Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert_tiny-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
a3a1c2e
•
1 Parent(s): 841fa4a

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.1697653141.46dc0c540dd0.2878.14 +3 -0
  5. test.tsv +0 -0
  6. training.log +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad22ff3d46025612327f040cd95168928b7f96f92ee56c75e24ce4f7bf730078
3
+ size 19050210
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 18:19:14 0.0000 2.1657 0.4872 0.0000 0.0000 0.0000 0.0000
3
+ 2 18:19:29 0.0000 0.5507 0.3801 0.0000 0.0000 0.0000 0.0000
4
+ 3 18:19:44 0.0000 0.4553 0.3371 0.3023 0.0938 0.1432 0.0787
5
+ 4 18:20:00 0.0000 0.4145 0.3276 0.3723 0.1869 0.2488 0.1468
6
+ 5 18:20:15 0.0000 0.3866 0.3182 0.3499 0.2369 0.2825 0.1717
7
+ 6 18:20:31 0.0000 0.3645 0.3086 0.3658 0.2760 0.3146 0.1948
8
+ 7 18:20:47 0.0000 0.3560 0.3127 0.3766 0.2611 0.3084 0.1897
9
+ 8 18:21:03 0.0000 0.3489 0.3095 0.3537 0.2721 0.3076 0.1897
10
+ 9 18:21:18 0.0000 0.3373 0.3095 0.3715 0.2768 0.3172 0.1963
11
+ 10 18:21:34 0.0000 0.3389 0.3081 0.3630 0.2807 0.3166 0.1963
runs/events.out.tfevents.1697653141.46dc0c540dd0.2878.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbfabdd4ccfa9779ff969e154d9a809b72c1128c238eb29a5afb8ae7a6ff75b3
3
+ size 253592
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 18:19:01,645 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 18:19:01,645 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=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-18 18:19:01,645 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 18:19:01,645 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
52
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
53
+ 2023-10-18 18:19:01,645 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 18:19:01,645 Train: 3575 sentences
55
+ 2023-10-18 18:19:01,646 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 18:19:01,646 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 18:19:01,646 Training Params:
58
+ 2023-10-18 18:19:01,646 - learning_rate: "3e-05"
59
+ 2023-10-18 18:19:01,646 - mini_batch_size: "8"
60
+ 2023-10-18 18:19:01,646 - max_epochs: "10"
61
+ 2023-10-18 18:19:01,646 - shuffle: "True"
62
+ 2023-10-18 18:19:01,646 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 18:19:01,646 Plugins:
64
+ 2023-10-18 18:19:01,646 - TensorboardLogger
65
+ 2023-10-18 18:19:01,646 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 18:19:01,646 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 18:19:01,646 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 18:19:01,646 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 18:19:01,646 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 18:19:01,646 Computation:
71
+ 2023-10-18 18:19:01,646 - compute on device: cuda:0
72
+ 2023-10-18 18:19:01,646 - embedding storage: none
73
+ 2023-10-18 18:19:01,646 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 18:19:01,646 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-18 18:19:01,646 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 18:19:01,646 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 18:19:01,646 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 18:19:02,711 epoch 1 - iter 44/447 - loss 4.26136576 - time (sec): 1.06 - samples/sec: 7683.39 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-18 18:19:03,723 epoch 1 - iter 88/447 - loss 4.19678316 - time (sec): 2.08 - samples/sec: 8059.03 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-18 18:19:04,806 epoch 1 - iter 132/447 - loss 3.92643463 - time (sec): 3.16 - samples/sec: 8288.46 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-18 18:19:05,849 epoch 1 - iter 176/447 - loss 3.69414494 - time (sec): 4.20 - samples/sec: 8386.38 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-18 18:19:07,106 epoch 1 - iter 220/447 - loss 3.39968934 - time (sec): 5.46 - samples/sec: 8144.20 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-18 18:19:08,094 epoch 1 - iter 264/447 - loss 3.08646118 - time (sec): 6.45 - samples/sec: 8230.31 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-18 18:19:09,072 epoch 1 - iter 308/447 - loss 2.80295080 - time (sec): 7.43 - samples/sec: 8211.99 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-18 18:19:10,022 epoch 1 - iter 352/447 - loss 2.55929558 - time (sec): 8.38 - samples/sec: 8228.60 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-18 18:19:11,033 epoch 1 - iter 396/447 - loss 2.36406683 - time (sec): 9.39 - samples/sec: 8184.90 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-18 18:19:12,060 epoch 1 - iter 440/447 - loss 2.19005741 - time (sec): 10.41 - samples/sec: 8187.98 - lr: 0.000029 - momentum: 0.000000
88
+ 2023-10-18 18:19:12,216 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 18:19:12,217 EPOCH 1 done: loss 2.1657 - lr: 0.000029
90
+ 2023-10-18 18:19:14,163 DEV : loss 0.48721176385879517 - f1-score (micro avg) 0.0
91
+ 2023-10-18 18:19:14,189 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 18:19:15,119 epoch 2 - iter 44/447 - loss 0.65125143 - time (sec): 0.93 - samples/sec: 9426.59 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-18 18:19:15,993 epoch 2 - iter 88/447 - loss 0.61628616 - time (sec): 1.80 - samples/sec: 9461.75 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-18 18:19:16,940 epoch 2 - iter 132/447 - loss 0.61557362 - time (sec): 2.75 - samples/sec: 9161.17 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-18 18:19:17,946 epoch 2 - iter 176/447 - loss 0.61002674 - time (sec): 3.76 - samples/sec: 8949.74 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-18 18:19:18,961 epoch 2 - iter 220/447 - loss 0.60306428 - time (sec): 4.77 - samples/sec: 8804.65 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-18 18:19:19,982 epoch 2 - iter 264/447 - loss 0.59448973 - time (sec): 5.79 - samples/sec: 8553.15 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-18 18:19:20,985 epoch 2 - iter 308/447 - loss 0.58231488 - time (sec): 6.80 - samples/sec: 8557.62 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-18 18:19:22,356 epoch 2 - iter 352/447 - loss 0.56475657 - time (sec): 8.17 - samples/sec: 8324.13 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-18 18:19:23,378 epoch 2 - iter 396/447 - loss 0.55753500 - time (sec): 9.19 - samples/sec: 8386.51 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-18 18:19:24,394 epoch 2 - iter 440/447 - loss 0.55052779 - time (sec): 10.20 - samples/sec: 8365.55 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-18 18:19:24,546 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 18:19:24,546 EPOCH 2 done: loss 0.5507 - lr: 0.000027
104
+ 2023-10-18 18:19:29,410 DEV : loss 0.3801082968711853 - f1-score (micro avg) 0.0
105
+ 2023-10-18 18:19:29,436 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-18 18:19:30,447 epoch 3 - iter 44/447 - loss 0.46421760 - time (sec): 1.01 - samples/sec: 8751.88 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-18 18:19:31,438 epoch 3 - iter 88/447 - loss 0.45746619 - time (sec): 2.00 - samples/sec: 8519.88 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-18 18:19:32,423 epoch 3 - iter 132/447 - loss 0.47573888 - time (sec): 2.99 - samples/sec: 8600.46 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-18 18:19:33,391 epoch 3 - iter 176/447 - loss 0.48006629 - time (sec): 3.95 - samples/sec: 8515.13 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-18 18:19:34,417 epoch 3 - iter 220/447 - loss 0.46868404 - time (sec): 4.98 - samples/sec: 8503.02 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-18 18:19:35,477 epoch 3 - iter 264/447 - loss 0.46315261 - time (sec): 6.04 - samples/sec: 8639.24 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-18 18:19:36,483 epoch 3 - iter 308/447 - loss 0.46299866 - time (sec): 7.05 - samples/sec: 8645.31 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-18 18:19:37,476 epoch 3 - iter 352/447 - loss 0.46009593 - time (sec): 8.04 - samples/sec: 8590.88 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-18 18:19:38,514 epoch 3 - iter 396/447 - loss 0.45871433 - time (sec): 9.08 - samples/sec: 8478.04 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-18 18:19:39,492 epoch 3 - iter 440/447 - loss 0.45734948 - time (sec): 10.06 - samples/sec: 8474.22 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-18 18:19:39,655 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-18 18:19:39,655 EPOCH 3 done: loss 0.4553 - lr: 0.000023
118
+ 2023-10-18 18:19:44,879 DEV : loss 0.33706629276275635 - f1-score (micro avg) 0.1432
119
+ 2023-10-18 18:19:44,905 saving best model
120
+ 2023-10-18 18:19:44,941 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-18 18:19:46,013 epoch 4 - iter 44/447 - loss 0.37224151 - time (sec): 1.07 - samples/sec: 7205.04 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-18 18:19:46,914 epoch 4 - iter 88/447 - loss 0.40787854 - time (sec): 1.97 - samples/sec: 8002.55 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-18 18:19:47,750 epoch 4 - iter 132/447 - loss 0.43149977 - time (sec): 2.81 - samples/sec: 8545.35 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-18 18:19:48,736 epoch 4 - iter 176/447 - loss 0.43216701 - time (sec): 3.80 - samples/sec: 8482.73 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-18 18:19:49,840 epoch 4 - iter 220/447 - loss 0.42198826 - time (sec): 4.90 - samples/sec: 8519.71 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-18 18:19:50,895 epoch 4 - iter 264/447 - loss 0.41309935 - time (sec): 5.95 - samples/sec: 8480.78 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-18 18:19:51,944 epoch 4 - iter 308/447 - loss 0.41310603 - time (sec): 7.00 - samples/sec: 8576.86 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-18 18:19:52,954 epoch 4 - iter 352/447 - loss 0.41193824 - time (sec): 8.01 - samples/sec: 8604.67 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-18 18:19:53,957 epoch 4 - iter 396/447 - loss 0.40773735 - time (sec): 9.02 - samples/sec: 8545.41 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-18 18:19:54,939 epoch 4 - iter 440/447 - loss 0.41410780 - time (sec): 10.00 - samples/sec: 8526.83 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-18 18:19:55,101 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-18 18:19:55,102 EPOCH 4 done: loss 0.4145 - lr: 0.000020
133
+ 2023-10-18 18:20:00,414 DEV : loss 0.32761430740356445 - f1-score (micro avg) 0.2488
134
+ 2023-10-18 18:20:00,442 saving best model
135
+ 2023-10-18 18:20:00,474 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-18 18:20:01,352 epoch 5 - iter 44/447 - loss 0.38465646 - time (sec): 0.88 - samples/sec: 10054.45 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-18 18:20:02,193 epoch 5 - iter 88/447 - loss 0.37699137 - time (sec): 1.72 - samples/sec: 9710.21 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-18 18:20:03,252 epoch 5 - iter 132/447 - loss 0.38217974 - time (sec): 2.78 - samples/sec: 9148.86 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-18 18:20:04,346 epoch 5 - iter 176/447 - loss 0.38342169 - time (sec): 3.87 - samples/sec: 8917.58 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-18 18:20:05,413 epoch 5 - iter 220/447 - loss 0.37709541 - time (sec): 4.94 - samples/sec: 8744.40 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-18 18:20:06,453 epoch 5 - iter 264/447 - loss 0.38233170 - time (sec): 5.98 - samples/sec: 8634.14 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-18 18:20:07,441 epoch 5 - iter 308/447 - loss 0.38767324 - time (sec): 6.97 - samples/sec: 8503.73 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-18 18:20:08,412 epoch 5 - iter 352/447 - loss 0.38682295 - time (sec): 7.94 - samples/sec: 8474.06 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-18 18:20:09,405 epoch 5 - iter 396/447 - loss 0.38506534 - time (sec): 8.93 - samples/sec: 8468.99 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-18 18:20:10,485 epoch 5 - iter 440/447 - loss 0.38807466 - time (sec): 10.01 - samples/sec: 8530.12 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-18 18:20:10,646 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-18 18:20:10,646 EPOCH 5 done: loss 0.3866 - lr: 0.000017
148
+ 2023-10-18 18:20:15,898 DEV : loss 0.31816405057907104 - f1-score (micro avg) 0.2825
149
+ 2023-10-18 18:20:15,924 saving best model
150
+ 2023-10-18 18:20:15,958 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-18 18:20:16,989 epoch 6 - iter 44/447 - loss 0.38056401 - time (sec): 1.03 - samples/sec: 7596.10 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-18 18:20:18,046 epoch 6 - iter 88/447 - loss 0.34090423 - time (sec): 2.09 - samples/sec: 8278.24 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-18 18:20:19,076 epoch 6 - iter 132/447 - loss 0.33389594 - time (sec): 3.12 - samples/sec: 8022.86 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-18 18:20:20,140 epoch 6 - iter 176/447 - loss 0.35003072 - time (sec): 4.18 - samples/sec: 8204.12 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-18 18:20:21,194 epoch 6 - iter 220/447 - loss 0.34996780 - time (sec): 5.24 - samples/sec: 8283.50 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-18 18:20:22,184 epoch 6 - iter 264/447 - loss 0.35206872 - time (sec): 6.23 - samples/sec: 8267.82 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-18 18:20:23,188 epoch 6 - iter 308/447 - loss 0.35224360 - time (sec): 7.23 - samples/sec: 8221.03 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-18 18:20:24,248 epoch 6 - iter 352/447 - loss 0.35331911 - time (sec): 8.29 - samples/sec: 8293.17 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-18 18:20:25,269 epoch 6 - iter 396/447 - loss 0.35145673 - time (sec): 9.31 - samples/sec: 8286.32 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-18 18:20:26,245 epoch 6 - iter 440/447 - loss 0.36336901 - time (sec): 10.29 - samples/sec: 8314.03 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-18 18:20:26,396 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-18 18:20:26,396 EPOCH 6 done: loss 0.3645 - lr: 0.000013
163
+ 2023-10-18 18:20:31,361 DEV : loss 0.3086220622062683 - f1-score (micro avg) 0.3146
164
+ 2023-10-18 18:20:31,387 saving best model
165
+ 2023-10-18 18:20:31,418 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-18 18:20:32,436 epoch 7 - iter 44/447 - loss 0.29886952 - time (sec): 1.02 - samples/sec: 9097.13 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-18 18:20:33,435 epoch 7 - iter 88/447 - loss 0.33142182 - time (sec): 2.02 - samples/sec: 8643.37 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-18 18:20:34,837 epoch 7 - iter 132/447 - loss 0.35366934 - time (sec): 3.42 - samples/sec: 7931.27 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-18 18:20:35,896 epoch 7 - iter 176/447 - loss 0.35387378 - time (sec): 4.48 - samples/sec: 7998.56 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-18 18:20:36,938 epoch 7 - iter 220/447 - loss 0.35892506 - time (sec): 5.52 - samples/sec: 7967.79 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-18 18:20:37,967 epoch 7 - iter 264/447 - loss 0.36143849 - time (sec): 6.55 - samples/sec: 7955.37 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-18 18:20:39,030 epoch 7 - iter 308/447 - loss 0.35509108 - time (sec): 7.61 - samples/sec: 7920.36 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-18 18:20:40,089 epoch 7 - iter 352/447 - loss 0.35704565 - time (sec): 8.67 - samples/sec: 7925.82 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-18 18:20:41,129 epoch 7 - iter 396/447 - loss 0.35473783 - time (sec): 9.71 - samples/sec: 7933.59 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-18 18:20:42,141 epoch 7 - iter 440/447 - loss 0.35569652 - time (sec): 10.72 - samples/sec: 7944.80 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-18 18:20:42,290 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-18 18:20:42,291 EPOCH 7 done: loss 0.3560 - lr: 0.000010
178
+ 2023-10-18 18:20:47,332 DEV : loss 0.31271788477897644 - f1-score (micro avg) 0.3084
179
+ 2023-10-18 18:20:47,359 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-18 18:20:48,418 epoch 8 - iter 44/447 - loss 0.35611823 - time (sec): 1.06 - samples/sec: 8936.31 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-18 18:20:49,444 epoch 8 - iter 88/447 - loss 0.33913763 - time (sec): 2.08 - samples/sec: 8439.88 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-18 18:20:50,449 epoch 8 - iter 132/447 - loss 0.35433170 - time (sec): 3.09 - samples/sec: 8459.77 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-18 18:20:51,446 epoch 8 - iter 176/447 - loss 0.36068417 - time (sec): 4.09 - samples/sec: 8370.91 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-18 18:20:52,446 epoch 8 - iter 220/447 - loss 0.36434763 - time (sec): 5.09 - samples/sec: 8367.59 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-18 18:20:53,489 epoch 8 - iter 264/447 - loss 0.35829319 - time (sec): 6.13 - samples/sec: 8302.49 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-18 18:20:54,488 epoch 8 - iter 308/447 - loss 0.35481202 - time (sec): 7.13 - samples/sec: 8227.89 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-18 18:20:55,533 epoch 8 - iter 352/447 - loss 0.35284971 - time (sec): 8.17 - samples/sec: 8234.63 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-18 18:20:56,603 epoch 8 - iter 396/447 - loss 0.34912209 - time (sec): 9.24 - samples/sec: 8207.41 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-18 18:20:57,689 epoch 8 - iter 440/447 - loss 0.35044302 - time (sec): 10.33 - samples/sec: 8232.50 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-18 18:20:57,851 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-18 18:20:57,852 EPOCH 8 done: loss 0.3489 - lr: 0.000007
192
+ 2023-10-18 18:21:03,152 DEV : loss 0.30949148535728455 - f1-score (micro avg) 0.3076
193
+ 2023-10-18 18:21:03,178 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-18 18:21:04,185 epoch 9 - iter 44/447 - loss 0.32539682 - time (sec): 1.01 - samples/sec: 8095.26 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-18 18:21:05,147 epoch 9 - iter 88/447 - loss 0.33926847 - time (sec): 1.97 - samples/sec: 7891.42 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-18 18:21:06,141 epoch 9 - iter 132/447 - loss 0.32815419 - time (sec): 2.96 - samples/sec: 8170.80 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-18 18:21:07,120 epoch 9 - iter 176/447 - loss 0.33881194 - time (sec): 3.94 - samples/sec: 8211.72 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-18 18:21:08,159 epoch 9 - iter 220/447 - loss 0.33813350 - time (sec): 4.98 - samples/sec: 8335.27 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-18 18:21:09,196 epoch 9 - iter 264/447 - loss 0.33632820 - time (sec): 6.02 - samples/sec: 8422.72 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-18 18:21:10,211 epoch 9 - iter 308/447 - loss 0.33126545 - time (sec): 7.03 - samples/sec: 8414.31 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-18 18:21:11,191 epoch 9 - iter 352/447 - loss 0.32912919 - time (sec): 8.01 - samples/sec: 8409.18 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-18 18:21:12,247 epoch 9 - iter 396/447 - loss 0.33415306 - time (sec): 9.07 - samples/sec: 8461.75 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-18 18:21:13,232 epoch 9 - iter 440/447 - loss 0.33729193 - time (sec): 10.05 - samples/sec: 8513.26 - lr: 0.000003 - momentum: 0.000000
204
+ 2023-10-18 18:21:13,386 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-18 18:21:13,386 EPOCH 9 done: loss 0.3373 - lr: 0.000003
206
+ 2023-10-18 18:21:18,663 DEV : loss 0.30950450897216797 - f1-score (micro avg) 0.3172
207
+ 2023-10-18 18:21:18,689 saving best model
208
+ 2023-10-18 18:21:18,727 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-18 18:21:19,781 epoch 10 - iter 44/447 - loss 0.38408660 - time (sec): 1.05 - samples/sec: 7711.43 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-18 18:21:20,865 epoch 10 - iter 88/447 - loss 0.36018147 - time (sec): 2.14 - samples/sec: 7669.34 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-18 18:21:21,926 epoch 10 - iter 132/447 - loss 0.33677093 - time (sec): 3.20 - samples/sec: 7694.37 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-18 18:21:22,942 epoch 10 - iter 176/447 - loss 0.33542182 - time (sec): 4.21 - samples/sec: 7781.88 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-18 18:21:23,921 epoch 10 - iter 220/447 - loss 0.33895587 - time (sec): 5.19 - samples/sec: 7785.80 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-18 18:21:24,933 epoch 10 - iter 264/447 - loss 0.33158441 - time (sec): 6.21 - samples/sec: 7904.22 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-18 18:21:25,897 epoch 10 - iter 308/447 - loss 0.33611357 - time (sec): 7.17 - samples/sec: 7965.44 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-18 18:21:26,978 epoch 10 - iter 352/447 - loss 0.33490933 - time (sec): 8.25 - samples/sec: 8196.71 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-18 18:21:27,987 epoch 10 - iter 396/447 - loss 0.33935900 - time (sec): 9.26 - samples/sec: 8215.23 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-18 18:21:28,964 epoch 10 - iter 440/447 - loss 0.33923817 - time (sec): 10.24 - samples/sec: 8278.81 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-18 18:21:29,144 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-18 18:21:29,144 EPOCH 10 done: loss 0.3389 - lr: 0.000000
221
+ 2023-10-18 18:21:34,419 DEV : loss 0.30806833505630493 - f1-score (micro avg) 0.3166
222
+ 2023-10-18 18:21:34,476 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-18 18:21:34,477 Loading model from best epoch ...
224
+ 2023-10-18 18:21:34,556 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
225
+ 2023-10-18 18:21:36,489
226
+ Results:
227
+ - F-score (micro) 0.3113
228
+ - F-score (macro) 0.1212
229
+ - Accuracy 0.1921
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.5018 0.4799 0.4906 596
235
+ pers 0.1140 0.1171 0.1156 333
236
+ org 0.0000 0.0000 0.0000 132
237
+ prod 0.0000 0.0000 0.0000 66
238
+ time 0.0000 0.0000 0.0000 49
239
+
240
+ micro avg 0.3564 0.2764 0.3113 1176
241
+ macro avg 0.1232 0.1194 0.1212 1176
242
+ weighted avg 0.2866 0.2764 0.2813 1176
243
+
244
+ 2023-10-18 18:21:36,489 ----------------------------------------------------------------------------------------------------