Hugging Face's logo

stefan-it
/
hmbench-newseye-de-hmbert_tiny-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
d54efa1
•
1 Parent(s): 68371c7

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697717544.46dc0c540dd0.4319.11 +3 -0
  5. test.tsv +0 -0
  6. training.log +243 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8d418acb3a8652642211c435b1f14f2fdef0e3852db4407d81d9f466e50b681
3
+ size 19048098
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 12:13:27 0.0000 0.9097 0.1408 0.3182 0.0265 0.0490 0.0251
3
+ 2 12:14:33 0.0000 0.3239 0.1307 0.2850 0.2273 0.2529 0.1448
4
+ 3 12:15:39 0.0000 0.2661 0.1417 0.2217 0.3523 0.2721 0.1576
5
+ 4 12:16:46 0.0000 0.2338 0.1450 0.2056 0.3636 0.2627 0.1517
6
+ 5 12:17:53 0.0000 0.2122 0.1654 0.2025 0.4015 0.2692 0.1565
7
+ 6 12:19:00 0.0000 0.1958 0.1603 0.2216 0.4072 0.2870 0.1685
8
+ 7 12:20:07 0.0000 0.1820 0.1664 0.2019 0.3674 0.2606 0.1507
9
+ 8 12:21:14 0.0000 0.1734 0.1701 0.2263 0.3845 0.2849 0.1671
10
+ 9 12:22:21 0.0000 0.1641 0.1792 0.2233 0.3958 0.2855 0.1675
11
+ 10 12:23:27 0.0000 0.1617 0.1829 0.2202 0.4167 0.2881 0.1692
runs/events.out.tfevents.1697717544.46dc0c540dd0.4319.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab6658f42ae478a7c40da702bc33bebf3f508a0b3b034edba9bce60de95df68
3
+ size 1464420
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-19 12:12:24,058 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-19 12:12:24,058 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-19 12:12:24,058 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-19 12:12:24,058 MultiCorpus: 20847 train + 1123 dev + 3350 test sentences
52
+ - NER_HIPE_2022 Corpus: 20847 train + 1123 dev + 3350 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/de/with_doc_seperator
53
+ 2023-10-19 12:12:24,058 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-19 12:12:24,058 Train: 20847 sentences
55
+ 2023-10-19 12:12:24,058 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-19 12:12:24,058 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-19 12:12:24,058 Training Params:
58
+ 2023-10-19 12:12:24,058 - learning_rate: "5e-05"
59
+ 2023-10-19 12:12:24,058 - mini_batch_size: "8"
60
+ 2023-10-19 12:12:24,058 - max_epochs: "10"
61
+ 2023-10-19 12:12:24,058 - shuffle: "True"
62
+ 2023-10-19 12:12:24,058 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-19 12:12:24,058 Plugins:
64
+ 2023-10-19 12:12:24,058 - TensorboardLogger
65
+ 2023-10-19 12:12:24,059 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-19 12:12:24,059 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-19 12:12:24,059 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-19 12:12:24,059 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-19 12:12:24,059 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-19 12:12:24,059 Computation:
71
+ 2023-10-19 12:12:24,059 - compute on device: cuda:0
72
+ 2023-10-19 12:12:24,059 - embedding storage: none
73
+ 2023-10-19 12:12:24,059 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-19 12:12:24,059 Model training base path: "hmbench-newseye/de-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
75
+ 2023-10-19 12:12:24,059 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-19 12:12:24,059 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-19 12:12:24,059 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-19 12:12:30,245 epoch 1 - iter 260/2606 - loss 3.29215868 - time (sec): 6.19 - samples/sec: 6125.45 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-19 12:12:36,395 epoch 1 - iter 520/2606 - loss 2.54663351 - time (sec): 12.34 - samples/sec: 6036.79 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-19 12:12:42,287 epoch 1 - iter 780/2606 - loss 1.98000977 - time (sec): 18.23 - samples/sec: 5915.66 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-19 12:12:48,508 epoch 1 - iter 1040/2606 - loss 1.60194669 - time (sec): 24.45 - samples/sec: 5924.28 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-19 12:12:54,610 epoch 1 - iter 1300/2606 - loss 1.39106299 - time (sec): 30.55 - samples/sec: 5902.93 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-19 12:13:01,049 epoch 1 - iter 1560/2606 - loss 1.23459866 - time (sec): 36.99 - samples/sec: 5904.98 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-19 12:13:07,064 epoch 1 - iter 1820/2606 - loss 1.13126722 - time (sec): 43.00 - samples/sec: 5895.47 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-19 12:13:13,149 epoch 1 - iter 2080/2606 - loss 1.04840712 - time (sec): 49.09 - samples/sec: 5904.15 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-19 12:13:19,453 epoch 1 - iter 2340/2606 - loss 0.97142483 - time (sec): 55.39 - samples/sec: 5935.98 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-19 12:13:25,404 epoch 1 - iter 2600/2606 - loss 0.91090610 - time (sec): 61.34 - samples/sec: 5977.09 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-19 12:13:25,524 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-19 12:13:25,524 EPOCH 1 done: loss 0.9097 - lr: 0.000050
90
+ 2023-10-19 12:13:27,771 DEV : loss 0.14083856344223022 - f1-score (micro avg) 0.049
91
+ 2023-10-19 12:13:27,795 saving best model
92
+ 2023-10-19 12:13:27,827 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-19 12:13:33,910 epoch 2 - iter 260/2606 - loss 0.33750708 - time (sec): 6.08 - samples/sec: 6097.84 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-19 12:13:40,145 epoch 2 - iter 520/2606 - loss 0.34632728 - time (sec): 12.32 - samples/sec: 6177.17 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-19 12:13:46,357 epoch 2 - iter 780/2606 - loss 0.33738274 - time (sec): 18.53 - samples/sec: 6059.22 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-19 12:13:52,438 epoch 2 - iter 1040/2606 - loss 0.33995850 - time (sec): 24.61 - samples/sec: 6083.78 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-19 12:13:57,789 epoch 2 - iter 1300/2606 - loss 0.34055467 - time (sec): 29.96 - samples/sec: 6142.43 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-19 12:14:03,922 epoch 2 - iter 1560/2606 - loss 0.33755029 - time (sec): 36.09 - samples/sec: 6101.82 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-19 12:14:10,023 epoch 2 - iter 1820/2606 - loss 0.33322099 - time (sec): 42.19 - samples/sec: 6115.49 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-19 12:14:16,125 epoch 2 - iter 2080/2606 - loss 0.32900406 - time (sec): 48.30 - samples/sec: 6057.42 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-19 12:14:22,224 epoch 2 - iter 2340/2606 - loss 0.32781761 - time (sec): 54.40 - samples/sec: 6080.19 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-19 12:14:28,034 epoch 2 - iter 2600/2606 - loss 0.32378050 - time (sec): 60.21 - samples/sec: 6090.09 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-19 12:14:28,158 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-19 12:14:28,158 EPOCH 2 done: loss 0.3239 - lr: 0.000044
105
+ 2023-10-19 12:14:33,294 DEV : loss 0.13072499632835388 - f1-score (micro avg) 0.2529
106
+ 2023-10-19 12:14:33,317 saving best model
107
+ 2023-10-19 12:14:33,350 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-19 12:14:39,474 epoch 3 - iter 260/2606 - loss 0.25574137 - time (sec): 6.12 - samples/sec: 5781.84 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-19 12:14:45,559 epoch 3 - iter 520/2606 - loss 0.26774606 - time (sec): 12.21 - samples/sec: 5992.37 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-19 12:14:51,497 epoch 3 - iter 780/2606 - loss 0.26961024 - time (sec): 18.15 - samples/sec: 5774.06 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-19 12:14:57,569 epoch 3 - iter 1040/2606 - loss 0.26961308 - time (sec): 24.22 - samples/sec: 5862.06 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-19 12:15:03,380 epoch 3 - iter 1300/2606 - loss 0.27095396 - time (sec): 30.03 - samples/sec: 5966.12 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-19 12:15:09,637 epoch 3 - iter 1560/2606 - loss 0.27006005 - time (sec): 36.29 - samples/sec: 6027.28 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-19 12:15:15,650 epoch 3 - iter 1820/2606 - loss 0.26808602 - time (sec): 42.30 - samples/sec: 6043.76 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-19 12:15:22,109 epoch 3 - iter 2080/2606 - loss 0.26544069 - time (sec): 48.76 - samples/sec: 6025.06 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-19 12:15:28,256 epoch 3 - iter 2340/2606 - loss 0.26734771 - time (sec): 54.91 - samples/sec: 6006.07 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-19 12:15:34,479 epoch 3 - iter 2600/2606 - loss 0.26623336 - time (sec): 61.13 - samples/sec: 6001.01 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-19 12:15:34,625 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-19 12:15:34,625 EPOCH 3 done: loss 0.2661 - lr: 0.000039
120
+ 2023-10-19 12:15:39,746 DEV : loss 0.14174337685108185 - f1-score (micro avg) 0.2721
121
+ 2023-10-19 12:15:39,769 saving best model
122
+ 2023-10-19 12:15:39,801 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-19 12:15:45,896 epoch 4 - iter 260/2606 - loss 0.25139617 - time (sec): 6.09 - samples/sec: 6246.82 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-19 12:15:52,182 epoch 4 - iter 520/2606 - loss 0.23480749 - time (sec): 12.38 - samples/sec: 6268.11 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-19 12:15:58,276 epoch 4 - iter 780/2606 - loss 0.24352221 - time (sec): 18.47 - samples/sec: 6182.49 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-19 12:16:04,376 epoch 4 - iter 1040/2606 - loss 0.24831904 - time (sec): 24.57 - samples/sec: 6075.18 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-19 12:16:10,652 epoch 4 - iter 1300/2606 - loss 0.24218416 - time (sec): 30.85 - samples/sec: 6009.23 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-19 12:16:16,800 epoch 4 - iter 1560/2606 - loss 0.23924425 - time (sec): 37.00 - samples/sec: 5955.66 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-19 12:16:23,005 epoch 4 - iter 1820/2606 - loss 0.23697081 - time (sec): 43.20 - samples/sec: 5993.23 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-19 12:16:29,000 epoch 4 - iter 2080/2606 - loss 0.23564226 - time (sec): 49.20 - samples/sec: 5965.50 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-19 12:16:35,148 epoch 4 - iter 2340/2606 - loss 0.23533143 - time (sec): 55.35 - samples/sec: 5934.69 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-19 12:16:41,289 epoch 4 - iter 2600/2606 - loss 0.23376594 - time (sec): 61.49 - samples/sec: 5959.34 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-19 12:16:41,416 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-19 12:16:41,417 EPOCH 4 done: loss 0.2338 - lr: 0.000033
135
+ 2023-10-19 12:16:46,618 DEV : loss 0.14498400688171387 - f1-score (micro avg) 0.2627
136
+ 2023-10-19 12:16:46,641 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-19 12:16:52,681 epoch 5 - iter 260/2606 - loss 0.19023305 - time (sec): 6.04 - samples/sec: 5769.39 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-19 12:16:58,701 epoch 5 - iter 520/2606 - loss 0.21196067 - time (sec): 12.06 - samples/sec: 5855.59 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-19 12:17:04,898 epoch 5 - iter 780/2606 - loss 0.21458042 - time (sec): 18.26 - samples/sec: 5909.45 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-19 12:17:11,106 epoch 5 - iter 1040/2606 - loss 0.21431244 - time (sec): 24.46 - samples/sec: 5961.35 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-19 12:17:17,204 epoch 5 - iter 1300/2606 - loss 0.21745310 - time (sec): 30.56 - samples/sec: 5900.25 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-19 12:17:23,385 epoch 5 - iter 1560/2606 - loss 0.21540934 - time (sec): 36.74 - samples/sec: 5920.43 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-19 12:17:29,536 epoch 5 - iter 1820/2606 - loss 0.21605849 - time (sec): 42.89 - samples/sec: 5966.77 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-19 12:17:35,911 epoch 5 - iter 2080/2606 - loss 0.21388261 - time (sec): 49.27 - samples/sec: 5952.00 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-19 12:17:42,028 epoch 5 - iter 2340/2606 - loss 0.21150192 - time (sec): 55.39 - samples/sec: 5950.63 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-19 12:17:48,297 epoch 5 - iter 2600/2606 - loss 0.21236748 - time (sec): 61.65 - samples/sec: 5944.70 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-19 12:17:48,443 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-19 12:17:48,443 EPOCH 5 done: loss 0.2122 - lr: 0.000028
149
+ 2023-10-19 12:17:53,633 DEV : loss 0.16542117297649384 - f1-score (micro avg) 0.2692
150
+ 2023-10-19 12:17:53,657 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-19 12:17:59,754 epoch 6 - iter 260/2606 - loss 0.18992843 - time (sec): 6.10 - samples/sec: 5941.18 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-19 12:18:05,959 epoch 6 - iter 520/2606 - loss 0.19973136 - time (sec): 12.30 - samples/sec: 6061.48 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-19 12:18:11,983 epoch 6 - iter 780/2606 - loss 0.20044914 - time (sec): 18.33 - samples/sec: 6043.26 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-19 12:18:18,208 epoch 6 - iter 1040/2606 - loss 0.19582093 - time (sec): 24.55 - samples/sec: 6172.37 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-19 12:18:24,346 epoch 6 - iter 1300/2606 - loss 0.19555968 - time (sec): 30.69 - samples/sec: 6129.34 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-19 12:18:30,281 epoch 6 - iter 1560/2606 - loss 0.19819069 - time (sec): 36.62 - samples/sec: 6027.05 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-19 12:18:36,257 epoch 6 - iter 1820/2606 - loss 0.19310853 - time (sec): 42.60 - samples/sec: 6027.45 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-19 12:18:42,270 epoch 6 - iter 2080/2606 - loss 0.19523538 - time (sec): 48.61 - samples/sec: 6028.21 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-19 12:18:48,569 epoch 6 - iter 2340/2606 - loss 0.19586601 - time (sec): 54.91 - samples/sec: 6030.74 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-19 12:18:54,595 epoch 6 - iter 2600/2606 - loss 0.19577802 - time (sec): 60.94 - samples/sec: 6012.96 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-19 12:18:54,761 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-19 12:18:54,762 EPOCH 6 done: loss 0.1958 - lr: 0.000022
163
+ 2023-10-19 12:19:00,041 DEV : loss 0.1602775603532791 - f1-score (micro avg) 0.287
164
+ 2023-10-19 12:19:00,064 saving best model
165
+ 2023-10-19 12:19:00,100 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-19 12:19:06,390 epoch 7 - iter 260/2606 - loss 0.19220321 - time (sec): 6.29 - samples/sec: 5805.07 - lr: 0.000022 - momentum: 0.000000
167
+ 2023-10-19 12:19:12,713 epoch 7 - iter 520/2606 - loss 0.17774848 - time (sec): 12.61 - samples/sec: 5762.84 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-19 12:19:18,869 epoch 7 - iter 780/2606 - loss 0.18234572 - time (sec): 18.77 - samples/sec: 5790.14 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-19 12:19:25,087 epoch 7 - iter 1040/2606 - loss 0.18561093 - time (sec): 24.99 - samples/sec: 5882.59 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-19 12:19:31,197 epoch 7 - iter 1300/2606 - loss 0.18840634 - time (sec): 31.10 - samples/sec: 5838.80 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-19 12:19:37,367 epoch 7 - iter 1560/2606 - loss 0.18474661 - time (sec): 37.27 - samples/sec: 5861.62 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-19 12:19:43,563 epoch 7 - iter 1820/2606 - loss 0.18465378 - time (sec): 43.46 - samples/sec: 5858.84 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-19 12:19:49,879 epoch 7 - iter 2080/2606 - loss 0.18296343 - time (sec): 49.78 - samples/sec: 5858.93 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-19 12:19:56,085 epoch 7 - iter 2340/2606 - loss 0.18362259 - time (sec): 55.98 - samples/sec: 5851.91 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-19 12:20:02,342 epoch 7 - iter 2600/2606 - loss 0.18183094 - time (sec): 62.24 - samples/sec: 5886.07 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-19 12:20:02,494 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-19 12:20:02,494 EPOCH 7 done: loss 0.1820 - lr: 0.000017
178
+ 2023-10-19 12:20:07,043 DEV : loss 0.1663893163204193 - f1-score (micro avg) 0.2606
179
+ 2023-10-19 12:20:07,067 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-19 12:20:13,480 epoch 8 - iter 260/2606 - loss 0.17327680 - time (sec): 6.41 - samples/sec: 5899.14 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-19 12:20:20,259 epoch 8 - iter 520/2606 - loss 0.17288993 - time (sec): 13.19 - samples/sec: 5772.22 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-19 12:20:26,391 epoch 8 - iter 780/2606 - loss 0.17832513 - time (sec): 19.32 - samples/sec: 5847.05 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-19 12:20:32,449 epoch 8 - iter 1040/2606 - loss 0.17895989 - time (sec): 25.38 - samples/sec: 5784.84 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-19 12:20:38,654 epoch 8 - iter 1300/2606 - loss 0.17337141 - time (sec): 31.59 - samples/sec: 5857.95 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-19 12:20:44,733 epoch 8 - iter 1560/2606 - loss 0.17298900 - time (sec): 37.67 - samples/sec: 5825.43 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-19 12:20:50,908 epoch 8 - iter 1820/2606 - loss 0.17399534 - time (sec): 43.84 - samples/sec: 5852.70 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-19 12:20:57,214 epoch 8 - iter 2080/2606 - loss 0.17397486 - time (sec): 50.15 - samples/sec: 5834.64 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-19 12:21:03,425 epoch 8 - iter 2340/2606 - loss 0.17437299 - time (sec): 56.36 - samples/sec: 5844.70 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-19 12:21:09,586 epoch 8 - iter 2600/2606 - loss 0.17324575 - time (sec): 62.52 - samples/sec: 5858.13 - lr: 0.000011 - momentum: 0.000000
190
+ 2023-10-19 12:21:09,745 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-19 12:21:09,745 EPOCH 8 done: loss 0.1734 - lr: 0.000011
192
+ 2023-10-19 12:21:14,256 DEV : loss 0.1701161116361618 - f1-score (micro avg) 0.2849
193
+ 2023-10-19 12:21:14,281 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-19 12:21:20,114 epoch 9 - iter 260/2606 - loss 0.16285426 - time (sec): 5.83 - samples/sec: 6017.71 - lr: 0.000011 - momentum: 0.000000
195
+ 2023-10-19 12:21:26,305 epoch 9 - iter 520/2606 - loss 0.15650374 - time (sec): 12.02 - samples/sec: 5899.13 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-19 12:21:32,497 epoch 9 - iter 780/2606 - loss 0.15289815 - time (sec): 18.22 - samples/sec: 5990.64 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-19 12:21:38,744 epoch 9 - iter 1040/2606 - loss 0.15983102 - time (sec): 24.46 - samples/sec: 5990.22 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-19 12:21:44,897 epoch 9 - iter 1300/2606 - loss 0.15901456 - time (sec): 30.62 - samples/sec: 6016.51 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-19 12:21:51,948 epoch 9 - iter 1560/2606 - loss 0.16225996 - time (sec): 37.67 - samples/sec: 5873.77 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-19 12:21:58,092 epoch 9 - iter 1820/2606 - loss 0.16300920 - time (sec): 43.81 - samples/sec: 5858.05 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-19 12:22:04,260 epoch 9 - iter 2080/2606 - loss 0.16260252 - time (sec): 49.98 - samples/sec: 5885.13 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-19 12:22:10,385 epoch 9 - iter 2340/2606 - loss 0.16370810 - time (sec): 56.10 - samples/sec: 5887.77 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-19 12:22:16,530 epoch 9 - iter 2600/2606 - loss 0.16412782 - time (sec): 62.25 - samples/sec: 5886.33 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-19 12:22:16,678 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-19 12:22:16,678 EPOCH 9 done: loss 0.1641 - lr: 0.000006
206
+ 2023-10-19 12:22:21,175 DEV : loss 0.17923708260059357 - f1-score (micro avg) 0.2855
207
+ 2023-10-19 12:22:21,199 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-19 12:22:27,204 epoch 10 - iter 260/2606 - loss 0.16832198 - time (sec): 6.00 - samples/sec: 5414.49 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-19 12:22:33,408 epoch 10 - iter 520/2606 - loss 0.15961189 - time (sec): 12.21 - samples/sec: 5784.32 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-19 12:22:39,261 epoch 10 - iter 780/2606 - loss 0.16066261 - time (sec): 18.06 - samples/sec: 5815.64 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-19 12:22:45,464 epoch 10 - iter 1040/2606 - loss 0.16755305 - time (sec): 24.26 - samples/sec: 5869.45 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-19 12:22:51,624 epoch 10 - iter 1300/2606 - loss 0.16288242 - time (sec): 30.43 - samples/sec: 5908.64 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-19 12:22:57,929 epoch 10 - iter 1560/2606 - loss 0.16326348 - time (sec): 36.73 - samples/sec: 5945.25 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-19 12:23:03,980 epoch 10 - iter 1820/2606 - loss 0.16190089 - time (sec): 42.78 - samples/sec: 5896.27 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-19 12:23:09,938 epoch 10 - iter 2080/2606 - loss 0.16132966 - time (sec): 48.74 - samples/sec: 5965.88 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-19 12:23:16,219 epoch 10 - iter 2340/2606 - loss 0.16166399 - time (sec): 55.02 - samples/sec: 5992.67 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-19 12:23:23,237 epoch 10 - iter 2600/2606 - loss 0.16180342 - time (sec): 62.04 - samples/sec: 5914.47 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-19 12:23:23,378 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-19 12:23:23,378 EPOCH 10 done: loss 0.1617 - lr: 0.000000
220
+ 2023-10-19 12:23:27,891 DEV : loss 0.18292318284511566 - f1-score (micro avg) 0.2881
221
+ 2023-10-19 12:23:27,916 saving best model
222
+ 2023-10-19 12:23:27,974 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-19 12:23:27,974 Loading model from best epoch ...
224
+ 2023-10-19 12:23:28,044 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
225
+ 2023-10-19 12:23:34,357
226
+ Results:
227
+ - F-score (micro) 0.321
228
+ - F-score (macro) 0.182
229
+ - Accuracy 0.1932
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ LOC 0.4269 0.5288 0.4724 1214
235
+ PER 0.1741 0.2178 0.1935 808
236
+ ORG 0.0652 0.0595 0.0622 353
237
+ HumanProd 0.0000 0.0000 0.0000 15
238
+
239
+ micro avg 0.2957 0.3510 0.3210 2390
240
+ macro avg 0.1665 0.2015 0.1820 2390
241
+ weighted avg 0.2853 0.3510 0.3146 2390
242
+
243
+ 2023-10-19 12:23:34,357 ----------------------------------------------------------------------------------------------------