,
1290
+ "learning_rate": 7.284222338919758e-06,
1291
+ "loss": 0.7364,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 0.73,
1296
+ "grad_norm": 0.26179305555253735,
1297
+ "learning_rate": 7.255659331201673e-06,
1298
+ "loss": 0.733,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 0.73,
1303
+ "grad_norm": 0.2604418741829541,
1304
+ "learning_rate": 7.227003602163296e-06,
1305
+ "loss": 0.7209,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 0.73,
1310
+ "grad_norm": 0.26185681215109163,
1311
+ "learning_rate": 7.198256329729412e-06,
1312
+ "loss": 0.7164,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.74,
1317
+ "grad_norm": 16.152387103951856,
1318
+ "learning_rate": 7.169418695587791e-06,
1319
+ "loss": 1.0372,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.74,
1324
+ "grad_norm": 21.228735850953576,
1325
+ "learning_rate": 7.140491885140629e-06,
1326
+ "loss": 1.0402,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.75,
1331
+ "grad_norm": 0.28404810159037286,
1332
+ "learning_rate": 7.1114770874558e-06,
1333
+ "loss": 0.7006,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.75,
1338
+ "grad_norm": 0.26609034714435736,
1339
+ "learning_rate": 7.082375495217996e-06,
1340
+ "loss": 0.7537,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.75,
1345
+ "grad_norm": 0.25765084929276133,
1346
+ "learning_rate": 7.053188304679691e-06,
1347
+ "loss": 0.7302,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.76,
1352
+ "grad_norm": 0.26384158886834463,
1353
+ "learning_rate": 7.023916715611969e-06,
1354
+ "loss": 0.712,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.76,
1359
+ "grad_norm": 0.27151931787506317,
1360
+ "learning_rate": 6.994561931255209e-06,
1361
+ "loss": 0.7502,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.77,
1366
+ "grad_norm": 0.27031492068457535,
1367
+ "learning_rate": 6.965125158269619e-06,
1368
+ "loss": 0.7179,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.77,
1373
+ "grad_norm": 0.26995073084719196,
1374
+ "learning_rate": 6.935607606685642e-06,
1375
+ "loss": 0.7624,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.77,
1380
+ "grad_norm": 0.25666755324587454,
1381
+ "learning_rate": 6.906010489854209e-06,
1382
+ "loss": 0.7426,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.78,
1387
+ "grad_norm": 0.2764461509009301,
1388
+ "learning_rate": 6.876335024396872e-06,
1389
+ "loss": 0.723,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.78,
1394
+ "grad_norm": 0.2597906002555833,
1395
+ "learning_rate": 6.846582430155783e-06,
1396
+ "loss": 0.7407,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.79,
1401
+ "grad_norm": 0.26409742487438864,
1402
+ "learning_rate": 6.816753930143558e-06,
1403
+ "loss": 0.7206,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.79,
1408
+ "grad_norm": 0.25320169233675405,
1409
+ "learning_rate": 6.786850750493006e-06,
1410
+ "loss": 0.7437,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.79,
1415
+ "grad_norm": 0.2708696048462205,
1416
+ "learning_rate": 6.7568741204067145e-06,
1417
+ "loss": 0.7422,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.8,
1422
+ "grad_norm": 0.26542323915181154,
1423
+ "learning_rate": 6.726825272106539e-06,
1424
+ "loss": 0.7514,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.8,
1429
+ "grad_norm": 0.26307166597433396,
1430
+ "learning_rate": 6.696705440782939e-06,
1431
+ "loss": 0.7509,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.81,
1436
+ "grad_norm": 0.26671446872754456,
1437
+ "learning_rate": 6.66651586454421e-06,
1438
+ "loss": 0.7465,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.81,
1443
+ "grad_norm": 0.2720083369272757,
1444
+ "learning_rate": 6.636257784365585e-06,
1445
+ "loss": 0.7349,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.81,
1450
+ "grad_norm": 0.2652218770116059,
1451
+ "learning_rate": 6.605932444038229e-06,
1452
+ "loss": 0.7348,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.82,
1457
+ "grad_norm": 0.26402314109149694,
1458
+ "learning_rate": 6.575541090118105e-06,
1459
+ "loss": 0.7495,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.82,
1464
+ "grad_norm": 0.2639803511821082,
1465
+ "learning_rate": 6.545084971874738e-06,
1466
+ "loss": 0.7138,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.83,
1471
+ "grad_norm": 0.2673567043268493,
1472
+ "learning_rate": 6.514565341239861e-06,
1473
+ "loss": 0.7341,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.83,
1478
+ "grad_norm": 74.0236556664021,
1479
+ "learning_rate": 6.483983452755953e-06,
1480
+ "loss": 1.084,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.83,
1485
+ "grad_norm": 0.2694930198888902,
1486
+ "learning_rate": 6.4533405635246696e-06,
1487
+ "loss": 0.7422,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.84,
1492
+ "grad_norm": 0.2808089325365656,
1493
+ "learning_rate": 6.4226379331551625e-06,
1494
+ "loss": 0.7543,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.84,
1499
+ "grad_norm": 0.24629087243802783,
1500
+ "learning_rate": 6.3918768237123175e-06,
1501
+ "loss": 0.7088,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.85,
1506
+ "grad_norm": 0.2605148206784209,
1507
+ "learning_rate": 6.361058499664856e-06,
1508
+ "loss": 0.7434,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.85,
1513
+ "grad_norm": 0.26199687024127344,
1514
+ "learning_rate": 6.330184227833376e-06,
1515
+ "loss": 0.7369,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.85,
1520
+ "grad_norm": 0.2693080928270376,
1521
+ "learning_rate": 6.299255277338265e-06,
1522
+ "loss": 0.7337,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.86,
1527
+ "grad_norm": 0.2573571779304293,
1528
+ "learning_rate": 6.268272919547537e-06,
1529
+ "loss": 0.7366,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.86,
1534
+ "grad_norm": 0.25347655388671,
1535
+ "learning_rate": 6.237238428024573e-06,
1536
+ "loss": 0.7392,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.87,
1541
+ "grad_norm": 0.254807709796356,
1542
+ "learning_rate": 6.2061530784757625e-06,
1543
+ "loss": 0.7709,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.87,
1548
+ "grad_norm": 0.25435065962054804,
1549
+ "learning_rate": 6.175018148698077e-06,
1550
+ "loss": 0.7472,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.87,
1555
+ "grad_norm": 0.25856868944475736,
1556
+ "learning_rate": 6.143834918526528e-06,
1557
+ "loss": 0.7442,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.88,
1562
+ "grad_norm": 0.24960062893507637,
1563
+ "learning_rate": 6.112604669781572e-06,
1564
+ "loss": 0.7163,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.88,
1569
+ "grad_norm": 0.2544024553733407,
1570
+ "learning_rate": 6.0813286862164175e-06,
1571
+ "loss": 0.7236,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.89,
1576
+ "grad_norm": 0.2532920039697931,
1577
+ "learning_rate": 6.050008253464247e-06,
1578
+ "loss": 0.7427,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.89,
1583
+ "grad_norm": 0.25372808971698796,
1584
+ "learning_rate": 6.018644658985378e-06,
1585
+ "loss": 0.7286,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.89,
1590
+ "grad_norm": 0.2570514856547558,
1591
+ "learning_rate": 5.987239192014336e-06,
1592
+ "loss": 0.7349,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.9,
1597
+ "grad_norm": 0.2578576277551542,
1598
+ "learning_rate": 5.955793143506863e-06,
1599
+ "loss": 0.7266,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.9,
1604
+ "grad_norm": 0.26312215832145636,
1605
+ "learning_rate": 5.9243078060868445e-06,
1606
+ "loss": 0.7389,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.91,
1611
+ "grad_norm": 0.26518617358808877,
1612
+ "learning_rate": 5.892784473993184e-06,
1613
+ "loss": 0.7108,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.91,
1618
+ "grad_norm": 0.25620517627113376,
1619
+ "learning_rate": 5.861224443026595e-06,
1620
+ "loss": 0.7232,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.91,
1625
+ "grad_norm": 28.36402580586963,
1626
+ "learning_rate": 5.82962901049634e-06,
1627
+ "loss": 0.9734,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.92,
1632
+ "grad_norm": 0.2807037939514787,
1633
+ "learning_rate": 5.797999475166897e-06,
1634
+ "loss": 0.7341,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.92,
1639
+ "grad_norm": 8.208344028346868,
1640
+ "learning_rate": 5.766337137204579e-06,
1641
+ "loss": 0.938,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.93,
1646
+ "grad_norm": 0.26445130385050997,
1647
+ "learning_rate": 5.734643298124091e-06,
1648
+ "loss": 0.7316,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.93,
1653
+ "grad_norm": 0.251567451954335,
1654
+ "learning_rate": 5.702919260735015e-06,
1655
+ "loss": 0.6966,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.93,
1660
+ "grad_norm": 0.26329080787916564,
1661
+ "learning_rate": 5.671166329088278e-06,
1662
+ "loss": 0.7319,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.94,
1667
+ "grad_norm": 0.2566777339661679,
1668
+ "learning_rate": 5.6393858084225305e-06,
1669
+ "loss": 0.7529,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.94,
1674
+ "grad_norm": 0.2710815554700812,
1675
+ "learning_rate": 5.6075790051105025e-06,
1676
+ "loss": 0.7515,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 0.95,
1681
+ "grad_norm": 0.27096961550302734,
1682
+ "learning_rate": 5.575747226605298e-06,
1683
+ "loss": 0.7073,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 0.95,
1688
+ "grad_norm": 0.2509131795738037,
1689
+ "learning_rate": 5.543891781386655e-06,
1690
+ "loss": 0.7513,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 0.95,
1695
+ "grad_norm": 0.26210506205941153,
1696
+ "learning_rate": 5.512013978907157e-06,
1697
+ "loss": 0.7569,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 0.96,
1702
+ "grad_norm": 0.25123130642497177,
1703
+ "learning_rate": 5.480115129538409e-06,
1704
+ "loss": 0.7239,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 0.96,
1709
+ "grad_norm": 0.2596821607229612,
1710
+ "learning_rate": 5.448196544517168e-06,
1711
+ "loss": 0.7256,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 0.97,
1716
+ "grad_norm": 0.2714818563550966,
1717
+ "learning_rate": 5.4162595358914475e-06,
1718
+ "loss": 0.7329,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 0.97,
1723
+ "grad_norm": 0.260503064108439,
1724
+ "learning_rate": 5.384305416466584e-06,
1725
+ "loss": 0.7112,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 0.97,
1730
+ "grad_norm": 0.2661267608396215,
1731
+ "learning_rate": 5.35233549975127e-06,
1732
+ "loss": 0.7534,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 0.98,
1737
+ "grad_norm": 0.27502743208671454,
1738
+ "learning_rate": 5.320351099903565e-06,
1739
+ "loss": 0.7355,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 0.98,
1744
+ "grad_norm": 0.2598641343680277,
1745
+ "learning_rate": 5.288353531676873e-06,
1746
+ "loss": 0.7476,
1747
+ "step": 246
1748
+ },
1749
+ {
1750
+ "epoch": 0.99,
1751
+ "grad_norm": 0.2629788348419056,
1752
+ "learning_rate": 5.256344110365896e-06,
1753
+ "loss": 0.7523,
1754
+ "step": 247
1755
+ },
1756
+ {
1757
+ "epoch": 0.99,
1758
+ "grad_norm": 0.256123432185156,
1759
+ "learning_rate": 5.224324151752575e-06,
1760
+ "loss": 0.7479,
1761
+ "step": 248
1762
+ },
1763
+ {
1764
+ "epoch": 0.99,
1765
+ "grad_norm": 0.2592695095071067,
1766
+ "learning_rate": 5.192294972051992e-06,
1767
+ "loss": 0.7586,
1768
+ "step": 249
1769
+ },
1770
+ {
1771
+ "epoch": 1.0,
1772
+ "grad_norm": 0.26264999139615697,
1773
+ "learning_rate": 5.160257887858278e-06,
1774
+ "loss": 0.7406,
1775
+ "step": 250
1776
+ },
1777
+ {
1778
+ "epoch": 1.0,
1779
+ "eval_loss": 0.7036678791046143,
1780
+ "eval_runtime": 96.3087,
1781
+ "eval_samples_per_second": 18.358,
1782
+ "eval_steps_per_second": 0.384,
1783
+ "step": 250
1784
+ },
1785
+ {
1786
+ "epoch": 1.0,
1787
+ "grad_norm": 0.2614921961545108,
1788
+ "learning_rate": 5.128214216090478e-06,
1789
+ "loss": 0.7488,
1790
+ "step": 251
1791
+ },
1792
+ {
1793
+ "epoch": 1.0,
1794
+ "grad_norm": 0.2605743808221771,
1795
+ "learning_rate": 5.0961652739384356e-06,
1796
+ "loss": 0.7338,
1797
+ "step": 252
1798
+ },
1799
+ {
1800
+ "epoch": 1.01,
1801
+ "grad_norm": 2.904417203670962,
1802
+ "learning_rate": 5.064112378808636e-06,
1803
+ "loss": 0.9738,
1804
+ "step": 253
1805
+ },
1806
+ {
1807
+ "epoch": 1.01,
1808
+ "grad_norm": 0.2581985759494367,
1809
+ "learning_rate": 5.032056848270056e-06,
1810
+ "loss": 0.7693,
1811
+ "step": 254
1812
+ },
1813
+ {
1814
+ "epoch": 1.02,
1815
+ "grad_norm": 0.25102446332314765,
1816
+ "learning_rate": 5e-06,
1817
+ "loss": 0.7213,
1818
+ "step": 255
1819
+ },
1820
+ {
1821
+ "epoch": 1.0,
1822
+ "grad_norm": 1.4216598983588058,
1823
+ "learning_rate": 4.967943151729945e-06,
1824
+ "loss": 0.9193,
1825
+ "step": 256
1826
+ },
1827
+ {
1828
+ "epoch": 1.0,
1829
+ "grad_norm": 0.32982276331099014,
1830
+ "learning_rate": 4.935887621191364e-06,
1831
+ "loss": 0.6842,
1832
+ "step": 257
1833
+ },
1834
+ {
1835
+ "epoch": 1.01,
1836
+ "grad_norm": 0.29043411467478625,
1837
+ "learning_rate": 4.903834726061565e-06,
1838
+ "loss": 0.7087,
1839
+ "step": 258
1840
+ },
1841
+ {
1842
+ "epoch": 1.01,
1843
+ "grad_norm": 0.25986254756592664,
1844
+ "learning_rate": 4.871785783909523e-06,
1845
+ "loss": 0.6741,
1846
+ "step": 259
1847
+ },
1848
+ {
1849
+ "epoch": 1.02,
1850
+ "grad_norm": 0.30049816553828484,
1851
+ "learning_rate": 4.839742112141725e-06,
1852
+ "loss": 0.7063,
1853
+ "step": 260
1854
+ },
1855
+ {
1856
+ "epoch": 1.02,
1857
+ "grad_norm": 0.2895999616622155,
1858
+ "learning_rate": 4.807705027948008e-06,
1859
+ "loss": 0.7146,
1860
+ "step": 261
1861
+ },
1862
+ {
1863
+ "epoch": 1.02,
1864
+ "grad_norm": 0.30041272052643164,
1865
+ "learning_rate": 4.775675848247427e-06,
1866
+ "loss": 0.7134,
1867
+ "step": 262
1868
+ },
1869
+ {
1870
+ "epoch": 1.03,
1871
+ "grad_norm": 0.27518299819790887,
1872
+ "learning_rate": 4.743655889634105e-06,
1873
+ "loss": 0.692,
1874
+ "step": 263
1875
+ },
1876
+ {
1877
+ "epoch": 1.03,
1878
+ "grad_norm": 0.26955160521446175,
1879
+ "learning_rate": 4.711646468323129e-06,
1880
+ "loss": 0.658,
1881
+ "step": 264
1882
+ },
1883
+ {
1884
+ "epoch": 1.04,
1885
+ "grad_norm": 0.27535739664976405,
1886
+ "learning_rate": 4.679648900096436e-06,
1887
+ "loss": 0.6908,
1888
+ "step": 265
1889
+ },
1890
+ {
1891
+ "epoch": 1.04,
1892
+ "grad_norm": 0.26763089124769246,
1893
+ "learning_rate": 4.64766450024873e-06,
1894
+ "loss": 0.6861,
1895
+ "step": 266
1896
+ },
1897
+ {
1898
+ "epoch": 1.04,
1899
+ "grad_norm": 74.38254133611925,
1900
+ "learning_rate": 4.615694583533418e-06,
1901
+ "loss": 0.9994,
1902
+ "step": 267
1903
+ },
1904
+ {
1905
+ "epoch": 1.05,
1906
+ "grad_norm": 0.2986551656205794,
1907
+ "learning_rate": 4.583740464108554e-06,
1908
+ "loss": 0.7075,
1909
+ "step": 268
1910
+ },
1911
+ {
1912
+ "epoch": 1.05,
1913
+ "grad_norm": 0.27619714658975547,
1914
+ "learning_rate": 4.551803455482833e-06,
1915
+ "loss": 0.6596,
1916
+ "step": 269
1917
+ },
1918
+ {
1919
+ "epoch": 1.06,
1920
+ "grad_norm": 0.25242413092583954,
1921
+ "learning_rate": 4.5198848704615915e-06,
1922
+ "loss": 0.6628,
1923
+ "step": 270
1924
+ },
1925
+ {
1926
+ "epoch": 1.06,
1927
+ "grad_norm": 0.26017582720690735,
1928
+ "learning_rate": 4.487986021092844e-06,
1929
+ "loss": 0.6916,
1930
+ "step": 271
1931
+ },
1932
+ {
1933
+ "epoch": 1.06,
1934
+ "grad_norm": 0.2719334401383232,
1935
+ "learning_rate": 4.456108218613346e-06,
1936
+ "loss": 0.6935,
1937
+ "step": 272
1938
+ },
1939
+ {
1940
+ "epoch": 1.07,
1941
+ "grad_norm": 0.2874168693732095,
1942
+ "learning_rate": 4.424252773394704e-06,
1943
+ "loss": 0.7013,
1944
+ "step": 273
1945
+ },
1946
+ {
1947
+ "epoch": 1.07,
1948
+ "grad_norm": 0.27088215577908004,
1949
+ "learning_rate": 4.392420994889498e-06,
1950
+ "loss": 0.693,
1951
+ "step": 274
1952
+ },
1953
+ {
1954
+ "epoch": 1.08,
1955
+ "grad_norm": 0.2532812233498042,
1956
+ "learning_rate": 4.3606141915774695e-06,
1957
+ "loss": 0.6762,
1958
+ "step": 275
1959
+ },
1960
+ {
1961
+ "epoch": 1.08,
1962
+ "grad_norm": 0.263089719520046,
1963
+ "learning_rate": 4.3288336709117246e-06,
1964
+ "loss": 0.6677,
1965
+ "step": 276
1966
+ },
1967
+ {
1968
+ "epoch": 1.08,
1969
+ "grad_norm": 0.2544227492529696,
1970
+ "learning_rate": 4.297080739264987e-06,
1971
+ "loss": 0.6744,
1972
+ "step": 277
1973
+ },
1974
+ {
1975
+ "epoch": 1.09,
1976
+ "grad_norm": 0.2645751047762965,
1977
+ "learning_rate": 4.265356701875911e-06,
1978
+ "loss": 0.7047,
1979
+ "step": 278
1980
+ },
1981
+ {
1982
+ "epoch": 1.09,
1983
+ "grad_norm": 0.2602397068309733,
1984
+ "learning_rate": 4.23366286279542e-06,
1985
+ "loss": 0.6792,
1986
+ "step": 279
1987
+ },
1988
+ {
1989
+ "epoch": 1.1,
1990
+ "grad_norm": 0.27012218470061766,
1991
+ "learning_rate": 4.2020005248331056e-06,
1992
+ "loss": 0.6914,
1993
+ "step": 280
1994
+ },
1995
+ {
1996
+ "epoch": 1.1,
1997
+ "grad_norm": 0.2645729945558582,
1998
+ "learning_rate": 4.170370989503662e-06,
1999
+ "loss": 0.6812,
2000
+ "step": 281
2001
+ },
2002
+ {
2003
+ "epoch": 1.1,
2004
+ "grad_norm": 0.26158176244234604,
2005
+ "learning_rate": 4.138775556973406e-06,
2006
+ "loss": 0.6545,
2007
+ "step": 282
2008
+ },
2009
+ {
2010
+ "epoch": 1.11,
2011
+ "grad_norm": 0.2609966416888788,
2012
+ "learning_rate": 4.107215526006818e-06,
2013
+ "loss": 0.6534,
2014
+ "step": 283
2015
+ },
2016
+ {
2017
+ "epoch": 1.11,
2018
+ "grad_norm": 0.2633177456953443,
2019
+ "learning_rate": 4.075692193913156e-06,
2020
+ "loss": 0.6617,
2021
+ "step": 284
2022
+ },
2023
+ {
2024
+ "epoch": 1.12,
2025
+ "grad_norm": 0.2711366514748812,
2026
+ "learning_rate": 4.04420685649314e-06,
2027
+ "loss": 0.7026,
2028
+ "step": 285
2029
+ },
2030
+ {
2031
+ "epoch": 1.12,
2032
+ "grad_norm": 0.26016920693531187,
2033
+ "learning_rate": 4.012760807985665e-06,
2034
+ "loss": 0.685,
2035
+ "step": 286
2036
+ },
2037
+ {
2038
+ "epoch": 1.12,
2039
+ "grad_norm": 0.2634077734164485,
2040
+ "learning_rate": 3.9813553410146225e-06,
2041
+ "loss": 0.6732,
2042
+ "step": 287
2043
+ },
2044
+ {
2045
+ "epoch": 1.13,
2046
+ "grad_norm": 0.2630739058989318,
2047
+ "learning_rate": 3.949991746535753e-06,
2048
+ "loss": 0.6898,
2049
+ "step": 288
2050
+ },
2051
+ {
2052
+ "epoch": 1.13,
2053
+ "grad_norm": 0.26810735877032293,
2054
+ "learning_rate": 3.918671313783583e-06,
2055
+ "loss": 0.6739,
2056
+ "step": 289
2057
+ },
2058
+ {
2059
+ "epoch": 1.14,
2060
+ "grad_norm": 0.2667138269733132,
2061
+ "learning_rate": 3.887395330218429e-06,
2062
+ "loss": 0.6649,
2063
+ "step": 290
2064
+ },
2065
+ {
2066
+ "epoch": 1.14,
2067
+ "grad_norm": 0.2563222658817468,
2068
+ "learning_rate": 3.856165081473474e-06,
2069
+ "loss": 0.708,
2070
+ "step": 291
2071
+ },
2072
+ {
2073
+ "epoch": 1.14,
2074
+ "grad_norm": 0.26451201369218524,
2075
+ "learning_rate": 3.824981851301924e-06,
2076
+ "loss": 0.6715,
2077
+ "step": 292
2078
+ },
2079
+ {
2080
+ "epoch": 1.15,
2081
+ "grad_norm": 0.2598494927634439,
2082
+ "learning_rate": 3.7938469215242374e-06,
2083
+ "loss": 0.6955,
2084
+ "step": 293
2085
+ },
2086
+ {
2087
+ "epoch": 1.15,
2088
+ "grad_norm": 0.25396403307478727,
2089
+ "learning_rate": 3.7627615719754294e-06,
2090
+ "loss": 0.6676,
2091
+ "step": 294
2092
+ },
2093
+ {
2094
+ "epoch": 1.16,
2095
+ "grad_norm": 0.2532765659210287,
2096
+ "learning_rate": 3.731727080452464e-06,
2097
+ "loss": 0.6748,
2098
+ "step": 295
2099
+ },
2100
+ {
2101
+ "epoch": 1.16,
2102
+ "grad_norm": 0.26061271523616963,
2103
+ "learning_rate": 3.7007447226617367e-06,
2104
+ "loss": 0.7058,
2105
+ "step": 296
2106
+ },
2107
+ {
2108
+ "epoch": 1.16,
2109
+ "grad_norm": 0.25801226716086006,
2110
+ "learning_rate": 3.669815772166625e-06,
2111
+ "loss": 0.6717,
2112
+ "step": 297
2113
+ },
2114
+ {
2115
+ "epoch": 1.17,
2116
+ "grad_norm": 0.2678578983084559,
2117
+ "learning_rate": 3.638941500335145e-06,
2118
+ "loss": 0.6785,
2119
+ "step": 298
2120
+ },
2121
+ {
2122
+ "epoch": 1.17,
2123
+ "grad_norm": 0.2629273311111566,
2124
+ "learning_rate": 3.608123176287685e-06,
2125
+ "loss": 0.6846,
2126
+ "step": 299
2127
+ },
2128
+ {
2129
+ "epoch": 1.18,
2130
+ "grad_norm": 0.26372287416738016,
2131
+ "learning_rate": 3.5773620668448384e-06,
2132
+ "loss": 0.7155,
2133
+ "step": 300
2134
+ },
2135
+ {
2136
+ "epoch": 1.18,
2137
+ "grad_norm": 0.2705437923133382,
2138
+ "learning_rate": 3.5466594364753325e-06,
2139
+ "loss": 0.6723,
2140
+ "step": 301
2141
+ },
2142
+ {
2143
+ "epoch": 1.18,
2144
+ "grad_norm": 0.2839291053250124,
2145
+ "learning_rate": 3.516016547244047e-06,
2146
+ "loss": 0.7035,
2147
+ "step": 302
2148
+ },
2149
+ {
2150
+ "epoch": 1.19,
2151
+ "grad_norm": 0.2760313377640414,
2152
+ "learning_rate": 3.48543465876014e-06,
2153
+ "loss": 0.6751,
2154
+ "step": 303
2155
+ },
2156
+ {
2157
+ "epoch": 1.19,
2158
+ "grad_norm": 0.25394626546919435,
2159
+ "learning_rate": 3.4549150281252635e-06,
2160
+ "loss": 0.6795,
2161
+ "step": 304
2162
+ },
2163
+ {
2164
+ "epoch": 1.2,
2165
+ "grad_norm": 0.2591221216055477,
2166
+ "learning_rate": 3.424458909881897e-06,
2167
+ "loss": 0.6766,
2168
+ "step": 305
2169
+ },
2170
+ {
2171
+ "epoch": 1.2,
2172
+ "grad_norm": 0.2691782924782941,
2173
+ "learning_rate": 3.3940675559617724e-06,
2174
+ "loss": 0.6895,
2175
+ "step": 306
2176
+ },
2177
+ {
2178
+ "epoch": 1.2,
2179
+ "grad_norm": 0.26815145183562566,
2180
+ "learning_rate": 3.363742215634416e-06,
2181
+ "loss": 0.6671,
2182
+ "step": 307
2183
+ },
2184
+ {
2185
+ "epoch": 1.21,
2186
+ "grad_norm": 0.26601253229287064,
2187
+ "learning_rate": 3.3334841354557923e-06,
2188
+ "loss": 0.6902,
2189
+ "step": 308
2190
+ },
2191
+ {
2192
+ "epoch": 1.21,
2193
+ "grad_norm": 0.2759140499002526,
2194
+ "learning_rate": 3.303294559217063e-06,
2195
+ "loss": 0.7011,
2196
+ "step": 309
2197
+ },
2198
+ {
2199
+ "epoch": 1.22,
2200
+ "grad_norm": 0.2532152571509874,
2201
+ "learning_rate": 3.273174727893463e-06,
2202
+ "loss": 0.6631,
2203
+ "step": 310
2204
+ },
2205
+ {
2206
+ "epoch": 1.22,
2207
+ "grad_norm": 0.2587732106097895,
2208
+ "learning_rate": 3.2431258795932863e-06,
2209
+ "loss": 0.6964,
2210
+ "step": 311
2211
+ },
2212
+ {
2213
+ "epoch": 1.22,
2214
+ "grad_norm": 0.26154429819114283,
2215
+ "learning_rate": 3.213149249506997e-06,
2216
+ "loss": 0.7018,
2217
+ "step": 312
2218
+ },
2219
+ {
2220
+ "epoch": 1.23,
2221
+ "grad_norm": 0.2640699829932556,
2222
+ "learning_rate": 3.183246069856443e-06,
2223
+ "loss": 0.6809,
2224
+ "step": 313
2225
+ },
2226
+ {
2227
+ "epoch": 1.23,
2228
+ "grad_norm": 0.26350081604751235,
2229
+ "learning_rate": 3.1534175698442194e-06,
2230
+ "loss": 0.655,
2231
+ "step": 314
2232
+ },
2233
+ {
2234
+ "epoch": 1.24,
2235
+ "grad_norm": 0.2620810766791341,
2236
+ "learning_rate": 3.12366497560313e-06,
2237
+ "loss": 0.7034,
2238
+ "step": 315
2239
+ },
2240
+ {
2241
+ "epoch": 1.24,
2242
+ "grad_norm": 0.26759545817238656,
2243
+ "learning_rate": 3.093989510145792e-06,
2244
+ "loss": 0.7238,
2245
+ "step": 316
2246
+ },
2247
+ {
2248
+ "epoch": 1.24,
2249
+ "grad_norm": 0.26779990918516644,
2250
+ "learning_rate": 3.0643923933143603e-06,
2251
+ "loss": 0.6733,
2252
+ "step": 317
2253
+ },
2254
+ {
2255
+ "epoch": 1.25,
2256
+ "grad_norm": 0.266460909749917,
2257
+ "learning_rate": 3.0348748417303826e-06,
2258
+ "loss": 0.6708,
2259
+ "step": 318
2260
+ },
2261
+ {
2262
+ "epoch": 1.25,
2263
+ "grad_norm": 0.26133722668937404,
2264
+ "learning_rate": 3.005438068744792e-06,
2265
+ "loss": 0.6838,
2266
+ "step": 319
2267
+ },
2268
+ {
2269
+ "epoch": 1.26,
2270
+ "grad_norm": 0.26893527319559857,
2271
+ "learning_rate": 2.976083284388031e-06,
2272
+ "loss": 0.662,
2273
+ "step": 320
2274
+ },
2275
+ {
2276
+ "epoch": 1.26,
2277
+ "grad_norm": 0.2699706439018165,
2278
+ "learning_rate": 2.9468116953203107e-06,
2279
+ "loss": 0.6867,
2280
+ "step": 321
2281
+ },
2282
+ {
2283
+ "epoch": 1.26,
2284
+ "grad_norm": 0.2660357193246072,
2285
+ "learning_rate": 2.9176245047820064e-06,
2286
+ "loss": 0.6802,
2287
+ "step": 322
2288
+ },
2289
+ {
2290
+ "epoch": 1.27,
2291
+ "grad_norm": 0.2676372441332764,
2292
+ "learning_rate": 2.8885229125442022e-06,
2293
+ "loss": 0.7143,
2294
+ "step": 323
2295
+ },
2296
+ {
2297
+ "epoch": 1.27,
2298
+ "grad_norm": 0.26172654998349437,
2299
+ "learning_rate": 2.859508114859374e-06,
2300
+ "loss": 0.6688,
2301
+ "step": 324
2302
+ },
2303
+ {
2304
+ "epoch": 1.28,
2305
+ "grad_norm": 0.26622148926216194,
2306
+ "learning_rate": 2.83058130441221e-06,
2307
+ "loss": 0.671,
2308
+ "step": 325
2309
+ },
2310
+ {
2311
+ "epoch": 1.28,
2312
+ "grad_norm": 0.28436198488003145,
2313
+ "learning_rate": 2.80174367027059e-06,
2314
+ "loss": 0.7157,
2315
+ "step": 326
2316
+ },
2317
+ {
2318
+ "epoch": 1.28,
2319
+ "grad_norm": 0.2637348527869296,
2320
+ "learning_rate": 2.772996397836704e-06,
2321
+ "loss": 0.6893,
2322
+ "step": 327
2323
+ },
2324
+ {
2325
+ "epoch": 1.29,
2326
+ "grad_norm": 0.27094660677035604,
2327
+ "learning_rate": 2.7443406687983267e-06,
2328
+ "loss": 0.7149,
2329
+ "step": 328
2330
+ },
2331
+ {
2332
+ "epoch": 1.29,
2333
+ "grad_norm": 0.26943858696681655,
2334
+ "learning_rate": 2.7157776610802416e-06,
2335
+ "loss": 0.6756,
2336
+ "step": 329
2337
+ },
2338
+ {
2339
+ "epoch": 1.3,
2340
+ "grad_norm": 0.2637431948145577,
2341
+ "learning_rate": 2.687308548795825e-06,
2342
+ "loss": 0.6731,
2343
+ "step": 330
2344
+ },
2345
+ {
2346
+ "epoch": 1.3,
2347
+ "grad_norm": 0.2605764257900338,
2348
+ "learning_rate": 2.6589345021987725e-06,
2349
+ "loss": 0.6601,
2350
+ "step": 331
2351
+ },
2352
+ {
2353
+ "epoch": 1.3,
2354
+ "grad_norm": 0.2691370320929689,
2355
+ "learning_rate": 2.6306566876350072e-06,
2356
+ "loss": 0.6747,
2357
+ "step": 332
2358
+ },
2359
+ {
2360
+ "epoch": 1.31,
2361
+ "grad_norm": 0.26505353096492007,
2362
+ "learning_rate": 2.6024762674947313e-06,
2363
+ "loss": 0.6355,
2364
+ "step": 333
2365
+ },
2366
+ {
2367
+ "epoch": 1.31,
2368
+ "grad_norm": 0.2771254154185314,
2369
+ "learning_rate": 2.5743944001646394e-06,
2370
+ "loss": 0.6679,
2371
+ "step": 334
2372
+ },
2373
+ {
2374
+ "epoch": 1.32,
2375
+ "grad_norm": 0.2734747453519109,
2376
+ "learning_rate": 2.5464122399803126e-06,
2377
+ "loss": 0.6842,
2378
+ "step": 335
2379
+ },
2380
+ {
2381
+ "epoch": 1.32,
2382
+ "grad_norm": 0.26644275829657593,
2383
+ "learning_rate": 2.5185309371787515e-06,
2384
+ "loss": 0.6986,
2385
+ "step": 336
2386
+ },
2387
+ {
2388
+ "epoch": 1.32,
2389
+ "grad_norm": 2.921169787601039,
2390
+ "learning_rate": 2.4907516378511137e-06,
2391
+ "loss": 0.9339,
2392
+ "step": 337
2393
+ },
2394
+ {
2395
+ "epoch": 1.33,
2396
+ "grad_norm": 0.25960894123414624,
2397
+ "learning_rate": 2.46307548389559e-06,
2398
+ "loss": 0.6743,
2399
+ "step": 338
2400
+ },
2401
+ {
2402
+ "epoch": 1.33,
2403
+ "grad_norm": 0.2637156946948773,
2404
+ "learning_rate": 2.43550361297047e-06,
2405
+ "loss": 0.682,
2406
+ "step": 339
2407
+ },
2408
+ {
2409
+ "epoch": 1.34,
2410
+ "grad_norm": 0.26481304373722364,
2411
+ "learning_rate": 2.408037158447375e-06,
2412
+ "loss": 0.6838,
2413
+ "step": 340
2414
+ },
2415
+ {
2416
+ "epoch": 1.34,
2417
+ "grad_norm": 0.3098032445823631,
2418
+ "learning_rate": 2.3806772493646725e-06,
2419
+ "loss": 0.6569,
2420
+ "step": 341
2421
+ },
2422
+ {
2423
+ "epoch": 1.34,
2424
+ "grad_norm": 0.26219269959571206,
2425
+ "learning_rate": 2.353425010381063e-06,
2426
+ "loss": 0.6761,
2427
+ "step": 342
2428
+ },
2429
+ {
2430
+ "epoch": 1.35,
2431
+ "grad_norm": 0.2595963563694489,
2432
+ "learning_rate": 2.3262815617293517e-06,
2433
+ "loss": 0.6705,
2434
+ "step": 343
2435
+ },
2436
+ {
2437
+ "epoch": 1.35,
2438
+ "grad_norm": 6.834107729255299,
2439
+ "learning_rate": 2.2992480191704003e-06,
2440
+ "loss": 0.9304,
2441
+ "step": 344
2442
+ },
2443
+ {
2444
+ "epoch": 1.36,
2445
+ "grad_norm": 0.27845487671808766,
2446
+ "learning_rate": 2.272325493947257e-06,
2447
+ "loss": 0.7032,
2448
+ "step": 345
2449
+ },
2450
+ {
2451
+ "epoch": 1.36,
2452
+ "grad_norm": 0.27640918477115356,
2453
+ "learning_rate": 2.245515092739488e-06,
2454
+ "loss": 0.6782,
2455
+ "step": 346
2456
+ },
2457
+ {
2458
+ "epoch": 1.36,
2459
+ "grad_norm": 0.2807587758407648,
2460
+ "learning_rate": 2.2188179176176767e-06,
2461
+ "loss": 0.6932,
2462
+ "step": 347
2463
+ },
2464
+ {
2465
+ "epoch": 1.37,
2466
+ "grad_norm": 0.27767259525555504,
2467
+ "learning_rate": 2.1922350659981262e-06,
2468
+ "loss": 0.6466,
2469
+ "step": 348
2470
+ },
2471
+ {
2472
+ "epoch": 1.37,
2473
+ "grad_norm": 0.267658673895331,
2474
+ "learning_rate": 2.165767630597752e-06,
2475
+ "loss": 0.7089,
2476
+ "step": 349
2477
+ },
2478
+ {
2479
+ "epoch": 1.38,
2480
+ "grad_norm": 0.2745228363539692,
2481
+ "learning_rate": 2.139416699389153e-06,
2482
+ "loss": 0.6778,
2483
+ "step": 350
2484
+ },
2485
+ {
2486
+ "epoch": 1.38,
2487
+ "grad_norm": 0.26408657536920843,
2488
+ "learning_rate": 2.1131833555559037e-06,
2489
+ "loss": 0.693,
2490
+ "step": 351
2491
+ },
2492
+ {
2493
+ "epoch": 1.38,
2494
+ "grad_norm": 0.27582062474841573,
2495
+ "learning_rate": 2.08706867744802e-06,
2496
+ "loss": 0.6896,
2497
+ "step": 352
2498
+ },
2499
+ {
2500
+ "epoch": 1.39,
2501
+ "grad_norm": 0.26826511006390147,
2502
+ "learning_rate": 2.061073738537635e-06,
2503
+ "loss": 0.6796,
2504
+ "step": 353
2505
+ },
2506
+ {
2507
+ "epoch": 1.39,
2508
+ "grad_norm": 0.26630216372896987,
2509
+ "learning_rate": 2.0351996073748713e-06,
2510
+ "loss": 0.664,
2511
+ "step": 354
2512
+ },
2513
+ {
2514
+ "epoch": 1.4,
2515
+ "grad_norm": 0.2809694093215496,
2516
+ "learning_rate": 2.00944734754392e-06,
2517
+ "loss": 0.7044,
2518
+ "step": 355
2519
+ },
2520
+ {
2521
+ "epoch": 1.4,
2522
+ "grad_norm": 1.2984772108139377,
2523
+ "learning_rate": 1.983818017619318e-06,
2524
+ "loss": 0.9348,
2525
+ "step": 356
2526
+ },
2527
+ {
2528
+ "epoch": 1.4,
2529
+ "grad_norm": 0.2721943586746493,
2530
+ "learning_rate": 1.9583126711224342e-06,
2531
+ "loss": 0.6918,
2532
+ "step": 357
2533
+ },
2534
+ {
2535
+ "epoch": 1.41,
2536
+ "grad_norm": 0.27480703238103743,
2537
+ "learning_rate": 1.932932356478168e-06,
2538
+ "loss": 0.6854,
2539
+ "step": 358
2540
+ },
2541
+ {
2542
+ "epoch": 1.41,
2543
+ "grad_norm": 0.27867368393846137,
2544
+ "learning_rate": 1.9076781169718426e-06,
2545
+ "loss": 0.6892,
2546
+ "step": 359
2547
+ },
2548
+ {
2549
+ "epoch": 1.42,
2550
+ "grad_norm": 0.2747868621778029,
2551
+ "learning_rate": 1.8825509907063328e-06,
2552
+ "loss": 0.6947,
2553
+ "step": 360
2554
+ },
2555
+ {
2556
+ "epoch": 1.42,
2557
+ "grad_norm": 0.2819831023326237,
2558
+ "learning_rate": 1.857552010559382e-06,
2559
+ "loss": 0.7059,
2560
+ "step": 361
2561
+ },
2562
+ {
2563
+ "epoch": 1.42,
2564
+ "grad_norm": 0.27392909848006375,
2565
+ "learning_rate": 1.8326822041411524e-06,
2566
+ "loss": 0.6909,
2567
+ "step": 362
2568
+ },
2569
+ {
2570
+ "epoch": 1.43,
2571
+ "grad_norm": 0.2743865258535757,
2572
+ "learning_rate": 1.8079425937519729e-06,
2573
+ "loss": 0.679,
2574
+ "step": 363
2575
+ },
2576
+ {
2577
+ "epoch": 1.43,
2578
+ "grad_norm": 2.5387012983068686,
2579
+ "learning_rate": 1.7833341963403312e-06,
2580
+ "loss": 0.8855,
2581
+ "step": 364
2582
+ },
2583
+ {
2584
+ "epoch": 1.44,
2585
+ "grad_norm": 0.265533513891752,
2586
+ "learning_rate": 1.7588580234610592e-06,
2587
+ "loss": 0.6915,
2588
+ "step": 365
2589
+ },
2590
+ {
2591
+ "epoch": 1.44,
2592
+ "grad_norm": 0.27359948413194535,
2593
+ "learning_rate": 1.7345150812337564e-06,
2594
+ "loss": 0.6983,
2595
+ "step": 366
2596
+ },
2597
+ {
2598
+ "epoch": 1.44,
2599
+ "grad_norm": 0.2742529435490673,
2600
+ "learning_rate": 1.7103063703014372e-06,
2601
+ "loss": 0.6712,
2602
+ "step": 367
2603
+ },
2604
+ {
2605
+ "epoch": 1.45,
2606
+ "grad_norm": 0.27199602044830407,
2607
+ "learning_rate": 1.6862328857893856e-06,
2608
+ "loss": 0.6929,
2609
+ "step": 368
2610
+ },
2611
+ {
2612
+ "epoch": 1.45,
2613
+ "grad_norm": 0.26752081718353027,
2614
+ "learning_rate": 1.6622956172642601e-06,
2615
+ "loss": 0.6693,
2616
+ "step": 369
2617
+ },
2618
+ {
2619
+ "epoch": 1.46,
2620
+ "grad_norm": 0.2729904749450422,
2621
+ "learning_rate": 1.6384955486934157e-06,
2622
+ "loss": 0.6545,
2623
+ "step": 370
2624
+ },
2625
+ {
2626
+ "epoch": 1.46,
2627
+ "grad_norm": 0.27686659493721505,
2628
+ "learning_rate": 1.6148336584044539e-06,
2629
+ "loss": 0.6957,
2630
+ "step": 371
2631
+ },
2632
+ {
2633
+ "epoch": 1.46,
2634
+ "grad_norm": 0.27203211099316454,
2635
+ "learning_rate": 1.5913109190450033e-06,
2636
+ "loss": 0.6709,
2637
+ "step": 372
2638
+ },
2639
+ {
2640
+ "epoch": 1.47,
2641
+ "grad_norm": 0.2748872025880921,
2642
+ "learning_rate": 1.567928297542749e-06,
2643
+ "loss": 0.6648,
2644
+ "step": 373
2645
+ },
2646
+ {
2647
+ "epoch": 1.47,
2648
+ "grad_norm": 0.28544562477258,
2649
+ "learning_rate": 1.544686755065677e-06,
2650
+ "loss": 0.6937,
2651
+ "step": 374
2652
+ },
2653
+ {
2654
+ "epoch": 1.48,
2655
+ "grad_norm": 0.27110159404128226,
2656
+ "learning_rate": 1.5215872469825682e-06,
2657
+ "loss": 0.6593,
2658
+ "step": 375
2659
+ },
2660
+ {
2661
+ "epoch": 1.48,
2662
+ "eval_loss": 0.6996302008628845,
2663
+ "eval_runtime": 96.9399,
2664
+ "eval_samples_per_second": 18.238,
2665
+ "eval_steps_per_second": 0.382,
2666
+ "step": 375
2667
+ },
2668
+ {
2669
+ "epoch": 1.48,
2670
+ "grad_norm": 0.28648432605335455,
2671
+ "learning_rate": 1.4986307228237268e-06,
2672
+ "loss": 0.6883,
2673
+ "step": 376
2674
+ },
2675
+ {
2676
+ "epoch": 1.48,
2677
+ "grad_norm": 0.2695264027977092,
2678
+ "learning_rate": 1.4758181262419425e-06,
2679
+ "loss": 0.6696,
2680
+ "step": 377
2681
+ },
2682
+ {
2683
+ "epoch": 1.49,
2684
+ "grad_norm": 0.2786040566891135,
2685
+ "learning_rate": 1.4531503949737107e-06,
2686
+ "loss": 0.6768,
2687
+ "step": 378
2688
+ },
2689
+ {
2690
+ "epoch": 1.49,
2691
+ "grad_norm": 0.2730138945863401,
2692
+ "learning_rate": 1.4306284608006837e-06,
2693
+ "loss": 0.699,
2694
+ "step": 379
2695
+ },
2696
+ {
2697
+ "epoch": 1.5,
2698
+ "grad_norm": 0.28711818986138005,
2699
+ "learning_rate": 1.4082532495113627e-06,
2700
+ "loss": 0.6961,
2701
+ "step": 380
2702
+ },
2703
+ {
2704
+ "epoch": 1.5,
2705
+ "grad_norm": 0.27838100192134935,
2706
+ "learning_rate": 1.3860256808630429e-06,
2707
+ "loss": 0.6589,
2708
+ "step": 381
2709
+ },
2710
+ {
2711
+ "epoch": 1.5,
2712
+ "grad_norm": 0.2798399005913698,
2713
+ "learning_rate": 1.3639466685440133e-06,
2714
+ "loss": 0.6924,
2715
+ "step": 382
2716
+ },
2717
+ {
2718
+ "epoch": 1.51,
2719
+ "grad_norm": 0.2801056534585314,
2720
+ "learning_rate": 1.3420171201359933e-06,
2721
+ "loss": 0.7047,
2722
+ "step": 383
2723
+ },
2724
+ {
2725
+ "epoch": 1.51,
2726
+ "grad_norm": 0.28576658015544487,
2727
+ "learning_rate": 1.3202379370768254e-06,
2728
+ "loss": 0.6617,
2729
+ "step": 384
2730
+ },
2731
+ {
2732
+ "epoch": 1.52,
2733
+ "grad_norm": 1.3100321738765892,
2734
+ "learning_rate": 1.298610014623423e-06,
2735
+ "loss": 0.9236,
2736
+ "step": 385
2737
+ },
2738
+ {
2739
+ "epoch": 1.52,
2740
+ "grad_norm": 0.303191205875695,
2741
+ "learning_rate": 1.2771342418149658e-06,
2742
+ "loss": 0.6896,
2743
+ "step": 386
2744
+ },
2745
+ {
2746
+ "epoch": 1.52,
2747
+ "grad_norm": 0.29469211064765755,
2748
+ "learning_rate": 1.2558115014363592e-06,
2749
+ "loss": 0.6804,
2750
+ "step": 387
2751
+ },
2752
+ {
2753
+ "epoch": 1.53,
2754
+ "grad_norm": 0.2772656639598833,
2755
+ "learning_rate": 1.234642669981946e-06,
2756
+ "loss": 0.7043,
2757
+ "step": 388
2758
+ },
2759
+ {
2760
+ "epoch": 1.53,
2761
+ "grad_norm": 0.28874341170670975,
2762
+ "learning_rate": 1.2136286176194744e-06,
2763
+ "loss": 0.6839,
2764
+ "step": 389
2765
+ },
2766
+ {
2767
+ "epoch": 1.54,
2768
+ "grad_norm": 0.29443238526351323,
2769
+ "learning_rate": 1.1927702081543279e-06,
2770
+ "loss": 0.6852,
2771
+ "step": 390
2772
+ },
2773
+ {
2774
+ "epoch": 1.54,
2775
+ "grad_norm": 0.28011985365824127,
2776
+ "learning_rate": 1.1720682989940264e-06,
2777
+ "loss": 0.7019,
2778
+ "step": 391
2779
+ },
2780
+ {
2781
+ "epoch": 1.54,
2782
+ "grad_norm": 0.2987249208096274,
2783
+ "learning_rate": 1.1515237411129698e-06,
2784
+ "loss": 0.6625,
2785
+ "step": 392
2786
+ },
2787
+ {
2788
+ "epoch": 1.55,
2789
+ "grad_norm": 0.30150125882304396,
2790
+ "learning_rate": 1.1311373790174656e-06,
2791
+ "loss": 0.7102,
2792
+ "step": 393
2793
+ },
2794
+ {
2795
+ "epoch": 1.55,
2796
+ "grad_norm": 0.28396138619493894,
2797
+ "learning_rate": 1.1109100507110133e-06,
2798
+ "loss": 0.6538,
2799
+ "step": 394
2800
+ },
2801
+ {
2802
+ "epoch": 1.56,
2803
+ "grad_norm": 0.28445333602874173,
2804
+ "learning_rate": 1.0908425876598512e-06,
2805
+ "loss": 0.6719,
2806
+ "step": 395
2807
+ },
2808
+ {
2809
+ "epoch": 1.56,
2810
+ "grad_norm": 0.2914051878027514,
2811
+ "learning_rate": 1.0709358147587883e-06,
2812
+ "loss": 0.6803,
2813
+ "step": 396
2814
+ },
2815
+ {
2816
+ "epoch": 1.56,
2817
+ "grad_norm": 0.2969873740157493,
2818
+ "learning_rate": 1.0511905502972885e-06,
2819
+ "loss": 0.6845,
2820
+ "step": 397
2821
+ },
2822
+ {
2823
+ "epoch": 1.57,
2824
+ "grad_norm": 0.27955221055069657,
2825
+ "learning_rate": 1.031607605925839e-06,
2826
+ "loss": 0.6819,
2827
+ "step": 398
2828
+ },
2829
+ {
2830
+ "epoch": 1.57,
2831
+ "grad_norm": 0.2840904640426781,
2832
+ "learning_rate": 1.0121877866225783e-06,
2833
+ "loss": 0.6685,
2834
+ "step": 399
2835
+ },
2836
+ {
2837
+ "epoch": 1.58,
2838
+ "grad_norm": 0.2866769315662431,
2839
+ "learning_rate": 9.929318906602176e-07,
2840
+ "loss": 0.7126,
2841
+ "step": 400
2842
+ },
2843
+ {
2844
+ "epoch": 1.58,
2845
+ "grad_norm": 0.28635331619928306,
2846
+ "learning_rate": 9.738407095732195e-07,
2847
+ "loss": 0.6825,
2848
+ "step": 401
2849
+ },
2850
+ {
2851
+ "epoch": 1.58,
2852
+ "grad_norm": 0.29612030431665504,
2853
+ "learning_rate": 9.549150281252633e-07,
2854
+ "loss": 0.6889,
2855
+ "step": 402
2856
+ },
2857
+ {
2858
+ "epoch": 1.59,
2859
+ "grad_norm": 0.2800350134356635,
2860
+ "learning_rate": 9.361556242769871e-07,
2861
+ "loss": 0.6902,
2862
+ "step": 403
2863
+ },
2864
+ {
2865
+ "epoch": 1.59,
2866
+ "grad_norm": 0.303825841465723,
2867
+ "learning_rate": 9.175632691540065e-07,
2868
+ "loss": 0.6949,
2869
+ "step": 404
2870
+ },
2871
+ {
2872
+ "epoch": 1.6,
2873
+ "grad_norm": 0.2869303466691903,
2874
+ "learning_rate": 8.991387270152202e-07,
2875
+ "loss": 0.6953,
2876
+ "step": 405
2877
+ },
2878
+ {
2879
+ "epoch": 1.6,
2880
+ "grad_norm": 0.2822567891211309,
2881
+ "learning_rate": 8.808827552213917e-07,
2882
+ "loss": 0.6733,
2883
+ "step": 406
2884
+ },
2885
+ {
2886
+ "epoch": 1.6,
2887
+ "grad_norm": 0.29613652418881947,
2888
+ "learning_rate": 8.627961042040183e-07,
2889
+ "loss": 0.6721,
2890
+ "step": 407
2891
+ },
2892
+ {
2893
+ "epoch": 1.61,
2894
+ "grad_norm": 0.2904383828418472,
2895
+ "learning_rate": 8.448795174344803e-07,
2896
+ "loss": 0.6849,
2897
+ "step": 408
2898
+ },
2899
+ {
2900
+ "epoch": 1.61,
2901
+ "grad_norm": 0.28422518396116003,
2902
+ "learning_rate": 8.271337313934869e-07,
2903
+ "loss": 0.676,
2904
+ "step": 409
2905
+ },
2906
+ {
2907
+ "epoch": 1.62,
2908
+ "grad_norm": 0.2998884374161429,
2909
+ "learning_rate": 8.095594755407971e-07,
2910
+ "loss": 0.72,
2911
+ "step": 410
2912
+ },
2913
+ {
2914
+ "epoch": 1.62,
2915
+ "grad_norm": 0.2877123964038153,
2916
+ "learning_rate": 7.921574722852343e-07,
2917
+ "loss": 0.686,
2918
+ "step": 411
2919
+ },
2920
+ {
2921
+ "epoch": 1.62,
2922
+ "grad_norm": 0.2848351263069502,
2923
+ "learning_rate": 7.749284369549954e-07,
2924
+ "loss": 0.6755,
2925
+ "step": 412
2926
+ },
2927
+ {
2928
+ "epoch": 1.63,
2929
+ "grad_norm": 3.762805837262192,
2930
+ "learning_rate": 7.578730777682386e-07,
2931
+ "loss": 0.9037,
2932
+ "step": 413
2933
+ },
2934
+ {
2935
+ "epoch": 1.63,
2936
+ "grad_norm": 0.2782769592021476,
2937
+ "learning_rate": 7.409920958039795e-07,
2938
+ "loss": 0.6686,
2939
+ "step": 414
2940
+ },
2941
+ {
2942
+ "epoch": 1.64,
2943
+ "grad_norm": 0.28369386272785363,
2944
+ "learning_rate": 7.242861849732696e-07,
2945
+ "loss": 0.6772,
2946
+ "step": 415
2947
+ },
2948
+ {
2949
+ "epoch": 1.64,
2950
+ "grad_norm": 0.28870985589458403,
2951
+ "learning_rate": 7.077560319906696e-07,
2952
+ "loss": 0.6665,
2953
+ "step": 416
2954
+ },
2955
+ {
2956
+ "epoch": 1.64,
2957
+ "grad_norm": 0.2880267458624612,
2958
+ "learning_rate": 6.914023163460248e-07,
2959
+ "loss": 0.6767,
2960
+ "step": 417
2961
+ },
2962
+ {
2963
+ "epoch": 1.65,
2964
+ "grad_norm": 0.2879073116640725,
2965
+ "learning_rate": 6.752257102765325e-07,
2966
+ "loss": 0.6733,
2967
+ "step": 418
2968
+ },
2969
+ {
2970
+ "epoch": 1.65,
2971
+ "grad_norm": 0.2978223401759706,
2972
+ "learning_rate": 6.592268787391077e-07,
2973
+ "loss": 0.707,
2974
+ "step": 419
2975
+ },
2976
+ {
2977
+ "epoch": 1.66,
2978
+ "grad_norm": 0.2781074725093229,
2979
+ "learning_rate": 6.43406479383053e-07,
2980
+ "loss": 0.6962,
2981
+ "step": 420
2982
+ },
2983
+ {
2984
+ "epoch": 1.66,
2985
+ "grad_norm": 0.29577562012306474,
2986
+ "learning_rate": 6.277651625230219e-07,
2987
+ "loss": 0.6772,
2988
+ "step": 421
2989
+ },
2990
+ {
2991
+ "epoch": 1.66,
2992
+ "grad_norm": 0.2848699679509908,
2993
+ "learning_rate": 6.12303571112286e-07,
2994
+ "loss": 0.7008,
2995
+ "step": 422
2996
+ },
2997
+ {
2998
+ "epoch": 1.67,
2999
+ "grad_norm": 0.2728708533046375,
3000
+ "learning_rate": 5.9702234071631e-07,
3001
+ "loss": 0.6994,
3002
+ "step": 423
3003
+ },
3004
+ {
3005
+ "epoch": 1.67,
3006
+ "grad_norm": 0.2971147397482144,
3007
+ "learning_rate": 5.819220994866237e-07,
3008
+ "loss": 0.6784,
3009
+ "step": 424
3010
+ },
3011
+ {
3012
+ "epoch": 1.67,
3013
+ "grad_norm": 0.2918077307247773,
3014
+ "learning_rate": 5.670034681349995e-07,
3015
+ "loss": 0.6798,
3016
+ "step": 425
3017
+ },
3018
+ {
3019
+ "epoch": 1.68,
3020
+ "grad_norm": 0.2766527969263755,
3021
+ "learning_rate": 5.522670599079416e-07,
3022
+ "loss": 0.692,
3023
+ "step": 426
3024
+ },
3025
+ {
3026
+ "epoch": 1.68,
3027
+ "grad_norm": 0.2896023594106076,
3028
+ "learning_rate": 5.377134805614714e-07,
3029
+ "loss": 0.6885,
3030
+ "step": 427
3031
+ },
3032
+ {
3033
+ "epoch": 1.69,
3034
+ "grad_norm": 0.29226174571780184,
3035
+ "learning_rate": 5.233433283362349e-07,
3036
+ "loss": 0.6609,
3037
+ "step": 428
3038
+ },
3039
+ {
3040
+ "epoch": 1.69,
3041
+ "grad_norm": 0.30313380575685006,
3042
+ "learning_rate": 5.091571939329049e-07,
3043
+ "loss": 0.6559,
3044
+ "step": 429
3045
+ },
3046
+ {
3047
+ "epoch": 1.69,
3048
+ "grad_norm": 0.2851579977806079,
3049
+ "learning_rate": 4.951556604879049e-07,
3050
+ "loss": 0.6862,
3051
+ "step": 430
3052
+ },
3053
+ {
3054
+ "epoch": 1.7,
3055
+ "grad_norm": 0.28828722620682673,
3056
+ "learning_rate": 4.813393035494329e-07,
3057
+ "loss": 0.673,
3058
+ "step": 431
3059
+ },
3060
+ {
3061
+ "epoch": 1.7,
3062
+ "grad_norm": 0.283083619090625,
3063
+ "learning_rate": 4.677086910538092e-07,
3064
+ "loss": 0.6477,
3065
+ "step": 432
3066
+ },
3067
+ {
3068
+ "epoch": 1.71,
3069
+ "grad_norm": 0.29809618255032516,
3070
+ "learning_rate": 4.542643833021254e-07,
3071
+ "loss": 0.7054,
3072
+ "step": 433
3073
+ },
3074
+ {
3075
+ "epoch": 1.71,
3076
+ "grad_norm": 0.3086409841744957,
3077
+ "learning_rate": 4.410069329372152e-07,
3078
+ "loss": 0.6763,
3079
+ "step": 434
3080
+ },
3081
+ {
3082
+ "epoch": 1.71,
3083
+ "grad_norm": 0.3016981542599131,
3084
+ "learning_rate": 4.279368849209381e-07,
3085
+ "loss": 0.6843,
3086
+ "step": 435
3087
+ },
3088
+ {
3089
+ "epoch": 1.72,
3090
+ "grad_norm": 0.27698126686942587,
3091
+ "learning_rate": 4.150547765117746e-07,
3092
+ "loss": 0.6891,
3093
+ "step": 436
3094
+ },
3095
+ {
3096
+ "epoch": 1.72,
3097
+ "grad_norm": 0.2793586730481018,
3098
+ "learning_rate": 4.0236113724274716e-07,
3099
+ "loss": 0.6796,
3100
+ "step": 437
3101
+ },
3102
+ {
3103
+ "epoch": 1.73,
3104
+ "grad_norm": 0.28666974827878056,
3105
+ "learning_rate": 3.8985648889964755e-07,
3106
+ "loss": 0.6648,
3107
+ "step": 438
3108
+ },
3109
+ {
3110
+ "epoch": 1.73,
3111
+ "grad_norm": 0.28527293041641727,
3112
+ "learning_rate": 3.77541345499593e-07,
3113
+ "loss": 0.7071,
3114
+ "step": 439
3115
+ },
3116
+ {
3117
+ "epoch": 1.73,
3118
+ "grad_norm": 0.29843069047155474,
3119
+ "learning_rate": 3.6541621326989183e-07,
3120
+ "loss": 0.6803,
3121
+ "step": 440
3122
+ },
3123
+ {
3124
+ "epoch": 1.74,
3125
+ "grad_norm": 0.3001228333782996,
3126
+ "learning_rate": 3.534815906272404e-07,
3127
+ "loss": 0.7176,
3128
+ "step": 441
3129
+ },
3130
+ {
3131
+ "epoch": 1.74,
3132
+ "grad_norm": 0.2928174202718284,
3133
+ "learning_rate": 3.417379681572297e-07,
3134
+ "loss": 0.6747,
3135
+ "step": 442
3136
+ },
3137
+ {
3138
+ "epoch": 1.75,
3139
+ "grad_norm": 0.2951128501223636,
3140
+ "learning_rate": 3.301858285941845e-07,
3141
+ "loss": 0.7046,
3142
+ "step": 443
3143
+ },
3144
+ {
3145
+ "epoch": 1.75,
3146
+ "grad_norm": 0.2931876464433515,
3147
+ "learning_rate": 3.18825646801314e-07,
3148
+ "loss": 0.6734,
3149
+ "step": 444
3150
+ },
3151
+ {
3152
+ "epoch": 1.75,
3153
+ "grad_norm": 0.29349560436630445,
3154
+ "learning_rate": 3.076578897511978e-07,
3155
+ "loss": 0.6852,
3156
+ "step": 445
3157
+ },
3158
+ {
3159
+ "epoch": 1.76,
3160
+ "grad_norm": 0.7457047514934827,
3161
+ "learning_rate": 2.966830165065876e-07,
3162
+ "loss": 0.9017,
3163
+ "step": 446
3164
+ },
3165
+ {
3166
+ "epoch": 1.76,
3167
+ "grad_norm": 0.2813462622367945,
3168
+ "learning_rate": 2.8590147820153513e-07,
3169
+ "loss": 0.6969,
3170
+ "step": 447
3171
+ },
3172
+ {
3173
+ "epoch": 1.77,
3174
+ "grad_norm": 0.30904433658187347,
3175
+ "learning_rate": 2.7531371802285436e-07,
3176
+ "loss": 0.6829,
3177
+ "step": 448
3178
+ },
3179
+ {
3180
+ "epoch": 1.77,
3181
+ "grad_norm": 0.28837856935691286,
3182
+ "learning_rate": 2.6492017119189415e-07,
3183
+ "loss": 0.6527,
3184
+ "step": 449
3185
+ },
3186
+ {
3187
+ "epoch": 1.77,
3188
+ "grad_norm": 0.2940858357017207,
3189
+ "learning_rate": 2.547212649466568e-07,
3190
+ "loss": 0.6696,
3191
+ "step": 450
3192
+ },
3193
+ {
3194
+ "epoch": 1.78,
3195
+ "grad_norm": 0.27956534271888384,
3196
+ "learning_rate": 2.447174185242324e-07,
3197
+ "loss": 0.7048,
3198
+ "step": 451
3199
+ },
3200
+ {
3201
+ "epoch": 1.78,
3202
+ "grad_norm": 0.28259810422391984,
3203
+ "learning_rate": 2.3490904314356412e-07,
3204
+ "loss": 0.6772,
3205
+ "step": 452
3206
+ },
3207
+ {
3208
+ "epoch": 1.79,
3209
+ "grad_norm": 0.2846763408984384,
3210
+ "learning_rate": 2.2529654198854834e-07,
3211
+ "loss": 0.7507,
3212
+ "step": 453
3213
+ },
3214
+ {
3215
+ "epoch": 1.79,
3216
+ "grad_norm": 0.2784656918785677,
3217
+ "learning_rate": 2.1588031019145638e-07,
3218
+ "loss": 0.7072,
3219
+ "step": 454
3220
+ },
3221
+ {
3222
+ "epoch": 1.79,
3223
+ "grad_norm": 0.28593045031546543,
3224
+ "learning_rate": 2.0666073481669714e-07,
3225
+ "loss": 0.6944,
3226
+ "step": 455
3227
+ },
3228
+ {
3229
+ "epoch": 1.8,
3230
+ "grad_norm": 0.296176705173677,
3231
+ "learning_rate": 1.9763819484490353e-07,
3232
+ "loss": 0.6691,
3233
+ "step": 456
3234
+ },
3235
+ {
3236
+ "epoch": 1.8,
3237
+ "grad_norm": 0.2923471158891105,
3238
+ "learning_rate": 1.8881306115735632e-07,
3239
+ "loss": 0.705,
3240
+ "step": 457
3241
+ },
3242
+ {
3243
+ "epoch": 1.81,
3244
+ "grad_norm": 0.2769134760770555,
3245
+ "learning_rate": 1.801856965207338e-07,
3246
+ "loss": 0.6845,
3247
+ "step": 458
3248
+ },
3249
+ {
3250
+ "epoch": 1.81,
3251
+ "grad_norm": 0.30153347516541434,
3252
+ "learning_rate": 1.7175645557220567e-07,
3253
+ "loss": 0.6935,
3254
+ "step": 459
3255
+ },
3256
+ {
3257
+ "epoch": 1.81,
3258
+ "grad_norm": 0.29938078931561396,
3259
+ "learning_rate": 1.6352568480485277e-07,
3260
+ "loss": 0.6822,
3261
+ "step": 460
3262
+ },
3263
+ {
3264
+ "epoch": 1.82,
3265
+ "grad_norm": 0.2909845977727433,
3266
+ "learning_rate": 1.5549372255342367e-07,
3267
+ "loss": 0.6959,
3268
+ "step": 461
3269
+ },
3270
+ {
3271
+ "epoch": 1.82,
3272
+ "grad_norm": 0.2851155920589762,
3273
+ "learning_rate": 1.4766089898042678e-07,
3274
+ "loss": 0.6909,
3275
+ "step": 462
3276
+ },
3277
+ {
3278
+ "epoch": 1.83,
3279
+ "grad_norm": 3.590844633307425,
3280
+ "learning_rate": 1.4002753606256082e-07,
3281
+ "loss": 0.9279,
3282
+ "step": 463
3283
+ },
3284
+ {
3285
+ "epoch": 1.83,
3286
+ "grad_norm": 0.289769942223222,
3287
+ "learning_rate": 1.3259394757747678e-07,
3288
+ "loss": 0.6664,
3289
+ "step": 464
3290
+ },
3291
+ {
3292
+ "epoch": 1.83,
3293
+ "grad_norm": 1.4756345980091514,
3294
+ "learning_rate": 1.253604390908819e-07,
3295
+ "loss": 0.9066,
3296
+ "step": 465
3297
+ },
3298
+ {
3299
+ "epoch": 1.84,
3300
+ "grad_norm": 0.2905542054012534,
3301
+ "learning_rate": 1.1832730794397951e-07,
3302
+ "loss": 0.6989,
3303
+ "step": 466
3304
+ },
3305
+ {
3306
+ "epoch": 1.84,
3307
+ "grad_norm": 0.3056790622208962,
3308
+ "learning_rate": 1.1149484324124326e-07,
3309
+ "loss": 0.64,
3310
+ "step": 467
3311
+ },
3312
+ {
3313
+ "epoch": 1.85,
3314
+ "grad_norm": 0.2915224050071343,
3315
+ "learning_rate": 1.0486332583853565e-07,
3316
+ "loss": 0.6411,
3317
+ "step": 468
3318
+ },
3319
+ {
3320
+ "epoch": 1.85,
3321
+ "grad_norm": 0.2947477867782055,
3322
+ "learning_rate": 9.843302833156377e-08,
3323
+ "loss": 0.6901,
3324
+ "step": 469
3325
+ },
3326
+ {
3327
+ "epoch": 1.85,
3328
+ "grad_norm": 0.6968434274277037,
3329
+ "learning_rate": 9.22042150446728e-08,
3330
+ "loss": 0.9234,
3331
+ "step": 470
3332
+ },
3333
+ {
3334
+ "epoch": 1.86,
3335
+ "grad_norm": 0.28365980605268926,
3336
+ "learning_rate": 8.617714201998084e-08,
3337
+ "loss": 0.6871,
3338
+ "step": 471
3339
+ },
3340
+ {
3341
+ "epoch": 1.86,
3342
+ "grad_norm": 0.29456041125148436,
3343
+ "learning_rate": 8.035205700685167e-08,
3344
+ "loss": 0.6841,
3345
+ "step": 472
3346
+ },
3347
+ {
3348
+ "epoch": 1.87,
3349
+ "grad_norm": 0.3143240746562965,
3350
+ "learning_rate": 7.47291994517163e-08,
3351
+ "loss": 0.6793,
3352
+ "step": 473
3353
+ },
3354
+ {
3355
+ "epoch": 1.87,
3356
+ "grad_norm": 0.3002190997085016,
3357
+ "learning_rate": 6.930880048822531e-08,
3358
+ "loss": 0.6909,
3359
+ "step": 474
3360
+ },
3361
+ {
3362
+ "epoch": 1.87,
3363
+ "grad_norm": 0.28198233683666907,
3364
+ "learning_rate": 6.409108292774912e-08,
3365
+ "loss": 0.6677,
3366
+ "step": 475
3367
+ },
3368
+ {
3369
+ "epoch": 1.88,
3370
+ "grad_norm": 0.2974351663902672,
3371
+ "learning_rate": 5.907626125022159e-08,
3372
+ "loss": 0.6863,
3373
+ "step": 476
3374
+ },
3375
+ {
3376
+ "epoch": 1.88,
3377
+ "grad_norm": 0.3167342201027022,
3378
+ "learning_rate": 5.426454159531913e-08,
3379
+ "loss": 0.6728,
3380
+ "step": 477
3381
+ },
3382
+ {
3383
+ "epoch": 1.89,
3384
+ "grad_norm": 0.2838121481556639,
3385
+ "learning_rate": 4.9656121753990924e-08,
3386
+ "loss": 0.6765,
3387
+ "step": 478
3388
+ },
3389
+ {
3390
+ "epoch": 1.89,
3391
+ "grad_norm": 0.28117138518414553,
3392
+ "learning_rate": 4.52511911603265e-08,
3393
+ "loss": 0.6827,
3394
+ "step": 479
3395
+ },
3396
+ {
3397
+ "epoch": 1.89,
3398
+ "grad_norm": 0.29399576903346636,
3399
+ "learning_rate": 4.104993088376974e-08,
3400
+ "loss": 0.6933,
3401
+ "step": 480
3402
+ },
3403
+ {
3404
+ "epoch": 1.9,
3405
+ "grad_norm": 0.29636385882946953,
3406
+ "learning_rate": 3.705251362167484e-08,
3407
+ "loss": 0.6641,
3408
+ "step": 481
3409
+ },
3410
+ {
3411
+ "epoch": 1.9,
3412
+ "grad_norm": 0.2913085312105263,
3413
+ "learning_rate": 3.325910369220975e-08,
3414
+ "loss": 0.6973,
3415
+ "step": 482
3416
+ },
3417
+ {
3418
+ "epoch": 1.91,
3419
+ "grad_norm": 0.29080057862930364,
3420
+ "learning_rate": 2.966985702759828e-08,
3421
+ "loss": 0.6678,
3422
+ "step": 483
3423
+ },
3424
+ {
3425
+ "epoch": 1.91,
3426
+ "grad_norm": 0.2952306166117519,
3427
+ "learning_rate": 2.6284921167712975e-08,
3428
+ "loss": 0.7017,
3429
+ "step": 484
3430
+ },
3431
+ {
3432
+ "epoch": 1.91,
3433
+ "grad_norm": 0.2959396595629797,
3434
+ "learning_rate": 2.3104435254008852e-08,
3435
+ "loss": 0.6569,
3436
+ "step": 485
3437
+ },
3438
+ {
3439
+ "epoch": 1.92,
3440
+ "grad_norm": 0.28791733733513286,
3441
+ "learning_rate": 2.012853002380466e-08,
3442
+ "loss": 0.6573,
3443
+ "step": 486
3444
+ },
3445
+ {
3446
+ "epoch": 1.92,
3447
+ "grad_norm": 0.2923526176448832,
3448
+ "learning_rate": 1.735732780490884e-08,
3449
+ "loss": 0.6903,
3450
+ "step": 487
3451
+ },
3452
+ {
3453
+ "epoch": 1.93,
3454
+ "grad_norm": 0.2908268098513957,
3455
+ "learning_rate": 1.4790942510590767e-08,
3456
+ "loss": 0.6756,
3457
+ "step": 488
3458
+ },
3459
+ {
3460
+ "epoch": 1.93,
3461
+ "grad_norm": 0.29069043095745606,
3462
+ "learning_rate": 1.2429479634897268e-08,
3463
+ "loss": 0.6722,
3464
+ "step": 489
3465
+ },
3466
+ {
3467
+ "epoch": 1.93,
3468
+ "grad_norm": 0.28912174671892155,
3469
+ "learning_rate": 1.0273036248318325e-08,
3470
+ "loss": 0.6927,
3471
+ "step": 490
3472
+ },
3473
+ {
3474
+ "epoch": 1.94,
3475
+ "grad_norm": 0.29773909318477504,
3476
+ "learning_rate": 8.321700993795812e-09,
3477
+ "loss": 0.6703,
3478
+ "step": 491
3479
+ },
3480
+ {
3481
+ "epoch": 1.94,
3482
+ "grad_norm": 0.2846360921300275,
3483
+ "learning_rate": 6.575554083078084e-09,
3484
+ "loss": 0.6915,
3485
+ "step": 492
3486
+ },
3487
+ {
3488
+ "epoch": 1.95,
3489
+ "grad_norm": 0.3040183654289367,
3490
+ "learning_rate": 5.034667293427053e-09,
3491
+ "loss": 0.6836,
3492
+ "step": 493
3493
+ },
3494
+ {
3495
+ "epoch": 1.95,
3496
+ "grad_norm": 0.29012455377167307,
3497
+ "learning_rate": 3.6991039646616657e-09,
3498
+ "loss": 0.6844,
3499
+ "step": 494
3500
+ },
3501
+ {
3502
+ "epoch": 1.95,
3503
+ "grad_norm": 0.2778518633390048,
3504
+ "learning_rate": 2.568918996560532e-09,
3505
+ "loss": 0.6779,
3506
+ "step": 495
3507
+ },
3508
+ {
3509
+ "epoch": 1.96,
3510
+ "grad_norm": 0.29541155663074187,
3511
+ "learning_rate": 1.6441588466009627e-09,
3512
+ "loss": 0.6979,
3513
+ "step": 496
3514
+ },
3515
+ {
3516
+ "epoch": 1.96,
3517
+ "grad_norm": 0.28364315270086676,
3518
+ "learning_rate": 9.248615280499362e-10,
3519
+ "loss": 0.6792,
3520
+ "step": 497
3521
+ },
3522
+ {
3523
+ "epoch": 1.97,
3524
+ "grad_norm": 0.2865142006406564,
3525
+ "learning_rate": 4.1105660840368154e-10,
3526
+ "loss": 0.7034,
3527
+ "step": 498
3528
+ },
3529
+ {
3530
+ "epoch": 1.97,
3531
+ "grad_norm": 0.2854424675916699,
3532
+ "learning_rate": 1.0276520816976388e-10,
3533
+ "loss": 0.6747,
3534
+ "step": 499
3535
+ },
3536
+ {
3537
+ "epoch": 1.97,
3538
+ "grad_norm": 0.29666466368391803,
3539
+ "learning_rate": 0.0,
3540
+ "loss": 0.6754,
3541
+ "step": 500
3542
+ },
3543
+ {
3544
+ "epoch": 1.97,
3545
+ "eval_loss": 0.6983408331871033,
3546
+ "eval_runtime": 93.907,
3547
+ "eval_samples_per_second": 18.827,
3548
+ "eval_steps_per_second": 0.394,
3549
+ "step": 500
3550
+ }
3551
+ ],
3552
+ "logging_steps": 1,
3553
+ "max_steps": 500,
3554
+ "num_input_tokens_seen": 0,
3555
+ "num_train_epochs": 2,
3556
+ "save_steps": 250,
3557
+ "total_flos": 1571976955035648.0,
3558
+ "train_batch_size": 6,
3559
+ "trial_name": null,
3560
+ "trial_params": null
3561
+ }