aixk commited on
Commit
0546d6d
·
verified ·
1 Parent(s): 226c50f

Upload folder using huggingface_hub

Browse files
checkpoint-500/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-500/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-500/hybrid_tokenizer_mapping.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5619fc35d039ed1746fe2d9faba129a3403179006ebcad4f2888ceb92c7213
3
+ size 501888768
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc01f9cc5eb8289f43534b9857aeff2519db112dba26c533ed20a6a1c45cb2b3
3
+ size 254046859
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515127194eeba6cba46616ff245b20b90c18e53c92677bde977dcf2fdbb706c0
3
+ size 14645
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899c8e287007343a5b21e67037b0708c70876c23c554626fa715f159c9e86953
3
+ size 1383
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f596d3976420c1cef22e6f9cb083db2f3d9fcff11af39cd66654634ab6c6973d
3
+ size 1465
checkpoint-500/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-500/trainer_state.json ADDED
@@ -0,0 +1,384 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.026446280991735537,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0005289256198347108,
14
+ "grad_norm": 14983.798828125,
15
+ "learning_rate": 2.4e-07,
16
+ "loss": 17.1865,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0010578512396694215,
21
+ "grad_norm": 2818.19287109375,
22
+ "learning_rate": 1.04e-06,
23
+ "loss": 16.2669,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0015867768595041322,
28
+ "grad_norm": 2148.98486328125,
29
+ "learning_rate": 1.84e-06,
30
+ "loss": 15.5605,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.002115702479338843,
35
+ "grad_norm": 2309.862548828125,
36
+ "learning_rate": 2.64e-06,
37
+ "loss": 15.2203,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.002644628099173554,
42
+ "grad_norm": 2205.408935546875,
43
+ "learning_rate": 3.44e-06,
44
+ "loss": 14.9347,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0031735537190082643,
49
+ "grad_norm": 2530.3701171875,
50
+ "learning_rate": 4.24e-06,
51
+ "loss": 14.8024,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0037024793388429752,
56
+ "grad_norm": 1678.7281494140625,
57
+ "learning_rate": 5.04e-06,
58
+ "loss": 14.6196,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.004231404958677686,
63
+ "grad_norm": 2254.43798828125,
64
+ "learning_rate": 5.84e-06,
65
+ "loss": 14.4786,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.004760330578512397,
70
+ "grad_norm": 2226.012939453125,
71
+ "learning_rate": 6.640000000000001e-06,
72
+ "loss": 14.3674,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.005289256198347108,
77
+ "grad_norm": 2211.912353515625,
78
+ "learning_rate": 7.44e-06,
79
+ "loss": 14.1906,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.005818181818181818,
84
+ "grad_norm": 3070.8232421875,
85
+ "learning_rate": 8.24e-06,
86
+ "loss": 14.1344,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.006347107438016529,
91
+ "grad_norm": 2257.41455078125,
92
+ "learning_rate": 9.04e-06,
93
+ "loss": 14.0681,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.00687603305785124,
98
+ "grad_norm": 2274.346435546875,
99
+ "learning_rate": 9.84e-06,
100
+ "loss": 13.9746,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0074049586776859504,
105
+ "grad_norm": 2632.0341796875,
106
+ "learning_rate": 1.064e-05,
107
+ "loss": 13.9974,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.007933884297520661,
112
+ "grad_norm": 1979.03857421875,
113
+ "learning_rate": 1.144e-05,
114
+ "loss": 13.6573,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.008462809917355372,
119
+ "grad_norm": 1911.6646728515625,
120
+ "learning_rate": 1.216e-05,
121
+ "loss": 13.5115,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.008991735537190083,
126
+ "grad_norm": 1221.2379150390625,
127
+ "learning_rate": 1.296e-05,
128
+ "loss": 13.4189,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.009520661157024794,
133
+ "grad_norm": 1295.5301513671875,
134
+ "learning_rate": 1.376e-05,
135
+ "loss": 13.1649,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.010049586776859505,
140
+ "grad_norm": 1181.076904296875,
141
+ "learning_rate": 1.4480000000000002e-05,
142
+ "loss": 13.0769,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.010578512396694216,
147
+ "grad_norm": 1546.213623046875,
148
+ "learning_rate": 1.528e-05,
149
+ "loss": 12.981,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.011107438016528925,
154
+ "grad_norm": 1649.0814208984375,
155
+ "learning_rate": 1.6080000000000002e-05,
156
+ "loss": 12.9791,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.011636363636363636,
161
+ "grad_norm": 1149.5986328125,
162
+ "learning_rate": 1.688e-05,
163
+ "loss": 12.9944,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.012165289256198347,
168
+ "grad_norm": 1094.528564453125,
169
+ "learning_rate": 1.7680000000000004e-05,
170
+ "loss": 12.712,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.012694214876033057,
175
+ "grad_norm": 1151.943603515625,
176
+ "learning_rate": 1.848e-05,
177
+ "loss": 12.7007,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.013223140495867768,
182
+ "grad_norm": 756.9489135742188,
183
+ "learning_rate": 1.9280000000000002e-05,
184
+ "loss": 12.6777,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.01375206611570248,
189
+ "grad_norm": 1089.9005126953125,
190
+ "learning_rate": 2.008e-05,
191
+ "loss": 12.551,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.01428099173553719,
196
+ "grad_norm": 1578.2489013671875,
197
+ "learning_rate": 2.0880000000000003e-05,
198
+ "loss": 12.6069,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.014809917355371901,
203
+ "grad_norm": 622.3321533203125,
204
+ "learning_rate": 2.168e-05,
205
+ "loss": 12.4807,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.015338842975206612,
210
+ "grad_norm": 653.3980712890625,
211
+ "learning_rate": 2.248e-05,
212
+ "loss": 12.2924,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.015867768595041323,
217
+ "grad_norm": 580.5093994140625,
218
+ "learning_rate": 2.328e-05,
219
+ "loss": 12.2673,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.016396694214876033,
224
+ "grad_norm": 870.7935791015625,
225
+ "learning_rate": 2.408e-05,
226
+ "loss": 11.8822,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.016925619834710744,
231
+ "grad_norm": 451.5616760253906,
232
+ "learning_rate": 2.488e-05,
233
+ "loss": 11.7939,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.017454545454545455,
238
+ "grad_norm": 1039.074462890625,
239
+ "learning_rate": 2.5679999999999998e-05,
240
+ "loss": 11.7623,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.017983471074380166,
245
+ "grad_norm": 826.6625366210938,
246
+ "learning_rate": 2.648e-05,
247
+ "loss": 11.5301,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.018512396694214877,
252
+ "grad_norm": 375.2585144042969,
253
+ "learning_rate": 2.728e-05,
254
+ "loss": 11.6941,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.019041322314049588,
259
+ "grad_norm": 535.522705078125,
260
+ "learning_rate": 2.8080000000000002e-05,
261
+ "loss": 11.3719,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.0195702479338843,
266
+ "grad_norm": 608.0570678710938,
267
+ "learning_rate": 2.888e-05,
268
+ "loss": 11.2682,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.02009917355371901,
273
+ "grad_norm": 678.4328002929688,
274
+ "learning_rate": 2.9680000000000004e-05,
275
+ "loss": 11.3097,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.02062809917355372,
280
+ "grad_norm": 567.5283203125,
281
+ "learning_rate": 3.0480000000000003e-05,
282
+ "loss": 11.2014,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.02115702479338843,
287
+ "grad_norm": 382.2688293457031,
288
+ "learning_rate": 3.1280000000000005e-05,
289
+ "loss": 10.9673,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.021685950413223142,
294
+ "grad_norm": 599.6221923828125,
295
+ "learning_rate": 3.208e-05,
296
+ "loss": 10.981,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.02221487603305785,
301
+ "grad_norm": 382.1618957519531,
302
+ "learning_rate": 3.288e-05,
303
+ "loss": 10.9526,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.02274380165289256,
308
+ "grad_norm": 1082.0447998046875,
309
+ "learning_rate": 3.368e-05,
310
+ "loss": 10.9535,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.02327272727272727,
315
+ "grad_norm": 360.10101318359375,
316
+ "learning_rate": 3.448e-05,
317
+ "loss": 10.7087,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.023801652892561982,
322
+ "grad_norm": 460.0298156738281,
323
+ "learning_rate": 3.528e-05,
324
+ "loss": 10.8773,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.024330578512396693,
329
+ "grad_norm": 389.6498107910156,
330
+ "learning_rate": 3.608e-05,
331
+ "loss": 10.7515,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.024859504132231404,
336
+ "grad_norm": 511.04937744140625,
337
+ "learning_rate": 3.6880000000000006e-05,
338
+ "loss": 10.4311,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.025388429752066115,
343
+ "grad_norm": 277.2391052246094,
344
+ "learning_rate": 3.7680000000000005e-05,
345
+ "loss": 10.3949,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.025917355371900826,
350
+ "grad_norm": 345.6590270996094,
351
+ "learning_rate": 3.848e-05,
352
+ "loss": 10.3248,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.026446280991735537,
357
+ "grad_norm": 354.5246887207031,
358
+ "learning_rate": 3.9280000000000003e-05,
359
+ "loss": 10.4081,
360
+ "step": 500
361
+ }
362
+ ],
363
+ "logging_steps": 10,
364
+ "max_steps": 10000000,
365
+ "num_input_tokens_seen": 0,
366
+ "num_train_epochs": 529,
367
+ "save_steps": 100,
368
+ "stateful_callbacks": {
369
+ "TrainerControl": {
370
+ "args": {
371
+ "should_epoch_stop": false,
372
+ "should_evaluate": false,
373
+ "should_log": false,
374
+ "should_save": true,
375
+ "should_training_stop": false
376
+ },
377
+ "attributes": {}
378
+ }
379
+ },
380
+ "total_flos": 8378154021273600.0,
381
+ "train_batch_size": 8,
382
+ "trial_name": null,
383
+ "trial_params": null
384
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5623a138829268598233d481b5532c5c6b7e4686976472a3d219e1ab580f03e5
3
+ size 5201