smithblack-0 commited on
Commit
90cc039
·
verified ·
1 Parent(s): 7c84108

Upload folder using huggingface_hub

Browse files
control_123/epoch0/metadata.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch_num": 0,
3
+ "global_batch_num": 134,
4
+ "device": "cuda",
5
+ "dtype": "bfloat16"
6
+ }
control_123/epoch0/metrics.json ADDED
@@ -0,0 +1,562 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
139
+ "losses": [
140
+ 10.9375,
141
+ 10.4375,
142
+ 10.125,
143
+ 9.75,
144
+ 9.5,
145
+ 9.25,
146
+ 8.9375,
147
+ 8.75,
148
+ 8.625,
149
+ 8.5625,
150
+ 8.5,
151
+ 8.4375,
152
+ 8.3125,
153
+ 8.375,
154
+ 8.375,
155
+ 8.375,
156
+ 8.3125,
157
+ 8.25,
158
+ 8.1875,
159
+ 8.125,
160
+ 8.1875,
161
+ 8.25,
162
+ 8.1875,
163
+ 8.125,
164
+ 8.1875,
165
+ 8.125,
166
+ 8.1875,
167
+ 8.125,
168
+ 8.0625,
169
+ 8.0625,
170
+ 8.125,
171
+ 8.0625,
172
+ 8.125,
173
+ 8.0,
174
+ 8.0,
175
+ 8.0,
176
+ 7.96875,
177
+ 8.0,
178
+ 8.0,
179
+ 8.0625,
180
+ 8.0,
181
+ 7.9375,
182
+ 7.90625,
183
+ 8.0,
184
+ 7.90625,
185
+ 7.9375,
186
+ 7.9375,
187
+ 7.875,
188
+ 7.875,
189
+ 7.9375,
190
+ 7.96875,
191
+ 7.90625,
192
+ 7.875,
193
+ 7.875,
194
+ 7.875,
195
+ 7.875,
196
+ 7.875,
197
+ 7.84375,
198
+ 7.84375,
199
+ 7.84375,
200
+ 7.8125,
201
+ 7.78125,
202
+ 7.8125,
203
+ 7.8125,
204
+ 7.78125,
205
+ 7.8125,
206
+ 7.71875,
207
+ 7.78125,
208
+ 7.8125,
209
+ 7.78125,
210
+ 7.8125,
211
+ 7.75,
212
+ 7.75,
213
+ 7.78125,
214
+ 7.71875,
215
+ 7.6875,
216
+ 7.6875,
217
+ 7.71875,
218
+ 7.6875,
219
+ 7.75,
220
+ 7.65625,
221
+ 7.71875,
222
+ 7.6875,
223
+ 7.625,
224
+ 7.65625,
225
+ 7.625,
226
+ 7.59375,
227
+ 7.59375,
228
+ 7.59375,
229
+ 7.65625,
230
+ 7.625,
231
+ 7.59375,
232
+ 7.59375,
233
+ 7.59375,
234
+ 7.59375,
235
+ 7.5625,
236
+ 7.59375,
237
+ 7.59375,
238
+ 7.5625,
239
+ 7.5625,
240
+ 7.53125,
241
+ 7.5625,
242
+ 7.5,
243
+ 7.4375,
244
+ 7.53125,
245
+ 7.40625,
246
+ 7.46875,
247
+ 7.5625,
248
+ 7.46875,
249
+ 7.46875,
250
+ 7.5,
251
+ 7.5625,
252
+ 7.59375,
253
+ 7.46875,
254
+ 7.46875,
255
+ 7.4375,
256
+ 7.46875,
257
+ 7.46875,
258
+ 7.46875,
259
+ 7.5,
260
+ 7.4375,
261
+ 7.53125,
262
+ 7.46875,
263
+ 7.46875,
264
+ 7.4375,
265
+ 7.375,
266
+ 7.46875,
267
+ 7.4375,
268
+ 7.40625,
269
+ 7.375,
270
+ 7.34375,
271
+ 7.46875,
272
+ 7.34375,
273
+ 7.40625
274
+ ],
275
+ "accuracies": [
276
+ 0.0,
277
+ 0.04434589800443459,
278
+ 0.05040629761300152,
279
+ 0.051403641881638845,
280
+ 0.04549262194729042,
281
+ 0.04651681633108372,
282
+ 0.044345255347516085,
283
+ 0.04710648148148148,
284
+ 0.05922487163255258,
285
+ 0.07615278527313066,
286
+ 0.0849886409972622,
287
+ 0.10091743119266056,
288
+ 0.106391493254059,
289
+ 0.10986180904522613,
290
+ 0.11295881961661729,
291
+ 0.11343618844948868,
292
+ 0.10697446574000367,
293
+ 0.10960139481753141,
294
+ 0.11440075793462814,
295
+ 0.11370262390670553,
296
+ 0.11277156850433254,
297
+ 0.11105026165267129,
298
+ 0.11369509043927649,
299
+ 0.11747315071799204,
300
+ 0.11463783281013835,
301
+ 0.11898656898656898,
302
+ 0.1146747180129885,
303
+ 0.11454706403068751,
304
+ 0.11551076390959508,
305
+ 0.12212861385538518,
306
+ 0.11605906783571758,
307
+ 0.11722642283570717,
308
+ 0.11782014344387912,
309
+ 0.12010507666931394,
310
+ 0.12454607353608715,
311
+ 0.12202295138688657,
312
+ 0.11981290477332694,
313
+ 0.1229088818626042,
314
+ 0.12582702509387853,
315
+ 0.12109761060403465,
316
+ 0.1265125262739306,
317
+ 0.12501687592817606,
318
+ 0.13166644500598484,
319
+ 0.13182912154031287,
320
+ 0.13451776649746192,
321
+ 0.13028631468347782,
322
+ 0.12836718414432105,
323
+ 0.1342669409968806,
324
+ 0.13514649375600385,
325
+ 0.1313969571230982,
326
+ 0.12860272077472906,
327
+ 0.13659653987582132,
328
+ 0.13911455381321242,
329
+ 0.13618013305282312,
330
+ 0.13699927572566717,
331
+ 0.13122171945701358,
332
+ 0.13988701881078563,
333
+ 0.13799655602398908,
334
+ 0.14215716298156428,
335
+ 0.14469256653410828,
336
+ 0.14123100393123275,
337
+ 0.1505314009661836,
338
+ 0.14527046572172403,
339
+ 0.14509561998766193,
340
+ 0.1493763310009127,
341
+ 0.14152431913288058,
342
+ 0.15143084260731318,
343
+ 0.1539343470914796,
344
+ 0.14741789769258942,
345
+ 0.14392357816157397,
346
+ 0.14797207846912985,
347
+ 0.1481924962937621,
348
+ 0.15064121505821168,
349
+ 0.15475645635828703,
350
+ 0.15929958027282268,
351
+ 0.15324854332435311,
352
+ 0.15836659147434784,
353
+ 0.15832710978342046,
354
+ 0.15416367552045945,
355
+ 0.15383124434681483,
356
+ 0.15975617116301527,
357
+ 0.15405611966371874,
358
+ 0.15663511341310948,
359
+ 0.16653122037112286,
360
+ 0.161051298290057,
361
+ 0.16165680473372782,
362
+ 0.1656753939542584,
363
+ 0.16401395399542135,
364
+ 0.16477308392442408,
365
+ 0.1672160094173043,
366
+ 0.1604350019619934,
367
+ 0.1643771555503595,
368
+ 0.16152380952380951,
369
+ 0.16112639005141696,
370
+ 0.16733510211636948,
371
+ 0.16626220775377332,
372
+ 0.167010043780582,
373
+ 0.1620298121939407,
374
+ 0.16259640102827763,
375
+ 0.16263796909492273,
376
+ 0.16637839647380462,
377
+ 0.1664381325497878,
378
+ 0.17336490464610266,
379
+ 0.17695549770670632,
380
+ 0.16493125467410688,
381
+ 0.17992150382152447,
382
+ 0.16654309017281696,
383
+ 0.17014263454392906,
384
+ 0.1719965953307393,
385
+ 0.17110313235112046,
386
+ 0.17147435897435898,
387
+ 0.17298781534237173,
388
+ 0.1651188035218912,
389
+ 0.17424760601915185,
390
+ 0.17603835855283642,
391
+ 0.17752242481092806,
392
+ 0.17549946165809308,
393
+ 0.1767236434553172,
394
+ 0.17017426273458444,
395
+ 0.17265185357080698,
396
+ 0.17630997269535822,
397
+ 0.1718667988569429,
398
+ 0.1752311201824949,
399
+ 0.18004470636049583,
400
+ 0.17762634866553095,
401
+ 0.18453172205438068,
402
+ 0.17852277438843808,
403
+ 0.1755398361876396,
404
+ 0.17947662452219934,
405
+ 0.18870977061304675,
406
+ 0.18411597856917744,
407
+ 0.1742022127006459,
408
+ 0.17761444528039816,
409
+ 0.18393460103074463
410
+ ],
411
+ "grad_norms": [
412
+ 0.52734375,
413
+ 0.828125,
414
+ 0.83984375,
415
+ 0.8359375,
416
+ 0.78515625,
417
+ 0.76171875,
418
+ 0.734375,
419
+ 0.6640625,
420
+ 0.5703125,
421
+ 0.453125,
422
+ 0.3203125,
423
+ 0.2490234375,
424
+ 0.2060546875,
425
+ 0.2197265625,
426
+ 0.2119140625,
427
+ 0.2197265625,
428
+ 0.1787109375,
429
+ 0.1767578125,
430
+ 0.2060546875,
431
+ 0.318359375,
432
+ 0.1533203125,
433
+ 0.283203125,
434
+ 0.1416015625,
435
+ 0.2021484375,
436
+ 0.146484375,
437
+ 0.1962890625,
438
+ 0.1474609375,
439
+ 0.1201171875,
440
+ 0.1318359375,
441
+ 0.146484375,
442
+ 0.15234375,
443
+ 0.11181640625,
444
+ 0.1298828125,
445
+ 0.13671875,
446
+ 0.1416015625,
447
+ 0.12158203125,
448
+ 0.1064453125,
449
+ 0.1240234375,
450
+ 0.1357421875,
451
+ 0.12890625,
452
+ 0.181640625,
453
+ 0.1552734375,
454
+ 0.173828125,
455
+ 0.1416015625,
456
+ 0.228515625,
457
+ 0.171875,
458
+ 0.138671875,
459
+ 0.2578125,
460
+ 0.17578125,
461
+ 0.208984375,
462
+ 0.17578125,
463
+ 0.2099609375,
464
+ 0.146484375,
465
+ 0.162109375,
466
+ 0.1494140625,
467
+ 0.1689453125,
468
+ 0.1650390625,
469
+ 0.13671875,
470
+ 0.154296875,
471
+ 0.166015625,
472
+ 0.1611328125,
473
+ 0.12451171875,
474
+ 0.1650390625,
475
+ 0.12158203125,
476
+ 0.185546875,
477
+ 0.2431640625,
478
+ 0.2021484375,
479
+ 0.2080078125,
480
+ 0.212890625,
481
+ 0.275390625,
482
+ 0.310546875,
483
+ 0.244140625,
484
+ 0.21484375,
485
+ 0.2255859375,
486
+ 0.177734375,
487
+ 0.177734375,
488
+ 0.13671875,
489
+ 0.177734375,
490
+ 0.193359375,
491
+ 0.162109375,
492
+ 0.177734375,
493
+ 0.177734375,
494
+ 0.162109375,
495
+ 0.166015625,
496
+ 0.1650390625,
497
+ 0.1630859375,
498
+ 0.1650390625,
499
+ 0.1279296875,
500
+ 0.158203125,
501
+ 0.134765625,
502
+ 0.154296875,
503
+ 0.13671875,
504
+ 0.14453125,
505
+ 0.2099609375,
506
+ 0.33203125,
507
+ 0.291015625,
508
+ 0.2158203125,
509
+ 0.2119140625,
510
+ 0.23046875,
511
+ 0.2333984375,
512
+ 0.146484375,
513
+ 0.1806640625,
514
+ 0.1767578125,
515
+ 0.1572265625,
516
+ 0.1650390625,
517
+ 0.1943359375,
518
+ 0.228515625,
519
+ 0.1552734375,
520
+ 0.2314453125,
521
+ 0.193359375,
522
+ 0.1376953125,
523
+ 0.1953125,
524
+ 0.185546875,
525
+ 0.1572265625,
526
+ 0.18359375,
527
+ 0.205078125,
528
+ 0.158203125,
529
+ 0.166015625,
530
+ 0.1728515625,
531
+ 0.15234375,
532
+ 0.259765625,
533
+ 0.22265625,
534
+ 0.1767578125,
535
+ 0.267578125,
536
+ 0.228515625,
537
+ 0.1572265625,
538
+ 0.26171875,
539
+ 0.2041015625,
540
+ 0.2138671875,
541
+ 0.1865234375,
542
+ 0.1650390625,
543
+ 0.1591796875,
544
+ 0.162109375,
545
+ 0.1533203125
546
+ ]
547
+ },
548
+ "eval": {
549
+ "effective_batch_nums": [
550
+ 133
551
+ ],
552
+ "losses": [
553
+ 7.494485294117647
554
+ ],
555
+ "perplexities": [
556
+ 1798.0990349241254
557
+ ],
558
+ "accuracies": [
559
+ 0.18015617980556828
560
+ ]
561
+ }
562
+ }
control_123/epoch0/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8afff860cd411d6902a17758e90840e372cf0bcf90ddf8711f7068bba7ed474
3
+ size 32139875
control_123/epoch0/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d3610e8540b055c0ae420da70a1d60d93246707936741730ba16fe19ae5816
3
+ size 64326347
control_123/epoch0/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d6a15ffc4de8d5feadf3e415a5d7453b357113b0f7dc0d355a450230cce1e4
3
+ size 1465
control_123/epoch0/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
control_123/epoch0/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
+ }
control_123/epoch0/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
control_123/epoch0/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
+ }
control_123/epoch0/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff