Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmbert-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
4f489cf
·
1 Parent(s): 2c56046

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 +240 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98e3566c061469064318a328ee06d3c5e7c333d0d169fe28d5bff1fa7ce57faf
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 22:27:10 0.0000 0.2345 0.1205 0.5254 0.7460 0.6165 0.4534
3
+ 2 22:30:04 0.0000 0.1055 0.1263 0.5254 0.7918 0.6317 0.4701
4
+ 3 22:32:55 0.0000 0.0842 0.2099 0.5124 0.7346 0.6037 0.4458
5
+ 4 22:35:44 0.0000 0.0612 0.1987 0.5397 0.6453 0.5878 0.4234
6
+ 5 22:38:32 0.0000 0.0444 0.3178 0.5195 0.7929 0.6277 0.4686
7
+ 6 22:41:21 0.0000 0.0292 0.3371 0.5590 0.6991 0.6213 0.4587
8
+ 7 22:44:11 0.0000 0.0212 0.3617 0.5407 0.7746 0.6369 0.4771
9
+ 8 22:47:00 0.0000 0.0147 0.3475 0.5608 0.7437 0.6394 0.4815
10
+ 9 22:49:49 0.0000 0.0088 0.3727 0.5695 0.7357 0.6420 0.4824
11
+ 10 22:52:39 0.0000 0.0056 0.3892 0.5534 0.7586 0.6400 0.4808
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-14 22:24:23,665 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-14 22:24:23,681 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 22:24:23,681 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-14 22:24:23,681 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 22:24:23,681 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-14 22:24:23,681 Train: 14465 sentences
55
+ 2023-10-14 22:24:23,681 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-14 22:24:23,681 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-14 22:24:23,681 Training Params:
58
+ 2023-10-14 22:24:23,682 - learning_rate: "5e-05"
59
+ 2023-10-14 22:24:23,682 - mini_batch_size: "4"
60
+ 2023-10-14 22:24:23,682 - max_epochs: "10"
61
+ 2023-10-14 22:24:23,682 - shuffle: "True"
62
+ 2023-10-14 22:24:23,682 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-14 22:24:23,682 Plugins:
64
+ 2023-10-14 22:24:23,682 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-14 22:24:23,682 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-14 22:24:23,682 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-14 22:24:23,682 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-14 22:24:23,682 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-14 22:24:23,682 Computation:
70
+ 2023-10-14 22:24:23,682 - compute on device: cuda:0
71
+ 2023-10-14 22:24:23,682 - embedding storage: none
72
+ 2023-10-14 22:24:23,682 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-14 22:24:23,682 Model training base path: "hmbench-letemps/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
74
+ 2023-10-14 22:24:23,682 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-14 22:24:23,682 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-14 22:24:39,984 epoch 1 - iter 361/3617 - loss 1.14411237 - time (sec): 16.30 - samples/sec: 2350.48 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-14 22:24:56,212 epoch 1 - iter 722/3617 - loss 0.67514192 - time (sec): 32.53 - samples/sec: 2339.73 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-14 22:25:12,297 epoch 1 - iter 1083/3617 - loss 0.50390301 - time (sec): 48.61 - samples/sec: 2328.13 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-14 22:25:28,530 epoch 1 - iter 1444/3617 - loss 0.40601014 - time (sec): 64.85 - samples/sec: 2353.71 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-14 22:25:44,722 epoch 1 - iter 1805/3617 - loss 0.34943623 - time (sec): 81.04 - samples/sec: 2350.57 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-14 22:26:01,008 epoch 1 - iter 2166/3617 - loss 0.31161011 - time (sec): 97.33 - samples/sec: 2361.85 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-14 22:26:17,105 epoch 1 - iter 2527/3617 - loss 0.28529419 - time (sec): 113.42 - samples/sec: 2354.24 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-14 22:26:33,313 epoch 1 - iter 2888/3617 - loss 0.26433511 - time (sec): 129.63 - samples/sec: 2349.50 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-14 22:26:49,604 epoch 1 - iter 3249/3617 - loss 0.24745537 - time (sec): 145.92 - samples/sec: 2345.15 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-14 22:27:05,658 epoch 1 - iter 3610/3617 - loss 0.23480737 - time (sec): 161.98 - samples/sec: 2341.11 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-14 22:27:05,978 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-14 22:27:05,979 EPOCH 1 done: loss 0.2345 - lr: 0.000050
88
+ 2023-10-14 22:27:10,539 DEV : loss 0.1204783022403717 - f1-score (micro avg) 0.6165
89
+ 2023-10-14 22:27:10,568 saving best model
90
+ 2023-10-14 22:27:11,666 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-14 22:27:27,870 epoch 2 - iter 361/3617 - loss 0.10944507 - time (sec): 16.20 - samples/sec: 2293.52 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-14 22:27:44,134 epoch 2 - iter 722/3617 - loss 0.11087767 - time (sec): 32.47 - samples/sec: 2324.72 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-14 22:28:00,333 epoch 2 - iter 1083/3617 - loss 0.10916242 - time (sec): 48.67 - samples/sec: 2340.48 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-14 22:28:16,951 epoch 2 - iter 1444/3617 - loss 0.10841737 - time (sec): 65.28 - samples/sec: 2342.27 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-14 22:28:33,376 epoch 2 - iter 1805/3617 - loss 0.10539028 - time (sec): 81.71 - samples/sec: 2348.58 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-14 22:28:49,734 epoch 2 - iter 2166/3617 - loss 0.10557440 - time (sec): 98.07 - samples/sec: 2340.97 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-14 22:29:06,485 epoch 2 - iter 2527/3617 - loss 0.10690549 - time (sec): 114.82 - samples/sec: 2324.15 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-14 22:29:23,693 epoch 2 - iter 2888/3617 - loss 0.10699756 - time (sec): 132.03 - samples/sec: 2293.87 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-14 22:29:40,741 epoch 2 - iter 3249/3617 - loss 0.10562800 - time (sec): 149.07 - samples/sec: 2292.12 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-14 22:29:58,572 epoch 2 - iter 3610/3617 - loss 0.10569211 - time (sec): 166.90 - samples/sec: 2272.40 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-14 22:29:58,905 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-14 22:29:58,906 EPOCH 2 done: loss 0.1055 - lr: 0.000044
103
+ 2023-10-14 22:30:04,590 DEV : loss 0.12628547847270966 - f1-score (micro avg) 0.6317
104
+ 2023-10-14 22:30:04,620 saving best model
105
+ 2023-10-14 22:30:05,095 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-14 22:30:22,157 epoch 3 - iter 361/3617 - loss 0.07241240 - time (sec): 17.06 - samples/sec: 2276.69 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-14 22:30:38,462 epoch 3 - iter 722/3617 - loss 0.08210114 - time (sec): 33.36 - samples/sec: 2296.47 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-14 22:30:54,856 epoch 3 - iter 1083/3617 - loss 0.08593425 - time (sec): 49.76 - samples/sec: 2290.48 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-14 22:31:11,133 epoch 3 - iter 1444/3617 - loss 0.08548915 - time (sec): 66.03 - samples/sec: 2313.74 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-14 22:31:27,541 epoch 3 - iter 1805/3617 - loss 0.08461469 - time (sec): 82.44 - samples/sec: 2306.26 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-14 22:31:43,628 epoch 3 - iter 2166/3617 - loss 0.08635041 - time (sec): 98.53 - samples/sec: 2312.85 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-14 22:31:59,971 epoch 3 - iter 2527/3617 - loss 0.08485842 - time (sec): 114.87 - samples/sec: 2312.01 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-14 22:32:16,971 epoch 3 - iter 2888/3617 - loss 0.08549985 - time (sec): 131.87 - samples/sec: 2296.93 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-14 22:32:33,296 epoch 3 - iter 3249/3617 - loss 0.08663415 - time (sec): 148.20 - samples/sec: 2303.61 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-14 22:32:49,490 epoch 3 - iter 3610/3617 - loss 0.08429051 - time (sec): 164.39 - samples/sec: 2306.91 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-14 22:32:49,802 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-14 22:32:49,802 EPOCH 3 done: loss 0.0842 - lr: 0.000039
118
+ 2023-10-14 22:32:55,446 DEV : loss 0.20989196002483368 - f1-score (micro avg) 0.6037
119
+ 2023-10-14 22:32:55,479 ----------------------------------------------------------------------------------------------------
120
+ 2023-10-14 22:33:12,003 epoch 4 - iter 361/3617 - loss 0.05375131 - time (sec): 16.52 - samples/sec: 2361.28 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-14 22:33:28,293 epoch 4 - iter 722/3617 - loss 0.05179870 - time (sec): 32.81 - samples/sec: 2333.17 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-14 22:33:44,488 epoch 4 - iter 1083/3617 - loss 0.05834655 - time (sec): 49.01 - samples/sec: 2341.86 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-14 22:34:00,581 epoch 4 - iter 1444/3617 - loss 0.06136827 - time (sec): 65.10 - samples/sec: 2328.16 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-14 22:34:16,773 epoch 4 - iter 1805/3617 - loss 0.06036277 - time (sec): 81.29 - samples/sec: 2325.90 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-14 22:34:33,269 epoch 4 - iter 2166/3617 - loss 0.05903167 - time (sec): 97.79 - samples/sec: 2325.15 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-14 22:34:49,619 epoch 4 - iter 2527/3617 - loss 0.06019423 - time (sec): 114.14 - samples/sec: 2326.09 - lr: 0.000035 - momentum: 0.000000
127
+ 2023-10-14 22:35:05,919 epoch 4 - iter 2888/3617 - loss 0.05917379 - time (sec): 130.44 - samples/sec: 2332.20 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-14 22:35:22,008 epoch 4 - iter 3249/3617 - loss 0.05967316 - time (sec): 146.53 - samples/sec: 2331.84 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-14 22:35:38,187 epoch 4 - iter 3610/3617 - loss 0.06116373 - time (sec): 162.71 - samples/sec: 2330.41 - lr: 0.000033 - momentum: 0.000000
130
+ 2023-10-14 22:35:38,504 ----------------------------------------------------------------------------------------------------
131
+ 2023-10-14 22:35:38,504 EPOCH 4 done: loss 0.0612 - lr: 0.000033
132
+ 2023-10-14 22:35:44,746 DEV : loss 0.1986590474843979 - f1-score (micro avg) 0.5878
133
+ 2023-10-14 22:35:44,778 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-14 22:36:01,076 epoch 5 - iter 361/3617 - loss 0.03740724 - time (sec): 16.30 - samples/sec: 2319.97 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-14 22:36:17,138 epoch 5 - iter 722/3617 - loss 0.03966765 - time (sec): 32.36 - samples/sec: 2346.52 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-14 22:36:33,336 epoch 5 - iter 1083/3617 - loss 0.03821815 - time (sec): 48.56 - samples/sec: 2340.28 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-14 22:36:49,708 epoch 5 - iter 1444/3617 - loss 0.04031259 - time (sec): 64.93 - samples/sec: 2319.12 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-14 22:37:05,485 epoch 5 - iter 1805/3617 - loss 0.04174152 - time (sec): 80.71 - samples/sec: 2332.59 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-14 22:37:21,125 epoch 5 - iter 2166/3617 - loss 0.04297498 - time (sec): 96.35 - samples/sec: 2339.87 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-14 22:37:36,708 epoch 5 - iter 2527/3617 - loss 0.04258961 - time (sec): 111.93 - samples/sec: 2344.68 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-14 22:37:52,583 epoch 5 - iter 2888/3617 - loss 0.04372580 - time (sec): 127.80 - samples/sec: 2364.58 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-14 22:38:08,775 epoch 5 - iter 3249/3617 - loss 0.04359994 - time (sec): 144.00 - samples/sec: 2365.75 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-14 22:38:25,264 epoch 5 - iter 3610/3617 - loss 0.04442056 - time (sec): 160.48 - samples/sec: 2364.36 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-14 22:38:25,575 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-14 22:38:25,575 EPOCH 5 done: loss 0.0444 - lr: 0.000028
146
+ 2023-10-14 22:38:31,994 DEV : loss 0.3178099989891052 - f1-score (micro avg) 0.6277
147
+ 2023-10-14 22:38:32,026 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-14 22:38:48,231 epoch 6 - iter 361/3617 - loss 0.03001037 - time (sec): 16.20 - samples/sec: 2221.52 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-14 22:39:04,620 epoch 6 - iter 722/3617 - loss 0.02850755 - time (sec): 32.59 - samples/sec: 2281.75 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-14 22:39:20,750 epoch 6 - iter 1083/3617 - loss 0.02922986 - time (sec): 48.72 - samples/sec: 2284.28 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-14 22:39:36,936 epoch 6 - iter 1444/3617 - loss 0.02915910 - time (sec): 64.91 - samples/sec: 2298.63 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-14 22:39:53,230 epoch 6 - iter 1805/3617 - loss 0.02933413 - time (sec): 81.20 - samples/sec: 2314.09 - lr: 0.000025 - momentum: 0.000000
153
+ 2023-10-14 22:40:09,709 epoch 6 - iter 2166/3617 - loss 0.03005081 - time (sec): 97.68 - samples/sec: 2315.74 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-14 22:40:26,048 epoch 6 - iter 2527/3617 - loss 0.02966232 - time (sec): 114.02 - samples/sec: 2326.67 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-14 22:40:42,383 epoch 6 - iter 2888/3617 - loss 0.02981839 - time (sec): 130.36 - samples/sec: 2339.47 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-14 22:40:58,524 epoch 6 - iter 3249/3617 - loss 0.02973966 - time (sec): 146.50 - samples/sec: 2330.85 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-14 22:41:14,900 epoch 6 - iter 3610/3617 - loss 0.02923805 - time (sec): 162.87 - samples/sec: 2328.46 - lr: 0.000022 - momentum: 0.000000
158
+ 2023-10-14 22:41:15,224 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-14 22:41:15,224 EPOCH 6 done: loss 0.0292 - lr: 0.000022
160
+ 2023-10-14 22:41:21,572 DEV : loss 0.33707916736602783 - f1-score (micro avg) 0.6213
161
+ 2023-10-14 22:41:21,602 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-14 22:41:37,794 epoch 7 - iter 361/3617 - loss 0.01859802 - time (sec): 16.19 - samples/sec: 2300.51 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-14 22:41:54,033 epoch 7 - iter 722/3617 - loss 0.01903138 - time (sec): 32.43 - samples/sec: 2362.56 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-14 22:42:10,288 epoch 7 - iter 1083/3617 - loss 0.01865096 - time (sec): 48.68 - samples/sec: 2382.51 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-14 22:42:26,441 epoch 7 - iter 1444/3617 - loss 0.02002715 - time (sec): 64.84 - samples/sec: 2354.60 - lr: 0.000020 - momentum: 0.000000
166
+ 2023-10-14 22:42:42,763 epoch 7 - iter 1805/3617 - loss 0.02137933 - time (sec): 81.16 - samples/sec: 2346.99 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-14 22:42:59,040 epoch 7 - iter 2166/3617 - loss 0.02148678 - time (sec): 97.44 - samples/sec: 2344.17 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-14 22:43:15,412 epoch 7 - iter 2527/3617 - loss 0.02120220 - time (sec): 113.81 - samples/sec: 2350.02 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-14 22:43:31,984 epoch 7 - iter 2888/3617 - loss 0.02087245 - time (sec): 130.38 - samples/sec: 2325.28 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-14 22:43:48,572 epoch 7 - iter 3249/3617 - loss 0.02107711 - time (sec): 146.97 - samples/sec: 2323.76 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-14 22:44:04,971 epoch 7 - iter 3610/3617 - loss 0.02122186 - time (sec): 163.37 - samples/sec: 2320.88 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-14 22:44:05,290 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-14 22:44:05,290 EPOCH 7 done: loss 0.0212 - lr: 0.000017
174
+ 2023-10-14 22:44:11,627 DEV : loss 0.361693799495697 - f1-score (micro avg) 0.6369
175
+ 2023-10-14 22:44:11,657 saving best model
176
+ 2023-10-14 22:44:12,152 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-14 22:44:27,823 epoch 8 - iter 361/3617 - loss 0.01351269 - time (sec): 15.67 - samples/sec: 2353.69 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-14 22:44:43,592 epoch 8 - iter 722/3617 - loss 0.01225598 - time (sec): 31.44 - samples/sec: 2406.07 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-14 22:44:59,904 epoch 8 - iter 1083/3617 - loss 0.01341753 - time (sec): 47.75 - samples/sec: 2381.72 - lr: 0.000015 - momentum: 0.000000
180
+ 2023-10-14 22:45:16,276 epoch 8 - iter 1444/3617 - loss 0.01425253 - time (sec): 64.12 - samples/sec: 2362.31 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-14 22:45:32,508 epoch 8 - iter 1805/3617 - loss 0.01310324 - time (sec): 80.35 - samples/sec: 2346.05 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-14 22:45:48,816 epoch 8 - iter 2166/3617 - loss 0.01431964 - time (sec): 96.66 - samples/sec: 2349.41 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-14 22:46:05,005 epoch 8 - iter 2527/3617 - loss 0.01396577 - time (sec): 112.85 - samples/sec: 2355.77 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-14 22:46:21,476 epoch 8 - iter 2888/3617 - loss 0.01450336 - time (sec): 129.32 - samples/sec: 2344.06 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-14 22:46:37,782 epoch 8 - iter 3249/3617 - loss 0.01434939 - time (sec): 145.63 - samples/sec: 2338.44 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-14 22:46:54,197 epoch 8 - iter 3610/3617 - loss 0.01473032 - time (sec): 162.04 - samples/sec: 2341.62 - lr: 0.000011 - momentum: 0.000000
187
+ 2023-10-14 22:46:54,511 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-14 22:46:54,511 EPOCH 8 done: loss 0.0147 - lr: 0.000011
189
+ 2023-10-14 22:47:00,034 DEV : loss 0.34752506017684937 - f1-score (micro avg) 0.6394
190
+ 2023-10-14 22:47:00,064 saving best model
191
+ 2023-10-14 22:47:00,550 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-14 22:47:17,022 epoch 9 - iter 361/3617 - loss 0.00749889 - time (sec): 16.47 - samples/sec: 2321.67 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-14 22:47:34,147 epoch 9 - iter 722/3617 - loss 0.00782066 - time (sec): 33.59 - samples/sec: 2255.80 - lr: 0.000010 - momentum: 0.000000
194
+ 2023-10-14 22:47:50,414 epoch 9 - iter 1083/3617 - loss 0.00872382 - time (sec): 49.86 - samples/sec: 2277.97 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-14 22:48:06,823 epoch 9 - iter 1444/3617 - loss 0.00879945 - time (sec): 66.27 - samples/sec: 2300.11 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-14 22:48:23,139 epoch 9 - iter 1805/3617 - loss 0.00900892 - time (sec): 82.58 - samples/sec: 2307.07 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-14 22:48:39,443 epoch 9 - iter 2166/3617 - loss 0.00903195 - time (sec): 98.89 - samples/sec: 2324.67 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-14 22:48:55,699 epoch 9 - iter 2527/3617 - loss 0.00896221 - time (sec): 115.14 - samples/sec: 2324.22 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-14 22:49:11,720 epoch 9 - iter 2888/3617 - loss 0.00879283 - time (sec): 131.16 - samples/sec: 2321.25 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-14 22:49:27,516 epoch 9 - iter 3249/3617 - loss 0.00879301 - time (sec): 146.96 - samples/sec: 2330.96 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-14 22:49:43,105 epoch 9 - iter 3610/3617 - loss 0.00879727 - time (sec): 162.55 - samples/sec: 2333.30 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-14 22:49:43,399 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-14 22:49:43,399 EPOCH 9 done: loss 0.0088 - lr: 0.000006
204
+ 2023-10-14 22:49:49,027 DEV : loss 0.3727048337459564 - f1-score (micro avg) 0.642
205
+ 2023-10-14 22:49:49,058 saving best model
206
+ 2023-10-14 22:49:49,702 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-14 22:50:06,227 epoch 10 - iter 361/3617 - loss 0.00310624 - time (sec): 16.52 - samples/sec: 2310.74 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-14 22:50:22,502 epoch 10 - iter 722/3617 - loss 0.00451557 - time (sec): 32.80 - samples/sec: 2328.34 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-14 22:50:38,889 epoch 10 - iter 1083/3617 - loss 0.00444647 - time (sec): 49.19 - samples/sec: 2309.90 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-14 22:50:55,390 epoch 10 - iter 1444/3617 - loss 0.00463820 - time (sec): 65.69 - samples/sec: 2314.50 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-14 22:51:11,711 epoch 10 - iter 1805/3617 - loss 0.00515326 - time (sec): 82.01 - samples/sec: 2320.49 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-14 22:51:28,115 epoch 10 - iter 2166/3617 - loss 0.00547593 - time (sec): 98.41 - samples/sec: 2315.27 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-14 22:51:44,415 epoch 10 - iter 2527/3617 - loss 0.00531709 - time (sec): 114.71 - samples/sec: 2314.93 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-14 22:52:00,847 epoch 10 - iter 2888/3617 - loss 0.00530082 - time (sec): 131.14 - samples/sec: 2319.13 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-14 22:52:16,770 epoch 10 - iter 3249/3617 - loss 0.00559223 - time (sec): 147.07 - samples/sec: 2311.01 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-14 22:52:33,249 epoch 10 - iter 3610/3617 - loss 0.00561927 - time (sec): 163.55 - samples/sec: 2320.26 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-14 22:52:33,559 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-14 22:52:33,559 EPOCH 10 done: loss 0.0056 - lr: 0.000000
219
+ 2023-10-14 22:52:39,953 DEV : loss 0.3892402648925781 - f1-score (micro avg) 0.64
220
+ 2023-10-14 22:52:40,542 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-14 22:52:40,543 Loading model from best epoch ...
222
+ 2023-10-14 22:52:42,344 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
223
+ 2023-10-14 22:52:50,738
224
+ Results:
225
+ - F-score (micro) 0.6467
226
+ - F-score (macro) 0.4935
227
+ - Accuracy 0.4931
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ loc 0.6436 0.7394 0.6882 591
233
+ pers 0.5801 0.7507 0.6545 357
234
+ org 0.2162 0.1013 0.1379 79
235
+
236
+ micro avg 0.6053 0.6943 0.6467 1027
237
+ macro avg 0.4800 0.5305 0.4935 1027
238
+ weighted avg 0.5886 0.6943 0.6341 1027
239
+
240
+ 2023-10-14 22:52:50,738 ----------------------------------------------------------------------------------------------------