aixk commited on
Commit
e606b41
·
verified ·
1 Parent(s): afbabef

Upload folder using huggingface_hub

Browse files
checkpoint-700/config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FastHyperNet125mForCausalLM"
4
+ ],
5
+ "dtype": "float32",
6
+ "hidden_size": 768,
7
+ "hyperbolic_dim": 16,
8
+ "initializer_range": 0.02,
9
+ "intermediate_size": 2048,
10
+ "max_position_embeddings": 512,
11
+ "model_type": "fasthypernet_125m_16k",
12
+ "num_attention_heads": 12,
13
+ "num_hidden_layers": 16,
14
+ "transformers_version": "5.13.1",
15
+ "use_cache": false,
16
+ "vocab_size": 16384
17
+ }
checkpoint-700/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.13.1"
6
+ }
checkpoint-700/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-700/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ae3660508721b1dba20000d166a08dcff77fc62590bb45502713df4b9861eb
3
+ size 543870712
checkpoint-700/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b514fef4b7e8b14bf3b823865e85c4d49b619c2d87b8d96e4e1851bccb290888
3
+ size 276872907
checkpoint-700/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a419a0d7fe975dc48bb38fc1134b687ce0edf41f5122451ad3693789f39aca5c
3
+ size 14645
checkpoint-700/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41fef1da4d36e83ab4c4514cf0e4e4e669a4f66b39cd337869b03e46e20fc3d4
3
+ size 1383
checkpoint-700/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a096f3fded1ea6b016d43b5fc33c38c01f7114961d1ce15e0e16bccaa1daadc
3
+ size 1465
checkpoint-700/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "HFCompatibleLinguisticTokenizer",
3
+ "vocab_size": 16384,
4
+ "model_max_length": 512,
5
+ "bos_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "unk_token": "<unk>",
8
+ "pad_token": "<pad>"
9
+ }
checkpoint-700/trainer_state.json ADDED
@@ -0,0 +1,524 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.002047606859482979,
6
+ "eval_steps": 500,
7
+ "global_step": 700,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 2.925152656404256e-05,
14
+ "grad_norm": 44.091312408447266,
15
+ "learning_rate": 4.1999999999999995e-07,
16
+ "loss": 9.3692,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 5.850305312808512e-05,
21
+ "grad_norm": 44.14885711669922,
22
+ "learning_rate": 1.0199999999999998e-06,
23
+ "loss": 9.3095,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 8.775457969212769e-05,
28
+ "grad_norm": 71.31829071044922,
29
+ "learning_rate": 1.62e-06,
30
+ "loss": 9.2848,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.00011700610625617024,
35
+ "grad_norm": 44.88148498535156,
36
+ "learning_rate": 2.22e-06,
37
+ "loss": 9.3214,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.0001462576328202128,
42
+ "grad_norm": 71.73838806152344,
43
+ "learning_rate": 2.8199999999999997e-06,
44
+ "loss": 9.2992,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.00017550915938425538,
49
+ "grad_norm": 63.85468292236328,
50
+ "learning_rate": 3.42e-06,
51
+ "loss": 9.3034,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.00020476068594829793,
56
+ "grad_norm": 47.08655548095703,
57
+ "learning_rate": 4.02e-06,
58
+ "loss": 9.2972,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.00023401221251234048,
63
+ "grad_norm": 46.76586151123047,
64
+ "learning_rate": 4.62e-06,
65
+ "loss": 9.282,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.00026326373907638306,
70
+ "grad_norm": 68.871826171875,
71
+ "learning_rate": 5.219999999999999e-06,
72
+ "loss": 9.2683,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.0002925152656404256,
77
+ "grad_norm": 40.276512145996094,
78
+ "learning_rate": 5.819999999999999e-06,
79
+ "loss": 9.2803,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.00032176679220446817,
84
+ "grad_norm": 43.05030059814453,
85
+ "learning_rate": 6.4199999999999995e-06,
86
+ "loss": 9.2783,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.00035101831876851075,
91
+ "grad_norm": 48.496463775634766,
92
+ "learning_rate": 7.02e-06,
93
+ "loss": 9.2473,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.0003802698453325533,
98
+ "grad_norm": 56.55481719970703,
99
+ "learning_rate": 7.619999999999999e-06,
100
+ "loss": 9.2961,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.00040952137189659586,
105
+ "grad_norm": 35.09830093383789,
106
+ "learning_rate": 8.22e-06,
107
+ "loss": 9.2656,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.00043877289846063844,
112
+ "grad_norm": 38.8115348815918,
113
+ "learning_rate": 8.819999999999999e-06,
114
+ "loss": 9.2461,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.00046802442502468097,
119
+ "grad_norm": 38.47610855102539,
120
+ "learning_rate": 9.419999999999998e-06,
121
+ "loss": 9.2523,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.0004972759515887235,
126
+ "grad_norm": 35.73860549926758,
127
+ "learning_rate": 1.0019999999999999e-05,
128
+ "loss": 9.2434,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.0005265274781527661,
133
+ "grad_norm": 35.11371994018555,
134
+ "learning_rate": 1.062e-05,
135
+ "loss": 9.2298,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.0005557790047168087,
140
+ "grad_norm": 41.20671844482422,
141
+ "learning_rate": 1.122e-05,
142
+ "loss": 9.2479,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.0005850305312808512,
147
+ "grad_norm": 31.733139038085938,
148
+ "learning_rate": 1.1819999999999999e-05,
149
+ "loss": 9.2436,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.0006142820578448938,
154
+ "grad_norm": 30.686948776245117,
155
+ "learning_rate": 1.2419999999999998e-05,
156
+ "loss": 9.2533,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.0006435335844089363,
161
+ "grad_norm": 28.569021224975586,
162
+ "learning_rate": 1.3019999999999999e-05,
163
+ "loss": 9.2148,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.0006727851109729789,
168
+ "grad_norm": 40.037601470947266,
169
+ "learning_rate": 1.362e-05,
170
+ "loss": 9.21,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.0007020366375370215,
175
+ "grad_norm": 63.61598587036133,
176
+ "learning_rate": 1.4219999999999998e-05,
177
+ "loss": 9.2505,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.000731288164101064,
182
+ "grad_norm": 29.98544692993164,
183
+ "learning_rate": 1.4819999999999999e-05,
184
+ "loss": 9.2188,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.0007605396906651066,
189
+ "grad_norm": 30.23026466369629,
190
+ "learning_rate": 1.5419999999999998e-05,
191
+ "loss": 9.1822,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.0007897912172291491,
196
+ "grad_norm": 21.082069396972656,
197
+ "learning_rate": 1.602e-05,
198
+ "loss": 9.2109,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.0008190427437931917,
203
+ "grad_norm": 34.52238464355469,
204
+ "learning_rate": 1.6619999999999997e-05,
205
+ "loss": 9.178,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.0008482942703572343,
210
+ "grad_norm": 54.66425704956055,
211
+ "learning_rate": 1.7219999999999998e-05,
212
+ "loss": 9.2251,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.0008775457969212769,
217
+ "grad_norm": 32.79227066040039,
218
+ "learning_rate": 1.782e-05,
219
+ "loss": 9.1966,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.0009067973234853194,
224
+ "grad_norm": 29.83945655822754,
225
+ "learning_rate": 1.842e-05,
226
+ "loss": 9.2206,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.0009360488500493619,
231
+ "grad_norm": 16.18548583984375,
232
+ "learning_rate": 1.9019999999999997e-05,
233
+ "loss": 9.2005,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.0009653003766134045,
238
+ "grad_norm": 27.39173698425293,
239
+ "learning_rate": 1.962e-05,
240
+ "loss": 9.2079,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.000994551903177447,
245
+ "grad_norm": 23.602752685546875,
246
+ "learning_rate": 2.022e-05,
247
+ "loss": 9.2022,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.0010238034297414896,
252
+ "grad_norm": 21.416629791259766,
253
+ "learning_rate": 2.082e-05,
254
+ "loss": 9.1674,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.0010530549563055323,
259
+ "grad_norm": Infinity,
260
+ "learning_rate": 2.1419999999999998e-05,
261
+ "loss": 9.1761,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.0010823064828695747,
266
+ "grad_norm": 27.356834411621094,
267
+ "learning_rate": 2.196e-05,
268
+ "loss": 9.2058,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.0011115580094336174,
273
+ "grad_norm": 24.82968521118164,
274
+ "learning_rate": 2.2559999999999997e-05,
275
+ "loss": 9.1643,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.00114080953599766,
280
+ "grad_norm": 19.21381187438965,
281
+ "learning_rate": 2.316e-05,
282
+ "loss": 9.1706,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.0011700610625617024,
287
+ "grad_norm": 18.351755142211914,
288
+ "learning_rate": 2.3699999999999997e-05,
289
+ "loss": 9.1917,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.001199312589125745,
294
+ "grad_norm": 17.74287223815918,
295
+ "learning_rate": 2.4299999999999998e-05,
296
+ "loss": 9.18,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.0012285641156897875,
301
+ "grad_norm": 24.708906173706055,
302
+ "learning_rate": 2.49e-05,
303
+ "loss": 9.2101,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.0012578156422538302,
308
+ "grad_norm": 22.12462043762207,
309
+ "learning_rate": 2.55e-05,
310
+ "loss": 9.2013,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.0012870671688178727,
315
+ "grad_norm": 24.500715255737305,
316
+ "learning_rate": 2.6099999999999997e-05,
317
+ "loss": 9.1629,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.0013163186953819152,
322
+ "grad_norm": 35.824031829833984,
323
+ "learning_rate": 2.6699999999999995e-05,
324
+ "loss": 9.1877,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.0013455702219459578,
329
+ "grad_norm": 28.570497512817383,
330
+ "learning_rate": 2.7299999999999996e-05,
331
+ "loss": 9.1961,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.0013748217485100003,
336
+ "grad_norm": 19.405773162841797,
337
+ "learning_rate": 2.7899999999999997e-05,
338
+ "loss": 9.1905,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.001404073275074043,
343
+ "grad_norm": 20.267793655395508,
344
+ "learning_rate": 2.8499999999999998e-05,
345
+ "loss": 9.1693,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.0014333248016380855,
350
+ "grad_norm": 18.131561279296875,
351
+ "learning_rate": 2.91e-05,
352
+ "loss": 9.1895,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.001462576328202128,
357
+ "grad_norm": 28.323633193969727,
358
+ "learning_rate": 2.97e-05,
359
+ "loss": 9.1714,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.0014918278547661706,
364
+ "grad_norm": 20.251134872436523,
365
+ "learning_rate": 3.0299999999999998e-05,
366
+ "loss": 9.1529,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.0015210793813302131,
371
+ "grad_norm": 17.09373664855957,
372
+ "learning_rate": 3.0839999999999996e-05,
373
+ "loss": 9.1546,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.0015503309078942558,
378
+ "grad_norm": 16.57909393310547,
379
+ "learning_rate": 3.144e-05,
380
+ "loss": 9.1673,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.0015795824344582983,
385
+ "grad_norm": 10.633030891418457,
386
+ "learning_rate": 3.204e-05,
387
+ "loss": 9.1716,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.0016088339610223408,
392
+ "grad_norm": 14.826539039611816,
393
+ "learning_rate": 3.263999999999999e-05,
394
+ "loss": 9.1649,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.0016380854875863834,
399
+ "grad_norm": 17.31394386291504,
400
+ "learning_rate": 3.3239999999999993e-05,
401
+ "loss": 9.173,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.001667337014150426,
406
+ "grad_norm": 13.405190467834473,
407
+ "learning_rate": 3.3839999999999994e-05,
408
+ "loss": 9.1724,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.0016965885407144686,
413
+ "grad_norm": 16.752643585205078,
414
+ "learning_rate": 3.4439999999999996e-05,
415
+ "loss": 9.1688,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.001725840067278511,
420
+ "grad_norm": 18.50242042541504,
421
+ "learning_rate": 3.5039999999999997e-05,
422
+ "loss": 9.1638,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.0017550915938425538,
427
+ "grad_norm": 14.997364044189453,
428
+ "learning_rate": 3.564e-05,
429
+ "loss": 9.1565,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.0017843431204065962,
434
+ "grad_norm": 11.956835746765137,
435
+ "learning_rate": 3.624e-05,
436
+ "loss": 9.1598,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.0018135946469706387,
441
+ "grad_norm": 15.849851608276367,
442
+ "learning_rate": 3.684e-05,
443
+ "loss": 9.1541,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.0018428461735346814,
448
+ "grad_norm": 17.481584548950195,
449
+ "learning_rate": 3.7439999999999994e-05,
450
+ "loss": 9.1533,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.0018720977000987239,
455
+ "grad_norm": 15.944308280944824,
456
+ "learning_rate": 3.8039999999999995e-05,
457
+ "loss": 9.1647,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.0019013492266627666,
462
+ "grad_norm": 15.674567222595215,
463
+ "learning_rate": 3.8639999999999996e-05,
464
+ "loss": 9.161,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.001930600753226809,
469
+ "grad_norm": 13.785255432128906,
470
+ "learning_rate": 3.924e-05,
471
+ "loss": 9.1601,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.0019598522797908517,
476
+ "grad_norm": 15.747488975524902,
477
+ "learning_rate": 3.984e-05,
478
+ "loss": 9.128,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.001989103806354894,
483
+ "grad_norm": 11.030411720275879,
484
+ "learning_rate": 4.044e-05,
485
+ "loss": 9.1476,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.0020183553329189367,
490
+ "grad_norm": 15.800025939941406,
491
+ "learning_rate": 4.104e-05,
492
+ "loss": 9.1129,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.002047606859482979,
497
+ "grad_norm": 11.431413650512695,
498
+ "learning_rate": 4.164e-05,
499
+ "loss": 9.1712,
500
+ "step": 700
501
+ }
502
+ ],
503
+ "logging_steps": 10,
504
+ "max_steps": 1000000,
505
+ "num_input_tokens_seen": 0,
506
+ "num_train_epochs": 3,
507
+ "save_steps": 100,
508
+ "stateful_callbacks": {
509
+ "TrainerControl": {
510
+ "args": {
511
+ "should_epoch_stop": false,
512
+ "should_evaluate": false,
513
+ "should_log": false,
514
+ "should_save": true,
515
+ "should_training_stop": false
516
+ },
517
+ "attributes": {}
518
+ }
519
+ },
520
+ "total_flos": 2043534508032000.0,
521
+ "train_batch_size": 4,
522
+ "trial_name": null,
523
+ "trial_params": null
524
+ }
checkpoint-700/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:345930ddfb53788d81724f387da0e4c9b3054879aaa61b84767ee1042bc4803a
3
+ size 5201