PurplelinkPL commited on
Commit
1afbcad
·
verified ·
1 Parent(s): b920cc7

Delete SynFinBERT_Final

Browse files
SynFinBERT_Final/checkpoint-31439/config.json DELETED
@@ -1,46 +0,0 @@
1
- {
2
- "architectures": [
3
- "ModernBertForMaskedLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_implementation": "sdpa",
8
- "bos_token_id": 50281,
9
- "classifier_activation": "gelu",
10
- "classifier_bias": false,
11
- "classifier_dropout": 0.0,
12
- "classifier_pooling": "mean",
13
- "cls_token_id": 50281,
14
- "decoder_bias": true,
15
- "deterministic_flash_attn": false,
16
- "embedding_dropout": 0.0,
17
- "eos_token_id": 50282,
18
- "global_attn_every_n_layers": 3,
19
- "global_rope_theta": 160000.0,
20
- "gradient_checkpointing": false,
21
- "hidden_activation": "gelu",
22
- "hidden_size": 768,
23
- "initializer_cutoff_factor": 2.0,
24
- "initializer_range": 0.02,
25
- "intermediate_size": 1152,
26
- "layer_norm_eps": 1e-05,
27
- "local_attention": 128,
28
- "local_rope_theta": 10000.0,
29
- "max_position_embeddings": 8192,
30
- "mlp_bias": false,
31
- "mlp_dropout": 0.0,
32
- "model_type": "modernbert",
33
- "norm_bias": false,
34
- "norm_eps": 1e-05,
35
- "num_attention_heads": 12,
36
- "num_hidden_layers": 22,
37
- "pad_token_id": 50283,
38
- "position_embedding_type": "absolute",
39
- "repad_logits_with_grad": false,
40
- "sep_token_id": 50282,
41
- "sparse_pred_ignore_index": -100,
42
- "sparse_prediction": false,
43
- "torch_dtype": "float32",
44
- "transformers_version": "4.54.0",
45
- "vocab_size": 50368
46
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
SynFinBERT_Final/checkpoint-31439/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:44e0ac1a63d93aac0a95266477546e4248339df56e16ed4336a8550740858b59
3
- size 598635032
 
 
 
 
SynFinBERT_Final/checkpoint-31439/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e7cc673d8fc1bcd885c54d30aec0daacb82105d6687c5b6974c0163039d9651
3
- size 1197359627
 
 
 
 
SynFinBERT_Final/checkpoint-31439/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc1047afaeb78bfefb5fd31cf31495f63e1d5860542b224294777dc9a8b20c58
3
- size 16389
 
 
 
 
SynFinBERT_Final/checkpoint-31439/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1705a17f9d6d640e6377f77fe8891ffef651f541363de0056e2dfa62f25c1bd4
3
- size 16389
 
 
 
 
SynFinBERT_Final/checkpoint-31439/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ab1c3a0edbd4f742052fc6b51f05a3b5007cd0a9206db9846113ec36893101d
3
- size 16389
 
 
 
 
SynFinBERT_Final/checkpoint-31439/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:183e8dfc6d1e37c32093f78d53ac8a2bb735a002f6b8b5e01daccac684f44445
3
- size 16389
 
 
 
 
SynFinBERT_Final/checkpoint-31439/rng_state_4.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab1cfc8ea83252c4f88d78bf9df1ea5ca3cc076c41f209742a4542060c806ca8
3
- size 16389
 
 
 
 
SynFinBERT_Final/checkpoint-31439/rng_state_5.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:870d09281998d4a17beafb9cce4ef3a071b9be91ca7875007bcd8f23302b4f15
3
- size 16389
 
 
 
 
SynFinBERT_Final/checkpoint-31439/rng_state_6.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:30af43e682687c937ae6f8f571ec1ba65bcd56697cd146d2a74d947f97704545
3
- size 16389
 
 
 
 
SynFinBERT_Final/checkpoint-31439/rng_state_7.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2031fa13eedf00740d1878ba7c14fea55fb07c7013c9bcf6a15d2415789f0ca8
3
- size 16389
 
 
 
 
SynFinBERT_Final/checkpoint-31439/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0c5e0eb199d261c19a86e71cdb35977f3635eef67e27b971ab784f951a1be8d
3
- size 1465
 
 
 
 
SynFinBERT_Final/checkpoint-31439/special_tokens_map.json DELETED
@@ -1,37 +0,0 @@
1
- {
2
- "cls_token": {
3
- "content": "[CLS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "mask_token": {
10
- "content": "[MASK]",
11
- "lstrip": true,
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,
21
- "single_word": false
22
- },
23
- "sep_token": {
24
- "content": "[SEP]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "unk_token": {
31
- "content": "[UNK]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- }
37
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
SynFinBERT_Final/checkpoint-31439/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
SynFinBERT_Final/checkpoint-31439/tokenizer_config.json DELETED
@@ -1,945 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "|||IP_ADDRESS|||",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": false
10
- },
11
- "1": {
12
- "content": "<|padding|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "50254": {
20
- "content": " ",
21
- "lstrip": false,
22
- "normalized": true,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": false
26
- },
27
- "50255": {
28
- "content": " ",
29
- "lstrip": false,
30
- "normalized": true,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": false
34
- },
35
- "50256": {
36
- "content": " ",
37
- "lstrip": false,
38
- "normalized": true,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": false
42
- },
43
- "50257": {
44
- "content": " ",
45
- "lstrip": false,
46
- "normalized": true,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": false
50
- },
51
- "50258": {
52
- "content": " ",
53
- "lstrip": false,
54
- "normalized": true,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": false
58
- },
59
- "50259": {
60
- "content": " ",
61
- "lstrip": false,
62
- "normalized": true,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": false
66
- },
67
- "50260": {
68
- "content": " ",
69
- "lstrip": false,
70
- "normalized": true,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": false
74
- },
75
- "50261": {
76
- "content": " ",
77
- "lstrip": false,
78
- "normalized": true,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": false
82
- },
83
- "50262": {
84
- "content": " ",
85
- "lstrip": false,
86
- "normalized": true,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": false
90
- },
91
- "50263": {
92
- "content": " ",
93
- "lstrip": false,
94
- "normalized": true,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": false
98
- },
99
- "50264": {
100
- "content": " ",
101
- "lstrip": false,
102
- "normalized": true,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": false
106
- },
107
- "50265": {
108
- "content": " ",
109
- "lstrip": false,
110
- "normalized": true,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": false
114
- },
115
- "50266": {
116
- "content": " ",
117
- "lstrip": false,
118
- "normalized": true,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": false
122
- },
123
- "50267": {
124
- "content": " ",
125
- "lstrip": false,
126
- "normalized": true,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": false
130
- },
131
- "50268": {
132
- "content": " ",
133
- "lstrip": false,
134
- "normalized": true,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": false
138
- },
139
- "50269": {
140
- "content": " ",
141
- "lstrip": false,
142
- "normalized": true,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": false
146
- },
147
- "50270": {
148
- "content": " ",
149
- "lstrip": false,
150
- "normalized": true,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": false
154
- },
155
- "50271": {
156
- "content": " ",
157
- "lstrip": false,
158
- "normalized": true,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": false
162
- },
163
- "50272": {
164
- "content": " ",
165
- "lstrip": false,
166
- "normalized": true,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": false
170
- },
171
- "50273": {
172
- "content": " ",
173
- "lstrip": false,
174
- "normalized": true,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": false
178
- },
179
- "50274": {
180
- "content": " ",
181
- "lstrip": false,
182
- "normalized": true,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": false
186
- },
187
- "50275": {
188
- "content": " ",
189
- "lstrip": false,
190
- "normalized": true,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": false
194
- },
195
- "50276": {
196
- "content": " ",
197
- "lstrip": false,
198
- "normalized": true,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": false
202
- },
203
- "50277": {
204
- "content": "|||EMAIL_ADDRESS|||",
205
- "lstrip": false,
206
- "normalized": true,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": false
210
- },
211
- "50278": {
212
- "content": "|||PHONE_NUMBER|||",
213
- "lstrip": false,
214
- "normalized": true,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": false
218
- },
219
- "50279": {
220
- "content": "<|endoftext|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "50280": {
228
- "content": "[UNK]",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "50281": {
236
- "content": "[CLS]",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "50282": {
244
- "content": "[SEP]",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "50283": {
252
- "content": "[PAD]",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "50284": {
260
- "content": "[MASK]",
261
- "lstrip": true,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "50285": {
268
- "content": "[unused0]",
269
- "lstrip": false,
270
- "normalized": true,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": false
274
- },
275
- "50286": {
276
- "content": "[unused1]",
277
- "lstrip": false,
278
- "normalized": true,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": false
282
- },
283
- "50287": {
284
- "content": "[unused2]",
285
- "lstrip": false,
286
- "normalized": true,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": false
290
- },
291
- "50288": {
292
- "content": "[unused3]",
293
- "lstrip": false,
294
- "normalized": true,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": false
298
- },
299
- "50289": {
300
- "content": "[unused4]",
301
- "lstrip": false,
302
- "normalized": true,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": false
306
- },
307
- "50290": {
308
- "content": "[unused5]",
309
- "lstrip": false,
310
- "normalized": true,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": false
314
- },
315
- "50291": {
316
- "content": "[unused6]",
317
- "lstrip": false,
318
- "normalized": true,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": false
322
- },
323
- "50292": {
324
- "content": "[unused7]",
325
- "lstrip": false,
326
- "normalized": true,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": false
330
- },
331
- "50293": {
332
- "content": "[unused8]",
333
- "lstrip": false,
334
- "normalized": true,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": false
338
- },
339
- "50294": {
340
- "content": "[unused9]",
341
- "lstrip": false,
342
- "normalized": true,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": false
346
- },
347
- "50295": {
348
- "content": "[unused10]",
349
- "lstrip": false,
350
- "normalized": true,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": false
354
- },
355
- "50296": {
356
- "content": "[unused11]",
357
- "lstrip": false,
358
- "normalized": true,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": false
362
- },
363
- "50297": {
364
- "content": "[unused12]",
365
- "lstrip": false,
366
- "normalized": true,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": false
370
- },
371
- "50298": {
372
- "content": "[unused13]",
373
- "lstrip": false,
374
- "normalized": true,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": false
378
- },
379
- "50299": {
380
- "content": "[unused14]",
381
- "lstrip": false,
382
- "normalized": true,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": false
386
- },
387
- "50300": {
388
- "content": "[unused15]",
389
- "lstrip": false,
390
- "normalized": true,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": false
394
- },
395
- "50301": {
396
- "content": "[unused16]",
397
- "lstrip": false,
398
- "normalized": true,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": false
402
- },
403
- "50302": {
404
- "content": "[unused17]",
405
- "lstrip": false,
406
- "normalized": true,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": false
410
- },
411
- "50303": {
412
- "content": "[unused18]",
413
- "lstrip": false,
414
- "normalized": true,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": false
418
- },
419
- "50304": {
420
- "content": "[unused19]",
421
- "lstrip": false,
422
- "normalized": true,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": false
426
- },
427
- "50305": {
428
- "content": "[unused20]",
429
- "lstrip": false,
430
- "normalized": true,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": false
434
- },
435
- "50306": {
436
- "content": "[unused21]",
437
- "lstrip": false,
438
- "normalized": true,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": false
442
- },
443
- "50307": {
444
- "content": "[unused22]",
445
- "lstrip": false,
446
- "normalized": true,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": false
450
- },
451
- "50308": {
452
- "content": "[unused23]",
453
- "lstrip": false,
454
- "normalized": true,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": false
458
- },
459
- "50309": {
460
- "content": "[unused24]",
461
- "lstrip": false,
462
- "normalized": true,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": false
466
- },
467
- "50310": {
468
- "content": "[unused25]",
469
- "lstrip": false,
470
- "normalized": true,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": false
474
- },
475
- "50311": {
476
- "content": "[unused26]",
477
- "lstrip": false,
478
- "normalized": true,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": false
482
- },
483
- "50312": {
484
- "content": "[unused27]",
485
- "lstrip": false,
486
- "normalized": true,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": false
490
- },
491
- "50313": {
492
- "content": "[unused28]",
493
- "lstrip": false,
494
- "normalized": true,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": false
498
- },
499
- "50314": {
500
- "content": "[unused29]",
501
- "lstrip": false,
502
- "normalized": true,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": false
506
- },
507
- "50315": {
508
- "content": "[unused30]",
509
- "lstrip": false,
510
- "normalized": true,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": false
514
- },
515
- "50316": {
516
- "content": "[unused31]",
517
- "lstrip": false,
518
- "normalized": true,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": false
522
- },
523
- "50317": {
524
- "content": "[unused32]",
525
- "lstrip": false,
526
- "normalized": true,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": false
530
- },
531
- "50318": {
532
- "content": "[unused33]",
533
- "lstrip": false,
534
- "normalized": true,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": false
538
- },
539
- "50319": {
540
- "content": "[unused34]",
541
- "lstrip": false,
542
- "normalized": true,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": false
546
- },
547
- "50320": {
548
- "content": "[unused35]",
549
- "lstrip": false,
550
- "normalized": true,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": false
554
- },
555
- "50321": {
556
- "content": "[unused36]",
557
- "lstrip": false,
558
- "normalized": true,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": false
562
- },
563
- "50322": {
564
- "content": "[unused37]",
565
- "lstrip": false,
566
- "normalized": true,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": false
570
- },
571
- "50323": {
572
- "content": "[unused38]",
573
- "lstrip": false,
574
- "normalized": true,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": false
578
- },
579
- "50324": {
580
- "content": "[unused39]",
581
- "lstrip": false,
582
- "normalized": true,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": false
586
- },
587
- "50325": {
588
- "content": "[unused40]",
589
- "lstrip": false,
590
- "normalized": true,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": false
594
- },
595
- "50326": {
596
- "content": "[unused41]",
597
- "lstrip": false,
598
- "normalized": true,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": false
602
- },
603
- "50327": {
604
- "content": "[unused42]",
605
- "lstrip": false,
606
- "normalized": true,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": false
610
- },
611
- "50328": {
612
- "content": "[unused43]",
613
- "lstrip": false,
614
- "normalized": true,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": false
618
- },
619
- "50329": {
620
- "content": "[unused44]",
621
- "lstrip": false,
622
- "normalized": true,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": false
626
- },
627
- "50330": {
628
- "content": "[unused45]",
629
- "lstrip": false,
630
- "normalized": true,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": false
634
- },
635
- "50331": {
636
- "content": "[unused46]",
637
- "lstrip": false,
638
- "normalized": true,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": false
642
- },
643
- "50332": {
644
- "content": "[unused47]",
645
- "lstrip": false,
646
- "normalized": true,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": false
650
- },
651
- "50333": {
652
- "content": "[unused48]",
653
- "lstrip": false,
654
- "normalized": true,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": false
658
- },
659
- "50334": {
660
- "content": "[unused49]",
661
- "lstrip": false,
662
- "normalized": true,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": false
666
- },
667
- "50335": {
668
- "content": "[unused50]",
669
- "lstrip": false,
670
- "normalized": true,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": false
674
- },
675
- "50336": {
676
- "content": "[unused51]",
677
- "lstrip": false,
678
- "normalized": true,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": false
682
- },
683
- "50337": {
684
- "content": "[unused52]",
685
- "lstrip": false,
686
- "normalized": true,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": false
690
- },
691
- "50338": {
692
- "content": "[unused53]",
693
- "lstrip": false,
694
- "normalized": true,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": false
698
- },
699
- "50339": {
700
- "content": "[unused54]",
701
- "lstrip": false,
702
- "normalized": true,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": false
706
- },
707
- "50340": {
708
- "content": "[unused55]",
709
- "lstrip": false,
710
- "normalized": true,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": false
714
- },
715
- "50341": {
716
- "content": "[unused56]",
717
- "lstrip": false,
718
- "normalized": true,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": false
722
- },
723
- "50342": {
724
- "content": "[unused57]",
725
- "lstrip": false,
726
- "normalized": true,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": false
730
- },
731
- "50343": {
732
- "content": "[unused58]",
733
- "lstrip": false,
734
- "normalized": true,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": false
738
- },
739
- "50344": {
740
- "content": "[unused59]",
741
- "lstrip": false,
742
- "normalized": true,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": false
746
- },
747
- "50345": {
748
- "content": "[unused60]",
749
- "lstrip": false,
750
- "normalized": true,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": false
754
- },
755
- "50346": {
756
- "content": "[unused61]",
757
- "lstrip": false,
758
- "normalized": true,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": false
762
- },
763
- "50347": {
764
- "content": "[unused62]",
765
- "lstrip": false,
766
- "normalized": true,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": false
770
- },
771
- "50348": {
772
- "content": "[unused63]",
773
- "lstrip": false,
774
- "normalized": true,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": false
778
- },
779
- "50349": {
780
- "content": "[unused64]",
781
- "lstrip": false,
782
- "normalized": true,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": false
786
- },
787
- "50350": {
788
- "content": "[unused65]",
789
- "lstrip": false,
790
- "normalized": true,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": false
794
- },
795
- "50351": {
796
- "content": "[unused66]",
797
- "lstrip": false,
798
- "normalized": true,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": false
802
- },
803
- "50352": {
804
- "content": "[unused67]",
805
- "lstrip": false,
806
- "normalized": true,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": false
810
- },
811
- "50353": {
812
- "content": "[unused68]",
813
- "lstrip": false,
814
- "normalized": true,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": false
818
- },
819
- "50354": {
820
- "content": "[unused69]",
821
- "lstrip": false,
822
- "normalized": true,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": false
826
- },
827
- "50355": {
828
- "content": "[unused70]",
829
- "lstrip": false,
830
- "normalized": true,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": false
834
- },
835
- "50356": {
836
- "content": "[unused71]",
837
- "lstrip": false,
838
- "normalized": true,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": false
842
- },
843
- "50357": {
844
- "content": "[unused72]",
845
- "lstrip": false,
846
- "normalized": true,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": false
850
- },
851
- "50358": {
852
- "content": "[unused73]",
853
- "lstrip": false,
854
- "normalized": true,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": false
858
- },
859
- "50359": {
860
- "content": "[unused74]",
861
- "lstrip": false,
862
- "normalized": true,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": false
866
- },
867
- "50360": {
868
- "content": "[unused75]",
869
- "lstrip": false,
870
- "normalized": true,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": false
874
- },
875
- "50361": {
876
- "content": "[unused76]",
877
- "lstrip": false,
878
- "normalized": true,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": false
882
- },
883
- "50362": {
884
- "content": "[unused77]",
885
- "lstrip": false,
886
- "normalized": true,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": false
890
- },
891
- "50363": {
892
- "content": "[unused78]",
893
- "lstrip": false,
894
- "normalized": true,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": false
898
- },
899
- "50364": {
900
- "content": "[unused79]",
901
- "lstrip": false,
902
- "normalized": true,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": false
906
- },
907
- "50365": {
908
- "content": "[unused80]",
909
- "lstrip": false,
910
- "normalized": true,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": false
914
- },
915
- "50366": {
916
- "content": "[unused81]",
917
- "lstrip": false,
918
- "normalized": true,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": false
922
- },
923
- "50367": {
924
- "content": "[unused82]",
925
- "lstrip": false,
926
- "normalized": true,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": false
930
- }
931
- },
932
- "clean_up_tokenization_spaces": true,
933
- "cls_token": "[CLS]",
934
- "extra_special_tokens": {},
935
- "mask_token": "[MASK]",
936
- "model_input_names": [
937
- "input_ids",
938
- "attention_mask"
939
- ],
940
- "model_max_length": 512,
941
- "pad_token": "[PAD]",
942
- "sep_token": "[SEP]",
943
- "tokenizer_class": "PreTrainedTokenizerFast",
944
- "unk_token": "[UNK]"
945
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
SynFinBERT_Final/checkpoint-31439/trainer_state.json DELETED
@@ -1,2480 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 1.0,
6
- "eval_steps": 1000,
7
- "global_step": 31439,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.003180813333969496,
14
- "grad_norm": 1.9245424270629883,
15
- "learning_rate": 0.00015714285714285713,
16
- "loss": 8.2575,
17
- "step": 100
18
- },
19
- {
20
- "epoch": 0.006361626667938992,
21
- "grad_norm": 1.3761227130889893,
22
- "learning_rate": 0.0003158730158730159,
23
- "loss": 5.5783,
24
- "step": 200
25
- },
26
- {
27
- "epoch": 0.009542440001908488,
28
- "grad_norm": 0.9447478652000427,
29
- "learning_rate": 0.00047460317460317457,
30
- "loss": 4.4497,
31
- "step": 300
32
- },
33
- {
34
- "epoch": 0.012723253335877984,
35
- "grad_norm": 0.7075384259223938,
36
- "learning_rate": 0.0004999910138240998,
37
- "loss": 3.9116,
38
- "step": 400
39
- },
40
- {
41
- "epoch": 0.01590406666984748,
42
- "grad_norm": 0.8543815612792969,
43
- "learning_rate": 0.0004999568836382269,
44
- "loss": 3.5602,
45
- "step": 500
46
- },
47
- {
48
- "epoch": 0.019084880003816976,
49
- "grad_norm": 0.6527402400970459,
50
- "learning_rate": 0.0004998972868887552,
51
- "loss": 3.3212,
52
- "step": 600
53
- },
54
- {
55
- "epoch": 0.022265693337786472,
56
- "grad_norm": 0.6321170330047607,
57
- "learning_rate": 0.0004998122296476297,
58
- "loss": 3.1642,
59
- "step": 700
60
- },
61
- {
62
- "epoch": 0.025446506671755968,
63
- "grad_norm": 0.559657633304596,
64
- "learning_rate": 0.0004997017205808072,
65
- "loss": 3.0596,
66
- "step": 800
67
- },
68
- {
69
- "epoch": 0.028627320005725463,
70
- "grad_norm": 0.552664041519165,
71
- "learning_rate": 0.0004995657709473746,
72
- "loss": 2.9709,
73
- "step": 900
74
- },
75
- {
76
- "epoch": 0.03180813333969496,
77
- "grad_norm": 0.5550724267959595,
78
- "learning_rate": 0.0004994043945984006,
79
- "loss": 2.9082,
80
- "step": 1000
81
- },
82
- {
83
- "epoch": 0.03180813333969496,
84
- "eval_loss": 2.8737545013427734,
85
- "eval_runtime": 37.1294,
86
- "eval_samples_per_second": 433.969,
87
- "eval_steps_per_second": 0.862,
88
- "step": 1000
89
- },
90
- {
91
- "epoch": 0.03498894667366446,
92
- "grad_norm": 0.509844958782196,
93
- "learning_rate": 0.0004992176079755249,
94
- "loss": 2.8425,
95
- "step": 1100
96
- },
97
- {
98
- "epoch": 0.03816976000763395,
99
- "grad_norm": 0.5158022046089172,
100
- "learning_rate": 0.0004990054301092832,
101
- "loss": 2.7958,
102
- "step": 1200
103
- },
104
- {
105
- "epoch": 0.04135057334160345,
106
- "grad_norm": 0.5071324706077576,
107
- "learning_rate": 0.0004987678826171686,
108
- "loss": 2.7506,
109
- "step": 1300
110
- },
111
- {
112
- "epoch": 0.044531386675572944,
113
- "grad_norm": 0.50673907995224,
114
- "learning_rate": 0.000498504989701428,
115
- "loss": 2.7146,
116
- "step": 1400
117
- },
118
- {
119
- "epoch": 0.04771220000954244,
120
- "grad_norm": 0.4866410493850708,
121
- "learning_rate": 0.0004982167781465977,
122
- "loss": 2.6794,
123
- "step": 1500
124
- },
125
- {
126
- "epoch": 0.050893013343511935,
127
- "grad_norm": 0.46448996663093567,
128
- "learning_rate": 0.0004979032773167736,
129
- "loss": 2.6494,
130
- "step": 1600
131
- },
132
- {
133
- "epoch": 0.05407382667748143,
134
- "grad_norm": 0.4766246974468231,
135
- "learning_rate": 0.0004975645191526194,
136
- "loss": 2.619,
137
- "step": 1700
138
- },
139
- {
140
- "epoch": 0.057254640011450926,
141
- "grad_norm": 0.48844242095947266,
142
- "learning_rate": 0.0004972005381681131,
143
- "loss": 2.5985,
144
- "step": 1800
145
- },
146
- {
147
- "epoch": 0.06043545334542042,
148
- "grad_norm": 0.4767601490020752,
149
- "learning_rate": 0.0004968113714470298,
150
- "loss": 2.5745,
151
- "step": 1900
152
- },
153
- {
154
- "epoch": 0.06361626667938992,
155
- "grad_norm": 0.4597737789154053,
156
- "learning_rate": 0.000496397058639164,
157
- "loss": 2.5532,
158
- "step": 2000
159
- },
160
- {
161
- "epoch": 0.06361626667938992,
162
- "eval_loss": 2.547260046005249,
163
- "eval_runtime": 32.0508,
164
- "eval_samples_per_second": 502.733,
165
- "eval_steps_per_second": 0.998,
166
- "step": 2000
167
- },
168
- {
169
- "epoch": 0.06679708001335942,
170
- "grad_norm": 0.4578069746494293,
171
- "learning_rate": 0.0004959576419562898,
172
- "loss": 2.533,
173
- "step": 2100
174
- },
175
- {
176
- "epoch": 0.06997789334732891,
177
- "grad_norm": 0.44575053453445435,
178
- "learning_rate": 0.0004954931661678598,
179
- "loss": 2.5119,
180
- "step": 2200
181
- },
182
- {
183
- "epoch": 0.07315870668129841,
184
- "grad_norm": 0.47240403294563293,
185
- "learning_rate": 0.0004950036785964443,
186
- "loss": 2.4937,
187
- "step": 2300
188
- },
189
- {
190
- "epoch": 0.0763395200152679,
191
- "grad_norm": 0.45646390318870544,
192
- "learning_rate": 0.0004944892291129098,
193
- "loss": 2.4813,
194
- "step": 2400
195
- },
196
- {
197
- "epoch": 0.0795203333492374,
198
- "grad_norm": 0.4440775215625763,
199
- "learning_rate": 0.0004939498701313381,
200
- "loss": 2.4616,
201
- "step": 2500
202
- },
203
- {
204
- "epoch": 0.0827011466832069,
205
- "grad_norm": 0.4970929026603699,
206
- "learning_rate": 0.0004933856566036854,
207
- "loss": 2.4481,
208
- "step": 2600
209
- },
210
- {
211
- "epoch": 0.08588196001717639,
212
- "grad_norm": 0.46313849091529846,
213
- "learning_rate": 0.0004927966460141848,
214
- "loss": 2.4384,
215
- "step": 2700
216
- },
217
- {
218
- "epoch": 0.08906277335114589,
219
- "grad_norm": 0.422512024641037,
220
- "learning_rate": 0.0004921828983734884,
221
- "loss": 2.4258,
222
- "step": 2800
223
- },
224
- {
225
- "epoch": 0.09224358668511538,
226
- "grad_norm": 0.4723884165287018,
227
- "learning_rate": 0.0004915444762125541,
228
- "loss": 2.4058,
229
- "step": 2900
230
- },
231
- {
232
- "epoch": 0.09542440001908488,
233
- "grad_norm": 0.40491607785224915,
234
- "learning_rate": 0.0004908814445762739,
235
- "loss": 2.3983,
236
- "step": 3000
237
- },
238
- {
239
- "epoch": 0.09542440001908488,
240
- "eval_loss": 2.3913981914520264,
241
- "eval_runtime": 31.9986,
242
- "eval_samples_per_second": 503.553,
243
- "eval_steps_per_second": 1.0,
244
- "step": 3000
245
- },
246
- {
247
- "epoch": 0.09860521335305437,
248
- "grad_norm": 0.43458184599876404,
249
- "learning_rate": 0.0004901938710168477,
250
- "loss": 2.386,
251
- "step": 3100
252
- },
253
- {
254
- "epoch": 0.10178602668702387,
255
- "grad_norm": 0.41318026185035706,
256
- "learning_rate": 0.0004894818255869004,
257
- "loss": 2.3747,
258
- "step": 3200
259
- },
260
- {
261
- "epoch": 0.10496684002099337,
262
- "grad_norm": 0.4289224147796631,
263
- "learning_rate": 0.0004887453808323446,
264
- "loss": 2.3683,
265
- "step": 3300
266
- },
267
- {
268
- "epoch": 0.10814765335496286,
269
- "grad_norm": 0.4377734363079071,
270
- "learning_rate": 0.000487984611784989,
271
- "loss": 2.3549,
272
- "step": 3400
273
- },
274
- {
275
- "epoch": 0.11132846668893236,
276
- "grad_norm": 0.3928932249546051,
277
- "learning_rate": 0.0004871995959548951,
278
- "loss": 2.3439,
279
- "step": 3500
280
- },
281
- {
282
- "epoch": 0.11450928002290185,
283
- "grad_norm": 0.4452105164527893,
284
- "learning_rate": 0.0004863904133224789,
285
- "loss": 2.3322,
286
- "step": 3600
287
- },
288
- {
289
- "epoch": 0.11769009335687135,
290
- "grad_norm": 0.4529866874217987,
291
- "learning_rate": 0.0004855571463303627,
292
- "loss": 2.3251,
293
- "step": 3700
294
- },
295
- {
296
- "epoch": 0.12087090669084084,
297
- "grad_norm": 0.49562081694602966,
298
- "learning_rate": 0.0004846998798749759,
299
- "loss": 2.3166,
300
- "step": 3800
301
- },
302
- {
303
- "epoch": 0.12405172002481034,
304
- "grad_norm": 0.39936354756355286,
305
- "learning_rate": 0.00048381870129790436,
306
- "loss": 2.3091,
307
- "step": 3900
308
- },
309
- {
310
- "epoch": 0.12723253335877985,
311
- "grad_norm": 0.4315975606441498,
312
- "learning_rate": 0.00048291370037699296,
313
- "loss": 2.3017,
314
- "step": 4000
315
- },
316
- {
317
- "epoch": 0.12723253335877985,
318
- "eval_loss": 2.2949767112731934,
319
- "eval_runtime": 32.0898,
320
- "eval_samples_per_second": 502.122,
321
- "eval_steps_per_second": 0.997,
322
- "step": 4000
323
- },
324
- {
325
- "epoch": 0.13041334669274934,
326
- "grad_norm": 0.44965338706970215,
327
- "learning_rate": 0.0004819849693171978,
328
- "loss": 2.2935,
329
- "step": 4100
330
- },
331
- {
332
- "epoch": 0.13359416002671884,
333
- "grad_norm": 0.43626508116722107,
334
- "learning_rate": 0.00048103260274119257,
335
- "loss": 2.2907,
336
- "step": 4200
337
- },
338
- {
339
- "epoch": 0.13677497336068833,
340
- "grad_norm": 0.43389347195625305,
341
- "learning_rate": 0.00048005669767972755,
342
- "loss": 2.278,
343
- "step": 4300
344
- },
345
- {
346
- "epoch": 0.13995578669465783,
347
- "grad_norm": 0.38533300161361694,
348
- "learning_rate": 0.0004790573535617441,
349
- "loss": 2.2703,
350
- "step": 4400
351
- },
352
- {
353
- "epoch": 0.14313660002862733,
354
- "grad_norm": 0.42043280601501465,
355
- "learning_rate": 0.0004780346722042441,
356
- "loss": 2.2663,
357
- "step": 4500
358
- },
359
- {
360
- "epoch": 0.14631741336259682,
361
- "grad_norm": 0.447324275970459,
362
- "learning_rate": 0.0004769887578019171,
363
- "loss": 2.2591,
364
- "step": 4600
365
- },
366
- {
367
- "epoch": 0.14949822669656632,
368
- "grad_norm": 0.4006219804286957,
369
- "learning_rate": 0.0004759197169165237,
370
- "loss": 2.2544,
371
- "step": 4700
372
- },
373
- {
374
- "epoch": 0.1526790400305358,
375
- "grad_norm": 0.42128533124923706,
376
- "learning_rate": 0.0004748276584660395,
377
- "loss": 2.2456,
378
- "step": 4800
379
- },
380
- {
381
- "epoch": 0.1558598533645053,
382
- "grad_norm": 0.4116060137748718,
383
- "learning_rate": 0.0004737126937135573,
384
- "loss": 2.2373,
385
- "step": 4900
386
- },
387
- {
388
- "epoch": 0.1590406666984748,
389
- "grad_norm": 0.39447852969169617,
390
- "learning_rate": 0.0004725749362559518,
391
- "loss": 2.2334,
392
- "step": 5000
393
- },
394
- {
395
- "epoch": 0.1590406666984748,
396
- "eval_loss": 2.2271738052368164,
397
- "eval_runtime": 32.1504,
398
- "eval_samples_per_second": 501.176,
399
- "eval_steps_per_second": 0.995,
400
- "step": 5000
401
- },
402
- {
403
- "epoch": 0.1622214800324443,
404
- "grad_norm": 0.39155691862106323,
405
- "learning_rate": 0.0004714145020123056,
406
- "loss": 2.2248,
407
- "step": 5100
408
- },
409
- {
410
- "epoch": 0.1654022933664138,
411
- "grad_norm": 0.409030944108963,
412
- "learning_rate": 0.00047023150921209924,
413
- "loss": 2.2218,
414
- "step": 5200
415
- },
416
- {
417
- "epoch": 0.1685831067003833,
418
- "grad_norm": 0.3944612741470337,
419
- "learning_rate": 0.000469026078383165,
420
- "loss": 2.2159,
421
- "step": 5300
422
- },
423
- {
424
- "epoch": 0.17176392003435278,
425
- "grad_norm": 0.406745970249176,
426
- "learning_rate": 0.0004677983323394076,
427
- "loss": 2.2117,
428
- "step": 5400
429
- },
430
- {
431
- "epoch": 0.17494473336832228,
432
- "grad_norm": 0.3991977274417877,
433
- "learning_rate": 0.00046654839616829094,
434
- "loss": 2.208,
435
- "step": 5500
436
- },
437
- {
438
- "epoch": 0.17812554670229178,
439
- "grad_norm": 0.41435664892196655,
440
- "learning_rate": 0.00046527639721809434,
441
- "loss": 2.2043,
442
- "step": 5600
443
- },
444
- {
445
- "epoch": 0.18130636003626127,
446
- "grad_norm": 0.4246859550476074,
447
- "learning_rate": 0.00046398246508493735,
448
- "loss": 2.1993,
449
- "step": 5700
450
- },
451
- {
452
- "epoch": 0.18448717337023077,
453
- "grad_norm": 0.39352065324783325,
454
- "learning_rate": 0.00046266673159957593,
455
- "loss": 2.1913,
456
- "step": 5800
457
- },
458
- {
459
- "epoch": 0.18766798670420026,
460
- "grad_norm": 0.4190274775028229,
461
- "learning_rate": 0.00046132933081397145,
462
- "loss": 2.1853,
463
- "step": 5900
464
- },
465
- {
466
- "epoch": 0.19084880003816976,
467
- "grad_norm": 0.3737799823284149,
468
- "learning_rate": 0.00045997039898763257,
469
- "loss": 2.1815,
470
- "step": 6000
471
- },
472
- {
473
- "epoch": 0.19084880003816976,
474
- "eval_loss": 2.181905746459961,
475
- "eval_runtime": 32.0284,
476
- "eval_samples_per_second": 503.085,
477
- "eval_steps_per_second": 0.999,
478
- "step": 6000
479
- },
480
- {
481
- "epoch": 0.19402961337213925,
482
- "grad_norm": 0.43058380484580994,
483
- "learning_rate": 0.0004585900745737328,
484
- "loss": 2.1757,
485
- "step": 6100
486
- },
487
- {
488
- "epoch": 0.19721042670610875,
489
- "grad_norm": 0.42727747559547424,
490
- "learning_rate": 0.00045718849820500435,
491
- "loss": 2.1738,
492
- "step": 6200
493
- },
494
- {
495
- "epoch": 0.20039124004007824,
496
- "grad_norm": 0.39294204115867615,
497
- "learning_rate": 0.0004557658126794099,
498
- "loss": 2.1666,
499
- "step": 6300
500
- },
501
- {
502
- "epoch": 0.20357205337404774,
503
- "grad_norm": 0.417127788066864,
504
- "learning_rate": 0.00045432216294559365,
505
- "loss": 2.1634,
506
- "step": 6400
507
- },
508
- {
509
- "epoch": 0.20675286670801724,
510
- "grad_norm": 0.4131268262863159,
511
- "learning_rate": 0.0004528576960881137,
512
- "loss": 2.1583,
513
- "step": 6500
514
- },
515
- {
516
- "epoch": 0.20993368004198673,
517
- "grad_norm": 0.39781948924064636,
518
- "learning_rate": 0.0004513725613124564,
519
- "loss": 2.1584,
520
- "step": 6600
521
- },
522
- {
523
- "epoch": 0.21311449337595623,
524
- "grad_norm": 0.40540438890457153,
525
- "learning_rate": 0.0004498669099298344,
526
- "loss": 2.1536,
527
- "step": 6700
528
- },
529
- {
530
- "epoch": 0.21629530670992572,
531
- "grad_norm": 0.389057993888855,
532
- "learning_rate": 0.000448340895341771,
533
- "loss": 2.1477,
534
- "step": 6800
535
- },
536
- {
537
- "epoch": 0.21947612004389522,
538
- "grad_norm": 0.39187559485435486,
539
- "learning_rate": 0.00044679467302447077,
540
- "loss": 2.1432,
541
- "step": 6900
542
- },
543
- {
544
- "epoch": 0.2226569333778647,
545
- "grad_norm": 0.4060874879360199,
546
- "learning_rate": 0.000445228400512979,
547
- "loss": 2.1402,
548
- "step": 7000
549
- },
550
- {
551
- "epoch": 0.2226569333778647,
552
- "eval_loss": 2.1366310119628906,
553
- "eval_runtime": 32.0552,
554
- "eval_samples_per_second": 502.665,
555
- "eval_steps_per_second": 0.998,
556
- "step": 7000
557
- },
558
- {
559
- "epoch": 0.2258377467118342,
560
- "grad_norm": 0.38960784673690796,
561
- "learning_rate": 0.0004436422373851313,
562
- "loss": 2.1386,
563
- "step": 7100
564
- },
565
- {
566
- "epoch": 0.2290185600458037,
567
- "grad_norm": 0.39033639430999756,
568
- "learning_rate": 0.00044203634524529566,
569
- "loss": 2.1321,
570
- "step": 7200
571
- },
572
- {
573
- "epoch": 0.2321993733797732,
574
- "grad_norm": 0.3941997289657593,
575
- "learning_rate": 0.00044041088770790715,
576
- "loss": 2.1275,
577
- "step": 7300
578
- },
579
- {
580
- "epoch": 0.2353801867137427,
581
- "grad_norm": 0.39588111639022827,
582
- "learning_rate": 0.00043876603038079846,
583
- "loss": 2.1256,
584
- "step": 7400
585
- },
586
- {
587
- "epoch": 0.2385610000477122,
588
- "grad_norm": 0.403410404920578,
589
- "learning_rate": 0.0004371019408483269,
590
- "loss": 2.1221,
591
- "step": 7500
592
- },
593
- {
594
- "epoch": 0.24174181338168169,
595
- "grad_norm": 0.39031487703323364,
596
- "learning_rate": 0.00043541878865430064,
597
- "loss": 2.119,
598
- "step": 7600
599
- },
600
- {
601
- "epoch": 0.24492262671565118,
602
- "grad_norm": 0.3408244252204895,
603
- "learning_rate": 0.0004337167452847046,
604
- "loss": 2.1166,
605
- "step": 7700
606
- },
607
- {
608
- "epoch": 0.24810344004962068,
609
- "grad_norm": 0.3924653232097626,
610
- "learning_rate": 0.0004319959841502292,
611
- "loss": 2.1061,
612
- "step": 7800
613
- },
614
- {
615
- "epoch": 0.2512842533835902,
616
- "grad_norm": 0.3763435184955597,
617
- "learning_rate": 0.000430256680568602,
618
- "loss": 2.107,
619
- "step": 7900
620
- },
621
- {
622
- "epoch": 0.2544650667175597,
623
- "grad_norm": 0.40163588523864746,
624
- "learning_rate": 0.00042849901174672625,
625
- "loss": 2.1038,
626
- "step": 8000
627
- },
628
- {
629
- "epoch": 0.2544650667175597,
630
- "eval_loss": 2.0991036891937256,
631
- "eval_runtime": 32.1051,
632
- "eval_samples_per_second": 501.883,
633
- "eval_steps_per_second": 0.997,
634
- "step": 8000
635
- },
636
- {
637
- "epoch": 0.25764588005152916,
638
- "grad_norm": 0.3803541958332062,
639
- "learning_rate": 0.0004267231567626261,
640
- "loss": 2.101,
641
- "step": 8100
642
- },
643
- {
644
- "epoch": 0.2608266933854987,
645
- "grad_norm": 0.40202075242996216,
646
- "learning_rate": 0.0004249292965472013,
647
- "loss": 2.0927,
648
- "step": 8200
649
- },
650
- {
651
- "epoch": 0.26400750671946815,
652
- "grad_norm": 0.37971481680870056,
653
- "learning_rate": 0.0004231176138657938,
654
- "loss": 2.0911,
655
- "step": 8300
656
- },
657
- {
658
- "epoch": 0.2671883200534377,
659
- "grad_norm": 0.39614948630332947,
660
- "learning_rate": 0.00042128829329956624,
661
- "loss": 2.091,
662
- "step": 8400
663
- },
664
- {
665
- "epoch": 0.27036913338740715,
666
- "grad_norm": 0.36135661602020264,
667
- "learning_rate": 0.00041944152122669673,
668
- "loss": 2.0877,
669
- "step": 8500
670
- },
671
- {
672
- "epoch": 0.27354994672137667,
673
- "grad_norm": 0.3757850229740143,
674
- "learning_rate": 0.00041757748580338935,
675
- "loss": 2.0812,
676
- "step": 8600
677
- },
678
- {
679
- "epoch": 0.27673076005534614,
680
- "grad_norm": 0.38584986329078674,
681
- "learning_rate": 0.0004156963769447046,
682
- "loss": 2.078,
683
- "step": 8700
684
- },
685
- {
686
- "epoch": 0.27991157338931566,
687
- "grad_norm": 0.37738028168678284,
688
- "learning_rate": 0.00041379838630520977,
689
- "loss": 2.0761,
690
- "step": 8800
691
- },
692
- {
693
- "epoch": 0.2830923867232851,
694
- "grad_norm": 0.3486759066581726,
695
- "learning_rate": 0.0004118837072594527,
696
- "loss": 2.0754,
697
- "step": 8900
698
- },
699
- {
700
- "epoch": 0.28627320005725465,
701
- "grad_norm": 0.4099483788013458,
702
- "learning_rate": 0.0004099525348822597,
703
- "loss": 2.0734,
704
- "step": 9000
705
- },
706
- {
707
- "epoch": 0.28627320005725465,
708
- "eval_loss": 2.068845272064209,
709
- "eval_runtime": 32.0981,
710
- "eval_samples_per_second": 501.992,
711
- "eval_steps_per_second": 0.997,
712
- "step": 9000
713
- },
714
- {
715
- "epoch": 0.2894540133912241,
716
- "grad_norm": 0.3736860454082489,
717
- "learning_rate": 0.0004080050659288609,
718
- "loss": 2.0665,
719
- "step": 9100
720
- },
721
- {
722
- "epoch": 0.29263482672519364,
723
- "grad_norm": 0.45644745230674744,
724
- "learning_rate": 0.00040604149881484414,
725
- "loss": 2.0636,
726
- "step": 9200
727
- },
728
- {
729
- "epoch": 0.2958156400591631,
730
- "grad_norm": 0.3984236717224121,
731
- "learning_rate": 0.0004040620335959391,
732
- "loss": 2.0662,
733
- "step": 9300
734
- },
735
- {
736
- "epoch": 0.29899645339313263,
737
- "grad_norm": 0.38279175758361816,
738
- "learning_rate": 0.0004020668719476355,
739
- "loss": 2.0641,
740
- "step": 9400
741
- },
742
- {
743
- "epoch": 0.3021772667271021,
744
- "grad_norm": 0.3570825755596161,
745
- "learning_rate": 0.00040005621714463515,
746
- "loss": 2.0555,
747
- "step": 9500
748
- },
749
- {
750
- "epoch": 0.3053580800610716,
751
- "grad_norm": 0.3757265508174896,
752
- "learning_rate": 0.0003980302740401418,
753
- "loss": 2.0549,
754
- "step": 9600
755
- },
756
- {
757
- "epoch": 0.3085388933950411,
758
- "grad_norm": 0.3575412929058075,
759
- "learning_rate": 0.00039598924904498995,
760
- "loss": 2.056,
761
- "step": 9700
762
- },
763
- {
764
- "epoch": 0.3117197067290106,
765
- "grad_norm": 0.36262449622154236,
766
- "learning_rate": 0.00039393335010661466,
767
- "loss": 2.0483,
768
- "step": 9800
769
- },
770
- {
771
- "epoch": 0.3149005200629801,
772
- "grad_norm": 0.3891037106513977,
773
- "learning_rate": 0.00039186278668786533,
774
- "loss": 2.043,
775
- "step": 9900
776
- },
777
- {
778
- "epoch": 0.3180813333969496,
779
- "grad_norm": 0.38782525062561035,
780
- "learning_rate": 0.0003897777697456647,
781
- "loss": 2.0415,
782
- "step": 10000
783
- },
784
- {
785
- "epoch": 0.3180813333969496,
786
- "eval_loss": 2.039027214050293,
787
- "eval_runtime": 32.0723,
788
- "eval_samples_per_second": 502.397,
789
- "eval_steps_per_second": 0.998,
790
- "step": 10000
791
- },
792
- {
793
- "epoch": 0.3212621467309191,
794
- "grad_norm": 0.3567207157611847,
795
- "learning_rate": 0.0003876785117095157,
796
- "loss": 2.0387,
797
- "step": 10100
798
- },
799
- {
800
- "epoch": 0.3244429600648886,
801
- "grad_norm": 0.40384364128112793,
802
- "learning_rate": 0.00038556522645985866,
803
- "loss": 2.0385,
804
- "step": 10200
805
- },
806
- {
807
- "epoch": 0.32762377339885806,
808
- "grad_norm": 0.36394068598747253,
809
- "learning_rate": 0.00038343812930627966,
810
- "loss": 2.0339,
811
- "step": 10300
812
- },
813
- {
814
- "epoch": 0.3308045867328276,
815
- "grad_norm": 0.3727739453315735,
816
- "learning_rate": 0.00038129743696557473,
817
- "loss": 2.0361,
818
- "step": 10400
819
- },
820
- {
821
- "epoch": 0.33398540006679706,
822
- "grad_norm": 0.3734021782875061,
823
- "learning_rate": 0.0003791433675396695,
824
- "loss": 2.0337,
825
- "step": 10500
826
- },
827
- {
828
- "epoch": 0.3371662134007666,
829
- "grad_norm": 0.3800587058067322,
830
- "learning_rate": 0.0003769761404933981,
831
- "loss": 2.0293,
832
- "step": 10600
833
- },
834
- {
835
- "epoch": 0.34034702673473605,
836
- "grad_norm": 0.3707159161567688,
837
- "learning_rate": 0.0003747959766321437,
838
- "loss": 2.026,
839
- "step": 10700
840
- },
841
- {
842
- "epoch": 0.34352784006870557,
843
- "grad_norm": 0.38164591789245605,
844
- "learning_rate": 0.0003726030980793411,
845
- "loss": 2.0239,
846
- "step": 10800
847
- },
848
- {
849
- "epoch": 0.34670865340267504,
850
- "grad_norm": 0.41090521216392517,
851
- "learning_rate": 0.000370397728253847,
852
- "loss": 2.0232,
853
- "step": 10900
854
- },
855
- {
856
- "epoch": 0.34988946673664456,
857
- "grad_norm": 0.36883971095085144,
858
- "learning_rate": 0.00036818009184717664,
859
- "loss": 2.0189,
860
- "step": 11000
861
- },
862
- {
863
- "epoch": 0.34988946673664456,
864
- "eval_loss": 2.0191915035247803,
865
- "eval_runtime": 32.0579,
866
- "eval_samples_per_second": 502.622,
867
- "eval_steps_per_second": 0.998,
868
- "step": 11000
869
- },
870
- {
871
- "epoch": 0.35307028007061403,
872
- "grad_norm": 0.37279367446899414,
873
- "learning_rate": 0.00036595041480061137,
874
- "loss": 2.0145,
875
- "step": 11100
876
- },
877
- {
878
- "epoch": 0.35625109340458355,
879
- "grad_norm": 0.37609952688217163,
880
- "learning_rate": 0.0003637089242821792,
881
- "loss": 2.0165,
882
- "step": 11200
883
- },
884
- {
885
- "epoch": 0.3594319067385531,
886
- "grad_norm": 0.3822253346443176,
887
- "learning_rate": 0.00036145584866350953,
888
- "loss": 2.0114,
889
- "step": 11300
890
- },
891
- {
892
- "epoch": 0.36261272007252254,
893
- "grad_norm": 0.36375653743743896,
894
- "learning_rate": 0.0003591914174965664,
895
- "loss": 2.0045,
896
- "step": 11400
897
- },
898
- {
899
- "epoch": 0.36579353340649207,
900
- "grad_norm": 0.3662492334842682,
901
- "learning_rate": 0.0003569158614902605,
902
- "loss": 2.0068,
903
- "step": 11500
904
- },
905
- {
906
- "epoch": 0.36897434674046153,
907
- "grad_norm": 0.35436445474624634,
908
- "learning_rate": 0.00035462941248694355,
909
- "loss": 2.003,
910
- "step": 11600
911
- },
912
- {
913
- "epoch": 0.37215516007443106,
914
- "grad_norm": 0.3709911108016968,
915
- "learning_rate": 0.00035233230343878757,
916
- "loss": 2.0003,
917
- "step": 11700
918
- },
919
- {
920
- "epoch": 0.3753359734084005,
921
- "grad_norm": 0.3669358193874359,
922
- "learning_rate": 0.00035002476838405077,
923
- "loss": 2.0022,
924
- "step": 11800
925
- },
926
- {
927
- "epoch": 0.37851678674237005,
928
- "grad_norm": 0.374642938375473,
929
- "learning_rate": 0.00034770704242323284,
930
- "loss": 1.9996,
931
- "step": 11900
932
- },
933
- {
934
- "epoch": 0.3816976000763395,
935
- "grad_norm": 0.35377413034439087,
936
- "learning_rate": 0.00034537936169512187,
937
- "loss": 1.9964,
938
- "step": 12000
939
- },
940
- {
941
- "epoch": 0.3816976000763395,
942
- "eval_loss": 1.9996683597564697,
943
- "eval_runtime": 32.0932,
944
- "eval_samples_per_second": 502.068,
945
- "eval_steps_per_second": 0.997,
946
- "step": 12000
947
- },
948
- {
949
- "epoch": 0.38487841341030904,
950
- "grad_norm": 0.3758770227432251,
951
- "learning_rate": 0.0003430419633527356,
952
- "loss": 1.9945,
953
- "step": 12100
954
- },
955
- {
956
- "epoch": 0.3880592267442785,
957
- "grad_norm": 0.37386536598205566,
958
- "learning_rate": 0.0003406950855391599,
959
- "loss": 1.996,
960
- "step": 12200
961
- },
962
- {
963
- "epoch": 0.39124004007824803,
964
- "grad_norm": 0.34490686655044556,
965
- "learning_rate": 0.00033833896736328506,
966
- "loss": 1.9894,
967
- "step": 12300
968
- },
969
- {
970
- "epoch": 0.3944208534122175,
971
- "grad_norm": 0.3701495826244354,
972
- "learning_rate": 0.000335973848875445,
973
- "loss": 1.9845,
974
- "step": 12400
975
- },
976
- {
977
- "epoch": 0.397601666746187,
978
- "grad_norm": 0.3556259870529175,
979
- "learning_rate": 0.0003335999710429598,
980
- "loss": 1.9845,
981
- "step": 12500
982
- },
983
- {
984
- "epoch": 0.4007824800801565,
985
- "grad_norm": 0.37552258372306824,
986
- "learning_rate": 0.000331217575725585,
987
- "loss": 1.981,
988
- "step": 12600
989
- },
990
- {
991
- "epoch": 0.403963293414126,
992
- "grad_norm": 0.37759602069854736,
993
- "learning_rate": 0.0003288269056508703,
994
- "loss": 1.9809,
995
- "step": 12700
996
- },
997
- {
998
- "epoch": 0.4071441067480955,
999
- "grad_norm": 0.35288146138191223,
1000
- "learning_rate": 0.0003264282043894293,
1001
- "loss": 1.9768,
1002
- "step": 12800
1003
- },
1004
- {
1005
- "epoch": 0.410324920082065,
1006
- "grad_norm": 0.375748872756958,
1007
- "learning_rate": 0.0003240217163301233,
1008
- "loss": 1.9782,
1009
- "step": 12900
1010
- },
1011
- {
1012
- "epoch": 0.41350573341603447,
1013
- "grad_norm": 0.38310039043426514,
1014
- "learning_rate": 0.0003216076866551627,
1015
- "loss": 1.9775,
1016
- "step": 13000
1017
- },
1018
- {
1019
- "epoch": 0.41350573341603447,
1020
- "eval_loss": 1.9790679216384888,
1021
- "eval_runtime": 32.0933,
1022
- "eval_samples_per_second": 502.067,
1023
- "eval_steps_per_second": 0.997,
1024
- "step": 13000
1025
- },
1026
- {
1027
- "epoch": 0.416686546750004,
1028
- "grad_norm": 0.37241339683532715,
1029
- "learning_rate": 0.00031918636131512664,
1030
- "loss": 1.9779,
1031
- "step": 13100
1032
- },
1033
- {
1034
- "epoch": 0.41986736008397346,
1035
- "grad_norm": 0.35883447527885437,
1036
- "learning_rate": 0.00031675798700390415,
1037
- "loss": 1.9716,
1038
- "step": 13200
1039
- },
1040
- {
1041
- "epoch": 0.423048173417943,
1042
- "grad_norm": 0.35947349667549133,
1043
- "learning_rate": 0.0003143228111335608,
1044
- "loss": 1.9705,
1045
- "step": 13300
1046
- },
1047
- {
1048
- "epoch": 0.42622898675191245,
1049
- "grad_norm": 0.34600597620010376,
1050
- "learning_rate": 0.00031188108180913056,
1051
- "loss": 1.9693,
1052
- "step": 13400
1053
- },
1054
- {
1055
- "epoch": 0.429409800085882,
1056
- "grad_norm": 0.36847108602523804,
1057
- "learning_rate": 0.00030943304780333894,
1058
- "loss": 1.9681,
1059
- "step": 13500
1060
- },
1061
- {
1062
- "epoch": 0.43259061341985144,
1063
- "grad_norm": 0.39360311627388,
1064
- "learning_rate": 0.00030697895853125606,
1065
- "loss": 1.9622,
1066
- "step": 13600
1067
- },
1068
- {
1069
- "epoch": 0.43577142675382097,
1070
- "grad_norm": 0.3634871542453766,
1071
- "learning_rate": 0.00030451906402488593,
1072
- "loss": 1.9632,
1073
- "step": 13700
1074
- },
1075
- {
1076
- "epoch": 0.43895224008779044,
1077
- "grad_norm": 0.3304957151412964,
1078
- "learning_rate": 0.00030205361490769214,
1079
- "loss": 1.9616,
1080
- "step": 13800
1081
- },
1082
- {
1083
- "epoch": 0.44213305342175996,
1084
- "grad_norm": 0.37383607029914856,
1085
- "learning_rate": 0.0002995828623690629,
1086
- "loss": 1.9558,
1087
- "step": 13900
1088
- },
1089
- {
1090
- "epoch": 0.4453138667557294,
1091
- "grad_norm": 0.3472614288330078,
1092
- "learning_rate": 0.0002971070581387197,
1093
- "loss": 1.9542,
1094
- "step": 14000
1095
- },
1096
- {
1097
- "epoch": 0.4453138667557294,
1098
- "eval_loss": 1.9504029750823975,
1099
- "eval_runtime": 32.1006,
1100
- "eval_samples_per_second": 501.953,
1101
- "eval_steps_per_second": 0.997,
1102
- "step": 14000
1103
- },
1104
- {
1105
- "epoch": 0.44849468008969895,
1106
- "grad_norm": 0.3644597828388214,
1107
- "learning_rate": 0.00029462645446106956,
1108
- "loss": 1.9526,
1109
- "step": 14100
1110
- },
1111
- {
1112
- "epoch": 0.4516754934236684,
1113
- "grad_norm": 0.33582156896591187,
1114
- "learning_rate": 0.00029214130406950546,
1115
- "loss": 1.9557,
1116
- "step": 14200
1117
- },
1118
- {
1119
- "epoch": 0.45485630675763794,
1120
- "grad_norm": 0.367532879114151,
1121
- "learning_rate": 0.00028965186016065715,
1122
- "loss": 1.9475,
1123
- "step": 14300
1124
- },
1125
- {
1126
- "epoch": 0.4580371200916074,
1127
- "grad_norm": 0.34935542941093445,
1128
- "learning_rate": 0.00028715837636859415,
1129
- "loss": 1.9498,
1130
- "step": 14400
1131
- },
1132
- {
1133
- "epoch": 0.46121793342557693,
1134
- "grad_norm": 0.3641268014907837,
1135
- "learning_rate": 0.0002846611067389849,
1136
- "loss": 1.945,
1137
- "step": 14500
1138
- },
1139
- {
1140
- "epoch": 0.4643987467595464,
1141
- "grad_norm": 0.3459928035736084,
1142
- "learning_rate": 0.00028216030570321355,
1143
- "loss": 1.9469,
1144
- "step": 14600
1145
- },
1146
- {
1147
- "epoch": 0.4675795600935159,
1148
- "grad_norm": 0.3485778570175171,
1149
- "learning_rate": 0.00027965622805245705,
1150
- "loss": 1.9419,
1151
- "step": 14700
1152
- },
1153
- {
1154
- "epoch": 0.4707603734274854,
1155
- "grad_norm": 0.3402996063232422,
1156
- "learning_rate": 0.00027714912891172675,
1157
- "loss": 1.9444,
1158
- "step": 14800
1159
- },
1160
- {
1161
- "epoch": 0.4739411867614549,
1162
- "grad_norm": 0.35919469594955444,
1163
- "learning_rate": 0.00027463926371387487,
1164
- "loss": 1.9414,
1165
- "step": 14900
1166
- },
1167
- {
1168
- "epoch": 0.4771220000954244,
1169
- "grad_norm": 0.34530550241470337,
1170
- "learning_rate": 0.00027212688817357,
1171
- "loss": 1.9388,
1172
- "step": 15000
1173
- },
1174
- {
1175
- "epoch": 0.4771220000954244,
1176
- "eval_loss": 1.9393974542617798,
1177
- "eval_runtime": 32.1088,
1178
- "eval_samples_per_second": 501.825,
1179
- "eval_steps_per_second": 0.997,
1180
- "step": 15000
1181
- },
1182
- {
1183
- "epoch": 0.4803028134293939,
1184
- "grad_norm": 0.34918758273124695,
1185
- "learning_rate": 0.0002696122582612442,
1186
- "loss": 1.9346,
1187
- "step": 15100
1188
- },
1189
- {
1190
- "epoch": 0.48348362676336337,
1191
- "grad_norm": 0.3463495969772339,
1192
- "learning_rate": 0.00026709563017701356,
1193
- "loss": 1.9347,
1194
- "step": 15200
1195
- },
1196
- {
1197
- "epoch": 0.4866644400973329,
1198
- "grad_norm": 0.3502143621444702,
1199
- "learning_rate": 0.0002645772603245755,
1200
- "loss": 1.929,
1201
- "step": 15300
1202
- },
1203
- {
1204
- "epoch": 0.48984525343130236,
1205
- "grad_norm": 0.349843293428421,
1206
- "learning_rate": 0.0002620574052850853,
1207
- "loss": 1.9305,
1208
- "step": 15400
1209
- },
1210
- {
1211
- "epoch": 0.4930260667652719,
1212
- "grad_norm": 0.3375796377658844,
1213
- "learning_rate": 0.00025953632179101494,
1214
- "loss": 1.9272,
1215
- "step": 15500
1216
- },
1217
- {
1218
- "epoch": 0.49620688009924135,
1219
- "grad_norm": 0.35436752438545227,
1220
- "learning_rate": 0.00025701426669999625,
1221
- "loss": 1.924,
1222
- "step": 15600
1223
- },
1224
- {
1225
- "epoch": 0.4993876934332109,
1226
- "grad_norm": 0.35758018493652344,
1227
- "learning_rate": 0.00025449149696865067,
1228
- "loss": 1.9231,
1229
- "step": 15700
1230
- },
1231
- {
1232
- "epoch": 0.5025685067671803,
1233
- "grad_norm": 0.3512331247329712,
1234
- "learning_rate": 0.0002519682696264102,
1235
- "loss": 1.9237,
1236
- "step": 15800
1237
- },
1238
- {
1239
- "epoch": 0.5057493201011498,
1240
- "grad_norm": 0.3526666760444641,
1241
- "learning_rate": 0.00024944484174932994,
1242
- "loss": 1.9207,
1243
- "step": 15900
1244
- },
1245
- {
1246
- "epoch": 0.5089301334351194,
1247
- "grad_norm": 0.3519933223724365,
1248
- "learning_rate": 0.0002469214704338962,
1249
- "loss": 1.9175,
1250
- "step": 16000
1251
- },
1252
- {
1253
- "epoch": 0.5089301334351194,
1254
- "eval_loss": 1.9168038368225098,
1255
- "eval_runtime": 32.0945,
1256
- "eval_samples_per_second": 502.048,
1257
- "eval_steps_per_second": 0.997,
1258
- "step": 16000
1259
- },
1260
- {
1261
- "epoch": 0.5121109467690889,
1262
- "grad_norm": 0.3831496238708496,
1263
- "learning_rate": 0.0002443984127708326,
1264
- "loss": 1.9235,
1265
- "step": 16100
1266
- },
1267
- {
1268
- "epoch": 0.5152917601030583,
1269
- "grad_norm": 0.342540442943573,
1270
- "learning_rate": 0.00024187592581890663,
1271
- "loss": 1.9112,
1272
- "step": 16200
1273
- },
1274
- {
1275
- "epoch": 0.5184725734370278,
1276
- "grad_norm": 0.3412289321422577,
1277
- "learning_rate": 0.0002393542665787396,
1278
- "loss": 1.9179,
1279
- "step": 16300
1280
- },
1281
- {
1282
- "epoch": 0.5216533867709974,
1283
- "grad_norm": 0.36094340682029724,
1284
- "learning_rate": 0.0002368336919666224,
1285
- "loss": 1.9111,
1286
- "step": 16400
1287
- },
1288
- {
1289
- "epoch": 0.5248342001049668,
1290
- "grad_norm": 0.338679701089859,
1291
- "learning_rate": 0.00023431445878833968,
1292
- "loss": 1.9102,
1293
- "step": 16500
1294
- },
1295
- {
1296
- "epoch": 0.5280150134389363,
1297
- "grad_norm": 0.3352338969707489,
1298
- "learning_rate": 0.00023179682371300594,
1299
- "loss": 1.9104,
1300
- "step": 16600
1301
- },
1302
- {
1303
- "epoch": 0.5311958267729058,
1304
- "grad_norm": 0.36914291977882385,
1305
- "learning_rate": 0.0002292810432469146,
1306
- "loss": 1.9064,
1307
- "step": 16700
1308
- },
1309
- {
1310
- "epoch": 0.5343766401068754,
1311
- "grad_norm": 0.3786391019821167,
1312
- "learning_rate": 0.00022676737370740463,
1313
- "loss": 1.9061,
1314
- "step": 16800
1315
- },
1316
- {
1317
- "epoch": 0.5375574534408448,
1318
- "grad_norm": 0.3459608852863312,
1319
- "learning_rate": 0.00022425607119674554,
1320
- "loss": 1.9045,
1321
- "step": 16900
1322
- },
1323
- {
1324
- "epoch": 0.5407382667748143,
1325
- "grad_norm": 0.3548073172569275,
1326
- "learning_rate": 0.0002217473915760449,
1327
- "loss": 1.9027,
1328
- "step": 17000
1329
- },
1330
- {
1331
- "epoch": 0.5407382667748143,
1332
- "eval_loss": 1.902103066444397,
1333
- "eval_runtime": 32.098,
1334
- "eval_samples_per_second": 501.994,
1335
- "eval_steps_per_second": 0.997,
1336
- "step": 17000
1337
- },
1338
- {
1339
- "epoch": 0.5439190801087839,
1340
- "grad_norm": 0.3637658953666687,
1341
- "learning_rate": 0.00021924159043918033,
1342
- "loss": 1.9014,
1343
- "step": 17100
1344
- },
1345
- {
1346
- "epoch": 0.5470998934427533,
1347
- "grad_norm": 0.33558160066604614,
1348
- "learning_rate": 0.00021673892308675835,
1349
- "loss": 1.9018,
1350
- "step": 17200
1351
- },
1352
- {
1353
- "epoch": 0.5502807067767228,
1354
- "grad_norm": 0.3354663848876953,
1355
- "learning_rate": 0.0002142396445001037,
1356
- "loss": 1.9003,
1357
- "step": 17300
1358
- },
1359
- {
1360
- "epoch": 0.5534615201106923,
1361
- "grad_norm": 0.36897751688957214,
1362
- "learning_rate": 0.00021174400931528063,
1363
- "loss": 1.8993,
1364
- "step": 17400
1365
- },
1366
- {
1367
- "epoch": 0.5566423334446619,
1368
- "grad_norm": 0.35250696539878845,
1369
- "learning_rate": 0.00020925227179714953,
1370
- "loss": 1.8935,
1371
- "step": 17500
1372
- },
1373
- {
1374
- "epoch": 0.5598231467786313,
1375
- "grad_norm": 0.3436286449432373,
1376
- "learning_rate": 0.0002067646858134618,
1377
- "loss": 1.8964,
1378
- "step": 17600
1379
- },
1380
- {
1381
- "epoch": 0.5630039601126008,
1382
- "grad_norm": 0.3421666920185089,
1383
- "learning_rate": 0.00020428150480899466,
1384
- "loss": 1.8923,
1385
- "step": 17700
1386
- },
1387
- {
1388
- "epoch": 0.5661847734465703,
1389
- "grad_norm": 0.3565044701099396,
1390
- "learning_rate": 0.0002018029817797289,
1391
- "loss": 1.8932,
1392
- "step": 17800
1393
- },
1394
- {
1395
- "epoch": 0.5693655867805398,
1396
- "grad_norm": 0.3318385183811188,
1397
- "learning_rate": 0.00019932936924707315,
1398
- "loss": 1.8882,
1399
- "step": 17900
1400
- },
1401
- {
1402
- "epoch": 0.5725464001145093,
1403
- "grad_norm": 0.3371005654335022,
1404
- "learning_rate": 0.00019686091923213606,
1405
- "loss": 1.8911,
1406
- "step": 18000
1407
- },
1408
- {
1409
- "epoch": 0.5725464001145093,
1410
- "eval_loss": 1.8916820287704468,
1411
- "eval_runtime": 32.1263,
1412
- "eval_samples_per_second": 501.551,
1413
- "eval_steps_per_second": 0.996,
1414
- "step": 18000
1415
- },
1416
- {
1417
- "epoch": 0.5757272134484788,
1418
- "grad_norm": 0.3281247019767761,
1419
- "learning_rate": 0.00019439788323004898,
1420
- "loss": 1.8854,
1421
- "step": 18100
1422
- },
1423
- {
1424
- "epoch": 0.5789080267824482,
1425
- "grad_norm": 0.3484356999397278,
1426
- "learning_rate": 0.00019194051218434283,
1427
- "loss": 1.8804,
1428
- "step": 18200
1429
- },
1430
- {
1431
- "epoch": 0.5820888401164178,
1432
- "grad_norm": 0.34183427691459656,
1433
- "learning_rate": 0.00018948905646138143,
1434
- "loss": 1.8837,
1435
- "step": 18300
1436
- },
1437
- {
1438
- "epoch": 0.5852696534503873,
1439
- "grad_norm": 0.34044957160949707,
1440
- "learning_rate": 0.00018704376582485253,
1441
- "loss": 1.8838,
1442
- "step": 18400
1443
- },
1444
- {
1445
- "epoch": 0.5884504667843568,
1446
- "grad_norm": 0.3419566750526428,
1447
- "learning_rate": 0.00018460488941032157,
1448
- "loss": 1.8827,
1449
- "step": 18500
1450
- },
1451
- {
1452
- "epoch": 0.5916312801183262,
1453
- "grad_norm": 0.33836421370506287,
1454
- "learning_rate": 0.00018217267569984834,
1455
- "loss": 1.8802,
1456
- "step": 18600
1457
- },
1458
- {
1459
- "epoch": 0.5948120934522958,
1460
- "grad_norm": 0.33309251070022583,
1461
- "learning_rate": 0.00017974737249667094,
1462
- "loss": 1.8782,
1463
- "step": 18700
1464
- },
1465
- {
1466
- "epoch": 0.5979929067862653,
1467
- "grad_norm": 0.3498755693435669,
1468
- "learning_rate": 0.00017732922689995848,
1469
- "loss": 1.8789,
1470
- "step": 18800
1471
- },
1472
- {
1473
- "epoch": 0.6011737201202347,
1474
- "grad_norm": 0.34821078181266785,
1475
- "learning_rate": 0.00017491848527963587,
1476
- "loss": 1.8783,
1477
- "step": 18900
1478
- },
1479
- {
1480
- "epoch": 0.6043545334542042,
1481
- "grad_norm": 0.35842365026474,
1482
- "learning_rate": 0.00017251539325128238,
1483
- "loss": 1.8745,
1484
- "step": 19000
1485
- },
1486
- {
1487
- "epoch": 0.6043545334542042,
1488
- "eval_loss": 1.877468228340149,
1489
- "eval_runtime": 32.1629,
1490
- "eval_samples_per_second": 500.981,
1491
- "eval_steps_per_second": 0.995,
1492
- "step": 19000
1493
- },
1494
- {
1495
- "epoch": 0.6075353467881738,
1496
- "grad_norm": 0.3450339734554291,
1497
- "learning_rate": 0.0001701201956511078,
1498
- "loss": 1.8697,
1499
- "step": 19100
1500
- },
1501
- {
1502
- "epoch": 0.6107161601221432,
1503
- "grad_norm": 0.3393618166446686,
1504
- "learning_rate": 0.00016773313651100713,
1505
- "loss": 1.8753,
1506
- "step": 19200
1507
- },
1508
- {
1509
- "epoch": 0.6138969734561127,
1510
- "grad_norm": 0.3536670506000519,
1511
- "learning_rate": 0.0001653544590336981,
1512
- "loss": 1.8683,
1513
- "step": 19300
1514
- },
1515
- {
1516
- "epoch": 0.6170777867900822,
1517
- "grad_norm": 0.33395901322364807,
1518
- "learning_rate": 0.00016298440556794264,
1519
- "loss": 1.8664,
1520
- "step": 19400
1521
- },
1522
- {
1523
- "epoch": 0.6202586001240518,
1524
- "grad_norm": 0.3403598666191101,
1525
- "learning_rate": 0.00016062321758385516,
1526
- "loss": 1.8683,
1527
- "step": 19500
1528
- },
1529
- {
1530
- "epoch": 0.6234394134580212,
1531
- "grad_norm": 0.36251527070999146,
1532
- "learning_rate": 0.00015827113564830097,
1533
- "loss": 1.8629,
1534
- "step": 19600
1535
- },
1536
- {
1537
- "epoch": 0.6266202267919907,
1538
- "grad_norm": 0.3264198899269104,
1539
- "learning_rate": 0.0001559283994003865,
1540
- "loss": 1.8661,
1541
- "step": 19700
1542
- },
1543
- {
1544
- "epoch": 0.6298010401259602,
1545
- "grad_norm": 0.3612154722213745,
1546
- "learning_rate": 0.0001535952475270434,
1547
- "loss": 1.8697,
1548
- "step": 19800
1549
- },
1550
- {
1551
- "epoch": 0.6329818534599297,
1552
- "grad_norm": 0.3527524471282959,
1553
- "learning_rate": 0.00015127191773871095,
1554
- "loss": 1.8622,
1555
- "step": 19900
1556
- },
1557
- {
1558
- "epoch": 0.6361626667938992,
1559
- "grad_norm": 0.3432440161705017,
1560
- "learning_rate": 0.00014895864674511656,
1561
- "loss": 1.8616,
1562
- "step": 20000
1563
- },
1564
- {
1565
- "epoch": 0.6361626667938992,
1566
- "eval_loss": 1.8657634258270264,
1567
- "eval_runtime": 32.1208,
1568
- "eval_samples_per_second": 501.638,
1569
- "eval_steps_per_second": 0.996,
1570
- "step": 20000
1571
- },
1572
- {
1573
- "epoch": 0.6393434801278687,
1574
- "grad_norm": 0.33134913444519043,
1575
- "learning_rate": 0.0001466556702311592,
1576
- "loss": 1.8596,
1577
- "step": 20100
1578
- },
1579
- {
1580
- "epoch": 0.6425242934618381,
1581
- "grad_norm": 0.3471083343029022,
1582
- "learning_rate": 0.0001443632228328971,
1583
- "loss": 1.8603,
1584
- "step": 20200
1585
- },
1586
- {
1587
- "epoch": 0.6457051067958077,
1588
- "grad_norm": 0.3317488133907318,
1589
- "learning_rate": 0.0001420815381136416,
1590
- "loss": 1.8582,
1591
- "step": 20300
1592
- },
1593
- {
1594
- "epoch": 0.6488859201297772,
1595
- "grad_norm": 0.34423279762268066,
1596
- "learning_rate": 0.0001398108485401613,
1597
- "loss": 1.8581,
1598
- "step": 20400
1599
- },
1600
- {
1601
- "epoch": 0.6520667334637467,
1602
- "grad_norm": 0.33473995327949524,
1603
- "learning_rate": 0.0001375513854589971,
1604
- "loss": 1.8518,
1605
- "step": 20500
1606
- },
1607
- {
1608
- "epoch": 0.6552475467977161,
1609
- "grad_norm": 0.4052187502384186,
1610
- "learning_rate": 0.0001353033790728922,
1611
- "loss": 1.8565,
1612
- "step": 20600
1613
- },
1614
- {
1615
- "epoch": 0.6584283601316857,
1616
- "grad_norm": 0.3393067717552185,
1617
- "learning_rate": 0.00013306705841733768,
1618
- "loss": 1.8535,
1619
- "step": 20700
1620
- },
1621
- {
1622
- "epoch": 0.6616091734656552,
1623
- "grad_norm": 0.32772359251976013,
1624
- "learning_rate": 0.00013084265133723766,
1625
- "loss": 1.8512,
1626
- "step": 20800
1627
- },
1628
- {
1629
- "epoch": 0.6647899867996246,
1630
- "grad_norm": 0.3381692171096802,
1631
- "learning_rate": 0.00012863038446369563,
1632
- "loss": 1.8513,
1633
- "step": 20900
1634
- },
1635
- {
1636
- "epoch": 0.6679708001335941,
1637
- "grad_norm": 0.34525567293167114,
1638
- "learning_rate": 0.0001264304831909246,
1639
- "loss": 1.8486,
1640
- "step": 21000
1641
- },
1642
- {
1643
- "epoch": 0.6679708001335941,
1644
- "eval_loss": 1.8506046533584595,
1645
- "eval_runtime": 32.1325,
1646
- "eval_samples_per_second": 501.455,
1647
- "eval_steps_per_second": 0.996,
1648
- "step": 21000
1649
- },
1650
- {
1651
- "epoch": 0.6711516134675637,
1652
- "grad_norm": 0.34088197350502014,
1653
- "learning_rate": 0.0001242431716532826,
1654
- "loss": 1.8528,
1655
- "step": 21100
1656
- },
1657
- {
1658
- "epoch": 0.6743324268015332,
1659
- "grad_norm": 0.3476403057575226,
1660
- "learning_rate": 0.00012206867270243732,
1661
- "loss": 1.8429,
1662
- "step": 21200
1663
- },
1664
- {
1665
- "epoch": 0.6775132401355026,
1666
- "grad_norm": 0.36645591259002686,
1667
- "learning_rate": 0.00011990720788466128,
1668
- "loss": 1.845,
1669
- "step": 21300
1670
- },
1671
- {
1672
- "epoch": 0.6806940534694721,
1673
- "grad_norm": 0.3571740686893463,
1674
- "learning_rate": 0.00011775899741825946,
1675
- "loss": 1.8451,
1676
- "step": 21400
1677
- },
1678
- {
1679
- "epoch": 0.6838748668034417,
1680
- "grad_norm": 0.3609398901462555,
1681
- "learning_rate": 0.00011562426017113278,
1682
- "loss": 1.842,
1683
- "step": 21500
1684
- },
1685
- {
1686
- "epoch": 0.6870556801374111,
1687
- "grad_norm": 0.35237523913383484,
1688
- "learning_rate": 0.00011350321363847929,
1689
- "loss": 1.8404,
1690
- "step": 21600
1691
- },
1692
- {
1693
- "epoch": 0.6902364934713806,
1694
- "grad_norm": 0.34250757098197937,
1695
- "learning_rate": 0.00011139607392063447,
1696
- "loss": 1.8411,
1697
- "step": 21700
1698
- },
1699
- {
1700
- "epoch": 0.6934173068053501,
1701
- "grad_norm": 0.3336504399776459,
1702
- "learning_rate": 0.00010930305570105417,
1703
- "loss": 1.8403,
1704
- "step": 21800
1705
- },
1706
- {
1707
- "epoch": 0.6965981201393197,
1708
- "grad_norm": 0.34285008907318115,
1709
- "learning_rate": 0.00010722437222444231,
1710
- "loss": 1.8413,
1711
- "step": 21900
1712
- },
1713
- {
1714
- "epoch": 0.6997789334732891,
1715
- "grad_norm": 0.3735544979572296,
1716
- "learning_rate": 0.00010516023527502425,
1717
- "loss": 1.8384,
1718
- "step": 22000
1719
- },
1720
- {
1721
- "epoch": 0.6997789334732891,
1722
- "eval_loss": 1.8285677433013916,
1723
- "eval_runtime": 32.1332,
1724
- "eval_samples_per_second": 501.445,
1725
- "eval_steps_per_second": 0.996,
1726
- "step": 22000
1727
- },
1728
- {
1729
- "epoch": 0.7029597468072586,
1730
- "grad_norm": 0.3442489802837372,
1731
- "learning_rate": 0.00010311085515496935,
1732
- "loss": 1.8365,
1733
- "step": 22100
1734
- },
1735
- {
1736
- "epoch": 0.7061405601412281,
1737
- "grad_norm": 0.3265076279640198,
1738
- "learning_rate": 0.00010107644066296473,
1739
- "loss": 1.8394,
1740
- "step": 22200
1741
- },
1742
- {
1743
- "epoch": 0.7093213734751976,
1744
- "grad_norm": 0.3419564366340637,
1745
- "learning_rate": 9.905719907294236e-05,
1746
- "loss": 1.834,
1747
- "step": 22300
1748
- },
1749
- {
1750
- "epoch": 0.7125021868091671,
1751
- "grad_norm": 0.3507215678691864,
1752
- "learning_rate": 9.70533361129606e-05,
1753
- "loss": 1.8351,
1754
- "step": 22400
1755
- },
1756
- {
1757
- "epoch": 0.7156830001431366,
1758
- "grad_norm": 0.3546813726425171,
1759
- "learning_rate": 9.506505594424424e-05,
1760
- "loss": 1.834,
1761
- "step": 22500
1762
- },
1763
- {
1764
- "epoch": 0.7188638134771062,
1765
- "grad_norm": 0.32974520325660706,
1766
- "learning_rate": 9.30925611403838e-05,
1767
- "loss": 1.8359,
1768
- "step": 22600
1769
- },
1770
- {
1771
- "epoch": 0.7220446268110756,
1772
- "grad_norm": 0.35666748881340027,
1773
- "learning_rate": 9.113605266669631e-05,
1774
- "loss": 1.8321,
1775
- "step": 22700
1776
- },
1777
- {
1778
- "epoch": 0.7252254401450451,
1779
- "grad_norm": 0.3441431522369385,
1780
- "learning_rate": 8.91957298597503e-05,
1781
- "loss": 1.8285,
1782
- "step": 22800
1783
- },
1784
- {
1785
- "epoch": 0.7284062534790146,
1786
- "grad_norm": 0.3351287245750427,
1787
- "learning_rate": 8.727179040705666e-05,
1788
- "loss": 1.8268,
1789
- "step": 22900
1790
- },
1791
- {
1792
- "epoch": 0.7315870668129841,
1793
- "grad_norm": 0.34751853346824646,
1794
- "learning_rate": 8.536443032692759e-05,
1795
- "loss": 1.8265,
1796
- "step": 23000
1797
- },
1798
- {
1799
- "epoch": 0.7315870668129841,
1800
- "eval_loss": 1.8300367593765259,
1801
- "eval_runtime": 32.1272,
1802
- "eval_samples_per_second": 501.538,
1803
- "eval_steps_per_second": 0.996,
1804
- "step": 23000
1805
- },
1806
- {
1807
- "epoch": 0.7347678801469536,
1808
- "grad_norm": 0.33557063341140747,
1809
- "learning_rate": 8.34738439485053e-05,
1810
- "loss": 1.8317,
1811
- "step": 23100
1812
- },
1813
- {
1814
- "epoch": 0.7379486934809231,
1815
- "grad_norm": 0.33028125762939453,
1816
- "learning_rate": 8.160022389196297e-05,
1817
- "loss": 1.8254,
1818
- "step": 23200
1819
- },
1820
- {
1821
- "epoch": 0.7411295068148925,
1822
- "grad_norm": 0.35035333037376404,
1823
- "learning_rate": 7.974376104888031e-05,
1824
- "loss": 1.8242,
1825
- "step": 23300
1826
- },
1827
- {
1828
- "epoch": 0.7443103201488621,
1829
- "grad_norm": 0.3394406735897064,
1830
- "learning_rate": 7.790464456279418e-05,
1831
- "loss": 1.8265,
1832
- "step": 23400
1833
- },
1834
- {
1835
- "epoch": 0.7474911334828316,
1836
- "grad_norm": 0.34416496753692627,
1837
- "learning_rate": 7.608306180992827e-05,
1838
- "loss": 1.8207,
1839
- "step": 23500
1840
- },
1841
- {
1842
- "epoch": 0.750671946816801,
1843
- "grad_norm": 0.32952558994293213,
1844
- "learning_rate": 7.42791983801027e-05,
1845
- "loss": 1.8217,
1846
- "step": 23600
1847
- },
1848
- {
1849
- "epoch": 0.7538527601507705,
1850
- "grad_norm": 0.3340277671813965,
1851
- "learning_rate": 7.249323805782485e-05,
1852
- "loss": 1.8199,
1853
- "step": 23700
1854
- },
1855
- {
1856
- "epoch": 0.7570335734847401,
1857
- "grad_norm": 0.3377705514431,
1858
- "learning_rate": 7.072536280356512e-05,
1859
- "loss": 1.8206,
1860
- "step": 23800
1861
- },
1862
- {
1863
- "epoch": 0.7602143868187096,
1864
- "grad_norm": 0.34252113103866577,
1865
- "learning_rate": 6.897575273521813e-05,
1866
- "loss": 1.8226,
1867
- "step": 23900
1868
- },
1869
- {
1870
- "epoch": 0.763395200152679,
1871
- "grad_norm": 0.3416256606578827,
1872
- "learning_rate": 6.724458610975132e-05,
1873
- "loss": 1.8184,
1874
- "step": 24000
1875
- },
1876
- {
1877
- "epoch": 0.763395200152679,
1878
- "eval_loss": 1.821753740310669,
1879
- "eval_runtime": 32.0785,
1880
- "eval_samples_per_second": 502.299,
1881
- "eval_steps_per_second": 0.998,
1882
- "step": 24000
1883
- },
1884
- {
1885
- "epoch": 0.7665760134866485,
1886
- "grad_norm": 0.34040501713752747,
1887
- "learning_rate": 6.553203930504362e-05,
1888
- "loss": 1.8183,
1889
- "step": 24100
1890
- },
1891
- {
1892
- "epoch": 0.7697568268206181,
1893
- "grad_norm": 0.356413871049881,
1894
- "learning_rate": 6.383828680191534e-05,
1895
- "loss": 1.8219,
1896
- "step": 24200
1897
- },
1898
- {
1899
- "epoch": 0.7729376401545875,
1900
- "grad_norm": 0.3355048596858978,
1901
- "learning_rate": 6.216350116635167e-05,
1902
- "loss": 1.817,
1903
- "step": 24300
1904
- },
1905
- {
1906
- "epoch": 0.776118453488557,
1907
- "grad_norm": 0.35275501012802124,
1908
- "learning_rate": 6.0507853031920554e-05,
1909
- "loss": 1.8158,
1910
- "step": 24400
1911
- },
1912
- {
1913
- "epoch": 0.7792992668225265,
1914
- "grad_norm": 0.34181755781173706,
1915
- "learning_rate": 5.887151108238806e-05,
1916
- "loss": 1.8165,
1917
- "step": 24500
1918
- },
1919
- {
1920
- "epoch": 0.7824800801564961,
1921
- "grad_norm": 0.35903728008270264,
1922
- "learning_rate": 5.7254642034532565e-05,
1923
- "loss": 1.8135,
1924
- "step": 24600
1925
- },
1926
- {
1927
- "epoch": 0.7856608934904655,
1928
- "grad_norm": 0.3354894816875458,
1929
- "learning_rate": 5.5657410621158446e-05,
1930
- "loss": 1.8128,
1931
- "step": 24700
1932
- },
1933
- {
1934
- "epoch": 0.788841706824435,
1935
- "grad_norm": 0.3340279757976532,
1936
- "learning_rate": 5.4079979574312766e-05,
1937
- "loss": 1.8122,
1938
- "step": 24800
1939
- },
1940
- {
1941
- "epoch": 0.7920225201584045,
1942
- "grad_norm": 0.3405105173587799,
1943
- "learning_rate": 5.252250960870572e-05,
1944
- "loss": 1.8109,
1945
- "step": 24900
1946
- },
1947
- {
1948
- "epoch": 0.795203333492374,
1949
- "grad_norm": 0.33750855922698975,
1950
- "learning_rate": 5.098515940533594e-05,
1951
- "loss": 1.8138,
1952
- "step": 25000
1953
- },
1954
- {
1955
- "epoch": 0.795203333492374,
1956
- "eval_loss": 1.8088994026184082,
1957
- "eval_runtime": 32.1476,
1958
- "eval_samples_per_second": 501.219,
1959
- "eval_steps_per_second": 0.995,
1960
- "step": 25000
1961
- },
1962
- {
1963
- "epoch": 0.7983841468263435,
1964
- "grad_norm": 0.3351406753063202,
1965
- "learning_rate": 4.946808559532373e-05,
1966
- "loss": 1.809,
1967
- "step": 25100
1968
- },
1969
- {
1970
- "epoch": 0.801564960160313,
1971
- "grad_norm": 0.34872087836265564,
1972
- "learning_rate": 4.797144274395307e-05,
1973
- "loss": 1.8131,
1974
- "step": 25200
1975
- },
1976
- {
1977
- "epoch": 0.8047457734942824,
1978
- "grad_norm": 0.33941712975502014,
1979
- "learning_rate": 4.649538333492348e-05,
1980
- "loss": 1.8091,
1981
- "step": 25300
1982
- },
1983
- {
1984
- "epoch": 0.807926586828252,
1985
- "grad_norm": 0.3459567129611969,
1986
- "learning_rate": 4.504005775481468e-05,
1987
- "loss": 1.8089,
1988
- "step": 25400
1989
- },
1990
- {
1991
- "epoch": 0.8111074001622215,
1992
- "grad_norm": 0.3222104012966156,
1993
- "learning_rate": 4.3605614277764715e-05,
1994
- "loss": 1.8085,
1995
- "step": 25500
1996
- },
1997
- {
1998
- "epoch": 0.814288213496191,
1999
- "grad_norm": 0.3289223313331604,
2000
- "learning_rate": 4.219219905036292e-05,
2001
- "loss": 1.8068,
2002
- "step": 25600
2003
- },
2004
- {
2005
- "epoch": 0.8174690268301604,
2006
- "grad_norm": 0.3424234092235565,
2007
- "learning_rate": 4.079995607676007e-05,
2008
- "loss": 1.8071,
2009
- "step": 25700
2010
- },
2011
- {
2012
- "epoch": 0.82064984016413,
2013
- "grad_norm": 0.34120631217956543,
2014
- "learning_rate": 3.942902720399685e-05,
2015
- "loss": 1.8059,
2016
- "step": 25800
2017
- },
2018
- {
2019
- "epoch": 0.8238306534980995,
2020
- "grad_norm": 0.3320011496543884,
2021
- "learning_rate": 3.80795521075519e-05,
2022
- "loss": 1.8066,
2023
- "step": 25900
2024
- },
2025
- {
2026
- "epoch": 0.8270114668320689,
2027
- "grad_norm": 0.3449844419956207,
2028
- "learning_rate": 3.6751668277110794e-05,
2029
- "loss": 1.8047,
2030
- "step": 26000
2031
- },
2032
- {
2033
- "epoch": 0.8270114668320689,
2034
- "eval_loss": 1.8011921644210815,
2035
- "eval_runtime": 32.1369,
2036
- "eval_samples_per_second": 501.386,
2037
- "eval_steps_per_second": 0.996,
2038
- "step": 26000
2039
- },
2040
- {
2041
- "epoch": 0.8301922801660384,
2042
- "grad_norm": 0.33759376406669617,
2043
- "learning_rate": 3.544551100255844e-05,
2044
- "loss": 1.805,
2045
- "step": 26100
2046
- },
2047
- {
2048
- "epoch": 0.833373093500008,
2049
- "grad_norm": 0.330618679523468,
2050
- "learning_rate": 3.416121336019509e-05,
2051
- "loss": 1.8044,
2052
- "step": 26200
2053
- },
2054
- {
2055
- "epoch": 0.8365539068339775,
2056
- "grad_norm": 0.3355448544025421,
2057
- "learning_rate": 3.2898906199178125e-05,
2058
- "loss": 1.8036,
2059
- "step": 26300
2060
- },
2061
- {
2062
- "epoch": 0.8397347201679469,
2063
- "grad_norm": 0.3439745008945465,
2064
- "learning_rate": 3.1658718128190486e-05,
2065
- "loss": 1.8039,
2066
- "step": 26400
2067
- },
2068
- {
2069
- "epoch": 0.8429155335019164,
2070
- "grad_norm": 0.34090688824653625,
2071
- "learning_rate": 3.0440775502337507e-05,
2072
- "loss": 1.8022,
2073
- "step": 26500
2074
- },
2075
- {
2076
- "epoch": 0.846096346835886,
2077
- "grad_norm": 0.33220720291137695,
2078
- "learning_rate": 2.9245202410273674e-05,
2079
- "loss": 1.8057,
2080
- "step": 26600
2081
- },
2082
- {
2083
- "epoch": 0.8492771601698554,
2084
- "grad_norm": 0.3338833749294281,
2085
- "learning_rate": 2.807212066155962e-05,
2086
- "loss": 1.8053,
2087
- "step": 26700
2088
- },
2089
- {
2090
- "epoch": 0.8524579735038249,
2091
- "grad_norm": 0.3296976387500763,
2092
- "learning_rate": 2.692164977425185e-05,
2093
- "loss": 1.7999,
2094
- "step": 26800
2095
- },
2096
- {
2097
- "epoch": 0.8556387868377944,
2098
- "grad_norm": 0.3248607814311981,
2099
- "learning_rate": 2.5793906962726017e-05,
2100
- "loss": 1.8027,
2101
- "step": 26900
2102
- },
2103
- {
2104
- "epoch": 0.858819600171764,
2105
- "grad_norm": 0.3374764323234558,
2106
- "learning_rate": 2.468900712573424e-05,
2107
- "loss": 1.7981,
2108
- "step": 27000
2109
- },
2110
- {
2111
- "epoch": 0.858819600171764,
2112
- "eval_loss": 1.7973639965057373,
2113
- "eval_runtime": 32.0857,
2114
- "eval_samples_per_second": 502.186,
2115
- "eval_steps_per_second": 0.997,
2116
- "step": 27000
2117
- },
2118
- {
2119
- "epoch": 0.8620004135057334,
2120
- "grad_norm": 0.3380274474620819,
2121
- "learning_rate": 2.360706283469902e-05,
2122
- "loss": 1.8004,
2123
- "step": 27100
2124
- },
2125
- {
2126
- "epoch": 0.8651812268397029,
2127
- "grad_norm": 0.3346974849700928,
2128
- "learning_rate": 2.2548184322244176e-05,
2129
- "loss": 1.8014,
2130
- "step": 27200
2131
- },
2132
- {
2133
- "epoch": 0.8683620401736724,
2134
- "grad_norm": 0.3224380314350128,
2135
- "learning_rate": 2.1512479470963604e-05,
2136
- "loss": 1.797,
2137
- "step": 27300
2138
- },
2139
- {
2140
- "epoch": 0.8715428535076419,
2141
- "grad_norm": 0.3305274546146393,
2142
- "learning_rate": 2.0500053802429946e-05,
2143
- "loss": 1.8004,
2144
- "step": 27400
2145
- },
2146
- {
2147
- "epoch": 0.8747236668416114,
2148
- "grad_norm": 0.33231696486473083,
2149
- "learning_rate": 1.951101046644377e-05,
2150
- "loss": 1.7991,
2151
- "step": 27500
2152
- },
2153
- {
2154
- "epoch": 0.8779044801755809,
2155
- "grad_norm": 0.34103721380233765,
2156
- "learning_rate": 1.8545450230524008e-05,
2157
- "loss": 1.795,
2158
- "step": 27600
2159
- },
2160
- {
2161
- "epoch": 0.8810852935095503,
2162
- "grad_norm": 0.33826613426208496,
2163
- "learning_rate": 1.7603471469641584e-05,
2164
- "loss": 1.7956,
2165
- "step": 27700
2166
- },
2167
- {
2168
- "epoch": 0.8842661068435199,
2169
- "grad_norm": 0.32677432894706726,
2170
- "learning_rate": 1.6685170156196472e-05,
2171
- "loss": 1.7989,
2172
- "step": 27800
2173
- },
2174
- {
2175
- "epoch": 0.8874469201774894,
2176
- "grad_norm": 0.3428284823894501,
2177
- "learning_rate": 1.579063985023982e-05,
2178
- "loss": 1.7925,
2179
- "step": 27900
2180
- },
2181
- {
2182
- "epoch": 0.8906277335114589,
2183
- "grad_norm": 0.33137476444244385,
2184
- "learning_rate": 1.491997168994147e-05,
2185
- "loss": 1.7968,
2186
- "step": 28000
2187
- },
2188
- {
2189
- "epoch": 0.8906277335114589,
2190
- "eval_loss": 1.796820878982544,
2191
- "eval_runtime": 32.0929,
2192
- "eval_samples_per_second": 502.074,
2193
- "eval_steps_per_second": 0.997,
2194
- "step": 28000
2195
- },
2196
- {
2197
- "epoch": 0.8938085468454284,
2198
- "grad_norm": 0.33493006229400635,
2199
- "learning_rate": 1.407325438230464e-05,
2200
- "loss": 1.7925,
2201
- "step": 28100
2202
- },
2203
- {
2204
- "epoch": 0.8969893601793979,
2205
- "grad_norm": 0.34214428067207336,
2206
- "learning_rate": 1.3250574194128063e-05,
2207
- "loss": 1.7975,
2208
- "step": 28200
2209
- },
2210
- {
2211
- "epoch": 0.9001701735133674,
2212
- "grad_norm": 0.32927870750427246,
2213
- "learning_rate": 1.2452014943216739e-05,
2214
- "loss": 1.795,
2215
- "step": 28300
2216
- },
2217
- {
2218
- "epoch": 0.9033509868473368,
2219
- "grad_norm": 0.32642796635627747,
2220
- "learning_rate": 1.1677657989842244e-05,
2221
- "loss": 1.7981,
2222
- "step": 28400
2223
- },
2224
- {
2225
- "epoch": 0.9065318001813064,
2226
- "grad_norm": 0.3503552973270416,
2227
- "learning_rate": 1.0927582228453637e-05,
2228
- "loss": 1.7942,
2229
- "step": 28500
2230
- },
2231
- {
2232
- "epoch": 0.9097126135152759,
2233
- "grad_norm": 0.3280312120914459,
2234
- "learning_rate": 1.0201864079639133e-05,
2235
- "loss": 1.7921,
2236
- "step": 28600
2237
- },
2238
- {
2239
- "epoch": 0.9128934268492453,
2240
- "grad_norm": 0.32568585872650146,
2241
- "learning_rate": 9.500577482340151e-06,
2242
- "loss": 1.7948,
2243
- "step": 28700
2244
- },
2245
- {
2246
- "epoch": 0.9160742401832148,
2247
- "grad_norm": 0.3296736180782318,
2248
- "learning_rate": 8.823793886318294e-06,
2249
- "loss": 1.7915,
2250
- "step": 28800
2251
- },
2252
- {
2253
- "epoch": 0.9192550535171844,
2254
- "grad_norm": 0.3363937437534332,
2255
- "learning_rate": 8.171582244875576e-06,
2256
- "loss": 1.7922,
2257
- "step": 28900
2258
- },
2259
- {
2260
- "epoch": 0.9224358668511539,
2261
- "grad_norm": 0.32553765177726746,
2262
- "learning_rate": 7.544009007829256e-06,
2263
- "loss": 1.7964,
2264
- "step": 29000
2265
- },
2266
- {
2267
- "epoch": 0.9224358668511539,
2268
- "eval_loss": 1.7941467761993408,
2269
- "eval_runtime": 32.173,
2270
- "eval_samples_per_second": 500.824,
2271
- "eval_steps_per_second": 0.995,
2272
- "step": 29000
2273
- },
2274
- {
2275
- "epoch": 0.9256166801851233,
2276
- "grad_norm": 0.3333429992198944,
2277
- "learning_rate": 6.941138114741729e-06,
2278
- "loss": 1.7934,
2279
- "step": 29100
2280
- },
2281
- {
2282
- "epoch": 0.9287974935190928,
2283
- "grad_norm": 0.32714954018592834,
2284
- "learning_rate": 6.363030988406071e-06,
2285
- "loss": 1.7905,
2286
- "step": 29200
2287
- },
2288
- {
2289
- "epoch": 0.9319783068530624,
2290
- "grad_norm": 0.32440173625946045,
2291
- "learning_rate": 5.809746528588067e-06,
2292
- "loss": 1.7914,
2293
- "step": 29300
2294
- },
2295
- {
2296
- "epoch": 0.9351591201870318,
2297
- "grad_norm": 0.3358508050441742,
2298
- "learning_rate": 5.2813411060252115e-06,
2299
- "loss": 1.7952,
2300
- "step": 29400
2301
- },
2302
- {
2303
- "epoch": 0.9383399335210013,
2304
- "grad_norm": 0.33145636320114136,
2305
- "learning_rate": 4.777868556683607e-06,
2306
- "loss": 1.7941,
2307
- "step": 29500
2308
- },
2309
- {
2310
- "epoch": 0.9415207468549708,
2311
- "grad_norm": 0.3216131031513214,
2312
- "learning_rate": 4.299380176272738e-06,
2313
- "loss": 1.792,
2314
- "step": 29600
2315
- },
2316
- {
2317
- "epoch": 0.9447015601889404,
2318
- "grad_norm": 0.3287525475025177,
2319
- "learning_rate": 3.845924715019461e-06,
2320
- "loss": 1.7899,
2321
- "step": 29700
2322
- },
2323
- {
2324
- "epoch": 0.9478823735229098,
2325
- "grad_norm": 0.32820937037467957,
2326
- "learning_rate": 3.417548372700946e-06,
2327
- "loss": 1.7928,
2328
- "step": 29800
2329
- },
2330
- {
2331
- "epoch": 0.9510631868568793,
2332
- "grad_norm": 0.32468679547309875,
2333
- "learning_rate": 3.014294793937944e-06,
2334
- "loss": 1.7952,
2335
- "step": 29900
2336
- },
2337
- {
2338
- "epoch": 0.9542440001908488,
2339
- "grad_norm": 0.3263169825077057,
2340
- "learning_rate": 2.6362050637477595e-06,
2341
- "loss": 1.7938,
2342
- "step": 30000
2343
- },
2344
- {
2345
- "epoch": 0.9542440001908488,
2346
- "eval_loss": 1.795248031616211,
2347
- "eval_runtime": 32.1204,
2348
- "eval_samples_per_second": 501.644,
2349
- "eval_steps_per_second": 0.996,
2350
- "step": 30000
2351
- },
2352
- {
2353
- "epoch": 0.9574248135248183,
2354
- "grad_norm": 0.33538147807121277,
2355
- "learning_rate": 2.2833177033586284e-06,
2356
- "loss": 1.7889,
2357
- "step": 30100
2358
- },
2359
- {
2360
- "epoch": 0.9606056268587878,
2361
- "grad_norm": 0.32708439230918884,
2362
- "learning_rate": 1.955668666284938e-06,
2363
- "loss": 1.7899,
2364
- "step": 30200
2365
- },
2366
- {
2367
- "epoch": 0.9637864401927573,
2368
- "grad_norm": 0.3282252252101898,
2369
- "learning_rate": 1.6532913346641033e-06,
2370
- "loss": 1.7904,
2371
- "step": 30300
2372
- },
2373
- {
2374
- "epoch": 0.9669672535267267,
2375
- "grad_norm": 0.32018953561782837,
2376
- "learning_rate": 1.3762165158555106e-06,
2377
- "loss": 1.7917,
2378
- "step": 30400
2379
- },
2380
- {
2381
- "epoch": 0.9701480668606963,
2382
- "grad_norm": 0.32321518659591675,
2383
- "learning_rate": 1.1244724393017492e-06,
2384
- "loss": 1.7895,
2385
- "step": 30500
2386
- },
2387
- {
2388
- "epoch": 0.9733288801946658,
2389
- "grad_norm": 0.3273015022277832,
2390
- "learning_rate": 8.980847536524672e-07,
2391
- "loss": 1.7885,
2392
- "step": 30600
2393
- },
2394
- {
2395
- "epoch": 0.9765096935286353,
2396
- "grad_norm": 0.3278350830078125,
2397
- "learning_rate": 6.970765241512134e-07,
2398
- "loss": 1.7928,
2399
- "step": 30700
2400
- },
2401
- {
2402
- "epoch": 0.9796905068626047,
2403
- "grad_norm": 0.3303736746311188,
2404
- "learning_rate": 5.214682302854268e-07,
2405
- "loss": 1.793,
2406
- "step": 30800
2407
- },
2408
- {
2409
- "epoch": 0.9828713201965743,
2410
- "grad_norm": 0.3265056014060974,
2411
- "learning_rate": 3.7127776369991207e-07,
2412
- "loss": 1.7881,
2413
- "step": 30900
2414
- },
2415
- {
2416
- "epoch": 0.9860521335305438,
2417
- "grad_norm": 0.32918035984039307,
2418
- "learning_rate": 2.465204263740195e-07,
2419
- "loss": 1.7872,
2420
- "step": 31000
2421
- },
2422
- {
2423
- "epoch": 0.9860521335305438,
2424
- "eval_loss": 1.7951247692108154,
2425
- "eval_runtime": 32.1506,
2426
- "eval_samples_per_second": 501.172,
2427
- "eval_steps_per_second": 0.995,
2428
- "step": 31000
2429
- },
2430
- {
2431
- "epoch": 0.9892329468645132,
2432
- "grad_norm": 0.33081668615341187,
2433
- "learning_rate": 1.472089290626144e-07,
2434
- "loss": 1.7908,
2435
- "step": 31100
2436
- },
2437
- {
2438
- "epoch": 0.9924137601984827,
2439
- "grad_norm": 0.32260140776634216,
2440
- "learning_rate": 7.335339000094643e-08,
2441
- "loss": 1.7947,
2442
- "step": 31200
2443
- },
2444
- {
2445
- "epoch": 0.9955945735324523,
2446
- "grad_norm": 0.32248544692993164,
2447
- "learning_rate": 2.4961333873918522e-08,
2448
- "loss": 1.7864,
2449
- "step": 31300
2450
- },
2451
- {
2452
- "epoch": 0.9987753868664218,
2453
- "grad_norm": 0.3256651759147644,
2454
- "learning_rate": 2.0376910493113963e-09,
2455
- "loss": 1.7875,
2456
- "step": 31400
2457
- }
2458
- ],
2459
- "logging_steps": 100,
2460
- "max_steps": 31439,
2461
- "num_input_tokens_seen": 0,
2462
- "num_train_epochs": 1,
2463
- "save_steps": 500,
2464
- "stateful_callbacks": {
2465
- "TrainerControl": {
2466
- "args": {
2467
- "should_epoch_stop": false,
2468
- "should_evaluate": false,
2469
- "should_log": false,
2470
- "should_save": true,
2471
- "should_training_stop": true
2472
- },
2473
- "attributes": {}
2474
- }
2475
- },
2476
- "total_flos": 5.48742728491257e+18,
2477
- "train_batch_size": 32,
2478
- "trial_name": null,
2479
- "trial_params": null
2480
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
SynFinBERT_Final/checkpoint-31439/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fc8b97dcbfe3b68dd807df9e7cae0352a04f713f492a6819a6f88527b5d8244
3
- size 5841
 
 
 
 
SynFinBERT_Final/config.json DELETED
@@ -1,46 +0,0 @@
1
- {
2
- "architectures": [
3
- "ModernBertForMaskedLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_implementation": "sdpa",
8
- "bos_token_id": 50281,
9
- "classifier_activation": "gelu",
10
- "classifier_bias": false,
11
- "classifier_dropout": 0.0,
12
- "classifier_pooling": "mean",
13
- "cls_token_id": 50281,
14
- "decoder_bias": true,
15
- "deterministic_flash_attn": false,
16
- "embedding_dropout": 0.0,
17
- "eos_token_id": 50282,
18
- "global_attn_every_n_layers": 3,
19
- "global_rope_theta": 160000.0,
20
- "gradient_checkpointing": false,
21
- "hidden_activation": "gelu",
22
- "hidden_size": 768,
23
- "initializer_cutoff_factor": 2.0,
24
- "initializer_range": 0.02,
25
- "intermediate_size": 1152,
26
- "layer_norm_eps": 1e-05,
27
- "local_attention": 128,
28
- "local_rope_theta": 10000.0,
29
- "max_position_embeddings": 8192,
30
- "mlp_bias": false,
31
- "mlp_dropout": 0.0,
32
- "model_type": "modernbert",
33
- "norm_bias": false,
34
- "norm_eps": 1e-05,
35
- "num_attention_heads": 12,
36
- "num_hidden_layers": 22,
37
- "pad_token_id": 50283,
38
- "position_embedding_type": "absolute",
39
- "repad_logits_with_grad": false,
40
- "sep_token_id": 50282,
41
- "sparse_pred_ignore_index": -100,
42
- "sparse_prediction": false,
43
- "torch_dtype": "float32",
44
- "transformers_version": "4.54.0",
45
- "vocab_size": 50368
46
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
SynFinBERT_Final/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:44e0ac1a63d93aac0a95266477546e4248339df56e16ed4336a8550740858b59
3
- size 598635032
 
 
 
 
SynFinBERT_Final/special_tokens_map.json DELETED
@@ -1,37 +0,0 @@
1
- {
2
- "cls_token": {
3
- "content": "[CLS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "mask_token": {
10
- "content": "[MASK]",
11
- "lstrip": true,
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,
21
- "single_word": false
22
- },
23
- "sep_token": {
24
- "content": "[SEP]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "unk_token": {
31
- "content": "[UNK]",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- }
37
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
SynFinBERT_Final/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
SynFinBERT_Final/tokenizer_config.json DELETED
@@ -1,945 +0,0 @@
1
- {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "|||IP_ADDRESS|||",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": false
10
- },
11
- "1": {
12
- "content": "<|padding|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "50254": {
20
- "content": " ",
21
- "lstrip": false,
22
- "normalized": true,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": false
26
- },
27
- "50255": {
28
- "content": " ",
29
- "lstrip": false,
30
- "normalized": true,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": false
34
- },
35
- "50256": {
36
- "content": " ",
37
- "lstrip": false,
38
- "normalized": true,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": false
42
- },
43
- "50257": {
44
- "content": " ",
45
- "lstrip": false,
46
- "normalized": true,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": false
50
- },
51
- "50258": {
52
- "content": " ",
53
- "lstrip": false,
54
- "normalized": true,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": false
58
- },
59
- "50259": {
60
- "content": " ",
61
- "lstrip": false,
62
- "normalized": true,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": false
66
- },
67
- "50260": {
68
- "content": " ",
69
- "lstrip": false,
70
- "normalized": true,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": false
74
- },
75
- "50261": {
76
- "content": " ",
77
- "lstrip": false,
78
- "normalized": true,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": false
82
- },
83
- "50262": {
84
- "content": " ",
85
- "lstrip": false,
86
- "normalized": true,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": false
90
- },
91
- "50263": {
92
- "content": " ",
93
- "lstrip": false,
94
- "normalized": true,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": false
98
- },
99
- "50264": {
100
- "content": " ",
101
- "lstrip": false,
102
- "normalized": true,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": false
106
- },
107
- "50265": {
108
- "content": " ",
109
- "lstrip": false,
110
- "normalized": true,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": false
114
- },
115
- "50266": {
116
- "content": " ",
117
- "lstrip": false,
118
- "normalized": true,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": false
122
- },
123
- "50267": {
124
- "content": " ",
125
- "lstrip": false,
126
- "normalized": true,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": false
130
- },
131
- "50268": {
132
- "content": " ",
133
- "lstrip": false,
134
- "normalized": true,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": false
138
- },
139
- "50269": {
140
- "content": " ",
141
- "lstrip": false,
142
- "normalized": true,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": false
146
- },
147
- "50270": {
148
- "content": " ",
149
- "lstrip": false,
150
- "normalized": true,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": false
154
- },
155
- "50271": {
156
- "content": " ",
157
- "lstrip": false,
158
- "normalized": true,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": false
162
- },
163
- "50272": {
164
- "content": " ",
165
- "lstrip": false,
166
- "normalized": true,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": false
170
- },
171
- "50273": {
172
- "content": " ",
173
- "lstrip": false,
174
- "normalized": true,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": false
178
- },
179
- "50274": {
180
- "content": " ",
181
- "lstrip": false,
182
- "normalized": true,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": false
186
- },
187
- "50275": {
188
- "content": " ",
189
- "lstrip": false,
190
- "normalized": true,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": false
194
- },
195
- "50276": {
196
- "content": " ",
197
- "lstrip": false,
198
- "normalized": true,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": false
202
- },
203
- "50277": {
204
- "content": "|||EMAIL_ADDRESS|||",
205
- "lstrip": false,
206
- "normalized": true,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": false
210
- },
211
- "50278": {
212
- "content": "|||PHONE_NUMBER|||",
213
- "lstrip": false,
214
- "normalized": true,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": false
218
- },
219
- "50279": {
220
- "content": "<|endoftext|>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "50280": {
228
- "content": "[UNK]",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "50281": {
236
- "content": "[CLS]",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "50282": {
244
- "content": "[SEP]",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "50283": {
252
- "content": "[PAD]",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "50284": {
260
- "content": "[MASK]",
261
- "lstrip": true,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "50285": {
268
- "content": "[unused0]",
269
- "lstrip": false,
270
- "normalized": true,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": false
274
- },
275
- "50286": {
276
- "content": "[unused1]",
277
- "lstrip": false,
278
- "normalized": true,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": false
282
- },
283
- "50287": {
284
- "content": "[unused2]",
285
- "lstrip": false,
286
- "normalized": true,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": false
290
- },
291
- "50288": {
292
- "content": "[unused3]",
293
- "lstrip": false,
294
- "normalized": true,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": false
298
- },
299
- "50289": {
300
- "content": "[unused4]",
301
- "lstrip": false,
302
- "normalized": true,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": false
306
- },
307
- "50290": {
308
- "content": "[unused5]",
309
- "lstrip": false,
310
- "normalized": true,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": false
314
- },
315
- "50291": {
316
- "content": "[unused6]",
317
- "lstrip": false,
318
- "normalized": true,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": false
322
- },
323
- "50292": {
324
- "content": "[unused7]",
325
- "lstrip": false,
326
- "normalized": true,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": false
330
- },
331
- "50293": {
332
- "content": "[unused8]",
333
- "lstrip": false,
334
- "normalized": true,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": false
338
- },
339
- "50294": {
340
- "content": "[unused9]",
341
- "lstrip": false,
342
- "normalized": true,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": false
346
- },
347
- "50295": {
348
- "content": "[unused10]",
349
- "lstrip": false,
350
- "normalized": true,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": false
354
- },
355
- "50296": {
356
- "content": "[unused11]",
357
- "lstrip": false,
358
- "normalized": true,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": false
362
- },
363
- "50297": {
364
- "content": "[unused12]",
365
- "lstrip": false,
366
- "normalized": true,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": false
370
- },
371
- "50298": {
372
- "content": "[unused13]",
373
- "lstrip": false,
374
- "normalized": true,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": false
378
- },
379
- "50299": {
380
- "content": "[unused14]",
381
- "lstrip": false,
382
- "normalized": true,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": false
386
- },
387
- "50300": {
388
- "content": "[unused15]",
389
- "lstrip": false,
390
- "normalized": true,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": false
394
- },
395
- "50301": {
396
- "content": "[unused16]",
397
- "lstrip": false,
398
- "normalized": true,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": false
402
- },
403
- "50302": {
404
- "content": "[unused17]",
405
- "lstrip": false,
406
- "normalized": true,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": false
410
- },
411
- "50303": {
412
- "content": "[unused18]",
413
- "lstrip": false,
414
- "normalized": true,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": false
418
- },
419
- "50304": {
420
- "content": "[unused19]",
421
- "lstrip": false,
422
- "normalized": true,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": false
426
- },
427
- "50305": {
428
- "content": "[unused20]",
429
- "lstrip": false,
430
- "normalized": true,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": false
434
- },
435
- "50306": {
436
- "content": "[unused21]",
437
- "lstrip": false,
438
- "normalized": true,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": false
442
- },
443
- "50307": {
444
- "content": "[unused22]",
445
- "lstrip": false,
446
- "normalized": true,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": false
450
- },
451
- "50308": {
452
- "content": "[unused23]",
453
- "lstrip": false,
454
- "normalized": true,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": false
458
- },
459
- "50309": {
460
- "content": "[unused24]",
461
- "lstrip": false,
462
- "normalized": true,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": false
466
- },
467
- "50310": {
468
- "content": "[unused25]",
469
- "lstrip": false,
470
- "normalized": true,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": false
474
- },
475
- "50311": {
476
- "content": "[unused26]",
477
- "lstrip": false,
478
- "normalized": true,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": false
482
- },
483
- "50312": {
484
- "content": "[unused27]",
485
- "lstrip": false,
486
- "normalized": true,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": false
490
- },
491
- "50313": {
492
- "content": "[unused28]",
493
- "lstrip": false,
494
- "normalized": true,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": false
498
- },
499
- "50314": {
500
- "content": "[unused29]",
501
- "lstrip": false,
502
- "normalized": true,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": false
506
- },
507
- "50315": {
508
- "content": "[unused30]",
509
- "lstrip": false,
510
- "normalized": true,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": false
514
- },
515
- "50316": {
516
- "content": "[unused31]",
517
- "lstrip": false,
518
- "normalized": true,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": false
522
- },
523
- "50317": {
524
- "content": "[unused32]",
525
- "lstrip": false,
526
- "normalized": true,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": false
530
- },
531
- "50318": {
532
- "content": "[unused33]",
533
- "lstrip": false,
534
- "normalized": true,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": false
538
- },
539
- "50319": {
540
- "content": "[unused34]",
541
- "lstrip": false,
542
- "normalized": true,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": false
546
- },
547
- "50320": {
548
- "content": "[unused35]",
549
- "lstrip": false,
550
- "normalized": true,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": false
554
- },
555
- "50321": {
556
- "content": "[unused36]",
557
- "lstrip": false,
558
- "normalized": true,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": false
562
- },
563
- "50322": {
564
- "content": "[unused37]",
565
- "lstrip": false,
566
- "normalized": true,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": false
570
- },
571
- "50323": {
572
- "content": "[unused38]",
573
- "lstrip": false,
574
- "normalized": true,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": false
578
- },
579
- "50324": {
580
- "content": "[unused39]",
581
- "lstrip": false,
582
- "normalized": true,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": false
586
- },
587
- "50325": {
588
- "content": "[unused40]",
589
- "lstrip": false,
590
- "normalized": true,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": false
594
- },
595
- "50326": {
596
- "content": "[unused41]",
597
- "lstrip": false,
598
- "normalized": true,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": false
602
- },
603
- "50327": {
604
- "content": "[unused42]",
605
- "lstrip": false,
606
- "normalized": true,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": false
610
- },
611
- "50328": {
612
- "content": "[unused43]",
613
- "lstrip": false,
614
- "normalized": true,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": false
618
- },
619
- "50329": {
620
- "content": "[unused44]",
621
- "lstrip": false,
622
- "normalized": true,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": false
626
- },
627
- "50330": {
628
- "content": "[unused45]",
629
- "lstrip": false,
630
- "normalized": true,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": false
634
- },
635
- "50331": {
636
- "content": "[unused46]",
637
- "lstrip": false,
638
- "normalized": true,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": false
642
- },
643
- "50332": {
644
- "content": "[unused47]",
645
- "lstrip": false,
646
- "normalized": true,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": false
650
- },
651
- "50333": {
652
- "content": "[unused48]",
653
- "lstrip": false,
654
- "normalized": true,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": false
658
- },
659
- "50334": {
660
- "content": "[unused49]",
661
- "lstrip": false,
662
- "normalized": true,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": false
666
- },
667
- "50335": {
668
- "content": "[unused50]",
669
- "lstrip": false,
670
- "normalized": true,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": false
674
- },
675
- "50336": {
676
- "content": "[unused51]",
677
- "lstrip": false,
678
- "normalized": true,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": false
682
- },
683
- "50337": {
684
- "content": "[unused52]",
685
- "lstrip": false,
686
- "normalized": true,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": false
690
- },
691
- "50338": {
692
- "content": "[unused53]",
693
- "lstrip": false,
694
- "normalized": true,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": false
698
- },
699
- "50339": {
700
- "content": "[unused54]",
701
- "lstrip": false,
702
- "normalized": true,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": false
706
- },
707
- "50340": {
708
- "content": "[unused55]",
709
- "lstrip": false,
710
- "normalized": true,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": false
714
- },
715
- "50341": {
716
- "content": "[unused56]",
717
- "lstrip": false,
718
- "normalized": true,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": false
722
- },
723
- "50342": {
724
- "content": "[unused57]",
725
- "lstrip": false,
726
- "normalized": true,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": false
730
- },
731
- "50343": {
732
- "content": "[unused58]",
733
- "lstrip": false,
734
- "normalized": true,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": false
738
- },
739
- "50344": {
740
- "content": "[unused59]",
741
- "lstrip": false,
742
- "normalized": true,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": false
746
- },
747
- "50345": {
748
- "content": "[unused60]",
749
- "lstrip": false,
750
- "normalized": true,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": false
754
- },
755
- "50346": {
756
- "content": "[unused61]",
757
- "lstrip": false,
758
- "normalized": true,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": false
762
- },
763
- "50347": {
764
- "content": "[unused62]",
765
- "lstrip": false,
766
- "normalized": true,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": false
770
- },
771
- "50348": {
772
- "content": "[unused63]",
773
- "lstrip": false,
774
- "normalized": true,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": false
778
- },
779
- "50349": {
780
- "content": "[unused64]",
781
- "lstrip": false,
782
- "normalized": true,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": false
786
- },
787
- "50350": {
788
- "content": "[unused65]",
789
- "lstrip": false,
790
- "normalized": true,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": false
794
- },
795
- "50351": {
796
- "content": "[unused66]",
797
- "lstrip": false,
798
- "normalized": true,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": false
802
- },
803
- "50352": {
804
- "content": "[unused67]",
805
- "lstrip": false,
806
- "normalized": true,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": false
810
- },
811
- "50353": {
812
- "content": "[unused68]",
813
- "lstrip": false,
814
- "normalized": true,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": false
818
- },
819
- "50354": {
820
- "content": "[unused69]",
821
- "lstrip": false,
822
- "normalized": true,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": false
826
- },
827
- "50355": {
828
- "content": "[unused70]",
829
- "lstrip": false,
830
- "normalized": true,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": false
834
- },
835
- "50356": {
836
- "content": "[unused71]",
837
- "lstrip": false,
838
- "normalized": true,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": false
842
- },
843
- "50357": {
844
- "content": "[unused72]",
845
- "lstrip": false,
846
- "normalized": true,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": false
850
- },
851
- "50358": {
852
- "content": "[unused73]",
853
- "lstrip": false,
854
- "normalized": true,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": false
858
- },
859
- "50359": {
860
- "content": "[unused74]",
861
- "lstrip": false,
862
- "normalized": true,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": false
866
- },
867
- "50360": {
868
- "content": "[unused75]",
869
- "lstrip": false,
870
- "normalized": true,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": false
874
- },
875
- "50361": {
876
- "content": "[unused76]",
877
- "lstrip": false,
878
- "normalized": true,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": false
882
- },
883
- "50362": {
884
- "content": "[unused77]",
885
- "lstrip": false,
886
- "normalized": true,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": false
890
- },
891
- "50363": {
892
- "content": "[unused78]",
893
- "lstrip": false,
894
- "normalized": true,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": false
898
- },
899
- "50364": {
900
- "content": "[unused79]",
901
- "lstrip": false,
902
- "normalized": true,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": false
906
- },
907
- "50365": {
908
- "content": "[unused80]",
909
- "lstrip": false,
910
- "normalized": true,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": false
914
- },
915
- "50366": {
916
- "content": "[unused81]",
917
- "lstrip": false,
918
- "normalized": true,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": false
922
- },
923
- "50367": {
924
- "content": "[unused82]",
925
- "lstrip": false,
926
- "normalized": true,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": false
930
- }
931
- },
932
- "clean_up_tokenization_spaces": true,
933
- "cls_token": "[CLS]",
934
- "extra_special_tokens": {},
935
- "mask_token": "[MASK]",
936
- "model_input_names": [
937
- "input_ids",
938
- "attention_mask"
939
- ],
940
- "model_max_length": 512,
941
- "pad_token": "[PAD]",
942
- "sep_token": "[SEP]",
943
- "tokenizer_class": "PreTrainedTokenizerFast",
944
- "unk_token": "[UNK]"
945
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
SynFinBERT_Final/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5fc8b97dcbfe3b68dd807df9e7cae0352a04f713f492a6819a6f88527b5d8244
3
- size 5841