aixk commited on
Commit
4c7465d
·
verified ·
1 Parent(s): fa611be

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:e823e132196e69a2cae0b56e9a1e72a97ad952c0f269295158f82e5c71c97533
3
+ size 501888768
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f697c2f8d29de69d66cb7fe7a19b604a71e512cfc8e391f20398e00ee42502
3
+ size 254046859
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e65f2c24fc5b32d07c41bff129ee4ef72b5868db543c709f17fadfdd9ea2750
3
+ size 14645
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33bbe8b5caa81a5040cdb06eb16aff8b44acc59b0cf530a0ad080c8042e325c
3
+ size 1383
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd86416237c0bc8dabdc129ef93760100d66a11a7dbc9f737e8d28064ae66f84
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": 0.021279991488003403,
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": 0.0004255998297600681,
14
+ "grad_norm": 5634.16845703125,
15
+ "learning_rate": 2.4e-07,
16
+ "loss": 14.1264,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0008511996595201362,
21
+ "grad_norm": 2312.5771484375,
22
+ "learning_rate": 1.04e-06,
23
+ "loss": 13.2905,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0012767994892802044,
28
+ "grad_norm": 2110.1591796875,
29
+ "learning_rate": 1.84e-06,
30
+ "loss": 12.6236,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0017023993190402723,
35
+ "grad_norm": 1493.8431396484375,
36
+ "learning_rate": 2.64e-06,
37
+ "loss": 12.3954,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.0021279991488003403,
42
+ "grad_norm": 1430.7598876953125,
43
+ "learning_rate": 3.44e-06,
44
+ "loss": 12.265,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0025535989785604087,
49
+ "grad_norm": 2192.621826171875,
50
+ "learning_rate": 4.24e-06,
51
+ "loss": 12.018,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0029791988083204767,
56
+ "grad_norm": 1678.5159912109375,
57
+ "learning_rate": 5.04e-06,
58
+ "loss": 11.8932,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.0034047986380805447,
63
+ "grad_norm": 1261.883056640625,
64
+ "learning_rate": 5.84e-06,
65
+ "loss": 11.8077,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0038303984678406127,
70
+ "grad_norm": 1710.3070068359375,
71
+ "learning_rate": 6.640000000000001e-06,
72
+ "loss": 11.6841,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.004255998297600681,
77
+ "grad_norm": 2306.063232421875,
78
+ "learning_rate": 7.44e-06,
79
+ "loss": 11.5426,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.004681598127360749,
84
+ "grad_norm": 2158.360107421875,
85
+ "learning_rate": 8.24e-06,
86
+ "loss": 11.4863,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.0051071979571208174,
91
+ "grad_norm": 2058.938232421875,
92
+ "learning_rate": 9.04e-06,
93
+ "loss": 11.5044,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.005532797786880885,
98
+ "grad_norm": 2320.1376953125,
99
+ "learning_rate": 9.84e-06,
100
+ "loss": 11.4696,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.005958397616640953,
105
+ "grad_norm": 3147.455078125,
106
+ "learning_rate": 1.064e-05,
107
+ "loss": 11.2994,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.006383997446401022,
112
+ "grad_norm": 1930.887451171875,
113
+ "learning_rate": 1.144e-05,
114
+ "loss": 11.2686,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.006809597276161089,
119
+ "grad_norm": 3005.495361328125,
120
+ "learning_rate": 1.224e-05,
121
+ "loss": 11.2556,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.007235197105921158,
126
+ "grad_norm": 1587.324462890625,
127
+ "learning_rate": 1.3039999999999999e-05,
128
+ "loss": 11.1593,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.007660796935681225,
133
+ "grad_norm": 1496.0810546875,
134
+ "learning_rate": 1.384e-05,
135
+ "loss": 11.0329,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.008086396765441295,
140
+ "grad_norm": 2397.255615234375,
141
+ "learning_rate": 1.4560000000000001e-05,
142
+ "loss": 11.0514,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.008511996595201361,
147
+ "grad_norm": 3627.1494140625,
148
+ "learning_rate": 1.536e-05,
149
+ "loss": 10.9684,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.00893759642496143,
154
+ "grad_norm": 1078.9390869140625,
155
+ "learning_rate": 1.616e-05,
156
+ "loss": 11.0077,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.009363196254721498,
161
+ "grad_norm": 1400.2003173828125,
162
+ "learning_rate": 1.696e-05,
163
+ "loss": 10.7138,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.009788796084481566,
168
+ "grad_norm": 880.6416015625,
169
+ "learning_rate": 1.7760000000000003e-05,
170
+ "loss": 10.4564,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.010214395914241635,
175
+ "grad_norm": 888.9507446289062,
176
+ "learning_rate": 1.856e-05,
177
+ "loss": 10.4699,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.010639995744001702,
182
+ "grad_norm": 604.7562255859375,
183
+ "learning_rate": 1.936e-05,
184
+ "loss": 10.5335,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.01106559557376177,
189
+ "grad_norm": 885.2161865234375,
190
+ "learning_rate": 2.016e-05,
191
+ "loss": 10.3258,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.011491195403521838,
196
+ "grad_norm": 689.9547729492188,
197
+ "learning_rate": 2.0960000000000003e-05,
198
+ "loss": 10.3034,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.011916795233281907,
203
+ "grad_norm": 1086.3548583984375,
204
+ "learning_rate": 2.176e-05,
205
+ "loss": 10.121,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.012342395063041975,
210
+ "grad_norm": 728.9247436523438,
211
+ "learning_rate": 2.256e-05,
212
+ "loss": 9.9983,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.012767994892802044,
217
+ "grad_norm": 931.4705200195312,
218
+ "learning_rate": 2.336e-05,
219
+ "loss": 10.1502,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.01319359472256211,
224
+ "grad_norm": 836.438720703125,
225
+ "learning_rate": 2.4160000000000002e-05,
226
+ "loss": 10.0117,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.013619194552322179,
231
+ "grad_norm": 481.8641662597656,
232
+ "learning_rate": 2.496e-05,
233
+ "loss": 10.0033,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.014044794382082247,
238
+ "grad_norm": 368.5486755371094,
239
+ "learning_rate": 2.576e-05,
240
+ "loss": 9.7842,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.014470394211842316,
245
+ "grad_norm": 408.945068359375,
246
+ "learning_rate": 2.6560000000000003e-05,
247
+ "loss": 10.0045,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.014895994041602384,
252
+ "grad_norm": 882.4168701171875,
253
+ "learning_rate": 2.7360000000000002e-05,
254
+ "loss": 9.8133,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.01532159387136245,
259
+ "grad_norm": 688.0091552734375,
260
+ "learning_rate": 2.816e-05,
261
+ "loss": 9.74,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.01574719370112252,
266
+ "grad_norm": 480.2123107910156,
267
+ "learning_rate": 2.8960000000000004e-05,
268
+ "loss": 9.7187,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.01617279353088259,
273
+ "grad_norm": 266.4781799316406,
274
+ "learning_rate": 2.976e-05,
275
+ "loss": 9.4574,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.016598393360642654,
280
+ "grad_norm": 426.8431091308594,
281
+ "learning_rate": 3.056e-05,
282
+ "loss": 9.4476,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.017023993190402723,
287
+ "grad_norm": 507.83984375,
288
+ "learning_rate": 3.136e-05,
289
+ "loss": 9.6252,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.01744959302016279,
294
+ "grad_norm": 345.3815612792969,
295
+ "learning_rate": 3.2160000000000004e-05,
296
+ "loss": 9.4701,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.01787519284992286,
301
+ "grad_norm": 661.6119384765625,
302
+ "learning_rate": 3.296e-05,
303
+ "loss": 9.2308,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.018300792679682928,
308
+ "grad_norm": 249.719970703125,
309
+ "learning_rate": 3.376e-05,
310
+ "loss": 9.2749,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.018726392509442996,
315
+ "grad_norm": 396.6395263671875,
316
+ "learning_rate": 3.456e-05,
317
+ "loss": 9.3583,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.019151992339203065,
322
+ "grad_norm": 317.9398193359375,
323
+ "learning_rate": 3.536000000000001e-05,
324
+ "loss": 9.2281,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.019577592168963133,
329
+ "grad_norm": 237.1824493408203,
330
+ "learning_rate": 3.616e-05,
331
+ "loss": 9.0913,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.0200031919987232,
336
+ "grad_norm": 427.8457336425781,
337
+ "learning_rate": 3.696e-05,
338
+ "loss": 9.0147,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.02042879182848327,
343
+ "grad_norm": 380.43719482421875,
344
+ "learning_rate": 3.776e-05,
345
+ "loss": 8.9519,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.020854391658243338,
350
+ "grad_norm": 222.20193481445312,
351
+ "learning_rate": 3.8560000000000004e-05,
352
+ "loss": 9.0848,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.021279991488003403,
357
+ "grad_norm": 343.4478454589844,
358
+ "learning_rate": 3.936e-05,
359
+ "loss": 8.8757,
360
+ "step": 500
361
+ }
362
+ ],
363
+ "logging_steps": 10,
364
+ "max_steps": 10000000,
365
+ "num_input_tokens_seen": 0,
366
+ "num_train_epochs": 426,
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": 7330212781670400.0,
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 sha256:297139a11e797886df97214381a888b42a0b5caa8afc09face8a71d0e1d36fd7
3
+ size 5201