Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmbert-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
4516356
·
1 Parent(s): 779b1b5

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 +237 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d97d9f93199187702adf26d91ec284fc9859d78a49d0dedf9b0264d2192e74
3
+ size 443311111
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 23:37:13 0.0000 0.2577 0.1282 0.4884 0.7449 0.5899 0.4286
3
+ 2 23:40:18 0.0000 0.0981 0.1390 0.5768 0.7780 0.6624 0.5026
4
+ 3 23:43:10 0.0000 0.0713 0.1975 0.5367 0.7437 0.6235 0.4620
5
+ 4 23:46:02 0.0000 0.0517 0.2679 0.5365 0.7826 0.6366 0.4757
6
+ 5 23:48:53 0.0000 0.0388 0.2993 0.5241 0.7574 0.6196 0.4613
7
+ 6 23:51:44 0.0000 0.0275 0.3179 0.5574 0.7391 0.6355 0.4733
8
+ 7 23:54:36 0.0000 0.0171 0.3402 0.5398 0.7998 0.6445 0.4837
9
+ 8 23:57:26 0.0000 0.0118 0.3621 0.5495 0.7494 0.6341 0.4736
10
+ 9 00:00:17 0.0000 0.0088 0.3611 0.5674 0.7563 0.6484 0.4885
11
+ 10 00:03:10 0.0000 0.0051 0.4055 0.5597 0.7780 0.6510 0.4896
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-14 23:34:14,669 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-14 23:34:14,669 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=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-14 23:34:14,670 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-14 23:34:14,670 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
52
+ - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
53
+ 2023-10-14 23:34:14,670 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-14 23:34:14,670 Train: 14465 sentences
55
+ 2023-10-14 23:34:14,670 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-14 23:34:14,670 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-14 23:34:14,670 Training Params:
58
+ 2023-10-14 23:34:14,670 - learning_rate: "3e-05"
59
+ 2023-10-14 23:34:14,670 - mini_batch_size: "4"
60
+ 2023-10-14 23:34:14,670 - max_epochs: "10"
61
+ 2023-10-14 23:34:14,670 - shuffle: "True"
62
+ 2023-10-14 23:34:14,670 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-14 23:34:14,670 Plugins:
64
+ 2023-10-14 23:34:14,670 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-14 23:34:14,670 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-14 23:34:14,670 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-14 23:34:14,670 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-14 23:34:14,670 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-14 23:34:14,670 Computation:
70
+ 2023-10-14 23:34:14,670 - compute on device: cuda:0
71
+ 2023-10-14 23:34:14,670 - embedding storage: none
72
+ 2023-10-14 23:34:14,670 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-14 23:34:14,670 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
74
+ 2023-10-14 23:34:14,670 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-14 23:34:14,670 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-14 23:34:31,234 epoch 1 - iter 361/3617 - loss 1.36163379 - time (sec): 16.56 - samples/sec: 2286.03 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-14 23:34:47,495 epoch 1 - iter 722/3617 - loss 0.78535193 - time (sec): 32.82 - samples/sec: 2288.96 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-14 23:35:06,592 epoch 1 - iter 1083/3617 - loss 0.57914316 - time (sec): 51.92 - samples/sec: 2183.91 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-14 23:35:23,708 epoch 1 - iter 1444/3617 - loss 0.47133260 - time (sec): 69.04 - samples/sec: 2183.38 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-14 23:35:40,204 epoch 1 - iter 1805/3617 - loss 0.40334999 - time (sec): 85.53 - samples/sec: 2212.25 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-14 23:35:56,791 epoch 1 - iter 2166/3617 - loss 0.35690213 - time (sec): 102.12 - samples/sec: 2222.98 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-14 23:36:13,063 epoch 1 - iter 2527/3617 - loss 0.32256725 - time (sec): 118.39 - samples/sec: 2230.09 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-14 23:36:31,390 epoch 1 - iter 2888/3617 - loss 0.29552514 - time (sec): 136.72 - samples/sec: 2208.50 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-14 23:36:48,635 epoch 1 - iter 3249/3617 - loss 0.27457449 - time (sec): 153.96 - samples/sec: 2214.58 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-14 23:37:07,987 epoch 1 - iter 3610/3617 - loss 0.25799655 - time (sec): 173.32 - samples/sec: 2188.26 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-14 23:37:08,344 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-14 23:37:08,344 EPOCH 1 done: loss 0.2577 - lr: 0.000030
88
+ 2023-10-14 23:37:13,548 DEV : loss 0.1281796246767044 - f1-score (micro avg) 0.5899
89
+ 2023-10-14 23:37:13,589 saving best model
90
+ 2023-10-14 23:37:14,042 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-14 23:37:31,572 epoch 2 - iter 361/3617 - loss 0.10519861 - time (sec): 17.53 - samples/sec: 2217.47 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-14 23:37:50,569 epoch 2 - iter 722/3617 - loss 0.10049883 - time (sec): 36.53 - samples/sec: 2096.09 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-14 23:38:07,284 epoch 2 - iter 1083/3617 - loss 0.10110167 - time (sec): 53.24 - samples/sec: 2145.24 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-14 23:38:23,594 epoch 2 - iter 1444/3617 - loss 0.09863041 - time (sec): 69.55 - samples/sec: 2200.65 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-14 23:38:41,303 epoch 2 - iter 1805/3617 - loss 0.10015583 - time (sec): 87.26 - samples/sec: 2188.65 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-14 23:38:59,829 epoch 2 - iter 2166/3617 - loss 0.09892596 - time (sec): 105.79 - samples/sec: 2178.56 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-14 23:39:16,761 epoch 2 - iter 2527/3617 - loss 0.10000026 - time (sec): 122.72 - samples/sec: 2180.19 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-14 23:39:34,633 epoch 2 - iter 2888/3617 - loss 0.09831535 - time (sec): 140.59 - samples/sec: 2164.63 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-14 23:39:51,700 epoch 2 - iter 3249/3617 - loss 0.09854326 - time (sec): 157.66 - samples/sec: 2170.25 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-14 23:40:11,440 epoch 2 - iter 3610/3617 - loss 0.09811914 - time (sec): 177.40 - samples/sec: 2138.64 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-14 23:40:11,809 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-14 23:40:11,809 EPOCH 2 done: loss 0.0981 - lr: 0.000027
103
+ 2023-10-14 23:40:18,793 DEV : loss 0.1390405148267746 - f1-score (micro avg) 0.6624
104
+ 2023-10-14 23:40:18,825 saving best model
105
+ 2023-10-14 23:40:19,506 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-14 23:40:36,393 epoch 3 - iter 361/3617 - loss 0.06299067 - time (sec): 16.88 - samples/sec: 2243.14 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-14 23:40:52,924 epoch 3 - iter 722/3617 - loss 0.06908990 - time (sec): 33.42 - samples/sec: 2302.91 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-14 23:41:09,158 epoch 3 - iter 1083/3617 - loss 0.06892332 - time (sec): 49.65 - samples/sec: 2289.47 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-14 23:41:25,608 epoch 3 - iter 1444/3617 - loss 0.07129677 - time (sec): 66.10 - samples/sec: 2289.03 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-14 23:41:41,972 epoch 3 - iter 1805/3617 - loss 0.07081905 - time (sec): 82.46 - samples/sec: 2275.35 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-14 23:41:58,328 epoch 3 - iter 2166/3617 - loss 0.07078356 - time (sec): 98.82 - samples/sec: 2286.31 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-14 23:42:14,621 epoch 3 - iter 2527/3617 - loss 0.07071235 - time (sec): 115.11 - samples/sec: 2294.00 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-14 23:42:30,794 epoch 3 - iter 2888/3617 - loss 0.07182890 - time (sec): 131.28 - samples/sec: 2301.27 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-14 23:42:47,165 epoch 3 - iter 3249/3617 - loss 0.07170442 - time (sec): 147.66 - samples/sec: 2299.57 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-14 23:43:03,880 epoch 3 - iter 3610/3617 - loss 0.07109717 - time (sec): 164.37 - samples/sec: 2308.22 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-14 23:43:04,189 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-14 23:43:04,189 EPOCH 3 done: loss 0.0713 - lr: 0.000023
118
+ 2023-10-14 23:43:10,654 DEV : loss 0.19752231240272522 - f1-score (micro avg) 0.6235
119
+ 2023-10-14 23:43:10,698 ----------------------------------------------------------------------------------------------------
120
+ 2023-10-14 23:43:27,930 epoch 4 - iter 361/3617 - loss 0.04436168 - time (sec): 17.23 - samples/sec: 2202.46 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-14 23:43:44,435 epoch 4 - iter 722/3617 - loss 0.04585262 - time (sec): 33.73 - samples/sec: 2218.87 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-14 23:44:01,096 epoch 4 - iter 1083/3617 - loss 0.04921851 - time (sec): 50.40 - samples/sec: 2279.70 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-14 23:44:17,549 epoch 4 - iter 1444/3617 - loss 0.04934984 - time (sec): 66.85 - samples/sec: 2280.98 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-14 23:44:34,110 epoch 4 - iter 1805/3617 - loss 0.05175654 - time (sec): 83.41 - samples/sec: 2279.99 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-14 23:44:50,541 epoch 4 - iter 2166/3617 - loss 0.05020951 - time (sec): 99.84 - samples/sec: 2282.77 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-14 23:45:07,182 epoch 4 - iter 2527/3617 - loss 0.05084194 - time (sec): 116.48 - samples/sec: 2283.21 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-14 23:45:23,435 epoch 4 - iter 2888/3617 - loss 0.05193754 - time (sec): 132.74 - samples/sec: 2285.41 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-14 23:45:39,602 epoch 4 - iter 3249/3617 - loss 0.05165414 - time (sec): 148.90 - samples/sec: 2291.14 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-14 23:45:55,738 epoch 4 - iter 3610/3617 - loss 0.05169628 - time (sec): 165.04 - samples/sec: 2298.21 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-14 23:45:56,041 ----------------------------------------------------------------------------------------------------
131
+ 2023-10-14 23:45:56,041 EPOCH 4 done: loss 0.0517 - lr: 0.000020
132
+ 2023-10-14 23:46:02,662 DEV : loss 0.2679402828216553 - f1-score (micro avg) 0.6366
133
+ 2023-10-14 23:46:02,698 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-14 23:46:19,607 epoch 5 - iter 361/3617 - loss 0.04298391 - time (sec): 16.91 - samples/sec: 2203.83 - lr: 0.000020 - momentum: 0.000000
135
+ 2023-10-14 23:46:36,400 epoch 5 - iter 722/3617 - loss 0.03826667 - time (sec): 33.70 - samples/sec: 2257.95 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-14 23:46:52,804 epoch 5 - iter 1083/3617 - loss 0.03941655 - time (sec): 50.10 - samples/sec: 2289.34 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-14 23:47:09,226 epoch 5 - iter 1444/3617 - loss 0.03859460 - time (sec): 66.53 - samples/sec: 2288.55 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-14 23:47:25,683 epoch 5 - iter 1805/3617 - loss 0.03843288 - time (sec): 82.98 - samples/sec: 2296.59 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-14 23:47:41,999 epoch 5 - iter 2166/3617 - loss 0.03940779 - time (sec): 99.30 - samples/sec: 2306.54 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-14 23:47:58,428 epoch 5 - iter 2527/3617 - loss 0.03985879 - time (sec): 115.73 - samples/sec: 2320.92 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-14 23:48:14,698 epoch 5 - iter 2888/3617 - loss 0.03859164 - time (sec): 132.00 - samples/sec: 2318.43 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-14 23:48:31,109 epoch 5 - iter 3249/3617 - loss 0.03871626 - time (sec): 148.41 - samples/sec: 2309.97 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-14 23:48:47,292 epoch 5 - iter 3610/3617 - loss 0.03883470 - time (sec): 164.59 - samples/sec: 2304.32 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-14 23:48:47,598 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-14 23:48:47,598 EPOCH 5 done: loss 0.0388 - lr: 0.000017
146
+ 2023-10-14 23:48:53,945 DEV : loss 0.2992906868457794 - f1-score (micro avg) 0.6196
147
+ 2023-10-14 23:48:53,975 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-14 23:49:10,350 epoch 6 - iter 361/3617 - loss 0.02858051 - time (sec): 16.37 - samples/sec: 2293.30 - lr: 0.000016 - momentum: 0.000000
149
+ 2023-10-14 23:49:26,688 epoch 6 - iter 722/3617 - loss 0.03008292 - time (sec): 32.71 - samples/sec: 2325.10 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-14 23:49:43,019 epoch 6 - iter 1083/3617 - loss 0.03008366 - time (sec): 49.04 - samples/sec: 2324.89 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-14 23:49:59,394 epoch 6 - iter 1444/3617 - loss 0.02765207 - time (sec): 65.42 - samples/sec: 2337.01 - lr: 0.000015 - momentum: 0.000000
152
+ 2023-10-14 23:50:15,811 epoch 6 - iter 1805/3617 - loss 0.02577909 - time (sec): 81.83 - samples/sec: 2323.08 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-14 23:50:32,251 epoch 6 - iter 2166/3617 - loss 0.02580397 - time (sec): 98.27 - samples/sec: 2317.84 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-14 23:50:49,652 epoch 6 - iter 2527/3617 - loss 0.02703633 - time (sec): 115.67 - samples/sec: 2292.76 - lr: 0.000014 - momentum: 0.000000
155
+ 2023-10-14 23:51:05,959 epoch 6 - iter 2888/3617 - loss 0.02642517 - time (sec): 131.98 - samples/sec: 2295.62 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-14 23:51:22,251 epoch 6 - iter 3249/3617 - loss 0.02767332 - time (sec): 148.27 - samples/sec: 2302.85 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-14 23:51:38,863 epoch 6 - iter 3610/3617 - loss 0.02746834 - time (sec): 164.89 - samples/sec: 2299.21 - lr: 0.000013 - momentum: 0.000000
158
+ 2023-10-14 23:51:39,164 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-14 23:51:39,165 EPOCH 6 done: loss 0.0275 - lr: 0.000013
160
+ 2023-10-14 23:51:44,769 DEV : loss 0.31786689162254333 - f1-score (micro avg) 0.6355
161
+ 2023-10-14 23:51:44,815 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-14 23:52:01,511 epoch 7 - iter 361/3617 - loss 0.01641665 - time (sec): 16.69 - samples/sec: 2222.47 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-14 23:52:17,844 epoch 7 - iter 722/3617 - loss 0.01652455 - time (sec): 33.03 - samples/sec: 2229.06 - lr: 0.000013 - momentum: 0.000000
164
+ 2023-10-14 23:52:34,199 epoch 7 - iter 1083/3617 - loss 0.01691783 - time (sec): 49.38 - samples/sec: 2267.82 - lr: 0.000012 - momentum: 0.000000
165
+ 2023-10-14 23:52:50,534 epoch 7 - iter 1444/3617 - loss 0.01601712 - time (sec): 65.72 - samples/sec: 2269.87 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-14 23:53:06,889 epoch 7 - iter 1805/3617 - loss 0.01694897 - time (sec): 82.07 - samples/sec: 2282.71 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-14 23:53:22,796 epoch 7 - iter 2166/3617 - loss 0.01691405 - time (sec): 97.98 - samples/sec: 2303.14 - lr: 0.000011 - momentum: 0.000000
168
+ 2023-10-14 23:53:38,736 epoch 7 - iter 2527/3617 - loss 0.01667359 - time (sec): 113.92 - samples/sec: 2325.32 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-14 23:53:54,461 epoch 7 - iter 2888/3617 - loss 0.01633718 - time (sec): 129.64 - samples/sec: 2328.61 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-14 23:54:10,751 epoch 7 - iter 3249/3617 - loss 0.01689256 - time (sec): 145.93 - samples/sec: 2345.45 - lr: 0.000010 - momentum: 0.000000
171
+ 2023-10-14 23:54:29,301 epoch 7 - iter 3610/3617 - loss 0.01707300 - time (sec): 164.48 - samples/sec: 2306.07 - lr: 0.000010 - momentum: 0.000000
172
+ 2023-10-14 23:54:29,666 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-14 23:54:29,666 EPOCH 7 done: loss 0.0171 - lr: 0.000010
174
+ 2023-10-14 23:54:36,234 DEV : loss 0.34024110436439514 - f1-score (micro avg) 0.6445
175
+ 2023-10-14 23:54:36,268 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-14 23:54:52,959 epoch 8 - iter 361/3617 - loss 0.00929665 - time (sec): 16.69 - samples/sec: 2233.85 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-14 23:55:09,344 epoch 8 - iter 722/3617 - loss 0.01095348 - time (sec): 33.07 - samples/sec: 2289.01 - lr: 0.000009 - momentum: 0.000000
178
+ 2023-10-14 23:55:25,644 epoch 8 - iter 1083/3617 - loss 0.01097502 - time (sec): 49.37 - samples/sec: 2284.68 - lr: 0.000009 - momentum: 0.000000
179
+ 2023-10-14 23:55:41,915 epoch 8 - iter 1444/3617 - loss 0.01199052 - time (sec): 65.65 - samples/sec: 2316.06 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-14 23:55:58,052 epoch 8 - iter 1805/3617 - loss 0.01155861 - time (sec): 81.78 - samples/sec: 2310.35 - lr: 0.000008 - momentum: 0.000000
181
+ 2023-10-14 23:56:14,251 epoch 8 - iter 2166/3617 - loss 0.01161260 - time (sec): 97.98 - samples/sec: 2313.58 - lr: 0.000008 - momentum: 0.000000
182
+ 2023-10-14 23:56:30,608 epoch 8 - iter 2527/3617 - loss 0.01230179 - time (sec): 114.34 - samples/sec: 2311.46 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-14 23:56:46,856 epoch 8 - iter 2888/3617 - loss 0.01231660 - time (sec): 130.59 - samples/sec: 2321.23 - lr: 0.000007 - momentum: 0.000000
184
+ 2023-10-14 23:57:03,177 epoch 8 - iter 3249/3617 - loss 0.01206507 - time (sec): 146.91 - samples/sec: 2320.26 - lr: 0.000007 - momentum: 0.000000
185
+ 2023-10-14 23:57:19,556 epoch 8 - iter 3610/3617 - loss 0.01178827 - time (sec): 163.29 - samples/sec: 2321.42 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-14 23:57:19,879 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-14 23:57:19,879 EPOCH 8 done: loss 0.0118 - lr: 0.000007
188
+ 2023-10-14 23:57:26,350 DEV : loss 0.36208638548851013 - f1-score (micro avg) 0.6341
189
+ 2023-10-14 23:57:26,383 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-14 23:57:42,883 epoch 9 - iter 361/3617 - loss 0.01142158 - time (sec): 16.50 - samples/sec: 2295.97 - lr: 0.000006 - momentum: 0.000000
191
+ 2023-10-14 23:57:59,357 epoch 9 - iter 722/3617 - loss 0.00738770 - time (sec): 32.97 - samples/sec: 2315.11 - lr: 0.000006 - momentum: 0.000000
192
+ 2023-10-14 23:58:15,686 epoch 9 - iter 1083/3617 - loss 0.00754335 - time (sec): 49.30 - samples/sec: 2318.80 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-14 23:58:31,888 epoch 9 - iter 1444/3617 - loss 0.00919711 - time (sec): 65.50 - samples/sec: 2311.16 - lr: 0.000005 - momentum: 0.000000
194
+ 2023-10-14 23:58:48,291 epoch 9 - iter 1805/3617 - loss 0.00809847 - time (sec): 81.91 - samples/sec: 2319.40 - lr: 0.000005 - momentum: 0.000000
195
+ 2023-10-14 23:59:04,676 epoch 9 - iter 2166/3617 - loss 0.00725574 - time (sec): 98.29 - samples/sec: 2317.26 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-14 23:59:20,803 epoch 9 - iter 2527/3617 - loss 0.00767874 - time (sec): 114.42 - samples/sec: 2317.79 - lr: 0.000004 - momentum: 0.000000
197
+ 2023-10-14 23:59:37,053 epoch 9 - iter 2888/3617 - loss 0.00829904 - time (sec): 130.67 - samples/sec: 2325.30 - lr: 0.000004 - momentum: 0.000000
198
+ 2023-10-14 23:59:53,365 epoch 9 - iter 3249/3617 - loss 0.00828150 - time (sec): 146.98 - samples/sec: 2324.96 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-15 00:00:09,734 epoch 9 - iter 3610/3617 - loss 0.00879170 - time (sec): 163.35 - samples/sec: 2322.22 - lr: 0.000003 - momentum: 0.000000
200
+ 2023-10-15 00:00:10,042 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-15 00:00:10,042 EPOCH 9 done: loss 0.0088 - lr: 0.000003
202
+ 2023-10-15 00:00:17,518 DEV : loss 0.36112189292907715 - f1-score (micro avg) 0.6484
203
+ 2023-10-15 00:00:17,562 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-15 00:00:34,052 epoch 10 - iter 361/3617 - loss 0.00393861 - time (sec): 16.49 - samples/sec: 2343.48 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-15 00:00:50,531 epoch 10 - iter 722/3617 - loss 0.00545373 - time (sec): 32.97 - samples/sec: 2330.96 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-15 00:01:06,889 epoch 10 - iter 1083/3617 - loss 0.00589789 - time (sec): 49.32 - samples/sec: 2303.79 - lr: 0.000002 - momentum: 0.000000
207
+ 2023-10-15 00:01:23,187 epoch 10 - iter 1444/3617 - loss 0.00530915 - time (sec): 65.62 - samples/sec: 2326.78 - lr: 0.000002 - momentum: 0.000000
208
+ 2023-10-15 00:01:39,466 epoch 10 - iter 1805/3617 - loss 0.00552918 - time (sec): 81.90 - samples/sec: 2319.90 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-15 00:01:55,596 epoch 10 - iter 2166/3617 - loss 0.00498351 - time (sec): 98.03 - samples/sec: 2313.78 - lr: 0.000001 - momentum: 0.000000
210
+ 2023-10-15 00:02:13,164 epoch 10 - iter 2527/3617 - loss 0.00454256 - time (sec): 115.60 - samples/sec: 2302.96 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-15 00:02:29,564 epoch 10 - iter 2888/3617 - loss 0.00484062 - time (sec): 132.00 - samples/sec: 2304.49 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-15 00:02:45,783 epoch 10 - iter 3249/3617 - loss 0.00485285 - time (sec): 148.22 - samples/sec: 2305.05 - lr: 0.000000 - momentum: 0.000000
213
+ 2023-10-15 00:03:02,013 epoch 10 - iter 3610/3617 - loss 0.00507728 - time (sec): 164.45 - samples/sec: 2304.88 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-15 00:03:02,337 ----------------------------------------------------------------------------------------------------
215
+ 2023-10-15 00:03:02,338 EPOCH 10 done: loss 0.0051 - lr: 0.000000
216
+ 2023-10-15 00:03:09,963 DEV : loss 0.4055171608924866 - f1-score (micro avg) 0.651
217
+ 2023-10-15 00:03:10,499 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-15 00:03:10,500 Loading model from best epoch ...
219
+ 2023-10-15 00:03:12,088 SequenceTagger predicts: Dictionary with 13 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
220
+ 2023-10-15 00:03:19,342
221
+ Results:
222
+ - F-score (micro) 0.6471
223
+ - F-score (macro) 0.4397
224
+ - Accuracy 0.4897
225
+
226
+ By class:
227
+ precision recall f1-score support
228
+
229
+ loc 0.6222 0.8054 0.7021 591
230
+ pers 0.5701 0.6723 0.6170 357
231
+ org 0.0000 0.0000 0.0000 79
232
+
233
+ micro avg 0.6037 0.6972 0.6471 1027
234
+ macro avg 0.3974 0.4926 0.4397 1027
235
+ weighted avg 0.5562 0.6972 0.6185 1027
236
+
237
+ 2023-10-15 00:03:19,342 ----------------------------------------------------------------------------------------------------