smithblack-0 commited on
Commit
d0dd560
·
verified ·
1 Parent(s): 8559676

Upload folder using huggingface_hub

Browse files
none_42/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
+ }
none_42/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
+ 10.625,
142
+ 9.6875,
143
+ 9.0625,
144
+ 8.75,
145
+ 8.75,
146
+ 8.625,
147
+ 8.625,
148
+ 8.625,
149
+ 8.5,
150
+ 8.4375,
151
+ 8.4375,
152
+ 8.375,
153
+ 8.375,
154
+ 8.3125,
155
+ 8.3125,
156
+ 8.3125,
157
+ 8.3125,
158
+ 8.25,
159
+ 8.25,
160
+ 8.25,
161
+ 8.1875,
162
+ 8.1875,
163
+ 8.125,
164
+ 8.125,
165
+ 8.0625,
166
+ 8.0625,
167
+ 8.125,
168
+ 8.125,
169
+ 8.0625,
170
+ 8.125,
171
+ 8.125,
172
+ 8.0,
173
+ 8.0,
174
+ 8.0625,
175
+ 8.0,
176
+ 8.0625,
177
+ 8.0625,
178
+ 8.0,
179
+ 8.0,
180
+ 8.0625,
181
+ 8.0,
182
+ 7.9375,
183
+ 7.96875,
184
+ 7.96875,
185
+ 7.90625,
186
+ 7.90625,
187
+ 7.90625,
188
+ 7.84375,
189
+ 7.84375,
190
+ 7.9375,
191
+ 7.84375,
192
+ 7.84375,
193
+ 7.78125,
194
+ 7.8125,
195
+ 7.75,
196
+ 7.78125,
197
+ 7.78125,
198
+ 7.75,
199
+ 7.6875,
200
+ 7.75,
201
+ 7.75,
202
+ 7.6875,
203
+ 7.78125,
204
+ 7.71875,
205
+ 7.65625,
206
+ 7.71875,
207
+ 7.71875,
208
+ 7.71875,
209
+ 7.65625,
210
+ 7.625,
211
+ 7.65625,
212
+ 7.59375,
213
+ 7.625,
214
+ 7.65625,
215
+ 7.59375,
216
+ 7.59375,
217
+ 7.59375,
218
+ 7.5,
219
+ 7.5,
220
+ 7.53125,
221
+ 7.5,
222
+ 7.5,
223
+ 7.4375,
224
+ 7.53125,
225
+ 7.5,
226
+ 7.5,
227
+ 7.5,
228
+ 7.5,
229
+ 7.46875,
230
+ 7.4375,
231
+ 7.40625,
232
+ 7.34375,
233
+ 7.3125,
234
+ 7.375,
235
+ 7.34375,
236
+ 7.375,
237
+ 7.375,
238
+ 7.34375,
239
+ 7.28125,
240
+ 7.375,
241
+ 7.3125,
242
+ 7.375,
243
+ 7.34375,
244
+ 7.25,
245
+ 7.34375,
246
+ 7.28125,
247
+ 7.34375,
248
+ 7.25,
249
+ 7.25,
250
+ 7.21875,
251
+ 7.3125,
252
+ 7.21875,
253
+ 7.3125,
254
+ 7.3125,
255
+ 7.25,
256
+ 7.25,
257
+ 7.25,
258
+ 7.1875,
259
+ 7.21875,
260
+ 7.21875,
261
+ 7.15625,
262
+ 7.125,
263
+ 7.21875,
264
+ 7.1875,
265
+ 7.125,
266
+ 7.1875,
267
+ 7.1875,
268
+ 7.15625,
269
+ 7.15625,
270
+ 7.21875,
271
+ 7.21875,
272
+ 7.1875,
273
+ 7.15625
274
+ ],
275
+ "accuracies": [
276
+ 0.0,
277
+ 0.013893234870767882,
278
+ 0.034600850259801606,
279
+ 0.021899562008759824,
280
+ 0.05627898113447247,
281
+ 0.04499423150878092,
282
+ 0.04868076407078515,
283
+ 0.05003629865415759,
284
+ 0.05263839430236322,
285
+ 0.07201225740551584,
286
+ 0.0785296574770259,
287
+ 0.07863527487293334,
288
+ 0.07291225095379399,
289
+ 0.07584987227353114,
290
+ 0.0964660936007641,
291
+ 0.09658085507163651,
292
+ 0.10326259106746911,
293
+ 0.10117214930049155,
294
+ 0.10166393545947308,
295
+ 0.10212660731948565,
296
+ 0.11444425177735391,
297
+ 0.10681192086150763,
298
+ 0.11210652267288458,
299
+ 0.11514491438252557,
300
+ 0.10862309606165423,
301
+ 0.11300166450896985,
302
+ 0.11462261327587239,
303
+ 0.1122224206703578,
304
+ 0.1179287447324735,
305
+ 0.1090515028802829,
306
+ 0.11344896218367927,
307
+ 0.10895581645964494,
308
+ 0.11973335059219468,
309
+ 0.11655180752025147,
310
+ 0.11625821876867902,
311
+ 0.1225903993952375,
312
+ 0.11949725257373839,
313
+ 0.11798026556218784,
314
+ 0.11953387087281502,
315
+ 0.12260697353417752,
316
+ 0.11811977804706933,
317
+ 0.11657602270040199,
318
+ 0.1227740229209521,
319
+ 0.11927841998859572,
320
+ 0.11917666051660517,
321
+ 0.11928671413791005,
322
+ 0.1282300480219529,
323
+ 0.126502439604903,
324
+ 0.12701599411095496,
325
+ 0.12755043227665705,
326
+ 0.11937626335547213,
327
+ 0.12975908126326302,
328
+ 0.12300217363508503,
329
+ 0.1319695646750655,
330
+ 0.13368808303770857,
331
+ 0.13623444704099033,
332
+ 0.13407532030542255,
333
+ 0.1301199725173088,
334
+ 0.1382593206805479,
335
+ 0.13503998090464256,
336
+ 0.13654933124405394,
337
+ 0.14083744435086032,
338
+ 0.14218095758237756,
339
+ 0.14351071514567781,
340
+ 0.14097549752674565,
341
+ 0.14829356689821807,
342
+ 0.15083655083655084,
343
+ 0.14851733433640524,
344
+ 0.14477692169862033,
345
+ 0.15269961036551424,
346
+ 0.15426677713338857,
347
+ 0.15616866215512754,
348
+ 0.1581180811808118,
349
+ 0.1605231866825208,
350
+ 0.15475413725606502,
351
+ 0.15668286755771568,
352
+ 0.1596916928347131,
353
+ 0.1663922859830668,
354
+ 0.16981013847985463,
355
+ 0.17054782027117407,
356
+ 0.16489662540061584,
357
+ 0.17174532391923697,
358
+ 0.16721748709920567,
359
+ 0.17773711497407746,
360
+ 0.17512124786996985,
361
+ 0.16882659942532105,
362
+ 0.17579130018548436,
363
+ 0.17506957478480356,
364
+ 0.16662394257882593,
365
+ 0.1685617964687732,
366
+ 0.17992177314211213,
367
+ 0.1702127659574468,
368
+ 0.18701729750430843,
369
+ 0.18959837830989484,
370
+ 0.18099334236728923,
371
+ 0.18308941162528886,
372
+ 0.18308771095792725,
373
+ 0.18160377358490565,
374
+ 0.18365271384220105,
375
+ 0.18985886710517913,
376
+ 0.18531730050054657,
377
+ 0.18433125514645335,
378
+ 0.17756954952857643,
379
+ 0.1888606997462977,
380
+ 0.1959358566513017,
381
+ 0.18359821996185632,
382
+ 0.18885818024169512,
383
+ 0.19125395152792413,
384
+ 0.19221813725490197,
385
+ 0.19393856092364786,
386
+ 0.1934380958642909,
387
+ 0.18506170673217523,
388
+ 0.19473011622953812,
389
+ 0.1892736592074009,
390
+ 0.19546211490424645,
391
+ 0.1984741853450825,
392
+ 0.19192756487916854,
393
+ 0.1865845152290165,
394
+ 0.20217556582256271,
395
+ 0.19367742652369577,
396
+ 0.19814614180811363,
397
+ 0.20243362831858408,
398
+ 0.20050967218811538,
399
+ 0.19522998296422486,
400
+ 0.19954891457569776,
401
+ 0.20521703688608112,
402
+ 0.19883075469469705,
403
+ 0.19755481102686182,
404
+ 0.20277777777777778,
405
+ 0.1964181542410454,
406
+ 0.1959100457185222,
407
+ 0.191645085012949,
408
+ 0.19516044187269857,
409
+ 0.2030889954536962
410
+ ],
411
+ "grad_norms": [
412
+ 0.2119140625,
413
+ 0.310546875,
414
+ 0.80859375,
415
+ 0.76171875,
416
+ 0.56640625,
417
+ 0.37109375,
418
+ 0.4921875,
419
+ 0.2353515625,
420
+ 0.380859375,
421
+ 0.2890625,
422
+ 0.25,
423
+ 0.2216796875,
424
+ 0.251953125,
425
+ 0.2431640625,
426
+ 0.2060546875,
427
+ 0.1796875,
428
+ 0.2119140625,
429
+ 0.154296875,
430
+ 0.20703125,
431
+ 0.23046875,
432
+ 0.2119140625,
433
+ 0.240234375,
434
+ 0.1572265625,
435
+ 0.1943359375,
436
+ 0.19921875,
437
+ 0.169921875,
438
+ 0.1533203125,
439
+ 0.30078125,
440
+ 0.41015625,
441
+ 0.216796875,
442
+ 0.16796875,
443
+ 0.1552734375,
444
+ 0.1328125,
445
+ 0.109375,
446
+ 0.130859375,
447
+ 0.11669921875,
448
+ 0.123046875,
449
+ 0.1259765625,
450
+ 0.1259765625,
451
+ 0.177734375,
452
+ 0.1259765625,
453
+ 0.11962890625,
454
+ 0.11328125,
455
+ 0.1787109375,
456
+ 0.404296875,
457
+ 0.2119140625,
458
+ 0.2392578125,
459
+ 0.2265625,
460
+ 0.11328125,
461
+ 0.275390625,
462
+ 0.31640625,
463
+ 0.1376953125,
464
+ 0.2255859375,
465
+ 0.171875,
466
+ 0.171875,
467
+ 0.1474609375,
468
+ 0.173828125,
469
+ 0.1787109375,
470
+ 0.1318359375,
471
+ 0.130859375,
472
+ 0.150390625,
473
+ 0.1357421875,
474
+ 0.1171875,
475
+ 0.1259765625,
476
+ 0.1376953125,
477
+ 0.10302734375,
478
+ 0.1220703125,
479
+ 0.1396484375,
480
+ 0.1103515625,
481
+ 0.11279296875,
482
+ 0.1357421875,
483
+ 0.115234375,
484
+ 0.1298828125,
485
+ 0.1416015625,
486
+ 0.1513671875,
487
+ 0.173828125,
488
+ 0.1708984375,
489
+ 0.138671875,
490
+ 0.150390625,
491
+ 0.1279296875,
492
+ 0.1015625,
493
+ 0.109375,
494
+ 0.1357421875,
495
+ 0.1484375,
496
+ 0.10693359375,
497
+ 0.1357421875,
498
+ 0.1298828125,
499
+ 0.11083984375,
500
+ 0.1728515625,
501
+ 0.1591796875,
502
+ 0.11572265625,
503
+ 0.130859375,
504
+ 0.1162109375,
505
+ 0.1181640625,
506
+ 0.12353515625,
507
+ 0.1220703125,
508
+ 0.115234375,
509
+ 0.11279296875,
510
+ 0.10986328125,
511
+ 0.0986328125,
512
+ 0.11474609375,
513
+ 0.12158203125,
514
+ 0.10302734375,
515
+ 0.1240234375,
516
+ 0.099609375,
517
+ 0.1279296875,
518
+ 0.1083984375,
519
+ 0.095703125,
520
+ 0.11083984375,
521
+ 0.103515625,
522
+ 0.1318359375,
523
+ 0.125,
524
+ 0.09033203125,
525
+ 0.1328125,
526
+ 0.126953125,
527
+ 0.10546875,
528
+ 0.10546875,
529
+ 0.1015625,
530
+ 0.10595703125,
531
+ 0.1103515625,
532
+ 0.0966796875,
533
+ 0.1171875,
534
+ 0.1513671875,
535
+ 0.115234375,
536
+ 0.15625,
537
+ 0.109375,
538
+ 0.1572265625,
539
+ 0.1044921875,
540
+ 0.11669921875,
541
+ 0.11669921875,
542
+ 0.10791015625,
543
+ 0.107421875,
544
+ 0.1572265625,
545
+ 0.13671875
546
+ ]
547
+ },
548
+ "eval": {
549
+ "effective_batch_nums": [
550
+ 134
551
+ ],
552
+ "losses": [
553
+ 7.369485294117647
554
+ ],
555
+ "perplexities": [
556
+ 1586.8168288608908
557
+ ],
558
+ "accuracies": [
559
+ 0.18996262633970487
560
+ ]
561
+ }
562
+ }
none_42/epoch0/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25c26778a2c94865e8f6e70b4c7e2de17634a1b431179fe5ca028d2133f471d7
3
+ size 29774371
none_42/epoch0/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212cf718427ba4d195d67dbd0486929eef52309f1ae06fe93c4edbd3f127e013
3
+ size 59595275
none_42/epoch0/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d11dc24db33095efe5867c3c3a75ef964eabbf277c20502b73b9b80f5184e6
3
+ size 1465
none_42/epoch0/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
none_42/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
+ }
none_42/epoch0/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
none_42/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
+ }
none_42/epoch0/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff