smithblack-0 commited on
Commit
5ecb0fe
·
verified ·
1 Parent(s): a59b061

Upload folder using huggingface_hub

Browse files
control_789/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_789/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
+ 11.0,
141
+ 10.6875,
142
+ 10.0,
143
+ 9.5,
144
+ 9.3125,
145
+ 9.0,
146
+ 8.75,
147
+ 8.5625,
148
+ 8.625,
149
+ 8.5,
150
+ 8.4375,
151
+ 8.4375,
152
+ 8.4375,
153
+ 8.375,
154
+ 8.3125,
155
+ 8.3125,
156
+ 8.3125,
157
+ 8.25,
158
+ 8.25,
159
+ 8.25,
160
+ 8.1875,
161
+ 8.1875,
162
+ 8.1875,
163
+ 8.25,
164
+ 8.1875,
165
+ 8.0625,
166
+ 8.1875,
167
+ 8.0625,
168
+ 8.125,
169
+ 8.125,
170
+ 8.0625,
171
+ 8.125,
172
+ 8.0625,
173
+ 8.0625,
174
+ 8.0,
175
+ 8.0,
176
+ 8.0625,
177
+ 8.125,
178
+ 8.0,
179
+ 7.9375,
180
+ 7.9375,
181
+ 7.96875,
182
+ 7.9375,
183
+ 8.0,
184
+ 7.9375,
185
+ 7.9375,
186
+ 7.90625,
187
+ 7.90625,
188
+ 7.9375,
189
+ 7.9375,
190
+ 7.96875,
191
+ 7.84375,
192
+ 7.90625,
193
+ 7.90625,
194
+ 7.9375,
195
+ 7.84375,
196
+ 7.84375,
197
+ 7.875,
198
+ 7.90625,
199
+ 7.84375,
200
+ 7.84375,
201
+ 7.8125,
202
+ 7.78125,
203
+ 7.90625,
204
+ 7.8125,
205
+ 7.8125,
206
+ 7.78125,
207
+ 7.75,
208
+ 7.84375,
209
+ 7.71875,
210
+ 7.75,
211
+ 7.78125,
212
+ 7.78125,
213
+ 7.71875,
214
+ 7.71875,
215
+ 7.6875,
216
+ 7.65625,
217
+ 7.71875,
218
+ 7.6875,
219
+ 7.6875,
220
+ 7.6875,
221
+ 7.65625,
222
+ 7.71875,
223
+ 7.625,
224
+ 7.6875,
225
+ 7.625,
226
+ 7.65625,
227
+ 7.5625,
228
+ 7.6875,
229
+ 7.625,
230
+ 7.65625,
231
+ 7.5625,
232
+ 7.59375,
233
+ 7.53125,
234
+ 7.625,
235
+ 7.59375,
236
+ 7.625,
237
+ 7.59375,
238
+ 7.53125,
239
+ 7.59375,
240
+ 7.53125,
241
+ 7.625,
242
+ 7.53125,
243
+ 7.59375,
244
+ 7.5,
245
+ 7.53125,
246
+ 7.46875,
247
+ 7.53125,
248
+ 7.5,
249
+ 7.4375,
250
+ 7.4375,
251
+ 7.46875,
252
+ 7.46875,
253
+ 7.5,
254
+ 7.46875,
255
+ 7.40625,
256
+ 7.4375,
257
+ 7.4375,
258
+ 7.53125,
259
+ 7.34375,
260
+ 7.4375,
261
+ 7.34375,
262
+ 7.40625,
263
+ 7.4375,
264
+ 7.34375,
265
+ 7.40625,
266
+ 7.40625,
267
+ 7.375,
268
+ 7.34375,
269
+ 7.375,
270
+ 7.46875,
271
+ 7.375,
272
+ 7.34375,
273
+ 7.40625
274
+ ],
275
+ "accuracies": [
276
+ 0.0,
277
+ 0.047754370791375796,
278
+ 0.04827222368768135,
279
+ 0.052247587667686515,
280
+ 0.044954881050041015,
281
+ 0.04950160500084474,
282
+ 0.04848041902673732,
283
+ 0.053017360154312486,
284
+ 0.04601882325769386,
285
+ 0.07889827718643695,
286
+ 0.0785199738048461,
287
+ 0.08915211970074813,
288
+ 0.09380530973451327,
289
+ 0.09380466911986488,
290
+ 0.09717737112785552,
291
+ 0.09915405420958738,
292
+ 0.10186152239356147,
293
+ 0.10477573996731433,
294
+ 0.10733733789928704,
295
+ 0.10465046142710659,
296
+ 0.11185308848080133,
297
+ 0.11115820064176303,
298
+ 0.1166936790923825,
299
+ 0.10680976108342916,
300
+ 0.10416065554850251,
301
+ 0.11886255924170616,
302
+ 0.11611078218538254,
303
+ 0.11992101011309915,
304
+ 0.11363785307031915,
305
+ 0.11122053706256976,
306
+ 0.12197272513519869,
307
+ 0.11195913091647688,
308
+ 0.11586263768628144,
309
+ 0.12090596936080296,
310
+ 0.119002487856889,
311
+ 0.11845409444478472,
312
+ 0.11706660686252524,
313
+ 0.11154500220444669,
314
+ 0.11909033042069325,
315
+ 0.12265520997216507,
316
+ 0.1261556129773184,
317
+ 0.12220452373367315,
318
+ 0.12326368623788958,
319
+ 0.12149251937751607,
320
+ 0.1297029702970297,
321
+ 0.12311701519099981,
322
+ 0.12549119026492583,
323
+ 0.12604314767880323,
324
+ 0.12320479129743934,
325
+ 0.12294208219827076,
326
+ 0.1269241773962804,
327
+ 0.13088912504427913,
328
+ 0.1321437331371106,
329
+ 0.12896245174874255,
330
+ 0.12449728973596783,
331
+ 0.12745439758336238,
332
+ 0.1375855034201368,
333
+ 0.13408412145345944,
334
+ 0.135811251407908,
335
+ 0.1346693152605749,
336
+ 0.139407598197038,
337
+ 0.13733350575455838,
338
+ 0.14441535776614312,
339
+ 0.1361381700830694,
340
+ 0.14538840647735274,
341
+ 0.14005851672815164,
342
+ 0.14679135762657208,
343
+ 0.14822771213748656,
344
+ 0.1450199203187251,
345
+ 0.1445857721746961,
346
+ 0.14450900639163278,
347
+ 0.14447810520517765,
348
+ 0.14562054208273895,
349
+ 0.1477556109725686,
350
+ 0.15242494226327943,
351
+ 0.14786107330927165,
352
+ 0.15137277101613358,
353
+ 0.15002754483687336,
354
+ 0.15657208296220892,
355
+ 0.1545996341535375,
356
+ 0.15618324234512224,
357
+ 0.15886031146767343,
358
+ 0.15094228504122498,
359
+ 0.1607208758764916,
360
+ 0.15870435217608805,
361
+ 0.16111559294687103,
362
+ 0.16194450975781802,
363
+ 0.1658436709623028,
364
+ 0.1526638223389126,
365
+ 0.16064004031750032,
366
+ 0.1610367113065494,
367
+ 0.16379859783301465,
368
+ 0.15792222867092282,
369
+ 0.16529019119809935,
370
+ 0.16160501713024794,
371
+ 0.16694004009476945,
372
+ 0.1644740943949124,
373
+ 0.16314962397575486,
374
+ 0.16270566727605118,
375
+ 0.1664274642631609,
376
+ 0.16840814896970405,
377
+ 0.17040687221149364,
378
+ 0.16965170841319147,
379
+ 0.16470787659622557,
380
+ 0.16921461080639513,
381
+ 0.16819740386970364,
382
+ 0.16674849637903522,
383
+ 0.16627575277337558,
384
+ 0.17100030590394616,
385
+ 0.1756427439990252,
386
+ 0.1709854359750331,
387
+ 0.17738872403560832,
388
+ 0.17801701064652353,
389
+ 0.1700870646766169,
390
+ 0.17699556886974974,
391
+ 0.1810459091456802,
392
+ 0.18108831400535236,
393
+ 0.1803352458094274,
394
+ 0.17006802721088435,
395
+ 0.17763779527559054,
396
+ 0.18126549403848424,
397
+ 0.1819463169506067,
398
+ 0.17534679970795813,
399
+ 0.17522585339234828,
400
+ 0.18627974600913894,
401
+ 0.18752561825385983,
402
+ 0.1833092694195784,
403
+ 0.18228694469628287,
404
+ 0.1884603517432891,
405
+ 0.18321006876865187,
406
+ 0.17237903225806453,
407
+ 0.18021457250049364,
408
+ 0.18809804692620266,
409
+ 0.17854763491005995
410
+ ],
411
+ "grad_norms": [
412
+ 0.482421875,
413
+ 1.0546875,
414
+ 0.828125,
415
+ 0.85546875,
416
+ 0.78515625,
417
+ 0.75,
418
+ 0.63671875,
419
+ 0.4609375,
420
+ 0.328125,
421
+ 0.255859375,
422
+ 0.2578125,
423
+ 0.2041015625,
424
+ 0.298828125,
425
+ 0.26953125,
426
+ 0.3359375,
427
+ 0.1689453125,
428
+ 0.259765625,
429
+ 0.1728515625,
430
+ 0.173828125,
431
+ 0.2021484375,
432
+ 0.1904296875,
433
+ 0.1552734375,
434
+ 0.1474609375,
435
+ 0.21875,
436
+ 0.1181640625,
437
+ 0.134765625,
438
+ 0.13671875,
439
+ 0.1552734375,
440
+ 0.2109375,
441
+ 0.11865234375,
442
+ 0.189453125,
443
+ 0.1728515625,
444
+ 0.1171875,
445
+ 0.185546875,
446
+ 0.12451171875,
447
+ 0.154296875,
448
+ 0.140625,
449
+ 0.11279296875,
450
+ 0.11767578125,
451
+ 0.115234375,
452
+ 0.140625,
453
+ 0.1357421875,
454
+ 0.11669921875,
455
+ 0.1162109375,
456
+ 0.1357421875,
457
+ 0.1337890625,
458
+ 0.134765625,
459
+ 0.138671875,
460
+ 0.1328125,
461
+ 0.1591796875,
462
+ 0.1318359375,
463
+ 0.193359375,
464
+ 0.1396484375,
465
+ 0.134765625,
466
+ 0.1416015625,
467
+ 0.1494140625,
468
+ 0.138671875,
469
+ 0.1357421875,
470
+ 0.11865234375,
471
+ 0.109375,
472
+ 0.1318359375,
473
+ 0.15234375,
474
+ 0.2236328125,
475
+ 0.453125,
476
+ 0.40625,
477
+ 0.22265625,
478
+ 0.208984375,
479
+ 0.1689453125,
480
+ 0.19140625,
481
+ 0.203125,
482
+ 0.1484375,
483
+ 0.20703125,
484
+ 0.1533203125,
485
+ 0.1796875,
486
+ 0.1337890625,
487
+ 0.1787109375,
488
+ 0.134765625,
489
+ 0.1484375,
490
+ 0.1650390625,
491
+ 0.140625,
492
+ 0.130859375,
493
+ 0.1181640625,
494
+ 0.140625,
495
+ 0.1279296875,
496
+ 0.146484375,
497
+ 0.1318359375,
498
+ 0.1396484375,
499
+ 0.14453125,
500
+ 0.1220703125,
501
+ 0.16796875,
502
+ 0.1494140625,
503
+ 0.1845703125,
504
+ 0.1552734375,
505
+ 0.1669921875,
506
+ 0.1376953125,
507
+ 0.15625,
508
+ 0.171875,
509
+ 0.173828125,
510
+ 0.1796875,
511
+ 0.20703125,
512
+ 0.181640625,
513
+ 0.1611328125,
514
+ 0.2119140625,
515
+ 0.263671875,
516
+ 0.1806640625,
517
+ 0.1513671875,
518
+ 0.1552734375,
519
+ 0.130859375,
520
+ 0.1259765625,
521
+ 0.146484375,
522
+ 0.1455078125,
523
+ 0.1376953125,
524
+ 0.1630859375,
525
+ 0.126953125,
526
+ 0.14453125,
527
+ 0.1279296875,
528
+ 0.150390625,
529
+ 0.177734375,
530
+ 0.1376953125,
531
+ 0.1591796875,
532
+ 0.1845703125,
533
+ 0.208984375,
534
+ 0.1943359375,
535
+ 0.134765625,
536
+ 0.181640625,
537
+ 0.1572265625,
538
+ 0.140625,
539
+ 0.1533203125,
540
+ 0.171875,
541
+ 0.13671875,
542
+ 0.1552734375,
543
+ 0.1748046875,
544
+ 0.1396484375,
545
+ 0.1591796875
546
+ ]
547
+ },
548
+ "eval": {
549
+ "effective_batch_nums": [
550
+ 134
551
+ ],
552
+ "losses": [
553
+ 7.481617647058823
554
+ ],
555
+ "perplexities": [
556
+ 1775.1099560456069
557
+ ],
558
+ "accuracies": [
559
+ 0.18078868032407283
560
+ ]
561
+ }
562
+ }
control_789/epoch0/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d051f5cc7db9ef1d3f1566ef5d4567f9d8366379e73e6856beb4bb406c15db0
3
+ size 29774371
control_789/epoch0/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9b1fb74a23801a88910e52b498c9c446e8350768d60715bc2e26f6e326f746
3
+ size 59595275
control_789/epoch0/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc73f144999e1cacf5b3ee8b4bdf7d0a6a3048ea650a22f179f2aaf055734d57
3
+ size 1465
control_789/epoch0/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
control_789/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_789/epoch0/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
control_789/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_789/epoch0/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff