Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
c50d32c
·
1 Parent(s): a334eaf

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.1697563082.bce904bcef33.2251.10 +3 -0
  5. test.tsv +0 -0
  6. training.log +236 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125da4dda7e79b6350a713a7f468034522b93ca7531610bb9d923e4a5cf11c60
3
+ size 440941957
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 17:18:58 0.0000 0.4834 0.0916 0.8135 0.7345 0.7720 0.6320
3
+ 2 17:19:55 0.0000 0.0855 0.0799 0.9033 0.7335 0.8096 0.6860
4
+ 3 17:20:52 0.0000 0.0595 0.0589 0.8678 0.8812 0.8744 0.7847
5
+ 4 17:21:48 0.0000 0.0441 0.0596 0.8982 0.8481 0.8725 0.7834
6
+ 5 17:22:44 0.0000 0.0328 0.0892 0.8917 0.8254 0.8573 0.7617
7
+ 6 17:23:40 0.0000 0.0254 0.1065 0.9086 0.7903 0.8453 0.7406
8
+ 7 17:24:38 0.0000 0.0186 0.1209 0.9077 0.8233 0.8635 0.7671
9
+ 8 17:25:34 0.0000 0.0142 0.1118 0.8975 0.8502 0.8732 0.7838
10
+ 9 17:26:30 0.0000 0.0093 0.1297 0.8982 0.8481 0.8725 0.7827
11
+ 10 17:27:27 0.0000 0.0071 0.1300 0.9021 0.8378 0.8688 0.7753
runs/events.out.tfevents.1697563082.bce904bcef33.2251.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9439ced0b63dc2dc5274e78ceea54aa1480ce4f666adc8dfce4cdacaa53fe8
3
+ size 407048
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 17:18:02,748 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 17:18:02,749 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=13, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 17:18:02,749 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 17:18:02,749 MultiCorpus: 5777 train + 722 dev + 723 test sentences
48
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
49
+ 2023-10-17 17:18:02,749 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 17:18:02,749 Train: 5777 sentences
51
+ 2023-10-17 17:18:02,749 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 17:18:02,749 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 17:18:02,749 Training Params:
54
+ 2023-10-17 17:18:02,749 - learning_rate: "3e-05"
55
+ 2023-10-17 17:18:02,749 - mini_batch_size: "8"
56
+ 2023-10-17 17:18:02,749 - max_epochs: "10"
57
+ 2023-10-17 17:18:02,749 - shuffle: "True"
58
+ 2023-10-17 17:18:02,749 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 17:18:02,749 Plugins:
60
+ 2023-10-17 17:18:02,749 - TensorboardLogger
61
+ 2023-10-17 17:18:02,749 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 17:18:02,749 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 17:18:02,749 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 17:18:02,750 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 17:18:02,750 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 17:18:02,750 Computation:
67
+ 2023-10-17 17:18:02,750 - compute on device: cuda:0
68
+ 2023-10-17 17:18:02,750 - embedding storage: none
69
+ 2023-10-17 17:18:02,750 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 17:18:02,750 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
71
+ 2023-10-17 17:18:02,750 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 17:18:02,750 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 17:18:02,750 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 17:18:07,968 epoch 1 - iter 72/723 - loss 2.92821673 - time (sec): 5.22 - samples/sec: 3292.93 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 17:18:13,496 epoch 1 - iter 144/723 - loss 1.89319940 - time (sec): 10.75 - samples/sec: 3167.75 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 17:18:18,433 epoch 1 - iter 216/723 - loss 1.32058159 - time (sec): 15.68 - samples/sec: 3297.96 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 17:18:23,739 epoch 1 - iter 288/723 - loss 1.03686421 - time (sec): 20.99 - samples/sec: 3311.38 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 17:18:29,178 epoch 1 - iter 360/723 - loss 0.84817600 - time (sec): 26.43 - samples/sec: 3337.99 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 17:18:34,423 epoch 1 - iter 432/723 - loss 0.72455943 - time (sec): 31.67 - samples/sec: 3362.64 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 17:18:39,508 epoch 1 - iter 504/723 - loss 0.63851899 - time (sec): 36.76 - samples/sec: 3367.76 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 17:18:44,724 epoch 1 - iter 576/723 - loss 0.57388505 - time (sec): 41.97 - samples/sec: 3368.99 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 17:18:49,488 epoch 1 - iter 648/723 - loss 0.52952118 - time (sec): 46.74 - samples/sec: 3359.70 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 17:18:54,674 epoch 1 - iter 720/723 - loss 0.48526860 - time (sec): 51.92 - samples/sec: 3378.76 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-17 17:18:54,959 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 17:18:54,959 EPOCH 1 done: loss 0.4834 - lr: 0.000030
86
+ 2023-10-17 17:18:58,198 DEV : loss 0.09162620455026627 - f1-score (micro avg) 0.772
87
+ 2023-10-17 17:18:58,220 saving best model
88
+ 2023-10-17 17:18:58,619 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 17:19:03,898 epoch 2 - iter 72/723 - loss 0.08263348 - time (sec): 5.28 - samples/sec: 3288.51 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 17:19:09,170 epoch 2 - iter 144/723 - loss 0.09517055 - time (sec): 10.55 - samples/sec: 3297.74 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 17:19:14,153 epoch 2 - iter 216/723 - loss 0.09988608 - time (sec): 15.53 - samples/sec: 3333.60 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 17:19:19,327 epoch 2 - iter 288/723 - loss 0.09627162 - time (sec): 20.71 - samples/sec: 3336.49 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 17:19:24,981 epoch 2 - iter 360/723 - loss 0.09485556 - time (sec): 26.36 - samples/sec: 3334.24 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 17:19:31,183 epoch 2 - iter 432/723 - loss 0.09259966 - time (sec): 32.56 - samples/sec: 3304.35 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 17:19:36,309 epoch 2 - iter 504/723 - loss 0.09012823 - time (sec): 37.69 - samples/sec: 3323.07 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 17:19:41,244 epoch 2 - iter 576/723 - loss 0.08785448 - time (sec): 42.62 - samples/sec: 3334.29 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 17:19:46,438 epoch 2 - iter 648/723 - loss 0.08710096 - time (sec): 47.82 - samples/sec: 3318.09 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 17:19:51,687 epoch 2 - iter 720/723 - loss 0.08553578 - time (sec): 53.07 - samples/sec: 3307.76 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 17:19:51,866 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 17:19:51,867 EPOCH 2 done: loss 0.0855 - lr: 0.000027
101
+ 2023-10-17 17:19:55,303 DEV : loss 0.07994066923856735 - f1-score (micro avg) 0.8096
102
+ 2023-10-17 17:19:55,325 saving best model
103
+ 2023-10-17 17:19:56,010 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 17:20:01,368 epoch 3 - iter 72/723 - loss 0.07121149 - time (sec): 5.36 - samples/sec: 3245.54 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 17:20:07,264 epoch 3 - iter 144/723 - loss 0.06286836 - time (sec): 11.25 - samples/sec: 3188.58 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 17:20:12,469 epoch 3 - iter 216/723 - loss 0.06127686 - time (sec): 16.46 - samples/sec: 3295.23 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 17:20:17,584 epoch 3 - iter 288/723 - loss 0.05764282 - time (sec): 21.57 - samples/sec: 3336.95 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 17:20:22,398 epoch 3 - iter 360/723 - loss 0.05703678 - time (sec): 26.39 - samples/sec: 3351.17 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 17:20:27,635 epoch 3 - iter 432/723 - loss 0.05805135 - time (sec): 31.62 - samples/sec: 3369.77 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 17:20:33,178 epoch 3 - iter 504/723 - loss 0.05996212 - time (sec): 37.17 - samples/sec: 3349.78 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 17:20:38,081 epoch 3 - iter 576/723 - loss 0.05992057 - time (sec): 42.07 - samples/sec: 3355.15 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 17:20:43,349 epoch 3 - iter 648/723 - loss 0.05949413 - time (sec): 47.34 - samples/sec: 3343.73 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 17:20:48,602 epoch 3 - iter 720/723 - loss 0.05955426 - time (sec): 52.59 - samples/sec: 3345.25 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 17:20:48,758 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 17:20:48,758 EPOCH 3 done: loss 0.0595 - lr: 0.000023
116
+ 2023-10-17 17:20:52,178 DEV : loss 0.058894336223602295 - f1-score (micro avg) 0.8744
117
+ 2023-10-17 17:20:52,208 saving best model
118
+ 2023-10-17 17:20:52,731 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 17:20:57,764 epoch 4 - iter 72/723 - loss 0.04355367 - time (sec): 5.03 - samples/sec: 3320.09 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 17:21:03,407 epoch 4 - iter 144/723 - loss 0.04290886 - time (sec): 10.67 - samples/sec: 3246.22 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-17 17:21:08,387 epoch 4 - iter 216/723 - loss 0.04393652 - time (sec): 15.65 - samples/sec: 3306.63 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 17:21:13,715 epoch 4 - iter 288/723 - loss 0.04557269 - time (sec): 20.98 - samples/sec: 3300.10 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 17:21:18,664 epoch 4 - iter 360/723 - loss 0.04428411 - time (sec): 25.93 - samples/sec: 3328.19 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-17 17:21:23,819 epoch 4 - iter 432/723 - loss 0.04366172 - time (sec): 31.08 - samples/sec: 3342.24 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 17:21:29,071 epoch 4 - iter 504/723 - loss 0.04336719 - time (sec): 36.34 - samples/sec: 3350.79 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 17:21:34,728 epoch 4 - iter 576/723 - loss 0.04464133 - time (sec): 41.99 - samples/sec: 3357.04 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-17 17:21:39,750 epoch 4 - iter 648/723 - loss 0.04399677 - time (sec): 47.01 - samples/sec: 3359.57 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 17:21:44,913 epoch 4 - iter 720/723 - loss 0.04409540 - time (sec): 52.18 - samples/sec: 3368.25 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-17 17:21:45,083 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 17:21:45,084 EPOCH 4 done: loss 0.0441 - lr: 0.000020
131
+ 2023-10-17 17:21:48,784 DEV : loss 0.05959029123187065 - f1-score (micro avg) 0.8725
132
+ 2023-10-17 17:21:48,804 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 17:21:54,022 epoch 5 - iter 72/723 - loss 0.02878262 - time (sec): 5.22 - samples/sec: 3441.74 - lr: 0.000020 - momentum: 0.000000
134
+ 2023-10-17 17:21:58,914 epoch 5 - iter 144/723 - loss 0.02578122 - time (sec): 10.11 - samples/sec: 3464.18 - lr: 0.000019 - momentum: 0.000000
135
+ 2023-10-17 17:22:04,106 epoch 5 - iter 216/723 - loss 0.03035057 - time (sec): 15.30 - samples/sec: 3464.67 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 17:22:09,621 epoch 5 - iter 288/723 - loss 0.02847141 - time (sec): 20.82 - samples/sec: 3417.29 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 17:22:14,738 epoch 5 - iter 360/723 - loss 0.02912372 - time (sec): 25.93 - samples/sec: 3391.91 - lr: 0.000018 - momentum: 0.000000
138
+ 2023-10-17 17:22:20,332 epoch 5 - iter 432/723 - loss 0.03092672 - time (sec): 31.53 - samples/sec: 3363.23 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 17:22:25,826 epoch 5 - iter 504/723 - loss 0.03207944 - time (sec): 37.02 - samples/sec: 3349.99 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 17:22:30,593 epoch 5 - iter 576/723 - loss 0.03267365 - time (sec): 41.79 - samples/sec: 3369.49 - lr: 0.000017 - momentum: 0.000000
141
+ 2023-10-17 17:22:35,527 epoch 5 - iter 648/723 - loss 0.03353305 - time (sec): 46.72 - samples/sec: 3379.33 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 17:22:40,601 epoch 5 - iter 720/723 - loss 0.03284765 - time (sec): 51.80 - samples/sec: 3391.87 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 17:22:40,767 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 17:22:40,767 EPOCH 5 done: loss 0.0328 - lr: 0.000017
145
+ 2023-10-17 17:22:44,271 DEV : loss 0.0892329216003418 - f1-score (micro avg) 0.8573
146
+ 2023-10-17 17:22:44,302 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-17 17:22:49,647 epoch 6 - iter 72/723 - loss 0.02078891 - time (sec): 5.34 - samples/sec: 3508.17 - lr: 0.000016 - momentum: 0.000000
148
+ 2023-10-17 17:22:55,042 epoch 6 - iter 144/723 - loss 0.01967175 - time (sec): 10.74 - samples/sec: 3329.42 - lr: 0.000016 - momentum: 0.000000
149
+ 2023-10-17 17:23:00,622 epoch 6 - iter 216/723 - loss 0.02336652 - time (sec): 16.32 - samples/sec: 3328.08 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 17:23:06,281 epoch 6 - iter 288/723 - loss 0.02495221 - time (sec): 21.98 - samples/sec: 3302.47 - lr: 0.000015 - momentum: 0.000000
151
+ 2023-10-17 17:23:11,871 epoch 6 - iter 360/723 - loss 0.02541744 - time (sec): 27.57 - samples/sec: 3251.44 - lr: 0.000015 - momentum: 0.000000
152
+ 2023-10-17 17:23:17,063 epoch 6 - iter 432/723 - loss 0.02514231 - time (sec): 32.76 - samples/sec: 3287.96 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 17:23:22,077 epoch 6 - iter 504/723 - loss 0.02636371 - time (sec): 37.77 - samples/sec: 3294.29 - lr: 0.000014 - momentum: 0.000000
154
+ 2023-10-17 17:23:27,176 epoch 6 - iter 576/723 - loss 0.02636581 - time (sec): 42.87 - samples/sec: 3312.52 - lr: 0.000014 - momentum: 0.000000
155
+ 2023-10-17 17:23:32,197 epoch 6 - iter 648/723 - loss 0.02508128 - time (sec): 47.89 - samples/sec: 3312.20 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 17:23:37,126 epoch 6 - iter 720/723 - loss 0.02535939 - time (sec): 52.82 - samples/sec: 3327.37 - lr: 0.000013 - momentum: 0.000000
157
+ 2023-10-17 17:23:37,304 ----------------------------------------------------------------------------------------------------
158
+ 2023-10-17 17:23:37,305 EPOCH 6 done: loss 0.0254 - lr: 0.000013
159
+ 2023-10-17 17:23:40,588 DEV : loss 0.10650834441184998 - f1-score (micro avg) 0.8453
160
+ 2023-10-17 17:23:40,620 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 17:23:45,947 epoch 7 - iter 72/723 - loss 0.01512900 - time (sec): 5.33 - samples/sec: 3225.11 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-17 17:23:51,221 epoch 7 - iter 144/723 - loss 0.01994325 - time (sec): 10.60 - samples/sec: 3255.50 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-17 17:23:56,636 epoch 7 - iter 216/723 - loss 0.01985443 - time (sec): 16.01 - samples/sec: 3264.32 - lr: 0.000012 - momentum: 0.000000
164
+ 2023-10-17 17:24:01,860 epoch 7 - iter 288/723 - loss 0.02211769 - time (sec): 21.24 - samples/sec: 3315.05 - lr: 0.000012 - momentum: 0.000000
165
+ 2023-10-17 17:24:07,334 epoch 7 - iter 360/723 - loss 0.02057789 - time (sec): 26.71 - samples/sec: 3281.98 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-17 17:24:12,648 epoch 7 - iter 432/723 - loss 0.02150567 - time (sec): 32.03 - samples/sec: 3313.55 - lr: 0.000011 - momentum: 0.000000
167
+ 2023-10-17 17:24:17,871 epoch 7 - iter 504/723 - loss 0.02078248 - time (sec): 37.25 - samples/sec: 3339.91 - lr: 0.000011 - momentum: 0.000000
168
+ 2023-10-17 17:24:23,204 epoch 7 - iter 576/723 - loss 0.02009060 - time (sec): 42.58 - samples/sec: 3324.99 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-17 17:24:28,361 epoch 7 - iter 648/723 - loss 0.01899026 - time (sec): 47.74 - samples/sec: 3315.02 - lr: 0.000010 - momentum: 0.000000
170
+ 2023-10-17 17:24:33,718 epoch 7 - iter 720/723 - loss 0.01860087 - time (sec): 53.10 - samples/sec: 3302.91 - lr: 0.000010 - momentum: 0.000000
171
+ 2023-10-17 17:24:34,113 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 17:24:34,113 EPOCH 7 done: loss 0.0186 - lr: 0.000010
173
+ 2023-10-17 17:24:38,254 DEV : loss 0.12094509601593018 - f1-score (micro avg) 0.8635
174
+ 2023-10-17 17:24:38,277 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 17:24:43,290 epoch 8 - iter 72/723 - loss 0.01674001 - time (sec): 5.01 - samples/sec: 3332.86 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-17 17:24:48,609 epoch 8 - iter 144/723 - loss 0.01250439 - time (sec): 10.33 - samples/sec: 3286.70 - lr: 0.000009 - momentum: 0.000000
177
+ 2023-10-17 17:24:53,757 epoch 8 - iter 216/723 - loss 0.01587244 - time (sec): 15.48 - samples/sec: 3308.07 - lr: 0.000009 - momentum: 0.000000
178
+ 2023-10-17 17:24:59,031 epoch 8 - iter 288/723 - loss 0.01474739 - time (sec): 20.75 - samples/sec: 3322.17 - lr: 0.000009 - momentum: 0.000000
179
+ 2023-10-17 17:25:04,515 epoch 8 - iter 360/723 - loss 0.01501380 - time (sec): 26.24 - samples/sec: 3299.67 - lr: 0.000008 - momentum: 0.000000
180
+ 2023-10-17 17:25:09,679 epoch 8 - iter 432/723 - loss 0.01426960 - time (sec): 31.40 - samples/sec: 3309.25 - lr: 0.000008 - momentum: 0.000000
181
+ 2023-10-17 17:25:15,004 epoch 8 - iter 504/723 - loss 0.01444987 - time (sec): 36.73 - samples/sec: 3318.21 - lr: 0.000008 - momentum: 0.000000
182
+ 2023-10-17 17:25:20,149 epoch 8 - iter 576/723 - loss 0.01498026 - time (sec): 41.87 - samples/sec: 3332.63 - lr: 0.000007 - momentum: 0.000000
183
+ 2023-10-17 17:25:25,819 epoch 8 - iter 648/723 - loss 0.01446914 - time (sec): 47.54 - samples/sec: 3344.99 - lr: 0.000007 - momentum: 0.000000
184
+ 2023-10-17 17:25:30,904 epoch 8 - iter 720/723 - loss 0.01414308 - time (sec): 52.63 - samples/sec: 3337.05 - lr: 0.000007 - momentum: 0.000000
185
+ 2023-10-17 17:25:31,090 ----------------------------------------------------------------------------------------------------
186
+ 2023-10-17 17:25:31,090 EPOCH 8 done: loss 0.0142 - lr: 0.000007
187
+ 2023-10-17 17:25:34,478 DEV : loss 0.11182001233100891 - f1-score (micro avg) 0.8732
188
+ 2023-10-17 17:25:34,498 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-17 17:25:39,684 epoch 9 - iter 72/723 - loss 0.00674938 - time (sec): 5.18 - samples/sec: 3305.14 - lr: 0.000006 - momentum: 0.000000
190
+ 2023-10-17 17:25:44,991 epoch 9 - iter 144/723 - loss 0.00755681 - time (sec): 10.49 - samples/sec: 3337.99 - lr: 0.000006 - momentum: 0.000000
191
+ 2023-10-17 17:25:50,324 epoch 9 - iter 216/723 - loss 0.00853434 - time (sec): 15.82 - samples/sec: 3317.89 - lr: 0.000006 - momentum: 0.000000
192
+ 2023-10-17 17:25:55,818 epoch 9 - iter 288/723 - loss 0.00885931 - time (sec): 21.32 - samples/sec: 3326.28 - lr: 0.000005 - momentum: 0.000000
193
+ 2023-10-17 17:26:01,443 epoch 9 - iter 360/723 - loss 0.00947749 - time (sec): 26.94 - samples/sec: 3312.93 - lr: 0.000005 - momentum: 0.000000
194
+ 2023-10-17 17:26:07,110 epoch 9 - iter 432/723 - loss 0.01029660 - time (sec): 32.61 - samples/sec: 3276.34 - lr: 0.000005 - momentum: 0.000000
195
+ 2023-10-17 17:26:11,975 epoch 9 - iter 504/723 - loss 0.00971519 - time (sec): 37.48 - samples/sec: 3293.67 - lr: 0.000004 - momentum: 0.000000
196
+ 2023-10-17 17:26:16,712 epoch 9 - iter 576/723 - loss 0.00913791 - time (sec): 42.21 - samples/sec: 3306.95 - lr: 0.000004 - momentum: 0.000000
197
+ 2023-10-17 17:26:21,888 epoch 9 - iter 648/723 - loss 0.00920760 - time (sec): 47.39 - samples/sec: 3334.43 - lr: 0.000004 - momentum: 0.000000
198
+ 2023-10-17 17:26:27,223 epoch 9 - iter 720/723 - loss 0.00937031 - time (sec): 52.72 - samples/sec: 3331.95 - lr: 0.000003 - momentum: 0.000000
199
+ 2023-10-17 17:26:27,395 ----------------------------------------------------------------------------------------------------
200
+ 2023-10-17 17:26:27,395 EPOCH 9 done: loss 0.0093 - lr: 0.000003
201
+ 2023-10-17 17:26:30,608 DEV : loss 0.1297394335269928 - f1-score (micro avg) 0.8725
202
+ 2023-10-17 17:26:30,624 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 17:26:35,888 epoch 10 - iter 72/723 - loss 0.01223344 - time (sec): 5.26 - samples/sec: 3424.14 - lr: 0.000003 - momentum: 0.000000
204
+ 2023-10-17 17:26:40,837 epoch 10 - iter 144/723 - loss 0.00842767 - time (sec): 10.21 - samples/sec: 3401.50 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-17 17:26:46,403 epoch 10 - iter 216/723 - loss 0.00985753 - time (sec): 15.78 - samples/sec: 3366.92 - lr: 0.000002 - momentum: 0.000000
206
+ 2023-10-17 17:26:51,833 epoch 10 - iter 288/723 - loss 0.00861439 - time (sec): 21.21 - samples/sec: 3356.16 - lr: 0.000002 - momentum: 0.000000
207
+ 2023-10-17 17:26:56,978 epoch 10 - iter 360/723 - loss 0.00751018 - time (sec): 26.35 - samples/sec: 3368.57 - lr: 0.000002 - momentum: 0.000000
208
+ 2023-10-17 17:27:02,349 epoch 10 - iter 432/723 - loss 0.00721843 - time (sec): 31.72 - samples/sec: 3352.43 - lr: 0.000001 - momentum: 0.000000
209
+ 2023-10-17 17:27:07,627 epoch 10 - iter 504/723 - loss 0.00709729 - time (sec): 37.00 - samples/sec: 3336.75 - lr: 0.000001 - momentum: 0.000000
210
+ 2023-10-17 17:27:13,126 epoch 10 - iter 576/723 - loss 0.00682846 - time (sec): 42.50 - samples/sec: 3317.73 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-17 17:27:18,630 epoch 10 - iter 648/723 - loss 0.00690953 - time (sec): 48.00 - samples/sec: 3309.77 - lr: 0.000000 - momentum: 0.000000
212
+ 2023-10-17 17:27:23,834 epoch 10 - iter 720/723 - loss 0.00716323 - time (sec): 53.21 - samples/sec: 3304.82 - lr: 0.000000 - momentum: 0.000000
213
+ 2023-10-17 17:27:23,986 ----------------------------------------------------------------------------------------------------
214
+ 2023-10-17 17:27:23,986 EPOCH 10 done: loss 0.0071 - lr: 0.000000
215
+ 2023-10-17 17:27:27,783 DEV : loss 0.12998518347740173 - f1-score (micro avg) 0.8688
216
+ 2023-10-17 17:27:28,161 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-17 17:27:28,162 Loading model from best epoch ...
218
+ 2023-10-17 17:27:29,632 SequenceTagger predicts: Dictionary with 13 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
219
+ 2023-10-17 17:27:32,734
220
+ Results:
221
+ - F-score (micro) 0.8457
222
+ - F-score (macro) 0.7463
223
+ - Accuracy 0.7446
224
+
225
+ By class:
226
+ precision recall f1-score support
227
+
228
+ PER 0.7904 0.8921 0.8382 482
229
+ LOC 0.9222 0.8799 0.9006 458
230
+ ORG 0.5882 0.4348 0.5000 69
231
+
232
+ micro avg 0.8362 0.8553 0.8457 1009
233
+ macro avg 0.7670 0.7356 0.7463 1009
234
+ weighted avg 0.8364 0.8553 0.8434 1009
235
+
236
+ 2023-10-17 17:27:32,735 ----------------------------------------------------------------------------------------------------