aixk commited on
Commit
7eda83e
·
verified ·
1 Parent(s): 1c38898

Upload folder using huggingface_hub

Browse files
checkpoint-600/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_tagless",
12
+ "num_attention_heads": 12,
13
+ "num_hidden_layers": 16,
14
+ "transformers_version": "5.13.1",
15
+ "use_cache": false,
16
+ "vocab_size": 8192
17
+ }
checkpoint-600/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-600/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-600/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78dd970103153cf86e74e8090d3332d8ccc805ae4068110e917bcde9f29aba02
3
+ size 501759848
checkpoint-600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4095602acfe7ad8dab6dbf9029092d61c7b6249c6bdb2fc70f4ae04a9f876eb2
3
+ size 254028555
checkpoint-600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b9f03641ea8d324f48ed36385daa59a2ddc5b6b1a85bef4f3628917a7b77fb
3
+ size 14645
checkpoint-600/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33705029b5cf95d55511ab7e24ac64aa8fd24295433dc63243d7bf04936e2bb
3
+ size 1383
checkpoint-600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ac021f8782e2651d9ab4b75133a8627ba5713b04ce2328324f0aac2d4b80a7
3
+ size 1465
checkpoint-600/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "HFCompatibleHybridTokenizer",
3
+ "vocab_size": 8192,
4
+ "model_max_length": 512,
5
+ "bos_token": "<bos>",
6
+ "eos_token": "<eos>",
7
+ "unk_token": "<unk>",
8
+ "pad_token": "<pad>"
9
+ }
checkpoint-600/trainer_state.json ADDED
@@ -0,0 +1,454 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.36921656859351565,
6
+ "eval_steps": 500,
7
+ "global_step": 600,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.006153609476558594,
14
+ "grad_norm": 25468.8046875,
15
+ "learning_rate": 1.9999999999999996e-07,
16
+ "loss": 8.7082,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.012307218953117188,
21
+ "grad_norm": 1228.4501953125,
22
+ "learning_rate": 1.2e-06,
23
+ "loss": 8.0776,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.018460828429675783,
28
+ "grad_norm": 355.1081237792969,
29
+ "learning_rate": 2.1999999999999997e-06,
30
+ "loss": 7.2372,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.024614437906234375,
35
+ "grad_norm": 255.58433532714844,
36
+ "learning_rate": 3.1999999999999994e-06,
37
+ "loss": 6.9725,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.03076804738279297,
42
+ "grad_norm": 253.23995971679688,
43
+ "learning_rate": 4.2e-06,
44
+ "loss": 6.8585,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.036921656859351566,
49
+ "grad_norm": 241.82064819335938,
50
+ "learning_rate": 5.199999999999999e-06,
51
+ "loss": 6.7367,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.043075266335910155,
56
+ "grad_norm": 229.0261993408203,
57
+ "learning_rate": 6.199999999999999e-06,
58
+ "loss": 6.6534,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.04922887581246875,
63
+ "grad_norm": 321.6871337890625,
64
+ "learning_rate": 7.2e-06,
65
+ "loss": 6.6305,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.055382485289027346,
70
+ "grad_norm": 465.00543212890625,
71
+ "learning_rate": 8.2e-06,
72
+ "loss": 6.6253,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.06153609476558594,
77
+ "grad_norm": 566.6929321289062,
78
+ "learning_rate": 9.199999999999998e-06,
79
+ "loss": 6.5724,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.06768970424214453,
84
+ "grad_norm": 432.230712890625,
85
+ "learning_rate": 1.02e-05,
86
+ "loss": 6.5328,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.07384331371870313,
91
+ "grad_norm": 289.2374267578125,
92
+ "learning_rate": 1.12e-05,
93
+ "loss": 6.5547,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.07999692319526172,
98
+ "grad_norm": 595.7386474609375,
99
+ "learning_rate": 1.2199999999999998e-05,
100
+ "loss": 6.5651,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.08615053267182031,
105
+ "grad_norm": 861.4376220703125,
106
+ "learning_rate": 1.3199999999999997e-05,
107
+ "loss": 6.5337,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.09230414214837891,
112
+ "grad_norm": 689.42919921875,
113
+ "learning_rate": 1.4199999999999998e-05,
114
+ "loss": 6.4927,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.0984577516249375,
119
+ "grad_norm": 380.9496765136719,
120
+ "learning_rate": 1.5199999999999998e-05,
121
+ "loss": 6.4812,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.1046113611014961,
126
+ "grad_norm": 221.21005249023438,
127
+ "learning_rate": 1.6199999999999997e-05,
128
+ "loss": 6.4508,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.11076497057805469,
133
+ "grad_norm": 199.30874633789062,
134
+ "learning_rate": 1.7199999999999998e-05,
135
+ "loss": 6.4642,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.11691858005461328,
140
+ "grad_norm": 252.44459533691406,
141
+ "learning_rate": 1.82e-05,
142
+ "loss": 6.45,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.12307218953117188,
147
+ "grad_norm": 121.32320404052734,
148
+ "learning_rate": 1.92e-05,
149
+ "loss": 6.4115,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.12922579900773049,
154
+ "grad_norm": 207.04344177246094,
155
+ "learning_rate": 2.0199999999999996e-05,
156
+ "loss": 6.4532,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.13537940848428906,
161
+ "grad_norm": 296.6274719238281,
162
+ "learning_rate": 2.12e-05,
163
+ "loss": 6.3985,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.14153301796084766,
168
+ "grad_norm": 140.3836212158203,
169
+ "learning_rate": 2.2199999999999998e-05,
170
+ "loss": 6.4152,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.14768662743740626,
175
+ "grad_norm": 168.14443969726562,
176
+ "learning_rate": 2.3199999999999998e-05,
177
+ "loss": 6.3686,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.15384023691396484,
182
+ "grad_norm": 141.07810974121094,
183
+ "learning_rate": 2.42e-05,
184
+ "loss": 6.3809,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.15999384639052344,
189
+ "grad_norm": 117.08052062988281,
190
+ "learning_rate": 2.52e-05,
191
+ "loss": 6.3423,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.16614745586708204,
196
+ "grad_norm": 122.97789764404297,
197
+ "learning_rate": 2.6199999999999996e-05,
198
+ "loss": 6.3486,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.17230106534364062,
203
+ "grad_norm": 73.85701751708984,
204
+ "learning_rate": 2.72e-05,
205
+ "loss": 6.329,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.17845467482019922,
210
+ "grad_norm": 78.00408935546875,
211
+ "learning_rate": 2.8199999999999998e-05,
212
+ "loss": 6.3096,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.18460828429675782,
217
+ "grad_norm": 150.3341827392578,
218
+ "learning_rate": 2.9199999999999995e-05,
219
+ "loss": 6.3063,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.1907618937733164,
224
+ "grad_norm": 61.75702667236328,
225
+ "learning_rate": 3.02e-05,
226
+ "loss": 6.3004,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.196915503249875,
231
+ "grad_norm": 83.836181640625,
232
+ "learning_rate": 3.119999999999999e-05,
233
+ "loss": 6.2534,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.2030691127264336,
238
+ "grad_norm": 190.2839813232422,
239
+ "learning_rate": 3.22e-05,
240
+ "loss": 6.2603,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.2092227222029922,
245
+ "grad_norm": 52.196563720703125,
246
+ "learning_rate": 3.3199999999999994e-05,
247
+ "loss": 6.2439,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.21537633167955078,
252
+ "grad_norm": 65.71736907958984,
253
+ "learning_rate": 3.42e-05,
254
+ "loss": 6.227,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.22152994115610938,
259
+ "grad_norm": 66.71468353271484,
260
+ "learning_rate": 3.5199999999999995e-05,
261
+ "loss": 6.2164,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.22768355063266799,
266
+ "grad_norm": 37.26243209838867,
267
+ "learning_rate": 3.62e-05,
268
+ "loss": 6.212,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.23383716010922656,
273
+ "grad_norm": 190.98501586914062,
274
+ "learning_rate": 3.7199999999999996e-05,
275
+ "loss": 6.1833,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.23999076958578516,
280
+ "grad_norm": 51.51064682006836,
281
+ "learning_rate": 3.8199999999999993e-05,
282
+ "loss": 6.1796,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.24614437906234377,
287
+ "grad_norm": 71.14685821533203,
288
+ "learning_rate": 3.919999999999999e-05,
289
+ "loss": 6.1614,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.25229798853890234,
294
+ "grad_norm": 47.48910140991211,
295
+ "learning_rate": 4.02e-05,
296
+ "loss": 6.1277,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.25845159801546097,
301
+ "grad_norm": 49.60618209838867,
302
+ "learning_rate": 4.12e-05,
303
+ "loss": 6.107,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.26460520749201955,
308
+ "grad_norm": 38.03694534301758,
309
+ "learning_rate": 4.2199999999999996e-05,
310
+ "loss": 6.0939,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.2707588169685781,
315
+ "grad_norm": 38.81101989746094,
316
+ "learning_rate": 4.319999999999999e-05,
317
+ "loss": 6.118,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.27691242644513675,
322
+ "grad_norm": 45.36625671386719,
323
+ "learning_rate": 4.42e-05,
324
+ "loss": 6.0641,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.2830660359216953,
329
+ "grad_norm": 44.09037780761719,
330
+ "learning_rate": 4.5199999999999994e-05,
331
+ "loss": 6.0417,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.2892196453982539,
336
+ "grad_norm": 39.48929214477539,
337
+ "learning_rate": 4.62e-05,
338
+ "loss": 6.0371,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.29537325487481253,
343
+ "grad_norm": 44.747039794921875,
344
+ "learning_rate": 4.7199999999999995e-05,
345
+ "loss": 6.0157,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.3015268643513711,
350
+ "grad_norm": 51.372249603271484,
351
+ "learning_rate": 4.82e-05,
352
+ "loss": 6.0378,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.3076804738279297,
357
+ "grad_norm": 46.31863021850586,
358
+ "learning_rate": 4.9199999999999997e-05,
359
+ "loss": 5.9815,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.3138340833044883,
364
+ "grad_norm": 74.35610961914062,
365
+ "learning_rate": 5.0199999999999994e-05,
366
+ "loss": 6.0108,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.3199876927810469,
371
+ "grad_norm": 31.986116409301758,
372
+ "learning_rate": 5.119999999999999e-05,
373
+ "loss": 5.9452,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.32614130225760546,
378
+ "grad_norm": 62.82748794555664,
379
+ "learning_rate": 5.2199999999999995e-05,
380
+ "loss": 5.9396,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.3322949117341641,
385
+ "grad_norm": 36.623085021972656,
386
+ "learning_rate": 5.32e-05,
387
+ "loss": 5.9078,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.33844852121072266,
392
+ "grad_norm": 66.77005004882812,
393
+ "learning_rate": 5.4199999999999996e-05,
394
+ "loss": 5.9127,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.34460213068728124,
399
+ "grad_norm": 42.2696533203125,
400
+ "learning_rate": 5.519999999999999e-05,
401
+ "loss": 5.8751,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.35075574016383987,
406
+ "grad_norm": 36.03275680541992,
407
+ "learning_rate": 5.619999999999999e-05,
408
+ "loss": 5.8704,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.35690934964039844,
413
+ "grad_norm": 34.99599838256836,
414
+ "learning_rate": 5.72e-05,
415
+ "loss": 5.8357,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.363062959116957,
420
+ "grad_norm": 37.03520584106445,
421
+ "learning_rate": 5.82e-05,
422
+ "loss": 5.8248,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.36921656859351565,
427
+ "grad_norm": 39.70176696777344,
428
+ "learning_rate": 5.9199999999999996e-05,
429
+ "loss": 5.782,
430
+ "step": 600
431
+ }
432
+ ],
433
+ "logging_steps": 10,
434
+ "max_steps": 100000,
435
+ "num_input_tokens_seen": 0,
436
+ "num_train_epochs": 62,
437
+ "save_steps": 100,
438
+ "stateful_callbacks": {
439
+ "TrainerControl": {
440
+ "args": {
441
+ "should_epoch_stop": false,
442
+ "should_evaluate": false,
443
+ "should_log": false,
444
+ "should_save": true,
445
+ "should_training_stop": false
446
+ },
447
+ "attributes": {}
448
+ }
449
+ },
450
+ "total_flos": 4.54385027776512e+16,
451
+ "train_batch_size": 16,
452
+ "trial_name": null,
453
+ "trial_params": null
454
+ }
checkpoint-600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4183c4264061f851b0692158bc778140daa0082cbcdb75e934ec1d340f04b990
3
+ size 5201