zodiache commited on
Commit
a16a66f
1 Parent(s): cbd3d82

Training in progress, step 10

Browse files
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-1.1-7b-it",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:345109096ca3a119ccdd388ed3dd11a0e64cfc06eb07e08784503527b26a7e1d
3
- size 2115012328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3fe0efe4f3d65c05bc61d16e3f3d48c2385263000c7733cb15118b2281eaa9b
3
+ size 12860096
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
  "epoch": 0.33,
3
- "eval_loss": 1.6449463367462158,
4
- "eval_runtime": 125.933,
5
- "eval_samples_per_second": 39.704,
6
- "eval_steps_per_second": 1.247,
7
- "train_loss": 1.7538025458343327,
8
- "train_runtime": 4604.2872,
9
- "train_samples_per_second": 3.558,
10
- "train_steps_per_second": 0.056
11
  }
 
1
  {
2
  "epoch": 0.33,
3
+ "eval_loss": 1.810941219329834,
4
+ "eval_runtime": 125.8181,
5
+ "eval_samples_per_second": 39.74,
6
+ "eval_steps_per_second": 1.248,
7
+ "train_loss": 2.2480679317377508,
8
+ "train_runtime": 4476.2307,
9
+ "train_samples_per_second": 3.66,
10
+ "train_steps_per_second": 0.057
11
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 0.33,
3
- "eval_loss": 1.6449463367462158,
4
- "eval_runtime": 125.933,
5
- "eval_samples_per_second": 39.704,
6
- "eval_steps_per_second": 1.247
7
  }
 
1
  {
2
  "epoch": 0.33,
3
+ "eval_loss": 1.810941219329834,
4
+ "eval_runtime": 125.8181,
5
+ "eval_samples_per_second": 39.74,
6
+ "eval_steps_per_second": 1.248
7
  }
special_tokens_map.json CHANGED
@@ -1,20 +1,31 @@
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": "<|eot_id|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "[PAD]",
 
 
 
 
 
 
 
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
  "bos_token": {
7
+ "content": "<bos>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
  "eos_token": {
14
+ "content": "<eos>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
  "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e44b5b81b4f8412ac309f8ee86e7765eb07066640e748c2b2c072aae3068651
3
- size 9085952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b157dea6218d105fc8bac45868ae969d2433430e1b63ff2c814747cfc04418
3
+ size 17518596
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json CHANGED
@@ -1,2071 +1,1757 @@
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": "[PAD]",
2053
- "lstrip": false,
2054
- "normalized": false,
2055
- "rstrip": false,
2056
- "single_word": false,
2057
- "special": true
2058
  }
2059
  },
2060
- "bos_token": "<|begin_of_text|>",
2061
- "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2062
- "clean_up_tokenization_spaces": true,
2063
- "eos_token": "<|eot_id|>",
2064
- "model_input_names": [
2065
- "input_ids",
2066
- "attention_mask"
2067
  ],
 
 
 
 
2068
  "model_max_length": 1000000000000000019884624838656,
2069
- "pad_token": "[PAD]",
2070
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
2071
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
+ "1": {
14
+ "content": "<eos>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
+ "2": {
22
+ "content": "<bos>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "3": {
30
+ "content": "<unk>",
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "4": {
38
+ "content": "<mask>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
+ "special": false
44
  },
45
+ "5": {
46
+ "content": "<2mass>",
47
  "lstrip": false,
48
  "normalized": false,
49
  "rstrip": false,
50
  "single_word": false,
51
+ "special": false
52
  },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
  "lstrip": false,
56
  "normalized": false,
57
  "rstrip": false,
58
  "single_word": false,
59
+ "special": false
60
  },
61
+ "7": {
62
+ "content": "<unused0>",
63
  "lstrip": false,
64
  "normalized": false,
65
  "rstrip": false,
66
  "single_word": false,
67
+ "special": false
68
  },
69
+ "8": {
70
+ "content": "<unused1>",
71
  "lstrip": false,
72
  "normalized": false,
73
  "rstrip": false,
74
  "single_word": false,
75
+ "special": false
76
  },
77
+ "9": {
78
+ "content": "<unused2>",
79
  "lstrip": false,
80
  "normalized": false,
81
  "rstrip": false,
82
  "single_word": false,
83
+ "special": false
84
  },
85
+ "10": {
86
+ "content": "<unused3>",
87
  "lstrip": false,
88
  "normalized": false,
89
  "rstrip": false,
90
  "single_word": false,
91
+ "special": false
92
  },
93
+ "11": {
94
+ "content": "<unused4>",
95
  "lstrip": false,
96
  "normalized": false,
97
  "rstrip": false,
98
  "single_word": false,
99
+ "special": false
100
  },
101
+ "12": {
102
+ "content": "<unused5>",
103
  "lstrip": false,
104
  "normalized": false,
105
  "rstrip": false,
106
  "single_word": false,
107
+ "special": false
108
  },
109
+ "13": {
110
+ "content": "<unused6>",
111
  "lstrip": false,
112
  "normalized": false,
113
  "rstrip": false,
114
  "single_word": false,
115
+ "special": false
116
  },
117
+ "14": {
118
+ "content": "<unused7>",
119
  "lstrip": false,
120
  "normalized": false,
121
  "rstrip": false,
122
  "single_word": false,
123
+ "special": false
124
  },
125
+ "15": {
126
+ "content": "<unused8>",
127
  "lstrip": false,
128
  "normalized": false,
129
  "rstrip": false,
130
  "single_word": false,
131
+ "special": false
132
  },
133
+ "16": {
134
+ "content": "<unused9>",
135
  "lstrip": false,
136
  "normalized": false,
137
  "rstrip": false,
138
  "single_word": false,
139
+ "special": false
140
  },
141
+ "17": {
142
+ "content": "<unused10>",
143
  "lstrip": false,
144
  "normalized": false,
145
  "rstrip": false,
146
  "single_word": false,
147
+ "special": false
148
  },
149
+ "18": {
150
+ "content": "<unused11>",
151
  "lstrip": false,
152
  "normalized": false,
153
  "rstrip": false,
154
  "single_word": false,
155
+ "special": false
156
  },
157
+ "19": {
158
+ "content": "<unused12>",
159
  "lstrip": false,
160
  "normalized": false,
161
  "rstrip": false,
162
  "single_word": false,
163
+ "special": false
164
  },
165
+ "20": {
166
+ "content": "<unused13>",
167
  "lstrip": false,
168
  "normalized": false,
169
  "rstrip": false,
170
  "single_word": false,
171
+ "special": false
172
  },
173
+ "21": {
174
+ "content": "<unused14>",
175
  "lstrip": false,
176
  "normalized": false,
177
  "rstrip": false,
178
  "single_word": false,
179
+ "special": false
180
  },
181
+ "22": {
182
+ "content": "<unused15>",
183
  "lstrip": false,
184
  "normalized": false,
185
  "rstrip": false,
186
  "single_word": false,
187
+ "special": false
188
  },
189
+ "23": {
190
+ "content": "<unused16>",
191
  "lstrip": false,
192
  "normalized": false,
193
  "rstrip": false,
194
  "single_word": false,
195
+ "special": false
196
  },
197
+ "24": {
198
+ "content": "<unused17>",
199
  "lstrip": false,
200
  "normalized": false,
201
  "rstrip": false,
202
  "single_word": false,
203
+ "special": false
204
  },
205
+ "25": {
206
+ "content": "<unused18>",
207
  "lstrip": false,
208
  "normalized": false,
209
  "rstrip": false,
210
  "single_word": false,
211
+ "special": false
212
  },
213
+ "26": {
214
+ "content": "<unused19>",
215
  "lstrip": false,
216
  "normalized": false,
217
  "rstrip": false,
218
  "single_word": false,
219
+ "special": false
220
  },
221
+ "27": {
222
+ "content": "<unused20>",
223
  "lstrip": false,
224
  "normalized": false,
225
  "rstrip": false,
226
  "single_word": false,
227
+ "special": false
228
  },
229
+ "28": {
230
+ "content": "<unused21>",
231
  "lstrip": false,
232
  "normalized": false,
233
  "rstrip": false,
234
  "single_word": false,
235
+ "special": false
236
  },
237
+ "29": {
238
+ "content": "<unused22>",
239
  "lstrip": false,
240
  "normalized": false,
241
  "rstrip": false,
242
  "single_word": false,
243
+ "special": false
244
  },
245
+ "30": {
246
+ "content": "<unused23>",
247
  "lstrip": false,
248
  "normalized": false,
249
  "rstrip": false,
250
  "single_word": false,
251
+ "special": false
252
  },
253
+ "31": {
254
+ "content": "<unused24>",
255
  "lstrip": false,
256
  "normalized": false,
257
  "rstrip": false,
258
  "single_word": false,
259
+ "special": false
260
  },
261
+ "32": {
262
+ "content": "<unused25>",
263
  "lstrip": false,
264
  "normalized": false,
265
  "rstrip": false,
266
  "single_word": false,
267
+ "special": false
268
  },
269
+ "33": {
270
+ "content": "<unused26>",
271
  "lstrip": false,
272
  "normalized": false,
273
  "rstrip": false,
274
  "single_word": false,
275
+ "special": false
276
  },
277
+ "34": {
278
+ "content": "<unused27>",
279
  "lstrip": false,
280
  "normalized": false,
281
  "rstrip": false,
282
  "single_word": false,
283
+ "special": false
284
  },
285
+ "35": {
286
+ "content": "<unused28>",
287
  "lstrip": false,
288
  "normalized": false,
289
  "rstrip": false,
290
  "single_word": false,
291
+ "special": false
292
  },
293
+ "36": {
294
+ "content": "<unused29>",
295
  "lstrip": false,
296
  "normalized": false,
297
  "rstrip": false,
298
  "single_word": false,
299
+ "special": false
300
  },
301
+ "37": {
302
+ "content": "<unused30>",
303
  "lstrip": false,
304
  "normalized": false,
305
  "rstrip": false,
306
  "single_word": false,
307
+ "special": false
308
  },
309
+ "38": {
310
+ "content": "<unused31>",
311
  "lstrip": false,
312
  "normalized": false,
313
  "rstrip": false,
314
  "single_word": false,
315
+ "special": false
316
  },
317
+ "39": {
318
+ "content": "<unused32>",
319
  "lstrip": false,
320
  "normalized": false,
321
  "rstrip": false,
322
  "single_word": false,
323
+ "special": false
324
  },
325
+ "40": {
326
+ "content": "<unused33>",
327
  "lstrip": false,
328
  "normalized": false,
329
  "rstrip": false,
330
  "single_word": false,
331
+ "special": false
332
  },
333
+ "41": {
334
+ "content": "<unused34>",
335
  "lstrip": false,
336
  "normalized": false,
337
  "rstrip": false,
338
  "single_word": false,
339
+ "special": false
340
  },
341
+ "42": {
342
+ "content": "<unused35>",
343
  "lstrip": false,
344
  "normalized": false,
345
  "rstrip": false,
346
  "single_word": false,
347
+ "special": false
348
  },
349
+ "43": {
350
+ "content": "<unused36>",
351
  "lstrip": false,
352
  "normalized": false,
353
  "rstrip": false,
354
  "single_word": false,
355
+ "special": false
356
  },
357
+ "44": {
358
+ "content": "<unused37>",
359
  "lstrip": false,
360
  "normalized": false,
361
  "rstrip": false,
362
  "single_word": false,
363
+ "special": false
364
  },
365
+ "45": {
366
+ "content": "<unused38>",
367
  "lstrip": false,
368
  "normalized": false,
369
  "rstrip": false,
370
  "single_word": false,
371
+ "special": false
372
  },
373
+ "46": {
374
+ "content": "<unused39>",
375
  "lstrip": false,
376
  "normalized": false,
377
  "rstrip": false,
378
  "single_word": false,
379
+ "special": false
380
  },
381
+ "47": {
382
+ "content": "<unused40>",
383
  "lstrip": false,
384
  "normalized": false,
385
  "rstrip": false,
386
  "single_word": false,
387
+ "special": false
388
  },
389
+ "48": {
390
+ "content": "<unused41>",
391
  "lstrip": false,
392
  "normalized": false,
393
  "rstrip": false,
394
  "single_word": false,
395
+ "special": false
396
  },
397
+ "49": {
398
+ "content": "<unused42>",
399
  "lstrip": false,
400
  "normalized": false,
401
  "rstrip": false,
402
  "single_word": false,
403
+ "special": false
404
  },
405
+ "50": {
406
+ "content": "<unused43>",
407
  "lstrip": false,
408
  "normalized": false,
409
  "rstrip": false,
410
  "single_word": false,
411
+ "special": false
412
  },
413
+ "51": {
414
+ "content": "<unused44>",
415
  "lstrip": false,
416
  "normalized": false,
417
  "rstrip": false,
418
  "single_word": false,
419
+ "special": false
420
  },
421
+ "52": {
422
+ "content": "<unused45>",
423
  "lstrip": false,
424
  "normalized": false,
425
  "rstrip": false,
426
  "single_word": false,
427
+ "special": false
428
  },
429
+ "53": {
430
+ "content": "<unused46>",
431
  "lstrip": false,
432
  "normalized": false,
433
  "rstrip": false,
434
  "single_word": false,
435
+ "special": false
436
  },
437
+ "54": {
438
+ "content": "<unused47>",
439
  "lstrip": false,
440
  "normalized": false,
441
  "rstrip": false,
442
  "single_word": false,
443
+ "special": false
444
  },
445
+ "55": {
446
+ "content": "<unused48>",
447
  "lstrip": false,
448
  "normalized": false,
449
  "rstrip": false,
450
  "single_word": false,
451
+ "special": false
452
  },
453
+ "56": {
454
+ "content": "<unused49>",
455
  "lstrip": false,
456
  "normalized": false,
457
  "rstrip": false,
458
  "single_word": false,
459
+ "special": false
460
  },
461
+ "57": {
462
+ "content": "<unused50>",
463
  "lstrip": false,
464
  "normalized": false,
465
  "rstrip": false,
466
  "single_word": false,
467
+ "special": false
468
  },
469
+ "58": {
470
+ "content": "<unused51>",
471
  "lstrip": false,
472
  "normalized": false,
473
  "rstrip": false,
474
  "single_word": false,
475
+ "special": false
476
  },
477
+ "59": {
478
+ "content": "<unused52>",
479
  "lstrip": false,
480
  "normalized": false,
481
  "rstrip": false,
482
  "single_word": false,
483
+ "special": false
484
  },
485
+ "60": {
486
+ "content": "<unused53>",
487
  "lstrip": false,
488
  "normalized": false,
489
  "rstrip": false,
490
  "single_word": false,
491
+ "special": false
492
  },
493
+ "61": {
494
+ "content": "<unused54>",
495
  "lstrip": false,
496
  "normalized": false,
497
  "rstrip": false,
498
  "single_word": false,
499
+ "special": false
 
 
 
 
 
 
 
 
500
  },
501
+ "62": {
502
+ "content": "<unused55>",
503
  "lstrip": false,
504
  "normalized": false,
505
  "rstrip": false,
506
  "single_word": false,
507
+ "special": false
 
 
 
 
 
 
 
 
508
  },
509
+ "63": {
510
+ "content": "<unused56>",
511
  "lstrip": false,
512
  "normalized": false,
513
  "rstrip": false,
514
  "single_word": false,
515
+ "special": false
516
  },
517
+ "64": {
518
+ "content": "<unused57>",
519
  "lstrip": false,
520
  "normalized": false,
521
  "rstrip": false,
522
  "single_word": false,
523
+ "special": false
524
  },
525
+ "65": {
526
+ "content": "<unused58>",
527
  "lstrip": false,
528
  "normalized": false,
529
  "rstrip": false,
530
  "single_word": false,
531
+ "special": false
532
  },
533
+ "66": {
534
+ "content": "<unused59>",
535
  "lstrip": false,
536
  "normalized": false,
537
  "rstrip": false,
538
  "single_word": false,
539
+ "special": false
540
  },
541
+ "67": {
542
+ "content": "<unused60>",
543
  "lstrip": false,
544
  "normalized": false,
545
  "rstrip": false,
546
  "single_word": false,
547
+ "special": false
548
  },
549
+ "68": {
550
+ "content": "<unused61>",
551
  "lstrip": false,
552
  "normalized": false,
553
  "rstrip": false,
554
  "single_word": false,
555
+ "special": false
556
  },
557
+ "69": {
558
+ "content": "<unused62>",
559
  "lstrip": false,
560
  "normalized": false,
561
  "rstrip": false,
562
  "single_word": false,
563
+ "special": false
564
  },
565
+ "70": {
566
+ "content": "<unused63>",
567
  "lstrip": false,
568
  "normalized": false,
569
  "rstrip": false,
570
  "single_word": false,
571
+ "special": false
572
  },
573
+ "71": {
574
+ "content": "<unused64>",
575
  "lstrip": false,
576
  "normalized": false,
577
  "rstrip": false,
578
  "single_word": false,
579
+ "special": false
580
  },
581
+ "72": {
582
+ "content": "<unused65>",
583
  "lstrip": false,
584
  "normalized": false,
585
  "rstrip": false,
586
  "single_word": false,
587
+ "special": false
588
  },
589
+ "73": {
590
+ "content": "<unused66>",
591
  "lstrip": false,
592
  "normalized": false,
593
  "rstrip": false,
594
  "single_word": false,
595
+ "special": false
596
  },
597
+ "74": {
598
+ "content": "<unused67>",
599
  "lstrip": false,
600
  "normalized": false,
601
  "rstrip": false,
602
  "single_word": false,
603
+ "special": false
604
  },
605
+ "75": {
606
+ "content": "<unused68>",
607
  "lstrip": false,
608
  "normalized": false,
609
  "rstrip": false,
610
  "single_word": false,
611
+ "special": false
612
  },
613
+ "76": {
614
+ "content": "<unused69>",
615
  "lstrip": false,
616
  "normalized": false,
617
  "rstrip": false,
618
  "single_word": false,
619
+ "special": false
620
  },
621
+ "77": {
622
+ "content": "<unused70>",
623
  "lstrip": false,
624
  "normalized": false,
625
  "rstrip": false,
626
  "single_word": false,
627
+ "special": false
628
  },
629
+ "78": {
630
+ "content": "<unused71>",
631
  "lstrip": false,
632
  "normalized": false,
633
  "rstrip": false,
634
  "single_word": false,
635
+ "special": false
636
  },
637
+ "79": {
638
+ "content": "<unused72>",
639
  "lstrip": false,
640
  "normalized": false,
641
  "rstrip": false,
642
  "single_word": false,
643
+ "special": false
644
  },
645
+ "80": {
646
+ "content": "<unused73>",
647
  "lstrip": false,
648
  "normalized": false,
649
  "rstrip": false,
650
  "single_word": false,
651
+ "special": false
652
  },
653
+ "81": {
654
+ "content": "<unused74>",
655
  "lstrip": false,
656
  "normalized": false,
657
  "rstrip": false,
658
  "single_word": false,
659
+ "special": false
660
  },
661
+ "82": {
662
+ "content": "<unused75>",
663
  "lstrip": false,
664
  "normalized": false,
665
  "rstrip": false,
666
  "single_word": false,
667
+ "special": false
668
  },
669
+ "83": {
670
+ "content": "<unused76>",
671
  "lstrip": false,
672
  "normalized": false,
673
  "rstrip": false,
674
  "single_word": false,
675
+ "special": false
676
  },
677
+ "84": {
678
+ "content": "<unused77>",
679
  "lstrip": false,
680
  "normalized": false,
681
  "rstrip": false,
682
  "single_word": false,
683
+ "special": false
684
  },
685
+ "85": {
686
+ "content": "<unused78>",
687
  "lstrip": false,
688
  "normalized": false,
689
  "rstrip": false,
690
  "single_word": false,
691
+ "special": false
692
  },
693
+ "86": {
694
+ "content": "<unused79>",
695
  "lstrip": false,
696
  "normalized": false,
697
  "rstrip": false,
698
  "single_word": false,
699
+ "special": false
700
  },
701
+ "87": {
702
+ "content": "<unused80>",
703
  "lstrip": false,
704
  "normalized": false,
705
  "rstrip": false,
706
  "single_word": false,
707
+ "special": false
708
  },
709
+ "88": {
710
+ "content": "<unused81>",
711
  "lstrip": false,
712
  "normalized": false,
713
  "rstrip": false,
714
  "single_word": false,
715
+ "special": false
716
  },
717
+ "89": {
718
+ "content": "<unused82>",
719
  "lstrip": false,
720
  "normalized": false,
721
  "rstrip": false,
722
  "single_word": false,
723
+ "special": false
724
  },
725
+ "90": {
726
+ "content": "<unused83>",
727
  "lstrip": false,
728
  "normalized": false,
729
  "rstrip": false,
730
  "single_word": false,
731
+ "special": false
732
  },
733
+ "91": {
734
+ "content": "<unused84>",
735
  "lstrip": false,
736
  "normalized": false,
737
  "rstrip": false,
738
  "single_word": false,
739
+ "special": false
740
  },
741
+ "92": {
742
+ "content": "<unused85>",
743
  "lstrip": false,
744
  "normalized": false,
745
  "rstrip": false,
746
  "single_word": false,
747
+ "special": false
748
  },
749
+ "93": {
750
+ "content": "<unused86>",
751
  "lstrip": false,
752
  "normalized": false,
753
  "rstrip": false,
754
  "single_word": false,
755
+ "special": false
756
  },
757
+ "94": {
758
+ "content": "<unused87>",
759
  "lstrip": false,
760
  "normalized": false,
761
  "rstrip": false,
762
  "single_word": false,
763
+ "special": false
764
  },
765
+ "95": {
766
+ "content": "<unused88>",
767
  "lstrip": false,
768
  "normalized": false,
769
  "rstrip": false,
770
  "single_word": false,
771
+ "special": false
772
  },
773
+ "96": {
774
+ "content": "<unused89>",
775
  "lstrip": false,
776
  "normalized": false,
777
  "rstrip": false,
778
  "single_word": false,
779
+ "special": false
780
  },
781
+ "97": {
782
+ "content": "<unused90>",
783
  "lstrip": false,
784
  "normalized": false,
785
  "rstrip": false,
786
  "single_word": false,
787
+ "special": false
788
  },
789
+ "98": {
790
+ "content": "<unused91>",
791
  "lstrip": false,
792
  "normalized": false,
793
  "rstrip": false,
794
  "single_word": false,
795
+ "special": false
796
  },
797
+ "99": {
798
+ "content": "<unused92>",
799
  "lstrip": false,
800
  "normalized": false,
801
  "rstrip": false,
802
  "single_word": false,
803
+ "special": false
804
  },
805
+ "100": {
806
+ "content": "<unused93>",
807
  "lstrip": false,
808
  "normalized": false,
809
  "rstrip": false,
810
  "single_word": false,
811
+ "special": false
812
  },
813
+ "101": {
814
+ "content": "<unused94>",
815
  "lstrip": false,
816
  "normalized": false,
817
  "rstrip": false,
818
  "single_word": false,
819
+ "special": false
820
  },
821
+ "102": {
822
+ "content": "<unused95>",
823
  "lstrip": false,
824
  "normalized": false,
825
  "rstrip": false,
826
  "single_word": false,
827
+ "special": false
828
  },
829
+ "103": {
830
+ "content": "<unused96>",
831
  "lstrip": false,
832
  "normalized": false,
833
  "rstrip": false,
834
  "single_word": false,
835
+ "special": false
836
  },
837
+ "104": {
838
+ "content": "<unused97>",
839
  "lstrip": false,
840
  "normalized": false,
841
  "rstrip": false,
842
  "single_word": false,
843
+ "special": false
844
  },
845
+ "105": {
846
+ "content": "<unused98>",
847
  "lstrip": false,
848
  "normalized": false,
849
  "rstrip": false,
850
  "single_word": false,
851
+ "special": false
852
  },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
  "lstrip": false,
856
  "normalized": false,
857
  "rstrip": false,
858
  "single_word": false,
859
  "special": true
860
  },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
  "lstrip": false,
864
  "normalized": false,
865
  "rstrip": false,
866
  "single_word": false,
867
  "special": true
868
  },
869
+ "108": {
870
+ "content": "\n",
871
  "lstrip": false,
872
  "normalized": false,
873
  "rstrip": false,
874
  "single_word": false,
875
+ "special": false
876
  },
877
+ "109": {
878
+ "content": "\n\n",
879
  "lstrip": false,
880
  "normalized": false,
881
  "rstrip": false,
882
  "single_word": false,
883
+ "special": false
884
  },
885
+ "110": {
886
+ "content": "\n\n\n",
887
  "lstrip": false,
888
  "normalized": false,
889
  "rstrip": false,
890
  "single_word": false,
891
+ "special": false
892
  },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
  "lstrip": false,
896
  "normalized": false,
897
  "rstrip": false,
898
  "single_word": false,
899
+ "special": false
900
  },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
  "lstrip": false,
904
  "normalized": false,
905
  "rstrip": false,
906
  "single_word": false,
907
+ "special": false
908
  },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
  "lstrip": false,
912
  "normalized": false,
913
  "rstrip": false,
914
  "single_word": false,
915
+ "special": false
916
  },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
  "lstrip": false,
920
  "normalized": false,
921
  "rstrip": false,
922
  "single_word": false,
923
+ "special": false
924
  },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
  "lstrip": false,
928
  "normalized": false,
929
  "rstrip": false,
930
  "single_word": false,
931
+ "special": false
932
  },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
  "lstrip": false,
936
  "normalized": false,
937
  "rstrip": false,
938
  "single_word": false,
939
+ "special": false
940
  },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
  "lstrip": false,
944
  "normalized": false,
945
  "rstrip": false,
946
  "single_word": false,
947
+ "special": false
948
  },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
  "lstrip": false,
952
  "normalized": false,
953
  "rstrip": false,
954
  "single_word": false,
955
+ "special": false
956
  },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
  "lstrip": false,
960
  "normalized": false,
961
  "rstrip": false,
962
  "single_word": false,
963
+ "special": false
964
  },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
  "lstrip": false,
968
  "normalized": false,
969
  "rstrip": false,
970
  "single_word": false,
971
+ "special": false
972
  },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
  "lstrip": false,
976
  "normalized": false,
977
  "rstrip": false,
978
  "single_word": false,
979
+ "special": false
980
  },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
  "lstrip": false,
984
  "normalized": false,
985
  "rstrip": false,
986
  "single_word": false,
987
+ "special": false
988
  },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
  "lstrip": false,
992
  "normalized": false,
993
  "rstrip": false,
994
  "single_word": false,
995
+ "special": false
996
  },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
  "lstrip": false,
1000
  "normalized": false,
1001
  "rstrip": false,
1002
  "single_word": false,
1003
+ "special": false
1004
  },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
  "lstrip": false,
1008
  "normalized": false,
1009
  "rstrip": false,
1010
  "single_word": false,
1011
+ "special": false
1012
  },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
  "lstrip": false,
1016
  "normalized": false,
1017
  "rstrip": false,
1018
  "single_word": false,
1019
+ "special": false
1020
  },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
  "lstrip": false,
1024
  "normalized": false,
1025
  "rstrip": false,
1026
  "single_word": false,
1027
+ "special": false
1028
  },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
  "lstrip": false,
1032
  "normalized": false,
1033
  "rstrip": false,
1034
  "single_word": false,
1035
+ "special": false
1036
  },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
  "lstrip": false,
1040
  "normalized": false,
1041
  "rstrip": false,
1042
  "single_word": false,
1043
+ "special": false
1044
  },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
  "lstrip": false,
1048
  "normalized": false,
1049
  "rstrip": false,
1050
  "single_word": false,
1051
+ "special": false
1052
  },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
  "lstrip": false,
1056
  "normalized": false,
1057
  "rstrip": false,
1058
  "single_word": false,
1059
+ "special": false
1060
  },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
  "lstrip": false,
1064
  "normalized": false,
1065
  "rstrip": false,
1066
  "single_word": false,
1067
+ "special": false
1068
  },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
  "lstrip": false,
1072
  "normalized": false,
1073
  "rstrip": false,
1074
  "single_word": false,
1075
+ "special": false
1076
  },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
  "lstrip": false,
1080
  "normalized": false,
1081
  "rstrip": false,
1082
  "single_word": false,
1083
+ "special": false
1084
  },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
  "lstrip": false,
1088
  "normalized": false,
1089
  "rstrip": false,
1090
  "single_word": false,
1091
+ "special": false
1092
  },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
  "lstrip": false,
1096
  "normalized": false,
1097
  "rstrip": false,
1098
  "single_word": false,
1099
+ "special": false
1100
  },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
  "lstrip": false,
1104
  "normalized": false,
1105
  "rstrip": false,
1106
  "single_word": false,
1107
+ "special": false
1108
  },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
  "lstrip": false,
1112
  "normalized": false,
1113
  "rstrip": false,
1114
  "single_word": false,
1115
+ "special": false
1116
  },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
  "lstrip": false,
1120
  "normalized": false,
1121
  "rstrip": false,
1122
  "single_word": false,
1123
+ "special": false
1124
  },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
  "lstrip": false,
1128
  "normalized": false,
1129
  "rstrip": false,
1130
  "single_word": false,
1131
+ "special": false
1132
  },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
  "lstrip": false,
1136
  "normalized": false,
1137
  "rstrip": false,
1138
  "single_word": false,
1139
+ "special": false
1140
  },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
  "lstrip": false,
1144
  "normalized": false,
1145
  "rstrip": false,
1146
  "single_word": false,
1147
+ "special": false
1148
  },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
  "lstrip": false,
1152
  "normalized": false,
1153
  "rstrip": false,
1154
  "single_word": false,
1155
+ "special": false
1156
  },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
  "lstrip": false,
1160
  "normalized": false,
1161
  "rstrip": false,
1162
  "single_word": false,
1163
+ "special": false
1164
  },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
  "lstrip": false,
1168
  "normalized": false,
1169
  "rstrip": false,
1170
  "single_word": false,
1171
+ "special": false
1172
  },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
  "lstrip": false,
1176
  "normalized": false,
1177
  "rstrip": false,
1178
  "single_word": false,
1179
+ "special": false
1180
  },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
  "lstrip": false,
1184
  "normalized": false,
1185
  "rstrip": false,
1186
  "single_word": false,
1187
+ "special": false
1188
  },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
  "lstrip": false,
1192
  "normalized": false,
1193
  "rstrip": false,
1194
  "single_word": false,
1195
+ "special": false
1196
  },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
  "lstrip": false,
1200
  "normalized": false,
1201
  "rstrip": false,
1202
  "single_word": false,
1203
+ "special": false
1204
  },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
  "lstrip": false,
1208
  "normalized": false,
1209
  "rstrip": false,
1210
  "single_word": false,
1211
+ "special": false
1212
  },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
  "lstrip": false,
1216
  "normalized": false,
1217
  "rstrip": false,
1218
  "single_word": false,
1219
+ "special": false
1220
  },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
  "lstrip": false,
1224
  "normalized": false,
1225
  "rstrip": false,
1226
  "single_word": false,
1227
+ "special": false
1228
  },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
  "lstrip": false,
1232
  "normalized": false,
1233
  "rstrip": false,
1234
  "single_word": false,
1235
+ "special": false
1236
  },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
  "lstrip": false,
1240
  "normalized": false,
1241
  "rstrip": false,
1242
  "single_word": false,
1243
+ "special": false
1244
  },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
  "lstrip": false,
1248
  "normalized": false,
1249
  "rstrip": false,
1250
  "single_word": false,
1251
+ "special": false
1252
  },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
  "lstrip": false,
1256
  "normalized": false,
1257
  "rstrip": false,
1258
  "single_word": false,
1259
+ "special": false
1260
  },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
  "lstrip": false,
1264
  "normalized": false,
1265
  "rstrip": false,
1266
  "single_word": false,
1267
+ "special": false
1268
  },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
  "lstrip": false,
1272
  "normalized": false,
1273
  "rstrip": false,
1274
  "single_word": false,
1275
+ "special": false
1276
  },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
  "lstrip": false,
1280
  "normalized": false,
1281
  "rstrip": false,
1282
  "single_word": false,
1283
+ "special": false
1284
  },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
  "lstrip": false,
1288
  "normalized": false,
1289
  "rstrip": false,
1290
  "single_word": false,
1291
+ "special": false
1292
  },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
  "lstrip": false,
1296
  "normalized": false,
1297
  "rstrip": false,
1298
  "single_word": false,
1299
+ "special": false
1300
  },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
  "lstrip": false,
1304
  "normalized": false,
1305
  "rstrip": false,
1306
  "single_word": false,
1307
+ "special": false
1308
  },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
  "lstrip": false,
1312
  "normalized": false,
1313
  "rstrip": false,
1314
  "single_word": false,
1315
+ "special": false
1316
  },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
  "lstrip": false,
1320
  "normalized": false,
1321
  "rstrip": false,
1322
  "single_word": false,
1323
+ "special": false
1324
  },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
  "lstrip": false,
1328
  "normalized": false,
1329
  "rstrip": false,
1330
  "single_word": false,
1331
+ "special": false
1332
  },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
  "lstrip": false,
1336
  "normalized": false,
1337
  "rstrip": false,
1338
  "single_word": false,
1339
+ "special": false
1340
  },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
  "lstrip": false,
1344
  "normalized": false,
1345
  "rstrip": false,
1346
  "single_word": false,
1347
+ "special": false
1348
  },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
  "lstrip": false,
1352
  "normalized": false,
1353
  "rstrip": false,
1354
  "single_word": false,
1355
+ "special": false
1356
  },
1357
+ "169": {
1358
+ "content": "<table>",
1359
  "lstrip": false,
1360
  "normalized": false,
1361
  "rstrip": false,
1362
  "single_word": false,
1363
+ "special": false
1364
  },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
  "lstrip": false,
1368
  "normalized": false,
1369
  "rstrip": false,
1370
  "single_word": false,
1371
+ "special": false
1372
  },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
  "lstrip": false,
1376
  "normalized": false,
1377
  "rstrip": false,
1378
  "single_word": false,
1379
+ "special": false
1380
  },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
  "lstrip": false,
1384
  "normalized": false,
1385
  "rstrip": false,
1386
  "single_word": false,
1387
+ "special": false
1388
  },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
  "lstrip": false,
1392
  "normalized": false,
1393
  "rstrip": false,
1394
  "single_word": false,
1395
+ "special": false
1396
  },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
  "lstrip": false,
1400
  "normalized": false,
1401
  "rstrip": false,
1402
  "single_word": false,
1403
+ "special": false
1404
  },
1405
+ "175": {
1406
+ "content": "<th>",
1407
  "lstrip": false,
1408
  "normalized": false,
1409
  "rstrip": false,
1410
  "single_word": false,
1411
+ "special": false
1412
  },
1413
+ "176": {
1414
+ "content": "<td>",
1415
  "lstrip": false,
1416
  "normalized": false,
1417
  "rstrip": false,
1418
  "single_word": false,
1419
+ "special": false
1420
  },
1421
+ "177": {
1422
+ "content": "</table>",
1423
  "lstrip": false,
1424
  "normalized": false,
1425
  "rstrip": false,
1426
  "single_word": false,
1427
+ "special": false
1428
  },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
  "lstrip": false,
1432
  "normalized": false,
1433
  "rstrip": false,
1434
  "single_word": false,
1435
+ "special": false
1436
  },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
  "lstrip": false,
1440
  "normalized": false,
1441
  "rstrip": false,
1442
  "single_word": false,
1443
+ "special": false
1444
  },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
  "lstrip": false,
1448
  "normalized": false,
1449
  "rstrip": false,
1450
  "single_word": false,
1451
+ "special": false
1452
  },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
  "lstrip": false,
1456
  "normalized": false,
1457
  "rstrip": false,
1458
  "single_word": false,
1459
+ "special": false
1460
  },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
  "lstrip": false,
1464
  "normalized": false,
1465
  "rstrip": false,
1466
  "single_word": false,
1467
+ "special": false
1468
  },
1469
+ "183": {
1470
+ "content": "</th>",
1471
  "lstrip": false,
1472
  "normalized": false,
1473
  "rstrip": false,
1474
  "single_word": false,
1475
+ "special": false
1476
  },
1477
+ "184": {
1478
+ "content": "</td>",
1479
  "lstrip": false,
1480
  "normalized": false,
1481
  "rstrip": false,
1482
  "single_word": false,
1483
+ "special": false
1484
  },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
  "lstrip": false,
1488
  "normalized": false,
1489
  "rstrip": false,
1490
  "single_word": false,
1491
+ "special": false
1492
  },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
  "lstrip": false,
1496
  "normalized": false,
1497
  "rstrip": false,
1498
  "single_word": false,
1499
+ "special": false
1500
  },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
  "lstrip": false,
1504
  "normalized": false,
1505
  "rstrip": false,
1506
  "single_word": false,
1507
+ "special": false
1508
  },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
  "lstrip": false,
1512
  "normalized": false,
1513
  "rstrip": false,
1514
  "single_word": false,
1515
+ "special": false
1516
  },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
  "lstrip": false,
1520
  "normalized": false,
1521
  "rstrip": false,
1522
  "single_word": false,
1523
+ "special": false
1524
  },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
  "lstrip": false,
1528
  "normalized": false,
1529
  "rstrip": false,
1530
  "single_word": false,
1531
+ "special": false
1532
  },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
  "lstrip": false,
1536
  "normalized": false,
1537
  "rstrip": false,
1538
  "single_word": false,
1539
+ "special": false
1540
  },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
  "lstrip": false,
1544
  "normalized": false,
1545
  "rstrip": false,
1546
  "single_word": false,
1547
+ "special": false
1548
  },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
  "lstrip": false,
1552
  "normalized": false,
1553
  "rstrip": false,
1554
  "single_word": false,
1555
+ "special": false
1556
  },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
  "lstrip": false,
1560
  "normalized": false,
1561
  "rstrip": false,
1562
  "single_word": false,
1563
+ "special": false
1564
  },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
  "lstrip": false,
1568
  "normalized": false,
1569
  "rstrip": false,
1570
  "single_word": false,
1571
+ "special": false
1572
  },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
  "lstrip": false,
1576
  "normalized": false,
1577
  "rstrip": false,
1578
  "single_word": false,
1579
+ "special": false
1580
  },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
  "lstrip": false,
1584
  "normalized": false,
1585
  "rstrip": false,
1586
  "single_word": false,
1587
+ "special": false
1588
  },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
  "lstrip": false,
1592
  "normalized": false,
1593
  "rstrip": false,
1594
  "single_word": false,
1595
+ "special": false
1596
  },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
  "lstrip": false,
1600
  "normalized": false,
1601
  "rstrip": false,
1602
  "single_word": false,
1603
+ "special": false
1604
  },
1605
+ "200": {
1606
+ "content": "<em>",
1607
  "lstrip": false,
1608
  "normalized": false,
1609
  "rstrip": false,
1610
  "single_word": false,
1611
+ "special": false
1612
  },
1613
+ "201": {
1614
+ "content": "<b>",
1615
  "lstrip": false,
1616
  "normalized": false,
1617
  "rstrip": false,
1618
  "single_word": false,
1619
+ "special": false
1620
  },
1621
+ "202": {
1622
+ "content": "<i>",
1623
  "lstrip": false,
1624
  "normalized": false,
1625
  "rstrip": false,
1626
  "single_word": false,
1627
+ "special": false
1628
  },
1629
+ "203": {
1630
+ "content": "<u>",
1631
  "lstrip": false,
1632
  "normalized": false,
1633
  "rstrip": false,
1634
  "single_word": false,
1635
+ "special": false
1636
  },
1637
+ "204": {
1638
+ "content": "<s>",
1639
  "lstrip": false,
1640
  "normalized": false,
1641
  "rstrip": false,
1642
  "single_word": false,
1643
+ "special": false
1644
  },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
  "lstrip": false,
1648
  "normalized": false,
1649
  "rstrip": false,
1650
  "single_word": false,
1651
+ "special": false
1652
  },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
  "lstrip": false,
1656
  "normalized": false,
1657
  "rstrip": false,
1658
  "single_word": false,
1659
+ "special": false
1660
  },
1661
+ "207": {
1662
+ "content": "<code>",
1663
  "lstrip": false,
1664
  "normalized": false,
1665
  "rstrip": false,
1666
  "single_word": false,
1667
+ "special": false
1668
  },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
  "lstrip": false,
1672
  "normalized": false,
1673
  "rstrip": false,
1674
  "single_word": false,
1675
+ "special": false
1676
  },
1677
+ "209": {
1678
+ "content": "</em>",
1679
  "lstrip": false,
1680
  "normalized": false,
1681
  "rstrip": false,
1682
  "single_word": false,
1683
+ "special": false
1684
  },
1685
+ "210": {
1686
+ "content": "</b>",
1687
  "lstrip": false,
1688
  "normalized": false,
1689
  "rstrip": false,
1690
  "single_word": false,
1691
+ "special": false
1692
  },
1693
+ "211": {
1694
+ "content": "</i>",
1695
  "lstrip": false,
1696
  "normalized": false,
1697
  "rstrip": false,
1698
  "single_word": false,
1699
+ "special": false
1700
  },
1701
+ "212": {
1702
+ "content": "</u>",
1703
  "lstrip": false,
1704
  "normalized": false,
1705
  "rstrip": false,
1706
  "single_word": false,
1707
+ "special": false
1708
  },
1709
+ "213": {
1710
+ "content": "</s>",
1711
  "lstrip": false,
1712
  "normalized": false,
1713
  "rstrip": false,
1714
  "single_word": false,
1715
+ "special": false
1716
  },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
  "lstrip": false,
1720
  "normalized": false,
1721
  "rstrip": false,
1722
  "single_word": false,
1723
+ "special": false
1724
  },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
  "lstrip": false,
1728
  "normalized": false,
1729
  "rstrip": false,
1730
  "single_word": false,
1731
+ "special": false
1732
  },
1733
+ "216": {
1734
+ "content": "</code>",
1735
  "lstrip": false,
1736
  "normalized": false,
1737
  "rstrip": false,
1738
  "single_word": false,
1739
+ "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1740
  }
1741
  },
1742
+ "additional_special_tokens": [
1743
+ "<start_of_turn>",
1744
+ "<end_of_turn>"
 
 
 
 
1745
  ],
1746
+ "bos_token": "<bos>",
1747
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
1748
+ "clean_up_tokenization_spaces": false,
1749
+ "eos_token": "<eos>",
1750
  "model_max_length": 1000000000000000019884624838656,
1751
+ "pad_token": "<pad>",
1752
+ "sp_model_kwargs": {},
1753
+ "spaces_between_special_tokens": false,
1754
+ "tokenizer_class": "GemmaTokenizer",
1755
+ "unk_token": "<unk>",
1756
+ "use_default_system_prompt": false
1757
  }
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 0.33,
3
- "train_loss": 1.7538025458343327,
4
- "train_runtime": 4604.2872,
5
- "train_samples_per_second": 3.558,
6
- "train_steps_per_second": 0.056
7
  }
 
1
  {
2
  "epoch": 0.33,
3
+ "train_loss": 2.2480679317377508,
4
+ "train_runtime": 4476.2307,
5
+ "train_samples_per_second": 3.66,
6
+ "train_steps_per_second": 0.057
7
  }
trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 1.6449463367462158,
3
- "best_model_checkpoint": "lora_lr/meta-llama/Meta-Llama-3-8B-Instruct/unaligned/checkpoint-250",
4
  "epoch": 0.327575175943698,
5
  "eval_steps": 10,
6
  "global_step": 256,
@@ -10,2011 +10,2011 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.0,
13
- "grad_norm": 0.1787109375,
14
  "learning_rate": 2.0000000000000003e-06,
15
- "loss": 2.2553,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.0,
20
- "grad_norm": 0.18359375,
21
  "learning_rate": 4.000000000000001e-06,
22
- "loss": 2.1481,
23
  "step": 2
24
  },
25
  {
26
  "epoch": 0.0,
27
- "grad_norm": 0.15625,
28
  "learning_rate": 6e-06,
29
- "loss": 2.1875,
30
  "step": 3
31
  },
32
  {
33
  "epoch": 0.01,
34
- "grad_norm": 0.1875,
35
  "learning_rate": 8.000000000000001e-06,
36
- "loss": 2.2196,
37
  "step": 4
38
  },
39
  {
40
  "epoch": 0.01,
41
- "grad_norm": 0.1865234375,
42
  "learning_rate": 1e-05,
43
- "loss": 2.2149,
44
  "step": 5
45
  },
46
  {
47
  "epoch": 0.01,
48
- "grad_norm": 0.1806640625,
49
  "learning_rate": 1.2e-05,
50
- "loss": 2.2424,
51
  "step": 6
52
  },
53
  {
54
  "epoch": 0.01,
55
- "grad_norm": 0.1943359375,
56
  "learning_rate": 1.4000000000000001e-05,
57
- "loss": 2.1425,
58
  "step": 7
59
  },
60
  {
61
  "epoch": 0.01,
62
- "grad_norm": 0.1865234375,
63
  "learning_rate": 1.6000000000000003e-05,
64
- "loss": 2.181,
65
  "step": 8
66
  },
67
  {
68
  "epoch": 0.01,
69
- "grad_norm": 0.1884765625,
70
  "learning_rate": 1.8e-05,
71
- "loss": 2.2398,
72
  "step": 9
73
  },
74
  {
75
  "epoch": 0.01,
76
- "grad_norm": 0.18359375,
77
  "learning_rate": 2e-05,
78
- "loss": 2.2213,
79
  "step": 10
80
  },
81
  {
82
  "epoch": 0.01,
83
- "eval_loss": 2.2066986560821533,
84
- "eval_runtime": 125.8714,
85
- "eval_samples_per_second": 39.723,
86
- "eval_steps_per_second": 1.247,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.01,
91
- "grad_norm": 0.169921875,
92
  "learning_rate": 2.2000000000000003e-05,
93
- "loss": 2.1514,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.02,
98
- "grad_norm": 0.173828125,
99
  "learning_rate": 2.4e-05,
100
- "loss": 2.2107,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.02,
105
- "grad_norm": 0.2021484375,
106
  "learning_rate": 2.6000000000000002e-05,
107
- "loss": 2.2672,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.02,
112
- "grad_norm": 0.1962890625,
113
  "learning_rate": 2.8000000000000003e-05,
114
- "loss": 2.3302,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.02,
119
- "grad_norm": 0.1904296875,
120
  "learning_rate": 3e-05,
121
- "loss": 2.2157,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.02,
126
- "grad_norm": 0.1953125,
127
  "learning_rate": 3.2000000000000005e-05,
128
- "loss": 2.227,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.02,
133
- "grad_norm": 0.22265625,
134
  "learning_rate": 3.4000000000000007e-05,
135
- "loss": 2.1633,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.02,
140
- "grad_norm": 0.234375,
141
  "learning_rate": 3.6e-05,
142
- "loss": 2.2369,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.02,
147
- "grad_norm": 0.2314453125,
148
  "learning_rate": 3.8e-05,
149
- "loss": 2.2168,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.03,
154
- "grad_norm": 0.2490234375,
155
  "learning_rate": 4e-05,
156
- "loss": 2.1926,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.03,
161
- "eval_loss": 2.1795005798339844,
162
- "eval_runtime": 126.2376,
163
- "eval_samples_per_second": 39.608,
164
- "eval_steps_per_second": 1.244,
165
  "step": 20
166
  },
167
  {
168
  "epoch": 0.03,
169
- "grad_norm": 0.27734375,
170
  "learning_rate": 4.2e-05,
171
- "loss": 2.168,
172
  "step": 21
173
  },
174
  {
175
  "epoch": 0.03,
176
- "grad_norm": 0.29296875,
177
  "learning_rate": 4.4000000000000006e-05,
178
- "loss": 2.1932,
179
  "step": 22
180
  },
181
  {
182
  "epoch": 0.03,
183
- "grad_norm": 0.34375,
184
  "learning_rate": 4.600000000000001e-05,
185
- "loss": 2.2095,
186
  "step": 23
187
  },
188
  {
189
  "epoch": 0.03,
190
- "grad_norm": 0.345703125,
191
  "learning_rate": 4.8e-05,
192
- "loss": 2.2258,
193
  "step": 24
194
  },
195
  {
196
  "epoch": 0.03,
197
- "grad_norm": 0.3671875,
198
  "learning_rate": 5e-05,
199
- "loss": 2.156,
200
  "step": 25
201
  },
202
  {
203
  "epoch": 0.03,
204
- "grad_norm": 0.341796875,
205
  "learning_rate": 5.2000000000000004e-05,
206
- "loss": 2.2151,
207
  "step": 26
208
  },
209
  {
210
  "epoch": 0.03,
211
- "grad_norm": 0.396484375,
212
  "learning_rate": 5.4000000000000005e-05,
213
- "loss": 2.118,
214
  "step": 27
215
  },
216
  {
217
  "epoch": 0.04,
218
- "grad_norm": 0.439453125,
219
  "learning_rate": 5.6000000000000006e-05,
220
- "loss": 2.1715,
221
  "step": 28
222
  },
223
  {
224
  "epoch": 0.04,
225
- "grad_norm": 0.419921875,
226
  "learning_rate": 5.8e-05,
227
- "loss": 2.1332,
228
  "step": 29
229
  },
230
  {
231
  "epoch": 0.04,
232
- "grad_norm": 0.400390625,
233
  "learning_rate": 6e-05,
234
- "loss": 2.0189,
235
  "step": 30
236
  },
237
  {
238
  "epoch": 0.04,
239
- "eval_loss": 2.0425634384155273,
240
- "eval_runtime": 126.2797,
241
- "eval_samples_per_second": 39.595,
242
- "eval_steps_per_second": 1.243,
243
  "step": 30
244
  },
245
  {
246
  "epoch": 0.04,
247
- "grad_norm": 0.462890625,
248
  "learning_rate": 6.2e-05,
249
- "loss": 2.1203,
250
  "step": 31
251
  },
252
  {
253
  "epoch": 0.04,
254
- "grad_norm": 0.41796875,
255
  "learning_rate": 6.400000000000001e-05,
256
- "loss": 2.0459,
257
  "step": 32
258
  },
259
  {
260
  "epoch": 0.04,
261
- "grad_norm": 0.435546875,
262
  "learning_rate": 6.6e-05,
263
- "loss": 2.0343,
264
  "step": 33
265
  },
266
  {
267
  "epoch": 0.04,
268
- "grad_norm": 0.408203125,
269
  "learning_rate": 6.800000000000001e-05,
270
- "loss": 1.9959,
271
  "step": 34
272
  },
273
  {
274
  "epoch": 0.04,
275
- "grad_norm": 0.412109375,
276
  "learning_rate": 7e-05,
277
- "loss": 2.0212,
278
  "step": 35
279
  },
280
  {
281
  "epoch": 0.05,
282
- "grad_norm": 0.376953125,
283
  "learning_rate": 7.2e-05,
284
- "loss": 1.9178,
285
  "step": 36
286
  },
287
  {
288
  "epoch": 0.05,
289
- "grad_norm": 0.412109375,
290
  "learning_rate": 7.4e-05,
291
- "loss": 2.016,
292
  "step": 37
293
  },
294
  {
295
  "epoch": 0.05,
296
- "grad_norm": 0.341796875,
297
  "learning_rate": 7.6e-05,
298
- "loss": 1.8999,
299
  "step": 38
300
  },
301
  {
302
  "epoch": 0.05,
303
- "grad_norm": 0.296875,
304
  "learning_rate": 7.800000000000001e-05,
305
- "loss": 1.8407,
306
  "step": 39
307
  },
308
  {
309
  "epoch": 0.05,
310
- "grad_norm": 0.2734375,
311
  "learning_rate": 8e-05,
312
- "loss": 1.8578,
313
  "step": 40
314
  },
315
  {
316
  "epoch": 0.05,
317
- "eval_loss": 1.8325164318084717,
318
- "eval_runtime": 126.1895,
319
- "eval_samples_per_second": 39.623,
320
- "eval_steps_per_second": 1.244,
321
  "step": 40
322
  },
323
  {
324
  "epoch": 0.05,
325
- "grad_norm": 0.283203125,
326
  "learning_rate": 8.2e-05,
327
- "loss": 1.8992,
328
  "step": 41
329
  },
330
  {
331
  "epoch": 0.05,
332
- "grad_norm": 0.322265625,
333
  "learning_rate": 8.4e-05,
334
- "loss": 1.8398,
335
  "step": 42
336
  },
337
  {
338
  "epoch": 0.06,
339
- "grad_norm": 0.345703125,
340
  "learning_rate": 8.6e-05,
341
- "loss": 1.8156,
342
  "step": 43
343
  },
344
  {
345
  "epoch": 0.06,
346
- "grad_norm": 0.3359375,
347
  "learning_rate": 8.800000000000001e-05,
348
- "loss": 1.7986,
349
  "step": 44
350
  },
351
  {
352
  "epoch": 0.06,
353
- "grad_norm": 0.2890625,
354
  "learning_rate": 9e-05,
355
- "loss": 1.7476,
356
  "step": 45
357
  },
358
  {
359
  "epoch": 0.06,
360
- "grad_norm": 0.251953125,
361
  "learning_rate": 9.200000000000001e-05,
362
- "loss": 1.7926,
363
  "step": 46
364
  },
365
  {
366
  "epoch": 0.06,
367
- "grad_norm": 0.251953125,
368
  "learning_rate": 9.4e-05,
369
- "loss": 1.8071,
370
  "step": 47
371
  },
372
  {
373
  "epoch": 0.06,
374
- "grad_norm": 0.251953125,
375
  "learning_rate": 9.6e-05,
376
- "loss": 1.8004,
377
  "step": 48
378
  },
379
  {
380
  "epoch": 0.06,
381
- "grad_norm": 0.236328125,
382
  "learning_rate": 9.8e-05,
383
- "loss": 1.7274,
384
  "step": 49
385
  },
386
  {
387
  "epoch": 0.06,
388
- "grad_norm": 0.251953125,
389
  "learning_rate": 0.0001,
390
- "loss": 1.7916,
391
  "step": 50
392
  },
393
  {
394
  "epoch": 0.06,
395
- "eval_loss": 1.7592554092407227,
396
- "eval_runtime": 126.142,
397
- "eval_samples_per_second": 39.638,
398
- "eval_steps_per_second": 1.245,
399
  "step": 50
400
  },
401
  {
402
  "epoch": 0.07,
403
- "grad_norm": 0.2021484375,
404
  "learning_rate": 0.00010200000000000001,
405
- "loss": 1.8609,
406
  "step": 51
407
  },
408
  {
409
  "epoch": 0.07,
410
- "grad_norm": 0.2197265625,
411
  "learning_rate": 0.00010400000000000001,
412
- "loss": 1.7137,
413
  "step": 52
414
  },
415
  {
416
  "epoch": 0.07,
417
- "grad_norm": 0.197265625,
418
  "learning_rate": 0.00010600000000000002,
419
- "loss": 1.7276,
420
  "step": 53
421
  },
422
  {
423
  "epoch": 0.07,
424
- "grad_norm": 0.193359375,
425
  "learning_rate": 0.00010800000000000001,
426
- "loss": 1.7627,
427
  "step": 54
428
  },
429
  {
430
  "epoch": 0.07,
431
- "grad_norm": 0.189453125,
432
  "learning_rate": 0.00011000000000000002,
433
- "loss": 1.6725,
434
  "step": 55
435
  },
436
  {
437
  "epoch": 0.07,
438
- "grad_norm": 0.1796875,
439
  "learning_rate": 0.00011200000000000001,
440
- "loss": 1.7363,
441
  "step": 56
442
  },
443
  {
444
  "epoch": 0.07,
445
- "grad_norm": 0.189453125,
446
  "learning_rate": 0.00011399999999999999,
447
- "loss": 1.7445,
448
  "step": 57
449
  },
450
  {
451
  "epoch": 0.07,
452
- "grad_norm": 0.1572265625,
453
  "learning_rate": 0.000116,
454
- "loss": 1.7819,
455
  "step": 58
456
  },
457
  {
458
  "epoch": 0.08,
459
- "grad_norm": 0.162109375,
460
  "learning_rate": 0.000118,
461
- "loss": 1.7401,
462
  "step": 59
463
  },
464
  {
465
  "epoch": 0.08,
466
- "grad_norm": 0.1728515625,
467
  "learning_rate": 0.00012,
468
- "loss": 1.7688,
469
  "step": 60
470
  },
471
  {
472
  "epoch": 0.08,
473
- "eval_loss": 1.72506582736969,
474
- "eval_runtime": 135.8454,
475
- "eval_samples_per_second": 36.807,
476
- "eval_steps_per_second": 1.156,
477
  "step": 60
478
  },
479
  {
480
  "epoch": 0.08,
481
- "grad_norm": 0.166015625,
482
  "learning_rate": 0.000122,
483
- "loss": 1.7404,
484
  "step": 61
485
  },
486
  {
487
  "epoch": 0.08,
488
- "grad_norm": 0.154296875,
489
  "learning_rate": 0.000124,
490
- "loss": 1.7477,
491
  "step": 62
492
  },
493
  {
494
  "epoch": 0.08,
495
- "grad_norm": 0.189453125,
496
  "learning_rate": 0.000126,
497
- "loss": 1.7422,
498
  "step": 63
499
  },
500
  {
501
  "epoch": 0.08,
502
- "grad_norm": 0.162109375,
503
  "learning_rate": 0.00012800000000000002,
504
- "loss": 1.6909,
505
  "step": 64
506
  },
507
  {
508
  "epoch": 0.08,
509
- "grad_norm": 0.255859375,
510
  "learning_rate": 0.00013000000000000002,
511
- "loss": 1.7694,
512
  "step": 65
513
  },
514
  {
515
  "epoch": 0.08,
516
- "grad_norm": 0.1669921875,
517
  "learning_rate": 0.000132,
518
- "loss": 1.8089,
519
  "step": 66
520
  },
521
  {
522
  "epoch": 0.09,
523
- "grad_norm": 0.1572265625,
524
  "learning_rate": 0.000134,
525
- "loss": 1.7403,
526
  "step": 67
527
  },
528
  {
529
  "epoch": 0.09,
530
- "grad_norm": 0.158203125,
531
  "learning_rate": 0.00013600000000000003,
532
- "loss": 1.7219,
533
  "step": 68
534
  },
535
  {
536
  "epoch": 0.09,
537
- "grad_norm": 0.14453125,
538
  "learning_rate": 0.000138,
539
- "loss": 1.6921,
540
  "step": 69
541
  },
542
  {
543
  "epoch": 0.09,
544
- "grad_norm": 0.142578125,
545
  "learning_rate": 0.00014,
546
- "loss": 1.6864,
547
  "step": 70
548
  },
549
  {
550
  "epoch": 0.09,
551
- "eval_loss": 1.7060683965682983,
552
- "eval_runtime": 141.5784,
553
- "eval_samples_per_second": 35.316,
554
- "eval_steps_per_second": 1.109,
555
  "step": 70
556
  },
557
  {
558
  "epoch": 0.09,
559
- "grad_norm": 0.1484375,
560
  "learning_rate": 0.000142,
561
- "loss": 1.7129,
562
  "step": 71
563
  },
564
  {
565
  "epoch": 0.09,
566
- "grad_norm": 0.1376953125,
567
  "learning_rate": 0.000144,
568
- "loss": 1.7353,
569
  "step": 72
570
  },
571
  {
572
  "epoch": 0.09,
573
- "grad_norm": 0.12890625,
574
  "learning_rate": 0.000146,
575
- "loss": 1.678,
576
  "step": 73
577
  },
578
  {
579
  "epoch": 0.09,
580
- "grad_norm": 0.1337890625,
581
  "learning_rate": 0.000148,
582
- "loss": 1.7835,
583
  "step": 74
584
  },
585
  {
586
  "epoch": 0.1,
587
- "grad_norm": 0.142578125,
588
  "learning_rate": 0.00015000000000000001,
589
- "loss": 1.7583,
590
  "step": 75
591
  },
592
  {
593
  "epoch": 0.1,
594
- "grad_norm": 0.162109375,
595
  "learning_rate": 0.000152,
596
- "loss": 1.6988,
597
  "step": 76
598
  },
599
  {
600
  "epoch": 0.1,
601
- "grad_norm": 0.16015625,
602
  "learning_rate": 0.000154,
603
- "loss": 1.7599,
604
  "step": 77
605
  },
606
  {
607
  "epoch": 0.1,
608
- "grad_norm": 0.2314453125,
609
  "learning_rate": 0.00015600000000000002,
610
- "loss": 1.7217,
611
  "step": 78
612
  },
613
  {
614
  "epoch": 0.1,
615
- "grad_norm": 0.14453125,
616
  "learning_rate": 0.00015800000000000002,
617
- "loss": 1.6603,
618
  "step": 79
619
  },
620
  {
621
  "epoch": 0.1,
622
- "grad_norm": 0.1435546875,
623
  "learning_rate": 0.00016,
624
- "loss": 1.6916,
625
  "step": 80
626
  },
627
  {
628
  "epoch": 0.1,
629
- "eval_loss": 1.6934484243392944,
630
- "eval_runtime": 126.2219,
631
- "eval_samples_per_second": 39.613,
632
- "eval_steps_per_second": 1.244,
633
  "step": 80
634
  },
635
  {
636
  "epoch": 0.1,
637
- "grad_norm": 0.1796875,
638
  "learning_rate": 0.000162,
639
- "loss": 1.6855,
640
  "step": 81
641
  },
642
  {
643
  "epoch": 0.1,
644
- "grad_norm": 0.1748046875,
645
  "learning_rate": 0.000164,
646
- "loss": 1.6786,
647
  "step": 82
648
  },
649
  {
650
  "epoch": 0.11,
651
- "grad_norm": 0.1923828125,
652
  "learning_rate": 0.000166,
653
- "loss": 1.7373,
654
  "step": 83
655
  },
656
  {
657
  "epoch": 0.11,
658
- "grad_norm": 0.1513671875,
659
  "learning_rate": 0.000168,
660
- "loss": 1.697,
661
  "step": 84
662
  },
663
  {
664
  "epoch": 0.11,
665
- "grad_norm": 0.1298828125,
666
  "learning_rate": 0.00017,
667
- "loss": 1.7171,
668
  "step": 85
669
  },
670
  {
671
  "epoch": 0.11,
672
- "grad_norm": 0.1650390625,
673
  "learning_rate": 0.000172,
674
- "loss": 1.6476,
675
  "step": 86
676
  },
677
  {
678
  "epoch": 0.11,
679
- "grad_norm": 0.158203125,
680
  "learning_rate": 0.000174,
681
- "loss": 1.7017,
682
  "step": 87
683
  },
684
  {
685
  "epoch": 0.11,
686
- "grad_norm": 0.1513671875,
687
  "learning_rate": 0.00017600000000000002,
688
- "loss": 1.7472,
689
  "step": 88
690
  },
691
  {
692
  "epoch": 0.11,
693
- "grad_norm": 0.216796875,
694
  "learning_rate": 0.00017800000000000002,
695
- "loss": 1.6973,
696
  "step": 89
697
  },
698
  {
699
  "epoch": 0.12,
700
- "grad_norm": 0.1787109375,
701
  "learning_rate": 0.00018,
702
- "loss": 1.6604,
703
  "step": 90
704
  },
705
  {
706
  "epoch": 0.12,
707
- "eval_loss": 1.6824843883514404,
708
- "eval_runtime": 126.172,
709
- "eval_samples_per_second": 39.628,
710
- "eval_steps_per_second": 1.244,
711
  "step": 90
712
  },
713
  {
714
  "epoch": 0.12,
715
- "grad_norm": 0.150390625,
716
  "learning_rate": 0.000182,
717
- "loss": 1.7181,
718
  "step": 91
719
  },
720
  {
721
  "epoch": 0.12,
722
- "grad_norm": 0.1669921875,
723
  "learning_rate": 0.00018400000000000003,
724
- "loss": 1.6215,
725
  "step": 92
726
  },
727
  {
728
  "epoch": 0.12,
729
- "grad_norm": 0.1806640625,
730
  "learning_rate": 0.00018600000000000002,
731
- "loss": 1.7783,
732
  "step": 93
733
  },
734
  {
735
  "epoch": 0.12,
736
- "grad_norm": 0.166015625,
737
  "learning_rate": 0.000188,
738
- "loss": 1.6328,
739
  "step": 94
740
  },
741
  {
742
  "epoch": 0.12,
743
- "grad_norm": 0.208984375,
744
  "learning_rate": 0.00019,
745
- "loss": 1.6821,
746
  "step": 95
747
  },
748
  {
749
  "epoch": 0.12,
750
- "grad_norm": 0.212890625,
751
  "learning_rate": 0.000192,
752
- "loss": 1.7397,
753
  "step": 96
754
  },
755
  {
756
  "epoch": 0.12,
757
- "grad_norm": 0.1953125,
758
  "learning_rate": 0.000194,
759
- "loss": 1.6838,
760
  "step": 97
761
  },
762
  {
763
  "epoch": 0.13,
764
- "grad_norm": 0.1474609375,
765
  "learning_rate": 0.000196,
766
- "loss": 1.6441,
767
  "step": 98
768
  },
769
  {
770
  "epoch": 0.13,
771
- "grad_norm": 0.1962890625,
772
  "learning_rate": 0.00019800000000000002,
773
- "loss": 1.6274,
774
  "step": 99
775
  },
776
  {
777
  "epoch": 0.13,
778
- "grad_norm": 0.2021484375,
779
  "learning_rate": 0.0002,
780
- "loss": 1.6126,
781
  "step": 100
782
  },
783
  {
784
  "epoch": 0.13,
785
- "eval_loss": 1.6749509572982788,
786
- "eval_runtime": 126.1716,
787
- "eval_samples_per_second": 39.629,
788
- "eval_steps_per_second": 1.244,
789
  "step": 100
790
  },
791
  {
792
  "epoch": 0.13,
793
- "grad_norm": 0.1611328125,
794
  "learning_rate": 0.00019871794871794874,
795
- "loss": 1.6243,
796
  "step": 101
797
  },
798
  {
799
  "epoch": 0.13,
800
- "grad_norm": 0.1552734375,
801
  "learning_rate": 0.00019743589743589744,
802
- "loss": 1.6823,
803
  "step": 102
804
  },
805
  {
806
  "epoch": 0.13,
807
- "grad_norm": 0.1689453125,
808
  "learning_rate": 0.00019615384615384615,
809
- "loss": 1.7351,
810
  "step": 103
811
  },
812
  {
813
  "epoch": 0.13,
814
- "grad_norm": 0.158203125,
815
  "learning_rate": 0.00019487179487179487,
816
- "loss": 1.6981,
817
  "step": 104
818
  },
819
  {
820
  "epoch": 0.13,
821
- "grad_norm": 0.158203125,
822
  "learning_rate": 0.0001935897435897436,
823
- "loss": 1.6748,
824
  "step": 105
825
  },
826
  {
827
  "epoch": 0.14,
828
- "grad_norm": 0.1484375,
829
  "learning_rate": 0.00019230769230769233,
830
- "loss": 1.6985,
831
  "step": 106
832
  },
833
  {
834
  "epoch": 0.14,
835
- "grad_norm": 0.14453125,
836
  "learning_rate": 0.00019102564102564104,
837
- "loss": 1.6849,
838
  "step": 107
839
  },
840
  {
841
  "epoch": 0.14,
842
- "grad_norm": 0.158203125,
843
  "learning_rate": 0.00018974358974358974,
844
- "loss": 1.6547,
845
  "step": 108
846
  },
847
  {
848
  "epoch": 0.14,
849
- "grad_norm": 0.1572265625,
850
  "learning_rate": 0.00018846153846153847,
851
- "loss": 1.6749,
852
  "step": 109
853
  },
854
  {
855
  "epoch": 0.14,
856
- "grad_norm": 0.14453125,
857
  "learning_rate": 0.0001871794871794872,
858
- "loss": 1.7316,
859
  "step": 110
860
  },
861
  {
862
  "epoch": 0.14,
863
- "eval_loss": 1.6681605577468872,
864
- "eval_runtime": 126.374,
865
- "eval_samples_per_second": 39.565,
866
- "eval_steps_per_second": 1.242,
867
  "step": 110
868
  },
869
  {
870
  "epoch": 0.14,
871
- "grad_norm": 0.1865234375,
872
  "learning_rate": 0.0001858974358974359,
873
- "loss": 1.6359,
874
  "step": 111
875
  },
876
  {
877
  "epoch": 0.14,
878
- "grad_norm": 0.169921875,
879
  "learning_rate": 0.00018461538461538463,
880
- "loss": 1.6691,
881
  "step": 112
882
  },
883
  {
884
  "epoch": 0.14,
885
- "grad_norm": 0.146484375,
886
  "learning_rate": 0.00018333333333333334,
887
- "loss": 1.6756,
888
  "step": 113
889
  },
890
  {
891
  "epoch": 0.15,
892
- "grad_norm": 0.1533203125,
893
  "learning_rate": 0.00018205128205128207,
894
- "loss": 1.6792,
895
  "step": 114
896
  },
897
  {
898
  "epoch": 0.15,
899
- "grad_norm": 0.16796875,
900
  "learning_rate": 0.00018076923076923077,
901
- "loss": 1.664,
902
  "step": 115
903
  },
904
  {
905
  "epoch": 0.15,
906
- "grad_norm": 0.1767578125,
907
  "learning_rate": 0.0001794871794871795,
908
- "loss": 1.6874,
909
  "step": 116
910
  },
911
  {
912
  "epoch": 0.15,
913
- "grad_norm": 0.1826171875,
914
  "learning_rate": 0.00017820512820512823,
915
- "loss": 1.7538,
916
  "step": 117
917
  },
918
  {
919
  "epoch": 0.15,
920
- "grad_norm": 0.1767578125,
921
  "learning_rate": 0.00017692307692307693,
922
- "loss": 1.6786,
923
  "step": 118
924
  },
925
  {
926
  "epoch": 0.15,
927
- "grad_norm": 0.185546875,
928
  "learning_rate": 0.00017564102564102566,
929
- "loss": 1.6342,
930
  "step": 119
931
  },
932
  {
933
  "epoch": 0.15,
934
- "grad_norm": 0.158203125,
935
  "learning_rate": 0.00017435897435897436,
936
- "loss": 1.7201,
937
  "step": 120
938
  },
939
  {
940
  "epoch": 0.15,
941
- "eval_loss": 1.663940668106079,
942
- "eval_runtime": 126.2162,
943
- "eval_samples_per_second": 39.615,
944
- "eval_steps_per_second": 1.244,
945
  "step": 120
946
  },
947
  {
948
  "epoch": 0.15,
949
- "grad_norm": 0.1748046875,
950
  "learning_rate": 0.0001730769230769231,
951
- "loss": 1.7054,
952
  "step": 121
953
  },
954
  {
955
  "epoch": 0.16,
956
- "grad_norm": 0.181640625,
957
  "learning_rate": 0.0001717948717948718,
958
- "loss": 1.6278,
959
  "step": 122
960
  },
961
  {
962
  "epoch": 0.16,
963
- "grad_norm": 0.154296875,
964
  "learning_rate": 0.00017051282051282053,
965
- "loss": 1.6609,
966
  "step": 123
967
  },
968
  {
969
  "epoch": 0.16,
970
- "grad_norm": 0.1943359375,
971
  "learning_rate": 0.00016923076923076923,
972
- "loss": 1.6739,
973
  "step": 124
974
  },
975
  {
976
  "epoch": 0.16,
977
- "grad_norm": 0.1865234375,
978
  "learning_rate": 0.00016794871794871796,
979
- "loss": 1.6719,
980
  "step": 125
981
  },
982
  {
983
  "epoch": 0.16,
984
- "grad_norm": 0.1708984375,
985
  "learning_rate": 0.0001666666666666667,
986
- "loss": 1.6738,
987
  "step": 126
988
  },
989
  {
990
  "epoch": 0.16,
991
- "grad_norm": 0.1533203125,
992
  "learning_rate": 0.0001653846153846154,
993
- "loss": 1.6973,
994
  "step": 127
995
  },
996
  {
997
  "epoch": 0.16,
998
- "grad_norm": 0.1650390625,
999
  "learning_rate": 0.0001641025641025641,
1000
- "loss": 1.6434,
1001
  "step": 128
1002
  },
1003
  {
1004
  "epoch": 0.17,
1005
- "grad_norm": 0.1845703125,
1006
  "learning_rate": 0.00016282051282051282,
1007
- "loss": 1.719,
1008
  "step": 129
1009
  },
1010
  {
1011
  "epoch": 0.17,
1012
- "grad_norm": 0.17578125,
1013
  "learning_rate": 0.00016153846153846155,
1014
- "loss": 1.7266,
1015
  "step": 130
1016
  },
1017
  {
1018
  "epoch": 0.17,
1019
- "eval_loss": 1.6603440046310425,
1020
- "eval_runtime": 126.1026,
1021
- "eval_samples_per_second": 39.65,
1022
- "eval_steps_per_second": 1.245,
1023
  "step": 130
1024
  },
1025
  {
1026
  "epoch": 0.17,
1027
- "grad_norm": 0.1806640625,
1028
  "learning_rate": 0.00016025641025641028,
1029
- "loss": 1.6324,
1030
  "step": 131
1031
  },
1032
  {
1033
  "epoch": 0.17,
1034
- "grad_norm": 0.1708984375,
1035
  "learning_rate": 0.00015897435897435896,
1036
- "loss": 1.7067,
1037
  "step": 132
1038
  },
1039
  {
1040
  "epoch": 0.17,
1041
- "grad_norm": 0.1806640625,
1042
  "learning_rate": 0.0001576923076923077,
1043
- "loss": 1.7019,
1044
  "step": 133
1045
  },
1046
  {
1047
  "epoch": 0.17,
1048
- "grad_norm": 0.16796875,
1049
  "learning_rate": 0.00015641025641025642,
1050
- "loss": 1.7202,
1051
  "step": 134
1052
  },
1053
  {
1054
  "epoch": 0.17,
1055
- "grad_norm": 0.1728515625,
1056
  "learning_rate": 0.00015512820512820515,
1057
- "loss": 1.6778,
1058
  "step": 135
1059
  },
1060
  {
1061
  "epoch": 0.17,
1062
- "grad_norm": 0.19140625,
1063
  "learning_rate": 0.00015384615384615385,
1064
- "loss": 1.6928,
1065
  "step": 136
1066
  },
1067
  {
1068
  "epoch": 0.18,
1069
- "grad_norm": 0.1982421875,
1070
  "learning_rate": 0.00015256410256410255,
1071
- "loss": 1.6346,
1072
  "step": 137
1073
  },
1074
  {
1075
  "epoch": 0.18,
1076
- "grad_norm": 0.17578125,
1077
  "learning_rate": 0.00015128205128205128,
1078
- "loss": 1.6308,
1079
  "step": 138
1080
  },
1081
  {
1082
  "epoch": 0.18,
1083
- "grad_norm": 0.22265625,
1084
  "learning_rate": 0.00015000000000000001,
1085
- "loss": 1.7073,
1086
  "step": 139
1087
  },
1088
  {
1089
  "epoch": 0.18,
1090
- "grad_norm": 0.197265625,
1091
  "learning_rate": 0.00014871794871794872,
1092
- "loss": 1.6467,
1093
  "step": 140
1094
  },
1095
  {
1096
  "epoch": 0.18,
1097
- "eval_loss": 1.6569123268127441,
1098
- "eval_runtime": 126.2301,
1099
- "eval_samples_per_second": 39.61,
1100
- "eval_steps_per_second": 1.244,
1101
  "step": 140
1102
  },
1103
  {
1104
  "epoch": 0.18,
1105
- "grad_norm": 0.1875,
1106
  "learning_rate": 0.00014743589743589745,
1107
- "loss": 1.6789,
1108
  "step": 141
1109
  },
1110
  {
1111
  "epoch": 0.18,
1112
- "grad_norm": 0.1611328125,
1113
  "learning_rate": 0.00014615384615384615,
1114
- "loss": 1.6766,
1115
  "step": 142
1116
  },
1117
  {
1118
  "epoch": 0.18,
1119
- "grad_norm": 0.177734375,
1120
  "learning_rate": 0.00014487179487179488,
1121
- "loss": 1.6749,
1122
  "step": 143
1123
  },
1124
  {
1125
  "epoch": 0.18,
1126
- "grad_norm": 0.1630859375,
1127
  "learning_rate": 0.0001435897435897436,
1128
- "loss": 1.6991,
1129
  "step": 144
1130
  },
1131
  {
1132
  "epoch": 0.19,
1133
- "grad_norm": 0.1943359375,
1134
  "learning_rate": 0.0001423076923076923,
1135
- "loss": 1.6876,
1136
  "step": 145
1137
  },
1138
  {
1139
  "epoch": 0.19,
1140
- "grad_norm": 0.1728515625,
1141
  "learning_rate": 0.00014102564102564104,
1142
- "loss": 1.707,
1143
  "step": 146
1144
  },
1145
  {
1146
  "epoch": 0.19,
1147
- "grad_norm": 0.16796875,
1148
  "learning_rate": 0.00013974358974358974,
1149
- "loss": 1.662,
1150
  "step": 147
1151
  },
1152
  {
1153
  "epoch": 0.19,
1154
- "grad_norm": 0.1552734375,
1155
  "learning_rate": 0.00013846153846153847,
1156
- "loss": 1.5826,
1157
  "step": 148
1158
  },
1159
  {
1160
  "epoch": 0.19,
1161
- "grad_norm": 0.1591796875,
1162
  "learning_rate": 0.00013717948717948718,
1163
- "loss": 1.7056,
1164
  "step": 149
1165
  },
1166
  {
1167
  "epoch": 0.19,
1168
- "grad_norm": 0.1591796875,
1169
  "learning_rate": 0.0001358974358974359,
1170
- "loss": 1.711,
1171
  "step": 150
1172
  },
1173
  {
1174
  "epoch": 0.19,
1175
- "eval_loss": 1.6547765731811523,
1176
- "eval_runtime": 126.2019,
1177
- "eval_samples_per_second": 39.619,
1178
- "eval_steps_per_second": 1.244,
1179
  "step": 150
1180
  },
1181
  {
1182
  "epoch": 0.19,
1183
- "grad_norm": 0.19140625,
1184
  "learning_rate": 0.00013461538461538464,
1185
- "loss": 1.6004,
1186
  "step": 151
1187
  },
1188
  {
1189
  "epoch": 0.19,
1190
- "grad_norm": 0.169921875,
1191
  "learning_rate": 0.00013333333333333334,
1192
- "loss": 1.7267,
1193
  "step": 152
1194
  },
1195
  {
1196
  "epoch": 0.2,
1197
- "grad_norm": 0.16015625,
1198
  "learning_rate": 0.00013205128205128204,
1199
- "loss": 1.6589,
1200
  "step": 153
1201
  },
1202
  {
1203
  "epoch": 0.2,
1204
- "grad_norm": 0.1787109375,
1205
  "learning_rate": 0.00013076923076923077,
1206
- "loss": 1.6143,
1207
  "step": 154
1208
  },
1209
  {
1210
  "epoch": 0.2,
1211
- "grad_norm": 0.166015625,
1212
  "learning_rate": 0.0001294871794871795,
1213
- "loss": 1.6815,
1214
  "step": 155
1215
  },
1216
  {
1217
  "epoch": 0.2,
1218
- "grad_norm": 0.158203125,
1219
  "learning_rate": 0.00012820512820512823,
1220
- "loss": 1.6267,
1221
  "step": 156
1222
  },
1223
  {
1224
  "epoch": 0.2,
1225
- "grad_norm": 0.1630859375,
1226
  "learning_rate": 0.00012692307692307693,
1227
- "loss": 1.6705,
1228
  "step": 157
1229
  },
1230
  {
1231
  "epoch": 0.2,
1232
- "grad_norm": 0.1796875,
1233
  "learning_rate": 0.00012564102564102564,
1234
- "loss": 1.6853,
1235
  "step": 158
1236
  },
1237
  {
1238
  "epoch": 0.2,
1239
- "grad_norm": 0.16015625,
1240
  "learning_rate": 0.00012435897435897437,
1241
- "loss": 1.6755,
1242
  "step": 159
1243
  },
1244
  {
1245
  "epoch": 0.2,
1246
- "grad_norm": 0.1572265625,
1247
  "learning_rate": 0.0001230769230769231,
1248
- "loss": 1.6165,
1249
  "step": 160
1250
  },
1251
  {
1252
  "epoch": 0.2,
1253
- "eval_loss": 1.6526222229003906,
1254
- "eval_runtime": 126.3096,
1255
- "eval_samples_per_second": 39.585,
1256
- "eval_steps_per_second": 1.243,
1257
  "step": 160
1258
  },
1259
  {
1260
  "epoch": 0.21,
1261
- "grad_norm": 0.166015625,
1262
  "learning_rate": 0.00012179487179487179,
1263
- "loss": 1.6913,
1264
  "step": 161
1265
  },
1266
  {
1267
  "epoch": 0.21,
1268
- "grad_norm": 0.162109375,
1269
  "learning_rate": 0.00012051282051282052,
1270
- "loss": 1.6403,
1271
  "step": 162
1272
  },
1273
  {
1274
  "epoch": 0.21,
1275
- "grad_norm": 0.162109375,
1276
  "learning_rate": 0.00011923076923076923,
1277
- "loss": 1.6667,
1278
  "step": 163
1279
  },
1280
  {
1281
  "epoch": 0.21,
1282
- "grad_norm": 0.1748046875,
1283
  "learning_rate": 0.00011794871794871796,
1284
- "loss": 1.616,
1285
  "step": 164
1286
  },
1287
  {
1288
  "epoch": 0.21,
1289
- "grad_norm": 0.177734375,
1290
  "learning_rate": 0.00011666666666666668,
1291
- "loss": 1.5773,
1292
  "step": 165
1293
  },
1294
  {
1295
  "epoch": 0.21,
1296
- "grad_norm": 0.1884765625,
1297
  "learning_rate": 0.00011538461538461538,
1298
- "loss": 1.6668,
1299
  "step": 166
1300
  },
1301
  {
1302
  "epoch": 0.21,
1303
- "grad_norm": 0.1708984375,
1304
  "learning_rate": 0.0001141025641025641,
1305
- "loss": 1.6904,
1306
  "step": 167
1307
  },
1308
  {
1309
  "epoch": 0.21,
1310
- "grad_norm": 0.177734375,
1311
  "learning_rate": 0.00011282051282051283,
1312
- "loss": 1.6935,
1313
  "step": 168
1314
  },
1315
  {
1316
  "epoch": 0.22,
1317
- "grad_norm": 0.1640625,
1318
  "learning_rate": 0.00011153846153846154,
1319
- "loss": 1.6615,
1320
  "step": 169
1321
  },
1322
  {
1323
  "epoch": 0.22,
1324
- "grad_norm": 0.185546875,
1325
  "learning_rate": 0.00011025641025641027,
1326
- "loss": 1.7506,
1327
  "step": 170
1328
  },
1329
  {
1330
  "epoch": 0.22,
1331
- "eval_loss": 1.650907278060913,
1332
- "eval_runtime": 125.9533,
1333
- "eval_samples_per_second": 39.697,
1334
- "eval_steps_per_second": 1.246,
1335
  "step": 170
1336
  },
1337
  {
1338
  "epoch": 0.22,
1339
- "grad_norm": 0.2158203125,
1340
  "learning_rate": 0.00010897435897435896,
1341
- "loss": 1.6593,
1342
  "step": 171
1343
  },
1344
  {
1345
  "epoch": 0.22,
1346
- "grad_norm": 0.166015625,
1347
  "learning_rate": 0.0001076923076923077,
1348
- "loss": 1.6011,
1349
  "step": 172
1350
  },
1351
  {
1352
  "epoch": 0.22,
1353
- "grad_norm": 0.171875,
1354
  "learning_rate": 0.00010641025641025641,
1355
- "loss": 1.675,
1356
  "step": 173
1357
  },
1358
  {
1359
  "epoch": 0.22,
1360
- "grad_norm": 0.177734375,
1361
  "learning_rate": 0.00010512820512820514,
1362
- "loss": 1.6491,
1363
  "step": 174
1364
  },
1365
  {
1366
  "epoch": 0.22,
1367
- "grad_norm": 0.169921875,
1368
  "learning_rate": 0.00010384615384615386,
1369
- "loss": 1.7251,
1370
  "step": 175
1371
  },
1372
  {
1373
  "epoch": 0.23,
1374
- "grad_norm": 0.1669921875,
1375
  "learning_rate": 0.00010256410256410256,
1376
- "loss": 1.6881,
1377
  "step": 176
1378
  },
1379
  {
1380
  "epoch": 0.23,
1381
- "grad_norm": 0.177734375,
1382
  "learning_rate": 0.00010128205128205129,
1383
- "loss": 1.6465,
1384
  "step": 177
1385
  },
1386
  {
1387
  "epoch": 0.23,
1388
- "grad_norm": 0.1943359375,
1389
  "learning_rate": 0.0001,
1390
- "loss": 1.6203,
1391
  "step": 178
1392
  },
1393
  {
1394
  "epoch": 0.23,
1395
- "grad_norm": 0.18359375,
1396
  "learning_rate": 9.871794871794872e-05,
1397
- "loss": 1.6638,
1398
  "step": 179
1399
  },
1400
  {
1401
  "epoch": 0.23,
1402
- "grad_norm": 0.1904296875,
1403
  "learning_rate": 9.743589743589744e-05,
1404
- "loss": 1.6636,
1405
  "step": 180
1406
  },
1407
  {
1408
  "epoch": 0.23,
1409
- "eval_loss": 1.6491334438323975,
1410
- "eval_runtime": 126.2676,
1411
- "eval_samples_per_second": 39.598,
1412
- "eval_steps_per_second": 1.243,
1413
  "step": 180
1414
  },
1415
  {
1416
  "epoch": 0.23,
1417
- "grad_norm": 0.1767578125,
1418
  "learning_rate": 9.615384615384617e-05,
1419
- "loss": 1.6722,
1420
  "step": 181
1421
  },
1422
  {
1423
  "epoch": 0.23,
1424
- "grad_norm": 0.158203125,
1425
  "learning_rate": 9.487179487179487e-05,
1426
- "loss": 1.6301,
1427
  "step": 182
1428
  },
1429
  {
1430
  "epoch": 0.23,
1431
- "grad_norm": 0.1728515625,
1432
  "learning_rate": 9.35897435897436e-05,
1433
- "loss": 1.6467,
1434
  "step": 183
1435
  },
1436
  {
1437
  "epoch": 0.24,
1438
- "grad_norm": 0.1904296875,
1439
  "learning_rate": 9.230769230769232e-05,
1440
- "loss": 1.6395,
1441
  "step": 184
1442
  },
1443
  {
1444
  "epoch": 0.24,
1445
- "grad_norm": 0.1689453125,
1446
  "learning_rate": 9.102564102564103e-05,
1447
- "loss": 1.7357,
1448
  "step": 185
1449
  },
1450
  {
1451
  "epoch": 0.24,
1452
- "grad_norm": 0.169921875,
1453
  "learning_rate": 8.974358974358975e-05,
1454
- "loss": 1.6724,
1455
  "step": 186
1456
  },
1457
  {
1458
  "epoch": 0.24,
1459
- "grad_norm": 0.185546875,
1460
  "learning_rate": 8.846153846153847e-05,
1461
- "loss": 1.7003,
1462
  "step": 187
1463
  },
1464
  {
1465
  "epoch": 0.24,
1466
- "grad_norm": 0.1787109375,
1467
  "learning_rate": 8.717948717948718e-05,
1468
- "loss": 1.6373,
1469
  "step": 188
1470
  },
1471
  {
1472
  "epoch": 0.24,
1473
- "grad_norm": 0.185546875,
1474
  "learning_rate": 8.58974358974359e-05,
1475
- "loss": 1.699,
1476
  "step": 189
1477
  },
1478
  {
1479
  "epoch": 0.24,
1480
- "grad_norm": 0.1748046875,
1481
  "learning_rate": 8.461538461538461e-05,
1482
- "loss": 1.6927,
1483
  "step": 190
1484
  },
1485
  {
1486
  "epoch": 0.24,
1487
- "eval_loss": 1.64810311794281,
1488
- "eval_runtime": 126.1264,
1489
- "eval_samples_per_second": 39.643,
1490
- "eval_steps_per_second": 1.245,
1491
  "step": 190
1492
  },
1493
  {
1494
  "epoch": 0.24,
1495
- "grad_norm": 0.177734375,
1496
  "learning_rate": 8.333333333333334e-05,
1497
- "loss": 1.6843,
1498
  "step": 191
1499
  },
1500
  {
1501
  "epoch": 0.25,
1502
- "grad_norm": 0.18359375,
1503
  "learning_rate": 8.205128205128205e-05,
1504
- "loss": 1.7133,
1505
  "step": 192
1506
  },
1507
  {
1508
  "epoch": 0.25,
1509
- "grad_norm": 0.1669921875,
1510
  "learning_rate": 8.076923076923078e-05,
1511
- "loss": 1.5758,
1512
  "step": 193
1513
  },
1514
  {
1515
  "epoch": 0.25,
1516
- "grad_norm": 0.1630859375,
1517
  "learning_rate": 7.948717948717948e-05,
1518
- "loss": 1.7406,
1519
  "step": 194
1520
  },
1521
  {
1522
  "epoch": 0.25,
1523
- "grad_norm": 0.169921875,
1524
  "learning_rate": 7.820512820512821e-05,
1525
- "loss": 1.6312,
1526
  "step": 195
1527
  },
1528
  {
1529
  "epoch": 0.25,
1530
- "grad_norm": 0.1669921875,
1531
  "learning_rate": 7.692307692307693e-05,
1532
- "loss": 1.6398,
1533
  "step": 196
1534
  },
1535
  {
1536
  "epoch": 0.25,
1537
- "grad_norm": 0.1767578125,
1538
  "learning_rate": 7.564102564102564e-05,
1539
- "loss": 1.6418,
1540
  "step": 197
1541
  },
1542
  {
1543
  "epoch": 0.25,
1544
- "grad_norm": 0.1591796875,
1545
  "learning_rate": 7.435897435897436e-05,
1546
- "loss": 1.6438,
1547
  "step": 198
1548
  },
1549
  {
1550
  "epoch": 0.25,
1551
- "grad_norm": 0.169921875,
1552
  "learning_rate": 7.307692307692307e-05,
1553
- "loss": 1.6514,
1554
  "step": 199
1555
  },
1556
  {
1557
  "epoch": 0.26,
1558
- "grad_norm": 0.1943359375,
1559
  "learning_rate": 7.17948717948718e-05,
1560
- "loss": 1.631,
1561
  "step": 200
1562
  },
1563
  {
1564
  "epoch": 0.26,
1565
- "eval_loss": 1.6470773220062256,
1566
- "eval_runtime": 126.2841,
1567
- "eval_samples_per_second": 39.593,
1568
- "eval_steps_per_second": 1.243,
1569
  "step": 200
1570
  },
1571
  {
1572
  "epoch": 0.26,
1573
- "grad_norm": 0.1904296875,
1574
  "learning_rate": 7.051282051282052e-05,
1575
- "loss": 1.6412,
1576
  "step": 201
1577
  },
1578
  {
1579
  "epoch": 0.26,
1580
- "grad_norm": 0.1728515625,
1581
  "learning_rate": 6.923076923076924e-05,
1582
- "loss": 1.7023,
1583
  "step": 202
1584
  },
1585
  {
1586
  "epoch": 0.26,
1587
- "grad_norm": 0.1708984375,
1588
  "learning_rate": 6.794871794871795e-05,
1589
- "loss": 1.7129,
1590
  "step": 203
1591
  },
1592
  {
1593
  "epoch": 0.26,
1594
- "grad_norm": 0.17578125,
1595
  "learning_rate": 6.666666666666667e-05,
1596
- "loss": 1.6855,
1597
  "step": 204
1598
  },
1599
  {
1600
  "epoch": 0.26,
1601
- "grad_norm": 0.18359375,
1602
  "learning_rate": 6.538461538461539e-05,
1603
- "loss": 1.6017,
1604
  "step": 205
1605
  },
1606
  {
1607
  "epoch": 0.26,
1608
- "grad_norm": 0.1787109375,
1609
  "learning_rate": 6.410256410256412e-05,
1610
- "loss": 1.6791,
1611
  "step": 206
1612
  },
1613
  {
1614
  "epoch": 0.26,
1615
- "grad_norm": 0.1767578125,
1616
  "learning_rate": 6.282051282051282e-05,
1617
- "loss": 1.5874,
1618
  "step": 207
1619
  },
1620
  {
1621
  "epoch": 0.27,
1622
- "grad_norm": 0.166015625,
1623
  "learning_rate": 6.153846153846155e-05,
1624
- "loss": 1.6805,
1625
  "step": 208
1626
  },
1627
  {
1628
  "epoch": 0.27,
1629
- "grad_norm": 0.2041015625,
1630
  "learning_rate": 6.025641025641026e-05,
1631
- "loss": 1.6416,
1632
  "step": 209
1633
  },
1634
  {
1635
  "epoch": 0.27,
1636
- "grad_norm": 0.1650390625,
1637
  "learning_rate": 5.897435897435898e-05,
1638
- "loss": 1.7009,
1639
  "step": 210
1640
  },
1641
  {
1642
  "epoch": 0.27,
1643
- "eval_loss": 1.64640212059021,
1644
- "eval_runtime": 126.2026,
1645
- "eval_samples_per_second": 39.619,
1646
- "eval_steps_per_second": 1.244,
1647
  "step": 210
1648
  },
1649
  {
1650
  "epoch": 0.27,
1651
- "grad_norm": 0.1787109375,
1652
  "learning_rate": 5.769230769230769e-05,
1653
- "loss": 1.6571,
1654
  "step": 211
1655
  },
1656
  {
1657
  "epoch": 0.27,
1658
- "grad_norm": 0.1875,
1659
  "learning_rate": 5.6410256410256414e-05,
1660
- "loss": 1.6447,
1661
  "step": 212
1662
  },
1663
  {
1664
  "epoch": 0.27,
1665
- "grad_norm": 0.173828125,
1666
  "learning_rate": 5.512820512820514e-05,
1667
- "loss": 1.6619,
1668
  "step": 213
1669
  },
1670
  {
1671
  "epoch": 0.27,
1672
- "grad_norm": 0.1728515625,
1673
  "learning_rate": 5.384615384615385e-05,
1674
- "loss": 1.6299,
1675
  "step": 214
1676
  },
1677
  {
1678
  "epoch": 0.28,
1679
- "grad_norm": 0.185546875,
1680
  "learning_rate": 5.256410256410257e-05,
1681
- "loss": 1.59,
1682
  "step": 215
1683
  },
1684
  {
1685
  "epoch": 0.28,
1686
- "grad_norm": 0.1826171875,
1687
  "learning_rate": 5.128205128205128e-05,
1688
- "loss": 1.6238,
1689
  "step": 216
1690
  },
1691
  {
1692
  "epoch": 0.28,
1693
- "grad_norm": 0.2041015625,
1694
  "learning_rate": 5e-05,
1695
- "loss": 1.673,
1696
  "step": 217
1697
  },
1698
  {
1699
  "epoch": 0.28,
1700
- "grad_norm": 0.1806640625,
1701
  "learning_rate": 4.871794871794872e-05,
1702
- "loss": 1.6962,
1703
  "step": 218
1704
  },
1705
  {
1706
  "epoch": 0.28,
1707
- "grad_norm": 0.1796875,
1708
  "learning_rate": 4.7435897435897435e-05,
1709
- "loss": 1.6256,
1710
  "step": 219
1711
  },
1712
  {
1713
  "epoch": 0.28,
1714
- "grad_norm": 0.177734375,
1715
  "learning_rate": 4.615384615384616e-05,
1716
- "loss": 1.6825,
1717
  "step": 220
1718
  },
1719
  {
1720
  "epoch": 0.28,
1721
- "eval_loss": 1.645533561706543,
1722
- "eval_runtime": 126.1441,
1723
- "eval_samples_per_second": 39.637,
1724
- "eval_steps_per_second": 1.245,
1725
  "step": 220
1726
  },
1727
  {
1728
  "epoch": 0.28,
1729
- "grad_norm": 0.2021484375,
1730
  "learning_rate": 4.4871794871794874e-05,
1731
- "loss": 1.6856,
1732
  "step": 221
1733
  },
1734
  {
1735
  "epoch": 0.28,
1736
- "grad_norm": 0.1728515625,
1737
  "learning_rate": 4.358974358974359e-05,
1738
- "loss": 1.6845,
1739
  "step": 222
1740
  },
1741
  {
1742
  "epoch": 0.29,
1743
- "grad_norm": 0.1728515625,
1744
  "learning_rate": 4.230769230769231e-05,
1745
- "loss": 1.6687,
1746
  "step": 223
1747
  },
1748
  {
1749
  "epoch": 0.29,
1750
- "grad_norm": 0.1650390625,
1751
  "learning_rate": 4.1025641025641023e-05,
1752
- "loss": 1.6538,
1753
  "step": 224
1754
  },
1755
  {
1756
  "epoch": 0.29,
1757
- "grad_norm": 0.2109375,
1758
  "learning_rate": 3.974358974358974e-05,
1759
- "loss": 1.6264,
1760
  "step": 225
1761
  },
1762
  {
1763
  "epoch": 0.29,
1764
- "grad_norm": 0.185546875,
1765
  "learning_rate": 3.846153846153846e-05,
1766
- "loss": 1.5731,
1767
  "step": 226
1768
  },
1769
  {
1770
  "epoch": 0.29,
1771
- "grad_norm": 0.162109375,
1772
  "learning_rate": 3.717948717948718e-05,
1773
- "loss": 1.6814,
1774
  "step": 227
1775
  },
1776
  {
1777
  "epoch": 0.29,
1778
- "grad_norm": 0.18359375,
1779
  "learning_rate": 3.58974358974359e-05,
1780
- "loss": 1.662,
1781
  "step": 228
1782
  },
1783
  {
1784
  "epoch": 0.29,
1785
- "grad_norm": 0.1884765625,
1786
  "learning_rate": 3.461538461538462e-05,
1787
- "loss": 1.5692,
1788
  "step": 229
1789
  },
1790
  {
1791
  "epoch": 0.29,
1792
- "grad_norm": 0.1767578125,
1793
  "learning_rate": 3.3333333333333335e-05,
1794
- "loss": 1.6712,
1795
  "step": 230
1796
  },
1797
  {
1798
  "epoch": 0.29,
1799
- "eval_loss": 1.6453105211257935,
1800
- "eval_runtime": 125.1792,
1801
- "eval_samples_per_second": 39.943,
1802
- "eval_steps_per_second": 1.254,
1803
  "step": 230
1804
  },
1805
  {
1806
  "epoch": 0.3,
1807
- "grad_norm": 0.2021484375,
1808
  "learning_rate": 3.205128205128206e-05,
1809
- "loss": 1.67,
1810
  "step": 231
1811
  },
1812
  {
1813
  "epoch": 0.3,
1814
- "grad_norm": 0.1796875,
1815
  "learning_rate": 3.0769230769230774e-05,
1816
- "loss": 1.5761,
1817
  "step": 232
1818
  },
1819
  {
1820
  "epoch": 0.3,
1821
- "grad_norm": 0.1875,
1822
  "learning_rate": 2.948717948717949e-05,
1823
- "loss": 1.6017,
1824
  "step": 233
1825
  },
1826
  {
1827
  "epoch": 0.3,
1828
- "grad_norm": 0.1982421875,
1829
  "learning_rate": 2.8205128205128207e-05,
1830
- "loss": 1.684,
1831
  "step": 234
1832
  },
1833
  {
1834
  "epoch": 0.3,
1835
- "grad_norm": 0.18359375,
1836
  "learning_rate": 2.6923076923076923e-05,
1837
- "loss": 1.6708,
1838
  "step": 235
1839
  },
1840
  {
1841
  "epoch": 0.3,
1842
- "grad_norm": 0.1865234375,
1843
  "learning_rate": 2.564102564102564e-05,
1844
- "loss": 1.6748,
1845
  "step": 236
1846
  },
1847
  {
1848
  "epoch": 0.3,
1849
- "grad_norm": 0.17578125,
1850
  "learning_rate": 2.435897435897436e-05,
1851
- "loss": 1.6203,
1852
  "step": 237
1853
  },
1854
  {
1855
  "epoch": 0.3,
1856
- "grad_norm": 0.1904296875,
1857
  "learning_rate": 2.307692307692308e-05,
1858
- "loss": 1.6658,
1859
  "step": 238
1860
  },
1861
  {
1862
  "epoch": 0.31,
1863
- "grad_norm": 0.173828125,
1864
  "learning_rate": 2.1794871794871795e-05,
1865
- "loss": 1.7107,
1866
  "step": 239
1867
  },
1868
  {
1869
  "epoch": 0.31,
1870
- "grad_norm": 0.1953125,
1871
  "learning_rate": 2.0512820512820512e-05,
1872
- "loss": 1.6987,
1873
  "step": 240
1874
  },
1875
  {
1876
  "epoch": 0.31,
1877
- "eval_loss": 1.6449843645095825,
1878
- "eval_runtime": 125.1567,
1879
- "eval_samples_per_second": 39.95,
1880
- "eval_steps_per_second": 1.254,
1881
  "step": 240
1882
  },
1883
  {
1884
  "epoch": 0.31,
1885
- "grad_norm": 0.1806640625,
1886
  "learning_rate": 1.923076923076923e-05,
1887
- "loss": 1.6973,
1888
  "step": 241
1889
  },
1890
  {
1891
  "epoch": 0.31,
1892
- "grad_norm": 0.1875,
1893
  "learning_rate": 1.794871794871795e-05,
1894
- "loss": 1.5889,
1895
  "step": 242
1896
  },
1897
  {
1898
  "epoch": 0.31,
1899
- "grad_norm": 0.1845703125,
1900
  "learning_rate": 1.6666666666666667e-05,
1901
- "loss": 1.6322,
1902
  "step": 243
1903
  },
1904
  {
1905
  "epoch": 0.31,
1906
- "grad_norm": 0.1953125,
1907
  "learning_rate": 1.5384615384615387e-05,
1908
- "loss": 1.611,
1909
  "step": 244
1910
  },
1911
  {
1912
  "epoch": 0.31,
1913
- "grad_norm": 0.169921875,
1914
  "learning_rate": 1.4102564102564104e-05,
1915
- "loss": 1.7048,
1916
  "step": 245
1917
  },
1918
  {
1919
  "epoch": 0.31,
1920
- "grad_norm": 0.1796875,
1921
  "learning_rate": 1.282051282051282e-05,
1922
- "loss": 1.6283,
1923
  "step": 246
1924
  },
1925
  {
1926
  "epoch": 0.32,
1927
- "grad_norm": 0.1748046875,
1928
  "learning_rate": 1.153846153846154e-05,
1929
- "loss": 1.6868,
1930
  "step": 247
1931
  },
1932
  {
1933
  "epoch": 0.32,
1934
- "grad_norm": 0.1943359375,
1935
  "learning_rate": 1.0256410256410256e-05,
1936
- "loss": 1.7102,
1937
  "step": 248
1938
  },
1939
  {
1940
  "epoch": 0.32,
1941
- "grad_norm": 0.193359375,
1942
  "learning_rate": 8.974358974358976e-06,
1943
- "loss": 1.6453,
1944
  "step": 249
1945
  },
1946
  {
1947
  "epoch": 0.32,
1948
- "grad_norm": 0.1796875,
1949
  "learning_rate": 7.692307692307694e-06,
1950
- "loss": 1.6217,
1951
  "step": 250
1952
  },
1953
  {
1954
  "epoch": 0.32,
1955
- "eval_loss": 1.6449463367462158,
1956
- "eval_runtime": 126.0264,
1957
- "eval_samples_per_second": 39.674,
1958
- "eval_steps_per_second": 1.246,
1959
  "step": 250
1960
  },
1961
  {
1962
  "epoch": 0.32,
1963
- "grad_norm": 0.189453125,
1964
  "learning_rate": 6.41025641025641e-06,
1965
- "loss": 1.7208,
1966
  "step": 251
1967
  },
1968
  {
1969
  "epoch": 0.32,
1970
- "grad_norm": 0.181640625,
1971
  "learning_rate": 5.128205128205128e-06,
1972
- "loss": 1.6421,
1973
  "step": 252
1974
  },
1975
  {
1976
  "epoch": 0.32,
1977
- "grad_norm": 0.1982421875,
1978
  "learning_rate": 3.846153846153847e-06,
1979
- "loss": 1.5272,
1980
  "step": 253
1981
  },
1982
  {
1983
  "epoch": 0.33,
1984
- "grad_norm": 0.1708984375,
1985
  "learning_rate": 2.564102564102564e-06,
1986
- "loss": 1.5856,
1987
  "step": 254
1988
  },
1989
  {
1990
  "epoch": 0.33,
1991
- "grad_norm": 0.1748046875,
1992
  "learning_rate": 1.282051282051282e-06,
1993
- "loss": 1.6374,
1994
  "step": 255
1995
  },
1996
  {
1997
  "epoch": 0.33,
1998
- "grad_norm": 0.1767578125,
1999
  "learning_rate": 0.0,
2000
- "loss": 1.6896,
2001
  "step": 256
2002
  },
2003
  {
2004
  "epoch": 0.33,
2005
  "step": 256,
2006
- "total_flos": 1.813217341042852e+17,
2007
- "train_loss": 1.7538025458343327,
2008
- "train_runtime": 4604.2872,
2009
- "train_samples_per_second": 3.558,
2010
- "train_steps_per_second": 0.056
2011
  },
2012
  {
2013
  "epoch": 0.33,
2014
- "eval_loss": 1.6449463367462158,
2015
- "eval_runtime": 125.933,
2016
- "eval_samples_per_second": 39.704,
2017
- "eval_steps_per_second": 1.247,
2018
  "step": 256
2019
  }
2020
  ],
@@ -2023,7 +2023,7 @@
2023
  "num_input_tokens_seen": 0,
2024
  "num_train_epochs": 1,
2025
  "save_steps": 10,
2026
- "total_flos": 1.813217341042852e+17,
2027
  "train_batch_size": 32,
2028
  "trial_name": null,
2029
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.810941219329834,
3
+ "best_model_checkpoint": "lora_lr/google/gemma-1.1-7b-it/unaligned/checkpoint-250",
4
  "epoch": 0.327575175943698,
5
  "eval_steps": 10,
6
  "global_step": 256,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.0,
13
+ "grad_norm": 1.015625,
14
  "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 4.7488,
16
  "step": 1
17
  },
18
  {
19
  "epoch": 0.0,
20
+ "grad_norm": 0.94140625,
21
  "learning_rate": 4.000000000000001e-06,
22
+ "loss": 4.5149,
23
  "step": 2
24
  },
25
  {
26
  "epoch": 0.0,
27
+ "grad_norm": 0.9140625,
28
  "learning_rate": 6e-06,
29
+ "loss": 4.3894,
30
  "step": 3
31
  },
32
  {
33
  "epoch": 0.01,
34
+ "grad_norm": 1.0078125,
35
  "learning_rate": 8.000000000000001e-06,
36
+ "loss": 4.6734,
37
  "step": 4
38
  },
39
  {
40
  "epoch": 0.01,
41
+ "grad_norm": 1.0,
42
  "learning_rate": 1e-05,
43
+ "loss": 4.6616,
44
  "step": 5
45
  },
46
  {
47
  "epoch": 0.01,
48
+ "grad_norm": 0.921875,
49
  "learning_rate": 1.2e-05,
50
+ "loss": 4.5625,
51
  "step": 6
52
  },
53
  {
54
  "epoch": 0.01,
55
+ "grad_norm": 0.9765625,
56
  "learning_rate": 1.4000000000000001e-05,
57
+ "loss": 4.5709,
58
  "step": 7
59
  },
60
  {
61
  "epoch": 0.01,
62
+ "grad_norm": 0.99609375,
63
  "learning_rate": 1.6000000000000003e-05,
64
+ "loss": 4.6627,
65
  "step": 8
66
  },
67
  {
68
  "epoch": 0.01,
69
+ "grad_norm": 1.0390625,
70
  "learning_rate": 1.8e-05,
71
+ "loss": 4.5995,
72
  "step": 9
73
  },
74
  {
75
  "epoch": 0.01,
76
+ "grad_norm": 1.0390625,
77
  "learning_rate": 2e-05,
78
+ "loss": 4.7668,
79
  "step": 10
80
  },
81
  {
82
  "epoch": 0.01,
83
+ "eval_loss": 4.575911521911621,
84
+ "eval_runtime": 126.7034,
85
+ "eval_samples_per_second": 39.462,
86
+ "eval_steps_per_second": 1.239,
87
  "step": 10
88
  },
89
  {
90
  "epoch": 0.01,
91
+ "grad_norm": 1.03125,
92
  "learning_rate": 2.2000000000000003e-05,
93
+ "loss": 4.5432,
94
  "step": 11
95
  },
96
  {
97
  "epoch": 0.02,
98
+ "grad_norm": 0.9296875,
99
  "learning_rate": 2.4e-05,
100
+ "loss": 4.2969,
101
  "step": 12
102
  },
103
  {
104
  "epoch": 0.02,
105
+ "grad_norm": 1.1015625,
106
  "learning_rate": 2.6000000000000002e-05,
107
+ "loss": 4.8134,
108
  "step": 13
109
  },
110
  {
111
  "epoch": 0.02,
112
+ "grad_norm": 1.109375,
113
  "learning_rate": 2.8000000000000003e-05,
114
+ "loss": 4.6818,
115
  "step": 14
116
  },
117
  {
118
  "epoch": 0.02,
119
+ "grad_norm": 1.1171875,
120
  "learning_rate": 3e-05,
121
+ "loss": 4.5194,
122
  "step": 15
123
  },
124
  {
125
  "epoch": 0.02,
126
+ "grad_norm": 1.1015625,
127
  "learning_rate": 3.2000000000000005e-05,
128
+ "loss": 4.3755,
129
  "step": 16
130
  },
131
  {
132
  "epoch": 0.02,
133
+ "grad_norm": 1.265625,
134
  "learning_rate": 3.4000000000000007e-05,
135
+ "loss": 4.5325,
136
  "step": 17
137
  },
138
  {
139
  "epoch": 0.02,
140
+ "grad_norm": 1.2265625,
141
  "learning_rate": 3.6e-05,
142
+ "loss": 4.3967,
143
  "step": 18
144
  },
145
  {
146
  "epoch": 0.02,
147
+ "grad_norm": 1.359375,
148
  "learning_rate": 3.8e-05,
149
+ "loss": 4.3274,
150
  "step": 19
151
  },
152
  {
153
  "epoch": 0.03,
154
+ "grad_norm": 1.375,
155
  "learning_rate": 4e-05,
156
+ "loss": 4.3029,
157
  "step": 20
158
  },
159
  {
160
  "epoch": 0.03,
161
+ "eval_loss": 4.288708686828613,
162
+ "eval_runtime": 126.1277,
163
+ "eval_samples_per_second": 39.642,
164
+ "eval_steps_per_second": 1.245,
165
  "step": 20
166
  },
167
  {
168
  "epoch": 0.03,
169
+ "grad_norm": 1.390625,
170
  "learning_rate": 4.2e-05,
171
+ "loss": 4.2266,
172
  "step": 21
173
  },
174
  {
175
  "epoch": 0.03,
176
+ "grad_norm": 1.5625,
177
  "learning_rate": 4.4000000000000006e-05,
178
+ "loss": 4.3114,
179
  "step": 22
180
  },
181
  {
182
  "epoch": 0.03,
183
+ "grad_norm": 1.609375,
184
  "learning_rate": 4.600000000000001e-05,
185
+ "loss": 4.2829,
186
  "step": 23
187
  },
188
  {
189
  "epoch": 0.03,
190
+ "grad_norm": 1.6796875,
191
  "learning_rate": 4.8e-05,
192
+ "loss": 4.1797,
193
  "step": 24
194
  },
195
  {
196
  "epoch": 0.03,
197
+ "grad_norm": 1.75,
198
  "learning_rate": 5e-05,
199
+ "loss": 4.0528,
200
  "step": 25
201
  },
202
  {
203
  "epoch": 0.03,
204
+ "grad_norm": 1.8359375,
205
  "learning_rate": 5.2000000000000004e-05,
206
+ "loss": 3.997,
207
  "step": 26
208
  },
209
  {
210
  "epoch": 0.03,
211
+ "grad_norm": 1.828125,
212
  "learning_rate": 5.4000000000000005e-05,
213
+ "loss": 3.9195,
214
  "step": 27
215
  },
216
  {
217
  "epoch": 0.04,
218
+ "grad_norm": 1.8203125,
219
  "learning_rate": 5.6000000000000006e-05,
220
+ "loss": 3.817,
221
  "step": 28
222
  },
223
  {
224
  "epoch": 0.04,
225
+ "grad_norm": 1.9296875,
226
  "learning_rate": 5.8e-05,
227
+ "loss": 3.8411,
228
  "step": 29
229
  },
230
  {
231
  "epoch": 0.04,
232
+ "grad_norm": 1.921875,
233
  "learning_rate": 6e-05,
234
+ "loss": 3.5259,
235
  "step": 30
236
  },
237
  {
238
  "epoch": 0.04,
239
+ "eval_loss": 3.5061299800872803,
240
+ "eval_runtime": 126.2241,
241
+ "eval_samples_per_second": 39.612,
242
+ "eval_steps_per_second": 1.244,
243
  "step": 30
244
  },
245
  {
246
  "epoch": 0.04,
247
+ "grad_norm": 2.0,
248
  "learning_rate": 6.2e-05,
249
+ "loss": 3.6587,
250
  "step": 31
251
  },
252
  {
253
  "epoch": 0.04,
254
+ "grad_norm": 1.765625,
255
  "learning_rate": 6.400000000000001e-05,
256
+ "loss": 3.3672,
257
  "step": 32
258
  },
259
  {
260
  "epoch": 0.04,
261
+ "grad_norm": 1.75,
262
  "learning_rate": 6.6e-05,
263
+ "loss": 3.3194,
264
  "step": 33
265
  },
266
  {
267
  "epoch": 0.04,
268
+ "grad_norm": 1.703125,
269
  "learning_rate": 6.800000000000001e-05,
270
+ "loss": 3.2215,
271
  "step": 34
272
  },
273
  {
274
  "epoch": 0.04,
275
+ "grad_norm": 1.6640625,
276
  "learning_rate": 7e-05,
277
+ "loss": 3.1773,
278
  "step": 35
279
  },
280
  {
281
  "epoch": 0.05,
282
+ "grad_norm": 1.546875,
283
  "learning_rate": 7.2e-05,
284
+ "loss": 2.9527,
285
  "step": 36
286
  },
287
  {
288
  "epoch": 0.05,
289
+ "grad_norm": 1.578125,
290
  "learning_rate": 7.4e-05,
291
+ "loss": 3.1381,
292
  "step": 37
293
  },
294
  {
295
  "epoch": 0.05,
296
+ "grad_norm": 1.453125,
297
  "learning_rate": 7.6e-05,
298
+ "loss": 2.947,
299
  "step": 38
300
  },
301
  {
302
  "epoch": 0.05,
303
+ "grad_norm": 1.2265625,
304
  "learning_rate": 7.800000000000001e-05,
305
+ "loss": 2.743,
306
  "step": 39
307
  },
308
  {
309
  "epoch": 0.05,
310
+ "grad_norm": 1.1171875,
311
  "learning_rate": 8e-05,
312
+ "loss": 2.6947,
313
  "step": 40
314
  },
315
  {
316
  "epoch": 0.05,
317
+ "eval_loss": 2.6360573768615723,
318
+ "eval_runtime": 125.9592,
319
+ "eval_samples_per_second": 39.695,
320
+ "eval_steps_per_second": 1.246,
321
  "step": 40
322
  },
323
  {
324
  "epoch": 0.05,
325
+ "grad_norm": 0.9453125,
326
  "learning_rate": 8.2e-05,
327
+ "loss": 2.6962,
328
  "step": 41
329
  },
330
  {
331
  "epoch": 0.05,
332
+ "grad_norm": 1.0390625,
333
  "learning_rate": 8.4e-05,
334
+ "loss": 2.6634,
335
  "step": 42
336
  },
337
  {
338
  "epoch": 0.06,
339
+ "grad_norm": 1.3203125,
340
  "learning_rate": 8.6e-05,
341
+ "loss": 2.5018,
342
  "step": 43
343
  },
344
  {
345
  "epoch": 0.06,
346
+ "grad_norm": 1.390625,
347
  "learning_rate": 8.800000000000001e-05,
348
+ "loss": 2.4608,
349
  "step": 44
350
  },
351
  {
352
  "epoch": 0.06,
353
+ "grad_norm": 1.328125,
354
  "learning_rate": 9e-05,
355
+ "loss": 2.425,
356
  "step": 45
357
  },
358
  {
359
  "epoch": 0.06,
360
+ "grad_norm": 0.5859375,
361
  "learning_rate": 9.200000000000001e-05,
362
+ "loss": 2.3978,
363
  "step": 46
364
  },
365
  {
366
  "epoch": 0.06,
367
+ "grad_norm": 0.5625,
368
  "learning_rate": 9.4e-05,
369
+ "loss": 2.3885,
370
  "step": 47
371
  },
372
  {
373
  "epoch": 0.06,
374
+ "grad_norm": 0.56640625,
375
  "learning_rate": 9.6e-05,
376
+ "loss": 2.373,
377
  "step": 48
378
  },
379
  {
380
  "epoch": 0.06,
381
+ "grad_norm": 0.64453125,
382
  "learning_rate": 9.8e-05,
383
+ "loss": 2.2775,
384
  "step": 49
385
  },
386
  {
387
  "epoch": 0.06,
388
+ "grad_norm": 0.609375,
389
  "learning_rate": 0.0001,
390
+ "loss": 2.3577,
391
  "step": 50
392
  },
393
  {
394
  "epoch": 0.06,
395
+ "eval_loss": 2.296643018722534,
396
+ "eval_runtime": 125.5906,
397
+ "eval_samples_per_second": 39.812,
398
+ "eval_steps_per_second": 1.25,
399
  "step": 50
400
  },
401
  {
402
  "epoch": 0.07,
403
+ "grad_norm": 0.5703125,
404
  "learning_rate": 0.00010200000000000001,
405
+ "loss": 2.447,
406
  "step": 51
407
  },
408
  {
409
  "epoch": 0.07,
410
+ "grad_norm": 0.59765625,
411
  "learning_rate": 0.00010400000000000001,
412
+ "loss": 2.2502,
413
  "step": 52
414
  },
415
  {
416
  "epoch": 0.07,
417
+ "grad_norm": 0.5546875,
418
  "learning_rate": 0.00010600000000000002,
419
+ "loss": 2.2093,
420
  "step": 53
421
  },
422
  {
423
  "epoch": 0.07,
424
+ "grad_norm": 0.8203125,
425
  "learning_rate": 0.00010800000000000001,
426
+ "loss": 2.2644,
427
  "step": 54
428
  },
429
  {
430
  "epoch": 0.07,
431
+ "grad_norm": 1.1171875,
432
  "learning_rate": 0.00011000000000000002,
433
+ "loss": 2.1485,
434
  "step": 55
435
  },
436
  {
437
  "epoch": 0.07,
438
+ "grad_norm": 0.92578125,
439
  "learning_rate": 0.00011200000000000001,
440
+ "loss": 2.1965,
441
  "step": 56
442
  },
443
  {
444
  "epoch": 0.07,
445
+ "grad_norm": 0.70703125,
446
  "learning_rate": 0.00011399999999999999,
447
+ "loss": 2.1916,
448
  "step": 57
449
  },
450
  {
451
  "epoch": 0.07,
452
+ "grad_norm": 0.53125,
453
  "learning_rate": 0.000116,
454
+ "loss": 2.2071,
455
  "step": 58
456
  },
457
  {
458
  "epoch": 0.08,
459
+ "grad_norm": 0.392578125,
460
  "learning_rate": 0.000118,
461
+ "loss": 2.1507,
462
  "step": 59
463
  },
464
  {
465
  "epoch": 0.08,
466
+ "grad_norm": 0.447265625,
467
  "learning_rate": 0.00012,
468
+ "loss": 2.1582,
469
  "step": 60
470
  },
471
  {
472
  "epoch": 0.08,
473
+ "eval_loss": 2.1068594455718994,
474
+ "eval_runtime": 124.951,
475
+ "eval_samples_per_second": 40.016,
476
+ "eval_steps_per_second": 1.256,
477
  "step": 60
478
  },
479
  {
480
  "epoch": 0.08,
481
+ "grad_norm": 0.3984375,
482
  "learning_rate": 0.000122,
483
+ "loss": 2.1486,
484
  "step": 61
485
  },
486
  {
487
  "epoch": 0.08,
488
+ "grad_norm": 0.38671875,
489
  "learning_rate": 0.000124,
490
+ "loss": 2.1137,
491
  "step": 62
492
  },
493
  {
494
  "epoch": 0.08,
495
+ "grad_norm": 0.65625,
496
  "learning_rate": 0.000126,
497
+ "loss": 2.1276,
498
  "step": 63
499
  },
500
  {
501
  "epoch": 0.08,
502
+ "grad_norm": 0.43359375,
503
  "learning_rate": 0.00012800000000000002,
504
+ "loss": 2.0382,
505
  "step": 64
506
  },
507
  {
508
  "epoch": 0.08,
509
+ "grad_norm": 0.5546875,
510
  "learning_rate": 0.00013000000000000002,
511
+ "loss": 2.118,
512
  "step": 65
513
  },
514
  {
515
  "epoch": 0.08,
516
+ "grad_norm": 0.94921875,
517
  "learning_rate": 0.000132,
518
+ "loss": 2.1625,
519
  "step": 66
520
  },
521
  {
522
  "epoch": 0.09,
523
+ "grad_norm": 0.443359375,
524
  "learning_rate": 0.000134,
525
+ "loss": 2.0544,
526
  "step": 67
527
  },
528
  {
529
  "epoch": 0.09,
530
+ "grad_norm": 0.36328125,
531
  "learning_rate": 0.00013600000000000003,
532
+ "loss": 2.0529,
533
  "step": 68
534
  },
535
  {
536
  "epoch": 0.09,
537
+ "grad_norm": 0.353515625,
538
  "learning_rate": 0.000138,
539
+ "loss": 2.0054,
540
  "step": 69
541
  },
542
  {
543
  "epoch": 0.09,
544
+ "grad_norm": 0.35546875,
545
  "learning_rate": 0.00014,
546
+ "loss": 2.0338,
547
  "step": 70
548
  },
549
  {
550
  "epoch": 0.09,
551
+ "eval_loss": 2.0194942951202393,
552
+ "eval_runtime": 125.4346,
553
+ "eval_samples_per_second": 39.861,
554
+ "eval_steps_per_second": 1.252,
555
  "step": 70
556
  },
557
  {
558
  "epoch": 0.09,
559
+ "grad_norm": 0.384765625,
560
  "learning_rate": 0.000142,
561
+ "loss": 2.0377,
562
  "step": 71
563
  },
564
  {
565
  "epoch": 0.09,
566
+ "grad_norm": 0.3515625,
567
  "learning_rate": 0.000144,
568
+ "loss": 2.0574,
569
  "step": 72
570
  },
571
  {
572
  "epoch": 0.09,
573
+ "grad_norm": 0.375,
574
  "learning_rate": 0.000146,
575
+ "loss": 1.9926,
576
  "step": 73
577
  },
578
  {
579
  "epoch": 0.09,
580
+ "grad_norm": 0.322265625,
581
  "learning_rate": 0.000148,
582
+ "loss": 2.1027,
583
  "step": 74
584
  },
585
  {
586
  "epoch": 0.1,
587
+ "grad_norm": 0.33984375,
588
  "learning_rate": 0.00015000000000000001,
589
+ "loss": 2.0283,
590
  "step": 75
591
  },
592
  {
593
  "epoch": 0.1,
594
+ "grad_norm": 0.28125,
595
  "learning_rate": 0.000152,
596
+ "loss": 1.9844,
597
  "step": 76
598
  },
599
  {
600
  "epoch": 0.1,
601
+ "grad_norm": 0.291015625,
602
  "learning_rate": 0.000154,
603
+ "loss": 2.0037,
604
  "step": 77
605
  },
606
  {
607
  "epoch": 0.1,
608
+ "grad_norm": 0.23046875,
609
  "learning_rate": 0.00015600000000000002,
610
+ "loss": 1.9911,
611
  "step": 78
612
  },
613
  {
614
  "epoch": 0.1,
615
+ "grad_norm": 0.353515625,
616
  "learning_rate": 0.00015800000000000002,
617
+ "loss": 1.933,
618
  "step": 79
619
  },
620
  {
621
  "epoch": 0.1,
622
+ "grad_norm": 0.69140625,
623
  "learning_rate": 0.00016,
624
+ "loss": 1.9856,
625
  "step": 80
626
  },
627
  {
628
  "epoch": 0.1,
629
+ "eval_loss": 1.9626843929290771,
630
+ "eval_runtime": 125.5025,
631
+ "eval_samples_per_second": 39.84,
632
+ "eval_steps_per_second": 1.251,
633
  "step": 80
634
  },
635
  {
636
  "epoch": 0.1,
637
+ "grad_norm": 0.26171875,
638
  "learning_rate": 0.000162,
639
+ "loss": 1.9761,
640
  "step": 81
641
  },
642
  {
643
  "epoch": 0.1,
644
+ "grad_norm": 0.2734375,
645
  "learning_rate": 0.000164,
646
+ "loss": 1.9205,
647
  "step": 82
648
  },
649
  {
650
  "epoch": 0.11,
651
+ "grad_norm": 0.279296875,
652
  "learning_rate": 0.000166,
653
+ "loss": 1.9885,
654
  "step": 83
655
  },
656
  {
657
  "epoch": 0.11,
658
+ "grad_norm": 0.291015625,
659
  "learning_rate": 0.000168,
660
+ "loss": 1.9419,
661
  "step": 84
662
  },
663
  {
664
  "epoch": 0.11,
665
+ "grad_norm": 0.298828125,
666
  "learning_rate": 0.00017,
667
+ "loss": 1.9895,
668
  "step": 85
669
  },
670
  {
671
  "epoch": 0.11,
672
+ "grad_norm": 0.27734375,
673
  "learning_rate": 0.000172,
674
+ "loss": 1.8674,
675
  "step": 86
676
  },
677
  {
678
  "epoch": 0.11,
679
+ "grad_norm": 0.25390625,
680
  "learning_rate": 0.000174,
681
+ "loss": 1.9472,
682
  "step": 87
683
  },
684
  {
685
  "epoch": 0.11,
686
+ "grad_norm": 0.361328125,
687
  "learning_rate": 0.00017600000000000002,
688
+ "loss": 1.9717,
689
  "step": 88
690
  },
691
  {
692
  "epoch": 0.11,
693
+ "grad_norm": 0.244140625,
694
  "learning_rate": 0.00017800000000000002,
695
+ "loss": 1.9376,
696
  "step": 89
697
  },
698
  {
699
  "epoch": 0.12,
700
+ "grad_norm": 0.234375,
701
  "learning_rate": 0.00018,
702
+ "loss": 1.9051,
703
  "step": 90
704
  },
705
  {
706
  "epoch": 0.12,
707
+ "eval_loss": 1.9230234622955322,
708
+ "eval_runtime": 125.5293,
709
+ "eval_samples_per_second": 39.831,
710
+ "eval_steps_per_second": 1.251,
711
  "step": 90
712
  },
713
  {
714
  "epoch": 0.12,
715
+ "grad_norm": 0.26171875,
716
  "learning_rate": 0.000182,
717
+ "loss": 1.9395,
718
  "step": 91
719
  },
720
  {
721
  "epoch": 0.12,
722
+ "grad_norm": 0.310546875,
723
  "learning_rate": 0.00018400000000000003,
724
+ "loss": 1.8496,
725
  "step": 92
726
  },
727
  {
728
  "epoch": 0.12,
729
+ "grad_norm": 0.3203125,
730
  "learning_rate": 0.00018600000000000002,
731
+ "loss": 2.0062,
732
  "step": 93
733
  },
734
  {
735
  "epoch": 0.12,
736
+ "grad_norm": 0.267578125,
737
  "learning_rate": 0.000188,
738
+ "loss": 1.9138,
739
  "step": 94
740
  },
741
  {
742
  "epoch": 0.12,
743
+ "grad_norm": 0.224609375,
744
  "learning_rate": 0.00019,
745
+ "loss": 1.9258,
746
  "step": 95
747
  },
748
  {
749
  "epoch": 0.12,
750
+ "grad_norm": 0.21484375,
751
  "learning_rate": 0.000192,
752
+ "loss": 1.9657,
753
  "step": 96
754
  },
755
  {
756
  "epoch": 0.12,
757
+ "grad_norm": 0.259765625,
758
  "learning_rate": 0.000194,
759
+ "loss": 1.9123,
760
  "step": 97
761
  },
762
  {
763
  "epoch": 0.13,
764
+ "grad_norm": 0.240234375,
765
  "learning_rate": 0.000196,
766
+ "loss": 1.8806,
767
  "step": 98
768
  },
769
  {
770
  "epoch": 0.13,
771
+ "grad_norm": 0.21484375,
772
  "learning_rate": 0.00019800000000000002,
773
+ "loss": 1.8394,
774
  "step": 99
775
  },
776
  {
777
  "epoch": 0.13,
778
+ "grad_norm": 0.244140625,
779
  "learning_rate": 0.0002,
780
+ "loss": 1.8164,
781
  "step": 100
782
  },
783
  {
784
  "epoch": 0.13,
785
+ "eval_loss": 1.8982120752334595,
786
+ "eval_runtime": 125.467,
787
+ "eval_samples_per_second": 39.851,
788
+ "eval_steps_per_second": 1.251,
789
  "step": 100
790
  },
791
  {
792
  "epoch": 0.13,
793
+ "grad_norm": 0.265625,
794
  "learning_rate": 0.00019871794871794874,
795
+ "loss": 1.8199,
796
  "step": 101
797
  },
798
  {
799
  "epoch": 0.13,
800
+ "grad_norm": 0.2158203125,
801
  "learning_rate": 0.00019743589743589744,
802
+ "loss": 1.9268,
803
  "step": 102
804
  },
805
  {
806
  "epoch": 0.13,
807
+ "grad_norm": 0.2578125,
808
  "learning_rate": 0.00019615384615384615,
809
+ "loss": 1.9563,
810
  "step": 103
811
  },
812
  {
813
  "epoch": 0.13,
814
+ "grad_norm": 0.20703125,
815
  "learning_rate": 0.00019487179487179487,
816
+ "loss": 1.9037,
817
  "step": 104
818
  },
819
  {
820
  "epoch": 0.13,
821
+ "grad_norm": 0.2265625,
822
  "learning_rate": 0.0001935897435897436,
823
+ "loss": 1.8942,
824
  "step": 105
825
  },
826
  {
827
  "epoch": 0.14,
828
+ "grad_norm": 0.2158203125,
829
  "learning_rate": 0.00019230769230769233,
830
+ "loss": 1.9245,
831
  "step": 106
832
  },
833
  {
834
  "epoch": 0.14,
835
+ "grad_norm": 0.2431640625,
836
  "learning_rate": 0.00019102564102564104,
837
+ "loss": 1.8898,
838
  "step": 107
839
  },
840
  {
841
  "epoch": 0.14,
842
+ "grad_norm": 0.310546875,
843
  "learning_rate": 0.00018974358974358974,
844
+ "loss": 1.8482,
845
  "step": 108
846
  },
847
  {
848
  "epoch": 0.14,
849
+ "grad_norm": 0.2197265625,
850
  "learning_rate": 0.00018846153846153847,
851
+ "loss": 1.8486,
852
  "step": 109
853
  },
854
  {
855
  "epoch": 0.14,
856
+ "grad_norm": 0.228515625,
857
  "learning_rate": 0.0001871794871794872,
858
+ "loss": 1.9404,
859
  "step": 110
860
  },
861
  {
862
  "epoch": 0.14,
863
+ "eval_loss": 1.877401351928711,
864
+ "eval_runtime": 125.8694,
865
+ "eval_samples_per_second": 39.724,
866
+ "eval_steps_per_second": 1.247,
867
  "step": 110
868
  },
869
  {
870
  "epoch": 0.14,
871
+ "grad_norm": 0.2734375,
872
  "learning_rate": 0.0001858974358974359,
873
+ "loss": 1.8611,
874
  "step": 111
875
  },
876
  {
877
  "epoch": 0.14,
878
+ "grad_norm": 0.2216796875,
879
  "learning_rate": 0.00018461538461538463,
880
+ "loss": 1.8728,
881
  "step": 112
882
  },
883
  {
884
  "epoch": 0.14,
885
+ "grad_norm": 0.27734375,
886
  "learning_rate": 0.00018333333333333334,
887
+ "loss": 1.8817,
888
  "step": 113
889
  },
890
  {
891
  "epoch": 0.15,
892
+ "grad_norm": 0.224609375,
893
  "learning_rate": 0.00018205128205128207,
894
+ "loss": 1.8841,
895
  "step": 114
896
  },
897
  {
898
  "epoch": 0.15,
899
+ "grad_norm": 0.2294921875,
900
  "learning_rate": 0.00018076923076923077,
901
+ "loss": 1.8691,
902
  "step": 115
903
  },
904
  {
905
  "epoch": 0.15,
906
+ "grad_norm": 0.28515625,
907
  "learning_rate": 0.0001794871794871795,
908
+ "loss": 1.9013,
909
  "step": 116
910
  },
911
  {
912
  "epoch": 0.15,
913
+ "grad_norm": 0.2265625,
914
  "learning_rate": 0.00017820512820512823,
915
+ "loss": 1.9729,
916
  "step": 117
917
  },
918
  {
919
  "epoch": 0.15,
920
+ "grad_norm": 0.2080078125,
921
  "learning_rate": 0.00017692307692307693,
922
+ "loss": 1.8934,
923
  "step": 118
924
  },
925
  {
926
  "epoch": 0.15,
927
+ "grad_norm": 0.2275390625,
928
  "learning_rate": 0.00017564102564102566,
929
+ "loss": 1.8559,
930
  "step": 119
931
  },
932
  {
933
  "epoch": 0.15,
934
+ "grad_norm": 0.21875,
935
  "learning_rate": 0.00017435897435897436,
936
+ "loss": 1.9225,
937
  "step": 120
938
  },
939
  {
940
  "epoch": 0.15,
941
+ "eval_loss": 1.8639016151428223,
942
+ "eval_runtime": 125.6482,
943
+ "eval_samples_per_second": 39.794,
944
+ "eval_steps_per_second": 1.25,
945
  "step": 120
946
  },
947
  {
948
  "epoch": 0.15,
949
+ "grad_norm": 0.2138671875,
950
  "learning_rate": 0.0001730769230769231,
951
+ "loss": 1.8796,
952
  "step": 121
953
  },
954
  {
955
  "epoch": 0.16,
956
+ "grad_norm": 0.29296875,
957
  "learning_rate": 0.0001717948717948718,
958
+ "loss": 1.8587,
959
  "step": 122
960
  },
961
  {
962
  "epoch": 0.16,
963
+ "grad_norm": 0.2236328125,
964
  "learning_rate": 0.00017051282051282053,
965
+ "loss": 1.8642,
966
  "step": 123
967
  },
968
  {
969
  "epoch": 0.16,
970
+ "grad_norm": 0.240234375,
971
  "learning_rate": 0.00016923076923076923,
972
+ "loss": 1.8532,
973
  "step": 124
974
  },
975
  {
976
  "epoch": 0.16,
977
+ "grad_norm": 0.2216796875,
978
  "learning_rate": 0.00016794871794871796,
979
+ "loss": 1.8731,
980
  "step": 125
981
  },
982
  {
983
  "epoch": 0.16,
984
+ "grad_norm": 0.310546875,
985
  "learning_rate": 0.0001666666666666667,
986
+ "loss": 1.8667,
987
  "step": 126
988
  },
989
  {
990
  "epoch": 0.16,
991
+ "grad_norm": 0.22265625,
992
  "learning_rate": 0.0001653846153846154,
993
+ "loss": 1.9161,
994
  "step": 127
995
  },
996
  {
997
  "epoch": 0.16,
998
+ "grad_norm": 0.2236328125,
999
  "learning_rate": 0.0001641025641025641,
1000
+ "loss": 1.831,
1001
  "step": 128
1002
  },
1003
  {
1004
  "epoch": 0.17,
1005
+ "grad_norm": 0.271484375,
1006
  "learning_rate": 0.00016282051282051282,
1007
+ "loss": 1.9271,
1008
  "step": 129
1009
  },
1010
  {
1011
  "epoch": 0.17,
1012
+ "grad_norm": 0.220703125,
1013
  "learning_rate": 0.00016153846153846155,
1014
+ "loss": 1.9196,
1015
  "step": 130
1016
  },
1017
  {
1018
  "epoch": 0.17,
1019
+ "eval_loss": 1.854244589805603,
1020
+ "eval_runtime": 125.489,
1021
+ "eval_samples_per_second": 39.844,
1022
+ "eval_steps_per_second": 1.251,
1023
  "step": 130
1024
  },
1025
  {
1026
  "epoch": 0.17,
1027
+ "grad_norm": 0.294921875,
1028
  "learning_rate": 0.00016025641025641028,
1029
+ "loss": 1.8143,
1030
  "step": 131
1031
  },
1032
  {
1033
  "epoch": 0.17,
1034
+ "grad_norm": 0.291015625,
1035
  "learning_rate": 0.00015897435897435896,
1036
+ "loss": 1.8742,
1037
  "step": 132
1038
  },
1039
  {
1040
  "epoch": 0.17,
1041
+ "grad_norm": 0.275390625,
1042
  "learning_rate": 0.0001576923076923077,
1043
+ "loss": 1.9119,
1044
  "step": 133
1045
  },
1046
  {
1047
  "epoch": 0.17,
1048
+ "grad_norm": 0.2353515625,
1049
  "learning_rate": 0.00015641025641025642,
1050
+ "loss": 1.9378,
1051
  "step": 134
1052
  },
1053
  {
1054
  "epoch": 0.17,
1055
+ "grad_norm": 0.2431640625,
1056
  "learning_rate": 0.00015512820512820515,
1057
+ "loss": 1.8725,
1058
  "step": 135
1059
  },
1060
  {
1061
  "epoch": 0.17,
1062
+ "grad_norm": 0.314453125,
1063
  "learning_rate": 0.00015384615384615385,
1064
+ "loss": 1.8882,
1065
  "step": 136
1066
  },
1067
  {
1068
  "epoch": 0.18,
1069
+ "grad_norm": 0.32421875,
1070
  "learning_rate": 0.00015256410256410255,
1071
+ "loss": 1.7994,
1072
  "step": 137
1073
  },
1074
  {
1075
  "epoch": 0.18,
1076
+ "grad_norm": 0.244140625,
1077
  "learning_rate": 0.00015128205128205128,
1078
+ "loss": 1.7943,
1079
  "step": 138
1080
  },
1081
  {
1082
  "epoch": 0.18,
1083
+ "grad_norm": 0.248046875,
1084
  "learning_rate": 0.00015000000000000001,
1085
+ "loss": 1.8982,
1086
  "step": 139
1087
  },
1088
  {
1089
  "epoch": 0.18,
1090
+ "grad_norm": 0.251953125,
1091
  "learning_rate": 0.00014871794871794872,
1092
+ "loss": 1.8085,
1093
  "step": 140
1094
  },
1095
  {
1096
  "epoch": 0.18,
1097
+ "eval_loss": 1.844925045967102,
1098
+ "eval_runtime": 125.5735,
1099
+ "eval_samples_per_second": 39.817,
1100
+ "eval_steps_per_second": 1.25,
1101
  "step": 140
1102
  },
1103
  {
1104
  "epoch": 0.18,
1105
+ "grad_norm": 0.2490234375,
1106
  "learning_rate": 0.00014743589743589745,
1107
+ "loss": 1.8725,
1108
  "step": 141
1109
  },
1110
  {
1111
  "epoch": 0.18,
1112
+ "grad_norm": 0.21875,
1113
  "learning_rate": 0.00014615384615384615,
1114
+ "loss": 1.8679,
1115
  "step": 142
1116
  },
1117
  {
1118
  "epoch": 0.18,
1119
+ "grad_norm": 0.2421875,
1120
  "learning_rate": 0.00014487179487179488,
1121
+ "loss": 1.8594,
1122
  "step": 143
1123
  },
1124
  {
1125
  "epoch": 0.18,
1126
+ "grad_norm": 0.2431640625,
1127
  "learning_rate": 0.0001435897435897436,
1128
+ "loss": 1.8896,
1129
  "step": 144
1130
  },
1131
  {
1132
  "epoch": 0.19,
1133
+ "grad_norm": 0.42578125,
1134
  "learning_rate": 0.0001423076923076923,
1135
+ "loss": 1.8578,
1136
  "step": 145
1137
  },
1138
  {
1139
  "epoch": 0.19,
1140
+ "grad_norm": 0.2392578125,
1141
  "learning_rate": 0.00014102564102564104,
1142
+ "loss": 1.8631,
1143
  "step": 146
1144
  },
1145
  {
1146
  "epoch": 0.19,
1147
+ "grad_norm": 0.33203125,
1148
  "learning_rate": 0.00013974358974358974,
1149
+ "loss": 1.8408,
1150
  "step": 147
1151
  },
1152
  {
1153
  "epoch": 0.19,
1154
+ "grad_norm": 0.251953125,
1155
  "learning_rate": 0.00013846153846153847,
1156
+ "loss": 1.752,
1157
  "step": 148
1158
  },
1159
  {
1160
  "epoch": 0.19,
1161
+ "grad_norm": 0.326171875,
1162
  "learning_rate": 0.00013717948717948718,
1163
+ "loss": 1.9149,
1164
  "step": 149
1165
  },
1166
  {
1167
  "epoch": 0.19,
1168
+ "grad_norm": 0.267578125,
1169
  "learning_rate": 0.0001358974358974359,
1170
+ "loss": 1.9018,
1171
  "step": 150
1172
  },
1173
  {
1174
  "epoch": 0.19,
1175
+ "eval_loss": 1.8380218744277954,
1176
+ "eval_runtime": 125.5888,
1177
+ "eval_samples_per_second": 39.812,
1178
+ "eval_steps_per_second": 1.25,
1179
  "step": 150
1180
  },
1181
  {
1182
  "epoch": 0.19,
1183
+ "grad_norm": 0.28125,
1184
  "learning_rate": 0.00013461538461538464,
1185
+ "loss": 1.7853,
1186
  "step": 151
1187
  },
1188
  {
1189
  "epoch": 0.19,
1190
+ "grad_norm": 0.2470703125,
1191
  "learning_rate": 0.00013333333333333334,
1192
+ "loss": 1.9392,
1193
  "step": 152
1194
  },
1195
  {
1196
  "epoch": 0.2,
1197
+ "grad_norm": 0.2490234375,
1198
  "learning_rate": 0.00013205128205128204,
1199
+ "loss": 1.8372,
1200
  "step": 153
1201
  },
1202
  {
1203
  "epoch": 0.2,
1204
+ "grad_norm": 0.28515625,
1205
  "learning_rate": 0.00013076923076923077,
1206
+ "loss": 1.8017,
1207
  "step": 154
1208
  },
1209
  {
1210
  "epoch": 0.2,
1211
+ "grad_norm": 0.255859375,
1212
  "learning_rate": 0.0001294871794871795,
1213
+ "loss": 1.8477,
1214
  "step": 155
1215
  },
1216
  {
1217
  "epoch": 0.2,
1218
+ "grad_norm": 0.2197265625,
1219
  "learning_rate": 0.00012820512820512823,
1220
+ "loss": 1.773,
1221
  "step": 156
1222
  },
1223
  {
1224
  "epoch": 0.2,
1225
+ "grad_norm": 0.2412109375,
1226
  "learning_rate": 0.00012692307692307693,
1227
+ "loss": 1.8194,
1228
  "step": 157
1229
  },
1230
  {
1231
  "epoch": 0.2,
1232
+ "grad_norm": 0.251953125,
1233
  "learning_rate": 0.00012564102564102564,
1234
+ "loss": 1.841,
1235
  "step": 158
1236
  },
1237
  {
1238
  "epoch": 0.2,
1239
+ "grad_norm": 0.2578125,
1240
  "learning_rate": 0.00012435897435897437,
1241
+ "loss": 1.8599,
1242
  "step": 159
1243
  },
1244
  {
1245
  "epoch": 0.2,
1246
+ "grad_norm": 0.2392578125,
1247
  "learning_rate": 0.0001230769230769231,
1248
+ "loss": 1.8224,
1249
  "step": 160
1250
  },
1251
  {
1252
  "epoch": 0.2,
1253
+ "eval_loss": 1.8314405679702759,
1254
+ "eval_runtime": 125.9116,
1255
+ "eval_samples_per_second": 39.71,
1256
+ "eval_steps_per_second": 1.247,
1257
  "step": 160
1258
  },
1259
  {
1260
  "epoch": 0.21,
1261
+ "grad_norm": 0.26953125,
1262
  "learning_rate": 0.00012179487179487179,
1263
+ "loss": 1.8628,
1264
  "step": 161
1265
  },
1266
  {
1267
  "epoch": 0.21,
1268
+ "grad_norm": 0.244140625,
1269
  "learning_rate": 0.00012051282051282052,
1270
+ "loss": 1.8015,
1271
  "step": 162
1272
  },
1273
  {
1274
  "epoch": 0.21,
1275
+ "grad_norm": 0.283203125,
1276
  "learning_rate": 0.00011923076923076923,
1277
+ "loss": 1.8325,
1278
  "step": 163
1279
  },
1280
  {
1281
  "epoch": 0.21,
1282
+ "grad_norm": 0.2578125,
1283
  "learning_rate": 0.00011794871794871796,
1284
+ "loss": 1.8038,
1285
  "step": 164
1286
  },
1287
  {
1288
  "epoch": 0.21,
1289
+ "grad_norm": 0.23828125,
1290
  "learning_rate": 0.00011666666666666668,
1291
+ "loss": 1.729,
1292
  "step": 165
1293
  },
1294
  {
1295
  "epoch": 0.21,
1296
+ "grad_norm": 0.375,
1297
  "learning_rate": 0.00011538461538461538,
1298
+ "loss": 1.8223,
1299
  "step": 166
1300
  },
1301
  {
1302
  "epoch": 0.21,
1303
+ "grad_norm": 0.30859375,
1304
  "learning_rate": 0.0001141025641025641,
1305
+ "loss": 1.8585,
1306
  "step": 167
1307
  },
1308
  {
1309
  "epoch": 0.21,
1310
+ "grad_norm": 0.271484375,
1311
  "learning_rate": 0.00011282051282051283,
1312
+ "loss": 1.9158,
1313
  "step": 168
1314
  },
1315
  {
1316
  "epoch": 0.22,
1317
+ "grad_norm": 0.2734375,
1318
  "learning_rate": 0.00011153846153846154,
1319
+ "loss": 1.8058,
1320
  "step": 169
1321
  },
1322
  {
1323
  "epoch": 0.22,
1324
+ "grad_norm": 0.265625,
1325
  "learning_rate": 0.00011025641025641027,
1326
+ "loss": 1.9334,
1327
  "step": 170
1328
  },
1329
  {
1330
  "epoch": 0.22,
1331
+ "eval_loss": 1.8285787105560303,
1332
+ "eval_runtime": 125.7453,
1333
+ "eval_samples_per_second": 39.763,
1334
+ "eval_steps_per_second": 1.249,
1335
  "step": 170
1336
  },
1337
  {
1338
  "epoch": 0.22,
1339
+ "grad_norm": 0.376953125,
1340
  "learning_rate": 0.00010897435897435896,
1341
+ "loss": 1.8184,
1342
  "step": 171
1343
  },
1344
  {
1345
  "epoch": 0.22,
1346
+ "grad_norm": 0.24609375,
1347
  "learning_rate": 0.0001076923076923077,
1348
+ "loss": 1.7568,
1349
  "step": 172
1350
  },
1351
  {
1352
  "epoch": 0.22,
1353
+ "grad_norm": 0.28515625,
1354
  "learning_rate": 0.00010641025641025641,
1355
+ "loss": 1.847,
1356
  "step": 173
1357
  },
1358
  {
1359
  "epoch": 0.22,
1360
+ "grad_norm": 0.267578125,
1361
  "learning_rate": 0.00010512820512820514,
1362
+ "loss": 1.8164,
1363
  "step": 174
1364
  },
1365
  {
1366
  "epoch": 0.22,
1367
+ "grad_norm": 0.2890625,
1368
  "learning_rate": 0.00010384615384615386,
1369
+ "loss": 1.9219,
1370
  "step": 175
1371
  },
1372
  {
1373
  "epoch": 0.23,
1374
+ "grad_norm": 0.25390625,
1375
  "learning_rate": 0.00010256410256410256,
1376
+ "loss": 1.8789,
1377
  "step": 176
1378
  },
1379
  {
1380
  "epoch": 0.23,
1381
+ "grad_norm": 0.275390625,
1382
  "learning_rate": 0.00010128205128205129,
1383
+ "loss": 1.8036,
1384
  "step": 177
1385
  },
1386
  {
1387
  "epoch": 0.23,
1388
+ "grad_norm": 0.306640625,
1389
  "learning_rate": 0.0001,
1390
+ "loss": 1.7451,
1391
  "step": 178
1392
  },
1393
  {
1394
  "epoch": 0.23,
1395
+ "grad_norm": 0.27734375,
1396
  "learning_rate": 9.871794871794872e-05,
1397
+ "loss": 1.8295,
1398
  "step": 179
1399
  },
1400
  {
1401
  "epoch": 0.23,
1402
+ "grad_norm": 0.26171875,
1403
  "learning_rate": 9.743589743589744e-05,
1404
+ "loss": 1.8326,
1405
  "step": 180
1406
  },
1407
  {
1408
  "epoch": 0.23,
1409
+ "eval_loss": 1.8210687637329102,
1410
+ "eval_runtime": 125.5174,
1411
+ "eval_samples_per_second": 39.835,
1412
+ "eval_steps_per_second": 1.251,
1413
  "step": 180
1414
  },
1415
  {
1416
  "epoch": 0.23,
1417
+ "grad_norm": 0.267578125,
1418
  "learning_rate": 9.615384615384617e-05,
1419
+ "loss": 1.817,
1420
  "step": 181
1421
  },
1422
  {
1423
  "epoch": 0.23,
1424
+ "grad_norm": 0.291015625,
1425
  "learning_rate": 9.487179487179487e-05,
1426
+ "loss": 1.7804,
1427
  "step": 182
1428
  },
1429
  {
1430
  "epoch": 0.23,
1431
+ "grad_norm": 0.267578125,
1432
  "learning_rate": 9.35897435897436e-05,
1433
+ "loss": 1.8063,
1434
  "step": 183
1435
  },
1436
  {
1437
  "epoch": 0.24,
1438
+ "grad_norm": 0.287109375,
1439
  "learning_rate": 9.230769230769232e-05,
1440
+ "loss": 1.7806,
1441
  "step": 184
1442
  },
1443
  {
1444
  "epoch": 0.24,
1445
+ "grad_norm": 0.275390625,
1446
  "learning_rate": 9.102564102564103e-05,
1447
+ "loss": 1.9115,
1448
  "step": 185
1449
  },
1450
  {
1451
  "epoch": 0.24,
1452
+ "grad_norm": 0.265625,
1453
  "learning_rate": 8.974358974358975e-05,
1454
+ "loss": 1.8414,
1455
  "step": 186
1456
  },
1457
  {
1458
  "epoch": 0.24,
1459
+ "grad_norm": 0.2314453125,
1460
  "learning_rate": 8.846153846153847e-05,
1461
+ "loss": 1.8451,
1462
  "step": 187
1463
  },
1464
  {
1465
  "epoch": 0.24,
1466
+ "grad_norm": 0.2294921875,
1467
  "learning_rate": 8.717948717948718e-05,
1468
+ "loss": 1.7911,
1469
  "step": 188
1470
  },
1471
  {
1472
  "epoch": 0.24,
1473
+ "grad_norm": 0.30078125,
1474
  "learning_rate": 8.58974358974359e-05,
1475
+ "loss": 1.8654,
1476
  "step": 189
1477
  },
1478
  {
1479
  "epoch": 0.24,
1480
+ "grad_norm": 0.27734375,
1481
  "learning_rate": 8.461538461538461e-05,
1482
+ "loss": 1.8412,
1483
  "step": 190
1484
  },
1485
  {
1486
  "epoch": 0.24,
1487
+ "eval_loss": 1.8182088136672974,
1488
+ "eval_runtime": 125.5312,
1489
+ "eval_samples_per_second": 39.831,
1490
+ "eval_steps_per_second": 1.251,
1491
  "step": 190
1492
  },
1493
  {
1494
  "epoch": 0.24,
1495
+ "grad_norm": 0.267578125,
1496
  "learning_rate": 8.333333333333334e-05,
1497
+ "loss": 1.869,
1498
  "step": 191
1499
  },
1500
  {
1501
  "epoch": 0.25,
1502
+ "grad_norm": 0.263671875,
1503
  "learning_rate": 8.205128205128205e-05,
1504
+ "loss": 1.8746,
1505
  "step": 192
1506
  },
1507
  {
1508
  "epoch": 0.25,
1509
+ "grad_norm": 0.25390625,
1510
  "learning_rate": 8.076923076923078e-05,
1511
+ "loss": 1.7365,
1512
  "step": 193
1513
  },
1514
  {
1515
  "epoch": 0.25,
1516
+ "grad_norm": 0.2734375,
1517
  "learning_rate": 7.948717948717948e-05,
1518
+ "loss": 1.891,
1519
  "step": 194
1520
  },
1521
  {
1522
  "epoch": 0.25,
1523
+ "grad_norm": 0.248046875,
1524
  "learning_rate": 7.820512820512821e-05,
1525
+ "loss": 1.7924,
1526
  "step": 195
1527
  },
1528
  {
1529
  "epoch": 0.25,
1530
+ "grad_norm": 0.240234375,
1531
  "learning_rate": 7.692307692307693e-05,
1532
+ "loss": 1.8078,
1533
  "step": 196
1534
  },
1535
  {
1536
  "epoch": 0.25,
1537
+ "grad_norm": 0.302734375,
1538
  "learning_rate": 7.564102564102564e-05,
1539
+ "loss": 1.8012,
1540
  "step": 197
1541
  },
1542
  {
1543
  "epoch": 0.25,
1544
+ "grad_norm": 0.275390625,
1545
  "learning_rate": 7.435897435897436e-05,
1546
+ "loss": 1.8252,
1547
  "step": 198
1548
  },
1549
  {
1550
  "epoch": 0.25,
1551
+ "grad_norm": 0.26953125,
1552
  "learning_rate": 7.307692307692307e-05,
1553
+ "loss": 1.8348,
1554
  "step": 199
1555
  },
1556
  {
1557
  "epoch": 0.26,
1558
+ "grad_norm": 0.2734375,
1559
  "learning_rate": 7.17948717948718e-05,
1560
+ "loss": 1.7759,
1561
  "step": 200
1562
  },
1563
  {
1564
  "epoch": 0.26,
1565
+ "eval_loss": 1.8161256313323975,
1566
+ "eval_runtime": 125.4822,
1567
+ "eval_samples_per_second": 39.846,
1568
+ "eval_steps_per_second": 1.251,
1569
  "step": 200
1570
  },
1571
  {
1572
  "epoch": 0.26,
1573
+ "grad_norm": 0.265625,
1574
  "learning_rate": 7.051282051282052e-05,
1575
+ "loss": 1.8081,
1576
  "step": 201
1577
  },
1578
  {
1579
  "epoch": 0.26,
1580
+ "grad_norm": 0.2412109375,
1581
  "learning_rate": 6.923076923076924e-05,
1582
+ "loss": 1.8619,
1583
  "step": 202
1584
  },
1585
  {
1586
  "epoch": 0.26,
1587
+ "grad_norm": 0.263671875,
1588
  "learning_rate": 6.794871794871795e-05,
1589
+ "loss": 1.898,
1590
  "step": 203
1591
  },
1592
  {
1593
  "epoch": 0.26,
1594
+ "grad_norm": 0.255859375,
1595
  "learning_rate": 6.666666666666667e-05,
1596
+ "loss": 1.8495,
1597
  "step": 204
1598
  },
1599
  {
1600
  "epoch": 0.26,
1601
+ "grad_norm": 0.25,
1602
  "learning_rate": 6.538461538461539e-05,
1603
+ "loss": 1.7347,
1604
  "step": 205
1605
  },
1606
  {
1607
  "epoch": 0.26,
1608
+ "grad_norm": 0.287109375,
1609
  "learning_rate": 6.410256410256412e-05,
1610
+ "loss": 1.8185,
1611
  "step": 206
1612
  },
1613
  {
1614
  "epoch": 0.26,
1615
+ "grad_norm": 0.251953125,
1616
  "learning_rate": 6.282051282051282e-05,
1617
+ "loss": 1.7143,
1618
  "step": 207
1619
  },
1620
  {
1621
  "epoch": 0.27,
1622
+ "grad_norm": 0.255859375,
1623
  "learning_rate": 6.153846153846155e-05,
1624
+ "loss": 1.8391,
1625
  "step": 208
1626
  },
1627
  {
1628
  "epoch": 0.27,
1629
+ "grad_norm": 0.3125,
1630
  "learning_rate": 6.025641025641026e-05,
1631
+ "loss": 1.8135,
1632
  "step": 209
1633
  },
1634
  {
1635
  "epoch": 0.27,
1636
+ "grad_norm": 0.265625,
1637
  "learning_rate": 5.897435897435898e-05,
1638
+ "loss": 1.8639,
1639
  "step": 210
1640
  },
1641
  {
1642
  "epoch": 0.27,
1643
+ "eval_loss": 1.8143140077590942,
1644
+ "eval_runtime": 125.8394,
1645
+ "eval_samples_per_second": 39.733,
1646
+ "eval_steps_per_second": 1.248,
1647
  "step": 210
1648
  },
1649
  {
1650
  "epoch": 0.27,
1651
+ "grad_norm": 0.259765625,
1652
  "learning_rate": 5.769230769230769e-05,
1653
+ "loss": 1.8108,
1654
  "step": 211
1655
  },
1656
  {
1657
  "epoch": 0.27,
1658
+ "grad_norm": 0.251953125,
1659
  "learning_rate": 5.6410256410256414e-05,
1660
+ "loss": 1.8078,
1661
  "step": 212
1662
  },
1663
  {
1664
  "epoch": 0.27,
1665
+ "grad_norm": 0.27734375,
1666
  "learning_rate": 5.512820512820514e-05,
1667
+ "loss": 1.8167,
1668
  "step": 213
1669
  },
1670
  {
1671
  "epoch": 0.27,
1672
+ "grad_norm": 0.26171875,
1673
  "learning_rate": 5.384615384615385e-05,
1674
+ "loss": 1.8148,
1675
  "step": 214
1676
  },
1677
  {
1678
  "epoch": 0.28,
1679
+ "grad_norm": 0.26171875,
1680
  "learning_rate": 5.256410256410257e-05,
1681
+ "loss": 1.7895,
1682
  "step": 215
1683
  },
1684
  {
1685
  "epoch": 0.28,
1686
+ "grad_norm": 0.275390625,
1687
  "learning_rate": 5.128205128205128e-05,
1688
+ "loss": 1.7537,
1689
  "step": 216
1690
  },
1691
  {
1692
  "epoch": 0.28,
1693
+ "grad_norm": 0.283203125,
1694
  "learning_rate": 5e-05,
1695
+ "loss": 1.8267,
1696
  "step": 217
1697
  },
1698
  {
1699
  "epoch": 0.28,
1700
+ "grad_norm": 0.26171875,
1701
  "learning_rate": 4.871794871794872e-05,
1702
+ "loss": 1.9016,
1703
  "step": 218
1704
  },
1705
  {
1706
  "epoch": 0.28,
1707
+ "grad_norm": 0.26953125,
1708
  "learning_rate": 4.7435897435897435e-05,
1709
+ "loss": 1.8097,
1710
  "step": 219
1711
  },
1712
  {
1713
  "epoch": 0.28,
1714
+ "grad_norm": 0.283203125,
1715
  "learning_rate": 4.615384615384616e-05,
1716
+ "loss": 1.8519,
1717
  "step": 220
1718
  },
1719
  {
1720
  "epoch": 0.28,
1721
+ "eval_loss": 1.8137133121490479,
1722
+ "eval_runtime": 125.6108,
1723
+ "eval_samples_per_second": 39.805,
1724
+ "eval_steps_per_second": 1.25,
1725
  "step": 220
1726
  },
1727
  {
1728
  "epoch": 0.28,
1729
+ "grad_norm": 0.2734375,
1730
  "learning_rate": 4.4871794871794874e-05,
1731
+ "loss": 1.8262,
1732
  "step": 221
1733
  },
1734
  {
1735
  "epoch": 0.28,
1736
+ "grad_norm": 0.271484375,
1737
  "learning_rate": 4.358974358974359e-05,
1738
+ "loss": 1.8572,
1739
  "step": 222
1740
  },
1741
  {
1742
  "epoch": 0.29,
1743
+ "grad_norm": 0.251953125,
1744
  "learning_rate": 4.230769230769231e-05,
1745
+ "loss": 1.8059,
1746
  "step": 223
1747
  },
1748
  {
1749
  "epoch": 0.29,
1750
+ "grad_norm": 0.255859375,
1751
  "learning_rate": 4.1025641025641023e-05,
1752
+ "loss": 1.813,
1753
  "step": 224
1754
  },
1755
  {
1756
  "epoch": 0.29,
1757
+ "grad_norm": 0.259765625,
1758
  "learning_rate": 3.974358974358974e-05,
1759
+ "loss": 1.8061,
1760
  "step": 225
1761
  },
1762
  {
1763
  "epoch": 0.29,
1764
+ "grad_norm": 0.26171875,
1765
  "learning_rate": 3.846153846153846e-05,
1766
+ "loss": 1.7375,
1767
  "step": 226
1768
  },
1769
  {
1770
  "epoch": 0.29,
1771
+ "grad_norm": 0.2734375,
1772
  "learning_rate": 3.717948717948718e-05,
1773
+ "loss": 1.8433,
1774
  "step": 227
1775
  },
1776
  {
1777
  "epoch": 0.29,
1778
+ "grad_norm": 0.27734375,
1779
  "learning_rate": 3.58974358974359e-05,
1780
+ "loss": 1.8459,
1781
  "step": 228
1782
  },
1783
  {
1784
  "epoch": 0.29,
1785
+ "grad_norm": 0.2578125,
1786
  "learning_rate": 3.461538461538462e-05,
1787
+ "loss": 1.7373,
1788
  "step": 229
1789
  },
1790
  {
1791
  "epoch": 0.29,
1792
+ "grad_norm": 0.248046875,
1793
  "learning_rate": 3.3333333333333335e-05,
1794
+ "loss": 1.862,
1795
  "step": 230
1796
  },
1797
  {
1798
  "epoch": 0.29,
1799
+ "eval_loss": 1.8112460374832153,
1800
+ "eval_runtime": 125.6176,
1801
+ "eval_samples_per_second": 39.803,
1802
+ "eval_steps_per_second": 1.25,
1803
  "step": 230
1804
  },
1805
  {
1806
  "epoch": 0.3,
1807
+ "grad_norm": 0.306640625,
1808
  "learning_rate": 3.205128205128206e-05,
1809
+ "loss": 1.8498,
1810
  "step": 231
1811
  },
1812
  {
1813
  "epoch": 0.3,
1814
+ "grad_norm": 0.2578125,
1815
  "learning_rate": 3.0769230769230774e-05,
1816
+ "loss": 1.7185,
1817
  "step": 232
1818
  },
1819
  {
1820
  "epoch": 0.3,
1821
+ "grad_norm": 0.25390625,
1822
  "learning_rate": 2.948717948717949e-05,
1823
+ "loss": 1.7511,
1824
  "step": 233
1825
  },
1826
  {
1827
  "epoch": 0.3,
1828
+ "grad_norm": 0.267578125,
1829
  "learning_rate": 2.8205128205128207e-05,
1830
+ "loss": 1.8457,
1831
  "step": 234
1832
  },
1833
  {
1834
  "epoch": 0.3,
1835
+ "grad_norm": 0.267578125,
1836
  "learning_rate": 2.6923076923076923e-05,
1837
+ "loss": 1.8456,
1838
  "step": 235
1839
  },
1840
  {
1841
  "epoch": 0.3,
1842
+ "grad_norm": 0.26953125,
1843
  "learning_rate": 2.564102564102564e-05,
1844
+ "loss": 1.8656,
1845
  "step": 236
1846
  },
1847
  {
1848
  "epoch": 0.3,
1849
+ "grad_norm": 0.2578125,
1850
  "learning_rate": 2.435897435897436e-05,
1851
+ "loss": 1.7922,
1852
  "step": 237
1853
  },
1854
  {
1855
  "epoch": 0.3,
1856
+ "grad_norm": 0.26953125,
1857
  "learning_rate": 2.307692307692308e-05,
1858
+ "loss": 1.8367,
1859
  "step": 238
1860
  },
1861
  {
1862
  "epoch": 0.31,
1863
+ "grad_norm": 0.2470703125,
1864
  "learning_rate": 2.1794871794871795e-05,
1865
+ "loss": 1.8649,
1866
  "step": 239
1867
  },
1868
  {
1869
  "epoch": 0.31,
1870
+ "grad_norm": 0.349609375,
1871
  "learning_rate": 2.0512820512820512e-05,
1872
+ "loss": 1.8575,
1873
  "step": 240
1874
  },
1875
  {
1876
  "epoch": 0.31,
1877
+ "eval_loss": 1.811773419380188,
1878
+ "eval_runtime": 125.6114,
1879
+ "eval_samples_per_second": 39.805,
1880
+ "eval_steps_per_second": 1.25,
1881
  "step": 240
1882
  },
1883
  {
1884
  "epoch": 0.31,
1885
+ "grad_norm": 0.251953125,
1886
  "learning_rate": 1.923076923076923e-05,
1887
+ "loss": 1.8488,
1888
  "step": 241
1889
  },
1890
  {
1891
  "epoch": 0.31,
1892
+ "grad_norm": 0.283203125,
1893
  "learning_rate": 1.794871794871795e-05,
1894
+ "loss": 1.7675,
1895
  "step": 242
1896
  },
1897
  {
1898
  "epoch": 0.31,
1899
+ "grad_norm": 0.26953125,
1900
  "learning_rate": 1.6666666666666667e-05,
1901
+ "loss": 1.7799,
1902
  "step": 243
1903
  },
1904
  {
1905
  "epoch": 0.31,
1906
+ "grad_norm": 0.251953125,
1907
  "learning_rate": 1.5384615384615387e-05,
1908
+ "loss": 1.756,
1909
  "step": 244
1910
  },
1911
  {
1912
  "epoch": 0.31,
1913
+ "grad_norm": 0.2392578125,
1914
  "learning_rate": 1.4102564102564104e-05,
1915
+ "loss": 1.8738,
1916
  "step": 245
1917
  },
1918
  {
1919
  "epoch": 0.31,
1920
+ "grad_norm": 0.265625,
1921
  "learning_rate": 1.282051282051282e-05,
1922
+ "loss": 1.7766,
1923
  "step": 246
1924
  },
1925
  {
1926
  "epoch": 0.32,
1927
+ "grad_norm": 0.25,
1928
  "learning_rate": 1.153846153846154e-05,
1929
+ "loss": 1.8446,
1930
  "step": 247
1931
  },
1932
  {
1933
  "epoch": 0.32,
1934
+ "grad_norm": 0.265625,
1935
  "learning_rate": 1.0256410256410256e-05,
1936
+ "loss": 1.885,
1937
  "step": 248
1938
  },
1939
  {
1940
  "epoch": 0.32,
1941
+ "grad_norm": 0.29296875,
1942
  "learning_rate": 8.974358974358976e-06,
1943
+ "loss": 1.809,
1944
  "step": 249
1945
  },
1946
  {
1947
  "epoch": 0.32,
1948
+ "grad_norm": 0.265625,
1949
  "learning_rate": 7.692307692307694e-06,
1950
+ "loss": 1.7866,
1951
  "step": 250
1952
  },
1953
  {
1954
  "epoch": 0.32,
1955
+ "eval_loss": 1.810941219329834,
1956
+ "eval_runtime": 125.5076,
1957
+ "eval_samples_per_second": 39.838,
1958
+ "eval_steps_per_second": 1.251,
1959
  "step": 250
1960
  },
1961
  {
1962
  "epoch": 0.32,
1963
+ "grad_norm": 0.263671875,
1964
  "learning_rate": 6.41025641025641e-06,
1965
+ "loss": 1.8828,
1966
  "step": 251
1967
  },
1968
  {
1969
  "epoch": 0.32,
1970
+ "grad_norm": 0.2890625,
1971
  "learning_rate": 5.128205128205128e-06,
1972
+ "loss": 1.8189,
1973
  "step": 252
1974
  },
1975
  {
1976
  "epoch": 0.32,
1977
+ "grad_norm": 0.25,
1978
  "learning_rate": 3.846153846153847e-06,
1979
+ "loss": 1.7144,
1980
  "step": 253
1981
  },
1982
  {
1983
  "epoch": 0.33,
1984
+ "grad_norm": 0.2734375,
1985
  "learning_rate": 2.564102564102564e-06,
1986
+ "loss": 1.7287,
1987
  "step": 254
1988
  },
1989
  {
1990
  "epoch": 0.33,
1991
+ "grad_norm": 0.251953125,
1992
  "learning_rate": 1.282051282051282e-06,
1993
+ "loss": 1.8007,
1994
  "step": 255
1995
  },
1996
  {
1997
  "epoch": 0.33,
1998
+ "grad_norm": 0.263671875,
1999
  "learning_rate": 0.0,
2000
+ "loss": 1.8333,
2001
  "step": 256
2002
  },
2003
  {
2004
  "epoch": 0.33,
2005
  "step": 256,
2006
+ "total_flos": 1.8626901413206426e+17,
2007
+ "train_loss": 2.2480679317377508,
2008
+ "train_runtime": 4476.2307,
2009
+ "train_samples_per_second": 3.66,
2010
+ "train_steps_per_second": 0.057
2011
  },
2012
  {
2013
  "epoch": 0.33,
2014
+ "eval_loss": 1.810941219329834,
2015
+ "eval_runtime": 125.8181,
2016
+ "eval_samples_per_second": 39.74,
2017
+ "eval_steps_per_second": 1.248,
2018
  "step": 256
2019
  }
2020
  ],
 
2023
  "num_input_tokens_seen": 0,
2024
  "num_train_epochs": 1,
2025
  "save_steps": 10,
2026
+ "total_flos": 1.8626901413206426e+17,
2027
  "train_batch_size": 32,
2028
  "trial_name": null,
2029
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfce3cdce6c99f960f4d9ca5a28082ea53558024bc5b1c5408c061f23df41820
3
- size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6a7c0c60daaf1331ee848eb0d4def43698c846e1bcc4f624b47ff278e07740
3
+ size 5176