speech-timer / training.log
File size: 29,118 Bytes
e107dad

69f5bca









































































































































































































































































































e107dad
69f5bca



e107dad

















































































































































69f5bca
e107dad


69f5bca

6d21fd2

e107dad






6d21fd2
e107dad



6d21fd2
e107dad
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
2021-11-14 01:12:49,647 ----------------------------------------------------------------------------------------------------
2021-11-14 01:12:49,648 Model: "SequenceTagger(
  (embeddings): TransformerWordEmbeddings(
    (model): CamembertModel(
      (embeddings): RobertaEmbeddings(
        (word_embeddings): Embedding(32005, 768, padding_idx=1)
        (position_embeddings): Embedding(514, 768, padding_idx=1)
        (token_type_embeddings): Embedding(1, 768)
        (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.1, inplace=False)
      )
      (encoder): RobertaEncoder(
        (layer): ModuleList(
          (0): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (1): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (2): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (3): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (4): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (5): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (6): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (7): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (8): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (9): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (10): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (11): RobertaLayer(
            (attention): RobertaAttention(
              (self): RobertaSelfAttention(
                (query): Linear(in_features=768, out_features=768, bias=True)
                (key): Linear(in_features=768, out_features=768, bias=True)
                (value): Linear(in_features=768, out_features=768, bias=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
              (output): RobertaSelfOutput(
                (dense): Linear(in_features=768, out_features=768, bias=True)
                (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
                (dropout): Dropout(p=0.1, inplace=False)
              )
            )
            (intermediate): RobertaIntermediate(
              (dense): Linear(in_features=768, out_features=3072, bias=True)
            )
            (output): RobertaOutput(
              (dense): Linear(in_features=3072, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
        )
      )
      (pooler): RobertaPooler(
        (dense): Linear(in_features=768, out_features=768, bias=True)
        (activation): Tanh()
      )
    )
  )
  (word_dropout): WordDropout(p=0.05)
  (locked_dropout): LockedDropout(p=0.5)
  (embedding2nn): Linear(in_features=1536, out_features=1536, bias=True)
  (linear): Linear(in_features=1536, out_features=16, bias=True)
  (beta): 1.0
  (weights): None
  (weight_tensor) None
)"
2021-11-14 01:12:49,649 ----------------------------------------------------------------------------------------------------
2021-11-14 01:12:49,649 Corpus: "Corpus: 56700 train + 6300 dev + 7000 test sentences"
2021-11-14 01:12:49,650 ----------------------------------------------------------------------------------------------------
2021-11-14 01:12:49,650 Parameters:
2021-11-14 01:12:49,650  - learning_rate: "5e-05"
2021-11-14 01:12:49,651  - mini_batch_size: "64"
2021-11-14 01:12:49,651  - patience: "3"
2021-11-14 01:12:49,652  - anneal_factor: "0.5"
2021-11-14 01:12:49,652  - max_epochs: "8"
2021-11-14 01:12:49,653  - shuffle: "True"
2021-11-14 01:12:49,653  - train_with_dev: "False"
2021-11-14 01:12:49,654  - batch_growth_annealing: "False"
2021-11-14 01:12:49,654 ----------------------------------------------------------------------------------------------------
2021-11-14 01:12:49,655 Model training base path: "training/flair_ner/14112021_011130"
2021-11-14 01:12:49,656 ----------------------------------------------------------------------------------------------------
2021-11-14 01:12:49,656 Device: cuda
2021-11-14 01:12:49,657 ----------------------------------------------------------------------------------------------------
2021-11-14 01:12:49,657 Embeddings storage mode: cpu
2021-11-14 01:12:49,659 ----------------------------------------------------------------------------------------------------
2021-11-14 01:13:08,832 epoch 1 - iter 88/886 - loss 0.98596606 - samples/sec: 293.89 - lr: 0.000050
2021-11-14 01:13:28,224 epoch 1 - iter 176/886 - loss 0.56674940 - samples/sec: 290.55 - lr: 0.000050
2021-11-14 01:13:46,801 epoch 1 - iter 264/886 - loss 0.42609266 - samples/sec: 303.28 - lr: 0.000050
2021-11-14 01:14:05,497 epoch 1 - iter 352/886 - loss 0.35537700 - samples/sec: 301.36 - lr: 0.000050
2021-11-14 01:14:24,349 epoch 1 - iter 440/886 - loss 0.31377922 - samples/sec: 298.86 - lr: 0.000050
2021-11-14 01:14:43,031 epoch 1 - iter 528/886 - loss 0.28429453 - samples/sec: 301.58 - lr: 0.000050
2021-11-14 01:15:02,142 epoch 1 - iter 616/886 - loss 0.27880202 - samples/sec: 294.85 - lr: 0.000050
2021-11-14 01:15:20,814 epoch 1 - iter 704/886 - loss 0.26046120 - samples/sec: 301.80 - lr: 0.000050
2021-11-14 01:15:39,918 epoch 1 - iter 792/886 - loss 0.24399388 - samples/sec: 295.02 - lr: 0.000050
2021-11-14 01:15:58,554 epoch 1 - iter 880/886 - loss 0.23065481 - samples/sec: 302.35 - lr: 0.000050
2021-11-14 01:15:59,827 ----------------------------------------------------------------------------------------------------
2021-11-14 01:15:59,828 EPOCH 1 done: loss 0.2298 - lr 0.0000500
2021-11-14 01:16:14,731 DEV : loss 0.0016565551050007343 - f1-score (micro avg)  0.9988
2021-11-14 01:16:14,821 BAD EPOCHS (no improvement): 0
2021-11-14 01:16:14,821 saving best model
2021-11-14 01:16:15,220 ----------------------------------------------------------------------------------------------------
2021-11-14 01:16:34,035 epoch 2 - iter 88/886 - loss 0.11443562 - samples/sec: 299.51 - lr: 0.000050
2021-11-14 01:16:52,711 epoch 2 - iter 176/886 - loss 0.11391112 - samples/sec: 301.72 - lr: 0.000050
2021-11-14 01:17:11,410 epoch 2 - iter 264/886 - loss 0.11275449 - samples/sec: 301.34 - lr: 0.000050
2021-11-14 01:17:30,059 epoch 2 - iter 352/886 - loss 0.11148830 - samples/sec: 302.14 - lr: 0.000050
2021-11-14 01:17:48,869 epoch 2 - iter 440/886 - loss 0.11192871 - samples/sec: 299.56 - lr: 0.000050
2021-11-14 01:18:07,635 epoch 2 - iter 528/886 - loss 0.11243003 - samples/sec: 300.27 - lr: 0.000050
2021-11-14 01:18:27,756 epoch 2 - iter 616/886 - loss 0.11202302 - samples/sec: 280.03 - lr: 0.000050
2021-11-14 01:18:46,477 epoch 2 - iter 704/886 - loss 0.11150461 - samples/sec: 301.00 - lr: 0.000050
2021-11-14 01:19:05,152 epoch 2 - iter 792/886 - loss 0.11090826 - samples/sec: 301.81 - lr: 0.000050
2021-11-14 01:19:23,958 epoch 2 - iter 880/886 - loss 0.11109339 - samples/sec: 299.71 - lr: 0.000050
2021-11-14 01:19:25,234 ----------------------------------------------------------------------------------------------------
2021-11-14 01:19:25,234 EPOCH 2 done: loss 0.1110 - lr 0.0000500
2021-11-14 01:19:41,637 DEV : loss 0.0011662252945825458 - f1-score (micro avg)  0.9987
2021-11-14 01:19:41,739 BAD EPOCHS (no improvement): 1
2021-11-14 01:19:41,742 ----------------------------------------------------------------------------------------------------
2021-11-14 01:20:00,648 epoch 3 - iter 88/886 - loss 0.11136958 - samples/sec: 298.07 - lr: 0.000050
2021-11-14 01:20:19,564 epoch 3 - iter 176/886 - loss 0.11280468 - samples/sec: 297.97 - lr: 0.000050
2021-11-14 01:20:38,568 epoch 3 - iter 264/886 - loss 0.11045104 - samples/sec: 296.60 - lr: 0.000050
2021-11-14 01:20:57,435 epoch 3 - iter 352/886 - loss 0.10911278 - samples/sec: 298.75 - lr: 0.000050
2021-11-14 01:21:16,245 epoch 3 - iter 440/886 - loss 0.10930290 - samples/sec: 299.56 - lr: 0.000050
2021-11-14 01:21:35,246 epoch 3 - iter 528/886 - loss 0.10928782 - samples/sec: 296.54 - lr: 0.000050
2021-11-14 01:21:54,644 epoch 3 - iter 616/886 - loss 0.10980571 - samples/sec: 290.50 - lr: 0.000050
2021-11-14 01:22:13,526 epoch 3 - iter 704/886 - loss 0.10986299 - samples/sec: 298.42 - lr: 0.000050
2021-11-14 01:22:32,408 epoch 3 - iter 792/886 - loss 0.11021279 - samples/sec: 298.42 - lr: 0.000050
2021-11-14 01:22:51,317 epoch 3 - iter 880/886 - loss 0.11010333 - samples/sec: 297.99 - lr: 0.000050
2021-11-14 01:22:52,607 ----------------------------------------------------------------------------------------------------
2021-11-14 01:22:52,608 EPOCH 3 done: loss 0.1101 - lr 0.0000500
2021-11-14 01:23:10,750 DEV : loss 0.0018373305210843682 - f1-score (micro avg)  0.9977
2021-11-14 01:23:10,838 BAD EPOCHS (no improvement): 2
2021-11-14 01:23:10,839 ----------------------------------------------------------------------------------------------------
2021-11-14 01:23:30,566 epoch 4 - iter 88/886 - loss 0.10992709 - samples/sec: 285.68 - lr: 0.000050
2021-11-14 01:23:50,362 epoch 4 - iter 176/886 - loss 0.10809355 - samples/sec: 284.67 - lr: 0.000050
2021-11-14 01:24:10,080 epoch 4 - iter 264/886 - loss 0.10844173 - samples/sec: 285.87 - lr: 0.000050
2021-11-14 01:24:30,946 epoch 4 - iter 352/886 - loss 0.10836201 - samples/sec: 270.06 - lr: 0.000050
2021-11-14 01:24:51,474 epoch 4 - iter 440/886 - loss 0.10794139 - samples/sec: 274.51 - lr: 0.000050
2021-11-14 01:25:12,388 epoch 4 - iter 528/886 - loss 0.10878776 - samples/sec: 269.43 - lr: 0.000050
2021-11-14 01:25:33,189 epoch 4 - iter 616/886 - loss 0.10894668 - samples/sec: 270.92 - lr: 0.000050
2021-11-14 01:25:54,237 epoch 4 - iter 704/886 - loss 0.10934898 - samples/sec: 267.79 - lr: 0.000050
2021-11-14 01:26:15,172 epoch 4 - iter 792/886 - loss 0.10987029 - samples/sec: 269.18 - lr: 0.000050
2021-11-14 01:26:35,568 epoch 4 - iter 880/886 - loss 0.10994285 - samples/sec: 276.35 - lr: 0.000050
2021-11-14 01:26:36,958 ----------------------------------------------------------------------------------------------------
2021-11-14 01:26:36,959 EPOCH 4 done: loss 0.1099 - lr 0.0000500
2021-11-14 01:26:56,814 DEV : loss 0.0014131164643913507 - f1-score (micro avg)  0.999
2021-11-14 01:26:56,904 BAD EPOCHS (no improvement): 0
2021-11-14 01:26:56,907 saving best model
2021-11-14 01:26:57,746 ----------------------------------------------------------------------------------------------------
2021-11-14 01:27:17,983 epoch 5 - iter 88/886 - loss 0.10864585 - samples/sec: 278.47 - lr: 0.000050
2021-11-14 01:27:37,584 epoch 5 - iter 176/886 - loss 0.10902201 - samples/sec: 287.48 - lr: 0.000050
2021-11-14 01:27:57,285 epoch 5 - iter 264/886 - loss 0.10824347 - samples/sec: 286.02 - lr: 0.000050
2021-11-14 01:28:16,752 epoch 5 - iter 352/886 - loss 0.10819784 - samples/sec: 289.50 - lr: 0.000050
2021-11-14 01:28:35,991 epoch 5 - iter 440/886 - loss 0.10806523 - samples/sec: 292.89 - lr: 0.000050
2021-11-14 01:28:55,004 epoch 5 - iter 528/886 - loss 0.10874710 - samples/sec: 296.35 - lr: 0.000050
2021-11-14 01:29:14,287 epoch 5 - iter 616/886 - loss 0.10819233 - samples/sec: 292.22 - lr: 0.000050
2021-11-14 01:29:33,882 epoch 5 - iter 704/886 - loss 0.10856081 - samples/sec: 287.57 - lr: 0.000050
2021-11-14 01:29:53,701 epoch 5 - iter 792/886 - loss 0.10878005 - samples/sec: 284.31 - lr: 0.000050
2021-11-14 01:30:13,249 epoch 5 - iter 880/886 - loss 0.10877142 - samples/sec: 288.26 - lr: 0.000050
2021-11-14 01:30:14,542 ----------------------------------------------------------------------------------------------------
2021-11-14 01:30:14,543 EPOCH 5 done: loss 0.1088 - lr 0.0000500
2021-11-14 01:30:32,668 DEV : loss 0.0017454695189371705 - f1-score (micro avg)  0.9993
2021-11-14 01:30:32,754 BAD EPOCHS (no improvement): 0
2021-11-14 01:30:32,757 saving best model
2021-11-14 01:30:33,509 ----------------------------------------------------------------------------------------------------
2021-11-14 01:30:52,836 epoch 6 - iter 88/886 - loss 0.10524382 - samples/sec: 291.60 - lr: 0.000050
2021-11-14 01:31:12,126 epoch 6 - iter 176/886 - loss 0.10690102 - samples/sec: 292.11 - lr: 0.000050
2021-11-14 01:31:31,803 epoch 6 - iter 264/886 - loss 0.10714116 - samples/sec: 286.38 - lr: 0.000050
2021-11-14 01:31:51,724 epoch 6 - iter 352/886 - loss 0.10771656 - samples/sec: 282.86 - lr: 0.000050
2021-11-14 01:32:11,047 epoch 6 - iter 440/886 - loss 0.10879216 - samples/sec: 291.61 - lr: 0.000050
2021-11-14 01:32:30,353 epoch 6 - iter 528/886 - loss 0.10867079 - samples/sec: 291.88 - lr: 0.000050
2021-11-14 01:32:49,795 epoch 6 - iter 616/886 - loss 0.10904316 - samples/sec: 289.82 - lr: 0.000050
2021-11-14 01:33:09,113 epoch 6 - iter 704/886 - loss 0.10898605 - samples/sec: 291.70 - lr: 0.000050
2021-11-14 01:33:28,312 epoch 6 - iter 792/886 - loss 0.10895071 - samples/sec: 293.49 - lr: 0.000050
2021-11-14 01:33:48,207 epoch 6 - iter 880/886 - loss 0.10936169 - samples/sec: 283.23 - lr: 0.000050
2021-11-14 01:33:49,618 ----------------------------------------------------------------------------------------------------
2021-11-14 01:33:49,619 EPOCH 6 done: loss 0.1094 - lr 0.0000500
2021-11-14 01:34:08,307 DEV : loss 0.0012574659194797277 - f1-score (micro avg)  0.9991
2021-11-14 01:34:08,393 BAD EPOCHS (no improvement): 1
2021-11-14 01:34:08,396 ----------------------------------------------------------------------------------------------------
2021-11-14 01:34:28,456 epoch 7 - iter 88/886 - loss 0.10772567 - samples/sec: 280.95 - lr: 0.000050
2021-11-14 01:34:48,077 epoch 7 - iter 176/886 - loss 0.10831423 - samples/sec: 287.18 - lr: 0.000050
2021-11-14 01:35:07,762 epoch 7 - iter 264/886 - loss 0.10889045 - samples/sec: 286.25 - lr: 0.000050
2021-11-14 01:35:27,543 epoch 7 - iter 352/886 - loss 0.10923627 - samples/sec: 284.87 - lr: 0.000050
2021-11-14 01:35:47,152 epoch 7 - iter 440/886 - loss 0.10891691 - samples/sec: 287.36 - lr: 0.000050
2021-11-14 01:36:06,760 epoch 7 - iter 528/886 - loss 0.10886164 - samples/sec: 287.38 - lr: 0.000050
2021-11-14 01:36:26,264 epoch 7 - iter 616/886 - loss 0.10925453 - samples/sec: 288.92 - lr: 0.000050
2021-11-14 01:36:45,846 epoch 7 - iter 704/886 - loss 0.10944528 - samples/sec: 287.78 - lr: 0.000050
2021-11-14 01:37:05,161 epoch 7 - iter 792/886 - loss 0.10963480 - samples/sec: 291.83 - lr: 0.000050
2021-11-14 01:37:25,344 epoch 7 - iter 880/886 - loss 0.10941620 - samples/sec: 279.19 - lr: 0.000050
2021-11-14 01:37:26,675 ----------------------------------------------------------------------------------------------------
2021-11-14 01:37:26,676 EPOCH 7 done: loss 0.1093 - lr 0.0000500
2021-11-14 01:37:46,332 DEV : loss 0.0008941686828620732 - f1-score (micro avg)  0.9994
2021-11-14 01:37:46,425 BAD EPOCHS (no improvement): 0
2021-11-14 01:37:46,428 saving best model
2021-11-14 01:37:47,268 ----------------------------------------------------------------------------------------------------
2021-11-14 01:38:06,968 epoch 8 - iter 88/886 - loss 0.10842313 - samples/sec: 286.09 - lr: 0.000050
2021-11-14 01:38:26,508 epoch 8 - iter 176/886 - loss 0.10686590 - samples/sec: 288.47 - lr: 0.000050
2021-11-14 01:38:45,880 epoch 8 - iter 264/886 - loss 0.10866318 - samples/sec: 290.87 - lr: 0.000050
2021-11-14 01:39:05,447 epoch 8 - iter 352/886 - loss 0.10886654 - samples/sec: 287.98 - lr: 0.000050
2021-11-14 01:39:25,039 epoch 8 - iter 440/886 - loss 0.10893653 - samples/sec: 287.62 - lr: 0.000050
2021-11-14 01:39:44,508 epoch 8 - iter 528/886 - loss 0.10845487 - samples/sec: 289.43 - lr: 0.000050
2021-11-14 01:40:04,009 epoch 8 - iter 616/886 - loss 0.10849658 - samples/sec: 288.96 - lr: 0.000050
2021-11-14 01:40:23,270 epoch 8 - iter 704/886 - loss 0.10852857 - samples/sec: 292.55 - lr: 0.000050
2021-11-14 01:40:42,423 epoch 8 - iter 792/886 - loss 0.10825218 - samples/sec: 294.21 - lr: 0.000050
2021-11-14 01:41:01,605 epoch 8 - iter 880/886 - loss 0.10839605 - samples/sec: 293.76 - lr: 0.000050
2021-11-14 01:41:02,928 ----------------------------------------------------------------------------------------------------
2021-11-14 01:41:02,929 EPOCH 8 done: loss 0.1084 - lr 0.0000500
2021-11-14 01:41:22,401 DEV : loss 0.0013162429677322507 - f1-score (micro avg)  0.9994
2021-11-14 01:41:22,539 BAD EPOCHS (no improvement): 1
2021-11-14 01:41:23,014 ----------------------------------------------------------------------------------------------------
2021-11-14 01:41:23,015 loading file training/flair_ner/14112021_011130/best-model.pt
2021-11-14 01:41:42,464 0.9996	0.9996	0.9996	0.9996
2021-11-14 01:41:42,465 
Results:
- F-score (micro) 0.9996
- F-score (macro) 0.9994
- Accuracy 0.9996

By class:
                 precision    recall  f1-score   support

      nb_rounds     1.0000    0.9988    0.9994      6894
 duration_wt_sd     1.0000    1.0000    1.0000      3288
duration_br_min     0.9982    1.0000    0.9991      3251
duration_wt_min     1.0000    1.0000    1.0000      2677
 duration_br_sd     0.9995    1.0000    0.9998      2080
 duration_wt_hr     1.0000    1.0000    1.0000      1050
 duration_br_hr     0.9957    1.0000    0.9978       230

      micro avg     0.9996    0.9996    0.9996     19470
      macro avg     0.9990    0.9998    0.9994     19470
   weighted avg     0.9996    0.9996    0.9996     19470
    samples avg     0.9996    0.9996    0.9996     19470

2021-11-14 01:41:42,466 ----------------------------------------------------------------------------------------------------