Fill-Mask
Transformers
PyTorch
English
bert
Inference Endpoints
sequoiaandrade commited on
Commit
9982f4a
·
1 Parent(s): 71e249b

Upload SafeAeroBERT files

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.23.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bae74914920b452d71e40aadcab35331f74b320cf51e9c2b55082954b42eb89
3
+ size 1554433
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9154208c846c82d1c5f71a458961aa6d9645432eb51b7a80dd55c9cc21697f59
3
+ size 438128811
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b7bf20eb436b3197418c8b18cde94c14592eda2d8826cc6ffe4c4e48eba4cbb
3
+ size 16543
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df0168a751b1257361283b5aa0c288d7c712011edfd861c618859611a2278ec
3
+ size 559
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8642e2ea00a020f1667e4c75ffeb51b55a74217527808f110fd5e8eb1a30a72
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "bert-base-uncased",
7
+ "pad_token": "[PAD]",
8
+ "padding": "max_length",
9
+ "return_special_tokens_mask": true,
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "truncation": true,
16
+ "unk_token": "[UNK]"
17
+ }
trainer_state.json ADDED
@@ -0,0 +1,796 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.187168922895821,
5
+ "global_step": 13005,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 9.986209216279854e-06,
13
+ "loss": 1.5736,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 9.974100235452405e-06,
19
+ "loss": 2.2457,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 9.961823074335689e-06,
25
+ "loss": 1.5859,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.07,
30
+ "learning_rate": 9.948705011772622e-06,
31
+ "loss": 1.728,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.08,
36
+ "learning_rate": 9.938109653548606e-06,
37
+ "loss": 1.7661,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.1,
42
+ "learning_rate": 9.927009754456779e-06,
43
+ "loss": 2.3678209948440125e+23,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "learning_rate": 9.910191725529768e-06,
49
+ "loss": 0.0,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 0.13,
54
+ "learning_rate": 9.893373696602759e-06,
55
+ "loss": 0.0,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 0.15,
60
+ "learning_rate": 9.876555667675748e-06,
61
+ "loss": 0.0,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 0.17,
66
+ "learning_rate": 9.85973763874874e-06,
67
+ "loss": 0.0,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 0.18,
72
+ "learning_rate": 9.84291960982173e-06,
73
+ "loss": 0.0,
74
+ "step": 1100
75
+ },
76
+ {
77
+ "epoch": 0.2,
78
+ "learning_rate": 9.826101580894721e-06,
79
+ "loss": 0.0,
80
+ "step": 1200
81
+ },
82
+ {
83
+ "epoch": 0.22,
84
+ "learning_rate": 9.80928355196771e-06,
85
+ "loss": 0.0,
86
+ "step": 1300
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "learning_rate": 9.792465523040701e-06,
91
+ "loss": 0.0,
92
+ "step": 1400
93
+ },
94
+ {
95
+ "epoch": 0.25,
96
+ "learning_rate": 9.77564749411369e-06,
97
+ "loss": 0.0,
98
+ "step": 1500
99
+ },
100
+ {
101
+ "epoch": 0.27,
102
+ "learning_rate": 9.758829465186681e-06,
103
+ "loss": 0.0,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "epoch": 0.29,
108
+ "learning_rate": 9.74201143625967e-06,
109
+ "loss": 0.0,
110
+ "step": 1700
111
+ },
112
+ {
113
+ "epoch": 0.3,
114
+ "learning_rate": 9.725193407332661e-06,
115
+ "loss": 0.0,
116
+ "step": 1800
117
+ },
118
+ {
119
+ "epoch": 0.32,
120
+ "learning_rate": 9.70837537840565e-06,
121
+ "loss": 0.0,
122
+ "step": 1900
123
+ },
124
+ {
125
+ "epoch": 0.34,
126
+ "learning_rate": 9.691557349478641e-06,
127
+ "loss": 0.0,
128
+ "step": 2000
129
+ },
130
+ {
131
+ "epoch": 0.35,
132
+ "learning_rate": 9.674739320551632e-06,
133
+ "loss": 0.0,
134
+ "step": 2100
135
+ },
136
+ {
137
+ "epoch": 0.37,
138
+ "learning_rate": 9.657921291624623e-06,
139
+ "loss": 0.0,
140
+ "step": 2200
141
+ },
142
+ {
143
+ "epoch": 0.39,
144
+ "learning_rate": 9.641103262697614e-06,
145
+ "loss": 0.0,
146
+ "step": 2300
147
+ },
148
+ {
149
+ "epoch": 0.4,
150
+ "learning_rate": 9.624285233770603e-06,
151
+ "loss": 0.0,
152
+ "step": 2400
153
+ },
154
+ {
155
+ "epoch": 0.42,
156
+ "learning_rate": 9.607467204843594e-06,
157
+ "loss": 0.0,
158
+ "step": 2500
159
+ },
160
+ {
161
+ "epoch": 0.44,
162
+ "learning_rate": 9.590649175916583e-06,
163
+ "loss": 0.0,
164
+ "step": 2600
165
+ },
166
+ {
167
+ "epoch": 0.45,
168
+ "learning_rate": 9.573831146989574e-06,
169
+ "loss": 0.0,
170
+ "step": 2700
171
+ },
172
+ {
173
+ "epoch": 0.47,
174
+ "learning_rate": 9.557013118062563e-06,
175
+ "loss": 0.0,
176
+ "step": 2800
177
+ },
178
+ {
179
+ "epoch": 0.49,
180
+ "learning_rate": 9.540195089135554e-06,
181
+ "loss": 0.0,
182
+ "step": 2900
183
+ },
184
+ {
185
+ "epoch": 0.5,
186
+ "learning_rate": 9.523377060208543e-06,
187
+ "loss": 0.0,
188
+ "step": 3000
189
+ },
190
+ {
191
+ "epoch": 0.52,
192
+ "learning_rate": 9.506559031281534e-06,
193
+ "loss": 0.0,
194
+ "step": 3100
195
+ },
196
+ {
197
+ "epoch": 0.54,
198
+ "learning_rate": 9.489741002354525e-06,
199
+ "loss": 0.0,
200
+ "step": 3200
201
+ },
202
+ {
203
+ "epoch": 0.55,
204
+ "learning_rate": 9.472922973427516e-06,
205
+ "loss": 0.0,
206
+ "step": 3300
207
+ },
208
+ {
209
+ "epoch": 0.57,
210
+ "learning_rate": 9.456104944500505e-06,
211
+ "loss": 0.0,
212
+ "step": 3400
213
+ },
214
+ {
215
+ "epoch": 0.59,
216
+ "learning_rate": 9.439286915573496e-06,
217
+ "loss": 0.0,
218
+ "step": 3500
219
+ },
220
+ {
221
+ "epoch": 0.61,
222
+ "learning_rate": 9.422468886646485e-06,
223
+ "loss": 0.0,
224
+ "step": 3600
225
+ },
226
+ {
227
+ "epoch": 0.62,
228
+ "learning_rate": 9.405650857719476e-06,
229
+ "loss": 0.0,
230
+ "step": 3700
231
+ },
232
+ {
233
+ "epoch": 0.64,
234
+ "learning_rate": 9.388832828792467e-06,
235
+ "loss": 0.0,
236
+ "step": 3800
237
+ },
238
+ {
239
+ "epoch": 0.66,
240
+ "learning_rate": 9.372014799865456e-06,
241
+ "loss": 0.0,
242
+ "step": 3900
243
+ },
244
+ {
245
+ "epoch": 0.67,
246
+ "learning_rate": 9.355196770938447e-06,
247
+ "loss": 0.0,
248
+ "step": 4000
249
+ },
250
+ {
251
+ "epoch": 0.69,
252
+ "learning_rate": 9.338378742011436e-06,
253
+ "loss": 0.0,
254
+ "step": 4100
255
+ },
256
+ {
257
+ "epoch": 0.71,
258
+ "learning_rate": 9.321560713084427e-06,
259
+ "loss": 0.0,
260
+ "step": 4200
261
+ },
262
+ {
263
+ "epoch": 0.72,
264
+ "learning_rate": 9.304742684157418e-06,
265
+ "loss": 0.0,
266
+ "step": 4300
267
+ },
268
+ {
269
+ "epoch": 0.74,
270
+ "learning_rate": 9.287924655230409e-06,
271
+ "loss": 0.0,
272
+ "step": 4400
273
+ },
274
+ {
275
+ "epoch": 0.76,
276
+ "learning_rate": 9.271106626303398e-06,
277
+ "loss": 0.0,
278
+ "step": 4500
279
+ },
280
+ {
281
+ "epoch": 0.77,
282
+ "learning_rate": 9.254288597376389e-06,
283
+ "loss": 0.0,
284
+ "step": 4600
285
+ },
286
+ {
287
+ "epoch": 0.79,
288
+ "learning_rate": 9.237470568449378e-06,
289
+ "loss": 0.0,
290
+ "step": 4700
291
+ },
292
+ {
293
+ "epoch": 0.81,
294
+ "learning_rate": 9.220652539522369e-06,
295
+ "loss": 0.0,
296
+ "step": 4800
297
+ },
298
+ {
299
+ "epoch": 0.82,
300
+ "learning_rate": 9.203834510595358e-06,
301
+ "loss": 0.0,
302
+ "step": 4900
303
+ },
304
+ {
305
+ "epoch": 0.84,
306
+ "learning_rate": 9.187016481668349e-06,
307
+ "loss": 0.0,
308
+ "step": 5000
309
+ },
310
+ {
311
+ "epoch": 0.86,
312
+ "learning_rate": 9.170198452741338e-06,
313
+ "loss": 0.0,
314
+ "step": 5100
315
+ },
316
+ {
317
+ "epoch": 0.87,
318
+ "learning_rate": 9.153380423814329e-06,
319
+ "loss": 0.0,
320
+ "step": 5200
321
+ },
322
+ {
323
+ "epoch": 0.89,
324
+ "learning_rate": 9.13656239488732e-06,
325
+ "loss": 0.0,
326
+ "step": 5300
327
+ },
328
+ {
329
+ "epoch": 0.91,
330
+ "learning_rate": 9.119744365960311e-06,
331
+ "loss": 0.0,
332
+ "step": 5400
333
+ },
334
+ {
335
+ "epoch": 0.92,
336
+ "learning_rate": 9.102926337033302e-06,
337
+ "loss": 0.0,
338
+ "step": 5500
339
+ },
340
+ {
341
+ "epoch": 0.94,
342
+ "learning_rate": 9.086108308106291e-06,
343
+ "loss": 0.0,
344
+ "step": 5600
345
+ },
346
+ {
347
+ "epoch": 0.96,
348
+ "learning_rate": 9.069290279179282e-06,
349
+ "loss": 0.0,
350
+ "step": 5700
351
+ },
352
+ {
353
+ "epoch": 0.98,
354
+ "learning_rate": 9.052472250252271e-06,
355
+ "loss": 0.0,
356
+ "step": 5800
357
+ },
358
+ {
359
+ "epoch": 0.99,
360
+ "learning_rate": 9.035654221325262e-06,
361
+ "loss": 0.0,
362
+ "step": 5900
363
+ },
364
+ {
365
+ "epoch": 1.01,
366
+ "learning_rate": 9.018836192398251e-06,
367
+ "loss": 0.0,
368
+ "step": 6000
369
+ },
370
+ {
371
+ "epoch": 1.03,
372
+ "learning_rate": 9.002018163471242e-06,
373
+ "loss": 0.0,
374
+ "step": 6100
375
+ },
376
+ {
377
+ "epoch": 1.04,
378
+ "learning_rate": 8.985200134544231e-06,
379
+ "loss": 0.0,
380
+ "step": 6200
381
+ },
382
+ {
383
+ "epoch": 1.06,
384
+ "learning_rate": 8.968382105617222e-06,
385
+ "loss": 0.0,
386
+ "step": 6300
387
+ },
388
+ {
389
+ "epoch": 1.08,
390
+ "learning_rate": 8.951564076690213e-06,
391
+ "loss": 0.0,
392
+ "step": 6400
393
+ },
394
+ {
395
+ "epoch": 1.09,
396
+ "learning_rate": 8.934746047763204e-06,
397
+ "loss": 0.0,
398
+ "step": 6500
399
+ },
400
+ {
401
+ "epoch": 1.11,
402
+ "learning_rate": 8.917928018836193e-06,
403
+ "loss": 0.0,
404
+ "step": 6600
405
+ },
406
+ {
407
+ "epoch": 1.13,
408
+ "learning_rate": 8.901109989909184e-06,
409
+ "loss": 0.0,
410
+ "step": 6700
411
+ },
412
+ {
413
+ "epoch": 1.14,
414
+ "learning_rate": 8.884291960982173e-06,
415
+ "loss": 0.0,
416
+ "step": 6800
417
+ },
418
+ {
419
+ "epoch": 1.16,
420
+ "learning_rate": 8.867473932055164e-06,
421
+ "loss": 0.0,
422
+ "step": 6900
423
+ },
424
+ {
425
+ "epoch": 1.18,
426
+ "learning_rate": 8.850655903128153e-06,
427
+ "loss": 0.0,
428
+ "step": 7000
429
+ },
430
+ {
431
+ "epoch": 1.19,
432
+ "learning_rate": 8.833837874201144e-06,
433
+ "loss": 0.0,
434
+ "step": 7100
435
+ },
436
+ {
437
+ "epoch": 1.21,
438
+ "learning_rate": 8.817019845274135e-06,
439
+ "loss": 0.0,
440
+ "step": 7200
441
+ },
442
+ {
443
+ "epoch": 1.23,
444
+ "learning_rate": 8.800201816347124e-06,
445
+ "loss": 0.0,
446
+ "step": 7300
447
+ },
448
+ {
449
+ "epoch": 1.24,
450
+ "learning_rate": 8.783383787420115e-06,
451
+ "loss": 0.0,
452
+ "step": 7400
453
+ },
454
+ {
455
+ "epoch": 1.26,
456
+ "learning_rate": 8.766565758493106e-06,
457
+ "loss": 0.0,
458
+ "step": 7500
459
+ },
460
+ {
461
+ "epoch": 1.28,
462
+ "learning_rate": 8.749747729566097e-06,
463
+ "loss": 0.0,
464
+ "step": 7600
465
+ },
466
+ {
467
+ "epoch": 1.29,
468
+ "learning_rate": 8.732929700639086e-06,
469
+ "loss": 0.0,
470
+ "step": 7700
471
+ },
472
+ {
473
+ "epoch": 1.31,
474
+ "learning_rate": 8.716111671712077e-06,
475
+ "loss": 0.0,
476
+ "step": 7800
477
+ },
478
+ {
479
+ "epoch": 1.33,
480
+ "learning_rate": 8.699293642785066e-06,
481
+ "loss": 0.0,
482
+ "step": 7900
483
+ },
484
+ {
485
+ "epoch": 1.35,
486
+ "learning_rate": 8.682475613858057e-06,
487
+ "loss": 0.0,
488
+ "step": 8000
489
+ },
490
+ {
491
+ "epoch": 1.36,
492
+ "learning_rate": 8.665657584931046e-06,
493
+ "loss": 0.0,
494
+ "step": 8100
495
+ },
496
+ {
497
+ "epoch": 1.38,
498
+ "learning_rate": 8.648839556004037e-06,
499
+ "loss": 0.0,
500
+ "step": 8200
501
+ },
502
+ {
503
+ "epoch": 1.4,
504
+ "learning_rate": 8.632021527077026e-06,
505
+ "loss": 0.0,
506
+ "step": 8300
507
+ },
508
+ {
509
+ "epoch": 1.41,
510
+ "learning_rate": 8.615203498150017e-06,
511
+ "loss": 0.0,
512
+ "step": 8400
513
+ },
514
+ {
515
+ "epoch": 1.43,
516
+ "learning_rate": 8.598385469223008e-06,
517
+ "loss": 0.0,
518
+ "step": 8500
519
+ },
520
+ {
521
+ "epoch": 1.45,
522
+ "learning_rate": 8.581567440295999e-06,
523
+ "loss": 0.0,
524
+ "step": 8600
525
+ },
526
+ {
527
+ "epoch": 1.46,
528
+ "learning_rate": 8.564749411368988e-06,
529
+ "loss": 0.0,
530
+ "step": 8700
531
+ },
532
+ {
533
+ "epoch": 1.48,
534
+ "learning_rate": 8.547931382441979e-06,
535
+ "loss": 0.0,
536
+ "step": 8800
537
+ },
538
+ {
539
+ "epoch": 1.5,
540
+ "learning_rate": 8.53111335351497e-06,
541
+ "loss": 0.0,
542
+ "step": 8900
543
+ },
544
+ {
545
+ "epoch": 1.51,
546
+ "learning_rate": 8.514295324587959e-06,
547
+ "loss": 0.0,
548
+ "step": 9000
549
+ },
550
+ {
551
+ "epoch": 1.53,
552
+ "learning_rate": 8.49747729566095e-06,
553
+ "loss": 0.0,
554
+ "step": 9100
555
+ },
556
+ {
557
+ "epoch": 1.55,
558
+ "learning_rate": 8.480659266733939e-06,
559
+ "loss": 0.0,
560
+ "step": 9200
561
+ },
562
+ {
563
+ "epoch": 1.56,
564
+ "learning_rate": 8.46384123780693e-06,
565
+ "loss": 0.0,
566
+ "step": 9300
567
+ },
568
+ {
569
+ "epoch": 1.58,
570
+ "learning_rate": 8.447023208879919e-06,
571
+ "loss": 0.0,
572
+ "step": 9400
573
+ },
574
+ {
575
+ "epoch": 1.6,
576
+ "learning_rate": 8.43020517995291e-06,
577
+ "loss": 0.0,
578
+ "step": 9500
579
+ },
580
+ {
581
+ "epoch": 1.61,
582
+ "learning_rate": 8.413387151025901e-06,
583
+ "loss": 0.0,
584
+ "step": 9600
585
+ },
586
+ {
587
+ "epoch": 1.63,
588
+ "learning_rate": 8.396569122098892e-06,
589
+ "loss": 0.0,
590
+ "step": 9700
591
+ },
592
+ {
593
+ "epoch": 1.65,
594
+ "learning_rate": 8.379751093171881e-06,
595
+ "loss": 0.0,
596
+ "step": 9800
597
+ },
598
+ {
599
+ "epoch": 1.66,
600
+ "learning_rate": 8.362933064244872e-06,
601
+ "loss": 0.0,
602
+ "step": 9900
603
+ },
604
+ {
605
+ "epoch": 1.68,
606
+ "learning_rate": 8.346115035317861e-06,
607
+ "loss": 0.0,
608
+ "step": 10000
609
+ },
610
+ {
611
+ "epoch": 1.7,
612
+ "learning_rate": 8.329297006390852e-06,
613
+ "loss": 0.0,
614
+ "step": 10100
615
+ },
616
+ {
617
+ "epoch": 1.72,
618
+ "learning_rate": 8.312478977463841e-06,
619
+ "loss": 0.0,
620
+ "step": 10200
621
+ },
622
+ {
623
+ "epoch": 1.73,
624
+ "learning_rate": 8.295660948536832e-06,
625
+ "loss": 0.0,
626
+ "step": 10300
627
+ },
628
+ {
629
+ "epoch": 1.75,
630
+ "learning_rate": 8.278842919609821e-06,
631
+ "loss": 0.0,
632
+ "step": 10400
633
+ },
634
+ {
635
+ "epoch": 1.77,
636
+ "learning_rate": 8.262024890682812e-06,
637
+ "loss": 0.0,
638
+ "step": 10500
639
+ },
640
+ {
641
+ "epoch": 1.78,
642
+ "learning_rate": 8.245206861755803e-06,
643
+ "loss": 0.0,
644
+ "step": 10600
645
+ },
646
+ {
647
+ "epoch": 1.8,
648
+ "learning_rate": 8.228388832828794e-06,
649
+ "loss": 0.0,
650
+ "step": 10700
651
+ },
652
+ {
653
+ "epoch": 1.82,
654
+ "learning_rate": 8.211570803901785e-06,
655
+ "loss": 0.0,
656
+ "step": 10800
657
+ },
658
+ {
659
+ "epoch": 1.83,
660
+ "learning_rate": 8.194752774974774e-06,
661
+ "loss": 0.0,
662
+ "step": 10900
663
+ },
664
+ {
665
+ "epoch": 1.85,
666
+ "learning_rate": 8.177934746047765e-06,
667
+ "loss": 0.0,
668
+ "step": 11000
669
+ },
670
+ {
671
+ "epoch": 1.87,
672
+ "learning_rate": 8.161116717120754e-06,
673
+ "loss": 0.0,
674
+ "step": 11100
675
+ },
676
+ {
677
+ "epoch": 1.88,
678
+ "learning_rate": 8.144298688193745e-06,
679
+ "loss": 0.0,
680
+ "step": 11200
681
+ },
682
+ {
683
+ "epoch": 1.9,
684
+ "learning_rate": 8.127480659266734e-06,
685
+ "loss": 0.0,
686
+ "step": 11300
687
+ },
688
+ {
689
+ "epoch": 1.92,
690
+ "learning_rate": 8.110662630339725e-06,
691
+ "loss": 0.0,
692
+ "step": 11400
693
+ },
694
+ {
695
+ "epoch": 1.93,
696
+ "learning_rate": 8.093844601412714e-06,
697
+ "loss": 0.0,
698
+ "step": 11500
699
+ },
700
+ {
701
+ "epoch": 1.95,
702
+ "learning_rate": 8.077026572485705e-06,
703
+ "loss": 0.0,
704
+ "step": 11600
705
+ },
706
+ {
707
+ "epoch": 1.97,
708
+ "learning_rate": 8.060208543558696e-06,
709
+ "loss": 0.0,
710
+ "step": 11700
711
+ },
712
+ {
713
+ "epoch": 1.98,
714
+ "learning_rate": 8.043390514631687e-06,
715
+ "loss": 0.0,
716
+ "step": 11800
717
+ },
718
+ {
719
+ "epoch": 2.0,
720
+ "learning_rate": 8.026572485704676e-06,
721
+ "loss": 0.0,
722
+ "step": 11900
723
+ },
724
+ {
725
+ "epoch": 2.02,
726
+ "learning_rate": 8.009754456777667e-06,
727
+ "loss": 0.0,
728
+ "step": 12000
729
+ },
730
+ {
731
+ "epoch": 2.03,
732
+ "learning_rate": 7.992936427850656e-06,
733
+ "loss": 0.0,
734
+ "step": 12100
735
+ },
736
+ {
737
+ "epoch": 2.05,
738
+ "learning_rate": 7.976118398923647e-06,
739
+ "loss": 0.0,
740
+ "step": 12200
741
+ },
742
+ {
743
+ "epoch": 2.07,
744
+ "learning_rate": 7.959300369996638e-06,
745
+ "loss": 0.0,
746
+ "step": 12300
747
+ },
748
+ {
749
+ "epoch": 2.09,
750
+ "learning_rate": 7.942482341069627e-06,
751
+ "loss": 0.0,
752
+ "step": 12400
753
+ },
754
+ {
755
+ "epoch": 2.1,
756
+ "learning_rate": 7.925664312142618e-06,
757
+ "loss": 0.0,
758
+ "step": 12500
759
+ },
760
+ {
761
+ "epoch": 2.12,
762
+ "learning_rate": 7.908846283215607e-06,
763
+ "loss": 0.0,
764
+ "step": 12600
765
+ },
766
+ {
767
+ "epoch": 2.14,
768
+ "learning_rate": 7.892028254288598e-06,
769
+ "loss": 0.0,
770
+ "step": 12700
771
+ },
772
+ {
773
+ "epoch": 2.15,
774
+ "learning_rate": 7.875210225361589e-06,
775
+ "loss": 0.0,
776
+ "step": 12800
777
+ },
778
+ {
779
+ "epoch": 2.17,
780
+ "learning_rate": 7.85839219643458e-06,
781
+ "loss": 0.0,
782
+ "step": 12900
783
+ },
784
+ {
785
+ "epoch": 2.19,
786
+ "learning_rate": 7.841574167507569e-06,
787
+ "loss": 0.0,
788
+ "step": 13000
789
+ }
790
+ ],
791
+ "max_steps": 59460,
792
+ "num_train_epochs": 10,
793
+ "total_flos": 1.314423778738176e+18,
794
+ "trial_name": null,
795
+ "trial_params": null
796
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef65b045ad4b2dc92fbc98d274f27e0862642b5ac670c481855351ab61a2199
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff