Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
79aa17f
•
1 Parent(s): 11651a2

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.1697558339.4c6324b99746.1390.4 +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 sha256:3501a76a9976dec1d1c5cb3a3440195a14e11faa0c3be186871c288ee2fc53dc
3
+ size 440966725
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 15:59:49 0.0000 0.8401 0.1743 0.5858 0.5950 0.5904 0.4334
3
+ 2 16:00:45 0.0000 0.1648 0.1194 0.7221 0.7131 0.7175 0.5798
4
+ 3 16:01:41 0.0000 0.0860 0.1344 0.7225 0.7654 0.7434 0.6157
5
+ 4 16:02:38 0.0000 0.0547 0.1577 0.7615 0.7514 0.7564 0.6293
6
+ 5 16:03:34 0.0000 0.0336 0.1874 0.7521 0.7686 0.7602 0.6354
7
+ 6 16:04:30 0.0000 0.0233 0.1992 0.8019 0.7756 0.7886 0.6671
8
+ 7 16:05:25 0.0000 0.0151 0.1998 0.7792 0.8139 0.7962 0.6813
9
+ 8 16:06:21 0.0000 0.0085 0.2182 0.7804 0.8030 0.7915 0.6726
10
+ 9 16:07:15 0.0000 0.0049 0.2285 0.7911 0.8022 0.7966 0.6808
11
+ 10 16:08:11 0.0000 0.0035 0.2287 0.7861 0.8045 0.7952 0.6774
runs/events.out.tfevents.1697558339.4c6324b99746.1390.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b5b26aa70e9d464f26499d0dfd349e7dee4ef5cc872e65694a06f63eee3391
3
+ size 253592
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 15:58:59,059 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 15:58:59,061 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): ElectraModel(
5
+ (embeddings): ElectraEmbeddings(
6
+ (word_embeddings): Embedding(32001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): ElectraEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x ElectraLayer(
15
+ (attention): ElectraAttention(
16
+ (self): ElectraSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): ElectraSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): ElectraIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): ElectraOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ )
41
+ )
42
+ (locked_dropout): LockedDropout(p=0.5)
43
+ (linear): Linear(in_features=768, out_features=21, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 15:58:59,061 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 15:58:59,062 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
48
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
49
+ 2023-10-17 15:58:59,062 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 15:58:59,062 Train: 3575 sentences
51
+ 2023-10-17 15:58:59,062 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 15:58:59,062 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 15:58:59,062 Training Params:
54
+ 2023-10-17 15:58:59,062 - learning_rate: "3e-05"
55
+ 2023-10-17 15:58:59,062 - mini_batch_size: "8"
56
+ 2023-10-17 15:58:59,062 - max_epochs: "10"
57
+ 2023-10-17 15:58:59,062 - shuffle: "True"
58
+ 2023-10-17 15:58:59,062 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 15:58:59,062 Plugins:
60
+ 2023-10-17 15:58:59,063 - TensorboardLogger
61
+ 2023-10-17 15:58:59,063 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 15:58:59,063 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 15:58:59,063 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 15:58:59,063 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 15:58:59,063 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 15:58:59,063 Computation:
67
+ 2023-10-17 15:58:59,063 - compute on device: cuda:0
68
+ 2023-10-17 15:58:59,063 - embedding storage: none
69
+ 2023-10-17 15:58:59,063 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 15:58:59,063 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
71
+ 2023-10-17 15:58:59,063 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 15:58:59,063 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 15:58:59,064 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 15:59:03,268 epoch 1 - iter 44/447 - loss 3.75328637 - time (sec): 4.20 - samples/sec: 2112.58 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 15:59:07,512 epoch 1 - iter 88/447 - loss 2.79174559 - time (sec): 8.45 - samples/sec: 2030.17 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 15:59:11,524 epoch 1 - iter 132/447 - loss 2.08551841 - time (sec): 12.46 - samples/sec: 1987.11 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 15:59:16,031 epoch 1 - iter 176/447 - loss 1.63894890 - time (sec): 16.97 - samples/sec: 2016.62 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 15:59:20,141 epoch 1 - iter 220/447 - loss 1.39670438 - time (sec): 21.08 - samples/sec: 2016.11 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 15:59:24,433 epoch 1 - iter 264/447 - loss 1.22305966 - time (sec): 25.37 - samples/sec: 2016.49 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 15:59:28,479 epoch 1 - iter 308/447 - loss 1.10231203 - time (sec): 29.41 - samples/sec: 2005.73 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 15:59:32,764 epoch 1 - iter 352/447 - loss 1.00085629 - time (sec): 33.70 - samples/sec: 2007.65 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 15:59:37,492 epoch 1 - iter 396/447 - loss 0.91299761 - time (sec): 38.43 - samples/sec: 2004.60 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 15:59:41,758 epoch 1 - iter 440/447 - loss 0.84847471 - time (sec): 42.69 - samples/sec: 2001.55 - lr: 0.000029 - momentum: 0.000000
84
+ 2023-10-17 15:59:42,398 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 15:59:42,398 EPOCH 1 done: loss 0.8401 - lr: 0.000029
86
+ 2023-10-17 15:59:49,299 DEV : loss 0.1743467152118683 - f1-score (micro avg) 0.5904
87
+ 2023-10-17 15:59:49,362 saving best model
88
+ 2023-10-17 15:59:50,000 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 15:59:54,169 epoch 2 - iter 44/447 - loss 0.20202135 - time (sec): 4.17 - samples/sec: 2020.85 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 15:59:58,785 epoch 2 - iter 88/447 - loss 0.19013888 - time (sec): 8.78 - samples/sec: 2021.47 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 16:00:03,225 epoch 2 - iter 132/447 - loss 0.19608616 - time (sec): 13.22 - samples/sec: 1930.61 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 16:00:08,005 epoch 2 - iter 176/447 - loss 0.18596049 - time (sec): 18.00 - samples/sec: 1937.03 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 16:00:12,138 epoch 2 - iter 220/447 - loss 0.18035707 - time (sec): 22.13 - samples/sec: 1977.69 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 16:00:16,236 epoch 2 - iter 264/447 - loss 0.17461322 - time (sec): 26.23 - samples/sec: 1965.57 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 16:00:20,493 epoch 2 - iter 308/447 - loss 0.16847653 - time (sec): 30.49 - samples/sec: 1986.10 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 16:00:24,739 epoch 2 - iter 352/447 - loss 0.16607108 - time (sec): 34.74 - samples/sec: 1993.31 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 16:00:28,945 epoch 2 - iter 396/447 - loss 0.16349240 - time (sec): 38.94 - samples/sec: 1988.06 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 16:00:33,205 epoch 2 - iter 440/447 - loss 0.16613347 - time (sec): 43.20 - samples/sec: 1976.45 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 16:00:33,854 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 16:00:33,855 EPOCH 2 done: loss 0.1648 - lr: 0.000027
101
+ 2023-10-17 16:00:45,420 DEV : loss 0.11944183707237244 - f1-score (micro avg) 0.7175
102
+ 2023-10-17 16:00:45,481 saving best model
103
+ 2023-10-17 16:00:46,934 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 16:00:51,110 epoch 3 - iter 44/447 - loss 0.08131650 - time (sec): 4.17 - samples/sec: 1891.39 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 16:00:55,405 epoch 3 - iter 88/447 - loss 0.08702455 - time (sec): 8.47 - samples/sec: 1967.19 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 16:00:59,963 epoch 3 - iter 132/447 - loss 0.07972396 - time (sec): 13.02 - samples/sec: 1964.70 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 16:01:04,142 epoch 3 - iter 176/447 - loss 0.07975901 - time (sec): 17.20 - samples/sec: 1939.38 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 16:01:08,611 epoch 3 - iter 220/447 - loss 0.08247967 - time (sec): 21.67 - samples/sec: 1967.29 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 16:01:12,697 epoch 3 - iter 264/447 - loss 0.08537389 - time (sec): 25.76 - samples/sec: 1978.18 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 16:01:17,006 epoch 3 - iter 308/447 - loss 0.08411404 - time (sec): 30.07 - samples/sec: 1987.82 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 16:01:21,139 epoch 3 - iter 352/447 - loss 0.08280911 - time (sec): 34.20 - samples/sec: 1990.44 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 16:01:25,354 epoch 3 - iter 396/447 - loss 0.08456497 - time (sec): 38.42 - samples/sec: 1993.20 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 16:01:29,534 epoch 3 - iter 440/447 - loss 0.08638185 - time (sec): 42.60 - samples/sec: 1984.93 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 16:01:30,441 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 16:01:30,442 EPOCH 3 done: loss 0.0860 - lr: 0.000023
116
+ 2023-10-17 16:01:41,799 DEV : loss 0.13438037037849426 - f1-score (micro avg) 0.7434
117
+ 2023-10-17 16:01:41,855 saving best model
118
+ 2023-10-17 16:01:43,314 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 16:01:47,660 epoch 4 - iter 44/447 - loss 0.05444230 - time (sec): 4.34 - samples/sec: 2164.26 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 16:01:52,647 epoch 4 - iter 88/447 - loss 0.05193996 - time (sec): 9.33 - samples/sec: 2018.23 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-17 16:01:57,154 epoch 4 - iter 132/447 - loss 0.05306498 - time (sec): 13.83 - samples/sec: 1941.12 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 16:02:01,286 epoch 4 - iter 176/447 - loss 0.05252827 - time (sec): 17.97 - samples/sec: 1934.72 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 16:02:05,472 epoch 4 - iter 220/447 - loss 0.05261466 - time (sec): 22.15 - samples/sec: 1950.76 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-17 16:02:09,829 epoch 4 - iter 264/447 - loss 0.05182422 - time (sec): 26.51 - samples/sec: 1953.80 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 16:02:13,882 epoch 4 - iter 308/447 - loss 0.05086636 - time (sec): 30.56 - samples/sec: 1955.14 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 16:02:18,196 epoch 4 - iter 352/447 - loss 0.05167051 - time (sec): 34.88 - samples/sec: 1968.66 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-17 16:02:22,250 epoch 4 - iter 396/447 - loss 0.05200802 - time (sec): 38.93 - samples/sec: 1971.49 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 16:02:26,437 epoch 4 - iter 440/447 - loss 0.05402605 - time (sec): 43.12 - samples/sec: 1980.43 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-17 16:02:27,080 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 16:02:27,080 EPOCH 4 done: loss 0.0547 - lr: 0.000020
131
+ 2023-10-17 16:02:38,092 DEV : loss 0.15765978395938873 - f1-score (micro avg) 0.7564
132
+ 2023-10-17 16:02:38,149 saving best model
133
+ 2023-10-17 16:02:39,959 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 16:02:44,066 epoch 5 - iter 44/447 - loss 0.02163230 - time (sec): 4.10 - samples/sec: 2014.16 - lr: 0.000020 - momentum: 0.000000
135
+ 2023-10-17 16:02:48,624 epoch 5 - iter 88/447 - loss 0.02328428 - time (sec): 8.66 - samples/sec: 2063.37 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 16:02:52,824 epoch 5 - iter 132/447 - loss 0.02815843 - time (sec): 12.86 - samples/sec: 2055.05 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 16:02:57,091 epoch 5 - iter 176/447 - loss 0.03162369 - time (sec): 17.13 - samples/sec: 2030.52 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-17 16:03:01,212 epoch 5 - iter 220/447 - loss 0.03390401 - time (sec): 21.25 - samples/sec: 2016.40 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 16:03:05,489 epoch 5 - iter 264/447 - loss 0.03510618 - time (sec): 25.53 - samples/sec: 1996.63 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 16:03:09,836 epoch 5 - iter 308/447 - loss 0.03570858 - time (sec): 29.87 - samples/sec: 2011.06 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-17 16:03:14,158 epoch 5 - iter 352/447 - loss 0.03496530 - time (sec): 34.19 - samples/sec: 2017.95 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 16:03:18,233 epoch 5 - iter 396/447 - loss 0.03442000 - time (sec): 38.27 - samples/sec: 2012.70 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 16:03:22,296 epoch 5 - iter 440/447 - loss 0.03343545 - time (sec): 42.33 - samples/sec: 2012.39 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-17 16:03:22,912 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 16:03:22,912 EPOCH 5 done: loss 0.0336 - lr: 0.000017
146
+ 2023-10-17 16:03:34,146 DEV : loss 0.18739798665046692 - f1-score (micro avg) 0.7602
147
+ 2023-10-17 16:03:34,211 saving best model
148
+ 2023-10-17 16:03:35,654 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 16:03:40,239 epoch 6 - iter 44/447 - loss 0.02567182 - time (sec): 4.58 - samples/sec: 1915.30 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 16:03:44,559 epoch 6 - iter 88/447 - loss 0.02386413 - time (sec): 8.90 - samples/sec: 1963.68 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-17 16:03:48,830 epoch 6 - iter 132/447 - loss 0.02665298 - time (sec): 13.17 - samples/sec: 1938.11 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-17 16:03:52,872 epoch 6 - iter 176/447 - loss 0.02638426 - time (sec): 17.21 - samples/sec: 1966.56 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 16:03:56,972 epoch 6 - iter 220/447 - loss 0.02455531 - time (sec): 21.31 - samples/sec: 2002.06 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-17 16:04:01,089 epoch 6 - iter 264/447 - loss 0.02439035 - time (sec): 25.43 - samples/sec: 1989.32 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-17 16:04:05,048 epoch 6 - iter 308/447 - loss 0.02384438 - time (sec): 29.39 - samples/sec: 1990.74 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 16:04:09,461 epoch 6 - iter 352/447 - loss 0.02340501 - time (sec): 33.80 - samples/sec: 1998.99 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-17 16:04:13,567 epoch 6 - iter 396/447 - loss 0.02300984 - time (sec): 37.91 - samples/sec: 1999.25 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-17 16:04:18,493 epoch 6 - iter 440/447 - loss 0.02335350 - time (sec): 42.83 - samples/sec: 1992.49 - lr: 0.000013 - momentum: 0.000000
159
+ 2023-10-17 16:04:19,112 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 16:04:19,113 EPOCH 6 done: loss 0.0233 - lr: 0.000013
161
+ 2023-10-17 16:04:30,550 DEV : loss 0.1992470622062683 - f1-score (micro avg) 0.7886
162
+ 2023-10-17 16:04:30,611 saving best model
163
+ 2023-10-17 16:04:32,023 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-17 16:04:36,035 epoch 7 - iter 44/447 - loss 0.01165349 - time (sec): 4.01 - samples/sec: 2154.32 - lr: 0.000013 - momentum: 0.000000
165
+ 2023-10-17 16:04:39,982 epoch 7 - iter 88/447 - loss 0.01076700 - time (sec): 7.95 - samples/sec: 2043.10 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-17 16:04:43,960 epoch 7 - iter 132/447 - loss 0.01479762 - time (sec): 11.93 - samples/sec: 2072.77 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-17 16:04:48,204 epoch 7 - iter 176/447 - loss 0.01368042 - time (sec): 16.18 - samples/sec: 2089.53 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-17 16:04:52,249 epoch 7 - iter 220/447 - loss 0.01535559 - time (sec): 20.22 - samples/sec: 2089.04 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-17 16:04:56,520 epoch 7 - iter 264/447 - loss 0.01497302 - time (sec): 24.49 - samples/sec: 2078.72 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-17 16:05:00,828 epoch 7 - iter 308/447 - loss 0.01480877 - time (sec): 28.80 - samples/sec: 2071.01 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-17 16:05:05,246 epoch 7 - iter 352/447 - loss 0.01534251 - time (sec): 33.22 - samples/sec: 2063.40 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-17 16:05:09,457 epoch 7 - iter 396/447 - loss 0.01577918 - time (sec): 37.43 - samples/sec: 2062.23 - lr: 0.000010 - momentum: 0.000000
173
+ 2023-10-17 16:05:13,493 epoch 7 - iter 440/447 - loss 0.01506408 - time (sec): 41.47 - samples/sec: 2055.56 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-17 16:05:14,130 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 16:05:14,130 EPOCH 7 done: loss 0.0151 - lr: 0.000010
176
+ 2023-10-17 16:05:25,738 DEV : loss 0.19981977343559265 - f1-score (micro avg) 0.7962
177
+ 2023-10-17 16:05:25,795 saving best model
178
+ 2023-10-17 16:05:27,205 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-17 16:05:31,392 epoch 8 - iter 44/447 - loss 0.00747848 - time (sec): 4.18 - samples/sec: 2091.78 - lr: 0.000010 - momentum: 0.000000
180
+ 2023-10-17 16:05:35,357 epoch 8 - iter 88/447 - loss 0.00942650 - time (sec): 8.15 - samples/sec: 2073.55 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-17 16:05:39,452 epoch 8 - iter 132/447 - loss 0.01019952 - time (sec): 12.24 - samples/sec: 2051.86 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-17 16:05:43,674 epoch 8 - iter 176/447 - loss 0.01051999 - time (sec): 16.46 - samples/sec: 2018.14 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-17 16:05:48,447 epoch 8 - iter 220/447 - loss 0.00988506 - time (sec): 21.24 - samples/sec: 2029.40 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-17 16:05:52,743 epoch 8 - iter 264/447 - loss 0.00923766 - time (sec): 25.53 - samples/sec: 2028.90 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-17 16:05:56,918 epoch 8 - iter 308/447 - loss 0.00896950 - time (sec): 29.71 - samples/sec: 2045.61 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-17 16:06:01,147 epoch 8 - iter 352/447 - loss 0.00877691 - time (sec): 33.94 - samples/sec: 2033.23 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-17 16:06:05,239 epoch 8 - iter 396/447 - loss 0.00839354 - time (sec): 38.03 - samples/sec: 2027.39 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-17 16:06:09,389 epoch 8 - iter 440/447 - loss 0.00837721 - time (sec): 42.18 - samples/sec: 2020.17 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-17 16:06:10,039 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 16:06:10,039 EPOCH 8 done: loss 0.0085 - lr: 0.000007
191
+ 2023-10-17 16:06:21,780 DEV : loss 0.21822908520698547 - f1-score (micro avg) 0.7915
192
+ 2023-10-17 16:06:21,841 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-17 16:06:25,974 epoch 9 - iter 44/447 - loss 0.00971530 - time (sec): 4.13 - samples/sec: 2046.00 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-17 16:06:30,128 epoch 9 - iter 88/447 - loss 0.00589797 - time (sec): 8.28 - samples/sec: 2051.38 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-17 16:06:34,084 epoch 9 - iter 132/447 - loss 0.00489136 - time (sec): 12.24 - samples/sec: 2019.89 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-17 16:06:38,278 epoch 9 - iter 176/447 - loss 0.00468170 - time (sec): 16.43 - samples/sec: 2041.42 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-17 16:06:42,419 epoch 9 - iter 220/447 - loss 0.00474446 - time (sec): 20.58 - samples/sec: 2047.85 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-17 16:06:46,728 epoch 9 - iter 264/447 - loss 0.00529921 - time (sec): 24.88 - samples/sec: 2054.82 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-17 16:06:50,744 epoch 9 - iter 308/447 - loss 0.00534902 - time (sec): 28.90 - samples/sec: 2056.82 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-17 16:06:54,817 epoch 9 - iter 352/447 - loss 0.00532626 - time (sec): 32.97 - samples/sec: 2060.60 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-17 16:06:59,232 epoch 9 - iter 396/447 - loss 0.00517003 - time (sec): 37.39 - samples/sec: 2059.50 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-17 16:07:03,570 epoch 9 - iter 440/447 - loss 0.00496894 - time (sec): 41.73 - samples/sec: 2052.54 - lr: 0.000003 - momentum: 0.000000
203
+ 2023-10-17 16:07:04,188 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 16:07:04,188 EPOCH 9 done: loss 0.0049 - lr: 0.000003
205
+ 2023-10-17 16:07:15,489 DEV : loss 0.2285258173942566 - f1-score (micro avg) 0.7966
206
+ 2023-10-17 16:07:15,545 saving best model
207
+ 2023-10-17 16:07:16,964 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-17 16:07:21,376 epoch 10 - iter 44/447 - loss 0.00131630 - time (sec): 4.41 - samples/sec: 2067.92 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 16:07:25,410 epoch 10 - iter 88/447 - loss 0.00319788 - time (sec): 8.44 - samples/sec: 2035.90 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-17 16:07:29,655 epoch 10 - iter 132/447 - loss 0.00353846 - time (sec): 12.69 - samples/sec: 1978.90 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 16:07:34,051 epoch 10 - iter 176/447 - loss 0.00330267 - time (sec): 17.08 - samples/sec: 1977.05 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 16:07:38,665 epoch 10 - iter 220/447 - loss 0.00339446 - time (sec): 21.70 - samples/sec: 1945.15 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-17 16:07:43,234 epoch 10 - iter 264/447 - loss 0.00404962 - time (sec): 26.27 - samples/sec: 1971.40 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 16:07:47,304 epoch 10 - iter 308/447 - loss 0.00401999 - time (sec): 30.34 - samples/sec: 1956.79 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 16:07:51,685 epoch 10 - iter 352/447 - loss 0.00372843 - time (sec): 34.72 - samples/sec: 1959.83 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-17 16:07:55,746 epoch 10 - iter 396/447 - loss 0.00351848 - time (sec): 38.78 - samples/sec: 1963.55 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-17 16:07:59,987 epoch 10 - iter 440/447 - loss 0.00359443 - time (sec): 43.02 - samples/sec: 1975.68 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-17 16:08:00,668 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-17 16:08:00,669 EPOCH 10 done: loss 0.0035 - lr: 0.000000
220
+ 2023-10-17 16:08:11,622 DEV : loss 0.22872760891914368 - f1-score (micro avg) 0.7952
221
+ 2023-10-17 16:08:12,224 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-17 16:08:12,226 Loading model from best epoch ...
223
+ 2023-10-17 16:08:14,951 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
224
+ 2023-10-17 16:08:21,279
225
+ Results:
226
+ - F-score (micro) 0.764
227
+ - F-score (macro) 0.6761
228
+ - Accuracy 0.6388
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ loc 0.8315 0.8775 0.8539 596
234
+ pers 0.7314 0.7688 0.7496 333
235
+ org 0.4892 0.5152 0.5018 132
236
+ prod 0.6154 0.4848 0.5424 66
237
+ time 0.7115 0.7551 0.7327 49
238
+
239
+ micro avg 0.7496 0.7789 0.7640 1176
240
+ macro avg 0.6758 0.6803 0.6761 1176
241
+ weighted avg 0.7476 0.7789 0.7623 1176
242
+
243
+ 2023-10-17 16:08:21,280 ----------------------------------------------------------------------------------------------------