smithblack-0 commited on
Commit
679b05f
·
verified ·
1 Parent(s): 2cb0520

Upload folder using huggingface_hub

Browse files
uniform_normalized_123/epoch2/metadata.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch_num": 2,
3
+ "global_batch_num": 402,
4
+ "device": "cuda",
5
+ "dtype": "bfloat16"
6
+ }
uniform_normalized_123/epoch2/metrics.json ADDED
@@ -0,0 +1,1258 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "training": {
3
+ "effective_batch_nums": [
4
+ 1,
5
+ 2,
6
+ 3,
7
+ 4,
8
+ 5,
9
+ 6,
10
+ 7,
11
+ 8,
12
+ 9,
13
+ 10,
14
+ 11,
15
+ 12,
16
+ 13,
17
+ 14,
18
+ 15,
19
+ 16,
20
+ 17,
21
+ 18,
22
+ 19,
23
+ 20,
24
+ 21,
25
+ 22,
26
+ 23,
27
+ 24,
28
+ 25,
29
+ 26,
30
+ 27,
31
+ 28,
32
+ 29,
33
+ 30,
34
+ 31,
35
+ 32,
36
+ 33,
37
+ 34,
38
+ 35,
39
+ 36,
40
+ 37,
41
+ 38,
42
+ 39,
43
+ 40,
44
+ 41,
45
+ 42,
46
+ 43,
47
+ 44,
48
+ 45,
49
+ 46,
50
+ 47,
51
+ 48,
52
+ 49,
53
+ 50,
54
+ 51,
55
+ 52,
56
+ 53,
57
+ 54,
58
+ 55,
59
+ 56,
60
+ 57,
61
+ 58,
62
+ 59,
63
+ 60,
64
+ 61,
65
+ 62,
66
+ 63,
67
+ 64,
68
+ 65,
69
+ 66,
70
+ 67,
71
+ 68,
72
+ 69,
73
+ 70,
74
+ 71,
75
+ 72,
76
+ 73,
77
+ 74,
78
+ 75,
79
+ 76,
80
+ 77,
81
+ 78,
82
+ 79,
83
+ 80,
84
+ 81,
85
+ 82,
86
+ 83,
87
+ 84,
88
+ 85,
89
+ 86,
90
+ 87,
91
+ 88,
92
+ 89,
93
+ 90,
94
+ 91,
95
+ 92,
96
+ 93,
97
+ 94,
98
+ 95,
99
+ 96,
100
+ 97,
101
+ 98,
102
+ 99,
103
+ 100,
104
+ 101,
105
+ 102,
106
+ 103,
107
+ 104,
108
+ 105,
109
+ 106,
110
+ 107,
111
+ 108,
112
+ 109,
113
+ 110,
114
+ 111,
115
+ 112,
116
+ 113,
117
+ 114,
118
+ 115,
119
+ 116,
120
+ 117,
121
+ 118,
122
+ 119,
123
+ 120,
124
+ 121,
125
+ 122,
126
+ 123,
127
+ 124,
128
+ 125,
129
+ 126,
130
+ 127,
131
+ 128,
132
+ 129,
133
+ 130,
134
+ 131,
135
+ 132,
136
+ 133,
137
+ 134,
138
+ 135,
139
+ 136,
140
+ 137,
141
+ 138,
142
+ 139,
143
+ 140,
144
+ 141,
145
+ 142,
146
+ 143,
147
+ 144,
148
+ 145,
149
+ 146,
150
+ 147,
151
+ 148,
152
+ 149,
153
+ 150,
154
+ 151,
155
+ 152,
156
+ 153,
157
+ 154,
158
+ 155,
159
+ 156,
160
+ 157,
161
+ 158,
162
+ 159,
163
+ 160,
164
+ 161,
165
+ 162,
166
+ 163,
167
+ 164,
168
+ 165,
169
+ 166,
170
+ 167,
171
+ 168,
172
+ 169,
173
+ 170,
174
+ 171,
175
+ 172,
176
+ 173,
177
+ 174,
178
+ 175,
179
+ 176,
180
+ 177,
181
+ 178,
182
+ 179,
183
+ 180,
184
+ 181,
185
+ 182,
186
+ 183,
187
+ 184,
188
+ 185,
189
+ 186,
190
+ 187,
191
+ 188,
192
+ 189,
193
+ 190,
194
+ 191,
195
+ 192,
196
+ 193,
197
+ 194,
198
+ 195,
199
+ 196,
200
+ 197,
201
+ 198,
202
+ 199,
203
+ 200,
204
+ 201,
205
+ 202,
206
+ 203,
207
+ 204,
208
+ 205,
209
+ 206,
210
+ 207,
211
+ 208,
212
+ 209,
213
+ 210,
214
+ 211,
215
+ 212,
216
+ 213,
217
+ 214,
218
+ 215,
219
+ 216,
220
+ 217,
221
+ 218,
222
+ 219,
223
+ 220,
224
+ 221,
225
+ 222,
226
+ 223,
227
+ 224,
228
+ 225,
229
+ 226,
230
+ 227,
231
+ 228,
232
+ 229,
233
+ 230,
234
+ 231,
235
+ 232,
236
+ 233,
237
+ 234,
238
+ 235,
239
+ 236,
240
+ 237,
241
+ 238,
242
+ 239,
243
+ 240,
244
+ 241,
245
+ 242,
246
+ 243,
247
+ 244,
248
+ 245,
249
+ 246,
250
+ 247,
251
+ 248,
252
+ 249,
253
+ 250,
254
+ 251,
255
+ 252,
256
+ 253,
257
+ 254,
258
+ 255,
259
+ 256,
260
+ 257,
261
+ 258,
262
+ 259,
263
+ 260,
264
+ 261,
265
+ 262,
266
+ 263,
267
+ 264,
268
+ 265,
269
+ 266,
270
+ 267,
271
+ 268,
272
+ 269,
273
+ 270,
274
+ 271,
275
+ 272,
276
+ 273,
277
+ 274,
278
+ 275,
279
+ 276,
280
+ 277,
281
+ 278,
282
+ 279,
283
+ 280,
284
+ 281,
285
+ 282,
286
+ 283,
287
+ 284,
288
+ 285,
289
+ 286,
290
+ 287,
291
+ 288,
292
+ 289,
293
+ 290,
294
+ 291,
295
+ 292,
296
+ 293,
297
+ 294,
298
+ 295,
299
+ 296,
300
+ 297,
301
+ 298,
302
+ 299,
303
+ 300,
304
+ 301,
305
+ 302,
306
+ 303,
307
+ 304,
308
+ 305,
309
+ 306,
310
+ 307,
311
+ 308,
312
+ 309,
313
+ 310,
314
+ 311,
315
+ 312,
316
+ 313,
317
+ 314,
318
+ 315,
319
+ 316,
320
+ 317,
321
+ 318,
322
+ 319,
323
+ 320,
324
+ 321,
325
+ 322,
326
+ 323,
327
+ 324,
328
+ 325,
329
+ 326,
330
+ 327,
331
+ 328,
332
+ 329,
333
+ 330,
334
+ 331,
335
+ 332,
336
+ 333,
337
+ 334,
338
+ 335,
339
+ 336,
340
+ 337,
341
+ 338,
342
+ 339,
343
+ 340,
344
+ 341,
345
+ 342,
346
+ 343,
347
+ 344,
348
+ 345,
349
+ 346,
350
+ 347,
351
+ 348,
352
+ 349,
353
+ 350,
354
+ 351,
355
+ 352,
356
+ 353,
357
+ 354,
358
+ 355,
359
+ 356,
360
+ 357,
361
+ 358,
362
+ 359,
363
+ 360,
364
+ 361,
365
+ 362,
366
+ 363,
367
+ 364,
368
+ 365,
369
+ 366,
370
+ 367,
371
+ 368,
372
+ 369,
373
+ 370,
374
+ 371,
375
+ 372,
376
+ 373,
377
+ 374,
378
+ 375,
379
+ 376,
380
+ 377,
381
+ 378,
382
+ 379,
383
+ 380,
384
+ 381,
385
+ 382,
386
+ 383,
387
+ 384,
388
+ 385,
389
+ 386,
390
+ 387,
391
+ 388,
392
+ 389,
393
+ 390,
394
+ 391,
395
+ 392,
396
+ 393,
397
+ 394,
398
+ 395,
399
+ 396,
400
+ 397,
401
+ 398,
402
+ 399,
403
+ 400,
404
+ 401,
405
+ 402
406
+ ],
407
+ "losses": [
408
+ 118.0,
409
+ 47.75,
410
+ 49.0,
411
+ 42.25,
412
+ 36.0,
413
+ 29.75,
414
+ 24.25,
415
+ 19.75,
416
+ 16.375,
417
+ 14.0625,
418
+ 12.25,
419
+ 11.1875,
420
+ 10.5625,
421
+ 10.125,
422
+ 9.9375,
423
+ 9.875,
424
+ 9.75,
425
+ 9.75,
426
+ 9.625,
427
+ 9.5,
428
+ 9.375,
429
+ 9.1875,
430
+ 9.0625,
431
+ 9.0,
432
+ 8.875,
433
+ 8.9375,
434
+ 8.8125,
435
+ 8.75,
436
+ 8.75,
437
+ 8.6875,
438
+ 8.6875,
439
+ 8.6875,
440
+ 8.6875,
441
+ 8.6875,
442
+ 8.625,
443
+ 8.625,
444
+ 8.6875,
445
+ 8.5,
446
+ 8.5,
447
+ 8.5625,
448
+ 8.5625,
449
+ 8.5,
450
+ 8.5625,
451
+ 8.5625,
452
+ 8.5,
453
+ 8.5,
454
+ 8.5,
455
+ 8.5,
456
+ 8.5,
457
+ 8.5,
458
+ 8.5,
459
+ 8.5,
460
+ 8.5,
461
+ 8.5,
462
+ 8.5,
463
+ 8.4375,
464
+ 8.5,
465
+ 8.5,
466
+ 8.5,
467
+ 8.5,
468
+ 8.4375,
469
+ 8.4375,
470
+ 8.4375,
471
+ 8.4375,
472
+ 8.4375,
473
+ 8.5,
474
+ 8.4375,
475
+ 8.4375,
476
+ 8.4375,
477
+ 8.4375,
478
+ 8.4375,
479
+ 8.4375,
480
+ 8.4375,
481
+ 8.4375,
482
+ 8.4375,
483
+ 8.5,
484
+ 8.4375,
485
+ 8.4375,
486
+ 8.4375,
487
+ 8.4375,
488
+ 8.375,
489
+ 8.4375,
490
+ 8.375,
491
+ 8.4375,
492
+ 8.375,
493
+ 8.375,
494
+ 8.4375,
495
+ 8.4375,
496
+ 8.375,
497
+ 8.375,
498
+ 8.375,
499
+ 8.4375,
500
+ 8.4375,
501
+ 8.4375,
502
+ 8.375,
503
+ 8.4375,
504
+ 8.375,
505
+ 8.375,
506
+ 8.4375,
507
+ 8.375,
508
+ 8.375,
509
+ 8.4375,
510
+ 8.4375,
511
+ 8.4375,
512
+ 8.375,
513
+ 8.4375,
514
+ 8.375,
515
+ 8.375,
516
+ 8.4375,
517
+ 8.4375,
518
+ 8.4375,
519
+ 8.375,
520
+ 8.4375,
521
+ 8.375,
522
+ 8.375,
523
+ 8.4375,
524
+ 8.4375,
525
+ 8.375,
526
+ 8.375,
527
+ 8.4375,
528
+ 8.375,
529
+ 8.4375,
530
+ 8.4375,
531
+ 8.4375,
532
+ 8.375,
533
+ 8.3125,
534
+ 8.375,
535
+ 8.375,
536
+ 8.4375,
537
+ 8.375,
538
+ 8.4375,
539
+ 8.375,
540
+ 8.4375,
541
+ 8.375,
542
+ 8.4375,
543
+ 8.3125,
544
+ 8.375,
545
+ 8.375,
546
+ 8.375,
547
+ 8.375,
548
+ 8.375,
549
+ 8.375,
550
+ 8.375,
551
+ 8.375,
552
+ 8.375,
553
+ 8.375,
554
+ 8.4375,
555
+ 8.375,
556
+ 8.375,
557
+ 8.375,
558
+ 8.375,
559
+ 8.375,
560
+ 8.375,
561
+ 8.375,
562
+ 8.375,
563
+ 8.4375,
564
+ 8.375,
565
+ 8.4375,
566
+ 8.375,
567
+ 8.375,
568
+ 8.375,
569
+ 8.3125,
570
+ 8.375,
571
+ 8.375,
572
+ 8.375,
573
+ 8.375,
574
+ 8.375,
575
+ 8.375,
576
+ 8.375,
577
+ 8.375,
578
+ 8.375,
579
+ 8.375,
580
+ 8.4375,
581
+ 8.375,
582
+ 8.375,
583
+ 8.375,
584
+ 8.375,
585
+ 8.375,
586
+ 8.375,
587
+ 8.3125,
588
+ 8.375,
589
+ 8.375,
590
+ 8.375,
591
+ 8.375,
592
+ 8.375,
593
+ 8.3125,
594
+ 8.375,
595
+ 8.3125,
596
+ 8.3125,
597
+ 8.3125,
598
+ 8.3125,
599
+ 8.3125,
600
+ 8.3125,
601
+ 8.375,
602
+ 8.25,
603
+ 8.375,
604
+ 8.3125,
605
+ 8.3125,
606
+ 8.3125,
607
+ 8.3125,
608
+ 8.3125,
609
+ 8.375,
610
+ 8.3125,
611
+ 8.3125,
612
+ 8.25,
613
+ 8.3125,
614
+ 8.3125,
615
+ 8.25,
616
+ 8.3125,
617
+ 8.3125,
618
+ 8.3125,
619
+ 8.25,
620
+ 8.3125,
621
+ 8.3125,
622
+ 8.25,
623
+ 8.25,
624
+ 8.25,
625
+ 8.25,
626
+ 8.3125,
627
+ 8.25,
628
+ 8.25,
629
+ 8.3125,
630
+ 8.25,
631
+ 8.25,
632
+ 8.25,
633
+ 8.25,
634
+ 8.25,
635
+ 8.25,
636
+ 8.25,
637
+ 8.3125,
638
+ 8.25,
639
+ 8.25,
640
+ 8.1875,
641
+ 8.25,
642
+ 8.25,
643
+ 8.25,
644
+ 8.25,
645
+ 8.3125,
646
+ 8.25,
647
+ 8.1875,
648
+ 8.25,
649
+ 8.3125,
650
+ 8.25,
651
+ 8.3125,
652
+ 8.3125,
653
+ 8.25,
654
+ 8.3125,
655
+ 8.25,
656
+ 8.3125,
657
+ 8.3125,
658
+ 8.25,
659
+ 8.3125,
660
+ 8.25,
661
+ 8.3125,
662
+ 8.3125,
663
+ 8.25,
664
+ 8.25,
665
+ 8.25,
666
+ 8.25,
667
+ 8.25,
668
+ 8.25,
669
+ 8.25,
670
+ 8.3125,
671
+ 8.3125,
672
+ 8.3125,
673
+ 8.3125,
674
+ 8.375,
675
+ 8.3125,
676
+ 8.3125,
677
+ 8.3125,
678
+ 8.3125,
679
+ 8.3125,
680
+ 8.3125,
681
+ 8.25,
682
+ 8.3125,
683
+ 8.25,
684
+ 8.3125,
685
+ 8.25,
686
+ 8.3125,
687
+ 8.3125,
688
+ 8.3125,
689
+ 8.25,
690
+ 8.25,
691
+ 8.25,
692
+ 8.3125,
693
+ 8.25,
694
+ 8.25,
695
+ 8.25,
696
+ 8.1875,
697
+ 8.25,
698
+ 8.25,
699
+ 8.25,
700
+ 8.1875,
701
+ 8.25,
702
+ 8.1875,
703
+ 8.25,
704
+ 8.1875,
705
+ 8.1875,
706
+ 8.25,
707
+ 8.25,
708
+ 8.3125,
709
+ 8.1875,
710
+ 8.3125,
711
+ 8.3125,
712
+ 8.1875,
713
+ 8.25,
714
+ 8.3125,
715
+ 8.25,
716
+ 8.25,
717
+ 8.25,
718
+ 8.25,
719
+ 8.25,
720
+ 8.25,
721
+ 8.3125,
722
+ 8.25,
723
+ 8.25,
724
+ 8.25,
725
+ 8.1875,
726
+ 8.25,
727
+ 8.25,
728
+ 8.25,
729
+ 8.1875,
730
+ 8.25,
731
+ 8.25,
732
+ 8.25,
733
+ 8.25,
734
+ 8.25,
735
+ 8.25,
736
+ 8.25,
737
+ 8.3125,
738
+ 8.25,
739
+ 8.25,
740
+ 8.25,
741
+ 8.25,
742
+ 8.25,
743
+ 8.1875,
744
+ 8.1875,
745
+ 8.1875,
746
+ 8.25,
747
+ 8.25,
748
+ 8.1875,
749
+ 8.25,
750
+ 8.25,
751
+ 8.1875,
752
+ 8.25,
753
+ 8.25,
754
+ 8.25,
755
+ 8.25,
756
+ 8.25,
757
+ 8.1875,
758
+ 8.1875,
759
+ 8.125,
760
+ 8.1875,
761
+ 8.1875,
762
+ 8.25,
763
+ 8.1875,
764
+ 8.1875,
765
+ 8.1875,
766
+ 8.1875,
767
+ 8.1875,
768
+ 8.1875,
769
+ 8.1875,
770
+ 8.1875,
771
+ 8.1875,
772
+ 8.25,
773
+ 8.25,
774
+ 8.1875,
775
+ 8.1875,
776
+ 8.125,
777
+ 8.1875,
778
+ 8.125,
779
+ 8.1875,
780
+ 8.25,
781
+ 8.125,
782
+ 8.1875,
783
+ 8.1875,
784
+ 8.125,
785
+ 8.125,
786
+ 8.125,
787
+ 8.125,
788
+ 8.125,
789
+ 8.1875,
790
+ 8.125,
791
+ 8.125,
792
+ 8.125,
793
+ 8.1875,
794
+ 8.1875,
795
+ 8.125,
796
+ 8.125,
797
+ 8.1875,
798
+ 8.125,
799
+ 8.125,
800
+ 8.125,
801
+ 8.125,
802
+ 8.1875,
803
+ 8.125,
804
+ 8.125,
805
+ 8.125,
806
+ 8.1875,
807
+ 8.1875,
808
+ 8.1875,
809
+ 8.1875
810
+ ],
811
+ "grad_norms": [
812
+ 27.0,
813
+ 21.75,
814
+ 21.75,
815
+ 14.5,
816
+ 10.25,
817
+ 6.5625,
818
+ 4.9375,
819
+ 3.578125,
820
+ 2.5625,
821
+ 3.171875,
822
+ 1.6328125,
823
+ 1.5703125,
824
+ 1.65625,
825
+ 1.421875,
826
+ 1.5390625,
827
+ 1.6796875,
828
+ 1.9140625,
829
+ 1.7890625,
830
+ 1.5390625,
831
+ 1.421875,
832
+ 1.3515625,
833
+ 1.2421875,
834
+ 0.8984375,
835
+ 0.6953125,
836
+ 0.7578125,
837
+ 0.75,
838
+ 0.6953125,
839
+ 0.5078125,
840
+ 0.43359375,
841
+ 0.423828125,
842
+ 0.46875,
843
+ 0.52734375,
844
+ 0.5078125,
845
+ 0.49609375,
846
+ 0.41796875,
847
+ 0.41796875,
848
+ 0.318359375,
849
+ 0.359375,
850
+ 0.416015625,
851
+ 0.427734375,
852
+ 0.421875,
853
+ 0.357421875,
854
+ 0.2890625,
855
+ 0.283203125,
856
+ 0.298828125,
857
+ 0.33984375,
858
+ 0.3671875,
859
+ 0.1904296875,
860
+ 0.326171875,
861
+ 0.267578125,
862
+ 0.2734375,
863
+ 0.20703125,
864
+ 0.21875,
865
+ 0.28125,
866
+ 0.2275390625,
867
+ 0.2109375,
868
+ 0.1884765625,
869
+ 0.2001953125,
870
+ 0.3046875,
871
+ 0.2119140625,
872
+ 0.16796875,
873
+ 0.302734375,
874
+ 0.251953125,
875
+ 0.1630859375,
876
+ 0.1943359375,
877
+ 0.23046875,
878
+ 0.1669921875,
879
+ 0.1748046875,
880
+ 0.2451171875,
881
+ 0.1787109375,
882
+ 0.181640625,
883
+ 0.1708984375,
884
+ 0.1904296875,
885
+ 0.1806640625,
886
+ 0.134765625,
887
+ 0.1796875,
888
+ 0.1630859375,
889
+ 0.1611328125,
890
+ 0.1943359375,
891
+ 0.169921875,
892
+ 0.140625,
893
+ 0.1943359375,
894
+ 0.2080078125,
895
+ 0.2138671875,
896
+ 0.181640625,
897
+ 0.2109375,
898
+ 0.1904296875,
899
+ 0.185546875,
900
+ 0.166015625,
901
+ 0.1572265625,
902
+ 0.1328125,
903
+ 0.1650390625,
904
+ 0.2060546875,
905
+ 0.12890625,
906
+ 0.177734375,
907
+ 0.1611328125,
908
+ 0.1875,
909
+ 0.15625,
910
+ 0.251953125,
911
+ 0.212890625,
912
+ 0.142578125,
913
+ 0.203125,
914
+ 0.19140625,
915
+ 0.1298828125,
916
+ 0.162109375,
917
+ 0.173828125,
918
+ 0.1630859375,
919
+ 0.171875,
920
+ 0.1640625,
921
+ 0.1572265625,
922
+ 0.166015625,
923
+ 0.169921875,
924
+ 0.177734375,
925
+ 0.15234375,
926
+ 0.169921875,
927
+ 0.1572265625,
928
+ 0.2001953125,
929
+ 0.169921875,
930
+ 0.275390625,
931
+ 0.1884765625,
932
+ 0.1494140625,
933
+ 0.169921875,
934
+ 0.1767578125,
935
+ 0.154296875,
936
+ 0.1650390625,
937
+ 0.287109375,
938
+ 0.166015625,
939
+ 0.328125,
940
+ 0.2412109375,
941
+ 0.1767578125,
942
+ 0.302734375,
943
+ 0.275390625,
944
+ 0.287109375,
945
+ 0.275390625,
946
+ 0.23046875,
947
+ 0.255859375,
948
+ 0.2373046875,
949
+ 0.2255859375,
950
+ 0.140625,
951
+ 0.20703125,
952
+ 0.162109375,
953
+ 0.1845703125,
954
+ 0.158203125,
955
+ 0.134765625,
956
+ 0.1455078125,
957
+ 0.1337890625,
958
+ 0.1728515625,
959
+ 0.169921875,
960
+ 0.16796875,
961
+ 0.171875,
962
+ 0.158203125,
963
+ 0.1748046875,
964
+ 0.2177734375,
965
+ 0.1923828125,
966
+ 0.146484375,
967
+ 0.1875,
968
+ 0.224609375,
969
+ 0.1826171875,
970
+ 0.1591796875,
971
+ 0.185546875,
972
+ 0.134765625,
973
+ 0.15234375,
974
+ 0.2021484375,
975
+ 0.177734375,
976
+ 0.1396484375,
977
+ 0.1826171875,
978
+ 0.18359375,
979
+ 0.16015625,
980
+ 0.146484375,
981
+ 0.1904296875,
982
+ 0.185546875,
983
+ 0.2197265625,
984
+ 0.2275390625,
985
+ 0.2138671875,
986
+ 0.1923828125,
987
+ 0.2021484375,
988
+ 0.2490234375,
989
+ 0.2099609375,
990
+ 0.1923828125,
991
+ 0.2421875,
992
+ 0.24609375,
993
+ 0.283203125,
994
+ 0.1904296875,
995
+ 0.31640625,
996
+ 0.2490234375,
997
+ 0.3046875,
998
+ 0.2294921875,
999
+ 0.24609375,
1000
+ 0.23828125,
1001
+ 0.39453125,
1002
+ 0.275390625,
1003
+ 0.224609375,
1004
+ 0.392578125,
1005
+ 0.447265625,
1006
+ 0.28515625,
1007
+ 0.2578125,
1008
+ 0.3671875,
1009
+ 0.23828125,
1010
+ 0.2119140625,
1011
+ 0.310546875,
1012
+ 0.337890625,
1013
+ 0.2275390625,
1014
+ 0.2421875,
1015
+ 0.2734375,
1016
+ 0.224609375,
1017
+ 0.33984375,
1018
+ 0.287109375,
1019
+ 0.259765625,
1020
+ 0.33203125,
1021
+ 0.2734375,
1022
+ 0.28125,
1023
+ 0.318359375,
1024
+ 0.30078125,
1025
+ 0.357421875,
1026
+ 0.298828125,
1027
+ 0.34375,
1028
+ 0.37109375,
1029
+ 0.310546875,
1030
+ 0.390625,
1031
+ 0.2333984375,
1032
+ 0.349609375,
1033
+ 0.40625,
1034
+ 0.314453125,
1035
+ 0.28515625,
1036
+ 0.2236328125,
1037
+ 0.3515625,
1038
+ 0.26171875,
1039
+ 0.2470703125,
1040
+ 0.318359375,
1041
+ 0.283203125,
1042
+ 0.3203125,
1043
+ 0.21484375,
1044
+ 0.37890625,
1045
+ 0.40625,
1046
+ 0.486328125,
1047
+ 0.451171875,
1048
+ 0.55859375,
1049
+ 0.48046875,
1050
+ 1.1796875,
1051
+ 0.494140625,
1052
+ 0.5546875,
1053
+ 0.625,
1054
+ 0.671875,
1055
+ 0.8671875,
1056
+ 0.6953125,
1057
+ 0.625,
1058
+ 0.921875,
1059
+ 1.6171875,
1060
+ 0.89453125,
1061
+ 1.2890625,
1062
+ 5.53125,
1063
+ 8.75,
1064
+ 0.97265625,
1065
+ 1.84375,
1066
+ 1.0546875,
1067
+ 2.59375,
1068
+ 4.0,
1069
+ 1.2890625,
1070
+ 1.296875,
1071
+ 1.3125,
1072
+ 1.15625,
1073
+ 3.078125,
1074
+ 2.984375,
1075
+ 2.140625,
1076
+ 2.5,
1077
+ 1.3984375,
1078
+ 1.21875,
1079
+ 1.1953125,
1080
+ 2.234375,
1081
+ 1.375,
1082
+ 1.7265625,
1083
+ 1.8359375,
1084
+ 2.78125,
1085
+ 1.578125,
1086
+ 1.65625,
1087
+ 1.90625,
1088
+ 2.640625,
1089
+ 1.578125,
1090
+ 1.2265625,
1091
+ 2.609375,
1092
+ 2.25,
1093
+ 2.046875,
1094
+ 1.796875,
1095
+ 1.3515625,
1096
+ 1.6640625,
1097
+ 4.1875,
1098
+ 1.65625,
1099
+ 1.625,
1100
+ 1.2734375,
1101
+ 1.9140625,
1102
+ 5.28125,
1103
+ 4.40625,
1104
+ 2.1875,
1105
+ 2.34375,
1106
+ 1.25,
1107
+ 1.9609375,
1108
+ 1.8828125,
1109
+ 1.640625,
1110
+ 2.078125,
1111
+ 2.796875,
1112
+ 1.671875,
1113
+ 6.84375,
1114
+ 2.453125,
1115
+ 2.375,
1116
+ 2.5625,
1117
+ 3.984375,
1118
+ 3.921875,
1119
+ 3.796875,
1120
+ 5.4375,
1121
+ 8.1875,
1122
+ 18.125,
1123
+ 6.625,
1124
+ 4.125,
1125
+ 3.15625,
1126
+ 4.1875,
1127
+ 4.71875,
1128
+ 5.65625,
1129
+ 61.0,
1130
+ 4.375,
1131
+ 3.625,
1132
+ 9.8125,
1133
+ 4.375,
1134
+ 5.46875,
1135
+ 4.59375,
1136
+ 5.09375,
1137
+ 4.875,
1138
+ 8.875,
1139
+ 9.125,
1140
+ 5.75,
1141
+ 7.59375,
1142
+ 7.8125,
1143
+ 9.625,
1144
+ 4.78125,
1145
+ 3.28125,
1146
+ 4.4375,
1147
+ 15.5,
1148
+ 3.71875,
1149
+ 5.4375,
1150
+ 6.90625,
1151
+ 14.0625,
1152
+ 5.6875,
1153
+ 5.125,
1154
+ 5.28125,
1155
+ 3.90625,
1156
+ 5.0,
1157
+ 4.96875,
1158
+ 48.75,
1159
+ 4.375,
1160
+ 4.625,
1161
+ 22.375,
1162
+ 4.125,
1163
+ 3.3125,
1164
+ 44.5,
1165
+ 4.71875,
1166
+ 13.5625,
1167
+ 4.875,
1168
+ 7.96875,
1169
+ 8.125,
1170
+ 4.8125,
1171
+ 4.84375,
1172
+ 12.125,
1173
+ 7.125,
1174
+ 17.25,
1175
+ 7.28125,
1176
+ 9.75,
1177
+ 14.1875,
1178
+ 14.3125,
1179
+ 6.15625,
1180
+ 6.28125,
1181
+ 9.8125,
1182
+ 10.625,
1183
+ 5.8125,
1184
+ 5.40625,
1185
+ 6.0625,
1186
+ 24.125,
1187
+ 6.09375,
1188
+ 6.90625,
1189
+ 5.875,
1190
+ 7.5625,
1191
+ 7.46875,
1192
+ 5.84375,
1193
+ 11.0,
1194
+ 5.78125,
1195
+ 6.875,
1196
+ 9.5,
1197
+ 4.6875,
1198
+ 6.53125,
1199
+ 10.0,
1200
+ 39.0,
1201
+ 7.15625,
1202
+ 6.15625,
1203
+ 6.40625,
1204
+ 5.25,
1205
+ 6.15625,
1206
+ 9.0,
1207
+ 9.3125,
1208
+ 16.75,
1209
+ 7.1875,
1210
+ 18.125,
1211
+ 7.8125,
1212
+ 10.0625,
1213
+ 27.875
1214
+ ]
1215
+ },
1216
+ "eval": {
1217
+ "effective_batch_nums": [
1218
+ 50,
1219
+ 100,
1220
+ 150,
1221
+ 200,
1222
+ 250,
1223
+ 300,
1224
+ 350,
1225
+ 400
1226
+ ],
1227
+ "losses": [
1228
+ 8.518382352941176,
1229
+ 8.4375,
1230
+ 8.411764705882353,
1231
+ 8.345588235294118,
1232
+ 8.341911764705882,
1233
+ 8.286764705882353,
1234
+ 8.261029411764707,
1235
+ 8.198529411764707
1236
+ ],
1237
+ "perplexities": [
1238
+ 5031.529411764706,
1239
+ 4644.705882352941,
1240
+ 4533.64705882353,
1241
+ 4234.35294117647,
1242
+ 4214.588235294118,
1243
+ 3993.4117647058824,
1244
+ 3886.1176470588234,
1245
+ 3650.823529411765
1246
+ ],
1247
+ "accuracies": [
1248
+ 0.041686481236024406,
1249
+ 0.05591755790070118,
1250
+ 0.05911992957817733,
1251
+ 0.08452136432163346,
1252
+ 0.07581475822852692,
1253
+ 0.08564447097629334,
1254
+ 0.0913207127174122,
1255
+ 0.09939999797638441
1256
+ ]
1257
+ }
1258
+ }
uniform_normalized_123/epoch2/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a591841b367e6ec4d2fd6d7b5f2895d877a3058c7e347ae8a79036f45ce4ef43
3
+ size 18206151
uniform_normalized_123/epoch2/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1bcf4d1ece8f9c4e297f94d6390085bd55a60583ce51e4a39a3239259e83e07
3
+ size 36464267
uniform_normalized_123/epoch2/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca809efd04bb824d479775610cf7f3c5c35b6e81b0647b2574978d9cc61f50d1
3
+ size 1465
uniform_normalized_123/epoch2/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
uniform_normalized_123/epoch2/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
uniform_normalized_123/epoch2/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
uniform_normalized_123/epoch2/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
uniform_normalized_123/epoch2/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff