aixk commited on
Commit
2bb9792
·
verified ·
1 Parent(s): 1876a5a

Upload folder using huggingface_hub

Browse files
checkpoint-800/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_8k",
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-800/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-800/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db649ed49a28107c049756c4b4e2fd965f4c10bf66ad92e99242507bc60dce40
3
+ size 492474480
checkpoint-800/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba2dfa0d153ce4994eee4911d7278873c9ad0b11a18061dbf075180eb1ac8bfc
3
+ size 251154535
checkpoint-800/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed963f14725f868248ae75a01c291f4d689976e224844e945dc5685fba7babb
3
+ size 14645
checkpoint-800/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b371aef50424900abf761128ca723dc8f63b75a8980fd0159b1a7051572027c9
3
+ size 1383
checkpoint-800/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4053b40973fc26b2d420c03c2e50ce425efb6af6f6b1edbba61a89dd77e91d8f
3
+ size 1465
checkpoint-800/trainer_state.json ADDED
@@ -0,0 +1,594 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.008191206155106339,
6
+ "eval_steps": 500,
7
+ "global_step": 800,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00011701723078723342,
14
+ "grad_norm": 35.62902069091797,
15
+ "learning_rate": 4.8e-07,
16
+ "loss": 8.8196,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.00023403446157446684,
21
+ "grad_norm": 24.634910583496094,
22
+ "learning_rate": 1.0799999999999998e-06,
23
+ "loss": 8.7875,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.00035105169236170026,
28
+ "grad_norm": 75.60508728027344,
29
+ "learning_rate": 1.6799999999999998e-06,
30
+ "loss": 8.7653,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0004680689231489337,
35
+ "grad_norm": 30.914854049682617,
36
+ "learning_rate": 2.2799999999999998e-06,
37
+ "loss": 8.7391,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.000585086153936167,
42
+ "grad_norm": 18.962827682495117,
43
+ "learning_rate": 2.8799999999999995e-06,
44
+ "loss": 8.7296,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.0007021033847234005,
49
+ "grad_norm": 18.906436920166016,
50
+ "learning_rate": 3.4799999999999993e-06,
51
+ "loss": 8.7164,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.0008191206155106339,
56
+ "grad_norm": 13.791674613952637,
57
+ "learning_rate": 4.079999999999999e-06,
58
+ "loss": 8.7195,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.0009361378462978674,
63
+ "grad_norm": 12.664645195007324,
64
+ "learning_rate": 4.679999999999999e-06,
65
+ "loss": 8.7124,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.0010531550770851007,
70
+ "grad_norm": 14.930170059204102,
71
+ "learning_rate": 5.28e-06,
72
+ "loss": 8.711,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.001170172307872334,
77
+ "grad_norm": 13.851901054382324,
78
+ "learning_rate": 5.88e-06,
79
+ "loss": 8.7166,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.00011701723078723342,
84
+ "grad_norm": 13.325752258300781,
85
+ "learning_rate": 6.48e-06,
86
+ "loss": 8.712,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.00023403446157446684,
91
+ "grad_norm": 14.18398666381836,
92
+ "learning_rate": 7.079999999999999e-06,
93
+ "loss": 8.7024,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.00035105169236170026,
98
+ "grad_norm": 15.51286792755127,
99
+ "learning_rate": 7.68e-06,
100
+ "loss": 8.7051,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.0004680689231489337,
105
+ "grad_norm": 24.811758041381836,
106
+ "learning_rate": 8.279999999999999e-06,
107
+ "loss": 8.699,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.000585086153936167,
112
+ "grad_norm": 29.789188385009766,
113
+ "learning_rate": 8.88e-06,
114
+ "loss": 8.7044,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.0007021033847234005,
119
+ "grad_norm": 71.08196258544922,
120
+ "learning_rate": 9.48e-06,
121
+ "loss": 8.6973,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.0008191206155106339,
126
+ "grad_norm": 47.864498138427734,
127
+ "learning_rate": 9.96e-06,
128
+ "loss": 8.7059,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.0009361378462978674,
133
+ "grad_norm": 101.52115631103516,
134
+ "learning_rate": 1.05e-05,
135
+ "loss": 8.6956,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.0010531550770851007,
140
+ "grad_norm": 37.618247985839844,
141
+ "learning_rate": 1.1099999999999999e-05,
142
+ "loss": 8.6901,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.001170172307872334,
147
+ "grad_norm": 17.787864685058594,
148
+ "learning_rate": 1.17e-05,
149
+ "loss": 8.6971,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.0012871895386595677,
154
+ "grad_norm": 14.663663864135742,
155
+ "learning_rate": 1.2299999999999999e-05,
156
+ "loss": 8.6873,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.001404206769446801,
161
+ "grad_norm": 33.8117561340332,
162
+ "learning_rate": 1.2899999999999998e-05,
163
+ "loss": 8.671,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.0015212240002340344,
168
+ "grad_norm": 11.041559219360352,
169
+ "learning_rate": 1.3499999999999998e-05,
170
+ "loss": 8.668,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.0016382412310212678,
175
+ "grad_norm": 14.919255256652832,
176
+ "learning_rate": 1.4099999999999999e-05,
177
+ "loss": 8.6683,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.0017552584618085014,
182
+ "grad_norm": 97.04206085205078,
183
+ "learning_rate": 1.47e-05,
184
+ "loss": 8.6838,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.0018722756925957347,
189
+ "grad_norm": 14.337169647216797,
190
+ "learning_rate": 1.53e-05,
191
+ "loss": 8.6837,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.0019892929233829683,
196
+ "grad_norm": 17.073949813842773,
197
+ "learning_rate": 1.5899999999999997e-05,
198
+ "loss": 8.6706,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.0021063101541702015,
203
+ "grad_norm": 39.961299896240234,
204
+ "learning_rate": 1.6499999999999998e-05,
205
+ "loss": 8.6764,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.002223327384957435,
210
+ "grad_norm": 12.410833358764648,
211
+ "learning_rate": 1.71e-05,
212
+ "loss": 8.6778,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.002340344615744668,
217
+ "grad_norm": 25.247007369995117,
218
+ "learning_rate": 1.7699999999999997e-05,
219
+ "loss": 8.6674,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.002457361846531902,
224
+ "grad_norm": 38.366981506347656,
225
+ "learning_rate": 1.8299999999999998e-05,
226
+ "loss": 8.669,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.0025743790773191354,
231
+ "grad_norm": 13.241379737854004,
232
+ "learning_rate": 1.89e-05,
233
+ "loss": 8.6524,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.0026913963081063685,
238
+ "grad_norm": 21.98308563232422,
239
+ "learning_rate": 1.95e-05,
240
+ "loss": 8.6522,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.002808413538893602,
245
+ "grad_norm": 14.93943977355957,
246
+ "learning_rate": 2.01e-05,
247
+ "loss": 8.6423,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.0029254307696808357,
252
+ "grad_norm": 12.576292991638184,
253
+ "learning_rate": 2.07e-05,
254
+ "loss": 8.6526,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.003042448000468069,
259
+ "grad_norm": 38.080223083496094,
260
+ "learning_rate": 2.1299999999999996e-05,
261
+ "loss": 8.6466,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.0031594652312553024,
266
+ "grad_norm": 13.30930233001709,
267
+ "learning_rate": 2.1899999999999997e-05,
268
+ "loss": 8.634,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.0032764824620425356,
273
+ "grad_norm": 15.718896865844727,
274
+ "learning_rate": 2.2499999999999998e-05,
275
+ "loss": 8.6377,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.003393499692829769,
280
+ "grad_norm": 12.291329383850098,
281
+ "learning_rate": 2.31e-05,
282
+ "loss": 8.6422,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.0035105169236170027,
287
+ "grad_norm": 19.100051879882812,
288
+ "learning_rate": 2.3699999999999997e-05,
289
+ "loss": 8.6247,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.003627534154404236,
294
+ "grad_norm": 18.914691925048828,
295
+ "learning_rate": 2.4299999999999998e-05,
296
+ "loss": 8.6192,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.0037445513851914695,
301
+ "grad_norm": 12.498556137084961,
302
+ "learning_rate": 2.49e-05,
303
+ "loss": 8.6306,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.003861568615978703,
308
+ "grad_norm": 21.343215942382812,
309
+ "learning_rate": 2.55e-05,
310
+ "loss": 8.6215,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.003978585846765937,
315
+ "grad_norm": 19.422046661376953,
316
+ "learning_rate": 2.6099999999999997e-05,
317
+ "loss": 8.6153,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.004095603077553169,
322
+ "grad_norm": 10.735276222229004,
323
+ "learning_rate": 2.6699999999999995e-05,
324
+ "loss": 8.608,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.004212620308340403,
329
+ "grad_norm": 36.70352554321289,
330
+ "learning_rate": 2.7299999999999996e-05,
331
+ "loss": 8.6132,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.0043296375391276365,
336
+ "grad_norm": 25.985517501831055,
337
+ "learning_rate": 2.7899999999999997e-05,
338
+ "loss": 8.6018,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.00444665476991487,
343
+ "grad_norm": 17.778667449951172,
344
+ "learning_rate": 2.8499999999999998e-05,
345
+ "loss": 8.5975,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.004563672000702104,
350
+ "grad_norm": 14.684576988220215,
351
+ "learning_rate": 2.91e-05,
352
+ "loss": 8.6116,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.004680689231489336,
357
+ "grad_norm": 23.132389068603516,
358
+ "learning_rate": 2.97e-05,
359
+ "loss": 8.5998,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.00479770646227657,
364
+ "grad_norm": 26.72182273864746,
365
+ "learning_rate": 3.0299999999999998e-05,
366
+ "loss": 8.5915,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.004914723693063804,
371
+ "grad_norm": 14.388787269592285,
372
+ "learning_rate": 3.09e-05,
373
+ "loss": 8.5993,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.005031740923851037,
378
+ "grad_norm": 22.068796157836914,
379
+ "learning_rate": 3.149999999999999e-05,
380
+ "loss": 8.6038,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.005148758154638271,
385
+ "grad_norm": 16.404687881469727,
386
+ "learning_rate": 3.2099999999999994e-05,
387
+ "loss": 8.596,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.005265775385425504,
392
+ "grad_norm": 16.075613021850586,
393
+ "learning_rate": 3.2699999999999995e-05,
394
+ "loss": 8.5873,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.005382792616212737,
399
+ "grad_norm": 39.547637939453125,
400
+ "learning_rate": 3.3299999999999996e-05,
401
+ "loss": 8.5834,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.005499809846999971,
406
+ "grad_norm": 15.356143951416016,
407
+ "learning_rate": 3.39e-05,
408
+ "loss": 8.5896,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.005616827077787204,
413
+ "grad_norm": 23.20166778564453,
414
+ "learning_rate": 3.45e-05,
415
+ "loss": 8.5958,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.005733844308574438,
420
+ "grad_norm": 16.21513557434082,
421
+ "learning_rate": 3.51e-05,
422
+ "loss": 8.6,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.005850861539361671,
427
+ "grad_norm": 17.083019256591797,
428
+ "learning_rate": 3.5699999999999994e-05,
429
+ "loss": 8.595,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.005967878770148904,
434
+ "grad_norm": 16.49594497680664,
435
+ "learning_rate": 3.6299999999999995e-05,
436
+ "loss": 8.5734,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.006084896000936138,
441
+ "grad_norm": 16.72525978088379,
442
+ "learning_rate": 3.6899999999999996e-05,
443
+ "loss": 8.5819,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.006201913231723371,
448
+ "grad_norm": 44.891204833984375,
449
+ "learning_rate": 3.75e-05,
450
+ "loss": 8.5838,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.006318930462510605,
455
+ "grad_norm": 18.448638916015625,
456
+ "learning_rate": 3.81e-05,
457
+ "loss": 8.5794,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.006435947693297838,
462
+ "grad_norm": 13.73890209197998,
463
+ "learning_rate": 3.87e-05,
464
+ "loss": 8.5781,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.006552964924085071,
469
+ "grad_norm": 13.98898696899414,
470
+ "learning_rate": 3.93e-05,
471
+ "loss": 8.5823,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.006669982154872305,
476
+ "grad_norm": 12.91236686706543,
477
+ "learning_rate": 3.99e-05,
478
+ "loss": 8.574,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.006786999385659538,
483
+ "grad_norm": 32.2785758972168,
484
+ "learning_rate": 4.05e-05,
485
+ "loss": 8.5709,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.006904016616446772,
490
+ "grad_norm": 27.913265228271484,
491
+ "learning_rate": 4.11e-05,
492
+ "loss": 8.569,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.0070210338472340055,
497
+ "grad_norm": 14.550382614135742,
498
+ "learning_rate": 4.17e-05,
499
+ "loss": 8.57,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.007138051078021238,
504
+ "grad_norm": 17.19097137451172,
505
+ "learning_rate": 4.229999999999999e-05,
506
+ "loss": 8.5707,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.007255068308808472,
511
+ "grad_norm": 13.487812042236328,
512
+ "learning_rate": 4.289999999999999e-05,
513
+ "loss": 8.578,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.007372085539595705,
518
+ "grad_norm": 12.733755111694336,
519
+ "learning_rate": 4.3499999999999993e-05,
520
+ "loss": 8.5699,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.007489102770382939,
525
+ "grad_norm": 21.559974670410156,
526
+ "learning_rate": 4.4099999999999995e-05,
527
+ "loss": 8.5696,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.0076061200011701725,
532
+ "grad_norm": 50.315956115722656,
533
+ "learning_rate": 4.4699999999999996e-05,
534
+ "loss": 8.5597,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.007723137231957406,
539
+ "grad_norm": 22.90480613708496,
540
+ "learning_rate": 4.5299999999999997e-05,
541
+ "loss": 8.5601,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.00784015446274464,
546
+ "grad_norm": 17.196212768554688,
547
+ "learning_rate": 4.59e-05,
548
+ "loss": 8.5682,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.007957171693531873,
553
+ "grad_norm": 18.132648468017578,
554
+ "learning_rate": 4.65e-05,
555
+ "loss": 8.5606,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.008074188924319105,
560
+ "grad_norm": 15.65187931060791,
561
+ "learning_rate": 4.709999999999999e-05,
562
+ "loss": 8.5556,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.008191206155106339,
567
+ "grad_norm": 16.17917823791504,
568
+ "learning_rate": 4.7699999999999994e-05,
569
+ "loss": 8.5584,
570
+ "step": 800
571
+ }
572
+ ],
573
+ "logging_steps": 10,
574
+ "max_steps": 1000000,
575
+ "num_input_tokens_seen": 0,
576
+ "num_train_epochs": 12,
577
+ "save_steps": 100,
578
+ "stateful_callbacks": {
579
+ "TrainerControl": {
580
+ "args": {
581
+ "should_epoch_stop": false,
582
+ "should_evaluate": false,
583
+ "should_log": false,
584
+ "should_save": true,
585
+ "should_training_stop": false
586
+ },
587
+ "attributes": {}
588
+ }
589
+ },
590
+ "total_flos": 1.08946582142976e+16,
591
+ "train_batch_size": 8,
592
+ "trial_name": null,
593
+ "trial_params": null
594
+ }
checkpoint-800/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7166b289221788c0b72cfb611814e5c1b0051dfd5cc0c2a27223317e1d329da
3
+ size 5201
checkpoint-800/vocab_multisense_8k.json ADDED
The diff for this file is too large to render. See raw diff