aixk commited on
Commit
2dbbf2e
·
verified ·
1 Parent(s): de88f0b

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": 4032
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 sha256:975fafac96c03f2a70454e1908da623437d625d74b55ed894bee4c233d5e7eda
3
+ size 483923272
checkpoint-600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80a0eb48f02b948de6da337774e54ccd1164bc26f215f59abc8edfdf3a34af6
3
+ size 245762443
checkpoint-600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1bcddf6b0cceff1ab709db20fff327db0b691cc7c0c12a69976165d29660d89
3
+ size 14645
checkpoint-600/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c387701e3c6b75694916a541e22925d716dec236d09b5afad30d5d233433c0
3
+ size 1383
checkpoint-600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a056f4b96fb707328200b22129ab9ffe3eb670692d665ad056c72923c8aaf4c5
3
+ size 1465
checkpoint-600/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "HFCompatibleHybridTokenizer",
3
+ "vocab_size": 4032,
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": 2.128,
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": 0.035555555555555556,
14
+ "grad_norm": 9809.728515625,
15
+ "learning_rate": 1.9999999999999996e-07,
16
+ "loss": 12.309,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.07111111111111111,
21
+ "grad_norm": 612.39404296875,
22
+ "learning_rate": 1.2e-06,
23
+ "loss": 11.3089,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.10666666666666667,
28
+ "grad_norm": 168.1624755859375,
29
+ "learning_rate": 2.1999999999999997e-06,
30
+ "loss": 10.1099,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.14222222222222222,
35
+ "grad_norm": 132.89761352539062,
36
+ "learning_rate": 3.1999999999999994e-06,
37
+ "loss": 9.7597,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.17777777777777778,
42
+ "grad_norm": 120.04608154296875,
43
+ "learning_rate": 4.2e-06,
44
+ "loss": 9.7068,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.21333333333333335,
49
+ "grad_norm": 74.61504364013672,
50
+ "learning_rate": 5.199999999999999e-06,
51
+ "loss": 9.7336,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.24888888888888888,
56
+ "grad_norm": 108.23493194580078,
57
+ "learning_rate": 6.199999999999999e-06,
58
+ "loss": 9.6298,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.28444444444444444,
63
+ "grad_norm": 179.29026794433594,
64
+ "learning_rate": 7.2e-06,
65
+ "loss": 9.5616,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.32,
70
+ "grad_norm": 1429.0501708984375,
71
+ "learning_rate": 8.2e-06,
72
+ "loss": 9.5532,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.35555555555555557,
77
+ "grad_norm": 1327.430419921875,
78
+ "learning_rate": 9.199999999999998e-06,
79
+ "loss": 9.5756,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.39111111111111113,
84
+ "grad_norm": 1303.9886474609375,
85
+ "learning_rate": 1.02e-05,
86
+ "loss": 9.516,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.4266666666666667,
91
+ "grad_norm": 2209.8125,
92
+ "learning_rate": 1.12e-05,
93
+ "loss": 9.2971,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.4622222222222222,
98
+ "grad_norm": 893.0194702148438,
99
+ "learning_rate": 1.2199999999999998e-05,
100
+ "loss": 9.1314,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.49777777777777776,
105
+ "grad_norm": 1277.308349609375,
106
+ "learning_rate": 1.3199999999999997e-05,
107
+ "loss": 8.9549,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.5333333333333333,
112
+ "grad_norm": 570.9115600585938,
113
+ "learning_rate": 1.4199999999999998e-05,
114
+ "loss": 8.775,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.5688888888888889,
119
+ "grad_norm": 4662.44140625,
120
+ "learning_rate": 1.51e-05,
121
+ "loss": 8.7164,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.6044444444444445,
126
+ "grad_norm": 1919.478759765625,
127
+ "learning_rate": 1.61e-05,
128
+ "loss": 8.7624,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.64,
133
+ "grad_norm": 222.35101318359375,
134
+ "learning_rate": 1.71e-05,
135
+ "loss": 8.5691,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.6755555555555556,
140
+ "grad_norm": 1398.421630859375,
141
+ "learning_rate": 1.81e-05,
142
+ "loss": 8.632,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.7111111111111111,
147
+ "grad_norm": 2069.802001953125,
148
+ "learning_rate": 1.9099999999999997e-05,
149
+ "loss": 8.4041,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.7466666666666667,
154
+ "grad_norm": 1576.723876953125,
155
+ "learning_rate": 2.01e-05,
156
+ "loss": 8.2905,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.7822222222222223,
161
+ "grad_norm": 3814.73388671875,
162
+ "learning_rate": 2.1099999999999998e-05,
163
+ "loss": 8.1529,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.8177777777777778,
168
+ "grad_norm": 900.2994384765625,
169
+ "learning_rate": 2.21e-05,
170
+ "loss": 8.0081,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.8533333333333334,
175
+ "grad_norm": 5148.7197265625,
176
+ "learning_rate": 2.31e-05,
177
+ "loss": 7.8704,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.8888888888888888,
182
+ "grad_norm": 2787.3720703125,
183
+ "learning_rate": 2.3999999999999997e-05,
184
+ "loss": 7.8391,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.9244444444444444,
189
+ "grad_norm": 700.3667602539062,
190
+ "learning_rate": 2.4999999999999998e-05,
191
+ "loss": 7.9066,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.96,
196
+ "grad_norm": 2678.900390625,
197
+ "learning_rate": 2.6e-05,
198
+ "loss": 7.833,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.9955555555555555,
203
+ "grad_norm": 1373.11865234375,
204
+ "learning_rate": 2.6999999999999996e-05,
205
+ "loss": 7.9211,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 1.0284444444444445,
210
+ "grad_norm": 1029.66650390625,
211
+ "learning_rate": 2.8e-05,
212
+ "loss": 7.7977,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 1.064,
217
+ "grad_norm": 964.4992065429688,
218
+ "learning_rate": 2.8999999999999997e-05,
219
+ "loss": 7.5804,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 1.0995555555555556,
224
+ "grad_norm": 2260.938232421875,
225
+ "learning_rate": 2.9999999999999997e-05,
226
+ "loss": 7.4538,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 1.1351111111111112,
231
+ "grad_norm": 1301.302001953125,
232
+ "learning_rate": 3.0999999999999995e-05,
233
+ "loss": 7.3267,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 1.1706666666666667,
238
+ "grad_norm": 3287.134033203125,
239
+ "learning_rate": 3.2e-05,
240
+ "loss": 7.494,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 1.2062222222222223,
245
+ "grad_norm": 3100.998779296875,
246
+ "learning_rate": 3.2999999999999996e-05,
247
+ "loss": 7.3305,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 1.2417777777777779,
252
+ "grad_norm": 6849.7470703125,
253
+ "learning_rate": 3.399999999999999e-05,
254
+ "loss": 7.3779,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 1.2773333333333334,
259
+ "grad_norm": 6482.72119140625,
260
+ "learning_rate": 3.5e-05,
261
+ "loss": 7.3045,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 1.3128888888888888,
266
+ "grad_norm": 1833.2020263671875,
267
+ "learning_rate": 3.5999999999999994e-05,
268
+ "loss": 7.5309,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 1.3484444444444446,
273
+ "grad_norm": 4076.072509765625,
274
+ "learning_rate": 3.7e-05,
275
+ "loss": 7.1969,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 1.384,
280
+ "grad_norm": 4126.76416015625,
281
+ "learning_rate": 3.8e-05,
282
+ "loss": 7.5074,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 1.4195555555555557,
287
+ "grad_norm": 210.43556213378906,
288
+ "learning_rate": 3.9e-05,
289
+ "loss": 7.5414,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 1.455111111111111,
294
+ "grad_norm": 535.0352172851562,
295
+ "learning_rate": 3.9999999999999996e-05,
296
+ "loss": 7.1273,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 1.4906666666666666,
301
+ "grad_norm": 1456.4652099609375,
302
+ "learning_rate": 4.0999999999999994e-05,
303
+ "loss": 7.2036,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 1.5262222222222221,
308
+ "grad_norm": 439.1557922363281,
309
+ "learning_rate": 4.2e-05,
310
+ "loss": 7.0091,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 1.561777777777778,
315
+ "grad_norm": 2724.52392578125,
316
+ "learning_rate": 4.3e-05,
317
+ "loss": 6.9096,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 1.5973333333333333,
322
+ "grad_norm": 836.12451171875,
323
+ "learning_rate": 4.4e-05,
324
+ "loss": 6.8527,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 1.6328888888888888,
329
+ "grad_norm": 574.1064453125,
330
+ "learning_rate": 4.4999999999999996e-05,
331
+ "loss": 6.7544,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 1.6684444444444444,
336
+ "grad_norm": 827.2996215820312,
337
+ "learning_rate": 4.599999999999999e-05,
338
+ "loss": 6.5927,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 1.704,
343
+ "grad_norm": 842.2186279296875,
344
+ "learning_rate": 4.7e-05,
345
+ "loss": 6.5057,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 1.7395555555555555,
350
+ "grad_norm": 527.792236328125,
351
+ "learning_rate": 4.7999999999999994e-05,
352
+ "loss": 6.4396,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.775111111111111,
357
+ "grad_norm": 285.5974426269531,
358
+ "learning_rate": 4.899999999999999e-05,
359
+ "loss": 6.4299,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.8106666666666666,
364
+ "grad_norm": 868.2779541015625,
365
+ "learning_rate": 4.9999999999999996e-05,
366
+ "loss": 6.3956,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.8462222222222222,
371
+ "grad_norm": 336.4075622558594,
372
+ "learning_rate": 5.1e-05,
373
+ "loss": 6.334,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.8817777777777778,
378
+ "grad_norm": 1787.1485595703125,
379
+ "learning_rate": 5.2e-05,
380
+ "loss": 6.2967,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.9173333333333333,
385
+ "grad_norm": 632.3417358398438,
386
+ "learning_rate": 5.2999999999999994e-05,
387
+ "loss": 6.3923,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.952888888888889,
392
+ "grad_norm": 1189.0301513671875,
393
+ "learning_rate": 5.399999999999999e-05,
394
+ "loss": 6.2544,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.9884444444444445,
399
+ "grad_norm": 1932.8629150390625,
400
+ "learning_rate": 5.499999999999999e-05,
401
+ "loss": 6.1686,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 2.021333333333333,
406
+ "grad_norm": 1381.8150634765625,
407
+ "learning_rate": 5.6e-05,
408
+ "loss": 6.1352,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 2.056888888888889,
413
+ "grad_norm": 1371.045654296875,
414
+ "learning_rate": 5.6999999999999996e-05,
415
+ "loss": 6.1076,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 2.0924444444444443,
420
+ "grad_norm": 315.6971435546875,
421
+ "learning_rate": 5.7999999999999994e-05,
422
+ "loss": 5.9693,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 2.128,
427
+ "grad_norm": 914.71923828125,
428
+ "learning_rate": 5.899999999999999e-05,
429
+ "loss": 5.9354,
430
+ "step": 600
431
+ }
432
+ ],
433
+ "logging_steps": 10,
434
+ "max_steps": 50000,
435
+ "num_input_tokens_seen": 0,
436
+ "num_train_epochs": 178,
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": 1.184483419766784e+16,
451
+ "train_batch_size": 8,
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:c694eaf58fbca4c4756e8d649e8e7c7463eb11743717ed4051aef62649027ad8
3
+ size 5201