Hugging Face's logo

smithblack-0
/
stage-one-v3

Model card Files
xet
 Community
smithblack-0 commited on
Commit
c1b1334
·
verified ·
1 Parent(s): 17dea82

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. control_42/epoch0/metadata.json +6 -0
  2. control_42/epoch0/metrics.json +430 -0
  3. control_42/epoch0/model.pt +3 -0
  4. control_42/epoch0/optimizer.pt +3 -0
  5. control_42/epoch0/scheduler.pt +3 -0
  6. control_42/epoch0/tokenizer/merges.txt +0 -0
  7. control_42/epoch0/tokenizer/special_tokens_map.json +6 -0
  8. control_42/epoch0/tokenizer/tokenizer.json +0 -0
  9. control_42/epoch0/tokenizer/tokenizer_config.json +21 -0
  10. control_42/epoch0/tokenizer/vocab.json +0 -0
control_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
+ }
control_42/epoch0/metrics.json ADDED
@@ -0,0 +1,430 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ 105.0,
141
+ 45.5,
142
+ 41.0,
143
+ 37.25,
144
+ 31.0,
145
+ 25.75,
146
+ 21.0,
147
+ 17.125,
148
+ 14.75,
149
+ 13.1875,
150
+ 12.0,
151
+ 11.125,
152
+ 10.625,
153
+ 10.1875,
154
+ 9.9375,
155
+ 9.75,
156
+ 9.625,
157
+ 9.5625,
158
+ 9.375,
159
+ 9.3125,
160
+ 9.125,
161
+ 9.0,
162
+ 9.0,
163
+ 9.0,
164
+ 8.875,
165
+ 8.8125,
166
+ 8.75,
167
+ 8.75,
168
+ 8.6875,
169
+ 8.75,
170
+ 8.625,
171
+ 8.625,
172
+ 8.625,
173
+ 8.625,
174
+ 8.5625,
175
+ 8.5625,
176
+ 8.5625,
177
+ 8.5625,
178
+ 8.5625,
179
+ 8.5,
180
+ 8.5,
181
+ 8.5,
182
+ 8.5,
183
+ 8.4375,
184
+ 8.5,
185
+ 8.5,
186
+ 8.5,
187
+ 8.5,
188
+ 8.5,
189
+ 8.5625,
190
+ 8.5,
191
+ 8.5,
192
+ 8.5,
193
+ 8.4375,
194
+ 8.4375,
195
+ 8.5,
196
+ 8.5,
197
+ 8.5,
198
+ 8.4375,
199
+ 8.4375,
200
+ 8.4375,
201
+ 8.4375,
202
+ 8.5,
203
+ 8.4375,
204
+ 8.4375,
205
+ 8.4375,
206
+ 8.4375,
207
+ 8.4375,
208
+ 8.4375,
209
+ 8.5,
210
+ 8.4375,
211
+ 8.4375,
212
+ 8.4375,
213
+ 8.4375,
214
+ 8.5,
215
+ 8.4375,
216
+ 8.4375,
217
+ 8.4375,
218
+ 8.4375,
219
+ 8.4375,
220
+ 8.4375,
221
+ 8.5,
222
+ 8.4375,
223
+ 8.4375,
224
+ 8.4375,
225
+ 8.4375,
226
+ 8.4375,
227
+ 8.4375,
228
+ 8.4375,
229
+ 8.4375,
230
+ 8.5,
231
+ 8.4375,
232
+ 8.4375,
233
+ 8.4375,
234
+ 8.4375,
235
+ 8.4375,
236
+ 8.4375,
237
+ 8.4375,
238
+ 8.4375,
239
+ 8.4375,
240
+ 8.375,
241
+ 8.4375,
242
+ 8.5,
243
+ 8.4375,
244
+ 8.4375,
245
+ 8.4375,
246
+ 8.4375,
247
+ 8.4375,
248
+ 8.4375,
249
+ 8.4375,
250
+ 8.4375,
251
+ 8.4375,
252
+ 8.4375,
253
+ 8.4375,
254
+ 8.4375,
255
+ 8.4375,
256
+ 8.4375,
257
+ 8.4375,
258
+ 8.4375,
259
+ 8.4375,
260
+ 8.4375,
261
+ 8.4375,
262
+ 8.4375,
263
+ 8.5,
264
+ 8.4375,
265
+ 8.4375,
266
+ 8.4375,
267
+ 8.4375,
268
+ 8.4375,
269
+ 8.4375,
270
+ 8.4375,
271
+ 8.4375,
272
+ 8.4375,
273
+ 8.4375
274
+ ],
275
+ "grad_norms": [
276
+ 76.5,
277
+ 19.375,
278
+ 15.875,
279
+ 11.125,
280
+ 6.84375,
281
+ 5.71875,
282
+ 3.9375,
283
+ 2.796875,
284
+ 2.515625,
285
+ 3.671875,
286
+ 3.578125,
287
+ 1.3671875,
288
+ 1.40625,
289
+ 1.390625,
290
+ 1.375,
291
+ 1.265625,
292
+ 1.2109375,
293
+ 1.078125,
294
+ 1.0625,
295
+ 1.109375,
296
+ 1.2109375,
297
+ 1.25,
298
+ 1.2109375,
299
+ 1.234375,
300
+ 1.296875,
301
+ 1.1015625,
302
+ 0.64453125,
303
+ 0.447265625,
304
+ 0.58203125,
305
+ 0.76171875,
306
+ 0.71875,
307
+ 0.625,
308
+ 0.4921875,
309
+ 0.375,
310
+ 0.396484375,
311
+ 0.5078125,
312
+ 0.515625,
313
+ 0.435546875,
314
+ 0.37890625,
315
+ 0.330078125,
316
+ 0.380859375,
317
+ 0.3515625,
318
+ 0.3515625,
319
+ 0.333984375,
320
+ 0.259765625,
321
+ 0.234375,
322
+ 0.26171875,
323
+ 0.26953125,
324
+ 0.291015625,
325
+ 0.263671875,
326
+ 0.2265625,
327
+ 0.1650390625,
328
+ 0.2001953125,
329
+ 0.26171875,
330
+ 0.32421875,
331
+ 0.267578125,
332
+ 0.2265625,
333
+ 0.1513671875,
334
+ 0.1611328125,
335
+ 0.19921875,
336
+ 0.26171875,
337
+ 0.267578125,
338
+ 0.2431640625,
339
+ 0.12353515625,
340
+ 0.14453125,
341
+ 0.255859375,
342
+ 0.2119140625,
343
+ 0.1689453125,
344
+ 0.189453125,
345
+ 0.1806640625,
346
+ 0.142578125,
347
+ 0.189453125,
348
+ 0.189453125,
349
+ 0.15625,
350
+ 0.228515625,
351
+ 0.1513671875,
352
+ 0.171875,
353
+ 0.1826171875,
354
+ 0.1669921875,
355
+ 0.1611328125,
356
+ 0.115234375,
357
+ 0.1337890625,
358
+ 0.142578125,
359
+ 0.158203125,
360
+ 0.15234375,
361
+ 0.158203125,
362
+ 0.1611328125,
363
+ 0.17578125,
364
+ 0.1474609375,
365
+ 0.18359375,
366
+ 0.1962890625,
367
+ 0.1787109375,
368
+ 0.1796875,
369
+ 0.197265625,
370
+ 0.1669921875,
371
+ 0.1708984375,
372
+ 0.181640625,
373
+ 0.14453125,
374
+ 0.1708984375,
375
+ 0.1748046875,
376
+ 0.1474609375,
377
+ 0.1953125,
378
+ 0.1953125,
379
+ 0.1318359375,
380
+ 0.11474609375,
381
+ 0.150390625,
382
+ 0.1865234375,
383
+ 0.1826171875,
384
+ 0.1943359375,
385
+ 0.1767578125,
386
+ 0.1865234375,
387
+ 0.130859375,
388
+ 0.1796875,
389
+ 0.1748046875,
390
+ 0.169921875,
391
+ 0.1279296875,
392
+ 0.1455078125,
393
+ 0.1474609375,
394
+ 0.2041015625,
395
+ 0.2255859375,
396
+ 0.146484375,
397
+ 0.16015625,
398
+ 0.185546875,
399
+ 0.1884765625,
400
+ 0.310546875,
401
+ 0.22265625,
402
+ 0.1669921875,
403
+ 0.23046875,
404
+ 0.2490234375,
405
+ 0.1923828125,
406
+ 0.1669921875,
407
+ 0.26953125,
408
+ 0.2734375,
409
+ 0.189453125
410
+ ]
411
+ },
412
+ "eval": {
413
+ "effective_batch_nums": [
414
+ 50,
415
+ 100
416
+ ],
417
+ "losses": [
418
+ 8.511029411764707,
419
+ 8.485294117647058
420
+ ],
421
+ "perplexities": [
422
+ 4990.117647058823,
423
+ 4865.882352941177
424
+ ],
425
+ "accuracies": [
426
+ 0.05091408201002726,
427
+ 0.05091408201002726
428
+ ]
429
+ }
430
+ }
control_42/epoch0/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4b6db86f5bc9ec72ff99ac986c0e7800228f29f31872f26d36e1858e4e90ae
3
+ size 23544999
control_42/epoch0/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15540757a54c81cc7f9c916589aab7840222f5b3346d9f709ffb607683cb4440
3
+ size 47166496
control_42/epoch0/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc71a72fd61c823a6961ace46a60f18ba9677a91e06c2f41120ca2bb0df87db3
3
+ size 1465
control_42/epoch0/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
control_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
+ }
control_42/epoch0/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
control_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
+ }
control_42/epoch0/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff