aixk commited on
Commit
e284470
·
verified ·
1 Parent(s): 09a1082

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_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-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:ceacba6f8422da4740f875f0326cf8dd22ebad0cbf81b7126a74323ae79e4078
3
+ size 543870712
checkpoint-600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4802adec25b42de26f8db52c5e4e55b96061dfbd6a54ab187269425797e90ec8
3
+ size 276872907
checkpoint-600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23bf61c7885319e12838cd6124025b90357bda3e0de1c466fea36fb786fcc127
3
+ size 14645
checkpoint-600/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e25af3ed4cf86b5aaf8404a315d04ce71c71dc58bfb266bc877f04c5a453dfa
3
+ size 1383
checkpoint-600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ca1067a0825718ba6e5d80e13b703c41a84d4be17c1660a215557b0e9b46b3a
3
+ size 1465
checkpoint-600/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-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": 0.0017573753014081702,
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": 2.9289588356802836e-05,
14
+ "grad_norm": 43.412994384765625,
15
+ "learning_rate": 4.8e-07,
16
+ "loss": 9.4322,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 5.857917671360567e-05,
21
+ "grad_norm": 24.38200569152832,
22
+ "learning_rate": 1.0799999999999998e-06,
23
+ "loss": 9.4165,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 8.786876507040851e-05,
28
+ "grad_norm": 25.624269485473633,
29
+ "learning_rate": 1.6799999999999998e-06,
30
+ "loss": 9.3983,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.00011715835342721134,
35
+ "grad_norm": 25.8831729888916,
36
+ "learning_rate": 2.2799999999999998e-06,
37
+ "loss": 9.4015,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.00014644794178401418,
42
+ "grad_norm": 18.858943939208984,
43
+ "learning_rate": 2.8799999999999995e-06,
44
+ "loss": 9.369,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.00017573753014081702,
49
+ "grad_norm": 32.19478225708008,
50
+ "learning_rate": 3.4799999999999993e-06,
51
+ "loss": 9.3743,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.00020502711849761985,
56
+ "grad_norm": 29.089111328125,
57
+ "learning_rate": 4.079999999999999e-06,
58
+ "loss": 9.3628,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.0002343167068544227,
63
+ "grad_norm": 45.67530822753906,
64
+ "learning_rate": 4.679999999999999e-06,
65
+ "loss": 9.359,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0002636062952112255,
70
+ "grad_norm": 33.06043243408203,
71
+ "learning_rate": 5.28e-06,
72
+ "loss": 9.3381,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.00029289588356802836,
77
+ "grad_norm": 32.19873809814453,
78
+ "learning_rate": 5.88e-06,
79
+ "loss": 9.3304,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.0003221854719248312,
84
+ "grad_norm": 39.30705261230469,
85
+ "learning_rate": 6.48e-06,
86
+ "loss": 9.3144,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.00035147506028163403,
91
+ "grad_norm": 42.05266189575195,
92
+ "learning_rate": 7.079999999999999e-06,
93
+ "loss": 9.3104,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.00038076464863843687,
98
+ "grad_norm": 33.91127014160156,
99
+ "learning_rate": 7.68e-06,
100
+ "loss": 9.3218,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0004100542369952397,
105
+ "grad_norm": 31.721614837646484,
106
+ "learning_rate": 8.279999999999999e-06,
107
+ "loss": 9.3045,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.00043934382535204254,
112
+ "grad_norm": 59.37827682495117,
113
+ "learning_rate": 8.88e-06,
114
+ "loss": 9.3054,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.0004686334137088454,
119
+ "grad_norm": 74.16336059570312,
120
+ "learning_rate": 9.48e-06,
121
+ "loss": 9.2952,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.0004979230020656483,
126
+ "grad_norm": 33.57463836669922,
127
+ "learning_rate": 1.0079999999999998e-05,
128
+ "loss": 9.2887,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.000527212590422451,
133
+ "grad_norm": 37.42033386230469,
134
+ "learning_rate": 1.068e-05,
135
+ "loss": 9.2839,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.0005565021787792539,
140
+ "grad_norm": 33.58783721923828,
141
+ "learning_rate": 1.1279999999999999e-05,
142
+ "loss": 9.2869,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.0005857917671360567,
147
+ "grad_norm": 33.92068862915039,
148
+ "learning_rate": 1.188e-05,
149
+ "loss": 9.2636,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.0006150813554928596,
154
+ "grad_norm": 36.4366455078125,
155
+ "learning_rate": 1.2479999999999999e-05,
156
+ "loss": 9.2653,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.0006443709438496624,
161
+ "grad_norm": 27.894250869750977,
162
+ "learning_rate": 1.3079999999999998e-05,
163
+ "loss": 9.2699,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.0006736605322064653,
168
+ "grad_norm": 39.57080078125,
169
+ "learning_rate": 1.3559999999999997e-05,
170
+ "loss": 9.2491,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.0007029501205632681,
175
+ "grad_norm": 18.53085708618164,
176
+ "learning_rate": 1.4159999999999998e-05,
177
+ "loss": 9.2552,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.000732239708920071,
182
+ "grad_norm": 41.72337341308594,
183
+ "learning_rate": 1.476e-05,
184
+ "loss": 9.2611,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.0007615292972768737,
189
+ "grad_norm": 21.73541831970215,
190
+ "learning_rate": 1.536e-05,
191
+ "loss": 9.2928,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.0007908188856336766,
196
+ "grad_norm": 59.771385192871094,
197
+ "learning_rate": 1.5959999999999996e-05,
198
+ "loss": 9.2558,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.0008201084739904794,
203
+ "grad_norm": 75.89784240722656,
204
+ "learning_rate": 1.6559999999999997e-05,
205
+ "loss": 9.2438,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.0008493980623472823,
210
+ "grad_norm": 33.123294830322266,
211
+ "learning_rate": 1.716e-05,
212
+ "loss": 9.278,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.0008786876507040851,
217
+ "grad_norm": 39.20044708251953,
218
+ "learning_rate": 1.776e-05,
219
+ "loss": 9.2508,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.000907977239060888,
224
+ "grad_norm": 10.648369789123535,
225
+ "learning_rate": 1.8359999999999997e-05,
226
+ "loss": 9.2503,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.0009372668274176908,
231
+ "grad_norm": 44.026634216308594,
232
+ "learning_rate": 1.896e-05,
233
+ "loss": 9.2699,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.0009665564157744936,
238
+ "grad_norm": 45.130611419677734,
239
+ "learning_rate": 1.9559999999999996e-05,
240
+ "loss": 9.2433,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.0009958460041312965,
245
+ "grad_norm": 30.56162452697754,
246
+ "learning_rate": 2.0159999999999997e-05,
247
+ "loss": 9.2355,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.0010251355924880993,
252
+ "grad_norm": 15.57412052154541,
253
+ "learning_rate": 2.0759999999999998e-05,
254
+ "loss": 9.2367,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.001054425180844902,
259
+ "grad_norm": 33.53938674926758,
260
+ "learning_rate": 2.136e-05,
261
+ "loss": 9.2414,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.0010837147692017049,
266
+ "grad_norm": 15.654319763183594,
267
+ "learning_rate": 2.196e-05,
268
+ "loss": 9.2358,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.0011130043575585079,
273
+ "grad_norm": 17.77244758605957,
274
+ "learning_rate": 2.2559999999999997e-05,
275
+ "loss": 9.224,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.0011422939459153107,
280
+ "grad_norm": 13.026928901672363,
281
+ "learning_rate": 2.316e-05,
282
+ "loss": 9.2303,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.0011715835342721134,
287
+ "grad_norm": 25.018850326538086,
288
+ "learning_rate": 2.376e-05,
289
+ "loss": 9.2103,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.0012008731226289162,
294
+ "grad_norm": 30.319482803344727,
295
+ "learning_rate": 2.4359999999999997e-05,
296
+ "loss": 9.2371,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.0012301627109857192,
301
+ "grad_norm": 14.935267448425293,
302
+ "learning_rate": 2.4959999999999998e-05,
303
+ "loss": 9.2569,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.001259452299342522,
308
+ "grad_norm": 8.77879524230957,
309
+ "learning_rate": 2.5559999999999996e-05,
310
+ "loss": 9.241,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.0012887418876993248,
315
+ "grad_norm": 44.00795364379883,
316
+ "learning_rate": 2.6159999999999997e-05,
317
+ "loss": 9.2009,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.0013180314760561276,
322
+ "grad_norm": 27.51123046875,
323
+ "learning_rate": 2.6759999999999998e-05,
324
+ "loss": 9.2257,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.0013473210644129306,
329
+ "grad_norm": 25.604936599731445,
330
+ "learning_rate": 2.736e-05,
331
+ "loss": 9.2245,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.0013766106527697333,
336
+ "grad_norm": 16.147348403930664,
337
+ "learning_rate": 2.796e-05,
338
+ "loss": 9.2356,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.0014059002411265361,
343
+ "grad_norm": 10.082588195800781,
344
+ "learning_rate": 2.856e-05,
345
+ "loss": 9.2074,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.001435189829483339,
350
+ "grad_norm": 7.7481889724731445,
351
+ "learning_rate": 2.9159999999999995e-05,
352
+ "loss": 9.2339,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.001464479417840142,
357
+ "grad_norm": 12.886085510253906,
358
+ "learning_rate": 2.9759999999999996e-05,
359
+ "loss": 9.2148,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.0014937690061969447,
364
+ "grad_norm": 20.852745056152344,
365
+ "learning_rate": 3.0359999999999997e-05,
366
+ "loss": 9.1892,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.0015230585945537475,
371
+ "grad_norm": 11.238962173461914,
372
+ "learning_rate": 3.0959999999999995e-05,
373
+ "loss": 9.2012,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.0015523481829105503,
378
+ "grad_norm": 10.45230484008789,
379
+ "learning_rate": 3.1559999999999996e-05,
380
+ "loss": 9.2047,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.0015816377712673533,
385
+ "grad_norm": 9.272976875305176,
386
+ "learning_rate": 3.216e-05,
387
+ "loss": 9.1891,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.001610927359624156,
392
+ "grad_norm": 13.807792663574219,
393
+ "learning_rate": 3.276e-05,
394
+ "loss": 9.2122,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.0016402169479809588,
399
+ "grad_norm": 12.749746322631836,
400
+ "learning_rate": 3.335999999999999e-05,
401
+ "loss": 9.2192,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.0016695065363377616,
406
+ "grad_norm": 16.324674606323242,
407
+ "learning_rate": 3.395999999999999e-05,
408
+ "loss": 9.2025,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.0016987961246945646,
413
+ "grad_norm": 12.50004768371582,
414
+ "learning_rate": 3.4559999999999994e-05,
415
+ "loss": 9.189,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.0017280857130513674,
420
+ "grad_norm": 16.172029495239258,
421
+ "learning_rate": 3.5159999999999995e-05,
422
+ "loss": 9.1991,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.0017573753014081702,
427
+ "grad_norm": 6.533432483673096,
428
+ "learning_rate": 3.5759999999999996e-05,
429
+ "loss": 9.1912,
430
+ "step": 600
431
+ }
432
+ ],
433
+ "logging_steps": 10,
434
+ "max_steps": 1000000,
435
+ "num_input_tokens_seen": 0,
436
+ "num_train_epochs": 3,
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": 1554894409728000.0,
451
+ "train_batch_size": 4,
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 sha256:52216374f0eeee8b1d9f89469c7170b070f292bc69dacbc00514897d8019d442
3
+ size 5201