aixk commited on
Commit
a5f89e5
·
verified ·
1 Parent(s): b356713

Upload folder using huggingface_hub

Browse files
checkpoint-1100/config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "FastHyperNet125mForCausalLM"
4
+ ],
5
+ "dtype": "float32",
6
+ "hidden_size": 768,
7
+ "hyperbolic_dim": 64,
8
+ "intermediate_size": 2048,
9
+ "max_position_embeddings": 512,
10
+ "model_type": "fasthypernet_125m_tagless",
11
+ "num_attention_heads": 12,
12
+ "num_hidden_layers": 16,
13
+ "transformers_version": "5.13.1",
14
+ "use_cache": false,
15
+ "vocab_size": 8192
16
+ }
checkpoint-1100/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-1100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e51e432e0981d9ccf81ed763667cd33f0276718e8df0cc7610e61d864b0cf50
3
+ size 542849784
checkpoint-1100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2780af024eb0245d11350781bc0f355d5b3cb6662bad68751901623ff6e33b98
3
+ size 273342083
checkpoint-1100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed963a9196a939cc5a3e3949eadcdadf8872275bca5c2eba3b3ad014716eac6
3
+ size 14645
checkpoint-1100/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bbdb4f22c6fbdd373958ab6d001cbbd7fb1f97835e80909998ceeed304f36d2
3
+ size 1383
checkpoint-1100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e7142216fbda4f3340ed750a77dae2e1a1bb1d6d02091f1d38985c1967b4e7f
3
+ size 1465
checkpoint-1100/trainer_state.json ADDED
@@ -0,0 +1,804 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.038148745426485636,
6
+ "eval_steps": 500,
7
+ "global_step": 1100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00034680677660441485,
14
+ "grad_norm": 8.286304473876953,
15
+ "learning_rate": 2.6999999999999996e-06,
16
+ "loss": 36.023321533203124,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.0006936135532088297,
21
+ "grad_norm": 5.303624153137207,
22
+ "learning_rate": 5.7e-06,
23
+ "loss": 35.81325988769531,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.0010404203298132447,
28
+ "grad_norm": 14.0803861618042,
29
+ "learning_rate": 8.7e-06,
30
+ "loss": 35.61415100097656,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0013872271064176594,
35
+ "grad_norm": 42.10546875,
36
+ "learning_rate": 1.17e-05,
37
+ "loss": 35.36910400390625,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.0017340338830220744,
42
+ "grad_norm": 43.37276840209961,
43
+ "learning_rate": 1.47e-05,
44
+ "loss": 34.86077880859375,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0020808406596264893,
49
+ "grad_norm": Infinity,
50
+ "learning_rate": 1.7699999999999997e-05,
51
+ "loss": 34.67452697753906,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.002427647436230904,
56
+ "grad_norm": 86.09446716308594,
57
+ "learning_rate": 2.04e-05,
58
+ "loss": 34.29078979492188,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.002774454212835319,
63
+ "grad_norm": 43.50123977661133,
64
+ "learning_rate": 2.34e-05,
65
+ "loss": 33.816766357421876,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0031212609894397335,
70
+ "grad_norm": 104.7258529663086,
71
+ "learning_rate": 2.6399999999999995e-05,
72
+ "loss": 33.36159057617188,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.0034680677660441487,
77
+ "grad_norm": 66.46515655517578,
78
+ "learning_rate": 2.91e-05,
79
+ "loss": 33.181732177734375,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.0038148745426485635,
84
+ "grad_norm": 127.66901397705078,
85
+ "learning_rate": 3.2099999999999994e-05,
86
+ "loss": 32.83320007324219,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.004161681319252979,
91
+ "grad_norm": 71.67156982421875,
92
+ "learning_rate": 3.51e-05,
93
+ "loss": 32.48929138183594,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.004508488095857393,
98
+ "grad_norm": 76.15655517578125,
99
+ "learning_rate": 3.81e-05,
100
+ "loss": 32.10602722167969,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.004855294872461808,
105
+ "grad_norm": 38.65349578857422,
106
+ "learning_rate": 4.11e-05,
107
+ "loss": 31.449526977539062,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.005202101649066222,
112
+ "grad_norm": 59.55622863769531,
113
+ "learning_rate": 4.4099999999999995e-05,
114
+ "loss": 31.01339111328125,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.005548908425670638,
119
+ "grad_norm": 130.26136779785156,
120
+ "learning_rate": 4.709999999999999e-05,
121
+ "loss": 30.92586669921875,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.005895715202275053,
126
+ "grad_norm": 77.2778549194336,
127
+ "learning_rate": 5.01e-05,
128
+ "loss": 30.492510986328124,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.006242521978879467,
133
+ "grad_norm": 29.711563110351562,
134
+ "learning_rate": 5.309999999999999e-05,
135
+ "loss": 29.836746215820312,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.006589328755483882,
140
+ "grad_norm": 29.891956329345703,
141
+ "learning_rate": 5.6099999999999995e-05,
142
+ "loss": 29.291275024414062,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.006936135532088297,
147
+ "grad_norm": 30.56305503845215,
148
+ "learning_rate": 5.91e-05,
149
+ "loss": 29.14805908203125,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.007282942308692712,
154
+ "grad_norm": 29.489208221435547,
155
+ "learning_rate": 6.209999999999999e-05,
156
+ "loss": 28.80553283691406,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.007629749085297127,
161
+ "grad_norm": 37.147377014160156,
162
+ "learning_rate": 6.51e-05,
163
+ "loss": 28.694085693359376,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.007976555861901541,
168
+ "grad_norm": 28.496992111206055,
169
+ "learning_rate": 6.81e-05,
170
+ "loss": 28.166943359375,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.008323362638505957,
175
+ "grad_norm": 29.42328453063965,
176
+ "learning_rate": 7.11e-05,
177
+ "loss": 27.878482055664062,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.008670169415110372,
182
+ "grad_norm": 27.867637634277344,
183
+ "learning_rate": 7.41e-05,
184
+ "loss": 26.99749755859375,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.009016976191714786,
189
+ "grad_norm": 29.695758819580078,
190
+ "learning_rate": 7.709999999999999e-05,
191
+ "loss": 27.208102416992187,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.0093637829683192,
196
+ "grad_norm": 34.605934143066406,
197
+ "learning_rate": 8.01e-05,
198
+ "loss": 26.798681640625,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.009710589744923616,
203
+ "grad_norm": 35.05394744873047,
204
+ "learning_rate": 8.31e-05,
205
+ "loss": 27.192486572265626,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.01005739652152803,
210
+ "grad_norm": 19.137067794799805,
211
+ "learning_rate": 8.609999999999999e-05,
212
+ "loss": 26.89140930175781,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.010404203298132445,
217
+ "grad_norm": 24.543006896972656,
218
+ "learning_rate": 8.879999999999999e-05,
219
+ "loss": 26.167477416992188,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.010751010074736861,
224
+ "grad_norm": 18.849651336669922,
225
+ "learning_rate": 9.18e-05,
226
+ "loss": 26.41388854980469,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.011097816851341275,
231
+ "grad_norm": 21.179908752441406,
232
+ "learning_rate": 9.479999999999999e-05,
233
+ "loss": 26.003546142578124,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.01144462362794569,
238
+ "grad_norm": 19.344528198242188,
239
+ "learning_rate": 9.779999999999999e-05,
240
+ "loss": 26.271051025390626,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.011791430404550106,
245
+ "grad_norm": 19.74913215637207,
246
+ "learning_rate": 0.0001008,
247
+ "loss": 26.064590454101562,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.01213823718115452,
252
+ "grad_norm": 17.638103485107422,
253
+ "learning_rate": 0.00010379999999999999,
254
+ "loss": 25.863119506835936,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.012485043957758934,
259
+ "grad_norm": 24.873981475830078,
260
+ "learning_rate": 0.00010679999999999998,
261
+ "loss": 26.28948059082031,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.01283185073436335,
266
+ "grad_norm": 17.048828125,
267
+ "learning_rate": 0.00010979999999999999,
268
+ "loss": 26.215179443359375,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.013178657510967764,
273
+ "grad_norm": 21.703975677490234,
274
+ "learning_rate": 0.00011279999999999999,
275
+ "loss": 26.152392578125,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.013525464287572179,
280
+ "grad_norm": 22.66498565673828,
281
+ "learning_rate": 0.0001158,
282
+ "loss": 26.0640625,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.013872271064176595,
287
+ "grad_norm": 16.945016860961914,
288
+ "learning_rate": 0.0001188,
289
+ "loss": 26.023715209960937,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.01421907784078101,
294
+ "grad_norm": 27.866268157958984,
295
+ "learning_rate": 0.00012179999999999999,
296
+ "loss": 25.43433380126953,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.014565884617385423,
301
+ "grad_norm": 22.481279373168945,
302
+ "learning_rate": 0.00012479999999999997,
303
+ "loss": 25.464639282226564,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.014912691393989838,
308
+ "grad_norm": 14.993969917297363,
309
+ "learning_rate": 0.0001278,
310
+ "loss": 25.218385314941408,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.015259498170594254,
315
+ "grad_norm": 14.426427841186523,
316
+ "learning_rate": 0.00013079999999999998,
317
+ "loss": 24.94810333251953,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.015606304947198668,
322
+ "grad_norm": 15.592818260192871,
323
+ "learning_rate": 0.0001338,
324
+ "loss": 25.38585662841797,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.015953111723803082,
329
+ "grad_norm": 14.709174156188965,
330
+ "learning_rate": 0.0001368,
331
+ "loss": 24.31098175048828,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.016299918500407497,
336
+ "grad_norm": 13.651994705200195,
337
+ "learning_rate": 0.00013979999999999998,
338
+ "loss": 24.82652893066406,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.016646725277011915,
343
+ "grad_norm": 17.521072387695312,
344
+ "learning_rate": 0.00014279999999999997,
345
+ "loss": 25.121923828125,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.01699353205361633,
350
+ "grad_norm": 13.458234786987305,
351
+ "learning_rate": 0.0001458,
352
+ "loss": 24.447775268554686,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.017340338830220743,
357
+ "grad_norm": 13.57589340209961,
358
+ "learning_rate": 0.00014879999999999998,
359
+ "loss": 24.76665802001953,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.017687145606825157,
364
+ "grad_norm": 12.934654235839844,
365
+ "learning_rate": 0.00015179999999999998,
366
+ "loss": 24.170372009277344,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.018033952383429572,
371
+ "grad_norm": 13.884750366210938,
372
+ "learning_rate": 0.0001548,
373
+ "loss": 24.240016174316406,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.018380759160033986,
378
+ "grad_norm": 13.660422325134277,
379
+ "learning_rate": 0.0001578,
380
+ "loss": 23.897187805175783,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.0187275659366384,
385
+ "grad_norm": 11.849883079528809,
386
+ "learning_rate": 0.0001608,
387
+ "loss": 23.574449157714845,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.019074372713242818,
392
+ "grad_norm": 10.595759391784668,
393
+ "learning_rate": 0.0001638,
394
+ "loss": 23.569731140136717,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.019421179489847232,
399
+ "grad_norm": 12.363926887512207,
400
+ "learning_rate": 0.0001668,
401
+ "loss": 23.617283630371094,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.019767986266451647,
406
+ "grad_norm": 10.968243598937988,
407
+ "learning_rate": 0.00016979999999999998,
408
+ "loss": 23.990586853027345,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.02011479304305606,
413
+ "grad_norm": 12.141168594360352,
414
+ "learning_rate": 0.00017279999999999997,
415
+ "loss": 23.807048034667968,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.020461599819660475,
420
+ "grad_norm": 14.928491592407227,
421
+ "learning_rate": 0.00017579999999999996,
422
+ "loss": 22.980938720703126,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.02080840659626489,
427
+ "grad_norm": 11.39072036743164,
428
+ "learning_rate": 0.00017879999999999998,
429
+ "loss": 23.521900939941407,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.021155213372869307,
434
+ "grad_norm": 10.157258033752441,
435
+ "learning_rate": 0.00018179999999999997,
436
+ "loss": 23.075851440429688,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.021502020149473722,
441
+ "grad_norm": 12.673665046691895,
442
+ "learning_rate": 0.0001848,
443
+ "loss": 23.70465850830078,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.021848826926078136,
448
+ "grad_norm": 11.242607116699219,
449
+ "learning_rate": 0.00018779999999999998,
450
+ "loss": 22.982296752929688,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.02219563370268255,
455
+ "grad_norm": 25.496898651123047,
456
+ "learning_rate": 0.00019079999999999998,
457
+ "loss": 22.516278076171876,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.022542440479286965,
462
+ "grad_norm": 11.215885162353516,
463
+ "learning_rate": 0.0001938,
464
+ "loss": 22.14655456542969,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.02288924725589138,
469
+ "grad_norm": 9.149953842163086,
470
+ "learning_rate": 0.00019679999999999999,
471
+ "loss": 22.114730834960938,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.023236054032495793,
476
+ "grad_norm": 14.604310035705566,
477
+ "learning_rate": 0.0001995,
478
+ "loss": 22.670735168457032,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.02358286080910021,
483
+ "grad_norm": 11.181646347045898,
484
+ "learning_rate": 0.0002025,
485
+ "loss": 22.34198455810547,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.023929667585704625,
490
+ "grad_norm": 10.59487533569336,
491
+ "learning_rate": 0.0002055,
492
+ "loss": 22.268771362304687,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.02427647436230904,
497
+ "grad_norm": 11.758952140808105,
498
+ "learning_rate": 0.00020849999999999997,
499
+ "loss": 21.350621032714844,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.024623281138913454,
504
+ "grad_norm": 18.59368896484375,
505
+ "learning_rate": 0.00021149999999999996,
506
+ "loss": 21.507183837890626,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.02497008791551787,
511
+ "grad_norm": 9.710185050964355,
512
+ "learning_rate": 0.00021449999999999998,
513
+ "loss": 21.502236938476564,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.025316894692122283,
518
+ "grad_norm": 20.68129539489746,
519
+ "learning_rate": 0.00021749999999999997,
520
+ "loss": 21.232615661621093,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.0256637014687267,
525
+ "grad_norm": 9.399124145507812,
526
+ "learning_rate": 0.00022049999999999997,
527
+ "loss": 21.146585083007814,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.026010508245331115,
532
+ "grad_norm": 9.145174026489258,
533
+ "learning_rate": 0.00022349999999999998,
534
+ "loss": 21.06390838623047,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.02635731502193553,
539
+ "grad_norm": 11.161269187927246,
540
+ "learning_rate": 0.00022649999999999998,
541
+ "loss": 20.896176147460938,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.026704121798539943,
546
+ "grad_norm": 8.362421035766602,
547
+ "learning_rate": 0.0002295,
548
+ "loss": 20.884358215332032,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.027050928575144358,
553
+ "grad_norm": 9.504199981689453,
554
+ "learning_rate": 0.00023249999999999999,
555
+ "loss": 20.086947631835937,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.027397735351748772,
560
+ "grad_norm": 8.848526954650879,
561
+ "learning_rate": 0.00023549999999999998,
562
+ "loss": 20.411599731445314,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.02774454212835319,
567
+ "grad_norm": 9.612874984741211,
568
+ "learning_rate": 0.0002385,
569
+ "loss": 20.284182739257812,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.028091348904957604,
574
+ "grad_norm": 8.688453674316406,
575
+ "learning_rate": 0.0002415,
576
+ "loss": 20.024198913574217,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.02843815568156202,
581
+ "grad_norm": 9.779630661010742,
582
+ "learning_rate": 0.0002445,
583
+ "loss": 19.91345977783203,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.028784962458166433,
588
+ "grad_norm": 12.37082576751709,
589
+ "learning_rate": 0.0002472,
590
+ "loss": 19.54875030517578,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.029131769234770847,
595
+ "grad_norm": 8.736369132995605,
596
+ "learning_rate": 0.00025019999999999996,
597
+ "loss": 19.499098205566405,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.02947857601137526,
602
+ "grad_norm": 10.752023696899414,
603
+ "learning_rate": 0.0002532,
604
+ "loss": 19.327198791503907,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.029825382787979676,
609
+ "grad_norm": 9.755398750305176,
610
+ "learning_rate": 0.0002562,
611
+ "loss": 19.291722106933594,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.030172189564584093,
616
+ "grad_norm": 8.066308975219727,
617
+ "learning_rate": 0.00025919999999999996,
618
+ "loss": 18.516694641113283,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.030518996341188508,
623
+ "grad_norm": 8.660676002502441,
624
+ "learning_rate": 0.0002622,
625
+ "loss": 18.70814666748047,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.030865803117792922,
630
+ "grad_norm": 8.439098358154297,
631
+ "learning_rate": 0.0002652,
632
+ "loss": 18.787985229492186,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.031212609894397336,
637
+ "grad_norm": 8.525120735168457,
638
+ "learning_rate": 0.00026819999999999996,
639
+ "loss": 18.356887817382812,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.031559416671001754,
644
+ "grad_norm": 9.237743377685547,
645
+ "learning_rate": 0.0002712,
646
+ "loss": 18.07917022705078,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.031906223447606165,
651
+ "grad_norm": 8.137825965881348,
652
+ "learning_rate": 0.0002742,
653
+ "loss": 18.066172790527343,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.03225303022421058,
658
+ "grad_norm": 20.67136001586914,
659
+ "learning_rate": 0.0002772,
660
+ "loss": 18.19664306640625,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.032599837000814993,
665
+ "grad_norm": 8.68689250946045,
666
+ "learning_rate": 0.0002802,
667
+ "loss": 17.834249877929686,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.03294664377741941,
672
+ "grad_norm": 8.076814651489258,
673
+ "learning_rate": 0.00028319999999999994,
674
+ "loss": 17.645645141601562,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.03329345055402383,
679
+ "grad_norm": 8.278287887573242,
680
+ "learning_rate": 0.00028619999999999996,
681
+ "loss": 17.20880889892578,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.03364025733062824,
686
+ "grad_norm": 8.195657730102539,
687
+ "learning_rate": 0.0002892,
688
+ "loss": 17.02202453613281,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.03398706410723266,
693
+ "grad_norm": 35.29956817626953,
694
+ "learning_rate": 0.00029219999999999995,
695
+ "loss": 17.46351013183594,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.03433387088383707,
700
+ "grad_norm": 14.36285400390625,
701
+ "learning_rate": 0.00029519999999999997,
702
+ "loss": 17.128692626953125,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.034680677660441486,
707
+ "grad_norm": 117.96296691894531,
708
+ "learning_rate": 0.0002979,
709
+ "loss": 16.577227783203124,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.0350274844370459,
714
+ "grad_norm": 33.18951416015625,
715
+ "learning_rate": 0.00029999999932027514,
716
+ "loss": 16.93028106689453,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.035374291213650315,
721
+ "grad_norm": 16.420063018798828,
722
+ "learning_rate": 0.00029999998723627847,
723
+ "loss": 17.68489990234375,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.03572109799025473,
728
+ "grad_norm": 37.7625732421875,
729
+ "learning_rate": 0.0002999999600472873,
730
+ "loss": 17.295022583007814,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.036067904766859143,
735
+ "grad_norm": 32.17815399169922,
736
+ "learning_rate": 0.00029999992266242694,
737
+ "loss": 17.40197296142578,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.03641471154346356,
742
+ "grad_norm": 10.255291938781738,
743
+ "learning_rate": 0.00029999986677395476,
744
+ "loss": 17.136293029785158,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.03676151832006797,
749
+ "grad_norm": 7.522293567657471,
750
+ "learning_rate": 0.0002999997957805001,
751
+ "loss": 16.333123779296876,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.03710832509667239,
756
+ "grad_norm": 7.725010395050049,
757
+ "learning_rate": 0.00029999970968207007,
758
+ "loss": 15.974671936035156,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.0374551318732768,
763
+ "grad_norm": 7.349689483642578,
764
+ "learning_rate": 0.00029999960847867344,
765
+ "loss": 15.520753479003906,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.03780193864988122,
770
+ "grad_norm": 6.910863399505615,
771
+ "learning_rate": 0.00029999949217032024,
772
+ "loss": 15.53778533935547,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.038148745426485636,
777
+ "grad_norm": 7.105229377746582,
778
+ "learning_rate": 0.00029999936075702236,
779
+ "loss": 15.192759704589843,
780
+ "step": 1100
781
+ }
782
+ ],
783
+ "logging_steps": 10,
784
+ "max_steps": 100000,
785
+ "num_input_tokens_seen": 0,
786
+ "num_train_epochs": 4,
787
+ "save_steps": 100,
788
+ "stateful_callbacks": {
789
+ "TrainerControl": {
790
+ "args": {
791
+ "should_epoch_stop": false,
792
+ "should_evaluate": false,
793
+ "should_log": false,
794
+ "should_save": true,
795
+ "should_training_stop": false
796
+ },
797
+ "attributes": {}
798
+ }
799
+ },
800
+ "total_flos": 6841904843980800.0,
801
+ "train_batch_size": 4,
802
+ "trial_name": null,
803
+ "trial_params": null
804
+ }
checkpoint-1100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd241599217f087cf90c5afde8d5857bb2c3234f97a197910829d91c3d8c1f7
3
+ size 5137