Hugging Face's logo

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

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
7d699c3
•
1 Parent(s): 2968d4a

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 sha256:67fb319cb7c46561087c07532d494314fde08a13150ed856742e01bba05dc786
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 15:57:37 0.0000 0.6654 0.1447 0.6774 0.7686 0.7202 0.5871
3
+ 2 15:58:38 0.0000 0.1294 0.1106 0.7354 0.8024 0.7675 0.6504
4
+ 3 15:59:40 0.0000 0.0738 0.1086 0.8338 0.8018 0.8175 0.7136
5
+ 4 16:00:42 0.0000 0.0490 0.1475 0.7538 0.8242 0.7874 0.6852
6
+ 5 16:01:43 0.0000 0.0359 0.1524 0.7919 0.8368 0.8137 0.7106
7
+ 6 16:02:44 0.0000 0.0272 0.1725 0.8042 0.8373 0.8204 0.7216
8
+ 7 16:03:47 0.0000 0.0190 0.2041 0.7946 0.8373 0.8154 0.7135
9
+ 8 16:04:50 0.0000 0.0158 0.1915 0.8097 0.8431 0.8260 0.7287
10
+ 9 16:05:51 0.0000 0.0117 0.1948 0.8148 0.8391 0.8267 0.7289
11
+ 10 16:06:54 0.0000 0.0083 0.1960 0.8150 0.8402 0.8274 0.7299
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 15:56:41,973 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 15:56:41,974 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 15:56:41,975 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 15:56:41,975 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 15:56:41,975 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 15:56:41,975 Train: 5901 sentences
55
+ 2023-10-13 15:56:41,975 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 15:56:41,975 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 15:56:41,975 Training Params:
58
+ 2023-10-13 15:56:41,975 - learning_rate: "3e-05"
59
+ 2023-10-13 15:56:41,975 - mini_batch_size: "8"
60
+ 2023-10-13 15:56:41,975 - max_epochs: "10"
61
+ 2023-10-13 15:56:41,975 - shuffle: "True"
62
+ 2023-10-13 15:56:41,975 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 15:56:41,975 Plugins:
64
+ 2023-10-13 15:56:41,975 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 15:56:41,975 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 15:56:41,975 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 15:56:41,975 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 15:56:41,975 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 15:56:41,975 Computation:
70
+ 2023-10-13 15:56:41,975 - compute on device: cuda:0
71
+ 2023-10-13 15:56:41,975 - embedding storage: none
72
+ 2023-10-13 15:56:41,975 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 15:56:41,975 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
74
+ 2023-10-13 15:56:41,975 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 15:56:41,975 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 15:56:47,173 epoch 1 - iter 73/738 - loss 3.05853360 - time (sec): 5.20 - samples/sec: 3385.89 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 15:56:52,161 epoch 1 - iter 146/738 - loss 2.01396427 - time (sec): 10.18 - samples/sec: 3514.39 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 15:56:56,988 epoch 1 - iter 219/738 - loss 1.53824384 - time (sec): 15.01 - samples/sec: 3444.77 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 15:57:01,882 epoch 1 - iter 292/738 - loss 1.24891774 - time (sec): 19.91 - samples/sec: 3432.48 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 15:57:06,840 epoch 1 - iter 365/738 - loss 1.07452913 - time (sec): 24.86 - samples/sec: 3418.88 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 15:57:11,658 epoch 1 - iter 438/738 - loss 0.94521822 - time (sec): 29.68 - samples/sec: 3426.34 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 15:57:16,509 epoch 1 - iter 511/738 - loss 0.85158135 - time (sec): 34.53 - samples/sec: 3412.22 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 15:57:20,999 epoch 1 - iter 584/738 - loss 0.78332215 - time (sec): 39.02 - samples/sec: 3392.42 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 15:57:25,830 epoch 1 - iter 657/738 - loss 0.72187463 - time (sec): 43.85 - samples/sec: 3388.05 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 15:57:30,631 epoch 1 - iter 730/738 - loss 0.66940959 - time (sec): 48.65 - samples/sec: 3389.93 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 15:57:31,100 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 15:57:31,100 EPOCH 1 done: loss 0.6654 - lr: 0.000030
88
+ 2023-10-13 15:57:37,172 DEV : loss 0.14468906819820404 - f1-score (micro avg) 0.7202
89
+ 2023-10-13 15:57:37,201 saving best model
90
+ 2023-10-13 15:57:37,657 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 15:57:41,990 epoch 2 - iter 73/738 - loss 0.14759708 - time (sec): 4.33 - samples/sec: 3490.78 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 15:57:46,742 epoch 2 - iter 146/738 - loss 0.14672610 - time (sec): 9.08 - samples/sec: 3447.45 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 15:57:51,446 epoch 2 - iter 219/738 - loss 0.14523852 - time (sec): 13.79 - samples/sec: 3442.51 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 15:57:56,392 epoch 2 - iter 292/738 - loss 0.14107499 - time (sec): 18.73 - samples/sec: 3369.54 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 15:58:01,243 epoch 2 - iter 365/738 - loss 0.14216356 - time (sec): 23.58 - samples/sec: 3333.33 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 15:58:06,232 epoch 2 - iter 438/738 - loss 0.13781464 - time (sec): 28.57 - samples/sec: 3340.70 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 15:58:11,636 epoch 2 - iter 511/738 - loss 0.13577481 - time (sec): 33.98 - samples/sec: 3350.22 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 15:58:16,471 epoch 2 - iter 584/738 - loss 0.13005589 - time (sec): 38.81 - samples/sec: 3352.85 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 15:58:21,461 epoch 2 - iter 657/738 - loss 0.12956762 - time (sec): 43.80 - samples/sec: 3362.65 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 15:58:26,771 epoch 2 - iter 730/738 - loss 0.12951791 - time (sec): 49.11 - samples/sec: 3353.97 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 15:58:27,274 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 15:58:27,274 EPOCH 2 done: loss 0.1294 - lr: 0.000027
103
+ 2023-10-13 15:58:38,435 DEV : loss 0.11062650382518768 - f1-score (micro avg) 0.7675
104
+ 2023-10-13 15:58:38,464 saving best model
105
+ 2023-10-13 15:58:39,090 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 15:58:43,863 epoch 3 - iter 73/738 - loss 0.06065277 - time (sec): 4.77 - samples/sec: 3236.91 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 15:58:48,700 epoch 3 - iter 146/738 - loss 0.07316894 - time (sec): 9.61 - samples/sec: 3338.82 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 15:58:54,048 epoch 3 - iter 219/738 - loss 0.07863303 - time (sec): 14.95 - samples/sec: 3233.00 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 15:58:58,383 epoch 3 - iter 292/738 - loss 0.07743735 - time (sec): 19.29 - samples/sec: 3281.31 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 15:59:03,909 epoch 3 - iter 365/738 - loss 0.07606154 - time (sec): 24.81 - samples/sec: 3262.96 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 15:59:09,129 epoch 3 - iter 438/738 - loss 0.07463572 - time (sec): 30.03 - samples/sec: 3309.18 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 15:59:13,987 epoch 3 - iter 511/738 - loss 0.07177934 - time (sec): 34.89 - samples/sec: 3306.95 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 15:59:18,942 epoch 3 - iter 584/738 - loss 0.07324880 - time (sec): 39.85 - samples/sec: 3320.00 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 15:59:24,146 epoch 3 - iter 657/738 - loss 0.07181062 - time (sec): 45.05 - samples/sec: 3315.65 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 15:59:28,957 epoch 3 - iter 730/738 - loss 0.07338875 - time (sec): 49.86 - samples/sec: 3305.07 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 15:59:29,439 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 15:59:29,439 EPOCH 3 done: loss 0.0738 - lr: 0.000023
118
+ 2023-10-13 15:59:40,672 DEV : loss 0.10864270478487015 - f1-score (micro avg) 0.8175
119
+ 2023-10-13 15:59:40,703 saving best model
120
+ 2023-10-13 15:59:41,239 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 15:59:46,028 epoch 4 - iter 73/738 - loss 0.04491633 - time (sec): 4.79 - samples/sec: 3162.59 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 15:59:50,685 epoch 4 - iter 146/738 - loss 0.04351311 - time (sec): 9.44 - samples/sec: 3264.79 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 15:59:55,499 epoch 4 - iter 219/738 - loss 0.04436716 - time (sec): 14.26 - samples/sec: 3321.07 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 16:00:00,085 epoch 4 - iter 292/738 - loss 0.04559344 - time (sec): 18.84 - samples/sec: 3331.80 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 16:00:05,124 epoch 4 - iter 365/738 - loss 0.04601732 - time (sec): 23.88 - samples/sec: 3329.15 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 16:00:10,439 epoch 4 - iter 438/738 - loss 0.04450045 - time (sec): 29.20 - samples/sec: 3316.64 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 16:00:16,073 epoch 4 - iter 511/738 - loss 0.04465368 - time (sec): 34.83 - samples/sec: 3316.58 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 16:00:20,833 epoch 4 - iter 584/738 - loss 0.04598766 - time (sec): 39.59 - samples/sec: 3332.91 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 16:00:25,931 epoch 4 - iter 657/738 - loss 0.05017371 - time (sec): 44.69 - samples/sec: 3328.90 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 16:00:30,598 epoch 4 - iter 730/738 - loss 0.04880929 - time (sec): 49.36 - samples/sec: 3338.99 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 16:00:31,086 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 16:00:31,086 EPOCH 4 done: loss 0.0490 - lr: 0.000020
133
+ 2023-10-13 16:00:42,240 DEV : loss 0.1474699079990387 - f1-score (micro avg) 0.7874
134
+ 2023-10-13 16:00:42,273 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-13 16:00:47,244 epoch 5 - iter 73/738 - loss 0.04483958 - time (sec): 4.97 - samples/sec: 3309.95 - lr: 0.000020 - momentum: 0.000000
136
+ 2023-10-13 16:00:52,261 epoch 5 - iter 146/738 - loss 0.03940692 - time (sec): 9.99 - samples/sec: 3306.44 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-13 16:00:57,081 epoch 5 - iter 219/738 - loss 0.03823729 - time (sec): 14.81 - samples/sec: 3372.73 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 16:01:01,852 epoch 5 - iter 292/738 - loss 0.03570809 - time (sec): 19.58 - samples/sec: 3372.43 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 16:01:06,660 epoch 5 - iter 365/738 - loss 0.03611074 - time (sec): 24.39 - samples/sec: 3366.09 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-13 16:01:11,422 epoch 5 - iter 438/738 - loss 0.03549566 - time (sec): 29.15 - samples/sec: 3345.91 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 16:01:16,434 epoch 5 - iter 511/738 - loss 0.03481242 - time (sec): 34.16 - samples/sec: 3329.04 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 16:01:21,988 epoch 5 - iter 584/738 - loss 0.03612795 - time (sec): 39.71 - samples/sec: 3312.86 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-13 16:01:27,611 epoch 5 - iter 657/738 - loss 0.03541289 - time (sec): 45.34 - samples/sec: 3304.32 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 16:01:32,079 epoch 5 - iter 730/738 - loss 0.03603975 - time (sec): 49.80 - samples/sec: 3305.92 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 16:01:32,629 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-13 16:01:32,630 EPOCH 5 done: loss 0.0359 - lr: 0.000017
147
+ 2023-10-13 16:01:43,734 DEV : loss 0.15243035554885864 - f1-score (micro avg) 0.8137
148
+ 2023-10-13 16:01:43,764 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-13 16:01:48,291 epoch 6 - iter 73/738 - loss 0.02753601 - time (sec): 4.53 - samples/sec: 3278.39 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-13 16:01:53,834 epoch 6 - iter 146/738 - loss 0.02412278 - time (sec): 10.07 - samples/sec: 3370.68 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-13 16:01:58,832 epoch 6 - iter 219/738 - loss 0.02730955 - time (sec): 15.07 - samples/sec: 3372.32 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 16:02:03,512 epoch 6 - iter 292/738 - loss 0.02914052 - time (sec): 19.75 - samples/sec: 3355.51 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-13 16:02:08,994 epoch 6 - iter 365/738 - loss 0.02963576 - time (sec): 25.23 - samples/sec: 3347.08 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-13 16:02:13,940 epoch 6 - iter 438/738 - loss 0.03069200 - time (sec): 30.18 - samples/sec: 3357.87 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 16:02:18,409 epoch 6 - iter 511/738 - loss 0.02902534 - time (sec): 34.64 - samples/sec: 3367.48 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-13 16:02:23,343 epoch 6 - iter 584/738 - loss 0.02744013 - time (sec): 39.58 - samples/sec: 3365.62 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-13 16:02:28,153 epoch 6 - iter 657/738 - loss 0.02726539 - time (sec): 44.39 - samples/sec: 3353.62 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 16:02:33,016 epoch 6 - iter 730/738 - loss 0.02719915 - time (sec): 49.25 - samples/sec: 3346.24 - lr: 0.000013 - momentum: 0.000000
159
+ 2023-10-13 16:02:33,486 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-13 16:02:33,487 EPOCH 6 done: loss 0.0272 - lr: 0.000013
161
+ 2023-10-13 16:02:44,645 DEV : loss 0.17250441014766693 - f1-score (micro avg) 0.8204
162
+ 2023-10-13 16:02:44,676 saving best model
163
+ 2023-10-13 16:02:45,316 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-13 16:02:50,958 epoch 7 - iter 73/738 - loss 0.01634149 - time (sec): 5.64 - samples/sec: 3018.98 - lr: 0.000013 - momentum: 0.000000
165
+ 2023-10-13 16:02:55,302 epoch 7 - iter 146/738 - loss 0.01514888 - time (sec): 9.98 - samples/sec: 3189.06 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-13 16:03:00,715 epoch 7 - iter 219/738 - loss 0.01838780 - time (sec): 15.40 - samples/sec: 3270.41 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-13 16:03:06,168 epoch 7 - iter 292/738 - loss 0.01756859 - time (sec): 20.85 - samples/sec: 3303.19 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-13 16:03:10,622 epoch 7 - iter 365/738 - loss 0.01866420 - time (sec): 25.30 - samples/sec: 3307.34 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 16:03:15,201 epoch 7 - iter 438/738 - loss 0.01851098 - time (sec): 29.88 - samples/sec: 3315.07 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-13 16:03:19,804 epoch 7 - iter 511/738 - loss 0.01926756 - time (sec): 34.48 - samples/sec: 3336.22 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-13 16:03:24,445 epoch 7 - iter 584/738 - loss 0.01977881 - time (sec): 39.13 - samples/sec: 3335.09 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 16:03:29,619 epoch 7 - iter 657/738 - loss 0.01907489 - time (sec): 44.30 - samples/sec: 3305.95 - lr: 0.000010 - momentum: 0.000000
173
+ 2023-10-13 16:03:35,450 epoch 7 - iter 730/738 - loss 0.01894560 - time (sec): 50.13 - samples/sec: 3288.28 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-13 16:03:35,947 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-13 16:03:35,948 EPOCH 7 done: loss 0.0190 - lr: 0.000010
176
+ 2023-10-13 16:03:47,105 DEV : loss 0.20412878692150116 - f1-score (micro avg) 0.8154
177
+ 2023-10-13 16:03:47,134 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-13 16:03:52,161 epoch 8 - iter 73/738 - loss 0.01344325 - time (sec): 5.03 - samples/sec: 3320.25 - lr: 0.000010 - momentum: 0.000000
179
+ 2023-10-13 16:03:57,698 epoch 8 - iter 146/738 - loss 0.01748030 - time (sec): 10.56 - samples/sec: 3185.06 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-13 16:04:04,280 epoch 8 - iter 219/738 - loss 0.01866343 - time (sec): 17.14 - samples/sec: 3081.13 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-13 16:04:09,445 epoch 8 - iter 292/738 - loss 0.01990917 - time (sec): 22.31 - samples/sec: 3033.63 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 16:04:14,015 epoch 8 - iter 365/738 - loss 0.01831245 - time (sec): 26.88 - samples/sec: 3065.14 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-13 16:04:18,968 epoch 8 - iter 438/738 - loss 0.01923268 - time (sec): 31.83 - samples/sec: 3095.99 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-13 16:04:23,888 epoch 8 - iter 511/738 - loss 0.01795623 - time (sec): 36.75 - samples/sec: 3121.73 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 16:04:28,303 epoch 8 - iter 584/738 - loss 0.01764510 - time (sec): 41.17 - samples/sec: 3142.12 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-13 16:04:33,109 epoch 8 - iter 657/738 - loss 0.01668878 - time (sec): 45.97 - samples/sec: 3159.38 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-13 16:04:38,749 epoch 8 - iter 730/738 - loss 0.01600711 - time (sec): 51.61 - samples/sec: 3191.33 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 16:04:39,252 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-13 16:04:39,252 EPOCH 8 done: loss 0.0158 - lr: 0.000007
190
+ 2023-10-13 16:04:50,416 DEV : loss 0.19149629771709442 - f1-score (micro avg) 0.826
191
+ 2023-10-13 16:04:50,445 saving best model
192
+ 2023-10-13 16:04:50,981 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-13 16:04:55,805 epoch 9 - iter 73/738 - loss 0.00698935 - time (sec): 4.82 - samples/sec: 3214.71 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-13 16:05:00,887 epoch 9 - iter 146/738 - loss 0.00952456 - time (sec): 9.91 - samples/sec: 3262.85 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-13 16:05:05,508 epoch 9 - iter 219/738 - loss 0.00949156 - time (sec): 14.53 - samples/sec: 3325.48 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 16:05:10,381 epoch 9 - iter 292/738 - loss 0.01022930 - time (sec): 19.40 - samples/sec: 3341.20 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-13 16:05:15,595 epoch 9 - iter 365/738 - loss 0.01120093 - time (sec): 24.61 - samples/sec: 3363.39 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-13 16:05:20,184 epoch 9 - iter 438/738 - loss 0.01043318 - time (sec): 29.20 - samples/sec: 3365.10 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 16:05:25,342 epoch 9 - iter 511/738 - loss 0.01017895 - time (sec): 34.36 - samples/sec: 3352.34 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-13 16:05:29,969 epoch 9 - iter 584/738 - loss 0.01017742 - time (sec): 38.99 - samples/sec: 3339.96 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-13 16:05:34,734 epoch 9 - iter 657/738 - loss 0.00985239 - time (sec): 43.75 - samples/sec: 3352.03 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 16:05:40,086 epoch 9 - iter 730/738 - loss 0.01123444 - time (sec): 49.10 - samples/sec: 3352.47 - lr: 0.000003 - momentum: 0.000000
203
+ 2023-10-13 16:05:40,697 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-13 16:05:40,698 EPOCH 9 done: loss 0.0117 - lr: 0.000003
205
+ 2023-10-13 16:05:51,786 DEV : loss 0.19480924308300018 - f1-score (micro avg) 0.8267
206
+ 2023-10-13 16:05:51,816 saving best model
207
+ 2023-10-13 16:05:52,417 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-13 16:05:57,660 epoch 10 - iter 73/738 - loss 0.01186703 - time (sec): 5.24 - samples/sec: 3361.08 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-13 16:06:02,305 epoch 10 - iter 146/738 - loss 0.00836274 - time (sec): 9.89 - samples/sec: 3390.77 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-13 16:06:06,585 epoch 10 - iter 219/738 - loss 0.01000260 - time (sec): 14.17 - samples/sec: 3456.57 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-13 16:06:11,468 epoch 10 - iter 292/738 - loss 0.00903905 - time (sec): 19.05 - samples/sec: 3427.99 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 16:06:16,389 epoch 10 - iter 365/738 - loss 0.00871698 - time (sec): 23.97 - samples/sec: 3393.43 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 16:06:21,868 epoch 10 - iter 438/738 - loss 0.00896638 - time (sec): 29.45 - samples/sec: 3398.02 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-13 16:06:26,485 epoch 10 - iter 511/738 - loss 0.00840529 - time (sec): 34.07 - samples/sec: 3368.60 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 16:06:32,017 epoch 10 - iter 584/738 - loss 0.00852755 - time (sec): 39.60 - samples/sec: 3327.66 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 16:06:37,311 epoch 10 - iter 657/738 - loss 0.00884580 - time (sec): 44.89 - samples/sec: 3302.90 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-13 16:06:42,635 epoch 10 - iter 730/738 - loss 0.00832851 - time (sec): 50.22 - samples/sec: 3284.25 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-13 16:06:43,054 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-13 16:06:43,054 EPOCH 10 done: loss 0.0083 - lr: 0.000000
220
+ 2023-10-13 16:06:54,526 DEV : loss 0.19598710536956787 - f1-score (micro avg) 0.8274
221
+ 2023-10-13 16:06:54,557 saving best model
222
+ 2023-10-13 16:06:55,518 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-13 16:06:55,520 Loading model from best epoch ...
224
+ 2023-10-13 16:06:57,087 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 16:07:03,859
226
+ Results:
227
+ - F-score (micro) 0.7929
228
+ - F-score (macro) 0.6926
229
+ - Accuracy 0.6785
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8673 0.8683 0.8678 858
235
+ pers 0.7402 0.8119 0.7744 537
236
+ org 0.5067 0.5758 0.5390 132
237
+ prod 0.6885 0.6885 0.6885 61
238
+ time 0.5469 0.6481 0.5932 54
239
+
240
+ micro avg 0.7742 0.8124 0.7929 1642
241
+ macro avg 0.6699 0.7185 0.6926 1642
242
+ weighted avg 0.7796 0.8124 0.7951 1642
243
+
244
+ 2023-10-13 16:07:03,859 ----------------------------------------------------------------------------------------------------