Hugging Face's logo

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

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
d111af7
•
1 Parent(s): ad9596a

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.1697650984.46dc0c540dd0.2878.2 +3 -0
  5. test.tsv +0 -0
  6. training.log +246 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c1e3374f99f120eec18902981e3b98638c0a16119df84581efb418e08f6b596
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 17:43:16 0.0000 1.7781 0.4776 0.0000 0.0000 0.0000 0.0000
3
+ 2 17:43:32 0.0000 0.5453 0.3955 0.5000 0.0023 0.0047 0.0023
4
+ 3 17:43:47 0.0000 0.4501 0.3401 0.3951 0.1134 0.1762 0.0986
5
+ 4 17:44:03 0.0000 0.4086 0.3386 0.4080 0.1837 0.2534 0.1489
6
+ 5 17:44:18 0.0000 0.3872 0.3214 0.3941 0.2299 0.2904 0.1760
7
+ 6 17:44:34 0.0000 0.3667 0.3145 0.4113 0.2557 0.3153 0.1941
8
+ 7 17:44:49 0.0000 0.3538 0.3077 0.3862 0.2721 0.3193 0.1986
9
+ 8 17:45:05 0.0000 0.3456 0.3056 0.3920 0.2823 0.3282 0.2049
10
+ 9 17:45:21 0.0000 0.3324 0.3064 0.3875 0.2760 0.3224 0.2007
11
+ 10 17:45:36 0.0000 0.3314 0.3061 0.3918 0.2776 0.3249 0.2026
runs/events.out.tfevents.1697650984.46dc0c540dd0.2878.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14966db6b501bf68632600b3878c0c76e6045aa3ab15fa0ed83f8d79d178a30
3
+ size 253592
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 17:43:04,080 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 17:43:04,080 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 17:43:04,080 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 17:43:04,080 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 17:43:04,080 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 17:43:04,080 Train: 3575 sentences
55
+ 2023-10-18 17:43:04,080 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 17:43:04,080 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 17:43:04,080 Training Params:
58
+ 2023-10-18 17:43:04,080 - learning_rate: "3e-05"
59
+ 2023-10-18 17:43:04,080 - mini_batch_size: "8"
60
+ 2023-10-18 17:43:04,080 - max_epochs: "10"
61
+ 2023-10-18 17:43:04,080 - shuffle: "True"
62
+ 2023-10-18 17:43:04,080 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 17:43:04,080 Plugins:
64
+ 2023-10-18 17:43:04,080 - TensorboardLogger
65
+ 2023-10-18 17:43:04,080 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 17:43:04,081 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 17:43:04,081 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 17:43:04,081 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 17:43:04,081 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 17:43:04,081 Computation:
71
+ 2023-10-18 17:43:04,081 - compute on device: cuda:0
72
+ 2023-10-18 17:43:04,081 - embedding storage: none
73
+ 2023-10-18 17:43:04,081 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 17:43:04,081 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-18 17:43:04,081 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 17:43:04,081 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 17:43:04,081 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 17:43:05,144 epoch 1 - iter 44/447 - loss 3.65841700 - time (sec): 1.06 - samples/sec: 7713.80 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-18 17:43:06,199 epoch 1 - iter 88/447 - loss 3.57458239 - time (sec): 2.12 - samples/sec: 7828.32 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-18 17:43:07,234 epoch 1 - iter 132/447 - loss 3.39036802 - time (sec): 3.15 - samples/sec: 7956.93 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-18 17:43:08,235 epoch 1 - iter 176/447 - loss 3.17329702 - time (sec): 4.15 - samples/sec: 8053.02 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-18 17:43:09,270 epoch 1 - iter 220/447 - loss 2.85941374 - time (sec): 5.19 - samples/sec: 8162.15 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-18 17:43:10,278 epoch 1 - iter 264/447 - loss 2.55730823 - time (sec): 6.20 - samples/sec: 8256.04 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-18 17:43:11,302 epoch 1 - iter 308/447 - loss 2.29715011 - time (sec): 7.22 - samples/sec: 8268.17 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-18 17:43:12,297 epoch 1 - iter 352/447 - loss 2.08270657 - time (sec): 8.22 - samples/sec: 8344.94 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-18 17:43:13,298 epoch 1 - iter 396/447 - loss 1.92246771 - time (sec): 9.22 - samples/sec: 8373.56 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-18 17:43:14,289 epoch 1 - iter 440/447 - loss 1.79687681 - time (sec): 10.21 - samples/sec: 8344.92 - lr: 0.000029 - momentum: 0.000000
88
+ 2023-10-18 17:43:14,437 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 17:43:14,437 EPOCH 1 done: loss 1.7781 - lr: 0.000029
90
+ 2023-10-18 17:43:16,615 DEV : loss 0.4775766432285309 - f1-score (micro avg) 0.0
91
+ 2023-10-18 17:43:16,640 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 17:43:17,685 epoch 2 - iter 44/447 - loss 0.59589924 - time (sec): 1.04 - samples/sec: 9017.00 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-18 17:43:18,715 epoch 2 - iter 88/447 - loss 0.56401892 - time (sec): 2.07 - samples/sec: 8811.19 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-18 17:43:19,789 epoch 2 - iter 132/447 - loss 0.56470757 - time (sec): 3.15 - samples/sec: 8633.50 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-18 17:43:20,799 epoch 2 - iter 176/447 - loss 0.56520829 - time (sec): 4.16 - samples/sec: 8345.06 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-18 17:43:21,845 epoch 2 - iter 220/447 - loss 0.55623726 - time (sec): 5.20 - samples/sec: 8399.40 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-18 17:43:22,847 epoch 2 - iter 264/447 - loss 0.54920417 - time (sec): 6.21 - samples/sec: 8342.39 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-18 17:43:23,868 epoch 2 - iter 308/447 - loss 0.55616306 - time (sec): 7.23 - samples/sec: 8312.48 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-18 17:43:24,933 epoch 2 - iter 352/447 - loss 0.55121105 - time (sec): 8.29 - samples/sec: 8275.02 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-18 17:43:25,962 epoch 2 - iter 396/447 - loss 0.55138490 - time (sec): 9.32 - samples/sec: 8261.89 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-18 17:43:26,977 epoch 2 - iter 440/447 - loss 0.54548733 - time (sec): 10.34 - samples/sec: 8232.48 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-18 17:43:27,142 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 17:43:27,142 EPOCH 2 done: loss 0.5453 - lr: 0.000027
104
+ 2023-10-18 17:43:32,386 DEV : loss 0.3954547643661499 - f1-score (micro avg) 0.0047
105
+ 2023-10-18 17:43:32,412 saving best model
106
+ 2023-10-18 17:43:32,446 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 17:43:33,438 epoch 3 - iter 44/447 - loss 0.46568998 - time (sec): 0.99 - samples/sec: 7873.33 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-18 17:43:34,448 epoch 3 - iter 88/447 - loss 0.48584638 - time (sec): 2.00 - samples/sec: 8243.38 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-18 17:43:35,426 epoch 3 - iter 132/447 - loss 0.48381208 - time (sec): 2.98 - samples/sec: 8146.00 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-18 17:43:36,433 epoch 3 - iter 176/447 - loss 0.46960679 - time (sec): 3.99 - samples/sec: 8330.61 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-18 17:43:37,453 epoch 3 - iter 220/447 - loss 0.46623827 - time (sec): 5.01 - samples/sec: 8371.67 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-18 17:43:38,479 epoch 3 - iter 264/447 - loss 0.46159907 - time (sec): 6.03 - samples/sec: 8435.20 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-18 17:43:39,455 epoch 3 - iter 308/447 - loss 0.45514585 - time (sec): 7.01 - samples/sec: 8383.41 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-18 17:43:40,425 epoch 3 - iter 352/447 - loss 0.45263927 - time (sec): 7.98 - samples/sec: 8415.36 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-18 17:43:41,417 epoch 3 - iter 396/447 - loss 0.45536448 - time (sec): 8.97 - samples/sec: 8428.60 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-18 17:43:42,459 epoch 3 - iter 440/447 - loss 0.45158447 - time (sec): 10.01 - samples/sec: 8515.27 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-18 17:43:42,605 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 17:43:42,606 EPOCH 3 done: loss 0.4501 - lr: 0.000023
119
+ 2023-10-18 17:43:47,818 DEV : loss 0.34006714820861816 - f1-score (micro avg) 0.1762
120
+ 2023-10-18 17:43:47,844 saving best model
121
+ 2023-10-18 17:43:47,878 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 17:43:48,930 epoch 4 - iter 44/447 - loss 0.40096435 - time (sec): 1.05 - samples/sec: 8641.77 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-18 17:43:49,946 epoch 4 - iter 88/447 - loss 0.42313975 - time (sec): 2.07 - samples/sec: 8518.95 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-18 17:43:50,941 epoch 4 - iter 132/447 - loss 0.43615643 - time (sec): 3.06 - samples/sec: 8605.19 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-18 17:43:51,951 epoch 4 - iter 176/447 - loss 0.43038311 - time (sec): 4.07 - samples/sec: 8692.14 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-18 17:43:52,941 epoch 4 - iter 220/447 - loss 0.42491578 - time (sec): 5.06 - samples/sec: 8589.74 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-18 17:43:53,937 epoch 4 - iter 264/447 - loss 0.41934533 - time (sec): 6.06 - samples/sec: 8550.42 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-18 17:43:54,941 epoch 4 - iter 308/447 - loss 0.41228277 - time (sec): 7.06 - samples/sec: 8549.29 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-18 17:43:56,014 epoch 4 - iter 352/447 - loss 0.40713092 - time (sec): 8.14 - samples/sec: 8457.46 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-18 17:43:57,053 epoch 4 - iter 396/447 - loss 0.41039188 - time (sec): 9.17 - samples/sec: 8419.34 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-18 17:43:58,086 epoch 4 - iter 440/447 - loss 0.40812616 - time (sec): 10.21 - samples/sec: 8356.67 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-18 17:43:58,234 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 17:43:58,234 EPOCH 4 done: loss 0.4086 - lr: 0.000020
134
+ 2023-10-18 17:44:03,498 DEV : loss 0.33860334753990173 - f1-score (micro avg) 0.2534
135
+ 2023-10-18 17:44:03,524 saving best model
136
+ 2023-10-18 17:44:03,556 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 17:44:04,590 epoch 5 - iter 44/447 - loss 0.36098289 - time (sec): 1.03 - samples/sec: 7878.70 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-18 17:44:05,601 epoch 5 - iter 88/447 - loss 0.39788915 - time (sec): 2.04 - samples/sec: 7724.01 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-18 17:44:06,617 epoch 5 - iter 132/447 - loss 0.37581248 - time (sec): 3.06 - samples/sec: 7780.33 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-18 17:44:07,695 epoch 5 - iter 176/447 - loss 0.37494525 - time (sec): 4.14 - samples/sec: 8048.39 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-18 17:44:08,706 epoch 5 - iter 220/447 - loss 0.37534730 - time (sec): 5.15 - samples/sec: 8161.94 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-18 17:44:09,732 epoch 5 - iter 264/447 - loss 0.37572997 - time (sec): 6.18 - samples/sec: 8254.05 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-18 17:44:10,768 epoch 5 - iter 308/447 - loss 0.37803576 - time (sec): 7.21 - samples/sec: 8247.46 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-18 17:44:11,797 epoch 5 - iter 352/447 - loss 0.38296535 - time (sec): 8.24 - samples/sec: 8275.23 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-18 17:44:12,634 epoch 5 - iter 396/447 - loss 0.38360699 - time (sec): 9.08 - samples/sec: 8430.98 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-18 17:44:13,491 epoch 5 - iter 440/447 - loss 0.38337258 - time (sec): 9.93 - samples/sec: 8583.20 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-18 17:44:13,633 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 17:44:13,633 EPOCH 5 done: loss 0.3872 - lr: 0.000017
149
+ 2023-10-18 17:44:18,644 DEV : loss 0.3213781416416168 - f1-score (micro avg) 0.2904
150
+ 2023-10-18 17:44:18,669 saving best model
151
+ 2023-10-18 17:44:18,713 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-18 17:44:19,667 epoch 6 - iter 44/447 - loss 0.39724277 - time (sec): 0.95 - samples/sec: 8724.03 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-18 17:44:20,673 epoch 6 - iter 88/447 - loss 0.35175566 - time (sec): 1.96 - samples/sec: 8833.06 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-18 17:44:21,765 epoch 6 - iter 132/447 - loss 0.33678911 - time (sec): 3.05 - samples/sec: 8716.95 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-18 17:44:22,726 epoch 6 - iter 176/447 - loss 0.35169461 - time (sec): 4.01 - samples/sec: 8618.93 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-18 17:44:24,015 epoch 6 - iter 220/447 - loss 0.36233877 - time (sec): 5.30 - samples/sec: 8117.05 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-18 17:44:24,995 epoch 6 - iter 264/447 - loss 0.36252351 - time (sec): 6.28 - samples/sec: 8149.49 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-18 17:44:25,991 epoch 6 - iter 308/447 - loss 0.36318080 - time (sec): 7.28 - samples/sec: 8180.81 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-18 17:44:27,018 epoch 6 - iter 352/447 - loss 0.36149952 - time (sec): 8.31 - samples/sec: 8230.02 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-18 17:44:28,069 epoch 6 - iter 396/447 - loss 0.36522263 - time (sec): 9.36 - samples/sec: 8223.75 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-18 17:44:29,035 epoch 6 - iter 440/447 - loss 0.36696941 - time (sec): 10.32 - samples/sec: 8242.81 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-18 17:44:29,194 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-18 17:44:29,194 EPOCH 6 done: loss 0.3667 - lr: 0.000013
164
+ 2023-10-18 17:44:34,156 DEV : loss 0.3145124316215515 - f1-score (micro avg) 0.3153
165
+ 2023-10-18 17:44:34,182 saving best model
166
+ 2023-10-18 17:44:34,215 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-18 17:44:35,237 epoch 7 - iter 44/447 - loss 0.33254949 - time (sec): 1.02 - samples/sec: 8026.91 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-18 17:44:36,289 epoch 7 - iter 88/447 - loss 0.33867551 - time (sec): 2.07 - samples/sec: 8083.21 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-18 17:44:37,293 epoch 7 - iter 132/447 - loss 0.34664698 - time (sec): 3.08 - samples/sec: 7937.45 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-18 17:44:38,336 epoch 7 - iter 176/447 - loss 0.35008385 - time (sec): 4.12 - samples/sec: 8059.32 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-18 17:44:39,361 epoch 7 - iter 220/447 - loss 0.34738790 - time (sec): 5.15 - samples/sec: 8109.70 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-18 17:44:40,353 epoch 7 - iter 264/447 - loss 0.34675104 - time (sec): 6.14 - samples/sec: 8102.12 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-18 17:44:41,348 epoch 7 - iter 308/447 - loss 0.35204448 - time (sec): 7.13 - samples/sec: 8185.69 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-18 17:44:42,408 epoch 7 - iter 352/447 - loss 0.35087997 - time (sec): 8.19 - samples/sec: 8314.56 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-18 17:44:43,385 epoch 7 - iter 396/447 - loss 0.34971556 - time (sec): 9.17 - samples/sec: 8296.34 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-18 17:44:44,485 epoch 7 - iter 440/447 - loss 0.35367941 - time (sec): 10.27 - samples/sec: 8320.95 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-18 17:44:44,643 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-18 17:44:44,644 EPOCH 7 done: loss 0.3538 - lr: 0.000010
179
+ 2023-10-18 17:44:49,903 DEV : loss 0.30769509077072144 - f1-score (micro avg) 0.3193
180
+ 2023-10-18 17:44:49,929 saving best model
181
+ 2023-10-18 17:44:49,962 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-18 17:44:50,958 epoch 8 - iter 44/447 - loss 0.33422276 - time (sec): 0.99 - samples/sec: 8165.06 - lr: 0.000010 - momentum: 0.000000
183
+ 2023-10-18 17:44:51,968 epoch 8 - iter 88/447 - loss 0.33262216 - time (sec): 2.01 - samples/sec: 8318.97 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-18 17:44:52,970 epoch 8 - iter 132/447 - loss 0.33401019 - time (sec): 3.01 - samples/sec: 8188.09 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-18 17:44:54,003 epoch 8 - iter 176/447 - loss 0.34047320 - time (sec): 4.04 - samples/sec: 8112.27 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-18 17:44:55,056 epoch 8 - iter 220/447 - loss 0.34431160 - time (sec): 5.09 - samples/sec: 8109.95 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-18 17:44:56,114 epoch 8 - iter 264/447 - loss 0.35113437 - time (sec): 6.15 - samples/sec: 8116.36 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-18 17:44:57,217 epoch 8 - iter 308/447 - loss 0.34790518 - time (sec): 7.25 - samples/sec: 8267.13 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-18 17:44:58,227 epoch 8 - iter 352/447 - loss 0.35030628 - time (sec): 8.26 - samples/sec: 8323.70 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-18 17:44:59,235 epoch 8 - iter 396/447 - loss 0.35029828 - time (sec): 9.27 - samples/sec: 8291.91 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-18 17:45:00,271 epoch 8 - iter 440/447 - loss 0.34699832 - time (sec): 10.31 - samples/sec: 8284.79 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-18 17:45:00,431 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-18 17:45:00,431 EPOCH 8 done: loss 0.3456 - lr: 0.000007
194
+ 2023-10-18 17:45:05,789 DEV : loss 0.3056319057941437 - f1-score (micro avg) 0.3282
195
+ 2023-10-18 17:45:05,815 saving best model
196
+ 2023-10-18 17:45:05,850 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-18 17:45:06,908 epoch 9 - iter 44/447 - loss 0.33033877 - time (sec): 1.06 - samples/sec: 7764.12 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-18 17:45:07,972 epoch 9 - iter 88/447 - loss 0.32438109 - time (sec): 2.12 - samples/sec: 7960.53 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-18 17:45:08,980 epoch 9 - iter 132/447 - loss 0.33253674 - time (sec): 3.13 - samples/sec: 8029.34 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-18 17:45:10,020 epoch 9 - iter 176/447 - loss 0.32688422 - time (sec): 4.17 - samples/sec: 8005.44 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-18 17:45:11,047 epoch 9 - iter 220/447 - loss 0.32819605 - time (sec): 5.20 - samples/sec: 7999.77 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-18 17:45:12,072 epoch 9 - iter 264/447 - loss 0.32313458 - time (sec): 6.22 - samples/sec: 8130.90 - lr: 0.000005 - momentum: 0.000000
203
+ 2023-10-18 17:45:13,119 epoch 9 - iter 308/447 - loss 0.32996163 - time (sec): 7.27 - samples/sec: 8219.22 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-18 17:45:14,091 epoch 9 - iter 352/447 - loss 0.33131371 - time (sec): 8.24 - samples/sec: 8213.97 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-18 17:45:15,118 epoch 9 - iter 396/447 - loss 0.33364538 - time (sec): 9.27 - samples/sec: 8198.10 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-18 17:45:16,158 epoch 9 - iter 440/447 - loss 0.33168082 - time (sec): 10.31 - samples/sec: 8290.47 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-18 17:45:16,310 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-18 17:45:16,310 EPOCH 9 done: loss 0.3324 - lr: 0.000003
209
+ 2023-10-18 17:45:21,581 DEV : loss 0.30642732977867126 - f1-score (micro avg) 0.3224
210
+ 2023-10-18 17:45:21,606 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-18 17:45:22,469 epoch 10 - iter 44/447 - loss 0.31571016 - time (sec): 0.86 - samples/sec: 9189.95 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-18 17:45:23,521 epoch 10 - iter 88/447 - loss 0.30383316 - time (sec): 1.91 - samples/sec: 8967.01 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-18 17:45:24,548 epoch 10 - iter 132/447 - loss 0.31717265 - time (sec): 2.94 - samples/sec: 8708.30 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-18 17:45:25,537 epoch 10 - iter 176/447 - loss 0.32673786 - time (sec): 3.93 - samples/sec: 8612.34 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-18 17:45:26,610 epoch 10 - iter 220/447 - loss 0.33065968 - time (sec): 5.00 - samples/sec: 8635.05 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-18 17:45:27,600 epoch 10 - iter 264/447 - loss 0.32901583 - time (sec): 5.99 - samples/sec: 8607.52 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-18 17:45:28,597 epoch 10 - iter 308/447 - loss 0.33533615 - time (sec): 6.99 - samples/sec: 8580.40 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 17:45:29,593 epoch 10 - iter 352/447 - loss 0.33627064 - time (sec): 7.99 - samples/sec: 8559.46 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-18 17:45:30,644 epoch 10 - iter 396/447 - loss 0.33572652 - time (sec): 9.04 - samples/sec: 8512.58 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-18 17:45:31,694 epoch 10 - iter 440/447 - loss 0.33227974 - time (sec): 10.09 - samples/sec: 8452.37 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-18 17:45:31,857 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-18 17:45:31,857 EPOCH 10 done: loss 0.3314 - lr: 0.000000
223
+ 2023-10-18 17:45:36,818 DEV : loss 0.3060940206050873 - f1-score (micro avg) 0.3249
224
+ 2023-10-18 17:45:36,875 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-18 17:45:36,875 Loading model from best epoch ...
226
+ 2023-10-18 17:45:36,950 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
227
+ 2023-10-18 17:45:39,234
228
+ Results:
229
+ - F-score (micro) 0.3356
230
+ - F-score (macro) 0.1275
231
+ - Accuracy 0.2112
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ loc 0.4857 0.5117 0.4984 596
237
+ pers 0.1595 0.1231 0.1390 333
238
+ org 0.0000 0.0000 0.0000 132
239
+ prod 0.0000 0.0000 0.0000 66
240
+ time 0.0000 0.0000 0.0000 49
241
+
242
+ micro avg 0.3905 0.2942 0.3356 1176
243
+ macro avg 0.1290 0.1270 0.1275 1176
244
+ weighted avg 0.2913 0.2942 0.2919 1176
245
+
246
+ 2023-10-18 17:45:39,234 ----------------------------------------------------------------------------------------------------