Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
b8d0e50
·
1 Parent(s): 58b8ca2

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76b5662b31504dbcb658b1865a368b5ba11cedda9ae2849b332aa9b31328254e
3
+ size 443335879
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 18:48:42 0.0000 0.5173 0.1587 0.6768 0.7148 0.6953 0.5557
3
+ 2 18:50:03 0.0000 0.1266 0.1343 0.7557 0.8150 0.7842 0.6709
4
+ 3 18:51:24 0.0000 0.0825 0.1547 0.7800 0.8144 0.7969 0.6883
5
+ 4 18:52:45 0.0000 0.0563 0.1703 0.7825 0.8408 0.8106 0.7082
6
+ 5 18:54:06 0.0000 0.0402 0.1790 0.8248 0.8276 0.8262 0.7309
7
+ 6 18:55:28 0.0000 0.0290 0.2176 0.7951 0.8202 0.8074 0.7089
8
+ 7 18:56:47 0.0000 0.0216 0.2037 0.8211 0.8385 0.8297 0.7375
9
+ 8 18:58:09 0.0000 0.0140 0.2041 0.8326 0.8402 0.8364 0.7454
10
+ 9 18:59:30 0.0000 0.0101 0.2134 0.8191 0.8454 0.8320 0.7406
11
+ 10 19:00:51 0.0000 0.0076 0.2185 0.8196 0.8431 0.8312 0.7393
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 18:47:26,353 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 18:47:26,354 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
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): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
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): BertSelfOutput(
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): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
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
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 18:47:26,354 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 18:47:26,354 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
52
+ - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
53
+ 2023-10-13 18:47:26,354 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 18:47:26,354 Train: 5901 sentences
55
+ 2023-10-13 18:47:26,354 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 18:47:26,354 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 18:47:26,354 Training Params:
58
+ 2023-10-13 18:47:26,354 - learning_rate: "3e-05"
59
+ 2023-10-13 18:47:26,354 - mini_batch_size: "4"
60
+ 2023-10-13 18:47:26,354 - max_epochs: "10"
61
+ 2023-10-13 18:47:26,354 - shuffle: "True"
62
+ 2023-10-13 18:47:26,354 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 18:47:26,354 Plugins:
64
+ 2023-10-13 18:47:26,355 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 18:47:26,355 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 18:47:26,355 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 18:47:26,355 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 18:47:26,355 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 18:47:26,355 Computation:
70
+ 2023-10-13 18:47:26,355 - compute on device: cuda:0
71
+ 2023-10-13 18:47:26,355 - embedding storage: none
72
+ 2023-10-13 18:47:26,355 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 18:47:26,355 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
74
+ 2023-10-13 18:47:26,355 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 18:47:26,355 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 18:47:33,216 epoch 1 - iter 147/1476 - loss 2.47203040 - time (sec): 6.86 - samples/sec: 2369.63 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 18:47:40,117 epoch 1 - iter 294/1476 - loss 1.53224631 - time (sec): 13.76 - samples/sec: 2378.60 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 18:47:46,944 epoch 1 - iter 441/1476 - loss 1.16457223 - time (sec): 20.59 - samples/sec: 2370.35 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 18:47:53,832 epoch 1 - iter 588/1476 - loss 0.95570083 - time (sec): 27.48 - samples/sec: 2364.52 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 18:48:01,003 epoch 1 - iter 735/1476 - loss 0.82886372 - time (sec): 34.65 - samples/sec: 2368.14 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 18:48:07,676 epoch 1 - iter 882/1476 - loss 0.73918529 - time (sec): 41.32 - samples/sec: 2345.23 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 18:48:14,768 epoch 1 - iter 1029/1476 - loss 0.66297514 - time (sec): 48.41 - samples/sec: 2363.63 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 18:48:21,818 epoch 1 - iter 1176/1476 - loss 0.60069633 - time (sec): 55.46 - samples/sec: 2382.71 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 18:48:28,594 epoch 1 - iter 1323/1476 - loss 0.55590049 - time (sec): 62.24 - samples/sec: 2387.70 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 18:48:35,652 epoch 1 - iter 1470/1476 - loss 0.51835277 - time (sec): 69.30 - samples/sec: 2393.10 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 18:48:35,906 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 18:48:35,906 EPOCH 1 done: loss 0.5173 - lr: 0.000030
88
+ 2023-10-13 18:48:42,033 DEV : loss 0.1586601436138153 - f1-score (micro avg) 0.6953
89
+ 2023-10-13 18:48:42,061 saving best model
90
+ 2023-10-13 18:48:42,528 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 18:48:49,482 epoch 2 - iter 147/1476 - loss 0.13516442 - time (sec): 6.95 - samples/sec: 2412.34 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 18:48:56,332 epoch 2 - iter 294/1476 - loss 0.13649252 - time (sec): 13.80 - samples/sec: 2404.93 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 18:49:03,501 epoch 2 - iter 441/1476 - loss 0.13545397 - time (sec): 20.97 - samples/sec: 2383.51 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 18:49:10,326 epoch 2 - iter 588/1476 - loss 0.13055225 - time (sec): 27.80 - samples/sec: 2354.64 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 18:49:17,578 epoch 2 - iter 735/1476 - loss 0.12511794 - time (sec): 35.05 - samples/sec: 2390.45 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 18:49:25,271 epoch 2 - iter 882/1476 - loss 0.12920863 - time (sec): 42.74 - samples/sec: 2446.74 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 18:49:31,880 epoch 2 - iter 1029/1476 - loss 0.12753320 - time (sec): 49.35 - samples/sec: 2427.35 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 18:49:38,827 epoch 2 - iter 1176/1476 - loss 0.12657849 - time (sec): 56.30 - samples/sec: 2430.44 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 18:49:45,338 epoch 2 - iter 1323/1476 - loss 0.12667487 - time (sec): 62.81 - samples/sec: 2406.92 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 18:49:52,047 epoch 2 - iter 1470/1476 - loss 0.12663562 - time (sec): 69.52 - samples/sec: 2388.22 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 18:49:52,313 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 18:49:52,313 EPOCH 2 done: loss 0.1266 - lr: 0.000027
103
+ 2023-10-13 18:50:03,449 DEV : loss 0.13426746428012848 - f1-score (micro avg) 0.7842
104
+ 2023-10-13 18:50:03,480 saving best model
105
+ 2023-10-13 18:50:04,015 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 18:50:11,260 epoch 3 - iter 147/1476 - loss 0.06400595 - time (sec): 7.24 - samples/sec: 2559.29 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 18:50:18,213 epoch 3 - iter 294/1476 - loss 0.06628312 - time (sec): 14.20 - samples/sec: 2483.12 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 18:50:25,140 epoch 3 - iter 441/1476 - loss 0.07296170 - time (sec): 21.12 - samples/sec: 2463.79 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 18:50:32,364 epoch 3 - iter 588/1476 - loss 0.08168640 - time (sec): 28.35 - samples/sec: 2478.57 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 18:50:39,055 epoch 3 - iter 735/1476 - loss 0.08289348 - time (sec): 35.04 - samples/sec: 2447.79 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 18:50:45,924 epoch 3 - iter 882/1476 - loss 0.08210391 - time (sec): 41.91 - samples/sec: 2430.46 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 18:50:52,737 epoch 3 - iter 1029/1476 - loss 0.08197948 - time (sec): 48.72 - samples/sec: 2410.53 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 18:50:59,573 epoch 3 - iter 1176/1476 - loss 0.08119702 - time (sec): 55.56 - samples/sec: 2406.42 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 18:51:06,452 epoch 3 - iter 1323/1476 - loss 0.08162410 - time (sec): 62.44 - samples/sec: 2401.71 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 18:51:13,132 epoch 3 - iter 1470/1476 - loss 0.08267840 - time (sec): 69.12 - samples/sec: 2400.10 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 18:51:13,388 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 18:51:13,389 EPOCH 3 done: loss 0.0825 - lr: 0.000023
118
+ 2023-10-13 18:51:24,588 DEV : loss 0.15468844771385193 - f1-score (micro avg) 0.7969
119
+ 2023-10-13 18:51:24,619 saving best model
120
+ 2023-10-13 18:51:25,121 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 18:51:31,983 epoch 4 - iter 147/1476 - loss 0.06136683 - time (sec): 6.86 - samples/sec: 2352.06 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 18:51:39,343 epoch 4 - iter 294/1476 - loss 0.06998431 - time (sec): 14.22 - samples/sec: 2509.18 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 18:51:46,299 epoch 4 - iter 441/1476 - loss 0.06564666 - time (sec): 21.17 - samples/sec: 2446.49 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 18:51:52,964 epoch 4 - iter 588/1476 - loss 0.06527905 - time (sec): 27.84 - samples/sec: 2380.86 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 18:51:59,887 epoch 4 - iter 735/1476 - loss 0.06299237 - time (sec): 34.76 - samples/sec: 2400.68 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 18:52:06,636 epoch 4 - iter 882/1476 - loss 0.06239020 - time (sec): 41.51 - samples/sec: 2398.39 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 18:52:13,344 epoch 4 - iter 1029/1476 - loss 0.06088924 - time (sec): 48.22 - samples/sec: 2377.28 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 18:52:20,126 epoch 4 - iter 1176/1476 - loss 0.05807939 - time (sec): 55.00 - samples/sec: 2374.78 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 18:52:27,021 epoch 4 - iter 1323/1476 - loss 0.05765390 - time (sec): 61.89 - samples/sec: 2371.42 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 18:52:34,328 epoch 4 - iter 1470/1476 - loss 0.05616269 - time (sec): 69.20 - samples/sec: 2396.99 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 18:52:34,590 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 18:52:34,590 EPOCH 4 done: loss 0.0563 - lr: 0.000020
133
+ 2023-10-13 18:52:45,814 DEV : loss 0.17033860087394714 - f1-score (micro avg) 0.8106
134
+ 2023-10-13 18:52:45,844 saving best model
135
+ 2023-10-13 18:52:46,323 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 18:52:53,267 epoch 5 - iter 147/1476 - loss 0.04144502 - time (sec): 6.94 - samples/sec: 2423.87 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-13 18:52:59,900 epoch 5 - iter 294/1476 - loss 0.04606724 - time (sec): 13.57 - samples/sec: 2328.10 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 18:53:06,912 epoch 5 - iter 441/1476 - loss 0.03973065 - time (sec): 20.58 - samples/sec: 2344.48 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 18:53:13,730 epoch 5 - iter 588/1476 - loss 0.03622589 - time (sec): 27.40 - samples/sec: 2366.89 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-13 18:53:20,750 epoch 5 - iter 735/1476 - loss 0.03811454 - time (sec): 34.42 - samples/sec: 2385.48 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 18:53:27,625 epoch 5 - iter 882/1476 - loss 0.03708256 - time (sec): 41.30 - samples/sec: 2394.12 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 18:53:34,708 epoch 5 - iter 1029/1476 - loss 0.03955991 - time (sec): 48.38 - samples/sec: 2398.84 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-13 18:53:41,663 epoch 5 - iter 1176/1476 - loss 0.04041590 - time (sec): 55.34 - samples/sec: 2397.38 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 18:53:48,587 epoch 5 - iter 1323/1476 - loss 0.04037167 - time (sec): 62.26 - samples/sec: 2404.17 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 18:53:55,407 epoch 5 - iter 1470/1476 - loss 0.04036140 - time (sec): 69.08 - samples/sec: 2400.21 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-13 18:53:55,675 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 18:53:55,675 EPOCH 5 done: loss 0.0402 - lr: 0.000017
148
+ 2023-10-13 18:54:06,901 DEV : loss 0.1789896935224533 - f1-score (micro avg) 0.8262
149
+ 2023-10-13 18:54:06,932 saving best model
150
+ 2023-10-13 18:54:07,408 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 18:54:14,802 epoch 6 - iter 147/1476 - loss 0.02954124 - time (sec): 7.39 - samples/sec: 2309.03 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 18:54:21,552 epoch 6 - iter 294/1476 - loss 0.02823268 - time (sec): 14.14 - samples/sec: 2296.57 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 18:54:28,596 epoch 6 - iter 441/1476 - loss 0.02553327 - time (sec): 21.18 - samples/sec: 2307.96 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-13 18:54:35,572 epoch 6 - iter 588/1476 - loss 0.02831420 - time (sec): 28.16 - samples/sec: 2319.15 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 18:54:42,364 epoch 6 - iter 735/1476 - loss 0.02702751 - time (sec): 34.95 - samples/sec: 2309.41 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 18:54:49,162 epoch 6 - iter 882/1476 - loss 0.02657347 - time (sec): 41.75 - samples/sec: 2301.97 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-13 18:54:56,165 epoch 6 - iter 1029/1476 - loss 0.02729635 - time (sec): 48.75 - samples/sec: 2333.31 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 18:55:03,119 epoch 6 - iter 1176/1476 - loss 0.02915968 - time (sec): 55.71 - samples/sec: 2337.65 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 18:55:10,018 epoch 6 - iter 1323/1476 - loss 0.02965009 - time (sec): 62.60 - samples/sec: 2342.88 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-13 18:55:17,017 epoch 6 - iter 1470/1476 - loss 0.02919942 - time (sec): 69.60 - samples/sec: 2372.02 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-13 18:55:17,440 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 18:55:17,440 EPOCH 6 done: loss 0.0290 - lr: 0.000013
163
+ 2023-10-13 18:55:28,623 DEV : loss 0.2175937294960022 - f1-score (micro avg) 0.8074
164
+ 2023-10-13 18:55:28,651 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 18:55:35,576 epoch 7 - iter 147/1476 - loss 0.03078954 - time (sec): 6.92 - samples/sec: 2523.71 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-13 18:55:42,711 epoch 7 - iter 294/1476 - loss 0.02613132 - time (sec): 14.06 - samples/sec: 2560.65 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-13 18:55:49,569 epoch 7 - iter 441/1476 - loss 0.02307156 - time (sec): 20.92 - samples/sec: 2556.92 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-13 18:55:56,397 epoch 7 - iter 588/1476 - loss 0.02372509 - time (sec): 27.74 - samples/sec: 2577.17 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 18:56:02,657 epoch 7 - iter 735/1476 - loss 0.02290695 - time (sec): 34.00 - samples/sec: 2544.01 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-13 18:56:09,563 epoch 7 - iter 882/1476 - loss 0.02287812 - time (sec): 40.91 - samples/sec: 2529.13 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-13 18:56:16,218 epoch 7 - iter 1029/1476 - loss 0.02273386 - time (sec): 47.57 - samples/sec: 2497.38 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 18:56:22,941 epoch 7 - iter 1176/1476 - loss 0.02186207 - time (sec): 54.29 - samples/sec: 2476.20 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-13 18:56:29,677 epoch 7 - iter 1323/1476 - loss 0.02249581 - time (sec): 61.02 - samples/sec: 2460.89 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-13 18:56:36,428 epoch 7 - iter 1470/1476 - loss 0.02161244 - time (sec): 67.78 - samples/sec: 2447.38 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-13 18:56:36,692 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 18:56:36,692 EPOCH 7 done: loss 0.0216 - lr: 0.000010
177
+ 2023-10-13 18:56:47,948 DEV : loss 0.20365940034389496 - f1-score (micro avg) 0.8297
178
+ 2023-10-13 18:56:47,979 saving best model
179
+ 2023-10-13 18:56:48,508 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-13 18:56:55,502 epoch 8 - iter 147/1476 - loss 0.01368682 - time (sec): 6.99 - samples/sec: 2531.95 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-13 18:57:02,204 epoch 8 - iter 294/1476 - loss 0.01246331 - time (sec): 13.69 - samples/sec: 2414.93 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 18:57:09,400 epoch 8 - iter 441/1476 - loss 0.01614129 - time (sec): 20.89 - samples/sec: 2483.02 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 18:57:16,317 epoch 8 - iter 588/1476 - loss 0.01524708 - time (sec): 27.81 - samples/sec: 2425.87 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-13 18:57:22,822 epoch 8 - iter 735/1476 - loss 0.01581981 - time (sec): 34.31 - samples/sec: 2384.81 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 18:57:29,986 epoch 8 - iter 882/1476 - loss 0.01639056 - time (sec): 41.48 - samples/sec: 2406.11 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 18:57:36,747 epoch 8 - iter 1029/1476 - loss 0.01574671 - time (sec): 48.24 - samples/sec: 2404.17 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-13 18:57:43,644 epoch 8 - iter 1176/1476 - loss 0.01490286 - time (sec): 55.13 - samples/sec: 2390.65 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 18:57:50,534 epoch 8 - iter 1323/1476 - loss 0.01468391 - time (sec): 62.02 - samples/sec: 2389.87 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 18:57:57,551 epoch 8 - iter 1470/1476 - loss 0.01407014 - time (sec): 69.04 - samples/sec: 2402.22 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-13 18:57:57,816 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-13 18:57:57,816 EPOCH 8 done: loss 0.0140 - lr: 0.000007
192
+ 2023-10-13 18:58:09,064 DEV : loss 0.20413334667682648 - f1-score (micro avg) 0.8364
193
+ 2023-10-13 18:58:09,094 saving best model
194
+ 2023-10-13 18:58:09,586 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-13 18:58:16,496 epoch 9 - iter 147/1476 - loss 0.01422764 - time (sec): 6.91 - samples/sec: 2327.73 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 18:58:23,345 epoch 9 - iter 294/1476 - loss 0.01591919 - time (sec): 13.76 - samples/sec: 2349.67 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-13 18:58:29,983 epoch 9 - iter 441/1476 - loss 0.01220372 - time (sec): 20.40 - samples/sec: 2307.67 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-13 18:58:37,103 epoch 9 - iter 588/1476 - loss 0.01151508 - time (sec): 27.52 - samples/sec: 2333.85 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 18:58:44,024 epoch 9 - iter 735/1476 - loss 0.01111149 - time (sec): 34.44 - samples/sec: 2316.75 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-13 18:58:51,025 epoch 9 - iter 882/1476 - loss 0.01047146 - time (sec): 41.44 - samples/sec: 2316.50 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-13 18:58:58,130 epoch 9 - iter 1029/1476 - loss 0.00997977 - time (sec): 48.54 - samples/sec: 2345.47 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 18:59:05,454 epoch 9 - iter 1176/1476 - loss 0.01061230 - time (sec): 55.87 - samples/sec: 2367.08 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-13 18:59:12,178 epoch 9 - iter 1323/1476 - loss 0.01020875 - time (sec): 62.59 - samples/sec: 2357.94 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-13 18:59:19,220 epoch 9 - iter 1470/1476 - loss 0.01015093 - time (sec): 69.63 - samples/sec: 2370.02 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-13 18:59:19,651 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-13 18:59:19,651 EPOCH 9 done: loss 0.0101 - lr: 0.000003
207
+ 2023-10-13 18:59:30,827 DEV : loss 0.21342383325099945 - f1-score (micro avg) 0.832
208
+ 2023-10-13 18:59:30,857 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-13 18:59:37,684 epoch 10 - iter 147/1476 - loss 0.00481638 - time (sec): 6.83 - samples/sec: 2248.25 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-13 18:59:44,816 epoch 10 - iter 294/1476 - loss 0.00647829 - time (sec): 13.96 - samples/sec: 2359.27 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 18:59:51,824 epoch 10 - iter 441/1476 - loss 0.00596617 - time (sec): 20.97 - samples/sec: 2362.46 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 18:59:58,867 epoch 10 - iter 588/1476 - loss 0.00519237 - time (sec): 28.01 - samples/sec: 2381.30 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 19:00:06,044 epoch 10 - iter 735/1476 - loss 0.00546008 - time (sec): 35.19 - samples/sec: 2406.51 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 19:00:12,744 epoch 10 - iter 882/1476 - loss 0.00545956 - time (sec): 41.89 - samples/sec: 2395.55 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 19:00:19,404 epoch 10 - iter 1029/1476 - loss 0.00758172 - time (sec): 48.55 - samples/sec: 2385.54 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 19:00:26,452 epoch 10 - iter 1176/1476 - loss 0.00734000 - time (sec): 55.59 - samples/sec: 2379.50 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 19:00:33,555 epoch 10 - iter 1323/1476 - loss 0.00755594 - time (sec): 62.70 - samples/sec: 2397.75 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-13 19:00:40,328 epoch 10 - iter 1470/1476 - loss 0.00764843 - time (sec): 69.47 - samples/sec: 2386.23 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 19:00:40,604 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 19:00:40,605 EPOCH 10 done: loss 0.0076 - lr: 0.000000
221
+ 2023-10-13 19:00:51,848 DEV : loss 0.21848614513874054 - f1-score (micro avg) 0.8312
222
+ 2023-10-13 19:00:52,254 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-13 19:00:52,255 Loading model from best epoch ...
224
+ 2023-10-13 19:00:53,719 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-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod
225
+ 2023-10-13 19:01:00,089
226
+ Results:
227
+ - F-score (micro) 0.805
228
+ - F-score (macro) 0.704
229
+ - Accuracy 0.6957
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8842 0.8718 0.8779 858
235
+ pers 0.7330 0.8231 0.7754 537
236
+ org 0.6308 0.6212 0.6260 132
237
+ time 0.5075 0.6296 0.5620 54
238
+ prod 0.7451 0.6230 0.6786 61
239
+
240
+ micro avg 0.7920 0.8185 0.8050 1642
241
+ macro avg 0.7001 0.7137 0.7040 1642
242
+ weighted avg 0.7968 0.8185 0.8064 1642
243
+
244
+ 2023-10-13 19:01:00,089 ----------------------------------------------------------------------------------------------------